[Cluster-devel] Current -nmw tree content

[Cluster-devel] Current -nmw tree content

[Steven Whitehouse]

Hi,

To keep everybody uptodate, here is the current content of my -nmw
GFS2 git tree. I'm posting it really because hera is still unavailable
and this is just a way to keep everybody uptodate with the tree
content.

There should be nothing surprising here... its all been posted before
at various times. The main item is the work on the resource group
code,

Steve.

[Cluster-devel] [PATCH 01/19] GFS2: Clean up dir hash table reading

[Steven Whitehouse]

Since there is now only a single caller to gfs2_dir_read_data()
and it has a number of constant arguments, we can factor
those out. Also some tests relating to the inode size were
being done twice.

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

diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index 1cc2f8e..2045d70 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -240,16 +240,15 @@ fail:
 	return error;
 }
 
-static int gfs2_dir_read_stuffed(struct gfs2_inode *ip, char *buf,
-				 u64 offset, unsigned int size)
+static int gfs2_dir_read_stuffed(struct gfs2_inode *ip, __be64 *buf,
+				 unsigned int size)
 {
 	struct buffer_head *dibh;
 	int error;
 
 	error = gfs2_meta_inode_buffer(ip, &dibh);
 	if (!error) {
-		offset += sizeof(struct gfs2_dinode);
-		memcpy(buf, dibh->b_data + offset, size);
+		memcpy(buf, dibh->b_data + sizeof(struct gfs2_dinode), size);
 		brelse(dibh);
 	}
 
@@ -261,13 +260,12 @@ static int gfs2_dir_read_stuffed(struct gfs2_inode *ip, char *buf,
  * gfs2_dir_read_data - Read a data from a directory inode
  * @ip: The GFS2 Inode
  * @buf: The buffer to place result into
- * @offset: File offset to begin jdata_readng from
  * @size: Amount of data to transfer
  *
  * Returns: The amount of data actually copied or the error
  */
-static int gfs2_dir_read_data(struct gfs2_inode *ip, char *buf, u64 offset,
-			      unsigned int size, unsigned ra)
+static int gfs2_dir_read_data(struct gfs2_inode *ip, __be64 *buf,
+			      unsigned int size)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	u64 lblock, dblock;
@@ -275,24 +273,14 @@ static int gfs2_dir_read_data(struct gfs2_inode *ip, char *buf, u64 offset,
 	unsigned int o;
 	int copied = 0;
 	int error = 0;
-	u64 disksize = i_size_read(&ip->i_inode);
-
-	if (offset >= disksize)
-		return 0;
-
-	if (offset + size > disksize)
-		size = disksize - offset;
-
-	if (!size)
-		return 0;
 
 	if (gfs2_is_stuffed(ip))
-		return gfs2_dir_read_stuffed(ip, buf, offset, size);
+		return gfs2_dir_read_stuffed(ip, buf, size);
 
 	if (gfs2_assert_warn(sdp, gfs2_is_jdata(ip)))
 		return -EINVAL;
 
-	lblock = offset;
+	lblock = 0;
 	o = do_div(lblock, sdp->sd_jbsize) + sizeof(struct gfs2_meta_header);
 
 	while (copied < size) {
@@ -311,8 +299,6 @@ static int gfs2_dir_read_data(struct gfs2_inode *ip, char *buf, u64 offset,
 			if (error || !dblock)
 				goto fail;
 			BUG_ON(extlen < 1);
-			if (!ra)
-				extlen = 1;
 			bh = gfs2_meta_ra(ip->i_gl, dblock, extlen);
 		} else {
 			error = gfs2_meta_read(ip->i_gl, dblock, DIO_WAIT, &bh);
@@ -328,7 +314,7 @@ static int gfs2_dir_read_data(struct gfs2_inode *ip, char *buf, u64 offset,
 		extlen--;
 		memcpy(buf, bh->b_data + o, amount);
 		brelse(bh);
-		buf += amount;
+		buf += (amount/sizeof(__be64));
 		copied += amount;
 		lblock++;
 		o = sizeof(struct gfs2_meta_header);
@@ -371,7 +357,7 @@ static __be64 *gfs2_dir_get_hash_table(struct gfs2_inode *ip)
 	if (hc == NULL)
 		return ERR_PTR(-ENOMEM);
 
-	ret = gfs2_dir_read_data(ip, (char *)hc, 0, hsize, 1);
+	ret = gfs2_dir_read_data(ip, hc, hsize);
 	if (ret < 0) {
 		kfree(hc);
 		return ERR_PTR(ret);
-- 
1.7.4

[Cluster-devel] [PATCH 02/19] GFS2: Split data write & wait in fsync

[Steven Whitehouse]

Now that the data writing is part of fsync proper, we can split
the waiting part out and do it later on. This reduces the
number of waits that we do during fsync on average.

There is also no need to take the i_mutex unless we are flushing
metadata to disk, so we can move that to within the metadata
flushing code.

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

diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index edeb9e8..92c3db4 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -551,8 +551,16 @@ static int gfs2_close(struct inode *inode, struct file *file)
  * @end: the end position in the file to sync
  * @datasync: set if we can ignore timestamp changes
  *
- * The VFS will flush data for us. We only need to worry
- * about metadata here.
+ * We split the data flushing here so that we don't wait for the data
+ * until after we've also sent the metadata to disk. Note that for
+ * data=ordered, we will write & wait for the data at the log flush
+ * stage anyway, so this is unlikely to make much of a difference
+ * except in the data=writeback case.
+ *
+ * If the fdatawrite fails due to any reason except -EIO, we will
+ * continue the remainder of the fsync, although we'll still report
+ * the error at the end. This is to match filemap_write_and_wait_range()
+ * behaviour.
  *
  * Returns: errno
  */
@@ -560,30 +568,36 @@ static int gfs2_close(struct inode *inode, struct file *file)
 static int gfs2_fsync(struct file *file, loff_t start, loff_t end,
 		      int datasync)
 {
-	struct inode *inode = file->f_mapping->host;
+	struct address_space *mapping = file->f_mapping;
+	struct inode *inode = mapping->host;
 	int sync_state = inode->i_state & (I_DIRTY_SYNC|I_DIRTY_DATASYNC);
 	struct gfs2_inode *ip = GFS2_I(inode);
-	int ret;
+	int ret, ret1 = 0;
 
-	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
-	if (ret)
-		return ret;
-	mutex_lock(&inode->i_mutex);
+	if (mapping->nrpages) {
+		ret1 = filemap_fdatawrite_range(mapping, start, end);
+		if (ret1 == -EIO)
+			return ret1;
+	}
 
 	if (datasync)
 		sync_state &= ~I_DIRTY_SYNC;
 
 	if (sync_state) {
+		mutex_lock(&inode->i_mutex);
 		ret = sync_inode_metadata(inode, 1);
 		if (ret) {
 			mutex_unlock(&inode->i_mutex);
 			return ret;
 		}
 		gfs2_ail_flush(ip->i_gl);
+		mutex_unlock(&inode->i_mutex);
 	}
 
-	mutex_unlock(&inode->i_mutex);
-	return 0;
+	if (mapping->nrpages)
+		ret = filemap_fdatawait_range(mapping, start, end);
+
+	return ret ? ret : ret1;
 }
 
 /**
-- 
1.7.4

[Cluster-devel] [PATCH 03/19] GFS2: Fix bug-trap in ail flush code

[Steven Whitehouse]

The assert was being tested under the wrong lock, a
legacy of the original code. Also, if it does trigger,
the resulting information was not always a lot of help.

This moves the patch under the correct lock and also
prints out more useful information in tacking down the
source of the problem.

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

diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index da21eca..99df483 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -28,6 +28,17 @@
 #include "trans.h"
 #include "dir.h"
 
+static void gfs2_ail_error(struct gfs2_glock *gl, const struct buffer_head *bh)
+{
+	fs_err(gl->gl_sbd, "AIL buffer %p: blocknr %llu state 0x%08lx mapping %p page state 0x%lx\n",
+	       bh, (unsigned long long)bh->b_blocknr, bh->b_state,
+	       bh->b_page->mapping, bh->b_page->flags);
+	fs_err(gl->gl_sbd, "AIL glock %u:%llu mapping %p\n",
+	       gl->gl_name.ln_type, gl->gl_name.ln_number,
+	       gfs2_glock2aspace(gl));
+	gfs2_lm_withdraw(gl->gl_sbd, "AIL error\n");
+}
+
 /**
  * __gfs2_ail_flush - remove all buffers for a given lock from the AIL
  * @gl: the glock
@@ -41,20 +52,24 @@ static void __gfs2_ail_flush(struct gfs2_glock *gl)
 	struct list_head *head = &gl->gl_ail_list;
 	struct gfs2_bufdata *bd;
 	struct buffer_head *bh;
+	sector_t blocknr;
 
 	spin_lock(&sdp->sd_ail_lock);
 	while (!list_empty(head)) {
 		bd = list_entry(head->next, struct gfs2_bufdata,
 				bd_ail_gl_list);
 		bh = bd->bd_bh;
-		gfs2_remove_from_ail(bd);
-		bd->bd_bh = NULL;
+		blocknr = bh->b_blocknr;
+		if (buffer_busy(bh))
+			gfs2_ail_error(gl, bh);
 		bh->b_private = NULL;
+		gfs2_remove_from_ail(bd); /* drops ref on bh */
 		spin_unlock(&sdp->sd_ail_lock);
 
-		bd->bd_blkno = bh->b_blocknr;
+		bd->bd_bh = NULL;
+		bd->bd_blkno = blocknr;
+
 		gfs2_log_lock(sdp);
-		gfs2_assert_withdraw(sdp, !buffer_busy(bh));
 		gfs2_trans_add_revoke(sdp, bd);
 		gfs2_log_unlock(sdp);
 
-- 
1.7.4

[Cluster-devel] [PATCH 04/19] GFS2: Make atime checks more efficient

[Steven Whitehouse]

We do not need to start a transaction unless the atime
check has proved positive. Also if we are going to flush
the complete ail list anyway, we might as well skip the
writeback for this specific inode's metadata, since that
will be done as part of the ail writeback process in an
order offering potentially more efficient I/O.

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

diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index b7beadd..afb8761 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -768,30 +768,30 @@ static int gfs2_write_inode(struct inode *inode, struct writeback_control *wbc)
 			goto do_flush;
 		unlock_required = 1;
 	}
-	ret = gfs2_trans_begin(sdp, RES_DINODE, 0);
-	if (ret)
-		goto do_unlock;
 	ret = gfs2_meta_inode_buffer(ip, &bh);
 	if (ret == 0) {
 		di = (struct gfs2_dinode *)bh->b_data;
 		atime.tv_sec = be64_to_cpu(di->di_atime);
 		atime.tv_nsec = be32_to_cpu(di->di_atime_nsec);
 		if (timespec_compare(&inode->i_atime, &atime) > 0) {
-			gfs2_trans_add_bh(ip->i_gl, bh, 1);
-			gfs2_dinode_out(ip, bh->b_data);
+			ret = gfs2_trans_begin(sdp, RES_DINODE, 0);
+			if (ret == 0) {
+				gfs2_trans_add_bh(ip->i_gl, bh, 1);
+				gfs2_dinode_out(ip, bh->b_data);
+				gfs2_trans_end(sdp);
+			}
 		}
 		brelse(bh);
 	}
-	gfs2_trans_end(sdp);
-do_unlock:
 	if (unlock_required)
 		gfs2_glock_dq_uninit(&gh);
 do_flush:
 	if (wbc->sync_mode == WB_SYNC_ALL)
 		gfs2_log_flush(GFS2_SB(inode), ip->i_gl);
-	filemap_fdatawrite(metamapping);
 	if (bdi->dirty_exceeded)
 		gfs2_ail1_flush(sdp, wbc);
+	else
+		filemap_fdatawrite(metamapping);
 	if (!ret && (wbc->sync_mode == WB_SYNC_ALL))
 		ret = filemap_fdatawait(metamapping);
 	if (ret)
-- 
1.7.4

[Cluster-devel] [PATCH 05/19] GFS2: Fix inode allocation error path

[Steven Whitehouse]

If we have got far enough through the inode allocation code
path that an inode has already been allocated, then we must
call iput to dispose of it, if an error occurs during a
later part of the process. This will always be the final iput
since there will be no other references to the inode.

Unlike when the inode has been unlinked, its block state will
be GFS2_BLKST_INODE rather than GFS2_BLKST_UNLINKED so we need
to skip the test in ->evict_inode() for this one case in order
to ensure that it will be deallocated correctly. This patch adds
a new flag in order to ensure that this will happen correctly.

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

diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 892ac37..be5801a 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -267,6 +267,7 @@ struct gfs2_alloc {
 enum {
 	GIF_INVALID		= 0,
 	GIF_QD_LOCKED		= 1,
+	GIF_ALLOC_FAILED	= 2,
 	GIF_SW_PAGED		= 3,
 };
 
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 900cf98..044efe2 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -736,10 +736,12 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 
 fail_gunlock2:
 	gfs2_glock_dq_uninit(ghs + 1);
-	if (inode && !IS_ERR(inode))
-		iput(inode);
 fail_gunlock:
 	gfs2_glock_dq_uninit(ghs);
+	if (inode && !IS_ERR(inode)) {
+		set_bit(GIF_ALLOC_FAILED, &GFS2_I(inode)->i_flags);
+		iput(inode);
+	}
 fail:
 	if (bh)
 		brelse(bh);
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index afb8761..9961de7 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1471,9 +1471,11 @@ static void gfs2_evict_inode(struct inode *inode)
 		goto out;
 	}
 
-	error = gfs2_check_blk_type(sdp, ip->i_no_addr, GFS2_BLKST_UNLINKED);
-	if (error)
-		goto out_truncate;
+	if (!test_bit(GIF_ALLOC_FAILED, &ip->i_flags)) {
+		error = gfs2_check_blk_type(sdp, ip->i_no_addr, GFS2_BLKST_UNLINKED);
+		if (error)
+			goto out_truncate;
+	}
 
 	if (test_bit(GIF_INVALID, &ip->i_flags)) {
 		error = gfs2_inode_refresh(ip);
@@ -1513,6 +1515,10 @@ static void gfs2_evict_inode(struct inode *inode)
 	goto out_unlock;
 
 out_truncate:
+	gfs2_log_flush(sdp, ip->i_gl);
+	write_inode_now(inode, 1);
+	gfs2_ail_flush(ip->i_gl);
+
 	/* Case 2 starts here */
 	error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks);
 	if (error)
-- 
1.7.4

[Cluster-devel] [PATCH 06/19] GFS2: Fix bug trap and journaled data fsync

[Steven Whitehouse]

Journaled data requires that a complete flush of all dirty data for
the file is done, in order that the ail flush which comes after
will succeed.

Also the recently enhanced bug trap can trigger falsely in case
an ail flush from fsync races with a page read. This updates the
bug trap such that it will ignore buffers which are locked and
only trigger on dirty and/or pinned buffers when the ail flush
is run from fsync. The original bug trap is retained when ail
flush is run from ->go_sync()

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

diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 92c3db4..9d12286 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -590,6 +590,8 @@ static int gfs2_fsync(struct file *file, loff_t start, loff_t end,
 			mutex_unlock(&inode->i_mutex);
 			return ret;
 		}
+		if (gfs2_is_jdata(ip))
+			filemap_write_and_wait(mapping);
 		gfs2_ail_flush(ip->i_gl);
 		mutex_unlock(&inode->i_mutex);
 	}
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 99df483..0cc3ff4 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -46,7 +46,7 @@ static void gfs2_ail_error(struct gfs2_glock *gl, const struct buffer_head *bh)
  * None of the buffers should be dirty, locked, or pinned.
  */
 
-static void __gfs2_ail_flush(struct gfs2_glock *gl)
+static void __gfs2_ail_flush(struct gfs2_glock *gl, unsigned long b_state)
 {
 	struct gfs2_sbd *sdp = gl->gl_sbd;
 	struct list_head *head = &gl->gl_ail_list;
@@ -60,7 +60,7 @@ static void __gfs2_ail_flush(struct gfs2_glock *gl)
 				bd_ail_gl_list);
 		bh = bd->bd_bh;
 		blocknr = bh->b_blocknr;
-		if (buffer_busy(bh))
+		if (bh->b_state & b_state)
 			gfs2_ail_error(gl, bh);
 		bh->b_private = NULL;
 		gfs2_remove_from_ail(bd); /* drops ref on bh */
@@ -99,7 +99,7 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
 	BUG_ON(current->journal_info);
 	current->journal_info = &tr;
 
-	__gfs2_ail_flush(gl);
+	__gfs2_ail_flush(gl, (1ul << BH_Dirty)|(1ul << BH_Pinned)|(1ul << BH_Lock));
 
 	gfs2_trans_end(sdp);
 	gfs2_log_flush(sdp, NULL);
@@ -117,7 +117,7 @@ void gfs2_ail_flush(struct gfs2_glock *gl)
 	ret = gfs2_trans_begin(sdp, 0, revokes);
 	if (ret)
 		return;
-	__gfs2_ail_flush(gl);
+	__gfs2_ail_flush(gl, (1ul << BH_Dirty)|(1ul << BH_Pinned));
 	gfs2_trans_end(sdp);
 	gfs2_log_flush(sdp, NULL);
 }
-- 
1.7.4

[Cluster-devel] [PATCH 07/19] GFS2: Use ->dirty_inode()

[Steven Whitehouse]

The aim of this patch is to use the newly enhanced ->dirty_inode()
super block operation to deal with atime updates, rather than
piggy backing that code into ->write_inode() as is currently
done.

The net result is a simplification of the code in various places
and a reduction of the number of gfs2_dinode_out() calls since
this is now implied by ->dirty_inode().

Some of the mark_inode_dirty() calls have been moved under glocks
in order to take advantage of then being able to avoid locking in
->dirty_inode() when we already have suitable locks.

One consequence is that generic_write_end() now correctly deals
with file size updates, so that we do not need a separate check
for that afterwards. This also, indirectly, means that fdatasync
should work correctly on GFS2 - the current code always syncs the
metadata whether it needs to or not.

Has survived testing with postmark (with and without atime) and
also fsx.

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

diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c
index 884c9af..6b85917 100644
--- a/fs/gfs2/acl.c
+++ b/fs/gfs2/acl.c
@@ -82,7 +82,7 @@ static int gfs2_set_mode(struct inode *inode, mode_t mode)
 		iattr.ia_valid = ATTR_MODE;
 		iattr.ia_mode = mode;
 
-		error = gfs2_setattr_simple(GFS2_I(inode), &iattr);
+		error = gfs2_setattr_simple(inode, &iattr);
 	}
 
 	return error;
@@ -160,6 +160,7 @@ out:
 
 int gfs2_acl_chmod(struct gfs2_inode *ip, struct iattr *attr)
 {
+	struct inode *inode = &ip->i_inode;
 	struct posix_acl *acl;
 	char *data;
 	unsigned int len;
@@ -169,7 +170,7 @@ int gfs2_acl_chmod(struct gfs2_inode *ip, struct iattr *attr)
 	if (IS_ERR(acl))
 		return PTR_ERR(acl);
 	if (!acl)
-		return gfs2_setattr_simple(ip, attr);
+		return gfs2_setattr_simple(inode, attr);
 
 	error = posix_acl_chmod(&acl, GFP_NOFS, attr->ia_mode);
 	if (error)
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index f9fbbe9..212fe74 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -787,7 +787,6 @@ static int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
 	u64 to = pos + copied;
 	void *kaddr;
 	unsigned char *buf = dibh->b_data + sizeof(struct gfs2_dinode);
-	struct gfs2_dinode *di = (struct gfs2_dinode *)dibh->b_data;
 
 	BUG_ON((pos + len) > (dibh->b_size - sizeof(struct gfs2_dinode)));
 	kaddr = kmap_atomic(page, KM_USER0);
@@ -804,7 +803,6 @@ static int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
 	if (copied) {
 		if (inode->i_size < to)
 			i_size_write(inode, to);
-		gfs2_dinode_out(ip, di);
 		mark_inode_dirty(inode);
 	}
 
@@ -873,10 +871,6 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping,
 		gfs2_page_add_databufs(ip, page, from, to);
 
 	ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
-	if (ret > 0) {
-		gfs2_dinode_out(ip, dibh->b_data);
-		mark_inode_dirty(inode);
-	}
 
 	if (inode == sdp->sd_rindex) {
 		adjust_fs_space(inode);
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index 2045d70..898e62e 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -1681,7 +1681,6 @@ int gfs2_dir_del(struct gfs2_inode *dip, const struct dentry *dentry)
 	const struct qstr *name = &dentry->d_name;
 	struct gfs2_dirent *dent, *prev = NULL;
 	struct buffer_head *bh;
-	int error;
 
 	/* Returns _either_ the entry (if its first in block) or the
 	   previous entry otherwise */
@@ -1710,22 +1709,15 @@ int gfs2_dir_del(struct gfs2_inode *dip, const struct dentry *dentry)
 	}
 	brelse(bh);
 
-	error = gfs2_meta_inode_buffer(dip, &bh);
-	if (error)
-		return error;
-
 	if (!dip->i_entries)
 		gfs2_consist_inode(dip);
-	gfs2_trans_add_bh(dip->i_gl, bh, 1);
 	dip->i_entries--;
 	dip->i_inode.i_mtime = dip->i_inode.i_ctime = CURRENT_TIME;
 	if (S_ISDIR(dentry->d_inode->i_mode))
 		drop_nlink(&dip->i_inode);
-	gfs2_dinode_out(dip, bh->b_data);
-	brelse(bh);
 	mark_inode_dirty(&dip->i_inode);
 
-	return error;
+	return 0;
 }
 
 /**
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 9d12286..4416a1c 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -802,7 +802,6 @@ static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
 		from = 0;
 	}
 
-	gfs2_dinode_out(ip, dibh->b_data);
 	mark_inode_dirty(inode);
 
 	brelse(dibh);
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 044efe2..a0b53d3 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -729,8 +729,8 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 		gfs2_inplace_release(dip);
 	gfs2_quota_unlock(dip);
 	gfs2_alloc_put(dip);
-	gfs2_glock_dq_uninit_m(2, ghs);
 	mark_inode_dirty(inode);
+	gfs2_glock_dq_uninit_m(2, ghs);
 	d_instantiate(dentry, inode);
 	return 0;
 
@@ -926,8 +926,9 @@ static int gfs2_link(struct dentry *old_dentry, struct inode *dir,
 	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
 	inc_nlink(&ip->i_inode);
 	ip->i_inode.i_ctime = CURRENT_TIME;
-	gfs2_dinode_out(ip, dibh->b_data);
-	mark_inode_dirty(&ip->i_inode);
+	ihold(inode);
+	d_instantiate(dentry, inode);
+	mark_inode_dirty(inode);
 
 out_brelse:
 	brelse(dibh);
@@ -949,11 +950,6 @@ out_child:
 out_parent:
 	gfs2_holder_uninit(ghs);
 	gfs2_holder_uninit(ghs + 1);
-	if (!error) {
-		ihold(inode);
-		d_instantiate(dentry, inode);
-		mark_inode_dirty(inode);
-	}
 	return error;
 }
 
@@ -1026,8 +1022,6 @@ static int gfs2_unlink_inode(struct gfs2_inode *dip,
 		clear_nlink(inode);
 	else
 		drop_nlink(inode);
-	gfs2_trans_add_bh(ip->i_gl, bh, 1);
-	gfs2_dinode_out(ip, bh->b_data);
 	mark_inode_dirty(inode);
 	if (inode->i_nlink == 0)
 		gfs2_unlink_di(inode);
@@ -1565,21 +1559,10 @@ int gfs2_permission(struct inode *inode, int mask)
 	return error;
 }
 
-static int __gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr)
+static int __gfs2_setattr_simple(struct inode *inode, struct iattr *attr)
 {
-	struct inode *inode = &ip->i_inode;
-	struct buffer_head *dibh;
-	int error;
-
-	error = gfs2_meta_inode_buffer(ip, &dibh);
-	if (error)
-		return error;
-
 	setattr_copy(inode, attr);
 	mark_inode_dirty(inode);
-	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
-	gfs2_dinode_out(ip, dibh->b_data);
-	brelse(dibh);
 	return 0;
 }
 
@@ -1591,19 +1574,19 @@ static int __gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr)
  * Returns: errno
  */
 
-int gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr)
+int gfs2_setattr_simple(struct inode *inode, struct iattr *attr)
 {
 	int error;
 
 	if (current->journal_info)
-		return __gfs2_setattr_simple(ip, attr);
+		return __gfs2_setattr_simple(inode, attr);
 
-	error = gfs2_trans_begin(GFS2_SB(&ip->i_inode), RES_DINODE, 0);
+	error = gfs2_trans_begin(GFS2_SB(inode), RES_DINODE, 0);
 	if (error)
 		return error;
 
-	error = __gfs2_setattr_simple(ip, attr);
-	gfs2_trans_end(GFS2_SB(&ip->i_inode));
+	error = __gfs2_setattr_simple(inode, attr);
+	gfs2_trans_end(GFS2_SB(inode));
 	return error;
 }
 
@@ -1641,7 +1624,7 @@ static int setattr_chown(struct inode *inode, struct iattr *attr)
 	if (error)
 		goto out_gunlock_q;
 
-	error = gfs2_setattr_simple(ip, attr);
+	error = gfs2_setattr_simple(inode, attr);
 	if (error)
 		goto out_end_trans;
 
@@ -1697,12 +1680,12 @@ static int gfs2_setattr(struct dentry *dentry, struct iattr *attr)
 	else if ((attr->ia_valid & ATTR_MODE) && IS_POSIXACL(inode))
 		error = gfs2_acl_chmod(ip, attr);
 	else
-		error = gfs2_setattr_simple(ip, attr);
+		error = gfs2_setattr_simple(inode, attr);
 
 out:
-	gfs2_glock_dq_uninit(&i_gh);
 	if (!error)
 		mark_inode_dirty(inode);
+	gfs2_glock_dq_uninit(&i_gh);
 	return error;
 }
 
diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h
index 8d90e0c..276e7b5 100644
--- a/fs/gfs2/inode.h
+++ b/fs/gfs2/inode.h
@@ -109,7 +109,7 @@ extern int gfs2_inode_refresh(struct gfs2_inode *ip);
 extern struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name,
 				  int is_root);
 extern int gfs2_permission(struct inode *inode, int mask);
-extern int gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr);
+extern int gfs2_setattr_simple(struct inode *inode, struct iattr *attr);
 extern struct inode *gfs2_lookup_simple(struct inode *dip, const char *name);
 extern void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf);
 
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 42e8d23..0c8e5d3 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -638,7 +638,7 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc,
 	unsigned long index = loc >> PAGE_CACHE_SHIFT;
 	unsigned offset = loc & (PAGE_CACHE_SIZE - 1);
 	unsigned blocksize, iblock, pos;
-	struct buffer_head *bh, *dibh;
+	struct buffer_head *bh;
 	struct page *page;
 	void *kaddr, *ptr;
 	struct gfs2_quota q, *qp;
@@ -736,22 +736,13 @@ get_a_page:
 		goto get_a_page;
 	}
 
-	/* Update the disk inode timestamp and size (if extended) */
-	err = gfs2_meta_inode_buffer(ip, &dibh);
-	if (err)
-		goto out;
-
 	size = loc + sizeof(struct gfs2_quota);
 	if (size > inode->i_size)
 		i_size_write(inode, size);
 	inode->i_mtime = inode->i_atime = CURRENT_TIME;
-	gfs2_trans_add_bh(ip->i_gl, dibh, 1);
-	gfs2_dinode_out(ip, dibh->b_data);
-	brelse(dibh);
 	mark_inode_dirty(inode);
-
-out:
 	return err;
+
 unlock_out:
 	unlock_page(page);
 	page_cache_release(page);
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 9961de7..b05fa59 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -752,47 +752,15 @@ static int gfs2_write_inode(struct inode *inode, struct writeback_control *wbc)
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	struct address_space *metamapping = gfs2_glock2aspace(ip->i_gl);
 	struct backing_dev_info *bdi = metamapping->backing_dev_info;
-	struct gfs2_holder gh;
-	struct buffer_head *bh;
-	struct timespec atime;
-	struct gfs2_dinode *di;
-	int ret = -EAGAIN;
-	int unlock_required = 0;
-
-	/* Skip timestamp update, if this is from a memalloc */
-	if (current->flags & PF_MEMALLOC)
-		goto do_flush;
-	if (!gfs2_glock_is_locked_by_me(ip->i_gl)) {
-		ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
-		if (ret)
-			goto do_flush;
-		unlock_required = 1;
-	}
-	ret = gfs2_meta_inode_buffer(ip, &bh);
-	if (ret == 0) {
-		di = (struct gfs2_dinode *)bh->b_data;
-		atime.tv_sec = be64_to_cpu(di->di_atime);
-		atime.tv_nsec = be32_to_cpu(di->di_atime_nsec);
-		if (timespec_compare(&inode->i_atime, &atime) > 0) {
-			ret = gfs2_trans_begin(sdp, RES_DINODE, 0);
-			if (ret == 0) {
-				gfs2_trans_add_bh(ip->i_gl, bh, 1);
-				gfs2_dinode_out(ip, bh->b_data);
-				gfs2_trans_end(sdp);
-			}
-		}
-		brelse(bh);
-	}
-	if (unlock_required)
-		gfs2_glock_dq_uninit(&gh);
-do_flush:
+	int ret = 0;
+
 	if (wbc->sync_mode == WB_SYNC_ALL)
 		gfs2_log_flush(GFS2_SB(inode), ip->i_gl);
 	if (bdi->dirty_exceeded)
 		gfs2_ail1_flush(sdp, wbc);
 	else
 		filemap_fdatawrite(metamapping);
-	if (!ret && (wbc->sync_mode == WB_SYNC_ALL))
+	if (wbc->sync_mode == WB_SYNC_ALL)
 		ret = filemap_fdatawait(metamapping);
 	if (ret)
 		mark_inode_dirty_sync(inode);
@@ -800,6 +768,64 @@ do_flush:
 }
 
 /**
+ * gfs2_dirty_inode - check for atime updates
+ * @inode: The inode in question
+ * @flags: The type of dirty
+ *
+ * Unfortunately it can be called under any combination of inode
+ * glock and transaction lock, so we have to check carefully.
+ *
+ * At the moment this deals only with atime - it should be possible
+ * to expand that role in future, once a review of the locking has
+ * been carried out.
+ */
+
+static void gfs2_dirty_inode(struct inode *inode, int flags)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct buffer_head *bh;
+	struct gfs2_holder gh;
+	int need_unlock = 0;
+	int need_endtrans = 0;
+	int ret;
+
+	if (!(flags & (I_DIRTY_DATASYNC|I_DIRTY_SYNC)))
+		return;
+
+	if (!gfs2_glock_is_locked_by_me(ip->i_gl)) {
+		ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+		if (ret) {
+			fs_err(sdp, "dirty_inode: glock %d\n", ret);
+			return;
+		}
+		need_unlock = 1;
+	}
+
+	if (current->journal_info == NULL) {
+		ret = gfs2_trans_begin(sdp, RES_DINODE, 0);
+		if (ret) {
+			fs_err(sdp, "dirty_inode: gfs2_trans_begin %d\n", ret);
+			goto out;
+		}
+		need_endtrans = 1;
+	}
+
+	ret = gfs2_meta_inode_buffer(ip, &bh);
+	if (ret == 0) {
+		gfs2_trans_add_bh(ip->i_gl, bh, 1);
+		gfs2_dinode_out(ip, bh->b_data);
+		brelse(bh);
+	}
+
+	if (need_endtrans)
+		gfs2_trans_end(sdp);
+out:
+	if (need_unlock)
+		gfs2_glock_dq_uninit(&gh);
+}
+
+/**
  * gfs2_make_fs_ro - Turn a Read-Write FS into a Read-Only one
  * @sdp: the filesystem
  *
@@ -1578,6 +1604,7 @@ const struct super_operations gfs2_super_ops = {
 	.alloc_inode		= gfs2_alloc_inode,
 	.destroy_inode		= gfs2_destroy_inode,
 	.write_inode		= gfs2_write_inode,
+	.dirty_inode		= gfs2_dirty_inode,
 	.evict_inode		= gfs2_evict_inode,
 	.put_super		= gfs2_put_super,
 	.sync_fs		= gfs2_sync_fs,
diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c
index 439b61c..695304c 100644
--- a/fs/gfs2/xattr.c
+++ b/fs/gfs2/xattr.c
@@ -1296,7 +1296,8 @@ fail:
 
 int gfs2_xattr_acl_chmod(struct gfs2_inode *ip, struct iattr *attr, char *data)
 {
-	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct inode *inode = &ip->i_inode;
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	struct gfs2_ea_location el;
 	int error;
 
@@ -1319,7 +1320,7 @@ int gfs2_xattr_acl_chmod(struct gfs2_inode *ip, struct iattr *attr, char *data)
 	if (error)
 		return error;
 
-	error = gfs2_setattr_simple(ip, attr);
+	error = gfs2_setattr_simple(inode, attr);
 	gfs2_trans_end(sdp);
 	return error;
 }
-- 
1.7.4

[Cluster-devel] [PATCH 08/19] GFS2: Clean up gfs2_create

[Steven Whitehouse]

If we pass through knowledge of whether the creation is intended to be
exclusive or not, then we can deal with that in gfs2_create_inode
and remove one set of locking. Also this removes the loop in
gfs2_create and simplifies the code a bit.

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

diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index a0b53d3..2af6905 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -663,7 +663,7 @@ static int gfs2_security_init(struct gfs2_inode *dip, struct gfs2_inode *ip,
 
 static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 			     unsigned int mode, dev_t dev, const char *symname,
-			     unsigned int size)
+			     unsigned int size, int excl)
 {
 	const struct qstr *name = &dentry->d_name;
 	struct gfs2_holder ghs[2];
@@ -683,6 +683,12 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 		goto fail;
 
 	error = create_ok(dip, name, mode);
+	if ((error == -EEXIST) && S_ISREG(mode) && !excl) {
+		inode = gfs2_lookupi(dir, &dentry->d_name, 0);
+		gfs2_glock_dq_uninit(ghs);
+		d_instantiate(dentry, inode);
+		return IS_ERR(inode) ? PTR_ERR(inode) : 0;
+	}
 	if (error)
 		goto fail_gunlock;
 
@@ -760,24 +766,10 @@ fail:
 static int gfs2_create(struct inode *dir, struct dentry *dentry,
 		       int mode, struct nameidata *nd)
 {
-	struct inode *inode;
-	int ret;
-
-	for (;;) {
-		ret = gfs2_create_inode(dir, dentry, S_IFREG | mode, 0, NULL, 0);
-		if (ret != -EEXIST || (nd && (nd->flags & LOOKUP_EXCL)))
-			return ret;
-
-		inode = gfs2_lookupi(dir, &dentry->d_name, 0);
-		if (inode) {
-			if (!IS_ERR(inode))
-				break;
-			return PTR_ERR(inode);
-		}
-	}
-
-	d_instantiate(dentry, inode);
-	return 0;
+	int excl = 0;
+	if (nd && (nd->flags & LOOKUP_EXCL))
+		excl = 1;
+	return gfs2_create_inode(dir, dentry, S_IFREG | mode, 0, NULL, 0, excl);
 }
 
 /**
@@ -1135,7 +1127,7 @@ static int gfs2_symlink(struct inode *dir, struct dentry *dentry,
 	if (size > sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode) - 1)
 		return -ENAMETOOLONG;
 
-	return gfs2_create_inode(dir, dentry, S_IFLNK | S_IRWXUGO, 0, symname, size);
+	return gfs2_create_inode(dir, dentry, S_IFLNK | S_IRWXUGO, 0, symname, size, 0);
 }
 
 /**
@@ -1149,7 +1141,7 @@ static int gfs2_symlink(struct inode *dir, struct dentry *dentry,
 
 static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 {
-	return gfs2_create_inode(dir, dentry, S_IFDIR | mode, 0, NULL, 0);
+	return gfs2_create_inode(dir, dentry, S_IFDIR | mode, 0, NULL, 0, 0);
 }
 
 /**
@@ -1164,7 +1156,7 @@ static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 static int gfs2_mknod(struct inode *dir, struct dentry *dentry, int mode,
 		      dev_t dev)
 {
-	return gfs2_create_inode(dir, dentry, mode, dev, NULL, 0);
+	return gfs2_create_inode(dir, dentry, mode, dev, NULL, 0, 0);
 }
 
 /*
-- 
1.7.4

[Cluster-devel] [PATCH 09/19] GFS2: Fix lseek after SEEK_DATA, SEEK_HOLE have been added

[Steven Whitehouse]

We need to take the inode's glock whenever the inode's size
is referenced, otherwise it might not be uptodate. Even
though generic_file_llseek_unlocked() doesn't implement
SEEK_DATA, SEEK_HOLE directly, it does reference the inode's
size in those cases, so we need to add them to the list
of origins which need the glock.

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>

diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 4416a1c..d717b72 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -59,15 +59,24 @@ static loff_t gfs2_llseek(struct file *file, loff_t offset, int origin)
 	struct gfs2_holder i_gh;
 	loff_t error;
 
-	if (origin == 2) {
+	switch (origin) {
+	case SEEK_END: /* These reference inode->i_size */
+	case SEEK_DATA:
+	case SEEK_HOLE:
 		error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY,
 					   &i_gh);
 		if (!error) {
 			error = generic_file_llseek_unlocked(file, offset, origin);
 			gfs2_glock_dq_uninit(&i_gh);
 		}
-	} else
+		break;
+	case SEEK_CUR:
+	case SEEK_SET:
 		error = generic_file_llseek_unlocked(file, offset, origin);
+		break;
+	default:
+		error = -EINVAL;
+	}
 
 	return error;
 }
-- 
1.7.4

[Cluster-devel] [PATCH 10/19] GFS2: Use rbtree for resource groups and clean up bitmap buffer ref count scheme

[Steven Whitehouse]

From: Bob Peterson <rpeterso@redhat.com>

Here is an update of Bob's original rbtree patch which, in addition, also
resolves the rather strange ref counting that was being done relating to
the bitmap blocks.

Originally we had a dual system for journaling resource groups. The metadata
blocks were journaled and also the rgrp itself was added to a list. The reason
for adding the rgrp to the list in the journal was so that the "repolish
clones" code could be run to update the free space, and potentially send any
discard requests when the log was flushed. This was done by comparing the
"cloned" bitmap with what had been written back on disk during the transaction
commit.

Due to this, there was a requirement to hang on to the rgrps' bitmap buffers
until the journal had been flushed. For that reason, there was a rather
complicated set up in the ->go_lock ->go_unlock functions for rgrps involving
both a mutex and a spinlock (the ->sd_rindex_spin) to maintain a reference
count on the buffers.

However, the journal maintains a reference count on the buffers anyway, since
they are being journaled as metadata buffers. So by moving the code which deals
with the post-journal accounting for bitmap blocks to the metadata journaling
code, we can entirely dispense with the rather strange buffer ref counting
scheme and also the requirement to journal the rgrps.

The net result of all this is that the ->sd_rindex_spin is left to do exactly
one job, and that is to look after the rbtree or rgrps.

This patch is designed to be a stepping stone towards using RCU for the rbtree
of resource groups, however the reduction in the number of uses of the
->sd_rindex_spin is likely to have benefits for multi-threaded workloads,
anyway.

The patch retains ->go_lock and ->go_unlock for rgrps, however these maybe also
be removed in future in favour of calling the functions directly where required
in the code. That will allow locking of resource groups without needing to
actually read them in - something that could be useful in speeding up statfs.

In the mean time though it is valid to dereference ->bi_bh only when the rgrp
is locked. This is basically the same rule as before, modulo the references not
being valid until the following journal flush.

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

diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 0cc3ff4..6f82aac 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -134,6 +134,8 @@ void gfs2_ail_flush(struct gfs2_glock *gl)
 static void rgrp_go_sync(struct gfs2_glock *gl)
 {
 	struct address_space *metamapping = gfs2_glock2aspace(gl);
+	struct gfs2_rgrpd *rgd = gl->gl_object;
+	unsigned int x;
 	int error;
 
 	if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags))
@@ -145,6 +147,15 @@ static void rgrp_go_sync(struct gfs2_glock *gl)
 	error = filemap_fdatawait(metamapping);
         mapping_set_error(metamapping, error);
 	gfs2_ail_empty_gl(gl);
+
+	if (!rgd)
+		return;
+
+	for (x = 0; x < rgd->rd_length; x++) {
+		struct gfs2_bitmap *bi = rgd->rd_bits + x;
+		kfree(bi->bi_clone);
+		bi->bi_clone = NULL;
+	}
 }
 
 /**
@@ -445,33 +456,6 @@ static int inode_go_dump(struct seq_file *seq, const struct gfs2_glock *gl)
 }
 
 /**
- * rgrp_go_lock - operation done after an rgrp lock is locked by
- *    a first holder on this node.
- * @gl: the glock
- * @flags:
- *
- * Returns: errno
- */
-
-static int rgrp_go_lock(struct gfs2_holder *gh)
-{
-	return gfs2_rgrp_bh_get(gh->gh_gl->gl_object);
-}
-
-/**
- * rgrp_go_unlock - operation done before an rgrp lock is unlocked by
- *    a last holder on this node.
- * @gl: the glock
- * @flags:
- *
- */
-
-static void rgrp_go_unlock(struct gfs2_holder *gh)
-{
-	gfs2_rgrp_bh_put(gh->gh_gl->gl_object);
-}
-
-/**
  * trans_go_sync - promote/demote the transaction glock
  * @gl: the glock
  * @state: the requested state
@@ -573,8 +557,8 @@ const struct gfs2_glock_operations gfs2_inode_glops = {
 const struct gfs2_glock_operations gfs2_rgrp_glops = {
 	.go_xmote_th = rgrp_go_sync,
 	.go_inval = rgrp_go_inval,
-	.go_lock = rgrp_go_lock,
-	.go_unlock = rgrp_go_unlock,
+	.go_lock = gfs2_rgrp_go_lock,
+	.go_unlock = gfs2_rgrp_go_unlock,
 	.go_dump = gfs2_rgrp_dump,
 	.go_type = LM_TYPE_RGRP,
 	.go_flags = GLOF_ASPACE,
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index be5801a..9e753fc 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -18,6 +18,7 @@
 #include <linux/rcupdate.h>
 #include <linux/rculist_bl.h>
 #include <linux/completion.h>
+#include <linux/rbtree.h>
 
 #define DIO_WAIT	0x00000010
 #define DIO_METADATA	0x00000020
@@ -78,8 +79,7 @@ struct gfs2_bitmap {
 };
 
 struct gfs2_rgrpd {
-	struct list_head rd_list;	/* Link with superblock */
-	struct list_head rd_list_mru;
+	struct rb_node rd_node;		/* Link with superblock */
 	struct gfs2_glock *rd_gl;	/* Glock for this rgrp */
 	u64 rd_addr;			/* grp block disk address */
 	u64 rd_data0;			/* first data location */
@@ -91,10 +91,7 @@ struct gfs2_rgrpd {
 	u32 rd_dinodes;
 	u64 rd_igeneration;
 	struct gfs2_bitmap *rd_bits;
-	struct mutex rd_mutex;
-	struct gfs2_log_element rd_le;
 	struct gfs2_sbd *rd_sbd;
-	unsigned int rd_bh_count;
 	u32 rd_last_alloc;
 	u32 rd_flags;
 #define GFS2_RDF_CHECK		0x10000000 /* check for unlinked inodes */
@@ -575,9 +572,7 @@ struct gfs2_sbd {
 	int sd_rindex_uptodate;
 	spinlock_t sd_rindex_spin;
 	struct mutex sd_rindex_mutex;
-	struct list_head sd_rindex_list;
-	struct list_head sd_rindex_mru_list;
-	struct gfs2_rgrpd *sd_rindex_forward;
+	struct rb_root sd_rindex_tree;
 	unsigned int sd_rgrps;
 	unsigned int sd_max_rg_data;
 
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 05bbb12..de05b4d 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -60,6 +60,29 @@ static void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh)
 	trace_gfs2_pin(bd, 1);
 }
 
+static bool buffer_is_rgrp(const struct gfs2_bufdata *bd)
+{
+	return bd->bd_gl->gl_name.ln_type == LM_TYPE_RGRP;
+}
+
+static void maybe_release_space(struct gfs2_bufdata *bd)
+{
+	struct gfs2_glock *gl = bd->bd_gl;
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_rgrpd *rgd = gl->gl_object;
+	unsigned int index = bd->bd_bh->b_blocknr - gl->gl_name.ln_number;
+	struct gfs2_bitmap *bi = rgd->rd_bits + index;
+
+	if (bi->bi_clone == 0)
+		return;
+	if (sdp->sd_args.ar_discard)
+		gfs2_rgrp_send_discards(sdp, rgd->rd_data0, bd->bd_bh, bi);
+	memcpy(bi->bi_clone + bi->bi_offset,
+	       bd->bd_bh->b_data + bi->bi_offset, bi->bi_len);
+	clear_bit(GBF_FULL, &bi->bi_flags);
+	rgd->rd_free_clone = rgd->rd_free;
+}
+
 /**
  * gfs2_unpin - Unpin a buffer
  * @sdp: the filesystem the buffer belongs to
@@ -81,6 +104,9 @@ static void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh,
 	mark_buffer_dirty(bh);
 	clear_buffer_pinned(bh);
 
+	if (buffer_is_rgrp(bd))
+		maybe_release_space(bd);
+
 	spin_lock(&sdp->sd_ail_lock);
 	if (bd->bd_ail) {
 		list_del(&bd->bd_ail_st_list);
@@ -469,42 +495,6 @@ static void revoke_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
 	gfs2_revoke_clean(sdp);
 }
 
-static void rg_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
-{
-	struct gfs2_rgrpd *rgd;
-	struct gfs2_trans *tr = current->journal_info;
-
-	tr->tr_touched = 1;
-
-	rgd = container_of(le, struct gfs2_rgrpd, rd_le);
-
-	gfs2_log_lock(sdp);
-	if (!list_empty(&le->le_list)){
-		gfs2_log_unlock(sdp);
-		return;
-	}
-	gfs2_rgrp_bh_hold(rgd);
-	sdp->sd_log_num_rg++;
-	list_add(&le->le_list, &sdp->sd_log_le_rg);
-	gfs2_log_unlock(sdp);
-}
-
-static void rg_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
-{
-	struct list_head *head = &sdp->sd_log_le_rg;
-	struct gfs2_rgrpd *rgd;
-
-	while (!list_empty(head)) {
-		rgd = list_entry(head->next, struct gfs2_rgrpd, rd_le.le_list);
-		list_del_init(&rgd->rd_le.le_list);
-		sdp->sd_log_num_rg--;
-
-		gfs2_rgrp_repolish_clones(rgd);
-		gfs2_rgrp_bh_put(rgd);
-	}
-	gfs2_assert_warn(sdp, !sdp->sd_log_num_rg);
-}
-
 /**
  * databuf_lo_add - Add a databuf to the transaction.
  *
@@ -771,8 +761,6 @@ const struct gfs2_log_operations gfs2_revoke_lops = {
 };
 
 const struct gfs2_log_operations gfs2_rg_lops = {
-	.lo_add = rg_lo_add,
-	.lo_after_commit = rg_lo_after_commit,
 	.lo_name = "rg",
 };
 
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 3bc073a..73ee412 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -77,8 +77,7 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
 
 	spin_lock_init(&sdp->sd_rindex_spin);
 	mutex_init(&sdp->sd_rindex_mutex);
-	INIT_LIST_HEAD(&sdp->sd_rindex_list);
-	INIT_LIST_HEAD(&sdp->sd_rindex_mru_list);
+	sdp->sd_rindex_tree.rb_node = NULL;
 
 	INIT_LIST_HEAD(&sdp->sd_jindex_list);
 	spin_lock_init(&sdp->sd_jindex_spin);
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 7f8af1e..00f6e3d 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -15,6 +15,7 @@
 #include <linux/gfs2_ondisk.h>
 #include <linux/prefetch.h>
 #include <linux/blkdev.h>
+#include <linux/rbtree.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -328,15 +329,25 @@ static inline int rgrp_contains_block(struct gfs2_rgrpd *rgd, u64 block)
 
 struct gfs2_rgrpd *gfs2_blk2rgrpd(struct gfs2_sbd *sdp, u64 blk)
 {
-	struct gfs2_rgrpd *rgd;
+	struct rb_node **newn, *parent = NULL;
 
 	spin_lock(&sdp->sd_rindex_spin);
 
-	list_for_each_entry(rgd, &sdp->sd_rindex_mru_list, rd_list_mru) {
-		if (rgrp_contains_block(rgd, blk)) {
-			list_move(&rgd->rd_list_mru, &sdp->sd_rindex_mru_list);
+	newn = &sdp->sd_rindex_tree.rb_node;
+
+	/* Figure out where to put new node */
+	while (*newn) {
+		struct gfs2_rgrpd *cur = rb_entry(*newn, struct gfs2_rgrpd,
+						  rd_node);
+
+		parent = *newn;
+		if (blk < cur->rd_addr)
+			newn = &((*newn)->rb_left);
+		else if (blk > cur->rd_data0 + cur->rd_data)
+			newn = &((*newn)->rb_right);
+		else {
 			spin_unlock(&sdp->sd_rindex_spin);
-			return rgd;
+			return cur;
 		}
 	}
 
@@ -354,8 +365,13 @@ struct gfs2_rgrpd *gfs2_blk2rgrpd(struct gfs2_sbd *sdp, u64 blk)
 
 struct gfs2_rgrpd *gfs2_rgrpd_get_first(struct gfs2_sbd *sdp)
 {
-	gfs2_assert(sdp, !list_empty(&sdp->sd_rindex_list));
-	return list_entry(sdp->sd_rindex_list.next, struct gfs2_rgrpd, rd_list);
+	const struct rb_node *n;
+	struct gfs2_rgrpd *rgd;
+
+	n = rb_first(&sdp->sd_rindex_tree);
+	rgd = rb_entry(n, struct gfs2_rgrpd, rd_node);
+
+	return rgd;
 }
 
 /**
@@ -367,28 +383,34 @@ struct gfs2_rgrpd *gfs2_rgrpd_get_first(struct gfs2_sbd *sdp)
 
 struct gfs2_rgrpd *gfs2_rgrpd_get_next(struct gfs2_rgrpd *rgd)
 {
-	if (rgd->rd_list.next == &rgd->rd_sbd->sd_rindex_list)
+	struct gfs2_sbd *sdp = rgd->rd_sbd;
+	const struct rb_node *n;
+
+	spin_lock(&sdp->sd_rindex_spin);
+	n = rb_next(&rgd->rd_node);
+	if (n == NULL)
+		n = rb_first(&sdp->sd_rindex_tree);
+
+	if (unlikely(&rgd->rd_node == n)) {
+		spin_unlock(&sdp->sd_rindex_spin);
 		return NULL;
-	return list_entry(rgd->rd_list.next, struct gfs2_rgrpd, rd_list);
+	}
+	rgd = rb_entry(n, struct gfs2_rgrpd, rd_node);
+	spin_unlock(&sdp->sd_rindex_spin);
+	return rgd;
 }
 
 static void clear_rgrpdi(struct gfs2_sbd *sdp)
 {
-	struct list_head *head;
+	struct rb_node *n;
 	struct gfs2_rgrpd *rgd;
 	struct gfs2_glock *gl;
 
-	spin_lock(&sdp->sd_rindex_spin);
-	sdp->sd_rindex_forward = NULL;
-	spin_unlock(&sdp->sd_rindex_spin);
-
-	head = &sdp->sd_rindex_list;
-	while (!list_empty(head)) {
-		rgd = list_entry(head->next, struct gfs2_rgrpd, rd_list);
+	while ((n = rb_first(&sdp->sd_rindex_tree))) {
+		rgd = rb_entry(n, struct gfs2_rgrpd, rd_node);
 		gl = rgd->rd_gl;
 
-		list_del(&rgd->rd_list);
-		list_del(&rgd->rd_list_mru);
+		rb_erase(n, &sdp->sd_rindex_tree);
 
 		if (gl) {
 			gl->gl_object = NULL;
@@ -535,6 +557,29 @@ static void gfs2_rindex_in(struct gfs2_rgrpd *rgd, const void *buf)
 	rgd->rd_bitbytes = be32_to_cpu(str->ri_bitbytes);
 }
 
+static void rgd_insert(struct gfs2_rgrpd *rgd)
+{
+	struct gfs2_sbd *sdp = rgd->rd_sbd;
+	struct rb_node **newn = &sdp->sd_rindex_tree.rb_node, *parent = NULL;
+
+	/* Figure out where to put new node */
+	while (*newn) {
+		struct gfs2_rgrpd *cur = rb_entry(*newn, struct gfs2_rgrpd,
+						  rd_node);
+
+		parent = *newn;
+		if (rgd->rd_addr < cur->rd_addr)
+			newn = &((*newn)->rb_left);
+		else if (rgd->rd_addr > cur->rd_addr)
+			newn = &((*newn)->rb_right);
+		else
+			return;
+	}
+
+	rb_link_node(&rgd->rd_node, parent, newn);
+	rb_insert_color(&rgd->rd_node, &sdp->sd_rindex_tree);
+}
+
 /**
  * read_rindex_entry - Pull in a new resource index entry from the disk
  * @gl: The glock covering the rindex inode
@@ -566,14 +611,11 @@ static int read_rindex_entry(struct gfs2_inode *ip,
 	if (!rgd)
 		return error;
 
-	mutex_init(&rgd->rd_mutex);
-	lops_init_le(&rgd->rd_le, &gfs2_rg_lops);
 	rgd->rd_sbd = sdp;
 
-	list_add_tail(&rgd->rd_list, &sdp->sd_rindex_list);
-	list_add_tail(&rgd->rd_list_mru, &sdp->sd_rindex_mru_list);
-
 	gfs2_rindex_in(rgd, buf);
+	rgd_insert(rgd);
+
 	error = compute_bitstructs(rgd);
 	if (error)
 		return error;
@@ -585,6 +627,8 @@ static int read_rindex_entry(struct gfs2_inode *ip,
 
 	rgd->rd_gl->gl_object = rgd;
 	rgd->rd_flags &= ~GFS2_RDF_UPTODATE;
+	if (rgd->rd_data > sdp->sd_max_rg_data)
+		sdp->sd_max_rg_data = rgd->rd_data;
 	return error;
 }
 
@@ -601,8 +645,6 @@ int gfs2_ri_update(struct gfs2_inode *ip)
 	struct inode *inode = &ip->i_inode;
 	struct file_ra_state ra_state;
 	u64 rgrp_count = i_size_read(inode);
-	struct gfs2_rgrpd *rgd;
-	unsigned int max_data = 0;
 	int error;
 
 	do_div(rgrp_count, sizeof(struct gfs2_rindex));
@@ -617,10 +659,6 @@ int gfs2_ri_update(struct gfs2_inode *ip)
 		}
 	}
 
-	list_for_each_entry(rgd, &sdp->sd_rindex_list, rd_list)
-		if (rgd->rd_data > max_data)
-			max_data = rgd->rd_data;
-	sdp->sd_max_rg_data = max_data;
 	sdp->sd_rindex_uptodate = 1;
 	return 0;
 }
@@ -694,7 +732,7 @@ static void gfs2_rgrp_out(struct gfs2_rgrpd *rgd, void *buf)
 }
 
 /**
- * gfs2_rgrp_bh_get - Read in a RG's header and bitmaps
+ * gfs2_rgrp_go_lock - Read in a RG's header and bitmaps
  * @rgd: the struct gfs2_rgrpd describing the RG to read in
  *
  * Read in all of a Resource Group's header and bitmap blocks.
@@ -703,8 +741,9 @@ static void gfs2_rgrp_out(struct gfs2_rgrpd *rgd, void *buf)
  * Returns: errno
  */
 
-int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd)
+int gfs2_rgrp_go_lock(struct gfs2_holder *gh)
 {
+	struct gfs2_rgrpd *rgd = gh->gh_gl->gl_object;
 	struct gfs2_sbd *sdp = rgd->rd_sbd;
 	struct gfs2_glock *gl = rgd->rd_gl;
 	unsigned int length = rgd->rd_length;
@@ -712,17 +751,6 @@ int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd)
 	unsigned int x, y;
 	int error;
 
-	mutex_lock(&rgd->rd_mutex);
-
-	spin_lock(&sdp->sd_rindex_spin);
-	if (rgd->rd_bh_count) {
-		rgd->rd_bh_count++;
-		spin_unlock(&sdp->sd_rindex_spin);
-		mutex_unlock(&rgd->rd_mutex);
-		return 0;
-	}
-	spin_unlock(&sdp->sd_rindex_spin);
-
 	for (x = 0; x < length; x++) {
 		bi = rgd->rd_bits + x;
 		error = gfs2_meta_read(gl, rgd->rd_addr + x, 0, &bi->bi_bh);
@@ -747,15 +775,9 @@ int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd)
 			clear_bit(GBF_FULL, &rgd->rd_bits[x].bi_flags);
 		gfs2_rgrp_in(rgd, (rgd->rd_bits[0].bi_bh)->b_data);
 		rgd->rd_flags |= (GFS2_RDF_UPTODATE | GFS2_RDF_CHECK);
+		rgd->rd_free_clone = rgd->rd_free;
 	}
 
-	spin_lock(&sdp->sd_rindex_spin);
-	rgd->rd_free_clone = rgd->rd_free;
-	rgd->rd_bh_count++;
-	spin_unlock(&sdp->sd_rindex_spin);
-
-	mutex_unlock(&rgd->rd_mutex);
-
 	return 0;
 
 fail:
@@ -765,52 +787,32 @@ fail:
 		bi->bi_bh = NULL;
 		gfs2_assert_warn(sdp, !bi->bi_clone);
 	}
-	mutex_unlock(&rgd->rd_mutex);
 
 	return error;
 }
 
-void gfs2_rgrp_bh_hold(struct gfs2_rgrpd *rgd)
-{
-	struct gfs2_sbd *sdp = rgd->rd_sbd;
-
-	spin_lock(&sdp->sd_rindex_spin);
-	gfs2_assert_warn(rgd->rd_sbd, rgd->rd_bh_count);
-	rgd->rd_bh_count++;
-	spin_unlock(&sdp->sd_rindex_spin);
-}
-
 /**
- * gfs2_rgrp_bh_put - Release RG bitmaps read in with gfs2_rgrp_bh_get()
+ * gfs2_rgrp_go_unlock - Release RG bitmaps read in with gfs2_rgrp_bh_get()
  * @rgd: the struct gfs2_rgrpd describing the RG to read in
  *
  */
 
-void gfs2_rgrp_bh_put(struct gfs2_rgrpd *rgd)
+void gfs2_rgrp_go_unlock(struct gfs2_holder *gh)
 {
-	struct gfs2_sbd *sdp = rgd->rd_sbd;
+	struct gfs2_rgrpd *rgd = gh->gh_gl->gl_object;
 	int x, length = rgd->rd_length;
 
-	spin_lock(&sdp->sd_rindex_spin);
-	gfs2_assert_warn(rgd->rd_sbd, rgd->rd_bh_count);
-	if (--rgd->rd_bh_count) {
-		spin_unlock(&sdp->sd_rindex_spin);
-		return;
-	}
-
 	for (x = 0; x < length; x++) {
 		struct gfs2_bitmap *bi = rgd->rd_bits + x;
-		kfree(bi->bi_clone);
-		bi->bi_clone = NULL;
 		brelse(bi->bi_bh);
 		bi->bi_bh = NULL;
 	}
 
-	spin_unlock(&sdp->sd_rindex_spin);
 }
 
-static void gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset,
-				    const struct gfs2_bitmap *bi)
+void gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset,
+			     struct buffer_head *bh,
+			     const struct gfs2_bitmap *bi)
 {
 	struct super_block *sb = sdp->sd_vfs;
 	struct block_device *bdev = sb->s_bdev;
@@ -823,7 +825,7 @@ static void gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset,
 	unsigned int x;
 
 	for (x = 0; x < bi->bi_len; x++) {
-		const u8 *orig = bi->bi_bh->b_data + bi->bi_offset + x;
+		const u8 *orig = bh->b_data + bi->bi_offset + x;
 		const u8 *clone = bi->bi_clone + bi->bi_offset + x;
 		u8 diff = ~(*orig | (*orig >> 1)) & (*clone | (*clone >> 1));
 		diff &= 0x55;
@@ -862,28 +864,6 @@ fail:
 	sdp->sd_args.ar_discard = 0;
 }
 
-void gfs2_rgrp_repolish_clones(struct gfs2_rgrpd *rgd)
-{
-	struct gfs2_sbd *sdp = rgd->rd_sbd;
-	unsigned int length = rgd->rd_length;
-	unsigned int x;
-
-	for (x = 0; x < length; x++) {
-		struct gfs2_bitmap *bi = rgd->rd_bits + x;
-		if (!bi->bi_clone)
-			continue;
-		if (sdp->sd_args.ar_discard)
-			gfs2_rgrp_send_discards(sdp, rgd->rd_data0, bi);
-		clear_bit(GBF_FULL, &bi->bi_flags);
-		memcpy(bi->bi_clone + bi->bi_offset,
-		       bi->bi_bh->b_data + bi->bi_offset, bi->bi_len);
-	}
-
-	spin_lock(&sdp->sd_rindex_spin);
-	rgd->rd_free_clone = rgd->rd_free;
-	spin_unlock(&sdp->sd_rindex_spin);
-}
-
 /**
  * gfs2_alloc_get - get the struct gfs2_alloc structure for an inode
  * @ip: the incore GFS2 inode structure
@@ -911,20 +891,15 @@ struct gfs2_alloc *gfs2_alloc_get(struct gfs2_inode *ip)
 
 static int try_rgrp_fit(struct gfs2_rgrpd *rgd, struct gfs2_alloc *al)
 {
-	struct gfs2_sbd *sdp = rgd->rd_sbd;
-	int ret = 0;
-
 	if (rgd->rd_flags & (GFS2_RGF_NOALLOC | GFS2_RDF_ERROR))
 		return 0;
 
-	spin_lock(&sdp->sd_rindex_spin);
 	if (rgd->rd_free_clone >= al->al_requested) {
 		al->al_rgd = rgd;
-		ret = 1;
+		return 1;
 	}
-	spin_unlock(&sdp->sd_rindex_spin);
 
-	return ret;
+	return 0;
 }
 
 /**
@@ -992,76 +967,6 @@ static void try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked, u64 skip
 }
 
 /**
- * recent_rgrp_next - get next RG from "recent" list
- * @cur_rgd: current rgrp
- *
- * Returns: The next rgrp in the recent list
- */
-
-static struct gfs2_rgrpd *recent_rgrp_next(struct gfs2_rgrpd *cur_rgd)
-{
-	struct gfs2_sbd *sdp = cur_rgd->rd_sbd;
-	struct list_head *head;
-	struct gfs2_rgrpd *rgd;
-
-	spin_lock(&sdp->sd_rindex_spin);
-	head = &sdp->sd_rindex_mru_list;
-	if (unlikely(cur_rgd->rd_list_mru.next == head)) {
-		spin_unlock(&sdp->sd_rindex_spin);
-		return NULL;
-	}
-	rgd = list_entry(cur_rgd->rd_list_mru.next, struct gfs2_rgrpd, rd_list_mru);
-	spin_unlock(&sdp->sd_rindex_spin);
-	return rgd;
-}
-
-/**
- * forward_rgrp_get - get an rgrp to try next from full list
- * @sdp: The GFS2 superblock
- *
- * Returns: The rgrp to try next
- */
-
-static struct gfs2_rgrpd *forward_rgrp_get(struct gfs2_sbd *sdp)
-{
-	struct gfs2_rgrpd *rgd;
-	unsigned int journals = gfs2_jindex_size(sdp);
-	unsigned int rg = 0, x;
-
-	spin_lock(&sdp->sd_rindex_spin);
-
-	rgd = sdp->sd_rindex_forward;
-	if (!rgd) {
-		if (sdp->sd_rgrps >= journals)
-			rg = sdp->sd_rgrps * sdp->sd_jdesc->jd_jid / journals;
-
-		for (x = 0, rgd = gfs2_rgrpd_get_first(sdp); x < rg;
-		     x++, rgd = gfs2_rgrpd_get_next(rgd))
-			/* Do Nothing */;
-
-		sdp->sd_rindex_forward = rgd;
-	}
-
-	spin_unlock(&sdp->sd_rindex_spin);
-
-	return rgd;
-}
-
-/**
- * forward_rgrp_set - set the forward rgrp pointer
- * @sdp: the filesystem
- * @rgd: The new forward rgrp
- *
- */
-
-static void forward_rgrp_set(struct gfs2_sbd *sdp, struct gfs2_rgrpd *rgd)
-{
-	spin_lock(&sdp->sd_rindex_spin);
-	sdp->sd_rindex_forward = rgd;
-	spin_unlock(&sdp->sd_rindex_spin);
-}
-
-/**
  * get_local_rgrp - Choose and lock a rgrp for allocation
  * @ip: the inode to reserve space for
  * @rgp: the chosen and locked rgrp
@@ -1076,14 +981,15 @@ static int get_local_rgrp(struct gfs2_inode *ip, u64 *last_unlinked)
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct gfs2_rgrpd *rgd, *begin = NULL;
 	struct gfs2_alloc *al = ip->i_alloc;
-	int flags = LM_FLAG_TRY;
-	int skipped = 0;
-	int loops = 0;
 	int error, rg_locked;
+	int loops = 0;
 
-	rgd = gfs2_blk2rgrpd(sdp, ip->i_goal);
+	rgd = begin = gfs2_blk2rgrpd(sdp, ip->i_goal);
 
-	while (rgd) {
+	if (rgd == NULL)
+		return -EBADSLT;
+
+	while (loops < 3) {
 		rg_locked = 0;
 
 		if (gfs2_glock_is_locked_by_me(rgd->rd_gl)) {
@@ -1096,80 +1002,24 @@ static int get_local_rgrp(struct gfs2_inode *ip, u64 *last_unlinked)
 		switch (error) {
 		case 0:
 			if (try_rgrp_fit(rgd, al))
-				goto out;
+				return 0;
 			if (rgd->rd_flags & GFS2_RDF_CHECK)
 				try_rgrp_unlink(rgd, last_unlinked, ip->i_no_addr);
 			if (!rg_locked)
 				gfs2_glock_dq_uninit(&al->al_rgd_gh);
 			/* fall through */
 		case GLR_TRYFAILED:
-			rgd = recent_rgrp_next(rgd);
-			break;
-
-		default:
-			return error;
-		}
-	}
-
-	/* Go through full list of rgrps */
-
-	begin = rgd = forward_rgrp_get(sdp);
-
-	for (;;) {
-		rg_locked = 0;
-
-		if (gfs2_glock_is_locked_by_me(rgd->rd_gl)) {
-			rg_locked = 1;
-			error = 0;
-		} else {
-			error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE, flags,
-						   &al->al_rgd_gh);
-		}
-		switch (error) {
-		case 0:
-			if (try_rgrp_fit(rgd, al))
-				goto out;
-			if (rgd->rd_flags & GFS2_RDF_CHECK)
-				try_rgrp_unlink(rgd, last_unlinked, ip->i_no_addr);
-			if (!rg_locked)
-				gfs2_glock_dq_uninit(&al->al_rgd_gh);
-			break;
-
-		case GLR_TRYFAILED:
-			skipped++;
+			rgd = gfs2_rgrpd_get_next(rgd);
+			if (rgd == begin)
+				loops++;
 			break;
 
 		default:
 			return error;
 		}
-
-		rgd = gfs2_rgrpd_get_next(rgd);
-		if (!rgd)
-			rgd = gfs2_rgrpd_get_first(sdp);
-
-		if (rgd == begin) {
-			if (++loops >= 3)
-				return -ENOSPC;
-			if (!skipped)
-				loops++;
-			flags = 0;
-			if (loops == 2)
-				gfs2_log_flush(sdp, NULL);
-		}
-	}
-
-out:
-	if (begin) {
-		spin_lock(&sdp->sd_rindex_spin);
-		list_move(&rgd->rd_list_mru, &sdp->sd_rindex_mru_list);
-		spin_unlock(&sdp->sd_rindex_spin);
-		rgd = gfs2_rgrpd_get_next(rgd);
-		if (!rgd)
-			rgd = gfs2_rgrpd_get_first(sdp);
-		forward_rgrp_set(sdp, rgd);
 	}
 
-	return 0;
+	return -ENOSPC;
 }
 
 /**
@@ -1352,6 +1202,7 @@ do_search:
 		/* The GFS2_BLKST_UNLINKED state doesn't apply to the clone
 		   bitmaps, so we must search the originals for that. */
 		buffer = bi->bi_bh->b_data + bi->bi_offset;
+		WARN_ON(!buffer_uptodate(bi->bi_bh));
 		if (old_state != GFS2_BLKST_UNLINKED && bi->bi_clone)
 			buffer = bi->bi_clone + bi->bi_offset;
 
@@ -1371,6 +1222,7 @@ skip:
 
 	if (blk == BFITNOENT)
 		return blk;
+
 	*n = 1;
 	if (old_state == new_state)
 		goto out;
@@ -1539,9 +1391,7 @@ int gfs2_alloc_block(struct gfs2_inode *ip, u64 *bn, unsigned int *n)
 	gfs2_statfs_change(sdp, 0, -(s64)*n, 0);
 	gfs2_quota_change(ip, *n, ip->i_inode.i_uid, ip->i_inode.i_gid);
 
-	spin_lock(&sdp->sd_rindex_spin);
 	rgd->rd_free_clone -= *n;
-	spin_unlock(&sdp->sd_rindex_spin);
 	trace_gfs2_block_alloc(ip, block, *n, GFS2_BLKST_USED);
 	*bn = block;
 	return 0;
@@ -1594,9 +1444,7 @@ int gfs2_alloc_di(struct gfs2_inode *dip, u64 *bn, u64 *generation)
 	gfs2_statfs_change(sdp, 0, -1, +1);
 	gfs2_trans_add_unrevoke(sdp, block, 1);
 
-	spin_lock(&sdp->sd_rindex_spin);
 	rgd->rd_free_clone--;
-	spin_unlock(&sdp->sd_rindex_spin);
 	trace_gfs2_block_alloc(dip, block, 1, GFS2_BLKST_DINODE);
 	*bn = block;
 	return 0;
@@ -1629,8 +1477,6 @@ void __gfs2_free_blocks(struct gfs2_inode *ip, u64 bstart, u32 blen, int meta)
 	gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1);
 	gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
 
-	gfs2_trans_add_rg(rgd);
-
 	/* Directories keep their data in the metadata address space */
 	if (meta || ip->i_depth)
 		gfs2_meta_wipe(ip, bstart, blen);
@@ -1666,7 +1512,6 @@ void gfs2_unlink_di(struct inode *inode)
 	trace_gfs2_block_alloc(ip, blkno, 1, GFS2_BLKST_UNLINKED);
 	gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1);
 	gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
-	gfs2_trans_add_rg(rgd);
 }
 
 static void gfs2_free_uninit_di(struct gfs2_rgrpd *rgd, u64 blkno)
@@ -1688,7 +1533,6 @@ static void gfs2_free_uninit_di(struct gfs2_rgrpd *rgd, u64 blkno)
 	gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
 
 	gfs2_statfs_change(sdp, 0, +1, -1);
-	gfs2_trans_add_rg(rgd);
 }
 
 
diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h
index d253f9a..59b950f 100644
--- a/fs/gfs2/rgrp.h
+++ b/fs/gfs2/rgrp.h
@@ -25,11 +25,8 @@ struct gfs2_rgrpd *gfs2_rgrpd_get_next(struct gfs2_rgrpd *rgd);
 extern void gfs2_clear_rgrpd(struct gfs2_sbd *sdp);
 extern int gfs2_rindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ri_gh);
 
-extern int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd);
-extern void gfs2_rgrp_bh_hold(struct gfs2_rgrpd *rgd);
-extern void gfs2_rgrp_bh_put(struct gfs2_rgrpd *rgd);
-
-extern void gfs2_rgrp_repolish_clones(struct gfs2_rgrpd *rgd);
+extern int gfs2_rgrp_go_lock(struct gfs2_holder *gh);
+extern void gfs2_rgrp_go_unlock(struct gfs2_holder *gh);
 
 extern struct gfs2_alloc *gfs2_alloc_get(struct gfs2_inode *ip);
 static inline void gfs2_alloc_put(struct gfs2_inode *ip)
@@ -72,5 +69,8 @@ extern void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state);
 extern void gfs2_rlist_free(struct gfs2_rgrp_list *rlist);
 extern u64 gfs2_ri_total(struct gfs2_sbd *sdp);
 extern int gfs2_rgrp_dump(struct seq_file *seq, const struct gfs2_glock *gl);
+extern void gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset,
+				    struct buffer_head *bh,
+				    const struct gfs2_bitmap *bi);
 
 #endif /* __RGRP_DOT_H__ */
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index 9ec73a8..86ac75d 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -185,8 +185,3 @@ void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno, unsigned int len)
 	gfs2_log_unlock(sdp);
 }
 
-void gfs2_trans_add_rg(struct gfs2_rgrpd *rgd)
-{
-	lops_add(rgd->rd_sbd, &rgd->rd_le);
-}
-
diff --git a/fs/gfs2/trans.h b/fs/gfs2/trans.h
index fb56b78..980c5c0 100644
--- a/fs/gfs2/trans.h
+++ b/fs/gfs2/trans.h
@@ -34,14 +34,12 @@ static inline unsigned int gfs2_rg_blocks(const struct gfs2_alloc *al)
 	       al->al_requested + 1 : al->al_rgd->rd_length;
 }
 
-int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
-		     unsigned int revokes);
+extern int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
+			    unsigned int revokes);
 
-void gfs2_trans_end(struct gfs2_sbd *sdp);
-
-void gfs2_trans_add_bh(struct gfs2_glock *gl, struct buffer_head *bh, int meta);
-void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd);
-void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno, unsigned int len);
-void gfs2_trans_add_rg(struct gfs2_rgrpd *rgd);
+extern void gfs2_trans_end(struct gfs2_sbd *sdp);
+extern void gfs2_trans_add_bh(struct gfs2_glock *gl, struct buffer_head *bh, int meta);
+extern void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd);
+extern void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno, unsigned int len);
 
 #endif /* __TRANS_DOT_H__ */
-- 
1.7.4

[Cluster-devel] [PATCH 11/19] GFS2: Make resource groups "append only" during life of fs

[Steven Whitehouse]

Since we have ruled out supporting online filesystem shrink,
it is possible to make the resource group list append only
during the life of a super block. This gives several benefits:

Firstly, we only need to read new rindex elements as they are added
rather than needing to reread the whole rindex file each time one
element is added.

Secondly, the rindex glock can be held for much shorter periods of
time, and is completely removed from the fast path for allocations.
The lock is taken in shared mode only when updating the resource
groups when the first allocation occurs, and after a grow has
taken place.

Thirdly, this results in a reduction in code size, and everything
gets a lot simpler to understand in this area.

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

diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 7878c47..e602961 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -783,11 +783,6 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 	else if (ip->i_depth)
 		revokes = sdp->sd_inptrs;
 
-	if (ip != GFS2_I(sdp->sd_rindex))
-		error = gfs2_rindex_hold(sdp, &ip->i_alloc->al_ri_gh);
-	else if (!sdp->sd_rgrps)
-		error = gfs2_ri_update(ip);
-
 	if (error)
 		return error;
 
@@ -887,8 +882,6 @@ out_rg_gunlock:
 out_rlist:
 	gfs2_rlist_free(&rlist);
 out:
-	if (ip != GFS2_I(sdp->sd_rindex))
-		gfs2_glock_dq_uninit(&ip->i_alloc->al_ri_gh);
 	return error;
 }
 
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index 898e62e..90b877b 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -1807,10 +1807,6 @@ static int leaf_dealloc(struct gfs2_inode *dip, u32 index, u32 len,
 	if (error)
 		goto out_put;
 
-	error = gfs2_rindex_hold(sdp, &dip->i_alloc->al_ri_gh);
-	if (error)
-		goto out_qs;
-
 	/*  Count the number of leaves  */
 	bh = leaf_bh;
 
@@ -1889,8 +1885,6 @@ out_rg_gunlock:
 	gfs2_glock_dq_m(rlist.rl_rgrps, rlist.rl_ghs);
 out_rlist:
 	gfs2_rlist_free(&rlist);
-	gfs2_glock_dq_uninit(&dip->i_alloc->al_ri_gh);
-out_qs:
 	gfs2_quota_unhold(dip);
 out_put:
 	gfs2_alloc_put(dip);
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 6f82aac..951541b 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -134,8 +134,7 @@ void gfs2_ail_flush(struct gfs2_glock *gl)
 static void rgrp_go_sync(struct gfs2_glock *gl)
 {
 	struct address_space *metamapping = gfs2_glock2aspace(gl);
-	struct gfs2_rgrpd *rgd = gl->gl_object;
-	unsigned int x;
+	struct gfs2_rgrpd *rgd;
 	int error;
 
 	if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags))
@@ -148,14 +147,11 @@ static void rgrp_go_sync(struct gfs2_glock *gl)
         mapping_set_error(metamapping, error);
 	gfs2_ail_empty_gl(gl);
 
-	if (!rgd)
-		return;
-
-	for (x = 0; x < rgd->rd_length; x++) {
-		struct gfs2_bitmap *bi = rgd->rd_bits + x;
-		kfree(bi->bi_clone);
-		bi->bi_clone = NULL;
-	}
+	spin_lock(&gl->gl_spin);
+	rgd = gl->gl_object;
+	if (rgd)
+		gfs2_free_clones(rgd);
+	spin_unlock(&gl->gl_spin);
 }
 
 /**
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 9e753fc..56847f5 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -255,7 +255,6 @@ struct gfs2_alloc {
 
 	unsigned int al_line;
 	char *al_file;
-	struct gfs2_holder al_ri_gh;
 	struct gfs2_holder al_rgd_gh;
 	struct gfs2_rgrpd *al_rgd;
 
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 2af6905..29703dd 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -1041,13 +1041,8 @@ static int gfs2_unlink(struct inode *dir, struct dentry *dentry)
 	struct buffer_head *bh;
 	struct gfs2_holder ghs[3];
 	struct gfs2_rgrpd *rgd;
-	struct gfs2_holder ri_gh;
 	int error;
 
-	error = gfs2_rindex_hold(sdp, &ri_gh);
-	if (error)
-		return error;
-
 	gfs2_holder_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
 	gfs2_holder_init(ip->i_gl,  LM_ST_EXCLUSIVE, 0, ghs + 1);
 
@@ -1104,7 +1099,6 @@ out_child:
 	gfs2_glock_dq(ghs);
 out_parent:
 	gfs2_holder_uninit(ghs);
-	gfs2_glock_dq_uninit(&ri_gh);
 	return error;
 }
 
@@ -1222,7 +1216,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
 	struct gfs2_inode *ip = GFS2_I(odentry->d_inode);
 	struct gfs2_inode *nip = NULL;
 	struct gfs2_sbd *sdp = GFS2_SB(odir);
-	struct gfs2_holder ghs[5], r_gh = { .gh_gl = NULL, }, ri_gh;
+	struct gfs2_holder ghs[5], r_gh = { .gh_gl = NULL, };
 	struct gfs2_rgrpd *nrgd;
 	unsigned int num_gh;
 	int dir_rename = 0;
@@ -1236,10 +1230,6 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
 			return 0;
 	}
 
-	error = gfs2_rindex_hold(sdp, &ri_gh);
-	if (error)
-		return error;
-
 	if (odip != ndip) {
 		error = gfs2_glock_nq_init(sdp->sd_rename_gl, LM_ST_EXCLUSIVE,
 					   0, &r_gh);
@@ -1376,7 +1366,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
 
 		al->al_requested = sdp->sd_max_dirres;
 
-		error = gfs2_inplace_reserve_ri(ndip);
+		error = gfs2_inplace_reserve(ndip);
 		if (error)
 			goto out_gunlock_q;
 
@@ -1447,7 +1437,6 @@ out_gunlock_r:
 	if (r_gh.gh_gl)
 		gfs2_glock_dq_uninit(&r_gh);
 out:
-	gfs2_glock_dq_uninit(&ri_gh);
 	return error;
 }
 
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 00f6e3d..88d5b75 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -332,14 +332,10 @@ struct gfs2_rgrpd *gfs2_blk2rgrpd(struct gfs2_sbd *sdp, u64 blk)
 	struct rb_node **newn, *parent = NULL;
 
 	spin_lock(&sdp->sd_rindex_spin);
-
 	newn = &sdp->sd_rindex_tree.rb_node;
-
-	/* Figure out where to put new node */
 	while (*newn) {
 		struct gfs2_rgrpd *cur = rb_entry(*newn, struct gfs2_rgrpd,
 						  rd_node);
-
 		parent = *newn;
 		if (blk < cur->rd_addr)
 			newn = &((*newn)->rb_left);
@@ -350,7 +346,6 @@ struct gfs2_rgrpd *gfs2_blk2rgrpd(struct gfs2_sbd *sdp, u64 blk)
 			return cur;
 		}
 	}
-
 	spin_unlock(&sdp->sd_rindex_spin);
 
 	return NULL;
@@ -368,8 +363,10 @@ struct gfs2_rgrpd *gfs2_rgrpd_get_first(struct gfs2_sbd *sdp)
 	const struct rb_node *n;
 	struct gfs2_rgrpd *rgd;
 
+	spin_lock(&sdp->sd_rindex_spin);
 	n = rb_first(&sdp->sd_rindex_tree);
 	rgd = rb_entry(n, struct gfs2_rgrpd, rd_node);
+	spin_unlock(&sdp->sd_rindex_spin);
 
 	return rgd;
 }
@@ -400,7 +397,18 @@ struct gfs2_rgrpd *gfs2_rgrpd_get_next(struct gfs2_rgrpd *rgd)
 	return rgd;
 }
 
-static void clear_rgrpdi(struct gfs2_sbd *sdp)
+void gfs2_free_clones(struct gfs2_rgrpd *rgd)
+{
+	int x;
+
+	for (x = 0; x < rgd->rd_length; x++) {
+		struct gfs2_bitmap *bi = rgd->rd_bits + x;
+		kfree(bi->bi_clone);
+		bi->bi_clone = NULL;
+	}
+}
+
+void gfs2_clear_rgrpd(struct gfs2_sbd *sdp)
 {
 	struct rb_node *n;
 	struct gfs2_rgrpd *rgd;
@@ -413,23 +421,19 @@ static void clear_rgrpdi(struct gfs2_sbd *sdp)
 		rb_erase(n, &sdp->sd_rindex_tree);
 
 		if (gl) {
+			spin_lock(&gl->gl_spin);
 			gl->gl_object = NULL;
+			spin_unlock(&gl->gl_spin);
 			gfs2_glock_add_to_lru(gl);
 			gfs2_glock_put(gl);
 		}
 
+		gfs2_free_clones(rgd);
 		kfree(rgd->rd_bits);
 		kmem_cache_free(gfs2_rgrpd_cachep, rgd);
 	}
 }
 
-void gfs2_clear_rgrpd(struct gfs2_sbd *sdp)
-{
-	mutex_lock(&sdp->sd_rindex_mutex);
-	clear_rgrpdi(sdp);
-	mutex_unlock(&sdp->sd_rindex_mutex);
-}
-
 static void gfs2_rindex_print(const struct gfs2_rgrpd *rgd)
 {
 	printk(KERN_INFO "  ri_addr = %llu\n", (unsigned long long)rgd->rd_addr);
@@ -546,17 +550,6 @@ u64 gfs2_ri_total(struct gfs2_sbd *sdp)
 	return total_data;
 }
 
-static void gfs2_rindex_in(struct gfs2_rgrpd *rgd, const void *buf)
-{
-	const struct gfs2_rindex *str = buf;
-
-	rgd->rd_addr = be64_to_cpu(str->ri_addr);
-	rgd->rd_length = be32_to_cpu(str->ri_length);
-	rgd->rd_data0 = be64_to_cpu(str->ri_data0);
-	rgd->rd_data = be32_to_cpu(str->ri_data);
-	rgd->rd_bitbytes = be32_to_cpu(str->ri_bitbytes);
-}
-
 static void rgd_insert(struct gfs2_rgrpd *rgd)
 {
 	struct gfs2_sbd *sdp = rgd->rd_sbd;
@@ -584,7 +577,7 @@ static void rgd_insert(struct gfs2_rgrpd *rgd)
  * read_rindex_entry - Pull in a new resource index entry from the disk
  * @gl: The glock covering the rindex inode
  *
- * Returns: 0 on success, error code otherwise
+ * Returns: 0 on success, > 0 on EOF, error code otherwise
  */
 
 static int read_rindex_entry(struct gfs2_inode *ip,
@@ -592,19 +585,18 @@ static int read_rindex_entry(struct gfs2_inode *ip,
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	loff_t pos = sdp->sd_rgrps * sizeof(struct gfs2_rindex);
-	char buf[sizeof(struct gfs2_rindex)];
+	struct gfs2_rindex buf;
 	int error;
 	struct gfs2_rgrpd *rgd;
 
-	error = gfs2_internal_read(ip, ra_state, buf, &pos,
+	if (pos >= i_size_read(&ip->i_inode))
+		return 1;
+
+	error = gfs2_internal_read(ip, ra_state, (char *)&buf, &pos,
 				   sizeof(struct gfs2_rindex));
-	if (!error)
-		return 0;
-	if (error != sizeof(struct gfs2_rindex)) {
-		if (error > 0)
-			error = -EIO;
-		return error;
-	}
+
+	if (error != sizeof(struct gfs2_rindex))
+		return (error == 0) ? 1 : error;
 
 	rgd = kmem_cache_zalloc(gfs2_rgrpd_cachep, GFP_NOFS);
 	error = -ENOMEM;
@@ -612,23 +604,34 @@ static int read_rindex_entry(struct gfs2_inode *ip,
 		return error;
 
 	rgd->rd_sbd = sdp;
-
-	gfs2_rindex_in(rgd, buf);
-	rgd_insert(rgd);
+	rgd->rd_addr = be64_to_cpu(buf.ri_addr);
+	rgd->rd_length = be32_to_cpu(buf.ri_length);
+	rgd->rd_data0 = be64_to_cpu(buf.ri_data0);
+	rgd->rd_data = be32_to_cpu(buf.ri_data);
+	rgd->rd_bitbytes = be32_to_cpu(buf.ri_bitbytes);
 
 	error = compute_bitstructs(rgd);
 	if (error)
-		return error;
+		goto fail;
 
 	error = gfs2_glock_get(sdp, rgd->rd_addr,
 			       &gfs2_rgrp_glops, CREATE, &rgd->rd_gl);
 	if (error)
-		return error;
+		goto fail;
 
 	rgd->rd_gl->gl_object = rgd;
 	rgd->rd_flags &= ~GFS2_RDF_UPTODATE;
 	if (rgd->rd_data > sdp->sd_max_rg_data)
 		sdp->sd_max_rg_data = rgd->rd_data;
+	spin_lock(&sdp->sd_rindex_spin);
+	rgd_insert(rgd);
+	sdp->sd_rgrps++;
+	spin_unlock(&sdp->sd_rindex_spin);
+	return error;
+
+fail:
+	kfree(rgd->rd_bits);
+	kmem_cache_free(gfs2_rgrpd_cachep, rgd);
 	return error;
 }
 
@@ -639,34 +642,28 @@ static int read_rindex_entry(struct gfs2_inode *ip,
  * Returns: 0 on successful update, error code otherwise
  */
 
-int gfs2_ri_update(struct gfs2_inode *ip)
+static int gfs2_ri_update(struct gfs2_inode *ip)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct inode *inode = &ip->i_inode;
 	struct file_ra_state ra_state;
-	u64 rgrp_count = i_size_read(inode);
 	int error;
 
-	do_div(rgrp_count, sizeof(struct gfs2_rindex));
-	clear_rgrpdi(sdp);
-
 	file_ra_state_init(&ra_state, inode->i_mapping);
-	for (sdp->sd_rgrps = 0; sdp->sd_rgrps < rgrp_count; sdp->sd_rgrps++) {
+	do {
 		error = read_rindex_entry(ip, &ra_state);
-		if (error) {
-			clear_rgrpdi(sdp);
-			return error;
-		}
-	}
+	} while (error == 0);
+
+	if (error < 0)
+		return error;
 
 	sdp->sd_rindex_uptodate = 1;
 	return 0;
 }
 
 /**
- * gfs2_rindex_hold - Grab a lock on the rindex
+ * gfs2_rindex_update - Update the rindex if required
  * @sdp: The GFS2 superblock
- * @ri_gh: the glock holder
  *
  * We grab a lock on the rindex inode to make sure that it doesn't
  * change whilst we are performing an operation. We keep this lock
@@ -678,30 +675,29 @@ int gfs2_ri_update(struct gfs2_inode *ip)
  * special file, which might have been updated if someone expanded the
  * filesystem (via gfs2_grow utility), which adds new resource groups.
  *
- * Returns: 0 on success, error code otherwise
+ * Returns: 0 on succeess, error code otherwise
  */
 
-int gfs2_rindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ri_gh)
+int gfs2_rindex_update(struct gfs2_sbd *sdp)
 {
 	struct gfs2_inode *ip = GFS2_I(sdp->sd_rindex);
 	struct gfs2_glock *gl = ip->i_gl;
-	int error;
-
-	error = gfs2_glock_nq_init(gl, LM_ST_SHARED, 0, ri_gh);
-	if (error)
-		return error;
+	struct gfs2_holder ri_gh;
+	int error = 0;
 
 	/* Read new copy from disk if we don't have the latest */
 	if (!sdp->sd_rindex_uptodate) {
 		mutex_lock(&sdp->sd_rindex_mutex);
-		if (!sdp->sd_rindex_uptodate) {
+		error = gfs2_glock_nq_init(gl, LM_ST_SHARED, 0, &ri_gh);
+		if (error)
+			return error;
+		if (!sdp->sd_rindex_uptodate)
 			error = gfs2_ri_update(ip);
-			if (error)
-				gfs2_glock_dq_uninit(ri_gh);
-		}
+		gfs2_glock_dq_uninit(&ri_gh);
 		mutex_unlock(&sdp->sd_rindex_mutex);
 	}
 
+
 	return error;
 }
 
@@ -873,8 +869,13 @@ fail:
 
 struct gfs2_alloc *gfs2_alloc_get(struct gfs2_inode *ip)
 {
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	int error;
 	BUG_ON(ip->i_alloc != NULL);
 	ip->i_alloc = kzalloc(sizeof(struct gfs2_alloc), GFP_NOFS);
+	error = gfs2_rindex_update(sdp);
+	if (error)
+		fs_warn(sdp, "rindex update returns %d\n", error);
 	return ip->i_alloc;
 }
 
@@ -1029,7 +1030,7 @@ static int get_local_rgrp(struct gfs2_inode *ip, u64 *last_unlinked)
  * Returns: errno
  */
 
-int gfs2_inplace_reserve_i(struct gfs2_inode *ip, int hold_rindex,
+int gfs2_inplace_reserve_i(struct gfs2_inode *ip,
 			   char *file, unsigned int line)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
@@ -1041,18 +1042,6 @@ int gfs2_inplace_reserve_i(struct gfs2_inode *ip, int hold_rindex,
 	if (gfs2_assert_warn(sdp, al->al_requested))
 		return -EINVAL;
 
-	if (hold_rindex) {
-		/* We need to hold the rindex unless the inode we're using is
-		   the rindex itself, in which case it's already held. */
-		if (ip != GFS2_I(sdp->sd_rindex))
-			error = gfs2_rindex_hold(sdp, &al->al_ri_gh);
-		else if (!sdp->sd_rgrps) /* We may not have the rindex read
-					    in, so: */
-			error = gfs2_ri_update(ip);
-		if (error)
-			return error;
-	}
-
 try_again:
 	do {
 		error = get_local_rgrp(ip, &last_unlinked);
@@ -1069,11 +1058,8 @@ try_again:
 		}
 	} while (error && tries++ < 3);
 
-	if (error) {
-		if (hold_rindex && ip != GFS2_I(sdp->sd_rindex))
-			gfs2_glock_dq_uninit(&al->al_ri_gh);
+	if (error)
 		return error;
-	}
 
 	/* no error, so we have the rgrp set in the inode's allocation. */
 	al->al_file = file;
@@ -1103,8 +1089,6 @@ void gfs2_inplace_release(struct gfs2_inode *ip)
 	al->al_rgd = NULL;
 	if (al->al_rgd_gh.gh_gl)
 		gfs2_glock_dq_uninit(&al->al_rgd_gh);
-	if (ip != GFS2_I(sdp->sd_rindex) && al->al_ri_gh.gh_gl)
-		gfs2_glock_dq_uninit(&al->al_ri_gh);
 }
 
 /**
@@ -1558,34 +1542,26 @@ void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip)
 int gfs2_check_blk_type(struct gfs2_sbd *sdp, u64 no_addr, unsigned int type)
 {
 	struct gfs2_rgrpd *rgd;
-	struct gfs2_holder ri_gh, rgd_gh;
-	struct gfs2_inode *ip = GFS2_I(sdp->sd_rindex);
-	int ri_locked = 0;
+	struct gfs2_holder rgd_gh;
 	int error;
 
-	if (!gfs2_glock_is_locked_by_me(ip->i_gl)) {
-		error = gfs2_rindex_hold(sdp, &ri_gh);
-		if (error)
-			goto fail;
-		ri_locked = 1;
-	}
+	error = gfs2_rindex_update(sdp);
+	if (error)
+		return error;
 
 	error = -EINVAL;
 	rgd = gfs2_blk2rgrpd(sdp, no_addr);
 	if (!rgd)
-		goto fail_rindex;
+		goto fail;
 
 	error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_SHARED, 0, &rgd_gh);
 	if (error)
-		goto fail_rindex;
+		goto fail;
 
 	if (gfs2_get_block_type(rgd, no_addr) != type)
 		error = -ESTALE;
 
 	gfs2_glock_dq_uninit(&rgd_gh);
-fail_rindex:
-	if (ri_locked)
-		gfs2_glock_dq_uninit(&ri_gh);
 fail:
 	return error;
 }
diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h
index 59b950f..0439fca 100644
--- a/fs/gfs2/rgrp.h
+++ b/fs/gfs2/rgrp.h
@@ -18,13 +18,13 @@ struct gfs2_holder;
 
 extern void gfs2_rgrp_verify(struct gfs2_rgrpd *rgd);
 
-struct gfs2_rgrpd *gfs2_blk2rgrpd(struct gfs2_sbd *sdp, u64 blk);
-struct gfs2_rgrpd *gfs2_rgrpd_get_first(struct gfs2_sbd *sdp);
-struct gfs2_rgrpd *gfs2_rgrpd_get_next(struct gfs2_rgrpd *rgd);
+extern struct gfs2_rgrpd *gfs2_blk2rgrpd(struct gfs2_sbd *sdp, u64 blk);
+extern struct gfs2_rgrpd *gfs2_rgrpd_get_first(struct gfs2_sbd *sdp);
+extern struct gfs2_rgrpd *gfs2_rgrpd_get_next(struct gfs2_rgrpd *rgd);
 
 extern void gfs2_clear_rgrpd(struct gfs2_sbd *sdp);
-extern int gfs2_rindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ri_gh);
-
+extern int gfs2_rindex_update(struct gfs2_sbd *sdp);
+extern void gfs2_free_clones(struct gfs2_rgrpd *rgd);
 extern int gfs2_rgrp_go_lock(struct gfs2_holder *gh);
 extern void gfs2_rgrp_go_unlock(struct gfs2_holder *gh);
 
@@ -36,16 +36,13 @@ static inline void gfs2_alloc_put(struct gfs2_inode *ip)
 	ip->i_alloc = NULL;
 }
 
-extern int gfs2_inplace_reserve_i(struct gfs2_inode *ip, int hold_rindex,
+extern int gfs2_inplace_reserve_i(struct gfs2_inode *ip,
 				  char *file, unsigned int line);
 #define gfs2_inplace_reserve(ip) \
-	gfs2_inplace_reserve_i((ip), 1, __FILE__, __LINE__)
-#define gfs2_inplace_reserve_ri(ip) \
-	gfs2_inplace_reserve_i((ip), 0, __FILE__, __LINE__)
+	gfs2_inplace_reserve_i((ip),  __FILE__, __LINE__)
 
 extern void gfs2_inplace_release(struct gfs2_inode *ip);
 
-extern int gfs2_ri_update(struct gfs2_inode *ip);
 extern int gfs2_alloc_block(struct gfs2_inode *ip, u64 *bn, unsigned int *n);
 extern int gfs2_alloc_di(struct gfs2_inode *ip, u64 *bn, u64 *generation);
 
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index b05fa59..f716c4f 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1037,7 +1037,6 @@ static int statfs_slow_fill(struct gfs2_rgrpd *rgd,
 
 static int gfs2_statfs_slow(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host *sc)
 {
-	struct gfs2_holder ri_gh;
 	struct gfs2_rgrpd *rgd_next;
 	struct gfs2_holder *gha, *gh;
 	unsigned int slots = 64;
@@ -1050,10 +1049,6 @@ static int gfs2_statfs_slow(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host
 	if (!gha)
 		return -ENOMEM;
 
-	error = gfs2_rindex_hold(sdp, &ri_gh);
-	if (error)
-		goto out;
-
 	rgd_next = gfs2_rgrpd_get_first(sdp);
 
 	for (;;) {
@@ -1096,9 +1091,6 @@ static int gfs2_statfs_slow(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host
 		yield();
 	}
 
-	gfs2_glock_dq_uninit(&ri_gh);
-
-out:
 	kfree(gha);
 	return error;
 }
@@ -1150,6 +1142,10 @@ static int gfs2_statfs(struct dentry *dentry, struct kstatfs *buf)
 	struct gfs2_statfs_change_host sc;
 	int error;
 
+	error = gfs2_rindex_update(sdp);
+	if (error)
+		return error;
+
 	if (gfs2_tune_get(sdp, gt_statfs_slow))
 		error = gfs2_statfs_slow(sdp, &sc);
 	else
@@ -1420,21 +1416,17 @@ static int gfs2_dinode_dealloc(struct gfs2_inode *ip)
 	if (error)
 		goto out;
 
-	error = gfs2_rindex_hold(sdp, &al->al_ri_gh);
-	if (error)
-		goto out_qs;
-
 	rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr);
 	if (!rgd) {
 		gfs2_consist_inode(ip);
 		error = -EIO;
-		goto out_rindex_relse;
+		goto out_qs;
 	}
 
 	error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0,
 				   &al->al_rgd_gh);
 	if (error)
-		goto out_rindex_relse;
+		goto out_qs;
 
 	error = gfs2_trans_begin(sdp, RES_RG_BIT + RES_STATFS + RES_QUOTA,
 				 sdp->sd_jdesc->jd_blocks);
@@ -1449,8 +1441,6 @@ static int gfs2_dinode_dealloc(struct gfs2_inode *ip)
 
 out_rg_gunlock:
 	gfs2_glock_dq_uninit(&al->al_rgd_gh);
-out_rindex_relse:
-	gfs2_glock_dq_uninit(&al->al_ri_gh);
 out_qs:
 	gfs2_quota_unhold(ip);
 out:
diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c
index 695304c..167f4af 100644
--- a/fs/gfs2/xattr.c
+++ b/fs/gfs2/xattr.c
@@ -332,15 +332,8 @@ static int ea_remove_unstuffed(struct gfs2_inode *ip, struct buffer_head *bh,
 	if (error)
 		goto out_alloc;
 
-	error = gfs2_rindex_hold(GFS2_SB(&ip->i_inode), &al->al_ri_gh);
-	if (error)
-		goto out_quota;
-
 	error = ea_dealloc_unstuffed(ip, bh, ea, prev, (leave) ? &error : NULL);
 
-	gfs2_glock_dq_uninit(&al->al_ri_gh);
-
-out_quota:
 	gfs2_quota_unhold(ip);
 out_alloc:
 	gfs2_alloc_put(ip);
@@ -1502,24 +1495,18 @@ int gfs2_ea_dealloc(struct gfs2_inode *ip)
 	if (error)
 		goto out_alloc;
 
-	error = gfs2_rindex_hold(GFS2_SB(&ip->i_inode), &al->al_ri_gh);
-	if (error)
-		goto out_quota;
-
 	error = ea_foreach(ip, ea_dealloc_unstuffed, NULL);
 	if (error)
-		goto out_rindex;
+		goto out_quota;
 
 	if (ip->i_diskflags & GFS2_DIF_EA_INDIRECT) {
 		error = ea_dealloc_indirect(ip);
 		if (error)
-			goto out_rindex;
+			goto out_quota;
 	}
 
 	error = ea_dealloc_block(ip);
 
-out_rindex:
-	gfs2_glock_dq_uninit(&al->al_ri_gh);
 out_quota:
 	gfs2_quota_unhold(ip);
 out_alloc:
-- 
1.7.4

[Cluster-devel] [PATCH 12/19] GFS2: Cache the most recently used resource group in the inode

[Steven Whitehouse]

This means that after the initial allocation for any inode, the
last used resource group is cached in the inode for future use.
This drastically reduces the number of lookups of resource
groups in the common case, and this the contention on that
data structure.

The allocation algorithm is the same as previously, except that we
always check to see if the goal block is within the cached rgrp
first before going to the rbtree to look one up.

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

diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 212fe74..4858e1f 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -663,7 +663,7 @@ static int gfs2_write_begin(struct file *file, struct address_space *mapping,
 	if (&ip->i_inode == sdp->sd_rindex)
 		rblocks += 2 * RES_STATFS;
 	if (alloc_required)
-		rblocks += gfs2_rg_blocks(al);
+		rblocks += gfs2_rg_blocks(ip);
 
 	error = gfs2_trans_begin(sdp, rblocks,
 				 PAGE_CACHE_SIZE/sdp->sd_sb.sb_bsize);
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index d717b72..3467f36 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -397,7 +397,7 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 		rblocks += data_blocks ? data_blocks : 1;
 	if (ind_blocks || data_blocks) {
 		rblocks += RES_STATFS + RES_QUOTA;
-		rblocks += gfs2_rg_blocks(al);
+		rblocks += gfs2_rg_blocks(ip);
 	}
 	ret = gfs2_trans_begin(sdp, rblocks, 0);
 	if (ret)
@@ -823,7 +823,7 @@ static void calc_max_reserv(struct gfs2_inode *ip, loff_t max, loff_t *len,
 			    unsigned int *data_blocks, unsigned int *ind_blocks)
 {
 	const struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-	unsigned int max_blocks = ip->i_alloc->al_rgd->rd_free_clone;
+	unsigned int max_blocks = ip->i_rgd->rd_free_clone;
 	unsigned int tmp, max_data = max_blocks - 3 * (sdp->sd_max_height - 1);
 
 	for (tmp = max_data; tmp > sdp->sd_diptrs;) {
@@ -912,7 +912,7 @@ retry:
 		al->al_requested = data_blocks + ind_blocks;
 
 		rblocks = RES_DINODE + ind_blocks + RES_STATFS + RES_QUOTA +
-			  RES_RG_HDR + gfs2_rg_blocks(al);
+			  RES_RG_HDR + gfs2_rg_blocks(ip);
 		if (gfs2_is_jdata(ip))
 			rblocks += data_blocks ? data_blocks : 1;
 
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 56847f5..55e335b 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -256,8 +256,6 @@ struct gfs2_alloc {
 	unsigned int al_line;
 	char *al_file;
 	struct gfs2_holder al_rgd_gh;
-	struct gfs2_rgrpd *al_rgd;
-
 };
 
 enum {
@@ -279,6 +277,7 @@ struct gfs2_inode {
 	struct gfs2_holder i_iopen_gh;
 	struct gfs2_holder i_gh; /* for prepare/commit_write only */
 	struct gfs2_alloc *i_alloc;
+	struct gfs2_rgrpd *i_rgd;
 	u64 i_goal;	/* goal block for allocations */
 	struct rw_semaphore i_rw_mutex;
 	struct list_head i_trunc_list;
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 29703dd..55b3bba 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -583,7 +583,7 @@ static int link_dinode(struct gfs2_inode *dip, const struct qstr *name,
 			goto fail_quota_locks;
 
 		error = gfs2_trans_begin(sdp, sdp->sd_max_dirres +
-					 al->al_rgd->rd_length +
+					 dip->i_rgd->rd_length +
 					 2 * RES_DINODE +
 					 RES_STATFS + RES_QUOTA, 0);
 		if (error)
@@ -613,8 +613,7 @@ fail_end_trans:
 	gfs2_trans_end(sdp);
 
 fail_ipreserv:
-	if (dip->i_alloc->al_rgd)
-		gfs2_inplace_release(dip);
+	gfs2_inplace_release(dip);
 
 fail_quota_locks:
 	gfs2_quota_unlock(dip);
@@ -731,8 +730,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 		brelse(bh);
 
 	gfs2_trans_end(sdp);
-	if (dip->i_alloc->al_rgd)
-		gfs2_inplace_release(dip);
+	gfs2_inplace_release(dip);
 	gfs2_quota_unlock(dip);
 	gfs2_alloc_put(dip);
 	mark_inode_dirty(inode);
@@ -896,7 +894,7 @@ static int gfs2_link(struct dentry *old_dentry, struct inode *dir,
 			goto out_gunlock_q;
 
 		error = gfs2_trans_begin(sdp, sdp->sd_max_dirres +
-					 gfs2_rg_blocks(al) +
+					 gfs2_rg_blocks(dip) +
 					 2 * RES_DINODE + RES_STATFS +
 					 RES_QUOTA, 0);
 		if (error)
@@ -1371,7 +1369,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
 			goto out_gunlock_q;
 
 		error = gfs2_trans_begin(sdp, sdp->sd_max_dirres +
-					 gfs2_rg_blocks(al) +
+					 gfs2_rg_blocks(ndip) +
 					 4 * RES_DINODE + 4 * RES_LEAF +
 					 RES_STATFS + RES_QUOTA + 4, 0);
 		if (error)
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 0c8e5d3..3f88b19 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -813,7 +813,7 @@ static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda)
 		goto out_alloc;
 
 	if (nalloc)
-		blocks += gfs2_rg_blocks(al) + nalloc * ind_blocks + RES_STATFS;
+		blocks += gfs2_rg_blocks(ip) + nalloc * ind_blocks + RES_STATFS;
 
 	error = gfs2_trans_begin(sdp, blocks, 0);
 	if (error)
@@ -1598,7 +1598,7 @@ static int gfs2_set_dqblk(struct super_block *sb, int type, qid_t id,
 		error = gfs2_inplace_reserve(ip);
 		if (error)
 			goto out_alloc;
-		blocks += gfs2_rg_blocks(al);
+		blocks += gfs2_rg_blocks(ip);
 	}
 
 	/* Some quotas span block boundaries and can update two blocks,
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 88d5b75..5bfb970 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -882,24 +882,21 @@ struct gfs2_alloc *gfs2_alloc_get(struct gfs2_inode *ip)
 /**
  * try_rgrp_fit - See if a given reservation will fit in a given RG
  * @rgd: the RG data
- * @al: the struct gfs2_alloc structure describing the reservation
+ * @ip: the inode
  *
  * If there's room for the requested blocks to be allocated from the RG:
- *   Sets the $al_rgd field in @al.
  *
  * Returns: 1 on success (it fits), 0 on failure (it doesn't fit)
  */
 
-static int try_rgrp_fit(struct gfs2_rgrpd *rgd, struct gfs2_alloc *al)
+static int try_rgrp_fit(const struct gfs2_rgrpd *rgd, const struct gfs2_inode *ip)
 {
+	const struct gfs2_alloc *al = ip->i_alloc;
+
 	if (rgd->rd_flags & (GFS2_RGF_NOALLOC | GFS2_RDF_ERROR))
 		return 0;
-
-	if (rgd->rd_free_clone >= al->al_requested) {
-		al->al_rgd = rgd;
+	if (rgd->rd_free_clone >= al->al_requested)
 		return 1;
-	}
-
 	return 0;
 }
 
@@ -985,7 +982,10 @@ static int get_local_rgrp(struct gfs2_inode *ip, u64 *last_unlinked)
 	int error, rg_locked;
 	int loops = 0;
 
-	rgd = begin = gfs2_blk2rgrpd(sdp, ip->i_goal);
+	if (ip->i_rgd && rgrp_contains_block(ip->i_rgd, ip->i_goal))
+		rgd = begin = ip->i_rgd;
+	else
+		rgd = begin = gfs2_blk2rgrpd(sdp, ip->i_goal);
 
 	if (rgd == NULL)
 		return -EBADSLT;
@@ -1002,8 +1002,10 @@ static int get_local_rgrp(struct gfs2_inode *ip, u64 *last_unlinked)
 		}
 		switch (error) {
 		case 0:
-			if (try_rgrp_fit(rgd, al))
+			if (try_rgrp_fit(rgd, ip)) {
+				ip->i_rgd = rgd;
 				return 0;
+			}
 			if (rgd->rd_flags & GFS2_RDF_CHECK)
 				try_rgrp_unlink(rgd, last_unlinked, ip->i_no_addr);
 			if (!rg_locked)
@@ -1014,7 +1016,6 @@ static int get_local_rgrp(struct gfs2_inode *ip, u64 *last_unlinked)
 			if (rgd == begin)
 				loops++;
 			break;
-
 		default:
 			return error;
 		}
@@ -1042,21 +1043,20 @@ int gfs2_inplace_reserve_i(struct gfs2_inode *ip,
 	if (gfs2_assert_warn(sdp, al->al_requested))
 		return -EINVAL;
 
-try_again:
 	do {
 		error = get_local_rgrp(ip, &last_unlinked);
-		/* If there is no space, flushing the log may release some */
-		if (error) {
-			if (ip == GFS2_I(sdp->sd_rindex) &&
-			    !sdp->sd_rindex_uptodate) {
-				error = gfs2_ri_update(ip);
-				if (error)
-					return error;
-				goto try_again;
-			}
-			gfs2_log_flush(sdp, NULL);
+		if (error != -ENOSPC)
+			break;
+		/* Check that fs hasn't grown if writing to rindex */
+		if (ip == GFS2_I(sdp->sd_rindex) && !sdp->sd_rindex_uptodate) {
+			error = gfs2_ri_update(ip);
+			if (error)
+				break;
+			continue;
 		}
-	} while (error && tries++ < 3);
+		/* Flushing the log may release space */
+		gfs2_log_flush(sdp, NULL);
+	} while (tries++ < 3);
 
 	if (error)
 		return error;
@@ -1086,7 +1086,6 @@ void gfs2_inplace_release(struct gfs2_inode *ip)
 		             al->al_alloced, al->al_requested, al->al_file,
 			     al->al_line);
 
-	al->al_rgd = NULL;
 	if (al->al_rgd_gh.gh_gl)
 		gfs2_glock_dq_uninit(&al->al_rgd_gh);
 }
@@ -1339,7 +1338,7 @@ int gfs2_alloc_block(struct gfs2_inode *ip, u64 *bn, unsigned int *n)
 	if (al == NULL)
 		return -ECANCELED;
 
-	rgd = al->al_rgd;
+	rgd = ip->i_rgd;
 
 	if (rgrp_contains_block(rgd, ip->i_goal))
 		goal = ip->i_goal - rgd->rd_data0;
@@ -1398,7 +1397,7 @@ int gfs2_alloc_di(struct gfs2_inode *dip, u64 *bn, u64 *generation)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
 	struct gfs2_alloc *al = dip->i_alloc;
-	struct gfs2_rgrpd *rgd = al->al_rgd;
+	struct gfs2_rgrpd *rgd = dip->i_rgd;
 	u32 blk;
 	u64 block;
 	unsigned int n = 1;
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index f716c4f..87e9141 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1574,6 +1574,7 @@ static struct inode *gfs2_alloc_inode(struct super_block *sb)
 	if (ip) {
 		ip->i_flags = 0;
 		ip->i_gl = NULL;
+		ip->i_rgd = NULL;
 	}
 	return &ip->i_inode;
 }
diff --git a/fs/gfs2/trans.h b/fs/gfs2/trans.h
index 980c5c0..f8f101e 100644
--- a/fs/gfs2/trans.h
+++ b/fs/gfs2/trans.h
@@ -28,10 +28,12 @@ struct gfs2_glock;
 
 /* reserve either the number of blocks to be allocated plus the rg header
  * block, or all of the blocks in the rg, whichever is smaller */
-static inline unsigned int gfs2_rg_blocks(const struct gfs2_alloc *al)
+static inline unsigned int gfs2_rg_blocks(const struct gfs2_inode *ip)
 {
-	return (al->al_requested < al->al_rgd->rd_length)?
-	       al->al_requested + 1 : al->al_rgd->rd_length;
+	const struct gfs2_alloc *al = ip->i_alloc;
+	if (al->al_requested < ip->i_rgd->rd_length)
+		return al->al_requested + 1;
+	return ip->i_rgd->rd_length;
 }
 
 extern int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c
index 167f4af..e7bf0ea 100644
--- a/fs/gfs2/xattr.c
+++ b/fs/gfs2/xattr.c
@@ -727,7 +727,7 @@ static int ea_alloc_skeleton(struct gfs2_inode *ip, struct gfs2_ea_request *er,
 		goto out_gunlock_q;
 
 	error = gfs2_trans_begin(GFS2_SB(&ip->i_inode),
-				 blks + gfs2_rg_blocks(al) +
+				 blks + gfs2_rg_blocks(ip) +
 				 RES_DINODE + RES_STATFS + RES_QUOTA, 0);
 	if (error)
 		goto out_ipres;
-- 
1.7.4

[Cluster-devel] [PATCH 13/19] GFS2: Remove obsolete assert

[Steven Whitehouse]

Given that a resource group has been locked, there is no reason why
we should not be able to allocate as many blocks as are free. The
al_requested parameter should really be considered as a minimum
number of blocks to be available. Should this limit be overshot,
there are other mechanisms which will prevent over allocation.

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

diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 5bfb970..08b3a80 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -1077,15 +1077,8 @@ int gfs2_inplace_reserve_i(struct gfs2_inode *ip,
 
 void gfs2_inplace_release(struct gfs2_inode *ip)
 {
-	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct gfs2_alloc *al = ip->i_alloc;
 
-	if (gfs2_assert_warn(sdp, al->al_alloced <= al->al_requested) == -1)
-		fs_warn(sdp, "al_alloced = %u, al_requested = %u "
-			     "al_file = %s, al_line = %u\n",
-		             al->al_alloced, al->al_requested, al->al_file,
-			     al->al_line);
-
 	if (al->al_rgd_gh.gh_gl)
 		gfs2_glock_dq_uninit(&al->al_rgd_gh);
 }
-- 
1.7.4

[Cluster-devel] [PATCH 14/19] GFS2: Call do_strip() directly from recursive_scan()

[Steven Whitehouse]

The recursive_scan() function only ever takes a single "bc"
argument, so we might as well just call do_strip() directly
from resource_scan() rather than pass it in as an argument.

Also the "data" argument is always a struct strip_mine, so
we can pass that in, rather than using a void pointer.

This also moves do_strip() ahead of recursive_scan() so that
we don't need to add a prototype.

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

diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index e602961..9d3a0c2 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -36,11 +36,6 @@ struct metapath {
 	__u16 mp_list[GFS2_MAX_META_HEIGHT];
 };
 
-typedef int (*block_call_t) (struct gfs2_inode *ip, struct buffer_head *dibh,
-			     struct buffer_head *bh, __be64 *top,
-			     __be64 *bottom, unsigned int height,
-			     void *data);
-
 struct strip_mine {
 	int sm_first;
 	unsigned int sm_height;
@@ -668,76 +663,6 @@ int gfs2_extent_map(struct inode *inode, u64 lblock, int *new, u64 *dblock, unsi
 }
 
 /**
- * recursive_scan - recursively scan through the end of a file
- * @ip: the inode
- * @dibh: the dinode buffer
- * @mp: the path through the metadata to the point to start
- * @height: the height the recursion is at
- * @block: the indirect block to look at
- * @first: 1 if this is the first block
- * @bc: the call to make for each piece of metadata
- * @data: data opaque to this function to pass to @bc
- *
- * When this is first called @height and @block should be zero and
- * @first should be 1.
- *
- * Returns: errno
- */
-
-static int recursive_scan(struct gfs2_inode *ip, struct buffer_head *dibh,
-			  struct metapath *mp, unsigned int height,
-			  u64 block, int first, block_call_t bc,
-			  void *data)
-{
-	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-	struct buffer_head *bh = NULL;
-	__be64 *top, *bottom;
-	u64 bn;
-	int error;
-	int mh_size = sizeof(struct gfs2_meta_header);
-
-	if (!height) {
-		error = gfs2_meta_inode_buffer(ip, &bh);
-		if (error)
-			return error;
-		dibh = bh;
-
-		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);
-		if (error)
-			return error;
-
-		top = (__be64 *)(bh->b_data + mh_size) +
-				  (first ? mp->mp_list[height] : 0);
-
-		bottom = (__be64 *)(bh->b_data + mh_size) + sdp->sd_inptrs;
-	}
-
-	error = bc(ip, dibh, bh, top, bottom, height, data);
-	if (error)
-		goto out;
-
-	if (height < ip->i_height - 1)
-		for (; top < bottom; top++, first = 0) {
-			if (!*top)
-				continue;
-
-			bn = be64_to_cpu(*top);
-
-			error = recursive_scan(ip, dibh, mp, height + 1, bn,
-					       first, bc, data);
-			if (error)
-				break;
-		}
-
-out:
-	brelse(bh);
-	return error;
-}
-
-/**
  * do_strip - Look for a layer a particular layer of the file and strip it off
  * @ip: the inode
  * @dibh: the dinode buffer
@@ -752,9 +677,8 @@ out:
 
 static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 		    struct buffer_head *bh, __be64 *top, __be64 *bottom,
-		    unsigned int height, void *data)
+		    unsigned int height, struct strip_mine *sm)
 {
-	struct strip_mine *sm = data;
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct gfs2_rgrp_list rlist;
 	u64 bn, bstart;
@@ -886,6 +810,75 @@ out:
 }
 
 /**
+ * recursive_scan - recursively scan through the end of a file
+ * @ip: the inode
+ * @dibh: the dinode buffer
+ * @mp: the path through the metadata to the point to start
+ * @height: the height the recursion is at
+ * @block: the indirect block to look at
+ * @first: 1 if this is the first block
+ * @sm: data opaque to this function to pass to @bc
+ *
+ * When this is first called @height and @block should be zero and
+ * @first should be 1.
+ *
+ * Returns: errno
+ */
+
+static int recursive_scan(struct gfs2_inode *ip, struct buffer_head *dibh,
+			  struct metapath *mp, unsigned int height,
+			  u64 block, int first, struct strip_mine *sm)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct buffer_head *bh = NULL;
+	__be64 *top, *bottom;
+	u64 bn;
+	int error;
+	int mh_size = sizeof(struct gfs2_meta_header);
+
+	if (!height) {
+		error = gfs2_meta_inode_buffer(ip, &bh);
+		if (error)
+			return error;
+		dibh = bh;
+
+		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);
+		if (error)
+			return error;
+
+		top = (__be64 *)(bh->b_data + mh_size) +
+				  (first ? mp->mp_list[height] : 0);
+
+		bottom = (__be64 *)(bh->b_data + mh_size) + sdp->sd_inptrs;
+	}
+
+	error = do_strip(ip, dibh, bh, top, bottom, height, sm);
+	if (error)
+		goto out;
+
+	if (height < ip->i_height - 1)
+		for (; top < bottom; top++, first = 0) {
+			if (!*top)
+				continue;
+
+			bn = be64_to_cpu(*top);
+
+			error = recursive_scan(ip, dibh, mp, height + 1, bn,
+					       first, sm);
+			if (error)
+				break;
+		}
+
+out:
+	brelse(bh);
+	return error;
+}
+
+
+/**
  * gfs2_block_truncate_page - Deal with zeroing out data for truncate
  *
  * This is partly borrowed from ext3.
@@ -1024,7 +1017,7 @@ static int trunc_dealloc(struct gfs2_inode *ip, u64 size)
 		sm.sm_first = !!size;
 		sm.sm_height = height;
 
-		error = recursive_scan(ip, NULL, &mp, 0, 0, 1, do_strip, &sm);
+		error = recursive_scan(ip, NULL, &mp, 0, 0, 1, &sm);
 		if (error)
 			break;
 	}
-- 
1.7.4

[Cluster-devel] [PATCH 15/19] GFS2: Use cached rgrp in gfs2_rlist_add()

[Steven Whitehouse]

Each block which is deallocated, requires a call to gfs2_rlist_add()
and each of those calls was calling gfs2_blk2rgrpd() in order to
figure out which rgrp the block belonged in. This can be speeded up
by making use of the rgrp cached in the inode. We also reset this
cached rgrp in case the block has changed rgrp. This should provide
a big reduction in gfs2_blk2rgrpd() calls during deallocation.

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

diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 9d3a0c2..22ad413 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -724,7 +724,7 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 			blen++;
 		else {
 			if (bstart)
-				gfs2_rlist_add(sdp, &rlist, bstart);
+				gfs2_rlist_add(ip, &rlist, bstart);
 
 			bstart = bn;
 			blen = 1;
@@ -732,7 +732,7 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 	}
 
 	if (bstart)
-		gfs2_rlist_add(sdp, &rlist, bstart);
+		gfs2_rlist_add(ip, &rlist, bstart);
 	else
 		goto out; /* Nothing to do */
 
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index 90b877b..8ccad24 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -1821,7 +1821,7 @@ static int leaf_dealloc(struct gfs2_inode *dip, u32 index, u32 len,
 		if (blk != leaf_no)
 			brelse(bh);
 
-		gfs2_rlist_add(sdp, &rlist, blk);
+		gfs2_rlist_add(dip, &rlist, blk);
 		l_blocks++;
 	}
 
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 08b3a80..3088fb2 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -1560,7 +1560,7 @@ fail:
 
 /**
  * gfs2_rlist_add - add a RG to a list of RGs
- * @sdp: the filesystem
+ * @ip: the inode
  * @rlist: the list of resource groups
  * @block: the block
  *
@@ -1570,9 +1570,10 @@ fail:
  *
  */
 
-void gfs2_rlist_add(struct gfs2_sbd *sdp, struct gfs2_rgrp_list *rlist,
+void gfs2_rlist_add(struct gfs2_inode *ip, struct gfs2_rgrp_list *rlist,
 		    u64 block)
 {
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct gfs2_rgrpd *rgd;
 	struct gfs2_rgrpd **tmp;
 	unsigned int new_space;
@@ -1581,12 +1582,15 @@ void gfs2_rlist_add(struct gfs2_sbd *sdp, struct gfs2_rgrp_list *rlist,
 	if (gfs2_assert_warn(sdp, !rlist->rl_ghs))
 		return;
 
-	rgd = gfs2_blk2rgrpd(sdp, block);
+	if (ip->i_rgd && rgrp_contains_block(ip->i_rgd, block))
+		rgd = ip->i_rgd;
+	else
+		rgd = gfs2_blk2rgrpd(sdp, block);
 	if (!rgd) {
-		if (gfs2_consist(sdp))
-			fs_err(sdp, "block = %llu\n", (unsigned long long)block);
+		fs_err(sdp, "rlist_add: no rgrp for block %llu\n", (unsigned long long)block);
 		return;
 	}
+	ip->i_rgd = rgd;
 
 	for (x = 0; x < rlist->rl_rgrps; x++)
 		if (rlist->rl_rgd[x] == rgd)
diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h
index 0439fca..0e886d8 100644
--- a/fs/gfs2/rgrp.h
+++ b/fs/gfs2/rgrp.h
@@ -60,7 +60,7 @@ struct gfs2_rgrp_list {
 	struct gfs2_holder *rl_ghs;
 };
 
-extern void gfs2_rlist_add(struct gfs2_sbd *sdp, struct gfs2_rgrp_list *rlist,
+extern void gfs2_rlist_add(struct gfs2_inode *ip, struct gfs2_rgrp_list *rlist,
 			   u64 block);
 extern void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist, unsigned int state);
 extern void gfs2_rlist_free(struct gfs2_rgrp_list *rlist);
diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c
index e7bf0ea..71d7bf8 100644
--- a/fs/gfs2/xattr.c
+++ b/fs/gfs2/xattr.c
@@ -1356,14 +1356,14 @@ static int ea_dealloc_indirect(struct gfs2_inode *ip)
 			blen++;
 		else {
 			if (bstart)
-				gfs2_rlist_add(sdp, &rlist, bstart);
+				gfs2_rlist_add(ip, &rlist, bstart);
 			bstart = bn;
 			blen = 1;
 		}
 		blks++;
 	}
 	if (bstart)
-		gfs2_rlist_add(sdp, &rlist, bstart);
+		gfs2_rlist_add(ip, &rlist, bstart);
 	else
 		goto out;
 
-- 
1.7.4

[Cluster-devel] [PATCH 16/19] GFS2: Fix AIL flush issue during fsync

[Steven Whitehouse]

Unfortunately, it is not enough to just ignore locked buffers during
the AIL flush from fsync. We need to be able to ignore all buffers
which are locked, dirty or pinned at this stage as they might have
been added subsequent to the log flush earlier in the fsync function.

In addition, this means that we no longer need to rely on i_mutex to
keep out writes during fsync, so we can, as a side-effect, remove
that protection too.

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
Tested-By: Abhijith Das <adas@redhat.com>

diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 3467f36..3b65f67 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -593,16 +593,12 @@ static int gfs2_fsync(struct file *file, loff_t start, loff_t end,
 		sync_state &= ~I_DIRTY_SYNC;
 
 	if (sync_state) {
-		mutex_lock(&inode->i_mutex);
 		ret = sync_inode_metadata(inode, 1);
-		if (ret) {
-			mutex_unlock(&inode->i_mutex);
+		if (ret)
 			return ret;
-		}
 		if (gfs2_is_jdata(ip))
 			filemap_write_and_wait(mapping);
-		gfs2_ail_flush(ip->i_gl);
-		mutex_unlock(&inode->i_mutex);
+		gfs2_ail_flush(ip->i_gl, 1);
 	}
 
 	if (mapping->nrpages)
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 951541b..78418b4 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -42,41 +42,41 @@ static void gfs2_ail_error(struct gfs2_glock *gl, const struct buffer_head *bh)
 /**
  * __gfs2_ail_flush - remove all buffers for a given lock from the AIL
  * @gl: the glock
+ * @fsync: set when called from fsync (not all buffers will be clean)
  *
  * None of the buffers should be dirty, locked, or pinned.
  */
 
-static void __gfs2_ail_flush(struct gfs2_glock *gl, unsigned long b_state)
+static void __gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
 {
 	struct gfs2_sbd *sdp = gl->gl_sbd;
 	struct list_head *head = &gl->gl_ail_list;
-	struct gfs2_bufdata *bd;
+	struct gfs2_bufdata *bd, *tmp;
 	struct buffer_head *bh;
+	const unsigned long b_state = (1UL << BH_Dirty)|(1UL << BH_Pinned)|(1UL << BH_Lock);
 	sector_t blocknr;
 
+	gfs2_log_lock(sdp);
 	spin_lock(&sdp->sd_ail_lock);
-	while (!list_empty(head)) {
-		bd = list_entry(head->next, struct gfs2_bufdata,
-				bd_ail_gl_list);
+	list_for_each_entry_safe(bd, tmp, head, bd_ail_gl_list) {
 		bh = bd->bd_bh;
-		blocknr = bh->b_blocknr;
-		if (bh->b_state & b_state)
+		if (bh->b_state & b_state) {
+			if (fsync)
+				continue;
 			gfs2_ail_error(gl, bh);
+		}
+		blocknr = bh->b_blocknr;
 		bh->b_private = NULL;
 		gfs2_remove_from_ail(bd); /* drops ref on bh */
-		spin_unlock(&sdp->sd_ail_lock);
 
 		bd->bd_bh = NULL;
 		bd->bd_blkno = blocknr;
 
-		gfs2_log_lock(sdp);
 		gfs2_trans_add_revoke(sdp, bd);
-		gfs2_log_unlock(sdp);
-
-		spin_lock(&sdp->sd_ail_lock);
 	}
-	gfs2_assert_withdraw(sdp, !atomic_read(&gl->gl_ail_count));
+	BUG_ON(!fsync && atomic_read(&gl->gl_ail_count));
 	spin_unlock(&sdp->sd_ail_lock);
+	gfs2_log_unlock(sdp);
 }
 
 
@@ -99,13 +99,13 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
 	BUG_ON(current->journal_info);
 	current->journal_info = &tr;
 
-	__gfs2_ail_flush(gl, (1ul << BH_Dirty)|(1ul << BH_Pinned)|(1ul << BH_Lock));
+	__gfs2_ail_flush(gl, 0);
 
 	gfs2_trans_end(sdp);
 	gfs2_log_flush(sdp, NULL);
 }
 
-void gfs2_ail_flush(struct gfs2_glock *gl)
+void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
 {
 	struct gfs2_sbd *sdp = gl->gl_sbd;
 	unsigned int revokes = atomic_read(&gl->gl_ail_count);
@@ -117,7 +117,7 @@ void gfs2_ail_flush(struct gfs2_glock *gl)
 	ret = gfs2_trans_begin(sdp, 0, revokes);
 	if (ret)
 		return;
-	__gfs2_ail_flush(gl, (1ul << BH_Dirty)|(1ul << BH_Pinned));
+	__gfs2_ail_flush(gl, fsync);
 	gfs2_trans_end(sdp);
 	gfs2_log_flush(sdp, NULL);
 }
diff --git a/fs/gfs2/glops.h b/fs/gfs2/glops.h
index 6fce409..bf95a2d 100644
--- a/fs/gfs2/glops.h
+++ b/fs/gfs2/glops.h
@@ -23,6 +23,6 @@ extern const struct gfs2_glock_operations gfs2_quota_glops;
 extern const struct gfs2_glock_operations gfs2_journal_glops;
 extern const struct gfs2_glock_operations *gfs2_glops_list[];
 
-extern void gfs2_ail_flush(struct gfs2_glock *gl);
+extern void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync);
 
 #endif /* __GLOPS_DOT_H__ */
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 87e9141..71e4209 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1533,7 +1533,7 @@ static void gfs2_evict_inode(struct inode *inode)
 out_truncate:
 	gfs2_log_flush(sdp, ip->i_gl);
 	write_inode_now(inode, 1);
-	gfs2_ail_flush(ip->i_gl);
+	gfs2_ail_flush(ip->i_gl, 0);
 
 	/* Case 2 starts here */
 	error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks);
-- 
1.7.4

[Cluster-devel] [PATCH 17/19] GFS2: Correctly set goal block after allocation

[Steven Whitehouse]

The new goal block should be set to the end of the newly
allocated extent, not the start of it.

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

diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 3088fb2..8ec4174 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -1346,7 +1346,7 @@ int gfs2_alloc_block(struct gfs2_inode *ip, u64 *bn, unsigned int *n)
 
 	rgd->rd_last_alloc = blk;
 	block = rgd->rd_data0 + blk;
-	ip->i_goal = block;
+	ip->i_goal = block + *n - 1;
 	error = gfs2_meta_inode_buffer(ip, &dibh);
 	if (error == 0) {
 		struct gfs2_dinode *di = (struct gfs2_dinode *)dibh->b_data;
-- 
1.7.4

[Cluster-devel] [PATCH 18/19] GFS2: Clean up ->page_mkwrite

[Steven Whitehouse]

This patch brings gfs2's ->page_mkwrite uptodate with respect to the
expectations set by the VM. Also added is a check to wait if the fs
is frozen, before we attempt to get a glock. This will only work on
the node which initiates the freeze, but thats ok since the transaction
lock will still provide the expected barrier on other nodes.

The major change here is that we return a locked page now, except when
we don't return a page at all (error cases). This removes the race
which required rechecking the page after it was returned.

Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
Cc: Nick Piggin <npiggin@kernel.dk>

diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 3b65f67..aa3a4dd 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -366,8 +366,15 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	unsigned int data_blocks, ind_blocks, rblocks;
 	struct gfs2_holder gh;
 	struct gfs2_alloc *al;
+	loff_t size;
 	int ret;
 
+	/* Wait if fs is frozen. This is racy so we check again later on
+	 * and retry if the fs has been frozen after the page lock has
+	 * been acquired
+	 */
+	vfs_check_frozen(inode->i_sb, SB_FREEZE_WRITE);
+
 	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
 	ret = gfs2_glock_nq(&gh);
 	if (ret)
@@ -376,8 +383,15 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	set_bit(GLF_DIRTY, &ip->i_gl->gl_flags);
 	set_bit(GIF_SW_PAGED, &ip->i_flags);
 
-	if (!gfs2_write_alloc_required(ip, pos, PAGE_CACHE_SIZE))
+	if (!gfs2_write_alloc_required(ip, pos, PAGE_CACHE_SIZE)) {
+		lock_page(page);
+		if (!PageUptodate(page) || page->mapping != inode->i_mapping) {
+			ret = -EAGAIN;
+			unlock_page(page);
+		}
 		goto out_unlock;
+	}
+
 	ret = -ENOMEM;
 	al = gfs2_alloc_get(ip);
 	if (al == NULL)
@@ -405,21 +419,29 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 
 	lock_page(page);
 	ret = -EINVAL;
-	last_index = ip->i_inode.i_size >> PAGE_CACHE_SHIFT;
-	if (page->index > last_index)
-		goto out_unlock_page;
+	size = i_size_read(inode);
+	last_index = (size - 1) >> PAGE_CACHE_SHIFT;
+	/* Check page index against inode size */
+	if (size == 0 || (page->index > last_index))
+		goto out_trans_end;
+
+	ret = -EAGAIN;
+	/* If truncated, we must retry the operation, we may have raced
+	 * with the glock demotion code.
+	 */
+	if (!PageUptodate(page) || page->mapping != inode->i_mapping)
+		goto out_trans_end;
+
+	/* Unstuff, if required, and allocate backing blocks for page */
 	ret = 0;
-	if (!PageUptodate(page) || page->mapping != ip->i_inode.i_mapping)
-		goto out_unlock_page;
-	if (gfs2_is_stuffed(ip)) {
+	if (gfs2_is_stuffed(ip))
 		ret = gfs2_unstuff_dinode(ip, page);
-		if (ret)
-			goto out_unlock_page;
-	}
-	ret = gfs2_allocate_page_backing(page);
+	if (ret == 0)
+		ret = gfs2_allocate_page_backing(page);
 
-out_unlock_page:
-	unlock_page(page);
+out_trans_end:
+	if (ret)
+		unlock_page(page);
 	gfs2_trans_end(sdp);
 out_trans_fail:
 	gfs2_inplace_release(ip);
@@ -431,11 +453,17 @@ out_unlock:
 	gfs2_glock_dq(&gh);
 out:
 	gfs2_holder_uninit(&gh);
-	if (ret == -ENOMEM)
-		ret = VM_FAULT_OOM;
-	else if (ret)
-		ret = VM_FAULT_SIGBUS;
-	return ret;
+	if (ret == 0) {
+		set_page_dirty(page);
+		/* This check must be post dropping of transaction lock */
+		if (inode->i_sb->s_frozen == SB_UNFROZEN) {
+			wait_on_page_writeback(page);
+		} else {
+			ret = -EAGAIN;
+			unlock_page(page);
+		}
+	}
+	return block_page_mkwrite_return(ret);
 }
 
 static const struct vm_operations_struct gfs2_vm_ops = {
-- 
1.7.4

[Cluster-devel] [PATCH 19/19] GFS2: Fix off-by-one in gfs2_blk2rgrpd

[Steven Whitehouse]

Bob reported:

I found an off-by-one problem with how I coded this section:
It should be:

+ else if (blk >= cur->rd_data0 + cur->rd_data)

In fact, cur->rd_data0 + cur->rd_data is the start of the next
rgrp (the next ri_addr), so without the "=" check it can land on
the wrong rgrp.

In all normal cases, this won't be a problem: you're searching
for a block _within_ the rgrp, which will pass the test properly.
Where it gets into trouble is if you search the rgrps for the
block exactly equal to ri_addr.  I don't think anything in the
kernel does this, but I found a place in gfs2-utils gfs2_edit
where it does.  So I definitely need to fix it in libgfs2.  I'd
like to suggest we fix it in the kernel as well for the sake of
keeping the functions similar.

So this patch fixes the above mentioned off by one error as well
as removing the unused parent pointer.

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

diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 8ec4174..1daf8a7 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -329,17 +329,16 @@ static inline int rgrp_contains_block(struct gfs2_rgrpd *rgd, u64 block)
 
 struct gfs2_rgrpd *gfs2_blk2rgrpd(struct gfs2_sbd *sdp, u64 blk)
 {
-	struct rb_node **newn, *parent = NULL;
+	struct rb_node **newn;
+	struct gfs2_rgrpd *cur;
 
 	spin_lock(&sdp->sd_rindex_spin);
 	newn = &sdp->sd_rindex_tree.rb_node;
 	while (*newn) {
-		struct gfs2_rgrpd *cur = rb_entry(*newn, struct gfs2_rgrpd,
-						  rd_node);
-		parent = *newn;
+		cur = rb_entry(*newn, struct gfs2_rgrpd, rd_node);
 		if (blk < cur->rd_addr)
 			newn = &((*newn)->rb_left);
-		else if (blk > cur->rd_data0 + cur->rd_data)
+		else if (blk >= cur->rd_data0 + cur->rd_data)
 			newn = &((*newn)->rb_right);
 		else {
 			spin_unlock(&sdp->sd_rindex_spin);
-- 
1.7.4