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

Pull networking updates from David Miller:

 1) Significantly shrink the core networking routing structures. Result
    of http://vger.kernel.org/~davem/seoul2017_netdev_keynote.pdf

 2) Add netdevsim driver for testing various offloads, from Jakub
    Kicinski.

 3) Support cross-chip FDB operations in DSA, from Vivien Didelot.

 4) Add a 2nd listener hash table for TCP, similar to what was done for
    UDP. From Martin KaFai Lau.

 5) Add eBPF based queue selection to tun, from Jason Wang.

 6) Lockless qdisc support, from John Fastabend.

 7) SCTP stream interleave support, from Xin Long.

 8) Smoother TCP receive autotuning, from Eric Dumazet.

 9) Lots of erspan tunneling enhancements, from William Tu.

10) Add true function call support to BPF, from Alexei Starovoitov.

11) Add explicit support for GRO HW offloading, from Michael Chan.

12) Support extack generation in more netlink subsystems. From Alexander
    Aring, Quentin Monnet, and Jakub Kicinski.

13) Add 1000BaseX, flow control, and EEE support to mvneta driver. From
    Russell King.

14) Add flow table abstraction to netfilter, from Pablo Neira Ayuso.

15) Many improvements and simplifications to the NFP driver bpf JIT,
    from Jakub Kicinski.

16) Support for ipv6 non-equal cost multipath routing, from Ido
    Schimmel.

17) Add resource abstration to devlink, from Arkadi Sharshevsky.

18) Packet scheduler classifier shared filter block support, from Jiri
    Pirko.

19) Avoid locking in act_csum, from Davide Caratti.

20) devinet_ioctl() simplifications from Al viro.

21) More TCP bpf improvements from Lawrence Brakmo.

22) Add support for onlink ipv6 route flag, similar to ipv4, from David
    Ahern.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1925 commits)
  tls: Add support for encryption using async offload accelerator
  ip6mr: fix stale iterator
  net/sched: kconfig: Remove blank help texts
  openvswitch: meter: Use 64-bit arithmetic instead of 32-bit
  tcp_nv: fix potential integer overflow in tcpnv_acked
  r8169: fix RTL8168EP take too long to complete driver initialization.
  qmi_wwan: Add support for Quectel EP06
  rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK
  ipmr: Fix ptrdiff_t print formatting
  ibmvnic: Wait for device response when changing MAC
  qlcnic: fix deadlock bug
  tcp: release sk_frag.page in tcp_disconnect
  ipv4: Get the address of interface correctly.
  net_sched: gen_estimator: fix lockdep splat
  net: macb: Handle HRESP error
  net/mlx5e: IPoIB, Fix copy-paste bug in flow steering refactoring
  ipv6: addrconf: break critical section in addrconf_verify_rtnl()
  ipv6: change route cache aging logic
  i40e/i40evf: Update DESC_NEEDED value to reflect larger value
  bnxt_en: cleanup DIM work on device shutdown
  ...

1 files changed, 72 insertions, 65 deletions

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index bd6b0e7..7a23078 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -54,7 +54,7 @@ static struct xfrm_policy_afinfo const __rcu *xfrm_policy_afinfo[AF_INET6 + 1]
 static struct kmem_cache *xfrm_dst_cache __read_mostly;
 static __read_mostly seqcount_t xfrm_policy_hash_generation;
 
-static void xfrm_init_pmtu(struct dst_entry *dst);
+static void xfrm_init_pmtu(struct xfrm_dst **bundle, int nr);
 static int stale_bundle(struct dst_entry *dst);
 static int xfrm_bundle_ok(struct xfrm_dst *xdst);
 static void xfrm_policy_queue_process(struct timer_list *t);
@@ -1256,7 +1256,7 @@ EXPORT_SYMBOL(xfrm_policy_delete);
 
 int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol)
 {
-	struct net *net = xp_net(pol);
+	struct net *net = sock_net(sk);
 	struct xfrm_policy *old_pol;
 
 #ifdef CONFIG_XFRM_SUB_POLICY
@@ -1543,7 +1543,9 @@ static inline int xfrm_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
  */
 
 static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
-					    struct xfrm_state **xfrm, int nx,
+					    struct xfrm_state **xfrm,
+					    struct xfrm_dst **bundle,
+					    int nx,
 					    const struct flowi *fl,
 					    struct dst_entry *dst)
 {
@@ -1551,8 +1553,8 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
 	unsigned long now = jiffies;
 	struct net_device *dev;
 	struct xfrm_mode *inner_mode;
-	struct dst_entry *dst_prev = NULL;
-	struct dst_entry *dst0 = NULL;
+	struct xfrm_dst *xdst_prev = NULL;
+	struct xfrm_dst *xdst0 = NULL;
 	int i = 0;
 	int err;
 	int header_len = 0;
@@ -1578,13 +1580,14 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
 			goto put_states;
 		}
 
-		if (!dst_prev)
-			dst0 = dst1;
+		bundle[i] = xdst;
+		if (!xdst_prev)
+			xdst0 = xdst;
 		else
 			/* Ref count is taken during xfrm_alloc_dst()
 			 * No need to do dst_clone() on dst1
 			 */
-			dst_prev->child = dst1;
+			xfrm_dst_set_child(xdst_prev, &xdst->u.dst);
 
 		if (xfrm[i]->sel.family == AF_UNSPEC) {
 			inner_mode = xfrm_ip2inner_mode(xfrm[i],
@@ -1621,8 +1624,7 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
 		dst1->input = dst_discard;
 		dst1->output = inner_mode->afinfo->output;
 
-		dst1->next = dst_prev;
-		dst_prev = dst1;
+		xdst_prev = xdst;
 
 		header_len += xfrm[i]->props.header_len;
 		if (xfrm[i]->type->flags & XFRM_TYPE_NON_FRAGMENT)
@@ -1630,40 +1632,39 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
 		trailer_len += xfrm[i]->props.trailer_len;
 	}
 
-	dst_prev->child = dst;
-	dst0->path = dst;
+	xfrm_dst_set_child(xdst_prev, dst);
+	xdst0->path = dst;
 
 	err = -ENODEV;
 	dev = dst->dev;
 	if (!dev)
 		goto free_dst;
 
-	xfrm_init_path((struct xfrm_dst *)dst0, dst, nfheader_len);
-	xfrm_init_pmtu(dst_prev);
-
-	for (dst_prev = dst0; dst_prev != dst; dst_prev = dst_prev->child) {
-		struct xfrm_dst *xdst = (struct xfrm_dst *)dst_prev;
+	xfrm_init_path(xdst0, dst, nfheader_len);
+	xfrm_init_pmtu(bundle, nx);
 
-		err = xfrm_fill_dst(xdst, dev, fl);
+	for (xdst_prev = xdst0; xdst_prev != (struct xfrm_dst *)dst;
+	     xdst_prev = (struct xfrm_dst *) xfrm_dst_child(&xdst_prev->u.dst)) {
+		err = xfrm_fill_dst(xdst_prev, dev, fl);
 		if (err)
 			goto free_dst;
 
-		dst_prev->header_len = header_len;
-		dst_prev->trailer_len = trailer_len;
-		header_len -= xdst->u.dst.xfrm->props.header_len;
-		trailer_len -= xdst->u.dst.xfrm->props.trailer_len;
+		xdst_prev->u.dst.header_len = header_len;
+		xdst_prev->u.dst.trailer_len = trailer_len;
+		header_len -= xdst_prev->u.dst.xfrm->props.header_len;
+		trailer_len -= xdst_prev->u.dst.xfrm->props.trailer_len;
 	}
 
 out:
-	return dst0;
+	return &xdst0->u.dst;
 
 put_states:
 	for (; i < nx; i++)
 		xfrm_state_put(xfrm[i]);
 free_dst:
-	if (dst0)
-		dst_release_immediate(dst0);
-	dst0 = ERR_PTR(err);
+	if (xdst0)
+		dst_release_immediate(&xdst0->u.dst);
+	xdst0 = ERR_PTR(err);
 	goto out;
 }
 
@@ -1807,7 +1808,7 @@ static bool xfrm_xdst_can_reuse(struct xfrm_dst *xdst,
 	for (i = 0; i < num; i++) {
 		if (!dst || dst->xfrm != xfrm[i])
 			return false;
-		dst = dst->child;
+		dst = xfrm_dst_child(dst);
 	}
 
 	return xfrm_bundle_ok(xdst);
@@ -1820,6 +1821,7 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols,
 {
 	struct net *net = xp_net(pols[0]);
 	struct xfrm_state *xfrm[XFRM_MAX_DEPTH];
+	struct xfrm_dst *bundle[XFRM_MAX_DEPTH];
 	struct xfrm_dst *xdst, *old;
 	struct dst_entry *dst;
 	int err;
@@ -1848,7 +1850,7 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols,
 
 	old = xdst;
 
-	dst = xfrm_bundle_create(pols[0], xfrm, err, fl, dst_orig);
+	dst = xfrm_bundle_create(pols[0], xfrm, bundle, err, fl, dst_orig);
 	if (IS_ERR(dst)) {
 		XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLEGENERROR);
 		return ERR_CAST(dst);
@@ -1888,8 +1890,8 @@ static void xfrm_policy_queue_process(struct timer_list *t)
 	xfrm_decode_session(skb, &fl, dst->ops->family);
 	spin_unlock(&pq->hold_queue.lock);
 
-	dst_hold(dst->path);
-	dst = xfrm_lookup(net, dst->path, &fl, sk, 0);
+	dst_hold(xfrm_dst_path(dst));
+	dst = xfrm_lookup(net, xfrm_dst_path(dst), &fl, sk, 0);
 	if (IS_ERR(dst))
 		goto purge_queue;
 
@@ -1918,8 +1920,8 @@ static void xfrm_policy_queue_process(struct timer_list *t)
 		skb = __skb_dequeue(&list);
 
 		xfrm_decode_session(skb, &fl, skb_dst(skb)->ops->family);
-		dst_hold(skb_dst(skb)->path);
-		dst = xfrm_lookup(net, skb_dst(skb)->path, &fl, skb->sk, 0);
+		dst_hold(xfrm_dst_path(skb_dst(skb)));
+		dst = xfrm_lookup(net, xfrm_dst_path(skb_dst(skb)), &fl, skb->sk, 0);
 		if (IS_ERR(dst)) {
 			kfree_skb(skb);
 			continue;
@@ -2020,8 +2022,8 @@ static struct xfrm_dst *xfrm_create_dummy_bundle(struct net *net,
 	dst1->output = xdst_queue_output;
 
 	dst_hold(dst);
-	dst1->child = dst;
-	dst1->path = dst;
+	xfrm_dst_set_child(xdst, dst);
+	xdst->path = dst;
 
 	xfrm_init_path((struct xfrm_dst *)dst1, dst, 0);
 
@@ -2590,7 +2592,7 @@ static int stale_bundle(struct dst_entry *dst)
 
 void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev)
 {
-	while ((dst = dst->child) && dst->xfrm && dst->dev == dev) {
+	while ((dst = xfrm_dst_child(dst)) && dst->xfrm && dst->dev == dev) {
 		dst->dev = dev_net(dev)->loopback_dev;
 		dev_hold(dst->dev);
 		dev_put(dev);
@@ -2614,13 +2616,15 @@ static struct dst_entry *xfrm_negative_advice(struct dst_entry *dst)
 	return dst;
 }
 
-static void xfrm_init_pmtu(struct dst_entry *dst)
+static void xfrm_init_pmtu(struct xfrm_dst **bundle, int nr)
 {
-	do {
-		struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
+	while (nr--) {
+		struct xfrm_dst *xdst = bundle[nr];
 		u32 pmtu, route_mtu_cached;
+		struct dst_entry *dst;
 
-		pmtu = dst_mtu(dst->child);
+		dst = &xdst->u.dst;
+		pmtu = dst_mtu(xfrm_dst_child(dst));
 		xdst->child_mtu_cached = pmtu;
 
 		pmtu = xfrm_state_mtu(dst->xfrm, pmtu);
@@ -2632,7 +2636,7 @@ static void xfrm_init_pmtu(struct dst_entry *dst)
 			pmtu = route_mtu_cached;
 
 		dst_metric_set(dst, RTAX_MTU, pmtu);
-	} while ((dst = dst->next));
+	}
 }
 
 /* Check that the bundle accepts the flow and its components are
@@ -2641,19 +2645,20 @@ static void xfrm_init_pmtu(struct dst_entry *dst)
 
 static int xfrm_bundle_ok(struct xfrm_dst *first)
 {
+	struct xfrm_dst *bundle[XFRM_MAX_DEPTH];
 	struct dst_entry *dst = &first->u.dst;
-	struct xfrm_dst *last;
+	struct xfrm_dst *xdst;
+	int start_from, nr;
 	u32 mtu;
 
-	if (!dst_check(dst->path, ((struct xfrm_dst *)dst)->path_cookie) ||
+	if (!dst_check(xfrm_dst_path(dst), ((struct xfrm_dst *)dst)->path_cookie) ||
 	    (dst->dev && !netif_running(dst->dev)))
 		return 0;
 
 	if (dst->flags & DST_XFRM_QUEUE)
 		return 1;
 
-	last = NULL;
-
+	start_from = nr = 0;
 	do {
 		struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
 
@@ -2665,9 +2670,11 @@ static int xfrm_bundle_ok(struct xfrm_dst *first)
 		    xdst->policy_genid != atomic_read(&xdst->pols[0]->genid))
 			return 0;
 
-		mtu = dst_mtu(dst->child);
+		bundle[nr++] = xdst;
+
+		mtu = dst_mtu(xfrm_dst_child(dst));
 		if (xdst->child_mtu_cached != mtu) {
-			last = xdst;
+			start_from = nr;
 			xdst->child_mtu_cached = mtu;
 		}
 
@@ -2675,30 +2682,30 @@ static int xfrm_bundle_ok(struct xfrm_dst *first)
 			return 0;
 		mtu = dst_mtu(xdst->route);
 		if (xdst->route_mtu_cached != mtu) {
-			last = xdst;
+			start_from = nr;
 			xdst->route_mtu_cached = mtu;
 		}
 
-		dst = dst->child;
+		dst = xfrm_dst_child(dst);
 	} while (dst->xfrm);
 
-	if (likely(!last))
+	if (likely(!start_from))
 		return 1;
 
-	mtu = last->child_mtu_cached;
-	for (;;) {
-		dst = &last->u.dst;
+	xdst = bundle[start_from - 1];
+	mtu = xdst->child_mtu_cached;
+	while (start_from--) {
+		dst = &xdst->u.dst;
 
 		mtu = xfrm_state_mtu(dst->xfrm, mtu);
-		if (mtu > last->route_mtu_cached)
-			mtu = last->route_mtu_cached;
+		if (mtu > xdst->route_mtu_cached)
+			mtu = xdst->route_mtu_cached;
 		dst_metric_set(dst, RTAX_MTU, mtu);
-
-		if (last == first)
+		if (!start_from)
 			break;
 
-		last = (struct xfrm_dst *)last->u.dst.next;
-		last->child_mtu_cached = mtu;
+		xdst = bundle[start_from - 1];
+		xdst->child_mtu_cached = mtu;
 	}
 
 	return 1;
@@ -2706,22 +2713,20 @@ static int xfrm_bundle_ok(struct xfrm_dst *first)
 
 static unsigned int xfrm_default_advmss(const struct dst_entry *dst)
 {
-	return dst_metric_advmss(dst->path);
+	return dst_metric_advmss(xfrm_dst_path(dst));
 }
 
 static unsigned int xfrm_mtu(const struct dst_entry *dst)
 {
 	unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
 
-	return mtu ? : dst_mtu(dst->path);
+	return mtu ? : dst_mtu(xfrm_dst_path(dst));
 }
 
 static const void *xfrm_get_dst_nexthop(const struct dst_entry *dst,
 					const void *daddr)
 {
-	const struct dst_entry *path = dst->path;
-
-	for (; dst != path; dst = dst->child) {
+	while (dst->xfrm) {
 		const struct xfrm_state *xfrm = dst->xfrm;
 
 		if (xfrm->props.mode == XFRM_MODE_TRANSPORT)
@@ -2730,6 +2735,8 @@ static const void *xfrm_get_dst_nexthop(const struct dst_entry *dst,
 			daddr = xfrm->coaddr;
 		else if (!(xfrm->type->flags & XFRM_TYPE_LOCAL_COADDR))
 			daddr = &xfrm->id.daddr;
+
+		dst = xfrm_dst_child(dst);
 	}
 	return daddr;
 }
@@ -2738,7 +2745,7 @@ static struct neighbour *xfrm_neigh_lookup(const struct dst_entry *dst,
 					   struct sk_buff *skb,
 					   const void *daddr)
 {
-	const struct dst_entry *path = dst->path;
+	const struct dst_entry *path = xfrm_dst_path(dst);
 
 	if (!skb)
 		daddr = xfrm_get_dst_nexthop(dst, daddr);
@@ -2747,7 +2754,7 @@ static struct neighbour *xfrm_neigh_lookup(const struct dst_entry *dst,
 
 static void xfrm_confirm_neigh(const struct dst_entry *dst, const void *daddr)
 {
-	const struct dst_entry *path = dst->path;
+	const struct dst_entry *path = xfrm_dst_path(dst);
 
 	daddr = xfrm_get_dst_nexthop(dst, daddr);
 	path->ops->confirm_neigh(path, daddr);