On Thu, Jun 24, 2021 at 03:00:39AM +0100, Matthew Wilcox wrote:
> On Wed, Jun 23, 2021 at 02:58:32PM -0700, Omar Sandoval wrote:
> > But what you described would look more like:
> >
> > // Needs to be large enough for maximum returned header + data.
> > char buffer[...];
> > struct iovec iov[] = {
> > { buffer, sizeof(buffer) },
> > };
> > preadv2(fd, iov, 2, -1, RWF_ENCODED);
> > // We should probably align the buffer.
> > struct encoded_iov *encoded_iov = (void *)buffer;
> > char *data = buffer + encoded_iov->size;
> >
> > That's a little uglier, but it should work, and allows for arbitrary
> > extensions. So, among these three alternatives (fixed size structure
> > with reserved space, variable size structure like above, or ioctl),
> > which would you prefer?
>
> Does that work for O_DIRECT and the required 512-byte alignment?
I suppose the kernel could pad the encoded_iov structure with zeroes to
the next sector boundary, since zeroes are effectively noops for
encoded_iov. (As an aside, RWF_ENCODED is always "direct I/O" in the
sense that it bypasses the page cache, but not necessarily in the sense
that it does DMA to/from the user buffers. The Btrfs implementation
doesn't do the latter yet.)
