tcp/dccp: fix hashdance race for passive sessions

Multiple cpus can process duplicates of incoming ACK messages
matching a SYN_RECV request socket. This is a rare event under
normal operations, but definitely can happen.

Only one must win the race, otherwise corruption would occur.

To fix this without adding new atomic ops, we use logic in
inet_ehash_nolisten() to detect the request was present in the same
ehash bucket where we try to insert the new child.

If request socket was not found, we have to undo the child creation.

This actually removes a spin_lock()/spin_unlock() pair in
reqsk_queue_unlink() for the fast path.

Fixes: e994b2f0fb92 ("tcp: do not lock listener to process SYN packets")
Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 20 insertions, 13 deletions

diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
index 923f5a1..b0e28d2 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -278,7 +278,9 @@ int dccp_v4_do_rcv(struct sock *sk, struct sk_buff *skb);
 
 struct sock *dccp_v4_request_recv_sock(const struct sock *sk, struct sk_buff *skb,
 				       struct request_sock *req,
-				       struct dst_entry *dst);
+				       struct dst_entry *dst,
+				       struct request_sock *req_unhash,
+				       bool *own_req);
 struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
 			    struct request_sock *req);
 
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 59bc180..5684e14 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -393,7 +393,9 @@ static inline u64 dccp_v4_init_sequence(const struct sk_buff *skb)
 struct sock *dccp_v4_request_recv_sock(const struct sock *sk,
 				       struct sk_buff *skb,
 				       struct request_sock *req,
-				       struct dst_entry *dst)
+				       struct dst_entry *dst,
+				       struct request_sock *req_unhash,
+				       bool *own_req)
 {
 	struct inet_request_sock *ireq;
 	struct inet_sock *newinet;
@@ -426,7 +428,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk,
 
 	if (__inet_inherit_port(sk, newsk) < 0)
 		goto put_and_exit;
-	__inet_hash_nolisten(newsk, NULL);
+	*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
 
 	return newsk;
 
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index d9cc731..ef4e48c 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -380,7 +380,9 @@ drop:
 static struct sock *dccp_v6_request_recv_sock(const struct sock *sk,
 					      struct sk_buff *skb,
 					      struct request_sock *req,
-					      struct dst_entry *dst)
+					      struct dst_entry *dst,
+					      struct request_sock *req_unhash,
+					      bool *own_req)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 	struct ipv6_pinfo *newnp;
@@ -393,7 +395,8 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk,
 		/*
 		 *	v6 mapped
 		 */
-		newsk = dccp_v4_request_recv_sock(sk, skb, req, dst);
+		newsk = dccp_v4_request_recv_sock(sk, skb, req, dst,
+						  req_unhash, own_req);
 		if (newsk == NULL)
 			return NULL;
 
@@ -511,7 +514,7 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk,
 		dccp_done(newsk);
 		goto out;
 	}
-	__inet_hash(newsk, NULL);
+	*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
 
 	return newsk;
 
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index d10aace..1994f8a 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -143,6 +143,7 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
 {
 	struct sock *child = NULL;
 	struct dccp_request_sock *dreq = dccp_rsk(req);
+	bool own_req;
 
 	/* Check for retransmitted REQUEST */
 	if (dccp_hdr(skb)->dccph_type == DCCP_PKT_REQUEST) {
@@ -182,14 +183,13 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
 	if (dccp_parse_options(sk, dreq, skb))
 		 goto drop;
 
-	child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL);
-	if (child == NULL)
+	child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL,
+							 req, &own_req);
+	if (!child)
 		goto listen_overflow;
 
-	inet_csk_reqsk_queue_drop(sk, req);
-	inet_csk_reqsk_queue_add(sk, req, child);
-out:
-	return child;
+	return inet_csk_complete_hashdance(sk, child, req, own_req);
+
 listen_overflow:
 	dccp_pr_debug("listen_overflow!\n");
 	DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_TOO_BUSY;
@@ -198,7 +198,7 @@ drop:
 		req->rsk_ops->send_reset(sk, skb);
 
 	inet_csk_reqsk_queue_drop(sk, req);
-	goto out;
+	return NULL;
 }
 
 EXPORT_SYMBOL_GPL(dccp_check_req);