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

Pull networking updates from David Miller:

 1) Support ipv6 checksum offload in sunvnet driver, from Shannon
    Nelson.

 2) Move to RB-tree instead of custom AVL code in inetpeer, from Eric
    Dumazet.

 3) Allow generic XDP to work on virtual devices, from John Fastabend.

 4) Add bpf device maps and XDP_REDIRECT, which can be used to build
    arbitrary switching frameworks using XDP. From John Fastabend.

 5) Remove UFO offloads from the tree, gave us little other than bugs.

 6) Remove the IPSEC flow cache, from Florian Westphal.

 7) Support ipv6 route offload in mlxsw driver.

 8) Support VF representors in bnxt_en, from Sathya Perla.

 9) Add support for forward error correction modes to ethtool, from
    Vidya Sagar Ravipati.

10) Add time filter for packet scheduler action dumping, from Jamal Hadi
    Salim.

11) Extend the zerocopy sendmsg() used by virtio and tap to regular
    sockets via MSG_ZEROCOPY. From Willem de Bruijn.

12) Significantly rework value tracking in the BPF verifier, from Edward
    Cree.

13) Add new jump instructions to eBPF, from Daniel Borkmann.

14) Rework rtnetlink plumbing so that operations can be run without
    taking the RTNL semaphore. From Florian Westphal.

15) Support XDP in tap driver, from Jason Wang.

16) Add 32-bit eBPF JIT for ARM, from Shubham Bansal.

17) Add Huawei hinic ethernet driver.

18) Allow to report MD5 keys in TCP inet_diag dumps, from Ivan
    Delalande.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1780 commits)
  i40e: point wb_desc at the nvm_wb_desc during i40e_read_nvm_aq
  i40e: avoid NVM acquire deadlock during NVM update
  drivers: net: xgene: Remove return statement from void function
  drivers: net: xgene: Configure tx/rx delay for ACPI
  drivers: net: xgene: Read tx/rx delay for ACPI
  rocker: fix kcalloc parameter order
  rds: Fix non-atomic operation on shared flag variable
  net: sched: don't use GFP_KERNEL under spin lock
  vhost_net: correctly check tx avail during rx busy polling
  net: mdio-mux: add mdio_mux parameter to mdio_mux_init()
  rxrpc: Make service connection lookup always check for retry
  net: stmmac: Delete dead code for MDIO registration
  gianfar: Fix Tx flow control deactivation
  cxgb4: Ignore MPS_TX_INT_CAUSE[Bubble] for T6
  cxgb4: Fix pause frame count in t4_get_port_stats
  cxgb4: fix memory leak
  tun: rename generic_xdp to skb_xdp
  tun: reserve extra headroom only when XDP is set
  net: dsa: bcm_sf2: Configure IMP port TC2QOS mapping
  net: dsa: bcm_sf2: Advertise number of egress queues
  ...

1 files changed, 32 insertions, 25 deletions

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 51390febd5e3b0..01130392b7c0f5 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -56,6 +56,8 @@
 #include <net/netfilter/nf_nat_helper.h>
 #include <net/netns/hash.h>
 
+#include "nf_internals.h"
+
 #define NF_CONNTRACK_VERSION	"0.5.0"
 
 int (*nfnetlink_parse_nat_setup_hook)(struct nf_conn *ct,
@@ -254,8 +256,8 @@ bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff,
 		       u_int16_t l3num,
 		       struct net *net, struct nf_conntrack_tuple *tuple)
 {
-	struct nf_conntrack_l3proto *l3proto;
-	struct nf_conntrack_l4proto *l4proto;
+	const struct nf_conntrack_l3proto *l3proto;
+	const struct nf_conntrack_l4proto *l4proto;
 	unsigned int protoff;
 	u_int8_t protonum;
 	int ret;
@@ -404,22 +406,19 @@ static void
 destroy_conntrack(struct nf_conntrack *nfct)
 {
 	struct nf_conn *ct = (struct nf_conn *)nfct;
-	struct nf_conntrack_l4proto *l4proto;
+	const struct nf_conntrack_l4proto *l4proto;
 
 	pr_debug("destroy_conntrack(%p)\n", ct);
-	NF_CT_ASSERT(atomic_read(&nfct->use) == 0);
+	WARN_ON(atomic_read(&nfct->use) != 0);
 
 	if (unlikely(nf_ct_is_template(ct))) {
 		nf_ct_tmpl_free(ct);
 		return;
 	}
-	rcu_read_lock();
 	l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
 	if (l4proto->destroy)
 		l4proto->destroy(ct);
 
-	rcu_read_unlock();
-
 	local_bh_disable();
 	/* Expectations will have been removed in clean_from_lists,
 	 * except TFTP can create an expectation on the first packet,
@@ -701,7 +700,7 @@ static int nf_ct_resolve_clash(struct net *net, struct sk_buff *skb,
 {
 	/* This is the conntrack entry already in hashes that won race. */
 	struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
-	struct nf_conntrack_l4proto *l4proto;
+	const struct nf_conntrack_l4proto *l4proto;
 
 	l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
 	if (l4proto->allow_clash &&
@@ -763,12 +762,11 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 	 * connections for unconfirmed conns.  But packet copies and
 	 * REJECT will give spurious warnings here.
 	 */
-	/* NF_CT_ASSERT(atomic_read(&ct->ct_general.use) == 1); */
 
 	/* No external references means no one else could have
 	 * confirmed us.
 	 */
-	NF_CT_ASSERT(!nf_ct_is_confirmed(ct));
+	WARN_ON(nf_ct_is_confirmed(ct));
 	pr_debug("Confirming conntrack %p\n", ct);
 	/* We have to check the DYING flag after unlink to prevent
 	 * a race against nf_ct_get_next_corpse() possibly called from
@@ -1090,7 +1088,7 @@ static void gc_worker(struct work_struct *work)
 
 static void conntrack_gc_work_init(struct conntrack_gc_work *gc_work)
 {
-	INIT_DELAYED_WORK(&gc_work->dwork, gc_worker);
+	INIT_DEFERRABLE_WORK(&gc_work->dwork, gc_worker);
 	gc_work->next_gc_run = HZ;
 	gc_work->exiting = false;
 }
@@ -1167,7 +1165,7 @@ void nf_conntrack_free(struct nf_conn *ct)
 	/* A freed object has refcnt == 0, that's
 	 * the golden rule for SLAB_TYPESAFE_BY_RCU
 	 */
-	NF_CT_ASSERT(atomic_read(&ct->ct_general.use) == 0);
+	WARN_ON(atomic_read(&ct->ct_general.use) != 0);
 
 	nf_ct_ext_destroy(ct);
 	nf_ct_ext_free(ct);
@@ -1183,8 +1181,8 @@ EXPORT_SYMBOL_GPL(nf_conntrack_free);
 static noinline struct nf_conntrack_tuple_hash *
 init_conntrack(struct net *net, struct nf_conn *tmpl,
 	       const struct nf_conntrack_tuple *tuple,
-	       struct nf_conntrack_l3proto *l3proto,
-	       struct nf_conntrack_l4proto *l4proto,
+	       const struct nf_conntrack_l3proto *l3proto,
+	       const struct nf_conntrack_l4proto *l4proto,
 	       struct sk_buff *skb,
 	       unsigned int dataoff, u32 hash)
 {
@@ -1295,8 +1293,8 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
 		  unsigned int dataoff,
 		  u_int16_t l3num,
 		  u_int8_t protonum,
-		  struct nf_conntrack_l3proto *l3proto,
-		  struct nf_conntrack_l4proto *l4proto)
+		  const struct nf_conntrack_l3proto *l3proto,
+		  const struct nf_conntrack_l4proto *l4proto)
 {
 	const struct nf_conntrack_zone *zone;
 	struct nf_conntrack_tuple tuple;
@@ -1351,10 +1349,10 @@ unsigned int
 nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
 		struct sk_buff *skb)
 {
+	const struct nf_conntrack_l3proto *l3proto;
+	const struct nf_conntrack_l4proto *l4proto;
 	struct nf_conn *ct, *tmpl;
 	enum ip_conntrack_info ctinfo;
-	struct nf_conntrack_l3proto *l3proto;
-	struct nf_conntrack_l4proto *l4proto;
 	unsigned int *timeouts;
 	unsigned int dataoff;
 	u_int8_t protonum;
@@ -1421,7 +1419,7 @@ repeat:
 	/* Decide what timeout policy we want to apply to this flow. */
 	timeouts = nf_ct_timeout_lookup(net, ct, l4proto);
 
-	ret = l4proto->packet(ct, skb, dataoff, ctinfo, pf, hooknum, timeouts);
+	ret = l4proto->packet(ct, skb, dataoff, ctinfo, pf, timeouts);
 	if (ret <= 0) {
 		/* Invalid: inverse of the return code tells
 		 * the netfilter core what to do */
@@ -1475,7 +1473,7 @@ void nf_conntrack_alter_reply(struct nf_conn *ct,
 	struct nf_conn_help *help = nfct_help(ct);
 
 	/* Should be unconfirmed, so not in hash table yet */
-	NF_CT_ASSERT(!nf_ct_is_confirmed(ct));
+	WARN_ON(nf_ct_is_confirmed(ct));
 
 	pr_debug("Altering reply tuple of %p to ", ct);
 	nf_ct_dump_tuple(newreply);
@@ -1497,7 +1495,7 @@ void __nf_ct_refresh_acct(struct nf_conn *ct,
 			  unsigned long extra_jiffies,
 			  int do_acct)
 {
-	NF_CT_ASSERT(skb);
+	WARN_ON(!skb);
 
 	/* Only update if this is not a fixed timeout */
 	if (test_bit(IPS_FIXED_TIMEOUT_BIT, &ct->status))
@@ -1695,6 +1693,18 @@ __nf_ct_unconfirmed_destroy(struct net *net)
 	}
 }
 
+void nf_ct_unconfirmed_destroy(struct net *net)
+{
+	might_sleep();
+
+	if (atomic_read(&net->ct.count) > 0) {
+		__nf_ct_unconfirmed_destroy(net);
+		nf_queue_nf_hook_drop(net);
+		synchronize_net();
+	}
+}
+EXPORT_SYMBOL_GPL(nf_ct_unconfirmed_destroy);
+
 void nf_ct_iterate_cleanup_net(struct net *net,
 			       int (*iter)(struct nf_conn *i, void *data),
 			       void *data, u32 portid, int report)
@@ -1706,14 +1716,10 @@ void nf_ct_iterate_cleanup_net(struct net *net,
 	if (atomic_read(&net->ct.count) == 0)
 		return;
 
-	__nf_ct_unconfirmed_destroy(net);
-
 	d.iter = iter;
 	d.data = data;
 	d.net = net;
 
-	synchronize_net();
-
 	nf_ct_iterate_cleanup(iter_net_only, &d, portid, report);
 }
 EXPORT_SYMBOL_GPL(nf_ct_iterate_cleanup_net);
@@ -1739,6 +1745,7 @@ nf_ct_iterate_destroy(int (*iter)(struct nf_conn *i, void *data), void *data)
 		if (atomic_read(&net->ct.count) == 0)
 			continue;
 		__nf_ct_unconfirmed_destroy(net);
+		nf_queue_nf_hook_drop(net);
 	}
 	rtnl_unlock();