1 files changed, 174 insertions, 82 deletions

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 2742cc7602bb..cc3ce0f762ec 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -93,6 +93,7 @@
 #include <linux/inet.h>
 #include <linux/netdevice.h>
 #include <linux/slab.h>
+#include <linux/sock_diag.h>
 #include <net/tcp_states.h>
 #include <linux/skbuff.h>
 #include <linux/proc_fs.h>
@@ -119,14 +120,13 @@
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ipv6_stubs.h>
 #endif
+#include <net/rps.h>
 
 struct udp_table udp_table __read_mostly;
 
 long sysctl_udp_mem[3] __read_mostly;
 EXPORT_IPV6_MOD(sysctl_udp_mem);
 
-atomic_long_t udp_memory_allocated ____cacheline_aligned_in_smp;
-EXPORT_IPV6_MOD(udp_memory_allocated);
 DEFINE_PER_CPU(int, udp_memory_per_cpu_fw_alloc);
 EXPORT_PER_CPU_SYMBOL_GPL(udp_memory_per_cpu_fw_alloc);
 
@@ -143,8 +143,8 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num,
 			       unsigned long *bitmap,
 			       struct sock *sk, unsigned int log)
 {
+	kuid_t uid = sk_uid(sk);
 	struct sock *sk2;
-	kuid_t uid = sock_i_uid(sk);
 
 	sk_for_each(sk2, &hslot->head) {
 		if (net_eq(sock_net(sk2), net) &&
@@ -156,7 +156,7 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num,
 		    inet_rcv_saddr_equal(sk, sk2, true)) {
 			if (sk2->sk_reuseport && sk->sk_reuseport &&
 			    !rcu_access_pointer(sk->sk_reuseport_cb) &&
-			    uid_eq(uid, sock_i_uid(sk2))) {
+			    uid_eq(uid, sk_uid(sk2))) {
 				if (!bitmap)
 					return 0;
 			} else {
@@ -178,8 +178,8 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num,
 				struct udp_hslot *hslot2,
 				struct sock *sk)
 {
+	kuid_t uid = sk_uid(sk);
 	struct sock *sk2;
-	kuid_t uid = sock_i_uid(sk);
 	int res = 0;
 
 	spin_lock(&hslot2->lock);
@@ -193,7 +193,7 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num,
 		    inet_rcv_saddr_equal(sk, sk2, true)) {
 			if (sk2->sk_reuseport && sk->sk_reuseport &&
 			    !rcu_access_pointer(sk->sk_reuseport_cb) &&
-			    uid_eq(uid, sock_i_uid(sk2))) {
+			    uid_eq(uid, sk_uid(sk2))) {
 				res = 0;
 			} else {
 				res = 1;
@@ -208,7 +208,7 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num,
 static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot)
 {
 	struct net *net = sock_net(sk);
-	kuid_t uid = sock_i_uid(sk);
+	kuid_t uid = sk_uid(sk);
 	struct sock *sk2;
 
 	sk_for_each(sk2, &hslot->head) {
@@ -218,7 +218,7 @@ static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot)
 		    ipv6_only_sock(sk2) == ipv6_only_sock(sk) &&
 		    (udp_sk(sk2)->udp_port_hash == udp_sk(sk)->udp_port_hash) &&
 		    (sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
-		    sk2->sk_reuseport && uid_eq(uid, sock_i_uid(sk2)) &&
+		    sk2->sk_reuseport && uid_eq(uid, sk_uid(sk2)) &&
 		    inet_rcv_saddr_equal(sk, sk2, false)) {
 			return reuseport_add_sock(sk, sk2,
 						  inet_rcv_saddr_any(sk));
@@ -1443,7 +1443,8 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		flowi4_init_output(fl4, ipc.oif, ipc.sockc.mark,
 				   ipc.tos & INET_DSCP_MASK, scope,
 				   sk->sk_protocol, flow_flags, faddr, saddr,
-				   dport, inet->inet_sport, sk->sk_uid);
+				   dport, inet->inet_sport,
+				   sk_uid(sk));
 
 		security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4));
 		rt = ip_route_output_flow(net, fl4, sk);
@@ -1942,8 +1943,8 @@ struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags,
 		error = -EAGAIN;
 		do {
 			spin_lock_bh(&queue->lock);
-			skb = __skb_try_recv_from_queue(sk, queue, flags, off,
-							err, &last);
+			skb = __skb_try_recv_from_queue(queue, flags, off, err,
+							&last);
 			if (skb) {
 				if (!(flags & MSG_PEEK))
 					udp_skb_destructor(sk, skb);
@@ -1964,8 +1965,8 @@ struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags,
 			spin_lock(&sk_queue->lock);
 			skb_queue_splice_tail_init(sk_queue, queue);
 
-			skb = __skb_try_recv_from_queue(sk, queue, flags, off,
-							err, &last);
+			skb = __skb_try_recv_from_queue(queue, flags, off, err,
+							&last);
 			if (skb && !(flags & MSG_PEEK))
 				udp_skb_dtor_locked(sk, skb);
 			spin_unlock(&sk_queue->lock);
@@ -2199,6 +2200,7 @@ void udp_lib_unhash(struct sock *sk)
 		struct udp_table *udptable = udp_get_table_prot(sk);
 		struct udp_hslot *hslot, *hslot2;
 
+		sock_rps_delete_flow(sk);
 		hslot  = udp_hashslot(udptable, sock_net(sk),
 				      udp_sk(sk)->udp_port_hash);
 		hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash);
@@ -2345,7 +2347,7 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
  */
 static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
 {
-	int drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
+	enum skb_drop_reason drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
 	struct udp_sock *up = udp_sk(sk);
 	int is_udplite = IS_UDPLITE(sk);
 
@@ -2434,10 +2436,8 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
 	    udp_lib_checksum_complete(skb))
 			goto csum_error;
 
-	if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr))) {
-		drop_reason = SKB_DROP_REASON_SOCKET_FILTER;
+	if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr), &drop_reason))
 		goto drop;
-	}
 
 	udp_csum_pull_header(skb);
 
@@ -2897,20 +2897,40 @@ void udp_destroy_sock(struct sock *sk)
 			if (encap_destroy)
 				encap_destroy(sk);
 		}
-		if (udp_test_bit(ENCAP_ENABLED, sk))
+		if (udp_test_bit(ENCAP_ENABLED, sk)) {
 			static_branch_dec(&udp_encap_needed_key);
+			udp_tunnel_cleanup_gro(sk);
+		}
 	}
 }
 
+typedef struct sk_buff *(*udp_gro_receive_t)(struct sock *sk,
+					     struct list_head *head,
+					     struct sk_buff *skb);
+
 static void set_xfrm_gro_udp_encap_rcv(__u16 encap_type, unsigned short family,
 				       struct sock *sk)
 {
 #ifdef CONFIG_XFRM
+	udp_gro_receive_t new_gro_receive;
+
 	if (udp_test_bit(GRO_ENABLED, sk) && encap_type == UDP_ENCAP_ESPINUDP) {
-		if (family == AF_INET)
-			WRITE_ONCE(udp_sk(sk)->gro_receive, xfrm4_gro_udp_encap_rcv);
-		else if (IS_ENABLED(CONFIG_IPV6) && family == AF_INET6)
-			WRITE_ONCE(udp_sk(sk)->gro_receive, ipv6_stub->xfrm6_gro_udp_encap_rcv);
+		if (IS_ENABLED(CONFIG_IPV6) && family == AF_INET6)
+			new_gro_receive = ipv6_stub->xfrm6_gro_udp_encap_rcv;
+		else
+			new_gro_receive = xfrm4_gro_udp_encap_rcv;
+
+		if (udp_sk(sk)->gro_receive != new_gro_receive) {
+			/*
+			 * With IPV6_ADDRFORM the gro callback could change
+			 * after being set, unregister the old one, if valid.
+			 */
+			if (udp_sk(sk)->gro_receive)
+				udp_tunnel_update_gro_rcv(sk, false);
+
+			WRITE_ONCE(udp_sk(sk)->gro_receive, new_gro_receive);
+			udp_tunnel_update_gro_rcv(sk, true);
+		}
 	}
 #endif
 }
@@ -2960,6 +2980,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case UDP_ENCAP:
+		sockopt_lock_sock(sk);
 		switch (val) {
 		case 0:
 #ifdef CONFIG_XFRM
@@ -2983,6 +3004,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
 			err = -ENOPROTOOPT;
 			break;
 		}
+		sockopt_release_sock(sk);
 		break;
 
 	case UDP_NO_CHECK6_TX:
@@ -3000,13 +3022,14 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case UDP_GRO:
-
+		sockopt_lock_sock(sk);
 		/* when enabling GRO, accept the related GSO packet type */
 		if (valbool)
 			udp_tunnel_encap_enable(sk);
 		udp_assign_bit(GRO_ENABLED, sk, valbool);
 		udp_assign_bit(ACCEPT_L4, sk, valbool);
 		set_xfrm_gro_udp_encap_rcv(up->encap_type, sk->sk_family, sk);
+		sockopt_release_sock(sk);
 		break;
 
 	/*
@@ -3208,7 +3231,7 @@ struct proto udp_prot = {
 #ifdef CONFIG_BPF_SYSCALL
 	.psock_update_sk_prot	= udp_bpf_update_proto,
 #endif
-	.memory_allocated	= &udp_memory_allocated,
+	.memory_allocated	= &net_aligned_data.udp_memory_allocated,
 	.per_cpu_fw_alloc	= &udp_memory_per_cpu_fw_alloc,
 
 	.sysctl_mem		= sysctl_udp_mem,
@@ -3360,7 +3383,7 @@ static void udp4_format_sock(struct sock *sp, struct seq_file *f,
 		sk_wmem_alloc_get(sp),
 		udp_rqueue_get(sp),
 		0, 0L, 0,
-		from_kuid_munged(seq_user_ns(f), sock_i_uid(sp)),
+		from_kuid_munged(seq_user_ns(f), sk_uid(sp)),
 		0, sock_i_ino(sp),
 		refcount_read(&sp->sk_refcnt), sp,
 		atomic_read(&sp->sk_drops));
@@ -3390,34 +3413,55 @@ struct bpf_iter__udp {
 	int bucket __aligned(8);
 };
 
+union bpf_udp_iter_batch_item {
+	struct sock *sk;
+	__u64 cookie;
+};
+
 struct bpf_udp_iter_state {
 	struct udp_iter_state state;
 	unsigned int cur_sk;
 	unsigned int end_sk;
 	unsigned int max_sk;
-	int offset;
-	struct sock **batch;
-	bool st_bucket_done;
+	union bpf_udp_iter_batch_item *batch;
 };
 
 static int bpf_iter_udp_realloc_batch(struct bpf_udp_iter_state *iter,
-				      unsigned int new_batch_sz);
+				      unsigned int new_batch_sz, gfp_t flags);
+static struct sock *bpf_iter_udp_resume(struct sock *first_sk,
+					union bpf_udp_iter_batch_item *cookies,
+					int n_cookies)
+{
+	struct sock *sk = NULL;
+	int i;
+
+	for (i = 0; i < n_cookies; i++) {
+		sk = first_sk;
+		udp_portaddr_for_each_entry_from(sk)
+			if (cookies[i].cookie == atomic64_read(&sk->sk_cookie))
+				goto done;
+	}
+done:
+	return sk;
+}
+
 static struct sock *bpf_iter_udp_batch(struct seq_file *seq)
 {
 	struct bpf_udp_iter_state *iter = seq->private;
 	struct udp_iter_state *state = &iter->state;
+	unsigned int find_cookie, end_cookie;
 	struct net *net = seq_file_net(seq);
-	int resume_bucket, resume_offset;
 	struct udp_table *udptable;
 	unsigned int batch_sks = 0;
-	bool resized = false;
+	int resume_bucket;
+	int resizes = 0;
 	struct sock *sk;
+	int err = 0;
 
 	resume_bucket = state->bucket;
-	resume_offset = iter->offset;
 
 	/* The current batch is done, so advance the bucket. */
-	if (iter->st_bucket_done)
+	if (iter->cur_sk == iter->end_sk)
 		state->bucket++;
 
 	udptable = udp_get_table_seq(seq, net);
@@ -3430,62 +3474,89 @@ again:
 	 * before releasing the bucket lock. This allows BPF programs that are
 	 * called in seq_show to acquire the bucket lock if needed.
 	 */
+	find_cookie = iter->cur_sk;
+	end_cookie = iter->end_sk;
 	iter->cur_sk = 0;
 	iter->end_sk = 0;
-	iter->st_bucket_done = false;
 	batch_sks = 0;
 
 	for (; state->bucket <= udptable->mask; state->bucket++) {
 		struct udp_hslot *hslot2 = &udptable->hash2[state->bucket].hslot;
 
 		if (hlist_empty(&hslot2->head))
-			continue;
+			goto next_bucket;
 
-		iter->offset = 0;
 		spin_lock_bh(&hslot2->lock);
-		udp_portaddr_for_each_entry(sk, &hslot2->head) {
+		sk = hlist_entry_safe(hslot2->head.first, struct sock,
+				      __sk_common.skc_portaddr_node);
+		/* Resume from the first (in iteration order) unseen socket from
+		 * the last batch that still exists in resume_bucket. Most of
+		 * the time this will just be where the last iteration left off
+		 * in resume_bucket unless that socket disappeared between
+		 * reads.
+		 */
+		if (state->bucket == resume_bucket)
+			sk = bpf_iter_udp_resume(sk, &iter->batch[find_cookie],
+						 end_cookie - find_cookie);
+fill_batch:
+		udp_portaddr_for_each_entry_from(sk) {
 			if (seq_sk_match(seq, sk)) {
-				/* Resume from the last iterated socket at the
-				 * offset in the bucket before iterator was stopped.
-				 */
-				if (state->bucket == resume_bucket &&
-				    iter->offset < resume_offset) {
-					++iter->offset;
-					continue;
-				}
 				if (iter->end_sk < iter->max_sk) {
 					sock_hold(sk);
-					iter->batch[iter->end_sk++] = sk;
+					iter->batch[iter->end_sk++].sk = sk;
 				}
 				batch_sks++;
 			}
 		}
+
+		/* Allocate a larger batch and try again. */
+		if (unlikely(resizes <= 1 && iter->end_sk &&
+			     iter->end_sk != batch_sks)) {
+			resizes++;
+
+			/* First, try with GFP_USER to maximize the chances of
+			 * grabbing more memory.
+			 */
+			if (resizes == 1) {
+				spin_unlock_bh(&hslot2->lock);
+				err = bpf_iter_udp_realloc_batch(iter,
+								 batch_sks * 3 / 2,
+								 GFP_USER);
+				if (err)
+					return ERR_PTR(err);
+				/* Start over. */
+				goto again;
+			}
+
+			/* Next, hold onto the lock, so the bucket doesn't
+			 * change while we get the rest of the sockets.
+			 */
+			err = bpf_iter_udp_realloc_batch(iter, batch_sks,
+							 GFP_NOWAIT);
+			if (err) {
+				spin_unlock_bh(&hslot2->lock);
+				return ERR_PTR(err);
+			}
+
+			/* Pick up where we left off. */
+			sk = iter->batch[iter->end_sk - 1].sk;
+			sk = hlist_entry_safe(sk->__sk_common.skc_portaddr_node.next,
+					      struct sock,
+					      __sk_common.skc_portaddr_node);
+			batch_sks = iter->end_sk;
+			goto fill_batch;
+		}
+
 		spin_unlock_bh(&hslot2->lock);
 
 		if (iter->end_sk)
 			break;
+next_bucket:
+		resizes = 0;
 	}
 
-	/* All done: no batch made. */
-	if (!iter->end_sk)
-		return NULL;
-
-	if (iter->end_sk == batch_sks) {
-		/* Batching is done for the current bucket; return the first
-		 * socket to be iterated from the batch.
-		 */
-		iter->st_bucket_done = true;
-		goto done;
-	}
-	if (!resized && !bpf_iter_udp_realloc_batch(iter, batch_sks * 3 / 2)) {
-		resized = true;
-		/* After allocating a larger batch, retry one more time to grab
-		 * the whole bucket.
-		 */
-		goto again;
-	}
-done:
-	return iter->batch[0];
+	WARN_ON_ONCE(iter->end_sk != batch_sks);
+	return iter->end_sk ? iter->batch[0].sk : NULL;
 }
 
 static void *bpf_iter_udp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
@@ -3496,16 +3567,14 @@ static void *bpf_iter_udp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	/* Whenever seq_next() is called, the iter->cur_sk is
 	 * done with seq_show(), so unref the iter->cur_sk.
 	 */
-	if (iter->cur_sk < iter->end_sk) {
-		sock_put(iter->batch[iter->cur_sk++]);
-		++iter->offset;
-	}
+	if (iter->cur_sk < iter->end_sk)
+		sock_put(iter->batch[iter->cur_sk++].sk);
 
 	/* After updating iter->cur_sk, check if there are more sockets
 	 * available in the current bucket batch.
 	 */
 	if (iter->cur_sk < iter->end_sk)
-		sk = iter->batch[iter->cur_sk];
+		sk = iter->batch[iter->cur_sk].sk;
 	else
 		/* Prepare a new batch. */
 		sk = bpf_iter_udp_batch(seq);
@@ -3557,7 +3626,7 @@ static int bpf_iter_udp_seq_show(struct seq_file *seq, void *v)
 		goto unlock;
 	}
 
-	uid = from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk));
+	uid = from_kuid_munged(seq_user_ns(seq), sk_uid(sk));
 	meta.seq = seq;
 	prog = bpf_iter_get_info(&meta, false);
 	ret = udp_prog_seq_show(prog, &meta, v, uid, state->bucket);
@@ -3569,8 +3638,19 @@ unlock:
 
 static void bpf_iter_udp_put_batch(struct bpf_udp_iter_state *iter)
 {
-	while (iter->cur_sk < iter->end_sk)
-		sock_put(iter->batch[iter->cur_sk++]);
+	union bpf_udp_iter_batch_item *item;
+	unsigned int cur_sk = iter->cur_sk;
+	__u64 cookie;
+
+	/* Remember the cookies of the sockets we haven't seen yet, so we can
+	 * pick up where we left off next time around.
+	 */
+	while (cur_sk < iter->end_sk) {
+		item = &iter->batch[cur_sk++];
+		cookie = sock_gen_cookie(item->sk);
+		sock_put(item->sk);
+		item->cookie = cookie;
+	}
 }
 
 static void bpf_iter_udp_seq_stop(struct seq_file *seq, void *v)
@@ -3586,10 +3666,8 @@ static void bpf_iter_udp_seq_stop(struct seq_file *seq, void *v)
 			(void)udp_prog_seq_show(prog, &meta, v, 0, 0);
 	}
 
-	if (iter->cur_sk < iter->end_sk) {
+	if (iter->cur_sk < iter->end_sk)
 		bpf_iter_udp_put_batch(iter);
-		iter->st_bucket_done = false;
-	}
 }
 
 static const struct seq_operations bpf_iter_udp_seq_ops = {
@@ -3810,6 +3888,15 @@ fallback:
 
 static int __net_init udp_pernet_init(struct net *net)
 {
+#if IS_ENABLED(CONFIG_NET_UDP_TUNNEL)
+	int i;
+
+	/* No tunnel is configured */
+	for (i = 0; i < ARRAY_SIZE(net->ipv4.udp_tunnel_gro); ++i) {
+		INIT_HLIST_HEAD(&net->ipv4.udp_tunnel_gro[i].list);
+		RCU_INIT_POINTER(net->ipv4.udp_tunnel_gro[i].sk, NULL);
+	}
+#endif
 	udp_sysctl_init(net);
 	udp_set_table(net);
 
@@ -3831,16 +3918,19 @@ DEFINE_BPF_ITER_FUNC(udp, struct bpf_iter_meta *meta,
 		     struct udp_sock *udp_sk, uid_t uid, int bucket)
 
 static int bpf_iter_udp_realloc_batch(struct bpf_udp_iter_state *iter,
-				      unsigned int new_batch_sz)
+				      unsigned int new_batch_sz, gfp_t flags)
 {
-	struct sock **new_batch;
+	union bpf_udp_iter_batch_item *new_batch;
 
 	new_batch = kvmalloc_array(new_batch_sz, sizeof(*new_batch),
-				   GFP_USER | __GFP_NOWARN);
+				   flags | __GFP_NOWARN);
 	if (!new_batch)
 		return -ENOMEM;
 
-	bpf_iter_udp_put_batch(iter);
+	if (flags != GFP_NOWAIT)
+		bpf_iter_udp_put_batch(iter);
+
+	memcpy(new_batch, iter->batch, sizeof(*iter->batch) * iter->end_sk);
 	kvfree(iter->batch);
 	iter->batch = new_batch;
 	iter->max_sk = new_batch_sz;
@@ -3859,10 +3949,12 @@ static int bpf_iter_init_udp(void *priv_data, struct bpf_iter_aux_info *aux)
 	if (ret)
 		return ret;
 
-	ret = bpf_iter_udp_realloc_batch(iter, INIT_BATCH_SZ);
+	ret = bpf_iter_udp_realloc_batch(iter, INIT_BATCH_SZ, GFP_USER);
 	if (ret)
 		bpf_iter_fini_seq_net(priv_data);
 
+	iter->state.bucket = -1;
+
 	return ret;
 }