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

Pull networking fixes from David Miller:

 1) Verify netlink attributes properly in nf_queue, from Eric Dumazet.

 2) Need to bump memory lock rlimit for test_sockmap bpf test, from
    Yonghong Song.

 3) Fix VLAN handling in lan78xx driver, from Dave Stevenson.

 4) Fix uninitialized read in nf_log, from Jann Horn.

 5) Fix raw command length parsing in mlx5, from Alex Vesker.

 6) Cleanup loopback RDS connections upon netns deletion, from Sowmini
    Varadhan.

 7) Fix regressions in FIB rule matching during create, from Jason A.
    Donenfeld and Roopa Prabhu.

 8) Fix mpls ether type detection in nfp, from Pieter Jansen van Vuuren.

 9) More bpfilter build fixes/adjustments from Masahiro Yamada.

10) Fix XDP_{TX,REDIRECT} flushing in various drivers, from Jesper
    Dangaard Brouer.

11) fib_tests.sh file permissions were broken, from Shuah Khan.

12) Make sure BH/preemption is disabled in data path of mac80211, from
    Denis Kenzior.

13) Don't ignore nla_parse_nested() return values in nl80211, from
    Johannes berg.

14) Properly account sock objects ot kmemcg, from Shakeel Butt.

15) Adjustments to setting bpf program permissions to read-only, from
    Daniel Borkmann.

16) TCP Fast Open key endianness was broken, it always took on the host
    endiannness. Whoops. Explicitly make it little endian. From Yuching
    Cheng.

17) Fix prefix route setting for link local addresses in ipv6, from
    David Ahern.

18) Potential Spectre v1 in zatm driver, from Gustavo A. R. Silva.

19) Various bpf sockmap fixes, from John Fastabend.

20) Use after free for GRO with ESP, from Sabrina Dubroca.

21) Passing bogus flags to crypto_alloc_shash() in ipv6 SR code, from
    Eric Biggers.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (87 commits)
  qede: Adverstise software timestamp caps when PHC is not available.
  qed: Fix use of incorrect size in memcpy call.
  qed: Fix setting of incorrect eswitch mode.
  qed: Limit msix vectors in kdump kernel to the minimum required count.
  ipvlan: call dev_change_flags when ipvlan mode is reset
  ipv6: sr: fix passing wrong flags to crypto_alloc_shash()
  net: fix use-after-free in GRO with ESP
  tcp: prevent bogus FRTO undos with non-SACK flows
  bpf: sockhash, add release routine
  bpf: sockhash fix omitted bucket lock in sock_close
  bpf: sockmap, fix smap_list_map_remove when psock is in many maps
  bpf: sockmap, fix crash when ipv6 sock is added
  net: fib_rules: bring back rule_exists to match rule during add
  hv_netvsc: split sub-channel setup into async and sync
  net: use dev_change_tx_queue_len() for SIOCSIFTXQLEN
  atm: zatm: Fix potential Spectre v1
  s390/qeth: consistently re-enable device features
  s390/qeth: don't clobber buffer on async TX completion
  s390/qeth: avoid using is_multicast_ether_addr_64bits on (u8 *)[6]
  s390/qeth: fix race when setting MAC address
  ...

5 files changed, 141 insertions, 46 deletions

diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index a04e1e88bf3a..50537ff961a7 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -285,16 +285,9 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
 		if (ifr->ifr_qlen < 0)
 			return -EINVAL;
 		if (dev->tx_queue_len ^ ifr->ifr_qlen) {
-			unsigned int orig_len = dev->tx_queue_len;
-
-			dev->tx_queue_len = ifr->ifr_qlen;
-			err = call_netdevice_notifiers(
-					NETDEV_CHANGE_TX_QUEUE_LEN, dev);
-			err = notifier_to_errno(err);
-			if (err) {
-				dev->tx_queue_len = orig_len;
+			err = dev_change_tx_queue_len(dev, ifr->ifr_qlen);
+			if (err)
 				return err;
-			}
 		}
 		return 0;
 
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 126ffc5bc630..f64aa13811ea 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -416,6 +416,14 @@ static struct fib_rule *rule_find(struct fib_rules_ops *ops,
 		if (rule->mark && r->mark != rule->mark)
 			continue;
 
+		if (rule->suppress_ifgroup != -1 &&
+		    r->suppress_ifgroup != rule->suppress_ifgroup)
+			continue;
+
+		if (rule->suppress_prefixlen != -1 &&
+		    r->suppress_prefixlen != rule->suppress_prefixlen)
+			continue;
+
 		if (rule->mark_mask && r->mark_mask != rule->mark_mask)
 			continue;
 
@@ -436,6 +444,9 @@ static struct fib_rule *rule_find(struct fib_rules_ops *ops,
 		if (rule->ip_proto && r->ip_proto != rule->ip_proto)
 			continue;
 
+		if (rule->proto && r->proto != rule->proto)
+			continue;
+
 		if (fib_rule_port_range_set(&rule->sport_range) &&
 		    !fib_rule_port_range_compare(&r->sport_range,
 						 &rule->sport_range))
@@ -645,6 +656,73 @@ errout:
 	return err;
 }
 
+static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh,
+		       struct nlattr **tb, struct fib_rule *rule)
+{
+	struct fib_rule *r;
+
+	list_for_each_entry(r, &ops->rules_list, list) {
+		if (r->action != rule->action)
+			continue;
+
+		if (r->table != rule->table)
+			continue;
+
+		if (r->pref != rule->pref)
+			continue;
+
+		if (memcmp(r->iifname, rule->iifname, IFNAMSIZ))
+			continue;
+
+		if (memcmp(r->oifname, rule->oifname, IFNAMSIZ))
+			continue;
+
+		if (r->mark != rule->mark)
+			continue;
+
+		if (r->suppress_ifgroup != rule->suppress_ifgroup)
+			continue;
+
+		if (r->suppress_prefixlen != rule->suppress_prefixlen)
+			continue;
+
+		if (r->mark_mask != rule->mark_mask)
+			continue;
+
+		if (r->tun_id != rule->tun_id)
+			continue;
+
+		if (r->fr_net != rule->fr_net)
+			continue;
+
+		if (r->l3mdev != rule->l3mdev)
+			continue;
+
+		if (!uid_eq(r->uid_range.start, rule->uid_range.start) ||
+		    !uid_eq(r->uid_range.end, rule->uid_range.end))
+			continue;
+
+		if (r->ip_proto != rule->ip_proto)
+			continue;
+
+		if (r->proto != rule->proto)
+			continue;
+
+		if (!fib_rule_port_range_compare(&r->sport_range,
+						 &rule->sport_range))
+			continue;
+
+		if (!fib_rule_port_range_compare(&r->dport_range,
+						 &rule->dport_range))
+			continue;
+
+		if (!ops->compare(r, frh, tb))
+			continue;
+		return 1;
+	}
+	return 0;
+}
+
 int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 		   struct netlink_ext_ack *extack)
 {
@@ -679,7 +757,7 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 		goto errout;
 
 	if ((nlh->nlmsg_flags & NLM_F_EXCL) &&
-	    rule_find(ops, frh, tb, rule, user_priority)) {
+	    rule_exists(ops, frh, tb, rule)) {
 		err = -EEXIST;
 		goto errout_free;
 	}
diff --git a/net/core/filter.c b/net/core/filter.c
index e7f12e9f598c..0ca6907d7efe 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4073,8 +4073,9 @@ static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params,
 	memcpy(params->smac, dev->dev_addr, ETH_ALEN);
 	params->h_vlan_TCI = 0;
 	params->h_vlan_proto = 0;
+	params->ifindex = dev->ifindex;
 
-	return dev->ifindex;
+	return 0;
 }
 #endif
 
@@ -4098,7 +4099,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	/* verify forwarding is enabled on this interface */
 	in_dev = __in_dev_get_rcu(dev);
 	if (unlikely(!in_dev || !IN_DEV_FORWARD(in_dev)))
-		return 0;
+		return BPF_FIB_LKUP_RET_FWD_DISABLED;
 
 	if (flags & BPF_FIB_LOOKUP_OUTPUT) {
 		fl4.flowi4_iif = 1;
@@ -4123,7 +4124,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 
 		tb = fib_get_table(net, tbid);
 		if (unlikely(!tb))
-			return 0;
+			return BPF_FIB_LKUP_RET_NOT_FWDED;
 
 		err = fib_table_lookup(tb, &fl4, &res, FIB_LOOKUP_NOREF);
 	} else {
@@ -4135,8 +4136,20 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 		err = fib_lookup(net, &fl4, &res, FIB_LOOKUP_NOREF);
 	}
 
-	if (err || res.type != RTN_UNICAST)
-		return 0;
+	if (err) {
+		/* map fib lookup errors to RTN_ type */
+		if (err == -EINVAL)
+			return BPF_FIB_LKUP_RET_BLACKHOLE;
+		if (err == -EHOSTUNREACH)
+			return BPF_FIB_LKUP_RET_UNREACHABLE;
+		if (err == -EACCES)
+			return BPF_FIB_LKUP_RET_PROHIBIT;
+
+		return BPF_FIB_LKUP_RET_NOT_FWDED;
+	}
+
+	if (res.type != RTN_UNICAST)
+		return BPF_FIB_LKUP_RET_NOT_FWDED;
 
 	if (res.fi->fib_nhs > 1)
 		fib_select_path(net, &res, &fl4, NULL);
@@ -4144,19 +4157,16 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	if (check_mtu) {
 		mtu = ip_mtu_from_fib_result(&res, params->ipv4_dst);
 		if (params->tot_len > mtu)
-			return 0;
+			return BPF_FIB_LKUP_RET_FRAG_NEEDED;
 	}
 
 	nh = &res.fi->fib_nh[res.nh_sel];
 
 	/* do not handle lwt encaps right now */
 	if (nh->nh_lwtstate)
-		return 0;
+		return BPF_FIB_LKUP_RET_UNSUPP_LWT;
 
 	dev = nh->nh_dev;
-	if (unlikely(!dev))
-		return 0;
-
 	if (nh->nh_gw)
 		params->ipv4_dst = nh->nh_gw;
 
@@ -4166,10 +4176,10 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	 * rcu_read_lock_bh is not needed here
 	 */
 	neigh = __ipv4_neigh_lookup_noref(dev, (__force u32)params->ipv4_dst);
-	if (neigh)
-		return bpf_fib_set_fwd_params(params, neigh, dev);
+	if (!neigh)
+		return BPF_FIB_LKUP_RET_NO_NEIGH;
 
-	return 0;
+	return bpf_fib_set_fwd_params(params, neigh, dev);
 }
 #endif
 
@@ -4190,7 +4200,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 
 	/* link local addresses are never forwarded */
 	if (rt6_need_strict(dst) || rt6_need_strict(src))
-		return 0;
+		return BPF_FIB_LKUP_RET_NOT_FWDED;
 
 	dev = dev_get_by_index_rcu(net, params->ifindex);
 	if (unlikely(!dev))
@@ -4198,7 +4208,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 
 	idev = __in6_dev_get_safely(dev);
 	if (unlikely(!idev || !net->ipv6.devconf_all->forwarding))
-		return 0;
+		return BPF_FIB_LKUP_RET_FWD_DISABLED;
 
 	if (flags & BPF_FIB_LOOKUP_OUTPUT) {
 		fl6.flowi6_iif = 1;
@@ -4225,7 +4235,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 
 		tb = ipv6_stub->fib6_get_table(net, tbid);
 		if (unlikely(!tb))
-			return 0;
+			return BPF_FIB_LKUP_RET_NOT_FWDED;
 
 		f6i = ipv6_stub->fib6_table_lookup(net, tb, oif, &fl6, strict);
 	} else {
@@ -4238,11 +4248,23 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	}
 
 	if (unlikely(IS_ERR_OR_NULL(f6i) || f6i == net->ipv6.fib6_null_entry))
-		return 0;
+		return BPF_FIB_LKUP_RET_NOT_FWDED;
+
+	if (unlikely(f6i->fib6_flags & RTF_REJECT)) {
+		switch (f6i->fib6_type) {
+		case RTN_BLACKHOLE:
+			return BPF_FIB_LKUP_RET_BLACKHOLE;
+		case RTN_UNREACHABLE:
+			return BPF_FIB_LKUP_RET_UNREACHABLE;
+		case RTN_PROHIBIT:
+			return BPF_FIB_LKUP_RET_PROHIBIT;
+		default:
+			return BPF_FIB_LKUP_RET_NOT_FWDED;
+		}
+	}
 
-	if (unlikely(f6i->fib6_flags & RTF_REJECT ||
-	    f6i->fib6_type != RTN_UNICAST))
-		return 0;
+	if (f6i->fib6_type != RTN_UNICAST)
+		return BPF_FIB_LKUP_RET_NOT_FWDED;
 
 	if (f6i->fib6_nsiblings && fl6.flowi6_oif == 0)
 		f6i = ipv6_stub->fib6_multipath_select(net, f6i, &fl6,
@@ -4252,11 +4274,11 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	if (check_mtu) {
 		mtu = ipv6_stub->ip6_mtu_from_fib6(f6i, dst, src);
 		if (params->tot_len > mtu)
-			return 0;
+			return BPF_FIB_LKUP_RET_FRAG_NEEDED;
 	}
 
 	if (f6i->fib6_nh.nh_lwtstate)
-		return 0;
+		return BPF_FIB_LKUP_RET_UNSUPP_LWT;
 
 	if (f6i->fib6_flags & RTF_GATEWAY)
 		*dst = f6i->fib6_nh.nh_gw;
@@ -4270,10 +4292,10 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	 */
 	neigh = ___neigh_lookup_noref(ipv6_stub->nd_tbl, neigh_key_eq128,
 				      ndisc_hashfn, dst, dev);
-	if (neigh)
-		return bpf_fib_set_fwd_params(params, neigh, dev);
+	if (!neigh)
+		return BPF_FIB_LKUP_RET_NO_NEIGH;
 
-	return 0;
+	return bpf_fib_set_fwd_params(params, neigh, dev);
 }
 #endif
 
@@ -4315,7 +4337,7 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb,
 	   struct bpf_fib_lookup *, params, int, plen, u32, flags)
 {
 	struct net *net = dev_net(skb->dev);
-	int index = -EAFNOSUPPORT;
+	int rc = -EAFNOSUPPORT;
 
 	if (plen < sizeof(*params))
 		return -EINVAL;
@@ -4326,25 +4348,25 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb,
 	switch (params->family) {
 #if IS_ENABLED(CONFIG_INET)
 	case AF_INET:
-		index = bpf_ipv4_fib_lookup(net, params, flags, false);
+		rc = bpf_ipv4_fib_lookup(net, params, flags, false);
 		break;
 #endif
 #if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
-		index = bpf_ipv6_fib_lookup(net, params, flags, false);
+		rc = bpf_ipv6_fib_lookup(net, params, flags, false);
 		break;
 #endif
 	}
 
-	if (index > 0) {
+	if (!rc) {
 		struct net_device *dev;
 
-		dev = dev_get_by_index_rcu(net, index);
+		dev = dev_get_by_index_rcu(net, params->ifindex);
 		if (!is_skb_forwardable(dev, skb))
-			index = 0;
+			rc = BPF_FIB_LKUP_RET_FRAG_NEEDED;
 	}
 
-	return index;
+	return rc;
 }
 
 static const struct bpf_func_proto bpf_skb_fib_lookup_proto = {
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index c642304f178c..eba8dae22c25 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5276,8 +5276,7 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len,
 			if (npages >= 1 << order) {
 				page = alloc_pages((gfp_mask & ~__GFP_DIRECT_RECLAIM) |
 						   __GFP_COMP |
-						   __GFP_NOWARN |
-						   __GFP_NORETRY,
+						   __GFP_NOWARN,
 						   order);
 				if (page)
 					goto fill_page;
diff --git a/net/core/sock.c b/net/core/sock.c
index bcc41829a16d..9e8f65585b81 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -3243,7 +3243,8 @@ static int req_prot_init(const struct proto *prot)
 
 	rsk_prot->slab = kmem_cache_create(rsk_prot->slab_name,
 					   rsk_prot->obj_size, 0,
-					   prot->slab_flags, NULL);
+					   SLAB_ACCOUNT | prot->slab_flags,
+					   NULL);
 
 	if (!rsk_prot->slab) {
 		pr_crit("%s: Can't create request sock SLAB cache!\n",
@@ -3258,7 +3259,8 @@ int proto_register(struct proto *prot, int alloc_slab)
 	if (alloc_slab) {
 		prot->slab = kmem_cache_create_usercopy(prot->name,
 					prot->obj_size, 0,
-					SLAB_HWCACHE_ALIGN | prot->slab_flags,
+					SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT |
+					prot->slab_flags,
 					prot->useroffset, prot->usersize,
 					NULL);
 
@@ -3281,6 +3283,7 @@ int proto_register(struct proto *prot, int alloc_slab)
 				kmem_cache_create(prot->twsk_prot->twsk_slab_name,
 						  prot->twsk_prot->twsk_obj_size,
 						  0,
+						  SLAB_ACCOUNT |
 						  prot->slab_flags,
 						  NULL);
 			if (prot->twsk_prot->twsk_slab == NULL)