mptcp: fix 3rd ack rtx timer
Subsystems (3)
Paolo Abeni
maintainercover mptcp: fix 3rd ack rtx timer
Eric noted that the MPTCP code do the wrong thing to schedule the MPJ 3rd ack timer. He also provided a patch to address the issues (patch 1/2).
To fix for good the MPJ 3rd ack retransmission timer, we additionally need to set it after the current ack is transmitted (patch 2/2)
Note that the bug went unnotice so far because all the related tests required some running data transfer, and that causes MPTCP-level ack even on the opening MPJ subflow. We now have explicit packet drill coverage for this code path.
Eric Dumazet (1):
mptcp: fix delack timer
Paolo Abeni (1):
mptcp: use delegate action to schedule 3rd ack retrans
net/mptcp/options.c | 32 ++++++++------------------- net/mptcp/protocol.c | 51 ++++++++++++++++++++++++++++++++++++-------- net/mptcp/protocol.h | 17 ++++++++------- 3 files changed, 60 insertions(+), 40 deletions(-)
Signature · 1 line
2.33.1
Paolo Abeni
maintainerPATCH 1/2 mptcp: fix delack timer
From: Eric Dumazet <[email protected]>
To compute the rtx timeout schedule_3rdack_retransmission() does multiple things in the wrong way: srtt_us is measured in usec/8 and the timeout itself is an absolute value.
--- net/mptcp/options.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
net/mptcp/options.c +2 -1
@@ -434,9 +434,10 @@ static void schedule_3rdack_retransmission(struct sock *sk)/* reschedule with a timeout above RTT, as we must look only for drop */ if (tp->srtt_us) - timeout = tp->srtt_us <<1 ; + timeout =usecs_to_jiffies (tp->srtt_us >> (3 -1 ));else timeout =TCP_TIMEOUT_INIT ; + timeout += jiffies;WARN_ON_ONCE (icsk->icsk_ack.pending &ICSK_ACK_TIMER ); icsk->icsk_ack.pending |=ICSK_ACK_SCHED |ICSK_ACK_TIMER ;
Signature · 1 line
2.33.1
Paolo Abeni
maintainerPATCH 2/2 mptcp: use delegate action to schedule 3rd ack retrans
In reply to Paolo AbeniScheduling a delack in mptcp_established_options_mp() is not a good idea: such function is called by tcp_send_ack() and the pending delayed ack will be cleared shortly after by the tcp_event_ack_sent() call in __tcp_transmit_skb().
Instead use the mptcp delegated action infrastructure to schedule the delayed ack after the current bh processing completes.
Additionally moves the schedule_3rdack_retransmission() helper into protocol.c to avoid making it visible in a different compilation unit.
--- net/mptcp/options.c | 33 ++++++++-------------------- net/mptcp/protocol.c | 51 ++++++++++++++++++++++++++++++++++++-------- net/mptcp/protocol.h | 17 ++++++++------- 3 files changed, 60 insertions(+), 41 deletions(-)
net/mptcp/options.c +9 -24
@@ -422,29 +422,6 @@ bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb,return false; } -/* MP_JOIN client subflow must wait for 4th ack before sending any data: -* TCP can't schedule delack timer before the subflow is fully established. -* MPTCP uses the delack timer to do 3rd ack retransmissions -*/ -static void schedule_3rdack_retransmission (struct sock *sk) -{ -struct inet_connection_sock *icsk =inet_csk (sk); -struct tcp_sock *tp =tcp_sk (sk); -unsigned long timeout; - -/* reschedule with a timeout above RTT, as we must look only for drop */ -if (tp->srtt_us) - timeout =usecs_to_jiffies (tp->srtt_us >> (3 -1 )); -else - timeout =TCP_TIMEOUT_INIT ; - timeout += jiffies; - -WARN_ON_ONCE (icsk->icsk_ack.pending &ICSK_ACK_TIMER ); - icsk->icsk_ack.pending |=ICSK_ACK_SCHED |ICSK_ACK_TIMER ; - icsk->icsk_ack.timeout = timeout; -sk_reset_timer (sk, &icsk->icsk_delack_timer, timeout); -} -static void clear_3rdack_retransmission (struct sock *sk) {struct inet_connection_sock *icsk =inet_csk (sk);
@@ -527,7 +504,15 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb, *size =TCPOLEN_MPTCP_MPJ_ACK ;pr_debug ("subflow=%p" , subflow); -schedule_3rdack_retransmission (sk); +/* we can use the full delegate action helper only from BH context +* If we are in process context - sk is flushing the backlog at +* socket lock release time - just set the appropriate flag, will +* be handled by the release callback +*/ +if (sock_owned_by_user (sk)) +set_bit (MPTCP_DELEGATE_ACK , &subflow->delegated_status); +else +mptcp_subflow_delegate (subflow,MPTCP_DELEGATE_ACK );return true; }return false;
net/mptcp/protocol.c +42 -9
74 lines not on this page · raw message
net/mptcp/protocol.h +9 -8
@@ -387,6 +387,7 @@ struct mptcp_delegated_action { DECLARE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions);#define MPTCP_DELEGATE_SEND 0 +#define MPTCP_DELEGATE_ACK 1/* MPTCP subflow context */ struct mptcp_subflow_context {
@@ -492,23 +493,23 @@ static inline void mptcp_add_pending_subflow(struct mptcp_sock *msk,void mptcp_subflow_process_delegated (struct sock *ssk); -static inline void mptcp_subflow_delegate (struct mptcp_subflow_context *subflow) +static inline void mptcp_subflow_delegate (struct mptcp_subflow_context *subflow,int action) {struct mptcp_delegated_action *delegated;bool schedule; +/* the caller held the subflow bh socket lock */ +lockdep_assert_in_softirq (); +/* The implied barrier pairs with mptcp_subflow_delegated_done(), and * ensures the below list check sees list updates done prior to status * bit changes */ -if (!test_and_set_bit (MPTCP_DELEGATE_SEND , &subflow->delegated_status)) { +if (!test_and_set_bit (action, &subflow->delegated_status)) {/* still on delegated list from previous scheduling */ if (!list_empty (&subflow->delegated_node))return ; -/* the caller held the subflow bh socket lock */ -lockdep_assert_in_softirq (); - delegated =this_cpu_ptr (&mptcp_delegated_actions); schedule =list_empty (&delegated->head);list_add_tail (&subflow->delegated_node, &delegated->head);
@@ -533,16 +534,16 @@ mptcp_subflow_delegated_next(struct mptcp_delegated_action *delegated)static inline bool mptcp_subflow_has_delegated_action (const struct mptcp_subflow_context *subflow) { -return test_bit (MPTCP_DELEGATE_SEND , &subflow->delegated_status); +return !!READ_ONCE (subflow->delegated_status); } -static inline void mptcp_subflow_delegated_done (struct mptcp_subflow_context *subflow) +static inline void mptcp_subflow_delegated_done (struct mptcp_subflow_context *subflow,int action) {/* pairs with mptcp_subflow_delegate, ensures delegate_node is updated before * touching the status bit */ smp_wmb (); -clear_bit (MPTCP_DELEGATE_SEND , &subflow->delegated_status); +clear_bit (action, &subflow->delegated_status); }int mptcp_is_enabled (const struct net *net);
Signature · 1 line
2.33.1
From: Paolo Abeni <[email protected]>
Date: Fri, 19 Nov 2021 15:27:53 +0100
Quoted 11 lines
Eric noted that the MPTCP code do the wrong thing to schedule the MPJ 3rd ack timer. He also provided a patch to address the issues (patch 1/2).
To fix for good the MPJ 3rd ack retransmission timer, we additionally need to set it after the current ack is transmitted (patch 2/2)
Note that the bug went unnotice so far because all the related tests required some running data transfer, and that causes MPTCP-level ack even on the opening MPJ subflow. We now have explicit packet drill coverage for this code path.
This series was applied to netdev/net.git (master) by David S. Miller <[email protected]>:
Hello:
This series was applied to netdev/net.git (master) by David S. Miller <[email protected]>:
Quoted 8 lines · On Fri, 19 Nov 2021 15:27:53 +0100 you wrote:
Eric noted that the MPTCP code do the wrong thing to schedule the MPJ 3rd ack timer. He also provided a patch to address the issues (patch 1/2).
To fix for good the MPJ 3rd ack retransmission timer, we additionally need to set it after the current ack is transmitted (patch 2/2)
[...]
Here is the summary with links:
- [net,1/2] mptcp: fix delack timer
https://git.kernel.org/netdev/net/c/ee50e67ba0e1 - [net,2/2] mptcp: use delegate action to schedule 3rd ack retrans https://git.kernel.org/netdev/net/c/bcd97734318d
You are awesome, thank you!
Signature · 2 lines
Deet-doot-dot, I am a bot. https://korg.docs.kernel.org/patchwork/pwbot.html