diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index 345a4b1..675879b 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -640,8 +640,8 @@
 	/* Skip cs, ip, orig_ax and gs. */	\
 	"	subl $16, %esp\n"	\
 	"	pushl %fs\n"		\
-	"	pushl %ds\n"		\
 	"	pushl %es\n"		\
+	"	pushl %ds\n"		\
 	"	pushl %eax\n"		\
 	"	pushl %ebp\n"		\
 	"	pushl %edi\n"		\
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 6fdb3ec..5525309 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -184,6 +184,7 @@
 					idx, r, disabled, pass);
 				if (pci_claim_resource(dev, idx) < 0) {
 					/* We'll assign a new address later */
+					dev->fw_addr[idx] = r->start;
 					r->end -= r->start;
 					r->start = 0;
 				}
diff --git a/crypto/ablkcipher.c b/crypto/ablkcipher.c
index 98a6610..a854df2a 100644
--- a/crypto/ablkcipher.c
+++ b/crypto/ablkcipher.c
@@ -165,7 +165,7 @@
 
 	p = kmalloc(n, GFP_ATOMIC);
 	if (!p)
-		ablkcipher_walk_done(req, walk, -ENOMEM);
+		return ablkcipher_walk_done(req, walk, -ENOMEM);
 
 	base = p + 1;
 
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 0743858..8757ecf 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2241,6 +2241,7 @@
 		page = read_cache_page_gfp(mapping, i,
 					   GFP_HIGHUSER |
 					   __GFP_COLD |
+					   __GFP_RECLAIMABLE |
 					   gfpmask);
 		if (IS_ERR(page))
 			goto err_pages;
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 40cea33..9ba9c4a 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -206,6 +206,7 @@
 	unsigned char max[3];
 
 	if (SYN_ID_MAJOR(priv->identity) < 4)
+		return 0;
 
 	if (synaptics_send_cmd(psmouse, SYN_QUE_RESOLUTION, res) == 0) {
 		if (res[0] != 0 && (res[1] & 0x80) && res[2] != 0) {
diff --git a/drivers/input/touchscreen/w90p910_ts.c b/drivers/input/touchscreen/w90p910_ts.c
index cc18265b..7a45d68 100644
--- a/drivers/input/touchscreen/w90p910_ts.c
+++ b/drivers/input/touchscreen/w90p910_ts.c
@@ -233,7 +233,7 @@
 	w90p910_ts->state = TS_IDLE;
 	spin_lock_init(&w90p910_ts->lock);
 	setup_timer(&w90p910_ts->timer, w90p910_check_pen_up,
-		    (unsigned long)&w90p910_ts);
+		    (unsigned long)w90p910_ts);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res) {
diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c
index 92379e2..2aaa131 100644
--- a/drivers/pci/setup-res.c
+++ b/drivers/pci/setup-res.c
@@ -156,6 +156,38 @@
 					     pcibios_align_resource, dev);
 	}
 
+	if (ret < 0 && dev->fw_addr[resno]) {
+		struct resource *root, *conflict;
+		resource_size_t start, end;
+
+		/*
+		 * If we failed to assign anything, let's try the address
+		 * where firmware left it.  That at least has a chance of
+		 * working, which is better than just leaving it disabled.
+		 */
+
+		if (res->flags & IORESOURCE_IO)
+			root = &ioport_resource;
+		else
+			root = &iomem_resource;
+
+		start = res->start;
+		end = res->end;
+		res->start = dev->fw_addr[resno];
+		res->end = res->start + size - 1;
+		dev_info(&dev->dev, "BAR %d: trying firmware assignment %pR\n",
+			 resno, res);
+		conflict = request_resource_conflict(root, res);
+		if (conflict) {
+			dev_info(&dev->dev,
+				 "BAR %d: %pR conflicts with %s %pR\n", resno,
+				 res, conflict->name, conflict);
+			res->start = start;
+			res->end = end;
+		} else
+			ret = 0;
+	}
+
 	if (!ret) {
 		res->flags &= ~IORESOURCE_STARTALIGN;
 		dev_info(&dev->dev, "BAR %d: assigned %pR\n", resno, res);
diff --git a/drivers/platform/x86/intel_scu_ipc.c b/drivers/platform/x86/intel_scu_ipc.c
index 40658e3..bb2f1fba 100644
--- a/drivers/platform/x86/intel_scu_ipc.c
+++ b/drivers/platform/x86/intel_scu_ipc.c
@@ -489,7 +489,7 @@
 		mutex_unlock(&ipclock);
 		return -ENODEV;
 	}
-	ipc_command(cmd << 12 | sub);
+	ipc_command(sub << 12 | cmd);
 	err = busy_loop();
 	mutex_unlock(&ipclock);
 	return err;
@@ -501,9 +501,9 @@
  *	@cmd: command
  *	@sub: sub type
  *	@in: input data
- *	@inlen: input length
+ *	@inlen: input length in dwords
  *	@out: output data
- *	@outlein: output length
+ *	@outlein: output length in dwords
  *
  *	Issue a command to the SCU which involves data transfers. Do the
  *	data copies under the lock but leave it for the caller to interpret
@@ -524,7 +524,7 @@
 	for (i = 0; i < inlen; i++)
 		ipc_data_writel(*in++, 4 * i);
 
-	ipc_command((cmd << 12) | sub | (inlen << 18));
+	ipc_command((sub << 12) | cmd | (inlen << 18));
 	err = busy_loop();
 
 	for (i = 0; i < outlen; i++)
@@ -556,6 +556,10 @@
 	u32 cmd = 0;
 
 	mutex_lock(&ipclock);
+	if (ipcdev.pdev == NULL) {
+		mutex_unlock(&ipclock);
+		return -ENODEV;
+	}
 	cmd = (addr >> 24) & 0xFF;
 	if (cmd == IPC_I2C_READ) {
 		writel(addr, ipcdev.i2c_base + IPC_I2C_CNTRL_ADDR);
diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c
index 34d51dd..bed7b46 100644
--- a/drivers/s390/block/dasd_devmap.c
+++ b/drivers/s390/block/dasd_devmap.c
@@ -948,8 +948,10 @@
 	if (device->discipline && device->discipline->get_uid &&
 	    !device->discipline->get_uid(device, &uid)) {
 		if (uid.type == UA_BASE_PAV_ALIAS ||
-		    uid.type == UA_HYPER_PAV_ALIAS)
+		    uid.type == UA_HYPER_PAV_ALIAS) {
+			dasd_put_device(device);
 			return sprintf(buf, "1\n");
+		}
 	}
 	dasd_put_device(device);
 
diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c
index ce7cb87..407d0e9 100644
--- a/drivers/s390/cio/chsc.c
+++ b/drivers/s390/cio/chsc.c
@@ -713,7 +713,7 @@
 	ret = chsc_determine_channel_path_desc(chpid, 0, 0, 0, 0, chsc_resp);
 	if (ret)
 		goto out_free;
-	memcpy(desc, &chsc_resp->data, chsc_resp->length);
+	memcpy(desc, &chsc_resp->data, sizeof(*desc));
 out_free:
 	kfree(chsc_resp);
 	return ret;
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 4a48c0f..84da64b 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -1041,6 +1041,7 @@
 
 	if (gfs2_is_stuffed(ip)) {
 		u64 dsize = size + sizeof(struct gfs2_inode);
+		ip->i_disksize = size;
 		ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
 		gfs2_trans_add_bh(ip->i_gl, dibh, 1);
 		gfs2_dinode_out(ip, dibh->b_data);
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index 8295c5b..26ca336 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -392,7 +392,7 @@
 	unsigned totlen = be16_to_cpu(dent->de_rec_len);
 
 	if (gfs2_dirent_sentinel(dent))
-		actual = GFS2_DIRENT_SIZE(0);
+		actual = 0;
 	if (totlen - actual >= required)
 		return 1;
 	return 0;
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index ddcdbf4..dbab3fd 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -706,8 +706,18 @@
 {
 	unsigned long delay = 0;
 	struct gfs2_glock *gl = container_of(work, struct gfs2_glock, gl_work.work);
+	struct gfs2_holder *gh;
 	int drop_ref = 0;
 
+	if (unlikely(test_bit(GLF_FROZEN, &gl->gl_flags))) {
+		spin_lock(&gl->gl_spin);
+		gh = find_first_waiter(gl);
+		if (gh && (gh->gh_flags & LM_FLAG_NOEXP) &&
+		    test_and_clear_bit(GLF_FROZEN, &gl->gl_flags))
+			set_bit(GLF_REPLY_PENDING, &gl->gl_flags);
+		spin_unlock(&gl->gl_spin);
+	}
+
 	if (test_and_clear_bit(GLF_REPLY_PENDING, &gl->gl_flags)) {
 		finish_xmote(gl, gl->gl_reply);
 		drop_ref = 1;
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index b5612cb..f03afd9 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -169,7 +169,7 @@
 {
 	struct inode *inode;
 	struct gfs2_inode *ip;
-	struct gfs2_glock *io_gl;
+	struct gfs2_glock *io_gl = NULL;
 	int error;
 
 	inode = gfs2_iget(sb, no_addr);
@@ -198,6 +198,7 @@
 		ip->i_iopen_gh.gh_gl->gl_object = ip;
 
 		gfs2_glock_put(io_gl);
+		io_gl = NULL;
 
 		if ((type == DT_UNKNOWN) && (no_formal_ino == 0))
 			goto gfs2_nfsbypass;
@@ -228,7 +229,8 @@
 fail_glock:
 	gfs2_glock_dq(&ip->i_iopen_gh);
 fail_iopen:
-	gfs2_glock_put(io_gl);
+	if (io_gl)
+		gfs2_glock_put(io_gl);
 fail_put:
 	if (inode->i_state & I_NEW)
 		ip->i_gl->gl_object = NULL;
@@ -256,7 +258,7 @@
 {
 	struct gfs2_sbd *sdp;
 	struct gfs2_inode *ip;
-	struct gfs2_glock *io_gl;
+	struct gfs2_glock *io_gl = NULL;
 	int error;
 	struct gfs2_holder gh;
 	struct inode *inode;
@@ -293,6 +295,7 @@
 
 	ip->i_iopen_gh.gh_gl->gl_object = ip;
 	gfs2_glock_put(io_gl);
+	io_gl = NULL;
 
 	inode->i_mode = DT2IF(DT_UNKNOWN);
 
@@ -319,7 +322,8 @@
 fail_glock:
 	gfs2_glock_dq(&ip->i_iopen_gh);
 fail_iopen:
-	gfs2_glock_put(io_gl);
+	if (io_gl)
+		gfs2_glock_put(io_gl);
 fail_put:
 	ip->i_gl->gl_object = NULL;
 	gfs2_glock_put(ip->i_gl);
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 49667d6..b256d6f 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -694,10 +694,8 @@
 		if (!buffer_mapped(bh))
 			goto unlock_out;
 		/* If it's a newly allocated disk block for quota, zero it */
-		if (buffer_new(bh)) {
-			memset(bh->b_data, 0, bh->b_size);
-			set_buffer_uptodate(bh);
-		}
+		if (buffer_new(bh))
+			zero_user(page, pos - blocksize, bh->b_size);
 	}
 
 	if (PageUptodate(page))
@@ -723,7 +721,7 @@
 
 	/* If quota straddles page boundary, we need to update the rest of the
 	 * quota at the beginning of the next page */
-	if (offset != 0) { /* first page, offset is closer to PAGE_CACHE_SIZE */
+	if ((offset + sizeof(struct gfs2_quota)) > PAGE_CACHE_SIZE) {
 		ptr = ptr + nbytes;
 		nbytes = sizeof(struct gfs2_quota) - nbytes;
 		offset = 0;
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index bc2ff59..0368808 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -297,7 +297,6 @@
 	struct page *new_page;
 	unsigned int new_offset;
 	struct buffer_head *bh_in = jh2bh(jh_in);
-	struct jbd2_buffer_trigger_type *triggers;
 	journal_t *journal = transaction->t_journal;
 
 	/*
@@ -328,21 +327,21 @@
 		done_copy_out = 1;
 		new_page = virt_to_page(jh_in->b_frozen_data);
 		new_offset = offset_in_page(jh_in->b_frozen_data);
-		triggers = jh_in->b_frozen_triggers;
 	} else {
 		new_page = jh2bh(jh_in)->b_page;
 		new_offset = offset_in_page(jh2bh(jh_in)->b_data);
-		triggers = jh_in->b_triggers;
 	}
 
 	mapped_data = kmap_atomic(new_page, KM_USER0);
 	/*
-	 * Fire any commit trigger.  Do this before checking for escaping,
-	 * as the trigger may modify the magic offset.  If a copy-out
-	 * happens afterwards, it will have the correct data in the buffer.
+	 * Fire data frozen trigger if data already wasn't frozen.  Do this
+	 * before checking for escaping, as the trigger may modify the magic
+	 * offset.  If a copy-out happens afterwards, it will have the correct
+	 * data in the buffer.
 	 */
-	jbd2_buffer_commit_trigger(jh_in, mapped_data + new_offset,
-				   triggers);
+	if (!done_copy_out)
+		jbd2_buffer_frozen_trigger(jh_in, mapped_data + new_offset,
+					   jh_in->b_triggers);
 
 	/*
 	 * Check for escaping
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index e214d68..b8e0806 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -725,6 +725,9 @@
 		page = jh2bh(jh)->b_page;
 		offset = ((unsigned long) jh2bh(jh)->b_data) & ~PAGE_MASK;
 		source = kmap_atomic(page, KM_USER0);
+		/* Fire data frozen trigger just before we copy the data */
+		jbd2_buffer_frozen_trigger(jh, source + offset,
+					   jh->b_triggers);
 		memcpy(jh->b_frozen_data, source+offset, jh2bh(jh)->b_size);
 		kunmap_atomic(source, KM_USER0);
 
@@ -963,15 +966,15 @@
 	jh->b_triggers = type;
 }
 
-void jbd2_buffer_commit_trigger(struct journal_head *jh, void *mapped_data,
+void jbd2_buffer_frozen_trigger(struct journal_head *jh, void *mapped_data,
 				struct jbd2_buffer_trigger_type *triggers)
 {
 	struct buffer_head *bh = jh2bh(jh);
 
-	if (!triggers || !triggers->t_commit)
+	if (!triggers || !triggers->t_frozen)
 		return;
 
-	triggers->t_commit(triggers, bh, mapped_data, bh->b_size);
+	triggers->t_frozen(triggers, bh, mapped_data, bh->b_size);
 }
 
 void jbd2_buffer_abort_trigger(struct journal_head *jh,
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 3623ca2..356e976 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -196,15 +196,14 @@
 			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;
@@ -459,36 +458,6 @@
 	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;
@@ -1131,23 +1100,37 @@
  */
 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;
@@ -1620,21 +1603,20 @@
  * 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);
 
@@ -1644,6 +1626,18 @@
 	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,
@@ -1679,7 +1673,11 @@
 		}
 	}
 
-	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;
@@ -1789,7 +1787,7 @@
 	 * 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);
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 6b5a492..153abb5 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -1671,7 +1671,7 @@
 	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;
@@ -1709,6 +1709,7 @@
 		}
 
 		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 "
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 4a7506a..94b97fc 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -2808,14 +2808,8 @@
 		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)) {
@@ -2826,9 +2820,21 @@
 	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
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index f8b75ce..9dfaac7 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -463,7 +463,7 @@
 	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
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 6a13ea6..2b10b36 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -724,28 +724,55 @@
 	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;
+	int ret = 0;
+	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 +781,56 @@
 		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;
+	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) {
+		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);
@@ -786,22 +838,114 @@
 	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;
-	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) {
-		ret = ocfs2_write_zero_page(inode, start_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;
 		}
 
-		start_off += sb->s_blocksize;
+		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;
+		}
+	}
+
+	*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
@@ -810,16 +954,63 @@
 		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;
@@ -840,7 +1031,7 @@
 	 * 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);
 
@@ -862,27 +1053,15 @@
 		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);
 
@@ -899,14 +1078,16 @@
 		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 d66cf4f..97bf761 100644
--- a/fs/ocfs2/file.h
+++ b/fs/ocfs2/file.h
@@ -54,8 +54,10 @@
 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/journal.c b/fs/ocfs2/journal.c
index 47878cf..625de9d 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -472,7 +472,7 @@
 	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 @@
  * 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 @@
  * 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 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 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 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 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 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 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 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),
@@ -1936,7 +1936,7 @@
 	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 @@
 		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());
 	}
 }
 
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index 3d74196..ec6adbf 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -118,6 +118,7 @@
 {
 	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 @@
 	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;
 }
 
diff --git a/fs/ocfs2/quota_global.c b/fs/ocfs2/quota_global.c
index 2bb35fe..4607923 100644
--- a/fs/ocfs2/quota_global.c
+++ b/fs/ocfs2/quota_global.c
@@ -775,7 +775,7 @@
 		 * 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 8bd70d4..dc78764 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -971,7 +971,7 @@
 	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 @@
 		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 4793f36..3ac5aa7 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -2931,6 +2931,12 @@
 
 	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;
@@ -4166,6 +4172,12 @@
 	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);
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index f4c2a9e..a8e6a95 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -741,7 +741,7 @@
 		     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);
 
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index e97b348..d03469f 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -709,7 +709,7 @@
 					 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);
@@ -719,39 +719,55 @@
 
 	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) && (status != -EAGAIN)) {
+			if (status != -ENOSPC)
+				mlog_errno(status);
+			break;
+		}
+
+		ocfs2_journal_dirty(handle, vb->vb_bh);
+
+		clusters_to_add -= le32_to_cpu(vb->vb_xv->xr_clusters) -
+					 prev_clusters;
+
+		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;
+			}
+		}
 	}
 
-	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;
-	}
-
-	ocfs2_journal_dirty(handle, vb->vb_bh);
-
-	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:
-
 	return status;
 }
 
@@ -6788,16 +6804,15 @@
 	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,
@@ -6816,14 +6831,6 @@
 			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);
@@ -6837,6 +6844,18 @@
 			       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,
@@ -6866,6 +6885,7 @@
 		}
 
 		ocfs2_xattr_bucket_journal_dirty(handle, args->new_bucket);
+
 		ocfs2_xattr_bucket_relse(args->old_bucket);
 		ocfs2_xattr_bucket_relse(args->new_bucket);
 	}
@@ -6874,6 +6894,75 @@
 	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.
  */
@@ -6885,8 +6974,6 @@
 				   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;
@@ -6895,6 +6982,9 @@
 	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);
@@ -6914,32 +7004,12 @@
 		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:
diff --git a/fs/partitions/ibm.c b/fs/partitions/ibm.c
index 3e73de5..fc84976 100644
--- a/fs/partitions/ibm.c
+++ b/fs/partitions/ibm.c
@@ -74,6 +74,7 @@
 	} *label;
 	unsigned char *data;
 	Sector sect;
+	sector_t labelsect;
 
 	res = 0;
 	blocksize = bdev_logical_block_size(bdev);
@@ -98,10 +99,19 @@
 		goto out_freeall;
 
 	/*
+	 * Special case for FBA disks: label sector does not depend on
+	 * blocksize.
+	 */
+	if ((info->cu_type == 0x6310 && info->dev_type == 0x9336) ||
+	    (info->cu_type == 0x3880 && info->dev_type == 0x3370))
+		labelsect = info->label_block;
+	else
+		labelsect = info->label_block * (blocksize >> 9);
+
+	/*
 	 * Get volume label, extract name and type.
 	 */
-	data = read_part_sector(state, info->label_block*(blocksize/512),
-				&sect);
+	data = read_part_sector(state, labelsect, &sect);
 	if (data == NULL)
 		goto out_readerr;
 
diff --git a/include/linux/i8042.h b/include/linux/i8042.h
index 9bf6870..a986ff5 100644
--- a/include/linux/i8042.h
+++ b/include/linux/i8042.h
@@ -46,31 +46,31 @@
 
 #else
 
-void i8042_lock_chip(void)
+static inline void i8042_lock_chip(void)
 {
 }
 
-void i8042_unlock_chip(void)
+static inline void i8042_unlock_chip(void)
 {
 }
 
-int i8042_command(unsigned char *param, int command)
+static inline int i8042_command(unsigned char *param, int command)
 {
 	return -ENODEV;
 }
 
-bool i8042_check_port_owner(const struct serio *serio)
+static inline bool i8042_check_port_owner(const struct serio *serio)
 {
 	return false;
 }
 
-int i8042_install_filter(bool (*filter)(unsigned char data, unsigned char str,
+static inline int i8042_install_filter(bool (*filter)(unsigned char data, unsigned char str,
 					struct serio *serio))
 {
 	return -ENODEV;
 }
 
-int i8042_remove_filter(bool (*filter)(unsigned char data, unsigned char str,
+static inline int i8042_remove_filter(bool (*filter)(unsigned char data, unsigned char str,
 				       struct serio *serio))
 {
 	return -ENODEV;
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index a4d2e9f..adf832d 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1026,11 +1026,12 @@
 
 struct jbd2_buffer_trigger_type {
 	/*
-	 * Fired just before a buffer is written to the journal.
-	 * mapped_data is a mapped buffer that is the frozen data for
-	 * commit.
+	 * Fired a the moment data to write to the journal are known to be
+	 * stable - so either at the moment b_frozen_data is created or just
+	 * before a buffer is written to the journal.  mapped_data is a mapped
+	 * buffer that is the frozen data for commit.
 	 */
-	void (*t_commit)(struct jbd2_buffer_trigger_type *type,
+	void (*t_frozen)(struct jbd2_buffer_trigger_type *type,
 			 struct buffer_head *bh, void *mapped_data,
 			 size_t size);
 
@@ -1042,7 +1043,7 @@
 			struct buffer_head *bh);
 };
 
-extern void jbd2_buffer_commit_trigger(struct journal_head *jh,
+extern void jbd2_buffer_frozen_trigger(struct journal_head *jh,
 				       void *mapped_data,
 				       struct jbd2_buffer_trigger_type *triggers);
 extern void jbd2_buffer_abort_trigger(struct journal_head *jh,
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 7cb0084..f26fda76b 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -288,6 +288,7 @@
 	 */
 	unsigned int	irq;
 	struct resource resource[DEVICE_COUNT_RESOURCE]; /* I/O and memory regions + expansion ROMs */
+	resource_size_t	fw_addr[DEVICE_COUNT_RESOURCE]; /* FW-assigned addr */
 
 	/* These fields are used by common fixups */
 	unsigned int	transparent:1;	/* Transparent PCI bridge */
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 7f614ce..13ebb54 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -124,7 +124,8 @@
 extern struct trace_event_functions exit_syscall_print_funcs;
 
 #define SYSCALL_TRACE_ENTER_EVENT(sname)				\
-	static struct syscall_metadata __syscall_meta_##sname;		\
+	static struct syscall_metadata					\
+	__attribute__((__aligned__(4))) __syscall_meta_##sname;		\
 	static struct ftrace_event_call					\
 	__attribute__((__aligned__(4))) event_enter_##sname;		\
 	static struct ftrace_event_call __used				\
@@ -138,7 +139,8 @@
 	}
 
 #define SYSCALL_TRACE_EXIT_EVENT(sname)					\
-	static struct syscall_metadata __syscall_meta_##sname;		\
+	static struct syscall_metadata					\
+	__attribute__((__aligned__(4))) __syscall_meta_##sname;		\
 	static struct ftrace_event_call					\
 	__attribute__((__aligned__(4))) event_exit_##sname;		\
 	static struct ftrace_event_call __used				\
diff --git a/kernel/early_res.c b/kernel/early_res.c
index 31aa933..7bfae88 100644
--- a/kernel/early_res.c
+++ b/kernel/early_res.c
@@ -7,6 +7,8 @@
 #include <linux/bootmem.h>
 #include <linux/mm.h>
 #include <linux/early_res.h>
+#include <linux/slab.h>
+#include <linux/kmemleak.h>
 
 /*
  * Early reserved memory areas.
@@ -319,6 +321,8 @@
 	struct early_res *r;
 	int i;
 
+	kmemleak_free_part(__va(start), end - start);
+
 	i = find_overlapped_early(start, end);
 	r = &early_res[i];
 	if (i >= max_early_res || r->end != end || r->start != start)
@@ -333,6 +337,8 @@
 	struct early_res *r;
 	int i;
 
+	kmemleak_free_part(__va(start), end - start);
+
 	if (start == end)
 		return;
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 431214b..68319dd 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3659,6 +3659,11 @@
 		ptr = phys_to_virt(addr);
 		memset(ptr, 0, size);
 		reserve_early_without_check(addr, addr + size, "BOOTMEM");
+		/*
+		 * The min_count is set to 0 so that bootmem allocated blocks
+		 * are never reported as leaks.
+		 */
+		kmemleak_alloc(ptr, size, 0, 0);
 		return ptr;
 	}
 
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index 6c00814..5bffada 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -9,6 +9,7 @@
 #include <linux/vmalloc.h>
 #include <linux/cgroup.h>
 #include <linux/swapops.h>
+#include <linux/kmemleak.h>
 
 static void __meminit
 __init_page_cgroup(struct page_cgroup *pc, unsigned long pfn)
@@ -126,6 +127,12 @@
 			if (!base)
 				base = vmalloc(table_size);
 		}
+		/*
+		 * The value stored in section->page_cgroup is (base - pfn)
+		 * and it does not point to the memory block allocated above,
+		 * causing kmemleak false positives.
+		 */
+		kmemleak_not_leak(base);
 	} else {
 		/*
  		 * We don't have to allocate page_cgroup again, but
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 3592057..fd7407c 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -107,7 +107,7 @@
 		goto out_free_syms;
 	err = 0;
 	if (symbol_conf.use_callchain) {
-		err = append_chain(he->callchain, data->callchain, syms);
+		err = append_chain(he->callchain, data->callchain, syms, data->period);
 		if (err)
 			goto out_free_syms;
 	}
diff --git a/tools/perf/util/PERF-VERSION-GEN b/tools/perf/util/PERF-VERSION-GEN
index 49ece79..97d7656 100755
--- a/tools/perf/util/PERF-VERSION-GEN
+++ b/tools/perf/util/PERF-VERSION-GEN
@@ -5,17 +5,13 @@
 fi
 
 GVF=${OUTPUT}PERF-VERSION-FILE
-DEF_VER=v0.0.2.PERF
 
 LF='
 '
 
-# First see if there is a version file (included in release tarballs),
-# then try git-describe, then default.
-if test -f version
-then
-	VN=$(cat version) || VN="$DEF_VER"
-elif test -d .git -o -f .git &&
+# First check if there is a .git to get the version from git describe
+# otherwise try to get the version from the kernel makefile
+if test -d ../../.git -o -f ../../.git &&
 	VN=$(git describe --abbrev=4 HEAD 2>/dev/null) &&
 	case "$VN" in
 	*$LF*) (exit 1) ;;
@@ -27,7 +23,12 @@
 then
 	VN=$(echo "$VN" | sed -e 's/-/./g');
 else
-	VN="$DEF_VER"
+	eval `grep '^VERSION\s*=' ../../Makefile|tr -d ' '`
+	eval `grep '^PATCHLEVEL\s*=' ../../Makefile|tr -d ' '`
+	eval `grep '^SUBLEVEL\s*=' ../../Makefile|tr -d ' '`
+	eval `grep '^EXTRAVERSION\s*=' ../../Makefile|tr -d ' '`
+
+	VN="${VERSION}.${PATCHLEVEL}.${SUBLEVEL}${EXTRAVERSION}"
 fi
 
 VN=$(expr "$VN" : v*'\(.*\)')
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 62b69ad..52c777e 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -230,7 +230,7 @@
 
 static void
 add_child(struct callchain_node *parent, struct resolved_chain *chain,
-	  int start)
+	  int start, u64 period)
 {
 	struct callchain_node *new;
 
@@ -238,7 +238,7 @@
 	fill_node(new, chain, start);
 
 	new->children_hit = 0;
-	new->hit = 1;
+	new->hit = period;
 }
 
 /*
@@ -248,7 +248,8 @@
  */
 static void
 split_add_child(struct callchain_node *parent, struct resolved_chain *chain,
-		struct callchain_list *to_split, int idx_parents, int idx_local)
+		struct callchain_list *to_split, int idx_parents, int idx_local,
+		u64 period)
 {
 	struct callchain_node *new;
 	struct list_head *old_tail;
@@ -275,41 +276,41 @@
 	/* create a new child for the new branch if any */
 	if (idx_total < chain->nr) {
 		parent->hit = 0;
-		add_child(parent, chain, idx_total);
-		parent->children_hit++;
+		add_child(parent, chain, idx_total, period);
+		parent->children_hit += period;
 	} else {
-		parent->hit = 1;
+		parent->hit = period;
 	}
 }
 
 static int
 __append_chain(struct callchain_node *root, struct resolved_chain *chain,
-	       unsigned int start);
+	       unsigned int start, u64 period);
 
 static void
 __append_chain_children(struct callchain_node *root,
 			struct resolved_chain *chain,
-			unsigned int start)
+			unsigned int start, u64 period)
 {
 	struct callchain_node *rnode;
 
 	/* lookup in childrens */
 	chain_for_each_child(rnode, root) {
-		unsigned int ret = __append_chain(rnode, chain, start);
+		unsigned int ret = __append_chain(rnode, chain, start, period);
 
 		if (!ret)
 			goto inc_children_hit;
 	}
 	/* nothing in children, add to the current node */
-	add_child(root, chain, start);
+	add_child(root, chain, start, period);
 
 inc_children_hit:
-	root->children_hit++;
+	root->children_hit += period;
 }
 
 static int
 __append_chain(struct callchain_node *root, struct resolved_chain *chain,
-	       unsigned int start)
+	       unsigned int start, u64 period)
 {
 	struct callchain_list *cnode;
 	unsigned int i = start;
@@ -345,18 +346,18 @@
 
 	/* we match only a part of the node. Split it and add the new chain */
 	if (i - start < root->val_nr) {
-		split_add_child(root, chain, cnode, start, i - start);
+		split_add_child(root, chain, cnode, start, i - start, period);
 		return 0;
 	}
 
 	/* we match 100% of the path, increment the hit */
 	if (i - start == root->val_nr && i == chain->nr) {
-		root->hit++;
+		root->hit += period;
 		return 0;
 	}
 
 	/* We match the node and still have a part remaining */
-	__append_chain_children(root, chain, i);
+	__append_chain_children(root, chain, i, period);
 
 	return 0;
 }
@@ -380,7 +381,7 @@
 
 
 int append_chain(struct callchain_node *root, struct ip_callchain *chain,
-		 struct map_symbol *syms)
+		 struct map_symbol *syms, u64 period)
 {
 	struct resolved_chain *filtered;
 
@@ -397,7 +398,7 @@
 	if (!filtered->nr)
 		goto end;
 
-	__append_chain_children(root, filtered, 0);
+	__append_chain_children(root, filtered, 0, period);
 end:
 	free(filtered);
 
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 1ca73e4..f2e9ee1 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -49,6 +49,9 @@
 	INIT_LIST_HEAD(&node->brothers);
 	INIT_LIST_HEAD(&node->children);
 	INIT_LIST_HEAD(&node->val);
+
+	node->parent = NULL;
+	node->hit = 0;
 }
 
 static inline u64 cumul_hits(struct callchain_node *node)
@@ -58,7 +61,7 @@
 
 int register_callchain_param(struct callchain_param *param);
 int append_chain(struct callchain_node *root, struct ip_callchain *chain,
-		 struct map_symbol *syms);
+		 struct map_symbol *syms, u64 period);
 
 bool ip_callchain__valid(struct ip_callchain *chain, event_t *event);
 #endif	/* __PERF_CALLCHAIN_H */