Merge git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-3.0-nmw

Pull GFS2 changes from Steven Whitehouse.

* git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-3.0-nmw: (24 commits)
  GFS2: Fix quota adjustment return code
  GFS2: Add rgrp information to block_alloc trace point
  GFS2: Eliminate unused "new" parameter to gfs2_meta_indirect_buffer
  GFS2: Update glock doc to add new stats info
  GFS2: Update main gfs2 doc
  GFS2: Remove redundant metadata block type check
  GFS2: Fix sgid propagation when using ACLs
  GFS2: eliminate log elements and simplify
  GFS2: Eliminate vestigial sd_log_le_rg
  GFS2: Eliminate needless parameter from function gfs2_setbit
  GFS2: Log code fixes
  GFS2: Remove unused argument from gfs2_internal_read
  GFS2: Remove bd_list_tr
  GFS2: Remove duplicate log code
  GFS2: Clean up log write code path
  GFS2: Use variable rather than qa to determine if unstuff necessary
  GFS2: Change variable blk to biblk
  GFS2: Fix function parameter comments in rgrp.c
  GFS2: Eliminate offset parameter to gfs2_setbit
  GFS2: Use slab for block reservation memory
  ...

23 files changed, 588 insertions, 499 deletions

diff --git a/Documentation/filesystems/gfs2-glocks.txt b/Documentation/filesystems/gfs2-glocks.txt
index 0494f78d87e..fcc79957be6 100644
--- a/Documentation/filesystems/gfs2-glocks.txt
+++ b/Documentation/filesystems/gfs2-glocks.txt
@@ -61,7 +61,9 @@ go_unlock        | Called on the final local unlock of a lock
 go_dump          | Called to print content of object for debugfs file, or on
                  | error to dump glock to the log.
 go_type          | The type of the glock, LM_TYPE_.....
-go_min_hold_time | The minimum hold time
+go_callback	 | Called if the DLM sends a callback to drop this lock
+go_flags	 | GLOF_ASPACE is set, if the glock has an address space
+                 | associated with it
 
 The minimum hold time for each lock is the time after a remote lock
 grant for which we ignore remote demote requests. This is in order to
@@ -89,6 +91,7 @@ go_demote_ok  |       Sometimes         |       Yes
 go_lock       |       Yes               |       No
 go_unlock     |       Yes               |       No
 go_dump       |       Sometimes         |       Yes
+go_callback   |       Sometimes (N/A)   |       Yes
 
 N.B. Operations must not drop either the bit lock or the spinlock
 if its held on entry. go_dump and do_demote_ok must never block.
@@ -111,4 +114,118 @@ itself (locking order as above), and the other, known as the iopen
 glock is used in conjunction with the i_nlink field in the inode to
 determine the lifetime of the inode in question. Locking of inodes
 is on a per-inode basis. Locking of rgrps is on a per rgrp basis.
+In general we prefer to lock local locks prior to cluster locks.
+
+                            Glock Statistics
+                           ------------------
+
+The stats are divided into two sets: those relating to the
+super block and those relating to an individual glock. The
+super block stats are done on a per cpu basis in order to
+try and reduce the overhead of gathering them. They are also
+further divided by glock type. All timings are in nanoseconds.
+
+In the case of both the super block and glock statistics,
+the same information is gathered in each case. The super
+block timing statistics are used to provide default values for
+the glock timing statistics, so that newly created glocks
+should have, as far as possible, a sensible starting point.
+The per-glock counters are initialised to zero when the
+glock is created. The per-glock statistics are lost when
+the glock is ejected from memory.
+
+The statistics are divided into three pairs of mean and
+variance, plus two counters. The mean/variance pairs are
+smoothed exponential estimates and the algorithm used is
+one which will be very familiar to those used to calculation
+of round trip times in network code. See "TCP/IP Illustrated,
+Volume 1", W. Richard Stevens, sect 21.3, "Round-Trip Time Measurement",
+p. 299 and onwards. Also, Volume 2, Sect. 25.10, p. 838 and onwards.
+Unlike the TCP/IP Illustrated case, the mean and variance are
+not scaled, but are in units of integer nanoseconds.
+
+The three pairs of mean/variance measure the following
+things:
+
+ 1. DLM lock time (non-blocking requests)
+ 2. DLM lock time (blocking requests)
+ 3. Inter-request time (again to the DLM)
+
+A non-blocking request is one which will complete right
+away, whatever the state of the DLM lock in question. That
+currently means any requests when (a) the current state of
+the lock is exclusive, i.e. a lock demotion (b) the requested
+state is either null or unlocked (again, a demotion) or (c) the
+"try lock" flag is set. A blocking request covers all the other
+lock requests.
+
+There are two counters. The first is there primarily to show
+how many lock requests have been made, and thus how much data
+has gone into the mean/variance calculations. The other counter
+is counting queuing of holders at the top layer of the glock
+code. Hopefully that number will be a lot larger than the number
+of dlm lock requests issued.
+
+So why gather these statistics? There are several reasons
+we'd like to get a better idea of these timings:
+
+1. To be able to better set the glock "min hold time"
+2. To spot performance issues more easily
+3. To improve the algorithm for selecting resource groups for
+allocation (to base it on lock wait time, rather than blindly
+using a "try lock")
+
+Due to the smoothing action of the updates, a step change in
+some input quantity being sampled will only fully be taken
+into account after 8 samples (or 4 for the variance) and this
+needs to be carefully considered when interpreting the
+results.
+
+Knowing both the time it takes a lock request to complete and
+the average time between lock requests for a glock means we
+can compute the total percentage of the time for which the
+node is able to use a glock vs. time that the rest of the
+cluster has its share. That will be very useful when setting
+the lock min hold time.
+
+Great care has been taken to ensure that we
+measure exactly the quantities that we want, as accurately
+as possible. There are always inaccuracies in any
+measuring system, but I hope this is as accurate as we
+can reasonably make it.
+
+Per sb stats can be found here:
+/sys/kernel/debug/gfs2/<fsname>/sbstats
+Per glock stats can be found here:
+/sys/kernel/debug/gfs2/<fsname>/glstats
+
+Assuming that debugfs is mounted on /sys/kernel/debug and also
+that <fsname> is replaced with the name of the gfs2 filesystem
+in question.
+
+The abbreviations used in the output as are follows:
+
+srtt     - Smoothed round trip time for non-blocking dlm requests
+srttvar  - Variance estimate for srtt
+srttb    - Smoothed round trip time for (potentially) blocking dlm requests
+srttvarb - Variance estimate for srttb
+sirt     - Smoothed inter-request time (for dlm requests)
+sirtvar  - Variance estimate for sirt
+dlm      - Number of dlm requests made (dcnt in glstats file)
+queue    - Number of glock requests queued (qcnt in glstats file)
+
+The sbstats file contains a set of these stats for each glock type (so 8 lines
+for each type) and for each cpu (one column per cpu). The glstats file contains
+a set of these stats for each glock in a similar format to the glocks file, but
+using the format mean/variance for each of the timing stats.
+
+The gfs2_glock_lock_time tracepoint prints out the current values of the stats
+for the glock in question, along with some addition information on each dlm
+reply that is received:
+
+status - The status of the dlm request
+flags  - The dlm request flags
+tdiff  - The time taken by this specific request
+(remaining fields as per above list)
+
 
diff --git a/Documentation/filesystems/gfs2.txt b/Documentation/filesystems/gfs2.txt
index 4cda926628a..cc4f2306609 100644
--- a/Documentation/filesystems/gfs2.txt
+++ b/Documentation/filesystems/gfs2.txt
@@ -1,7 +1,7 @@
 Global File System
 ------------------
 
-http://sources.redhat.com/cluster/wiki/
+https://fedorahosted.org/cluster/wiki/HomePage
 
 GFS is a cluster file system. It allows a cluster of computers to
 simultaneously use a block device that is shared between them (with FC,
@@ -30,7 +30,8 @@ needed, simply:
 
 If you are using Fedora, you need to install the gfs2-utils package
 and, for lock_dlm, you will also need to install the cman package
-and write a cluster.conf as per the documentation.
+and write a cluster.conf as per the documentation. For F17 and above
+cman has been replaced by the dlm package.
 
 GFS2 is not on-disk compatible with previous versions of GFS, but it
 is pretty close.
@@ -39,8 +40,6 @@ The following man pages can be found at the URL above:
   fsck.gfs2		to repair a filesystem
   gfs2_grow		to expand a filesystem online
   gfs2_jadd		to add journals to a filesystem online
-  gfs2_tool		to manipulate, examine and tune a filesystem
-  gfs2_quota	to examine and change quota values in a filesystem
+  tunegfs2		to manipulate, examine and tune a filesystem
   gfs2_convert	to convert a gfs filesystem to gfs2 in-place
-  mount.gfs2	to help mount(8) mount a filesystem
   mkfs.gfs2		to make a filesystem
diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c
index 230eb0f005b..bd4a5892c93 100644
--- a/fs/gfs2/acl.c
+++ b/fs/gfs2/acl.c
@@ -73,12 +73,8 @@ static int gfs2_set_mode(struct inode *inode, umode_t mode)
 	int error = 0;
 
 	if (mode != inode->i_mode) {
-		struct iattr iattr;
-
-		iattr.ia_valid = ATTR_MODE;
-		iattr.ia_mode = mode;
-
-		error = gfs2_setattr_simple(inode, &iattr);
+		inode->i_mode = mode;
+		mark_inode_dirty(inode);
 	}
 
 	return error;
@@ -126,9 +122,7 @@ int gfs2_acl_create(struct gfs2_inode *dip, struct inode *inode)
 		return PTR_ERR(acl);
 	if (!acl) {
 		mode &= ~current_umask();
-		if (mode != inode->i_mode)
-			error = gfs2_set_mode(inode, mode);
-		return error;
+		return gfs2_set_mode(inode, mode);
 	}
 
 	if (S_ISDIR(inode->i_mode)) {
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 9b2ff0e851b..e80a464850c 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -36,8 +36,8 @@
 #include "glops.h"
 
 
-void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page,
-			    unsigned int from, unsigned int to)
+static void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page,
+				   unsigned int from, unsigned int to)
 {
 	struct buffer_head *head = page_buffers(page);
 	unsigned int bsize = head->b_size;
@@ -517,15 +517,14 @@ out:
 /**
  * gfs2_internal_read - read an internal file
  * @ip: The gfs2 inode
- * @ra_state: The readahead state (or NULL for no readahead)
  * @buf: The buffer to fill
  * @pos: The file position
  * @size: The amount to read
  *
  */
 
-int gfs2_internal_read(struct gfs2_inode *ip, struct file_ra_state *ra_state,
-                       char *buf, loff_t *pos, unsigned size)
+int gfs2_internal_read(struct gfs2_inode *ip, char *buf, loff_t *pos,
+                       unsigned size)
 {
 	struct address_space *mapping = ip->i_inode.i_mapping;
 	unsigned long index = *pos / PAGE_CACHE_SIZE;
@@ -943,8 +942,8 @@ static void gfs2_discard(struct gfs2_sbd *sdp, struct buffer_head *bh)
 	clear_buffer_dirty(bh);
 	bd = bh->b_private;
 	if (bd) {
-		if (!list_empty(&bd->bd_le.le_list) && !buffer_pinned(bh))
-			list_del_init(&bd->bd_le.le_list);
+		if (!list_empty(&bd->bd_list) && !buffer_pinned(bh))
+			list_del_init(&bd->bd_list);
 		else
 			gfs2_remove_from_journal(bh, current->journal_info, 0);
 	}
@@ -1084,10 +1083,9 @@ int gfs2_releasepage(struct page *page, gfp_t gfp_mask)
 		bd = bh->b_private;
 		if (bd) {
 			gfs2_assert_warn(sdp, bd->bd_bh == bh);
-			gfs2_assert_warn(sdp, list_empty(&bd->bd_list_tr));
-			if (!list_empty(&bd->bd_le.le_list)) {
+			if (!list_empty(&bd->bd_list)) {
 				if (!buffer_pinned(bh))
-					list_del_init(&bd->bd_le.le_list);
+					list_del_init(&bd->bd_list);
 				else
 					bd = NULL;
 			}
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 03c04febe26..dab54099dd9 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -324,7 +324,7 @@ static int lookup_metapath(struct gfs2_inode *ip, struct metapath *mp)
 		if (!dblock)
 			return x + 1;
 
-		ret = gfs2_meta_indirect_buffer(ip, x+1, dblock, 0, &mp->mp_bh[x+1]);
+		ret = gfs2_meta_indirect_buffer(ip, x+1, dblock, &mp->mp_bh[x+1]);
 		if (ret)
 			return ret;
 	}
@@ -882,7 +882,7 @@ static int recursive_scan(struct gfs2_inode *ip, struct buffer_head *dibh,
 		top = (__be64 *)(bh->b_data + sizeof(struct gfs2_dinode)) + mp->mp_list[0];
 		bottom = (__be64 *)(bh->b_data + sizeof(struct gfs2_dinode)) + sdp->sd_diptrs;
 	} else {
-		error = gfs2_meta_indirect_buffer(ip, height, block, 0, &bh);
+		error = gfs2_meta_indirect_buffer(ip, height, block, &bh);
 		if (error)
 			return error;
 
@@ -1169,6 +1169,7 @@ static int do_grow(struct inode *inode, u64 size)
 	struct buffer_head *dibh;
 	struct gfs2_qadata *qa = NULL;
 	int error;
+	int unstuff = 0;
 
 	if (gfs2_is_stuffed(ip) &&
 	    (size > (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode)))) {
@@ -1183,13 +1184,14 @@ static int do_grow(struct inode *inode, u64 size)
 		error = gfs2_inplace_reserve(ip, 1);
 		if (error)
 			goto do_grow_qunlock;
+		unstuff = 1;
 	}
 
 	error = gfs2_trans_begin(sdp, RES_DINODE + RES_STATFS + RES_RG_BIT, 0);
 	if (error)
 		goto do_grow_release;
 
-	if (qa) {
+	if (unstuff) {
 		error = gfs2_unstuff_dinode(ip, NULL);
 		if (error)
 			goto do_end_trans;
@@ -1208,7 +1210,7 @@ static int do_grow(struct inode *inode, u64 size)
 do_end_trans:
 	gfs2_trans_end(sdp);
 do_grow_release:
-	if (qa) {
+	if (unstuff) {
 		gfs2_inplace_release(ip);
 do_grow_qunlock:
 		gfs2_quota_unlock(ip);
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index a3d2c9ee8d6..31b199f6efc 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -558,14 +558,14 @@ fail:
 }
 
 /**
- * gfs2_close - called to close a struct file
+ * gfs2_release - called to close a struct file
  * @inode: the inode the struct file belongs to
  * @file: the struct file being closed
  *
  * Returns: errno
  */
 
-static int gfs2_close(struct inode *inode, struct file *file)
+static int gfs2_release(struct inode *inode, struct file *file)
 {
 	struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
 	struct gfs2_file *fp;
@@ -1005,7 +1005,7 @@ const struct file_operations gfs2_file_fops = {
 	.unlocked_ioctl	= gfs2_ioctl,
 	.mmap		= gfs2_mmap,
 	.open		= gfs2_open,
-	.release	= gfs2_close,
+	.release	= gfs2_release,
 	.fsync		= gfs2_fsync,
 	.lock		= gfs2_lock,
 	.flock		= gfs2_flock,
@@ -1019,7 +1019,7 @@ const struct file_operations gfs2_dir_fops = {
 	.readdir	= gfs2_readdir,
 	.unlocked_ioctl	= gfs2_ioctl,
 	.open		= gfs2_open,
-	.release	= gfs2_close,
+	.release	= gfs2_release,
 	.fsync		= gfs2_fsync,
 	.lock		= gfs2_lock,
 	.flock		= gfs2_flock,
@@ -1037,7 +1037,7 @@ const struct file_operations gfs2_file_fops_nolock = {
 	.unlocked_ioctl	= gfs2_ioctl,
 	.mmap		= gfs2_mmap,
 	.open		= gfs2_open,
-	.release	= gfs2_close,
+	.release	= gfs2_release,
 	.fsync		= gfs2_fsync,
 	.splice_read	= generic_file_splice_read,
 	.splice_write	= generic_file_splice_write,
@@ -1049,7 +1049,7 @@ const struct file_operations gfs2_dir_fops_nolock = {
 	.readdir	= gfs2_readdir,
 	.unlocked_ioctl	= gfs2_ioctl,
 	.open		= gfs2_open,
-	.release	= gfs2_close,
+	.release	= gfs2_release,
 	.fsync		= gfs2_fsync,
 	.llseek		= default_llseek,
 };
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 1656df7aacd..4bdcf378418 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -94,7 +94,6 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
 	/* A shortened, inline version of gfs2_trans_begin() */
 	tr.tr_reserved = 1 + gfs2_struct2blk(sdp, tr.tr_revokes, sizeof(u64));
 	tr.tr_ip = (unsigned long)__builtin_return_address(0);
-	INIT_LIST_HEAD(&tr.tr_list_buf);
 	gfs2_log_reserve(sdp, tr.tr_reserved);
 	BUG_ON(current->journal_info);
 	current->journal_info = &tr;
@@ -379,11 +378,6 @@ int gfs2_inode_refresh(struct gfs2_inode *ip)
 	if (error)
 		return error;
 
-	if (gfs2_metatype_check(GFS2_SB(&ip->i_inode), dibh, GFS2_METATYPE_DI)) {
-		brelse(dibh);
-		return -EIO;
-	}
-
 	error = gfs2_dinode_in(ip, dibh->b_data);
 	brelse(dibh);
 	clear_bit(GIF_INVALID, &ip->i_flags);
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 47d0bda5ac2..aa9949e5de2 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -26,7 +26,7 @@
 #define DIO_METADATA	0x00000020
 
 struct gfs2_log_operations;
-struct gfs2_log_element;
+struct gfs2_bufdata;
 struct gfs2_holder;
 struct gfs2_glock;
 struct gfs2_quota_data;
@@ -52,7 +52,7 @@ struct gfs2_log_header_host {
  */
 
 struct gfs2_log_operations {
-	void (*lo_add) (struct gfs2_sbd *sdp, struct gfs2_log_element *le);
+	void (*lo_add) (struct gfs2_sbd *sdp, struct gfs2_bufdata *bd);
 	void (*lo_before_commit) (struct gfs2_sbd *sdp);
 	void (*lo_after_commit) (struct gfs2_sbd *sdp, struct gfs2_ail *ai);
 	void (*lo_before_scan) (struct gfs2_jdesc *jd,
@@ -64,11 +64,6 @@ struct gfs2_log_operations {
 	const char *lo_name;
 };
 
-struct gfs2_log_element {
-	struct list_head le_list;
-	const struct gfs2_log_operations *le_ops;
-};
-
 #define GBF_FULL 1
 
 struct gfs2_bitmap {
@@ -118,15 +113,10 @@ TAS_BUFFER_FNS(Zeronew, zeronew)
 struct gfs2_bufdata {
 	struct buffer_head *bd_bh;
 	struct gfs2_glock *bd_gl;
+	u64 bd_blkno;
 
-	union {
-		struct list_head list_tr;
-		u64 blkno;
-	} u;
-#define bd_list_tr u.list_tr
-#define bd_blkno u.blkno
-
-	struct gfs2_log_element bd_le;
+	struct list_head bd_list;
+	const struct gfs2_log_operations *bd_ops;
 
 	struct gfs2_ail *bd_ail;
 	struct list_head bd_ail_st_list;
@@ -411,13 +401,10 @@ struct gfs2_trans {
 
 	int tr_touched;
 
-	unsigned int tr_num_buf;
 	unsigned int tr_num_buf_new;
 	unsigned int tr_num_databuf_new;
 	unsigned int tr_num_buf_rm;
 	unsigned int tr_num_databuf_rm;
-	struct list_head tr_list_buf;
-
 	unsigned int tr_num_revoke;
 	unsigned int tr_num_revoke_rm;
 };
@@ -699,7 +686,6 @@ struct gfs2_sbd {
 
 	struct list_head sd_log_le_buf;
 	struct list_head sd_log_le_revoke;
-	struct list_head sd_log_le_rg;
 	struct list_head sd_log_le_databuf;
 	struct list_head sd_log_le_ordered;
 
@@ -716,7 +702,9 @@ struct gfs2_sbd {
 
 	struct rw_semaphore sd_log_flush_lock;
 	atomic_t sd_log_in_flight;
+	struct bio *sd_log_bio;
 	wait_queue_head_t sd_log_flush_wait;
+	int sd_log_error;
 
 	unsigned int sd_log_flush_head;
 	u64 sd_log_flush_wrapped;
diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h
index 276e7b52b65..c53c7477f6d 100644
--- a/fs/gfs2/inode.h
+++ b/fs/gfs2/inode.h
@@ -17,10 +17,7 @@
 
 extern int gfs2_releasepage(struct page *page, gfp_t gfp_mask);
 extern int gfs2_internal_read(struct gfs2_inode *ip,
-			      struct file_ra_state *ra_state,
 			      char *buf, loff_t *pos, unsigned size);
-extern void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page,
-				   unsigned int from, unsigned int to);
 extern void gfs2_set_aops(struct inode *inode);
 
 static inline int gfs2_is_stuffed(const struct gfs2_inode *ip)
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 4752eadc7f6..f4beeb9c81c 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -32,8 +32,6 @@
 #include "dir.h"
 #include "trace_gfs2.h"
 
-#define PULL 1
-
 /**
  * gfs2_struct2blk - compute stuff
  * @sdp: the filesystem
@@ -359,18 +357,6 @@ retry:
 	return 0;
 }
 
-u64 gfs2_log_bmap(struct gfs2_sbd *sdp, unsigned int lbn)
-{
-	struct gfs2_journal_extent *je;
-
-	list_for_each_entry(je, &sdp->sd_jdesc->extent_list, extent_list) {
-		if (lbn >= je->lblock && lbn < je->lblock + je->blocks)
-			return je->dblock + lbn - je->lblock;
-	}
-
-	return -1;
-}
-
 /**
  * log_distance - Compute distance between two journal blocks
  * @sdp: The GFS2 superblock
@@ -466,17 +452,6 @@ static unsigned int current_tail(struct gfs2_sbd *sdp)
 	return tail;
 }
 
-void gfs2_log_incr_head(struct gfs2_sbd *sdp)
-{
-	BUG_ON((sdp->sd_log_flush_head == sdp->sd_log_tail) &&
-	       (sdp->sd_log_flush_head != sdp->sd_log_head));
-
-	if (++sdp->sd_log_flush_head == sdp->sd_jdesc->jd_blocks) {
-		sdp->sd_log_flush_head = 0;
-		sdp->sd_log_flush_wrapped = 1;
-	}
-}
-
 static void log_pull_tail(struct gfs2_sbd *sdp, unsigned int new_tail)
 {
 	unsigned int dist = log_distance(sdp, new_tail, sdp->sd_log_tail);
@@ -511,8 +486,8 @@ static int bd_cmp(void *priv, struct list_head *a, struct list_head *b)
 {
 	struct gfs2_bufdata *bda, *bdb;
 
-	bda = list_entry(a, struct gfs2_bufdata, bd_le.le_list);
-	bdb = list_entry(b, struct gfs2_bufdata, bd_le.le_list);
+	bda = list_entry(a, struct gfs2_bufdata, bd_list);
+	bdb = list_entry(b, struct gfs2_bufdata, bd_list);
 
 	if (bda->bd_bh->b_blocknr < bdb->bd_bh->b_blocknr)
 		return -1;
@@ -530,8 +505,8 @@ static void gfs2_ordered_write(struct gfs2_sbd *sdp)
 	gfs2_log_lock(sdp);
 	list_sort(NULL, &sdp->sd_log_le_ordered, &bd_cmp);
 	while (!list_empty(&sdp->sd_log_le_ordered)) {
-		bd = list_entry(sdp->sd_log_le_ordered.next, struct gfs2_bufdata, bd_le.le_list);
-		list_move(&bd->bd_le.le_list, &written);
+		bd = list_entry(sdp->sd_log_le_ordered.next, struct gfs2_bufdata, bd_list);
+		list_move(&bd->bd_list, &written);
 		bh = bd->bd_bh;
 		if (!buffer_dirty(bh))
 			continue;
@@ -558,7 +533,7 @@ static void gfs2_ordered_wait(struct gfs2_sbd *sdp)
 
 	gfs2_log_lock(sdp);
 	while (!list_empty(&sdp->sd_log_le_ordered)) {
-		bd = list_entry(sdp->sd_log_le_ordered.prev, struct gfs2_bufdata, bd_le.le_list);
+		bd = list_entry(sdp->sd_log_le_ordered.prev, struct gfs2_bufdata, bd_list);
 		bh = bd->bd_bh;
 		if (buffer_locked(bh)) {
 			get_bh(bh);
@@ -568,7 +543,7 @@ static void gfs2_ordered_wait(struct gfs2_sbd *sdp)
 			gfs2_log_lock(sdp);
 			continue;
 		}
-		list_del_init(&bd->bd_le.le_list);
+		list_del_init(&bd->bd_list);
 	}
 	gfs2_log_unlock(sdp);
 }
@@ -580,25 +555,19 @@ static void gfs2_ordered_wait(struct gfs2_sbd *sdp)
  * Returns: the initialized log buffer descriptor
  */
 
-static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull)
+static void log_write_header(struct gfs2_sbd *sdp, u32 flags)
 {
-	u64 blkno = gfs2_log_bmap(sdp, sdp->sd_log_flush_head);
-	struct buffer_head *bh;
 	struct gfs2_log_header *lh;
 	unsigned int tail;
 	u32 hash;
-
-	bh = sb_getblk(sdp->sd_vfs, blkno);
-	lock_buffer(bh);
-	memset(bh->b_data, 0, bh->b_size);
-	set_buffer_uptodate(bh);
-	clear_buffer_dirty(bh);
+	int rw = WRITE_FLUSH_FUA | REQ_META;
+	struct page *page = mempool_alloc(gfs2_page_pool, GFP_NOIO);
+	lh = page_address(page);
+	clear_page(lh);
 
 	gfs2_ail1_empty(sdp);
 	tail = current_tail(sdp);
 
-	lh = (struct gfs2_log_header *)bh->b_data;
-	memset(lh, 0, sizeof(struct gfs2_log_header));
 	lh->lh_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
 	lh->lh_header.mh_type = cpu_to_be32(GFS2_METATYPE_LH);
 	lh->lh_header.__pad0 = cpu_to_be64(0);
@@ -608,31 +577,22 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull)
 	lh->lh_flags = cpu_to_be32(flags);
 	lh->lh_tail = cpu_to_be32(tail);
 	lh->lh_blkno = cpu_to_be32(sdp->sd_log_flush_head);
-	hash = gfs2_disk_hash(bh->b_data, sizeof(struct gfs2_log_header));
+	hash = gfs2_disk_hash(page_address(page), sizeof(struct gfs2_log_header));
 	lh->lh_hash = cpu_to_be32(hash);
 
-	bh->b_end_io = end_buffer_write_sync;
-	get_bh(bh);
 	if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags)) {
 		gfs2_ordered_wait(sdp);
 		log_flush_wait(sdp);
-		submit_bh(WRITE_SYNC | REQ_META | REQ_PRIO, bh);
-	} else {
-		submit_bh(WRITE_FLUSH_FUA | REQ_META, bh);
+		rw = WRITE_SYNC | REQ_META | REQ_PRIO;
 	}
-	wait_on_buffer(bh);
 
-	if (!buffer_uptodate(bh))
-		gfs2_io_error_bh(sdp, bh);
-	brelse(bh);
+	sdp->sd_log_idle = (tail == sdp->sd_log_flush_head);
+	gfs2_log_write_page(sdp, page);
+	gfs2_log_flush_bio(sdp, rw);
+	log_flush_wait(sdp);
 
 	if (sdp->sd_log_tail != tail)
 		log_pull_tail(sdp, tail);
-	else
-		gfs2_assert_withdraw(sdp, !pull);
-
-	sdp->sd_log_idle = (tail == sdp->sd_log_flush_head);
-	gfs2_log_incr_head(sdp);
 }
 
 /**
@@ -678,15 +638,14 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
 
 	gfs2_ordered_write(sdp);
 	lops_before_commit(sdp);
+	gfs2_log_flush_bio(sdp, WRITE);
 
 	if (sdp->sd_log_head != sdp->sd_log_flush_head) {
-		log_write_header(sdp, 0, 0);
+		log_write_header(sdp, 0);
 	} else if (sdp->sd_log_tail != current_tail(sdp) && !sdp->sd_log_idle){
-		gfs2_log_lock(sdp);
 		atomic_dec(&sdp->sd_log_blks_free); /* Adjust for unreserved buffer */
 		trace_gfs2_log_blocks(sdp, -1);
-		gfs2_log_unlock(sdp);
-		log_write_header(sdp, 0, PULL);
+		log_write_header(sdp, 0);
 	}
 	lops_after_commit(sdp, ai);
 
@@ -735,21 +694,6 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 	gfs2_log_unlock(sdp);
 }
 
-static void buf_lo_incore_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
-{
-	struct list_head *head = &tr->tr_list_buf;
-	struct gfs2_bufdata *bd;
-
-	gfs2_log_lock(sdp);
-	while (!list_empty(head)) {
-		bd = list_entry(head->next, struct gfs2_bufdata, bd_list_tr);
-		list_del_init(&bd->bd_list_tr);
-		tr->tr_num_buf--;
-	}
-	gfs2_log_unlock(sdp);
-	gfs2_assert_warn(sdp, !tr->tr_num_buf);
-}
-
 /**
  * gfs2_log_commit - Commit a transaction to the log
  * @sdp: the filesystem
@@ -768,8 +712,6 @@ static void buf_lo_incore_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 {
 	log_refund(sdp, tr);
-	buf_lo_incore_commit(sdp, tr);
-
 	up_read(&sdp->sd_log_flush_lock);
 
 	if (atomic_read(&sdp->sd_log_pinned) > atomic_read(&sdp->sd_log_thresh1) ||
@@ -798,8 +740,7 @@ void gfs2_log_shutdown(struct gfs2_sbd *sdp)
 	sdp->sd_log_flush_head = sdp->sd_log_head;
 	sdp->sd_log_flush_wrapped = 0;
 
-	log_write_header(sdp, GFS2_LOG_HEAD_UNMOUNT,
-			 (sdp->sd_log_tail == current_tail(sdp)) ? 0 : PULL);
+	log_write_header(sdp, GFS2_LOG_HEAD_UNMOUNT);
 
 	gfs2_assert_warn(sdp, atomic_read(&sdp->sd_log_blks_free) == sdp->sd_jdesc->jd_blocks);
 	gfs2_assert_warn(sdp, sdp->sd_log_head == sdp->sd_log_tail);
@@ -854,11 +795,9 @@ int gfs2_logd(void *data)
 	struct gfs2_sbd *sdp = data;
 	unsigned long t = 1;
 	DEFINE_WAIT(wait);
-	unsigned preflush;
 
 	while (!kthread_should_stop()) {
 
-		preflush = atomic_read(&sdp->sd_log_pinned);
 		if (gfs2_jrnl_flush_reqd(sdp) || t == 0) {
 			gfs2_ail1_empty(sdp);
 			gfs2_log_flush(sdp, NULL);
diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h
index ff07454b582..3fd5215ea25 100644
--- a/fs/gfs2/log.h
+++ b/fs/gfs2/log.h
@@ -52,8 +52,6 @@ extern unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct,
 			    unsigned int ssize);
 
 extern int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks);
-extern void gfs2_log_incr_head(struct gfs2_sbd *sdp);
-extern u64 gfs2_log_bmap(struct gfs2_sbd *sdp, unsigned int lbn);
 extern void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl);
 extern void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *trans);
 extern void gfs2_remove_from_ail(struct gfs2_bufdata *bd);
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 6b1efb594d9..852c1be1dd3 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -127,146 +127,277 @@ static void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh,
 	atomic_dec(&sdp->sd_log_pinned);
 }
 
-
-static inline struct gfs2_log_descriptor *bh_log_desc(struct buffer_head *bh)
+static void gfs2_log_incr_head(struct gfs2_sbd *sdp)
 {
-	return (struct gfs2_log_descriptor *)bh->b_data;
+	BUG_ON((sdp->sd_log_flush_head == sdp->sd_log_tail) &&
+	       (sdp->sd_log_flush_head != sdp->sd_log_head));
+
+	if (++sdp->sd_log_flush_head == sdp->sd_jdesc->jd_blocks) {
+		sdp->sd_log_flush_head = 0;
+		sdp->sd_log_flush_wrapped = 1;
+	}
 }
 
-static inline __be64 *bh_log_ptr(struct buffer_head *bh)
+static u64 gfs2_log_bmap(struct gfs2_sbd *sdp)
 {
-	struct gfs2_log_descriptor *ld = bh_log_desc(bh);
-	return (__force __be64 *)(ld + 1);
+	unsigned int lbn = sdp->sd_log_flush_head;
+	struct gfs2_journal_extent *je;
+	u64 block;
+
+	list_for_each_entry(je, &sdp->sd_jdesc->extent_list, extent_list) {
+		if (lbn >= je->lblock && lbn < je->lblock + je->blocks) {
+			block = je->dblock + lbn - je->lblock;
+			gfs2_log_incr_head(sdp);
+			return block;
+		}
+	}
+
+	return -1;
 }
 
-static inline __be64 *bh_ptr_end(struct buffer_head *bh)
+/**
+ * gfs2_end_log_write_bh - end log write of pagecache data with buffers
+ * @sdp: The superblock
+ * @bvec: The bio_vec
+ * @error: The i/o status
+ *
+ * This finds the relavent buffers and unlocks then and sets the
+ * error flag according to the status of the i/o request. This is
+ * used when the log is writing data which has an in-place version
+ * that is pinned in the pagecache.
+ */
+
+static void gfs2_end_log_write_bh(struct gfs2_sbd *sdp, struct bio_vec *bvec,
+				  int error)
 {
-	return (__force __be64 *)(bh->b_data + bh->b_size);
+	struct buffer_head *bh, *next;
+	struct page *page = bvec->bv_page;
+	unsigned size;
+
+	bh = page_buffers(page);
+	size = bvec->bv_len;
+	while (bh_offset(bh) < bvec->bv_offset)
+		bh = bh->b_this_page;
+	do {
+		if (error)
+			set_buffer_write_io_error(bh);
+		unlock_buffer(bh);
+		next = bh->b_this_page;
+		size -= bh->b_size;
+		brelse(bh);
+		bh = next;
+	} while(bh && size);
 }
 
 /**
- * gfs2_log_write_endio - End of I/O for a log buffer
- * @bh: The buffer head
- * @uptodate: I/O Status
+ * gfs2_end_log_write - end of i/o to the log
+ * @bio: The bio
+ * @error: Status of i/o request
+ *
+ * Each bio_vec contains either data from the pagecache or data
+ * relating to the log itself. Here we iterate over the bio_vec
+ * array, processing both kinds of data.
  *
  */