From 082116ffcb7457ae50e3ddb0213d66ab29408f30 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sun, 20 Feb 2022 15:06:29 +0800 Subject: [PATCH 1/9] net: tcp: introduce tcp_drop_reason() For TCP protocol, tcp_drop() is used to free the skb when it needs to be dropped. To make use of kfree_skb_reason() and pass the drop reason to it, introduce the function tcp_drop_reason(). Meanwhile, make tcp_drop() an inline call to tcp_drop_reason(). Reviewed-by: Mengen Sun Reviewed-by: Hao Peng Signed-off-by: Menglong Dong Reviewed-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 92e65d56dc2c..0f41fdfd8c27 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4684,10 +4684,16 @@ static bool tcp_ooo_try_coalesce(struct sock *sk, return res; } -static void tcp_drop(struct sock *sk, struct sk_buff *skb) +static void tcp_drop_reason(struct sock *sk, struct sk_buff *skb, + enum skb_drop_reason reason) { sk_drops_add(sk, skb); - __kfree_skb(skb); + kfree_skb_reason(skb, reason); +} + +static void tcp_drop(struct sock *sk, struct sk_buff *skb) +{ + tcp_drop_reason(sk, skb, SKB_DROP_REASON_NOT_SPECIFIED); } /* This one checks to see if we can put data from the From 255f9034d3050fb1d0691226712c6b7f1ca674cd Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sun, 20 Feb 2022 15:06:30 +0800 Subject: [PATCH 2/9] net: tcp: add skb drop reasons to tcp_v4_rcv() Use kfree_skb_reason() for some path in tcp_v4_rcv() that missed before, including: SKB_DROP_REASON_SOCKET_FILTER SKB_DROP_REASON_XFRM_POLICY Reviewed-by: Mengen Sun Reviewed-by: Hao Peng Signed-off-by: Menglong Dong Reviewed-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 6873f46fc8ba..a3beab01e9a7 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2057,6 +2057,8 @@ int tcp_v4_rcv(struct sk_buff *skb) iph = ip_hdr(skb); tcp_v4_fill_cb(skb, iph, th); nsk = tcp_check_req(sk, skb, req, false, &req_stolen); + } else { + drop_reason = SKB_DROP_REASON_SOCKET_FILTER; } if (!nsk) { reqsk_put(req); @@ -2092,8 +2094,10 @@ int tcp_v4_rcv(struct sk_buff *skb) } } - if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) + if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) { + drop_reason = SKB_DROP_REASON_XFRM_POLICY; goto discard_and_relse; + } if (tcp_v4_inbound_md5_hash(sk, skb, dif, sdif)) goto discard_and_relse; @@ -2166,6 +2170,7 @@ int tcp_v4_rcv(struct sk_buff *skb) do_time_wait: if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { + drop_reason = SKB_DROP_REASON_XFRM_POLICY; inet_twsk_put(inet_twsk(sk)); goto discard_it; } From c0e3154d9c889e1aa1af098f40301395f2e33d8a Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sun, 20 Feb 2022 15:06:31 +0800 Subject: [PATCH 3/9] net: tcp: use kfree_skb_reason() for tcp_v6_rcv() Replace kfree_skb() used in tcp_v6_rcv() with kfree_skb_reason(). Reviewed-by: Mengen Sun Reviewed-by: Hao Peng Signed-off-by: Menglong Dong Reviewed-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: David S. Miller --- net/ipv6/tcp_ipv6.c | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 0c648bf07f39..0aa17073df1a 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1627,6 +1627,7 @@ static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr, INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) { + enum skb_drop_reason drop_reason; int sdif = inet6_sdif(skb); int dif = inet6_iif(skb); const struct tcphdr *th; @@ -1636,6 +1637,7 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) int ret; struct net *net = dev_net(skb->dev); + drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; if (skb->pkt_type != PACKET_HOST) goto discard_it; @@ -1649,8 +1651,10 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) th = (const struct tcphdr *)skb->data; - if (unlikely(th->doff < sizeof(struct tcphdr)/4)) + if (unlikely(th->doff < sizeof(struct tcphdr) / 4)) { + drop_reason = SKB_DROP_REASON_PKT_TOO_SMALL; goto bad_packet; + } if (!pskb_may_pull(skb, th->doff*4)) goto discard_it; @@ -1706,6 +1710,8 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) hdr = ipv6_hdr(skb); tcp_v6_fill_cb(skb, hdr, th); nsk = tcp_check_req(sk, skb, req, false, &req_stolen); + } else { + drop_reason = SKB_DROP_REASON_SOCKET_FILTER; } if (!nsk) { reqsk_put(req); @@ -1741,14 +1747,18 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) } } - if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) + if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) { + drop_reason = SKB_DROP_REASON_XFRM_POLICY; goto discard_and_relse; + } if (tcp_v6_inbound_md5_hash(sk, skb, dif, sdif)) goto discard_and_relse; - if (tcp_filter(sk, skb)) + if (tcp_filter(sk, skb)) { + drop_reason = SKB_DROP_REASON_SOCKET_FILTER; goto discard_and_relse; + } th = (const struct tcphdr *)skb->data; hdr = ipv6_hdr(skb); tcp_v6_fill_cb(skb, hdr, th); @@ -1779,6 +1789,7 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) return ret ? -1 : 0; no_tcp_socket: + drop_reason = SKB_DROP_REASON_NO_SOCKET; if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard_it; @@ -1786,6 +1797,7 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) if (tcp_checksum_complete(skb)) { csum_error: + drop_reason = SKB_DROP_REASON_TCP_CSUM; trace_tcp_bad_csum(skb); __TCP_INC_STATS(net, TCP_MIB_CSUMERRORS); bad_packet: @@ -1795,7 +1807,7 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) } discard_it: - kfree_skb(skb); + kfree_skb_reason(skb, drop_reason); return 0; discard_and_relse: @@ -1806,6 +1818,7 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) do_time_wait: if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { + drop_reason = SKB_DROP_REASON_XFRM_POLICY; inet_twsk_put(inet_twsk(sk)); goto discard_it; } From 643b622b51f1f0015e0a80f90b4ef9032e6ddb1b Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sun, 20 Feb 2022 15:06:32 +0800 Subject: [PATCH 4/9] net: tcp: add skb drop reasons to tcp_v{4,6}_inbound_md5_hash() Pass the address of drop reason to tcp_v4_inbound_md5_hash() and tcp_v6_inbound_md5_hash() to store the reasons for skb drops when this function fails. Therefore, the drop reason can be passed to kfree_skb_reason() when the skb needs to be freed. Following drop reasons are added: SKB_DROP_REASON_TCP_MD5NOTFOUND SKB_DROP_REASON_TCP_MD5UNEXPECTED SKB_DROP_REASON_TCP_MD5FAILURE SKB_DROP_REASON_TCP_MD5* above correspond to LINUX_MIB_TCPMD5* Reviewed-by: Mengen Sun Reviewed-by: Hao Peng Signed-off-by: Menglong Dong Reviewed-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/skbuff.h | 12 ++++++++++++ include/trace/events/skb.h | 4 ++++ net/ipv4/tcp_ipv4.c | 13 +++++++++---- net/ipv6/tcp_ipv6.c | 11 ++++++++--- 4 files changed, 33 insertions(+), 7 deletions(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a5adbf6b51e8..46678eb587ff 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -346,6 +346,18 @@ enum skb_drop_reason { * udp packet drop out of * udp_memory_allocated. */ + SKB_DROP_REASON_TCP_MD5NOTFOUND, /* no MD5 hash and one + * expected, corresponding + * to LINUX_MIB_TCPMD5NOTFOUND + */ + SKB_DROP_REASON_TCP_MD5UNEXPECTED, /* MD5 hash and we're not + * expecting one, corresponding + * to LINUX_MIB_TCPMD5UNEXPECTED + */ + SKB_DROP_REASON_TCP_MD5FAILURE, /* MD5 hash and its wrong, + * corresponding to + * LINUX_MIB_TCPMD5FAILURE + */ SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index cfcfd26399f7..46c06b0be850 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -27,6 +27,10 @@ EM(SKB_DROP_REASON_IP_NOPROTO, IP_NOPROTO) \ EM(SKB_DROP_REASON_SOCKET_RCVBUFF, SOCKET_RCVBUFF) \ EM(SKB_DROP_REASON_PROTO_MEM, PROTO_MEM) \ + EM(SKB_DROP_REASON_TCP_MD5NOTFOUND, TCP_MD5NOTFOUND) \ + EM(SKB_DROP_REASON_TCP_MD5UNEXPECTED, \ + TCP_MD5UNEXPECTED) \ + EM(SKB_DROP_REASON_TCP_MD5FAILURE, TCP_MD5FAILURE) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a3beab01e9a7..d3c417119057 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1412,7 +1412,8 @@ EXPORT_SYMBOL(tcp_v4_md5_hash_skb); /* Called with rcu_read_lock() */ static bool tcp_v4_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, - int dif, int sdif) + int dif, int sdif, + enum skb_drop_reason *reason) { #ifdef CONFIG_TCP_MD5SIG /* @@ -1445,11 +1446,13 @@ static bool tcp_v4_inbound_md5_hash(const struct sock *sk, return false; if (hash_expected && !hash_location) { + *reason = SKB_DROP_REASON_TCP_MD5NOTFOUND; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND); return true; } if (!hash_expected && hash_location) { + *reason = SKB_DROP_REASON_TCP_MD5UNEXPECTED; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED); return true; } @@ -1462,6 +1465,7 @@ static bool tcp_v4_inbound_md5_hash(const struct sock *sk, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) { + *reason = SKB_DROP_REASON_TCP_MD5FAILURE; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE); net_info_ratelimited("MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s L3 index %d\n", &iph->saddr, ntohs(th->source), @@ -1971,13 +1975,13 @@ static void tcp_v4_fill_cb(struct sk_buff *skb, const struct iphdr *iph, int tcp_v4_rcv(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); + enum skb_drop_reason drop_reason; int sdif = inet_sdif(skb); int dif = inet_iif(skb); const struct iphdr *iph; const struct tcphdr *th; bool refcounted; struct sock *sk; - int drop_reason; int ret; drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; @@ -2025,7 +2029,8 @@ int tcp_v4_rcv(struct sk_buff *skb) struct sock *nsk; sk = req->rsk_listener; - if (unlikely(tcp_v4_inbound_md5_hash(sk, skb, dif, sdif))) { + if (unlikely(tcp_v4_inbound_md5_hash(sk, skb, dif, sdif, + &drop_reason))) { sk_drops_add(sk, skb); reqsk_put(req); goto discard_it; @@ -2099,7 +2104,7 @@ int tcp_v4_rcv(struct sk_buff *skb) goto discard_and_relse; } - if (tcp_v4_inbound_md5_hash(sk, skb, dif, sdif)) + if (tcp_v4_inbound_md5_hash(sk, skb, dif, sdif, &drop_reason)) goto discard_and_relse; nf_reset_ct(skb); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 0aa17073df1a..1262b790b146 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -775,7 +775,8 @@ static int tcp_v6_md5_hash_skb(char *md5_hash, static bool tcp_v6_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, - int dif, int sdif) + int dif, int sdif, + enum skb_drop_reason *reason) { #ifdef CONFIG_TCP_MD5SIG const __u8 *hash_location = NULL; @@ -798,11 +799,13 @@ static bool tcp_v6_inbound_md5_hash(const struct sock *sk, return false; if (hash_expected && !hash_location) { + *reason = SKB_DROP_REASON_TCP_MD5NOTFOUND; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND); return true; } if (!hash_expected && hash_location) { + *reason = SKB_DROP_REASON_TCP_MD5UNEXPECTED; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED); return true; } @@ -813,6 +816,7 @@ static bool tcp_v6_inbound_md5_hash(const struct sock *sk, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) { + *reason = SKB_DROP_REASON_TCP_MD5FAILURE; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE); net_info_ratelimited("MD5 Hash %s for [%pI6c]:%u->[%pI6c]:%u L3 index %d\n", genhash ? "failed" : "mismatch", @@ -1681,7 +1685,8 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) struct sock *nsk; sk = req->rsk_listener; - if (tcp_v6_inbound_md5_hash(sk, skb, dif, sdif)) { + if (tcp_v6_inbound_md5_hash(sk, skb, dif, sdif, + &drop_reason)) { sk_drops_add(sk, skb); reqsk_put(req); goto discard_it; @@ -1752,7 +1757,7 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) goto discard_and_relse; } - if (tcp_v6_inbound_md5_hash(sk, skb, dif, sdif)) + if (tcp_v6_inbound_md5_hash(sk, skb, dif, sdif, &drop_reason)) goto discard_and_relse; if (tcp_filter(sk, skb)) { From 7a26dc9e7b43f5a24c4b843713e728582adf1c38 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sun, 20 Feb 2022 15:06:33 +0800 Subject: [PATCH 5/9] net: tcp: add skb drop reasons to tcp_add_backlog() Pass the address of drop_reason to tcp_add_backlog() to store the reasons for skb drops when fails. Following drop reasons are introduced: SKB_DROP_REASON_SOCKET_BACKLOG Reviewed-by: Mengen Sun Reviewed-by: Hao Peng Signed-off-by: Menglong Dong Reviewed-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 ++++ include/net/tcp.h | 3 ++- include/trace/events/skb.h | 1 + net/ipv4/tcp_ipv4.c | 7 +++++-- net/ipv6/tcp_ipv6.c | 2 +- 5 files changed, 13 insertions(+), 4 deletions(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 46678eb587ff..f7f33c79945b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -358,6 +358,10 @@ enum skb_drop_reason { * corresponding to * LINUX_MIB_TCPMD5FAILURE */ + SKB_DROP_REASON_SOCKET_BACKLOG, /* failed to add skb to socket + * backlog (see + * LINUX_MIB_TCPBACKLOGDROP) + */ SKB_DROP_REASON_MAX, }; diff --git a/include/net/tcp.h b/include/net/tcp.h index eff2487d972d..04f4650e0ff0 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1367,7 +1367,8 @@ static inline bool tcp_checksum_complete(struct sk_buff *skb) __skb_checksum_complete(skb); } -bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb); +bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, + enum skb_drop_reason *reason); #ifdef CONFIG_INET void __sk_defer_free_flush(struct sock *sk); diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 46c06b0be850..bfccd77e9071 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -31,6 +31,7 @@ EM(SKB_DROP_REASON_TCP_MD5UNEXPECTED, \ TCP_MD5UNEXPECTED) \ EM(SKB_DROP_REASON_TCP_MD5FAILURE, TCP_MD5FAILURE) \ + EM(SKB_DROP_REASON_SOCKET_BACKLOG, SOCKET_BACKLOG) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index d3c417119057..cbca8637ba2f 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1811,7 +1811,8 @@ int tcp_v4_early_demux(struct sk_buff *skb) return 0; } -bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb) +bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, + enum skb_drop_reason *reason) { u32 limit, tail_gso_size, tail_gso_segs; struct skb_shared_info *shinfo; @@ -1837,6 +1838,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb) if (unlikely(tcp_checksum_complete(skb))) { bh_unlock_sock(sk); trace_tcp_bad_csum(skb); + *reason = SKB_DROP_REASON_TCP_CSUM; __TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); __TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); return true; @@ -1925,6 +1927,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb) if (unlikely(sk_add_backlog(sk, skb, limit))) { bh_unlock_sock(sk); + *reason = SKB_DROP_REASON_SOCKET_BACKLOG; __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPBACKLOGDROP); return true; } @@ -2133,7 +2136,7 @@ int tcp_v4_rcv(struct sk_buff *skb) if (!sock_owned_by_user(sk)) { ret = tcp_v4_do_rcv(sk, skb); } else { - if (tcp_add_backlog(sk, skb)) + if (tcp_add_backlog(sk, skb, &drop_reason)) goto discard_and_relse; } bh_unlock_sock(sk); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 1262b790b146..abf0ad547858 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1784,7 +1784,7 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb) if (!sock_owned_by_user(sk)) { ret = tcp_v6_do_rcv(sk, skb); } else { - if (tcp_add_backlog(sk, skb)) + if (tcp_add_backlog(sk, skb, &drop_reason)) goto discard_and_relse; } bh_unlock_sock(sk); From 8eba65fa5f06519042b98564089b942d795e3f8d Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sun, 20 Feb 2022 15:06:34 +0800 Subject: [PATCH 6/9] net: tcp: use kfree_skb_reason() for tcp_v{4,6}_do_rcv() Replace kfree_skb() used in tcp_v4_do_rcv() and tcp_v6_do_rcv() with kfree_skb_reason(). Reviewed-by: Mengen Sun Reviewed-by: Hao Peng Signed-off-by: Menglong Dong Reviewed-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 5 ++++- net/ipv6/tcp_ipv6.c | 5 ++++- 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index cbca8637ba2f..d42824aedc36 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1708,6 +1708,7 @@ INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *, */ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) { + enum skb_drop_reason reason; struct sock *rsk; if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ @@ -1730,6 +1731,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) return 0; } + reason = SKB_DROP_REASON_NOT_SPECIFIED; if (tcp_checksum_complete(skb)) goto csum_err; @@ -1757,7 +1759,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) reset: tcp_v4_send_reset(rsk, skb); discard: - kfree_skb(skb); + kfree_skb_reason(skb, reason); /* Be careful here. If this function gets more complicated and * gcc suffers from register pressure on the x86, sk (in %ebx) * might be destroyed here. This current version compiles correctly, @@ -1766,6 +1768,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) return 0; csum_err: + reason = SKB_DROP_REASON_TCP_CSUM; trace_tcp_bad_csum(skb); TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index abf0ad547858..91cee8010285 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1476,6 +1476,7 @@ int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) { struct ipv6_pinfo *np = tcp_inet6_sk(sk); struct sk_buff *opt_skb = NULL; + enum skb_drop_reason reason; struct tcp_sock *tp; /* Imagine: socket is IPv6. IPv4 packet arrives, @@ -1510,6 +1511,7 @@ int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) if (np->rxopt.all) opt_skb = skb_clone(skb, sk_gfp_mask(sk, GFP_ATOMIC)); + reason = SKB_DROP_REASON_NOT_SPECIFIED; if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ struct dst_entry *dst; @@ -1563,9 +1565,10 @@ int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) discard: if (opt_skb) __kfree_skb(opt_skb); - kfree_skb(skb); + kfree_skb_reason(skb, reason); return 0; csum_err: + reason = SKB_DROP_REASON_TCP_CSUM; trace_tcp_bad_csum(skb); TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); From 2a968ef60e1fac4e694d9f60ce19a3b66b40e8c3 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sun, 20 Feb 2022 15:06:35 +0800 Subject: [PATCH 7/9] net: tcp: use tcp_drop_reason() for tcp_rcv_established() Replace tcp_drop() used in tcp_rcv_established() with tcp_drop_reason(). Following drop reasons are added: SKB_DROP_REASON_TCP_FLAGS Reviewed-by: Mengen Sun Reviewed-by: Hao Peng Signed-off-by: Menglong Dong Reviewed-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + include/trace/events/skb.h | 1 + net/ipv4/tcp_input.c | 9 +++++++-- 3 files changed, 9 insertions(+), 2 deletions(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f7f33c79945b..671db9f49efe 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -362,6 +362,7 @@ enum skb_drop_reason { * backlog (see * LINUX_MIB_TCPBACKLOGDROP) */ + SKB_DROP_REASON_TCP_FLAGS, /* TCP flags invalid */ SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index bfccd77e9071..d332e7313a61 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -32,6 +32,7 @@ TCP_MD5UNEXPECTED) \ EM(SKB_DROP_REASON_TCP_MD5FAILURE, TCP_MD5FAILURE) \ EM(SKB_DROP_REASON_SOCKET_BACKLOG, SOCKET_BACKLOG) \ + EM(SKB_DROP_REASON_TCP_FLAGS, TCP_FLAGS) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 0f41fdfd8c27..2d8495a62bc4 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5787,6 +5787,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, */ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb) { + enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED; const struct tcphdr *th = (const struct tcphdr *)skb->data; struct tcp_sock *tp = tcp_sk(sk); unsigned int len = skb->len; @@ -5875,6 +5876,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb) tp->rcv_rtt_last_tsecr = tp->rx_opt.rcv_tsecr; return; } else { /* Header too small */ + reason = SKB_DROP_REASON_PKT_TOO_SMALL; TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); goto discard; } @@ -5930,8 +5932,10 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb) if (len < (th->doff << 2) || tcp_checksum_complete(skb)) goto csum_error; - if (!th->ack && !th->rst && !th->syn) + if (!th->ack && !th->rst && !th->syn) { + reason = SKB_DROP_REASON_TCP_FLAGS; goto discard; + } /* * Standard slow path. @@ -5957,12 +5961,13 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb) return; csum_error: + reason = SKB_DROP_REASON_TCP_CSUM; trace_tcp_bad_csum(skb); TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); discard: - tcp_drop(sk, skb); + tcp_drop_reason(sk, skb, reason); } EXPORT_SYMBOL(tcp_rcv_established); From a7ec381049c0d1f03e342063d75f5c3b314d0ec2 Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sun, 20 Feb 2022 15:06:36 +0800 Subject: [PATCH 8/9] net: tcp: use tcp_drop_reason() for tcp_data_queue() Replace tcp_drop() used in tcp_data_queue() with tcp_drop_reason(). Following drop reasons are introduced: SKB_DROP_REASON_TCP_ZEROWINDOW SKB_DROP_REASON_TCP_OLD_DATA SKB_DROP_REASON_TCP_OVERWINDOW SKB_DROP_REASON_TCP_OLD_DATA is used for the case that end_seq of skb less than the left edges of receive window. (Maybe there is a better name?) Reviewed-by: Mengen Sun Reviewed-by: Hao Peng Signed-off-by: Menglong Dong Reviewed-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/skbuff.h | 13 +++++++++++++ include/trace/events/skb.h | 3 +++ net/ipv4/tcp_input.c | 13 +++++++++++-- 3 files changed, 27 insertions(+), 2 deletions(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 671db9f49efe..554ef2c848ee 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -363,6 +363,19 @@ enum skb_drop_reason { * LINUX_MIB_TCPBACKLOGDROP) */ SKB_DROP_REASON_TCP_FLAGS, /* TCP flags invalid */ + SKB_DROP_REASON_TCP_ZEROWINDOW, /* TCP receive window size is zero, + * see LINUX_MIB_TCPZEROWINDOWDROP + */ + SKB_DROP_REASON_TCP_OLD_DATA, /* the TCP data reveived is already + * received before (spurious retrans + * may happened), see + * LINUX_MIB_DELAYEDACKLOST + */ + SKB_DROP_REASON_TCP_OVERWINDOW, /* the TCP data is out of window, + * the seq of the first byte exceed + * the right edges of receive + * window + */ SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index d332e7313a61..cc1c8f7eaf72 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -33,6 +33,9 @@ EM(SKB_DROP_REASON_TCP_MD5FAILURE, TCP_MD5FAILURE) \ EM(SKB_DROP_REASON_SOCKET_BACKLOG, SOCKET_BACKLOG) \ EM(SKB_DROP_REASON_TCP_FLAGS, TCP_FLAGS) \ + EM(SKB_DROP_REASON_TCP_ZEROWINDOW, TCP_ZEROWINDOW) \ + EM(SKB_DROP_REASON_TCP_OLD_DATA, TCP_OLD_DATA) \ + EM(SKB_DROP_REASON_TCP_OVERWINDOW, TCP_OVERWINDOW) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2d8495a62bc4..041c778fd0b5 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4988,6 +4988,7 @@ void tcp_data_ready(struct sock *sk) static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); + enum skb_drop_reason reason; bool fragstolen; int eaten; @@ -5006,6 +5007,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) skb_dst_drop(skb); __skb_pull(skb, tcp_hdr(skb)->doff * 4); + reason = SKB_DROP_REASON_NOT_SPECIFIED; tp->rx_opt.dsack = 0; /* Queue data for delivery to the user. @@ -5014,6 +5016,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) */ if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt) { if (tcp_receive_window(tp) == 0) { + reason = SKB_DROP_REASON_TCP_ZEROWINDOW; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPZEROWINDOWDROP); goto out_of_window; } @@ -5023,6 +5026,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) if (skb_queue_len(&sk->sk_receive_queue) == 0) sk_forced_mem_schedule(sk, skb->truesize); else if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) { + reason = SKB_DROP_REASON_PROTO_MEM; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP); sk->sk_data_ready(sk); goto drop; @@ -5059,6 +5063,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) if (!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) { tcp_rcv_spurious_retrans(sk, skb); /* A retransmit, 2nd most common case. Force an immediate ack. */ + reason = SKB_DROP_REASON_TCP_OLD_DATA; NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST); tcp_dsack_set(sk, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq); @@ -5066,13 +5071,16 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS); inet_csk_schedule_ack(sk); drop: - tcp_drop(sk, skb); + tcp_drop_reason(sk, skb, reason); return; } /* Out of window. F.e. zero window probe. */ - if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt + tcp_receive_window(tp))) + if (!before(TCP_SKB_CB(skb)->seq, + tp->rcv_nxt + tcp_receive_window(tp))) { + reason = SKB_DROP_REASON_TCP_OVERWINDOW; goto out_of_window; + } if (before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) { /* Partial packet, seq < rcv_next < end_seq */ @@ -5082,6 +5090,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) * remembering D-SACK for its head made in previous line. */ if (!tcp_receive_window(tp)) { + reason = SKB_DROP_REASON_TCP_ZEROWINDOW; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPZEROWINDOWDROP); goto out_of_window; } From d25e481be0c519d1a458b14191dc8c2a8bb3e24a Mon Sep 17 00:00:00 2001 From: Menglong Dong Date: Sun, 20 Feb 2022 15:06:37 +0800 Subject: [PATCH 9/9] net: tcp: use tcp_drop_reason() for tcp_data_queue_ofo() Replace tcp_drop() used in tcp_data_queue_ofo with tcp_drop_reason(). Following drop reasons are introduced: SKB_DROP_REASON_TCP_OFOMERGE Reviewed-by: Mengen Sun Reviewed-by: Hao Peng Signed-off-by: Menglong Dong Reviewed-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 ++++ include/trace/events/skb.h | 1 + net/ipv4/tcp_input.c | 10 ++++++---- 3 files changed, 11 insertions(+), 4 deletions(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 554ef2c848ee..a3e90efe6586 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -376,6 +376,10 @@ enum skb_drop_reason { * the right edges of receive * window */ + SKB_DROP_REASON_TCP_OFOMERGE, /* the data of skb is already in + * the ofo queue, corresponding to + * LINUX_MIB_TCPOFOMERGE + */ SKB_DROP_REASON_MAX, }; diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index cc1c8f7eaf72..2ab7193313aa 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -36,6 +36,7 @@ EM(SKB_DROP_REASON_TCP_ZEROWINDOW, TCP_ZEROWINDOW) \ EM(SKB_DROP_REASON_TCP_OLD_DATA, TCP_OLD_DATA) \ EM(SKB_DROP_REASON_TCP_OVERWINDOW, TCP_OVERWINDOW) \ + EM(SKB_DROP_REASON_TCP_OFOMERGE, TCP_OFOMERGE) \ EMe(SKB_DROP_REASON_MAX, MAX) #undef EM diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 041c778fd0b5..2088f93fa37b 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4779,7 +4779,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFODROP); sk->sk_data_ready(sk); - tcp_drop(sk, skb); + tcp_drop_reason(sk, skb, SKB_DROP_REASON_PROTO_MEM); return; } @@ -4842,7 +4842,8 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) /* All the bits are present. Drop. */ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOMERGE); - tcp_drop(sk, skb); + tcp_drop_reason(sk, skb, + SKB_DROP_REASON_TCP_OFOMERGE); skb = NULL; tcp_dsack_set(sk, seq, end_seq); goto add_sack; @@ -4861,7 +4862,8 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) TCP_SKB_CB(skb1)->end_seq); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOMERGE); - tcp_drop(sk, skb1); + tcp_drop_reason(sk, skb1, + SKB_DROP_REASON_TCP_OFOMERGE); goto merge_right; } } else if (tcp_ooo_try_coalesce(sk, skb1, @@ -4889,7 +4891,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) tcp_dsack_extend(sk, TCP_SKB_CB(skb1)->seq, TCP_SKB_CB(skb1)->end_seq); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOMERGE); - tcp_drop(sk, skb1); + tcp_drop_reason(sk, skb1, SKB_DROP_REASON_TCP_OFOMERGE); } /* If there is no skb after us, we are the last_skb ! */ if (!skb1)