Merge v7.1.5linux-rolling-stable

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

15 files changed, 274 insertions, 41 deletions

diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 6e5fd3f12a84..be09e766ac1f 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -7576,7 +7576,7 @@ int ocfs2_trim_mainbm(struct super_block *sb, struct fstrim_range *range)
 	len = range->len >> osb->s_clustersize_bits;
 	minlen = range->minlen >> osb->s_clustersize_bits;
 
-	if (minlen >= osb->bitmap_cpg || range->len < sb->s_blocksize)
+	if (minlen >= osb->bitmap_cpg || range->len < osb->s_clustersize)
 		return -EINVAL;
 
 	trace_ocfs2_trim_mainbm(start, len, minlen);
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 6ec198bdab12..4acdbb70882c 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -2372,6 +2372,15 @@ commit:
 unlock:
 	up_write(&oi->ip_alloc_sem);
 
+	if (data_ac) {
+		ocfs2_free_alloc_context(data_ac);
+		data_ac = NULL;
+	}
+	if (meta_ac) {
+		ocfs2_free_alloc_context(meta_ac);
+		meta_ac = NULL;
+	}
+
 	/* everything looks good, let's start the cleanup */
 	if (!ret && dwc->dw_orphaned) {
 		BUG_ON(dwc->dw_writer_pid != task_pid_nr(current));
@@ -2383,10 +2392,6 @@ unlock:
 	ocfs2_inode_unlock(inode, 1);
 	brelse(di_bh);
 out:
-	if (data_ac)
-		ocfs2_free_alloc_context(data_ac);
-	if (meta_ac)
-		ocfs2_free_alloc_context(meta_ac);
 	ocfs2_run_deallocs(osb, &dealloc);
 	ocfs2_dio_free_write_ctx(inode, dwc);
 
diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c
index 701d27d908d4..6114299b121e 100644
--- a/fs/ocfs2/buffer_head_io.c
+++ b/fs/ocfs2/buffer_head_io.c
@@ -350,8 +350,6 @@ read_failure:
 						wait_on_buffer(bh);
 					put_bh(bh);
 					bhs[i] = NULL;
-				} else if (bh && buffer_uptodate(bh)) {
-					clear_buffer_uptodate(bh);
 				}
 				continue;
 			}
@@ -380,8 +378,11 @@ read_failure:
 				BUG_ON(buffer_jbd(bh));
 				clear_buffer_needs_validate(bh);
 				status = validate(sb, bh);
-				if (status)
+				if (status) {
+					if (buffer_uptodate(bh))
+						clear_buffer_uptodate(bh);
 					goto read_failure;
+				}
 			}
 		}
 
diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
index fe4fdd09bae3..564567358620 100644
--- a/fs/ocfs2/dlm/dlmdebug.c
+++ b/fs/ocfs2/dlm/dlmdebug.c
@@ -560,6 +560,7 @@ static int debug_lockres_open(struct inode *inode, struct file *file)
 	struct dlm_ctxt *dlm = inode->i_private;
 	struct debug_lockres *dl;
 	void *buf;
+	int status = -ENOMEM;
 
 	buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
 	if (!buf)
@@ -572,16 +573,23 @@ static int debug_lockres_open(struct inode *inode, struct file *file)
 	dl->dl_len = PAGE_SIZE;
 	dl->dl_buf = buf;
 
-	dlm_grab(dlm);
-	dl->dl_ctxt = dlm;
+	/* ->release uses dl_ctxt after open, so it needs a real pin. */
+	dl->dl_ctxt = dlm_grab(dlm);
+	if (!dl->dl_ctxt) {
+		status = -ENOENT;
+		goto bailseq;
+	}
 
 	return 0;
 
+bailseq:
+	seq_release_private(inode, file);
 bailfree:
 	kfree(buf);
 bail:
-	mlog_errno(-ENOMEM);
-	return -ENOMEM;
+	if (status != -ENOENT)
+		mlog_errno(status);
+	return status;
 }
 
 static int debug_lockres_release(struct inode *inode, struct file *file)
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 7283bb2c5a31..a23dd8f86c89 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -3134,6 +3134,22 @@ static void *ocfs2_dlm_seq_next(struct seq_file *m, void *v, loff_t *pos)
  *	- Add last pr/ex unlock times and first lock wait time in usecs
  */
 #define OCFS2_DLM_DEBUG_STR_VERSION 4
+
+/*
+ * The debug iterator snapshots lockres by value, so a userspace-stack LVB
+ * pointer copied from the original lockres must be rebased to the copied
+ * lksb before the dump walks the raw bytes.
+ */
+static void ocfs2_dlm_seq_rebase_lvb(struct ocfs2_lock_res *lockres)
+{
+	if (!ocfs2_stack_supports_plocks())
+		return;
+
+	if (lockres->l_lksb.lksb_fsdlm.sb_lvbptr)
+		lockres->l_lksb.lksb_fsdlm.sb_lvbptr =
+			(char *)&lockres->l_lksb + sizeof(struct dlm_lksb);
+}
+
 static int ocfs2_dlm_seq_show(struct seq_file *m, void *v)
 {
 	int i;
@@ -3191,6 +3207,7 @@ static int ocfs2_dlm_seq_show(struct seq_file *m, void *v)
 		   lockres->l_blocking);
 
 	/* Dump the raw LVB */
+	ocfs2_dlm_seq_rebase_lvb(lockres);
 	lvb = ocfs2_dlm_lvb(&lockres->l_lksb);
 	for(i = 0; i < DLM_LVB_LEN; i++)
 		seq_printf(m, "0x%x\t", lvb[i]);
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index a510a0eb1adc..662dbc845b8b 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -13,6 +13,7 @@
 #include <linux/pagemap.h>
 #include <linux/quotaops.h>
 #include <linux/iversion.h>
+#include <linux/fs_dirent.h>
 
 #include <asm/byteorder.h>
 
@@ -64,7 +65,40 @@ static int ocfs2_filecheck_read_inode_block_full(struct inode *inode,
 static int ocfs2_filecheck_validate_inode_block(struct super_block *sb,
 						struct buffer_head *bh);
 static int ocfs2_filecheck_repair_inode_block(struct super_block *sb,
-					      struct buffer_head *bh);
+						      struct buffer_head *bh);
+
+static bool ocfs2_valid_inode_mode(umode_t mode)
+{
+	return fs_umode_to_ftype(mode) != FT_UNKNOWN;
+}
+
+static bool ocfs2_dinode_has_unexpected_rdev(struct ocfs2_dinode *di)
+{
+	umode_t mode = le16_to_cpu(di->i_mode);
+
+	if (le32_to_cpu(di->i_flags) & OCFS2_SYSTEM_FL)
+		return false;
+
+	return !S_ISCHR(mode) && !S_ISBLK(mode) && di->id1.dev1.i_rdev != 0;
+}
+
+static bool ocfs2_dinode_has_size_without_clusters(struct super_block *sb,
+						   struct ocfs2_dinode *di)
+{
+	umode_t mode = le16_to_cpu(di->i_mode);
+
+	if (le32_to_cpu(di->i_flags) & OCFS2_SYSTEM_FL)
+		return false;
+	if (le16_to_cpu(di->i_dyn_features) & OCFS2_INLINE_DATA_FL)
+		return false;
+	if (!le64_to_cpu(di->i_size) || le32_to_cpu(di->i_clusters))
+		return false;
+
+	if (S_ISDIR(mode))
+		return true;
+
+	return !ocfs2_sparse_alloc(OCFS2_SB(sb)) && S_ISREG(mode);
+}
 
 void ocfs2_set_inode_flags(struct inode *inode)
 {
@@ -1494,6 +1528,86 @@ int ocfs2_validate_inode_block(struct super_block *sb,
 		goto bail;
 	}
 
+	/*
+	 * Reject dinodes whose i_mode does not name one of the seven
+	 * canonical POSIX file types.  ocfs2_populate_inode() copies
+	 * i_mode verbatim into inode->i_mode and then dispatches via
+	 * switch (mode & S_IFMT) to file/dir/symlink/special_file iops;
+	 * an unrecognised type falls into ocfs2_special_file_iops with
+	 * init_special_inode(), which interprets i_rdev.  Constrain the
+	 * type here so the dispatch only ever sees a value mkfs.ocfs2 /
+	 * VFS can produce.
+	 */
+	if (!ocfs2_valid_inode_mode(le16_to_cpu(di->i_mode))) {
+		rc = ocfs2_error(sb,
+				 "Invalid dinode #%llu: mode 0%o has unknown file type\n",
+				 (unsigned long long)bh->b_blocknr,
+				 le16_to_cpu(di->i_mode));
+		goto bail;
+	}
+
+	/*
+	 * id1.dev1.i_rdev is the device-number arm of the id1 union and
+	 * is only meaningful for character and block device inodes.  For
+	 * any other regular user-visible file type the on-disk value
+	 * must be zero.  ocfs2_populate_inode() currently runs
+	 *
+	 *     inode->i_rdev = huge_decode_dev(le64_to_cpu(fe->id1.dev1.i_rdev));
+	 *
+	 * unconditionally, before the S_IFMT switch decides whether the
+	 * inode is a special file.  As a result, an i_rdev value present
+	 * on a non-device inode is silently published into the in-core
+	 * inode; a subsequent forced re-read or in-core mode mutation
+	 * (cluster peer with raw write access to the shared LUN,
+	 * on-disk corruption, or a separately forged dinode) can then
+	 * expose the attacker-controlled device number to
+	 * init_special_inode() without ever showing an unusual i_mode
+	 * at validation time.
+	 *
+	 * System inodes (OCFS2_SYSTEM_FL) legitimately use the bitmap1
+	 * and journal1 arms of the same union (allocator i_used /
+	 * i_total counters and the journal ij_flags /
+	 * ij_recovery_generation pair); those bytes are not an i_rdev
+	 * and must not be checked here.  Restrict the cross-check to
+	 * non-system inodes, which is the full attacker-controllable
+	 * surface.
+	 */
+	if (ocfs2_dinode_has_unexpected_rdev(di)) {
+		rc = ocfs2_error(sb,
+				 "Invalid dinode #%llu: non-device mode 0%o with i_rdev %llu\n",
+				 (unsigned long long)bh->b_blocknr,
+				 le16_to_cpu(di->i_mode),
+				 (unsigned long long)le64_to_cpu(di->id1.dev1.i_rdev));
+		goto bail;
+	}
+
+	/*
+	 * Non-inline directories must not have i_size without allocated
+	 * clusters: directory growth adds storage before advancing i_size,
+	 * and readdir walks i_size block-by-block.  A forged directory
+	 * with zero clusters and a huge i_size would repeatedly fault on
+	 * holes while advancing through the claimed size.
+	 *
+	 * Non-inline regular files have the same invariant on non-sparse
+	 * volumes.  Sparse regular files are different: truncate can
+	 * legitimately grow i_size without allocating clusters, so keep
+	 * the sparse-alloc carveout for S_IFREG only.  System inodes and
+	 * inline-data dinodes have their own storage rules.
+	 */
+	if (ocfs2_dinode_has_size_without_clusters(sb, di)) {
+		if (S_ISDIR(le16_to_cpu(di->i_mode)))
+			rc = ocfs2_error(sb,
+					 "Invalid dinode #%llu: directory i_size %llu with i_clusters 0 and no inline-data flag\n",
+					 (unsigned long long)bh->b_blocknr,
+					 (unsigned long long)le64_to_cpu(di->i_size));
+		else
+			rc = ocfs2_error(sb,
+					 "Invalid dinode #%llu: regular file i_size %llu with i_clusters 0 and no inline-data flag on non-sparse volume\n",
+					 (unsigned long long)bh->b_blocknr,
+					 (unsigned long long)le64_to_cpu(di->i_size));
+		goto bail;
+	}
+
 	if (le16_to_cpu(di->i_dyn_features) & OCFS2_INLINE_DATA_FL) {
 		struct ocfs2_inline_data *data = &di->id2.i_data;
 
@@ -1525,6 +1639,29 @@ int ocfs2_validate_inode_block(struct super_block *sb,
 		}
 	}
 
+	if (S_ISLNK(le16_to_cpu(di->i_mode)) &&
+	    !le32_to_cpu(di->i_clusters)) {
+		int max_inline = ocfs2_fast_symlink_chars(sb);
+		u64 i_size = le64_to_cpu(di->i_size);
+
+		if (i_size >= max_inline) {
+			rc = ocfs2_error(sb,
+					 "Invalid dinode #%llu: fast symlink i_size %llu exceeds max %d\n",
+					 (unsigned long long)bh->b_blocknr,
+					 (unsigned long long)i_size,
+					 max_inline - 1);
+			goto bail;
+		}
+
+		if (strnlen((char *)di->id2.i_symlink, i_size + 1) != i_size) {
+			rc = ocfs2_error(sb,
+					 "Invalid dinode #%llu: fast symlink is not NUL-terminated at i_size %llu\n",
+					 (unsigned long long)bh->b_blocknr,
+					 (unsigned long long)i_size);
+			goto bail;
+		}
+	}
+
 	if (le32_to_cpu(di->i_flags) & OCFS2_CHAIN_FL) {
 		struct ocfs2_chain_list *cl = &di->id2.i_chain;
 		u16 bpc = 1 << (OCFS2_SB(sb)->s_clustersize_bits -
@@ -1559,6 +1696,38 @@ int ocfs2_validate_inode_block(struct super_block *sb,
 		goto bail;
 	}
 
+	if (ocfs2_dinode_has_extents(di)) {
+		struct ocfs2_extent_list *el = &di->id2.i_list;
+		u16 count = le16_to_cpu(el->l_count);
+		u16 next_free = le16_to_cpu(el->l_next_free_rec);
+
+		if (count == 0) {
+			rc = ocfs2_error(sb,
+					 "Invalid dinode %llu: extent list l_count is zero\n",
+					 (unsigned long long)bh->b_blocknr);
+			goto bail;
+		}
+		/*
+		 * The exact capacity depends on i_xattr_inline_size, another
+		 * unvalidated on-disk field. Inline xattrs only shrink the
+		 * list, so the no-xattr maximum is a safe upper bound that a
+		 * valid l_count never exceeds.
+		 */
+		if (count > ocfs2_extent_recs_per_inode(sb)) {
+			rc = ocfs2_error(sb,
+					 "Invalid dinode %llu: extent list l_count %u exceeds max %u\n",
+					 (unsigned long long)bh->b_blocknr, count,
+					 ocfs2_extent_recs_per_inode(sb));
+			goto bail;
+		}
+		if (next_free > count) {
+			rc = ocfs2_error(sb,
+					 "Invalid dinode %llu: extent list l_next_free_rec %u exceeds l_count %u\n",
+					 (unsigned long long)bh->b_blocknr, next_free, count);
+			goto bail;
+		}
+	}
+
 	rc = 0;
 
 bail:
@@ -1624,6 +1793,40 @@ static int ocfs2_filecheck_validate_inode_block(struct super_block *sb,
 		     (unsigned long long)bh->b_blocknr,
 		     le32_to_cpu(di->i_fs_generation));
 		rc = -OCFS2_FILECHECK_ERR_GENERATION;
+		goto bail;
+	}
+
+	if (!ocfs2_valid_inode_mode(le16_to_cpu(di->i_mode))) {
+		mlog(ML_ERROR,
+		     "Filecheck: invalid dinode #%llu: mode 0%o has unknown file type\n",
+		     (unsigned long long)bh->b_blocknr,
+		     le16_to_cpu(di->i_mode));
+		rc = -OCFS2_FILECHECK_ERR_INVALIDINO;
+		goto bail;
+	}
+
+	if (ocfs2_dinode_has_unexpected_rdev(di)) {
+		mlog(ML_ERROR,
+		     "Filecheck: invalid dinode #%llu: non-device mode 0%o with i_rdev %llu\n",
+		     (unsigned long long)bh->b_blocknr,
+		     le16_to_cpu(di->i_mode),
+		     (unsigned long long)le64_to_cpu(di->id1.dev1.i_rdev));
+		rc = -OCFS2_FILECHECK_ERR_INVALIDINO;
+		goto bail;
+	}
+
+	if (ocfs2_dinode_has_size_without_clusters(sb, di)) {
+		if (S_ISDIR(le16_to_cpu(di->i_mode)))
+			mlog(ML_ERROR,
+			     "Filecheck: invalid dinode #%llu: directory i_size %llu with i_clusters 0 and no inline-data flag\n",
+			     (unsigned long long)bh->b_blocknr,
+			     (unsigned long long)le64_to_cpu(di->i_size));
+		else
+			mlog(ML_ERROR,
+			     "Filecheck: invalid dinode #%llu: regular file i_size %llu with i_clusters 0 and no inline-data flag on non-sparse volume\n",
+			     (unsigned long long)bh->b_blocknr,
+			     (unsigned long long)le64_to_cpu(di->i_size));
+		rc = -OCFS2_FILECHECK_ERR_INVALIDINO;
 	}
 
 bail:
@@ -1812,4 +2015,3 @@ const struct ocfs2_caching_operations ocfs2_inode_caching_ops = {
 	.co_io_lock		= ocfs2_inode_cache_io_lock,
 	.co_io_unlock		= ocfs2_inode_cache_io_unlock,
 };
-
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index f9bf3bac085d..d8afbc1a76bb 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -473,8 +473,12 @@ bail:
  */
 int ocfs2_assure_trans_credits(handle_t *handle, int nblocks)
 {
-	int old_nblks = jbd2_handle_buffer_credits(handle);
+	int old_nblks;
 
+	if (is_handle_aborted(handle))
+		return -EROFS;
+
+	old_nblks = jbd2_handle_buffer_credits(handle);
 	trace_ocfs2_assure_trans_credits(old_nblks);
 	if (old_nblks >= nblocks)
 		return 0;
@@ -1022,11 +1026,8 @@ static int ocfs2_journal_toggle_dirty(struct ocfs2_super *osb,
 	struct ocfs2_dinode *fe;
 
 	fe = (struct ocfs2_dinode *)bh->b_data;
-
-	/* The journal bh on the osb always comes from ocfs2_journal_init()
-	 * and was validated there inside ocfs2_inode_lock_full().  It's a
-	 * code bug if we mess it up. */
-	BUG_ON(!OCFS2_IS_VALID_DINODE(fe));
+	if (WARN_ON(!OCFS2_IS_VALID_DINODE(fe)))
+		return -EIO;
 
 	flags = le32_to_cpu(fe->id1.journal1.ij_flags);
 	if (dirty)
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index 6397170f302f..f8b3b2a3d630 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -196,6 +196,9 @@ static inline void ocfs2_checkpoint_inode(struct inode *inode)
 	if (ocfs2_mount_local(osb))
 		return;
 
+	if (!osb->journal)
+		return;
+
 	if (!ocfs2_ci_fully_checkpointed(INODE_CACHE(inode))) {
 		/* WARNING: This only kicks off a single
 		 * checkpoint. If someone races you and adds more
diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index c53de4439d93..ad1678ee7cc4 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -534,6 +534,8 @@ static void ocfs2_probe_alloc_group(struct inode *inode, struct buffer_head *bh,
 	u32 base_cpos = ocfs2_blocks_to_clusters(inode->i_sb,
 						 le64_to_cpu(gd->bg_blkno));
 
+	*phys_cpos = 0;
+
 	for (i = base_bit; i < le16_to_cpu(gd->bg_bits); i++) {
 
 		used = ocfs2_test_bit(i, (unsigned long *)gd->bg_bitmap);
@@ -555,7 +557,7 @@ static void ocfs2_probe_alloc_group(struct inode *inode, struct buffer_head *bh,
 			last_free_bits++;
 
 		if (last_free_bits == move_len) {
-			i -= move_len;
+			i = i - move_len + 1;
 			*goal_bit = i;
 			*phys_cpos = base_cpos + i;
 			break;
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 7b50e03dfa66..62cad6522c7a 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -494,8 +494,6 @@ struct ocfs2_super
 	struct rb_root	osb_rf_lock_tree;
 	struct ocfs2_refcount_tree *osb_ref_tree_lru;
 
-	struct mutex system_file_mutex;
-
 	/*
 	 * OCFS2 needs to schedule several different types of work which
 	 * require cluster locking, disk I/O, recovery waits, etc. Since these
diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index 12cbb4fccda0..f55810c59b1b 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -302,7 +302,7 @@ static int ocfs2_add_recovery_chunk(struct super_block *sb,
 	if (!rc)
 		return -ENOMEM;
 	rc->rc_chunk = chunk;
-	rc->rc_bitmap = kmalloc(sb->s_blocksize, GFP_NOFS);
+	rc->rc_bitmap = kzalloc(sb->s_blocksize, GFP_NOFS);
 	if (!rc->rc_bitmap) {
 		kfree(rc);
 		return -ENOMEM;
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 8eee5be4d1ed..7323bde70caa 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -2131,10 +2131,15 @@ static int ocfs2_remove_refcount_extent(handle_t *handle,
 		rb->rf_flags = 0;
 		rb->rf_parent = 0;
 		rb->rf_cpos = 0;
-		memset(&rb->rf_records, 0, sb->s_blocksize -
-		       offsetof(struct ocfs2_refcount_block, rf_records));
+		rb->rf_records.rl_used = 0;
+		rb->rf_records.rl_reserved2 = 0;
+		rb->rf_records.rl_reserved1 = 0;
+		/* rl_count determines the memset size and fortify object size. */
 		rb->rf_records.rl_count =
 				cpu_to_le16(ocfs2_refcount_recs_per_rb(sb));
+		memset(rb->rf_records.rl_recs, 0,
+		       le16_to_cpu(rb->rf_records.rl_count) *
+		       sizeof(*rb->rf_records.rl_recs));
 	}
 
 	ocfs2_journal_dirty(handle, ref_root_bh);
diff --git a/fs/ocfs2/stack_user.c b/fs/ocfs2/stack_user.c
index 5803f1dee679..91e19d33847c 100644
--- a/fs/ocfs2/stack_user.c
+++ b/fs/ocfs2/stack_user.c
@@ -327,18 +327,14 @@ static int ocfs2_control_install_private(struct file *file)
 		ocfs2_control_this_node = p->op_this_node;
 		running_proto.pv_major = p->op_proto.pv_major;
 		running_proto.pv_minor = p->op_proto.pv_minor;
-	}
-
-out_unlock:
-	mutex_unlock(&ocfs2_control_lock);
-
-	if (!rc && set_p) {
-		/* We set the global values successfully */
 		atomic_inc(&ocfs2_control_opened);
 		ocfs2_control_set_handshake_state(file,
 					OCFS2_CONTROL_HANDSHAKE_VALID);
 	}
 
+out_unlock:
+	mutex_unlock(&ocfs2_control_lock);
+
 	return rc;
 }
 
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index b875f01c9756..6dd45c2153f8 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1997,8 +1997,6 @@ static int ocfs2_initialize_super(struct super_block *sb,
 	spin_lock_init(&osb->osb_xattr_lock);
 	ocfs2_init_steal_slots(osb);
 
-	mutex_init(&osb->system_file_mutex);
-
 	atomic_set(&osb->alloc_stats.moves, 0);
 	atomic_set(&osb->alloc_stats.local_data, 0);
 	atomic_set(&osb->alloc_stats.bitmap_data, 0);
diff --git a/fs/ocfs2/sysfile.c b/fs/ocfs2/sysfile.c
index d53a6cc866be..67e492f4b828 100644
--- a/fs/ocfs2/sysfile.c
+++ b/fs/ocfs2/sysfile.c
@@ -98,11 +98,9 @@ struct inode *ocfs2_get_system_file_inode(struct ocfs2_super *osb,
 	} else
 		arr = get_local_system_inode(osb, type, slot);
 
-	mutex_lock(&osb->system_file_mutex);
 	if (arr && ((inode = *arr) != NULL)) {
 		/* get a ref in addition to the array ref */
 		inode = igrab(inode);
-		mutex_unlock(&osb->system_file_mutex);
 		BUG_ON(!inode);
 
 		return inode;
@@ -112,11 +110,10 @@ struct inode *ocfs2_get_system_file_inode(struct ocfs2_super *osb,
 	inode = _ocfs2_get_system_file_inode(osb, type, slot);
 
 	/* add one more if putting into array for first time */
-	if (arr && inode) {
-		*arr = igrab(inode);
-		BUG_ON(!*arr);
+	if (inode && arr && !*arr && !cmpxchg(&(*arr), NULL, inode)) {
+		inode = igrab(inode);
+		BUG_ON(!inode);
 	}
-	mutex_unlock(&osb->system_file_mutex);
 	return inode;
 }