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 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux/tcp.h') 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) */ -- cgit v1.2.3-55-g7522 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 'include/linux/tcp.h') 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 v1.2.3-55-g7522 From cd8ae85299d54155702a56811b2e035e63064d3d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 3 May 2015 21:34:46 -0700 Subject: tcp: provide SYN headers for passive connections This patch allows a server application to get the TCP SYN headers for its passive connections. This is useful if the server is doing fingerprinting of clients based on SYN packet contents. Two socket options are added: TCP_SAVE_SYN and TCP_SAVED_SYN. The first is used on a socket to enable saving the SYN headers for child connections. This can be set before or after the listen() call. The latter is used to retrieve the SYN headers for passive connections, if the parent listener has enabled TCP_SAVE_SYN. TCP_SAVED_SYN is read once, it frees the saved SYN headers. The data returned in TCP_SAVED_SYN are network (IPv4/IPv6) and TCP headers. Original patch was written by Tom Herbert, I changed it to not hold a full skb (and associated dst and conntracking reference). We have used such patch for about 3 years at Google. Signed-off-by: Eric Dumazet Acked-by: Neal Cardwell Tested-by: Neal Cardwell Signed-off-by: David S. Miller --- include/linux/tcp.h | 8 ++++++++ include/net/request_sock.h | 4 +++- include/uapi/linux/tcp.h | 2 ++ net/ipv4/tcp.c | 35 +++++++++++++++++++++++++++++++++++ net/ipv4/tcp_input.c | 18 ++++++++++++++++++ net/ipv4/tcp_ipv4.c | 1 + net/ipv4/tcp_minisocks.c | 3 +++ 7 files changed, 70 insertions(+), 1 deletion(-) (limited to 'include/linux/tcp.h') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 3b2911502a8c..e6fb5df22db1 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -199,6 +199,7 @@ struct tcp_sock { 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 */ + save_syn:1, /* Save headers of SYN packet */ is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */ u32 tlp_high_seq; /* snd_nxt at the time of TLP retransmit. */ @@ -326,6 +327,7 @@ struct tcp_sock { * socket. Used to retransmit SYNACKs etc. */ struct request_sock *fastopen_rsk; + u32 *saved_syn; }; enum tsq_flags { @@ -393,4 +395,10 @@ static inline int fastopen_init_queue(struct sock *sk, int backlog) return 0; } +static inline void tcp_saved_syn_free(struct tcp_sock *tp) +{ + kfree(tp->saved_syn); + tp->saved_syn = NULL; +} + #endif /* _LINUX_TCP_H */ diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 9f4265ce8892..87935cad2f7b 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -64,6 +64,7 @@ struct request_sock { struct timer_list rsk_timer; const struct request_sock_ops *rsk_ops; struct sock *sk; + u32 *saved_syn; u32 secid; u32 peer_secid; }; @@ -77,7 +78,7 @@ 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; - + req->saved_syn = NULL; /* Following is temporary. It is coupled with debugging * helpers in reqsk_put() & reqsk_free() */ @@ -104,6 +105,7 @@ static inline void reqsk_free(struct request_sock *req) req->rsk_ops->destructor(req); if (req->rsk_listener) sock_put(req->rsk_listener); + kfree(req->saved_syn); kmem_cache_free(req->rsk_ops->slab, req); } diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index faa72f4fa547..51ebedba577f 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -113,6 +113,8 @@ enum { #define TCP_TIMESTAMP 24 #define TCP_NOTSENT_LOWAT 25 /* limit number of unsent bytes in write queue */ #define TCP_CC_INFO 26 /* Get Congestion Control (optional) info */ +#define TCP_SAVE_SYN 27 /* Record SYN headers for new connections */ +#define TCP_SAVED_SYN 28 /* Get SYN headers recorded for connection */ struct tcp_repair_opt { __u32 opt_code; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 46efa03d2b11..ecccfdc50d76 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2482,6 +2482,13 @@ static int do_tcp_setsockopt(struct sock *sk, int level, icsk->icsk_syn_retries = val; break; + case TCP_SAVE_SYN: + if (val < 0 || val > 1) + err = -EINVAL; + else + tp->save_syn = val; + break; + case TCP_LINGER2: if (val < 0) tp->linger2 = -1; @@ -2818,6 +2825,34 @@ static int do_tcp_getsockopt(struct sock *sk, int level, case TCP_NOTSENT_LOWAT: val = tp->notsent_lowat; break; + case TCP_SAVE_SYN: + val = tp->save_syn; + break; + case TCP_SAVED_SYN: { + if (get_user(len, optlen)) + return -EFAULT; + + lock_sock(sk); + if (tp->saved_syn) { + len = min_t(unsigned int, tp->saved_syn[0], len); + if (put_user(len, optlen)) { + release_sock(sk); + return -EFAULT; + } + if (copy_to_user(optval, tp->saved_syn + 1, len)) { + release_sock(sk); + return -EFAULT; + } + tcp_saved_syn_free(tp); + release_sock(sk); + } else { + release_sock(sk); + len = 0; + if (put_user(len, optlen)) + return -EFAULT; + } + return 0; + } default: return -ENOPROTOOPT; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 09bdc4abfcbb..df2ca615cd0c 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -6060,6 +6060,23 @@ static bool tcp_syn_flood_action(struct sock *sk, return want_cookie; } +static void tcp_reqsk_record_syn(const struct sock *sk, + struct request_sock *req, + const struct sk_buff *skb) +{ + if (tcp_sk(sk)->save_syn) { + u32 len = skb_network_header_len(skb) + tcp_hdrlen(skb); + u32 *copy; + + copy = kmalloc(len + sizeof(u32), GFP_ATOMIC); + if (copy) { + copy[0] = len; + memcpy(©[1], skb_network_header(skb), len); + req->saved_syn = copy; + } + } +} + 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) @@ -6192,6 +6209,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tcp_rsk(req)->tfo_listener = false; af_ops->queue_hash_add(sk, req, TCP_TIMEOUT_INIT); } + tcp_reqsk_record_syn(sk, req, skb); return 0; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index fc1c658ec6c1..91cb4768a860 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1802,6 +1802,7 @@ void tcp_v4_destroy_sock(struct sock *sk) /* If socket is aborted during connect operation */ tcp_free_fastopen_req(tp); + tcp_saved_syn_free(tp); sk_sockets_allocated_dec(sk); sock_release_memcg(sk); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index e5d7649136fc..ebe2ab2596ed 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -536,6 +536,9 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, newtp->fastopen_rsk = NULL; newtp->syn_data_acked = 0; + newtp->saved_syn = req->saved_syn; + req->saved_syn = NULL; + TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_PASSIVEOPENS); } return newsk; -- cgit v1.2.3-55-g7522 From 2efd055c53c06b7e89c167c98069bab9afce7e59 Mon Sep 17 00:00:00 2001 From: Marcelo Ricardo Leitner Date: Wed, 20 May 2015 16:35:41 -0700 Subject: tcp: add tcpi_segs_in and tcpi_segs_out to tcp_info This patch tracks the total number of inbound and outbound segments on a TCP socket. One may use this number to have an idea on connection quality when compared against the retransmissions. RFC4898 named these : tcpEStatsPerfSegsIn and tcpEStatsPerfSegsOut These are a 32bit field each 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->segs_out was placed near tp->snd_nxt for good data locality and minimal performance impact, while tp->segs_in was placed near tp->bytes_received for the same reason. Join work with Eric Dumazet. Note that received SYN are accounted on the listener, but sent SYNACK are not accounted. Signed-off-by: Marcelo Ricardo Leitner Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 7 ++++++- include/uapi/linux/tcp.h | 4 +++- net/ipv4/tcp.c | 2 ++ net/ipv4/tcp_ipv4.c | 1 + net/ipv4/tcp_minisocks.c | 1 + net/ipv4/tcp_output.c | 1 + net/ipv6/tcp_ipv6.c | 1 + 7 files changed, 15 insertions(+), 2 deletions(-) (limited to 'include/linux/tcp.h') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index e6fb5df22db1..f0212026c77f 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -149,11 +149,16 @@ struct tcp_sock { * sum(delta(rcv_nxt)), or how many bytes * were acked. */ + u32 segs_in; /* RFC4898 tcpEStatsPerfSegsIn + * total number of segments in. + */ 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 */ u32 snd_nxt; /* Next sequence we send */ - + u32 segs_out; /* RFC4898 tcpEStatsPerfSegsOut + * The total number of segments sent. + */ u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked * sum(delta(snd_una)), or how many bytes * were acked. diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 51ebedba577f..65a77b071e22 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -192,8 +192,10 @@ struct tcp_info { __u64 tcpi_pacing_rate; __u64 tcpi_max_pacing_rate; - __u64 tcpi_bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked */ + __u64 tcpi_bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked */ __u64 tcpi_bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived */ + __u32 tcpi_segs_out; /* RFC4898 tcpEStatsPerfSegsOut */ + __u32 tcpi_segs_in; /* RFC4898 tcpEStatsPerfSegsIn */ }; /* for TCP_MD5SIG socket option */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 0a3f9a00565b..7f3e721b9e69 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2695,6 +2695,8 @@ 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; + info->tcpi_segs_out = tp->segs_out; + info->tcpi_segs_in = tp->segs_in; spin_unlock_bh(&sk->sk_lock.slock); } EXPORT_SYMBOL_GPL(tcp_get_info); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 0cc4b5a630cd..feb875769b8d 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1626,6 +1626,7 @@ process: skb->dev = NULL; bh_lock_sock_nested(sk); + tcp_sk(sk)->segs_in += max_t(u16, 1, skb_shinfo(skb)->gso_segs); ret = 0; if (!sock_owned_by_user(sk)) { if (!tcp_prequeue(sk, skb)) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index ebe2ab2596ed..b62d15c86946 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -448,6 +448,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, newtp->rcv_wup = newtp->copied_seq = newtp->rcv_nxt = treq->rcv_isn + 1; + newtp->segs_in = 0; newtp->snd_sml = newtp->snd_una = newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 3aebe0157dfa..534e5fdb04c1 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1027,6 +1027,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, TCP_ADD_STATS(sock_net(sk), TCP_MIB_OUTSEGS, tcp_skb_pcount(skb)); + tp->segs_out += tcp_skb_pcount(skb); /* OK, its time to fill skb_shinfo(skb)->gso_segs */ skb_shinfo(skb)->gso_segs = tcp_skb_pcount(skb); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index b6575d665568..beac6bf840b9 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1421,6 +1421,7 @@ process: skb->dev = NULL; bh_lock_sock_nested(sk); + tcp_sk(sk)->segs_in += max_t(u16, 1, skb_shinfo(skb)->gso_segs); ret = 0; if (!sock_owned_by_user(sk)) { if (!tcp_prequeue(sk, skb)) -- cgit v1.2.3-55-g7522 From d654976cbf852ee20612ee10dbe57cdacda9f452 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 21 May 2015 21:51:19 -0700 Subject: tcp: fix a potential deadlock in tcp_get_info() Taking socket spinlock in tcp_get_info() can deadlock, as inet_diag_dump_icsk() holds the &hashinfo->ehash_locks[i], while packet processing can use the reverse locking order. We could avoid this locking for TCP_LISTEN states, but lockdep would certainly get confused as all TCP sockets share same lockdep classes. [ 523.722504] ====================================================== [ 523.728706] [ INFO: possible circular locking dependency detected ] [ 523.734990] 4.1.0-dbg-DEV #1676 Not tainted [ 523.739202] ------------------------------------------------------- [ 523.745474] ss/18032 is trying to acquire lock: [ 523.750002] (slock-AF_INET){+.-...}, at: [] tcp_get_info+0x2c4/0x360 [ 523.758129] [ 523.758129] but task is already holding lock: [ 523.763968] (&(&hashinfo->ehash_locks[i])->rlock){+.-...}, at: [] inet_diag_dump_icsk+0x1d5/0x6c0 [ 523.774661] [ 523.774661] which lock already depends on the new lock. [ 523.774661] [ 523.782850] [ 523.782850] the existing dependency chain (in reverse order) is: [ 523.790326] -> #1 (&(&hashinfo->ehash_locks[i])->rlock){+.-...}: [ 523.796599] [] lock_acquire+0xbb/0x270 [ 523.802565] [] _raw_spin_lock+0x38/0x50 [ 523.808628] [] __inet_hash_nolisten+0x78/0x110 [ 523.815273] [] tcp_v4_syn_recv_sock+0x24b/0x350 [ 523.822067] [] tcp_check_req+0x3c1/0x500 [ 523.828199] [] tcp_v4_do_rcv+0x239/0x3d0 [ 523.834331] [] tcp_v4_rcv+0xa8e/0xc10 [ 523.840202] [] ip_local_deliver_finish+0x133/0x3e0 [ 523.847214] [] ip_local_deliver+0xaa/0xc0 [ 523.853440] [] ip_rcv_finish+0x168/0x5c0 [ 523.859624] [] ip_rcv+0x307/0x420 Lets use u64_sync infrastructure instead. As a bonus, 64bit arches get optimized, as these are nop for them. Fixes: 0df48c26d841 ("tcp: add tcpi_bytes_acked to tcp_info") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 2 ++ net/ipv4/tcp.c | 11 +++++++---- net/ipv4/tcp_fastopen.c | 4 ++++ net/ipv4/tcp_input.c | 4 ++++ 4 files changed, 17 insertions(+), 4 deletions(-) (limited to 'include/linux/tcp.h') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 3b2911502a8c..e8bbf403618f 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -158,6 +158,8 @@ struct tcp_sock { * sum(delta(snd_una)), or how many bytes * were acked. */ + struct u64_stats_sync syncp; /* protects 64bit vars (cf tcp_get_info()) */ + 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/net/ipv4/tcp.c b/net/ipv4/tcp.c index 46efa03d2b11..f1377f2a0472 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -402,6 +402,7 @@ void tcp_init_sock(struct sock *sk) tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_clamp = ~0; tp->mss_cache = TCP_MSS_DEFAULT; + u64_stats_init(&tp->syncp); tp->reordering = sysctl_tcp_reordering; tcp_enable_early_retrans(tp); @@ -2598,6 +2599,7 @@ 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); u32 now = tcp_time_stamp; + unsigned int start; u32 rate; memset(info, 0, sizeof(*info)); @@ -2665,10 +2667,11 @@ void tcp_get_info(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; - info->tcpi_bytes_received = tp->bytes_received; - spin_unlock_bh(&sk->sk_lock.slock); + do { + start = u64_stats_fetch_begin_irq(&tp->syncp); + info->tcpi_bytes_acked = tp->bytes_acked; + info->tcpi_bytes_received = tp->bytes_received; + } while (u64_stats_fetch_retry_irq(&tp->syncp, start)); } EXPORT_SYMBOL_GPL(tcp_get_info); diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 3c673d5e6cff..46b087a27503 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -206,6 +206,10 @@ 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; + + /* u64_stats_update_begin(&tp->syncp) not needed here, + * as we certainly are not changing upper 32bit value (0) + */ 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 243d674b3ef5..c9ab964189a0 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3286,7 +3286,9 @@ static void tcp_snd_una_update(struct tcp_sock *tp, u32 ack) { u32 delta = ack - tp->snd_una; + u64_stats_update_begin(&tp->syncp); tp->bytes_acked += delta; + u64_stats_update_end(&tp->syncp); tp->snd_una = ack; } @@ -3295,7 +3297,9 @@ static void tcp_rcv_nxt_update(struct tcp_sock *tp, u32 seq) { u32 delta = seq - tp->rcv_nxt; + u64_stats_update_begin(&tp->syncp); tp->bytes_received += delta; + u64_stats_update_end(&tp->syncp); tp->rcv_nxt = seq; } -- cgit v1.2.3-55-g7522