Merge branch 'for-linus-4.11' of git://git.kernel.org/pub/scm/linux/k…

…ernel/git/mason/linux-btrfs

Pull more btrfs updates from Chris Mason:
 "Btrfs round two.

  These are mostly a continuation of Dave Sterba's collection of
  cleanups, but Filipe also has some bug fixes and performance
  improvements"

* 'for-linus-4.11' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (69 commits)
  btrfs: add dummy callback for readpage_io_failed and drop checks
  btrfs: drop checks for mandatory extent_io_ops callbacks
  btrfs: document existence of extent_io ops callbacks
  btrfs: let writepage_end_io_hook return void
  btrfs: do proper error handling in btrfs_insert_xattr_item
  btrfs: handle allocation error in update_dev_stat_item
  btrfs: remove BUG_ON from __tree_mod_log_insert
  btrfs: derive maximum output size in the compression implementation
  btrfs: use predefined limits for calculating maximum number of pages for compression
  btrfs: export compression buffer limits in a header
  btrfs: merge nr_pages input and output parameter in compress_pages
  btrfs: merge length input and output parameter in compress_pages
  btrfs: constify name of subvolume in creation helpers
  btrfs: constify buffers used by compression helpers
  btrfs: constify input buffer of btrfs_csum_data
  btrfs: constify device path passed to relevant helpers
  btrfs: make btrfs_inode_resume_unlocked_dio take btrfs_inode
  btrfs: make btrfs_inode_block_unlocked_dio take btrfs_inode
  btrfs: Make btrfs_add_nondir take btrfs_inode
  btrfs: Make btrfs_add_link take btrfs_inode
  ...

fs/btrfs/btrfs_inode.h

@@ -237,20 +237,20 @@ static inline u64 btrfs_ino(struct btrfs_inode *inode)
 	return ino;
 }
 
-static inline void btrfs_i_size_write(struct inode *inode, u64 size)
+static inline void btrfs_i_size_write(struct btrfs_inode *inode, u64 size)
 {
-	i_size_write(inode, size);
-	BTRFS_I(inode)->disk_i_size = size;
+	i_size_write(&inode->vfs_inode, size);
+	inode->disk_i_size = size;
 }
 
-static inline bool btrfs_is_free_space_inode(struct inode *inode)
+static inline bool btrfs_is_free_space_inode(struct btrfs_inode *inode)
 {
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_root *root = inode->root;
 
 	if (root == root->fs_info->tree_root &&
-	    btrfs_ino(BTRFS_I(inode)) != BTRFS_BTREE_INODE_OBJECTID)
+	    btrfs_ino(inode) != BTRFS_BTREE_INODE_OBJECTID)
 		return true;
-	if (BTRFS_I(inode)->location.objectid == BTRFS_FREE_INO_OBJECTID)
+	if (inode->location.objectid == BTRFS_FREE_INO_OBJECTID)
 		return true;
 	return false;
 }
@@ -311,34 +311,33 @@ struct btrfs_dio_private {
  * to grab i_mutex. It is used to avoid the endless truncate due to
  * nonlocked dio read.
  */
-static inline void btrfs_inode_block_unlocked_dio(struct inode *inode)
+static inline void btrfs_inode_block_unlocked_dio(struct btrfs_inode *inode)
 {
-	set_bit(BTRFS_INODE_READDIO_NEED_LOCK, &BTRFS_I(inode)->runtime_flags);
+	set_bit(BTRFS_INODE_READDIO_NEED_LOCK, &inode->runtime_flags);
 	smp_mb();
 }
 
-static inline void btrfs_inode_resume_unlocked_dio(struct inode *inode)
+static inline void btrfs_inode_resume_unlocked_dio(struct btrfs_inode *inode)
 {
 	smp_mb__before_atomic();
-	clear_bit(BTRFS_INODE_READDIO_NEED_LOCK,
-		  &BTRFS_I(inode)->runtime_flags);
+	clear_bit(BTRFS_INODE_READDIO_NEED_LOCK, &inode->runtime_flags);
 }
 
-static inline void btrfs_print_data_csum_error(struct inode *inode,
+static inline void btrfs_print_data_csum_error(struct btrfs_inode *inode,
 		u64 logical_start, u32 csum, u32 csum_expected, int mirror_num)
 {
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_root *root = inode->root;
 
 	/* Output minus objectid, which is more meaningful */
 	if (root->objectid >= BTRFS_LAST_FREE_OBJECTID)
 		btrfs_warn_rl(root->fs_info,
 	"csum failed root %lld ino %lld off %llu csum 0x%08x expected csum 0x%08x mirror %d",
-			root->objectid, btrfs_ino(BTRFS_I(inode)),
+			root->objectid, btrfs_ino(inode),
 			logical_start, csum, csum_expected, mirror_num);
 	else
 		btrfs_warn_rl(root->fs_info,
 	"csum failed root %llu ino %llu off %llu csum 0x%08x expected csum 0x%08x mirror %d",
-			root->objectid, btrfs_ino(BTRFS_I(inode)),
+			root->objectid, btrfs_ino(inode),
 			logical_start, csum, csum_expected, mirror_num);
 }
 

fs/btrfs/compression.c

@@ -100,7 +100,7 @@ static struct bio *compressed_bio_alloc(struct block_device *bdev,
 	return btrfs_bio_alloc(bdev, first_byte >> 9, BIO_MAX_PAGES, gfp_flags);
 }
 
-static int check_compressed_csum(struct inode *inode,
+static int check_compressed_csum(struct btrfs_inode *inode,
 				 struct compressed_bio *cb,
 				 u64 disk_start)
 {
@@ -111,7 +111,7 @@ static int check_compressed_csum(struct inode *inode,
 	u32 csum;
 	u32 *cb_sum = &cb->sums;
 
-	if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)
+	if (inode->flags & BTRFS_INODE_NODATASUM)
 		return 0;
 
 	for (i = 0; i < cb->nr_pages; i++) {
@@ -125,7 +125,7 @@ static int check_compressed_csum(struct inode *inode,
 
 		if (csum != *cb_sum) {
 			btrfs_print_data_csum_error(inode, disk_start, csum,
-						    *cb_sum, cb->mirror_num);
+					*cb_sum, cb->mirror_num);
 			ret = -EIO;
 			goto fail;
 		}
@@ -165,7 +165,7 @@ static void end_compressed_bio_read(struct bio *bio)
 		goto out;
 
 	inode = cb->inode;
-	ret = check_compressed_csum(inode, cb,
+	ret = check_compressed_csum(BTRFS_I(inode), cb,
 				    (u64)bio->bi_iter.bi_sector << 9);
 	if (ret)
 		goto csum_failed;
@@ -911,43 +911,38 @@ static void free_workspaces(void)
 }
 
 /*
- * given an address space and start/len, compress the bytes.
+ * Given an address space and start and length, compress the bytes into @pages
+ * that are allocated on demand.
  *
- * pages are allocated to hold the compressed result and stored
- * in 'pages'
+ * @out_pages is an in/out parameter, holds maximum number of pages to allocate
+ * and returns number of actually allocated pages
  *
- * out_pages is used to return the number of pages allocated.  There
- * may be pages allocated even if we return an error
- *
- * total_in is used to return the number of bytes actually read.  It
- * may be smaller then len if we had to exit early because we
+ * @total_in is used to return the number of bytes actually read.  It
+ * may be smaller than the input length if we had to exit early because we
  * ran out of room in the pages array or because we cross the
  * max_out threshold.
  *
- * total_out is used to return the total number of compressed bytes
+ * @total_out is an in/out parameter, must be set to the input length and will
+ * be also used to return the total number of compressed bytes
  *
- * max_out tells us the max number of bytes that we're allowed to
+ * @max_out tells us the max number of bytes that we're allowed to
  * stuff into pages
  */
 int btrfs_compress_pages(int type, struct address_space *mapping,
-			 u64 start, unsigned long len,
-			 struct page **pages,
-			 unsigned long nr_dest_pages,
+			 u64 start, struct page **pages,
 			 unsigned long *out_pages,
 			 unsigned long *total_in,
-			 unsigned long *total_out,
-			 unsigned long max_out)
+			 unsigned long *total_out)
 {
 	struct list_head *workspace;
 	int ret;
 
 	workspace = find_workspace(type);
 
 	ret = btrfs_compress_op[type-1]->compress_pages(workspace, mapping,
-						      start, len, pages,
-						      nr_dest_pages, out_pages,
-						      total_in, total_out,
-						      max_out);
+						      start, pages,
+						      out_pages,
+						      total_in, total_out);
 	free_workspace(type, workspace);
 	return ret;
 }
@@ -1015,7 +1010,7 @@ void btrfs_exit_compress(void)
  *
  * total_out is the last byte of the buffer
  */
-int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
+int btrfs_decompress_buf2page(const char *buf, unsigned long buf_start,
 			      unsigned long total_out, u64 disk_start,
 			      struct bio *bio)
 {

fs/btrfs/compression.h

@@ -19,20 +19,32 @@
 #ifndef __BTRFS_COMPRESSION_
 #define __BTRFS_COMPRESSION_
 
+/*
+ * We want to make sure that amount of RAM required to uncompress an extent is
+ * reasonable, so we limit the total size in ram of a compressed extent to
+ * 128k.  This is a crucial number because it also controls how easily we can
+ * spread reads across cpus for decompression.
+ *
+ * We also want to make sure the amount of IO required to do a random read is
+ * reasonably small, so we limit the size of a compressed extent to 128k.
+ */
+
+/* Maximum length of compressed data stored on disk */
+#define BTRFS_MAX_COMPRESSED		(SZ_128K)
+/* Maximum size of data before compression */
+#define BTRFS_MAX_UNCOMPRESSED		(SZ_128K)
+
 void btrfs_init_compress(void);
 void btrfs_exit_compress(void);
 
 int btrfs_compress_pages(int type, struct address_space *mapping,
-			 u64 start, unsigned long len,
-			 struct page **pages,
-			 unsigned long nr_dest_pages,
+			 u64 start, struct page **pages,
 			 unsigned long *out_pages,
 			 unsigned long *total_in,
-			 unsigned long *total_out,
-			 unsigned long max_out);
+			 unsigned long *total_out);
 int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page,
 		     unsigned long start_byte, size_t srclen, size_t destlen);
-int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
+int btrfs_decompress_buf2page(const char *buf, unsigned long buf_start,
 			      unsigned long total_out, u64 disk_start,
 			      struct bio *bio);
 
@@ -59,13 +71,11 @@ struct btrfs_compress_op {
 
 	int (*compress_pages)(struct list_head *workspace,
 			      struct address_space *mapping,
-			      u64 start, unsigned long len,
+			      u64 start,
 			      struct page **pages,
-			      unsigned long nr_dest_pages,
 			      unsigned long *out_pages,
 			      unsigned long *total_in,
-			      unsigned long *total_out,
-			      unsigned long max_out);
+			      unsigned long *total_out);
 
 	int (*decompress_bio)(struct list_head *workspace,
 				 struct page **pages_in,

fs/btrfs/ctree.c

@@ -453,8 +453,6 @@ __tree_mod_log_insert(struct btrfs_fs_info *fs_info, struct tree_mod_elem *tm)
 	struct rb_node *parent = NULL;
 	struct tree_mod_elem *cur;
 
-	BUG_ON(!tm);
-
 	tm->seq = btrfs_inc_tree_mod_seq(fs_info);
 
 	tm_root = &fs_info->tree_mod_log;
@@ -4159,6 +4157,9 @@ static noinline int push_for_double_split(struct btrfs_trans_handle *trans,
 
 	/* try to push all the items before our slot into the next leaf */
 	slot = path->slots[0];
+	space_needed = data_size;
+	if (slot > 0)
+		space_needed -= btrfs_leaf_free_space(fs_info, path->nodes[0]);
 	ret = push_leaf_left(trans, root, path, 1, space_needed, 0, slot);
 	if (ret < 0)
 		return ret;
@@ -4214,6 +4215,10 @@ static noinline int split_leaf(struct btrfs_trans_handle *trans,
 		if (wret < 0)
 			return wret;
 		if (wret) {
+			space_needed = data_size;
+			if (slot > 0)
+				space_needed -= btrfs_leaf_free_space(fs_info,
+								      l);
 			wret = push_leaf_left(trans, root, path, space_needed,
 					      space_needed, 0, (u32)-1);
 			if (wret < 0)

fs/btrfs/ctree.h

@@ -2687,24 +2687,24 @@ enum btrfs_flush_state {
 };
 
 int btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len);
-int btrfs_alloc_data_chunk_ondemand(struct inode *inode, u64 bytes);
+int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes);
 void btrfs_free_reserved_data_space(struct inode *inode, u64 start, u64 len);
 void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start,
 					    u64 len);
 void btrfs_trans_release_metadata(struct btrfs_trans_handle *trans,
 				  struct btrfs_fs_info *fs_info);
 void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans);
 int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans,
-				  struct inode *inode);
-void btrfs_orphan_release_metadata(struct inode *inode);
+				  struct btrfs_inode *inode);
+void btrfs_orphan_release_metadata(struct btrfs_inode *inode);
 int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
 				     struct btrfs_block_rsv *rsv,
 				     int nitems,
 				     u64 *qgroup_reserved, bool use_global_rsv);
 void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info,
 				      struct btrfs_block_rsv *rsv);
-int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes);
-void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes);
+int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes);
+void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes);
 int btrfs_delalloc_reserve_space(struct inode *inode, u64 start, u64 len);
 void btrfs_delalloc_release_space(struct inode *inode, u64 start, u64 len);
 void btrfs_init_block_rsv(struct btrfs_block_rsv *rsv, unsigned short type);
@@ -2982,7 +2982,7 @@ int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir,
 			  const char *name, int name_len);
 int btrfs_insert_dir_item(struct btrfs_trans_handle *trans,
 			  struct btrfs_root *root, const char *name,
-			  int name_len, struct inode *dir,
+			  int name_len, struct btrfs_inode *dir,
 			  struct btrfs_key *location, u8 type, u64 index);
 struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans,
 					     struct btrfs_root *root,
@@ -3081,7 +3081,7 @@ int btrfs_csum_one_bio(struct inode *inode, struct bio *bio,
 		       u64 file_start, int contig);
 int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
 			     struct list_head *list, int search_commit);
-void btrfs_extent_item_to_extent_map(struct inode *inode,
+void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
 				     const struct btrfs_path *path,
 				     struct btrfs_file_extent_item *fi,
 				     const bool new_inline,
@@ -3100,9 +3100,9 @@ struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode,
 						    int delay_iput);
 void btrfs_wait_and_free_delalloc_work(struct btrfs_delalloc_work *work);
 
-struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *page,
-					   size_t pg_offset, u64 start, u64 len,
-					   int create);
+struct extent_map *btrfs_get_extent_fiemap(struct btrfs_inode *inode,
+		struct page *page, size_t pg_offset, u64 start,
+		u64 len, int create);
 noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 			      u64 *orig_start, u64 *orig_block_len,
 			      u64 *ram_bytes);
@@ -3123,13 +3123,13 @@ static inline void btrfs_force_ra(struct address_space *mapping,
 }
 
 struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry);
-int btrfs_set_inode_index(struct inode *dir, u64 *index);
+int btrfs_set_inode_index(struct btrfs_inode *dir, u64 *index);
 int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
 		       struct btrfs_root *root,
 		       struct btrfs_inode *dir, struct btrfs_inode *inode,
 		       const char *name, int name_len);
 int btrfs_add_link(struct btrfs_trans_handle *trans,
-		   struct inode *parent_inode, struct inode *inode,
+		   struct btrfs_inode *parent_inode, struct btrfs_inode *inode,
 		   const char *name, int name_len, int add_backref, u64 index);
 int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
 			struct btrfs_root *root,
@@ -3166,15 +3166,16 @@ void btrfs_destroy_cachep(void);
 long btrfs_ioctl_trans_end(struct file *file);
 struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
 			 struct btrfs_root *root, int *was_new);
-struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page,
-				    size_t pg_offset, u64 start, u64 end,
-				    int create);
+struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
+		struct page *page, size_t pg_offset,
+		u64 start, u64 end, int create);
 int btrfs_update_inode(struct btrfs_trans_handle *trans,
 			      struct btrfs_root *root,
 			      struct inode *inode);
 int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root, struct inode *inode);
-int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode);
+int btrfs_orphan_add(struct btrfs_trans_handle *trans,
+		struct btrfs_inode *inode);
 int btrfs_orphan_cleanup(struct btrfs_root *root);
 void btrfs_orphan_commit_root(struct btrfs_trans_handle *trans,
 			      struct btrfs_root *root);
@@ -3215,11 +3216,11 @@ ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen,
 int btrfs_auto_defrag_init(void);
 void btrfs_auto_defrag_exit(void);
 int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
-			   struct inode *inode);
+			   struct btrfs_inode *inode);
 int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info);
 void btrfs_cleanup_defrag_inodes(struct btrfs_fs_info *fs_info);
 int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync);
-void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
+void btrfs_drop_extent_cache(struct btrfs_inode *inode, u64 start, u64 end,
 			     int skip_pinned);
 extern const struct file_operations btrfs_file_operations;
 int __btrfs_drop_extents(struct btrfs_trans_handle *trans,
@@ -3233,7 +3234,7 @@ int btrfs_drop_extents(struct btrfs_trans_handle *trans,
 		       struct btrfs_root *root, struct inode *inode, u64 start,
 		       u64 end, int drop_cache);
 int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
-			      struct inode *inode, u64 start, u64 end);
+			      struct btrfs_inode *inode, u64 start, u64 end);
 int btrfs_release_file(struct inode *inode, struct file *file);
 int btrfs_dirty_pages(struct inode *inode, struct page **pages,
 		      size_t num_pages, loff_t pos, size_t write_bytes,

fs/btrfs/delayed-inode.c

@@ -1790,7 +1790,7 @@ int btrfs_fill_inode(struct inode *inode, u32 *rdev)
 
 	i_uid_write(inode, btrfs_stack_inode_uid(inode_item));
 	i_gid_write(inode, btrfs_stack_inode_gid(inode_item));
-	btrfs_i_size_write(inode, btrfs_stack_inode_size(inode_item));
+	btrfs_i_size_write(BTRFS_I(inode), btrfs_stack_inode_size(inode_item));
 	inode->i_mode = btrfs_stack_inode_mode(inode_item);
 	set_nlink(inode, btrfs_stack_inode_nlink(inode_item));
 	inode_set_bytes(inode, btrfs_stack_inode_nbytes(inode_item));