Merge branch 'for-linus-4.1' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs

Pull btrfs updates from Chris Mason:
 "I've been running these through a longer set of load tests because my
  commits change the free space cache writeout.  It fixes commit stalls
  on large filesystems (~20T space used and up) that we have been
  triggering here.  We were seeing new writers blocked for 10 seconds or
  more during commits, which is far from good.

  Josef and I fixed up ENOSPC aborts when deleting huge files (3T or
  more), that are triggered because our metadata reservations were not
  properly accounting for crcs and were not replenishing during the
  truncate.

  Also in this series, a number of qgroup fixes from Fujitsu and Dave
  Sterba collected most of the pending cleanups from the list"

* 'for-linus-4.1' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (93 commits)
  btrfs: quota: Update quota tree after qgroup relationship change.
  btrfs: quota: Automatically update related qgroups or mark INCONSISTENT flags when assigning/deleting a qgroup relations.
  btrfs: qgroup: clear STATUS_FLAG_ON in disabling quota.
  btrfs: Update btrfs qgroup status item when rescan is done.
  btrfs: qgroup: Fix dead judgement on qgroup_rescan_leaf() return value.
  btrfs: Don't allow subvolid >= (1 << BTRFS_QGROUP_LEVEL_SHIFT) to be created
  btrfs: Check qgroup level in kernel qgroup assign.
  btrfs: qgroup: allow to remove qgroup which has parent but no child.
  btrfs: qgroup: return EINVAL if level of parent is not higher than child's.
  btrfs: qgroup: do a reservation in a higher level.
  Btrfs: qgroup, Account data space in more proper timings.
  Btrfs: qgroup: Introduce a may_use to account space_info->bytes_may_use.
  Btrfs: qgroup: free reserved in exceeding quota.
  Btrfs: qgroup: cleanup, remove an unsued parameter in btrfs_create_qgroup().
  btrfs: qgroup: fix limit args override whole limit struct
  btrfs: qgroup: update limit info in function btrfs_run_qgroups().
  btrfs: qgroup: consolidate the parameter of fucntion update_qgroup_limit_item().
  btrfs: qgroup: update qgroup in memory at the same time when we update it in btree.
  btrfs: qgroup: inherit limit info from srcgroup in creating snapshot.
  btrfs: Support busy loop of write and delete
  ...

fs/btrfs/async-thread.c

@@ -87,7 +87,7 @@ BTRFS_WORK_HELPER(scrubwrc_helper);
 BTRFS_WORK_HELPER(scrubnc_helper);
 
 static struct __btrfs_workqueue *
-__btrfs_alloc_workqueue(const char *name, int flags, int max_active,
+__btrfs_alloc_workqueue(const char *name, unsigned int flags, int max_active,
 			 int thresh)
 {
 	struct __btrfs_workqueue *ret = kzalloc(sizeof(*ret), GFP_NOFS);
@@ -132,7 +132,7 @@ static inline void
 __btrfs_destroy_workqueue(struct __btrfs_workqueue *wq);
 
 struct btrfs_workqueue *btrfs_alloc_workqueue(const char *name,
-					      int flags,
+					      unsigned int flags,
 					      int max_active,
 					      int thresh)
 {

fs/btrfs/async-thread.h

@@ -66,7 +66,7 @@ BTRFS_WORK_HELPER_PROTO(scrubwrc_helper);
 BTRFS_WORK_HELPER_PROTO(scrubnc_helper);
 
 struct btrfs_workqueue *btrfs_alloc_workqueue(const char *name,
-					      int flags,
+					      unsigned int flags,
 					      int max_active,
 					      int thresh);
 void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t helper,

fs/btrfs/backref.c

@@ -1206,7 +1206,7 @@ int btrfs_check_shared(struct btrfs_trans_handle *trans,
 	struct ulist *roots = NULL;
 	struct ulist_iterator uiter;
 	struct ulist_node *node;
-	struct seq_list elem = {};
+	struct seq_list elem = SEQ_LIST_INIT(elem);
 	int ret = 0;
 
 	tmp = ulist_alloc(GFP_NOFS);
@@ -1610,7 +1610,7 @@ int iterate_extent_inodes(struct btrfs_fs_info *fs_info,
 	struct ulist *roots = NULL;
 	struct ulist_node *ref_node = NULL;
 	struct ulist_node *root_node = NULL;
-	struct seq_list tree_mod_seq_elem = {};
+	struct seq_list tree_mod_seq_elem = SEQ_LIST_INIT(tree_mod_seq_elem);
 	struct ulist_iterator ref_uiter;
 	struct ulist_iterator root_uiter;
 

fs/btrfs/btrfs_inode.h

@@ -66,7 +66,11 @@ struct btrfs_inode {
 	 */
 	struct btrfs_key location;
 
-	/* Lock for counters */
+	/*
+	 * Lock for counters and all fields used to determine if the inode is in
+	 * the log or not (last_trans, last_sub_trans, last_log_commit,
+	 * logged_trans).
+	 */
 	spinlock_t lock;
 
 	/* the extent_tree has caches of all the extent mappings to disk */
@@ -250,6 +254,9 @@ static inline bool btrfs_is_free_space_inode(struct inode *inode)
 
 static inline int btrfs_inode_in_log(struct inode *inode, u64 generation)
 {
+	int ret = 0;
+
+	spin_lock(&BTRFS_I(inode)->lock);
 	if (BTRFS_I(inode)->logged_trans == generation &&
 	    BTRFS_I(inode)->last_sub_trans <=
 	    BTRFS_I(inode)->last_log_commit &&
@@ -263,9 +270,10 @@ static inline int btrfs_inode_in_log(struct inode *inode, u64 generation)
 		 */
 		smp_mb();
 		if (list_empty(&BTRFS_I(inode)->extent_tree.modified_extents))
-			return 1;
+			ret = 1;
 	}
-	return 0;
+	spin_unlock(&BTRFS_I(inode)->lock);
+	return ret;
 }
 
 #define BTRFS_DIO_ORIG_BIO_SUBMITTED	0x1

fs/btrfs/check-integrity.c

@@ -2990,8 +2990,8 @@ static void __btrfsic_submit_bio(int rw, struct bio *bio)
 			       (unsigned long long)bio->bi_iter.bi_sector,
 			       dev_bytenr, bio->bi_bdev);
 
-		mapped_datav = kmalloc(sizeof(*mapped_datav) * bio->bi_vcnt,
-				       GFP_NOFS);
+		mapped_datav = kmalloc_array(bio->bi_vcnt,
+					     sizeof(*mapped_datav), GFP_NOFS);
 		if (!mapped_datav)
 			goto leave;
 		cur_bytenr = dev_bytenr;
@@ -3241,8 +3241,5 @@ void btrfsic_unmount(struct btrfs_root *root,
 
 	mutex_unlock(&btrfsic_mutex);
 
-	if (is_vmalloc_addr(state))
-		vfree(state);
-	else
-		kfree(state);
+	kvfree(state);
 }

fs/btrfs/compression.c

@@ -622,7 +622,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	cb->orig_bio = bio;
 
 	nr_pages = DIV_ROUND_UP(compressed_len, PAGE_CACHE_SIZE);
-	cb->compressed_pages = kzalloc(sizeof(struct page *) * nr_pages,
+	cb->compressed_pages = kcalloc(nr_pages, sizeof(struct page *),
 				       GFP_NOFS);
 	if (!cb->compressed_pages)
 		goto fail1;
@@ -750,7 +750,7 @@ static int comp_num_workspace[BTRFS_COMPRESS_TYPES];
 static atomic_t comp_alloc_workspace[BTRFS_COMPRESS_TYPES];
 static wait_queue_head_t comp_workspace_wait[BTRFS_COMPRESS_TYPES];
 
-static struct btrfs_compress_op *btrfs_compress_op[] = {
+static const struct btrfs_compress_op * const btrfs_compress_op[] = {
 	&btrfs_zlib_compress,
 	&btrfs_lzo_compress,
 };

fs/btrfs/compression.h

@@ -77,7 +77,7 @@ struct btrfs_compress_op {
 			  size_t srclen, size_t destlen);
 };
 
-extern struct btrfs_compress_op btrfs_zlib_compress;
-extern struct btrfs_compress_op btrfs_lzo_compress;
+extern const struct btrfs_compress_op btrfs_zlib_compress;
+extern const struct btrfs_compress_op btrfs_lzo_compress;
 
 #endif

fs/btrfs/ctree.c

@@ -578,7 +578,7 @@ tree_mod_log_insert_move(struct btrfs_fs_info *fs_info,
 	if (!tree_mod_need_log(fs_info, eb))
 		return 0;
 
-	tm_list = kzalloc(nr_items * sizeof(struct tree_mod_elem *), flags);
+	tm_list = kcalloc(nr_items, sizeof(struct tree_mod_elem *), flags);
 	if (!tm_list)
 		return -ENOMEM;
 
@@ -677,7 +677,7 @@ tree_mod_log_insert_root(struct btrfs_fs_info *fs_info,
 
 	if (log_removal && btrfs_header_level(old_root) > 0) {
 		nritems = btrfs_header_nritems(old_root);
-		tm_list = kzalloc(nritems * sizeof(struct tree_mod_elem *),
+		tm_list = kcalloc(nritems, sizeof(struct tree_mod_elem *),
 				  flags);
 		if (!tm_list) {
 			ret = -ENOMEM;
@@ -814,7 +814,7 @@ tree_mod_log_eb_copy(struct btrfs_fs_info *fs_info, struct extent_buffer *dst,
 	if (btrfs_header_level(dst) == 0 && btrfs_header_level(src) == 0)
 		return 0;
 
-	tm_list = kzalloc(nr_items * 2 * sizeof(struct tree_mod_elem *),
+	tm_list = kcalloc(nr_items * 2, sizeof(struct tree_mod_elem *),
 			  GFP_NOFS);
 	if (!tm_list)
 		return -ENOMEM;
@@ -905,8 +905,7 @@ tree_mod_log_free_eb(struct btrfs_fs_info *fs_info, struct extent_buffer *eb)
 		return 0;
 
 	nritems = btrfs_header_nritems(eb);
-	tm_list = kzalloc(nritems * sizeof(struct tree_mod_elem *),
-			  GFP_NOFS);
+	tm_list = kcalloc(nritems, sizeof(struct tree_mod_elem *), GFP_NOFS);
 	if (!tm_list)
 		return -ENOMEM;
 
@@ -1073,7 +1072,7 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
 			ret = btrfs_dec_ref(trans, root, buf, 1);
 			BUG_ON(ret); /* -ENOMEM */
 		}
-		clean_tree_block(trans, root, buf);
+		clean_tree_block(trans, root->fs_info, buf);
 		*last_ref = 1;
 	}
 	return 0;
@@ -1678,7 +1677,7 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
 			continue;
 		}
 
-		cur = btrfs_find_tree_block(root, blocknr);
+		cur = btrfs_find_tree_block(root->fs_info, blocknr);
 		if (cur)
 			uptodate = btrfs_buffer_uptodate(cur, gen, 0);
 		else
@@ -1943,7 +1942,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 
 		path->locks[level] = 0;
 		path->nodes[level] = NULL;
-		clean_tree_block(trans, root, mid);
+		clean_tree_block(trans, root->fs_info, mid);
 		btrfs_tree_unlock(mid);
 		/* once for the path */
 		free_extent_buffer(mid);
@@ -1997,7 +1996,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 		if (wret < 0 && wret != -ENOSPC)
 			ret = wret;
 		if (btrfs_header_nritems(right) == 0) {
-			clean_tree_block(trans, root, right);
+			clean_tree_block(trans, root->fs_info, right);
 			btrfs_tree_unlock(right);
 			del_ptr(root, path, level + 1, pslot + 1);
 			root_sub_used(root, right->len);
@@ -2041,7 +2040,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 		BUG_ON(wret == 1);
 	}
 	if (btrfs_header_nritems(mid) == 0) {
-		clean_tree_block(trans, root, mid);
+		clean_tree_block(trans, root->fs_info, mid);
 		btrfs_tree_unlock(mid);
 		del_ptr(root, path, level + 1, pslot);
 		root_sub_used(root, mid->len);
@@ -2259,7 +2258,7 @@ static void reada_for_search(struct btrfs_root *root,
 
 	search = btrfs_node_blockptr(node, slot);
 	blocksize = root->nodesize;
-	eb = btrfs_find_tree_block(root, search);
+	eb = btrfs_find_tree_block(root->fs_info, search);
 	if (eb) {
 		free_extent_buffer(eb);
 		return;
@@ -2319,7 +2318,7 @@ static noinline void reada_for_balance(struct btrfs_root *root,
 	if (slot > 0) {
 		block1 = btrfs_node_blockptr(parent, slot - 1);
 		gen = btrfs_node_ptr_generation(parent, slot - 1);
-		eb = btrfs_find_tree_block(root, block1);
+		eb = btrfs_find_tree_block(root->fs_info, block1);
 		/*
 		 * if we get -eagain from btrfs_buffer_uptodate, we
 		 * don't want to return eagain here.  That will loop
@@ -2332,7 +2331,7 @@ static noinline void reada_for_balance(struct btrfs_root *root,
 	if (slot + 1 < nritems) {
 		block2 = btrfs_node_blockptr(parent, slot + 1);
 		gen = btrfs_node_ptr_generation(parent, slot + 1);
-		eb = btrfs_find_tree_block(root, block2);
+		eb = btrfs_find_tree_block(root->fs_info, block2);
 		if (eb && btrfs_buffer_uptodate(eb, gen, 1) != 0)
 			block2 = 0;
 		free_extent_buffer(eb);
@@ -2450,7 +2449,7 @@ read_block_for_search(struct btrfs_trans_handle *trans,
 	blocknr = btrfs_node_blockptr(b, slot);
 	gen = btrfs_node_ptr_generation(b, slot);
 
-	tmp = btrfs_find_tree_block(root, blocknr);
+	tmp = btrfs_find_tree_block(root->fs_info, blocknr);
 	if (tmp) {
 		/* first we do an atomic uptodate check */
 		if (btrfs_buffer_uptodate(tmp, gen, 1) > 0) {
@@ -3126,7 +3125,8 @@ again:
  * higher levels
  *
  */
-static void fixup_low_keys(struct btrfs_root *root, struct btrfs_path *path,
+static void fixup_low_keys(struct btrfs_fs_info *fs_info,
+			   struct btrfs_path *path,
 			   struct btrfs_disk_key *key, int level)
 {
 	int i;
@@ -3137,7 +3137,7 @@ static void fixup_low_keys(struct btrfs_root *root, struct btrfs_path *path,
 		if (!path->nodes[i])
 			break;
 		t = path->nodes[i];
-		tree_mod_log_set_node_key(root->fs_info, t, tslot, 1);
+		tree_mod_log_set_node_key(fs_info, t, tslot, 1);
 		btrfs_set_node_key(t, key, tslot);
 		btrfs_mark_buffer_dirty(path->nodes[i]);
 		if (tslot != 0)
@@ -3151,7 +3151,8 @@ static void fixup_low_keys(struct btrfs_root *root, struct btrfs_path *path,
  * This function isn't completely safe. It's the caller's responsibility
  * that the new key won't break the order
  */
-void btrfs_set_item_key_safe(struct btrfs_root *root, struct btrfs_path *path,
+void btrfs_set_item_key_safe(struct btrfs_fs_info *fs_info,
+			     struct btrfs_path *path,
 			     struct btrfs_key *new_key)
 {
 	struct btrfs_disk_key disk_key;
@@ -3173,7 +3174,7 @@ void btrfs_set_item_key_safe(struct btrfs_root *root, struct btrfs_path *path,
 	btrfs_set_item_key(eb, &disk_key, slot);
 	btrfs_mark_buffer_dirty(eb);
 	if (slot == 0)
-		fixup_low_keys(root, path, &disk_key, 1);
+		fixup_low_keys(fs_info, path, &disk_key, 1);
 }
 
 /*
@@ -3692,7 +3693,7 @@ static noinline int __push_leaf_right(struct btrfs_trans_handle *trans,
 	if (left_nritems)
 		btrfs_mark_buffer_dirty(left);
 	else
-		clean_tree_block(trans, root, left);
+		clean_tree_block(trans, root->fs_info, left);
 
 	btrfs_mark_buffer_dirty(right);
 
@@ -3704,7 +3705,7 @@ static noinline int __push_leaf_right(struct btrfs_trans_handle *trans,
 	if (path->slots[0] >= left_nritems) {
 		path->slots[0] -= left_nritems;
 		if (btrfs_header_nritems(path->nodes[0]) == 0)
-			clean_tree_block(trans, root, path->nodes[0]);
+			clean_tree_block(trans, root->fs_info, path->nodes[0]);
 		btrfs_tree_unlock(path->nodes[0]);
 		free_extent_buffer(path->nodes[0]);
 		path->nodes[0] = right;
@@ -3928,10 +3929,10 @@ static noinline int __push_leaf_left(struct btrfs_trans_handle *trans,
 	if (right_nritems)
 		btrfs_mark_buffer_dirty(right);
 	else
-		clean_tree_block(trans, root, right);
+		clean_tree_block(trans, root->fs_info, right);
 
 	btrfs_item_key(right, &disk_key, 0);
-	fixup_low_keys(root, path, &disk_key, 1);
+	fixup_low_keys(root->fs_info, path, &disk_key, 1);
 
 	/* then fixup the leaf pointer in the path */
 	if (path->slots[0] < push_items) {
@@ -4168,6 +4169,7 @@ static noinline int split_leaf(struct btrfs_trans_handle *trans,
 	int mid;
 	int slot;
 	struct extent_buffer *right;
+	struct btrfs_fs_info *fs_info = root->fs_info;
 	int ret = 0;
 	int wret;
 	int split;
@@ -4271,10 +4273,10 @@ again:
 	btrfs_set_header_backref_rev(right, BTRFS_MIXED_BACKREF_REV);
 	btrfs_set_header_owner(right, root->root_key.objectid);
 	btrfs_set_header_level(right, 0);
-	write_extent_buffer(right, root->fs_info->fsid,
+	write_extent_buffer(right, fs_info->fsid,
 			    btrfs_header_fsid(), BTRFS_FSID_SIZE);
 
-	write_extent_buffer(right, root->fs_info->chunk_tree_uuid,
+	write_extent_buffer(right, fs_info->chunk_tree_uuid,
 			    btrfs_header_chunk_tree_uuid(right),
 			    BTRFS_UUID_SIZE);
 
@@ -4297,7 +4299,7 @@ again:
 			path->nodes[0] = right;
 			path->slots[0] = 0;
 			if (path->slots[1] == 0)
-				fixup_low_keys(root, path, &disk_key, 1);
+				fixup_low_keys(fs_info, path, &disk_key, 1);
 		}
 		btrfs_mark_buffer_dirty(right);
 		return ret;
@@ -4615,7 +4617,7 @@ void btrfs_truncate_item(struct btrfs_root *root, struct btrfs_path *path,
 		btrfs_set_disk_key_offset(&disk_key, offset + size_diff);
 		btrfs_set_item_key(leaf, &disk_key, slot);
 		if (slot == 0)
-			fixup_low_keys(root, path, &disk_key, 1);
+			fixup_low_keys(root->fs_info, path, &disk_key, 1);
 	}
 
 	item = btrfs_item_nr(slot);
@@ -4716,7 +4718,7 @@ void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path,
 
 	if (path->slots[0] == 0) {
 		btrfs_cpu_key_to_disk(&disk_key, cpu_key);
-		fixup_low_keys(root, path, &disk_key, 1);
+		fixup_low_keys(root->fs_info, path, &disk_key, 1);
 	}
 	btrfs_unlock_up_safe(path, 1);
 
@@ -4888,7 +4890,7 @@ static void del_ptr(struct btrfs_root *root, struct btrfs_path *path,
 		struct btrfs_disk_key disk_key;
 
 		btrfs_node_key(parent, &disk_key, 0);
-		fixup_low_keys(root, path, &disk_key, level + 1);
+		fixup_low_keys(root->fs_info, path, &disk_key, level + 1);
 	}
 	btrfs_mark_buffer_dirty(parent);
 }
@@ -4981,7 +4983,7 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 			btrfs_set_header_level(leaf, 0);
 		} else {
 			btrfs_set_path_blocking(path);
-			clean_tree_block(trans, root, leaf);
+			clean_tree_block(trans, root->fs_info, leaf);
 			btrfs_del_leaf(trans, root, path, leaf);
 		}
 	} else {
@@ -4990,7 +4992,7 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 			struct btrfs_disk_key disk_key;
 
 			btrfs_item_key(leaf, &disk_key, 0);
-			fixup_low_keys(root, path, &disk_key, 1);
+			fixup_low_keys(root->fs_info, path, &disk_key, 1);
 		}
 
 		/* delete the leaf if it is mostly empty */

fs/btrfs/ctree.h

@@ -1061,6 +1061,12 @@ struct btrfs_block_group_item {
 	__le64 flags;
 } __attribute__ ((__packed__));
 
+#define BTRFS_QGROUP_LEVEL_SHIFT		48
+static inline u64 btrfs_qgroup_level(u64 qgroupid)
+{
+	return qgroupid >> BTRFS_QGROUP_LEVEL_SHIFT;
+}
+
 /*
  * is subvolume quota turned on?
  */
@@ -1256,6 +1262,20 @@ struct btrfs_caching_control {
 	atomic_t count;
 };
 
+struct btrfs_io_ctl {
+	void *cur, *orig;
+	struct page *page;
+	struct page **pages;
+	struct btrfs_root *root;
+	struct inode *inode;
+	unsigned long size;
+	int index;
+	int num_pages;
+	int entries;
+	int bitmaps;
+	unsigned check_crcs:1;
+};
+
 struct btrfs_block_group_cache {
 	struct btrfs_key key;
 	struct btrfs_block_group_item item;
@@ -1321,6 +1341,9 @@ struct btrfs_block_group_cache {
 
 	/* For dirty block groups */
 	struct list_head dirty_list;
+	struct list_head io_list;
+
+	struct btrfs_io_ctl io_ctl;
 };
 
 /* delayed seq elem */
@@ -1329,6 +1352,8 @@ struct seq_list {
 	u64 seq;
 };
 
+#define SEQ_LIST_INIT(name)	{ .list = LIST_HEAD_INIT((name).list), .seq = 0 }
+
 enum btrfs_orphan_cleanup_state {
 	ORPHAN_CLEANUP_STARTED	= 1,
 	ORPHAN_CLEANUP_DONE	= 2,
@@ -1472,6 +1497,12 @@ struct btrfs_fs_info {
 	struct mutex chunk_mutex;
 	struct mutex volume_mutex;
 
+	/*
+	 * this is taken to make sure we don't set block groups ro after
+	 * the free space cache has been allocated on them
+	 */
+	struct mutex ro_block_group_mutex;
+
 	/* this is used during read/modify/write to make sure
 	 * no two ios are trying to mod the same stripe at the same
 	 * time
@@ -1513,6 +1544,7 @@ struct btrfs_fs_info {
 
 	spinlock_t delayed_iput_lock;
 	struct list_head delayed_iputs;
+	struct rw_semaphore delayed_iput_sem;
 
 	/* this protects tree_mod_seq_list */
 	spinlock_t tree_mod_seq_lock;
@@ -3295,6 +3327,9 @@ static inline gfp_t btrfs_alloc_write_mask(struct address_space *mapping)
 }
 
 /* extent-tree.c */
+
+u64 btrfs_csum_bytes_to_leaves(struct btrfs_root *root, u64 csum_bytes);
+
 static inline u64 btrfs_calc_trans_metadata_size(struct btrfs_root *root,
 						 unsigned num_items)
 {
@@ -3385,6 +3420,8 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 			 u64 bytenr, u64 num_bytes, u64 parent,
 			 u64 root_objectid, u64 owner, u64 offset, int no_quota);
 
+int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans,
+				   struct btrfs_root *root);
 int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans,
 				    struct btrfs_root *root);
 int btrfs_setup_space_cache(struct btrfs_trans_handle *trans,
@@ -3417,7 +3454,7 @@ enum btrfs_reserve_flush_enum {
 	BTRFS_RESERVE_FLUSH_ALL,
 };
 
-int btrfs_check_data_free_space(struct inode *inode, u64 bytes);
+int btrfs_check_data_free_space(struct inode *inode, u64 bytes, u64 write_bytes);
 void btrfs_free_reserved_data_space(struct inode *inode, u64 bytes);
 void btrfs_trans_release_metadata(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root);
@@ -3440,6 +3477,7 @@ struct btrfs_block_rsv *btrfs_alloc_block_rsv(struct btrfs_root *root,
 					      unsigned short type);
 void btrfs_free_block_rsv(struct btrfs_root *root,
 			  struct btrfs_block_rsv *rsv);
+void __btrfs_free_block_rsv(struct btrfs_block_rsv *rsv);
 int btrfs_block_rsv_add(struct btrfs_root *root,
 			struct btrfs_block_rsv *block_rsv, u64 num_bytes,
 			enum btrfs_reserve_flush_enum flush);
@@ -3486,7 +3524,8 @@ int btrfs_previous_item(struct btrfs_root *root,
 			int type);
 int btrfs_previous_extent_item(struct btrfs_root *root,
 			struct btrfs_path *path, u64 min_objectid);
-void btrfs_set_item_key_safe(struct btrfs_root *root, struct btrfs_path *path,
+void btrfs_set_item_key_safe(struct btrfs_fs_info *fs_info,
+			     struct btrfs_path *path,
 			     struct btrfs_key *new_key);
 struct extent_buffer *btrfs_root_node(struct btrfs_root *root);
 struct extent_buffer *btrfs_lock_root_node(struct btrfs_root *root);
@@ -4180,7 +4219,8 @@ int btree_readahead_hook(struct btrfs_root *root, struct extent_buffer *eb,
 static inline int is_fstree(u64 rootid)
 {
 	if (rootid == BTRFS_FS_TREE_OBJECTID ||
-	    (s64)rootid >= (s64)BTRFS_FIRST_FREE_OBJECTID)
+	    ((s64)rootid >= (s64)BTRFS_FIRST_FREE_OBJECTID &&
+	      !btrfs_qgroup_level(rootid)))
 		return 1;
 	return 0;
 }

fs/btrfs/delayed-inode.c

@@ -1383,7 +1383,7 @@ out:
 
 
 static int btrfs_wq_run_delayed_node(struct btrfs_delayed_root *delayed_root,
-				     struct btrfs_root *root, int nr)
+				     struct btrfs_fs_info *fs_info, int nr)
 {
 	struct btrfs_async_delayed_work *async_work;
 
@@ -1399,7 +1399,7 @@ static int btrfs_wq_run_delayed_node(struct btrfs_delayed_root *delayed_root,
 			btrfs_async_run_delayed_root, NULL, NULL);
 	async_work->nr = nr;
 
-	btrfs_queue_work(root->fs_info->delayed_workers, &async_work->work);
+	btrfs_queue_work(fs_info->delayed_workers, &async_work->work);
 	return 0;
 }
 
@@ -1426,6 +1426,7 @@ static int could_end_wait(struct btrfs_delayed_root *delayed_root, int seq)
 void btrfs_balance_delayed_items(struct btrfs_root *root)
 {
 	struct btrfs_delayed_root *delayed_root;
+	struct btrfs_fs_info *fs_info = root->fs_info;
 
 	delayed_root = btrfs_get_delayed_root(root);
 
@@ -1438,7 +1439,7 @@ void btrfs_balance_delayed_items(struct btrfs_root *root)
 
 		seq = atomic_read(&delayed_root->items_seq);
 
-		ret = btrfs_wq_run_delayed_node(delayed_root, root, 0);
+		ret = btrfs_wq_run_delayed_node(delayed_root, fs_info, 0);
 		if (ret)
 			return;
 
@@ -1447,7 +1448,7 @@ void btrfs_balance_delayed_items(struct btrfs_root *root)
 		return;
 	}
 
-	btrfs_wq_run_delayed_node(delayed_root, root, BTRFS_DELAYED_BATCH);
+	btrfs_wq_run_delayed_node(delayed_root, fs_info, BTRFS_DELAYED_BATCH);
 }
 
 /* Will return 0 or -ENOMEM */

fs/btrfs/delayed-ref.c

@@ -489,11 +489,13 @@ update_existing_ref(struct btrfs_trans_handle *trans,
  * existing and update must have the same bytenr
  */
 static noinline void
-update_existing_head_ref(struct btrfs_delayed_ref_node *existing,
+update_existing_head_ref(struct btrfs_delayed_ref_root *delayed_refs,
+			 struct btrfs_delayed_ref_node *existing,
 			 struct btrfs_delayed_ref_node *update)
 {
 	struct btrfs_delayed_ref_head *existing_ref;
 	struct btrfs_delayed_ref_head *ref;
+	int old_ref_mod;
 
 	existing_ref = btrfs_delayed_node_to_head(existing);
 	ref = btrfs_delayed_node_to_head(update);
@@ -541,7 +543,20 @@ update_existing_head_ref(struct btrfs_delayed_ref_node *existing,
 	 * only need the lock for this case cause we could be processing it
 	 * currently, for refs we just added we know we're a-ok.
 	 */
+	old_ref_mod = existing_ref->total_ref_mod;
 	existing->ref_mod += update->ref_mod;
+	existing_ref->total_ref_mod += update->ref_mod;
+
+	/*
+	 * If we are going to from a positive ref mod to a negative or vice
+	 * versa we need to make sure to adjust pending_csums accordingly.
+	 */
+	if (existing_ref->is_data) {
+		if (existing_ref->total_ref_mod >= 0 && old_ref_mod < 0)
+			delayed_refs->pending_csums -= existing->num_bytes;
+		if (existing_ref->total_ref_mod < 0 && old_ref_mod >= 0)
+			delayed_refs->pending_csums += existing->num_bytes;
+	}
 	spin_unlock(&existing_ref->lock);
 }
 
@@ -605,6 +620,7 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
 	head_ref->is_data = is_data;
 	head_ref->ref_root = RB_ROOT;
 	head_ref->processing = 0;
+	head_ref->total_ref_mod = count_mod;
 
 	spin_lock_init(&head_ref->lock);
 	mutex_init(&head_ref->mutex);
@@ -614,7 +630,7 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
 	existing = htree_insert(&delayed_refs->href_root,
 				&head_ref->href_node);
 	if (existing) {
-		update_existing_head_ref(&existing->node, ref);
+		update_existing_head_ref(delayed_refs, &existing->node, ref);
 		/*
 		 * we've updated the existing ref, free the newly
 		 * allocated ref
@@ -622,6 +638,8 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
 		kmem_cache_free(btrfs_delayed_ref_head_cachep, head_ref);
 		head_ref = existing;
 	} else {
+		if (is_data && count_mod < 0)
+			delayed_refs->pending_csums += num_bytes;
 		delayed_refs->num_heads++;
 		delayed_refs->num_heads_ready++;
 		atomic_inc(&delayed_refs->num_entries);

fs/btrfs/delayed-ref.h

@@ -88,6 +88,14 @@ struct btrfs_delayed_ref_head {
 	struct rb_node href_node;
 
 	struct btrfs_delayed_extent_op *extent_op;
+
+	/*
+	 * This is used to track the final ref_mod from all the refs associated
+	 * with this head ref, this is not adjusted as delayed refs are run,
+	 * this is meant to track if we need to do the csum accounting or not.
+	 */
+	int total_ref_mod;
+
 	/*
 	 * when a new extent is allocated, it is just reserved in memory
 	 * The actual extent isn't inserted into the extent allocation tree
@@ -138,6 +146,8 @@ struct btrfs_delayed_ref_root {
 	/* total number of head nodes ready for processing */
 	unsigned long num_heads_ready;
 
+	u64 pending_csums;
+
 	/*
 	 * set when the tree is flushing before a transaction commit,
 	 * used by the throttling code to decide if new updates need

fs/btrfs/dev-replace.c

@@ -670,8 +670,8 @@ void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info,
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED:
 		srcdev = dev_replace->srcdev;
-		args->status.progress_1000 = div64_u64(dev_replace->cursor_left,
-			div64_u64(btrfs_device_get_total_bytes(srcdev), 1000));
+		args->status.progress_1000 = div_u64(dev_replace->cursor_left,
+			div_u64(btrfs_device_get_total_bytes(srcdev), 1000));
 		break;
 	}
 	btrfs_dev_replace_unlock(dev_replace);
@@ -806,7 +806,7 @@ static int btrfs_dev_replace_kthread(void *data)
 		btrfs_dev_replace_status(fs_info, status_args);
 		progress = status_args->status.progress_1000;
 		kfree(status_args);
-		do_div(progress, 10);
+		progress = div_u64(progress, 10);
 		printk_in_rcu(KERN_INFO
 			"BTRFS: continuing dev_replace from %s (devid %llu) to %s @%u%%\n",
 			dev_replace->srcdev->missing ? "<missing disk>" :

fs/btrfs/disk-io.h

@@ -52,7 +52,7 @@ int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr,
 struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root,
 						   u64 bytenr);
 void clean_tree_block(struct btrfs_trans_handle *trans,
-		      struct btrfs_root *root, struct extent_buffer *buf);
+		      struct btrfs_fs_info *fs_info, struct extent_buffer *buf);
 int open_ctree(struct super_block *sb,
 	       struct btrfs_fs_devices *fs_devices,
 	       char *options);
@@ -61,7 +61,7 @@ int write_ctree_super(struct btrfs_trans_handle *trans,
 		      struct btrfs_root *root, int max_mirrors);
 struct buffer_head *btrfs_read_dev_super(struct block_device *bdev);
 int btrfs_commit_super(struct btrfs_root *root);
-struct extent_buffer *btrfs_find_tree_block(struct btrfs_root *root,
+struct extent_buffer *btrfs_find_tree_block(struct btrfs_fs_info *fs_info,
 					    u64 bytenr);
 struct btrfs_root *btrfs_read_fs_root(struct btrfs_root *tree_root,
 				      struct btrfs_key *location);

fs/btrfs/extent_io.c

@@ -4514,8 +4514,11 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		}
 		ret = fiemap_fill_next_extent(fieinfo, em_start, disko,
 					      em_len, flags);
-		if (ret)
+		if (ret) {
+			if (ret == 1)
+				ret = 0;
 			goto out_free;
+		}
 	}
 out_free:
 	free_extent_map(em);

fs/btrfs/extent_io.h

@@ -97,7 +97,7 @@ struct extent_io_tree {
 	u64 dirty_bytes;
 	int track_uptodate;
 	spinlock_t lock;
-	struct extent_io_ops *ops;
+	const struct extent_io_ops *ops;
 };
 
 struct extent_state {

fs/btrfs/file-item.c

@@ -185,8 +185,8 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
 	nblocks = bio->bi_iter.bi_size >> inode->i_sb->s_blocksize_bits;
 	if (!dst) {
 		if (nblocks * csum_size > BTRFS_BIO_INLINE_CSUM_SIZE) {
-			btrfs_bio->csum_allocated = kmalloc(nblocks * csum_size,
-							    GFP_NOFS);
+			btrfs_bio->csum_allocated = kmalloc_array(nblocks,
+					csum_size, GFP_NOFS);
 			if (!btrfs_bio->csum_allocated) {
 				btrfs_free_path(path);
 				return -ENOMEM;
@@ -553,7 +553,7 @@ static noinline void truncate_one_csum(struct btrfs_root *root,
 		btrfs_truncate_item(root, path, new_size, 0);
 
 		key->offset = end_byte;
-		btrfs_set_item_key_safe(root, path, key);
+		btrfs_set_item_key_safe(root->fs_info, path, key);
 	} else {
 		BUG();
 	}

fs/btrfs/file.c

@@ -273,11 +273,7 @@ void btrfs_cleanup_defrag_inodes(struct btrfs_fs_info *fs_info)
 		defrag = rb_entry(node, struct inode_defrag, rb_node);
 		kmem_cache_free(btrfs_inode_defrag_cachep, defrag);
 
-		if (need_resched()) {
-			spin_unlock(&fs_info->defrag_inodes_lock);
-			cond_resched();
-			spin_lock(&fs_info->defrag_inodes_lock);
-		}
+		cond_resched_lock(&fs_info->defrag_inodes_lock);
 
 		node = rb_first(&fs_info->defrag_inodes);
 	}
@@ -868,7 +864,7 @@ next_slot:
 
 			memcpy(&new_key, &key, sizeof(new_key));
 			new_key.offset = end;
-			btrfs_set_item_key_safe(root, path, &new_key);
+			btrfs_set_item_key_safe(root->fs_info, path, &new_key);
 
 			extent_offset += end - key.offset;
 			btrfs_set_file_extent_offset(leaf, fi, extent_offset);
@@ -1126,7 +1122,7 @@ again:
 				     ino, bytenr, orig_offset,
 				     &other_start, &other_end)) {
 			new_key.offset = end;
-			btrfs_set_item_key_safe(root, path, &new_key);
+			btrfs_set_item_key_safe(root->fs_info, path, &new_key);
 			fi = btrfs_item_ptr(leaf, path->slots[0],
 					    struct btrfs_file_extent_item);
 			btrfs_set_file_extent_generation(leaf, fi,
@@ -1160,7 +1156,7 @@ again:
 							 trans->transid);
 			path->slots[0]++;
 			new_key.offset = start;
-			btrfs_set_item_key_safe(root, path, &new_key);
+			btrfs_set_item_key_safe(root->fs_info, path, &new_key);
 
 			fi = btrfs_item_ptr(leaf, path->slots[0],
 					    struct btrfs_file_extent_item);
@@ -1485,7 +1481,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 			PAGE_CACHE_SIZE / (sizeof(struct page *)));
 	nrptrs = min(nrptrs, current->nr_dirtied_pause - current->nr_dirtied);
 	nrptrs = max(nrptrs, 8);
-	pages = kmalloc(nrptrs * sizeof(struct page *), GFP_KERNEL);
+	pages = kmalloc_array(nrptrs, sizeof(struct page *), GFP_KERNEL);
 	if (!pages)
 		return -ENOMEM;
 
@@ -1514,7 +1510,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 		}
 
 		reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
-		ret = btrfs_check_data_free_space(inode, reserve_bytes);
+		ret = btrfs_check_data_free_space(inode, reserve_bytes, write_bytes);
 		if (ret == -ENOSPC &&
 		    (BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
 					      BTRFS_INODE_PREALLOC))) {
@@ -1635,8 +1631,8 @@ again:
 			btrfs_end_write_no_snapshoting(root);
 
 		if (only_release_metadata && copied > 0) {
-			u64 lockstart = round_down(pos, root->sectorsize);
-			u64 lockend = lockstart +
+			lockstart = round_down(pos, root->sectorsize);
+			lockend = lockstart +
 				(dirty_pages << PAGE_CACHE_SHIFT) - 1;
 
 			set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
@@ -1809,7 +1805,9 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	 * otherwise subsequent syncs to a file that's been synced in this
 	 * transaction will appear to have already occured.
 	 */
+	spin_lock(&BTRFS_I(inode)->lock);
 	BTRFS_I(inode)->last_sub_trans = root->log_transid;
+	spin_unlock(&BTRFS_I(inode)->lock);
 	if (num_written > 0) {
 		err = generic_write_sync(file, pos, num_written);
 		if (err < 0)
@@ -2162,7 +2160,7 @@ static int fill_holes(struct btrfs_trans_handle *trans, struct inode *inode,
 		u64 num_bytes;
 
 		key.offset = offset;
-		btrfs_set_item_key_safe(root, path, &key);
+		btrfs_set_item_key_safe(root->fs_info, path, &key);
 		fi = btrfs_item_ptr(leaf, path->slots[0],
 				    struct btrfs_file_extent_item);
 		num_bytes = btrfs_file_extent_num_bytes(leaf, fi) + end -
@@ -2545,7 +2543,6 @@ static long btrfs_fallocate(struct file *file, int mode,
 {
 	struct inode *inode = file_inode(file);
 	struct extent_state *cached_state = NULL;
-	struct btrfs_root *root = BTRFS_I(inode)->root;
 	u64 cur_offset;
 	u64 last_byte;
 	u64 alloc_start;
@@ -2570,14 +2567,9 @@ static long btrfs_fallocate(struct file *file, int mode,
 	 * Make sure we have enough space before we do the
 	 * allocation.
 	 */
-	ret = btrfs_check_data_free_space(inode, alloc_end - alloc_start);
+	ret = btrfs_check_data_free_space(inode, alloc_end - alloc_start, alloc_end - alloc_start);
 	if (ret)
 		return ret;
-	if (root->fs_info->quota_enabled) {
-		ret = btrfs_qgroup_reserve(root, alloc_end - alloc_start);
-		if (ret)
-			goto out_reserve_fail;
-	}
 
 	mutex_lock(&inode->i_mutex);
 	ret = inode_newsize_ok(inode, alloc_end);
@@ -2667,23 +2659,35 @@ static long btrfs_fallocate(struct file *file, int mode,
 							1 << inode->i_blkbits,
 							offset + len,
 							&alloc_hint);
-
-			if (ret < 0) {
-				free_extent_map(em);
-				break;
-			}
 		} else if (actual_end > inode->i_size &&
 			   !(mode & FALLOC_FL_KEEP_SIZE)) {
+			struct btrfs_trans_handle *trans;
+			struct btrfs_root *root = BTRFS_I(inode)->root;
+
 			/*
 			 * We didn't need to allocate any more space, but we
 			 * still extended the size of the file so we need to
-			 * update i_size.
+			 * update i_size and the inode item.
 			 */
-			inode->i_ctime = CURRENT_TIME;
-			i_size_write(inode, actual_end);
-			btrfs_ordered_update_i_size(inode, actual_end, NULL);
+			trans = btrfs_start_transaction(root, 1);
+			if (IS_ERR(trans)) {
+				ret = PTR_ERR(trans);
+			} else {
+				inode->i_ctime = CURRENT_TIME;
+				i_size_write(inode, actual_end);
+				btrfs_ordered_update_i_size(inode, actual_end,
+							    NULL);
+				ret = btrfs_update_inode(trans, root, inode);
+				if (ret)
+					btrfs_end_transaction(trans, root);
+				else
+					ret = btrfs_end_transaction(trans,
+								    root);
+			}
 		}
 		free_extent_map(em);
+		if (ret < 0)
+			break;
 
 		cur_offset = last_byte;
 		if (cur_offset >= alloc_end) {
@@ -2695,9 +2699,6 @@ static long btrfs_fallocate(struct file *file, int mode,
 			     &cached_state, GFP_NOFS);
 out:
 	mutex_unlock(&inode->i_mutex);
-	if (root->fs_info->quota_enabled)
-		btrfs_qgroup_free(root, alloc_end - alloc_start);
-out_reserve_fail:
 	/* Let go of our reservation. */
 	btrfs_free_reserved_data_space(inode, alloc_end - alloc_start);
 	return ret;