Merge branch 'rxrpc-implement-jumbo-data-transmission-and-rack-tlp'

David Howells says:

====================
rxrpc: Implement jumbo DATA transmission and RACK-TLP

Here's a series of patches to implement two main features:

 (1) The transmission of jumbo data packets whereby several DATA packets of
     a particular size can be glued together into a single UDP packet,
     allowing us to make use of larger MTU sizes.  The basic jumbo
     subpacket capacity is 1412 bytes (RXRPC_JUMBO_DATALEN) and, say, an
     MTU of 8192 allows five of them to be transmitted as one.

     An alternative (and possibly more efficient way) would be to
     expand/shrink the capacity of each DATA packet to match the MTU and
     thus save on header and tail-gap overhead, but the Rx protocol does
     not provide a mechanism for splitting the data - especially as the
     transported data is encrypted per-packet - and so UDP fragmentation
     would be the only way to handle this.

     In fact, in the future, AF_RXRPC also needs to look at shrinking the
     packet size where the MTU is smaller - for instance in the case of
     being carried by IPv6 over wifi where there isn't capacity for a 1412
     byte capacity.

 (2) RACK-TLP to manage packet loss and retransmission in conjunction with
     the congestion control algorithm.

These allow for better data throughput and work towards being able to have
larger transmission windows.

To this end, the following changes are also made:

 (1) Use a single large array of kvec structs for the I/O thread rather
     than having one per transmission buffer.  We need a much bigger
     collection of kvecs for ping padding

 (2) Implement path-MTU probing by sending padded PING ACK packets and
     monitoring for PING RESPONSE ACKs.  The pmtud value determined is used
     to configure the construction of jumbo DATA packets.

 (3) The transmission queue is changed from a linked list of transmission
     buffer structs to a linked list of transmission-queue structs, each of
     which points to either 32 or 64 transmission buffers (depending on cpu
     word size) and various bits of metadata are concentrated in the queue
     structs rather than the buffers to make better use of the cpu cache.

 (4) SACK data is stored in the transmission-queue structures in batches of
     32 or 64 making it faster to process rather than being spread amongst
     all the individual packet buffers.

 (5) Don't change the DF flag on the UDP socket unless we need to - and
     basically only enable it for path-MTU probing.

There are also some additional bits:

 (1) Fix the handling of connection aborts to poke the aborted connections.

 (2) Don't set the MORE-PACKETS Rx header flag on the wire.  No one
     actually checks it and it is, in any case, generated inconsistently
     between implementations.

 (3) Request an ACK when, during call transmission, there's a stall in the
     app generating the data to be transmitted.

 (4) Fix attention starvation in the I/O thread by making sure we go
     through all outstanding events rather than returning to the beginning
     of the check cycle after any time we process an event.

 (5) Don't use the skbuff timestamp in the calculation of timeouts and RTT
     as we really should include local processing time in that too.
     Further, getting receive skbuff timestamps may be expensive.

 (6) Make RTT tracking per call with the saving of the value between calls,
     even within the same connection channel.  The initial call timeout
     starts off large to allow the server time to set up its state before
     the initial reply.

 (7) Don't allocate txbuf structs for ACK packets, but rather use page
     frags and MSG_SPLICE_PAGES.

 (8) Use irq-disabling locks for interactions between app threads and I/O
     threads so that the I/O thread doesn't get help up.

 (9) Make rxrpc set the REQUEST-ACK flag on an outgoing packet when cwnd is
     at RXRPC_MIN_CWND (currently 4), not at 2 which it can never reach.

(10) Add some tracing bits and pieces (including displaying the userStatus
     field in an ACK header) and some more stats counters (including
     different sizes of jumbo packets sent/received).

Link: https://lore.kernel.org/r/20240306000655.1100294-1-dhowells@redhat.com/ [1]
====================

Link: https://patch.msgid.link/20241204074710.990092-1-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 770 insertions, 113 deletions

diff --git a/include/linux/ktime.h b/include/linux/ktime.h
index 3a4e723eae0f..383ed9985802 100644
--- a/include/linux/ktime.h
+++ b/include/linux/ktime.h
@@ -222,6 +222,11 @@ static inline ktime_t ns_to_ktime(u64 ns)
 	return ns;
 }
 
+static inline ktime_t us_to_ktime(u64 us)
+{
+	return us * NSEC_PER_USEC;
+}
+
 static inline ktime_t ms_to_ktime(u64 ms)
 {
 	return ms * NSEC_PER_MSEC;
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index d03e0bd8c028..2f119d18a061 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -117,8 +117,10 @@
 #define rxrpc_call_poke_traces \
 	EM(rxrpc_call_poke_abort,		"Abort")	\
 	EM(rxrpc_call_poke_complete,		"Compl")	\
+	EM(rxrpc_call_poke_conn_abort,		"Conn-abort")	\
 	EM(rxrpc_call_poke_error,		"Error")	\
 	EM(rxrpc_call_poke_idle,		"Idle")		\
+	EM(rxrpc_call_poke_rx_packet,		"Rx-packet")	\
 	EM(rxrpc_call_poke_set_timeout,		"Set-timo")	\
 	EM(rxrpc_call_poke_start,		"Start")	\
 	EM(rxrpc_call_poke_timer,		"Timer")	\
@@ -127,9 +129,9 @@
 #define rxrpc_skb_traces \
 	EM(rxrpc_skb_eaten_by_unshare,		"ETN unshare  ") \
 	EM(rxrpc_skb_eaten_by_unshare_nomem,	"ETN unshar-nm") \
+	EM(rxrpc_skb_get_call_rx,		"GET call-rx  ") \
 	EM(rxrpc_skb_get_conn_secured,		"GET conn-secd") \
 	EM(rxrpc_skb_get_conn_work,		"GET conn-work") \
-	EM(rxrpc_skb_get_last_nack,		"GET last-nack") \
 	EM(rxrpc_skb_get_local_work,		"GET locl-work") \
 	EM(rxrpc_skb_get_reject_work,		"GET rej-work ") \
 	EM(rxrpc_skb_get_to_recvmsg,		"GET to-recv  ") \
@@ -138,12 +140,12 @@
 	EM(rxrpc_skb_new_error_report,		"NEW error-rpt") \
 	EM(rxrpc_skb_new_jumbo_subpacket,	"NEW jumbo-sub") \
 	EM(rxrpc_skb_new_unshared,		"NEW unshared ") \
+	EM(rxrpc_skb_put_call_rx,		"PUT call-rx  ") \
 	EM(rxrpc_skb_put_conn_secured,		"PUT conn-secd") \
 	EM(rxrpc_skb_put_conn_work,		"PUT conn-work") \
 	EM(rxrpc_skb_put_error_report,		"PUT error-rep") \
 	EM(rxrpc_skb_put_input,			"PUT input    ") \
 	EM(rxrpc_skb_put_jumbo_subpacket,	"PUT jumbo-sub") \
-	EM(rxrpc_skb_put_last_nack,		"PUT last-nack") \
 	EM(rxrpc_skb_put_purge,			"PUT purge    ") \
 	EM(rxrpc_skb_put_rotate,		"PUT rotate   ") \
 	EM(rxrpc_skb_put_unknown,		"PUT unknown  ") \
@@ -282,6 +284,7 @@
 	EM(rxrpc_call_see_activate_client,	"SEE act-clnt") \
 	EM(rxrpc_call_see_connect_failed,	"SEE con-fail") \
 	EM(rxrpc_call_see_connected,		"SEE connect ") \
+	EM(rxrpc_call_see_conn_abort,		"SEE conn-abt") \
 	EM(rxrpc_call_see_disconnected,		"SEE disconn ") \
 	EM(rxrpc_call_see_distribute_error,	"SEE dist-err") \
 	EM(rxrpc_call_see_input,		"SEE input   ") \
@@ -292,7 +295,6 @@
 
 #define rxrpc_txqueue_traces \
 	EM(rxrpc_txqueue_await_reply,		"AWR") \
-	EM(rxrpc_txqueue_dequeue,		"DEQ") \
 	EM(rxrpc_txqueue_end,			"END") \
 	EM(rxrpc_txqueue_queue,			"QUE") \
 	EM(rxrpc_txqueue_queue_last,		"QLS") \
@@ -300,6 +302,13 @@
 	EM(rxrpc_txqueue_rotate_last,		"RLS") \
 	E_(rxrpc_txqueue_wait,			"WAI")
 
+#define rxrpc_txdata_traces \
+	EM(rxrpc_txdata_inject_loss,		" *INJ-LOSS*") \
+	EM(rxrpc_txdata_new_data,		" ") \
+	EM(rxrpc_txdata_retransmit,		" *RETRANS*") \
+	EM(rxrpc_txdata_tlp_new_data,		" *TLP-NEW*") \
+	E_(rxrpc_txdata_tlp_retransmit,		" *TLP-RETRANS*")
+
 #define rxrpc_receive_traces \
 	EM(rxrpc_receive_end,			"END") \
 	EM(rxrpc_receive_front,			"FRN") \
@@ -335,11 +344,10 @@
 	E_(rxrpc_rtt_tx_ping,			"PING")
 
 #define rxrpc_rtt_rx_traces \
-	EM(rxrpc_rtt_rx_other_ack,		"OACK") \
+	EM(rxrpc_rtt_rx_data_ack,		"DACK") \
 	EM(rxrpc_rtt_rx_obsolete,		"OBSL") \
 	EM(rxrpc_rtt_rx_lost,			"LOST") \
-	EM(rxrpc_rtt_rx_ping_response,		"PONG") \
-	E_(rxrpc_rtt_rx_requested_ack,		"RACK")
+	E_(rxrpc_rtt_rx_ping_response,		"PONG")
 
 #define rxrpc_timer_traces \
 	EM(rxrpc_timer_trace_delayed_ack,	"DelayAck ") \
@@ -347,11 +355,12 @@
 	EM(rxrpc_timer_trace_hard,		"HardLimit") \
 	EM(rxrpc_timer_trace_idle,		"IdleLimit") \
 	EM(rxrpc_timer_trace_keepalive,		"KeepAlive") \
-	EM(rxrpc_timer_trace_lost_ack,		"LostAck  ") \
 	EM(rxrpc_timer_trace_ping,		"DelayPing") \
-	EM(rxrpc_timer_trace_resend,		"Resend   ") \
-	EM(rxrpc_timer_trace_resend_reset,	"ResendRst") \
-	E_(rxrpc_timer_trace_resend_tx,		"ResendTx ")
+	EM(rxrpc_timer_trace_rack_off,		"RACK-OFF ") \
+	EM(rxrpc_timer_trace_rack_zwp,		"RACK-ZWP ") \
+	EM(rxrpc_timer_trace_rack_reo,		"RACK-Reo ") \
+	EM(rxrpc_timer_trace_rack_tlp_pto,	"TLP-PTO  ") \
+	E_(rxrpc_timer_trace_rack_rto,		"RTO      ")
 
 #define rxrpc_propose_ack_traces \
 	EM(rxrpc_propose_ack_client_tx_end,	"ClTxEnd") \
@@ -362,22 +371,24 @@
 	EM(rxrpc_propose_ack_ping_for_lost_ack,	"LostAck") \
 	EM(rxrpc_propose_ack_ping_for_lost_reply, "LostRpl") \
 	EM(rxrpc_propose_ack_ping_for_0_retrans, "0-Retrn") \
+	EM(rxrpc_propose_ack_ping_for_mtu_probe, "MTUProb") \
 	EM(rxrpc_propose_ack_ping_for_old_rtt,	"OldRtt ") \
 	EM(rxrpc_propose_ack_ping_for_params,	"Params ") \
 	EM(rxrpc_propose_ack_ping_for_rtt,	"Rtt    ") \
 	EM(rxrpc_propose_ack_processing_op,	"ProcOp ") \
 	EM(rxrpc_propose_ack_respond_to_ack,	"Rsp2Ack") \
 	EM(rxrpc_propose_ack_respond_to_ping,	"Rsp2Png") \
+	EM(rxrpc_propose_ack_retransmit,	"Retrans") \
 	EM(rxrpc_propose_ack_retry_tx,		"RetryTx") \
 	EM(rxrpc_propose_ack_rotate_rx,		"RxAck  ") \
 	EM(rxrpc_propose_ack_rx_idle,		"RxIdle ") \
 	E_(rxrpc_propose_ack_terminal_ack,	"ClTerm ")
 
-#define rxrpc_congest_modes \
-	EM(RXRPC_CALL_CONGEST_AVOIDANCE,	"CongAvoid") \
-	EM(RXRPC_CALL_FAST_RETRANSMIT,		"FastReTx ") \
-	EM(RXRPC_CALL_PACKET_LOSS,		"PktLoss  ") \
-	E_(RXRPC_CALL_SLOW_START,		"SlowStart")
+#define rxrpc_ca_states \
+	EM(RXRPC_CA_CONGEST_AVOIDANCE,		"CongAvoid") \
+	EM(RXRPC_CA_FAST_RETRANSMIT,		"FastReTx ") \
+	EM(RXRPC_CA_PACKET_LOSS,		"PktLoss  ") \
+	E_(RXRPC_CA_SLOW_START,			"SlowStart")
 
 #define rxrpc_congest_changes \
 	EM(rxrpc_cong_begin_retransmission,	" Retrans") \
@@ -450,7 +461,7 @@
 
 #define rxrpc_req_ack_traces \
 	EM(rxrpc_reqack_ack_lost,		"ACK-LOST  ")	\
-	EM(rxrpc_reqack_already_on,		"ALREADY-ON")	\
+	EM(rxrpc_reqack_app_stall,		"APP-STALL ")	\
 	EM(rxrpc_reqack_more_rtt,		"MORE-RTT  ")	\
 	EM(rxrpc_reqack_no_srv_last,		"NO-SRVLAST")	\
 	EM(rxrpc_reqack_old_rtt,		"OLD-RTT   ")	\
@@ -460,21 +471,60 @@
 /* ---- Must update size of stat_why_req_ack[] if more are added! */
 
 #define rxrpc_txbuf_traces \
-	EM(rxrpc_txbuf_alloc_ack,		"ALLOC ACK  ")	\
 	EM(rxrpc_txbuf_alloc_data,		"ALLOC DATA ")	\
 	EM(rxrpc_txbuf_free,			"FREE       ")	\
 	EM(rxrpc_txbuf_get_buffer,		"GET BUFFER ")	\
 	EM(rxrpc_txbuf_get_trans,		"GET TRANS  ")	\
 	EM(rxrpc_txbuf_get_retrans,		"GET RETRANS")	\
-	EM(rxrpc_txbuf_put_ack_tx,		"PUT ACK TX ")	\
 	EM(rxrpc_txbuf_put_cleaned,		"PUT CLEANED")	\
 	EM(rxrpc_txbuf_put_nomem,		"PUT NOMEM  ")	\
 	EM(rxrpc_txbuf_put_rotated,		"PUT ROTATED")	\
 	EM(rxrpc_txbuf_put_send_aborted,	"PUT SEND-X ")	\
 	EM(rxrpc_txbuf_put_trans,		"PUT TRANS  ")	\
+	EM(rxrpc_txbuf_see_lost,		"SEE LOST   ")	\
 	EM(rxrpc_txbuf_see_out_of_step,		"OUT-OF-STEP")	\
-	EM(rxrpc_txbuf_see_send_more,		"SEE SEND+  ")	\
-	E_(rxrpc_txbuf_see_unacked,		"SEE UNACKED")
+	E_(rxrpc_txbuf_see_send_more,		"SEE SEND+  ")
+
+#define rxrpc_tq_traces \
+	EM(rxrpc_tq_alloc,			"ALLOC") \
+	EM(rxrpc_tq_cleaned,			"CLEAN") \
+	EM(rxrpc_tq_decant,			"DCNT ") \
+	EM(rxrpc_tq_decant_advance,		"DCNT>") \
+	EM(rxrpc_tq_queue,			"QUEUE") \
+	EM(rxrpc_tq_queue_dup,			"QUE!!") \
+	EM(rxrpc_tq_rotate,			"ROT  ") \
+	EM(rxrpc_tq_rotate_and_free,		"ROT-F") \
+	EM(rxrpc_tq_rotate_and_keep,		"ROT-K") \
+	EM(rxrpc_tq_transmit,			"XMIT ") \
+	E_(rxrpc_tq_transmit_advance,		"XMIT>")
+
+#define rxrpc_pmtud_reduce_traces \
+	EM(rxrpc_pmtud_reduce_ack,		"Ack  ")	\
+	EM(rxrpc_pmtud_reduce_icmp,		"Icmp ")	\
+	E_(rxrpc_pmtud_reduce_route,		"Route")
+
+#define rxrpc_rotate_traces \
+	EM(rxrpc_rotate_trace_hack,		"hard-ack")	\
+	EM(rxrpc_rotate_trace_sack,		"soft-ack")	\
+	E_(rxrpc_rotate_trace_snak,		"soft-nack")
+
+#define rxrpc_rack_timer_modes \
+	EM(RXRPC_CALL_RACKTIMER_OFF,		"---") \
+	EM(RXRPC_CALL_RACKTIMER_RACK_REORDER,	"REO") \
+	EM(RXRPC_CALL_RACKTIMER_TLP_PTO,	"TLP") \
+	E_(RXRPC_CALL_RACKTIMER_RTO,		"RTO")
+
+#define rxrpc_tlp_probe_traces \
+	EM(rxrpc_tlp_probe_trace_busy,		"busy")		\
+	EM(rxrpc_tlp_probe_trace_transmit_new,	"transmit-new")	\
+	E_(rxrpc_tlp_probe_trace_retransmit,	"retransmit")
+
+#define rxrpc_tlp_ack_traces \
+	EM(rxrpc_tlp_ack_trace_acked,		"acked")	\
+	EM(rxrpc_tlp_ack_trace_dup_acked,	"dup-acked")	\
+	EM(rxrpc_tlp_ack_trace_hard_beyond,	"hard-beyond")	\
+	EM(rxrpc_tlp_ack_trace_incomplete,	"incomplete")	\
+	E_(rxrpc_tlp_ack_trace_new_data,	"new-data")
 
 /*
  * Generate enums for tracing information.
@@ -496,18 +546,24 @@ enum rxrpc_congest_change	{ rxrpc_congest_changes } __mode(byte);
 enum rxrpc_conn_trace		{ rxrpc_conn_traces } __mode(byte);
 enum rxrpc_local_trace		{ rxrpc_local_traces } __mode(byte);
 enum rxrpc_peer_trace		{ rxrpc_peer_traces } __mode(byte);
+enum rxrpc_pmtud_reduce_trace	{ rxrpc_pmtud_reduce_traces } __mode(byte);
 enum rxrpc_propose_ack_outcome	{ rxrpc_propose_ack_outcomes } __mode(byte);
 enum rxrpc_propose_ack_trace	{ rxrpc_propose_ack_traces } __mode(byte);
 enum rxrpc_receive_trace	{ rxrpc_receive_traces } __mode(byte);
 enum rxrpc_recvmsg_trace	{ rxrpc_recvmsg_traces } __mode(byte);
 enum rxrpc_req_ack_trace	{ rxrpc_req_ack_traces } __mode(byte);
+enum rxrpc_rotate_trace		{ rxrpc_rotate_traces } __mode(byte);
 enum rxrpc_rtt_rx_trace		{ rxrpc_rtt_rx_traces } __mode(byte);
 enum rxrpc_rtt_tx_trace		{ rxrpc_rtt_tx_traces } __mode(byte);
 enum rxrpc_sack_trace		{ rxrpc_sack_traces } __mode(byte);
 enum rxrpc_skb_trace		{ rxrpc_skb_traces } __mode(byte);
 enum rxrpc_timer_trace		{ rxrpc_timer_traces } __mode(byte);
+enum rxrpc_tlp_ack_trace	{ rxrpc_tlp_ack_traces } __mode(byte);
+enum rxrpc_tlp_probe_trace	{ rxrpc_tlp_probe_traces } __mode(byte);
+enum rxrpc_tq_trace		{ rxrpc_tq_traces } __mode(byte);
 enum rxrpc_tx_point		{ rxrpc_tx_points } __mode(byte);
 enum rxrpc_txbuf_trace		{ rxrpc_txbuf_traces } __mode(byte);
+enum rxrpc_txdata_trace		{ rxrpc_txdata_traces } __mode(byte);
 enum rxrpc_txqueue_trace	{ rxrpc_txqueue_traces } __mode(byte);
 
 #endif /* end __RXRPC_DECLARE_TRACE_ENUMS_ONCE_ONLY */
@@ -525,24 +581,31 @@ enum rxrpc_txqueue_trace	{ rxrpc_txqueue_traces } __mode(byte);
 
 rxrpc_abort_reasons;
 rxrpc_bundle_traces;
+rxrpc_ca_states;
 rxrpc_call_poke_traces;
 rxrpc_call_traces;
 rxrpc_client_traces;
 rxrpc_congest_changes;
-rxrpc_congest_modes;
 rxrpc_conn_traces;
 rxrpc_local_traces;
+rxrpc_pmtud_reduce_traces;
 rxrpc_propose_ack_traces;
+rxrpc_rack_timer_modes;
 rxrpc_receive_traces;
 rxrpc_recvmsg_traces;
 rxrpc_req_ack_traces;
+rxrpc_rotate_traces;
 rxrpc_rtt_rx_traces;
 rxrpc_rtt_tx_traces;
 rxrpc_sack_traces;
 rxrpc_skb_traces;
 rxrpc_timer_traces;
+rxrpc_tlp_ack_traces;
+rxrpc_tlp_probe_traces;
+rxrpc_tq_traces;
 rxrpc_tx_points;
 rxrpc_txbuf_traces;
+rxrpc_txdata_traces;
 rxrpc_txqueue_traces;
 
 /*
@@ -581,6 +644,20 @@ TRACE_EVENT(rxrpc_local,
 		      __entry->usage)
 	    );
 
+TRACE_EVENT(rxrpc_iothread_rx,
+	    TP_PROTO(struct rxrpc_local *local, unsigned int nr_rx),
+	    TP_ARGS(local, nr_rx),
+	    TP_STRUCT__entry(
+		    __field(unsigned int,	local)
+		    __field(unsigned int,	nr_rx)
+			     ),
+	    TP_fast_assign(
+		    __entry->local = local->debug_id;
+		    __entry->nr_rx = nr_rx;
+			   ),
+	    TP_printk("L=%08x nrx=%u", __entry->local, __entry->nr_rx)
+	    );
+
 TRACE_EVENT(rxrpc_peer,
 	    TP_PROTO(unsigned int peer_debug_id, int ref, enum rxrpc_peer_trace why),
 
@@ -865,34 +942,101 @@ TRACE_EVENT(rxrpc_txqueue,
 	    TP_STRUCT__entry(
 		    __field(unsigned int,		call)
 		    __field(enum rxrpc_txqueue_trace,	why)
-		    __field(rxrpc_seq_t,		acks_hard_ack)
 		    __field(rxrpc_seq_t,		tx_bottom)
+		    __field(rxrpc_seq_t,		acks_hard_ack)
 		    __field(rxrpc_seq_t,		tx_top)
-		    __field(rxrpc_seq_t,		tx_prepared)
+		    __field(rxrpc_seq_t,		send_top)
 		    __field(int,			tx_winsize)
 			     ),
 
 	    TP_fast_assign(
 		    __entry->call = call->debug_id;
 		    __entry->why = why;
-		    __entry->acks_hard_ack = call->acks_hard_ack;
 		    __entry->tx_bottom = call->tx_bottom;
+		    __entry->acks_hard_ack = call->acks_hard_ack;
 		    __entry->tx_top = call->tx_top;
-		    __entry->tx_prepared = call->tx_prepared;
+		    __entry->send_top = call->send_top;
 		    __entry->tx_winsize = call->tx_winsize;
 			   ),
 
-	    TP_printk("c=%08x %s f=%08x h=%08x n=%u/%u/%u/%u",
+	    TP_printk("c=%08x %s b=%08x h=%08x n=%u/%u/%u/%u",
 		      __entry->call,
 		      __print_symbolic(__entry->why, rxrpc_txqueue_traces),
 		      __entry->tx_bottom,
 		      __entry->acks_hard_ack,
-		      __entry->tx_top - __entry->tx_bottom,
+		      __entry->acks_hard_ack - __entry->tx_bottom,
 		      __entry->tx_top - __entry->acks_hard_ack,
-		      __entry->tx_prepared - __entry->tx_bottom,
+		      __entry->send_top - __entry->tx_top,
 		      __entry->tx_winsize)
 	    );
 
+TRACE_EVENT(rxrpc_transmit,
+	    TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t send_top, int space),
+
+	    TP_ARGS(call, send_top, space),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,	call)
+		    __field(rxrpc_seq_t,	seq)
+		    __field(u16,		space)
+		    __field(u16,		tx_winsize)
+		    __field(u16,		cong_cwnd)
+		    __field(u16,		cong_extra)
+		    __field(u16,		in_flight)
+		    __field(u16,		prepared)
+		    __field(u16,		pmtud_jumbo)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->call	= call->debug_id;
+		    __entry->seq	= call->tx_top + 1;
+		    __entry->space	= space;
+		    __entry->tx_winsize	= call->tx_winsize;
+		    __entry->cong_cwnd	= call->cong_cwnd;
+		    __entry->cong_extra	= call->cong_extra;
+		    __entry->prepared	= send_top - call->tx_bottom;
+		    __entry->in_flight	= call->tx_top - call->tx_bottom;
+		    __entry->pmtud_jumbo = call->peer->pmtud_jumbo;
+			   ),
+
+	    TP_printk("c=%08x q=%08x sp=%u tw=%u cw=%u+%u pr=%u if=%u pj=%u",
+		      __entry->call,
+		      __entry->seq,
+		      __entry->space,
+		      __entry->tx_winsize,
+		      __entry->cong_cwnd,
+		      __entry->cong_extra,
+		      __entry->prepared,
+		      __entry->in_flight,
+		      __entry->pmtud_jumbo)
+	    );
+
+TRACE_EVENT(rxrpc_tx_rotate,
+	    TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t seq, rxrpc_seq_t to),
+
+	    TP_ARGS(call, seq, to),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,	call)
+		    __field(rxrpc_seq_t,	seq)
+		    __field(rxrpc_seq_t,	to)
+		    __field(rxrpc_seq_t,	top)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->call	= call->debug_id;
+		    __entry->seq	= seq;
+		    __entry->to		= to;
+		    __entry->top	= call->tx_top;
+			   ),
+
+	    TP_printk("c=%08x q=%08x-%08x-%08x",
+		      __entry->call,
+		      __entry->seq,
+		      __entry->to,
+		      __entry->top)
+	    );
+
 TRACE_EVENT(rxrpc_rx_data,
 	    TP_PROTO(unsigned int call, rxrpc_seq_t seq,
 		     rxrpc_serial_t serial, u8 flags),
@@ -921,11 +1065,9 @@ TRACE_EVENT(rxrpc_rx_data,
 	    );
 
 TRACE_EVENT(rxrpc_rx_ack,
-	    TP_PROTO(struct rxrpc_call *call,
-		     rxrpc_serial_t serial, rxrpc_serial_t ack_serial,
-		     rxrpc_seq_t first, rxrpc_seq_t prev, u8 reason, u8 n_acks),
+	    TP_PROTO(struct rxrpc_call *call, struct rxrpc_skb_priv *sp),
 
-	    TP_ARGS(call, serial, ack_serial, first, prev, reason, n_acks),
+	    TP_ARGS(call, sp),
 
 	    TP_STRUCT__entry(
 		    __field(unsigned int,	call)
@@ -935,23 +1077,26 @@ TRACE_EVENT(rxrpc_rx_ack,
 		    __field(rxrpc_seq_t,	prev)
 		    __field(u8,			reason)
 		    __field(u8,			n_acks)
+		    __field(u8,			user_status)
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call->debug_id;
-		    __entry->serial = serial;
-		    __entry->ack_serial = ack_serial;
-		    __entry->first = first;
-		    __entry->prev = prev;
-		    __entry->reason = reason;
-		    __entry->n_acks = n_acks;
+		    __entry->call	= call->debug_id;
+		    __entry->serial	= sp->hdr.serial;
+		    __entry->user_status = sp->hdr.userStatus;
+		    __entry->ack_serial = sp->ack.acked_serial;
+		    __entry->first	= sp->ack.first_ack;
+		    __entry->prev	= sp->ack.prev_ack;
+		    __entry->reason	= sp->ack.reason;
+		    __entry->n_acks	= sp->ack.nr_acks;
 			   ),
 
-	    TP_printk("c=%08x %08x %s r=%08x f=%08x p=%08x n=%u",
+	    TP_printk("c=%08x %08x %s r=%08x us=%02x f=%08x p=%08x n=%u",
 		      __entry->call,
 		      __entry->serial,
 		      __print_symbolic(__entry->reason, rxrpc_ack_names),
 		      __entry->ack_serial,
+		      __entry->user_status,
 		      __entry->first,
 		      __entry->prev,
 		      __entry->n_acks)
@@ -981,6 +1126,29 @@ TRACE_EVENT(rxrpc_rx_abort,
 		      __entry->abort_code)
 	    );
 
+TRACE_EVENT(rxrpc_rx_conn_abort,
+	    TP_PROTO(const struct rxrpc_connection *conn, const struct sk_buff *skb),
+
+	    TP_ARGS(conn, skb),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,	conn)
+		    __field(rxrpc_serial_t,	serial)
+		    __field(u32,		abort_code)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->conn = conn->debug_id;
+		    __entry->serial = rxrpc_skb(skb)->hdr.serial;
+		    __entry->abort_code = skb->priority;
+			   ),
+
+	    TP_printk("C=%08x ABORT %08x ac=%d",
+		      __entry->conn,
+		      __entry->serial,
+		      __entry->abort_code)
+	    );
+
 TRACE_EVENT(rxrpc_rx_challenge,
 	    TP_PROTO(struct rxrpc_connection *conn, rxrpc_serial_t serial,
 		     u32 version, u32 nonce, u32 min_level),
@@ -1102,9 +1270,10 @@ TRACE_EVENT(rxrpc_tx_packet,
 
 TRACE_EVENT(rxrpc_tx_data,
 	    TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t seq,
-		     rxrpc_serial_t serial, unsigned int flags, bool lose),
+		     rxrpc_serial_t serial, unsigned int flags,
+		     enum rxrpc_txdata_trace trace),
 
-	    TP_ARGS(call, seq, serial, flags, lose),
+	    TP_ARGS(call, seq, serial, flags, trace),
 
 	    TP_STRUCT__entry(
 		    __field(unsigned int,	call)
@@ -1113,7 +1282,7 @@ TRACE_EVENT(rxrpc_tx_data,
 		    __field(u32,		cid)
 		    __field(u32,		call_id)
 		    __field(u16,		flags)
-		    __field(bool,		lose)
+		    __field(enum rxrpc_txdata_trace, trace)
 			     ),
 
 	    TP_fast_assign(
@@ -1123,26 +1292,26 @@ TRACE_EVENT(rxrpc_tx_data,
 		    __entry->seq = seq;
 		    __entry->serial = serial;
 		    __entry->flags = flags;
-		    __entry->lose = lose;
+		    __entry->trace = trace;
 			   ),
 
-	    TP_printk("c=%08x DATA %08x:%08x %08x q=%08x fl=%02x%s%s",
+	    TP_printk("c=%08x DATA %08x:%08x %08x q=%08x fl=%02x%s",
 		      __entry->call,
 		      __entry->cid,
 		      __entry->call_id,
 		      __entry->serial,
 		      __entry->seq,
 		      __entry->flags & RXRPC_TXBUF_WIRE_FLAGS,
-		      __entry->flags & RXRPC_TXBUF_RESENT ? " *RETRANS*" : "",
-		      __entry->lose ? " *LOSE*" : "")
+		      __print_symbolic(__entry->trace, rxrpc_txdata_traces))
 	    );
 
 TRACE_EVENT(rxrpc_tx_ack,
 	    TP_PROTO(unsigned int call, rxrpc_serial_t serial,
 		     rxrpc_seq_t ack_first, rxrpc_serial_t ack_serial,
-		     u8 reason, u8 n_acks, u16 rwind),
+		     u8 reason, u8 n_acks, u16 rwind,
+		     enum rxrpc_propose_ack_trace trace),
 
-	    TP_ARGS(call, serial, ack_first, ack_serial, reason, n_acks, rwind),
+	    TP_ARGS(call, serial, ack_first, ack_serial, reason, n_acks, rwind, trace),
 
 	    TP_STRUCT__entry(
 		    __field(unsigned int,	call)
@@ -1152,6 +1321,7 @@ TRACE_EVENT(rxrpc_tx_ack,
 		    __field(u8,			reason)
 		    __field(u8,			n_acks)
 		    __field(u16,		rwind)
+		    __field(enum rxrpc_propose_ack_trace, trace)
 			     ),
 
 	    TP_fast_assign(
@@ -1162,16 +1332,18 @@ TRACE_EVENT(rxrpc_tx_ack,
 		    __entry->reason = reason;
 		    __entry->n_acks = n_acks;
 		    __entry->rwind = rwind;
+		    __entry->trace = trace;
 			   ),
 
-	    TP_printk(" c=%08x ACK  %08x %s f=%08x r=%08x n=%u rw=%u",
+	    TP_printk(" c=%08x ACK  %08x %s f=%08x r=%08x n=%u rw=%u %s",
 		      __entry->call,
 		      __entry->serial,
 		      __print_symbolic(__entry->reason, rxrpc_ack_names),
 		      __entry->ack_first,
 		      __entry->ack_serial,
 		      __entry->n_acks,
-		      __entry->rwind)
+		      __entry->rwind,
+		      __print_symbolic(__entry->trace, rxrpc_propose_ack_traces))
 	    );
 
 TRACE_EVENT(rxrpc_receive,
@@ -1296,9 +1468,9 @@ TRACE_EVENT(rxrpc_rtt_rx,
 	    TP_PROTO(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why,
 		     int slot,
 		     rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial,
-		     u32 rtt, u32 rto),
+		     u32 rtt, u32 srtt, u32 rto),
 
-	    TP_ARGS(call, why, slot, send_serial, resp_serial, rtt, rto),
+	    TP_ARGS(call, why, slot, send_serial, resp_serial, rtt, srtt, rto),
 
 	    TP_STRUCT__entry(
 		    __field(unsigned int,		call)
@@ -1307,7 +1479,9 @@ TRACE_EVENT(rxrpc_rtt_rx,
 		    __field(rxrpc_serial_t,		send_serial)
 		    __field(rxrpc_serial_t,		resp_serial)
 		    __field(u32,			rtt)
+		    __field(u32,			srtt)
 		    __field(u32,			rto)
+		    __field(u32,			min_rtt)
 			     ),
 
 	    TP_fast_assign(
@@ -1317,17 +1491,21 @@ TRACE_EVENT(rxrpc_rtt_rx,
 		    __entry->send_serial = send_serial;
 		    __entry->resp_serial = resp_serial;
 		    __entry->rtt = rtt;
+		    __entry->srtt = srtt;
 		    __entry->rto = rto;
+		    __entry->min_rtt = minmax_get(&call->min_rtt)
 			   ),
 
-	    TP_printk("c=%08x [%d] %s sr=%08x rr=%08x rtt=%u rto=%u",
+	    TP_printk("c=%08x [%d] %s sr=%08x rr=%08x rtt=%u srtt=%u rto=%u min=%u",
 		      __entry->call,
 		      __entry->slot,
 		      __print_symbolic(__entry->why, rxrpc_rtt_rx_traces),
 		      __entry->send_serial,
 		      __entry->resp_serial,
 		      __entry->rtt,
-		      __entry->rto)
+		      __entry->srtt / 8,
+		      __entry->rto,
+		      __entry->min_rtt)
 	    );
 
 TRACE_EVENT(rxrpc_timer_set,
@@ -1544,112 +1722,125 @@ TRACE_EVENT(rxrpc_drop_ack,
 	    );
 
 TRACE_EVENT(rxrpc_retransmit,
-	    TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t seq,
-		     rxrpc_serial_t serial, ktime_t expiry),
+	    TP_PROTO(struct rxrpc_call *call,
+		     struct rxrpc_send_data_req *req,
+		     struct rxrpc_txbuf *txb),
 
-	    TP_ARGS(call, seq, serial, expiry),
+	    TP_ARGS(call, req, txb),
 
 	    TP_STRUCT__entry(
 		    __field(unsigned int,	call)
+		    __field(unsigned int,	qbase)
 		    __field(rxrpc_seq_t,	seq)
 		    __field(rxrpc_serial_t,	serial)
-		    __field(ktime_t,		expiry)
 			     ),
 
 	    TP_fast_assign(
 		    __entry->call = call->debug_id;
-		    __entry->seq = seq;
-		    __entry->serial = serial;
-		    __entry->expiry = expiry;
+		    __entry->qbase = req->tq->qbase;
+		    __entry->seq = req->seq;
+		    __entry->serial = txb->serial;
 			   ),
 
-	    TP_printk("c=%08x q=%x r=%x xp=%lld",
+	    TP_printk("c=%08x tq=%x q=%x r=%x",
 		      __entry->call,
+		      __entry->qbase,
 		      __entry->seq,
-		      __entry->serial,
-		      ktime_to_us(__entry->expiry))
+		      __entry->serial)
 	    );
 
 TRACE_EVENT(rxrpc_congest,
-	    TP_PROTO(struct rxrpc_call *call, struct rxrpc_ack_summary *summary,
-		     rxrpc_serial_t ack_serial, enum rxrpc_congest_change change),
+	    TP_PROTO(struct rxrpc_call *call, struct rxrpc_ack_summary *summary),
 
-	    TP_ARGS(call, summary, ack_serial, change),
+	    TP_ARGS(call, summary),
 
 	    TP_STRUCT__entry(
 		    __field(unsigned int,			call)
-		    __field(enum rxrpc_congest_change,		change)
+		    __field(enum rxrpc_ca_state,		ca_state)
 		    __field(rxrpc_seq_t,			hard_ack)
 		    __field(rxrpc_seq_t,			top)
 		    __field(rxrpc_seq_t,			lowest_nak)
-		    __field(rxrpc_serial_t,			ack_serial)
+		    __field(u16,				nr_sacks)
+		    __field(u16,				nr_snacks)
+		    __field(u16,				cwnd)
+		    __field(u16,				ssthresh)
+		    __field(u16,				cumul_acks)
+		    __field(u16,				dup_acks)
 		    __field_struct(struct rxrpc_ack_summary,	sum)
 			     ),
 
 	    TP_fast_assign(
 		    __entry->call	= call->debug_id;
-		    __entry->change	= change;
+		    __entry->ca_state	= call->cong_ca_state;
 		    __entry->hard_ack	= call->acks_hard_ack;
 		    __entry->top	= call->tx_top;
 		    __entry->lowest_nak	= call->acks_lowest_nak;
-		    __entry->ack_serial	= ack_serial;
+		    __entry->nr_sacks	= call->acks_nr_sacks;
+		    __entry->nr_snacks	= call->acks_nr_snacks;
+		    __entry->cwnd	= call->cong_cwnd;
+		    __entry->ssthresh	= call->cong_ssthresh;
+		    __entry->cumul_acks	= call->cong_cumul_acks;
+		    __entry->dup_acks	= call->cong_dup_acks;
 		    memcpy(&__entry->sum, summary, sizeof(__entry->sum));
 			   ),
 
-	    TP_printk("c=%08x r=%08x %s q=%08x %s cw=%u ss=%u nA=%u,%u+%u,%u b=%u u=%u d=%u l=%x%s%s%s",
+	    TP_printk("c=%08x r=%08x %s q=%08x %s cw=%u ss=%u A=%u+%u/%u+%u r=%u b=%u u=%u d=%u l=%x%s%s%s",
 		      __entry->call,
-		      __entry->ack_serial,
+		      __entry->sum.acked_serial,
 		      __print_symbolic(__entry->sum.ack_reason, rxrpc_ack_names),
 		      __entry->hard_ack,
-		      __print_symbolic(__entry->sum.mode, rxrpc_congest_modes),
-		      __entry->sum.cwnd,
-		      __entry->sum.ssthresh,
-		      __entry->sum.nr_acks, __entry->sum.nr_retained_nacks,
-		      __entry->sum.nr_new_acks,
-		      __entry->sum.nr_new_nacks,
+		      __print_symbolic(__entry->ca_state, rxrpc_ca_states),
+		      __entry->cwnd,
+		      __entry->ssthresh,
+		      __entry->nr_sacks, __entry->sum.nr_new_sacks,
+		      __entry->nr_snacks, __entry->sum.nr_new_snacks,
+		      __entry->sum.nr_new_hacks,
 		      __entry->top - __entry->hard_ack,
-		      __entry->sum.cumulative_acks,
-		      __entry->sum.dup_acks,
-		      __entry->lowest_nak, __entry->sum.new_low_nack ? "!" : "",
-		      __print_symbolic(__entry->change, rxrpc_congest_changes),
+		      __entry->cumul_acks,
+		      __entry->dup_acks,
+		      __entry->lowest_nak, __entry->sum.new_low_snack ? "!" : "",
+		      __print_symbolic(__entry->sum.change, rxrpc_congest_changes),
 		      __entry->sum.retrans_timeo ? " rTxTo" : "")
 	    );
 
 TRACE_EVENT(rxrpc_reset_cwnd,
-	    TP_PROTO(struct rxrpc_call *call, ktime_t now),
+	    TP_PROTO(struct rxrpc_call *call, ktime_t since_last_tx, ktime_t rtt),
 
-	    TP_ARGS(call, now),
+	    TP_ARGS(call, since_last_tx, rtt),
 
 	    TP_STRUCT__entry(
 		    __field(unsigned int,		call)
-		    __field(enum rxrpc_congest_mode,	mode)
+		    __field(enum rxrpc_ca_state,	ca_state)
 		    __field(unsigned short,		cwnd)
 		    __field(unsigned short,		extra)
 		    __field(rxrpc_seq_t,		hard_ack)
 		    __field(rxrpc_seq_t,		prepared)
 		    __field(ktime_t,			since_last_tx)
+		    __field(ktime_t,			rtt)
 		    __field(bool,			has_data)
 			     ),
 
 	    TP_fast_assign(
 		    __entry->call	= call->debug_id;
-		    __entry->mode	= call->cong_mode;
+		    __entry->ca_state	= call->cong_ca_state;
 		    __entry->cwnd	= call->cong_cwnd;
 		    __entry->extra	= call->cong_extra;
 		    __entry->hard_ack	= call->acks_hard_ack;
-		    __entry->prepared	= call->tx_prepared - call->tx_bottom;
-		    __entry->since_last_tx = ktime_sub(now, call->tx_last_sent);
-		    __entry->has_data	= !list_empty(&call->tx_sendmsg);
+		    __entry->prepared	= call->send_top - call->tx_bottom;
+		    __entry->since_last_tx = since_last_tx;
+		    __entry->rtt	= rtt;
+		    __entry->has_data	= call->tx_bottom != call->tx_top;
 			   ),
 
-	    TP_printk("c=%08x q=%08x %s cw=%u+%u pr=%u tm=%llu d=%u",
+	    TP_printk("c=%08x q=%08x %s cw=%u+%u pr=%u tm=%llu/%llu d=%u",
 		      __entry->call,
 		      __entry->hard_ack,
-		      __print_symbolic(__entry->mode, rxrpc_congest_modes),
+		      __print_symbolic(__entry->ca_state, rxrpc_ca_states),
 		      __entry->cwnd,
 		      __entry->extra,
 		      __entry->prepared,
-		      ktime_to_ns(__entry->since_last_tx),
+		      ktime_to_us(__entry->since_last_tx),
+		      ktime_to_us(__entry->rtt),
 		      __entry->has_data)
 	    );
 
@@ -1722,10 +1913,36 @@ TRACE_EVENT(rxrpc_connect_call,
 		      &__entry->srx.transport)
 	    );
 
+TRACE_EVENT(rxrpc_apply_acks,
+	    TP_PROTO(struct rxrpc_call *call, struct rxrpc_txqueue *tq),
+
+	    TP_ARGS(call, tq),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,	call)
+		    __field(unsigned int,	nr_rep)
+		    __field(rxrpc_seq_t,	qbase)
+		    __field(unsigned long,	acks)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->call = call->debug_id;
+		    __entry->qbase = tq->qbase;
+		    __entry->acks = tq->segment_acked;
+		    __entry->nr_rep = tq->nr_reported_acks;
+			   ),
+
+	    TP_printk("c=%08x tq=%x acks=%016lx rep=%u",
+		      __entry->call,
+		      __entry->qbase,
+		      __entry->acks,
+		      __entry->nr_rep)
+	    );
+
 TRACE_EVENT(rxrpc_resend,
-	    TP_PROTO(struct rxrpc_call *call, struct sk_buff *ack),
+	    TP_PROTO(struct rxrpc_call *call, rxrpc_serial_t ack_serial),
 
-	    TP_ARGS(call, ack),
+	    TP_ARGS(call, ack_serial),
 
 	    TP_STRUCT__entry(
 		    __field(unsigned int,	call)
@@ -1735,11 +1952,10 @@ TRACE_EVENT(rxrpc_resend,
 			     ),
 
 	    TP_fast_assign(
-		    struct rxrpc_skb_priv *sp = ack ? rxrpc_skb(ack) : NULL;
 		    __entry->call = call->debug_id;
 		    __entry->seq = call->acks_hard_ack;
 		    __entry->transmitted = call->tx_transmitted;
-		    __entry->ack_serial = sp ? sp->hdr.serial : 0;
+		    __entry->ack_serial = ack_serial;
 			   ),
 
 	    TP_printk("c=%08x r=%x q=%x tq=%x",
@@ -1749,6 +1965,63 @@ TRACE_EVENT(rxrpc_resend,
 		      __entry->transmitted)
 	    );
 
+TRACE_EVENT(rxrpc_resend_lost,
+	    TP_PROTO(struct rxrpc_call *call, struct rxrpc_txqueue *tq, unsigned long lost),
+
+	    TP_ARGS(call, tq, lost),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,	call)
+		    __field(rxrpc_seq_t,	qbase)
+		    __field(u8,			nr_rep)
+		    __field(unsigned long,	lost)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->call = call->debug_id;
+		    __entry->qbase = tq->qbase;
+		    __entry->nr_rep = tq->nr_reported_acks;
+		    __entry->lost = lost;
+			   ),
+
+	    TP_printk("c=%08x tq=%x lost=%016lx nr=%u",
+		      __entry->call,
+		      __entry->qbase,
+		      __entry->lost,
+		      __entry->nr_rep)
+	    );
+
+TRACE_EVENT(rxrpc_rotate,
+	    TP_PROTO(struct rxrpc_call *call, struct rxrpc_txqueue *tq,
+		     struct rxrpc_ack_summary *summary, rxrpc_seq_t seq,
+		     enum rxrpc_rotate_trace trace),
+
+	    TP_ARGS(call, tq, summary, seq, trace),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,	call)
+		    __field(rxrpc_seq_t,	qbase)
+		    __field(rxrpc_seq_t,	seq)
+		    __field(unsigned int,	nr_rep)
+		    __field(enum rxrpc_rotate_trace, trace)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->call = call->debug_id;
+		    __entry->qbase = tq->qbase;
+		    __entry->seq = seq;
+		    __entry->nr_rep = tq->nr_reported_acks;
+		    __entry->trace = trace;
+			   ),
+
+	    TP_printk("c=%08x tq=%x q=%x nr=%x %s",
+		      __entry->call,
+		      __entry->qbase,
+		      __entry->seq,
+		      __entry->nr_rep,
+		      __print_symbolic(__entry->trace, rxrpc_rotate_traces))
+	    );
+
 TRACE_EVENT(rxrpc_rx_icmp,
 	    TP_PROTO(struct rxrpc_peer *peer, struct sock_extended_err *ee,
 		     struct sockaddr_rxrpc *srx),
@@ -1858,38 +2131,36 @@ TRACE_EVENT(rxrpc_notify_socket,
 	    );
 
 TRACE_EVENT(rxrpc_rx_discard_ack,
-	    TP_PROTO(unsigned int debug_id, rxrpc_serial_t serial,
-		     rxrpc_seq_t first_soft_ack, rxrpc_seq_t call_ackr_first,
-		     rxrpc_seq_t prev_pkt, rxrpc_seq_t call_ackr_prev),
+	    TP_PROTO(struct rxrpc_call *call, rxrpc_serial_t serial,
+		     rxrpc_seq_t hard_ack, rxrpc_seq_t prev_pkt),
 
-	    TP_ARGS(debug_id, serial, first_soft_ack, call_ackr_first,
-		    prev_pkt, call_ackr_prev),
+	    TP_ARGS(call, serial, hard_ack, prev_pkt),
 
 	    TP_STRUCT__entry(
 		    __field(unsigned int,	debug_id)
 		    __field(rxrpc_serial_t,	serial)
-		    __field(rxrpc_seq_t,	first_soft_ack)
-		    __field(rxrpc_seq_t,	call_ackr_first)
+		    __field(rxrpc_seq_t,	hard_ack)
 		    __field(rxrpc_seq_t,	prev_pkt)
-		    __field(rxrpc_seq_t,	call_ackr_prev)
+		    __field(rxrpc_seq_t,	acks_hard_ack)
+		    __field(rxrpc_seq_t,	acks_prev_seq)
 			     ),
 
 	    TP_fast_assign(
-		    __entry->debug_id		= debug_id;
+		    __entry->debug_id		= call->debug_id;
 		    __entry->serial		= serial;
-		    __entry->first_soft_ack	= first_soft_ack;
-		    __entry->call_ackr_first	= call_ackr_first;
+		    __entry->hard_ack		= hard_ack;
 		    __entry->prev_pkt		= prev_pkt;
-		    __entry->call_ackr_prev	= call_ackr_prev;
+		    __entry->acks_hard_ack	= call->acks_hard_ack;
+		    __entry->acks_prev_seq	= call->acks_prev_seq;
 			   ),
 
 	    TP_printk("c=%08x r=%08x %08x<%08x %08x<%08x",
 		      __entry->debug_id,
 		      __entry->serial,
-		      __entry->first_soft_ack,
-		      __entry->call_ackr_first,
+		      __entry->hard_ack,
+		      __entry->acks_hard_ack,
 		      __entry->prev_pkt,
-		      __entry->call_ackr_prev)
+		      __entry->acks_prev_seq)
 	    );
 
 TRACE_EVENT(rxrpc_req_ack,
@@ -1947,6 +2218,33 @@ TRACE_EVENT(rxrpc_txbuf,
 		      __entry->ref)
 	    );
 
+TRACE_EVENT(rxrpc_tq,
+	    TP_PROTO(struct rxrpc_call *call, struct rxrpc_txqueue *tq,
+		     rxrpc_seq_t seq, enum rxrpc_tq_trace trace),
+
+	    TP_ARGS(call, tq, seq, trace),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,		call_debug_id)
+		    __field(rxrpc_seq_t,		qbase)
+		    __field(rxrpc_seq_t,		seq)
+		    __field(enum rxrpc_tq_trace,	trace)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->call_debug_id = call->debug_id;
+		    __entry->qbase = tq ? tq->qbase : call->tx_qbase;
+		    __entry->seq = seq;
+		    __entry->trace = trace;
+			   ),
+
+	    TP_printk("c=%08x bq=%08x q=%08x %s",
+		      __entry->call_debug_id,
+		      __entry->qbase,
+		      __entry->seq,
+		      __print_symbolic(__entry->trace, rxrpc_tq_traces))
+	    );
+
 TRACE_EVENT(rxrpc_poke_call,
 	    TP_PROTO(struct rxrpc_call *call, bool busy,
 		     enum rxrpc_call_poke_trace what),
@@ -2015,6 +2313,360 @@ TRACE_EVENT(rxrpc_sack,
 		      __entry->sack)
 	    );
 
+TRACE_EVENT(rxrpc_pmtud_tx,
+	    TP_PROTO(struct rxrpc_call *call),
+
+	    TP_ARGS(call),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,	peer_debug_id)
+		    __field(unsigned int,	call_debug_id)
+		    __field(rxrpc_serial_t,	ping_serial)
+		    __field(unsigned short,	pmtud_trial)
+		    __field(unsigned short,	pmtud_good)
+		    __field(unsigned short,	pmtud_bad)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->peer_debug_id = call->peer->debug_id;
+		    __entry->call_debug_id = call->debug_id;
+		    __entry->ping_serial = call->conn->pmtud_probe;
+		    __entry->pmtud_trial = call->peer->pmtud_trial;
+		    __entry->pmtud_good = call->peer->pmtud_good;
+		    __entry->pmtud_bad = call->peer->pmtud_bad;
+			   ),
+
+	    TP_printk("P=%08x c=%08x pr=%08x %u-%u-%u",
+		      __entry->peer_debug_id,
+		      __entry->call_debug_id,
+		      __entry->ping_serial,
+		      __entry->pmtud_good,
+		      __entry->pmtud_trial,
+		      __entry->pmtud_bad)
+	    );
+
+TRACE_EVENT(rxrpc_pmtud_rx,
+	    TP_PROTO(struct rxrpc_connection *conn, rxrpc_serial_t resp_serial),
+
+	    TP_ARGS(conn, resp_serial),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,	peer_debug_id)
+		    __field(unsigned int,	call_debug_id)
+		    __field(rxrpc_serial_t,	ping_serial)
+		    __field(rxrpc_serial_t,	resp_serial)
+		    __field(unsigned short,	max_data)
+		    __field(u8,			jumbo_max)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->peer_debug_id = conn->peer->debug_id;
+		    __entry->call_debug_id = conn->pmtud_call;
+		    __entry->ping_serial = conn->pmtud_probe;
+		    __entry->resp_serial = resp_serial;
+		    __entry->max_data = conn->peer->max_data;
+		    __entry->jumbo_max = conn->peer->pmtud_jumbo;
+			   ),
+
+	    TP_printk("P=%08x c=%08x pr=%08x rr=%08x max=%u jm=%u",
+		      __entry->peer_debug_id,
+		      __entry->call_debug_id,
+		      __entry->ping_serial,
+		      __entry->resp_serial,
+		      __entry->max_data,
+		      __entry->jumbo_max)
+	    );
+
+TRACE_EVENT(rxrpc_pmtud_lost,
+	    TP_PROTO(struct rxrpc_connection *conn, rxrpc_serial_t resp_serial),
+
+	    TP_ARGS(conn, resp_serial),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,	peer_debug_id)
+		    __field(unsigned int,	call_debug_id)
+		    __field(rxrpc_serial_t,	ping_serial)
+		    __field(rxrpc_serial_t,	resp_serial)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->peer_debug_id = conn->peer->debug_id;
+		    __entry->call_debug_id = conn->pmtud_call;
+		    __entry->ping_serial = conn->pmtud_probe;
+		    __entry->resp_serial = resp_serial;
+			   ),
+
+	    TP_printk("P=%08x c=%08x pr=%08x rr=%08x",
+		      __entry->peer_debug_id,
+		      __entry->call_debug_id,
+		      __entry->ping_serial,
+		      __entry->resp_serial)
+	    );
+
+TRACE_EVENT(rxrpc_pmtud_reduce,
+	    TP_PROTO(struct rxrpc_peer *peer, rxrpc_serial_t serial,
+		     unsigned int max_data, enum rxrpc_pmtud_reduce_trace reason),
+
+	    TP_ARGS(peer, serial, max_data, reason),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,	peer_debug_id)
+		    __field(rxrpc_serial_t,	serial)
+		    __field(unsigned int,	max_data)
+		    __field(enum rxrpc_pmtud_reduce_trace, reason)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->peer_debug_id = peer->debug_id;
+		    __entry->serial = serial;
+		    __entry->max_data = max_data;
+		    __entry->reason = reason;
+			   ),
+
+	    TP_printk("P=%08x %s r=%08x m=%u",
+		      __entry->peer_debug_id,
+		      __print_symbolic(__entry->reason, rxrpc_pmtud_reduce_traces),
+		      __entry->serial, __entry->max_data)
+	    );
+
+TRACE_EVENT(rxrpc_rack,
+	    TP_PROTO(struct rxrpc_call *call, ktime_t timo),
+
+	    TP_ARGS(call, timo),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,	call)
+		    __field(rxrpc_serial_t,	ack_serial)
+		    __field(rxrpc_seq_t,	seq)
+		    __field(enum rxrpc_rack_timer_mode, mode)
+		    __field(unsigned short,	nr_sent)
+		    __field(unsigned short,	nr_lost)
+		    __field(unsigned short,	nr_resent)
+		    __field(unsigned short,	nr_sacked)
+		    __field(ktime_t,		timo)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->call	= call->debug_id;
+		    __entry->ack_serial	= call->rx_serial;
+		    __entry->seq	= call->rack_end_seq;
+		    __entry->mode	= call->rack_timer_mode;
+		    __entry->nr_sent	= call->tx_nr_sent;
+		    __entry->nr_lost	= call->tx_nr_lost;
+		    __entry->nr_resent	= call->tx_nr_resent;
+		    __entry->nr_sacked	= call->acks_nr_sacks;
+		    __entry->timo	= timo;
+			   ),
+
+	    TP_printk("c=%08x r=%08x q=%08x %s slrs=%u,%u,%u,%u t=%lld",
+		      __entry->call, __entry->ack_serial, __entry->seq,
+		      __print_symbolic(__entry->mode, rxrpc_rack_timer_modes),
+		      __entry->nr_sent, __entry->nr_lost,
+		      __entry->nr_resent, __entry->nr_sacked,
+		      ktime_to_us(__entry->timo))
+	    );
+
+TRACE_EVENT(rxrpc_rack_update,
+	    TP_PROTO(struct rxrpc_call *call, struct rxrpc_ack_summary *summary),
+
+	    TP_ARGS(call, summary),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,	call)
+		    __field(rxrpc_serial_t,	ack_serial)
+		    __field(rxrpc_seq_t,	seq)
+		    __field(int,		xmit_ts)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->call	= call->debug_id;
+		    __entry->ack_serial	= call->rx_serial;
+		    __entry->seq	= call->rack_end_seq;
+		    __entry->xmit_ts	= ktime_sub(call->acks_latest_ts, call->rack_xmit_ts);
+			   ),
+
+	    TP_printk("c=%08x r=%08x q=%08x xt=%lld",
+		      __entry->call, __entry->ack_serial, __entry->seq,
+		      ktime_to_us(__entry->xmit_ts))
+	    );
+
+TRACE_EVENT(rxrpc_rack_scan_loss,
+	    TP_PROTO(struct rxrpc_call *call),
+
+	    TP_ARGS(call),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,	call)
+		    __field(ktime_t,		rack_rtt)
+		    __field(ktime_t,		rack_reo_wnd)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->call		= call->debug_id;
+		    __entry->rack_rtt		= call->rack_rtt;
+		    __entry->rack_reo_wnd	= call->rack_reo_wnd;
+			   ),
+
+	    TP_printk("c=%08x rtt=%lld reow=%lld",
+		      __entry->call, ktime_to_us(__entry->rack_rtt),
+		      ktime_to_us(__entry->rack_reo_wnd))
+	    );
+
+TRACE_EVENT(rxrpc_rack_scan_loss_tq,
+	    TP_PROTO(struct rxrpc_call *call, const struct rxrpc_txqueue *tq,
+		     unsigned long nacks),
+
+	    TP_ARGS(call, tq, nacks),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,	call)
+		    __field(rxrpc_seq_t,	qbase)
+		    __field(unsigned long,	nacks)
+		    __field(unsigned long,	lost)
+		    __field(unsigned long,	retrans)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->call	= call->debug_id;
+		    __entry->qbase	= tq->qbase;
+		    __entry->nacks	= nacks;
+		    __entry->lost	= tq->segment_lost;
+		    __entry->retrans	= tq->segment_retransmitted;
+			   ),
+
+	    TP_printk("c=%08x q=%08x n=%lx l=%lx r=%lx",
+		      __entry->call, __entry->qbase,
+		      __entry->nacks, __entry->lost, __entry->retrans)
+	    );
+
+TRACE_EVENT(rxrpc_rack_detect_loss,
+	    TP_PROTO(struct rxrpc_call *call, struct rxrpc_ack_summary *summary,
+		     rxrpc_seq_t seq),
+
+	    TP_ARGS(call, summary, seq),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,	call)
+		    __field(rxrpc_serial_t,	ack_serial)
+		    __field(rxrpc_seq_t,	seq)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->call	= call->debug_id;
+		    __entry->ack_serial	= call->rx_serial;
+		    __entry->seq	= seq;
+			   ),
+
+	    TP_printk("c=%08x r=%08x q=%08x",
+		      __entry->call, __entry->ack_serial, __entry->seq)
+	    );
+
+TRACE_EVENT(rxrpc_rack_mark_loss_tq,
+	    TP_PROTO(struct rxrpc_call *call, const struct rxrpc_txqueue *tq),
+
+	    TP_ARGS(call, tq),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,	call)
+		    __field(rxrpc_seq_t,	qbase)
+		    __field(rxrpc_seq_t,	trans)
+		    __field(unsigned long,	acked)
+		    __field(unsigned long,	lost)
+		    __field(unsigned long,	retrans)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->call	= call->debug_id;
+		    __entry->qbase	= tq->qbase;
+		    __entry->trans	= call->tx_transmitted;
+		    __entry->acked	= tq->segment_acked;
+		    __entry->lost	= tq->segment_lost;
+		    __entry->retrans	= tq->segment_retransmitted;
+			   ),
+
+	    TP_printk("c=%08x tq=%08x txq=%08x a=%lx l=%lx r=%lx",
+		      __entry->call, __entry->qbase, __entry->trans,
+		      __entry->acked, __entry->lost, __entry->retrans)
+	    );
+
+TRACE_EVENT(rxrpc_tlp_probe,
+	    TP_PROTO(struct rxrpc_call *call, enum rxrpc_tlp_probe_trace trace),
+
+	    TP_ARGS(call, trace),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,		call)
+		    __field(rxrpc_serial_t,		serial)
+		    __field(rxrpc_seq_t,		seq)
+		    __field(enum rxrpc_tlp_probe_trace,	trace)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->call	= call->debug_id;
+		    __entry->serial	= call->tlp_serial;
+		    __entry->seq	= call->tlp_seq;
+		    __entry->trace	= trace;
+			   ),
+
+	    TP_printk("c=%08x r=%08x pq=%08x %s",
+		      __entry->call, __entry->serial, __entry->seq,
+		      __print_symbolic(__entry->trace, rxrpc_tlp_probe_traces))
+	    );
+
+TRACE_EVENT(rxrpc_tlp_ack,
+	    TP_PROTO(struct rxrpc_call *call, struct rxrpc_ack_summary *summary,
+		     enum rxrpc_tlp_ack_trace trace),
+
+	    TP_ARGS(call, summary, trace),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,		call)
+		    __field(rxrpc_serial_t,		serial)
+		    __field(rxrpc_seq_t,		tlp_seq)
+		    __field(rxrpc_seq_t,		hard_ack)
+		    __field(enum rxrpc_tlp_ack_trace,	trace)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->call	= call->debug_id;
+		    __entry->serial	= call->tlp_serial;
+		    __entry->tlp_seq	= call->tlp_seq;
+		    __entry->hard_ack	= call->acks_hard_ack;
+		    __entry->trace	= trace;
+			   ),
+
+	    TP_printk("c=%08x r=%08x pq=%08x hq=%08x %s",
+		      __entry->call, __entry->serial,
+		      __entry->tlp_seq, __entry->hard_ack,
+		      __print_symbolic(__entry->trace, rxrpc_tlp_ack_traces))
+	    );
+
+TRACE_EVENT(rxrpc_rack_timer,
+	    TP_PROTO(struct rxrpc_call *call, ktime_t delay, bool exp),
+
+	    TP_ARGS(call, delay, exp),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,		call)
+		    __field(bool,			exp)
+		    __field(enum rxrpc_rack_timer_mode,	mode)
+		    __field(ktime_t,			delay)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->call		= call->debug_id;
+		    __entry->exp		= exp;
+		    __entry->mode		= call->rack_timer_mode;
+		    __entry->delay		= delay;
+			   ),
+
+	    TP_printk("c=%08x %s %s to=%lld",
+		      __entry->call,
+		      __entry->exp ? "Exp" : "Set",
+		      __print_symbolic(__entry->mode, rxrpc_rack_timer_modes),
+		      ktime_to_us(__entry->delay))
+	    );
+
 #undef EM
 #undef E_