Commit e08d0b3d authored by Eric Dumazet's avatar Eric Dumazet Committed by David S. Miller
Browse files

inet: implement lockless IP_TOS 



Some reads of inet->tos are racy.

Add needed READ_ONCE() annotations and convert IP_TOS option lockless.

v2: missing changes in include/net/route.h (David Ahern)

Signed-off-by: default avatarEric Dumazet <edumazet@google.com>
Reviewed-by: default avatarDavid Ahern <dsahern@kernel.org>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent ceaa7141

include/net/ip.h

+1 −2
Original line number Diff line number Diff line
@@ -258,7 +258,7 @@ static inline u8 ip_sendmsg_scope(const struct inet_sock *inet, 


static inline __u8 get_rttos(struct ipcm_cookie* ipc, struct inet_sock *inet)

{

	return (ipc->tos != -1) ? RT_TOS(ipc->tos) : RT_TOS(inet->tos);

	return (ipc->tos != -1) ? RT_TOS(ipc->tos) : RT_TOS(READ_ONCE(inet->tos));

}



/* datagram.c */
@@ -810,6 +810,5 @@ int ip_sock_set_mtu_discover(struct sock *sk, int val); 
void ip_sock_set_pktinfo(struct sock *sk);

void ip_sock_set_recverr(struct sock *sk);

void ip_sock_set_tos(struct sock *sk, int val);

void  __ip_sock_set_tos(struct sock *sk, int val);



#endif	/* _IP_H */

include/net/route.h

+2 −2
Original line number Diff line number Diff line
@@ -37,7 +37,7 @@ 


#define RTO_ONLINK	0x01



#define RT_CONN_FLAGS(sk)   (RT_TOS(inet_sk(sk)->tos) | sock_flag(sk, SOCK_LOCALROUTE))

#define RT_CONN_FLAGS(sk)   (RT_TOS(READ_ONCE(inet_sk(sk)->tos)) | sock_flag(sk, SOCK_LOCALROUTE))

#define RT_CONN_FLAGS_TOS(sk,tos)   (RT_TOS(tos) | sock_flag(sk, SOCK_LOCALROUTE))



static inline __u8 ip_sock_rt_scope(const struct sock *sk)
@@ -50,7 +50,7 @@ static inline __u8 ip_sock_rt_scope(const struct sock *sk) 


static inline __u8 ip_sock_rt_tos(const struct sock *sk)

{

	return RT_TOS(inet_sk(sk)->tos);

	return RT_TOS(READ_ONCE(inet_sk(sk)->tos));

}



struct ip_tunnel_info;

net/dccp/ipv4.c

+1 −1
Original line number Diff line number Diff line
@@ -511,7 +511,7 @@ static int dccp_v4_send_response(const struct sock *sk, struct request_sock *req 
		err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,

					    ireq->ir_rmt_addr,

					    rcu_dereference(ireq->ireq_opt),

					    inet_sk(sk)->tos);

					    READ_ONCE(inet_sk(sk)->tos));

		rcu_read_unlock();

		err = net_xmit_eval(err);

	}

net/ipv4/inet_diag.c

+1 −1
Original line number Diff line number Diff line
@@ -134,7 +134,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, 
	 * hence this needs to be included regardless of socket family.

	 */

	if (ext & (1 << (INET_DIAG_TOS - 1)))

		if (nla_put_u8(skb, INET_DIAG_TOS, inet->tos) < 0)

		if (nla_put_u8(skb, INET_DIAG_TOS, READ_ONCE(inet->tos)) < 0)

			goto errout;



#if IS_ENABLED(CONFIG_IPV6)

net/ipv4/ip_output.c

+2 −2
Original line number Diff line number Diff line
@@ -544,7 +544,7 @@ EXPORT_SYMBOL(__ip_queue_xmit); 


int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl)

{

	return __ip_queue_xmit(sk, skb, fl, inet_sk(sk)->tos);

	return __ip_queue_xmit(sk, skb, fl, READ_ONCE(inet_sk(sk)->tos));

}

EXPORT_SYMBOL(ip_queue_xmit);
@@ -1438,7 +1438,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, 
	iph = ip_hdr(skb);

	iph->version = 4;

	iph->ihl = 5;

	iph->tos = (cork->tos != -1) ? cork->tos : inet->tos;

	iph->tos = (cork->tos != -1) ? cork->tos : READ_ONCE(inet->tos);

	iph->frag_off = df;

	iph->ttl = ttl;

	iph->protocol = sk->sk_protocol;