From: Bob Peterson <rpeterso@redhat.com>
Subject: [RHEL 5.1] [GFS2] bz #248176: GFS2: invalid metadata block, gfs2_meta_indirect_buffer
Date: Thu, 09 Aug 2007 10:46:53 -0500
Bugzilla: 248176
Message-Id: <1186674413.25269.92.camel@technetium.msp.redhat.com>
Changelog: [GFS2] invalid metadata block


Hi,

This patch is for bug #248176: GFS2: invalid metadata block.
There are several places where gfs2 file system buffer
corruption and block corruption were possible.  For more
details, see:

https://bugzilla.redhat.com/bugzilla/show_bug.cgi?id=248176

This patch is now in the upstream git tree for gfs2, and it 
has been tested thoroughly using the "revolver" QE test,
which does a wide variety of strenuous file system I/O
combined with node recovery and journal replay.

Regards,

Bob Peterson
--
Signed-off-by: Bob Peterson <rpeterso@redhat.com> 
--
diff -pur a/fs/gfs2/log.c b/fs/gfs2/log.c
--- a/fs/gfs2/log.c	2007-08-09 08:43:02.000000000 -0500
+++ b/fs/gfs2/log.c	2007-08-08 08:05:32.000000000 -0500
@@ -83,11 +83,6 @@ static void gfs2_ail1_start_one(struct g
 
 			gfs2_assert(sdp, bd->bd_ail == ai);
 
-			if (!bh){
-				list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list);
-                                continue;
-                        }
-
 			if (!buffer_busy(bh)) {
 				if (!buffer_uptodate(bh)) {
 					gfs2_log_unlock(sdp);
@@ -130,11 +125,6 @@ static int gfs2_ail1_empty_one(struct gf
 					 bd_ail_st_list) {
 		bh = bd->bd_bh;
 
-		if (!bh){
-			list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list);
-			continue;
-		}
-
 		gfs2_assert(sdp, bd->bd_ail == ai);
 
 		if (buffer_busy(bh)) {
@@ -155,13 +145,14 @@ static int gfs2_ail1_empty_one(struct gf
 
 static void gfs2_ail1_start(struct gfs2_sbd *sdp, int flags)
 {
-	struct list_head *head = &sdp->sd_ail1_list;
+	struct list_head *head;
 	u64 sync_gen;
 	struct list_head *first;
 	struct gfs2_ail *first_ai, *ai, *tmp;
 	int done = 0;
 
 	gfs2_log_lock(sdp);
+	head = &sdp->sd_ail1_list;
 	if (list_empty(head)) {
 		gfs2_log_unlock(sdp);
 		return;
diff -pur a/fs/gfs2/lops.c b/fs/gfs2/lops.c
--- a/fs/gfs2/lops.c	2007-08-09 08:43:02.000000000 -0500
+++ b/fs/gfs2/lops.c	2007-08-08 08:05:08.000000000 -0500
@@ -117,7 +117,7 @@ static void buf_lo_before_commit(struct 
 	struct buffer_head *bh;
 	struct gfs2_log_descriptor *ld;
 	struct gfs2_bufdata *bd1 = NULL, *bd2;
-	unsigned int total = sdp->sd_log_num_buf;
+	unsigned int total;
 	unsigned int offset = BUF_OFFSET;
 	unsigned int limit;
 	unsigned int num;
@@ -127,12 +127,16 @@ static void buf_lo_before_commit(struct 
 	limit = buf_limit(sdp);
 	/* for 4k blocks, limit = 503 */
 
+	gfs2_log_lock(sdp);
+	total = sdp->sd_log_num_buf;
 	bd1 = bd2 = list_prepare_entry(bd1, &sdp->sd_log_le_buf, bd_le.le_list);
 	while(total) {
 		num = total;
 		if (total > limit)
 			num = limit;
+		gfs2_log_unlock(sdp);
 		bh = gfs2_log_get_buf(sdp);
+		gfs2_log_lock(sdp);
 		ld = (struct gfs2_log_descriptor *)bh->b_data;
 		ptr = (__be64 *)(bh->b_data + offset);
 		ld->ld_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
@@ -152,21 +156,27 @@ static void buf_lo_before_commit(struct 
 				break;
 		}
 
+		gfs2_log_unlock(sdp);
 		set_buffer_dirty(bh);
 		ll_rw_block(WRITE, 1, &bh);
+		gfs2_log_lock(sdp);
 
 		n = 0;
 		list_for_each_entry_continue(bd2, &sdp->sd_log_le_buf,
 					     bd_le.le_list) {
+			gfs2_log_unlock(sdp);
 			bh = gfs2_log_fake_buf(sdp, bd2->bd_bh);
 			set_buffer_dirty(bh);
 			ll_rw_block(WRITE, 1, &bh);
+			gfs2_log_lock(sdp);
 			if (++n >= num)
 				break;
 		}
 
+		BUG_ON(total < num);
 		total -= num;
 	}
+	gfs2_log_unlock(sdp);
 }
 
 static void buf_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
@@ -524,7 +534,7 @@ static void databuf_lo_before_commit(str
 	struct gfs2_log_descriptor *ld;
 	unsigned int limit;
 	unsigned int total_dbuf;
-	unsigned int total_jdata = sdp->sd_log_num_jdata;
+	unsigned int total_jdata;
 	unsigned int num, n;
 	__be64 *ptr = NULL;
 
@@ -536,6 +546,7 @@ static void databuf_lo_before_commit(str
 	 */
 	gfs2_log_lock(sdp);
 	total_dbuf = sdp->sd_log_num_databuf;
+	total_jdata = sdp->sd_log_num_jdata;
 	bd2 = bd1 = list_prepare_entry(bd1, &sdp->sd_log_le_databuf,
 				       bd_le.le_list);
 	while(total_dbuf) {
@@ -621,10 +632,10 @@ static void databuf_lo_before_commit(str
 		}
 		gfs2_log_unlock(sdp);
 		if (bh) {
-			set_buffer_mapped(bh);
 			set_buffer_dirty(bh);
 			ll_rw_block(WRITE, 1, &bh);
 			bh = NULL;
+			ptr = NULL;
 		}
 		n = 0;
 		gfs2_log_lock(sdp);
diff -pur a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
--- a/fs/gfs2/ops_fstype.c	2007-08-09 08:43:03.000000000 -0500
+++ b/fs/gfs2/ops_fstype.c	2007-08-09 09:17:51.000000000 -0500
@@ -359,7 +359,7 @@ static int init_journal(struct gfs2_sbd 
 
 		ip = GFS2_I(sdp->sd_jdesc->jd_inode);
 		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED,
-					   LM_FLAG_NOEXP | GL_EXACT,
+					   LM_FLAG_NOEXP | GL_EXACT | GL_NOCACHE,
 					   &sdp->sd_jinode_gh);
 		if (error) {
 			fs_err(sdp, "can't acquire journal inode glock: %d\n",
Only in b/fs/gfs2: ops_fstype.c.~1~
diff -pur a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c
--- a/fs/gfs2/recovery.c	2007-08-09 08:42:51.000000000 -0500
+++ b/fs/gfs2/recovery.c	2007-08-08 08:07:03.000000000 -0500
@@ -469,7 +469,7 @@ int gfs2_recover_journal(struct gfs2_jde
 		};
 
 		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED,
-					   LM_FLAG_NOEXP, &ji_gh);
+					   LM_FLAG_NOEXP | GL_NOCACHE, &ji_gh);
 		if (error)
 			goto fail_gunlock_j;
 	} else {
diff -pur a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
--- a/fs/gfs2/rgrp.c	2007-08-09 08:43:03.000000000 -0500
+++ b/fs/gfs2/rgrp.c	2007-08-08 08:06:37.000000000 -0500
@@ -31,6 +31,7 @@
 #include "inode.h"
 
 #define BFITNOENT ((u32)~0)
+#define NO_BLOCK ((u64)~0)
 
 /*
  * These routines are used by the resource group routines (rgrp.c)
@@ -116,8 +117,7 @@ static unsigned char gfs2_testbit(struct
  * @buffer: the buffer that holds the bitmaps
  * @buflen: the length (in bytes) of the buffer
  * @goal: start search at this block's bit-pair (within @buffer)
- * @old_state: GFS2_BLKST_XXX the state of the block we're looking for;
- *       bit 0 = alloc(1)/free(0), bit 1 = meta(1)/data(0)
+ * @old_state: GFS2_BLKST_XXX the state of the block we're looking for.
  *
  * Scope of @goal and returned block number is only within this bitmap buffer,
  * not entire rgrp or filesystem.  @buffer will be offset from the actual
@@ -137,9 +137,13 @@ static u32 gfs2_bitfit(struct gfs2_rgrpd
 	byte = buffer + (goal / GFS2_NBBY);
 	bit = (goal % GFS2_NBBY) * GFS2_BIT_SIZE;
 	end = buffer + buflen;
-	alloc = (old_state & 1) ? 0 : 0x55;
+	alloc = (old_state == GFS2_BLKST_FREE) ? 0x55 : 0;
 
 	while (byte < end) {
+		/* If we're looking for a free block we can eliminate all
+		   bitmap settings with 0x55, which represents four data
+		   blocks in a row.  If we're looking for a data block, we can
+		   eliminate 0x00 which corresponds to four free blocks. */
 		if ((*byte & 0x55) == alloc) {
 			blk += (8 - bit) >> 1;
 
@@ -859,19 +863,24 @@ static int try_rgrp_fit(struct gfs2_rgrp
 static struct inode *try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked)
 {
 	struct inode *inode;
-	u32 goal = 0;
+	u32 goal = 0, block;
 	u64 no_addr;
+	struct gfs2_sbd *sdp = rgd->rd_sbd;
 
 	for(;;) {
 		if (goal >= rgd->rd_data)
 			break;
-		goal = rgblk_search(rgd, goal, GFS2_BLKST_UNLINKED,
-				    GFS2_BLKST_UNLINKED);
-		if (goal == BFITNOENT)
+		down_write(&sdp->sd_log_flush_lock);
+		block = rgblk_search(rgd, goal, GFS2_BLKST_UNLINKED,
+				     GFS2_BLKST_UNLINKED);
+		up_write(&sdp->sd_log_flush_lock);
+		if (block == BFITNOENT)
 			break;
-		no_addr = goal + rgd->rd_data0;
+		/* rgblk_search can return a block < goal, so we need to
+		   keep it marching forward. */
+		no_addr = block + rgd->rd_data0;
 		goal++;
-		if (no_addr < *last_unlinked)
+		if (*last_unlinked != NO_BLOCK && no_addr <= *last_unlinked)
 			continue;
 		*last_unlinked = no_addr;
 		inode = gfs2_inode_lookup(rgd->rd_sbd->sd_vfs, DT_UNKNOWN,
@@ -1152,7 +1161,7 @@ int gfs2_inplace_reserve_i(struct gfs2_i
 	struct gfs2_alloc *al = &ip->i_alloc;
 	struct inode *inode;
 	int error = 0;
-	u64 last_unlinked = 0;
+	u64 last_unlinked = NO_BLOCK;
 
 	if (gfs2_assert_warn(sdp, al->al_requested))
 		return -EINVAL;
@@ -1289,7 +1298,9 @@ static u32 rgblk_search(struct gfs2_rgrp
 	   allocatable block anywhere else, we want to be able wrap around and
 	   search in the first part of our first-searched bit block.  */
 	for (x = 0; x <= length; x++) {
-		if (bi->bi_clone)
+		/* The GFS2_BLKST_UNLINKED state doesn't apply to the clone
+		   bitmaps, so we must search the originals for that. */
+		if (old_state != GFS2_BLKST_UNLINKED && bi->bi_clone)
 			blk = gfs2_bitfit(rgd, bi->bi_clone + bi->bi_offset,
 					  bi->bi_len, goal, old_state);
 		else
@@ -1305,9 +1316,7 @@ static u32 rgblk_search(struct gfs2_rgrp
 		goal = 0;
 	}
 
-	if (old_state != new_state) {
-		gfs2_assert_withdraw(rgd->rd_sbd, blk != BFITNOENT);
-
+	if (blk != BFITNOENT && old_state != new_state) {
 		gfs2_trans_add_bh(rgd->rd_gl, bi->bi_bh, 1);
 		gfs2_setbit(rgd, bi->bi_bh->b_data + bi->bi_offset,
 			    bi->bi_len, blk, new_state);