linux/net/mptcp/options.c

1334 lines
35 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/* Multipath TCP
*
* Copyright (c) 2017 - 2019, Intel Corporation.
*/
#define pr_fmt(fmt) "MPTCP: " fmt
#include <linux/kernel.h>
#include <crypto/sha2.h>
#include <net/tcp.h>
#include <net/mptcp.h>
#include "protocol.h"
#include "mib.h"
static bool mptcp_cap_flag_sha256(u8 flags)
{
return (flags & MPTCP_CAP_FLAG_MASK) == MPTCP_CAP_HMAC_SHA256;
}
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
static void mptcp_parse_option(const struct sk_buff *skb,
const unsigned char *ptr, int opsize,
struct mptcp_options_received *mp_opt)
{
u8 subtype = *ptr >> 4;
int expected_opsize;
u8 version;
u8 flags;
switch (subtype) {
case MPTCPOPT_MP_CAPABLE:
/* strict size checking */
if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)) {
if (skb->len > tcp_hdr(skb)->doff << 2)
expected_opsize = TCPOLEN_MPTCP_MPC_ACK_DATA;
else
expected_opsize = TCPOLEN_MPTCP_MPC_ACK;
} else {
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_ACK)
expected_opsize = TCPOLEN_MPTCP_MPC_SYNACK;
else
expected_opsize = TCPOLEN_MPTCP_MPC_SYN;
}
if (opsize != expected_opsize)
break;
/* try to be gentle vs future versions on the initial syn */
version = *ptr++ & MPTCP_VERSION_MASK;
if (opsize != TCPOLEN_MPTCP_MPC_SYN) {
if (version != MPTCP_SUPPORTED_VERSION)
break;
} else if (version < MPTCP_SUPPORTED_VERSION) {
break;
}
flags = *ptr++;
if (!mptcp_cap_flag_sha256(flags) ||
(flags & MPTCP_CAP_EXTENSIBILITY))
break;
/* RFC 6824, Section 3.1:
* "For the Checksum Required bit (labeled "A"), if either
* host requires the use of checksums, checksums MUST be used.
* In other words, the only way for checksums not to be used
* is if both hosts in their SYNs set A=0."
*
* Section 3.3.0:
* "If a checksum is not present when its use has been
* negotiated, the receiver MUST close the subflow with a RST as
* it is considered broken."
*
* We don't implement DSS checksum - fall back to TCP.
*/
if (flags & MPTCP_CAP_CHECKSUM_REQD)
break;
mp_opt->mp_capable = 1;
if (opsize >= TCPOLEN_MPTCP_MPC_SYNACK) {
mp_opt->sndr_key = get_unaligned_be64(ptr);
ptr += 8;
}
if (opsize >= TCPOLEN_MPTCP_MPC_ACK) {
mp_opt->rcvr_key = get_unaligned_be64(ptr);
ptr += 8;
}
if (opsize == TCPOLEN_MPTCP_MPC_ACK_DATA) {
/* Section 3.1.:
* "the data parameters in a MP_CAPABLE are semantically
* equivalent to those in a DSS option and can be used
* interchangeably."
*/
mp_opt->dss = 1;
mp_opt->use_map = 1;
mp_opt->mpc_map = 1;
mp_opt->data_len = get_unaligned_be16(ptr);
ptr += 2;
}
pr_debug("MP_CAPABLE version=%x, flags=%x, optlen=%d sndr=%llu, rcvr=%llu len=%d",
version, flags, opsize, mp_opt->sndr_key,
mp_opt->rcvr_key, mp_opt->data_len);
break;
case MPTCPOPT_MP_JOIN:
mp_opt->mp_join = 1;
if (opsize == TCPOLEN_MPTCP_MPJ_SYN) {
mp_opt->backup = *ptr++ & MPTCPOPT_BACKUP;
mp_opt->join_id = *ptr++;
mp_opt->token = get_unaligned_be32(ptr);
ptr += 4;
mp_opt->nonce = get_unaligned_be32(ptr);
ptr += 4;
pr_debug("MP_JOIN bkup=%u, id=%u, token=%u, nonce=%u",
mp_opt->backup, mp_opt->join_id,
mp_opt->token, mp_opt->nonce);
} else if (opsize == TCPOLEN_MPTCP_MPJ_SYNACK) {
mp_opt->backup = *ptr++ & MPTCPOPT_BACKUP;
mp_opt->join_id = *ptr++;
mp_opt->thmac = get_unaligned_be64(ptr);
ptr += 8;
mp_opt->nonce = get_unaligned_be32(ptr);
ptr += 4;
pr_debug("MP_JOIN bkup=%u, id=%u, thmac=%llu, nonce=%u",
mp_opt->backup, mp_opt->join_id,
mp_opt->thmac, mp_opt->nonce);
} else if (opsize == TCPOLEN_MPTCP_MPJ_ACK) {
ptr += 2;
memcpy(mp_opt->hmac, ptr, MPTCPOPT_HMAC_LEN);
pr_debug("MP_JOIN hmac");
} else {
pr_warn("MP_JOIN bad option size");
mp_opt->mp_join = 0;
}
break;
case MPTCPOPT_DSS:
pr_debug("DSS");
ptr++;
/* we must clear 'mpc_map' be able to detect MP_CAPABLE
* map vs DSS map in mptcp_incoming_options(), and reconstruct
* map info accordingly
*/
mp_opt->mpc_map = 0;
flags = (*ptr++) & MPTCP_DSS_FLAG_MASK;
mp_opt->data_fin = (flags & MPTCP_DSS_DATA_FIN) != 0;
mp_opt->dsn64 = (flags & MPTCP_DSS_DSN64) != 0;
mp_opt->use_map = (flags & MPTCP_DSS_HAS_MAP) != 0;
mp_opt->ack64 = (flags & MPTCP_DSS_ACK64) != 0;
mp_opt->use_ack = (flags & MPTCP_DSS_HAS_ACK);
pr_debug("data_fin=%d dsn64=%d use_map=%d ack64=%d use_ack=%d",
mp_opt->data_fin, mp_opt->dsn64,
mp_opt->use_map, mp_opt->ack64,
mp_opt->use_ack);
expected_opsize = TCPOLEN_MPTCP_DSS_BASE;
if (mp_opt->use_ack) {
if (mp_opt->ack64)
expected_opsize += TCPOLEN_MPTCP_DSS_ACK64;
else
expected_opsize += TCPOLEN_MPTCP_DSS_ACK32;
}
if (mp_opt->use_map) {
if (mp_opt->dsn64)
expected_opsize += TCPOLEN_MPTCP_DSS_MAP64;
else
expected_opsize += TCPOLEN_MPTCP_DSS_MAP32;
}
/* RFC 6824, Section 3.3:
* If a checksum is present, but its use had
* not been negotiated in the MP_CAPABLE handshake,
* the checksum field MUST be ignored.
*/
if (opsize != expected_opsize &&
opsize != expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM)
break;
mp_opt->dss = 1;
if (mp_opt->use_ack) {
if (mp_opt->ack64) {
mp_opt->data_ack = get_unaligned_be64(ptr);
ptr += 8;
} else {
mp_opt->data_ack = get_unaligned_be32(ptr);
ptr += 4;
}
pr_debug("data_ack=%llu", mp_opt->data_ack);
}
if (mp_opt->use_map) {
if (mp_opt->dsn64) {
mp_opt->data_seq = get_unaligned_be64(ptr);
ptr += 8;
} else {
mp_opt->data_seq = get_unaligned_be32(ptr);
ptr += 4;
}
mp_opt->subflow_seq = get_unaligned_be32(ptr);
ptr += 4;
mp_opt->data_len = get_unaligned_be16(ptr);
ptr += 2;
pr_debug("data_seq=%llu subflow_seq=%u data_len=%u",
mp_opt->data_seq, mp_opt->subflow_seq,
mp_opt->data_len);
}
break;
case MPTCPOPT_ADD_ADDR:
mp_opt->echo = (*ptr++) & MPTCP_ADDR_ECHO;
if (!mp_opt->echo) {
if (opsize == TCPOLEN_MPTCP_ADD_ADDR ||
opsize == TCPOLEN_MPTCP_ADD_ADDR_PORT)
mp_opt->family = MPTCP_ADDR_IPVERSION_4;
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
else if (opsize == TCPOLEN_MPTCP_ADD_ADDR6 ||
opsize == TCPOLEN_MPTCP_ADD_ADDR6_PORT)
mp_opt->family = MPTCP_ADDR_IPVERSION_6;
#endif
else
break;
} else {
if (opsize == TCPOLEN_MPTCP_ADD_ADDR_BASE ||
opsize == TCPOLEN_MPTCP_ADD_ADDR_BASE_PORT)
mp_opt->family = MPTCP_ADDR_IPVERSION_4;
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
else if (opsize == TCPOLEN_MPTCP_ADD_ADDR6_BASE ||
opsize == TCPOLEN_MPTCP_ADD_ADDR6_BASE_PORT)
mp_opt->family = MPTCP_ADDR_IPVERSION_6;
#endif
else
break;
}
mp_opt->add_addr = 1;
mp_opt->addr_id = *ptr++;
if (mp_opt->family == MPTCP_ADDR_IPVERSION_4) {
memcpy((u8 *)&mp_opt->addr.s_addr, (u8 *)ptr, 4);
ptr += 4;
if (opsize == TCPOLEN_MPTCP_ADD_ADDR_PORT ||
opsize == TCPOLEN_MPTCP_ADD_ADDR_BASE_PORT) {
mp_opt->port = get_unaligned_be16(ptr);
ptr += 2;
}
}
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
else {
memcpy(mp_opt->addr6.s6_addr, (u8 *)ptr, 16);
ptr += 16;
if (opsize == TCPOLEN_MPTCP_ADD_ADDR6_PORT ||
opsize == TCPOLEN_MPTCP_ADD_ADDR6_BASE_PORT) {
mp_opt->port = get_unaligned_be16(ptr);
ptr += 2;
}
}
#endif
if (!mp_opt->echo) {
mp_opt->ahmac = get_unaligned_be64(ptr);
ptr += 8;
}
pr_debug("ADD_ADDR%s: id=%d, ahmac=%llu, echo=%d, port=%d",
(mp_opt->family == MPTCP_ADDR_IPVERSION_6) ? "6" : "",
mp_opt->addr_id, mp_opt->ahmac, mp_opt->echo, mp_opt->port);
break;
case MPTCPOPT_RM_ADDR:
if (opsize != TCPOLEN_MPTCP_RM_ADDR_BASE)
break;
ptr++;
mp_opt->rm_addr = 1;
mp_opt->rm_id = *ptr++;
pr_debug("RM_ADDR: id=%d", mp_opt->rm_id);
break;
case MPTCPOPT_MP_PRIO:
if (opsize != TCPOLEN_MPTCP_PRIO)
break;
mp_opt->mp_prio = 1;
mp_opt->backup = *ptr++ & MPTCP_PRIO_BKUP;
pr_debug("MP_PRIO: prio=%d", mp_opt->backup);
break;
case MPTCPOPT_MP_FASTCLOSE:
if (opsize != TCPOLEN_MPTCP_FASTCLOSE)
break;
ptr += 2;
mp_opt->rcvr_key = get_unaligned_be64(ptr);
ptr += 8;
mp_opt->fastclose = 1;
break;
default:
break;
}
}
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)
{
const struct tcphdr *th = tcp_hdr(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
const unsigned char *ptr;
int length;
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
/* initialize option status */
mp_opt->mp_capable = 0;
mp_opt->mp_join = 0;
mp_opt->add_addr = 0;
mp_opt->ahmac = 0;
mp_opt->fastclose = 0;
mp_opt->port = 0;
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
mp_opt->rm_addr = 0;
mp_opt->dss = 0;
mp_opt->mp_prio = 0;
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
length = (th->doff * 4) - sizeof(struct tcphdr);
ptr = (const unsigned char *)(th + 1);
while (length > 0) {
int opcode = *ptr++;
int opsize;
switch (opcode) {
case TCPOPT_EOL:
return;
case TCPOPT_NOP: /* Ref: RFC 793 section 3.1 */
length--;
continue;
default:
opsize = *ptr++;
if (opsize < 2) /* "silly options" */
return;
if (opsize > length)
return; /* don't parse partial options */
if (opcode == TCPOPT_MPTCP)
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
mptcp_parse_option(skb, ptr, opsize, mp_opt);
ptr += opsize - 2;
length -= opsize;
}
}
}
bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb,
unsigned int *size, struct mptcp_out_options *opts)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
/* we will use snd_isn to detect first pkt [re]transmission
* in mptcp_established_options_mp()
*/
subflow->snd_isn = TCP_SKB_CB(skb)->end_seq;
if (subflow->request_mptcp) {
opts->suboptions = OPTION_MPTCP_MPC_SYN;
*size = TCPOLEN_MPTCP_MPC_SYN;
return true;
} else if (subflow->request_join) {
pr_debug("remote_token=%u, nonce=%u", subflow->remote_token,
subflow->local_nonce);
opts->suboptions = OPTION_MPTCP_MPJ_SYN;
opts->join_id = subflow->local_id;
opts->token = subflow->remote_token;
opts->nonce = subflow->local_nonce;
opts->backup = subflow->request_bkup;
*size = TCPOLEN_MPTCP_MPJ_SYN;
return true;
}
return false;
}
/* MP_JOIN client subflow must wait for 4th ack before sending any data:
* TCP can't schedule delack timer before the subflow is fully established.
* MPTCP uses the delack timer to do 3rd ack retransmissions
*/
static void schedule_3rdack_retransmission(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
unsigned long timeout;
/* reschedule with a timeout above RTT, as we must look only for drop */
if (tp->srtt_us)
timeout = tp->srtt_us << 1;
else
timeout = TCP_TIMEOUT_INIT;
WARN_ON_ONCE(icsk->icsk_ack.pending & ICSK_ACK_TIMER);
icsk->icsk_ack.pending |= ICSK_ACK_SCHED | ICSK_ACK_TIMER;
icsk->icsk_ack.timeout = timeout;
sk_reset_timer(sk, &icsk->icsk_delack_timer, timeout);
}
static void clear_3rdack_retransmission(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
sk_stop_timer(sk, &icsk->icsk_delack_timer);
icsk->icsk_ack.timeout = 0;
icsk->icsk_ack.ato = 0;
icsk->icsk_ack.pending &= ~(ICSK_ACK_SCHED | ICSK_ACK_TIMER);
}
static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb,
bool snd_data_fin_enable,
unsigned int *size,
unsigned int remaining,
struct mptcp_out_options *opts)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_ext *mpext;
unsigned int data_len;
/* When skb is not available, we better over-estimate the emitted
* options len. A full DSS option (28 bytes) is longer than
* TCPOLEN_MPTCP_MPC_ACK_DATA(22) or TCPOLEN_MPTCP_MPJ_ACK(24), so
* tell the caller to defer the estimate to
* mptcp_established_options_dss(), which will reserve enough space.
*/
if (!skb)
return false;
/* MPC/MPJ needed only on 3rd ack packet, DATA_FIN and TCP shutdown take precedence */
if (subflow->fully_established || snd_data_fin_enable ||
subflow->snd_isn != TCP_SKB_CB(skb)->seq ||
sk->sk_state != TCP_ESTABLISHED)
return false;
if (subflow->mp_capable) {
mpext = mptcp_get_ext(skb);
data_len = mpext ? mpext->data_len : 0;
/* we will check ext_copy.data_len in mptcp_write_options() to
* discriminate between TCPOLEN_MPTCP_MPC_ACK_DATA and
* TCPOLEN_MPTCP_MPC_ACK
*/
opts->ext_copy.data_len = data_len;
opts->suboptions = OPTION_MPTCP_MPC_ACK;
opts->sndr_key = subflow->local_key;
opts->rcvr_key = subflow->remote_key;
/* Section 3.1.
* The MP_CAPABLE option is carried on the SYN, SYN/ACK, and ACK
* packets that start the first subflow of an MPTCP connection,
* as well as the first packet that carries data
*/
if (data_len > 0)
*size = ALIGN(TCPOLEN_MPTCP_MPC_ACK_DATA, 4);
else
*size = TCPOLEN_MPTCP_MPC_ACK;
pr_debug("subflow=%p, local_key=%llu, remote_key=%llu map_len=%d",
subflow, subflow->local_key, subflow->remote_key,
data_len);
return true;
} else if (subflow->mp_join) {
opts->suboptions = OPTION_MPTCP_MPJ_ACK;
memcpy(opts->hmac, subflow->hmac, MPTCPOPT_HMAC_LEN);
*size = TCPOLEN_MPTCP_MPJ_ACK;
pr_debug("subflow=%p", subflow);
schedule_3rdack_retransmission(sk);
return true;
}
return false;
}
static void mptcp_write_data_fin(struct mptcp_subflow_context *subflow,
struct sk_buff *skb, struct mptcp_ext *ext)
{
/* The write_seq value has already been incremented, so the actual
* sequence number for the DATA_FIN is one less.
*/
u64 data_fin_tx_seq = READ_ONCE(mptcp_sk(subflow->conn)->write_seq) - 1;
if (!ext->use_map || !skb->len) {
/* RFC6824 requires a DSS mapping with specific values
* if DATA_FIN is set but no data payload is mapped
*/
ext->data_fin = 1;
ext->use_map = 1;
ext->dsn64 = 1;
ext->data_seq = data_fin_tx_seq;
ext->subflow_seq = 0;
ext->data_len = 1;
} else if (ext->data_seq + ext->data_len == data_fin_tx_seq) {
/* If there's an existing DSS mapping and it is the
* final mapping, DATA_FIN consumes 1 additional byte of
* mapping space.
*/
ext->data_fin = 1;
ext->data_len++;
}
}
static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
bool snd_data_fin_enable,
unsigned int *size,
unsigned int remaining,
struct mptcp_out_options *opts)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
unsigned int dss_size = 0;
struct mptcp_ext *mpext;
unsigned int ack_size;
bool ret = false;
u64 ack_seq;
mpext = skb ? mptcp_get_ext(skb) : NULL;
if (!skb || (mpext && mpext->use_map) || snd_data_fin_enable) {
unsigned int map_size;
map_size = TCPOLEN_MPTCP_DSS_BASE + TCPOLEN_MPTCP_DSS_MAP64;
remaining -= map_size;
dss_size = map_size;
if (mpext)
opts->ext_copy = *mpext;
if (skb && snd_data_fin_enable)
mptcp_write_data_fin(subflow, skb, &opts->ext_copy);
ret = true;
}
/* passive sockets msk will set the 'can_ack' after accept(), even
* if the first subflow may have the already the remote key handy
*/
opts->ext_copy.use_ack = 0;
if (!READ_ONCE(msk->can_ack)) {
*size = ALIGN(dss_size, 4);
return ret;
}
ack_seq = READ_ONCE(msk->ack_seq);
if (READ_ONCE(msk->use_64bit_ack)) {
ack_size = TCPOLEN_MPTCP_DSS_ACK64;
opts->ext_copy.data_ack = ack_seq;
opts->ext_copy.ack64 = 1;
} else {
ack_size = TCPOLEN_MPTCP_DSS_ACK32;
opts->ext_copy.data_ack32 = (uint32_t)ack_seq;
opts->ext_copy.ack64 = 0;
}
opts->ext_copy.use_ack = 1;
WRITE_ONCE(msk->old_wspace, __mptcp_space((struct sock *)msk));
/* Add kind/length/subtype/flag overhead if mapping is not populated */
if (dss_size == 0)
ack_size += TCPOLEN_MPTCP_DSS_BASE;
dss_size += ack_size;
*size = ALIGN(dss_size, 4);
return true;
}
static u64 add_addr_generate_hmac(u64 key1, u64 key2, u8 addr_id,
struct in_addr *addr)
{
u8 hmac[SHA256_DIGEST_SIZE];
u8 msg[7];
msg[0] = addr_id;
memcpy(&msg[1], &addr->s_addr, 4);
msg[5] = 0;
msg[6] = 0;
mptcp_crypto_hmac_sha(key1, key2, msg, 7, hmac);
return get_unaligned_be64(&hmac[SHA256_DIGEST_SIZE - sizeof(u64)]);
}
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
static u64 add_addr6_generate_hmac(u64 key1, u64 key2, u8 addr_id,
struct in6_addr *addr)
{
u8 hmac[SHA256_DIGEST_SIZE];
u8 msg[19];
msg[0] = addr_id;
memcpy(&msg[1], &addr->s6_addr, 16);
msg[17] = 0;
msg[18] = 0;
mptcp_crypto_hmac_sha(key1, key2, msg, 19, hmac);
return get_unaligned_be64(&hmac[SHA256_DIGEST_SIZE - sizeof(u64)]);
}
#endif
static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *skb,
unsigned int *size,
unsigned int remaining,
struct mptcp_out_options *opts)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
bool drop_other_suboptions = false;
unsigned int opt_size = *size;
struct mptcp_addr_info saddr;
bool echo;
bool port;
int len;
if ((mptcp_pm_should_add_signal_ipv6(msk) ||
mptcp_pm_should_add_signal_port(msk)) &&
skb && skb_is_tcp_pure_ack(skb)) {
pr_debug("drop other suboptions");
opts->suboptions = 0;
mptcp: clear use_ack and use_map when dropping other suboptions This patch cleared use_ack and use_map when dropping other suboptions to fix the following syzkaller BUG: [ 15.223006] BUG: unable to handle page fault for address: 0000000000223b10 [ 15.223700] #PF: supervisor read access in kernel mode [ 15.224209] #PF: error_code(0x0000) - not-present page [ 15.224724] PGD b8d5067 P4D b8d5067 PUD c0a5067 PMD 0 [ 15.225237] Oops: 0000 [#1] SMP [ 15.225556] CPU: 0 PID: 7747 Comm: syz-executor Not tainted 5.10.0-rc6+ #24 [ 15.226281] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014 [ 15.227292] RIP: 0010:skb_release_data+0x89/0x1e0 [ 15.227816] Code: 5b 5d 41 5c 41 5d 41 5e 41 5f e9 02 06 8a ff e8 fd 05 8a ff 45 31 ed 80 7d 02 00 4c 8d 65 30 74 55 e8 eb 05 8a ff 49 8b 1c 24 <4c> 8b 7b 08 41 f6 c7 01 0f 85 18 01 00 00 e8 d4 05 8a ff 8b 43 34 [ 15.229669] RSP: 0018:ffffc900019c7c08 EFLAGS: 00010293 [ 15.230188] RAX: ffff88800daad900 RBX: 0000000000223b08 RCX: 0000000000000006 [ 15.230895] RDX: 0000000000000000 RSI: ffffffff818e06c5 RDI: ffff88807f6dc700 [ 15.231593] RBP: ffff88807f71a4c0 R08: 0000000000000001 R09: 0000000000000001 [ 15.232299] R10: ffffc900019c7c18 R11: 0000000000000000 R12: ffff88807f71a4f0 [ 15.233007] R13: 0000000000000000 R14: ffff88807f6dc700 R15: 0000000000000002 [ 15.233714] FS: 00007f65d9b5f700(0000) GS:ffff88807c400000(0000) knlGS:0000000000000000 [ 15.234509] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 15.235081] CR2: 0000000000223b10 CR3: 000000000b883000 CR4: 00000000000006f0 [ 15.235788] Call Trace: [ 15.236042] skb_release_all+0x28/0x30 [ 15.236419] __kfree_skb+0x11/0x20 [ 15.236768] tcp_data_queue+0x270/0x1240 [ 15.237161] ? tcp_urg+0x50/0x2a0 [ 15.237496] tcp_rcv_established+0x39a/0x890 [ 15.237997] ? mark_held_locks+0x49/0x70 [ 15.238467] tcp_v4_do_rcv+0xb9/0x270 [ 15.238915] __release_sock+0x8a/0x160 [ 15.239365] release_sock+0x32/0xd0 [ 15.239793] __inet_stream_connect+0x1d2/0x400 [ 15.240313] ? do_wait_intr_irq+0x80/0x80 [ 15.240791] inet_stream_connect+0x36/0x50 [ 15.241275] mptcp_stream_connect+0x69/0x1b0 [ 15.241787] __sys_connect+0x122/0x140 [ 15.242236] ? syscall_enter_from_user_mode+0x17/0x50 [ 15.242836] ? lockdep_hardirqs_on_prepare+0xd4/0x170 [ 15.243436] __x64_sys_connect+0x1a/0x20 [ 15.243924] do_syscall_64+0x33/0x40 [ 15.244313] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 15.244821] RIP: 0033:0x7f65d946e469 [ 15.245183] 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 [ 15.247019] RSP: 002b:00007f65d9b5eda8 EFLAGS: 00000246 ORIG_RAX: 000000000000002a [ 15.247770] RAX: ffffffffffffffda RBX: 000000000049bf00 RCX: 00007f65d946e469 [ 15.248471] RDX: 0000000000000010 RSI: 00000000200000c0 RDI: 0000000000000005 [ 15.249205] RBP: 000000000049bf00 R08: 0000000000000000 R09: 0000000000000000 [ 15.249908] R10: 0000000000000000 R11: 0000000000000246 R12: 000000000049bf0c [ 15.250603] R13: 00007fffe8a25cef R14: 00007f65d9b3f000 R15: 0000000000000003 [ 15.251312] Modules linked in: [ 15.251626] CR2: 0000000000223b10 [ 15.251965] BUG: kernel NULL pointer dereference, address: 0000000000000048 [ 15.252005] ---[ end trace f5c51fe19123c773 ]--- [ 15.252822] #PF: supervisor read access in kernel mode [ 15.252823] #PF: error_code(0x0000) - not-present page [ 15.252825] PGD c6c6067 P4D c6c6067 PUD c0d8067 [ 15.253294] RIP: 0010:skb_release_data+0x89/0x1e0 [ 15.253910] PMD 0 [ 15.253914] Oops: 0000 [#2] SMP [ 15.253917] CPU: 1 PID: 7746 Comm: syz-executor Tainted: G D 5.10.0-rc6+ #24 [ 15.253920] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014 [ 15.254435] Code: 5b 5d 41 5c 41 5d 41 5e 41 5f e9 02 06 8a ff e8 fd 05 8a ff 45 31 ed 80 7d 02 00 4c 8d 65 30 74 55 e8 eb 05 8a ff 49 8b 1c 24 <4c> 8b 7b 08 41 f6 c7 01 0f 85 18 01 00 00 e8 d4 05 8a ff 8b 43 34 [ 15.254899] RIP: 0010:skb_release_data+0x89/0x1e0 [ 15.254902] Code: 5b 5d 41 5c 41 5d 41 5e 41 5f e9 02 06 8a ff e8 fd 05 8a ff 45 31 ed 80 7d 02 00 4c 8d 65 30 74 55 e8 eb 05 8a ff 49 8b 1c 24 <4c> 8b 7b 08 41 f6 c7 01 0f 85 18 01 00 00 e8 d4 05 8a ff 8b 43 34 [ 15.254905] RSP: 0018:ffffc900019bfc08 EFLAGS: 00010293 [ 15.255376] RSP: 0018:ffffc900019c7c08 EFLAGS: 00010293 [ 15.255580] [ 15.255583] RAX: ffff888004a7ac80 RBX: 0000000000000040 RCX: 0000000000000000 [ 15.255912] [ 15.256724] RDX: 0000000000000000 RSI: ffffffff818e06c5 RDI: ffff88807f6ddd00 [ 15.257620] RAX: ffff88800daad900 RBX: 0000000000223b08 RCX: 0000000000000006 [ 15.259817] RBP: ffff88800e9006c0 R08: 0000000000000000 R09: 0000000000000000 [ 15.259818] R10: 0000000000000000 R11: 0000000000000000 R12: ffff88800e9006f0 [ 15.259820] R13: 0000000000000000 R14: ffff88807f6ddd00 R15: 0000000000000002 [ 15.259822] FS: 00007fae4a60a700(0000) GS:ffff88807c500000(0000) knlGS:0000000000000000 [ 15.259826] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 15.260296] RDX: 0000000000000000 RSI: ffffffff818e06c5 RDI: ffff88807f6dc700 [ 15.262514] CR2: 0000000000000048 CR3: 000000000b89c000 CR4: 00000000000006e0 [ 15.262515] Call Trace: [ 15.262519] skb_release_all+0x28/0x30 [ 15.262523] __kfree_skb+0x11/0x20 [ 15.263054] RBP: ffff88807f71a4c0 R08: 0000000000000001 R09: 0000000000000001 [ 15.263680] tcp_data_queue+0x270/0x1240 [ 15.263843] R10: ffffc900019c7c18 R11: 0000000000000000 R12: ffff88807f71a4f0 [ 15.264693] ? tcp_urg+0x50/0x2a0 [ 15.264856] R13: 0000000000000000 R14: ffff88807f6dc700 R15: 0000000000000002 [ 15.265720] tcp_rcv_established+0x39a/0x890 [ 15.266438] FS: 00007f65d9b5f700(0000) GS:ffff88807c400000(0000) knlGS:0000000000000000 [ 15.267283] ? __schedule+0x3fa/0x880 [ 15.267287] tcp_v4_do_rcv+0xb9/0x270 [ 15.267290] __release_sock+0x8a/0x160 [ 15.268049] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 15.268788] release_sock+0x32/0xd0 [ 15.268791] __inet_stream_connect+0x1d2/0x400 [ 15.268795] ? do_wait_intr_irq+0x80/0x80 [ 15.269593] CR2: 0000000000223b10 CR3: 000000000b883000 CR4: 00000000000006f0 [ 15.270246] inet_stream_connect+0x36/0x50 [ 15.270250] mptcp_stream_connect+0x69/0x1b0 [ 15.270253] __sys_connect+0x122/0x140 [ 15.271097] Kernel panic - not syncing: Fatal exception [ 15.271820] ? syscall_enter_from_user_mode+0x17/0x50 [ 15.283542] ? lockdep_hardirqs_on_prepare+0xd4/0x170 [ 15.284275] __x64_sys_connect+0x1a/0x20 [ 15.284853] do_syscall_64+0x33/0x40 [ 15.285369] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 15.286105] RIP: 0033:0x7fae49f19469 [ 15.286638] 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 [ 15.289295] RSP: 002b:00007fae4a609da8 EFLAGS: 00000246 ORIG_RAX: 000000000000002a [ 15.290375] RAX: ffffffffffffffda RBX: 000000000049bf00 RCX: 00007fae49f19469 [ 15.291403] RDX: 0000000000000010 RSI: 00000000200000c0 RDI: 0000000000000005 [ 15.292437] RBP: 000000000049bf00 R08: 0000000000000000 R09: 0000000000000000 [ 15.293456] R10: 0000000000000000 R11: 0000000000000246 R12: 000000000049bf0c [ 15.294473] R13: 00007fff0004b6bf R14: 00007fae4a5ea000 R15: 0000000000000003 [ 15.295492] Modules linked in: [ 15.295944] CR2: 0000000000000048 [ 15.296567] Kernel Offset: disabled [ 15.296941] ---[ end Kernel panic - not syncing: Fatal exception ]--- Reported-by: Christoph Paasch <cpaasch@apple.com> Fixes: 84dfe3677a6f (mptcp: send out dedicated ADD_ADDR packet) Signed-off-by: Geliang Tang <geliangtang@gmail.com> Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com> Link: https://lore.kernel.org/r/ccca4e8f01457a1b495c5d612ed16c5f7a585706.1608010058.git.geliangtang@gmail.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-12-15 17:56:51 +08:00
opts->ext_copy.use_ack = 0;
opts->ext_copy.use_map = 0;
remaining += opt_size;
drop_other_suboptions = true;
}
if (!mptcp_pm_should_add_signal(msk) ||
!(mptcp_pm_add_addr_signal(msk, remaining, &saddr, &echo, &port)))
return false;
len = mptcp_add_addr_len(saddr.family, echo, port);
if (remaining < len)
return false;
*size = len;
if (drop_other_suboptions)
*size -= opt_size;
opts->addr_id = saddr.id;
if (port)
opts->port = ntohs(saddr.port);
if (saddr.family == AF_INET) {
opts->suboptions |= OPTION_MPTCP_ADD_ADDR;
opts->addr = saddr.addr;
if (!echo) {
opts->ahmac = add_addr_generate_hmac(msk->local_key,
msk->remote_key,
opts->addr_id,
&opts->addr);
}
}
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
else if (saddr.family == AF_INET6) {
opts->suboptions |= OPTION_MPTCP_ADD_ADDR6;
opts->addr6 = saddr.addr6;
if (!echo) {
opts->ahmac = add_addr6_generate_hmac(msk->local_key,
msk->remote_key,
opts->addr_id,
&opts->addr6);
}
}
#endif
pr_debug("addr_id=%d, ahmac=%llu, echo=%d, port=%d",
opts->addr_id, opts->ahmac, echo, opts->port);
return true;
}
static bool mptcp_established_options_rm_addr(struct sock *sk,
unsigned int *size,
unsigned int remaining,
struct mptcp_out_options *opts)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
struct mptcp_rm_list rm_list;
int i, len;
if (!mptcp_pm_should_rm_signal(msk) ||
!(mptcp_pm_rm_addr_signal(msk, remaining, &rm_list)))
return false;
len = mptcp_rm_addr_len(&rm_list);
if (len < 0)
return false;
if (remaining < len)
return false;
*size = len;
opts->suboptions |= OPTION_MPTCP_RM_ADDR;
opts->rm_list = rm_list;
for (i = 0; i < opts->rm_list.nr; i++)
pr_debug("rm_list_ids[%d]=%d", i, opts->rm_list.ids[i]);
return true;
}
static bool mptcp_established_options_mp_prio(struct sock *sk,
unsigned int *size,
unsigned int remaining,
struct mptcp_out_options *opts)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
if (!subflow->send_mp_prio)
return false;
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
/* account for the trailing 'nop' option */
if (remaining < TCPOLEN_MPTCP_PRIO_ALIGN)
return false;
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
*size = TCPOLEN_MPTCP_PRIO_ALIGN;
opts->suboptions |= OPTION_MPTCP_PRIO;
opts->backup = subflow->request_bkup;
pr_debug("prio=%d", opts->backup);
return true;
}
bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
unsigned int *size, unsigned int remaining,
struct mptcp_out_options *opts)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
unsigned int opt_size = 0;
bool snd_data_fin;
bool ret = false;
opts->suboptions = 0;
if (unlikely(__mptcp_check_fallback(msk)))
return false;
/* prevent adding of any MPTCP related options on reset packet
* until we support MP_TCPRST/MP_FASTCLOSE
*/
if (unlikely(skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST))
return false;
snd_data_fin = mptcp_data_fin_enabled(msk);
if (mptcp_established_options_mp(sk, skb, snd_data_fin, &opt_size, remaining, opts))
ret = true;
else if (mptcp_established_options_dss(sk, skb, snd_data_fin, &opt_size, remaining, opts))
ret = true;
/* we reserved enough space for the above options, and exceeding the
* TCP option space would be fatal
*/
if (WARN_ON_ONCE(opt_size > remaining))
return false;
*size += opt_size;
remaining -= opt_size;
if (mptcp_established_options_add_addr(sk, skb, &opt_size, remaining, opts)) {
*size += opt_size;
remaining -= opt_size;
ret = true;
} else if (mptcp_established_options_rm_addr(sk, &opt_size, remaining, opts)) {
*size += opt_size;
remaining -= opt_size;
ret = true;
}
if (mptcp_established_options_mp_prio(sk, &opt_size, remaining, opts)) {
*size += opt_size;
remaining -= opt_size;
ret = true;
}
return ret;
}
bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
struct mptcp_out_options *opts)
{
struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
if (subflow_req->mp_capable) {
opts->suboptions = OPTION_MPTCP_MPC_SYNACK;
opts->sndr_key = subflow_req->local_key;
*size = TCPOLEN_MPTCP_MPC_SYNACK;
pr_debug("subflow_req=%p, local_key=%llu",
subflow_req, subflow_req->local_key);
return true;
} else if (subflow_req->mp_join) {
opts->suboptions = OPTION_MPTCP_MPJ_SYNACK;
opts->backup = subflow_req->backup;
opts->join_id = subflow_req->local_id;
opts->thmac = subflow_req->thmac;
opts->nonce = subflow_req->local_nonce;
pr_debug("req=%p, bkup=%u, id=%u, thmac=%llu, nonce=%u",
subflow_req, opts->backup, opts->join_id,
opts->thmac, opts->nonce);
*size = TCPOLEN_MPTCP_MPJ_SYNACK;
return true;
}
return false;
}
static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
struct mptcp_subflow_context *subflow,
struct sk_buff *skb,
struct mptcp_options_received *mp_opt)
{
/* here we can process OoO, in-window pkts, only in-sequence 4th ack
* will make the subflow fully established
*/
if (likely(subflow->fully_established)) {
/* on passive sockets, check for 3rd ack retransmission
* note that msk is always set by subflow_syn_recv_sock()
* for mp_join subflows
*/
if (TCP_SKB_CB(skb)->seq == subflow->ssn_offset + 1 &&
TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq &&
subflow->mp_join && mp_opt->mp_join &&
READ_ONCE(msk->pm.server_side))
tcp_send_ack(ssk);
goto fully_established;
}
/* we must process OoO packets before the first subflow is fully
* established. OoO packets are instead a protocol violation
* for MP_JOIN subflows as the peer must not send any data
* before receiving the forth ack - cfr. RFC 8684 section 3.2.
*/
if (TCP_SKB_CB(skb)->seq != subflow->ssn_offset + 1) {
if (subflow->mp_join)
goto reset;
return subflow->mp_capable;
}
if (mp_opt->dss && mp_opt->use_ack) {
/* subflows are fully established as soon as we get any
* additional ack.
*/
subflow->fully_established = 1;
WRITE_ONCE(msk->fully_established, true);
goto fully_established;
}
if (mp_opt->add_addr) {
WRITE_ONCE(msk->fully_established, true);
return true;
}
/* If the first established packet does not contain MP_CAPABLE + data
* then fallback to TCP. Fallback scenarios requires a reset for
* MP_JOIN subflows.
*/
if (!mp_opt->mp_capable) {
if (subflow->mp_join)
goto reset;
subflow->mp_capable = 0;
pr_fallback(msk);
__mptcp_do_fallback(msk);
return false;
}
if (unlikely(!READ_ONCE(msk->pm.server_side)))
pr_warn_once("bogus mpc option on established client sk");
mptcp_subflow_fully_established(subflow, mp_opt);
fully_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
/* if the subflow is not already linked into the conn_list, we can't
* notify the PM: this subflow is still on the listener queue
* and the PM possibly acquiring the subflow lock could race with
* the listener close
*/
if (likely(subflow->pm_notified) || list_empty(&subflow->node))
return true;
subflow->pm_notified = 1;
if (subflow->mp_join) {
clear_3rdack_retransmission(ssk);
mptcp_pm_subflow_established(msk, subflow);
} else {
mptcp_pm_fully_established(msk, ssk, GFP_ATOMIC);
}
return true;
reset:
mptcp_subflow_reset(ssk);
return false;
}
static u64 expand_ack(u64 old_ack, u64 cur_ack, bool use_64bit)
{
u32 old_ack32, cur_ack32;
if (use_64bit)
return cur_ack;
old_ack32 = (u32)old_ack;
cur_ack32 = (u32)cur_ack;
cur_ack = (old_ack & GENMASK_ULL(63, 32)) + cur_ack32;
if (unlikely(before(cur_ack32, old_ack32)))
return cur_ack + (1LL << 32);
return cur_ack;
}
static void ack_update_msk(struct mptcp_sock *msk,
struct sock *ssk,
struct mptcp_options_received *mp_opt)
{
u64 new_wnd_end, new_snd_una, snd_nxt = READ_ONCE(msk->snd_nxt);
struct sock *sk = (struct sock *)msk;
u64 old_snd_una;
mptcp_data_lock(sk);
/* avoid ack expansion on update conflict, to reduce the risk of
* wrongly expanding to a future ack sequence number, which is way
* more dangerous than missing an ack
*/
old_snd_una = msk->snd_una;
new_snd_una = expand_ack(old_snd_una, mp_opt->data_ack, mp_opt->ack64);
/* ACK for data not even sent yet? Ignore. */
if (after64(new_snd_una, snd_nxt))
new_snd_una = old_snd_una;
new_wnd_end = new_snd_una + tcp_sk(ssk)->snd_wnd;
if (after64(new_wnd_end, msk->wnd_end))
msk->wnd_end = new_wnd_end;
/* this assumes mptcp_incoming_options() is invoked after tcp_ack() */
if (after64(msk->wnd_end, READ_ONCE(msk->snd_nxt)))
__mptcp_check_push(sk, ssk);
if (after64(new_snd_una, old_snd_una)) {
msk->snd_una = new_snd_una;
__mptcp_data_acked(sk);
}
mptcp_data_unlock(sk);
}
bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool use_64bit)
{
/* Skip if DATA_FIN was already received.
* If updating simultaneously with the recvmsg loop, values
* should match. If they mismatch, the peer is misbehaving and
* we will prefer the most recent information.
*/
if (READ_ONCE(msk->rcv_data_fin) || !READ_ONCE(msk->first))
return false;
WRITE_ONCE(msk->rcv_data_fin_seq,
expand_ack(READ_ONCE(msk->ack_seq), data_fin_seq, use_64bit));
WRITE_ONCE(msk->rcv_data_fin, 1);
return true;
}
static bool add_addr_hmac_valid(struct mptcp_sock *msk,
struct mptcp_options_received *mp_opt)
{
u64 hmac = 0;
if (mp_opt->echo)
return true;
if (mp_opt->family == MPTCP_ADDR_IPVERSION_4)
hmac = add_addr_generate_hmac(msk->remote_key,
msk->local_key,
mp_opt->addr_id, &mp_opt->addr);
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
else
hmac = add_addr6_generate_hmac(msk->remote_key,
msk->local_key,
mp_opt->addr_id, &mp_opt->addr6);
#endif
pr_debug("msk=%p, ahmac=%llu, mp_opt->ahmac=%llu\n",
msk, (unsigned long long)hmac,
(unsigned long long)mp_opt->ahmac);
return hmac == mp_opt->ahmac;
}
void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
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;
struct mptcp_ext *mpext;
if (__mptcp_check_fallback(msk)) {
/* Keep it simple and unconditionally trigger send data cleanup and
* pending queue spooling. We will need to acquire the data lock
* for more accurate checks, and once the lock is acquired, such
* helpers are cheap.
*/
mptcp_data_lock(subflow->conn);
if (sk_stream_memory_free(sk))
__mptcp_check_push(subflow->conn, sk);
__mptcp_data_acked(subflow->conn);
mptcp_data_unlock(subflow->conn);
return;
}
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
mptcp_get_options(skb, &mp_opt);
if (!check_fully_established(msk, sk, subflow, skb, &mp_opt))
return;
if (mp_opt.fastclose &&
msk->local_key == mp_opt.rcvr_key) {
WRITE_ONCE(msk->rcv_fastclose, true);
mptcp_schedule_work((struct sock *)msk);
}
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
if (mp_opt.add_addr && add_addr_hmac_valid(msk, &mp_opt)) {
struct mptcp_addr_info addr;
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
addr.port = htons(mp_opt.port);
addr.id = mp_opt.addr_id;
if (mp_opt.family == MPTCP_ADDR_IPVERSION_4) {
addr.family = AF_INET;
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
addr.addr = mp_opt.addr;
}
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
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
else if (mp_opt.family == MPTCP_ADDR_IPVERSION_6) {
addr.family = AF_INET6;
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
addr.addr6 = mp_opt.addr6;
}
#endif
if (!mp_opt.echo) {
mptcp_pm_add_addr_received(msk, &addr);
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ADDADDR);
} else {
mptcp_pm_del_add_timer(msk, &addr);
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADD);
}
if (mp_opt.port)
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_PORTADD);
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
mp_opt.add_addr = 0;
}
if (mp_opt.rm_addr) {
mptcp_pm_rm_addr_received(msk, mp_opt.rm_id);
mp_opt.rm_addr = 0;
}
if (mp_opt.mp_prio) {
mptcp_pm_mp_prio_received(sk, mp_opt.backup);
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPPRIORX);
mp_opt.mp_prio = 0;
}
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
if (!mp_opt.dss)
return;
/* we can't wait for recvmsg() to update the ack_seq, otherwise
* monodirectional flows will stuck
*/
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
if (mp_opt.use_ack)
ack_update_msk(msk, sk, &mp_opt);
/* Zero-data-length packets are dropped by the caller and not
* propagated to the MPTCP layer, so the skb extension does not
* need to be allocated or populated. DATA_FIN information, if
* present, needs to be updated here before the skb is freed.
*/
if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) {
if (mp_opt.data_fin && mp_opt.data_len == 1 &&
mptcp_update_rcv_data_fin(msk, mp_opt.data_seq, mp_opt.dsn64) &&
schedule_work(&msk->work))
sock_hold(subflow->conn);
return;
}
mpext = skb_ext_add(skb, SKB_EXT_MPTCP);
if (!mpext)
return;
memset(mpext, 0, sizeof(*mpext));
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
if (mp_opt.use_map) {
if (mp_opt.mpc_map) {
/* this is an MP_CAPABLE carrying MPTCP data
* we know this map the first chunk of data
*/
mptcp_crypto_key_sha(subflow->remote_key, NULL,
&mpext->data_seq);
mpext->data_seq++;
mpext->subflow_seq = 1;
mpext->dsn64 = 1;
mpext->mpc_map = 1;
mpext->data_fin = 0;
} else {
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
mpext->data_seq = mp_opt.data_seq;
mpext->subflow_seq = mp_opt.subflow_seq;
mpext->dsn64 = mp_opt.dsn64;
mpext->data_fin = mp_opt.data_fin;
}
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
mpext->data_len = mp_opt.data_len;
mpext->use_map = 1;
}
}
static void mptcp_set_rwin(const struct tcp_sock *tp)
{
const struct sock *ssk = (const struct sock *)tp;
const struct mptcp_subflow_context *subflow;
struct mptcp_sock *msk;
u64 ack_seq;
subflow = mptcp_subflow_ctx(ssk);
msk = mptcp_sk(subflow->conn);
ack_seq = READ_ONCE(msk->ack_seq) + tp->rcv_wnd;
if (after64(ack_seq, READ_ONCE(msk->rcv_wnd_sent)))
WRITE_ONCE(msk->rcv_wnd_sent, ack_seq);
}
void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
struct mptcp_out_options *opts)
{
if ((OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK |
OPTION_MPTCP_MPC_ACK) & opts->suboptions) {
u8 len;
if (OPTION_MPTCP_MPC_SYN & opts->suboptions)
len = TCPOLEN_MPTCP_MPC_SYN;
else if (OPTION_MPTCP_MPC_SYNACK & opts->suboptions)
len = TCPOLEN_MPTCP_MPC_SYNACK;
else if (opts->ext_copy.data_len)
len = TCPOLEN_MPTCP_MPC_ACK_DATA;
else
len = TCPOLEN_MPTCP_MPC_ACK;
*ptr++ = mptcp_option(MPTCPOPT_MP_CAPABLE, len,
MPTCP_SUPPORTED_VERSION,
MPTCP_CAP_HMAC_SHA256);
if (!((OPTION_MPTCP_MPC_SYNACK | OPTION_MPTCP_MPC_ACK) &
opts->suboptions))
goto mp_capable_done;
put_unaligned_be64(opts->sndr_key, ptr);
ptr += 2;
if (!((OPTION_MPTCP_MPC_ACK) & opts->suboptions))
goto mp_capable_done;
put_unaligned_be64(opts->rcvr_key, ptr);
ptr += 2;
if (!opts->ext_copy.data_len)
goto mp_capable_done;
put_unaligned_be32(opts->ext_copy.data_len << 16 |
TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
ptr += 1;
}
mp_capable_done:
if ((OPTION_MPTCP_ADD_ADDR
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
| OPTION_MPTCP_ADD_ADDR6
#endif
) & opts->suboptions) {
u8 len = TCPOLEN_MPTCP_ADD_ADDR_BASE;
u8 echo = MPTCP_ADDR_ECHO;
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
if (OPTION_MPTCP_ADD_ADDR6 & opts->suboptions)
len = TCPOLEN_MPTCP_ADD_ADDR6_BASE;
#endif
if (opts->port)
len += TCPOLEN_MPTCP_PORT_LEN;
if (opts->ahmac) {
len += sizeof(opts->ahmac);
echo = 0;
}
*ptr++ = mptcp_option(MPTCPOPT_ADD_ADDR,
len, echo, opts->addr_id);
if (OPTION_MPTCP_ADD_ADDR & opts->suboptions) {
memcpy((u8 *)ptr, (u8 *)&opts->addr.s_addr, 4);
ptr += 1;
}
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
else if (OPTION_MPTCP_ADD_ADDR6 & opts->suboptions) {
memcpy((u8 *)ptr, opts->addr6.s6_addr, 16);
ptr += 4;
}
#endif
if (!opts->port) {
if (opts->ahmac) {
put_unaligned_be64(opts->ahmac, ptr);
ptr += 2;
}
} else {
if (opts->ahmac) {
u8 *bptr = (u8 *)ptr;
put_unaligned_be16(opts->port, bptr);
bptr += 2;
put_unaligned_be64(opts->ahmac, bptr);
bptr += 8;
put_unaligned_be16(TCPOPT_NOP << 8 |
TCPOPT_NOP, bptr);
ptr += 3;
} else {
put_unaligned_be32(opts->port << 16 |
TCPOPT_NOP << 8 |
TCPOPT_NOP, ptr);
ptr += 1;
}
}
}
if (OPTION_MPTCP_RM_ADDR & opts->suboptions) {
u8 i = 1;
*ptr++ = mptcp_option(MPTCPOPT_RM_ADDR,
TCPOLEN_MPTCP_RM_ADDR_BASE + opts->rm_list.nr,
0, opts->rm_list.ids[0]);
while (i < opts->rm_list.nr) {
u8 id1, id2, id3, id4;
id1 = opts->rm_list.ids[i];
id2 = i + 1 < opts->rm_list.nr ? opts->rm_list.ids[i + 1] : TCPOPT_NOP;
id3 = i + 2 < opts->rm_list.nr ? opts->rm_list.ids[i + 2] : TCPOPT_NOP;
id4 = i + 3 < opts->rm_list.nr ? opts->rm_list.ids[i + 3] : TCPOPT_NOP;
put_unaligned_be32(id1 << 24 | id2 << 16 | id3 << 8 | id4, ptr);
ptr += 1;
i += 4;
}
}
if (OPTION_MPTCP_PRIO & opts->suboptions) {
const struct sock *ssk = (const struct sock *)tp;
struct mptcp_subflow_context *subflow;
subflow = mptcp_subflow_ctx(ssk);
subflow->send_mp_prio = 0;
*ptr++ = mptcp_option(MPTCPOPT_MP_PRIO,
TCPOLEN_MPTCP_PRIO,
opts->backup, TCPOPT_NOP);
}
if (OPTION_MPTCP_MPJ_SYN & opts->suboptions) {
*ptr++ = mptcp_option(MPTCPOPT_MP_JOIN,
TCPOLEN_MPTCP_MPJ_SYN,
opts->backup, opts->join_id);
put_unaligned_be32(opts->token, ptr);
ptr += 1;
put_unaligned_be32(opts->nonce, ptr);
ptr += 1;
}
if (OPTION_MPTCP_MPJ_SYNACK & opts->suboptions) {
*ptr++ = mptcp_option(MPTCPOPT_MP_JOIN,
TCPOLEN_MPTCP_MPJ_SYNACK,
opts->backup, opts->join_id);
put_unaligned_be64(opts->thmac, ptr);
ptr += 2;
put_unaligned_be32(opts->nonce, ptr);
ptr += 1;
}
if (OPTION_MPTCP_MPJ_ACK & opts->suboptions) {
*ptr++ = mptcp_option(MPTCPOPT_MP_JOIN,
TCPOLEN_MPTCP_MPJ_ACK, 0, 0);
memcpy(ptr, opts->hmac, MPTCPOPT_HMAC_LEN);
ptr += 5;
}
if (opts->ext_copy.use_ack || opts->ext_copy.use_map) {
struct mptcp_ext *mpext = &opts->ext_copy;
u8 len = TCPOLEN_MPTCP_DSS_BASE;
u8 flags = 0;
if (mpext->use_ack) {
flags = MPTCP_DSS_HAS_ACK;
if (mpext->ack64) {
len += TCPOLEN_MPTCP_DSS_ACK64;
flags |= MPTCP_DSS_ACK64;
} else {
len += TCPOLEN_MPTCP_DSS_ACK32;
}
}
if (mpext->use_map) {
len += TCPOLEN_MPTCP_DSS_MAP64;
/* Use only 64-bit mapping flags for now, add
* support for optional 32-bit mappings later.
*/
flags |= MPTCP_DSS_HAS_MAP | MPTCP_DSS_DSN64;
if (mpext->data_fin)
flags |= MPTCP_DSS_DATA_FIN;
}
*ptr++ = mptcp_option(MPTCPOPT_DSS, len, 0, flags);
if (mpext->use_ack) {
if (mpext->ack64) {
put_unaligned_be64(mpext->data_ack, ptr);
ptr += 2;
} else {
put_unaligned_be32(mpext->data_ack32, ptr);
ptr += 1;
}
}
if (mpext->use_map) {
put_unaligned_be64(mpext->data_seq, ptr);
ptr += 2;
put_unaligned_be32(mpext->subflow_seq, ptr);
ptr += 1;
put_unaligned_be32(mpext->data_len << 16 |
TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
}
}
if (tp)
mptcp_set_rwin(tp);
}