9 files changed, 125 insertions, 36 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 0432b04cf9b0..f01a9b858347 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3471,6 +3471,9 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb,
 	if (gso_segs > READ_ONCE(dev->gso_max_segs))
 		return features & ~NETIF_F_GSO_MASK;
 
+	if (unlikely(skb->len >= READ_ONCE(dev->gso_max_size)))
+		return features & ~NETIF_F_GSO_MASK;
+
 	if (!skb_shinfo(skb)->gso_type) {
 		skb_warn_bad_offload(skb);
 		return features & ~NETIF_F_GSO_MASK;
@@ -3753,6 +3756,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 
 	qdisc_calculate_pkt_len(skb, q);
 
+	tcf_set_drop_reason(skb, SKB_DROP_REASON_QDISC_DROP);
+
 	if (q->flags & TCQ_F_NOLOCK) {
 		if (q->flags & TCQ_F_CAN_BYPASS && nolock_qdisc_is_empty(q) &&
 		    qdisc_run_begin(q)) {
@@ -3782,7 +3787,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 no_lock_out:
 		if (unlikely(to_free))
 			kfree_skb_list_reason(to_free,
-					      SKB_DROP_REASON_QDISC_DROP);
+					      tcf_get_drop_reason(to_free));
 		return rc;
 	}
 
@@ -3837,7 +3842,8 @@ no_lock_out:
 	}
 	spin_unlock(root_lock);
 	if (unlikely(to_free))
-		kfree_skb_list_reason(to_free, SKB_DROP_REASON_QDISC_DROP);
+		kfree_skb_list_reason(to_free,
+				      tcf_get_drop_reason(to_free));
 	if (unlikely(contended))
 		spin_unlock(&q->busylock);
 	return rc;
@@ -3923,14 +3929,14 @@ static int tc_run(struct tcx_entry *entry, struct sk_buff *skb,
 
 	tc_skb_cb(skb)->mru = 0;
 	tc_skb_cb(skb)->post_ct = false;
-	res.drop_reason = *drop_reason;
+	tcf_set_drop_reason(skb, *drop_reason);
 
 	mini_qdisc_bstats_cpu_update(miniq, skb);
 	ret = tcf_classify(skb, miniq->block, miniq->filter_list, &res, false);
 	/* Only tcf related quirks below. */
 	switch (ret) {
 	case TC_ACT_SHOT:
-		*drop_reason = res.drop_reason;
+		*drop_reason = tcf_get_drop_reason(skb);
 		mini_qdisc_qstats_cpu_drop(miniq);
 		break;
 	case TC_ACT_OK:
@@ -11620,6 +11626,7 @@ static void __init net_dev_struct_check(void)
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_max_size);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_ipv4_max_size);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_max_segs);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_partial_features);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, num_tc);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, mtu);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, needed_headroom);
@@ -11633,7 +11640,7 @@ static void __init net_dev_struct_check(void)
 #ifdef CONFIG_NET_XGRESS
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, tcx_egress);
 #endif
-	CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_tx, 152);
+	CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_tx, 160);
 
 	/* TXRX read-mostly hotpath */
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, flags);
@@ -11660,7 +11667,7 @@ static void __init net_dev_struct_check(void)
 #ifdef CONFIG_NET_XGRESS
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, tcx_ingress);
 #endif
-	CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_rx, 96);
+	CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_rx, 104);
 }
 
 /*
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index b240d9aae4a6..b0f221d658be 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -183,7 +183,7 @@ out:
 }
 
 static const struct genl_multicast_group dropmon_mcgrps[] = {
-	{ .name = "events", .cap_sys_admin = 1 },
+	{ .name = "events", .flags = GENL_MCAST_CAP_SYS_ADMIN, },
 };
 
 static void send_dm_alert(struct work_struct *work)
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 75282222e0b4..96622bfb838a 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -53,7 +53,7 @@ bool fib_rule_matchall(const struct fib_rule *rule)
 EXPORT_SYMBOL_GPL(fib_rule_matchall);
 
 int fib_default_rule_add(struct fib_rules_ops *ops,
-			 u32 pref, u32 table, u32 flags)
+			 u32 pref, u32 table)
 {
 	struct fib_rule *r;
 
@@ -65,7 +65,6 @@ int fib_default_rule_add(struct fib_rules_ops *ops,
 	r->action = FR_ACT_TO_TBL;
 	r->pref = pref;
 	r->table = table;
-	r->flags = flags;
 	r->proto = RTPROT_KERNEL;
 	r->fr_net = ops->fro_net;
 	r->uid_range = fib_kuid_range_unset;
diff --git a/net/core/filter.c b/net/core/filter.c
index 4ff6100c6a27..24061f29c9dd 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -87,7 +87,7 @@
 #include "dev.h"
 
 static const struct bpf_func_proto *
-bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog);
+bpf_sk_base_func_proto(enum bpf_func_id func_id);
 
 int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len)
 {
@@ -203,7 +203,7 @@ BPF_CALL_3(bpf_skb_get_nlattr_nest, struct sk_buff *, skb, u32, a, u32, x)
 		return 0;
 
 	nla = (struct nlattr *) &skb->data[a];
-	if (nla->nla_len > skb->len - a)
+	if (!nla_ok(nla, skb->len - a))
 		return 0;
 
 	nla = nla_find_nested(nla, x);
@@ -7862,7 +7862,7 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_ktime_get_coarse_ns:
 		return &bpf_ktime_get_coarse_ns_proto;
 	default:
-		return bpf_base_func_proto(func_id, prog);
+		return bpf_base_func_proto(func_id);
 	}
 }
 
@@ -7955,7 +7955,7 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 			return NULL;
 		}
 	default:
-		return bpf_sk_base_func_proto(func_id, prog);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -7974,7 +7974,7 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_perf_event_output:
 		return &bpf_skb_event_output_proto;
 	default:
-		return bpf_sk_base_func_proto(func_id, prog);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -8161,7 +8161,7 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 #endif
 #endif
 	default:
-		return bpf_sk_base_func_proto(func_id, prog);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -8220,7 +8220,7 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 #endif
 #endif
 	default:
-		return bpf_sk_base_func_proto(func_id, prog);
+		return bpf_sk_base_func_proto(func_id);
 	}
 
 #if IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)
@@ -8281,7 +8281,7 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_tcp_sock_proto;
 #endif /* CONFIG_INET */
 	default:
-		return bpf_sk_base_func_proto(func_id, prog);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -8323,7 +8323,7 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_cgroup_classid_curr_proto;
 #endif
 	default:
-		return bpf_sk_base_func_proto(func_id, prog);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -8367,7 +8367,7 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_skc_lookup_tcp_proto;
 #endif
 	default:
-		return bpf_sk_base_func_proto(func_id, prog);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -8378,7 +8378,7 @@ flow_dissector_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_skb_load_bytes:
 		return &bpf_flow_dissector_load_bytes_proto;
 	default:
-		return bpf_sk_base_func_proto(func_id, prog);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -8405,7 +8405,7 @@ lwt_out_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_skb_under_cgroup:
 		return &bpf_skb_under_cgroup_proto;
 	default:
-		return bpf_sk_base_func_proto(func_id, prog);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -8580,7 +8580,7 @@ static bool cg_skb_is_valid_access(int off, int size,
 		return false;
 	case bpf_ctx_range(struct __sk_buff, data):
 	case bpf_ctx_range(struct __sk_buff, data_end):
-		if (!bpf_token_capable(prog->aux->token, CAP_BPF))
+		if (!bpf_capable())
 			return false;
 		break;
 	}
@@ -8592,7 +8592,7 @@ static bool cg_skb_is_valid_access(int off, int size,
 		case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]):
 			break;
 		case bpf_ctx_range(struct __sk_buff, tstamp):
-			if (!bpf_token_capable(prog->aux->token, CAP_BPF))
+			if (!bpf_capable())
 				return false;
 			break;
 		default:
@@ -11236,7 +11236,7 @@ sk_reuseport_func_proto(enum bpf_func_id func_id,
 	case BPF_FUNC_ktime_get_coarse_ns:
 		return &bpf_ktime_get_coarse_ns_proto;
 	default:
-		return bpf_base_func_proto(func_id, prog);
+		return bpf_base_func_proto(func_id);
 	}
 }
 
@@ -11418,7 +11418,7 @@ sk_lookup_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_sk_release:
 		return &bpf_sk_release_proto;
 	default:
-		return bpf_sk_base_func_proto(func_id, prog);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -11752,7 +11752,7 @@ const struct bpf_func_proto bpf_sock_from_file_proto = {
 };
 
 static const struct bpf_func_proto *
-bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+bpf_sk_base_func_proto(enum bpf_func_id func_id)
 {
 	const struct bpf_func_proto *func;
 
@@ -11781,10 +11781,10 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_ktime_get_coarse_ns:
 		return &bpf_ktime_get_coarse_ns_proto;
 	default:
-		return bpf_base_func_proto(func_id, prog);
+		return bpf_base_func_proto(func_id);
 	}
 
-	if (!bpf_token_capable(prog->aux->token, CAP_PERFMON))
+	if (!perfmon_capable())
 		return NULL;
 
 	return func;
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 57cea67b7562..ea55a758a475 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3669,10 +3669,8 @@ static int pktgen_thread_worker(void *arg)
 		if (unlikely(!pkt_dev && t->control == 0)) {
 			if (t->net->pktgen_exiting)
 				break;
-			wait_event_interruptible_timeout(t->queue,
-							 t->control != 0,
-							 HZ/10);
-			try_to_freeze();
+			wait_event_freezable_timeout(t->queue,
+						     t->control != 0, HZ / 10);
 			continue;
 		}
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 94c4572512b8..5f6ed6da3cfc 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -6410,17 +6410,64 @@ static int rtnl_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 	return dev->netdev_ops->ndo_mdb_add(dev, tb, nlh->nlmsg_flags, extack);
 }
 
+static int rtnl_validate_mdb_entry_del_bulk(const struct nlattr *attr,
+					    struct netlink_ext_ack *extack)
+{
+	struct br_mdb_entry *entry = nla_data(attr);
+	struct br_mdb_entry zero_entry = {};
+
+	if (nla_len(attr) != sizeof(struct br_mdb_entry)) {
+		NL_SET_ERR_MSG_ATTR(extack, attr, "Invalid attribute length");
+		return -EINVAL;
+	}
+
+	if (entry->state != MDB_PERMANENT && entry->state != MDB_TEMPORARY) {
+		NL_SET_ERR_MSG(extack, "Unknown entry state");
+		return -EINVAL;
+	}
+
+	if (entry->flags) {
+		NL_SET_ERR_MSG(extack, "Entry flags cannot be set");
+		return -EINVAL;
+	}
+
+	if (entry->vid >= VLAN_N_VID - 1) {
+		NL_SET_ERR_MSG(extack, "Invalid entry VLAN id");
+		return -EINVAL;
+	}
+
+	if (memcmp(&entry->addr, &zero_entry.addr, sizeof(entry->addr))) {
+		NL_SET_ERR_MSG(extack, "Entry address cannot be set");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static const struct nla_policy mdba_del_bulk_policy[MDBA_SET_ENTRY_MAX + 1] = {
+	[MDBA_SET_ENTRY] = NLA_POLICY_VALIDATE_FN(NLA_BINARY,
+						  rtnl_validate_mdb_entry_del_bulk,
+						  sizeof(struct br_mdb_entry)),
+	[MDBA_SET_ENTRY_ATTRS] = { .type = NLA_NESTED },
+};
+
 static int rtnl_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 			struct netlink_ext_ack *extack)
 {
+	bool del_bulk = !!(nlh->nlmsg_flags & NLM_F_BULK);
 	struct nlattr *tb[MDBA_SET_ENTRY_MAX + 1];
 	struct net *net = sock_net(skb->sk);
 	struct br_port_msg *bpm;
 	struct net_device *dev;
 	int err;
 
-	err = nlmsg_parse_deprecated(nlh, sizeof(*bpm), tb,
-				     MDBA_SET_ENTRY_MAX, mdba_policy, extack);
+	if (!del_bulk)
+		err = nlmsg_parse_deprecated(nlh, sizeof(*bpm), tb,
+					     MDBA_SET_ENTRY_MAX, mdba_policy,
+					     extack);
+	else
+		err = nlmsg_parse(nlh, sizeof(*bpm), tb, MDBA_SET_ENTRY_MAX,
+				  mdba_del_bulk_policy, extack);
 	if (err)
 		return err;
 
@@ -6441,6 +6488,14 @@ static int rtnl_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return -EINVAL;
 	}
 
+	if (del_bulk) {
+		if (!dev->netdev_ops->ndo_mdb_del_bulk) {
+			NL_SET_ERR_MSG(extack, "Device does not support MDB bulk deletion");
+			return -EOPNOTSUPP;
+		}
+		return dev->netdev_ops->ndo_mdb_del_bulk(dev, tb, extack);
+	}
+
 	if (!dev->netdev_ops->ndo_mdb_del) {
 		NL_SET_ERR_MSG(extack, "Device does not support MDB operations");
 		return -EOPNOTSUPP;
@@ -6686,5 +6741,6 @@ void __init rtnetlink_init(void)
 
 	rtnl_register(PF_BRIDGE, RTM_GETMDB, rtnl_mdb_get, rtnl_mdb_dump, 0);
 	rtnl_register(PF_BRIDGE, RTM_NEWMDB, rtnl_mdb_add, NULL, 0);
-	rtnl_register(PF_BRIDGE, RTM_DELMDB, rtnl_mdb_del, NULL, 0);
+	rtnl_register(PF_BRIDGE, RTM_DELMDB, rtnl_mdb_del, NULL,
+		      RTNL_FLAG_BULK_DEL_SUPPORTED);
 }
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 4d4b11b0a83d..12d22c0b8551 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4861,7 +4861,9 @@ static __always_inline unsigned int skb_ext_total_length(void)
 static void skb_extensions_init(void)
 {
 	BUILD_BUG_ON(SKB_EXT_NUM >= 8);
+#if !IS_ENABLED(CONFIG_KCOV_INSTRUMENT_ALL)
 	BUILD_BUG_ON(skb_ext_total_length() > 255);
+#endif
 
 	skbuff_ext_cache = kmem_cache_create("skbuff_ext_cache",
 					     SKB_EXT_ALIGN_VALUE * skb_ext_total_length(),
@@ -5993,6 +5995,31 @@ int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len)
 }
 EXPORT_SYMBOL(skb_ensure_writable);
 
+int skb_ensure_writable_head_tail(struct sk_buff *skb, struct net_device *dev)
+{
+	int needed_headroom = dev->needed_headroom;
+	int needed_tailroom = dev->needed_tailroom;
+
+	/* For tail taggers, we need to pad short frames ourselves, to ensure
+	 * that the tail tag does not fail at its role of being at the end of
+	 * the packet, once the conduit interface pads the frame. Account for
+	 * that pad length here, and pad later.
+	 */
+	if (unlikely(needed_tailroom && skb->len < ETH_ZLEN))
+		needed_tailroom += ETH_ZLEN - skb->len;
+	/* skb_headroom() returns unsigned int... */
+	needed_headroom = max_t(int, needed_headroom - skb_headroom(skb), 0);
+	needed_tailroom = max_t(int, needed_tailroom - skb_tailroom(skb), 0);
+
+	if (likely(!needed_headroom && !needed_tailroom && !skb_cloned(skb)))
+		/* No reallocation needed, yay! */
+		return 0;
+
+	return pskb_expand_head(skb, needed_headroom, needed_tailroom,
+				GFP_ATOMIC);
+}
+EXPORT_SYMBOL(skb_ensure_writable_head_tail);
+
 /* remove VLAN header from packet and update csum accordingly.
  * expects a non skb_vlan_tag_present skb with a vlan tag payload
  */
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 4292c2ed1828..27d733c0f65e 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -536,6 +536,8 @@ static bool sock_map_sk_state_allowed(const struct sock *sk)
 {
 	if (sk_is_tcp(sk))
 		return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_LISTEN);
+	if (sk_is_stream_unix(sk))
+		return (1 << sk->sk_state) & TCPF_ESTABLISHED;
 	return true;
 }
 
diff --git a/net/core/stream.c b/net/core/stream.c
index 96fbcb9bbb30..b16dfa568a2d 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -79,7 +79,7 @@ int sk_stream_wait_connect(struct sock *sk, long *timeo_p)
 		remove_wait_queue(sk_sleep(sk), &wait);
 		sk->sk_write_pending--;
 	} while (!done);
-	return 0;
+	return done < 0 ? done : 0;
 }
 EXPORT_SYMBOL(sk_stream_wait_connect);