Commit bce3bb30 authored by Jakub Kicinski's avatar Jakub Kicinski
Browse files

Merge branch 'mptcp-fixes-for-5-19' 

Mat Martineau says:

====================
mptcp: Fixes for 5.19

Several categories of fixes from the mptcp tree:

Patches 1-3 are fixes related to MP_FAIL and FASTCLOSE, to make sure
MIBs are accurate, and to handle MP_FAIL transmission and responses at
the correct times. sk_timer conflicts are also resolved.

Patches 4 and 6 handle two separate race conditions, one at socket
shutdown and one with unaccepted subflows.

Patch 5 makes sure read operations are not blocked during fallback to
TCP.

Patch 7 improves the diag selftest, which were incorrectly failing on
slow machines (like the VMs used for CI testing).

Patch 8 avoids possible symbol redefinition errors in the userspace
mptcp.h file.

Patch 9 fixes a selftest build issue with gcc 12.
====================

Link: https://lore.kernel.org/r/20220628010243.166605-1-mathew.j.martineau@linux.intel.com


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parents ab84db25 fd37c2ec

include/uapi/linux/mptcp.h

+5 −4
Original line number Original line Diff line number Diff line
@@ -2,16 +2,17 @@ 
#ifndef _UAPI_MPTCP_H

#ifndef _UAPI_MPTCP_H

#define _UAPI_MPTCP_H

#define _UAPI_MPTCP_H





#ifndef __KERNEL__

#include <netinet/in.h>		/* for sockaddr_in and sockaddr_in6	*/

#include <sys/socket.h>		/* for struct sockaddr			*/

#endif



#include <linux/const.h>

#include <linux/const.h>

#include <linux/types.h>

#include <linux/types.h>

#include <linux/in.h>		/* for sockaddr_in			*/

#include <linux/in.h>		/* for sockaddr_in			*/

#include <linux/in6.h>		/* for sockaddr_in6			*/

#include <linux/in6.h>		/* for sockaddr_in6			*/

#include <linux/socket.h>	/* for sockaddr_storage and sa_family	*/

#include <linux/socket.h>	/* for sockaddr_storage and sa_family	*/





#ifndef __KERNEL__

#include <sys/socket.h>		/* for struct sockaddr			*/

#endif



#define MPTCP_SUBFLOW_FLAG_MCAP_REM		_BITUL(0)

#define MPTCP_SUBFLOW_FLAG_MCAP_REM		_BITUL(0)

#define MPTCP_SUBFLOW_FLAG_MCAP_LOC		_BITUL(1)

#define MPTCP_SUBFLOW_FLAG_MCAP_LOC		_BITUL(1)

#define MPTCP_SUBFLOW_FLAG_JOIN_REM		_BITUL(2)

#define MPTCP_SUBFLOW_FLAG_JOIN_REM		_BITUL(2)

net/mptcp/options.c

+4 −3
Original line number Original line Diff line number Diff line
@@ -765,6 +765,7 @@ static noinline bool mptcp_established_options_rst(struct sock *sk, struct sk_bu 
	opts->suboptions |= OPTION_MPTCP_RST;

	opts->suboptions |= OPTION_MPTCP_RST;

	opts->reset_transient = subflow->reset_transient;

	opts->reset_transient = subflow->reset_transient;

	opts->reset_reason = subflow->reset_reason;

	opts->reset_reason = subflow->reset_reason;

	MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPRSTTX);





	return true;

	return true;

}

}
@@ -788,6 +789,7 @@ static bool mptcp_established_options_fastclose(struct sock *sk, 
	opts->rcvr_key = msk->remote_key;

	opts->rcvr_key = msk->remote_key;





	pr_debug("FASTCLOSE key=%llu", opts->rcvr_key);

	pr_debug("FASTCLOSE key=%llu", opts->rcvr_key);

	MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFASTCLOSETX);

	return true;

	return true;

}

}
@@ -809,6 +811,7 @@ static bool mptcp_established_options_mp_fail(struct sock *sk, 
	opts->fail_seq = subflow->map_seq;

	opts->fail_seq = subflow->map_seq;





	pr_debug("MP_FAIL fail_seq=%llu", opts->fail_seq);

	pr_debug("MP_FAIL fail_seq=%llu", opts->fail_seq);

	MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFAILTX);





	return true;

	return true;

}

}
@@ -833,13 +836,11 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, 
		    mptcp_established_options_mp_fail(sk, &opt_size, remaining, opts)) {

		    mptcp_established_options_mp_fail(sk, &opt_size, remaining, opts)) {

			*size += opt_size;

			*size += opt_size;

			remaining -= opt_size;

			remaining -= opt_size;

			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFASTCLOSETX);

		}

		}

		/* MP_RST can be used with MP_FASTCLOSE and MP_FAIL if there is room */

		/* MP_RST can be used with MP_FASTCLOSE and MP_FAIL if there is room */

		if (mptcp_established_options_rst(sk, skb, &opt_size, remaining, opts)) {

		if (mptcp_established_options_rst(sk, skb, &opt_size, remaining, opts)) {

			*size += opt_size;

			*size += opt_size;

			remaining -= opt_size;

			remaining -= opt_size;

			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPRSTTX);

		}

		}

		return true;

		return true;

	}

	}
@@ -966,7 +967,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, 
			goto reset;

			goto reset;

		subflow->mp_capable = 0;

		subflow->mp_capable = 0;

		pr_fallback(msk);

		pr_fallback(msk);

		__mptcp_do_fallback(msk);

		mptcp_do_fallback(ssk);

		return false;

		return false;

	}

	}

net/mptcp/pm.c

+4 −6
Original line number Original line Diff line number Diff line
@@ -299,23 +299,21 @@ void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq) 
{

{

	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);

	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);

	struct mptcp_sock *msk = mptcp_sk(subflow->conn);

	struct mptcp_sock *msk = mptcp_sk(subflow->conn);

	struct sock *s = (struct sock *)msk;





	pr_debug("fail_seq=%llu", fail_seq);

	pr_debug("fail_seq=%llu", fail_seq);





	if (!READ_ONCE(msk->allow_infinite_fallback))

	if (!READ_ONCE(msk->allow_infinite_fallback))

		return;

		return;





	if (!READ_ONCE(subflow->mp_fail_response_expect)) {

	if (!subflow->fail_tout) {

		pr_debug("send MP_FAIL response and infinite map");

		pr_debug("send MP_FAIL response and infinite map");





		subflow->send_mp_fail = 1;

		subflow->send_mp_fail = 1;

		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFAILTX);

		subflow->send_infinite_map = 1;

		subflow->send_infinite_map = 1;

	} else if (!sock_flag(sk, SOCK_DEAD)) {

		tcp_send_ack(sk);

	} else {

		pr_debug("MP_FAIL response received");

		pr_debug("MP_FAIL response received");



		WRITE_ONCE(subflow->fail_tout, 0);

		sk_stop_timer(s, &s->sk_timer);

	}

	}

}

}

net/mptcp/protocol.c

+53 −31
Original line number Original line Diff line number Diff line
@@ -500,7 +500,7 @@ static void mptcp_set_timeout(struct sock *sk) 
	__mptcp_set_timeout(sk, tout);

	__mptcp_set_timeout(sk, tout);

}

}





static bool tcp_can_send_ack(const struct sock *ssk)

static inline bool tcp_can_send_ack(const struct sock *ssk)

{

{

	return !((1 << inet_sk_state_load(ssk)) &

	return !((1 << inet_sk_state_load(ssk)) &

	       (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_TIME_WAIT | TCPF_CLOSE | TCPF_LISTEN));

	       (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_TIME_WAIT | TCPF_CLOSE | TCPF_LISTEN));
@@ -1245,7 +1245,7 @@ static void mptcp_update_infinite_map(struct mptcp_sock *msk, 
	MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPTX);

	MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPTX);

	mptcp_subflow_ctx(ssk)->send_infinite_map = 0;

	mptcp_subflow_ctx(ssk)->send_infinite_map = 0;

	pr_fallback(msk);

	pr_fallback(msk);

	__mptcp_do_fallback(msk);

	mptcp_do_fallback(ssk);

}

}





static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,

static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
@@ -2175,21 +2175,6 @@ static void mptcp_retransmit_timer(struct timer_list *t) 
	sock_put(sk);

	sock_put(sk);

}

}





static struct mptcp_subflow_context *

mp_fail_response_expect_subflow(struct mptcp_sock *msk)

{

	struct mptcp_subflow_context *subflow, *ret = NULL;



	mptcp_for_each_subflow(msk, subflow) {

		if (READ_ONCE(subflow->mp_fail_response_expect)) {

			ret = subflow;

			break;

		}

	}



	return ret;

}



static void mptcp_timeout_timer(struct timer_list *t)

static void mptcp_timeout_timer(struct timer_list *t)

{

{

	struct sock *sk = from_timer(sk, t, sk_timer);

	struct sock *sk = from_timer(sk, t, sk_timer);
@@ -2346,6 +2331,11 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, 
		kfree_rcu(subflow, rcu);

		kfree_rcu(subflow, rcu);

	} else {

	} else {

		/* otherwise tcp will dispose of the ssk and subflow ctx */

		/* otherwise tcp will dispose of the ssk and subflow ctx */

		if (ssk->sk_state == TCP_LISTEN) {

			tcp_set_state(ssk, TCP_CLOSE);

			mptcp_subflow_queue_clean(ssk);

			inet_csk_listen_stop(ssk);

		}

		__tcp_close(ssk, 0);

		__tcp_close(ssk, 0);





		/* close acquired an extra ref */

		/* close acquired an extra ref */
@@ -2518,27 +2508,50 @@ static void __mptcp_retrans(struct sock *sk) 
		mptcp_reset_timer(sk);

		mptcp_reset_timer(sk);

}

}





/* schedule the timeout timer for the relevant event: either close timeout

 * or mp_fail timeout. The close timeout takes precedence on the mp_fail one

 */

void mptcp_reset_timeout(struct mptcp_sock *msk, unsigned long fail_tout)

{

	struct sock *sk = (struct sock *)msk;

	unsigned long timeout, close_timeout;



	if (!fail_tout && !sock_flag(sk, SOCK_DEAD))

		return;



	close_timeout = inet_csk(sk)->icsk_mtup.probe_timestamp - tcp_jiffies32 + jiffies + TCP_TIMEWAIT_LEN;



	/* the close timeout takes precedence on the fail one, and here at least one of

	 * them is active

	 */

	timeout = sock_flag(sk, SOCK_DEAD) ? close_timeout : fail_tout;



	sk_reset_timer(sk, &sk->sk_timer, timeout);

}



static void mptcp_mp_fail_no_response(struct mptcp_sock *msk)

static void mptcp_mp_fail_no_response(struct mptcp_sock *msk)

{

{

	struct mptcp_subflow_context *subflow;

	struct sock *ssk = msk->first;

	struct sock *ssk;

	bool slow;

	bool slow;





	subflow = mp_fail_response_expect_subflow(msk);

	if (!ssk)

	if (subflow) {

		return;



	pr_debug("MP_FAIL doesn't respond, reset the subflow");

	pr_debug("MP_FAIL doesn't respond, reset the subflow");





		ssk = mptcp_subflow_tcp_sock(subflow);

	slow = lock_sock_fast(ssk);

	slow = lock_sock_fast(ssk);

	mptcp_subflow_reset(ssk);

	mptcp_subflow_reset(ssk);

	WRITE_ONCE(mptcp_subflow_ctx(ssk)->fail_tout, 0);

	unlock_sock_fast(ssk, slow);

	unlock_sock_fast(ssk, slow);

	}



	mptcp_reset_timeout(msk, 0);

}

}





static void mptcp_worker(struct work_struct *work)

static void mptcp_worker(struct work_struct *work)

{

{

	struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work);

	struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work);

	struct sock *sk = &msk->sk.icsk_inet.sk;

	struct sock *sk = &msk->sk.icsk_inet.sk;

	unsigned long fail_tout;

	int state;

	int state;





	lock_sock(sk);

	lock_sock(sk);
@@ -2575,6 +2588,8 @@ static void mptcp_worker(struct work_struct *work) 
	if (test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags))

	if (test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags))

		__mptcp_retrans(sk);

		__mptcp_retrans(sk);





	fail_tout = msk->first ? READ_ONCE(mptcp_subflow_ctx(msk->first)->fail_tout) : 0;

	if (fail_tout && time_after(jiffies, fail_tout))

		mptcp_mp_fail_no_response(msk);

		mptcp_mp_fail_no_response(msk);





unlock:

unlock:
@@ -2822,6 +2837,7 @@ static void __mptcp_destroy_sock(struct sock *sk) 
static void mptcp_close(struct sock *sk, long timeout)

static void mptcp_close(struct sock *sk, long timeout)

{

{

	struct mptcp_subflow_context *subflow;

	struct mptcp_subflow_context *subflow;

	struct mptcp_sock *msk = mptcp_sk(sk);

	bool do_cancel_work = false;

	bool do_cancel_work = false;





	lock_sock(sk);

	lock_sock(sk);
@@ -2840,10 +2856,16 @@ static void mptcp_close(struct sock *sk, long timeout) 
cleanup:

cleanup:

	/* orphan all the subflows */

	/* orphan all the subflows */

	inet_csk(sk)->icsk_mtup.probe_timestamp = tcp_jiffies32;

	inet_csk(sk)->icsk_mtup.probe_timestamp = tcp_jiffies32;

	mptcp_for_each_subflow(mptcp_sk(sk), subflow) {

	mptcp_for_each_subflow(msk, subflow) {

		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);

		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);

		bool slow = lock_sock_fast_nested(ssk);

		bool slow = lock_sock_fast_nested(ssk);





		/* since the close timeout takes precedence on the fail one,

		 * cancel the latter

		 */

		if (ssk == msk->first)

			subflow->fail_tout = 0;



		sock_orphan(ssk);

		sock_orphan(ssk);

		unlock_sock_fast(ssk, slow);

		unlock_sock_fast(ssk, slow);

	}

	}
@@ -2852,13 +2874,13 @@ static void mptcp_close(struct sock *sk, long timeout) 
	sock_hold(sk);

	sock_hold(sk);

	pr_debug("msk=%p state=%d", sk, sk->sk_state);

	pr_debug("msk=%p state=%d", sk, sk->sk_state);

	if (mptcp_sk(sk)->token)

	if (mptcp_sk(sk)->token)

		mptcp_event(MPTCP_EVENT_CLOSED, mptcp_sk(sk), NULL, GFP_KERNEL);

		mptcp_event(MPTCP_EVENT_CLOSED, msk, NULL, GFP_KERNEL);





	if (sk->sk_state == TCP_CLOSE) {

	if (sk->sk_state == TCP_CLOSE) {

		__mptcp_destroy_sock(sk);

		__mptcp_destroy_sock(sk);

		do_cancel_work = true;

		do_cancel_work = true;

	} else {

	} else {

		sk_reset_timer(sk, &sk->sk_timer, jiffies + TCP_TIMEWAIT_LEN);

		mptcp_reset_timeout(msk, 0);

	}

	}

	release_sock(sk);

	release_sock(sk);

	if (do_cancel_work)

	if (do_cancel_work)

net/mptcp/protocol.h

+20 −4
Original line number Original line Diff line number Diff line
@@ -306,6 +306,7 @@ struct mptcp_sock { 




	u32 setsockopt_seq;

	u32 setsockopt_seq;

	char		ca_name[TCP_CA_NAME_MAX];

	char		ca_name[TCP_CA_NAME_MAX];

	struct mptcp_sock	*dl_next;

};

};





#define mptcp_data_lock(sk) spin_lock_bh(&(sk)->sk_lock.slock)

#define mptcp_data_lock(sk) spin_lock_bh(&(sk)->sk_lock.slock)
@@ -468,7 +469,6 @@ struct mptcp_subflow_context { 
		local_id_valid : 1, /* local_id is correctly initialized */

		local_id_valid : 1, /* local_id is correctly initialized */

		valid_csum_seen : 1;        /* at least one csum validated */

		valid_csum_seen : 1;        /* at least one csum validated */

	enum mptcp_data_avail data_avail;

	enum mptcp_data_avail data_avail;

	bool	mp_fail_response_expect;

	u32	remote_nonce;

	u32	remote_nonce;

	u64	thmac;

	u64	thmac;

	u32	local_nonce;

	u32	local_nonce;
@@ -482,6 +482,7 @@ struct mptcp_subflow_context { 
	u8	stale_count;

	u8	stale_count;





	long	delegated_status;

	long	delegated_status;

	unsigned long	fail_tout;





	);

	);
@@ -608,6 +609,7 @@ void mptcp_close_ssk(struct sock *sk, struct sock *ssk, 
		     struct mptcp_subflow_context *subflow);

		     struct mptcp_subflow_context *subflow);

void mptcp_subflow_send_ack(struct sock *ssk);

void mptcp_subflow_send_ack(struct sock *ssk);

void mptcp_subflow_reset(struct sock *ssk);

void mptcp_subflow_reset(struct sock *ssk);

void mptcp_subflow_queue_clean(struct sock *ssk);

void mptcp_sock_graft(struct sock *sk, struct socket *parent);

void mptcp_sock_graft(struct sock *sk, struct socket *parent);

struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk);

struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk);
@@ -662,6 +664,7 @@ void mptcp_get_options(const struct sk_buff *skb, 




void mptcp_finish_connect(struct sock *sk);

void mptcp_finish_connect(struct sock *sk);

void __mptcp_set_connected(struct sock *sk);

void __mptcp_set_connected(struct sock *sk);

void mptcp_reset_timeout(struct mptcp_sock *msk, unsigned long fail_tout);

static inline bool mptcp_is_fully_established(struct sock *sk)

static inline bool mptcp_is_fully_established(struct sock *sk)

{

{

	return inet_sk_state_load(sk) == TCP_ESTABLISHED &&

	return inet_sk_state_load(sk) == TCP_ESTABLISHED &&
@@ -926,12 +929,25 @@ static inline void __mptcp_do_fallback(struct mptcp_sock *msk) 
	set_bit(MPTCP_FALLBACK_DONE, &msk->flags);

	set_bit(MPTCP_FALLBACK_DONE, &msk->flags);

}

}





static inline void mptcp_do_fallback(struct sock *sk)

static inline void mptcp_do_fallback(struct sock *ssk)

{

{

	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);

	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);

	struct mptcp_sock *msk = mptcp_sk(subflow->conn);

	struct sock *sk = subflow->conn;

	struct mptcp_sock *msk;





	msk = mptcp_sk(sk);

	__mptcp_do_fallback(msk);

	__mptcp_do_fallback(msk);

	if (READ_ONCE(msk->snd_data_fin_enable) && !(ssk->sk_shutdown & SEND_SHUTDOWN)) {

		gfp_t saved_allocation = ssk->sk_allocation;



		/* we are in a atomic (BH) scope, override ssk default for data

		 * fin allocation

		 */

		ssk->sk_allocation = GFP_ATOMIC;

		ssk->sk_shutdown |= SEND_SHUTDOWN;

		tcp_shutdown(ssk, SEND_SHUTDOWN);

		ssk->sk_allocation = saved_allocation;

	}

}

}





#define pr_fallback(a) pr_debug("%s:fallback to TCP (msk=%p)", __func__, a)

#define pr_fallback(a) pr_debug("%s:fallback to TCP (msk=%p)", __func__, a)