Re: [PATCH v1 23/30] io_uring/rsrc: split io_buffer_register_request() logic

[Joanne Koong <joannelkoong@gmail.com>]

On Sun, Dec 7, 2025 at 5:42 PM Caleb Sander Mateos
<csander@purestorage.com> wrote:
>
> On Tue, Dec 2, 2025 at 4:37 PM Joanne Koong <joannelkoong@gmail.com> wrote:
> >
> > Split the main initialization logic in io_buffer_register_request() into
> > a helper function.
> >
> > This is a preparatory patch for supporting kernel-populated buffers in
> > fuse io-uring, which will be reusing this logic.
> >
> > Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
> > ---
> >  io_uring/rsrc.c | 80 +++++++++++++++++++++++++++++--------------------
> >  1 file changed, 48 insertions(+), 32 deletions(-)
> >
> > diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
> > index 59cafe63d187..18abba6f6b86 100644
> > --- a/io_uring/rsrc.c
> > +++ b/io_uring/rsrc.c
> > @@ -941,63 +941,79 @@ int io_sqe_buffers_register(struct io_ring_ctx *ctx, void __user *arg,
> >         return ret;
> >  }
> >
> > -int io_buffer_register_request(struct io_ring_ctx *ctx, struct request *rq,
> > -                              void (*release)(void *), unsigned int index,
> > -                              unsigned int issue_flags)
> > +static int io_buffer_init(struct io_ring_ctx *ctx, unsigned int nr_bvecs,
>
> Consider adding "kernel" somewhere in the name to distinguish this
> from the userspace registered buffer initialization

I can rename this to io_kernel_buffer_init().

>
> > +                         unsigned int total_bytes, u8 dir,
> > +                         void (*release)(void *), void *priv,
> > +                         unsigned int index)
> >  {
> >         struct io_rsrc_data *data = &ctx->buf_table;
> > -       struct req_iterator rq_iter;
> >         struct io_mapped_ubuf *imu;
> >         struct io_rsrc_node *node;
> > -       struct bio_vec bv;
> > -       unsigned int nr_bvecs = 0;
> > -       int ret = 0;
> >
> > -       io_ring_submit_lock(ctx, issue_flags);
> > -       if (index >= data->nr) {
> > -               ret = -EINVAL;
> > -               goto unlock;
> > -       }
> > +       if (index >= data->nr)
> > +               return -EINVAL;
> >         index = array_index_nospec(index, data->nr);
> >
> > -       if (data->nodes[index]) {
> > -               ret = -EBUSY;
> > -               goto unlock;
> > -       }
> > +       if (data->nodes[index])
> > +               return -EBUSY;
> >
> >         node = io_rsrc_node_alloc(ctx, IORING_RSRC_BUFFER);
> > -       if (!node) {
> > -               ret = -ENOMEM;
> > -               goto unlock;
> > -       }
> > +       if (!node)
> > +               return -ENOMEM;
> >
> > -       /*
> > -        * blk_rq_nr_phys_segments() may overestimate the number of bvecs
> > -        * but avoids needing to iterate over the bvecs
> > -        */
> > -       imu = io_alloc_imu(ctx, blk_rq_nr_phys_segments(rq));
> > +       imu = io_alloc_imu(ctx, nr_bvecs);
> >         if (!imu) {
> >                 kfree(node);
> > -               ret = -ENOMEM;
> > -               goto unlock;
> > +               return -ENOMEM;
> >         }
> >
> >         imu->ubuf = 0;
> > -       imu->len = blk_rq_bytes(rq);
> > +       imu->len = total_bytes;
> >         imu->acct_pages = 0;
> >         imu->folio_shift = PAGE_SHIFT;
> > +       imu->nr_bvecs = nr_bvecs;
> >         refcount_set(&imu->refs, 1);
> >         imu->release = release;
> > -       imu->priv = rq;
> > +       imu->priv = priv;
> >         imu->is_kbuf = true;
> > -       imu->dir = 1 << rq_data_dir(rq);
> > +       imu->dir = 1 << dir;
> > +
> > +       node->buf = imu;
> > +       data->nodes[index] = node;
> > +
> > +       return 0;
> > +}
> > +
> > +int io_buffer_register_request(struct io_ring_ctx *ctx, struct request *rq,
> > +                              void (*release)(void *), unsigned int index,
> > +                              unsigned int issue_flags)
> > +{
> > +       struct req_iterator rq_iter;
> > +       struct io_mapped_ubuf *imu;
> > +       struct bio_vec bv;
> > +       unsigned int nr_bvecs;
> > +       unsigned int total_bytes;
> > +       int ret;
> > +
> > +       io_ring_submit_lock(ctx, issue_flags);
> > +
> > +       /*
> > +        * blk_rq_nr_phys_segments() may overestimate the number of bvecs
> > +        * but avoids needing to iterate over the bvecs
> > +        */
> > +       nr_bvecs = blk_rq_nr_phys_segments(rq);
> > +       total_bytes = blk_rq_bytes(rq);
>
> These could be initialized before io_ring_submit_lock()
>
> > +       ret = io_buffer_init(ctx, nr_bvecs, total_bytes, rq_data_dir(rq), release, rq,
> > +                            index);
> > +       if (ret)
> > +               goto unlock;
> >
> > +       imu = ctx->buf_table.nodes[index]->buf;
>
> It would be nice to avoid all these additional dereferences. Could
> io_buffer_init() return the struct io_mapped_ubuf *, using ERR_PTR()
> to return any error code?

I'll make this change for v2.

Thanks,
Joanne
>
> Best,
> Caleb