16 files changed, 504 insertions, 224 deletions

diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index bc2ff5932769..036880895bfc 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -297,7 +297,6 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
         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 @@ repeat:
                 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 e214d68620ac..b8e0806681bb 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -725,6 +725,9 @@ done:
                 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 @@ void jbd2_journal_set_triggers(struct buffer_head *bh,
         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 3623ca20cc18..356e976772bf 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;
@@ -459,36 +458,6 @@ 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;
@@ -1131,23 +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;
@@ -1620,21 +1603,20 @@ 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);
 
@@ -1644,6 +1626,18 @@ 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,
@@ -1679,7 +1673,11 @@ 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;
@@ -1789,7 +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);
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 6b5a492e1749..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;
@@ -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 "
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)) {
@@ -2826,9 +2820,21 @@ 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
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
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 6a13ea64c447..2b10b36d1577 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;
+        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 @@ 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;
+        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 @@ 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;
-        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;
+                }
+
+                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;
                 }
 
-                start_off += sb->s_blocksize;
+                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 @@ 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;
@@ -840,7 +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);
 
@@ -862,27 +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);
 
@@ -899,14 +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/journal.c b/fs/ocfs2/journal.c
index 47878cf16418..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),
@@ -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());
         }
 }
 
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;
 }
 
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..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;
@@ -4166,6 +4172,12 @@ 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);
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);
 
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index e97b34842cfe..d03469f61801 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;
 }
@@ -6788,16 +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,
@@ -6816,14 +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);
@@ -6837,6 +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,
@@ -6866,6 +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);
         }
@@ -6874,6 +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.
  */
@@ -6885,8 +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;
@@ -6895,6 +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);
@@ -6914,32 +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:
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index a4d2e9f7088a..adf832dec3f3 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1026,11 +1026,12 @@ void __jbd2_journal_insert_checkpoint(struct journal_head *, transaction_t *);
 
 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 jbd2_buffer_trigger_type {
                         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,