GFS2: Move recovery variables to journal structure in memory

If multiple nodes fail and their recovery work runs simultaneously, they
would use the same unprotected variables in the superblock. For example,
they would stomp on each other's revoked blocks lists, which resulted
in file system metadata corruption. This patch moves the necessary
variables so that each journal has its own separate area for tracking
its journal replay.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

1 files changed, 17 insertions, 21 deletions

diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index ae1d6352a1eb..a294d8d8bcd4 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -520,13 +520,11 @@ static void buf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 static void buf_lo_before_scan(struct gfs2_jdesc *jd,
 			       struct gfs2_log_header_host *head, int pass)
 {
-	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
-
 	if (pass != 0)
 		return;
 
-	sdp->sd_found_blocks = 0;
-	sdp->sd_replayed_blocks = 0;
+	jd->jd_found_blocks = 0;
+	jd->jd_replayed_blocks = 0;
 }
 
 static int buf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
@@ -549,9 +547,9 @@ static int buf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
 	for (; blks; gfs2_replay_incr_blk(sdp, &start), blks--) {
 		blkno = be64_to_cpu(*ptr++);
 
-		sdp->sd_found_blocks++;
+		jd->jd_found_blocks++;
 
-		if (gfs2_revoke_check(sdp, blkno, start))
+		if (gfs2_revoke_check(jd, blkno, start))
 			continue;
 
 		error = gfs2_replay_read_block(jd, start, &bh_log);
@@ -572,7 +570,7 @@ static int buf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
 		if (error)
 			break;
 
-		sdp->sd_replayed_blocks++;
+		jd->jd_replayed_blocks++;
 	}
 
 	return error;
@@ -615,7 +613,7 @@ static void buf_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
 	gfs2_meta_sync(ip->i_gl);
 
 	fs_info(sdp, "jid=%u: Replayed %u of %u blocks\n",
-	        jd->jd_jid, sdp->sd_replayed_blocks, sdp->sd_found_blocks);
+	        jd->jd_jid, jd->jd_replayed_blocks, jd->jd_found_blocks);
 }
 
 static void revoke_lo_before_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
@@ -677,13 +675,11 @@ static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 static void revoke_lo_before_scan(struct gfs2_jdesc *jd,
 				  struct gfs2_log_header_host *head, int pass)
 {
-	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
-
 	if (pass != 0)
 		return;
 
-	sdp->sd_found_revokes = 0;
-	sdp->sd_replay_tail = head->lh_tail;
+	jd->jd_found_revokes = 0;
+	jd->jd_replay_tail = head->lh_tail;
 }
 
 static int revoke_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
@@ -715,13 +711,13 @@ static int revoke_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
 		while (offset + sizeof(u64) <= sdp->sd_sb.sb_bsize) {
 			blkno = be64_to_cpu(*(__be64 *)(bh->b_data + offset));
 
-			error = gfs2_revoke_add(sdp, blkno, start);
+			error = gfs2_revoke_add(jd, blkno, start);
 			if (error < 0) {
 				brelse(bh);
 				return error;
 			}
 			else if (error)
-				sdp->sd_found_revokes++;
+				jd->jd_found_revokes++;
 
 			if (!--revokes)
 				break;
@@ -741,16 +737,16 @@ static void revoke_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
 	struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
 
 	if (error) {
-		gfs2_revoke_clean(sdp);
+		gfs2_revoke_clean(jd);
 		return;
 	}
 	if (pass != 1)
 		return;
 
 	fs_info(sdp, "jid=%u: Found %u revoke tags\n",
-	        jd->jd_jid, sdp->sd_found_revokes);
+	        jd->jd_jid, jd->jd_found_revokes);
 
-	gfs2_revoke_clean(sdp);
+	gfs2_revoke_clean(jd);
 }
 
 /**
@@ -789,9 +785,9 @@ static int databuf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
 		blkno = be64_to_cpu(*ptr++);
 		esc = be64_to_cpu(*ptr++);
 
-		sdp->sd_found_blocks++;
+		jd->jd_found_blocks++;
 
-		if (gfs2_revoke_check(sdp, blkno, start))
+		if (gfs2_revoke_check(jd, blkno, start))
 			continue;
 
 		error = gfs2_replay_read_block(jd, start, &bh_log);
@@ -811,7 +807,7 @@ static int databuf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
 		brelse(bh_log);
 		brelse(bh_ip);
 
-		sdp->sd_replayed_blocks++;
+		jd->jd_replayed_blocks++;
 	}
 
 	return error;
@@ -835,7 +831,7 @@ static void databuf_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
 	gfs2_meta_sync(ip->i_gl);
 
 	fs_info(sdp, "jid=%u: Replayed %u of %u data blocks\n",
-		jd->jd_jid, sdp->sd_replayed_blocks, sdp->sd_found_blocks);
+		jd->jd_jid, jd->jd_replayed_blocks, jd->jd_found_blocks);
 }
 
 static void databuf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)