From 33cf7c90fe2f97afb1cadaa0cfb782cb9d1b9ee2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 11 Mar 2015 18:53:14 -0700 Subject: net: add real socket cookies A long standing problem in netlink socket dumps is the use of kernel socket addresses as cookies. 1) It is a security concern. 2) Sockets can be reused quite quickly, so there is no guarantee a cookie is used once and identify a flow. 3) request sock, establish sock, and timewait socks for a given flow have different cookies. Part of our effort to bring better TCP statistics requires to switch to a different allocator. In this patch, I chose to use a per network namespace 64bit generator, and to use it only in the case a socket needs to be dumped to netlink. (This might be refined later if needed) Note that I tried to carry cookies from request sock, to establish sock, then timewait sockets. Signed-off-by: Eric Dumazet Cc: Eric Salo Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index fb4cf8b8e121..d7045f5f6ebf 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5965,6 +5965,8 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tmp_opt.tstamp_ok = tmp_opt.saw_tstamp; tcp_openreq_init(req, &tmp_opt, skb, sk); + inet_rsk(req)->ireq_net = sock_net(sk); + atomic64_set(&inet_rsk(req)->ir_cookie, 0); af_ops->init_req(req, sk, skb); -- cgit v1.2.3 From d77c555d325d6ece7d352995c97460988c152f58 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 11 Mar 2015 20:27:52 -0700 Subject: net: fix CONFIG_NET_NS=n compilation I forgot to use write_pnet() in three locations. Signed-off-by: Eric Dumazet Fixes: 33cf7c90fe2f9 ("net: add real socket cookies") Reported-by: kbuild test robot Signed-off-by: David S. Miller --- net/dccp/ipv4.c | 2 +- net/ipv4/syncookies.c | 2 +- net/ipv4/tcp_input.c | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 207281ae3536..a78e0b999f96 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -641,7 +641,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) ireq = inet_rsk(req); ireq->ir_loc_addr = ip_hdr(skb)->daddr; ireq->ir_rmt_addr = ip_hdr(skb)->saddr; - ireq->ireq_net = sock_net(sk); + write_pnet(&ireq->ireq_net, sock_net(sk)); atomic64_set(&ireq->ir_cookie, 0); /* diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index ece31b426013..18e5a67fda81 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -346,7 +346,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; treq->snt_synack = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsecr : 0; treq->listener = NULL; - ireq->ireq_net = sock_net(sk); + write_pnet(&ireq->ireq_net, sock_net(sk)); /* We throwed the options of the initial SYN away, so we hope * the ACK carries the same options again (see RFC1122 4.2.3.8) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index d7045f5f6ebf..26f24995bd3d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5965,7 +5965,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tmp_opt.tstamp_ok = tmp_opt.saw_tstamp; tcp_openreq_init(req, &tmp_opt, skb, sk); - inet_rsk(req)->ireq_net = sock_net(sk); + write_pnet(&inet_rsk(req)->ireq_net, sock_net(sk)); atomic64_set(&inet_rsk(req)->ir_cookie, 0); af_ops->init_req(req, sk, skb); -- cgit v1.2.3 From bd337c581b2b0d933d37f664bf55b342577fed3a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 12 Mar 2015 16:44:03 -0700 Subject: ipv6: add missing ireq_net & ir_cookie initializations I forgot to update dccp_v6_conn_request() & cookie_v6_check(). They both need to set ireq->ireq_net and ireq->ir_cookie Lets clear ireq->ir_cookie in inet_reqsk_alloc() Signed-off-by: Eric Dumazet Fixes: 33cf7c90fe2f ("net: add real socket cookies") Signed-off-by: David S. Miller --- include/net/inet_sock.h | 1 + net/dccp/ipv4.c | 1 - net/dccp/ipv6.c | 1 + net/ipv4/tcp_input.c | 1 - net/ipv6/syncookies.c | 1 + 5 files changed, 3 insertions(+), 2 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index e565afdc14ad..30f7170abbf3 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -249,6 +249,7 @@ static inline struct request_sock *inet_reqsk_alloc(struct request_sock_ops *ops if (req != NULL) { kmemcheck_annotate_bitfield(ireq, flags); ireq->opt = NULL; + atomic64_set(&ireq->ir_cookie, 0); } return req; diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index a78e0b999f96..f695874b5ade 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -642,7 +642,6 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) ireq->ir_loc_addr = ip_hdr(skb)->daddr; ireq->ir_rmt_addr = ip_hdr(skb)->saddr; write_pnet(&ireq->ireq_net, sock_net(sk)); - atomic64_set(&ireq->ir_cookie, 0); /* * Step 3: Process LISTEN state diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 6bcaa33cd804..703a21acf434 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -403,6 +403,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) ireq = inet_rsk(req); ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; + write_pnet(&ireq->ireq_net, sock_net(sk)); if (ipv6_opt_accepted(sk, skb, IP6CB(skb)) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 26f24995bd3d..da61a8e75f68 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5966,7 +5966,6 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tmp_opt.tstamp_ok = tmp_opt.saw_tstamp; tcp_openreq_init(req, &tmp_opt, skb, sk); write_pnet(&inet_rsk(req)->ireq_net, sock_net(sk)); - atomic64_set(&inet_rsk(req)->ir_cookie, 0); af_ops->init_req(req, sk, skb); diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 7337fc7947e2..66bba6a84e47 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -196,6 +196,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq = inet_rsk(req); treq = tcp_rsk(req); treq->listener = NULL; + write_pnet(&ireq->ireq_net, sock_net(sk)); if (security_inet_conn_request(sk, skb, req)) goto out_free; -- cgit v1.2.3 From 16f86165bd0a94a96ab99629828cc9057db50221 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 13 Mar 2015 15:51:10 -0700 Subject: inet: fill request sock ir_iif for IPv4 Once request socks will be in ehash table, they will need to have a valid ir_iff field. This is currently true only for IPv6. This patch extends support for IPv4 as well. This means inet_diag_fill_req() can now properly use ir_iif, which is better for IPv6 link locals anyway, as request sockets and established sockets will propagate consistent netlink idiag_if. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/dccp/ipv4.c | 1 + net/ipv4/inet_diag.c | 2 +- net/ipv4/syncookies.c | 2 ++ net/ipv4/tcp_input.c | 3 +++ net/ipv6/tcp_ipv6.c | 2 -- 5 files changed, 7 insertions(+), 3 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 8f6f4004daac..7f6456afbaec 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -643,6 +643,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) ireq->ir_rmt_addr = ip_hdr(skb)->saddr; write_pnet(&ireq->ireq_net, sock_net(sk)); ireq->ireq_family = AF_INET; + ireq->ir_iif = sk->sk_bound_dev_if; /* * Step 3: Process LISTEN state diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 43789c99031f..e1e4d8c0384a 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -733,7 +733,7 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk, r->idiag_timer = 1; r->idiag_retrans = req->num_retrans; - r->id.idiag_if = sk->sk_bound_dev_if; + r->id.idiag_if = ireq->ir_iif; BUILD_BUG_ON(offsetof(struct inet_request_sock, ir_cookie) != offsetof(struct sock, sk_cookie)); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 0c432730c7b4..f17db898ed26 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -349,6 +349,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) write_pnet(&ireq->ireq_net, sock_net(sk)); ireq->ireq_family = AF_INET; + ireq->ir_iif = sk->sk_bound_dev_if; + /* We throwed the options of the initial SYN away, so we hope * the ACK carries the same options again (see RFC1122 4.2.3.8) */ diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index da61a8e75f68..717d437b6ce1 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5967,6 +5967,9 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tcp_openreq_init(req, &tmp_opt, skb, sk); write_pnet(&inet_rsk(req)->ireq_net, sock_net(sk)); + /* Note: tcp_v6_init_req() might override ir_iif for link locals */ + inet_rsk(req)->ir_iif = sk->sk_bound_dev_if; + af_ops->init_req(req, sk, skb); if (security_inet_conn_request(sk, skb, req)) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index c5fc6a5e4adc..d89f028dc8c4 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -734,8 +734,6 @@ static void tcp_v6_init_req(struct request_sock *req, struct sock *sk, ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; - ireq->ir_iif = sk->sk_bound_dev_if; - /* So that link locals have meaning */ if (!sk->sk_bound_dev_if && ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) -- cgit v1.2.3 From 1bfc4438a7ef99e8a6cba0bd3a86249430256621 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 16 Mar 2015 21:06:19 -0700 Subject: tcp: move tcp_openreq_init() to tcp_input.c This big helper is called once from tcp_conn_request(), there is no point having it in an include. Compiler will inline it anyway. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 25 ------------------------- net/ipv4/tcp_input.c | 25 +++++++++++++++++++++++++ 2 files changed, 25 insertions(+), 25 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/include/net/tcp.h b/include/net/tcp.h index 2e11e38205c2..9fe1d535cd6c 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1137,31 +1137,6 @@ static inline int tcp_full_space(const struct sock *sk) return tcp_win_from_space(sk->sk_rcvbuf); } -static inline void tcp_openreq_init(struct request_sock *req, - struct tcp_options_received *rx_opt, - struct sk_buff *skb, struct sock *sk) -{ - struct inet_request_sock *ireq = inet_rsk(req); - - req->rcv_wnd = 0; /* So that tcp_send_synack() knows! */ - req->cookie_ts = 0; - tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq; - tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; - tcp_rsk(req)->snt_synack = tcp_time_stamp; - tcp_rsk(req)->last_oow_ack_time = 0; - req->mss = rx_opt->mss_clamp; - req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0; - ireq->tstamp_ok = rx_opt->tstamp_ok; - ireq->sack_ok = rx_opt->sack_ok; - ireq->snd_wscale = rx_opt->snd_wscale; - ireq->wscale_ok = rx_opt->wscale_ok; - ireq->acked = 0; - ireq->ecn_ok = 0; - ireq->ir_rmt_port = tcp_hdr(skb)->source; - ireq->ir_num = ntohs(tcp_hdr(skb)->dest); - ireq->ir_mark = inet_request_mark(sk, skb); -} - extern void tcp_openreq_init_rwin(struct request_sock *req, struct sock *sk, struct dst_entry *dst); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 717d437b6ce1..10d6bd93f229 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5912,6 +5912,31 @@ static void tcp_ecn_create_request(struct request_sock *req, inet_rsk(req)->ecn_ok = 1; } +static void tcp_openreq_init(struct request_sock *req, + const struct tcp_options_received *rx_opt, + struct sk_buff *skb, const struct sock *sk) +{ + struct inet_request_sock *ireq = inet_rsk(req); + + req->rcv_wnd = 0; /* So that tcp_send_synack() knows! */ + req->cookie_ts = 0; + tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq; + tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; + tcp_rsk(req)->snt_synack = tcp_time_stamp; + tcp_rsk(req)->last_oow_ack_time = 0; + req->mss = rx_opt->mss_clamp; + req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0; + ireq->tstamp_ok = rx_opt->tstamp_ok; + ireq->sack_ok = rx_opt->sack_ok; + ireq->snd_wscale = rx_opt->snd_wscale; + ireq->wscale_ok = rx_opt->wscale_ok; + ireq->acked = 0; + ireq->ecn_ok = 0; + ireq->ir_rmt_port = tcp_hdr(skb)->source; + ireq->ir_num = ntohs(tcp_hdr(skb)->dest); + ireq->ir_mark = inet_request_mark(sk, skb); +} + int tcp_conn_request(struct request_sock_ops *rsk_ops, const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb) -- cgit v1.2.3 From 7970ddc8f9ffe149b392975da60739ccd1796dea Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 16 Mar 2015 21:06:20 -0700 Subject: tcp: uninline tcp_oow_rate_limited() tcp_oow_rate_limited() is hardly used in fast path, there is no point inlining it. Signed-of-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/tcp.h | 32 ++------------------------------ net/ipv4/tcp_input.c | 30 ++++++++++++++++++++++++++++++ 2 files changed, 32 insertions(+), 30 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/include/net/tcp.h b/include/net/tcp.h index 9fe1d535cd6c..5b29835b81d8 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1216,36 +1216,8 @@ static inline bool tcp_paws_reject(const struct tcp_options_received *rx_opt, return true; } -/* Return true if we're currently rate-limiting out-of-window ACKs and - * thus shouldn't send a dupack right now. We rate-limit dupacks in - * response to out-of-window SYNs or ACKs to mitigate ACK loops or DoS - * attacks that send repeated SYNs or ACKs for the same connection. To - * do this, we do not send a duplicate SYNACK or ACK if the remote - * endpoint is sending out-of-window SYNs or pure ACKs at a high rate. - */ -static inline bool tcp_oow_rate_limited(struct net *net, - const struct sk_buff *skb, - int mib_idx, u32 *last_oow_ack_time) -{ - /* Data packets without SYNs are not likely part of an ACK loop. */ - if ((TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) && - !tcp_hdr(skb)->syn) - goto not_rate_limited; - - if (*last_oow_ack_time) { - s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time); - - if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) { - NET_INC_STATS_BH(net, mib_idx); - return true; /* rate-limited: don't send yet! */ - } - } - - *last_oow_ack_time = tcp_time_stamp; - -not_rate_limited: - return false; /* not rate-limited: go ahead, send dupack now! */ -} +bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb, + int mib_idx, u32 *last_oow_ack_time); static inline void tcp_mib_init(struct net *net) { diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 10d6bd93f229..7257eb206c07 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3321,6 +3321,36 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32 return flag; } +/* Return true if we're currently rate-limiting out-of-window ACKs and + * thus shouldn't send a dupack right now. We rate-limit dupacks in + * response to out-of-window SYNs or ACKs to mitigate ACK loops or DoS + * attacks that send repeated SYNs or ACKs for the same connection. To + * do this, we do not send a duplicate SYNACK or ACK if the remote + * endpoint is sending out-of-window SYNs or pure ACKs at a high rate. + */ +bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb, + int mib_idx, u32 *last_oow_ack_time) +{ + /* Data packets without SYNs are not likely part of an ACK loop. */ + if ((TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) && + !tcp_hdr(skb)->syn) + goto not_rate_limited; + + if (*last_oow_ack_time) { + s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time); + + if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) { + NET_INC_STATS_BH(net, mib_idx); + return true; /* rate-limited: don't send yet! */ + } + } + + *last_oow_ack_time = tcp_time_stamp; + +not_rate_limited: + return false; /* not rate-limited: go ahead, send dupack now! */ +} + /* RFC 5961 7 [ACK Throttling] */ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb) { -- cgit v1.2.3 From 407640de2152e33341ce1131dac269672c3d50f7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 17 Mar 2015 18:32:26 -0700 Subject: inet: add sk_listener argument to inet_reqsk_alloc() listener socket can be used to set net pointer, and will be later used to hold a reference on listener. Add a const qualifier to first argument (struct request_sock_ops *), and factorize all write_pnet(&ireq->ireq_net, sock_net(sk)); Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_sock.h | 9 ++++++--- net/dccp/ipv4.c | 3 +-- net/dccp/ipv6.c | 3 +-- net/ipv4/syncookies.c | 3 +-- net/ipv4/tcp_input.c | 3 +-- net/ipv6/syncookies.c | 3 +-- 6 files changed, 11 insertions(+), 13 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index c9ed91891887..cf7abb00941b 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -244,16 +244,19 @@ static inline unsigned int __inet_ehashfn(const __be32 laddr, initval); } -static inline struct request_sock *inet_reqsk_alloc(struct request_sock_ops *ops) +static inline struct request_sock * +inet_reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener) { struct request_sock *req = reqsk_alloc(ops); - struct inet_request_sock *ireq = inet_rsk(req); - if (req != NULL) { + if (req) { + struct inet_request_sock *ireq = inet_rsk(req); + kmemcheck_annotate_bitfield(ireq, flags); ireq->opt = NULL; atomic64_set(&ireq->ir_cookie, 0); ireq->ireq_state = TCP_NEW_SYN_RECV; + write_pnet(&ireq->ireq_net, sock_net(sk_listener)); /* Following is temporary. It is coupled with debugging * helpers in reqsk_put() & reqsk_free() diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 7f6456afbaec..bf897829f4f0 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -624,7 +624,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) goto drop; - req = inet_reqsk_alloc(&dccp_request_sock_ops); + req = inet_reqsk_alloc(&dccp_request_sock_ops, sk); if (req == NULL) goto drop; @@ -641,7 +641,6 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) ireq = inet_rsk(req); ireq->ir_loc_addr = ip_hdr(skb)->daddr; ireq->ir_rmt_addr = ip_hdr(skb)->saddr; - write_pnet(&ireq->ireq_net, sock_net(sk)); ireq->ireq_family = AF_INET; ireq->ir_iif = sk->sk_bound_dev_if; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 5166b0043f95..d7e7c7b0a3f1 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -386,7 +386,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) goto drop; - req = inet_reqsk_alloc(&dccp6_request_sock_ops); + req = inet_reqsk_alloc(&dccp6_request_sock_ops, sk); if (req == NULL) goto drop; @@ -403,7 +403,6 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) ireq = inet_rsk(req); ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; - write_pnet(&ireq->ireq_net, sock_net(sk)); ireq->ireq_family = AF_INET6; if (ipv6_opt_accepted(sk, skb, IP6CB(skb)) || diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 5ae0c49f5e2e..eb940750bb1b 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -325,7 +325,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) goto out; ret = NULL; - req = inet_reqsk_alloc(&tcp_request_sock_ops); /* for safety */ + req = inet_reqsk_alloc(&tcp_request_sock_ops, sk); /* for safety */ if (!req) goto out; @@ -346,7 +346,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; treq->snt_synack = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsecr : 0; treq->listener = NULL; - write_pnet(&ireq->ireq_net, sock_net(sk)); ireq->ireq_family = AF_INET; ireq->ir_iif = sk->sk_bound_dev_if; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 7257eb206c07..2a480f6811ea 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6004,7 +6004,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, goto drop; } - req = inet_reqsk_alloc(rsk_ops); + req = inet_reqsk_alloc(rsk_ops, sk); if (!req) goto drop; @@ -6020,7 +6020,6 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tmp_opt.tstamp_ok = tmp_opt.saw_tstamp; tcp_openreq_init(req, &tmp_opt, skb, sk); - write_pnet(&inet_rsk(req)->ireq_net, sock_net(sk)); /* Note: tcp_v6_init_req() might override ir_iif for link locals */ inet_rsk(req)->ir_iif = sk->sk_bound_dev_if; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 58875ce8e178..039e74dd29fe 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -189,14 +189,13 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) goto out; ret = NULL; - req = inet_reqsk_alloc(&tcp6_request_sock_ops); + req = inet_reqsk_alloc(&tcp6_request_sock_ops, sk); if (!req) goto out; ireq = inet_rsk(req); treq = tcp_rsk(req); treq->listener = NULL; - write_pnet(&ireq->ireq_net, sock_net(sk)); ireq->ireq_family = AF_INET6; if (security_inet_conn_request(sk, skb, req)) -- cgit v1.2.3 From e49bb337d77d54afebe4fe5b9008955e1337f83d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 17 Mar 2015 18:32:27 -0700 Subject: inet: uninline inet_reqsk_alloc() inet_reqsk_alloc() is becoming fat and should not be inlined. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_sock.h | 24 ++---------------------- net/ipv4/tcp_input.c | 24 ++++++++++++++++++++++++ 2 files changed, 26 insertions(+), 22 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index cf7abb00941b..6fec7343070f 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -244,28 +244,8 @@ static inline unsigned int __inet_ehashfn(const __be32 laddr, initval); } -static inline struct request_sock * -inet_reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener) -{ - struct request_sock *req = reqsk_alloc(ops); - - if (req) { - struct inet_request_sock *ireq = inet_rsk(req); - - kmemcheck_annotate_bitfield(ireq, flags); - ireq->opt = NULL; - atomic64_set(&ireq->ir_cookie, 0); - ireq->ireq_state = TCP_NEW_SYN_RECV; - write_pnet(&ireq->ireq_net, sock_net(sk_listener)); - - /* Following is temporary. It is coupled with debugging - * helpers in reqsk_put() & reqsk_free() - */ - atomic_set(&ireq->ireq_refcnt, 0); - } - - return req; -} +struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, + struct sock *sk_listener); static inline __u8 inet_sk_flowi_flags(const struct sock *sk) { diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2a480f6811ea..52b74e0eab2a 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5967,6 +5967,30 @@ static void tcp_openreq_init(struct request_sock *req, ireq->ir_mark = inet_request_mark(sk, skb); } +struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, + struct sock *sk_listener) +{ + struct request_sock *req = reqsk_alloc(ops); + + if (req) { + struct inet_request_sock *ireq = inet_rsk(req); + + kmemcheck_annotate_bitfield(ireq, flags); + ireq->opt = NULL; + atomic64_set(&ireq->ir_cookie, 0); + ireq->ireq_state = TCP_NEW_SYN_RECV; + write_pnet(&ireq->ireq_net, sock_net(sk_listener)); + + /* Following is temporary. It is coupled with debugging + * helpers in reqsk_put() & reqsk_free() + */ + atomic_set(&ireq->ireq_refcnt, 0); + } + + return req; +} +EXPORT_SYMBOL(inet_reqsk_alloc); + int tcp_conn_request(struct request_sock_ops *rsk_ops, const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb) -- cgit v1.2.3 From 4e9a578e5b6bdfa8b7fed7a41f28a86a7cffc85f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 17 Mar 2015 18:32:28 -0700 Subject: inet: add rsk_listener field to struct request_sock Once we'll be able to lookup request sockets in ehash table, we'll need to get access to listener which created this request. This avoid doing a lookup to find the listener, which benefits for a more solid SO_REUSEPORT, and is needed once we no longer queue request sock into a listener private queue. Note that 'struct tcp_request_sock'->listener could be reduced to a single bit, as TFO listener should match req->rsk_listener. TFO will no longer need to hold a reference on the listener. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/request_sock.h | 12 +++++++++--- net/ipv4/tcp_input.c | 2 +- 2 files changed, 10 insertions(+), 4 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 56dc2faba47e..723d1cbdf20e 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -52,6 +52,7 @@ struct request_sock { #define rsk_refcnt __req_common.skc_refcnt struct request_sock *dl_next; + struct sock *rsk_listener; u16 mss; u8 num_retrans; /* number of retransmits */ u8 cookie_ts:1; /* syncookie: encode tcpopts in timestamp */ @@ -67,13 +68,16 @@ struct request_sock { u32 peer_secid; }; -static inline struct request_sock *reqsk_alloc(const struct request_sock_ops *ops) +static inline struct request_sock * +reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener) { struct request_sock *req = kmem_cache_alloc(ops->slab, GFP_ATOMIC); - if (req != NULL) + if (req) { req->rsk_ops = ops; - + sock_hold(sk_listener); + req->rsk_listener = sk_listener; + } return req; } @@ -88,6 +92,8 @@ static inline void reqsk_free(struct request_sock *req) WARN_ON_ONCE(atomic_read(&req->rsk_refcnt) != 0); req->rsk_ops->destructor(req); + if (req->rsk_listener) + sock_put(req->rsk_listener); kmem_cache_free(req->rsk_ops->slab, req); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 52b74e0eab2a..fbe518981d36 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5970,7 +5970,7 @@ static void tcp_openreq_init(struct request_sock *req, struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener) { - struct request_sock *req = reqsk_alloc(ops); + struct request_sock *req = reqsk_alloc(ops, sk_listener); if (req) { struct inet_request_sock *ireq = inet_rsk(req); -- cgit v1.2.3 From 9439ce00f208d95703a6725e4ea986dd90e37ffd Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 17 Mar 2015 18:32:29 -0700 Subject: tcp: rename struct tcp_request_sock listener The listener field in struct tcp_request_sock is a pointer back to the listener. We now have req->rsk_listener, so TCP only needs one boolean and not a full pointer. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 +- net/core/request_sock.c | 18 +++++++----------- net/ipv4/inet_connection_sock.c | 7 +++---- net/ipv4/syncookies.c | 2 +- net/ipv4/tcp_fastopen.c | 7 +------ net/ipv4/tcp_input.c | 2 +- net/ipv6/syncookies.c | 2 +- 7 files changed, 15 insertions(+), 25 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 97dbf16f7d9d..f869ae8afbaf 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -111,7 +111,7 @@ struct tcp_request_sock_ops; struct tcp_request_sock { struct inet_request_sock req; const struct tcp_request_sock_ops *af_specific; - struct sock *listener; /* needed for TFO */ + bool tfo_listener; u32 rcv_isn; u32 snt_isn; u32 snt_synack; /* synack sent time */ diff --git a/net/core/request_sock.c b/net/core/request_sock.c index e910317ef6d9..cc39a2aa663a 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -153,24 +153,22 @@ void reqsk_queue_destroy(struct request_sock_queue *queue) * case might also exist in tcp_v4_hnd_req() that will trigger this locking * order. * - * When a TFO req is created, it needs to sock_hold its listener to prevent - * the latter data structure from going away. - * - * This function also sets "treq->listener" to NULL and unreference listener - * socket. treq->listener is used by the listener so it is protected by the + * This function also sets "treq->tfo_listener" to false. + * treq->tfo_listener is used by the listener so it is protected by the * fastopenq->lock in this function. */ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, bool reset) { - struct sock *lsk = tcp_rsk(req)->listener; - struct fastopen_queue *fastopenq = - inet_csk(lsk)->icsk_accept_queue.fastopenq; + struct sock *lsk = req->rsk_listener; + struct fastopen_queue *fastopenq; + + fastopenq = inet_csk(lsk)->icsk_accept_queue.fastopenq; tcp_sk(sk)->fastopen_rsk = NULL; spin_lock_bh(&fastopenq->lock); fastopenq->qlen--; - tcp_rsk(req)->listener = NULL; + tcp_rsk(req)->tfo_listener = false; if (req->sk) /* the child socket hasn't been accepted yet */ goto out; @@ -179,7 +177,6 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, * special RST handling below. */ spin_unlock_bh(&fastopenq->lock); - sock_put(lsk); reqsk_put(req); return; } @@ -201,5 +198,4 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, fastopenq->qlen++; out: spin_unlock_bh(&fastopenq->lock); - sock_put(lsk); } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 3390ba6f96b2..741f0d96a7f7 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -325,7 +325,7 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err) sk_acceptq_removed(sk); if (sk->sk_protocol == IPPROTO_TCP && queue->fastopenq != NULL) { spin_lock_bh(&queue->fastopenq->lock); - if (tcp_rsk(req)->listener) { + if (tcp_rsk(req)->tfo_listener) { /* We are still waiting for the final ACK from 3WHS * so can't free req now. Instead, we set req->sk to * NULL to signify that the child socket is taken @@ -817,9 +817,9 @@ void inet_csk_listen_stop(struct sock *sk) percpu_counter_inc(sk->sk_prot->orphan_count); - if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->listener) { + if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) { BUG_ON(tcp_sk(child)->fastopen_rsk != req); - BUG_ON(sk != tcp_rsk(req)->listener); + BUG_ON(sk != req->rsk_listener); /* Paranoid, to prevent race condition if * an inbound pkt destined for child is @@ -828,7 +828,6 @@ void inet_csk_listen_stop(struct sock *sk) * tcp_v4_destroy_sock(). */ tcp_sk(child)->fastopen_rsk = NULL; - sock_put(sk); } inet_csk_destroy_sock(child); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index eb940750bb1b..574b67765a06 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -345,7 +345,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) ireq->tstamp_ok = tcp_opt.saw_tstamp; req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; treq->snt_synack = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsecr : 0; - treq->listener = NULL; + treq->tfo_listener = false; ireq->ireq_family = AF_INET; ireq->ir_iif = sk->sk_bound_dev_if; diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 84381319e1bc..186fd394ec0a 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -155,12 +155,7 @@ static bool tcp_fastopen_create_child(struct sock *sk, tp = tcp_sk(child); tp->fastopen_rsk = req; - /* Do a hold on the listner sk so that if the listener is being - * closed, the child that has been accepted can live on and still - * access listen_lock. - */ - sock_hold(sk); - tcp_rsk(req)->listener = sk; + tcp_rsk(req)->tfo_listener = true; /* RFC1323: The window in SYN & SYN/ACK segments is never * scaled. So correct it appropriately. diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index fbe518981d36..a94ddb96fc85 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6120,7 +6120,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, if (err || want_cookie) goto drop_and_free; - tcp_rsk(req)->listener = NULL; + tcp_rsk(req)->tfo_listener = false; af_ops->queue_hash_add(sk, req, TCP_TIMEOUT_INIT); } diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 039e74dd29fe..1ef0c926ce9d 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -195,7 +195,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq = inet_rsk(req); treq = tcp_rsk(req); - treq->listener = NULL; + treq->tfo_listener = false; ireq->ireq_family = AF_INET6; if (security_inet_conn_request(sk, skb, req)) -- cgit v1.2.3 From 0470c8ca1d57927f2cc3e1d5add1fb2834609447 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 17 Mar 2015 18:32:31 -0700 Subject: inet: fix request sock refcounting While testing last patch series, I found req sock refcounting was wrong. We must set skc_refcnt to 1 for all request socks added in hashes, but also on request sockets created by FastOpen or syncookies. It is tricky because we need to defer this initialization so that future RCU lookups do not try to take a refcount on a not yet fully initialized request socket. Also get rid of ireq_refcnt alias. Signed-off-by: Eric Dumazet Fixes: 13854e5a6046 ("inet: add proper refcounting to request sock") Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 5 ----- include/net/inet_sock.h | 1 - include/net/request_sock.h | 11 +++++++++++ net/ipv4/syncookies.c | 11 ++++++----- net/ipv4/tcp_fastopen.c | 1 + net/ipv4/tcp_input.c | 4 ---- net/ipv6/syncookies.c | 7 ++++--- 7 files changed, 22 insertions(+), 18 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 191feec60205..b9a6b0a94cc6 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -275,11 +275,6 @@ static inline void inet_csk_reqsk_queue_add(struct sock *sk, struct sock *child) { reqsk_queue_add(&inet_csk(sk)->icsk_accept_queue, req, sk, child); - /* before letting lookups find us, make sure all req fields - * are committed to memory. - */ - smp_wmb(); - atomic_set(&req->rsk_refcnt, 1); } void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 6fec7343070f..b6c3737da4e9 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -81,7 +81,6 @@ struct inet_request_sock { #define ir_cookie req.__req_common.skc_cookie #define ireq_net req.__req_common.skc_net #define ireq_state req.__req_common.skc_state -#define ireq_refcnt req.__req_common.skc_refcnt #define ireq_family req.__req_common.skc_family kmemcheck_bitfield_begin(flags); diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 723d1cbdf20e..3fa4f824900a 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -77,6 +77,11 @@ reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener) req->rsk_ops = ops; sock_hold(sk_listener); req->rsk_listener = sk_listener; + + /* Following is temporary. It is coupled with debugging + * helpers in reqsk_put() & reqsk_free() + */ + atomic_set(&req->rsk_refcnt, 0); } return req; } @@ -292,6 +297,12 @@ static inline void reqsk_queue_hash_req(struct request_sock_queue *queue, req->sk = NULL; req->dl_next = lopt->syn_table[hash]; + /* before letting lookups find us, make sure all req fields + * are committed to memory and refcnt initialized. + */ + smp_wmb(); + atomic_set(&req->rsk_refcnt, 1); + write_lock(&queue->syn_wait_lock); lopt->syn_table[hash] = req; write_unlock(&queue->syn_wait_lock); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 574b67765a06..34e755403715 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -227,11 +227,12 @@ static struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb, struct sock *child; child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst); - if (child) + if (child) { + atomic_set(&req->rsk_refcnt, 1); inet_csk_reqsk_queue_add(sk, req, child); - else + } else { reqsk_free(req); - + } return child; } @@ -356,7 +357,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) ireq->opt = tcp_v4_save_options(skb); if (security_inet_conn_request(sk, skb, req)) { - reqsk_put(req); + reqsk_free(req); goto out; } @@ -377,7 +378,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) security_req_classify_flow(req, flowi4_to_flowi(&fl4)); rt = ip_route_output_key(sock_net(sk), &fl4); if (IS_ERR(rt)) { - reqsk_put(req); + reqsk_free(req); goto out; } diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 186fd394ec0a..82e375a0cbcf 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -169,6 +169,7 @@ static bool tcp_fastopen_create_child(struct sock *sk, inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS, TCP_TIMEOUT_INIT, TCP_RTO_MAX); + atomic_set(&req->rsk_refcnt, 1); /* Add the child socket directly into the accept queue */ inet_csk_reqsk_queue_add(sk, req, child); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index a94ddb96fc85..1dfbaee3554e 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5981,10 +5981,6 @@ struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, ireq->ireq_state = TCP_NEW_SYN_RECV; write_pnet(&ireq->ireq_net, sock_net(sk_listener)); - /* Following is temporary. It is coupled with debugging - * helpers in reqsk_put() & reqsk_free() - */ - atomic_set(&ireq->ireq_refcnt, 0); } return req; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 1ef0c926ce9d..da5823e5e5a7 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -49,11 +49,12 @@ static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb, struct sock *child; child = icsk->icsk_af_ops->syn_recv_sock(sk, skb, req, dst); - if (child) + if (child) { + atomic_set(&req->rsk_refcnt, 1); inet_csk_reqsk_queue_add(sk, req, child); - else + } else { reqsk_free(req); - + } return child; } -- cgit v1.2.3 From 52452c542559ac980b48dbf22a30ee7fa0af507c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 19 Mar 2015 19:04:19 -0700 Subject: inet: drop prev pointer handling in request sock When request sock are put in ehash table, the whole notion of having a previous request to update dl_next is pointless. Also, following patch will get rid of big purge timer, so we want to delete a request sock without holding listener lock. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet6_connection_sock.h | 1 - include/net/inet_connection_sock.h | 11 ++++------- include/net/request_sock.h | 15 +++++++++++---- include/net/tcp.h | 3 +-- net/dccp/dccp.h | 3 +-- net/dccp/ipv4.c | 14 ++++++-------- net/dccp/ipv6.c | 19 ++++++++----------- net/dccp/minisocks.c | 7 +++---- net/ipv4/inet_connection_sock.c | 22 ++++++++++++---------- net/ipv4/tcp_input.c | 2 +- net/ipv4/tcp_ipv4.c | 17 ++++++++--------- net/ipv4/tcp_minisocks.c | 5 ++--- net/ipv6/inet6_connection_sock.c | 10 ++++------ net/ipv6/tcp_ipv6.c | 12 ++++++------ 14 files changed, 67 insertions(+), 74 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/include/net/inet6_connection_sock.h b/include/net/inet6_connection_sock.h index 74af137304be..15bd40878d2a 100644 --- a/include/net/inet6_connection_sock.h +++ b/include/net/inet6_connection_sock.h @@ -29,7 +29,6 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk, struct flowi6 *fl6, const struct request_sock *req); struct request_sock *inet6_csk_search_req(const struct sock *sk, - struct request_sock ***prevp, const __be16 rport, const struct in6_addr *raddr, const struct in6_addr *laddr, diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index b9a6b0a94cc6..423a46106e57 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -257,7 +257,6 @@ inet_csk_rto_backoff(const struct inet_connection_sock *icsk, struct sock *inet_csk_accept(struct sock *sk, int flags, int *err); struct request_sock *inet_csk_search_req(const struct sock *sk, - struct request_sock ***prevp, const __be16 rport, const __be32 raddr, const __be32 laddr); @@ -310,17 +309,15 @@ static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) } static inline void inet_csk_reqsk_queue_unlink(struct sock *sk, - struct request_sock *req, - struct request_sock **prev) + struct request_sock *req) { - reqsk_queue_unlink(&inet_csk(sk)->icsk_accept_queue, req, prev); + reqsk_queue_unlink(&inet_csk(sk)->icsk_accept_queue, req); } static inline void inet_csk_reqsk_queue_drop(struct sock *sk, - struct request_sock *req, - struct request_sock **prev) + struct request_sock *req) { - inet_csk_reqsk_queue_unlink(sk, req, prev); + inet_csk_reqsk_queue_unlink(sk, req); inet_csk_reqsk_queue_removed(sk, req); reqsk_free(req); } diff --git a/include/net/request_sock.h b/include/net/request_sock.h index e7ef86340514..65223905d139 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -50,6 +50,7 @@ int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req); struct request_sock { struct sock_common __req_common; #define rsk_refcnt __req_common.skc_refcnt +#define rsk_hash __req_common.skc_hash struct request_sock *dl_next; struct sock *rsk_listener; @@ -216,11 +217,16 @@ static inline int reqsk_queue_empty(struct request_sock_queue *queue) } static inline void reqsk_queue_unlink(struct request_sock_queue *queue, - struct request_sock *req, - struct request_sock **prev_req) + struct request_sock *req) { + struct listen_sock *lopt = queue->listen_opt; + struct request_sock **prev; + write_lock(&queue->syn_wait_lock); - *prev_req = req->dl_next; + prev = &lopt->syn_table[req->rsk_hash]; + while (*prev != req) + prev = &(*prev)->dl_next; + *prev = req->dl_next; write_unlock(&queue->syn_wait_lock); } @@ -300,7 +306,6 @@ static inline void reqsk_queue_hash_req(struct request_sock_queue *queue, req->num_retrans = 0; req->num_timeout = 0; req->sk = NULL; - req->dl_next = lopt->syn_table[hash]; /* before letting lookups find us, make sure all req fields * are committed to memory and refcnt initialized. @@ -308,7 +313,9 @@ static inline void reqsk_queue_hash_req(struct request_sock_queue *queue, smp_wmb(); atomic_set(&req->rsk_refcnt, 1); + req->rsk_hash = hash; write_lock(&queue->syn_wait_lock); + req->dl_next = lopt->syn_table[hash]; lopt->syn_table[hash] = req; write_unlock(&queue->syn_wait_lock); } diff --git a/include/net/tcp.h b/include/net/tcp.h index 5b29835b81d8..082fd79132b7 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -406,8 +406,7 @@ enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, const struct tcphdr *th); struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, - struct request_sock *req, struct request_sock **prev, - bool fastopen); + struct request_sock *req, bool fastopen); int tcp_child_process(struct sock *parent, struct sock *child, struct sk_buff *skb); void tcp_enter_loss(struct sock *sk); diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 3b1d64d6e093..2396f50c5b04 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -280,8 +280,7 @@ struct sock *dccp_v4_request_recv_sock(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst); struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, - struct request_sock *req, - struct request_sock **prev); + struct request_sock *req); int dccp_child_process(struct sock *parent, struct sock *child, struct sk_buff *skb); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index e7ad291cd96b..5bffbbaf1fac 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -288,11 +288,11 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) } switch (sk->sk_state) { - struct request_sock *req , **prev; + struct request_sock *req; case DCCP_LISTEN: if (sock_owned_by_user(sk)) goto out; - req = inet_csk_search_req(sk, &prev, dh->dccph_dport, + req = inet_csk_search_req(sk, dh->dccph_dport, iph->daddr, iph->saddr); if (!req) goto out; @@ -314,7 +314,7 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) * created socket, and POSIX does not want network * errors returned from accept(). */ - inet_csk_reqsk_queue_drop(sk, req, prev); + inet_csk_reqsk_queue_drop(sk, req); goto out; case DCCP_REQUESTING: @@ -448,13 +448,11 @@ static struct sock *dccp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) const struct dccp_hdr *dh = dccp_hdr(skb); const struct iphdr *iph = ip_hdr(skb); struct sock *nsk; - struct request_sock **prev; /* Find possible connection requests. */ - struct request_sock *req = inet_csk_search_req(sk, &prev, - dh->dccph_sport, + struct request_sock *req = inet_csk_search_req(sk, dh->dccph_sport, iph->saddr, iph->daddr); - if (req != NULL) - return dccp_check_req(sk, skb, req, prev); + if (req) + return dccp_check_req(sk, skb, req); nsk = inet_lookup_established(sock_net(sk), &dccp_hashinfo, iph->saddr, dh->dccph_sport, diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index c655de5f67c9..ae2184039fe3 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -149,12 +149,12 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, /* Might be for an request_sock */ switch (sk->sk_state) { - struct request_sock *req, **prev; + struct request_sock *req; case DCCP_LISTEN: if (sock_owned_by_user(sk)) goto out; - req = inet6_csk_search_req(sk, &prev, dh->dccph_dport, + req = inet6_csk_search_req(sk, dh->dccph_dport, &hdr->daddr, &hdr->saddr, inet6_iif(skb)); if (req == NULL) @@ -172,7 +172,7 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, goto out; } - inet_csk_reqsk_queue_drop(sk, req, prev); + inet_csk_reqsk_queue_drop(sk, req); goto out; case DCCP_REQUESTING: @@ -317,16 +317,13 @@ static struct sock *dccp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) { const struct dccp_hdr *dh = dccp_hdr(skb); const struct ipv6hdr *iph = ipv6_hdr(skb); + struct request_sock *req; struct sock *nsk; - struct request_sock **prev; - /* Find possible connection requests. */ - struct request_sock *req = inet6_csk_search_req(sk, &prev, - dh->dccph_sport, - &iph->saddr, - &iph->daddr, - inet6_iif(skb)); + + req = inet6_csk_search_req(sk, dh->dccph_sport, &iph->saddr, + &iph->daddr, inet6_iif(skb)); if (req != NULL) - return dccp_check_req(sk, skb, req, prev); + return dccp_check_req(sk, skb, req); nsk = __inet6_lookup_established(sock_net(sk), &dccp_hashinfo, &iph->saddr, dh->dccph_sport, diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index b50dc436db1f..332f7d6d9942 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -152,8 +152,7 @@ EXPORT_SYMBOL_GPL(dccp_create_openreq_child); * as an request_sock. */ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, - struct request_sock *req, - struct request_sock **prev) + struct request_sock *req) { struct sock *child = NULL; struct dccp_request_sock *dreq = dccp_rsk(req); @@ -200,7 +199,7 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, if (child == NULL) goto listen_overflow; - inet_csk_reqsk_queue_unlink(sk, req, prev); + inet_csk_reqsk_queue_unlink(sk, req); inet_csk_reqsk_queue_removed(sk, req); inet_csk_reqsk_queue_add(sk, req, child); out: @@ -212,7 +211,7 @@ drop: if (dccp_hdr(skb)->dccph_type != DCCP_PKT_RESET) req->rsk_ops->send_reset(sk, skb); - inet_csk_reqsk_queue_drop(sk, req, prev); + inet_csk_reqsk_queue_drop(sk, req); goto out; } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index f0f91858aecf..4f57a017928c 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -480,18 +480,17 @@ static inline u32 inet_synq_hash(const __be32 raddr, const __be16 rport, #endif struct request_sock *inet_csk_search_req(const struct sock *sk, - struct request_sock ***prevp, const __be16 rport, const __be32 raddr, const __be32 laddr) { const struct inet_connection_sock *icsk = inet_csk(sk); struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt; - struct request_sock *req, **prev; + struct request_sock *req; - for (prev = &lopt->syn_table[inet_synq_hash(raddr, rport, lopt->hash_rnd, - lopt->nr_table_entries)]; - (req = *prev) != NULL; - prev = &req->dl_next) { + for (req = lopt->syn_table[inet_synq_hash(raddr, rport, lopt->hash_rnd, + lopt->nr_table_entries)]; + req != NULL; + req = req->dl_next) { const struct inet_request_sock *ireq = inet_rsk(req); if (ireq->ir_rmt_port == rport && @@ -499,7 +498,6 @@ struct request_sock *inet_csk_search_req(const struct sock *sk, ireq->ir_loc_addr == laddr && AF_INET_FAMILY(req->rsk_ops->family)) { WARN_ON(req->sk); - *prevp = prev; break; } } @@ -610,7 +608,10 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, i = lopt->clock_hand; do { - reqp=&lopt->syn_table[i]; + reqp = &lopt->syn_table[i]; + if (!*reqp) + goto next_bucket; + write_lock(&queue->syn_wait_lock); while ((req = *reqp) != NULL) { if (time_after_eq(now, req->expires)) { int expire = 0, resend = 0; @@ -635,14 +636,15 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, } /* Drop this request */ - inet_csk_reqsk_queue_unlink(parent, req, reqp); + *reqp = req->dl_next; reqsk_queue_removed(queue, req); reqsk_put(req); continue; } reqp = &req->dl_next; } - + write_unlock(&queue->syn_wait_lock); +next_bucket: i = (i + 1) & (lopt->nr_table_entries - 1); } while (--budget > 0); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 1dfbaee3554e..95caea707f54 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5694,7 +5694,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV && sk->sk_state != TCP_FIN_WAIT1); - if (tcp_check_req(sk, skb, req, NULL, true) == NULL) + if (tcp_check_req(sk, skb, req, true) == NULL) goto discard; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index ddd0b1f25b96..19c3770f1e97 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -458,12 +458,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) } switch (sk->sk_state) { - struct request_sock *req, **prev; + struct request_sock *req; case TCP_LISTEN: if (sock_owned_by_user(sk)) goto out; - req = inet_csk_search_req(sk, &prev, th->dest, + req = inet_csk_search_req(sk, th->dest, iph->daddr, iph->saddr); if (!req) goto out; @@ -484,7 +484,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) * created socket, and POSIX does not want network * errors returned from accept(). */ - inet_csk_reqsk_queue_drop(sk, req, prev); + inet_csk_reqsk_queue_drop(sk, req); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); goto out; @@ -1392,15 +1392,14 @@ EXPORT_SYMBOL(tcp_v4_syn_recv_sock); static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) { - struct tcphdr *th = tcp_hdr(skb); + const struct tcphdr *th = tcp_hdr(skb); const struct iphdr *iph = ip_hdr(skb); + struct request_sock *req; struct sock *nsk; - struct request_sock **prev; - /* Find possible connection requests. */ - struct request_sock *req = inet_csk_search_req(sk, &prev, th->source, - iph->saddr, iph->daddr); + + req = inet_csk_search_req(sk, th->source, iph->saddr, iph->daddr); if (req) - return tcp_check_req(sk, skb, req, prev, false); + return tcp_check_req(sk, skb, req, false); nsk = inet_lookup_established(sock_net(sk), &tcp_hashinfo, iph->saddr, th->source, iph->daddr, th->dest, inet_iif(skb)); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index dd11ac7798c6..848bcab358e4 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -572,7 +572,6 @@ EXPORT_SYMBOL(tcp_create_openreq_child); struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, struct request_sock *req, - struct request_sock **prev, bool fastopen) { struct tcp_options_received tmp_opt; @@ -766,7 +765,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, if (child == NULL) goto listen_overflow; - inet_csk_reqsk_queue_unlink(sk, req, prev); + inet_csk_reqsk_queue_unlink(sk, req); inet_csk_reqsk_queue_removed(sk, req); inet_csk_reqsk_queue_add(sk, req, child); @@ -791,7 +790,7 @@ embryonic_reset: tcp_reset(sk); } if (!fastopen) { - inet_csk_reqsk_queue_drop(sk, req, prev); + inet_csk_reqsk_queue_drop(sk, req); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_EMBRYONICRSTS); } return NULL; diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 29b32206e494..b7acb9ebc4f5 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -113,7 +113,6 @@ static u32 inet6_synq_hash(const struct in6_addr *raddr, const __be16 rport, } struct request_sock *inet6_csk_search_req(const struct sock *sk, - struct request_sock ***prevp, const __be16 rport, const struct in6_addr *raddr, const struct in6_addr *laddr, @@ -121,13 +120,13 @@ struct request_sock *inet6_csk_search_req(const struct sock *sk, { const struct inet_connection_sock *icsk = inet_csk(sk); struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt; - struct request_sock *req, **prev; + struct request_sock *req; - for (prev = &lopt->syn_table[inet6_synq_hash(raddr, rport, + for (req = lopt->syn_table[inet6_synq_hash(raddr, rport, lopt->hash_rnd, lopt->nr_table_entries)]; - (req = *prev) != NULL; - prev = &req->dl_next) { + req != NULL; + req = req->dl_next) { const struct inet_request_sock *ireq = inet_rsk(req); if (ireq->ir_rmt_port == rport && @@ -136,7 +135,6 @@ struct request_sock *inet6_csk_search_req(const struct sock *sk, ipv6_addr_equal(&ireq->ir_v6_loc_addr, laddr) && (!ireq->ir_iif || ireq->ir_iif == iif)) { WARN_ON(req->sk != NULL); - *prevp = prev; return req; } } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 720676d073d9..146f123b52c9 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -403,13 +403,13 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, /* Might be for an request_sock */ switch (sk->sk_state) { - struct request_sock *req, **prev; + struct request_sock *req; case TCP_LISTEN: if (sock_owned_by_user(sk)) goto out; /* Note : We use inet6_iif() here, not tcp_v6_iif() */ - req = inet6_csk_search_req(sk, &prev, th->dest, &hdr->daddr, + req = inet6_csk_search_req(sk, th->dest, &hdr->daddr, &hdr->saddr, inet6_iif(skb)); if (!req) goto out; @@ -424,7 +424,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, goto out; } - inet_csk_reqsk_queue_drop(sk, req, prev); + inet_csk_reqsk_queue_drop(sk, req); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); goto out; @@ -980,16 +980,16 @@ static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, static struct sock *tcp_v6_hnd_req(struct sock *sk, struct sk_buff *skb) { - struct request_sock *req, **prev; const struct tcphdr *th = tcp_hdr(skb); + struct request_sock *req; struct sock *nsk; /* Find possible connection requests. */ - req = inet6_csk_search_req(sk, &prev, th->source, + req = inet6_csk_search_req(sk, th->source, &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, tcp_v6_iif(skb)); if (req) - return tcp_check_req(sk, skb, req, prev, false); + return tcp_check_req(sk, skb, req, false); nsk = __inet6_lookup_established(sock_net(sk), &tcp_hashinfo, &ipv6_hdr(skb)->saddr, th->source, -- cgit v1.2.3 From 0144a81cccf7532bead90f0542f517bd028d3b3c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 24 Mar 2015 21:45:56 -0700 Subject: tcp: fix ipv4 mapped request socks ss should display ipv4 mapped request sockets like this : tcp SYN-RECV 0 0 ::ffff:192.168.0.1:8080 ::ffff:192.0.2.1:35261 and not like this : tcp SYN-RECV 0 0 192.168.0.1:8080 192.0.2.1:35261 We should init ireq->ireq_family based on listener sk_family, not the actual protocol carried by SYN packet. This means we can set ireq_family in inet_reqsk_alloc() Fixes: 3f66b083a5b7 ("inet: introduce ireq_family") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/syncookies.c | 1 - net/ipv4/tcp_input.c | 2 +- net/ipv4/tcp_ipv4.c | 1 - net/ipv6/syncookies.c | 1 - net/ipv6/tcp_ipv6.c | 1 - 5 files changed, 1 insertion(+), 5 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 805dc444741d..df849e5a10f1 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -347,7 +347,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; treq->snt_synack = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsecr : 0; treq->tfo_listener = false; - ireq->ireq_family = AF_INET; ireq->ir_iif = sk->sk_bound_dev_if; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 95caea707f54..023196f7ec37 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5980,7 +5980,7 @@ struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, atomic64_set(&ireq->ir_cookie, 0); ireq->ireq_state = TCP_NEW_SYN_RECV; write_pnet(&ireq->ireq_net, sock_net(sk_listener)); - + ireq->ireq_family = sk_listener->sk_family; } return req; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index fc8995a702a6..e073517b2cc7 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1206,7 +1206,6 @@ static void tcp_v4_init_req(struct request_sock *req, struct sock *sk_listener, sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr); ireq->no_srccheck = inet_sk(sk_listener)->transparent; ireq->opt = tcp_v4_save_options(skb); - ireq->ireq_family = AF_INET; } static struct dst_entry *tcp_v4_route_req(struct sock *sk, struct flowi *fl, diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 2819137fc87d..21bc2eb53c57 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -197,7 +197,6 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq = inet_rsk(req); treq = tcp_rsk(req); treq->tfo_listener = false; - ireq->ireq_family = AF_INET6; if (security_inet_conn_request(sk, skb, req)) goto out_free; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index a9568caf4675..cbdf6912d2c6 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -688,7 +688,6 @@ static void tcp_v6_init_req(struct request_sock *req, struct sock *sk, atomic_inc(&skb->users); ireq->pktopts = skb; } - ireq->ireq_family = AF_INET6; } static struct dst_entry *tcp_v6_route_req(struct sock *sk, struct flowi *fl, -- cgit v1.2.3 From 41d25fe0927aabb1d4b671871a99a55bcd203257 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 25 Mar 2015 15:08:47 -0700 Subject: tcp: tcp_syn_flood_action() can be static After commit 1fb6f159fd21 ("tcp: add tcp_conn_request"), tcp_syn_flood_action() is no longer used from IPv6. We can make it static, by moving it above tcp_conn_request() Signed-off-by: Eric Dumazet Reviewed-by: Octavian Purdila Signed-off-by: David S. Miller --- include/net/tcp.h | 2 -- net/ipv4/tcp_input.c | 29 +++++++++++++++++++++++++++++ net/ipv4/tcp_ipv4.c | 29 ----------------------------- 3 files changed, 29 insertions(+), 31 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/include/net/tcp.h b/include/net/tcp.h index 42690daa924e..963303fb96ae 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -529,8 +529,6 @@ int tcp_write_wakeup(struct sock *); void tcp_send_fin(struct sock *sk); void tcp_send_active_reset(struct sock *sk, gfp_t priority); int tcp_send_synack(struct sock *); -bool tcp_syn_flood_action(struct sock *sk, const struct sk_buff *skb, - const char *proto); void tcp_push_one(struct sock *, unsigned int mss_now); void tcp_send_ack(struct sock *sk); void tcp_send_delayed_ack(struct sock *sk); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 023196f7ec37..18b80e8bc533 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5987,6 +5987,35 @@ struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, } EXPORT_SYMBOL(inet_reqsk_alloc); +/* + * Return true if a syncookie should be sent + */ +static bool tcp_syn_flood_action(struct sock *sk, + const struct sk_buff *skb, + const char *proto) +{ + const char *msg = "Dropping request"; + bool want_cookie = false; + struct listen_sock *lopt; + +#ifdef CONFIG_SYN_COOKIES + if (sysctl_tcp_syncookies) { + msg = "Sending cookies"; + want_cookie = true; + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDOCOOKIES); + } else +#endif + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP); + + lopt = inet_csk(sk)->icsk_accept_queue.listen_opt; + if (!lopt->synflood_warned && sysctl_tcp_syncookies != 2) { + lopt->synflood_warned = 1; + pr_info("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n", + proto, ntohs(tcp_hdr(skb)->dest), msg); + } + return want_cookie; +} + int tcp_conn_request(struct request_sock_ops *rsk_ops, const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index e073517b2cc7..5aababa20a21 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -856,35 +856,6 @@ static void tcp_v4_reqsk_destructor(struct request_sock *req) kfree(inet_rsk(req)->opt); } -/* - * Return true if a syncookie should be sent - */ -bool tcp_syn_flood_action(struct sock *sk, - const struct sk_buff *skb, - const char *proto) -{ - const char *msg = "Dropping request"; - bool want_cookie = false; - struct listen_sock *lopt; - -#ifdef CONFIG_SYN_COOKIES - if (sysctl_tcp_syncookies) { - msg = "Sending cookies"; - want_cookie = true; - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDOCOOKIES); - } else -#endif - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP); - - lopt = inet_csk(sk)->icsk_accept_queue.listen_opt; - if (!lopt->synflood_warned && sysctl_tcp_syncookies != 2) { - lopt->synflood_warned = 1; - pr_info("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n", - proto, ntohs(tcp_hdr(skb)->dest), msg); - } - return want_cookie; -} -EXPORT_SYMBOL(tcp_syn_flood_action); #ifdef CONFIG_TCP_MD5SIG /* -- cgit v1.2.3 From 51456b2914a34d16b1255b7c55d5cbf6a681d306 Mon Sep 17 00:00:00 2001 From: Ian Morris Date: Fri, 3 Apr 2015 09:17:26 +0100 Subject: ipv4: coding style: comparison for equality with NULL The ipv4 code uses a mixture of coding styles. In some instances check for NULL pointer is done as x == NULL and sometimes as !x. !x is preferred according to checkpatch and this patch makes the code consistent by adopting the latter form. No changes detected by objdiff. Signed-off-by: Ian Morris Signed-off-by: David S. Miller --- net/ipv4/af_inet.c | 6 +++--- net/ipv4/arp.c | 26 ++++++++++++------------- net/ipv4/cipso_ipv4.c | 36 +++++++++++++++++----------------- net/ipv4/devinet.c | 40 +++++++++++++++++++------------------- net/ipv4/esp4.c | 2 +- net/ipv4/fib_frontend.c | 26 ++++++++++++------------- net/ipv4/fib_rules.c | 4 ++-- net/ipv4/fib_semantics.c | 24 +++++++++++------------ net/ipv4/fib_trie.c | 12 ++++++------ net/ipv4/geneve.c | 2 +- net/ipv4/gre_offload.c | 2 +- net/ipv4/icmp.c | 6 +++--- net/ipv4/igmp.c | 12 ++++++------ net/ipv4/inet_fragment.c | 4 ++-- net/ipv4/ip_fragment.c | 11 ++++++----- net/ipv4/ip_gre.c | 4 ++-- net/ipv4/ip_input.c | 5 +++-- net/ipv4/ip_output.c | 23 ++++++++++++---------- net/ipv4/ip_sockglue.c | 4 ++-- net/ipv4/ip_tunnel.c | 8 ++++---- net/ipv4/ipcomp.c | 2 +- net/ipv4/ipconfig.c | 6 ++++-- net/ipv4/ipip.c | 2 +- net/ipv4/ipmr.c | 48 +++++++++++++++++++++++----------------------- net/ipv4/ping.c | 2 +- net/ipv4/raw.c | 2 +- net/ipv4/route.c | 20 +++++++++---------- net/ipv4/sysctl_net_ipv4.c | 6 +++--- net/ipv4/tcp.c | 2 +- net/ipv4/tcp_fastopen.c | 6 +++--- net/ipv4/tcp_input.c | 16 ++++++++-------- net/ipv4/tcp_ipv4.c | 6 +++--- net/ipv4/tcp_metrics.c | 2 +- net/ipv4/tcp_minisocks.c | 2 +- net/ipv4/tcp_output.c | 21 ++++++++++---------- net/ipv4/udp.c | 6 +++--- net/ipv4/udp_diag.c | 2 +- net/ipv4/xfrm4_input.c | 2 +- net/ipv4/xfrm4_policy.c | 2 +- 39 files changed, 210 insertions(+), 202 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 64a9c0fdc4aa..7d3b00c01bc8 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -217,7 +217,7 @@ int inet_listen(struct socket *sock, int backlog) * shutdown() (rather than close()). */ if ((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) != 0 && - inet_csk(sk)->icsk_accept_queue.fastopenq == NULL) { + !inet_csk(sk)->icsk_accept_queue.fastopenq) { if ((sysctl_tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) != 0) err = fastopen_init_queue(sk, backlog); else if ((sysctl_tcp_fastopen & @@ -314,11 +314,11 @@ lookup_protocol: answer_flags = answer->flags; rcu_read_unlock(); - WARN_ON(answer_prot->slab == NULL); + WARN_ON(!answer_prot->slab); err = -ENOBUFS; sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot); - if (sk == NULL) + if (!sk) goto out; err = 0; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 5f5c674e130a..ffe84226a2c8 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -228,7 +228,7 @@ static int arp_constructor(struct neighbour *neigh) rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); - if (in_dev == NULL) { + if (!in_dev) { rcu_read_unlock(); return -EINVAL; } @@ -475,7 +475,7 @@ static inline int arp_fwd_pvlan(struct in_device *in_dev, */ /* - * Create an arp packet. If (dest_hw == NULL), we create a broadcast + * Create an arp packet. If dest_hw is not set, we create a broadcast * message. */ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, @@ -495,7 +495,7 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, */ skb = alloc_skb(arp_hdr_len(dev) + hlen + tlen, GFP_ATOMIC); - if (skb == NULL) + if (!skb) return NULL; skb_reserve(skb, hlen); @@ -503,9 +503,9 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, arp = (struct arphdr *) skb_put(skb, arp_hdr_len(dev)); skb->dev = dev; skb->protocol = htons(ETH_P_ARP); - if (src_hw == NULL) + if (!src_hw) src_hw = dev->dev_addr; - if (dest_hw == NULL) + if (!dest_hw) dest_hw = dev->broadcast; /* @@ -614,7 +614,7 @@ void arp_send(int type, int ptype, __be32 dest_ip, skb = arp_create(type, ptype, dest_ip, dev, src_ip, dest_hw, src_hw, target_hw); - if (skb == NULL) + if (!skb) return; arp_xmit(skb); @@ -644,7 +644,7 @@ static int arp_process(struct sk_buff *skb) * is ARP'able. */ - if (in_dev == NULL) + if (!in_dev) goto out; arp = arp_hdr(skb); @@ -808,7 +808,7 @@ static int arp_process(struct sk_buff *skb) is_garp = arp->ar_op == htons(ARPOP_REQUEST) && tip == sip && inet_addr_type(net, sip) == RTN_UNICAST; - if (n == NULL && + if (!n && ((arp->ar_op == htons(ARPOP_REPLY) && inet_addr_type(net, sip) == RTN_UNICAST) || is_garp)) n = __neigh_lookup(&arp_tbl, &sip, dev, 1); @@ -900,7 +900,7 @@ out_of_mem: static int arp_req_set_proxy(struct net *net, struct net_device *dev, int on) { - if (dev == NULL) { + if (!dev) { IPV4_DEVCONF_ALL(net, PROXY_ARP) = on; return 0; } @@ -926,7 +926,7 @@ static int arp_req_set_public(struct net *net, struct arpreq *r, return -ENODEV; } if (mask) { - if (pneigh_lookup(&arp_tbl, net, &ip, dev, 1) == NULL) + if (!pneigh_lookup(&arp_tbl, net, &ip, dev, 1)) return -ENOBUFS; return 0; } @@ -947,7 +947,7 @@ static int arp_req_set(struct net *net, struct arpreq *r, ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; if (r->arp_flags & ATF_PERM) r->arp_flags |= ATF_COM; - if (dev == NULL) { + if (!dev) { struct rtable *rt = ip_route_output(net, ip, 0, RTO_ONLINK, 0); if (IS_ERR(rt)) @@ -1067,7 +1067,7 @@ static int arp_req_delete(struct net *net, struct arpreq *r, return arp_req_delete_public(net, r, dev); ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; - if (dev == NULL) { + if (!dev) { struct rtable *rt = ip_route_output(net, ip, 0, RTO_ONLINK, 0); if (IS_ERR(rt)) return PTR_ERR(rt); @@ -1116,7 +1116,7 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg) if (r.arp_dev[0]) { err = -ENODEV; dev = __dev_get_by_name(net, r.arp_dev); - if (dev == NULL) + if (!dev) goto out; /* Mmmm... It is wrong... ARPHRD_NETROM==0 */ diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index e361ea6f3fc8..1b28e1183c1b 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -255,7 +255,7 @@ static int __init cipso_v4_cache_init(void) cipso_v4_cache = kcalloc(CIPSO_V4_CACHE_BUCKETS, sizeof(struct cipso_v4_map_cache_bkt), GFP_KERNEL); - if (cipso_v4_cache == NULL) + if (!cipso_v4_cache) return -ENOMEM; for (iter = 0; iter < CIPSO_V4_CACHE_BUCKETS; iter++) { @@ -339,7 +339,7 @@ static int cipso_v4_cache_check(const unsigned char *key, secattr->cache = entry->lsm_data; secattr->flags |= NETLBL_SECATTR_CACHE; secattr->type = NETLBL_NLTYPE_CIPSOV4; - if (prev_entry == NULL) { + if (!prev_entry) { spin_unlock_bh(&cipso_v4_cache[bkt].lock); return 0; } @@ -393,10 +393,10 @@ int cipso_v4_cache_add(const unsigned char *cipso_ptr, cipso_ptr_len = cipso_ptr[1]; entry = kzalloc(sizeof(*entry), GFP_ATOMIC); - if (entry == NULL) + if (!entry) return -ENOMEM; entry->key = kmemdup(cipso_ptr, cipso_ptr_len, GFP_ATOMIC); - if (entry->key == NULL) { + if (!entry->key) { ret_val = -ENOMEM; goto cache_add_failure; } @@ -547,7 +547,7 @@ doi_add_return: */ void cipso_v4_doi_free(struct cipso_v4_doi *doi_def) { - if (doi_def == NULL) + if (!doi_def) return; switch (doi_def->type) { @@ -598,7 +598,7 @@ int cipso_v4_doi_remove(u32 doi, struct netlbl_audit *audit_info) spin_lock(&cipso_v4_doi_list_lock); doi_def = cipso_v4_doi_search(doi); - if (doi_def == NULL) { + if (!doi_def) { spin_unlock(&cipso_v4_doi_list_lock); ret_val = -ENOENT; goto doi_remove_return; @@ -644,7 +644,7 @@ struct cipso_v4_doi *cipso_v4_doi_getdef(u32 doi) rcu_read_lock(); doi_def = cipso_v4_doi_search(doi); - if (doi_def == NULL) + if (!doi_def) goto doi_getdef_return; if (!atomic_inc_not_zero(&doi_def->refcount)) doi_def = NULL; @@ -664,7 +664,7 @@ doi_getdef_return: */ void cipso_v4_doi_putdef(struct cipso_v4_doi *doi_def) { - if (doi_def == NULL) + if (!doi_def) return; if (!atomic_dec_and_test(&doi_def->refcount)) @@ -1642,7 +1642,7 @@ int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option) rcu_read_lock(); doi_def = cipso_v4_doi_search(get_unaligned_be32(&opt[2])); - if (doi_def == NULL) { + if (!doi_def) { err_offset = 2; goto validate_return_locked; } @@ -1736,7 +1736,7 @@ int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option) * not the loopback device drop the packet. Further, * there is no legitimate reason for setting this from * userspace so reject it if skb is NULL. */ - if (skb == NULL || !(skb->dev->flags & IFF_LOOPBACK)) { + if (!skb || !(skb->dev->flags & IFF_LOOPBACK)) { err_offset = opt_iter; goto validate_return_locked; } @@ -1897,7 +1897,7 @@ int cipso_v4_sock_setattr(struct sock *sk, * defined yet but it is not a problem as the only users of these * "lite" PF_INET sockets are functions which do an accept() call * afterwards so we will label the socket as part of the accept(). */ - if (sk == NULL) + if (!sk) return 0; /* We allocate the maximum CIPSO option size here so we are probably @@ -1905,7 +1905,7 @@ int cipso_v4_sock_setattr(struct sock *sk, * on and after all we are only talking about 40 bytes. */ buf_len = CIPSO_V4_OPT_LEN_MAX; buf = kmalloc(buf_len, GFP_ATOMIC); - if (buf == NULL) { + if (!buf) { ret_val = -ENOMEM; goto socket_setattr_failure; } @@ -1921,7 +1921,7 @@ int cipso_v4_sock_setattr(struct sock *sk, * set the IPOPT_CIPSO option. */ opt_len = (buf_len + 3) & ~3; opt = kzalloc(sizeof(*opt) + opt_len, GFP_ATOMIC); - if (opt == NULL) { + if (!opt) { ret_val = -ENOMEM; goto socket_setattr_failure; } @@ -1981,7 +1981,7 @@ int cipso_v4_req_setattr(struct request_sock *req, * on and after all we are only talking about 40 bytes. */ buf_len = CIPSO_V4_OPT_LEN_MAX; buf = kmalloc(buf_len, GFP_ATOMIC); - if (buf == NULL) { + if (!buf) { ret_val = -ENOMEM; goto req_setattr_failure; } @@ -1997,7 +1997,7 @@ int cipso_v4_req_setattr(struct request_sock *req, * set the IPOPT_CIPSO option. */ opt_len = (buf_len + 3) & ~3; opt = kzalloc(sizeof(*opt) + opt_len, GFP_ATOMIC); - if (opt == NULL) { + if (!opt) { ret_val = -ENOMEM; goto req_setattr_failure; } @@ -2102,7 +2102,7 @@ void cipso_v4_sock_delattr(struct sock *sk) sk_inet = inet_sk(sk); opt = rcu_dereference_protected(sk_inet->inet_opt, 1); - if (opt == NULL || opt->opt.cipso == 0) + if (!opt || opt->opt.cipso == 0) return; hdr_delta = cipso_v4_delopt(&sk_inet->inet_opt); @@ -2128,7 +2128,7 @@ void cipso_v4_req_delattr(struct request_sock *req) req_inet = inet_rsk(req); opt = req_inet->opt; - if (opt == NULL || opt->opt.cipso == 0) + if (!opt || opt->opt.cipso == 0) return; cipso_v4_delopt(&req_inet->opt); @@ -2157,7 +2157,7 @@ int cipso_v4_getattr(const unsigned char *cipso, doi = get_unaligned_be32(&cipso[2]); rcu_read_lock(); doi_def = cipso_v4_doi_search(doi); - if (doi_def == NULL) + if (!doi_def) goto getattr_return; /* XXX - This code assumes only one tag per CIPSO option which isn't * really a good assumption to make but since we only support the MAC diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index c6473f365ad1..0ee21689d37e 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -585,7 +585,7 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh) ifm = nlmsg_data(nlh); in_dev = inetdev_by_index(net, ifm->ifa_index); - if (in_dev == NULL) { + if (!in_dev) { err = -ENODEV; goto errout; } @@ -755,21 +755,21 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, ifm = nlmsg_data(nlh); err = -EINVAL; - if (ifm->ifa_prefixlen > 32 || tb[IFA_LOCAL] == NULL) + if (ifm->ifa_prefixlen > 32 || !tb[IFA_LOCAL]) goto errout; dev = __dev_get_by_index(net, ifm->ifa_index); err = -ENODEV; - if (dev == NULL) + if (!dev) goto errout; in_dev = __in_dev_get_rtnl(dev); err = -ENOBUFS; - if (in_dev == NULL) + if (!in_dev) goto errout; ifa = inet_alloc_ifa(); - if (ifa == NULL) + if (!ifa) /* * A potential indev allocation can be left alive, it stays * assigned to its device and is destroy with it. @@ -780,7 +780,7 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh, neigh_parms_data_state_setall(in_dev->arp_parms); in_dev_hold(in_dev); - if (tb[IFA_ADDRESS] == NULL) + if (!tb[IFA_ADDRESS]) tb[IFA_ADDRESS] = tb[IFA_LOCAL]; INIT_HLIST_NODE(&ifa->hash); @@ -1340,7 +1340,7 @@ static void inetdev_changename(struct net_device *dev, struct in_device *in_dev) if (named++ == 0) goto skip; dot = strchr(old, ':'); - if (dot == NULL) { + if (!dot) { sprintf(old, ":%d", named); dot = old; } @@ -1509,7 +1509,7 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, u32 preferred, valid; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*ifm), flags); - if (nlh == NULL) + if (!nlh) return -EMSGSIZE; ifm = nlmsg_data(nlh); @@ -1628,7 +1628,7 @@ static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh, net = dev_net(ifa->ifa_dev->dev); skb = nlmsg_new(inet_nlmsg_size(), GFP_KERNEL); - if (skb == NULL) + if (!skb) goto errout; err = inet_fill_ifaddr(skb, ifa, portid, seq, event, 0); @@ -1665,7 +1665,7 @@ static int inet_fill_link_af(struct sk_buff *skb, const struct net_device *dev) return -ENODATA; nla = nla_reserve(skb, IFLA_INET_CONF, IPV4_DEVCONF_MAX * 4); - if (nla == NULL) + if (!nla) return -EMSGSIZE; for (i = 0; i < IPV4_DEVCONF_MAX; i++) @@ -1754,7 +1754,7 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex, nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct netconfmsg), flags); - if (nlh == NULL) + if (!nlh) return -EMSGSIZE; ncm = nlmsg_data(nlh); @@ -1796,7 +1796,7 @@ void inet_netconf_notify_devconf(struct net *net, int type, int ifindex, int err = -ENOBUFS; skb = nlmsg_new(inet_netconf_msgsize_devconf(type), GFP_ATOMIC); - if (skb == NULL) + if (!skb) goto errout; err = inet_netconf_fill_devconf(skb, ifindex, devconf, 0, 0, @@ -1853,10 +1853,10 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb, break; default: dev = __dev_get_by_index(net, ifindex); - if (dev == NULL) + if (!dev) goto errout; in_dev = __in_dev_get_rtnl(dev); - if (in_dev == NULL) + if (!in_dev) goto errout; devconf = &in_dev->cnf; break; @@ -1864,7 +1864,7 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb, err = -ENOBUFS; skb = nlmsg_new(inet_netconf_msgsize_devconf(-1), GFP_ATOMIC); - if (skb == NULL) + if (!skb) goto errout; err = inet_netconf_fill_devconf(skb, ifindex, devconf, @@ -2215,7 +2215,7 @@ static void __devinet_sysctl_unregister(struct ipv4_devconf *cnf) { struct devinet_sysctl_table *t = cnf->sysctl; - if (t == NULL) + if (!t) return; cnf->sysctl = NULL; @@ -2276,16 +2276,16 @@ static __net_init int devinet_init_net(struct net *net) if (!net_eq(net, &init_net)) { all = kmemdup(all, sizeof(ipv4_devconf), GFP_KERNEL); - if (all == NULL) + if (!all) goto err_alloc_all; dflt = kmemdup(dflt, sizeof(ipv4_devconf_dflt), GFP_KERNEL); - if (dflt == NULL) + if (!dflt) goto err_alloc_dflt; #ifdef CONFIG_SYSCTL tbl = kmemdup(tbl, sizeof(ctl_forward_entry), GFP_KERNEL); - if (tbl == NULL) + if (!tbl) goto err_alloc_ctl; tbl[0].data = &all->data[IPV4_DEVCONF_FORWARDING - 1]; @@ -2305,7 +2305,7 @@ static __net_init int devinet_init_net(struct net *net) err = -ENOMEM; forw_hdr = register_net_sysctl(net, "net/ipv4", tbl); - if (forw_hdr == NULL) + if (!forw_hdr) goto err_reg_ctl; net->ipv4.forw_hdr = forw_hdr; #endif diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 60173d4d3a0e..421a80b09b62 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -553,7 +553,7 @@ static int esp_init_authenc(struct xfrm_state *x) int err; err = -EINVAL; - if (x->ealg == NULL) + if (!x->ealg) goto error; err = -ENAMETOOLONG; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 718b0a16ea40..2166d2bf1562 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -53,11 +53,11 @@ static int __net_init fib4_rules_init(struct net *net) struct fib_table *local_table, *main_table; main_table = fib_trie_table(RT_TABLE_MAIN, NULL); - if (main_table == NULL) + if (!main_table) return -ENOMEM; local_table = fib_trie_table(RT_TABLE_LOCAL, main_table); - if (local_table == NULL) + if (!local_table) goto fail; hlist_add_head_rcu(&local_table->tb_hlist, @@ -486,7 +486,7 @@ static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt, for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) if (strcmp(ifa->ifa_label, devname) == 0) break; - if (ifa == NULL) + if (!ifa) return -ENODEV; cfg->fc_prefsrc = ifa->ifa_local; } @@ -514,7 +514,7 @@ static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt, int len = 0; mx = kzalloc(3 * nla_total_size(4), GFP_KERNEL); - if (mx == NULL) + if (!mx) return -ENOMEM; if (rt->rt_flags & RTF_MTU) @@ -676,7 +676,7 @@ static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh) goto errout; tb = fib_get_table(net, cfg.fc_table); - if (tb == NULL) { + if (!tb) { err = -ESRCH; goto errout; } @@ -698,7 +698,7 @@ static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh) goto errout; tb = fib_new_table(net, cfg.fc_table); - if (tb == NULL) { + if (!tb) { err = -ENOBUFS; goto errout; } @@ -779,7 +779,7 @@ static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifad else tb = fib_new_table(net, RT_TABLE_LOCAL); - if (tb == NULL) + if (!tb) return; cfg.fc_table = tb->tb_id; @@ -806,7 +806,7 @@ void fib_add_ifaddr(struct in_ifaddr *ifa) if (ifa->ifa_flags & IFA_F_SECONDARY) { prim = inet_ifa_byprefix(in_dev, prefix, mask); - if (prim == NULL) { + if (!prim) { pr_warn("%s: bug: prim == NULL\n", __func__); return; } @@ -860,7 +860,7 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim) if (ifa->ifa_flags & IFA_F_SECONDARY) { prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask); - if (prim == NULL) { + if (!prim) { pr_warn("%s: bug: prim == NULL\n", __func__); return; } @@ -1030,7 +1030,7 @@ static void nl_fib_input(struct sk_buff *skb) return; skb = netlink_skb_clone(skb, GFP_KERNEL); - if (skb == NULL) + if (!skb) return; nlh = nlmsg_hdr(skb); @@ -1051,7 +1051,7 @@ static int __net_init nl_fib_lookup_init(struct net *net) }; sk = netlink_kernel_create(net, NETLINK_FIB_LOOKUP, &cfg); - if (sk == NULL) + if (!sk) return -EAFNOSUPPORT; net->ipv4.fibnl = sk; return 0; @@ -1089,7 +1089,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, case NETDEV_DOWN: fib_del_ifaddr(ifa, NULL); atomic_inc(&net->ipv4.dev_addr_genid); - if (ifa->ifa_dev->ifa_list == NULL) { + if (!ifa->ifa_dev->ifa_list) { /* Last address was deleted from this interface. * Disable IP. */ @@ -1157,7 +1157,7 @@ static int __net_init ip_fib_net_init(struct net *net) size = max_t(size_t, size, L1_CACHE_BYTES); net->ipv4.fib_table_hash = kzalloc(size, GFP_KERNEL); - if (net->ipv4.fib_table_hash == NULL) + if (!net->ipv4.fib_table_hash) return -ENOMEM; err = fib4_rules_init(net); diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 8162dd8e86d7..56151982f74e 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -153,7 +153,7 @@ static struct fib_table *fib_empty_table(struct net *net) u32 id; for (id = 1; id <= RT_TABLE_MAX; id++) - if (fib_get_table(net, id) == NULL) + if (!fib_get_table(net, id)) return fib_new_table(net, id); return NULL; } @@ -184,7 +184,7 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct fib_table *table; table = fib_empty_table(net); - if (table == NULL) { + if (!table) { err = -ENOBUFS; goto errout; } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index eac5aec7772a..8d695b6659c7 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -390,7 +390,7 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, int err = -ENOBUFS; skb = nlmsg_new(fib_nlmsg_size(fa->fa_info), GFP_KERNEL); - if (skb == NULL) + if (!skb) goto errout; err = fib_dump_info(skb, info->portid, seq, event, tb_id, @@ -503,7 +503,7 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) } #ifdef CONFIG_IP_ROUTE_MULTIPATH - if (cfg->fc_mp == NULL) + if (!cfg->fc_mp) return 0; rtnh = cfg->fc_mp; @@ -646,7 +646,7 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, rcu_read_lock(); err = -ENODEV; in_dev = inetdev_by_index(net, nh->nh_oif); - if (in_dev == NULL) + if (!in_dev) goto out; err = -ENETDOWN; if (!(in_dev->dev->flags & IFF_UP)) @@ -803,7 +803,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) } fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL); - if (fi == NULL) + if (!fi) goto failure; fib_info_cnt++; if (cfg->fc_mx) { @@ -921,7 +921,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) nh->nh_scope = RT_SCOPE_NOWHERE; nh->nh_dev = dev_get_by_index(net, fi->fib_nh->nh_oif); err = -ENODEV; - if (nh->nh_dev == NULL) + if (!nh->nh_dev) goto failure; } else { change_nexthops(fi) { @@ -995,7 +995,7 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, struct rtmsg *rtm; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*rtm), flags); - if (nlh == NULL) + if (!nlh) return -EMSGSIZE; rtm = nlmsg_data(nlh); @@ -1045,12 +1045,12 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, struct nlattr *mp; mp = nla_nest_start(skb, RTA_MULTIPATH); - if (mp == NULL) + if (!mp) goto nla_put_failure; for_nexthops(fi) { rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh)); - if (rtnh == NULL) + if (!rtnh) goto nla_put_failure; rtnh->rtnh_flags = nh->nh_flags & 0xFF; @@ -1093,7 +1093,7 @@ int fib_sync_down_addr(struct net *net, __be32 local) struct hlist_head *head = &fib_info_laddrhash[hash]; struct fib_info *fi; - if (fib_info_laddrhash == NULL || local == 0) + if (!fib_info_laddrhash || local == 0) return 0; hlist_for_each_entry(fi, head, fib_lhash) { @@ -1182,7 +1182,7 @@ void fib_select_default(struct fib_result *res) fib_alias_accessed(fa); - if (fi == NULL) { + if (!fi) { if (next_fi != res->fi) break; } else if (!fib_detect_death(fi, order, &last_resort, @@ -1195,7 +1195,7 @@ void fib_select_default(struct fib_result *res) order++; } - if (order <= 0 || fi == NULL) { + if (order <= 0 || !fi) { tb->tb_default = -1; goto out; } @@ -1251,7 +1251,7 @@ int fib_sync_up(struct net_device *dev) alive++; continue; } - if (nexthop_nh->nh_dev == NULL || + if (!nexthop_nh->nh_dev || !(nexthop_nh->nh_dev->flags & IFF_UP)) continue; if (nexthop_nh->nh_dev != dev || diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 2c7c299ee2b9..9e4a3e3423b4 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -391,9 +391,9 @@ static void put_child(struct key_vector *tn, unsigned long i, BUG_ON(i >= child_length(tn)); /* update emptyChildren, overflow into fullChildren */ - if (n == NULL && chi != NULL) + if (!n && chi != NULL) empty_child_inc(tn); - if (n != NULL && chi == NULL) + if (n != NULL && !chi) empty_child_dec(tn); /* update fullChildren */ @@ -528,7 +528,7 @@ static struct key_vector *inflate(struct trie *t, unsigned long j, k; /* An empty child */ - if (inode == NULL) + if (!inode) continue; /* A leaf or an internal node with skipped bits */ @@ -1154,7 +1154,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) } err = -ENOBUFS; new_fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL); - if (new_fa == NULL) + if (!new_fa) goto out; fi_drop = fa->fa_info; @@ -1204,7 +1204,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) err = -ENOBUFS; new_fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL); - if (new_fa == NULL) + if (!new_fa) goto out; new_fa->fa_info = fi; @@ -1975,7 +1975,7 @@ struct fib_table *fib_trie_table(u32 id, struct fib_table *alias) sz += sizeof(struct trie); tb = kzalloc(sz, GFP_KERNEL); - if (tb == NULL) + if (!tb) return NULL; tb->tb_id = id; diff --git a/net/ipv4/geneve.c b/net/ipv4/geneve.c index 5a4828ba05ad..a7d8be3dd3de 100644 --- a/net/ipv4/geneve.c +++ b/net/ipv4/geneve.c @@ -196,7 +196,7 @@ static struct sk_buff **geneve_gro_receive(struct sk_buff **head, rcu_read_lock(); ptype = gro_find_receive_by_type(type); - if (ptype == NULL) { + if (!ptype) { flush = 1; goto out_unlock; } diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 51973ddc05a6..9358f11aae40 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -149,7 +149,7 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head, rcu_read_lock(); ptype = gro_find_receive_by_type(type); - if (ptype == NULL) + if (!ptype) goto out_unlock; grehlen = GRE_HEADER_SECTION; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 5e564014a0b7..f5203fba6236 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -399,7 +399,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) return; sk = icmp_xmit_lock(net); - if (sk == NULL) + if (!sk) return; inet = inet_sk(sk); @@ -609,7 +609,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) skb_in->data, sizeof(_inner_type), &_inner_type); - if (itp == NULL) + if (!itp) goto out; /* @@ -627,7 +627,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) return; sk = icmp_xmit_lock(net); - if (sk == NULL) + if (!sk) goto out_free; /* diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index ad09213ac5b2..27d204b834f9 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -692,7 +692,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; skb = alloc_skb(IGMP_SIZE + hlen + tlen, GFP_ATOMIC); - if (skb == NULL) { + if (!skb) { ip_rt_put(rt); return -1; } @@ -981,7 +981,7 @@ int igmp_rcv(struct sk_buff *skb) int len = skb->len; bool dropped = true; - if (in_dev == NULL) + if (!in_dev) goto drop; if (!pskb_may_pull(skb, sizeof(struct igmphdr))) @@ -1888,7 +1888,7 @@ int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr) if (count >= sysctl_igmp_max_memberships) goto done; iml = sock_kmalloc(sk, sizeof(*iml), GFP_KERNEL); - if (iml == NULL) + if (!iml) goto done; memcpy(&iml->multi, imr, sizeof(*imr)); @@ -1909,7 +1909,7 @@ static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml, struct ip_sf_socklist *psf = rtnl_dereference(iml->sflist); int err; - if (psf == NULL) { + if (!psf) { /* any-source empty exclude case */ return ip_mc_del_src(in_dev, &iml->multi.imr_multiaddr.s_addr, iml->sfmode, 0, NULL, 0); @@ -2360,7 +2360,7 @@ void ip_mc_drop_socket(struct sock *sk) struct ip_mc_socklist *iml; struct net *net = sock_net(sk); - if (inet->mc_list == NULL) + if (!inet->mc_list) return; rtnl_lock(); @@ -2587,7 +2587,7 @@ static inline struct ip_sf_list *igmp_mcf_get_first(struct seq_file *seq) for_each_netdev_rcu(net, state->dev) { struct in_device *idev; idev = __in_dev_get_rcu(state->dev); - if (unlikely(idev == NULL)) + if (unlikely(!idev)) continue; im = rcu_dereference(idev->mc_list); if (likely(im != NULL)) { diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index e7920352646a..5e346a082e5f 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -385,7 +385,7 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, } q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC); - if (q == NULL) + if (!q) return NULL; q->net = nf; @@ -406,7 +406,7 @@ static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf, struct inet_frag_queue *q; q = inet_frag_alloc(nf, f, arg); - if (q == NULL) + if (!q) return NULL; return inet_frag_intern(nf, q, f, arg); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 145a50c4d566..5a6cf8667a9d 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -372,7 +372,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) goto err; err = -ENOMEM; - if (pskb_pull(skb, ihl) == NULL) + if (!pskb_pull(skb, ihl)) goto err; err = pskb_trim_rcsum(skb, end - offset); @@ -537,7 +537,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, qp->q.fragments = head; } - WARN_ON(head == NULL); + WARN_ON(!head); WARN_ON(FRAG_CB(head)->offset != 0); /* Allocate a new buffer for the datagram. */ @@ -559,7 +559,8 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, struct sk_buff *clone; int i, plen = 0; - if ((clone = alloc_skb(0, GFP_ATOMIC)) == NULL) + clone = alloc_skb(0, GFP_ATOMIC); + if (!clone) goto out_nomem; clone->next = head->next; head->next = clone; @@ -754,7 +755,7 @@ static int __net_init ip4_frags_ns_ctl_register(struct net *net) table = ip4_frags_ns_ctl_table; if (!net_eq(net, &init_net)) { table = kmemdup(table, sizeof(ip4_frags_ns_ctl_table), GFP_KERNEL); - if (table == NULL) + if (!table) goto err_alloc; table[0].data = &net->ipv4.frags.high_thresh; @@ -770,7 +771,7 @@ static int __net_init ip4_frags_ns_ctl_register(struct net *net) } hdr = register_net_sysctl(net, "net/ipv4", table); - if (hdr == NULL) + if (!hdr) goto err_reg; net->ipv4.frags_hdr = hdr; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 1060ca0bc23a..5fd706473c73 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -182,7 +182,7 @@ static int ipgre_err(struct sk_buff *skb, u32 info, t = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags, iph->daddr, iph->saddr, tpi->key); - if (t == NULL) + if (!t) return PACKET_REJECT; if (t->parms.iph.daddr == 0 || @@ -423,7 +423,7 @@ static int ipgre_open(struct net_device *dev) return -EADDRNOTAVAIL; dev = rt->dst.dev; ip_rt_put(rt); - if (__in_dev_get_rtnl(dev) == NULL) + if (!__in_dev_get_rtnl(dev)) return -EADDRNOTAVAIL; t->mlink = dev->ifindex; ip_mc_inc_group(__in_dev_get_rtnl(dev), t->parms.iph.daddr); diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 3d4da2c16b6a..00bed6fe3b66 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -314,7 +314,7 @@ static int ip_rcv_finish(struct sk_buff *skb) const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; - if (sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) { + if (sysctl_ip_early_demux && !skb_dst(skb) && !skb->sk) { const struct net_protocol *ipprot; int protocol = iph->protocol; @@ -387,7 +387,8 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, IP_UPD_PO_STATS_BH(dev_net(dev), IPSTATS_MIB_IN, skb->len); - if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) { + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) { IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INDISCARDS); goto out; } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 8259e777b249..561d67b2ac74 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -182,7 +182,7 @@ static inline int ip_finish_output2(struct sk_buff *skb) struct sk_buff *skb2; skb2 = skb_realloc_headroom(skb, LL_RESERVED_SPACE(dev)); - if (skb2 == NULL) { + if (!skb2) { kfree_skb(skb); return -ENOMEM; } @@ -381,7 +381,7 @@ int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl) /* Make sure we can route this packet. */ rt = (struct rtable *)__sk_dst_check(sk, 0); - if (rt == NULL) { + if (!rt) { __be32 daddr; /* Use correct destination address if we have options. */ @@ -790,12 +790,13 @@ static inline int ip_ufo_append_data(struct sock *sk, * device, so create one single skb packet containing complete * udp datagram */ - if ((skb = skb_peek_tail(queue)) == NULL) { + skb = skb_peek_tail(queue); + if (!skb) { skb = sock_alloc_send_skb(sk, hh_len + fragheaderlen + transhdrlen + 20, (flags & MSG_DONTWAIT), &err); - if (skb == NULL) + if (!skb) return err; /* reserve space for Hardware header */ @@ -961,10 +962,10 @@ alloc_new_skb: skb = sock_wmalloc(sk, alloclen + hh_len + 15, 1, sk->sk_allocation); - if (unlikely(skb == NULL)) + if (unlikely(!skb)) err = -ENOBUFS; } - if (skb == NULL) + if (!skb) goto error; /* @@ -1088,10 +1089,10 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, */ opt = ipc->opt; if (opt) { - if (cork->opt == NULL) { + if (!cork->opt) { cork->opt = kmalloc(sizeof(struct ip_options) + 40, sk->sk_allocation); - if (unlikely(cork->opt == NULL)) + if (unlikely(!cork->opt)) return -ENOBUFS; } memcpy(cork->opt, &opt->opt, sizeof(struct ip_options) + opt->opt.optlen); @@ -1198,7 +1199,8 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, return -EMSGSIZE; } - if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL) + skb = skb_peek_tail(&sk->sk_write_queue); + if (!skb) return -EINVAL; cork->length += size; @@ -1329,7 +1331,8 @@ struct sk_buff *__ip_make_skb(struct sock *sk, __be16 df = 0; __u8 ttl; - if ((skb = __skb_dequeue(queue)) == NULL) + skb = __skb_dequeue(queue); + if (!skb) goto out; tail_skb = &(skb_shinfo(skb)->frag_list); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index f6a0d54b308a..f64b1b24c64f 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -351,7 +351,7 @@ int ip_ra_control(struct sock *sk, unsigned char on, return 0; } } - if (new_ra == NULL) { + if (!new_ra) { spin_unlock_bh(&ip_ra_lock); return -ENOBUFS; } @@ -482,7 +482,7 @@ int ip_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) err = -EAGAIN; skb = sock_dequeue_err_skb(sk); - if (skb == NULL) + if (!skb) goto out; copied = skb->len; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 4bb7252110a6..31eaa9ba1803 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -654,7 +654,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, if (dst == 0) { /* NBMA tunnel */ - if (skb_dst(skb) == NULL) { + if (!skb_dst(skb)) { dev->stats.tx_fifo_errors++; goto tx_error; } @@ -672,7 +672,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, neigh = dst_neigh_lookup(skb_dst(skb), &ipv6_hdr(skb)->daddr); - if (neigh == NULL) + if (!neigh) goto tx_error; addr6 = (const struct in6_addr *)&neigh->primary_key; @@ -843,7 +843,7 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) case SIOCGETTUNNEL: if (dev == itn->fb_tunnel_dev) { t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type); - if (t == NULL) + if (!t) t = netdev_priv(dev); } memcpy(p, &t->parms, sizeof(*p)); @@ -914,7 +914,7 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) if (dev == itn->fb_tunnel_dev) { err = -ENOENT; t = ip_tunnel_find(itn, p, itn->fb_tunnel_dev->type); - if (t == NULL) + if (!t) goto done; err = -EPERM; if (t == netdev_priv(itn->fb_tunnel_dev)) diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index c0855d50a3fa..d97f4f2787f5 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -63,7 +63,7 @@ static struct xfrm_state *ipcomp_tunnel_create(struct xfrm_state *x) struct xfrm_state *t; t = xfrm_state_alloc(net); - if (t == NULL) + if (!t) goto out; t->id.proto = IPPROTO_IPIP; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index b26376ef87f6..8e7328c6a390 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -504,7 +504,8 @@ ic_rarp_recv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt if (!net_eq(dev_net(dev), &init_net)) goto drop; - if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) return NET_RX_DROP; if (!pskb_may_pull(skb, sizeof(struct arphdr))) @@ -958,7 +959,8 @@ static int __init ic_bootp_recv(struct sk_buff *skb, struct net_device *dev, str if (skb->pkt_type == PACKET_OTHERHOST) goto drop; - if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) return NET_RX_DROP; if (!pskb_may_pull(skb, diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 5c81f6e40842..ff96396ebec5 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -144,7 +144,7 @@ static int ipip_err(struct sk_buff *skb, u32 info) err = -ENOENT; t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, iph->daddr, iph->saddr, 0); - if (t == NULL) + if (!t) goto out; if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 3ef30cf57f4a..a170e4bc9006 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -189,7 +189,7 @@ static int ipmr_rule_action(struct fib_rule *rule, struct flowi *flp, } mrt = ipmr_get_table(rule->fr_net, rule->table); - if (mrt == NULL) + if (!mrt) return -EAGAIN; res->mrt = mrt; return 0; @@ -253,7 +253,7 @@ static int __net_init ipmr_rules_init(struct net *net) INIT_LIST_HEAD(&net->ipv4.mr_tables); mrt = ipmr_new_table(net, RT_TABLE_DEFAULT); - if (mrt == NULL) { + if (!mrt) { err = -ENOMEM; goto err1; } @@ -320,7 +320,7 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id) return mrt; mrt = kzalloc(sizeof(*mrt), GFP_KERNEL); - if (mrt == NULL) + if (!mrt) return NULL; write_pnet(&mrt->net, net); mrt->id = id; @@ -422,7 +422,7 @@ struct net_device *ipmr_new_tunnel(struct net *net, struct vifctl *v) dev->flags |= IFF_MULTICAST; in_dev = __in_dev_get_rtnl(dev); - if (in_dev == NULL) + if (!in_dev) goto failure; ipv4_devconf_setall(in_dev); @@ -506,7 +506,7 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt) dev = alloc_netdev(0, name, NET_NAME_UNKNOWN, reg_vif_setup); - if (dev == NULL) + if (!dev) return NULL; dev_net_set(dev, net); @@ -762,7 +762,7 @@ static int vif_add(struct net *net, struct mr_table *mrt, case 0: if (vifc->vifc_flags == VIFF_USE_IFINDEX) { dev = dev_get_by_index(net, vifc->vifc_lcl_ifindex); - if (dev && __in_dev_get_rtnl(dev) == NULL) { + if (dev && !__in_dev_get_rtnl(dev)) { dev_put(dev); return -EADDRNOTAVAIL; } @@ -1008,7 +1008,7 @@ static int ipmr_cache_report(struct mr_table *mrt, rcu_read_lock(); mroute_sk = rcu_dereference(mrt->mroute_sk); - if (mroute_sk == NULL) { + if (!mroute_sk) { rcu_read_unlock(); kfree_skb(skb); return -EINVAL; @@ -1161,7 +1161,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, return -EINVAL; c = ipmr_cache_alloc(); - if (c == NULL) + if (!c) return -ENOMEM; c->mfc_origin = mfc->mfcc_origin.s_addr; @@ -1283,7 +1283,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi return -EOPNOTSUPP; mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); - if (mrt == NULL) + if (!mrt) return -ENOENT; if (optname != MRT_INIT) { @@ -1446,7 +1446,7 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int return -EOPNOTSUPP; mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); - if (mrt == NULL) + if (!mrt) return -ENOENT; if (optname != MRT_VERSION && @@ -1492,7 +1492,7 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg) struct mr_table *mrt; mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); - if (mrt == NULL) + if (!mrt) return -ENOENT; switch (cmd) { @@ -1566,7 +1566,7 @@ int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) struct mr_table *mrt; mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); - if (mrt == NULL) + if (!mrt) return -ENOENT; switch (cmd) { @@ -1701,7 +1701,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, struct flowi4 fl4; int encap = 0; - if (vif->dev == NULL) + if (!vif->dev) goto out_free; #ifdef CONFIG_IP_PIMSM @@ -1992,7 +1992,7 @@ int ip_mr_input(struct sk_buff *skb) /* already under rcu_read_lock() */ cache = ipmr_cache_find(mrt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr); - if (cache == NULL) { + if (!cache) { int vif = ipmr_find_vif(mrt, skb->dev); if (vif >= 0) @@ -2003,13 +2003,13 @@ int ip_mr_input(struct sk_buff *skb) /* * No usable cache entry */ - if (cache == NULL) { + if (!cache) { int vif; if (local) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); ip_local_deliver(skb); - if (skb2 == NULL) + if (!skb2) return -ENOBUFS; skb = skb2; } @@ -2068,7 +2068,7 @@ static int __pim_rcv(struct mr_table *mrt, struct sk_buff *skb, reg_dev = mrt->vif_table[mrt->mroute_reg_vif_num].dev; read_unlock(&mrt_lock); - if (reg_dev == NULL) + if (!reg_dev) return 1; skb->mac_header = skb->network_header; @@ -2198,18 +2198,18 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb, int err; mrt = ipmr_get_table(net, RT_TABLE_DEFAULT); - if (mrt == NULL) + if (!mrt) return -ENOENT; rcu_read_lock(); cache = ipmr_cache_find(mrt, saddr, daddr); - if (cache == NULL && skb->dev) { + if (!cache && skb->dev) { int vif = ipmr_find_vif(mrt, skb->dev); if (vif >= 0) cache = ipmr_cache_find_any(mrt, daddr, vif); } - if (cache == NULL) { + if (!cache) { struct sk_buff *skb2; struct iphdr *iph; struct net_device *dev; @@ -2267,7 +2267,7 @@ static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, int err; nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags); - if (nlh == NULL) + if (!nlh) return -EMSGSIZE; rtm = nlmsg_data(nlh); @@ -2332,7 +2332,7 @@ static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc, skb = nlmsg_new(mroute_msgsize(mfc->mfc_parent >= MAXVIFS, mrt->maxvif), GFP_ATOMIC); - if (skb == NULL) + if (!skb) goto errout; err = ipmr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0); @@ -2447,7 +2447,7 @@ static void *ipmr_vif_seq_start(struct seq_file *seq, loff_t *pos) struct mr_table *mrt; mrt = ipmr_get_table(net, RT_TABLE_DEFAULT); - if (mrt == NULL) + if (!mrt) return ERR_PTR(-ENOENT); iter->mrt = mrt; @@ -2566,7 +2566,7 @@ static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos) struct mr_table *mrt; mrt = ipmr_get_table(net, RT_TABLE_DEFAULT); - if (mrt == NULL) + if (!mrt) return ERR_PTR(-ENOENT); it->mrt = mrt; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 344e7cdfb8d4..2dcd2e60df64 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -516,7 +516,7 @@ void ping_err(struct sk_buff *skb, int offset, u32 info) ntohs(icmph->un.echo.sequence)); sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id)); - if (sk == NULL) { + if (!sk) { pr_debug("no socket, dropping\n"); return; /* No socket for error */ } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 56946f47d446..46a78204189d 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -363,7 +363,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, skb = sock_alloc_send_skb(sk, length + hlen + tlen + 15, flags & MSG_DONTWAIT, &err); - if (skb == NULL) + if (!skb) goto error; skb_reserve(skb, hlen); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 652b92ebd7ba..26a1cb348b3d 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1056,7 +1056,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) __build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0); rt = (struct rtable *)odst; - if (odst->obsolete && odst->ops->check(odst, 0) == NULL) { + if (odst->obsolete && !odst->ops->check(odst, 0)) { rt = ip_route_output_flow(sock_net(sk), &fl4, sk); if (IS_ERR(rt)) goto out; @@ -1450,7 +1450,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, /* Primary sanity checks. */ - if (in_dev == NULL) + if (!in_dev) return -EINVAL; if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) || @@ -1553,7 +1553,7 @@ static int __mkroute_input(struct sk_buff *skb, /* get a working reference to the output device */ out_dev = __in_dev_get_rcu(FIB_RES_DEV(*res)); - if (out_dev == NULL) { + if (!out_dev) { net_crit_ratelimited("Bug in ip_route_input_slow(). Please report.\n"); return -EINVAL; } @@ -2054,7 +2054,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) ipv4_is_lbcast(fl4->daddr))) { /* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */ dev_out = __ip_dev_find(net, fl4->saddr, false); - if (dev_out == NULL) + if (!dev_out) goto out; /* Special hack: user can direct multicasts @@ -2087,7 +2087,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) if (fl4->flowi4_oif) { dev_out = dev_get_by_index_rcu(net, fl4->flowi4_oif); rth = ERR_PTR(-ENODEV); - if (dev_out == NULL) + if (!dev_out) goto out; /* RACE: Check return value of inet_select_addr instead. */ @@ -2299,7 +2299,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 metrics[RTAX_MAX]; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*r), flags); - if (nlh == NULL) + if (!nlh) return -EMSGSIZE; r = nlmsg_data(nlh); @@ -2421,7 +2421,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh) rtm = nlmsg_data(nlh); skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); - if (skb == NULL) { + if (!skb) { err = -ENOBUFS; goto errout; } @@ -2452,7 +2452,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh) struct net_device *dev; dev = __dev_get_by_index(net, iif); - if (dev == NULL) { + if (!dev) { err = -ENODEV; goto errout_free; } @@ -2651,7 +2651,7 @@ static __net_init int sysctl_route_net_init(struct net *net) tbl = ipv4_route_flush_table; if (!net_eq(net, &init_net)) { tbl = kmemdup(tbl, sizeof(ipv4_route_flush_table), GFP_KERNEL); - if (tbl == NULL) + if (!tbl) goto err_dup; /* Don't export sysctls to unprivileged users */ @@ -2661,7 +2661,7 @@ static __net_init int sysctl_route_net_init(struct net *net) tbl[0].extra1 = net; net->ipv4.route_hdr = register_net_sysctl(net, "net/ipv4/route", tbl); - if (net->ipv4.route_hdr == NULL) + if (!net->ipv4.route_hdr) goto err_reg; return 0; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index fdf899163d44..c3852a7ff3c7 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -909,7 +909,7 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) int i; table = kmemdup(table, sizeof(ipv4_net_table), GFP_KERNEL); - if (table == NULL) + if (!table) goto err_alloc; /* Update the variables to point into the current struct net */ @@ -918,7 +918,7 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) } net->ipv4.ipv4_hdr = register_net_sysctl(net, "net/ipv4", table); - if (net->ipv4.ipv4_hdr == NULL) + if (!net->ipv4.ipv4_hdr) goto err_reg; net->ipv4.sysctl_local_reserved_ports = kzalloc(65536 / 8, GFP_KERNEL); @@ -956,7 +956,7 @@ static __init int sysctl_ipv4_init(void) struct ctl_table_header *hdr; hdr = register_net_sysctl(&init_net, "net/ipv4", ipv4_table); - if (hdr == NULL) + if (!hdr) return -ENOMEM; if (register_pernet_subsys(&ipv4_sysctl_ops)) { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index dbd51cefaf02..5bd809bfd0aa 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1047,7 +1047,7 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, tp->fastopen_req = kzalloc(sizeof(struct tcp_fastopen_request), sk->sk_allocation); - if (unlikely(tp->fastopen_req == NULL)) + if (unlikely(!tp->fastopen_req)) return -ENOBUFS; tp->fastopen_req->data = msg; tp->fastopen_req->size = size; diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 2eb887ec0ce3..5da55e2b5cd2 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -141,7 +141,7 @@ static bool tcp_fastopen_create_child(struct sock *sk, req->sk = NULL; child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL); - if (child == NULL) + if (!child) return false; spin_lock(&queue->fastopenq->lock); @@ -214,7 +214,7 @@ static bool tcp_fastopen_create_child(struct sock *sk, sk->sk_data_ready(sk); bh_unlock_sock(child); sock_put(child); - WARN_ON(req->sk == NULL); + WARN_ON(!req->sk); return true; } @@ -233,7 +233,7 @@ static bool tcp_fastopen_queue_check(struct sock *sk) * temporarily vs a server not supporting Fast Open at all. */ fastopenq = inet_csk(sk)->icsk_accept_queue.fastopenq; - if (fastopenq == NULL || fastopenq->max_qlen == 0) + if (!fastopenq || fastopenq->max_qlen == 0) return false; if (fastopenq->qlen >= fastopenq->max_qlen) { diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 18b80e8bc533..1fd283684303 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -866,7 +866,7 @@ static void tcp_update_reordering(struct sock *sk, const int metric, /* This must be called before lost_out is incremented */ static void tcp_verify_retransmit_hint(struct tcp_sock *tp, struct sk_buff *skb) { - if ((tp->retransmit_skb_hint == NULL) || + if (!tp->retransmit_skb_hint || before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(tp->retransmit_skb_hint)->seq)) tp->retransmit_skb_hint = skb; @@ -1614,7 +1614,7 @@ static struct sk_buff *tcp_maybe_skipping_dsack(struct sk_buff *skb, struct tcp_sacktag_state *state, u32 skip_to_seq) { - if (next_dup == NULL) + if (!next_dup) return skb; if (before(next_dup->start_seq, skip_to_seq)) { @@ -1783,7 +1783,7 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, if (tcp_highest_sack_seq(tp) == cache->end_seq) { /* ...but better entrypoint exists! */ skb = tcp_highest_sack(sk); - if (skb == NULL) + if (!skb) break; state.fack_count = tp->fackets_out; cache++; @@ -1798,7 +1798,7 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, if (!before(start_seq, tcp_highest_sack_seq(tp))) { skb = tcp_highest_sack(sk); - if (skb == NULL) + if (!skb) break; state.fack_count = tp->fackets_out; } @@ -3698,7 +3698,7 @@ void tcp_parse_options(const struct sk_buff *skb, */ if (opsize < TCPOLEN_EXP_FASTOPEN_BASE || get_unaligned_be16(ptr) != TCPOPT_FASTOPEN_MAGIC || - foc == NULL || !th->syn || (opsize & 1)) + !foc || !th->syn || (opsize & 1)) break; foc->len = opsize - TCPOLEN_EXP_FASTOPEN_BASE; if (foc->len >= TCP_FASTOPEN_COOKIE_MIN && @@ -4669,7 +4669,7 @@ static void tcp_collapse_ofo_queue(struct sock *sk) struct sk_buff *head; u32 start, end; - if (skb == NULL) + if (!skb) return; start = TCP_SKB_CB(skb)->seq; @@ -5124,7 +5124,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb, { struct tcp_sock *tp = tcp_sk(sk); - if (unlikely(sk->sk_rx_dst == NULL)) + if (unlikely(!sk->sk_rx_dst)) inet_csk(sk)->icsk_af_ops->sk_rx_dst_set(sk, skb); /* * Header prediction. @@ -5694,7 +5694,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV && sk->sk_state != TCP_FIN_WAIT1); - if (tcp_check_req(sk, skb, req, true) == NULL) + if (!tcp_check_req(sk, skb, req, true)) goto discard; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 69f9cf684744..9ff311cf00f3 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -122,7 +122,7 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) and use initial timestamp retrieved from peer table. */ if (tcptw->tw_ts_recent_stamp && - (twp == NULL || (sysctl_tcp_tw_reuse && + (!twp || (sysctl_tcp_tw_reuse && get_seconds() - tcptw->tw_ts_recent_stamp > 1))) { tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2; if (tp->write_seq == 0) @@ -494,7 +494,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) /* Only in fast or simultaneous open. If a fast open socket is * is already accepted it is treated as a connected one below. */ - if (fastopen && fastopen->sk == NULL) + if (fastopen && !fastopen->sk) break; if (!sock_owned_by_user(sk)) { @@ -1390,7 +1390,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) sk_mark_napi_id(sk, skb); if (dst) { if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif || - dst->ops->check(dst, 0) == NULL) { + !dst->ops->check(dst, 0)) { dst_release(dst); sk->sk_rx_dst = NULL; } diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 71ec14c87579..78ecc4a01712 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -505,7 +505,7 @@ void tcp_init_metrics(struct sock *sk) struct tcp_metrics_block *tm; u32 val, crtt = 0; /* cached RTT scaled by 8 */ - if (dst == NULL) + if (!dst) goto reset; dst_confirm(dst); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 274e96fb369b..f0db1599a09c 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -763,7 +763,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, * socket is created, wait for troubles. */ child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL); - if (child == NULL) + if (!child) goto listen_overflow; inet_csk_reqsk_queue_unlink(sk, req); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 2e69b8d16e68..bdc80734cd2c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -565,7 +565,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, opts->mss = tcp_advertise_mss(sk); remaining -= TCPOLEN_MSS_ALIGNED; - if (likely(sysctl_tcp_timestamps && *md5 == NULL)) { + if (likely(sysctl_tcp_timestamps && !*md5)) { opts->options |= OPTION_TS; opts->tsval = tcp_skb_timestamp(skb) + tp->tsoffset; opts->tsecr = tp->rx_opt.ts_recent; @@ -1148,7 +1148,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len, /* Get a new skb... force flag on. */ buff = sk_stream_alloc_skb(sk, nsize, gfp); - if (buff == NULL) + if (!buff) return -ENOMEM; /* We'll just try again later. */ sk->sk_wmem_queued += buff->truesize; @@ -1707,7 +1707,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, return tcp_fragment(sk, skb, len, mss_now, gfp); buff = sk_stream_alloc_skb(sk, 0, gfp); - if (unlikely(buff == NULL)) + if (unlikely(!buff)) return -ENOMEM; sk->sk_wmem_queued += buff->truesize; @@ -1925,7 +1925,8 @@ static int tcp_mtu_probe(struct sock *sk) } /* We're allowed to probe. Build it now. */ - if ((nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC)) == NULL) + nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC); + if (!nskb) return -1; sk->sk_wmem_queued += nskb->truesize; sk_mem_charge(sk, nskb->truesize); @@ -2733,7 +2734,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk) if (skb == tcp_send_head(sk)) break; /* we could do better than to assign each time */ - if (hole == NULL) + if (!hole) tp->retransmit_skb_hint = skb; /* Assume this retransmit will generate @@ -2765,7 +2766,7 @@ begin_fwd: goto begin_fwd; } else if (!(sacked & TCPCB_LOST)) { - if (hole == NULL && !(sacked & (TCPCB_SACKED_RETRANS|TCPCB_SACKED_ACKED))) + if (!hole && !(sacked & (TCPCB_SACKED_RETRANS|TCPCB_SACKED_ACKED))) hole = skb; continue; @@ -2868,14 +2869,14 @@ int tcp_send_synack(struct sock *sk) struct sk_buff *skb; skb = tcp_write_queue_head(sk); - if (skb == NULL || !(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { + if (!skb || !(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) { pr_debug("%s: wrong queue state\n", __func__); return -EFAULT; } if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK)) { if (skb_cloned(skb)) { struct sk_buff *nskb = skb_copy(skb, GFP_ATOMIC); - if (nskb == NULL) + if (!nskb) return -ENOMEM; tcp_unlink_write_queue(skb, sk); __skb_header_release(nskb); @@ -3300,7 +3301,7 @@ void tcp_send_ack(struct sock *sk) * sock. */ buff = alloc_skb(MAX_TCP_HEADER, sk_gfp_atomic(sk, GFP_ATOMIC)); - if (buff == NULL) { + if (!buff) { inet_csk_schedule_ack(sk); inet_csk(sk)->icsk_ack.ato = TCP_ATO_MIN; inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, @@ -3344,7 +3345,7 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent) /* We don't queue it, tcp_transmit_skb() sets ownership. */ skb = alloc_skb(MAX_TCP_HEADER, sk_gfp_atomic(sk, GFP_ATOMIC)); - if (skb == NULL) + if (!skb) return -1; /* Reserve space for headers and set control bits. */ diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 294af16633af..9f525a2a68df 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -633,7 +633,7 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) sk = __udp4_lib_lookup(net, iph->daddr, uh->dest, iph->saddr, uh->source, skb->dev->ifindex, udptable); - if (sk == NULL) { + if (!sk) { ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); return; /* No socket for error */ } @@ -1011,7 +1011,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (connected) rt = (struct rtable *)sk_dst_check(sk, 0); - if (rt == NULL) { + if (!rt) { struct net *net = sock_net(sk); fl4 = &fl4_stack; @@ -1619,7 +1619,7 @@ static void flush_stack(struct sock **stack, unsigned int count, for (i = 0; i < count; i++) { sk = stack[i]; - if (likely(skb1 == NULL)) + if (likely(!skb1)) skb1 = (i == final) ? skb : skb_clone(skb, GFP_ATOMIC); if (!skb1) { diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index 2dbfc1f1f7b3..b763c39ae1d7 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -58,7 +58,7 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, goto out_nosk; err = -ENOENT; - if (sk == NULL) + if (!sk) goto out_nosk; err = sock_diag_check_cookie(sk, req->id.idiag_cookie); diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index aac6197b7a71..cac7468db0a1 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -24,7 +24,7 @@ int xfrm4_extract_input(struct xfrm_state *x, struct sk_buff *skb) static inline int xfrm4_rcv_encap_finish(struct sk_buff *skb) { - if (skb_dst(skb) == NULL) { + if (!skb_dst(skb)) { const struct iphdr *iph = ip_hdr(skb); if (ip_route_input_noref(skb, iph->daddr, iph->saddr, diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index c224c856247b..bff69746e05f 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -298,7 +298,7 @@ static void __net_exit xfrm4_net_exit(struct net *net) { struct ctl_table *table; - if (net->ipv4.xfrm4_hdr == NULL) + if (!net->ipv4.xfrm4_hdr) return; table = net->ipv4.xfrm4_hdr->ctl_table_arg; -- cgit v1.2.3 From 00db41243e8d5032c2e0f5bf6063bb19324bfdb3 Mon Sep 17 00:00:00 2001 From: Ian Morris Date: Fri, 3 Apr 2015 09:17:27 +0100 Subject: ipv4: coding style: comparison for inequality with NULL The ipv4 code uses a mixture of coding styles. In some instances check for non-NULL pointer is done as x != NULL and sometimes as x. x is preferred according to checkpatch and this patch makes the code consistent by adopting the latter form. No changes detected by objdiff. Signed-off-by: Ian Morris Signed-off-by: David S. Miller --- net/ipv4/af_inet.c | 2 +- net/ipv4/arp.c | 2 +- net/ipv4/cipso_ipv4.c | 6 +++--- net/ipv4/devinet.c | 2 +- net/ipv4/fib_trie.c | 4 ++-- net/ipv4/geneve.c | 2 +- net/ipv4/gre_offload.c | 2 +- net/ipv4/igmp.c | 8 ++++---- net/ipv4/inet_connection_sock.c | 8 ++++---- net/ipv4/inet_hashtables.c | 2 +- net/ipv4/inet_timewait_sock.c | 2 +- net/ipv4/ip_fragment.c | 3 ++- net/ipv4/ip_input.c | 2 +- net/ipv4/ip_options.c | 2 +- net/ipv4/ip_output.c | 6 +++--- net/ipv4/ip_sockglue.c | 2 +- net/ipv4/ip_tunnel.c | 2 +- net/ipv4/ip_vti.c | 2 +- net/ipv4/ipmr.c | 2 +- net/ipv4/ping.c | 2 +- net/ipv4/raw.c | 4 ++-- net/ipv4/route.c | 2 +- net/ipv4/tcp.c | 12 ++++++------ net/ipv4/tcp_diag.c | 2 +- net/ipv4/tcp_input.c | 12 ++++++------ net/ipv4/tcp_ipv4.c | 4 ++-- net/ipv4/tcp_minisocks.c | 6 +++--- net/ipv4/tcp_output.c | 14 +++++++------- net/ipv4/udp.c | 4 ++-- net/ipv4/udp_offload.c | 4 ++-- 30 files changed, 64 insertions(+), 63 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 7d3b00c01bc8..8b47a4d79d04 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1269,7 +1269,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, if (udpfrag) { iph->id = htons(id); iph->frag_off = htons(offset >> 3); - if (skb->next != NULL) + if (skb->next) iph->frag_off |= htons(IP_MF); offset += skb->len - nhoff - ihl; } else { diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index ffe84226a2c8..c6e67aa46c32 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -569,7 +569,7 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, break; #endif default: - if (target_hw != NULL) + if (target_hw) memcpy(arp_ptr, target_hw, dev->addr_len); else memset(arp_ptr, 0, dev->addr_len); diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 1b28e1183c1b..bdb2a07ec363 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -502,7 +502,7 @@ int cipso_v4_doi_add(struct cipso_v4_doi *doi_def, atomic_set(&doi_def->refcount, 1); spin_lock(&cipso_v4_doi_list_lock); - if (cipso_v4_doi_search(doi_def->doi) != NULL) { + if (cipso_v4_doi_search(doi_def->doi)) { spin_unlock(&cipso_v4_doi_list_lock); ret_val = -EEXIST; goto doi_add_return; @@ -513,7 +513,7 @@ int cipso_v4_doi_add(struct cipso_v4_doi *doi_def, doi_add_return: audit_buf = netlbl_audit_start(AUDIT_MAC_CIPSOV4_ADD, audit_info); - if (audit_buf != NULL) { + if (audit_buf) { const char *type_str; switch (doi_type) { case CIPSO_V4_MAP_TRANS: @@ -617,7 +617,7 @@ int cipso_v4_doi_remove(u32 doi, struct netlbl_audit *audit_info) doi_remove_return: audit_buf = netlbl_audit_start(AUDIT_MAC_CIPSOV4_DEL, audit_info); - if (audit_buf != NULL) { + if (audit_buf) { audit_log_format(audit_buf, " cipso_doi=%u res=%u", doi, ret_val == 0 ? 1 : 0); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 0ee21689d37e..419d23c53ec7 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1290,7 +1290,7 @@ __be32 inet_confirm_addr(struct net *net, struct in_device *in_dev, __be32 addr = 0; struct net_device *dev; - if (in_dev != NULL) + if (in_dev) return confirm_addr_indev(in_dev, dst, local, scope); rcu_read_lock(); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 9e4a3e3423b4..e13fcc602da2 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -391,9 +391,9 @@ static void put_child(struct key_vector *tn, unsigned long i, BUG_ON(i >= child_length(tn)); /* update emptyChildren, overflow into fullChildren */ - if (!n && chi != NULL) + if (!n && chi) empty_child_inc(tn); - if (n != NULL && !chi) + if (n && !chi) empty_child_dec(tn); /* update fullChildren */ diff --git a/net/ipv4/geneve.c b/net/ipv4/geneve.c index a7d8be3dd3de..e64f8e9785d1 100644 --- a/net/ipv4/geneve.c +++ b/net/ipv4/geneve.c @@ -230,7 +230,7 @@ static int geneve_gro_complete(struct sk_buff *skb, int nhoff, rcu_read_lock(); ptype = gro_find_complete_by_type(type); - if (ptype != NULL) + if (ptype) err = ptype->callbacks.gro_complete(skb, nhoff + gh_len); rcu_read_unlock(); diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 9358f11aae40..5aa46d4b44ef 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -243,7 +243,7 @@ static int gre_gro_complete(struct sk_buff *skb, int nhoff) rcu_read_lock(); ptype = gro_find_complete_by_type(type); - if (ptype != NULL) + if (ptype) err = ptype->callbacks.gro_complete(skb, nhoff + grehlen); rcu_read_unlock(); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 27d204b834f9..a3a697f5ffba 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -2370,7 +2370,7 @@ void ip_mc_drop_socket(struct sock *sk) inet->mc_list = iml->next_rcu; in_dev = inetdev_by_index(net, iml->multi.imr_ifindex); (void) ip_mc_leave_src(sk, iml, in_dev); - if (in_dev != NULL) + if (in_dev) ip_mc_dec_group(in_dev, iml->multi.imr_multiaddr.s_addr); /* decrease mem now to avoid the memleak warning */ atomic_sub(sizeof(*iml), &sk->sk_omem_alloc); @@ -2590,10 +2590,10 @@ static inline struct ip_sf_list *igmp_mcf_get_first(struct seq_file *seq) if (unlikely(!idev)) continue; im = rcu_dereference(idev->mc_list); - if (likely(im != NULL)) { + if (likely(im)) { spin_lock_bh(&im->lock); psf = im->sources; - if (likely(psf != NULL)) { + if (likely(psf)) { state->im = im; state->idev = idev; break; @@ -2663,7 +2663,7 @@ static void igmp_mcf_seq_stop(struct seq_file *seq, void *v) __releases(rcu) { struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); - if (likely(state->im != NULL)) { + if (likely(state->im)) { spin_unlock_bh(&state->im->lock); state->im = NULL; } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 79c0c9439fdc..5c3dd6267ed3 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -673,7 +673,7 @@ struct sock *inet_csk_clone_lock(const struct sock *sk, { struct sock *newsk = sk_clone_lock(sk, priority); - if (newsk != NULL) { + if (newsk) { struct inet_connection_sock *newicsk = inet_csk(newsk); newsk->sk_state = TCP_SYN_RECV; @@ -843,7 +843,7 @@ void inet_csk_listen_stop(struct sock *sk) sk_acceptq_removed(sk); reqsk_put(req); } - if (queue->fastopenq != NULL) { + if (queue->fastopenq) { /* Free all the reqs queued in rskq_rst_head. */ spin_lock_bh(&queue->fastopenq->lock); acc_req = queue->fastopenq->rskq_rst_head; @@ -875,7 +875,7 @@ int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname, { const struct inet_connection_sock *icsk = inet_csk(sk); - if (icsk->icsk_af_ops->compat_getsockopt != NULL) + if (icsk->icsk_af_ops->compat_getsockopt) return icsk->icsk_af_ops->compat_getsockopt(sk, level, optname, optval, optlen); return icsk->icsk_af_ops->getsockopt(sk, level, optname, @@ -888,7 +888,7 @@ int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname, { const struct inet_connection_sock *icsk = inet_csk(sk); - if (icsk->icsk_af_ops->compat_setsockopt != NULL) + if (icsk->icsk_af_ops->compat_setsockopt) return icsk->icsk_af_ops->compat_setsockopt(sk, level, optname, optval, optlen); return icsk->icsk_af_ops->setsockopt(sk, level, optname, diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 0fb841b9d834..d4630bf2d9aa 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -64,7 +64,7 @@ struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep, { struct inet_bind_bucket *tb = kmem_cache_alloc(cachep, GFP_ATOMIC); - if (tb != NULL) { + if (tb) { write_pnet(&tb->ib_net, net); tb->port = snum; tb->fastreuse = 0; diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index f38e387448fb..118f0f195820 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -173,7 +173,7 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, const int stat struct inet_timewait_sock *tw = kmem_cache_alloc(sk->sk_prot_creator->twsk_prot->twsk_slab, GFP_ATOMIC); - if (tw != NULL) { + if (tw) { const struct inet_sock *inet = inet_sk(sk); kmemcheck_annotate_bitfield(tw, flags); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 5a6cf8667a9d..cc1da6d9cb35 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -639,7 +639,8 @@ int ip_defrag(struct sk_buff *skb, u32 user) IP_INC_STATS_BH(net, IPSTATS_MIB_REASMREQDS); /* Lookup (or create) queue header */ - if ((qp = ip_find(net, ip_hdr(skb), user)) != NULL) { + qp = ip_find(net, ip_hdr(skb), user); + if (qp) { int ret; spin_lock(&qp->q.lock); diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 00bed6fe3b66..2e0410ed8f16 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -203,7 +203,7 @@ static int ip_local_deliver_finish(struct sk_buff *skb) raw = raw_local_deliver(skb, protocol); ipprot = rcu_dereference(inet_protos[protocol]); - if (ipprot != NULL) { + if (ipprot) { int ret; if (!ipprot->no_policy) { diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index 5b3d91be2db0..bd246792360b 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -264,7 +264,7 @@ int ip_options_compile(struct net *net, unsigned char *iph; int optlen, l; - if (skb != NULL) { + if (skb) { rt = skb_rtable(skb); optptr = (unsigned char *)&(ip_hdr(skb)[1]); } else diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 561d67b2ac74..26f6f7956168 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -257,7 +257,7 @@ static int ip_finish_output(struct sk_buff *skb) { #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM) /* Policy lookup after SNAT yielded a new policy */ - if (skb_dst(skb)->xfrm != NULL) { + if (skb_dst(skb)->xfrm) { IPCB(skb)->flags |= IPSKB_REROUTED; return dst_output(skb); } @@ -376,7 +376,7 @@ int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl) inet_opt = rcu_dereference(inet->inet_opt); fl4 = &fl->u.ip4; rt = skb_rtable(skb); - if (rt != NULL) + if (rt) goto packet_routed; /* Make sure we can route this packet. */ @@ -587,7 +587,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) ip_options_fragment(frag); offset += skb->len - hlen; iph->frag_off = htons(offset>>3); - if (frag->next != NULL) + if (frag->next) iph->frag_off |= htons(IP_MF); /* Ready, complete checksum */ ip_send_check(iph); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index f64b1b24c64f..7cfb0893f263 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -387,7 +387,7 @@ void ip_icmp_error(struct sock *sk, struct sk_buff *skb, int err, skb_network_header(skb); serr->port = port; - if (skb_pull(skb, payload - skb->data) != NULL) { + if (skb_pull(skb, payload - skb->data)) { skb_reset_transport_header(skb); if (sock_queue_err_skb(sk, skb) == 0) return; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 31eaa9ba1803..6d364ab8e14e 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -876,7 +876,7 @@ int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd) break; } if (dev != itn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) { - if (t != NULL) { + if (t) { if (t->dev != dev) { err = -EEXIST; break; diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index c4f93c0d1104..9f7269f3c54a 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -60,7 +60,7 @@ static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi, tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, iph->saddr, iph->daddr, 0); - if (tunnel != NULL) { + if (tunnel) { if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index a170e4bc9006..c204b728bbc1 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -316,7 +316,7 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id) unsigned int i; mrt = ipmr_get_table(net, id); - if (mrt != NULL) + if (mrt) return mrt; mrt = kzalloc(sizeof(*mrt), GFP_KERNEL); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 2dcd2e60df64..a93f260cf24c 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -971,7 +971,7 @@ bool ping_rcv(struct sk_buff *skb) skb_push(skb, skb->data - (u8 *)icmph); sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id)); - if (sk != NULL) { + if (sk) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); pr_debug("rcv on socket %p\n", sk); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 46a78204189d..6d0fa8fb8af0 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -293,7 +293,7 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info) read_lock(&raw_v4_hashinfo.lock); raw_sk = sk_head(&raw_v4_hashinfo.ht[hash]); - if (raw_sk != NULL) { + if (raw_sk) { iph = (const struct iphdr *)skb->data; net = dev_net(skb->dev); @@ -872,7 +872,7 @@ static int raw_ioctl(struct sock *sk, int cmd, unsigned long arg) spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); - if (skb != NULL) + if (skb) amount = skb->len; spin_unlock_bh(&sk->sk_receive_queue.lock); return put_user(amount, (int __user *)arg); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 26a1cb348b3d..a78540f28276 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1591,7 +1591,7 @@ static int __mkroute_input(struct sk_buff *skb, fnhe = find_exception(&FIB_RES_NH(*res), daddr); if (do_cache) { - if (fnhe != NULL) + if (fnhe) rth = rcu_dereference(fnhe->fnhe_rth_input); else rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 5bd809bfd0aa..094a6822c71d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -496,7 +496,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) /* Connected or passive Fast Open socket? */ if (sk->sk_state != TCP_SYN_SENT && - (sk->sk_state != TCP_SYN_RECV || tp->fastopen_rsk != NULL)) { + (sk->sk_state != TCP_SYN_RECV || tp->fastopen_rsk)) { int target = sock_rcvlowat(sk, 0, INT_MAX); if (tp->urg_seq == tp->copied_seq && @@ -1028,7 +1028,7 @@ static inline int select_size(const struct sock *sk, bool sg) void tcp_free_fastopen_req(struct tcp_sock *tp) { - if (tp->fastopen_req != NULL) { + if (tp->fastopen_req) { kfree(tp->fastopen_req); tp->fastopen_req = NULL; } @@ -1042,7 +1042,7 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE)) return -EOPNOTSUPP; - if (tp->fastopen_req != NULL) + if (tp->fastopen_req) return -EALREADY; /* Another Fast Open is in progress */ tp->fastopen_req = kzalloc(sizeof(struct tcp_fastopen_request), @@ -2138,7 +2138,7 @@ adjudge_to_death: * aborted (e.g., closed with unread data) before 3WHS * finishes. */ - if (req != NULL) + if (req) reqsk_fastopen_remove(sk, req, false); inet_csk_destroy_sock(sk); } @@ -2776,7 +2776,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_FASTOPEN: - if (icsk->icsk_accept_queue.fastopenq != NULL) + if (icsk->icsk_accept_queue.fastopenq) val = icsk->icsk_accept_queue.fastopenq->max_qlen; else val = 0; @@ -2960,7 +2960,7 @@ void tcp_done(struct sock *sk) tcp_set_state(sk, TCP_CLOSE); tcp_clear_xmit_timers(sk); - if (req != NULL) + if (req) reqsk_fastopen_remove(sk, req, false); sk->sk_shutdown = SHUTDOWN_MASK; diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index 86dc119a3815..79b34a0f4a4a 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -29,7 +29,7 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, r->idiag_rqueue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); r->idiag_wqueue = tp->write_seq - tp->snd_una; } - if (info != NULL) + if (info) tcp_get_info(sk, info); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 1fd283684303..df7e7fa12733 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1256,7 +1256,7 @@ static u8 tcp_sacktag_one(struct sock *sk, fack_count += pcount; /* Lost marker hint past SACKed? Tweak RFC3517 cnt */ - if (!tcp_is_fack(tp) && (tp->lost_skb_hint != NULL) && + if (!tcp_is_fack(tp) && tp->lost_skb_hint && before(start_seq, TCP_SKB_CB(tp->lost_skb_hint)->seq)) tp->lost_cnt_hint += pcount; @@ -1535,7 +1535,7 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, if (!before(TCP_SKB_CB(skb)->seq, end_seq)) break; - if ((next_dup != NULL) && + if (next_dup && before(TCP_SKB_CB(skb)->seq, next_dup->end_seq)) { in_sack = tcp_match_skb_to_sack(sk, skb, next_dup->start_seq, @@ -1551,7 +1551,7 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, if (in_sack <= 0) { tmp = tcp_shift_skb_data(sk, skb, state, start_seq, end_seq, dup_sack); - if (tmp != NULL) { + if (tmp) { if (tmp != skb) { skb = tmp; continue; @@ -5321,7 +5321,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb) tcp_set_state(sk, TCP_ESTABLISHED); - if (skb != NULL) { + if (skb) { icsk->icsk_af_ops->sk_rx_dst_set(sk, skb); security_inet_conn_established(sk, skb); } @@ -5690,7 +5690,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, } req = tp->fastopen_rsk; - if (req != NULL) { + if (req) { WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV && sk->sk_state != TCP_FIN_WAIT1); @@ -5780,7 +5780,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, * ACK we have received, this would have acknowledged * our SYNACK so stop the SYNACK timer. */ - if (req != NULL) { + if (req) { /* Return RST if ack_seq is invalid. * Note that RFC793 only says to generate a * DUPACK for it but for TCP Fast Open it seems diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 9ff311cf00f3..560f9571f7c4 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1305,7 +1305,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, /* Copy over the MD5 key from the original socket */ key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&newinet->inet_daddr, AF_INET); - if (key != NULL) { + if (key) { /* * We're using one, so create a matching key * on the newsk structure. If we fail to get @@ -1797,7 +1797,7 @@ void tcp_v4_destroy_sock(struct sock *sk) if (inet_csk(sk)->icsk_bind_hash) inet_put_port(sk); - BUG_ON(tp->fastopen_rsk != NULL); + BUG_ON(tp->fastopen_rsk); /* If socket is aborted during connect operation */ tcp_free_fastopen_req(tp); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index f0db1599a09c..d7003911c894 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -294,7 +294,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) if (tcp_death_row.tw_count < tcp_death_row.sysctl_max_tw_buckets) tw = inet_twsk_alloc(sk, state); - if (tw != NULL) { + if (tw) { struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); const int rto = (icsk->icsk_rto << 2) - (icsk->icsk_rto >> 1); struct inet_sock *inet = inet_sk(sk); @@ -332,7 +332,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) struct tcp_md5sig_key *key; tcptw->tw_md5_key = NULL; key = tp->af_specific->md5_lookup(sk, sk); - if (key != NULL) { + if (key) { tcptw->tw_md5_key = kmemdup(key, sizeof(*key), GFP_ATOMIC); if (tcptw->tw_md5_key && !tcp_alloc_md5sig_pool()) BUG(); @@ -454,7 +454,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, { struct sock *newsk = inet_csk_clone_lock(sk, req, GFP_ATOMIC); - if (newsk != NULL) { + if (newsk) { const struct inet_request_sock *ireq = inet_rsk(req); struct tcp_request_sock *treq = tcp_rsk(req); struct inet_connection_sock *newicsk = inet_csk(newsk); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index bdc80734cd2c..7404e5238e00 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -641,7 +641,7 @@ static unsigned int tcp_synack_options(struct sock *sk, if (unlikely(!ireq->tstamp_ok)) remaining -= TCPOLEN_SACKPERM_ALIGNED; } - if (foc != NULL && foc->len >= 0) { + if (foc && foc->len >= 0) { u32 need = TCPOLEN_EXP_FASTOPEN_BASE + foc->len; need = (need + 3) & ~3U; /* Align to 32 bits */ if (remaining >= need) { @@ -2224,7 +2224,7 @@ void tcp_send_loss_probe(struct sock *sk) int mss = tcp_current_mss(sk); int err = -1; - if (tcp_send_head(sk) != NULL) { + if (tcp_send_head(sk)) { err = tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC); goto rearm_timer; } @@ -2758,7 +2758,7 @@ begin_fwd: if (!tcp_can_forward_retransmit(sk)) break; /* Backtrack if necessary to non-L'ed skb */ - if (hole != NULL) { + if (hole) { skb = hole; hole = NULL; } @@ -2811,7 +2811,7 @@ void tcp_send_fin(struct sock *sk) */ mss_now = tcp_current_mss(sk); - if (tcp_send_head(sk) != NULL) { + if (tcp_send_head(sk)) { TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_FIN; TCP_SKB_CB(skb)->end_seq++; tp->write_seq++; @@ -3015,7 +3015,7 @@ static void tcp_connect_init(struct sock *sk) (sysctl_tcp_timestamps ? TCPOLEN_TSTAMP_ALIGNED : 0); #ifdef CONFIG_TCP_MD5SIG - if (tp->af_specific->md5_lookup(sk, sk) != NULL) + if (tp->af_specific->md5_lookup(sk, sk)) tp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED; #endif @@ -3376,8 +3376,8 @@ int tcp_write_wakeup(struct sock *sk) if (sk->sk_state == TCP_CLOSE) return -1; - if ((skb = tcp_send_head(sk)) != NULL && - before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp))) { + skb = tcp_send_head(sk); + if (skb && before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp))) { int err; unsigned int mss = tcp_current_mss(sk); unsigned int seg_size = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 9f525a2a68df..2162fc6ce1c1 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1522,7 +1522,7 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) /* if we're overly short, let UDP handle it */ encap_rcv = ACCESS_ONCE(up->encap_rcv); - if (skb->len > sizeof(struct udphdr) && encap_rcv != NULL) { + if (skb->len > sizeof(struct udphdr) && encap_rcv) { int ret; /* Verify checksum before giving to encap */ @@ -1802,7 +1802,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, saddr, daddr, udptable, proto); sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable); - if (sk != NULL) { + if (sk) { int ret; if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 4915d8284a86..f9386160cbee 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -285,7 +285,7 @@ void udp_del_offload(struct udp_offload *uo) pr_warn("udp_del_offload: didn't find offload for port %d\n", ntohs(uo->port)); unlock: spin_unlock(&udp_offload_lock); - if (uo_priv != NULL) + if (uo_priv) call_rcu(&uo_priv->rcu, udp_offload_free_routine); } EXPORT_SYMBOL(udp_del_offload); @@ -394,7 +394,7 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff) break; } - if (uo_priv != NULL) { + if (uo_priv) { NAPI_GRO_CB(skb)->proto = uo_priv->offload->ipproto; err = uo_priv->offload->callbacks.gro_complete(skb, nhoff + sizeof(struct udphdr), -- cgit v1.2.3 From 7f9b838b71eb78a27de27a12ca5de8542fac3115 Mon Sep 17 00:00:00 2001 From: Daniel Lee Date: Mon, 6 Apr 2015 14:37:26 -0700 Subject: tcp: RFC7413 option support for Fast Open server Fast Open has been using the experimental option with a magic number (RFC6994) to request and grant Fast Open cookies. This patch enables the server to support the official IANA option 34 in RFC7413 in addition. The change has passed all existing Fast Open tests with both old and new options at Google. Signed-off-by: Daniel Lee Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + include/net/tcp.h | 2 ++ net/ipv4/tcp_fastopen.c | 1 + net/ipv4/tcp_input.c | 42 ++++++++++++++++++++++++++++++------------ net/ipv4/tcp_output.c | 34 +++++++++++++++++++++++----------- 5 files changed, 57 insertions(+), 23 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index f869ae8afbaf..a48d00318683 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -58,6 +58,7 @@ static inline unsigned int tcp_optlen(const struct sk_buff *skb) struct tcp_fastopen_cookie { s8 len; u8 val[TCP_FASTOPEN_COOKIE_MAX]; + bool exp; /* In RFC6994 experimental option format */ }; /* This defines a selective acknowledgement block. */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 963303fb96ae..7292c3c575bc 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -179,6 +179,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); #define TCPOPT_SACK 5 /* SACK Block */ #define TCPOPT_TIMESTAMP 8 /* Better RTT estimations/PAWS */ #define TCPOPT_MD5SIG 19 /* MD5 Signature (RFC2385) */ +#define TCPOPT_FASTOPEN 34 /* Fast open (RFC7413) */ #define TCPOPT_EXP 254 /* Experimental */ /* Magic number to be after the option value for sharing TCP * experimental options. See draft-ietf-tcpm-experimental-options-00.txt @@ -194,6 +195,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); #define TCPOLEN_SACK_PERM 2 #define TCPOLEN_TIMESTAMP 10 #define TCPOLEN_MD5SIG 18 +#define TCPOLEN_FASTOPEN_BASE 2 #define TCPOLEN_EXP_FASTOPEN_BASE 4 /* But this is what stacks really send out. */ diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 5da55e2b5cd2..e3d87aca6be8 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -303,6 +303,7 @@ fastopen: } else if (foc->len > 0) /* Client presents an invalid cookie */ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVEFAIL); + valid_foc.exp = foc->exp; *foc = valid_foc; return false; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index c1ce304ba8d2..24f1630b2afb 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3603,6 +3603,23 @@ old_ack: return 0; } +static void tcp_parse_fastopen_option(int len, const unsigned char *cookie, + bool syn, struct tcp_fastopen_cookie *foc, + bool exp_opt) +{ + /* Valid only in SYN or SYN-ACK with an even length. */ + if (!foc || !syn || len < 0 || (len & 1)) + return; + + if (len >= TCP_FASTOPEN_COOKIE_MIN && + len <= TCP_FASTOPEN_COOKIE_MAX) + memcpy(foc->val, cookie, len); + else if (len != 0) + len = -1; + foc->len = len; + foc->exp = exp_opt; +} + /* Look for tcp options. Normally only called on SYN and SYNACK packets. * But, this can also be called on packets in the established flow when * the fast version below fails. @@ -3692,21 +3709,22 @@ void tcp_parse_options(const struct sk_buff *skb, */ break; #endif + case TCPOPT_FASTOPEN: + tcp_parse_fastopen_option( + opsize - TCPOLEN_FASTOPEN_BASE, + ptr, th->syn, foc, false); + break; + case TCPOPT_EXP: /* Fast Open option shares code 254 using a - * 16 bits magic number. It's valid only in - * SYN or SYN-ACK with an even size. + * 16 bits magic number. */ - if (opsize < TCPOLEN_EXP_FASTOPEN_BASE || - get_unaligned_be16(ptr) != TCPOPT_FASTOPEN_MAGIC || - !foc || !th->syn || (opsize & 1)) - break; - foc->len = opsize - TCPOLEN_EXP_FASTOPEN_BASE; - if (foc->len >= TCP_FASTOPEN_COOKIE_MIN && - foc->len <= TCP_FASTOPEN_COOKIE_MAX) - memcpy(foc->val, ptr + 2, foc->len); - else if (foc->len != 0) - foc->len = -1; + if (opsize >= TCPOLEN_EXP_FASTOPEN_BASE && + get_unaligned_be16(ptr) == + TCPOPT_FASTOPEN_MAGIC) + tcp_parse_fastopen_option(opsize - + TCPOLEN_EXP_FASTOPEN_BASE, + ptr + 2, th->syn, foc, true); break; } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 7404e5238e00..464bd8c5de69 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -518,17 +518,26 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp, if (unlikely(OPTION_FAST_OPEN_COOKIE & options)) { struct tcp_fastopen_cookie *foc = opts->fastopen_cookie; + u8 *p = (u8 *)ptr; + u32 len; /* Fast Open option length */ + + if (foc->exp) { + len = TCPOLEN_EXP_FASTOPEN_BASE + foc->len; + *ptr = htonl((TCPOPT_EXP << 24) | (len << 16) | + TCPOPT_FASTOPEN_MAGIC); + p += TCPOLEN_EXP_FASTOPEN_BASE; + } else { + len = TCPOLEN_FASTOPEN_BASE + foc->len; + *p++ = TCPOPT_FASTOPEN; + *p++ = len; + } - *ptr++ = htonl((TCPOPT_EXP << 24) | - ((TCPOLEN_EXP_FASTOPEN_BASE + foc->len) << 16) | - TCPOPT_FASTOPEN_MAGIC); - - memcpy(ptr, foc->val, foc->len); - if ((foc->len & 3) == 2) { - u8 *align = ((u8 *)ptr) + foc->len; - align[0] = align[1] = TCPOPT_NOP; + memcpy(p, foc->val, foc->len); + if ((len & 3) == 2) { + p[foc->len] = TCPOPT_NOP; + p[foc->len + 1] = TCPOPT_NOP; } - ptr += (foc->len + 3) >> 2; + ptr += (len + 3) >> 2; } } @@ -641,8 +650,11 @@ static unsigned int tcp_synack_options(struct sock *sk, if (unlikely(!ireq->tstamp_ok)) remaining -= TCPOLEN_SACKPERM_ALIGNED; } - if (foc && foc->len >= 0) { - u32 need = TCPOLEN_EXP_FASTOPEN_BASE + foc->len; + if (foc != NULL && foc->len >= 0) { + u32 need = foc->len; + + need += foc->exp ? TCPOLEN_EXP_FASTOPEN_BASE : + TCPOLEN_FASTOPEN_BASE; need = (need + 3) & ~3U; /* Align to 32 bits */ if (remaining >= need) { opts->options |= OPTION_FAST_OPEN_COOKIE; -- cgit v1.2.3 From 2646c831c00c5d22aa72b79d24069c1b412cda7c Mon Sep 17 00:00:00 2001 From: Daniel Lee Date: Mon, 6 Apr 2015 14:37:27 -0700 Subject: tcp: RFC7413 option support for Fast Open client Fast Open has been using an experimental option with a magic number (RFC6994). This patch makes the client by default use the RFC7413 option (34) to get and send Fast Open cookies. This patch makes the client solicit cookies from a given server first with the RFC7413 option. If that fails to elicit a cookie, then it tries the RFC6994 experimental option. If that also fails, it uses the RFC7413 option on all subsequent connect attempts. If the server returns a Fast Open cookie then the client caches the form of the option that successfully elicited a cookie, and uses that form on later connects when it presents that cookie. The idea is to gradually obsolete the use of experimental options as the servers and clients upgrade, while keeping the interoperability meanwhile. Signed-off-by: Daniel Lee Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + include/net/tcp.h | 3 ++- net/ipv4/tcp_input.c | 29 +++++++++++++++++++---------- net/ipv4/tcp_metrics.c | 13 +++++++++++-- net/ipv4/tcp_output.c | 6 +++++- net/ipv4/tcp_timer.c | 2 +- 6 files changed, 39 insertions(+), 15 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index a48d00318683..0caa3a2d4106 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -189,6 +189,7 @@ struct tcp_sock { u8 do_early_retrans:1,/* Enable RFC5827 early-retransmit */ syn_data:1, /* SYN includes data */ syn_fastopen:1, /* SYN includes Fast Open option */ + syn_fastopen_exp:1,/* SYN includes Fast Open exp. option */ syn_data_acked:1,/* data in SYN is acked by SYN-ACK */ is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */ u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 7292c3c575bc..9598871485ce 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1339,7 +1339,8 @@ void tcp_fastopen_cache_get(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie, int *syn_loss, unsigned long *last_syn_loss); void tcp_fastopen_cache_set(struct sock *sk, u16 mss, - struct tcp_fastopen_cookie *cookie, bool syn_lost); + struct tcp_fastopen_cookie *cookie, bool syn_lost, + u16 try_exp); struct tcp_fastopen_request { /* Fast Open cookie. Size 0 means a cookie request */ struct tcp_fastopen_cookie cookie; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 24f1630b2afb..031cf72cd05c 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5378,8 +5378,8 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *data = tp->syn_data ? tcp_write_queue_head(sk) : NULL; - u16 mss = tp->rx_opt.mss_clamp; - bool syn_drop; + u16 mss = tp->rx_opt.mss_clamp, try_exp = 0; + bool syn_drop = false; if (mss == tp->rx_opt.user_mss) { struct tcp_options_received opt; @@ -5391,16 +5391,25 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, mss = opt.mss_clamp; } - if (!tp->syn_fastopen) /* Ignore an unsolicited cookie */ + if (!tp->syn_fastopen) { + /* Ignore an unsolicited cookie */ cookie->len = -1; + } else if (tp->total_retrans) { + /* SYN timed out and the SYN-ACK neither has a cookie nor + * acknowledges data. Presumably the remote received only + * the retransmitted (regular) SYNs: either the original + * SYN-data or the corresponding SYN-ACK was dropped. + */ + syn_drop = (cookie->len < 0 && data); + } else if (cookie->len < 0 && !tp->syn_data) { + /* We requested a cookie but didn't get it. If we did not use + * the (old) exp opt format then try so next time (try_exp=1). + * Otherwise we go back to use the RFC7413 opt (try_exp=2). + */ + try_exp = tp->syn_fastopen_exp ? 2 : 1; + } - /* The SYN-ACK neither has cookie nor acknowledges the data. Presumably - * the remote receives only the retransmitted (regular) SYNs: either - * the original SYN-data or the corresponding SYN-ACK is lost. - */ - syn_drop = (cookie->len <= 0 && data && tp->total_retrans); - - tcp_fastopen_cache_set(sk, mss, cookie, syn_drop); + tcp_fastopen_cache_set(sk, mss, cookie, syn_drop, try_exp); if (data) { /* Retransmit unacked data in SYN */ tcp_for_write_queue_from(data, sk) { diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 78ecc4a01712..a51d63a43e33 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -28,7 +28,8 @@ static struct tcp_metrics_block *__tcp_get_metrics(const struct inetpeer_addr *s struct tcp_fastopen_metrics { u16 mss; - u16 syn_loss:10; /* Recurring Fast Open SYN losses */ + u16 syn_loss:10, /* Recurring Fast Open SYN losses */ + try_exp:2; /* Request w/ exp. option (once) */ unsigned long last_syn_loss; /* Last Fast Open SYN loss */ struct tcp_fastopen_cookie cookie; }; @@ -131,6 +132,8 @@ static void tcpm_suck_dst(struct tcp_metrics_block *tm, if (fastopen_clear) { tm->tcpm_fastopen.mss = 0; tm->tcpm_fastopen.syn_loss = 0; + tm->tcpm_fastopen.try_exp = 0; + tm->tcpm_fastopen.cookie.exp = false; tm->tcpm_fastopen.cookie.len = 0; } } @@ -713,6 +716,8 @@ void tcp_fastopen_cache_get(struct sock *sk, u16 *mss, if (tfom->mss) *mss = tfom->mss; *cookie = tfom->cookie; + if (cookie->len <= 0 && tfom->try_exp == 1) + cookie->exp = true; *syn_loss = tfom->syn_loss; *last_syn_loss = *syn_loss ? tfom->last_syn_loss : 0; } while (read_seqretry(&fastopen_seqlock, seq)); @@ -721,7 +726,8 @@ void tcp_fastopen_cache_get(struct sock *sk, u16 *mss, } void tcp_fastopen_cache_set(struct sock *sk, u16 mss, - struct tcp_fastopen_cookie *cookie, bool syn_lost) + struct tcp_fastopen_cookie *cookie, bool syn_lost, + u16 try_exp) { struct dst_entry *dst = __sk_dst_get(sk); struct tcp_metrics_block *tm; @@ -738,6 +744,9 @@ void tcp_fastopen_cache_set(struct sock *sk, u16 mss, tfom->mss = mss; if (cookie && cookie->len > 0) tfom->cookie = *cookie; + else if (try_exp > tfom->try_exp && + tfom->cookie.len <= 0 && !tfom->cookie.exp) + tfom->try_exp = try_exp; if (syn_lost) { ++tfom->syn_loss; tfom->last_syn_loss = jiffies; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 464bd8c5de69..e662d85d1635 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -592,13 +592,17 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, } if (fastopen && fastopen->cookie.len >= 0) { - u32 need = TCPOLEN_EXP_FASTOPEN_BASE + fastopen->cookie.len; + u32 need = fastopen->cookie.len; + + need += fastopen->cookie.exp ? TCPOLEN_EXP_FASTOPEN_BASE : + TCPOLEN_FASTOPEN_BASE; need = (need + 3) & ~3U; /* Align to 32 bits */ if (remaining >= need) { opts->options |= OPTION_FAST_OPEN_COOKIE; opts->fastopen_cookie = &fastopen->cookie; remaining -= need; tp->syn_fastopen = 1; + tp->syn_fastopen_exp = fastopen->cookie.exp ? 1 : 0; } } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 2568fd282873..8c65dc147d8b 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -167,7 +167,7 @@ static int tcp_write_timeout(struct sock *sk) if (icsk->icsk_retransmits) { dst_negative_advice(sk); if (tp->syn_fastopen || tp->syn_data) - tcp_fastopen_cache_set(sk, 0, NULL, true); + tcp_fastopen_cache_set(sk, 0, NULL, true, 0); if (tp->syn_data) NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVEFAIL); -- cgit v1.2.3 From 3d0d26c7976bf190c3f1d2efbc31462db8246bc0 Mon Sep 17 00:00:00 2001 From: Kenneth Klette Jonassen Date: Sat, 11 Apr 2015 02:17:49 +0200 Subject: tcp: fix bogus RTT for CC when retransmissions are acked Since retransmitted segments are not used for RTT estimation, previously SACKed segments present in the rtx queue are used. This estimation can be several times larger than the actual RTT. When a cumulative ack covers both previously SACKed and retransmitted segments, CC may thus get a bogus RTT. Such segments previously had an RTT estimation in tcp_sacktag_one(), so it seems reasonable to not reuse them in tcp_clean_rtx_queue() at all. Afaik, this has had no effect on SRTT/RTO because of Karn's check. Signed-off-by: Kenneth Klette Jonassen Acked-by: Neal Cardwell Tested-by: Neal Cardwell Acked-by: Yuchung Cheng Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 031cf72cd05c..a7ef679dd3ea 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3099,17 +3099,15 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (sacked & TCPCB_SACKED_RETRANS) tp->retrans_out -= acked_pcount; flag |= FLAG_RETRANS_DATA_ACKED; - } else { + } else if (!(sacked & TCPCB_SACKED_ACKED)) { last_ackt = skb->skb_mstamp; WARN_ON_ONCE(last_ackt.v64 == 0); if (!first_ackt.v64) first_ackt = last_ackt; - if (!(sacked & TCPCB_SACKED_ACKED)) { - reord = min(pkts_acked, reord); - if (!after(scb->end_seq, tp->high_seq)) - flag |= FLAG_ORIG_SACK_ACKED; - } + reord = min(pkts_acked, reord); + if (!after(scb->end_seq, tp->high_seq)) + flag |= FLAG_ORIG_SACK_ACKED; } if (sacked & TCPCB_SACKED_ACKED) -- cgit v1.2.3 From 3c7151275c0c9a80c3375f9874b1c7129a105eea Mon Sep 17 00:00:00 2001 From: "jbaron@akamai.com" Date: Mon, 20 Apr 2015 20:05:07 +0000 Subject: tcp: add memory barriers to write space paths Ensure that we either see that the buffer has write space in tcp_poll() or that we perform a wakeup from the input side. Did not run into any actual problem here, but thought that we should make things explicit. Signed-off-by: Jason Baron Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 4 +++- net/ipv4/tcp_input.c | 2 ++ 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 59c8a027721b..8c5cd9efebbc 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -520,8 +520,10 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) /* Race breaker. If space is freed after * wspace test but before the flags are set, - * IO signal will be lost. + * IO signal will be lost. Memory barrier + * pairs with the input side. */ + smp_mb__after_atomic(); if (sk_stream_is_writeable(sk)) mask |= POLLOUT | POLLWRNORM; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index a7ef679dd3ea..3a4d9b34bed4 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4845,6 +4845,8 @@ static void tcp_check_space(struct sock *sk) { if (sock_flag(sk, SOCK_QUEUE_SHRUNK)) { sock_reset_flag(sk, SOCK_QUEUE_SHRUNK); + /* pairs with tcp_poll() */ + smp_mb__after_atomic(); if (sk->sk_socket && test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) tcp_new_space(sk); -- cgit v1.2.3 From 0df48c26d8418c5c9fba63fac15b660d70ca2f1c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 28 Apr 2015 15:28:17 -0700 Subject: tcp: add tcpi_bytes_acked to tcp_info This patch tracks total number of bytes acked for a TCP socket. This is the sum of all changes done to tp->snd_una, and allows for precise tracking of delivered data. RFC4898 named this : tcpEStatsAppHCThruOctetsAcked This is a 64bit field, and can be fetched both from TCP_INFO getsockopt() if one has a handle on a TCP socket, or from inet_diag netlink facility (iproute2/ss patch will follow) Note that tp->bytes_acked was placed near tp->snd_una for best data locality and minimal performance impact. Signed-off-by: Eric Dumazet Acked-by: Yuchung Cheng Cc: Matt Mathis Cc: Eric Salo Cc: Martin Lau Cc: Chris Rapier Signed-off-by: David S. Miller --- include/linux/tcp.h | 4 ++++ include/net/tcp.h | 2 +- include/uapi/linux/tcp.h | 1 + net/ipv4/tcp.c | 6 +++++- net/ipv4/tcp_input.c | 13 +++++++++++-- 5 files changed, 22 insertions(+), 4 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 0caa3a2d4106..0f73b43171da 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -150,6 +150,10 @@ struct tcp_sock { u32 rcv_wup; /* rcv_nxt on last window update sent */ u32 snd_nxt; /* Next sequence we send */ + u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked + * sum(delta(snd_una)), or how many bytes + * were acked. + */ u32 snd_una; /* First byte we want an ack for */ u32 snd_sml; /* Last byte of the most recently transmitted small packet */ u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */ diff --git a/include/net/tcp.h b/include/net/tcp.h index 051dc5c2802d..dd7b4ea6a10c 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -576,7 +576,7 @@ static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize) } /* tcp.c */ -void tcp_get_info(const struct sock *, struct tcp_info *); +void tcp_get_info(struct sock *, struct tcp_info *); /* Read 'sendfile()'-style from a TCP socket */ typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *, diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 3b9718328d8b..6666e98a0af9 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -189,6 +189,7 @@ struct tcp_info { __u64 tcpi_pacing_rate; __u64 tcpi_max_pacing_rate; + __u64 tcpi_bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked */ }; /* for TCP_MD5SIG socket option */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 8c5cd9efebbc..4bf0e8ca7b5b 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2592,7 +2592,7 @@ EXPORT_SYMBOL(compat_tcp_setsockopt); #endif /* Return information about state of tcp endpoint in API format. */ -void tcp_get_info(const struct sock *sk, struct tcp_info *info) +void tcp_get_info(struct sock *sk, struct tcp_info *info) { const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); @@ -2663,6 +2663,10 @@ void tcp_get_info(const struct sock *sk, struct tcp_info *info) rate = READ_ONCE(sk->sk_max_pacing_rate); info->tcpi_max_pacing_rate = rate != ~0U ? rate : ~0ULL; + + spin_lock_bh(&sk->sk_lock.slock); + info->tcpi_bytes_acked = tp->bytes_acked; + spin_unlock_bh(&sk->sk_lock.slock); } EXPORT_SYMBOL_GPL(tcp_get_info); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 3a4d9b34bed4..378d3f4d4dc3 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3280,6 +3280,15 @@ static inline bool tcp_may_update_window(const struct tcp_sock *tp, (ack_seq == tp->snd_wl1 && nwin > tp->snd_wnd); } +/* If we update tp->snd_una, also update tp->bytes_acked */ +static void tcp_snd_una_update(struct tcp_sock *tp, u32 ack) +{ + u32 delta = ack - tp->snd_una; + + tp->bytes_acked += delta; + tp->snd_una = ack; +} + /* Update our send window. * * Window update algorithm, described in RFC793/RFC1122 (used in linux-2.2 @@ -3315,7 +3324,7 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32 } } - tp->snd_una = ack; + tcp_snd_una_update(tp, ack); return flag; } @@ -3497,7 +3506,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) * Note, we use the fact that SND.UNA>=SND.WL2. */ tcp_update_wl(tp, ack_seq); - tp->snd_una = ack; + tcp_snd_una_update(tp, ack); flag |= FLAG_WIN_UPDATE; tcp_in_ack_event(sk, CA_ACK_WIN_UPDATE); -- cgit v1.2.3 From bdd1f9edacb5f5835d1e6276571bbbe5b88ded48 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 28 Apr 2015 15:28:18 -0700 Subject: tcp: add tcpi_bytes_received to tcp_info This patch tracks total number of payload bytes received on a TCP socket. This is the sum of all changes done to tp->rcv_nxt RFC4898 named this : tcpEStatsAppHCThruOctetsReceived This is a 64bit field, and can be fetched both from TCP_INFO getsockopt() if one has a handle on a TCP socket, or from inet_diag netlink facility (iproute2/ss patch will follow) Note that tp->bytes_received was placed near tp->rcv_nxt for best data locality and minimal performance impact. Signed-off-by: Eric Dumazet Cc: Yuchung Cheng Cc: Matt Mathis Cc: Eric Salo Cc: Martin Lau Cc: Chris Rapier Acked-by: Yuchung Cheng Signed-off-by: David S. Miller --- include/linux/tcp.h | 4 ++++ include/uapi/linux/tcp.h | 1 + net/ipv4/tcp.c | 1 + net/ipv4/tcp_fastopen.c | 1 + net/ipv4/tcp_input.c | 17 +++++++++++++---- 5 files changed, 20 insertions(+), 4 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 0f73b43171da..3b2911502a8c 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -145,6 +145,10 @@ struct tcp_sock { * read the code and the spec side by side (and laugh ...) * See RFC793 and RFC1122. The RFC writes these in capitals. */ + u64 bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived + * sum(delta(rcv_nxt)), or how many bytes + * were acked. + */ u32 rcv_nxt; /* What we want to receive next */ u32 copied_seq; /* Head of yet unread data */ u32 rcv_wup; /* rcv_nxt on last window update sent */ diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 6666e98a0af9..a48f93f3207b 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -190,6 +190,7 @@ struct tcp_info { __u64 tcpi_pacing_rate; __u64 tcpi_max_pacing_rate; __u64 tcpi_bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked */ + __u64 tcpi_bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived */ }; /* for TCP_MD5SIG socket option */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 4bf0e8ca7b5b..99fcc0b22c92 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2666,6 +2666,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) spin_lock_bh(&sk->sk_lock.slock); info->tcpi_bytes_acked = tp->bytes_acked; + info->tcpi_bytes_received = tp->bytes_received; spin_unlock_bh(&sk->sk_lock.slock); } EXPORT_SYMBOL_GPL(tcp_get_info); diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index e3d87aca6be8..3c673d5e6cff 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -206,6 +206,7 @@ static bool tcp_fastopen_create_child(struct sock *sk, skb_set_owner_r(skb2, child); __skb_queue_tail(&child->sk_receive_queue, skb2); tp->syn_data_acked = 1; + tp->bytes_received = end_seq - TCP_SKB_CB(skb)->seq - 1; } else { end_seq = TCP_SKB_CB(skb)->seq + 1; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 378d3f4d4dc3..7e6962bcfc30 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3289,6 +3289,15 @@ static void tcp_snd_una_update(struct tcp_sock *tp, u32 ack) tp->snd_una = ack; } +/* If we update tp->rcv_nxt, also update tp->bytes_received */ +static void tcp_rcv_nxt_update(struct tcp_sock *tp, u32 seq) +{ + u32 delta = seq - tp->rcv_nxt; + + tp->bytes_received += delta; + tp->rcv_nxt = seq; +} + /* Update our send window. * * Window update algorithm, described in RFC793/RFC1122 (used in linux-2.2 @@ -4245,7 +4254,7 @@ static void tcp_ofo_queue(struct sock *sk) tail = skb_peek_tail(&sk->sk_receive_queue); eaten = tail && tcp_try_coalesce(sk, tail, skb, &fragstolen); - tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; + tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq); if (!eaten) __skb_queue_tail(&sk->sk_receive_queue, skb); if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) @@ -4413,7 +4422,7 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int __skb_pull(skb, hdrlen); eaten = (tail && tcp_try_coalesce(sk, tail, skb, fragstolen)) ? 1 : 0; - tcp_sk(sk)->rcv_nxt = TCP_SKB_CB(skb)->end_seq; + tcp_rcv_nxt_update(tcp_sk(sk), TCP_SKB_CB(skb)->end_seq); if (!eaten) { __skb_queue_tail(&sk->sk_receive_queue, skb); skb_set_owner_r(skb, sk); @@ -4506,7 +4515,7 @@ queue_and_out: eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen); } - tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; + tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq); if (skb->len) tcp_event_data_recv(sk, skb); if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) @@ -5254,7 +5263,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb, tcp_rcv_rtt_measure_ts(sk, skb); __skb_pull(skb, tcp_header_len); - tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; + tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPHPHITSTOUSER); eaten = 1; } -- cgit v1.2.3 From 9dac8835440622c2f84591673969d510ce198c11 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Wed, 29 Apr 2015 11:28:30 -0700 Subject: tcp: update reordering first before detecting loss tcp_mark_lost_retrans is not used when FACK is disabled. Since tcp_update_reordering may disable FACK, it should be called first before tcp_mark_lost_retrans. Signed-off-by: Yuchung Cheng Signed-off-by: Nandita Dukkipati Signed-off-by: Neal Cardwell Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 7e6962bcfc30..bc790ea9960f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1820,14 +1820,12 @@ advance_sp: for (j = 0; j < used_sacks; j++) tp->recv_sack_cache[i++] = sp[j]; - tcp_mark_lost_retrans(sk); - - tcp_verify_left_out(tp); - if ((state.reord < tp->fackets_out) && ((inet_csk(sk)->icsk_ca_state != TCP_CA_Loss) || tp->undo_marker)) tcp_update_reordering(sk, tp->fackets_out - state.reord, 0); + tcp_mark_lost_retrans(sk); + tcp_verify_left_out(tp); out: #if FASTRETRANS_DEBUG > 0 -- cgit v1.2.3