1 files changed, 129 insertions, 181 deletions

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 0c3040a63ebd..53bcc17c91e4 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -831,7 +831,9 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
 			 */
 			if (!skb_queue_empty(&sk->sk_receive_queue))
 				break;
-			sk_wait_data(sk, &timeo, NULL);
+			ret = sk_wait_data(sk, &timeo, NULL);
+			if (ret < 0)
+				break;
 			if (signal_pending(current)) {
 				ret = sock_intr_errno(timeo);
 				break;
@@ -925,10 +927,11 @@ int tcp_send_mss(struct sock *sk, int *size_goal, int flags)
 	return mss_now;
 }
 
-/* In some cases, both sendmsg() could have added an skb to the write queue,
- * but failed adding payload on it.  We need to remove it to consume less
+/* In some cases, sendmsg() could have added an skb to the write queue,
+ * but failed adding payload on it. We need to remove it to consume less
  * memory, but more importantly be able to generate EPOLLOUT for Edge Trigger
- * epoll() users.
+ * epoll() users. Another reason is that tcp_write_xmit() does not like
+ * finding an empty skb in the write queue.
  */
 void tcp_remove_empty_skb(struct sock *sk)
 {
@@ -1287,6 +1290,7 @@ new_segment:
 
 wait_for_space:
 		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+		tcp_remove_empty_skb(sk);
 		if (copied)
 			tcp_push(sk, flags & ~MSG_MORE, mss_now,
 				 TCP_NAGLE_PUSH, size_goal);
@@ -1621,16 +1625,13 @@ EXPORT_SYMBOL(tcp_read_sock);
 
 int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 {
-	struct tcp_sock *tp = tcp_sk(sk);
-	u32 seq = tp->copied_seq;
 	struct sk_buff *skb;
 	int copied = 0;
-	u32 offset;
 
 	if (sk->sk_state == TCP_LISTEN)
 		return -ENOTCONN;
 
-	while ((skb = tcp_recv_skb(sk, seq, &offset)) != NULL) {
+	while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) {
 		u8 tcp_flags;
 		int used;
 
@@ -1643,13 +1644,10 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 				copied = used;
 			break;
 		}
-		seq += used;
 		copied += used;
 
-		if (tcp_flags & TCPHDR_FIN) {
-			++seq;
+		if (tcp_flags & TCPHDR_FIN)
 			break;
-		}
 	}
 	return copied;
 }
@@ -2448,7 +2446,11 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
 			__sk_flush_backlog(sk);
 		} else {
 			tcp_cleanup_rbuf(sk, copied);
-			sk_wait_data(sk, &timeo, last);
+			err = sk_wait_data(sk, &timeo, last);
+			if (err < 0) {
+				err = copied ? : err;
+				goto out;
+			}
 		}
 
 		if ((flags & MSG_PEEK) &&
@@ -2972,12 +2974,6 @@ int tcp_disconnect(struct sock *sk, int flags)
 	int old_state = sk->sk_state;
 	u32 seq;
 
-	/* Deny disconnect if other threads are blocked in sk_wait_event()
-	 * or inet_wait_for_connect().
-	 */
-	if (sk->sk_wait_pending)
-		return -EBUSY;
-
 	if (old_state != TCP_CLOSE)
 		tcp_set_state(sk, TCP_CLOSE);
 
@@ -3597,6 +3593,31 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 		__tcp_sock_set_quickack(sk, val);
 		break;
 
+	case TCP_AO_REPAIR:
+		err = tcp_ao_set_repair(sk, optval, optlen);
+		break;
+#ifdef CONFIG_TCP_AO
+	case TCP_AO_ADD_KEY:
+	case TCP_AO_DEL_KEY:
+	case TCP_AO_INFO: {
+		/* If this is the first TCP-AO setsockopt() on the socket,
+		 * sk_state has to be LISTEN or CLOSE. Allow TCP_REPAIR
+		 * in any state.
+		 */
+		if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
+			goto ao_parse;
+		if (rcu_dereference_protected(tcp_sk(sk)->ao_info,
+					      lockdep_sock_is_held(sk)))
+			goto ao_parse;
+		if (tp->repair)
+			goto ao_parse;
+		err = -EISCONN;
+		break;
+ao_parse:
+		err = tp->af_specific->ao_parse(sk, optname, optval, optlen);
+		break;
+	}
+#endif
 #ifdef CONFIG_TCP_MD5SIG
 	case TCP_MD5SIG:
 	case TCP_MD5SIG_EXT:
@@ -3635,10 +3656,16 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 			tp->fastopen_no_cookie = val;
 		break;
 	case TCP_TIMESTAMP:
-		if (!tp->repair)
+		if (!tp->repair) {
 			err = -EPERM;
-		else
-			WRITE_ONCE(tp->tsoffset, val - tcp_time_stamp_raw());
+			break;
+		}
+		/* val is an opaque field,
+		 * and low order bit contains usec_ts enable bit.
+		 * Its a best effort, and we do not care if user makes an error.
+		 */
+		tp->tcp_usec_ts = val & 1;
+		WRITE_ONCE(tp->tsoffset, val - tcp_clock_ts(tp->tcp_usec_ts));
 		break;
 	case TCP_REPAIR_WINDOW:
 		err = tcp_repair_set_window(tp, optval, optlen);
@@ -3760,9 +3787,12 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 		info->tcpi_options |= TCPI_OPT_ECN_SEEN;
 	if (tp->syn_data_acked)
 		info->tcpi_options |= TCPI_OPT_SYN_DATA;
+	if (tp->tcp_usec_ts)
+		info->tcpi_options |= TCPI_OPT_USEC_TS;
 
 	info->tcpi_rto = jiffies_to_usecs(icsk->icsk_rto);
-	info->tcpi_ato = jiffies_to_usecs(icsk->icsk_ack.ato);
+	info->tcpi_ato = jiffies_to_usecs(min_t(u32, icsk->icsk_ack.ato,
+						tcp_delack_max(sk)));
 	info->tcpi_snd_mss = tp->mss_cache;
 	info->tcpi_rcv_mss = icsk->icsk_ack.rcv_mss;
 
@@ -3818,6 +3848,13 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	info->tcpi_rcv_wnd = tp->rcv_wnd;
 	info->tcpi_rehash = tp->plb_rehash + tp->timeout_rehash;
 	info->tcpi_fastopen_client_fail = tp->fastopen_client_fail;
+
+	info->tcpi_total_rto = tp->total_rto;
+	info->tcpi_total_rto_recoveries = tp->total_rto_recoveries;
+	info->tcpi_total_rto_time = tp->total_rto_time;
+	if (tp->rto_stamp)
+		info->tcpi_total_rto_time += tcp_clock_ms() - tp->rto_stamp;
+
 	unlock_sock_fast(sk, slow);
 }
 EXPORT_SYMBOL_GPL(tcp_get_info);
@@ -4141,7 +4178,11 @@ int do_tcp_getsockopt(struct sock *sk, int level,
 		break;
 
 	case TCP_TIMESTAMP:
-		val = tcp_time_stamp_raw() + READ_ONCE(tp->tsoffset);
+		val = tcp_clock_ts(tp->tcp_usec_ts) + READ_ONCE(tp->tsoffset);
+		if (tp->tcp_usec_ts)
+			val |= 1;
+		else
+			val &= ~1;
 		break;
 	case TCP_NOTSENT_LOWAT:
 		val = READ_ONCE(tp->notsent_lowat);
@@ -4251,6 +4292,21 @@ zerocopy_rcv_out:
 		return err;
 	}
 #endif
+	case TCP_AO_REPAIR:
+		return tcp_ao_get_repair(sk, optval, optlen);
+	case TCP_AO_GET_KEYS:
+	case TCP_AO_INFO: {
+		int err;
+
+		sockopt_lock_sock(sk);
+		if (optname == TCP_AO_GET_KEYS)
+			err = tcp_ao_get_mkts(sk, optval, optlen);
+		else
+			err = tcp_ao_get_sock_info(sk, optval, optlen);
+		sockopt_release_sock(sk);
+
+		return err;
+	}
 	default:
 		return -ENOPROTOOPT;
 	}
@@ -4289,141 +4345,52 @@ int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval,
 EXPORT_SYMBOL(tcp_getsockopt);
 
 #ifdef CONFIG_TCP_MD5SIG
-static DEFINE_PER_CPU(struct tcp_md5sig_pool, tcp_md5sig_pool);
-static DEFINE_MUTEX(tcp_md5sig_mutex);
-static bool tcp_md5sig_pool_populated = false;
+int tcp_md5_sigpool_id = -1;
+EXPORT_SYMBOL_GPL(tcp_md5_sigpool_id);
 
-static void __tcp_alloc_md5sig_pool(void)
+int tcp_md5_alloc_sigpool(void)
 {
-	struct crypto_ahash *hash;
-	int cpu;
-
-	hash = crypto_alloc_ahash("md5", 0, CRYPTO_ALG_ASYNC);
-	if (IS_ERR(hash))
-		return;
-
-	for_each_possible_cpu(cpu) {
-		void *scratch = per_cpu(tcp_md5sig_pool, cpu).scratch;
-		struct ahash_request *req;
-
-		if (!scratch) {
-			scratch = kmalloc_node(sizeof(union tcp_md5sum_block) +
-					       sizeof(struct tcphdr),
-					       GFP_KERNEL,
-					       cpu_to_node(cpu));
-			if (!scratch)
-				return;
-			per_cpu(tcp_md5sig_pool, cpu).scratch = scratch;
-		}
-		if (per_cpu(tcp_md5sig_pool, cpu).md5_req)
-			continue;
-
-		req = ahash_request_alloc(hash, GFP_KERNEL);
-		if (!req)
-			return;
-
-		ahash_request_set_callback(req, 0, NULL, NULL);
-
-		per_cpu(tcp_md5sig_pool, cpu).md5_req = req;
-	}
-	/* before setting tcp_md5sig_pool_populated, we must commit all writes
-	 * to memory. See smp_rmb() in tcp_get_md5sig_pool()
-	 */
-	smp_wmb();
-	/* Paired with READ_ONCE() from tcp_alloc_md5sig_pool()
-	 * and tcp_get_md5sig_pool().
-	*/
-	WRITE_ONCE(tcp_md5sig_pool_populated, true);
-}
-
-bool tcp_alloc_md5sig_pool(void)
-{
-	/* Paired with WRITE_ONCE() from __tcp_alloc_md5sig_pool() */
-	if (unlikely(!READ_ONCE(tcp_md5sig_pool_populated))) {
-		mutex_lock(&tcp_md5sig_mutex);
-
-		if (!tcp_md5sig_pool_populated)
-			__tcp_alloc_md5sig_pool();
+	size_t scratch_size;
+	int ret;
 
-		mutex_unlock(&tcp_md5sig_mutex);
+	scratch_size = sizeof(union tcp_md5sum_block) + sizeof(struct tcphdr);
+	ret = tcp_sigpool_alloc_ahash("md5", scratch_size);
+	if (ret >= 0) {
+		/* As long as any md5 sigpool was allocated, the return
+		 * id would stay the same. Re-write the id only for the case
+		 * when previously all MD5 keys were deleted and this call
+		 * allocates the first MD5 key, which may return a different
+		 * sigpool id than was used previously.
+		 */
+		WRITE_ONCE(tcp_md5_sigpool_id, ret); /* Avoids the compiler potentially being smart here */
+		return 0;
 	}
-	/* Paired with WRITE_ONCE() from __tcp_alloc_md5sig_pool() */
-	return READ_ONCE(tcp_md5sig_pool_populated);
+	return ret;
 }
-EXPORT_SYMBOL(tcp_alloc_md5sig_pool);
 
-
-/**
- *	tcp_get_md5sig_pool - get md5sig_pool for this user
- *
- *	We use percpu structure, so if we succeed, we exit with preemption
- *	and BH disabled, to make sure another thread or softirq handling
- *	wont try to get same context.
- */
-struct tcp_md5sig_pool *tcp_get_md5sig_pool(void)
+void tcp_md5_release_sigpool(void)
 {
-	local_bh_disable();
-
-	/* Paired with WRITE_ONCE() from __tcp_alloc_md5sig_pool() */
-	if (READ_ONCE(tcp_md5sig_pool_populated)) {
-		/* coupled with smp_wmb() in __tcp_alloc_md5sig_pool() */
-		smp_rmb();
-		return this_cpu_ptr(&tcp_md5sig_pool);
-	}
-	local_bh_enable();
-	return NULL;
+	tcp_sigpool_release(READ_ONCE(tcp_md5_sigpool_id));
 }
-EXPORT_SYMBOL(tcp_get_md5sig_pool);
 
-int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp,
-			  const struct sk_buff *skb, unsigned int header_len)
+void tcp_md5_add_sigpool(void)
 {
-	struct scatterlist sg;
-	const struct tcphdr *tp = tcp_hdr(skb);
-	struct ahash_request *req = hp->md5_req;
-	unsigned int i;
-	const unsigned int head_data_len = skb_headlen(skb) > header_len ?
-					   skb_headlen(skb) - header_len : 0;
-	const struct skb_shared_info *shi = skb_shinfo(skb);
-	struct sk_buff *frag_iter;
-
-	sg_init_table(&sg, 1);
-
-	sg_set_buf(&sg, ((u8 *) tp) + header_len, head_data_len);
-	ahash_request_set_crypt(req, &sg, NULL, head_data_len);
-	if (crypto_ahash_update(req))
-		return 1;
-
-	for (i = 0; i < shi->nr_frags; ++i) {
-		const skb_frag_t *f = &shi->frags[i];
-		unsigned int offset = skb_frag_off(f);
-		struct page *page = skb_frag_page(f) + (offset >> PAGE_SHIFT);
-
-		sg_set_page(&sg, page, skb_frag_size(f),
-			    offset_in_page(offset));
-		ahash_request_set_crypt(req, &sg, NULL, skb_frag_size(f));
-		if (crypto_ahash_update(req))
-			return 1;
-	}
-
-	skb_walk_frags(skb, frag_iter)
-		if (tcp_md5_hash_skb_data(hp, frag_iter, 0))
-			return 1;
-
-	return 0;
+	tcp_sigpool_get(READ_ONCE(tcp_md5_sigpool_id));
 }
-EXPORT_SYMBOL(tcp_md5_hash_skb_data);
 
-int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, const struct tcp_md5sig_key *key)
+int tcp_md5_hash_key(struct tcp_sigpool *hp,
+		     const struct tcp_md5sig_key *key)
 {
 	u8 keylen = READ_ONCE(key->keylen); /* paired with WRITE_ONCE() in tcp_md5_do_add */
 	struct scatterlist sg;
 
 	sg_init_one(&sg, key->key, keylen);
-	ahash_request_set_crypt(hp->md5_req, &sg, NULL, keylen);
+	ahash_request_set_crypt(hp->req, &sg, NULL, keylen);
 
-	/* We use data_race() because tcp_md5_do_add() might change key->key under us */
-	return data_race(crypto_ahash_update(hp->md5_req));
+	/* We use data_race() because tcp_md5_do_add() might change
+	 * key->key under us
+	 */
+	return data_race(crypto_ahash_update(hp->req));
 }
 EXPORT_SYMBOL(tcp_md5_hash_key);
 
@@ -4431,42 +4398,24 @@ EXPORT_SYMBOL(tcp_md5_hash_key);
 enum skb_drop_reason
 tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb,
 		     const void *saddr, const void *daddr,
-		     int family, int dif, int sdif)
+		     int family, int l3index, const __u8 *hash_location)
 {
-	/*
-	 * This gets called for each TCP segment that arrives
-	 * so we want to be efficient.
+	/* This gets called for each TCP segment that has TCP-MD5 option.
 	 * We have 3 drop cases:
 	 * o No MD5 hash and one expected.
 	 * o MD5 hash and we're not expecting one.
 	 * o MD5 hash and its wrong.
 	 */
-	const __u8 *hash_location = NULL;
-	struct tcp_md5sig_key *hash_expected;
-	const struct tcphdr *th = tcp_hdr(skb);
 	const struct tcp_sock *tp = tcp_sk(sk);
-	int genhash, l3index;
+	struct tcp_md5sig_key *key;
 	u8 newhash[16];
+	int genhash;
 
-	/* sdif set, means packet ingressed via a device
-	 * in an L3 domain and dif is set to the l3mdev
-	 */
-	l3index = sdif ? dif : 0;
-
-	hash_expected = tcp_md5_do_lookup(sk, l3index, saddr, family);
-	hash_location = tcp_parse_md5sig_option(th);
-
-	/* We've parsed the options - do we have a hash? */
-	if (!hash_expected && !hash_location)
-		return SKB_NOT_DROPPED_YET;
+	key = tcp_md5_do_lookup(sk, l3index, saddr, family);
 
-	if (hash_expected && !hash_location) {
-		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND);
-		return SKB_DROP_REASON_TCP_MD5NOTFOUND;
-	}
-
-	if (!hash_expected && hash_location) {
+	if (!key && hash_location) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED);
+		tcp_hash_fail("Unexpected MD5 Hash found", family, skb, "");
 		return SKB_DROP_REASON_TCP_MD5UNEXPECTED;
 	}
 
@@ -4475,27 +4424,26 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb,
 	 * IPv4-mapped case.
 	 */
 	if (family == AF_INET)
-		genhash = tcp_v4_md5_hash_skb(newhash,
-					      hash_expected,
-					      NULL, skb);
+		genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, skb);
 	else
-		genhash = tp->af_specific->calc_md5_hash(newhash,
-							 hash_expected,
+		genhash = tp->af_specific->calc_md5_hash(newhash, key,
 							 NULL, skb);
-
 	if (genhash || memcmp(hash_location, newhash, 16) != 0) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE);
 		if (family == AF_INET) {
-			net_info_ratelimited("MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s L3 index %d\n",
-					saddr, ntohs(th->source),
-					daddr, ntohs(th->dest),
-					genhash ? " tcp_v4_calc_md5_hash failed"
-					: "", l3index);
+			tcp_hash_fail("MD5 Hash failed", AF_INET, skb, "%s L3 index %d",
+				      genhash ? "tcp_v4_calc_md5_hash failed"
+				      : "", l3index);
 		} else {
-			net_info_ratelimited("MD5 Hash %s for [%pI6c]:%u->[%pI6c]:%u L3 index %d\n",
-					genhash ? "failed" : "mismatch",
-					saddr, ntohs(th->source),
-					daddr, ntohs(th->dest), l3index);
+			if (genhash) {
+				tcp_hash_fail("MD5 Hash failed",
+					      AF_INET6, skb, "L3 index %d",
+					      l3index);
+			} else {
+				tcp_hash_fail("MD5 Hash mismatch",
+					      AF_INET6, skb, "L3 index %d",
+					      l3index);
+			}
 		}
 		return SKB_DROP_REASON_TCP_MD5FAILURE;
 	}