Merge branch 'misc-4.10' into for-chris-4.10-20161130

33 files changed, 782 insertions, 827 deletions

diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index 8e99251650b3..86f681fd200d 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -1539,7 +1539,7 @@ static int btrfsic_map_block(struct btrfsic_state *state, u64 bytenr, u32 len,
 	struct btrfs_device *device;
 
 	length = len;
-	ret = btrfs_map_block(state->root->fs_info, READ,
+	ret = btrfs_map_block(state->root->fs_info, BTRFS_MAP_READ,
 			      bytenr, &length, &multi, mirror_num);
 
 	if (ret) {
@@ -2819,10 +2819,11 @@ static void __btrfsic_submit_bio(struct bio *bio)
 	 * btrfsic_mount(), this might return NULL */
 	dev_state = btrfsic_dev_state_lookup(bio->bi_bdev);
 	if (NULL != dev_state &&
-	    (bio_op(bio) == REQ_OP_WRITE) && NULL != bio->bi_io_vec) {
+	    (bio_op(bio) == REQ_OP_WRITE) && bio_has_data(bio)) {
 		unsigned int i;
 		u64 dev_bytenr;
 		u64 cur_bytenr;
+		struct bio_vec *bvec;
 		int bio_is_patched;
 		char **mapped_datav;
 
@@ -2840,32 +2841,23 @@ static void __btrfsic_submit_bio(struct bio *bio)
 		if (!mapped_datav)
 			goto leave;
 		cur_bytenr = dev_bytenr;
-		for (i = 0; i < bio->bi_vcnt; i++) {
-			BUG_ON(bio->bi_io_vec[i].bv_len != PAGE_SIZE);
-			mapped_datav[i] = kmap(bio->bi_io_vec[i].bv_page);
-			if (!mapped_datav[i]) {
-				while (i > 0) {
-					i--;
-					kunmap(bio->bi_io_vec[i].bv_page);
-				}
-				kfree(mapped_datav);
-				goto leave;
-			}
+
+		bio_for_each_segment_all(bvec, bio, i) {
+			BUG_ON(bvec->bv_len != PAGE_SIZE);
+			mapped_datav[i] = kmap(bvec->bv_page);
+
 			if (dev_state->state->print_mask &
 			    BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH_VERBOSE)
 				pr_info("#%u: bytenr=%llu, len=%u, offset=%u\n",
-				       i, cur_bytenr, bio->bi_io_vec[i].bv_len,
-				       bio->bi_io_vec[i].bv_offset);
-			cur_bytenr += bio->bi_io_vec[i].bv_len;
+				       i, cur_bytenr, bvec->bv_len, bvec->bv_offset);
+			cur_bytenr += bvec->bv_len;
 		}
 		btrfsic_process_written_block(dev_state, dev_bytenr,
 					      mapped_datav, bio->bi_vcnt,
 					      bio, &bio_is_patched,
 					      NULL, bio->bi_opf);
-		while (i > 0) {
-			i--;
-			kunmap(bio->bi_io_vec[i].bv_page);
-		}
+		bio_for_each_segment_all(bvec, bio, i)
+			kunmap(bvec->bv_page);
 		kfree(mapped_datav);
 	} else if (NULL != dev_state && (bio->bi_opf & REQ_PREFLUSH)) {
 		if (dev_state->state->print_mask &
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index d4d8b7e36b2f..ae4c000cbffc 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -81,9 +81,9 @@ struct compressed_bio {
 	u32 sums;
 };
 
-static int btrfs_decompress_biovec(int type, struct page **pages_in,
-				   u64 disk_start, struct bio_vec *bvec,
-				   int vcnt, size_t srclen);
+static int btrfs_decompress_bio(int type, struct page **pages_in,
+				   u64 disk_start, struct bio *orig_bio,
+				   size_t srclen);
 
 static inline int compressed_bio_size(struct btrfs_root *root,
 				      unsigned long disk_size)
@@ -120,7 +120,7 @@ static int check_compressed_csum(struct inode *inode,
 
 		kaddr = kmap_atomic(page);
 		csum = btrfs_csum_data(kaddr, csum, PAGE_SIZE);
-		btrfs_csum_final(csum, (char *)&csum);
+		btrfs_csum_final(csum, (u8 *)&csum);
 		kunmap_atomic(kaddr);
 
 		if (csum != *cb_sum) {
@@ -175,11 +175,10 @@ static void end_compressed_bio_read(struct bio *bio)
 	/* ok, we're the last bio for this extent, lets start
 	 * the decompression.
 	 */
-	ret = btrfs_decompress_biovec(cb->compress_type,
+	ret = btrfs_decompress_bio(cb->compress_type,
 				      cb->compressed_pages,
 				      cb->start,
-				      cb->orig_bio->bi_io_vec,
-				      cb->orig_bio->bi_vcnt,
+				      cb->orig_bio,
 				      cb->compressed_len);
 csum_failed:
 	if (ret)
@@ -446,6 +445,13 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start,
 	return 0;
 }
 
+static u64 bio_end_offset(struct bio *bio)
+{
+	struct bio_vec *last = &bio->bi_io_vec[bio->bi_vcnt - 1];
+
+	return page_offset(last->bv_page) + last->bv_len + last->bv_offset;
+}
+
 static noinline int add_ra_bio_pages(struct inode *inode,
 				     u64 compressed_end,
 				     struct compressed_bio *cb)
@@ -464,8 +470,7 @@ static noinline int add_ra_bio_pages(struct inode *inode,
 	u64 end;
 	int misses = 0;
 
-	page = cb->orig_bio->bi_io_vec[cb->orig_bio->bi_vcnt - 1].bv_page;
-	last_offset = (page_offset(page) + PAGE_SIZE);
+	last_offset = bio_end_offset(cb->orig_bio);
 	em_tree = &BTRFS_I(inode)->extent_tree;
 	tree = &BTRFS_I(inode)->io_tree;
 
@@ -563,7 +568,6 @@ next:
  *
  * bio->bi_iter.bi_sector points to the compressed extent on disk
  * bio->bi_io_vec points to all of the inode pages
- * bio->bi_vcnt is a count of pages
  *
  * After the compressed pages are read, we copy the bytes into the
  * bio we were passed and then call the bio end_io calls
@@ -575,7 +579,6 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	struct extent_map_tree *em_tree;
 	struct compressed_bio *cb;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
-	unsigned long uncompressed_len = bio->bi_vcnt * PAGE_SIZE;
 	unsigned long compressed_len;
 	unsigned long nr_pages;
 	unsigned long pg_index;
@@ -620,7 +623,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	free_extent_map(em);
 	em = NULL;
 
-	cb->len = uncompressed_len;
+	cb->len = bio->bi_iter.bi_size;
 	cb->compressed_len = compressed_len;
 	cb->compress_type = extent_compress_type(bio_flags);
 	cb->orig_bio = bio;
@@ -648,8 +651,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	add_ra_bio_pages(inode, em_start + em_len, cb);
 
 	/* include any pages we added in add_ra-bio_pages */
-	uncompressed_len = bio->bi_vcnt * PAGE_SIZE;
-	cb->len = uncompressed_len;
+	cb->len = bio->bi_iter.bi_size;
 
 	comp_bio = compressed_bio_alloc(bdev, cur_disk_byte, GFP_NOFS);
 	if (!comp_bio)
@@ -959,9 +961,7 @@ int btrfs_compress_pages(int type, struct address_space *mapping,
  *
  * disk_start is the starting logical offset of this array in the file
  *
- * bvec is a bio_vec of pages from the file that we want to decompress into
- *
- * vcnt is the count of pages in the biovec
+ * orig_bio contains the pages from the file that we want to decompress into
  *
  * srclen is the number of bytes in pages_in
  *
@@ -970,18 +970,18 @@ int btrfs_compress_pages(int type, struct address_space *mapping,
  * be contiguous.  They all correspond to the range of bytes covered by
  * the compressed extent.
  */
-static int btrfs_decompress_biovec(int type, struct page **pages_in,
-				   u64 disk_start, struct bio_vec *bvec,
-				   int vcnt, size_t srclen)
+static int btrfs_decompress_bio(int type, struct page **pages_in,
+				   u64 disk_start, struct bio *orig_bio,
+				   size_t srclen)
 {
 	struct list_head *workspace;
 	int ret;
 
 	workspace = find_workspace(type);
 
-	ret = btrfs_compress_op[type-1]->decompress_biovec(workspace, pages_in,
-							 disk_start,
-							 bvec, vcnt, srclen);
+	ret = btrfs_compress_op[type-1]->decompress_bio(workspace, pages_in,
+							 disk_start, orig_bio,
+							 srclen);
 	free_workspace(type, workspace);
 	return ret;
 }
@@ -1021,9 +1021,7 @@ void btrfs_exit_compress(void)
  */
 int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
 			      unsigned long total_out, u64 disk_start,
-			      struct bio_vec *bvec, int vcnt,
-			      unsigned long *pg_index,
-			      unsigned long *pg_offset)
+			      struct bio *bio)
 {
 	unsigned long buf_offset;
 	unsigned long current_buf_start;
@@ -1031,13 +1029,13 @@ int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
 	unsigned long working_bytes = total_out - buf_start;
 	unsigned long bytes;
 	char *kaddr;
-	struct page *page_out = bvec[*pg_index].bv_page;
+	struct bio_vec bvec = bio_iter_iovec(bio, bio->bi_iter);
 
 	/*
 	 * start byte is the first byte of the page we're currently
 	 * copying into relative to the start of the compressed data.
 	 */
-	start_byte = page_offset(page_out) - disk_start;
+	start_byte = page_offset(bvec.bv_page) - disk_start;
 
 	/* we haven't yet hit data corresponding to this page */
 	if (total_out <= start_byte)
@@ -1057,80 +1055,46 @@ int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
 
 	/* copy bytes from the working buffer into the pages */
 	while (working_bytes > 0) {
-		bytes = min(PAGE_SIZE - *pg_offset,
-			    PAGE_SIZE - buf_offset);
+		bytes = min_t(unsigned long, bvec.bv_len,
+				PAGE_SIZE - buf_offset);
 		bytes = min(bytes, working_bytes);
-		kaddr = kmap_atomic(page_out);
-		memcpy(kaddr + *pg_offset, buf + buf_offset, bytes);
+
+		kaddr = kmap_atomic(bvec.bv_page);
+		memcpy(kaddr + bvec.bv_offset, buf + buf_offset, bytes);
 		kunmap_atomic(kaddr);
-		flush_dcache_page(page_out);
+		flush_dcache_page(bvec.bv_page);
 
-		*pg_offset += bytes;
 		buf_offset += bytes;
 		working_bytes -= bytes;
 		current_buf_start += bytes;
 
 		/* check if we need to pick another page */
-		if (*pg_offset == PAGE_SIZE) {
-			(*pg_index)++;
-			if (*pg_index >= vcnt)
-				return 0;
+		bio_advance(bio, bytes);
+		if (!bio->bi_iter.bi_size)
+			return 0;
+		bvec = bio_iter_iovec(bio, bio->bi_iter);
 
-			page_out = bvec[*pg_index].bv_page;
-			*pg_offset = 0;
-			start_byte = page_offset(page_out) - disk_start;
+		start_byte = page_offset(bvec.bv_page) - disk_start;
 
-			/*
-			 * make sure our new page is covered by this
-			 * working buffer
-			 */
-			if (total_out <= start_byte)
-				return 1;
+		/*
+		 * make sure our new page is covered by this
+		 * working buffer
+		 */
+		if (total_out <= start_byte)
+			return 1;
 
-			/*
-			 * the next page in the biovec might not be adjacent
-			 * to the last page, but it might still be found
-			 * inside this working buffer. bump our offset pointer
-			 */
-			if (total_out > start_byte &&
-			    current_buf_start < start_byte) {
-				buf_offset = start_byte - buf_start;
-				working_bytes = total_out - start_byte;
-				current_buf_start = buf_start + buf_offset;
-			}
+		/*
+		 * the next page in the biovec might not be adjacent
+		 * to the last page, but it might still be found
+		 * inside this working buffer. bump our offset pointer
+		 */
+		if (total_out > start_byte &&
+		    current_buf_start < start_byte) {
+			buf_offset = start_byte - buf_start;
+			working_bytes = total_out - start_byte;
+			current_buf_start = buf_start + buf_offset;
 		}
 	}
 
 	return 1;
 }
-
-/*
- * When uncompressing data, we need to make sure and zero any parts of
- * the biovec that were not filled in by the decompression code.  pg_index
- * and pg_offset indicate the last page and the last offset of that page
- * that have been filled in.  This will zero everything remaining in the
- * biovec.
- */
-void btrfs_clear_biovec_end(struct bio_vec *bvec, int vcnt,
-				   unsigned long pg_index,
-				   unsigned long pg_offset)
-{
-	while (pg_index < vcnt) {
-		struct page *page = bvec[pg_index].bv_page;
-		unsigned long off = bvec[pg_index].bv_offset;
-		unsigned long len = bvec[pg_index].bv_len;
-
-		if (pg_offset < off)
-			pg_offset = off;
-		if (pg_offset < off + len) {
-			unsigned long bytes = off + len - pg_offset;
-			char *kaddr;
-
-			kaddr = kmap_atomic(page);
-			memset(kaddr + pg_offset, 0, bytes);
-			kunmap_atomic(kaddr);
-		}
-		pg_index++;
-		pg_offset = 0;
-	}
-}
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index f49d8b8c0f00..09879579fbc8 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -34,9 +34,7 @@ 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,
 			      unsigned long total_out, u64 disk_start,
-			      struct bio_vec *bvec, int vcnt,
-			      unsigned long *pg_index,
-			      unsigned long *pg_offset);
+			      struct bio *bio);
 
 int btrfs_submit_compressed_write(struct inode *inode, u64 start,
 				  unsigned long len, u64 disk_start,
@@ -45,9 +43,6 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start,
 				  unsigned long nr_pages);
 int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 				 int mirror_num, unsigned long bio_flags);
-void btrfs_clear_biovec_end(struct bio_vec *bvec, int vcnt,
-				   unsigned long pg_index,
-				   unsigned long pg_offset);
 
 enum btrfs_compression_type {
 	BTRFS_COMPRESS_NONE  = 0,
@@ -72,11 +67,10 @@ struct btrfs_compress_op {
 			      unsigned long *total_out,
 			      unsigned long max_out);
 
-	int (*decompress_biovec)(struct list_head *workspace,
+	int (*decompress_bio)(struct list_head *workspace,
 				 struct page **pages_in,
 				 u64 disk_start,
-				 struct bio_vec *bvec,
-				 int vcnt,
+				 struct bio *orig_bio,
 				 size_t srclen);
 
 	int (*decompress)(struct list_head *workspace,
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index f6ba165d3f81..25286a5912fc 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -260,7 +260,7 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans,
 	if (IS_ERR(cow))
 		return PTR_ERR(cow);
 
-	copy_extent_buffer(cow, buf, 0, 0, cow->len);
+	copy_extent_buffer_full(cow, buf);
 	btrfs_set_header_bytenr(cow, cow->start);
 	btrfs_set_header_generation(cow, trans->transid);
 	btrfs_set_header_backref_rev(cow, BTRFS_MIXED_BACKREF_REV);
@@ -271,8 +271,7 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans,
 	else
 		btrfs_set_header_owner(cow, new_root_objectid);
 
-	write_extent_buffer(cow, root->fs_info->fsid, btrfs_header_fsid(),
-			    BTRFS_FSID_SIZE);
+	write_extent_buffer_fsid(cow, root->fs_info->fsid);
 
 	WARN_ON(btrfs_header_generation(buf) > trans->transid);
 	if (new_root_objectid == BTRFS_TREE_RELOC_OBJECTID)
@@ -1130,7 +1129,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 
 	/* cow is set to blocking by btrfs_init_new_buffer */
 
-	copy_extent_buffer(cow, buf, 0, 0, cow->len);
+	copy_extent_buffer_full(cow, buf);
 	btrfs_set_header_bytenr(cow, cow->start);
 	btrfs_set_header_generation(cow, trans->transid);
 	btrfs_set_header_backref_rev(cow, BTRFS_MIXED_BACKREF_REV);
@@ -1141,8 +1140,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 	else
 		btrfs_set_header_owner(cow, root->root_key.objectid);
 
-	write_extent_buffer(cow, root->fs_info->fsid, btrfs_header_fsid(),
-			    BTRFS_FSID_SIZE);
+	write_extent_buffer_fsid(cow, root->fs_info->fsid);
 
 	ret = update_ref_for_cow(trans, root, buf, cow, &last_ref);
 	if (ret) {
@@ -1670,7 +1668,7 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
 			continue;
 		}
 
-		cur = btrfs_find_tree_block(root->fs_info, blocknr);
+		cur = find_extent_buffer(root->fs_info, blocknr);
 		if (cur)
 			uptodate = btrfs_buffer_uptodate(cur, gen, 0);
 		else
@@ -2255,7 +2253,7 @@ static void reada_for_search(struct btrfs_root *root,
 
 	search = btrfs_node_blockptr(node, slot);
 	blocksize = root->nodesize;
-	eb = btrfs_find_tree_block(root->fs_info, search);
+	eb = find_extent_buffer(root->fs_info, search);
 	if (eb) {
 		free_extent_buffer(eb);
 		return;
@@ -2314,7 +2312,7 @@ 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->fs_info, block1);
+		eb = find_extent_buffer(root->fs_info, block1);
 		/*
 		 * if we get -eagain from btrfs_buffer_uptodate, we
 		 * don't want to return eagain here.  That will loop
@@ -2327,7 +2325,7 @@ 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->fs_info, block2);
+		eb = find_extent_buffer(root->fs_info, block2);
 		if (eb && btrfs_buffer_uptodate(eb, gen, 1) != 0)
 			block2 = 0;
 		free_extent_buffer(eb);
@@ -2445,7 +2443,7 @@ 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->fs_info, blocknr);
+	tmp = find_extent_buffer(root->fs_info, blocknr);
 	if (tmp) {
 		/* first we do an atomic uptodate check */
 		if (btrfs_buffer_uptodate(tmp, gen, 1) > 0) {
@@ -3350,7 +3348,7 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans,
 
 	root_add_used(root, root->nodesize);
 
-	memset_extent_buffer(c, 0, 0, sizeof(struct btrfs_header));
+	memzero_extent_buffer(c, 0, sizeof(struct btrfs_header));
 	btrfs_set_header_nritems(c, 1);
 	btrfs_set_header_level(c, level);
 	btrfs_set_header_bytenr(c, c->start);
@@ -3358,11 +3356,8 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans,
 	btrfs_set_header_backref_rev(c, BTRFS_MIXED_BACKREF_REV);
 	btrfs_set_header_owner(c, root->root_key.objectid);
 
-	write_extent_buffer(c, root->fs_info->fsid, btrfs_header_fsid(),
-			    BTRFS_FSID_SIZE);
-
-	write_extent_buffer(c, root->fs_info->chunk_tree_uuid,
-			    btrfs_header_chunk_tree_uuid(c), BTRFS_UUID_SIZE);
+	write_extent_buffer_fsid(c, root->fs_info->fsid);
+	write_extent_buffer_chunk_tree_uuid(c, root->fs_info->chunk_tree_uuid);
 
 	btrfs_set_node_key(c, &lower_key, 0);
 	btrfs_set_node_blockptr(c, 0, lower->start);
@@ -3489,17 +3484,15 @@ static noinline int split_node(struct btrfs_trans_handle *trans,
 
 	root_add_used(root, root->nodesize);
 
-	memset_extent_buffer(split, 0, 0, sizeof(struct btrfs_header));
+	memzero_extent_buffer(split, 0, sizeof(struct btrfs_header));
 	btrfs_set_header_level(split, btrfs_header_level(c));
 	btrfs_set_header_bytenr(split, split->start);
 	btrfs_set_header_generation(split, trans->transid);
 	btrfs_set_header_backref_rev(split, BTRFS_MIXED_BACKREF_REV);
 	btrfs_set_header_owner(split, root->root_key.objectid);
-	write_extent_buffer(split, root->fs_info->fsid,
-			    btrfs_header_fsid(), BTRFS_FSID_SIZE);
-	write_extent_buffer(split, root->fs_info->chunk_tree_uuid,
-			    btrfs_header_chunk_tree_uuid(split),
-			    BTRFS_UUID_SIZE);
+	write_extent_buffer_fsid(split, root->fs_info->fsid);
+	write_extent_buffer_chunk_tree_uuid(split,
+			root->fs_info->chunk_tree_uuid);
 
 	ret = tree_mod_log_eb_copy(root->fs_info, split, c, 0,
 				   mid, c_nritems - mid);
@@ -4277,18 +4270,14 @@ again:
 
 	root_add_used(root, root->nodesize);
 
-	memset_extent_buffer(right, 0, 0, sizeof(struct btrfs_header));
+	memzero_extent_buffer(right, 0, sizeof(struct btrfs_header));
 	btrfs_set_header_bytenr(right, right->start);
 	btrfs_set_header_generation(right, trans->transid);
 	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, fs_info->fsid,
-			    btrfs_header_fsid(), BTRFS_FSID_SIZE);
-
-	write_extent_buffer(right, fs_info->chunk_tree_uuid,
-			    btrfs_header_chunk_tree_uuid(right),
-			    BTRFS_UUID_SIZE);
+	write_extent_buffer_fsid(right, fs_info->fsid);
+	write_extent_buffer_chunk_tree_uuid(right, fs_info->chunk_tree_uuid);
 
 	if (split == 0) {
 		if (mid <= slot) {
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 0b8ce2b9f7d0..1b25a460ecea 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -90,9 +90,6 @@ static const int btrfs_csum_sizes[] = { 4 };
 /* four bytes for CRC32 */
 #define BTRFS_EMPTY_DIR_SIZE 0
 
-/* specific to btrfs_map_block(), therefore not in include/linux/blk_types.h */
-#define REQ_GET_READ_MIRRORS	(1 << 30)
-
 /* ioprio of readahead is set to idle */
 #define BTRFS_IOPRIO_READA (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0))
 
@@ -429,6 +426,10 @@ struct btrfs_space_info {
 	struct list_head ro_bgs;
 	struct list_head priority_tickets;
 	struct list_head tickets;
+	/*
+	 * tickets_id just indicates the next ticket will be handled, so note
+	 * it's not stored per ticket.
+	 */
 	u64 tickets_id;
 
 	struct rw_semaphore groups_sem;
@@ -798,7 +799,6 @@ struct btrfs_fs_info {
 	spinlock_t super_lock;
 	struct btrfs_super_block *super_copy;
 	struct btrfs_super_block *super_for_commit;
-	struct block_device *__bdev;
 	struct super_block *sb;
 	struct inode *btree_inode;
 	struct backing_dev_info bdi;
@@ -2210,6 +2210,8 @@ btrfs_disk_balance_args_to_cpu(struct btrfs_balance_args *cpu,
 	cpu->target = le64_to_cpu(disk->target);
 	cpu->flags = le64_to_cpu(disk->flags);
 	cpu->limit = le64_to_cpu(disk->limit);
+	cpu->stripes_min = le32_to_cpu(disk->stripes_min);
+	cpu->stripes_max = le32_to_cpu(disk->stripes_max);
 }
 
 static inline void
@@ -2228,6 +2230,8 @@ btrfs_cpu_balance_args_to_disk(struct btrfs_disk_balance_args *disk,
 	disk->target = cpu_to_le64(cpu->target);
 	disk->flags = cpu_to_le64(cpu->flags);
 	disk->limit = cpu_to_le64(cpu->limit);
+	disk->stripes_min = cpu_to_le32(cpu->stripes_min);
+	disk->stripes_max = cpu_to_le32(cpu->stripes_max);
 }
 
 /* struct btrfs_super_block */
@@ -3660,7 +3664,7 @@ struct reada_control *btrfs_reada_add(struct btrfs_root *root,
 int btrfs_reada_wait(void *handle);
 void btrfs_reada_detach(void *handle);
 int btree_readahead_hook(struct btrfs_fs_info *fs_info,
-			 struct extent_buffer *eb, u64 start, int err);
+			 struct extent_buffer *eb, int err);
 
 static inline int is_fstree(u64 rootid)
 {
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 0fcf5f25d524..d90d4446f9fe 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1686,7 +1686,7 @@ int btrfs_should_delete_dir_index(struct list_head *del_list,
  *
  */
 int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
-				    struct list_head *ins_list, bool *emitted)
+				    struct list_head *ins_list)
 {
 	struct btrfs_dir_item *di;
 	struct btrfs_delayed_item *curr, *next;
@@ -1730,7 +1730,6 @@ int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
 
 		if (over)
 			return 1;
-		*emitted = true;
 	}
 	return 0;
 }
diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h
index 2495b3d4075f..2c1cbe245104 100644
--- a/fs/btrfs/delayed-inode.h
+++ b/fs/btrfs/delayed-inode.h
@@ -146,7 +146,7 @@ void btrfs_readdir_put_delayed_items(struct inode *inode,
 int btrfs_should_delete_dir_index(struct list_head *del_list,
 				  u64 index);
 int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
-				    struct list_head *ins_list, bool *emitted);
+				    struct list_head *ins_list);
 
 /* for init */
 int __init btrfs_delayed_inode_init(void);
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 8d93854a4b4f..ef724a5fc30e 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -189,6 +189,8 @@ static inline void drop_delayed_ref(struct btrfs_trans_handle *trans,
 	} else {
 		assert_spin_locked(&head->lock);
 		list_del(&ref->list);
+		if (!list_empty(&ref->add_list))
+			list_del(&ref->add_list);
 	}
 	ref->in_tree = 0;
 	btrfs_put_delayed_ref(ref);
@@ -431,6 +433,15 @@ add_delayed_ref_tail_merge(struct btrfs_trans_handle *trans,
 			exist->action = ref->action;
 			mod = -exist->ref_mod;
 			exist->ref_mod = ref->ref_mod;
+			if (ref->action == BTRFS_ADD_DELAYED_REF)
+				list_add_tail(&exist->add_list,
+					      &href->ref_add_list);
+			else if (ref->action == BTRFS_DROP_DELAYED_REF) {
+				ASSERT(!list_empty(&exist->add_list));
+				list_del(&exist->add_list);
+			} else {
+				ASSERT(0);
+			}
 		} else
 			mod = -ref->ref_mod;
 	}
@@ -444,6 +455,8 @@ add_delayed_ref_tail_merge(struct btrfs_trans_handle *trans,
 
 add_tail:
 	list_add_tail(&ref->list, &href->ref_list);
+	if (ref->action == BTRFS_ADD_DELAYED_REF)
+		list_add_tail(&ref->add_list, &href->ref_add_list);
 	atomic_inc(&root->num_entries);
 	trans->delayed_ref_updates++;
 	spin_unlock(&href->lock);
@@ -590,6 +603,7 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
 	head_ref->must_insert_reserved = must_insert_reserved;
 	head_ref->is_data = is_data;
 	INIT_LIST_HEAD(&head_ref->ref_list);
+	INIT_LIST_HEAD(&head_ref->ref_add_list);
 	head_ref->processing = 0;
 	head_ref->total_ref_mod = count_mod;
 	head_ref->qgroup_reserved = 0;
@@ -606,7 +620,7 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
 		qrecord->num_bytes = num_bytes;
 		qrecord->old_roots = NULL;
 
-		if(btrfs_qgroup_insert_dirty_extent_nolock(fs_info,
+		if(btrfs_qgroup_trace_extent_nolock(fs_info,
 					delayed_refs, qrecord))
 			kfree(qrecord);
 	}
@@ -671,6 +685,8 @@ add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
 	ref->is_head = 0;
 	ref->in_tree = 1;
 	ref->seq = seq;
+	INIT_LIST_HEAD(&ref->list);
+	INIT_LIST_HEAD(&ref->add_list);
 
 	full_ref = btrfs_delayed_node_to_tree_ref(ref);
 	full_ref->parent = parent;
@@ -726,6 +742,8 @@ add_delayed_data_ref(struct btrfs_fs_info *fs_info,
 	ref->is_head = 0;
 	ref->in_tree = 1;
 	ref->seq = seq;
+	INIT_LIST_HEAD(&ref->list);
+	INIT_LIST_HEAD(&ref->add_list);
 
 	full_ref = btrfs_delayed_node_to_data_ref(ref);
 	full_ref->parent = parent;
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index 43f3629760e9..dba97842b47a 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -42,6 +42,12 @@ struct btrfs_delayed_ref_node {
 
 	/*data/tree ref use list, stored in ref_head->ref_list. */
 	struct list_head list;
+	/*
+	 * If action is BTRFS_ADD_DELAYED_REF, also link this node to
+	 * ref_head->ref_add_list, then we do not need to iterate the
+	 * whole ref_head->ref_list to find BTRFS_ADD_DELAYED_REF nodes.
+	 */
+	struct list_head add_list;
 
 	/* the starting bytenr of the extent */
 	u64 bytenr;
@@ -99,6 +105,8 @@ struct btrfs_delayed_ref_head {
 
 	spinlock_t lock;
 	struct list_head ref_list;
+	/* accumulate add BTRFS_ADD_DELAYED_REF nodes to this ref_add_list. */
+	struct list_head ref_add_list;
 
 	struct rb_node href_node;
 
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 3a57f99d96aa..811662cce977 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -271,7 +271,7 @@ u32 btrfs_csum_data(char *data, u32 seed, size_t len)
 	return btrfs_crc32c(seed, data, len);
 }
 
-void btrfs_csum_final(u32 crc, char *result)
+void btrfs_csum_final(u32 crc, u8 *result)
 {
 	put_unaligned_le32(~crc, result);
 }
@@ -747,7 +747,7 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 err:
 	if (reads_done &&
 	    test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
-		btree_readahead_hook(fs_info, eb, eb->start, ret);
+		btree_readahead_hook(fs_info, eb, ret);
 
 	if (ret) {
 		/*
@@ -772,7 +772,7 @@ static int btree_io_failed_hook(struct page *page, int failed_mirror)
 	eb->read_mirror = failed_mirror;
 	atomic_dec(&eb->io_pages);
 	if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
-		btree_readahead_hook(eb->fs_info, eb, eb->start, -EIO);
+		btree_readahead_hook(eb->fs_info, eb, -EIO);
 	return -EIO;	/* we fixed nothing */
 }
 
@@ -1191,12 +1191,6 @@ int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr,
 	return 0;
 }
 
-struct extent_buffer *btrfs_find_tree_block(struct btrfs_fs_info *fs_info,
-					    u64 bytenr)
-{
-	return find_extent_buffer(fs_info, bytenr);
-}
-
 struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root,
 						 u64 bytenr)
 {
@@ -1418,18 +1412,15 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
 		goto fail;
 	}
 
-	memset_extent_buffer(leaf, 0, 0, sizeof(struct btrfs_header));
+	memzero_extent_buffer(leaf, 0, sizeof(struct btrfs_header));
 	btrfs_set_header_bytenr(leaf, leaf->start);
 	btrfs_set_header_generation(leaf, trans->transid);
 	btrfs_set_header_backref_rev(leaf, BTRFS_MIXED_BACKREF_REV);
 	btrfs_set_header_owner(leaf, objectid);
 	root->node = leaf;
 
-	write_extent_buffer(leaf, fs_info->fsid, btrfs_header_fsid(),
-			    BTRFS_FSID_SIZE);
-	write_extent_buffer(leaf, fs_info->chunk_tree_uuid,
-			    btrfs_header_chunk_tree_uuid(leaf),
-			    BTRFS_UUID_SIZE);
+	write_extent_buffer_fsid(leaf, fs_info->fsid);
+	write_extent_buffer_chunk_tree_uuid(leaf, fs_info->chunk_tree_uuid);
 	btrfs_mark_buffer_dirty(leaf);
 
 	root->commit_root = btrfs_root_node(root);
@@ -1505,15 +1496,14 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
 		return ERR_CAST(leaf);
 	}
 
-	memset_extent_buffer(leaf, 0, 0, sizeof(struct btrfs_header));
+	memzero_extent_buffer(leaf, 0, sizeof(struct btrfs_header));
 	btrfs_set_header_bytenr(leaf, leaf->start);
 	btrfs_set_header_generation(leaf, trans->transid);
 	btrfs_set_header_backref_rev(leaf, BTRFS_MIXED_BACKREF_REV);
 	btrfs_set_header_owner(leaf, BTRFS_TREE_LOG_OBJECTID);
 	root->node = leaf;
 
-	write_extent_buffer(root->node, root->fs_info->fsid,
-			    btrfs_header_fsid(), BTRFS_FSID_SIZE);
+	write_extent_buffer_fsid(root->node, root->fs_info->fsid);
 	btrfs_mark_buffer_dirty(root->node);
 	btrfs_tree_unlock(root->node);
 	return root;
@@ -4354,6 +4344,8 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
 						 list) {
 			ref->in_tree = 0;
 			list_del(&ref->list);
+			if (!list_empty(&ref->add_list))
+				list_del(&ref->add_list);
 			atomic_dec(&delayed_refs->num_entries);
 			btrfs_put_delayed_ref(ref);
 		}
@@ -4452,7 +4444,7 @@ static int btrfs_destroy_marked_extents(struct btrfs_root *root,
 
 		clear_extent_bits(dirty_pages, start, end, mark);
 		while (start <= end) {
-			eb = btrfs_find_tree_block(root->fs_info, start);
+			eb = find_extent_buffer(root->fs_info, start);
 			start += root->nodesize;
 			if (!eb)
 				continue;
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index 1a3237e5700f..729540701458 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -63,8 +63,6 @@ struct buffer_head *btrfs_read_dev_super(struct block_device *bdev);
 int btrfs_read_dev_one_super(struct block_device *bdev, int copy_num,
 			struct buffer_head **bh_ret);
 int btrfs_commit_super(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);
 int btrfs_init_fs_root(struct btrfs_root *root);
@@ -121,7 +119,7 @@ int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid,
 			  int atomic);
 int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid);
 u32 btrfs_csum_data(char *data, u32 seed, size_t len);
-void btrfs_csum_final(u32 crc, char *result);
+void btrfs_csum_final(u32 crc, u8 *result);
 int btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio,
 			enum btrfs_wq_endio_type metadata);
 int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode,
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 4607af38c72e..0d80136206b1 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1114,7 +1114,7 @@ static int convert_extent_item_v0(struct btrfs_trans_handle *trans,
 				       BTRFS_BLOCK_FLAG_FULL_BACKREF);
 		bi = (struct btrfs_tree_block_info *)(item + 1);
 		/* FIXME: get first key of the block */
-		memset_extent_buffer(leaf, 0, (unsigned long)bi, sizeof(*bi));
+		memzero_extent_buffer(leaf, (unsigned long)bi, sizeof(*bi));
 		btrfs_set_tree_block_level(leaf, bi, (int)owner);
 	} else {
 		btrfs_set_extent_flags(leaf, item, BTRFS_EXTENT_FLAG_DATA);
@@ -2036,7 +2036,7 @@ int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
 	 */
 	btrfs_bio_counter_inc_blocked(root->fs_info);
 	/* Tell the block device(s) that the sectors can be discarded */
-	ret = btrfs_map_block(root->fs_info, REQ_OP_DISCARD,
+	ret = btrfs_map_block(root->fs_info, BTRFS_MAP_DISCARD,
 			      bytenr, &num_bytes, &bbio, 0);
 	/* Error condition is -ENOMEM */
 	if (!ret) {
@@ -2454,13 +2454,14 @@ select_delayed_ref(struct btrfs_delayed_ref_head *head)
 	 * the extent item from the extent tree, when there still are references
 	 * to add, which would fail because they would not find the extent item.
 	 */
-	list_for_each_entry(ref, &head->ref_list, list) {
-		if (ref->action == BTRFS_ADD_DELAYED_REF)
-			return ref;
-	}
+	if (!list_empty(&head->ref_add_list))
+		return list_first_entry(&head->ref_add_list,
+				struct btrfs_delayed_ref_node, add_list);
 
-	return list_entry(head->ref_list.next, struct btrfs_delayed_ref_node,
-			  list);
+	ref = list_first_entry(&head->ref_list, struct btrfs_delayed_ref_node,
+			       list);
+	ASSERT(list_empty(&ref->add_list));
+	return ref;
 }
 
 /*
@@ -2620,6 +2621,8 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 			actual_count++;
 			ref->in_tree = 0;
 			list_del(&ref->list);
+			if (!list_empty(&ref->add_list))
+				list_del(&ref->add_list);
 		}
 		atomic_dec(&delayed_refs->num_entries);
 
@@ -2826,7 +2829,7 @@ int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans,
 	smp_mb();
 	avg_runtime = fs_info->avg_delayed_ref_runtime;
 	val = num_entries * avg_runtime;
-	if (num_entries * avg_runtime >= NSEC_PER_SEC)
+	if (val >= NSEC_PER_SEC)
 		return 1;
 	if (val >= NSEC_PER_SEC / 2)
 		return 2;
@@ -4322,6 +4325,13 @@ void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start,
  */
 void btrfs_free_reserved_data_space(struct inode *inode, u64 start, u64 len)
 {
+	struct btrfs_root *root = BTRFS_I(inode)->root;
+
+	/* Make sure the range is aligned to sectorsize */
+	len = round_up(start + len, root->sectorsize) -
+	      round_down(start, root->sectorsize);
+	start = round_down(start, root->sectorsize);
+
 	btrfs_free_reserved_data_space_noquota(inode, start, len);
 	btrfs_qgroup_free_data(inode, start, len);
 }
@@ -6499,16 +6509,9 @@ void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg)
  * @num_bytes:	The number of bytes in question
  * @delalloc:   The blocks are allocated for the delalloc write
  *
- * This is called by the allocator when it reserves space. Metadata
- * reservations should be called with RESERVE_ALLOC so we do the proper
- * ENOSPC accounting.  For data we handle the reservation through clearing the
- * delalloc bits in the io_tree.  We have to do this since we could end up
- * allocating less disk space for the amount of data we have reserved in the
- * case of compression.
- *
- * If this is a reservation and the block group has become read only we cannot
- * make the reservation and return -EAGAIN, otherwise this function always
- * succeeds.
+ * This is called by the allocator when it reserves space. If this is a
+ * reservation and the block group has become read only we cannot make the
+ * reservation and return -EAGAIN, otherwise this function always succeeds.
  */
 static int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache,
 				    u64 ram_bytes, u64 num_bytes, int delalloc)
@@ -8538,220 +8541,6 @@ reada:
 	wc->reada_slot = slot;
 }
 
-static int account_leaf_items(struct btrfs_trans_handle *trans,
-			      struct btrfs_root *root,
-			      struct extent_buffer *eb)
-{
-	int nr = btrfs_header_nritems(eb);
-	int i, extent_type, ret;
-	struct btrfs_key key;
-	struct btrfs_file_extent_item *fi;
-	u64 bytenr, num_bytes;
-
-	/* We can be called directly from walk_up_proc() */
-	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &root->fs_info->flags))
-		return 0;
-
-	for (i = 0; i < nr; i++) {
-		btrfs_item_key_to_cpu(eb, &key, i);
-
-		if (key.type != BTRFS_EXTENT_DATA_KEY)
-			continue;
-
-		fi = btrfs_item_ptr(eb, i, struct btrfs_file_extent_item);
-		/* filter out non qgroup-accountable extents  */
-		extent_type = btrfs_file_extent_type(eb, fi);
-
-		if (extent_type == BTRFS_FILE_EXTENT_INLINE)
-			continue;
-
-		bytenr = btrfs_file_extent_disk_bytenr(eb, fi);
-		if (!bytenr)
-			continue;
-
-		num_bytes = btrfs_file_extent_disk_num_bytes(eb, fi);
-
-		ret = btrfs_qgroup_insert_dirty_extent(trans, root->fs_info,
-				bytenr, num_bytes, GFP_NOFS);
-		if (ret)
-			return ret;
-	}
-	return 0;
-}
-
-/*
- * Walk up the tree from the bottom, freeing leaves and any interior
- * nodes which have had all slots visited. If a node (leaf or
- * interior) is freed, the node above it will have it's slot
- * incremented. The root node will never be freed.
- *
- * At the end of this function, we should have a path which has all
- * slots incremented to the next position for a search. If we need to
- * read a new node it will be NULL and the node above it will have the
- * correct slot selected for a later read.
- *
- * If we increment the root nodes slot counter past the number of
- * elements, 1 is returned to signal completion of the search.
- */
-static int adjust_slots_upwards(struct btrfs_root *root,
-				struct btrfs_path *path, int root_level)
-{
-	int level = 0;
-	int nr, slot;
-	struct extent_buffer *eb;
-
-	if (root_level == 0)
-		return 1;
-
-	while (level <= root_level) {
-		eb = path->nodes[level];
-		nr = btrfs_header_nritems(eb);
-		path->slots[level]++;
-		slot = path->slots[level];
-		if (slot >= nr || level == 0) {
-			/*
-			 * Don't free the root -  we will detect this
-			 * condition after our loop and return a
-			 * positive value for caller to stop walking the tree.
-			 */
-			if (level != root_level) {
-				btrfs_tree_unlock_rw(eb, path->locks[level]);
-				path->locks[level] = 0;
-
-				free_extent_buffer(eb);
-				path->nodes[level] = NULL;
-				path->slots[level] = 0;
-			}
-		} else {
-			/*
-			 * We have a valid slot to walk back down
-			 * from. Stop here so caller can process these
-			 * new nodes.
-			 */
-			break;
-		}
-
-		level++;
-	}
-
-	eb = path->nodes[root_level];
-	if (path->slots[root_level] >= btrfs_header_nritems(eb))
-		return 1;
-
-	return 0;
-}
-
-/*
- * root_eb is the subtree root and is locked before this function is called.
- */
-static int account_shared_subtree(struct btrfs_trans_handle *trans,
-				  struct btrfs_root *root,
-				  struct extent_buffer *root_eb,
-				  u64 root_gen,
-				  int root_level)
-{
-	int ret = 0;
-	int level;
-	struct extent_buffer *eb = root_eb;
-	struct btrfs_path *path = NULL;
-
-	BUG_ON(root_level < 0 || root_level > BTRFS_MAX_LEVEL);
-	BUG_ON(root_eb == NULL);
-
-	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &root->fs_info->flags))
-		return 0;
-
-	if (!extent_buffer_uptodate(root_eb)) {
-		ret = btrfs_read_buffer(root_eb, root_gen);
-		if (ret)
-			goto out;
-	}
-
-	if (root_level == 0) {
-		ret = account_leaf_items(trans, root, root_eb);
-		goto out;
-	}
-
-	path = btrfs_alloc_path();
-	if (!path)
-		return -ENOMEM;
-
-	/*
-	 * Walk down the tree.  Missing extent blocks are filled in as
-	 * we go. Metadata is accounted every time we read a new
-	 * extent block.
-	 *
-	 * When we reach a leaf, we account for file extent items in it,
-	 * walk back up the tree (adjusting slot pointers as we go)
-	 * and restart the search process.
-	 */
-	extent_buffer_get(root_eb); /* For path */
-	path->nodes[root_level] = root_eb;
-	path->slots[root_level] = 0;
-	path->locks[root_level] = 0; /* so release_path doesn't try to unlock */
-walk_down:
-	level = root_level;
-	while (level >= 0) {
-		if (path->nodes[level] == NULL) {
-			int parent_slot;
-			u64 child_gen;
-			u64 child_bytenr;
-
-			/* We need to get child blockptr/gen from
-			 * parent before we can read it. */
-			eb = path->nodes[level + 1];
-			parent_slot = path->slots[level + 1];
-			child_bytenr = btrfs_node_blockptr(eb, parent_slot);
-			child_gen = btrfs_node_ptr_generation(eb, parent_slot);
-
-			eb = read_tree_block(root, child_bytenr, child_gen);
-			if (IS_ERR(eb)) {
-				ret = PTR_ERR(eb);
-				goto out;
-			} else if (!extent_buffer_uptodate(eb)) {
-				free_extent_buffer(eb);
-				ret = -EIO;
-				goto out;
-			}
-
-			path->nodes[level] = eb;
-			path->slots[level] = 0;
-
-			btrfs_tree_read_lock(eb);
-			btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
-			path->locks[level] = BTRFS_READ_LOCK_BLOCKING;
-
-			ret = btrfs_qgroup_insert_dirty_extent(trans,
-					root->fs_info, child_bytenr,
-					root->nodesize, GFP_NOFS);
-			if (ret)
-				goto out;
-		}
-
-		if (level == 0) {
-			ret = account_leaf_items(trans, root, path->nodes[level]);
-			if (ret)
-				goto out;
-
-			/* Nonzero return here means we completed our search */
-			ret = adjust_slots_upwards(root, path, root_level);
-			if (ret)
-				break;
-
-			/* Restart search with new slots */
-			goto walk_down;
-		}
-
-		level--;
-	}
-
-	ret = 0;
-out:
-	btrfs_free_path(path);
-
-	return ret;
-}
-
 /*
  * helper to process tree block while walking down the tree.
  *
@@ -8873,7 +8662,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 	bytenr = btrfs_node_blockptr(path->nodes[level], path->slots[level]);
 	blocksize = root->nodesize;
 
-	next = btrfs_find_tree_block(root->fs_info, bytenr);
+	next = find_extent_buffer(root->fs_info, bytenr);
 	if (!next) {
 		next = btrfs_find_create_tree_block(root, bytenr);
 		if (IS_ERR(next))
@@ -8980,8 +8769,8 @@ skip:
 		}
 
 		if (need_account) {
-			ret = account_shared_subtree(trans, root, next,
-						     generation, level - 1);
+			ret = btrfs_qgroup_trace_subtree(trans, root, next,
+							 generation, level - 1);
 			if (ret) {
 				btrfs_err_rl(root->fs_info,
 					     "Error %d accounting shared subtree. Quota is out of sync, rescan required.",
@@ -9078,7 +8867,7 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
 			else
 				ret = btrfs_dec_ref(trans, root, eb, 0);
 			BUG_ON(ret); /* -ENOMEM */
-			ret = account_leaf_items(trans, root, eb);
+			ret = btrfs_qgroup_trace_leaf_items(trans, root, eb);
 			if (ret) {
 				btrfs_err_rl(root->fs_info,
 					     "error %d accounting leaf items. Quota is out of sync, rescan required.",
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 8ed05d95584a..d24af9dc76c7 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2029,7 +2029,7 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
 	 * read repair operation.
 	 */
 	btrfs_bio_counter_inc_blocked(fs_info);
-	ret = btrfs_map_block(fs_info, WRITE, logical,
+	ret = btrfs_map_block(fs_info, BTRFS_MAP_WRITE, logical,
 			      &map_length, &bbio, mirror_num);
 	if (ret) {
 		btrfs_bio_counter_dec(fs_info);
@@ -3743,7 +3743,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 	if (btrfs_header_level(eb) > 0) {
 		end = btrfs_node_key_ptr_offset(nritems);
 
-		memset_extent_buffer(eb, 0, end, eb->len - end);
+		memzero_extent_buffer(eb, end, eb->len - end);
 	} else {
 		/*
 		 * leaf:
@@ -3752,7 +3752,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 		start = btrfs_item_nr_offset(nritems);
 		end = btrfs_leaf_data(eb) +
 		      leaf_data_end(fs_info->tree_root, eb);
-		memset_extent_buffer(eb, 0, start, end - start);
+		memzero_extent_buffer(eb, start, end - start);
 	}
 
 	for (i = 0; i < num_pages; i++) {
@@ -4720,9 +4720,9 @@ struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src)
 		WARN_ON(PageDirty(p));
 		SetPageUptodate(p);
 		new->pages[i] = p;
+		copy_page(page_address(p), page_address(src->pages[i]));
 	}
 
-	copy_extent_buffer(new, src, 0, 0, src->len);
 	set_bit(EXTENT_BUFFER_UPTODATE, &new->bflags);
 	set_bit(EXTENT_BUFFER_DUMMY, &new->bflags);
 
@@ -5465,6 +5465,27 @@ int memcmp_extent_buffer(struct extent_buffer *eb, const void *ptrv,
 	return ret;
 }
 
+void write_extent_buffer_chunk_tree_uuid(struct extent_buffer *eb,
+		const void *srcv)
+{
+	char *kaddr;
+
+	WARN_ON(!PageUptodate(eb->pages[0]));
+	kaddr = page_address(eb->pages[0]);
+	memcpy(kaddr + offsetof(struct btrfs_header, chunk_tree_uuid), srcv,
+			BTRFS_FSID_SIZE);
+}
+
+void write_extent_buffer_fsid(struct extent_buffer *eb, const void *srcv)
+{
+	char *kaddr;
+
+	WARN_ON(!PageUptodate(eb->pages[0]));
+	kaddr = page_address(eb->pages[0]);
+	memcpy(kaddr + offsetof(struct btrfs_header, fsid), srcv,
+			BTRFS_FSID_SIZE);
+}
+
 void write_extent_buffer(struct extent_buffer *eb, const void *srcv,
 			 unsigned long start, unsigned long len)
 {
@@ -5496,8 +5517,8 @@ void write_extent_buffer(struct extent_buffer *eb, const void *srcv,
 	}
 }
 
-void memset_extent_buffer(struct extent_buffer *eb, char c,
-			  unsigned long start, unsigned long len)
+void memzero_extent_buffer(struct extent_buffer *eb, unsigned long start,
+		unsigned long len)
 {
 	size_t cur;
 	size_t offset;
@@ -5517,7 +5538,7 @@ void memset_extent_buffer(struct extent_buffer *eb, char c,
 
 		cur = min(len, PAGE_SIZE - offset);
 		kaddr = page_address(page);
-		memset(kaddr + offset, c, cur);
+		memset(kaddr + offset, 0, cur);
 
 		len -= cur;
 		offset = 0;
@@ -5525,6 +5546,20 @@ void memset_extent_buffer(struct extent_buffer *eb, char c,
 	}
 }
 
+void copy_extent_buffer_full(struct extent_buffer *dst,
+			     struct extent_buffer *src)
+{
+	int i;
+	unsigned num_pages;
+
+	ASSERT(dst->len == src->len);
+
+	num_pages = num_extent_pages(dst->start, dst->len);
+	for (i = 0; i < num_pages; i++)
+		copy_page(page_address(dst->pages[i]),
+				page_address(src->pages[i]));
+}
+
 void copy_extent_buffer(struct extent_buffer *dst, struct extent_buffer *src,
 			unsigned long dst_offset, unsigned long src_offset,
 			unsigned long len)
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index ab31d145227e..ae64c1917d0a 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -405,8 +405,13 @@ void read_extent_buffer(struct extent_buffer *eb, void *dst,
 int read_extent_buffer_to_user(struct extent_buffer *eb, void __user *dst,
 			       unsigned long start,
 			       unsigned long len);
+void write_extent_buffer_fsid(struct extent_buffer *eb, const void *src);
+void write_extent_buffer_chunk_tree_uuid(struct extent_buffer *eb,
+		const void *src);
 void write_extent_buffer(struct extent_buffer *eb, const void *src,
 			 unsigned long start, unsigned long len);
+void copy_extent_buffer_full(struct extent_buffer *dst,
+			     struct extent_buffer *src);
 void copy_extent_buffer(struct extent_buffer *dst, struct extent_buffer *src,
 			unsigned long dst_offset, unsigned long src_offset,
 			unsigned long len);
@@ -414,8 +419,8 @@ void memcpy_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
 			   unsigned long src_offset, unsigned long len);
 void memmove_extent_buffer(struct extent_buffer *dst, unsigned long dst_offset,
 			   unsigned long src_offset, unsigned long len);
-void memset_extent_buffer(struct extent_buffer *eb, char c,
-			  unsigned long start, unsigned long len);
+void memzero_extent_buffer(struct extent_buffer *eb, unsigned long start,
+			   unsigned long len);
 int extent_buffer_test_bit(struct extent_buffer *eb, unsigned long start,
 			   unsigned long pos);
 void extent_buffer_bitmap_set(struct extent_buffer *eb, unsigned long start,
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index d0d571c47d33..5e74178ba9d9 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -163,7 +163,7 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
 				   struct inode *inode, struct bio *bio,
 				   u64 logical_offset, u32 *dst, int dio)
 {
-	struct bio_vec *bvec = bio->bi_io_vec;
+	struct bio_vec *bvec;
 	struct btrfs_io_bio *btrfs_bio = btrfs_io_bio(bio);
 	struct btrfs_csum_item *item = NULL;
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
@@ -176,8 +176,7 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
 	u64 page_bytes_left;
 	u32 diff;
 	int nblocks;
-	int bio_index = 0;
-	int count;
+	int count = 0, i;
 	u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy);
 
 	path = btrfs_alloc_path();
@@ -223,8 +222,11 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
 	if (dio)
 		offset = logical_offset;
 
-	page_bytes_left = bvec->bv_len;
-	while (bio_index < bio->bi_vcnt) {
+	bio_for_each_segment_all(bvec, bio, i) {
+		page_bytes_left = bvec->bv_len;
+		if (count)
+			goto next;
+
 		if (!dio)
 			offset = page_offset(bvec->bv_page) + bvec->bv_offset;
 		count = btrfs_find_ordered_sum(inode, offset, disk_bytenr,
@@ -285,29 +287,17 @@ static int __btrfs_lookup_bio_sums(struct btrfs_root *root,
 found:
 		csum += count * csum_size;
 		nblocks -= count;
-
+next:
 		while (count--) {
 			disk_bytenr += root->sectorsize;
 			offset += root->sectorsize;
 			page_bytes_left -= root->sectorsize;
-			if (!page_bytes_left) {
-				bio_index++;
-				/*
-				 * make sure we're still inside the
-				 * bio before we update page_bytes_left
-				 */
-				if (bio_index >= bio->bi_vcnt) {
-					WARN_ON_ONCE(count);
-					goto done;
-				}
-				bvec++;
-				page_bytes_left = bvec->bv_len;
-			}
-
+			if (!page_bytes_left)
+				break; /* move to next bio */
 		}
 	}
 
-done:
+	WARN_ON_ONCE(count);
 	btrfs_free_path(path);
 	return 0;
 }
@@ -447,13 +437,12 @@ int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode,
 		       struct bio *bio, u64 file_start, int contig)
 {
 	struct btrfs_ordered_sum *sums;
-	struct btrfs_ordered_extent *ordered;
+	struct btrfs_ordered_extent *ordered = NULL;
 	char *data;
-	struct bio_vec *bvec = bio->bi_io_vec;
-	int bio_index = 0;
+	struct bio_vec *bvec;
 	int index;
 	int nr_sectors;
-	int i;
+	int i, j;
 	unsigned long total_bytes = 0;
 	unsigned long this_sum_bytes = 0;
 	u64 offset;
@@ -470,17 +459,20 @@ int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode,
 	if (contig)
 		offset = file_start;
 	else
-		offset = page_offset(bvec->bv_page) + bvec->bv_offset;
+		offset = 0; /* shut up gcc */
 
-	ordered = btrfs_lookup_ordered_extent(inode, offset);
-	BUG_ON(!ordered); /* Logic error */
 	sums->bytenr = (u64)bio->bi_iter.bi_sector << 9;
 	index = 0;
 
-	while (bio_index < bio->bi_vcnt) {
+	bio_for_each_segment_all(bvec, bio, j) {
 		if (!contig)
 			offset = page_offset(bvec->bv_page) + bvec->bv_offset;
 
+		if (!ordered) {
+			ordered = btrfs_lookup_ordered_extent(inode, offset);
+			BUG_ON(!ordered); /* Logic error */
+		}
+
 		data = kmap_atomic(bvec->bv_page);
 
 		nr_sectors = BTRFS_BYTES_TO_BLKS(root->fs_info,
@@ -529,9 +521,6 @@ int btrfs_csum_one_bio(struct btrfs_root *root, struct inode *inode,
 		}
 
 		kunmap_atomic(data);
-
-		bio_index++;
-		bvec++;
 	}
 	this_sum_bytes = 0;
 	btrfs_add_ordered_sum(inode, ordered, sums);
@@ -689,7 +678,7 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans,
 			item_offset = btrfs_item_ptr_offset(leaf,
 							    path->slots[0]);
 
-			memset_extent_buffer(leaf, 0, item_offset + offset,
+			memzero_extent_buffer(leaf, item_offset + offset,
 					     shift_len);
 			key.offset = bytenr;
 
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 3a14c87d9c92..3c1f4be36f16 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -27,7 +27,6 @@
 #include <linux/falloc.h>
 #include <linux/swap.h>
 #include <linux/writeback.h>
-#include <linux/statfs.h>
 #include <linux/compat.h>
 #include <linux/slab.h>
 #include <linux/btrfs.h>
@@ -706,6 +705,7 @@ int __btrfs_drop_extents(struct btrfs_trans_handle *trans,
 	u64 num_bytes = 0;
 	u64 extent_offset = 0;
 	u64 extent_end = 0;
+	u64 last_end = start;
 	int del_nr = 0;
 	int del_slot = 0;
 	int extent_type;
@@ -797,8 +797,10 @@ next_slot:
 		 * extent item in the call to setup_items_for_insert() later
 		 * in this function.
 		 */
-		if (extent_end == key.offset && extent_end >= search_start)
+		if (extent_end == key.offset && extent_end >= search_start) {
+			last_end = extent_end;
 			goto delete_extent_item;
+		}
 
 		if (extent_end <= search_start) {
 			path->slots[0]++;
@@ -861,6 +863,12 @@ next_slot:
 			key.offset = start;
 		}
 		/*
+		 * From here on out we will have actually dropped something, so
+		 * last_end can be updated.
+		 */
+		last_end = extent_end;
+
+		/*
 		 *  | ---- range to drop ----- |
 		 *      | -------- extent -------- |
 		 */
@@ -1010,7 +1018,7 @@ delete_extent_item:
 	if (!replace_extent || !(*key_inserted))
 		btrfs_release_path(path);
 	if (drop_end)
-		*drop_end = found ? min(end, extent_end) : end;
+		*drop_end = found ? min(end, last_end) : end;
 	return ret;
 }
 
@@ -2224,9 +2232,15 @@ static int fill_holes(struct btrfs_trans_handle *trans, struct inode *inode,
 	key.offset = offset;
 
 	ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
-	if (ret < 0)
+	if (ret <= 0) {
+		/*
+		 * We should have dropped this offset, so if we find it then
+		 * something has gone horribly wrong.
+		 */
+		if (ret == 0)
+			ret = -EINVAL;
 		return ret;
-	BUG_ON(!ret);
+	}
 
 	leaf = path->nodes[0];
 	if (hole_mergeable(inode, leaf, path->slots[0]-1, offset, end)) {
@@ -2525,10 +2539,17 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 
 		trans->block_rsv = &root->fs_info->trans_block_rsv;
 
-		if (cur_offset < ino_size) {
+		if (cur_offset < drop_end && cur_offset < ino_size) {
 			ret = fill_holes(trans, inode, path, cur_offset,
 					 drop_end);
 			if (ret) {
+				/*
+				 * If we failed then we didn't insert our hole
+				 * entries for the area we dropped, so now the
+				 * fs is corrupted, so we must abort the
+				 * transaction.
+				 */
+				btrfs_abort_transaction(trans, ret);
 				err = ret;
 				break;
 			}
@@ -2593,6 +2614,8 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	if (cur_offset < ino_size && cur_offset < drop_end) {
 		ret = fill_holes(trans, inode, path, cur_offset, drop_end);
 		if (ret) {
+			/* Same comment as above. */
+			btrfs_abort_transaction(trans, ret);
 			err = ret;
 			goto out_trans;
 		}
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index e4b48f377d3a..c698dccb3757 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -75,8 +75,6 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root,
 	btrfs_release_path(path);
 
 	inode = btrfs_iget(root->fs_info->sb, &location, root, NULL);
-	if (!inode)
-		return ERR_PTR(-ENOENT);
 	if (IS_ERR(inode))
 		return inode;
 	if (is_bad_inode(inode)) {
@@ -153,7 +151,7 @@ static int __create_free_space_inode(struct btrfs_root *root,
 	inode_item = btrfs_item_ptr(leaf, path->slots[0],
 				    struct btrfs_inode_item);
 	btrfs_item_key(leaf, &disk_key, path->slots[0]);
-	memset_extent_buffer(leaf, 0, (unsigned long)inode_item,
+	memzero_extent_buffer(leaf, (unsigned long)inode_item,
 			     sizeof(*inode_item));
 	btrfs_set_inode_generation(leaf, inode_item, trans->transid);
 	btrfs_set_inode_size(leaf, inode_item, 0);
@@ -181,7 +179,7 @@ static int __create_free_space_inode(struct btrfs_root *root,
 	leaf = path->nodes[0];
 	header = btrfs_item_ptr(leaf, path->slots[0],
 				struct btrfs_free_space_header);
-	memset_extent_buffer(leaf, 0, (unsigned long)header, sizeof(*header));
+	memzero_extent_buffer(leaf, (unsigned long)header, sizeof(*header));
 	btrfs_set_free_space_key(leaf, header, &disk_key);
 	btrfs_mark_buffer_dirty(leaf);
 	btrfs_release_path(path);
@@ -476,7 +474,7 @@ static void io_ctl_set_crc(struct btrfs_io_ctl *io_ctl, int index)
 
 	crc = btrfs_csum_data(io_ctl->orig + offset, crc,
 			      PAGE_SIZE - offset);
-	btrfs_csum_final(crc, (char *)&crc);
+	btrfs_csum_final(crc, (u8 *)&crc);
 	io_ctl_unmap_page(io_ctl);
 	tmp = page_address(io_ctl->pages[0]);
 	tmp += index;
@@ -504,7 +502,7 @@ static int io_ctl_check_crc(struct btrfs_io_ctl *io_ctl, int index)
 	io_ctl_map_page(io_ctl, 0);
 	crc = btrfs_csum_data(io_ctl->orig + offset, crc,
 			      PAGE_SIZE - offset);
-	btrfs_csum_final(crc, (char *)&crc);
+	btrfs_csum_final(crc, (u8 *)&crc);
 	if (val != crc) {
 		btrfs_err_rl(io_ctl->root->fs_info,
 			"csum mismatch on free space cache");
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 8e3a5a266917..c96d94ef846d 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -30,7 +30,6 @@
 #include <linux/mpage.h>
 #include <linux/swap.h>
 #include <linux/writeback.h>
-#include <linux/statfs.h>
 #include <linux/compat.h>
 #include <linux/bit_spinlock.h>
 #include <linux/xattr.h>
@@ -1864,7 +1863,7 @@ int btrfs_merge_bio_hook(struct page *page, unsigned long offset,
 
 	length = bio->bi_iter.bi_size;
 	map_length = length;
-	ret = btrfs_map_block(root->fs_info, bio_op(bio), logical,
+	ret = btrfs_map_block(root->fs_info, btrfs_op(bio), logical,
 			      &map_length, NULL, 0);
 	if (ret < 0)
 		return ret;
@@ -3103,7 +3102,7 @@ static int __readpage_endio_check(struct inode *inode,
 
 	kaddr = kmap_atomic(page);
 	csum = btrfs_csum_data(kaddr + pgoff, csum,  len);
-	btrfs_csum_final(csum, (char *)&csum);
+	btrfs_csum_final(csum, (u8 *)&csum);
 	if (csum != csum_expected)
 		goto zeroit;
 
@@ -5805,20 +5804,11 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 	int slot;
 	unsigned char d_type;
 	int over = 0;
-	u32 di_cur;
-	u32 di_total;
-	u32 di_len;
-	int key_type = BTRFS_DIR_INDEX_KEY;
 	char tmp_name[32];
 	char *name_ptr;
 	int name_len;
-	int is_curr = 0;	/* ctx->pos points to the current index? */
-	bool emitted;
 	bool put = false;
-
-	/* FIXME, use a real flag for deciding about the key type */
-	if (root->fs_info->tree_root == root)
-		key_type = BTRFS_DIR_ITEM_KEY;
+	struct btrfs_key location;
 
 	if (!dir_emit_dots(file, ctx))
 		return 0;
@@ -5829,14 +5819,11 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 
 	path->reada = READA_FORWARD;
 
-	if (key_type == BTRFS_DIR_INDEX_KEY) {
-		INIT_LIST_HEAD(&ins_list);
-		INIT_LIST_HEAD(&del_list);
-		put = btrfs_readdir_get_delayed_items(inode, &ins_list,
-						      &del_list);
-	}
+	INIT_LIST_HEAD(&ins_list);
+	INIT_LIST_HEAD(&del_list);
+	put = btrfs_readdir_get_delayed_items(inode, &ins_list, &del_list);
 
-	key.type = key_type;
+	key.type = BTRFS_DIR_INDEX_KEY;
 	key.offset = ctx->pos;
 	key.objectid = btrfs_ino(inode);
 
@@ -5844,7 +5831,6 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 	if (ret < 0)
 		goto err;
 
-	emitted = false;
 	while (1) {
 		leaf = path->nodes[0];
 		slot = path->slots[0];
@@ -5862,98 +5848,52 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 
 		if (found_key.objectid != key.objectid)
 			break;
-		if (found_key.type != key_type)
+		if (found_key.type != BTRFS_DIR_INDEX_KEY)
 			break;
 		if (found_key.offset < ctx->pos)
 			goto next;
-		if (key_type == BTRFS_DIR_INDEX_KEY &&
-		    btrfs_should_delete_dir_index(&del_list,
-						  found_key.offset))
+		if (btrfs_should_delete_dir_index(&del_list, found_key.offset))
 			goto next;
 
 		ctx->pos = found_key.offset;
-		is_curr = 1;
 
 		di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item);
-		di_cur = 0;
-		di_total = btrfs_item_size(leaf, item);
-
-		while (di_cur < di_total) {
-			struct btrfs_key location;
-
-			if (verify_dir_item(root, leaf, di))
-				break;
+		if (verify_dir_item(root, leaf, di))
+			goto next;
 
-			name_len = btrfs_dir_name_len(leaf, di);
-			if (name_len <= sizeof(tmp_name)) {
-				name_ptr = tmp_name;
-			} else {
-				name_ptr = kmalloc(name_len, GFP_KERNEL);
-				if (!name_ptr) {
-					ret = -ENOMEM;
-					goto err;
-				}
+		name_len = btrfs_dir_name_len(leaf, di);
+		if (name_len <= sizeof(tmp_name)) {
+			name_ptr = tmp_name;
+		} else {
+			name_ptr = kmalloc(name_len, GFP_KERNEL);
+			if (!name_ptr) {
+				ret = -ENOMEM;
+				goto err;
 			}
-			read_extent_buffer(leaf, name_ptr,
-					   (unsigned long)(di + 1), name_len);
-
-			d_type = btrfs_filetype_table[btrfs_dir_type(leaf, di)];
-			btrfs_dir_item_key_to_cpu(leaf, di, &location);
+		}
+		read_extent_buffer(leaf, name_ptr, (unsigned long)(di + 1),
+				   name_len);
 
+		d_type = btrfs_filetype_table[btrfs_dir_type(leaf, di)];
+		btrfs_dir_item_key_to_cpu(leaf, di, &location);
 
-			/* is this a reference to our own snapshot? If so
-			 * skip it.
-			 *
-			 * In contrast to old kernels, we insert the snapshot's
-			 * dir item and dir index after it has been created, so
-			 * we won't find a reference to our own snapshot. We
-			 * still keep the following code for backward
-			 * compatibility.
-			 */
-			if (location.type == BTRFS_ROOT_ITEM_KEY &&
-			    location.objectid == root->root_key.objectid) {
-				over = 0;
-				goto skip;
-			}
-			over = !dir_emit(ctx, name_ptr, name_len,
-				       location.objectid, d_type);
+		over = !dir_emit(ctx, name_ptr, name_len, location.objectid,
+				 d_type);
 
-skip:
-			if (name_ptr != tmp_name)
-				kfree(name_ptr);
+		if (name_ptr != tmp_name)
+			kfree(name_ptr);
 
-			if (over)
-				goto nopos;
-			emitted = true;
-			di_len = btrfs_dir_name_len(leaf, di) +
-				 btrfs_dir_data_len(leaf, di) + sizeof(*di);
-			di_cur += di_len;
-			di = (struct btrfs_dir_item *)((char *)di + di_len);
-		}
+		if (over)
+			goto nopos;
+		ctx->pos++;
 next:
 		path->slots[0]++;
 	}
 
-	if (key_type == BTRFS_DIR_INDEX_KEY) {
-		if (is_curr)
-			ctx->pos++;
-		ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list, &emitted);
-		if (ret)
-			goto nopos;
-	}
-
-	/*
-	 * If we haven't emitted any dir entry, we must not touch ctx->pos as
-	 * it was was set to the termination value in previous call. We assume
-	 * that "." and ".." were emitted if we reach this point and set the
-	 * termination value as well for an empty directory.
-	 */
-	if (ctx->pos > 2 && !emitted)
+	ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list);
+	if (ret)
 		goto nopos;
 
-	/* Reached end of directory/root. Bump pos past the last item. */
-	ctx->pos++;
-
 	/*
 	 * Stop new entries from being returned after we return the last
 	 * entry.
@@ -5971,12 +5911,10 @@ next:
 	 * last entry requires it because doing so has broken 32bit apps
 	 * in the past.
 	 */
-	if (key_type == BTRFS_DIR_INDEX_KEY) {
-		if (ctx->pos >= INT_MAX)
-			ctx->pos = LLONG_MAX;
-		else
-			ctx->pos = INT_MAX;
-	}
+	if (ctx->pos >= INT_MAX)
+		ctx->pos = LLONG_MAX;
+	else
+		ctx->pos = INT_MAX;
 nopos:
 	ret = 0;
 err:
@@ -6277,7 +6215,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 
 	inode_item = btrfs_item_ptr(path->nodes[0], path->slots[0],
 				  struct btrfs_inode_item);
-	memset_extent_buffer(path->nodes[0], 0, (unsigned long)inode_item,
+	memzero_extent_buffer(path->nodes[0], (unsigned long)inode_item,
 			     sizeof(*inode_item));
 	fill_inode_item(trans, path->nodes[0], inode_item, inode);
 
@@ -7049,11 +6987,11 @@ insert:
 		 * extent causing the -EEXIST.
 		 */
 		if (existing->start == em->start &&
-		    extent_map_end(existing) == extent_map_end(em) &&
+		    extent_map_end(existing) >= extent_map_end(em) &&
 		    em->block_start == existing->block_start) {
 			/*
-			 * these two extents are the same, it happens
-			 * with inlines especially
+			 * The existing extent map already encompasses the
+			 * entire extent map we tried to add.
 			 */
 			free_extent_map(em);
 			em = existing;
@@ -7783,10 +7721,12 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 	}
 
 	/*
-	 * this will cow the extent, reset the len in case we changed
-	 * it above
+	 * this will cow the extent, if em is within [start, len], then
+	 * probably we've found a preallocated/existing extent, let's
+	 * give it a chance to use preallocated space.
 	 */
-	len = bh_result->b_size;
+	len = min_t(u64, bh_result->b_size, em->len - (start - em->start));
+	len = ALIGN(len, root->sectorsize);
 	free_extent_map(em);
 	em = btrfs_new_extent_direct(inode, start, len);
 	if (IS_ERR(em)) {
@@ -8394,7 +8334,7 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip,
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct bio *bio;
 	struct bio *orig_bio = dip->orig_bio;
-	struct bio_vec *bvec = orig_bio->bi_io_vec;
+	struct bio_vec *bvec;
 	u64 start_sector = orig_bio->bi_iter.bi_sector;
 	u64 file_offset = dip->logical_offset;
 	u64 submit_len = 0;
@@ -8403,10 +8343,10 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip,
 	int async_submit = 0;
 	int nr_sectors;
 	int ret;
-	int i;
+	int i, j;
 
 	map_length = orig_bio->bi_iter.bi_size;
-	ret = btrfs_map_block(root->fs_info, bio_op(orig_bio),
+	ret = btrfs_map_block(root->fs_info, btrfs_op(orig_bio),
 			      start_sector << 9, &map_length, NULL, 0);
 	if (ret)
 		return -EIO;
@@ -8433,7 +8373,7 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip,
 	btrfs_io_bio(bio)->logical = file_offset;
 	atomic_inc(&dip->pending_bios);
 
-	while (bvec <= (orig_bio->bi_io_vec + orig_bio->bi_vcnt - 1)) {
+	bio_for_each_segment_all(bvec, orig_bio, j) {
 		nr_sectors = BTRFS_BYTES_TO_BLKS(root->fs_info, bvec->bv_len);
 		i = 0;
 next_block:
@@ -8472,7 +8412,7 @@ next_block:
 			btrfs_io_bio(bio)->logical = file_offset;
 
 			map_length = orig_bio->bi_iter.bi_size;
-			ret = btrfs_map_block(root->fs_info, bio_op(orig_bio),
+			ret = btrfs_map_block(root->fs_info, btrfs_op(orig_bio),
 					      start_sector << 9,
 					      &map_length, NULL, 0);
 			if (ret) {
@@ -8487,7 +8427,6 @@ next_block:
 				i++;
 				goto next_block;
 			}
-			bvec++;
 		}
 	}
 
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 7acbd2cf6192..4a20f3e68cb4 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -33,7 +33,6 @@
 #include <linux/namei.h>
 #include <linux/swap.h>
 #include <linux/writeback.h>
-#include <linux/statfs.h>
 #include <linux/compat.h>
 #include <linux/bit_spinlock.h>
 #include <linux/security.h>
@@ -502,17 +501,15 @@ static noinline int create_subvol(struct inode *dir,
 		goto fail;
 	}
 
-	memset_extent_buffer(leaf, 0, 0, sizeof(struct btrfs_header));
+	memzero_extent_buffer(leaf, 0, sizeof(struct btrfs_header));
 	btrfs_set_header_bytenr(leaf, leaf->start);
 	btrfs_set_header_generation(leaf, trans->transid);
 	btrfs_set_header_backref_rev(leaf, BTRFS_MIXED_BACKREF_REV);
 	btrfs_set_header_owner(leaf, objectid);
 
-	write_extent_buffer(leaf, root->fs_info->fsid, btrfs_header_fsid(),
-			    BTRFS_FSID_SIZE);
-	write_extent_buffer(leaf, root->fs_info->chunk_tree_uuid,
-			    btrfs_header_chunk_tree_uuid(leaf),
-			    BTRFS_UUID_SIZE);
+	write_extent_buffer_fsid(leaf, root->fs_info->fsid);
+	write_extent_buffer_chunk_tree_uuid(leaf,
+			root->fs_info->chunk_tree_uuid);
 	btrfs_mark_buffer_dirty(leaf);
 
 	inode_item = &root_item->inode;
@@ -4572,11 +4569,8 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_root *root,
 		return -EPERM;
 
 	loi = memdup_user(arg, sizeof(*loi));
-	if (IS_ERR(loi)) {
-		ret = PTR_ERR(loi);
-		loi = NULL;
-		goto out;
-	}
+	if (IS_ERR(loi))
+		return PTR_ERR(loi);
 
 	path = btrfs_alloc_path();
 	if (!path) {
@@ -5203,11 +5197,8 @@ static long btrfs_ioctl_set_received_subvol_32(struct file *file,
 	int ret = 0;
 
 	args32 = memdup_user(arg, sizeof(*args32));
-	if (IS_ERR(args32)) {
-		ret = PTR_ERR(args32);
-		args32 = NULL;
-		goto out;
-	}
+	if (IS_ERR(args32))
+		return PTR_ERR(args32);
 
 	args64 = kmalloc(sizeof(*args64), GFP_KERNEL);
 	if (!args64) {
@@ -5255,11 +5246,8 @@ static long btrfs_ioctl_set_received_subvol(struct file *file,
 	int ret = 0;
 
 	sa = memdup_user(arg, sizeof(*sa));
-	if (IS_ERR(sa)) {
-		ret = PTR_ERR(sa);
-		sa = NULL;
-		goto out;
-	}
+	if (IS_ERR(sa))
+		return PTR_ERR(sa);
 
 	ret = _btrfs_ioctl_set_received_subvol(file, sa);
 
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index 48655da0f4ca..45d26980caf9 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -254,25 +254,21 @@ out:
 	return ret;
 }
 
-static int lzo_decompress_biovec(struct list_head *ws,
+static int lzo_decompress_bio(struct list_head *ws,
 				 struct page **pages_in,
 				 u64 disk_start,
-				 struct bio_vec *bvec,
-				 int vcnt,
+				 struct bio *orig_bio,
 				 size_t srclen)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	int ret = 0, ret2;
 	char *data_in;
 	unsigned long page_in_index = 0;
-	unsigned long page_out_index = 0;
 	unsigned long total_pages_in = DIV_ROUND_UP(srclen, PAGE_SIZE);
 	unsigned long buf_start;
 	unsigned long buf_offset = 0;
 	unsigned long bytes;
 	unsigned long working_bytes;
-	unsigned long pg_offset;
-
 	size_t in_len;
 	size_t out_len;
 	unsigned long in_offset;
@@ -292,7 +288,6 @@ static int lzo_decompress_biovec(struct list_head *ws,
 	in_page_bytes_left = PAGE_SIZE - LZO_LEN;
 
 	tot_out = 0;
-	pg_offset = 0;
 
 	while (tot_in < tot_len) {
 		in_len = read_compress_length(data_in + in_offset);
@@ -365,16 +360,14 @@ cont:
 		tot_out += out_len;
 
 		ret2 = btrfs_decompress_buf2page(workspace->buf, buf_start,
-						 tot_out, disk_start,
-						 bvec, vcnt,
-						 &page_out_index, &pg_offset);
+						 tot_out, disk_start, orig_bio);
 		if (ret2 == 0)
 			break;
 	}
 done:
 	kunmap(pages_in[page_in_index]);
 	if (!ret)
-		btrfs_clear_biovec_end(bvec, vcnt, page_out_index, pg_offset);
+		zero_fill_bio(orig_bio);
 	return ret;
 }
 
@@ -438,6 +431,6 @@ const struct btrfs_compress_op btrfs_lzo_compress = {
 	.alloc_workspace	= lzo_alloc_workspace,
 	.free_workspace		= lzo_free_workspace,
 	.compress_pages		= lzo_compress_pages,
-	.decompress_biovec	= lzo_decompress_biovec,
+	.decompress_bio		= lzo_decompress_bio,
 	.decompress		= lzo_decompress,
 };
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 11f4fffe503e..605a3227980a 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -131,8 +131,15 @@ struct btrfs_qgroup_list {
 	struct btrfs_qgroup *member;
 };
 
-#define ptr_to_u64(x) ((u64)(uintptr_t)x)
-#define u64_to_ptr(x) ((struct btrfs_qgroup *)(uintptr_t)x)
+static inline u64 qgroup_to_aux(struct btrfs_qgroup *qg)
+{
+	return (u64)(uintptr_t)qg;
+}
+
+static inline struct btrfs_qgroup* unode_aux_to_qgroup(struct ulist_node *n)
+{
+	return (struct btrfs_qgroup *)(uintptr_t)n->aux;
+}
 
 static int
 qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
@@ -1066,7 +1073,7 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info,
 	/* Get all of the parent groups that contain this qgroup */
 	list_for_each_entry(glist, &qgroup->groups, next_group) {
 		ret = ulist_add(tmp, glist->group->qgroupid,
-				ptr_to_u64(glist->group), GFP_ATOMIC);
+				qgroup_to_aux(glist->group), GFP_ATOMIC);
 		if (ret < 0)
 			goto out;
 	}
@@ -1074,7 +1081,7 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info,
 	/* Iterate all of the parents and adjust their reference counts */
 	ULIST_ITER_INIT(&uiter);
 	while ((unode = ulist_next(tmp, &uiter))) {
-		qgroup = u64_to_ptr(unode->aux);
+		qgroup = unode_aux_to_qgroup(unode);
 		qgroup->rfer += sign * num_bytes;
 		qgroup->rfer_cmpr += sign * num_bytes;
 		WARN_ON(sign < 0 && qgroup->excl < num_bytes);
@@ -1087,7 +1094,7 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info,
 		/* Add any parents of the parents */
 		list_for_each_entry(glist, &qgroup->groups, next_group) {
 			ret = ulist_add(tmp, glist->group->qgroupid,
-					ptr_to_u64(glist->group), GFP_ATOMIC);
+					qgroup_to_aux(glist->group), GFP_ATOMIC);
 			if (ret < 0)
 				goto out;
 		}
@@ -1450,7 +1457,7 @@ int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
-int btrfs_qgroup_insert_dirty_extent_nolock(struct btrfs_fs_info *fs_info,
+int btrfs_qgroup_trace_extent_nolock(struct btrfs_fs_info *fs_info,
 				struct btrfs_delayed_ref_root *delayed_refs,
 				struct btrfs_qgroup_extent_record *record)
 {
@@ -1460,7 +1467,7 @@ int btrfs_qgroup_insert_dirty_extent_nolock(struct btrfs_fs_info *fs_info,
 	u64 bytenr = record->bytenr;
 
 	assert_spin_locked(&delayed_refs->lock);
-	trace_btrfs_qgroup_insert_dirty_extent(fs_info, record);
+	trace_btrfs_qgroup_trace_extent(fs_info, record);
 
 	while (*p) {
 		parent_node = *p;
@@ -1479,7 +1486,7 @@ int btrfs_qgroup_insert_dirty_extent_nolock(struct btrfs_fs_info *fs_info,
 	return 0;
 }
 
-int btrfs_qgroup_insert_dirty_extent(struct btrfs_trans_handle *trans,
+int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans,
 		struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes,
 		gfp_t gfp_flag)
 {
@@ -1502,7 +1509,7 @@ int btrfs_qgroup_insert_dirty_extent(struct btrfs_trans_handle *trans,
 	record->old_roots = NULL;
 
 	spin_lock(&delayed_refs->lock);
-	ret = btrfs_qgroup_insert_dirty_extent_nolock(fs_info, delayed_refs,
+	ret = btrfs_qgroup_trace_extent_nolock(fs_info, delayed_refs,
 						      record);
 	spin_unlock(&delayed_refs->lock);
 	if (ret > 0)
@@ -1510,6 +1517,219 @@ int btrfs_qgroup_insert_dirty_extent(struct btrfs_trans_handle *trans,
 	return 0;
 }
 
+int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans,
+				  struct btrfs_root *root,
+				  struct extent_buffer *eb)
+{
+	int nr = btrfs_header_nritems(eb);
+	int i, extent_type, ret;
+	struct btrfs_key key;
+	struct btrfs_file_extent_item *fi;
+	u64 bytenr, num_bytes;
+
+	/* We can be called directly from walk_up_proc() */
+	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &root->fs_info->flags))
+		return 0;
+
+	for (i = 0; i < nr; i++) {
+		btrfs_item_key_to_cpu(eb, &key, i);
+
+		if (key.type != BTRFS_EXTENT_DATA_KEY)
+			continue;
+
+		fi = btrfs_item_ptr(eb, i, struct btrfs_file_extent_item);
+		/* filter out non qgroup-accountable extents  */
+		extent_type = btrfs_file_extent_type(eb, fi);
+
+		if (extent_type == BTRFS_FILE_EXTENT_INLINE)
+			continue;
+
+		bytenr = btrfs_file_extent_disk_bytenr(eb, fi);
+		if (!bytenr)
+			continue;
+
+		num_bytes = btrfs_file_extent_disk_num_bytes(eb, fi);
+
+		ret = btrfs_qgroup_trace_extent(trans, root->fs_info,
+						bytenr, num_bytes, GFP_NOFS);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+/*
+ * Walk up the tree from the bottom, freeing leaves and any interior
+ * nodes which have had all slots visited. If a node (leaf or
+ * interior) is freed, the node above it will have it's slot
+ * incremented. The root node will never be freed.
+ *
+ * At the end of this function, we should have a path which has all
+ * slots incremented to the next position for a search. If we need to
+ * read a new node it will be NULL and the node above it will have the
+ * correct slot selected for a later read.
+ *
+ * If we increment the root nodes slot counter past the number of
+ * elements, 1 is returned to signal completion of the search.
+ */
+static int adjust_slots_upwards(struct btrfs_root *root,
+				struct btrfs_path *path, int root_level)
+{
+	int level = 0;
+	int nr, slot;
+	struct extent_buffer *eb;
+
+	if (root_level == 0)
+		return 1;
+
+	while (level <= root_level) {
+		eb = path->nodes[level];
+		nr = btrfs_header_nritems(eb);
+		path->slots[level]++;
+		slot = path->slots[level];
+		if (slot >= nr || level == 0) {
+			/*
+			 * Don't free the root -  we will detect this
+			 * condition after our loop and return a
+			 * positive value for caller to stop walking the tree.
+			 */
+			if (level != root_level) {
+				btrfs_tree_unlock_rw(eb, path->locks[level]);
+				path->locks[level] = 0;
+
+				free_extent_buffer(eb);
+				path->nodes[level] = NULL;
+				path->slots[level] = 0;
+			}
+		} else {
+			/*
+			 * We have a valid slot to walk back down
+			 * from. Stop here so caller can process these
+			 * new nodes.
+			 */
+			break;
+		}
+
+		level++;
+	}
+
+	eb = path->nodes[root_level];
+	if (path->slots[root_level] >= btrfs_header_nritems(eb))
+		return 1;
+
+	return 0;
+}
+
+int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans,
+			       struct btrfs_root *root,
+			       struct extent_buffer *root_eb,
+			       u64 root_gen, int root_level)
+{
+	int ret = 0;
+	int level;
+	struct extent_buffer *eb = root_eb;
+	struct btrfs_path *path = NULL;
+
+	BUG_ON(root_level < 0 || root_level > BTRFS_MAX_LEVEL);
+	BUG_ON(root_eb == NULL);
+
+	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &root->fs_info->flags))
+		return 0;
+
+	if (!extent_buffer_uptodate(root_eb)) {
+		ret = btrfs_read_buffer(root_eb, root_gen);
+		if (ret)
+			goto out;
+	}
+
+	if (root_level == 0) {
+		ret = btrfs_qgroup_trace_leaf_items(trans, root, root_eb);
+		goto out;
+	}
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	/*
+	 * Walk down the tree.  Missing extent blocks are filled in as
+	 * we go. Metadata is accounted every time we read a new
+	 * extent block.
+	 *
+	 * When we reach a leaf, we account for file extent items in it,
+	 * walk back up the tree (adjusting slot pointers as we go)
+	 * and restart the search process.
+	 */
+	extent_buffer_get(root_eb); /* For path */
+	path->nodes[root_level] = root_eb;
+	path->slots[root_level] = 0;
+	path->locks[root_level] = 0; /* so release_path doesn't try to unlock */
+walk_down:
+	level = root_level;
+	while (level >= 0) {
+		if (path->nodes[level] == NULL) {
+			int parent_slot;
+			u64 child_gen;
+			u64 child_bytenr;
+
+			/*
+			 * We need to get child blockptr/gen from parent before
+			 * we can read it.
+			  */
+			eb = path->nodes[level + 1];
+			parent_slot = path->slots[level + 1];
+			child_bytenr = btrfs_node_blockptr(eb, parent_slot);
+			child_gen = btrfs_node_ptr_generation(eb, parent_slot);
+
+			eb = read_tree_block(root, child_bytenr, child_gen);
+			if (IS_ERR(eb)) {
+				ret = PTR_ERR(eb);
+				goto out;
+			} else if (!extent_buffer_uptodate(eb)) {
+				free_extent_buffer(eb);
+				ret = -EIO;
+				goto out;
+			}
+
+			path->nodes[level] = eb;
+			path->slots[level] = 0;
+
+			btrfs_tree_read_lock(eb);
+			btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
+			path->locks[level] = BTRFS_READ_LOCK_BLOCKING;
+
+			ret = btrfs_qgroup_trace_extent(trans,
+					root->fs_info, child_bytenr,
+					root->nodesize, GFP_NOFS);
+			if (ret)
+				goto out;
+		}
+
+		if (level == 0) {
+			ret = btrfs_qgroup_trace_leaf_items(trans, root,
+					path->nodes[level]);
+			if (ret)
+				goto out;
+
+			/* Nonzero return here means we completed our search */
+			ret = adjust_slots_upwards(root, path, root_level);
+			if (ret)
+				break;
+
+			/* Restart search with new slots */
+			goto walk_down;
+		}
+
+		level--;
+	}
+
+	ret = 0;
+out:
+	btrfs_free_path(path);
+
+	return ret;
+}
+
 #define UPDATE_NEW	0
 #define UPDATE_OLD	1
 /*
@@ -1535,30 +1755,30 @@ static int qgroup_update_refcnt(struct btrfs_fs_info *fs_info,
 			continue;
 
 		ulist_reinit(tmp);
-		ret = ulist_add(qgroups, qg->qgroupid, ptr_to_u64(qg),
+		ret = ulist_add(qgroups, qg->qgroupid, qgroup_to_aux(qg),
 				GFP_ATOMIC);
 		if (ret < 0)
 			return ret;
-		ret = ulist_add(tmp, qg->qgroupid, ptr_to_u64(qg), GFP_ATOMIC);
+		ret = ulist_add(tmp, qg->qgroupid, qgroup_to_aux(qg), GFP_ATOMIC);
 		if (ret < 0)
 			return ret;
 		ULIST_ITER_INIT(&tmp_uiter);
 		while ((tmp_unode = ulist_next(tmp, &tmp_uiter))) {
 			struct btrfs_qgroup_list *glist;
 
-			qg = u64_to_ptr(tmp_unode->aux);
+			qg = unode_aux_to_qgroup(tmp_unode);
 			if (update_old)
 				btrfs_qgroup_update_old_refcnt(qg, seq, 1);
 			else
 				btrfs_qgroup_update_new_refcnt(qg, seq, 1);
 			list_for_each_entry(glist, &qg->groups, next_group) {
 				ret = ulist_add(qgroups, glist->group->qgroupid,
-						ptr_to_u64(glist->group),
+						qgroup_to_aux(glist->group),
 						GFP_ATOMIC);
 				if (ret < 0)
 					return ret;
 				ret = ulist_add(tmp, glist->group->qgroupid,
-						ptr_to_u64(glist->group),
+						qgroup_to_aux(glist->group),
 						GFP_ATOMIC);
 				if (ret < 0)
 					return ret;
@@ -1619,7 +1839,7 @@ static int qgroup_update_counters(struct btrfs_fs_info *fs_info,
 	while ((unode = ulist_next(qgroups, &uiter))) {
 		bool dirty = false;
 
-		qg = u64_to_ptr(unode->aux);
+		qg = unode_aux_to_qgroup(unode);
 		cur_old_count = btrfs_qgroup_get_old_refcnt(qg, seq);
 		cur_new_count = btrfs_qgroup_get_new_refcnt(qg, seq);
 
@@ -2125,7 +2345,7 @@ static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes)
 		struct btrfs_qgroup *qg;
 		struct btrfs_qgroup_list *glist;
 
-		qg = u64_to_ptr(unode->aux);
+		qg = unode_aux_to_qgroup(unode);
 
 		if ((qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_RFER) &&
 		    qg->reserved + (s64)qg->rfer + num_bytes >
@@ -2157,7 +2377,7 @@ static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes)
 	while ((unode = ulist_next(fs_info->qgroup_ulist, &uiter))) {
 		struct btrfs_qgroup *qg;
 
-		qg = u64_to_ptr(unode->aux);
+		qg = unode_aux_to_qgroup(unode);
 
 		qg->reserved += num_bytes;
 	}
@@ -2202,7 +2422,7 @@ void btrfs_qgroup_free_refroot(struct btrfs_fs_info *fs_info,
 		struct btrfs_qgroup *qg;
 		struct btrfs_qgroup_list *glist;
 
-		qg = u64_to_ptr(unode->aux);
+		qg = unode_aux_to_qgroup(unode);
 
 		qg->reserved -= num_bytes;
 
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index 1bc64c864b62..99c879dbedc1 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -23,6 +23,34 @@
 #include "delayed-ref.h"
 
 /*
+ * Btrfs qgroup overview
+ *
+ * Btrfs qgroup splits into 3 main part:
+ * 1) Reserve
+ *    Reserve metadata/data space for incoming operations
+ *    Affect how qgroup limit works
+ *
+ * 2) Trace
+ *    Tell btrfs qgroup to trace dirty extents.
+ *
+ *    Dirty extents including:
+ *    - Newly allocated extents
+ *    - Extents going to be deleted (in this trans)
+ *    - Extents whose owner is going to be modified
+ *
+ *    This is the main part affects whether qgroup numbers will stay
+ *    consistent.
+ *    Btrfs qgroup can trace clean extents and won't cause any problem,
+ *    but it will consume extra CPU time, it should be avoided if possible.
+ *
+ * 3) Account
+ *    Btrfs qgroup will updates its numbers, based on dirty extents traced
+ *    in previous step.
+ *
+ *    Normally at qgroup rescan and transaction commit time.
+ */
+
+/*
  * Record a dirty extent, and info qgroup to update quota on it
  * TODO: Use kmem cache to alloc it.
  */
@@ -65,8 +93,8 @@ struct btrfs_delayed_extent_op;
 int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans,
 					 struct btrfs_fs_info *fs_info);
 /*
- * Insert one dirty extent record into @delayed_refs, informing qgroup to
- * account that extent at commit trans time.
+ * Inform qgroup to trace one dirty extent, its info is recorded in @record.
+ * So qgroup can account it at commit trans time.
  *
  * No lock version, caller must acquire delayed ref lock and allocate memory.
  *
@@ -74,14 +102,15 @@ int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans,
  * Return >0 for existing record, caller can free @record safely.
  * Error is not possible
  */
-int btrfs_qgroup_insert_dirty_extent_nolock(
+int btrfs_qgroup_trace_extent_nolock(
 		struct btrfs_fs_info *fs_info,
 		struct btrfs_delayed_ref_root *delayed_refs,
 		struct btrfs_qgroup_extent_record *record);
 
 /*
- * Insert one dirty extent record into @delayed_refs, informing qgroup to
- * account that extent at commit trans time.
+ * Inform qgroup to trace one dirty extent, specified by @bytenr and
+ * @num_bytes.
+ * So qgroup can account it at commit trans time.
  *
  * Better encapsulated version.
  *
@@ -89,10 +118,33 @@ int btrfs_qgroup_insert_dirty_extent_nolock(
  * Return <0 for error, like memory allocation failure or invalid parameter
  * (NULL trans)
  */
-int btrfs_qgroup_insert_dirty_extent(struct btrfs_trans_handle *trans,
+int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans,
 		struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes,
 		gfp_t gfp_flag);
 
+/*
+ * Inform qgroup to trace all leaf items of data
+ *
+ * Return 0 for success
+ * Return <0 for error(ENOMEM)
+ */
+int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans,
+				  struct btrfs_root *root,
+				  struct extent_buffer *eb);
+/*
+ * Inform qgroup to trace a whole subtree, including all its child tree
+ * blocks and data.
+ * The root tree block is specified by @root_eb.
+ *
+ * Normally used by relocation(tree block swap) and subvolume deletion.
+ *
+ * Return 0 for success
+ * Return <0 for error(ENOMEM or tree search error)
+ */
+int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans,
+			       struct btrfs_root *root,
+			       struct extent_buffer *root_eb,
+			       u64 root_gen, int root_level);
 int
 btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans,
 			    struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index d016d4a79864..eece126d6973 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -1144,10 +1144,10 @@ static void validate_rbio_for_rmw(struct btrfs_raid_bio *rbio)
 static void index_rbio_pages(struct btrfs_raid_bio *rbio)
 {
 	struct bio *bio;
+	struct bio_vec *bvec;
 	u64 start;
 	unsigned long stripe_offset;
 	unsigned long page_index;
-	struct page *p;
 	int i;
 
 	spin_lock_irq(&rbio->bio_list_lock);
@@ -1156,10 +1156,8 @@ static void index_rbio_pages(struct btrfs_raid_bio *rbio)
 		stripe_offset = start - rbio->bbio->raid_map[0];
 		page_index = stripe_offset >> PAGE_SHIFT;
 
-		for (i = 0; i < bio->bi_vcnt; i++) {
-			p = bio->bi_io_vec[i].bv_page;
-			rbio->bio_pages[page_index + i] = p;
-		}
+		bio_for_each_segment_all(bvec, bio, i)
+			rbio->bio_pages[page_index + i] = bvec->bv_page;
 	}
 	spin_unlock_irq(&rbio->bio_list_lock);
 }
@@ -1433,13 +1431,11 @@ static int fail_bio_stripe(struct btrfs_raid_bio *rbio,
  */
 static void set_bio_pages_uptodate(struct bio *bio)
 {
+	struct bio_vec *bvec;
 	int i;
-	struct page *p;
 
-	for (i = 0; i < bio->bi_vcnt; i++) {
-		p = bio->bi_io_vec[i].bv_page;
-		SetPageUptodate(p);
-	}
+	bio_for_each_segment_all(bvec, bio, i)
+		SetPageUptodate(bvec->bv_page);
 }
 
 /*
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 75bab76739be..f0beb63a6d82 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -107,18 +107,14 @@ static int reada_add_block(struct reada_control *rc, u64 logical,
 /* in case of err, eb might be NULL */
 static void __readahead_hook(struct btrfs_fs_info *fs_info,
 			     struct reada_extent *re, struct extent_buffer *eb,
-			     u64 start, int err)
+			     int err)
 {
-	int level = 0;
 	int nritems;
 	int i;
 	u64 bytenr;
 	u64 generation;
 	struct list_head list;
 
-	if (eb)
-		level = btrfs_header_level(eb);
-
 	spin_lock(&re->lock);
 	/*
 	 * just take the full list from the extent. afterwards we
@@ -143,7 +139,7 @@ static void __readahead_hook(struct btrfs_fs_info *fs_info,
 	 * trigger more readahead depending from the content, e.g.
 	 * fetch the checksums for the extents in the leaf.
 	 */
-	if (!level)
+	if (!btrfs_header_level(eb))
 		goto cleanup;
 
 	nritems = btrfs_header_nritems(eb);
@@ -213,12 +209,8 @@ cleanup:
 	return;
 }
 
-/*
- * start is passed separately in case eb in NULL, which may be the case with
- * failed I/O
- */
 int btree_readahead_hook(struct btrfs_fs_info *fs_info,
-			 struct extent_buffer *eb, u64 start, int err)
+			 struct extent_buffer *eb, int err)
 {
 	int ret = 0;
 	struct reada_extent *re;
@@ -226,7 +218,7 @@ int btree_readahead_hook(struct btrfs_fs_info *fs_info,
 	/* find extent */
 	spin_lock(&fs_info->reada_lock);
 	re = radix_tree_lookup(&fs_info->reada_tree,
-			       start >> PAGE_SHIFT);
+			       eb->start >> PAGE_SHIFT);
 	if (re)
 		re->refcnt++;
 	spin_unlock(&fs_info->reada_lock);
@@ -235,7 +227,7 @@ int btree_readahead_hook(struct btrfs_fs_info *fs_info,
 		goto start_machine;
 	}
 
-	__readahead_hook(fs_info, re, eb, start, err);
+	__readahead_hook(fs_info, re, eb, err);
 	reada_extent_put(fs_info, re);	/* our ref */
 
 start_machine:
@@ -354,8 +346,8 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
 	 * map block
 	 */
 	length = blocksize;
-	ret = btrfs_map_block(fs_info, REQ_GET_READ_MIRRORS, logical, &length,
-			      &bbio, 0);
+	ret = btrfs_map_block(fs_info, BTRFS_MAP_GET_READ_MIRRORS, logical,
+			&length, &bbio, 0);
 	if (ret || !bbio || length < blocksize)
 		goto error;
 
@@ -401,7 +393,6 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
 	ret = radix_tree_insert(&fs_info->reada_tree, index, re);
 	if (ret == -EEXIST) {
 		re_exist = radix_tree_lookup(&fs_info->reada_tree, index);
-		BUG_ON(!re_exist);
 		re_exist->refcnt++;
 		spin_unlock(&fs_info->reada_lock);
 		btrfs_dev_replace_unlock(&fs_info->dev_replace, 0);
@@ -448,7 +439,6 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
 				/* ignore whether the entry was inserted */
 				radix_tree_delete(&dev->reada_extents, index);
 			}
-			BUG_ON(fs_info == NULL);
 			radix_tree_delete(&fs_info->reada_tree, index);
 			spin_unlock(&fs_info->reada_lock);
 			btrfs_dev_replace_unlock(&fs_info->dev_replace, 0);
@@ -717,9 +707,9 @@ static int reada_start_machine_dev(struct btrfs_fs_info *fs_info,
 	ret = reada_tree_block_flagged(fs_info->extent_root, logical,
 			mirror_num, &eb);
 	if (ret)
-		__readahead_hook(fs_info, re, NULL, logical, ret);
+		__readahead_hook(fs_info, re, NULL, ret);
 	else if (eb)
-		__readahead_hook(fs_info, re, eb, eb->start, ret);
+		__readahead_hook(fs_info, re, eb, ret);
 
 	if (eb)
 		free_extent_buffer(eb);
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index c4af0cdb783d..3dc7232aa038 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -1901,6 +1901,29 @@ again:
 		BUG_ON(ret);
 
 		/*
+		 * Info qgroup to trace both subtrees.
+		 *
+		 * We must trace both trees.
+		 * 1) Tree reloc subtree
+		 *    If not traced, we will leak data numbers
+		 * 2) Fs subtree
+		 *    If not traced, we will double count old data
+		 *    and tree block numbers, if current trans doesn't free
+		 *    data reloc tree inode.
+		 */
+		ret = btrfs_qgroup_trace_subtree(trans, src, parent,
+				btrfs_header_generation(parent),
+				btrfs_header_level(parent));
+		if (ret < 0)
+			break;
+		ret = btrfs_qgroup_trace_subtree(trans, dest,
+				path->nodes[level],
+				btrfs_header_generation(path->nodes[level]),
+				btrfs_header_level(path->nodes[level]));
+		if (ret < 0)
+			break;
+
+		/*
 		 * swap blocks in fs tree and reloc tree.
 		 */
 		btrfs_set_node_blockptr(parent, slot, new_bytenr);
@@ -3949,90 +3972,6 @@ int prepare_to_relocate(struct reloc_control *rc)
 	return 0;
 }
 
-/*
- * Qgroup fixer for data chunk relocation.
- * The data relocation is done in the following steps
- * 1) Copy data extents into data reloc tree
- * 2) Create tree reloc tree(special snapshot) for related subvolumes
- * 3) Modify file extents in tree reloc tree
- * 4) Merge tree reloc tree with original fs tree, by swapping tree blocks
- *
- * The problem is, data and tree reloc tree are not accounted to qgroup,
- * and 4) will only info qgroup to track tree blocks change, not file extents
- * in the tree blocks.
- *
- * The good news is, related data extents are all in data reloc tree, so we
- * only need to info qgroup to track all file extents in data reloc tree
- * before commit trans.
- */
-static int qgroup_fix_relocated_data_extents(struct btrfs_trans_handle *trans,
-					     struct reloc_control *rc)
-{
-	struct btrfs_fs_info *fs_info = rc->extent_root->fs_info;
-	struct inode *inode = rc->data_inode;
-	struct btrfs_root *data_reloc_root = BTRFS_I(inode)->root;
-	struct btrfs_path *path;
-	struct btrfs_key key;
-	int ret = 0;
-
-	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
-		return 0;
-
-	/*
-	 * Only for stage where we update data pointers the qgroup fix is
-	 * valid.
-	 * For MOVING_DATA stage, we will miss the timing of swapping tree
-	 * blocks, and won't fix it.
-	 */
-	if (!(rc->stage == UPDATE_DATA_PTRS && rc->extents_found))
-		return 0;
-
-	path = btrfs_alloc_path();
-	if (!path)
-		return -ENOMEM;
-	key.objectid = btrfs_ino(inode);
-	key.type = BTRFS_EXTENT_DATA_KEY;
-	key.offset = 0;
-
-	ret = btrfs_search_slot(NULL, data_reloc_root, &key, path, 0, 0);
-	if (ret < 0)
-		goto out;
-
-	lock_extent(&BTRFS_I(inode)->io_tree, 0, (u64)-1);
-	while (1) {
-		struct btrfs_file_extent_item *fi;
-
-		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
-		if (key.objectid > btrfs_ino(inode))
-			break;
-		if (key.type != BTRFS_EXTENT_DATA_KEY)
-			goto next;
-		fi = btrfs_item_ptr(path->nodes[0], path->slots[0],
-				    struct btrfs_file_extent_item);
-		if (btrfs_file_extent_type(path->nodes[0], fi) !=
-				BTRFS_FILE_EXTENT_REG)
-			goto next;
-		ret = btrfs_qgroup_insert_dirty_extent(trans, fs_info,
-			btrfs_file_extent_disk_bytenr(path->nodes[0], fi),
-			btrfs_file_extent_disk_num_bytes(path->nodes[0], fi),
-			GFP_NOFS);
-		if (ret < 0)
-			break;
-next:
-		ret = btrfs_next_item(data_reloc_root, path);
-		if (ret < 0)
-			break;
-		if (ret > 0) {
-			ret = 0;
-			break;
-		}
-	}
-	unlock_extent(&BTRFS_I(inode)->io_tree, 0 , (u64)-1);
-out:
-	btrfs_free_path(path);
-	return ret;
-}
-
 static noinline_for_stack int relocate_block_group(struct reloc_control *rc)
 {
 	struct rb_root blocks = RB_ROOT;
@@ -4223,13 +4162,6 @@ restart:
 		err = PTR_ERR(trans);
 		goto out_free;
 	}
-	ret = qgroup_fix_relocated_data_extents(trans, rc);
-	if (ret < 0) {
-		btrfs_abort_transaction(trans, ret);
-		if (!err)
-			err = ret;
-		goto out_free;
-	}
 	btrfs_commit_transaction(trans, rc->extent_root);
 out_free:
 	btrfs_free_block_rsv(rc->extent_root, rc->block_rsv);
@@ -4255,7 +4187,7 @@ static int __insert_orphan_inode(struct btrfs_trans_handle *trans,
 
 	leaf = path->nodes[0];
 	item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_inode_item);
-	memset_extent_buffer(leaf, 0, (unsigned long)item, sizeof(*item));
+	memzero_extent_buffer(leaf, (unsigned long)item, sizeof(*item));
 	btrfs_set_inode_generation(leaf, item, 1);
 	btrfs_set_inode_size(leaf, item, 0);
 	btrfs_set_inode_mode(leaf, item, S_IFREG | 0600);
@@ -4333,6 +4265,45 @@ static struct reloc_control *alloc_reloc_control(struct btrfs_fs_info *fs_info)
 }
 
 /*
+ * Print the block group being relocated
+ */
+static void describe_relocation(struct btrfs_fs_info *fs_info,
+				struct btrfs_block_group_cache *block_group)
+{
+	char buf[128];		/* prefixed by a '|' that'll be dropped */
+	u64 flags = block_group->flags;
+
+	/* Shouldn't happen */
+	if (!flags) {
+		strcpy(buf, "|NONE");
+	} else {
+		char *bp = buf;
+
+#define DESCRIBE_FLAG(f, d) \
+		if (flags & BTRFS_BLOCK_GROUP_##f) { \
+			bp += snprintf(bp, buf - bp + sizeof(buf), "|%s", d); \
+			flags &= ~BTRFS_BLOCK_GROUP_##f; \
+		}
+		DESCRIBE_FLAG(DATA,     "data");
+		DESCRIBE_FLAG(SYSTEM,   "system");
+		DESCRIBE_FLAG(METADATA, "metadata");
+		DESCRIBE_FLAG(RAID0,    "raid0");
+		DESCRIBE_FLAG(RAID1,    "raid1");
+		DESCRIBE_FLAG(DUP,      "dup");
+		DESCRIBE_FLAG(RAID10,   "raid10");
+		DESCRIBE_FLAG(RAID5,    "raid5");
+		DESCRIBE_FLAG(RAID6,    "raid6");
+		if (flags)
+			snprintf(buf, buf - bp + sizeof(buf), "|0x%llx", flags);
+#undef DESCRIBE_FLAG
+	}
+
+	btrfs_info(fs_info,
+		   "relocating block group %llu flags %s",
+		   block_group->key.objectid, buf + 1);
+}
+
+/*
  * function to relocate all extents in a block group.
  */
 int btrfs_relocate_block_group(struct btrfs_root *extent_root, u64 group_start)
@@ -4388,9 +4359,7 @@ int btrfs_relocate_block_group(struct btrfs_root *extent_root, u64 group_start)
 		goto out;
 	}
 
-	btrfs_info(extent_root->fs_info,
-		   "relocating block group %llu flags %llu",
-		   rc->block_group->key.objectid, rc->block_group->flags);
+	describe_relocation(extent_root->fs_info, rc->block_group);
 
 	btrfs_wait_block_group_reservations(rc->block_group);
 	btrfs_wait_nocow_writers(rc->block_group);
@@ -4598,11 +4567,6 @@ int btrfs_recover_relocation(struct btrfs_root *root)
 		err = PTR_ERR(trans);
 		goto out_free;
 	}
-	err = qgroup_fix_relocated_data_extents(trans, rc);
-	if (err < 0) {
-		btrfs_abort_transaction(trans, err);
-		goto out_free;
-	}
 	err = btrfs_commit_transaction(trans, rc->extent_root);
 out_free:
 	kfree(rc);
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index fffb9ab8526e..589d79219c18 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1334,8 +1334,8 @@ static int scrub_setup_recheck_block(struct scrub_block *original_sblock,
 		 * with a length of PAGE_SIZE, each returned stripe
 		 * represents one mirror
 		 */
-		ret = btrfs_map_sblock(fs_info, REQ_GET_READ_MIRRORS, logical,
-				       &mapped_length, &bbio, 0, 1);
+		ret = btrfs_map_sblock(fs_info, BTRFS_MAP_GET_READ_MIRRORS,
+				logical, &mapped_length, &bbio, 0, 1);
 		if (ret || !bbio || mapped_length < sublen) {
 			btrfs_put_bbio(bbio);
 			return -EIO;
@@ -2191,8 +2191,8 @@ static void scrub_missing_raid56_pages(struct scrub_block *sblock)
 	int ret;
 	int i;
 
-	ret = btrfs_map_sblock(fs_info, REQ_GET_READ_MIRRORS, logical, &length,
-			       &bbio, 0, 1);
+	ret = btrfs_map_sblock(fs_info, BTRFS_MAP_GET_READ_MIRRORS, logical,
+			&length, &bbio, 0, 1);
 	if (ret || !bbio || !bbio->raid_map)
 		goto bbio_out;
 
@@ -2778,7 +2778,7 @@ static void scrub_parity_check_and_repair(struct scrub_parity *sparity)
 		goto out;
 
 	length = sparity->logic_end - sparity->logic_start;
-	ret = btrfs_map_sblock(sctx->dev_root->fs_info, WRITE,
+	ret = btrfs_map_sblock(sctx->dev_root->fs_info, BTRFS_MAP_WRITE,
 			       sparity->logic_start,
 			       &length, &bbio, 0, 1);
 	if (ret || !bbio || !bbio->raid_map)
@@ -2988,8 +2988,9 @@ again:
 
 			mapped_length = extent_len;
 			bbio = NULL;
-			ret = btrfs_map_block(fs_info, READ, extent_logical,
-					      &mapped_length, &bbio, 0);
+			ret = btrfs_map_block(fs_info, BTRFS_MAP_READ,
+					extent_logical, &mapped_length, &bbio,
+					0);
 			if (!ret) {
 				if (!bbio || mapped_length < extent_len)
 					ret = -EIO;
@@ -4076,7 +4077,7 @@ static void scrub_remap_extent(struct btrfs_fs_info *fs_info,
 	int ret;
 
 	mapped_length = extent_len;
-	ret = btrfs_map_block(fs_info, READ, extent_logical,
+	ret = btrfs_map_block(fs_info, BTRFS_MAP_READ, extent_logical,
 			      &mapped_length, &bbio, 0);
 	if (ret || !bbio || mapped_length < extent_len ||
 	    !bbio->stripes[0].dev->bdev) {
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 74ed5aae6cea..adec3a0b01d5 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -2086,10 +2086,6 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	u64 thresh = 0;
 	int mixed = 0;
 
-	/*
-	 * holding chunk_mutex to avoid allocating new chunks, holding
-	 * device_list_mutex to avoid the device being removed
-	 */
 	rcu_read_lock();
 	list_for_each_entry_rcu(found, head, list) {
 		if (found->flags & BTRFS_BLOCK_GROUP_DATA) {
diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c
index caad80bb9bd0..2c7a0a922510 100644
--- a/fs/btrfs/tests/extent-io-tests.c
+++ b/fs/btrfs/tests/extent-io-tests.c
@@ -306,7 +306,7 @@ static int __test_eb_bitmaps(unsigned long *bitmap, struct extent_buffer *eb,
 	int ret;
 
 	memset(bitmap, 0, len);
-	memset_extent_buffer(eb, 0, 0, len);
+	memzero_extent_buffer(eb, 0, len);
 	if (memcmp_extent_buffer(eb, bitmap, 0, len) != 0) {
 		test_msg("Bitmap was not zeroed\n");
 		return -EINVAL;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 3d33c4e41e5f..e0478f51cf16 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -689,7 +689,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 		 * as the owner of the file extent changed from log tree
 		 * (doesn't affect qgroup) to fs/file tree(affects qgroup)
 		 */
-		ret = btrfs_qgroup_insert_dirty_extent(trans, root->fs_info,
+		ret = btrfs_qgroup_trace_extent(trans, root->fs_info,
 				btrfs_file_extent_disk_bytenr(eb, item),
 				btrfs_file_extent_disk_num_bytes(eb, item),
 				GFP_NOFS);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 71a60cc01451..1886b94f13ac 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1595,8 +1595,8 @@ static int btrfs_alloc_dev_extent(struct btrfs_trans_handle *trans,
 	btrfs_set_dev_extent_chunk_objectid(leaf, extent, chunk_objectid);
 	btrfs_set_dev_extent_chunk_offset(leaf, extent, chunk_offset);
 
-	write_extent_buffer(leaf, root->fs_info->chunk_tree_uuid,
-		    btrfs_dev_extent_chunk_tree_uuid(extent), BTRFS_UUID_SIZE);
+	write_extent_buffer_chunk_tree_uuid(leaf,
+			root->fs_info->chunk_tree_uuid);
 
 	btrfs_set_dev_extent_length(leaf, extent, num_bytes);
 	btrfs_mark_buffer_dirty(leaf);
@@ -3062,7 +3062,7 @@ static int insert_balance_item(struct btrfs_root *root,
 	leaf = path->nodes[0];
 	item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_balance_item);
 
-	memset_extent_buffer(leaf, 0, (unsigned long)item, sizeof(*item));
+	memzero_extent_buffer(leaf, (unsigned long)item, sizeof(*item));
 
 	btrfs_cpu_balance_args_to_disk(&disk_bargs, &bctl->data);
 	btrfs_set_balance_data(leaf, item, &disk_bargs);
@@ -5329,7 +5329,8 @@ void btrfs_put_bbio(struct btrfs_bio *bbio)
 		kfree(bbio);
 }
 
-static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int op,
+static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
+			     enum btrfs_map_op op,
 			     u64 logical, u64 *length,
 			     struct btrfs_bio **bbio_ret,
 			     int mirror_num, int need_raid_map)
@@ -5414,7 +5415,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int op,
 		raid56_full_stripe_start *= full_stripe_len;
 	}
 
-	if (op == REQ_OP_DISCARD) {
+	if (op == BTRFS_MAP_DISCARD) {
 		/* we don't discard raid56 yet */
 		if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
 			ret = -EOPNOTSUPP;
@@ -5427,7 +5428,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int op,
 		   For other RAID types and for RAID[56] reads, just allow a single
 		   stripe (on a single disk). */
 		if ((map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) &&
-		    (op == REQ_OP_WRITE)) {
+		    (op == BTRFS_MAP_WRITE)) {
 			max_len = stripe_len * nr_data_stripes(map) -
 				(offset - raid56_full_stripe_start);
 		} else {
@@ -5452,8 +5453,8 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int op,
 		btrfs_dev_replace_set_lock_blocking(dev_replace);
 
 	if (dev_replace_is_ongoing && mirror_num == map->num_stripes + 1 &&
-	    op != REQ_OP_WRITE && op != REQ_OP_DISCARD &&
-	    op != REQ_GET_READ_MIRRORS && dev_replace->tgtdev != NULL) {
+	    op != BTRFS_MAP_WRITE && op != BTRFS_MAP_DISCARD &&
+	    op != BTRFS_MAP_GET_READ_MIRRORS && dev_replace->tgtdev != NULL) {
 		/*
 		 * in dev-replace case, for repair case (that's the only
 		 * case where the mirror is selected explicitly when
@@ -5474,7 +5475,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int op,
 		int found = 0;
 		u64 physical_of_found = 0;
 
-		ret = __btrfs_map_block(fs_info, REQ_GET_READ_MIRRORS,
+		ret = __btrfs_map_block(fs_info, BTRFS_MAP_GET_READ_MIRRORS,
 			     logical, &tmp_length, &tmp_bbio, 0, 0);
 		if (ret) {
 			WARN_ON(tmp_bbio != NULL);
@@ -5484,7 +5485,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int op,
 		tmp_num_stripes = tmp_bbio->num_stripes;
 		if (mirror_num > tmp_num_stripes) {
 			/*
-			 * REQ_GET_READ_MIRRORS does not contain this
+			 * BTRFS_MAP_GET_READ_MIRRORS does not contain this
 			 * mirror, that means that the requested area
 			 * is not left of the left cursor
 			 */
@@ -5540,17 +5541,17 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int op,
 			    (offset + *length);
 
 	if (map->type & BTRFS_BLOCK_GROUP_RAID0) {
-		if (op == REQ_OP_DISCARD)
+		if (op == BTRFS_MAP_DISCARD)
 			num_stripes = min_t(u64, map->num_stripes,
 					    stripe_nr_end - stripe_nr_orig);
 		stripe_nr = div_u64_rem(stripe_nr, map->num_stripes,
 				&stripe_index);
-		if (op != REQ_OP_WRITE && op != REQ_OP_DISCARD &&
-		    op != REQ_GET_READ_MIRRORS)
+		if (op != BTRFS_MAP_WRITE && op != BTRFS_MAP_DISCARD &&
+		    op != BTRFS_MAP_GET_READ_MIRRORS)
 			mirror_num = 1;
 	} else if (map->type & BTRFS_BLOCK_GROUP_RAID1) {
-		if (op == REQ_OP_WRITE || op == REQ_OP_DISCARD ||
-		    op == REQ_GET_READ_MIRRORS)
+		if (op == BTRFS_MAP_WRITE || op == BTRFS_MAP_DISCARD ||
+		    op == BTRFS_MAP_GET_READ_MIRRORS)
 			num_stripes = map->num_stripes;
 		else if (mirror_num)
 			stripe_index = mirror_num - 1;
@@ -5563,8 +5564,8 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int op,
 		}
 
 	} else if (map->type & BTRFS_BLOCK_GROUP_DUP) {
-		if (op == REQ_OP_WRITE || op == REQ_OP_DISCARD ||
-		    op == REQ_GET_READ_MIRRORS) {
+		if (op == BTRFS_MAP_WRITE || op == BTRFS_MAP_DISCARD ||
+		    op == BTRFS_MAP_GET_READ_MIRRORS) {
 			num_stripes = map->num_stripes;
 		} else if (mirror_num) {
 			stripe_index = mirror_num - 1;
@@ -5578,9 +5579,9 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int op,
 		stripe_nr = div_u64_rem(stripe_nr, factor, &stripe_index);
 		stripe_index *= map->sub_stripes;
 
-		if (op == REQ_OP_WRITE || op == REQ_GET_READ_MIRRORS)
+		if (op == BTRFS_MAP_WRITE || op == BTRFS_MAP_GET_READ_MIRRORS)
 			num_stripes = map->sub_stripes;
-		else if (op == REQ_OP_DISCARD)
+		else if (op == BTRFS_MAP_DISCARD)
 			num_stripes = min_t(u64, map->sub_stripes *
 					    (stripe_nr_end - stripe_nr_orig),
 					    map->num_stripes);
@@ -5598,7 +5599,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int op,
 
 	} else if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
 		if (need_raid_map &&
-		    (op == REQ_OP_WRITE || op == REQ_GET_READ_MIRRORS ||
+		    (op == BTRFS_MAP_WRITE || op == BTRFS_MAP_GET_READ_MIRRORS ||
 		     mirror_num > 1)) {
 			/* push stripe_nr back to the start of the full stripe */
 			stripe_nr = div_u64(raid56_full_stripe_start,
@@ -5626,8 +5627,8 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int op,
 			/* We distribute the parity blocks across stripes */
 			div_u64_rem(stripe_nr + stripe_index, map->num_stripes,
 					&stripe_index);
-			if ((op != REQ_OP_WRITE && op != REQ_OP_DISCARD &&
-			    op != REQ_GET_READ_MIRRORS) && mirror_num <= 1)
+			if ((op != BTRFS_MAP_WRITE && op != BTRFS_MAP_DISCARD &&
+			    op != BTRFS_MAP_GET_READ_MIRRORS) && mirror_num <= 1)
 				mirror_num = 1;
 		}
 	} else {
@@ -5650,9 +5651,9 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int op,
 
 	num_alloc_stripes = num_stripes;
 	if (dev_replace_is_ongoing) {
-		if (op == REQ_OP_WRITE || op == REQ_OP_DISCARD)
+		if (op == BTRFS_MAP_WRITE || op == BTRFS_MAP_DISCARD)
 			num_alloc_stripes <<= 1;
-		if (op == REQ_GET_READ_MIRRORS)
+		if (op == BTRFS_MAP_GET_READ_MIRRORS)
 			num_alloc_stripes++;
 		tgtdev_indexes = num_stripes;
 	}
@@ -5668,7 +5669,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int op,
 	/* build raid_map */
 	if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK &&
 	    need_raid_map &&
-	    ((op == REQ_OP_WRITE || op == REQ_GET_READ_MIRRORS) ||
+	    ((op == BTRFS_MAP_WRITE || op == BTRFS_MAP_GET_READ_MIRRORS) ||
 	    mirror_num > 1)) {
 		u64 tmp;
 		unsigned rot;
@@ -5693,7 +5694,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int op,
 				RAID6_Q_STRIPE;
 	}
 
-	if (op == REQ_OP_DISCARD) {
+	if (op == BTRFS_MAP_DISCARD) {
 		u32 factor = 0;
 		u32 sub_stripes = 0;
 		u64 stripes_per_dev = 0;
@@ -5773,7 +5774,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int op,
 		}
 	}
 
-	if (op == REQ_OP_WRITE || op == REQ_GET_READ_MIRRORS)
+	if (op == BTRFS_MAP_WRITE || op == BTRFS_MAP_GET_READ_MIRRORS)
 		max_errors = btrfs_chunk_max_errors(map);
 
 	if (bbio->raid_map)
@@ -5781,7 +5782,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int op,
 
 	tgtdev_indexes = 0;
 	if (dev_replace_is_ongoing &&
-	   (op == REQ_OP_WRITE || op == REQ_OP_DISCARD) &&
+	   (op == BTRFS_MAP_WRITE || op == BTRFS_MAP_DISCARD) &&
 	    dev_replace->tgtdev != NULL) {
 		int index_where_to_add;
 		u64 srcdev_devid = dev_replace->srcdev->devid;
@@ -5816,7 +5817,8 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info, int op,
 			}
 		}
 		num_stripes = index_where_to_add;
-	} else if (dev_replace_is_ongoing && (op == REQ_GET_READ_MIRRORS) &&
+	} else if (dev_replace_is_ongoing &&
+		   op == BTRFS_MAP_GET_READ_MIRRORS &&
 		   dev_replace->tgtdev != NULL) {
 		u64 srcdev_devid = dev_replace->srcdev->devid;
 		int index_srcdev = 0;
@@ -5888,7 +5890,7 @@ out:
 	return ret;
 }
 
-int btrfs_map_block(struct btrfs_fs_info *fs_info, int op,
+int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 		      u64 logical, u64 *length,
 		      struct btrfs_bio **bbio_ret, int mirror_num)
 {
@@ -5897,7 +5899,7 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, int op,
 }
 
 /* For Scrub/replace */
-int btrfs_map_sblock(struct btrfs_fs_info *fs_info, int op,
+int btrfs_map_sblock(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 		     u64 logical, u64 *length,
 		     struct btrfs_bio **bbio_ret, int mirror_num,
 		     int need_raid_map)
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 09ed29c67848..9029a3134922 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -371,14 +371,35 @@ struct btrfs_balance_control {
 	struct btrfs_balance_progress stat;
 };
 
+enum btrfs_map_op {
+	BTRFS_MAP_READ,
+	BTRFS_MAP_WRITE,
+	BTRFS_MAP_DISCARD,
+	BTRFS_MAP_GET_READ_MIRRORS,
+};
+
+static inline enum btrfs_map_op btrfs_op(struct bio *bio)
+{
+	switch (bio_op(bio)) {
+	case REQ_OP_DISCARD:
+		return BTRFS_MAP_DISCARD;
+	case REQ_OP_WRITE:
+		return BTRFS_MAP_WRITE;
+	default:
+		WARN_ON_ONCE(1);
+	case REQ_OP_READ:
+		return BTRFS_MAP_READ;
+	}
+}
+
 int btrfs_account_dev_extents_size(struct btrfs_device *device, u64 start,
 				   u64 end, u64 *length);
 void btrfs_get_bbio(struct btrfs_bio *bbio);
 void btrfs_put_bbio(struct btrfs_bio *bbio);
-int btrfs_map_block(struct btrfs_fs_info *fs_info, int op,
+int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 		    u64 logical, u64 *length,
 		    struct btrfs_bio **bbio_ret, int mirror_num);
-int btrfs_map_sblock(struct btrfs_fs_info *fs_info, int op,
+int btrfs_map_sblock(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 		     u64 logical, u64 *length,
 		     struct btrfs_bio **bbio_ret, int mirror_num,
 		     int need_raid_map);
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index 441b81a3e545..da497f184ff4 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -210,10 +210,9 @@ out:
 	return ret;
 }
 
-static int zlib_decompress_biovec(struct list_head *ws, struct page **pages_in,
+static int zlib_decompress_bio(struct list_head *ws, struct page **pages_in,
 				  u64 disk_start,
-				  struct bio_vec *bvec,
-				  int vcnt,
+				  struct bio *orig_bio,
 				  size_t srclen)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
@@ -222,10 +221,8 @@ static int zlib_decompress_biovec(struct list_head *ws, struct page **pages_in,
 	char *data_in;
 	size_t total_out = 0;
 	unsigned long page_in_index = 0;
-	unsigned long page_out_index = 0;
 	unsigned long total_pages_in = DIV_ROUND_UP(srclen, PAGE_SIZE);
 	unsigned long buf_start;
-	unsigned long pg_offset;
 
 	data_in = kmap(pages_in[page_in_index]);
 	workspace->strm.next_in = data_in;
@@ -235,7 +232,6 @@ static int zlib_decompress_biovec(struct list_head *ws, struct page **pages_in,
 	workspace->strm.total_out = 0;
 	workspace->strm.next_out = workspace->buf;
 	workspace->strm.avail_out = PAGE_SIZE;
-	pg_offset = 0;
 
 	/* If it's deflate, and it's got no preset dictionary, then
 	   we can tell zlib to skip the adler32 check. */
@@ -250,6 +246,7 @@ static int zlib_decompress_biovec(struct list_head *ws, struct page **pages_in,
 
 	if (Z_OK != zlib_inflateInit2(&workspace->strm, wbits)) {
 		pr_warn("BTRFS: inflateInit failed\n");
+		kunmap(pages_in[page_in_index]);
 		return -EIO;
 	}
 	while (workspace->strm.total_in < srclen) {
@@ -266,8 +263,7 @@ static int zlib_decompress_biovec(struct list_head *ws, struct page **pages_in,
 
 		ret2 = btrfs_decompress_buf2page(workspace->buf, buf_start,
 						 total_out, disk_start,
-						 bvec, vcnt,
-						 &page_out_index, &pg_offset);
+						 orig_bio);
 		if (ret2 == 0) {
 			ret = 0;
 			goto done;
@@ -300,7 +296,7 @@ done:
 	if (data_in)
 		kunmap(pages_in[page_in_index]);
 	if (!ret)
-		btrfs_clear_biovec_end(bvec, vcnt, page_out_index, pg_offset);
+		zero_fill_bio(orig_bio);
 	return ret;
 }
 
@@ -407,6 +403,6 @@ const struct btrfs_compress_op btrfs_zlib_compress = {
 	.alloc_workspace	= zlib_alloc_workspace,
 	.free_workspace		= zlib_free_workspace,
 	.compress_pages		= zlib_compress_pages,
-	.decompress_biovec	= zlib_decompress_biovec,
+	.decompress_bio		= zlib_decompress_bio,
 	.decompress		= zlib_decompress,
 };
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index e030d6f6c19a..e61bbc3b82d5 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -1406,7 +1406,7 @@ DEFINE_EVENT(btrfs_qgroup_extent, btrfs_qgroup_account_extents,
 	TP_ARGS(fs_info, rec)
 );
 
-DEFINE_EVENT(btrfs_qgroup_extent, btrfs_qgroup_insert_dirty_extent,
+DEFINE_EVENT(btrfs_qgroup_extent, btrfs_qgroup_trace_extent,
 
 	TP_PROTO(struct btrfs_fs_info *fs_info,
 		 struct btrfs_qgroup_extent_record *rec),