[Lsf-pc] [LSF/MM/BPF ATTEND][LSF/MM/BPF TOPIC] Meta/Integrity/PI improvements

[Dongyang Li]

On Tue, 2024-04-02 at 22:22 +0530, Kanchan Joshi wrote:
> On 4/2/2024 4:15 PM, Dongyang Li wrote:
> > Martin, Kanchan,
> > > 
> > > Kanchan,
> > > 
> > > > - Generic user interface that user-space can use to exchange
> > > > meta.
> > > > A
> > > > new io_uring opcode IORING_OP_READ/WRITE_META - seems feasible
> > > > for
> > > > direct IO.
> > > 
> > > Yep. I'm interested in this too. Reviving this effort is near the
> > > top
> > > of
> > > my todo list so I'm happy to collaborate.
> > If we are going to have a interface to exchange meta/integrity to
> > user-
> > space, we could also have a interface in kernel to do the same?
> 
> Not sure if I follow.
> Currently when blk-integrity allocates/attaches the meta buffer, it 
> decides what to put in it and how to go about integrity 
> generation/verification.
> When user-space is sending the meta buffer, it will decide what to 
> put/verify. Passed meta buffer will be used directly, and blk-
> integrity 
> will only facilitate that without doing any in-kernel 
> generation/verification.
This is what I was trying to get, but for in-kernel users instead of
user-space, however...
> 
> > It would be useful for some network filesystem/block device drivers
> > like nbd/drbd/NVMe-oF to use blk-integrity as network checksum, and
> > the
> > same checksum covers the I/O on the server as well.
> > 
> > The integrity can be generated on the client and send over network,
> > on server blk-integrity can just offload to storage.
> > Verify follows the same principle: on server blk-integrity gets
> > the PI from storage using the interface, and send over network,
> > on client we can do the usual verify.
> > 
> > In the past we tried to achieve this, there's patch to add optional
> > generate/verify functions and they take priority over the ones from
> > the
> > integrity profile, and the optional generate/verify functions does
> > the
> > meta/PI exchange, but that didn't get traction. It would be much
> > better
> > if we can have an bio interface for this.
> 
> Any link to the patches?
> I am not sure what this bio interface is for. Does this mean 
> verify/generate functions to be specified for each bio?
Yes, and it's an awkward way to save the meta/PI before the PI buffer
gets freed right after verify.
> Now also in-kernel users can add the meta buffer to the bio. It is up
> to 
> the bio owner to implement any custom processing on this meta buffer.
This makes me realise if in-kernel user does its own meta/PI buffer
management without bio_integrity_prep(), it won't be freed by
bio_integrity_free() and we can put/get to the meta/PI buffer and reuse
the PI data. I will give this a try. Thanks