netdev - Re: [PATCH bpf-next 04/10] i40e: xsk: terminate NAPI when XSK Rx queue gets full

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Tue, 5 Apr 2022 15:04:17 +0200
From:   Jesper Dangaard Brouer <jbrouer@...hat.com>
To:     Maciej Fijalkowski <maciej.fijalkowski@...el.com>,
        bpf@...r.kernel.org, ast@...nel.org, daniel@...earbox.net,
        magnus.karlsson@...el.com, bjorn@...nel.org
Cc:     brouer@...hat.com, netdev@...r.kernel.org, maximmi@...dia.com,
        alexandr.lobakin@...el.com,
        Toke Hoiland Jorgensen <toke@...hat.com>
Subject: Re: [PATCH bpf-next 04/10] i40e: xsk: terminate NAPI when XSK Rx
 queue gets full



On 05/04/2022 13.06, Maciej Fijalkowski wrote:
> Correlate -ENOBUFS that was returned from xdp_do_redirect() with a XSK
> Rx queue being full. In such case, terminate the softirq processing and
> let the user space to consume descriptors from XSK Rx queue so that
> there is room that driver can use later on.
> 
> Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@...el.com>
> ---
>   .../ethernet/intel/i40e/i40e_txrx_common.h    |  1 +
>   drivers/net/ethernet/intel/i40e/i40e_xsk.c    | 21 ++++++++++++-------
>   2 files changed, 15 insertions(+), 7 deletions(-)
> 
[...]

I noticed you are only doing this for the Zero-Copy variants.
Wouldn't this also be a benefit for normal AF_XDP ?


> diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
> index c1d25b0b0ca2..9f9e4ce9a24d 100644
> --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
> +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
> @@ -161,9 +161,10 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
>   
>   	if (likely(act == XDP_REDIRECT)) {
>   		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
> -		if (err)
> -			goto out_failure;
> -		return I40E_XDP_REDIR;
> +		if (!err)
> +			return I40E_XDP_REDIR;
> +		result = (err == -ENOBUFS) ? I40E_XDP_EXIT : I40E_XDP_CONSUMED;
> +		goto out_failure;
>   	}
>   
>   	switch (act) {
> @@ -175,6 +176,9 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
>   		if (result == I40E_XDP_CONSUMED)
>   			goto out_failure;
>   		break;
> +	case XDP_DROP:
> +		result = I40E_XDP_CONSUMED;
> +		break;
>   	default:
>   		bpf_warn_invalid_xdp_action(rx_ring->netdev, xdp_prog, act);
>   		fallthrough;
> @@ -182,9 +186,6 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp)
>   out_failure:
>   		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
>   		fallthrough; /* handle aborts by dropping packet */
> -	case XDP_DROP:
> -		result = I40E_XDP_CONSUMED;
> -		break;
>   	}
>   	return result;
>   }
> @@ -370,6 +371,12 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
>   		xsk_buff_dma_sync_for_cpu(bi, rx_ring->xsk_pool);
>   
>   		xdp_res = i40e_run_xdp_zc(rx_ring, bi);
> +		if (xdp_res == I40E_XDP_EXIT) {
> +			failure = true;
> +			xsk_buff_free(bi);
> +			next_to_clean = (next_to_clean + 1) & count_mask;
> +			break;
> +		}
>   		i40e_handle_xdp_result_zc(rx_ring, bi, rx_desc, &rx_packets,
>   					  &rx_bytes, size, xdp_res);
>   		total_rx_packets += rx_packets;
> @@ -382,7 +389,7 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget)
>   	cleaned_count = (next_to_clean - rx_ring->next_to_use - 1) & count_mask;
>   
>   	if (cleaned_count >= I40E_RX_BUFFER_WRITE)
> -		failure = !i40e_alloc_rx_buffers_zc(rx_ring, cleaned_count);
> +		failure |= !i40e_alloc_rx_buffers_zc(rx_ring, cleaned_count);
>   
>   	i40e_finalize_xdp_rx(rx_ring, xdp_xmit);
>   	i40e_update_rx_stats(rx_ring, total_rx_bytes, total_rx_packets);
>