btrfs: add ioctls and send/receive support for reading/writing compressed data

index 82e8eb32ff3d..f471894d87d4 100644
@@ -165,11 +165,6 @@ extern char *simple_dname(struct dentry *, char *, int);
 extern void dput_to_list(struct dentry *, struct list_head *);
 extern void shrink_dentry_list(struct list_head *);
 
-/*
- * read_write.c
- */
-extern int rw_verify_area(int, struct file *, const loff_t *, size_t);
-
 /*
  * pipe.c
  */

index 9db7adf160d2..0029ff2b0ca8 100644
@@ -400,6 +400,7 @@ int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t
 	return security_file_permission(file,
 				read_write == READ ? MAY_READ : MAY_WRITE);
 }
+EXPORT_SYMBOL(rw_verify_area);
 
 static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos)
 {

index 1751addcb36e..0de4d75339b9 100644
@@ -3274,6 +3274,7 @@ extern loff_t fixed_size_llseek(struct file *file, loff_t offset,
 		int whence, loff_t size);
 extern loff_t no_seek_end_llseek_size(struct file *, loff_t, int, loff_t);
 extern loff_t no_seek_end_llseek(struct file *, loff_t, int);
+extern int rw_verify_area(int, struct file *, const loff_t *, size_t);
 extern int generic_file_open(struct inode * inode, struct file * filp);
 extern int nonseekable_open(struct inode * inode, struct file * filp);
 extern int stream_open(struct inode * inode, struct file * filp);

index 0029ff2b0ca8..46b3dcff3b24 100644
@@ -1633,24 +1633,16 @@ int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count)
 	return 0;
 }
 
-/*
- * Performs necessary checks before doing a write
- *
- * Can adjust writing position or amount of bytes to write.
- * Returns appropriate error code that caller should return or
- * zero in case that write should be allowed.
- */
-ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
+/* Like generic_write_checks(), but takes size of write instead of iter. */
+int generic_write_checks_count(struct kiocb *iocb, loff_t *count)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file->f_mapping->host;
-	loff_t count;
-	int ret;
 
 	if (IS_SWAPFILE(inode))
 		return -ETXTBSY;
 
-	if (!iov_iter_count(from))
+	if (!*count)
 		return 0;
 
 	/* FIXME: this is for backwards compatibility with 2.4 */

@@ -1660,8 +1652,23 @@ ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
 	if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT))
 		return -EINVAL;
 
-	count = iov_iter_count(from);
-	ret = generic_write_check_limits(file, iocb->ki_pos, &count);
+	return generic_write_check_limits(iocb->ki_filp, iocb->ki_pos, count);
+}
+EXPORT_SYMBOL(generic_write_checks_count);
+
+/*
+ * Performs necessary checks before doing a write
+ *
+ * Can adjust writing position or amount of bytes to write.
+ * Returns appropriate error code that caller should return or
+ * zero in case that write should be allowed.
+ */
+ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from)
+{
+	loff_t count = iov_iter_count(from);
+	int ret;
+
+	ret = generic_write_checks_count(iocb, &count);
 	if (ret)
 		return ret;
 

index 0de4d75339b9..3a2ff5306236 100644
@@ -3227,6 +3227,7 @@ extern int sb_min_blocksize(struct super_block *, int);
 extern int generic_file_mmap(struct file *, struct vm_area_struct *);
 extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
 extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *);
+extern int generic_write_checks_count(struct kiocb *iocb, loff_t *count);
 extern int generic_write_check_limits(struct file *file, loff_t pos,
 		loff_t *count);
 extern int generic_file_rw_checks(struct file *file_in, struct file *file_out);

index 7869ad12bc6e..e645b3c2f09a 100644
@@ -480,7 +480,8 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
 			BUG_ON(ret); /* -ENOMEM */
 
 			if (!skip_sum) {
-				ret = btrfs_csum_one_bio(inode, bio, start, 1);
+				ret = btrfs_csum_one_bio(inode, bio, start,
+							 true);
 				BUG_ON(ret); /* -ENOMEM */
 			}
 

@@ -516,7 +517,7 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
 	BUG_ON(ret); /* -ENOMEM */
 
 	if (!skip_sum) {
-		ret = btrfs_csum_one_bio(inode, bio, start, 1);
+		ret = btrfs_csum_one_bio(inode, bio, start, true);
 		BUG_ON(ret); /* -ENOMEM */
 	}
 

index 38870ae46cbb..8ea383cac13b 100644
@@ -3115,7 +3115,7 @@ int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root,
 			   struct btrfs_ordered_sum *sums);
 blk_status_t btrfs_csum_one_bio(struct btrfs_inode *inode, struct bio *bio,
-				u64 file_start, int contig);
+				u64 offset, bool one_ordered);
 int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
 			     struct list_head *list, int search_commit);
 void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,

index 2673c6ba7a4e..aa5fb66e6987 100644
@@ -614,28 +614,28 @@ int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
  * btrfs_csum_one_bio - Calculates checksums of the data contained inside a bio
  * @inode:	 Owner of the data inside the bio
  * @bio:	 Contains the data to be checksummed
- * @file_start:  offset in file this bio begins to describe
- * @contig:	 Boolean. If true/1 means all bio vecs in this bio are
- *		 contiguous and they begin at @file_start in the file. False/0
- *		 means this bio can contain potentially discontiguous bio vecs
- *		 so the logical offset of each should be calculated separately.
+ * @offset:      If (u64)-1, @bio may contain discontiguous bio vecs, so the
+ *               file offsets are determined from the page offsets in the bio.
+ *               Otherwise, this is the starting file offset of the bio vecs in
+ *               @bio, which must be contiguous.
+ * @one_ordered: If true, @bio only refers to one ordered extent.
  */
 blk_status_t btrfs_csum_one_bio(struct btrfs_inode *inode, struct bio *bio,
-		       u64 file_start, int contig)
+				u64 offset, bool one_ordered)
 {
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
 	struct btrfs_ordered_sum *sums;
 	struct btrfs_ordered_extent *ordered = NULL;
+	const bool use_page_offsets = (offset == (u64)-1);
 	char *data;
 	struct bvec_iter iter;
 	struct bio_vec bvec;
 	int index;
-	int nr_sectors;
+	int blockcount;
 	unsigned long total_bytes = 0;
 	unsigned long this_sum_bytes = 0;
 	int i;
-	u64 offset;
 	unsigned nofs_flag;
 
 	nofs_flag = memalloc_nofs_save();

@@ -649,18 +649,13 @@ blk_status_t btrfs_csum_one_bio(struct btrfs_inode *inode, struct bio *bio,
 	sums->len = bio->bi_iter.bi_size;
 	INIT_LIST_HEAD(&sums->list);
 
-	if (contig)
-		offset = file_start;
-	else
-		offset = 0; /* shut up gcc */
-
 	sums->bytenr = bio->bi_iter.bi_sector << 9;
 	index = 0;
 
 	shash->tfm = fs_info->csum_shash;
 
 	bio_for_each_segment(bvec, bio, iter) {
-		if (!contig)
+		if (use_page_offsets)
 			offset = page_offset(bvec.bv_page) + bvec.bv_offset;
 
 		if (!ordered) {

@@ -668,13 +663,14 @@ blk_status_t btrfs_csum_one_bio(struct btrfs_inode *inode, struct bio *bio,
 			BUG_ON(!ordered); /* Logic error */
 		}
 
-		nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info,
+		blockcount = BTRFS_BYTES_TO_BLKS(fs_info,
 						 bvec.bv_len + fs_info->sectorsize
 						 - 1);
 
-		for (i = 0; i < nr_sectors; i++) {
-			if (offset >= ordered->file_offset + ordered->num_bytes ||
-			    offset < ordered->file_offset) {
+		for (i = 0; i < blockcount; i++) {
+			if (!one_ordered &&
+			    !in_range(offset, ordered->file_offset,
+				      ordered->num_bytes)) {
 				unsigned long bytes_left;
 
 				sums->len = this_sum_bytes;

index 0517f31a3bed..8063d05e4a20 100644
@@ -2286,7 +2286,7 @@ int btrfs_bio_fits_in_stripe(struct page *page, size_t size, struct bio *bio,
 static blk_status_t btrfs_submit_bio_start(struct inode *inode, struct bio *bio,
 					   u64 dio_file_offset)
 {
-	return btrfs_csum_one_bio(BTRFS_I(inode), bio, 0, 0);
+	return btrfs_csum_one_bio(BTRFS_I(inode), bio, (u64)-1, false);
 }
 
 /*

@@ -2538,7 +2538,7 @@ blk_status_t btrfs_submit_data_bio(struct inode *inode, struct bio *bio,
 					  0, btrfs_submit_bio_start);
 		goto out;
 	} else if (!skip_sum) {
-		ret = btrfs_csum_one_bio(BTRFS_I(inode), bio, 0, 0);
+		ret = btrfs_csum_one_bio(BTRFS_I(inode), bio, (u64)-1, false);
 		if (ret)
 			goto out;
 	}

@@ -8140,7 +8140,7 @@ static blk_status_t btrfs_submit_bio_start_direct_io(struct inode *inode,
 						     struct bio *bio,
 						     u64 dio_file_offset)
 {
-	return btrfs_csum_one_bio(BTRFS_I(inode), bio, dio_file_offset, 1);
+	return btrfs_csum_one_bio(BTRFS_I(inode), bio, dio_file_offset, false);
 }
 
 static void btrfs_end_dio_bio(struct bio *bio)

@@ -8199,7 +8199,7 @@ static inline blk_status_t btrfs_submit_dio_bio(struct bio *bio,
 		 * If we aren't doing async submit, calculate the csum of the
 		 * bio now.
 		 */
-		ret = btrfs_csum_one_bio(BTRFS_I(inode), bio, file_offset, 1);
+		ret = btrfs_csum_one_bio(BTRFS_I(inode), bio, file_offset, false);
 		if (ret)
 			goto err;
 	} else {

index 8063d05e4a20..a85c1050ae95 100644
@@ -945,12 +945,12 @@ static noinline void submit_compressed_extents(struct async_chunk *async_chunk)
 			goto out_free_reserve;
 		free_extent_map(em);
 
-		ret = btrfs_add_ordered_extent_compress(inode,
-						async_extent->start,
-						ins.objectid,
-						async_extent->ram_size,
-						ins.offset,
-						async_extent->compress_type);
+		ret = btrfs_add_ordered_extent(inode, async_extent->start,
+					       async_extent->ram_size,
+					       async_extent->ram_size,
+					       ins.objectid, ins.offset, 0,
+					       1 << BTRFS_ORDERED_COMPRESSED,
+					       async_extent->compress_type);
 		if (ret) {
 			btrfs_drop_extent_cache(inode, async_extent->start,
 						async_extent->start +

@@ -1180,9 +1180,9 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
 		}
 		free_extent_map(em);
 
-		ret = btrfs_add_ordered_extent(inode, start, ins.objectid,
-					       ram_size, cur_alloc_size,
-					       BTRFS_ORDERED_REGULAR);
+		ret = btrfs_add_ordered_extent(inode, start, ram_size, ram_size,
+					       ins.objectid, cur_alloc_size, 0,
+					       0, BTRFS_COMPRESS_NONE);
 		if (ret)
 			goto out_drop_extent_cache;
 

@@ -1843,10 +1843,11 @@ static noinline int run_delalloc_nocow(struct btrfs_inode *inode,
 				goto error;
 			}
 			free_extent_map(em);
-			ret = btrfs_add_ordered_extent(inode, cur_offset,
-						       disk_bytenr, num_bytes,
-						       num_bytes,
-						       BTRFS_ORDERED_PREALLOC);
+			ret = btrfs_add_ordered_extent(inode,
+					cur_offset, num_bytes, num_bytes,
+					disk_bytenr, num_bytes, 0,
+					1 << BTRFS_ORDERED_PREALLOC,
+					BTRFS_COMPRESS_NONE);
 			if (ret) {
 				btrfs_drop_extent_cache(inode, cur_offset,
 							cur_offset + num_bytes - 1,

@@ -1855,9 +1856,11 @@ static noinline int run_delalloc_nocow(struct btrfs_inode *inode,
 			}
 		} else {
 			ret = btrfs_add_ordered_extent(inode, cur_offset,
+						       num_bytes, num_bytes,
 						       disk_bytenr, num_bytes,
-						       num_bytes,
-						       BTRFS_ORDERED_NOCOW);
+						       0,
+						       1 << BTRFS_ORDERED_NOCOW,
+						       BTRFS_COMPRESS_NONE);
 			if (ret)
 				goto error;
 		}

@@ -2842,6 +2845,7 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans,
 	struct btrfs_key ins;
 	u64 disk_num_bytes = btrfs_stack_file_extent_disk_num_bytes(stack_fi);
 	u64 disk_bytenr = btrfs_stack_file_extent_disk_bytenr(stack_fi);
+	u64 offset = btrfs_stack_file_extent_offset(stack_fi);
 	u64 num_bytes = btrfs_stack_file_extent_num_bytes(stack_fi);
 	u64 ram_bytes = btrfs_stack_file_extent_ram_bytes(stack_fi);
 	struct btrfs_drop_extents_args drop_args = { 0 };

@@ -2916,7 +2920,8 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans,
 		goto out;
 
 	ret = btrfs_alloc_reserved_file_extent(trans, root, btrfs_ino(inode),
-					       file_pos, qgroup_reserved, &ins);
+					       file_pos - offset,
+					       qgroup_reserved, &ins);
 out:
 	btrfs_free_path(path);
 

@@ -2942,20 +2947,20 @@ static int insert_ordered_extent_file_extent(struct btrfs_trans_handle *trans,
 					     struct btrfs_ordered_extent *oe)
 {
 	struct btrfs_file_extent_item stack_fi;
-	u64 logical_len;
 	bool update_inode_bytes;
+	u64 num_bytes = oe->num_bytes;
+	u64 ram_bytes = oe->ram_bytes;
 
 	memset(&stack_fi, 0, sizeof(stack_fi));
 	btrfs_set_stack_file_extent_type(&stack_fi, BTRFS_FILE_EXTENT_REG);
 	btrfs_set_stack_file_extent_disk_bytenr(&stack_fi, oe->disk_bytenr);
 	btrfs_set_stack_file_extent_disk_num_bytes(&stack_fi,
 						   oe->disk_num_bytes);
+	btrfs_set_stack_file_extent_offset(&stack_fi, oe->offset);
 	if (test_bit(BTRFS_ORDERED_TRUNCATED, &oe->flags))
-		logical_len = oe->truncated_len;
-	else
-		logical_len = oe->num_bytes;
-	btrfs_set_stack_file_extent_num_bytes(&stack_fi, logical_len);
-	btrfs_set_stack_file_extent_ram_bytes(&stack_fi, logical_len);
+		num_bytes = ram_bytes = oe->truncated_len;
+	btrfs_set_stack_file_extent_num_bytes(&stack_fi, num_bytes);
+	btrfs_set_stack_file_extent_ram_bytes(&stack_fi, ram_bytes);
 	btrfs_set_stack_file_extent_compression(&stack_fi, oe->compress_type);
 	/* Encryption and other encoding is reserved and all 0 */
 

@@ -7395,8 +7400,11 @@ static struct extent_map *btrfs_create_dio_extent(struct btrfs_inode *inode,
 		if (IS_ERR(em))
 			goto out;
 	}
-	ret = btrfs_add_ordered_extent_dio(inode, start, block_start, len,
-					   block_len, type);
+	ret = btrfs_add_ordered_extent(inode, start, len, len, block_start,
+				       block_len, 0,
+				       (1 << type) |
+				       (1 << BTRFS_ORDERED_DIRECT),
+				       BTRFS_COMPRESS_NONE);
 	if (ret) {
 		if (em) {
 			free_extent_map(em);

157 lines not on this page · raw message

index 4194e960ff61..0feb0c29839e 100644
@@ -76,6 +76,13 @@ enum {
 	BTRFS_ORDERED_PENDING,
 };
 
+/* BTRFS_ORDERED_* flags that specify the type of the extent. */
+#define BTRFS_ORDERED_TYPE_FLAGS ((1UL << BTRFS_ORDERED_REGULAR) |	\
+				  (1UL << BTRFS_ORDERED_NOCOW) |	\
+				  (1UL << BTRFS_ORDERED_PREALLOC) |	\
+				  (1UL << BTRFS_ORDERED_COMPRESSED) |	\
+				  (1UL << BTRFS_ORDERED_DIRECT))
+
 struct btrfs_ordered_extent {
 	/* logical offset in the file */
 	u64 file_offset;

@@ -84,9 +91,11 @@ struct btrfs_ordered_extent {
 	 * These fields directly correspond to the same fields in
 	 * btrfs_file_extent_item.
 	 */
-	u64 disk_bytenr;
 	u64 num_bytes;
+	u64 ram_bytes;
+	u64 disk_bytenr;
 	u64 disk_num_bytes;
+	u64 offset;
 
 	/* number of bytes that still need writing */
 	u64 bytes_left;

@@ -179,14 +188,9 @@ bool btrfs_dec_test_ordered_pending(struct btrfs_inode *inode,
 				    struct btrfs_ordered_extent **cached,
 				    u64 file_offset, u64 io_size);
 int btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset,
-			     u64 disk_bytenr, u64 num_bytes, u64 disk_num_bytes,
-			     int type);
-int btrfs_add_ordered_extent_dio(struct btrfs_inode *inode, u64 file_offset,
-				 u64 disk_bytenr, u64 num_bytes,
-				 u64 disk_num_bytes, int type);
-int btrfs_add_ordered_extent_compress(struct btrfs_inode *inode, u64 file_offset,
-				      u64 disk_bytenr, u64 num_bytes,
-				      u64 disk_num_bytes, int compress_type);
+			     u64 num_bytes, u64 ram_bytes, u64 disk_bytenr,
+			     u64 disk_num_bytes, u64 offset, int flags,
+			     int compress_type);
 void btrfs_add_ordered_sum(struct btrfs_ordered_extent *entry,
 			   struct btrfs_ordered_sum *sum);
 struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct btrfs_inode *inode,

index 8ea383cac13b..b95ec5fb68d5 100644
@@ -2802,7 +2802,8 @@ void btrfs_subvolume_release_metadata(struct btrfs_root *root,
 				      struct btrfs_block_rsv *rsv);
 void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes);
 
-int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes);
+int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes,
+				    u64 disk_num_bytes);
 u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo);
 int btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info,
 				   u64 start, u64 end);

index 2059d1504149..143650004991 100644
@@ -267,11 +267,11 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
 }
 
 static void calc_inode_reservations(struct btrfs_fs_info *fs_info,
-				    u64 num_bytes, u64 *meta_reserve,
-				    u64 *qgroup_reserve)
+				    u64 num_bytes, u64 disk_num_bytes,
+				    u64 *meta_reserve, u64 *qgroup_reserve)
 {
 	u64 nr_extents = count_max_extents(num_bytes);
-	u64 csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, num_bytes);
+	u64 csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, disk_num_bytes);
 	u64 inode_update = btrfs_calc_metadata_size(fs_info, 1);
 
 	*meta_reserve = btrfs_calc_insert_metadata_size(fs_info,

@@ -285,7 +285,8 @@ static void calc_inode_reservations(struct btrfs_fs_info *fs_info,
 	*qgroup_reserve = nr_extents * fs_info->nodesize;
 }
 
-int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
+int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes,
+				    u64 disk_num_bytes)
 {
 	struct btrfs_root *root = inode->root;
 	struct btrfs_fs_info *fs_info = root->fs_info;

@@ -315,6 +316,7 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
 	}
 
 	num_bytes = ALIGN(num_bytes, fs_info->sectorsize);
+	disk_num_bytes = ALIGN(disk_num_bytes, fs_info->sectorsize);
 
 	/*
 	 * We always want to do it this way, every other way is wrong and ends

@@ -326,8 +328,8 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
 	 * everything out and try again, which is bad.  This way we just
 	 * over-reserve slightly, and clean up the mess when we are done.
 	 */
-	calc_inode_reservations(fs_info, num_bytes, &meta_reserve,
-				&qgroup_reserve);
+	calc_inode_reservations(fs_info, num_bytes, disk_num_bytes,
+				&meta_reserve, &qgroup_reserve);
 	ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_reserve, true);
 	if (ret)
 		return ret;

@@ -346,7 +348,7 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
 	spin_lock(&inode->lock);
 	nr_extents = count_max_extents(num_bytes);
 	btrfs_mod_outstanding_extents(inode, nr_extents);
-	inode->csum_bytes += num_bytes;
+	inode->csum_bytes += disk_num_bytes;
 	btrfs_calculate_inode_block_rsv_size(fs_info, inode);
 	spin_unlock(&inode->lock);
 

@@ -451,7 +453,7 @@ int btrfs_delalloc_reserve_space(struct btrfs_inode *inode,
 	ret = btrfs_check_data_free_space(inode, reserved, start, len);
 	if (ret < 0)
 		return ret;
-	ret = btrfs_delalloc_reserve_metadata(inode, len);
+	ret = btrfs_delalloc_reserve_metadata(inode, len, len);
 	if (ret < 0)
 		btrfs_free_reserved_data_space(inode, *reserved, start, len);
 	return ret;

index 7ff577005d0f..6f9cb8baffd2 100644
@@ -1741,7 +1741,8 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb,
 					 fs_info->sectorsize);
 		WARN_ON(reserve_bytes == 0);
 		ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode),
-				reserve_bytes);
+						      reserve_bytes,
+						      reserve_bytes);
 		if (ret) {
 			if (!only_release_metadata)
 				btrfs_free_reserved_data_space(BTRFS_I(inode),

index a85c1050ae95..6aad4b641d5c 100644
@@ -5043,7 +5043,7 @@ int btrfs_truncate_block(struct btrfs_inode *inode, loff_t from, loff_t len,
 			goto out;
 		}
 	}
-	ret = btrfs_delalloc_reserve_metadata(inode, blocksize);
+	ret = btrfs_delalloc_reserve_metadata(inode, blocksize, blocksize);
 	if (ret < 0) {
 		if (!only_release_metadata)
 			btrfs_free_reserved_data_space(inode, data_reserved,

index 63d2b22cf438..879fa0ea465c 100644
@@ -3017,7 +3017,7 @@ static int relocate_one_page(struct inode *inode, struct file_ra_state *ra,
 
 		/* Reserve metadata for this range */
 		ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode),
-						      clamped_len);
+						      clamped_len, clamped_len);
 		if (ret)
 			goto release_page;
 

index 6aad4b641d5c..a87a34f56234 100644
@@ -236,9 +236,10 @@ static int btrfs_init_inode_security(struct btrfs_trans_handle *trans,
 static int insert_inline_extent(struct btrfs_trans_handle *trans,
 				struct btrfs_path *path, bool extent_inserted,
 				struct btrfs_root *root, struct inode *inode,
-				u64 start, size_t size, size_t compressed_size,
+				size_t size, size_t compressed_size,
 				int compress_type,
-				struct page **compressed_pages)
+				struct page **compressed_pages,
+				bool update_i_size)
 {
 	struct extent_buffer *leaf;
 	struct page *page = NULL;

@@ -247,7 +248,7 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans,
 	struct btrfs_file_extent_item *ei;
 	int ret;
 	size_t cur_size = size;
-	unsigned long offset;
+	u64 i_size;
 
 	ASSERT((compressed_size > 0 && compressed_pages) ||
 	       (compressed_size == 0 && !compressed_pages));

@@ -260,7 +261,7 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans,
 		size_t datasize;
 
 		key.objectid = btrfs_ino(BTRFS_I(inode));
-		key.offset = start;
+		key.offset = 0;
 		key.type = BTRFS_EXTENT_DATA_KEY;
 
 		datasize = btrfs_file_extent_calc_inline_size(cur_size);

@@ -297,12 +298,10 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans,
 		btrfs_set_file_extent_compression(leaf, ei,
 						  compress_type);
 	} else {
-		page = find_get_page(inode->i_mapping,
-				     start >> PAGE_SHIFT);
+		page = find_get_page(inode->i_mapping, 0);
 		btrfs_set_file_extent_compression(leaf, ei, 0);
 		kaddr = kmap_atomic(page);
-		offset = offset_in_page(start);
-		write_extent_buffer(leaf, kaddr + offset, ptr, size);
+		write_extent_buffer(leaf, kaddr, ptr, size);
 		kunmap_atomic(kaddr);
 		put_page(page);
 	}

@@ -313,8 +312,8 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans,
 	 * We align size to sectorsize for inline extents just for simplicity
 	 * sake.
 	 */
-	size = ALIGN(size, root->fs_info->sectorsize);
-	ret = btrfs_inode_set_file_extent_range(BTRFS_I(inode), start, size);
+	ret = btrfs_inode_set_file_extent_range(BTRFS_I(inode), 0,
+					ALIGN(size, root->fs_info->sectorsize));
 	if (ret)
 		goto fail;
 

@@ -327,7 +326,13 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans,
 	 * before we unlock the pages.  Otherwise we
 	 * could end up racing with unlink.
 	 */
-	BTRFS_I(inode)->disk_i_size = inode->i_size;
+	i_size = i_size_read(inode);
+	if (update_i_size && size > i_size) {
+		i_size_write(inode, size);
+		i_size = size;
+	}
+	BTRFS_I(inode)->disk_i_size = i_size;
+
 fail:
 	return ret;
 }

@@ -338,35 +343,31 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans,
  * does the checks required to make sure the data is small enough
  * to fit as an inline extent.
  */
-static noinline int cow_file_range_inline(struct btrfs_inode *inode, u64 start,
-					  u64 end, size_t compressed_size,
+static noinline int cow_file_range_inline(struct btrfs_inode *inode, u64 size,
+					  size_t compressed_size,
 					  int compress_type,
-					  struct page **compressed_pages)
+					  struct page **compressed_pages,
+					  bool update_i_size)
 {
 	struct btrfs_drop_extents_args drop_args = { 0 };
 	struct btrfs_root *root = inode->root;
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_trans_handle *trans;
-	u64 isize = i_size_read(&inode->vfs_inode);
-	u64 actual_end = min(end + 1, isize);
-	u64 inline_len = actual_end - start;
-	u64 aligned_end = ALIGN(end, fs_info->sectorsize);
-	u64 data_len = inline_len;
+	u64 data_len = compressed_size ? compressed_size : size;
 	int ret;
 	struct btrfs_path *path;
 
-	if (compressed_size)
-		data_len = compressed_size;
-
-	if (start > 0 ||
-	    actual_end > fs_info->sectorsize ||
+	/*
+	 * We can create an inline extent if it ends at or beyond the current
+	 * i_size, is no larger than a sector (decompressed), and the (possibly
+	 * compressed) data fits in a leaf and the configured maximum inline
+	 * size.
+	 */
+	if (size < i_size_read(&inode->vfs_inode) ||
+	    size > fs_info->sectorsize ||
 	    data_len > BTRFS_MAX_INLINE_DATA_SIZE(fs_info) ||
-	    (!compressed_size &&
-	    (actual_end & (fs_info->sectorsize - 1)) == 0) ||
-	    end + 1 < isize ||
-	    data_len > fs_info->max_inline) {
+	    data_len > fs_info->max_inline)
 		return 1;
-	}
 
 	path = btrfs_alloc_path();
 	if (!path)

@@ -380,30 +381,21 @@ static noinline int cow_file_range_inline(struct btrfs_inode *inode, u64 start,
 	trans->block_rsv = &inode->block_rsv;
 
 	drop_args.path = path;
-	drop_args.start = start;
-	drop_args.end = aligned_end;
+	drop_args.start = 0;
+	drop_args.end = fs_info->sectorsize;
 	drop_args.drop_cache = true;
 	drop_args.replace_extent = true;
-
-	if (compressed_size && compressed_pages)
-		drop_args.extent_item_size = btrfs_file_extent_calc_inline_size(
-		   compressed_size);
-	else
-		drop_args.extent_item_size = btrfs_file_extent_calc_inline_size(
-		    inline_len);
-
+	drop_args.extent_item_size = btrfs_file_extent_calc_inline_size(data_len);
 	ret = btrfs_drop_extents(trans, root, inode, &drop_args);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		goto out;
 	}
 
-	if (isize > actual_end)
-		inline_len = min_t(u64, isize, actual_end);
-	ret = insert_inline_extent(trans, path, drop_args.extent_inserted,
-				   root, &inode->vfs_inode, start,
-				   inline_len, compressed_size,
-				   compress_type, compressed_pages);
+	ret = insert_inline_extent(trans, path, drop_args.extent_inserted, root,
+				   &inode->vfs_inode, size, compressed_size,
+				   compress_type, compressed_pages,
+				   update_i_size);
 	if (ret && ret != -ENOSPC) {
 		btrfs_abort_transaction(trans, ret);
 		goto out;

@@ -412,7 +404,7 @@ static noinline int cow_file_range_inline(struct btrfs_inode *inode, u64 start,
 		goto out;
 	}
 
-	btrfs_update_inode_bytes(inode, inline_len, drop_args.bytes_found);
+	btrfs_update_inode_bytes(inode, size, drop_args.bytes_found);
 	ret = btrfs_update_inode(trans, root, inode);
 	if (ret && ret != -ENOSPC) {
 		btrfs_abort_transaction(trans, ret);

@@ -695,14 +687,15 @@ static noinline int compress_file_range(struct async_chunk *async_chunk)
 			/* we didn't compress the entire range, try
 			 * to make an uncompressed inline extent.
 			 */
-			ret = cow_file_range_inline(BTRFS_I(inode), start, end,
+			ret = cow_file_range_inline(BTRFS_I(inode), actual_end,
 						    0, BTRFS_COMPRESS_NONE,
-						    NULL);
+						    NULL, false);
 		} else {
 			/* try making a compressed inline extent */
-			ret = cow_file_range_inline(BTRFS_I(inode), start, end,
+			ret = cow_file_range_inline(BTRFS_I(inode), actual_end,
 						    total_compressed,
-						    compress_type, pages);
+						    compress_type, pages,
+						    false);
 		}
 		if (ret <= 0) {
 			unsigned long clear_flags = EXTENT_DELALLOC |

@@ -1098,9 +1091,12 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
 	 * So here we skip inline extent creation completely.
 	 */
 	if (start == 0 && fs_info->sectorsize == PAGE_SIZE) {
+		u64 actual_end = min_t(u64, i_size_read(&inode->vfs_inode),
+				       end + 1);
+
 		/* lets try to make an inline extent */
-		ret = cow_file_range_inline(inode, start, end, 0,
-					    BTRFS_COMPRESS_NONE, NULL);
+		ret = cow_file_range_inline(inode, actual_end, 0,
+					    BTRFS_COMPRESS_NONE, NULL, false);
 		if (ret == 0) {
 			/*
 			 * We use DO_ACCOUNTING here because we need the

index d7d3cfead056..95da52955894 100644
@@ -861,6 +861,134 @@ struct btrfs_ioctl_get_subvol_rootref_args {
 		__u8 align[7];
 };
 
+/*
+ * Data and metadata for an encoded read or write.
+ *
+ * Encoded I/O bypasses any encoding automatically done by the filesystem (e.g.,
+ * compression). This can be used to read the compressed contents of a file or
+ * write pre-compressed data directly to a file.
+ *
+ * BTRFS_IOC_ENCODED_READ and BTRFS_IOC_ENCODED_WRITE are essentially
+ * preadv/pwritev with additional metadata about how the data is encoded and the
+ * size of the unencoded data.
+ *
+ * BTRFS_IOC_ENCODED_READ fills the given iovecs with the encoded data, fills
+ * the metadata fields, and returns the size of the encoded data. It reads one
+ * extent per call. It can also read data which is not encoded.
+ *
+ * BTRFS_IOC_ENCODED_WRITE uses the metadata fields, writes the encoded data
+ * from the iovecs, and returns the size of the encoded data. Note that the
+ * encoded data is not validated when it is written; if it is not valid (e.g.,
+ * it cannot be decompressed), then a subsequent read may return an error.
+ *
+ * Since the filesystem page cache contains decoded data, encoded I/O bypasses
+ * the page cache. Encoded I/O requires CAP_SYS_ADMIN.
+ */
+struct btrfs_ioctl_encoded_io_args {
+	/* Input parameters for both reads and writes. */
+
+	/*
+	 * iovecs containing encoded data.
+	 *
+	 * For reads, if the size of the encoded data is larger than the sum of
+	 * iov[n].iov_len for 0 <= n < iovcnt, then the ioctl fails with
+	 * ENOBUFS.
+	 *
+	 * For writes, the size of the encoded data is the sum of iov[n].iov_len
+	 * for 0 <= n < iovcnt. This must be less than 128 KiB (this limit may
+	 * increase in the future). This must also be less than or equal to
+	 * unencoded_len.
+	 */
+	const struct iovec __user *iov;
+	/* Number of iovecs. */
+	unsigned long iovcnt;
+	/*
+	 * Offset in file.
+	 *
+	 * For writes, must be aligned to the sector size of the filesystem.
+	 */
+	__s64 offset;
+	/* Currently must be zero. */
+	__u64 flags;
+
+	/*
+	 * For reads, the following members are filled in with the metadata for
+	 * the encoded data.
+	 * For writes, the following members must be set to the metadata for the
+	 * encoded data.
+	 */
+
+	/*
+	 * Length of the data in the file.
+	 *
+	 * Must be less than or equal to unencoded_len - unencoded_offset. For
+	 * writes, must be aligned to the sector size of the filesystem unless
+	 * the data ends at or beyond the current end of the file.
+	 */
+	__u64 len;
+	/*
+	 * Length of the unencoded (i.e., decrypted and decompressed) data.
+	 *
+	 * For writes, must be no more than 128 KiB (this limit may increase in
+	 * the future). If the unencoded data is actually longer than
+	 * unencoded_len, then it is truncated; if it is shorter, then it is
+	 * extended with zeroes.
+	 */
+	__u64 unencoded_len;
+	/*
+	 * Offset from the first byte of the unencoded data to the first byte of
+	 * logical data in the file.
+	 *
+	 * Must be less than unencoded_len.
+	 */
+	__u64 unencoded_offset;
+	/*
+	 * BTRFS_ENCODED_IO_COMPRESSION_* type.
+	 *
+	 * For writes, must not be BTRFS_ENCODED_IO_COMPRESSION_NONE.
+	 */
+	__u32 compression;
+	/* Currently always BTRFS_ENCODED_IO_ENCRYPTION_NONE. */
+	__u32 encryption;
+	/*
+	 * Reserved for future expansion.
+	 *
+	 * For reads, always returned as zero. Users should check for non-zero
+	 * bytes. If there are any, then the kernel has a newer version of this
+	 * structure with additional information that the user definition is
+	 * missing.
+	 *
+	 * For writes, must be zeroed.
+	 */
+	__u8 reserved[32];
+};
+
+/* Data is not compressed. */
+#define BTRFS_ENCODED_IO_COMPRESSION_NONE 0
+/* Data is compressed as a single zlib stream. */
+#define BTRFS_ENCODED_IO_COMPRESSION_ZLIB 1
+/*
+ * Data is compressed as a single zstd frame with the windowLog compression
+ * parameter set to no more than 17.
+ */
+#define BTRFS_ENCODED_IO_COMPRESSION_ZSTD 2
+/*
+ * Data is compressed page by page (using the page size indicated by the name of
+ * the constant) with LZO1X and wrapped in the format documented in
+ * fs/btrfs/lzo.c. For writes, the compression page size must match the
+ * filesystem page size.
+ */
+#define BTRFS_ENCODED_IO_COMPRESSION_LZO_4K 3
+#define BTRFS_ENCODED_IO_COMPRESSION_LZO_8K 4
+#define BTRFS_ENCODED_IO_COMPRESSION_LZO_16K 5
+#define BTRFS_ENCODED_IO_COMPRESSION_LZO_32K 6
+#define BTRFS_ENCODED_IO_COMPRESSION_LZO_64K 7
+#define BTRFS_ENCODED_IO_COMPRESSION_TYPES 8
+
+/* Data is not encrypted. */
+#define BTRFS_ENCODED_IO_ENCRYPTION_NONE 0
+#define BTRFS_ENCODED_IO_ENCRYPTION_TYPES 1
+
 /* Error codes as returned by the kernel */
 enum btrfs_err_code {
 	BTRFS_ERROR_DEV_RAID1_MIN_NOT_MET = 1,

@@ -989,5 +1117,9 @@ enum btrfs_err_code {
 				struct btrfs_ioctl_ino_lookup_user_args)
 #define BTRFS_IOC_SNAP_DESTROY_V2 _IOW(BTRFS_IOCTL_MAGIC, 63, \
 				struct btrfs_ioctl_vol_args_v2)
+#define BTRFS_IOC_ENCODED_READ _IOR(BTRFS_IOCTL_MAGIC, 64, \
+				    struct btrfs_ioctl_encoded_io_args)
+#define BTRFS_IOC_ENCODED_WRITE _IOW(BTRFS_IOCTL_MAGIC, 64, \
+				     struct btrfs_ioctl_encoded_io_args)
 
 #endif /* _UAPI_LINUX_BTRFS_H */

index b95ec5fb68d5..cbd7e07c1c34 100644
@@ -3223,6 +3223,10 @@ int btrfs_writepage_cow_fixup(struct page *page);
 void btrfs_writepage_endio_finish_ordered(struct btrfs_inode *inode,
 					  struct page *page, u64 start,
 					  u64 end, bool uptodate);
+struct btrfs_ioctl_encoded_io_args;
+ssize_t btrfs_encoded_read(struct kiocb *iocb, struct iov_iter *iter,
+			   struct btrfs_ioctl_encoded_io_args *encoded);
+
 extern const struct dentry_operations btrfs_dentry_operations;
 extern const struct iomap_ops btrfs_dio_iomap_ops;
 extern const struct iomap_dio_ops btrfs_dio_ops;

495 lines not on this page · raw message

135 lines not on this page · raw message

index e645b3c2f09a..a9845aab3b18 100644
@@ -353,7 +353,8 @@ static void end_compressed_bio_write(struct bio *bio)
 			cb->start, cb->start + cb->len - 1,
 			!cb->errors);
 
-	end_compressed_writeback(inode, cb);
+	if (cb->writeback)
+		end_compressed_writeback(inode, cb);
 	/* note, our inode could be gone now */
 
 	/*

@@ -389,7 +390,8 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
 				 struct page **compressed_pages,
 				 unsigned int nr_pages,
 				 unsigned int write_flags,
-				 struct cgroup_subsys_state *blkcg_css)
+				 struct cgroup_subsys_state *blkcg_css,
+				 bool writeback)
 {
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct bio *bio = NULL;

@@ -415,6 +417,7 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
 	cb->mirror_num = 0;
 	cb->compressed_pages = compressed_pages;
 	cb->compressed_len = compressed_len;
+	cb->writeback = writeback;
 	cb->orig_bio = NULL;
 	cb->nr_pages = nr_pages;
 

index 399be0b435bf..2ba9402f308d 100644
@@ -52,6 +52,9 @@ struct compressed_bio {
 	/* The compression algorithm for this bio */
 	u8 compress_type;
 
+	/* Whether this is a write for writeback. */
+	bool writeback;
+
 	/* IO errors */
 	u8 errors;
 	int mirror_num;

@@ -95,7 +98,8 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
 				  struct page **compressed_pages,
 				  unsigned int nr_pages,
 				  unsigned int write_flags,
-				  struct cgroup_subsys_state *blkcg_css);
+				  struct cgroup_subsys_state *blkcg_css,
+				  bool writeback);
 blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 				 int mirror_num, unsigned long bio_flags);
 

index cbd7e07c1c34..7753976bc3c7 100644
@@ -3226,6 +3226,8 @@ void btrfs_writepage_endio_finish_ordered(struct btrfs_inode *inode,
 struct btrfs_ioctl_encoded_io_args;
 ssize_t btrfs_encoded_read(struct kiocb *iocb, struct iov_iter *iter,
 			   struct btrfs_ioctl_encoded_io_args *encoded);
+ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from,
+			     const struct btrfs_ioctl_encoded_io_args *encoded);
 
 extern const struct dentry_operations btrfs_dentry_operations;
 extern const struct iomap_ops btrfs_dio_iomap_ops;

@@ -3286,6 +3288,8 @@ int btrfs_replace_file_extents(struct btrfs_inode *inode,
 			   struct btrfs_trans_handle **trans_out);
 int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
 			      struct btrfs_inode *inode, u64 start, u64 end);
+ssize_t btrfs_do_write_iter(struct kiocb *iocb, struct iov_iter *from,
+			    const struct btrfs_ioctl_encoded_io_args *encoded);
 int btrfs_release_file(struct inode *inode, struct file *file);
 int btrfs_dirty_pages(struct btrfs_inode *inode, struct page **pages,
 		      size_t num_pages, loff_t pos, size_t write_bytes,

94 lines not on this page · raw message

280 lines not on this page · raw message

123 lines not on this page · raw message

index 550c34fa0e6d..180f302dee93 100644
@@ -521,9 +521,15 @@ void btrfs_remove_ordered_extent(struct btrfs_inode *btrfs_inode,
 	spin_lock(&btrfs_inode->lock);
 	btrfs_mod_outstanding_extents(btrfs_inode, -1);
 	spin_unlock(&btrfs_inode->lock);
-	if (root != fs_info->tree_root)
-		btrfs_delalloc_release_metadata(btrfs_inode, entry->num_bytes,
-						false);
+	if (root != fs_info->tree_root) {
+		u64 release;
+
+		if (test_bit(BTRFS_ORDERED_ENCODED, &entry->flags))
+			release = entry->disk_num_bytes;
+		else
+			release = entry->num_bytes;
+		btrfs_delalloc_release_metadata(btrfs_inode, release, false);
+	}
 
 	percpu_counter_add_batch(&fs_info->ordered_bytes, -entry->num_bytes,
 				 fs_info->delalloc_batch);

index 0feb0c29839e..aeb17714ba5a 100644
@@ -74,6 +74,8 @@ enum {
 	BTRFS_ORDERED_LOGGED_CSUM,
 	/* We wait for this extent to complete in the current transaction */
 	BTRFS_ORDERED_PENDING,
+	/* BTRFS_IOC_ENCODED_WRITE */
+	BTRFS_ORDERED_ENCODED,
 };
 
 /* BTRFS_ORDERED_* flags that specify the type of the extent. */

@@ -81,7 +83,8 @@ enum {
 				  (1UL << BTRFS_ORDERED_NOCOW) |	\
 				  (1UL << BTRFS_ORDERED_PREALLOC) |	\
 				  (1UL << BTRFS_ORDERED_COMPRESSED) |	\
-				  (1UL << BTRFS_ORDERED_DIRECT))
+				  (1UL << BTRFS_ORDERED_DIRECT) |	\
+				  (1UL << BTRFS_ORDERED_ENCODED))
 
 struct btrfs_ordered_extent {
 	/* logical offset in the file */

index afdcbe7844e0..2ec07943f173 100644
@@ -7287,7 +7287,7 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg)
 
 	sctx->clone_roots_cnt = arg->clone_sources_count;
 
-	sctx->send_max_size = BTRFS_SEND_BUF_SIZE;
+	sctx->send_max_size = BTRFS_SEND_BUF_SIZE_V1;
 	sctx->send_buf = kvmalloc(sctx->send_max_size, GFP_KERNEL);
 	if (!sctx->send_buf) {
 		ret = -ENOMEM;

index de91488b7cd0..9f4f7b96b1eb 100644
@@ -12,7 +12,11 @@
 #define BTRFS_SEND_STREAM_MAGIC "btrfs-stream"
 #define BTRFS_SEND_STREAM_VERSION 1
 
-#define BTRFS_SEND_BUF_SIZE SZ_64K
+/*
+ * In send stream v1, no command is larger than 64k. In send stream v2, no limit
+ * should be assumed.
+ */
+#define BTRFS_SEND_BUF_SIZE_V1 SZ_64K
 
 enum btrfs_tlv_type {
 	BTRFS_TLV_U8,

@@ -76,6 +80,13 @@ enum btrfs_send_cmd {
 
 	BTRFS_SEND_C_END,
 	BTRFS_SEND_C_UPDATE_EXTENT,
+
+	/* The following commands were added in send stream v2. */
+
+	BTRFS_SEND_C_FALLOCATE,
+	BTRFS_SEND_C_SETFLAGS,
+	BTRFS_SEND_C_ENCODED_WRITE,
+
 	__BTRFS_SEND_C_MAX,
 };
 #define BTRFS_SEND_C_MAX (__BTRFS_SEND_C_MAX - 1)

@@ -106,6 +117,11 @@ enum {
 	BTRFS_SEND_A_PATH_LINK,
 
 	BTRFS_SEND_A_FILE_OFFSET,
+	/*
+	 * In send stream v2, this attribute is special: it must be the last
+	 * attribute in a command, its header contains only the type, and its
+	 * length is implicitly the remaining length of the command.
+	 */
 	BTRFS_SEND_A_DATA,
 
 	BTRFS_SEND_A_CLONE_UUID,

@@ -114,6 +130,18 @@ enum {
 	BTRFS_SEND_A_CLONE_OFFSET,
 	BTRFS_SEND_A_CLONE_LEN,
 
+	/* The following attributes were added in send stream v2. */
+
+	BTRFS_SEND_A_FALLOCATE_MODE,
+
+	BTRFS_SEND_A_SETFLAGS_FLAGS,
+
+	BTRFS_SEND_A_UNENCODED_FILE_LEN,
+	BTRFS_SEND_A_UNENCODED_LEN,
+	BTRFS_SEND_A_UNENCODED_OFFSET,
+	BTRFS_SEND_A_COMPRESSION,
+	BTRFS_SEND_A_ENCRYPTION,
+
 	__BTRFS_SEND_A_MAX,
 };
 #define BTRFS_SEND_A_MAX (__BTRFS_SEND_A_MAX - 1)

index 95da52955894..4f875f355e83 100644
@@ -771,6 +771,19 @@ struct btrfs_ioctl_received_subvol_args {
  */
 #define BTRFS_SEND_FLAG_OMIT_END_CMD		0x4
 
+/*
+ * Use version 2 of the send stream, which adds new commands and supports larger
+ * writes.
+ */
+#define BTRFS_SEND_FLAG_STREAM_V2		0x8
+
+/*
+ * Send compressed data using the ENCODED_WRITE command instead of decompressing
+ * the data and sending it with the WRITE command. This requires
+ * BTRFS_SEND_FLAG_STREAM_V2.
+ */
+#define BTRFS_SEND_FLAG_COMPRESSED		0x10
+
 #define BTRFS_SEND_FLAG_MASK \
 	(BTRFS_SEND_FLAG_NO_FILE_DATA | \
 	 BTRFS_SEND_FLAG_OMIT_STREAM_HEADER | \

index 90ca915fed78..46443d80b431 100644
@@ -81,6 +81,7 @@ struct send_ctx {
 	char *send_buf;
 	u32 send_size;
 	u32 send_max_size;
+	bool put_data;
 	struct page **send_buf_pages;
 	u64 total_send_size;
 	u64 cmd_send_size[BTRFS_SEND_C_MAX + 1];

@@ -575,6 +576,9 @@ static int tlv_put(struct send_ctx *sctx, u16 attr, const void *data, int len)
 	int total_len = sizeof(*hdr) + len;
 	int left = sctx->send_max_size - sctx->send_size;
 
+	if (WARN_ON(sctx->put_data))
+		return -EINVAL;
+
 	if (unlikely(left < total_len))
 		return -EOVERFLOW;
 

@@ -718,6 +722,7 @@ static int send_cmd(struct send_ctx *sctx)
 	sctx->total_send_size += sctx->send_size;
 	sctx->cmd_send_size[get_unaligned_le16(&hdr->cmd)] += sctx->send_size;
 	sctx->send_size = 0;
+	sctx->put_data = false;
 
 	return ret;
 }

@@ -4913,6 +4918,9 @@ static inline u64 max_send_read_size(const struct send_ctx *sctx)
 
 static int put_data_header(struct send_ctx *sctx, u32 len)
 {
+	if (WARN_ON(sctx->put_data))
+		return -EINVAL;
+	sctx->put_data = true;
 	if (sctx->flags & BTRFS_SEND_FLAG_STREAM_V2) {
 		/*
 		 * In v2, the data attribute header doesn't include a length; it

@@ -5368,6 +5376,7 @@ static int send_encoded_extent(struct send_ctx *sctx, struct btrfs_path *path,
 	sctx->cmd_send_size[le16_to_cpu(hdr->cmd)] +=
 		sctx->send_size + block_len;
 	sctx->send_size = 0;
+	sctx->put_data = false;
 
 tlv_put_failure:
 out:

index 2ec07943f173..80736e2670eb 100644
@@ -4908,14 +4908,27 @@ static inline u64 max_send_read_size(const struct send_ctx *sctx)
 
 static int put_data_header(struct send_ctx *sctx, u32 len)
 {
-	struct btrfs_tlv_header *hdr;
+	if (sctx->flags & BTRFS_SEND_FLAG_STREAM_V2) {
+		/*
+		 * In v2, the data attribute header doesn't include a length; it
+		 * is implicitly to the end of the command.
+		 */
+		if (sctx->send_max_size - sctx->send_size < 2 + len)
+			return -EOVERFLOW;
+		put_unaligned_le16(BTRFS_SEND_A_DATA,
+				   sctx->send_buf + sctx->send_size);
+		sctx->send_size += 2;
+	} else {
+		struct btrfs_tlv_header *hdr;
 
-	if (sctx->send_max_size - sctx->send_size < sizeof(*hdr) + len)
-		return -EOVERFLOW;
-	hdr = (struct btrfs_tlv_header *)(sctx->send_buf + sctx->send_size);
-	put_unaligned_le16(BTRFS_SEND_A_DATA, &hdr->tlv_type);
-	put_unaligned_le16(len, &hdr->tlv_len);
-	sctx->send_size += sizeof(*hdr);
+		if (sctx->send_max_size - sctx->send_size < sizeof(*hdr) + len)
+			return -EOVERFLOW;
+		hdr = (struct btrfs_tlv_header *)(sctx->send_buf +
+						  sctx->send_size);
+		put_unaligned_le16(BTRFS_SEND_A_DATA, &hdr->tlv_type);
+		put_unaligned_le16(len, &hdr->tlv_len);
+		sctx->send_size += sizeof(*hdr);
+	}
 	return 0;
 }
 

@@ -7287,7 +7300,12 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg)
 
 	sctx->clone_roots_cnt = arg->clone_sources_count;
 
-	sctx->send_max_size = BTRFS_SEND_BUF_SIZE_V1;
+	if (sctx->flags & BTRFS_SEND_FLAG_STREAM_V2) {
+		sctx->send_max_size = ALIGN(SZ_16K + BTRFS_MAX_COMPRESSED,
+					    PAGE_SIZE);
+	} else {
+		sctx->send_max_size = BTRFS_SEND_BUF_SIZE_V1;
+	}
 	sctx->send_buf = kvmalloc(sctx->send_max_size, GFP_KERNEL);
 	if (!sctx->send_buf) {
 		ret = -ENOMEM;

index 80736e2670eb..a000efe2658a 100644
@@ -81,6 +81,7 @@ struct send_ctx {
 	char *send_buf;
 	u32 send_size;
 	u32 send_max_size;
+	struct page **send_buf_pages;
 	u64 total_send_size;
 	u64 cmd_send_size[BTRFS_SEND_C_MAX + 1];
 	u64 flags;	/* 'flags' member of btrfs_ioctl_send_args is u64 */

@@ -7223,6 +7224,7 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg)
 	struct btrfs_root *clone_root;
 	struct send_ctx *sctx = NULL;
 	u32 i;
+	u32 send_buf_num_pages = 0;
 	u64 *clone_sources_tmp = NULL;
 	int clone_sources_to_rollback = 0;
 	size_t alloc_size;

@@ -7303,10 +7305,28 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg)
 	if (sctx->flags & BTRFS_SEND_FLAG_STREAM_V2) {
 		sctx->send_max_size = ALIGN(SZ_16K + BTRFS_MAX_COMPRESSED,
 					    PAGE_SIZE);
+		send_buf_num_pages = sctx->send_max_size >> PAGE_SHIFT;
+		sctx->send_buf_pages = kcalloc(send_buf_num_pages,
+					       sizeof(*sctx->send_buf_pages),
+					       GFP_KERNEL);
+		if (!sctx->send_buf_pages) {
+			send_buf_num_pages = 0;
+			ret = -ENOMEM;
+			goto out;
+		}
+		for (i = 0; i < send_buf_num_pages; i++) {
+			sctx->send_buf_pages[i] = alloc_page(GFP_KERNEL);
+			if (!sctx->send_buf_pages[i]) {
+				ret = -ENOMEM;
+				goto out;
+			}
+		}
+		sctx->send_buf = vmap(sctx->send_buf_pages, send_buf_num_pages,
+				      VM_MAP, PAGE_KERNEL);
 	} else {
 		sctx->send_max_size = BTRFS_SEND_BUF_SIZE_V1;
+		sctx->send_buf = kvmalloc(sctx->send_max_size, GFP_KERNEL);
 	}
-	sctx->send_buf = kvmalloc(sctx->send_max_size, GFP_KERNEL);
 	if (!sctx->send_buf) {
 		ret = -ENOMEM;
 		goto out;

@@ -7513,7 +7533,16 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg)
 			fput(sctx->send_filp);
 
 		kvfree(sctx->clone_roots);
-		kvfree(sctx->send_buf);
+		if (sctx->flags & BTRFS_SEND_FLAG_STREAM_V2) {
+			vunmap(sctx->send_buf);
+			for (i = 0; i < send_buf_num_pages; i++) {
+				if (sctx->send_buf_pages[i])
+					__free_page(sctx->send_buf_pages[i]);
+			}
+			kfree(sctx->send_buf_pages);
+		} else {
+			kvfree(sctx->send_buf);
+		}
 
 		name_cache_free(sctx);
 

index 7753976bc3c7..caec0422a5c4 100644
@@ -3223,6 +3223,10 @@ int btrfs_writepage_cow_fixup(struct page *page);
 void btrfs_writepage_endio_finish_ordered(struct btrfs_inode *inode,
 					  struct page *page, u64 start,
 					  u64 end, bool uptodate);
+int btrfs_encoded_io_compression_from_extent(int compress_type);
+int btrfs_encoded_read_regular_fill_pages(struct inode *inode, u64 offset,
+					  u64 disk_io_size,
+					  struct page **pages);
 struct btrfs_ioctl_encoded_io_args;
 ssize_t btrfs_encoded_read(struct kiocb *iocb, struct iov_iter *iter,
 			   struct btrfs_ioctl_encoded_io_args *encoded);

index e751af96c198..6c40419eb2b1 100644
@@ -10502,7 +10502,7 @@ void btrfs_set_range_writeback(struct btrfs_inode *inode, u64 start, u64 end)
 	}
 }
 
-static int btrfs_encoded_io_compression_from_extent(int compress_type)
+int btrfs_encoded_io_compression_from_extent(int compress_type)
 {
 	switch (compress_type) {
 	case BTRFS_COMPRESS_NONE:

@@ -10705,8 +10705,8 @@ static void btrfs_encoded_read_endio(struct bio *bio)
 	bio_put(bio);
 }
 
-static int btrfs_encoded_read_regular_fill_pages(struct inode *inode, u64 offset,
-						 u64 disk_io_size, struct page **pages)
+int btrfs_encoded_read_regular_fill_pages(struct inode *inode, u64 offset,
+					  u64 disk_io_size, struct page **pages)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_encoded_read_private priv = {

292 lines not on this page · raw message

index 0ba8dc3a9f56..90ca915fed78 100644
@@ -671,7 +671,10 @@ static int send_header(struct send_ctx *sctx)
 	struct btrfs_stream_header hdr;
 
 	strcpy(hdr.magic, BTRFS_SEND_STREAM_MAGIC);
-	hdr.version = cpu_to_le32(BTRFS_SEND_STREAM_VERSION);
+	if (sctx->flags & BTRFS_SEND_FLAG_STREAM_V2)
+		hdr.version = cpu_to_le32(2);
+	else
+		hdr.version = cpu_to_le32(1);
 
 	return write_buf(sctx->send_filp, &hdr, sizeof(hdr),
 					&sctx->send_off);

@@ -7466,6 +7469,11 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg)
 		ret = -EINVAL;
 		goto out;
 	}
+	if ((arg->flags & BTRFS_SEND_FLAG_COMPRESSED) &&
+	    !(arg->flags & BTRFS_SEND_FLAG_STREAM_V2)) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	sctx = kzalloc(sizeof(struct send_ctx), GFP_KERNEL);
 	if (!sctx) {

index 9f4f7b96b1eb..9c83e14a43b2 100644
@@ -10,7 +10,7 @@
 #include "ctree.h"
 
 #define BTRFS_SEND_STREAM_MAGIC "btrfs-stream"
-#define BTRFS_SEND_STREAM_VERSION 1
+#define BTRFS_SEND_STREAM_VERSION 2
 
 /*
  * In send stream v1, no command is larger than 64k. In send stream v2, no limit

index 4f875f355e83..5c13e407982f 100644
@@ -787,7 +787,9 @@ struct btrfs_ioctl_received_subvol_args {
 #define BTRFS_SEND_FLAG_MASK \
 	(BTRFS_SEND_FLAG_NO_FILE_DATA | \
 	 BTRFS_SEND_FLAG_OMIT_STREAM_HEADER | \
-	 BTRFS_SEND_FLAG_OMIT_END_CMD)
+	 BTRFS_SEND_FLAG_OMIT_END_CMD | \
+	 BTRFS_SEND_FLAG_STREAM_V2 | \
+	 BTRFS_SEND_FLAG_COMPRESSED)
 
 struct btrfs_ioctl_send_args {
 	__s64 send_fd;			/* in */

index a0c52f79..cd5aa311 100644
@@ -24,13 +24,23 @@
 #include "crypto/crc32c.h"
 #include "common/utils.h"
 
+struct btrfs_send_attribute {
+	u16 tlv_type;
+	/*
+	 * Note: in btrfs_tlv_header, this is __le16, but we need 32 bits for
+	 * attributes with file data as of version 2 of the send stream format
+	 */
+	u32 tlv_len;
+	char *data;
+};
+
 struct btrfs_send_stream {
 	char read_buf[BTRFS_SEND_BUF_SIZE];
 	int fd;
 
 	int cmd;
 	struct btrfs_cmd_header *cmd_hdr;
-	struct btrfs_tlv_header *cmd_attrs[BTRFS_SEND_A_MAX + 1];
+	struct btrfs_send_attribute cmd_attrs[BTRFS_SEND_A_MAX + 1];
 	u32 version;
 
 	/*

@@ -152,6 +162,7 @@ static int read_cmd(struct btrfs_send_stream *sctx)
 		struct btrfs_tlv_header *tlv_hdr;
 		u16 tlv_type;
 		u16 tlv_len;
+		struct btrfs_send_attribute *send_attr;
 
 		tlv_hdr = (struct btrfs_tlv_header *)data;
 		tlv_type = le16_to_cpu(tlv_hdr->tlv_type);

@@ -164,10 +175,15 @@ static int read_cmd(struct btrfs_send_stream *sctx)
 			goto out;
 		}
 
-		sctx->cmd_attrs[tlv_type] = tlv_hdr;
+		send_attr = &sctx->cmd_attrs[tlv_type];
+		send_attr->tlv_type = tlv_type;
+		send_attr->tlv_len = tlv_len;
+		pos += sizeof(*tlv_hdr);
+		data += sizeof(*tlv_hdr);
 
-		data += sizeof(*tlv_hdr) + tlv_len;
-		pos += sizeof(*tlv_hdr) + tlv_len;
+		send_attr->data = data;
+		pos += send_attr->tlv_len;
+		data += send_attr->tlv_len;
 	}
 
 	sctx->cmd = cmd;

@@ -180,7 +196,7 @@ out:
 static int tlv_get(struct btrfs_send_stream *sctx, int attr, void **data, int *len)
 {
 	int ret;
-	struct btrfs_tlv_header *hdr;
+	struct btrfs_send_attribute *send_attr;
 
 	if (attr <= 0 || attr > BTRFS_SEND_A_MAX) {
 		error("invalid attribute requested, attr = %d", attr);

@@ -188,15 +204,15 @@ static int tlv_get(struct btrfs_send_stream *sctx, int attr, void **data, int *l
 		goto out;
 	}
 
-	hdr = sctx->cmd_attrs[attr];
-	if (!hdr) {
+	send_attr = &sctx->cmd_attrs[attr];
+	if (!send_attr->data) {
 		error("attribute %d requested but not present", attr);
 		ret = -ENOENT;
 		goto out;
 	}
 
-	*len = le16_to_cpu(hdr->tlv_len);
-	*data = hdr + 1;
+	*len = send_attr->tlv_len;
+	*data = send_attr->data;
 
 	ret = 0;
 

index cd5aa311..3d3585c3 100644
@@ -35,11 +35,11 @@ struct btrfs_send_attribute {
 };
 
 struct btrfs_send_stream {
-	char read_buf[BTRFS_SEND_BUF_SIZE];
+	char *read_buf;
+	size_t read_buf_sz;
 	int fd;
 
 	int cmd;
-	struct btrfs_cmd_header *cmd_hdr;
 	struct btrfs_send_attribute cmd_attrs[BTRFS_SEND_A_MAX + 1];
 	u32 version;
 

@@ -111,11 +111,12 @@ static int read_cmd(struct btrfs_send_stream *sctx)
 	u32 pos;
 	u32 crc;
 	u32 crc2;
+	struct btrfs_cmd_header *cmd_hdr;
+	size_t buf_len;
 
 	memset(sctx->cmd_attrs, 0, sizeof(sctx->cmd_attrs));
 
-	ASSERT(sizeof(*sctx->cmd_hdr) <= sizeof(sctx->read_buf));
-	ret = read_buf(sctx, sctx->read_buf, sizeof(*sctx->cmd_hdr));
+	ret = read_buf(sctx, sctx->read_buf, sizeof(*cmd_hdr));
 	if (ret < 0)
 		goto out;
 	if (ret) {

@@ -124,18 +125,22 @@ static int read_cmd(struct btrfs_send_stream *sctx)
 		goto out;
 	}
 
-	sctx->cmd_hdr = (struct btrfs_cmd_header *)sctx->read_buf;
-	cmd = le16_to_cpu(sctx->cmd_hdr->cmd);
-	cmd_len = le32_to_cpu(sctx->cmd_hdr->len);
-
-	if (cmd_len + sizeof(*sctx->cmd_hdr) >= sizeof(sctx->read_buf)) {
-		ret = -EINVAL;
-		error("command length %u too big for buffer %zu",
-				cmd_len, sizeof(sctx->read_buf));
-		goto out;
+	cmd_hdr = (struct btrfs_cmd_header *)sctx->read_buf;
+	cmd_len = le32_to_cpu(cmd_hdr->len);
+	cmd = le16_to_cpu(cmd_hdr->cmd);
+	buf_len = sizeof(*cmd_hdr) + cmd_len;
+	if (sctx->read_buf_sz < buf_len) {
+		sctx->read_buf = realloc(sctx->read_buf, buf_len);
+		if (!sctx->read_buf) {
+			ret = -ENOMEM;
+			error("failed to reallocate read buffer for cmd");
+			goto out;
+		}
+		sctx->read_buf_sz = buf_len;
+		/* We need to reset cmd_hdr after realloc of sctx->read_buf */
+		cmd_hdr = (struct btrfs_cmd_header *)sctx->read_buf;
 	}
-
-	data = sctx->read_buf + sizeof(*sctx->cmd_hdr);
+	data = sctx->read_buf + sizeof(*cmd_hdr);
 	ret = read_buf(sctx, data, cmd_len);
 	if (ret < 0)
 		goto out;

@@ -145,11 +150,12 @@ static int read_cmd(struct btrfs_send_stream *sctx)
 		goto out;
 	}
 
-	crc = le32_to_cpu(sctx->cmd_hdr->crc);
-	sctx->cmd_hdr->crc = 0;
+	crc = le32_to_cpu(cmd_hdr->crc);
+	/* in send, crc is computed with header crc = 0, replicate that */
+	cmd_hdr->crc = 0;
 
 	crc2 = crc32c(0, (unsigned char*)sctx->read_buf,
-			sizeof(*sctx->cmd_hdr) + cmd_len);
+			sizeof(*cmd_hdr) + cmd_len);
 
 	if (crc != crc2) {
 		ret = -EINVAL;

@@ -524,19 +530,28 @@ int btrfs_read_and_process_send_stream(int fd,
 		goto out;
 	}
 
+	sctx.read_buf = malloc(BTRFS_SEND_BUF_SIZE_V1);
+	if (!sctx.read_buf) {
+		ret = -ENOMEM;
+		error("unable to allocate send stream read buffer");
+		goto out;
+	}
+	sctx.read_buf_sz = BTRFS_SEND_BUF_SIZE_V1;
+
 	while (1) {
 		ret = read_and_process_cmd(&sctx);
 		if (ret < 0) {
 			last_err = ret;
 			errors++;
 			if (max_errors > 0 && errors >= max_errors)
-				goto out;
+				break;
 		} else if (ret > 0) {
 			if (!honor_end_cmd)
 				ret = 0;
-			goto out;
+			break;
 		}
 	}
+	free(sctx.read_buf);
 
 out:
 	if (last_err && !ret)

index 8dd865ec..228928a0 100644
@@ -33,7 +33,7 @@ extern "C" {
 #define BTRFS_SEND_STREAM_MAGIC "btrfs-stream"
 #define BTRFS_SEND_STREAM_VERSION 1
 
-#define BTRFS_SEND_BUF_SIZE SZ_64K
+#define BTRFS_SEND_BUF_SIZE_V1 SZ_64K
 #define BTRFS_SEND_READ_SIZE (1024 * 48)
 
 enum btrfs_tlv_type {

index 3d3585c3..4d819185 100644
@@ -165,28 +165,44 @@ static int read_cmd(struct btrfs_send_stream *sctx)
 
 	pos = 0;
 	while (pos < cmd_len) {
-		struct btrfs_tlv_header *tlv_hdr;
 		u16 tlv_type;
-		u16 tlv_len;
 		struct btrfs_send_attribute *send_attr;
 
-		tlv_hdr = (struct btrfs_tlv_header *)data;
-		tlv_type = le16_to_cpu(tlv_hdr->tlv_type);
-		tlv_len = le16_to_cpu(tlv_hdr->tlv_len);
+		if (cmd_len - pos < sizeof(__le16)) {
+			error("send stream is truncated");
+			ret = -EINVAL;
+			goto out;
+		}
+		tlv_type = le16_to_cpu(*(__le16 *)data);
 
 		if (tlv_type == 0 || tlv_type > BTRFS_SEND_A_MAX) {
-			error("invalid tlv in cmd tlv_type = %hu, tlv_len = %hu",
-					tlv_type, tlv_len);
+			error("invalid tlv in cmd tlv_type = %hu", tlv_type);
 			ret = -EINVAL;
 			goto out;
 		}
 
 		send_attr = &sctx->cmd_attrs[tlv_type];
 		send_attr->tlv_type = tlv_type;
-		send_attr->tlv_len = tlv_len;
-		pos += sizeof(*tlv_hdr);
-		data += sizeof(*tlv_hdr);
 
+		pos += sizeof(tlv_type);
+		data += sizeof(tlv_type);
+		if (sctx->version == 2 && tlv_type == BTRFS_SEND_A_DATA) {
+			send_attr->tlv_len = cmd_len - pos;
+		} else {
+			if (cmd_len - pos < sizeof(__le16)) {
+				error("send stream is truncated");
+				ret = -EINVAL;
+				goto out;
+			}
+			send_attr->tlv_len = le16_to_cpu(*(__le16 *)data);
+			pos += sizeof(__le16);
+			data += sizeof(__le16);
+		}
+		if (cmd_len - pos < send_attr->tlv_len) {
+			error("send stream is truncated");
+			ret = -EINVAL;
+			goto out;
+		}
 		send_attr->data = data;
 		pos += send_attr->tlv_len;
 		data += send_attr->tlv_len;