Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Add Maglev hashing scheduler to IPVS, from Inju Song.

 2) Lots of new TC subsystem tests from Roman Mashak.

 3) Add TCP zero copy receive and fix delayed acks and autotuning with
    SO_RCVLOWAT, from Eric Dumazet.

 4) Add XDP_REDIRECT support to mlx5 driver, from Jesper Dangaard
    Brouer.

 5) Add ttl inherit support to vxlan, from Hangbin Liu.

 6) Properly separate ipv6 routes into their logically independant
    components. fib6_info for the routing table, and fib6_nh for sets of
    nexthops, which thus can be shared. From David Ahern.

 7) Add bpf_xdp_adjust_tail helper, which can be used to generate ICMP
    messages from XDP programs. From Nikita V. Shirokov.

 8) Lots of long overdue cleanups to the r8169 driver, from Heiner
    Kallweit.

 9) Add BTF ("BPF Type Format"), from Martin KaFai Lau.

10) Add traffic condition monitoring to iwlwifi, from Luca Coelho.

11) Plumb extack down into fib_rules, from Roopa Prabhu.

12) Add Flower classifier offload support to igb, from Vinicius Costa
    Gomes.

13) Add UDP GSO support, from Willem de Bruijn.

14) Add documentation for eBPF helpers, from Quentin Monnet.

15) Add TLS tx offload to mlx5, from Ilya Lesokhin.

16) Allow applications to be given the number of bytes available to read
    on a socket via a control message returned from recvmsg(), from
    Soheil Hassas Yeganeh.

17) Add x86_32 eBPF JIT compiler, from Wang YanQing.

18) Add AF_XDP sockets, with zerocopy support infrastructure as well.
    From Björn Töpel.

19) Remove indirect load support from all of the BPF JITs and handle
    these operations in the verifier by translating them into native BPF
    instead. From Daniel Borkmann.

20) Add GRO support to ipv6 gre tunnels, from Eran Ben Elisha.

21) Allow XDP programs to do lookups in the main kernel routing tables
    for forwarding. From David Ahern.

22) Allow drivers to store hardware state into an ELF section of kernel
    dump vmcore files, and use it in cxgb4. From Rahul Lakkireddy.

23) Various RACK and loss detection improvements in TCP, from Yuchung
    Cheng.

24) Add TCP SACK compression, from Eric Dumazet.

25) Add User Mode Helper support and basic bpfilter infrastructure, from
    Alexei Starovoitov.

26) Support ports and protocol values in RTM_GETROUTE, from Roopa
    Prabhu.

27) Support bulking in ->ndo_xdp_xmit() API, from Jesper Dangaard
    Brouer.

28) Add lots of forwarding selftests, from Petr Machata.

29) Add generic network device failover driver, from Sridhar Samudrala.

* ra.kernel.org:/pub/scm/linux/kernel/git/davem/net-next: (1959 commits)
  strparser: Add __strp_unpause and use it in ktls.
  rxrpc: Fix terminal retransmission connection ID to include the channel
  net: hns3: Optimize PF CMDQ interrupt switching process
  net: hns3: Fix for VF mailbox receiving unknown message
  net: hns3: Fix for VF mailbox cannot receiving PF response
  bnx2x: use the right constant
  Revert "net: sched: cls: Fix offloading when ingress dev is vxlan"
  net: dsa: b53: Fix for brcm tag issue in Cygnus SoC
  enic: fix UDP rss bits
  netdev-FAQ: clarify DaveM's position for stable backports
  rtnetlink: validate attributes in do_setlink()
  mlxsw: Add extack messages for port_{un, }split failures
  netdevsim: Add extack error message for devlink reload
  devlink: Add extack to reload and port_{un, }split operations
  net: metrics: add proper netlink validation
  ipmr: fix error path when ipmr_new_table fails
  ip6mr: only set ip6mr_table from setsockopt when ip6mr_new_table succeeds
  net: hns3: remove unused hclgevf_cfg_func_mta_filter
  netfilter: provide udp*_lib_lookup for nf_tproxy
  qed*: Utilize FW 8.37.2.0
  ...

1 files changed, 102 insertions, 46 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 9c149238a4ce..6e18242a1cae 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1285,6 +1285,7 @@ int dev_set_alias(struct net_device *dev, const char *alias, size_t len)
 
 	return len;
 }
+EXPORT_SYMBOL(dev_set_alias);
 
 /**
  *	dev_get_alias - get ifalias of a device
@@ -1586,7 +1587,7 @@ const char *netdev_cmd_to_name(enum netdev_cmd cmd)
 	N(UDP_TUNNEL_DROP_INFO) N(CHANGE_TX_QUEUE_LEN)
 	N(CVLAN_FILTER_PUSH_INFO) N(CVLAN_FILTER_DROP_INFO)
 	N(SVLAN_FILTER_PUSH_INFO) N(SVLAN_FILTER_DROP_INFO)
-	};
+	}
 #undef N
 	return "UNKNOWN_NETDEV_EVENT";
 }
@@ -1754,38 +1755,38 @@ int call_netdevice_notifiers(unsigned long val, struct net_device *dev)
 EXPORT_SYMBOL(call_netdevice_notifiers);
 
 #ifdef CONFIG_NET_INGRESS
-static struct static_key ingress_needed __read_mostly;
+static DEFINE_STATIC_KEY_FALSE(ingress_needed_key);
 
 void net_inc_ingress_queue(void)
 {
-	static_key_slow_inc(&ingress_needed);
+	static_branch_inc(&ingress_needed_key);
 }
 EXPORT_SYMBOL_GPL(net_inc_ingress_queue);
 
 void net_dec_ingress_queue(void)
 {
-	static_key_slow_dec(&ingress_needed);
+	static_branch_dec(&ingress_needed_key);
 }
 EXPORT_SYMBOL_GPL(net_dec_ingress_queue);
 #endif
 
 #ifdef CONFIG_NET_EGRESS
-static struct static_key egress_needed __read_mostly;
+static DEFINE_STATIC_KEY_FALSE(egress_needed_key);
 
 void net_inc_egress_queue(void)
 {
-	static_key_slow_inc(&egress_needed);
+	static_branch_inc(&egress_needed_key);
 }
 EXPORT_SYMBOL_GPL(net_inc_egress_queue);
 
 void net_dec_egress_queue(void)
 {
-	static_key_slow_dec(&egress_needed);
+	static_branch_dec(&egress_needed_key);
 }
 EXPORT_SYMBOL_GPL(net_dec_egress_queue);
 #endif
 
-static struct static_key netstamp_needed __read_mostly;
+static DEFINE_STATIC_KEY_FALSE(netstamp_needed_key);
 #ifdef HAVE_JUMP_LABEL
 static atomic_t netstamp_needed_deferred;
 static atomic_t netstamp_wanted;
@@ -1796,9 +1797,9 @@ static void netstamp_clear(struct work_struct *work)
 
 	wanted = atomic_add_return(deferred, &netstamp_wanted);
 	if (wanted > 0)
-		static_key_enable(&netstamp_needed);
+		static_branch_enable(&netstamp_needed_key);
 	else
-		static_key_disable(&netstamp_needed);
+		static_branch_disable(&netstamp_needed_key);
 }
 static DECLARE_WORK(netstamp_work, netstamp_clear);
 #endif
@@ -1818,7 +1819,7 @@ void net_enable_timestamp(void)
 	atomic_inc(&netstamp_needed_deferred);
 	schedule_work(&netstamp_work);
 #else
-	static_key_slow_inc(&netstamp_needed);
+	static_branch_inc(&netstamp_needed_key);
 #endif
 }
 EXPORT_SYMBOL(net_enable_timestamp);
@@ -1838,7 +1839,7 @@ void net_disable_timestamp(void)
 	atomic_dec(&netstamp_needed_deferred);
 	schedule_work(&netstamp_work);
 #else
-	static_key_slow_dec(&netstamp_needed);
+	static_branch_dec(&netstamp_needed_key);
 #endif
 }
 EXPORT_SYMBOL(net_disable_timestamp);
@@ -1846,15 +1847,15 @@ EXPORT_SYMBOL(net_disable_timestamp);
 static inline void net_timestamp_set(struct sk_buff *skb)
 {
 	skb->tstamp = 0;
-	if (static_key_false(&netstamp_needed))
+	if (static_branch_unlikely(&netstamp_needed_key))
 		__net_timestamp(skb);
 }
 
-#define net_timestamp_check(COND, SKB)			\
-	if (static_key_false(&netstamp_needed)) {		\
-		if ((COND) && !(SKB)->tstamp)	\
-			__net_timestamp(SKB);		\
-	}						\
+#define net_timestamp_check(COND, SKB)				\
+	if (static_branch_unlikely(&netstamp_needed_key)) {	\
+		if ((COND) && !(SKB)->tstamp)			\
+			__net_timestamp(SKB);			\
+	}							\
 
 bool is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb)
 {
@@ -2614,17 +2615,16 @@ EXPORT_SYMBOL(netif_device_attach);
  * Returns a Tx hash based on the given packet descriptor a Tx queues' number
  * to be used as a distribution range.
  */
-u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb,
-		  unsigned int num_tx_queues)
+static u16 skb_tx_hash(const struct net_device *dev, struct sk_buff *skb)
 {
 	u32 hash;
 	u16 qoffset = 0;
-	u16 qcount = num_tx_queues;
+	u16 qcount = dev->real_num_tx_queues;
 
 	if (skb_rx_queue_recorded(skb)) {
 		hash = skb_get_rx_queue(skb);
-		while (unlikely(hash >= num_tx_queues))
-			hash -= num_tx_queues;
+		while (unlikely(hash >= qcount))
+			hash -= qcount;
 		return hash;
 	}
 
@@ -2637,7 +2637,6 @@ u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb,
 
 	return (u16) reciprocal_scale(skb_get_hash(skb), qcount) + qoffset;
 }
-EXPORT_SYMBOL(__skb_tx_hash);
 
 static void skb_warn_bad_offload(const struct sk_buff *skb)
 {
@@ -3095,6 +3094,10 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device
 	if (unlikely(!skb))
 		goto out_null;
 
+	skb = sk_validate_xmit_skb(skb, dev);
+	if (unlikely(!skb))
+		goto out_null;
+
 	if (netif_needs_gso(skb, features)) {
 		struct sk_buff *segs;
 
@@ -3223,7 +3226,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 			rc = NET_XMIT_DROP;
 		} else {
 			rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
-			__qdisc_run(q);
+			qdisc_run(q);
 		}
 
 		if (unlikely(to_free))
@@ -3511,7 +3514,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
 #ifdef CONFIG_NET_CLS_ACT
 	skb->tc_at_ingress = 0;
 # ifdef CONFIG_NET_EGRESS
-	if (static_key_false(&egress_needed)) {
+	if (static_branch_unlikely(&egress_needed_key)) {
 		skb = sch_handle_egress(skb, &rc, dev);
 		if (!skb)
 			goto out;
@@ -3606,6 +3609,44 @@ int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv)
 }
 EXPORT_SYMBOL(dev_queue_xmit_accel);
 
+int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
+{
+	struct net_device *dev = skb->dev;
+	struct sk_buff *orig_skb = skb;
+	struct netdev_queue *txq;
+	int ret = NETDEV_TX_BUSY;
+	bool again = false;
+
+	if (unlikely(!netif_running(dev) ||
+		     !netif_carrier_ok(dev)))
+		goto drop;
+
+	skb = validate_xmit_skb_list(skb, dev, &again);
+	if (skb != orig_skb)
+		goto drop;
+
+	skb_set_queue_mapping(skb, queue_id);
+	txq = skb_get_tx_queue(dev, skb);
+
+	local_bh_disable();
+
+	HARD_TX_LOCK(dev, txq, smp_processor_id());
+	if (!netif_xmit_frozen_or_drv_stopped(txq))
+		ret = netdev_start_xmit(skb, dev, txq, false);
+	HARD_TX_UNLOCK(dev, txq);
+
+	local_bh_enable();
+
+	if (!dev_xmit_complete(ret))
+		kfree_skb(skb);
+
+	return ret;
+drop:
+	atomic_long_inc(&dev->tx_dropped);
+	kfree_skb_list(skb);
+	return NET_XMIT_DROP;
+}
+EXPORT_SYMBOL(dev_direct_xmit);
 
 /*************************************************************************
  *			Receiver routines
@@ -3975,12 +4016,12 @@ static struct netdev_rx_queue *netif_get_rxqueue(struct sk_buff *skb)
 }
 
 static u32 netif_receive_generic_xdp(struct sk_buff *skb,
+				     struct xdp_buff *xdp,
 				     struct bpf_prog *xdp_prog)
 {
 	struct netdev_rx_queue *rxqueue;
+	void *orig_data, *orig_data_end;
 	u32 metalen, act = XDP_DROP;
-	struct xdp_buff xdp;
-	void *orig_data;
 	int hlen, off;
 	u32 mac_len;
 
@@ -4015,31 +4056,42 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 	 */
 	mac_len = skb->data - skb_mac_header(skb);
 	hlen = skb_headlen(skb) + mac_len;
-	xdp.data = skb->data - mac_len;
-	xdp.data_meta = xdp.data;
-	xdp.data_end = xdp.data + hlen;
-	xdp.data_hard_start = skb->data - skb_headroom(skb);
-	orig_data = xdp.data;
+	xdp->data = skb->data - mac_len;
+	xdp->data_meta = xdp->data;
+	xdp->data_end = xdp->data + hlen;
+	xdp->data_hard_start = skb->data - skb_headroom(skb);
+	orig_data_end = xdp->data_end;
+	orig_data = xdp->data;
 
 	rxqueue = netif_get_rxqueue(skb);
-	xdp.rxq = &rxqueue->xdp_rxq;
+	xdp->rxq = &rxqueue->xdp_rxq;
 
-	act = bpf_prog_run_xdp(xdp_prog, &xdp);
+	act = bpf_prog_run_xdp(xdp_prog, xdp);
 
-	off = xdp.data - orig_data;
+	off = xdp->data - orig_data;
 	if (off > 0)
 		__skb_pull(skb, off);
 	else if (off < 0)
 		__skb_push(skb, -off);
 	skb->mac_header += off;
 
+	/* check if bpf_xdp_adjust_tail was used. it can only "shrink"
+	 * pckt.
+	 */
+	off = orig_data_end - xdp->data_end;
+	if (off != 0) {
+		skb_set_tail_pointer(skb, xdp->data_end - xdp->data);
+		skb->len -= off;
+
+	}
+
 	switch (act) {
 	case XDP_REDIRECT:
 	case XDP_TX:
 		__skb_push(skb, mac_len);
 		break;
 	case XDP_PASS:
-		metalen = xdp.data - xdp.data_meta;
+		metalen = xdp->data - xdp->data_meta;
 		if (metalen)
 			skb_metadata_set(skb, metalen);
 		break;
@@ -4084,22 +4136,24 @@ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog)
 }
 EXPORT_SYMBOL_GPL(generic_xdp_tx);
 
-static struct static_key generic_xdp_needed __read_mostly;
+static DEFINE_STATIC_KEY_FALSE(generic_xdp_needed_key);
 
 int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb)
 {
 	if (xdp_prog) {
-		u32 act = netif_receive_generic_xdp(skb, xdp_prog);
+		struct xdp_buff xdp;
+		u32 act;
 		int err;
 
+		act = netif_receive_generic_xdp(skb, &xdp, xdp_prog);
 		if (act != XDP_PASS) {
 			switch (act) {
 			case XDP_REDIRECT:
 				err = xdp_do_generic_redirect(skb->dev, skb,
-							      xdp_prog);
+							      &xdp, xdp_prog);
 				if (err)
 					goto out_redir;
-			/* fallthru to submit skb */
+				break;
 			case XDP_TX:
 				generic_xdp_tx(skb, xdp_prog);
 				break;
@@ -4122,7 +4176,7 @@ static int netif_rx_internal(struct sk_buff *skb)
 
 	trace_netif_rx(skb);
 
-	if (static_key_false(&generic_xdp_needed)) {
+	if (static_branch_unlikely(&generic_xdp_needed_key)) {
 		int ret;
 
 		preempt_disable();
@@ -4494,7 +4548,7 @@ another_round:
 
 skip_taps:
 #ifdef CONFIG_NET_INGRESS
-	if (static_key_false(&ingress_needed)) {
+	if (static_branch_unlikely(&ingress_needed_key)) {
 		skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev);
 		if (!skb)
 			goto out;
@@ -4654,9 +4708,9 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp)
 			bpf_prog_put(old);
 
 		if (old && !new) {
-			static_key_slow_dec(&generic_xdp_needed);
+			static_branch_dec(&generic_xdp_needed_key);
 		} else if (new && !old) {
-			static_key_slow_inc(&generic_xdp_needed);
+			static_branch_inc(&generic_xdp_needed_key);
 			dev_disable_lro(dev);
 			dev_disable_gro_hw(dev);
 		}
@@ -4684,7 +4738,7 @@ static int netif_receive_skb_internal(struct sk_buff *skb)
 	if (skb_defer_rx_timestamp(skb))
 		return NET_RX_SUCCESS;
 
-	if (static_key_false(&generic_xdp_needed)) {
+	if (static_branch_unlikely(&generic_xdp_needed_key)) {
 		int ret;
 
 		preempt_disable();
@@ -7852,6 +7906,8 @@ int register_netdevice(struct net_device *dev)
 	int ret;
 	struct net *net = dev_net(dev);
 
+	BUILD_BUG_ON(sizeof(netdev_features_t) * BITS_PER_BYTE <
+		     NETDEV_FEATURE_COUNT);
 	BUG_ON(dev_boot_phase);
 	ASSERT_RTNL();