diff options
Diffstat (limited to 'net/ipv4')
67 files changed, 2649 insertions, 854 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 974de4d20f25..f96bd489b362 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -180,8 +180,8 @@ config NET_IPIP config NET_IPGRE_DEMUX tristate "IP: GRE demultiplexer" help - This is helper module to demultiplex GRE packets on GRE version field criteria. - Required by ip_gre and pptp modules. + This is helper module to demultiplex GRE packets on GRE version field criteria. + Required by ip_gre and pptp modules. config NET_IP_TUNNEL tristate @@ -378,6 +378,17 @@ config INET_ESP_OFFLOAD If unsure, say N. +config INET_ESPINTCP + bool "IP: ESP in TCP encapsulation (RFC 8229)" + depends on XFRM && INET_ESP + select STREAM_PARSER + select NET_SOCK_MSG + help + Support for RFC 8229 encapsulation of ESP and IKE over + TCP/IPv4 sockets. + + If unsure, say N. + config INET_IPCOMP tristate "IP: IPComp transformation" select INET_XFRM_TUNNEL @@ -459,200 +470,200 @@ config TCP_CONG_BIC tristate "Binary Increase Congestion (BIC) control" default m ---help--- - BIC-TCP is a sender-side only change that ensures a linear RTT - fairness under large windows while offering both scalability and - bounded TCP-friendliness. The protocol combines two schemes - called additive increase and binary search increase. When the - congestion window is large, additive increase with a large - increment ensures linear RTT fairness as well as good - scalability. Under small congestion windows, binary search - increase provides TCP friendliness. - See http://www.csc.ncsu.edu/faculty/rhee/export/bitcp/ + BIC-TCP is a sender-side only change that ensures a linear RTT + fairness under large windows while offering both scalability and + bounded TCP-friendliness. The protocol combines two schemes + called additive increase and binary search increase. When the + congestion window is large, additive increase with a large + increment ensures linear RTT fairness as well as good + scalability. Under small congestion windows, binary search + increase provides TCP friendliness. + See http://www.csc.ncsu.edu/faculty/rhee/export/bitcp/ config TCP_CONG_CUBIC tristate "CUBIC TCP" default y ---help--- - This is version 2.0 of BIC-TCP which uses a cubic growth function - among other techniques. - See http://www.csc.ncsu.edu/faculty/rhee/export/bitcp/cubic-paper.pdf + This is version 2.0 of BIC-TCP which uses a cubic growth function + among other techniques. + See http://www.csc.ncsu.edu/faculty/rhee/export/bitcp/cubic-paper.pdf config TCP_CONG_WESTWOOD tristate "TCP Westwood+" default m ---help--- - TCP Westwood+ is a sender-side only modification of the TCP Reno - protocol stack that optimizes the performance of TCP congestion - control. It is based on end-to-end bandwidth estimation to set - congestion window and slow start threshold after a congestion - episode. Using this estimation, TCP Westwood+ adaptively sets a - slow start threshold and a congestion window which takes into - account the bandwidth used at the time congestion is experienced. - TCP Westwood+ significantly increases fairness wrt TCP Reno in - wired networks and throughput over wireless links. + TCP Westwood+ is a sender-side only modification of the TCP Reno + protocol stack that optimizes the performance of TCP congestion + control. It is based on end-to-end bandwidth estimation to set + congestion window and slow start threshold after a congestion + episode. Using this estimation, TCP Westwood+ adaptively sets a + slow start threshold and a congestion window which takes into + account the bandwidth used at the time congestion is experienced. + TCP Westwood+ significantly increases fairness wrt TCP Reno in + wired networks and throughput over wireless links. config TCP_CONG_HTCP - tristate "H-TCP" - default m + tristate "H-TCP" + default m ---help--- - H-TCP is a send-side only modifications of the TCP Reno - protocol stack that optimizes the performance of TCP - congestion control for high speed network links. It uses a - modeswitch to change the alpha and beta parameters of TCP Reno - based on network conditions and in a way so as to be fair with - other Reno and H-TCP flows. + H-TCP is a send-side only modifications of the TCP Reno + protocol stack that optimizes the performance of TCP + congestion control for high speed network links. It uses a + modeswitch to change the alpha and beta parameters of TCP Reno + based on network conditions and in a way so as to be fair with + other Reno and H-TCP flows. config TCP_CONG_HSTCP tristate "High Speed TCP" default n ---help--- - Sally Floyd's High Speed TCP (RFC 3649) congestion control. - A modification to TCP's congestion control mechanism for use - with large congestion windows. A table indicates how much to - increase the congestion window by when an ACK is received. - For more detail see http://www.icir.org/floyd/hstcp.html + Sally Floyd's High Speed TCP (RFC 3649) congestion control. + A modification to TCP's congestion control mechanism for use + with large congestion windows. A table indicates how much to + increase the congestion window by when an ACK is received. + For more detail see http://www.icir.org/floyd/hstcp.html config TCP_CONG_HYBLA tristate "TCP-Hybla congestion control algorithm" default n ---help--- - TCP-Hybla is a sender-side only change that eliminates penalization of - long-RTT, large-bandwidth connections, like when satellite legs are - involved, especially when sharing a common bottleneck with normal - terrestrial connections. + TCP-Hybla is a sender-side only change that eliminates penalization of + long-RTT, large-bandwidth connections, like when satellite legs are + involved, especially when sharing a common bottleneck with normal + terrestrial connections. config TCP_CONG_VEGAS tristate "TCP Vegas" default n ---help--- - TCP Vegas is a sender-side only change to TCP that anticipates - the onset of congestion by estimating the bandwidth. TCP Vegas - adjusts the sending rate by modifying the congestion - window. TCP Vegas should provide less packet loss, but it is - not as aggressive as TCP Reno. + TCP Vegas is a sender-side only change to TCP that anticipates + the onset of congestion by estimating the bandwidth. TCP Vegas + adjusts the sending rate by modifying the congestion + window. TCP Vegas should provide less packet loss, but it is + not as aggressive as TCP Reno. config TCP_CONG_NV - tristate "TCP NV" - default n - ---help--- - TCP NV is a follow up to TCP Vegas. It has been modified to deal with - 10G networks, measurement noise introduced by LRO, GRO and interrupt - coalescence. In addition, it will decrease its cwnd multiplicatively - instead of linearly. + tristate "TCP NV" + default n + ---help--- + TCP NV is a follow up to TCP Vegas. It has been modified to deal with + 10G networks, measurement noise introduced by LRO, GRO and interrupt + coalescence. In addition, it will decrease its cwnd multiplicatively + instead of linearly. - Note that in general congestion avoidance (cwnd decreased when # packets - queued grows) cannot coexist with congestion control (cwnd decreased only - when there is packet loss) due to fairness issues. One scenario when they - can coexist safely is when the CA flows have RTTs << CC flows RTTs. + Note that in general congestion avoidance (cwnd decreased when # packets + queued grows) cannot coexist with congestion control (cwnd decreased only + when there is packet loss) due to fairness issues. One scenario when they + can coexist safely is when the CA flows have RTTs << CC flows RTTs. - For further details see http://www.brakmo.org/networking/tcp-nv/ + For further details see http://www.brakmo.org/networking/tcp-nv/ config TCP_CONG_SCALABLE tristate "Scalable TCP" default n ---help--- - Scalable TCP is a sender-side only change to TCP which uses a - MIMD congestion control algorithm which has some nice scaling - properties, though is known to have fairness issues. - See http://www.deneholme.net/tom/scalable/ + Scalable TCP is a sender-side only change to TCP which uses a + MIMD congestion control algorithm which has some nice scaling + properties, though is known to have fairness issues. + See http://www.deneholme.net/tom/scalable/ config TCP_CONG_LP tristate "TCP Low Priority" default n ---help--- - TCP Low Priority (TCP-LP), a distributed algorithm whose goal is - to utilize only the excess network bandwidth as compared to the - ``fair share`` of bandwidth as targeted by TCP. - See http://www-ece.rice.edu/networks/TCP-LP/ + TCP Low Priority (TCP-LP), a distributed algorithm whose goal is + to utilize only the excess network bandwidth as compared to the + ``fair share`` of bandwidth as targeted by TCP. + See http://www-ece.rice.edu/networks/TCP-LP/ config TCP_CONG_VENO tristate "TCP Veno" default n ---help--- - TCP Veno is a sender-side only enhancement of TCP to obtain better - throughput over wireless networks. TCP Veno makes use of state - distinguishing to circumvent the difficult judgment of the packet loss - type. TCP Veno cuts down less congestion window in response to random - loss packets. - See <http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=1177186> + TCP Veno is a sender-side only enhancement of TCP to obtain better + throughput over wireless networks. TCP Veno makes use of state + distinguishing to circumvent the difficult judgment of the packet loss + type. TCP Veno cuts down less congestion window in response to random + loss packets. + See <http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=1177186> config TCP_CONG_YEAH tristate "YeAH TCP" select TCP_CONG_VEGAS default n ---help--- - YeAH-TCP is a sender-side high-speed enabled TCP congestion control - algorithm, which uses a mixed loss/delay approach to compute the - congestion window. It's design goals target high efficiency, - internal, RTT and Reno fairness, resilience to link loss while - keeping network elements load as low as possible. + YeAH-TCP is a sender-side high-speed enabled TCP congestion control + algorithm, which uses a mixed loss/delay approach to compute the + congestion window. It's design goals target high efficiency, + internal, RTT and Reno fairness, resilience to link loss while + keeping network elements load as low as possible. - For further details look here: - http://wil.cs.caltech.edu/pfldnet2007/paper/YeAH_TCP.pdf + For further details look here: + http://wil.cs.caltech.edu/pfldnet2007/paper/YeAH_TCP.pdf config TCP_CONG_ILLINOIS tristate "TCP Illinois" default n ---help--- - TCP-Illinois is a sender-side modification of TCP Reno for - high speed long delay links. It uses round-trip-time to - adjust the alpha and beta parameters to achieve a higher average - throughput and maintain fairness. + TCP-Illinois is a sender-side modification of TCP Reno for + high speed long delay links. It uses round-trip-time to + adjust the alpha and beta parameters to achieve a higher average + throughput and maintain fairness. - For further details see: - http://www.ews.uiuc.edu/~shaoliu/tcpillinois/index.html + For further details see: + http://www.ews.uiuc.edu/~shaoliu/tcpillinois/index.html config TCP_CONG_DCTCP tristate "DataCenter TCP (DCTCP)" default n ---help--- - DCTCP leverages Explicit Congestion Notification (ECN) in the network to - provide multi-bit feedback to the end hosts. It is designed to provide: + DCTCP leverages Explicit Congestion Notification (ECN) in the network to + provide multi-bit feedback to the end hosts. It is designed to provide: - - High burst tolerance (incast due to partition/aggregate), - - Low latency (short flows, queries), - - High throughput (continuous data updates, large file transfers) with - commodity, shallow-buffered switches. + - High burst tolerance (incast due to partition/aggregate), + - Low latency (short flows, queries), + - High throughput (continuous data updates, large file transfers) with + commodity, shallow-buffered switches. - All switches in the data center network running DCTCP must support - ECN marking and be configured for marking when reaching defined switch - buffer thresholds. The default ECN marking threshold heuristic for - DCTCP on switches is 20 packets (30KB) at 1Gbps, and 65 packets - (~100KB) at 10Gbps, but might need further careful tweaking. + All switches in the data center network running DCTCP must support + ECN marking and be configured for marking when reaching defined switch + buffer thresholds. The default ECN marking threshold heuristic for + DCTCP on switches is 20 packets (30KB) at 1Gbps, and 65 packets + (~100KB) at 10Gbps, but might need further careful tweaking. - For further details see: - http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp-final.pdf + For further details see: + http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp-final.pdf config TCP_CONG_CDG tristate "CAIA Delay-Gradient (CDG)" default n ---help--- - CAIA Delay-Gradient (CDG) is a TCP congestion control that modifies - the TCP sender in order to: + CAIA Delay-Gradient (CDG) is a TCP congestion control that modifies + the TCP sender in order to: o Use the delay gradient as a congestion signal. o Back off with an average probability that is independent of the RTT. o Coexist with flows that use loss-based congestion control. o Tolerate packet loss unrelated to congestion. - For further details see: - D.A. Hayes and G. Armitage. "Revisiting TCP congestion control using - delay gradients." In Networking 2011. Preprint: http://goo.gl/No3vdg + For further details see: + D.A. Hayes and G. Armitage. "Revisiting TCP congestion control using + delay gradients." In Networking 2011. Preprint: http://goo.gl/No3vdg config TCP_CONG_BBR tristate "BBR TCP" default n ---help--- - BBR (Bottleneck Bandwidth and RTT) TCP congestion control aims to - maximize network utilization and minimize queues. It builds an explicit - model of the the bottleneck delivery rate and path round-trip - propagation delay. It tolerates packet loss and delay unrelated to - congestion. It can operate over LAN, WAN, cellular, wifi, or cable - modem links. It can coexist with flows that use loss-based congestion - control, and can operate with shallow buffers, deep buffers, - bufferbloat, policers, or AQM schemes that do not provide a delay - signal. It requires the fq ("Fair Queue") pacing packet scheduler. + BBR (Bottleneck Bandwidth and RTT) TCP congestion control aims to + maximize network utilization and minimize queues. It builds an explicit + model of the the bottleneck delivery rate and path round-trip + propagation delay. It tolerates packet loss and delay unrelated to + congestion. It can operate over LAN, WAN, cellular, wifi, or cable + modem links. It can coexist with flows that use loss-based congestion + control, and can operate with shallow buffers, deep buffers, + bufferbloat, policers, or AQM schemes that do not provide a delay + signal. It requires the fq ("Fair Queue") pacing packet scheduler. choice prompt "Default TCP congestion control" diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index d57ecfaf89d4..9d97bace13c8 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -65,3 +65,7 @@ obj-$(CONFIG_NETLABEL) += cipso_ipv4.o obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \ xfrm4_output.o xfrm4_protocol.o + +ifeq ($(CONFIG_BPF_JIT),y) +obj-$(CONFIG_BPF_SYSCALL) += bpf_tcp_ca.o +endif diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index ed2301ef872e..2fe295432c24 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -208,7 +208,7 @@ int inet_listen(struct socket *sock, int backlog) if (!((1 << old_state) & (TCPF_CLOSE | TCPF_LISTEN))) goto out; - sk->sk_max_ack_backlog = backlog; + WRITE_ONCE(sk->sk_max_ack_backlog, backlog); /* Really, if the socket is already in listen state * we can only allow the backlog to be adjusted. */ @@ -495,7 +495,7 @@ int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, snum = ntohs(addr->sin_port); err = -EACCES; - if (snum && snum < inet_prot_sock(net) && + if (snum && inet_port_requires_bind_service(net, snum) && !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE)) goto out; @@ -1845,13 +1845,8 @@ static __net_init int inet_init_net(struct net *net) return 0; } -static __net_exit void inet_exit_net(struct net *net) -{ -} - static __net_initdata struct pernet_operations af_inet_ops = { .init = inet_init_net, - .exit = inet_exit_net, }; static int __init init_inet_pernet_ops(void) diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c new file mode 100644 index 000000000000..574972bc7299 --- /dev/null +++ b/net/ipv4/bpf_tcp_ca.c @@ -0,0 +1,252 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ + +#include <linux/types.h> +#include <linux/bpf_verifier.h> +#include <linux/bpf.h> +#include <linux/btf.h> +#include <linux/filter.h> +#include <net/tcp.h> + +static u32 optional_ops[] = { + offsetof(struct tcp_congestion_ops, init), + offsetof(struct tcp_congestion_ops, release), + offsetof(struct tcp_congestion_ops, set_state), + offsetof(struct tcp_congestion_ops, cwnd_event), + offsetof(struct tcp_congestion_ops, in_ack_event), + offsetof(struct tcp_congestion_ops, pkts_acked), + offsetof(struct tcp_congestion_ops, min_tso_segs), + offsetof(struct tcp_congestion_ops, sndbuf_expand), + offsetof(struct tcp_congestion_ops, cong_control), +}; + +static u32 unsupported_ops[] = { + offsetof(struct tcp_congestion_ops, get_info), +}; + +static const struct btf_type *tcp_sock_type; +static u32 tcp_sock_id, sock_id; + +static int bpf_tcp_ca_init(struct btf *btf) +{ + s32 type_id; + + type_id = btf_find_by_name_kind(btf, "sock", BTF_KIND_STRUCT); + if (type_id < 0) + return -EINVAL; + sock_id = type_id; + + type_id = btf_find_by_name_kind(btf, "tcp_sock", BTF_KIND_STRUCT); + if (type_id < 0) + return -EINVAL; + tcp_sock_id = type_id; + tcp_sock_type = btf_type_by_id(btf, tcp_sock_id); + + return 0; +} + +static bool is_optional(u32 member_offset) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(optional_ops); i++) { + if (member_offset == optional_ops[i]) + return true; + } + + return false; +} + +static bool is_unsupported(u32 member_offset) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(unsupported_ops); i++) { + if (member_offset == unsupported_ops[i]) + return true; + } + + return false; +} + +extern struct btf *btf_vmlinux; + +static bool bpf_tcp_ca_is_valid_access(int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS) + return false; + if (type != BPF_READ) + return false; + if (off % size != 0) + return false; + + if (!btf_ctx_access(off, size, type, prog, info)) + return false; + + if (info->reg_type == PTR_TO_BTF_ID && info->btf_id == sock_id) + /* promote it to tcp_sock */ + info->btf_id = tcp_sock_id; + + return true; +} + +static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log, + const struct btf_type *t, int off, + int size, enum bpf_access_type atype, + u32 *next_btf_id) +{ + size_t end; + + if (atype == BPF_READ) + return btf_struct_access(log, t, off, size, atype, next_btf_id); + + if (t != tcp_sock_type) { + bpf_log(log, "only read is supported\n"); + return -EACCES; + } + + switch (off) { + case bpf_ctx_range(struct inet_connection_sock, icsk_ca_priv): + end = offsetofend(struct inet_connection_sock, icsk_ca_priv); + break; + case offsetof(struct inet_connection_sock, icsk_ack.pending): + end = offsetofend(struct inet_connection_sock, + icsk_ack.pending); + break; + case offsetof(struct tcp_sock, snd_cwnd): + end = offsetofend(struct tcp_sock, snd_cwnd); + break; + case offsetof(struct tcp_sock, snd_cwnd_cnt): + end = offsetofend(struct tcp_sock, snd_cwnd_cnt); + break; + case offsetof(struct tcp_sock, snd_ssthresh): + end = offsetofend(struct tcp_sock, snd_ssthresh); + break; + case offsetof(struct tcp_sock, ecn_flags): + end = offsetofend(struct tcp_sock, ecn_flags); + break; + default: + bpf_log(log, "no write support to tcp_sock at off %d\n", off); + return -EACCES; + } + + if (off + size > end) { + bpf_log(log, + "write access at off %d with size %d beyond the member of tcp_sock ended at %zu\n", + off, size, end); + return -EACCES; + } + + return NOT_INIT; +} + +BPF_CALL_2(bpf_tcp_send_ack, struct tcp_sock *, tp, u32, rcv_nxt) +{ + /* bpf_tcp_ca prog cannot have NULL tp */ + __tcp_send_ack((struct sock *)tp, rcv_nxt); + return 0; +} + +static const struct bpf_func_proto bpf_tcp_send_ack_proto = { + .func = bpf_tcp_send_ack, + .gpl_only = false, + /* In case we want to report error later */ + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg2_type = ARG_ANYTHING, + .btf_id = &tcp_sock_id, +}; + +static const struct bpf_func_proto * +bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id, + const struct bpf_prog *prog) +{ + switch (func_id) { + case BPF_FUNC_tcp_send_ack: + return &bpf_tcp_send_ack_proto; + default: + return bpf_base_func_proto(func_id); + } +} + +static const struct bpf_verifier_ops bpf_tcp_ca_verifier_ops = { + .get_func_proto = bpf_tcp_ca_get_func_proto, + .is_valid_access = bpf_tcp_ca_is_valid_access, + .btf_struct_access = bpf_tcp_ca_btf_struct_access, +}; + +static int bpf_tcp_ca_init_member(const struct btf_type *t, + const struct btf_member *member, + void *kdata, const void *udata) +{ + const struct tcp_congestion_ops *utcp_ca; + struct tcp_congestion_ops *tcp_ca; + size_t tcp_ca_name_len; + int prog_fd; + u32 moff; + + utcp_ca = (const struct tcp_congestion_ops *)udata; + tcp_ca = (struct tcp_congestion_ops *)kdata; + + moff = btf_member_bit_offset(t, member) / 8; + switch (moff) { + case offsetof(struct tcp_congestion_ops, flags): + if (utcp_ca->flags & ~TCP_CONG_MASK) + return -EINVAL; + tcp_ca->flags = utcp_ca->flags; + return 1; + case offsetof(struct tcp_congestion_ops, name): + tcp_ca_name_len = strnlen(utcp_ca->name, sizeof(utcp_ca->name)); + if (!tcp_ca_name_len || + tcp_ca_name_len == sizeof(utcp_ca->name)) + return -EINVAL; + if (tcp_ca_find(utcp_ca->name)) + return -EEXIST; + memcpy(tcp_ca->name, utcp_ca->name, sizeof(tcp_ca->name)); + return 1; + } + + if (!btf_type_resolve_func_ptr(btf_vmlinux, member->type, NULL)) + return 0; + + /* Ensure bpf_prog is provided for compulsory func ptr */ + prog_fd = (int)(*(unsigned long *)(udata + moff)); + if (!prog_fd && !is_optional(moff) && !is_unsupported(moff)) + return -EINVAL; + + return 0; +} + +static int bpf_tcp_ca_check_member(const struct btf_type *t, + const struct btf_member *member) +{ + if (is_unsupported(btf_member_bit_offset(t, member) / 8)) + return -ENOTSUPP; + return 0; +} + +static int bpf_tcp_ca_reg(void *kdata) +{ + return tcp_register_congestion_control(kdata); +} + +static void bpf_tcp_ca_unreg(void *kdata) +{ + tcp_unregister_congestion_control(kdata); +} + +/* Avoid sparse warning. It is only used in bpf_struct_ops.c. */ +extern struct bpf_struct_ops bpf_tcp_congestion_ops; + +struct bpf_struct_ops bpf_tcp_congestion_ops = { + .verifier_ops = &bpf_tcp_ca_verifier_ops, + .reg = bpf_tcp_ca_reg, + .unreg = bpf_tcp_ca_unreg, + .check_member = bpf_tcp_ca_check_member, + .init_member = bpf_tcp_ca_init_member, + .init = bpf_tcp_ca_init, + .name = "tcp_congestion_ops", +}; diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 7bd29e694603..4a8550c49202 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -15,6 +15,7 @@ #include <net/sock.h> #include <net/route.h> #include <net/tcp_states.h> +#include <net/sock_reuseport.h> int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { @@ -69,9 +70,10 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len } inet->inet_daddr = fl4->daddr; inet->inet_dport = usin->sin_port; + reuseport_has_conns(sk, true); sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); - inet->inet_id = jiffies; + inet->inet_id = prandom_u32(); sk_dst_set(sk, &rt->dst); err = 0; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index a4b5bd4d2c89..e4632bd2026d 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1496,11 +1496,6 @@ skip: } } -static bool inetdev_valid_mtu(unsigned int mtu) -{ - return mtu >= IPV4_MIN_MTU; -} - static void inetdev_send_gratuitous_arp(struct net_device *dev, struct in_device *in_dev) diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 5c967764041f..103c7d599a3c 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -18,6 +18,8 @@ #include <net/icmp.h> #include <net/protocol.h> #include <net/udp.h> +#include <net/tcp.h> +#include <net/espintcp.h> #include <linux/highmem.h> @@ -117,6 +119,132 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp) put_page(sg_page(sg)); } +#ifdef CONFIG_INET_ESPINTCP +struct esp_tcp_sk { + struct sock *sk; + struct rcu_head rcu; +}; + +static void esp_free_tcp_sk(struct rcu_head *head) +{ + struct esp_tcp_sk *esk = container_of(head, struct esp_tcp_sk, rcu); + + sock_put(esk->sk); + kfree(esk); +} + +static struct sock *esp_find_tcp_sk(struct xfrm_state *x) +{ + struct xfrm_encap_tmpl *encap = x->encap; + struct esp_tcp_sk *esk; + __be16 sport, dport; + struct sock *nsk; + struct sock *sk; + + sk = rcu_dereference(x->encap_sk); + if (sk && sk->sk_state == TCP_ESTABLISHED) + return sk; + + spin_lock_bh(&x->lock); + sport = encap->encap_sport; + dport = encap->encap_dport; + nsk = rcu_dereference_protected(x->encap_sk, + lockdep_is_held(&x->lock)); + if (sk && sk == nsk) { + esk = kmalloc(sizeof(*esk), GFP_ATOMIC); + if (!esk) { + spin_unlock_bh(&x->lock); + return ERR_PTR(-ENOMEM); + } + RCU_INIT_POINTER(x->encap_sk, NULL); + esk->sk = sk; + call_rcu(&esk->rcu, esp_free_tcp_sk); + } + spin_unlock_bh(&x->lock); + + sk = inet_lookup_established(xs_net(x), &tcp_hashinfo, x->id.daddr.a4, + dport, x->props.saddr.a4, sport, 0); + if (!sk) + return ERR_PTR(-ENOENT); + + if (!tcp_is_ulp_esp(sk)) { + sock_put(sk); + return ERR_PTR(-EINVAL); + } + + spin_lock_bh(&x->lock); + nsk = rcu_dereference_protected(x->encap_sk, + lockdep_is_held(&x->lock)); + if (encap->encap_sport != sport || + encap->encap_dport != dport) { + sock_put(sk); + sk = nsk ?: ERR_PTR(-EREMCHG); + } else if (sk == nsk) { + sock_put(sk); + } else { + rcu_assign_pointer(x->encap_sk, sk); + } + spin_unlock_bh(&x->lock); + + return sk; +} + +static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb) +{ + struct sock *sk; + int err; + + rcu_read_lock(); + + sk = esp_find_tcp_sk(x); + err = PTR_ERR_OR_ZERO(sk); + if (err) + goto out; + + bh_lock_sock(sk); + if (sock_owned_by_user(sk)) + err = espintcp_queue_out(sk, skb); + else + err = espintcp_push_skb(sk, skb); + bh_unlock_sock(sk); + +out: + rcu_read_unlock(); + return err; +} + +static int esp_output_tcp_encap_cb(struct net *net, struct sock *sk, + struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + struct xfrm_state *x = dst->xfrm; + + return esp_output_tcp_finish(x, skb); +} + +static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb) +{ + int err; + + local_bh_disable(); + err = xfrm_trans_queue_net(xs_net(x), skb, esp_output_tcp_encap_cb); + local_bh_enable(); + + /* EINPROGRESS just happens to do the right thing. It + * actually means that the skb has been consumed and + * isn't coming back. + */ + return err ?: -EINPROGRESS; +} +#else +static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb) +{ + kfree_skb(skb); + + return -EOPNOTSUPP; +} +#endif + static void esp_output_done(struct crypto_async_request *base, int err) { struct sk_buff *skb = base->data; @@ -147,7 +275,11 @@ static void esp_output_done(struct crypto_async_request *base, int err) secpath_reset(skb); xfrm_dev_resume(skb); } else { - xfrm_output_resume(skb, err); + if (!err && + x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) + esp_output_tail_tcp(x, skb); + else + xfrm_output_resume(skb, err); } } @@ -225,45 +357,100 @@ static void esp_output_fill_trailer(u8 *tail, int tfclen, int plen, __u8 proto) tail[plen - 1] = proto; } -static int esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp) +static struct ip_esp_hdr *esp_output_udp_encap(struct sk_buff *skb, + int encap_type, + struct esp_info *esp, + __be16 sport, + __be16 dport) { - int encap_type; struct udphdr *uh; __be32 *udpdata32; - __be16 sport, dport; - struct xfrm_encap_tmpl *encap = x->encap; - struct ip_esp_hdr *esph = esp->esph; unsigned int len; - spin_lock_bh(&x->lock); - sport = encap->encap_sport; - dport = encap->encap_dport; - encap_type = encap->encap_type; - spin_unlock_bh(&x->lock); - len = skb->len + esp->tailen - skb_transport_offset(skb); - if (len + sizeof(struct iphdr) >= IP_MAX_MTU) - return -EMSGSIZE; + if (len + sizeof(struct iphdr) > IP_MAX_MTU) + return ERR_PTR(-EMSGSIZE); - uh = (struct udphdr *)esph; + uh = (struct udphdr *)esp->esph; uh->source = sport; uh->dest = dport; uh->len = htons(len); uh->check = 0; + *skb_mac_header(skb) = IPPROTO_UDP; + + if (encap_type == UDP_ENCAP_ESPINUDP_NON_IKE) { + udpdata32 = (__be32 *)(uh + 1); + udpdata32[0] = udpdata32[1] = 0; + return (struct ip_esp_hdr *)(udpdata32 + 2); + } + + return (struct ip_esp_hdr *)(uh + 1); +} + +#ifdef CONFIG_INET_ESPINTCP +static struct ip_esp_hdr *esp_output_tcp_encap(struct xfrm_state *x, + struct sk_buff *skb, + struct esp_info *esp) +{ + __be16 *lenp = (void *)esp->esph; + struct ip_esp_hdr *esph; + unsigned int len; + struct sock *sk; + + len = skb->len + esp->tailen - skb_transport_offset(skb); + if (len > IP_MAX_MTU) + return ERR_PTR(-EMSGSIZE); + + rcu_read_lock(); + sk = esp_find_tcp_sk(x); + rcu_read_unlock(); + + if (IS_ERR(sk)) + return ERR_CAST(sk); + + *lenp = htons(len); + esph = (struct ip_esp_hdr *)(lenp + 1); + + return esph; +} +#else +static struct ip_esp_hdr *esp_output_tcp_encap(struct xfrm_state *x, + struct sk_buff *skb, + struct esp_info *esp) +{ + return ERR_PTR(-EOPNOTSUPP); +} +#endif + +static int esp_output_encap(struct xfrm_state *x, struct sk_buff *skb, + struct esp_info *esp) +{ + struct xfrm_encap_tmpl *encap = x->encap; + struct ip_esp_hdr *esph; + __be16 sport, dport; + int encap_type; + + spin_lock_bh(&x->lock); + sport = encap->encap_sport; + dport = encap->encap_dport; + encap_type = encap->encap_type; + spin_unlock_bh(&x->lock); + switch (encap_type) { default: case UDP_ENCAP_ESPINUDP: - esph = (struct ip_esp_hdr *)(uh + 1); - break; case UDP_ENCAP_ESPINUDP_NON_IKE: - udpdata32 = (__be32 *)(uh + 1); - udpdata32[0] = udpdata32[1] = 0; - esph = (struct ip_esp_hdr *)(udpdata32 + 2); + esph = esp_output_udp_encap(skb, encap_type, esp, sport, dport); + break; + case TCP_ENCAP_ESPINTCP: + esph = esp_output_tcp_encap(x, skb, esp); break; } - *skb_mac_header(skb) = IPPROTO_UDP; + if (IS_ERR(esph)) + return PTR_ERR(esph); + esp->esph = esph; return 0; @@ -279,9 +466,9 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * struct sk_buff *trailer; int tailen = esp->tailen; - /* this is non-NULL only with UDP Encapsulation */ + /* this is non-NULL only with TCP/UDP Encapsulation */ if (x->encap) { - int err = esp_output_udp_encap(x, skb, esp); + int err = esp_output_encap(x, skb, esp); if (err < 0) return err; @@ -474,6 +661,9 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * if (sg != dsg) esp_ssg_unref(x, tmp); + if (!err && x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) + err = esp_output_tail_tcp(x, skb); + error_free: kfree(tmp); error: @@ -600,7 +790,23 @@ int esp_input_done2(struct sk_buff *skb, int err) if (x->encap) { struct xfrm_encap_tmpl *encap = x->encap; + struct tcphdr *th = (void *)(skb_network_header(skb) + ihl); struct udphdr *uh = (void *)(skb_network_header(skb) + ihl); + __be16 source; + + switch (x->encap->encap_type) { + case TCP_ENCAP_ESPINTCP: + source = th->source; + break; + case UDP_ENCAP_ESPINUDP: + case UDP_ENCAP_ESPINUDP_NON_IKE: + source = uh->source; + break; + default: + WARN_ON_ONCE(1); + err = -EINVAL; + goto out; + } /* * 1) if the NAT-T peer's IP or port changed then @@ -609,11 +815,11 @@ int esp_input_done2(struct sk_buff *skb, int err) * SRC ports. */ if (iph->saddr != x->props.saddr.a4 || - uh->source != encap->encap_sport) { + source != encap->encap_sport) { xfrm_address_t ipaddr; ipaddr.a4 = iph->saddr; - km_new_mapping(x, &ipaddr, uh->source); + km_new_mapping(x, &ipaddr, source); /* XXX: perhaps add an extra * policy check here, to see @@ -988,6 +1194,14 @@ static int esp_init_state(struct xfrm_state *x) case UDP_ENCAP_ESPINUDP_NON_IKE: x->props.header_len += sizeof(struct udphdr) + 2 * sizeof(u32); break; +#ifdef CONFIG_INET_ESPINTCP + case TCP_ENCAP_ESPINTCP: + /* only the length field, TCP encap is done by + * the socket + */ + x->props.header_len += 2; + break; +#endif } } diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index 0e4a7cf6bc87..e2e219c7854a 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -57,6 +57,8 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head, if (!x) goto out_reset; + skb->mark = xfrm_smark_get(skb->mark, x); + sp->xvec[sp->len++] = x; sp->olen++; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index e8bc939b56dd..577db1d50a24 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -70,11 +70,6 @@ fail: fib_free_table(main_table); return -ENOMEM; } - -static bool fib4_has_custom_rules(struct net *net) -{ - return false; -} #else struct fib_table *fib_new_table(struct net *net, u32 id) @@ -124,17 +119,13 @@ struct fib_table *fib_get_table(struct net *net, u32 id) h = id & (FIB_TABLE_HASHSZ - 1); head = &net->ipv4.fib_table_hash[h]; - hlist_for_each_entry_rcu(tb, head, tb_hlist) { + hlist_for_each_entry_rcu(tb, head, tb_hlist, + lockdep_rtnl_is_held()) { if (tb->tb_id == id) return tb; } return NULL; } - -static bool fib4_has_custom_rules(struct net *net) -{ - return net->ipv4.fib_has_custom_rules; -} #endif /* CONFIG_IP_MULTIPLE_TABLES */ static void fib_replace_table(struct net *net, struct fib_table *old, @@ -1147,7 +1138,7 @@ void fib_modify_prefix_metric(struct in_ifaddr *ifa, u32 new_metric) if (!(dev->flags & IFF_UP) || ifa->ifa_flags & (IFA_F_SECONDARY | IFA_F_NOPREFIXROUTE) || ipv4_is_zeronet(prefix) || - prefix == ifa->ifa_local || ifa->ifa_prefixlen == 32) + (prefix == ifa->ifa_local && ifa->ifa_prefixlen == 32)) return; /* add the new */ diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index a68b5e21ec51..c092e9a55790 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -16,6 +16,9 @@ struct fib_alias { u8 fa_slen; u32 tb_id; s16 fa_default; + u8 offload:1, + trap:1, + unused:6; struct rcu_head rcu; }; @@ -35,9 +38,8 @@ struct fib_info *fib_create_info(struct fib_config *cfg, int fib_nh_match(struct fib_config *cfg, struct fib_info *fi, struct netlink_ext_ack *extack); bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi); -int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, u32 tb_id, - u8 type, __be32 dst, int dst_len, u8 tos, struct fib_info *fi, - unsigned int); +int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, + struct fib_rt_info *fri, unsigned int flags); void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, int dst_len, u32 tb_id, const struct nl_info *info, unsigned int nlm_flags); diff --git a/net/ipv4/fib_notifier.c b/net/ipv4/fib_notifier.c index b804ccbdb241..0c28bd469a68 100644 --- a/net/ipv4/fib_notifier.c +++ b/net/ipv4/fib_notifier.c @@ -9,12 +9,12 @@ #include <net/netns/ipv4.h> #include <net/ip_fib.h> -int call_fib4_notifier(struct notifier_block *nb, struct net *net, +int call_fib4_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info) { info->family = AF_INET; - return call_fib_notifier(nb, net, event_type, info); + return call_fib_notifier(nb, event_type, info); } int call_fib4_notifiers(struct net *net, enum fib_event_type event_type, @@ -34,17 +34,16 @@ static unsigned int fib4_seq_read(struct net *net) return net->ipv4.fib_seq + fib4_rules_seq_read(net); } -static int fib4_dump(struct net *net, struct notifier_block *nb) +static int fib4_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { int err; - err = fib4_rules_dump(net, nb); + err = fib4_rules_dump(net, nb, extack); if (err) return err; - fib_notify(net, nb); - - return 0; + return fib_notify(net, nb, extack); } static const struct fib_notifier_ops fib4_notifier_ops_template = { diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index b43a7ba5c6a4..f99e3bac5cab 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -65,9 +65,10 @@ bool fib4_rule_default(const struct fib_rule *rule) } EXPORT_SYMBOL_GPL(fib4_rule_default); -int fib4_rules_dump(struct net *net, struct notifier_block *nb) +int fib4_rules_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { - return fib_rules_dump(net, nb, AF_INET); + return fib_rules_dump(net, nb, AF_INET, extack); } unsigned int fib4_rules_seq_read(struct net *net) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 2db089e10ba0..a803cdd9400a 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -504,6 +504,7 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, int dst_len, u32 tb_id, const struct nl_info *info, unsigned int nlm_flags) { + struct fib_rt_info fri; struct sk_buff *skb; u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0; int err = -ENOBUFS; @@ -512,9 +513,15 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, if (!skb) goto errout; - err = fib_dump_info(skb, info->portid, seq, event, tb_id, - fa->fa_type, key, dst_len, - fa->fa_tos, fa->fa_info, nlm_flags); + fri.fi = fa->fa_info; + fri.tb_id = tb_id; + fri.dst = key; + fri.dst_len = dst_len; + fri.tos = fa->fa_tos; + fri.type = fa->fa_type; + fri.offload = fa->offload; + fri.trap = fa->trap; + err = fib_dump_info(skb, info->portid, seq, event, &fri, nlm_flags); if (err < 0) { /* -EMSGSIZE implies BUG in fib_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -1582,7 +1589,7 @@ failure: } int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nhc, - unsigned char *flags, bool skip_oif) + u8 rt_family, unsigned char *flags, bool skip_oif) { if (nhc->nhc_flags & RTNH_F_DEAD) *flags |= RTNH_F_DEAD; @@ -1613,7 +1620,7 @@ int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nhc, /* if gateway family does not match nexthop family * gateway is encoded as RTA_VIA */ - if (nhc->nhc_gw_family != nhc->nhc_family) { + if (rt_family != nhc->nhc_gw_family) { int alen = sizeof(struct in6_addr); struct nlattr *nla; struct rtvia *via; @@ -1654,7 +1661,7 @@ EXPORT_SYMBOL_GPL(fib_nexthop_info); #if IS_ENABLED(CONFIG_IP_ROUTE_MULTIPATH) || IS_ENABLED(CONFIG_IPV6) int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nhc, - int nh_weight) + int nh_weight, u8 rt_family) { const struct net_device *dev = nhc->nhc_dev; struct rtnexthop *rtnh; @@ -1667,7 +1674,7 @@ int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nhc, rtnh->rtnh_hops = nh_weight - 1; rtnh->rtnh_ifindex = dev ? dev->ifindex : 0; - if (fib_nexthop_info(skb, nhc, &flags, true) < 0) + if (fib_nexthop_info(skb, nhc, rt_family, &flags, true) < 0) goto nla_put_failure; rtnh->rtnh_flags = flags; @@ -1693,13 +1700,14 @@ static int fib_add_multipath(struct sk_buff *skb, struct fib_info *fi) goto nla_put_failure; if (unlikely(fi->nh)) { - if (nexthop_mpath_fill_node(skb, fi->nh) < 0) + if (nexthop_mpath_fill_node(skb, fi->nh, AF_INET) < 0) goto nla_put_failure; goto mp_end; } for_nexthops(fi) { - if (fib_add_nexthop(skb, &nh->nh_common, nh->fib_nh_weight) < 0) + if (fib_add_nexthop(skb, &nh->nh_common, nh->fib_nh_weight, + AF_INET) < 0) goto nla_put_failure; #ifdef CONFIG_IP_ROUTE_CLASSID if (nh->nh_tclassid && @@ -1724,10 +1732,11 @@ static int fib_add_multipath(struct sk_buff *skb, struct fib_info *fi) #endif int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, - u32 tb_id, u8 type, __be32 dst, int dst_len, u8 tos, - struct fib_info *fi, unsigned int flags) + struct fib_rt_info *fri, unsigned int flags) { - unsigned int nhs = fib_info_num_path(fi); + unsigned int nhs = fib_info_num_path(fri->fi); + struct fib_info *fi = fri->fi; + u32 tb_id = fri->tb_id; struct nlmsghdr *nlh; struct rtmsg *rtm; @@ -1737,22 +1746,22 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, rtm = nlmsg_data(nlh); rtm->rtm_family = AF_INET; - rtm->rtm_dst_len = dst_len; + rtm->rtm_dst_len = fri->dst_len; rtm->rtm_src_len = 0; - rtm->rtm_tos = tos; + rtm->rtm_tos = fri->tos; if (tb_id < 256) rtm->rtm_table = tb_id; else rtm->rtm_table = RT_TABLE_COMPAT; if (nla_put_u32(skb, RTA_TABLE, tb_id)) goto nla_put_failure; - rtm->rtm_type = type; + rtm->rtm_type = fri->type; rtm->rtm_flags = fi->fib_flags; rtm->rtm_scope = fi->fib_scope; rtm->rtm_protocol = fi->fib_protocol; if (rtm->rtm_dst_len && - nla_put_in_addr(skb, RTA_DST, dst)) + nla_put_in_addr(skb, RTA_DST, fri->dst)) goto nla_put_failure; if (fi->fib_priority && nla_put_u32(skb, RTA_PRIORITY, fi->fib_priority)) @@ -1775,7 +1784,7 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, const struct fib_nh_common *nhc = fib_info_nhc(fi, 0); unsigned char flags = 0; - if (fib_nexthop_info(skb, nhc, &flags, false) < 0) + if (fib_nexthop_info(skb, nhc, AF_INET, &flags, false) < 0) goto nla_put_failure; rtm->rtm_flags = flags; @@ -1794,6 +1803,11 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, goto nla_put_failure; } + if (fri->offload) + rtm->rtm_flags |= RTM_F_OFFLOAD; + if (fri->trap) + rtm->rtm_flags |= RTM_F_TRAP; + nlmsg_end(skb, nlh); return 0; @@ -1813,8 +1827,8 @@ int fib_sync_down_addr(struct net_device *dev, __be32 local) int ret = 0; unsigned int hash = fib_laddr_hashfn(local); struct hlist_head *head = &fib_info_laddrhash[hash]; + int tb_id = l3mdev_fib_table(dev) ? : RT_TABLE_MAIN; struct net *net = dev_net(dev); - int tb_id = l3mdev_fib_table(dev); struct fib_info *fi; if (!fib_info_laddrhash || local == 0) diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 2b2b3d291ab0..ff0c24371e33 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -74,11 +74,13 @@ #include <trace/events/fib.h> #include "fib_lookup.h" -static int call_fib_entry_notifier(struct notifier_block *nb, struct net *net, +static int call_fib_entry_notifier(struct notifier_block *nb, enum fib_event_type event_type, u32 dst, - int dst_len, struct fib_alias *fa) + int dst_len, struct fib_alias *fa, + struct netlink_ext_ack *extack) { struct fib_entry_notifier_info info = { + .info.extack = extack, .dst = dst, .dst_len = dst_len, .fi = fa->fa_info, @@ -86,7 +88,7 @@ static int call_fib_entry_notifier(struct notifier_block *nb, struct net *net, .type = fa->fa_type, .tb_id = fa->tb_id, }; - return call_fib4_notifier(nb, net, event_type, &info.info); + return call_fib4_notifier(nb, event_type, &info.info); } static int call_fib_entry_notifiers(struct net *net, @@ -978,9 +980,12 @@ static struct key_vector *fib_find_node(struct trie *t, /* Return the first fib alias matching TOS with * priority less than or equal to PRIO. + * If 'find_first' is set, return the first matching + * fib alias, regardless of TOS and priority. */ static struct fib_alias *fib_find_alias(struct hlist_head *fah, u8 slen, - u8 tos, u32 prio, u32 tb_id) + u8 tos, u32 prio, u32 tb_id, + bool find_first) { struct fib_alias *fa; @@ -996,6 +1001,8 @@ static struct fib_alias *fib_find_alias(struct hlist_head *fah, u8 slen, continue; if (fa->tb_id != tb_id) break; + if (find_first) + return fa; if (fa->fa_tos > tos) continue; if (fa->fa_info->fib_priority >= prio || fa->fa_tos < tos) @@ -1005,6 +1012,52 @@ static struct fib_alias *fib_find_alias(struct hlist_head *fah, u8 slen, return NULL; } +static struct fib_alias * +fib_find_matching_alias(struct net *net, const struct fib_rt_info *fri) +{ + u8 slen = KEYLENGTH - fri->dst_len; + struct key_vector *l, *tp; + struct fib_table *tb; + struct fib_alias *fa; + struct trie *t; + + tb = fib_get_table(net, fri->tb_id); + if (!tb) + return NULL; + + t = (struct trie *)tb->tb_data; + l = fib_find_node(t, &tp, be32_to_cpu(fri->dst)); + if (!l) + return NULL; + + hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { + if (fa->fa_slen == slen && fa->tb_id == fri->tb_id && + fa->fa_tos == fri->tos && fa->fa_info == fri->fi && + fa->fa_type == fri->type) + return fa; + } + + return NULL; +} + +void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri) +{ + struct fib_alias *fa_match; + + rcu_read_lock(); + + fa_match = fib_find_matching_alias(net, fri); + if (!fa_match) + goto out; + + fa_match->offload = fri->offload; + fa_match->trap = fri->trap; + +out: + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(fib_alias_hw_flags_set); + static void trie_rebalance(struct trie *t, struct key_vector *tn) { while (!IS_TRIE(tn)) @@ -1061,9 +1114,6 @@ noleaf: return -ENOMEM; } -/* fib notifier for ADD is sent before calling fib_insert_alias with - * the expectation that the only possible failure ENOMEM - */ static int fib_insert_alias(struct trie *t, struct key_vector *tp, struct key_vector *l, struct fib_alias *new, struct fib_alias *fa, t_key key) @@ -1116,11 +1166,13 @@ static bool fib_valid_key_len(u32 key, u8 plen, struct netlink_ext_ack *extack) return true; } +static void fib_remove_alias(struct trie *t, struct key_vector *tp, + struct key_vector *l, struct fib_alias *old); + /* Caller must hold RTNL. */ int fib_table_insert(struct net *net, struct fib_table *tb, struct fib_config *cfg, struct netlink_ext_ack *extack) { - enum fib_event_type event = FIB_EVENT_ENTRY_ADD; struct trie *t = (struct trie *)tb->tb_data; struct fib_alias *fa, *new_fa; struct key_vector *l, *tp; @@ -1147,7 +1199,7 @@ int fib_table_insert(struct net *net, struct fib_table *tb, l = fib_find_node(t, &tp, key); fa = l ? fib_find_alias(&l->leaf, slen, tos, fi->fib_priority, - tb->tb_id) : NULL; + tb->tb_id, false) : NULL; /* Now fa, if non-NULL, points to the first fib alias * with the same keys [prefix,tos,priority], if such key already @@ -1214,19 +1266,29 @@ int fib_table_insert(struct net *net, struct fib_table *tb, new_fa->fa_slen = fa->fa_slen; new_fa->tb_id = tb->tb_id; new_fa->fa_default = -1; + new_fa->offload = 0; + new_fa->trap = 0; - err = call_fib_entry_notifiers(net, - FIB_EVENT_ENTRY_REPLACE, - key, plen, new_fa, - extack); - if (err) - goto out_free_new_fa; + hlist_replace_rcu(&fa->fa_list, &new_fa->fa_list); + + if (fib_find_alias(&l->leaf, fa->fa_slen, 0, 0, + tb->tb_id, true) == new_fa) { + enum fib_event_type fib_event; + + fib_event = FIB_EVENT_ENTRY_REPLACE; + err = call_fib_entry_notifiers(net, fib_event, + key, plen, + new_fa, extack); + if (err) { + hlist_replace_rcu(&new_fa->fa_list, + &fa->fa_list); + goto out_free_new_fa; + } + } rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id, &cfg->fc_nlinfo, nlflags); - hlist_replace_rcu(&fa->fa_list, &new_fa->fa_list); - alias_free_mem_rcu(fa); fib_release_info(fi_drop); @@ -1242,12 +1304,10 @@ int fib_table_insert(struct net *net, struct fib_table *tb, if (fa_match) goto out; - if (cfg->fc_nlflags & NLM_F_APPEND) { - event = FIB_EVENT_ENTRY_APPEND; + if (cfg->fc_nlflags & NLM_F_APPEND) nlflags |= NLM_F_APPEND; - } else { + else fa = fa_first; - } } err = -ENOENT; if (!(cfg->fc_nlflags & NLM_F_CREATE)) @@ -1266,15 +1326,29 @@ int fib_table_insert(struct net *net, struct fib_table *tb, new_fa->fa_slen = slen; new_fa->tb_id = tb->tb_id; new_fa->fa_default = -1; - - err = call_fib_entry_notifiers(net, event, key, plen, new_fa, extack); - if (err) - goto out_free_new_fa; + new_fa->offload = 0; + new_fa->trap = 0; /* Insert new entry to the list. */ err = fib_insert_alias(t, tp, l, new_fa, fa, key); if (err) - goto out_fib_notif; + goto out_free_new_fa; + + /* The alias was already inserted, so the node must exist. */ + l = l ? l : fib_find_node(t, &tp, key); + if (WARN_ON_ONCE(!l)) + goto out_free_new_fa; + + if (fib_find_alias(&l->leaf, new_fa->fa_slen, 0, 0, tb->tb_id, true) == + new_fa) { + enum fib_event_type fib_event; + + fib_event = FIB_EVENT_ENTRY_REPLACE; + err = call_fib_entry_notifiers(net, fib_event, key, plen, + new_fa, extack); + if (err) + goto out_remove_new_fa; + } if (!plen) tb->tb_num_default++; @@ -1285,14 +1359,8 @@ int fib_table_insert(struct net *net, struct fib_table *tb, succeeded: return 0; -out_fib_notif: - /* notifier was sent that entry would be added to trie, but - * the add failed and need to recover. Only failure for - * fib_insert_alias is ENOMEM. - */ - NL_SET_ERR_MSG(extack, "Failed to insert route into trie"); - call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, key, - plen, new_fa, NULL); +out_remove_new_fa: + fib_remove_alias(t, tp, l, new_fa); out_free_new_fa: kmem_cache_free(fn_alias_kmem, new_fa); out: @@ -1543,6 +1611,36 @@ static void fib_remove_alias(struct trie *t, struct key_vector *tp, node_pull_suffix(tp, fa->fa_slen); } +static void fib_notify_alias_delete(struct net *net, u32 key, + struct hlist_head *fah, + struct fib_alias *fa_to_delete, + struct netlink_ext_ack *extack) +{ + struct fib_alias *fa_next, *fa_to_notify; + u32 tb_id = fa_to_delete->tb_id; + u8 slen = fa_to_delete->fa_slen; + enum fib_event_type fib_event; + + /* Do not notify if we do not care about the route. */ + if (fib_find_alias(fah, slen, 0, 0, tb_id, true) != fa_to_delete) + return; + + /* Determine if the route should be replaced by the next route in the + * list. + */ + fa_next = hlist_entry_safe(fa_to_delete->fa_list.next, + struct fib_alias, fa_list); + if (fa_next && fa_next->fa_slen == slen && fa_next->tb_id == tb_id) { + fib_event = FIB_EVENT_ENTRY_REPLACE; + fa_to_notify = fa_next; + } else { + fib_event = FIB_EVENT_ENTRY_DEL; + fa_to_notify = fa_to_delete; + } + call_fib_entry_notifiers(net, fib_event, key, KEYLENGTH - slen, + fa_to_notify, extack); +} + /* Caller must hold RTNL. */ int fib_table_delete(struct net *net, struct fib_table *tb, struct fib_config *cfg, struct netlink_ext_ack *extack) @@ -1564,7 +1662,7 @@ int fib_table_delete(struct net *net, struct fib_table *tb, if (!l) return -ESRCH; - fa = fib_find_alias(&l->leaf, slen, tos, 0, tb->tb_id); + fa = fib_find_alias(&l->leaf, slen, tos, 0, tb->tb_id, false); if (!fa) return -ESRCH; @@ -1596,8 +1694,7 @@ int fib_table_delete(struct net *net, struct fib_table *tb, if (!fa_to_delete) return -ESRCH; - call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, key, plen, - fa_to_delete, extack); + fib_notify_alias_delete(net, key, &l->leaf, fa_to_delete, extack); rtmsg_fib(RTM_DELROUTE, htonl(key), fa_to_delete, plen, tb->tb_id, &cfg->fc_nlinfo, 0); @@ -1921,10 +2018,8 @@ int fib_table_flush(struct net *net, struct fib_table *tb, bool flush_all) continue; } - call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, - n->key, - KEYLENGTH - fa->fa_slen, fa, - NULL); + fib_notify_alias_delete(net, n->key, &n->leaf, fa, + NULL); hlist_del_rcu(&fa->fa_list); fib_release_info(fa->fa_info); alias_free_mem_rcu(fa); @@ -2015,10 +2110,13 @@ void fib_info_notify_update(struct net *net, struct nl_info *info) } } -static void fib_leaf_notify(struct net *net, struct key_vector *l, - struct fib_table *tb, struct notifier_block *nb) +static int fib_leaf_notify(struct key_vector *l, struct fib_table *tb, + struct notifier_block *nb, + struct netlink_ext_ack *extack) { struct fib_alias *fa; + int last_slen = -1; + int err; hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { struct fib_info *fi = fa->fa_info; @@ -2032,39 +2130,57 @@ static void fib_leaf_notify(struct net *net, struct key_vector *l, if (tb->tb_id != fa->tb_id) continue; - call_fib_entry_notifier(nb, net, FIB_EVENT_ENTRY_ADD, l->key, - KEYLENGTH - fa->fa_slen, fa); + if (fa->fa_slen == last_slen) + continue; + + last_slen = fa->fa_slen; + err = call_fib_entry_notifier(nb, FIB_EVENT_ENTRY_REPLACE, + l->key, KEYLENGTH - fa->fa_slen, + fa, extack); + if (err) + return err; } + return 0; } -static void fib_table_notify(struct net *net, struct fib_table *tb, - struct notifier_block *nb) +static int fib_table_notify(struct fib_table *tb, struct notifier_block *nb, + struct netlink_ext_ack *extack) { struct trie *t = (struct trie *)tb->tb_data; struct key_vector *l, *tp = t->kv; t_key key = 0; + int err; while ((l = leaf_walk_rcu(&tp, key)) != NULL) { - fib_leaf_notify(net, l, tb, nb); + err = fib_leaf_notify(l, tb, nb, extack); + if (err) + return err; key = l->key + 1; /* stop in case of wrap around */ if (key < l->key) break; } + return 0; } -void fib_notify(struct net *net, struct notifier_block *nb) +int fib_notify(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { unsigned int h; + int err; for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct fib_table *tb; - hlist_for_each_entry_rcu(tb, head, tb_hlist) - fib_table_notify(net, tb, nb); + hlist_for_each_entry_rcu(tb, head, tb_hlist) { + err = fib_table_notify(tb, nb, extack); + if (err) + return err; + } } + return 0; } static void __trie_free_rcu(struct rcu_head *head) @@ -2128,14 +2244,20 @@ static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb, if (filter->dump_routes) { if (!s_fa) { + struct fib_rt_info fri; + + fri.fi = fi; + fri.tb_id = tb->tb_id; + fri.dst = xkey; + fri.dst_len = KEYLENGTH - fa->fa_slen; + fri.tos = fa->fa_tos; + fri.type = fa->fa_type; + fri.offload = fa->offload; + fri.trap = fa->trap; err = fib_dump_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - RTM_NEWROUTE, - tb->tb_id, fa->fa_type, - xkey, - KEYLENGTH - fa->fa_slen, - fa->fa_tos, fi, flags); + RTM_NEWROUTE, &fri, flags); if (err < 0) goto stop; } @@ -2145,7 +2267,7 @@ static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb, if (filter->dump_exceptions) { err = fib_dump_info_fnhe(skb, cb, tb->tb_id, fi, - &i_fa, s_fa); + &i_fa, s_fa, flags); if (err < 0) goto stop; } @@ -2175,6 +2297,12 @@ int fib_table_dump(struct fib_table *tb, struct sk_buff *skb, int count = cb->args[2]; t_key key = cb->args[3]; + /* First time here, count and key are both always 0. Count > 0 + * and key == 0 means the dump has wrapped around and we are done. + */ + if (count && !key) + return skb->len; + while ((l = leaf_walk_rcu(&tp, key)) != NULL) { int err; diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 30fa771d382a..dcc79ff54b41 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -662,8 +662,8 @@ static const struct nla_policy fou_nl_policy[FOU_ATTR_MAX + 1] = { [FOU_ATTR_REMCSUM_NOPARTIAL] = { .type = NLA_FLAG, }, [FOU_ATTR_LOCAL_V4] = { .type = NLA_U32, }, [FOU_ATTR_PEER_V4] = { .type = NLA_U32, }, - [FOU_ATTR_LOCAL_V6] = { .type = sizeof(struct in6_addr), }, - [FOU_ATTR_PEER_V6] = { .type = sizeof(struct in6_addr), }, + [FOU_ATTR_LOCAL_V6] = { .len = sizeof(struct in6_addr), }, + [FOU_ATTR_PEER_V6] = { .len = sizeof(struct in6_addr), }, [FOU_ATTR_PEER_PORT] = { .type = NLA_U16, }, [FOU_ATTR_IFINDEX] = { .type = NLA_S32, }, }; diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c index 44bfeecac33e..5fd6e8ed02b5 100644 --- a/net/ipv4/gre_demux.c +++ b/net/ipv4/gre_demux.c @@ -127,7 +127,7 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, if (!pskb_may_pull(skb, nhs + hdr_len + sizeof(*ershdr))) return -EINVAL; - ershdr = (struct erspan_base_hdr *)options; + ershdr = (struct erspan_base_hdr *)(skb->data + nhs + hdr_len); tpi->key = cpu_to_be32(get_session_id(ershdr)); } diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 4de7e962d3da..2e6d1b7a7bc9 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -174,7 +174,7 @@ static struct sk_buff *gre_gro_receive(struct list_head *head, if (skb_gro_checksum_simple_validate(skb)) goto out_unlock; - skb_gro_checksum_try_convert(skb, IPPROTO_GRE, 0, + skb_gro_checksum_try_convert(skb, IPPROTO_GRE, null_compute_pseudo); } diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 1510e951f451..f369e7ce685b 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -249,10 +249,11 @@ bool icmp_global_allow(void) bool rc = false; /* Check if token bucket is empty and cannot be refilled - * without taking the spinlock. + * without taking the spinlock. The READ_ONCE() are paired + * with the following WRITE_ONCE() in this same function. */ - if (!icmp_global.credit) { - delta = min_t(u32, now - icmp_global.stamp, HZ); + if (!READ_ONCE(icmp_global.credit)) { + delta = min_t(u32, now - READ_ONCE(icmp_global.stamp), HZ); if (delta < HZ / 50) return false; } @@ -262,14 +263,14 @@ bool icmp_global_allow(void) if (delta >= HZ / 50) { incr = sysctl_icmp_msgs_per_sec * delta / HZ ; if (incr) - icmp_global.stamp = now; + WRITE_ONCE(icmp_global.stamp, now); } credit = min_t(u32, icmp_global.credit + incr, sysctl_icmp_msgs_burst); if (credit) { credit--; rc = true; } - icmp_global.credit = credit; + WRITE_ONCE(icmp_global.credit, credit); spin_unlock(&icmp_global.lock); return rc; } @@ -582,7 +583,13 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, if (!rt) goto out; - net = dev_net(rt->dst.dev); + + if (rt->dst.dev) + net = dev_net(rt->dst.dev); + else if (skb_in->dev) + net = dev_net(skb_in->dev); + else + goto out; /* * Find the original header. It is expected to be valid, of course. @@ -676,7 +683,8 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, dev = dev_get_by_index_rcu(net, inet_iif(skb_in)); if (dev) - saddr = inet_select_addr(dev, 0, RT_SCOPE_LINK); + saddr = inet_select_addr(dev, iph->saddr, + RT_SCOPE_LINK); else saddr = 0; rcu_read_unlock(); @@ -740,6 +748,39 @@ out:; } EXPORT_SYMBOL(__icmp_send); +#if IS_ENABLED(CONFIG_NF_NAT) +#include <net/netfilter/nf_conntrack.h> +void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info) +{ + struct sk_buff *cloned_skb = NULL; + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + __be32 orig_ip; + + ct = nf_ct_get(skb_in, &ctinfo); + if (!ct || !(ct->status & IPS_SRC_NAT)) { + icmp_send(skb_in, type, code, info); + return; + } + + if (skb_shared(skb_in)) + skb_in = cloned_skb = skb_clone(skb_in, GFP_ATOMIC); + + if (unlikely(!skb_in || skb_network_header(skb_in) < skb_in->head || + (skb_network_header(skb_in) + sizeof(struct iphdr)) > + skb_tail_pointer(skb_in) || skb_ensure_writable(skb_in, + skb_network_offset(skb_in) + sizeof(struct iphdr)))) + goto out; + + orig_ip = ip_hdr(skb_in)->saddr; + ip_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.ip; + icmp_send(skb_in, type, code, info); + ip_hdr(skb_in)->saddr = orig_ip; +out: + consume_skb(cloned_skb); +} +EXPORT_SYMBOL(icmp_ndo_send); +#endif static void icmp_socket_deliver(struct sk_buff *skb, u32 info) { @@ -902,7 +943,7 @@ static bool icmp_redirect(struct sk_buff *skb) return false; } - icmp_socket_deliver(skb, icmp_hdr(skb)->un.gateway); + icmp_socket_deliver(skb, ntohl(icmp_hdr(skb)->un.gateway)); return true; } diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 180f6896b98b..3b9c7a2725a9 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1475,7 +1475,7 @@ EXPORT_SYMBOL(__ip_mc_inc_group); void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) { - __ip_mc_inc_group(in_dev, addr, MCAST_EXCLUDE); + __ip_mc_inc_group(in_dev, addr, GFP_KERNEL); } EXPORT_SYMBOL(ip_mc_inc_group); @@ -1563,7 +1563,7 @@ static int ip_mc_check_igmp_msg(struct sk_buff *skb) } } -static inline __sum16 ip_mc_validate_checksum(struct sk_buff *skb) +static __sum16 ip_mc_validate_checksum(struct sk_buff *skb) { return skb_checksum_simple_validate(skb); } @@ -2197,7 +2197,7 @@ static int __ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr, iml->sflist = NULL; iml->sfmode = mode; rcu_assign_pointer(inet->mc_list, iml); - __ip_mc_inc_group(in_dev, addr, mode); + ____ip_mc_inc_group(in_dev, addr, mode, GFP_KERNEL); err = 0; done: return err; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index f5c163d4771b..a4db79b1b643 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -560,7 +560,7 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk, rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) goto no_route; - if (opt && opt->opt.is_strictroute && rt->rt_gw_family) + if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway) goto route_err; rcu_read_unlock(); return &rt->dst; @@ -598,7 +598,7 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, rt = ip_route_output_flow(net, fl4, sk); if (IS_ERR(rt)) goto no_route; - if (opt && opt->opt.is_strictroute && rt->rt_gw_family) + if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway) goto route_err; return &rt->dst; @@ -610,12 +610,6 @@ no_route: } EXPORT_SYMBOL_GPL(inet_csk_route_child_sock); -#if IS_ENABLED(CONFIG_IPV6) -#define AF_INET_FAMILY(fam) ((fam) == AF_INET) -#else -#define AF_INET_FAMILY(fam) true -#endif - /* Decide when to expire the request and when to resend SYN-ACK */ static inline void syn_ack_recalc(struct request_sock *req, const int thresh, const int max_retries, @@ -716,7 +710,7 @@ static void reqsk_timer_handler(struct timer_list *t) * ones are about to clog our table. */ qlen = reqsk_queue_len(queue); - if ((qlen << 1) > max(8U, sk_listener->sk_max_ack_backlog)) { + if ((qlen << 1) > max(8U, READ_ONCE(sk_listener->sk_max_ack_backlog))) { int young = reqsk_queue_len_young(queue) << 1; while (thresh > 2) { @@ -770,6 +764,18 @@ void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, } EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add); +static void inet_clone_ulp(const struct request_sock *req, struct sock *newsk, + const gfp_t priority) +{ + struct inet_connection_sock *icsk = inet_csk(newsk); + + if (!icsk->icsk_ulp_ops) + return; + + if (icsk->icsk_ulp_ops->clone) + icsk->icsk_ulp_ops->clone(req, newsk, priority); +} + /** * inet_csk_clone_lock - clone an inet socket, and lock its clone * @sk: the socket to clone @@ -810,6 +816,8 @@ struct sock *inet_csk_clone_lock(const struct sock *sk, /* Deinitialize accept_queue to trap illegal accesses. */ memset(&newicsk->icsk_accept_queue, 0, sizeof(newicsk->icsk_accept_queue)); + inet_clone_ulp(req, newsk, priority); + security_inet_csk_clone(newsk, req); } return newsk; @@ -906,7 +914,7 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req, percpu_counter_inc(sk->sk_prot->orphan_count); if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) { - BUG_ON(tcp_sk(child)->fastopen_rsk != req); + BUG_ON(rcu_access_pointer(tcp_sk(child)->fastopen_rsk) != req); BUG_ON(sk != req->rsk_listener); /* Paranoid, to prevent race condition if @@ -915,7 +923,7 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req, * Also to satisfy an assertion in * tcp_v4_destroy_sock(). */ - tcp_sk(child)->fastopen_rsk = NULL; + RCU_INIT_POINTER(tcp_sk(child)->fastopen_rsk, NULL); } inet_csk_destroy_sock(child); } @@ -934,7 +942,7 @@ struct sock *inet_csk_reqsk_queue_add(struct sock *sk, req->sk = child; req->dl_next = NULL; if (queue->rskq_accept_head == NULL) - queue->rskq_accept_head = req; + WRITE_ONCE(queue->rskq_accept_head, req); else queue->rskq_accept_tail->dl_next = req; queue->rskq_accept_tail = req; @@ -1086,7 +1094,7 @@ struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu) if (!dst) goto out; } - dst->ops->update_pmtu(dst, sk, NULL, mtu); + dst->ops->update_pmtu(dst, sk, NULL, mtu, true); dst = __sk_dst_check(sk, 0); if (!dst) diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index bbb005eb5218..f11e997e517b 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -193,7 +193,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, if (ext & (1 << (INET_DIAG_MEMINFO - 1))) { struct inet_diag_meminfo minfo = { .idiag_rmem = sk_rmem_alloc_get(sk), - .idiag_wmem = sk->sk_wmem_queued, + .idiag_wmem = READ_ONCE(sk->sk_wmem_queued), .idiag_fmem = sk->sk_forward_alloc, .idiag_tmem = sk_wmem_alloc_get(sk), }; @@ -226,17 +226,17 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, r->idiag_timer = 1; r->idiag_retrans = icsk->icsk_retransmits; r->idiag_expires = - jiffies_to_msecs(icsk->icsk_timeout - jiffies); + jiffies_delta_to_msecs(icsk->icsk_timeout - jiffies); } else if (icsk->icsk_pending == ICSK_TIME_PROBE0) { r->idiag_timer = 4; r->idiag_retrans = icsk->icsk_probes_out; r->idiag_expires = - jiffies_to_msecs(icsk->icsk_timeout - jiffies); + jiffies_delta_to_msecs(icsk->icsk_timeout - jiffies); } else if (timer_pending(&sk->sk_timer)) { r->idiag_timer = 2; r->idiag_retrans = icsk->icsk_probes_out; r->idiag_expires = - jiffies_to_msecs(sk->sk_timer.expires - jiffies); + jiffies_delta_to_msecs(sk->sk_timer.expires - jiffies); } else { r->idiag_timer = 0; r->idiag_expires = 0; @@ -342,16 +342,13 @@ static int inet_twsk_diag_fill(struct sock *sk, r = nlmsg_data(nlh); BUG_ON(tw->tw_state != TCP_TIME_WAIT); - tmo = tw->tw_timer.expires - jiffies; - if (tmo < 0) - tmo = 0; - inet_diag_msg_common_fill(r, sk); r->idiag_retrans = 0; r->idiag_state = tw->tw_substate; r->idiag_timer = 3; - r->idiag_expires = jiffies_to_msecs(tmo); + tmo = tw->tw_timer.expires - jiffies; + r->idiag_expires = jiffies_delta_to_msecs(tmo); r->idiag_rqueue = 0; r->idiag_wqueue = 0; r->idiag_uid = 0; @@ -385,7 +382,7 @@ static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb, offsetof(struct sock, sk_cookie)); tmo = inet_reqsk(sk)->rsk_timer.expires - jiffies; - r->idiag_expires = (tmo >= 0) ? jiffies_to_msecs(tmo) : 0; + r->idiag_expires = jiffies_delta_to_msecs(tmo); r->idiag_rqueue = 0; r->idiag_wqueue = 0; r->idiag_uid = 0; @@ -914,11 +911,12 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, for (i = s_i; i < INET_LHTABLE_SIZE; i++) { struct inet_listen_hashbucket *ilb; + struct hlist_nulls_node *node; num = 0; ilb = &hashinfo->listening_hash[i]; spin_lock(&ilb->lock); - sk_for_each(sk, &ilb->head) { + sk_nulls_for_each(sk, node, &ilb->nulls_head) { struct inet_sock *inet = inet_sk(sk); if (!net_eq(sock_net(sk), net)) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 97824864e40d..2bbaaf0c7176 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -240,7 +240,7 @@ static inline int compute_score(struct sock *sk, struct net *net, return -1; score = sk->sk_family == PF_INET ? 2 : 1; - if (sk->sk_incoming_cpu == raw_smp_processor_id()) + if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) score++; } return score; @@ -516,10 +516,11 @@ static int inet_reuseport_add_sock(struct sock *sk, struct inet_listen_hashbucket *ilb) { struct inet_bind_bucket *tb = inet_csk(sk)->icsk_bind_hash; + const struct hlist_nulls_node *node; struct sock *sk2; kuid_t uid = sock_i_uid(sk); - sk_for_each_rcu(sk2, &ilb->head) { + sk_nulls_for_each_rcu(sk2, node, &ilb->nulls_head) { if (sk2 != sk && sk2->sk_family == sk->sk_family && ipv6_only_sock(sk2) == ipv6_only_sock(sk) && @@ -555,9 +556,9 @@ int __inet_hash(struct sock *sk, struct sock *osk) } if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport && sk->sk_family == AF_INET6) - hlist_add_tail_rcu(&sk->sk_node, &ilb->head); + __sk_nulls_add_node_tail_rcu(sk, &ilb->nulls_head); else - hlist_add_head_rcu(&sk->sk_node, &ilb->head); + __sk_nulls_add_node_rcu(sk, &ilb->nulls_head); inet_hash2(hashinfo, sk); ilb->count++; sock_set_flag(sk, SOCK_RCU_FREE); @@ -606,11 +607,9 @@ void inet_unhash(struct sock *sk) reuseport_detach_sock(sk); if (ilb) { inet_unhash2(hashinfo, sk); - __sk_del_node_init(sk); - ilb->count--; - } else { - __sk_nulls_del_node_init_rcu(sk); + ilb->count--; } + __sk_nulls_del_node_init_rcu(sk); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); unlock: spin_unlock_bh(lock); @@ -750,7 +749,8 @@ void inet_hashinfo_init(struct inet_hashinfo *h) for (i = 0; i < INET_LHTABLE_SIZE; i++) { spin_lock_init(&h->listening_hash[i].lock); - INIT_HLIST_HEAD(&h->listening_hash[i].head); + INIT_HLIST_NULLS_HEAD(&h->listening_hash[i].nulls_head, + i + LISTENING_NULLS_BASE); h->listening_hash[i].count = 0; } diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index be778599bfed..ff327a62c9ce 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -160,7 +160,12 @@ static void inet_peer_gc(struct inet_peer_base *base, base->total / inet_peer_threshold * HZ; for (i = 0; i < gc_cnt; i++) { p = gc_stack[i]; - delta = (__u32)jiffies - p->dtime; + + /* The READ_ONCE() pairs with the WRITE_ONCE() + * in inet_putpeer() + */ + delta = (__u32)jiffies - READ_ONCE(p->dtime); + if (delta < ttl || !refcount_dec_if_one(&p->refcnt)) gc_stack[i] = NULL; } @@ -237,7 +242,10 @@ EXPORT_SYMBOL_GPL(inet_getpeer); void inet_putpeer(struct inet_peer *p) { - p->dtime = (__u32)jiffies; + /* The WRITE_ONCE() pairs with itself (we run lockless) + * and the READ_ONCE() in inet_peer_gc() + */ + WRITE_ONCE(p->dtime, (__u32)jiffies); if (refcount_dec_and_test(&p->refcnt)) call_rcu(&p->rcu, inetpeer_free_rcu); diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 06f6f280b9ff..00ec819f949b 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -123,7 +123,7 @@ int ip_forward(struct sk_buff *skb) rt = skb_rtable(skb); - if (opt->is_strictroute && rt->rt_gw_family) + if (opt->is_strictroute && rt->rt_uses_gateway) goto sr_failed; IPCB(skb)->flags |= IPSKB_FORWARDED; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index a53a543fe055..8274f98c511c 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -340,6 +340,8 @@ static int __ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi, iph->saddr, iph->daddr, tpi->key); if (tunnel) { + const struct iphdr *tnl_params; + if (__iptunnel_pull_header(skb, hdr_len, tpi->proto, raw_proto, false) < 0) goto drop; @@ -348,7 +350,9 @@ static int __ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi, skb_pop_mac_header(skb); else skb_reset_mac_header(skb); - if (tunnel->collect_md) { + + tnl_params = &tunnel->parms.iph; + if (tunnel->collect_md || tnl_params->daddr == 0) { __be16 flags; __be64 tun_id; @@ -509,9 +513,9 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) key = &tun_info->key; if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT)) goto err_free_skb; - md = ip_tunnel_info_opts(tun_info); - if (!md) + if (tun_info->options_len < sizeof(*md)) goto err_free_skb; + md = ip_tunnel_info_opts(tun_info); /* ERSPAN has fixed 8 byte GRE header */ version = md->version; @@ -1446,6 +1450,7 @@ static void erspan_setup(struct net_device *dev) struct ip_tunnel *t = netdev_priv(dev); ether_setup(dev); + dev->max_mtu = 0; dev->netdev_ops = &erspan_netdev_ops; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; @@ -1459,8 +1464,8 @@ static const struct nla_policy ipgre_policy[IFLA_GRE_MAX + 1] = { [IFLA_GRE_OFLAGS] = { .type = NLA_U16 }, [IFLA_GRE_IKEY] = { .type = NLA_U32 }, [IFLA_GRE_OKEY] = { .type = NLA_U32 }, - [IFLA_GRE_LOCAL] = { .len = FIELD_SIZEOF(struct iphdr, saddr) }, - [IFLA_GRE_REMOTE] = { .len = FIELD_SIZEOF(struct iphdr, daddr) }, + [IFLA_GRE_LOCAL] = { .len = sizeof_field(struct iphdr, saddr) }, + [IFLA_GRE_REMOTE] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_GRE_TTL] = { .type = NLA_U8 }, [IFLA_GRE_TOS] = { .type = NLA_U8 }, [IFLA_GRE_PMTUDISC] = { .type = NLA_U8 }, diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 1e2392b7c64e..aa438c6758a7 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -199,7 +199,7 @@ resubmit: kfree_skb(skb); return; } - nf_reset(skb); + nf_reset_ct(skb); } ret = INDIRECT_CALL_2(ipprot->handler, tcp_v4_rcv, udp_rcv, skb); @@ -302,16 +302,31 @@ drop: return true; } +static bool ip_can_use_hint(const struct sk_buff *skb, const struct iphdr *iph, + const struct sk_buff *hint) +{ + return hint && !skb_dst(skb) && ip_hdr(hint)->daddr == iph->daddr && + ip_hdr(hint)->tos == iph->tos; +} + INDIRECT_CALLABLE_DECLARE(int udp_v4_early_demux(struct sk_buff *)); INDIRECT_CALLABLE_DECLARE(int tcp_v4_early_demux(struct sk_buff *)); static int ip_rcv_finish_core(struct net *net, struct sock *sk, - struct sk_buff *skb, struct net_device *dev) + struct sk_buff *skb, struct net_device *dev, + const struct sk_buff *hint) { const struct iphdr *iph = ip_hdr(skb); int (*edemux)(struct sk_buff *skb); struct rtable *rt; int err; + if (ip_can_use_hint(skb, iph, hint)) { + err = ip_route_use_hint(skb, iph->daddr, iph->saddr, iph->tos, + dev, hint); + if (unlikely(err)) + goto drop_error; + } + if (net->ipv4.sysctl_ip_early_demux && !skb_dst(skb) && !skb->sk && @@ -408,7 +423,7 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) if (!skb) return NET_RX_SUCCESS; - ret = ip_rcv_finish_core(net, sk, skb, dev); + ret = ip_rcv_finish_core(net, sk, skb, dev, NULL); if (ret != NET_RX_DROP) ret = dst_input(skb); return ret; @@ -535,11 +550,20 @@ static void ip_sublist_rcv_finish(struct list_head *head) } } +static struct sk_buff *ip_extract_route_hint(const struct net *net, + struct sk_buff *skb, int rt_type) +{ + if (fib4_has_custom_rules(net) || rt_type == RTN_BROADCAST) + return NULL; + + return skb; +} + static void ip_list_rcv_finish(struct net *net, struct sock *sk, struct list_head *head) { + struct sk_buff *skb, *next, *hint = NULL; struct dst_entry *curr_dst = NULL; - struct sk_buff *skb, *next; struct list_head sublist; INIT_LIST_HEAD(&sublist); @@ -554,11 +578,14 @@ static void ip_list_rcv_finish(struct net *net, struct sock *sk, skb = l3mdev_ip_rcv(skb); if (!skb) continue; - if (ip_rcv_finish_core(net, sk, skb, dev) == NET_RX_DROP) + if (ip_rcv_finish_core(net, sk, skb, dev, hint) == NET_RX_DROP) continue; dst = skb_dst(skb); if (curr_dst != dst) { + hint = ip_extract_route_hint(net, skb, + ((struct rtable *)dst)->rt_type); + /* dispatch old sublist */ if (!list_empty(&sublist)) ip_sublist_rcv_finish(&sublist); @@ -611,5 +638,6 @@ void ip_list_rcv(struct list_head *head, struct packet_type *pt, list_add_tail(&skb->list, &sublist); } /* dispatch final sublist */ - ip_sublist_rcv(&sublist, curr_dev, curr_net); + if (!list_empty(&sublist)) + ip_sublist_rcv(&sublist, curr_dev, curr_net); } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index cc7ef0d05bbd..d84819893db9 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -240,8 +240,8 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s static int ip_finish_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu) { + struct sk_buff *segs, *nskb; netdev_features_t features; - struct sk_buff *segs; int ret = 0; /* common case: seglen is <= mtu @@ -272,8 +272,7 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk, consume_skb(skb); - do { - struct sk_buff *nskb = segs->next; + skb_list_walk_safe(segs, segs, nskb) { int err; skb_mark_not_on_list(segs); @@ -281,8 +280,7 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk, if (err && ret == 0) ret = err; - segs = nskb; - } while (segs); + } return ret; } @@ -422,7 +420,7 @@ int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb) int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct net_device *dev = skb_dst(skb)->dev; + struct net_device *dev = skb_dst(skb)->dev, *indev = skb->dev; IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len); @@ -430,7 +428,7 @@ int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb) skb->protocol = htons(ETH_P_IP); return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, - net, sk, skb, NULL, dev, + net, sk, skb, indev, dev, ip_finish_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); } @@ -499,7 +497,7 @@ int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl, skb_dst_set_noref(skb, &rt->dst); packet_routed: - if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_gw_family) + if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_uses_gateway) goto no_route; /* OK, we know where to send it, allocate and build IP header. */ @@ -645,11 +643,12 @@ void ip_fraglist_prepare(struct sk_buff *skb, struct ip_fraglist_iter *iter) EXPORT_SYMBOL(ip_fraglist_prepare); void ip_frag_init(struct sk_buff *skb, unsigned int hlen, - unsigned int ll_rs, unsigned int mtu, + unsigned int ll_rs, unsigned int mtu, bool DF, struct ip_frag_state *state) { struct iphdr *iph = ip_hdr(skb); + state->DF = DF; state->hlen = hlen; state->ll_rs = ll_rs; state->mtu = mtu; @@ -668,9 +667,6 @@ static void ip_frag_ipcb(struct sk_buff *from, struct sk_buff *to, /* Copy the flags to each fragment. */ IPCB(to)->flags = IPCB(from)->flags; - if (IPCB(from)->flags & IPSKB_FRAG_PMTU) - state->iph->frag_off |= htons(IP_DF); - /* ANK: dirty, but effective trick. Upgrade options only if * the segment to be fragmented was THE FIRST (otherwise, * options are already fixed) and make it ONCE @@ -738,6 +734,8 @@ struct sk_buff *ip_frag_next(struct sk_buff *skb, struct ip_frag_state *state) */ iph = ip_hdr(skb2); iph->frag_off = htons((state->offset >> 3)); + if (state->DF) + iph->frag_off |= htons(IP_DF); /* * Added AC : If we are fragmenting a fragment that's not the @@ -771,6 +769,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, struct rtable *rt = skb_rtable(skb); unsigned int mtu, hlen, ll_rs; struct ip_fraglist_iter iter; + ktime_t tstamp = skb->tstamp; struct ip_frag_state state; int err = 0; @@ -846,6 +845,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, ip_fraglist_prepare(skb, &iter); } + skb->tstamp = tstamp; err = output(net, sk, skb); if (!err) @@ -881,7 +881,8 @@ slow_path: * Fragment the datagram. */ - ip_frag_init(skb, hlen, ll_rs, mtu, &state); + ip_frag_init(skb, hlen, ll_rs, mtu, IPCB(skb)->flags & IPSKB_FRAG_PMTU, + &state); /* * Keep copying data until we run out. @@ -900,6 +901,7 @@ slow_path: /* * Put this fragment into the sending queue. */ + skb2->tstamp = tstamp; err = output(net, sk, skb2); if (err) goto fail; @@ -1254,18 +1256,22 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, cork->addr = ipc->addr; } - /* - * We steal reference to this route, caller should not release it - */ - *rtp = NULL; cork->fragsize = ip_sk_use_pmtu(sk) ? - dst_mtu(&rt->dst) : rt->dst.dev->mtu; + dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu); + + if (!inetdev_valid_mtu(cork->fragsize)) + return -ENETUNREACH; cork->gso_size = ipc->gso_size; + cork->dst = &rt->dst; + /* We stole this route, caller should not release it. */ + *rtp = NULL; + cork->length = 0; cork->ttl = ipc->ttl; cork->tos = ipc->tos; + cork->mark = ipc->sockc.mark; cork->priority = ipc->priority; cork->transmit_time = ipc->sockc.transmit_time; cork->tx_flags = 0; @@ -1529,7 +1535,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, } skb->priority = (cork->tos != -1) ? cork->priority: sk->sk_priority; - skb->mark = sk->sk_mark; + skb->mark = cork->mark; skb->tstamp = cork->transmit_time; /* * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec @@ -1693,7 +1699,6 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, inet_sk(sk)->tos = arg->tos; - sk->sk_priority = skb->priority; sk->sk_protocol = ip_hdr(skb)->protocol; sk->sk_bound_dev_if = arg->bound_dev_if; sk->sk_sndbuf = sysctl_wmem_default; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 38c02bb62e2c..74e1d964a615 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -505,7 +505,7 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; if (skb_valid_dst(skb)) - skb_dst_update_pmtu(skb, mtu); + skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IP)) { if (!skb_is_gso(skb) && @@ -1236,10 +1236,8 @@ int ip_tunnel_init(struct net_device *dev) iph->version = 4; iph->ihl = 5; - if (tunnel->collect_md) { - dev->features |= NETIF_F_NETNS_LOCAL; + if (tunnel->collect_md) netif_keep_dst(dev); - } return 0; } EXPORT_SYMBOL_GPL(ip_tunnel_init); diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 1452a97914a0..47f8b947eef1 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -34,6 +34,9 @@ #include <net/netns/generic.h> #include <net/rtnetlink.h> #include <net/dst_metadata.h> +#include <net/geneve.h> +#include <net/vxlan.h> +#include <net/erspan.h> const struct ip_tunnel_encap_ops __rcu * iptun_encaps[MAX_IPTUN_ENCAP_OPS] __read_mostly; @@ -126,15 +129,14 @@ struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, if (!md || md->type != METADATA_IP_TUNNEL || md->u.tun_info.mode & IP_TUNNEL_INFO_TX) - return NULL; - res = metadata_dst_alloc(0, METADATA_IP_TUNNEL, flags); + src = &md->u.tun_info; + res = metadata_dst_alloc(src->options_len, METADATA_IP_TUNNEL, flags); if (!res) return NULL; dst = &res->u.tun_info; - src = &md->u.tun_info; dst->key.tun_id = src->key.tun_id; if (src->mode & IP_TUNNEL_INFO_IPV6) memcpy(&dst->key.u.ipv6.dst, &src->key.u.ipv6.src, @@ -143,6 +145,8 @@ struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, dst->key.u.ipv4.dst = src->key.u.ipv4.src; dst->key.tun_flags = src->key.tun_flags; dst->mode = src->mode | IP_TUNNEL_INFO_TX; + ip_tunnel_info_opts_set(dst, ip_tunnel_info_opts(src), + src->options_len, 0); return res; } @@ -211,30 +215,243 @@ void ip_tunnel_get_stats64(struct net_device *dev, EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64); static const struct nla_policy ip_tun_policy[LWTUNNEL_IP_MAX + 1] = { + [LWTUNNEL_IP_UNSPEC] = { .strict_start_type = LWTUNNEL_IP_OPTS }, [LWTUNNEL_IP_ID] = { .type = NLA_U64 }, [LWTUNNEL_IP_DST] = { .type = NLA_U32 }, [LWTUNNEL_IP_SRC] = { .type = NLA_U32 }, [LWTUNNEL_IP_TTL] = { .type = NLA_U8 }, [LWTUNNEL_IP_TOS] = { .type = NLA_U8 }, [LWTUNNEL_IP_FLAGS] = { .type = NLA_U16 }, + [LWTUNNEL_IP_OPTS] = { .type = NLA_NESTED }, +}; + +static const struct nla_policy ip_opts_policy[LWTUNNEL_IP_OPTS_MAX + 1] = { + [LWTUNNEL_IP_OPTS_GENEVE] = { .type = NLA_NESTED }, + [LWTUNNEL_IP_OPTS_VXLAN] = { .type = NLA_NESTED }, + [LWTUNNEL_IP_OPTS_ERSPAN] = { .type = NLA_NESTED }, +}; + +static const struct nla_policy +geneve_opt_policy[LWTUNNEL_IP_OPT_GENEVE_MAX + 1] = { + [LWTUNNEL_IP_OPT_GENEVE_CLASS] = { .type = NLA_U16 }, + [LWTUNNEL_IP_OPT_GENEVE_TYPE] = { .type = NLA_U8 }, + [LWTUNNEL_IP_OPT_GENEVE_DATA] = { .type = NLA_BINARY, .len = 128 }, +}; + +static const struct nla_policy +vxlan_opt_policy[LWTUNNEL_IP_OPT_VXLAN_MAX + 1] = { + [LWTUNNEL_IP_OPT_VXLAN_GBP] = { .type = NLA_U32 }, }; +static const struct nla_policy +erspan_opt_policy[LWTUNNEL_IP_OPT_ERSPAN_MAX + 1] = { + [LWTUNNEL_IP_OPT_ERSPAN_VER] = { .type = NLA_U8 }, + [LWTUNNEL_IP_OPT_ERSPAN_INDEX] = { .type = NLA_U32 }, + [LWTUNNEL_IP_OPT_ERSPAN_DIR] = { .type = NLA_U8 }, + [LWTUNNEL_IP_OPT_ERSPAN_HWID] = { .type = NLA_U8 }, +}; + +static int ip_tun_parse_opts_geneve(struct nlattr *attr, + struct ip_tunnel_info *info, int opts_len, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[LWTUNNEL_IP_OPT_GENEVE_MAX + 1]; + int data_len, err; + + err = nla_parse_nested(tb, LWTUNNEL_IP_OPT_GENEVE_MAX, attr, + geneve_opt_policy, extack); + if (err) + return err; + + if (!tb[LWTUNNEL_IP_OPT_GENEVE_CLASS] || + !tb[LWTUNNEL_IP_OPT_GENEVE_TYPE] || + !tb[LWTUNNEL_IP_OPT_GENEVE_DATA]) + return -EINVAL; + + attr = tb[LWTUNNEL_IP_OPT_GENEVE_DATA]; + data_len = nla_len(attr); + if (data_len % 4) + return -EINVAL; + + if (info) { + struct geneve_opt *opt = ip_tunnel_info_opts(info) + opts_len; + + memcpy(opt->opt_data, nla_data(attr), data_len); + opt->length = data_len / 4; + attr = tb[LWTUNNEL_IP_OPT_GENEVE_CLASS]; + opt->opt_class = nla_get_be16(attr); + attr = tb[LWTUNNEL_IP_OPT_GENEVE_TYPE]; + opt->type = nla_get_u8(attr); + info->key.tun_flags |= TUNNEL_GENEVE_OPT; + } + + return sizeof(struct geneve_opt) + data_len; +} + +static int ip_tun_parse_opts_vxlan(struct nlattr *attr, + struct ip_tunnel_info *info, int opts_len, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[LWTUNNEL_IP_OPT_VXLAN_MAX + 1]; + int err; + + err = nla_parse_nested(tb, LWTUNNEL_IP_OPT_VXLAN_MAX, attr, + vxlan_opt_policy, extack); + if (err) + return err; + + if (!tb[LWTUNNEL_IP_OPT_VXLAN_GBP]) + return -EINVAL; + + if (info) { + struct vxlan_metadata *md = + ip_tunnel_info_opts(info) + opts_len; + + attr = tb[LWTUNNEL_IP_OPT_VXLAN_GBP]; + md->gbp = nla_get_u32(attr); + info->key.tun_flags |= TUNNEL_VXLAN_OPT; + } + + return sizeof(struct vxlan_metadata); +} + +static int ip_tun_parse_opts_erspan(struct nlattr *attr, + struct ip_tunnel_info *info, int opts_len, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[LWTUNNEL_IP_OPT_ERSPAN_MAX + 1]; + int err; + u8 ver; + + err = nla_parse_nested(tb, LWTUNNEL_IP_OPT_ERSPAN_MAX, attr, + erspan_opt_policy, extack); + if (err) + return err; + + if (!tb[LWTUNNEL_IP_OPT_ERSPAN_VER]) + return -EINVAL; + + ver = nla_get_u8(tb[LWTUNNEL_IP_OPT_ERSPAN_VER]); + if (ver == 1) { + if (!tb[LWTUNNEL_IP_OPT_ERSPAN_INDEX]) + return -EINVAL; + } else if (ver == 2) { + if (!tb[LWTUNNEL_IP_OPT_ERSPAN_DIR] || + !tb[LWTUNNEL_IP_OPT_ERSPAN_HWID]) + return -EINVAL; + } else { + return -EINVAL; + } + + if (info) { + struct erspan_metadata *md = + ip_tunnel_info_opts(info) + opts_len; + + md->version = ver; + if (ver == 1) { + attr = tb[LWTUNNEL_IP_OPT_ERSPAN_INDEX]; + md->u.index = nla_get_be32(attr); + } else { + attr = tb[LWTUNNEL_IP_OPT_ERSPAN_DIR]; + md->u.md2.dir = nla_get_u8(attr); + attr = tb[LWTUNNEL_IP_OPT_ERSPAN_HWID]; + set_hwid(&md->u.md2, nla_get_u8(attr)); + } + + info->key.tun_flags |= TUNNEL_ERSPAN_OPT; + } + + return sizeof(struct erspan_metadata); +} + +static int ip_tun_parse_opts(struct nlattr *attr, struct ip_tunnel_info *info, + struct netlink_ext_ack *extack) +{ + int err, rem, opt_len, opts_len = 0, type = 0; + struct nlattr *nla; + + if (!attr) + return 0; + + err = nla_validate(nla_data(attr), nla_len(attr), LWTUNNEL_IP_OPTS_MAX, + ip_opts_policy, extack); + if (err) + return err; + + nla_for_each_attr(nla, nla_data(attr), nla_len(attr), rem) { + switch (nla_type(nla)) { + case LWTUNNEL_IP_OPTS_GENEVE: + if (type && type != TUNNEL_GENEVE_OPT) + return -EINVAL; + opt_len = ip_tun_parse_opts_geneve(nla, info, opts_len, + extack); + if (opt_len < 0) + return opt_len; + opts_len += opt_len; + if (opts_len > IP_TUNNEL_OPTS_MAX) + return -EINVAL; + type = TUNNEL_GENEVE_OPT; + break; + case LWTUNNEL_IP_OPTS_VXLAN: + if (type) + return -EINVAL; + opt_len = ip_tun_parse_opts_vxlan(nla, info, opts_len, + extack); + if (opt_len < 0) + return opt_len; + opts_len += opt_len; + type = TUNNEL_VXLAN_OPT; + break; + case LWTUNNEL_IP_OPTS_ERSPAN: + if (type) + return -EINVAL; + opt_len = ip_tun_parse_opts_erspan(nla, info, opts_len, + extack); + if (opt_len < 0) + return opt_len; + opts_len += opt_len; + type = TUNNEL_ERSPAN_OPT; + break; + default: + return -EINVAL; + } + } + + return opts_len; +} + +static int ip_tun_get_optlen(struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + return ip_tun_parse_opts(attr, NULL, extack); +} + +static int ip_tun_set_opts(struct nlattr *attr, struct ip_tunnel_info *info, + struct netlink_ext_ack *extack) +{ + return ip_tun_parse_opts(attr, info, extack); +} + static int ip_tun_build_state(struct nlattr *attr, unsigned int family, const void *cfg, struct lwtunnel_state **ts, struct netlink_ext_ack *extack) { - struct ip_tunnel_info *tun_info; - struct lwtunnel_state *new_state; struct nlattr *tb[LWTUNNEL_IP_MAX + 1]; - int err; + struct lwtunnel_state *new_state; + struct ip_tunnel_info *tun_info; + int err, opt_len; err = nla_parse_nested_deprecated(tb, LWTUNNEL_IP_MAX, attr, ip_tun_policy, extack); if (err < 0) return err; - new_state = lwtunnel_state_alloc(sizeof(*tun_info)); + opt_len = ip_tun_get_optlen(tb[LWTUNNEL_IP_OPTS], extack); + if (opt_len < 0) + return opt_len; + + new_state = lwtunnel_state_alloc(sizeof(*tun_info) + opt_len); if (!new_state) return -ENOMEM; @@ -242,6 +459,12 @@ static int ip_tun_build_state(struct nlattr *attr, tun_info = lwt_tun_info(new_state); + err = ip_tun_set_opts(tb[LWTUNNEL_IP_OPTS], tun_info, extack); + if (err < 0) { + lwtstate_free(new_state); + return err; + } + #ifdef CONFIG_DST_CACHE err = dst_cache_init(&tun_info->dst_cache, GFP_KERNEL); if (err) { @@ -266,10 +489,12 @@ static int ip_tun_build_state(struct nlattr *attr, tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP_TOS]); if (tb[LWTUNNEL_IP_FLAGS]) - tun_info->key.tun_flags = nla_get_be16(tb[LWTUNNEL_IP_FLAGS]); + tun_info->key.tun_flags |= + (nla_get_be16(tb[LWTUNNEL_IP_FLAGS]) & + ~TUNNEL_OPTIONS_PRESENT); tun_info->mode = IP_TUNNEL_INFO_TX; - tun_info->options_len = 0; + tun_info->options_len = opt_len; *ts = new_state; @@ -285,6 +510,114 @@ static void ip_tun_destroy_state(struct lwtunnel_state *lwtstate) #endif } +static int ip_tun_fill_encap_opts_geneve(struct sk_buff *skb, + struct ip_tunnel_info *tun_info) +{ + struct geneve_opt *opt; + struct nlattr *nest; + int offset = 0; + + nest = nla_nest_start_noflag(skb, LWTUNNEL_IP_OPTS_GENEVE); + if (!nest) + return -ENOMEM; + + while (tun_info->options_len > offset) { + opt = ip_tunnel_info_opts(tun_info) + offset; + if (nla_put_be16(skb, LWTUNNEL_IP_OPT_GENEVE_CLASS, + opt->opt_class) || + nla_put_u8(skb, LWTUNNEL_IP_OPT_GENEVE_TYPE, opt->type) || + nla_put(skb, LWTUNNEL_IP_OPT_GENEVE_DATA, opt->length * 4, + opt->opt_data)) { + nla_nest_cancel(skb, nest); + return -ENOMEM; + } + offset += sizeof(*opt) + opt->length * 4; + } + + nla_nest_end(skb, nest); + return 0; +} + +static int ip_tun_fill_encap_opts_vxlan(struct sk_buff *skb, + struct ip_tunnel_info *tun_info) +{ + struct vxlan_metadata *md; + struct nlattr *nest; + + nest = nla_nest_start_noflag(skb, LWTUNNEL_IP_OPTS_VXLAN); + if (!nest) + return -ENOMEM; + + md = ip_tunnel_info_opts(tun_info); + if (nla_put_u32(skb, LWTUNNEL_IP_OPT_VXLAN_GBP, md->gbp)) { + nla_nest_cancel(skb, nest); + return -ENOMEM; + } + + nla_nest_end(skb, nest); + return 0; +} + +static int ip_tun_fill_encap_opts_erspan(struct sk_buff *skb, + struct ip_tunnel_info *tun_info) +{ + struct erspan_metadata *md; + struct nlattr *nest; + + nest = nla_nest_start_noflag(skb, LWTUNNEL_IP_OPTS_ERSPAN); + if (!nest) + return -ENOMEM; + + md = ip_tunnel_info_opts(tun_info); + if (nla_put_u8(skb, LWTUNNEL_IP_OPT_ERSPAN_VER, md->version)) + goto err; + + if (md->version == 1 && + nla_put_be32(skb, LWTUNNEL_IP_OPT_ERSPAN_INDEX, md->u.index)) + goto err; + + if (md->version == 2 && + (nla_put_u8(skb, LWTUNNEL_IP_OPT_ERSPAN_DIR, md->u.md2.dir) || + nla_put_u8(skb, LWTUNNEL_IP_OPT_ERSPAN_HWID, + get_hwid(&md->u.md2)))) + goto err; + + nla_nest_end(skb, nest); + return 0; +err: + nla_nest_cancel(skb, nest); + return -ENOMEM; +} + +static int ip_tun_fill_encap_opts(struct sk_buff *skb, int type, + struct ip_tunnel_info *tun_info) +{ + struct nlattr *nest; + int err = 0; + + if (!(tun_info->key.tun_flags & TUNNEL_OPTIONS_PRESENT)) + return 0; + + nest = nla_nest_start_noflag(skb, type); + if (!nest) + return -ENOMEM; + + if (tun_info->key.tun_flags & TUNNEL_GENEVE_OPT) + err = ip_tun_fill_encap_opts_geneve(skb, tun_info); + else if (tun_info->key.tun_flags & TUNNEL_VXLAN_OPT) + err = ip_tun_fill_encap_opts_vxlan(skb, tun_info); + else if (tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT) + err = ip_tun_fill_encap_opts_erspan(skb, tun_info); + + if (err) { + nla_nest_cancel(skb, nest); + return err; + } + + nla_nest_end(skb, nest); + return 0; +} + static int ip_tun_fill_encap_info(struct sk_buff *skb, struct lwtunnel_state *lwtstate) { @@ -296,12 +629,52 @@ static int ip_tun_fill_encap_info(struct sk_buff *skb, nla_put_in_addr(skb, LWTUNNEL_IP_SRC, tun_info->key.u.ipv4.src) || nla_put_u8(skb, LWTUNNEL_IP_TOS, tun_info->key.tos) || nla_put_u8(skb, LWTUNNEL_IP_TTL, tun_info->key.ttl) || - nla_put_be16(skb, LWTUNNEL_IP_FLAGS, tun_info->key.tun_flags)) + nla_put_be16(skb, LWTUNNEL_IP_FLAGS, tun_info->key.tun_flags) || + ip_tun_fill_encap_opts(skb, LWTUNNEL_IP_OPTS, tun_info)) return -ENOMEM; return 0; } +static int ip_tun_opts_nlsize(struct ip_tunnel_info *info) +{ + int opt_len; + + if (!(info->key.tun_flags & TUNNEL_OPTIONS_PRESENT)) + return 0; + + opt_len = nla_total_size(0); /* LWTUNNEL_IP_OPTS */ + if (info->key.tun_flags & TUNNEL_GENEVE_OPT) { + struct geneve_opt *opt; + int offset = 0; + + opt_len += nla_total_size(0); /* LWTUNNEL_IP_OPTS_GENEVE */ + while (info->options_len > offset) { + opt = ip_tunnel_info_opts(info) + offset; + opt_len += nla_total_size(2) /* OPT_GENEVE_CLASS */ + + nla_total_size(1) /* OPT_GENEVE_TYPE */ + + nla_total_size(opt->length * 4); + /* OPT_GENEVE_DATA */ + offset += sizeof(*opt) + opt->length * 4; + } + } else if (info->key.tun_flags & TUNNEL_VXLAN_OPT) { + opt_len += nla_total_size(0) /* LWTUNNEL_IP_OPTS_VXLAN */ + + nla_total_size(4); /* OPT_VXLAN_GBP */ + } else if (info->key.tun_flags & TUNNEL_ERSPAN_OPT) { + struct erspan_metadata *md = ip_tunnel_info_opts(info); + + opt_len += nla_total_size(0) /* LWTUNNEL_IP_OPTS_ERSPAN */ + + nla_total_size(1) /* OPT_ERSPAN_VER */ + + (md->version == 1 ? nla_total_size(4) + /* OPT_ERSPAN_INDEX (v1) */ + : nla_total_size(1) + + nla_total_size(1)); + /* OPT_ERSPAN_DIR + HWID (v2) */ + } + + return opt_len; +} + static int ip_tun_encap_nlsize(struct lwtunnel_state *lwtstate) { return nla_total_size_64bit(8) /* LWTUNNEL_IP_ID */ @@ -309,13 +682,21 @@ static int ip_tun_encap_nlsize(struct lwtunnel_state *lwtstate) + nla_total_size(4) /* LWTUNNEL_IP_SRC */ + nla_total_size(1) /* LWTUNNEL_IP_TOS */ + nla_total_size(1) /* LWTUNNEL_IP_TTL */ - + nla_total_size(2); /* LWTUNNEL_IP_FLAGS */ + + nla_total_size(2) /* LWTUNNEL_IP_FLAGS */ + + ip_tun_opts_nlsize(lwt_tun_info(lwtstate)); + /* LWTUNNEL_IP_OPTS */ } static int ip_tun_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b) { - return memcmp(lwt_tun_info(a), lwt_tun_info(b), - sizeof(struct ip_tunnel_info)); + struct ip_tunnel_info *info_a = lwt_tun_info(a); + struct ip_tunnel_info *info_b = lwt_tun_info(b); + + return memcmp(info_a, info_b, sizeof(info_a->key)) || + info_a->mode != info_b->mode || + info_a->options_len != info_b->options_len || + memcmp(ip_tunnel_info_opts(info_a), + ip_tunnel_info_opts(info_b), info_a->options_len); } static const struct lwtunnel_encap_ops ip_tun_lwt_ops = { @@ -328,12 +709,14 @@ static const struct lwtunnel_encap_ops ip_tun_lwt_ops = { }; static const struct nla_policy ip6_tun_policy[LWTUNNEL_IP6_MAX + 1] = { + [LWTUNNEL_IP6_UNSPEC] = { .strict_start_type = LWTUNNEL_IP6_OPTS }, [LWTUNNEL_IP6_ID] = { .type = NLA_U64 }, [LWTUNNEL_IP6_DST] = { .len = sizeof(struct in6_addr) }, [LWTUNNEL_IP6_SRC] = { .len = sizeof(struct in6_addr) }, [LWTUNNEL_IP6_HOPLIMIT] = { .type = NLA_U8 }, [LWTUNNEL_IP6_TC] = { .type = NLA_U8 }, [LWTUNNEL_IP6_FLAGS] = { .type = NLA_U16 }, + [LWTUNNEL_IP6_OPTS] = { .type = NLA_NESTED }, }; static int ip6_tun_build_state(struct nlattr *attr, @@ -341,17 +724,21 @@ static int ip6_tun_build_state(struct nlattr *attr, struct lwtunnel_state **ts, struct netlink_ext_ack *extack) { - struct ip_tunnel_info *tun_info; - struct lwtunnel_state *new_state; struct nlattr *tb[LWTUNNEL_IP6_MAX + 1]; - int err; + struct lwtunnel_state *new_state; + struct ip_tunnel_info *tun_info; + int err, opt_len; err = nla_parse_nested_deprecated(tb, LWTUNNEL_IP6_MAX, attr, ip6_tun_policy, extack); if (err < 0) return err; - new_state = lwtunnel_state_alloc(sizeof(*tun_info)); + opt_len = ip_tun_get_optlen(tb[LWTUNNEL_IP6_OPTS], extack); + if (opt_len < 0) + return opt_len; + + new_state = lwtunnel_state_alloc(sizeof(*tun_info) + opt_len); if (!new_state) return -ENOMEM; @@ -359,6 +746,12 @@ static int ip6_tun_build_state(struct nlattr *attr, tun_info = lwt_tun_info(new_state); + err = ip_tun_set_opts(tb[LWTUNNEL_IP6_OPTS], tun_info, extack); + if (err < 0) { + lwtstate_free(new_state); + return err; + } + if (tb[LWTUNNEL_IP6_ID]) tun_info->key.tun_id = nla_get_be64(tb[LWTUNNEL_IP6_ID]); @@ -375,10 +768,12 @@ static int ip6_tun_build_state(struct nlattr *attr, tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP6_TC]); if (tb[LWTUNNEL_IP6_FLAGS]) - tun_info->key.tun_flags = nla_get_be16(tb[LWTUNNEL_IP6_FLAGS]); + tun_info->key.tun_flags |= + (nla_get_be16(tb[LWTUNNEL_IP6_FLAGS]) & + ~TUNNEL_OPTIONS_PRESENT); tun_info->mode = IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_IPV6; - tun_info->options_len = 0; + tun_info->options_len = opt_len; *ts = new_state; @@ -396,7 +791,8 @@ static int ip6_tun_fill_encap_info(struct sk_buff *skb, nla_put_in6_addr(skb, LWTUNNEL_IP6_SRC, &tun_info->key.u.ipv6.src) || nla_put_u8(skb, LWTUNNEL_IP6_TC, tun_info->key.tos) || nla_put_u8(skb, LWTUNNEL_IP6_HOPLIMIT, tun_info->key.ttl) || - nla_put_be16(skb, LWTUNNEL_IP6_FLAGS, tun_info->key.tun_flags)) + nla_put_be16(skb, LWTUNNEL_IP6_FLAGS, tun_info->key.tun_flags) || + ip_tun_fill_encap_opts(skb, LWTUNNEL_IP6_OPTS, tun_info)) return -ENOMEM; return 0; @@ -409,7 +805,9 @@ static int ip6_tun_encap_nlsize(struct lwtunnel_state *lwtstate) + nla_total_size(16) /* LWTUNNEL_IP6_SRC */ + nla_total_size(1) /* LWTUNNEL_IP6_HOPLIMIT */ + nla_total_size(1) /* LWTUNNEL_IP6_TC */ - + nla_total_size(2); /* LWTUNNEL_IP6_FLAGS */ + + nla_total_size(2) /* LWTUNNEL_IP6_FLAGS */ + + ip_tun_opts_nlsize(lwt_tun_info(lwtstate)); + /* LWTUNNEL_IP6_OPTS */ } static const struct lwtunnel_encap_ops ip6_tun_lwt_ops = { diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index cfb025606793..37cddd18f282 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -187,8 +187,17 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, int mtu; if (!dst) { - dev->stats.tx_carrier_errors++; - goto tx_error_icmp; + struct rtable *rt; + + fl->u.ip4.flowi4_oif = dev->ifindex; + fl->u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC; + rt = __ip_route_output_key(dev_net(dev), &fl->u.ip4); + if (IS_ERR(rt)) { + dev->stats.tx_carrier_errors++; + goto tx_error_icmp; + } + dst = &rt->dst; + skb_dst_set(skb, dst); } dst_hold(dst); @@ -214,7 +223,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, mtu = dst_mtu(dst); if (skb->len > mtu) { - skb_dst_update_pmtu(skb, mtu); + skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IP)) { icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); @@ -580,8 +589,8 @@ static const struct nla_policy vti_policy[IFLA_VTI_MAX + 1] = { [IFLA_VTI_LINK] = { .type = NLA_U32 }, [IFLA_VTI_IKEY] = { .type = NLA_U32 }, [IFLA_VTI_OKEY] = { .type = NLA_U32 }, - [IFLA_VTI_LOCAL] = { .len = FIELD_SIZEOF(struct iphdr, saddr) }, - [IFLA_VTI_REMOTE] = { .len = FIELD_SIZEOF(struct iphdr, daddr) }, + [IFLA_VTI_LOCAL] = { .len = sizeof_field(struct iphdr, saddr) }, + [IFLA_VTI_REMOTE] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_VTI_FWMARK] = { .type = NLA_U32 }, }; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 9bcca08efec9..4438f6b12335 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -1334,7 +1334,7 @@ static int __init ipconfig_proc_net_init(void) /* Create a new file under /proc/net/ipconfig */ static int ipconfig_proc_net_create(const char *name, - const struct file_operations *fops) + const struct proc_ops *proc_ops) { char *pname; struct proc_dir_entry *p; @@ -1346,7 +1346,7 @@ static int ipconfig_proc_net_create(const char *name, if (!pname) return -ENOMEM; - p = proc_create(pname, 0444, init_net.proc_net, fops); + p = proc_create(pname, 0444, init_net.proc_net, proc_ops); kfree(pname); if (!p) return -ENOMEM; @@ -1355,7 +1355,7 @@ static int ipconfig_proc_net_create(const char *name, } /* Write NTP server IP addresses to /proc/net/ipconfig/ntp_servers */ -static int ntp_servers_seq_show(struct seq_file *seq, void *v) +static int ntp_servers_show(struct seq_file *seq, void *v) { int i; @@ -1365,7 +1365,7 @@ static int ntp_servers_seq_show(struct seq_file *seq, void *v) } return 0; } -DEFINE_SHOW_ATTRIBUTE(ntp_servers_seq); +DEFINE_PROC_SHOW_ATTRIBUTE(ntp_servers); #endif /* CONFIG_PROC_FS */ /* @@ -1412,6 +1412,9 @@ static int __init wait_for_devices(void) struct net_device *dev; int found = 0; + /* make sure deferred device probes are finished */ + wait_for_device_probe(); + rtnl_lock(); for_each_netdev(&init_net, dev) { if (ic_is_init_dev(dev)) { @@ -1453,7 +1456,7 @@ static int __init ip_auto_config(void) proc_create_single("pnp", 0444, init_net.proc_net, pnp_seq_show); if (ipconfig_proc_net_init() == 0) - ipconfig_proc_net_create("ntp_servers", &ntp_servers_seq_fops); + ipconfig_proc_net_create("ntp_servers", &ntp_servers_proc_ops); #endif /* CONFIG_PROC_FS */ if (!ic_enable) @@ -1483,10 +1486,10 @@ static int __init ip_auto_config(void) * missing values. */ if (ic_myaddr == NONE || -#ifdef CONFIG_ROOT_NFS +#if defined(CONFIG_ROOT_NFS) || defined(CONFIG_CIFS_ROOT) (root_server_addr == NONE && ic_servaddr == NONE && - ROOT_DEV == Root_NFS) || + (ROOT_DEV == Root_NFS || ROOT_DEV == Root_CIFS)) || #endif ic_first_dev->next) { #ifdef IPCONFIG_DYNAMIC @@ -1513,6 +1516,12 @@ static int __init ip_auto_config(void) goto try_try_again; } #endif +#ifdef CONFIG_CIFS_ROOT + if (ROOT_DEV == Root_CIFS) { + pr_err("IP-Config: Retrying forever (CIFS root)...\n"); + goto try_try_again; + } +#endif if (--retries) { pr_err("IP-Config: Reopening network devices...\n"); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index c07bc82cbbe9..6e68def66822 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -278,9 +278,10 @@ static void __net_exit ipmr_rules_exit(struct net *net) rtnl_unlock(); } -static int ipmr_rules_dump(struct net *net, struct notifier_block *nb) +static int ipmr_rules_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { - return fib_rules_dump(net, nb, RTNL_FAMILY_IPMR); + return fib_rules_dump(net, nb, RTNL_FAMILY_IPMR, extack); } static unsigned int ipmr_rules_seq_read(struct net *net) @@ -336,7 +337,8 @@ static void __net_exit ipmr_rules_exit(struct net *net) rtnl_unlock(); } -static int ipmr_rules_dump(struct net *net, struct notifier_block *nb) +static int ipmr_rules_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { return 0; } @@ -1134,8 +1136,8 @@ static int ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, if (!found) { /* Create a new entry if allowable */ - if (atomic_read(&mrt->cache_resolve_queue_len) >= 10 || - (c = ipmr_cache_alloc_unres()) == NULL) { + c = ipmr_cache_alloc_unres(); + if (!c) { spin_unlock_bh(&mfc_unres_lock); kfree_skb(skb); @@ -1794,7 +1796,7 @@ static void ip_encap(struct net *net, struct sk_buff *skb, ip_send_check(iph); memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); - nf_reset(skb); + nf_reset_ct(skb); } static inline int ipmr_forward_finish(struct net *net, struct sock *sk, @@ -2140,7 +2142,7 @@ int ip_mr_input(struct sk_buff *skb) mroute_sk = rcu_dereference(mrt->mroute_sk); if (mroute_sk) { - nf_reset(skb); + nf_reset_ct(skb); raw_rcv(mroute_sk, skb); return 0; } @@ -2289,7 +2291,8 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb, rcu_read_unlock(); return -ENODEV; } - skb2 = skb_clone(skb, GFP_ATOMIC); + + skb2 = skb_realloc_headroom(skb, sizeof(struct iphdr)); if (!skb2) { read_unlock(&mrt_lock); rcu_read_unlock(); @@ -3040,10 +3043,11 @@ static unsigned int ipmr_seq_read(struct net *net) return net->ipv4.ipmr_seq + ipmr_rules_seq_read(net); } -static int ipmr_dump(struct net *net, struct notifier_block *nb) +static int ipmr_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { return mr_dump(net, nb, RTNL_FAMILY_IPMR, ipmr_rules_dump, - ipmr_mr_table_iter, &mrt_lock); + ipmr_mr_table_iter, &mrt_lock, extack); } static const struct fib_notifier_ops ipmr_notifier_ops_template = { diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c index ea48bd15a575..aa8738a91210 100644 --- a/net/ipv4/ipmr_base.c +++ b/net/ipv4/ipmr_base.c @@ -386,15 +386,17 @@ EXPORT_SYMBOL(mr_rtm_dumproute); int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, int (*rules_dump)(struct net *net, - struct notifier_block *nb), + struct notifier_block *nb, + struct netlink_ext_ack *extack), struct mr_table *(*mr_iter)(struct net *net, struct mr_table *mrt), - rwlock_t *mrt_lock) + rwlock_t *mrt_lock, + struct netlink_ext_ack *extack) { struct mr_table *mrt; int err; - err = rules_dump(net, nb); + err = rules_dump(net, nb, extack); if (err) return err; @@ -409,17 +411,25 @@ int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, if (!v->dev) continue; - mr_call_vif_notifier(nb, net, family, - FIB_EVENT_VIF_ADD, - v, vifi, mrt->id); + err = mr_call_vif_notifier(nb, family, + FIB_EVENT_VIF_ADD, + v, vifi, mrt->id, extack); + if (err) + break; } read_unlock(mrt_lock); + if (err) + return err; + /* Notify on table MFC entries */ - list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) - mr_call_mfc_notifier(nb, net, family, - FIB_EVENT_ENTRY_ADD, - mfc, mrt->id); + list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) { + err = mr_call_mfc_notifier(nb, family, + FIB_EVENT_ENTRY_ADD, + mfc, mrt->id, extack); + if (err) + return err; + } } return 0; diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 69e76d677f9e..f17b402111ce 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -272,7 +272,7 @@ config IP_NF_TARGET_CLUSTERIP The CLUSTERIP target allows you to build load-balancing clusters of network servers without having a dedicated load-balancing router/server/switch. - + To compile it as a module, choose M here. If unsure, say N. config IP_NF_TARGET_ECN @@ -281,7 +281,7 @@ config IP_NF_TARGET_ECN depends on NETFILTER_ADVANCED ---help--- This option adds a `ECN' target, which can be used in the iptables mangle - table. + table. You can use this target to remove the ECN bits from the IPv4 header of an IP packet. This is particularly useful, if you need to work around @@ -306,7 +306,7 @@ config IP_NF_RAW This option adds a `raw' table to iptables. This table is the very first in the netfilter framework and hooks in at the PREROUTING and OUTPUT chains. - + If you want to compile it as a module, say M here and read <file:Documentation/kbuild/modules.rst>. If unsure, say `N'. @@ -318,7 +318,7 @@ config IP_NF_SECURITY help This option adds a `security' table to iptables, for use with Mandatory Access Control (MAC) policy. - + If unsure, say N. endif # IP_NF_IPTABLES diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index c50e0ec095d2..7c497c78105f 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -31,7 +31,7 @@ obj-$(CONFIG_NFT_DUP_IPV4) += nft_dup_ipv4.o # flow table support obj-$(CONFIG_NF_FLOW_TABLE_IPV4) += nf_flow_table_ipv4.o -# generic IP tables +# generic IP tables obj-$(CONFIG_IP_NF_IPTABLES) += ip_tables.o # the three instances of ip_tables diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 214154b47d56..f1f78a742b36 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -384,10 +384,11 @@ next: ; return 1; } -static inline int check_target(struct arpt_entry *e, const char *name) +static int check_target(struct arpt_entry *e, struct net *net, const char *name) { struct xt_entry_target *t = arpt_get_target(e); struct xt_tgchk_param par = { + .net = net, .table = name, .entryinfo = e, .target = t->u.kernel.target, @@ -399,8 +400,9 @@ static inline int check_target(struct arpt_entry *e, const char *name) return xt_check_target(&par, t->u.target_size - sizeof(*t), 0, false); } -static inline int -find_check_entry(struct arpt_entry *e, const char *name, unsigned int size, +static int +find_check_entry(struct arpt_entry *e, struct net *net, const char *name, + unsigned int size, struct xt_percpu_counter_alloc_state *alloc_state) { struct xt_entry_target *t; @@ -419,7 +421,7 @@ find_check_entry(struct arpt_entry *e, const char *name, unsigned int size, } t->u.kernel.target = target; - ret = check_target(e, name); + ret = check_target(e, net, name); if (ret) goto err; return 0; @@ -494,12 +496,13 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e, return 0; } -static inline void cleanup_entry(struct arpt_entry *e) +static void cleanup_entry(struct arpt_entry *e, struct net *net) { struct xt_tgdtor_param par; struct xt_entry_target *t; t = arpt_get_target(e); + par.net = net; par.target = t->u.kernel.target; par.targinfo = t->data; par.family = NFPROTO_ARP; @@ -512,7 +515,9 @@ static inline void cleanup_entry(struct arpt_entry *e) /* Checks and translates the user-supplied table segment (held in * newinfo). */ -static int translate_table(struct xt_table_info *newinfo, void *entry0, +static int translate_table(struct net *net, + struct xt_table_info *newinfo, + void *entry0, const struct arpt_replace *repl) { struct xt_percpu_counter_alloc_state alloc_state = { 0 }; @@ -569,7 +574,7 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0, /* Finally, each sanity check must pass */ i = 0; xt_entry_foreach(iter, entry0, newinfo->size) { - ret = find_check_entry(iter, repl->name, repl->size, + ret = find_check_entry(iter, net, repl->name, repl->size, &alloc_state); if (ret != 0) break; @@ -580,7 +585,7 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0, xt_entry_foreach(iter, entry0, newinfo->size) { if (i-- == 0) break; - cleanup_entry(iter); + cleanup_entry(iter, net); } return ret; } @@ -923,7 +928,7 @@ static int __do_replace(struct net *net, const char *name, /* Decrease module usage counts and free resource */ loc_cpu_old_entry = oldinfo->entries; xt_entry_foreach(iter, loc_cpu_old_entry, oldinfo->size) - cleanup_entry(iter); + cleanup_entry(iter, net); xt_free_table_info(oldinfo); if (copy_to_user(counters_ptr, counters, @@ -974,7 +979,7 @@ static int do_replace(struct net *net, const void __user *user, goto free_newinfo; } - ret = translate_table(newinfo, loc_cpu_entry, &tmp); + ret = translate_table(net, newinfo, loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; @@ -986,7 +991,7 @@ static int do_replace(struct net *net, const void __user *user, free_newinfo_untrans: xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) - cleanup_entry(iter); + cleanup_entry(iter, net); free_newinfo: xt_free_table_info(newinfo); return ret; @@ -1149,7 +1154,8 @@ compat_copy_entry_from_user(struct compat_arpt_entry *e, void **dstptr, } } -static int translate_compat_table(struct xt_table_info **pinfo, +static int translate_compat_table(struct net *net, + struct xt_table_info **pinfo, void **pentry0, const struct compat_arpt_replace *compatr) { @@ -1217,7 +1223,7 @@ static int translate_compat_table(struct xt_table_info **pinfo, repl.num_counters = 0; repl.counters = NULL; repl.size = newinfo->size; - ret = translate_table(newinfo, entry1, &repl); + ret = translate_table(net, newinfo, entry1, &repl); if (ret) goto free_newinfo; @@ -1270,7 +1276,7 @@ static int compat_do_replace(struct net *net, void __user *user, goto free_newinfo; } - ret = translate_compat_table(&newinfo, &loc_cpu_entry, &tmp); + ret = translate_compat_table(net, &newinfo, &loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; @@ -1282,7 +1288,7 @@ static int compat_do_replace(struct net *net, void __user *user, free_newinfo_untrans: xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) - cleanup_entry(iter); + cleanup_entry(iter, net); free_newinfo: xt_free_table_info(newinfo); return ret; @@ -1509,7 +1515,7 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len return ret; } -static void __arpt_unregister_table(struct xt_table *table) +static void __arpt_unregister_table(struct net *net, struct xt_table *table) { struct xt_table_info *private; void *loc_cpu_entry; @@ -1521,7 +1527,7 @@ static void __arpt_unregister_table(struct xt_table *table) /* Decrease module usage counts and free resources */ loc_cpu_entry = private->entries; xt_entry_foreach(iter, loc_cpu_entry, private->size) - cleanup_entry(iter); + cleanup_entry(iter, net); if (private->number > private->initial_entries) module_put(table_owner); xt_free_table_info(private); @@ -1546,7 +1552,7 @@ int arpt_register_table(struct net *net, loc_cpu_entry = newinfo->entries; memcpy(loc_cpu_entry, repl->entries, repl->size); - ret = translate_table(newinfo, loc_cpu_entry, repl); + ret = translate_table(net, newinfo, loc_cpu_entry, repl); if (ret != 0) goto out_free; @@ -1561,7 +1567,7 @@ int arpt_register_table(struct net *net, ret = nf_register_net_hooks(net, ops, hweight32(table->valid_hooks)); if (ret != 0) { - __arpt_unregister_table(new_table); + __arpt_unregister_table(net, new_table); *res = NULL; } @@ -1576,7 +1582,7 @@ void arpt_unregister_table(struct net *net, struct xt_table *table, const struct nf_hook_ops *ops) { nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks)); - __arpt_unregister_table(table); + __arpt_unregister_table(net, table); } /* The built-in targets: standard (NULL) and error. */ diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 6bdb1ab8af61..f8755a4ae9d4 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -58,7 +58,7 @@ struct clusterip_config { }; #ifdef CONFIG_PROC_FS -static const struct file_operations clusterip_proc_fops; +static const struct proc_ops clusterip_proc_ops; #endif struct clusterip_net { @@ -280,7 +280,7 @@ clusterip_config_init(struct net *net, const struct ipt_clusterip_tgt_info *i, mutex_lock(&cn->mutex); c->pde = proc_create_data(buffer, 0600, cn->procdir, - &clusterip_proc_fops, c); + &clusterip_proc_ops, c); mutex_unlock(&cn->mutex); if (!c->pde) { err = -ENOMEM; @@ -804,12 +804,12 @@ static ssize_t clusterip_proc_write(struct file *file, const char __user *input, return size; } -static const struct file_operations clusterip_proc_fops = { - .open = clusterip_proc_open, - .read = seq_read, - .write = clusterip_proc_write, - .llseek = seq_lseek, - .release = clusterip_proc_release, +static const struct proc_ops clusterip_proc_ops = { + .proc_open = clusterip_proc_open, + .proc_read = seq_read, + .proc_write = clusterip_proc_write, + .proc_lseek = seq_lseek, + .proc_release = clusterip_proc_release, }; #endif /* CONFIG_PROC_FS */ diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index 0e70f3f65f6f..748dc3ce58d3 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -36,8 +36,8 @@ synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par) opts.options |= XT_SYNPROXY_OPT_ECN; opts.options &= info->options; - opts.mss_encode = opts.mss; - opts.mss = info->mss; + opts.mss_encode = opts.mss_option; + opts.mss_option = info->mss; if (opts.options & XT_SYNPROXY_OPT_TIMESTAMP) synproxy_init_timestamp_cookie(info, &opts); else diff --git a/net/ipv4/netfilter/nf_dup_ipv4.c b/net/ipv4/netfilter/nf_dup_ipv4.c index af3fbf76dbd3..6cc5743c553a 100644 --- a/net/ipv4/netfilter/nf_dup_ipv4.c +++ b/net/ipv4/netfilter/nf_dup_ipv4.c @@ -65,7 +65,7 @@ void nf_dup_ipv4(struct net *net, struct sk_buff *skb, unsigned int hooknum, #if IS_ENABLED(CONFIG_NF_CONNTRACK) /* Avoid counting cloned packets towards the original connection. */ - nf_reset(skb); + nf_reset_ct(skb); nf_ct_set(skb, NULL, IP_CT_UNTRACKED); #endif /* diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c index 012c4047c788..e32e41b99f0f 100644 --- a/net/ipv4/netfilter/nf_flow_table_ipv4.c +++ b/net/ipv4/netfilter/nf_flow_table_ipv4.c @@ -9,6 +9,8 @@ static struct nf_flowtable_type flowtable_ipv4 = { .family = NFPROTO_IPV4, .init = nf_flow_table_init, + .setup = nf_flow_table_offload_setup, + .action = nf_flow_rule_route_ipv4, .free = nf_flow_table_free, .hook = nf_flow_offload_ip_hook, .owner = THIS_MODULE, diff --git a/net/ipv4/netfilter/nf_socket_ipv4.c b/net/ipv4/netfilter/nf_socket_ipv4.c index 36a28d46149c..c94445b44d8c 100644 --- a/net/ipv4/netfilter/nf_socket_ipv4.c +++ b/net/ipv4/netfilter/nf_socket_ipv4.c @@ -31,16 +31,8 @@ extract_icmp4_fields(const struct sk_buff *skb, u8 *protocol, if (icmph == NULL) return 1; - switch (icmph->type) { - case ICMP_DEST_UNREACH: - case ICMP_SOURCE_QUENCH: - case ICMP_REDIRECT: - case ICMP_TIME_EXCEEDED: - case ICMP_PARAMETERPROB: - break; - default: + if (!icmp_is_err(icmph->type)) return 1; - } inside_iph = skb_header_pointer(skb, outside_hdrlen + sizeof(struct icmphdr), diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 5fe5a3981d43..d072c326dd64 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -23,7 +23,6 @@ static void remove_nexthop(struct net *net, struct nexthop *nh, #define NH_DEV_HASHSIZE (1U << NH_DEV_HASHBITS) static const struct nla_policy rtm_nh_policy[NHA_MAX + 1] = { - [NHA_UNSPEC] = { .strict_start_type = NHA_UNSPEC + 1 }, [NHA_ID] = { .type = NLA_U32 }, [NHA_GROUP] = { .type = NLA_BINARY }, [NHA_GROUP_TYPE] = { .type = NLA_U16 }, @@ -322,7 +321,9 @@ static size_t nh_nlmsg_size_single(struct nexthop *nh) static size_t nh_nlmsg_size(struct nexthop *nh) { - size_t sz = nla_total_size(4); /* NHA_ID */ + size_t sz = NLMSG_ALIGN(sizeof(struct nhmsg)); + + sz += nla_total_size(4); /* NHA_ID */ if (nh->is_group) sz += nh_nlmsg_size_grp(nh); @@ -1151,7 +1152,7 @@ static int nh_create_ipv4(struct net *net, struct nexthop *nh, .fc_encap_type = cfg->nh_encap_type, }; u32 tb_id = l3mdev_fib_table(cfg->dev); - int err = -EINVAL; + int err; err = fib_nh_init(net, fib_nh, &fib_cfg, 1, extack); if (err) { diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 9d24ef5c5d8f..535427292194 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -781,7 +781,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } else if (!ipc.oif) ipc.oif = inet->uc_index; - flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos, + flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, RT_SCOPE_UNIVERSE, sk->sk_protocol, inet_sk_flowi_flags(sk), faddr, saddr, 0, 0, sk->sk_uid); diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index cc90243ccf76..2580303249e2 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -289,6 +289,8 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPRcvQDrop", LINUX_MIB_TCPRCVQDROP), SNMP_MIB_ITEM("TCPWqueueTooBig", LINUX_MIB_TCPWQUEUETOOBIG), SNMP_MIB_ITEM("TCPFastOpenPassiveAltKey", LINUX_MIB_TCPFASTOPENPASSIVEALTKEY), + SNMP_MIB_ITEM("TcpTimeoutRehash", LINUX_MIB_TCPTIMEOUTREHASH), + SNMP_MIB_ITEM("TcpDuplicateDataRehash", LINUX_MIB_TCPDUPLICATEDATAREHASH), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 40a6abbc9cf6..3183413ebc6c 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -332,7 +332,7 @@ int raw_rcv(struct sock *sk, struct sk_buff *skb) kfree_skb(skb); return NET_RX_DROP; } - nf_reset(skb); + nf_reset_ct(skb); skb_push(skb, skb->data - skb_network_header(skb)); @@ -375,7 +375,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, skb_reserve(skb, hlen); skb->priority = sk->sk_priority; - skb->mark = sk->sk_mark; + skb->mark = sockc->mark; skb->tstamp = sockc->transmit_time; skb_dst_set(skb, &rt->dst); *rtp = NULL; @@ -623,7 +623,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } } - flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos, + flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, RT_SCOPE_UNIVERSE, hdrincl ? IPPROTO_RAW : sk->sk_protocol, inet_sk_flowi_flags(sk) | diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 517300d587a7..ebe7060d0fc9 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -139,7 +139,8 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst); static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu); + struct sk_buff *skb, u32 mtu, + bool confirm_neigh); static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); static void ipv4_dst_destroy(struct dst_entry *dst); @@ -236,11 +237,11 @@ static int rt_cache_seq_open(struct inode *inode, struct file *file) return seq_open(file, &rt_cache_seq_ops); } -static const struct file_operations rt_cache_seq_fops = { - .open = rt_cache_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, +static const struct proc_ops rt_cache_proc_ops = { + .proc_open = rt_cache_seq_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = seq_release, }; @@ -270,6 +271,7 @@ static void *rt_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos) *pos = cpu+1; return &per_cpu(rt_cache_stat, cpu); } + (*pos)++; return NULL; } @@ -326,11 +328,11 @@ static int rt_cpu_seq_open(struct inode *inode, struct file *file) return seq_open(file, &rt_cpu_seq_ops); } -static const struct file_operations rt_cpu_seq_fops = { - .open = rt_cpu_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, +static const struct proc_ops rt_cpu_proc_ops = { + .proc_open = rt_cpu_seq_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = seq_release, }; #ifdef CONFIG_IP_ROUTE_CLASSID @@ -364,12 +366,12 @@ static int __net_init ip_rt_do_proc_init(struct net *net) struct proc_dir_entry *pde; pde = proc_create("rt_cache", 0444, net->proc_net, - &rt_cache_seq_fops); + &rt_cache_proc_ops); if (!pde) goto err1; pde = proc_create("rt_cache", 0444, - net->proc_net_stat, &rt_cpu_seq_fops); + net->proc_net_stat, &rt_cpu_proc_ops); if (!pde) goto err2; @@ -635,6 +637,7 @@ static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnh if (fnhe->fnhe_gw) { rt->rt_flags |= RTCF_REDIRECTED; + rt->rt_uses_gateway = 1; rt->rt_gw_family = AF_INET; rt->rt_gw4 = fnhe->fnhe_gw; } @@ -915,16 +918,15 @@ void ip_rt_send_redirect(struct sk_buff *skb) if (peer->rate_tokens == 0 || time_after(jiffies, (peer->rate_last + - (ip_rt_redirect_load << peer->rate_tokens)))) { + (ip_rt_redirect_load << peer->n_redirects)))) { __be32 gw = rt_nexthop(rt, ip_hdr(skb)->daddr); icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw); peer->rate_last = jiffies; - ++peer->rate_tokens; ++peer->n_redirects; #ifdef CONFIG_IP_ROUTE_VERBOSE if (log_martians && - peer->rate_tokens == ip_rt_redirect_number) + peer->n_redirects == ip_rt_redirect_number) net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n", &ip_hdr(skb)->saddr, inet_iif(skb), &ip_hdr(skb)->daddr, &gw); @@ -1043,7 +1045,8 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) } static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { struct rtable *rt = (struct rtable *) dst; struct flowi4 fl4; @@ -1313,7 +1316,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) mtu = READ_ONCE(dst->dev->mtu); if (unlikely(ip_mtu_locked(dst))) { - if (rt->rt_gw_family && mtu > 576) + if (rt->rt_uses_gateway && mtu > 576) mtu = 576; } @@ -1482,7 +1485,7 @@ static bool rt_cache_route(struct fib_nh_common *nhc, struct rtable *rt) prev = cmpxchg(p, orig, rt); if (prev == orig) { if (orig) { - dst_dev_put(&orig->dst); + rt_add_uncached_list(orig); dst_release(&orig->dst); } } else { @@ -1569,6 +1572,7 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr, struct fib_nh_common *nhc = FIB_RES_NHC(*res); if (nhc->nhc_gw_family && nhc->nhc_scope == RT_SCOPE_LINK) { + rt->rt_uses_gateway = 1; rt->rt_gw_family = nhc->nhc_gw_family; /* only INET and INET6 are supported */ if (likely(nhc->nhc_gw_family == AF_INET)) @@ -1634,6 +1638,7 @@ struct rtable *rt_dst_alloc(struct net_device *dev, rt->rt_iif = 0; rt->rt_pmtu = 0; rt->rt_mtu_locked = 0; + rt->rt_uses_gateway = 0; rt->rt_gw_family = 0; rt->rt_gw4 = 0; INIT_LIST_HEAD(&rt->rt_uncached); @@ -1892,10 +1897,7 @@ static void ip_multipath_l3_keys(const struct sk_buff *skb, if (!icmph) goto out; - if (icmph->type != ICMP_DEST_UNREACH && - icmph->type != ICMP_REDIRECT && - icmph->type != ICMP_TIME_EXCEEDED && - icmph->type != ICMP_PARAMETERPROB) + if (!icmp_is_err(icmph->type)) goto out; inner_iph = skb_header_pointer(skb, @@ -2020,10 +2022,52 @@ static int ip_mkroute_input(struct sk_buff *skb, return __mkroute_input(skb, res, in_dev, daddr, saddr, tos); } +/* Implements all the saddr-related checks as ip_route_input_slow(), + * assuming daddr is valid and the destination is not a local broadcast one. + * Uses the provided hint instead of performing a route lookup. + */ +int ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr, + u8 tos, struct net_device *dev, + const struct sk_buff *hint) +{ + struct in_device *in_dev = __in_dev_get_rcu(dev); + struct rtable *rt = (struct rtable *)hint; + struct net *net = dev_net(dev); + int err = -EINVAL; + u32 tag = 0; + + if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) + goto martian_source; + + if (ipv4_is_zeronet(saddr)) + goto martian_source; + + if (ipv4_is_loopback(saddr) && !IN_DEV_NET_ROUTE_LOCALNET(in_dev, net)) + goto martian_source; + + if (rt->rt_type != RTN_LOCAL) + goto skip_validate_source; + + tos &= IPTOS_RT_MASK; + err = fib_validate_source(skb, saddr, daddr, tos, 0, dev, in_dev, &tag); + if (err < 0) + goto martian_source; + +skip_validate_source: + skb_dst_copy(skb, hint); + return 0; + +martian_source: + ip_handle_martian_source(dev, in_dev, skb, daddr, saddr); + return err; +} + /* * NOTE. We drop all the packets that has local source * addresses, because every properly looped back packet * must have correct destination already attached by output routine. + * Changes in the enforced policies must be applied also to + * ip_route_use_hint(). * * Such approach solves two big problems: * 1. Not simplex devices are handled properly. @@ -2468,14 +2512,17 @@ struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4, int orig_oif = fl4->flowi4_oif; unsigned int flags = 0; struct rtable *rth; - int err = -ENETUNREACH; + int err; if (fl4->saddr) { - rth = ERR_PTR(-EINVAL); if (ipv4_is_multicast(fl4->saddr) || ipv4_is_lbcast(fl4->saddr) || - ipv4_is_zeronet(fl4->saddr)) + ipv4_is_zeronet(fl4->saddr)) { + rth = ERR_PTR(-EINVAL); goto out; + } + + rth = ERR_PTR(-ENETUNREACH); /* I removed check for oif == dev_out->oif here. It was wrong for two reasons: @@ -2643,7 +2690,8 @@ static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst) } static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { } @@ -2694,6 +2742,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or rt->rt_genid = rt_genid_ipv4(net); rt->rt_flags = ort->rt_flags; rt->rt_type = ort->rt_type; + rt->rt_uses_gateway = ort->rt_uses_gateway; rt->rt_gw_family = ort->rt_gw_family; if (rt->rt_gw_family == AF_INET) rt->rt_gw4 = ort->rt_gw4; @@ -2728,7 +2777,8 @@ EXPORT_SYMBOL_GPL(ip_route_output_flow); /* called with rcu_read_lock held */ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, struct rtable *rt, u32 table_id, struct flowi4 *fl4, - struct sk_buff *skb, u32 portid, u32 seq) + struct sk_buff *skb, u32 portid, u32 seq, + unsigned int flags) { struct rtmsg *r; struct nlmsghdr *nlh; @@ -2736,7 +2786,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 error; u32 metrics[RTAX_MAX]; - nlh = nlmsg_put(skb, portid, seq, RTM_NEWROUTE, sizeof(*r), 0); + nlh = nlmsg_put(skb, portid, seq, RTM_NEWROUTE, sizeof(*r), flags); if (!nlh) return -EMSGSIZE; @@ -2777,21 +2827,23 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, if (nla_put_in_addr(skb, RTA_PREFSRC, fl4->saddr)) goto nla_put_failure; } - if (rt->rt_gw_family == AF_INET && - nla_put_in_addr(skb, RTA_GATEWAY, rt->rt_gw4)) { - goto nla_put_failure; - } else if (rt->rt_gw_family == AF_INET6) { - int alen = sizeof(struct in6_addr); - struct nlattr *nla; - struct rtvia *via; - - nla = nla_reserve(skb, RTA_VIA, alen + 2); - if (!nla) + if (rt->rt_uses_gateway) { + if (rt->rt_gw_family == AF_INET && + nla_put_in_addr(skb, RTA_GATEWAY, rt->rt_gw4)) { goto nla_put_failure; - - via = nla_data(nla); - via->rtvia_family = AF_INET6; - memcpy(via->rtvia_addr, &rt->rt_gw6, alen); + } else if (rt->rt_gw_family == AF_INET6) { + int alen = sizeof(struct in6_addr); + struct nlattr *nla; + struct rtvia *via; + + nla = nla_reserve(skb, RTA_VIA, alen + 2); + if (!nla) + goto nla_put_failure; + + via = nla_data(nla); + via->rtvia_family = AF_INET6; + memcpy(via->rtvia_addr, &rt->rt_gw6, alen); + } } expires = rt->dst.expires; @@ -2860,7 +2912,7 @@ nla_put_failure: static int fnhe_dump_bucket(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, u32 table_id, struct fnhe_hash_bucket *bucket, int genid, - int *fa_index, int fa_start) + int *fa_index, int fa_start, unsigned int flags) { int i; @@ -2891,7 +2943,7 @@ static int fnhe_dump_bucket(struct net *net, struct sk_buff *skb, err = rt_fill_info(net, fnhe->fnhe_daddr, 0, rt, table_id, NULL, skb, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq); + cb->nlh->nlmsg_seq, flags); if (err) return err; next: @@ -2904,7 +2956,7 @@ next: int fib_dump_info_fnhe(struct sk_buff *skb, struct netlink_callback *cb, u32 table_id, struct fib_info *fi, - int *fa_index, int fa_start) + int *fa_index, int fa_start, unsigned int flags) { struct net *net = sock_net(cb->skb->sk); int nhsel, genid = fnhe_genid(net); @@ -2922,7 +2974,8 @@ int fib_dump_info_fnhe(struct sk_buff *skb, struct netlink_callback *cb, err = 0; if (bucket) err = fnhe_dump_bucket(net, skb, cb, table_id, bucket, - genid, fa_index, fa_start); + genid, fa_index, fa_start, + flags); rcu_read_unlock(); if (err) return err; @@ -3171,19 +3224,45 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, skb_reset_mac_header(skb); if (rtm->rtm_flags & RTM_F_FIB_MATCH) { + struct fib_rt_info fri; + if (!res.fi) { err = fib_props[res.type].error; if (!err) err = -EHOSTUNREACH; goto errout_rcu; } + fri.fi = res.fi; + fri.tb_id = table_id; + fri.dst = res.prefix; + fri.dst_len = res.prefixlen; + fri.tos = fl4.flowi4_tos; + fri.type = rt->rt_type; + fri.offload = 0; + fri.trap = 0; + if (res.fa_head) { + struct fib_alias *fa; + + hlist_for_each_entry_rcu(fa, res.fa_head, fa_list) { + u8 slen = 32 - fri.dst_len; + + if (fa->fa_slen == slen && + fa->tb_id == fri.tb_id && + fa->fa_tos == fri.tos && + fa->fa_info == res.fi && + fa->fa_type == fri.type) { + fri.offload = fa->offload; + fri.trap = fa->trap; + break; + } + } + } err = fib_dump_info(skb, NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, RTM_NEWROUTE, table_id, - rt->rt_type, res.prefix, res.prefixlen, - fl4.flowi4_tos, res.fi, 0); + nlh->nlmsg_seq, RTM_NEWROUTE, &fri, 0); } else { err = rt_fill_info(net, dst, src, rt, table_id, &fl4, skb, - NETLINK_CB(in_skb).portid, nlh->nlmsg_seq); + NETLINK_CB(in_skb).portid, + nlh->nlmsg_seq, 0); } if (err < 0) goto errout_rcu; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 535b69326f66..9a4f6b16c9bc 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -62,10 +62,10 @@ static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport, * Since subsequent timestamps use the normal tcp_time_stamp value, we * must make sure that the resulting initial timestamp is <= tcp_time_stamp. */ -u64 cookie_init_timestamp(struct request_sock *req) +u64 cookie_init_timestamp(struct request_sock *req, u64 now) { struct inet_request_sock *ireq; - u32 ts, ts_now = tcp_time_stamp_raw(); + u32 ts, ts_now = tcp_ns_to_ts(now); u32 options = 0; ireq = inet_rsk(req); @@ -349,6 +349,10 @@ 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 = 0; treq->tfo_listener = false; + + if (IS_ENABLED(CONFIG_MPTCP)) + treq->is_mptcp = 0; + if (IS_ENABLED(CONFIG_SMC)) ireq->smc_ok = 0; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 0b980e841927..9684af02e0a5 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -340,6 +340,10 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write, user_key[i * 4 + 1], user_key[i * 4 + 2], user_key[i * 4 + 3]); + + if (WARN_ON_ONCE(off >= tbl.maxlen - 1)) + break; + if (i + 1 < n_keys) off += snprintf(tbl.data + off, tbl.maxlen - off, ","); } @@ -820,6 +824,15 @@ static struct ctl_table ipv4_net_table[] = { .extra2 = &tcp_min_snd_mss_max, }, { + .procname = "tcp_mtu_probe_floor", + .data = &init_net.ipv4.sysctl_tcp_mtu_probe_floor, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &tcp_min_snd_mss_min, + .extra2 = &tcp_min_snd_mss_max, + }, + { .procname = "tcp_probe_threshold", .data = &init_net.ipv4.sysctl_tcp_probe_threshold, .maxlen = sizeof(int), @@ -1028,7 +1041,7 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_fib_multipath_hash_policy, .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, + .extra2 = &two, }, #endif { @@ -1180,6 +1193,15 @@ static struct ctl_table ipv4_net_table[] = { .proc_handler = proc_dointvec, }, { + .procname = "tcp_no_ssthresh_metrics_save", + .data = &init_net.ipv4.sysctl_tcp_no_ssthresh_metrics_save, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { .procname = "tcp_moderate_rcvbuf", .data = &init_net.ipv4.sysctl_tcp_moderate_rcvbuf, .maxlen = sizeof(int), diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 77b485d60b9d..eb2d80519f8e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -271,6 +271,7 @@ #include <net/icmp.h> #include <net/inet_common.h> #include <net/tcp.h> +#include <net/mptcp.h> #include <net/xfrm.h> #include <net/ip.h> #include <net/sock.h> @@ -326,7 +327,7 @@ void tcp_enter_memory_pressure(struct sock *sk) { unsigned long val; - if (tcp_memory_pressure) + if (READ_ONCE(tcp_memory_pressure)) return; val = jiffies; @@ -341,7 +342,7 @@ void tcp_leave_memory_pressure(struct sock *sk) { unsigned long val; - if (!tcp_memory_pressure) + if (!READ_ONCE(tcp_memory_pressure)) return; val = xchg(&tcp_memory_pressure, 0); if (val) @@ -443,15 +444,13 @@ void tcp_init_sock(struct sock *sk) tp->tsoffset = 0; tp->rack.reo_wnd_steps = 1; - sk->sk_state = TCP_CLOSE; - sk->sk_write_space = sk_stream_write_space; sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); icsk->icsk_sync_mss = tcp_sync_mss; - sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1]; - sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1]; + WRITE_ONCE(sk->sk_sndbuf, sock_net(sk)->ipv4.sysctl_tcp_wmem[1]); + WRITE_ONCE(sk->sk_rcvbuf, sock_net(sk)->ipv4.sysctl_tcp_rmem[1]); sk_sockets_allocated_inc(sk); sk->sk_route_forced_caps = NETIF_F_GSO; @@ -477,7 +476,7 @@ static void tcp_tx_timestamp(struct sock *sk, u16 tsflags) static inline bool tcp_stream_is_readable(const struct tcp_sock *tp, int target, struct sock *sk) { - return (tp->rcv_nxt - tp->copied_seq >= target) || + return (READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq) >= target) || (sk->sk_prot->stream_memory_read ? sk->sk_prot->stream_memory_read(sk) : false); } @@ -543,10 +542,10 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) /* Connected or passive Fast Open socket? */ if (state != TCP_SYN_SENT && - (state != TCP_SYN_RECV || tp->fastopen_rsk)) { + (state != TCP_SYN_RECV || rcu_access_pointer(tp->fastopen_rsk))) { int target = sock_rcvlowat(sk, 0, INT_MAX); - if (tp->urg_seq == tp->copied_seq && + if (READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq) && !sock_flag(sk, SOCK_URGINLINE) && tp->urg_data) target++; @@ -584,7 +583,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) } /* This barrier is coupled with smp_wmb() in tcp_reset() */ smp_rmb(); - if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) + if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR; return mask; @@ -607,7 +606,8 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) unlock_sock_fast(sk, slow); break; case SIOCATMARK: - answ = tp->urg_data && tp->urg_seq == tp->copied_seq; + answ = tp->urg_data && + READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq); break; case SIOCOUTQ: if (sk->sk_state == TCP_LISTEN) @@ -616,7 +616,7 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) answ = 0; else - answ = tp->write_seq - tp->snd_una; + answ = READ_ONCE(tp->write_seq) - tp->snd_una; break; case SIOCOUTQNSD: if (sk->sk_state == TCP_LISTEN) @@ -625,7 +625,8 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) answ = 0; else - answ = tp->write_seq - tp->snd_nxt; + answ = READ_ONCE(tp->write_seq) - + READ_ONCE(tp->snd_nxt); break; default: return -ENOIOCTLCMD; @@ -657,7 +658,7 @@ static void skb_entail(struct sock *sk, struct sk_buff *skb) tcb->sacked = 0; __skb_header_release(skb); tcp_add_write_queue_tail(sk, skb); - sk->sk_wmem_queued += skb->truesize; + sk_wmem_queued_add(sk, skb->truesize); sk_mem_charge(sk, skb->truesize); if (tp->nonagle & TCP_NAGLE_PUSH) tp->nonagle &= ~TCP_NAGLE_PUSH; @@ -690,8 +691,8 @@ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb, refcount_read(&sk->sk_wmem_alloc) > skb->truesize; } -static void tcp_push(struct sock *sk, int flags, int mss_now, - int nonagle, int size_goal) +void tcp_push(struct sock *sk, int flags, int mss_now, + int nonagle, int size_goal) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; @@ -925,7 +926,7 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now, return max(size_goal, mss_now); } -static int tcp_send_mss(struct sock *sk, int *size_goal, int flags) +int tcp_send_mss(struct sock *sk, int *size_goal, int flags) { int mss_now; @@ -935,6 +936,22 @@ static int tcp_send_mss(struct sock *sk, int *size_goal, int flags) return mss_now; } +/* In some cases, both sendpage() and sendmsg() could have added + * an skb to the write queue, but failed adding payload on it. + * We need to remove it to consume less memory, but more + * importantly be able to generate EPOLLOUT for Edge Trigger epoll() + * users. + */ +static void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb) +{ + if (skb && !skb->len) { + tcp_unlink_write_queue(skb, sk); + if (tcp_write_queue_empty(sk)) + tcp_chrono_stop(sk, TCP_CHRONO_BUSY); + sk_wmem_free_skb(sk, skb); + } +} + ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset, size_t size, int flags) { @@ -1016,10 +1033,10 @@ new_segment: skb->len += copy; skb->data_len += copy; skb->truesize += copy; - sk->sk_wmem_queued += copy; + sk_wmem_queued_add(sk, copy); sk_mem_charge(sk, copy); skb->ip_summed = CHECKSUM_PARTIAL; - tp->write_seq += copy; + WRITE_ONCE(tp->write_seq, tp->write_seq + copy); TCP_SKB_CB(skb)->end_seq += copy; tcp_skb_pcount_set(skb, 0); @@ -1064,12 +1081,12 @@ out: return copied; do_error: + tcp_remove_empty_skb(sk, tcp_write_queue_tail(sk)); if (copied) goto out; out_err: /* make sure we wake any epoll edge trigger waiter */ - if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && - err == -EAGAIN)) { + if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) { sk->sk_write_space(sk); tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED); } @@ -1165,7 +1182,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) struct sockcm_cookie sockc; int flags, err, copied = 0; int mss_now = 0, size_goal, copied_syn = 0; - bool process_backlog = false; + int process_backlog = 0; bool zc = false; long timeo; @@ -1257,9 +1274,10 @@ new_segment: if (!sk_stream_memory_free(sk)) goto wait_for_sndbuf; - if (process_backlog && sk_flush_backlog(sk)) { - process_backlog = false; - goto restart; + if (unlikely(process_backlog >= 16)) { + process_backlog = 0; + if (sk_flush_backlog(sk)) + goto restart; } first_skb = tcp_rtx_and_write_queues_empty(sk); skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation, @@ -1267,7 +1285,7 @@ new_segment: if (!skb) goto wait_for_memory; - process_backlog = true; + process_backlog++; skb->ip_summed = CHECKSUM_PARTIAL; skb_entail(sk, skb); @@ -1344,7 +1362,7 @@ new_segment: if (!copied) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH; - tp->write_seq += copy; + WRITE_ONCE(tp->write_seq, tp->write_seq + copy); TCP_SKB_CB(skb)->end_seq += copy; tcp_skb_pcount_set(skb, 0); @@ -1388,26 +1406,18 @@ out_nopush: sock_zerocopy_put(uarg); return copied + copied_syn; +do_error: + skb = tcp_write_queue_tail(sk); do_fault: - if (!skb->len) { - tcp_unlink_write_queue(skb, sk); - /* It is the one place in all of TCP, except connection - * reset, where we can be unlinking the send_head. - */ - if (tcp_write_queue_empty(sk)) - tcp_chrono_stop(sk, TCP_CHRONO_BUSY); - sk_wmem_free_skb(sk, skb); - } + tcp_remove_empty_skb(sk, skb); -do_error: if (copied + copied_syn) goto out; out_err: sock_zerocopy_put_abort(uarg, true); err = sk_stream_error(sk, flags, err); /* make sure we wake any epoll edge trigger waiter */ - if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && - err == -EAGAIN)) { + if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) { sk->sk_write_space(sk); tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED); } @@ -1657,9 +1667,9 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, sk_eat_skb(sk, skb); if (!desc->count) break; - tp->copied_seq = seq; + WRITE_ONCE(tp->copied_seq, seq); } - tp->copied_seq = seq; + WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk); @@ -1688,7 +1698,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val) else cap = sock_net(sk)->ipv4.sysctl_tcp_rmem[2] >> 1; val = min(val, cap); - sk->sk_rcvlowat = val ? : 1; + WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); /* Check if we need to signal EPOLLIN right now */ tcp_data_ready(sk); @@ -1698,7 +1708,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val) val <<= 1; if (val > sk->sk_rcvbuf) { - sk->sk_rcvbuf = val; + WRITE_ONCE(sk->sk_rcvbuf, val); tcp_sk(sk)->window_clamp = tcp_win_from_space(sk, val); } return 0; @@ -1728,8 +1738,8 @@ static int tcp_zerocopy_receive(struct sock *sk, struct tcp_zerocopy_receive *zc) { unsigned long address = (unsigned long)zc->address; + u32 length = 0, seq, offset, zap_len; const skb_frag_t *frags = NULL; - u32 length = 0, seq, offset; struct vm_area_struct *vma; struct sk_buff *skb = NULL; struct tcp_sock *tp; @@ -1756,17 +1766,19 @@ static int tcp_zerocopy_receive(struct sock *sk, seq = tp->copied_seq; inq = tcp_inq(sk); zc->length = min_t(u32, zc->length, inq); - zc->length &= ~(PAGE_SIZE - 1); - if (zc->length) { - zap_page_range(vma, address, zc->length); + zap_len = zc->length & ~(PAGE_SIZE - 1); + if (zap_len) { + zap_page_range(vma, address, zap_len); zc->recv_skip_hint = 0; } else { - zc->recv_skip_hint = inq; + zc->recv_skip_hint = zc->length; } ret = 0; while (length + PAGE_SIZE <= zc->length) { if (zc->recv_skip_hint < PAGE_SIZE) { if (skb) { + if (zc->recv_skip_hint > 0) + break; skb = skb->next; offset = seq - TCP_SKB_CB(skb)->seq; } else { @@ -1779,18 +1791,18 @@ static int tcp_zerocopy_receive(struct sock *sk, break; frags = skb_shinfo(skb)->frags; while (offset) { - if (frags->size > offset) + if (skb_frag_size(frags) > offset) goto out; - offset -= frags->size; + offset -= skb_frag_size(frags); frags++; } } - if (frags->size != PAGE_SIZE || frags->page_offset) { + if (skb_frag_size(frags) != PAGE_SIZE || skb_frag_off(frags)) { int remaining = zc->recv_skip_hint; - while (remaining && (frags->size != PAGE_SIZE || - frags->page_offset)) { - remaining -= frags->size; + while (remaining && (skb_frag_size(frags) != PAGE_SIZE || + skb_frag_off(frags))) { + remaining -= skb_frag_size(frags); frags++; } zc->recv_skip_hint -= remaining; @@ -1808,7 +1820,7 @@ static int tcp_zerocopy_receive(struct sock *sk, out: up_read(¤t->mm->mmap_sem); if (length) { - tp->copied_seq = seq; + WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk); /* Clean up data we have read: This will do ACK frames. */ @@ -1851,29 +1863,33 @@ static void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, if (sock_flag(sk, SOCK_RCVTSTAMP)) { if (sock_flag(sk, SOCK_RCVTSTAMPNS)) { if (new_tstamp) { - struct __kernel_timespec kts = {tss->ts[0].tv_sec, tss->ts[0].tv_nsec}; - + struct __kernel_timespec kts = { + .tv_sec = tss->ts[0].tv_sec, + .tv_nsec = tss->ts[0].tv_nsec, + }; put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_NEW, sizeof(kts), &kts); } else { - struct timespec ts_old = timespec64_to_timespec(tss->ts[0]); - + struct __kernel_old_timespec ts_old = { + .tv_sec = tss->ts[0].tv_sec, + .tv_nsec = tss->ts[0].tv_nsec, + }; put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_OLD, sizeof(ts_old), &ts_old); } } else { if (new_tstamp) { - struct __kernel_sock_timeval stv; - - stv.tv_sec = tss->ts[0].tv_sec; - stv.tv_usec = tss->ts[0].tv_nsec / 1000; + struct __kernel_sock_timeval stv = { + .tv_sec = tss->ts[0].tv_sec, + .tv_usec = tss->ts[0].tv_nsec / 1000, + }; put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_NEW, sizeof(stv), &stv); } else { - struct __kernel_old_timeval tv; - - tv.tv_sec = tss->ts[0].tv_sec; - tv.tv_usec = tss->ts[0].tv_nsec / 1000; + struct __kernel_old_timeval tv = { + .tv_sec = tss->ts[0].tv_sec, + .tv_usec = tss->ts[0].tv_nsec / 1000, + }; put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD, sizeof(tv), &tv); } @@ -1945,13 +1961,12 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, struct sk_buff *skb, *last; u32 urg_hole = 0; struct scm_timestamping_internal tss; - bool has_tss = false; - bool has_cmsg; + int cmsg_flags; if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); - if (sk_can_busy_loop(sk) && skb_queue_empty(&sk->sk_receive_queue) && + if (sk_can_busy_loop(sk) && skb_queue_empty_lockless(&sk->sk_receive_queue) && (sk->sk_state == TCP_ESTABLISHED)) sk_busy_loop(sk, nonblock); @@ -1961,7 +1976,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, if (sk->sk_state == TCP_LISTEN) goto out; - has_cmsg = tp->recvmsg_inq; + cmsg_flags = tp->recvmsg_inq ? 1 : 0; timeo = sock_rcvtimeo(sk, nonblock); /* Urgent data needs to be handled specially. */ @@ -2034,7 +2049,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, /* Well, if we have backlog, try to process it now yet. */ - if (copied >= target && !sk->sk_backlog.tail) + if (copied >= target && !READ_ONCE(sk->sk_backlog.tail)) break; if (copied) { @@ -2106,7 +2121,7 @@ found_ok_skb: if (urg_offset < used) { if (!urg_offset) { if (!sock_flag(sk, SOCK_URGINLINE)) { - ++*seq; + WRITE_ONCE(*seq, *seq + 1); urg_hole++; offset++; used--; @@ -2128,7 +2143,7 @@ found_ok_skb: } } - *seq += used; + WRITE_ONCE(*seq, *seq + used); copied += used; len -= used; @@ -2144,8 +2159,7 @@ skip_copy: if (TCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, &tss); - has_tss = true; - has_cmsg = true; + cmsg_flags |= 2; } if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) goto found_fin_ok; @@ -2155,7 +2169,7 @@ skip_copy: found_fin_ok: /* Process the FIN. */ - ++*seq; + WRITE_ONCE(*seq, *seq + 1); if (!(flags & MSG_PEEK)) sk_eat_skb(sk, skb); break; @@ -2170,10 +2184,10 @@ found_fin_ok: release_sock(sk); - if (has_cmsg) { - if (has_tss) + if (cmsg_flags) { + if (cmsg_flags & 2) tcp_recv_timestamp(msg, sk, &tss); - if (tp->recvmsg_inq) { + if (cmsg_flags & 1) { inq = tcp_inq_hint(sk); put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(inq), &inq); } @@ -2476,7 +2490,10 @@ adjudge_to_death: } if (sk->sk_state == TCP_CLOSE) { - struct request_sock *req = tcp_sk(sk)->fastopen_rsk; + struct request_sock *req; + + req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, + lockdep_sock_is_held(sk)); /* We could get here with a non-NULL req if the socket is * aborted (e.g., closed with unread data) before 3WHS * finishes. @@ -2508,6 +2525,7 @@ static void tcp_rtx_queue_purge(struct sock *sk) { struct rb_node *p = rb_first(&sk->tcp_rtx_queue); + tcp_sk(sk)->highest_sack = NULL; while (p) { struct sk_buff *skb = rb_to_skb(p); @@ -2548,6 +2566,7 @@ int tcp_disconnect(struct sock *sk, int flags) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); int old_state = sk->sk_state; + u32 seq; if (old_state != TCP_CLOSE) tcp_set_state(sk, TCP_CLOSE); @@ -2574,7 +2593,7 @@ int tcp_disconnect(struct sock *sk, int flags) __kfree_skb(sk->sk_rx_skb_cache); sk->sk_rx_skb_cache = NULL; } - tp->copied_seq = tp->rcv_nxt; + WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); tp->urg_data = 0; tcp_write_queue_purge(sk); tcp_fastopen_active_disable_ofo_check(sk); @@ -2590,21 +2609,25 @@ int tcp_disconnect(struct sock *sk, int flags) tp->srtt_us = 0; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); tp->rcv_rtt_last_tsecr = 0; - tp->write_seq += tp->max_window + 2; - if (tp->write_seq == 0) - tp->write_seq = 1; + + seq = tp->write_seq + tp->max_window + 2; + if (!seq) + seq = 1; + WRITE_ONCE(tp->write_seq, seq); + icsk->icsk_backoff = 0; - tp->snd_cwnd = 2; icsk->icsk_probes_out = 0; icsk->icsk_rto = TCP_TIMEOUT_INIT; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd = TCP_INIT_CWND; tp->snd_cwnd_cnt = 0; tp->window_clamp = 0; + tp->delivered = 0; tp->delivered_ce = 0; tcp_set_ca_state(sk, TCP_CA_Open); tp->is_sack_reneg = 0; tcp_clear_retrans(tp); + tp->total_retrans = 0; inet_csk_delack_init(sk); /* Initialize rcv_mss to TCP_MIN_MSS to avoid division by 0 * issue in __tcp_select_window() @@ -2616,10 +2639,14 @@ int tcp_disconnect(struct sock *sk, int flags) sk->sk_rx_dst = NULL; tcp_saved_syn_free(tp); tp->compressed_ack = 0; + tp->segs_in = 0; + tp->segs_out = 0; tp->bytes_sent = 0; tp->bytes_acked = 0; tp->bytes_received = 0; tp->bytes_retrans = 0; + tp->data_segs_in = 0; + tp->data_segs_out = 0; tp->duplicate_sack[0].start_seq = 0; tp->duplicate_sack[0].end_seq = 0; tp->dsack_dups = 0; @@ -2640,11 +2667,13 @@ int tcp_disconnect(struct sock *sk, int flags) tp->rx_opt.saw_tstamp = 0; tp->rx_opt.dsack = 0; tp->rx_opt.num_sacks = 0; + tp->rcv_ooopack = 0; /* Clean up fastopen related fields */ tcp_free_fastopen_req(tp); inet->defer_connect = 0; + tp->fastopen_client_fail = 0; WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); @@ -2918,9 +2947,9 @@ static int do_tcp_setsockopt(struct sock *sk, int level, if (sk->sk_state != TCP_CLOSE) err = -EPERM; else if (tp->repair_queue == TCP_SEND_QUEUE) - tp->write_seq = val; + WRITE_ONCE(tp->write_seq, val); else if (tp->repair_queue == TCP_RECV_QUEUE) - tp->rcv_nxt = val; + WRITE_ONCE(tp->rcv_nxt, val); else err = -EINVAL; break; @@ -3203,8 +3232,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) * tcpi_unacked -> Number of children ready for accept() * tcpi_sacked -> max backlog */ - info->tcpi_unacked = sk->sk_ack_backlog; - info->tcpi_sacked = sk->sk_max_ack_backlog; + info->tcpi_unacked = READ_ONCE(sk->sk_ack_backlog); + info->tcpi_sacked = READ_ONCE(sk->sk_max_ack_backlog); return; } @@ -3282,6 +3311,9 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_bytes_retrans = tp->bytes_retrans; info->tcpi_dsack_dups = tp->dsack_dups; info->tcpi_reord_seen = tp->reord_seen; + info->tcpi_rcv_ooopack = tp->rcv_ooopack; + info->tcpi_snd_wnd = tp->snd_wnd; + info->tcpi_fastopen_client_fail = tp->fastopen_client_fail; unlock_sock_fast(sk, slow); } EXPORT_SYMBOL_GPL(tcp_get_info); @@ -3311,6 +3343,7 @@ static size_t tcp_opt_stats_get_size(void) nla_total_size(sizeof(u32)) + /* TCP_NLA_DSACK_DUPS */ nla_total_size(sizeof(u32)) + /* TCP_NLA_REORD_SEEN */ nla_total_size(sizeof(u32)) + /* TCP_NLA_SRTT */ + nla_total_size(sizeof(u16)) + /* TCP_NLA_TIMEOUT_REHASH */ 0; } @@ -3365,6 +3398,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk) nla_put_u32(stats, TCP_NLA_DSACK_DUPS, tp->dsack_dups); nla_put_u32(stats, TCP_NLA_REORD_SEEN, tp->reord_seen); nla_put_u32(stats, TCP_NLA_SRTT, tp->srtt_us >> 3); + nla_put_u16(stats, TCP_NLA_TIMEOUT_REHASH, tp->timeout_rehash); return stats; } @@ -3784,8 +3818,8 @@ int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *hp, return 1; for (i = 0; i < shi->nr_frags; ++i) { - const struct skb_frag_struct *f = &shi->frags[i]; - unsigned int offset = f->page_offset; + const skb_frag_t *f = &shi->frags[i]; + unsigned int offset = skb_frag_off(f); struct page *page = skb_frag_page(f) + (offset >> PAGE_SHIFT); sg_set_page(&sg, page, skb_frag_size(f), @@ -3817,7 +3851,13 @@ EXPORT_SYMBOL(tcp_md5_hash_key); void tcp_done(struct sock *sk) { - struct request_sock *req = tcp_sk(sk)->fastopen_rsk; + struct request_sock *req; + + /* We might be called with a new socket, after + * inet_csk_prepare_forced_close() has been called + * so we can not use lockdep_sock_is_held(sk) + */ + req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, 1); if (sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV) TCP_INC_STATS(sock_net(sk), TCP_MIB_ATTEMPTFAILS); @@ -3916,7 +3956,7 @@ void __init tcp_init(void) BUILD_BUG_ON(TCP_MIN_SND_MSS <= MAX_TCP_OPTION_SPACE); BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > - FIELD_SIZEOF(struct sk_buff, cb)); + sizeof_field(struct sk_buff, cb)); percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL); percpu_counter_init(&tcp_orphan_count, 0, GFP_KERNEL); @@ -3990,4 +4030,5 @@ void __init tcp_init(void) tcp_metrics_init(); BUG_ON(tcp_register_congestion_control(&tcp_reno) != 0); tcp_tasklet_init(); + mptcp_init(); } diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 56be7d27f208..6c4d79baff26 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -306,7 +306,8 @@ static u32 bbr_tso_segs_goal(struct sock *sk) /* Sort of tcp_tso_autosize() but ignoring * driver provided sk_gso_max_size. */ - bytes = min_t(unsigned long, sk->sk_pacing_rate >> sk->sk_pacing_shift, + bytes = min_t(unsigned long, + sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift), GSO_MAX_SIZE - 1 - MAX_TCP_HEADER); segs = max_t(u32, bytes / tp->mss_cache, bbr_min_tso_segs(sk)); @@ -346,7 +347,7 @@ static void bbr_cwnd_event(struct sock *sk, enum tcp_ca_event event) /* Calculate bdp based on min RTT and the estimated bottleneck bandwidth: * - * bdp = bw * min_rtt * gain + * bdp = ceil(bw * min_rtt * gain) * * The key factor, gain, controls the amount of queue. While a small gain * builds a smaller queue, it becomes more vulnerable to noise in RTT @@ -370,7 +371,9 @@ static u32 bbr_bdp(struct sock *sk, u32 bw, int gain) w = (u64)bw * bbr->min_rtt_us; - /* Apply a gain to the given value, then remove the BW_SCALE shift. */ + /* Apply a gain to the given value, remove the BW_SCALE shift, and + * round the value up to avoid a negative feedback loop. + */ bdp = (((w * gain) >> BBR_SCALE) + BW_UNIT - 1) / BW_UNIT; return bdp; @@ -386,7 +389,7 @@ static u32 bbr_bdp(struct sock *sk, u32 bw, int gain) * which allows 2 outstanding 2-packet sequences, to try to keep pipe * full even with ACK-every-other-packet delayed ACKs. */ -static u32 bbr_quantization_budget(struct sock *sk, u32 cwnd, int gain) +static u32 bbr_quantization_budget(struct sock *sk, u32 cwnd) { struct bbr *bbr = inet_csk_ca(sk); @@ -397,7 +400,7 @@ static u32 bbr_quantization_budget(struct sock *sk, u32 cwnd, int gain) cwnd = (cwnd + 1) & ~1U; /* Ensure gain cycling gets inflight above BDP even for small BDPs. */ - if (bbr->mode == BBR_PROBE_BW && gain > BBR_UNIT) + if (bbr->mode == BBR_PROBE_BW && bbr->cycle_idx == 0) cwnd += 2; return cwnd; @@ -409,7 +412,7 @@ static u32 bbr_inflight(struct sock *sk, u32 bw, int gain) u32 inflight; inflight = bbr_bdp(sk, bw, gain); - inflight = bbr_quantization_budget(sk, inflight, gain); + inflight = bbr_quantization_budget(sk, inflight); return inflight; } @@ -529,7 +532,7 @@ static void bbr_set_cwnd(struct sock *sk, const struct rate_sample *rs, * due to aggregation (of data and/or ACKs) visible in the ACK stream. */ target_cwnd += bbr_ack_aggregation_cwnd(sk); - target_cwnd = bbr_quantization_budget(sk, target_cwnd, gain); + target_cwnd = bbr_quantization_budget(sk, target_cwnd); /* If we're below target cwnd, slow start cwnd toward target cwnd. */ if (bbr_full_bw_reached(sk)) /* only cut cwnd if we filled the pipe */ @@ -776,8 +779,7 @@ static void bbr_update_bw(struct sock *sk, const struct rate_sample *rs) * bandwidth sample. Delivered is in packets and interval_us in uS and * ratio will be <<1 for most connections. So delivered is first scaled. */ - bw = (u64)rs->delivered * BW_UNIT; - do_div(bw, rs->interval_us); + bw = div64_long((u64)rs->delivered * BW_UNIT, rs->interval_us); /* If this sample is application-limited, it is likely to have a very * low delivered count that represents application behavior rather than diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 8a56e09cfb0e..8a01428f80c1 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -121,14 +121,14 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, struct sk_psock *psock; int copied, ret; - if (unlikely(flags & MSG_ERRQUEUE)) - return inet_recv_error(sk, msg, len, addr_len); - if (!skb_queue_empty(&sk->sk_receive_queue)) - return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); - psock = sk_psock_get(sk); if (unlikely(!psock)) return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); + if (unlikely(flags & MSG_ERRQUEUE)) + return inet_recv_error(sk, msg, len, addr_len); + if (!skb_queue_empty(&sk->sk_receive_queue) && + sk_psock_queue_empty(psock)) + return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); lock_sock(sk); msg_bytes_ready: copied = __tcp_bpf_recvmsg(sk, psock, msg, len, flags); @@ -139,7 +139,7 @@ msg_bytes_ready: timeo = sock_rcvtimeo(sk, nonblock); data = tcp_bpf_wait_data(sk, psock, flags, timeo, &err); if (data) { - if (skb_queue_empty(&sk->sk_receive_queue)) + if (!sk_psock_queue_empty(psock)) goto msg_bytes_ready; release_sock(sk); sk_psock_put(sk, psock); @@ -301,7 +301,7 @@ EXPORT_SYMBOL_GPL(tcp_bpf_sendmsg_redir); static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock, struct sk_msg *msg, int *copied, int flags) { - bool cork = false, enospc = msg->sg.start == msg->sg.end; + bool cork = false, enospc = sk_msg_full(msg); struct sock *sk_redir; u32 tosend, delta = 0; int ret; @@ -315,10 +315,7 @@ more_data: */ delta = msg->sg.size; psock->eval = sk_psock_msg_verdict(sk, psock, msg); - if (msg->sg.size < delta) - delta -= msg->sg.size; - else - delta = 0; + delta -= msg->sg.size; } if (msg->cork_bytes && diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index c445a81d144e..3172e31987be 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -21,7 +21,7 @@ static DEFINE_SPINLOCK(tcp_cong_list_lock); static LIST_HEAD(tcp_cong_list); /* Simple linear search, don't expect many entries! */ -static struct tcp_congestion_ops *tcp_ca_find(const char *name) +struct tcp_congestion_ops *tcp_ca_find(const char *name) { struct tcp_congestion_ops *e; @@ -162,7 +162,7 @@ void tcp_assign_congestion_control(struct sock *sk) rcu_read_lock(); ca = rcu_dereference(net->ipv4.tcp_congestion_control); - if (unlikely(!try_module_get(ca->owner))) + if (unlikely(!bpf_try_module_get(ca, ca->owner))) ca = &tcp_reno; icsk->icsk_ca_ops = ca; rcu_read_unlock(); @@ -208,7 +208,7 @@ void tcp_cleanup_congestion_control(struct sock *sk) if (icsk->icsk_ca_ops->release) icsk->icsk_ca_ops->release(sk); - module_put(icsk->icsk_ca_ops->owner); + bpf_module_put(icsk->icsk_ca_ops, icsk->icsk_ca_ops->owner); } /* Used by sysctl to change default congestion control */ @@ -222,12 +222,12 @@ int tcp_set_default_congestion_control(struct net *net, const char *name) ca = tcp_ca_find_autoload(net, name); if (!ca) { ret = -ENOENT; - } else if (!try_module_get(ca->owner)) { + } else if (!bpf_try_module_get(ca, ca->owner)) { ret = -EBUSY; } else { prev = xchg(&net->ipv4.tcp_congestion_control, ca); if (prev) - module_put(prev->owner); + bpf_module_put(prev, prev->owner); ca->flags |= TCP_CONG_NON_RESTRICTED; ret = 0; @@ -256,6 +256,9 @@ void tcp_get_available_congestion_control(char *buf, size_t maxlen) offs += snprintf(buf + offs, maxlen - offs, "%s%s", offs == 0 ? "" : " ", ca->name); + + if (WARN_ON_ONCE(offs >= maxlen)) + break; } rcu_read_unlock(); } @@ -285,6 +288,9 @@ void tcp_get_allowed_congestion_control(char *buf, size_t maxlen) offs += snprintf(buf + offs, maxlen - offs, "%s%s", offs == 0 ? "" : " ", ca->name); + + if (WARN_ON_ONCE(offs >= maxlen)) + break; } rcu_read_unlock(); } @@ -360,19 +366,19 @@ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load, } else if (!load) { const struct tcp_congestion_ops *old_ca = icsk->icsk_ca_ops; - if (try_module_get(ca->owner)) { + if (bpf_try_module_get(ca, ca->owner)) { if (reinit) { tcp_reinit_congestion_control(sk, ca); } else { icsk->icsk_ca_ops = ca; - module_put(old_ca->owner); + bpf_module_put(old_ca, old_ca->owner); } } else { err = -EBUSY; } } else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || cap_net_admin)) { err = -EPERM; - } else if (!try_module_get(ca->owner)) { + } else if (!bpf_try_module_get(ca, ca->owner)) { err = -EBUSY; } else { tcp_reinit_congestion_control(sk, ca); diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 1b3d032a4df2..8f8eefd3a3ce 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -40,8 +40,8 @@ /* Number of delay samples for detecting the increase of delay */ #define HYSTART_MIN_SAMPLES 8 -#define HYSTART_DELAY_MIN (4U<<3) -#define HYSTART_DELAY_MAX (16U<<3) +#define HYSTART_DELAY_MIN (4000U) /* 4 ms */ +#define HYSTART_DELAY_MAX (16000U) /* 16 ms */ #define HYSTART_DELAY_THRESH(x) clamp(x, HYSTART_DELAY_MIN, HYSTART_DELAY_MAX) static int fast_convergence __read_mostly = 1; @@ -53,7 +53,7 @@ static int tcp_friendliness __read_mostly = 1; static int hystart __read_mostly = 1; static int hystart_detect __read_mostly = HYSTART_ACK_TRAIN | HYSTART_DELAY; static int hystart_low_window __read_mostly = 16; -static int hystart_ack_delta __read_mostly = 2; +static int hystart_ack_delta_us __read_mostly = 2000; static u32 cube_rtt_scale __read_mostly; static u32 beta_scale __read_mostly; @@ -77,8 +77,8 @@ MODULE_PARM_DESC(hystart_detect, "hybrid slow start detection mechanisms" " 1: packet-train 2: delay 3: both packet-train and delay"); module_param(hystart_low_window, int, 0644); MODULE_PARM_DESC(hystart_low_window, "lower bound cwnd for hybrid slow start"); -module_param(hystart_ack_delta, int, 0644); -MODULE_PARM_DESC(hystart_ack_delta, "spacing between ack's indicating train (msecs)"); +module_param(hystart_ack_delta_us, int, 0644); +MODULE_PARM_DESC(hystart_ack_delta_us, "spacing between ack's indicating train (usecs)"); /* BIC TCP Parameters */ struct bictcp { @@ -89,7 +89,7 @@ struct bictcp { u32 bic_origin_point;/* origin point of bic function */ u32 bic_K; /* time to origin point from the beginning of the current epoch */ - u32 delay_min; /* min delay (msec << 3) */ + u32 delay_min; /* min delay (usec) */ u32 epoch_start; /* beginning of an epoch */ u32 ack_cnt; /* number of acks */ u32 tcp_cwnd; /* estimated tcp cwnd */ @@ -117,13 +117,9 @@ static inline void bictcp_reset(struct bictcp *ca) ca->found = 0; } -static inline u32 bictcp_clock(void) +static inline u32 bictcp_clock_us(const struct sock *sk) { -#if HZ < 1000 - return ktime_to_ms(ktime_get_real()); -#else - return jiffies_to_msecs(jiffies); -#endif + return tcp_sk(sk)->tcp_mstamp; } static inline void bictcp_hystart_reset(struct sock *sk) @@ -131,9 +127,9 @@ static inline void bictcp_hystart_reset(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); - ca->round_start = ca->last_ack = bictcp_clock(); + ca->round_start = ca->last_ack = bictcp_clock_us(sk); ca->end_seq = tp->snd_nxt; - ca->curr_rtt = 0; + ca->curr_rtt = ~0U; ca->sample_cnt = 0; } @@ -276,7 +272,7 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd, u32 acked) */ t = (s32)(tcp_jiffies32 - ca->epoch_start); - t += msecs_to_jiffies(ca->delay_min >> 3); + t += usecs_to_jiffies(ca->delay_min); /* change the unit from HZ to bictcp_HZ */ t <<= BICTCP_HZ; do_div(t, HZ); @@ -376,22 +372,54 @@ static void bictcp_state(struct sock *sk, u8 new_state) } } +/* Account for TSO/GRO delays. + * Otherwise short RTT flows could get too small ssthresh, since during + * slow start we begin with small TSO packets and ca->delay_min would + * not account for long aggregation delay when TSO packets get bigger. + * Ideally even with a very small RTT we would like to have at least one + * TSO packet being sent and received by GRO, and another one in qdisc layer. + * We apply another 100% factor because @rate is doubled at this point. + * We cap the cushion to 1ms. + */ +static u32 hystart_ack_delay(struct sock *sk) +{ + unsigned long rate; + + rate = READ_ONCE(sk->sk_pacing_rate); + if (!rate) + return 0; + return min_t(u64, USEC_PER_MSEC, + div64_ul((u64)GSO_MAX_SIZE * 4 * USEC_PER_SEC, rate)); +} + static void hystart_update(struct sock *sk, u32 delay) { struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); - - if (ca->found & hystart_detect) - return; + u32 threshold; if (hystart_detect & HYSTART_ACK_TRAIN) { - u32 now = bictcp_clock(); + u32 now = bictcp_clock_us(sk); /* first detection parameter - ack-train detection */ - if ((s32)(now - ca->last_ack) <= hystart_ack_delta) { + if ((s32)(now - ca->last_ack) <= hystart_ack_delta_us) { ca->last_ack = now; - if ((s32)(now - ca->round_start) > ca->delay_min >> 4) { - ca->found |= HYSTART_ACK_TRAIN; + + threshold = ca->delay_min + hystart_ack_delay(sk); + + /* Hystart ack train triggers if we get ack past + * ca->delay_min/2. + * Pacing might have delayed packets up to RTT/2 + * during slow start. + */ + if (sk->sk_pacing_status == SK_PACING_NONE) + threshold >>= 1; + + if ((s32)(now - ca->round_start) > threshold) { + ca->found = 1; + pr_debug("hystart_ack_train (%u > %u) delay_min %u (+ ack_delay %u) cwnd %u\n", + now - ca->round_start, threshold, + ca->delay_min, hystart_ack_delay(sk), tp->snd_cwnd); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHYSTARTTRAINDETECT); NET_ADD_STATS(sock_net(sk), @@ -405,14 +433,14 @@ static void hystart_update(struct sock *sk, u32 delay) if (hystart_detect & HYSTART_DELAY) { /* obtain the minimum delay of more than sampling packets */ if (ca->sample_cnt < HYSTART_MIN_SAMPLES) { - if (ca->curr_rtt == 0 || ca->curr_rtt > delay) + if (ca->curr_rtt > delay) ca->curr_rtt = delay; ca->sample_cnt++; } else { if (ca->curr_rtt > ca->delay_min + HYSTART_DELAY_THRESH(ca->delay_min >> 3)) { - ca->found |= HYSTART_DELAY; + ca->found = 1; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHYSTARTDELAYDETECT); NET_ADD_STATS(sock_net(sk), @@ -424,9 +452,6 @@ static void hystart_update(struct sock *sk, u32 delay) } } -/* Track delayed acknowledgment ratio using sliding window - * ratio = (15*ratio + sample) / 16 - */ static void bictcp_acked(struct sock *sk, const struct ack_sample *sample) { const struct tcp_sock *tp = tcp_sk(sk); @@ -441,7 +466,7 @@ static void bictcp_acked(struct sock *sk, const struct ack_sample *sample) if (ca->epoch_start && (s32)(tcp_jiffies32 - ca->epoch_start) < HZ) return; - delay = (sample->rtt_us << 3) / USEC_PER_MSEC; + delay = sample->rtt_us; if (delay == 0) delay = 1; @@ -450,7 +475,7 @@ static void bictcp_acked(struct sock *sk, const struct ack_sample *sample) ca->delay_min = delay; /* hystart triggers when cwnd is larger than some threshold */ - if (hystart && tcp_in_slow_start(tp) && + if (!ca->found && tcp_in_slow_start(tp) && hystart && tp->snd_cwnd >= hystart_low_window) hystart_update(sk, delay); } diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index a3a386236d93..0d08f9e2d8d0 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -21,13 +21,14 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, struct tcp_info *info = _info; if (inet_sk_state_load(sk) == TCP_LISTEN) { - r->idiag_rqueue = sk->sk_ack_backlog; - r->idiag_wqueue = sk->sk_max_ack_backlog; + r->idiag_rqueue = READ_ONCE(sk->sk_ack_backlog); + r->idiag_wqueue = READ_ONCE(sk->sk_max_ack_backlog); } else if (sk->sk_type == SOCK_STREAM) { const struct tcp_sock *tp = tcp_sk(sk); - r->idiag_rqueue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); - r->idiag_wqueue = tp->write_seq - tp->snd_una; + r->idiag_rqueue = max_t(int, READ_ONCE(tp->rcv_nxt) - + READ_ONCE(tp->copied_seq), 0); + r->idiag_wqueue = READ_ONCE(tp->write_seq) - tp->snd_una; } if (info) tcp_get_info(sk, info); @@ -81,13 +82,42 @@ static int tcp_diag_put_md5sig(struct sk_buff *skb, } #endif +static int tcp_diag_put_ulp(struct sk_buff *skb, struct sock *sk, + const struct tcp_ulp_ops *ulp_ops) +{ + struct nlattr *nest; + int err; + + nest = nla_nest_start_noflag(skb, INET_DIAG_ULP_INFO); + if (!nest) + return -EMSGSIZE; + + err = nla_put_string(skb, INET_ULP_INFO_NAME, ulp_ops->name); + if (err) + goto nla_failure; + + if (ulp_ops->get_info) + err = ulp_ops->get_info(sk, skb); + if (err) + goto nla_failure; + + nla_nest_end(skb, nest); + return 0; + +nla_failure: + nla_nest_cancel(skb, nest); + return err; +} + static int tcp_diag_get_aux(struct sock *sk, bool net_admin, struct sk_buff *skb) { + struct inet_connection_sock *icsk = inet_csk(sk); + int err = 0; + #ifdef CONFIG_TCP_MD5SIG if (net_admin) { struct tcp_md5sig_info *md5sig; - int err = 0; rcu_read_lock(); md5sig = rcu_dereference(tcp_sk(sk)->md5sig_info); @@ -99,11 +129,21 @@ static int tcp_diag_get_aux(struct sock *sk, bool net_admin, } #endif + if (net_admin) { + const struct tcp_ulp_ops *ulp_ops; + + ulp_ops = icsk->icsk_ulp_ops; + if (ulp_ops) + err = tcp_diag_put_ulp(skb, sk, ulp_ops); + if (err) + return err; + } return 0; } static size_t tcp_diag_get_aux_size(struct sock *sk, bool net_admin) { + struct inet_connection_sock *icsk = inet_csk(sk); size_t size = 0; #ifdef CONFIG_TCP_MD5SIG @@ -124,6 +164,17 @@ static size_t tcp_diag_get_aux_size(struct sock *sk, bool net_admin) } #endif + if (net_admin && sk_fullsock(sk)) { + const struct tcp_ulp_ops *ulp_ops; + + ulp_ops = icsk->icsk_ulp_ops; + if (ulp_ops) { + size += nla_total_size(0) + + nla_total_size(TCP_ULP_NAME_MAX); + if (ulp_ops->get_info_size) + size += ulp_ops->get_info_size(sk); + } + } return size; } diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 3fd451271a70..19ad9586c720 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -253,7 +253,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, */ tp = tcp_sk(child); - tp->fastopen_rsk = req; + rcu_assign_pointer(tp->fastopen_rsk, req); tcp_rsk(req)->tfo_listener = true; /* RFC1323: The window in SYN & SYN/ACK segments is never @@ -422,7 +422,10 @@ bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss, cookie->len = -1; return true; } - return cookie->len > 0; + if (cookie->len > 0) + return true; + tcp_sk(sk)->fastopen_client_fail = TFO_COOKIE_UNAVAILABLE; + return false; } /* This function checks if we want to defer sending SYN until the first diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index c21e8a22fb3b..316ebdf8151d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -79,6 +79,7 @@ #include <trace/events/tcp.h> #include <linux/jump_label_ratelimit.h> #include <net/busy_poll.h> +#include <net/mptcp.h> int sysctl_tcp_max_orphans __read_mostly = NR_FILE; @@ -266,7 +267,7 @@ static void tcp_ecn_accept_cwr(struct sock *sk, const struct sk_buff *skb) static void tcp_ecn_withdraw_cwr(struct tcp_sock *tp) { - tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR; + tp->ecn_flags &= ~TCP_ECN_QUEUE_CWR; } static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb) @@ -359,7 +360,8 @@ static void tcp_sndbuf_expand(struct sock *sk) sndmem *= nr_segs * per_mss; if (sk->sk_sndbuf < sndmem) - sk->sk_sndbuf = min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2]); + WRITE_ONCE(sk->sk_sndbuf, + min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2])); } /* 2. Tuning advertised window (window_clamp, rcv_ssthresh) @@ -483,8 +485,9 @@ static void tcp_clamp_window(struct sock *sk) !(sk->sk_userlocks & SOCK_RCVBUF_LOCK) && !tcp_under_memory_pressure(sk) && sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) { - sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc), - net->ipv4.sysctl_tcp_rmem[2]); + WRITE_ONCE(sk->sk_rcvbuf, + min(atomic_read(&sk->sk_rmem_alloc), + net->ipv4.sysctl_tcp_rmem[2])); } if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) tp->rcv_ssthresh = min(tp->window_clamp, 2U * tp->advmss); @@ -648,7 +651,7 @@ void tcp_rcv_space_adjust(struct sock *sk) rcvbuf = min_t(u64, rcvwin * rcvmem, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]); if (rcvbuf > sk->sk_rcvbuf) { - sk->sk_rcvbuf = rcvbuf; + WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); /* Make the window clamp follow along. */ tp->window_clamp = tcp_win_from_space(sk, rcvbuf); @@ -913,9 +916,10 @@ static void tcp_check_sack_reordering(struct sock *sk, const u32 low_seq, /* 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 || - before(TCP_SKB_CB(skb)->seq, - TCP_SKB_CB(tp->retransmit_skb_hint)->seq)) + if ((!tp->retransmit_skb_hint && tp->retrans_out >= tp->lost_out) || + (tp->retransmit_skb_hint && + before(TCP_SKB_CB(skb)->seq, + TCP_SKB_CB(tp->retransmit_skb_hint)->seq))) tp->retransmit_skb_hint = skb; } @@ -1420,7 +1424,7 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, if ((TCP_SKB_CB(prev)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED) goto fallback; - if (!tcp_skb_can_collapse_to(prev)) + if (!tcp_skb_can_collapse(prev, skb)) goto fallback; in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) && @@ -1725,8 +1729,11 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, } /* Ignore very old stuff early */ - if (!after(sp[used_sacks].end_seq, prior_snd_una)) + if (!after(sp[used_sacks].end_seq, prior_snd_una)) { + if (i == 0) + first_sack_index = -1; continue; + } used_sacks++; } @@ -2666,7 +2673,7 @@ static void tcp_process_loss(struct sock *sk, int flag, int num_dupack, struct tcp_sock *tp = tcp_sk(sk); bool recovered = !before(tp->snd_una, tp->high_seq); - if ((flag & FLAG_SND_UNA_ADVANCED || tp->fastopen_rsk) && + if ((flag & FLAG_SND_UNA_ADVANCED || rcu_access_pointer(tp->fastopen_rsk)) && tcp_try_undo_loss(sk, false)) return; @@ -2990,7 +2997,7 @@ void tcp_rearm_rto(struct sock *sk) /* If the retrans timer is currently being used by Fast Open * for SYN-ACK retrans purpose, stay put. */ - if (tp->fastopen_rsk) + if (rcu_access_pointer(tp->fastopen_rsk)) return; if (!tp->packets_out) { @@ -3158,6 +3165,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack, tp->retransmit_skb_hint = NULL; if (unlikely(skb == tp->lost_skb_hint)) tp->lost_skb_hint = NULL; + tcp_highest_sack_replace(sk, skb, next); tcp_rtx_queue_unlink_and_free(skb, sk); } @@ -3362,7 +3370,7 @@ static void tcp_rcv_nxt_update(struct tcp_sock *tp, u32 seq) sock_owned_by_me((struct sock *)tp); tp->bytes_received += delta; - tp->rcv_nxt = seq; + WRITE_ONCE(tp->rcv_nxt, seq); } /* Update our send window. @@ -3548,7 +3556,7 @@ static void tcp_xmit_recovery(struct sock *sk, int rexmit) if (rexmit == REXMIT_NONE || sk->sk_state == TCP_SYN_SENT) return; - if (unlikely(rexmit == 2)) { + if (unlikely(rexmit == REXMIT_NEW)) { __tcp_push_pending_frames(sk, tcp_current_mss(sk), TCP_NAGLE_OFF); if (after(tp->snd_nxt, tp->high_seq)) @@ -3782,6 +3790,49 @@ static void smc_parse_options(const struct tcphdr *th, #endif } +/* Try to parse the MSS option from the TCP header. Return 0 on failure, clamped + * value on success. + */ +static u16 tcp_parse_mss_option(const struct tcphdr *th, u16 user_mss) +{ + const unsigned char *ptr = (const unsigned char *)(th + 1); + int length = (th->doff * 4) - sizeof(struct tcphdr); + u16 mss = 0; + + while (length > 0) { + int opcode = *ptr++; + int opsize; + + switch (opcode) { + case TCPOPT_EOL: + return mss; + case TCPOPT_NOP: /* Ref: RFC 793 section 3.1 */ + length--; + continue; + default: + if (length < 2) + return mss; + opsize = *ptr++; + if (opsize < 2) /* "silly options" */ + return mss; + if (opsize > length) + return mss; /* fail on partial options */ + if (opcode == TCPOPT_MSS && opsize == TCPOLEN_MSS) { + u16 in_mss = get_unaligned_be16(ptr); + + if (in_mss) { + if (user_mss && user_mss < in_mss) + in_mss = user_mss; + mss = in_mss; + } + } + ptr += opsize - 2; + length -= opsize; + } + } + return mss; +} + /* 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. @@ -3875,6 +3926,10 @@ void tcp_parse_options(const struct net *net, */ break; #endif + case TCPOPT_MPTCP: + mptcp_parse_option(skb, ptr, opsize, opt_rx); + break; + case TCPOPT_FASTOPEN: tcp_parse_fastopen_option( opsize - TCPOLEN_FASTOPEN_BASE, @@ -4216,8 +4271,10 @@ static void tcp_rcv_spurious_retrans(struct sock *sk, const struct sk_buff *skb) * The receiver remembers and reflects via DSACKs. Leverage the * DSACK state and change the txhash to re-route speculatively. */ - if (TCP_SKB_CB(skb)->seq == tcp_sk(sk)->duplicate_sack[0].start_seq) + if (TCP_SKB_CB(skb)->seq == tcp_sk(sk)->duplicate_sack[0].start_seq) { sk_rethink_txhash(sk); + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDUPLICATEDATAREHASH); + } } static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb) @@ -4375,6 +4432,9 @@ static bool tcp_try_coalesce(struct sock *sk, if (TCP_SKB_CB(from)->seq != TCP_SKB_CB(to)->end_seq) return false; + if (!mptcp_skb_can_collapse(to, from)) + return false; + #ifdef CONFIG_TLS_DEVICE if (from->decrypted != to->decrypted) return false; @@ -4512,6 +4572,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) tp->pred_flags = 0; inet_csk_schedule_ack(sk); + tp->rcv_ooopack += max_t(u16, 1, skb_shinfo(skb)->gso_segs); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOQUEUE); seq = TCP_SKB_CB(skb)->seq; end_seq = TCP_SKB_CB(skb)->end_seq; @@ -4712,6 +4773,9 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) bool fragstolen; int eaten; + if (sk_is_mptcp(sk)) + mptcp_incoming_options(sk, skb, &tp->rx_opt); + if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) { __kfree_skb(skb); return; @@ -4883,7 +4947,7 @@ restart: /* The first skb to collapse is: * - not SYN/FIN and * - bloated or contains data before "start" or - * overlaps to the next one. + * overlaps to the next one and mptcp allow collapsing. */ if (!(TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) && (tcp_win_from_space(sk, skb->truesize) > skb->len || @@ -4892,7 +4956,7 @@ restart: break; } - if (n && n != tail && + if (n && n != tail && mptcp_skb_can_collapse(skb, n) && TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(n)->seq) { end_of_skbs = false; break; @@ -4925,6 +4989,7 @@ restart: else __skb_queue_tail(&tmp, nskb); /* defer rbtree insertion */ skb_set_owner_r(nskb, sk); + mptcp_skb_ext_move(nskb, skb); /* Copy data, releasing collapsed skbs. */ while (copy > 0) { @@ -4944,6 +5009,7 @@ restart: skb = tcp_collapse_one(sk, skb, list, root); if (!skb || skb == tail || + !mptcp_skb_can_collapse(nskb, skb) || (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN))) goto end; #ifdef CONFIG_TLS_DEVICE @@ -5312,7 +5378,7 @@ static void tcp_check_urg(struct sock *sk, const struct tcphdr *th) } tp->urg_data = TCP_URG_NOTYET; - tp->urg_seq = ptr; + WRITE_ONCE(tp->urg_seq, ptr); /* Disable header prediction. */ tp->pred_flags = 0; @@ -5768,6 +5834,10 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, tcp_fastopen_cache_set(sk, mss, cookie, syn_drop, try_exp); if (data) { /* Retransmit unacked data in SYN */ + if (tp->total_retrans) + tp->fastopen_client_fail = TFO_SYN_RETRANSMITTED; + else + tp->fastopen_client_fail = TFO_DATA_NOT_ACKED; skb_rbtree_walk_from(data) { if (__tcp_retransmit_skb(sk, data, 1)) break; @@ -5838,8 +5908,14 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, * the segment and return)" */ if (!after(TCP_SKB_CB(skb)->ack_seq, tp->snd_una) || - after(TCP_SKB_CB(skb)->ack_seq, tp->snd_nxt)) + after(TCP_SKB_CB(skb)->ack_seq, tp->snd_nxt)) { + /* Previous FIN/ACK or RST/ACK might be ignored. */ + if (icsk->icsk_retransmits == 0) + inet_csk_reset_xmit_timer(sk, + ICSK_TIME_RETRANS, + TCP_TIMEOUT_MIN, TCP_RTO_MAX); goto reset_and_undo; + } if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && !between(tp->rx_opt.rcv_tsecr, tp->retrans_stamp, @@ -5888,7 +5964,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, /* Ok.. it's good. Set up sequence numbers and * move to established. */ - tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; + WRITE_ONCE(tp->rcv_nxt, TCP_SKB_CB(skb)->seq + 1); tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1; /* RFC1323: The window in SYN & SYN/ACK segments is @@ -5914,10 +5990,13 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); tcp_initialize_rcv_mss(sk); + if (sk_is_mptcp(sk)) + mptcp_rcv_synsent(sk); + /* Remember, tcp_poll() does not lock socket! * Change state from SYN-SENT only after copied_seq * is initialized. */ - tp->copied_seq = tp->rcv_nxt; + WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); smc_check_reset_syn(tp); @@ -5991,8 +6070,8 @@ discard: tp->tcp_header_len = sizeof(struct tcphdr); } - tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; - tp->copied_seq = tp->rcv_nxt; + WRITE_ONCE(tp->rcv_nxt, TCP_SKB_CB(skb)->seq + 1); + WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1; /* RFC1323: The window in SYN & SYN/ACK segments is @@ -6043,6 +6122,8 @@ reset_and_undo: static void tcp_rcv_synrecv_state_fastopen(struct sock *sk) { + struct request_sock *req; + tcp_try_undo_loss(sk, false); /* Reset rtx states to prevent spurious retransmits_timed_out() */ @@ -6052,7 +6133,9 @@ static void tcp_rcv_synrecv_state_fastopen(struct sock *sk) /* Once we leave TCP_SYN_RECV or TCP_FIN_WAIT_1, * we no longer need req so release it. */ - reqsk_fastopen_remove(sk, tcp_sk(sk)->fastopen_rsk, false); + req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, + lockdep_sock_is_held(sk)); + reqsk_fastopen_remove(sk, req, false); /* Re-arm the timer because data may have been sent out. * This is similar to the regular data transmission case @@ -6127,7 +6210,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tcp_mstamp_refresh(tp); tp->rx_opt.saw_tstamp = 0; - req = tp->fastopen_rsk; + req = rcu_dereference_protected(tp->fastopen_rsk, + lockdep_sock_is_held(sk)); if (req) { bool req_stolen; @@ -6167,7 +6251,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tcp_try_undo_spurious_syn(sk); tp->retrans_stamp = 0; tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); - tp->copied_seq = tp->rcv_nxt; + WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); } smp_mb(); tcp_set_state(sk, TCP_ESTABLISHED); @@ -6274,8 +6358,11 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) case TCP_CLOSE_WAIT: case TCP_CLOSING: case TCP_LAST_ACK: - if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) + if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) { + if (sk_is_mptcp(sk)) + mptcp_incoming_options(sk, skb, &tp->rx_opt); break; + } /* fall through */ case TCP_FIN_WAIT1: case TCP_FIN_WAIT2: @@ -6422,9 +6509,7 @@ EXPORT_SYMBOL(inet_reqsk_alloc); /* * Return true if a syncookie should be sent */ -static bool tcp_syn_flood_action(const struct sock *sk, - const struct sk_buff *skb, - const char *proto) +static bool tcp_syn_flood_action(const struct sock *sk, const char *proto) { struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; const char *msg = "Dropping request"; @@ -6444,7 +6529,7 @@ static bool tcp_syn_flood_action(const struct sock *sk, net->ipv4.sysctl_tcp_syncookies != 2 && xchg(&queue->synflood_warned, 1) == 0) net_info_ratelimited("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n", - proto, ntohs(tcp_hdr(skb)->dest), msg); + proto, sk->sk_num, msg); return want_cookie; } @@ -6466,6 +6551,36 @@ static void tcp_reqsk_record_syn(const struct sock *sk, } } +/* If a SYN cookie is required and supported, returns a clamped MSS value to be + * used for SYN cookie generation. + */ +u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops, + const struct tcp_request_sock_ops *af_ops, + struct sock *sk, struct tcphdr *th) +{ + struct tcp_sock *tp = tcp_sk(sk); + u16 mss; + + if (sock_net(sk)->ipv4.sysctl_tcp_syncookies != 2 && + !inet_csk_reqsk_queue_is_full(sk)) + return 0; + + if (!tcp_syn_flood_action(sk, rsk_ops->slab_name)) + return 0; + + if (sk_acceptq_is_full(sk)) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); + return 0; + } + + mss = tcp_parse_mss_option(th, tp->rx_opt.user_mss); + if (!mss) + mss = af_ops->mss_clamp; + + return mss; +} +EXPORT_SYMBOL_GPL(tcp_get_syncookie_mss); + 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) @@ -6487,7 +6602,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, */ if ((net->ipv4.sysctl_tcp_syncookies == 2 || inet_csk_reqsk_queue_is_full(sk)) && !isn) { - want_cookie = tcp_syn_flood_action(sk, skb, rsk_ops->slab_name); + want_cookie = tcp_syn_flood_action(sk, rsk_ops->slab_name); if (!want_cookie) goto drop; } @@ -6503,6 +6618,9 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tcp_rsk(req)->af_specific = af_ops; tcp_rsk(req)->ts_off = 0; +#if IS_ENABLED(CONFIG_MPTCP) + tcp_rsk(req)->is_mptcp = 0; +#endif tcp_clear_options(&tmp_opt); tmp_opt.mss_clamp = af_ops->mss_clamp; @@ -6525,6 +6643,9 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, af_ops->init_req(req, sk, skb); + if (IS_ENABLED(CONFIG_MPTCP) && want_cookie) + tcp_rsk(req)->is_mptcp = 0; + if (security_inet_conn_request(sk, skb, req)) goto drop_and_free; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index d57641cb3477..df1166b76126 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -121,11 +121,9 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) #if IS_ENABLED(CONFIG_IPV6) if (tw->tw_family == AF_INET6) { if (ipv6_addr_loopback(&tw->tw_v6_daddr) || - (ipv6_addr_v4mapped(&tw->tw_v6_daddr) && - (tw->tw_v6_daddr.s6_addr[12] == 127)) || + ipv6_addr_v4mapped_loopback(&tw->tw_v6_daddr) || ipv6_addr_loopback(&tw->tw_v6_rcv_saddr) || - (ipv6_addr_v4mapped(&tw->tw_v6_rcv_saddr) && - (tw->tw_v6_rcv_saddr.s6_addr[12] == 127))) + ipv6_addr_v4mapped_loopback(&tw->tw_v6_rcv_saddr)) loopback = true; } else #endif @@ -164,9 +162,11 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) * without appearing to create any others. */ if (likely(!tp->repair)) { - tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2; - if (tp->write_seq == 0) - tp->write_seq = 1; + u32 seq = tcptw->tw_snd_nxt + 65535 + 2; + + if (!seq) + seq = 1; + WRITE_ONCE(tp->write_seq, seq); tp->rx_opt.ts_recent = tcptw->tw_ts_recent; tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp; } @@ -253,7 +253,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) tp->rx_opt.ts_recent = 0; tp->rx_opt.ts_recent_stamp = 0; if (likely(!tp->repair)) - tp->write_seq = 0; + WRITE_ONCE(tp->write_seq, 0); } inet->inet_dport = usin->sin_port; @@ -291,16 +291,17 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (likely(!tp->repair)) { if (!tp->write_seq) - tp->write_seq = secure_tcp_seq(inet->inet_saddr, - inet->inet_daddr, - inet->inet_sport, - usin->sin_port); + WRITE_ONCE(tp->write_seq, + secure_tcp_seq(inet->inet_saddr, + inet->inet_daddr, + inet->inet_sport, + usin->sin_port)); tp->tsoffset = secure_tcp_ts_off(sock_net(sk), inet->inet_saddr, inet->inet_daddr); } - inet->inet_id = tp->write_seq ^ jiffies; + inet->inet_id = prandom_u32(); if (tcp_fastopen_defer_connect(sk, &err)) return err; @@ -478,7 +479,7 @@ int tcp_v4_err(struct sk_buff *icmp_skb, u32 info) icsk = inet_csk(sk); tp = tcp_sk(sk); /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ - fastopen = tp->fastopen_rsk; + fastopen = rcu_dereference(tp->fastopen_rsk); snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; if (sk->sk_state != TCP_LISTEN && !between(seq, snd_una, tp->snd_nxt)) { @@ -700,9 +701,21 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) rcu_read_lock(); hash_location = tcp_parse_md5sig_option(th); if (sk && sk_fullsock(sk)) { - key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *) - &ip_hdr(skb)->saddr, AF_INET); + const union tcp_md5_addr *addr; + int l3index; + + /* sdif set, means packet ingressed via a device + * in an L3 domain and inet_iif is set to it. + */ + l3index = tcp_v4_sdif(skb) ? inet_iif(skb) : 0; + addr = (union tcp_md5_addr *)&ip_hdr(skb)->saddr; + key = tcp_md5_do_lookup(sk, l3index, addr, AF_INET); } else if (hash_location) { + const union tcp_md5_addr *addr; + int sdif = tcp_v4_sdif(skb); + int dif = inet_iif(skb); + int l3index; + /* * active side is lost. Try to find listening socket through * source port, and then find md5 key through listening socket. @@ -713,14 +726,17 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) sk1 = __inet_lookup_listener(net, &tcp_hashinfo, NULL, 0, ip_hdr(skb)->saddr, th->source, ip_hdr(skb)->daddr, - ntohs(th->source), inet_iif(skb), - tcp_v4_sdif(skb)); + ntohs(th->source), dif, sdif); /* don't send rst if it can't find key */ if (!sk1) goto out; - key = tcp_md5_do_lookup(sk1, (union tcp_md5_addr *) - &ip_hdr(skb)->saddr, AF_INET); + /* sdif set, means packet ingressed via a device + * in an L3 domain and dif is set to it. + */ + l3index = sdif ? dif : 0; + addr = (union tcp_md5_addr *)&ip_hdr(skb)->saddr; + key = tcp_md5_do_lookup(sk1, l3index, addr, AF_INET); if (!key) goto out; @@ -771,6 +787,8 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) if (sk) { ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_mark : sk->sk_mark; + ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ? + inet_twsk(sk)->tw_priority : sk->sk_priority; transmit_time = tcp_transmit_time(sk); } ip_send_unicast_reply(ctl_sk, @@ -866,6 +884,8 @@ static void tcp_v4_send_ack(const struct sock *sk, ctl_sk = this_cpu_read(*net->ipv4.tcp_sk); ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_mark : sk->sk_mark; + ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ? + inet_twsk(sk)->tw_priority : sk->sk_priority; transmit_time = tcp_transmit_time(sk); ip_send_unicast_reply(ctl_sk, skb, &TCP_SKB_CB(skb)->header.h4.opt, @@ -900,6 +920,9 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *req) { + const union tcp_md5_addr *addr; + int l3index; + /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV * sk->sk_state == TCP_SYN_RECV -> for Fast Open. */ @@ -911,14 +934,15 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, * exception of <SYN> segments, MUST be right-shifted by * Rcv.Wind.Shift bits: */ + addr = (union tcp_md5_addr *)&ip_hdr(skb)->saddr; + l3index = tcp_v4_sdif(skb) ? inet_iif(skb) : 0; tcp_v4_send_ack(sk, skb, seq, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, req->ts_recent, 0, - tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->saddr, - AF_INET), + tcp_md5_do_lookup(sk, l3index, addr, AF_INET), inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0, ip_hdr(skb)->tos); } @@ -978,7 +1002,7 @@ DEFINE_STATIC_KEY_FALSE(tcp_md5_needed); EXPORT_SYMBOL(tcp_md5_needed); /* Find the Key structure for an address. */ -struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, +struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index, const union tcp_md5_addr *addr, int family) { @@ -998,7 +1022,8 @@ struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, hlist_for_each_entry_rcu(key, &md5sig->head, node) { if (key->family != family) continue; - + if (key->l3index && key->l3index != l3index) + continue; if (family == AF_INET) { mask = inet_make_mask(key->prefixlen); match = (key->addr.a4.s_addr & mask) == @@ -1022,7 +1047,8 @@ EXPORT_SYMBOL(__tcp_md5_do_lookup); static struct tcp_md5sig_key *tcp_md5_do_lookup_exact(const struct sock *sk, const union tcp_md5_addr *addr, - int family, u8 prefixlen) + int family, u8 prefixlen, + int l3index) { const struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; @@ -1041,6 +1067,8 @@ static struct tcp_md5sig_key *tcp_md5_do_lookup_exact(const struct sock *sk, hlist_for_each_entry_rcu(key, &md5sig->head, node) { if (key->family != family) continue; + if (key->l3index && key->l3index != l3index) + continue; if (!memcmp(&key->addr, addr, size) && key->prefixlen == prefixlen) return key; @@ -1052,23 +1080,26 @@ struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, const struct sock *addr_sk) { const union tcp_md5_addr *addr; + int l3index; + l3index = l3mdev_master_ifindex_by_index(sock_net(sk), + addr_sk->sk_bound_dev_if); addr = (const union tcp_md5_addr *)&addr_sk->sk_daddr; - return tcp_md5_do_lookup(sk, addr, AF_INET); + return tcp_md5_do_lookup(sk, l3index, addr, AF_INET); } EXPORT_SYMBOL(tcp_v4_md5_lookup); /* This can be called on a newly created socket, from other files */ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, - int family, u8 prefixlen, const u8 *newkey, u8 newkeylen, - gfp_t gfp) + int family, u8 prefixlen, int l3index, + const u8 *newkey, u8 newkeylen, gfp_t gfp) { /* Add Key to the list */ struct tcp_md5sig_key *key; struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_info *md5sig; - key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen); + key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index); if (key) { /* Pre-existing entry - just update that one. */ memcpy(key->key, newkey, newkeylen); @@ -1100,6 +1131,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, key->keylen = newkeylen; key->family = family; key->prefixlen = prefixlen; + key->l3index = l3index; memcpy(&key->addr, addr, (family == AF_INET6) ? sizeof(struct in6_addr) : sizeof(struct in_addr)); @@ -1109,11 +1141,11 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, EXPORT_SYMBOL(tcp_md5_do_add); int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family, - u8 prefixlen) + u8 prefixlen, int l3index) { struct tcp_md5sig_key *key; - key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen); + key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index); if (!key) return -ENOENT; hlist_del_rcu(&key->node); @@ -1144,7 +1176,9 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, int optname, { struct tcp_md5sig cmd; struct sockaddr_in *sin = (struct sockaddr_in *)&cmd.tcpm_addr; + const union tcp_md5_addr *addr; u8 prefixlen = 32; + int l3index = 0; if (optlen < sizeof(cmd)) return -EINVAL; @@ -1162,16 +1196,34 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, int optname, return -EINVAL; } + if (optname == TCP_MD5SIG_EXT && + cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX) { + struct net_device *dev; + + rcu_read_lock(); + dev = dev_get_by_index_rcu(sock_net(sk), cmd.tcpm_ifindex); + if (dev && netif_is_l3_master(dev)) + l3index = dev->ifindex; + + rcu_read_unlock(); + + /* ok to reference set/not set outside of rcu; + * right now device MUST be an L3 master + */ + if (!dev || !l3index) + return -EINVAL; + } + + addr = (union tcp_md5_addr *)&sin->sin_addr.s_addr; + if (!cmd.tcpm_keylen) - return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr, - AF_INET, prefixlen); + return tcp_md5_do_del(sk, addr, AF_INET, prefixlen, l3index); if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN) return -EINVAL; - return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr, - AF_INET, prefixlen, cmd.tcpm_key, cmd.tcpm_keylen, - GFP_KERNEL); + return tcp_md5_do_add(sk, addr, AF_INET, prefixlen, l3index, + cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); } static int tcp_v4_md5_hash_headers(struct tcp_md5sig_pool *hp, @@ -1281,7 +1333,8 @@ 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) + const struct sk_buff *skb, + int dif, int sdif) { #ifdef CONFIG_TCP_MD5SIG /* @@ -1296,11 +1349,17 @@ static bool tcp_v4_inbound_md5_hash(const struct sock *sk, struct tcp_md5sig_key *hash_expected; const struct iphdr *iph = ip_hdr(skb); const struct tcphdr *th = tcp_hdr(skb); - int genhash; + const union tcp_md5_addr *addr; unsigned char newhash[16]; + int genhash, l3index; + + /* sdif set, means packet ingressed via a device + * in an L3 domain and dif is set to the l3mdev + */ + l3index = sdif ? dif : 0; - hash_expected = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&iph->saddr, - AF_INET); + addr = (union tcp_md5_addr *)&iph->saddr; + hash_expected = tcp_md5_do_lookup(sk, l3index, addr, AF_INET); hash_location = tcp_parse_md5sig_option(th); /* We've parsed the options - do we have a hash? */ @@ -1326,11 +1385,11 @@ static bool tcp_v4_inbound_md5_hash(const struct sock *sk, if (genhash || memcmp(hash_location, newhash, 16) != 0) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE); - net_info_ratelimited("MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s\n", + net_info_ratelimited("MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s L3 index %d\n", &iph->saddr, ntohs(th->source), &iph->daddr, ntohs(th->dest), genhash ? " tcp_v4_calc_md5_hash failed" - : ""); + : "", l3index); return true; } return false; @@ -1367,7 +1426,7 @@ struct request_sock_ops tcp_request_sock_ops __read_mostly = { .syn_ack_timeout = tcp_syn_ack_timeout, }; -static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { +const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { .mss_clamp = TCP_MSS_DEFAULT, #ifdef CONFIG_TCP_MD5SIG .req_md5_lookup = tcp_v4_md5_lookup, @@ -1414,7 +1473,9 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct tcp_sock *newtp; struct sock *newsk; #ifdef CONFIG_TCP_MD5SIG + const union tcp_md5_addr *addr; struct tcp_md5sig_key *key; + int l3index; #endif struct ip_options_rcu *inet_opt; @@ -1443,7 +1504,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, inet_csk(newsk)->icsk_ext_hdr_len = 0; if (inet_opt) inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; - newinet->inet_id = newtp->write_seq ^ jiffies; + newinet->inet_id = prandom_u32(); if (!dst) { dst = inet_csk_route_child_sock(sk, newsk, req); @@ -1462,9 +1523,10 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, tcp_initialize_rcv_mss(newsk); #ifdef CONFIG_TCP_MD5SIG + l3index = l3mdev_master_ifindex_by_index(sock_net(sk), ireq->ir_iif); /* Copy over the MD5 key from the original socket */ - key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&newinet->inet_daddr, - AF_INET); + addr = (union tcp_md5_addr *)&newinet->inet_daddr; + key = tcp_md5_do_lookup(sk, l3index, addr, AF_INET); if (key) { /* * We're using one, so create a matching key @@ -1472,8 +1534,8 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, * memory, then we end up not copying the key * across. Shucks. */ - tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newinet->inet_daddr, - AF_INET, 32, key->key, key->keylen, GFP_ATOMIC); + tcp_md5_do_add(newsk, addr, AF_INET, 32, l3index, + key->key, key->keylen, GFP_ATOMIC); sk_nocaps_add(newsk, NETIF_F_GSO_MASK); } #endif @@ -1515,6 +1577,21 @@ static struct sock *tcp_v4_cookie_check(struct sock *sk, struct sk_buff *skb) return sk; } +u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph, + struct tcphdr *th, u32 *cookie) +{ + u16 mss = 0; +#ifdef CONFIG_SYN_COOKIES + mss = tcp_get_syncookie_mss(&tcp_request_sock_ops, + &tcp_request_sock_ipv4_ops, sk, th); + if (mss) { + *cookie = __cookie_v4_init_sequence(iph, th, &mss); + tcp_synq_overflow(sk); + } +#endif + return mss; +} + /* The socket must have it's spinlock held when we get * here, unless it is a TCP_LISTEN socket. * @@ -1625,7 +1702,7 @@ int tcp_v4_early_demux(struct sk_buff *skb) bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb) { - u32 limit = sk->sk_rcvbuf + sk->sk_sndbuf; + u32 limit = READ_ONCE(sk->sk_rcvbuf) + READ_ONCE(sk->sk_sndbuf); struct skb_shared_info *shinfo; const struct tcphdr *th; struct tcphdr *thtail; @@ -1788,6 +1865,7 @@ int tcp_v4_rcv(struct sk_buff *skb) struct net *net = dev_net(skb->dev); struct sk_buff *skb_to_free; int sdif = inet_sdif(skb); + int dif = inet_iif(skb); const struct iphdr *iph; const struct tcphdr *th; bool refcounted; @@ -1836,7 +1914,7 @@ process: struct sock *nsk; sk = req->rsk_listener; - if (unlikely(tcp_v4_inbound_md5_hash(sk, skb))) { + if (unlikely(tcp_v4_inbound_md5_hash(sk, skb, dif, sdif))) { sk_drops_add(sk, skb); reqsk_put(req); goto discard_it; @@ -1894,10 +1972,10 @@ process: if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; - if (tcp_v4_inbound_md5_hash(sk, skb)) + if (tcp_v4_inbound_md5_hash(sk, skb, dif, sdif)) goto discard_and_relse; - nf_reset(skb); + nf_reset_ct(skb); if (tcp_filter(sk, skb)) goto discard_and_relse; @@ -2102,7 +2180,7 @@ void tcp_v4_destroy_sock(struct sock *sk) if (inet_csk(sk)->icsk_bind_hash) inet_put_port(sk); - BUG_ON(tp->fastopen_rsk); + BUG_ON(rcu_access_pointer(tp->fastopen_rsk)); /* If socket is aborted during connect operation */ tcp_free_fastopen_req(tp); @@ -2127,13 +2205,14 @@ static void *listening_get_next(struct seq_file *seq, void *cur) struct tcp_iter_state *st = seq->private; struct net *net = seq_file_net(seq); struct inet_listen_hashbucket *ilb; + struct hlist_nulls_node *node; struct sock *sk = cur; if (!sk) { get_head: ilb = &tcp_hashinfo.listening_hash[st->bucket]; spin_lock(&ilb->lock); - sk = sk_head(&ilb->head); + sk = sk_nulls_head(&ilb->nulls_head); st->offset = 0; goto get_sk; } @@ -2141,9 +2220,9 @@ get_head: ++st->num; ++st->offset; - sk = sk_next(sk); + sk = sk_nulls_next(sk); get_sk: - sk_for_each_from(sk) { + sk_nulls_for_each_from(sk, node) { if (!net_eq(sock_net(sk), net)) continue; if (sk->sk_family == afinfo->family) @@ -2431,17 +2510,18 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) state = inet_sk_state_load(sk); if (state == TCP_LISTEN) - rx_queue = sk->sk_ack_backlog; + rx_queue = READ_ONCE(sk->sk_ack_backlog); else /* Because we don't lock the socket, * we might find a transient negative value. */ - rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); + rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) - + READ_ONCE(tp->copied_seq), 0); seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX " "%08X %5u %8d %lu %d %pK %lu %lu %u %u %d", i, src, srcp, dest, destp, state, - tp->write_seq - tp->snd_una, + READ_ONCE(tp->write_seq) - tp->snd_una, rx_queue, timer_active, jiffies_delta_to_clock_t(timer_expires - jiffies), @@ -2598,7 +2678,8 @@ static void __net_exit tcp_sk_exit(struct net *net) int cpu; if (net->ipv4.tcp_congestion_control) - module_put(net->ipv4.tcp_congestion_control->owner); + bpf_module_put(net->ipv4.tcp_congestion_control, + net->ipv4.tcp_congestion_control->owner); for_each_possible_cpu(cpu) inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu)); @@ -2637,6 +2718,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_min_snd_mss = TCP_MIN_SND_MSS; net->ipv4.sysctl_tcp_probe_threshold = TCP_PROBE_THRESHOLD; net->ipv4.sysctl_tcp_probe_interval = TCP_PROBE_INTERVAL; + net->ipv4.sysctl_tcp_mtu_probe_floor = TCP_MIN_SND_MSS; net->ipv4.sysctl_tcp_keepalive_time = TCP_KEEPALIVE_TIME; net->ipv4.sysctl_tcp_keepalive_probes = TCP_KEEPALIVE_PROBES; @@ -2652,12 +2734,13 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT; net->ipv4.sysctl_tcp_notsent_lowat = UINT_MAX; net->ipv4.sysctl_tcp_tw_reuse = 2; + net->ipv4.sysctl_tcp_no_ssthresh_metrics_save = 1; cnt = tcp_hashinfo.ehash_mask + 1; net->ipv4.tcp_death_row.sysctl_max_tw_buckets = cnt / 2; net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo; - net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 256); + net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 128); net->ipv4.sysctl_tcp_sack = 1; net->ipv4.sysctl_tcp_window_scaling = 1; net->ipv4.sysctl_tcp_timestamps = 1; @@ -2703,7 +2786,8 @@ static int __net_init tcp_sk_init(struct net *net) /* Reno is always built in */ if (!net_eq(net, &init_net) && - try_module_get(init_net.ipv4.tcp_congestion_control->owner)) + bpf_try_module_get(init_net.ipv4.tcp_congestion_control, + init_net.ipv4.tcp_congestion_control->owner)) net->ipv4.tcp_congestion_control = init_net.ipv4.tcp_congestion_control; else net->ipv4.tcp_congestion_control = &tcp_reno; diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index c4848e7a0aad..279db8822439 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -385,7 +385,8 @@ void tcp_update_metrics(struct sock *sk) if (tcp_in_initial_slowstart(tp)) { /* Slow start still did not finish. */ - if (!tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) { + if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save && + !tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) { val = tcp_metric_get(tm, TCP_METRIC_SSTHRESH); if (val && (tp->snd_cwnd >> 1) > val) tcp_metric_set(tm, TCP_METRIC_SSTHRESH, @@ -400,7 +401,8 @@ void tcp_update_metrics(struct sock *sk) } else if (!tcp_in_slow_start(tp) && icsk->icsk_ca_state == TCP_CA_Open) { /* Cong. avoidance phase, cwnd is reliable. */ - if (!tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) + if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save && + !tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) tcp_metric_set(tm, TCP_METRIC_SSTHRESH, max(tp->snd_cwnd >> 1, tp->snd_ssthresh)); if (!tcp_metric_locked(tm, TCP_METRIC_CWND)) { @@ -416,7 +418,8 @@ void tcp_update_metrics(struct sock *sk) tcp_metric_set(tm, TCP_METRIC_CWND, (val + tp->snd_ssthresh) >> 1); } - if (!tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) { + if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save && + !tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) { val = tcp_metric_get(tm, TCP_METRIC_SSTHRESH); if (val && tp->snd_ssthresh > val) tcp_metric_set(tm, TCP_METRIC_SSTHRESH, @@ -441,6 +444,7 @@ void tcp_init_metrics(struct sock *sk) { struct dst_entry *dst = __sk_dst_get(sk); struct tcp_sock *tp = tcp_sk(sk); + struct net *net = sock_net(sk); struct tcp_metrics_block *tm; u32 val, crtt = 0; /* cached RTT scaled by 8 */ @@ -458,7 +462,8 @@ void tcp_init_metrics(struct sock *sk) if (tcp_metric_locked(tm, TCP_METRIC_CWND)) tp->snd_cwnd_clamp = tcp_metric_get(tm, TCP_METRIC_CWND); - val = tcp_metric_get(tm, TCP_METRIC_SSTHRESH); + val = net->ipv4.sysctl_tcp_no_ssthresh_metrics_save ? + 0 : tcp_metric_get(tm, TCP_METRIC_SSTHRESH); if (val) { tp->snd_ssthresh = val; if (tp->snd_ssthresh > tp->snd_cwnd_clamp) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 8bcaf2586b68..ad3b56d9fa71 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -266,6 +266,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) tw->tw_transparent = inet->transparent; tw->tw_mark = sk->sk_mark; + tw->tw_priority = sk->sk_priority; tw->tw_rcv_wscale = tp->rx_opt.rcv_wscale; tcptw->tw_rcv_nxt = tp->rcv_nxt; tcptw->tw_snd_nxt = tp->snd_nxt; @@ -413,7 +414,7 @@ void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst) rcu_read_lock(); ca = tcp_ca_find_key(ca_key); - if (likely(ca && try_module_get(ca->owner))) { + if (likely(ca && bpf_try_module_get(ca, ca->owner))) { icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst); icsk->icsk_ca_ops = ca; ca_got_dst = true; @@ -424,7 +425,7 @@ void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst) /* If no valid choice made yet, assign current system default ca. */ if (!ca_got_dst && (!icsk->icsk_ca_setsockopt || - !try_module_get(icsk->icsk_ca_ops->owner))) + !bpf_try_module_get(icsk->icsk_ca_ops, icsk->icsk_ca_ops->owner))) tcp_assign_congestion_control(sk); tcp_set_ca_state(sk, TCP_CA_Open); @@ -461,6 +462,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, struct tcp_request_sock *treq = tcp_rsk(req); struct inet_connection_sock *newicsk; struct tcp_sock *oldtp, *newtp; + u32 seq; if (!newsk) return NULL; @@ -474,12 +476,16 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, /* Now setup tcp_sock */ newtp->pred_flags = 0; - newtp->rcv_wup = newtp->copied_seq = - newtp->rcv_nxt = treq->rcv_isn + 1; + seq = treq->rcv_isn + 1; + newtp->rcv_wup = seq; + WRITE_ONCE(newtp->copied_seq, seq); + WRITE_ONCE(newtp->rcv_nxt, seq); newtp->segs_in = 1; - newtp->snd_sml = newtp->snd_una = - newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1; + seq = treq->snt_isn + 1; + newtp->snd_sml = newtp->snd_una = seq; + WRITE_ONCE(newtp->snd_nxt, seq); + newtp->snd_up = seq; INIT_LIST_HEAD(&newtp->tsq_node); INIT_LIST_HEAD(&newtp->tsorted_sent_queue); @@ -494,7 +500,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->total_retrans = req->num_retrans; tcp_init_xmit_timers(newsk); - newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1; + WRITE_ONCE(newtp->write_seq, newtp->pushed_seq = treq->snt_isn + 1); if (sock_flag(newsk, SOCK_KEEPOPEN)) inet_csk_reset_keepalive_timer(newsk, @@ -540,7 +546,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->rx_opt.mss_clamp = req->mss; tcp_ecn_openreq_child(newtp, req); newtp->fastopen_req = NULL; - newtp->fastopen_rsk = NULL; + RCU_INIT_POINTER(newtp->fastopen_rsk, NULL); __TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 979520e46e33..306e25d743e8 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -38,6 +38,7 @@ #define pr_fmt(fmt) "TCP: " fmt #include <net/tcp.h> +#include <net/mptcp.h> #include <linux/compiler.h> #include <linux/gfp.h> @@ -67,11 +68,14 @@ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); unsigned int prior_packets = tp->packets_out; - tp->snd_nxt = TCP_SKB_CB(skb)->end_seq; + WRITE_ONCE(tp->snd_nxt, TCP_SKB_CB(skb)->end_seq); __skb_unlink(skb, &sk->sk_write_queue); tcp_rbtree_insert(&sk->tcp_rtx_queue, skb); + if (tp->highest_sack == NULL) + tp->highest_sack = skb; + tp->packets_out += tcp_skb_pcount(skb); if (!prior_packets || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) tcp_rearm_rto(sk); @@ -411,6 +415,7 @@ static inline bool tcp_urg_mode(const struct tcp_sock *tp) #define OPTION_WSCALE (1 << 3) #define OPTION_FAST_OPEN_COOKIE (1 << 8) #define OPTION_SMC (1 << 9) +#define OPTION_MPTCP (1 << 10) static void smc_options_write(__be32 *ptr, u16 *options) { @@ -436,8 +441,17 @@ struct tcp_out_options { __u8 *hash_location; /* temporary pointer, overloaded */ __u32 tsval, tsecr; /* need to include OPTION_TS */ struct tcp_fastopen_cookie *fastopen_cookie; /* Fast open cookie */ + struct mptcp_out_options mptcp; }; +static void mptcp_options_write(__be32 *ptr, struct tcp_out_options *opts) +{ +#if IS_ENABLED(CONFIG_MPTCP) + if (unlikely(OPTION_MPTCP & opts->options)) + mptcp_write_options(ptr, &opts->mptcp); +#endif +} + /* Write previously computed TCP options to the packet. * * Beware: Something in the Internet is very sensitive to the ordering of @@ -546,6 +560,8 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp, } smc_options_write(ptr, &options); + + mptcp_options_write(ptr, opts); } static void smc_set_option(const struct tcp_sock *tp, @@ -581,6 +597,22 @@ static void smc_set_option_cond(const struct tcp_sock *tp, #endif } +static void mptcp_set_option_cond(const struct request_sock *req, + struct tcp_out_options *opts, + unsigned int *remaining) +{ + if (rsk_is_mptcp(req)) { + unsigned int size; + + if (mptcp_synack_options(req, &size, &opts->mptcp)) { + if (*remaining >= size) { + opts->options |= OPTION_MPTCP; + *remaining -= size; + } + } + } +} + /* Compute TCP options for SYN packets. This is not the final * network wire format yet. */ @@ -650,6 +682,15 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, smc_set_option(tp, opts, &remaining); + if (sk_is_mptcp(sk)) { + unsigned int size; + + if (mptcp_syn_options(sk, skb, &size, &opts->mptcp)) { + opts->options |= OPTION_MPTCP; + remaining -= size; + } + } + return MAX_TCP_OPTION_SPACE - remaining; } @@ -711,6 +752,8 @@ static unsigned int tcp_synack_options(const struct sock *sk, } } + mptcp_set_option_cond(req, opts, &remaining); + smc_set_option_cond(tcp_sk(sk), ireq, opts, &remaining); return MAX_TCP_OPTION_SPACE - remaining; @@ -748,13 +791,35 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb size += TCPOLEN_TSTAMP_ALIGNED; } + /* MPTCP options have precedence over SACK for the limited TCP + * option space because a MPTCP connection would be forced to + * fall back to regular TCP if a required multipath option is + * missing. SACK still gets a chance to use whatever space is + * left. + */ + if (sk_is_mptcp(sk)) { + unsigned int remaining = MAX_TCP_OPTION_SPACE - size; + unsigned int opt_size = 0; + + if (mptcp_established_options(sk, skb, &opt_size, remaining, + &opts->mptcp)) { + opts->options |= OPTION_MPTCP; + size += opt_size; + } + } + eff_sacks = tp->rx_opt.num_sacks + tp->rx_opt.dsack; if (unlikely(eff_sacks)) { const unsigned int remaining = MAX_TCP_OPTION_SPACE - size; + if (unlikely(remaining < TCPOLEN_SACK_BASE_ALIGNED + + TCPOLEN_SACK_PERBLOCK)) + return size; + opts->num_sack_blocks = min_t(unsigned int, eff_sacks, (remaining - TCPOLEN_SACK_BASE_ALIGNED) / TCPOLEN_SACK_PERBLOCK); + size += TCPOLEN_SACK_BASE_ALIGNED + opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK; } @@ -1050,11 +1115,22 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, tcb = TCP_SKB_CB(skb); memset(&opts, 0, sizeof(opts)); - if (unlikely(tcb->tcp_flags & TCPHDR_SYN)) + if (unlikely(tcb->tcp_flags & TCPHDR_SYN)) { tcp_options_size = tcp_syn_options(sk, skb, &opts, &md5); - else + } else { tcp_options_size = tcp_established_options(sk, skb, &opts, &md5); + /* Force a PSH flag on all (GSO) packets to expedite GRO flush + * at receiver : This slightly improve GRO performance. + * Note that we do not force the PSH flag for non GSO packets, + * because they might be sent under high congestion events, + * and in this case it is better to delay the delivery of 1-MSS + * packets and thus the corresponding ACK packet that would + * release the following packet. + */ + if (tcp_skb_pcount(skb) > 1) + tcb->tcp_flags |= TCPHDR_PSH; + } tcp_header_size = tcp_options_size + sizeof(struct tcphdr); /* if no packet is in qdisc/device queue, then allow XPS to select @@ -1185,10 +1261,10 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); /* Advance write_seq and place onto the write_queue. */ - tp->write_seq = TCP_SKB_CB(skb)->end_seq; + WRITE_ONCE(tp->write_seq, TCP_SKB_CB(skb)->end_seq); __skb_header_release(skb); tcp_add_write_queue_tail(sk, skb); - sk->sk_wmem_queued += skb->truesize; + sk_wmem_queued_add(sk, skb->truesize); sk_mem_charge(sk, skb->truesize); } @@ -1322,7 +1398,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, return -ENOMEM; /* We'll just try again later. */ skb_copy_decrypted(buff, skb); - sk->sk_wmem_queued += buff->truesize; + sk_wmem_queued_add(sk, buff->truesize); sk_mem_charge(sk, buff->truesize); nlen = skb->len - len - nsize; buff->truesize += nlen; @@ -1403,7 +1479,7 @@ static int __pskb_trim_head(struct sk_buff *skb, int len) } else { shinfo->frags[k] = shinfo->frags[i]; if (eat) { - shinfo->frags[k].page_offset += eat; + skb_frag_off_add(&shinfo->frags[k], eat); skb_frag_size_sub(&shinfo->frags[k], eat); eat = 0; } @@ -1432,7 +1508,7 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) if (delta_truesize) { skb->truesize -= delta_truesize; - sk->sk_wmem_queued -= delta_truesize; + sk_wmem_queued_add(sk, -delta_truesize); sk_mem_uncharge(sk, delta_truesize); sock_set_flag(sk, SOCK_QUEUE_SHRUNK); } @@ -1713,7 +1789,7 @@ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, u32 bytes, segs; bytes = min_t(unsigned long, - sk->sk_pacing_rate >> sk->sk_pacing_shift, + sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift), sk->sk_gso_max_size - 1 - MAX_TCP_HEADER); /* Goal is to send at least one packet per ms, @@ -1877,7 +1953,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, return -ENOMEM; skb_copy_decrypted(buff, skb); - sk->sk_wmem_queued += buff->truesize; + sk_wmem_queued_add(sk, buff->truesize); sk_mem_charge(sk, buff->truesize); buff->truesize += nlen; skb->truesize -= nlen; @@ -2053,7 +2129,7 @@ static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len) if (len <= skb->len) break; - if (unlikely(TCP_SKB_CB(skb)->eor)) + if (unlikely(TCP_SKB_CB(skb)->eor) || tcp_has_tx_tstamp(skb)) return false; len -= skb->len; @@ -2141,7 +2217,7 @@ static int tcp_mtu_probe(struct sock *sk) nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC, false); if (!nskb) return -1; - sk->sk_wmem_queued += nskb->truesize; + sk_wmem_queued_add(sk, nskb->truesize); sk_mem_charge(sk, nskb->truesize); skb = tcp_send_head(sk); @@ -2170,6 +2246,7 @@ static int tcp_mtu_probe(struct sock *sk) * we need to propagate it to the new skb. */ TCP_SKB_CB(nskb)->eor = TCP_SKB_CB(skb)->eor; + tcp_skb_collapse_tstamp(nskb, skb); tcp_unlink_write_queue(skb, sk); sk_wmem_free_skb(sk, skb); } else { @@ -2247,7 +2324,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, limit = max_t(unsigned long, 2 * skb->truesize, - sk->sk_pacing_rate >> sk->sk_pacing_shift); + sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift)); if (sk->sk_pacing_status == SK_PACING_NONE) limit = min_t(unsigned long, limit, sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes); @@ -2425,6 +2502,14 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (tcp_small_queue_check(sk, skb, 0)) break; + /* Argh, we hit an empty skb(), presumably a thread + * is sleeping in sendmsg()/sk_stream_wait_memory(). + * We do not want to send a pure-ack packet and have + * a strange looking rtx queue with empty packet(s). + */ + if (TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq) + break; + if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp))) break; @@ -2470,7 +2555,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) /* Don't do any loss probe on a Fast Open connection before 3WHS * finishes. */ - if (tp->fastopen_rsk) + if (rcu_access_pointer(tp->fastopen_rsk)) return false; early_retrans = sock_net(sk)->ipv4.sysctl_tcp_early_retrans; @@ -2841,7 +2926,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, if (!tcp_can_collapse(sk, skb)) break; - if (!tcp_skb_can_collapse_to(to)) + if (!tcp_skb_can_collapse(to, skb)) break; space -= skb->len; @@ -3108,7 +3193,7 @@ void sk_forced_mem_schedule(struct sock *sk, int size) */ void tcp_send_fin(struct sock *sk) { - struct sk_buff *skb, *tskb = tcp_write_queue_tail(sk); + struct sk_buff *skb, *tskb, *tail = tcp_write_queue_tail(sk); struct tcp_sock *tp = tcp_sk(sk); /* Optimization, tack on the FIN if we have one skb in write queue and @@ -3116,6 +3201,7 @@ void tcp_send_fin(struct sock *sk) * Note: in the latter case, FIN packet will be sent after a timeout, * as TCP stack thinks it has already been transmitted. */ + tskb = tail; if (!tskb && tcp_under_memory_pressure(sk)) tskb = skb_rb_last(&sk->tcp_rtx_queue); @@ -3123,14 +3209,14 @@ void tcp_send_fin(struct sock *sk) TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN; TCP_SKB_CB(tskb)->end_seq++; tp->write_seq++; - if (tcp_write_queue_empty(sk)) { + if (!tail) { /* This means tskb was already sent. * Pretend we included the FIN on previous transmit. * We need to set tp->snd_nxt to the value it would have * if FIN had been sent. This is because retransmit path * does not change tp->snd_nxt. */ - tp->snd_nxt++; + WRITE_ONCE(tp->snd_nxt, tp->snd_nxt + 1); return; } } else { @@ -3207,10 +3293,11 @@ int tcp_send_synack(struct sock *sk) if (!nskb) return -ENOMEM; INIT_LIST_HEAD(&nskb->tcp_tsorted_anchor); + tcp_highest_sack_replace(sk, skb, nskb); tcp_rtx_queue_unlink_and_free(skb, sk); __skb_header_release(nskb); tcp_rbtree_insert(&sk->tcp_rtx_queue, nskb); - sk->sk_wmem_queued += nskb->truesize; + sk_wmem_queued_add(sk, nskb->truesize); sk_mem_charge(sk, nskb->truesize); skb = nskb; } @@ -3278,7 +3365,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, now = tcp_clock_ns(); #ifdef CONFIG_SYN_COOKIES if (unlikely(req->cookie_ts)) - skb->skb_mstamp_ns = cookie_init_timestamp(req); + skb->skb_mstamp_ns = cookie_init_timestamp(req, now); else #endif { @@ -3343,8 +3430,8 @@ static void tcp_ca_dst_init(struct sock *sk, const struct dst_entry *dst) rcu_read_lock(); ca = tcp_ca_find_key(ca_key); - if (likely(ca && try_module_get(ca->owner))) { - module_put(icsk->icsk_ca_ops->owner); + if (likely(ca && bpf_try_module_get(ca, ca->owner))) { + bpf_module_put(icsk->icsk_ca_ops, icsk->icsk_ca_ops->owner); icsk->icsk_ca_dst_locked = tcp_ca_dst_locked(dst); icsk->icsk_ca_ops = ca; } @@ -3414,14 +3501,14 @@ static void tcp_connect_init(struct sock *sk) tp->snd_una = tp->write_seq; tp->snd_sml = tp->write_seq; tp->snd_up = tp->write_seq; - tp->snd_nxt = tp->write_seq; + WRITE_ONCE(tp->snd_nxt, tp->write_seq); if (likely(!tp->repair)) tp->rcv_nxt = 0; else tp->rcv_tstamp = tcp_jiffies32; tp->rcv_wup = tp->rcv_nxt; - tp->copied_seq = tp->rcv_nxt; + WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); inet_csk(sk)->icsk_rto = tcp_timeout_init(sk); inet_csk(sk)->icsk_retransmits = 0; @@ -3435,9 +3522,9 @@ static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb) tcb->end_seq += skb->len; __skb_header_release(skb); - sk->sk_wmem_queued += skb->truesize; + sk_wmem_queued_add(sk, skb->truesize); sk_mem_charge(sk, skb->truesize); - tp->write_seq = tcb->end_seq; + WRITE_ONCE(tp->write_seq, tcb->end_seq); tp->packets_out += tcp_skb_pcount(skb); } @@ -3574,11 +3661,11 @@ int tcp_connect(struct sock *sk) /* We change tp->snd_nxt after the tcp_transmit_skb() call * in order to make this packet get counted in tcpOutSegs. */ - tp->snd_nxt = tp->write_seq; + WRITE_ONCE(tp->snd_nxt, tp->write_seq); tp->pushed_seq = tp->write_seq; buff = tcp_send_head(sk); if (unlikely(buff)) { - tp->snd_nxt = TCP_SKB_CB(buff)->seq; + WRITE_ONCE(tp->snd_nxt, TCP_SKB_CB(buff)->seq); tp->pushed_seq = TCP_SKB_CB(buff)->seq; } TCP_INC_STATS(sock_net(sk), TCP_MIB_ACTIVEOPENS); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index c801cd37cc2a..c3f26dcd6704 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -154,7 +154,7 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk) } else { mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1; mss = min(net->ipv4.sysctl_tcp_base_mss, mss); - mss = max(mss, 68 - tcp_sk(sk)->tcp_header_len); + mss = max(mss, net->ipv4.sysctl_tcp_mtu_probe_floor); mss = max(mss, net->ipv4.sysctl_tcp_min_snd_mss); icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss); } @@ -198,8 +198,13 @@ static bool retransmits_timed_out(struct sock *sk, return false; start_ts = tcp_sk(sk)->retrans_stamp; - if (likely(timeout == 0)) - timeout = tcp_model_timeout(sk, boundary, TCP_RTO_MIN); + if (likely(timeout == 0)) { + unsigned int rto_base = TCP_RTO_MIN; + + if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) + rto_base = tcp_timeout_init(sk); + timeout = tcp_model_timeout(sk, boundary, rto_base); + } return (s32)(tcp_time_stamp(tcp_sk(sk)) - start_ts - timeout) >= 0; } @@ -210,7 +215,7 @@ static int tcp_write_timeout(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); - bool expired, do_reset; + bool expired = false, do_reset; int retry_until; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { @@ -218,6 +223,9 @@ static int tcp_write_timeout(struct sock *sk) dst_negative_advice(sk); } else { sk_rethink_txhash(sk); + tp->timeout_rehash++; + __NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPTIMEOUTREHASH); } retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries; expired = icsk->icsk_retransmits >= retry_until; @@ -229,6 +237,9 @@ static int tcp_write_timeout(struct sock *sk) dst_negative_advice(sk); } else { sk_rethink_txhash(sk); + tp->timeout_rehash++; + __NET_INC_STATS(sock_net(sk), + LINUX_MIB_TCPTIMEOUTREHASH); } retry_until = net->ipv4.sysctl_tcp_retries2; @@ -242,9 +253,10 @@ static int tcp_write_timeout(struct sock *sk) if (tcp_out_of_resources(sk, do_reset)) return 1; } + } + if (!expired) expired = retransmits_timed_out(sk, retry_until, icsk->icsk_user_timeout); - } tcp_fastopen_active_detect_blackhole(sk, expired); if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RTO_CB_FLAG)) @@ -380,15 +392,13 @@ abort: tcp_write_err(sk); * Timer for Fast Open socket to retransmit SYNACK. Note that the * sk here is the child socket, not the parent (listener) socket. */ -static void tcp_fastopen_synack_timer(struct sock *sk) +static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req) { struct inet_connection_sock *icsk = inet_csk(sk); int max_retries = icsk->icsk_syn_retries ? : sock_net(sk)->ipv4.sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */ struct tcp_sock *tp = tcp_sk(sk); - struct request_sock *req; - req = tcp_sk(sk)->fastopen_rsk; req->rsk_ops->syn_ack_timeout(req); if (req->num_timeout >= max_retries) { @@ -429,17 +439,26 @@ void tcp_retransmit_timer(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); struct inet_connection_sock *icsk = inet_csk(sk); + struct request_sock *req; + struct sk_buff *skb; - if (tp->fastopen_rsk) { + req = rcu_dereference_protected(tp->fastopen_rsk, + lockdep_sock_is_held(sk)); + if (req) { WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV && sk->sk_state != TCP_FIN_WAIT1); - tcp_fastopen_synack_timer(sk); + tcp_fastopen_synack_timer(sk, req); /* Before we receive ACK to our SYN-ACK don't retransmit * anything else (e.g., data or FIN segments). */ return; } - if (!tp->packets_out || WARN_ON_ONCE(tcp_rtx_queue_empty(sk))) + + if (!tp->packets_out) + return; + + skb = tcp_rtx_queue_head(sk); + if (WARN_ON_ONCE(!skb)) return; tp->tlp_high_seq = 0; @@ -473,7 +492,7 @@ void tcp_retransmit_timer(struct sock *sk) goto out; } tcp_enter_loss(sk); - tcp_retransmit_skb(sk, tcp_rtx_queue_head(sk), 1); + tcp_retransmit_skb(sk, skb, 1); __sk_dst_reset(sk); goto out_reset_timer; } diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c index 4849edb62d52..38d3ad141161 100644 --- a/net/ipv4/tcp_ulp.c +++ b/net/ipv4/tcp_ulp.c @@ -92,21 +92,26 @@ void tcp_get_available_ulp(char *buf, size_t maxlen) offs += snprintf(buf + offs, maxlen - offs, "%s%s", offs == 0 ? "" : " ", ulp_ops->name); + + if (WARN_ON_ONCE(offs >= maxlen)) + break; } rcu_read_unlock(); } -void tcp_update_ulp(struct sock *sk, struct proto *proto) +void tcp_update_ulp(struct sock *sk, struct proto *proto, + void (*write_space)(struct sock *sk)) { struct inet_connection_sock *icsk = inet_csk(sk); if (!icsk->icsk_ulp_ops) { + sk->sk_write_space = write_space; sk->sk_prot = proto; return; } if (icsk->icsk_ulp_ops->update) - icsk->icsk_ulp_ops->update(sk, proto); + icsk->icsk_ulp_ops->update(sk, proto, write_space); } void tcp_cleanup_ulp(struct sock *sk) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index d88821c794fb..db76b9609299 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -388,7 +388,7 @@ static int compute_score(struct sock *sk, struct net *net, return -1; score += 4; - if (sk->sk_incoming_cpu == raw_smp_processor_id()) + if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) score++; return score; } @@ -423,12 +423,13 @@ static struct sock *udp4_lib_lookup2(struct net *net, score = compute_score(sk, net, saddr, sport, daddr, hnum, dif, sdif); if (score > badness) { - if (sk->sk_reuseport) { + if (sk->sk_reuseport && + sk->sk_state != TCP_ESTABLISHED) { hash = udp_ehashfn(net, daddr, hnum, saddr, sport); result = reuseport_select_sock(sk, hash, skb, sizeof(struct udphdr)); - if (result) + if (result && !reuseport_has_conns(sk, false)) return result; } badness = score; @@ -820,6 +821,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4, int is_udplite = IS_UDPLITE(sk); int offset = skb_transport_offset(skb); int len = skb->len - offset; + int datalen = len - sizeof(*uh); __wsum csum = 0; /* @@ -853,10 +855,12 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4, return -EIO; } - skb_shinfo(skb)->gso_size = cork->gso_size; - skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4; - skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(len - sizeof(uh), - cork->gso_size); + if (datalen > cork->gso_size) { + skb_shinfo(skb)->gso_size = cork->gso_size; + skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4; + skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(datalen, + cork->gso_size); + } goto csum_partial; } @@ -1130,7 +1134,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl4 = &fl4_stack; - flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos, + flowi4_init_output(fl4, ipc.oif, ipc.sockc.mark, tos, RT_SCOPE_UNIVERSE, sk->sk_protocol, flow_flags, faddr, saddr, dport, inet->inet_sport, @@ -1293,6 +1297,27 @@ out: #define UDP_SKB_IS_STATELESS 0x80000000 +/* all head states (dst, sk, nf conntrack) except skb extensions are + * cleared by udp_rcv(). + * + * We need to preserve secpath, if present, to eventually process + * IP_CMSG_PASSSEC at recvmsg() time. + * + * Other extensions can be cleared. + */ +static bool udp_try_make_stateless(struct sk_buff *skb) +{ + if (!skb_has_extensions(skb)) + return true; + + if (!secpath_exists(skb)) { + skb_ext_reset(skb); + return true; + } + + return false; +} + static void udp_set_dev_scratch(struct sk_buff *skb) { struct udp_dev_scratch *scratch = udp_skb_scratch(skb); @@ -1304,14 +1329,24 @@ static void udp_set_dev_scratch(struct sk_buff *skb) scratch->csum_unnecessary = !!skb_csum_unnecessary(skb); scratch->is_linear = !skb_is_nonlinear(skb); #endif - /* all head states execept sp (dst, sk, nf) are always cleared by - * udp_rcv() and we need to preserve secpath, if present, to eventually - * process IP_CMSG_PASSSEC at recvmsg() time - */ - if (likely(!skb_sec_path(skb))) + if (udp_try_make_stateless(skb)) scratch->_tsize_state |= UDP_SKB_IS_STATELESS; } +static void udp_skb_csum_unnecessary_set(struct sk_buff *skb) +{ + /* We come here after udp_lib_checksum_complete() returned 0. + * This means that __skb_checksum_complete() might have + * set skb->csum_valid to 1. + * On 64bit platforms, we can set csum_unnecessary + * to true, but only if the skb is not shared. + */ +#if BITS_PER_LONG == 64 + if (!skb_shared(skb)) + udp_skb_scratch(skb)->csum_unnecessary = true; +#endif +} + static int udp_skb_truesize(struct sk_buff *skb) { return udp_skb_scratch(skb)->_tsize_state & ~UDP_SKB_IS_STATELESS; @@ -1333,7 +1368,8 @@ static void udp_rmem_release(struct sock *sk, int size, int partial, if (likely(partial)) { up->forward_deficit += size; size = up->forward_deficit; - if (size < (sk->sk_rcvbuf >> 2)) + if (size < (sk->sk_rcvbuf >> 2) && + !skb_queue_empty(&up->reader_queue)) return; } else { size += up->forward_deficit; @@ -1440,7 +1476,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) * queue contains some other skb */ rmem = atomic_add_return(size, &sk->sk_rmem_alloc); - if (rmem > (size + sk->sk_rcvbuf)) + if (rmem > (size + (unsigned int)sk->sk_rcvbuf)) goto uncharge_drop; spin_lock(&list->lock); @@ -1546,10 +1582,7 @@ static struct sk_buff *__first_packet_length(struct sock *sk, *total += skb->truesize; kfree_skb(skb); } else { - /* the csum related bits could be changed, refresh - * the scratch area - */ - udp_set_dev_scratch(skb); + udp_skb_csum_unnecessary_set(skb); break; } } @@ -1573,7 +1606,7 @@ static int first_packet_length(struct sock *sk) spin_lock_bh(&rcvq->lock); skb = __first_packet_length(sk, rcvq, &total); - if (!skb && !skb_queue_empty(sk_queue)) { + if (!skb && !skb_queue_empty_lockless(sk_queue)) { spin_lock(&sk_queue->lock); skb_queue_splice_tail_init(sk_queue, rcvq); spin_unlock(&sk_queue->lock); @@ -1646,7 +1679,7 @@ struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, return skb; } - if (skb_queue_empty(sk_queue)) { + if (skb_queue_empty_lockless(sk_queue)) { spin_unlock_bh(&queue->lock); goto busy_check; } @@ -1672,11 +1705,12 @@ busy_check: break; sk_busy_loop(sk, flags & MSG_DONTWAIT); - } while (!skb_queue_empty(sk_queue)); + } while (!skb_queue_empty_lockless(sk_queue)); /* sk_queue is empty, reader_queue may contain peeked packets */ } while (timeo && - !__skb_wait_for_more_packets(sk, &error, &timeo, + !__skb_wait_for_more_packets(sk, &sk->sk_receive_queue, + &error, &timeo, (struct sk_buff *)sk_queue)); *err = error; @@ -1968,7 +2002,7 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) */ if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) goto drop; - nf_reset(skb); + nf_reset_ct(skb); if (static_branch_unlikely(&udp_encap_needed_key) && up->encap_type) { int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); @@ -2072,8 +2106,7 @@ static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) BUILD_BUG_ON(sizeof(struct udp_skb_cb) > SKB_SGO_CB_OFFSET); __skb_push(skb, -skb_mac_offset(skb)); segs = udp_rcv_segment(sk, skb, true); - for (skb = segs; skb; skb = next) { - next = skb->next; + skb_list_walk_safe(segs, skb, next) { __skb_pull(skb, skb_transport_offset(skb)); ret = udp_queue_rcv_one_skb(sk, skb); if (ret > 0) @@ -2297,7 +2330,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; - nf_reset(skb); + nf_reset_ct(skb); /* No socket. Drop packet silently, if checksum is wrong */ if (udp_lib_checksum_complete(skb)) @@ -2519,9 +2552,11 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, case UDP_ENCAP: switch (val) { case 0: +#ifdef CONFIG_XFRM case UDP_ENCAP_ESPINUDP: case UDP_ENCAP_ESPINUDP_NON_IKE: up->encap_rcv = xfrm4_udp_encap_rcv; +#endif /* FALLTHROUGH */ case UDP_ENCAP_L2TPINUDP: up->encap_type = val; @@ -2708,7 +2743,7 @@ __poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait) __poll_t mask = datagram_poll(file, sock, wait); struct sock *sk = sock->sk; - if (!skb_queue_empty(&udp_sk(sk)->reader_queue)) + if (!skb_queue_empty_lockless(&udp_sk(sk)->reader_queue)) mask |= EPOLLIN | EPOLLRDNORM; /* Check for false positives due to checksum errors */ diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index a3908e55ed89..1a98583a79f4 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -184,6 +184,20 @@ out_unlock: } EXPORT_SYMBOL(skb_udp_tunnel_segment); +static struct sk_buff *__udp_gso_segment_list(struct sk_buff *skb, + netdev_features_t features) +{ + unsigned int mss = skb_shinfo(skb)->gso_size; + + skb = skb_segment_list(skb, features, skb_mac_header_len(skb)); + if (IS_ERR(skb)) + return skb; + + udp_hdr(skb)->len = htons(sizeof(struct udphdr) + mss); + + return skb; +} + struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, netdev_features_t features) { @@ -196,6 +210,9 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, __sum16 check; __be16 newlen; + if (skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST) + return __udp_gso_segment_list(gso_skb, features); + mss = skb_shinfo(gso_skb)->gso_size; if (gso_skb->len <= sizeof(*uh) + mss) return ERR_PTR(-EINVAL); @@ -354,6 +371,7 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head, struct udphdr *uh2; struct sk_buff *p; unsigned int ulen; + int ret = 0; /* requires non zero csum, for symmetry with GSO */ if (!uh->check) { @@ -369,7 +387,6 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head, } /* pull encapsulating udp header */ skb_gro_pull(skb, sizeof(struct udphdr)); - skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr)); list_for_each_entry(p, head, list) { if (!NAPI_GRO_CB(p)->same_flow) @@ -383,14 +400,40 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head, continue; } + if (NAPI_GRO_CB(skb)->is_flist != NAPI_GRO_CB(p)->is_flist) { + NAPI_GRO_CB(skb)->flush = 1; + return p; + } + /* Terminate the flow on len mismatch or if it grow "too much". * Under small packet flood GRO count could elsewhere grow a lot * leading to excessive truesize values. * On len mismatch merge the first packet shorter than gso_size, * otherwise complete the GRO packet. */ - if (ulen > ntohs(uh2->len) || skb_gro_receive(p, skb) || - ulen != ntohs(uh2->len) || + if (ulen > ntohs(uh2->len)) { + pp = p; + } else { + if (NAPI_GRO_CB(skb)->is_flist) { + if (!pskb_may_pull(skb, skb_gro_offset(skb))) { + NAPI_GRO_CB(skb)->flush = 1; + return NULL; + } + if ((skb->ip_summed != p->ip_summed) || + (skb->csum_level != p->csum_level)) { + NAPI_GRO_CB(skb)->flush = 1; + return NULL; + } + ret = skb_gro_receive_list(p, skb); + } else { + skb_gro_postpull_rcsum(skb, uh, + sizeof(struct udphdr)); + + ret = skb_gro_receive(p, skb); + } + } + + if (ret || ulen != ntohs(uh2->len) || NAPI_GRO_CB(p)->count >= UDP_GRO_CNT_MAX) pp = p; @@ -401,36 +444,29 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head, return NULL; } -INDIRECT_CALLABLE_DECLARE(struct sock *udp6_lib_lookup_skb(struct sk_buff *skb, - __be16 sport, __be16 dport)); struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, - struct udphdr *uh, udp_lookup_t lookup) + struct udphdr *uh, struct sock *sk) { struct sk_buff *pp = NULL; struct sk_buff *p; struct udphdr *uh2; unsigned int off = skb_gro_offset(skb); int flush = 1; - struct sock *sk; - rcu_read_lock(); - sk = INDIRECT_CALL_INET(lookup, udp6_lib_lookup_skb, - udp4_lib_lookup_skb, skb, uh->source, uh->dest); - if (!sk) - goto out_unlock; + if (skb->dev->features & NETIF_F_GRO_FRAGLIST) + NAPI_GRO_CB(skb)->is_flist = sk ? !udp_sk(sk)->gro_enabled: 1; - if (udp_sk(sk)->gro_enabled) { + if ((sk && udp_sk(sk)->gro_enabled) || NAPI_GRO_CB(skb)->is_flist) { pp = call_gro_receive(udp_gro_receive_segment, head, skb); - rcu_read_unlock(); return pp; } - if (NAPI_GRO_CB(skb)->encap_mark || + if (!sk || NAPI_GRO_CB(skb)->encap_mark || (skb->ip_summed != CHECKSUM_PARTIAL && NAPI_GRO_CB(skb)->csum_cnt == 0 && !NAPI_GRO_CB(skb)->csum_valid) || !udp_sk(sk)->gro_receive) - goto out_unlock; + goto out; /* mark that this skb passed once through the tunnel gro layer */ NAPI_GRO_CB(skb)->encap_mark = 1; @@ -457,8 +493,7 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr)); pp = call_gro_receive_sk(udp_sk(sk)->gro_receive, sk, head, skb); -out_unlock: - rcu_read_unlock(); +out: skb_gro_flush_final(skb, pp, flush); return pp; } @@ -468,8 +503,10 @@ INDIRECT_CALLABLE_SCOPE struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb) { struct udphdr *uh = udp_gro_udphdr(skb); + struct sk_buff *pp; + struct sock *sk; - if (unlikely(!uh) || !static_branch_unlikely(&udp_encap_needed_key)) + if (unlikely(!uh)) goto flush; /* Don't bother verifying checksum if we're going to flush anyway. */ @@ -480,11 +517,15 @@ struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb) inet_gro_compute_pseudo)) goto flush; else if (uh->check) - skb_gro_checksum_try_convert(skb, IPPROTO_UDP, uh->check, + skb_gro_checksum_try_convert(skb, IPPROTO_UDP, inet_gro_compute_pseudo); skip: NAPI_GRO_CB(skb)->is_ipv6 = 0; - return udp_gro_receive(head, skb, uh, udp4_lib_lookup_skb); + rcu_read_lock(); + sk = static_branch_unlikely(&udp_encap_needed_key) ? udp4_lib_lookup_skb(skb, uh->source, uh->dest) : NULL; + pp = udp_gro_receive(head, skb, uh, sk); + rcu_read_unlock(); + return pp; flush: NAPI_GRO_CB(skb)->flush = 1; @@ -517,9 +558,7 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff, rcu_read_lock(); sk = INDIRECT_CALL_INET(lookup, udp6_lib_lookup_skb, udp4_lib_lookup_skb, skb, uh->source, uh->dest); - if (sk && udp_sk(sk)->gro_enabled) { - err = udp_gro_complete_segment(skb); - } else if (sk && udp_sk(sk)->gro_complete) { + if (sk && udp_sk(sk)->gro_complete) { skb_shinfo(skb)->gso_type = uh->check ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; @@ -529,6 +568,8 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff, skb->encapsulation = 1; err = udp_sk(sk)->gro_complete(sk, skb, nhoff + sizeof(struct udphdr)); + } else { + err = udp_gro_complete_segment(skb); } rcu_read_unlock(); @@ -544,6 +585,23 @@ INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff) const struct iphdr *iph = ip_hdr(skb); struct udphdr *uh = (struct udphdr *)(skb->data + nhoff); + if (NAPI_GRO_CB(skb)->is_flist) { + uh->len = htons(skb->len - nhoff); + + skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4); + skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; + + if (skb->ip_summed == CHECKSUM_UNNECESSARY) { + if (skb->csum_level < SKB_MAX_CSUM_LEVEL) + skb->csum_level++; + } else { + skb->ip_summed = CHECKSUM_UNNECESSARY; + skb->csum_level = 0; + } + + return 0; + } + if (uh->check) uh->check = ~udp_v4_check(skb->len - nhoff, iph->saddr, iph->daddr, 0); diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index ecff3fce9807..89ba7c87de5d 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -92,7 +92,7 @@ static int __xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb) int xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb) { return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, - net, sk, skb, NULL, skb_dst(skb)->dev, + net, sk, skb, skb->dev, skb_dst(skb)->dev, __xfrm4_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); } diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index cdef8f9a3b01..9ebd54752e03 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -85,6 +85,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.rt.rt_flags = rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST | RTCF_LOCAL); xdst->u.rt.rt_type = rt->rt_type; + xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway; xdst->u.rt.rt_gw_family = rt->rt_gw_family; if (rt->rt_gw_family == AF_INET) xdst->u.rt.rt_gw4 = rt->rt_gw4; @@ -99,12 +100,13 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, } static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct dst_entry *path = xdst->route; - path->ops->update_pmtu(path, sk, skb, mtu); + path->ops->update_pmtu(path, sk, skb, mtu, confirm_neigh); } static void xfrm4_redirect(struct dst_entry *dst, struct sock *sk, diff --git a/net/ipv4/xfrm4_protocol.c b/net/ipv4/xfrm4_protocol.c index 8a4285712808..ea595c8549c7 100644 --- a/net/ipv4/xfrm4_protocol.c +++ b/net/ipv4/xfrm4_protocol.c @@ -72,6 +72,14 @@ int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, if (!head) goto out; + if (!skb_dst(skb)) { + const struct iphdr *iph = ip_hdr(skb); + + if (ip_route_input_noref(skb, iph->daddr, iph->saddr, + iph->tos, skb->dev)) + goto drop; + } + for_each_protocol_rcu(*head, handler) if ((ret = handler->input_handler(skb, nexthdr, spi, encap_type)) != -EINVAL) return ret; @@ -79,6 +87,7 @@ int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, out: icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); +drop: kfree_skb(skb); return 0; } |
