diff mbox series

[v6,11/11] btrfs: implement RWF_ENCODED writes

Message ID fe58a0fe2c1455567fe1e9e62232e8b711797a93.1605723568.git.osandov@fb.com (mailing list archive)
State New, archived
Headers show
Series fs: interface for directly reading/writing compressed data | expand

Commit Message

Omar Sandoval Nov. 18, 2020, 7:18 p.m. UTC
From: Omar Sandoval <osandov@fb.com>

The implementation resembles direct I/O: we have to flush any ordered
extents, invalidate the page cache, and do the io tree/delalloc/extent
map/ordered extent dance. From there, we can reuse the compression code
with a minor modification to distinguish the write from writeback. This
also creates inline extents when possible.

Now that read and write are implemented, this also sets the
FMODE_ENCODED_IO flag in btrfs_file_open().

Signed-off-by: Omar Sandoval <osandov@fb.com>
---
 fs/btrfs/compression.c  |   7 +-
 fs/btrfs/compression.h  |   6 +-
 fs/btrfs/ctree.h        |   2 +
 fs/btrfs/file.c         |  37 +++++-
 fs/btrfs/inode.c        | 259 +++++++++++++++++++++++++++++++++++++++-
 fs/btrfs/ordered-data.c |  12 +-
 fs/btrfs/ordered-data.h |   2 +
 7 files changed, 313 insertions(+), 12 deletions(-)

Comments

Josef Bacik Dec. 2, 2020, 10:03 p.m. UTC | #1
On 11/18/20 2:18 PM, Omar Sandoval wrote:
> From: Omar Sandoval <osandov@fb.com>
> 
> The implementation resembles direct I/O: we have to flush any ordered
> extents, invalidate the page cache, and do the io tree/delalloc/extent
> map/ordered extent dance. From there, we can reuse the compression code
> with a minor modification to distinguish the write from writeback. This
> also creates inline extents when possible.
> 
> Now that read and write are implemented, this also sets the
> FMODE_ENCODED_IO flag in btrfs_file_open().
> 
> Signed-off-by: Omar Sandoval <osandov@fb.com>
> ---
>   fs/btrfs/compression.c  |   7 +-
>   fs/btrfs/compression.h  |   6 +-
>   fs/btrfs/ctree.h        |   2 +
>   fs/btrfs/file.c         |  37 +++++-
>   fs/btrfs/inode.c        | 259 +++++++++++++++++++++++++++++++++++++++-
>   fs/btrfs/ordered-data.c |  12 +-
>   fs/btrfs/ordered-data.h |   2 +
>   7 files changed, 313 insertions(+), 12 deletions(-)
> 
> diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
> index eaa6fe21c08e..015c9e5d75b9 100644
> --- a/fs/btrfs/compression.c
> +++ b/fs/btrfs/compression.c
> @@ -336,7 +336,8 @@ static void end_compressed_bio_write(struct bio *bio)
>   			bio->bi_status == BLK_STS_OK);
>   	cb->compressed_pages[0]->mapping = NULL;
>   
> -	end_compressed_writeback(inode, cb);
> +	if (cb->writeback)
> +		end_compressed_writeback(inode, cb);
>   	/* note, our inode could be gone now */
>   
>   	/*
> @@ -372,7 +373,8 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
>   				 struct page **compressed_pages,
>   				 unsigned long 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;
> @@ -396,6 +398,7 @@ 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;
>   
> diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
> index 8001b700ea3a..f95cdc16f503 100644
> --- a/fs/btrfs/compression.h
> +++ b/fs/btrfs/compression.h
> @@ -49,6 +49,9 @@ struct compressed_bio {
>   	/* the compression algorithm for this bio */
>   	int compress_type;
>   
> +	/* Whether this is a write for writeback. */
> +	bool writeback;
> +
>   	/* number of compressed pages in the array */
>   	unsigned long nr_pages;
>   
> @@ -96,7 +99,8 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
>   				  struct page **compressed_pages,
>   				  unsigned long 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);
>   
> diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
> index ce78424f1d98..9b585ac9c7a9 100644
> --- a/fs/btrfs/ctree.h
> +++ b/fs/btrfs/ctree.h
> @@ -3134,6 +3134,8 @@ int btrfs_writepage_cow_fixup(struct page *page, u64 start, u64 end);
>   void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start,
>   					  u64 end, int uptodate);
>   ssize_t btrfs_encoded_read(struct kiocb *iocb, struct iov_iter *iter);
> +ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from,
> +			       struct encoded_iov *encoded);
>   
>   extern const struct dentry_operations btrfs_dentry_operations;
>   extern const struct iomap_ops btrfs_dio_iomap_ops;
> diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
> index 193477565200..f815ffb93d43 100644
> --- a/fs/btrfs/file.c
> +++ b/fs/btrfs/file.c
> @@ -1994,6 +1994,32 @@ static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
>   	return written ? written : err;
>   }
>   
> +static ssize_t btrfs_encoded_write(struct kiocb *iocb, struct iov_iter *from)
> +{
> +	struct file *file = iocb->ki_filp;
> +	struct inode *inode = file_inode(file);
> +	struct encoded_iov encoded;
> +	ssize_t ret;
> +
> +	ret = copy_encoded_iov_from_iter(&encoded, from);
> +	if (ret)
> +		return ret;
> +
> +	btrfs_inode_lock(inode, 0);
> +	ret = generic_encoded_write_checks(iocb, &encoded);
> +	if (ret || encoded.len == 0)
> +		goto out;
> +
> +	ret = btrfs_write_check(iocb, from, encoded.len);
> +	if (ret < 0)
> +		goto out;
> +
> +	ret = btrfs_do_encoded_write(iocb, from, &encoded);
> +out:
> +	btrfs_inode_unlock(inode, 0);
> +	return ret;
> +}
> +
>   static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
>   				    struct iov_iter *from)
>   {
> @@ -2012,14 +2038,17 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
>   	if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
>   		return -EROFS;
>   
> -	if (!(iocb->ki_flags & IOCB_DIRECT) &&
> -	    (iocb->ki_flags & IOCB_NOWAIT))
> +	if ((iocb->ki_flags & IOCB_NOWAIT) &&
> +	    (!(iocb->ki_flags & IOCB_DIRECT) ||
> +	     (iocb->ki_flags & IOCB_ENCODED)))
>   		return -EOPNOTSUPP;
>   
>   	if (sync)
>   		atomic_inc(&BTRFS_I(inode)->sync_writers);
>   
> -	if (iocb->ki_flags & IOCB_DIRECT)
> +	if (iocb->ki_flags & IOCB_ENCODED)
> +		num_written = btrfs_encoded_write(iocb, from);
> +	else if (iocb->ki_flags & IOCB_DIRECT)
>   		num_written = btrfs_direct_write(iocb, from);
>   	else
>   		num_written = btrfs_buffered_write(iocb, from);
> @@ -3586,7 +3615,7 @@ static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int whence)
>   
>   static int btrfs_file_open(struct inode *inode, struct file *filp)
>   {
> -	filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC;
> +	filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC | FMODE_ENCODED_IO;
>   	return generic_file_open(inode, filp);
>   }
>   
> diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
> index b0e800897b3b..2bf7b487939f 100644
> --- a/fs/btrfs/inode.c
> +++ b/fs/btrfs/inode.c
> @@ -935,7 +935,7 @@ static noinline void submit_compressed_extents(struct async_chunk *async_chunk)
>   				    ins.offset, async_extent->pages,
>   				    async_extent->nr_pages,
>   				    async_chunk->write_flags,
> -				    async_chunk->blkcg_css)) {
> +				    async_chunk->blkcg_css, true)) {
>   			struct page *p = async_extent->pages[0];
>   			const u64 start = async_extent->start;
>   			const u64 end = start + async_extent->ram_size - 1;
> @@ -2703,6 +2703,7 @@ static int insert_ordered_extent_file_extent(struct btrfs_trans_handle *trans,
>   	 * except if the ordered extent was truncated.
>   	 */
>   	update_inode_bytes = test_bit(BTRFS_ORDERED_DIRECT, &oe->flags) ||
> +	                     test_bit(BTRFS_ORDERED_ENCODED, &oe->flags) ||

Gotta use our git hooks, checkpatch caught the spaces here.  Thanks,

Josef
Josef Bacik Dec. 3, 2020, 2:37 p.m. UTC | #2
On 11/18/20 2:18 PM, Omar Sandoval wrote:
> From: Omar Sandoval <osandov@fb.com>
> 
> The implementation resembles direct I/O: we have to flush any ordered
> extents, invalidate the page cache, and do the io tree/delalloc/extent
> map/ordered extent dance. From there, we can reuse the compression code
> with a minor modification to distinguish the write from writeback. This
> also creates inline extents when possible.
> 
> Now that read and write are implemented, this also sets the
> FMODE_ENCODED_IO flag in btrfs_file_open().
> 
> Signed-off-by: Omar Sandoval <osandov@fb.com>

Fix up the spacing thing and then you can add

Reviewed-by: Josef Bacik <josef@toxicpanda.com>

Thanks,

Josef
diff mbox series

Patch

diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index eaa6fe21c08e..015c9e5d75b9 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -336,7 +336,8 @@  static void end_compressed_bio_write(struct bio *bio)
 			bio->bi_status == BLK_STS_OK);
 	cb->compressed_pages[0]->mapping = NULL;
 
-	end_compressed_writeback(inode, cb);
+	if (cb->writeback)
+		end_compressed_writeback(inode, cb);
 	/* note, our inode could be gone now */
 
 	/*
@@ -372,7 +373,8 @@  blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
 				 struct page **compressed_pages,
 				 unsigned long 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;
@@ -396,6 +398,7 @@  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;
 
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 8001b700ea3a..f95cdc16f503 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -49,6 +49,9 @@  struct compressed_bio {
 	/* the compression algorithm for this bio */
 	int compress_type;
 
+	/* Whether this is a write for writeback. */
+	bool writeback;
+
 	/* number of compressed pages in the array */
 	unsigned long nr_pages;
 
@@ -96,7 +99,8 @@  blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
 				  struct page **compressed_pages,
 				  unsigned long 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);
 
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index ce78424f1d98..9b585ac9c7a9 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3134,6 +3134,8 @@  int btrfs_writepage_cow_fixup(struct page *page, u64 start, u64 end);
 void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start,
 					  u64 end, int uptodate);
 ssize_t btrfs_encoded_read(struct kiocb *iocb, struct iov_iter *iter);
+ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from,
+			       struct encoded_iov *encoded);
 
 extern const struct dentry_operations btrfs_dentry_operations;
 extern const struct iomap_ops btrfs_dio_iomap_ops;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 193477565200..f815ffb93d43 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1994,6 +1994,32 @@  static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
 	return written ? written : err;
 }
 
+static ssize_t btrfs_encoded_write(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file_inode(file);
+	struct encoded_iov encoded;
+	ssize_t ret;
+
+	ret = copy_encoded_iov_from_iter(&encoded, from);
+	if (ret)
+		return ret;
+
+	btrfs_inode_lock(inode, 0);
+	ret = generic_encoded_write_checks(iocb, &encoded);
+	if (ret || encoded.len == 0)
+		goto out;
+
+	ret = btrfs_write_check(iocb, from, encoded.len);
+	if (ret < 0)
+		goto out;
+
+	ret = btrfs_do_encoded_write(iocb, from, &encoded);
+out:
+	btrfs_inode_unlock(inode, 0);
+	return ret;
+}
+
 static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 				    struct iov_iter *from)
 {
@@ -2012,14 +2038,17 @@  static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
 		return -EROFS;
 
-	if (!(iocb->ki_flags & IOCB_DIRECT) &&
-	    (iocb->ki_flags & IOCB_NOWAIT))
+	if ((iocb->ki_flags & IOCB_NOWAIT) &&
+	    (!(iocb->ki_flags & IOCB_DIRECT) ||
+	     (iocb->ki_flags & IOCB_ENCODED)))
 		return -EOPNOTSUPP;
 
 	if (sync)
 		atomic_inc(&BTRFS_I(inode)->sync_writers);
 
-	if (iocb->ki_flags & IOCB_DIRECT)
+	if (iocb->ki_flags & IOCB_ENCODED)
+		num_written = btrfs_encoded_write(iocb, from);
+	else if (iocb->ki_flags & IOCB_DIRECT)
 		num_written = btrfs_direct_write(iocb, from);
 	else
 		num_written = btrfs_buffered_write(iocb, from);
@@ -3586,7 +3615,7 @@  static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int whence)
 
 static int btrfs_file_open(struct inode *inode, struct file *filp)
 {
-	filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC;
+	filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC | FMODE_ENCODED_IO;
 	return generic_file_open(inode, filp);
 }
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index b0e800897b3b..2bf7b487939f 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -935,7 +935,7 @@  static noinline void submit_compressed_extents(struct async_chunk *async_chunk)
 				    ins.offset, async_extent->pages,
 				    async_extent->nr_pages,
 				    async_chunk->write_flags,
-				    async_chunk->blkcg_css)) {
+				    async_chunk->blkcg_css, true)) {
 			struct page *p = async_extent->pages[0];
 			const u64 start = async_extent->start;
 			const u64 end = start + async_extent->ram_size - 1;
@@ -2703,6 +2703,7 @@  static int insert_ordered_extent_file_extent(struct btrfs_trans_handle *trans,
 	 * except if the ordered extent was truncated.
 	 */
 	update_inode_bytes = test_bit(BTRFS_ORDERED_DIRECT, &oe->flags) ||
+	                     test_bit(BTRFS_ORDERED_ENCODED, &oe->flags) ||
 			     test_bit(BTRFS_ORDERED_TRUNCATED, &oe->flags);
 
 	return insert_reserved_file_extent(trans, BTRFS_I(oe->inode),
@@ -2737,7 +2738,8 @@  static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 
 	if (!test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags) &&
 	    !test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags) &&
-	    !test_bit(BTRFS_ORDERED_DIRECT, &ordered_extent->flags))
+	    !test_bit(BTRFS_ORDERED_DIRECT, &ordered_extent->flags) &&
+	    !test_bit(BTRFS_ORDERED_ENCODED, &ordered_extent->flags))
 		clear_bits |= EXTENT_DELALLOC_NEW;
 
 	freespace_inode = btrfs_is_free_space_inode(inode);
@@ -10432,6 +10434,259 @@  ssize_t btrfs_encoded_read(struct kiocb *iocb, struct iov_iter *iter)
 	return ret;
 }
 
+ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from,
+			       struct encoded_iov *encoded)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
+	struct extent_changeset *data_reserved = NULL;
+	struct extent_state *cached_state = NULL;
+	int compression;
+	size_t orig_count;
+	u64 start, end;
+	u64 num_bytes, ram_bytes, disk_num_bytes;
+	unsigned long nr_pages, i;
+	struct page **pages;
+	struct btrfs_key ins;
+	bool extent_reserved = false;
+	struct extent_map *em;
+	ssize_t ret;
+
+	switch (encoded->compression) {
+	case ENCODED_IOV_COMPRESSION_BTRFS_ZLIB:
+		compression = BTRFS_COMPRESS_ZLIB;
+		break;
+	case ENCODED_IOV_COMPRESSION_BTRFS_ZSTD:
+		compression = BTRFS_COMPRESS_ZSTD;
+		break;
+	case ENCODED_IOV_COMPRESSION_BTRFS_LZO_4K:
+	case ENCODED_IOV_COMPRESSION_BTRFS_LZO_8K:
+	case ENCODED_IOV_COMPRESSION_BTRFS_LZO_16K:
+	case ENCODED_IOV_COMPRESSION_BTRFS_LZO_32K:
+	case ENCODED_IOV_COMPRESSION_BTRFS_LZO_64K:
+		/* The page size must match for LZO. */
+		if (encoded->compression -
+		    ENCODED_IOV_COMPRESSION_BTRFS_LZO_4K + 12 != PAGE_SHIFT)
+			return -EINVAL;
+		compression = BTRFS_COMPRESS_LZO;
+		break;
+	default:
+		return -EINVAL;
+	}
+	if (encoded->encryption != ENCODED_IOV_ENCRYPTION_NONE)
+		return -EINVAL;
+
+	orig_count = iov_iter_count(from);
+
+	/* The extent size must be sane. */
+	if (encoded->unencoded_len > BTRFS_MAX_UNCOMPRESSED ||
+	    orig_count > BTRFS_MAX_COMPRESSED || orig_count == 0)
+		return -EINVAL;
+
+	/*
+	 * The compressed data must be smaller than the decompressed data.
+	 *
+	 * It's of course possible for data to compress to larger or the same
+	 * size, but the buffered I/O path falls back to no compression for such
+	 * data, and we don't want to break any assumptions by creating these
+	 * extents.
+	 *
+	 * Note that this is less strict than the current check we have that the
+	 * compressed data must be at least one sector smaller than the
+	 * decompressed data. We only want to enforce the weaker requirement
+	 * from old kernels that it is at least one byte smaller.
+	 */
+	if (orig_count >= encoded->unencoded_len)
+		return -EINVAL;
+
+	/* The extent must start on a sector boundary. */
+	start = iocb->ki_pos;
+	if (!IS_ALIGNED(start, fs_info->sectorsize))
+		return -EINVAL;
+
+	/*
+	 * The extent must end on a sector boundary. However, we allow a write
+	 * which ends at or extends i_size to have an unaligned length; we round
+	 * up the extent size and set i_size to the unaligned end.
+	 */
+	if (start + encoded->len < inode->i_size &&
+	    !IS_ALIGNED(start + encoded->len, fs_info->sectorsize))
+		return -EINVAL;
+
+	/* Finally, the offset in the unencoded data must be sector-aligned. */
+	if (!IS_ALIGNED(encoded->unencoded_offset, fs_info->sectorsize))
+		return -EINVAL;
+
+	num_bytes = ALIGN(encoded->len, fs_info->sectorsize);
+	ram_bytes = ALIGN(encoded->unencoded_len, fs_info->sectorsize);
+	end = start + num_bytes - 1;
+
+	/*
+	 * If the extent cannot be inline, the compressed data on disk must be
+	 * sector-aligned. For convenience, we extend it with zeroes if it
+	 * isn't.
+	 */
+	disk_num_bytes = ALIGN(orig_count, fs_info->sectorsize);
+	nr_pages = DIV_ROUND_UP(disk_num_bytes, PAGE_SIZE);
+	pages = kvcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL_ACCOUNT);
+	if (!pages)
+		return -ENOMEM;
+	for (i = 0; i < nr_pages; i++) {
+		size_t bytes = min_t(size_t, PAGE_SIZE, iov_iter_count(from));
+		char *kaddr;
+
+		pages[i] = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_HIGHMEM);
+		if (!pages[i]) {
+			ret = -ENOMEM;
+			goto out_pages;
+		}
+		kaddr = kmap(pages[i]);
+		if (copy_from_iter(kaddr, bytes, from) != bytes) {
+			kunmap(pages[i]);
+			ret = -EFAULT;
+			goto out_pages;
+		}
+		if (bytes < PAGE_SIZE)
+			memset(kaddr + bytes, 0, PAGE_SIZE - bytes);
+		kunmap(pages[i]);
+	}
+
+	for (;;) {
+		struct btrfs_ordered_extent *ordered;
+
+		ret = btrfs_wait_ordered_range(inode, start, num_bytes);
+		if (ret)
+			goto out_pages;
+		ret = invalidate_inode_pages2_range(inode->i_mapping,
+						    start >> PAGE_SHIFT,
+						    end >> PAGE_SHIFT);
+		if (ret)
+			goto out_pages;
+		lock_extent_bits(io_tree, start, end, &cached_state);
+		ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), start,
+						     num_bytes);
+		if (!ordered &&
+		    !filemap_range_has_page(inode->i_mapping, start, end))
+			break;
+		if (ordered)
+			btrfs_put_ordered_extent(ordered);
+		unlock_extent_cached(io_tree, start, end, &cached_state);
+		cond_resched();
+	}
+
+	/*
+	 * We don't use the higher-level delalloc space functions because our
+	 * num_bytes and disk_num_bytes are different.
+	 */
+	ret = btrfs_alloc_data_chunk_ondemand(BTRFS_I(inode), disk_num_bytes);
+	if (ret)
+		goto out_unlock;
+	ret = btrfs_qgroup_reserve_data(BTRFS_I(inode), &data_reserved, start,
+					num_bytes);
+	if (ret)
+		goto out_free_data_space;
+	ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), num_bytes,
+					      disk_num_bytes);
+	if (ret)
+		goto out_qgroup_free_data;
+
+	/* Try an inline extent first. */
+	if (start == 0 && encoded->unencoded_len == encoded->len &&
+	    encoded->unencoded_offset == 0) {
+		ret = cow_file_range_inline(BTRFS_I(inode), encoded->len,
+					    orig_count, compression, pages,
+					    true);
+		if (ret <= 0) {
+			if (ret == 0)
+				ret = orig_count;
+			goto out_delalloc_release;
+		}
+	}
+
+	ret = btrfs_reserve_extent(root, disk_num_bytes, disk_num_bytes,
+				   disk_num_bytes, 0, 0, &ins, 1, 1);
+	if (ret)
+		goto out_delalloc_release;
+	extent_reserved = true;
+
+	em = create_io_em(BTRFS_I(inode), start, num_bytes,
+			  start - encoded->unencoded_offset, ins.objectid,
+			  ins.offset, ins.offset, ram_bytes, compression,
+			  BTRFS_ORDERED_COMPRESSED);
+	if (IS_ERR(em)) {
+		ret = PTR_ERR(em);
+		goto out_free_reserved;
+	}
+	free_extent_map(em);
+
+	ret = btrfs_add_ordered_extent(BTRFS_I(inode), start, num_bytes,
+				       ram_bytes, ins.objectid, ins.offset,
+				       encoded->unencoded_offset,
+				       (1 << BTRFS_ORDERED_ENCODED) |
+				       (1 << BTRFS_ORDERED_COMPRESSED),
+				       compression);
+	if (ret) {
+		btrfs_drop_extent_cache(BTRFS_I(inode), start, end, 0);
+		goto out_free_reserved;
+	}
+	btrfs_dec_block_group_reservations(fs_info, ins.objectid);
+
+	if (start + encoded->len > inode->i_size)
+		i_size_write(inode, start + encoded->len);
+
+	unlock_extent_cached(io_tree, start, end, &cached_state);
+
+	btrfs_delalloc_release_extents(BTRFS_I(inode), num_bytes);
+
+	if (btrfs_submit_compressed_write(BTRFS_I(inode), start, num_bytes,
+					  ins.objectid, ins.offset, pages,
+					  nr_pages, 0, NULL, false)) {
+		struct page *page = pages[0];
+
+		page->mapping = inode->i_mapping;
+		btrfs_writepage_endio_finish_ordered(page, start, end, 0);
+		page->mapping = NULL;
+		ret = -EIO;
+		goto out_pages;
+	}
+	ret = orig_count;
+	goto out;
+
+out_free_reserved:
+	btrfs_dec_block_group_reservations(fs_info, ins.objectid);
+	btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, 1);
+out_delalloc_release:
+	btrfs_delalloc_release_extents(BTRFS_I(inode), num_bytes);
+	btrfs_delalloc_release_metadata(BTRFS_I(inode), disk_num_bytes,
+					ret < 0);
+out_qgroup_free_data:
+	if (ret < 0) {
+		btrfs_qgroup_free_data(BTRFS_I(inode), data_reserved, start,
+				       num_bytes);
+	}
+out_free_data_space:
+	/*
+	 * If btrfs_reserve_extent() succeeded, then we already decremented
+	 * bytes_may_use.
+	 */
+	if (!extent_reserved)
+		btrfs_free_reserved_data_space_noquota(fs_info, disk_num_bytes);
+out_unlock:
+	unlock_extent_cached(io_tree, start, end, &cached_state);
+out_pages:
+	for (i = 0; i < nr_pages; i++) {
+		if (pages[i])
+			__free_page(pages[i]);
+	}
+	kvfree(pages);
+out:
+	if (ret >= 0)
+		iocb->ki_pos += encoded->len;
+	return ret;
+}
+
 #ifdef CONFIG_SWAP
 /*
  * Add an entry indicating a block group or device which is pinned by a
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 76dc47315016..34f5fb548fb5 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -460,9 +460,15 @@  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);
+	}
 
 	if (test_bit(BTRFS_ORDERED_DIRECT, &entry->flags))
 		percpu_counter_add_batch(&fs_info->dio_bytes, -entry->num_bytes,
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index f2798c1fc7b0..19b7ea0354c0 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -62,6 +62,8 @@  enum {
 	BTRFS_ORDERED_LOGGED_CSUM,
 	/* We wait for this extent to complete in the current transaction */
 	BTRFS_ORDERED_PENDING,
+	/* RWF_ENCODED I/O */
+	BTRFS_ORDERED_ENCODED,
 };
 
 struct btrfs_ordered_extent {