[GFS2] assertion failure after writing to journaled file, umount

This patch passes all my nasty tests that were causing the code to
fail under one circumstance or another.  Here is a complete summary
of all changes from today's git tree, in order of appearance:

1. There are now separate variables for metadata buffer accounting.
2. Variable sd_log_num_hdrs is no longer needed, since the header
   accounting is taken care of by the reserve/refund sequence.
3. Fixed a tiny grammatical problem in a comment.
4. Added a new function "calc_reserved" to calculate the reserved
   log space.  This isn't entirely necessary, but it has two benefits:
   First, it simplifies the gfs2_log_refund function greatly.
   Second, it allows for easier debugging because I could sprinkle the
   code with calls to this function to make sure the accounting is
   proper (by adding asserts and printks) at strategic point of the code.
5. In log_pull_tail there apparently was a kludge to fix up the
   accounting based on a "pull" parameter.  The buffer accounting is
   now done properly, so the kludge was removed.
6. File sync operations were making a call to gfs2_log_flush that
   writes another journal header.  Since that header was unplanned
   for (reserved) by the reserve/refund sequence, the free space had
   to be decremented so that when log_pull_tail gets called, the free
   space is be adjusted properly.  (Did I hear you call that a kludge?
   well, maybe, but a lot more justifiable than the one I removed).
7. In the gfs2_log_shutdown code, it optionally syncs the log by
   specifying the PULL parameter to log_write_header.  I'm not sure
   this is necessary anymore.  It just seems to me there could be
   cases where shutdown is called while there are outstanding log
   buffers.
8. In the (data)buf_lo_before_commit functions, I changed some offset
   values from being calculated on the fly to being constants.	That
   simplified some code and we might as well let the compiler do the
   calculation once rather than redoing those cycles at run time.
9. This version has my rewritten databuf_lo_add function.
   This version is much more like its predecessor, buf_lo_add, which
   makes it easier to understand.  Again, this might not be necessary,
   but it seems as if this one works as well as the previous one,
   maybe even better, so I decided to leave it in.
10. In databuf_lo_before_commit, a previous data corruption problem
   was caused by going off the end of the buffer.  The proper solution
   is to have the proper limit in place, rather than stopping earlier.
   (Thus my previous attempt to fix it is wrong).
   If you don't wrap the buffer, you're stopping too early and that
   causes more log buffer accounting problems.
11. In lops.h there are two new (previously mentioned) constants for
   figuring out the data offset for the journal buffers.
12. There are also two new functions, buf_limit and databuf_limit to
   calculate how many entries will fit in the buffer.
13. In function gfs2_meta_wipe, it needs to distinguish between pinned
   metadata buffers and journaled data buffers for proper journal buffer
   accounting.	It can't use the JDATA gfs2_inode flag because it's
   sometimes passed the "real" inode and sometimes the "metadata
   inode" and the inode flags will be random bits in a metadata
   gfs2_inode.	It needs to base its decision on which was passed in.

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

1 files changed, 23 insertions, 30 deletions

diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index df6bceea379a..dd810ad68cf0 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -17,6 +17,7 @@
 
 #include "gfs2.h"
 #include "incore.h"
+#include "inode.h"
 #include "glock.h"
 #include "log.h"
 #include "lops.h"
@@ -117,15 +118,13 @@ static void buf_lo_before_commit(struct gfs2_sbd *sdp)
 	struct gfs2_log_descriptor *ld;
 	struct gfs2_bufdata *bd1 = NULL, *bd2;
 	unsigned int total = sdp->sd_log_num_buf;
-	unsigned int offset = sizeof(struct gfs2_log_descriptor);
+	unsigned int offset = BUF_OFFSET;
 	unsigned int limit;
 	unsigned int num;
 	unsigned n;
 	__be64 *ptr;
 
-	offset += sizeof(__be64) - 1;
-	offset &= ~(sizeof(__be64) - 1);
-	limit = (sdp->sd_sb.sb_bsize - offset)/sizeof(__be64);
+	limit = buf_limit(sdp);
 	/* for 4k blocks, limit = 503 */
 
 	bd1 = bd2 = list_prepare_entry(bd1, &sdp->sd_log_le_buf, bd_le.le_list);
@@ -134,7 +133,6 @@ static void buf_lo_before_commit(struct gfs2_sbd *sdp)
 		if (total > limit)
 			num = limit;
 		bh = gfs2_log_get_buf(sdp);
-		sdp->sd_log_num_hdrs++;
 		ld = (struct gfs2_log_descriptor *)bh->b_data;
 		ptr = (__be64 *)(bh->b_data + offset);
 		ld->ld_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
@@ -469,27 +467,26 @@ static void databuf_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
 	struct gfs2_inode *ip = GFS2_I(mapping->host);
 
 	gfs2_log_lock(sdp);
-	tr->tr_touched = 1;
-	if (list_empty(&bd->bd_list_tr) &&
-	    (ip->i_di.di_flags & GFS2_DIF_JDATA)) {
-		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 {
+	if (!list_empty(&bd->bd_list_tr)) {
 		gfs2_log_unlock(sdp);
+		return;
 	}
+	tr->tr_touched = 1;
+	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_trans_add_gl(bd->bd_gl);
-	gfs2_log_lock(sdp);
-	if (list_empty(&le->le_list)) {
-		if (ip->i_di.di_flags & GFS2_DIF_JDATA)
-			sdp->sd_log_num_jdata++;
-		sdp->sd_log_num_databuf++;
-		list_add(&le->le_list, &sdp->sd_log_le_databuf);
+	if (gfs2_is_jdata(ip)) {
+		sdp->sd_log_num_jdata++;
+		gfs2_pin(sdp, bd->bd_bh);
+		tr->tr_num_databuf_new++;
 	}
+	sdp->sd_log_num_databuf++;
+	gfs2_log_lock(sdp);
+	list_add(&le->le_list, &sdp->sd_log_le_databuf);
 	gfs2_log_unlock(sdp);
 }
 
@@ -522,7 +519,6 @@ static void databuf_lo_before_commit(struct gfs2_sbd *sdp)
 	LIST_HEAD(started);
 	struct gfs2_bufdata *bd1 = NULL, *bd2, *bdt;
 	struct buffer_head *bh = NULL,*bh1 = NULL;
-	unsigned int offset = sizeof(struct gfs2_log_descriptor);
 	struct gfs2_log_descriptor *ld;
 	unsigned int limit;
 	unsigned int total_dbuf = sdp->sd_log_num_databuf;
@@ -530,9 +526,7 @@ static void databuf_lo_before_commit(struct gfs2_sbd *sdp)
 	unsigned int num, n;
 	__be64 *ptr = NULL;
 
-	offset += 2*sizeof(__be64) - 1;
-	offset &= ~(2*sizeof(__be64) - 1);
-	limit = (sdp->sd_sb.sb_bsize - offset)/sizeof(__be64);
+	limit = databuf_limit(sdp);
 
 	/*
 	 * Start writing ordered buffers, write journaled buffers
@@ -583,10 +577,10 @@ static void databuf_lo_before_commit(struct gfs2_sbd *sdp)
 				gfs2_log_unlock(sdp);
 				if (!bh) {
 					bh = gfs2_log_get_buf(sdp);
-					sdp->sd_log_num_hdrs++;
 					ld = (struct gfs2_log_descriptor *)
 					     bh->b_data;
-					ptr = (__be64 *)(bh->b_data + offset);
+					ptr = (__be64 *)(bh->b_data +
+							 DATABUF_OFFSET);
 					ld->ld_header.mh_magic =
 						cpu_to_be32(GFS2_MAGIC);
 					ld->ld_header.mh_type =
@@ -607,8 +601,7 @@ static void databuf_lo_before_commit(struct gfs2_sbd *sdp)
 				if (unlikely(magic != 0))
 					set_buffer_escaped(bh1);
 				gfs2_log_lock(sdp);
-				n += 2;
-				if (n >= num)
+				if (++n >= num)
 					break;
 			} else if (!bh1) {
 				total_dbuf--;