1 files changed, 191 insertions, 71 deletions

diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index 42f247cbdcee..0178219f0db5 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -25,9 +25,11 @@
 #include <net/page_pool/helpers.h>
 #include <net/netlink.h>
 #include <net/net_shaper.h>
+#include <net/netdev_lock.h>
 #include <net/pkt_cls.h>
 #include <net/rtnetlink.h>
 #include <net/udp_tunnel.h>
+#include <net/busy_poll.h>
 
 #include "netdevsim.h"
 
@@ -35,7 +37,53 @@ MODULE_IMPORT_NS("NETDEV_INTERNAL");
 
 #define NSIM_RING_SIZE		256
 
-static int nsim_napi_rx(struct nsim_rq *rq, struct sk_buff *skb)
+static void nsim_start_peer_tx_queue(struct net_device *dev, struct nsim_rq *rq)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+	struct net_device *peer_dev;
+	struct netdevsim *peer_ns;
+	struct netdev_queue *txq;
+	u16 idx;
+
+	idx = rq->napi.index;
+	rcu_read_lock();
+	peer_ns = rcu_dereference(ns->peer);
+	if (!peer_ns)
+		goto out;
+
+	/* TX device */
+	peer_dev = peer_ns->netdev;
+	if (dev->real_num_tx_queues != peer_dev->num_rx_queues)
+		goto out;
+
+	txq = netdev_get_tx_queue(peer_dev, idx);
+	if (!netif_tx_queue_stopped(txq))
+		goto out;
+
+	netif_tx_wake_queue(txq);
+out:
+	rcu_read_unlock();
+}
+
+static void nsim_stop_tx_queue(struct net_device *tx_dev,
+			       struct net_device *rx_dev,
+			       struct nsim_rq *rq,
+			       u16 idx)
+{
+	/* If different queues size, do not stop, since it is not
+	 * easy to find which TX queue is mapped here
+	 */
+	if (rx_dev->real_num_tx_queues != tx_dev->num_rx_queues)
+		return;
+
+	/* rq is the queue on the receive side */
+	netif_subqueue_try_stop(tx_dev, idx,
+				NSIM_RING_SIZE - skb_queue_len(&rq->skb_queue),
+				NSIM_RING_SIZE / 2);
+}
+
+static int nsim_napi_rx(struct net_device *tx_dev, struct net_device *rx_dev,
+			struct nsim_rq *rq, struct sk_buff *skb)
 {
 	if (skb_queue_len(&rq->skb_queue) > NSIM_RING_SIZE) {
 		dev_kfree_skb_any(skb);
@@ -43,13 +91,22 @@ static int nsim_napi_rx(struct nsim_rq *rq, struct sk_buff *skb)
 	}
 
 	skb_queue_tail(&rq->skb_queue, skb);
+
+	/* Stop the peer TX queue avoiding dropping packets later */
+	if (skb_queue_len(&rq->skb_queue) >= NSIM_RING_SIZE)
+		nsim_stop_tx_queue(tx_dev, rx_dev, rq,
+				   skb_get_queue_mapping(skb));
+
 	return NET_RX_SUCCESS;
 }
 
-static int nsim_forward_skb(struct net_device *dev, struct sk_buff *skb,
+static int nsim_forward_skb(struct net_device *tx_dev,
+			    struct net_device *rx_dev,
+			    struct sk_buff *skb,
 			    struct nsim_rq *rq)
 {
-	return __dev_forward_skb(dev, skb) ?: nsim_napi_rx(rq, skb);
+	return __dev_forward_skb(rx_dev, skb) ?:
+		nsim_napi_rx(tx_dev, rx_dev, rq, skb);
 }
 
 static netdev_tx_t nsim_start_xmit(struct sk_buff *skb, struct net_device *dev)
@@ -84,25 +141,21 @@ static netdev_tx_t nsim_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		skb_linearize(skb);
 
 	skb_tx_timestamp(skb);
-	if (unlikely(nsim_forward_skb(peer_dev, skb, rq) == NET_RX_DROP))
+	if (unlikely(nsim_forward_skb(dev, peer_dev, skb, rq) == NET_RX_DROP))
 		goto out_drop_cnt;
 
-	napi_schedule(&rq->napi);
+	if (!hrtimer_active(&rq->napi_timer))
+		hrtimer_start(&rq->napi_timer, us_to_ktime(5), HRTIMER_MODE_REL);
 
 	rcu_read_unlock();
-	u64_stats_update_begin(&ns->syncp);
-	ns->tx_packets++;
-	ns->tx_bytes += len;
-	u64_stats_update_end(&ns->syncp);
+	dev_dstats_tx_add(dev, len);
 	return NETDEV_TX_OK;
 
 out_drop_free:
 	dev_kfree_skb(skb);
 out_drop_cnt:
 	rcu_read_unlock();
-	u64_stats_update_begin(&ns->syncp);
-	ns->tx_dropped++;
-	u64_stats_update_end(&ns->syncp);
+	dev_dstats_tx_dropped(dev);
 	return NETDEV_TX_OK;
 }
 
@@ -114,7 +167,8 @@ static int nsim_change_mtu(struct net_device *dev, int new_mtu)
 {
 	struct netdevsim *ns = netdev_priv(dev);
 
-	if (ns->xdp.prog && new_mtu > NSIM_XDP_MAX_MTU)
+	if (ns->xdp.prog && !ns->xdp.prog->aux->xdp_has_frags &&
+	    new_mtu > NSIM_XDP_MAX_MTU)
 		return -EBUSY;
 
 	WRITE_ONCE(dev->mtu, new_mtu);
@@ -122,20 +176,6 @@ static int nsim_change_mtu(struct net_device *dev, int new_mtu)
 	return 0;
 }
 
-static void
-nsim_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
-{
-	struct netdevsim *ns = netdev_priv(dev);
-	unsigned int start;
-
-	do {
-		start = u64_stats_fetch_begin(&ns->syncp);
-		stats->tx_bytes = ns->tx_bytes;
-		stats->tx_packets = ns->tx_packets;
-		stats->tx_dropped = ns->tx_dropped;
-	} while (u64_stats_fetch_retry(&ns->syncp, start));
-}
-
 static int
 nsim_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv)
 {
@@ -346,17 +386,46 @@ static int nsim_get_iflink(const struct net_device *dev)
 
 static int nsim_rcv(struct nsim_rq *rq, int budget)
 {
+	struct net_device *dev = rq->napi.dev;
+	struct bpf_prog *xdp_prog;
+	struct netdevsim *ns;
 	struct sk_buff *skb;
-	int i;
+	unsigned int skblen;
+	int i, ret;
+
+	ns = netdev_priv(dev);
+	xdp_prog = READ_ONCE(ns->xdp.prog);
 
 	for (i = 0; i < budget; i++) {
 		if (skb_queue_empty(&rq->skb_queue))
 			break;
 
 		skb = skb_dequeue(&rq->skb_queue);
-		netif_receive_skb(skb);
+
+		if (xdp_prog) {
+			/* skb might be freed directly by XDP, save the len */
+			skblen = skb->len;
+
+			if (skb->ip_summed == CHECKSUM_PARTIAL)
+				skb_checksum_help(skb);
+			ret = do_xdp_generic(xdp_prog, &skb);
+			if (ret != XDP_PASS) {
+				dev_dstats_rx_add(dev, skblen);
+				continue;
+			}
+		}
+
+		/* skb might be discard at netif_receive_skb, save the len */
+		skblen = skb->len;
+		skb_mark_napi_id(skb, &rq->napi);
+		ret = netif_receive_skb(skb);
+		if (ret == NET_RX_SUCCESS)
+			dev_dstats_rx_add(dev, skblen);
+		else
+			dev_dstats_rx_dropped(dev);
 	}
 
+	nsim_start_peer_tx_queue(dev, rq);
 	return i;
 }
 
@@ -366,7 +435,8 @@ static int nsim_poll(struct napi_struct *napi, int budget)
 	int done;
 
 	done = nsim_rcv(rq, budget);
-	napi_complete(napi);
+	if (done < budget)
+		napi_complete_done(napi, done);
 
 	return done;
 }
@@ -401,7 +471,7 @@ static int nsim_init_napi(struct netdevsim *ns)
 	for (i = 0; i < dev->num_rx_queues; i++) {
 		rq = ns->rq[i];
 
-		netif_napi_add_config(dev, &rq->napi, nsim_poll, i);
+		netif_napi_add_config_locked(dev, &rq->napi, nsim_poll, i);
 	}
 
 	for (i = 0; i < dev->num_rx_queues; i++) {
@@ -421,11 +491,27 @@ err_pp_destroy:
 	}
 
 	for (i = 0; i < dev->num_rx_queues; i++)
-		__netif_napi_del(&ns->rq[i]->napi);
+		__netif_napi_del_locked(&ns->rq[i]->napi);
 
 	return err;
 }
 
+static enum hrtimer_restart nsim_napi_schedule(struct hrtimer *timer)
+{
+	struct nsim_rq *rq;
+
+	rq = container_of(timer, struct nsim_rq, napi_timer);
+	napi_schedule(&rq->napi);
+
+	return HRTIMER_NORESTART;
+}
+
+static void nsim_rq_timer_init(struct nsim_rq *rq)
+{
+	hrtimer_setup(&rq->napi_timer, nsim_napi_schedule, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
+}
+
 static void nsim_enable_napi(struct netdevsim *ns)
 {
 	struct net_device *dev = ns->netdev;
@@ -435,7 +521,7 @@ static void nsim_enable_napi(struct netdevsim *ns)
 		struct nsim_rq *rq = ns->rq[i];
 
 		netif_queue_set_napi(dev, i, NETDEV_QUEUE_TYPE_RX, &rq->napi);
-		napi_enable(&rq->napi);
+		napi_enable_locked(&rq->napi);
 	}
 }
 
@@ -444,6 +530,8 @@ static int nsim_open(struct net_device *dev)
 	struct netdevsim *ns = netdev_priv(dev);
 	int err;
 
+	netdev_assert_locked(dev);
+
 	err = nsim_init_napi(ns);
 	if (err)
 		return err;
@@ -461,8 +549,8 @@ static void nsim_del_napi(struct netdevsim *ns)
 	for (i = 0; i < dev->num_rx_queues; i++) {
 		struct nsim_rq *rq = ns->rq[i];
 
-		napi_disable(&rq->napi);
-		__netif_napi_del(&rq->napi);
+		napi_disable_locked(&rq->napi);
+		__netif_napi_del_locked(&rq->napi);
 	}
 	synchronize_net();
 
@@ -477,6 +565,8 @@ static int nsim_stop(struct net_device *dev)
 	struct netdevsim *ns = netdev_priv(dev);
 	struct netdevsim *peer;
 
+	netdev_assert_locked(dev);
+
 	netif_carrier_off(dev);
 	peer = rtnl_dereference(ns->peer);
 	if (peer)
@@ -530,7 +620,6 @@ static const struct net_device_ops nsim_netdev_ops = {
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_change_mtu		= nsim_change_mtu,
-	.ndo_get_stats64	= nsim_get_stats64,
 	.ndo_set_vf_mac		= nsim_set_vf_mac,
 	.ndo_set_vf_vlan	= nsim_set_vf_vlan,
 	.ndo_set_vf_rate	= nsim_set_vf_rate,
@@ -554,7 +643,6 @@ static const struct net_device_ops nsim_vf_netdev_ops = {
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_change_mtu		= nsim_change_mtu,
-	.ndo_get_stats64	= nsim_get_stats64,
 	.ndo_setup_tc		= nsim_setup_tc,
 	.ndo_set_features	= nsim_set_features,
 };
@@ -568,7 +656,7 @@ static void nsim_get_queue_stats_rx(struct net_device *dev, int idx,
 	struct rtnl_link_stats64 rtstats = {};
 
 	if (!idx)
-		nsim_get_stats64(dev, &rtstats);
+		dev_get_stats(dev, &rtstats);
 
 	stats->packets = rtstats.rx_packets - !!rtstats.rx_packets;
 	stats->bytes = rtstats.rx_bytes;
@@ -580,7 +668,7 @@ static void nsim_get_queue_stats_tx(struct net_device *dev, int idx,
 	struct rtnl_link_stats64 rtstats = {};
 
 	if (!idx)
-		nsim_get_stats64(dev, &rtstats);
+		dev_get_stats(dev, &rtstats);
 
 	stats->packets = rtstats.tx_packets - !!rtstats.tx_packets;
 	stats->bytes = rtstats.tx_bytes;
@@ -592,7 +680,7 @@ static void nsim_get_base_stats(struct net_device *dev,
 {
 	struct rtnl_link_stats64 rtstats = {};
 
-	nsim_get_stats64(dev, &rtstats);
+	dev_get_stats(dev, &rtstats);
 
 	rx->packets = !!rtstats.rx_packets;
 	rx->bytes = 0;
@@ -615,11 +703,20 @@ static struct nsim_rq *nsim_queue_alloc(void)
 		return NULL;
 
 	skb_queue_head_init(&rq->skb_queue);
+	nsim_rq_timer_init(rq);
 	return rq;
 }
 
-static void nsim_queue_free(struct nsim_rq *rq)
+static void nsim_queue_free(struct net_device *dev, struct nsim_rq *rq)
 {
+	hrtimer_cancel(&rq->napi_timer);
+
+	if (rq->skb_queue.qlen) {
+		local_bh_disable();
+		dev_dstats_rx_dropped_add(dev, rq->skb_queue.qlen);
+		local_bh_enable();
+	}
+
 	skb_queue_purge_reason(&rq->skb_queue, SKB_DROP_REASON_QUEUE_PURGE);
 	kfree(rq);
 }
@@ -645,8 +742,11 @@ nsim_queue_mem_alloc(struct net_device *dev, void *per_queue_mem, int idx)
 	if (ns->rq_reset_mode > 3)
 		return -EINVAL;
 
-	if (ns->rq_reset_mode == 1)
+	if (ns->rq_reset_mode == 1) {
+		if (!netif_running(ns->netdev))
+			return -ENETDOWN;
 		return nsim_create_page_pool(&qmem->pp, &ns->rq[idx]->napi);
+	}
 
 	qmem->rq = nsim_queue_alloc();
 	if (!qmem->rq)
@@ -657,12 +757,13 @@ nsim_queue_mem_alloc(struct net_device *dev, void *per_queue_mem, int idx)
 		goto err_free;
 
 	if (!ns->rq_reset_mode)
-		netif_napi_add_config(dev, &qmem->rq->napi, nsim_poll, idx);
+		netif_napi_add_config_locked(dev, &qmem->rq->napi, nsim_poll,
+					     idx);
 
 	return 0;
 
 err_free:
-	nsim_queue_free(qmem->rq);
+	nsim_queue_free(dev, qmem->rq);
 	return err;
 }
 
@@ -674,9 +775,9 @@ static void nsim_queue_mem_free(struct net_device *dev, void *per_queue_mem)
 	page_pool_destroy(qmem->pp);
 	if (qmem->rq) {
 		if (!ns->rq_reset_mode)
-			netif_napi_del(&qmem->rq->napi);
+			netif_napi_del_locked(&qmem->rq->napi);
 		page_pool_destroy(qmem->rq->page_pool);
-		nsim_queue_free(qmem->rq);
+		nsim_queue_free(dev, qmem->rq);
 	}
 }
 
@@ -686,9 +787,11 @@ nsim_queue_start(struct net_device *dev, void *per_queue_mem, int idx)
 	struct nsim_queue_mem *qmem = per_queue_mem;
 	struct netdevsim *ns = netdev_priv(dev);
 
+	netdev_assert_locked(dev);
+
 	if (ns->rq_reset_mode == 1) {
 		ns->rq[idx]->page_pool = qmem->pp;
-		napi_enable(&ns->rq[idx]->napi);
+		napi_enable_locked(&ns->rq[idx]->napi);
 		return 0;
 	}
 
@@ -696,15 +799,17 @@ nsim_queue_start(struct net_device *dev, void *per_queue_mem, int idx)
 	 * here we want to test various call orders.
 	 */
 	if (ns->rq_reset_mode == 2) {
-		netif_napi_del(&ns->rq[idx]->napi);
-		netif_napi_add_config(dev, &qmem->rq->napi, nsim_poll, idx);
+		netif_napi_del_locked(&ns->rq[idx]->napi);
+		netif_napi_add_config_locked(dev, &qmem->rq->napi, nsim_poll,
+					     idx);
 	} else if (ns->rq_reset_mode == 3) {
-		netif_napi_add_config(dev, &qmem->rq->napi, nsim_poll, idx);
-		netif_napi_del(&ns->rq[idx]->napi);
+		netif_napi_add_config_locked(dev, &qmem->rq->napi, nsim_poll,
+					     idx);
+		netif_napi_del_locked(&ns->rq[idx]->napi);
 	}
 
 	ns->rq[idx] = qmem->rq;
-	napi_enable(&ns->rq[idx]->napi);
+	napi_enable_locked(&ns->rq[idx]->napi);
 
 	return 0;
 }
@@ -714,7 +819,9 @@ static int nsim_queue_stop(struct net_device *dev, void *per_queue_mem, int idx)
 	struct nsim_queue_mem *qmem = per_queue_mem;
 	struct netdevsim *ns = netdev_priv(dev);
 
-	napi_disable(&ns->rq[idx]->napi);
+	netdev_assert_locked(dev);
+
+	napi_disable_locked(&ns->rq[idx]->napi);
 
 	if (ns->rq_reset_mode == 1) {
 		qmem->pp = ns->rq[idx]->page_pool;
@@ -753,12 +860,7 @@ nsim_qreset_write(struct file *file, const char __user *data,
 	if (ret != 2)
 		return -EINVAL;
 
-	rtnl_lock();
-	if (!netif_running(ns->netdev)) {
-		ret = -ENETDOWN;
-		goto exit_unlock;
-	}
-
+	netdev_lock(ns->netdev);
 	if (queue >= ns->netdev->real_num_rx_queues) {
 		ret = -EINVAL;
 		goto exit_unlock;
@@ -772,7 +874,7 @@ nsim_qreset_write(struct file *file, const char __user *data,
 
 	ret = count;
 exit_unlock:
-	rtnl_unlock();
+	netdev_unlock(ns->netdev);
 	return ret;
 }
 
@@ -819,7 +921,8 @@ nsim_pp_hold_write(struct file *file, const char __user *data,
 		if (!ns->page)
 			ret = -ENOMEM;
 	} else {
-		page_pool_put_full_page(ns->page->pp, ns->page, false);
+		page_pool_put_full_page(pp_page_to_nmdesc(ns->page)->pp,
+					ns->page, false);
 		ns->page = NULL;
 	}
 
@@ -841,22 +944,23 @@ static void nsim_setup(struct net_device *dev)
 	ether_setup(dev);
 	eth_hw_addr_random(dev);
 
-	dev->tx_queue_len = 0;
 	dev->flags &= ~IFF_MULTICAST;
-	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE |
-			   IFF_NO_QUEUE;
+	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 	dev->features |= NETIF_F_HIGHDMA |
 			 NETIF_F_SG |
 			 NETIF_F_FRAGLIST |
 			 NETIF_F_HW_CSUM |
+			 NETIF_F_LRO |
 			 NETIF_F_TSO;
 	dev->hw_features |= NETIF_F_HW_TC |
 			    NETIF_F_SG |
 			    NETIF_F_FRAGLIST |
 			    NETIF_F_HW_CSUM |
+			    NETIF_F_LRO |
 			    NETIF_F_TSO;
+	dev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS;
 	dev->max_mtu = ETH_MAX_MTU;
-	dev->xdp_features = NETDEV_XDP_ACT_HW_OFFLOAD;
+	dev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_HW_OFFLOAD;
 }
 
 static int nsim_queue_init(struct netdevsim *ns)
@@ -890,7 +994,7 @@ static void nsim_queue_uninit(struct netdevsim *ns)
 	int i;
 
 	for (i = 0; i < dev->num_rx_queues; i++)
-		nsim_queue_free(ns->rq[i]);
+		nsim_queue_free(dev, ns->rq[i]);
 
 	kfree(ns->rq);
 	ns->rq = NULL;
@@ -909,6 +1013,7 @@ static int nsim_init_netdevsim(struct netdevsim *ns)
 	ns->netdev->netdev_ops = &nsim_netdev_ops;
 	ns->netdev->stat_ops = &nsim_stat_ops;
 	ns->netdev->queue_mgmt_ops = &nsim_queue_mgmt_ops;
+	netdev_lockdep_set_classes(ns->netdev);
 
 	err = nsim_udp_tunnels_info_create(ns->nsim_dev, ns->netdev);
 	if (err)
@@ -930,6 +1035,14 @@ static int nsim_init_netdevsim(struct netdevsim *ns)
 	if (err)
 		goto err_ipsec_teardown;
 	rtnl_unlock();
+
+	if (IS_ENABLED(CONFIG_DEBUG_NET)) {
+		ns->nb.notifier_call = netdev_debug_event;
+		if (register_netdevice_notifier_dev_net(ns->netdev, &ns->nb,
+							&ns->nn))
+			ns->nb.notifier_call = NULL;
+	}
+
 	return 0;
 
 err_ipsec_teardown:
@@ -963,8 +1076,9 @@ static void nsim_exit_netdevsim(struct netdevsim *ns)
 	mock_phc_destroy(ns->phc);
 }
 
-struct netdevsim *
-nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port)
+struct netdevsim *nsim_create(struct nsim_dev *nsim_dev,
+			      struct nsim_dev_port *nsim_dev_port,
+			      u8 perm_addr[ETH_ALEN])
 {
 	struct net_device *dev;
 	struct netdevsim *ns;
@@ -975,10 +1089,12 @@ nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port)
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
 
+	if (perm_addr)
+		memcpy(dev->perm_addr, perm_addr, ETH_ALEN);
+
 	dev_net_set(dev, nsim_dev_net(nsim_dev));
 	ns = netdev_priv(dev);
 	ns->netdev = dev;
-	u64_stats_init(&ns->syncp);
 	ns->nsim_dev = nsim_dev;
 	ns->nsim_dev_port = nsim_dev_port;
 	ns->nsim_bus_dev = nsim_dev->nsim_bus_dev;
@@ -997,7 +1113,6 @@ nsim_create(struct nsim_dev *nsim_dev, struct nsim_dev_port *nsim_dev_port)
 	ns->qr_dfs = debugfs_create_file("queue_reset", 0200,
 					 nsim_dev_port->ddir, ns,
 					 &nsim_qreset_fops);
-
 	return ns;
 
 err_free_netdev:
@@ -1013,6 +1128,10 @@ void nsim_destroy(struct netdevsim *ns)
 	debugfs_remove(ns->qr_dfs);
 	debugfs_remove(ns->pp_dfs);
 
+	if (ns->nb.notifier_call)
+		unregister_netdevice_notifier_dev_net(ns->netdev, &ns->nb,
+						      &ns->nn);
+
 	rtnl_lock();
 	peer = rtnl_dereference(ns->peer);
 	if (peer)
@@ -1031,7 +1150,8 @@ void nsim_destroy(struct netdevsim *ns)
 
 	/* Put this intentionally late to exercise the orphaning path */
 	if (ns->page) {
-		page_pool_put_full_page(ns->page->pp, ns->page, false);
+		page_pool_put_full_page(pp_page_to_nmdesc(ns->page)->pp,
+					ns->page, false);
 		ns->page = NULL;
 	}