netdev - Re: [patch net-next] virtio_net: add support for Byte Queue Limits

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: <20240509084050-mutt-send-email-mst@kernel.org>
Date: Thu, 9 May 2024 08:41:39 -0400
From: "Michael S. Tsirkin" <mst@...hat.com>
To: Jiri Pirko <jiri@...nulli.us>
Cc: netdev@...r.kernel.org, davem@...emloft.net, edumazet@...gle.com,
	kuba@...nel.org, pabeni@...hat.com, jasowang@...hat.com,
	xuanzhuo@...ux.alibaba.com, virtualization@...ts.linux.dev,
	ast@...nel.org, daniel@...earbox.net, hawk@...nel.org,
	john.fastabend@...il.com
Subject: Re: [patch net-next] virtio_net: add support for Byte Queue Limits

On Thu, May 09, 2024 at 01:46:15PM +0200, Jiri Pirko wrote:
> From: Jiri Pirko <jiri@...dia.com>
> 
> Add support for Byte Queue Limits (BQL).
> 
> Signed-off-by: Jiri Pirko <jiri@...dia.com>

Can we get more detail on the benefits you observe etc?
Thanks!

> ---
>  drivers/net/virtio_net.c | 33 ++++++++++++++++++++-------------
>  1 file changed, 20 insertions(+), 13 deletions(-)
> 
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index 218a446c4c27..c53d6dc6d332 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -84,7 +84,9 @@ struct virtnet_stat_desc {
>  
>  struct virtnet_sq_free_stats {
>  	u64 packets;
> +	u64 xdp_packets;
>  	u64 bytes;
> +	u64 xdp_bytes;
>  };
>  
>  struct virtnet_sq_stats {
> @@ -512,19 +514,19 @@ static void __free_old_xmit(struct send_queue *sq, bool in_napi,
>  	void *ptr;
>  
>  	while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) {
> -		++stats->packets;
> -
>  		if (!is_xdp_frame(ptr)) {
>  			struct sk_buff *skb = ptr;
>  
>  			pr_debug("Sent skb %p\n", skb);
>  
> +			stats->packets++;
>  			stats->bytes += skb->len;
>  			napi_consume_skb(skb, in_napi);
>  		} else {
>  			struct xdp_frame *frame = ptr_to_xdp(ptr);
>  
> -			stats->bytes += xdp_get_frame_len(frame);
> +			stats->xdp_packets++;
> +			stats->xdp_bytes += xdp_get_frame_len(frame);
>  			xdp_return_frame(frame);
>  		}
>  	}
> @@ -965,7 +967,8 @@ static void virtnet_rq_unmap_free_buf(struct virtqueue *vq, void *buf)
>  	virtnet_rq_free_buf(vi, rq, buf);
>  }
>  
> -static void free_old_xmit(struct send_queue *sq, bool in_napi)
> +static void free_old_xmit(struct send_queue *sq, struct netdev_queue *txq,
> +			  bool in_napi)
>  {
>  	struct virtnet_sq_free_stats stats = {0};
>  
> @@ -974,9 +977,11 @@ static void free_old_xmit(struct send_queue *sq, bool in_napi)
>  	/* Avoid overhead when no packets have been processed
>  	 * happens when called speculatively from start_xmit.
>  	 */
> -	if (!stats.packets)
> +	if (!stats.packets && !stats.xdp_packets)
>  		return;
>  
> +	netdev_tx_completed_queue(txq, stats.packets, stats.bytes);
> +
>  	u64_stats_update_begin(&sq->stats.syncp);
>  	u64_stats_add(&sq->stats.bytes, stats.bytes);
>  	u64_stats_add(&sq->stats.packets, stats.packets);
> @@ -1013,13 +1018,15 @@ static void check_sq_full_and_disable(struct virtnet_info *vi,
>  	 * early means 16 slots are typically wasted.
>  	 */
>  	if (sq->vq->num_free < 2+MAX_SKB_FRAGS) {
> -		netif_stop_subqueue(dev, qnum);
> +		struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum);
> +
> +		netif_tx_stop_queue(txq);
>  		if (use_napi) {
>  			if (unlikely(!virtqueue_enable_cb_delayed(sq->vq)))
>  				virtqueue_napi_schedule(&sq->napi, sq->vq);
>  		} else if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) {
>  			/* More just got used, free them then recheck. */
> -			free_old_xmit(sq, false);
> +			free_old_xmit(sq, txq, false);
>  			if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) {
>  				netif_start_subqueue(dev, qnum);
>  				virtqueue_disable_cb(sq->vq);
> @@ -2319,7 +2326,7 @@ static void virtnet_poll_cleantx(struct receive_queue *rq)
>  
>  		do {
>  			virtqueue_disable_cb(sq->vq);
> -			free_old_xmit(sq, true);
> +			free_old_xmit(sq, txq, true);
>  		} while (unlikely(!virtqueue_enable_cb_delayed(sq->vq)));
>  
>  		if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS)
> @@ -2471,7 +2478,7 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget)
>  	txq = netdev_get_tx_queue(vi->dev, index);
>  	__netif_tx_lock(txq, raw_smp_processor_id());
>  	virtqueue_disable_cb(sq->vq);
> -	free_old_xmit(sq, true);
> +	free_old_xmit(sq, txq, true);
>  
>  	if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS)
>  		netif_tx_wake_queue(txq);
> @@ -2553,7 +2560,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
>  	struct send_queue *sq = &vi->sq[qnum];
>  	int err;
>  	struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum);
> -	bool kick = !netdev_xmit_more();
> +	bool xmit_more = netdev_xmit_more();
>  	bool use_napi = sq->napi.weight;
>  
>  	/* Free up any pending old buffers before queueing new ones. */
> @@ -2561,9 +2568,9 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
>  		if (use_napi)
>  			virtqueue_disable_cb(sq->vq);
>  
> -		free_old_xmit(sq, false);
> +		free_old_xmit(sq, txq, false);
>  
> -	} while (use_napi && kick &&
> +	} while (use_napi && !xmit_more &&
>  	       unlikely(!virtqueue_enable_cb_delayed(sq->vq)));
>  
>  	/* timestamp packet in software */
> @@ -2592,7 +2599,7 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
>  
>  	check_sq_full_and_disable(vi, dev, sq);
>  
> -	if (kick || netif_xmit_stopped(txq)) {
> +	if (__netdev_tx_sent_queue(txq, skb->len, xmit_more)) {
>  		if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) {
>  			u64_stats_update_begin(&sq->stats.syncp);
>  			u64_stats_inc(&sq->stats.kicks);
> -- 
> 2.44.0