Powerpc KVM work is based on a commit after rc4.

Merging master into next to satisfy the dependencies.

Conflicts:
	arch/arm/kvm/reset.c

10 files changed, 113 insertions, 64 deletions

diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 88c5ea75ebf..f1d85cfc0a5 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -628,6 +628,7 @@ xfs_buf_item_unlock(
 		else if (aborted) {
 			ASSERT(XFS_FORCED_SHUTDOWN(lip->li_mountp));
 			if (lip->li_flags & XFS_LI_IN_AIL) {
+				spin_lock(&lip->li_ailp->xa_lock);
 				xfs_trans_ail_delete(lip->li_ailp, lip,
 						     SHUTDOWN_LOG_IO_ERROR);
 			}
diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c
index 069537c845e..20bf8e8002d 100644
--- a/fs/xfs/xfs_da_btree.c
+++ b/fs/xfs/xfs_da_btree.c
@@ -1224,6 +1224,7 @@ xfs_da3_node_toosmall(
 	/* start with smaller blk num */
 	forward = nodehdr.forw < nodehdr.back;
 	for (i = 0; i < 2; forward = !forward, i++) {
+		struct xfs_da3_icnode_hdr thdr;
 		if (forward)
 			blkno = nodehdr.forw;
 		else
@@ -1236,10 +1237,10 @@ xfs_da3_node_toosmall(
 			return(error);
 
 		node = bp->b_addr;
-		xfs_da3_node_hdr_from_disk(&nodehdr, node);
+		xfs_da3_node_hdr_from_disk(&thdr, node);
 		xfs_trans_brelse(state->args->trans, bp);
 
-		if (count - nodehdr.count >= 0)
+		if (count - thdr.count >= 0)
 			break;	/* fits with at least 25% to spare */
 	}
 	if (i >= 2) {
diff --git a/fs/xfs/xfs_dir2_block.c b/fs/xfs/xfs_dir2_block.c
index 0957aa98b6c..12dad188939 100644
--- a/fs/xfs/xfs_dir2_block.c
+++ b/fs/xfs/xfs_dir2_block.c
@@ -1158,7 +1158,7 @@ xfs_dir2_sf_to_block(
 	/*
 	 * Create entry for .
 	 */
-	dep = xfs_dir3_data_dot_entry_p(hdr);
+	dep = xfs_dir3_data_dot_entry_p(mp, hdr);
 	dep->inumber = cpu_to_be64(dp->i_ino);
 	dep->namelen = 1;
 	dep->name[0] = '.';
@@ -1172,7 +1172,7 @@ xfs_dir2_sf_to_block(
 	/*
 	 * Create entry for ..
 	 */
-	dep = xfs_dir3_data_dotdot_entry_p(hdr);
+	dep = xfs_dir3_data_dotdot_entry_p(mp, hdr);
 	dep->inumber = cpu_to_be64(xfs_dir2_sf_get_parent_ino(sfp));
 	dep->namelen = 2;
 	dep->name[0] = dep->name[1] = '.';
@@ -1183,7 +1183,7 @@ xfs_dir2_sf_to_block(
 	blp[1].hashval = cpu_to_be32(xfs_dir_hash_dotdot);
 	blp[1].address = cpu_to_be32(xfs_dir2_byte_to_dataptr(mp,
 				(char *)dep - (char *)hdr));
-	offset = xfs_dir3_data_first_offset(hdr);
+	offset = xfs_dir3_data_first_offset(mp);
 	/*
 	 * Loop over existing entries, stuff them in.
 	 */
diff --git a/fs/xfs/xfs_dir2_format.h b/fs/xfs/xfs_dir2_format.h
index a0961a61ac1..9cf67381adf 100644
--- a/fs/xfs/xfs_dir2_format.h
+++ b/fs/xfs/xfs_dir2_format.h
@@ -497,69 +497,58 @@ xfs_dir3_data_unused_p(struct xfs_dir2_data_hdr *hdr)
 /*
  * Offsets of . and .. in data space (always block 0)
  *
- * The macros are used for shortform directories as they have no headers to read
- * the magic number out of. Shortform directories need to know the size of the
- * data block header because the sfe embeds the block offset of the entry into
- * it so that it doesn't change when format conversion occurs. Bad Things Happen
- * if we don't follow this rule.
- *
  * XXX: there is scope for significant optimisation of the logic here. Right
  * now we are checking for "dir3 format" over and over again. Ideally we should
  * only do it once for each operation.
  */
-#define	XFS_DIR3_DATA_DOT_OFFSET(mp)	\
-	xfs_dir3_data_hdr_size(xfs_sb_version_hascrc(&(mp)->m_sb))
-#define	XFS_DIR3_DATA_DOTDOT_OFFSET(mp)	\
-	(XFS_DIR3_DATA_DOT_OFFSET(mp) + xfs_dir3_data_entsize(mp, 1))
-#define	XFS_DIR3_DATA_FIRST_OFFSET(mp)		\
-	(XFS_DIR3_DATA_DOTDOT_OFFSET(mp) + xfs_dir3_data_entsize(mp, 2))
-
 static inline xfs_dir2_data_aoff_t
-xfs_dir3_data_dot_offset(struct xfs_dir2_data_hdr *hdr)
+xfs_dir3_data_dot_offset(struct xfs_mount *mp)
 {
-	return xfs_dir3_data_entry_offset(hdr);
+	return xfs_dir3_data_hdr_size(xfs_sb_version_hascrc(&mp->m_sb));
 }
 
 static inline xfs_dir2_data_aoff_t
-xfs_dir3_data_dotdot_offset(struct xfs_dir2_data_hdr *hdr)
+xfs_dir3_data_dotdot_offset(struct xfs_mount *mp)
 {
-	bool dir3 = hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
-		    hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC);
-	return xfs_dir3_data_dot_offset(hdr) +
-		__xfs_dir3_data_entsize(dir3, 1);
+	return xfs_dir3_data_dot_offset(mp) +
+		xfs_dir3_data_entsize(mp, 1);
 }
 
 static inline xfs_dir2_data_aoff_t
-xfs_dir3_data_first_offset(struct xfs_dir2_data_hdr *hdr)
+xfs_dir3_data_first_offset(struct xfs_mount *mp)
 {
-	bool dir3 = hdr->magic == cpu_to_be32(XFS_DIR3_DATA_MAGIC) ||
-		    hdr->magic == cpu_to_be32(XFS_DIR3_BLOCK_MAGIC);
-	return xfs_dir3_data_dotdot_offset(hdr) +
-		__xfs_dir3_data_entsize(dir3, 2);
+	return xfs_dir3_data_dotdot_offset(mp) +
+		xfs_dir3_data_entsize(mp, 2);
 }
 
 /*
  * location of . and .. in data space (always block 0)
  */
 static inline struct xfs_dir2_data_entry *
-xfs_dir3_data_dot_entry_p(struct xfs_dir2_data_hdr *hdr)
+xfs_dir3_data_dot_entry_p(
+	struct xfs_mount	*mp,
+	struct xfs_dir2_data_hdr *hdr)
 {
 	return (struct xfs_dir2_data_entry *)
-		((char *)hdr + xfs_dir3_data_dot_offset(hdr));
+		((char *)hdr + xfs_dir3_data_dot_offset(mp));
 }
 
 static inline struct xfs_dir2_data_entry *
-xfs_dir3_data_dotdot_entry_p(struct xfs_dir2_data_hdr *hdr)
+xfs_dir3_data_dotdot_entry_p(
+	struct xfs_mount	*mp,
+	struct xfs_dir2_data_hdr *hdr)
 {
 	return (struct xfs_dir2_data_entry *)
-		((char *)hdr + xfs_dir3_data_dotdot_offset(hdr));
+		((char *)hdr + xfs_dir3_data_dotdot_offset(mp));
 }
 
 static inline struct xfs_dir2_data_entry *
-xfs_dir3_data_first_entry_p(struct xfs_dir2_data_hdr *hdr)
+xfs_dir3_data_first_entry_p(
+	struct xfs_mount	*mp,
+	struct xfs_dir2_data_hdr *hdr)
 {
 	return (struct xfs_dir2_data_entry *)
-		((char *)hdr + xfs_dir3_data_first_offset(hdr));
+		((char *)hdr + xfs_dir3_data_first_offset(mp));
 }
 
 /*
diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c
index 8993ec17452..8f84153e98a 100644
--- a/fs/xfs/xfs_dir2_readdir.c
+++ b/fs/xfs/xfs_dir2_readdir.c
@@ -119,9 +119,9 @@ xfs_dir2_sf_getdents(
 	 * mp->m_dirdatablk.
 	 */
 	dot_offset = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk,
-					     XFS_DIR3_DATA_DOT_OFFSET(mp));
+					     xfs_dir3_data_dot_offset(mp));
 	dotdot_offset = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk,
-						XFS_DIR3_DATA_DOTDOT_OFFSET(mp));
+						xfs_dir3_data_dotdot_offset(mp));
 
 	/*
 	 * Put . entry unless we're starting past it.
diff --git a/fs/xfs/xfs_dir2_sf.c b/fs/xfs/xfs_dir2_sf.c
index bb6e2848f47..3ef6d402084 100644
--- a/fs/xfs/xfs_dir2_sf.c
+++ b/fs/xfs/xfs_dir2_sf.c
@@ -557,7 +557,7 @@ xfs_dir2_sf_addname_hard(
 	 * to insert the new entry.
 	 * If it's going to end up at the end then oldsfep will point there.
 	 */
-	for (offset = XFS_DIR3_DATA_FIRST_OFFSET(mp),
+	for (offset = xfs_dir3_data_first_offset(mp),
 	      oldsfep = xfs_dir2_sf_firstentry(oldsfp),
 	      add_datasize = xfs_dir3_data_entsize(mp, args->namelen),
 	      eof = (char *)oldsfep == &buf[old_isize];
@@ -640,7 +640,7 @@ xfs_dir2_sf_addname_pick(
 
 	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
 	size = xfs_dir3_data_entsize(mp, args->namelen);
-	offset = XFS_DIR3_DATA_FIRST_OFFSET(mp);
+	offset = xfs_dir3_data_first_offset(mp);
 	sfep = xfs_dir2_sf_firstentry(sfp);
 	holefit = 0;
 	/*
@@ -713,7 +713,7 @@ xfs_dir2_sf_check(
 	mp = dp->i_mount;
 
 	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
-	offset = XFS_DIR3_DATA_FIRST_OFFSET(mp);
+	offset = xfs_dir3_data_first_offset(mp);
 	ino = xfs_dir2_sf_get_parent_ino(sfp);
 	i8count = ino > XFS_DIR2_MAX_SHORT_INUM;
 
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 71520e6e5d6..1ee776d477c 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -64,7 +64,8 @@ int xfs_dqerror_mod = 33;
 struct kmem_zone		*xfs_qm_dqtrxzone;
 static struct kmem_zone		*xfs_qm_dqzone;
 
-static struct lock_class_key xfs_dquot_other_class;
+static struct lock_class_key xfs_dquot_group_class;
+static struct lock_class_key xfs_dquot_project_class;
 
 /*
  * This is called to free all the memory associated with a dquot
@@ -703,8 +704,20 @@ xfs_qm_dqread(
 	 * Make sure group quotas have a different lock class than user
 	 * quotas.
 	 */
-	if (!(type & XFS_DQ_USER))
-		lockdep_set_class(&dqp->q_qlock, &xfs_dquot_other_class);
+	switch (type) {
+	case XFS_DQ_USER:
+		/* uses the default lock class */
+		break;
+	case XFS_DQ_GROUP:
+		lockdep_set_class(&dqp->q_qlock, &xfs_dquot_group_class);
+		break;
+	case XFS_DQ_PROJ:
+		lockdep_set_class(&dqp->q_qlock, &xfs_dquot_project_class);
+		break;
+	default:
+		ASSERT(0);
+		break;
+	}
 
 	XFS_STATS_INC(xs_qm_dquot);
 
diff --git a/fs/xfs/xfs_fs.h b/fs/xfs/xfs_fs.h
index 1edb5cc3e5f..18272c766a5 100644
--- a/fs/xfs/xfs_fs.h
+++ b/fs/xfs/xfs_fs.h
@@ -515,7 +515,7 @@ typedef struct xfs_swapext
 /*	XFS_IOC_GETBIOSIZE ---- deprecated 47	   */
 #define XFS_IOC_GETBMAPX	_IOWR('X', 56, struct getbmap)
 #define XFS_IOC_ZERO_RANGE	_IOW ('X', 57, struct xfs_flock64)
-#define XFS_IOC_FREE_EOFBLOCKS	_IOR ('X', 58, struct xfs_eofblocks)
+#define XFS_IOC_FREE_EOFBLOCKS	_IOR ('X', 58, struct xfs_fs_eofblocks)
 
 /*
  * ioctl commands that replace IRIX syssgi()'s
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 193206ba435..474807a401c 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -119,11 +119,6 @@ xfs_inode_free(
 		ip->i_itemp = NULL;
 	}
 
-	/* asserts to verify all state is correct here */
-	ASSERT(atomic_read(&ip->i_pincount) == 0);
-	ASSERT(!spin_is_locked(&ip->i_flags_lock));
-	ASSERT(!xfs_isiflocked(ip));
-
 	/*
 	 * Because we use RCU freeing we need to ensure the inode always
 	 * appears to be reclaimed with an invalid inode number when in the
@@ -135,6 +130,10 @@ xfs_inode_free(
 	ip->i_ino = 0;
 	spin_unlock(&ip->i_flags_lock);
 
+	/* asserts to verify all state is correct here */
+	ASSERT(atomic_read(&ip->i_pincount) == 0);
+	ASSERT(!xfs_isiflocked(ip));
+
 	call_rcu(&VFS_I(ip)->i_rcu, xfs_inode_free_callback);
 }
 
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index dabda9521b4..39797490a1f 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -1585,6 +1585,7 @@ xlog_recover_add_to_trans(
 		"bad number of regions (%d) in inode log format",
 				  in_f->ilf_size);
 			ASSERT(0);
+			kmem_free(ptr);
 			return XFS_ERROR(EIO);
 		}
 
@@ -1970,6 +1971,13 @@ xlog_recover_do_inode_buffer(
  * magic number.  If we don't recognise the magic number in the buffer, then
  * return a LSN of -1 so that the caller knows it was an unrecognised block and
  * so can recover the buffer.
+ *
+ * Note: we cannot rely solely on magic number matches to determine that the
+ * buffer has a valid LSN - we also need to verify that it belongs to this
+ * filesystem, so we need to extract the object's LSN and compare it to that
+ * which we read from the superblock. If the UUIDs don't match, then we've got a
+ * stale metadata block from an old filesystem instance that we need to recover
+ * over the top of.
  */
 static xfs_lsn_t
 xlog_recover_get_buf_lsn(
@@ -1980,6 +1988,8 @@ xlog_recover_get_buf_lsn(
 	__uint16_t		magic16;
 	__uint16_t		magicda;
 	void			*blk = bp->b_addr;
+	uuid_t			*uuid;
+	xfs_lsn_t		lsn = -1;
 
 	/* v4 filesystems always recover immediately */
 	if (!xfs_sb_version_hascrc(&mp->m_sb))
@@ -1992,43 +2002,79 @@ xlog_recover_get_buf_lsn(
 	case XFS_ABTB_MAGIC:
 	case XFS_ABTC_MAGIC:
 	case XFS_IBT_CRC_MAGIC:
-	case XFS_IBT_MAGIC:
-		return be64_to_cpu(
-				((struct xfs_btree_block *)blk)->bb_u.s.bb_lsn);
+	case XFS_IBT_MAGIC: {
+		struct xfs_btree_block *btb = blk;
+
+		lsn = be64_to_cpu(btb->bb_u.s.bb_lsn);
+		uuid = &btb->bb_u.s.bb_uuid;
+		break;
+	}
 	case XFS_BMAP_CRC_MAGIC:
-	case XFS_BMAP_MAGIC:
-		return be64_to_cpu(
-				((struct xfs_btree_block *)blk)->bb_u.l.bb_lsn);
+	case XFS_BMAP_MAGIC: {
+		struct xfs_btree_block *btb = blk;
+
+		lsn = be64_to_cpu(btb->bb_u.l.bb_lsn);
+		uuid = &btb->bb_u.l.bb_uuid;
+		break;
+	}
 	case XFS_AGF_MAGIC:
-		return be64_to_cpu(((struct xfs_agf *)blk)->agf_lsn);
+		lsn = be64_to_cpu(((struct xfs_agf *)blk)->agf_lsn);
+		uuid = &((struct xfs_agf *)blk)->agf_uuid;
+		break;
 	case XFS_AGFL_MAGIC:
-		return be64_to_cpu(((struct xfs_agfl *)blk)->agfl_lsn);
+		lsn = be64_to_cpu(((struct xfs_agfl *)blk)->agfl_lsn);
+		uuid = &((struct xfs_agfl *)blk)->agfl_uuid;
+		break;
 	case XFS_AGI_MAGIC:
-		return be64_to_cpu(((struct xfs_agi *)blk)->agi_lsn);
+		lsn = be64_to_cpu(((struct xfs_agi *)blk)->agi_lsn);
+		uuid = &((struct xfs_agi *)blk)->agi_uuid;
+		break;
 	case XFS_SYMLINK_MAGIC:
-		return be64_to_cpu(((struct xfs_dsymlink_hdr *)blk)->sl_lsn);
+		lsn = be64_to_cpu(((struct xfs_dsymlink_hdr *)blk)->sl_lsn);
+		uuid = &((struct xfs_dsymlink_hdr *)blk)->sl_uuid;
+		break;
 	case XFS_DIR3_BLOCK_MAGIC:
 	case XFS_DIR3_DATA_MAGIC:
 	case XFS_DIR3_FREE_MAGIC:
-		return be64_to_cpu(((struct xfs_dir3_blk_hdr *)blk)->lsn);
+		lsn = be64_to_cpu(((struct xfs_dir3_blk_hdr *)blk)->lsn);
+		uuid = &((struct xfs_dir3_blk_hdr *)blk)->uuid;
+		break;
 	case XFS_ATTR3_RMT_MAGIC:
-		return be64_to_cpu(((struct xfs_attr3_rmt_hdr *)blk)->rm_lsn);
+		lsn = be64_to_cpu(((struct xfs_attr3_rmt_hdr *)blk)->rm_lsn);
+		uuid = &((struct xfs_attr3_rmt_hdr *)blk)->rm_uuid;
+		break;
 	case XFS_SB_MAGIC:
-		return be64_to_cpu(((struct xfs_dsb *)blk)->sb_lsn);
+		lsn = be64_to_cpu(((struct xfs_dsb *)blk)->sb_lsn);
+		uuid = &((struct xfs_dsb *)blk)->sb_uuid;
+		break;
 	default:
 		break;
 	}
 
+	if (lsn != (xfs_lsn_t)-1) {
+		if (!uuid_equal(&mp->m_sb.sb_uuid, uuid))
+			goto recover_immediately;
+		return lsn;
+	}
+
 	magicda = be16_to_cpu(((struct xfs_da_blkinfo *)blk)->magic);
 	switch (magicda) {
 	case XFS_DIR3_LEAF1_MAGIC:
 	case XFS_DIR3_LEAFN_MAGIC:
 	case XFS_DA3_NODE_MAGIC:
-		return be64_to_cpu(((struct xfs_da3_blkinfo *)blk)->lsn);
+		lsn = be64_to_cpu(((struct xfs_da3_blkinfo *)blk)->lsn);
+		uuid = &((struct xfs_da3_blkinfo *)blk)->uuid;
+		break;
 	default:
 		break;
 	}
 
+	if (lsn != (xfs_lsn_t)-1) {
+		if (!uuid_equal(&mp->m_sb.sb_uuid, uuid))
+			goto recover_immediately;
+		return lsn;
+	}
+
 	/*
 	 * We do individual object checks on dquot and inode buffers as they
 	 * have their own individual LSN records. Also, we could have a stale