1 files changed, 244 insertions, 140 deletions

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index ebd07ad82431..060135ceaf0e 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -113,7 +113,6 @@ do {								\
 } while (0)
 #endif
 
-#define TUN_HEADROOM 256
 #define TUN_RX_PAD (NET_IP_ALIGN + NET_SKB_PAD)
 
 /* TUN device flags */
@@ -181,6 +180,7 @@ struct tun_file {
 	};
 	struct napi_struct napi;
 	bool napi_enabled;
+	bool napi_frags_enabled;
 	struct mutex napi_mutex;	/* Protects access to the above napi */
 	struct list_head next;
 	struct tun_struct *detached;
@@ -313,32 +313,32 @@ static int tun_napi_poll(struct napi_struct *napi, int budget)
 }
 
 static void tun_napi_init(struct tun_struct *tun, struct tun_file *tfile,
-			  bool napi_en)
+			  bool napi_en, bool napi_frags)
 {
 	tfile->napi_enabled = napi_en;
+	tfile->napi_frags_enabled = napi_en && napi_frags;
 	if (napi_en) {
 		netif_napi_add(tun->dev, &tfile->napi, tun_napi_poll,
 			       NAPI_POLL_WEIGHT);
 		napi_enable(&tfile->napi);
-		mutex_init(&tfile->napi_mutex);
 	}
 }
 
-static void tun_napi_disable(struct tun_struct *tun, struct tun_file *tfile)
+static void tun_napi_disable(struct tun_file *tfile)
 {
 	if (tfile->napi_enabled)
 		napi_disable(&tfile->napi);
 }
 
-static void tun_napi_del(struct tun_struct *tun, struct tun_file *tfile)
+static void tun_napi_del(struct tun_file *tfile)
 {
 	if (tfile->napi_enabled)
 		netif_napi_del(&tfile->napi);
 }
 
-static bool tun_napi_frags_enabled(const struct tun_struct *tun)
+static bool tun_napi_frags_enabled(const struct tun_file *tfile)
 {
-	return READ_ONCE(tun->flags) & IFF_NAPI_FRAGS;
+	return tfile->napi_frags_enabled;
 }
 
 #ifdef CONFIG_TUN_VNET_CROSS_LE
@@ -562,12 +562,11 @@ static inline void tun_flow_save_rps_rxhash(struct tun_flow_entry *e, u32 hash)
 		e->rps_rxhash = hash;
 }
 
-/* We try to identify a flow through its rxhash first. The reason that
+/* We try to identify a flow through its rxhash. The reason that
  * we do not check rxq no. is because some cards(e.g 82599), chooses
  * the rxq based on the txq where the last packet of the flow comes. As
  * the userspace application move between processors, we may get a
- * different rxq no. here. If we could not get rxhash, then we would
- * hope the rxq no. may help here.
+ * different rxq no. here.
  */
 static u16 tun_automq_select_queue(struct tun_struct *tun, struct sk_buff *skb)
 {
@@ -578,18 +577,13 @@ static u16 tun_automq_select_queue(struct tun_struct *tun, struct sk_buff *skb)
 	numqueues = READ_ONCE(tun->numqueues);
 
 	txq = __skb_get_hash_symmetric(skb);
-	if (txq) {
-		e = tun_flow_find(&tun->flows[tun_hashfn(txq)], txq);
-		if (e) {
-			tun_flow_save_rps_rxhash(e, txq);
-			txq = e->queue_index;
-		} else
-			/* use multiply and shift instead of expensive divide */
-			txq = ((u64)txq * numqueues) >> 32;
-	} else if (likely(skb_rx_queue_recorded(skb))) {
-		txq = skb_get_rx_queue(skb);
-		while (unlikely(txq >= numqueues))
-			txq -= numqueues;
+	e = tun_flow_find(&tun->flows[tun_hashfn(txq)], txq);
+	if (e) {
+		tun_flow_save_rps_rxhash(e, txq);
+		txq = e->queue_index;
+	} else {
+		/* use multiply and shift instead of expensive divide */
+		txq = ((u64)txq * numqueues) >> 32;
 	}
 
 	return txq;
@@ -690,8 +684,8 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
 	tun = rtnl_dereference(tfile->tun);
 
 	if (tun && clean) {
-		tun_napi_disable(tun, tfile);
-		tun_napi_del(tun, tfile);
+		tun_napi_disable(tfile);
+		tun_napi_del(tfile);
 	}
 
 	if (tun && !tfile->detached) {
@@ -758,7 +752,7 @@ static void tun_detach_all(struct net_device *dev)
 	for (i = 0; i < n; i++) {
 		tfile = rtnl_dereference(tun->tfiles[i]);
 		BUG_ON(!tfile);
-		tun_napi_disable(tun, tfile);
+		tun_napi_disable(tfile);
 		tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN;
 		tfile->socket.sk->sk_data_ready(tfile->socket.sk);
 		RCU_INIT_POINTER(tfile->tun, NULL);
@@ -774,7 +768,7 @@ static void tun_detach_all(struct net_device *dev)
 	synchronize_net();
 	for (i = 0; i < n; i++) {
 		tfile = rtnl_dereference(tun->tfiles[i]);
-		tun_napi_del(tun, tfile);
+		tun_napi_del(tfile);
 		/* Drop read queue */
 		tun_queue_purge(tfile);
 		xdp_rxq_info_unreg(&tfile->xdp_rxq);
@@ -793,7 +787,7 @@ static void tun_detach_all(struct net_device *dev)
 }
 
 static int tun_attach(struct tun_struct *tun, struct file *file,
-		      bool skip_filter, bool napi)
+		      bool skip_filter, bool napi, bool napi_frags)
 {
 	struct tun_file *tfile = file->private_data;
 	struct net_device *dev = tun->dev;
@@ -866,9 +860,12 @@ static int tun_attach(struct tun_struct *tun, struct file *file,
 		tun_enable_queue(tfile);
 	} else {
 		sock_hold(&tfile->sk);
-		tun_napi_init(tun, tfile, napi);
+		tun_napi_init(tun, tfile, napi, napi_frags);
 	}
 
+	if (rtnl_dereference(tun->xdp_prog))
+		sock_set_flag(&tfile->sk, SOCK_XDP);
+
 	tun_set_real_num_queues(tun);
 
 	/* device is allowed to go away first, so no need to hold extra
@@ -1044,16 +1041,13 @@ static void tun_automq_xmit(struct tun_struct *tun, struct sk_buff *skb)
 		/* Select queue was not called for the skbuff, so we extract the
 		 * RPS hash and save it into the flow_table here.
 		 */
+		struct tun_flow_entry *e;
 		__u32 rxhash;
 
 		rxhash = __skb_get_hash_symmetric(skb);
-		if (rxhash) {
-			struct tun_flow_entry *e;
-			e = tun_flow_find(&tun->flows[tun_hashfn(rxhash)],
-					rxhash);
-			if (e)
-				tun_flow_save_rps_rxhash(e, rxhash);
-		}
+		e = tun_flow_find(&tun->flows[tun_hashfn(rxhash)], rxhash);
+		if (e)
+			tun_flow_save_rps_rxhash(e, rxhash);
 	}
 #endif
 }
@@ -1153,43 +1147,6 @@ static netdev_features_t tun_net_fix_features(struct net_device *dev,
 
 	return (features & tun->set_features) | (features & ~TUN_USER_FEATURES);
 }
-#ifdef CONFIG_NET_POLL_CONTROLLER
-static void tun_poll_controller(struct net_device *dev)
-{
-	/*
-	 * Tun only receives frames when:
-	 * 1) the char device endpoint gets data from user space
-	 * 2) the tun socket gets a sendmsg call from user space
-	 * If NAPI is not enabled, since both of those are synchronous
-	 * operations, we are guaranteed never to have pending data when we poll
-	 * for it so there is nothing to do here but return.
-	 * We need this though so netpoll recognizes us as an interface that
-	 * supports polling, which enables bridge devices in virt setups to
-	 * still use netconsole
-	 * If NAPI is enabled, however, we need to schedule polling for all
-	 * queues unless we are using napi_gro_frags(), which we call in
-	 * process context and not in NAPI context.
-	 */
-	struct tun_struct *tun = netdev_priv(dev);
-
-	if (tun->flags & IFF_NAPI) {
-		struct tun_file *tfile;
-		int i;
-
-		if (tun_napi_frags_enabled(tun))
-			return;
-
-		rcu_read_lock();
-		for (i = 0; i < tun->numqueues; i++) {
-			tfile = rcu_dereference(tun->tfiles[i]);
-			if (tfile->napi_enabled)
-				napi_schedule(&tfile->napi);
-		}
-		rcu_read_unlock();
-	}
-	return;
-}
-#endif
 
 static void tun_set_headroom(struct net_device *dev, int new_hr)
 {
@@ -1241,13 +1198,29 @@ static int tun_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 		       struct netlink_ext_ack *extack)
 {
 	struct tun_struct *tun = netdev_priv(dev);
+	struct tun_file *tfile;
 	struct bpf_prog *old_prog;
+	int i;
 
 	old_prog = rtnl_dereference(tun->xdp_prog);
 	rcu_assign_pointer(tun->xdp_prog, prog);
 	if (old_prog)
 		bpf_prog_put(old_prog);
 
+	for (i = 0; i < tun->numqueues; i++) {
+		tfile = rtnl_dereference(tun->tfiles[i]);
+		if (prog)
+			sock_set_flag(&tfile->sk, SOCK_XDP);
+		else
+			sock_reset_flag(&tfile->sk, SOCK_XDP);
+	}
+	list_for_each_entry(tfile, &tun->disabled, next) {
+		if (prog)
+			sock_set_flag(&tfile->sk, SOCK_XDP);
+		else
+			sock_reset_flag(&tfile->sk, SOCK_XDP);
+	}
+
 	return 0;
 }
 
@@ -1283,9 +1256,6 @@ static const struct net_device_ops tun_netdev_ops = {
 	.ndo_start_xmit		= tun_net_xmit,
 	.ndo_fix_features	= tun_net_fix_features,
 	.ndo_select_queue	= tun_select_queue,
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	.ndo_poll_controller	= tun_poll_controller,
-#endif
 	.ndo_set_rx_headroom	= tun_set_headroom,
 	.ndo_get_stats64	= tun_net_get_stats64,
 };
@@ -1365,9 +1335,6 @@ static const struct net_device_ops tap_netdev_ops = {
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_select_queue	= tun_select_queue,
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	.ndo_poll_controller	= tun_poll_controller,
-#endif
 	.ndo_features_check	= passthru_features_check,
 	.ndo_set_rx_headroom	= tun_set_headroom,
 	.ndo_get_stats64	= tun_net_get_stats64,
@@ -1617,6 +1584,55 @@ static bool tun_can_build_skb(struct tun_struct *tun, struct tun_file *tfile,
 	return true;
 }
 
+static struct sk_buff *__tun_build_skb(struct page_frag *alloc_frag, char *buf,
+				       int buflen, int len, int pad)
+{
+	struct sk_buff *skb = build_skb(buf, buflen);
+
+	if (!skb)
+		return ERR_PTR(-ENOMEM);
+
+	skb_reserve(skb, pad);
+	skb_put(skb, len);
+
+	get_page(alloc_frag->page);
+	alloc_frag->offset += buflen;
+
+	return skb;
+}
+
+static int tun_xdp_act(struct tun_struct *tun, struct bpf_prog *xdp_prog,
+		       struct xdp_buff *xdp, u32 act)
+{
+	int err;
+
+	switch (act) {
+	case XDP_REDIRECT:
+		err = xdp_do_redirect(tun->dev, xdp, xdp_prog);
+		if (err)
+			return err;
+		break;
+	case XDP_TX:
+		err = tun_xdp_tx(tun->dev, xdp);
+		if (err < 0)
+			return err;
+		break;
+	case XDP_PASS:
+		break;
+	default:
+		bpf_warn_invalid_xdp_action(act);
+		/* fall through */
+	case XDP_ABORTED:
+		trace_xdp_exception(tun->dev, xdp_prog, act);
+		/* fall through */
+	case XDP_DROP:
+		this_cpu_inc(tun->pcpu_stats->rx_dropped);
+		break;
+	}
+
+	return act;
+}
+
 static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 				     struct tun_file *tfile,
 				     struct iov_iter *from,
@@ -1624,18 +1640,17 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 				     int len, int *skb_xdp)
 {
 	struct page_frag *alloc_frag = &current->task_frag;
-	struct sk_buff *skb;
 	struct bpf_prog *xdp_prog;
 	int buflen = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-	unsigned int delta = 0;
 	char *buf;
 	size_t copied;
-	int err, pad = TUN_RX_PAD;
+	int pad = TUN_RX_PAD;
+	int err = 0;
 
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(tun->xdp_prog);
 	if (xdp_prog)
-		pad += TUN_HEADROOM;
+		pad += XDP_PACKET_HEADROOM;
 	buflen += SKB_DATA_ALIGN(len + pad);
 	rcu_read_unlock();
 
@@ -1654,17 +1669,18 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 	 * of xdp_prog above, this should be rare and for simplicity
 	 * we do XDP on skb in case the headroom is not enough.
 	 */
-	if (hdr->gso_type || !xdp_prog)
+	if (hdr->gso_type || !xdp_prog) {
 		*skb_xdp = 1;
-	else
-		*skb_xdp = 0;
+		return __tun_build_skb(alloc_frag, buf, buflen, len, pad);
+	}
+
+	*skb_xdp = 0;
 
 	local_bh_disable();
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(tun->xdp_prog);
-	if (xdp_prog && !*skb_xdp) {
+	if (xdp_prog) {
 		struct xdp_buff xdp;
-		void *orig_data;
 		u32 act;
 
 		xdp.data_hard_start = buf;
@@ -1672,66 +1688,33 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 		xdp_set_data_meta_invalid(&xdp);
 		xdp.data_end = xdp.data + len;
 		xdp.rxq = &tfile->xdp_rxq;
-		orig_data = xdp.data;
-		act = bpf_prog_run_xdp(xdp_prog, &xdp);
 
-		switch (act) {
-		case XDP_REDIRECT:
-			get_page(alloc_frag->page);
-			alloc_frag->offset += buflen;
-			err = xdp_do_redirect(tun->dev, &xdp, xdp_prog);
-			xdp_do_flush_map();
-			if (err)
-				goto err_redirect;
-			rcu_read_unlock();
-			local_bh_enable();
-			return NULL;
-		case XDP_TX:
+		act = bpf_prog_run_xdp(xdp_prog, &xdp);
+		if (act == XDP_REDIRECT || act == XDP_TX) {
 			get_page(alloc_frag->page);
 			alloc_frag->offset += buflen;
-			if (tun_xdp_tx(tun->dev, &xdp) < 0)
-				goto err_redirect;
-			rcu_read_unlock();
-			local_bh_enable();
-			return NULL;
-		case XDP_PASS:
-			delta = orig_data - xdp.data;
-			len = xdp.data_end - xdp.data;
-			break;
-		default:
-			bpf_warn_invalid_xdp_action(act);
-			/* fall through */
-		case XDP_ABORTED:
-			trace_xdp_exception(tun->dev, xdp_prog, act);
-			/* fall through */
-		case XDP_DROP:
-			goto err_xdp;
 		}
-	}
+		err = tun_xdp_act(tun, xdp_prog, &xdp, act);
+		if (err < 0)
+			goto err_xdp;
+		if (err == XDP_REDIRECT)
+			xdp_do_flush_map();
+		if (err != XDP_PASS)
+			goto out;
 
-	skb = build_skb(buf, buflen);
-	if (!skb) {
-		rcu_read_unlock();
-		local_bh_enable();
-		return ERR_PTR(-ENOMEM);
+		pad = xdp.data - xdp.data_hard_start;
+		len = xdp.data_end - xdp.data;
 	}
-
-	skb_reserve(skb, pad - delta);
-	skb_put(skb, len);
-	get_page(alloc_frag->page);
-	alloc_frag->offset += buflen;
-
 	rcu_read_unlock();
 	local_bh_enable();
 
-	return skb;
+	return __tun_build_skb(alloc_frag, buf, buflen, len, pad);
 
-err_redirect:
-	put_page(alloc_frag->page);
 err_xdp:
+	put_page(alloc_frag->page);
+out:
 	rcu_read_unlock();
 	local_bh_enable();
-	this_cpu_inc(tun->pcpu_stats->rx_dropped);
 	return NULL;
 }
 
@@ -1752,7 +1735,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	int err;
 	u32 rxhash = 0;
 	int skb_xdp = 1;
-	bool frags = tun_napi_frags_enabled(tun);
+	bool frags = tun_napi_frags_enabled(tfile);
 
 	if (!(tun->dev->flags & IFF_UP))
 		return -EIO;
@@ -2306,6 +2289,8 @@ static void tun_setup(struct net_device *dev)
 static int tun_validate(struct nlattr *tb[], struct nlattr *data[],
 			struct netlink_ext_ack *extack)
 {
+	if (!data)
+		return 0;
 	return -EINVAL;
 }
 
@@ -2392,18 +2377,133 @@ static void tun_sock_write_space(struct sock *sk)
 	kill_fasync(&tfile->fasync, SIGIO, POLL_OUT);
 }
 
+static int tun_xdp_one(struct tun_struct *tun,
+		       struct tun_file *tfile,
+		       struct xdp_buff *xdp, int *flush)
+{
+	struct tun_xdp_hdr *hdr = xdp->data_hard_start;
+	struct virtio_net_hdr *gso = &hdr->gso;
+	struct tun_pcpu_stats *stats;
+	struct bpf_prog *xdp_prog;
+	struct sk_buff *skb = NULL;
+	u32 rxhash = 0, act;
+	int buflen = hdr->buflen;
+	int err = 0;
+	bool skb_xdp = false;
+
+	xdp_prog = rcu_dereference(tun->xdp_prog);
+	if (xdp_prog) {
+		if (gso->gso_type) {
+			skb_xdp = true;
+			goto build;
+		}
+		xdp_set_data_meta_invalid(xdp);
+		xdp->rxq = &tfile->xdp_rxq;
+
+		act = bpf_prog_run_xdp(xdp_prog, xdp);
+		err = tun_xdp_act(tun, xdp_prog, xdp, act);
+		if (err < 0) {
+			put_page(virt_to_head_page(xdp->data));
+			return err;
+		}
+
+		switch (err) {
+		case XDP_REDIRECT:
+			*flush = true;
+			/* fall through */
+		case XDP_TX:
+			return 0;
+		case XDP_PASS:
+			break;
+		default:
+			put_page(virt_to_head_page(xdp->data));
+			return 0;
+		}
+	}
+
+build:
+	skb = build_skb(xdp->data_hard_start, buflen);
+	if (!skb) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	skb_reserve(skb, xdp->data - xdp->data_hard_start);
+	skb_put(skb, xdp->data_end - xdp->data);
+
+	if (virtio_net_hdr_to_skb(skb, gso, tun_is_little_endian(tun))) {
+		this_cpu_inc(tun->pcpu_stats->rx_frame_errors);
+		kfree_skb(skb);
+		err = -EINVAL;
+		goto out;
+	}
+
+	skb->protocol = eth_type_trans(skb, tun->dev);
+	skb_reset_network_header(skb);
+	skb_probe_transport_header(skb, 0);
+
+	if (skb_xdp) {
+		err = do_xdp_generic(xdp_prog, skb);
+		if (err != XDP_PASS)
+			goto out;
+	}
+
+	if (!rcu_dereference(tun->steering_prog))
+		rxhash = __skb_get_hash_symmetric(skb);
+
+	netif_receive_skb(skb);
+
+	stats = get_cpu_ptr(tun->pcpu_stats);
+	u64_stats_update_begin(&stats->syncp);
+	stats->rx_packets++;
+	stats->rx_bytes += skb->len;
+	u64_stats_update_end(&stats->syncp);
+	put_cpu_ptr(stats);
+
+	if (rxhash)
+		tun_flow_update(tun, rxhash, tfile);
+
+out:
+	return err;
+}
+
 static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
 {
-	int ret;
+	int ret, i;
 	struct tun_file *tfile = container_of(sock, struct tun_file, socket);
 	struct tun_struct *tun = tun_get(tfile);
+	struct tun_msg_ctl *ctl = m->msg_control;
+	struct xdp_buff *xdp;
 
 	if (!tun)
 		return -EBADFD;
 
-	ret = tun_get_user(tun, tfile, m->msg_control, &m->msg_iter,
+	if (ctl && (ctl->type == TUN_MSG_PTR)) {
+		int n = ctl->num;
+		int flush = 0;
+
+		local_bh_disable();
+		rcu_read_lock();
+
+		for (i = 0; i < n; i++) {
+			xdp = &((struct xdp_buff *)ctl->ptr)[i];
+			tun_xdp_one(tun, tfile, xdp, &flush);
+		}
+
+		if (flush)
+			xdp_do_flush_map();
+
+		rcu_read_unlock();
+		local_bh_enable();
+
+		ret = total_len;
+		goto out;
+	}
+
+	ret = tun_get_user(tun, tfile, ctl ? ctl->ptr : NULL, &m->msg_iter,
 			   m->msg_flags & MSG_DONTWAIT,
 			   m->msg_flags & MSG_MORE);
+out:
 	tun_put(tun);
 	return ret;
 }
@@ -2577,7 +2677,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 			return err;
 
 		err = tun_attach(tun, file, ifr->ifr_flags & IFF_NOFILTER,
-				 ifr->ifr_flags & IFF_NAPI);
+				 ifr->ifr_flags & IFF_NAPI,
+				 ifr->ifr_flags & IFF_NAPI_FRAGS);
 		if (err < 0)
 			return err;
 
@@ -2675,7 +2776,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
 			      (ifr->ifr_flags & TUN_FEATURES);
 
 		INIT_LIST_HEAD(&tun->disabled);
-		err = tun_attach(tun, file, false, ifr->ifr_flags & IFF_NAPI);
+		err = tun_attach(tun, file, false, ifr->ifr_flags & IFF_NAPI,
+				 ifr->ifr_flags & IFF_NAPI_FRAGS);
 		if (err < 0)
 			goto err_free_flow;
 
@@ -2824,7 +2926,8 @@ static int tun_set_queue(struct file *file, struct ifreq *ifr)
 		ret = security_tun_dev_attach_queue(tun->security);
 		if (ret < 0)
 			goto unlock;
-		ret = tun_attach(tun, file, false, tun->flags & IFF_NAPI);
+		ret = tun_attach(tun, file, false, tun->flags & IFF_NAPI,
+				 tun->flags & IFF_NAPI_FRAGS);
 	} else if (ifr->ifr_flags & IFF_DETACH_QUEUE) {
 		tun = rtnl_dereference(tfile->tun);
 		if (!tun || !(tun->flags & IFF_MULTI_QUEUE) || tfile->detached)
@@ -3242,6 +3345,7 @@ static int tun_chr_open(struct inode *inode, struct file * file)
 		return -ENOMEM;
 	}
 
+	mutex_init(&tfile->napi_mutex);
 	RCU_INIT_POINTER(tfile->tun, NULL);
 	tfile->flags = 0;
 	tfile->ifindex = 0;