Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs

Pull btrfs update from Chris Mason:
 "A big set of fixes and features.

  In terms of line count, most of the code comes from Stefan, who added
  the ability to replace a single drive in place.  This is different
  from how btrfs normally replaces drives, and is much much much faster.

  Josef is plowing through our synchronous write performance.  This pull
  request does not include the DIO_OWN_WAITING patch that was discussed
  on the list, but it has a number of other improvements to cut down our
  latencies and CPU time during fsync/O_DIRECT writes.

  Miao Xie has a big series of fixes and is spreading out ordered
  operations over more CPUs.  This improves performance and reduces
  contention.

  I've put in fixes for error handling around hash collisions.  These
  are going back to individual stable kernels as I test against them.

  Otherwise we have a lot of fixes and cleanups, thanks everyone!
  raid5/6 is being rebased against the device replacement code.  I'll
  have it posted this Friday along with a nice series of benchmarks."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (115 commits)
  Btrfs: fix a bug of per-file nocow
  Btrfs: fix hash overflow handling
  Btrfs: don't take inode delalloc mutex if we're a free space inode
  Btrfs: fix autodefrag and umount lockup
  Btrfs: fix permissions of empty files not affected by umask
  Btrfs: put raid properties into global table
  Btrfs: fix BUG() in scrub when first superblock reading gives EIO
  Btrfs: do not call file_update_time in aio_write
  Btrfs: only unlock and relock if we have to
  Btrfs: use tokens where we can in the tree log
  Btrfs: optimize leaf_space_used
  Btrfs: don't memset new tokens
  Btrfs: only clear dirty on the buffer if it is marked as dirty
  Btrfs: move checks in set_page_dirty under DEBUG
  Btrfs: log changed inodes based on the extent map tree
  Btrfs: add path->really_keep_locks
  Btrfs: do not mark ems as prealloc if we are writing to them
  Btrfs: keep track of the extents original block length
  Btrfs: inline csums if we're fsyncing
  Btrfs: don't bother copying if we're only logging the inode
  ...

1 files changed, 10 insertions, 14 deletions

diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index ce9f79216723..f169d6b11d7f 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -49,7 +49,7 @@ void extent_map_tree_init(struct extent_map_tree *tree)
 struct extent_map *alloc_extent_map(void)
 {
         struct extent_map *em;
-        em = kmem_cache_alloc(extent_map_cache, GFP_NOFS);
+        em = kmem_cache_zalloc(extent_map_cache, GFP_NOFS);
         if (!em)
                 return NULL;
         em->in_tree = 0;
@@ -198,16 +198,15 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em)
                         merge = rb_entry(rb, struct extent_map, rb_node);
                 if (rb && mergable_maps(merge, em)) {
                         em->start = merge->start;
+                        em->orig_start = merge->orig_start;
                         em->len += merge->len;
                         em->block_len += merge->block_len;
                         em->block_start = merge->block_start;
                         merge->in_tree = 0;
-                        if (merge->generation > em->generation) {
-                                em->mod_start = em->start;
-                                em->mod_len = em->len;
-                                em->generation = merge->generation;
-                                list_move(&em->list, &tree->modified_extents);
-                        }
+                        em->mod_len = (em->mod_len + em->mod_start) - merge->mod_start;
+                        em->mod_start = merge->mod_start;
+                        em->generation = max(em->generation, merge->generation);
+                        list_move(&em->list, &tree->modified_extents);
 
                         list_del_init(&merge->list);
                         rb_erase(&merge->rb_node, &tree->map);
@@ -223,11 +222,8 @@ static void try_merge_map(struct extent_map_tree *tree, struct extent_map *em)
                 em->block_len += merge->len;
                 rb_erase(&merge->rb_node, &tree->map);
                 merge->in_tree = 0;
-                if (merge->generation > em->generation) {
-                        em->mod_len = em->len;
-                        em->generation = merge->generation;
-                        list_move(&em->list, &tree->modified_extents);
-                }
+                em->mod_len = (merge->mod_start + merge->mod_len) - em->mod_start;
+                em->generation = max(em->generation, merge->generation);
                 list_del_init(&merge->list);
                 free_extent_map(merge);
         }
@@ -265,9 +261,9 @@ int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len,
         em->mod_start = em->start;
         em->mod_len = em->len;
 
-        if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) {
+        if (test_bit(EXTENT_FLAG_FILLING, &em->flags)) {
                 prealloc = true;
-                clear_bit(EXTENT_FLAG_PREALLOC, &em->flags);
+                clear_bit(EXTENT_FLAG_FILLING, &em->flags);
         }
 
         try_merge_map(tree, em);