ocfs2: Validate metadata only when it's read from disk.

Add an optional validation hook to ocfs2_read_blocks().  Now the
validation function is only called when a block was actually read off of
disk.  It is not called when the buffer was in cache.

We add a buffer state bit BH_NeedsValidate to flag these buffers.  It
must always be one higher than the last JBD2 buffer state bit.

The dinode, dirblock, extent_block, and xattr_block validators are
lifted to this scheme directly.  The group_descriptor validator needs to
be split into two pieces.  The first part only needs the gd buffer and
is passed to ocfs2_read_block().  The second part requires the dinode as
well, and is called every time.  It's only 3 compares, so it's tiny.
This also allows us to clean up the non-fatal gd check used by resize.c.
It now has no magic argument.

Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>

1 files changed, 32 insertions, 1 deletions

diff --git a/fs/ocfs2/buffer_head_io.c b/fs/ocfs2/buffer_head_io.c
index 3a178ec48d7..0e9eed0c223 100644
--- a/fs/ocfs2/buffer_head_io.c
+++ b/fs/ocfs2/buffer_head_io.c
@@ -39,6 +39,19 @@
 
 #include "buffer_head_io.h"
 
+/*
+ * Bits on bh->b_state used by ocfs2.
+ *
+ * These MUST be after the JBD2 bits.  Currently BH_Unshadow is the last
+ * JBD2 bit.
+ */
+enum ocfs2_state_bits {
+	BH_NeedsValidate = BH_Unshadow + 1,
+};
+
+/* Expand the magic b_state functions */
+BUFFER_FNS(NeedsValidate, needs_validate);
+
 int ocfs2_write_block(struct ocfs2_super *osb, struct buffer_head *bh,
 		      struct inode *inode)
 {
@@ -166,7 +179,9 @@ bail:
 }
 
 int ocfs2_read_blocks(struct inode *inode, u64 block, int nr,
-		      struct buffer_head *bhs[], int flags)
+		      struct buffer_head *bhs[], int flags,
+		      int (*validate)(struct super_block *sb,
+				      struct buffer_head *bh))
 {
 	int status = 0;
 	int i, ignore_cache = 0;
@@ -298,6 +313,8 @@ int ocfs2_read_blocks(struct inode *inode, u64 block, int nr,
 
 			clear_buffer_uptodate(bh);
 			get_bh(bh); /* for end_buffer_read_sync() */
+			if (validate)
+				set_buffer_needs_validate(bh);
 			bh->b_end_io = end_buffer_read_sync;
 			submit_bh(READ, bh);
 			continue;
@@ -328,6 +345,20 @@ int ocfs2_read_blocks(struct inode *inode, u64 block, int nr,
 				bhs[i] = NULL;
 				continue;
 			}
+
+			if (buffer_needs_validate(bh)) {
+				/* We never set NeedsValidate if the
+				 * buffer was held by the journal, so
+				 * that better not have changed */
+				BUG_ON(buffer_jbd(bh));
+				clear_buffer_needs_validate(bh);
+				status = validate(inode->i_sb, bh);
+				if (status) {
+					put_bh(bh);
+					bhs[i] = NULL;
+					continue;
+				}
+			}
 		}
 
 		/* Always set the buffer in the cache, even if it was