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

Pull btrfs update from Chris Mason:
 "From a feature point of view, most of the code here comes from Miao
  Xie and others at Fujitsu to implement scrubbing and replacing devices
  on raid56.  This has been in development for a while, and it's a big
  improvement.

  Filipe and Josef have a great assortment of fixes, many of which solve
  problems corruptions either after a crash or in error conditions.  I
  still have a round two from Filipe for next week that solves
  corruptions with discard and block group removal"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (62 commits)
  Btrfs: make get_caching_control unconditionally return the ctl
  Btrfs: fix unprotected deletion from pending_chunks list
  Btrfs: fix fs mapping extent map leak
  Btrfs: fix memory leak after block remove + trimming
  Btrfs: make btrfs_abort_transaction consider existence of new block groups
  Btrfs: fix race between writing free space cache and trimming
  Btrfs: fix race between fs trimming and block group remove/allocation
  Btrfs, replace: enable dev-replace for raid56
  Btrfs: fix freeing used extents after removing empty block group
  Btrfs: fix crash caused by block group removal
  Btrfs: fix invalid block group rbtree access after bg is removed
  Btrfs, raid56: fix use-after-free problem in the final device replace procedure on raid56
  Btrfs, replace: write raid56 parity into the replace target device
  Btrfs, replace: write dirty pages into the replace target device
  Btrfs, raid56: support parity scrub on raid56
  Btrfs, raid56: use a variant to record the operation type
  Btrfs, scrub: repair the common data on RAID5/6 if it is corrupted
  Btrfs, raid56: don't change bbio and raid_map
  Btrfs: remove unnecessary code of stripe_index assignment in __btrfs_map_block
  Btrfs: remove noused bbio_ret in __btrfs_map_block in condition
  ...

1 files changed, 34 insertions, 7 deletions

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index bf3f424e0013..4ebabd237153 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -595,9 +595,14 @@ int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 		clear = 1;
 again:
 	if (!prealloc && (mask & __GFP_WAIT)) {
+		/*
+		 * Don't care for allocation failure here because we might end
+		 * up not needing the pre-allocated extent state at all, which
+		 * is the case if we only have in the tree extent states that
+		 * cover our input range and don't cover too any other range.
+		 * If we end up needing a new extent state we allocate it later.
+		 */
 		prealloc = alloc_extent_state(mask);
-		if (!prealloc)
-			return -ENOMEM;
 	}
 
 	spin_lock(&tree->lock);
@@ -796,17 +801,25 @@ static void set_state_bits(struct extent_io_tree *tree,
 	state->state |= bits_to_set;
 }
 
-static void cache_state(struct extent_state *state,
-			struct extent_state **cached_ptr)
+static void cache_state_if_flags(struct extent_state *state,
+				 struct extent_state **cached_ptr,
+				 const u64 flags)
 {
 	if (cached_ptr && !(*cached_ptr)) {
-		if (state->state & (EXTENT_IOBITS | EXTENT_BOUNDARY)) {
+		if (!flags || (state->state & flags)) {
 			*cached_ptr = state;
 			atomic_inc(&state->refs);
 		}
 	}
 }
 
+static void cache_state(struct extent_state *state,
+			struct extent_state **cached_ptr)
+{
+	return cache_state_if_flags(state, cached_ptr,
+				    EXTENT_IOBITS | EXTENT_BOUNDARY);
+}
+
 /*
  * set some bits on a range in the tree.  This may require allocations or
  * sleeping, so the gfp mask is used to indicate what is allowed.
@@ -1058,13 +1071,21 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 	int err = 0;
 	u64 last_start;
 	u64 last_end;
+	bool first_iteration = true;
 
 	btrfs_debug_check_extent_io_range(tree, start, end);
 
 again:
 	if (!prealloc && (mask & __GFP_WAIT)) {
+		/*
+		 * Best effort, don't worry if extent state allocation fails
+		 * here for the first iteration. We might have a cached state
+		 * that matches exactly the target range, in which case no
+		 * extent state allocations are needed. We'll only know this
+		 * after locking the tree.
+		 */
 		prealloc = alloc_extent_state(mask);
-		if (!prealloc)
+		if (!prealloc && !first_iteration)
 			return -ENOMEM;
 	}
 
@@ -1234,6 +1255,7 @@ search_again:
 	spin_unlock(&tree->lock);
 	if (mask & __GFP_WAIT)
 		cond_resched();
+	first_iteration = false;
 	goto again;
 }
 
@@ -1482,7 +1504,7 @@ int find_first_extent_bit(struct extent_io_tree *tree, u64 start,
 	state = find_first_extent_bit_state(tree, start, bits);
 got_it:
 	if (state) {
-		cache_state(state, cached_state);
+		cache_state_if_flags(state, cached_state, 0);
 		*start_ret = state->start;
 		*end_ret = state->end;
 		ret = 0;
@@ -1746,6 +1768,9 @@ int extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
 	if (page_ops == 0)
 		return 0;
 
+	if ((page_ops & PAGE_SET_ERROR) && nr_pages > 0)
+		mapping_set_error(inode->i_mapping, -EIO);
+
 	while (nr_pages > 0) {
 		ret = find_get_pages_contig(inode->i_mapping, index,
 				     min_t(unsigned long,
@@ -1763,6 +1788,8 @@ int extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
 				clear_page_dirty_for_io(pages[i]);
 			if (page_ops & PAGE_SET_WRITEBACK)
 				set_page_writeback(pages[i]);
+			if (page_ops & PAGE_SET_ERROR)
+				SetPageError(pages[i]);
 			if (page_ops & PAGE_END_WRITEBACK)
 				end_page_writeback(pages[i]);
 			if (page_ops & PAGE_UNLOCK)