1 files changed, 323 insertions, 345 deletions

diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 756fae9eaf8..3966fadbceb 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -18,7 +18,9 @@
 #include <linux/kthread.h>
 #include <linux/freezer.h>
 #include <linux/bio.h>
+#include <linux/blkdev.h>
 #include <linux/writeback.h>
+#include <linux/list_sort.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -31,8 +33,6 @@
 #include "dir.h"
 #include "trace_gfs2.h"
 
-#define PULL 1
-
 /**
  * gfs2_struct2blk - compute stuff
  * @sdp: the filesystem
@@ -74,7 +74,7 @@ unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct,
 
 void gfs2_remove_from_ail(struct gfs2_bufdata *bd)
 {
-	bd->bd_ail = NULL;
+	bd->bd_tr = NULL;
 	list_del_init(&bd->bd_ail_st_list);
 	list_del_init(&bd->bd_ail_gl_list);
 	atomic_dec(&bd->bd_gl->gl_ail_count);
@@ -91,7 +91,7 @@ void gfs2_remove_from_ail(struct gfs2_bufdata *bd)
 
 static int gfs2_ail1_start_one(struct gfs2_sbd *sdp,
 			       struct writeback_control *wbc,
-			       struct gfs2_ail *ai)
+			       struct gfs2_trans *tr)
 __releases(&sdp->sd_ail_lock)
 __acquires(&sdp->sd_ail_lock)
 {
@@ -100,15 +100,15 @@ __acquires(&sdp->sd_ail_lock)
 	struct gfs2_bufdata *bd, *s;
 	struct buffer_head *bh;
 
-	list_for_each_entry_safe_reverse(bd, s, &ai->ai_ail1_list, bd_ail_st_list) {
+	list_for_each_entry_safe_reverse(bd, s, &tr->tr_ail1_list, bd_ail_st_list) {
 		bh = bd->bd_bh;
 
-		gfs2_assert(sdp, bd->bd_ail == ai);
+		gfs2_assert(sdp, bd->bd_tr == tr);
 
 		if (!buffer_busy(bh)) {
 			if (!buffer_uptodate(bh))
 				gfs2_io_error_bh(sdp, bh);
-			list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list);
+			list_move(&bd->bd_ail_st_list, &tr->tr_ail2_list);
 			continue;
 		}
 
@@ -117,7 +117,7 @@ __acquires(&sdp->sd_ail_lock)
 		if (gl == bd->bd_gl)
 			continue;
 		gl = bd->bd_gl;
-		list_move(&bd->bd_ail_st_list, &ai->ai_ail1_list);
+		list_move(&bd->bd_ail_st_list, &tr->tr_ail1_list);
 		mapping = bh->b_page->mapping;
 		if (!mapping)
 			continue;
@@ -145,18 +145,21 @@ __acquires(&sdp->sd_ail_lock)
 void gfs2_ail1_flush(struct gfs2_sbd *sdp, struct writeback_control *wbc)
 {
 	struct list_head *head = &sdp->sd_ail1_list;
-	struct gfs2_ail *ai;
+	struct gfs2_trans *tr;
+	struct blk_plug plug;
 
 	trace_gfs2_ail_flush(sdp, wbc, 1);
+	blk_start_plug(&plug);
 	spin_lock(&sdp->sd_ail_lock);
 restart:
-	list_for_each_entry_reverse(ai, head, ai_list) {
+	list_for_each_entry_reverse(tr, head, tr_list) {
 		if (wbc->nr_to_write <= 0)
 			break;
-		if (gfs2_ail1_start_one(sdp, wbc, ai))
+		if (gfs2_ail1_start_one(sdp, wbc, tr))
 			goto restart;
 	}
 	spin_unlock(&sdp->sd_ail_lock);
+	blk_finish_plug(&plug);
 	trace_gfs2_ail_flush(sdp, wbc, 0);
 }
 
@@ -184,20 +187,20 @@ static void gfs2_ail1_start(struct gfs2_sbd *sdp)
  *
  */
 
-static void gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+static void gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 {
 	struct gfs2_bufdata *bd, *s;
 	struct buffer_head *bh;
 
-	list_for_each_entry_safe_reverse(bd, s, &ai->ai_ail1_list,
+	list_for_each_entry_safe_reverse(bd, s, &tr->tr_ail1_list,
 					 bd_ail_st_list) {
 		bh = bd->bd_bh;
-		gfs2_assert(sdp, bd->bd_ail == ai);
+		gfs2_assert(sdp, bd->bd_tr == tr);
 		if (buffer_busy(bh))
 			continue;
 		if (!buffer_uptodate(bh))
 			gfs2_io_error_bh(sdp, bh);
-		list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list);
+		list_move(&bd->bd_ail_st_list, &tr->tr_ail2_list);
 	}
 
 }
@@ -211,16 +214,17 @@ static void gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
 
 static int gfs2_ail1_empty(struct gfs2_sbd *sdp)
 {
-	struct gfs2_ail *ai, *s;
+	struct gfs2_trans *tr, *s;
+	int oldest_tr = 1;
 	int ret;
 
 	spin_lock(&sdp->sd_ail_lock);
-	list_for_each_entry_safe_reverse(ai, s, &sdp->sd_ail1_list, ai_list) {
-		gfs2_ail1_empty_one(sdp, ai);
-		if (list_empty(&ai->ai_ail1_list))
-			list_move(&ai->ai_list, &sdp->sd_ail2_list);
+	list_for_each_entry_safe_reverse(tr, s, &sdp->sd_ail1_list, tr_list) {
+		gfs2_ail1_empty_one(sdp, tr);
+		if (list_empty(&tr->tr_ail1_list) && oldest_tr)
+			list_move(&tr->tr_list, &sdp->sd_ail2_list);
 		else
-			break;
+			oldest_tr = 0;
 	}
 	ret = list_empty(&sdp->sd_ail1_list);
 	spin_unlock(&sdp->sd_ail_lock);
@@ -230,13 +234,13 @@ static int gfs2_ail1_empty(struct gfs2_sbd *sdp)
 
 static void gfs2_ail1_wait(struct gfs2_sbd *sdp)
 {
-	struct gfs2_ail *ai;
+	struct gfs2_trans *tr;
 	struct gfs2_bufdata *bd;
 	struct buffer_head *bh;
 
 	spin_lock(&sdp->sd_ail_lock);
-	list_for_each_entry_reverse(ai, &sdp->sd_ail1_list, ai_list) {
-		list_for_each_entry(bd, &ai->ai_ail1_list, bd_ail_st_list) {
+	list_for_each_entry_reverse(tr, &sdp->sd_ail1_list, tr_list) {
+		list_for_each_entry(bd, &tr->tr_ail1_list, bd_ail_st_list) {
 			bh = bd->bd_bh;
 			if (!buffer_locked(bh))
 				continue;
@@ -257,46 +261,63 @@ static void gfs2_ail1_wait(struct gfs2_sbd *sdp)
  *
  */
 
-static void gfs2_ail2_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+static void gfs2_ail2_empty_one(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 {
-	struct list_head *head = &ai->ai_ail2_list;
+	struct list_head *head = &tr->tr_ail2_list;
 	struct gfs2_bufdata *bd;
 
 	while (!list_empty(head)) {
 		bd = list_entry(head->prev, struct gfs2_bufdata,
 				bd_ail_st_list);
-		gfs2_assert(sdp, bd->bd_ail == ai);
+		gfs2_assert(sdp, bd->bd_tr == tr);
 		gfs2_remove_from_ail(bd);
 	}
 }
 
 static void ail2_empty(struct gfs2_sbd *sdp, unsigned int new_tail)
 {
-	struct gfs2_ail *ai, *safe;
+	struct gfs2_trans *tr, *safe;
 	unsigned int old_tail = sdp->sd_log_tail;
 	int wrap = (new_tail < old_tail);
 	int a, b, rm;
 
 	spin_lock(&sdp->sd_ail_lock);
 
-	list_for_each_entry_safe(ai, safe, &sdp->sd_ail2_list, ai_list) {
-		a = (old_tail <= ai->ai_first);
-		b = (ai->ai_first < new_tail);
+	list_for_each_entry_safe(tr, safe, &sdp->sd_ail2_list, tr_list) {
+		a = (old_tail <= tr->tr_first);
+		b = (tr->tr_first < new_tail);
 		rm = (wrap) ? (a || b) : (a && b);
 		if (!rm)
 			continue;
 
-		gfs2_ail2_empty_one(sdp, ai);
-		list_del(&ai->ai_list);
-		gfs2_assert_warn(sdp, list_empty(&ai->ai_ail1_list));
-		gfs2_assert_warn(sdp, list_empty(&ai->ai_ail2_list));
-		kfree(ai);
+		gfs2_ail2_empty_one(sdp, tr);
+		list_del(&tr->tr_list);
+		gfs2_assert_warn(sdp, list_empty(&tr->tr_ail1_list));
+		gfs2_assert_warn(sdp, list_empty(&tr->tr_ail2_list));
+		kfree(tr);
 	}
 
 	spin_unlock(&sdp->sd_ail_lock);
 }
 
 /**
+ * gfs2_log_release - Release a given number of log blocks
+ * @sdp: The GFS2 superblock
+ * @blks: The number of blocks
+ *
+ */
+
+void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks)
+{
+
+	atomic_add(blks, &sdp->sd_log_blks_free);
+	trace_gfs2_log_blocks(sdp, blks);
+	gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <=
+				  sdp->sd_jdesc->jd_blocks);
+	up_read(&sdp->sd_log_flush_lock);
+}
+
+/**
  * gfs2_log_reserve - Make a log reservation
  * @sdp: The GFS2 superblock
  * @blks: The number of blocks to reserve
@@ -318,7 +339,7 @@ static void ail2_empty(struct gfs2_sbd *sdp, unsigned int new_tail)
 
 int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks)
 {
-	unsigned reserved_blks = 6 * (4096 / sdp->sd_vfs->s_blocksize);
+	unsigned reserved_blks = 7 * (4096 / sdp->sd_vfs->s_blocksize);
 	unsigned wanted = blks + reserved_blks;
 	DEFINE_WAIT(wait);
 	int did_wait = 0;
@@ -354,20 +375,11 @@ retry:
 		wake_up(&sdp->sd_log_waitq);
 
 	down_read(&sdp->sd_log_flush_lock);
-
-	return 0;
-}
-
-static u64 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;
+	if (unlikely(!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))) {
+		gfs2_log_release(sdp, blks);
+		return -EROFS;
 	}
-
-	return -1;
+	return 0;
 }
 
 /**
@@ -422,24 +434,22 @@ static inline unsigned int log_distance(struct gfs2_sbd *sdp, unsigned int newer
 static unsigned int calc_reserved(struct gfs2_sbd *sdp)
 {
 	unsigned int reserved = 0;
-	unsigned int mbuf_limit, metabufhdrs_needed;
-	unsigned int dbuf_limit, databufhdrs_needed;
-	unsigned int revokes = 0;
-
-	mbuf_limit = buf_limit(sdp);
-	metabufhdrs_needed = (sdp->sd_log_commited_buf +
-			      (mbuf_limit - 1)) / mbuf_limit;
-	dbuf_limit = databuf_limit(sdp);
-	databufhdrs_needed = (sdp->sd_log_commited_databuf +
-			      (dbuf_limit - 1)) / dbuf_limit;
+	unsigned int mbuf;
+	unsigned int dbuf;
+	struct gfs2_trans *tr = sdp->sd_log_tr;
+
+	if (tr) {
+		mbuf = tr->tr_num_buf_new - tr->tr_num_buf_rm;
+		dbuf = tr->tr_num_databuf_new - tr->tr_num_databuf_rm;
+		reserved = mbuf + dbuf;
+		/* Account for header blocks */
+		reserved += DIV_ROUND_UP(mbuf, buf_limit(sdp));
+		reserved += DIV_ROUND_UP(dbuf, databuf_limit(sdp));
+	}
 
 	if (sdp->sd_log_commited_revoke > 0)
-		revokes = gfs2_struct2blk(sdp, sdp->sd_log_commited_revoke,
+		reserved += gfs2_struct2blk(sdp, sdp->sd_log_commited_revoke,
 					  sizeof(u64));
-
-	reserved = sdp->sd_log_commited_buf + metabufhdrs_needed +
-		sdp->sd_log_commited_databuf + databufhdrs_needed +
-		revokes;
 	/* One for the overall header */
 	if (reserved)
 		reserved++;
@@ -448,7 +458,7 @@ static unsigned int calc_reserved(struct gfs2_sbd *sdp)
 
 static unsigned int current_tail(struct gfs2_sbd *sdp)
 {
-	struct gfs2_ail *ai;
+	struct gfs2_trans *tr;
 	unsigned int tail;
 
 	spin_lock(&sdp->sd_ail_lock);
@@ -456,8 +466,9 @@ static unsigned int current_tail(struct gfs2_sbd *sdp)
 	if (list_empty(&sdp->sd_ail1_list)) {
 		tail = sdp->sd_log_head;
 	} else {
-		ai = list_entry(sdp->sd_ail1_list.prev, struct gfs2_ail, ai_list);
-		tail = ai->ai_first;
+		tr = list_entry(sdp->sd_ail1_list.prev, struct gfs2_trans,
+				tr_list);
+		tail = tr->tr_first;
 	}
 
 	spin_unlock(&sdp->sd_ail_lock);
@@ -465,122 +476,166 @@ static unsigned int current_tail(struct gfs2_sbd *sdp)
 	return tail;
 }
 
-void gfs2_log_incr_head(struct gfs2_sbd *sdp)
+static void log_pull_tail(struct gfs2_sbd *sdp, unsigned int new_tail)
 {
-	if (sdp->sd_log_flush_head == sdp->sd_log_tail)
-		BUG_ON(sdp->sd_log_flush_head != sdp->sd_log_head);
+	unsigned int dist = log_distance(sdp, new_tail, sdp->sd_log_tail);
 
-	if (++sdp->sd_log_flush_head == sdp->sd_jdesc->jd_blocks) {
-		sdp->sd_log_flush_head = 0;
-		sdp->sd_log_flush_wrapped = 1;
-	}
+	ail2_empty(sdp, new_tail);
+
+	atomic_add(dist, &sdp->sd_log_blks_free);
+	trace_gfs2_log_blocks(sdp, dist);
+	gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <=
+			     sdp->sd_jdesc->jd_blocks);
+
+	sdp->sd_log_tail = new_tail;
 }
 
-/**
- * gfs2_log_write_endio - End of I/O for a log buffer
- * @bh: The buffer head
- * @uptodate: I/O Status
- *
- */
 
-static void gfs2_log_write_endio(struct buffer_head *bh, int uptodate)
+static void log_flush_wait(struct gfs2_sbd *sdp)
 {
-	struct gfs2_sbd *sdp = bh->b_private;
-	bh->b_private = NULL;
+	DEFINE_WAIT(wait);
 
-	end_buffer_write_sync(bh, uptodate);
-	if (atomic_dec_and_test(&sdp->sd_log_in_flight))
-		wake_up(&sdp->sd_log_flush_wait);
+	if (atomic_read(&sdp->sd_log_in_flight)) {
+		do {
+			prepare_to_wait(&sdp->sd_log_flush_wait, &wait,
+					TASK_UNINTERRUPTIBLE);
+			if (atomic_read(&sdp->sd_log_in_flight))
+				io_schedule();
+		} while(atomic_read(&sdp->sd_log_in_flight));
+		finish_wait(&sdp->sd_log_flush_wait, &wait);
+	}
 }
 
-/**
- * gfs2_log_get_buf - Get and initialize a buffer to use for log control data
- * @sdp: The GFS2 superblock
- *
- * Returns: the buffer_head
- */
-
-struct buffer_head *gfs2_log_get_buf(struct gfs2_sbd *sdp)
+static int ip_cmp(void *priv, struct list_head *a, struct list_head *b)
 {
-	u64 blkno = log_bmap(sdp, sdp->sd_log_flush_head);
-	struct buffer_head *bh;
+	struct gfs2_inode *ipa, *ipb;
 
-	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);
-	gfs2_log_incr_head(sdp);
-	atomic_inc(&sdp->sd_log_in_flight);
-	bh->b_private = sdp;
-	bh->b_end_io = gfs2_log_write_endio;
+	ipa = list_entry(a, struct gfs2_inode, i_ordered);
+	ipb = list_entry(b, struct gfs2_inode, i_ordered);
 
-	return bh;
+	if (ipa->i_no_addr < ipb->i_no_addr)
+		return -1;
+	if (ipa->i_no_addr > ipb->i_no_addr)
+		return 1;
+	return 0;
 }
 
-/**
- * gfs2_fake_write_endio - 
- * @bh: The buffer head
- * @uptodate: The I/O Status
- *
- */
-
-static void gfs2_fake_write_endio(struct buffer_head *bh, int uptodate)
+static void gfs2_ordered_write(struct gfs2_sbd *sdp)
 {
-	struct buffer_head *real_bh = bh->b_private;
-	struct gfs2_bufdata *bd = real_bh->b_private;
-	struct gfs2_sbd *sdp = bd->bd_gl->gl_sbd;
+	struct gfs2_inode *ip;
+	LIST_HEAD(written);
 
-	end_buffer_write_sync(bh, uptodate);
-	free_buffer_head(bh);
-	unlock_buffer(real_bh);
-	brelse(real_bh);
-	if (atomic_dec_and_test(&sdp->sd_log_in_flight))
-		wake_up(&sdp->sd_log_flush_wait);
+	spin_lock(&sdp->sd_ordered_lock);
+	list_sort(NULL, &sdp->sd_log_le_ordered, &ip_cmp);
+	while (!list_empty(&sdp->sd_log_le_ordered)) {
+		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;
+		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);
+	spin_unlock(&sdp->sd_ordered_lock);
 }
 
-/**
- * gfs2_log_fake_buf - Build a fake buffer head to write metadata buffer to log
- * @sdp: the filesystem
- * @data: the data the buffer_head should point to
- *
- * Returns: the log buffer descriptor
- */
-
-struct buffer_head *gfs2_log_fake_buf(struct gfs2_sbd *sdp,
-				      struct buffer_head *real)
+static void gfs2_ordered_wait(struct gfs2_sbd *sdp)
 {
-	u64 blkno = log_bmap(sdp, sdp->sd_log_flush_head);
-	struct buffer_head *bh;
+	struct gfs2_inode *ip;
 
-	bh = alloc_buffer_head(GFP_NOFS | __GFP_NOFAIL);
-	atomic_set(&bh->b_count, 1);
-	bh->b_state = (1 << BH_Mapped) | (1 << BH_Uptodate) | (1 << BH_Lock);
-	set_bh_page(bh, real->b_page, bh_offset(real));
-	bh->b_blocknr = blkno;
-	bh->b_size = sdp->sd_sb.sb_bsize;
-	bh->b_bdev = sdp->sd_vfs->s_bdev;
-	bh->b_private = real;
-	bh->b_end_io = gfs2_fake_write_endio;
+	spin_lock(&sdp->sd_ordered_lock);
+	while (!list_empty(&sdp->sd_log_le_ordered)) {
+		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;
+		spin_unlock(&sdp->sd_ordered_lock);
+		filemap_fdatawait(ip->i_inode.i_mapping);
+		spin_lock(&sdp->sd_ordered_lock);
+	}
+	spin_unlock(&sdp->sd_ordered_lock);
+}
 
-	gfs2_log_incr_head(sdp);
-	atomic_inc(&sdp->sd_log_in_flight);
+void gfs2_ordered_del_inode(struct gfs2_inode *ip)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 
-	return bh;
+	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);
 }
 
-static void log_pull_tail(struct gfs2_sbd *sdp, unsigned int new_tail)
+void gfs2_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
 {
-	unsigned int dist = log_distance(sdp, new_tail, sdp->sd_log_tail);
+	struct buffer_head *bh = bd->bd_bh;
+	struct gfs2_glock *gl = bd->bd_gl;
 
-	ail2_empty(sdp, new_tail);
+	bh->b_private = NULL;
+	bd->bd_blkno = bh->b_blocknr;
+	gfs2_remove_from_ail(bd); /* drops ref on bh */
+	bd->bd_bh = NULL;
+	bd->bd_ops = &gfs2_revoke_lops;
+	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);
+}
 
-	atomic_add(dist, &sdp->sd_log_blks_free);
-	trace_gfs2_log_blocks(sdp, dist);
-	gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <=
-			     sdp->sd_jdesc->jd_blocks);
+void gfs2_write_revokes(struct gfs2_sbd *sdp)
+{
+	struct gfs2_trans *tr;
+	struct gfs2_bufdata *bd, *tmp;
+	int have_revokes = 0;
+	int max_revokes = (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_log_descriptor)) / sizeof(u64);
 
-	sdp->sd_log_tail = new_tail;
+	gfs2_ail1_empty(sdp);
+	spin_lock(&sdp->sd_ail_lock);
+	list_for_each_entry(tr, &sdp->sd_ail1_list, tr_list) {
+		list_for_each_entry(bd, &tr->tr_ail2_list, bd_ail_st_list) {
+			if (list_empty(&bd->bd_list)) {
+				have_revokes = 1;
+				goto done;
+			}
+		}
+	}
+done:
+	spin_unlock(&sdp->sd_ail_lock);
+	if (have_revokes == 0)
+		return;
+	while (sdp->sd_log_num_revoke > max_revokes)
+		max_revokes += (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_meta_header)) / sizeof(u64);
+	max_revokes -= sdp->sd_log_num_revoke;
+	if (!sdp->sd_log_num_revoke) {
+		atomic_dec(&sdp->sd_log_blks_free);
+		/* If no blocks have been reserved, we need to also
+		 * reserve a block for the header */
+		if (!sdp->sd_log_blks_reserved)
+			atomic_dec(&sdp->sd_log_blks_free);
+	}
+	gfs2_log_lock(sdp);
+	spin_lock(&sdp->sd_ail_lock);
+	list_for_each_entry(tr, &sdp->sd_ail1_list, tr_list) {
+		list_for_each_entry_safe(bd, tmp, &tr->tr_ail2_list, bd_ail_st_list) {
+			if (max_revokes == 0)
+				goto out_of_blocks;
+			if (!list_empty(&bd->bd_list))
+				continue;
+			gfs2_add_revoke(sdp, bd);
+			max_revokes--;
+		}
+	}
+out_of_blocks:
+	spin_unlock(&sdp->sd_ail_lock);
+	gfs2_log_unlock(sdp);
+
+	if (!sdp->sd_log_num_revoke) {
+		atomic_inc(&sdp->sd_log_blks_free);
+		if (!sdp->sd_log_blks_reserved)
+			atomic_inc(&sdp->sd_log_blks_free);
+	}
 }
 
 /**
@@ -590,25 +645,18 @@ static void log_pull_tail(struct gfs2_sbd *sdp, unsigned int new_tail)
  * 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 = log_bmap(sdp, sdp->sd_log_flush_head);
-	struct buffer_head *bh;
 	struct gfs2_log_header *lh;
 	unsigned int tail;
 	u32 hash;
+	int rw = WRITE_FLUSH_FUA | REQ_META;
+	struct page *page = mempool_alloc(gfs2_page_pool, GFP_NOIO);
+	lh = page_address(page);
+	clear_page(lh);
 
-	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);
-
-	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);
@@ -618,96 +666,22 @@ 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))
-		submit_bh(WRITE_SYNC | REQ_META | REQ_PRIO, bh);
-	else
-		submit_bh(WRITE_FLUSH_FUA | REQ_META, bh);
-	wait_on_buffer(bh);
+	if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags)) {
+		gfs2_ordered_wait(sdp);
+		log_flush_wait(sdp);
+		rw = WRITE_SYNC | REQ_META | REQ_PRIO;
+	}
 
-	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);
-}
-
-static void log_flush_commit(struct gfs2_sbd *sdp)
-{
-	DEFINE_WAIT(wait);
-
-	if (atomic_read(&sdp->sd_log_in_flight)) {
-		do {
-			prepare_to_wait(&sdp->sd_log_flush_wait, &wait,
-					TASK_UNINTERRUPTIBLE);
-			if (atomic_read(&sdp->sd_log_in_flight))
-				io_schedule();
-		} while(atomic_read(&sdp->sd_log_in_flight));
-		finish_wait(&sdp->sd_log_flush_wait, &wait);
-	}
-
-	log_write_header(sdp, 0, 0);
-}
-
-static void gfs2_ordered_write(struct gfs2_sbd *sdp)
-{
-	struct gfs2_bufdata *bd;
-	struct buffer_head *bh;
-	LIST_HEAD(written);
-
-	gfs2_log_lock(sdp);
-	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);
-		bh = bd->bd_bh;
-		if (!buffer_dirty(bh))
-			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);
-	}
-	list_splice(&written, &sdp->sd_log_le_ordered);
-	gfs2_log_unlock(sdp);
-}
-
-static void gfs2_ordered_wait(struct gfs2_sbd *sdp)
-{
-	struct gfs2_bufdata *bd;
-	struct buffer_head *bh;
-
-	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);
-		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);
-			continue;
-		}
-		list_del_init(&bd->bd_le.le_list);
-	}
-	gfs2_log_unlock(sdp);
 }
 
 /**
@@ -717,9 +691,10 @@ static void gfs2_ordered_wait(struct gfs2_sbd *sdp)
  *
  */
 
-void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
+void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl,
+		    enum gfs2_flush_type type)
 {
-	struct gfs2_ail *ai;
+	struct gfs2_trans *tr;
 
 	down_write(&sdp->sd_log_flush_lock);
 
@@ -730,78 +705,129 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
 	}
 	trace_gfs2_log_flush(sdp, 1);
 
-	ai = kzalloc(sizeof(struct gfs2_ail), GFP_NOFS | __GFP_NOFAIL);
-	INIT_LIST_HEAD(&ai->ai_ail1_list);
-	INIT_LIST_HEAD(&ai->ai_ail2_list);
-
-	if (sdp->sd_log_num_buf != sdp->sd_log_commited_buf) {
-		printk(KERN_INFO "GFS2: log buf %u %u\n", sdp->sd_log_num_buf,
-		       sdp->sd_log_commited_buf);
-		gfs2_assert_withdraw(sdp, 0);
-	}
-	if (sdp->sd_log_num_databuf != sdp->sd_log_commited_databuf) {
-		printk(KERN_INFO "GFS2: log databuf %u %u\n",
-		       sdp->sd_log_num_databuf, sdp->sd_log_commited_databuf);
-		gfs2_assert_withdraw(sdp, 0);
+	sdp->sd_log_flush_head = sdp->sd_log_head;
+	sdp->sd_log_flush_wrapped = 0;
+	tr = sdp->sd_log_tr;
+	if (tr) {
+		sdp->sd_log_tr = NULL;
+		INIT_LIST_HEAD(&tr->tr_ail1_list);
+		INIT_LIST_HEAD(&tr->tr_ail2_list);
+		tr->tr_first = sdp->sd_log_flush_head;
 	}
+
 	gfs2_assert_withdraw(sdp,
 			sdp->sd_log_num_revoke == sdp->sd_log_commited_revoke);
 
-	sdp->sd_log_flush_head = sdp->sd_log_head;
-	sdp->sd_log_flush_wrapped = 0;
-	ai->ai_first = sdp->sd_log_flush_head;
-
 	gfs2_ordered_write(sdp);
-	lops_before_commit(sdp);
-	gfs2_ordered_wait(sdp);
+	lops_before_commit(sdp, tr);
+	gfs2_log_flush_bio(sdp, WRITE);
 
-	if (sdp->sd_log_head != sdp->sd_log_flush_head)
-		log_flush_commit(sdp);
-	else if (sdp->sd_log_tail != current_tail(sdp) && !sdp->sd_log_idle){
-		gfs2_log_lock(sdp);
+	if (sdp->sd_log_head != sdp->sd_log_flush_head) {
+		log_flush_wait(sdp);
+		log_write_header(sdp, 0);
+	} else if (sdp->sd_log_tail != current_tail(sdp) && !sdp->sd_log_idle){
 		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);
+	lops_after_commit(sdp, tr);
 
 	gfs2_log_lock(sdp);
 	sdp->sd_log_head = sdp->sd_log_flush_head;
 	sdp->sd_log_blks_reserved = 0;
-	sdp->sd_log_commited_buf = 0;
-	sdp->sd_log_commited_databuf = 0;
 	sdp->sd_log_commited_revoke = 0;
 
 	spin_lock(&sdp->sd_ail_lock);
-	if (!list_empty(&ai->ai_ail1_list)) {
-		list_add(&ai->ai_list, &sdp->sd_ail1_list);
-		ai = NULL;
+	if (tr && !list_empty(&tr->tr_ail1_list)) {
+		list_add(&tr->tr_list, &sdp->sd_ail1_list);
+		tr = NULL;
 	}
 	spin_unlock(&sdp->sd_ail_lock);
 	gfs2_log_unlock(sdp);
+
+	if (atomic_read(&sdp->sd_log_freeze))
+		type = FREEZE_FLUSH;
+	if (type != NORMAL_FLUSH) {
+		if (!sdp->sd_log_idle) {
+			for (;;) {
+				gfs2_ail1_start(sdp);
+				gfs2_ail1_wait(sdp);
+				if (gfs2_ail1_empty(sdp))
+					break;
+			}
+			atomic_dec(&sdp->sd_log_blks_free); /* Adjust for unreserved buffer */
+			trace_gfs2_log_blocks(sdp, -1);
+			sdp->sd_log_flush_wrapped = 0;
+			log_write_header(sdp, 0);
+			sdp->sd_log_head = sdp->sd_log_flush_head;
+		}
+		if (type == SHUTDOWN_FLUSH || type == FREEZE_FLUSH)
+			gfs2_log_shutdown(sdp);
+		if (type == FREEZE_FLUSH) {
+			int error;
+
+			atomic_set(&sdp->sd_log_freeze, 0);
+			wake_up(&sdp->sd_log_frozen_wait);
+			error = gfs2_glock_nq_init(sdp->sd_freeze_gl,
+						   LM_ST_SHARED, 0,
+						   &sdp->sd_thaw_gh);
+			if (error) {
+				printk(KERN_INFO "GFS2: couln't get freeze lock : %d\n", error);
+				gfs2_assert_withdraw(sdp, 0);
+			}
+			else
+				gfs2_glock_dq_uninit(&sdp->sd_thaw_gh);
+		}
+	}
+
 	trace_gfs2_log_flush(sdp, 0);
 	up_write(&sdp->sd_log_flush_lock);
 
-	kfree(ai);
+	kfree(tr);
+}
+
+/**
+ * gfs2_merge_trans - Merge a new transaction into a cached transaction
+ * @old: Original transaction to be expanded
+ * @new: New transaction to be merged
+ */
+
+static void gfs2_merge_trans(struct gfs2_trans *old, struct gfs2_trans *new)
+{
+	WARN_ON_ONCE(old->tr_attached != 1);
+
+	old->tr_num_buf_new	+= new->tr_num_buf_new;
+	old->tr_num_databuf_new	+= new->tr_num_databuf_new;
+	old->tr_num_buf_rm	+= new->tr_num_buf_rm;
+	old->tr_num_databuf_rm	+= new->tr_num_databuf_rm;
+	old->tr_num_revoke	+= new->tr_num_revoke;
+	old->tr_num_revoke_rm	+= new->tr_num_revoke_rm;
+
+	list_splice_tail_init(&new->tr_databuf, &old->tr_databuf);
+	list_splice_tail_init(&new->tr_buf, &old->tr_buf);
 }
 
 static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 {
 	unsigned int reserved;
 	unsigned int unused;
+	unsigned int maxres;
 
 	gfs2_log_lock(sdp);
 
-	sdp->sd_log_commited_buf += tr->tr_num_buf_new - tr->tr_num_buf_rm;
-	sdp->sd_log_commited_databuf += tr->tr_num_databuf_new -
-		tr->tr_num_databuf_rm;
-	gfs2_assert_withdraw(sdp, (((int)sdp->sd_log_commited_buf) >= 0) ||
-			     (((int)sdp->sd_log_commited_databuf) >= 0));
+	if (sdp->sd_log_tr) {
+		gfs2_merge_trans(sdp->sd_log_tr, tr);
+	} else if (tr->tr_num_buf_new || tr->tr_num_databuf_new) {
+		gfs2_assert_withdraw(sdp, tr->tr_alloced);
+		sdp->sd_log_tr = tr;
+		tr->tr_attached = 1;
+	}
+
 	sdp->sd_log_commited_revoke += tr->tr_num_revoke - tr->tr_num_revoke_rm;
 	reserved = calc_reserved(sdp);
-	gfs2_assert_withdraw(sdp, sdp->sd_log_blks_reserved + tr->tr_reserved >= reserved);
-	unused = sdp->sd_log_blks_reserved - reserved + tr->tr_reserved;
+	maxres = sdp->sd_log_blks_reserved + tr->tr_reserved;
+	gfs2_assert_withdraw(sdp, maxres >= reserved);
+	unused = maxres - reserved;
 	atomic_add(unused, &sdp->sd_log_blks_free);
 	trace_gfs2_log_blocks(sdp, unused);
 	gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <=
@@ -811,21 +837,6 @@ 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
@@ -844,9 +855,6 @@ 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) ||
 	    ((sdp->sd_jdesc->jd_blocks - atomic_read(&sdp->sd_log_blks_free)) >
@@ -862,53 +870,25 @@ void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 
 void gfs2_log_shutdown(struct gfs2_sbd *sdp)
 {
-	down_write(&sdp->sd_log_flush_lock);
-
 	gfs2_assert_withdraw(sdp, !sdp->sd_log_blks_reserved);
-	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_buf);
 	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke);
-	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_rg);
-	gfs2_assert_withdraw(sdp, !sdp->sd_log_num_databuf);
 	gfs2_assert_withdraw(sdp, list_empty(&sdp->sd_ail1_list));
 
 	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);
 	gfs2_assert_warn(sdp, list_empty(&sdp->sd_ail2_list));
 
 	sdp->sd_log_head = sdp->sd_log_flush_head;
 	sdp->sd_log_tail = sdp->sd_log_head;
-
-	up_write(&sdp->sd_log_flush_lock);
-}
-
-
-/**
- * gfs2_meta_syncfs - sync all the buffers in a filesystem
- * @sdp: the filesystem
- *
- */
-
-void gfs2_meta_syncfs(struct gfs2_sbd *sdp)
-{
-	gfs2_log_flush(sdp, NULL);
-	for (;;) {
-		gfs2_ail1_start(sdp);
-		gfs2_ail1_wait(sdp);
-		if (gfs2_ail1_empty(sdp))
-			break;
-	}
-	gfs2_log_flush(sdp, NULL);
 }
 
 static inline int gfs2_jrnl_flush_reqd(struct gfs2_sbd *sdp)
 {
-	return (atomic_read(&sdp->sd_log_pinned) >= atomic_read(&sdp->sd_log_thresh1));
+	return (atomic_read(&sdp->sd_log_pinned) >= atomic_read(&sdp->sd_log_thresh1) || atomic_read(&sdp->sd_log_freeze));
 }
 
 static inline int gfs2_ail_flush_reqd(struct gfs2_sbd *sdp)
@@ -930,21 +910,19 @@ 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);
+			gfs2_log_flush(sdp, NULL, NORMAL_FLUSH);
 		}
 
 		if (gfs2_ail_flush_reqd(sdp)) {
 			gfs2_ail1_start(sdp);
 			gfs2_ail1_wait(sdp);
 			gfs2_ail1_empty(sdp);
-			gfs2_log_flush(sdp, NULL);
+			gfs2_log_flush(sdp, NULL, NORMAL_FLUSH);
 		}
 
 		if (!gfs2_ail_flush_reqd(sdp))