OpenCloudOS-Kernel/net/mptcp/protocol.h

796 lines
23 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0 */
/* Multipath TCP
*
* Copyright (c) 2017 - 2019, Intel Corporation.
*/
#ifndef __MPTCP_PROTOCOL_H
#define __MPTCP_PROTOCOL_H
#include <linux/random.h>
#include <net/tcp.h>
#include <net/inet_connection_sock.h>
#include <uapi/linux/mptcp.h>
#define MPTCP_SUPPORTED_VERSION 1
/* MPTCP option bits */
#define OPTION_MPTCP_MPC_SYN BIT(0)
#define OPTION_MPTCP_MPC_SYNACK BIT(1)
#define OPTION_MPTCP_MPC_ACK BIT(2)
#define OPTION_MPTCP_MPJ_SYN BIT(3)
#define OPTION_MPTCP_MPJ_SYNACK BIT(4)
#define OPTION_MPTCP_MPJ_ACK BIT(5)
#define OPTION_MPTCP_ADD_ADDR BIT(6)
#define OPTION_MPTCP_ADD_ADDR6 BIT(7)
#define OPTION_MPTCP_RM_ADDR BIT(8)
#define OPTION_MPTCP_FASTCLOSE BIT(9)
#define OPTION_MPTCP_PRIO BIT(10)
/* MPTCP option subtypes */
#define MPTCPOPT_MP_CAPABLE 0
#define MPTCPOPT_MP_JOIN 1
#define MPTCPOPT_DSS 2
#define MPTCPOPT_ADD_ADDR 3
#define MPTCPOPT_RM_ADDR 4
#define MPTCPOPT_MP_PRIO 5
#define MPTCPOPT_MP_FAIL 6
#define MPTCPOPT_MP_FASTCLOSE 7
/* MPTCP suboption lengths */
#define TCPOLEN_MPTCP_MPC_SYN 4
#define TCPOLEN_MPTCP_MPC_SYNACK 12
#define TCPOLEN_MPTCP_MPC_ACK 20
#define TCPOLEN_MPTCP_MPC_ACK_DATA 22
#define TCPOLEN_MPTCP_MPJ_SYN 12
#define TCPOLEN_MPTCP_MPJ_SYNACK 16
#define TCPOLEN_MPTCP_MPJ_ACK 24
#define TCPOLEN_MPTCP_DSS_BASE 4
#define TCPOLEN_MPTCP_DSS_ACK32 4
#define TCPOLEN_MPTCP_DSS_ACK64 8
#define TCPOLEN_MPTCP_DSS_MAP32 10
#define TCPOLEN_MPTCP_DSS_MAP64 14
#define TCPOLEN_MPTCP_DSS_CHECKSUM 2
#define TCPOLEN_MPTCP_ADD_ADDR 16
#define TCPOLEN_MPTCP_ADD_ADDR_PORT 20
#define TCPOLEN_MPTCP_ADD_ADDR_BASE 8
#define TCPOLEN_MPTCP_ADD_ADDR_BASE_PORT 12
#define TCPOLEN_MPTCP_ADD_ADDR6 28
#define TCPOLEN_MPTCP_ADD_ADDR6_PORT 32
#define TCPOLEN_MPTCP_ADD_ADDR6_BASE 20
#define TCPOLEN_MPTCP_ADD_ADDR6_BASE_PORT 24
#define TCPOLEN_MPTCP_PORT_LEN 4
#define TCPOLEN_MPTCP_RM_ADDR_BASE 4
mptcp: fix length of MP_PRIO suboption With version 0 of the protocol it was legal to encode the 'Subflow Id' in the MP_PRIO suboption, to specify which subflow would change its 'Backup' flag. This has been removed from v1 specification: thus, according to RFC 8684 §3.3.8, the resulting 'Length' for MP_PRIO changed from 4 to 3 byte. Current Linux generates / parses MP_PRIO according to the old spec, using 'Length' equal to 4, and hardcoding 1 as 'Subflow Id'; RFC compliance can improve if we change 'Length' in other to become 3, leaving a 'Nop' after the MP_PRIO suboption. In this way the kernel will emit and accept *only* MP_PRIO suboptions that are compliant to version 1 of the MPTCP protocol. unpatched 5.11-rc kernel: [root@bottarga ~]# tcpdump -tnnr unpatched.pcap | grep prio reading from file unpatched.pcap, link-type LINUX_SLL (Linux cooked v1) dropped privs to tcpdump IP 10.0.3.2.48433 > 10.0.1.1.10006: Flags [.], ack 1, win 502, options [nop,nop,TS val 4032325513 ecr 1876514270,mptcp prio non-backup id 1,mptcp dss ack 14084896651682217737], length 0 patched 5.11-rc kernel: [root@bottarga ~]# tcpdump -tnnr patched.pcap | grep prio reading from file patched.pcap, link-type LINUX_SLL (Linux cooked v1) dropped privs to tcpdump IP 10.0.3.2.49735 > 10.0.1.1.10006: Flags [.], ack 1, win 502, options [nop,nop,TS val 1276737699 ecr 2686399734,mptcp prio non-backup,nop,mptcp dss ack 18433038869082491686], length 0 Changes since v2: - when accounting for option space, don't increment 'TCPOLEN_MPTCP_PRIO' and use 'TCPOLEN_MPTCP_PRIO_ALIGN' instead, thanks to Matthieu Baerts. Changes since v1: - refactor patch to avoid using 'TCPOLEN_MPTCP_PRIO' with its old value, thanks to Geliang Tang. Fixes: 067065422fcd ("mptcp: add the outgoing MP_PRIO support") Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com> Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Reviewed-by: Matteo Croce <mcroce@linux.microsoft.com> Link: https://lore.kernel.org/r/846cdd41e6ad6ec88ef23fee1552ab39c2f5a3d1.1612184361.git.dcaratti@redhat.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-02-01 21:05:26 +08:00
#define TCPOLEN_MPTCP_PRIO 3
#define TCPOLEN_MPTCP_PRIO_ALIGN 4
#define TCPOLEN_MPTCP_FASTCLOSE 12
/* MPTCP MP_JOIN flags */
#define MPTCPOPT_BACKUP BIT(0)
#define MPTCPOPT_HMAC_LEN 20
#define MPTCPOPT_THMAC_LEN 8
/* MPTCP MP_CAPABLE flags */
#define MPTCP_VERSION_MASK (0x0F)
#define MPTCP_CAP_CHECKSUM_REQD BIT(7)
#define MPTCP_CAP_EXTENSIBILITY BIT(6)
#define MPTCP_CAP_HMAC_SHA256 BIT(0)
#define MPTCP_CAP_FLAG_MASK (0x3F)
/* MPTCP DSS flags */
#define MPTCP_DSS_DATA_FIN BIT(4)
#define MPTCP_DSS_DSN64 BIT(3)
#define MPTCP_DSS_HAS_MAP BIT(2)
#define MPTCP_DSS_ACK64 BIT(1)
#define MPTCP_DSS_HAS_ACK BIT(0)
#define MPTCP_DSS_FLAG_MASK (0x1F)
/* MPTCP ADD_ADDR flags */
#define MPTCP_ADDR_ECHO BIT(0)
#define MPTCP_ADDR_IPVERSION_4 4
#define MPTCP_ADDR_IPVERSION_6 6
/* MPTCP MP_PRIO flags */
#define MPTCP_PRIO_BKUP BIT(0)
/* MPTCP socket flags */
#define MPTCP_DATA_READY 0
#define MPTCP_NOSPACE 1
#define MPTCP_WORK_RTX 2
#define MPTCP_WORK_EOF 3
#define MPTCP_FALLBACK_DONE 4
#define MPTCP_WORK_CLOSE_SUBFLOW 5
#define MPTCP_PUSH_PENDING 6
#define MPTCP_CLEAN_UNA 7
#define MPTCP_ERROR_REPORT 8
static inline bool before64(__u64 seq1, __u64 seq2)
{
return (__s64)(seq1 - seq2) < 0;
}
#define after64(seq2, seq1) before64(seq1, seq2)
mptcp: move option parsing into mptcp_incoming_options() The mptcp_options_received structure carries several per packet flags (mp_capable, mp_join, etc.). Such fields must be cleared on each packet, even on dropped ones or packet not carrying any MPTCP options, but the current mptcp code clears them only on TCP option reset. On several races/corner cases we end-up with stray bits in incoming options, leading to WARN_ON splats. e.g.: [ 171.164906] Bad mapping: ssn=32714 map_seq=1 map_data_len=32713 [ 171.165006] WARNING: CPU: 1 PID: 5026 at net/mptcp/subflow.c:533 warn_bad_map (linux-mptcp/net/mptcp/subflow.c:533 linux-mptcp/net/mptcp/subflow.c:531) [ 171.167632] Modules linked in: ip6_vti ip_vti ip_gre ipip sit tunnel4 ip_tunnel geneve ip6_udp_tunnel udp_tunnel macsec macvtap tap ipvlan macvlan 8021q garp mrp xfrm_interface veth netdevsim nlmon dummy team bonding vcan bridge stp llc ip6_gre gre ip6_tunnel tunnel6 tun binfmt_misc intel_rapl_msr intel_rapl_common rfkill kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel joydev virtio_balloon pcspkr i2c_piix4 sunrpc ip_tables xfs libcrc32c crc32c_intel serio_raw virtio_console ata_generic virtio_blk virtio_net net_failover failover ata_piix libata [ 171.199464] CPU: 1 PID: 5026 Comm: repro Not tainted 5.7.0-rc1.mptcp_f227fdf5d388+ #95 [ 171.200886] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-2.fc30 04/01/2014 [ 171.202546] RIP: 0010:warn_bad_map (linux-mptcp/net/mptcp/subflow.c:533 linux-mptcp/net/mptcp/subflow.c:531) [ 171.206537] Code: c1 ea 03 0f b6 14 02 48 89 f8 83 e0 07 83 c0 03 38 d0 7c 04 84 d2 75 1d 8b 55 3c 44 89 e6 48 c7 c7 20 51 13 95 e8 37 8b 22 fe <0f> 0b 48 83 c4 08 5b 5d 41 5c c3 89 4c 24 04 e8 db d6 94 fe 8b 4c [ 171.220473] RSP: 0018:ffffc90000150560 EFLAGS: 00010282 [ 171.221639] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 [ 171.223108] RDX: 0000000000000000 RSI: 0000000000000008 RDI: fffff5200002a09e [ 171.224388] RBP: ffff8880aa6e3c00 R08: 0000000000000001 R09: fffffbfff2ec9955 [ 171.225706] R10: ffffffff9764caa7 R11: fffffbfff2ec9954 R12: 0000000000007fca [ 171.227211] R13: ffff8881066f4a7f R14: ffff8880aa6e3c00 R15: 0000000000000020 [ 171.228460] FS: 00007f8623719740(0000) GS:ffff88810be00000(0000) knlGS:0000000000000000 [ 171.230065] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 171.231303] CR2: 00007ffdab190a50 CR3: 00000001038ea006 CR4: 0000000000160ee0 [ 171.232586] Call Trace: [ 171.233109] <IRQ> [ 171.233531] get_mapping_status (linux-mptcp/net/mptcp/subflow.c:691) [ 171.234371] mptcp_subflow_data_available (linux-mptcp/net/mptcp/subflow.c:736 linux-mptcp/net/mptcp/subflow.c:832) [ 171.238181] subflow_state_change (linux-mptcp/net/mptcp/subflow.c:1085 (discriminator 1)) [ 171.239066] tcp_fin (linux-mptcp/net/ipv4/tcp_input.c:4217) [ 171.240123] tcp_data_queue (linux-mptcp/./include/linux/compiler.h:199 linux-mptcp/net/ipv4/tcp_input.c:4822) [ 171.245083] tcp_rcv_established (linux-mptcp/./include/linux/skbuff.h:1785 linux-mptcp/./include/net/tcp.h:1774 linux-mptcp/./include/net/tcp.h:1847 linux-mptcp/net/ipv4/tcp_input.c:5238 linux-mptcp/net/ipv4/tcp_input.c:5730) [ 171.254089] tcp_v4_rcv (linux-mptcp/./include/linux/spinlock.h:393 linux-mptcp/net/ipv4/tcp_ipv4.c:2009) [ 171.258969] ip_protocol_deliver_rcu (linux-mptcp/net/ipv4/ip_input.c:204 (discriminator 1)) [ 171.260214] ip_local_deliver_finish (linux-mptcp/./include/linux/rcupdate.h:651 linux-mptcp/net/ipv4/ip_input.c:232) [ 171.261389] ip_local_deliver (linux-mptcp/./include/linux/netfilter.h:307 linux-mptcp/./include/linux/netfilter.h:301 linux-mptcp/net/ipv4/ip_input.c:252) [ 171.265884] ip_rcv (linux-mptcp/./include/linux/netfilter.h:307 linux-mptcp/./include/linux/netfilter.h:301 linux-mptcp/net/ipv4/ip_input.c:539) [ 171.273666] process_backlog (linux-mptcp/./include/linux/rcupdate.h:651 linux-mptcp/net/core/dev.c:6135) [ 171.275328] net_rx_action (linux-mptcp/net/core/dev.c:6572 linux-mptcp/net/core/dev.c:6640) [ 171.280472] __do_softirq (linux-mptcp/./arch/x86/include/asm/jump_label.h:25 linux-mptcp/./include/linux/jump_label.h:200 linux-mptcp/./include/trace/events/irq.h:142 linux-mptcp/kernel/softirq.c:293) [ 171.281379] do_softirq_own_stack (linux-mptcp/arch/x86/entry/entry_64.S:1083) [ 171.282358] </IRQ> We could address the issue clearing explicitly the relevant fields in several places - tcp_parse_option, tcp_fast_parse_options, possibly others. Instead we move the MPTCP option parsing into the already existing mptcp ingress hook, so that we need to clear the fields in a single place. This allows us dropping an MPTCP hook from the TCP code and removing the quite large mptcp_options_received from the tcp_sock struct. On the flip side, the MPTCP sockets will traverse the option space twice (in tcp_parse_option() and in mptcp_incoming_options(). That looks acceptable: we already do that for syn and 3rd ack packets, plain TCP socket will benefit from it, and even MPTCP sockets will experience better code locality, reducing the jumps between TCP and MPTCP code. v1 -> v2: - rebased on current '-net' tree Fixes: 648ef4b88673 ("mptcp: Implement MPTCP receive path") Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 21:01:52 +08:00
struct mptcp_options_received {
u64 sndr_key;
u64 rcvr_key;
u64 data_ack;
u64 data_seq;
u32 subflow_seq;
u16 data_len;
u16 mp_capable : 1,
mp_join : 1,
fastclose : 1,
mptcp: move option parsing into mptcp_incoming_options() The mptcp_options_received structure carries several per packet flags (mp_capable, mp_join, etc.). Such fields must be cleared on each packet, even on dropped ones or packet not carrying any MPTCP options, but the current mptcp code clears them only on TCP option reset. On several races/corner cases we end-up with stray bits in incoming options, leading to WARN_ON splats. e.g.: [ 171.164906] Bad mapping: ssn=32714 map_seq=1 map_data_len=32713 [ 171.165006] WARNING: CPU: 1 PID: 5026 at net/mptcp/subflow.c:533 warn_bad_map (linux-mptcp/net/mptcp/subflow.c:533 linux-mptcp/net/mptcp/subflow.c:531) [ 171.167632] Modules linked in: ip6_vti ip_vti ip_gre ipip sit tunnel4 ip_tunnel geneve ip6_udp_tunnel udp_tunnel macsec macvtap tap ipvlan macvlan 8021q garp mrp xfrm_interface veth netdevsim nlmon dummy team bonding vcan bridge stp llc ip6_gre gre ip6_tunnel tunnel6 tun binfmt_misc intel_rapl_msr intel_rapl_common rfkill kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel joydev virtio_balloon pcspkr i2c_piix4 sunrpc ip_tables xfs libcrc32c crc32c_intel serio_raw virtio_console ata_generic virtio_blk virtio_net net_failover failover ata_piix libata [ 171.199464] CPU: 1 PID: 5026 Comm: repro Not tainted 5.7.0-rc1.mptcp_f227fdf5d388+ #95 [ 171.200886] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-2.fc30 04/01/2014 [ 171.202546] RIP: 0010:warn_bad_map (linux-mptcp/net/mptcp/subflow.c:533 linux-mptcp/net/mptcp/subflow.c:531) [ 171.206537] Code: c1 ea 03 0f b6 14 02 48 89 f8 83 e0 07 83 c0 03 38 d0 7c 04 84 d2 75 1d 8b 55 3c 44 89 e6 48 c7 c7 20 51 13 95 e8 37 8b 22 fe <0f> 0b 48 83 c4 08 5b 5d 41 5c c3 89 4c 24 04 e8 db d6 94 fe 8b 4c [ 171.220473] RSP: 0018:ffffc90000150560 EFLAGS: 00010282 [ 171.221639] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 [ 171.223108] RDX: 0000000000000000 RSI: 0000000000000008 RDI: fffff5200002a09e [ 171.224388] RBP: ffff8880aa6e3c00 R08: 0000000000000001 R09: fffffbfff2ec9955 [ 171.225706] R10: ffffffff9764caa7 R11: fffffbfff2ec9954 R12: 0000000000007fca [ 171.227211] R13: ffff8881066f4a7f R14: ffff8880aa6e3c00 R15: 0000000000000020 [ 171.228460] FS: 00007f8623719740(0000) GS:ffff88810be00000(0000) knlGS:0000000000000000 [ 171.230065] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 171.231303] CR2: 00007ffdab190a50 CR3: 00000001038ea006 CR4: 0000000000160ee0 [ 171.232586] Call Trace: [ 171.233109] <IRQ> [ 171.233531] get_mapping_status (linux-mptcp/net/mptcp/subflow.c:691) [ 171.234371] mptcp_subflow_data_available (linux-mptcp/net/mptcp/subflow.c:736 linux-mptcp/net/mptcp/subflow.c:832) [ 171.238181] subflow_state_change (linux-mptcp/net/mptcp/subflow.c:1085 (discriminator 1)) [ 171.239066] tcp_fin (linux-mptcp/net/ipv4/tcp_input.c:4217) [ 171.240123] tcp_data_queue (linux-mptcp/./include/linux/compiler.h:199 linux-mptcp/net/ipv4/tcp_input.c:4822) [ 171.245083] tcp_rcv_established (linux-mptcp/./include/linux/skbuff.h:1785 linux-mptcp/./include/net/tcp.h:1774 linux-mptcp/./include/net/tcp.h:1847 linux-mptcp/net/ipv4/tcp_input.c:5238 linux-mptcp/net/ipv4/tcp_input.c:5730) [ 171.254089] tcp_v4_rcv (linux-mptcp/./include/linux/spinlock.h:393 linux-mptcp/net/ipv4/tcp_ipv4.c:2009) [ 171.258969] ip_protocol_deliver_rcu (linux-mptcp/net/ipv4/ip_input.c:204 (discriminator 1)) [ 171.260214] ip_local_deliver_finish (linux-mptcp/./include/linux/rcupdate.h:651 linux-mptcp/net/ipv4/ip_input.c:232) [ 171.261389] ip_local_deliver (linux-mptcp/./include/linux/netfilter.h:307 linux-mptcp/./include/linux/netfilter.h:301 linux-mptcp/net/ipv4/ip_input.c:252) [ 171.265884] ip_rcv (linux-mptcp/./include/linux/netfilter.h:307 linux-mptcp/./include/linux/netfilter.h:301 linux-mptcp/net/ipv4/ip_input.c:539) [ 171.273666] process_backlog (linux-mptcp/./include/linux/rcupdate.h:651 linux-mptcp/net/core/dev.c:6135) [ 171.275328] net_rx_action (linux-mptcp/net/core/dev.c:6572 linux-mptcp/net/core/dev.c:6640) [ 171.280472] __do_softirq (linux-mptcp/./arch/x86/include/asm/jump_label.h:25 linux-mptcp/./include/linux/jump_label.h:200 linux-mptcp/./include/trace/events/irq.h:142 linux-mptcp/kernel/softirq.c:293) [ 171.281379] do_softirq_own_stack (linux-mptcp/arch/x86/entry/entry_64.S:1083) [ 171.282358] </IRQ> We could address the issue clearing explicitly the relevant fields in several places - tcp_parse_option, tcp_fast_parse_options, possibly others. Instead we move the MPTCP option parsing into the already existing mptcp ingress hook, so that we need to clear the fields in a single place. This allows us dropping an MPTCP hook from the TCP code and removing the quite large mptcp_options_received from the tcp_sock struct. On the flip side, the MPTCP sockets will traverse the option space twice (in tcp_parse_option() and in mptcp_incoming_options(). That looks acceptable: we already do that for syn and 3rd ack packets, plain TCP socket will benefit from it, and even MPTCP sockets will experience better code locality, reducing the jumps between TCP and MPTCP code. v1 -> v2: - rebased on current '-net' tree Fixes: 648ef4b88673 ("mptcp: Implement MPTCP receive path") Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 21:01:52 +08:00
dss : 1,
add_addr : 1,
rm_addr : 1,
mp_prio : 1,
mptcp: move option parsing into mptcp_incoming_options() The mptcp_options_received structure carries several per packet flags (mp_capable, mp_join, etc.). Such fields must be cleared on each packet, even on dropped ones or packet not carrying any MPTCP options, but the current mptcp code clears them only on TCP option reset. On several races/corner cases we end-up with stray bits in incoming options, leading to WARN_ON splats. e.g.: [ 171.164906] Bad mapping: ssn=32714 map_seq=1 map_data_len=32713 [ 171.165006] WARNING: CPU: 1 PID: 5026 at net/mptcp/subflow.c:533 warn_bad_map (linux-mptcp/net/mptcp/subflow.c:533 linux-mptcp/net/mptcp/subflow.c:531) [ 171.167632] Modules linked in: ip6_vti ip_vti ip_gre ipip sit tunnel4 ip_tunnel geneve ip6_udp_tunnel udp_tunnel macsec macvtap tap ipvlan macvlan 8021q garp mrp xfrm_interface veth netdevsim nlmon dummy team bonding vcan bridge stp llc ip6_gre gre ip6_tunnel tunnel6 tun binfmt_misc intel_rapl_msr intel_rapl_common rfkill kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel joydev virtio_balloon pcspkr i2c_piix4 sunrpc ip_tables xfs libcrc32c crc32c_intel serio_raw virtio_console ata_generic virtio_blk virtio_net net_failover failover ata_piix libata [ 171.199464] CPU: 1 PID: 5026 Comm: repro Not tainted 5.7.0-rc1.mptcp_f227fdf5d388+ #95 [ 171.200886] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-2.fc30 04/01/2014 [ 171.202546] RIP: 0010:warn_bad_map (linux-mptcp/net/mptcp/subflow.c:533 linux-mptcp/net/mptcp/subflow.c:531) [ 171.206537] Code: c1 ea 03 0f b6 14 02 48 89 f8 83 e0 07 83 c0 03 38 d0 7c 04 84 d2 75 1d 8b 55 3c 44 89 e6 48 c7 c7 20 51 13 95 e8 37 8b 22 fe <0f> 0b 48 83 c4 08 5b 5d 41 5c c3 89 4c 24 04 e8 db d6 94 fe 8b 4c [ 171.220473] RSP: 0018:ffffc90000150560 EFLAGS: 00010282 [ 171.221639] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 [ 171.223108] RDX: 0000000000000000 RSI: 0000000000000008 RDI: fffff5200002a09e [ 171.224388] RBP: ffff8880aa6e3c00 R08: 0000000000000001 R09: fffffbfff2ec9955 [ 171.225706] R10: ffffffff9764caa7 R11: fffffbfff2ec9954 R12: 0000000000007fca [ 171.227211] R13: ffff8881066f4a7f R14: ffff8880aa6e3c00 R15: 0000000000000020 [ 171.228460] FS: 00007f8623719740(0000) GS:ffff88810be00000(0000) knlGS:0000000000000000 [ 171.230065] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 171.231303] CR2: 00007ffdab190a50 CR3: 00000001038ea006 CR4: 0000000000160ee0 [ 171.232586] Call Trace: [ 171.233109] <IRQ> [ 171.233531] get_mapping_status (linux-mptcp/net/mptcp/subflow.c:691) [ 171.234371] mptcp_subflow_data_available (linux-mptcp/net/mptcp/subflow.c:736 linux-mptcp/net/mptcp/subflow.c:832) [ 171.238181] subflow_state_change (linux-mptcp/net/mptcp/subflow.c:1085 (discriminator 1)) [ 171.239066] tcp_fin (linux-mptcp/net/ipv4/tcp_input.c:4217) [ 171.240123] tcp_data_queue (linux-mptcp/./include/linux/compiler.h:199 linux-mptcp/net/ipv4/tcp_input.c:4822) [ 171.245083] tcp_rcv_established (linux-mptcp/./include/linux/skbuff.h:1785 linux-mptcp/./include/net/tcp.h:1774 linux-mptcp/./include/net/tcp.h:1847 linux-mptcp/net/ipv4/tcp_input.c:5238 linux-mptcp/net/ipv4/tcp_input.c:5730) [ 171.254089] tcp_v4_rcv (linux-mptcp/./include/linux/spinlock.h:393 linux-mptcp/net/ipv4/tcp_ipv4.c:2009) [ 171.258969] ip_protocol_deliver_rcu (linux-mptcp/net/ipv4/ip_input.c:204 (discriminator 1)) [ 171.260214] ip_local_deliver_finish (linux-mptcp/./include/linux/rcupdate.h:651 linux-mptcp/net/ipv4/ip_input.c:232) [ 171.261389] ip_local_deliver (linux-mptcp/./include/linux/netfilter.h:307 linux-mptcp/./include/linux/netfilter.h:301 linux-mptcp/net/ipv4/ip_input.c:252) [ 171.265884] ip_rcv (linux-mptcp/./include/linux/netfilter.h:307 linux-mptcp/./include/linux/netfilter.h:301 linux-mptcp/net/ipv4/ip_input.c:539) [ 171.273666] process_backlog (linux-mptcp/./include/linux/rcupdate.h:651 linux-mptcp/net/core/dev.c:6135) [ 171.275328] net_rx_action (linux-mptcp/net/core/dev.c:6572 linux-mptcp/net/core/dev.c:6640) [ 171.280472] __do_softirq (linux-mptcp/./arch/x86/include/asm/jump_label.h:25 linux-mptcp/./include/linux/jump_label.h:200 linux-mptcp/./include/trace/events/irq.h:142 linux-mptcp/kernel/softirq.c:293) [ 171.281379] do_softirq_own_stack (linux-mptcp/arch/x86/entry/entry_64.S:1083) [ 171.282358] </IRQ> We could address the issue clearing explicitly the relevant fields in several places - tcp_parse_option, tcp_fast_parse_options, possibly others. Instead we move the MPTCP option parsing into the already existing mptcp ingress hook, so that we need to clear the fields in a single place. This allows us dropping an MPTCP hook from the TCP code and removing the quite large mptcp_options_received from the tcp_sock struct. On the flip side, the MPTCP sockets will traverse the option space twice (in tcp_parse_option() and in mptcp_incoming_options(). That looks acceptable: we already do that for syn and 3rd ack packets, plain TCP socket will benefit from it, and even MPTCP sockets will experience better code locality, reducing the jumps between TCP and MPTCP code. v1 -> v2: - rebased on current '-net' tree Fixes: 648ef4b88673 ("mptcp: Implement MPTCP receive path") Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 21:01:52 +08:00
family : 4,
echo : 1,
backup : 1;
u32 token;
u32 nonce;
u64 thmac;
u8 hmac[MPTCPOPT_HMAC_LEN];
mptcp: move option parsing into mptcp_incoming_options() The mptcp_options_received structure carries several per packet flags (mp_capable, mp_join, etc.). Such fields must be cleared on each packet, even on dropped ones or packet not carrying any MPTCP options, but the current mptcp code clears them only on TCP option reset. On several races/corner cases we end-up with stray bits in incoming options, leading to WARN_ON splats. e.g.: [ 171.164906] Bad mapping: ssn=32714 map_seq=1 map_data_len=32713 [ 171.165006] WARNING: CPU: 1 PID: 5026 at net/mptcp/subflow.c:533 warn_bad_map (linux-mptcp/net/mptcp/subflow.c:533 linux-mptcp/net/mptcp/subflow.c:531) [ 171.167632] Modules linked in: ip6_vti ip_vti ip_gre ipip sit tunnel4 ip_tunnel geneve ip6_udp_tunnel udp_tunnel macsec macvtap tap ipvlan macvlan 8021q garp mrp xfrm_interface veth netdevsim nlmon dummy team bonding vcan bridge stp llc ip6_gre gre ip6_tunnel tunnel6 tun binfmt_misc intel_rapl_msr intel_rapl_common rfkill kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel joydev virtio_balloon pcspkr i2c_piix4 sunrpc ip_tables xfs libcrc32c crc32c_intel serio_raw virtio_console ata_generic virtio_blk virtio_net net_failover failover ata_piix libata [ 171.199464] CPU: 1 PID: 5026 Comm: repro Not tainted 5.7.0-rc1.mptcp_f227fdf5d388+ #95 [ 171.200886] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-2.fc30 04/01/2014 [ 171.202546] RIP: 0010:warn_bad_map (linux-mptcp/net/mptcp/subflow.c:533 linux-mptcp/net/mptcp/subflow.c:531) [ 171.206537] Code: c1 ea 03 0f b6 14 02 48 89 f8 83 e0 07 83 c0 03 38 d0 7c 04 84 d2 75 1d 8b 55 3c 44 89 e6 48 c7 c7 20 51 13 95 e8 37 8b 22 fe <0f> 0b 48 83 c4 08 5b 5d 41 5c c3 89 4c 24 04 e8 db d6 94 fe 8b 4c [ 171.220473] RSP: 0018:ffffc90000150560 EFLAGS: 00010282 [ 171.221639] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 [ 171.223108] RDX: 0000000000000000 RSI: 0000000000000008 RDI: fffff5200002a09e [ 171.224388] RBP: ffff8880aa6e3c00 R08: 0000000000000001 R09: fffffbfff2ec9955 [ 171.225706] R10: ffffffff9764caa7 R11: fffffbfff2ec9954 R12: 0000000000007fca [ 171.227211] R13: ffff8881066f4a7f R14: ffff8880aa6e3c00 R15: 0000000000000020 [ 171.228460] FS: 00007f8623719740(0000) GS:ffff88810be00000(0000) knlGS:0000000000000000 [ 171.230065] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 171.231303] CR2: 00007ffdab190a50 CR3: 00000001038ea006 CR4: 0000000000160ee0 [ 171.232586] Call Trace: [ 171.233109] <IRQ> [ 171.233531] get_mapping_status (linux-mptcp/net/mptcp/subflow.c:691) [ 171.234371] mptcp_subflow_data_available (linux-mptcp/net/mptcp/subflow.c:736 linux-mptcp/net/mptcp/subflow.c:832) [ 171.238181] subflow_state_change (linux-mptcp/net/mptcp/subflow.c:1085 (discriminator 1)) [ 171.239066] tcp_fin (linux-mptcp/net/ipv4/tcp_input.c:4217) [ 171.240123] tcp_data_queue (linux-mptcp/./include/linux/compiler.h:199 linux-mptcp/net/ipv4/tcp_input.c:4822) [ 171.245083] tcp_rcv_established (linux-mptcp/./include/linux/skbuff.h:1785 linux-mptcp/./include/net/tcp.h:1774 linux-mptcp/./include/net/tcp.h:1847 linux-mptcp/net/ipv4/tcp_input.c:5238 linux-mptcp/net/ipv4/tcp_input.c:5730) [ 171.254089] tcp_v4_rcv (linux-mptcp/./include/linux/spinlock.h:393 linux-mptcp/net/ipv4/tcp_ipv4.c:2009) [ 171.258969] ip_protocol_deliver_rcu (linux-mptcp/net/ipv4/ip_input.c:204 (discriminator 1)) [ 171.260214] ip_local_deliver_finish (linux-mptcp/./include/linux/rcupdate.h:651 linux-mptcp/net/ipv4/ip_input.c:232) [ 171.261389] ip_local_deliver (linux-mptcp/./include/linux/netfilter.h:307 linux-mptcp/./include/linux/netfilter.h:301 linux-mptcp/net/ipv4/ip_input.c:252) [ 171.265884] ip_rcv (linux-mptcp/./include/linux/netfilter.h:307 linux-mptcp/./include/linux/netfilter.h:301 linux-mptcp/net/ipv4/ip_input.c:539) [ 171.273666] process_backlog (linux-mptcp/./include/linux/rcupdate.h:651 linux-mptcp/net/core/dev.c:6135) [ 171.275328] net_rx_action (linux-mptcp/net/core/dev.c:6572 linux-mptcp/net/core/dev.c:6640) [ 171.280472] __do_softirq (linux-mptcp/./arch/x86/include/asm/jump_label.h:25 linux-mptcp/./include/linux/jump_label.h:200 linux-mptcp/./include/trace/events/irq.h:142 linux-mptcp/kernel/softirq.c:293) [ 171.281379] do_softirq_own_stack (linux-mptcp/arch/x86/entry/entry_64.S:1083) [ 171.282358] </IRQ> We could address the issue clearing explicitly the relevant fields in several places - tcp_parse_option, tcp_fast_parse_options, possibly others. Instead we move the MPTCP option parsing into the already existing mptcp ingress hook, so that we need to clear the fields in a single place. This allows us dropping an MPTCP hook from the TCP code and removing the quite large mptcp_options_received from the tcp_sock struct. On the flip side, the MPTCP sockets will traverse the option space twice (in tcp_parse_option() and in mptcp_incoming_options(). That looks acceptable: we already do that for syn and 3rd ack packets, plain TCP socket will benefit from it, and even MPTCP sockets will experience better code locality, reducing the jumps between TCP and MPTCP code. v1 -> v2: - rebased on current '-net' tree Fixes: 648ef4b88673 ("mptcp: Implement MPTCP receive path") Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 21:01:52 +08:00
u8 join_id;
u8 use_map:1,
dsn64:1,
data_fin:1,
use_ack:1,
ack64:1,
mpc_map:1,
__unused:2;
u8 addr_id;
u8 rm_id;
union {
struct in_addr addr;
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
struct in6_addr addr6;
#endif
};
u64 ahmac;
u16 port;
};
static inline __be32 mptcp_option(u8 subopt, u8 len, u8 nib, u8 field)
{
return htonl((TCPOPT_MPTCP << 24) | (len << 16) | (subopt << 12) |
((nib & 0xF) << 8) | field);
}
struct mptcp_addr_info {
sa_family_t family;
__be16 port;
u8 id;
u8 flags;
int ifindex;
union {
struct in_addr addr;
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
struct in6_addr addr6;
#endif
};
};
enum mptcp_pm_status {
MPTCP_PM_ADD_ADDR_RECEIVED,
MPTCP_PM_ADD_ADDR_SEND_ACK,
MPTCP_PM_RM_ADDR_RECEIVED,
MPTCP_PM_ESTABLISHED,
mptcp: link MPC subflow into msk only after accept Christoph reported the following splat: WARNING: CPU: 0 PID: 4615 at net/ipv4/inet_connection_sock.c:1031 inet_csk_listen_stop+0x8e8/0xad0 net/ipv4/inet_connection_sock.c:1031 Modules linked in: CPU: 0 PID: 4615 Comm: syz-executor.4 Not tainted 5.9.0 #37 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 RIP: 0010:inet_csk_listen_stop+0x8e8/0xad0 net/ipv4/inet_connection_sock.c:1031 Code: 03 00 00 00 e8 79 b2 3d ff e9 ad f9 ff ff e8 1f 76 ba fe be 02 00 00 00 4c 89 f7 e8 62 b2 3d ff e9 14 f9 ff ff e8 08 76 ba fe <0f> 0b e9 97 f8 ff ff e8 fc 75 ba fe be 03 00 00 00 4c 89 f7 e8 3f RSP: 0018:ffffc900037f7948 EFLAGS: 00010293 RAX: ffff88810a349c80 RBX: ffff888114ee1b00 RCX: ffffffff827b14cd RDX: 0000000000000000 RSI: ffffffff827b1c38 RDI: 0000000000000005 RBP: ffff88810a2a8000 R08: ffff88810a349c80 R09: fffff520006fef1f R10: 0000000000000003 R11: fffff520006fef1e R12: ffff888114ee2d00 R13: dffffc0000000000 R14: 0000000000000001 R15: ffff888114ee1d68 FS: 00007f2ac1945700(0000) GS:ffff88811b400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007ffd44798bc0 CR3: 0000000109810002 CR4: 0000000000170ef0 Call Trace: __tcp_close+0xd86/0x1110 net/ipv4/tcp.c:2433 __mptcp_close_ssk+0x256/0x430 net/mptcp/protocol.c:1761 __mptcp_destroy_sock+0x49b/0x770 net/mptcp/protocol.c:2127 mptcp_close+0x62d/0x910 net/mptcp/protocol.c:2184 inet_release+0xe9/0x1f0 net/ipv4/af_inet.c:434 __sock_release+0xd2/0x280 net/socket.c:596 sock_close+0x15/0x20 net/socket.c:1277 __fput+0x276/0x960 fs/file_table.c:281 task_work_run+0x109/0x1d0 kernel/task_work.c:151 get_signal+0xe8f/0x1d40 kernel/signal.c:2561 arch_do_signal+0x88/0x1b60 arch/x86/kernel/signal.c:811 exit_to_user_mode_loop kernel/entry/common.c:161 [inline] exit_to_user_mode_prepare+0x9b/0xf0 kernel/entry/common.c:191 syscall_exit_to_user_mode+0x22/0x150 kernel/entry/common.c:266 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7f2ac1254469 Code: 00 f3 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d ff 49 2b 00 f7 d8 64 89 01 48 RSP: 002b:00007f2ac1944dc8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffbf RBX: 000000000069bf00 RCX: 00007f2ac1254469 RDX: 0000000000000000 RSI: 0000000000008982 RDI: 0000000000000003 RBP: 000000000069bf00 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 000000000069bf0c R13: 00007ffeb53f178f R14: 00000000004668b0 R15: 0000000000000003 After commit 0397c6d85f9c ("mptcp: keep unaccepted MPC subflow into join list"), the msk's workqueue and/or PM can touch the MPC subflow - and acquire its socket lock - even if it's still unaccepted. If the above event races with the relevant listener socket close, we can end-up with the above splat. This change addresses the issue delaying the MPC socket insertion in conn_list at accept time - that is, partially reverting the blamed commit. We must additionally ensure that mptcp_pm_fully_established() happens after accept() time, or the PM will not be able to handle properly such event - conn_list could be empty otherwise. In the receive path, we check the subflow list node to ensure it is out of the listener queue. Be sure client subflows do not match transiently such condition moving them into the join list earlier at creation time. Since we now have multiple mptcp_pm_fully_established() call sites from different code-paths, said helper can now race with itself. Use an additional PM status bit to avoid multiple notifications. Reported-by: Christoph Paasch <cpaasch@apple.com> Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/103 Fixes: 0397c6d85f9c ("mptcp: keep unaccepted MPC subflow into join list"), Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net> Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-12-09 19:03:29 +08:00
MPTCP_PM_ALREADY_ESTABLISHED, /* persistent status, set after ESTABLISHED event */
MPTCP_PM_SUBFLOW_ESTABLISHED,
};
enum mptcp_addr_signal_status {
MPTCP_ADD_ADDR_SIGNAL,
MPTCP_ADD_ADDR_ECHO,
MPTCP_ADD_ADDR_IPV6,
MPTCP_ADD_ADDR_PORT,
MPTCP_RM_ADDR_SIGNAL,
};
struct mptcp_pm_data {
struct mptcp_addr_info local;
struct mptcp_addr_info remote;
struct list_head anno_list;
spinlock_t lock; /*protects the whole PM data */
u8 addr_signal;
bool server_side;
bool work_pending;
bool accept_addr;
bool accept_subflow;
u8 add_addr_signaled;
u8 add_addr_accepted;
u8 local_addr_used;
u8 subflows;
u8 status;
u8 rm_id;
};
struct mptcp_data_frag {
struct list_head list;
u64 data_seq;
u16 data_len;
u16 offset;
u16 overhead;
u16 already_sent;
struct page *page;
};
/* MPTCP connection sock */
struct mptcp_sock {
/* inet_connection_sock must be the first member */
struct inet_connection_sock sk;
u64 local_key;
u64 remote_key;
u64 write_seq;
u64 snd_nxt;
u64 ack_seq;
u64 rcv_wnd_sent;
u64 rcv_data_fin_seq;
int wmem_reserved;
struct sock *last_snd;
int snd_burst;
int old_wspace;
u64 snd_una;
u64 wnd_end;
unsigned long timer_ival;
u32 token;
int rmem_released;
unsigned long flags;
bool can_ack;
bool fully_established;
bool rcv_data_fin;
bool snd_data_fin_enable;
bool rcv_fastclose;
bool use_64bit_ack; /* Set when we received a 64-bit DSN */
spinlock_t join_list_lock;
struct sock *ack_hint;
struct work_struct work;
struct sk_buff *ooo_last_skb;
struct rb_root out_of_order_queue;
struct sk_buff_head receive_queue;
struct sk_buff_head skb_tx_cache; /* this is wmem accounted */
int tx_pending_data;
int size_goal_cache;
struct list_head conn_list;
struct list_head rtx_queue;
struct mptcp_data_frag *first_pending;
struct list_head join_list;
struct socket *subflow; /* outgoing connect/listener/!mp_capable */
struct sock *first;
struct mptcp_pm_data pm;
mptcp: add receive buffer auto-tuning When mptcp is used, userspace doesn't read from the tcp (subflow) socket but from the parent (mptcp) socket receive queue. skbs are moved from the subflow socket to the mptcp rx queue either from 'data_ready' callback (if mptcp socket can be locked), a work queue, or the socket receive function. This means tcp_rcv_space_adjust() is never called and thus no receive buffer size auto-tuning is done. An earlier (not merged) patch added tcp_rcv_space_adjust() calls to the function that moves skbs from subflow to mptcp socket. While this enabled autotuning, it also meant tuning was done even if userspace was reading the mptcp socket very slowly. This adds mptcp_rcv_space_adjust() and calls it after userspace has read data from the mptcp socket rx queue. Its very similar to tcp_rcv_space_adjust, with two differences: 1. The rtt estimate is the largest one observed on a subflow 2. The rcvbuf size and window clamp of all subflows is adjusted to the mptcp-level rcvbuf. Otherwise, we get spurious drops at tcp (subflow) socket level if the skbs are not moved to the mptcp socket fast enough. Before: time mptcp_connect.sh -t -f $((4*1024*1024)) -d 300 -l 0.01% -r 0 -e "" -m mmap [..] ns4 MPTCP -> ns3 (10.0.3.2:10108 ) MPTCP (duration 40823ms) [ OK ] ns4 MPTCP -> ns3 (10.0.3.2:10109 ) TCP (duration 23119ms) [ OK ] ns4 TCP -> ns3 (10.0.3.2:10110 ) MPTCP (duration 5421ms) [ OK ] ns4 MPTCP -> ns3 (dead:beef:3::2:10111) MPTCP (duration 41446ms) [ OK ] ns4 MPTCP -> ns3 (dead:beef:3::2:10112) TCP (duration 23427ms) [ OK ] ns4 TCP -> ns3 (dead:beef:3::2:10113) MPTCP (duration 5426ms) [ OK ] Time: 1396 seconds After: ns4 MPTCP -> ns3 (10.0.3.2:10108 ) MPTCP (duration 5417ms) [ OK ] ns4 MPTCP -> ns3 (10.0.3.2:10109 ) TCP (duration 5427ms) [ OK ] ns4 TCP -> ns3 (10.0.3.2:10110 ) MPTCP (duration 5422ms) [ OK ] ns4 MPTCP -> ns3 (dead:beef:3::2:10111) MPTCP (duration 5415ms) [ OK ] ns4 MPTCP -> ns3 (dead:beef:3::2:10112) TCP (duration 5422ms) [ OK ] ns4 TCP -> ns3 (dead:beef:3::2:10113) MPTCP (duration 5423ms) [ OK ] Time: 296 seconds Signed-off-by: Florian Westphal <fw@strlen.de> Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-07-01 03:24:45 +08:00
struct {
u32 space; /* bytes copied in last measurement window */
u32 copied; /* bytes copied in this measurement window */
u64 time; /* start time of measurement window */
u64 rtt_us; /* last maximum rtt of subflows */
} rcvq_space;
};
#define mptcp_lock_sock(___sk, cb) do { \
struct sock *__sk = (___sk); /* silence macro reuse warning */ \
might_sleep(); \
spin_lock_bh(&__sk->sk_lock.slock); \
if (__sk->sk_lock.owned) \
__lock_sock(__sk); \
cb; \
__sk->sk_lock.owned = 1; \
spin_unlock(&__sk->sk_lock.slock); \
mutex_acquire(&__sk->sk_lock.dep_map, 0, 0, _RET_IP_); \
local_bh_enable(); \
} while (0)
#define mptcp_data_lock(sk) spin_lock_bh(&(sk)->sk_lock.slock)
#define mptcp_data_unlock(sk) spin_unlock_bh(&(sk)->sk_lock.slock)
#define mptcp_for_each_subflow(__msk, __subflow) \
list_for_each_entry(__subflow, &((__msk)->conn_list), node)
static inline void msk_owned_by_me(const struct mptcp_sock *msk)
{
sock_owned_by_me((const struct sock *)msk);
}
static inline struct mptcp_sock *mptcp_sk(const struct sock *sk)
{
return (struct mptcp_sock *)sk;
}
static inline int __mptcp_space(const struct sock *sk)
{
return tcp_space(sk) + READ_ONCE(mptcp_sk(sk)->rmem_released);
}
static inline struct mptcp_data_frag *mptcp_send_head(const struct sock *sk)
{
const struct mptcp_sock *msk = mptcp_sk(sk);
return READ_ONCE(msk->first_pending);
}
static inline struct mptcp_data_frag *mptcp_send_next(struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
struct mptcp_data_frag *cur;
cur = msk->first_pending;
return list_is_last(&cur->list, &msk->rtx_queue) ? NULL :
list_next_entry(cur, list);
}
static inline struct mptcp_data_frag *mptcp_pending_tail(const struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
if (!msk->first_pending)
return NULL;
if (WARN_ON_ONCE(list_empty(&msk->rtx_queue)))
return NULL;
return list_last_entry(&msk->rtx_queue, struct mptcp_data_frag, list);
}
mptcp: fix spurious retransmissions Syzkaller was able to trigger the following splat again: WARNING: CPU: 1 PID: 12512 at net/mptcp/protocol.c:761 mptcp_reset_timer+0x12a/0x160 net/mptcp/protocol.c:761 Modules linked in: CPU: 1 PID: 12512 Comm: kworker/1:6 Not tainted 5.10.0-rc6 #52 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 Workqueue: events mptcp_worker RIP: 0010:mptcp_reset_timer+0x12a/0x160 net/mptcp/protocol.c:761 Code: e8 4b 0c ad ff e8 56 21 88 fe 48 b8 00 00 00 00 00 fc ff df 48 c7 04 03 00 00 00 00 48 83 c4 40 5b 5d 41 5c c3 e8 36 21 88 fe <0f> 0b 41 bc c8 00 00 00 eb 98 e8 e7 b1 af fe e9 30 ff ff ff 48 c7 RSP: 0018:ffffc900018c7c68 EFLAGS: 00010293 RAX: ffff888108cb1c80 RBX: 1ffff92000318f8d RCX: ffffffff82ad0307 RDX: 0000000000000000 RSI: ffffffff82ad036a RDI: 0000000000000007 RBP: ffff888113e2d000 R08: ffff888108cb1c80 R09: ffffed10227c5ab7 R10: ffff888113e2d5b7 R11: ffffed10227c5ab6 R12: 0000000000000000 R13: ffff88801f100000 R14: ffff888113e2d5b0 R15: 0000000000000001 FS: 0000000000000000(0000) GS:ffff88811b500000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fd76a874ef8 CR3: 000000001689c005 CR4: 0000000000170ee0 Call Trace: mptcp_worker+0xaa4/0x1560 net/mptcp/protocol.c:2334 process_one_work+0x8d3/0x1200 kernel/workqueue.c:2272 worker_thread+0x9c/0x1090 kernel/workqueue.c:2418 kthread+0x303/0x410 kernel/kthread.c:292 ret_from_fork+0x22/0x30 arch/x86/entry/entry_64.S:296 The mptcp_worker tries to update the MPTCP retransmission timer even if such timer is not currently scheduled. The mptcp_rtx_head() return value is bogus: we can have enqueued data not yet transmitted. The above may additionally cause spurious, unneeded MPTCP-level retransmissions. Fix the issue adding an explicit clearing of the rtx queue before trying to retransmit and checking for unacked data. Additionally drop an unneeded timer stop call and the unused mptcp_rtx_tail() helper. Reported-by: Christoph Paasch <cpaasch@apple.com> Fixes: 6e628cd3a8f7 ("mptcp: use mptcp release_cb for delayed tasks") Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-02-12 07:30:39 +08:00
static inline struct mptcp_data_frag *mptcp_rtx_head(const struct sock *sk)
{
struct mptcp_sock *msk = mptcp_sk(sk);
mptcp: fix spurious retransmissions Syzkaller was able to trigger the following splat again: WARNING: CPU: 1 PID: 12512 at net/mptcp/protocol.c:761 mptcp_reset_timer+0x12a/0x160 net/mptcp/protocol.c:761 Modules linked in: CPU: 1 PID: 12512 Comm: kworker/1:6 Not tainted 5.10.0-rc6 #52 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 Workqueue: events mptcp_worker RIP: 0010:mptcp_reset_timer+0x12a/0x160 net/mptcp/protocol.c:761 Code: e8 4b 0c ad ff e8 56 21 88 fe 48 b8 00 00 00 00 00 fc ff df 48 c7 04 03 00 00 00 00 48 83 c4 40 5b 5d 41 5c c3 e8 36 21 88 fe <0f> 0b 41 bc c8 00 00 00 eb 98 e8 e7 b1 af fe e9 30 ff ff ff 48 c7 RSP: 0018:ffffc900018c7c68 EFLAGS: 00010293 RAX: ffff888108cb1c80 RBX: 1ffff92000318f8d RCX: ffffffff82ad0307 RDX: 0000000000000000 RSI: ffffffff82ad036a RDI: 0000000000000007 RBP: ffff888113e2d000 R08: ffff888108cb1c80 R09: ffffed10227c5ab7 R10: ffff888113e2d5b7 R11: ffffed10227c5ab6 R12: 0000000000000000 R13: ffff88801f100000 R14: ffff888113e2d5b0 R15: 0000000000000001 FS: 0000000000000000(0000) GS:ffff88811b500000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fd76a874ef8 CR3: 000000001689c005 CR4: 0000000000170ee0 Call Trace: mptcp_worker+0xaa4/0x1560 net/mptcp/protocol.c:2334 process_one_work+0x8d3/0x1200 kernel/workqueue.c:2272 worker_thread+0x9c/0x1090 kernel/workqueue.c:2418 kthread+0x303/0x410 kernel/kthread.c:292 ret_from_fork+0x22/0x30 arch/x86/entry/entry_64.S:296 The mptcp_worker tries to update the MPTCP retransmission timer even if such timer is not currently scheduled. The mptcp_rtx_head() return value is bogus: we can have enqueued data not yet transmitted. The above may additionally cause spurious, unneeded MPTCP-level retransmissions. Fix the issue adding an explicit clearing of the rtx queue before trying to retransmit and checking for unacked data. Additionally drop an unneeded timer stop call and the unused mptcp_rtx_tail() helper. Reported-by: Christoph Paasch <cpaasch@apple.com> Fixes: 6e628cd3a8f7 ("mptcp: use mptcp release_cb for delayed tasks") Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-02-12 07:30:39 +08:00
if (msk->snd_una == READ_ONCE(msk->snd_nxt))
return NULL;
return list_first_entry_or_null(&msk->rtx_queue, struct mptcp_data_frag, list);
}
struct mptcp_subflow_request_sock {
struct tcp_request_sock sk;
u16 mp_capable : 1,
mp_join : 1,
backup : 1;
u8 local_id;
u8 remote_id;
u64 local_key;
u64 idsn;
u32 token;
u32 ssn_offset;
u64 thmac;
u32 local_nonce;
u32 remote_nonce;
struct mptcp_sock *msk;
struct hlist_nulls_node token_node;
};
static inline struct mptcp_subflow_request_sock *
mptcp_subflow_rsk(const struct request_sock *rsk)
{
return (struct mptcp_subflow_request_sock *)rsk;
}
enum mptcp_data_avail {
MPTCP_SUBFLOW_NODATA,
MPTCP_SUBFLOW_DATA_AVAIL,
MPTCP_SUBFLOW_OOO_DATA
};
struct mptcp_delegated_action {
struct napi_struct napi;
struct list_head head;
};
DECLARE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions);
#define MPTCP_DELEGATE_SEND 0
/* MPTCP subflow context */
struct mptcp_subflow_context {
struct list_head node;/* conn_list of subflows */
u64 local_key;
u64 remote_key;
u64 idsn;
u64 map_seq;
u32 snd_isn;
u32 token;
u32 rel_write_seq;
u32 map_subflow_seq;
u32 ssn_offset;
u32 map_data_len;
u32 request_mptcp : 1, /* send MP_CAPABLE */
request_join : 1, /* send MP_JOIN */
request_bkup : 1,
mp_capable : 1, /* remote is MPTCP capable */
mp_join : 1, /* remote is JOINing */
fully_established : 1, /* path validated */
pm_notified : 1, /* PM hook called for established status */
conn_finished : 1,
map_valid : 1,
mpc_map : 1,
backup : 1,
send_mp_prio : 1,
rx_eof : 1,
mptcp: refactor shutdown and close We must not close the subflows before all the MPTCP level data, comprising the DATA_FIN has been acked at the MPTCP level, otherwise we could be unable to retransmit as needed. __mptcp_wr_shutdown() shutdown is responsible to check for the correct status and close all subflows. Is called by the output path after spooling any data and at shutdown/close time. In a similar way, __mptcp_destroy_sock() is responsible to clean-up the MPTCP level status, and is called when the msk transition to TCP_CLOSE. The protocol level close() does not force anymore the TCP_CLOSE status, but orphan the msk socket and all the subflows. Orphaned msk sockets are forciby closed after a timeout or when all MPTCP-level data is acked. There is a caveat about keeping the orphaned subflows around: the TCP stack can asynchronusly call tcp_cleanup_ulp() on them via tcp_close(). To prevent accessing freed memory on later MPTCP level operations, the msk acquires a reference to each subflow socket and prevent subflow_ulp_release() from releasing the subflow context before __mptcp_destroy_sock(). The additional subflow references are released by __mptcp_done() and the async ULP release is detected checking ULP ops. If such field has been already cleared by the ULP release path, the dangling context is freed directly by __mptcp_done(). Co-developed-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-11-16 17:48:09 +08:00
can_ack : 1, /* only after processing the remote a key */
disposable : 1; /* ctx can be free at ulp release time */
enum mptcp_data_avail data_avail;
u32 remote_nonce;
u64 thmac;
u32 local_nonce;
u32 remote_token;
u8 hmac[MPTCPOPT_HMAC_LEN];
u8 local_id;
u8 remote_id;
long delegated_status;
struct list_head delegated_node; /* link into delegated_action, protected by local BH */
struct sock *tcp_sock; /* tcp sk backpointer */
struct sock *conn; /* parent mptcp_sock */
const struct inet_connection_sock_af_ops *icsk_af_ops;
void (*tcp_data_ready)(struct sock *sk);
void (*tcp_state_change)(struct sock *sk);
void (*tcp_write_space)(struct sock *sk);
void (*tcp_error_report)(struct sock *sk);
struct rcu_head rcu;
};
static inline struct mptcp_subflow_context *
mptcp_subflow_ctx(const struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
/* Use RCU on icsk_ulp_data only for sock diag code */
return (__force struct mptcp_subflow_context *)icsk->icsk_ulp_data;
}
static inline struct sock *
mptcp_subflow_tcp_sock(const struct mptcp_subflow_context *subflow)
{
return subflow->tcp_sock;
}
static inline u64
mptcp_subflow_get_map_offset(const struct mptcp_subflow_context *subflow)
{
return tcp_sk(mptcp_subflow_tcp_sock(subflow))->copied_seq -
subflow->ssn_offset -
subflow->map_subflow_seq;
}
static inline u64
mptcp_subflow_get_mapped_dsn(const struct mptcp_subflow_context *subflow)
{
return subflow->map_seq + mptcp_subflow_get_map_offset(subflow);
}
static inline void mptcp_add_pending_subflow(struct mptcp_sock *msk,
struct mptcp_subflow_context *subflow)
{
sock_hold(mptcp_subflow_tcp_sock(subflow));
spin_lock_bh(&msk->join_list_lock);
list_add_tail(&subflow->node, &msk->join_list);
spin_unlock_bh(&msk->join_list_lock);
}
void mptcp_subflow_process_delegated(struct sock *ssk);
static inline void mptcp_subflow_delegate(struct mptcp_subflow_context *subflow)
{
struct mptcp_delegated_action *delegated;
bool schedule;
/* The implied barrier pairs with mptcp_subflow_delegated_done(), and
* ensures the below list check sees list updates done prior to status
* bit changes
*/
if (!test_and_set_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status)) {
/* still on delegated list from previous scheduling */
if (!list_empty(&subflow->delegated_node))
return;
/* the caller held the subflow bh socket lock */
lockdep_assert_in_softirq();
delegated = this_cpu_ptr(&mptcp_delegated_actions);
schedule = list_empty(&delegated->head);
list_add_tail(&subflow->delegated_node, &delegated->head);
sock_hold(mptcp_subflow_tcp_sock(subflow));
if (schedule)
napi_schedule(&delegated->napi);
}
}
static inline struct mptcp_subflow_context *
mptcp_subflow_delegated_next(struct mptcp_delegated_action *delegated)
{
struct mptcp_subflow_context *ret;
if (list_empty(&delegated->head))
return NULL;
ret = list_first_entry(&delegated->head, struct mptcp_subflow_context, delegated_node);
list_del_init(&ret->delegated_node);
return ret;
}
static inline bool mptcp_subflow_has_delegated_action(const struct mptcp_subflow_context *subflow)
{
return test_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status);
}
static inline void mptcp_subflow_delegated_done(struct mptcp_subflow_context *subflow)
{
/* pairs with mptcp_subflow_delegate, ensures delegate_node is updated before
* touching the status bit
*/
smp_wmb();
clear_bit(MPTCP_DELEGATE_SEND, &subflow->delegated_status);
}
int mptcp_is_enabled(struct net *net);
unsigned int mptcp_get_add_addr_timeout(struct net *net);
void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
struct mptcp_options_received *mp_opt);
bool mptcp_subflow_data_available(struct sock *sk);
void __init mptcp_subflow_init(void);
void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how);
void mptcp_close_ssk(struct sock *sk, struct sock *ssk,
struct mptcp_subflow_context *subflow);
void mptcp_subflow_reset(struct sock *ssk);
void mptcp_sock_graft(struct sock *sk, struct socket *parent);
struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk);
/* called with sk socket lock held */
int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
const struct mptcp_addr_info *remote);
int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock);
void mptcp_info2sockaddr(const struct mptcp_addr_info *info,
struct sockaddr_storage *addr,
unsigned short family);
static inline void mptcp_subflow_tcp_fallback(struct sock *sk,
struct mptcp_subflow_context *ctx)
{
sk->sk_data_ready = ctx->tcp_data_ready;
sk->sk_state_change = ctx->tcp_state_change;
sk->sk_write_space = ctx->tcp_write_space;
sk->sk_error_report = ctx->tcp_error_report;
inet_csk(sk)->icsk_af_ops = ctx->icsk_af_ops;
}
void __init mptcp_proto_init(void);
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
int __init mptcp_proto_v6_init(void);
#endif
struct sock *mptcp_sk_clone(const struct sock *sk,
mptcp: move option parsing into mptcp_incoming_options() The mptcp_options_received structure carries several per packet flags (mp_capable, mp_join, etc.). Such fields must be cleared on each packet, even on dropped ones or packet not carrying any MPTCP options, but the current mptcp code clears them only on TCP option reset. On several races/corner cases we end-up with stray bits in incoming options, leading to WARN_ON splats. e.g.: [ 171.164906] Bad mapping: ssn=32714 map_seq=1 map_data_len=32713 [ 171.165006] WARNING: CPU: 1 PID: 5026 at net/mptcp/subflow.c:533 warn_bad_map (linux-mptcp/net/mptcp/subflow.c:533 linux-mptcp/net/mptcp/subflow.c:531) [ 171.167632] Modules linked in: ip6_vti ip_vti ip_gre ipip sit tunnel4 ip_tunnel geneve ip6_udp_tunnel udp_tunnel macsec macvtap tap ipvlan macvlan 8021q garp mrp xfrm_interface veth netdevsim nlmon dummy team bonding vcan bridge stp llc ip6_gre gre ip6_tunnel tunnel6 tun binfmt_misc intel_rapl_msr intel_rapl_common rfkill kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel joydev virtio_balloon pcspkr i2c_piix4 sunrpc ip_tables xfs libcrc32c crc32c_intel serio_raw virtio_console ata_generic virtio_blk virtio_net net_failover failover ata_piix libata [ 171.199464] CPU: 1 PID: 5026 Comm: repro Not tainted 5.7.0-rc1.mptcp_f227fdf5d388+ #95 [ 171.200886] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-2.fc30 04/01/2014 [ 171.202546] RIP: 0010:warn_bad_map (linux-mptcp/net/mptcp/subflow.c:533 linux-mptcp/net/mptcp/subflow.c:531) [ 171.206537] Code: c1 ea 03 0f b6 14 02 48 89 f8 83 e0 07 83 c0 03 38 d0 7c 04 84 d2 75 1d 8b 55 3c 44 89 e6 48 c7 c7 20 51 13 95 e8 37 8b 22 fe <0f> 0b 48 83 c4 08 5b 5d 41 5c c3 89 4c 24 04 e8 db d6 94 fe 8b 4c [ 171.220473] RSP: 0018:ffffc90000150560 EFLAGS: 00010282 [ 171.221639] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 [ 171.223108] RDX: 0000000000000000 RSI: 0000000000000008 RDI: fffff5200002a09e [ 171.224388] RBP: ffff8880aa6e3c00 R08: 0000000000000001 R09: fffffbfff2ec9955 [ 171.225706] R10: ffffffff9764caa7 R11: fffffbfff2ec9954 R12: 0000000000007fca [ 171.227211] R13: ffff8881066f4a7f R14: ffff8880aa6e3c00 R15: 0000000000000020 [ 171.228460] FS: 00007f8623719740(0000) GS:ffff88810be00000(0000) knlGS:0000000000000000 [ 171.230065] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 171.231303] CR2: 00007ffdab190a50 CR3: 00000001038ea006 CR4: 0000000000160ee0 [ 171.232586] Call Trace: [ 171.233109] <IRQ> [ 171.233531] get_mapping_status (linux-mptcp/net/mptcp/subflow.c:691) [ 171.234371] mptcp_subflow_data_available (linux-mptcp/net/mptcp/subflow.c:736 linux-mptcp/net/mptcp/subflow.c:832) [ 171.238181] subflow_state_change (linux-mptcp/net/mptcp/subflow.c:1085 (discriminator 1)) [ 171.239066] tcp_fin (linux-mptcp/net/ipv4/tcp_input.c:4217) [ 171.240123] tcp_data_queue (linux-mptcp/./include/linux/compiler.h:199 linux-mptcp/net/ipv4/tcp_input.c:4822) [ 171.245083] tcp_rcv_established (linux-mptcp/./include/linux/skbuff.h:1785 linux-mptcp/./include/net/tcp.h:1774 linux-mptcp/./include/net/tcp.h:1847 linux-mptcp/net/ipv4/tcp_input.c:5238 linux-mptcp/net/ipv4/tcp_input.c:5730) [ 171.254089] tcp_v4_rcv (linux-mptcp/./include/linux/spinlock.h:393 linux-mptcp/net/ipv4/tcp_ipv4.c:2009) [ 171.258969] ip_protocol_deliver_rcu (linux-mptcp/net/ipv4/ip_input.c:204 (discriminator 1)) [ 171.260214] ip_local_deliver_finish (linux-mptcp/./include/linux/rcupdate.h:651 linux-mptcp/net/ipv4/ip_input.c:232) [ 171.261389] ip_local_deliver (linux-mptcp/./include/linux/netfilter.h:307 linux-mptcp/./include/linux/netfilter.h:301 linux-mptcp/net/ipv4/ip_input.c:252) [ 171.265884] ip_rcv (linux-mptcp/./include/linux/netfilter.h:307 linux-mptcp/./include/linux/netfilter.h:301 linux-mptcp/net/ipv4/ip_input.c:539) [ 171.273666] process_backlog (linux-mptcp/./include/linux/rcupdate.h:651 linux-mptcp/net/core/dev.c:6135) [ 171.275328] net_rx_action (linux-mptcp/net/core/dev.c:6572 linux-mptcp/net/core/dev.c:6640) [ 171.280472] __do_softirq (linux-mptcp/./arch/x86/include/asm/jump_label.h:25 linux-mptcp/./include/linux/jump_label.h:200 linux-mptcp/./include/trace/events/irq.h:142 linux-mptcp/kernel/softirq.c:293) [ 171.281379] do_softirq_own_stack (linux-mptcp/arch/x86/entry/entry_64.S:1083) [ 171.282358] </IRQ> We could address the issue clearing explicitly the relevant fields in several places - tcp_parse_option, tcp_fast_parse_options, possibly others. Instead we move the MPTCP option parsing into the already existing mptcp ingress hook, so that we need to clear the fields in a single place. This allows us dropping an MPTCP hook from the TCP code and removing the quite large mptcp_options_received from the tcp_sock struct. On the flip side, the MPTCP sockets will traverse the option space twice (in tcp_parse_option() and in mptcp_incoming_options(). That looks acceptable: we already do that for syn and 3rd ack packets, plain TCP socket will benefit from it, and even MPTCP sockets will experience better code locality, reducing the jumps between TCP and MPTCP code. v1 -> v2: - rebased on current '-net' tree Fixes: 648ef4b88673 ("mptcp: Implement MPTCP receive path") Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 21:01:52 +08:00
const struct mptcp_options_received *mp_opt,
struct request_sock *req);
void mptcp_get_options(const struct sk_buff *skb,
mptcp: move option parsing into mptcp_incoming_options() The mptcp_options_received structure carries several per packet flags (mp_capable, mp_join, etc.). Such fields must be cleared on each packet, even on dropped ones or packet not carrying any MPTCP options, but the current mptcp code clears them only on TCP option reset. On several races/corner cases we end-up with stray bits in incoming options, leading to WARN_ON splats. e.g.: [ 171.164906] Bad mapping: ssn=32714 map_seq=1 map_data_len=32713 [ 171.165006] WARNING: CPU: 1 PID: 5026 at net/mptcp/subflow.c:533 warn_bad_map (linux-mptcp/net/mptcp/subflow.c:533 linux-mptcp/net/mptcp/subflow.c:531) [ 171.167632] Modules linked in: ip6_vti ip_vti ip_gre ipip sit tunnel4 ip_tunnel geneve ip6_udp_tunnel udp_tunnel macsec macvtap tap ipvlan macvlan 8021q garp mrp xfrm_interface veth netdevsim nlmon dummy team bonding vcan bridge stp llc ip6_gre gre ip6_tunnel tunnel6 tun binfmt_misc intel_rapl_msr intel_rapl_common rfkill kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel joydev virtio_balloon pcspkr i2c_piix4 sunrpc ip_tables xfs libcrc32c crc32c_intel serio_raw virtio_console ata_generic virtio_blk virtio_net net_failover failover ata_piix libata [ 171.199464] CPU: 1 PID: 5026 Comm: repro Not tainted 5.7.0-rc1.mptcp_f227fdf5d388+ #95 [ 171.200886] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-2.fc30 04/01/2014 [ 171.202546] RIP: 0010:warn_bad_map (linux-mptcp/net/mptcp/subflow.c:533 linux-mptcp/net/mptcp/subflow.c:531) [ 171.206537] Code: c1 ea 03 0f b6 14 02 48 89 f8 83 e0 07 83 c0 03 38 d0 7c 04 84 d2 75 1d 8b 55 3c 44 89 e6 48 c7 c7 20 51 13 95 e8 37 8b 22 fe <0f> 0b 48 83 c4 08 5b 5d 41 5c c3 89 4c 24 04 e8 db d6 94 fe 8b 4c [ 171.220473] RSP: 0018:ffffc90000150560 EFLAGS: 00010282 [ 171.221639] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 [ 171.223108] RDX: 0000000000000000 RSI: 0000000000000008 RDI: fffff5200002a09e [ 171.224388] RBP: ffff8880aa6e3c00 R08: 0000000000000001 R09: fffffbfff2ec9955 [ 171.225706] R10: ffffffff9764caa7 R11: fffffbfff2ec9954 R12: 0000000000007fca [ 171.227211] R13: ffff8881066f4a7f R14: ffff8880aa6e3c00 R15: 0000000000000020 [ 171.228460] FS: 00007f8623719740(0000) GS:ffff88810be00000(0000) knlGS:0000000000000000 [ 171.230065] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 171.231303] CR2: 00007ffdab190a50 CR3: 00000001038ea006 CR4: 0000000000160ee0 [ 171.232586] Call Trace: [ 171.233109] <IRQ> [ 171.233531] get_mapping_status (linux-mptcp/net/mptcp/subflow.c:691) [ 171.234371] mptcp_subflow_data_available (linux-mptcp/net/mptcp/subflow.c:736 linux-mptcp/net/mptcp/subflow.c:832) [ 171.238181] subflow_state_change (linux-mptcp/net/mptcp/subflow.c:1085 (discriminator 1)) [ 171.239066] tcp_fin (linux-mptcp/net/ipv4/tcp_input.c:4217) [ 171.240123] tcp_data_queue (linux-mptcp/./include/linux/compiler.h:199 linux-mptcp/net/ipv4/tcp_input.c:4822) [ 171.245083] tcp_rcv_established (linux-mptcp/./include/linux/skbuff.h:1785 linux-mptcp/./include/net/tcp.h:1774 linux-mptcp/./include/net/tcp.h:1847 linux-mptcp/net/ipv4/tcp_input.c:5238 linux-mptcp/net/ipv4/tcp_input.c:5730) [ 171.254089] tcp_v4_rcv (linux-mptcp/./include/linux/spinlock.h:393 linux-mptcp/net/ipv4/tcp_ipv4.c:2009) [ 171.258969] ip_protocol_deliver_rcu (linux-mptcp/net/ipv4/ip_input.c:204 (discriminator 1)) [ 171.260214] ip_local_deliver_finish (linux-mptcp/./include/linux/rcupdate.h:651 linux-mptcp/net/ipv4/ip_input.c:232) [ 171.261389] ip_local_deliver (linux-mptcp/./include/linux/netfilter.h:307 linux-mptcp/./include/linux/netfilter.h:301 linux-mptcp/net/ipv4/ip_input.c:252) [ 171.265884] ip_rcv (linux-mptcp/./include/linux/netfilter.h:307 linux-mptcp/./include/linux/netfilter.h:301 linux-mptcp/net/ipv4/ip_input.c:539) [ 171.273666] process_backlog (linux-mptcp/./include/linux/rcupdate.h:651 linux-mptcp/net/core/dev.c:6135) [ 171.275328] net_rx_action (linux-mptcp/net/core/dev.c:6572 linux-mptcp/net/core/dev.c:6640) [ 171.280472] __do_softirq (linux-mptcp/./arch/x86/include/asm/jump_label.h:25 linux-mptcp/./include/linux/jump_label.h:200 linux-mptcp/./include/trace/events/irq.h:142 linux-mptcp/kernel/softirq.c:293) [ 171.281379] do_softirq_own_stack (linux-mptcp/arch/x86/entry/entry_64.S:1083) [ 171.282358] </IRQ> We could address the issue clearing explicitly the relevant fields in several places - tcp_parse_option, tcp_fast_parse_options, possibly others. Instead we move the MPTCP option parsing into the already existing mptcp ingress hook, so that we need to clear the fields in a single place. This allows us dropping an MPTCP hook from the TCP code and removing the quite large mptcp_options_received from the tcp_sock struct. On the flip side, the MPTCP sockets will traverse the option space twice (in tcp_parse_option() and in mptcp_incoming_options(). That looks acceptable: we already do that for syn and 3rd ack packets, plain TCP socket will benefit from it, and even MPTCP sockets will experience better code locality, reducing the jumps between TCP and MPTCP code. v1 -> v2: - rebased on current '-net' tree Fixes: 648ef4b88673 ("mptcp: Implement MPTCP receive path") Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 21:01:52 +08:00
struct mptcp_options_received *mp_opt);
void mptcp_finish_connect(struct sock *sk);
static inline bool mptcp_is_fully_established(struct sock *sk)
{
return inet_sk_state_load(sk) == TCP_ESTABLISHED &&
READ_ONCE(mptcp_sk(sk)->fully_established);
}
mptcp: add receive buffer auto-tuning When mptcp is used, userspace doesn't read from the tcp (subflow) socket but from the parent (mptcp) socket receive queue. skbs are moved from the subflow socket to the mptcp rx queue either from 'data_ready' callback (if mptcp socket can be locked), a work queue, or the socket receive function. This means tcp_rcv_space_adjust() is never called and thus no receive buffer size auto-tuning is done. An earlier (not merged) patch added tcp_rcv_space_adjust() calls to the function that moves skbs from subflow to mptcp socket. While this enabled autotuning, it also meant tuning was done even if userspace was reading the mptcp socket very slowly. This adds mptcp_rcv_space_adjust() and calls it after userspace has read data from the mptcp socket rx queue. Its very similar to tcp_rcv_space_adjust, with two differences: 1. The rtt estimate is the largest one observed on a subflow 2. The rcvbuf size and window clamp of all subflows is adjusted to the mptcp-level rcvbuf. Otherwise, we get spurious drops at tcp (subflow) socket level if the skbs are not moved to the mptcp socket fast enough. Before: time mptcp_connect.sh -t -f $((4*1024*1024)) -d 300 -l 0.01% -r 0 -e "" -m mmap [..] ns4 MPTCP -> ns3 (10.0.3.2:10108 ) MPTCP (duration 40823ms) [ OK ] ns4 MPTCP -> ns3 (10.0.3.2:10109 ) TCP (duration 23119ms) [ OK ] ns4 TCP -> ns3 (10.0.3.2:10110 ) MPTCP (duration 5421ms) [ OK ] ns4 MPTCP -> ns3 (dead:beef:3::2:10111) MPTCP (duration 41446ms) [ OK ] ns4 MPTCP -> ns3 (dead:beef:3::2:10112) TCP (duration 23427ms) [ OK ] ns4 TCP -> ns3 (dead:beef:3::2:10113) MPTCP (duration 5426ms) [ OK ] Time: 1396 seconds After: ns4 MPTCP -> ns3 (10.0.3.2:10108 ) MPTCP (duration 5417ms) [ OK ] ns4 MPTCP -> ns3 (10.0.3.2:10109 ) TCP (duration 5427ms) [ OK ] ns4 TCP -> ns3 (10.0.3.2:10110 ) MPTCP (duration 5422ms) [ OK ] ns4 MPTCP -> ns3 (dead:beef:3::2:10111) MPTCP (duration 5415ms) [ OK ] ns4 MPTCP -> ns3 (dead:beef:3::2:10112) TCP (duration 5422ms) [ OK ] ns4 TCP -> ns3 (dead:beef:3::2:10113) MPTCP (duration 5423ms) [ OK ] Time: 296 seconds Signed-off-by: Florian Westphal <fw@strlen.de> Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-07-01 03:24:45 +08:00
void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk);
void mptcp_data_ready(struct sock *sk, struct sock *ssk);
bool mptcp_finish_join(struct sock *sk);
bool mptcp_schedule_work(struct sock *sk);
void __mptcp_check_push(struct sock *sk, struct sock *ssk);
void __mptcp_data_acked(struct sock *sk);
void __mptcp_error_report(struct sock *sk);
void mptcp_subflow_eof(struct sock *sk);
bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool use_64bit);
void __mptcp_flush_join_list(struct mptcp_sock *msk);
mptcp: refactor shutdown and close We must not close the subflows before all the MPTCP level data, comprising the DATA_FIN has been acked at the MPTCP level, otherwise we could be unable to retransmit as needed. __mptcp_wr_shutdown() shutdown is responsible to check for the correct status and close all subflows. Is called by the output path after spooling any data and at shutdown/close time. In a similar way, __mptcp_destroy_sock() is responsible to clean-up the MPTCP level status, and is called when the msk transition to TCP_CLOSE. The protocol level close() does not force anymore the TCP_CLOSE status, but orphan the msk socket and all the subflows. Orphaned msk sockets are forciby closed after a timeout or when all MPTCP-level data is acked. There is a caveat about keeping the orphaned subflows around: the TCP stack can asynchronusly call tcp_cleanup_ulp() on them via tcp_close(). To prevent accessing freed memory on later MPTCP level operations, the msk acquires a reference to each subflow socket and prevent subflow_ulp_release() from releasing the subflow context before __mptcp_destroy_sock(). The additional subflow references are released by __mptcp_done() and the async ULP release is detected checking ULP ops. If such field has been already cleared by the ULP release path, the dangling context is freed directly by __mptcp_done(). Co-developed-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-11-16 17:48:09 +08:00
static inline bool mptcp_data_fin_enabled(const struct mptcp_sock *msk)
{
return READ_ONCE(msk->snd_data_fin_enable) &&
READ_ONCE(msk->write_seq) == READ_ONCE(msk->snd_nxt);
}
static inline bool mptcp_propagate_sndbuf(struct sock *sk, struct sock *ssk)
{
if ((sk->sk_userlocks & SOCK_SNDBUF_LOCK) || ssk->sk_sndbuf <= READ_ONCE(sk->sk_sndbuf))
return false;
WRITE_ONCE(sk->sk_sndbuf, ssk->sk_sndbuf);
return true;
}
static inline void mptcp_write_space(struct sock *sk)
{
if (sk_stream_is_writeable(sk)) {
/* pairs with memory barrier in mptcp_poll */
smp_mb();
if (test_and_clear_bit(MPTCP_NOSPACE, &mptcp_sk(sk)->flags))
sk_stream_write_space(sk);
}
}
void mptcp_destroy_common(struct mptcp_sock *msk);
void __init mptcp_token_init(void);
static inline void mptcp_token_init_request(struct request_sock *req)
{
mptcp_subflow_rsk(req)->token_node.pprev = NULL;
}
int mptcp_token_new_request(struct request_sock *req);
void mptcp_token_destroy_request(struct request_sock *req);
int mptcp_token_new_connect(struct sock *sk);
void mptcp_token_accept(struct mptcp_subflow_request_sock *r,
struct mptcp_sock *msk);
bool mptcp_token_exists(u32 token);
struct mptcp_sock *mptcp_token_get_sock(u32 token);
struct mptcp_sock *mptcp_token_iter_next(const struct net *net, long *s_slot,
long *s_num);
void mptcp_token_destroy(struct mptcp_sock *msk);
void mptcp_crypto_key_sha(u64 key, u32 *token, u64 *idsn);
void mptcp_crypto_hmac_sha(u64 key1, u64 key2, u8 *msg, int len, void *hmac);
void __init mptcp_pm_init(void);
void mptcp_pm_data_init(struct mptcp_sock *msk);
void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int server_side);
void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk, gfp_t gfp);
bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk);
void mptcp_pm_connection_closed(struct mptcp_sock *msk);
void mptcp_pm_subflow_established(struct mptcp_sock *msk,
struct mptcp_subflow_context *subflow);
void mptcp_pm_subflow_closed(struct mptcp_sock *msk, u8 id);
void mptcp_pm_add_addr_received(struct mptcp_sock *msk,
const struct mptcp_addr_info *addr);
void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk);
void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, u8 rm_id);
void mptcp_pm_mp_prio_received(struct sock *sk, u8 bkup);
int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
struct mptcp_addr_info *addr,
u8 bkup);
void mptcp_pm_free_anno_list(struct mptcp_sock *msk);
bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk);
struct mptcp_pm_add_entry *
mptcp_pm_del_add_timer(struct mptcp_sock *msk,
struct mptcp_addr_info *addr);
int mptcp_pm_announce_addr(struct mptcp_sock *msk,
const struct mptcp_addr_info *addr,
bool echo, bool port);
int mptcp_pm_remove_addr(struct mptcp_sock *msk, u8 local_id);
int mptcp_pm_remove_subflow(struct mptcp_sock *msk, u8 local_id);
void mptcp_event(enum mptcp_event_type type, const struct mptcp_sock *msk,
const struct sock *ssk, gfp_t gfp);
void mptcp_event_addr_announced(const struct mptcp_sock *msk, const struct mptcp_addr_info *info);
void mptcp_event_addr_removed(const struct mptcp_sock *msk, u8 id);
static inline bool mptcp_pm_should_add_signal(struct mptcp_sock *msk)
{
return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_ADD_ADDR_SIGNAL);
}
static inline bool mptcp_pm_should_add_signal_echo(struct mptcp_sock *msk)
{
return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_ADD_ADDR_ECHO);
}
static inline bool mptcp_pm_should_add_signal_ipv6(struct mptcp_sock *msk)
{
return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_ADD_ADDR_IPV6);
}
static inline bool mptcp_pm_should_add_signal_port(struct mptcp_sock *msk)
{
return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_ADD_ADDR_PORT);
}
static inline bool mptcp_pm_should_rm_signal(struct mptcp_sock *msk)
{
return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_RM_ADDR_SIGNAL);
}
static inline unsigned int mptcp_add_addr_len(int family, bool echo, bool port)
{
u8 len = TCPOLEN_MPTCP_ADD_ADDR_BASE;
if (family == AF_INET6)
len = TCPOLEN_MPTCP_ADD_ADDR6_BASE;
if (!echo)
len += MPTCPOPT_THMAC_LEN;
if (port)
len += TCPOLEN_MPTCP_PORT_LEN;
return len;
}
bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
struct mptcp_addr_info *saddr, bool *echo, bool *port);
bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
u8 *rm_id);
int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);
void __init mptcp_pm_nl_init(void);
void mptcp_pm_nl_data_init(struct mptcp_sock *msk);
void mptcp_pm_nl_work(struct mptcp_sock *msk);
void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, u8 rm_id);
int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);
unsigned int mptcp_pm_get_add_addr_signal_max(struct mptcp_sock *msk);
unsigned int mptcp_pm_get_add_addr_accept_max(struct mptcp_sock *msk);
unsigned int mptcp_pm_get_subflows_max(struct mptcp_sock *msk);
unsigned int mptcp_pm_get_local_addr_max(struct mptcp_sock *msk);
static inline struct mptcp_ext *mptcp_get_ext(struct sk_buff *skb)
{
return (struct mptcp_ext *)skb_ext_find(skb, SKB_EXT_MPTCP);
}
void mptcp_diag_subflow_init(struct tcp_ulp_ops *ops);
static inline bool __mptcp_check_fallback(const struct mptcp_sock *msk)
{
return test_bit(MPTCP_FALLBACK_DONE, &msk->flags);
}
static inline bool mptcp_check_fallback(const struct sock *sk)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
return __mptcp_check_fallback(msk);
}
static inline void __mptcp_do_fallback(struct mptcp_sock *msk)
{
if (test_bit(MPTCP_FALLBACK_DONE, &msk->flags)) {
pr_debug("TCP fallback already done (msk=%p)", msk);
return;
}
set_bit(MPTCP_FALLBACK_DONE, &msk->flags);
}
static inline void mptcp_do_fallback(struct sock *sk)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
__mptcp_do_fallback(msk);
}
#define pr_fallback(a) pr_debug("%s:fallback to TCP (msk=%p)", __func__, a)
mptcp: fallback in case of simultaneous connect when a MPTCP client tries to connect to itself, tcp_finish_connect() is never reached. Because of this, depending on the socket current state, multiple faulty behaviours can be observed: 1) a WARN_ON() in subflow_data_ready() is hit WARNING: CPU: 2 PID: 882 at net/mptcp/subflow.c:911 subflow_data_ready+0x18b/0x230 [...] CPU: 2 PID: 882 Comm: gh35 Not tainted 5.7.0+ #187 [...] RIP: 0010:subflow_data_ready+0x18b/0x230 [...] Call Trace: tcp_data_queue+0xd2f/0x4250 tcp_rcv_state_process+0xb1c/0x49d3 tcp_v4_do_rcv+0x2bc/0x790 __release_sock+0x153/0x2d0 release_sock+0x4f/0x170 mptcp_shutdown+0x167/0x4e0 __sys_shutdown+0xe6/0x180 __x64_sys_shutdown+0x50/0x70 do_syscall_64+0x9a/0x370 entry_SYSCALL_64_after_hwframe+0x44/0xa9 2) client is stuck forever in mptcp_sendmsg() because the socket is not TCP_ESTABLISHED crash> bt 4847 PID: 4847 TASK: ffff88814b2fb100 CPU: 1 COMMAND: "gh35" #0 [ffff8881376ff680] __schedule at ffffffff97248da4 #1 [ffff8881376ff778] schedule at ffffffff9724a34f #2 [ffff8881376ff7a0] schedule_timeout at ffffffff97252ba0 #3 [ffff8881376ff8a8] wait_woken at ffffffff958ab4ba #4 [ffff8881376ff940] sk_stream_wait_connect at ffffffff96c2d859 #5 [ffff8881376ffa28] mptcp_sendmsg at ffffffff97207fca #6 [ffff8881376ffbc0] sock_sendmsg at ffffffff96be1b5b #7 [ffff8881376ffbe8] sock_write_iter at ffffffff96be1daa #8 [ffff8881376ffce8] new_sync_write at ffffffff95e5cb52 #9 [ffff8881376ffe50] vfs_write at ffffffff95e6547f #10 [ffff8881376ffe90] ksys_write at ffffffff95e65d26 #11 [ffff8881376fff28] do_syscall_64 at ffffffff956088ba #12 [ffff8881376fff50] entry_SYSCALL_64_after_hwframe at ffffffff9740008c RIP: 00007f126f6956ed RSP: 00007ffc2a320278 RFLAGS: 00000217 RAX: ffffffffffffffda RBX: 0000000020000044 RCX: 00007f126f6956ed RDX: 0000000000000004 RSI: 00000000004007b8 RDI: 0000000000000003 RBP: 00007ffc2a3202a0 R8: 0000000000400720 R9: 0000000000400720 R10: 0000000000400720 R11: 0000000000000217 R12: 00000000004004b0 R13: 00007ffc2a320380 R14: 0000000000000000 R15: 0000000000000000 ORIG_RAX: 0000000000000001 CS: 0033 SS: 002b 3) tcpdump captures show that DSS is exchanged even when MP_CAPABLE handshake didn't complete. $ tcpdump -tnnr bad.pcap IP 127.0.0.1.20000 > 127.0.0.1.20000: Flags [S], seq 3208913911, win 65483, options [mss 65495,sackOK,TS val 3291706876 ecr 3291694721,nop,wscale 7,mptcp capable v1], length 0 IP 127.0.0.1.20000 > 127.0.0.1.20000: Flags [S.], seq 3208913911, ack 3208913912, win 65483, options [mss 65495,sackOK,TS val 3291706876 ecr 3291706876,nop,wscale 7,mptcp capable v1], length 0 IP 127.0.0.1.20000 > 127.0.0.1.20000: Flags [.], ack 1, win 512, options [nop,nop,TS val 3291706876 ecr 3291706876], length 0 IP 127.0.0.1.20000 > 127.0.0.1.20000: Flags [F.], seq 1, ack 1, win 512, options [nop,nop,TS val 3291707876 ecr 3291706876,mptcp dss fin seq 0 subseq 0 len 1,nop,nop], length 0 IP 127.0.0.1.20000 > 127.0.0.1.20000: Flags [.], ack 2, win 512, options [nop,nop,TS val 3291707876 ecr 3291707876], length 0 force a fallback to TCP in these cases, and adjust the main socket state to avoid hanging in mptcp_sendmsg(). Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/35 Reported-by: Christoph Paasch <cpaasch@apple.com> Suggested-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-06-30 04:26:21 +08:00
static inline bool subflow_simultaneous_connect(struct sock *sk)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct sock *parent = subflow->conn;
return sk->sk_state == TCP_ESTABLISHED &&
!mptcp_sk(parent)->pm.server_side &&
!subflow->conn_finished;
}
#ifdef CONFIG_SYN_COOKIES
void subflow_init_req_cookie_join_save(const struct mptcp_subflow_request_sock *subflow_req,
struct sk_buff *skb);
bool mptcp_token_join_cookie_init_state(struct mptcp_subflow_request_sock *subflow_req,
struct sk_buff *skb);
void __init mptcp_join_cookie_init(void);
#else
static inline void
subflow_init_req_cookie_join_save(const struct mptcp_subflow_request_sock *subflow_req,
struct sk_buff *skb) {}
static inline bool
mptcp_token_join_cookie_init_state(struct mptcp_subflow_request_sock *subflow_req,
struct sk_buff *skb)
{
return false;
}
static inline void mptcp_join_cookie_init(void) {}
#endif
#endif /* __MPTCP_PROTOCOL_H */