Merge branch 'for-4.13-part2' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:
 "We've identified and fixed a silent corruption (introduced by code in
  the first pull), a fixup after the blk_status_t merge and two fixes to
  incremental send that Filipe has been hunting for some time"

* 'for-4.13-part2' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  Btrfs: fix unexpected return value of bio_readpage_error
  btrfs: btrfs_create_repair_bio never fails, skip error handling
  btrfs: cloned bios must not be iterated by bio_for_each_segment_all
  Btrfs: fix write corruption due to bio cloning on raid5/6
  Btrfs: incremental send, fix invalid memory access
  Btrfs: incremental send, fix invalid path for link commands

fs/btrfs/compression.c

@@ -152,6 +152,7 @@ static void end_compressed_bio_read(struct bio *bio)
 		 * we have verified the checksum already, set page
 		 * checked so the end_io handlers know about it
 		 */
+		ASSERT(!bio_flagged(bio, BIO_CLONED));
 		bio_for_each_segment_all(bvec, cb->orig_bio, i)
 			SetPageChecked(bvec->bv_page);
 

fs/btrfs/disk-io.c

@@ -964,6 +964,7 @@ static blk_status_t btree_csum_one_bio(struct bio *bio)
 	struct btrfs_root *root;
 	int i, ret = 0;
 
+	ASSERT(!bio_flagged(bio, BIO_CLONED));
 	bio_for_each_segment_all(bvec, bio, i) {
 		root = BTRFS_I(bvec->bv_page->mapping->host)->root;
 		ret = csum_dirty_buffer(root->fs_info, bvec->bv_page);

fs/btrfs/extent_io.c

@@ -2258,7 +2258,7 @@ int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
 	return 0;
 }
 
-int btrfs_check_repairable(struct inode *inode, struct bio *failed_bio,
+bool btrfs_check_repairable(struct inode *inode, struct bio *failed_bio,
 			   struct io_failure_record *failrec, int failed_mirror)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
@@ -2274,7 +2274,7 @@ int btrfs_check_repairable(struct inode *inode, struct bio *failed_bio,
 		btrfs_debug(fs_info,
 			"Check Repairable: cannot repair, num_copies=%d, next_mirror %d, failed_mirror %d",
 			num_copies, failrec->this_mirror, failed_mirror);
-		return 0;
+		return false;
 	}
 
 	/*
@@ -2315,10 +2315,10 @@ int btrfs_check_repairable(struct inode *inode, struct bio *failed_bio,
 		btrfs_debug(fs_info,
 			"Check Repairable: (fail) num_copies=%d, next_mirror %d, failed_mirror %d",
 			num_copies, failrec->this_mirror, failed_mirror);
-		return 0;
+		return false;
 	}
 
-	return 1;
+	return true;
 }
 
 
@@ -2382,8 +2382,8 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 	if (ret)
 		return ret;
 
-	ret = btrfs_check_repairable(inode, failed_bio, failrec, failed_mirror);
-	if (!ret) {
+	if (!btrfs_check_repairable(inode, failed_bio, failrec,
+				    failed_mirror)) {
 		free_io_failure(failure_tree, tree, failrec);
 		return -EIO;
 	}
@@ -2396,10 +2396,6 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 				      start - page_offset(page),
 				      (int)phy_offset, failed_bio->bi_end_io,
 				      NULL);
-	if (!bio) {
-		free_io_failure(failure_tree, tree, failrec);
-		return -EIO;
-	}
 	bio_set_op_attrs(bio, REQ_OP_READ, read_mode);
 
 	btrfs_debug(btrfs_sb(inode->i_sb),
@@ -2456,6 +2452,7 @@ static void end_bio_extent_writepage(struct bio *bio)
 	u64 end;
 	int i;
 
+	ASSERT(!bio_flagged(bio, BIO_CLONED));
 	bio_for_each_segment_all(bvec, bio, i) {
 		struct page *page = bvec->bv_page;
 		struct inode *inode = page->mapping->host;
@@ -2526,6 +2523,7 @@ static void end_bio_extent_readpage(struct bio *bio)
 	int ret;
 	int i;
 
+	ASSERT(!bio_flagged(bio, BIO_CLONED));
 	bio_for_each_segment_all(bvec, bio, i) {
 		struct page *page = bvec->bv_page;
 		struct inode *inode = page->mapping->host;
@@ -3680,6 +3678,7 @@ static void end_bio_extent_buffer_writepage(struct bio *bio)
 	struct extent_buffer *eb;
 	int i, done;
 
+	ASSERT(!bio_flagged(bio, BIO_CLONED));
 	bio_for_each_segment_all(bvec, bio, i) {
 		struct page *page = bvec->bv_page;
 

fs/btrfs/extent_io.h

@@ -539,7 +539,7 @@ void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start,
 		u64 end);
 int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
 				struct io_failure_record **failrec_ret);
-int btrfs_check_repairable(struct inode *inode, struct bio *failed_bio,
+bool btrfs_check_repairable(struct inode *inode, struct bio *failed_bio,
 			    struct io_failure_record *failrec, int fail_mirror);
 struct bio *btrfs_create_repair_bio(struct inode *inode, struct bio *failed_bio,
 				    struct io_failure_record *failrec,

fs/btrfs/inode.c

@@ -8016,10 +8016,6 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio,
 	isector >>= inode->i_sb->s_blocksize_bits;
 	bio = btrfs_create_repair_bio(inode, failed_bio, failrec, page,
 				pgoff, isector, repair_endio, repair_arg);
-	if (!bio) {
-		free_io_failure(failure_tree, io_tree, failrec);
-		return -EIO;
-	}
 	bio_set_op_attrs(bio, REQ_OP_READ, read_mode);
 
 	btrfs_debug(BTRFS_I(inode)->root->fs_info,
@@ -8059,6 +8055,7 @@ static void btrfs_retry_endio_nocsum(struct bio *bio)
 	ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(inode));
 
 	done->uptodate = 1;
+	ASSERT(!bio_flagged(bio, BIO_CLONED));
 	bio_for_each_segment_all(bvec, bio, i)
 		clean_io_failure(BTRFS_I(inode)->root->fs_info, failure_tree,
 				 io_tree, done->start, bvec->bv_page,
@@ -8150,6 +8147,7 @@ static void btrfs_retry_endio(struct bio *bio)
 	io_tree = &BTRFS_I(inode)->io_tree;
 	failure_tree = &BTRFS_I(inode)->io_failure_tree;
 
+	ASSERT(!bio_flagged(bio, BIO_CLONED));
 	bio_for_each_segment_all(bvec, bio, i) {
 		ret = __readpage_endio_check(inode, io_bio, i, bvec->bv_page,
 					     bvec->bv_offset, done->start,

fs/btrfs/raid56.c

@@ -1136,20 +1136,27 @@ 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;
-	int i;
 
 	spin_lock_irq(&rbio->bio_list_lock);
 	bio_list_for_each(bio, &rbio->bio_list) {
+		struct bio_vec bvec;
+		struct bvec_iter iter;
+		int i = 0;
+
 		start = (u64)bio->bi_iter.bi_sector << 9;
 		stripe_offset = start - rbio->bbio->raid_map[0];
 		page_index = stripe_offset >> PAGE_SHIFT;
 
-		bio_for_each_segment_all(bvec, bio, i)
-			rbio->bio_pages[page_index + i] = bvec->bv_page;
+		if (bio_flagged(bio, BIO_CLONED))
+			bio->bi_iter = btrfs_io_bio(bio)->iter;
+
+		bio_for_each_segment(bvec, bio, iter) {
+			rbio->bio_pages[page_index + i] = bvec.bv_page;
+			i++;
+		}
 	}
 	spin_unlock_irq(&rbio->bio_list_lock);
 }
@@ -1423,11 +1430,14 @@ 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 bio_vec bvec;
+	struct bvec_iter iter;
+
+	if (bio_flagged(bio, BIO_CLONED))
+		bio->bi_iter = btrfs_io_bio(bio)->iter;
 
-	bio_for_each_segment_all(bvec, bio, i)
-		SetPageUptodate(bvec->bv_page);
+	bio_for_each_segment(bvec, bio, iter)
+		SetPageUptodate(bvec.bv_page);
 }
 
 /*

fs/btrfs/send.c

@@ -1856,7 +1856,7 @@ static int is_first_ref(struct btrfs_root *root,
  */
 static int will_overwrite_ref(struct send_ctx *sctx, u64 dir, u64 dir_gen,
 			      const char *name, int name_len,
-			      u64 *who_ino, u64 *who_gen)
+			      u64 *who_ino, u64 *who_gen, u64 *who_mode)
 {
 	int ret = 0;
 	u64 gen;
@@ -1905,7 +1905,7 @@ static int will_overwrite_ref(struct send_ctx *sctx, u64 dir, u64 dir_gen,
 	if (other_inode > sctx->send_progress ||
 	    is_waiting_for_move(sctx, other_inode)) {
 		ret = get_inode_info(sctx->parent_root, other_inode, NULL,
-				who_gen, NULL, NULL, NULL, NULL);
+				who_gen, who_mode, NULL, NULL, NULL);
 		if (ret < 0)
 			goto out;
 
@@ -3683,6 +3683,36 @@ static int wait_for_parent_move(struct send_ctx *sctx,
 	return ret;
 }
 
+static int update_ref_path(struct send_ctx *sctx, struct recorded_ref *ref)
+{
+	int ret;
+	struct fs_path *new_path;
+
+	/*
+	 * Our reference's name member points to its full_path member string, so
+	 * we use here a new path.
+	 */
+	new_path = fs_path_alloc();
+	if (!new_path)
+		return -ENOMEM;
+
+	ret = get_cur_path(sctx, ref->dir, ref->dir_gen, new_path);
+	if (ret < 0) {
+		fs_path_free(new_path);
+		return ret;
+	}
+	ret = fs_path_add(new_path, ref->name, ref->name_len);
+	if (ret < 0) {
+		fs_path_free(new_path);
+		return ret;
+	}
+
+	fs_path_free(ref->full_path);
+	set_ref_path(ref, new_path);
+
+	return 0;
+}
+
 /*
  * This does all the move/link/unlink/rmdir magic.
  */
@@ -3696,10 +3726,12 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
 	struct fs_path *valid_path = NULL;
 	u64 ow_inode = 0;
 	u64 ow_gen;
+	u64 ow_mode;
 	int did_overwrite = 0;
 	int is_orphan = 0;
 	u64 last_dir_ino_rm = 0;
 	bool can_rename = true;
+	bool orphanized_dir = false;
 	bool orphanized_ancestor = false;
 
 	btrfs_debug(fs_info, "process_recorded_refs %llu", sctx->cur_ino);
@@ -3798,7 +3830,7 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
 		 */
 		ret = will_overwrite_ref(sctx, cur->dir, cur->dir_gen,
 				cur->name, cur->name_len,
-				&ow_inode, &ow_gen);
+				&ow_inode, &ow_gen, &ow_mode);
 		if (ret < 0)
 			goto out;
 		if (ret) {
@@ -3815,6 +3847,8 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
 						cur->full_path);
 				if (ret < 0)
 					goto out;
+				if (S_ISDIR(ow_mode))
+					orphanized_dir = true;
 
 				/*
 				 * If ow_inode has its rename operation delayed
@@ -3920,6 +3954,18 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
 				if (ret < 0)
 					goto out;
 			} else {
+				/*
+				 * We might have previously orphanized an inode
+				 * which is an ancestor of our current inode,
+				 * so our reference's full path, which was
+				 * computed before any such orphanizations, must
+				 * be updated.
+				 */
+				if (orphanized_dir) {
+					ret = update_ref_path(sctx, cur);
+					if (ret < 0)
+						goto out;
+				}
 				ret = send_link(sctx, cur->full_path,
 						valid_path);
 				if (ret < 0)
@@ -3990,35 +4036,10 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
 				 * ancestor inode.
 				 */
 				if (orphanized_ancestor) {
-					struct fs_path *new_path;
-
-					/*
-					 * Our reference's name member points to
-					 * its full_path member string, so we
-					 * use here a new path.
-					 */
-					new_path = fs_path_alloc();
-					if (!new_path) {
-						ret = -ENOMEM;
-						goto out;
-					}
-					ret = get_cur_path(sctx, cur->dir,
-							   cur->dir_gen,
-							   new_path);
-					if (ret < 0) {
-						fs_path_free(new_path);
-						goto out;
-					}
-					ret = fs_path_add(new_path,
-							  cur->name,
-							  cur->name_len);
-					if (ret < 0) {
-						fs_path_free(new_path);
+					ret = update_ref_path(sctx, cur);
+					if (ret < 0)
 						goto out;
 				}
-					fs_path_free(cur->full_path);
-					set_ref_path(cur, new_path);
-				}
 				ret = send_unlink(sctx, cur->full_path);
 				if (ret < 0)
 					goto out;
@@ -5249,15 +5270,12 @@ static int is_extent_unchanged(struct send_ctx *sctx,
 			goto out;
 		}
 
-		right_disknr = btrfs_file_extent_disk_bytenr(eb, ei);
 		if (right_type == BTRFS_FILE_EXTENT_INLINE) {
 			right_len = btrfs_file_extent_inline_len(eb, slot, ei);
 			right_len = PAGE_ALIGN(right_len);
 		} else {
 			right_len = btrfs_file_extent_num_bytes(eb, ei);
 		}
-		right_offset = btrfs_file_extent_offset(eb, ei);
-		right_gen = btrfs_file_extent_generation(eb, ei);
 
 		/*
 		 * Are we at extent 8? If yes, we know the extent is changed.
@@ -5282,6 +5300,10 @@ static int is_extent_unchanged(struct send_ctx *sctx,
 			goto out;
 		}
 
+		right_disknr = btrfs_file_extent_disk_bytenr(eb, ei);
+		right_offset = btrfs_file_extent_offset(eb, ei);
+		right_gen = btrfs_file_extent_generation(eb, ei);
+
 		left_offset_fixed = left_offset;
 		if (key.offset < ekey->offset) {
 			/* Fix the right offset for 2a and 7. */