From: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
To: netdev@vger.kernel.org
Cc: "Michael S. Tsirkin" <mst@redhat.com>,
"Jason Wang" <jasowang@redhat.com>,
"David S. Miller" <davem@davemloft.net>,
"Jakub Kicinski" <kuba@kernel.org>,
"Björn Töpel" <bjorn.topel@intel.com>,
"Magnus Karlsson" <magnus.karlsson@intel.com>,
"Jonathan Lemon" <jonathan.lemon@gmail.com>,
"Alexei Starovoitov" <ast@kernel.org>,
"Daniel Borkmann" <daniel@iogearbox.net>,
"Jesper Dangaard Brouer" <hawk@kernel.org>,
"John Fastabend" <john.fastabend@gmail.com>,
"Andrii Nakryiko" <andrii@kernel.org>,
"Martin KaFai Lau" <kafai@fb.com>,
"Song Liu" <songliubraving@fb.com>, "Yonghong Song" <yhs@fb.com>,
"KP Singh" <kpsingh@kernel.org>,
virtualization@lists.linux-foundation.org, bpf@vger.kernel.org
Subject: [PATCH net-next v2 4/7] virtio-net, xsk: support xsk enable/disable
Date: Sat, 16 Jan 2021 10:59:25 +0800 [thread overview]
Message-ID: <bf265fef497a84ea7411b51e761228ac912d78b9.1610765285.git.xuanzhuo@linux.alibaba.com> (raw)
In-Reply-To: <cover.1610765285.git.xuanzhuo@linux.alibaba.com>
In-Reply-To: <cover.1610765285.git.xuanzhuo@linux.alibaba.com>
When enable, a certain number of struct virtnet_xsk_hdr is allocated to
save the information of each packet and virtio hdr.This number is the
limit of the received module parameters.
When struct virtnet_xsk_hdr is used up, or the sq->vq->num_free of
virtio-net is too small, it will be considered that the device is busy.
* xsk_num_max: the xsk.hdr max num
* xsk_num_percent: the max hdr num be the percent of the virtio ring
size. The real xsk hdr num will the min of xsk_num_max and the percent
of the num of virtio ring
* xsk_budget: the budget for xsk run
Signed-off-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
---
drivers/net/virtio_net.c | 97 ++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 97 insertions(+)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 9013328..a62d456 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -22,10 +22,19 @@
#include <net/route.h>
#include <net/xdp.h>
#include <net/net_failover.h>
+#include <net/xdp_sock_drv.h>
static int napi_weight = NAPI_POLL_WEIGHT;
module_param(napi_weight, int, 0444);
+static int xsk_num_max = 1024;
+static int xsk_num_percent = 80;
+static int xsk_budget = 128;
+
+module_param(xsk_num_max, int, 0644);
+module_param(xsk_num_percent, int, 0644);
+module_param(xsk_budget, int, 0644);
+
static bool csum = true, gso = true, napi_tx = true;
module_param(csum, bool, 0444);
module_param(gso, bool, 0444);
@@ -149,6 +158,15 @@ struct send_queue {
struct virtnet_sq_stats stats;
struct napi_struct napi;
+
+ struct {
+ struct xsk_buff_pool __rcu *pool;
+ struct virtnet_xsk_hdr __rcu *hdr;
+
+ u64 hdr_con;
+ u64 hdr_pro;
+ u64 hdr_n;
+ } xsk;
};
/* Internal representation of a receive virtqueue */
@@ -2540,11 +2558,90 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
return err;
}
+static int virtnet_xsk_pool_enable(struct net_device *dev,
+ struct xsk_buff_pool *pool,
+ u16 qid)
+{
+ struct virtnet_info *vi = netdev_priv(dev);
+ struct send_queue *sq = &vi->sq[qid];
+ struct virtnet_xsk_hdr *hdr;
+ int n, ret = 0;
+
+ if (qid >= dev->real_num_rx_queues || qid >= dev->real_num_tx_queues)
+ return -EINVAL;
+
+ if (qid >= vi->curr_queue_pairs)
+ return -EINVAL;
+
+ rcu_read_lock();
+
+ ret = -EBUSY;
+ if (rcu_dereference(sq->xsk.pool))
+ goto end;
+
+ /* check last xsk wait for hdr been free */
+ if (rcu_dereference(sq->xsk.hdr))
+ goto end;
+
+ n = virtqueue_get_vring_size(sq->vq);
+ n = min(xsk_num_max, n * (xsk_num_percent % 100) / 100);
+
+ ret = -ENOMEM;
+ hdr = kcalloc(n, sizeof(struct virtnet_xsk_hdr), GFP_ATOMIC);
+ if (!hdr)
+ goto end;
+
+ memset(&sq->xsk, 0, sizeof(sq->xsk));
+
+ sq->xsk.hdr_pro = n;
+ sq->xsk.hdr_n = n;
+
+ rcu_assign_pointer(sq->xsk.pool, pool);
+ rcu_assign_pointer(sq->xsk.hdr, hdr);
+
+ ret = 0;
+end:
+ rcu_read_unlock();
+
+ return ret;
+}
+
+static int virtnet_xsk_pool_disable(struct net_device *dev, u16 qid)
+{
+ struct virtnet_info *vi = netdev_priv(dev);
+ struct send_queue *sq = &vi->sq[qid];
+ struct virtnet_xsk_hdr *hdr = NULL;
+
+ if (qid >= dev->real_num_rx_queues || qid >= dev->real_num_tx_queues)
+ return -EINVAL;
+
+ if (qid >= vi->curr_queue_pairs)
+ return -EINVAL;
+
+ rcu_assign_pointer(sq->xsk.pool, NULL);
+
+ if (sq->xsk.hdr_pro - sq->xsk.hdr_con == sq->xsk.hdr_n)
+ hdr = rcu_replace_pointer(sq->xsk.hdr, hdr, true);
+
+ synchronize_rcu(); /* Sync with the XSK wakeup and with NAPI. */
+
+ kfree(hdr);
+
+ return 0;
+}
+
static int virtnet_xdp(struct net_device *dev, struct netdev_bpf *xdp)
{
switch (xdp->command) {
case XDP_SETUP_PROG:
return virtnet_xdp_set(dev, xdp->prog, xdp->extack);
+ case XDP_SETUP_XSK_POOL:
+ xdp->xsk.need_dma = false;
+ if (xdp->xsk.pool)
+ return virtnet_xsk_pool_enable(dev, xdp->xsk.pool,
+ xdp->xsk.queue_id);
+ else
+ return virtnet_xsk_pool_disable(dev, xdp->xsk.queue_id);
default:
return -EINVAL;
}
--
1.8.3.1
next prev parent reply other threads:[~2021-01-16 3:01 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-01-05 9:11 [PATCH netdev 0/5] virtio-net support xdp socket zero copy xmit Xuan Zhuo
2021-01-05 9:11 ` [PATCH netdev 1/5] xsk: support get page for drv Xuan Zhuo
2021-01-05 9:11 ` [PATCH netdev 2/5] virtio-net: support XDP_TX when not more queues Xuan Zhuo
2021-01-05 9:11 ` [PATCH netdev 3/5] virtio-net, xsk: distinguish XDP_TX and XSK XMIT ctx Xuan Zhuo
2021-01-05 9:11 ` [PATCH netdev 4/5] xsk, virtio-net: prepare for support xsk Xuan Zhuo
2021-01-05 9:11 ` [PATCH netdev 5/5] virtio-net, xsk: virtio-net support xsk zero copy tx Xuan Zhuo
2021-01-05 13:21 ` Michael S. Tsirkin
2021-01-05 9:32 ` [PATCH netdev 0/5] virtio-net support xdp socket zero copy xmit Jason Wang
2021-01-05 12:25 ` Michael S. Tsirkin
2021-01-16 2:59 ` [PATCH net-next v2 0/7] " Xuan Zhuo
2021-01-16 2:59 ` [PATCH net-next v2 1/7] xsk: support get page for drv Xuan Zhuo
2021-01-16 2:59 ` [PATCH net-next v2 2/7] virtio-net, xsk: distinguish XDP_TX and XSK XMIT ctx Xuan Zhuo
2021-01-18 6:45 ` Jason Wang
2021-01-16 2:59 ` [PATCH net-next v2 3/7] xsk, virtio-net: prepare for support xsk zerocopy xmit Xuan Zhuo
2021-01-16 2:59 ` Xuan Zhuo [this message]
2021-01-16 2:59 ` [PATCH net-next v2 5/7] virtio-net, xsk: realize the function of xsk packet sending Xuan Zhuo
2021-01-16 4:47 ` Jakub Kicinski
2021-01-18 9:10 ` Jason Wang
2021-01-18 12:27 ` Michael S. Tsirkin
2021-01-16 2:59 ` [PATCH net-next v2 6/7] virtio-net, xsk: implement xsk wakeup callback Xuan Zhuo
2021-01-19 4:50 ` Jason Wang
2021-01-16 2:59 ` [PATCH net-next v2 7/7] virtio-net, xsk: set xsk completed when packet sent done Xuan Zhuo
2021-01-18 6:28 ` [PATCH net-next v2 0/7] virtio-net support xdp socket zero copy xmit Jason Wang
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=bf265fef497a84ea7411b51e761228ac912d78b9.1610765285.git.xuanzhuo@linux.alibaba.com \
--to=xuanzhuo@linux.alibaba.com \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bjorn.topel@intel.com \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=hawk@kernel.org \
--cc=jasowang@redhat.com \
--cc=john.fastabend@gmail.com \
--cc=jonathan.lemon@gmail.com \
--cc=kafai@fb.com \
--cc=kpsingh@kernel.org \
--cc=kuba@kernel.org \
--cc=magnus.karlsson@intel.com \
--cc=mst@redhat.com \
--cc=netdev@vger.kernel.org \
--cc=songliubraving@fb.com \
--cc=virtualization@lists.linux-foundation.org \
--cc=yhs@fb.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).