| 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
| ||
|
Message-Id: <20230807122447.85725-1-huangjie.albert@bytedance.com>
Date: Mon, 7 Aug 2023 20:24:47 +0800
From: Albert Huang <huangjie.albert@...edance.com>
To: unlisted-recipients:; (no To-header on input)
Cc: Albert Huang <huangjie.albert@...edance.com>,
"David S. Miller" <davem@...emloft.net>,
Eric Dumazet <edumazet@...gle.com>,
Jakub Kicinski <kuba@...nel.org>,
Paolo Abeni <pabeni@...hat.com>,
Alexei Starovoitov <ast@...nel.org>,
Daniel Borkmann <daniel@...earbox.net>,
Jesper Dangaard Brouer <hawk@...nel.org>,
John Fastabend <john.fastabend@...il.com>,
netdev@...r.kernel.org (open list:NETWORKING DRIVERS),
linux-kernel@...r.kernel.org (open list),
bpf@...r.kernel.org (open list:XDP (eXpress Data Path))
Subject: [RFC v2 Optimizing veth xsk performance 5/9] veth: use send queue tx napi to xmit xsk tx desc
use send queue tx napi to xmit xsk tx desc
Signed-off-by: Albert Huang <huangjie.albert@...edance.com>
---
drivers/net/veth.c | 230 ++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 229 insertions(+), 1 deletion(-)
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 25faba879505..28b891dd8dc9 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -27,6 +27,8 @@
#include <linux/bpf_trace.h>
#include <linux/net_tstamp.h>
#include <net/page_pool.h>
+#include <net/xdp_sock_drv.h>
+#include <net/xdp.h>
#define DRV_NAME "veth"
#define DRV_VERSION "1.0"
@@ -1061,6 +1063,141 @@ static int veth_poll(struct napi_struct *napi, int budget)
return done;
}
+static struct sk_buff *veth_build_skb(void *head, int headroom, int len,
+ int buflen)
+{
+ struct sk_buff *skb;
+
+ skb = build_skb(head, buflen);
+ if (!skb)
+ return NULL;
+
+ skb_reserve(skb, headroom);
+ skb_put(skb, len);
+
+ return skb;
+}
+
+static int veth_xsk_tx_xmit(struct veth_sq *sq, struct xsk_buff_pool *xsk_pool, int budget)
+{
+ struct veth_priv *priv, *peer_priv;
+ struct net_device *dev, *peer_dev;
+ struct veth_stats stats = {};
+ struct sk_buff *skb = NULL;
+ struct veth_rq *peer_rq;
+ struct xdp_desc desc;
+ int done = 0;
+
+ dev = sq->dev;
+ priv = netdev_priv(dev);
+ peer_dev = priv->peer;
+ peer_priv = netdev_priv(peer_dev);
+
+ /* todo: queue index must set before this */
+ peer_rq = &peer_priv->rq[sq->queue_index];
+
+ /* set xsk wake up flag, to do: where to disable */
+ if (xsk_uses_need_wakeup(xsk_pool))
+ xsk_set_tx_need_wakeup(xsk_pool);
+
+ while (budget-- > 0) {
+ unsigned int truesize = 0;
+ struct page *page;
+ void *vaddr;
+ void *addr;
+
+ if (!xsk_tx_peek_desc(xsk_pool, &desc))
+ break;
+
+ addr = xsk_buff_raw_get_data(xsk_pool, desc.addr);
+
+ /* can not hold all data in a page */
+ truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+ truesize += desc.len + xsk_pool->headroom;
+ if (truesize > PAGE_SIZE) {
+ xsk_tx_completed_addr(xsk_pool, desc.addr);
+ stats.xdp_drops++;
+ break;
+ }
+
+ page = dev_alloc_page();
+ if (!page) {
+ xsk_tx_completed_addr(xsk_pool, desc.addr);
+ stats.xdp_drops++;
+ break;
+ }
+ vaddr = page_to_virt(page);
+
+ memcpy(vaddr + xsk_pool->headroom, addr, desc.len);
+ xsk_tx_completed_addr(xsk_pool, desc.addr);
+
+ skb = veth_build_skb(vaddr, xsk_pool->headroom, desc.len, PAGE_SIZE);
+ if (!skb) {
+ put_page(page);
+ stats.xdp_drops++;
+ break;
+ }
+ skb->protocol = eth_type_trans(skb, peer_dev);
+ napi_gro_receive(&peer_rq->xdp_napi, skb);
+
+ stats.xdp_bytes += desc.len;
+ done++;
+ }
+
+ /* release, move consumer，and wakeup the producer */
+ if (done) {
+ napi_schedule(&peer_rq->xdp_napi);
+ xsk_tx_release(xsk_pool);
+ }
+
+ u64_stats_update_begin(&sq->stats.syncp);
+ sq->stats.vs.xdp_packets += done;
+ sq->stats.vs.xdp_bytes += stats.xdp_bytes;
+ sq->stats.vs.xdp_drops += stats.xdp_drops;
+ u64_stats_update_end(&sq->stats.syncp);
+
+ return done;
+}
+
+static int veth_poll_tx(struct napi_struct *napi, int budget)
+{
+ struct veth_sq *sq = container_of(napi, struct veth_sq, xdp_napi);
+ struct xsk_buff_pool *pool;
+ int done = 0;
+
+ sq->xsk.last_cpu = smp_processor_id();
+
+ /* xmit for tx queue */
+ rcu_read_lock();
+ pool = rcu_dereference(sq->xsk.pool);
+ if (pool)
+ done = veth_xsk_tx_xmit(sq, pool, budget);
+
+ rcu_read_unlock();
+
+ if (done < budget) {
+ /* if done < budget, the tx ring is no buffer */
+ napi_complete_done(napi, done);
+ }
+
+ return done;
+}
+
+static int veth_napi_add_tx(struct net_device *dev)
+{
+ struct veth_priv *priv = netdev_priv(dev);
+ int i;
+
+ for (i = 0; i < dev->real_num_rx_queues; i++) {
+ struct veth_sq *sq = &priv->sq[i];
+
+ netif_napi_add(dev, &sq->xdp_napi, veth_poll_tx);
+ napi_enable(&sq->xdp_napi);
+ }
+
+ return 0;
+}
+
static int veth_create_page_pool(struct veth_rq *rq)
{
struct page_pool_params pp_params = {
@@ -1153,6 +1290,19 @@ static void veth_napi_del_range(struct net_device *dev, int start, int end)
}
}
+static void veth_napi_del_tx(struct net_device *dev)
+{
+ struct veth_priv *priv = netdev_priv(dev);
+ int i;
+
+ for (i = 0; i < dev->real_num_rx_queues; i++) {
+ struct veth_sq *sq = &priv->sq[i];
+
+ napi_disable(&sq->xdp_napi);
+ __netif_napi_del(&sq->xdp_napi);
+ }
+}
+
static void veth_napi_del(struct net_device *dev)
{
veth_napi_del_range(dev, 0, dev->real_num_rx_queues);
@@ -1360,7 +1510,7 @@ static void veth_set_xdp_features(struct net_device *dev)
struct veth_priv *priv_peer = netdev_priv(peer);
xdp_features_t val = NETDEV_XDP_ACT_BASIC |
NETDEV_XDP_ACT_REDIRECT |
- NETDEV_XDP_ACT_RX_SG;
+ NETDEV_XDP_ACT_RX_SG | NETDEV_XDP_ACT_XSK_ZEROCOPY;
if (priv_peer->_xdp_prog || veth_gro_requested(peer))
val |= NETDEV_XDP_ACT_NDO_XMIT |
@@ -1737,11 +1887,89 @@ static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog,
return err;
}
+static int veth_xsk_pool_enable(struct net_device *dev, struct xsk_buff_pool *pool, u16 qid)
+{
+ struct veth_priv *peer_priv;
+ struct veth_priv *priv = netdev_priv(dev);
+ struct net_device *peer_dev = priv->peer;
+ int err = 0;
+
+ if (qid >= dev->real_num_tx_queues)
+ return -EINVAL;
+
+ if (!peer_dev)
+ return -EINVAL;
+
+ /* no dma, so we just skip dma skip in xsk zero copy */
+ pool->dma_check_skip = true;
+
+ peer_priv = netdev_priv(peer_dev);
+
+ /* enable peer tx xdp here, this side
+ * xdp is enable by veth_xdp_set
+ * to do: we need to check whther this side is already enable xdp
+ * maybe it do not have xdp prog
+ */
+ if (!(peer_priv->_xdp_prog) && (!veth_gro_requested(peer_dev))) {
+ /* peer should enable napi*/
+ err = veth_napi_enable(peer_dev);
+ if (err)
+ return err;
+ }
+
+ /* Here is already protected by rtnl_lock, so rcu_assign_pointer
+ * is safe.
+ */
+ rcu_assign_pointer(priv->sq[qid].xsk.pool, pool);
+
+ veth_napi_add_tx(dev);
+
+ return err;
+}
+
+static int veth_xsk_pool_disable(struct net_device *dev, u16 qid)
+{
+ struct veth_priv *peer_priv;
+ struct veth_priv *priv = netdev_priv(dev);
+ struct net_device *peer_dev = priv->peer;
+ int err = 0;
+
+ if (qid >= dev->real_num_tx_queues)
+ return -EINVAL;
+
+ if (!peer_dev)
+ return -EINVAL;
+
+ peer_priv = netdev_priv(peer_dev);
+
+ /* to do: this may be failed */
+ if (!(peer_priv->_xdp_prog) && (!veth_gro_requested(peer_dev))) {
+ /* disable peer napi */
+ veth_napi_del(peer_dev);
+ }
+
+ veth_napi_del_tx(dev);
+
+ rcu_assign_pointer(priv->sq[qid].xsk.pool, NULL);
+ return err;
+}
+
+/* this is for setup xdp */
+static int veth_xsk_pool_setup(struct net_device *dev, struct netdev_bpf *xdp)
+{
+ if (xdp->xsk.pool)
+ return veth_xsk_pool_enable(dev, xdp->xsk.pool, xdp->xsk.queue_id);
+ else
+ return veth_xsk_pool_disable(dev, xdp->xsk.queue_id);
+}
+
static int veth_xdp(struct net_device *dev, struct netdev_bpf *xdp)
{
switch (xdp->command) {
case XDP_SETUP_PROG:
return veth_xdp_set(dev, xdp->prog, xdp->extack);
+ case XDP_SETUP_XSK_POOL:
+ return veth_xsk_pool_setup(dev, xdp);
default:
return -EINVAL;
}
--
2.20.1
Powered by blists - more mailing lists