Merge branch 'for-linus-4.5' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs

Pull btrfs updates from Chris Mason:
 "This has our usual assortment of fixes and cleanups, but the biggest
  change included is Omar Sandoval's free space tree.  It's not the
  default yet, mounting -o space_cache=v2 enables it and sets a readonly
  compat bit.  The tree can actually be deleted and regenerated if there
  are any problems, but it has held up really well in testing so far.

  For very large filesystems (30T+) our existing free space caching code
  can end up taking a huge amount of time during commits.  The new tree
  based code is faster and less work overall to update as the commit
  progresses.

  Omar worked on this during the summer and we'll hammer on it in
  production here at FB over the next few months"

* 'for-linus-4.5' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (73 commits)
  Btrfs: fix fitrim discarding device area reserved for boot loader's use
  Btrfs: Check metadata redundancy on balance
  btrfs: statfs: report zero available if metadata are exhausted
  btrfs: preallocate path for snapshot creation at ioctl time
  btrfs: allocate root item at snapshot ioctl time
  btrfs: do an allocation earlier during snapshot creation
  btrfs: use smaller type for btrfs_path locks
  btrfs: use smaller type for btrfs_path lowest_level
  btrfs: use smaller type for btrfs_path reada
  btrfs: cleanup, use enum values for btrfs_path reada
  btrfs: constify static arrays
  btrfs: constify remaining structs with function pointers
  btrfs tests: replace whole ops structure for free space tests
  btrfs: use list_for_each_entry* in backref.c
  btrfs: use list_for_each_entry_safe in free-space-cache.c
  btrfs: use list_for_each_entry* in check-integrity.c
  Btrfs: use linux/sizes.h to represent constants
  btrfs: cleanup, remove stray return statements
  btrfs: zero out delayed node upon allocation
  btrfs: pass proper enum type to start_transaction()
  ...

1 files changed, 185 insertions, 125 deletions

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 9abe18763a7f..2e7c97a3f344 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1285,20 +1285,6 @@ search_again:
 }
 
 /* wrappers around set/clear extent bit */
-int set_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end,
-		     gfp_t mask)
-{
-	return set_extent_bit(tree, start, end, EXTENT_DIRTY, NULL,
-			      NULL, mask);
-}
-
-int set_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
-		    unsigned bits, gfp_t mask)
-{
-	return set_extent_bit(tree, start, end, bits, NULL,
-			      NULL, mask);
-}
-
 int set_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
 			   unsigned bits, gfp_t mask,
 			   struct extent_changeset *changeset)
@@ -1323,17 +1309,6 @@ int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end,
 				  cached, mask, NULL);
 }
 
-int clear_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
-		      unsigned bits, gfp_t mask)
-{
-	int wake = 0;
-
-	if (bits & EXTENT_LOCKED)
-		wake = 1;
-
-	return clear_extent_bit(tree, start, end, bits, wake, 0, NULL, mask);
-}
-
 int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
 			     unsigned bits, gfp_t mask,
 			     struct extent_changeset *changeset)
@@ -1348,63 +1323,18 @@ int clear_record_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
 				  changeset);
 }
 
-int set_extent_delalloc(struct extent_io_tree *tree, u64 start, u64 end,
-			struct extent_state **cached_state, gfp_t mask)
-{
-	return set_extent_bit(tree, start, end,
-			      EXTENT_DELALLOC | EXTENT_UPTODATE,
-			      NULL, cached_state, mask);
-}
-
-int set_extent_defrag(struct extent_io_tree *tree, u64 start, u64 end,
-		      struct extent_state **cached_state, gfp_t mask)
-{
-	return set_extent_bit(tree, start, end,
-			      EXTENT_DELALLOC | EXTENT_UPTODATE | EXTENT_DEFRAG,
-			      NULL, cached_state, mask);
-}
-
-int clear_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end,
-		       gfp_t mask)
-{
-	return clear_extent_bit(tree, start, end,
-				EXTENT_DIRTY | EXTENT_DELALLOC |
-				EXTENT_DO_ACCOUNTING, 0, 0, NULL, mask);
-}
-
-int set_extent_new(struct extent_io_tree *tree, u64 start, u64 end,
-		     gfp_t mask)
-{
-	return set_extent_bit(tree, start, end, EXTENT_NEW, NULL,
-			      NULL, mask);
-}
-
-int set_extent_uptodate(struct extent_io_tree *tree, u64 start, u64 end,
-			struct extent_state **cached_state, gfp_t mask)
-{
-	return set_extent_bit(tree, start, end, EXTENT_UPTODATE, NULL,
-			      cached_state, mask);
-}
-
-int clear_extent_uptodate(struct extent_io_tree *tree, u64 start, u64 end,
-			  struct extent_state **cached_state, gfp_t mask)
-{
-	return clear_extent_bit(tree, start, end, EXTENT_UPTODATE, 0, 0,
-				cached_state, mask);
-}
-
 /*
  * either insert or lock state struct between start and end use mask to tell
  * us if waiting is desired.
  */
 int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
-		     unsigned bits, struct extent_state **cached_state)
+		     struct extent_state **cached_state)
 {
 	int err;
 	u64 failed_start;
 
 	while (1) {
-		err = __set_extent_bit(tree, start, end, EXTENT_LOCKED | bits,
+		err = __set_extent_bit(tree, start, end, EXTENT_LOCKED,
 				       EXTENT_LOCKED, &failed_start,
 				       cached_state, GFP_NOFS, NULL);
 		if (err == -EEXIST) {
@@ -1417,11 +1347,6 @@ int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end,
 	return err;
 }
 
-int lock_extent(struct extent_io_tree *tree, u64 start, u64 end)
-{
-	return lock_extent_bits(tree, start, end, 0, NULL);
-}
-
 int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end)
 {
 	int err;
@@ -1438,20 +1363,7 @@ int try_lock_extent(struct extent_io_tree *tree, u64 start, u64 end)
 	return 1;
 }
 
-int unlock_extent_cached(struct extent_io_tree *tree, u64 start, u64 end,
-			 struct extent_state **cached, gfp_t mask)
-{
-	return clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, cached,
-				mask);
-}
-
-int unlock_extent(struct extent_io_tree *tree, u64 start, u64 end)
-{
-	return clear_extent_bit(tree, start, end, EXTENT_LOCKED, 1, 0, NULL,
-				GFP_NOFS);
-}
-
-int extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end)
+void extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end)
 {
 	unsigned long index = start >> PAGE_CACHE_SHIFT;
 	unsigned long end_index = end >> PAGE_CACHE_SHIFT;
@@ -1464,10 +1376,9 @@ int extent_range_clear_dirty_for_io(struct inode *inode, u64 start, u64 end)
 		page_cache_release(page);
 		index++;
 	}
-	return 0;
 }
 
-int extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end)
+void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end)
 {
 	unsigned long index = start >> PAGE_CACHE_SHIFT;
 	unsigned long end_index = end >> PAGE_CACHE_SHIFT;
@@ -1481,13 +1392,12 @@ int extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end)
 		page_cache_release(page);
 		index++;
 	}
-	return 0;
 }
 
 /*
  * helper function to set both pages and extents in the tree writeback
  */
-static int set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end)
+static void set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end)
 {
 	unsigned long index = start >> PAGE_CACHE_SHIFT;
 	unsigned long end_index = end >> PAGE_CACHE_SHIFT;
@@ -1500,7 +1410,6 @@ static int set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end)
 		page_cache_release(page);
 		index++;
 	}
-	return 0;
 }
 
 /* find the first state struct with 'bits' set after 'start', and
@@ -1800,7 +1709,7 @@ again:
 	BUG_ON(ret); /* Only valid values are 0 and -EAGAIN */
 
 	/* step three, lock the state bits for the whole range */
-	lock_extent_bits(tree, delalloc_start, delalloc_end, 0, &cached_state);
+	lock_extent_bits(tree, delalloc_start, delalloc_end, &cached_state);
 
 	/* then test to make sure it is all still delalloc */
 	ret = test_range_bit(tree, delalloc_start, delalloc_end,
@@ -1820,7 +1729,7 @@ out_failed:
 	return found;
 }
 
-int extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
+void extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
 				 struct page *locked_page,
 				 unsigned clear_bits,
 				 unsigned long page_ops)
@@ -1835,7 +1744,7 @@ int extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
 
 	clear_extent_bit(tree, start, end, clear_bits, 1, 0, NULL, GFP_NOFS);
 	if (page_ops == 0)
-		return 0;
+		return;
 
 	if ((page_ops & PAGE_SET_ERROR) && nr_pages > 0)
 		mapping_set_error(inode->i_mapping, -EIO);
@@ -1869,7 +1778,6 @@ int extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
 		index += ret;
 		cond_resched();
 	}
-	return 0;
 }
 
 /*
@@ -2516,7 +2424,7 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 
 /* lots and lots of room for performance fixes in the end_bio funcs */
 
-int end_extent_writepage(struct page *page, int err, u64 start, u64 end)
+void end_extent_writepage(struct page *page, int err, u64 start, u64 end)
 {
 	int uptodate = (err == 0);
 	struct extent_io_tree *tree;
@@ -2537,7 +2445,6 @@ int end_extent_writepage(struct page *page, int err, u64 start, u64 end)
 		ret = ret < 0 ? ret : -EIO;
 		mapping_set_error(page->mapping, ret);
 	}
-	return 0;
 }
 
 /*
@@ -2579,9 +2486,7 @@ static void end_bio_extent_writepage(struct bio *bio)
 		start = page_offset(page);
 		end = start + bvec->bv_offset + bvec->bv_len - 1;
 
-		if (end_extent_writepage(page, bio->bi_error, start, end))
-			continue;
-
+		end_extent_writepage(page, bio->bi_error, start, end);
 		end_page_writeback(page);
 	}
 
@@ -4326,7 +4231,7 @@ int extent_invalidatepage(struct extent_io_tree *tree,
 	if (start > end)
 		return 0;
 
-	lock_extent_bits(tree, start, end, 0, &cached_state);
+	lock_extent_bits(tree, start, end, &cached_state);
 	wait_on_page_writeback(page);
 	clear_extent_bit(tree, start, end,
 			 EXTENT_LOCKED | EXTENT_DIRTY | EXTENT_DELALLOC |
@@ -4387,7 +4292,7 @@ int try_release_extent_mapping(struct extent_map_tree *map,
 	u64 end = start + PAGE_CACHE_SIZE - 1;
 
 	if (gfpflags_allow_blocking(mask) &&
-	    page->mapping->host->i_size > 16 * 1024 * 1024) {
+	    page->mapping->host->i_size > SZ_16M) {
 		u64 len;
 		while (start <= end) {
 			len = end - start + 1;
@@ -4536,7 +4441,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		last_for_get_extent = isize;
 	}
 
-	lock_extent_bits(&BTRFS_I(inode)->io_tree, start, start + len - 1, 0,
+	lock_extent_bits(&BTRFS_I(inode)->io_tree, start, start + len - 1,
 			 &cached_state);
 
 	em = get_extent_skip_holes(inode, start, last_for_get_extent,
@@ -4797,24 +4702,14 @@ struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src)
 	return new;
 }
 
-struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
-						u64 start)
+struct extent_buffer *__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
+						  u64 start, unsigned long len)
 {
 	struct extent_buffer *eb;
-	unsigned long len;
 	unsigned long num_pages;
 	unsigned long i;
 
-	if (!fs_info) {
-		/*
-		 * Called only from tests that don't always have a fs_info
-		 * available, but we know that nodesize is 4096
-		 */
-		len = 4096;
-	} else {
-		len = fs_info->tree_root->nodesize;
-	}
-	num_pages = num_extent_pages(0, len);
+	num_pages = num_extent_pages(start, len);
 
 	eb = __alloc_extent_buffer(fs_info, start, len);
 	if (!eb)
@@ -4837,6 +4732,24 @@ err:
 	return NULL;
 }
 
+struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
+						u64 start)
+{
+	unsigned long len;
+
+	if (!fs_info) {
+		/*
+		 * Called only from tests that don't always have a fs_info
+		 * available, but we know that nodesize is 4096
+		 */
+		len = 4096;
+	} else {
+		len = fs_info->tree_root->nodesize;
+	}
+
+	return __alloc_dummy_extent_buffer(fs_info, start, len);
+}
+
 static void check_buffer_tree_ref(struct extent_buffer *eb)
 {
 	int refs;
@@ -5227,7 +5140,7 @@ int set_extent_buffer_dirty(struct extent_buffer *eb)
 	return was_dirty;
 }
 
-int clear_extent_buffer_uptodate(struct extent_buffer *eb)
+void clear_extent_buffer_uptodate(struct extent_buffer *eb)
 {
 	unsigned long i;
 	struct page *page;
@@ -5240,10 +5153,9 @@ int clear_extent_buffer_uptodate(struct extent_buffer *eb)
 		if (page)
 			ClearPageUptodate(page);
 	}
-	return 0;
 }
 
-int set_extent_buffer_uptodate(struct extent_buffer *eb)
+void set_extent_buffer_uptodate(struct extent_buffer *eb)
 {
 	unsigned long i;
 	struct page *page;
@@ -5255,7 +5167,6 @@ int set_extent_buffer_uptodate(struct extent_buffer *eb)
 		page = eb->pages[i];
 		SetPageUptodate(page);
 	}
-	return 0;
 }
 
 int extent_buffer_uptodate(struct extent_buffer *eb)
@@ -5594,6 +5505,155 @@ void copy_extent_buffer(struct extent_buffer *dst, struct extent_buffer *src,
 	}
 }
 
+/*
+ * The extent buffer bitmap operations are done with byte granularity because
+ * bitmap items are not guaranteed to be aligned to a word and therefore a
+ * single word in a bitmap may straddle two pages in the extent buffer.
+ */
+#define BIT_BYTE(nr) ((nr) / BITS_PER_BYTE)
+#define BYTE_MASK ((1 << BITS_PER_BYTE) - 1)
+#define BITMAP_FIRST_BYTE_MASK(start) \
+	((BYTE_MASK << ((start) & (BITS_PER_BYTE - 1))) & BYTE_MASK)
+#define BITMAP_LAST_BYTE_MASK(nbits) \
+	(BYTE_MASK >> (-(nbits) & (BITS_PER_BYTE - 1)))
+
+/*
+ * eb_bitmap_offset() - calculate the page and offset of the byte containing the
+ * given bit number
+ * @eb: the extent buffer
+ * @start: offset of the bitmap item in the extent buffer
+ * @nr: bit number
+ * @page_index: return index of the page in the extent buffer that contains the
+ * given bit number
+ * @page_offset: return offset into the page given by page_index
+ *
+ * This helper hides the ugliness of finding the byte in an extent buffer which
+ * contains a given bit.
+ */
+static inline void eb_bitmap_offset(struct extent_buffer *eb,
+				    unsigned long start, unsigned long nr,
+				    unsigned long *page_index,
+				    size_t *page_offset)
+{
+	size_t start_offset = eb->start & ((u64)PAGE_CACHE_SIZE - 1);
+	size_t byte_offset = BIT_BYTE(nr);
+	size_t offset;
+
+	/*
+	 * The byte we want is the offset of the extent buffer + the offset of
+	 * the bitmap item in the extent buffer + the offset of the byte in the
+	 * bitmap item.
+	 */
+	offset = start_offset + start + byte_offset;
+
+	*page_index = offset >> PAGE_CACHE_SHIFT;
+	*page_offset = offset & (PAGE_CACHE_SIZE - 1);
+}
+
+/**
+ * extent_buffer_test_bit - determine whether a bit in a bitmap item is set
+ * @eb: the extent buffer
+ * @start: offset of the bitmap item in the extent buffer
+ * @nr: bit number to test
+ */
+int extent_buffer_test_bit(struct extent_buffer *eb, unsigned long start,
+			   unsigned long nr)
+{
+	char *kaddr;
+	struct page *page;
+	unsigned long i;
+	size_t offset;
+
+	eb_bitmap_offset(eb, start, nr, &i, &offset);
+	page = eb->pages[i];
+	WARN_ON(!PageUptodate(page));
+	kaddr = page_address(page);
+	return 1U & (kaddr[offset] >> (nr & (BITS_PER_BYTE - 1)));
+}
+
+/**
+ * extent_buffer_bitmap_set - set an area of a bitmap
+ * @eb: the extent buffer
+ * @start: offset of the bitmap item in the extent buffer
+ * @pos: bit number of the first bit
+ * @len: number of bits to set
+ */
+void extent_buffer_bitmap_set(struct extent_buffer *eb, unsigned long start,
+			      unsigned long pos, unsigned long len)
+{
+	char *kaddr;
+	struct page *page;
+	unsigned long i;
+	size_t offset;
+	const unsigned int size = pos + len;
+	int bits_to_set = BITS_PER_BYTE - (pos % BITS_PER_BYTE);
+	unsigned int mask_to_set = BITMAP_FIRST_BYTE_MASK(pos);
+
+	eb_bitmap_offset(eb, start, pos, &i, &offset);
+	page = eb->pages[i];
+	WARN_ON(!PageUptodate(page));
+	kaddr = page_address(page);
+
+	while (len >= bits_to_set) {
+		kaddr[offset] |= mask_to_set;
+		len -= bits_to_set;
+		bits_to_set = BITS_PER_BYTE;
+		mask_to_set = ~0U;
+		if (++offset >= PAGE_CACHE_SIZE && len > 0) {
+			offset = 0;
+			page = eb->pages[++i];
+			WARN_ON(!PageUptodate(page));
+			kaddr = page_address(page);
+		}
+	}
+	if (len) {
+		mask_to_set &= BITMAP_LAST_BYTE_MASK(size);
+		kaddr[offset] |= mask_to_set;
+	}
+}
+
+
+/**
+ * extent_buffer_bitmap_clear - clear an area of a bitmap
+ * @eb: the extent buffer
+ * @start: offset of the bitmap item in the extent buffer
+ * @pos: bit number of the first bit
+ * @len: number of bits to clear
+ */
+void extent_buffer_bitmap_clear(struct extent_buffer *eb, unsigned long start,
+				unsigned long pos, unsigned long len)
+{
+	char *kaddr;
+	struct page *page;
+	unsigned long i;
+	size_t offset;
+	const unsigned int size = pos + len;
+	int bits_to_clear = BITS_PER_BYTE - (pos % BITS_PER_BYTE);
+	unsigned int mask_to_clear = BITMAP_FIRST_BYTE_MASK(pos);
+
+	eb_bitmap_offset(eb, start, pos, &i, &offset);
+	page = eb->pages[i];
+	WARN_ON(!PageUptodate(page));
+	kaddr = page_address(page);
+
+	while (len >= bits_to_clear) {
+		kaddr[offset] &= ~mask_to_clear;
+		len -= bits_to_clear;
+		bits_to_clear = BITS_PER_BYTE;
+		mask_to_clear = ~0U;
+		if (++offset >= PAGE_CACHE_SIZE && len > 0) {
+			offset = 0;
+			page = eb->pages[++i];
+			WARN_ON(!PageUptodate(page));
+			kaddr = page_address(page);
+		}
+	}
+	if (len) {
+		mask_to_clear &= BITMAP_LAST_BYTE_MASK(size);
+		kaddr[offset] &= ~mask_to_clear;
+	}
+}
+
 static inline bool areas_overlap(unsigned long src, unsigned long dst, unsigned long len)
 {
 	unsigned long distance = (src > dst) ? src - dst : dst - src;