From: Steven Whitehouse <swhiteho@redhat.com>
Subject: [RHEL 5.1] [GFS2] Journaled data issues (bz #238162)
Date: Wed, 13 Jun 2007 14:10:23 +0100
Bugzilla: 238162
Message-Id: <1181740223.8765.10.camel@quoit>
Changelog: [GFS2] Journaled data issues


Hi,

This patch resolves the outstanding issues relating to journaled data
files in GFS2. Its a combination of two upstream patches which have been
tested to ensure that they fix the various issues of bz #238162.

One issue is a counter whose increment is incorrect resulting in an
overrun of a block in some circumstances. Another is that certain
structures containing journal state were potentially getting added to a
list twice, potentially corrupting the list. Another was attempting to
write journal headers into blocks which were not mapped at the time. A
further issue was journaled data buffers getting lost on umount in
certain cases.

The patch adds some new #defines to page-flags.h. These are taken from
the upstream kernel and shouldn't affect any other code.

Steve.

-------------------------------------------------------------------------------
diff -Nru linux-rhel-base/fs/gfs2/log.c linux-2.6.18.noarch/fs/gfs2/log.c
--- linux-rhel-base/fs/gfs2/log.c	2007-06-13 10:30:16.000000000 +0100
+++ linux-2.6.18.noarch/fs/gfs2/log.c	2007-06-13 10:45:26.000000000 +0100
@@ -83,6 +83,11 @@
 
 			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);
@@ -125,6 +130,11 @@
 					 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)) {
@@ -227,7 +237,10 @@
 		list_del(&bd->bd_ail_st_list);
 		list_del(&bd->bd_ail_gl_list);
 		atomic_dec(&bd->bd_gl->gl_ail_count);
-		brelse(bd->bd_bh);
+		if (bd->bd_bh)
+			brelse(bd->bd_bh);
+		else
+			kmem_cache_free(gfs2_bufdata_cachep, bd);
 	}
 }
 
@@ -565,7 +578,7 @@
 	INIT_LIST_HEAD(&ai->ai_ail1_list);
 	INIT_LIST_HEAD(&ai->ai_ail2_list);
 
-	gfs2_assert_withdraw(sdp, sdp->sd_log_num_buf == sdp->sd_log_commited_buf);
+	gfs2_assert_withdraw(sdp, sdp->sd_log_num_buf + sdp->sd_log_num_jdata == sdp->sd_log_commited_buf);
 	gfs2_assert_withdraw(sdp,
 			sdp->sd_log_num_revoke == sdp->sd_log_commited_revoke);
 
diff -Nru linux-rhel-base/fs/gfs2/lops.c linux-2.6.18.noarch/fs/gfs2/lops.c
--- linux-rhel-base/fs/gfs2/lops.c	2007-06-13 10:30:16.000000000 +0100
+++ linux-2.6.18.noarch/fs/gfs2/lops.c	2007-06-13 10:45:26.000000000 +0100
@@ -475,6 +475,8 @@
 		tr->tr_num_buf++;
 		list_add(&bd->bd_list_tr, &tr->tr_list_buf);
 		gfs2_log_unlock(sdp);
+		if (!list_empty(&le->le_list))
+			return;
 		gfs2_pin(sdp, bd->bd_bh);
 		tr->tr_num_buf_new++;
 	} else {
@@ -605,7 +607,8 @@
 				if (unlikely(magic != 0))
 					set_buffer_escaped(bh1);
 				gfs2_log_lock(sdp);
-				if (n++ > num)
+				n += 2;
+				if (n >= num)
 					break;
 			} else if (!bh1) {
 				total_dbuf--;
@@ -622,6 +625,7 @@
 		}
 		gfs2_log_unlock(sdp);
 		if (bh) {
+			set_buffer_mapped(bh);
 			set_buffer_dirty(bh);
 			ll_rw_block(WRITE, 1, &bh);
 			bh = NULL;
diff -Nru linux-rhel-base/fs/gfs2/ops_address.c linux-2.6.18.noarch/fs/gfs2/ops_address.c
--- linux-rhel-base/fs/gfs2/ops_address.c	2007-06-13 10:30:18.000000000 +0100
+++ linux-2.6.18.noarch/fs/gfs2/ops_address.c	2007-06-13 10:45:26.000000000 +0100
@@ -50,6 +50,8 @@
 		end = start + bsize;
 		if (end <= from || start >= to)
 			continue;
+		if (gfs2_is_jdata(ip))
+			set_buffer_uptodate(bh);
 		gfs2_trans_add_bh(ip->i_gl, bh, 0);
 	}
 }
@@ -135,7 +137,9 @@
 		return 0; /* don't care */
 	}
 
-	if (sdp->sd_args.ar_data == GFS2_DATA_ORDERED || gfs2_is_jdata(ip)) {
+	if ((sdp->sd_args.ar_data == GFS2_DATA_ORDERED || gfs2_is_jdata(ip)) &&
+	    PageChecked(page)) {
+		ClearPageChecked(page);
 		error = gfs2_trans_begin(sdp, RES_DINODE + 1, 0);
 		if (error)
 			goto out_ignore;
@@ -582,6 +586,23 @@
 }
 
 /**
+ * gfs2_set_page_dirty - Page dirtying function
+ * @page: The page to dirty
+ *
+ * Returns: 1 if it dirtyed the page, or 0 otherwise
+ */
+ 
+static int gfs2_set_page_dirty(struct page *page)
+{
+	struct gfs2_inode *ip = GFS2_I(page->mapping->host);
+	struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
+
+	if (sdp->sd_args.ar_data == GFS2_DATA_ORDERED || gfs2_is_jdata(ip))
+		SetPageChecked(page);
+	return __set_page_dirty_buffers(page);
+}
+
+/**
  * gfs2_bmap - Block map function
  * @mapping: Address space info
  * @lblock: The block to map
@@ -617,6 +638,8 @@
 	if (bd) {
 		bd->bd_bh = NULL;
 		bh->b_private = NULL;
+		if (!bd->bd_ail && list_empty(&bd->bd_le.le_list))
+			kmem_cache_free(gfs2_bufdata_cachep, bd);
 	}
 	gfs2_log_unlock(sdp);
 
@@ -637,6 +660,8 @@
 	unsigned int curr_off = 0;
 
 	BUG_ON(!PageLocked(page));
+	if (offset == 0)
+		ClearPageChecked(page);
 	if (!page_has_buffers(page))
 		return;
 
@@ -849,6 +874,7 @@
 	.sync_page = block_sync_page,
 	.prepare_write = gfs2_prepare_write,
 	.commit_write = gfs2_commit_write,
+	.set_page_dirty = gfs2_set_page_dirty,
 	.bmap = gfs2_bmap,
 	.invalidatepage = gfs2_invalidatepage,
 	.releasepage = gfs2_releasepage,
diff -Nru linux-rhel-base/include/linux/page-flags.h linux-2.6.18.noarch/include/linux/page-flags.h
--- linux-rhel-base/include/linux/page-flags.h	2007-06-13 10:30:11.000000000 +0100
+++ linux-2.6.18.noarch/include/linux/page-flags.h	2007-06-13 13:59:04.000000000 +0100
@@ -72,6 +72,7 @@
 #define PG_slab			 7	/* slab debug (Suparna wants this) */
 
 #define PG_fs_misc		 8
+#define PG_owner_priv_1          8      /* Owner use. If pagecache, fs may use*/
 #define PG_arch_1		 9
 #define PG_reserved		10
 #define PG_private		11	/* Has something at ->private */
@@ -86,6 +87,8 @@
 #define PG_nosave_free		18	/* Free, should not be written */
 #define PG_buddy		19	/* Page is free, on buddy lists */
 
+/* PG_owner_priv_1 users should have descriptive aliases */
+#define PG_checked              PG_owner_priv_1 /* Used by some filesystems */
 
 #if (BITS_PER_LONG > 32)
 /*
@@ -161,6 +164,10 @@
 #define PageHighMem(page)	0 /* needed to optimize away at compile time */
 #endif
 
+#define PageChecked(page)       test_bit(PG_checked, &(page)->flags)
+#define SetPageChecked(page)    set_bit(PG_checked, &(page)->flags)
+#define ClearPageChecked(page)  clear_bit(PG_checked, &(page)->flags)
+
 #define PageReserved(page)	test_bit(PG_reserved, &(page)->flags)
 #define SetPageReserved(page)	set_bit(PG_reserved, &(page)->flags)
 #define ClearPageReserved(page)	clear_bit(PG_reserved, &(page)->flags)