netdev - Re: [PATCH net-next 1/2] xsk: introduce XDP_GENERIC_XMIT

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]
Message-ID: <aJtucfMw+mXp79FV@boxer>
Date: Tue, 12 Aug 2025 18:40:17 +0200
From: Maciej Fijalkowski <maciej.fijalkowski@...el.com>
To: Jason Xing <kerneljasonxing@...il.com>
CC: <davem@...emloft.net>, <edumazet@...gle.com>, <kuba@...nel.org>,
	<pabeni@...hat.com>, <bjorn@...nel.org>, <magnus.karlsson@...el.com>,
	<jonathan.lemon@...il.com>, <sdf@...ichev.me>, <ast@...nel.org>,
	<daniel@...earbox.net>, <hawk@...nel.org>, <john.fastabend@...il.com>,
	<horms@...nel.org>, <andrew+netdev@...n.ch>, <bpf@...r.kernel.org>,
	<netdev@...r.kernel.org>, Jason Xing <kernelxing@...cent.com>
Subject: Re: [PATCH net-next 1/2] xsk: introduce XDP_GENERIC_XMIT_BATCH
 setsockopt

On Mon, Aug 11, 2025 at 09:12:35PM +0800, Jason Xing wrote:
> From: Jason Xing <kernelxing@...cent.com>
> 
> This patch is to prepare for later batch xmit in generic path. Add a new
> socket option to provide an alternative to achieve a higher overall
> throughput.
> 
> skb_batch will be used to store newly allocated skb at one time in the
> xmit path.

I don't think we need yet another setsockopt. You previously added a knob
for manipulating max tx budget on generic xmit and that should be enough.
I think that we should strive for making the batching approach a default
path in xsk generic xmit.

> 
> Signed-off-by: Jason Xing <kernelxing@...cent.com>
> ---
>  Documentation/networking/af_xdp.rst |  9 ++++++++
>  include/net/xdp_sock.h              |  2 ++
>  include/uapi/linux/if_xdp.h         |  1 +
>  net/xdp/xsk.c                       | 32 +++++++++++++++++++++++++++++
>  tools/include/uapi/linux/if_xdp.h   |  1 +
>  5 files changed, 45 insertions(+)
> 
> diff --git a/Documentation/networking/af_xdp.rst b/Documentation/networking/af_xdp.rst
> index 50d92084a49c..1194bdfaf61e 100644
> --- a/Documentation/networking/af_xdp.rst
> +++ b/Documentation/networking/af_xdp.rst
> @@ -447,6 +447,15 @@ mode to allow application to tune the per-socket maximum iteration for
>  better throughput and less frequency of send syscall.
>  Allowed range is [32, xs->tx->nentries].
>  
> +XDP_GENERIC_XMIT_BATCH
> +----------------------
> +
> +It provides an option that allows application to use batch xmit in the copy
> +mode. Batch process minimizes the number of grabbing/releasing queue lock
> +without redundant actions compared to before to gain the overall performance
> +improvement whereas it might increase the latency of per packet. The maximum
> +value shouldn't be larger than xs->max_tx_budget.
> +
>  XDP_STATISTICS getsockopt
>  -------------------------
>  
> diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
> index ce587a225661..b5a3e37da8db 100644
> --- a/include/net/xdp_sock.h
> +++ b/include/net/xdp_sock.h
> @@ -61,6 +61,7 @@ struct xdp_sock {
>  		XSK_BOUND,
>  		XSK_UNBOUND,
>  	} state;
> +	struct sk_buff **skb_batch;
>  
>  	struct xsk_queue *tx ____cacheline_aligned_in_smp;
>  	struct list_head tx_list;
> @@ -70,6 +71,7 @@ struct xdp_sock {
>  	 * preventing other XSKs from being starved.
>  	 */
>  	u32 tx_budget_spent;
> +	u32 generic_xmit_batch;
>  
>  	/* Statistics */
>  	u64 rx_dropped;
> diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h
> index 23a062781468..44cb72cd328e 100644
> --- a/include/uapi/linux/if_xdp.h
> +++ b/include/uapi/linux/if_xdp.h
> @@ -80,6 +80,7 @@ struct xdp_mmap_offsets {
>  #define XDP_STATISTICS			7
>  #define XDP_OPTIONS			8
>  #define XDP_MAX_TX_SKB_BUDGET		9
> +#define XDP_GENERIC_XMIT_BATCH		10
>  
>  struct xdp_umem_reg {
>  	__u64 addr; /* Start of packet data area */
> diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
> index 9c3acecc14b1..7a149f4ac273 100644
> --- a/net/xdp/xsk.c
> +++ b/net/xdp/xsk.c
> @@ -1122,6 +1122,7 @@ static int xsk_release(struct socket *sock)
>  	xskq_destroy(xs->tx);
>  	xskq_destroy(xs->fq_tmp);
>  	xskq_destroy(xs->cq_tmp);
> +	kfree(xs->skb_batch);
>  
>  	sock_orphan(sk);
>  	sock->sk = NULL;
> @@ -1456,6 +1457,37 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
>  		WRITE_ONCE(xs->max_tx_budget, budget);
>  		return 0;
>  	}
> +	case XDP_GENERIC_XMIT_BATCH:
> +	{
> +		unsigned int batch, batch_alloc_len;
> +		struct sk_buff **new;
> +
> +		if (optlen != sizeof(batch))
> +			return -EINVAL;
> +		if (copy_from_sockptr(&batch, optval, sizeof(batch)))
> +			return -EFAULT;
> +		if (batch > xs->max_tx_budget)
> +			return -EACCES;
> +
> +		mutex_lock(&xs->mutex);
> +		if (!batch) {
> +			kfree(xs->skb_batch);
> +			xs->generic_xmit_batch = 0;
> +			goto out;
> +		}
> +		batch_alloc_len = sizeof(struct sk_buff *) * batch;
> +		new = kmalloc(batch_alloc_len, GFP_KERNEL);
> +		if (!new)
> +			return -ENOMEM;
> +		if (xs->skb_batch)
> +			kfree(xs->skb_batch);
> +
> +		xs->skb_batch = new;
> +		xs->generic_xmit_batch = batch;
> +out:
> +		mutex_unlock(&xs->mutex);
> +		return 0;
> +	}
>  	default:
>  		break;
>  	}
> diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h
> index 23a062781468..44cb72cd328e 100644
> --- a/tools/include/uapi/linux/if_xdp.h
> +++ b/tools/include/uapi/linux/if_xdp.h
> @@ -80,6 +80,7 @@ struct xdp_mmap_offsets {
>  #define XDP_STATISTICS			7
>  #define XDP_OPTIONS			8
>  #define XDP_MAX_TX_SKB_BUDGET		9
> +#define XDP_GENERIC_XMIT_BATCH		10
>  
>  struct xdp_umem_reg {
>  	__u64 addr; /* Start of packet data area */
> -- 
> 2.41.3
>