From 1ffcbc8537d0bc32aaca7000cb9c904ec4b6300f Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Tue, 17 Apr 2018 16:45:47 +0200 Subject: tun: convert to use generic xdp_frame and xdp_return_frame API The tuntap driver invented it's own driver specific way of queuing XDP packets, by storing the xdp_buff information in the top of the XDP frame data. Convert it over to use the more generic xdp_frame structure. The main problem with the in-driver method is that the xdp_rxq_info pointer cannot be trused/used when dequeueing the frame. V3: Remove check based on feedback from Jason Signed-off-by: Jesper Dangaard Brouer Signed-off-by: David S. Miller --- drivers/vhost/net.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'drivers/vhost') diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 986058a57917..bbf38befefb2 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -32,6 +32,7 @@ #include #include +#include #include "vhost.h" @@ -181,10 +182,10 @@ static void vhost_net_buf_unproduce(struct vhost_net_virtqueue *nvq) static int vhost_net_buf_peek_len(void *ptr) { - if (tun_is_xdp_buff(ptr)) { - struct xdp_buff *xdp = tun_ptr_to_xdp(ptr); + if (tun_is_xdp_frame(ptr)) { + struct xdp_frame *xdpf = tun_ptr_to_xdp(ptr); - return xdp->data_end - xdp->data; + return xdpf->len; } return __skb_array_len_with_tag(ptr); -- cgit v1.2.3 From db688c24eada63b1efe6d0d7d835e5c3bdd71fd3 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 24 Apr 2018 10:34:36 +0200 Subject: vhost_net: use packet weight for rx handler, too Similar to commit a2ac99905f1e ("vhost-net: set packet weight of tx polling to 2 * vq size"), we need a packet-based limit for handler_rx, too - elsewhere, under rx flood with small packets, tx can be delayed for a very long time, even without busypolling. The pkt limit applied to handle_rx must be the same applied by handle_tx, or we will get unfair scheduling between rx and tx. Tying such limit to the queue length makes it less effective for large queue length values and can introduce large process scheduler latencies, so a constant valued is used - likewise the existing bytes limit. The selected limit has been validated with PVP[1] performance test with different queue sizes: queue size 256 512 1024 baseline 366 354 362 weight 128 715 723 670 weight 256 740 745 733 weight 512 600 460 583 weight 1024 423 427 418 A packet weight of 256 gives peek performances in under all the tested scenarios. No measurable regression in unidirectional performance tests has been detected. [1] https://developers.redhat.com/blog/2017/06/05/measuring-and-comparing-open-vswitch-performance/ Signed-off-by: Paolo Abeni Acked-by: Jason Wang Signed-off-by: David S. Miller --- drivers/vhost/net.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'drivers/vhost') diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index bbf38befefb2..c4b49fca4871 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -46,8 +46,10 @@ MODULE_PARM_DESC(experimental_zcopytx, "Enable Zero Copy TX;" #define VHOST_NET_WEIGHT 0x80000 /* Max number of packets transferred before requeueing the job. - * Using this limit prevents one virtqueue from starving rx. */ -#define VHOST_NET_PKT_WEIGHT(vq) ((vq)->num * 2) + * Using this limit prevents one virtqueue from starving others with small + * pkts. + */ +#define VHOST_NET_PKT_WEIGHT 256 /* MAX number of TX used buffers for outstanding zerocopy */ #define VHOST_MAX_PEND 128 @@ -587,7 +589,7 @@ static void handle_tx(struct vhost_net *net) vhost_zerocopy_signal_used(net, vq); vhost_net_tx_packet(net); if (unlikely(total_len >= VHOST_NET_WEIGHT) || - unlikely(++sent_pkts >= VHOST_NET_PKT_WEIGHT(vq))) { + unlikely(++sent_pkts >= VHOST_NET_PKT_WEIGHT)) { vhost_poll_queue(&vq->poll); break; } @@ -769,6 +771,7 @@ static void handle_rx(struct vhost_net *net) struct socket *sock; struct iov_iter fixup; __virtio16 num_buffers; + int recv_pkts = 0; mutex_lock_nested(&vq->mutex, 0); sock = vq->private_data; @@ -872,7 +875,8 @@ static void handle_rx(struct vhost_net *net) if (unlikely(vq_log)) vhost_log_write(vq, vq_log, log, vhost_len); total_len += vhost_len; - if (unlikely(total_len >= VHOST_NET_WEIGHT)) { + if (unlikely(total_len >= VHOST_NET_WEIGHT) || + unlikely(++recv_pkts >= VHOST_NET_PKT_WEIGHT)) { vhost_poll_queue(&vq->poll); goto out; } -- cgit v1.2.3