Merge tag 'gfs2-merge-window' of git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-3.0-nmw

Pull GFS2 updates from Steven Whitehouse:
 "One of the main highlights this time, is not the patches themselves
  but instead the widening contributor base.  It is good to see that
  interest is increasing in GFS2, and I'd like to thank all the
  contributors to this patch set.

  In addition to the usual set of bug fixes and clean ups, there are
  patches to improve inode creation performance when xattrs are required
  and some improvements to the transaction code which is intended to
  help improve scalability after further changes in due course.

  Journal extent mapping is also updated to make it more efficient and
  again, this is a foundation for future work in this area.

  The maximum number of ACLs has been increased to 300 (for a 4k block
  size) which means that even with a few additional xattrs from selinux,
  everything should fit within a single fs block.

  There is also a patch to bring GFS2's own copy of the writepages code
  up to the same level as the core VFS.  Eventually we may be able to
  merge some of this code, since it is fairly similar.

  The other major change this time, is bringing consistency to the
  printing of messages via fs_<level>, pr_<level> macros"

* tag 'gfs2-merge-window' of git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-3.0-nmw: (29 commits)
  GFS2: Fix address space from page function
  GFS2: Fix uninitialized VFS inode in gfs2_create_inode
  GFS2: Fix return value in slot_get()
  GFS2: inline function gfs2_set_mode
  GFS2: Remove extraneous function gfs2_security_init
  GFS2: Increase the max number of ACLs
  GFS2: Re-add a call to log_flush_wait when flushing the journal
  GFS2: Ensure workqueue is scheduled after noexp request
  GFS2: check NULL return value in gfs2_ok_to_move
  GFS2: Convert gfs2_lm_withdraw to use fs_err
  GFS2: Use fs_<level> more often
  GFS2: Use pr_<level> more consistently
  GFS2: Move recovery variables to journal structure in memory
  GFS2: global conversion to pr_foo()
  GFS2: return -E2BIG if hit the maximum limits of ACLs
  GFS2: Clean up journal extent mapping
  GFS2: replace kmalloc - __vmalloc / memset 0
  GFS2: Remove extra "if" in gfs2_log_flush()
  fs: NULL dereference in posix_acl_to_xattr()
  GFS2: Move log buffer accounting to transaction
  ...

28 files changed, 604 insertions, 437 deletions

diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c
index ba9456685f47..3088e2a38e30 100644
--- a/fs/gfs2/acl.c
+++ b/fs/gfs2/acl.c
@@ -64,18 +64,6 @@ struct posix_acl *gfs2_get_acl(struct inode *inode, int type)
 	return acl;
 }
 
-static int gfs2_set_mode(struct inode *inode, umode_t mode)
-{
-	int error = 0;
-
-	if (mode != inode->i_mode) {
-		inode->i_mode = mode;
-		mark_inode_dirty(inode);
-	}
-
-	return error;
-}
-
 int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 {
 	int error;
@@ -85,8 +73,8 @@ int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 
 	BUG_ON(name == NULL);
 
-	if (acl->a_count > GFS2_ACL_MAX_ENTRIES)
-		return -EINVAL;
+	if (acl->a_count > GFS2_ACL_MAX_ENTRIES(GFS2_SB(inode)))
+		return -E2BIG;
 
 	if (type == ACL_TYPE_ACCESS) {
 		umode_t mode = inode->i_mode;
@@ -98,9 +86,10 @@ int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 		if (error == 0)
 			acl = NULL;
 
-		error = gfs2_set_mode(inode, mode);
-		if (error)
-			return error;
+		if (mode != inode->i_mode) {
+			inode->i_mode = mode;
+			mark_inode_dirty(inode);
+		}
 	}
 
 	if (acl) {
diff --git a/fs/gfs2/acl.h b/fs/gfs2/acl.h
index 301260c999ba..2d65ec4cd4be 100644
--- a/fs/gfs2/acl.h
+++ b/fs/gfs2/acl.h
@@ -14,7 +14,7 @@
 
 #define GFS2_POSIX_ACL_ACCESS		"posix_acl_access"
 #define GFS2_POSIX_ACL_DEFAULT		"posix_acl_default"
-#define GFS2_ACL_MAX_ENTRIES		25
+#define GFS2_ACL_MAX_ENTRIES(sdp) ((300 << (sdp)->sd_sb.sb_bsize_shift) >> 12)
 
 extern struct posix_acl *gfs2_get_acl(struct inode *inode, int type);
 extern int gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type);
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 49436fa7cd4f..ce62dcac90b6 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -21,6 +21,7 @@
 #include <linux/gfs2_ondisk.h>
 #include <linux/backing-dev.h>
 #include <linux/aio.h>
+#include <trace/events/writeback.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -230,13 +231,11 @@ static int gfs2_writepages(struct address_space *mapping,
 static int gfs2_write_jdata_pagevec(struct address_space *mapping,
 				    struct writeback_control *wbc,
 				    struct pagevec *pvec,
-				    int nr_pages, pgoff_t end)
+				    int nr_pages, pgoff_t end,
+				    pgoff_t *done_index)
 {
 	struct inode *inode = mapping->host;
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	loff_t i_size = i_size_read(inode);
-	pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
-	unsigned offset = i_size & (PAGE_CACHE_SIZE-1);
 	unsigned nrblocks = nr_pages * (PAGE_CACHE_SIZE/inode->i_sb->s_blocksize);
 	int i;
 	int ret;
@@ -248,40 +247,83 @@ static int gfs2_write_jdata_pagevec(struct address_space *mapping,
 	for(i = 0; i < nr_pages; i++) {
 		struct page *page = pvec->pages[i];
 
+		/*
+		 * At this point, the page may be truncated or
+		 * invalidated (changing page->mapping to NULL), or
+		 * even swizzled back from swapper_space to tmpfs file
+		 * mapping. However, page->index will not change
+		 * because we have a reference on the page.
+		 */
+		if (page->index > end) {
+			/*
+			 * can't be range_cyclic (1st pass) because
+			 * end == -1 in that case.
+			 */
+			ret = 1;
+			break;
+		}
+
+		*done_index = page->index;
+
 		lock_page(page);
 
 		if (unlikely(page->mapping != mapping)) {
+continue_unlock:
 			unlock_page(page);
 			continue;
 		}
 
-		if (!wbc->range_cyclic && page->index > end) {
-			ret = 1;
-			unlock_page(page);
-			continue;
+		if (!PageDirty(page)) {
+			/* someone wrote it for us */
+			goto continue_unlock;
 		}
 
-		if (wbc->sync_mode != WB_SYNC_NONE)
-			wait_on_page_writeback(page);
-
-		if (PageWriteback(page) ||
-		    !clear_page_dirty_for_io(page)) {
-			unlock_page(page);
-			continue;
+		if (PageWriteback(page)) {
+			if (wbc->sync_mode != WB_SYNC_NONE)
+				wait_on_page_writeback(page);
+			else
+				goto continue_unlock;
 		}
 
-		/* Is the page fully outside i_size? (truncate in progress) */
-		if (page->index > end_index || (page->index == end_index && !offset)) {
-			page->mapping->a_ops->invalidatepage(page, 0,
-							     PAGE_CACHE_SIZE);
-			unlock_page(page);
-			continue;
-		}
+		BUG_ON(PageWriteback(page));
+		if (!clear_page_dirty_for_io(page))
+			goto continue_unlock;
+
+		trace_wbc_writepage(wbc, mapping->backing_dev_info);
 
 		ret = __gfs2_jdata_writepage(page, wbc);
+		if (unlikely(ret)) {
+			if (ret == AOP_WRITEPAGE_ACTIVATE) {
+				unlock_page(page);
+				ret = 0;
+			} else {
+
+				/*
+				 * done_index is set past this page,
+				 * so media errors will not choke
+				 * background writeout for the entire
+				 * file. This has consequences for
+				 * range_cyclic semantics (ie. it may
+				 * not be suitable for data integrity
+				 * writeout).
+				 */
+				*done_index = page->index + 1;
+				ret = 1;
+				break;
+			}
+		}
 
-		if (ret || (--(wbc->nr_to_write) <= 0))
+		/*
+		 * We stop writing back only if we are not doing
+		 * integrity sync. In case of integrity sync we have to
+		 * keep going until we have written all the pages
+		 * we tagged for writeback prior to entering this loop.
+		 */
+		if (--wbc->nr_to_write <= 0 && wbc->sync_mode == WB_SYNC_NONE) {
 			ret = 1;
+			break;
+		}
+
 	}
 	gfs2_trans_end(sdp);
 	return ret;
@@ -306,51 +348,69 @@ static int gfs2_write_cache_jdata(struct address_space *mapping,
 	int done = 0;
 	struct pagevec pvec;
 	int nr_pages;
+	pgoff_t uninitialized_var(writeback_index);
 	pgoff_t index;
 	pgoff_t end;
-	int scanned = 0;
+	pgoff_t done_index;
+	int cycled;
 	int range_whole = 0;
+	int tag;
 
 	pagevec_init(&pvec, 0);
 	if (wbc->range_cyclic) {
-		index = mapping->writeback_index; /* Start from prev offset */
+		writeback_index = mapping->writeback_index; /* prev offset */
+		index = writeback_index;
+		if (index == 0)
+			cycled = 1;
+		else
+			cycled = 0;
 		end = -1;
 	} else {
 		index = wbc->range_start >> PAGE_CACHE_SHIFT;
 		end = wbc->range_end >> PAGE_CACHE_SHIFT;
 		if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
 			range_whole = 1;
-		scanned = 1;
+		cycled = 1; /* ignore range_cyclic tests */
 	}
+	if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
+		tag = PAGECACHE_TAG_TOWRITE;
+	else
+		tag = PAGECACHE_TAG_DIRTY;
 
 retry:
-	 while (!done && (index <= end) &&
-		(nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
-					       PAGECACHE_TAG_DIRTY,
-					       min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
-		scanned = 1;
-		ret = gfs2_write_jdata_pagevec(mapping, wbc, &pvec, nr_pages, end);
+	if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
+		tag_pages_for_writeback(mapping, index, end);
+	done_index = index;
+	while (!done && (index <= end)) {
+		nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
+			      min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
+		if (nr_pages == 0)
+			break;
+
+		ret = gfs2_write_jdata_pagevec(mapping, wbc, &pvec, nr_pages, end, &done_index);
 		if (ret)
 			done = 1;
 		if (ret > 0)
 			ret = 0;
-
 		pagevec_release(&pvec);
 		cond_resched();
 	}
 
-	if (!scanned && !done) {
+	if (!cycled && !done) {
 		/*
+		 * range_cyclic:
 		 * We hit the last page and there is more work to be done: wrap
 		 * back to the start of the file
 		 */
-		scanned = 1;
+		cycled = 1;
 		index = 0;
+		end = writeback_index - 1;
 		goto retry;
 	}
 
 	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
-		mapping->writeback_index = index;
+		mapping->writeback_index = done_index;
+
 	return ret;
 }
 
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index fe0500c0af7a..c62d4b9f51dc 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -1328,6 +1328,121 @@ int gfs2_file_dealloc(struct gfs2_inode *ip)
 }
 
 /**
+ * gfs2_free_journal_extents - Free cached journal bmap info
+ * @jd: The journal
+ *
+ */
+
+void gfs2_free_journal_extents(struct gfs2_jdesc *jd)
+{
+	struct gfs2_journal_extent *jext;
+
+	while(!list_empty(&jd->extent_list)) {
+		jext = list_entry(jd->extent_list.next, struct gfs2_journal_extent, list);
+		list_del(&jext->list);
+		kfree(jext);
+	}
+}
+
+/**
+ * gfs2_add_jextent - Add or merge a new extent to extent cache
+ * @jd: The journal descriptor
+ * @lblock: The logical block at start of new extent
+ * @pblock: The physical block at start of new extent
+ * @blocks: Size of extent in fs blocks
+ *
+ * Returns: 0 on success or -ENOMEM
+ */
+
+static int gfs2_add_jextent(struct gfs2_jdesc *jd, u64 lblock, u64 dblock, u64 blocks)
+{
+	struct gfs2_journal_extent *jext;
+
+	if (!list_empty(&jd->extent_list)) {
+		jext = list_entry(jd->extent_list.prev, struct gfs2_journal_extent, list);
+		if ((jext->dblock + jext->blocks) == dblock) {
+			jext->blocks += blocks;
+			return 0;
+		}
+	}
+
+	jext = kzalloc(sizeof(struct gfs2_journal_extent), GFP_NOFS);
+	if (jext == NULL)
+		return -ENOMEM;
+	jext->dblock = dblock;
+	jext->lblock = lblock;
+	jext->blocks = blocks;
+	list_add_tail(&jext->list, &jd->extent_list);
+	jd->nr_extents++;
+	return 0;
+}
+
+/**
+ * gfs2_map_journal_extents - Cache journal bmap info
+ * @sdp: The super block
+ * @jd: The journal to map
+ *
+ * Create a reusable "extent" mapping from all logical
+ * blocks to all physical blocks for the given journal.  This will save
+ * us time when writing journal blocks.  Most journals will have only one
+ * extent that maps all their logical blocks.  That's because gfs2.mkfs
+ * arranges the journal blocks sequentially to maximize performance.
+ * So the extent would map the first block for the entire file length.
+ * However, gfs2_jadd can happen while file activity is happening, so
+ * those journals may not be sequential.  Less likely is the case where
+ * the users created their own journals by mounting the metafs and
+ * laying it out.  But it's still possible.  These journals might have
+ * several extents.
+ *
+ * Returns: 0 on success, or error on failure
+ */
+
+int gfs2_map_journal_extents(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd)
+{
+	u64 lblock = 0;
+	u64 lblock_stop;
+	struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
+	struct buffer_head bh;
+	unsigned int shift = sdp->sd_sb.sb_bsize_shift;
+	u64 size;
+	int rc;
+
+	lblock_stop = i_size_read(jd->jd_inode) >> shift;
+	size = (lblock_stop - lblock) << shift;
+	jd->nr_extents = 0;
+	WARN_ON(!list_empty(&jd->extent_list));
+
+	do {
+		bh.b_state = 0;
+		bh.b_blocknr = 0;
+		bh.b_size = size;
+		rc = gfs2_block_map(jd->jd_inode, lblock, &bh, 0);
+		if (rc || !buffer_mapped(&bh))
+			goto fail;
+		rc = gfs2_add_jextent(jd, lblock, bh.b_blocknr, bh.b_size >> shift);
+		if (rc)
+			goto fail;
+		size -= bh.b_size;
+		lblock += (bh.b_size >> ip->i_inode.i_blkbits);
+	} while(size > 0);
+
+	fs_info(sdp, "journal %d mapped with %u extents\n", jd->jd_jid,
+		jd->nr_extents);
+	return 0;
+
+fail:
+	fs_warn(sdp, "error %d mapping journal %u at offset %llu (extent %u)\n",
+		rc, jd->jd_jid,
+		(unsigned long long)(i_size_read(jd->jd_inode) - size),
+		jd->nr_extents);
+	fs_warn(sdp, "bmap=%d lblock=%llu block=%llu, state=0x%08lx, size=%llu\n",
+		rc, (unsigned long long)lblock, (unsigned long long)bh.b_blocknr,
+		bh.b_state, (unsigned long long)bh.b_size);
+	gfs2_free_journal_extents(jd);
+	return rc;
+}
+
+/**
  * gfs2_write_alloc_required - figure out if a write will require an allocation
  * @ip: the file being written to
  * @offset: the offset to write to
diff --git a/fs/gfs2/bmap.h b/fs/gfs2/bmap.h
index 42fea03e2bd9..81ded5e2aaa2 100644
--- a/fs/gfs2/bmap.h
+++ b/fs/gfs2/bmap.h
@@ -55,5 +55,7 @@ extern int gfs2_truncatei_resume(struct gfs2_inode *ip);
 extern int gfs2_file_dealloc(struct gfs2_inode *ip);
 extern int gfs2_write_alloc_required(struct gfs2_inode *ip, u64 offset,
 				     unsigned int len);
+extern int gfs2_map_journal_extents(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd);
+extern void gfs2_free_journal_extents(struct gfs2_jdesc *jd);
 
 #endif /* __BMAP_DOT_H__ */
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index fa32655449c8..1a349f9a9685 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -53,6 +53,8 @@
  * but never before the maximum hash table size has been reached.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/buffer_head.h>
@@ -507,8 +509,8 @@ static int gfs2_check_dirent(struct gfs2_dirent *dent, unsigned int offset,
 		goto error;
 	return 0;
 error:
-	printk(KERN_WARNING "gfs2_check_dirent: %s (%s)\n", msg,
-	       first ? "first in block" : "not first in block");
+	pr_warn("%s: %s (%s)\n",
+		__func__, msg, first ? "first in block" : "not first in block");
 	return -EIO;
 }
 
@@ -531,8 +533,7 @@ static int gfs2_dirent_offset(const void *buf)
 	}
 	return offset;
 wrong_type:
-	printk(KERN_WARNING "gfs2_scan_dirent: wrong block type %u\n",
-	       be32_to_cpu(h->mh_type));
+	pr_warn("%s: wrong block type %u\n", __func__, be32_to_cpu(h->mh_type));
 	return -1;
 }
 
@@ -728,7 +729,7 @@ static int get_leaf(struct gfs2_inode *dip, u64 leaf_no,
 
 	error = gfs2_meta_read(dip->i_gl, leaf_no, DIO_WAIT, bhp);
 	if (!error && gfs2_metatype_check(GFS2_SB(&dip->i_inode), *bhp, GFS2_METATYPE_LF)) {
-		/* printk(KERN_INFO "block num=%llu\n", leaf_no); */
+		/* pr_info("block num=%llu\n", leaf_no); */
 		error = -EIO;
 	}
 
@@ -1006,7 +1007,8 @@ static int dir_split_leaf(struct inode *inode, const struct qstr *name)
 	len = 1 << (dip->i_depth - be16_to_cpu(oleaf->lf_depth));
 	half_len = len >> 1;
 	if (!half_len) {
-		printk(KERN_WARNING "i_depth %u lf_depth %u index %u\n", dip->i_depth, be16_to_cpu(oleaf->lf_depth), index);
+		pr_warn("i_depth %u lf_depth %u index %u\n",
+			dip->i_depth, be16_to_cpu(oleaf->lf_depth), index);
 		gfs2_consist_inode(dip);
 		error = -EIO;
 		goto fail_brelse;
@@ -1684,6 +1686,14 @@ static int dir_new_leaf(struct inode *inode, const struct qstr *name)
 	return 0;
 }
 
+static u16 gfs2_inode_ra_len(const struct gfs2_inode *ip)
+{
+	u64 where = ip->i_no_addr + 1;
+	if (ip->i_eattr == where)
+		return 1;
+	return 0;
+}
+
 /**
  * gfs2_dir_add - Add new filename into directory
  * @inode: The directory inode
@@ -1721,6 +1731,7 @@ int gfs2_dir_add(struct inode *inode, const struct qstr *name,
 			dent = gfs2_init_dirent(inode, dent, name, bh);
 			gfs2_inum_out(nip, dent);
 			dent->de_type = cpu_to_be16(IF2DT(nip->i_inode.i_mode));
+			dent->de_rahead = cpu_to_be16(gfs2_inode_ra_len(nip));
 			tv = CURRENT_TIME;
 			if (ip->i_diskflags & GFS2_DIF_EXHASH) {
 				leaf = (struct gfs2_leaf *)bh->b_data;
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index efc078f0ee4e..6c794085abac 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -811,6 +811,8 @@ static long gfs2_fallocate(struct file *file, int mode, loff_t offset,
 	loff_t bsize_mask = ~((loff_t)sdp->sd_sb.sb_bsize - 1);
 	loff_t next = (offset + len - 1) >> sdp->sd_sb.sb_bsize_shift;
 	loff_t max_chunk_size = UINT_MAX & bsize_mask;
+	struct gfs2_holder gh;
+
 	next = (next + 1) << sdp->sd_sb.sb_bsize_shift;
 
 	/* We only support the FALLOC_FL_KEEP_SIZE mode */
@@ -831,8 +833,10 @@ static long gfs2_fallocate(struct file *file, int mode, loff_t offset,
 	if (error)
 		return error;
 
-	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &ip->i_gh);
-	error = gfs2_glock_nq(&ip->i_gh);
+	mutex_lock(&inode->i_mutex);
+
+	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+	error = gfs2_glock_nq(&gh);
 	if (unlikely(error))
 		goto out_uninit;
 
@@ -900,9 +904,10 @@ out_trans_fail:
 out_qunlock:
 	gfs2_quota_unlock(ip);
 out_unlock:
-	gfs2_glock_dq(&ip->i_gh);
+	gfs2_glock_dq(&gh);
 out_uninit:
-	gfs2_holder_uninit(&ip->i_gh);
+	gfs2_holder_uninit(&gh);
+	mutex_unlock(&inode->i_mutex);
 	return error;
 }
 
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index ca0be6c69a26..aec7f73832f0 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -7,6 +7,8 @@
  * of the GNU General Public License version 2.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
@@ -468,7 +470,7 @@ retry:
 			do_xmote(gl, gh, LM_ST_UNLOCKED);
 			break;
 		default: /* Everything else */
-			printk(KERN_ERR "GFS2: wanted %u got %u\n", gl->gl_target, state);
+			pr_err("wanted %u got %u\n", gl->gl_target, state);
 			GLOCK_BUG_ON(gl, 1);
 		}
 		spin_unlock(&gl->gl_spin);
@@ -542,7 +544,7 @@ __acquires(&gl->gl_spin)
 		/* lock_dlm */
 		ret = sdp->sd_lockstruct.ls_ops->lm_lock(gl, target, lck_flags);
 		if (ret) {
-			printk(KERN_ERR "GFS2: lm_lock ret %d\n", ret);
+			pr_err("lm_lock ret %d\n", ret);
 			GLOCK_BUG_ON(gl, 1);
 		}
 	} else { /* lock_nolock */
@@ -935,7 +937,7 @@ void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...)
 		vaf.fmt = fmt;
 		vaf.va = &args;
 
-		printk(KERN_ERR " %pV", &vaf);
+		pr_err("%pV", &vaf);
 	}
 
 	va_end(args);
@@ -1010,13 +1012,13 @@ do_cancel:
 	return;
 
 trap_recursive:
-	printk(KERN_ERR "original: %pSR\n", (void *)gh2->gh_ip);
-	printk(KERN_ERR "pid: %d\n", pid_nr(gh2->gh_owner_pid));
-	printk(KERN_ERR "lock type: %d req lock state : %d\n",
+	pr_err("original: %pSR\n", (void *)gh2->gh_ip);
+	pr_err("pid: %d\n", pid_nr(gh2->gh_owner_pid));
+	pr_err("lock type: %d req lock state : %d\n",
 	       gh2->gh_gl->gl_name.ln_type, gh2->gh_state);
-	printk(KERN_ERR "new: %pSR\n", (void *)gh->gh_ip);
-	printk(KERN_ERR "pid: %d\n", pid_nr(gh->gh_owner_pid));
-	printk(KERN_ERR "lock type: %d req lock state : %d\n",
+	pr_err("new: %pSR\n", (void *)gh->gh_ip);
+	pr_err("pid: %d\n", pid_nr(gh->gh_owner_pid));
+	pr_err("lock type: %d req lock state : %d\n",
 	       gh->gh_gl->gl_name.ln_type, gh->gh_state);
 	gfs2_dump_glock(NULL, gl);
 	BUG();
@@ -1045,9 +1047,13 @@ int gfs2_glock_nq(struct gfs2_holder *gh)
 
 	spin_lock(&gl->gl_spin);
 	add_to_queue(gh);
-	if ((LM_FLAG_NOEXP & gh->gh_flags) &&
-	    test_and_clear_bit(GLF_FROZEN, &gl->gl_flags))
+	if (unlikely((LM_FLAG_NOEXP & gh->gh_flags) &&
+		     test_and_clear_bit(GLF_FROZEN, &gl->gl_flags))) {
 		set_bit(GLF_REPLY_PENDING, &gl->gl_flags);
+		gl->gl_lockref.count++;
+		if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
+			gl->gl_lockref.count--;
+	}
 	run_queue(gl, 1);
 	spin_unlock(&gl->gl_spin);
 
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 3bf0631b5d56..54b66809e818 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -82,6 +82,8 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
 	struct gfs2_trans tr;
 
 	memset(&tr, 0, sizeof(tr));
+	INIT_LIST_HEAD(&tr.tr_buf);
+	INIT_LIST_HEAD(&tr.tr_databuf);
 	tr.tr_revokes = atomic_read(&gl->gl_ail_count);
 
 	if (!tr.tr_revokes)
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index cf0e34400f71..bdf70c18610c 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -52,7 +52,7 @@ struct gfs2_log_header_host {
  */
 
 struct gfs2_log_operations {
-	void (*lo_before_commit) (struct gfs2_sbd *sdp);
+	void (*lo_before_commit) (struct gfs2_sbd *sdp, struct gfs2_trans *tr);
 	void (*lo_after_commit) (struct gfs2_sbd *sdp, struct gfs2_trans *tr);
 	void (*lo_before_scan) (struct gfs2_jdesc *jd,
 				struct gfs2_log_header_host *head, int pass);
@@ -371,6 +371,7 @@ enum {
 	GIF_ALLOC_FAILED	= 2,
 	GIF_SW_PAGED		= 3,
 	GIF_ORDERED		= 4,
+	GIF_FREE_VFS_INODE      = 5,
 };
 
 struct gfs2_inode {
@@ -462,11 +463,11 @@ struct gfs2_trans {
 	unsigned int tr_blocks;
 	unsigned int tr_revokes;
 	unsigned int tr_reserved;
+	unsigned int tr_touched:1;
+	unsigned int tr_attached:1;
 
 	struct gfs2_holder tr_t_gh;
 
-	int tr_touched;
-	int tr_attached;
 
 	unsigned int tr_num_buf_new;
 	unsigned int tr_num_databuf_new;
@@ -476,6 +477,8 @@ struct gfs2_trans {
 	unsigned int tr_num_revoke_rm;
 
 	struct list_head tr_list;
+	struct list_head tr_databuf;
+	struct list_head tr_buf;
 
 	unsigned int tr_first;
 	struct list_head tr_ail1_list;
@@ -483,7 +486,7 @@ struct gfs2_trans {
 };
 
 struct gfs2_journal_extent {
-	struct list_head extent_list;
+	struct list_head list;
 
 	unsigned int lblock; /* First logical block */
 	u64 dblock; /* First disk block */
@@ -493,6 +496,7 @@ struct gfs2_journal_extent {
 struct gfs2_jdesc {
 	struct list_head jd_list;
 	struct list_head extent_list;
+	unsigned int nr_extents;
 	struct work_struct jd_work;
 	struct inode *jd_inode;
 	unsigned long jd_flags;
@@ -500,6 +504,15 @@ struct gfs2_jdesc {
 	unsigned int jd_jid;
 	unsigned int jd_blocks;
 	int jd_recover_error;
+	/* Replay stuff */
+
+	unsigned int jd_found_blocks;
+	unsigned int jd_found_revokes;
+	unsigned int jd_replayed_blocks;
+
+	struct list_head jd_revoke_list;
+	unsigned int jd_replay_tail;
+
 };
 
 struct gfs2_statfs_change_host {
@@ -746,19 +759,12 @@ struct gfs2_sbd {
 
 	struct gfs2_trans *sd_log_tr;
 	unsigned int sd_log_blks_reserved;
-	unsigned int sd_log_commited_buf;
-	unsigned int sd_log_commited_databuf;
 	int sd_log_commited_revoke;
 
 	atomic_t sd_log_pinned;
-	unsigned int sd_log_num_buf;
 	unsigned int sd_log_num_revoke;
-	unsigned int sd_log_num_rg;
-	unsigned int sd_log_num_databuf;
 
-	struct list_head sd_log_le_buf;
 	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;
 
@@ -786,15 +792,6 @@ struct gfs2_sbd {
 	struct list_head sd_ail1_list;
 	struct list_head sd_ail2_list;
 
-	/* Replay stuff */
-
-	struct list_head sd_revoke_list;
-	unsigned int sd_replay_tail;
-
-	unsigned int sd_found_blocks;
-	unsigned int sd_found_revokes;
-	unsigned int sd_replayed_blocks;
-
 	/* For quiescing the filesystem */
 	struct gfs2_holder sd_freeze_gh;
 
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 5c524180c98e..28cc7bf6575a 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -376,12 +376,11 @@ static void munge_mode_uid_gid(const struct gfs2_inode *dip,
 		inode->i_gid = current_fsgid();
 }
 
-static int alloc_dinode(struct gfs2_inode *ip, u32 flags)
+static int alloc_dinode(struct gfs2_inode *ip, u32 flags, unsigned *dblocks)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-	struct gfs2_alloc_parms ap = { .target = RES_DINODE, .aflags = flags, };
+	struct gfs2_alloc_parms ap = { .target = *dblocks, .aflags = flags, };
 	int error;
-	int dblocks = 1;
 
 	error = gfs2_quota_lock_check(ip);
 	if (error)
@@ -391,11 +390,11 @@ static int alloc_dinode(struct gfs2_inode *ip, u32 flags)
 	if (error)
 		goto out_quota;
 
-	error = gfs2_trans_begin(sdp, RES_RG_BIT + RES_STATFS + RES_QUOTA, 0);
+	error = gfs2_trans_begin(sdp, (*dblocks * RES_RG_BIT) + RES_STATFS + RES_QUOTA, 0);
 	if (error)
 		goto out_ipreserv;
 
-	error = gfs2_alloc_blocks(ip, &ip->i_no_addr, &dblocks, 1, &ip->i_generation);
+	error = gfs2_alloc_blocks(ip, &ip->i_no_addr, dblocks, 1, &ip->i_generation);
 	ip->i_no_formal_ino = ip->i_generation;
 	ip->i_inode.i_ino = ip->i_no_addr;
 	ip->i_goal = ip->i_no_addr;
@@ -428,6 +427,33 @@ static void gfs2_init_dir(struct buffer_head *dibh,
 }
 
 /**
+ * gfs2_init_xattr - Initialise an xattr block for a new inode
+ * @ip: The inode in question
+ *
+ * This sets up an empty xattr block for a new inode, ready to
+ * take any ACLs, LSM xattrs, etc.
+ */
+
+static void gfs2_init_xattr(struct gfs2_inode *ip)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct buffer_head *bh;
+	struct gfs2_ea_header *ea;
+
+	bh = gfs2_meta_new(ip->i_gl, ip->i_eattr);
+	gfs2_trans_add_meta(ip->i_gl, bh);
+	gfs2_metatype_set(bh, GFS2_METATYPE_EA, GFS2_FORMAT_EA);
+	gfs2_buffer_clear_tail(bh, sizeof(struct gfs2_meta_header));
+
+	ea = GFS2_EA_BH2FIRST(bh);
+	ea->ea_rec_len = cpu_to_be32(sdp->sd_jbsize);
+	ea->ea_type = GFS2_EATYPE_UNUSED;
+	ea->ea_flags = GFS2_EAFLAG_LAST;
+
+	brelse(bh);
+}
+
+/**
  * init_dinode - Fill in a new dinode structure
  * @dip: The directory this inode is being created in
  * @ip: The inode
@@ -545,13 +571,6 @@ static int gfs2_initxattrs(struct inode *inode, const struct xattr *xattr_array,
 	return err;
 }
 
-static int gfs2_security_init(struct gfs2_inode *dip, struct gfs2_inode *ip,
-			      const struct qstr *qstr)
-{
-	return security_inode_init_security(&ip->i_inode, &dip->i_inode, qstr,
-					    &gfs2_initxattrs, NULL);
-}
-
 /**
  * gfs2_create_inode - Create a new inode
  * @dir: The parent directory
@@ -578,8 +597,9 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
 	struct gfs2_glock *io_gl;
 	struct dentry *d;
-	int error;
+	int error, free_vfs_inode = 0;
 	u32 aflags = 0;
+	unsigned blocks = 1;
 	struct gfs2_diradd da = { .bh = NULL, };
 
 	if (!name->len || name->len > GFS2_FNAMESIZE)
@@ -676,10 +696,15 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	    (dip->i_diskflags & GFS2_DIF_TOPDIR))
 		aflags |= GFS2_AF_ORLOV;
 
-	error = alloc_dinode(ip, aflags);
+	if (default_acl || acl)
+		blocks++;
+
+	error = alloc_dinode(ip, aflags, &blocks);
 	if (error)
 		goto fail_free_inode;
 
+	gfs2_set_inode_blocks(inode, blocks);
+
 	error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl);
 	if (error)
 		goto fail_free_inode;
@@ -689,10 +714,14 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	if (error)
 		goto fail_free_inode;
 
-	error = gfs2_trans_begin(sdp, RES_DINODE, 0);
+	error = gfs2_trans_begin(sdp, blocks, 0);