Merge tag 'xfs-for-linus-v3.12-rc3' of git://oss.sgi.com/xfs/xfs

Pull xfs bugfixes from Ben Myers:
 - fix for directory node collapse regression
 - fix for recovery over stale on disk structures
 - fix for eofblocks ioctl
 - fix asserts in xfs_inode_free
 - lock the ail before removing an item from it

* tag 'xfs-for-linus-v3.12-rc3' of git://oss.sgi.com/xfs/xfs:
  xfs: fix node forward in xfs_node_toosmall
  xfs: log recovery lsn ordering needs uuid check
  xfs: fix XFS_IOC_FREE_EOFBLOCKS definition
  xfs: asserting lock not held during freeing not valid
  xfs: lock the AIL before removing the buffer item

5 files changed, 68 insertions, 22 deletions

diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 88c5ea75ebf6..f1d85cfc0a54 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 069537c845e5..20bf8e8002d6 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_fs.h b/fs/xfs/xfs_fs.h
index 1edb5cc3e5f4..18272c766a50 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 193206ba4358..474807a401c8 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 dabda9521b4b..cc179878fe41 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -1970,6 +1970,13 @@ 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 +1987,8 @@ 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 +2001,79 @@ 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