From 6469272c350872980891dbe38e81c936c43f2d9b Mon Sep 17 00:00:00 2001
From: Julia Lawall <julia@diku.dk>
Date: Wed, 26 May 2010 17:58:53 +0200
Subject: fs/ocfs2/dlm: Add missing spin_unlock

Add a spin_unlock missing on the error path.  Unlock as in the other code
that leads to the leave label.

The semantic match that finds this problem is as follows:
(http://coccinelle.lip6.fr/)

// <smpl>
@@
expression E1;
@@

* spin_lock(E1,...);
  <+... when != E1
  if (...) {
    ... when != E1
*   return ...;
  }
  ...+>
* spin_unlock(E1,...);
// </smpl>

Signed-off-by: Julia Lawall <julia@diku.dk>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
---
 fs/ocfs2/dlm/dlmdomain.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'fs/ocfs2')

diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 6b5a492e1749..2ccad86fb590 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -1709,6 +1709,7 @@ retry:
 		}
 
 		if (dlm_protocol_compare(&dlm->fs_locking_proto, fs_proto)) {
+			spin_unlock(&dlm_domain_lock);
 			mlog(ML_ERROR,
 			     "Requested locking protocol version is not "
 			     "compatible with already registered domain "
-- 
cgit v1.2.3


From 40f165f416bde747d85cdf71bc9dde700912f71f Mon Sep 17 00:00:00 2001
From: Tao Ma <tao.ma@oracle.com>
Date: Fri, 28 May 2010 14:22:59 +0800
Subject: ocfs2: Move orphan scan work to ocfs2_wq.

We used to let orphan scan work in the default work queue,
but there is a corner case which will make the system deadlock.
The scenario is like this:
1. set heartbeat threadshold to 200. this will allow us to have a
   great chance to have a orphan scan work before our quorum decision.
2. mount node 1.
3. after 1~2 minutes, mount node 2(in order to make the bug easier
   to reproduce, better add maxcpus=1 to kernel command line).
4. node 1 do orphan scan work.
5. node 2 do orphan scan work.
6. node 1 do orphan scan work. After this, node 1 hold the orphan scan
   lock while node 2 know node 1 is the master.
7. ifdown eth2 in node 2(eth2 is what we do ocfs2 interconnection).

Now when node 2 begins orphan scan, the system queue is blocked.

The root cause is that both orphan scan work and quorum decision work
will use the system event work queue. orphan scan has a chance of
blocking the event work queue(in dlm_wait_for_node_death) so that there
is no chance for quorum decision work to proceed.

This patch resolve it by moving orphan scan work to ocfs2_wq.

Signed-off-by: Tao Ma <tao.ma@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
---
 fs/ocfs2/journal.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'fs/ocfs2')

diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 47878cf16418..39113b5e79e7 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -1936,7 +1936,7 @@ void ocfs2_orphan_scan_work(struct work_struct *work)
 	mutex_lock(&os->os_lock);
 	ocfs2_queue_orphan_scan(osb);
 	if (atomic_read(&os->os_state) == ORPHAN_SCAN_ACTIVE)
-		schedule_delayed_work(&os->os_orphan_scan_work,
+		queue_delayed_work(ocfs2_wq, &os->os_orphan_scan_work,
 				      ocfs2_orphan_scan_timeout());
 	mutex_unlock(&os->os_lock);
 }
@@ -1976,8 +1976,8 @@ void ocfs2_orphan_scan_start(struct ocfs2_super *osb)
 		atomic_set(&os->os_state, ORPHAN_SCAN_INACTIVE);
 	else {
 		atomic_set(&os->os_state, ORPHAN_SCAN_ACTIVE);
-		schedule_delayed_work(&os->os_orphan_scan_work,
-				      ocfs2_orphan_scan_timeout());
+		queue_delayed_work(ocfs2_wq, &os->os_orphan_scan_work,
+				   ocfs2_orphan_scan_timeout());
 	}
 }
 
-- 
cgit v1.2.3


From 1739da40543ed2129050ccfa8a076a851ab6ed00 Mon Sep 17 00:00:00 2001
From: Tao Ma <tao.ma@oracle.com>
Date: Wed, 9 Jun 2010 16:43:05 +0800
Subject: ocfs2: Limit default local alloc size within bitmap range.

In commit 6b82021b9e91cd689fdffadbcdb9a42597bbe764, we increase
our local alloc size and calculate how much megabytes we can
get according to group size and volume size.
But we also need to check the maximum bits a local alloc block
bitmap can have. With a bs=512, cs=32K, local volume with 160G,
it calculate 96MB while the maximum local alloc size is only
76M. So the bitmap will overflow and corrupt the system truncate
log file. See bug
http://oss.oracle.com/bugzilla/show_bug.cgi?id=1262

Signed-off-by: Tao Ma <tao.ma@oracle.com>
Acked-by: Mark Fasheh <mfasheh@suse.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
---
 fs/ocfs2/localalloc.c | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'fs/ocfs2')

diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index 3d7419682dc0..ec6adbf8f551 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -118,6 +118,7 @@ unsigned int ocfs2_la_default_mb(struct ocfs2_super *osb)
 {
 	unsigned int la_mb;
 	unsigned int gd_mb;
+	unsigned int la_max_mb;
 	unsigned int megs_per_slot;
 	struct super_block *sb = osb->sb;
 
@@ -182,6 +183,12 @@ unsigned int ocfs2_la_default_mb(struct ocfs2_super *osb)
 	if (megs_per_slot < la_mb)
 		la_mb = megs_per_slot;
 
+	/* We can't store more bits than we can in a block. */
+	la_max_mb = ocfs2_clusters_to_megabytes(osb->sb,
+						ocfs2_local_alloc_size(sb) * 8);
+	if (la_mb > la_max_mb)
+		la_mb = la_max_mb;
+
 	return la_mb;
 }
 
-- 
cgit v1.2.3


From a4bfb4cf11fd2211b788af59dc8a8b4394bca227 Mon Sep 17 00:00:00 2001
From: Joel Becker <joel.becker@oracle.com>
Date: Tue, 6 Jul 2010 14:36:06 -0700
Subject: ocfs2: When zero extending, do it by page.

ocfs2_zero_extend() does its zeroing block by block, but it calls a
function named ocfs2_write_zero_page().  Let's have
ocfs2_write_zero_page() handle the page level.  From
ocfs2_zero_extend()'s perspective, it is now page-at-a-time.

Signed-off-by: Joel Becker <joel.becker@oracle.com>
Cc: stable@kernel.org
---
 fs/ocfs2/aops.c |  30 --------------
 fs/ocfs2/file.c | 118 ++++++++++++++++++++++++++++++++++++++++----------------
 2 files changed, 84 insertions(+), 64 deletions(-)

(limited to 'fs/ocfs2')

diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 3623ca20cc18..9a5c931439bd 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -459,36 +459,6 @@ int walk_page_buffers(	handle_t *handle,
 	return ret;
 }
 
-handle_t *ocfs2_start_walk_page_trans(struct inode *inode,
-							 struct page *page,
-							 unsigned from,
-							 unsigned to)
-{
-	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
-	handle_t *handle;
-	int ret = 0;
-
-	handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
-	if (IS_ERR(handle)) {
-		ret = -ENOMEM;
-		mlog_errno(ret);
-		goto out;
-	}
-
-	if (ocfs2_should_order_data(inode)) {
-		ret = ocfs2_jbd2_file_inode(handle, inode);
-		if (ret < 0)
-			mlog_errno(ret);
-	}
-out:
-	if (ret) {
-		if (!IS_ERR(handle))
-			ocfs2_commit_trans(osb, handle);
-		handle = ERR_PTR(ret);
-	}
-	return handle;
-}
-
 static sector_t ocfs2_bmap(struct address_space *mapping, sector_t block)
 {
 	sector_t status;
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 6a13ea64c447..4cfc976a9067 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -724,28 +724,55 @@ leave:
 	return status;
 }
 
+/*
+ * While a write will already be ordering the data, a truncate will not.
+ * Thus, we need to explicitly order the zeroed pages.
+ */
+static handle_t *ocfs2_zero_start_ordered_transaction(struct inode *inode)
+{
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	handle_t *handle = NULL;
+	int ret = 0;
+
+	if (!ocfs2_should_order_data(inode))
+		goto out;
+
+	handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
+	if (IS_ERR(handle)) {
+		ret = -ENOMEM;
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ret = ocfs2_jbd2_file_inode(handle, inode);
+	if (ret < 0)
+		mlog_errno(ret);
+
+out:
+	if (ret) {
+		if (!IS_ERR(handle))
+			ocfs2_commit_trans(osb, handle);
+		handle = ERR_PTR(ret);
+	}
+	return handle;
+}
+
 /* Some parts of this taken from generic_cont_expand, which turned out
  * to be too fragile to do exactly what we need without us having to
  * worry about recursive locking in ->write_begin() and ->write_end(). */
-static int ocfs2_write_zero_page(struct inode *inode,
-				 u64 size)
+static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
+				 u64 abs_to)
 {
 	struct address_space *mapping = inode->i_mapping;
 	struct page *page;
-	unsigned long index;
-	unsigned int offset;
+	unsigned long index = abs_from >> PAGE_CACHE_SHIFT;
 	handle_t *handle = NULL;
 	int ret;
+	unsigned zero_from, zero_to, block_start, block_end;
 
-	offset = (size & (PAGE_CACHE_SIZE-1)); /* Within page */
-	/* ugh.  in prepare/commit_write, if from==to==start of block, we
-	** skip the prepare.  make sure we never send an offset for the start
-	** of a block
-	*/
-	if ((offset & (inode->i_sb->s_blocksize - 1)) == 0) {
-		offset++;
-	}
-	index = size >> PAGE_CACHE_SHIFT;
+	BUG_ON(abs_from >= abs_to);
+	BUG_ON(abs_to > (((u64)index + 1) << PAGE_CACHE_SHIFT));
+	BUG_ON(abs_from & (inode->i_blkbits - 1));
 
 	page = grab_cache_page(mapping, index);
 	if (!page) {
@@ -754,31 +781,51 @@ static int ocfs2_write_zero_page(struct inode *inode,
 		goto out;
 	}
 
-	ret = ocfs2_prepare_write_nolock(inode, page, offset, offset);
-	if (ret < 0) {
-		mlog_errno(ret);
-		goto out_unlock;
-	}
+	/* Get the offsets within the page that we want to zero */
+	zero_from = abs_from & (PAGE_CACHE_SIZE - 1);
+	zero_to = abs_to & (PAGE_CACHE_SIZE - 1);
+	if (!zero_to)
+		zero_to = PAGE_CACHE_SIZE;
 
-	if (ocfs2_should_order_data(inode)) {
-		handle = ocfs2_start_walk_page_trans(inode, page, offset,
-						     offset);
-		if (IS_ERR(handle)) {
-			ret = PTR_ERR(handle);
-			handle = NULL;
+	/* We know that zero_from is block aligned */
+	for (block_start = zero_from; block_start < zero_to;
+	     block_start = block_end) {
+		block_end = block_start + (1 << inode->i_blkbits);
+
+		/*
+		 * block_start is block-aligned.  Bump it by one to
+		 * force ocfs2_{prepare,commit}_write() to zero the
+		 * whole block.
+		 */
+		ret = ocfs2_prepare_write_nolock(inode, page,
+						 block_start + 1,
+						 block_start + 1);
+		if (ret < 0) {
+			mlog_errno(ret);
 			goto out_unlock;
 		}
-	}
 
-	/* must not update i_size! */
-	ret = block_commit_write(page, offset, offset);
-	if (ret < 0)
-		mlog_errno(ret);
-	else
-		ret = 0;
+		if (!handle) {
+			handle = ocfs2_zero_start_ordered_transaction(inode);
+			if (IS_ERR(handle)) {
+				ret = PTR_ERR(handle);
+				handle = NULL;
+				break;
+			}
+		}
+
+		/* must not update i_size! */
+		ret = block_commit_write(page, block_start + 1,
+					 block_start + 1);
+		if (ret < 0)
+			mlog_errno(ret);
+		else
+			ret = 0;
+	}
 
 	if (handle)
 		ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
+
 out_unlock:
 	unlock_page(page);
 	page_cache_release(page);
@@ -790,18 +837,21 @@ static int ocfs2_zero_extend(struct inode *inode,
 			     u64 zero_to_size)
 {
 	int ret = 0;
-	u64 start_off;
+	u64 start_off, next_off;
 	struct super_block *sb = inode->i_sb;
 
 	start_off = ocfs2_align_bytes_to_blocks(sb, i_size_read(inode));
 	while (start_off < zero_to_size) {
-		ret = ocfs2_write_zero_page(inode, start_off);
+		next_off = (start_off & PAGE_CACHE_MASK) + PAGE_CACHE_SIZE;
+		if (next_off > zero_to_size)
+			next_off = zero_to_size;
+		ret = ocfs2_write_zero_page(inode, start_off, next_off);
 		if (ret < 0) {
 			mlog_errno(ret);
 			goto out;
 		}
 
-		start_off += sb->s_blocksize;
+		start_off = next_off;
 
 		/*
 		 * Very large extends have the potential to lock up
-- 
cgit v1.2.3


From 5693486bad2bc2ac585a2c24f7e2f3964b478df9 Mon Sep 17 00:00:00 2001
From: Joel Becker <joel.becker@oracle.com>
Date: Thu, 1 Jul 2010 15:13:31 -0700
Subject: ocfs2: Zero the tail cluster when extending past i_size.

ocfs2's allocation unit is the cluster.  This can be larger than a block
or even a memory page.  This means that a file may have many blocks in
its last extent that are beyond the block containing i_size.  There also
may be more unwritten extents after that.

When ocfs2 grows a file, it zeros the entire cluster in order to ensure
future i_size growth will see cleared blocks.  Unfortunately,
block_write_full_page() drops the pages past i_size.  This means that
ocfs2 is actually leaking garbage data into the tail end of that last
cluster.  This is a bug.

We adjust ocfs2_write_begin_nolock() and ocfs2_extend_file() to detect
when a write or truncate is past i_size.  They will use
ocfs2_zero_extend() to ensure the data is properly zeroed.

Older versions of ocfs2_zero_extend() simply zeroed every block between
i_size and the zeroing position.  This presumes three things:

1) There is allocation for all of these blocks.
2) The extents are not unwritten.
3) The extents are not refcounted.

(1) and (2) hold true for non-sparse filesystems, which used to be the
only users of ocfs2_zero_extend().  (3) is another bug.

Since we're now using ocfs2_zero_extend() for sparse filesystems as
well, we teach ocfs2_zero_extend() to check every extent between
i_size and the zeroing position.  If the extent is unwritten, it is
ignored.  If it is refcounted, it is CoWed.  Then it is zeroed.

Signed-off-by: Joel Becker <joel.becker@oracle.com>
Cc: stable@kernel.org
---
 fs/ocfs2/aops.c         |  42 ++++++----
 fs/ocfs2/file.c         | 201 +++++++++++++++++++++++++++++++++++++++---------
 fs/ocfs2/file.h         |   6 +-
 fs/ocfs2/quota_global.c |   2 +-
 fs/ocfs2/quota_local.c  |   4 +-
 fs/ocfs2/refcounttree.c |   6 ++
 6 files changed, 207 insertions(+), 54 deletions(-)

(limited to 'fs/ocfs2')

diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 9a5c931439bd..742893ea7390 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -196,15 +196,14 @@ int ocfs2_get_block(struct inode *inode, sector_t iblock,
 			dump_stack();
 			goto bail;
 		}
-
-		past_eof = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode));
-		mlog(0, "Inode %lu, past_eof = %llu\n", inode->i_ino,
-		     (unsigned long long)past_eof);
-
-		if (create && (iblock >= past_eof))
-			set_buffer_new(bh_result);
 	}
 
+	past_eof = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode));
+	mlog(0, "Inode %lu, past_eof = %llu\n", inode->i_ino,
+	     (unsigned long long)past_eof);
+	if (create && (iblock >= past_eof))
+		set_buffer_new(bh_result);
+
 bail:
 	if (err < 0)
 		err = -EIO;
@@ -1590,21 +1589,20 @@ out:
  * write path can treat it as an non-allocating write, which has no
  * special case code for sparse/nonsparse files.
  */
-static int ocfs2_expand_nonsparse_inode(struct inode *inode, loff_t pos,
-					unsigned len,
+static int ocfs2_expand_nonsparse_inode(struct inode *inode,
+					struct buffer_head *di_bh,
+					loff_t pos, unsigned len,
 					struct ocfs2_write_ctxt *wc)
 {
 	int ret;
-	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	loff_t newsize = pos + len;
 
-	if (ocfs2_sparse_alloc(osb))
-		return 0;
+	BUG_ON(ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)));
 
 	if (newsize <= i_size_read(inode))
 		return 0;
 
-	ret = ocfs2_extend_no_holes(inode, newsize, pos);
+	ret = ocfs2_extend_no_holes(inode, di_bh, newsize, pos);
 	if (ret)
 		mlog_errno(ret);
 
@@ -1614,6 +1612,18 @@ static int ocfs2_expand_nonsparse_inode(struct inode *inode, loff_t pos,
 	return ret;
 }
 
+static int ocfs2_zero_tail(struct inode *inode, struct buffer_head *di_bh,
+			   loff_t pos)
+{
+	int ret = 0;
+
+	BUG_ON(!ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)));
+	if (pos > i_size_read(inode))
+		ret = ocfs2_zero_extend(inode, di_bh, pos);
+
+	return ret;
+}
+
 int ocfs2_write_begin_nolock(struct address_space *mapping,
 			     loff_t pos, unsigned len, unsigned flags,
 			     struct page **pagep, void **fsdata,
@@ -1649,7 +1659,11 @@ int ocfs2_write_begin_nolock(struct address_space *mapping,
 		}
 	}
 
-	ret = ocfs2_expand_nonsparse_inode(inode, pos, len, wc);
+	if (ocfs2_sparse_alloc(osb))
+		ret = ocfs2_zero_tail(inode, di_bh, pos);
+	else
+		ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos, len,
+						   wc);
 	if (ret) {
 		mlog_errno(ret);
 		goto out;
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 4cfc976a9067..ac15911b31c4 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -787,6 +787,11 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
 	if (!zero_to)
 		zero_to = PAGE_CACHE_SIZE;
 
+	mlog(0,
+	     "abs_from = %llu, abs_to = %llu, index = %lu, zero_from = %u, zero_to = %u\n",
+	     (unsigned long long)abs_from, (unsigned long long)abs_to,
+	     index, zero_from, zero_to);
+
 	/* We know that zero_from is block aligned */
 	for (block_start = zero_from; block_start < zero_to;
 	     block_start = block_end) {
@@ -833,25 +838,114 @@ out:
 	return ret;
 }
 
-static int ocfs2_zero_extend(struct inode *inode,
-			     u64 zero_to_size)
+/*
+ * Find the next range to zero.  We do this in terms of bytes because
+ * that's what ocfs2_zero_extend() wants, and it is dealing with the
+ * pagecache.  We may return multiple extents.
+ *
+ * zero_start and zero_end are ocfs2_zero_extend()s current idea of what
+ * needs to be zeroed.  range_start and range_end return the next zeroing
+ * range.  A subsequent call should pass the previous range_end as its
+ * zero_start.  If range_end is 0, there's nothing to do.
+ *
+ * Unwritten extents are skipped over.  Refcounted extents are CoWd.
+ */
+static int ocfs2_zero_extend_get_range(struct inode *inode,
+				       struct buffer_head *di_bh,
+				       u64 zero_start, u64 zero_end,
+				       u64 *range_start, u64 *range_end)
 {
-	int ret = 0;
-	u64 start_off, next_off;
-	struct super_block *sb = inode->i_sb;
+	int rc = 0, needs_cow = 0;
+	u32 p_cpos, zero_clusters = 0;
+	u32 zero_cpos =
+		zero_start >> OCFS2_SB(inode->i_sb)->s_clustersize_bits;
+	u32 last_cpos = ocfs2_clusters_for_bytes(inode->i_sb, zero_end);
+	unsigned int num_clusters = 0;
+	unsigned int ext_flags = 0;
 
-	start_off = ocfs2_align_bytes_to_blocks(sb, i_size_read(inode));
-	while (start_off < zero_to_size) {
-		next_off = (start_off & PAGE_CACHE_MASK) + PAGE_CACHE_SIZE;
-		if (next_off > zero_to_size)
-			next_off = zero_to_size;
-		ret = ocfs2_write_zero_page(inode, start_off, next_off);
-		if (ret < 0) {
-			mlog_errno(ret);
+	while (zero_cpos < last_cpos) {
+		rc = ocfs2_get_clusters(inode, zero_cpos, &p_cpos,
+					&num_clusters, &ext_flags);
+		if (rc) {
+			mlog_errno(rc);
+			goto out;
+		}
+
+		if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN)) {
+			zero_clusters = num_clusters;
+			if (ext_flags & OCFS2_EXT_REFCOUNTED)
+				needs_cow = 1;
+			break;
+		}
+
+		zero_cpos += num_clusters;
+	}
+	if (!zero_clusters) {
+		*range_end = 0;
+		goto out;
+	}
+
+	while ((zero_cpos + zero_clusters) < last_cpos) {
+		rc = ocfs2_get_clusters(inode, zero_cpos + zero_clusters,
+					&p_cpos, &num_clusters,
+					&ext_flags);
+		if (rc) {
+			mlog_errno(rc);
+			goto out;
+		}
+
+		if (!p_cpos || (ext_flags & OCFS2_EXT_UNWRITTEN))
+			break;
+		if (ext_flags & OCFS2_EXT_REFCOUNTED)
+			needs_cow = 1;
+		zero_clusters += num_clusters;
+	}
+	if ((zero_cpos + zero_clusters) > last_cpos)
+		zero_clusters = last_cpos - zero_cpos;
+
+	if (needs_cow) {
+		rc = ocfs2_refcount_cow(inode, di_bh, zero_cpos, zero_clusters,
+					UINT_MAX);
+		if (rc) {
+			mlog_errno(rc);
 			goto out;
 		}
+	}
 
-		start_off = next_off;
+	*range_start = ocfs2_clusters_to_bytes(inode->i_sb, zero_cpos);
+	*range_end = ocfs2_clusters_to_bytes(inode->i_sb,
+					     zero_cpos + zero_clusters);
+
+out:
+	return rc;
+}
+
+/*
+ * Zero one range returned from ocfs2_zero_extend_get_range().  The caller
+ * has made sure that the entire range needs zeroing.
+ */
+static int ocfs2_zero_extend_range(struct inode *inode, u64 range_start,
+				   u64 range_end)
+{
+	int rc = 0;
+	u64 next_pos;
+	u64 zero_pos = range_start;
+
+	mlog(0, "range_start = %llu, range_end = %llu\n",
+	     (unsigned long long)range_start,
+	     (unsigned long long)range_end);
+	BUG_ON(range_start >= range_end);
+
+	while (zero_pos < range_end) {
+		next_pos = (zero_pos & PAGE_CACHE_MASK) + PAGE_CACHE_SIZE;
+		if (next_pos > range_end)
+			next_pos = range_end;
+		rc = ocfs2_write_zero_page(inode, zero_pos, next_pos);
+		if (rc < 0) {
+			mlog_errno(rc);
+			break;
+		}
+		zero_pos = next_pos;
 
 		/*
 		 * Very large extends have the potential to lock up
@@ -860,16 +954,63 @@ static int ocfs2_zero_extend(struct inode *inode,
 		cond_resched();
 	}
 
-out:
+	return rc;
+}
+
+int ocfs2_zero_extend(struct inode *inode, struct buffer_head *di_bh,
+		      loff_t zero_to_size)
+{
+	int ret = 0;
+	u64 zero_start, range_start = 0, range_end = 0;
+	struct super_block *sb = inode->i_sb;
+
+	zero_start = ocfs2_align_bytes_to_blocks(sb, i_size_read(inode));
+	mlog(0, "zero_start %llu for i_size %llu\n",
+	     (unsigned long long)zero_start,
+	     (unsigned long long)i_size_read(inode));
+	while (zero_start < zero_to_size) {
+		ret = ocfs2_zero_extend_get_range(inode, di_bh, zero_start,
+						  zero_to_size,
+						  &range_start,
+						  &range_end);
+		if (ret) {
+			mlog_errno(ret);
+			break;
+		}
+		if (!range_end)
+			break;
+		/* Trim the ends */
+		if (range_start < zero_start)
+			range_start = zero_start;
+		if (range_end > zero_to_size)
+			range_end = zero_to_size;
+
+		ret = ocfs2_zero_extend_range(inode, range_start,
+					      range_end);
+		if (ret) {
+			mlog_errno(ret);
+			break;
+		}
+		zero_start = range_end;
+	}
+
 	return ret;
 }
 
-int ocfs2_extend_no_holes(struct inode *inode, u64 new_i_size, u64 zero_to)
+int ocfs2_extend_no_holes(struct inode *inode, struct buffer_head *di_bh,
+			  u64 new_i_size, u64 zero_to)
 {
 	int ret;
 	u32 clusters_to_add;
 	struct ocfs2_inode_info *oi = OCFS2_I(inode);
 
+	/*
+	 * Only quota files call this without a bh, and they can't be
+	 * refcounted.
+	 */
+	BUG_ON(!di_bh && (oi->ip_dyn_features & OCFS2_HAS_REFCOUNT_FL));
+	BUG_ON(!di_bh && !(oi->ip_flags & OCFS2_INODE_SYSTEM_FILE));
+
 	clusters_to_add = ocfs2_clusters_for_bytes(inode->i_sb, new_i_size);
 	if (clusters_to_add < oi->ip_clusters)
 		clusters_to_add = 0;
@@ -890,7 +1031,7 @@ int ocfs2_extend_no_holes(struct inode *inode, u64 new_i_size, u64 zero_to)
 	 * still need to zero the area between the old i_size and the
 	 * new i_size.
 	 */
-	ret = ocfs2_zero_extend(inode, zero_to);
+	ret = ocfs2_zero_extend(inode, di_bh, zero_to);
 	if (ret < 0)
 		mlog_errno(ret);
 
@@ -912,27 +1053,15 @@ static int ocfs2_extend_file(struct inode *inode,
 		goto out;
 
 	if (i_size_read(inode) == new_i_size)
-  		goto out;
+		goto out;
 	BUG_ON(new_i_size < i_size_read(inode));
 
-	/*
-	 * Fall through for converting inline data, even if the fs
-	 * supports sparse files.
-	 *
-	 * The check for inline data here is legal - nobody can add
-	 * the feature since we have i_mutex. We must check it again
-	 * after acquiring ip_alloc_sem though, as paths like mmap
-	 * might have raced us to converting the inode to extents.
-	 */
-	if (!(oi->ip_dyn_features & OCFS2_INLINE_DATA_FL)
-	    && ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)))
-		goto out_update_size;
-
 	/*
 	 * The alloc sem blocks people in read/write from reading our
 	 * allocation until we're done changing it. We depend on
 	 * i_mutex to block other extend/truncate calls while we're
-	 * here.
+	 * here.  We even have to hold it for sparse files because there
+	 * might be some tail zeroing.
 	 */
 	down_write(&oi->ip_alloc_sem);
 
@@ -949,14 +1078,16 @@ static int ocfs2_extend_file(struct inode *inode,
 		ret = ocfs2_convert_inline_data_to_extents(inode, di_bh);
 		if (ret) {
 			up_write(&oi->ip_alloc_sem);
-
 			mlog_errno(ret);
 			goto out;
 		}
 	}
 
-	if (!ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)))
-		ret = ocfs2_extend_no_holes(inode, new_i_size, new_i_size);
+	if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)))
+		ret = ocfs2_zero_extend(inode, di_bh, new_i_size);
+	else
+		ret = ocfs2_extend_no_holes(inode, di_bh, new_i_size,
+					    new_i_size);
 
 	up_write(&oi->ip_alloc_sem);
 
diff --git a/fs/ocfs2/file.h b/fs/ocfs2/file.h
index d66cf4f7c70e..97bf761c9e7c 100644
--- a/fs/ocfs2/file.h
+++ b/fs/ocfs2/file.h
@@ -54,8 +54,10 @@ int ocfs2_add_inode_data(struct ocfs2_super *osb,
 int ocfs2_simple_size_update(struct inode *inode,
 			     struct buffer_head *di_bh,
 			     u64 new_i_size);
-int ocfs2_extend_no_holes(struct inode *inode, u64 new_i_size,
-			  u64 zero_to);
+int ocfs2_extend_no_holes(struct inode *inode, struct buffer_head *di_bh,
+			  u64 new_i_size, u64 zero_to);
+int ocfs2_zero_extend(struct inode *inode, struct buffer_head *di_bh,
+		      loff_t zero_to);
 int ocfs2_setattr(struct dentry *dentry, struct iattr *attr);
 int ocfs2_getattr(struct vfsmount *mnt, struct dentry *dentry,
 		  struct kstat *stat);
diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c
index 2bb35fe00511..4607923eb24c 100644
--- a/fs/ocfs2/quota_global.c
+++ b/fs/ocfs2/quota_global.c
@@ -775,7 +775,7 @@ static int ocfs2_acquire_dquot(struct dquot *dquot)
 		 * locking allocators ranks above a transaction start
 		 */
 		WARN_ON(journal_current_handle());
-		status = ocfs2_extend_no_holes(gqinode,
+		status = ocfs2_extend_no_holes(gqinode, NULL,
 			gqinode->i_size + (need_alloc << sb->s_blocksize_bits),
 			gqinode->i_size);
 		if (status < 0)
diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index 8bd70d4d184d..dc78764ccc4c 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -971,7 +971,7 @@ static struct ocfs2_quota_chunk *ocfs2_local_quota_add_chunk(
 	u64 p_blkno;
 
 	/* We are protected by dqio_sem so no locking needed */
-	status = ocfs2_extend_no_holes(lqinode,
+	status = ocfs2_extend_no_holes(lqinode, NULL,
 				       lqinode->i_size + 2 * sb->s_blocksize,
 				       lqinode->i_size);
 	if (status < 0) {
@@ -1114,7 +1114,7 @@ static struct ocfs2_quota_chunk *ocfs2_extend_local_quota_file(
 		return ocfs2_local_quota_add_chunk(sb, type, offset);
 
 	/* We are protected by dqio_sem so no locking needed */
-	status = ocfs2_extend_no_holes(lqinode,
+	status = ocfs2_extend_no_holes(lqinode, NULL,
 				       lqinode->i_size + sb->s_blocksize,
 				       lqinode->i_size);
 	if (status < 0) {
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 4793f36f6518..32949df10694 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -4166,6 +4166,12 @@ static int __ocfs2_reflink(struct dentry *old_dentry,
 	struct inode *inode = old_dentry->d_inode;
 	struct buffer_head *new_bh = NULL;
 
+	if (OCFS2_I(inode)->ip_flags & OCFS2_INODE_SYSTEM_FILE) {
+		ret = -EINVAL;
+		mlog_errno(ret);
+		goto out;
+	}
+
 	ret = filemap_fdatawrite(inode->i_mapping);
 	if (ret) {
 		mlog_errno(ret);
-- 
cgit v1.2.3


From 693c241a5f6aa01417f5f4caf9f82e60e316398d Mon Sep 17 00:00:00 2001
From: Joel Becker <joel.becker@oracle.com>
Date: Fri, 2 Jul 2010 17:20:27 -0700
Subject: ocfs2: No need to zero pages past i_size.

When ocfs2 fills a hole, it does so by allocating clusters.  When a
cluster is larger than the write, ocfs2 must zero the portions of the
cluster outside of the write.  If the clustersize is smaller than a
pagecache page, this is handled by the normal pagecache mechanisms, but
when the clustersize is larger than a page, ocfs2's write code will zero
the pages adjacent to the write.  This makes sure the entire cluster is
zeroed correctly.

Currently ocfs2 behaves exactly the same when writing past i_size.
However, this means ocfs2 is writing zeroed pages for portions of a new
cluster that are beyond i_size.  The page writeback code isn't expecting
this.  It treats all pages past the one containing i_size as left behind
due to a previous truncate operation.

Thankfully, ocfs2 calculates the number of pages it will be working on
up front.  The rest of the write code merely honors the original
calculation.  We can simply trim the number of pages to only cover the
actual file data.

Signed-off-by: Joel Becker <joel.becker@oracle.com>
Cc: stable@kernel.org
---
 fs/ocfs2/aops.c | 22 ++++++++++++++++++----
 1 file changed, 18 insertions(+), 4 deletions(-)

(limited to 'fs/ocfs2')

diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 742893ea7390..356e976772bf 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -1100,23 +1100,37 @@ out:
  */
 static int ocfs2_grab_pages_for_write(struct address_space *mapping,
 				      struct ocfs2_write_ctxt *wc,
-				      u32 cpos, loff_t user_pos, int new,
+				      u32 cpos, loff_t user_pos,
+				      unsigned user_len, int new,
 				      struct page *mmap_page)
 {
 	int ret = 0, i;
-	unsigned long start, target_index, index;
+	unsigned long start, target_index, end_index, index;
 	struct inode *inode = mapping->host;
+	loff_t last_byte;
 
 	target_index = user_pos >> PAGE_CACHE_SHIFT;
 
 	/*
 	 * Figure out how many pages we'll be manipulating here. For
 	 * non allocating write, we just change the one
-	 * page. Otherwise, we'll need a whole clusters worth.
+	 * page. Otherwise, we'll need a whole clusters worth.  If we're
+	 * writing past i_size, we only need enough pages to cover the
+	 * last page of the write.
 	 */
 	if (new) {
 		wc->w_num_pages = ocfs2_pages_per_cluster(inode->i_sb);
 		start = ocfs2_align_clusters_to_page_index(inode->i_sb, cpos);
+		/*
+		 * We need the index *past* the last page we could possibly
+		 * touch.  This is the page past the end of the write or
+		 * i_size, whichever is greater.
+		 */
+		last_byte = max(user_pos + user_len, i_size_read(inode));
+		BUG_ON(last_byte < 1);
+		end_index = ((last_byte - 1) >> PAGE_CACHE_SHIFT) + 1;
+		if ((start + wc->w_num_pages) > end_index)
+			wc->w_num_pages = end_index - start;
 	} else {
 		wc->w_num_pages = 1;
 		start = target_index;
@@ -1773,7 +1787,7 @@ int ocfs2_write_begin_nolock(struct address_space *mapping,
 	 * that we can zero and flush if we error after adding the
 	 * extent.
 	 */
-	ret = ocfs2_grab_pages_for_write(mapping, wc, wc->w_cpos, pos,
+	ret = ocfs2_grab_pages_for_write(mapping, wc, wc->w_cpos, pos, len,
 					 cluster_of_pages, mmap_page);
 	if (ret) {
 		mlog_errno(ret);
-- 
cgit v1.2.3


From f471c9df922a80ca9af1d9a490b4aab3f990ec19 Mon Sep 17 00:00:00 2001
From: Wengang Wang <wen.gang.wang@oracle.com>
Date: Wed, 30 Jun 2010 20:23:30 +0800
Subject: ocfs2/dlm: don't access beyond bitmap size

dlm->recovery_map is defined as
	unsigned long recovery_map[BITS_TO_LONGS(O2NM_MAX_NODES)];

We should treat O2NM_MAX_NODES as the bit map size in bits.
This patches fixes a bit operation that takes O2NM_MAX_NODES + 1 as bitmap size.

Signed-off-by: Wengang Wang <wen.gang.wang@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
---
 fs/ocfs2/dlm/dlmrecovery.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'fs/ocfs2')

diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index f8b75ce4be70..9dfaac73b36d 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -463,7 +463,7 @@ static int dlm_do_recovery(struct dlm_ctxt *dlm)
 	if (dlm->reco.dead_node == O2NM_INVALID_NODE_NUM) {
 		int bit;
 
-		bit = find_next_bit (dlm->recovery_map, O2NM_MAX_NODES+1, 0);
+		bit = find_next_bit (dlm->recovery_map, O2NM_MAX_NODES, 0);
 		if (bit >= O2NM_MAX_NODES || bit < 0)
 			dlm_set_reco_dead_node(dlm, O2NM_INVALID_NODE_NUM);
 		else
-- 
cgit v1.2.3


From 0a463b74e7e6856b24e613de2b85237c6e11890b Mon Sep 17 00:00:00 2001
From: Tao Ma <tao.ma@oracle.com>
Date: Thu, 8 Jul 2010 11:11:11 +0800
Subject: ocfs2: Remove the redundant cpu_to_le64.

In ocfs2_block_group_alloc, we set c_blkno by bg->bg_blkno.
But actually bg->bg_blkno is already changed to little endian
in ocfs2_block_group_fill. So remove the extra cpu_to_le64.

Reported-by: Marcos Matsunaga <Marcos.Matsunaga@oracle.com>
Signed-off-by: Tao Ma <tao.ma@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
---
 fs/ocfs2/suballoc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'fs/ocfs2')

diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index f4c2a9eb8c4d..a8e6a95a353f 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -741,7 +741,7 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb,
 		     le16_to_cpu(bg->bg_free_bits_count));
 	le32_add_cpu(&cl->cl_recs[alloc_rec].c_total,
 		     le16_to_cpu(bg->bg_bits));
-	cl->cl_recs[alloc_rec].c_blkno  = cpu_to_le64(bg->bg_blkno);
+	cl->cl_recs[alloc_rec].c_blkno = bg->bg_blkno;
 	if (le16_to_cpu(cl->cl_next_free_rec) < le16_to_cpu(cl->cl_count))
 		le16_add_cpu(&cl->cl_next_free_rec, 1);
 
-- 
cgit v1.2.3


From a78f9f4668949a6588b8872f162e86685c63d023 Mon Sep 17 00:00:00 2001
From: Tao Ma <tao.ma@oracle.com>
Date: Fri, 9 Jul 2010 14:53:11 +0800
Subject: ocfs2: make xattr extension work with new local alloc reservation.

The old ocfs2_xattr_extent_allocation is too optimistic about
the clusters we can get. So actually if the file system is
too fragmented, ocfs2_add_clusters_in_btree will return us
with EGAIN and we need to allocate clusters once again.

So this patch change it to a while loop so that we can allocate
clusters until we reach clusters_to_add.

Signed-off-by: Tao Ma <tao.ma@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
Cc: stable@kernel.org
---
 fs/ocfs2/xattr.c | 74 ++++++++++++++++++++++++++++++++++----------------------
 1 file changed, 45 insertions(+), 29 deletions(-)

(limited to 'fs/ocfs2')

diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index e97b34842cfe..2be19083713f 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -709,7 +709,7 @@ static int ocfs2_xattr_extend_allocation(struct inode *inode,
 					 struct ocfs2_xattr_value_buf *vb,
 					 struct ocfs2_xattr_set_ctxt *ctxt)
 {
-	int status = 0;
+	int status = 0, credits;
 	handle_t *handle = ctxt->handle;
 	enum ocfs2_alloc_restarted why;
 	u32 prev_clusters, logical_start = le32_to_cpu(vb->vb_xv->xr_clusters);
@@ -719,38 +719,54 @@ static int ocfs2_xattr_extend_allocation(struct inode *inode,
 
 	ocfs2_init_xattr_value_extent_tree(&et, INODE_CACHE(inode), vb);
 
-	status = vb->vb_access(handle, INODE_CACHE(inode), vb->vb_bh,
-			      OCFS2_JOURNAL_ACCESS_WRITE);
-	if (status < 0) {
-		mlog_errno(status);
-		goto leave;
-	}
+	while (clusters_to_add) {
+		status = vb->vb_access(handle, INODE_CACHE(inode), vb->vb_bh,
+				       OCFS2_JOURNAL_ACCESS_WRITE);
+		if (status < 0) {
+			mlog_errno(status);
+			break;
+		}
 
-	prev_clusters = le32_to_cpu(vb->vb_xv->xr_clusters);
-	status = ocfs2_add_clusters_in_btree(handle,
-					     &et,
-					     &logical_start,
-					     clusters_to_add,
-					     0,
-					     ctxt->data_ac,
-					     ctxt->meta_ac,
-					     &why);
-	if (status < 0) {
-		mlog_errno(status);
-		goto leave;
-	}
+		prev_clusters = le32_to_cpu(vb->vb_xv->xr_clusters);
+		status = ocfs2_add_clusters_in_btree(handle,
+						     &et,
+						     &logical_start,
+						     clusters_to_add,
+						     0,
+						     ctxt->data_ac,
+						     ctxt->meta_ac,
+						     &why);
+		if ((status < 0) && (status != -EAGAIN)) {
+			if (status != -ENOSPC)
+				mlog_errno(status);
+			break;
+		}
 
-	ocfs2_journal_dirty(handle, vb->vb_bh);
+		ocfs2_journal_dirty(handle, vb->vb_bh);
 
-	clusters_to_add -= le32_to_cpu(vb->vb_xv->xr_clusters) - prev_clusters;
+		clusters_to_add -= le32_to_cpu(vb->vb_xv->xr_clusters) -
+					 prev_clusters;
 
-	/*
-	 * We should have already allocated enough space before the transaction,
-	 * so no need to restart.
-	 */
-	BUG_ON(why != RESTART_NONE || clusters_to_add);
-
-leave:
+		if (why != RESTART_NONE && clusters_to_add) {
+			/*
+			 * We can only fail in case the alloc file doesn't give
+			 * up enough clusters.
+			 */
+			BUG_ON(why == RESTART_META);
+
+			mlog(0, "restarting xattr value extension for %u"
+			     " clusters,.\n", clusters_to_add);
+			credits = ocfs2_calc_extend_credits(inode->i_sb,
+							    &vb->vb_xv->xr_list,
+							    clusters_to_add);
+			status = ocfs2_extend_trans(handle, credits);
+			if (status < 0) {
+				status = -ENOMEM;
+				mlog_errno(status);
+				break;
+			}
+		}
+	}
 
 	return status;
 }
-- 
cgit v1.2.3


From 121a39bb00b421211f4f590c440a8f636d3ae807 Mon Sep 17 00:00:00 2001
From: Tao Ma <tao.ma@oracle.com>
Date: Fri, 9 Jul 2010 14:53:12 +0800
Subject: ocfs2: Make xattr reflink work with new local alloc reservation.

The new reservation code in local alloc has add the limitation
that the caller should handle the case that the local alloc
doesn't give use enough contiguous clusters. It make the old
xattr reflink code broken.

So this patch udpate the xattr reflink code so that it can
handle the case that local alloc give us one cluster at a time.

Signed-off-by: Tao Ma <tao.ma@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
---
 fs/ocfs2/xattr.c | 126 +++++++++++++++++++++++++++++++++++++++----------------
 1 file changed, 90 insertions(+), 36 deletions(-)

(limited to 'fs/ocfs2')

diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index 2be19083713f..d03469f61801 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -6804,16 +6804,15 @@ out:
 	return ret;
 }
 
-static int ocfs2_reflink_xattr_buckets(handle_t *handle,
+static int ocfs2_reflink_xattr_bucket(handle_t *handle,
 				u64 blkno, u64 new_blkno, u32 clusters,
+				u32 *cpos, int num_buckets,
 				struct ocfs2_alloc_context *meta_ac,
 				struct ocfs2_alloc_context *data_ac,
 				struct ocfs2_reflink_xattr_tree_args *args)
 {
 	int i, j, ret = 0;
 	struct super_block *sb = args->reflink->old_inode->i_sb;
-	u32 bpc = ocfs2_xattr_buckets_per_cluster(OCFS2_SB(sb));
-	u32 num_buckets = clusters * bpc;
 	int bpb = args->old_bucket->bu_blocks;
 	struct ocfs2_xattr_value_buf vb = {
 		.vb_access = ocfs2_journal_access,
@@ -6832,14 +6831,6 @@ static int ocfs2_reflink_xattr_buckets(handle_t *handle,
 			break;
 		}
 
-		/*
-		 * The real bucket num in this series of blocks is stored
-		 * in the 1st bucket.
-		 */
-		if (i == 0)
-			num_buckets = le16_to_cpu(
-				bucket_xh(args->old_bucket)->xh_num_buckets);
-
 		ret = ocfs2_xattr_bucket_journal_access(handle,
 						args->new_bucket,
 						OCFS2_JOURNAL_ACCESS_CREATE);
@@ -6853,6 +6844,18 @@ static int ocfs2_reflink_xattr_buckets(handle_t *handle,
 			       bucket_block(args->old_bucket, j),
 			       sb->s_blocksize);
 
+		/*
+		 * Record the start cpos so that we can use it to initialize
+		 * our xattr tree we also set the xh_num_bucket for the new
+		 * bucket.
+		 */
+		if (i == 0) {
+			*cpos = le32_to_cpu(bucket_xh(args->new_bucket)->
+					    xh_entries[0].xe_name_hash);
+			bucket_xh(args->new_bucket)->xh_num_buckets =
+				cpu_to_le16(num_buckets);
+		}
+
 		ocfs2_xattr_bucket_journal_dirty(handle, args->new_bucket);
 
 		ret = ocfs2_reflink_xattr_header(handle, args->reflink,
@@ -6882,6 +6885,7 @@ static int ocfs2_reflink_xattr_buckets(handle_t *handle,
 		}
 
 		ocfs2_xattr_bucket_journal_dirty(handle, args->new_bucket);
+
 		ocfs2_xattr_bucket_relse(args->old_bucket);
 		ocfs2_xattr_bucket_relse(args->new_bucket);
 	}
@@ -6890,6 +6894,75 @@ static int ocfs2_reflink_xattr_buckets(handle_t *handle,
 	ocfs2_xattr_bucket_relse(args->new_bucket);
 	return ret;
 }
+
+static int ocfs2_reflink_xattr_buckets(handle_t *handle,
+				struct inode *inode,
+				struct ocfs2_reflink_xattr_tree_args *args,
+				struct ocfs2_extent_tree *et,
+				struct ocfs2_alloc_context *meta_ac,
+				struct ocfs2_alloc_context *data_ac,
+				u64 blkno, u32 cpos, u32 len)
+{
+	int ret, first_inserted = 0;
+	u32 p_cluster, num_clusters, reflink_cpos = 0;
+	u64 new_blkno;
+	unsigned int num_buckets, reflink_buckets;
+	unsigned int bpc =
+		ocfs2_xattr_buckets_per_cluster(OCFS2_SB(inode->i_sb));
+
+	ret = ocfs2_read_xattr_bucket(args->old_bucket, blkno);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+	num_buckets = le16_to_cpu(bucket_xh(args->old_bucket)->xh_num_buckets);
+	ocfs2_xattr_bucket_relse(args->old_bucket);
+
+	while (len && num_buckets) {
+		ret = ocfs2_claim_clusters(handle, data_ac,
+					   1, &p_cluster, &num_clusters);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
+		new_blkno = ocfs2_clusters_to_blocks(inode->i_sb, p_cluster);
+		reflink_buckets = min(num_buckets, bpc * num_clusters);
+
+		ret = ocfs2_reflink_xattr_bucket(handle, blkno,
+						 new_blkno, num_clusters,
+						 &reflink_cpos, reflink_buckets,
+						 meta_ac, data_ac, args);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
+		/*
+		 * For the 1st allocated cluster, we make it use the same cpos
+		 * so that the xattr tree looks the same as the original one
+		 * in the most case.
+		 */
+		if (!first_inserted) {
+			reflink_cpos = cpos;
+			first_inserted = 1;
+		}
+		ret = ocfs2_insert_extent(handle, et, reflink_cpos, new_blkno,
+					  num_clusters, 0, meta_ac);
+		if (ret)
+			mlog_errno(ret);
+
+		mlog(0, "insert new xattr extent rec start %llu len %u to %u\n",
+		     (unsigned long long)new_blkno, num_clusters, reflink_cpos);
+
+		len -= num_clusters;
+		blkno += ocfs2_clusters_to_blocks(inode->i_sb, num_clusters);
+		num_buckets -= reflink_buckets;
+	}
+out:
+	return ret;
+}
+
 /*
  * Create the same xattr extent record in the new inode's xattr tree.
  */
@@ -6901,8 +6974,6 @@ static int ocfs2_reflink_xattr_rec(struct inode *inode,
 				   void *para)
 {
 	int ret, credits = 0;
-	u32 p_cluster, num_clusters;
-	u64 new_blkno;
 	handle_t *handle;
 	struct ocfs2_reflink_xattr_tree_args *args =
 			(struct ocfs2_reflink_xattr_tree_args *)para;
@@ -6911,6 +6982,9 @@ static int ocfs2_reflink_xattr_rec(struct inode *inode,
 	struct ocfs2_alloc_context *data_ac = NULL;
 	struct ocfs2_extent_tree et;
 
+	mlog(0, "reflink xattr buckets %llu len %u\n",
+	     (unsigned long long)blkno, len);
+
 	ocfs2_init_xattr_tree_extent_tree(&et,
 					  INODE_CACHE(args->reflink->new_inode),
 					  args->new_blk_bh);
@@ -6930,32 +7004,12 @@ static int ocfs2_reflink_xattr_rec(struct inode *inode,
 		goto out;
 	}
 
-	ret = ocfs2_claim_clusters(handle, data_ac,
-				   len, &p_cluster, &num_clusters);
-	if (ret) {
-		mlog_errno(ret);
-		goto out_commit;
-	}
-
-	new_blkno = ocfs2_clusters_to_blocks(osb->sb, p_cluster);
-
-	mlog(0, "reflink xattr buckets %llu to %llu, len %u\n",
-	     (unsigned long long)blkno, (unsigned long long)new_blkno, len);
-	ret = ocfs2_reflink_xattr_buckets(handle, blkno, new_blkno, len,
-					  meta_ac, data_ac, args);
-	if (ret) {
-		mlog_errno(ret);
-		goto out_commit;
-	}
-
-	mlog(0, "insert new xattr extent rec start %llu len %u to %u\n",
-	     (unsigned long long)new_blkno, len, cpos);
-	ret = ocfs2_insert_extent(handle, &et, cpos, new_blkno,
-				  len, 0, meta_ac);
+	ret = ocfs2_reflink_xattr_buckets(handle, inode, args, &et,
+					  meta_ac, data_ac,
+					  blkno, cpos, len);
 	if (ret)
 		mlog_errno(ret);
 
-out_commit:
 	ocfs2_commit_trans(osb, handle);
 
 out:
-- 
cgit v1.2.3


From e372357ba55ae89307af15cd680467d8f0db4f01 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <error27@gmail.com>
Date: Sat, 10 Jul 2010 16:33:36 +0200
Subject: ocfs2: tighten up strlen() checking

This function is only called from one place and it's like this:
	dlm_register_domain(conn->cc_name, dlm_key, &fs_version);

The "conn->cc_name" is 64 characters long.  If strlen(conn->cc_name)
were equal to O2NM_MAX_NAME_LEN (64) that would be a bug because
strlen() doesn't count the NULL character.

In fact, if you look how O2NM_MAX_NAME_LEN is used, it mostly describes
64 character buffers.  The only exception is nd_name from struct
o2nm_node.

Anyway I looked into it and in this case the domain string comes from
osb->uuid_str in ocfs2_setup_osb_uuid().  That's 32 characters and NULL
which easily fits into O2NM_MAX_NAME_LEN.  This patch doesn't change how
the code works, but I think it makes the code a little cleaner.

Signed-off-by: Dan Carpenter <error27@gmail.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
---
 fs/ocfs2/dlm/dlmdomain.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'fs/ocfs2')

diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 2ccad86fb590..153abb5abef0 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -1671,7 +1671,7 @@ struct dlm_ctxt * dlm_register_domain(const char *domain,
 	struct dlm_ctxt *dlm = NULL;
 	struct dlm_ctxt *new_ctxt = NULL;
 
-	if (strlen(domain) > O2NM_MAX_NAME_LEN) {
+	if (strlen(domain) >= O2NM_MAX_NAME_LEN) {
 		ret = -ENAMETOOLONG;
 		mlog(ML_ERROR, "domain name length too long\n");
 		goto leave;
-- 
cgit v1.2.3


From f5e27b6ddfbafdd9c9c2f06bbf28af12581409bc Mon Sep 17 00:00:00 2001
From: Tao Ma <tao.ma@oracle.com>
Date: Wed, 14 Jul 2010 11:19:32 +0800
Subject: ocfs2: Don't duplicate pages past i_size during CoW.

During CoW, the pages after i_size don't contain valid data, so there's
no need to read and duplicate them.

Signed-off-by: Tao Ma <tao.ma@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
---
 fs/ocfs2/refcounttree.c | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'fs/ocfs2')

diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 32949df10694..3ac5aa733e9c 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -2931,6 +2931,12 @@ static int ocfs2_duplicate_clusters_by_page(handle_t *handle,
 
 	offset = ((loff_t)cpos) << OCFS2_SB(sb)->s_clustersize_bits;
 	end = offset + (new_len << OCFS2_SB(sb)->s_clustersize_bits);
+	/*
+	 * We only duplicate pages until we reach the page contains i_size - 1.
+	 * So trim 'end' to i_size.
+	 */
+	if (end > i_size_read(context->inode))
+		end = i_size_read(context->inode);
 
 	while (offset < end) {
 		page_index = offset >> PAGE_CACHE_SHIFT;
-- 
cgit v1.2.3


From a39953dd95ff10e311083d94f4f95c348cb22464 Mon Sep 17 00:00:00 2001
From: Wengang Wang <wen.gang.wang@oracle.com>
Date: Wed, 14 Jul 2010 22:38:21 +0800
Subject: ocfs2/dlm: Remove BUG_ON from migration in the rare case of a down
 node

For migration, we are waiting for DLM_LOCK_RES_MIGRATING flag to be set
before sending DLM_MIG_LOCKRES_MSG message to the target. We are using
dlm_migration_can_proceed() for that purpose.  However, if the node is
down, dlm_migration_can_proceed() will also return "go ahead".  In this
rare case, the DLM_LOCK_RES_MIGRATING flag might not be set yet. Remove
the BUG_ON() that trips over this condition.

Signed-off-by: Wengang Wang <wen.gang.wang@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
---
 fs/ocfs2/dlm/dlmmaster.c | 22 ++++++++++++++--------
 1 file changed, 14 insertions(+), 8 deletions(-)

(limited to 'fs/ocfs2')

diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 4a7506a4e314..94b97fc6a88e 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -2808,14 +2808,8 @@ again:
 		mlog(0, "trying again...\n");
 		goto again;
 	}
-	/* now that we are sure the MIGRATING state is there, drop
-	 * the unneded state which blocked threads trying to DIRTY */
-	spin_lock(&res->spinlock);
-	BUG_ON(!(res->state & DLM_LOCK_RES_BLOCK_DIRTY));
-	BUG_ON(!(res->state & DLM_LOCK_RES_MIGRATING));
-	res->state &= ~DLM_LOCK_RES_BLOCK_DIRTY;
-	spin_unlock(&res->spinlock);
 
+	ret = 0;
 	/* did the target go down or die? */
 	spin_lock(&dlm->spinlock);
 	if (!test_bit(target, dlm->domain_map)) {
@@ -2825,10 +2819,22 @@ again:
 	}
 	spin_unlock(&dlm->spinlock);
 
+	/*
+	 * if target is down, we need to clear DLM_LOCK_RES_BLOCK_DIRTY for
+	 * another try; otherwise, we are sure the MIGRATING state is there,
+	 * drop the unneded state which blocked threads trying to DIRTY
+	 */
+	spin_lock(&res->spinlock);
+	BUG_ON(!(res->state & DLM_LOCK_RES_BLOCK_DIRTY));
+	res->state &= ~DLM_LOCK_RES_BLOCK_DIRTY;
+	if (!ret)
+		BUG_ON(!(res->state & DLM_LOCK_RES_MIGRATING));
+	spin_unlock(&res->spinlock);
+
 	/*
 	 * at this point:
 	 *
-	 *   o the DLM_LOCK_RES_MIGRATING flag is set
+	 *   o the DLM_LOCK_RES_MIGRATING flag is set if target not down
 	 *   o there are no pending asts on this lockres
 	 *   o all processes trying to reserve an ast on this
 	 *     lockres must wait for the MIGRATING flag to clear
-- 
cgit v1.2.3


From 13ceef099edd2b70c5a6f3a9ef5d6d97cda2e096 Mon Sep 17 00:00:00 2001
From: Jan Kara <jack@suse.cz>
Date: Wed, 14 Jul 2010 07:56:33 +0200
Subject: jbd2/ocfs2: Fix block checksumming when a buffer is used in several
 transactions

OCFS2 uses t_commit trigger to compute and store checksum of the just
committed blocks. When a buffer has b_frozen_data, checksum is computed
for it instead of b_data but this can result in an old checksum being
written to the filesystem in the following scenario:

1) transaction1 is opened
2) handle1 is opened
3) journal_access(handle1, bh)
    - This sets jh->b_transaction to transaction1
4) modify(bh)
5) journal_dirty(handle1, bh)
6) handle1 is closed
7) start committing transaction1, opening transaction2
8) handle2 is opened
9) journal_access(handle2, bh)
    - This copies off b_frozen_data to make it safe for transaction1 to commit.
      jh->b_next_transaction is set to transaction2.
10) jbd2_journal_write_metadata() checksums b_frozen_data
11) the journal correctly writes b_frozen_data to the disk journal
12) handle2 is closed
    - There was no dirty call for the bh on handle2, so it is never queued for
      any more journal operation
13) Checkpointing finally happens, and it just spools the bh via normal buffer
writeback.  This will write b_data, which was never triggered on and thus
contains a wrong (old) checksum.

This patch fixes the problem by calling the trigger at the moment data is
frozen for journal commit - i.e., either when b_frozen_data is created by
do_get_write_access or just before we write a buffer to the log if
b_frozen_data does not exist. We also rename the trigger to t_frozen as
that better describes when it is called.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>
---
 fs/ocfs2/journal.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

(limited to 'fs/ocfs2')

diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 39113b5e79e7..625de9d7088c 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -472,7 +472,7 @@ static inline struct ocfs2_triggers *to_ocfs2_trigger(struct jbd2_buffer_trigger
 	return container_of(triggers, struct ocfs2_triggers, ot_triggers);
 }
 
-static void ocfs2_commit_trigger(struct jbd2_buffer_trigger_type *triggers,
+static void ocfs2_frozen_trigger(struct jbd2_buffer_trigger_type *triggers,
 				 struct buffer_head *bh,
 				 void *data, size_t size)
 {
@@ -491,7 +491,7 @@ static void ocfs2_commit_trigger(struct jbd2_buffer_trigger_type *triggers,
  * Quota blocks have their own trigger because the struct ocfs2_block_check
  * offset depends on the blocksize.
  */
-static void ocfs2_dq_commit_trigger(struct jbd2_buffer_trigger_type *triggers,
+static void ocfs2_dq_frozen_trigger(struct jbd2_buffer_trigger_type *triggers,
 				 struct buffer_head *bh,
 				 void *data, size_t size)
 {
@@ -511,7 +511,7 @@ static void ocfs2_dq_commit_trigger(struct jbd2_buffer_trigger_type *triggers,
  * Directory blocks also have their own trigger because the
  * struct ocfs2_block_check offset depends on the blocksize.
  */
-static void ocfs2_db_commit_trigger(struct jbd2_buffer_trigger_type *triggers,
+static void ocfs2_db_frozen_trigger(struct jbd2_buffer_trigger_type *triggers,
 				 struct buffer_head *bh,
 				 void *data, size_t size)
 {
@@ -544,7 +544,7 @@ static void ocfs2_abort_trigger(struct jbd2_buffer_trigger_type *triggers,
 
 static struct ocfs2_triggers di_triggers = {
 	.ot_triggers = {
-		.t_commit = ocfs2_commit_trigger,
+		.t_frozen = ocfs2_frozen_trigger,
 		.t_abort = ocfs2_abort_trigger,
 	},
 	.ot_offset	= offsetof(struct ocfs2_dinode, i_check),
@@ -552,7 +552,7 @@ static struct ocfs2_triggers di_triggers = {
 
 static struct ocfs2_triggers eb_triggers = {
 	.ot_triggers = {
-		.t_commit = ocfs2_commit_trigger,
+		.t_frozen = ocfs2_frozen_trigger,
 		.t_abort = ocfs2_abort_trigger,
 	},
 	.ot_offset	= offsetof(struct ocfs2_extent_block, h_check),
@@ -560,7 +560,7 @@ static struct ocfs2_triggers eb_triggers = {
 
 static struct ocfs2_triggers rb_triggers = {
 	.ot_triggers = {
-		.t_commit = ocfs2_commit_trigger,
+		.t_frozen = ocfs2_frozen_trigger,
 		.t_abort = ocfs2_abort_trigger,
 	},
 	.ot_offset	= offsetof(struct ocfs2_refcount_block, rf_check),
@@ -568,7 +568,7 @@ static struct ocfs2_triggers rb_triggers = {
 
 static struct ocfs2_triggers gd_triggers = {
 	.ot_triggers = {
-		.t_commit = ocfs2_commit_trigger,
+		.t_frozen = ocfs2_frozen_trigger,
 		.t_abort = ocfs2_abort_trigger,
 	},
 	.ot_offset	= offsetof(struct ocfs2_group_desc, bg_check),
@@ -576,14 +576,14 @@ static struct ocfs2_triggers gd_triggers = {
 
 static struct ocfs2_triggers db_triggers = {
 	.ot_triggers = {
-		.t_commit = ocfs2_db_commit_trigger,
+		.t_frozen = ocfs2_db_frozen_trigger,
 		.t_abort = ocfs2_abort_trigger,
 	},
 };
 
 static struct ocfs2_triggers xb_triggers = {
 	.ot_triggers = {
-		.t_commit = ocfs2_commit_trigger,
+		.t_frozen = ocfs2_frozen_trigger,
 		.t_abort = ocfs2_abort_trigger,
 	},
 	.ot_offset	= offsetof(struct ocfs2_xattr_block, xb_check),
@@ -591,14 +591,14 @@ static struct ocfs2_triggers xb_triggers = {
 
 static struct ocfs2_triggers dq_triggers = {
 	.ot_triggers = {
-		.t_commit = ocfs2_dq_commit_trigger,
+		.t_frozen = ocfs2_dq_frozen_trigger,
 		.t_abort = ocfs2_abort_trigger,
 	},
 };
 
 static struct ocfs2_triggers dr_triggers = {
 	.ot_triggers = {
-		.t_commit = ocfs2_commit_trigger,
+		.t_frozen = ocfs2_frozen_trigger,
 		.t_abort = ocfs2_abort_trigger,
 	},
 	.ot_offset	= offsetof(struct ocfs2_dx_root_block, dr_check),
@@ -606,7 +606,7 @@ static struct ocfs2_triggers dr_triggers = {
 
 static struct ocfs2_triggers dl_triggers = {
 	.ot_triggers = {
-		.t_commit = ocfs2_commit_trigger,
+		.t_frozen = ocfs2_frozen_trigger,
 		.t_abort = ocfs2_abort_trigger,
 	},
 	.ot_offset	= offsetof(struct ocfs2_dx_leaf, dl_check),
-- 
cgit v1.2.3


From 5453258d532e72731b0829e4fefd36dd611a2fff Mon Sep 17 00:00:00 2001
From: Joel Becker <joel.becker@oracle.com>
Date: Fri, 16 Jul 2010 13:32:33 -0700
Subject: ocfs2: Silence gcc warning in ocfs2_write_zero_page().

ocfs2_write_zero_page() has a loop that won't ever be skipped, but gcc
doesn't know that.  Set ret=0 just to make gcc happy.

Signed-off-by: Joel Becker <joel.becker@oracle.com>
---
 fs/ocfs2/file.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'fs/ocfs2')

diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index ac15911b31c4..2b10b36d1577 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -767,7 +767,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
 	struct page *page;
 	unsigned long index = abs_from >> PAGE_CACHE_SHIFT;
 	handle_t *handle = NULL;
-	int ret;
+	int ret = 0;
 	unsigned zero_from, zero_to, block_start, block_end;
 
 	BUG_ON(abs_from >= abs_to);
-- 
cgit v1.2.3