Merge tag 'xfs-for-linus-4.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/dgc/linux-xfs

Pull xfs updates from Dave Chinner:
 "There's quite a lot in this request, and there's some cross-over with
  ext4, dax and quota code due to the nature of the changes being made.

  As for the rest of the XFS changes, there are lots of little things
  all over the place, which add up to a lot of changes in the end.

  The major changes are that we've reduced the size of the struct
  xfs_inode by ~100 bytes (gives an inode cache footprint reduction of
  >10%), the writepage code now only does a single set of mapping tree
  lockups so uses less CPU, delayed allocation reservations won't
  overrun under random write loads anymore, and we added compile time
  verification for on-disk structure sizes so we find out when a commit
  or platform/compiler change breaks the on disk structure as early as
  possible.

  Change summary:

   - error propagation for direct IO failures fixes for both XFS and
     ext4
   - new quota interfaces and XFS implementation for iterating all the
     quota IDs in the filesystem
   - locking fixes for real-time device extent allocation
   - reduction of duplicate information in the xfs and vfs inode, saving
     roughly 100 bytes of memory per cached inode.
   - buffer flag cleanup
   - rework of the writepage code to use the generic write clustering
     mechanisms
   - several fixes for inode flag based DAX enablement
   - rework of remount option parsing
   - compile time verification of on-disk format structure sizes
   - delayed allocation reservation overrun fixes
   - lots of little error handling fixes
   - small memory leak fixes
   - enable xfsaild freezing again"

* tag 'xfs-for-linus-4.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/dgc/linux-xfs: (66 commits)
  xfs: always set rvalp in xfs_dir2_node_trim_free
  xfs: ensure committed is initialized in xfs_trans_roll
  xfs: borrow indirect blocks from freed extent when available
  xfs: refactor delalloc indlen reservation split into helper
  xfs: update freeblocks counter after extent deletion
  xfs: debug mode forced buffered write failure
  xfs: remove impossible condition
  xfs: check sizes of XFS on-disk structures at compile time
  xfs: ioends require logically contiguous file offsets
  xfs: use named array initializers for log item dumping
  xfs: fix computation of inode btree maxlevels
  xfs: reinitialise per-AG structures if geometry changes during recovery
  xfs: remove xfs_trans_get_block_res
  xfs: fix up inode32/64 (re)mount handling
  xfs: fix format specifier , should be %llx and not %llu
  xfs: sanitize remount options
  xfs: convert mount option parsing to tokens
  xfs: fix two memory leaks in xfs_attr_list.c error paths
  xfs: XFS_DIFLAG2_DAX limited by PAGE_SIZE
  xfs: dynamically switch modes when XFS_DIFLAG2_DAX is set/cleared
  ...

1 files changed, 37 insertions, 6 deletions

diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index d7a490f..bf2d607 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -63,6 +63,9 @@ xfs_inode_alloc(
 		return NULL;
 	}
 
+	/* VFS doesn't initialise i_mode! */
+	VFS_I(ip)->i_mode = 0;
+
 	XFS_STATS_INC(mp, vn_active);
 	ASSERT(atomic_read(&ip->i_pincount) == 0);
 	ASSERT(!spin_is_locked(&ip->i_flags_lock));
@@ -79,7 +82,7 @@ xfs_inode_alloc(
 	memset(&ip->i_df, 0, sizeof(xfs_ifork_t));
 	ip->i_flags = 0;
 	ip->i_delayed_blks = 0;
-	memset(&ip->i_d, 0, sizeof(xfs_icdinode_t));
+	memset(&ip->i_d, 0, sizeof(ip->i_d));
 
 	return ip;
 }
@@ -98,7 +101,7 @@ void
 xfs_inode_free(
 	struct xfs_inode	*ip)
 {
-	switch (ip->i_d.di_mode & S_IFMT) {
+	switch (VFS_I(ip)->i_mode & S_IFMT) {
 	case S_IFREG:
 	case S_IFDIR:
 	case S_IFLNK:
@@ -135,6 +138,34 @@ xfs_inode_free(
 }
 
 /*
+ * When we recycle a reclaimable inode, we need to re-initialise the VFS inode
+ * part of the structure. This is made more complex by the fact we store
+ * information about the on-disk values in the VFS inode and so we can't just
+ * overwrite the values unconditionally. Hence we save the parameters we
+ * need to retain across reinitialisation, and rewrite them into the VFS inode
+ * after reinitialisation even if it fails.
+ */
+static int
+xfs_reinit_inode(
+	struct xfs_mount	*mp,
+	struct inode		*inode)
+{
+	int		error;
+	uint32_t	nlink = inode->i_nlink;
+	uint32_t	generation = inode->i_generation;
+	uint64_t	version = inode->i_version;
+	umode_t		mode = inode->i_mode;
+
+	error = inode_init_always(mp->m_super, inode);
+
+	set_nlink(inode, nlink);
+	inode->i_generation = generation;
+	inode->i_version = version;
+	inode->i_mode = mode;
+	return error;
+}
+
+/*
  * Check the validity of the inode we just found it the cache
  */
 static int
@@ -185,7 +216,7 @@ xfs_iget_cache_hit(
 	/*
 	 * If lookup is racing with unlink return an error immediately.
 	 */
-	if (ip->i_d.di_mode == 0 && !(flags & XFS_IGET_CREATE)) {
+	if (VFS_I(ip)->i_mode == 0 && !(flags & XFS_IGET_CREATE)) {
 		error = -ENOENT;
 		goto out_error;
 	}
@@ -208,7 +239,7 @@ xfs_iget_cache_hit(
 		spin_unlock(&ip->i_flags_lock);
 		rcu_read_unlock();
 
-		error = inode_init_always(mp->m_super, inode);
+		error = xfs_reinit_inode(mp, inode);
 		if (error) {
 			/*
 			 * Re-initializing the inode failed, and we are in deep
@@ -295,7 +326,7 @@ xfs_iget_cache_miss(
 
 	trace_xfs_iget_miss(ip);
 
-	if ((ip->i_d.di_mode == 0) && !(flags & XFS_IGET_CREATE)) {
+	if ((VFS_I(ip)->i_mode == 0) && !(flags & XFS_IGET_CREATE)) {
 		error = -ENOENT;
 		goto out_destroy;
 	}
@@ -444,7 +475,7 @@ again:
 	 * If we have a real type for an on-disk inode, we can setup the inode
 	 * now.	 If it's a new inode being created, xfs_ialloc will handle it.
 	 */
-	if (xfs_iflags_test(ip, XFS_INEW) && ip->i_d.di_mode != 0)
+	if (xfs_iflags_test(ip, XFS_INEW) && VFS_I(ip)->i_mode != 0)
 		xfs_setup_existing_inode(ip);
 	return 0;