On Thu, Jun 24, 2021 at 10:52:17AM -0700, Linus Torvalds wrote:

On Wed, Jun 23, 2021 at 11:15 PM Omar Sandoval [off-list ref] wrote:

quoted

On Thu, Jun 24, 2021 at 03:00:39AM +0100, Matthew Wilcox wrote:

quoted

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.

Ugh.

I really think the whole "embed the control structure in the stream"
is wrong. The alignment issue is just another sign of that.

Separating it out is the right thing to do. At least the "first iov
entry" thing did separate the control structure from the actual data.
I detest the whole "embed the two together".

I'll suggest the fixed-size struct encoded_iov again, then. If we're
willing to give up some of the flexibility of a variable size, then
userspace can always put the fixed-size structure in its own iovec or
include it inline with the data, depending on what's more convenient and
whether it's using O_DIRECT. A fixed size is much easier for both the
kernel and userspace to deal with. Do we really need to support
unlimited extensions to encoded_iov, or can we stick 32-64 bytes of
reserved space at the end of the structure and call it a day?