On Tue, Oct 22, 2019 at 01:02:15PM +1100, Aleksa Sarai wrote: > On 2019-10-21, Darrick J. Wong <darrick.wong@xxxxxxxxxx> wrote: > > On Tue, Oct 22, 2019 at 05:38:31AM +1100, Aleksa Sarai wrote: > > > On 2019-10-21, Darrick J. Wong <darrick.wong@xxxxxxxxxx> wrote: > > > > On Tue, Oct 15, 2019 at 11:42:40AM -0700, Omar Sandoval wrote: > > > > > From: Omar Sandoval <osandov@xxxxxx> > > > > > > > > > > Btrfs supports transparent compression: data written by the user can be > > > > > compressed when written to disk and decompressed when read back. > > > > > However, we'd like to add an interface to write pre-compressed data > > > > > directly to the filesystem, and the matching interface to read > > > > > compressed data without decompressing it. This adds support for > > > > > so-called "encoded I/O" via preadv2() and pwritev2(). > > > > > > > > > > A new RWF_ENCODED flags indicates that a read or write is "encoded". If > > > > > this flag is set, iov[0].iov_base points to a struct encoded_iov which > > > > > is used for metadata: namely, the compression algorithm, unencoded > > > > > (i.e., decompressed) length, and what subrange of the unencoded data > > > > > should be used (needed for truncated or hole-punched extents and when > > > > > reading in the middle of an extent). For reads, the filesystem returns > > > > > this information; for writes, the caller provides it to the filesystem. > > > > > iov[0].iov_len must be set to sizeof(struct encoded_iov), which can be > > > > > used to extend the interface in the future. The remaining iovecs contain > > > > > the encoded extent. > > > > > > > > > > Filesystems must indicate that they support encoded writes by setting > > > > > FMODE_ENCODED_IO in ->file_open(). > > > > > > > > > > Signed-off-by: Omar Sandoval <osandov@xxxxxx> > > > > > --- > > > > > include/linux/fs.h | 14 +++++++ > > > > > include/uapi/linux/fs.h | 26 ++++++++++++- > > > > > mm/filemap.c | 82 ++++++++++++++++++++++++++++++++++------- > > > > > 3 files changed, 108 insertions(+), 14 deletions(-) > > > > > > > > > > diff --git a/include/linux/fs.h b/include/linux/fs.h > > > > > index e0d909d35763..54681f21e05e 100644 > > > > > --- a/include/linux/fs.h > > > > > +++ b/include/linux/fs.h > > > > > @@ -175,6 +175,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, > > > > > /* File does not contribute to nr_files count */ > > > > > #define FMODE_NOACCOUNT ((__force fmode_t)0x20000000) > > > > > > > > > > +/* File supports encoded IO */ > > > > > +#define FMODE_ENCODED_IO ((__force fmode_t)0x40000000) > > > > > + > > > > > /* > > > > > * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector > > > > > * that indicates that they should check the contents of the iovec are > > > > > @@ -314,6 +317,7 @@ enum rw_hint { > > > > > #define IOCB_SYNC (1 << 5) > > > > > #define IOCB_WRITE (1 << 6) > > > > > #define IOCB_NOWAIT (1 << 7) > > > > > +#define IOCB_ENCODED (1 << 8) > > > > > > > > > > struct kiocb { > > > > > struct file *ki_filp; > > > > > @@ -3088,6 +3092,11 @@ 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 *); > > > > > +struct encoded_iov; > > > > > +extern int generic_encoded_write_checks(struct kiocb *, struct encoded_iov *); > > > > > +extern ssize_t check_encoded_read(struct kiocb *, struct iov_iter *); > > > > > +extern int import_encoded_write(struct kiocb *, struct encoded_iov *, > > > > > + struct iov_iter *); > > > > > extern int generic_remap_checks(struct file *file_in, loff_t pos_in, > > > > > struct file *file_out, loff_t pos_out, > > > > > loff_t *count, unsigned int remap_flags); > > > > > @@ -3403,6 +3412,11 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) > > > > > return -EOPNOTSUPP; > > > > > ki->ki_flags |= IOCB_NOWAIT; > > > > > } > > > > > + if (flags & RWF_ENCODED) { > > > > > + if (!(ki->ki_filp->f_mode & FMODE_ENCODED_IO)) > > > > > + return -EOPNOTSUPP; > > > > > + ki->ki_flags |= IOCB_ENCODED; > > > > > + } > > > > > if (flags & RWF_HIPRI) > > > > > ki->ki_flags |= IOCB_HIPRI; > > > > > if (flags & RWF_DSYNC) > > > > > diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h > > > > > index 379a612f8f1d..ed92a8a257cb 100644 > > > > > --- a/include/uapi/linux/fs.h > > > > > +++ b/include/uapi/linux/fs.h > > > > > @@ -284,6 +284,27 @@ struct fsxattr { > > > > > > > > > > typedef int __bitwise __kernel_rwf_t; > > > > > > > > > > +enum { > > > > > + ENCODED_IOV_COMPRESSION_NONE, > > > > > + ENCODED_IOV_COMPRESSION_ZLIB, > > > > > + ENCODED_IOV_COMPRESSION_LZO, > > > > > + ENCODED_IOV_COMPRESSION_ZSTD, > > > > > + ENCODED_IOV_COMPRESSION_TYPES = ENCODED_IOV_COMPRESSION_ZSTD, > > > > > +}; > > > > > + > > > > > +enum { > > > > > + ENCODED_IOV_ENCRYPTION_NONE, > > > > > + ENCODED_IOV_ENCRYPTION_TYPES = ENCODED_IOV_ENCRYPTION_NONE, > > > > > +}; > > > > > + > > > > > +struct encoded_iov { > > > > > + __u64 len; > > > > > + __u64 unencoded_len; > > > > > + __u64 unencoded_offset; > > > > > + __u32 compression; > > > > > + __u32 encryption; > > > > > > > > Can we add some must-be-zero padding space at the end here for whomever > > > > comes along next wanting to add more encoding info? > > > > > > I would suggest to copy the extension design of copy_struct_from_user(). > > > Adding must-be-zero padding is a less-ideal solution to the extension > > > problem than length-based extension. > > > > Come to think of it, you /do/ have to specify iov_len so... yeah, do > > that instead; we can always extend the structure later. > > Just to clarify -- if we want to make the interface forward-compatible > from the outset (programs built 4 years from now running on 5.5), we > will need to implement this in the original merge. Otherwise userspace > will need to handle backwards-compatibility themselves once new features > are added. > > @Omar: If it'd make your life easier, I can send some draft patches > which port copy_struct_from_user() to iovec-land. You're right, I didn't think about the case of newer programs on older kernels. I can do that for the next submission. RWF_ENCODED should probably translate the E2BIG from copy_struct_from_user() to EINVAL, though, to avoid ambiguity with the case that the buffer wasn't big enough to return the encoded data.