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

Pull networking updates from David Miller:
 "Highlights:

   1) Support AES128-CCM ciphers in kTLS, from Vakul Garg.

   2) Add fib_sync_mem to control the amount of dirty memory we allow to
      queue up between synchronize RCU calls, from David Ahern.

   3) Make flow classifier more lockless, from Vlad Buslov.

   4) Add PHY downshift support to aquantia driver, from Heiner
      Kallweit.

   5) Add SKB cache for TCP rx and tx, from Eric Dumazet. This reduces
      contention on SLAB spinlocks in heavy RPC workloads.

   6) Partial GSO offload support in XFRM, from Boris Pismenny.

   7) Add fast link down support to ethtool, from Heiner Kallweit.

   8) Use siphash for IP ID generator, from Eric Dumazet.

   9) Pull nexthops even further out from ipv4/ipv6 routes and FIB
      entries, from David Ahern.

  10) Move skb->xmit_more into a per-cpu variable, from Florian
      Westphal.

  11) Improve eBPF verifier speed and increase maximum program size,
      from Alexei Starovoitov.

  12) Eliminate per-bucket spinlocks in rhashtable, and instead use bit
      spinlocks. From Neil Brown.

  13) Allow tunneling with GUE encap in ipvs, from Jacky Hu.

  14) Improve link partner cap detection in generic PHY code, from
      Heiner Kallweit.

  15) Add layer 2 encap support to bpf_skb_adjust_room(), from Alan
      Maguire.

  16) Remove SKB list implementation assumptions in SCTP, your's truly.

  17) Various cleanups, optimizations, and simplifications in r8169
      driver. From Heiner Kallweit.

  18) Add memory accounting on TX and RX path of SCTP, from Xin Long.

  19) Switch PHY drivers over to use dynamic featue detection, from
      Heiner Kallweit.

  20) Support flow steering without masking in dpaa2-eth, from Ioana
      Ciocoi.

  21) Implement ndo_get_devlink_port in netdevsim driver, from Jiri
      Pirko.

  22) Increase the strict parsing of current and future netlink
      attributes, also export such policies to userspace. From Johannes
      Berg.

  23) Allow DSA tag drivers to be modular, from Andrew Lunn.

  24) Remove legacy DSA probing support, also from Andrew Lunn.

  25) Allow ll_temac driver to be used on non-x86 platforms, from Esben
      Haabendal.

  26) Add a generic tracepoint for TX queue timeouts to ease debugging,
      from Cong Wang.

  27) More indirect call optimizations, from Paolo Abeni"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1763 commits)
  cxgb4: Fix error path in cxgb4_init_module
  net: phy: improve pause mode reporting in phy_print_status
  dt-bindings: net: Fix a typo in the phy-mode list for ethernet bindings
  net: macb: Change interrupt and napi enable order in open
  net: ll_temac: Improve error message on error IRQ
  net/sched: remove block pointer from common offload structure
  net: ethernet: support of_get_mac_address new ERR_PTR error
  net: usb: smsc: fix warning reported by kbuild test robot
  staging: octeon-ethernet: Fix of_get_mac_address ERR_PTR check
  net: dsa: support of_get_mac_address new ERR_PTR error
  net: dsa: sja1105: Fix status initialization in sja1105_get_ethtool_stats
  vrf: sit mtu should not be updated when vrf netdev is the link
  net: dsa: Fix error cleanup path in dsa_init_module
  l2tp: Fix possible NULL pointer dereference
  taprio: add null check on sched_nest to avoid potential null pointer dereference
  net: mvpp2: cls: fix less than zero check on a u32 variable
  net_sched: sch_fq: handle non connected flows
  net_sched: sch_fq: do not assume EDT packets are ordered
  net: hns3: use devm_kcalloc when allocating desc_cb
  net: hns3: some cleanup for struct hns3_enet_ring
  ...

1 files changed, 243 insertions, 37 deletions

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index a6b58df7a70f..410233c5681e 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -27,10 +27,14 @@
 #include <linux/cpu.h>
 #include <linux/audit.h>
 #include <linux/rhashtable.h>
+#include <linux/if_tunnel.h>
 #include <net/dst.h>
 #include <net/flow.h>
 #include <net/xfrm.h>
 #include <net/ip.h>
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
+#include <net/mip6.h>
+#endif
 #ifdef CONFIG_XFRM_STATISTICS
 #include <net/snmp.h>
 #endif
@@ -2450,18 +2454,10 @@ xfrm_tmpl_resolve(struct xfrm_policy **pols, int npols, const struct flowi *fl,
 
 static int xfrm_get_tos(const struct flowi *fl, int family)
 {
-	const struct xfrm_policy_afinfo *afinfo;
-	int tos;
+	if (family == AF_INET)
+		return IPTOS_RT_MASK & fl->u.ip4.flowi4_tos;
 
-	afinfo = xfrm_policy_get_afinfo(family);
-	if (!afinfo)
-		return 0;
-
-	tos = afinfo->get_tos(fl);
-
-	rcu_read_unlock();
-
-	return tos;
+	return 0;
 }
 
 static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family)
@@ -2499,21 +2495,14 @@ static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family)
 	return xdst;
 }
 
-static inline int xfrm_init_path(struct xfrm_dst *path, struct dst_entry *dst,
-				 int nfheader_len)
+static void xfrm_init_path(struct xfrm_dst *path, struct dst_entry *dst,
+			   int nfheader_len)
 {
-	const struct xfrm_policy_afinfo *afinfo =
-		xfrm_policy_get_afinfo(dst->ops->family);
-	int err;
-
-	if (!afinfo)
-		return -EINVAL;
-
-	err = afinfo->init_path(path, dst, nfheader_len);
-
-	rcu_read_unlock();
-
-	return err;
+	if (dst->ops->family == AF_INET6) {
+		struct rt6_info *rt = (struct rt6_info *)dst;
+		path->path_cookie = rt6_get_cookie(rt);
+		path->u.rt6.rt6i_nfheader_len = nfheader_len;
+	}
 }
 
 static inline int xfrm_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
@@ -2545,10 +2534,11 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
 					    const struct flowi *fl,
 					    struct dst_entry *dst)
 {
+	const struct xfrm_state_afinfo *afinfo;
+	const struct xfrm_mode *inner_mode;
 	struct net *net = xp_net(policy);
 	unsigned long now = jiffies;
 	struct net_device *dev;
-	struct xfrm_mode *inner_mode;
 	struct xfrm_dst *xdst_prev = NULL;
 	struct xfrm_dst *xdst0 = NULL;
 	int i = 0;
@@ -2594,7 +2584,7 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
 				goto put_states;
 			}
 		} else
-			inner_mode = xfrm[i]->inner_mode;
+			inner_mode = &xfrm[i]->inner_mode;
 
 		xdst->route = dst;
 		dst_copy_metrics(dst1, dst);
@@ -2622,7 +2612,14 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
 		dst1->lastuse = now;
 
 		dst1->input = dst_discard;
-		dst1->output = inner_mode->afinfo->output;
+
+		rcu_read_lock();
+		afinfo = xfrm_state_afinfo_get_rcu(inner_mode->family);
+		if (likely(afinfo))
+			dst1->output = afinfo->output;
+		else
+			dst1->output = dst_discard_out;
+		rcu_read_unlock();
 
 		xdst_prev = xdst;
 
@@ -3263,20 +3260,229 @@ xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int star
 	return start;
 }
 
+static void
+decode_session4(struct sk_buff *skb, struct flowi *fl, bool reverse)
+{
+	const struct iphdr *iph = ip_hdr(skb);
+	u8 *xprth = skb_network_header(skb) + iph->ihl * 4;
+	struct flowi4 *fl4 = &fl->u.ip4;
+	int oif = 0;
+
+	if (skb_dst(skb))
+		oif = skb_dst(skb)->dev->ifindex;
+
+	memset(fl4, 0, sizeof(struct flowi4));
+	fl4->flowi4_mark = skb->mark;
+	fl4->flowi4_oif = reverse ? skb->skb_iif : oif;
+
+	if (!ip_is_fragment(iph)) {
+		switch (iph->protocol) {
+		case IPPROTO_UDP:
+		case IPPROTO_UDPLITE:
+		case IPPROTO_TCP:
+		case IPPROTO_SCTP:
+		case IPPROTO_DCCP:
+			if (xprth + 4 < skb->data ||
+			    pskb_may_pull(skb, xprth + 4 - skb->data)) {
+				__be16 *ports;
+
+				xprth = skb_network_header(skb) + iph->ihl * 4;
+				ports = (__be16 *)xprth;
+
+				fl4->fl4_sport = ports[!!reverse];
+				fl4->fl4_dport = ports[!reverse];
+			}
+			break;
+		case IPPROTO_ICMP:
+			if (xprth + 2 < skb->data ||
+			    pskb_may_pull(skb, xprth + 2 - skb->data)) {
+				u8 *icmp;
+
+				xprth = skb_network_header(skb) + iph->ihl * 4;
+				icmp = xprth;
+
+				fl4->fl4_icmp_type = icmp[0];
+				fl4->fl4_icmp_code = icmp[1];
+			}
+			break;
+		case IPPROTO_ESP:
+			if (xprth + 4 < skb->data ||
+			    pskb_may_pull(skb, xprth + 4 - skb->data)) {
+				__be32 *ehdr;
+
+				xprth = skb_network_header(skb) + iph->ihl * 4;
+				ehdr = (__be32 *)xprth;
+
+				fl4->fl4_ipsec_spi = ehdr[0];
+			}
+			break;
+		case IPPROTO_AH:
+			if (xprth + 8 < skb->data ||
+			    pskb_may_pull(skb, xprth + 8 - skb->data)) {
+				__be32 *ah_hdr;
+
+				xprth = skb_network_header(skb) + iph->ihl * 4;
+				ah_hdr = (__be32 *)xprth;
+
+				fl4->fl4_ipsec_spi = ah_hdr[1];
+			}
+			break;
+		case IPPROTO_COMP:
+			if (xprth + 4 < skb->data ||
+			    pskb_may_pull(skb, xprth + 4 - skb->data)) {
+				__be16 *ipcomp_hdr;
+
+				xprth = skb_network_header(skb) + iph->ihl * 4;
+				ipcomp_hdr = (__be16 *)xprth;
+
+				fl4->fl4_ipsec_spi = htonl(ntohs(ipcomp_hdr[1]));
+			}
+			break;
+		case IPPROTO_GRE:
+			if (xprth + 12 < skb->data ||
+			    pskb_may_pull(skb, xprth + 12 - skb->data)) {
+				__be16 *greflags;
+				__be32 *gre_hdr;
+
+				xprth = skb_network_header(skb) + iph->ihl * 4;
+				greflags = (__be16 *)xprth;
+				gre_hdr = (__be32 *)xprth;
+
+				if (greflags[0] & GRE_KEY) {
+					if (greflags[0] & GRE_CSUM)
+						gre_hdr++;
+					fl4->fl4_gre_key = gre_hdr[1];
+				}
+			}
+			break;
+		default:
+			fl4->fl4_ipsec_spi = 0;
+			break;
+		}
+	}
+	fl4->flowi4_proto = iph->protocol;
+	fl4->daddr = reverse ? iph->saddr : iph->daddr;
+	fl4->saddr = reverse ? iph->daddr : iph->saddr;
+	fl4->flowi4_tos = iph->tos;
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+static void
+decode_session6(struct sk_buff *skb, struct flowi *fl, bool reverse)
+{
+	struct flowi6 *fl6 = &fl->u.ip6;
+	int onlyproto = 0;
+	const struct ipv6hdr *hdr = ipv6_hdr(skb);
+	u32 offset = sizeof(*hdr);
+	struct ipv6_opt_hdr *exthdr;
+	const unsigned char *nh = skb_network_header(skb);
+	u16 nhoff = IP6CB(skb)->nhoff;
+	int oif = 0;
+	u8 nexthdr;
+
+	if (!nhoff)
+		nhoff = offsetof(struct ipv6hdr, nexthdr);
+
+	nexthdr = nh[nhoff];
+
+	if (skb_dst(skb))
+		oif = skb_dst(skb)->dev->ifindex;
+
+	memset(fl6, 0, sizeof(struct flowi6));
+	fl6->flowi6_mark = skb->mark;
+	fl6->flowi6_oif = reverse ? skb->skb_iif : oif;
+
+	fl6->daddr = reverse ? hdr->saddr : hdr->daddr;
+	fl6->saddr = reverse ? hdr->daddr : hdr->saddr;
+
+	while (nh + offset + sizeof(*exthdr) < skb->data ||
+	       pskb_may_pull(skb, nh + offset + sizeof(*exthdr) - skb->data)) {
+		nh = skb_network_header(skb);
+		exthdr = (struct ipv6_opt_hdr *)(nh + offset);
+
+		switch (nexthdr) {
+		case NEXTHDR_FRAGMENT:
+			onlyproto = 1;
+			/* fall through */
+		case NEXTHDR_ROUTING:
+		case NEXTHDR_HOP:
+		case NEXTHDR_DEST:
+			offset += ipv6_optlen(exthdr);
+			nexthdr = exthdr->nexthdr;
+			exthdr = (struct ipv6_opt_hdr *)(nh + offset);
+			break;
+		case IPPROTO_UDP:
+		case IPPROTO_UDPLITE:
+		case IPPROTO_TCP:
+		case IPPROTO_SCTP:
+		case IPPROTO_DCCP:
+			if (!onlyproto && (nh + offset + 4 < skb->data ||
+			     pskb_may_pull(skb, nh + offset + 4 - skb->data))) {
+				__be16 *ports;
+
+				nh = skb_network_header(skb);
+				ports = (__be16 *)(nh + offset);
+				fl6->fl6_sport = ports[!!reverse];
+				fl6->fl6_dport = ports[!reverse];
+			}
+			fl6->flowi6_proto = nexthdr;
+			return;
+		case IPPROTO_ICMPV6:
+			if (!onlyproto && (nh + offset + 2 < skb->data ||
+			    pskb_may_pull(skb, nh + offset + 2 - skb->data))) {
+				u8 *icmp;
+
+				nh = skb_network_header(skb);
+				icmp = (u8 *)(nh + offset);
+				fl6->fl6_icmp_type = icmp[0];
+				fl6->fl6_icmp_code = icmp[1];
+			}
+			fl6->flowi6_proto = nexthdr;
+			return;
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
+		case IPPROTO_MH:
+			offset += ipv6_optlen(exthdr);
+			if (!onlyproto && (nh + offset + 3 < skb->data ||
+			    pskb_may_pull(skb, nh + offset + 3 - skb->data))) {
+				struct ip6_mh *mh;
+
+				nh = skb_network_header(skb);
+				mh = (struct ip6_mh *)(nh + offset);
+				fl6->fl6_mh_type = mh->ip6mh_type;
+			}
+			fl6->flowi6_proto = nexthdr;
+			return;
+#endif
+		/* XXX Why are there these headers? */
+		case IPPROTO_AH:
+		case IPPROTO_ESP:
+		case IPPROTO_COMP:
+		default:
+			fl6->fl6_ipsec_spi = 0;
+			fl6->flowi6_proto = nexthdr;
+			return;
+		}
+	}
+}
+#endif
+
 int __xfrm_decode_session(struct sk_buff *skb, struct flowi *fl,
 			  unsigned int family, int reverse)
 {
-	const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
-	int err;
-
-	if (unlikely(afinfo == NULL))
+	switch (family) {
+	case AF_INET:
+		decode_session4(skb, fl, reverse);
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case AF_INET6:
+		decode_session6(skb, fl, reverse);
+		break;
+#endif
+	default:
 		return -EAFNOSUPPORT;
+	}
 
-	afinfo->decode_session(skb, fl, reverse);
-
-	err = security_xfrm_decode_session(skb, &fl->flowi_secid);
-	rcu_read_unlock();
-	return err;
+	return security_xfrm_decode_session(skb, &fl->flowi_secid);
 }
 EXPORT_SYMBOL(__xfrm_decode_session);