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

Pull GFS2 updates from Steven Whitehouse:
 "This is one of the smallest collections of patches for the merge
  window for some time.  There are some clean ups relating to the
  transaction code and the shrinker, which are mostly in preparation for
  further development, but also make the code much easier to follow in
  these areas.

  There is a patch which allows the use of ->writepages even in the
  default ordered write mode for all writebacks.  This results in
  sending larger i/os to the block layer, and a subsequent increase in
  performance.  It also reduces the number of different i/o paths by
  one.

  There is also a bug fix reinstating the withdraw ack system which
  somehow got lost when the lock modules were merged into GFS2."

* git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-3.0-nmw:
  GFS2: Reinstate withdraw ack system
  GFS2: Get a block reservation before resizing a file
  GFS2: Split glock lru processing into two parts
  GFS2: Use ->writepages for ordered writes
  GFS2: Clean up freeze code
  GFS2: Merge gfs2_attach_bufdata() into trans.c
  GFS2: Copy gfs2_trans_add_bh into new data/meta functions
  GFS2: Split gfs2_trans_add_bh() into two
  GFS2: Merge revoke adding functions
  GFS2: Separate LRU scanning from shrinker

23 files changed, 375 insertions, 374 deletions

diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 30de4f2a2ea9..24f414f0ce61 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -51,7 +51,7 @@ static void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page,
 			continue;
 		if (gfs2_is_jdata(ip))
 			set_buffer_uptodate(bh);
-		gfs2_trans_add_bh(ip->i_gl, bh, 0);
+		gfs2_trans_add_data(ip->i_gl, bh);
 	}
 }
 
@@ -230,16 +230,14 @@ out_ignore:
 }
 
 /**
- * gfs2_writeback_writepages - Write a bunch of dirty pages back to disk
+ * gfs2_writepages - Write a bunch of dirty pages back to disk
  * @mapping: The mapping to write
  * @wbc: Write-back control
  *
- * For the data=writeback case we can already ignore buffer heads
- * and write whole extents at once. This is a big reduction in the
- * number of I/O requests we send and the bmap calls we make in this case.
+ * Used for both ordered and writeback modes.
  */
-static int gfs2_writeback_writepages(struct address_space *mapping,
-				     struct writeback_control *wbc)
+static int gfs2_writepages(struct address_space *mapping,
+			   struct writeback_control *wbc)
 {
 	return mpage_writepages(mapping, wbc, gfs2_get_block_noalloc);
 }
@@ -852,7 +850,7 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping,
 		goto failed;
 	}
 
-	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+	gfs2_trans_add_meta(ip->i_gl, dibh);
 
 	if (gfs2_is_stuffed(ip))
 		return gfs2_stuffed_write_end(inode, dibh, pos, len, copied, page);
@@ -1102,7 +1100,7 @@ cannot_release:
 
 static const struct address_space_operations gfs2_writeback_aops = {
 	.writepage = gfs2_writeback_writepage,
-	.writepages = gfs2_writeback_writepages,
+	.writepages = gfs2_writepages,
 	.readpage = gfs2_readpage,
 	.readpages = gfs2_readpages,
 	.write_begin = gfs2_write_begin,
@@ -1118,6 +1116,7 @@ static const struct address_space_operations gfs2_writeback_aops = {
 
 static const struct address_space_operations gfs2_ordered_aops = {
 	.writepage = gfs2_ordered_writepage,
+	.writepages = gfs2_writepages,
 	.readpage = gfs2_readpage,
 	.readpages = gfs2_readpages,
 	.write_begin = gfs2_write_begin,
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index a68e91bcef3d..df686d13a7d2 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -22,6 +22,7 @@
 #include "meta_io.h"
 #include "quota.h"
 #include "rgrp.h"
+#include "log.h"
 #include "super.h"
 #include "trans.h"
 #include "dir.h"
@@ -93,7 +94,7 @@ static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh,
 	if (!gfs2_is_jdata(ip))
 		mark_buffer_dirty(bh);
 	if (!gfs2_is_writeback(ip))
-		gfs2_trans_add_bh(ip->i_gl, bh, 0);
+		gfs2_trans_add_data(ip->i_gl, bh);
 
 	if (release) {
 		unlock_page(page);
@@ -153,7 +154,7 @@ int gfs2_unstuff_dinode(struct gfs2_inode *ip, struct page *page)
 
 	/*  Set up the pointer to the new block  */
 
-	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+	gfs2_trans_add_meta(ip->i_gl, dibh);
 	di = (struct gfs2_dinode *)dibh->b_data;
 	gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode));
 
@@ -405,7 +406,7 @@ static inline __be64 *gfs2_indirect_init(struct metapath *mp,
 	BUG_ON(i < 1);
 	BUG_ON(mp->mp_bh[i] != NULL);
 	mp->mp_bh[i] = gfs2_meta_new(gl, bn);
-	gfs2_trans_add_bh(gl, mp->mp_bh[i], 1);
+	gfs2_trans_add_meta(gl, mp->mp_bh[i]);
 	gfs2_metatype_set(mp->mp_bh[i], GFS2_METATYPE_IN, GFS2_FORMAT_IN);
 	gfs2_buffer_clear_tail(mp->mp_bh[i], sizeof(struct gfs2_meta_header));
 	ptr += offset;
@@ -468,7 +469,7 @@ static int gfs2_bmap_alloc(struct inode *inode, const sector_t lblock,
 	BUG_ON(sheight < 1);
 	BUG_ON(dibh == NULL);
 
-	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+	gfs2_trans_add_meta(ip->i_gl, dibh);
 
 	if (height == sheight) {
 		struct buffer_head *bh;
@@ -544,7 +545,7 @@ static int gfs2_bmap_alloc(struct inode *inode, const sector_t lblock,
 		/* Branching from existing tree */
 		case ALLOC_GROW_DEPTH:
 			if (i > 1 && i < height)
-				gfs2_trans_add_bh(ip->i_gl, mp->mp_bh[i-1], 1);
+				gfs2_trans_add_meta(ip->i_gl, mp->mp_bh[i-1]);
 			for (; i < height && n > 0; i++, n--)
 				gfs2_indirect_init(mp, ip->i_gl, i,
 						   mp->mp_list[i-1], bn++);
@@ -556,7 +557,7 @@ static int gfs2_bmap_alloc(struct inode *inode, const sector_t lblock,
 		case ALLOC_DATA:
 			BUG_ON(n > dblks);
 			BUG_ON(mp->mp_bh[end_of_metadata] == NULL);
-			gfs2_trans_add_bh(ip->i_gl, mp->mp_bh[end_of_metadata], 1);
+			gfs2_trans_add_meta(ip->i_gl, mp->mp_bh[end_of_metadata]);
 			dblks = n;
 			ptr = metapointer(end_of_metadata, mp);
 			dblock = bn;
@@ -796,8 +797,8 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 
 	down_write(&ip->i_rw_mutex);
 
-	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
-	gfs2_trans_add_bh(ip->i_gl, bh, 1);
+	gfs2_trans_add_meta(ip->i_gl, dibh);
+	gfs2_trans_add_meta(ip->i_gl, bh);
 
 	bstart = 0;
 	blen = 0;
@@ -981,7 +982,7 @@ static int gfs2_block_truncate_page(struct address_space *mapping, loff_t from)
 	}
 
 	if (!gfs2_is_writeback(ip))
-		gfs2_trans_add_bh(ip->i_gl, bh, 0);
+		gfs2_trans_add_data(ip->i_gl, bh);
 
 	zero_user(page, offset, length);
 	mark_buffer_dirty(bh);
@@ -1046,7 +1047,7 @@ static int trunc_start(struct inode *inode, u64 oldsize, u64 newsize)
 	if (error)
 		goto out;
 
-	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+	gfs2_trans_add_meta(ip->i_gl, dibh);
 
 	if (gfs2_is_stuffed(ip)) {
 		gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode) + newsize);
@@ -1137,11 +1138,12 @@ static int trunc_end(struct gfs2_inode *ip)
 		ip->i_height = 0;
 		ip->i_goal = ip->i_no_addr;
 		gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode));
+		gfs2_ordered_del_inode(ip);
 	}
 	ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
 	ip->i_diskflags &= ~GFS2_DIF_TRUNC_IN_PROG;
 
-	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+	gfs2_trans_add_meta(ip->i_gl, dibh);
 	gfs2_dinode_out(ip, dibh->b_data);
 	brelse(dibh);
 
@@ -1246,7 +1248,7 @@ static int do_grow(struct inode *inode, u64 size)
 
 	i_size_write(inode, size);
 	ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
-	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+	gfs2_trans_add_meta(ip->i_gl, dibh);
 	gfs2_dinode_out(ip, dibh->b_data);
 	brelse(dibh);
 
@@ -1286,6 +1288,10 @@ int gfs2_setattr_size(struct inode *inode, u64 newsize)
 
 	inode_dio_wait(inode);
 
+	ret = gfs2_rs_alloc(GFS2_I(inode));
+	if (ret)
+		return ret;
+
 	oldsize = inode->i_size;
 	if (newsize >= oldsize)
 		return do_grow(inode, newsize);
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index 9a35670fdc38..7179478e5a28 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -93,7 +93,7 @@ int gfs2_dir_get_new_buffer(struct gfs2_inode *ip, u64 block,
 	struct buffer_head *bh;
 
 	bh = gfs2_meta_new(ip->i_gl, block);
-	gfs2_trans_add_bh(ip->i_gl, bh, 1);
+	gfs2_trans_add_meta(ip->i_gl, bh);
 	gfs2_metatype_set(bh, GFS2_METATYPE_JD, GFS2_FORMAT_JD);
 	gfs2_buffer_clear_tail(bh, sizeof(struct gfs2_meta_header));
 	*bhp = bh;
@@ -127,7 +127,7 @@ static int gfs2_dir_write_stuffed(struct gfs2_inode *ip, const char *buf,
 	if (error)
 		return error;
 
-	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+	gfs2_trans_add_meta(ip->i_gl, dibh);
 	memcpy(dibh->b_data + offset + sizeof(struct gfs2_dinode), buf, size);
 	if (ip->i_inode.i_size < offset + size)
 		i_size_write(&ip->i_inode, offset + size);
@@ -209,7 +209,7 @@ static int gfs2_dir_write_data(struct gfs2_inode *ip, const char *buf,
 		if (error)
 			goto fail;
 
-		gfs2_trans_add_bh(ip->i_gl, bh, 1);
+		gfs2_trans_add_meta(ip->i_gl, bh);
 		memcpy(bh->b_data + o, buf, amount);
 		brelse(bh);
 
@@ -231,7 +231,7 @@ out:
 		i_size_write(&ip->i_inode, offset + copied);
 	ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
 
-	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+	gfs2_trans_add_meta(ip->i_gl, dibh);
 	gfs2_dinode_out(ip, dibh->b_data);
 	brelse(dibh);
 
@@ -647,7 +647,7 @@ static void dirent_del(struct gfs2_inode *dip, struct buffer_head *bh,
 		return;
 	}
 
-	gfs2_trans_add_bh(dip->i_gl, bh, 1);
+	gfs2_trans_add_meta(dip->i_gl, bh);
 
 	/* If there is no prev entry, this is the first entry in the block.
 	   The de_rec_len is already as big as it needs to be.  Just zero
@@ -690,7 +690,7 @@ static struct gfs2_dirent *gfs2_init_dirent(struct inode *inode,
 		offset = GFS2_DIRENT_SIZE(be16_to_cpu(dent->de_name_len));
 	totlen = be16_to_cpu(dent->de_rec_len);
 	BUG_ON(offset + name->len > totlen);
-	gfs2_trans_add_bh(ip->i_gl, bh, 1);
+	gfs2_trans_add_meta(ip->i_gl, bh);
 	ndent = (struct gfs2_dirent *)((char *)dent + offset);
 	dent->de_rec_len = cpu_to_be16(offset);
 	gfs2_qstr2dirent(name, totlen - offset, ndent);
@@ -831,7 +831,7 @@ static struct gfs2_leaf *new_leaf(struct inode *inode, struct buffer_head **pbh,
 		return NULL;
 
 	gfs2_trans_add_unrevoke(GFS2_SB(inode), bn, 1);
-	gfs2_trans_add_bh(ip->i_gl, bh, 1);
+	gfs2_trans_add_meta(ip->i_gl, bh);
 	gfs2_metatype_set(bh, GFS2_METATYPE_LF, GFS2_FORMAT_LF);
 	leaf = (struct gfs2_leaf *)bh->b_data;
 	leaf->lf_depth = cpu_to_be16(depth);
@@ -916,7 +916,7 @@ static int dir_make_exhash(struct inode *inode)
 	/*  We're done with the new leaf block, now setup the new
 	    hash table.  */
 
-	gfs2_trans_add_bh(dip->i_gl, dibh, 1);
+	gfs2_trans_add_meta(dip->i_gl, dibh);
 	gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode));
 
 	lp = (__be64 *)(dibh->b_data + sizeof(struct gfs2_dinode));
@@ -976,7 +976,7 @@ static int dir_split_leaf(struct inode *inode, const struct qstr *name)
 		return 1; /* can't split */
 	}
 
-	gfs2_trans_add_bh(dip->i_gl, obh, 1);
+	gfs2_trans_add_meta(dip->i_gl, obh);
 
 	nleaf = new_leaf(inode, &nbh, be16_to_cpu(oleaf->lf_depth) + 1);
 	if (!nleaf) {
@@ -1069,7 +1069,7 @@ static int dir_split_leaf(struct inode *inode, const struct qstr *name)
 
 	error = gfs2_meta_inode_buffer(dip, &dibh);
 	if (!gfs2_assert_withdraw(GFS2_SB(&dip->i_inode), !error)) {
-		gfs2_trans_add_bh(dip->i_gl, dibh, 1);
+		gfs2_trans_add_meta(dip->i_gl, dibh);
 		gfs2_add_inode_blocks(&dip->i_inode, 1);
 		gfs2_dinode_out(dip, dibh->b_data);
 		brelse(dibh);
@@ -1622,7 +1622,7 @@ static int dir_new_leaf(struct inode *inode, const struct qstr *name)
 			return error;
 	} while(1);
 
-	gfs2_trans_add_bh(ip->i_gl, obh, 1);
+	gfs2_trans_add_meta(ip->i_gl, obh);
 
 	leaf = new_leaf(inode, &bh, be16_to_cpu(oleaf->lf_depth));
 	if (!leaf) {
@@ -1636,7 +1636,7 @@ static int dir_new_leaf(struct inode *inode, const struct qstr *name)
 	error = gfs2_meta_inode_buffer(ip, &bh);
 	if (error)
 		return error;
-	gfs2_trans_add_bh(ip->i_gl, bh, 1);
+	gfs2_trans_add_meta(ip->i_gl, bh);
 	gfs2_add_inode_blocks(&ip->i_inode, 1);
 	gfs2_dinode_out(ip, bh->b_data);
 	brelse(bh);
@@ -1795,7 +1795,7 @@ int gfs2_dir_mvino(struct gfs2_inode *dip, const struct qstr *filename,
 	if (IS_ERR(dent))
 		return PTR_ERR(dent);
 
-	gfs2_trans_add_bh(dip->i_gl, bh, 1);
+	gfs2_trans_add_meta(dip->i_gl, bh);
 	gfs2_inum_out(nip, dent);
 	dent->de_type = cpu_to_be16(new_type);
 
@@ -1804,7 +1804,7 @@ int gfs2_dir_mvino(struct gfs2_inode *dip, const struct qstr *filename,
 		error = gfs2_meta_inode_buffer(dip, &bh);
 		if (error)
 			return error;
-		gfs2_trans_add_bh(dip->i_gl, bh, 1);
+		gfs2_trans_add_meta(dip->i_gl, bh);
 	}
 
 	dip->i_inode.i_mtime = dip->i_inode.i_ctime = CURRENT_TIME;
@@ -1917,7 +1917,7 @@ static int leaf_dealloc(struct gfs2_inode *dip, u32 index, u32 len,
 	if (error)
 		goto out_end_trans;
 
-	gfs2_trans_add_bh(dip->i_gl, dibh, 1);
+	gfs2_trans_add_meta(dip->i_gl, dibh);
 	/* On the last dealloc, make this a regular file in case we crash.
 	   (We don't want to free these blocks a second time.)  */
 	if (last_dealloc)
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 991ab2d484dd..06b7092a3f25 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -276,7 +276,7 @@ static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask)
 	error = gfs2_meta_inode_buffer(ip, &bh);
 	if (error)
 		goto out_trans_end;
-	gfs2_trans_add_bh(ip->i_gl, bh, 1);
+	gfs2_trans_add_meta(ip->i_gl, bh);
 	ip->i_diskflags = new_flags;
 	gfs2_dinode_out(ip, bh->b_data);
 	brelse(bh);
@@ -709,7 +709,7 @@ static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
 	if (unlikely(error))
 		return error;
 
-	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+	gfs2_trans_add_meta(ip->i_gl, dibh);
 
 	if (gfs2_is_stuffed(ip)) {
 		error = gfs2_unstuff_dinode(ip, NULL);
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 992c5c0cb504..cf3515546739 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -30,6 +30,7 @@
 #include <linux/rculist_bl.h>
 #include <linux/bit_spinlock.h>
 #include <linux/percpu.h>
+#include <linux/list_sort.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -1376,56 +1377,105 @@ void gfs2_glock_complete(struct gfs2_glock *gl, int ret)
 		gfs2_glock_put(gl);
 }
 
+static int glock_cmp(void *priv, struct list_head *a, struct list_head *b)
+{
+	struct gfs2_glock *gla, *glb;
 
-static int gfs2_shrink_glock_memory(struct shrinker *shrink,
-				    struct shrink_control *sc)
+	gla = list_entry(a, struct gfs2_glock, gl_lru);
+	glb = list_entry(b, struct gfs2_glock, gl_lru);
+
+	if (gla->gl_name.ln_number > glb->gl_name.ln_number)
+		return 1;
+	if (gla->gl_name.ln_number < glb->gl_name.ln_number)
+		return -1;
+
+	return 0;
+}
+
+/**
+ * gfs2_dispose_glock_lru - Demote a list of glocks
+ * @list: The list to dispose of
+ *
+ * Disposing of glocks may involve disk accesses, so that here we sort
+ * the glocks by number (i.e. disk location of the inodes) so that if
+ * there are any such accesses, they'll be sent in order (mostly).
+ *
+ * Must be called under the lru_lock, but may drop and retake this
+ * lock. While the lru_lock is dropped, entries may vanish from the
+ * list, but no new entries will appear on the list (since it is
+ * private)
+ */
+
+static void gfs2_dispose_glock_lru(struct list_head *list)
+__releases(&lru_lock)
+__acquires(&lru_lock)
 {
 	struct gfs2_glock *gl;
-	int may_demote;
-	int nr_skipped = 0;
-	int nr = sc->nr_to_scan;
-	gfp_t gfp_mask = sc->gfp_mask;
-	LIST_HEAD(skipped);
 
-	if (nr == 0)
-		goto out;
+	list_sort(NULL, list, glock_cmp);
 
-	if (!(gfp_mask & __GFP_FS))
-		return -1;
+	while(!list_empty(list)) {
+		gl = list_entry(list->next, struct gfs2_glock, gl_lru);
+		list_del_init(&gl->gl_lru);
+		clear_bit(GLF_LRU, &gl->gl_flags);
+		gfs2_glock_hold(gl);
+		spin_unlock(&lru_lock);
+		spin_lock(&gl->gl_spin);
+		if (demote_ok(gl))
+			handle_callback(gl, LM_ST_UNLOCKED, 0);
+		WARN_ON(!test_and_clear_bit(GLF_LOCK, &gl->gl_flags));
+		smp_mb__after_clear_bit();
+		if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
+			gfs2_glock_put_nolock(gl);
+		spin_unlock(&gl->gl_spin);
+		spin_lock(&lru_lock);
+	}
+}
+
+/**
+ * gfs2_scan_glock_lru - Scan the LRU looking for locks to demote
+ * @nr: The number of entries to scan
+ *
+ * This function selects the entries on the LRU which are able to
+ * be demoted, and then kicks off the process by calling
+ * gfs2_dispose_glock_lru() above.
+ */
+
+static void gfs2_scan_glock_lru(int nr)
+{
+	struct gfs2_glock *gl;
+	LIST_HEAD(skipped);
+	LIST_HEAD(dispose);
 
 	spin_lock(&lru_lock);
 	while(nr && !list_empty(&lru_list)) {
 		gl = list_entry(lru_list.next, struct gfs2_glock, gl_lru);
-		list_del_init(&gl->gl_lru);
-		clear_bit(GLF_LRU, &gl->gl_flags);
-		atomic_dec(&lru_count);
 
 		/* Test for being demotable */
 		if (!test_and_set_bit(GLF_LOCK, &gl->gl_flags)) {
-			gfs2_glock_hold(gl);
-			spin_unlock(&lru_lock);
-			spin_lock(&gl->gl_spin);
-			may_demote = demote_ok(gl);
-			if (may_demote) {
-				handle_callback(gl, LM_ST_UNLOCKED, 0);
-				nr--;
-			}
-			clear_bit(GLF_LOCK, &gl->gl_flags);
-			smp_mb__after_clear_bit();
-			if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
-				gfs2_glock_put_nolock(gl);
-			spin_unlock(&gl->gl_spin);
-			spin_lock(&lru_lock);
+			list_move(&gl->gl_lru, &dispose);
+			atomic_dec(&lru_count);
+			nr--;
 			continue;
 		}
-		nr_skipped++;
-		list_add(&gl->gl_lru, &skipped);
-		set_bit(GLF_LRU, &gl->gl_flags);
+
+		list_move(&gl->gl_lru, &skipped);
 	}
 	list_splice(&skipped, &lru_list);
-	atomic_add(nr_skipped, &lru_count);
+	if (!list_empty(&dispose))
+		gfs2_dispose_glock_lru(&dispose);
 	spin_unlock(&lru_lock);
-out:
+}
+
+static int gfs2_shrink_glock_memory(struct shrinker *shrink,
+				    struct shrink_control *sc)
+{
+	if (sc->nr_to_scan) {
+		if (!(sc->gfp_mask & __GFP_FS))
+			return -1;
+		gfs2_scan_glock_lru(sc->nr_to_scan);
+	}
+
 	return (atomic_read(&lru_count) / 100) * sysctl_vfs_cache_pressure;
 }
 
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index c373a24fedd9..e2601ba38ef5 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -52,7 +52,6 @@ struct gfs2_log_header_host {
  */
 
 struct gfs2_log_operations {
-	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,
@@ -341,6 +340,7 @@ enum {
 	GIF_QD_LOCKED		= 1,
 	GIF_ALLOC_FAILED	= 2,
 	GIF_SW_PAGED		= 3,
+	GIF_ORDERED		= 4,
 };
 
 struct gfs2_inode {
@@ -357,6 +357,7 @@ struct gfs2_inode {
 	struct gfs2_rgrpd *i_rgd;
 	u64 i_goal;	/* goal block for allocations */
 	struct rw_semaphore i_rw_mutex;
+	struct list_head i_ordered;
 	struct list_head i_trunc_list;
 	__be64 *i_hash_cache;
 	u32 i_entries;
@@ -641,6 +642,7 @@ struct gfs2_sbd {
 	wait_queue_head_t sd_glock_wait;
 	atomic_t sd_glock_disposal;
 	struct completion sd_locking_init;
+	struct completion sd_wdack;
 	struct delayed_work sd_control_work;
 
 	/* Inode Stuff */
@@ -723,6 +725,7 @@ struct gfs2_sbd {
 	struct list_head sd_log_le_revoke;
 	struct list_head sd_log_le_databuf;
 	struct list_head sd_log_le_ordered;
+	spinlock_t sd_ordered_lock;
 
 	atomic_t sd_log_thresh1;
 	atomic_t sd_log_thresh2;
@@ -758,10 +761,7 @@ struct gfs2_sbd {
 	unsigned int sd_replayed_blocks;
 
 	/* For quiescing the filesystem */
-
 	struct gfs2_holder sd_freeze_gh;
-	struct mutex sd_freeze_lock;
-	unsigned int sd_freeze_count;
 
 	char sd_fsname[GFS2_FSNAME_LEN];
 	char sd_table_name[GFS2_FSNAME_LEN];
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 2b6f5698ef18..db048a8ab6a8 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -447,7 +447,7 @@ static void init_dinode(struct gfs2_inode *dip, struct gfs2_inode *ip,
 	struct timespec tv = CURRENT_TIME;
 
 	dibh = gfs2_meta_new(ip->i_gl, ip->i_no_addr);
-	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+	gfs2_trans_add_meta(ip->i_gl, dibh);
 	gfs2_metatype_set(dibh, GFS2_METATYPE_DI, GFS2_FORMAT_DI);
 	gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode));
 	di = (struct gfs2_dinode *)dibh->b_data;
@@ -584,7 +584,7 @@ static int link_dinode(struct gfs2_inode *dip, const struct qstr *name,
 	if (error)
 		goto fail_end_trans;
 	set_nlink(&ip->i_inode, S_ISDIR(ip->i_inode.i_mode) ? 2 : 1);
-	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+	gfs2_trans_add_meta(ip->i_gl, dibh);
 	gfs2_dinode_out(ip, dibh->b_data);
 	brelse(dibh);
 	return 0;
@@ -931,7 +931,7 @@ static int gfs2_link(struct dentry *old_dentry, struct inode *dir,
 	if (error)
 		goto out_brelse;
 
-	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+	gfs2_trans_add_meta(ip->i_gl, dibh);
 	inc_nlink(&ip->i_inode);
 	ip->i_inode.i_ctime = CURRENT_TIME;
 	ihold(inode);
@@ -1412,7 +1412,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
 		if (error)
 			goto out_end_trans;
 		ip->i_inode.i_ctime = CURRENT_TIME;
-		gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+		gfs2_trans_add_meta(ip->i_gl, dibh);
 		gfs2_dinode_out(ip, dibh->b_data);
 		brelse(dibh);
 	}
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index f4beeb9c81c1..9a2ca8be7647 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -482,70 +482,66 @@ static void log_flush_wait(struct gfs2_sbd *sdp)
 	}
 }
 
-static int bd_cmp(void *priv, struct list_head *a, struct list_head *b)
+static int ip_cmp(void *priv, struct list_head *a, struct list_head *b)
 {
-	struct gfs2_bufdata *bda, *bdb;
+	struct gfs2_inode *ipa, *ipb;
 
-	bda = list_entry(a, struct gfs2_bufdata, bd_list);
-	bdb = list_entry(b, struct gfs2_bufdata, bd_list);
+	ipa = list_entry(a, struct gfs2_inode, i_ordered);
+	ipb = list_entry(b, struct gfs2_inode, i_ordered);
 
-	if (bda->bd_bh->b_blocknr < bdb->bd_bh->b_blocknr)
+	if (ipa->i_no_addr < ipb->i_no_addr)
 		return -1;
-	if (bda->bd_bh->b_blocknr > bdb->bd_bh->b_blocknr)
+	if (ipa->i_no_addr > ipb->i_no_addr)
 		return 1;
 	return 0;
 }
 
 static void gfs2_ordered_write(struct gfs2_sbd *sdp)
 {
-	struct gfs2_bufdata *bd;
-	struct buffer_head *bh;
+	struct gfs2_inode *ip;
 	LIST_HEAD(written);
 
-	gfs2_log_lock(sdp);
-	list_sort(NULL, &sdp->sd_log_le_ordered, &bd_cmp);
+	spin_lock(&sdp->sd_ordered_lock);
+	list_sort(NULL, &sdp->sd_log_le_ordered, &ip_cmp);
 	while (!list_empty(&sdp->sd_log_le_ordered)) {
-		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))
+		ip = list_entry(sdp->sd_log_le_ordered.next, struct gfs2_inode, i_ordered);
+		list_move(&ip->i_ordered, &written);
+		if (ip->i_inode.i_mapping->nrpages == 0)
 			continue;
-		get_bh(bh);
-		gfs2_log_unlock(sdp);
-		lock_buffer(bh);
-		if (buffer_mapped(bh) && test_clear_buffer_dirty(bh)) {
-			bh->b_end_io = end_buffer_write_sync;
-			submit_bh(WRITE_SYNC, bh);
-		} else {
-			unlock_buffer(bh);
-			brelse(bh);
-		}
-		gfs2_log_lock(sdp);
+		spin_unlock(&sdp->sd_ordered_lock);
+		filemap_fdatawrite(ip->i_inode.i_mapping);
+		spin_lock(&sdp->sd_ordered_lock);
 	}
 	list_splice(&written, &sdp->sd_log_le_ordered);
-	gfs2_log_unlock(sdp);
+	spin_unlock(&sdp->sd_ordered_lock);
 }
 
 static void gfs2_ordered_wait(struct gfs2_sbd *sdp)
 {
-	struct gfs2_bufdata *bd;
-	struct buffer_head *bh;
+	struct gfs2_inode *ip;
 
-	gfs2_log_lock(sdp);
+	spin_lock(&sdp->sd_ordered_lock);
 	while (!list_empty(&sdp->sd_log_le_ordered)) {
-		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);
-			gfs2_log_unlock(sdp);
-			wait_on_buffer(bh);
-			brelse(bh);
-			gfs2_log_lock(sdp);
+		ip = list_entry(sdp->sd_log_le_ordered.next, struct gfs2_inode, i_ordered);
+		list_del(&ip->i_ordered);
+		WARN_ON(!test_and_clear_bit(GIF_ORDERED, &ip->i_flags));
+		if (ip->i_inode.i_mapping->nrpages == 0)
 			continue;
-		}
-		list_del_init(&bd->bd_list);
+		spin_unlock(&sdp->sd_ordered_lock);
+		filemap_fdatawait(ip->i_inode.i_mapping);
+		spin_lock(&sdp->sd_ordered_lock);
 	}
-	gfs2_log_unlock(sdp);
+	spin_unlock(&sdp->sd_ordered_lock);
+}
+
+void gfs2_ordered_del_inode(struct gfs2_inode *ip)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+
+	spin_lock(&sdp->sd_ordered_lock);
+	if (test_and_clear_bit(GIF_ORDERED, &ip->i_flags))
+		list_del(&ip->i_ordered);
+	spin_unlock(&sdp->sd_ordered_lock);
 }
 
 /**
diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h
index 3fd5215ea25f..3566f35915e0 100644
--- a/fs/gfs2/log.h
+++ b/fs/gfs2/log.h
@@ -48,6 +48,18 @@ static inline void gfs2_log_pointers_init(struct gfs2_sbd *sdp,
 	sdp->sd_log_head = sdp->sd_log_tail = value;
 }
 
+static inline void gfs2_ordered_add_inode(struct gfs2_inode *ip)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+
+	if (!test_bit(GIF_ORDERED, &ip->i_flags)) {
+		spin_lock(&sdp->sd_ordered_lock);
+		if (!test_and_set_bit(GIF_ORDERED, &ip->i_flags))
+			list_add(&ip->i_ordered, &sdp->sd_log_le_ordered);
+		spin_unlock(&sdp->sd_ordered_lock);
+	}
+}
+extern void gfs2_ordered_del_inode(struct gfs2_inode *ip);
 extern unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct,
 			    unsigned int ssize);
 
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 9ceccb1595a3..a5055977a214 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -37,7 +37,7 @@
  *
  * The log lock must be held when calling this function
  */
-static void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh)
+void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh)
 {
 	struct gfs2_bufdata *bd;
 
@@ -388,32 +388,6 @@ static struct page *gfs2_get_log_desc(struct gfs2_sbd *sdp, u32 ld_type,
 	return page;
 }
 
-static void buf_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
-{
-	struct gfs2_meta_header *mh;
-	struct gfs2_trans *tr;
-
-	tr = current->journal_info;
-	tr->tr_touched = 1;
-	if (!list_empty(&bd->bd_list))
-		return;
-	set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
-	set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags);
-	mh = (struct gfs2_meta_header *)bd->bd_bh->b_data;
-	if (unlikely(mh->mh_magic != cpu_to_be32(GFS2_MAGIC))) {
-		printk(KERN_ERR
-		       "Attempting to add uninitialised block to journal (inplace block=%lld)\n",
-		       (unsigned long long)bd->bd_bh->b_blocknr);
-		BUG();
-	}
-	gfs2_pin(sdp, bd->bd_bh);
-	mh->__pad0 = cpu_to_be64(0);
-	mh->mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid);
-	sdp->sd_log_num_buf++;
-	list_add(&bd->bd_list, &sdp->sd_log_le_buf);
-	tr->tr_num_buf_new++;
-}
-
 static void gfs2_check_magic(struct buffer_head *bh)
 {
 	void *kaddr;
@@ -600,20 +574,6 @@ static void buf_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
 	        jd->jd_jid, sdp->sd_replayed_blocks, sdp->sd_found_blocks);
 }
 
-static void revoke_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
-{
-	struct gfs2_glock *gl = bd->bd_gl;
-	struct gfs2_trans *tr;
-
-	tr = current->journal_info;
-	tr->tr_touched = 1;
-	tr->tr_num_revoke++;
-	sdp->sd_log_num_revoke++;
-	atomic_inc(&gl->gl_revokes);
-	set_bit(GLF_LFLUSH, &gl->gl_flags);
-	list_add(&bd->bd_list, &sdp->sd_log_le_revoke);
-}
-
 static void revoke_lo_before_commit(struct gfs2_sbd *sdp)
 {
 	struct gfs2_meta_header *mh;
@@ -749,44 +709,6 @@ static void revoke_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
 }
 
 /**
- * databuf_lo_add - Add a databuf to the transaction.
- *
- * This is used in two distinct cases:
- * i) In ordered write mode
- *    We put the data buffer on a list so that we can ensure that its
- *    synced to disk at the right time
- * ii) In journaled data mode
- *    We need to journal the data block in the same way as metadata in
- *    the functions above. The difference is that here we have a tag
- *    which is two __be64's being the block number (as per meta data)
- *    and a flag which says whether the data block needs escaping or
- *    not. This means we need a new log entry for each 251 or so data
- *    blocks, which isn't an enormous overhead but twice as much as
- *    for normal metadata blocks.
- */
-static void databuf_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
-{
-	struct gfs2_trans *tr = current->journal_info;
-	struct address_space *mapping = bd->bd_bh->b_page->mapping;
-	struct gfs2_inode *ip = GFS2_I(mapping->host);
-
-	if (tr)
-		tr->tr_touched = 1;
-	if (!list_empty(&bd->bd_list))
-		return;
-	set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
-	set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags);
-	if (gfs2_is_jdata(ip)) {
-		gfs2_pin(sdp, bd->bd_bh);
-		tr->tr_num_databuf_new++;
-		sdp->sd_log_num_databuf++;
-		list_add_tail(&bd->bd_list, &sdp->sd_log_le_databuf);
-	} else {