OpenCloudOS-Kernel/net/mptcp/subflow.c

1824 lines
50 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 <linux/module.h>
#include <linux/netdevice.h>
#include <crypto/algapi.h>
#include <crypto/sha2.h>
#include <net/sock.h>
#include <net/inet_common.h>
#include <net/inet_hashtables.h>
#include <net/protocol.h>
#include <net/tcp.h>
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
#include <net/ip6_route.h>
#include <net/transp_v6.h>
#endif
#include <net/mptcp.h>
#include <uapi/linux/mptcp.h>
#include "protocol.h"
#include "mib.h"
#include <trace/events/mptcp.h>
static void mptcp_subflow_ops_undo_override(struct sock *ssk);
static void SUBFLOW_REQ_INC_STATS(struct request_sock *req,
enum linux_mptcp_mib_field field)
{
MPTCP_INC_STATS(sock_net(req_to_sk(req)), field);
}
static void subflow_req_destructor(struct request_sock *req)
{
struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
pr_debug("subflow_req=%p", subflow_req);
if (subflow_req->msk)
sock_put((struct sock *)subflow_req->msk);
mptcp_token_destroy_request(req);
tcp_request_sock_ops.destructor(req);
}
static void subflow_generate_hmac(u64 key1, u64 key2, u32 nonce1, u32 nonce2,
void *hmac)
{
u8 msg[8];
put_unaligned_be32(nonce1, &msg[0]);
put_unaligned_be32(nonce2, &msg[4]);
mptcp_crypto_hmac_sha(key1, key2, msg, 8, hmac);
}
static bool mptcp_can_accept_new_subflow(const struct mptcp_sock *msk)
{
return mptcp_is_fully_established((void *)msk) &&
READ_ONCE(msk->pm.accept_subflow);
}
/* validate received token and create truncated hmac and nonce for SYN-ACK */
static void subflow_req_create_thmac(struct mptcp_subflow_request_sock *subflow_req)
{
struct mptcp_sock *msk = subflow_req->msk;
u8 hmac[SHA256_DIGEST_SIZE];
get_random_bytes(&subflow_req->local_nonce, sizeof(u32));
subflow_generate_hmac(msk->local_key, msk->remote_key,
subflow_req->local_nonce,
subflow_req->remote_nonce, hmac);
subflow_req->thmac = get_unaligned_be64(hmac);
}
static struct mptcp_sock *subflow_token_join_request(struct request_sock *req)
{
struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
struct mptcp_sock *msk;
int local_id;
msk = mptcp_token_get_sock(sock_net(req_to_sk(req)), subflow_req->token);
if (!msk) {
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINNOTOKEN);
return NULL;
}
local_id = mptcp_pm_get_local_id(msk, (struct sock_common *)req);
if (local_id < 0) {
sock_put((struct sock *)msk);
return NULL;
}
subflow_req->local_id = local_id;
return msk;
}
static void subflow_init_req(struct request_sock *req, const struct sock *sk_listener)
{
struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
subflow_req->mp_capable = 0;
subflow_req->mp_join = 0;
subflow_req->csum_reqd = mptcp_is_checksum_enabled(sock_net(sk_listener));
subflow_req->allow_join_id0 = mptcp_allow_join_id0(sock_net(sk_listener));
subflow_req->msk = NULL;
mptcp_token_init_request(req);
}
static bool subflow_use_different_sport(struct mptcp_sock *msk, const struct sock *sk)
{
return inet_sk(sk)->inet_sport != inet_sk((struct sock *)msk)->inet_sport;
}
static void subflow_add_reset_reason(struct sk_buff *skb, u8 reason)
{
struct mptcp_ext *mpext = skb_ext_add(skb, SKB_EXT_MPTCP);
if (mpext) {
memset(mpext, 0, sizeof(*mpext));
mpext->reset_reason = reason;
}
}
/* Init mptcp request socket.
*
* Returns an error code if a JOIN has failed and a TCP reset
* should be sent.
*/
static int subflow_check_req(struct request_sock *req,
const struct sock *sk_listener,
struct sk_buff *skb)
{
struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk_listener);
struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
struct mptcp_options_received mp_opt;
bool opt_mp_capable, opt_mp_join;
pr_debug("subflow_req=%p, listener=%p", subflow_req, listener);
#ifdef CONFIG_TCP_MD5SIG
/* no MPTCP if MD5SIG is enabled on this socket or we may run out of
* TCP option space.
*/
if (rcu_access_pointer(tcp_sk(sk_listener)->md5sig_info))
return -EINVAL;
#endif
mptcp_get_options(sk_listener, skb, &mp_opt);
opt_mp_capable = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPC);
opt_mp_join = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ);
if (opt_mp_capable) {
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE);
if (opt_mp_join)
return 0;
} else if (opt_mp_join) {
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX);
}
if (opt_mp_capable && listener->request_mptcp) {
int err, retries = MPTCP_TOKEN_MAX_RETRIES;
subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq;
again:
do {
get_random_bytes(&subflow_req->local_key, sizeof(subflow_req->local_key));
} while (subflow_req->local_key == 0);
if (unlikely(req->syncookie)) {
mptcp_crypto_key_sha(subflow_req->local_key,
&subflow_req->token,
&subflow_req->idsn);
if (mptcp_token_exists(subflow_req->token)) {
if (retries-- > 0)
goto again;
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_TOKENFALLBACKINIT);
} else {
subflow_req->mp_capable = 1;
}
return 0;
}
err = mptcp_token_new_request(req);
if (err == 0)
subflow_req->mp_capable = 1;
else if (retries-- > 0)
goto again;
else
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_TOKENFALLBACKINIT);
} else if (opt_mp_join && listener->request_mptcp) {
subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq;
subflow_req->mp_join = 1;
mptcp: move option parsing into mptcp_incoming_options() The mptcp_options_received structure carries several per packet flags (mp_capable, mp_join, etc.). Such fields must be cleared on each packet, even on dropped ones or packet not carrying any MPTCP options, but the current mptcp code clears them only on TCP option reset. On several races/corner cases we end-up with stray bits in incoming options, leading to WARN_ON splats. e.g.: [ 171.164906] Bad mapping: ssn=32714 map_seq=1 map_data_len=32713 [ 171.165006] WARNING: CPU: 1 PID: 5026 at net/mptcp/subflow.c:533 warn_bad_map (linux-mptcp/net/mptcp/subflow.c:533 linux-mptcp/net/mptcp/subflow.c:531) [ 171.167632] Modules linked in: ip6_vti ip_vti ip_gre ipip sit tunnel4 ip_tunnel geneve ip6_udp_tunnel udp_tunnel macsec macvtap tap ipvlan macvlan 8021q garp mrp xfrm_interface veth netdevsim nlmon dummy team bonding vcan bridge stp llc ip6_gre gre ip6_tunnel tunnel6 tun binfmt_misc intel_rapl_msr intel_rapl_common rfkill kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel joydev virtio_balloon pcspkr i2c_piix4 sunrpc ip_tables xfs libcrc32c crc32c_intel serio_raw virtio_console ata_generic virtio_blk virtio_net net_failover failover ata_piix libata [ 171.199464] CPU: 1 PID: 5026 Comm: repro Not tainted 5.7.0-rc1.mptcp_f227fdf5d388+ #95 [ 171.200886] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-2.fc30 04/01/2014 [ 171.202546] RIP: 0010:warn_bad_map (linux-mptcp/net/mptcp/subflow.c:533 linux-mptcp/net/mptcp/subflow.c:531) [ 171.206537] Code: c1 ea 03 0f b6 14 02 48 89 f8 83 e0 07 83 c0 03 38 d0 7c 04 84 d2 75 1d 8b 55 3c 44 89 e6 48 c7 c7 20 51 13 95 e8 37 8b 22 fe <0f> 0b 48 83 c4 08 5b 5d 41 5c c3 89 4c 24 04 e8 db d6 94 fe 8b 4c [ 171.220473] RSP: 0018:ffffc90000150560 EFLAGS: 00010282 [ 171.221639] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 [ 171.223108] RDX: 0000000000000000 RSI: 0000000000000008 RDI: fffff5200002a09e [ 171.224388] RBP: ffff8880aa6e3c00 R08: 0000000000000001 R09: fffffbfff2ec9955 [ 171.225706] R10: ffffffff9764caa7 R11: fffffbfff2ec9954 R12: 0000000000007fca [ 171.227211] R13: ffff8881066f4a7f R14: ffff8880aa6e3c00 R15: 0000000000000020 [ 171.228460] FS: 00007f8623719740(0000) GS:ffff88810be00000(0000) knlGS:0000000000000000 [ 171.230065] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 171.231303] CR2: 00007ffdab190a50 CR3: 00000001038ea006 CR4: 0000000000160ee0 [ 171.232586] Call Trace: [ 171.233109] <IRQ> [ 171.233531] get_mapping_status (linux-mptcp/net/mptcp/subflow.c:691) [ 171.234371] mptcp_subflow_data_available (linux-mptcp/net/mptcp/subflow.c:736 linux-mptcp/net/mptcp/subflow.c:832) [ 171.238181] subflow_state_change (linux-mptcp/net/mptcp/subflow.c:1085 (discriminator 1)) [ 171.239066] tcp_fin (linux-mptcp/net/ipv4/tcp_input.c:4217) [ 171.240123] tcp_data_queue (linux-mptcp/./include/linux/compiler.h:199 linux-mptcp/net/ipv4/tcp_input.c:4822) [ 171.245083] tcp_rcv_established (linux-mptcp/./include/linux/skbuff.h:1785 linux-mptcp/./include/net/tcp.h:1774 linux-mptcp/./include/net/tcp.h:1847 linux-mptcp/net/ipv4/tcp_input.c:5238 linux-mptcp/net/ipv4/tcp_input.c:5730) [ 171.254089] tcp_v4_rcv (linux-mptcp/./include/linux/spinlock.h:393 linux-mptcp/net/ipv4/tcp_ipv4.c:2009) [ 171.258969] ip_protocol_deliver_rcu (linux-mptcp/net/ipv4/ip_input.c:204 (discriminator 1)) [ 171.260214] ip_local_deliver_finish (linux-mptcp/./include/linux/rcupdate.h:651 linux-mptcp/net/ipv4/ip_input.c:232) [ 171.261389] ip_local_deliver (linux-mptcp/./include/linux/netfilter.h:307 linux-mptcp/./include/linux/netfilter.h:301 linux-mptcp/net/ipv4/ip_input.c:252) [ 171.265884] ip_rcv (linux-mptcp/./include/linux/netfilter.h:307 linux-mptcp/./include/linux/netfilter.h:301 linux-mptcp/net/ipv4/ip_input.c:539) [ 171.273666] process_backlog (linux-mptcp/./include/linux/rcupdate.h:651 linux-mptcp/net/core/dev.c:6135) [ 171.275328] net_rx_action (linux-mptcp/net/core/dev.c:6572 linux-mptcp/net/core/dev.c:6640) [ 171.280472] __do_softirq (linux-mptcp/./arch/x86/include/asm/jump_label.h:25 linux-mptcp/./include/linux/jump_label.h:200 linux-mptcp/./include/trace/events/irq.h:142 linux-mptcp/kernel/softirq.c:293) [ 171.281379] do_softirq_own_stack (linux-mptcp/arch/x86/entry/entry_64.S:1083) [ 171.282358] </IRQ> We could address the issue clearing explicitly the relevant fields in several places - tcp_parse_option, tcp_fast_parse_options, possibly others. Instead we move the MPTCP option parsing into the already existing mptcp ingress hook, so that we need to clear the fields in a single place. This allows us dropping an MPTCP hook from the TCP code and removing the quite large mptcp_options_received from the tcp_sock struct. On the flip side, the MPTCP sockets will traverse the option space twice (in tcp_parse_option() and in mptcp_incoming_options(). That looks acceptable: we already do that for syn and 3rd ack packets, plain TCP socket will benefit from it, and even MPTCP sockets will experience better code locality, reducing the jumps between TCP and MPTCP code. v1 -> v2: - rebased on current '-net' tree Fixes: 648ef4b88673 ("mptcp: Implement MPTCP receive path") Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 21:01:52 +08:00
subflow_req->backup = mp_opt.backup;
subflow_req->remote_id = mp_opt.join_id;
subflow_req->token = mp_opt.token;
subflow_req->remote_nonce = mp_opt.nonce;
subflow_req->msk = subflow_token_join_request(req);
/* Can't fall back to TCP in this case. */
if (!subflow_req->msk) {
subflow_add_reset_reason(skb, MPTCP_RST_EMPTCP);
return -EPERM;
}
if (subflow_use_different_sport(subflow_req->msk, sk_listener)) {
pr_debug("syn inet_sport=%d %d",
ntohs(inet_sk(sk_listener)->inet_sport),
ntohs(inet_sk((struct sock *)subflow_req->msk)->inet_sport));
if (!mptcp_pm_sport_in_anno_list(subflow_req->msk, sk_listener)) {
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTSYNRX);
return -EPERM;
}
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINPORTSYNRX);
}
subflow_req_create_thmac(subflow_req);
if (unlikely(req->syncookie)) {
if (mptcp_can_accept_new_subflow(subflow_req->msk))
subflow_init_req_cookie_join_save(subflow_req, skb);
mptcp: fix syncookie process if mptcp can not_accept new subflow Lots of "TCP: tcp_fin: Impossible, sk->sk_state=7" in client side when doing stress testing using wrk and webfsd. There are at least two cases may trigger this warning: 1.mptcp is in syncookie, and server recv MP_JOIN SYN request, in subflow_check_req(), the mptcp_can_accept_new_subflow() return false, so subflow_init_req_cookie_join_save() isn't called, i.e. not store the data present in the MP_JOIN syn request and the random nonce in hash table - join_entries[], but still send synack. When recv 3rd-ack, mptcp_token_join_cookie_init_state() will return false, and 3rd-ack is dropped, then if mptcp conn is closed by client, client will send a DATA_FIN and a MPTCP FIN, the DATA_FIN doesn't have MP_CAPABLE or MP_JOIN, so mptcp_subflow_init_cookie_req() will return 0, and pass the cookie check, MP_JOIN request is fallback to normal TCP. Server will send a TCP FIN if closed, in client side, when process TCP FIN, it will do reset, the code path is: tcp_data_queue()->mptcp_incoming_options() ->check_fully_established()->mptcp_subflow_reset(). mptcp_subflow_reset() will set sock state to TCP_CLOSE, so tcp_fin will hit TCP_CLOSE, and print the warning. 2.mptcp is in syncookie, and server recv 3rd-ack, in mptcp_subflow_init_cookie_req(), mptcp_can_accept_new_subflow() return false, and subflow_req->mp_join is not set to 1, so in subflow_syn_recv_sock() will not reset the MP_JOIN subflow, but fallback to normal TCP, and then the same thing happens when server will send a TCP FIN if closed. For case1, subflow_check_req() return -EPERM, then tcp_conn_request() will drop MP_JOIN SYN. For case2, let subflow_syn_recv_sock() call mptcp_can_accept_new_subflow(), and do fatal fallback, send reset. Fixes: 9466a1ccebbe ("mptcp: enable JOIN requests even if cookies are in use") Signed-off-by: Jianguo Wu <wujianguo@chinatelecom.cn> Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-07-10 08:20:48 +08:00
else
return -EPERM;
}
pr_debug("token=%u, remote_nonce=%u msk=%p", subflow_req->token,
subflow_req->remote_nonce, subflow_req->msk);
}
return 0;
}
int mptcp_subflow_init_cookie_req(struct request_sock *req,
const struct sock *sk_listener,
struct sk_buff *skb)
{
struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk_listener);
struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
struct mptcp_options_received mp_opt;
bool opt_mp_capable, opt_mp_join;
int err;
subflow_init_req(req, sk_listener);
mptcp_get_options(sk_listener, skb, &mp_opt);
opt_mp_capable = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPC);
opt_mp_join = !!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ);
if (opt_mp_capable && opt_mp_join)
return -EINVAL;
if (opt_mp_capable && listener->request_mptcp) {
if (mp_opt.sndr_key == 0)
return -EINVAL;
subflow_req->local_key = mp_opt.rcvr_key;
err = mptcp_token_new_request(req);
if (err)
return err;
subflow_req->mp_capable = 1;
subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq - 1;
} else if (opt_mp_join && listener->request_mptcp) {
if (!mptcp_token_join_cookie_init_state(subflow_req, skb))
return -EINVAL;
mptcp: fix syncookie process if mptcp can not_accept new subflow Lots of "TCP: tcp_fin: Impossible, sk->sk_state=7" in client side when doing stress testing using wrk and webfsd. There are at least two cases may trigger this warning: 1.mptcp is in syncookie, and server recv MP_JOIN SYN request, in subflow_check_req(), the mptcp_can_accept_new_subflow() return false, so subflow_init_req_cookie_join_save() isn't called, i.e. not store the data present in the MP_JOIN syn request and the random nonce in hash table - join_entries[], but still send synack. When recv 3rd-ack, mptcp_token_join_cookie_init_state() will return false, and 3rd-ack is dropped, then if mptcp conn is closed by client, client will send a DATA_FIN and a MPTCP FIN, the DATA_FIN doesn't have MP_CAPABLE or MP_JOIN, so mptcp_subflow_init_cookie_req() will return 0, and pass the cookie check, MP_JOIN request is fallback to normal TCP. Server will send a TCP FIN if closed, in client side, when process TCP FIN, it will do reset, the code path is: tcp_data_queue()->mptcp_incoming_options() ->check_fully_established()->mptcp_subflow_reset(). mptcp_subflow_reset() will set sock state to TCP_CLOSE, so tcp_fin will hit TCP_CLOSE, and print the warning. 2.mptcp is in syncookie, and server recv 3rd-ack, in mptcp_subflow_init_cookie_req(), mptcp_can_accept_new_subflow() return false, and subflow_req->mp_join is not set to 1, so in subflow_syn_recv_sock() will not reset the MP_JOIN subflow, but fallback to normal TCP, and then the same thing happens when server will send a TCP FIN if closed. For case1, subflow_check_req() return -EPERM, then tcp_conn_request() will drop MP_JOIN SYN. For case2, let subflow_syn_recv_sock() call mptcp_can_accept_new_subflow(), and do fatal fallback, send reset. Fixes: 9466a1ccebbe ("mptcp: enable JOIN requests even if cookies are in use") Signed-off-by: Jianguo Wu <wujianguo@chinatelecom.cn> Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-07-10 08:20:48 +08:00
subflow_req->mp_join = 1;
subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq - 1;
}
return 0;
}
EXPORT_SYMBOL_GPL(mptcp_subflow_init_cookie_req);
static struct dst_entry *subflow_v4_route_req(const struct sock *sk,
struct sk_buff *skb,
struct flowi *fl,
struct request_sock *req)
{
struct dst_entry *dst;
int err;
tcp_rsk(req)->is_mptcp = 1;
subflow_init_req(req, sk);
dst = tcp_request_sock_ipv4_ops.route_req(sk, skb, fl, req);
if (!dst)
return NULL;
err = subflow_check_req(req, sk, skb);
if (err == 0)
return dst;
dst_release(dst);
if (!req->syncookie)
tcp_request_sock_ops.send_reset(sk, skb);
return NULL;
}
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
static struct dst_entry *subflow_v6_route_req(const struct sock *sk,
struct sk_buff *skb,
struct flowi *fl,
struct request_sock *req)
{
struct dst_entry *dst;
int err;
tcp_rsk(req)->is_mptcp = 1;
subflow_init_req(req, sk);
dst = tcp_request_sock_ipv6_ops.route_req(sk, skb, fl, req);
if (!dst)
return NULL;
err = subflow_check_req(req, sk, skb);
if (err == 0)
return dst;
dst_release(dst);
if (!req->syncookie)
tcp6_request_sock_ops.send_reset(sk, skb);
return NULL;
}
#endif
/* validate received truncated hmac and create hmac for third ACK */
static bool subflow_thmac_valid(struct mptcp_subflow_context *subflow)
{
u8 hmac[SHA256_DIGEST_SIZE];
u64 thmac;
subflow_generate_hmac(subflow->remote_key, subflow->local_key,
subflow->remote_nonce, subflow->local_nonce,
hmac);
thmac = get_unaligned_be64(hmac);
pr_debug("subflow=%p, token=%u, thmac=%llu, subflow->thmac=%llu\n",
subflow, subflow->token,
(unsigned long long)thmac,
(unsigned long long)subflow->thmac);
return thmac == subflow->thmac;
}
void mptcp_subflow_reset(struct sock *ssk)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
struct sock *sk = subflow->conn;
/* must hold: tcp_done() could drop last reference on parent */
sock_hold(sk);
tcp_set_state(ssk, TCP_CLOSE);
tcp_send_active_reset(ssk, GFP_ATOMIC);
tcp_done(ssk);
if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &mptcp_sk(sk)->flags) &&
schedule_work(&mptcp_sk(sk)->work))
return; /* worker will put sk for us */
sock_put(sk);
}
static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct sock *sk)
{
return inet_sk(sk)->inet_dport != inet_sk((struct sock *)msk)->inet_dport;
}
void __mptcp_set_connected(struct sock *sk)
{
if (sk->sk_state == TCP_SYN_SENT) {
inet_sk_state_store(sk, TCP_ESTABLISHED);
sk->sk_state_change(sk);
}
}
static void mptcp_set_connected(struct sock *sk)
{
mptcp_data_lock(sk);
if (!sock_owned_by_user(sk))
__mptcp_set_connected(sk);
else
__set_bit(MPTCP_CONNECTED, &mptcp_sk(sk)->cb_flags);
mptcp_data_unlock(sk);
}
static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
mptcp: move option parsing into mptcp_incoming_options() The mptcp_options_received structure carries several per packet flags (mp_capable, mp_join, etc.). Such fields must be cleared on each packet, even on dropped ones or packet not carrying any MPTCP options, but the current mptcp code clears them only on TCP option reset. On several races/corner cases we end-up with stray bits in incoming options, leading to WARN_ON splats. e.g.: [ 171.164906] Bad mapping: ssn=32714 map_seq=1 map_data_len=32713 [ 171.165006] WARNING: CPU: 1 PID: 5026 at net/mptcp/subflow.c:533 warn_bad_map (linux-mptcp/net/mptcp/subflow.c:533 linux-mptcp/net/mptcp/subflow.c:531) [ 171.167632] Modules linked in: ip6_vti ip_vti ip_gre ipip sit tunnel4 ip_tunnel geneve ip6_udp_tunnel udp_tunnel macsec macvtap tap ipvlan macvlan 8021q garp mrp xfrm_interface veth netdevsim nlmon dummy team bonding vcan bridge stp llc ip6_gre gre ip6_tunnel tunnel6 tun binfmt_misc intel_rapl_msr intel_rapl_common rfkill kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel joydev virtio_balloon pcspkr i2c_piix4 sunrpc ip_tables xfs libcrc32c crc32c_intel serio_raw virtio_console ata_generic virtio_blk virtio_net net_failover failover ata_piix libata [ 171.199464] CPU: 1 PID: 5026 Comm: repro Not tainted 5.7.0-rc1.mptcp_f227fdf5d388+ #95 [ 171.200886] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-2.fc30 04/01/2014 [ 171.202546] RIP: 0010:warn_bad_map (linux-mptcp/net/mptcp/subflow.c:533 linux-mptcp/net/mptcp/subflow.c:531) [ 171.206537] Code: c1 ea 03 0f b6 14 02 48 89 f8 83 e0 07 83 c0 03 38 d0 7c 04 84 d2 75 1d 8b 55 3c 44 89 e6 48 c7 c7 20 51 13 95 e8 37 8b 22 fe <0f> 0b 48 83 c4 08 5b 5d 41 5c c3 89 4c 24 04 e8 db d6 94 fe 8b 4c [ 171.220473] RSP: 0018:ffffc90000150560 EFLAGS: 00010282 [ 171.221639] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 [ 171.223108] RDX: 0000000000000000 RSI: 0000000000000008 RDI: fffff5200002a09e [ 171.224388] RBP: ffff8880aa6e3c00 R08: 0000000000000001 R09: fffffbfff2ec9955 [ 171.225706] R10: ffffffff9764caa7 R11: fffffbfff2ec9954 R12: 0000000000007fca [ 171.227211] R13: ffff8881066f4a7f R14: ffff8880aa6e3c00 R15: 0000000000000020 [ 171.228460] FS: 00007f8623719740(0000) GS:ffff88810be00000(0000) knlGS:0000000000000000 [ 171.230065] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 171.231303] CR2: 00007ffdab190a50 CR3: 00000001038ea006 CR4: 0000000000160ee0 [ 171.232586] Call Trace: [ 171.233109] <IRQ> [ 171.233531] get_mapping_status (linux-mptcp/net/mptcp/subflow.c:691) [ 171.234371] mptcp_subflow_data_available (linux-mptcp/net/mptcp/subflow.c:736 linux-mptcp/net/mptcp/subflow.c:832) [ 171.238181] subflow_state_change (linux-mptcp/net/mptcp/subflow.c:1085 (discriminator 1)) [ 171.239066] tcp_fin (linux-mptcp/net/ipv4/tcp_input.c:4217) [ 171.240123] tcp_data_queue (linux-mptcp/./include/linux/compiler.h:199 linux-mptcp/net/ipv4/tcp_input.c:4822) [ 171.245083] tcp_rcv_established (linux-mptcp/./include/linux/skbuff.h:1785 linux-mptcp/./include/net/tcp.h:1774 linux-mptcp/./include/net/tcp.h:1847 linux-mptcp/net/ipv4/tcp_input.c:5238 linux-mptcp/net/ipv4/tcp_input.c:5730) [ 171.254089] tcp_v4_rcv (linux-mptcp/./include/linux/spinlock.h:393 linux-mptcp/net/ipv4/tcp_ipv4.c:2009) [ 171.258969] ip_protocol_deliver_rcu (linux-mptcp/net/ipv4/ip_input.c:204 (discriminator 1)) [ 171.260214] ip_local_deliver_finish (linux-mptcp/./include/linux/rcupdate.h:651 linux-mptcp/net/ipv4/ip_input.c:232) [ 171.261389] ip_local_deliver (linux-mptcp/./include/linux/netfilter.h:307 linux-mptcp/./include/linux/netfilter.h:301 linux-mptcp/net/ipv4/ip_input.c:252) [ 171.265884] ip_rcv (linux-mptcp/./include/linux/netfilter.h:307 linux-mptcp/./include/linux/netfilter.h:301 linux-mptcp/net/ipv4/ip_input.c:539) [ 171.273666] process_backlog (linux-mptcp/./include/linux/rcupdate.h:651 linux-mptcp/net/core/dev.c:6135) [ 171.275328] net_rx_action (linux-mptcp/net/core/dev.c:6572 linux-mptcp/net/core/dev.c:6640) [ 171.280472] __do_softirq (linux-mptcp/./arch/x86/include/asm/jump_label.h:25 linux-mptcp/./include/linux/jump_label.h:200 linux-mptcp/./include/trace/events/irq.h:142 linux-mptcp/kernel/softirq.c:293) [ 171.281379] do_softirq_own_stack (linux-mptcp/arch/x86/entry/entry_64.S:1083) [ 171.282358] </IRQ> We could address the issue clearing explicitly the relevant fields in several places - tcp_parse_option, tcp_fast_parse_options, possibly others. Instead we move the MPTCP option parsing into the already existing mptcp ingress hook, so that we need to clear the fields in a single place. This allows us dropping an MPTCP hook from the TCP code and removing the quite large mptcp_options_received from the tcp_sock struct. On the flip side, the MPTCP sockets will traverse the option space twice (in tcp_parse_option() and in mptcp_incoming_options(). That looks acceptable: we already do that for syn and 3rd ack packets, plain TCP socket will benefit from it, and even MPTCP sockets will experience better code locality, reducing the jumps between TCP and MPTCP code. v1 -> v2: - rebased on current '-net' tree Fixes: 648ef4b88673 ("mptcp: Implement MPTCP receive path") Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 21:01:52 +08:00
struct mptcp_options_received mp_opt;
struct sock *parent = subflow->conn;
subflow->icsk_af_ops->sk_rx_dst_set(sk, skb);
/* be sure no special action on any packet other than syn-ack */
if (subflow->conn_finished)
return;
mptcp_propagate_sndbuf(parent, sk);
subflow->rel_write_seq = 1;
subflow->conn_finished = 1;
subflow->ssn_offset = TCP_SKB_CB(skb)->seq;
pr_debug("subflow=%p synack seq=%x", subflow, subflow->ssn_offset);
mptcp_get_options(sk, skb, &mp_opt);
if (subflow->request_mptcp) {
if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPC)) {
MPTCP_INC_STATS(sock_net(sk),
MPTCP_MIB_MPCAPABLEACTIVEFALLBACK);
mptcp_do_fallback(sk);
pr_fallback(mptcp_sk(subflow->conn));
goto fallback;
}
if (mp_opt.suboptions & OPTION_MPTCP_CSUMREQD)
WRITE_ONCE(mptcp_sk(parent)->csum_enabled, true);
if (mp_opt.deny_join_id0)
WRITE_ONCE(mptcp_sk(parent)->pm.remote_deny_join_id0, true);
subflow->mp_capable = 1;
subflow->can_ack = 1;
mptcp: move option parsing into mptcp_incoming_options() The mptcp_options_received structure carries several per packet flags (mp_capable, mp_join, etc.). Such fields must be cleared on each packet, even on dropped ones or packet not carrying any MPTCP options, but the current mptcp code clears them only on TCP option reset. On several races/corner cases we end-up with stray bits in incoming options, leading to WARN_ON splats. e.g.: [ 171.164906] Bad mapping: ssn=32714 map_seq=1 map_data_len=32713 [ 171.165006] WARNING: CPU: 1 PID: 5026 at net/mptcp/subflow.c:533 warn_bad_map (linux-mptcp/net/mptcp/subflow.c:533 linux-mptcp/net/mptcp/subflow.c:531) [ 171.167632] Modules linked in: ip6_vti ip_vti ip_gre ipip sit tunnel4 ip_tunnel geneve ip6_udp_tunnel udp_tunnel macsec macvtap tap ipvlan macvlan 8021q garp mrp xfrm_interface veth netdevsim nlmon dummy team bonding vcan bridge stp llc ip6_gre gre ip6_tunnel tunnel6 tun binfmt_misc intel_rapl_msr intel_rapl_common rfkill kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel joydev virtio_balloon pcspkr i2c_piix4 sunrpc ip_tables xfs libcrc32c crc32c_intel serio_raw virtio_console ata_generic virtio_blk virtio_net net_failover failover ata_piix libata [ 171.199464] CPU: 1 PID: 5026 Comm: repro Not tainted 5.7.0-rc1.mptcp_f227fdf5d388+ #95 [ 171.200886] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-2.fc30 04/01/2014 [ 171.202546] RIP: 0010:warn_bad_map (linux-mptcp/net/mptcp/subflow.c:533 linux-mptcp/net/mptcp/subflow.c:531) [ 171.206537] Code: c1 ea 03 0f b6 14 02 48 89 f8 83 e0 07 83 c0 03 38 d0 7c 04 84 d2 75 1d 8b 55 3c 44 89 e6 48 c7 c7 20 51 13 95 e8 37 8b 22 fe <0f> 0b 48 83 c4 08 5b 5d 41 5c c3 89 4c 24 04 e8 db d6 94 fe 8b 4c [ 171.220473] RSP: 0018:ffffc90000150560 EFLAGS: 00010282 [ 171.221639] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 [ 171.223108] RDX: 0000000000000000 RSI: 0000000000000008 RDI: fffff5200002a09e [ 171.224388] RBP: ffff8880aa6e3c00 R08: 0000000000000001 R09: fffffbfff2ec9955 [ 171.225706] R10: ffffffff9764caa7 R11: fffffbfff2ec9954 R12: 0000000000007fca [ 171.227211] R13: ffff8881066f4a7f R14: ffff8880aa6e3c00 R15: 0000000000000020 [ 171.228460] FS: 00007f8623719740(0000) GS:ffff88810be00000(0000) knlGS:0000000000000000 [ 171.230065] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 171.231303] CR2: 00007ffdab190a50 CR3: 00000001038ea006 CR4: 0000000000160ee0 [ 171.232586] Call Trace: [ 171.233109] <IRQ> [ 171.233531] get_mapping_status (linux-mptcp/net/mptcp/subflow.c:691) [ 171.234371] mptcp_subflow_data_available (linux-mptcp/net/mptcp/subflow.c:736 linux-mptcp/net/mptcp/subflow.c:832) [ 171.238181] subflow_state_change (linux-mptcp/net/mptcp/subflow.c:1085 (discriminator 1)) [ 171.239066] tcp_fin (linux-mptcp/net/ipv4/tcp_input.c:4217) [ 171.240123] tcp_data_queue (linux-mptcp/./include/linux/compiler.h:199 linux-mptcp/net/ipv4/tcp_input.c:4822) [ 171.245083] tcp_rcv_established (linux-mptcp/./include/linux/skbuff.h:1785 linux-mptcp/./include/net/tcp.h:1774 linux-mptcp/./include/net/tcp.h:1847 linux-mptcp/net/ipv4/tcp_input.c:5238 linux-mptcp/net/ipv4/tcp_input.c:5730) [ 171.254089] tcp_v4_rcv (linux-mptcp/./include/linux/spinlock.h:393 linux-mptcp/net/ipv4/tcp_ipv4.c:2009) [ 171.258969] ip_protocol_deliver_rcu (linux-mptcp/net/ipv4/ip_input.c:204 (discriminator 1)) [ 171.260214] ip_local_deliver_finish (linux-mptcp/./include/linux/rcupdate.h:651 linux-mptcp/net/ipv4/ip_input.c:232) [ 171.261389] ip_local_deliver (linux-mptcp/./include/linux/netfilter.h:307 linux-mptcp/./include/linux/netfilter.h:301 linux-mptcp/net/ipv4/ip_input.c:252) [ 171.265884] ip_rcv (linux-mptcp/./include/linux/netfilter.h:307 linux-mptcp/./include/linux/netfilter.h:301 linux-mptcp/net/ipv4/ip_input.c:539) [ 171.273666] process_backlog (linux-mptcp/./include/linux/rcupdate.h:651 linux-mptcp/net/core/dev.c:6135) [ 171.275328] net_rx_action (linux-mptcp/net/core/dev.c:6572 linux-mptcp/net/core/dev.c:6640) [ 171.280472] __do_softirq (linux-mptcp/./arch/x86/include/asm/jump_label.h:25 linux-mptcp/./include/linux/jump_label.h:200 linux-mptcp/./include/trace/events/irq.h:142 linux-mptcp/kernel/softirq.c:293) [ 171.281379] do_softirq_own_stack (linux-mptcp/arch/x86/entry/entry_64.S:1083) [ 171.282358] </IRQ> We could address the issue clearing explicitly the relevant fields in several places - tcp_parse_option, tcp_fast_parse_options, possibly others. Instead we move the MPTCP option parsing into the already existing mptcp ingress hook, so that we need to clear the fields in a single place. This allows us dropping an MPTCP hook from the TCP code and removing the quite large mptcp_options_received from the tcp_sock struct. On the flip side, the MPTCP sockets will traverse the option space twice (in tcp_parse_option() and in mptcp_incoming_options(). That looks acceptable: we already do that for syn and 3rd ack packets, plain TCP socket will benefit from it, and even MPTCP sockets will experience better code locality, reducing the jumps between TCP and MPTCP code. v1 -> v2: - rebased on current '-net' tree Fixes: 648ef4b88673 ("mptcp: Implement MPTCP receive path") Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 21:01:52 +08:00
subflow->remote_key = mp_opt.sndr_key;
pr_debug("subflow=%p, remote_key=%llu", subflow,
subflow->remote_key);
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEACK);
mptcp_finish_connect(sk);
mptcp_set_connected(parent);
} else if (subflow->request_join) {
u8 hmac[SHA256_DIGEST_SIZE];
if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ)) {
subflow->reset_reason = MPTCP_RST_EMPTCP;
goto do_reset;
}
subflow->backup = mp_opt.backup;
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
subflow->thmac = mp_opt.thmac;
subflow->remote_nonce = mp_opt.nonce;
pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u backup=%d",
subflow, subflow->thmac, subflow->remote_nonce,
subflow->backup);
if (!subflow_thmac_valid(subflow)) {
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINACKMAC);
subflow->reset_reason = MPTCP_RST_EMPTCP;
goto do_reset;
}
if (!mptcp_finish_join(sk))
goto do_reset;
subflow_generate_hmac(subflow->local_key, subflow->remote_key,
subflow->local_nonce,
subflow->remote_nonce,
hmac);
memcpy(subflow->hmac, hmac, MPTCPOPT_HMAC_LEN);
subflow->mp_join = 1;
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX);
if (subflow_use_different_dport(mptcp_sk(parent), sk)) {
pr_debug("synack inet_dport=%d %d",
ntohs(inet_sk(sk)->inet_dport),
ntohs(inet_sk(parent)->inet_dport));
MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINPORTSYNACKRX);
}
} else if (mptcp_check_fallback(sk)) {
fallback:
mptcp_rcv_space_init(mptcp_sk(parent), sk);
mptcp_set_connected(parent);
}
return;
do_reset:
subflow->reset_transient = 0;
mptcp_subflow_reset(sk);
}
struct request_sock_ops mptcp_subflow_request_sock_ops;
EXPORT_SYMBOL_GPL(mptcp_subflow_request_sock_ops);
static struct tcp_request_sock_ops subflow_request_sock_ipv4_ops;
static int subflow_v4_conn_request(struct sock *sk, struct sk_buff *skb)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
pr_debug("subflow=%p", subflow);
/* Never answer to SYNs sent to broadcast or multicast */
if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
goto drop;
return tcp_conn_request(&mptcp_subflow_request_sock_ops,
&subflow_request_sock_ipv4_ops,
sk, skb);
drop:
tcp_listendrop(sk);
return 0;
}
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
static struct tcp_request_sock_ops subflow_request_sock_ipv6_ops;
static struct inet_connection_sock_af_ops subflow_v6_specific;
static struct inet_connection_sock_af_ops subflow_v6m_specific;
static struct proto tcpv6_prot_override;
static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
pr_debug("subflow=%p", subflow);
if (skb->protocol == htons(ETH_P_IP))
return subflow_v4_conn_request(sk, skb);
if (!ipv6_unicast_destination(skb))
goto drop;
if (ipv6_addr_v4mapped(&ipv6_hdr(skb)->saddr)) {
__IP6_INC_STATS(sock_net(sk), NULL, IPSTATS_MIB_INHDRERRORS);
return 0;
}
return tcp_conn_request(&mptcp_subflow_request_sock_ops,
&subflow_request_sock_ipv6_ops, sk, skb);
drop:
tcp_listendrop(sk);
return 0; /* don't send reset */
}
#endif
/* validate hmac received in third ACK */
static bool subflow_hmac_valid(const struct request_sock *req,
mptcp: move option parsing into mptcp_incoming_options() The mptcp_options_received structure carries several per packet flags (mp_capable, mp_join, etc.). Such fields must be cleared on each packet, even on dropped ones or packet not carrying any MPTCP options, but the current mptcp code clears them only on TCP option reset. On several races/corner cases we end-up with stray bits in incoming options, leading to WARN_ON splats. e.g.: [ 171.164906] Bad mapping: ssn=32714 map_seq=1 map_data_len=32713 [ 171.165006] WARNING: CPU: 1 PID: 5026 at net/mptcp/subflow.c:533 warn_bad_map (linux-mptcp/net/mptcp/subflow.c:533 linux-mptcp/net/mptcp/subflow.c:531) [ 171.167632] Modules linked in: ip6_vti ip_vti ip_gre ipip sit tunnel4 ip_tunnel geneve ip6_udp_tunnel udp_tunnel macsec macvtap tap ipvlan macvlan 8021q garp mrp xfrm_interface veth netdevsim nlmon dummy team bonding vcan bridge stp llc ip6_gre gre ip6_tunnel tunnel6 tun binfmt_misc intel_rapl_msr intel_rapl_common rfkill kvm_intel kvm irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel joydev virtio_balloon pcspkr i2c_piix4 sunrpc ip_tables xfs libcrc32c crc32c_intel serio_raw virtio_console ata_generic virtio_blk virtio_net net_failover failover ata_piix libata [ 171.199464] CPU: 1 PID: 5026 Comm: repro Not tainted 5.7.0-rc1.mptcp_f227fdf5d388+ #95 [ 171.200886] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-2.fc30 04/01/2014 [ 171.202546] RIP: 0010:warn_bad_map (linux-mptcp/net/mptcp/subflow.c:533 linux-mptcp/net/mptcp/subflow.c:531) [ 171.206537] Code: c1 ea 03 0f b6 14 02 48 89 f8 83 e0 07 83 c0 03 38 d0 7c 04 84 d2 75 1d 8b 55 3c 44 89 e6 48 c7 c7 20 51 13 95 e8 37 8b 22 fe <0f> 0b 48 83 c4 08 5b 5d 41 5c c3 89 4c 24 04 e8 db d6 94 fe 8b 4c [ 171.220473] RSP: 0018:ffffc90000150560 EFLAGS: 00010282 [ 171.221639] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 [ 171.223108] RDX: 0000000000000000 RSI: 0000000000000008 RDI: fffff5200002a09e [ 171.224388] RBP: ffff8880aa6e3c00 R08: 0000000000000001 R09: fffffbfff2ec9955 [ 171.225706] R10: ffffffff9764caa7 R11: fffffbfff2ec9954 R12: 0000000000007fca [ 171.227211] R13: ffff8881066f4a7f R14: ffff8880aa6e3c00 R15: 0000000000000020 [ 171.228460] FS: 00007f8623719740(0000) GS:ffff88810be00000(0000) knlGS:0000000000000000 [ 171.230065] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 171.231303] CR2: 00007ffdab190a50 CR3: 00000001038ea006 CR4: 0000000000160ee0 [ 171.232586] Call Trace: [ 171.233109] <IRQ> [ 171.233531] get_mapping_status (linux-mptcp/net/mptcp/subflow.c:691) [ 171.234371] mptcp_subflow_data_available (linux-mptcp/net/mptcp/subflow.c:736 linux-mptcp/net/mptcp/subflow.c:832) [ 171.238181] subflow_state_change (linux-mptcp/net/mptcp/subflow.c:1085 (discriminator 1)) [ 171.239066] tcp_fin (linux-mptcp/net/ipv4/tcp_input.c:4217) [ 171.240123] tcp_data_queue (linux-mptcp/./include/linux/compiler.h:199 linux-mptcp/net/ipv4/tcp_input.c:4822) [ 171.245083] tcp_rcv_established (linux-mptcp/./include/linux/skbuff.h:1785 linux-mptcp/./include/net/tcp.h:1774 linux-mptcp/./include/net/tcp.h:1847 linux-mptcp/net/ipv4/tcp_input.c:5238 linux-mptcp/net/ipv4/tcp_input.c:5730) [ 171.254089] tcp_v4_rcv (linux-mptcp/./include/linux/spinlock.h:393 linux-mptcp/net/ipv4/tcp_ipv4.c:2009) [ 171.258969] ip_protocol_deliver_rcu (linux-mptcp/net/ipv4/ip_input.c:204 (discriminator 1)) [ 171.260214] ip_local_deliver_finish (linux-mptcp/./include/linux/rcupdate.h:651 linux-mptcp/net/ipv4/ip_input.c:232) [ 171.261389] ip_local_deliver (linux-mptcp/./include/linux/netfilter.h:307 linux-mptcp/./include/linux/netfilter.h:301 linux-mptcp/net/ipv4/ip_input.c:252) [ 171.265884] ip_rcv (linux-mptcp/./include/linux/netfilter.h:307 linux-mptcp/./include/linux/netfilter.h:301 linux-mptcp/net/ipv4/ip_input.c:539) [ 171.273666] process_backlog (linux-mptcp/./include/linux/rcupdate.h:651 linux-mptcp/net/core/dev.c:6135) [ 171.275328] net_rx_action (linux-mptcp/net/core/dev.c:6572 linux-mptcp/net/core/dev.c:6640) [ 171.280472] __do_softirq (linux-mptcp/./arch/x86/include/asm/jump_label.h:25 linux-mptcp/./include/linux/jump_label.h:200 linux-mptcp/./include/trace/events/irq.h:142 linux-mptcp/kernel/softirq.c:293) [ 171.281379] do_softirq_own_stack (linux-mptcp/arch/x86/entry/entry_64.S:1083) [ 171.282358] </IRQ> We could address the issue clearing explicitly the relevant fields in several places - tcp_parse_option, tcp_fast_parse_options, possibly others. Instead we move the MPTCP option parsing into the already existing mptcp ingress hook, so that we need to clear the fields in a single place. This allows us dropping an MPTCP hook from the TCP code and removing the quite large mptcp_options_received from the tcp_sock struct. On the flip side, the MPTCP sockets will traverse the option space twice (in tcp_parse_option() and in mptcp_incoming_options(). That looks acceptable: we already do that for syn and 3rd ack packets, plain TCP socket will benefit from it, and even MPTCP sockets will experience better code locality, reducing the jumps between TCP and MPTCP code. v1 -> v2: - rebased on current '-net' tree Fixes: 648ef4b88673 ("mptcp: Implement MPTCP receive path") Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-04-30 21:01:52 +08:00
const struct mptcp_options_received *mp_opt)
{
const struct mptcp_subflow_request_sock *subflow_req;
u8 hmac[SHA256_DIGEST_SIZE];
struct mptcp_sock *msk;
subflow_req = mptcp_subflow_rsk(req);
msk = subflow_req->msk;
if (!msk)
return false;
subflow_generate_hmac(msk->remote_key, msk->local_key,
subflow_req->remote_nonce,
subflow_req->local_nonce, hmac);
return !crypto_memneq(hmac, mp_opt->hmac, MPTCPOPT_HMAC_LEN);
}
static void mptcp_sock_destruct(struct sock *sk)
{
/* if new mptcp socket isn't accepted, it is free'd
* from the tcp listener sockets request queue, linked
* from req->sk. The tcp socket is released.
* This calls the ULP release function which will
* also remove the mptcp socket, via
* sock_put(ctx->conn).
*
* Problem is that the mptcp socket will be in
* ESTABLISHED state and will not have the SOCK_DEAD flag.
* Both result in warnings from inet_sock_destruct.
*/
if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) {
sk->sk_state = TCP_CLOSE;
WARN_ON_ONCE(sk->sk_socket);
sock_orphan(sk);
}
mptcp_destroy_common(mptcp_sk(sk));
inet_sock_destruct(sk);
}
static void mptcp_force_close(struct sock *sk)
{
/* the msk is not yet exposed to user-space */
inet_sk_state_store(sk, TCP_CLOSE);
sk_common_release(sk);
}
static void subflow_ulp_fallback(struct sock *sk,
struct mptcp_subflow_context *old_ctx)
{
struct inet_connection_sock *icsk = inet_csk(sk);
mptcp_subflow_tcp_fallback(sk, old_ctx);
icsk->icsk_ulp_ops = NULL;
rcu_assign_pointer(icsk->icsk_ulp_data, NULL);
tcp_sk(sk)->is_mptcp = 0;
mptcp_subflow_ops_undo_override(sk);
}
static void subflow_drop_ctx(struct sock *ssk)
{
struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(ssk);
if (!ctx)
return;
subflow_ulp_fallback(ssk, ctx);
if (ctx->conn)
sock_put(ctx->conn);
kfree_rcu(ctx, rcu);
}
void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
struct mptcp_options_received *mp_opt)
{
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
subflow->remote_key = mp_opt->sndr_key;
subflow->fully_established = 1;
subflow->can_ack = 1;
WRITE_ONCE(msk->fully_established, true);
}
static struct sock *subflow_syn_recv_sock(const struct sock *sk,
struct sk_buff *skb,
struct request_sock *req,
struct dst_entry *dst,
struct request_sock *req_unhash,
bool *own_req)
{
struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk);
struct mptcp_subflow_request_sock *subflow_req;
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;
bool fallback, fallback_is_fatal;
struct sock *new_msk = NULL;
struct sock *child;
pr_debug("listener=%p, req=%p, conn=%p", listener, req, listener->conn);
/* After child creation we must look for MPC even when options
* are not parsed
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.suboptions = 0;
/* hopefully temporary handling for MP_JOIN+syncookie */
subflow_req = mptcp_subflow_rsk(req);
fallback_is_fatal = tcp_rsk(req)->is_mptcp && subflow_req->mp_join;
fallback = !tcp_rsk(req)->is_mptcp;
if (fallback)
goto create_child;
/* if the sk is MP_CAPABLE, we try to fetch the client key */
if (subflow_req->mp_capable) {
/* we can receive and accept an in-window, out-of-order pkt,
* which may not carry the MP_CAPABLE opt even on mptcp enabled
* paths: always try to extract the peer key, and fallback
* for packets missing it.
* Even OoO DSS packets coming legitly after dropped or
* reordered MPC will cause fallback, but we don't have other
* options.
*/
mptcp_get_options(sk, skb, &mp_opt);
if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPC)) {
fallback = true;
goto create_child;
}
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
new_msk = mptcp_sk_clone(listener->conn, &mp_opt, req);
if (!new_msk)
fallback = true;
} else if (subflow_req->mp_join) {
mptcp_get_options(sk, skb, &mp_opt);
if (!(mp_opt.suboptions & OPTIONS_MPTCP_MPJ) ||
!subflow_hmac_valid(req, &mp_opt) ||
!mptcp_can_accept_new_subflow(subflow_req->msk)) {
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC);
fallback = true;
}
}
create_child:
child = listener->icsk_af_ops->syn_recv_sock(sk, skb, req, dst,
req_unhash, own_req);
if (child && *own_req) {
struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(child);
tcp_rsk(req)->drop_req = false;
/* we need to fallback on ctx allocation failure and on pre-reqs
* checking above. In the latter scenario we additionally need
* to reset the context to non MPTCP status.
*/
if (!ctx || fallback) {
if (fallback_is_fatal) {
subflow_add_reset_reason(skb, MPTCP_RST_EMPTCP);
goto dispose_child;
}
subflow_drop_ctx(child);
goto out;
}
/* ssk inherits options of listener sk */
ctx->setsockopt_seq = listener->setsockopt_seq;
if (ctx->mp_capable) {
/* this can't race with mptcp_close(), as the msk is
* not yet exposted to user-space
*/
inet_sk_state_store((void *)new_msk, TCP_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
/* record the newly created socket as the first msk
* subflow, but don't link it yet into conn_list
*/
WRITE_ONCE(mptcp_sk(new_msk)->first, child);
/* new mpc subflow takes ownership of the newly
* created mptcp socket
*/
new_msk->sk_destruct = mptcp_sock_destruct;
mptcp_sk(new_msk)->setsockopt_seq = ctx->setsockopt_seq;
mptcp_pm_new_connection(mptcp_sk(new_msk), child, 1);
mptcp_token_accept(subflow_req, mptcp_sk(new_msk));
ctx->conn = new_msk;
new_msk = NULL;
/* with OoO packets we can reach here without ingress
* mpc option
*/
if (mp_opt.suboptions & OPTIONS_MPTCP_MPC)
mptcp_subflow_fully_established(ctx, &mp_opt);
} else if (ctx->mp_join) {
struct mptcp_sock *owner;
owner = subflow_req->msk;
if (!owner) {
subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT);
goto dispose_child;
}
/* move the msk reference ownership to the subflow */
subflow_req->msk = NULL;
ctx->conn = (struct sock *)owner;
if (subflow_use_different_sport(owner, sk)) {
pr_debug("ack inet_sport=%d %d",
ntohs(inet_sk(sk)->inet_sport),
ntohs(inet_sk((struct sock *)owner)->inet_sport));
if (!mptcp_pm_sport_in_anno_list(owner, sk)) {
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTACKRX);
goto dispose_child;
}
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINPORTACKRX);
}
if (!mptcp_finish_join(child))
goto dispose_child;
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKRX);
tcp_rsk(req)->drop_req = true;
}
}
out:
/* dispose of the left over mptcp master, if any */
if (unlikely(new_msk))
mptcp_force_close(new_msk);
/* check for expected invariant - should never trigger, just help
* catching eariler subtle bugs
*/
WARN_ON_ONCE(child && *own_req && tcp_sk(child)->is_mptcp &&
(!mptcp_subflow_ctx(child) ||
!mptcp_subflow_ctx(child)->conn));
return child;
dispose_child:
subflow_drop_ctx(child);
tcp_rsk(req)->drop_req = true;
inet_csk_prepare_for_destroy_sock(child);
tcp_done(child);
req->rsk_ops->send_reset(sk, skb);
/* The last child reference will be released by the caller */
return child;
}
static struct inet_connection_sock_af_ops subflow_specific;
static struct proto tcp_prot_override;
enum mapping_status {
MAPPING_OK,
MAPPING_INVALID,
MAPPING_EMPTY,
MAPPING_DATA_FIN,
MAPPING_DUMMY
};
static void dbg_bad_map(struct mptcp_subflow_context *subflow, u32 ssn)
{
pr_debug("Bad mapping: ssn=%d map_seq=%d map_data_len=%d",
ssn, subflow->map_subflow_seq, subflow->map_data_len);
}
static bool skb_is_fully_mapped(struct sock *ssk, struct sk_buff *skb)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
unsigned int skb_consumed;
skb_consumed = tcp_sk(ssk)->copied_seq - TCP_SKB_CB(skb)->seq;
if (WARN_ON_ONCE(skb_consumed >= skb->len))
return true;
return skb->len - skb_consumed <= subflow->map_data_len -
mptcp_subflow_get_map_offset(subflow);
}
static bool validate_mapping(struct sock *ssk, struct sk_buff *skb)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
u32 ssn = tcp_sk(ssk)->copied_seq - subflow->ssn_offset;
if (unlikely(before(ssn, subflow->map_subflow_seq))) {
/* Mapping covers data later in the subflow stream,
* currently unsupported.
*/
dbg_bad_map(subflow, ssn);
return false;
}
if (unlikely(!before(ssn, subflow->map_subflow_seq +
subflow->map_data_len))) {
/* Mapping does covers past subflow data, invalid */
dbg_bad_map(subflow, ssn);
return false;
}
return true;
}
static enum mapping_status validate_data_csum(struct sock *ssk, struct sk_buff *skb,
bool csum_reqd)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
u32 offset, seq, delta;
u16 csum;
int len;
if (!csum_reqd)
return MAPPING_OK;
/* mapping already validated on previous traversal */
if (subflow->map_csum_len == subflow->map_data_len)
return MAPPING_OK;
/* traverse the receive queue, ensuring it contains a full
* DSS mapping and accumulating the related csum.
* Preserve the accoumlate csum across multiple calls, to compute
* the csum only once
*/
delta = subflow->map_data_len - subflow->map_csum_len;
for (;;) {
seq = tcp_sk(ssk)->copied_seq + subflow->map_csum_len;
offset = seq - TCP_SKB_CB(skb)->seq;
/* if the current skb has not been accounted yet, csum its contents
* up to the amount covered by the current DSS
*/
if (offset < skb->len) {
__wsum csum;
len = min(skb->len - offset, delta);
csum = skb_checksum(skb, offset, len, 0);
subflow->map_data_csum = csum_block_add(subflow->map_data_csum, csum,
subflow->map_csum_len);
delta -= len;
subflow->map_csum_len += len;
}
if (delta == 0)
break;
if (skb_queue_is_last(&ssk->sk_receive_queue, skb)) {
/* if this subflow is closed, the partial mapping
* will be never completed; flush the pending skbs, so
* that subflow_sched_work_if_closed() can kick in
*/
if (unlikely(ssk->sk_state == TCP_CLOSE))
while ((skb = skb_peek(&ssk->sk_receive_queue)))
sk_eat_skb(ssk, skb);
/* not enough data to validate the csum */
return MAPPING_EMPTY;
}
/* the DSS mapping for next skbs will be validated later,
* when a get_mapping_status call will process such skb
*/
skb = skb->next;
}
/* note that 'map_data_len' accounts only for the carried data, does
* not include the eventual seq increment due to the data fin,
* while the pseudo header requires the original DSS data len,
* including that
*/
csum = __mptcp_make_csum(subflow->map_seq,
subflow->map_subflow_seq,
subflow->map_data_len + subflow->map_data_fin,
subflow->map_data_csum);
if (unlikely(csum)) {
MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DATACSUMERR);
subflow->send_mp_fail = 1;
MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPFAILTX);
return subflow->mp_join ? MAPPING_INVALID : MAPPING_DUMMY;
}
return MAPPING_OK;
}
static enum mapping_status get_mapping_status(struct sock *ssk,
struct mptcp_sock *msk)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
bool csum_reqd = READ_ONCE(msk->csum_enabled);
struct mptcp_ext *mpext;
struct sk_buff *skb;
u16 data_len;
u64 map_seq;
skb = skb_peek(&ssk->sk_receive_queue);
if (!skb)
return MAPPING_EMPTY;
if (mptcp_check_fallback(ssk))
return MAPPING_DUMMY;
mpext = mptcp_get_ext(skb);
if (!mpext || !mpext->use_map) {
if (!subflow->map_valid && !skb->len) {
/* the TCP stack deliver 0 len FIN pkt to the receive
* queue, that is the only 0len pkts ever expected here,
* and we can admit no mapping only for 0 len pkts
*/
if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN))
WARN_ONCE(1, "0len seq %d:%d flags %x",
TCP_SKB_CB(skb)->seq,
TCP_SKB_CB(skb)->end_seq,
TCP_SKB_CB(skb)->tcp_flags);
sk_eat_skb(ssk, skb);
return MAPPING_EMPTY;
}
if (!subflow->map_valid)
return MAPPING_INVALID;
goto validate_seq;
}
trace_get_mapping_status(mpext);
data_len = mpext->data_len;
if (data_len == 0) {
MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPRX);
return MAPPING_INVALID;
}
if (mpext->data_fin == 1) {
if (data_len == 1) {
bool updated = mptcp_update_rcv_data_fin(msk, mpext->data_seq,
mpext->dsn64);
pr_debug("DATA_FIN with no payload seq=%llu", mpext->data_seq);
if (subflow->map_valid) {
/* A DATA_FIN might arrive in a DSS
* option before the previous mapping
* has been fully consumed. Continue
* handling the existing mapping.
*/
skb_ext_del(skb, SKB_EXT_MPTCP);
return MAPPING_OK;
} else {
if (updated && schedule_work(&msk->work))
sock_hold((struct sock *)msk);
return MAPPING_DATA_FIN;
}
} else {
u64 data_fin_seq = mpext->data_seq + data_len - 1;
/* If mpext->data_seq is a 32-bit value, data_fin_seq
* must also be limited to 32 bits.
*/
if (!mpext->dsn64)
data_fin_seq &= GENMASK_ULL(31, 0);
mptcp_update_rcv_data_fin(msk, data_fin_seq, mpext->dsn64);
pr_debug("DATA_FIN with mapping seq=%llu dsn64=%d",
data_fin_seq, mpext->dsn64);
}
/* Adjust for DATA_FIN using 1 byte of sequence space */
data_len--;
}
map_seq = mptcp_expand_seq(READ_ONCE(msk->ack_seq), mpext->data_seq, mpext->dsn64);
WRITE_ONCE(mptcp_sk(subflow->conn)->use_64bit_ack, !!mpext->dsn64);
if (subflow->map_valid) {
/* Allow replacing only with an identical map */
if (subflow->map_seq == map_seq &&
subflow->map_subflow_seq == mpext->subflow_seq &&
subflow->map_data_len == data_len &&
subflow->map_csum_reqd == mpext->csum_reqd) {
skb_ext_del(skb, SKB_EXT_MPTCP);
goto validate_csum;
}
/* If this skb data are fully covered by the current mapping,
* the new map would need caching, which is not supported
*/
if (skb_is_fully_mapped(ssk, skb)) {
MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DSSNOMATCH);
return MAPPING_INVALID;
}
/* will validate the next map after consuming the current one */
goto validate_csum;
}
subflow->map_seq = map_seq;
subflow->map_subflow_seq = mpext->subflow_seq;
subflow->map_data_len = data_len;
subflow->map_valid = 1;
subflow->map_data_fin = mpext->data_fin;
subflow->mpc_map = mpext->mpc_map;
subflow->map_csum_reqd = mpext->csum_reqd;
subflow->map_csum_len = 0;
subflow->map_data_csum = csum_unfold(mpext->csum);
/* Cfr RFC 8684 Section 3.3.0 */
if (unlikely(subflow->map_csum_reqd != csum_reqd))
return MAPPING_INVALID;
pr_debug("new map seq=%llu subflow_seq=%u data_len=%u csum=%d:%u",
subflow->map_seq, subflow->map_subflow_seq,
subflow->map_data_len, subflow->map_csum_reqd,
subflow->map_data_csum);
validate_seq:
/* we revalidate valid mapping on new skb, because we must ensure
* the current skb is completely covered by the available mapping
*/
if (!validate_mapping(ssk, skb)) {
MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DSSTCPMISMATCH);
return MAPPING_INVALID;
}
skb_ext_del(skb, SKB_EXT_MPTCP);
validate_csum:
return validate_data_csum(ssk, skb, csum_reqd);
}
static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb,
u64 limit)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
bool fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN;
u32 incr;
incr = limit >= skb->len ? skb->len + fin : limit;
pr_debug("discarding=%d len=%d seq=%d", incr, skb->len,
subflow->map_subflow_seq);
MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DUPDATA);
tcp_sk(ssk)->copied_seq += incr;
if (!before(tcp_sk(ssk)->copied_seq, TCP_SKB_CB(skb)->end_seq))
sk_eat_skb(ssk, skb);
if (mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len)
subflow->map_valid = 0;
}
/* sched mptcp worker to remove the subflow if no more data is pending */
static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ssk)
{
struct sock *sk = (struct sock *)msk;
if (likely(ssk->sk_state != TCP_CLOSE))
return;
if (skb_queue_empty(&ssk->sk_receive_queue) &&
!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) {
sock_hold(sk);
if (!schedule_work(&msk->work))
sock_put(sk);
}
}
static bool subflow_check_data_avail(struct sock *ssk)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
enum mapping_status status;
struct mptcp_sock *msk;
struct sk_buff *skb;
if (!skb_peek(&ssk->sk_receive_queue))
WRITE_ONCE(subflow->data_avail, 0);
if (subflow->data_avail)
return true;
msk = mptcp_sk(subflow->conn);
for (;;) {
u64 ack_seq;
u64 old_ack;
status = get_mapping_status(ssk, msk);
trace_subflow_check_data_avail(status, skb_peek(&ssk->sk_receive_queue));
if (unlikely(status == MAPPING_INVALID))
goto fallback;
if (unlikely(status == MAPPING_DUMMY))
goto fallback;
if (status != MAPPING_OK)
goto no_data;
skb = skb_peek(&ssk->sk_receive_queue);
if (WARN_ON_ONCE(!skb))
goto no_data;
/* if msk lacks the remote key, this subflow must provide an
* MP_CAPABLE-based mapping
*/
if (unlikely(!READ_ONCE(msk->can_ack))) {
if (!subflow->mpc_map)
goto fallback;
WRITE_ONCE(msk->remote_key, subflow->remote_key);
WRITE_ONCE(msk->ack_seq, subflow->map_seq);
WRITE_ONCE(msk->can_ack, true);
}
old_ack = READ_ONCE(msk->ack_seq);
ack_seq = mptcp_subflow_get_mapped_dsn(subflow);
pr_debug("msk ack_seq=%llx subflow ack_seq=%llx", old_ack,
ack_seq);
if (unlikely(before64(ack_seq, old_ack))) {
mptcp_subflow_discard_data(ssk, skb, old_ack - ack_seq);
continue;
}
WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL);
break;
}
return true;
no_data:
subflow_sched_work_if_closed(msk, ssk);
return false;
fallback:
/* RFC 8684 section 3.7. */
if (subflow->send_mp_fail) {
if (mptcp_has_another_subflow(ssk)) {
while ((skb = skb_peek(&ssk->sk_receive_queue)))
sk_eat_skb(ssk, skb);
}
ssk->sk_err = EBADMSG;
tcp_set_state(ssk, TCP_CLOSE);
subflow->reset_transient = 0;
subflow->reset_reason = MPTCP_RST_EMIDDLEBOX;
tcp_send_active_reset(ssk, GFP_ATOMIC);
WRITE_ONCE(subflow->data_avail, 0);
return true;
}
if (subflow->mp_join || subflow->fully_established) {
/* fatal protocol error, close the socket.
* subflow_error_report() will introduce the appropriate barriers
*/
ssk->sk_err = EBADMSG;
tcp_set_state(ssk, TCP_CLOSE);
subflow->reset_transient = 0;
subflow->reset_reason = MPTCP_RST_EMPTCP;
tcp_send_active_reset(ssk, GFP_ATOMIC);
WRITE_ONCE(subflow->data_avail, 0);
return false;
}
__mptcp_do_fallback(msk);
skb = skb_peek(&ssk->sk_receive_queue);
subflow->map_valid = 1;
subflow->map_seq = READ_ONCE(msk->ack_seq);
subflow->map_data_len = skb->len;
subflow->map_subflow_seq = tcp_sk(ssk)->copied_seq - subflow->ssn_offset;
WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL);
return true;
}
bool mptcp_subflow_data_available(struct sock *sk)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
/* check if current mapping is still valid */
if (subflow->map_valid &&
mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len) {
subflow->map_valid = 0;
WRITE_ONCE(subflow->data_avail, 0);
pr_debug("Done with mapping: seq=%u data_len=%u",
subflow->map_subflow_seq,
subflow->map_data_len);
}
return subflow_check_data_avail(sk);
}
/* If ssk has an mptcp parent socket, use the mptcp rcvbuf occupancy,
* not the ssk one.
*
* In mptcp, rwin is about the mptcp-level connection data.
*
* Data that is still on the ssk rx queue can thus be ignored,
* as far as mptcp peer is concerned that data is still inflight.
* DSS ACK is updated when skb is moved to the mptcp rx queue.
*/
void mptcp_space(const struct sock *ssk, int *space, int *full_space)
{
const struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
const struct sock *sk = subflow->conn;
*space = __mptcp_space(sk);
*full_space = tcp_full_space(sk);
}
void __mptcp_error_report(struct sock *sk)
{
struct mptcp_subflow_context *subflow;
struct mptcp_sock *msk = mptcp_sk(sk);
mptcp_for_each_subflow(msk, subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
int err = sock_error(ssk);
if (!err)
continue;
/* only propagate errors on fallen-back sockets or
* on MPC connect
*/
if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(msk))
continue;
inet_sk_state_store(sk, inet_sk_state_load(ssk));
sk->sk_err = -err;
/* This barrier is coupled with smp_rmb() in mptcp_poll() */
smp_wmb();
sk_error_report(sk);
break;
}
}
static void subflow_error_report(struct sock *ssk)
{
struct sock *sk = mptcp_subflow_ctx(ssk)->conn;
mptcp_data_lock(sk);
if (!sock_owned_by_user(sk))
__mptcp_error_report(sk);
else
__set_bit(MPTCP_ERROR_REPORT, &mptcp_sk(sk)->cb_flags);
mptcp_data_unlock(sk);
}
mptcp: fix soft lookup in subflow_error_report() Maxim reported a soft lookup in subflow_error_report(): watchdog: BUG: soft lockup - CPU#0 stuck for 22s! [swapper/0:0] RIP: 0010:native_queued_spin_lock_slowpath RSP: 0018:ffffa859c0003bc0 EFLAGS: 00000202 RAX: 0000000000000101 RBX: 0000000000000001 RCX: 0000000000000000 RDX: ffff9195c2772d88 RSI: 0000000000000000 RDI: ffff9195c2772d88 RBP: ffff9195c2772d00 R08: 00000000000067b0 R09: c6e31da9eb1e44f4 R10: ffff9195ef379700 R11: ffff9195edb50710 R12: ffff9195c2772d88 R13: ffff9195f500e3d0 R14: ffff9195ef379700 R15: ffff9195ef379700 FS: 0000000000000000(0000) GS:ffff91961f400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000c000407000 CR3: 0000000002988000 CR4: 00000000000006f0 Call Trace: <IRQ> _raw_spin_lock_bh subflow_error_report mptcp_subflow_data_available __mptcp_move_skbs_from_subflow mptcp_data_ready tcp_data_queue tcp_rcv_established tcp_v4_do_rcv tcp_v4_rcv ip_protocol_deliver_rcu ip_local_deliver_finish __netif_receive_skb_one_core netif_receive_skb rtl8139_poll 8139too __napi_poll net_rx_action __do_softirq __irq_exit_rcu common_interrupt </IRQ> The calling function - mptcp_subflow_data_available() - can be invoked from different contexts: - plain ssk socket lock - ssk socket lock + mptcp_data_lock - ssk socket lock + mptcp_data_lock + msk socket lock. Since subflow_error_report() tries to acquire the mptcp_data_lock, the latter two call chains will cause soft lookup. This change addresses the issue moving the error reporting call to outer functions, where the held locks list is known and the we can acquire only the needed one. Reported-by: Maxim Galaganov <max@internet.ru> Fixes: 15cc10453398 ("mptcp: deliver ssk errors to msk") Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/199 Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-06-11 06:59:44 +08:00
static void subflow_data_ready(struct sock *sk)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
u16 state = 1 << inet_sk_state_load(sk);
struct sock *parent = subflow->conn;
struct mptcp_sock *msk;
msk = mptcp_sk(parent);
if (state & TCPF_LISTEN) {
/* MPJ subflow are removed from accept queue before reaching here,
* avoid stray wakeups
*/
if (reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue))
return;
parent->sk_data_ready(parent);
return;
}
WARN_ON_ONCE(!__mptcp_check_fallback(msk) && !subflow->mp_capable &&
!subflow->mp_join && !(state & TCPF_CLOSE));
if (mptcp_subflow_data_available(sk))
mptcp_data_ready(parent, sk);
else if (unlikely(sk->sk_err))
subflow_error_report(sk);
}
static void subflow_write_space(struct sock *ssk)
{
struct sock *sk = mptcp_subflow_ctx(ssk)->conn;
mptcp_propagate_sndbuf(sk, ssk);
mptcp_write_space(sk);
}
static struct inet_connection_sock_af_ops *
subflow_default_af_ops(struct sock *sk)
{
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
if (sk->sk_family == AF_INET6)
return &subflow_v6_specific;
#endif
return &subflow_specific;
}
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
void mptcpv6_handle_mapped(struct sock *sk, bool mapped)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_connection_sock_af_ops *target;
target = mapped ? &subflow_v6m_specific : subflow_default_af_ops(sk);
pr_debug("subflow=%p family=%d ops=%p target=%p mapped=%d",
subflow, sk->sk_family, icsk->icsk_af_ops, target, mapped);
if (likely(icsk->icsk_af_ops == target))
return;
subflow->icsk_af_ops = icsk->icsk_af_ops;
icsk->icsk_af_ops = target;
}
#endif
void mptcp_info2sockaddr(const struct mptcp_addr_info *info,
struct sockaddr_storage *addr,
unsigned short family)
{
memset(addr, 0, sizeof(*addr));
addr->ss_family = family;
if (addr->ss_family == AF_INET) {
struct sockaddr_in *in_addr = (struct sockaddr_in *)addr;
if (info->family == AF_INET)
in_addr->sin_addr = info->addr;
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
else if (ipv6_addr_v4mapped(&info->addr6))
in_addr->sin_addr.s_addr = info->addr6.s6_addr32[3];
#endif
in_addr->sin_port = info->port;
}
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
else if (addr->ss_family == AF_INET6) {
struct sockaddr_in6 *in6_addr = (struct sockaddr_in6 *)addr;
if (info->family == AF_INET)
ipv6_addr_set_v4mapped(info->addr.s_addr,
&in6_addr->sin6_addr);
else
in6_addr->sin6_addr = info->addr6;
in6_addr->sin6_port = info->port;
}
#endif
}
int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
const struct mptcp_addr_info *remote)
{
struct mptcp_sock *msk = mptcp_sk(sk);
struct mptcp_subflow_context *subflow;
struct sockaddr_storage addr;
int remote_id = remote->id;
int local_id = loc->id;
struct socket *sf;
struct sock *ssk;
u32 remote_token;
int addrlen;
int ifindex;
u8 flags;
int err;
if (!mptcp_is_fully_established(sk))
return -ENOTCONN;
err = mptcp_subflow_create_socket(sk, &sf);
if (err)
return err;
ssk = sf->sk;
subflow = mptcp_subflow_ctx(ssk);
do {
get_random_bytes(&subflow->local_nonce, sizeof(u32));
} while (!subflow->local_nonce);
if (!local_id) {
err = mptcp_pm_get_local_id(msk, (struct sock_common *)ssk);
if (err < 0)
goto failed;
local_id = err;
}
mptcp_pm_get_flags_and_ifindex_by_id(sock_net(sk), local_id,
&flags, &ifindex);
subflow->remote_key = msk->remote_key;
subflow->local_key = msk->local_key;
subflow->token = msk->token;
mptcp_info2sockaddr(loc, &addr, ssk->sk_family);
addrlen = sizeof(struct sockaddr_in);
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
if (addr.ss_family == AF_INET6)
addrlen = sizeof(struct sockaddr_in6);
#endif
mptcp_sockopt_sync(msk, ssk);
ssk->sk_bound_dev_if = ifindex;
err = kernel_bind(sf, (struct sockaddr *)&addr, addrlen);
if (err)
goto failed;
mptcp_crypto_key_sha(subflow->remote_key, &remote_token, NULL);
pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d", msk,
remote_token, local_id, remote_id);
subflow->remote_token = remote_token;
subflow->local_id = local_id;
subflow->remote_id = remote_id;
subflow->request_join = 1;
subflow->request_bkup = !!(flags & MPTCP_PM_ADDR_FLAG_BACKUP);
mptcp_info2sockaddr(remote, &addr, ssk->sk_family);
sock_hold(ssk);
list_add_tail(&subflow->node, &msk->conn_list);
err = kernel_connect(sf, (struct sockaddr *)&addr, addrlen, O_NONBLOCK);
if (err && err != -EINPROGRESS)
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
goto failed_unlink;
/* discard the subflow socket */
mptcp_sock_graft(ssk, sk->sk_socket);
iput(SOCK_INODE(sf));
return err;
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
failed_unlink:
list_del(&subflow->node);
sock_put(mptcp_subflow_tcp_sock(subflow));
failed:
mptcp: refactor shutdown and close We must not close the subflows before all the MPTCP level data, comprising the DATA_FIN has been acked at the MPTCP level, otherwise we could be unable to retransmit as needed. __mptcp_wr_shutdown() shutdown is responsible to check for the correct status and close all subflows. Is called by the output path after spooling any data and at shutdown/close time. In a similar way, __mptcp_destroy_sock() is responsible to clean-up the MPTCP level status, and is called when the msk transition to TCP_CLOSE. The protocol level close() does not force anymore the TCP_CLOSE status, but orphan the msk socket and all the subflows. Orphaned msk sockets are forciby closed after a timeout or when all MPTCP-level data is acked. There is a caveat about keeping the orphaned subflows around: the TCP stack can asynchronusly call tcp_cleanup_ulp() on them via tcp_close(). To prevent accessing freed memory on later MPTCP level operations, the msk acquires a reference to each subflow socket and prevent subflow_ulp_release() from releasing the subflow context before __mptcp_destroy_sock(). The additional subflow references are released by __mptcp_done() and the async ULP release is detected checking ULP ops. If such field has been already cleared by the ULP release path, the dangling context is freed directly by __mptcp_done(). Co-developed-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-11-16 17:48:09 +08:00
subflow->disposable = 1;
sock_release(sf);
return err;
}
static void mptcp_attach_cgroup(struct sock *parent, struct sock *child)
{
#ifdef CONFIG_SOCK_CGROUP_DATA
struct sock_cgroup_data *parent_skcd = &parent->sk_cgrp_data,
*child_skcd = &child->sk_cgrp_data;
/* only the additional subflows created by kworkers have to be modified */
if (cgroup_id(sock_cgroup_ptr(parent_skcd)) !=
cgroup_id(sock_cgroup_ptr(child_skcd))) {
#ifdef CONFIG_MEMCG
struct mem_cgroup *memcg = parent->sk_memcg;
mem_cgroup_sk_free(child);
if (memcg && css_tryget(&memcg->css))
child->sk_memcg = memcg;
#endif /* CONFIG_MEMCG */
cgroup_sk_free(child_skcd);
*child_skcd = *parent_skcd;
cgroup_sk_clone(child_skcd);
}
#endif /* CONFIG_SOCK_CGROUP_DATA */
}
static void mptcp_subflow_ops_override(struct sock *ssk)
{
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
if (ssk->sk_prot == &tcpv6_prot)
ssk->sk_prot = &tcpv6_prot_override;
else
#endif
ssk->sk_prot = &tcp_prot_override;
}
static void mptcp_subflow_ops_undo_override(struct sock *ssk)
{
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
if (ssk->sk_prot == &tcpv6_prot_override)
ssk->sk_prot = &tcpv6_prot;
else
#endif
ssk->sk_prot = &tcp_prot;
}
int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock)
{
struct mptcp_subflow_context *subflow;
struct net *net = sock_net(sk);
struct socket *sf;
int err;
mptcp: be careful on subflow creation Nicolas reported the following oops: [ 1521.392541] BUG: kernel NULL pointer dereference, address: 00000000000000c0 [ 1521.394189] #PF: supervisor read access in kernel mode [ 1521.395376] #PF: error_code(0x0000) - not-present page [ 1521.396607] PGD 0 P4D 0 [ 1521.397156] Oops: 0000 [#1] SMP PTI [ 1521.398020] CPU: 0 PID: 22986 Comm: kworker/0:2 Not tainted 5.8.0-rc4+ #109 [ 1521.399618] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014 [ 1521.401728] Workqueue: events mptcp_worker [ 1521.402651] RIP: 0010:mptcp_subflow_create_socket+0xf1/0x1c0 [ 1521.403954] Code: 24 08 89 44 24 04 48 8b 7a 18 e8 2a 48 d4 ff 8b 44 24 04 85 c0 75 7a 48 8b 8b 78 02 00 00 48 8b 54 24 08 48 8d bb 80 00 00 00 <48> 8b 89 c0 00 00 00 48 89 8a c0 00 00 00 48 8b 8b 78 02 00 00 8b [ 1521.408201] RSP: 0000:ffffabc4002d3c60 EFLAGS: 00010246 [ 1521.409433] RAX: 0000000000000000 RBX: ffffa0b9ad8c9a00 RCX: 0000000000000000 [ 1521.411096] RDX: ffffa0b9ae78a300 RSI: 00000000fffffe01 RDI: ffffa0b9ad8c9a80 [ 1521.412734] RBP: ffffa0b9adff2e80 R08: ffffa0b9af02d640 R09: ffffa0b9ad923a00 [ 1521.414333] R10: ffffabc4007139f8 R11: fefefefefefefeff R12: ffffabc4002d3cb0 [ 1521.415918] R13: ffffa0b9ad91fa58 R14: ffffa0b9ad8c9f9c R15: 0000000000000000 [ 1521.417592] FS: 0000000000000000(0000) GS:ffffa0b9af000000(0000) knlGS:0000000000000000 [ 1521.419490] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1521.420839] CR2: 00000000000000c0 CR3: 000000002951e006 CR4: 0000000000160ef0 [ 1521.422511] Call Trace: [ 1521.423103] __mptcp_subflow_connect+0x94/0x1f0 [ 1521.425376] mptcp_pm_create_subflow_or_signal_addr+0x200/0x2a0 [ 1521.426736] mptcp_worker+0x31b/0x390 [ 1521.431324] process_one_work+0x1fc/0x3f0 [ 1521.432268] worker_thread+0x2d/0x3b0 [ 1521.434197] kthread+0x117/0x130 [ 1521.435783] ret_from_fork+0x22/0x30 on some unconventional configuration. The MPTCP protocol is trying to create a subflow for an unaccepted server socket. That is allowed by the RFC, even if subflow creation will likely fail. Unaccepted sockets have still a NULL sk_socket field, avoid the issue by failing earlier. Reported-and-tested-by: Nicolas Rybowski <nicolas.rybowski@tessares.net> Fixes: 7d14b0d2b9b3 ("mptcp: set correct vfs info for subflows") Signed-off-by: Paolo Abeni <pabeni@redhat.com> Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-08-05 00:31:06 +08:00
/* un-accepted server sockets can reach here - on bad configuration
* bail early to avoid greater trouble later
*/
if (unlikely(!sk->sk_socket))
return -EINVAL;
err = sock_create_kern(net, sk->sk_family, SOCK_STREAM, IPPROTO_TCP,
&sf);
if (err)
return err;
lock_sock(sf->sk);
/* the newly created socket has to be in the same cgroup as its parent */
mptcp_attach_cgroup(sk, sf->sk);
/* kernel sockets do not by default acquire net ref, but TCP timer
* needs it.
*/
sf->sk->sk_net_refcnt = 1;
mptcp: adjust to use netns refcount tracker MPTCP can change sk_net_refcnt after sock_create_kern() call. We need to change its corresponding get_net() to avoid a splat at release time, as in : refcount_t: decrement hit 0; leaking memory. WARNING: CPU: 0 PID: 3599 at lib/refcount.c:31 refcount_warn_saturate+0xbf/0x1e0 lib/refcount.c:31 Modules linked in: CPU: 1 PID: 3599 Comm: syz-fuzzer Not tainted 5.16.0-rc4-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:refcount_warn_saturate+0xbf/0x1e0 lib/refcount.c:31 Code: 1d b1 99 a1 09 31 ff 89 de e8 5d 3a 9c fd 84 db 75 e0 e8 74 36 9c fd 48 c7 c7 60 00 05 8a c6 05 91 99 a1 09 01 e8 cc 4b 27 05 <0f> 0b eb c4 e8 58 36 9c fd 0f b6 1d 80 99 a1 09 31 ff 89 de e8 28 RSP: 0018:ffffc90001f5fab0 EFLAGS: 00010286 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 RDX: ffff888021873a00 RSI: ffffffff815f1e28 RDI: fffff520003ebf48 RBP: 0000000000000004 R08: 0000000000000000 R09: 0000000000000000 R10: ffffffff815ebbce R11: 0000000000000000 R12: 1ffff920003ebf5b R13: 00000000ffffffef R14: ffffffff8d2fcd94 R15: ffffc90001f5fd10 FS: 000000c00008a090(0000) GS:ffff8880b9d00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f0a5b59e300 CR3: 000000001cbe6000 CR4: 00000000003506e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> __refcount_dec include/linux/refcount.h:344 [inline] refcount_dec include/linux/refcount.h:359 [inline] ref_tracker_free+0x4fe/0x610 lib/ref_tracker.c:101 netns_tracker_free include/net/net_namespace.h:327 [inline] put_net_track include/net/net_namespace.h:341 [inline] __sk_destruct+0x4a6/0x920 net/core/sock.c:2042 sk_destruct+0xbd/0xe0 net/core/sock.c:2058 __sk_free+0xef/0x3d0 net/core/sock.c:2069 sk_free+0x78/0xa0 net/core/sock.c:2080 sock_put include/net/sock.h:1911 [inline] __mptcp_close_ssk+0x435/0x590 net/mptcp/protocol.c:2276 __mptcp_destroy_sock+0x35f/0x830 net/mptcp/protocol.c:2702 mptcp_close+0x5f8/0x7f0 net/mptcp/protocol.c:2750 inet_release+0x12e/0x280 net/ipv4/af_inet.c:428 inet6_release+0x4c/0x70 net/ipv6/af_inet6.c:476 __sock_release+0xcd/0x280 net/socket.c:649 sock_close+0x18/0x20 net/socket.c:1314 __fput+0x286/0x9f0 fs/file_table.c:280 task_work_run+0xdd/0x1a0 kernel/task_work.c:164 tracehook_notify_resume include/linux/tracehook.h:189 [inline] exit_to_user_mode_loop kernel/entry/common.c:175 [inline] exit_to_user_mode_prepare+0x27e/0x290 kernel/entry/common.c:207 __syscall_exit_to_user_mode_work kernel/entry/common.c:289 [inline] syscall_exit_to_user_mode+0x19/0x60 kernel/entry/common.c:300 do_syscall_64+0x42/0xb0 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x44/0xae Fixes: ffa84b5ffb37 ("net: add netns refcount tracker to struct sock") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Cc: Mat Martineau <mathew.j.martineau@linux.intel.com> Cc: Florian Westphal <fw@strlen.de> Acked-by: Paolo Abeni <pabeni@redhat.com> Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net> Link: https://lore.kernel.org/r/20211214043208.3543046-1-eric.dumazet@gmail.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2021-12-14 12:32:08 +08:00
get_net_track(net, &sf->sk->ns_tracker, GFP_KERNEL);
sock_inuse_add(net, 1);
err = tcp_set_ulp(sf->sk, "mptcp");
release_sock(sf->sk);
if (err) {
sock_release(sf);
return err;
}
/* the newly created socket really belongs to the owning MPTCP master
* socket, even if for additional subflows the allocation is performed
* by a kernel workqueue. Adjust inode references, so that the
* procfs/diag interaces really show this one belonging to the correct
* user.
*/
SOCK_INODE(sf)->i_ino = SOCK_INODE(sk->sk_socket)->i_ino;
SOCK_INODE(sf)->i_uid = SOCK_INODE(sk->sk_socket)->i_uid;
SOCK_INODE(sf)->i_gid = SOCK_INODE(sk->sk_socket)->i_gid;
subflow = mptcp_subflow_ctx(sf->sk);
pr_debug("subflow=%p", subflow);
*new_sock = sf;
sock_hold(sk);
subflow->conn = sk;
mptcp_subflow_ops_override(sf->sk);
return 0;
}
static struct mptcp_subflow_context *subflow_create_ctx(struct sock *sk,
gfp_t priority)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct mptcp_subflow_context *ctx;
ctx = kzalloc(sizeof(*ctx), priority);
if (!ctx)
return NULL;
rcu_assign_pointer(icsk->icsk_ulp_data, ctx);
INIT_LIST_HEAD(&ctx->node);
INIT_LIST_HEAD(&ctx->delegated_node);
pr_debug("subflow=%p", ctx);
ctx->tcp_sock = sk;
return ctx;
}
static void __subflow_state_change(struct sock *sk)
{
struct socket_wq *wq;
rcu_read_lock();
wq = rcu_dereference(sk->sk_wq);
if (skwq_has_sleeper(wq))
wake_up_interruptible_all(&wq->wait);
rcu_read_unlock();
}
static bool subflow_is_done(const struct sock *sk)
{
return sk->sk_shutdown & RCV_SHUTDOWN || sk->sk_state == TCP_CLOSE;
}
static void subflow_state_change(struct sock *sk)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct sock *parent = subflow->conn;
__subflow_state_change(sk);
mptcp: fallback in case of simultaneous connect when a MPTCP client tries to connect to itself, tcp_finish_connect() is never reached. Because of this, depending on the socket current state, multiple faulty behaviours can be observed: 1) a WARN_ON() in subflow_data_ready() is hit WARNING: CPU: 2 PID: 882 at net/mptcp/subflow.c:911 subflow_data_ready+0x18b/0x230 [...] CPU: 2 PID: 882 Comm: gh35 Not tainted 5.7.0+ #187 [...] RIP: 0010:subflow_data_ready+0x18b/0x230 [...] Call Trace: tcp_data_queue+0xd2f/0x4250 tcp_rcv_state_process+0xb1c/0x49d3 tcp_v4_do_rcv+0x2bc/0x790 __release_sock+0x153/0x2d0 release_sock+0x4f/0x170 mptcp_shutdown+0x167/0x4e0 __sys_shutdown+0xe6/0x180 __x64_sys_shutdown+0x50/0x70 do_syscall_64+0x9a/0x370 entry_SYSCALL_64_after_hwframe+0x44/0xa9 2) client is stuck forever in mptcp_sendmsg() because the socket is not TCP_ESTABLISHED crash> bt 4847 PID: 4847 TASK: ffff88814b2fb100 CPU: 1 COMMAND: "gh35" #0 [ffff8881376ff680] __schedule at ffffffff97248da4 #1 [ffff8881376ff778] schedule at ffffffff9724a34f #2 [ffff8881376ff7a0] schedule_timeout at ffffffff97252ba0 #3 [ffff8881376ff8a8] wait_woken at ffffffff958ab4ba #4 [ffff8881376ff940] sk_stream_wait_connect at ffffffff96c2d859 #5 [ffff8881376ffa28] mptcp_sendmsg at ffffffff97207fca #6 [ffff8881376ffbc0] sock_sendmsg at ffffffff96be1b5b #7 [ffff8881376ffbe8] sock_write_iter at ffffffff96be1daa #8 [ffff8881376ffce8] new_sync_write at ffffffff95e5cb52 #9 [ffff8881376ffe50] vfs_write at ffffffff95e6547f #10 [ffff8881376ffe90] ksys_write at ffffffff95e65d26 #11 [ffff8881376fff28] do_syscall_64 at ffffffff956088ba #12 [ffff8881376fff50] entry_SYSCALL_64_after_hwframe at ffffffff9740008c RIP: 00007f126f6956ed RSP: 00007ffc2a320278 RFLAGS: 00000217 RAX: ffffffffffffffda RBX: 0000000020000044 RCX: 00007f126f6956ed RDX: 0000000000000004 RSI: 00000000004007b8 RDI: 0000000000000003 RBP: 00007ffc2a3202a0 R8: 0000000000400720 R9: 0000000000400720 R10: 0000000000400720 R11: 0000000000000217 R12: 00000000004004b0 R13: 00007ffc2a320380 R14: 0000000000000000 R15: 0000000000000000 ORIG_RAX: 0000000000000001 CS: 0033 SS: 002b 3) tcpdump captures show that DSS is exchanged even when MP_CAPABLE handshake didn't complete. $ tcpdump -tnnr bad.pcap IP 127.0.0.1.20000 > 127.0.0.1.20000: Flags [S], seq 3208913911, win 65483, options [mss 65495,sackOK,TS val 3291706876 ecr 3291694721,nop,wscale 7,mptcp capable v1], length 0 IP 127.0.0.1.20000 > 127.0.0.1.20000: Flags [S.], seq 3208913911, ack 3208913912, win 65483, options [mss 65495,sackOK,TS val 3291706876 ecr 3291706876,nop,wscale 7,mptcp capable v1], length 0 IP 127.0.0.1.20000 > 127.0.0.1.20000: Flags [.], ack 1, win 512, options [nop,nop,TS val 3291706876 ecr 3291706876], length 0 IP 127.0.0.1.20000 > 127.0.0.1.20000: Flags [F.], seq 1, ack 1, win 512, options [nop,nop,TS val 3291707876 ecr 3291706876,mptcp dss fin seq 0 subseq 0 len 1,nop,nop], length 0 IP 127.0.0.1.20000 > 127.0.0.1.20000: Flags [.], ack 2, win 512, options [nop,nop,TS val 3291707876 ecr 3291707876], length 0 force a fallback to TCP in these cases, and adjust the main socket state to avoid hanging in mptcp_sendmsg(). Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/35 Reported-by: Christoph Paasch <cpaasch@apple.com> Suggested-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-06-30 04:26:21 +08:00
if (subflow_simultaneous_connect(sk)) {
mptcp_propagate_sndbuf(parent, sk);
mptcp: fallback in case of simultaneous connect when a MPTCP client tries to connect to itself, tcp_finish_connect() is never reached. Because of this, depending on the socket current state, multiple faulty behaviours can be observed: 1) a WARN_ON() in subflow_data_ready() is hit WARNING: CPU: 2 PID: 882 at net/mptcp/subflow.c:911 subflow_data_ready+0x18b/0x230 [...] CPU: 2 PID: 882 Comm: gh35 Not tainted 5.7.0+ #187 [...] RIP: 0010:subflow_data_ready+0x18b/0x230 [...] Call Trace: tcp_data_queue+0xd2f/0x4250 tcp_rcv_state_process+0xb1c/0x49d3 tcp_v4_do_rcv+0x2bc/0x790 __release_sock+0x153/0x2d0 release_sock+0x4f/0x170 mptcp_shutdown+0x167/0x4e0 __sys_shutdown+0xe6/0x180 __x64_sys_shutdown+0x50/0x70 do_syscall_64+0x9a/0x370 entry_SYSCALL_64_after_hwframe+0x44/0xa9 2) client is stuck forever in mptcp_sendmsg() because the socket is not TCP_ESTABLISHED crash> bt 4847 PID: 4847 TASK: ffff88814b2fb100 CPU: 1 COMMAND: "gh35" #0 [ffff8881376ff680] __schedule at ffffffff97248da4 #1 [ffff8881376ff778] schedule at ffffffff9724a34f #2 [ffff8881376ff7a0] schedule_timeout at ffffffff97252ba0 #3 [ffff8881376ff8a8] wait_woken at ffffffff958ab4ba #4 [ffff8881376ff940] sk_stream_wait_connect at ffffffff96c2d859 #5 [ffff8881376ffa28] mptcp_sendmsg at ffffffff97207fca #6 [ffff8881376ffbc0] sock_sendmsg at ffffffff96be1b5b #7 [ffff8881376ffbe8] sock_write_iter at ffffffff96be1daa #8 [ffff8881376ffce8] new_sync_write at ffffffff95e5cb52 #9 [ffff8881376ffe50] vfs_write at ffffffff95e6547f #10 [ffff8881376ffe90] ksys_write at ffffffff95e65d26 #11 [ffff8881376fff28] do_syscall_64 at ffffffff956088ba #12 [ffff8881376fff50] entry_SYSCALL_64_after_hwframe at ffffffff9740008c RIP: 00007f126f6956ed RSP: 00007ffc2a320278 RFLAGS: 00000217 RAX: ffffffffffffffda RBX: 0000000020000044 RCX: 00007f126f6956ed RDX: 0000000000000004 RSI: 00000000004007b8 RDI: 0000000000000003 RBP: 00007ffc2a3202a0 R8: 0000000000400720 R9: 0000000000400720 R10: 0000000000400720 R11: 0000000000000217 R12: 00000000004004b0 R13: 00007ffc2a320380 R14: 0000000000000000 R15: 0000000000000000 ORIG_RAX: 0000000000000001 CS: 0033 SS: 002b 3) tcpdump captures show that DSS is exchanged even when MP_CAPABLE handshake didn't complete. $ tcpdump -tnnr bad.pcap IP 127.0.0.1.20000 > 127.0.0.1.20000: Flags [S], seq 3208913911, win 65483, options [mss 65495,sackOK,TS val 3291706876 ecr 3291694721,nop,wscale 7,mptcp capable v1], length 0 IP 127.0.0.1.20000 > 127.0.0.1.20000: Flags [S.], seq 3208913911, ack 3208913912, win 65483, options [mss 65495,sackOK,TS val 3291706876 ecr 3291706876,nop,wscale 7,mptcp capable v1], length 0 IP 127.0.0.1.20000 > 127.0.0.1.20000: Flags [.], ack 1, win 512, options [nop,nop,TS val 3291706876 ecr 3291706876], length 0 IP 127.0.0.1.20000 > 127.0.0.1.20000: Flags [F.], seq 1, ack 1, win 512, options [nop,nop,TS val 3291707876 ecr 3291706876,mptcp dss fin seq 0 subseq 0 len 1,nop,nop], length 0 IP 127.0.0.1.20000 > 127.0.0.1.20000: Flags [.], ack 2, win 512, options [nop,nop,TS val 3291707876 ecr 3291707876], length 0 force a fallback to TCP in these cases, and adjust the main socket state to avoid hanging in mptcp_sendmsg(). Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/35 Reported-by: Christoph Paasch <cpaasch@apple.com> Suggested-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-06-30 04:26:21 +08:00
mptcp_do_fallback(sk);
mptcp: add receive buffer auto-tuning When mptcp is used, userspace doesn't read from the tcp (subflow) socket but from the parent (mptcp) socket receive queue. skbs are moved from the subflow socket to the mptcp rx queue either from 'data_ready' callback (if mptcp socket can be locked), a work queue, or the socket receive function. This means tcp_rcv_space_adjust() is never called and thus no receive buffer size auto-tuning is done. An earlier (not merged) patch added tcp_rcv_space_adjust() calls to the function that moves skbs from subflow to mptcp socket. While this enabled autotuning, it also meant tuning was done even if userspace was reading the mptcp socket very slowly. This adds mptcp_rcv_space_adjust() and calls it after userspace has read data from the mptcp socket rx queue. Its very similar to tcp_rcv_space_adjust, with two differences: 1. The rtt estimate is the largest one observed on a subflow 2. The rcvbuf size and window clamp of all subflows is adjusted to the mptcp-level rcvbuf. Otherwise, we get spurious drops at tcp (subflow) socket level if the skbs are not moved to the mptcp socket fast enough. Before: time mptcp_connect.sh -t -f $((4*1024*1024)) -d 300 -l 0.01% -r 0 -e "" -m mmap [..] ns4 MPTCP -> ns3 (10.0.3.2:10108 ) MPTCP (duration 40823ms) [ OK ] ns4 MPTCP -> ns3 (10.0.3.2:10109 ) TCP (duration 23119ms) [ OK ] ns4 TCP -> ns3 (10.0.3.2:10110 ) MPTCP (duration 5421ms) [ OK ] ns4 MPTCP -> ns3 (dead:beef:3::2:10111) MPTCP (duration 41446ms) [ OK ] ns4 MPTCP -> ns3 (dead:beef:3::2:10112) TCP (duration 23427ms) [ OK ] ns4 TCP -> ns3 (dead:beef:3::2:10113) MPTCP (duration 5426ms) [ OK ] Time: 1396 seconds After: ns4 MPTCP -> ns3 (10.0.3.2:10108 ) MPTCP (duration 5417ms) [ OK ] ns4 MPTCP -> ns3 (10.0.3.2:10109 ) TCP (duration 5427ms) [ OK ] ns4 TCP -> ns3 (10.0.3.2:10110 ) MPTCP (duration 5422ms) [ OK ] ns4 MPTCP -> ns3 (dead:beef:3::2:10111) MPTCP (duration 5415ms) [ OK ] ns4 MPTCP -> ns3 (dead:beef:3::2:10112) TCP (duration 5422ms) [ OK ] ns4 TCP -> ns3 (dead:beef:3::2:10113) MPTCP (duration 5423ms) [ OK ] Time: 296 seconds Signed-off-by: Florian Westphal <fw@strlen.de> Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-07-01 03:24:45 +08:00
mptcp_rcv_space_init(mptcp_sk(parent), sk);
mptcp: fallback in case of simultaneous connect when a MPTCP client tries to connect to itself, tcp_finish_connect() is never reached. Because of this, depending on the socket current state, multiple faulty behaviours can be observed: 1) a WARN_ON() in subflow_data_ready() is hit WARNING: CPU: 2 PID: 882 at net/mptcp/subflow.c:911 subflow_data_ready+0x18b/0x230 [...] CPU: 2 PID: 882 Comm: gh35 Not tainted 5.7.0+ #187 [...] RIP: 0010:subflow_data_ready+0x18b/0x230 [...] Call Trace: tcp_data_queue+0xd2f/0x4250 tcp_rcv_state_process+0xb1c/0x49d3 tcp_v4_do_rcv+0x2bc/0x790 __release_sock+0x153/0x2d0 release_sock+0x4f/0x170 mptcp_shutdown+0x167/0x4e0 __sys_shutdown+0xe6/0x180 __x64_sys_shutdown+0x50/0x70 do_syscall_64+0x9a/0x370 entry_SYSCALL_64_after_hwframe+0x44/0xa9 2) client is stuck forever in mptcp_sendmsg() because the socket is not TCP_ESTABLISHED crash> bt 4847 PID: 4847 TASK: ffff88814b2fb100 CPU: 1 COMMAND: "gh35" #0 [ffff8881376ff680] __schedule at ffffffff97248da4 #1 [ffff8881376ff778] schedule at ffffffff9724a34f #2 [ffff8881376ff7a0] schedule_timeout at ffffffff97252ba0 #3 [ffff8881376ff8a8] wait_woken at ffffffff958ab4ba #4 [ffff8881376ff940] sk_stream_wait_connect at ffffffff96c2d859 #5 [ffff8881376ffa28] mptcp_sendmsg at ffffffff97207fca #6 [ffff8881376ffbc0] sock_sendmsg at ffffffff96be1b5b #7 [ffff8881376ffbe8] sock_write_iter at ffffffff96be1daa #8 [ffff8881376ffce8] new_sync_write at ffffffff95e5cb52 #9 [ffff8881376ffe50] vfs_write at ffffffff95e6547f #10 [ffff8881376ffe90] ksys_write at ffffffff95e65d26 #11 [ffff8881376fff28] do_syscall_64 at ffffffff956088ba #12 [ffff8881376fff50] entry_SYSCALL_64_after_hwframe at ffffffff9740008c RIP: 00007f126f6956ed RSP: 00007ffc2a320278 RFLAGS: 00000217 RAX: ffffffffffffffda RBX: 0000000020000044 RCX: 00007f126f6956ed RDX: 0000000000000004 RSI: 00000000004007b8 RDI: 0000000000000003 RBP: 00007ffc2a3202a0 R8: 0000000000400720 R9: 0000000000400720 R10: 0000000000400720 R11: 0000000000000217 R12: 00000000004004b0 R13: 00007ffc2a320380 R14: 0000000000000000 R15: 0000000000000000 ORIG_RAX: 0000000000000001 CS: 0033 SS: 002b 3) tcpdump captures show that DSS is exchanged even when MP_CAPABLE handshake didn't complete. $ tcpdump -tnnr bad.pcap IP 127.0.0.1.20000 > 127.0.0.1.20000: Flags [S], seq 3208913911, win 65483, options [mss 65495,sackOK,TS val 3291706876 ecr 3291694721,nop,wscale 7,mptcp capable v1], length 0 IP 127.0.0.1.20000 > 127.0.0.1.20000: Flags [S.], seq 3208913911, ack 3208913912, win 65483, options [mss 65495,sackOK,TS val 3291706876 ecr 3291706876,nop,wscale 7,mptcp capable v1], length 0 IP 127.0.0.1.20000 > 127.0.0.1.20000: Flags [.], ack 1, win 512, options [nop,nop,TS val 3291706876 ecr 3291706876], length 0 IP 127.0.0.1.20000 > 127.0.0.1.20000: Flags [F.], seq 1, ack 1, win 512, options [nop,nop,TS val 3291707876 ecr 3291706876,mptcp dss fin seq 0 subseq 0 len 1,nop,nop], length 0 IP 127.0.0.1.20000 > 127.0.0.1.20000: Flags [.], ack 2, win 512, options [nop,nop,TS val 3291707876 ecr 3291707876], length 0 force a fallback to TCP in these cases, and adjust the main socket state to avoid hanging in mptcp_sendmsg(). Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/35 Reported-by: Christoph Paasch <cpaasch@apple.com> Suggested-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-06-30 04:26:21 +08:00
pr_fallback(mptcp_sk(parent));
subflow->conn_finished = 1;
mptcp_set_connected(parent);
mptcp: fallback in case of simultaneous connect when a MPTCP client tries to connect to itself, tcp_finish_connect() is never reached. Because of this, depending on the socket current state, multiple faulty behaviours can be observed: 1) a WARN_ON() in subflow_data_ready() is hit WARNING: CPU: 2 PID: 882 at net/mptcp/subflow.c:911 subflow_data_ready+0x18b/0x230 [...] CPU: 2 PID: 882 Comm: gh35 Not tainted 5.7.0+ #187 [...] RIP: 0010:subflow_data_ready+0x18b/0x230 [...] Call Trace: tcp_data_queue+0xd2f/0x4250 tcp_rcv_state_process+0xb1c/0x49d3 tcp_v4_do_rcv+0x2bc/0x790 __release_sock+0x153/0x2d0 release_sock+0x4f/0x170 mptcp_shutdown+0x167/0x4e0 __sys_shutdown+0xe6/0x180 __x64_sys_shutdown+0x50/0x70 do_syscall_64+0x9a/0x370 entry_SYSCALL_64_after_hwframe+0x44/0xa9 2) client is stuck forever in mptcp_sendmsg() because the socket is not TCP_ESTABLISHED crash> bt 4847 PID: 4847 TASK: ffff88814b2fb100 CPU: 1 COMMAND: "gh35" #0 [ffff8881376ff680] __schedule at ffffffff97248da4 #1 [ffff8881376ff778] schedule at ffffffff9724a34f #2 [ffff8881376ff7a0] schedule_timeout at ffffffff97252ba0 #3 [ffff8881376ff8a8] wait_woken at ffffffff958ab4ba #4 [ffff8881376ff940] sk_stream_wait_connect at ffffffff96c2d859 #5 [ffff8881376ffa28] mptcp_sendmsg at ffffffff97207fca #6 [ffff8881376ffbc0] sock_sendmsg at ffffffff96be1b5b #7 [ffff8881376ffbe8] sock_write_iter at ffffffff96be1daa #8 [ffff8881376ffce8] new_sync_write at ffffffff95e5cb52 #9 [ffff8881376ffe50] vfs_write at ffffffff95e6547f #10 [ffff8881376ffe90] ksys_write at ffffffff95e65d26 #11 [ffff8881376fff28] do_syscall_64 at ffffffff956088ba #12 [ffff8881376fff50] entry_SYSCALL_64_after_hwframe at ffffffff9740008c RIP: 00007f126f6956ed RSP: 00007ffc2a320278 RFLAGS: 00000217 RAX: ffffffffffffffda RBX: 0000000020000044 RCX: 00007f126f6956ed RDX: 0000000000000004 RSI: 00000000004007b8 RDI: 0000000000000003 RBP: 00007ffc2a3202a0 R8: 0000000000400720 R9: 0000000000400720 R10: 0000000000400720 R11: 0000000000000217 R12: 00000000004004b0 R13: 00007ffc2a320380 R14: 0000000000000000 R15: 0000000000000000 ORIG_RAX: 0000000000000001 CS: 0033 SS: 002b 3) tcpdump captures show that DSS is exchanged even when MP_CAPABLE handshake didn't complete. $ tcpdump -tnnr bad.pcap IP 127.0.0.1.20000 > 127.0.0.1.20000: Flags [S], seq 3208913911, win 65483, options [mss 65495,sackOK,TS val 3291706876 ecr 3291694721,nop,wscale 7,mptcp capable v1], length 0 IP 127.0.0.1.20000 > 127.0.0.1.20000: Flags [S.], seq 3208913911, ack 3208913912, win 65483, options [mss 65495,sackOK,TS val 3291706876 ecr 3291706876,nop,wscale 7,mptcp capable v1], length 0 IP 127.0.0.1.20000 > 127.0.0.1.20000: Flags [.], ack 1, win 512, options [nop,nop,TS val 3291706876 ecr 3291706876], length 0 IP 127.0.0.1.20000 > 127.0.0.1.20000: Flags [F.], seq 1, ack 1, win 512, options [nop,nop,TS val 3291707876 ecr 3291706876,mptcp dss fin seq 0 subseq 0 len 1,nop,nop], length 0 IP 127.0.0.1.20000 > 127.0.0.1.20000: Flags [.], ack 2, win 512, options [nop,nop,TS val 3291707876 ecr 3291707876], length 0 force a fallback to TCP in these cases, and adjust the main socket state to avoid hanging in mptcp_sendmsg(). Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/35 Reported-by: Christoph Paasch <cpaasch@apple.com> Suggested-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-06-30 04:26:21 +08:00
}
/* as recvmsg() does not acquire the subflow socket for ssk selection
* a fin packet carrying a DSS can be unnoticed if we don't trigger
* the data available machinery here.
*/
if (mptcp_subflow_data_available(sk))
mptcp_data_ready(parent, sk);
mptcp: fix soft lookup in subflow_error_report() Maxim reported a soft lookup in subflow_error_report(): watchdog: BUG: soft lockup - CPU#0 stuck for 22s! [swapper/0:0] RIP: 0010:native_queued_spin_lock_slowpath RSP: 0018:ffffa859c0003bc0 EFLAGS: 00000202 RAX: 0000000000000101 RBX: 0000000000000001 RCX: 0000000000000000 RDX: ffff9195c2772d88 RSI: 0000000000000000 RDI: ffff9195c2772d88 RBP: ffff9195c2772d00 R08: 00000000000067b0 R09: c6e31da9eb1e44f4 R10: ffff9195ef379700 R11: ffff9195edb50710 R12: ffff9195c2772d88 R13: ffff9195f500e3d0 R14: ffff9195ef379700 R15: ffff9195ef379700 FS: 0000000000000000(0000) GS:ffff91961f400000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000c000407000 CR3: 0000000002988000 CR4: 00000000000006f0 Call Trace: <IRQ> _raw_spin_lock_bh subflow_error_report mptcp_subflow_data_available __mptcp_move_skbs_from_subflow mptcp_data_ready tcp_data_queue tcp_rcv_established tcp_v4_do_rcv tcp_v4_rcv ip_protocol_deliver_rcu ip_local_deliver_finish __netif_receive_skb_one_core netif_receive_skb rtl8139_poll 8139too __napi_poll net_rx_action __do_softirq __irq_exit_rcu common_interrupt </IRQ> The calling function - mptcp_subflow_data_available() - can be invoked from different contexts: - plain ssk socket lock - ssk socket lock + mptcp_data_lock - ssk socket lock + mptcp_data_lock + msk socket lock. Since subflow_error_report() tries to acquire the mptcp_data_lock, the latter two call chains will cause soft lookup. This change addresses the issue moving the error reporting call to outer functions, where the held locks list is known and the we can acquire only the needed one. Reported-by: Maxim Galaganov <max@internet.ru> Fixes: 15cc10453398 ("mptcp: deliver ssk errors to msk") Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/199 Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-06-11 06:59:44 +08:00
else if (unlikely(sk->sk_err))
subflow_error_report(sk);
subflow_sched_work_if_closed(mptcp_sk(parent), sk);
if (__mptcp_check_fallback(mptcp_sk(parent)) &&
!subflow->rx_eof && subflow_is_done(sk)) {
subflow->rx_eof = 1;
mptcp_subflow_eof(parent);
}
}
static int subflow_ulp_init(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct mptcp_subflow_context *ctx;
struct tcp_sock *tp = tcp_sk(sk);
int err = 0;
/* disallow attaching ULP to a socket unless it has been
* created with sock_create_kern()
*/
if (!sk->sk_kern_sock) {
err = -EOPNOTSUPP;
goto out;
}
ctx = subflow_create_ctx(sk, GFP_KERNEL);
if (!ctx) {
err = -ENOMEM;
goto out;
}
pr_debug("subflow=%p, family=%d", ctx, sk->sk_family);
tp->is_mptcp = 1;
ctx->icsk_af_ops = icsk->icsk_af_ops;
icsk->icsk_af_ops = subflow_default_af_ops(sk);
ctx->tcp_data_ready = sk->sk_data_ready;
ctx->tcp_state_change = sk->sk_state_change;
ctx->tcp_write_space = sk->sk_write_space;
ctx->tcp_error_report = sk->sk_error_report;
sk->sk_data_ready = subflow_data_ready;
sk->sk_write_space = subflow_write_space;
sk->sk_state_change = subflow_state_change;
sk->sk_error_report = subflow_error_report;
out:
return err;
}
mptcp: refactor shutdown and close We must not close the subflows before all the MPTCP level data, comprising the DATA_FIN has been acked at the MPTCP level, otherwise we could be unable to retransmit as needed. __mptcp_wr_shutdown() shutdown is responsible to check for the correct status and close all subflows. Is called by the output path after spooling any data and at shutdown/close time. In a similar way, __mptcp_destroy_sock() is responsible to clean-up the MPTCP level status, and is called when the msk transition to TCP_CLOSE. The protocol level close() does not force anymore the TCP_CLOSE status, but orphan the msk socket and all the subflows. Orphaned msk sockets are forciby closed after a timeout or when all MPTCP-level data is acked. There is a caveat about keeping the orphaned subflows around: the TCP stack can asynchronusly call tcp_cleanup_ulp() on them via tcp_close(). To prevent accessing freed memory on later MPTCP level operations, the msk acquires a reference to each subflow socket and prevent subflow_ulp_release() from releasing the subflow context before __mptcp_destroy_sock(). The additional subflow references are released by __mptcp_done() and the async ULP release is detected checking ULP ops. If such field has been already cleared by the ULP release path, the dangling context is freed directly by __mptcp_done(). Co-developed-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-11-16 17:48:09 +08:00
static void subflow_ulp_release(struct sock *ssk)
{
mptcp: refactor shutdown and close We must not close the subflows before all the MPTCP level data, comprising the DATA_FIN has been acked at the MPTCP level, otherwise we could be unable to retransmit as needed. __mptcp_wr_shutdown() shutdown is responsible to check for the correct status and close all subflows. Is called by the output path after spooling any data and at shutdown/close time. In a similar way, __mptcp_destroy_sock() is responsible to clean-up the MPTCP level status, and is called when the msk transition to TCP_CLOSE. The protocol level close() does not force anymore the TCP_CLOSE status, but orphan the msk socket and all the subflows. Orphaned msk sockets are forciby closed after a timeout or when all MPTCP-level data is acked. There is a caveat about keeping the orphaned subflows around: the TCP stack can asynchronusly call tcp_cleanup_ulp() on them via tcp_close(). To prevent accessing freed memory on later MPTCP level operations, the msk acquires a reference to each subflow socket and prevent subflow_ulp_release() from releasing the subflow context before __mptcp_destroy_sock(). The additional subflow references are released by __mptcp_done() and the async ULP release is detected checking ULP ops. If such field has been already cleared by the ULP release path, the dangling context is freed directly by __mptcp_done(). Co-developed-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-11-16 17:48:09 +08:00
struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(ssk);
bool release = true;
struct sock *sk;
if (!ctx)
return;
mptcp: refactor shutdown and close We must not close the subflows before all the MPTCP level data, comprising the DATA_FIN has been acked at the MPTCP level, otherwise we could be unable to retransmit as needed. __mptcp_wr_shutdown() shutdown is responsible to check for the correct status and close all subflows. Is called by the output path after spooling any data and at shutdown/close time. In a similar way, __mptcp_destroy_sock() is responsible to clean-up the MPTCP level status, and is called when the msk transition to TCP_CLOSE. The protocol level close() does not force anymore the TCP_CLOSE status, but orphan the msk socket and all the subflows. Orphaned msk sockets are forciby closed after a timeout or when all MPTCP-level data is acked. There is a caveat about keeping the orphaned subflows around: the TCP stack can asynchronusly call tcp_cleanup_ulp() on them via tcp_close(). To prevent accessing freed memory on later MPTCP level operations, the msk acquires a reference to each subflow socket and prevent subflow_ulp_release() from releasing the subflow context before __mptcp_destroy_sock(). The additional subflow references are released by __mptcp_done() and the async ULP release is detected checking ULP ops. If such field has been already cleared by the ULP release path, the dangling context is freed directly by __mptcp_done(). Co-developed-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-11-16 17:48:09 +08:00
sk = ctx->conn;
if (sk) {
/* if the msk has been orphaned, keep the ctx
* alive, will be freed by __mptcp_close_ssk(),
* when the subflow is still unaccepted
mptcp: refactor shutdown and close We must not close the subflows before all the MPTCP level data, comprising the DATA_FIN has been acked at the MPTCP level, otherwise we could be unable to retransmit as needed. __mptcp_wr_shutdown() shutdown is responsible to check for the correct status and close all subflows. Is called by the output path after spooling any data and at shutdown/close time. In a similar way, __mptcp_destroy_sock() is responsible to clean-up the MPTCP level status, and is called when the msk transition to TCP_CLOSE. The protocol level close() does not force anymore the TCP_CLOSE status, but orphan the msk socket and all the subflows. Orphaned msk sockets are forciby closed after a timeout or when all MPTCP-level data is acked. There is a caveat about keeping the orphaned subflows around: the TCP stack can asynchronusly call tcp_cleanup_ulp() on them via tcp_close(). To prevent accessing freed memory on later MPTCP level operations, the msk acquires a reference to each subflow socket and prevent subflow_ulp_release() from releasing the subflow context before __mptcp_destroy_sock(). The additional subflow references are released by __mptcp_done() and the async ULP release is detected checking ULP ops. If such field has been already cleared by the ULP release path, the dangling context is freed directly by __mptcp_done(). Co-developed-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-11-16 17:48:09 +08:00
*/
release = ctx->disposable || list_empty(&ctx->node);
mptcp: refactor shutdown and close We must not close the subflows before all the MPTCP level data, comprising the DATA_FIN has been acked at the MPTCP level, otherwise we could be unable to retransmit as needed. __mptcp_wr_shutdown() shutdown is responsible to check for the correct status and close all subflows. Is called by the output path after spooling any data and at shutdown/close time. In a similar way, __mptcp_destroy_sock() is responsible to clean-up the MPTCP level status, and is called when the msk transition to TCP_CLOSE. The protocol level close() does not force anymore the TCP_CLOSE status, but orphan the msk socket and all the subflows. Orphaned msk sockets are forciby closed after a timeout or when all MPTCP-level data is acked. There is a caveat about keeping the orphaned subflows around: the TCP stack can asynchronusly call tcp_cleanup_ulp() on them via tcp_close(). To prevent accessing freed memory on later MPTCP level operations, the msk acquires a reference to each subflow socket and prevent subflow_ulp_release() from releasing the subflow context before __mptcp_destroy_sock(). The additional subflow references are released by __mptcp_done() and the async ULP release is detected checking ULP ops. If such field has been already cleared by the ULP release path, the dangling context is freed directly by __mptcp_done(). Co-developed-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-11-16 17:48:09 +08:00
sock_put(sk);
}
mptcp_subflow_ops_undo_override(ssk);
mptcp: refactor shutdown and close We must not close the subflows before all the MPTCP level data, comprising the DATA_FIN has been acked at the MPTCP level, otherwise we could be unable to retransmit as needed. __mptcp_wr_shutdown() shutdown is responsible to check for the correct status and close all subflows. Is called by the output path after spooling any data and at shutdown/close time. In a similar way, __mptcp_destroy_sock() is responsible to clean-up the MPTCP level status, and is called when the msk transition to TCP_CLOSE. The protocol level close() does not force anymore the TCP_CLOSE status, but orphan the msk socket and all the subflows. Orphaned msk sockets are forciby closed after a timeout or when all MPTCP-level data is acked. There is a caveat about keeping the orphaned subflows around: the TCP stack can asynchronusly call tcp_cleanup_ulp() on them via tcp_close(). To prevent accessing freed memory on later MPTCP level operations, the msk acquires a reference to each subflow socket and prevent subflow_ulp_release() from releasing the subflow context before __mptcp_destroy_sock(). The additional subflow references are released by __mptcp_done() and the async ULP release is detected checking ULP ops. If such field has been already cleared by the ULP release path, the dangling context is freed directly by __mptcp_done(). Co-developed-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-11-16 17:48:09 +08:00
if (release)
kfree_rcu(ctx, rcu);
}
static void subflow_ulp_clone(const struct request_sock *req,
struct sock *newsk,
const gfp_t priority)
{
struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
struct mptcp_subflow_context *old_ctx = mptcp_subflow_ctx(newsk);
struct mptcp_subflow_context *new_ctx;
if (!tcp_rsk(req)->is_mptcp ||
(!subflow_req->mp_capable && !subflow_req->mp_join)) {
subflow_ulp_fallback(newsk, old_ctx);
return;
}
new_ctx = subflow_create_ctx(newsk, priority);
if (!new_ctx) {
subflow_ulp_fallback(newsk, old_ctx);
return;
}
new_ctx->conn_finished = 1;
new_ctx->icsk_af_ops = old_ctx->icsk_af_ops;
new_ctx->tcp_data_ready = old_ctx->tcp_data_ready;
new_ctx->tcp_state_change = old_ctx->tcp_state_change;
new_ctx->tcp_write_space = old_ctx->tcp_write_space;
new_ctx->tcp_error_report = old_ctx->tcp_error_report;
new_ctx->rel_write_seq = 1;
new_ctx->tcp_sock = newsk;
if (subflow_req->mp_capable) {
/* see comments in subflow_syn_recv_sock(), MPTCP connection
* is fully established only after we receive the remote key
*/
new_ctx->mp_capable = 1;
new_ctx->local_key = subflow_req->local_key;
new_ctx->token = subflow_req->token;
new_ctx->ssn_offset = subflow_req->ssn_offset;
new_ctx->idsn = subflow_req->idsn;
} else if (subflow_req->mp_join) {
new_ctx->ssn_offset = subflow_req->ssn_offset;
new_ctx->mp_join = 1;
new_ctx->fully_established = 1;
new_ctx->backup = subflow_req->backup;
new_ctx->local_id = subflow_req->local_id;
new_ctx->remote_id = subflow_req->remote_id;
new_ctx->token = subflow_req->token;
new_ctx->thmac = subflow_req->thmac;
}
}
static void tcp_release_cb_override(struct sock *ssk)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
if (mptcp_subflow_has_delegated_action(subflow))
mptcp_subflow_process_delegated(ssk);
tcp_release_cb(ssk);
}
static struct tcp_ulp_ops subflow_ulp_ops __read_mostly = {
.name = "mptcp",
.owner = THIS_MODULE,
.init = subflow_ulp_init,
.release = subflow_ulp_release,
.clone = subflow_ulp_clone,
};
static int subflow_ops_init(struct request_sock_ops *subflow_ops)
{
subflow_ops->obj_size = sizeof(struct mptcp_subflow_request_sock);
subflow_ops->slab_name = "request_sock_subflow";
subflow_ops->slab = kmem_cache_create(subflow_ops->slab_name,
subflow_ops->obj_size, 0,
SLAB_ACCOUNT |
SLAB_TYPESAFE_BY_RCU,
NULL);
if (!subflow_ops->slab)
return -ENOMEM;
subflow_ops->destructor = subflow_req_destructor;
return 0;
}
void __init mptcp_subflow_init(void)
{
mptcp_subflow_request_sock_ops = tcp_request_sock_ops;
if (subflow_ops_init(&mptcp_subflow_request_sock_ops) != 0)
panic("MPTCP: failed to init subflow request sock ops\n");
subflow_request_sock_ipv4_ops = tcp_request_sock_ipv4_ops;
subflow_request_sock_ipv4_ops.route_req = subflow_v4_route_req;
subflow_specific = ipv4_specific;
subflow_specific.conn_request = subflow_v4_conn_request;
subflow_specific.syn_recv_sock = subflow_syn_recv_sock;
subflow_specific.sk_rx_dst_set = subflow_finish_connect;
tcp_prot_override = tcp_prot;
tcp_prot_override.release_cb = tcp_release_cb_override;
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
subflow_request_sock_ipv6_ops = tcp_request_sock_ipv6_ops;
subflow_request_sock_ipv6_ops.route_req = subflow_v6_route_req;
subflow_v6_specific = ipv6_specific;
subflow_v6_specific.conn_request = subflow_v6_conn_request;
subflow_v6_specific.syn_recv_sock = subflow_syn_recv_sock;
subflow_v6_specific.sk_rx_dst_set = subflow_finish_connect;
subflow_v6m_specific = subflow_v6_specific;
subflow_v6m_specific.queue_xmit = ipv4_specific.queue_xmit;
subflow_v6m_specific.send_check = ipv4_specific.send_check;
subflow_v6m_specific.net_header_len = ipv4_specific.net_header_len;
subflow_v6m_specific.mtu_reduced = ipv4_specific.mtu_reduced;
subflow_v6m_specific.net_frag_header_len = 0;
tcpv6_prot_override = tcpv6_prot;
tcpv6_prot_override.release_cb = tcp_release_cb_override;
#endif
mptcp_diag_subflow_init(&subflow_ulp_ops);
if (tcp_register_ulp(&subflow_ulp_ops) != 0)
panic("MPTCP: failed to register subflows to ULP\n");
}