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

Pull networking updates from David Miller:

 1) BBR TCP congestion control, from Neal Cardwell, Yuchung Cheng and
    co. at Google. https://lwn.net/Articles/701165/

 2) Do TCP Small Queues for retransmits, from Eric Dumazet.

 3) Support collect_md mode for all IPV4 and IPV6 tunnels, from Alexei
    Starovoitov.

 4) Allow cls_flower to classify packets in ip tunnels, from Amir Vadai.

 5) Support DSA tagging in older mv88e6xxx switches, from Andrew Lunn.

 6) Support GMAC protocol in iwlwifi mwm, from Ayala Beker.

 7) Support ndo_poll_controller in mlx5, from Calvin Owens.

 8) Move VRF processing to an output hook and allow l3mdev to be
    loopback, from David Ahern.

 9) Support SOCK_DESTROY for UDP sockets. Also from David Ahern.

10) Congestion control in RXRPC, from David Howells.

11) Support geneve RX offload in ixgbe, from Emil Tantilov.

12) When hitting pressure for new incoming TCP data SKBs, perform a
    partial rathern than a full purge of the OFO queue (which could be
    huge). From Eric Dumazet.

13) Convert XFRM state and policy lookups to RCU, from Florian Westphal.

14) Support RX network flow classification to igb, from Gangfeng Huang.

15) Hardware offloading of eBPF in nfp driver, from Jakub Kicinski.

16) New skbmod packet action, from Jamal Hadi Salim.

17) Remove some inefficiencies in snmp proc output, from Jia He.

18) Add FIB notifications to properly propagate route changes to
    hardware which is doing forwarding offloading. From Jiri Pirko.

19) New dsa driver for qca8xxx chips, from John Crispin.

20) Implement RFC7559 ipv6 router solicitation backoff, from Maciej
    Żenczykowski.

21) Add L3 mode to ipvlan, from Mahesh Bandewar.

22) Support 802.1ad in mlx4, from Moshe Shemesh.

23) Support hardware LRO in mediatek driver, from Nelson Chang.

24) Add TC offloading to mlx5, from Or Gerlitz.

25) Convert various drivers to ethtool ksettings interfaces, from
    Philippe Reynes.

26) TX max rate limiting for cxgb4, from Rahul Lakkireddy.

27) NAPI support for ath10k, from Rajkumar Manoharan.

28) Support XDP in mlx5, from Rana Shahout and Saeed Mahameed.

29) UDP replicast support in TIPC, from Richard Alpe.

30) Per-queue statistics for qed driver, from Sudarsana Reddy Kalluru.

31) Support BQL in thunderx driver, from Sunil Goutham.

32) TSO support in alx driver, from Tobias Regnery.

33) Add stream parser engine and use it in kcm.

34) Support async DHCP replies in ipconfig module, from Uwe
    Kleine-König.

35) DSA port fast aging for mv88e6xxx driver, from Vivien Didelot.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1715 commits)
  mlxsw: switchx2: Fix misuse of hard_header_len
  mlxsw: spectrum: Fix misuse of hard_header_len
  net/faraday: Stop NCSI device on shutdown
  net/ncsi: Introduce ncsi_stop_dev()
  net/ncsi: Rework the channel monitoring
  net/ncsi: Allow to extend NCSI request properties
  net/ncsi: Rework request index allocation
  net/ncsi: Don't probe on the reserved channel ID (0x1f)
  net/ncsi: Introduce NCSI_RESERVED_CHANNEL
  net/ncsi: Avoid unused-value build warning from ia64-linux-gcc
  net: Add netdev all_adj_list refcnt propagation to fix panic
  net: phy: Add Edge-rate driver for Microsemi PHYs.
  vmxnet3: Wake queue from reset work
  i40e: avoid NULL pointer dereference and recursive errors on early PCI error
  qed: Add RoCE ll2 & GSI support
  qed: Add support for memory registeration verbs
  qed: Add support for QP verbs
  qed: PD,PKEY and CQ verb support
  qed: Add support for RoCE hw init
  qede: Add qedr framework
  ...

1 files changed, 35 insertions, 199 deletions

diff --git a/drivers/target/iscsi/cxgbit/cxgbit_cm.c b/drivers/target/iscsi/cxgbit/cxgbit_cm.c
index 0ae0b131abfc..2fb1bf1a26c5 100644
--- a/drivers/target/iscsi/cxgbit/cxgbit_cm.c
+++ b/drivers/target/iscsi/cxgbit/cxgbit_cm.c
@@ -24,6 +24,7 @@
 #include <net/ip6_route.h>
 #include <net/addrconf.h>
 
+#include <libcxgb_cm.h>
 #include "cxgbit.h"
 #include "clip_tbl.h"
 
@@ -72,15 +73,6 @@ out:
 	return wr_waitp->ret;
 }
 
-/* Returns whether a CPL status conveys negative advice.
- */
-static int cxgbit_is_neg_adv(unsigned int status)
-{
-	return status == CPL_ERR_RTX_NEG_ADVICE ||
-		status == CPL_ERR_PERSIST_NEG_ADVICE ||
-		status == CPL_ERR_KEEPALV_NEG_ADVICE;
-}
-
 static int cxgbit_np_hashfn(const struct cxgbit_np *cnp)
 {
 	return ((unsigned long)cnp >> 10) & (NP_INFO_HASH_SIZE - 1);
@@ -623,21 +615,14 @@ void cxgbit_free_np(struct iscsi_np *np)
 static void cxgbit_send_halfclose(struct cxgbit_sock *csk)
 {
 	struct sk_buff *skb;
-	struct cpl_close_con_req *req;
-	unsigned int len = roundup(sizeof(struct cpl_close_con_req), 16);
+	u32 len = roundup(sizeof(struct cpl_close_con_req), 16);
 
 	skb = alloc_skb(len, GFP_ATOMIC);
 	if (!skb)
 		return;
 
-	req = (struct cpl_close_con_req *)__skb_put(skb, len);
-	memset(req, 0, len);
-
-	set_wr_txq(skb, CPL_PRIORITY_DATA, csk->txq_idx);
-	INIT_TP_WR(req, csk->tid);
-	OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_CLOSE_CON_REQ,
-						    csk->tid));
-	req->rsvd = 0;
+	cxgb_mk_close_con_req(skb, len, csk->tid, csk->txq_idx,
+			      NULL, NULL);
 
 	cxgbit_skcb_flags(skb) |= SKCBF_TX_FLAG_COMPL;
 	__skb_queue_tail(&csk->txq, skb);
@@ -662,9 +647,8 @@ static void cxgbit_abort_arp_failure(void *handle, struct sk_buff *skb)
 
 static int cxgbit_send_abort_req(struct cxgbit_sock *csk)
 {
-	struct cpl_abort_req *req;
-	unsigned int len = roundup(sizeof(*req), 16);
 	struct sk_buff *skb;
+	u32 len = roundup(sizeof(struct cpl_abort_req), 16);
 
 	pr_debug("%s: csk %p tid %u; state %d\n",
 		 __func__, csk, csk->tid, csk->com.state);
@@ -675,15 +659,9 @@ static int cxgbit_send_abort_req(struct cxgbit_sock *csk)
 		cxgbit_send_tx_flowc_wr(csk);
 
 	skb = __skb_dequeue(&csk->skbq);
-	req = (struct cpl_abort_req *)__skb_put(skb, len);
-	memset(req, 0, len);
+	cxgb_mk_abort_req(skb, len, csk->tid, csk->txq_idx,
+			  csk->com.cdev, cxgbit_abort_arp_failure);
 
-	set_wr_txq(skb, CPL_PRIORITY_DATA, csk->txq_idx);
-	t4_set_arp_err_handler(skb, csk->com.cdev, cxgbit_abort_arp_failure);
-	INIT_TP_WR(req, csk->tid);
-	OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_ABORT_REQ,
-						    csk->tid));
-	req->cmd = CPL_ABORT_SEND_RST;
 	return cxgbit_l2t_send(csk->com.cdev, skb, csk->l2t);
 }
 
@@ -789,109 +767,6 @@ void _cxgbit_free_csk(struct kref *kref)
 	kfree(csk);
 }
 
-static void
-cxgbit_get_tuple_info(struct cpl_pass_accept_req *req, int *iptype,
-		      __u8 *local_ip, __u8 *peer_ip, __be16 *local_port,
-		      __be16 *peer_port)
-{
-	u32 eth_len = ETH_HDR_LEN_G(be32_to_cpu(req->hdr_len));
-	u32 ip_len = IP_HDR_LEN_G(be32_to_cpu(req->hdr_len));
-	struct iphdr *ip = (struct iphdr *)((u8 *)(req + 1) + eth_len);
-	struct ipv6hdr *ip6 = (struct ipv6hdr *)((u8 *)(req + 1) + eth_len);
-	struct tcphdr *tcp = (struct tcphdr *)
-			      ((u8 *)(req + 1) + eth_len + ip_len);
-
-	if (ip->version == 4) {
-		pr_debug("%s saddr 0x%x daddr 0x%x sport %u dport %u\n",
-			 __func__,
-			 ntohl(ip->saddr), ntohl(ip->daddr),
-			 ntohs(tcp->source),
-			 ntohs(tcp->dest));
-		*iptype = 4;
-		memcpy(peer_ip, &ip->saddr, 4);
-		memcpy(local_ip, &ip->daddr, 4);
-	} else {
-		pr_debug("%s saddr %pI6 daddr %pI6 sport %u dport %u\n",
-			 __func__,
-			 ip6->saddr.s6_addr, ip6->daddr.s6_addr,
-			 ntohs(tcp->source),
-			 ntohs(tcp->dest));
-		*iptype = 6;
-		memcpy(peer_ip, ip6->saddr.s6_addr, 16);
-		memcpy(local_ip, ip6->daddr.s6_addr, 16);
-	}
-
-	*peer_port = tcp->source;
-	*local_port = tcp->dest;
-}
-
-static int
-cxgbit_our_interface(struct cxgbit_device *cdev, struct net_device *egress_dev)
-{
-	u8 i;
-
-	egress_dev = cxgbit_get_real_dev(egress_dev);
-	for (i = 0; i < cdev->lldi.nports; i++)
-		if (cdev->lldi.ports[i] == egress_dev)
-			return 1;
-	return 0;
-}
-
-static struct dst_entry *
-cxgbit_find_route6(struct cxgbit_device *cdev, __u8 *local_ip, __u8 *peer_ip,
-		   __be16 local_port, __be16 peer_port, u8 tos,
-		   __u32 sin6_scope_id)
-{
-	struct dst_entry *dst = NULL;
-
-	if (IS_ENABLED(CONFIG_IPV6)) {
-		struct flowi6 fl6;
-
-		memset(&fl6, 0, sizeof(fl6));
-		memcpy(&fl6.daddr, peer_ip, 16);
-		memcpy(&fl6.saddr, local_ip, 16);
-		if (ipv6_addr_type(&fl6.daddr) & IPV6_ADDR_LINKLOCAL)
-			fl6.flowi6_oif = sin6_scope_id;
-		dst = ip6_route_output(&init_net, NULL, &fl6);
-		if (!dst)
-			goto out;
-		if (!cxgbit_our_interface(cdev, ip6_dst_idev(dst)->dev) &&
-		    !(ip6_dst_idev(dst)->dev->flags & IFF_LOOPBACK)) {
-			dst_release(dst);
-			dst = NULL;
-		}
-	}
-out:
-	return dst;
-}
-
-static struct dst_entry *
-cxgbit_find_route(struct cxgbit_device *cdev, __be32 local_ip, __be32 peer_ip,
-		  __be16 local_port, __be16 peer_port, u8 tos)
-{
-	struct rtable *rt;
-	struct flowi4 fl4;
-	struct neighbour *n;
-
-	rt = ip_route_output_ports(&init_net, &fl4, NULL, peer_ip,
-				   local_ip,
-				   peer_port, local_port, IPPROTO_TCP,
-				   tos, 0);
-	if (IS_ERR(rt))
-		return NULL;
-	n = dst_neigh_lookup(&rt->dst, &peer_ip);
-	if (!n)
-		return NULL;
-	if (!cxgbit_our_interface(cdev, n->dev) &&
-	    !(n->dev->flags & IFF_LOOPBACK)) {
-		neigh_release(n);
-		dst_release(&rt->dst);
-		return NULL;
-	}
-	neigh_release(n);
-	return &rt->dst;
-}
-
 static void cxgbit_set_tcp_window(struct cxgbit_sock *csk, struct port_info *pi)
 {
 	unsigned int linkspeed;
@@ -1072,21 +947,14 @@ int cxgbit_ofld_send(struct cxgbit_device *cdev, struct sk_buff *skb)
 
 static void cxgbit_release_tid(struct cxgbit_device *cdev, u32 tid)
 {
-	struct cpl_tid_release *req;
-	unsigned int len = roundup(sizeof(*req), 16);
+	u32 len = roundup(sizeof(struct cpl_tid_release), 16);
 	struct sk_buff *skb;
 
 	skb = alloc_skb(len, GFP_ATOMIC);
 	if (!skb)
 		return;
 
-	req = (struct cpl_tid_release *)__skb_put(skb, len);
-	memset(req, 0, len);
-
-	INIT_TP_WR(req, tid);
-	OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(
-		   CPL_TID_RELEASE, tid));
-	set_wr_txq(skb, CPL_PRIORITY_SETUP, 0);
+	cxgb_mk_tid_release(skb, len, tid, 0);
 	cxgbit_ofld_send(cdev, skb);
 }
 
@@ -1108,20 +976,6 @@ cxgbit_l2t_send(struct cxgbit_device *cdev, struct sk_buff *skb,
 	return ret < 0 ? ret : 0;
 }
 
-static void
-cxgbit_best_mtu(const unsigned short *mtus, unsigned short mtu,
-		unsigned int *idx, int use_ts, int ipv6)
-{
-	unsigned short hdr_size = (ipv6 ? sizeof(struct ipv6hdr) :
-				   sizeof(struct iphdr)) +
-				   sizeof(struct tcphdr) +
-				   (use_ts ? round_up(TCPOLEN_TIMESTAMP,
-				    4) : 0);
-	unsigned short data_size = mtu - hdr_size;
-
-	cxgb4_best_aligned_mtu(mtus, hdr_size, data_size, 8, idx);
-}
-
 static void cxgbit_send_rx_credits(struct cxgbit_sock *csk, struct sk_buff *skb)
 {
 	if (csk->com.state != CSK_STATE_ESTABLISHED) {
@@ -1140,22 +994,18 @@ static void cxgbit_send_rx_credits(struct cxgbit_sock *csk, struct sk_buff *skb)
 int cxgbit_rx_data_ack(struct cxgbit_sock *csk)
 {
 	struct sk_buff *skb;
-	struct cpl_rx_data_ack *req;
-	unsigned int len = roundup(sizeof(*req), 16);
+	u32 len = roundup(sizeof(struct cpl_rx_data_ack), 16);
+	u32 credit_dack;
 
 	skb = alloc_skb(len, GFP_KERNEL);
 	if (!skb)
 		return -1;
 
-	req = (struct cpl_rx_data_ack *)__skb_put(skb, len);
-	memset(req, 0, len);
+	credit_dack = RX_DACK_CHANGE_F | RX_DACK_MODE_V(1) |
+		      RX_CREDITS_V(csk->rx_credits);
 
-	set_wr_txq(skb, CPL_PRIORITY_ACK, csk->ctrlq_idx);
-	INIT_TP_WR(req, csk->tid);
-	OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_RX_DATA_ACK,
-						    csk->tid));
-	req->credit_dack = cpu_to_be32(RX_DACK_CHANGE_F | RX_DACK_MODE_V(1) |
-				       RX_CREDITS_V(csk->rx_credits));
+	cxgb_mk_rx_data_ack(skb, len, csk->tid, csk->ctrlq_idx,
+			    credit_dack);
 
 	csk->rx_credits = 0;
 
@@ -1210,15 +1060,6 @@ out:
 	return -ENOMEM;
 }
 
-static u32 cxgbit_compute_wscale(u32 win)
-{
-	u32 wscale = 0;
-
-	while (wscale < 14 && (65535 << wscale) < win)
-		wscale++;
-	return wscale;
-}
-
 static void
 cxgbit_pass_accept_rpl(struct cxgbit_sock *csk, struct cpl_pass_accept_req *req)
 {
@@ -1246,10 +1087,10 @@ cxgbit_pass_accept_rpl(struct cxgbit_sock *csk, struct cpl_pass_accept_req *req)
 	INIT_TP_WR(rpl5, csk->tid);
 	OPCODE_TID(rpl5) = cpu_to_be32(MK_OPCODE_TID(CPL_PASS_ACCEPT_RPL,
 						     csk->tid));
-	cxgbit_best_mtu(csk->com.cdev->lldi.mtus, csk->mtu, &mtu_idx,
-			req->tcpopt.tstamp,
-			(csk->com.remote_addr.ss_family == AF_INET) ? 0 : 1);
-	wscale = cxgbit_compute_wscale(csk->rcv_win);
+	cxgb_best_mtu(csk->com.cdev->lldi.mtus, csk->mtu, &mtu_idx,
+		      req->tcpopt.tstamp,
+		      (csk->com.remote_addr.ss_family == AF_INET) ? 0 : 1);
+	wscale = cxgb_compute_wscale(csk->rcv_win);
 	/*
 	 * Specify the largest window that will fit in opt0. The
 	 * remainder will be specified in the rx_data_ack.
@@ -1340,8 +1181,8 @@ cxgbit_pass_accept_req(struct cxgbit_device *cdev, struct sk_buff *skb)
 		goto rel_skb;
 	}
 
-	cxgbit_get_tuple_info(req, &iptype, local_ip, peer_ip,
-			      &local_port, &peer_port);
+	cxgb_get_4tuple(req, cdev->lldi.adapter_type, &iptype, local_ip,
+			peer_ip, &local_port, &peer_port);
 
 	/* Find output route */
 	if (iptype == 4)  {
@@ -1350,21 +1191,23 @@ cxgbit_pass_accept_req(struct cxgbit_device *cdev, struct sk_buff *skb)
 			 , __func__, cnp, tid,
 			 local_ip, peer_ip, ntohs(local_port),
 			 ntohs(peer_port), peer_mss);
-		dst = cxgbit_find_route(cdev, *(__be32 *)local_ip,
-					*(__be32 *)peer_ip,
-					local_port, peer_port,
-					PASS_OPEN_TOS_G(ntohl(req->tos_stid)));
+		dst = cxgb_find_route(&cdev->lldi, cxgbit_get_real_dev,
+				      *(__be32 *)local_ip,
+				      *(__be32 *)peer_ip,
+				      local_port, peer_port,
+				      PASS_OPEN_TOS_G(ntohl(req->tos_stid)));
 	} else {
 		pr_debug("%s parent sock %p tid %u laddr %pI6 raddr %pI6 "
 			 "lport %d rport %d peer_mss %d\n"
 			 , __func__, cnp, tid,
 			 local_ip, peer_ip, ntohs(local_port),
 			 ntohs(peer_port), peer_mss);
-		dst = cxgbit_find_route6(cdev, local_ip, peer_ip,
-					 local_port, peer_port,
-					 PASS_OPEN_TOS_G(ntohl(req->tos_stid)),
-					 ((struct sockaddr_in6 *)
-					 &cnp->com.local_addr)->sin6_scope_id);
+		dst = cxgb_find_route6(&cdev->lldi, cxgbit_get_real_dev,
+				       local_ip, peer_ip,
+				       local_port, peer_port,
+				       PASS_OPEN_TOS_G(ntohl(req->tos_stid)),
+				       ((struct sockaddr_in6 *)
+					&cnp->com.local_addr)->sin6_scope_id);
 	}
 	if (!dst) {
 		pr_err("%s - failed to find dst entry!\n",
@@ -1795,16 +1638,15 @@ static void cxgbit_abort_req_rss(struct cxgbit_sock *csk, struct sk_buff *skb)
 {
 	struct cpl_abort_req_rss *hdr = cplhdr(skb);
 	unsigned int tid = GET_TID(hdr);
-	struct cpl_abort_rpl *rpl;
 	struct sk_buff *rpl_skb;
 	bool release = false;
 	bool wakeup_thread = false;
-	unsigned int len = roundup(sizeof(*rpl), 16);
+	u32 len = roundup(sizeof(struct cpl_abort_rpl), 16);
 
 	pr_debug("%s: csk %p; tid %u; state %d\n",
 		 __func__, csk, tid, csk->com.state);
 
-	if (cxgbit_is_neg_adv(hdr->status)) {
+	if (cxgb_is_neg_adv(hdr->status)) {
 		pr_err("%s: got neg advise %d on tid %u\n",
 		       __func__, hdr->status, tid);
 		goto rel_skb;
@@ -1839,14 +1681,8 @@ static void cxgbit_abort_req_rss(struct cxgbit_sock *csk, struct sk_buff *skb)
 		cxgbit_send_tx_flowc_wr(csk);
 
 	rpl_skb = __skb_dequeue(&csk->skbq);
-	set_wr_txq(skb, CPL_PRIORITY_DATA, csk->txq_idx);
-
-	rpl = (struct cpl_abort_rpl *)__skb_put(rpl_skb, len);
-	memset(rpl, 0, len);
 
-	INIT_TP_WR(rpl, csk->tid);
-	OPCODE_TID(rpl) = cpu_to_be32(MK_OPCODE_TID(CPL_ABORT_RPL, tid));
-	rpl->cmd = CPL_ABORT_NO_RST;
+	cxgb_mk_abort_rpl(rpl_skb, len, csk->tid, csk->txq_idx);
 	cxgbit_ofld_send(csk->com.cdev, rpl_skb);
 
 	if (wakeup_thread) {