1 files changed, 261 insertions, 114 deletions

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 9482def1f310..42a96b3547c9 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -103,6 +103,7 @@
 #include <net/ip_tunnels.h>
 #include <net/route.h>
 #include <net/checksum.h>
+#include <net/gso.h>
 #include <net/xfrm.h>
 #include <trace/events/udp.h>
 #include <linux/static_key.h>
@@ -1062,8 +1063,8 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	int free = 0;
 	int connected = 0;
 	__be32 daddr, faddr, saddr;
+	u8 tos, scope;
 	__be16 dport;
-	u8  tos;
 	int err, is_udplite = IS_UDPLITE(sk);
 	int corkreq = READ_ONCE(up->corkflag) || msg->msg_flags&MSG_MORE;
 	int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);
@@ -1183,12 +1184,9 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		connected = 0;
 	}
 	tos = get_rttos(&ipc, inet);
-	if (sock_flag(sk, SOCK_LOCALROUTE) ||
-	    (msg->msg_flags & MSG_DONTROUTE) ||
-	    (ipc.opt && ipc.opt->opt.is_strictroute)) {
-		tos |= RTO_ONLINK;
+	scope = ip_sendmsg_scope(inet, &ipc, msg);
+	if (scope == RT_SCOPE_LINK)
 		connected = 0;
-	}
 
 	if (ipv4_is_multicast(daddr)) {
 		if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif))
@@ -1221,11 +1219,9 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 		fl4 = &fl4_stack;
 
-		flowi4_init_output(fl4, ipc.oif, ipc.sockc.mark, tos,
-				   RT_SCOPE_UNIVERSE, sk->sk_protocol,
-				   flow_flags,
-				   faddr, saddr, dport, inet->inet_sport,
-				   sk->sk_uid);
+		flowi4_init_output(fl4, ipc.oif, ipc.sockc.mark, tos, scope,
+				   sk->sk_protocol, flow_flags, faddr, saddr,
+				   dport, inet->inet_sport, sk->sk_uid);
 
 		security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4));
 		rt = ip_route_output_flow(net, fl4, sk);
@@ -1329,58 +1325,20 @@ do_confirm:
 }
 EXPORT_SYMBOL(udp_sendmsg);
 
-int udp_sendpage(struct sock *sk, struct page *page, int offset,
-		 size_t size, int flags)
+void udp_splice_eof(struct socket *sock)
 {
-	struct inet_sock *inet = inet_sk(sk);
+	struct sock *sk = sock->sk;
 	struct udp_sock *up = udp_sk(sk);
-	int ret;
-
-	if (flags & MSG_SENDPAGE_NOTLAST)
-		flags |= MSG_MORE;
 
-	if (!up->pending) {
-		struct msghdr msg = {	.msg_flags = flags|MSG_MORE };
-
-		/* Call udp_sendmsg to specify destination address which
-		 * sendpage interface can't pass.
-		 * This will succeed only when the socket is connected.
-		 */
-		ret = udp_sendmsg(sk, &msg, 0);
-		if (ret < 0)
-			return ret;
-	}
+	if (!up->pending || READ_ONCE(up->corkflag))
+		return;
 
 	lock_sock(sk);
-
-	if (unlikely(!up->pending)) {
-		release_sock(sk);
-
-		net_dbg_ratelimited("cork failed\n");
-		return -EINVAL;
-	}
-
-	ret = ip_append_page(sk, &inet->cork.fl.u.ip4,
-			     page, offset, size, flags);
-	if (ret == -EOPNOTSUPP) {
-		release_sock(sk);
-		return sock_no_sendpage(sk->sk_socket, page, offset,
-					size, flags);
-	}
-	if (ret < 0) {
-		udp_flush_pending_frames(sk);
-		goto out;
-	}
-
-	up->len += size;
-	if (!(READ_ONCE(up->corkflag) || (flags&MSG_MORE)))
-		ret = udp_push_pending_frames(sk);
-	if (!ret)
-		ret = size;
-out:
+	if (up->pending && !READ_ONCE(up->corkflag))
+		udp_push_pending_frames(sk);
 	release_sock(sk);
-	return ret;
 }
+EXPORT_SYMBOL_GPL(udp_splice_eof);
 
 #define UDP_SKB_IS_STATELESS 0x80000000
 
@@ -1720,21 +1678,19 @@ static int first_packet_length(struct sock *sk)
  *	IOCTL requests applicable to the UDP protocol
  */
 
-int udp_ioctl(struct sock *sk, int cmd, unsigned long arg)
+int udp_ioctl(struct sock *sk, int cmd, int *karg)
 {
 	switch (cmd) {
 	case SIOCOUTQ:
 	{
-		int amount = sk_wmem_alloc_get(sk);
-
-		return put_user(amount, (int __user *)arg);
+		*karg = sk_wmem_alloc_get(sk);
+		return 0;
 	}
 
 	case SIOCINQ:
 	{
-		int amount = max_t(int, 0, first_packet_length(sk));
-
-		return put_user(amount, (int __user *)arg);
+		*karg = max_t(int, 0, first_packet_length(sk));
+		return 0;
 	}
 
 	default:
@@ -2927,7 +2883,8 @@ EXPORT_SYMBOL(udp_poll);
 
 int udp_abort(struct sock *sk, int err)
 {
-	lock_sock(sk);
+	if (!has_current_bpf_ctx())
+		lock_sock(sk);
 
 	/* udp{v6}_destroy_sock() sets it under the sk lock, avoid racing
 	 * with close()
@@ -2940,7 +2897,8 @@ int udp_abort(struct sock *sk, int err)
 	__udp_disconnect(sk, 0);
 
 out:
-	release_sock(sk);
+	if (!has_current_bpf_ctx())
+		release_sock(sk);
 
 	return 0;
 }
@@ -2960,7 +2918,7 @@ struct proto udp_prot = {
 	.getsockopt		= udp_getsockopt,
 	.sendmsg		= udp_sendmsg,
 	.recvmsg		= udp_recvmsg,
-	.sendpage		= udp_sendpage,
+	.splice_eof		= udp_splice_eof,
 	.release_cb		= ip4_datagram_release_cb,
 	.hash			= udp_lib_hash,
 	.unhash			= udp_lib_unhash,
@@ -2985,9 +2943,30 @@ EXPORT_SYMBOL(udp_prot);
 /* ------------------------------------------------------------------------ */
 #ifdef CONFIG_PROC_FS
 
-static struct udp_table *udp_get_table_afinfo(struct udp_seq_afinfo *afinfo,
-					      struct net *net)
+static unsigned short seq_file_family(const struct seq_file *seq);
+static bool seq_sk_match(struct seq_file *seq, const struct sock *sk)
 {
+	unsigned short family = seq_file_family(seq);
+
+	/* AF_UNSPEC is used as a match all */
+	return ((family == AF_UNSPEC || family == sk->sk_family) &&
+		net_eq(sock_net(sk), seq_file_net(seq)));
+}
+
+#ifdef CONFIG_BPF_SYSCALL
+static const struct seq_operations bpf_iter_udp_seq_ops;
+#endif
+static struct udp_table *udp_get_table_seq(struct seq_file *seq,
+					   struct net *net)
+{
+	const struct udp_seq_afinfo *afinfo;
+
+#ifdef CONFIG_BPF_SYSCALL
+	if (seq->op == &bpf_iter_udp_seq_ops)
+		return net->ipv4.udp_table;
+#endif
+
+	afinfo = pde_data(file_inode(seq->file));
 	return afinfo->udp_table ? : net->ipv4.udp_table;
 }
 
@@ -2995,16 +2974,10 @@ static struct sock *udp_get_first(struct seq_file *seq, int start)
 {
 	struct udp_iter_state *state = seq->private;
 	struct net *net = seq_file_net(seq);
-	struct udp_seq_afinfo *afinfo;
 	struct udp_table *udptable;
 	struct sock *sk;
 
-	if (state->bpf_seq_afinfo)
-		afinfo = state->bpf_seq_afinfo;
-	else
-		afinfo = pde_data(file_inode(seq->file));
-
-	udptable = udp_get_table_afinfo(afinfo, net);
+	udptable = udp_get_table_seq(seq, net);
 
 	for (state->bucket = start; state->bucket <= udptable->mask;
 	     ++state->bucket) {
@@ -3015,10 +2988,7 @@ static struct sock *udp_get_first(struct seq_file *seq, int start)
 
 		spin_lock_bh(&hslot->lock);
 		sk_for_each(sk, &hslot->head) {
-			if (!net_eq(sock_net(sk), net))
-				continue;
-			if (afinfo->family == AF_UNSPEC ||
-			    sk->sk_family == afinfo->family)
+			if (seq_sk_match(seq, sk))
 				goto found;
 		}
 		spin_unlock_bh(&hslot->lock);
@@ -3032,22 +3002,14 @@ static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk)
 {
 	struct udp_iter_state *state = seq->private;
 	struct net *net = seq_file_net(seq);
-	struct udp_seq_afinfo *afinfo;
 	struct udp_table *udptable;
 
-	if (state->bpf_seq_afinfo)
-		afinfo = state->bpf_seq_afinfo;
-	else
-		afinfo = pde_data(file_inode(seq->file));
-
 	do {
 		sk = sk_next(sk);
-	} while (sk && (!net_eq(sock_net(sk), net) ||
-			(afinfo->family != AF_UNSPEC &&
-			 sk->sk_family != afinfo->family)));
+	} while (sk && !seq_sk_match(seq, sk));
 
 	if (!sk) {
-		udptable = udp_get_table_afinfo(afinfo, net);
+		udptable = udp_get_table_seq(seq, net);
 
 		if (state->bucket <= udptable->mask)
 			spin_unlock_bh(&udptable->hash[state->bucket].lock);
@@ -3093,15 +3055,9 @@ EXPORT_SYMBOL(udp_seq_next);
 void udp_seq_stop(struct seq_file *seq, void *v)
 {
 	struct udp_iter_state *state = seq->private;
-	struct udp_seq_afinfo *afinfo;
 	struct udp_table *udptable;
 
-	if (state->bpf_seq_afinfo)
-		afinfo = state->bpf_seq_afinfo;
-	else
-		afinfo = pde_data(file_inode(seq->file));
-
-	udptable = udp_get_table_afinfo(afinfo, seq_file_net(seq));
+	udptable = udp_get_table_seq(seq, seq_file_net(seq));
 
 	if (state->bucket <= udptable->mask)
 		spin_unlock_bh(&udptable->hash[state->bucket].lock);
@@ -3154,6 +3110,143 @@ struct bpf_iter__udp {
 	int bucket __aligned(8);
 };
 
+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;
+};
+
+static int bpf_iter_udp_realloc_batch(struct bpf_udp_iter_state *iter,
+				      unsigned int new_batch_sz);
+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;
+	struct net *net = seq_file_net(seq);
+	struct udp_table *udptable;
+	unsigned int batch_sks = 0;
+	bool resized = false;
+	struct sock *sk;
+
+	/* The current batch is done, so advance the bucket. */
+	if (iter->st_bucket_done) {
+		state->bucket++;
+		iter->offset = 0;
+	}
+
+	udptable = udp_get_table_seq(seq, net);
+
+again:
+	/* New batch for the next bucket.
+	 * Iterate over the hash table to find a bucket with sockets matching
+	 * the iterator attributes, and return the first matching socket from
+	 * the bucket. The remaining matched sockets from the bucket are batched
+	 * before releasing the bucket lock. This allows BPF programs that are
+	 * called in seq_show to acquire the bucket lock if needed.
+	 */
+	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];
+
+		if (hlist_empty(&hslot2->head)) {
+			iter->offset = 0;
+			continue;
+		}
+
+		spin_lock_bh(&hslot2->lock);
+		udp_portaddr_for_each_entry(sk, &hslot2->head) {
+			if (seq_sk_match(seq, sk)) {
+				/* Resume from the last iterated socket at the
+				 * offset in the bucket before iterator was stopped.
+				 */
+				if (iter->offset) {
+					--iter->offset;
+					continue;
+				}
+				if (iter->end_sk < iter->max_sk) {
+					sock_hold(sk);
+					iter->batch[iter->end_sk++] = sk;
+				}
+				batch_sks++;
+			}
+		}
+		spin_unlock_bh(&hslot2->lock);
+
+		if (iter->end_sk)
+			break;
+
+		/* Reset the current bucket's offset before moving to the next bucket. */
+		iter->offset = 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.
+		 */
+		state->bucket--;
+		goto again;
+	}
+done:
+	return iter->batch[0];
+}
+
+static void *bpf_iter_udp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct bpf_udp_iter_state *iter = seq->private;
+	struct sock *sk;
+
+	/* 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;
+	}
+
+	/* 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];
+	else
+		/* Prepare a new batch. */
+		sk = bpf_iter_udp_batch(seq);
+
+	++*pos;
+	return sk;
+}
+
+static void *bpf_iter_udp_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	/* bpf iter does not support lseek, so it always
+	 * continue from where it was stop()-ped.
+	 */
+	if (*pos)
+		return bpf_iter_udp_batch(seq);
+
+	return SEQ_START_TOKEN;
+}
+
 static int udp_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta,
 			     struct udp_sock *udp_sk, uid_t uid, int bucket)
 {
@@ -3174,18 +3267,37 @@ static int bpf_iter_udp_seq_show(struct seq_file *seq, void *v)
 	struct bpf_prog *prog;
 	struct sock *sk = v;
 	uid_t uid;
+	int ret;
 
 	if (v == SEQ_START_TOKEN)
 		return 0;
 
+	lock_sock(sk);
+
+	if (unlikely(sk_unhashed(sk))) {
+		ret = SEQ_SKIP;
+		goto unlock;
+	}
+
 	uid = from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk));
 	meta.seq = seq;
 	prog = bpf_iter_get_info(&meta, false);
-	return udp_prog_seq_show(prog, &meta, v, uid, state->bucket);
+	ret = udp_prog_seq_show(prog, &meta, v, uid, state->bucket);
+
+unlock:
+	release_sock(sk);
+	return ret;
+}
+
+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++]);
 }
 
 static void bpf_iter_udp_seq_stop(struct seq_file *seq, void *v)
 {
+	struct bpf_udp_iter_state *iter = seq->private;
 	struct bpf_iter_meta meta;
 	struct bpf_prog *prog;
 
@@ -3196,17 +3308,35 @@ static void bpf_iter_udp_seq_stop(struct seq_file *seq, void *v)
 			(void)udp_prog_seq_show(prog, &meta, v, 0, 0);
 	}
 
-	udp_seq_stop(seq, v);
+	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 = {
-	.start		= udp_seq_start,
-	.next		= udp_seq_next,
+	.start		= bpf_iter_udp_seq_start,
+	.next		= bpf_iter_udp_seq_next,
 	.stop		= bpf_iter_udp_seq_stop,
 	.show		= bpf_iter_udp_seq_show,
 };
 #endif
 
+static unsigned short seq_file_family(const struct seq_file *seq)
+{
+	const struct udp_seq_afinfo *afinfo;
+
+#ifdef CONFIG_BPF_SYSCALL
+	/* BPF iterator: bpf programs to filter sockets. */
+	if (seq->op == &bpf_iter_udp_seq_ops)
+		return AF_UNSPEC;
+#endif
+
+	/* Proc fs iterator */
+	afinfo = pde_data(file_inode(seq->file));
+	return afinfo->family;
+}
+
 const struct seq_operations udp_seq_ops = {
 	.start		= udp_seq_start,
 	.next		= udp_seq_next,
@@ -3415,38 +3545,55 @@ static struct pernet_operations __net_initdata udp_sysctl_ops = {
 DEFINE_BPF_ITER_FUNC(udp, struct bpf_iter_meta *meta,
 		     struct udp_sock *udp_sk, uid_t uid, int bucket)
 
-static int bpf_iter_init_udp(void *priv_data, struct bpf_iter_aux_info *aux)
+static int bpf_iter_udp_realloc_batch(struct bpf_udp_iter_state *iter,
+				      unsigned int new_batch_sz)
 {
-	struct udp_iter_state *st = priv_data;
-	struct udp_seq_afinfo *afinfo;
-	int ret;
+	struct sock **new_batch;
 
-	afinfo = kmalloc(sizeof(*afinfo), GFP_USER | __GFP_NOWARN);
-	if (!afinfo)
+	new_batch = kvmalloc_array(new_batch_sz, sizeof(*new_batch),
+				   GFP_USER | __GFP_NOWARN);
+	if (!new_batch)
 		return -ENOMEM;
 
-	afinfo->family = AF_UNSPEC;
-	afinfo->udp_table = NULL;
-	st->bpf_seq_afinfo = afinfo;
+	bpf_iter_udp_put_batch(iter);
+	kvfree(iter->batch);
+	iter->batch = new_batch;
+	iter->max_sk = new_batch_sz;
+
+	return 0;
+}
+
+#define INIT_BATCH_SZ 16
+
+static int bpf_iter_init_udp(void *priv_data, struct bpf_iter_aux_info *aux)
+{
+	struct bpf_udp_iter_state *iter = priv_data;
+	int ret;
+
 	ret = bpf_iter_init_seq_net(priv_data, aux);
 	if (ret)
-		kfree(afinfo);
+		return ret;
+
+	ret = bpf_iter_udp_realloc_batch(iter, INIT_BATCH_SZ);
+	if (ret)
+		bpf_iter_fini_seq_net(priv_data);
+
 	return ret;
 }
 
 static void bpf_iter_fini_udp(void *priv_data)
 {
-	struct udp_iter_state *st = priv_data;
+	struct bpf_udp_iter_state *iter = priv_data;
 
-	kfree(st->bpf_seq_afinfo);
 	bpf_iter_fini_seq_net(priv_data);
+	kvfree(iter->batch);
 }
 
 static const struct bpf_iter_seq_info udp_seq_info = {
 	.seq_ops		= &bpf_iter_udp_seq_ops,
 	.init_seq_private	= bpf_iter_init_udp,
 	.fini_seq_private	= bpf_iter_fini_udp,
-	.seq_priv_size		= sizeof(struct udp_iter_state),
+	.seq_priv_size		= sizeof(struct bpf_udp_iter_state),
 };
 
 static struct bpf_iter_reg udp_reg_info = {
@@ -3454,7 +3601,7 @@ static struct bpf_iter_reg udp_reg_info = {
 	.ctx_arg_info_size	= 1,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__udp, udp_sk),
-		  PTR_TO_BTF_ID_OR_NULL },
+		  PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED },
 	},
 	.seq_info		= &udp_seq_info,
 };