On 12/19/23 2:03 PM, David Wei wrote:
> @@ -750,6 +753,54 @@ enum {
> SOCKET_URING_OP_SETSOCKOPT,
> };
>
> +struct io_uring_rbuf_rqe {
> + __u32 off;
> + __u32 len;
> + __u16 region;
> + __u8 __pad[6];
> +};
> +
> +struct io_uring_rbuf_cqe {
> + __u32 off;
> + __u32 len;
> + __u16 region;
> + __u8 sock;
> + __u8 flags;
> + __u8 __pad[2];
> +};
Looks like this leaves a gap? Should be __pad[4] or probably just __u32
__pad; For all of these, definitely worth thinking about if we'll ever
need more than the slight padding. Might not hurt to always leave 8
bytes extra, outside of the required padding.
> +struct io_rbuf_rqring_offsets {
> + __u32 head;
> + __u32 tail;
> + __u32 rqes;
> + __u8 __pad[4];
> +};
Ditto here, __u32 __pad;
> +struct io_rbuf_cqring_offsets {
> + __u32 head;
> + __u32 tail;
> + __u32 cqes;
> + __u8 __pad[4];
> +};
And here.
> +
> +/*
> + * Argument for IORING_REGISTER_ZC_RX_IFQ
> + */
> +struct io_uring_zc_rx_ifq_reg {
> + __u32 if_idx;
> + /* hw rx descriptor ring id */
> + __u32 if_rxq_id;
> + __u32 region_id;
> + __u32 rq_entries;
> + __u32 cq_entries;
> + __u32 flags;
> + __u16 cpu;
> +
> + __u32 mmap_sz;
> + struct io_rbuf_rqring_offsets rq_off;
> + struct io_rbuf_cqring_offsets cq_off;
> +};
You have rq_off starting at a 48-bit offset here, don't think this is
going to work as it's uapi. You'd need padding to align it to 64-bits.
> diff --git a/io_uring/zc_rx.c b/io_uring/zc_rx.c
> new file mode 100644
> index 000000000000..5fc94cad5e3a
> --- /dev/null
> +++ b/io_uring/zc_rx.c
> +int io_register_zc_rx_ifq(struct io_ring_ctx *ctx,
> + struct io_uring_zc_rx_ifq_reg __user *arg)
> +{
> + struct io_uring_zc_rx_ifq_reg reg;
> + struct io_zc_rx_ifq *ifq;
> + int ret;
> +
> + if (!(ctx->flags & IORING_SETUP_DEFER_TASKRUN))
> + return -EINVAL;
> + if (copy_from_user(®, arg, sizeof(reg)))
> + return -EFAULT;
> + if (ctx->ifq)
> + return -EBUSY;
> + if (reg.if_rxq_id == -1)
> + return -EINVAL;
> +
> + ifq = io_zc_rx_ifq_alloc(ctx);
> + if (!ifq)
> + return -ENOMEM;
> +
> + /* TODO: initialise network interface */
> +
> + ret = io_allocate_rbuf_ring(ifq, ®);
> + if (ret)
> + goto err;
> +
> + /* TODO: map zc region and initialise zc pool */
> +
> + ifq->rq_entries = reg.rq_entries;
> + ifq->cq_entries = reg.cq_entries;
> + ifq->if_rxq_id = reg.if_rxq_id;
> + ctx->ifq = ifq;
As these TODO's are removed in later patches, I think you should just
not include them to begin with. It reads more like notes to yourself,
doesn't really add anything to the series.
> +void io_shutdown_zc_rx_ifqs(struct io_ring_ctx *ctx)
> +{
> + lockdep_assert_held(&ctx->uring_lock);
> +}
This is a bit odd?
--
Jens Axboe
