From 4d843be56ba6a8c0e566afd58775742d9e721505 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 5 Apr 2022 21:48:48 +0100 Subject: rxrpc: Trace setting of the request-ack flag Add a tracepoint to log why the request-ack flag is set on an outgoing DATA packet, allowing debugging as to why. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index d20bf4aa0204..4c501c660123 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -242,6 +242,16 @@ EM(rxrpc_tx_point_version_keepalive, "VerKeepalive") \ E_(rxrpc_tx_point_version_reply, "VerReply") +#define rxrpc_req_ack_traces \ + EM(rxrpc_reqack_ack_lost, "ACK-LOST ") \ + EM(rxrpc_reqack_already_on, "ALREADY-ON") \ + EM(rxrpc_reqack_more_rtt, "MORE-RTT ") \ + EM(rxrpc_reqack_no_srv_last, "NO-SRVLAST") \ + EM(rxrpc_reqack_old_rtt, "OLD-RTT ") \ + EM(rxrpc_reqack_retrans, "RETRANS ") \ + EM(rxrpc_reqack_slow_start, "SLOW-START") \ + E_(rxrpc_reqack_small_txwin, "SMALL-TXWN") + /* * Generate enums for tracing information. */ @@ -263,6 +273,7 @@ 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_rtt_rx_trace { rxrpc_rtt_rx_traces } __mode(byte); enum rxrpc_rtt_tx_trace { rxrpc_rtt_tx_traces } __mode(byte); enum rxrpc_skb_trace { rxrpc_skb_traces } __mode(byte); @@ -290,6 +301,7 @@ rxrpc_propose_ack_outcomes; rxrpc_propose_ack_traces; rxrpc_receive_traces; rxrpc_recvmsg_traces; +rxrpc_req_ack_traces; rxrpc_rtt_rx_traces; rxrpc_rtt_tx_traces; rxrpc_skb_traces; @@ -1395,6 +1407,30 @@ TRACE_EVENT(rxrpc_rx_discard_ack, __entry->call_ackr_prev) ); +TRACE_EVENT(rxrpc_req_ack, + TP_PROTO(unsigned int call_debug_id, rxrpc_seq_t seq, + enum rxrpc_req_ack_trace why), + + TP_ARGS(call_debug_id, seq, why), + + TP_STRUCT__entry( + __field(unsigned int, call_debug_id ) + __field(rxrpc_seq_t, seq ) + __field(enum rxrpc_req_ack_trace, why ) + ), + + TP_fast_assign( + __entry->call_debug_id = call_debug_id; + __entry->seq = seq; + __entry->why = why; + ), + + TP_printk("c=%08x q=%08x REQ-%s", + __entry->call_debug_id, + __entry->seq, + __print_symbolic(__entry->why, rxrpc_req_ack_traces)) + ); + #undef EM #undef E_ #endif /* _TRACE_RXRPC_H */ -- cgit v1.2.3 From 334dfbfc5a7187c99761df2392dd4cc49c453bea Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 22 Apr 2022 00:20:49 +0100 Subject: rxrpc: Split call timer-expiration from call timer-set tracepoint Split the tracepoint for call timer-set to separate out the call timer-expiration event Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 42 +++++++++++++++++++++++++++++++++++++++++- net/rxrpc/call_object.c | 2 +- 2 files changed, 42 insertions(+), 2 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 4c501c660123..a72f04e3d264 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -133,7 +133,6 @@ #define rxrpc_timer_traces \ EM(rxrpc_timer_begin, "Begin ") \ - EM(rxrpc_timer_expired, "*EXPR*") \ EM(rxrpc_timer_exp_ack, "ExpAck") \ EM(rxrpc_timer_exp_hard, "ExpHrd") \ EM(rxrpc_timer_exp_idle, "ExpIdl") \ @@ -1019,6 +1018,47 @@ TRACE_EVENT(rxrpc_timer, __entry->timer - __entry->now) ); +TRACE_EVENT(rxrpc_timer_expired, + TP_PROTO(struct rxrpc_call *call, unsigned long now), + + TP_ARGS(call, now), + + TP_STRUCT__entry( + __field(unsigned int, call ) + __field(long, now ) + __field(long, ack_at ) + __field(long, ack_lost_at ) + __field(long, resend_at ) + __field(long, ping_at ) + __field(long, expect_rx_by ) + __field(long, expect_req_by ) + __field(long, expect_term_by ) + __field(long, timer ) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->now = now; + __entry->ack_at = call->ack_at; + __entry->ack_lost_at = call->ack_lost_at; + __entry->resend_at = call->resend_at; + __entry->expect_rx_by = call->expect_rx_by; + __entry->expect_req_by = call->expect_req_by; + __entry->expect_term_by = call->expect_term_by; + __entry->timer = call->timer.expires; + ), + + TP_printk("c=%08x EXPIRED a=%ld la=%ld r=%ld xr=%ld xq=%ld xt=%ld t=%ld", + __entry->call, + __entry->ack_at - __entry->now, + __entry->ack_lost_at - __entry->now, + __entry->resend_at - __entry->now, + __entry->expect_rx_by - __entry->now, + __entry->expect_req_by - __entry->now, + __entry->expect_term_by - __entry->now, + __entry->timer - __entry->now) + ); + TRACE_EVENT(rxrpc_rx_lose, TP_PROTO(struct rxrpc_skb_priv *sp), diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 6401cdf7a624..a75861a0c477 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -52,7 +52,7 @@ static void rxrpc_call_timer_expired(struct timer_list *t) _enter("%d", call->debug_id); if (call->state < RXRPC_CALL_COMPLETE) { - trace_rxrpc_timer(call, rxrpc_timer_expired, jiffies); + trace_rxrpc_timer_expired(call, jiffies); __rxrpc_queue_call(call); } else { rxrpc_put_call(call, rxrpc_call_put); -- cgit v1.2.3 From f7fa52421f76309c574f2575701660bc3ea3a705 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 18 Aug 2022 11:52:36 +0100 Subject: rxrpc: Record stats for why the REQUEST-ACK flag is being set Record stats for why the REQUEST-ACK flag is being set. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 1 + net/rxrpc/ar-internal.h | 2 ++ net/rxrpc/output.c | 1 + net/rxrpc/proc.c | 14 ++++++++++++++ 4 files changed, 18 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index a72f04e3d264..794523d15321 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -250,6 +250,7 @@ EM(rxrpc_reqack_retrans, "RETRANS ") \ EM(rxrpc_reqack_slow_start, "SLOW-START") \ E_(rxrpc_reqack_small_txwin, "SMALL-TXWN") +/* ---- Must update size of stat_why_req_ack[] if more are added! */ /* * Generate enums for tracing information. diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 8ed707a11d43..436a1e8d0abd 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -107,6 +107,8 @@ struct rxrpc_net { atomic_t stat_tx_ack_skip; atomic_t stat_tx_acks[256]; atomic_t stat_rx_acks[256]; + + atomic_t stat_why_req_ack[8]; }; /* diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index f350d39e3a60..77ed46ab33c5 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -430,6 +430,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, else goto dont_set_request_ack; + rxrpc_inc_stat(call->rxnet, stat_why_req_ack[why]); trace_rxrpc_req_ack(call->debug_id, sp->hdr.seq, why); if (why != rxrpc_reqack_no_srv_last) whdr.flags |= RXRPC_REQUEST_ACK; diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index 488c403f1d33..9bd357f39c39 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -445,6 +445,18 @@ int rxrpc_stats_show(struct seq_file *seq, void *v) atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_PING_RESPONSE]), atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_DELAY]), atomic_read(&rxnet->stat_rx_acks[RXRPC_ACK_IDLE])); + seq_printf(seq, + "Why-Req-A: acklost=%u already=%u mrtt=%u ortt=%u\n", + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_ack_lost]), + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_already_on]), + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_more_rtt]), + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_old_rtt])); + seq_printf(seq, + "Why-Req-A: nolast=%u retx=%u slows=%u smtxw=%u\n", + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_no_srv_last]), + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_retrans]), + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_slow_start]), + atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_small_txwin])); seq_printf(seq, "Buffers : txb=%u rxb=%u\n", atomic_read(&rxrpc_n_tx_skbs), @@ -476,5 +488,7 @@ int rxrpc_stats_clear(struct file *file, char *buf, size_t size) atomic_set(&rxnet->stat_tx_ack_skip, 0); memset(&rxnet->stat_tx_acks, 0, sizeof(rxnet->stat_tx_acks)); memset(&rxnet->stat_rx_acks, 0, sizeof(rxnet->stat_rx_acks)); + + memset(&rxnet->stat_why_req_ack, 0, sizeof(rxnet->stat_why_req_ack)); return size; } -- cgit v1.2.3 From 27f699ccb89d65165175525254fec3d9d6b8d500 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 7 Oct 2022 13:52:06 +0100 Subject: rxrpc: Remove the flags from the rxrpc_skb tracepoint Remove the flags from the rxrpc_skb tracepoint as we're no longer going to be using this for the transmission buffers and so marking which are transmission buffers isn't going to be necessary. Note that this also remove the rxrpc skb flag that indicates if this is a transmission buffer and so the count is not updated for the moment. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 9 +++------ net/rxrpc/ar-internal.h | 1 - net/rxrpc/sendmsg.c | 1 - net/rxrpc/skbuff.c | 20 +++++++------------- 4 files changed, 10 insertions(+), 21 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 794523d15321..484c8d032ab8 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -461,14 +461,13 @@ TRACE_EVENT(rxrpc_call, TRACE_EVENT(rxrpc_skb, TP_PROTO(struct sk_buff *skb, enum rxrpc_skb_trace op, - int usage, int mod_count, u8 flags, const void *where), + int usage, int mod_count, const void *where), - TP_ARGS(skb, op, usage, mod_count, flags, where), + TP_ARGS(skb, op, usage, mod_count, where), TP_STRUCT__entry( __field(struct sk_buff *, skb ) __field(enum rxrpc_skb_trace, op ) - __field(u8, flags ) __field(int, usage ) __field(int, mod_count ) __field(const void *, where ) @@ -476,16 +475,14 @@ TRACE_EVENT(rxrpc_skb, TP_fast_assign( __entry->skb = skb; - __entry->flags = flags; __entry->op = op; __entry->usage = usage; __entry->mod_count = mod_count; __entry->where = where; ), - TP_printk("s=%p %cx %s u=%d m=%d p=%pSR", + TP_printk("s=%p Rx %s u=%d m=%d p=%pSR", __entry->skb, - __entry->flags & RXRPC_SKB_TX_BUFFER ? 'T' : 'R', __print_symbolic(__entry->op, rxrpc_skb_traces), __entry->usage, __entry->mod_count, diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index ba0ee5d1c723..92f20b6c23ca 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -198,7 +198,6 @@ struct rxrpc_skb_priv { u8 nr_subpackets; /* Number of subpackets */ u8 rx_flags; /* Received packet flags */ #define RXRPC_SKB_INCL_LAST 0x01 /* - Includes last packet */ -#define RXRPC_SKB_TX_BUFFER 0x02 /* - Is transmit buffer */ union { int remain; /* amount of space remaining for next write */ diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index ad6f2cd08916..b2d28aa12e10 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -363,7 +363,6 @@ reload: goto maybe_error; sp = rxrpc_skb(skb); - sp->rx_flags |= RXRPC_SKB_TX_BUFFER; rxrpc_new_skb(skb, rxrpc_skb_new); _debug("ALLOC SEND %p", skb); diff --git a/net/rxrpc/skbuff.c b/net/rxrpc/skbuff.c index 580a5acffee7..0c827d5bb2b8 100644 --- a/net/rxrpc/skbuff.c +++ b/net/rxrpc/skbuff.c @@ -14,8 +14,7 @@ #include #include "ar-internal.h" -#define is_tx_skb(skb) (rxrpc_skb(skb)->rx_flags & RXRPC_SKB_TX_BUFFER) -#define select_skb_count(skb) (is_tx_skb(skb) ? &rxrpc_n_tx_skbs : &rxrpc_n_rx_skbs) +#define select_skb_count(skb) (&rxrpc_n_rx_skbs) /* * Note the allocation or reception of a socket buffer. @@ -24,8 +23,7 @@ void rxrpc_new_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) { const void *here = __builtin_return_address(0); int n = atomic_inc_return(select_skb_count(skb)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, - rxrpc_skb(skb)->rx_flags, here); + trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); } /* @@ -36,8 +34,7 @@ void rxrpc_see_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) const void *here = __builtin_return_address(0); if (skb) { int n = atomic_read(select_skb_count(skb)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, - rxrpc_skb(skb)->rx_flags, here); + trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); } } @@ -48,8 +45,7 @@ void rxrpc_get_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) { const void *here = __builtin_return_address(0); int n = atomic_inc_return(select_skb_count(skb)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, - rxrpc_skb(skb)->rx_flags, here); + trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); skb_get(skb); } @@ -60,7 +56,7 @@ void rxrpc_eaten_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) { const void *here = __builtin_return_address(0); int n = atomic_inc_return(&rxrpc_n_rx_skbs); - trace_rxrpc_skb(skb, op, 0, n, 0, here); + trace_rxrpc_skb(skb, op, 0, n, here); } /* @@ -72,8 +68,7 @@ void rxrpc_free_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) if (skb) { int n; n = atomic_dec_return(select_skb_count(skb)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, - rxrpc_skb(skb)->rx_flags, here); + trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); kfree_skb(skb); } } @@ -88,8 +83,7 @@ void rxrpc_purge_queue(struct sk_buff_head *list) while ((skb = skb_dequeue((list))) != NULL) { int n = atomic_dec_return(select_skb_count(skb)); trace_rxrpc_skb(skb, rxrpc_skb_purged, - refcount_read(&skb->users), n, - rxrpc_skb(skb)->rx_flags, here); + refcount_read(&skb->users), n, here); kfree_skb(skb); } } -- cgit v1.2.3 From 02a1935640f8f8539b8f2dbd6eeb539de93b2ce4 Mon Sep 17 00:00:00 2001 From: David Howells Date: Tue, 5 Apr 2022 21:16:32 +0100 Subject: rxrpc: Define rxrpc_txbuf struct to carry data to be transmitted Define a struct, rxrpc_txbuf, to carry data to be transmitted instead of a socket buffer so that it can be placed onto multiple queues at once. This also allows the data buffer to be in the same allocation as the internal data. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 45 +++++++++++++++++++ net/rxrpc/Makefile | 1 + net/rxrpc/ar-internal.h | 53 +++++++++++++++++++++++ net/rxrpc/proc.c | 3 +- net/rxrpc/txbuf.c | 100 +++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 201 insertions(+), 1 deletion(-) create mode 100644 net/rxrpc/txbuf.c (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 484c8d032ab8..47b157b1d32b 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -252,6 +252,18 @@ E_(rxrpc_reqack_small_txwin, "SMALL-TXWN") /* ---- 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_trans, "GET TRANS ") \ + EM(rxrpc_txbuf_get_retrans, "GET RETRANS") \ + EM(rxrpc_txbuf_put_cleaned, "PUT CLEANED") \ + EM(rxrpc_txbuf_put_rotated, "PUT ROTATED") \ + EM(rxrpc_txbuf_put_send_aborted, "PUT SEND-X ") \ + EM(rxrpc_txbuf_see_send_more, "SEE SEND+ ") \ + E_(rxrpc_txbuf_see_unacked, "SEE UNACKED") + /* * Generate enums for tracing information. */ @@ -280,6 +292,7 @@ enum rxrpc_skb_trace { rxrpc_skb_traces } __mode(byte); enum rxrpc_timer_trace { rxrpc_timer_traces } __mode(byte); enum rxrpc_transmit_trace { rxrpc_transmit_traces } __mode(byte); enum rxrpc_tx_point { rxrpc_tx_points } __mode(byte); +enum rxrpc_txbuf_trace { rxrpc_txbuf_traces } __mode(byte); #endif /* end __RXRPC_DECLARE_TRACE_ENUMS_ONCE_ONLY */ @@ -308,6 +321,7 @@ rxrpc_skb_traces; rxrpc_timer_traces; rxrpc_transmit_traces; rxrpc_tx_points; +rxrpc_txbuf_traces; /* * Now redefine the EM() and E_() macros to map the enums to the strings that @@ -1469,6 +1483,37 @@ TRACE_EVENT(rxrpc_req_ack, __print_symbolic(__entry->why, rxrpc_req_ack_traces)) ); +TRACE_EVENT(rxrpc_txbuf, + TP_PROTO(unsigned int debug_id, + unsigned int call_debug_id, rxrpc_seq_t seq, + int ref, enum rxrpc_txbuf_trace what), + + TP_ARGS(debug_id, call_debug_id, seq, ref, what), + + TP_STRUCT__entry( + __field(unsigned int, debug_id ) + __field(unsigned int, call_debug_id ) + __field(rxrpc_seq_t, seq ) + __field(int, ref ) + __field(enum rxrpc_txbuf_trace, what ) + ), + + TP_fast_assign( + __entry->debug_id = debug_id; + __entry->call_debug_id = call_debug_id; + __entry->seq = seq; + __entry->ref = ref; + __entry->what = what; + ), + + TP_printk("B=%08x c=%08x q=%08x %s r=%d", + __entry->debug_id, + __entry->call_debug_id, + __entry->seq, + __print_symbolic(__entry->what, rxrpc_txbuf_traces), + __entry->ref) + ); + #undef EM #undef E_ #endif /* _TRACE_RXRPC_H */ diff --git a/net/rxrpc/Makefile b/net/rxrpc/Makefile index b11281bed2a4..fdeba488fc6e 100644 --- a/net/rxrpc/Makefile +++ b/net/rxrpc/Makefile @@ -30,6 +30,7 @@ rxrpc-y := \ sendmsg.o \ server_key.o \ skbuff.o \ + txbuf.o \ utils.o rxrpc-$(CONFIG_PROC_FS) += proc.o diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 282cb986f8a7..49e90614d5e5 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -29,6 +29,7 @@ struct rxrpc_crypt { struct key_preparsed_payload; struct rxrpc_connection; +struct rxrpc_txbuf; /* * Mark applied to socket buffers in skb->mark. skb->priority is used @@ -759,6 +760,48 @@ struct rxrpc_send_params { bool upgrade; /* If the connection is upgradeable */ }; +/* + * Buffer of data to be output as a packet. + */ +struct rxrpc_txbuf { + struct rcu_head rcu; + struct list_head call_link; /* Link in call->tx_queue */ + struct list_head tx_link; /* Link in live Enc queue or Tx queue */ + struct rxrpc_call *call; /* Call to which belongs */ + ktime_t last_sent; /* Time at which last transmitted */ + refcount_t ref; + rxrpc_seq_t seq; /* Sequence number of this packet */ + unsigned int call_debug_id; + unsigned int debug_id; + unsigned int len; /* Amount of data in buffer */ + unsigned int space; /* Remaining data space */ + unsigned int offset; /* Offset of fill point */ + unsigned long flags; +#define RXRPC_TXBUF_ACKED 0 /* Set if ACK'd */ +#define RXRPC_TXBUF_NACKED 1 /* Set if NAK'd */ +#define RXRPC_TXBUF_LAST 2 /* Set if last packet in Tx phase */ +#define RXRPC_TXBUF_RESENT 3 /* Set if has been resent */ +#define RXRPC_TXBUF_RETRANS 4 /* Set if should be retransmitted */ + struct { + /* The packet for encrypting and DMA'ing. We align it such + * that data[] aligns correctly for any crypto blocksize. + */ + u8 pad[64 - sizeof(struct rxrpc_wire_header)]; + struct rxrpc_wire_header wire; /* Network-ready header */ + u8 data[RXRPC_JUMBO_DATALEN]; /* Data packet */ + } __aligned(64); +}; + +static inline bool rxrpc_sending_to_server(const struct rxrpc_txbuf *txb) +{ + return txb->wire.flags & RXRPC_CLIENT_INITIATED; +} + +static inline bool rxrpc_sending_to_client(const struct rxrpc_txbuf *txb) +{ + return !rxrpc_sending_to_server(txb); +} + #include /* @@ -1125,6 +1168,16 @@ static inline int __init rxrpc_sysctl_init(void) { return 0; } static inline void rxrpc_sysctl_exit(void) {} #endif +/* + * txbuf.c + */ +extern atomic_t rxrpc_nr_txbuf; +struct rxrpc_txbuf *rxrpc_alloc_txbuf(struct rxrpc_call *call, u8 packet_type, + gfp_t gfp); +void rxrpc_get_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what); +void rxrpc_see_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what); +void rxrpc_put_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what); + /* * utils.c */ diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index 9bd357f39c39..3877afd23598 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -458,7 +458,8 @@ int rxrpc_stats_show(struct seq_file *seq, void *v) atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_slow_start]), atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_small_txwin])); seq_printf(seq, - "Buffers : txb=%u rxb=%u\n", + "Buffers : txb=%u,%u rxb=%u\n", + atomic_read(&rxrpc_nr_txbuf), atomic_read(&rxrpc_n_tx_skbs), atomic_read(&rxrpc_n_rx_skbs)); return 0; diff --git a/net/rxrpc/txbuf.c b/net/rxrpc/txbuf.c new file mode 100644 index 000000000000..66d922ad65d0 --- /dev/null +++ b/net/rxrpc/txbuf.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* RxRPC Tx data buffering. + * + * Copyright (C) 2022 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include "ar-internal.h" + +static atomic_t rxrpc_txbuf_debug_ids; +atomic_t rxrpc_nr_txbuf; + +/* + * Allocate and partially initialise an I/O request structure. + */ +struct rxrpc_txbuf *rxrpc_alloc_txbuf(struct rxrpc_call *call, u8 packet_type, + gfp_t gfp) +{ + struct rxrpc_txbuf *txb; + + txb = kmalloc(sizeof(*txb), gfp); + if (txb) { + INIT_LIST_HEAD(&txb->call_link); + INIT_LIST_HEAD(&txb->tx_link); + refcount_set(&txb->ref, 1); + txb->call = call; + txb->call_debug_id = call->debug_id; + txb->debug_id = atomic_inc_return(&rxrpc_txbuf_debug_ids); + txb->space = sizeof(txb->data); + txb->len = 0; + txb->offset = 0; + txb->flags = 0; + txb->seq = call->tx_top + 1; + txb->wire.epoch = htonl(call->conn->proto.epoch); + txb->wire.cid = htonl(call->cid); + txb->wire.callNumber = htonl(call->call_id); + txb->wire.seq = htonl(txb->seq); + txb->wire.type = packet_type; + txb->wire.flags = call->conn->out_clientflag; + txb->wire.userStatus = 0; + txb->wire.securityIndex = call->security_ix; + txb->wire._rsvd = 0; + txb->wire.serviceId = htons(call->service_id); + + trace_rxrpc_txbuf(txb->debug_id, + txb->call_debug_id, txb->seq, 1, + packet_type == RXRPC_PACKET_TYPE_DATA ? + rxrpc_txbuf_alloc_data : + rxrpc_txbuf_alloc_ack); + atomic_inc(&rxrpc_nr_txbuf); + } + + return txb; +} + +void rxrpc_get_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what) +{ + int r; + + __refcount_inc(&txb->ref, &r); + trace_rxrpc_txbuf(txb->debug_id, txb->call_debug_id, txb->seq, r + 1, what); +} + +void rxrpc_see_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what) +{ + int r = refcount_read(&txb->ref); + + trace_rxrpc_txbuf(txb->debug_id, txb->call_debug_id, txb->seq, r, what); +} + +static void rxrpc_free_txbuf(struct rcu_head *rcu) +{ + struct rxrpc_txbuf *txb = container_of(rcu, struct rxrpc_txbuf, rcu); + + trace_rxrpc_txbuf(txb->debug_id, txb->call_debug_id, txb->seq, 0, + rxrpc_txbuf_free); + kfree(txb); + atomic_dec(&rxrpc_nr_txbuf); +} + +void rxrpc_put_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what) +{ + unsigned int debug_id, call_debug_id; + rxrpc_seq_t seq; + bool dead; + int r; + + if (txb) { + debug_id = txb->debug_id; + call_debug_id = txb->call_debug_id; + seq = txb->seq; + dead = __refcount_dec_and_test(&txb->ref, &r); + trace_rxrpc_txbuf(debug_id, call_debug_id, seq, r - 1, what); + if (dead) + call_rcu(&txb->rcu, rxrpc_free_txbuf); + } +} -- cgit v1.2.3 From 72f0c6fb057971864fe4d42b289b8e6ede836ef1 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 30 Jan 2020 21:48:13 +0000 Subject: rxrpc: Allocate ACK records at proposal and queue for transmission Allocate rxrpc_txbuf records for ACKs and put onto a queue for the transmitter thread to dispatch. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 47 ++++++++--- net/rxrpc/ar-internal.h | 21 +++-- net/rxrpc/call_accept.c | 5 +- net/rxrpc/call_event.c | 189 ++++++++++++++++++++++++------------------- net/rxrpc/input.c | 89 +++++++++----------- net/rxrpc/local_object.c | 7 ++ net/rxrpc/output.c | 157 +++++++++++++++++------------------ net/rxrpc/recvmsg.c | 33 +++----- net/rxrpc/sendmsg.c | 4 +- net/rxrpc/txbuf.c | 1 + 10 files changed, 285 insertions(+), 268 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 47b157b1d32b..1597ff7ad97e 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -34,7 +34,8 @@ EM(rxrpc_local_new, "NEW") \ EM(rxrpc_local_processing, "PRO") \ EM(rxrpc_local_put, "PUT") \ - E_(rxrpc_local_queued, "QUE") + EM(rxrpc_local_queued, "QUE") \ + E_(rxrpc_local_tx_ack, "TAK") #define rxrpc_peer_traces \ EM(rxrpc_peer_got, "GOT") \ @@ -258,7 +259,9 @@ EM(rxrpc_txbuf_free, "FREE ") \ 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_see_send_more, "SEE SEND+ ") \ @@ -1095,19 +1098,16 @@ TRACE_EVENT(rxrpc_rx_lose, TRACE_EVENT(rxrpc_propose_ack, TP_PROTO(struct rxrpc_call *call, enum rxrpc_propose_ack_trace why, - u8 ack_reason, rxrpc_serial_t serial, bool immediate, - bool background, enum rxrpc_propose_ack_outcome outcome), + u8 ack_reason, rxrpc_serial_t serial, + enum rxrpc_propose_ack_outcome outcome), - TP_ARGS(call, why, ack_reason, serial, immediate, background, - outcome), + TP_ARGS(call, why, ack_reason, serial, outcome), TP_STRUCT__entry( __field(unsigned int, call ) __field(enum rxrpc_propose_ack_trace, why ) __field(rxrpc_serial_t, serial ) __field(u8, ack_reason ) - __field(bool, immediate ) - __field(bool, background ) __field(enum rxrpc_propose_ack_outcome, outcome ) ), @@ -1116,21 +1116,44 @@ TRACE_EVENT(rxrpc_propose_ack, __entry->why = why; __entry->serial = serial; __entry->ack_reason = ack_reason; - __entry->immediate = immediate; - __entry->background = background; __entry->outcome = outcome; ), - TP_printk("c=%08x %s %s r=%08x i=%u b=%u%s", + TP_printk("c=%08x %s %s r=%08x%s", __entry->call, __print_symbolic(__entry->why, rxrpc_propose_ack_traces), __print_symbolic(__entry->ack_reason, rxrpc_ack_names), __entry->serial, - __entry->immediate, - __entry->background, __print_symbolic(__entry->outcome, rxrpc_propose_ack_outcomes)) ); +TRACE_EVENT(rxrpc_send_ack, + TP_PROTO(struct rxrpc_call *call, enum rxrpc_propose_ack_trace why, + u8 ack_reason, rxrpc_serial_t serial), + + TP_ARGS(call, why, ack_reason, serial), + + TP_STRUCT__entry( + __field(unsigned int, call ) + __field(enum rxrpc_propose_ack_trace, why ) + __field(rxrpc_serial_t, serial ) + __field(u8, ack_reason ) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->why = why; + __entry->serial = serial; + __entry->ack_reason = ack_reason; + ), + + TP_printk("c=%08x %s %s r=%08x", + __entry->call, + __print_symbolic(__entry->why, rxrpc_propose_ack_traces), + __print_symbolic(__entry->ack_reason, rxrpc_ack_names), + __entry->serial) + ); + TRACE_EVENT(rxrpc_retransmit, TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t seq, u8 annotation, s64 expiry), diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 49e90614d5e5..802a8f372af2 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -292,6 +292,8 @@ struct rxrpc_local { struct hlist_node link; struct socket *socket; /* my UDP socket */ struct work_struct processor; + struct list_head ack_tx_queue; /* List of ACKs that need sending */ + spinlock_t ack_tx_lock; /* ACK list lock */ struct rxrpc_sock __rcu *service; /* Service(s) listening on this endpoint */ struct rw_semaphore defrag_sem; /* control re-enablement of IP DF bit */ struct sk_buff_head reject_queue; /* packets awaiting rejection */ @@ -520,10 +522,8 @@ enum rxrpc_call_flag { * Events that can be raised on a call. */ enum rxrpc_call_event { - RXRPC_CALL_EV_ACK, /* need to generate ACK */ RXRPC_CALL_EV_ABORT, /* need to generate abort */ RXRPC_CALL_EV_RESEND, /* Tx resend required */ - RXRPC_CALL_EV_PING, /* Ping send required */ RXRPC_CALL_EV_EXPIRED, /* Expiry occurred */ RXRPC_CALL_EV_ACK_LOST, /* ACK may be lost, send ping */ }; @@ -782,13 +782,20 @@ struct rxrpc_txbuf { #define RXRPC_TXBUF_LAST 2 /* Set if last packet in Tx phase */ #define RXRPC_TXBUF_RESENT 3 /* Set if has been resent */ #define RXRPC_TXBUF_RETRANS 4 /* Set if should be retransmitted */ + u8 /*enum rxrpc_propose_ack_trace*/ ack_why; /* If ack, why */ struct { /* The packet for encrypting and DMA'ing. We align it such * that data[] aligns correctly for any crypto blocksize. */ u8 pad[64 - sizeof(struct rxrpc_wire_header)]; struct rxrpc_wire_header wire; /* Network-ready header */ - u8 data[RXRPC_JUMBO_DATALEN]; /* Data packet */ + union { + u8 data[RXRPC_JUMBO_DATALEN]; /* Data packet */ + struct { + struct rxrpc_ackpacket ack; + u8 acks[0]; + }; + }; } __aligned(64); }; @@ -824,8 +831,10 @@ int rxrpc_user_charge_accept(struct rxrpc_sock *, unsigned long); /* * call_event.c */ -void rxrpc_propose_ACK(struct rxrpc_call *, u8, u32, bool, bool, - enum rxrpc_propose_ack_trace); +void rxrpc_propose_ping(struct rxrpc_call *call, u32 serial, + enum rxrpc_propose_ack_trace why); +void rxrpc_send_ACK(struct rxrpc_call *, u8, rxrpc_serial_t, enum rxrpc_propose_ack_trace); +void rxrpc_propose_ACK(struct rxrpc_call *, u8, u32, enum rxrpc_propose_ack_trace); void rxrpc_process_call(struct work_struct *); void rxrpc_reduce_call_timer(struct rxrpc_call *call, @@ -1030,7 +1039,7 @@ static inline struct rxrpc_net *rxrpc_net(struct net *net) /* * output.c */ -int rxrpc_send_ack_packet(struct rxrpc_call *, bool, rxrpc_serial_t *); +void rxrpc_transmit_ack_packets(struct rxrpc_local *); int rxrpc_send_abort_packet(struct rxrpc_call *); int rxrpc_send_data_packet(struct rxrpc_call *, struct sk_buff *, bool); void rxrpc_reject_packets(struct rxrpc_local *); diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 99e10eea3732..d8db277d5ebe 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -248,9 +248,8 @@ static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb) if (call->peer->rtt_count < 3 || ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), now)) - rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial, - true, true, - rxrpc_propose_ack_ping_for_params); + rxrpc_send_ACK(call, RXRPC_ACK_PING, sp->hdr.serial, + rxrpc_propose_ack_ping_for_params); } /* diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 70f70a0393f7..67b54ad914a1 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -20,46 +20,39 @@ /* * Propose a PING ACK be sent. */ -static void rxrpc_propose_ping(struct rxrpc_call *call, - bool immediate, bool background) +void rxrpc_propose_ping(struct rxrpc_call *call, u32 serial, + enum rxrpc_propose_ack_trace why) { - if (immediate) { - if (background && - !test_and_set_bit(RXRPC_CALL_EV_PING, &call->events)) - rxrpc_queue_call(call); - } else { - unsigned long now = jiffies; - unsigned long ping_at = now + rxrpc_idle_ack_delay; + unsigned long now = jiffies; + unsigned long ping_at = now + rxrpc_idle_ack_delay; - if (time_before(ping_at, call->ping_at)) { - WRITE_ONCE(call->ping_at, ping_at); - rxrpc_reduce_call_timer(call, ping_at, now, - rxrpc_timer_set_for_ping); - } + spin_lock_bh(&call->lock); + + if (time_before(ping_at, call->ping_at)) { + rxrpc_inc_stat(call->rxnet, stat_tx_acks[RXRPC_ACK_PING]); + WRITE_ONCE(call->ping_at, ping_at); + rxrpc_reduce_call_timer(call, ping_at, now, + rxrpc_timer_set_for_ping); + trace_rxrpc_propose_ack(call, why, RXRPC_ACK_PING, serial, + rxrpc_propose_ack_use); } + + spin_unlock_bh(&call->lock); } /* * propose an ACK be sent */ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, - u32 serial, bool immediate, bool background, - enum rxrpc_propose_ack_trace why) + u32 serial, enum rxrpc_propose_ack_trace why) { enum rxrpc_propose_ack_outcome outcome = rxrpc_propose_ack_use; unsigned long expiry = rxrpc_soft_ack_delay; + unsigned long now = jiffies, ack_at; s8 prior = rxrpc_ack_priority[ack_reason]; rxrpc_inc_stat(call->rxnet, stat_tx_acks[ack_reason]); - /* Pings are handled specially because we don't want to accidentally - * lose a ping response by subsuming it into a ping. - */ - if (ack_reason == RXRPC_ACK_PING) { - rxrpc_propose_ping(call, immediate, background); - goto trace; - } - /* Update DELAY, IDLE, REQUESTED and PING_RESPONSE ACK serial * numbers, but we don't alter the timeout. */ @@ -71,8 +64,6 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, outcome = rxrpc_propose_ack_update; call->ackr_serial = serial; } - if (!immediate) - goto trace; } else if (prior > rxrpc_ack_priority[call->ackr_reason]) { call->ackr_reason = ack_reason; call->ackr_serial = serial; @@ -84,8 +75,6 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, case RXRPC_ACK_REQUESTED: if (rxrpc_requested_ack_delay < expiry) expiry = rxrpc_requested_ack_delay; - if (serial == 1) - immediate = false; break; case RXRPC_ACK_DELAY: @@ -99,52 +88,89 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, break; default: - immediate = true; - break; + WARN_ON(1); + return; } - if (test_bit(RXRPC_CALL_EV_ACK, &call->events)) { - _debug("already scheduled"); - } else if (immediate || expiry == 0) { - _debug("immediate ACK %lx", call->events); - if (!test_and_set_bit(RXRPC_CALL_EV_ACK, &call->events) && - background) - rxrpc_queue_call(call); - } else { - unsigned long now = jiffies, ack_at; - - if (call->peer->srtt_us != 0) - ack_at = usecs_to_jiffies(call->peer->srtt_us >> 3); - else - ack_at = expiry; - - ack_at += READ_ONCE(call->tx_backoff); - ack_at += now; - if (time_before(ack_at, call->ack_at)) { - WRITE_ONCE(call->ack_at, ack_at); - rxrpc_reduce_call_timer(call, ack_at, now, - rxrpc_timer_set_for_ack); - } + + if (call->peer->srtt_us != 0) + ack_at = usecs_to_jiffies(call->peer->srtt_us >> 3); + else + ack_at = expiry; + + ack_at += READ_ONCE(call->tx_backoff); + ack_at += now; + if (time_before(ack_at, call->ack_at)) { + WRITE_ONCE(call->ack_at, ack_at); + rxrpc_reduce_call_timer(call, ack_at, now, + rxrpc_timer_set_for_ack); } -trace: - trace_rxrpc_propose_ack(call, why, ack_reason, serial, immediate, - background, outcome); + trace_rxrpc_propose_ack(call, why, ack_reason, serial, outcome); } /* * propose an ACK be sent, locking the call structure */ -void rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, - u32 serial, bool immediate, bool background, +void rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, u32 serial, enum rxrpc_propose_ack_trace why) { spin_lock_bh(&call->lock); - __rxrpc_propose_ACK(call, ack_reason, serial, - immediate, background, why); + __rxrpc_propose_ACK(call, ack_reason, serial, why); spin_unlock_bh(&call->lock); } +/* + * Queue an ACK for immediate transmission. + */ +void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason, + rxrpc_serial_t serial, enum rxrpc_propose_ack_trace why) +{ + struct rxrpc_local *local = call->conn->params.local; + struct rxrpc_txbuf *txb; + + if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) + return; + + rxrpc_inc_stat(call->rxnet, stat_tx_acks[ack_reason]); + + txb = rxrpc_alloc_txbuf(call, RXRPC_PACKET_TYPE_ACK, + in_softirq() ? GFP_ATOMIC | __GFP_NOWARN : GFP_NOFS); + if (!txb) { + kleave(" = -ENOMEM"); + return; + } + + txb->ack_why = why; + txb->wire.seq = 0; + txb->wire.type = RXRPC_PACKET_TYPE_ACK; + txb->wire.flags |= RXRPC_SLOW_START_OK; + txb->ack.bufferSpace = 0; + txb->ack.maxSkew = 0; + txb->ack.firstPacket = 0; + txb->ack.previousPacket = 0; + txb->ack.serial = htonl(serial); + txb->ack.reason = ack_reason; + txb->ack.nAcks = 0; + + if (!rxrpc_try_get_call(call, rxrpc_call_got)) { + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_nomem); + return; + } + + spin_lock_bh(&local->ack_tx_lock); + list_add_tail(&txb->tx_link, &local->ack_tx_queue); + spin_unlock_bh(&local->ack_tx_lock); + trace_rxrpc_send_ack(call, why, ack_reason, serial); + + if (in_task()) { + rxrpc_transmit_ack_packets(call->peer->local); + } else { + rxrpc_get_local(local); + rxrpc_queue_local(local); + } +} + /* * Handle congestion being detected by the retransmit timeout. */ @@ -230,9 +256,8 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) ack_ts = ktime_sub(now, call->acks_latest_ts); if (ktime_to_us(ack_ts) < (call->peer->srtt_us >> 3)) goto out; - rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, false, - rxrpc_propose_ack_ping_for_lost_ack); - rxrpc_send_ack_packet(call, true, NULL); + rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, + rxrpc_propose_ack_ping_for_lost_ack); goto out; } @@ -291,9 +316,10 @@ void rxrpc_process_call(struct work_struct *work) { struct rxrpc_call *call = container_of(work, struct rxrpc_call, processor); - rxrpc_serial_t *send_ack; unsigned long now, next, t; unsigned int iterations = 0; + rxrpc_serial_t ackr_serial; + u8 ackr_reason; rxrpc_see_call(call); @@ -342,7 +368,15 @@ recheck_state: if (time_after_eq(now, t)) { trace_rxrpc_timer(call, rxrpc_timer_exp_ack, now); cmpxchg(&call->ack_at, t, now + MAX_JIFFY_OFFSET); - set_bit(RXRPC_CALL_EV_ACK, &call->events); + spin_lock_bh(&call->lock); + ackr_reason = call->ackr_reason; + ackr_serial = call->ackr_serial; + call->ackr_reason = 0; + call->ackr_serial = 0; + spin_unlock_bh(&call->lock); + if (ackr_reason) + rxrpc_send_ACK(call, ackr_reason, ackr_serial, + rxrpc_propose_ack_ping_for_lost_ack); } t = READ_ONCE(call->ack_lost_at); @@ -356,16 +390,16 @@ recheck_state: if (time_after_eq(now, t)) { trace_rxrpc_timer(call, rxrpc_timer_exp_keepalive, now); cmpxchg(&call->keepalive_at, t, now + MAX_JIFFY_OFFSET); - rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, true, - rxrpc_propose_ack_ping_for_keepalive); - set_bit(RXRPC_CALL_EV_PING, &call->events); + rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, + rxrpc_propose_ack_ping_for_keepalive); } t = READ_ONCE(call->ping_at); if (time_after_eq(now, t)) { trace_rxrpc_timer(call, rxrpc_timer_exp_ping, now); cmpxchg(&call->ping_at, t, now + MAX_JIFFY_OFFSET); - set_bit(RXRPC_CALL_EV_PING, &call->events); + rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, + rxrpc_propose_ack_ping_for_keepalive); } t = READ_ONCE(call->resend_at); @@ -388,25 +422,10 @@ recheck_state: goto recheck_state; } - send_ack = NULL; if (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events)) { call->acks_lost_top = call->tx_top; - rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, false, - rxrpc_propose_ack_ping_for_lost_ack); - send_ack = &call->acks_lost_ping; - } - - if (test_and_clear_bit(RXRPC_CALL_EV_ACK, &call->events) || - send_ack) { - if (call->ackr_reason) { - rxrpc_send_ack_packet(call, false, send_ack); - goto recheck_state; - } - } - - if (test_and_clear_bit(RXRPC_CALL_EV_PING, &call->events)) { - rxrpc_send_ack_packet(call, true, NULL); - goto recheck_state; + rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, + rxrpc_propose_ack_ping_for_lost_ack); } if (test_and_clear_bit(RXRPC_CALL_EV_RESEND, &call->events) && diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 0cb23ba79e3b..e23f66ef8c06 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -398,8 +398,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) unsigned int j, nr_subpackets, nr_unacked = 0; rxrpc_serial_t serial = sp->hdr.serial, ack_serial = serial; rxrpc_seq_t seq0 = sp->hdr.seq, hard_ack; - bool immediate_ack = false, jumbo_bad = false; - u8 ack = 0; + bool jumbo_bad = false; _enter("{%u,%u},{%u,%u}", call->rx_hard_ack, call->rx_top, skb->len, seq0); @@ -447,9 +446,9 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) nr_subpackets = sp->nr_subpackets; if (nr_subpackets > 1) { if (call->nr_jumbo_bad > 3) { - ack = RXRPC_ACK_NOSPACE; - ack_serial = serial; - goto ack; + rxrpc_send_ACK(call, RXRPC_ACK_NOSPACE, serial, + rxrpc_propose_ack_input_data); + goto unlock; } } @@ -459,6 +458,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) unsigned int ix = seq & RXRPC_RXTX_BUFF_MASK; bool terminal = (j == nr_subpackets - 1); bool last = terminal && (sp->rx_flags & RXRPC_SKB_INCL_LAST); + bool acked = false; u8 flags, annotation = j; _proto("Rx DATA+%u %%%u { #%x t=%u l=%u }", @@ -488,25 +488,22 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) trace_rxrpc_rx_data(call->debug_id, seq, serial, flags, annotation); if (before_eq(seq, hard_ack)) { - ack = RXRPC_ACK_DUPLICATE; - ack_serial = serial; + rxrpc_send_ACK(call, RXRPC_ACK_DUPLICATE, serial, + rxrpc_propose_ack_input_data); continue; } if (call->rxtx_buffer[ix]) { rxrpc_input_dup_data(call, seq, nr_subpackets > 1, &jumbo_bad); - if (ack != RXRPC_ACK_DUPLICATE) { - ack = RXRPC_ACK_DUPLICATE; - ack_serial = serial; - } - immediate_ack = true; + rxrpc_send_ACK(call, RXRPC_ACK_DUPLICATE, serial, + rxrpc_propose_ack_input_data); continue; } if (after(seq, hard_ack + call->rx_winsize)) { - ack = RXRPC_ACK_EXCEEDS_WINDOW; - ack_serial = serial; + rxrpc_send_ACK(call, RXRPC_ACK_EXCEEDS_WINDOW, serial, + rxrpc_propose_ack_input_data); if (flags & RXRPC_JUMBO_PACKET) { if (!jumbo_bad) { call->nr_jumbo_bad++; @@ -514,12 +511,13 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) } } - goto ack; + goto unlock; } - if (flags & RXRPC_REQUEST_ACK && !ack) { - ack = RXRPC_ACK_REQUESTED; - ack_serial = serial; + if (flags & RXRPC_REQUEST_ACK) { + rxrpc_send_ACK(call, RXRPC_ACK_REQUESTED, serial, + rxrpc_propose_ack_input_data); + acked = true; } if (after(seq0, call->ackr_highest_seq)) @@ -542,11 +540,11 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) smp_store_release(&call->rx_top, seq); } else if (before(seq, call->rx_top)) { /* Send an immediate ACK if we fill in a hole */ - if (!ack) { - ack = RXRPC_ACK_DELAY; - ack_serial = serial; + if (!acked) { + rxrpc_send_ACK(call, RXRPC_ACK_DELAY, serial, + rxrpc_propose_ack_input_data); + acked = true; } - immediate_ack = true; } if (terminal) { @@ -558,14 +556,8 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) sp = NULL; } - nr_unacked++; - if (last) { set_bit(RXRPC_CALL_RX_LAST, &call->flags); - if (!ack) { - ack = RXRPC_ACK_DELAY; - ack_serial = serial; - } trace_rxrpc_receive(call, rxrpc_receive_queue_last, serial, seq); } else { trace_rxrpc_receive(call, rxrpc_receive_queue, serial, seq); @@ -574,32 +566,30 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) if (after_eq(seq, call->rx_expect_next)) { if (after(seq, call->rx_expect_next)) { _net("OOS %u > %u", seq, call->rx_expect_next); - ack = RXRPC_ACK_OUT_OF_SEQUENCE; - ack_serial = serial; + rxrpc_send_ACK(call, RXRPC_ACK_OUT_OF_SEQUENCE, serial, + rxrpc_propose_ack_input_data); + acked = true; } call->rx_expect_next = seq + 1; } - if (!ack) + + if (!acked) { + nr_unacked++; ack_serial = serial; + } } -ack: - if (atomic_add_return(nr_unacked, &call->ackr_nr_unacked) > 2 && !ack) - ack = RXRPC_ACK_IDLE; - - if (ack) - rxrpc_propose_ACK(call, ack, ack_serial, - immediate_ack, true, - rxrpc_propose_ack_input_data); +unlock: + if (atomic_add_return(nr_unacked, &call->ackr_nr_unacked) > 2) + rxrpc_send_ACK(call, RXRPC_ACK_IDLE, ack_serial, + rxrpc_propose_ack_input_data); else - rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial, - false, true, + rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, ack_serial, rxrpc_propose_ack_input_data); trace_rxrpc_notify_socket(call->debug_id, serial); rxrpc_notify_socket(call); -unlock: spin_unlock(&call->input_lock); rxrpc_free_skb(skb, rxrpc_skb_freed); _leave(" [queued]"); @@ -893,13 +883,11 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) if (buf.ack.reason == RXRPC_ACK_PING) { _proto("Rx ACK %%%u PING Request", ack_serial); - rxrpc_propose_ACK(call, RXRPC_ACK_PING_RESPONSE, - ack_serial, true, true, - rxrpc_propose_ack_respond_to_ping); + rxrpc_send_ACK(call, RXRPC_ACK_PING_RESPONSE, ack_serial, + rxrpc_propose_ack_respond_to_ping); } else if (sp->hdr.flags & RXRPC_REQUEST_ACK) { - rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED, - ack_serial, true, true, - rxrpc_propose_ack_respond_to_ack); + rxrpc_send_ACK(call, RXRPC_ACK_REQUESTED, ack_serial, + rxrpc_propose_ack_respond_to_ack); } /* If we get an EXCEEDS_WINDOW ACK from the server, it probably @@ -1011,9 +999,8 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) RXRPC_TX_ANNO_LAST && summary.nr_acks == call->tx_top - hard_ack && rxrpc_is_client_call(call)) - rxrpc_propose_ACK(call, RXRPC_ACK_PING, ack_serial, - false, true, - rxrpc_propose_ack_ping_for_lost_reply); + rxrpc_propose_ping(call, ack_serial, + rxrpc_propose_ack_ping_for_lost_reply); rxrpc_congestion_management(call, skb, &summary, acked_serial); out: diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index e95e75e785fb..a178f71e5082 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -97,6 +97,8 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet, local->rxnet = rxnet; INIT_HLIST_NODE(&local->link); INIT_WORK(&local->processor, rxrpc_local_processor); + INIT_LIST_HEAD(&local->ack_tx_queue); + spin_lock_init(&local->ack_tx_lock); init_rwsem(&local->defrag_sem); skb_queue_head_init(&local->reject_queue); skb_queue_head_init(&local->event_queue); @@ -432,6 +434,11 @@ static void rxrpc_local_processor(struct work_struct *work) break; } + if (!list_empty(&local->ack_tx_queue)) { + rxrpc_transmit_ack_packets(local); + again = true; + } + if (!skb_queue_empty(&local->reject_queue)) { rxrpc_reject_packets(local); again = true; diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 71885d741987..1edbc678e8be 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -16,14 +16,6 @@ #include #include "ar-internal.h" -struct rxrpc_ack_buffer { - struct rxrpc_wire_header whdr; - struct rxrpc_ackpacket ack; - u8 acks[255]; - u8 pad[3]; - struct rxrpc_ackinfo ackinfo; -}; - extern int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len); static ssize_t do_udp_sendmsg(struct socket *sk, struct msghdr *msg, size_t len) @@ -82,22 +74,21 @@ static void rxrpc_set_keepalive(struct rxrpc_call *call) */ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, struct rxrpc_call *call, - struct rxrpc_ack_buffer *pkt, + struct rxrpc_txbuf *txb, rxrpc_seq_t *_hard_ack, - rxrpc_seq_t *_top, - u8 reason) + rxrpc_seq_t *_top) { - rxrpc_serial_t serial; + struct rxrpc_ackinfo ackinfo; unsigned int tmp; rxrpc_seq_t hard_ack, top, seq; int ix; u32 mtu, jmax; - u8 *ackp = pkt->acks; + u8 *ackp = txb->acks; tmp = atomic_xchg(&call->ackr_nr_unacked, 0); tmp |= atomic_xchg(&call->ackr_nr_consumed, 0); - if (!tmp && (reason == RXRPC_ACK_DELAY || - reason == RXRPC_ACK_IDLE)) { + if (!tmp && (txb->ack.reason == RXRPC_ACK_DELAY || + txb->ack.reason == RXRPC_ACK_IDLE)) { rxrpc_inc_stat(call->rxnet, stat_tx_ack_skip); return 0; } @@ -105,24 +96,16 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, rxrpc_inc_stat(call->rxnet, stat_tx_ack_fill); /* Barrier against rxrpc_input_data(). */ - serial = call->ackr_serial; hard_ack = READ_ONCE(call->rx_hard_ack); top = smp_load_acquire(&call->rx_top); *_hard_ack = hard_ack; *_top = top; - pkt->ack.bufferSpace = htons(0); - pkt->ack.maxSkew = htons(0); - pkt->ack.firstPacket = htonl(hard_ack + 1); - pkt->ack.previousPacket = htonl(call->ackr_highest_seq); - pkt->ack.serial = htonl(serial); - pkt->ack.reason = reason; - pkt->ack.nAcks = top - hard_ack; - - if (reason == RXRPC_ACK_PING) - pkt->whdr.flags |= RXRPC_REQUEST_ACK; + txb->ack.firstPacket = htonl(hard_ack + 1); + txb->ack.previousPacket = htonl(call->ackr_highest_seq); + txb->ack.nAcks = top - hard_ack; - if (after(top, hard_ack)) { + if (txb->ack.nAcks) { seq = hard_ack + 1; do { ix = seq & RXRPC_RXTX_BUFF_MASK; @@ -137,15 +120,16 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, mtu = conn->params.peer->if_mtu; mtu -= conn->params.peer->hdrsize; jmax = (call->nr_jumbo_bad > 3) ? 1 : rxrpc_rx_jumbo_max; - pkt->ackinfo.rxMTU = htonl(rxrpc_rx_mtu); - pkt->ackinfo.maxMTU = htonl(mtu); - pkt->ackinfo.rwind = htonl(call->rx_winsize); - pkt->ackinfo.jumbo_max = htonl(jmax); + ackinfo.rxMTU = htonl(rxrpc_rx_mtu); + ackinfo.maxMTU = htonl(mtu); + ackinfo.rwind = htonl(call->rx_winsize); + ackinfo.jumbo_max = htonl(jmax); *ackp++ = 0; *ackp++ = 0; *ackp++ = 0; - return top - hard_ack + 3; + memcpy(ackp, &ackinfo, sizeof(ackinfo)); + return top - hard_ack + 3 + sizeof(ackinfo); } /* @@ -194,26 +178,21 @@ static void rxrpc_cancel_rtt_probe(struct rxrpc_call *call, /* * Send an ACK call packet. */ -int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, - rxrpc_serial_t *_serial) +static int rxrpc_send_ack_packet(struct rxrpc_local *local, struct rxrpc_txbuf *txb) { struct rxrpc_connection *conn; struct rxrpc_ack_buffer *pkt; + struct rxrpc_call *call = txb->call; struct msghdr msg; - struct kvec iov[2]; + struct kvec iov[1]; rxrpc_serial_t serial; rxrpc_seq_t hard_ack, top; size_t len, n; int ret, rtt_slot = -1; - u8 reason; if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) return -ECONNRESET; - pkt = kzalloc(sizeof(*pkt), GFP_KERNEL); - if (!pkt) - return -ENOMEM; - conn = call->conn; msg.msg_name = &call->peer->srx.transport; @@ -222,85 +201,93 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, msg.msg_controllen = 0; msg.msg_flags = 0; - pkt->whdr.epoch = htonl(conn->proto.epoch); - pkt->whdr.cid = htonl(call->cid); - pkt->whdr.callNumber = htonl(call->call_id); - pkt->whdr.seq = 0; - pkt->whdr.type = RXRPC_PACKET_TYPE_ACK; - pkt->whdr.flags = RXRPC_SLOW_START_OK | conn->out_clientflag; - pkt->whdr.userStatus = 0; - pkt->whdr.securityIndex = call->security_ix; - pkt->whdr._rsvd = 0; - pkt->whdr.serviceId = htons(call->service_id); + if (txb->ack.reason == RXRPC_ACK_PING) + txb->wire.flags |= RXRPC_REQUEST_ACK; spin_lock_bh(&call->lock); - if (ping) { - reason = RXRPC_ACK_PING; - } else { - reason = call->ackr_reason; - if (!call->ackr_reason) { - spin_unlock_bh(&call->lock); - ret = 0; - goto out; - } - call->ackr_reason = 0; - } - n = rxrpc_fill_out_ack(conn, call, pkt, &hard_ack, &top, reason); - + n = rxrpc_fill_out_ack(conn, call, txb, &hard_ack, &top); spin_unlock_bh(&call->lock); if (n == 0) { kfree(pkt); return 0; } - iov[0].iov_base = pkt; - iov[0].iov_len = sizeof(pkt->whdr) + sizeof(pkt->ack) + n; - iov[1].iov_base = &pkt->ackinfo; - iov[1].iov_len = sizeof(pkt->ackinfo); - len = iov[0].iov_len + iov[1].iov_len; + iov[0].iov_base = &txb->wire; + iov[0].iov_len = sizeof(txb->wire) + sizeof(txb->ack) + n; + len = iov[0].iov_len; serial = atomic_inc_return(&conn->serial); - pkt->whdr.serial = htonl(serial); + txb->wire.serial = htonl(serial); trace_rxrpc_tx_ack(call->debug_id, serial, - ntohl(pkt->ack.firstPacket), - ntohl(pkt->ack.serial), - pkt->ack.reason, pkt->ack.nAcks); - if (_serial) - *_serial = serial; + ntohl(txb->ack.firstPacket), + ntohl(txb->ack.serial), txb->ack.reason, txb->ack.nAcks); + if (txb->ack_why == rxrpc_propose_ack_ping_for_lost_ack) + call->acks_lost_ping = serial; - if (ping) + if (txb->ack.reason == RXRPC_ACK_PING) rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_ping); rxrpc_inc_stat(call->rxnet, stat_tx_ack_send); - iov_iter_kvec(&msg.msg_iter, WRITE, iov, 2, len); + iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, len); ret = do_udp_sendmsg(conn->params.local->socket, &msg, len); call->peer->last_tx_at = ktime_get_seconds(); if (ret < 0) trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_ack); else - trace_rxrpc_tx_packet(call->debug_id, &pkt->whdr, + trace_rxrpc_tx_packet(call->debug_id, &txb->wire, rxrpc_tx_point_call_ack); rxrpc_tx_backoff(call, ret); if (call->state < RXRPC_CALL_COMPLETE) { - if (ret < 0) { + if (ret < 0) rxrpc_cancel_rtt_probe(call, serial, rtt_slot); - rxrpc_propose_ACK(call, pkt->ack.reason, - ntohl(pkt->ack.serial), - false, true, - rxrpc_propose_ack_retry_tx); - } - rxrpc_set_keepalive(call); } -out: kfree(pkt); return ret; } +/* + * ACK transmitter for a local endpoint. The UDP socket locks around each + * transmission, so we can only transmit one packet at a time, ACK, DATA or + * otherwise. + */ +void rxrpc_transmit_ack_packets(struct rxrpc_local *local) +{ + LIST_HEAD(queue); + int ret; + + trace_rxrpc_local(local->debug_id, rxrpc_local_tx_ack, + refcount_read(&local->ref), NULL); + + if (list_empty(&local->ack_tx_queue)) + return; + + spin_lock_bh(&local->ack_tx_lock); + list_splice_tail_init(&local->ack_tx_queue, &queue); + spin_unlock_bh(&local->ack_tx_lock); + + while (!list_empty(&queue)) { + struct rxrpc_txbuf *txb = + list_entry(queue.next, struct rxrpc_txbuf, tx_link); + + ret = rxrpc_send_ack_packet(local, txb); + if (ret < 0 && ret != -ECONNRESET) { + spin_lock_bh(&local->ack_tx_lock); + list_splice_init(&queue, &local->ack_tx_queue); + spin_unlock_bh(&local->ack_tx_lock); + break; + } + + list_del_init(&txb->tx_link); + rxrpc_put_call(txb->call, rxrpc_call_put); + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_ack_tx); + } +} + /* * Send an ABORT call packet. */ diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index a378e7a672a8..104dd4a29f05 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -189,7 +189,7 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) ASSERTCMP(call->rx_hard_ack, ==, call->rx_top); if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY) { - rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, serial, false, true, + rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, serial, rxrpc_propose_ack_terminal_ack); //rxrpc_send_ack_packet(call, false, NULL); } @@ -206,7 +206,7 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) call->state = RXRPC_CALL_SERVER_ACK_REQUEST; call->expect_req_by = jiffies + MAX_JIFFY_OFFSET; write_unlock_bh(&call->state_lock); - rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial, false, true, + rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial, rxrpc_propose_ack_processing_op); break; default: @@ -259,12 +259,11 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) rxrpc_end_rx_phase(call, serial); } else { /* Check to see if there's an ACK that needs sending. */ - if (atomic_inc_return(&call->ackr_nr_consumed) > 2) - rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, serial, - true, false, - rxrpc_propose_ack_rotate_rx); - if (call->ackr_reason && call->ackr_reason != RXRPC_ACK_DELAY) - rxrpc_send_ack_packet(call, false, NULL); + if (atomic_inc_return(&call->ackr_nr_consumed) > 2) { + rxrpc_send_ACK(call, RXRPC_ACK_IDLE, serial, + rxrpc_propose_ack_rotate_rx); + rxrpc_transmit_ack_packets(call->peer->local); + } } } @@ -363,10 +362,6 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, unsigned int rx_pkt_offset, rx_pkt_len; int ix, copy, ret = -EAGAIN, ret2; - if (test_and_clear_bit(RXRPC_CALL_RX_UNDERRUN, &call->flags) && - call->ackr_reason) - rxrpc_send_ack_packet(call, false, NULL); - rx_pkt_offset = call->rx_pkt_offset; rx_pkt_len = call->rx_pkt_len; rx_pkt_last = call->rx_pkt_last; @@ -389,6 +384,7 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, if (!skb) { trace_rxrpc_recvmsg(call, rxrpc_recvmsg_hole, seq, rx_pkt_offset, rx_pkt_len, 0); + rxrpc_transmit_ack_packets(call->peer->local); break; } smp_rmb(); @@ -604,6 +600,7 @@ try_again: if (ret == -EAGAIN) ret = 0; + rxrpc_transmit_ack_packets(call->peer->local); if (after(call->rx_top, call->rx_hard_ack) && call->rxtx_buffer[(call->rx_hard_ack + 1) & RXRPC_RXTX_BUFF_MASK]) rxrpc_notify_socket(call); @@ -734,17 +731,7 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call, read_phase_complete: ret = 1; out: - switch (call->ackr_reason) { - case RXRPC_ACK_IDLE: - break; - case RXRPC_ACK_DELAY: - if (ret != -EAGAIN) - break; - fallthrough; - default: - rxrpc_send_ack_packet(call, false, NULL); - } - + rxrpc_transmit_ack_packets(call->peer->local); if (_service) *_service = call->service_id; mutex_unlock(&call->user_mutex); diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index b2d28aa12e10..ef4949259020 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -332,9 +332,7 @@ reload: rxrpc_see_skb(skb, rxrpc_skb_seen); do { - /* Check to see if there's a ping ACK to reply to. */ - if (call->ackr_reason == RXRPC_ACK_PING_RESPONSE) - rxrpc_send_ack_packet(call, false, NULL); + rxrpc_transmit_ack_packets(call->peer->local); if (!skb) { size_t remain, bufsize, chunk, offset; diff --git a/net/rxrpc/txbuf.c b/net/rxrpc/txbuf.c index 66d922ad65d0..45a7b48a5e10 100644 --- a/net/rxrpc/txbuf.c +++ b/net/rxrpc/txbuf.c @@ -33,6 +33,7 @@ struct rxrpc_txbuf *rxrpc_alloc_txbuf(struct rxrpc_call *call, u8 packet_type, txb->len = 0; txb->offset = 0; txb->flags = 0; + txb->ack_why = 0; txb->seq = call->tx_top + 1; txb->wire.epoch = htonl(call->conn->proto.epoch); txb->wire.cid = htonl(call->cid); -- cgit v1.2.3 From 530403d9ba1c3f51c721a394f642e56309072295 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 30 Jan 2020 21:48:14 +0000 Subject: rxrpc: Clean up ACK handling Clean up the rxrpc_propose_ACK() function. If deferred PING ACK proposal is split out, it's only really needed for deferred DELAY ACKs. All other ACKs, bar terminal IDLE ACK are sent immediately. The deferred IDLE ACK submission can be handled by conversion of a DELAY ACK into an IDLE ACK if there's nothing to be SACK'd. Also, because there's a delay between an ACK being generated and being transmitted, it's possible that other ACKs of the same type will be generated during that interval. Apart from the ACK time and the serial number responded to, most of the ACK body, including window and SACK parameters, are not filled out till the point of transmission - so we can avoid generating a new ACK if there's one pending that will cover the SACK data we need to convey. Therefore, don't propose a new DELAY or IDLE ACK for a call if there's one already pending. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 52 ++++++++++++++++-------- net/rxrpc/ar-internal.h | 10 ++--- net/rxrpc/call_event.c | 95 ++++++++++++-------------------------------- net/rxrpc/call_object.c | 2 +- net/rxrpc/input.c | 8 ++-- net/rxrpc/misc.c | 18 --------- net/rxrpc/output.c | 7 ++++ net/rxrpc/protocol.h | 7 ---- net/rxrpc/recvmsg.c | 14 +++---- net/rxrpc/sendmsg.c | 2 +- net/rxrpc/sysctl.c | 9 ----- 11 files changed, 86 insertions(+), 138 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 1597ff7ad97e..d32e9858c682 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -158,6 +158,7 @@ #define rxrpc_propose_ack_traces \ EM(rxrpc_propose_ack_client_tx_end, "ClTxEnd") \ EM(rxrpc_propose_ack_input_data, "DataIn ") \ + EM(rxrpc_propose_ack_input_data_hole, "DataInH") \ EM(rxrpc_propose_ack_ping_for_check_life, "ChkLife") \ EM(rxrpc_propose_ack_ping_for_keepalive, "KeepAlv") \ EM(rxrpc_propose_ack_ping_for_lost_ack, "LostAck") \ @@ -170,11 +171,6 @@ EM(rxrpc_propose_ack_rotate_rx, "RxAck ") \ E_(rxrpc_propose_ack_terminal_ack, "ClTerm ") -#define rxrpc_propose_ack_outcomes \ - EM(rxrpc_propose_ack_subsume, " Subsume") \ - EM(rxrpc_propose_ack_update, " Update") \ - E_(rxrpc_propose_ack_use, " New") - #define rxrpc_congest_modes \ EM(RXRPC_CALL_CONGEST_AVOIDANCE, "CongAvoid") \ EM(RXRPC_CALL_FAST_RETRANSMIT, "FastReTx ") \ @@ -313,7 +309,6 @@ rxrpc_congest_changes; rxrpc_congest_modes; rxrpc_conn_traces; rxrpc_local_traces; -rxrpc_propose_ack_outcomes; rxrpc_propose_ack_traces; rxrpc_receive_traces; rxrpc_recvmsg_traces; @@ -1012,7 +1007,7 @@ TRACE_EVENT(rxrpc_timer, __entry->call = call->debug_id; __entry->why = why; __entry->now = now; - __entry->ack_at = call->ack_at; + __entry->ack_at = call->delay_ack_at; __entry->ack_lost_at = call->ack_lost_at; __entry->resend_at = call->resend_at; __entry->expect_rx_by = call->expect_rx_by; @@ -1054,7 +1049,7 @@ TRACE_EVENT(rxrpc_timer_expired, TP_fast_assign( __entry->call = call->debug_id; __entry->now = now; - __entry->ack_at = call->ack_at; + __entry->ack_at = call->delay_ack_at; __entry->ack_lost_at = call->ack_lost_at; __entry->resend_at = call->resend_at; __entry->expect_rx_by = call->expect_rx_by; @@ -1098,17 +1093,15 @@ TRACE_EVENT(rxrpc_rx_lose, TRACE_EVENT(rxrpc_propose_ack, TP_PROTO(struct rxrpc_call *call, enum rxrpc_propose_ack_trace why, - u8 ack_reason, rxrpc_serial_t serial, - enum rxrpc_propose_ack_outcome outcome), + u8 ack_reason, rxrpc_serial_t serial), - TP_ARGS(call, why, ack_reason, serial, outcome), + TP_ARGS(call, why, ack_reason, serial), TP_STRUCT__entry( __field(unsigned int, call ) __field(enum rxrpc_propose_ack_trace, why ) __field(rxrpc_serial_t, serial ) __field(u8, ack_reason ) - __field(enum rxrpc_propose_ack_outcome, outcome ) ), TP_fast_assign( @@ -1116,15 +1109,13 @@ TRACE_EVENT(rxrpc_propose_ack, __entry->why = why; __entry->serial = serial; __entry->ack_reason = ack_reason; - __entry->outcome = outcome; ), - TP_printk("c=%08x %s %s r=%08x%s", + TP_printk("c=%08x %s %s r=%08x", __entry->call, __print_symbolic(__entry->why, rxrpc_propose_ack_traces), __print_symbolic(__entry->ack_reason, rxrpc_ack_names), - __entry->serial, - __print_symbolic(__entry->outcome, rxrpc_propose_ack_outcomes)) + __entry->serial) ); TRACE_EVENT(rxrpc_send_ack, @@ -1154,6 +1145,35 @@ TRACE_EVENT(rxrpc_send_ack, __entry->serial) ); +TRACE_EVENT(rxrpc_drop_ack, + TP_PROTO(struct rxrpc_call *call, enum rxrpc_propose_ack_trace why, + u8 ack_reason, rxrpc_serial_t serial, bool nobuf), + + TP_ARGS(call, why, ack_reason, serial, nobuf), + + TP_STRUCT__entry( + __field(unsigned int, call ) + __field(enum rxrpc_propose_ack_trace, why ) + __field(rxrpc_serial_t, serial ) + __field(u8, ack_reason ) + __field(bool, nobuf ) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->why = why; + __entry->serial = serial; + __entry->ack_reason = ack_reason; + __entry->nobuf = nobuf; + ), + + TP_printk("c=%08x %s %s r=%08x nbf=%u", + __entry->call, + __print_symbolic(__entry->why, rxrpc_propose_ack_traces), + __print_symbolic(__entry->ack_reason, rxrpc_ack_names), + __entry->serial, __entry->nobuf) + ); + TRACE_EVENT(rxrpc_retransmit, TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t seq, u8 annotation, s64 expiry), diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 802a8f372af2..5a81545a58d5 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -516,6 +516,8 @@ enum rxrpc_call_flag { RXRPC_CALL_DISCONNECTED, /* The call has been disconnected */ RXRPC_CALL_KERNEL, /* The call was made by the kernel */ RXRPC_CALL_UPGRADE, /* Service upgrade was requested for the call */ + RXRPC_CALL_DELAY_ACK_PENDING, /* DELAY ACK generation is pending */ + RXRPC_CALL_IDLE_ACK_PENDING, /* IDLE ACK generation is pending */ }; /* @@ -582,7 +584,7 @@ struct rxrpc_call { struct rxrpc_net *rxnet; /* Network namespace to which call belongs */ const struct rxrpc_security *security; /* applied security module */ struct mutex user_mutex; /* User access mutex */ - unsigned long ack_at; /* When deferred ACK needs to happen */ + unsigned long delay_ack_at; /* When DELAY ACK needs to happen */ unsigned long ack_lost_at; /* When ACK is figured as lost */ unsigned long resend_at; /* When next resend needs to happen */ unsigned long ping_at; /* When next to send a ping */ @@ -834,7 +836,8 @@ int rxrpc_user_charge_accept(struct rxrpc_sock *, unsigned long); void rxrpc_propose_ping(struct rxrpc_call *call, u32 serial, enum rxrpc_propose_ack_trace why); void rxrpc_send_ACK(struct rxrpc_call *, u8, rxrpc_serial_t, enum rxrpc_propose_ack_trace); -void rxrpc_propose_ACK(struct rxrpc_call *, u8, u32, enum rxrpc_propose_ack_trace); +void rxrpc_propose_delay_ACK(struct rxrpc_call *, rxrpc_serial_t, + enum rxrpc_propose_ack_trace); void rxrpc_process_call(struct work_struct *); void rxrpc_reduce_call_timer(struct rxrpc_call *call, @@ -1016,15 +1019,12 @@ static inline bool __rxrpc_use_local(struct rxrpc_local *local) * misc.c */ extern unsigned int rxrpc_max_backlog __read_mostly; -extern unsigned long rxrpc_requested_ack_delay; extern unsigned long rxrpc_soft_ack_delay; extern unsigned long rxrpc_idle_ack_delay; extern unsigned int rxrpc_rx_window_size; extern unsigned int rxrpc_rx_mtu; extern unsigned int rxrpc_rx_jumbo_max; -extern const s8 rxrpc_ack_priority[]; - /* * net_ns.c */ diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 67b54ad914a1..36f60ac1d95d 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -29,70 +29,29 @@ void rxrpc_propose_ping(struct rxrpc_call *call, u32 serial, spin_lock_bh(&call->lock); if (time_before(ping_at, call->ping_at)) { - rxrpc_inc_stat(call->rxnet, stat_tx_acks[RXRPC_ACK_PING]); WRITE_ONCE(call->ping_at, ping_at); rxrpc_reduce_call_timer(call, ping_at, now, rxrpc_timer_set_for_ping); - trace_rxrpc_propose_ack(call, why, RXRPC_ACK_PING, serial, - rxrpc_propose_ack_use); + trace_rxrpc_propose_ack(call, why, RXRPC_ACK_PING, serial); } spin_unlock_bh(&call->lock); } /* - * propose an ACK be sent + * Propose a DELAY ACK be sent in the future. */ -static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, - u32 serial, enum rxrpc_propose_ack_trace why) +static void __rxrpc_propose_delay_ACK(struct rxrpc_call *call, + rxrpc_serial_t serial, + enum rxrpc_propose_ack_trace why) { - enum rxrpc_propose_ack_outcome outcome = rxrpc_propose_ack_use; unsigned long expiry = rxrpc_soft_ack_delay; unsigned long now = jiffies, ack_at; - s8 prior = rxrpc_ack_priority[ack_reason]; - - rxrpc_inc_stat(call->rxnet, stat_tx_acks[ack_reason]); - - /* Update DELAY, IDLE, REQUESTED and PING_RESPONSE ACK serial - * numbers, but we don't alter the timeout. - */ - _debug("prior %u %u vs %u %u", - ack_reason, prior, - call->ackr_reason, rxrpc_ack_priority[call->ackr_reason]); - if (ack_reason == call->ackr_reason) { - if (RXRPC_ACK_UPDATEABLE & (1 << ack_reason)) { - outcome = rxrpc_propose_ack_update; - call->ackr_serial = serial; - } - } else if (prior > rxrpc_ack_priority[call->ackr_reason]) { - call->ackr_reason = ack_reason; - call->ackr_serial = serial; - } else { - outcome = rxrpc_propose_ack_subsume; - } - - switch (ack_reason) { - case RXRPC_ACK_REQUESTED: - if (rxrpc_requested_ack_delay < expiry) - expiry = rxrpc_requested_ack_delay; - break; - - case RXRPC_ACK_DELAY: - if (rxrpc_soft_ack_delay < expiry) - expiry = rxrpc_soft_ack_delay; - break; - - case RXRPC_ACK_IDLE: - if (rxrpc_idle_ack_delay < expiry) - expiry = rxrpc_idle_ack_delay; - break; - - default: - WARN_ON(1); - return; - } + call->ackr_serial = serial; + if (rxrpc_soft_ack_delay < expiry) + expiry = rxrpc_soft_ack_delay; if (call->peer->srtt_us != 0) ack_at = usecs_to_jiffies(call->peer->srtt_us >> 3); else @@ -100,23 +59,23 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, ack_at += READ_ONCE(call->tx_backoff); ack_at += now; - if (time_before(ack_at, call->ack_at)) { - WRITE_ONCE(call->ack_at, ack_at); + if (time_before(ack_at, call->delay_ack_at)) { + WRITE_ONCE(call->delay_ack_at, ack_at); rxrpc_reduce_call_timer(call, ack_at, now, rxrpc_timer_set_for_ack); } - trace_rxrpc_propose_ack(call, why, ack_reason, serial, outcome); + trace_rxrpc_propose_ack(call, why, RXRPC_ACK_DELAY, serial); } /* - * propose an ACK be sent, locking the call structure + * Propose a DELAY ACK be sent, locking the call structure */ -void rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, u32 serial, - enum rxrpc_propose_ack_trace why) +void rxrpc_propose_delay_ACK(struct rxrpc_call *call, rxrpc_serial_t serial, + enum rxrpc_propose_ack_trace why) { spin_lock_bh(&call->lock); - __rxrpc_propose_ACK(call, ack_reason, serial, why); + __rxrpc_propose_delay_ACK(call, serial, why); spin_unlock_bh(&call->lock); } @@ -131,6 +90,11 @@ void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason, if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) return; + if (ack_reason == RXRPC_ACK_DELAY && + test_and_set_bit(RXRPC_CALL_DELAY_ACK_PENDING, &call->flags)) { + trace_rxrpc_drop_ack(call, why, ack_reason, serial, false); + return; + } rxrpc_inc_stat(call->rxnet, stat_tx_acks[ack_reason]); @@ -319,7 +283,6 @@ void rxrpc_process_call(struct work_struct *work) unsigned long now, next, t; unsigned int iterations = 0; rxrpc_serial_t ackr_serial; - u8 ackr_reason; rxrpc_see_call(call); @@ -364,19 +327,13 @@ recheck_state: set_bit(RXRPC_CALL_EV_EXPIRED, &call->events); } - t = READ_ONCE(call->ack_at); + t = READ_ONCE(call->delay_ack_at); if (time_after_eq(now, t)) { trace_rxrpc_timer(call, rxrpc_timer_exp_ack, now); - cmpxchg(&call->ack_at, t, now + MAX_JIFFY_OFFSET); - spin_lock_bh(&call->lock); - ackr_reason = call->ackr_reason; - ackr_serial = call->ackr_serial; - call->ackr_reason = 0; - call->ackr_serial = 0; - spin_unlock_bh(&call->lock); - if (ackr_reason) - rxrpc_send_ACK(call, ackr_reason, ackr_serial, - rxrpc_propose_ack_ping_for_lost_ack); + cmpxchg(&call->delay_ack_at, t, now + MAX_JIFFY_OFFSET); + ackr_serial = xchg(&call->ackr_serial, 0); + rxrpc_send_ACK(call, RXRPC_ACK_DELAY, ackr_serial, + rxrpc_propose_ack_ping_for_lost_ack); } t = READ_ONCE(call->ack_lost_at); @@ -441,7 +398,7 @@ recheck_state: set(call->expect_req_by); set(call->expect_term_by); - set(call->ack_at); + set(call->delay_ack_at); set(call->ack_lost_at); set(call->resend_at); set(call->keepalive_at); diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 8290d94e9233..8f9e88897197 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -222,7 +222,7 @@ static void rxrpc_start_call_timer(struct rxrpc_call *call) unsigned long now = jiffies; unsigned long j = now + MAX_JIFFY_OFFSET; - call->ack_at = j; + call->delay_ack_at = j; call->ack_lost_at = j; call->resend_at = j; call->ping_at = j; diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index e23f66ef8c06..4df1bdc4de6c 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -299,7 +299,7 @@ static bool rxrpc_receiving_reply(struct rxrpc_call *call) now = jiffies; timo = now + MAX_JIFFY_OFFSET; WRITE_ONCE(call->resend_at, timo); - WRITE_ONCE(call->ack_at, timo); + WRITE_ONCE(call->delay_ack_at, timo); trace_rxrpc_timer(call, rxrpc_timer_init_for_reply, now); } @@ -542,7 +542,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) /* Send an immediate ACK if we fill in a hole */ if (!acked) { rxrpc_send_ACK(call, RXRPC_ACK_DELAY, serial, - rxrpc_propose_ack_input_data); + rxrpc_propose_ack_input_data_hole); acked = true; } } @@ -584,8 +584,8 @@ unlock: rxrpc_send_ACK(call, RXRPC_ACK_IDLE, ack_serial, rxrpc_propose_ack_input_data); else - rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, ack_serial, - rxrpc_propose_ack_input_data); + rxrpc_propose_delay_ACK(call, ack_serial, + rxrpc_propose_ack_input_data); trace_rxrpc_notify_socket(call->debug_id, serial); rxrpc_notify_socket(call); diff --git a/net/rxrpc/misc.c b/net/rxrpc/misc.c index d4144fd86f84..f5f03f27bd6c 100644 --- a/net/rxrpc/misc.c +++ b/net/rxrpc/misc.c @@ -16,12 +16,6 @@ */ unsigned int rxrpc_max_backlog __read_mostly = 10; -/* - * How long to wait before scheduling ACK generation after seeing a - * packet with RXRPC_REQUEST_ACK set (in jiffies). - */ -unsigned long rxrpc_requested_ack_delay = 1; - /* * How long to wait before scheduling an ACK with subtype DELAY (in jiffies). * @@ -62,15 +56,3 @@ unsigned int rxrpc_rx_mtu = 5692; * sender that we're willing to handle. */ unsigned int rxrpc_rx_jumbo_max = 4; - -const s8 rxrpc_ack_priority[] = { - [0] = 0, - [RXRPC_ACK_DELAY] = 1, - [RXRPC_ACK_REQUESTED] = 2, - [RXRPC_ACK_IDLE] = 3, - [RXRPC_ACK_DUPLICATE] = 4, - [RXRPC_ACK_OUT_OF_SEQUENCE] = 5, - [RXRPC_ACK_EXCEEDS_WINDOW] = 6, - [RXRPC_ACK_NOSPACE] = 7, - [RXRPC_ACK_PING_RESPONSE] = 8, -}; diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 1edbc678e8be..d35657b659ad 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -115,6 +115,8 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, *ackp++ = RXRPC_ACK_TYPE_NACK; seq++; } while (before_eq(seq, top)); + } else if (txb->ack.reason == RXRPC_ACK_DELAY) { + txb->ack.reason = RXRPC_ACK_IDLE; } mtu = conn->params.peer->if_mtu; @@ -204,6 +206,11 @@ static int rxrpc_send_ack_packet(struct rxrpc_local *local, struct rxrpc_txbuf * if (txb->ack.reason == RXRPC_ACK_PING) txb->wire.flags |= RXRPC_REQUEST_ACK; + if (txb->ack.reason == RXRPC_ACK_DELAY) + clear_bit(RXRPC_CALL_DELAY_ACK_PENDING, &call->flags); + if (txb->ack.reason == RXRPC_ACK_IDLE) + clear_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags); + spin_lock_bh(&call->lock); n = rxrpc_fill_out_ack(conn, call, txb, &hard_ack, &top); spin_unlock_bh(&call->lock); diff --git a/net/rxrpc/protocol.h b/net/rxrpc/protocol.h index d2cf8e1d218f..f3d4e2700901 100644 --- a/net/rxrpc/protocol.h +++ b/net/rxrpc/protocol.h @@ -132,13 +132,6 @@ struct rxrpc_ackpacket { } __packed; -/* Some ACKs refer to specific packets and some are general and can be updated. */ -#define RXRPC_ACK_UPDATEABLE ((1 << RXRPC_ACK_REQUESTED) | \ - (1 << RXRPC_ACK_PING_RESPONSE) | \ - (1 << RXRPC_ACK_DELAY) | \ - (1 << RXRPC_ACK_IDLE)) - - /* * ACK packets can have a further piece of information tagged on the end */ diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 104dd4a29f05..46e784edc0f4 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -188,11 +188,8 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) trace_rxrpc_receive(call, rxrpc_receive_end, 0, call->rx_top); ASSERTCMP(call->rx_hard_ack, ==, call->rx_top); - if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY) { - rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, serial, - rxrpc_propose_ack_terminal_ack); - //rxrpc_send_ack_packet(call, false, NULL); - } + if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY) + rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_terminal_ack); write_lock_bh(&call->state_lock); @@ -206,8 +203,8 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) call->state = RXRPC_CALL_SERVER_ACK_REQUEST; call->expect_req_by = jiffies + MAX_JIFFY_OFFSET; write_unlock_bh(&call->state_lock); - rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial, - rxrpc_propose_ack_processing_op); + rxrpc_propose_delay_ACK(call, serial, + rxrpc_propose_ack_processing_op); break; default: write_unlock_bh(&call->state_lock); @@ -259,7 +256,8 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) rxrpc_end_rx_phase(call, serial); } else { /* Check to see if there's an ACK that needs sending. */ - if (atomic_inc_return(&call->ackr_nr_consumed) > 2) { + if (atomic_inc_return(&call->ackr_nr_consumed) > 2 && + !test_and_set_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags)) { rxrpc_send_ACK(call, RXRPC_ACK_IDLE, serial, rxrpc_propose_ack_rotate_rx); rxrpc_transmit_ack_packets(call->peer->local); diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index ef4949259020..e32805a49324 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -234,7 +234,7 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, case RXRPC_CALL_SERVER_ACK_REQUEST: call->state = RXRPC_CALL_SERVER_SEND_REPLY; now = jiffies; - WRITE_ONCE(call->ack_at, now + MAX_JIFFY_OFFSET); + WRITE_ONCE(call->delay_ack_at, now + MAX_JIFFY_OFFSET); if (call->ackr_reason == RXRPC_ACK_DELAY) call->ackr_reason = 0; trace_rxrpc_timer(call, rxrpc_timer_init_for_send_reply, now); diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c index 555e0910786b..2bd987364e44 100644 --- a/net/rxrpc/sysctl.c +++ b/net/rxrpc/sysctl.c @@ -26,15 +26,6 @@ static const unsigned long max_jiffies = MAX_JIFFY_OFFSET; */ static struct ctl_table rxrpc_sysctl_table[] = { /* Values measured in milliseconds but used in jiffies */ - { - .procname = "req_ack_delay", - .data = &rxrpc_requested_ack_delay, - .maxlen = sizeof(unsigned long), - .mode = 0644, - .proc_handler = proc_doulongvec_ms_jiffies_minmax, - .extra1 = (void *)&one_jiffy, - .extra2 = (void *)&max_jiffies, - }, { .procname = "soft_ack_delay", .data = &rxrpc_soft_ack_delay, -- cgit v1.2.3 From faf92e8d53f5f03842da25af971a3f0ef88ffba2 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 7 Oct 2022 17:22:40 +0100 Subject: rxrpc: Split the rxrpc_recvmsg tracepoint Split the rxrpc_recvmsg tracepoint so that the tracepoints that are about data packet processing (and which have extra pieces of information) are separate from the tracepoint that shows the general flow of recvmsg(). Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 24 ++++++++++++++++++++++++ net/rxrpc/recvmsg.c | 37 ++++++++++++++++++------------------- 2 files changed, 42 insertions(+), 19 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index d32e9858c682..84464b29e54a 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -885,6 +885,30 @@ TRACE_EVENT(rxrpc_receive, ); TRACE_EVENT(rxrpc_recvmsg, + TP_PROTO(struct rxrpc_call *call, enum rxrpc_recvmsg_trace why, + int ret), + + TP_ARGS(call, why, ret), + + TP_STRUCT__entry( + __field(unsigned int, call ) + __field(enum rxrpc_recvmsg_trace, why ) + __field(int, ret ) + ), + + TP_fast_assign( + __entry->call = call ? call->debug_id : 0; + __entry->why = why; + __entry->ret = ret; + ), + + TP_printk("c=%08x %s ret=%d", + __entry->call, + __print_symbolic(__entry->why, rxrpc_recvmsg_traces), + __entry->ret) + ); + +TRACE_EVENT(rxrpc_recvdata, TP_PROTO(struct rxrpc_call *call, enum rxrpc_recvmsg_trace why, rxrpc_seq_t seq, unsigned int offset, unsigned int len, int ret), diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 46e784edc0f4..77cde6311559 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -173,8 +173,8 @@ static int rxrpc_recvmsg_term(struct rxrpc_call *call, struct msghdr *msg) break; } - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_terminal, call->rx_hard_ack, - call->rx_pkt_offset, call->rx_pkt_len, ret); + trace_rxrpc_recvdata(call, rxrpc_recvmsg_terminal, call->rx_hard_ack, + call->rx_pkt_offset, call->rx_pkt_len, ret); return ret; } @@ -380,8 +380,8 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, ix = seq & RXRPC_RXTX_BUFF_MASK; skb = call->rxtx_buffer[ix]; if (!skb) { - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_hole, seq, - rx_pkt_offset, rx_pkt_len, 0); + trace_rxrpc_recvdata(call, rxrpc_recvmsg_hole, seq, + rx_pkt_offset, rx_pkt_len, 0); rxrpc_transmit_ack_packets(call->peer->local); break; } @@ -404,15 +404,15 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, &call->rxtx_annotations[ix], &rx_pkt_offset, &rx_pkt_len, &rx_pkt_last); - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_next, seq, - rx_pkt_offset, rx_pkt_len, ret2); + trace_rxrpc_recvdata(call, rxrpc_recvmsg_next, seq, + rx_pkt_offset, rx_pkt_len, ret2); if (ret2 < 0) { ret = ret2; goto out; } } else { - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_cont, seq, - rx_pkt_offset, rx_pkt_len, 0); + trace_rxrpc_recvdata(call, rxrpc_recvmsg_cont, seq, + rx_pkt_offset, rx_pkt_len, 0); } /* We have to handle short, empty and used-up DATA packets. */ @@ -435,8 +435,8 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, } if (rx_pkt_len > 0) { - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_full, seq, - rx_pkt_offset, rx_pkt_len, 0); + trace_rxrpc_recvdata(call, rxrpc_recvmsg_full, seq, + rx_pkt_offset, rx_pkt_len, 0); ASSERTCMP(*_offset, ==, len); ret = 0; break; @@ -464,8 +464,8 @@ out: call->rx_pkt_last = rx_pkt_last; } done: - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_data_return, seq, - rx_pkt_offset, rx_pkt_len, ret); + trace_rxrpc_recvdata(call, rxrpc_recvmsg_data_return, seq, + rx_pkt_offset, rx_pkt_len, ret); if (ret == -EAGAIN) set_bit(RXRPC_CALL_RX_UNDERRUN, &call->flags); return ret; @@ -488,7 +488,7 @@ int rxrpc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, DEFINE_WAIT(wait); - trace_rxrpc_recvmsg(NULL, rxrpc_recvmsg_enter, 0, 0, 0, 0); + trace_rxrpc_recvmsg(NULL, rxrpc_recvmsg_enter, 0); if (flags & (MSG_OOB | MSG_TRUNC)) return -EOPNOTSUPP; @@ -525,8 +525,7 @@ try_again: if (list_empty(&rx->recvmsg_q)) { if (signal_pending(current)) goto wait_interrupted; - trace_rxrpc_recvmsg(NULL, rxrpc_recvmsg_wait, - 0, 0, 0, 0); + trace_rxrpc_recvmsg(NULL, rxrpc_recvmsg_wait, 0); timeo = schedule_timeout(timeo); } finish_wait(sk_sleep(&rx->sk), &wait); @@ -545,7 +544,7 @@ try_again: rxrpc_get_call(call, rxrpc_call_got); write_unlock_bh(&rx->recvmsg_lock); - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_dequeue, 0, 0, 0, 0); + trace_rxrpc_recvmsg(call, rxrpc_recvmsg_dequeue, 0); /* We're going to drop the socket lock, so we need to lock the call * against interference by sendmsg. @@ -630,7 +629,7 @@ try_again: error_unlock_call: mutex_unlock(&call->user_mutex); rxrpc_put_call(call, rxrpc_call_put); - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, 0, 0, 0, ret); + trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, ret); return ret; error_requeue_call: @@ -638,14 +637,14 @@ error_requeue_call: write_lock_bh(&rx->recvmsg_lock); list_add(&call->recvmsg_link, &rx->recvmsg_q); write_unlock_bh(&rx->recvmsg_lock); - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_requeue, 0, 0, 0, 0); + trace_rxrpc_recvmsg(call, rxrpc_recvmsg_requeue, 0); } else { rxrpc_put_call(call, rxrpc_call_put); } error_no_call: release_sock(&rx->sk); error_trace: - trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, 0, 0, 0, ret); + trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, ret); return ret; wait_interrupted: -- cgit v1.2.3 From d4d02d8bb5c412d977af7ea7c7ea91977a6a64dc Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 7 Oct 2022 17:44:39 +0100 Subject: rxrpc: Clone received jumbo subpackets and queue separately Split up received jumbo packets into separate skbuffs by cloning the original skbuff for each subpacket and setting the offset and length of the data in that subpacket in the skbuff's private data. The subpackets are then placed on the recvmsg queue separately. The security class then gets to revise the offset and length to remove its metadata. If we fail to clone a packet, we just drop it and let the peer resend it. The original packet gets used for the final subpacket. This should make it easier to handle parallel decryption of the subpackets. It also simplifies the handling of lost or misordered packets in the queuing/buffering loop as the possibility of overlapping jumbo packets no longer needs to be considered. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 12 +- net/rxrpc/ar-internal.h | 32 +--- net/rxrpc/input.c | 401 ++++++++++++++++++++----------------------- net/rxrpc/insecure.c | 13 +- net/rxrpc/output.c | 2 +- net/rxrpc/protocol.h | 2 +- net/rxrpc/recvmsg.c | 104 ++--------- net/rxrpc/rxkad.c | 96 +++-------- 8 files changed, 245 insertions(+), 417 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 84464b29e54a..03a984e661bc 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -18,6 +18,7 @@ */ #define rxrpc_skb_traces \ EM(rxrpc_skb_cleaned, "CLN") \ + EM(rxrpc_skb_cloned_jumbo, "CLJ") \ EM(rxrpc_skb_freed, "FRE") \ EM(rxrpc_skb_got, "GOT") \ EM(rxrpc_skb_lost, "*L*") \ @@ -630,16 +631,15 @@ TRACE_EVENT(rxrpc_transmit, TRACE_EVENT(rxrpc_rx_data, TP_PROTO(unsigned int call, rxrpc_seq_t seq, - rxrpc_serial_t serial, u8 flags, u8 anno), + rxrpc_serial_t serial, u8 flags), - TP_ARGS(call, seq, serial, flags, anno), + TP_ARGS(call, seq, serial, flags), TP_STRUCT__entry( __field(unsigned int, call ) __field(rxrpc_seq_t, seq ) __field(rxrpc_serial_t, serial ) __field(u8, flags ) - __field(u8, anno ) ), TP_fast_assign( @@ -647,15 +647,13 @@ TRACE_EVENT(rxrpc_rx_data, __entry->seq = seq; __entry->serial = serial; __entry->flags = flags; - __entry->anno = anno; ), - TP_printk("c=%08x DATA %08x q=%08x fl=%02x a=%02x", + TP_printk("c=%08x DATA %08x q=%08x fl=%02x", __entry->call, __entry->serial, __entry->seq, - __entry->flags, - __entry->anno) + __entry->flags) ); TRACE_EVENT(rxrpc_rx_ack, diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 5a81545a58d5..e93ed18816b1 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -195,19 +195,14 @@ struct rxrpc_host_header { * - max 48 bytes (struct sk_buff::cb) */ struct rxrpc_skb_priv { - atomic_t nr_ring_pins; /* Number of rxtx ring pins */ - u8 nr_subpackets; /* Number of subpackets */ - u8 rx_flags; /* Received packet flags */ -#define RXRPC_SKB_INCL_LAST 0x01 /* - Includes last packet */ - union { - int remain; /* amount of space remaining for next write */ - - /* List of requested ACKs on subpackets */ - unsigned long rx_req_ack[(RXRPC_MAX_NR_JUMBO + BITS_PER_LONG - 1) / - BITS_PER_LONG]; - }; - - struct rxrpc_host_header hdr; /* RxRPC packet header from this packet */ + u16 remain; + u16 offset; /* Offset of data */ + u16 len; /* Length of data */ + u8 rx_flags; /* Received packet flags */ + u8 flags; +#define RXRPC_RX_VERIFIED 0x01 + + struct rxrpc_host_header hdr; /* RxRPC packet header from this packet */ }; #define rxrpc_skb(__skb) ((struct rxrpc_skb_priv *) &(__skb)->cb) @@ -252,16 +247,11 @@ struct rxrpc_security { int (*secure_packet)(struct rxrpc_call *, struct sk_buff *, size_t); /* verify the security on a received packet */ - int (*verify_packet)(struct rxrpc_call *, struct sk_buff *, - unsigned int, unsigned int, rxrpc_seq_t, u16); + int (*verify_packet)(struct rxrpc_call *, struct sk_buff *); /* Free crypto request on a call */ void (*free_call_crypto)(struct rxrpc_call *); - /* Locate the data in a received packet that has been verified. */ - void (*locate_data)(struct rxrpc_call *, struct sk_buff *, - unsigned int *, unsigned int *); - /* issue a challenge */ int (*issue_challenge)(struct rxrpc_connection *); @@ -628,7 +618,6 @@ struct rxrpc_call { int debug_id; /* debug ID for printks */ unsigned short rx_pkt_offset; /* Current recvmsg packet offset */ unsigned short rx_pkt_len; /* Current recvmsg packet len */ - bool rx_pkt_last; /* Current recvmsg packet is last */ /* Rx/Tx circular buffer, depending on phase. * @@ -652,8 +641,6 @@ struct rxrpc_call { #define RXRPC_TX_ANNO_LAST 0x04 #define RXRPC_TX_ANNO_RESENT 0x08 -#define RXRPC_RX_ANNO_SUBPACKET 0x3f /* Subpacket number in jumbogram */ -#define RXRPC_RX_ANNO_VERIFIED 0x80 /* Set if verified and decrypted */ rxrpc_seq_t tx_hard_ack; /* Dead slot in buffer; the first transmitted but * not hard-ACK'd packet follows this. */ @@ -681,7 +668,6 @@ struct rxrpc_call { rxrpc_serial_t rx_serial; /* Highest serial received for this call */ u8 rx_winsize; /* Size of Rx window */ u8 tx_winsize; /* Maximum size of Tx window */ - u8 nr_jumbo_bad; /* Number of jumbo dups/exceeds-windows */ spinlock_t input_lock; /* Lock for packet input to this call */ diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 4df1bdc4de6c..0e7545ed0128 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -313,78 +313,178 @@ static bool rxrpc_receiving_reply(struct rxrpc_call *call) } /* - * Scan a data packet to validate its structure and to work out how many - * subpackets it contains. - * - * A jumbo packet is a collection of consecutive packets glued together with - * little headers between that indicate how to change the initial header for - * each subpacket. - * - * RXRPC_JUMBO_PACKET must be set on all but the last subpacket - and all but - * the last are RXRPC_JUMBO_DATALEN in size. The last subpacket may be of any - * size. + * Process a DATA packet, adding the packet to the Rx ring. The caller's + * packet ref must be passed on or discarded. */ -static bool rxrpc_validate_data(struct sk_buff *skb) +static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - unsigned int offset = sizeof(struct rxrpc_wire_header); - unsigned int len = skb->len; - u8 flags = sp->hdr.flags; + rxrpc_serial_t serial = sp->hdr.serial; + rxrpc_seq_t seq = sp->hdr.seq, hard_ack; + unsigned int ix = seq & RXRPC_RXTX_BUFF_MASK; + bool last = sp->hdr.flags & RXRPC_LAST_PACKET; + bool acked = false; - for (;;) { - if (flags & RXRPC_REQUEST_ACK) - __set_bit(sp->nr_subpackets, sp->rx_req_ack); - sp->nr_subpackets++; + rxrpc_inc_stat(call->rxnet, stat_rx_data); + if (sp->hdr.flags & RXRPC_REQUEST_ACK) + rxrpc_inc_stat(call->rxnet, stat_rx_data_reqack); + if (sp->hdr.flags & RXRPC_JUMBO_PACKET) + rxrpc_inc_stat(call->rxnet, stat_rx_data_jumbo); - if (!(flags & RXRPC_JUMBO_PACKET)) - break; + hard_ack = READ_ONCE(call->rx_hard_ack); - if (len - offset < RXRPC_JUMBO_SUBPKTLEN) - goto protocol_error; - if (flags & RXRPC_LAST_PACKET) - goto protocol_error; - offset += RXRPC_JUMBO_DATALEN; - if (skb_copy_bits(skb, offset, &flags, 1) < 0) - goto protocol_error; - offset += sizeof(struct rxrpc_jumbo_header); + _proto("Rx DATA %%%u { #%x l=%u }", serial, seq, last); + + if (last) { + if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && + seq != call->rx_top) { + rxrpc_proto_abort("LSN", call, seq); + goto out; + } + } else { + if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && + after_eq(seq, call->rx_top)) { + rxrpc_proto_abort("LSA", call, seq); + goto out; + } } - if (flags & RXRPC_LAST_PACKET) - sp->rx_flags |= RXRPC_SKB_INCL_LAST; - return true; + trace_rxrpc_rx_data(call->debug_id, seq, serial, sp->hdr.flags); -protocol_error: - return false; + if (before_eq(seq, hard_ack)) { + rxrpc_send_ACK(call, RXRPC_ACK_DUPLICATE, serial, + rxrpc_propose_ack_input_data); + goto out; + } + + if (call->rxtx_buffer[ix]) { + rxrpc_send_ACK(call, RXRPC_ACK_DUPLICATE, serial, + rxrpc_propose_ack_input_data); + goto out; + } + + if (after(seq, hard_ack + call->rx_winsize)) { + rxrpc_send_ACK(call, RXRPC_ACK_EXCEEDS_WINDOW, serial, + rxrpc_propose_ack_input_data); + goto out; + } + + if (sp->hdr.flags & RXRPC_REQUEST_ACK) { + rxrpc_send_ACK(call, RXRPC_ACK_REQUESTED, serial, + rxrpc_propose_ack_input_data); + acked = true; + } + + if (after(seq, call->ackr_highest_seq)) + call->ackr_highest_seq = seq; + + /* Queue the packet. We use a couple of memory barriers here as need + * to make sure that rx_top is perceived to be set after the buffer + * pointer and that the buffer pointer is set after the annotation and + * the skb data. + * + * Barriers against rxrpc_recvmsg_data() and rxrpc_rotate_rx_window() + * and also rxrpc_fill_out_ack(). + */ + call->rxtx_annotations[ix] = 1; + smp_wmb(); + call->rxtx_buffer[ix] = skb; + if (after(seq, call->rx_top)) { + smp_store_release(&call->rx_top, seq); + } else if (before(seq, call->rx_top)) { + /* Send an immediate ACK if we fill in a hole */ + if (!acked) { + rxrpc_send_ACK(call, RXRPC_ACK_DELAY, serial, + rxrpc_propose_ack_input_data_hole); + acked = true; + } + } + + /* From this point on, we're not allowed to touch the packet any longer + * as its ref now belongs to the Rx ring. + */ + skb = NULL; + sp = NULL; + + if (last) { + set_bit(RXRPC_CALL_RX_LAST, &call->flags); + trace_rxrpc_receive(call, rxrpc_receive_queue_last, serial, seq); + } else { + trace_rxrpc_receive(call, rxrpc_receive_queue, serial, seq); + } + + if (after_eq(seq, call->rx_expect_next)) { + if (after(seq, call->rx_expect_next)) { + _net("OOS %u > %u", seq, call->rx_expect_next); + rxrpc_send_ACK(call, RXRPC_ACK_OUT_OF_SEQUENCE, serial, + rxrpc_propose_ack_input_data); + acked = true; + } + call->rx_expect_next = seq + 1; + } + +out: + if (!acked && + atomic_inc_return(&call->ackr_nr_unacked) > 2) + rxrpc_send_ACK(call, RXRPC_ACK_IDLE, serial, + rxrpc_propose_ack_input_data); + else + rxrpc_propose_delay_ACK(call, serial, + rxrpc_propose_ack_input_data); + + trace_rxrpc_notify_socket(call->debug_id, serial); + rxrpc_notify_socket(call); + + rxrpc_free_skb(skb, rxrpc_skb_freed); + _leave(" [queued]"); } /* - * Handle reception of a duplicate packet. - * - * We have to take care to avoid an attack here whereby we're given a series of - * jumbograms, each with a sequence number one before the preceding one and - * filled up to maximum UDP size. If they never send us the first packet in - * the sequence, they can cause us to have to hold on to around 2MiB of kernel - * space until the call times out. - * - * We limit the space usage by only accepting three duplicate jumbo packets per - * call. After that, we tell the other side we're no longer accepting jumbos - * (that information is encoded in the ACK packet). + * Split a jumbo packet and file the bits separately. */ -static void rxrpc_input_dup_data(struct rxrpc_call *call, rxrpc_seq_t seq, - bool is_jumbo, bool *_jumbo_bad) +static bool rxrpc_input_split_jumbo(struct rxrpc_call *call, struct sk_buff *skb) { - /* Discard normal packets that are duplicates. */ - if (is_jumbo) - return; + struct rxrpc_jumbo_header jhdr; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb), *jsp; + struct sk_buff *jskb; + unsigned int offset = sizeof(struct rxrpc_wire_header); + unsigned int len = skb->len - offset; - /* Skip jumbo subpackets that are duplicates. When we've had three or - * more partially duplicate jumbo packets, we refuse to take any more - * jumbos for this call. - */ - if (!*_jumbo_bad) { - call->nr_jumbo_bad++; - *_jumbo_bad = true; + while (sp->hdr.flags & RXRPC_JUMBO_PACKET) { + if (len < RXRPC_JUMBO_SUBPKTLEN) + goto protocol_error; + if (sp->hdr.flags & RXRPC_LAST_PACKET) + goto protocol_error; + if (skb_copy_bits(skb, offset + RXRPC_JUMBO_DATALEN, + &jhdr, sizeof(jhdr)) < 0) + goto protocol_error; + + jskb = skb_clone(skb, GFP_ATOMIC); + if (!jskb) { + kdebug("couldn't clone"); + return false; + } + rxrpc_new_skb(jskb, rxrpc_skb_cloned_jumbo); + jsp = rxrpc_skb(jskb); + jsp->offset = offset; + jsp->len = RXRPC_JUMBO_DATALEN; + rxrpc_input_data_one(call, jskb); + + sp->hdr.flags = jhdr.flags; + sp->hdr._rsvd = ntohs(jhdr._rsvd); + sp->hdr.seq++; + sp->hdr.serial++; + offset += RXRPC_JUMBO_SUBPKTLEN; + len -= RXRPC_JUMBO_SUBPKTLEN; } + + sp->offset = offset; + sp->len = len; + rxrpc_input_data_one(call, skb); + return true; + +protocol_error: + return false; } /* @@ -395,16 +495,14 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); enum rxrpc_call_state state; - unsigned int j, nr_subpackets, nr_unacked = 0; - rxrpc_serial_t serial = sp->hdr.serial, ack_serial = serial; - rxrpc_seq_t seq0 = sp->hdr.seq, hard_ack; - bool jumbo_bad = false; + rxrpc_serial_t serial = sp->hdr.serial; + rxrpc_seq_t seq0 = sp->hdr.seq; _enter("{%u,%u},{%u,%u}", call->rx_hard_ack, call->rx_top, skb->len, seq0); - _proto("Rx DATA %%%u { #%u f=%02x n=%u }", - sp->hdr.serial, seq0, sp->hdr.flags, sp->nr_subpackets); + _proto("Rx DATA %%%u { #%u f=%02x }", + sp->hdr.serial, seq0, sp->hdr.flags); state = READ_ONCE(call->state); if (state >= RXRPC_CALL_COMPLETE) { @@ -412,6 +510,24 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) return; } + /* Unshare the packet so that it can be modified for in-place + * decryption. + */ + if (sp->hdr.securityIndex != 0) { + struct sk_buff *nskb = skb_unshare(skb, GFP_ATOMIC); + if (!nskb) { + rxrpc_eaten_skb(skb, rxrpc_skb_unshared_nomem); + return; + } + + if (nskb != skb) { + rxrpc_eaten_skb(skb, rxrpc_skb_received); + skb = nskb; + rxrpc_new_skb(skb, rxrpc_skb_unshared); + sp = rxrpc_skb(skb); + } + } + if (state == RXRPC_CALL_SERVER_RECV_REQUEST) { unsigned long timo = READ_ONCE(call->next_req_timo); unsigned long now, expect_req_by; @@ -425,12 +541,6 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) } } - rxrpc_inc_stat(call->rxnet, stat_rx_data); - if (sp->hdr.flags & RXRPC_REQUEST_ACK) - rxrpc_inc_stat(call->rxnet, stat_rx_data_reqack); - if (sp->hdr.flags & RXRPC_JUMBO_PACKET) - rxrpc_inc_stat(call->rxnet, stat_rx_data_jumbo); - spin_lock(&call->input_lock); /* Received data implicitly ACKs all of the request packets we sent @@ -439,154 +549,15 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) if ((state == RXRPC_CALL_CLIENT_SEND_REQUEST || state == RXRPC_CALL_CLIENT_AWAIT_REPLY) && !rxrpc_receiving_reply(call)) - goto unlock; - - hard_ack = READ_ONCE(call->rx_hard_ack); - - nr_subpackets = sp->nr_subpackets; - if (nr_subpackets > 1) { - if (call->nr_jumbo_bad > 3) { - rxrpc_send_ACK(call, RXRPC_ACK_NOSPACE, serial, - rxrpc_propose_ack_input_data); - goto unlock; - } - } - - for (j = 0; j < nr_subpackets; j++) { - rxrpc_serial_t serial = sp->hdr.serial + j; - rxrpc_seq_t seq = seq0 + j; - unsigned int ix = seq & RXRPC_RXTX_BUFF_MASK; - bool terminal = (j == nr_subpackets - 1); - bool last = terminal && (sp->rx_flags & RXRPC_SKB_INCL_LAST); - bool acked = false; - u8 flags, annotation = j; - - _proto("Rx DATA+%u %%%u { #%x t=%u l=%u }", - j, serial, seq, terminal, last); - - if (last) { - if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && - seq != call->rx_top) { - rxrpc_proto_abort("LSN", call, seq); - goto unlock; - } - } else { - if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && - after_eq(seq, call->rx_top)) { - rxrpc_proto_abort("LSA", call, seq); - goto unlock; - } - } - - flags = 0; - if (last) - flags |= RXRPC_LAST_PACKET; - if (!terminal) - flags |= RXRPC_JUMBO_PACKET; - if (test_bit(j, sp->rx_req_ack)) - flags |= RXRPC_REQUEST_ACK; - trace_rxrpc_rx_data(call->debug_id, seq, serial, flags, annotation); - - if (before_eq(seq, hard_ack)) { - rxrpc_send_ACK(call, RXRPC_ACK_DUPLICATE, serial, - rxrpc_propose_ack_input_data); - continue; - } - - if (call->rxtx_buffer[ix]) { - rxrpc_input_dup_data(call, seq, nr_subpackets > 1, - &jumbo_bad); - rxrpc_send_ACK(call, RXRPC_ACK_DUPLICATE, serial, - rxrpc_propose_ack_input_data); - continue; - } - - if (after(seq, hard_ack + call->rx_winsize)) { - rxrpc_send_ACK(call, RXRPC_ACK_EXCEEDS_WINDOW, serial, - rxrpc_propose_ack_input_data); - if (flags & RXRPC_JUMBO_PACKET) { - if (!jumbo_bad) { - call->nr_jumbo_bad++; - jumbo_bad = true; - } - } - - goto unlock; - } - - if (flags & RXRPC_REQUEST_ACK) { - rxrpc_send_ACK(call, RXRPC_ACK_REQUESTED, serial, - rxrpc_propose_ack_input_data); - acked = true; - } - - if (after(seq0, call->ackr_highest_seq)) - call->ackr_highest_seq = seq0; - - /* Queue the packet. We use a couple of memory barriers here as need - * to make sure that rx_top is perceived to be set after the buffer - * pointer and that the buffer pointer is set after the annotation and - * the skb data. - * - * Barriers against rxrpc_recvmsg_data() and rxrpc_rotate_rx_window() - * and also rxrpc_fill_out_ack(). - */ - if (!terminal) - rxrpc_get_skb(skb, rxrpc_skb_got); - call->rxtx_annotations[ix] = annotation; - smp_wmb(); - call->rxtx_buffer[ix] = skb; - if (after(seq, call->rx_top)) { - smp_store_release(&call->rx_top, seq); - } else if (before(seq, call->rx_top)) { - /* Send an immediate ACK if we fill in a hole */ - if (!acked) { - rxrpc_send_ACK(call, RXRPC_ACK_DELAY, serial, - rxrpc_propose_ack_input_data_hole); - acked = true; - } - } - - if (terminal) { - /* From this point on, we're not allowed to touch the - * packet any longer as its ref now belongs to the Rx - * ring. - */ - skb = NULL; - sp = NULL; - } - - if (last) { - set_bit(RXRPC_CALL_RX_LAST, &call->flags); - trace_rxrpc_receive(call, rxrpc_receive_queue_last, serial, seq); - } else { - trace_rxrpc_receive(call, rxrpc_receive_queue, serial, seq); - } - - if (after_eq(seq, call->rx_expect_next)) { - if (after(seq, call->rx_expect_next)) { - _net("OOS %u > %u", seq, call->rx_expect_next); - rxrpc_send_ACK(call, RXRPC_ACK_OUT_OF_SEQUENCE, serial, - rxrpc_propose_ack_input_data); - acked = true; - } - call->rx_expect_next = seq + 1; - } + goto out; - if (!acked) { - nr_unacked++; - ack_serial = serial; - } + if (!rxrpc_input_split_jumbo(call, skb)) { + rxrpc_proto_abort("VLD", call, sp->hdr.seq); + goto out; } + skb = NULL; -unlock: - if (atomic_add_return(nr_unacked, &call->ackr_nr_unacked) > 2) - rxrpc_send_ACK(call, RXRPC_ACK_IDLE, ack_serial, - rxrpc_propose_ack_input_data); - else - rxrpc_propose_delay_ACK(call, ack_serial, - rxrpc_propose_ack_input_data); - +out: trace_rxrpc_notify_socket(call->debug_id, serial); rxrpc_notify_socket(call); @@ -1288,8 +1259,6 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) if (sp->hdr.callNumber == 0 || sp->hdr.seq == 0) goto bad_message; - if (!rxrpc_validate_data(skb)) - goto bad_message; /* Unshare the packet so that it can be modified for in-place * decryption. @@ -1403,7 +1372,7 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) trace_rxrpc_rx_data(chan->call_debug_id, sp->hdr.seq, sp->hdr.serial, - sp->hdr.flags, 0); + sp->hdr.flags); rxrpc_post_packet_to_conn(conn, skb); goto out; } diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c index 9aae99d67833..fd68f0e3af27 100644 --- a/net/rxrpc/insecure.c +++ b/net/rxrpc/insecure.c @@ -31,10 +31,11 @@ static int none_secure_packet(struct rxrpc_call *call, struct sk_buff *skb, return 0; } -static int none_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int offset, unsigned int len, - rxrpc_seq_t seq, u16 expected_cksum) +static int none_verify_packet(struct rxrpc_call *call, struct sk_buff *skb) { + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + + sp->flags |= RXRPC_RX_VERIFIED; return 0; } @@ -42,11 +43,6 @@ static void none_free_call_crypto(struct rxrpc_call *call) { } -static void none_locate_data(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int *_offset, unsigned int *_len) -{ -} - static int none_respond_to_challenge(struct rxrpc_connection *conn, struct sk_buff *skb, u32 *_abort_code) @@ -95,7 +91,6 @@ const struct rxrpc_security rxrpc_no_security = { .how_much_data = none_how_much_data, .secure_packet = none_secure_packet, .verify_packet = none_verify_packet, - .locate_data = none_locate_data, .respond_to_challenge = none_respond_to_challenge, .verify_response = none_verify_response, .clear = none_clear, diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index d35657b659ad..f7bb792c8aa1 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -121,7 +121,7 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, mtu = conn->params.peer->if_mtu; mtu -= conn->params.peer->hdrsize; - jmax = (call->nr_jumbo_bad > 3) ? 1 : rxrpc_rx_jumbo_max; + jmax = rxrpc_rx_jumbo_max; ackinfo.rxMTU = htonl(rxrpc_rx_mtu); ackinfo.maxMTU = htonl(mtu); ackinfo.rwind = htonl(call->rx_winsize); diff --git a/net/rxrpc/protocol.h b/net/rxrpc/protocol.h index f3d4e2700901..6760cb99c6d6 100644 --- a/net/rxrpc/protocol.h +++ b/net/rxrpc/protocol.h @@ -84,7 +84,7 @@ struct rxrpc_jumbo_header { __be16 _rsvd; /* reserved */ __be16 cksum; /* kerberos security checksum */ }; -}; +} __packed; #define RXRPC_JUMBO_DATALEN 1412 /* non-terminal jumbo packet data length */ #define RXRPC_JUMBO_SUBPKTLEN (RXRPC_JUMBO_DATALEN + sizeof(struct rxrpc_jumbo_header)) diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 77cde6311559..401aae687830 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -222,7 +222,6 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) rxrpc_serial_t serial; rxrpc_seq_t hard_ack, top; bool last = false; - u8 subpacket; int ix; _enter("%d", call->debug_id); @@ -237,11 +236,9 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) rxrpc_see_skb(skb, rxrpc_skb_rotated); sp = rxrpc_skb(skb); - subpacket = call->rxtx_annotations[ix] & RXRPC_RX_ANNO_SUBPACKET; - serial = sp->hdr.serial + subpacket; + serial = sp->hdr.serial; - if (subpacket == sp->nr_subpackets - 1 && - sp->rx_flags & RXRPC_SKB_INCL_LAST) + if (sp->hdr.flags & RXRPC_LAST_PACKET) last = true; call->rxtx_buffer[ix] = NULL; @@ -266,80 +263,15 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) } /* - * Decrypt and verify a (sub)packet. The packet's length may be changed due to - * padding, but if this is the case, the packet length will be resident in the - * socket buffer. Note that we can't modify the master skb info as the skb may - * be the home to multiple subpackets. + * Decrypt and verify a DATA packet. */ -static int rxrpc_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, - u8 annotation, - unsigned int offset, unsigned int len) +static int rxrpc_verify_data(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - rxrpc_seq_t seq = sp->hdr.seq; - u16 cksum = sp->hdr.cksum; - u8 subpacket = annotation & RXRPC_RX_ANNO_SUBPACKET; - _enter(""); - - /* For all but the head jumbo subpacket, the security checksum is in a - * jumbo header immediately prior to the data. - */ - if (subpacket > 0) { - __be16 tmp; - if (skb_copy_bits(skb, offset - 2, &tmp, 2) < 0) - BUG(); - cksum = ntohs(tmp); - seq += subpacket; - } - - return call->security->verify_packet(call, skb, offset, len, - seq, cksum); -} - -/* - * Locate the data within a packet. This is complicated by: - * - * (1) An skb may contain a jumbo packet - so we have to find the appropriate - * subpacket. - * - * (2) The (sub)packets may be encrypted and, if so, the encrypted portion - * contains an extra header which includes the true length of the data, - * excluding any encrypted padding. - */ -static int rxrpc_locate_data(struct rxrpc_call *call, struct sk_buff *skb, - u8 *_annotation, - unsigned int *_offset, unsigned int *_len, - bool *_last) -{ - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - unsigned int offset = sizeof(struct rxrpc_wire_header); - unsigned int len; - bool last = false; - int ret; - u8 annotation = *_annotation; - u8 subpacket = annotation & RXRPC_RX_ANNO_SUBPACKET; - - /* Locate the subpacket */ - offset += subpacket * RXRPC_JUMBO_SUBPKTLEN; - len = skb->len - offset; - if (subpacket < sp->nr_subpackets - 1) - len = RXRPC_JUMBO_DATALEN; - else if (sp->rx_flags & RXRPC_SKB_INCL_LAST) - last = true; - - if (!(annotation & RXRPC_RX_ANNO_VERIFIED)) { - ret = rxrpc_verify_packet(call, skb, annotation, offset, len); - if (ret < 0) - return ret; - *_annotation |= RXRPC_RX_ANNO_VERIFIED; - } - - *_offset = offset; - *_len = len; - *_last = last; - call->security->locate_data(call, skb, _offset, _len); - return 0; + if (sp->flags & RXRPC_RX_VERIFIED) + return 0; + return call->security->verify_packet(call, skb); } /* @@ -356,13 +288,11 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, rxrpc_serial_t serial; rxrpc_seq_t hard_ack, top, seq; size_t remain; - bool rx_pkt_last; unsigned int rx_pkt_offset, rx_pkt_len; int ix, copy, ret = -EAGAIN, ret2; rx_pkt_offset = call->rx_pkt_offset; rx_pkt_len = call->rx_pkt_len; - rx_pkt_last = call->rx_pkt_last; if (call->state >= RXRPC_CALL_SERVER_ACK_REQUEST) { seq = call->rx_hard_ack; @@ -391,7 +321,6 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, if (!(flags & MSG_PEEK)) { serial = sp->hdr.serial; - serial += call->rxtx_annotations[ix] & RXRPC_RX_ANNO_SUBPACKET; trace_rxrpc_receive(call, rxrpc_receive_front, serial, seq); } @@ -400,10 +329,9 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, sock_recv_timestamp(msg, sock->sk, skb); if (rx_pkt_offset == 0) { - ret2 = rxrpc_locate_data(call, skb, - &call->rxtx_annotations[ix], - &rx_pkt_offset, &rx_pkt_len, - &rx_pkt_last); + ret2 = rxrpc_verify_data(call, skb); + rx_pkt_offset = sp->offset; + rx_pkt_len = sp->len; trace_rxrpc_recvdata(call, rxrpc_recvmsg_next, seq, rx_pkt_offset, rx_pkt_len, ret2); if (ret2 < 0) { @@ -443,16 +371,13 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, } /* The whole packet has been transferred. */ - if (!(flags & MSG_PEEK)) - rxrpc_rotate_rx_window(call); + if (sp->hdr.flags & RXRPC_LAST_PACKET) + ret = 1; rx_pkt_offset = 0; rx_pkt_len = 0; - if (rx_pkt_last) { - ASSERTCMP(seq, ==, READ_ONCE(call->rx_top)); - ret = 1; - goto out; - } + if (!(flags & MSG_PEEK)) + rxrpc_rotate_rx_window(call); seq++; } @@ -461,7 +386,6 @@ out: if (!(flags & MSG_PEEK)) { call->rx_pkt_offset = rx_pkt_offset; call->rx_pkt_len = rx_pkt_len; - call->rx_pkt_last = rx_pkt_last; } done: trace_rxrpc_recvdata(call, rxrpc_recvmsg_data_return, seq, diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 78fa0524156f..b19937776aa9 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -439,11 +439,11 @@ static int rxkad_secure_packet(struct rxrpc_call *call, * decrypt partial encryption on a packet (level 1 security) */ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int offset, unsigned int len, rxrpc_seq_t seq, struct skcipher_request *req) { struct rxkad_level1_hdr sechdr; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_crypt iv; struct scatterlist sg[16]; bool aborted; @@ -453,9 +453,9 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, _enter(""); - if (len < 8) { + if (sp->len < 8) { aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_hdr", "V1H", - RXKADSEALEDINCON); + RXKADSEALEDINCON); goto protocol_error; } @@ -463,7 +463,7 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, * directly into the target buffer. */ sg_init_table(sg, ARRAY_SIZE(sg)); - ret = skb_to_sgvec(skb, sg, offset, 8); + ret = skb_to_sgvec(skb, sg, sp->offset, 8); if (unlikely(ret < 0)) return ret; @@ -477,12 +477,13 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, skcipher_request_zero(req); /* Extract the decrypted packet length */ - if (skb_copy_bits(skb, offset, &sechdr, sizeof(sechdr)) < 0) { + if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0) { aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_len", "XV1", RXKADDATALEN); goto protocol_error; } - len -= sizeof(sechdr); + sp->offset += sizeof(sechdr); + sp->len -= sizeof(sechdr); buf = ntohl(sechdr.data_size); data_size = buf & 0xffff; @@ -496,11 +497,12 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, goto protocol_error; } - if (data_size > len) { + if (data_size > sp->len) { aborted = rxrpc_abort_eproto(call, skb, "rxkad_1_datalen", "V1L", RXKADDATALEN); goto protocol_error; } + sp->len = data_size; _leave(" = 0 [dlen=%x]", data_size); return 0; @@ -515,12 +517,12 @@ protocol_error: * wholly decrypt a packet (level 2 security) */ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int offset, unsigned int len, rxrpc_seq_t seq, struct skcipher_request *req) { const struct rxrpc_key_token *token; struct rxkad_level2_hdr sechdr; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_crypt iv; struct scatterlist _sg[4], *sg; bool aborted; @@ -528,9 +530,9 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, u16 check; int nsg, ret; - _enter(",{%d}", skb->len); + _enter(",{%d}", sp->len); - if (len < 8) { + if (sp->len < 8) { aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_hdr", "V2H", RXKADSEALEDINCON); goto protocol_error; @@ -550,7 +552,7 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, } sg_init_table(sg, nsg); - ret = skb_to_sgvec(skb, sg, offset, len); + ret = skb_to_sgvec(skb, sg, sp->offset, sp->len); if (unlikely(ret < 0)) { if (sg != _sg) kfree(sg); @@ -563,19 +565,20 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher); skcipher_request_set_callback(req, 0, NULL, NULL); - skcipher_request_set_crypt(req, sg, sg, len, iv.x); + skcipher_request_set_crypt(req, sg, sg, sp->len, iv.x); crypto_skcipher_decrypt(req); skcipher_request_zero(req); if (sg != _sg) kfree(sg); /* Extract the decrypted packet length */ - if (skb_copy_bits(skb, offset, &sechdr, sizeof(sechdr)) < 0) { + if (skb_copy_bits(skb, sp->offset, &sechdr, sizeof(sechdr)) < 0) { aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_len", "XV2", RXKADDATALEN); goto protocol_error; } - len -= sizeof(sechdr); + sp->offset += sizeof(sechdr); + sp->len -= sizeof(sechdr); buf = ntohl(sechdr.data_size); data_size = buf & 0xffff; @@ -589,12 +592,13 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, goto protocol_error; } - if (data_size > len) { + if (data_size > sp->len) { aborted = rxrpc_abort_eproto(call, skb, "rxkad_2_datalen", "V2L", RXKADDATALEN); goto protocol_error; } + sp->len = data_size; _leave(" = 0 [dlen=%x]", data_size); return 0; @@ -609,16 +613,15 @@ nomem: } /* - * Verify the security on a received packet or subpacket (if part of a - * jumbo packet). + * Verify the security on a received packet and the subpackets therein. */ -static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int offset, unsigned int len, - rxrpc_seq_t seq, u16 expected_cksum) +static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb) { + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct skcipher_request *req; struct rxrpc_crypt iv; struct scatterlist sg; + rxrpc_seq_t seq = sp->hdr.seq; bool aborted; u16 cksum; u32 x, y; @@ -654,7 +657,7 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, if (cksum == 0) cksum = 1; /* zero checksums are not permitted */ - if (cksum != expected_cksum) { + if (cksum != sp->hdr.cksum) { aborted = rxrpc_abort_eproto(call, skb, "rxkad_csum", "VCK", RXKADSEALEDINCON); goto protocol_error; @@ -664,9 +667,9 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, case RXRPC_SECURITY_PLAIN: return 0; case RXRPC_SECURITY_AUTH: - return rxkad_verify_packet_1(call, skb, offset, len, seq, req); + return rxkad_verify_packet_1(call, skb, seq, req); case RXRPC_SECURITY_ENCRYPT: - return rxkad_verify_packet_2(call, skb, offset, len, seq, req); + return rxkad_verify_packet_2(call, skb, seq, req); default: return -ENOANO; } @@ -677,52 +680,6 @@ protocol_error: return -EPROTO; } -/* - * Locate the data contained in a packet that was partially encrypted. - */ -static void rxkad_locate_data_1(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int *_offset, unsigned int *_len) -{ - struct rxkad_level1_hdr sechdr; - - if (skb_copy_bits(skb, *_offset, &sechdr, sizeof(sechdr)) < 0) - BUG(); - *_offset += sizeof(sechdr); - *_len = ntohl(sechdr.data_size) & 0xffff; -} - -/* - * Locate the data contained in a packet that was completely encrypted. - */ -static void rxkad_locate_data_2(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int *_offset, unsigned int *_len) -{ - struct rxkad_level2_hdr sechdr; - - if (skb_copy_bits(skb, *_offset, &sechdr, sizeof(sechdr)) < 0) - BUG(); - *_offset += sizeof(sechdr); - *_len = ntohl(sechdr.data_size) & 0xffff; -} - -/* - * Locate the data contained in an already decrypted packet. - */ -static void rxkad_locate_data(struct rxrpc_call *call, struct sk_buff *skb, - unsigned int *_offset, unsigned int *_len) -{ - switch (call->conn->params.security_level) { - case RXRPC_SECURITY_AUTH: - rxkad_locate_data_1(call, skb, _offset, _len); - return; - case RXRPC_SECURITY_ENCRYPT: - rxkad_locate_data_2(call, skb, _offset, _len); - return; - default: - return; - } -} - /* * issue a challenge */ @@ -1397,7 +1354,6 @@ const struct rxrpc_security rxkad = { .secure_packet = rxkad_secure_packet, .verify_packet = rxkad_verify_packet, .free_call_crypto = rxkad_free_call_crypto, - .locate_data = rxkad_locate_data, .issue_challenge = rxkad_issue_challenge, .respond_to_challenge = rxkad_respond_to_challenge, .verify_response = rxkad_verify_response, -- cgit v1.2.3 From 5d7edbc9231ec6b60f9c5b7e7980e9a1cd92e6bb Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 27 Aug 2022 14:27:56 +0100 Subject: rxrpc: Get rid of the Rx ring Get rid of the Rx ring and replace it with a pair of queues instead. One queue gets the packets that are in-sequence and are ready for processing by recvmsg(); the other queue gets the out-of-sequence packets for addition to the first queue as the holes get filled. The annotation ring is removed and replaced with a SACK table. The SACK table has the bits set that correspond exactly to the sequence number of the packet being acked. The SACK ring is copied when an ACK packet is being assembled and rotated so that the first ACK is in byte 0. Flow control handling is altered so that packets that are moved to the in-sequence queue are hard-ACK'd even before they're consumed - and then the Rx window size in the ACK packet (rsize) is shrunk down to compensate (even going to 0 if the window is full). Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 19 ++-- net/rxrpc/ar-internal.h | 29 +++--- net/rxrpc/call_object.c | 7 +- net/rxrpc/conn_object.c | 2 +- net/rxrpc/input.c | 213 ++++++++++++++++++++++++++----------------- net/rxrpc/misc.c | 5 +- net/rxrpc/output.c | 95 +++++++++++-------- net/rxrpc/proc.c | 7 +- net/rxrpc/recvmsg.c | 117 ++++++++++++------------ net/rxrpc/rxkad.c | 1 - net/rxrpc/sysctl.c | 2 +- 11 files changed, 290 insertions(+), 207 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 03a984e661bc..284a1560b0a8 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -104,7 +104,12 @@ EM(rxrpc_receive_incoming, "INC") \ EM(rxrpc_receive_queue, "QUE") \ EM(rxrpc_receive_queue_last, "QLS") \ - E_(rxrpc_receive_rotate, "ROT") + EM(rxrpc_receive_queue_oos, "QUO") \ + EM(rxrpc_receive_queue_oos_last, "QOL") \ + EM(rxrpc_receive_oos, "OOS") \ + EM(rxrpc_receive_oos_last, "OSL") \ + EM(rxrpc_receive_rotate, "ROT") \ + E_(rxrpc_receive_rotate_last, "RLS") #define rxrpc_recvmsg_traces \ EM(rxrpc_recvmsg_cont, "CONT") \ @@ -860,8 +865,7 @@ TRACE_EVENT(rxrpc_receive, __field(enum rxrpc_receive_trace, why ) __field(rxrpc_serial_t, serial ) __field(rxrpc_seq_t, seq ) - __field(rxrpc_seq_t, hard_ack ) - __field(rxrpc_seq_t, top ) + __field(u64, window ) ), TP_fast_assign( @@ -869,8 +873,7 @@ TRACE_EVENT(rxrpc_receive, __entry->why = why; __entry->serial = serial; __entry->seq = seq; - __entry->hard_ack = call->rx_hard_ack; - __entry->top = call->rx_top; + __entry->window = atomic64_read(&call->ackr_window); ), TP_printk("c=%08x %s r=%08x q=%08x w=%08x-%08x", @@ -878,8 +881,8 @@ TRACE_EVENT(rxrpc_receive, __print_symbolic(__entry->why, rxrpc_receive_traces), __entry->serial, __entry->seq, - __entry->hard_ack, - __entry->top) + lower_32_bits(__entry->window), + upper_32_bits(__entry->window)) ); TRACE_EVENT(rxrpc_recvmsg, @@ -1459,7 +1462,7 @@ TRACE_EVENT(rxrpc_call_reset, __entry->call_serial = call->rx_serial; __entry->conn_serial = call->conn->hi_serial; __entry->tx_seq = call->tx_hard_ack; - __entry->rx_seq = call->rx_hard_ack; + __entry->rx_seq = call->rx_highest_seq; ), TP_printk("c=%08x %08x:%08x r=%08x/%08x tx=%08x rx=%08x", diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index e93ed18816b1..c6c5bb3d3688 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -198,7 +198,6 @@ struct rxrpc_skb_priv { u16 remain; u16 offset; /* Offset of data */ u16 len; /* Length of data */ - u8 rx_flags; /* Received packet flags */ u8 flags; #define RXRPC_RX_VERIFIED 0x01 @@ -644,8 +643,20 @@ struct rxrpc_call { rxrpc_seq_t tx_hard_ack; /* Dead slot in buffer; the first transmitted but * not hard-ACK'd packet follows this. */ + + /* Transmitted data tracking. */ rxrpc_seq_t tx_top; /* Highest Tx slot allocated. */ u16 tx_backoff; /* Delay to insert due to Tx failure */ + u8 tx_winsize; /* Maximum size of Tx window */ + + /* Received data tracking */ + struct sk_buff_head recvmsg_queue; /* Queue of packets ready for recvmsg() */ + struct sk_buff_head rx_oos_queue; /* Queue of out of sequence packets */ + + rxrpc_seq_t rx_highest_seq; /* Higest sequence number received */ + rxrpc_seq_t rx_consumed; /* Highest packet consumed */ + rxrpc_serial_t rx_serial; /* Highest serial received for this call */ + u8 rx_winsize; /* Size of Rx window */ /* TCP-style slow-start congestion control [RFC5681]. Since the SMSS * is fixed, we keep these numbers in terms of segments (ie. DATA @@ -660,23 +671,19 @@ struct rxrpc_call { u8 cong_cumul_acks; /* Cumulative ACK count */ ktime_t cong_tstamp; /* Last time cwnd was changed */ - rxrpc_seq_t rx_hard_ack; /* Dead slot in buffer; the first received but not - * consumed packet follows this. - */ - rxrpc_seq_t rx_top; /* Highest Rx slot allocated. */ - rxrpc_seq_t rx_expect_next; /* Expected next packet sequence number */ - rxrpc_serial_t rx_serial; /* Highest serial received for this call */ - u8 rx_winsize; /* Size of Rx window */ - u8 tx_winsize; /* Maximum size of Tx window */ - spinlock_t input_lock; /* Lock for packet input to this call */ /* Receive-phase ACK management (ACKs we send). */ u8 ackr_reason; /* reason to ACK */ rxrpc_serial_t ackr_serial; /* serial of packet being ACK'd */ - rxrpc_seq_t ackr_highest_seq; /* Higest sequence number received */ + atomic64_t ackr_window; /* Base (in LSW) and top (in MSW) of SACK window */ atomic_t ackr_nr_unacked; /* Number of unacked packets */ atomic_t ackr_nr_consumed; /* Number of packets needing hard ACK */ + struct { +#define RXRPC_SACK_SIZE 256 + /* SACK table for soft-acked packets */ + u8 ackr_sack_table[RXRPC_SACK_SIZE]; + } __aligned(8); /* RTT management */ rxrpc_serial_t rtt_serial[4]; /* Serial number of DATA or PING sent */ diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 8f9e88897197..4d8601c6a32d 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -155,6 +155,8 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, INIT_LIST_HEAD(&call->accept_link); INIT_LIST_HEAD(&call->recvmsg_link); INIT_LIST_HEAD(&call->sock_link); + skb_queue_head_init(&call->recvmsg_queue); + skb_queue_head_init(&call->rx_oos_queue); init_waitqueue_head(&call->waitq); spin_lock_init(&call->lock); spin_lock_init(&call->notify_lock); @@ -165,13 +167,12 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, call->tx_total_len = -1; call->next_rx_timo = 20 * HZ; call->next_req_timo = 1 * HZ; + atomic64_set(&call->ackr_window, 0x100000001ULL); memset(&call->sock_node, 0xed, sizeof(call->sock_node)); - /* Leave space in the ring to handle a maxed-out jumbo packet */ call->rx_winsize = rxrpc_rx_window_size; call->tx_winsize = 16; - call->rx_expect_next = 1; call->cong_cwnd = 2; call->cong_ssthresh = RXRPC_RXTX_BUFF_SIZE - 1; @@ -519,6 +520,8 @@ static void rxrpc_cleanup_ring(struct rxrpc_call *call) rxrpc_free_skb(call->rxtx_buffer[i], rxrpc_skb_cleaned); call->rxtx_buffer[i] = NULL; } + skb_queue_purge(&call->recvmsg_queue); + skb_queue_purge(&call->rx_oos_queue); } /* diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 22089e37e97f..f7ea71ae6159 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -175,7 +175,7 @@ void __rxrpc_disconnect_call(struct rxrpc_connection *conn, trace_rxrpc_disconnect_call(call); switch (call->completion) { case RXRPC_CALL_SUCCEEDED: - chan->last_seq = call->rx_hard_ack; + chan->last_seq = call->rx_highest_seq; chan->last_type = RXRPC_PACKET_TYPE_ACK; break; case RXRPC_CALL_LOCALLY_ABORTED: diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 0e7545ed0128..947e7196e2be 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -312,18 +312,43 @@ static bool rxrpc_receiving_reply(struct rxrpc_call *call) return rxrpc_end_tx_phase(call, true, "ETD"); } +static void rxrpc_input_update_ack_window(struct rxrpc_call *call, + rxrpc_seq_t window, rxrpc_seq_t wtop) +{ + atomic64_set_release(&call->ackr_window, ((u64)wtop) << 32 | window); +} + /* - * Process a DATA packet, adding the packet to the Rx ring. The caller's - * packet ref must be passed on or discarded. + * Push a DATA packet onto the Rx queue. + */ +static void rxrpc_input_queue_data(struct rxrpc_call *call, struct sk_buff *skb, + rxrpc_seq_t window, rxrpc_seq_t wtop, + enum rxrpc_receive_trace why) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + bool last = sp->hdr.flags & RXRPC_LAST_PACKET; + + __skb_queue_tail(&call->recvmsg_queue, skb); + rxrpc_input_update_ack_window(call, window, wtop); + + trace_rxrpc_receive(call, last ? why + 1 : why, sp->hdr.serial, sp->hdr.seq); +} + +/* + * Process a DATA packet. */ static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + struct sk_buff *oos; rxrpc_serial_t serial = sp->hdr.serial; - rxrpc_seq_t seq = sp->hdr.seq, hard_ack; - unsigned int ix = seq & RXRPC_RXTX_BUFF_MASK; + u64 win = atomic64_read(&call->ackr_window); + rxrpc_seq_t window = lower_32_bits(win); + rxrpc_seq_t wtop = upper_32_bits(win); + rxrpc_seq_t wlimit = window + call->rx_winsize - 1; + rxrpc_seq_t seq = sp->hdr.seq; bool last = sp->hdr.flags & RXRPC_LAST_PACKET; - bool acked = false; + int ack_reason = -1; rxrpc_inc_stat(call->rxnet, stat_rx_data); if (sp->hdr.flags & RXRPC_REQUEST_ACK) @@ -331,112 +356,135 @@ static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb) if (sp->hdr.flags & RXRPC_JUMBO_PACKET) rxrpc_inc_stat(call->rxnet, stat_rx_data_jumbo); - hard_ack = READ_ONCE(call->rx_hard_ack); - - _proto("Rx DATA %%%u { #%x l=%u }", serial, seq, last); - if (last) { - if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && - seq != call->rx_top) { + if (test_and_set_bit(RXRPC_CALL_RX_LAST, &call->flags) && + seq + 1 != wtop) { rxrpc_proto_abort("LSN", call, seq); - goto out; + goto err_free; } } else { if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && - after_eq(seq, call->rx_top)) { + after_eq(seq, wtop)) { + pr_warn("Packet beyond last: c=%x q=%x window=%x-%x wlimit=%x\n", + call->debug_id, seq, window, wtop, wlimit); rxrpc_proto_abort("LSA", call, seq); - goto out; + goto err_free; } } + if (after(seq, call->rx_highest_seq)) + call->rx_highest_seq = seq; + trace_rxrpc_rx_data(call->debug_id, seq, serial, sp->hdr.flags); - if (before_eq(seq, hard_ack)) { - rxrpc_send_ACK(call, RXRPC_ACK_DUPLICATE, serial, - rxrpc_propose_ack_input_data); - goto out; + if (before(seq, window)) { + ack_reason = RXRPC_ACK_DUPLICATE; + goto send_ack; } - - if (call->rxtx_buffer[ix]) { - rxrpc_send_ACK(call, RXRPC_ACK_DUPLICATE, serial, - rxrpc_propose_ack_input_data); - goto out; + if (after(seq, wlimit)) { + ack_reason = RXRPC_ACK_EXCEEDS_WINDOW; + goto send_ack; } - if (after(seq, hard_ack + call->rx_winsize)) { - rxrpc_send_ACK(call, RXRPC_ACK_EXCEEDS_WINDOW, serial, - rxrpc_propose_ack_input_data); - goto out; - } + /* Queue the packet. */ + if (seq == window) { + rxrpc_seq_t reset_from; + bool reset_sack = false; - if (sp->hdr.flags & RXRPC_REQUEST_ACK) { - rxrpc_send_ACK(call, RXRPC_ACK_REQUESTED, serial, - rxrpc_propose_ack_input_data); - acked = true; - } + if (sp->hdr.flags & RXRPC_REQUEST_ACK) + ack_reason = RXRPC_ACK_REQUESTED; + /* Send an immediate ACK if we fill in a hole */ + else if (!skb_queue_empty(&call->rx_oos_queue)) + ack_reason = RXRPC_ACK_DELAY; - if (after(seq, call->ackr_highest_seq)) - call->ackr_highest_seq = seq; + window++; + if (after(window, wtop)) + wtop = window; - /* Queue the packet. We use a couple of memory barriers here as need - * to make sure that rx_top is perceived to be set after the buffer - * pointer and that the buffer pointer is set after the annotation and - * the skb data. - * - * Barriers against rxrpc_recvmsg_data() and rxrpc_rotate_rx_window() - * and also rxrpc_fill_out_ack(). - */ - call->rxtx_annotations[ix] = 1; - smp_wmb(); - call->rxtx_buffer[ix] = skb; - if (after(seq, call->rx_top)) { - smp_store_release(&call->rx_top, seq); - } else if (before(seq, call->rx_top)) { - /* Send an immediate ACK if we fill in a hole */ - if (!acked) { - rxrpc_send_ACK(call, RXRPC_ACK_DELAY, serial, - rxrpc_propose_ack_input_data_hole); - acked = true; + spin_lock(&call->recvmsg_queue.lock); + rxrpc_input_queue_data(call, skb, window, wtop, rxrpc_receive_queue); + skb = NULL; + + while ((oos = skb_peek(&call->rx_oos_queue))) { + struct rxrpc_skb_priv *osp = rxrpc_skb(oos); + + if (after(osp->hdr.seq, window)) + break; + + __skb_unlink(oos, &call->rx_oos_queue); + last = osp->hdr.flags & RXRPC_LAST_PACKET; + seq = osp->hdr.seq; + if (!reset_sack) { + reset_from = seq; + reset_sack = true; + } + + window++; + rxrpc_input_queue_data(call, oos, window, wtop, + rxrpc_receive_queue_oos); } - } - /* From this point on, we're not allowed to touch the packet any longer - * as its ref now belongs to the Rx ring. - */ - skb = NULL; - sp = NULL; + spin_unlock(&call->recvmsg_queue.lock); - if (last) { - set_bit(RXRPC_CALL_RX_LAST, &call->flags); - trace_rxrpc_receive(call, rxrpc_receive_queue_last, serial, seq); + if (reset_sack) { + do { + call->ackr_sack_table[reset_from % RXRPC_SACK_SIZE] = 0; + } while (reset_from++, before(reset_from, window)); + } } else { - trace_rxrpc_receive(call, rxrpc_receive_queue, serial, seq); - } + bool keep = false; + + ack_reason = RXRPC_ACK_OUT_OF_SEQUENCE; + + if (!call->ackr_sack_table[seq % RXRPC_SACK_SIZE]) { + call->ackr_sack_table[seq % RXRPC_SACK_SIZE] = 1; + keep = 1; + } + + if (after(seq + 1, wtop)) { + wtop = seq + 1; + rxrpc_input_update_ack_window(call, window, wtop); + } + + if (!keep) { + ack_reason = RXRPC_ACK_DUPLICATE; + goto send_ack; + } + + skb_queue_walk(&call->rx_oos_queue, oos) { + struct rxrpc_skb_priv *osp = rxrpc_skb(oos); - if (after_eq(seq, call->rx_expect_next)) { - if (after(seq, call->rx_expect_next)) { - _net("OOS %u > %u", seq, call->rx_expect_next); - rxrpc_send_ACK(call, RXRPC_ACK_OUT_OF_SEQUENCE, serial, - rxrpc_propose_ack_input_data); - acked = true; + if (after(osp->hdr.seq, seq)) { + __skb_queue_before(&call->rx_oos_queue, oos, skb); + goto oos_queued; + } } - call->rx_expect_next = seq + 1; + + __skb_queue_tail(&call->rx_oos_queue, skb); + oos_queued: + trace_rxrpc_receive(call, last ? rxrpc_receive_oos_last : rxrpc_receive_oos, + sp->hdr.serial, sp->hdr.seq); + skb = NULL; } -out: - if (!acked && - atomic_inc_return(&call->ackr_nr_unacked) > 2) - rxrpc_send_ACK(call, RXRPC_ACK_IDLE, serial, +send_ack: + if (ack_reason < 0 && + atomic_inc_return(&call->ackr_nr_unacked) > 2 && + test_and_set_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags)) { + ack_reason = RXRPC_ACK_IDLE; + } else if (ack_reason >= 0) { + set_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags); + } + + if (ack_reason >= 0) + rxrpc_send_ACK(call, ack_reason, serial, rxrpc_propose_ack_input_data); else rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_input_data); - trace_rxrpc_notify_socket(call->debug_id, serial); - rxrpc_notify_socket(call); - +err_free: rxrpc_free_skb(skb, rxrpc_skb_freed); - _leave(" [queued]"); } /* @@ -498,8 +546,9 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_serial_t serial = sp->hdr.serial; rxrpc_seq_t seq0 = sp->hdr.seq; - _enter("{%u,%u},{%u,%u}", - call->rx_hard_ack, call->rx_top, skb->len, seq0); + _enter("{%llx,%x},{%u,%x}", + atomic64_read(&call->ackr_window), call->rx_highest_seq, + skb->len, seq0); _proto("Rx DATA %%%u { #%u f=%02x }", sp->hdr.serial, seq0, sp->hdr.flags); diff --git a/net/rxrpc/misc.c b/net/rxrpc/misc.c index f5f03f27bd6c..056c428d8bf3 100644 --- a/net/rxrpc/misc.c +++ b/net/rxrpc/misc.c @@ -40,10 +40,7 @@ unsigned long rxrpc_idle_ack_delay = HZ / 2; * limit is hit, we should generate an EXCEEDS_WINDOW ACK and discard further * packets. */ -unsigned int rxrpc_rx_window_size = RXRPC_INIT_RX_WINDOW_SIZE; -#if (RXRPC_RXTX_BUFF_SIZE - 1) < RXRPC_INIT_RX_WINDOW_SIZE -#error Need to reduce RXRPC_INIT_RX_WINDOW_SIZE -#endif +unsigned int rxrpc_rx_window_size = 255; /* * Maximum Rx MTU size. This indicates to the sender the size of jumbo packet diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index f7bb792c8aa1..0a4f37d7b6b5 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -74,47 +74,64 @@ static void rxrpc_set_keepalive(struct rxrpc_call *call) */ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, struct rxrpc_call *call, - struct rxrpc_txbuf *txb, - rxrpc_seq_t *_hard_ack, - rxrpc_seq_t *_top) + struct rxrpc_txbuf *txb) { struct rxrpc_ackinfo ackinfo; - unsigned int tmp; - rxrpc_seq_t hard_ack, top, seq; - int ix; + unsigned int qsize; + rxrpc_seq_t window, wtop, wrap_point, ix, first; + int rsize; + u64 wtmp; u32 mtu, jmax; u8 *ackp = txb->acks; + u8 sack_buffer[sizeof(call->ackr_sack_table)] __aligned(8); - tmp = atomic_xchg(&call->ackr_nr_unacked, 0); - tmp |= atomic_xchg(&call->ackr_nr_consumed, 0); - if (!tmp && (txb->ack.reason == RXRPC_ACK_DELAY || - txb->ack.reason == RXRPC_ACK_IDLE)) { - rxrpc_inc_stat(call->rxnet, stat_tx_ack_skip); - return 0; - } - + atomic_set(&call->ackr_nr_unacked, 0); + atomic_set(&call->ackr_nr_consumed, 0); rxrpc_inc_stat(call->rxnet, stat_tx_ack_fill); /* Barrier against rxrpc_input_data(). */ - hard_ack = READ_ONCE(call->rx_hard_ack); - top = smp_load_acquire(&call->rx_top); - *_hard_ack = hard_ack; - *_top = top; - - txb->ack.firstPacket = htonl(hard_ack + 1); - txb->ack.previousPacket = htonl(call->ackr_highest_seq); - txb->ack.nAcks = top - hard_ack; - - if (txb->ack.nAcks) { - seq = hard_ack + 1; - do { - ix = seq & RXRPC_RXTX_BUFF_MASK; - if (call->rxtx_buffer[ix]) - *ackp++ = RXRPC_ACK_TYPE_ACK; - else - *ackp++ = RXRPC_ACK_TYPE_NACK; - seq++; - } while (before_eq(seq, top)); +retry: + wtmp = atomic64_read_acquire(&call->ackr_window); + window = lower_32_bits(wtmp); + wtop = upper_32_bits(wtmp); + txb->ack.firstPacket = htonl(window); + txb->ack.nAcks = 0; + + if (after(wtop, window)) { + /* Try to copy the SACK ring locklessly. We can use the copy, + * only if the now-current top of the window didn't go past the + * previously read base - otherwise we can't know whether we + * have old data or new data. + */ + memcpy(sack_buffer, call->ackr_sack_table, sizeof(sack_buffer)); + wrap_point = window + RXRPC_SACK_SIZE - 1; + wtmp = atomic64_read_acquire(&call->ackr_window); + window = lower_32_bits(wtmp); + wtop = upper_32_bits(wtmp); + if (after(wtop, wrap_point)) { + cond_resched(); + goto retry; + } + + /* The buffer is maintained as a ring with an invariant mapping + * between bit position and sequence number, so we'll probably + * need to rotate it. + */ + txb->ack.nAcks = wtop - window; + ix = window % RXRPC_SACK_SIZE; + first = sizeof(sack_buffer) - ix; + + if (ix + txb->ack.nAcks <= RXRPC_SACK_SIZE) { + memcpy(txb->acks, sack_buffer + ix, txb->ack.nAcks); + } else { + memcpy(txb->acks, sack_buffer + ix, first); + memcpy(txb->acks + first, sack_buffer, + txb->ack.nAcks - first); + } + + ackp += txb->ack.nAcks; + } else if (before(wtop, window)) { + pr_warn("ack window backward %x %x", window, wtop); } else if (txb->ack.reason == RXRPC_ACK_DELAY) { txb->ack.reason = RXRPC_ACK_IDLE; } @@ -122,16 +139,18 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, mtu = conn->params.peer->if_mtu; mtu -= conn->params.peer->hdrsize; jmax = rxrpc_rx_jumbo_max; + qsize = (window - 1) - call->rx_consumed; + rsize = max_t(int, call->rx_winsize - qsize, 0); ackinfo.rxMTU = htonl(rxrpc_rx_mtu); ackinfo.maxMTU = htonl(mtu); - ackinfo.rwind = htonl(call->rx_winsize); + ackinfo.rwind = htonl(rsize); ackinfo.jumbo_max = htonl(jmax); *ackp++ = 0; *ackp++ = 0; *ackp++ = 0; memcpy(ackp, &ackinfo, sizeof(ackinfo)); - return top - hard_ack + 3 + sizeof(ackinfo); + return txb->ack.nAcks + 3 + sizeof(ackinfo); } /* @@ -188,7 +207,6 @@ static int rxrpc_send_ack_packet(struct rxrpc_local *local, struct rxrpc_txbuf * struct msghdr msg; struct kvec iov[1]; rxrpc_serial_t serial; - rxrpc_seq_t hard_ack, top; size_t len, n; int ret, rtt_slot = -1; @@ -212,7 +230,7 @@ static int rxrpc_send_ack_packet(struct rxrpc_local *local, struct rxrpc_txbuf * clear_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags); spin_lock_bh(&call->lock); - n = rxrpc_fill_out_ack(conn, call, txb, &hard_ack, &top); + n = rxrpc_fill_out_ack(conn, call, txb); spin_unlock_bh(&call->lock); if (n == 0) { kfree(pkt); @@ -236,6 +254,9 @@ static int rxrpc_send_ack_packet(struct rxrpc_local *local, struct rxrpc_txbuf * rxrpc_inc_stat(call->rxnet, stat_tx_ack_send); + /* Grab the highest received seq as late as possible */ + txb->ack.previousPacket = htonl(call->rx_highest_seq); + iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, len); ret = do_udp_sendmsg(conn->params.local->socket, &msg, len); call->peer->last_tx_at = ktime_get_seconds(); diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index 3877afd23598..d48af0178866 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -54,8 +54,9 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) struct rxrpc_call *call; struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); unsigned long timeout = 0; - rxrpc_seq_t tx_hard_ack, rx_hard_ack; + rxrpc_seq_t tx_hard_ack; char lbuff[50], rbuff[50]; + u64 wtmp; if (v == &rxnet->calls) { seq_puts(seq, @@ -91,7 +92,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) } tx_hard_ack = READ_ONCE(call->tx_hard_ack); - rx_hard_ack = READ_ONCE(call->rx_hard_ack); + wtmp = atomic64_read_acquire(&call->ackr_window); seq_printf(seq, "UDP %-47.47s %-47.47s %4x %08x %08x %s %3u" " %-8.8s %08x %08x %08x %02x %08x %02x %08x %06lx\n", @@ -106,7 +107,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) call->abort_code, call->debug_id, tx_hard_ack, READ_ONCE(call->tx_top) - tx_hard_ack, - rx_hard_ack, READ_ONCE(call->rx_top) - rx_hard_ack, + lower_32_bits(wtmp), upper_32_bits(wtmp) - lower_32_bits(wtmp), call->rx_serial, timeout); diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 401aae687830..efb85f983657 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -173,7 +173,8 @@ static int rxrpc_recvmsg_term(struct rxrpc_call *call, struct msghdr *msg) break; } - trace_rxrpc_recvdata(call, rxrpc_recvmsg_terminal, call->rx_hard_ack, + trace_rxrpc_recvdata(call, rxrpc_recvmsg_terminal, + lower_32_bits(atomic64_read(&call->ackr_window)) - 1, call->rx_pkt_offset, call->rx_pkt_len, ret); return ret; } @@ -183,10 +184,11 @@ static int rxrpc_recvmsg_term(struct rxrpc_call *call, struct msghdr *msg) */ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) { + rxrpc_seq_t whigh = READ_ONCE(call->rx_highest_seq); + _enter("%d,%s", call->debug_id, rxrpc_call_states[call->state]); - trace_rxrpc_receive(call, rxrpc_receive_end, 0, call->rx_top); - ASSERTCMP(call->rx_hard_ack, ==, call->rx_top); + trace_rxrpc_receive(call, rxrpc_receive_end, 0, whigh); if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY) rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_terminal_ack); @@ -220,45 +222,53 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) struct rxrpc_skb_priv *sp; struct sk_buff *skb; rxrpc_serial_t serial; - rxrpc_seq_t hard_ack, top; - bool last = false; - int ix; + rxrpc_seq_t old_consumed = call->rx_consumed, tseq; + bool last; + int acked; _enter("%d", call->debug_id); - hard_ack = call->rx_hard_ack; - top = smp_load_acquire(&call->rx_top); - ASSERT(before(hard_ack, top)); - - hard_ack++; - ix = hard_ack & RXRPC_RXTX_BUFF_MASK; - skb = call->rxtx_buffer[ix]; +further_rotation: + skb = skb_dequeue(&call->recvmsg_queue); rxrpc_see_skb(skb, rxrpc_skb_rotated); - sp = rxrpc_skb(skb); + sp = rxrpc_skb(skb); + tseq = sp->hdr.seq; serial = sp->hdr.serial; + last = sp->hdr.flags & RXRPC_LAST_PACKET; - if (sp->hdr.flags & RXRPC_LAST_PACKET) - last = true; - - call->rxtx_buffer[ix] = NULL; - call->rxtx_annotations[ix] = 0; /* Barrier against rxrpc_input_data(). */ - smp_store_release(&call->rx_hard_ack, hard_ack); + if (after(tseq, call->rx_consumed)) + smp_store_release(&call->rx_consumed, tseq); rxrpc_free_skb(skb, rxrpc_skb_freed); - trace_rxrpc_receive(call, rxrpc_receive_rotate, serial, hard_ack); + trace_rxrpc_receive(call, last ? rxrpc_receive_rotate_last : rxrpc_receive_rotate, + serial, call->rx_consumed); if (last) { rxrpc_end_rx_phase(call, serial); - } else { - /* Check to see if there's an ACK that needs sending. */ - if (atomic_inc_return(&call->ackr_nr_consumed) > 2 && - !test_and_set_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags)) { - rxrpc_send_ACK(call, RXRPC_ACK_IDLE, serial, - rxrpc_propose_ack_rotate_rx); - rxrpc_transmit_ack_packets(call->peer->local); - } + return; + } + + /* The next packet on the queue might entirely overlap with the one we + * just consumed; if so, rotate that away also. + */ + skb = skb_peek(&call->recvmsg_queue); + if (skb) { + sp = rxrpc_skb(skb); + if (sp->hdr.seq != call->rx_consumed && + after_eq(call->rx_consumed, sp->hdr.seq)) + goto further_rotation; + } + + /* Check to see if there's an ACK that needs sending. */ + acked = atomic_add_return(call->rx_consumed - old_consumed, + &call->ackr_nr_consumed); + if (acked > 2 && + !test_and_set_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags)) { + rxrpc_send_ACK(call, RXRPC_ACK_IDLE, serial, + rxrpc_propose_ack_rotate_rx); + rxrpc_transmit_ack_packets(call->peer->local); } } @@ -285,46 +295,38 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, { struct rxrpc_skb_priv *sp; struct sk_buff *skb; - rxrpc_serial_t serial; - rxrpc_seq_t hard_ack, top, seq; + rxrpc_seq_t seq = 0; size_t remain; unsigned int rx_pkt_offset, rx_pkt_len; - int ix, copy, ret = -EAGAIN, ret2; + int copy, ret = -EAGAIN, ret2; rx_pkt_offset = call->rx_pkt_offset; rx_pkt_len = call->rx_pkt_len; if (call->state >= RXRPC_CALL_SERVER_ACK_REQUEST) { - seq = call->rx_hard_ack; + seq = lower_32_bits(atomic64_read(&call->ackr_window)) - 1; ret = 1; goto done; } - /* Barriers against rxrpc_input_data(). */ - hard_ack = call->rx_hard_ack; - seq = hard_ack + 1; - - while (top = smp_load_acquire(&call->rx_top), - before_eq(seq, top) - ) { - ix = seq & RXRPC_RXTX_BUFF_MASK; - skb = call->rxtx_buffer[ix]; - if (!skb) { - trace_rxrpc_recvdata(call, rxrpc_recvmsg_hole, seq, - rx_pkt_offset, rx_pkt_len, 0); - rxrpc_transmit_ack_packets(call->peer->local); - break; - } - smp_rmb(); + /* No one else can be removing stuff from the queue, so we shouldn't + * need the Rx lock to walk it. + */ + skb = skb_peek(&call->recvmsg_queue); + while (skb) { rxrpc_see_skb(skb, rxrpc_skb_seen); sp = rxrpc_skb(skb); + seq = sp->hdr.seq; - if (!(flags & MSG_PEEK)) { - serial = sp->hdr.serial; - trace_rxrpc_receive(call, rxrpc_receive_front, - serial, seq); + if (after_eq(call->rx_consumed, seq)) { + kdebug("obsolete %x %x", call->rx_consumed, seq); + goto skip_obsolete; } + if (!(flags & MSG_PEEK)) + trace_rxrpc_receive(call, rxrpc_receive_front, + sp->hdr.serial, seq); + if (msg) sock_recv_timestamp(msg, sock->sk, skb); @@ -338,6 +340,7 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, ret = ret2; goto out; } + rxrpc_transmit_ack_packets(call->peer->local); } else { trace_rxrpc_recvdata(call, rxrpc_recvmsg_cont, seq, rx_pkt_offset, rx_pkt_len, 0); @@ -370,16 +373,17 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, break; } + skip_obsolete: /* The whole packet has been transferred. */ if (sp->hdr.flags & RXRPC_LAST_PACKET) ret = 1; rx_pkt_offset = 0; rx_pkt_len = 0; + skb = skb_peek_next(skb, &call->recvmsg_queue); + if (!(flags & MSG_PEEK)) rxrpc_rotate_rx_window(call); - - seq++; } out: @@ -522,8 +526,7 @@ try_again: ret = 0; rxrpc_transmit_ack_packets(call->peer->local); - if (after(call->rx_top, call->rx_hard_ack) && - call->rxtx_buffer[(call->rx_hard_ack + 1) & RXRPC_RXTX_BUFF_MASK]) + if (!skb_queue_empty(&call->recvmsg_queue)) rxrpc_notify_socket(call); break; default: diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index b19937776aa9..d87c99b36e01 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -1191,7 +1191,6 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, abort_code = RXKADPACKETSHORT; if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header) + sizeof(*response), ticket, ticket_len) < 0) - goto protocol_error_free; ret = rxkad_decrypt_ticket(conn, server_key, skb, ticket, ticket_len, &session_key, &expiry, _abort_code); diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c index 2bd987364e44..cde3224a5cd2 100644 --- a/net/rxrpc/sysctl.c +++ b/net/rxrpc/sysctl.c @@ -14,7 +14,7 @@ static struct ctl_table_header *rxrpc_sysctl_reg_table; static const unsigned int four = 4; static const unsigned int max_backlog = RXRPC_BACKLOG_MAX - 1; static const unsigned int n_65535 = 65535; -static const unsigned int n_max_acks = RXRPC_RXTX_BUFF_SIZE - 1; +static const unsigned int n_max_acks = 255; static const unsigned long one_jiffy = 1; static const unsigned long max_jiffies = MAX_JIFFY_OFFSET; -- cgit v1.2.3 From a4ea4c47761943d90cd5d1688b3c3c65922ff2b1 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 31 Mar 2022 23:55:08 +0100 Subject: rxrpc: Don't use a ring buffer for call Tx queue Change the way the Tx queueing works to make the following ends easier to achieve: (1) The filling of packets, the encryption of packets and the transmission of packets can be handled in parallel by separate threads, rather than rxrpc_sendmsg() allocating, filling, encrypting and transmitting each packet before moving onto the next one. (2) Get rid of the fixed-size ring which sets a hard limit on the number of packets that can be retained in the ring. This allows the number of packets to increase without having to allocate a very large ring or having variable-sized rings. [Note: the downside of this is that it's then less efficient to locate a packet for retransmission as we then have to step through a list and examine each buffer in the list.] (3) Allow the filler/encrypter to run ahead of the transmission window. (4) Make it easier to do zero copy UDP from the packet buffers. (5) Make it easier to do zero copy from userspace to the packet buffers - and thence to UDP (only if for unauthenticated connections). To that end, the following changes are made: (1) Use the new rxrpc_txbuf struct instead of sk_buff for keeping packets to be transmitted in. This allows them to be placed on multiple queues simultaneously. An sk_buff isn't really necessary as it's never passed on to lower-level networking code. (2) Keep the transmissable packets in a linked list on the call struct rather than in a ring. As a consequence, the annotation buffer isn't used either; rather a flag is set on the packet to indicate ackedness. (3) Use the RXRPC_CALL_TX_LAST flag to indicate that the last packet to be transmitted has been queued. Add RXRPC_CALL_TX_ALL_ACKED to indicate that all packets up to and including the last got hard acked. (4) Wire headers are now stored in the txbuf rather than being concocted on the stack and they're stored immediately before the data, thereby allowing zerocopy of a single span. (5) Don't bother with instant-resend on transmission failure; rather, leave it for a timer or an ACK packet to trigger. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 78 +++++++++--------- net/rxrpc/af_rxrpc.c | 5 +- net/rxrpc/ar-internal.h | 31 +++---- net/rxrpc/call_event.c | 111 +++++++++---------------- net/rxrpc/call_object.c | 15 +++- net/rxrpc/input.c | 145 ++++++++++++++------------------- net/rxrpc/insecure.c | 3 +- net/rxrpc/output.c | 89 +++++++++----------- net/rxrpc/proc.c | 9 +-- net/rxrpc/rxkad.c | 102 +++++++++-------------- net/rxrpc/sendmsg.c | 188 +++++++++++++++++-------------------------- net/rxrpc/txbuf.c | 34 ++++++++ 12 files changed, 349 insertions(+), 461 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 284a1560b0a8..71ca74e40ec8 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -75,6 +75,7 @@ EM(rxrpc_call_got, "GOT") \ EM(rxrpc_call_got_kernel, "Gke") \ EM(rxrpc_call_got_timer, "GTM") \ + EM(rxrpc_call_got_tx, "Gtx") \ EM(rxrpc_call_got_userid, "Gus") \ EM(rxrpc_call_new_client, "NWc") \ EM(rxrpc_call_new_service, "NWs") \ @@ -83,20 +84,22 @@ EM(rxrpc_call_put_noqueue, "PnQ") \ EM(rxrpc_call_put_notimer, "PnT") \ EM(rxrpc_call_put_timer, "PTM") \ + EM(rxrpc_call_put_tx, "Ptx") \ EM(rxrpc_call_put_userid, "Pus") \ EM(rxrpc_call_queued, "QUE") \ EM(rxrpc_call_queued_ref, "QUR") \ EM(rxrpc_call_release, "RLS") \ E_(rxrpc_call_seen, "SEE") -#define rxrpc_transmit_traces \ - EM(rxrpc_transmit_await_reply, "AWR") \ - EM(rxrpc_transmit_end, "END") \ - EM(rxrpc_transmit_queue, "QUE") \ - EM(rxrpc_transmit_queue_last, "QLS") \ - EM(rxrpc_transmit_rotate, "ROT") \ - EM(rxrpc_transmit_rotate_last, "RLS") \ - E_(rxrpc_transmit_wait, "WAI") +#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") \ + EM(rxrpc_txqueue_rotate, "ROT") \ + EM(rxrpc_txqueue_rotate_last, "RLS") \ + E_(rxrpc_txqueue_wait, "WAI") #define rxrpc_receive_traces \ EM(rxrpc_receive_end, "END") \ @@ -259,6 +262,7 @@ 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 ") \ @@ -266,6 +270,7 @@ 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_send_more, "SEE SEND+ ") \ E_(rxrpc_txbuf_see_unacked, "SEE UNACKED") @@ -295,9 +300,9 @@ enum rxrpc_rtt_rx_trace { rxrpc_rtt_rx_traces } __mode(byte); enum rxrpc_rtt_tx_trace { rxrpc_rtt_tx_traces } __mode(byte); enum rxrpc_skb_trace { rxrpc_skb_traces } __mode(byte); enum rxrpc_timer_trace { rxrpc_timer_traces } __mode(byte); -enum rxrpc_transmit_trace { rxrpc_transmit_traces } __mode(byte); enum rxrpc_tx_point { rxrpc_tx_points } __mode(byte); enum rxrpc_txbuf_trace { rxrpc_txbuf_traces } __mode(byte); +enum rxrpc_txqueue_trace { rxrpc_txqueue_traces } __mode(byte); #endif /* end __RXRPC_DECLARE_TRACE_ENUMS_ONCE_ONLY */ @@ -323,9 +328,9 @@ rxrpc_rtt_rx_traces; rxrpc_rtt_tx_traces; rxrpc_skb_traces; rxrpc_timer_traces; -rxrpc_transmit_traces; rxrpc_tx_points; rxrpc_txbuf_traces; +rxrpc_txqueue_traces; /* * Now redefine the EM() and E_() macros to map the enums to the strings that @@ -605,15 +610,16 @@ TRACE_EVENT(rxrpc_call_complete, __entry->abort_code) ); -TRACE_EVENT(rxrpc_transmit, - TP_PROTO(struct rxrpc_call *call, enum rxrpc_transmit_trace why), +TRACE_EVENT(rxrpc_txqueue, + TP_PROTO(struct rxrpc_call *call, enum rxrpc_txqueue_trace why), TP_ARGS(call, why), TP_STRUCT__entry( __field(unsigned int, call ) - __field(enum rxrpc_transmit_trace, why ) - __field(rxrpc_seq_t, tx_hard_ack ) + __field(enum rxrpc_txqueue_trace, why ) + __field(rxrpc_seq_t, acks_hard_ack ) + __field(rxrpc_seq_t, tx_bottom ) __field(rxrpc_seq_t, tx_top ) __field(int, tx_winsize ) ), @@ -621,16 +627,19 @@ TRACE_EVENT(rxrpc_transmit, TP_fast_assign( __entry->call = call->debug_id; __entry->why = why; - __entry->tx_hard_ack = call->tx_hard_ack; + __entry->acks_hard_ack = call->acks_hard_ack; + __entry->tx_bottom = call->tx_bottom; __entry->tx_top = call->tx_top; __entry->tx_winsize = call->tx_winsize; ), - TP_printk("c=%08x %s f=%08x n=%u/%u", + TP_printk("c=%08x %s f=%08x h=%08x n=%u/%u/%u", __entry->call, - __print_symbolic(__entry->why, rxrpc_transmit_traces), - __entry->tx_hard_ack + 1, - __entry->tx_top - __entry->tx_hard_ack, + __print_symbolic(__entry->why, rxrpc_txqueue_traces), + __entry->tx_bottom, + __entry->acks_hard_ack, + __entry->tx_top - __entry->tx_bottom, + __entry->tx_top - __entry->acks_hard_ack, __entry->tx_winsize) ); @@ -1200,29 +1209,25 @@ TRACE_EVENT(rxrpc_drop_ack, ); TRACE_EVENT(rxrpc_retransmit, - TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t seq, u8 annotation, - s64 expiry), + TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t seq, s64 expiry), - TP_ARGS(call, seq, annotation, expiry), + TP_ARGS(call, seq, expiry), TP_STRUCT__entry( __field(unsigned int, call ) __field(rxrpc_seq_t, seq ) - __field(u8, annotation ) __field(s64, expiry ) ), TP_fast_assign( __entry->call = call->debug_id; __entry->seq = seq; - __entry->annotation = annotation; __entry->expiry = expiry; ), - TP_printk("c=%08x q=%x a=%02x xp=%lld", + TP_printk("c=%08x q=%x xp=%lld", __entry->call, __entry->seq, - __entry->annotation, __entry->expiry) ); @@ -1245,14 +1250,14 @@ TRACE_EVENT(rxrpc_congest, TP_fast_assign( __entry->call = call->debug_id; __entry->change = change; - __entry->hard_ack = call->tx_hard_ack; + __entry->hard_ack = call->acks_hard_ack; __entry->top = call->tx_top; __entry->lowest_nak = call->acks_lowest_nak; __entry->ack_serial = ack_serial; memcpy(&__entry->sum, summary, sizeof(__entry->sum)); ), - TP_printk("c=%08x r=%08x %s q=%08x %s cw=%u ss=%u nr=%u,%u nw=%u,%u r=%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 nA=%u,%u+%u,%u r=%u b=%u u=%u d=%u l=%x%s%s%s", __entry->call, __entry->ack_serial, __print_symbolic(__entry->sum.ack_reason, rxrpc_ack_names), @@ -1362,26 +1367,23 @@ TRACE_EVENT(rxrpc_connect_call, ); TRACE_EVENT(rxrpc_resend, - TP_PROTO(struct rxrpc_call *call, int ix), + TP_PROTO(struct rxrpc_call *call), - TP_ARGS(call, ix), + TP_ARGS(call), TP_STRUCT__entry( __field(unsigned int, call ) - __field(int, ix ) - __array(u8, anno, 64 ) + __field(rxrpc_seq_t, seq ) ), TP_fast_assign( __entry->call = call->debug_id; - __entry->ix = ix; - memcpy(__entry->anno, call->rxtx_annotations, 64); + __entry->seq = call->acks_hard_ack; ), - TP_printk("c=%08x ix=%u a=%64phN", + TP_printk("c=%08x q=%x", __entry->call, - __entry->ix, - __entry->anno) + __entry->seq) ); TRACE_EVENT(rxrpc_rx_icmp, @@ -1461,7 +1463,7 @@ TRACE_EVENT(rxrpc_call_reset, __entry->call_id = call->call_id; __entry->call_serial = call->rx_serial; __entry->conn_serial = call->conn->hi_serial; - __entry->tx_seq = call->tx_hard_ack; + __entry->tx_seq = call->acks_hard_ack; __entry->rx_seq = call->rx_highest_seq; ), diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index ceba28e9dce6..2f3991cf8715 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -39,7 +39,7 @@ atomic_t rxrpc_debug_id; EXPORT_SYMBOL(rxrpc_debug_id); /* count of skbs currently in use */ -atomic_t rxrpc_n_tx_skbs, rxrpc_n_rx_skbs; +atomic_t rxrpc_n_rx_skbs; struct workqueue_struct *rxrpc_workqueue; @@ -979,7 +979,7 @@ static int __init af_rxrpc_init(void) goto error_call_jar; } - rxrpc_workqueue = alloc_workqueue("krxrpcd", 0, 1); + rxrpc_workqueue = alloc_workqueue("krxrpcd", WQ_HIGHPRI | WQ_MEM_RECLAIM | WQ_UNBOUND, 1); if (!rxrpc_workqueue) { pr_notice("Failed to allocate work queue\n"); goto error_work_queue; @@ -1059,7 +1059,6 @@ static void __exit af_rxrpc_exit(void) sock_unregister(PF_RXRPC); proto_unregister(&rxrpc_proto); unregister_pernet_device(&rxrpc_net_ops); - ASSERTCMP(atomic_read(&rxrpc_n_tx_skbs), ==, 0); ASSERTCMP(atomic_read(&rxrpc_n_rx_skbs), ==, 0); /* Make sure the local and peer records pinned by any dying connections diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index c6c5bb3d3688..d7aebe82e17c 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -195,7 +195,6 @@ struct rxrpc_host_header { * - max 48 bytes (struct sk_buff::cb) */ struct rxrpc_skb_priv { - u16 remain; u16 offset; /* Offset of data */ u16 len; /* Length of data */ u8 flags; @@ -243,7 +242,7 @@ struct rxrpc_security { size_t *, size_t *, size_t *); /* impose security on a packet */ - int (*secure_packet)(struct rxrpc_call *, struct sk_buff *, size_t); + int (*secure_packet)(struct rxrpc_call *, struct rxrpc_txbuf *); /* verify the security on a received packet */ int (*verify_packet)(struct rxrpc_call *, struct sk_buff *); @@ -497,6 +496,7 @@ enum rxrpc_call_flag { RXRPC_CALL_EXPOSED, /* The call was exposed to the world */ RXRPC_CALL_RX_LAST, /* Received the last packet (at rxtx_top) */ RXRPC_CALL_TX_LAST, /* Last packet in Tx buffer (at rxtx_top) */ + RXRPC_CALL_TX_ALL_ACKED, /* Last packet has been hard-acked */ RXRPC_CALL_SEND_PING, /* A ping will need to be sent */ RXRPC_CALL_RETRANS_TIMEOUT, /* Retransmission due to timeout occurred */ RXRPC_CALL_BEGAN_RX_TIMER, /* We began the expect_rx_by timer */ @@ -594,7 +594,7 @@ struct rxrpc_call { struct list_head recvmsg_link; /* Link in rx->recvmsg_q */ struct list_head sock_link; /* Link in rx->sock_calls */ struct rb_node sock_node; /* Node in rx->calls */ - struct sk_buff *tx_pending; /* Tx socket buffer being filled */ + struct rxrpc_txbuf *tx_pending; /* Tx buffer being filled */ wait_queue_head_t waitq; /* Wait queue for channel or Tx */ s64 tx_total_len; /* Total length left to be transmitted (or -1) */ __be32 crypto_buf[2]; /* Temporary packet crypto buffer */ @@ -632,22 +632,16 @@ struct rxrpc_call { #define RXRPC_INIT_RX_WINDOW_SIZE 63 struct sk_buff **rxtx_buffer; u8 *rxtx_annotations; -#define RXRPC_TX_ANNO_ACK 0 -#define RXRPC_TX_ANNO_UNACK 1 -#define RXRPC_TX_ANNO_NAK 2 -#define RXRPC_TX_ANNO_RETRANS 3 -#define RXRPC_TX_ANNO_MASK 0x03 -#define RXRPC_TX_ANNO_LAST 0x04 -#define RXRPC_TX_ANNO_RESENT 0x08 - - rxrpc_seq_t tx_hard_ack; /* Dead slot in buffer; the first transmitted but - * not hard-ACK'd packet follows this. - */ /* Transmitted data tracking. */ + spinlock_t tx_lock; /* Transmit queue lock */ + struct list_head tx_buffer; /* Buffer of transmissible packets */ + rxrpc_seq_t tx_bottom; /* First packet in buffer */ + rxrpc_seq_t tx_transmitted; /* Highest packet transmitted */ rxrpc_seq_t tx_top; /* Highest Tx slot allocated. */ u16 tx_backoff; /* Delay to insert due to Tx failure */ u8 tx_winsize; /* Maximum size of Tx window */ +#define RXRPC_TX_MAX_WINDOW 128 /* Received data tracking */ struct sk_buff_head recvmsg_queue; /* Queue of packets ready for recvmsg() */ @@ -657,6 +651,7 @@ struct rxrpc_call { rxrpc_seq_t rx_consumed; /* Highest packet consumed */ rxrpc_serial_t rx_serial; /* Highest serial received for this call */ u8 rx_winsize; /* Size of Rx window */ + spinlock_t input_lock; /* Lock for packet input to this call */ /* TCP-style slow-start congestion control [RFC5681]. Since the SMSS * is fixed, we keep these numbers in terms of segments (ie. DATA @@ -671,8 +666,6 @@ struct rxrpc_call { u8 cong_cumul_acks; /* Cumulative ACK count */ ktime_t cong_tstamp; /* Last time cwnd was changed */ - spinlock_t input_lock; /* Lock for packet input to this call */ - /* Receive-phase ACK management (ACKs we send). */ u8 ackr_reason; /* reason to ACK */ rxrpc_serial_t ackr_serial; /* serial of packet being ACK'd */ @@ -697,6 +690,7 @@ struct rxrpc_call { ktime_t acks_latest_ts; /* Timestamp of latest ACK received */ rxrpc_seq_t acks_first_seq; /* first sequence number received */ rxrpc_seq_t acks_prev_seq; /* Highest previousPacket received */ + rxrpc_seq_t acks_hard_ack; /* Latest hard-ack point */ rxrpc_seq_t acks_lowest_nak; /* Lowest NACK in the buffer (or ==tx_hard_ack) */ rxrpc_seq_t acks_lost_top; /* tx_top at the time lost-ack ping sent */ rxrpc_serial_t acks_lost_ping; /* Serial number of probe ACK */ @@ -809,7 +803,7 @@ static inline bool rxrpc_sending_to_client(const struct rxrpc_txbuf *txb) /* * af_rxrpc.c */ -extern atomic_t rxrpc_n_tx_skbs, rxrpc_n_rx_skbs; +extern atomic_t rxrpc_n_rx_skbs; extern struct workqueue_struct *rxrpc_workqueue; /* @@ -831,6 +825,7 @@ void rxrpc_propose_ping(struct rxrpc_call *call, u32 serial, void rxrpc_send_ACK(struct rxrpc_call *, u8, rxrpc_serial_t, enum rxrpc_propose_ack_trace); void rxrpc_propose_delay_ACK(struct rxrpc_call *, rxrpc_serial_t, enum rxrpc_propose_ack_trace); +void rxrpc_shrink_call_tx_buffer(struct rxrpc_call *); void rxrpc_process_call(struct work_struct *); void rxrpc_reduce_call_timer(struct rxrpc_call *call, @@ -1034,7 +1029,7 @@ static inline struct rxrpc_net *rxrpc_net(struct net *net) */ void rxrpc_transmit_ack_packets(struct rxrpc_local *); int rxrpc_send_abort_packet(struct rxrpc_call *); -int rxrpc_send_data_packet(struct rxrpc_call *, struct sk_buff *, bool); +int rxrpc_send_data_packet(struct rxrpc_call *, struct rxrpc_txbuf *); void rxrpc_reject_packets(struct rxrpc_local *); void rxrpc_send_keepalive(struct rxrpc_peer *); diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 36f60ac1d95d..3c37b280eb20 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -148,62 +148,52 @@ static void rxrpc_congestion_timeout(struct rxrpc_call *call) */ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) { - struct sk_buff *skb; + struct rxrpc_txbuf *txb; unsigned long resend_at; - rxrpc_seq_t cursor, seq, top; + rxrpc_seq_t transmitted = READ_ONCE(call->tx_transmitted); ktime_t now, max_age, oldest, ack_ts; - int ix; - u8 annotation, anno_type, retrans = 0, unacked = 0; + bool unacked = false; + LIST_HEAD(retrans_queue); - _enter("{%d,%d}", call->tx_hard_ack, call->tx_top); + _enter("{%d,%d}", call->acks_hard_ack, call->tx_top); now = ktime_get_real(); max_age = ktime_sub_us(now, jiffies_to_usecs(call->peer->rto_j)); - spin_lock_bh(&call->lock); - - cursor = call->tx_hard_ack; - top = call->tx_top; - ASSERT(before_eq(cursor, top)); - if (cursor == top) - goto out_unlock; + spin_lock(&call->tx_lock); /* Scan the packet list without dropping the lock and decide which of * the packets in the Tx buffer we're going to resend and what the new * resend timeout will be. */ - trace_rxrpc_resend(call, (cursor + 1) & RXRPC_RXTX_BUFF_MASK); + trace_rxrpc_resend(call); oldest = now; - for (seq = cursor + 1; before_eq(seq, top); seq++) { - ix = seq & RXRPC_RXTX_BUFF_MASK; - annotation = call->rxtx_annotations[ix]; - anno_type = annotation & RXRPC_TX_ANNO_MASK; - annotation &= ~RXRPC_TX_ANNO_MASK; - if (anno_type == RXRPC_TX_ANNO_ACK) + list_for_each_entry(txb, &call->tx_buffer, call_link) { + if (test_bit(RXRPC_TXBUF_ACKED, &txb->flags)) continue; + if (after(txb->seq, transmitted)) + break; - skb = call->rxtx_buffer[ix]; - rxrpc_see_skb(skb, rxrpc_skb_seen); + rxrpc_see_txbuf(txb, rxrpc_txbuf_see_unacked); - if (anno_type == RXRPC_TX_ANNO_UNACK) { - if (ktime_after(skb->tstamp, max_age)) { - if (ktime_before(skb->tstamp, oldest)) - oldest = skb->tstamp; + if (test_bit(RXRPC_TXBUF_RESENT, &txb->flags)) { + if (ktime_after(txb->last_sent, max_age)) { + if (ktime_before(txb->last_sent, oldest)) + oldest = txb->last_sent; continue; } - if (!(annotation & RXRPC_TX_ANNO_RESENT)) - unacked++; + unacked = true; } - /* Okay, we need to retransmit a packet. */ - call->rxtx_annotations[ix] = RXRPC_TX_ANNO_RETRANS | annotation; - retrans++; - trace_rxrpc_retransmit(call, seq, annotation | anno_type, - ktime_to_ns(ktime_sub(skb->tstamp, max_age))); + rxrpc_get_txbuf(txb, rxrpc_txbuf_get_retrans); + list_move_tail(&txb->tx_link, &retrans_queue); } + spin_unlock(&call->tx_lock); + resend_at = nsecs_to_jiffies(ktime_to_ns(ktime_sub(now, oldest))); - resend_at += jiffies + rxrpc_get_rto_backoff(call->peer, retrans); + resend_at += jiffies + rxrpc_get_rto_backoff(call->peer, + !list_empty(&retrans_queue)); WRITE_ONCE(call->resend_at, resend_at); if (unacked) @@ -213,7 +203,8 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) * that an ACK got lost somewhere. Send a ping to find out instead of * retransmitting data. */ - if (!retrans) { + if (list_empty(&retrans_queue)) { + spin_lock_bh(&call->lock); rxrpc_reduce_call_timer(call, resend_at, now_j, rxrpc_timer_set_for_resend); spin_unlock_bh(&call->lock); @@ -225,50 +216,19 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) goto out; } - /* Now go through the Tx window and perform the retransmissions. We - * have to drop the lock for each send. If an ACK comes in whilst the - * lock is dropped, it may clear some of the retransmission markers for - * packets that it soft-ACKs. - */ - for (seq = cursor + 1; before_eq(seq, top); seq++) { - ix = seq & RXRPC_RXTX_BUFF_MASK; - annotation = call->rxtx_annotations[ix]; - anno_type = annotation & RXRPC_TX_ANNO_MASK; - if (anno_type != RXRPC_TX_ANNO_RETRANS) - continue; - - /* We need to reset the retransmission state, but we need to do - * so before we drop the lock as a new ACK/NAK may come in and - * confuse things - */ - annotation &= ~RXRPC_TX_ANNO_MASK; - annotation |= RXRPC_TX_ANNO_UNACK | RXRPC_TX_ANNO_RESENT; - call->rxtx_annotations[ix] = annotation; - - skb = call->rxtx_buffer[ix]; - if (!skb) - continue; - - rxrpc_get_skb(skb, rxrpc_skb_got); - spin_unlock_bh(&call->lock); - + while ((txb = list_first_entry_or_null(&retrans_queue, + struct rxrpc_txbuf, tx_link))) { + list_del_init(&txb->tx_link); + set_bit(RXRPC_TXBUF_RESENT, &txb->flags); rxrpc_inc_stat(call->rxnet, stat_tx_data_retrans); - if (rxrpc_send_data_packet(call, skb, true) < 0) { - rxrpc_free_skb(skb, rxrpc_skb_freed); - return; - } + rxrpc_send_data_packet(call, txb); + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_trans); - if (rxrpc_is_client_call(call)) - rxrpc_expose_client_call(call); - - rxrpc_free_skb(skb, rxrpc_skb_freed); - spin_lock_bh(&call->lock); - if (after(call->tx_hard_ack, seq)) - seq = call->tx_hard_ack; + trace_rxrpc_retransmit(call, txb->seq, + ktime_to_ns(ktime_sub(txb->last_sent, + max_age))); } -out_unlock: - spin_unlock_bh(&call->lock); out: _leave(""); } @@ -301,6 +261,9 @@ recheck_state: goto recheck_state; } + if (READ_ONCE(call->acks_hard_ack) != call->tx_bottom) + rxrpc_shrink_call_tx_buffer(call); + if (call->state == RXRPC_CALL_COMPLETE) { rxrpc_delete_call_timer(call); goto out_put; diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 4d8601c6a32d..ed5f6f0e4286 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -155,11 +155,13 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, INIT_LIST_HEAD(&call->accept_link); INIT_LIST_HEAD(&call->recvmsg_link); INIT_LIST_HEAD(&call->sock_link); + INIT_LIST_HEAD(&call->tx_buffer); skb_queue_head_init(&call->recvmsg_queue); skb_queue_head_init(&call->rx_oos_queue); init_waitqueue_head(&call->waitq); spin_lock_init(&call->lock); spin_lock_init(&call->notify_lock); + spin_lock_init(&call->tx_lock); spin_lock_init(&call->input_lock); rwlock_init(&call->state_lock); refcount_set(&call->ref, 1); @@ -175,7 +177,7 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, call->tx_winsize = 16; call->cong_cwnd = 2; - call->cong_ssthresh = RXRPC_RXTX_BUFF_SIZE - 1; + call->cong_ssthresh = RXRPC_TX_MAX_WINDOW; call->rxnet = rxnet; call->rtt_avail = RXRPC_CALL_RTT_AVAIL_MASK; @@ -510,7 +512,7 @@ void rxrpc_get_call(struct rxrpc_call *call, enum rxrpc_call_trace op) } /* - * Clean up the RxTx skb ring. + * Clean up the Rx skb ring. */ static void rxrpc_cleanup_ring(struct rxrpc_call *call) { @@ -686,6 +688,8 @@ static void rxrpc_rcu_destroy_call(struct rcu_head *rcu) */ void rxrpc_cleanup_call(struct rxrpc_call *call) { + struct rxrpc_txbuf *txb; + _net("DESTROY CALL %d", call->debug_id); memset(&call->sock_node, 0xcd, sizeof(call->sock_node)); @@ -694,7 +698,12 @@ void rxrpc_cleanup_call(struct rxrpc_call *call) ASSERT(test_bit(RXRPC_CALL_RELEASED, &call->flags)); rxrpc_cleanup_ring(call); - rxrpc_free_skb(call->tx_pending, rxrpc_skb_cleaned); + while ((txb = list_first_entry_or_null(&call->tx_buffer, + struct rxrpc_txbuf, call_link))) { + list_del(&txb->call_link); + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_cleaned); + } + rxrpc_put_txbuf(call->tx_pending, rxrpc_txbuf_put_cleaned); call_rcu(&call->rcu, rxrpc_rcu_destroy_call); } diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 947e7196e2be..b1f7debd4f3e 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -32,7 +32,7 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, bool resend = false; summary->flight_size = - (call->tx_top - call->tx_hard_ack) - summary->nr_acks; + (call->tx_top - call->acks_hard_ack) - summary->nr_acks; if (test_and_clear_bit(RXRPC_CALL_RETRANS_TIMEOUT, &call->flags)) { summary->retrans_timeo = true; @@ -150,8 +150,8 @@ resume_normality: out: cumulative_acks = 0; out_no_clear_ca: - if (cwnd >= RXRPC_RXTX_BUFF_SIZE - 1) - cwnd = RXRPC_RXTX_BUFF_SIZE - 1; + if (cwnd >= RXRPC_TX_MAX_WINDOW) + cwnd = RXRPC_TX_MAX_WINDOW; call->cong_cwnd = cwnd; call->cong_cumul_acks = cumulative_acks; trace_rxrpc_congest(call, summary, acked_serial, change); @@ -169,9 +169,8 @@ send_extra_data: /* Send some previously unsent DATA if we have some to advance the ACK * state. */ - if (call->rxtx_annotations[call->tx_top & RXRPC_RXTX_BUFF_MASK] & - RXRPC_TX_ANNO_LAST || - summary->nr_acks != call->tx_top - call->tx_hard_ack) { + if (test_bit(RXRPC_CALL_TX_LAST, &call->flags) || + summary->nr_acks != call->tx_top - call->acks_hard_ack) { call->cong_extra++; wake_up(&call->waitq); } @@ -184,53 +183,40 @@ send_extra_data: static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, struct rxrpc_ack_summary *summary) { - struct sk_buff *skb, *list = NULL; + struct rxrpc_txbuf *txb; bool rot_last = false; - int ix; - u8 annotation; - if (call->acks_lowest_nak == call->tx_hard_ack) { - call->acks_lowest_nak = to; - } else if (before_eq(call->acks_lowest_nak, to)) { - summary->new_low_nack = true; - call->acks_lowest_nak = to; - } - - spin_lock(&call->lock); - - while (before(call->tx_hard_ack, to)) { - call->tx_hard_ack++; - ix = call->tx_hard_ack & RXRPC_RXTX_BUFF_MASK; - skb = call->rxtx_buffer[ix]; - annotation = call->rxtx_annotations[ix]; - rxrpc_see_skb(skb, rxrpc_skb_rotated); - call->rxtx_buffer[ix] = NULL; - call->rxtx_annotations[ix] = 0; - skb->next = list; - list = skb; - - if (annotation & RXRPC_TX_ANNO_LAST) { + list_for_each_entry_rcu(txb, &call->tx_buffer, call_link, false) { + if (before_eq(txb->seq, call->acks_hard_ack)) + continue; + if (!test_bit(RXRPC_TXBUF_ACKED, &txb->flags)) + summary->nr_rot_new_acks++; + if (test_bit(RXRPC_TXBUF_LAST, &txb->flags)) { set_bit(RXRPC_CALL_TX_LAST, &call->flags); rot_last = true; } - if ((annotation & RXRPC_TX_ANNO_MASK) != RXRPC_TX_ANNO_ACK) - summary->nr_rot_new_acks++; + if (txb->seq == to) + break; } - spin_unlock(&call->lock); + if (rot_last) + set_bit(RXRPC_CALL_TX_ALL_ACKED, &call->flags); - trace_rxrpc_transmit(call, (rot_last ? - rxrpc_transmit_rotate_last : - rxrpc_transmit_rotate)); - wake_up(&call->waitq); + _enter("%x,%x,%x,%d", to, call->acks_hard_ack, call->tx_top, rot_last); - while (list) { - skb = list; - list = skb->next; - skb_mark_not_on_list(skb); - rxrpc_free_skb(skb, rxrpc_skb_freed); + if (call->acks_lowest_nak == call->acks_hard_ack) { + call->acks_lowest_nak = to; + } else if (before_eq(call->acks_lowest_nak, to)) { + summary->new_low_nack = true; + call->acks_lowest_nak = to; } + smp_store_release(&call->acks_hard_ack, to); + + trace_rxrpc_txqueue(call, (rot_last ? + rxrpc_txqueue_rotate_last : + rxrpc_txqueue_rotate)); + wake_up(&call->waitq); return rot_last; } @@ -270,9 +256,9 @@ static bool rxrpc_end_tx_phase(struct rxrpc_call *call, bool reply_begun, write_unlock(&call->state_lock); if (state == RXRPC_CALL_CLIENT_AWAIT_REPLY) - trace_rxrpc_transmit(call, rxrpc_transmit_await_reply); + trace_rxrpc_txqueue(call, rxrpc_txqueue_await_reply); else - trace_rxrpc_transmit(call, rxrpc_transmit_end); + trace_rxrpc_txqueue(call, rxrpc_txqueue_end); _leave(" = ok"); return true; @@ -678,30 +664,21 @@ static void rxrpc_complete_rtt_probe(struct rxrpc_call *call, */ static void rxrpc_input_check_for_lost_ack(struct rxrpc_call *call) { - rxrpc_seq_t top, bottom, seq; + struct rxrpc_txbuf *txb; + rxrpc_seq_t top, bottom; bool resend = false; - spin_lock_bh(&call->lock); - - bottom = call->tx_hard_ack + 1; - top = call->acks_lost_top; + bottom = READ_ONCE(call->acks_hard_ack) + 1; + top = READ_ONCE(call->acks_lost_top); if (before(bottom, top)) { - for (seq = bottom; before_eq(seq, top); seq++) { - int ix = seq & RXRPC_RXTX_BUFF_MASK; - u8 annotation = call->rxtx_annotations[ix]; - u8 anno_type = annotation & RXRPC_TX_ANNO_MASK; - - if (anno_type != RXRPC_TX_ANNO_UNACK) + list_for_each_entry_rcu(txb, &call->tx_buffer, call_link, false) { + if (test_bit(RXRPC_TXBUF_ACKED, &txb->flags)) continue; - annotation &= ~RXRPC_TX_ANNO_MASK; - annotation |= RXRPC_TX_ANNO_RETRANS; - call->rxtx_annotations[ix] = annotation; + set_bit(RXRPC_TXBUF_RETRANS, &txb->flags); resend = true; } } - spin_unlock_bh(&call->lock); - if (resend && !test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events)) rxrpc_queue_call(call); } @@ -735,8 +712,8 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU), rwind, ntohl(ackinfo->jumbo_max)); - if (rwind > RXRPC_RXTX_BUFF_SIZE - 1) - rwind = RXRPC_RXTX_BUFF_SIZE - 1; + if (rwind > RXRPC_TX_MAX_WINDOW) + rwind = RXRPC_TX_MAX_WINDOW; if (call->tx_winsize != rwind) { if (rwind > call->tx_winsize) wake = true; @@ -775,22 +752,24 @@ static void rxrpc_input_soft_acks(struct rxrpc_call *call, u8 *acks, rxrpc_seq_t seq, int nr_acks, struct rxrpc_ack_summary *summary) { - int ix; - u8 annotation, anno_type; - - for (; nr_acks > 0; nr_acks--, seq++) { - ix = seq & RXRPC_RXTX_BUFF_MASK; - annotation = call->rxtx_annotations[ix]; - anno_type = annotation & RXRPC_TX_ANNO_MASK; - annotation &= ~RXRPC_TX_ANNO_MASK; - switch (*acks++) { + struct rxrpc_txbuf *txb; + + list_for_each_entry_rcu(txb, &call->tx_buffer, call_link, false) { + if (before(txb->seq, seq)) + continue; + if (after_eq(txb->seq, seq + nr_acks)) + break; + switch (acks[txb->seq - seq]) { case RXRPC_ACK_TYPE_ACK: summary->nr_acks++; - if (anno_type == RXRPC_TX_ANNO_ACK) + if (test_bit(RXRPC_TXBUF_ACKED, &txb->flags)) continue; + /* A lot of the time the packet is going to + * have been ACK.'d already. + */ + clear_bit(RXRPC_TXBUF_NACKED, &txb->flags); + set_bit(RXRPC_TXBUF_ACKED, &txb->flags); summary->nr_new_acks++; - call->rxtx_annotations[ix] = - RXRPC_TX_ANNO_ACK | annotation; break; case RXRPC_ACK_TYPE_NACK: if (!summary->nr_nacks && @@ -799,13 +778,12 @@ static void rxrpc_input_soft_acks(struct rxrpc_call *call, u8 *acks, summary->new_low_nack = true; } summary->nr_nacks++; - if (anno_type == RXRPC_TX_ANNO_NAK) + if (test_bit(RXRPC_TXBUF_NACKED, &txb->flags)) continue; summary->nr_new_nacks++; - if (anno_type == RXRPC_TX_ANNO_RETRANS) - continue; - call->rxtx_annotations[ix] = - RXRPC_TX_ANNO_NAK | annotation; + clear_bit(RXRPC_TXBUF_ACKED, &txb->flags); + set_bit(RXRPC_TXBUF_NACKED, &txb->flags); + set_bit(RXRPC_TXBUF_RETRANS, &txb->flags); break; default: return rxrpc_proto_abort("SFT", call, 0); @@ -930,7 +908,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) if (unlikely(buf.ack.reason == RXRPC_ACK_OUT_OF_SEQUENCE) && first_soft_ack == 1 && prev_pkt == 0 && - call->tx_hard_ack == 0 && + call->acks_hard_ack == 0 && rxrpc_is_client_call(call)) { rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED, 0, -ENETRESET); @@ -989,7 +967,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) goto out; } - if (before(hard_ack, call->tx_hard_ack) || + if (before(hard_ack, call->acks_hard_ack) || after(hard_ack, call->tx_top)) { rxrpc_proto_abort("AKW", call, 0); goto out; @@ -999,7 +977,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) goto out; } - if (after(hard_ack, call->tx_hard_ack)) { + if (after(hard_ack, call->acks_hard_ack)) { if (rxrpc_rotate_tx_window(call, hard_ack, &summary)) { rxrpc_end_tx_phase(call, false, "ETA"); goto out; @@ -1015,8 +993,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) &summary); } - if (call->rxtx_annotations[call->tx_top & RXRPC_RXTX_BUFF_MASK] & - RXRPC_TX_ANNO_LAST && + if (test_bit(RXRPC_CALL_TX_LAST, &call->flags) && summary.nr_acks == call->tx_top - hard_ack && rxrpc_is_client_call(call)) rxrpc_propose_ping(call, ack_serial, diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c index fd68f0e3af27..0eb8471bfc53 100644 --- a/net/rxrpc/insecure.c +++ b/net/rxrpc/insecure.c @@ -25,8 +25,7 @@ static int none_how_much_data(struct rxrpc_call *call, size_t remain, return 0; } -static int none_secure_packet(struct rxrpc_call *call, struct sk_buff *skb, - size_t data_size) +static int none_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) { return 0; } diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 0a4f37d7b6b5..e2f501cef040 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -335,7 +335,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) * channel instead, thereby closing off this call. */ if (rxrpc_is_client_call(call) && - test_bit(RXRPC_CALL_TX_LAST, &call->flags)) + test_bit(RXRPC_CALL_TX_ALL_ACKED, &call->flags)) return 0; if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) @@ -383,20 +383,17 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) /* * send a packet through the transport endpoint */ -int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, - bool retrans) +int rxrpc_send_data_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) { enum rxrpc_req_ack_trace why; struct rxrpc_connection *conn = call->conn; - struct rxrpc_wire_header whdr; - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct msghdr msg; - struct kvec iov[2]; + struct kvec iov[1]; rxrpc_serial_t serial; size_t len; int ret, rtt_slot = -1; - _enter(",{%d}", skb->len); + _enter("%x,{%d}", txb->seq, txb->len); if (hlist_unhashed(&call->error_link)) { spin_lock_bh(&call->peer->lock); @@ -406,29 +403,16 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, /* Each transmission of a Tx packet needs a new serial number */ serial = atomic_inc_return(&conn->serial); - - whdr.epoch = htonl(conn->proto.epoch); - whdr.cid = htonl(call->cid); - whdr.callNumber = htonl(call->call_id); - whdr.seq = htonl(sp->hdr.seq); - whdr.serial = htonl(serial); - whdr.type = RXRPC_PACKET_TYPE_DATA; - whdr.flags = sp->hdr.flags; - whdr.userStatus = 0; - whdr.securityIndex = call->security_ix; - whdr._rsvd = htons(sp->hdr._rsvd); - whdr.serviceId = htons(call->service_id); + txb->wire.serial = htonl(serial); if (test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags) && - sp->hdr.seq == 1) - whdr.userStatus = RXRPC_USERSTATUS_SERVICE_UPGRADE; + txb->seq == 1) + txb->wire.userStatus = RXRPC_USERSTATUS_SERVICE_UPGRADE; - iov[0].iov_base = &whdr; - iov[0].iov_len = sizeof(whdr); - iov[1].iov_base = skb->head; - iov[1].iov_len = skb->len; - len = iov[0].iov_len + iov[1].iov_len; - iov_iter_kvec(&msg.msg_iter, WRITE, iov, 2, len); + iov[0].iov_base = &txb->wire; + iov[0].iov_len = sizeof(txb->wire) + txb->len; + len = iov[0].iov_len; + iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, len); msg.msg_name = &call->peer->srx.transport; msg.msg_namelen = call->peer->srx.transport_len; @@ -443,19 +427,19 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, * service call, lest OpenAFS incorrectly send us an ACK with some * soft-ACKs in it and then never follow up with a proper hard ACK. */ - if (whdr.flags & RXRPC_REQUEST_ACK) + if (txb->wire.flags & RXRPC_REQUEST_ACK) why = rxrpc_reqack_already_on; - else if ((whdr.flags & RXRPC_LAST_PACKET) && rxrpc_to_client(sp)) + else if (test_bit(RXRPC_TXBUF_LAST, &txb->flags) && rxrpc_sending_to_client(txb)) why = rxrpc_reqack_no_srv_last; else if (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events)) why = rxrpc_reqack_ack_lost; - else if (retrans) + else if (test_bit(RXRPC_TXBUF_RESENT, &txb->flags)) why = rxrpc_reqack_retrans; else if (call->cong_mode == RXRPC_CALL_SLOW_START && call->cong_cwnd <= 2) why = rxrpc_reqack_slow_start; else if (call->tx_winsize <= 2) why = rxrpc_reqack_small_txwin; - else if (call->peer->rtt_count < 3 && sp->hdr.seq & 1) + else if (call->peer->rtt_count < 3 && txb->seq & 1) why = rxrpc_reqack_more_rtt; else if (ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), ktime_get_real())) why = rxrpc_reqack_old_rtt; @@ -463,35 +447,36 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, goto dont_set_request_ack; rxrpc_inc_stat(call->rxnet, stat_why_req_ack[why]); - trace_rxrpc_req_ack(call->debug_id, sp->hdr.seq, why); + trace_rxrpc_req_ack(call->debug_id, txb->seq, why); if (why != rxrpc_reqack_no_srv_last) - whdr.flags |= RXRPC_REQUEST_ACK; + txb->wire.flags |= RXRPC_REQUEST_ACK; dont_set_request_ack: if (IS_ENABLED(CONFIG_AF_RXRPC_INJECT_LOSS)) { static int lose; if ((lose++ & 7) == 7) { ret = 0; - trace_rxrpc_tx_data(call, sp->hdr.seq, serial, - whdr.flags, retrans, true); + trace_rxrpc_tx_data(call, txb->seq, serial, + txb->wire.flags, + test_bit(RXRPC_TXBUF_RESENT, &txb->flags), + true); goto done; } } - trace_rxrpc_tx_data(call, sp->hdr.seq, serial, whdr.flags, retrans, - false); + trace_rxrpc_tx_data(call, txb->seq, serial, txb->wire.flags, + test_bit(RXRPC_TXBUF_RESENT, &txb->flags), false); + cmpxchg(&call->tx_transmitted, txb->seq - 1, txb->seq); /* send the packet with the don't fragment bit set if we currently * think it's small enough */ - if (iov[1].iov_len >= call->peer->maxdata) + if (txb->len >= call->peer->maxdata) goto send_fragmentable; down_read(&conn->params.local->defrag_sem); - sp->hdr.serial = serial; - smp_wmb(); /* Set serial before timestamp */ - skb->tstamp = ktime_get_real(); - if (whdr.flags & RXRPC_REQUEST_ACK) + txb->last_sent = ktime_get_real(); + if (txb->wire.flags & RXRPC_REQUEST_ACK) rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_data); /* send the packet by UDP @@ -510,7 +495,7 @@ dont_set_request_ack: trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_data_nofrag); } else { - trace_rxrpc_tx_packet(call->debug_id, &whdr, + trace_rxrpc_tx_packet(call->debug_id, &txb->wire, rxrpc_tx_point_call_data_nofrag); } @@ -520,8 +505,8 @@ dont_set_request_ack: done: if (ret >= 0) { - if (whdr.flags & RXRPC_REQUEST_ACK) { - call->peer->rtt_last_req = skb->tstamp; + if (txb->wire.flags & RXRPC_REQUEST_ACK) { + call->peer->rtt_last_req = txb->last_sent; if (call->peer->rtt_count > 1) { unsigned long nowj = jiffies, ack_lost_at; @@ -533,7 +518,7 @@ done: } } - if (sp->hdr.seq == 1 && + if (txb->seq == 1 && !test_and_set_bit(RXRPC_CALL_BEGAN_RX_TIMER, &call->flags)) { unsigned long nowj = jiffies, expect_rx_by; @@ -565,23 +550,21 @@ send_fragmentable: down_write(&conn->params.local->defrag_sem); - sp->hdr.serial = serial; - smp_wmb(); /* Set serial before timestamp */ - skb->tstamp = ktime_get_real(); - if (whdr.flags & RXRPC_REQUEST_ACK) + txb->last_sent = ktime_get_real(); + if (txb->wire.flags & RXRPC_REQUEST_ACK) rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_data); switch (conn->params.local->srx.transport.family) { case AF_INET6: case AF_INET: ip_sock_set_mtu_discover(conn->params.local->socket->sk, - IP_PMTUDISC_DONT); + IP_PMTUDISC_DONT); rxrpc_inc_stat(call->rxnet, stat_tx_data_send_frag); ret = do_udp_sendmsg(conn->params.local->socket, &msg, len); conn->params.peer->last_tx_at = ktime_get_seconds(); ip_sock_set_mtu_discover(conn->params.local->socket->sk, - IP_PMTUDISC_DO); + IP_PMTUDISC_DO); break; default: @@ -593,7 +576,7 @@ send_fragmentable: trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_data_frag); } else { - trace_rxrpc_tx_packet(call->debug_id, &whdr, + trace_rxrpc_tx_packet(call->debug_id, &txb->wire, rxrpc_tx_point_call_data_frag); } rxrpc_tx_backoff(call, ret); diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index d48af0178866..0807753ec2dc 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -54,7 +54,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) struct rxrpc_call *call; struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); unsigned long timeout = 0; - rxrpc_seq_t tx_hard_ack; + rxrpc_seq_t acks_hard_ack; char lbuff[50], rbuff[50]; u64 wtmp; @@ -91,7 +91,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) timeout -= jiffies; } - tx_hard_ack = READ_ONCE(call->tx_hard_ack); + acks_hard_ack = READ_ONCE(call->acks_hard_ack); wtmp = atomic64_read_acquire(&call->ackr_window); seq_printf(seq, "UDP %-47.47s %-47.47s %4x %08x %08x %s %3u" @@ -106,7 +106,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) rxrpc_call_states[call->state], call->abort_code, call->debug_id, - tx_hard_ack, READ_ONCE(call->tx_top) - tx_hard_ack, + acks_hard_ack, READ_ONCE(call->tx_top) - acks_hard_ack, lower_32_bits(wtmp), upper_32_bits(wtmp) - lower_32_bits(wtmp), call->rx_serial, timeout); @@ -459,9 +459,8 @@ int rxrpc_stats_show(struct seq_file *seq, void *v) atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_slow_start]), atomic_read(&rxnet->stat_why_req_ack[rxrpc_reqack_small_txwin])); seq_printf(seq, - "Buffers : txb=%u,%u rxb=%u\n", + "Buffers : txb=%u rxb=%u\n", atomic_read(&rxrpc_nr_txbuf), - atomic_read(&rxrpc_n_tx_skbs), atomic_read(&rxrpc_n_rx_skbs)); return 0; } diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index d87c99b36e01..8fc055587f0e 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -259,11 +259,10 @@ static void rxkad_free_call_crypto(struct rxrpc_call *call) * partially encrypt a packet (level 1 security) */ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, - struct sk_buff *skb, u32 data_size, + struct rxrpc_txbuf *txb, struct skcipher_request *req) { - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - struct rxkad_level1_hdr hdr; + struct rxkad_level1_hdr *hdr = (void *)txb->data; struct rxrpc_crypt iv; struct scatterlist sg; size_t pad; @@ -271,22 +270,22 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, _enter(""); - check = sp->hdr.seq ^ call->call_id; - data_size |= (u32)check << 16; - - hdr.data_size = htonl(data_size); - memcpy(skb->head, &hdr, sizeof(hdr)); + check = txb->seq ^ ntohl(txb->wire.callNumber); + hdr->data_size = htonl((u32)check << 16 | txb->len); - pad = sizeof(struct rxkad_level1_hdr) + data_size; + txb->len += sizeof(struct rxkad_level1_hdr); + pad = txb->len; pad = RXKAD_ALIGN - pad; pad &= RXKAD_ALIGN - 1; - if (pad) - skb_put_zero(skb, pad); + if (pad) { + memset(txb->data + txb->offset, 0, pad); + txb->len += pad; + } /* start the encryption afresh */ memset(&iv, 0, sizeof(iv)); - sg_init_one(&sg, skb->head, 8); + sg_init_one(&sg, txb->data, 8); skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher); skcipher_request_set_callback(req, 0, NULL, NULL); skcipher_request_set_crypt(req, &sg, &sg, 8, iv.x); @@ -301,87 +300,60 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call, * wholly encrypt a packet (level 2 security) */ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call, - struct sk_buff *skb, - u32 data_size, + struct rxrpc_txbuf *txb, struct skcipher_request *req) { const struct rxrpc_key_token *token; - struct rxkad_level2_hdr rxkhdr; - struct rxrpc_skb_priv *sp; + struct rxkad_level2_hdr *rxkhdr = (void *)txb->data; struct rxrpc_crypt iv; - struct scatterlist sg[16]; - unsigned int len; + struct scatterlist sg; size_t pad; u16 check; - int err; - - sp = rxrpc_skb(skb); + int ret; _enter(""); - check = sp->hdr.seq ^ call->call_id; + check = txb->seq ^ ntohl(txb->wire.callNumber); - rxkhdr.data_size = htonl(data_size | (u32)check << 16); - rxkhdr.checksum = 0; - memcpy(skb->head, &rxkhdr, sizeof(rxkhdr)); + rxkhdr->data_size = htonl(txb->len | (u32)check << 16); + rxkhdr->checksum = 0; - pad = sizeof(struct rxkad_level2_hdr) + data_size; + txb->len += sizeof(struct rxkad_level2_hdr); + pad = txb->len; pad = RXKAD_ALIGN - pad; pad &= RXKAD_ALIGN - 1; - if (pad) - skb_put_zero(skb, pad); + if (pad) { + memset(txb->data + txb->offset, 0, pad); + txb->len += pad; + } /* encrypt from the session key */ token = call->conn->params.key->payload.data[0]; memcpy(&iv, token->kad->session_key, sizeof(iv)); - sg_init_one(&sg[0], skb->head, sizeof(rxkhdr)); + sg_init_one(&sg, txb->data, txb->len); skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher); skcipher_request_set_callback(req, 0, NULL, NULL); - skcipher_request_set_crypt(req, &sg[0], &sg[0], sizeof(rxkhdr), iv.x); - crypto_skcipher_encrypt(req); - - /* we want to encrypt the skbuff in-place */ - err = -EMSGSIZE; - if (skb_shinfo(skb)->nr_frags > 16) - goto out; - - len = round_up(data_size, RXKAD_ALIGN); - - sg_init_table(sg, ARRAY_SIZE(sg)); - err = skb_to_sgvec(skb, sg, 8, len); - if (unlikely(err < 0)) - goto out; - skcipher_request_set_crypt(req, sg, sg, len, iv.x); - crypto_skcipher_encrypt(req); - - _leave(" = 0"); - err = 0; - -out: + skcipher_request_set_crypt(req, &sg, &sg, txb->len, iv.x); + ret = crypto_skcipher_encrypt(req); skcipher_request_zero(req); - return err; + return ret; } /* * checksum an RxRPC packet header */ -static int rxkad_secure_packet(struct rxrpc_call *call, - struct sk_buff *skb, - size_t data_size) +static int rxkad_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) { - struct rxrpc_skb_priv *sp; struct skcipher_request *req; struct rxrpc_crypt iv; struct scatterlist sg; u32 x, y; int ret; - sp = rxrpc_skb(skb); - - _enter("{%d{%x}},{#%u},%zu,", + _enter("{%d{%x}},{#%u},%u,", call->debug_id, key_serial(call->conn->params.key), - sp->hdr.seq, data_size); + txb->seq, txb->len); if (!call->conn->rxkad.cipher) return 0; @@ -398,9 +370,9 @@ static int rxkad_secure_packet(struct rxrpc_call *call, memcpy(&iv, call->conn->rxkad.csum_iv.x, sizeof(iv)); /* calculate the security checksum */ - x = (call->cid & RXRPC_CHANNELMASK) << (32 - RXRPC_CIDSHIFT); - x |= sp->hdr.seq & 0x3fffffff; - call->crypto_buf[0] = htonl(call->call_id); + x = (ntohl(txb->wire.cid) & RXRPC_CHANNELMASK) << (32 - RXRPC_CIDSHIFT); + x |= txb->seq & 0x3fffffff; + call->crypto_buf[0] = txb->wire.callNumber; call->crypto_buf[1] = htonl(x); sg_init_one(&sg, call->crypto_buf, 8); @@ -414,17 +386,17 @@ static int rxkad_secure_packet(struct rxrpc_call *call, y = (y >> 16) & 0xffff; if (y == 0) y = 1; /* zero checksums are not permitted */ - sp->hdr.cksum = y; + txb->wire.cksum = htons(y); switch (call->conn->params.security_level) { case RXRPC_SECURITY_PLAIN: ret = 0; break; case RXRPC_SECURITY_AUTH: - ret = rxkad_secure_packet_auth(call, skb, data_size, req); + ret = rxkad_secure_packet_auth(call, txb, req); break; case RXRPC_SECURITY_ENCRYPT: - ret = rxkad_secure_packet_encrypt(call, skb, data_size, req); + ret = rxkad_secure_packet_encrypt(call, txb, req); break; default: ret = -EPERM; diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index e32805a49324..a96ae7f58148 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -25,7 +25,7 @@ static bool rxrpc_check_tx_space(struct rxrpc_call *call, rxrpc_seq_t *_tx_win) unsigned int win_size = min_t(unsigned int, call->tx_winsize, call->cong_cwnd + call->cong_extra); - rxrpc_seq_t tx_win = READ_ONCE(call->tx_hard_ack); + rxrpc_seq_t tx_win = smp_load_acquire(&call->acks_hard_ack); if (_tx_win) *_tx_win = tx_win; @@ -50,7 +50,12 @@ static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx, if (signal_pending(current)) return sock_intr_errno(*timeo); - trace_rxrpc_transmit(call, rxrpc_transmit_wait); + if (READ_ONCE(call->acks_hard_ack) != call->tx_bottom) { + rxrpc_shrink_call_tx_buffer(call); + continue; + } + + trace_rxrpc_txqueue(call, rxrpc_txqueue_wait); *timeo = schedule_timeout(*timeo); } } @@ -71,12 +76,11 @@ static int rxrpc_wait_for_tx_window_waitall(struct rxrpc_sock *rx, rtt = 2; timeout = rtt; - tx_start = READ_ONCE(call->tx_hard_ack); + tx_start = smp_load_acquire(&call->acks_hard_ack); for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); - tx_win = READ_ONCE(call->tx_hard_ack); if (rxrpc_check_tx_space(call, &tx_win)) return 0; @@ -87,12 +91,17 @@ static int rxrpc_wait_for_tx_window_waitall(struct rxrpc_sock *rx, tx_win == tx_start && signal_pending(current)) return -EINTR; + if (READ_ONCE(call->acks_hard_ack) != call->tx_bottom) { + rxrpc_shrink_call_tx_buffer(call); + continue; + } + if (tx_win != tx_start) { timeout = rtt; tx_start = tx_win; } - trace_rxrpc_transmit(call, rxrpc_transmit_wait); + trace_rxrpc_txqueue(call, rxrpc_txqueue_wait); timeout = schedule_timeout(timeout); } } @@ -112,7 +121,12 @@ static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx, if (call->state >= RXRPC_CALL_COMPLETE) return call->error; - trace_rxrpc_transmit(call, rxrpc_transmit_wait); + if (READ_ONCE(call->acks_hard_ack) != call->tx_bottom) { + rxrpc_shrink_call_tx_buffer(call); + continue; + } + + trace_rxrpc_txqueue(call, rxrpc_txqueue_wait); *timeo = schedule_timeout(*timeo); } } @@ -129,8 +143,8 @@ static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx, DECLARE_WAITQUEUE(myself, current); int ret; - _enter(",{%u,%u,%u}", - call->tx_hard_ack, call->tx_top, call->tx_winsize); + _enter(",{%u,%u,%u,%u}", + call->tx_bottom, call->acks_hard_ack, call->tx_top, call->tx_winsize); add_wait_queue(&call->waitq, &myself); @@ -154,24 +168,6 @@ static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx, return ret; } -/* - * Schedule an instant Tx resend. - */ -static inline void rxrpc_instant_resend(struct rxrpc_call *call, int ix) -{ - spin_lock_bh(&call->lock); - - if (call->state < RXRPC_CALL_COMPLETE) { - call->rxtx_annotations[ix] = - (call->rxtx_annotations[ix] & RXRPC_TX_ANNO_LAST) | - RXRPC_TX_ANNO_RETRANS; - if (!test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events)) - rxrpc_queue_call(call); - } - - spin_unlock_bh(&call->lock); -} - /* * Notify the owner of the call that the transmit phase is ended and the last * packet has been queued. @@ -188,40 +184,35 @@ static void rxrpc_notify_end_tx(struct rxrpc_sock *rx, struct rxrpc_call *call, * the packet immediately. Returns the error from rxrpc_send_data_packet() * in case the caller wants to do something with it. */ -static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, - struct sk_buff *skb, bool last, - rxrpc_notify_end_tx_t notify_end_tx) +static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, + struct rxrpc_txbuf *txb, + rxrpc_notify_end_tx_t notify_end_tx) { - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); unsigned long now; - rxrpc_seq_t seq = sp->hdr.seq; - int ret, ix; - u8 annotation = RXRPC_TX_ANNO_UNACK; - - _net("queue skb %p [%d]", skb, seq); + rxrpc_seq_t seq = txb->seq; + bool last = test_bit(RXRPC_TXBUF_LAST, &txb->flags); + int ret; rxrpc_inc_stat(call->rxnet, stat_tx_data); ASSERTCMP(seq, ==, call->tx_top + 1); - if (last) - annotation |= RXRPC_TX_ANNO_LAST; - /* We have to set the timestamp before queueing as the retransmit * algorithm can see the packet as soon as we queue it. */ - skb->tstamp = ktime_get_real(); + txb->last_sent = ktime_get_real(); - ix = seq & RXRPC_RXTX_BUFF_MASK; - rxrpc_get_skb(skb, rxrpc_skb_got); - call->rxtx_annotations[ix] = annotation; - smp_wmb(); - call->rxtx_buffer[ix] = skb; + /* Add the packet to the call's output buffer */ + rxrpc_get_txbuf(txb, rxrpc_txbuf_get_buffer); + spin_lock(&call->tx_lock); + list_add_tail(&txb->call_link, &call->tx_buffer); call->tx_top = seq; + spin_unlock(&call->tx_lock); + if (last) - trace_rxrpc_transmit(call, rxrpc_transmit_queue_last); + trace_rxrpc_txqueue(call, rxrpc_txqueue_queue_last); else - trace_rxrpc_transmit(call, rxrpc_transmit_queue); + trace_rxrpc_txqueue(call, rxrpc_txqueue_queue); if (last || call->state == RXRPC_CALL_SERVER_ACK_REQUEST) { _debug("________awaiting reply/ACK__________"); @@ -254,7 +245,7 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, if (seq == 1 && rxrpc_is_client_call(call)) rxrpc_expose_client_call(call); - ret = rxrpc_send_data_packet(call, skb, false); + ret = rxrpc_send_data_packet(call, txb); if (ret < 0) { switch (ret) { case -ENETUNREACH: @@ -264,8 +255,6 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, 0, ret); goto out; } - _debug("need instant resend %d", ret); - rxrpc_instant_resend(call, ix); } else { unsigned long now = jiffies; unsigned long resend_at = now + call->peer->rto_j; @@ -276,9 +265,7 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, } out: - rxrpc_free_skb(skb, rxrpc_skb_freed); - _leave(" = %d", ret); - return ret; + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_trans); } /* @@ -292,8 +279,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, rxrpc_notify_end_tx_t notify_end_tx, bool *_dropped_lock) { - struct rxrpc_skb_priv *sp; - struct sk_buff *skb; + struct rxrpc_txbuf *txb; struct sock *sk = &rx->sk; enum rxrpc_call_state state; long timeo; @@ -327,14 +313,15 @@ reload: goto maybe_error; } - skb = call->tx_pending; + txb = call->tx_pending; call->tx_pending = NULL; - rxrpc_see_skb(skb, rxrpc_skb_seen); + if (txb) + rxrpc_see_txbuf(txb, rxrpc_txbuf_see_send_more); do { rxrpc_transmit_ack_packets(call->peer->local); - if (!skb) { + if (!txb) { size_t remain, bufsize, chunk, offset; _debug("alloc"); @@ -355,52 +342,31 @@ reload: _debug("SIZE: %zu/%zu @%zu", chunk, bufsize, offset); /* create a buffer that we can retain until it's ACK'd */ - skb = sock_alloc_send_skb( - sk, bufsize, msg->msg_flags & MSG_DONTWAIT, &ret); - if (!skb) + ret = -ENOMEM; + txb = rxrpc_alloc_txbuf(call, RXRPC_PACKET_TYPE_DATA, + GFP_KERNEL); + if (!txb) goto maybe_error; - sp = rxrpc_skb(skb); - rxrpc_new_skb(skb, rxrpc_skb_new); - - _debug("ALLOC SEND %p", skb); - - ASSERTCMP(skb->mark, ==, 0); - - __skb_put(skb, offset); - - sp->remain = chunk; - if (sp->remain > skb_tailroom(skb)) - sp->remain = skb_tailroom(skb); - - _net("skb: hr %d, tr %d, hl %d, rm %d", - skb_headroom(skb), - skb_tailroom(skb), - skb_headlen(skb), - sp->remain); - - skb->ip_summed = CHECKSUM_UNNECESSARY; + txb->offset = offset; + txb->space -= offset; + txb->space = min_t(size_t, chunk, txb->space); } _debug("append"); - sp = rxrpc_skb(skb); /* append next segment of data to the current buffer */ if (msg_data_left(msg) > 0) { - int copy = skb_tailroom(skb); - ASSERTCMP(copy, >, 0); - if (copy > msg_data_left(msg)) - copy = msg_data_left(msg); - if (copy > sp->remain) - copy = sp->remain; - - _debug("add"); - ret = skb_add_data(skb, &msg->msg_iter, copy); - _debug("added"); - if (ret < 0) + size_t copy = min_t(size_t, txb->space, msg_data_left(msg)); + + _debug("add %zu", copy); + if (!copy_from_iter_full(txb->data + txb->offset, copy, + &msg->msg_iter)) goto efault; - sp->remain -= copy; - skb->mark += copy; + _debug("added"); + txb->space -= copy; + txb->len += copy; + txb->offset += copy; copied += copy; if (call->tx_total_len != -1) call->tx_total_len -= copy; @@ -412,32 +378,22 @@ reload: goto call_terminated; /* add the packet to the send queue if it's now full */ - if (sp->remain <= 0 || + if (!txb->space || (msg_data_left(msg) == 0 && !more)) { - struct rxrpc_connection *conn = call->conn; - uint32_t seq; - - seq = call->tx_top + 1; - - sp->hdr.seq = seq; - sp->hdr._rsvd = 0; - sp->hdr.flags = conn->out_clientflag; - - if (msg_data_left(msg) == 0 && !more) - sp->hdr.flags |= RXRPC_LAST_PACKET; - else if (call->tx_top - call->tx_hard_ack < + if (msg_data_left(msg) == 0 && !more) { + txb->wire.flags |= RXRPC_LAST_PACKET; + __set_bit(RXRPC_TXBUF_LAST, &txb->flags); + } + else if (call->tx_top - call->acks_hard_ack < call->tx_winsize) - sp->hdr.flags |= RXRPC_MORE_PACKETS; + txb->wire.flags |= RXRPC_MORE_PACKETS; - ret = call->security->secure_packet(call, skb, skb->mark); + ret = call->security->secure_packet(call, txb); if (ret < 0) goto out; - ret = rxrpc_queue_packet(rx, call, skb, - !msg_data_left(msg) && !more, - notify_end_tx); - /* Should check for failure here */ - skb = NULL; + rxrpc_queue_packet(rx, call, txb, notify_end_tx); + txb = NULL; } } while (msg_data_left(msg) > 0); @@ -450,12 +406,12 @@ success: read_unlock_bh(&call->state_lock); } out: - call->tx_pending = skb; + call->tx_pending = txb; _leave(" = %d", ret); return ret; call_terminated: - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_send_aborted); _leave(" = %d", call->error); return call->error; diff --git a/net/rxrpc/txbuf.c b/net/rxrpc/txbuf.c index 45a7b48a5e10..96bfee89927b 100644 --- a/net/rxrpc/txbuf.c +++ b/net/rxrpc/txbuf.c @@ -99,3 +99,37 @@ void rxrpc_put_txbuf(struct rxrpc_txbuf *txb, enum rxrpc_txbuf_trace what) call_rcu(&txb->rcu, rxrpc_free_txbuf); } } + +/* + * Shrink the transmit buffer. + */ +void rxrpc_shrink_call_tx_buffer(struct rxrpc_call *call) +{ + struct rxrpc_txbuf *txb; + rxrpc_seq_t hard_ack = smp_load_acquire(&call->acks_hard_ack); + + _enter("%x/%x/%x", call->tx_bottom, call->acks_hard_ack, call->tx_top); + + for (;;) { + spin_lock(&call->tx_lock); + txb = list_first_entry_or_null(&call->tx_buffer, + struct rxrpc_txbuf, call_link); + if (!txb) + break; + hard_ack = smp_load_acquire(&call->acks_hard_ack); + if (before(hard_ack, txb->seq)) + break; + + ASSERTCMP(txb->seq, ==, call->tx_bottom + 1); + call->tx_bottom++; + list_del_rcu(&txb->call_link); + + trace_rxrpc_txqueue(call, rxrpc_txqueue_dequeue); + + spin_unlock(&call->tx_lock); + + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_rotated); + } + + spin_unlock(&call->tx_lock); +} -- cgit v1.2.3 From d57a3a151660902091491ac2633134e1be92557f Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 7 May 2022 10:06:13 +0100 Subject: rxrpc: Save last ACK's SACK table rather than marking txbufs Improve the tracking of which packets need to be transmitted by saving the last ACK packet that we receive that has a populated soft-ACK table rather than marking packets. Then we can step through the soft-ACK table and look at the packets we've transmitted beyond that to determine which packets we might want to retransmit. We also look at the highest serial number that has been acked to try and guess which packets we've transmitted the peer is likely to have seen. If necessary, we send a ping to retrieve that number. One downside that might be a problem is that we can't then compare the previous acked/unacked state so easily in rxrpc_input_soft_acks() - which is a potential problem for the slow-start algorithm. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 7 +- net/core/skbuff.c | 1 + net/rxrpc/ar-internal.h | 12 ++-- net/rxrpc/call_event.c | 117 ++++++++++++++++++++++++------ net/rxrpc/call_object.c | 2 + net/rxrpc/input.c | 164 ++++++++++++++++++++----------------------- net/rxrpc/sendmsg.c | 1 - 7 files changed, 185 insertions(+), 119 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 71ca74e40ec8..a11de55c3c14 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -17,6 +17,7 @@ * Declare tracing information enums and their string mappings for display. */ #define rxrpc_skb_traces \ + EM(rxrpc_skb_ack, "ACK") \ EM(rxrpc_skb_cleaned, "CLN") \ EM(rxrpc_skb_cloned_jumbo, "CLJ") \ EM(rxrpc_skb_freed, "FRE") \ @@ -1257,7 +1258,7 @@ TRACE_EVENT(rxrpc_congest, 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 r=%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 nA=%u,%u+%u r=%u b=%u u=%u d=%u l=%x%s%s%s", __entry->call, __entry->ack_serial, __print_symbolic(__entry->sum.ack_reason, rxrpc_ack_names), @@ -1265,8 +1266,8 @@ TRACE_EVENT(rxrpc_congest, __print_symbolic(__entry->sum.mode, rxrpc_congest_modes), __entry->sum.cwnd, __entry->sum.ssthresh, - __entry->sum.nr_acks, __entry->sum.nr_nacks, - __entry->sum.nr_new_acks, __entry->sum.nr_new_nacks, + __entry->sum.nr_acks, __entry->sum.saw_nacks, + __entry->sum.nr_new_acks, __entry->sum.nr_rot_new_acks, __entry->top - __entry->hard_ack, __entry->sum.cumulative_acks, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 1d84a17eada5..2143244e8ec3 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -6431,6 +6431,7 @@ void skb_condense(struct sk_buff *skb) */ skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); } +EXPORT_SYMBOL(skb_condense); #ifdef CONFIG_SKB_EXTENSIONS static void *skb_ext_get_ptr(struct skb_ext *ext, enum skb_ext_id id) diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 5ec30e84360b..168d03b56ada 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -694,6 +694,8 @@ struct rxrpc_call { rxrpc_seq_t acks_lost_top; /* tx_top at the time lost-ack ping sent */ rxrpc_serial_t acks_lost_ping; /* Serial number of probe ACK */ rxrpc_serial_t acks_highest_serial; /* Highest serial number ACK'd */ + struct sk_buff *acks_soft_tbl; /* The last ACK packet with NAKs in it */ + spinlock_t acks_ack_lock; /* Access to ->acks_last_ack */ }; /* @@ -702,10 +704,9 @@ struct rxrpc_call { struct rxrpc_ack_summary { u8 ack_reason; u8 nr_acks; /* Number of ACKs in packet */ - u8 nr_nacks; /* Number of NACKs in packet */ u8 nr_new_acks; /* Number of new ACKs in packet */ - u8 nr_new_nacks; /* Number of new NACKs in packet */ u8 nr_rot_new_acks; /* Number of rotated new ACKs */ + bool saw_nacks; /* Saw NACKs in packet */ bool new_low_nack; /* T if new low NACK found */ bool retrans_timeo; /* T if reTx due to timeout happened */ u8 flight_size; /* Number of unreceived transmissions */ @@ -765,11 +766,8 @@ struct rxrpc_txbuf { unsigned int space; /* Remaining data space */ unsigned int offset; /* Offset of fill point */ unsigned long flags; -#define RXRPC_TXBUF_ACKED 0 /* Set if ACK'd */ -#define RXRPC_TXBUF_NACKED 1 /* Set if NAK'd */ -#define RXRPC_TXBUF_LAST 2 /* Set if last packet in Tx phase */ -#define RXRPC_TXBUF_RESENT 3 /* Set if has been resent */ -#define RXRPC_TXBUF_RETRANS 4 /* Set if should be retransmitted */ +#define RXRPC_TXBUF_LAST 0 /* Set if last packet in Tx phase */ +#define RXRPC_TXBUF_RESENT 1 /* Set if has been resent */ u8 /*enum rxrpc_propose_ack_trace*/ ack_why; /* If ack, why */ struct { /* The packet for encrypting and DMA'ing. We align it such diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index dbfaf8170929..1e21a708390e 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -132,48 +132,127 @@ static void rxrpc_congestion_timeout(struct rxrpc_call *call) */ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) { + struct rxrpc_ackpacket *ack = NULL; struct rxrpc_txbuf *txb; + struct sk_buff *ack_skb = NULL; unsigned long resend_at; rxrpc_seq_t transmitted = READ_ONCE(call->tx_transmitted); ktime_t now, max_age, oldest, ack_ts; bool unacked = false; + unsigned int i; LIST_HEAD(retrans_queue); _enter("{%d,%d}", call->acks_hard_ack, call->tx_top); now = ktime_get_real(); max_age = ktime_sub_us(now, jiffies_to_usecs(call->peer->rto_j)); + oldest = now; + + /* See if there's an ACK saved with a soft-ACK table in it. */ + if (call->acks_soft_tbl) { + spin_lock_bh(&call->acks_ack_lock); + ack_skb = call->acks_soft_tbl; + if (ack_skb) { + rxrpc_get_skb(ack_skb, rxrpc_skb_ack); + ack = (void *)ack_skb->data + sizeof(struct rxrpc_wire_header); + } + spin_unlock_bh(&call->acks_ack_lock); + } + + if (list_empty(&call->tx_buffer)) + goto no_resend; spin_lock(&call->tx_lock); - /* Scan the packet list without dropping the lock and decide which of - * the packets in the Tx buffer we're going to resend and what the new - * resend timeout will be. - */ + if (list_empty(&call->tx_buffer)) + goto no_further_resend; + trace_rxrpc_resend(call); - oldest = now; - list_for_each_entry(txb, &call->tx_buffer, call_link) { - if (test_bit(RXRPC_TXBUF_ACKED, &txb->flags)) - continue; - if (after(txb->seq, transmitted)) - break; + txb = list_first_entry(&call->tx_buffer, struct rxrpc_txbuf, call_link); - rxrpc_see_txbuf(txb, rxrpc_txbuf_see_unacked); + /* Scan the soft ACK table without dropping the lock and resend any + * explicitly NAK'd packets. + */ + if (ack) { + for (i = 0; i < ack->nAcks; i++) { + rxrpc_seq_t seq; - if (test_bit(RXRPC_TXBUF_RESENT, &txb->flags)) { - if (ktime_after(txb->last_sent, max_age)) { - if (ktime_before(txb->last_sent, oldest)) - oldest = txb->last_sent; + if (ack->acks[i] & 1) continue; + seq = ntohl(ack->firstPacket) + i; + if (after(txb->seq, transmitted)) + break; + if (after(txb->seq, seq)) + continue; /* A new hard ACK probably came in */ + list_for_each_entry_from(txb, &call->tx_buffer, call_link) { + if (txb->seq == seq) + goto found_txb; + } + goto no_further_resend; + + found_txb: + if (after(ntohl(txb->wire.serial), call->acks_highest_serial)) + continue; /* Ack point not yet reached */ + + rxrpc_see_txbuf(txb, rxrpc_txbuf_see_unacked); + + if (list_empty(&txb->tx_link)) { + rxrpc_get_txbuf(txb, rxrpc_txbuf_get_retrans); + rxrpc_get_call(call, rxrpc_call_got_tx); + list_add_tail(&txb->tx_link, &retrans_queue); + set_bit(RXRPC_TXBUF_RESENT, &txb->flags); } - unacked = true; + + trace_rxrpc_retransmit(call, txb->seq, + ktime_to_ns(ktime_sub(txb->last_sent, + max_age))); + + if (list_is_last(&txb->call_link, &call->tx_buffer)) + goto no_further_resend; + txb = list_next_entry(txb, call_link); } + } - rxrpc_get_txbuf(txb, rxrpc_txbuf_get_retrans); - list_move_tail(&txb->tx_link, &retrans_queue); + /* Fast-forward through the Tx queue to the point the peer says it has + * seen. Anything between the soft-ACK table and that point will get + * ACK'd or NACK'd in due course, so don't worry about it here; here we + * need to consider retransmitting anything beyond that point. + * + * Note that ACK for a packet can beat the update of tx_transmitted. + */ + if (after_eq(READ_ONCE(call->acks_prev_seq), READ_ONCE(call->tx_transmitted))) + goto no_further_resend; + + list_for_each_entry_from(txb, &call->tx_buffer, call_link) { + if (before_eq(txb->seq, READ_ONCE(call->acks_prev_seq))) + continue; + if (after(txb->seq, READ_ONCE(call->tx_transmitted))) + break; /* Not transmitted yet */ + + if (ack && ack->reason == RXRPC_ACK_PING_RESPONSE && + before(ntohl(txb->wire.serial), ntohl(ack->serial))) + goto do_resend; /* Wasn't accounted for by a more recent ping. */ + + if (ktime_after(txb->last_sent, max_age)) { + if (ktime_before(txb->last_sent, oldest)) + oldest = txb->last_sent; + continue; + } + + do_resend: + unacked = true; + if (list_empty(&txb->tx_link)) { + rxrpc_get_txbuf(txb, rxrpc_txbuf_get_retrans); + list_add_tail(&txb->tx_link, &retrans_queue); + set_bit(RXRPC_TXBUF_RESENT, &txb->flags); + rxrpc_inc_stat(call->rxnet, stat_tx_data_retrans); + } } +no_further_resend: spin_unlock(&call->tx_lock); +no_resend: + rxrpc_free_skb(ack_skb, rxrpc_skb_freed); resend_at = nsecs_to_jiffies(ktime_to_ns(ktime_sub(now, oldest))); resend_at += jiffies + rxrpc_get_rto_backoff(call->peer, @@ -201,8 +280,6 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) while ((txb = list_first_entry_or_null(&retrans_queue, struct rxrpc_txbuf, tx_link))) { list_del_init(&txb->tx_link); - set_bit(RXRPC_TXBUF_RESENT, &txb->flags); - rxrpc_inc_stat(call->rxnet, stat_tx_data_retrans); rxrpc_send_data_packet(call, txb); rxrpc_put_txbuf(txb, rxrpc_txbuf_put_trans); diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index a3ae2ab45f9e..91771031ad3c 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -162,6 +162,7 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, spin_lock_init(&call->notify_lock); spin_lock_init(&call->tx_lock); spin_lock_init(&call->input_lock); + spin_lock_init(&call->acks_ack_lock); rwlock_init(&call->state_lock); refcount_set(&call->ref, 1); call->debug_id = debug_id; @@ -701,6 +702,7 @@ void rxrpc_cleanup_call(struct rxrpc_call *call) rxrpc_put_txbuf(txb, rxrpc_txbuf_put_cleaned); } rxrpc_put_txbuf(call->tx_pending, rxrpc_txbuf_put_cleaned); + rxrpc_free_skb(call->acks_soft_tbl, rxrpc_skb_cleaned); call_rcu(&call->rcu, rxrpc_rcu_destroy_call); } diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index e6e1267915de..5c17fed4b60f 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -60,7 +60,7 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, switch (call->cong_mode) { case RXRPC_CALL_SLOW_START: - if (summary->nr_nacks > 0) + if (summary->saw_nacks) goto packet_loss_detected; if (summary->cumulative_acks > 0) cwnd += 1; @@ -71,7 +71,7 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, goto out; case RXRPC_CALL_CONGEST_AVOIDANCE: - if (summary->nr_nacks > 0) + if (summary->saw_nacks) goto packet_loss_detected; /* We analyse the number of packets that get ACK'd per RTT @@ -90,7 +90,7 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, goto out; case RXRPC_CALL_PACKET_LOSS: - if (summary->nr_nacks == 0) + if (!summary->saw_nacks) goto resume_normality; if (summary->new_low_nack) { @@ -128,7 +128,7 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, } else { change = rxrpc_cong_progress; cwnd = call->cong_ssthresh; - if (summary->nr_nacks == 0) + if (!summary->saw_nacks) goto resume_normality; } goto out; @@ -189,8 +189,7 @@ static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, list_for_each_entry_rcu(txb, &call->tx_buffer, call_link, false) { if (before_eq(txb->seq, call->acks_hard_ack)) continue; - if (!test_bit(RXRPC_TXBUF_ACKED, &txb->flags)) - summary->nr_rot_new_acks++; + summary->nr_rot_new_acks++; if (test_bit(RXRPC_TXBUF_LAST, &txb->flags)) { set_bit(RXRPC_CALL_TX_LAST, &call->flags); rot_last = true; @@ -661,22 +660,8 @@ static void rxrpc_complete_rtt_probe(struct rxrpc_call *call, */ static void rxrpc_input_check_for_lost_ack(struct rxrpc_call *call) { - struct rxrpc_txbuf *txb; - rxrpc_seq_t top, bottom; - bool resend = false; - - bottom = READ_ONCE(call->acks_hard_ack) + 1; - top = READ_ONCE(call->acks_lost_top); - if (before(bottom, top)) { - list_for_each_entry_rcu(txb, &call->tx_buffer, call_link, false) { - if (test_bit(RXRPC_TXBUF_ACKED, &txb->flags)) - continue; - set_bit(RXRPC_TXBUF_RETRANS, &txb->flags); - resend = true; - } - } - - if (resend && !test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events)) + if (after(call->acks_lost_top, call->acks_prev_seq) && + !test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events)) rxrpc_queue_call(call); } @@ -749,41 +734,19 @@ static void rxrpc_input_soft_acks(struct rxrpc_call *call, u8 *acks, rxrpc_seq_t seq, int nr_acks, struct rxrpc_ack_summary *summary) { - struct rxrpc_txbuf *txb; + unsigned int i; - list_for_each_entry_rcu(txb, &call->tx_buffer, call_link, false) { - if (before(txb->seq, seq)) - continue; - if (after_eq(txb->seq, seq + nr_acks)) - break; - switch (acks[txb->seq - seq]) { - case RXRPC_ACK_TYPE_ACK: + for (i = 0; i < nr_acks; i++) { + if (acks[i] == RXRPC_ACK_TYPE_ACK) { summary->nr_acks++; - if (test_bit(RXRPC_TXBUF_ACKED, &txb->flags)) - continue; - /* A lot of the time the packet is going to - * have been ACK.'d already. - */ - clear_bit(RXRPC_TXBUF_NACKED, &txb->flags); - set_bit(RXRPC_TXBUF_ACKED, &txb->flags); summary->nr_new_acks++; - break; - case RXRPC_ACK_TYPE_NACK: - if (!summary->nr_nacks && - call->acks_lowest_nak != seq) { - call->acks_lowest_nak = seq; + } else { + if (!summary->saw_nacks && + call->acks_lowest_nak != seq + i) { + call->acks_lowest_nak = seq + i; summary->new_low_nack = true; } - summary->nr_nacks++; - if (test_bit(RXRPC_TXBUF_NACKED, &txb->flags)) - continue; - summary->nr_new_nacks++; - clear_bit(RXRPC_TXBUF_ACKED, &txb->flags); - set_bit(RXRPC_TXBUF_NACKED, &txb->flags); - set_bit(RXRPC_TXBUF_RETRANS, &txb->flags); - break; - default: - return rxrpc_proto_abort("SFT", call, 0); + summary->saw_nacks = true; } } } @@ -825,12 +788,10 @@ static bool rxrpc_is_ack_valid(struct rxrpc_call *call, static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_ack_summary summary = { 0 }; + struct rxrpc_ackpacket ack; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - union { - struct rxrpc_ackpacket ack; - struct rxrpc_ackinfo info; - u8 acks[RXRPC_MAXACKS]; - } buf; + struct rxrpc_ackinfo info; + struct sk_buff *skb_old = NULL, *skb_put = skb; rxrpc_serial_t ack_serial, acked_serial; rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt; int nr_acks, offset, ioffset; @@ -838,30 +799,28 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) _enter(""); offset = sizeof(struct rxrpc_wire_header); - if (skb_copy_bits(skb, offset, &buf.ack, sizeof(buf.ack)) < 0) { - _debug("extraction failure"); - return rxrpc_proto_abort("XAK", call, 0); + if (skb_copy_bits(skb, offset, &ack, sizeof(ack)) < 0) { + rxrpc_proto_abort("XAK", call, 0); + goto out_not_locked; } - offset += sizeof(buf.ack); + offset += sizeof(ack); ack_serial = sp->hdr.serial; - acked_serial = ntohl(buf.ack.serial); - first_soft_ack = ntohl(buf.ack.firstPacket); - prev_pkt = ntohl(buf.ack.previousPacket); + acked_serial = ntohl(ack.serial); + first_soft_ack = ntohl(ack.firstPacket); + prev_pkt = ntohl(ack.previousPacket); hard_ack = first_soft_ack - 1; - nr_acks = buf.ack.nAcks; - summary.ack_reason = (buf.ack.reason < RXRPC_ACK__INVALID ? - buf.ack.reason : RXRPC_ACK__INVALID); + nr_acks = ack.nAcks; + summary.ack_reason = (ack.reason < RXRPC_ACK__INVALID ? + ack.reason : RXRPC_ACK__INVALID); trace_rxrpc_rx_ack(call, ack_serial, acked_serial, first_soft_ack, prev_pkt, summary.ack_reason, nr_acks); - rxrpc_inc_stat(call->rxnet, stat_rx_acks[buf.ack.reason]); + rxrpc_inc_stat(call->rxnet, stat_rx_acks[ack.reason]); - switch (buf.ack.reason) { + switch (ack.reason) { case RXRPC_ACK_PING_RESPONSE: - rxrpc_input_ping_response(call, skb->tstamp, acked_serial, - ack_serial); rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, rxrpc_rtt_rx_ping_response); break; @@ -876,7 +835,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) break; } - if (buf.ack.reason == RXRPC_ACK_PING) { + if (ack.reason == RXRPC_ACK_PING) { _proto("Rx ACK %%%u PING Request", ack_serial); rxrpc_send_ACK(call, RXRPC_ACK_PING_RESPONSE, ack_serial, rxrpc_propose_ack_respond_to_ping); @@ -889,7 +848,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) * indicates that the client address changed due to NAT. The server * lost the call because it switched to a different peer. */ - if (unlikely(buf.ack.reason == RXRPC_ACK_EXCEEDS_WINDOW) && + if (unlikely(ack.reason == RXRPC_ACK_EXCEEDS_WINDOW) && first_soft_ack == 1 && prev_pkt == 0 && rxrpc_is_client_call(call)) { @@ -902,7 +861,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) * indicate a change of address. However, we can retransmit the call * if we still have it buffered to the beginning. */ - if (unlikely(buf.ack.reason == RXRPC_ACK_OUT_OF_SEQUENCE) && + if (unlikely(ack.reason == RXRPC_ACK_OUT_OF_SEQUENCE) && first_soft_ack == 1 && prev_pkt == 0 && call->acks_hard_ack == 0 && @@ -917,14 +876,19 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) trace_rxrpc_rx_discard_ack(call->debug_id, ack_serial, first_soft_ack, call->acks_first_seq, prev_pkt, call->acks_prev_seq); - return; + goto out_not_locked; } - buf.info.rxMTU = 0; + info.rxMTU = 0; ioffset = offset + nr_acks + 3; - if (skb->len >= ioffset + sizeof(buf.info) && - skb_copy_bits(skb, ioffset, &buf.info, sizeof(buf.info)) < 0) - return rxrpc_proto_abort("XAI", call, 0); + if (skb->len >= ioffset + sizeof(info) && + skb_copy_bits(skb, ioffset, &info, sizeof(info)) < 0) { + rxrpc_proto_abort("XAI", call, 0); + goto out_not_locked; + } + + if (nr_acks > 0) + skb_condense(skb); spin_lock(&call->input_lock); @@ -940,13 +904,22 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) call->acks_first_seq = first_soft_ack; call->acks_prev_seq = prev_pkt; - if (buf.ack.reason != RXRPC_ACK_PING && - after(acked_serial, call->acks_highest_serial)) - call->acks_highest_serial = acked_serial; + switch (ack.reason) { + case RXRPC_ACK_PING: + break; + case RXRPC_ACK_PING_RESPONSE: + rxrpc_input_ping_response(call, skb->tstamp, acked_serial, + ack_serial); + fallthrough; + default: + if (after(acked_serial, call->acks_highest_serial)) + call->acks_highest_serial = acked_serial; + break; + } /* Parse rwind and mtu sizes if provided. */ - if (buf.info.rxMTU) - rxrpc_input_ackinfo(call, skb, &buf.info); + if (info.rxMTU) + rxrpc_input_ackinfo(call, skb, &info); if (first_soft_ack == 0) { rxrpc_proto_abort("AK0", call, 0); @@ -982,12 +955,24 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) } if (nr_acks > 0) { - if (skb_copy_bits(skb, offset, buf.acks, nr_acks) < 0) { + if (offset > (int)skb->len - nr_acks) { rxrpc_proto_abort("XSA", call, 0); goto out; } - rxrpc_input_soft_acks(call, buf.acks, first_soft_ack, nr_acks, - &summary); + + spin_lock(&call->acks_ack_lock); + skb_old = call->acks_soft_tbl; + call->acks_soft_tbl = skb; + spin_unlock(&call->acks_ack_lock); + + rxrpc_input_soft_acks(call, skb->data + offset, first_soft_ack, + nr_acks, &summary); + skb_put = NULL; + } else if (call->acks_soft_tbl) { + spin_lock(&call->acks_ack_lock); + skb_old = call->acks_soft_tbl; + call->acks_soft_tbl = NULL; + spin_unlock(&call->acks_ack_lock); } if (test_bit(RXRPC_CALL_TX_LAST, &call->flags) && @@ -999,6 +984,9 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_congestion_management(call, skb, &summary, acked_serial); out: spin_unlock(&call->input_lock); +out_not_locked: + rxrpc_free_skb(skb_put, rxrpc_skb_freed); + rxrpc_free_skb(skb_old, rxrpc_skb_freed); } /* @@ -1071,7 +1059,7 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call, case RXRPC_PACKET_TYPE_ACK: rxrpc_input_ack(call, skb); - break; + goto no_free; case RXRPC_PACKET_TYPE_BUSY: _proto("Rx BUSY %%%u", sp->hdr.serial); diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index a96ae7f58148..9b567aff3e84 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -600,7 +600,6 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, */ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) __releases(&rx->sk.sk_lock.slock) - __releases(&call->user_mutex) { enum rxrpc_call_state state; struct rxrpc_call *call; -- cgit v1.2.3 From 1fc4fa2ac93dcf3542f2dc6f7ff88fb022da5116 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 3 Oct 2022 18:49:11 +0100 Subject: rxrpc: Fix congestion management rxrpc has a problem in its congestion management in that it saves the congestion window size (cwnd) from one call to another, but if this is 0 at the time is saved, then the next call may not actually manage to ever transmit anything. To this end: (1) Don't save cwnd between calls, but rather reset back down to the initial cwnd and re-enter slow-start if data transmission is idle for more than an RTT. (2) Preserve ssthresh instead, as that is a handy estimate of pipe capacity. Knowing roughly when to stop slow start and enter congestion avoidance can reduce the tendency to overshoot and drop larger amounts of packets when probing. In future, cwind growth also needs to be constrained when the window isn't being filled due to being application limited. Reported-by: Simon Wilkinson cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 1 + net/rxrpc/ar-internal.h | 9 +++++---- net/rxrpc/call_accept.c | 3 ++- net/rxrpc/call_object.c | 7 ++++++- net/rxrpc/conn_client.c | 3 ++- net/rxrpc/conn_object.c | 2 +- net/rxrpc/input.c | 21 ++++++++++++++++++++- net/rxrpc/output.c | 1 + net/rxrpc/peer_object.c | 7 +------ net/rxrpc/proc.c | 4 ++-- net/rxrpc/sendmsg.c | 22 +++++++++++++++++++--- 11 files changed, 60 insertions(+), 20 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index a11de55c3c14..b9886d1df825 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -193,6 +193,7 @@ EM(rxrpc_cong_new_low_nack, " NewLowN") \ EM(rxrpc_cong_no_change, " -") \ EM(rxrpc_cong_progress, " Progres") \ + EM(rxrpc_cong_idle_reset, " IdleRes") \ EM(rxrpc_cong_retransmit_again, " ReTxAgn") \ EM(rxrpc_cong_rtt_window_end, " RttWinE") \ E_(rxrpc_cong_saw_nack, " SawNack") diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 775eb91aabb2..6bbe28ecf583 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -332,7 +332,7 @@ struct rxrpc_peer { u32 rto_j; /* Retransmission timeout in jiffies */ u8 backoff; /* Backoff timeout */ - u8 cong_cwnd; /* Congestion window size */ + u8 cong_ssthresh; /* Congestion slow-start threshold */ }; /* @@ -626,6 +626,7 @@ struct rxrpc_call { u16 tx_backoff; /* Delay to insert due to Tx failure */ u8 tx_winsize; /* Maximum size of Tx window */ #define RXRPC_TX_MAX_WINDOW 128 + ktime_t tx_last_sent; /* Last time a transmission occurred */ /* Received data tracking */ struct sk_buff_head recvmsg_queue; /* Queue of packets ready for recvmsg() */ @@ -687,10 +688,10 @@ struct rxrpc_call { * Summary of a new ACK and the changes it made to the Tx buffer packet states. */ struct rxrpc_ack_summary { + u16 nr_acks; /* Number of ACKs in packet */ + u16 nr_new_acks; /* Number of new ACKs in packet */ + u16 nr_rot_new_acks; /* Number of rotated new ACKs */ u8 ack_reason; - u8 nr_acks; /* Number of ACKs in packet */ - u8 nr_new_acks; /* Number of new ACKs in packet */ - u8 nr_rot_new_acks; /* Number of rotated new ACKs */ bool saw_nacks; /* Saw NACKs in packet */ bool new_low_nack; /* T if new low NACK found */ bool retrans_timeo; /* T if reTx due to timeout happened */ diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index d8db277d5ebe..48790ee77019 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -324,7 +324,8 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, call->security = conn->security; call->security_ix = conn->security_ix; call->peer = rxrpc_get_peer(conn->params.peer); - call->cong_cwnd = call->peer->cong_cwnd; + call->cong_ssthresh = call->peer->cong_ssthresh; + call->tx_last_sent = ktime_get_real(); return call; } diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index aa19daaa487b..1befe22cd301 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -166,7 +166,12 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, call->rx_winsize = rxrpc_rx_window_size; call->tx_winsize = 16; - call->cong_cwnd = 2; + if (RXRPC_TX_SMSS > 2190) + call->cong_cwnd = 2; + else if (RXRPC_TX_SMSS > 1095) + call->cong_cwnd = 3; + else + call->cong_cwnd = 4; call->cong_ssthresh = RXRPC_TX_MAX_WINDOW; call->rxnet = rxnet; diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 3c9eeb5b750c..f020f308ed9e 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -363,7 +363,8 @@ static struct rxrpc_bundle *rxrpc_prep_call(struct rxrpc_sock *rx, if (!cp->peer) goto error; - call->cong_cwnd = cp->peer->cong_cwnd; + call->tx_last_sent = ktime_get_real(); + call->cong_ssthresh = cp->peer->cong_ssthresh; if (call->cong_cwnd >= call->cong_ssthresh) call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE; else diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index f7ea71ae6159..156bd26daf74 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -207,7 +207,7 @@ void rxrpc_disconnect_call(struct rxrpc_call *call) { struct rxrpc_connection *conn = call->conn; - call->peer->cong_cwnd = call->cong_cwnd; + call->peer->cong_ssthresh = call->cong_ssthresh; if (!hlist_unhashed(&call->error_link)) { spin_lock_bh(&call->peer->lock); diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 5c17fed4b60f..bdf70b81addc 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -58,6 +58,25 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, summary->cumulative_acks = cumulative_acks; summary->dup_acks = call->cong_dup_acks; + /* If we haven't transmitted anything for >1RTT, we should reset the + * congestion management state. + */ + if ((call->cong_mode == RXRPC_CALL_SLOW_START || + call->cong_mode == RXRPC_CALL_CONGEST_AVOIDANCE) && + ktime_before(ktime_add_us(call->tx_last_sent, + call->peer->srtt_us >> 3), + ktime_get_real()) + ) { + change = rxrpc_cong_idle_reset; + summary->mode = RXRPC_CALL_SLOW_START; + if (RXRPC_TX_SMSS > 2190) + summary->cwnd = 2; + else if (RXRPC_TX_SMSS > 1095) + summary->cwnd = 3; + else + summary->cwnd = 4; + } + switch (call->cong_mode) { case RXRPC_CALL_SLOW_START: if (summary->saw_nacks) @@ -205,7 +224,7 @@ static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, if (call->acks_lowest_nak == call->acks_hard_ack) { call->acks_lowest_nak = to; - } else if (before_eq(call->acks_lowest_nak, to)) { + } else if (after(to, call->acks_lowest_nak)) { summary->new_low_nack = true; call->acks_lowest_nak = to; } diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 2c3f7e4e30d7..46432e70a16b 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -501,6 +501,7 @@ dont_set_request_ack: done: if (ret >= 0) { + call->tx_last_sent = txb->last_sent; if (txb->wire.flags & RXRPC_REQUEST_ACK) { call->peer->rtt_last_req = txb->last_sent; if (call->peer->rtt_count > 1) { diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 26d2ae9baaf2..041a51225c5f 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -227,12 +227,7 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp) rxrpc_peer_init_rtt(peer); - if (RXRPC_TX_SMSS > 2190) - peer->cong_cwnd = 2; - else if (RXRPC_TX_SMSS > 1095) - peer->cong_cwnd = 3; - else - peer->cong_cwnd = 4; + peer->cong_ssthresh = RXRPC_TX_MAX_WINDOW; trace_rxrpc_peer(peer->debug_id, rxrpc_peer_new, 1, here); } diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index 0807753ec2dc..fae22a8b38d6 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -217,7 +217,7 @@ static int rxrpc_peer_seq_show(struct seq_file *seq, void *v) seq_puts(seq, "Proto Local " " Remote " - " Use CW MTU LastUse RTT RTO\n" + " Use SST MTU LastUse RTT RTO\n" ); return 0; } @@ -235,7 +235,7 @@ static int rxrpc_peer_seq_show(struct seq_file *seq, void *v) lbuff, rbuff, refcount_read(&peer->ref), - peer->cong_cwnd, + peer->cong_ssthresh, peer->mtu, now - peer->last_tx_at, peer->srtt_us >> 3, diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 9b567aff3e84..e5fd8a95bf71 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -22,11 +22,27 @@ */ static bool rxrpc_check_tx_space(struct rxrpc_call *call, rxrpc_seq_t *_tx_win) { - unsigned int win_size = - min_t(unsigned int, call->tx_winsize, - call->cong_cwnd + call->cong_extra); + unsigned int win_size; rxrpc_seq_t tx_win = smp_load_acquire(&call->acks_hard_ack); + /* If we haven't transmitted anything for >1RTT, we should reset the + * congestion management state. + */ + if (ktime_before(ktime_add_us(call->tx_last_sent, + call->peer->srtt_us >> 3), + ktime_get_real())) { + if (RXRPC_TX_SMSS > 2190) + win_size = 2; + else if (RXRPC_TX_SMSS > 1095) + win_size = 3; + else + win_size = 4; + win_size += call->cong_extra; + } else { + win_size = min_t(unsigned int, call->tx_winsize, + call->cong_cwnd + call->cong_extra); + } + if (_tx_win) *_tx_win = tx_win; return call->tx_top - tx_win < win_size; -- cgit v1.2.3 From 14e5f71e31ff3925cc970fa7907393ee7f4b748d Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Tue, 22 Nov 2022 20:09:47 -0800 Subject: net: use %pS for kfree_skb tracing event location For the cases where 'reason' doesn't give any clue, it's still nice to be able to track the kfree_skb caller location. %p doesn't help much so let's use %pS which prints the symbol+offset. Signed-off-by: Stanislav Fomichev Link: https://lore.kernel.org/r/20221123040947.1015721-1-sdf@google.com Signed-off-by: Paolo Abeni --- include/trace/events/skb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/trace') diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 50a974f7dfb4..25ab1ff9423d 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -42,7 +42,7 @@ TRACE_EVENT(kfree_skb, __entry->reason = reason; ), - TP_printk("skbaddr=%p protocol=%u location=%p reason: %s", + TP_printk("skbaddr=%p protocol=%u location=%pS reason: %s", __entry->skbaddr, __entry->protocol, __entry->location, __print_symbolic(__entry->reason, DEFINE_DROP_REASON(FN, FNe))) -- cgit v1.2.3 From 2ebdb26e6abd2a773ab5f009ac38a6de973a2bcf Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 20 Oct 2022 11:51:06 +0100 Subject: rxrpc: Remove the [k_]proto() debugging macros Remove the kproto() and _proto() debugging macros in preference to using tracepoints for this. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 60 ++++++++++++++++++++++++++++++++++++++++++++ net/rxrpc/ar-internal.h | 10 -------- net/rxrpc/conn_event.c | 4 --- net/rxrpc/input.c | 17 ------------- net/rxrpc/local_event.c | 3 --- net/rxrpc/output.c | 2 -- net/rxrpc/peer_event.c | 4 --- net/rxrpc/rxkad.c | 9 +++---- 8 files changed, 63 insertions(+), 46 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index b9886d1df825..2b77f9a75bf7 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -733,6 +733,66 @@ TRACE_EVENT(rxrpc_rx_abort, __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), + + TP_ARGS(conn, serial, version, nonce, min_level), + + TP_STRUCT__entry( + __field(unsigned int, conn ) + __field(rxrpc_serial_t, serial ) + __field(u32, version ) + __field(u32, nonce ) + __field(u32, min_level ) + ), + + TP_fast_assign( + __entry->conn = conn->debug_id; + __entry->serial = serial; + __entry->version = version; + __entry->nonce = nonce; + __entry->min_level = min_level; + ), + + TP_printk("C=%08x CHALLENGE %08x v=%x n=%x ml=%x", + __entry->conn, + __entry->serial, + __entry->version, + __entry->nonce, + __entry->min_level) + ); + +TRACE_EVENT(rxrpc_rx_response, + TP_PROTO(struct rxrpc_connection *conn, rxrpc_serial_t serial, + u32 version, u32 kvno, u32 ticket_len), + + TP_ARGS(conn, serial, version, kvno, ticket_len), + + TP_STRUCT__entry( + __field(unsigned int, conn ) + __field(rxrpc_serial_t, serial ) + __field(u32, version ) + __field(u32, kvno ) + __field(u32, ticket_len ) + ), + + TP_fast_assign( + __entry->conn = conn->debug_id; + __entry->serial = serial; + __entry->version = version; + __entry->kvno = kvno; + __entry->ticket_len = ticket_len; + ), + + TP_printk("C=%08x RESPONSE %08x v=%x kvno=%x tl=%x", + __entry->conn, + __entry->serial, + __entry->version, + __entry->kvno, + __entry->ticket_len) + ); + TRACE_EVENT(rxrpc_rx_rwind_change, TP_PROTO(struct rxrpc_call *call, rxrpc_serial_t serial, u32 rwind, bool wake), diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index f5c538ce3e23..a3a29390e12b 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -1190,7 +1190,6 @@ extern unsigned int rxrpc_debug; #define kenter(FMT,...) dbgprintk("==> %s("FMT")",__func__ ,##__VA_ARGS__) #define kleave(FMT,...) dbgprintk("<== %s()"FMT"",__func__ ,##__VA_ARGS__) #define kdebug(FMT,...) dbgprintk(" "FMT ,##__VA_ARGS__) -#define kproto(FMT,...) dbgprintk("### "FMT ,##__VA_ARGS__) #define knet(FMT,...) dbgprintk("@@@ "FMT ,##__VA_ARGS__) @@ -1198,14 +1197,12 @@ extern unsigned int rxrpc_debug; #define _enter(FMT,...) kenter(FMT,##__VA_ARGS__) #define _leave(FMT,...) kleave(FMT,##__VA_ARGS__) #define _debug(FMT,...) kdebug(FMT,##__VA_ARGS__) -#define _proto(FMT,...) kproto(FMT,##__VA_ARGS__) #define _net(FMT,...) knet(FMT,##__VA_ARGS__) #elif defined(CONFIG_AF_RXRPC_DEBUG) #define RXRPC_DEBUG_KENTER 0x01 #define RXRPC_DEBUG_KLEAVE 0x02 #define RXRPC_DEBUG_KDEBUG 0x04 -#define RXRPC_DEBUG_KPROTO 0x08 #define RXRPC_DEBUG_KNET 0x10 #define _enter(FMT,...) \ @@ -1226,12 +1223,6 @@ do { \ kdebug(FMT,##__VA_ARGS__); \ } while (0) -#define _proto(FMT,...) \ -do { \ - if (unlikely(rxrpc_debug & RXRPC_DEBUG_KPROTO)) \ - kproto(FMT,##__VA_ARGS__); \ -} while (0) - #define _net(FMT,...) \ do { \ if (unlikely(rxrpc_debug & RXRPC_DEBUG_KNET)) \ @@ -1242,7 +1233,6 @@ do { \ #define _enter(FMT,...) no_printk("==> %s("FMT")",__func__ ,##__VA_ARGS__) #define _leave(FMT,...) no_printk("<== %s()"FMT"",__func__ ,##__VA_ARGS__) #define _debug(FMT,...) no_printk(" "FMT ,##__VA_ARGS__) -#define _proto(FMT,...) no_printk("### "FMT ,##__VA_ARGS__) #define _net(FMT,...) no_printk("@@@ "FMT ,##__VA_ARGS__) #endif diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index aab069701398..d5549cbfc71b 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -122,14 +122,12 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, switch (chan->last_type) { case RXRPC_PACKET_TYPE_ABORT: - _proto("Tx ABORT %%%u { %d } [re]", serial, conn->abort_code); break; case RXRPC_PACKET_TYPE_ACK: trace_rxrpc_tx_ack(chan->call_debug_id, serial, ntohl(pkt.ack.firstPacket), ntohl(pkt.ack.serial), pkt.ack.reason, 0); - _proto("Tx ACK %%%u [re]", serial); break; } @@ -242,7 +240,6 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn, serial = atomic_inc_return(&conn->serial); rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED, serial); whdr.serial = htonl(serial); - _proto("Tx CONN ABORT %%%u { %d }", serial, conn->abort_code); ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); if (ret < 0) { @@ -315,7 +312,6 @@ static int rxrpc_process_event(struct rxrpc_connection *conn, return -EPROTO; } abort_code = ntohl(wtmp); - _proto("Rx ABORT %%%u { ac=%d }", sp->hdr.serial, abort_code); conn->error = -ECONNABORTED; conn->abort_code = abort_code; diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index bdf70b81addc..646ee61af40e 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -551,9 +551,6 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) atomic64_read(&call->ackr_window), call->rx_highest_seq, skb->len, seq0); - _proto("Rx DATA %%%u { #%u f=%02x }", - sp->hdr.serial, seq0, sp->hdr.flags); - state = READ_ONCE(call->state); if (state >= RXRPC_CALL_COMPLETE) { rxrpc_free_skb(skb, rxrpc_skb_freed); @@ -708,11 +705,6 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, bool wake = false; u32 rwind = ntohl(ackinfo->rwind); - _proto("Rx ACK %%%u Info { rx=%u max=%u rwin=%u jm=%u }", - sp->hdr.serial, - ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU), - rwind, ntohl(ackinfo->jumbo_max)); - if (rwind > RXRPC_TX_MAX_WINDOW) rwind = RXRPC_TX_MAX_WINDOW; if (call->tx_winsize != rwind) { @@ -855,7 +847,6 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) } if (ack.reason == RXRPC_ACK_PING) { - _proto("Rx ACK %%%u PING Request", ack_serial); rxrpc_send_ACK(call, RXRPC_ACK_PING_RESPONSE, ack_serial, rxrpc_propose_ack_respond_to_ping); } else if (sp->hdr.flags & RXRPC_REQUEST_ACK) { @@ -1014,9 +1005,6 @@ out_not_locked: static void rxrpc_input_ackall(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_ack_summary summary = { 0 }; - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - - _proto("Rx ACKALL %%%u", sp->hdr.serial); spin_lock(&call->input_lock); @@ -1044,8 +1032,6 @@ static void rxrpc_input_abort(struct rxrpc_call *call, struct sk_buff *skb) trace_rxrpc_rx_abort(call, sp->hdr.serial, abort_code); - _proto("Rx ABORT %%%u { %x }", sp->hdr.serial, abort_code); - rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED, abort_code, -ECONNABORTED); } @@ -1081,8 +1067,6 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call, goto no_free; case RXRPC_PACKET_TYPE_BUSY: - _proto("Rx BUSY %%%u", sp->hdr.serial); - /* Just ignore BUSY packets from the server; the retry and * lifespan timers will take care of business. BUSY packets * from the client don't make sense. @@ -1325,7 +1309,6 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) goto discard; default: - _proto("Rx Bad Packet Type %u", sp->hdr.type); goto bad_message; } diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c index 19e929c7c38b..f23a3fbabbda 100644 --- a/net/rxrpc/local_event.c +++ b/net/rxrpc/local_event.c @@ -63,8 +63,6 @@ static void rxrpc_send_version_request(struct rxrpc_local *local, len = iov[0].iov_len + iov[1].iov_len; - _proto("Tx VERSION (reply)"); - ret = kernel_sendmsg(local->socket, &msg, iov, 2, len); if (ret < 0) trace_rxrpc_tx_fail(local->debug_id, 0, ret, @@ -98,7 +96,6 @@ void rxrpc_process_local_events(struct rxrpc_local *local) if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header), &v, 1) < 0) return; - _proto("Rx VERSION { %02x }", v); if (v == 0) rxrpc_send_version_request(local, &sp->hdr, skb); break; diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index c5eed0e83e47..635acf3dbd77 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -701,8 +701,6 @@ void rxrpc_send_keepalive(struct rxrpc_peer *peer) len = iov[0].iov_len + iov[1].iov_len; - _proto("Tx VERSION (keepalive)"); - iov_iter_kvec(&msg.msg_iter, WRITE, iov, 2, len); ret = do_udp_sendmsg(peer->local->socket, &msg, len); if (ret < 0) diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index cda3890657a9..be781c156e89 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -253,15 +253,12 @@ static void rxrpc_store_error(struct rxrpc_peer *peer, break; default: - _proto("Rx Received ICMP error { type=%u code=%u }", - ee->ee_type, ee->ee_code); break; } break; case SO_EE_ORIGIN_NONE: case SO_EE_ORIGIN_LOCAL: - _proto("Rx Received local error { error=%d }", err); compl = RXRPC_CALL_LOCAL_ERROR; break; @@ -270,7 +267,6 @@ static void rxrpc_store_error(struct rxrpc_peer *peer, err = EHOSTUNREACH; fallthrough; default: - _proto("Rx Received error report { orig=%u }", ee->ee_origin); break; } diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 110a5550c0a6..36cf40442a7e 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -704,7 +704,6 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn) serial = atomic_inc_return(&conn->serial); whdr.serial = htonl(serial); - _proto("Tx CHALLENGE %%%u", serial); ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); if (ret < 0) { @@ -762,7 +761,6 @@ static int rxkad_send_response(struct rxrpc_connection *conn, serial = atomic_inc_return(&conn->serial); whdr.serial = htonl(serial); - _proto("Tx RESPONSE %%%u", serial); ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 3, len); if (ret < 0) { @@ -856,8 +854,7 @@ static int rxkad_respond_to_challenge(struct rxrpc_connection *conn, nonce = ntohl(challenge.nonce); min_level = ntohl(challenge.min_level); - _proto("Rx CHALLENGE %%%u { v=%u n=%u ml=%u }", - sp->hdr.serial, version, nonce, min_level); + trace_rxrpc_rx_challenge(conn, sp->hdr.serial, version, nonce, min_level); eproto = tracepoint_string("chall_ver"); abort_code = RXKADINCONSISTENCY; @@ -1139,8 +1136,8 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, version = ntohl(response->version); ticket_len = ntohl(response->ticket_len); kvno = ntohl(response->kvno); - _proto("Rx RESPONSE %%%u { v=%u kv=%u tl=%u }", - sp->hdr.serial, version, kvno, ticket_len); + + trace_rxrpc_rx_response(conn, sp->hdr.serial, version, kvno, ticket_len); eproto = tracepoint_string("rxkad_rsp_ver"); abort_code = RXKADINCONSISTENCY; -- cgit v1.2.3 From 0fde882fc9ee9cc2e66e8c5a5a93c83932d7ca95 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 21 Oct 2022 13:00:34 +0100 Subject: rxrpc: trace: Don't use __builtin_return_address for rxrpc_local tracing In rxrpc tracing, use enums to generate lists of points of interest rather than __builtin_return_address() for the rxrpc_local tracepoint Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 49 ++++++++++++++++++++-------- net/rxrpc/af_rxrpc.c | 8 ++--- net/rxrpc/ar-internal.h | 41 ++++++++++++++++++----- net/rxrpc/call_accept.c | 4 +-- net/rxrpc/call_event.c | 2 +- net/rxrpc/conn_client.c | 2 +- net/rxrpc/conn_event.c | 4 +-- net/rxrpc/conn_object.c | 2 +- net/rxrpc/input.c | 4 +-- net/rxrpc/local_object.c | 78 ++++++++++++++++++++++++-------------------- net/rxrpc/output.c | 3 +- net/rxrpc/peer_event.c | 4 +-- net/rxrpc/peer_object.c | 4 +-- 13 files changed, 129 insertions(+), 76 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 2b77f9a75bf7..015569845b1d 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -32,12 +32,35 @@ E_(rxrpc_skb_unshared_nomem, "US0") #define rxrpc_local_traces \ - EM(rxrpc_local_got, "GOT") \ - EM(rxrpc_local_new, "NEW") \ - EM(rxrpc_local_processing, "PRO") \ - EM(rxrpc_local_put, "PUT") \ - EM(rxrpc_local_queued, "QUE") \ - E_(rxrpc_local_tx_ack, "TAK") + EM(rxrpc_local_free, "FREE ") \ + EM(rxrpc_local_get_client_conn, "GET conn-cln") \ + EM(rxrpc_local_get_for_use, "GET for-use ") \ + EM(rxrpc_local_get_peer, "GET peer ") \ + EM(rxrpc_local_get_prealloc_conn, "GET conn-pre") \ + EM(rxrpc_local_get_queue, "GET queue ") \ + EM(rxrpc_local_new, "NEW ") \ + EM(rxrpc_local_processing, "PROCESSING ") \ + EM(rxrpc_local_put_already_queued, "PUT alreadyq") \ + EM(rxrpc_local_put_bind, "PUT bind ") \ + EM(rxrpc_local_put_for_use, "PUT for-use ") \ + EM(rxrpc_local_put_kill_conn, "PUT conn-kil") \ + EM(rxrpc_local_put_peer, "PUT peer ") \ + EM(rxrpc_local_put_prealloc_conn, "PUT conn-pre") \ + EM(rxrpc_local_put_release_sock, "PUT rel-sock") \ + EM(rxrpc_local_put_queue, "PUT queue ") \ + EM(rxrpc_local_queued, "QUEUED ") \ + EM(rxrpc_local_see_tx_ack, "SEE tx-ack ") \ + EM(rxrpc_local_stop, "STOP ") \ + EM(rxrpc_local_stopped, "STOPPED ") \ + EM(rxrpc_local_unuse_bind, "UNU bind ") \ + EM(rxrpc_local_unuse_conn_work, "UNU conn-wrk") \ + EM(rxrpc_local_unuse_peer_keepalive, "UNU peer-kpa") \ + EM(rxrpc_local_unuse_release_sock, "UNU rel-sock") \ + EM(rxrpc_local_unuse_work, "UNU work ") \ + EM(rxrpc_local_use_conn_work, "USE conn-wrk") \ + EM(rxrpc_local_use_lookup, "USE lookup ") \ + EM(rxrpc_local_use_peer_keepalive, "USE peer-kpa") \ + E_(rxrpc_local_use_work, "USE work ") #define rxrpc_peer_traces \ EM(rxrpc_peer_got, "GOT") \ @@ -345,29 +368,29 @@ rxrpc_txqueue_traces; TRACE_EVENT(rxrpc_local, TP_PROTO(unsigned int local_debug_id, enum rxrpc_local_trace op, - int usage, const void *where), + int ref, int usage), - TP_ARGS(local_debug_id, op, usage, where), + TP_ARGS(local_debug_id, op, ref, usage), TP_STRUCT__entry( __field(unsigned int, local ) __field(int, op ) + __field(int, ref ) __field(int, usage ) - __field(const void *, where ) ), TP_fast_assign( __entry->local = local_debug_id; __entry->op = op; + __entry->ref = ref; __entry->usage = usage; - __entry->where = where; ), - TP_printk("L=%08x %s u=%d sp=%pSR", + TP_printk("L=%08x %s r=%d u=%d", __entry->local, __print_symbolic(__entry->op, rxrpc_local_traces), - __entry->usage, - __entry->where) + __entry->ref, + __entry->usage) ); TRACE_EVENT(rxrpc_peer, diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index aacdd96a9886..989ebca899f3 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -194,8 +194,8 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len) service_in_use: write_unlock(&local->services_lock); - rxrpc_unuse_local(local); - rxrpc_put_local(local); + rxrpc_unuse_local(local, rxrpc_local_unuse_bind); + rxrpc_put_local(local, rxrpc_local_put_bind); ret = -EADDRINUSE; error_unlock: release_sock(&rx->sk); @@ -888,8 +888,8 @@ static int rxrpc_release_sock(struct sock *sk) flush_workqueue(rxrpc_workqueue); rxrpc_purge_queue(&sk->sk_receive_queue); - rxrpc_unuse_local(rx->local); - rxrpc_put_local(rx->local); + rxrpc_unuse_local(rx->local, rxrpc_local_unuse_release_sock); + rxrpc_put_local(rx->local, rxrpc_local_put_release_sock); rx->local = NULL; key_put(rx->key); rx->key = NULL; diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 7c48b0163032..dde9ce21ef48 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -979,22 +979,45 @@ extern void rxrpc_process_local_events(struct rxrpc_local *); * local_object.c */ struct rxrpc_local *rxrpc_lookup_local(struct net *, const struct sockaddr_rxrpc *); -struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *); -struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *); -void rxrpc_put_local(struct rxrpc_local *); -struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *); -void rxrpc_unuse_local(struct rxrpc_local *); +struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *, enum rxrpc_local_trace); +struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *, enum rxrpc_local_trace); +void rxrpc_put_local(struct rxrpc_local *, enum rxrpc_local_trace); +struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *, enum rxrpc_local_trace); +void rxrpc_unuse_local(struct rxrpc_local *, enum rxrpc_local_trace); void rxrpc_queue_local(struct rxrpc_local *); void rxrpc_destroy_all_locals(struct rxrpc_net *); -static inline bool __rxrpc_unuse_local(struct rxrpc_local *local) +static inline bool __rxrpc_unuse_local(struct rxrpc_local *local, + enum rxrpc_local_trace why) { - return atomic_dec_return(&local->active_users) == 0; + unsigned int debug_id = local->debug_id; + int r, u; + + r = refcount_read(&local->ref); + u = atomic_dec_return(&local->active_users); + trace_rxrpc_local(debug_id, why, r, u); + return u == 0; +} + +static inline bool __rxrpc_use_local(struct rxrpc_local *local, + enum rxrpc_local_trace why) +{ + int r, u; + + r = refcount_read(&local->ref); + u = atomic_fetch_add_unless(&local->active_users, 1, 0); + trace_rxrpc_local(local->debug_id, why, r, u); + return u != 0; } -static inline bool __rxrpc_use_local(struct rxrpc_local *local) +static inline void rxrpc_see_local(struct rxrpc_local *local, + enum rxrpc_local_trace why) { - return atomic_fetch_add_unless(&local->active_users, 1, 0) != 0; + int r, u; + + r = refcount_read(&local->ref); + u = atomic_read(&local->active_users); + trace_rxrpc_local(local->debug_id, why, r, u); } /* diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 4888959e4727..1b12d4e28373 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -197,7 +197,7 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx) tail = b->peer_backlog_tail; while (CIRC_CNT(head, tail, size) > 0) { struct rxrpc_peer *peer = b->peer_backlog[tail]; - rxrpc_put_local(peer->local); + rxrpc_put_local(peer->local, rxrpc_local_put_prealloc_conn); kfree(peer); tail = (tail + 1) & (size - 1); } @@ -305,7 +305,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, b->conn_backlog[conn_tail] = NULL; smp_store_release(&b->conn_backlog_tail, (conn_tail + 1) & (RXRPC_BACKLOG_MAX - 1)); - conn->local = rxrpc_get_local(local); + conn->local = rxrpc_get_local(local, rxrpc_local_get_prealloc_conn); conn->peer = peer; rxrpc_see_connection(conn); rxrpc_new_incoming_connection(rx, conn, sec, skb); diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index b17ed37434bd..591af8e2e3d0 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -114,7 +114,7 @@ void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason, if (in_task()) { rxrpc_transmit_ack_packets(call->peer->local); } else { - rxrpc_get_local(local); + rxrpc_get_local(local, rxrpc_local_get_queue); rxrpc_queue_local(local); } } diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 71404b33623f..9a69b4c1b182 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -208,7 +208,7 @@ rxrpc_alloc_client_connection(struct rxrpc_bundle *bundle, gfp_t gfp) rxrpc_get_bundle(bundle); rxrpc_get_peer(conn->peer); - rxrpc_get_local(conn->local); + rxrpc_get_local(conn->local, rxrpc_local_get_client_conn); key_get(conn->key); trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_client, diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index f890a30c4df6..225edaf019f1 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -474,9 +474,9 @@ void rxrpc_process_connection(struct work_struct *work) rxrpc_see_connection(conn); - if (__rxrpc_use_local(conn->local)) { + if (__rxrpc_use_local(conn->local, rxrpc_local_use_conn_work)) { rxrpc_do_process_connection(conn); - rxrpc_unuse_local(conn->local); + rxrpc_unuse_local(conn->local, rxrpc_local_unuse_conn_work); } rxrpc_put_connection(conn); diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index ad6e5ee1f069..725359afeac0 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -366,7 +366,7 @@ static void rxrpc_destroy_connection(struct rcu_head *rcu) if (atomic_dec_and_test(&conn->local->rxnet->nr_conns)) wake_up_var(&conn->local->rxnet->nr_conns); - rxrpc_put_local(conn->local); + rxrpc_put_local(conn->local, rxrpc_local_put_kill_conn); kfree(conn); _leave(""); diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 42c8257158f7..cecfd201d832 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -1133,7 +1133,7 @@ static void rxrpc_post_packet_to_local(struct rxrpc_local *local, { _enter("%p,%p", local, skb); - if (rxrpc_get_local_maybe(local)) { + if (rxrpc_get_local_maybe(local, rxrpc_local_get_queue)) { skb_queue_tail(&local->event_queue, skb); rxrpc_queue_local(local); } else { @@ -1146,7 +1146,7 @@ static void rxrpc_post_packet_to_local(struct rxrpc_local *local, */ static void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) { - if (rxrpc_get_local_maybe(local)) { + if (rxrpc_get_local_maybe(local, rxrpc_local_get_queue)) { skb_queue_tail(&local->reject_queue, skb); rxrpc_queue_local(local); } else { diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 11080c335d42..1617ce651b9b 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -110,7 +110,7 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet, local->debug_id = atomic_inc_return(&rxrpc_debug_id); memcpy(&local->srx, srx, sizeof(*srx)); local->srx.srx_service = 0; - trace_rxrpc_local(local->debug_id, rxrpc_local_new, 1, NULL); + trace_rxrpc_local(local->debug_id, rxrpc_local_new, 1, 1); } _leave(" = %p", local); @@ -228,7 +228,7 @@ struct rxrpc_local *rxrpc_lookup_local(struct net *net, * we're attempting to use a local address that the dying * object is still using. */ - if (!rxrpc_use_local(local)) + if (!rxrpc_use_local(local, rxrpc_local_use_lookup)) break; goto found; @@ -272,32 +272,32 @@ addr_in_use: /* * Get a ref on a local endpoint. */ -struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *local) +struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *local, + enum rxrpc_local_trace why) { - const void *here = __builtin_return_address(0); - int r; + int r, u; + u = atomic_read(&local->active_users); __refcount_inc(&local->ref, &r); - trace_rxrpc_local(local->debug_id, rxrpc_local_got, r + 1, here); + trace_rxrpc_local(local->debug_id, why, r + 1, u); return local; } /* * Get a ref on a local endpoint unless its usage has already reached 0. */ -struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local) +struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local, + enum rxrpc_local_trace why) { - const void *here = __builtin_return_address(0); - int r; + int r, u; - if (local) { - if (__refcount_inc_not_zero(&local->ref, &r)) - trace_rxrpc_local(local->debug_id, rxrpc_local_got, - r + 1, here); - else - local = NULL; + if (local && __refcount_inc_not_zero(&local->ref, &r)) { + u = atomic_read(&local->active_users); + trace_rxrpc_local(local->debug_id, why, r + 1, u); + return local; } - return local; + + return NULL; } /* @@ -305,31 +305,31 @@ struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local) */ void rxrpc_queue_local(struct rxrpc_local *local) { - const void *here = __builtin_return_address(0); unsigned int debug_id = local->debug_id; int r = refcount_read(&local->ref); + int u = atomic_read(&local->active_users); if (rxrpc_queue_work(&local->processor)) - trace_rxrpc_local(debug_id, rxrpc_local_queued, r + 1, here); + trace_rxrpc_local(debug_id, rxrpc_local_queued, r, u); else - rxrpc_put_local(local); + rxrpc_put_local(local, rxrpc_local_put_already_queued); } /* * Drop a ref on a local endpoint. */ -void rxrpc_put_local(struct rxrpc_local *local) +void rxrpc_put_local(struct rxrpc_local *local, enum rxrpc_local_trace why) { - const void *here = __builtin_return_address(0); unsigned int debug_id; bool dead; - int r; + int r, u; if (local) { debug_id = local->debug_id; + u = atomic_read(&local->active_users); dead = __refcount_dec_and_test(&local->ref, &r); - trace_rxrpc_local(debug_id, rxrpc_local_put, r, here); + trace_rxrpc_local(debug_id, why, r, u); if (dead) call_rcu(&local->rcu, rxrpc_local_rcu); @@ -339,14 +339,15 @@ void rxrpc_put_local(struct rxrpc_local *local) /* * Start using a local endpoint. */ -struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *local) +struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *local, + enum rxrpc_local_trace why) { - local = rxrpc_get_local_maybe(local); + local = rxrpc_get_local_maybe(local, rxrpc_local_get_for_use); if (!local) return NULL; - if (!__rxrpc_use_local(local)) { - rxrpc_put_local(local); + if (!__rxrpc_use_local(local, why)) { + rxrpc_put_local(local, rxrpc_local_put_for_use); return NULL; } @@ -357,11 +358,18 @@ struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *local) * Cease using a local endpoint. Once the number of active users reaches 0, we * start the closure of the transport in the work processor. */ -void rxrpc_unuse_local(struct rxrpc_local *local) +void rxrpc_unuse_local(struct rxrpc_local *local, enum rxrpc_local_trace why) { + unsigned int debug_id; + int r, u; + if (local) { - if (__rxrpc_unuse_local(local)) { - rxrpc_get_local(local); + debug_id = local->debug_id; + r = refcount_read(&local->ref); + u = atomic_dec_return(&local->active_users); + trace_rxrpc_local(debug_id, why, r, u); + if (u == 0) { + rxrpc_get_local(local, rxrpc_local_get_queue); rxrpc_queue_local(local); } } @@ -418,12 +426,11 @@ static void rxrpc_local_processor(struct work_struct *work) if (local->dead) return; - trace_rxrpc_local(local->debug_id, rxrpc_local_processing, - refcount_read(&local->ref), NULL); + rxrpc_see_local(local, rxrpc_local_processing); do { again = false; - if (!__rxrpc_use_local(local)) { + if (!__rxrpc_use_local(local, rxrpc_local_use_work)) { rxrpc_local_destroyer(local); break; } @@ -443,10 +450,10 @@ static void rxrpc_local_processor(struct work_struct *work) again = true; } - __rxrpc_unuse_local(local); + __rxrpc_unuse_local(local, rxrpc_local_unuse_work); } while (again); - rxrpc_put_local(local); + rxrpc_put_local(local, rxrpc_local_put_queue); } /* @@ -460,6 +467,7 @@ static void rxrpc_local_rcu(struct rcu_head *rcu) ASSERT(!work_pending(&local->processor)); + rxrpc_see_local(local, rxrpc_local_free); kfree(local); _leave(""); } diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index b5d8eac8c49c..2762b7ada9ae 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -288,8 +288,7 @@ void rxrpc_transmit_ack_packets(struct rxrpc_local *local) LIST_HEAD(queue); int ret; - trace_rxrpc_local(local->debug_id, rxrpc_local_tx_ack, - refcount_read(&local->ref), NULL); + rxrpc_see_local(local, rxrpc_local_see_tx_ack); if (list_empty(&local->ack_tx_queue)) return; diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index ad4d1769e02b..3f8d104ecaa7 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -266,7 +266,7 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet, if (!rxrpc_get_peer_maybe(peer)) continue; - if (__rxrpc_use_local(peer->local)) { + if (__rxrpc_use_local(peer->local, rxrpc_local_use_peer_keepalive)) { spin_unlock_bh(&rxnet->peer_hash_lock); keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME; @@ -289,7 +289,7 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet, spin_lock_bh(&rxnet->peer_hash_lock); list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive[slot & mask]); - rxrpc_unuse_local(peer->local); + rxrpc_unuse_local(peer->local, rxrpc_local_unuse_peer_keepalive); } rxrpc_put_peer_locked(peer); } diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index b3c3c1c344fc..bcef897560e7 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -215,7 +215,7 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp) peer = kzalloc(sizeof(struct rxrpc_peer), gfp); if (peer) { refcount_set(&peer->ref, 1); - peer->local = rxrpc_get_local(local); + peer->local = rxrpc_get_local(local, rxrpc_local_get_peer); INIT_HLIST_HEAD(&peer->error_targets); peer->service_conns = RB_ROOT; seqlock_init(&peer->service_conn_lock); @@ -294,7 +294,7 @@ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_sock *rx, static void rxrpc_free_peer(struct rxrpc_peer *peer) { - rxrpc_put_local(peer->local); + rxrpc_put_local(peer->local, rxrpc_local_put_peer); kfree_rcu(peer, rcu); } -- cgit v1.2.3 From 47c810a79844462d3468d831edc00971757693e0 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 21 Oct 2022 13:39:34 +0100 Subject: rxrpc: trace: Don't use __builtin_return_address for rxrpc_peer tracing In rxrpc tracing, use enums to generate lists of points of interest rather than __builtin_return_address() for the rxrpc_peer tracepoint Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 43 ++++++++++++++++++++++++++----------------- net/rxrpc/af_rxrpc.c | 2 +- net/rxrpc/ar-internal.h | 11 ++++++----- net/rxrpc/call_accept.c | 8 +++++--- net/rxrpc/call_object.c | 2 +- net/rxrpc/conn_client.c | 8 ++++---- net/rxrpc/conn_object.c | 2 +- net/rxrpc/peer_event.c | 8 ++++---- net/rxrpc/peer_object.c | 34 ++++++++++++++++------------------ net/rxrpc/sendmsg.c | 2 +- 10 files changed, 65 insertions(+), 55 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 015569845b1d..1c74143a51c1 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -63,10 +63,23 @@ E_(rxrpc_local_use_work, "USE work ") #define rxrpc_peer_traces \ - EM(rxrpc_peer_got, "GOT") \ - EM(rxrpc_peer_new, "NEW") \ - EM(rxrpc_peer_processing, "PRO") \ - E_(rxrpc_peer_put, "PUT") + EM(rxrpc_peer_free, "FREE ") \ + EM(rxrpc_peer_get_accept, "GET accept ") \ + EM(rxrpc_peer_get_activate_call, "GET act-call") \ + EM(rxrpc_peer_get_bundle, "GET bundle ") \ + EM(rxrpc_peer_get_client_conn, "GET cln-conn") \ + EM(rxrpc_peer_get_input_error, "GET inpt-err") \ + EM(rxrpc_peer_get_keepalive, "GET keepaliv") \ + EM(rxrpc_peer_get_lookup_client, "GET look-cln") \ + EM(rxrpc_peer_get_service_conn, "GET srv-conn") \ + EM(rxrpc_peer_new_client, "NEW client ") \ + EM(rxrpc_peer_new_prealloc, "NEW prealloc") \ + EM(rxrpc_peer_put_bundle, "PUT bundle ") \ + EM(rxrpc_peer_put_call, "PUT call ") \ + EM(rxrpc_peer_put_conn, "PUT conn ") \ + EM(rxrpc_peer_put_discard_tmp, "PUT disc-tmp") \ + EM(rxrpc_peer_put_input_error, "PUT inpt-err") \ + E_(rxrpc_peer_put_keepalive, "PUT keepaliv") #define rxrpc_conn_traces \ EM(rxrpc_conn_got, "GOT") \ @@ -394,30 +407,26 @@ TRACE_EVENT(rxrpc_local, ); TRACE_EVENT(rxrpc_peer, - TP_PROTO(unsigned int peer_debug_id, enum rxrpc_peer_trace op, - int usage, const void *where), + TP_PROTO(unsigned int peer_debug_id, int ref, enum rxrpc_peer_trace why), - TP_ARGS(peer_debug_id, op, usage, where), + TP_ARGS(peer_debug_id, ref, why), TP_STRUCT__entry( __field(unsigned int, peer ) - __field(int, op ) - __field(int, usage ) - __field(const void *, where ) + __field(int, ref ) + __field(int, why ) ), TP_fast_assign( __entry->peer = peer_debug_id; - __entry->op = op; - __entry->usage = usage; - __entry->where = where; + __entry->ref = ref; + __entry->why = why; ), - TP_printk("P=%08x %s u=%d sp=%pSR", + TP_printk("P=%08x %s r=%d", __entry->peer, - __print_symbolic(__entry->op, rxrpc_peer_traces), - __entry->usage, - __entry->where) + __print_symbolic(__entry->why, rxrpc_peer_traces), + __entry->ref) ); TRACE_EVENT(rxrpc_conn, diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 989ebca899f3..7a0dc01741e7 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -328,7 +328,7 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, mutex_unlock(&call->user_mutex); } - rxrpc_put_peer(cp.peer); + rxrpc_put_peer(cp.peer, rxrpc_peer_put_discard_tmp); _leave(" = %p", call); return call; } diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index dde9ce21ef48..6cb111e9761c 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -1063,14 +1063,15 @@ struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *, const struct sockaddr_rxrpc *); struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *, struct rxrpc_local *, struct sockaddr_rxrpc *, gfp_t); -struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *, gfp_t); +struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *, gfp_t, + enum rxrpc_peer_trace); void rxrpc_new_incoming_peer(struct rxrpc_sock *, struct rxrpc_local *, struct rxrpc_peer *); void rxrpc_destroy_all_peers(struct rxrpc_net *); -struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *); -struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *); -void rxrpc_put_peer(struct rxrpc_peer *); -void rxrpc_put_peer_locked(struct rxrpc_peer *); +struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *, enum rxrpc_peer_trace); +struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *, enum rxrpc_peer_trace); +void rxrpc_put_peer(struct rxrpc_peer *, enum rxrpc_peer_trace); +void rxrpc_put_peer_locked(struct rxrpc_peer *, enum rxrpc_peer_trace); /* * proc.c diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 1b12d4e28373..f6bc3b07c3e5 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -70,7 +70,9 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, head = b->peer_backlog_head; tail = READ_ONCE(b->peer_backlog_tail); if (CIRC_CNT(head, tail, size) < max) { - struct rxrpc_peer *peer = rxrpc_alloc_peer(rx->local, gfp); + struct rxrpc_peer *peer; + + peer = rxrpc_alloc_peer(rx->local, gfp, rxrpc_peer_new_prealloc); if (!peer) return -ENOMEM; b->peer_backlog[head] = peer; @@ -286,7 +288,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, return NULL; if (!conn) { - if (peer && !rxrpc_get_peer_maybe(peer)) + if (peer && !rxrpc_get_peer_maybe(peer, rxrpc_peer_get_service_conn)) peer = NULL; if (!peer) { peer = b->peer_backlog[peer_tail]; @@ -323,7 +325,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, call->conn = conn; call->security = conn->security; call->security_ix = conn->security_ix; - call->peer = rxrpc_get_peer(conn->peer); + call->peer = rxrpc_get_peer(conn->peer, rxrpc_peer_get_accept); call->cong_ssthresh = call->peer->cong_ssthresh; call->tx_last_sent = ktime_get_real(); return call; diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 59928f0a8fe1..1b725afd6e2c 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -636,7 +636,7 @@ static void rxrpc_destroy_call(struct work_struct *work) rxrpc_delete_call_timer(call); rxrpc_put_connection(call->conn); - rxrpc_put_peer(call->peer); + rxrpc_put_peer(call->peer, rxrpc_peer_put_call); kmem_cache_free(rxrpc_call_jar, call); if (atomic_dec_and_test(&rxnet->nr_calls)) wake_up_var(&rxnet->nr_calls); diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 9a69b4c1b182..9444da235a48 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -123,7 +123,7 @@ static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_conn_parameters *cp, bundle = kzalloc(sizeof(*bundle), gfp); if (bundle) { bundle->local = cp->local; - bundle->peer = rxrpc_get_peer(cp->peer); + bundle->peer = rxrpc_get_peer(cp->peer, rxrpc_peer_get_bundle); bundle->key = cp->key; bundle->exclusive = cp->exclusive; bundle->upgrade = cp->upgrade; @@ -145,7 +145,7 @@ struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *bundle) static void rxrpc_free_bundle(struct rxrpc_bundle *bundle) { - rxrpc_put_peer(bundle->peer); + rxrpc_put_peer(bundle->peer, rxrpc_peer_put_bundle); kfree(bundle); } @@ -207,7 +207,7 @@ rxrpc_alloc_client_connection(struct rxrpc_bundle *bundle, gfp_t gfp) write_unlock(&rxnet->conn_lock); rxrpc_get_bundle(bundle); - rxrpc_get_peer(conn->peer); + rxrpc_get_peer(conn->peer, rxrpc_peer_get_client_conn); rxrpc_get_local(conn->local, rxrpc_local_get_client_conn); key_get(conn->key); @@ -543,7 +543,7 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn, rxrpc_see_call(call); list_del_init(&call->chan_wait_link); - call->peer = rxrpc_get_peer(conn->peer); + call->peer = rxrpc_get_peer(conn->peer, rxrpc_peer_get_activate_call); call->conn = rxrpc_get_connection(conn); call->cid = conn->proto.cid | channel; call->call_id = call_id; diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 725359afeac0..554ee5dd3325 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -362,7 +362,7 @@ static void rxrpc_destroy_connection(struct rcu_head *rcu) conn->security->clear(conn); key_put(conn->key); rxrpc_put_bundle(conn->bundle); - rxrpc_put_peer(conn->peer); + rxrpc_put_peer(conn->peer, rxrpc_peer_put_conn); if (atomic_dec_and_test(&conn->local->rxnet->nr_conns)) wake_up_var(&conn->local->rxnet->nr_conns); diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index 3f8d104ecaa7..5e97d321ac38 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -168,7 +168,7 @@ void rxrpc_error_report(struct sock *sk) } peer = rxrpc_lookup_peer_local_rcu(local, skb, &srx); - if (peer && !rxrpc_get_peer_maybe(peer)) + if (peer && !rxrpc_get_peer_maybe(peer, rxrpc_peer_get_input_error)) peer = NULL; if (!peer) { rcu_read_unlock(); @@ -190,7 +190,7 @@ void rxrpc_error_report(struct sock *sk) out: rcu_read_unlock(); rxrpc_free_skb(skb, rxrpc_skb_freed); - rxrpc_put_peer(peer); + rxrpc_put_peer(peer, rxrpc_peer_put_input_error); _leave(""); } @@ -263,7 +263,7 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet, struct rxrpc_peer, keepalive_link); list_del_init(&peer->keepalive_link); - if (!rxrpc_get_peer_maybe(peer)) + if (!rxrpc_get_peer_maybe(peer, rxrpc_peer_get_keepalive)) continue; if (__rxrpc_use_local(peer->local, rxrpc_local_use_peer_keepalive)) { @@ -291,7 +291,7 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet, &rxnet->peer_keepalive[slot & mask]); rxrpc_unuse_local(peer->local, rxrpc_local_unuse_peer_keepalive); } - rxrpc_put_peer_locked(peer); + rxrpc_put_peer_locked(peer, rxrpc_peer_put_keepalive); } spin_unlock_bh(&rxnet->peer_hash_lock); diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index bcef897560e7..9e682a60a800 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -205,9 +205,9 @@ static void rxrpc_assess_MTU_size(struct rxrpc_sock *rx, /* * Allocate a peer. */ -struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp) +struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp, + enum rxrpc_peer_trace why) { - const void *here = __builtin_return_address(0); struct rxrpc_peer *peer; _enter(""); @@ -226,7 +226,7 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp) rxrpc_peer_init_rtt(peer); peer->cong_ssthresh = RXRPC_TX_MAX_WINDOW; - trace_rxrpc_peer(peer->debug_id, rxrpc_peer_new, 1, here); + trace_rxrpc_peer(peer->debug_id, why, 1); } _leave(" = %p", peer); @@ -282,7 +282,7 @@ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_sock *rx, _enter(""); - peer = rxrpc_alloc_peer(local, gfp); + peer = rxrpc_alloc_peer(local, gfp, rxrpc_peer_new_client); if (peer) { memcpy(&peer->srx, srx, sizeof(*srx)); rxrpc_init_peer(rx, peer, hash_key); @@ -294,6 +294,7 @@ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_sock *rx, static void rxrpc_free_peer(struct rxrpc_peer *peer) { + trace_rxrpc_peer(peer->debug_id, 0, rxrpc_peer_free); rxrpc_put_local(peer->local, rxrpc_local_put_peer); kfree_rcu(peer, rcu); } @@ -334,7 +335,7 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *rx, /* search the peer list first */ rcu_read_lock(); peer = __rxrpc_lookup_peer_rcu(local, srx, hash_key); - if (peer && !rxrpc_get_peer_maybe(peer)) + if (peer && !rxrpc_get_peer_maybe(peer, rxrpc_peer_get_lookup_client)) peer = NULL; rcu_read_unlock(); @@ -352,7 +353,7 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *rx, /* Need to check that we aren't racing with someone else */ peer = __rxrpc_lookup_peer_rcu(local, srx, hash_key); - if (peer && !rxrpc_get_peer_maybe(peer)) + if (peer && !rxrpc_get_peer_maybe(peer, rxrpc_peer_get_lookup_client)) peer = NULL; if (!peer) { hash_add_rcu(rxnet->peer_hash, @@ -376,27 +377,26 @@ struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_sock *rx, /* * Get a ref on a peer record. */ -struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *peer) +struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *peer, enum rxrpc_peer_trace why) { - const void *here = __builtin_return_address(0); int r; __refcount_inc(&peer->ref, &r); - trace_rxrpc_peer(peer->debug_id, rxrpc_peer_got, r + 1, here); + trace_rxrpc_peer(peer->debug_id, why, r + 1); return peer; } /* * Get a ref on a peer record unless its usage has already reached 0. */ -struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer) +struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer, + enum rxrpc_peer_trace why) { - const void *here = __builtin_return_address(0); int r; if (peer) { if (__refcount_inc_not_zero(&peer->ref, &r)) - trace_rxrpc_peer(peer->debug_id, rxrpc_peer_got, r + 1, here); + trace_rxrpc_peer(peer->debug_id, r + 1, why); else peer = NULL; } @@ -423,9 +423,8 @@ static void __rxrpc_put_peer(struct rxrpc_peer *peer) /* * Drop a ref on a peer record. */ -void rxrpc_put_peer(struct rxrpc_peer *peer) +void rxrpc_put_peer(struct rxrpc_peer *peer, enum rxrpc_peer_trace why) { - const void *here = __builtin_return_address(0); unsigned int debug_id; bool dead; int r; @@ -433,7 +432,7 @@ void rxrpc_put_peer(struct rxrpc_peer *peer) if (peer) { debug_id = peer->debug_id; dead = __refcount_dec_and_test(&peer->ref, &r); - trace_rxrpc_peer(debug_id, rxrpc_peer_put, r - 1, here); + trace_rxrpc_peer(debug_id, r - 1, why); if (dead) __rxrpc_put_peer(peer); } @@ -443,15 +442,14 @@ void rxrpc_put_peer(struct rxrpc_peer *peer) * Drop a ref on a peer record where the caller already holds the * peer_hash_lock. */ -void rxrpc_put_peer_locked(struct rxrpc_peer *peer) +void rxrpc_put_peer_locked(struct rxrpc_peer *peer, enum rxrpc_peer_trace why) { - const void *here = __builtin_return_address(0); unsigned int debug_id = peer->debug_id; bool dead; int r; dead = __refcount_dec_and_test(&peer->ref, &r); - trace_rxrpc_peer(debug_id, rxrpc_peer_put, r - 1, here); + trace_rxrpc_peer(debug_id, r - 1, why); if (dead) { hash_del_rcu(&peer->hash_link); list_del_init(&peer->keepalive_link); diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index e5fd8a95bf71..cfe0badba0b3 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -604,7 +604,7 @@ rxrpc_new_client_call_for_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, atomic_inc_return(&rxrpc_debug_id)); /* The socket is now unlocked */ - rxrpc_put_peer(cp.peer); + rxrpc_put_peer(cp.peer, rxrpc_peer_put_discard_tmp); _leave(" = %p\n", call); return call; } -- cgit v1.2.3 From 7fa25105b2d32fcb0f38668bc20d0adf6508322f Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 21 Oct 2022 14:06:16 +0100 Subject: rxrpc: trace: Don't use __builtin_return_address for rxrpc_conn tracing In rxrpc tracing, use enums to generate lists of points of interest rather than __builtin_return_address() for the rxrpc_conn tracepoint Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 58 ++++++++++++++++++++++++++++---------------- net/rxrpc/ar-internal.h | 21 +++++++++------- net/rxrpc/call_accept.c | 9 +++---- net/rxrpc/call_object.c | 2 +- net/rxrpc/conn_client.c | 28 ++++++++++----------- net/rxrpc/conn_event.c | 4 +-- net/rxrpc/conn_object.c | 40 +++++++++++++++--------------- net/rxrpc/conn_service.c | 4 +-- net/rxrpc/input.c | 2 +- 9 files changed, 92 insertions(+), 76 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 1c74143a51c1..e09568a8c173 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -82,14 +82,34 @@ E_(rxrpc_peer_put_keepalive, "PUT keepaliv") #define rxrpc_conn_traces \ - EM(rxrpc_conn_got, "GOT") \ - EM(rxrpc_conn_new_client, "NWc") \ - EM(rxrpc_conn_new_service, "NWs") \ - EM(rxrpc_conn_put_client, "PTc") \ - EM(rxrpc_conn_put_service, "PTs") \ - EM(rxrpc_conn_queued, "QUE") \ - EM(rxrpc_conn_reap_service, "RPs") \ - E_(rxrpc_conn_seen, "SEE") + EM(rxrpc_conn_free, "FREE ") \ + EM(rxrpc_conn_get_activate_call, "GET act-call") \ + EM(rxrpc_conn_get_call_input, "GET inp-call") \ + EM(rxrpc_conn_get_conn_input, "GET inp-conn") \ + EM(rxrpc_conn_get_idle, "GET idle ") \ + EM(rxrpc_conn_get_poke, "GET poke ") \ + EM(rxrpc_conn_get_service_conn, "GET svc-conn") \ + EM(rxrpc_conn_new_client, "NEW client ") \ + EM(rxrpc_conn_new_service, "NEW service ") \ + EM(rxrpc_conn_put_already_queued, "PUT alreadyq") \ + EM(rxrpc_conn_put_call, "PUT call ") \ + EM(rxrpc_conn_put_call_input, "PUT inp-call") \ + EM(rxrpc_conn_put_conn_input, "PUT inp-conn") \ + EM(rxrpc_conn_put_discard, "PUT discard ") \ + EM(rxrpc_conn_put_discard_idle, "PUT disc-idl") \ + EM(rxrpc_conn_put_local_dead, "PUT loc-dead") \ + EM(rxrpc_conn_put_noreuse, "PUT noreuse ") \ + EM(rxrpc_conn_put_poke, "PUT poke ") \ + EM(rxrpc_conn_put_unbundle, "PUT unbundle") \ + EM(rxrpc_conn_put_unidle, "PUT unidle ") \ + EM(rxrpc_conn_put_work, "PUT work ") \ + EM(rxrpc_conn_queue_challenge, "GQ chall ") \ + EM(rxrpc_conn_queue_retry_work, "GQ retry-wk") \ + EM(rxrpc_conn_queue_rx_work, "GQ rx-work ") \ + EM(rxrpc_conn_queue_timer, "GQ timer ") \ + EM(rxrpc_conn_see_new_service_conn, "SEE new-svc ") \ + EM(rxrpc_conn_see_reap_service, "SEE reap-svc") \ + E_(rxrpc_conn_see_work, "SEE work ") #define rxrpc_client_traces \ EM(rxrpc_client_activate_chans, "Activa") \ @@ -430,30 +450,26 @@ TRACE_EVENT(rxrpc_peer, ); TRACE_EVENT(rxrpc_conn, - TP_PROTO(unsigned int conn_debug_id, enum rxrpc_conn_trace op, - int usage, const void *where), + TP_PROTO(unsigned int conn_debug_id, int ref, enum rxrpc_conn_trace why), - TP_ARGS(conn_debug_id, op, usage, where), + TP_ARGS(conn_debug_id, ref, why), TP_STRUCT__entry( __field(unsigned int, conn ) - __field(int, op ) - __field(int, usage ) - __field(const void *, where ) + __field(int, ref ) + __field(int, why ) ), TP_fast_assign( __entry->conn = conn_debug_id; - __entry->op = op; - __entry->usage = usage; - __entry->where = where; + __entry->ref = ref; + __entry->why = why; ), - TP_printk("C=%08x %s u=%d sp=%pSR", + TP_printk("C=%08x %s r=%d", __entry->conn, - __print_symbolic(__entry->op, rxrpc_conn_traces), - __entry->usage, - __entry->where) + __print_symbolic(__entry->why, rxrpc_conn_traces), + __entry->ref) ); TRACE_EVENT(rxrpc_client, diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 6cb111e9761c..bc8281c410c5 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -882,7 +882,7 @@ int rxrpc_connect_call(struct rxrpc_sock *, struct rxrpc_call *, gfp_t); void rxrpc_expose_client_call(struct rxrpc_call *); void rxrpc_disconnect_client_call(struct rxrpc_bundle *, struct rxrpc_call *); -void rxrpc_put_client_conn(struct rxrpc_connection *); +void rxrpc_put_client_conn(struct rxrpc_connection *, enum rxrpc_conn_trace); void rxrpc_discard_expired_client_conns(struct work_struct *); void rxrpc_destroy_all_client_connections(struct rxrpc_net *); void rxrpc_clean_up_local_conns(struct rxrpc_local *); @@ -906,11 +906,13 @@ struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *, void __rxrpc_disconnect_call(struct rxrpc_connection *, struct rxrpc_call *); void rxrpc_disconnect_call(struct rxrpc_call *); void rxrpc_kill_connection(struct rxrpc_connection *); -bool rxrpc_queue_conn(struct rxrpc_connection *); -void rxrpc_see_connection(struct rxrpc_connection *); -struct rxrpc_connection *rxrpc_get_connection(struct rxrpc_connection *); -struct rxrpc_connection *rxrpc_get_connection_maybe(struct rxrpc_connection *); -void rxrpc_put_service_conn(struct rxrpc_connection *); +bool rxrpc_queue_conn(struct rxrpc_connection *, enum rxrpc_conn_trace); +void rxrpc_see_connection(struct rxrpc_connection *, enum rxrpc_conn_trace); +struct rxrpc_connection *rxrpc_get_connection(struct rxrpc_connection *, + enum rxrpc_conn_trace); +struct rxrpc_connection *rxrpc_get_connection_maybe(struct rxrpc_connection *, + enum rxrpc_conn_trace); +void rxrpc_put_service_conn(struct rxrpc_connection *, enum rxrpc_conn_trace); void rxrpc_service_connection_reaper(struct work_struct *); void rxrpc_destroy_all_connections(struct rxrpc_net *); @@ -924,15 +926,16 @@ static inline bool rxrpc_conn_is_service(const struct rxrpc_connection *conn) return !rxrpc_conn_is_client(conn); } -static inline void rxrpc_put_connection(struct rxrpc_connection *conn) +static inline void rxrpc_put_connection(struct rxrpc_connection *conn, + enum rxrpc_conn_trace why) { if (!conn) return; if (rxrpc_conn_is_client(conn)) - rxrpc_put_client_conn(conn); + rxrpc_put_client_conn(conn, why); else - rxrpc_put_service_conn(conn); + rxrpc_put_service_conn(conn, why); } static inline void rxrpc_reduce_conn_timer(struct rxrpc_connection *conn, diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index f6bc3b07c3e5..04b52e28e0cc 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -91,9 +91,6 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, b->conn_backlog[head] = conn; smp_store_release(&b->conn_backlog_head, (head + 1) & (size - 1)); - - trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_service, - refcount_read(&conn->ref), here); } /* Now it gets complicated, because calls get registered with the @@ -309,10 +306,10 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, (conn_tail + 1) & (RXRPC_BACKLOG_MAX - 1)); conn->local = rxrpc_get_local(local, rxrpc_local_get_prealloc_conn); conn->peer = peer; - rxrpc_see_connection(conn); + rxrpc_see_connection(conn, rxrpc_conn_see_new_service_conn); rxrpc_new_incoming_connection(rx, conn, sec, skb); } else { - rxrpc_get_connection(conn); + rxrpc_get_connection(conn, rxrpc_conn_get_service_conn); } /* And now we can allocate and set up a new call */ @@ -402,7 +399,7 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, case RXRPC_CONN_SERVICE_UNSECURED: conn->state = RXRPC_CONN_SERVICE_CHALLENGING; set_bit(RXRPC_CONN_EV_CHALLENGE, &call->conn->events); - rxrpc_queue_conn(call->conn); + rxrpc_queue_conn(call->conn, rxrpc_conn_queue_challenge); break; case RXRPC_CONN_SERVICE: diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 1b725afd6e2c..29ec4013aa0b 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -635,7 +635,7 @@ static void rxrpc_destroy_call(struct work_struct *work) rxrpc_delete_call_timer(call); - rxrpc_put_connection(call->conn); + rxrpc_put_connection(call->conn, rxrpc_conn_put_call); rxrpc_put_peer(call->peer, rxrpc_peer_put_call); kmem_cache_free(rxrpc_call_jar, call); if (atomic_dec_and_test(&rxnet->nr_calls)) diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 9444da235a48..dcfec6a45255 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -211,9 +211,8 @@ rxrpc_alloc_client_connection(struct rxrpc_bundle *bundle, gfp_t gfp) rxrpc_get_local(conn->local, rxrpc_local_get_client_conn); key_get(conn->key); - trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_client, - refcount_read(&conn->ref), - __builtin_return_address(0)); + trace_rxrpc_conn(conn->debug_id, refcount_read(&conn->ref), + rxrpc_conn_new_client); atomic_inc(&rxnet->nr_client_conns); trace_rxrpc_client(conn, -1, rxrpc_client_alloc); @@ -467,10 +466,10 @@ static void rxrpc_add_conn_to_bundle(struct rxrpc_bundle *bundle, gfp_t gfp) if (candidate) { _debug("discard C=%x", candidate->debug_id); trace_rxrpc_client(candidate, -1, rxrpc_client_duplicate); - rxrpc_put_connection(candidate); + rxrpc_put_connection(candidate, rxrpc_conn_put_discard); } - rxrpc_put_connection(old); + rxrpc_put_connection(old, rxrpc_conn_put_noreuse); _leave(""); } @@ -544,7 +543,7 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn, rxrpc_see_call(call); list_del_init(&call->chan_wait_link); call->peer = rxrpc_get_peer(conn->peer, rxrpc_peer_get_activate_call); - call->conn = rxrpc_get_connection(conn); + call->conn = rxrpc_get_connection(conn, rxrpc_conn_get_activate_call); call->cid = conn->proto.cid | channel; call->call_id = call_id; call->security = conn->security; @@ -592,7 +591,7 @@ static void rxrpc_unidle_conn(struct rxrpc_bundle *bundle, struct rxrpc_connecti } spin_unlock(&rxnet->client_conn_cache_lock); if (drop_ref) - rxrpc_put_connection(conn); + rxrpc_put_connection(conn, rxrpc_conn_put_unidle); } } @@ -896,7 +895,7 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call trace_rxrpc_client(conn, channel, rxrpc_client_to_idle); conn->idle_timestamp = jiffies; - rxrpc_get_connection(conn); + rxrpc_get_connection(conn, rxrpc_conn_get_idle); spin_lock(&rxnet->client_conn_cache_lock); list_move_tail(&conn->cache_link, &rxnet->idle_client_conns); spin_unlock(&rxnet->client_conn_cache_lock); @@ -938,7 +937,7 @@ static void rxrpc_unbundle_conn(struct rxrpc_connection *conn) if (need_drop) { rxrpc_deactivate_bundle(bundle); - rxrpc_put_connection(conn); + rxrpc_put_connection(conn, rxrpc_conn_put_unbundle); } } @@ -983,15 +982,15 @@ static void rxrpc_kill_client_conn(struct rxrpc_connection *conn) /* * Clean up a dead client connections. */ -void rxrpc_put_client_conn(struct rxrpc_connection *conn) +void rxrpc_put_client_conn(struct rxrpc_connection *conn, + enum rxrpc_conn_trace why) { - const void *here = __builtin_return_address(0); unsigned int debug_id = conn->debug_id; bool dead; int r; dead = __refcount_dec_and_test(&conn->ref, &r); - trace_rxrpc_conn(debug_id, rxrpc_conn_put_client, r - 1, here); + trace_rxrpc_conn(debug_id, r - 1, why); if (dead) rxrpc_kill_client_conn(conn); } @@ -1063,7 +1062,8 @@ next: spin_unlock(&rxnet->client_conn_cache_lock); rxrpc_unbundle_conn(conn); - rxrpc_put_connection(conn); /* Drop the ->cache_link ref */ + /* Drop the ->cache_link ref */ + rxrpc_put_connection(conn, rxrpc_conn_put_discard_idle); nr_conns--; goto next; @@ -1134,7 +1134,7 @@ void rxrpc_clean_up_local_conns(struct rxrpc_local *local) struct rxrpc_connection, cache_link); list_del_init(&conn->cache_link); rxrpc_unbundle_conn(conn); - rxrpc_put_connection(conn); + rxrpc_put_connection(conn, rxrpc_conn_put_local_dead); } _leave(" [culled]"); diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 225edaf019f1..817f895c77ca 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -472,14 +472,14 @@ void rxrpc_process_connection(struct work_struct *work) struct rxrpc_connection *conn = container_of(work, struct rxrpc_connection, processor); - rxrpc_see_connection(conn); + rxrpc_see_connection(conn, rxrpc_conn_see_work); if (__rxrpc_use_local(conn->local, rxrpc_local_use_conn_work)) { rxrpc_do_process_connection(conn); rxrpc_unuse_local(conn->local, rxrpc_local_unuse_conn_work); } - rxrpc_put_connection(conn); + rxrpc_put_connection(conn, rxrpc_conn_put_work); _leave(""); return; } diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 554ee5dd3325..bbace8d9953d 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -26,7 +26,7 @@ static void rxrpc_connection_timer(struct timer_list *timer) struct rxrpc_connection *conn = container_of(timer, struct rxrpc_connection, timer); - rxrpc_queue_conn(conn); + rxrpc_queue_conn(conn, rxrpc_conn_queue_timer); } /* @@ -260,43 +260,42 @@ void rxrpc_kill_connection(struct rxrpc_connection *conn) * Queue a connection's work processor, getting a ref to pass to the work * queue. */ -bool rxrpc_queue_conn(struct rxrpc_connection *conn) +bool rxrpc_queue_conn(struct rxrpc_connection *conn, enum rxrpc_conn_trace why) { - const void *here = __builtin_return_address(0); int r; if (!__refcount_inc_not_zero(&conn->ref, &r)) return false; if (rxrpc_queue_work(&conn->processor)) - trace_rxrpc_conn(conn->debug_id, rxrpc_conn_queued, r + 1, here); + trace_rxrpc_conn(conn->debug_id, why, r + 1); else - rxrpc_put_connection(conn); + rxrpc_put_connection(conn, rxrpc_conn_put_already_queued); return true; } /* * Note the re-emergence of a connection. */ -void rxrpc_see_connection(struct rxrpc_connection *conn) +void rxrpc_see_connection(struct rxrpc_connection *conn, + enum rxrpc_conn_trace why) { - const void *here = __builtin_return_address(0); if (conn) { - int n = refcount_read(&conn->ref); + int r = refcount_read(&conn->ref); - trace_rxrpc_conn(conn->debug_id, rxrpc_conn_seen, n, here); + trace_rxrpc_conn(conn->debug_id, r, why); } } /* * Get a ref on a connection. */ -struct rxrpc_connection *rxrpc_get_connection(struct rxrpc_connection *conn) +struct rxrpc_connection *rxrpc_get_connection(struct rxrpc_connection *conn, + enum rxrpc_conn_trace why) { - const void *here = __builtin_return_address(0); int r; __refcount_inc(&conn->ref, &r); - trace_rxrpc_conn(conn->debug_id, rxrpc_conn_got, r, here); + trace_rxrpc_conn(conn->debug_id, r + 1, why); return conn; } @@ -304,14 +303,14 @@ struct rxrpc_connection *rxrpc_get_connection(struct rxrpc_connection *conn) * Try to get a ref on a connection. */ struct rxrpc_connection * -rxrpc_get_connection_maybe(struct rxrpc_connection *conn) +rxrpc_get_connection_maybe(struct rxrpc_connection *conn, + enum rxrpc_conn_trace why) { - const void *here = __builtin_return_address(0); int r; if (conn) { if (__refcount_inc_not_zero(&conn->ref, &r)) - trace_rxrpc_conn(conn->debug_id, rxrpc_conn_got, r + 1, here); + trace_rxrpc_conn(conn->debug_id, r + 1, why); else conn = NULL; } @@ -331,14 +330,14 @@ static void rxrpc_set_service_reap_timer(struct rxrpc_net *rxnet, /* * Release a service connection */ -void rxrpc_put_service_conn(struct rxrpc_connection *conn) +void rxrpc_put_service_conn(struct rxrpc_connection *conn, + enum rxrpc_conn_trace why) { - const void *here = __builtin_return_address(0); unsigned int debug_id = conn->debug_id; int r; __refcount_dec(&conn->ref, &r); - trace_rxrpc_conn(debug_id, rxrpc_conn_put_service, r - 1, here); + trace_rxrpc_conn(debug_id, r - 1, why); if (r - 1 == 1) rxrpc_set_service_reap_timer(conn->local->rxnet, jiffies + rxrpc_connection_expiry); @@ -354,6 +353,9 @@ static void rxrpc_destroy_connection(struct rcu_head *rcu) _enter("{%d,u=%d}", conn->debug_id, refcount_read(&conn->ref)); + trace_rxrpc_conn(conn->debug_id, refcount_read(&conn->ref), + rxrpc_conn_free); + ASSERTCMP(refcount_read(&conn->ref), ==, 0); del_timer_sync(&conn->timer); @@ -419,7 +421,7 @@ void rxrpc_service_connection_reaper(struct work_struct *work) */ if (!refcount_dec_if_one(&conn->ref)) continue; - trace_rxrpc_conn(conn->debug_id, rxrpc_conn_reap_service, 0, NULL); + rxrpc_see_connection(conn, rxrpc_conn_see_reap_service); if (rxrpc_conn_is_client(conn)) BUG(); diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c index a3b91864ef21..bf087213bd4d 100644 --- a/net/rxrpc/conn_service.c +++ b/net/rxrpc/conn_service.c @@ -141,9 +141,7 @@ struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *rxn list_add_tail(&conn->proc_link, &rxnet->conn_proc_list); write_unlock(&rxnet->conn_lock); - trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_service, - refcount_read(&conn->ref), - __builtin_return_address(0)); + rxrpc_see_connection(conn, rxrpc_conn_new_service); } return conn; diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index cecfd201d832..c8ff7489b412 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -1121,7 +1121,7 @@ static void rxrpc_post_packet_to_conn(struct rxrpc_connection *conn, _enter("%p,%p", conn, skb); skb_queue_tail(&conn->rx_queue, skb); - rxrpc_queue_conn(conn); + rxrpc_queue_conn(conn, rxrpc_conn_queue_rx_work); } /* -- cgit v1.2.3 From cb0fc0c9722c0c001510e2a6d9b0a78b80421487 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 21 Oct 2022 14:39:26 +0100 Subject: rxrpc: trace: Don't use __builtin_return_address for rxrpc_call tracing In rxrpc tracing, use enums to generate lists of points of interest rather than __builtin_return_address() for the rxrpc_call tracepoint Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 83 ++++++++++++++++++++--------------- net/rxrpc/ar-internal.h | 8 ++-- net/rxrpc/call_accept.c | 16 +++---- net/rxrpc/call_event.c | 8 ++-- net/rxrpc/call_object.c | 102 +++++++++++++++++++------------------------ net/rxrpc/conn_client.c | 2 +- net/rxrpc/input.c | 8 ++-- net/rxrpc/output.c | 2 +- net/rxrpc/peer_event.c | 2 +- net/rxrpc/recvmsg.c | 8 ++-- net/rxrpc/sendmsg.c | 4 +- 11 files changed, 121 insertions(+), 122 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index e09568a8c173..3f6de4294148 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -127,26 +127,44 @@ E_(rxrpc_client_to_idle, "->Idle") #define rxrpc_call_traces \ - EM(rxrpc_call_connected, "CON") \ - EM(rxrpc_call_error, "*E*") \ - EM(rxrpc_call_got, "GOT") \ - EM(rxrpc_call_got_kernel, "Gke") \ - EM(rxrpc_call_got_timer, "GTM") \ - EM(rxrpc_call_got_tx, "Gtx") \ - EM(rxrpc_call_got_userid, "Gus") \ - EM(rxrpc_call_new_client, "NWc") \ - EM(rxrpc_call_new_service, "NWs") \ - EM(rxrpc_call_put, "PUT") \ - EM(rxrpc_call_put_kernel, "Pke") \ - EM(rxrpc_call_put_noqueue, "PnQ") \ - EM(rxrpc_call_put_notimer, "PnT") \ - EM(rxrpc_call_put_timer, "PTM") \ - EM(rxrpc_call_put_tx, "Ptx") \ - EM(rxrpc_call_put_userid, "Pus") \ - EM(rxrpc_call_queued, "QUE") \ - EM(rxrpc_call_queued_ref, "QUR") \ - EM(rxrpc_call_release, "RLS") \ - E_(rxrpc_call_seen, "SEE") + EM(rxrpc_call_get_input, "GET input ") \ + EM(rxrpc_call_get_kernel_service, "GET krnl-srv") \ + EM(rxrpc_call_get_notify_socket, "GET notify ") \ + EM(rxrpc_call_get_recvmsg, "GET recvmsg ") \ + EM(rxrpc_call_get_release_sock, "GET rel-sock") \ + EM(rxrpc_call_get_sendmsg, "GET sendmsg ") \ + EM(rxrpc_call_get_send_ack, "GET send-ack") \ + EM(rxrpc_call_get_timer, "GET timer ") \ + EM(rxrpc_call_get_userid, "GET user-id ") \ + EM(rxrpc_call_new_client, "NEW client ") \ + EM(rxrpc_call_new_prealloc_service, "NEW prealloc") \ + EM(rxrpc_call_put_already_queued, "PUT alreadyq") \ + EM(rxrpc_call_put_discard_prealloc, "PUT disc-pre") \ + EM(rxrpc_call_put_input, "PUT input ") \ + EM(rxrpc_call_put_kernel, "PUT kernel ") \ + EM(rxrpc_call_put_recvmsg, "PUT recvmsg ") \ + EM(rxrpc_call_put_release_sock, "PUT rls-sock") \ + EM(rxrpc_call_put_release_sock_tba, "PUT rls-sk-a") \ + EM(rxrpc_call_put_send_ack, "PUT send-ack") \ + EM(rxrpc_call_put_sendmsg, "PUT sendmsg ") \ + EM(rxrpc_call_put_timer, "PUT timer ") \ + EM(rxrpc_call_put_timer_already, "PUT timer-al") \ + EM(rxrpc_call_put_unnotify, "PUT unnotify") \ + EM(rxrpc_call_put_userid_exists, "PUT u-exists") \ + EM(rxrpc_call_put_work, "PUT work ") \ + EM(rxrpc_call_queue_abort, "QUE abort ") \ + EM(rxrpc_call_queue_requeue, "QUE requeue ") \ + EM(rxrpc_call_queue_resend, "QUE resend ") \ + EM(rxrpc_call_queue_timer, "QUE timer ") \ + EM(rxrpc_call_see_accept, "SEE accept ") \ + 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_distribute_error, "SEE dist-err") \ + EM(rxrpc_call_see_input, "SEE input ") \ + EM(rxrpc_call_see_release, "SEE release ") \ + EM(rxrpc_call_see_userid_exists, "SEE u-exists") \ + E_(rxrpc_call_see_zap, "SEE zap ") #define rxrpc_txqueue_traces \ EM(rxrpc_txqueue_await_reply, "AWR") \ @@ -503,32 +521,29 @@ TRACE_EVENT(rxrpc_client, ); TRACE_EVENT(rxrpc_call, - TP_PROTO(unsigned int call_debug_id, enum rxrpc_call_trace op, - int usage, const void *where, const void *aux), + TP_PROTO(unsigned int call_debug_id, int ref, unsigned long aux, + enum rxrpc_call_trace why), - TP_ARGS(call_debug_id, op, usage, where, aux), + TP_ARGS(call_debug_id, ref, aux, why), TP_STRUCT__entry( __field(unsigned int, call ) - __field(int, op ) - __field(int, usage ) - __field(const void *, where ) - __field(const void *, aux ) + __field(int, ref ) + __field(int, why ) + __field(unsigned long, aux ) ), TP_fast_assign( __entry->call = call_debug_id; - __entry->op = op; - __entry->usage = usage; - __entry->where = where; + __entry->ref = ref; + __entry->why = why; __entry->aux = aux; ), - TP_printk("c=%08x %s u=%d sp=%pSR a=%p", + TP_printk("c=%08x %s r=%d a=%lx", __entry->call, - __print_symbolic(__entry->op, rxrpc_call_traces), - __entry->usage, - __entry->where, + __print_symbolic(__entry->why, rxrpc_call_traces), + __entry->ref, __entry->aux) ); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index bc8281c410c5..82eb09b961a0 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -847,10 +847,10 @@ void rxrpc_incoming_call(struct rxrpc_sock *, struct rxrpc_call *, struct sk_buff *); void rxrpc_release_call(struct rxrpc_sock *, struct rxrpc_call *); void rxrpc_release_calls_on_socket(struct rxrpc_sock *); -bool __rxrpc_queue_call(struct rxrpc_call *); -bool rxrpc_queue_call(struct rxrpc_call *); -void rxrpc_see_call(struct rxrpc_call *); -bool rxrpc_try_get_call(struct rxrpc_call *call, enum rxrpc_call_trace op); +bool __rxrpc_queue_call(struct rxrpc_call *, enum rxrpc_call_trace); +bool rxrpc_queue_call(struct rxrpc_call *, enum rxrpc_call_trace); +void rxrpc_see_call(struct rxrpc_call *, enum rxrpc_call_trace); +bool rxrpc_try_get_call(struct rxrpc_call *, enum rxrpc_call_trace); void rxrpc_get_call(struct rxrpc_call *, enum rxrpc_call_trace); void rxrpc_put_call(struct rxrpc_call *, enum rxrpc_call_trace); void rxrpc_cleanup_call(struct rxrpc_call *); diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 04b52e28e0cc..dd4ca4bee77f 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -38,7 +38,6 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, unsigned long user_call_ID, gfp_t gfp, unsigned int debug_id) { - const void *here = __builtin_return_address(0); struct rxrpc_call *call, *xcall; struct rxrpc_net *rxnet = rxrpc_net(sock_net(&rx->sk)); struct rb_node *parent, **pp; @@ -102,9 +101,8 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, call->flags |= (1 << RXRPC_CALL_IS_SERVICE); call->state = RXRPC_CALL_SERVER_PREALLOC; - trace_rxrpc_call(call->debug_id, rxrpc_call_new_service, - refcount_read(&call->ref), - here, (const void *)user_call_ID); + trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), + user_call_ID, rxrpc_call_new_prealloc_service); write_lock(&rx->call_lock); @@ -125,11 +123,11 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, call->user_call_ID = user_call_ID; call->notify_rx = notify_rx; if (user_attach_call) { - rxrpc_get_call(call, rxrpc_call_got_kernel); + rxrpc_get_call(call, rxrpc_call_get_kernel_service); user_attach_call(call, user_call_ID); } - rxrpc_get_call(call, rxrpc_call_got_userid); + rxrpc_get_call(call, rxrpc_call_get_userid); rb_link_node(&call->sock_node, parent, pp); rb_insert_color(&call->sock_node, &rx->calls); set_bit(RXRPC_CALL_HAS_USERID, &call->flags); @@ -229,7 +227,7 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx) } rxrpc_call_completed(call); rxrpc_release_call(rx, call); - rxrpc_put_call(call, rxrpc_call_put); + rxrpc_put_call(call, rxrpc_call_put_discard_prealloc); tail = (tail + 1) & (size - 1); } @@ -318,7 +316,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, smp_store_release(&b->call_backlog_tail, (call_tail + 1) & (RXRPC_BACKLOG_MAX - 1)); - rxrpc_see_call(call); + rxrpc_see_call(call, rxrpc_call_see_accept); call->conn = conn; call->security = conn->security; call->security_ix = conn->security_ix; @@ -430,7 +428,7 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, * (recvmsg queue, to-be-accepted queue or user ID tree) or the kernel * service to prevent the call from being deallocated too early. */ - rxrpc_put_call(call, rxrpc_call_put); + rxrpc_put_call(call, rxrpc_call_put_discard_prealloc); _leave(" = %p{%d}", call, call->debug_id); return call; diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 591af8e2e3d0..0c8d2186cda8 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -101,7 +101,7 @@ void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason, txb->ack.reason = ack_reason; txb->ack.nAcks = 0; - if (!rxrpc_try_get_call(call, rxrpc_call_got)) { + if (!rxrpc_try_get_call(call, rxrpc_call_get_send_ack)) { rxrpc_put_txbuf(txb, rxrpc_txbuf_put_nomem); return; } @@ -302,7 +302,7 @@ void rxrpc_process_call(struct work_struct *work) unsigned int iterations = 0; rxrpc_serial_t ackr_serial; - rxrpc_see_call(call); + rxrpc_see_call(call, rxrpc_call_see_input); //printk("\n--------------------\n"); _enter("{%d,%s,%lx}", @@ -436,12 +436,12 @@ recheck_state: goto requeue; out_put: - rxrpc_put_call(call, rxrpc_call_put); + rxrpc_put_call(call, rxrpc_call_put_work); out: _leave(""); return; requeue: - __rxrpc_queue_call(call); + __rxrpc_queue_call(call, rxrpc_call_queue_requeue); goto out; } diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 29ec4013aa0b..afd957f6dc1c 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -53,9 +53,9 @@ static void rxrpc_call_timer_expired(struct timer_list *t) if (call->state < RXRPC_CALL_COMPLETE) { trace_rxrpc_timer_expired(call, jiffies); - __rxrpc_queue_call(call); + __rxrpc_queue_call(call, rxrpc_call_queue_timer); } else { - rxrpc_put_call(call, rxrpc_call_put); + rxrpc_put_call(call, rxrpc_call_put_already_queued); } } @@ -64,10 +64,10 @@ void rxrpc_reduce_call_timer(struct rxrpc_call *call, unsigned long now, enum rxrpc_timer_trace why) { - if (rxrpc_try_get_call(call, rxrpc_call_got_timer)) { + if (rxrpc_try_get_call(call, rxrpc_call_get_timer)) { trace_rxrpc_timer(call, why, now); if (timer_reduce(&call->timer, expire_at)) - rxrpc_put_call(call, rxrpc_call_put_notimer); + rxrpc_put_call(call, rxrpc_call_put_timer_already); } } @@ -110,7 +110,7 @@ struct rxrpc_call *rxrpc_find_call_by_user_ID(struct rxrpc_sock *rx, return NULL; found_extant_call: - rxrpc_get_call(call, rxrpc_call_got); + rxrpc_get_call(call, rxrpc_call_get_sendmsg); read_unlock(&rx->call_lock); _leave(" = %p [%d]", call, refcount_read(&call->ref)); return call; @@ -270,7 +270,6 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, struct rxrpc_net *rxnet; struct semaphore *limiter; struct rb_node *parent, **pp; - const void *here = __builtin_return_address(0); int ret; _enter("%p,%lx", rx, p->user_call_ID); @@ -291,9 +290,8 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, call->interruptibility = p->interruptibility; call->tx_total_len = p->tx_total_len; - trace_rxrpc_call(call->debug_id, rxrpc_call_new_client, - refcount_read(&call->ref), - here, (const void *)p->user_call_ID); + trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), + p->user_call_ID, rxrpc_call_new_client); if (p->kernel) __set_bit(RXRPC_CALL_KERNEL, &call->flags); @@ -322,7 +320,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, rcu_assign_pointer(call->socket, rx); call->user_call_ID = p->user_call_ID; __set_bit(RXRPC_CALL_HAS_USERID, &call->flags); - rxrpc_get_call(call, rxrpc_call_got_userid); + rxrpc_get_call(call, rxrpc_call_get_userid); rb_link_node(&call->sock_node, parent, pp); rb_insert_color(&call->sock_node, &rx->calls); list_add(&call->sock_link, &rx->sock_calls); @@ -344,8 +342,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, if (ret < 0) goto error_attached_to_socket; - trace_rxrpc_call(call->debug_id, rxrpc_call_connected, - refcount_read(&call->ref), here, NULL); + rxrpc_see_call(call, rxrpc_call_see_connected); rxrpc_start_call_timer(call); @@ -362,11 +359,11 @@ error_dup_user_ID: release_sock(&rx->sk); __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, RX_CALL_DEAD, -EEXIST); - trace_rxrpc_call(call->debug_id, rxrpc_call_error, - refcount_read(&call->ref), here, ERR_PTR(-EEXIST)); + trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), 0, + rxrpc_call_see_userid_exists); rxrpc_release_call(rx, call); mutex_unlock(&call->user_mutex); - rxrpc_put_call(call, rxrpc_call_put); + rxrpc_put_call(call, rxrpc_call_put_userid_exists); _leave(" = -EEXIST"); return ERR_PTR(-EEXIST); @@ -376,8 +373,8 @@ error_dup_user_ID: * leave the error to recvmsg() to deal with. */ error_attached_to_socket: - trace_rxrpc_call(call->debug_id, rxrpc_call_error, - refcount_read(&call->ref), here, ERR_PTR(ret)); + trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), ret, + rxrpc_call_see_connect_failed); set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, RX_CALL_DEAD, ret); @@ -428,72 +425,65 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx, /* * Queue a call's work processor, getting a ref to pass to the work queue. */ -bool rxrpc_queue_call(struct rxrpc_call *call) +bool rxrpc_queue_call(struct rxrpc_call *call, enum rxrpc_call_trace why) { - const void *here = __builtin_return_address(0); int n; if (!__refcount_inc_not_zero(&call->ref, &n)) return false; if (rxrpc_queue_work(&call->processor)) - trace_rxrpc_call(call->debug_id, rxrpc_call_queued, n + 1, - here, NULL); + trace_rxrpc_call(call->debug_id, n + 1, 0, why); else - rxrpc_put_call(call, rxrpc_call_put_noqueue); + rxrpc_put_call(call, rxrpc_call_put_already_queued); return true; } /* * Queue a call's work processor, passing the callers ref to the work queue. */ -bool __rxrpc_queue_call(struct rxrpc_call *call) +bool __rxrpc_queue_call(struct rxrpc_call *call, enum rxrpc_call_trace why) { - const void *here = __builtin_return_address(0); int n = refcount_read(&call->ref); + ASSERTCMP(n, >=, 1); if (rxrpc_queue_work(&call->processor)) - trace_rxrpc_call(call->debug_id, rxrpc_call_queued_ref, n, - here, NULL); + trace_rxrpc_call(call->debug_id, n, 0, why); else - rxrpc_put_call(call, rxrpc_call_put_noqueue); + rxrpc_put_call(call, rxrpc_call_put_already_queued); return true; } /* * Note the re-emergence of a call. */ -void rxrpc_see_call(struct rxrpc_call *call) +void rxrpc_see_call(struct rxrpc_call *call, enum rxrpc_call_trace why) { - const void *here = __builtin_return_address(0); if (call) { - int n = refcount_read(&call->ref); + int r = refcount_read(&call->ref); - trace_rxrpc_call(call->debug_id, rxrpc_call_seen, n, - here, NULL); + trace_rxrpc_call(call->debug_id, r, 0, why); } } -bool rxrpc_try_get_call(struct rxrpc_call *call, enum rxrpc_call_trace op) +bool rxrpc_try_get_call(struct rxrpc_call *call, enum rxrpc_call_trace why) { - const void *here = __builtin_return_address(0); - int n; + int r; - if (!__refcount_inc_not_zero(&call->ref, &n)) + if (!__refcount_inc_not_zero(&call->ref, &r)) return false; - trace_rxrpc_call(call->debug_id, op, n + 1, here, NULL); + trace_rxrpc_call(call->debug_id, r + 1, 0, why); return true; } /* * Note the addition of a ref on a call. */ -void rxrpc_get_call(struct rxrpc_call *call, enum rxrpc_call_trace op) +void rxrpc_get_call(struct rxrpc_call *call, enum rxrpc_call_trace why) { - const void *here = __builtin_return_address(0); - int n; + int r; - __refcount_inc(&call->ref, &n); - trace_rxrpc_call(call->debug_id, op, n + 1, here, NULL); + __refcount_inc(&call->ref, &r); + trace_rxrpc_call(call->debug_id, r + 1, 0, why); } /* @@ -510,15 +500,13 @@ static void rxrpc_cleanup_ring(struct rxrpc_call *call) */ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) { - const void *here = __builtin_return_address(0); struct rxrpc_connection *conn = call->conn; bool put = false; _enter("{%d,%d}", call->debug_id, refcount_read(&call->ref)); - trace_rxrpc_call(call->debug_id, rxrpc_call_release, - refcount_read(&call->ref), - here, (const void *)call->flags); + trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), + call->flags, rxrpc_call_see_release); ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); @@ -544,14 +532,14 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) write_unlock_bh(&rx->recvmsg_lock); if (put) - rxrpc_put_call(call, rxrpc_call_put); + rxrpc_put_call(call, rxrpc_call_put_unnotify); write_lock(&rx->call_lock); if (test_and_clear_bit(RXRPC_CALL_HAS_USERID, &call->flags)) { rb_erase(&call->sock_node, &rx->calls); memset(&call->sock_node, 0xdd, sizeof(call->sock_node)); - rxrpc_put_call(call, rxrpc_call_put_userid); + rxrpc_put_call(call, rxrpc_call_put_userid_exists); } list_del(&call->sock_link); @@ -580,17 +568,17 @@ void rxrpc_release_calls_on_socket(struct rxrpc_sock *rx) struct rxrpc_call, accept_link); list_del(&call->accept_link); rxrpc_abort_call("SKR", call, 0, RX_CALL_DEAD, -ECONNRESET); - rxrpc_put_call(call, rxrpc_call_put); + rxrpc_put_call(call, rxrpc_call_put_release_sock_tba); } while (!list_empty(&rx->sock_calls)) { call = list_entry(rx->sock_calls.next, struct rxrpc_call, sock_link); - rxrpc_get_call(call, rxrpc_call_got); + rxrpc_get_call(call, rxrpc_call_get_release_sock); rxrpc_abort_call("SKT", call, 0, RX_CALL_DEAD, -ECONNRESET); rxrpc_send_abort_packet(call); rxrpc_release_call(rx, call); - rxrpc_put_call(call, rxrpc_call_put); + rxrpc_put_call(call, rxrpc_call_put_release_sock); } _leave(""); @@ -599,20 +587,18 @@ void rxrpc_release_calls_on_socket(struct rxrpc_sock *rx) /* * release a call */ -void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace op) +void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace why) { struct rxrpc_net *rxnet = call->rxnet; - const void *here = __builtin_return_address(0); unsigned int debug_id = call->debug_id; bool dead; - int n; + int r; ASSERT(call != NULL); - dead = __refcount_dec_and_test(&call->ref, &n); - trace_rxrpc_call(debug_id, op, n, here, NULL); + dead = __refcount_dec_and_test(&call->ref, &r); + trace_rxrpc_call(debug_id, r - 1, 0, why); if (dead) { - _debug("call %d dead", call->debug_id); ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); if (!list_empty(&call->link)) { @@ -701,7 +687,7 @@ void rxrpc_destroy_all_calls(struct rxrpc_net *rxnet) struct rxrpc_call, link); _debug("Zapping call %p", call); - rxrpc_see_call(call); + rxrpc_see_call(call, rxrpc_call_see_zap); list_del_init(&call->link); pr_err("Call %p still in use (%d,%s,%lx,%lx)!\n", diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index dcfec6a45255..4352e777aa2a 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -540,7 +540,7 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn, clear_bit(RXRPC_CONN_FINAL_ACK_0 + channel, &conn->flags); clear_bit(conn->bundle_shift + channel, &bundle->avail_chans); - rxrpc_see_call(call); + rxrpc_see_call(call, rxrpc_call_see_activate_client); list_del_init(&call->chan_wait_link); call->peer = rxrpc_get_peer(conn->peer, rxrpc_peer_get_activate_call); call->conn = rxrpc_get_connection(conn, rxrpc_conn_get_activate_call); diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index c8ff7489b412..09b44cd11c9b 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -14,7 +14,7 @@ static void rxrpc_proto_abort(const char *why, { if (rxrpc_abort_call(why, call, seq, RX_PROTOCOL_ERROR, -EBADMSG)) { set_bit(RXRPC_CALL_EV_ABORT, &call->events); - rxrpc_queue_call(call); + rxrpc_queue_call(call, rxrpc_call_queue_abort); } } @@ -175,7 +175,7 @@ out_no_clear_ca: call->cong_cumul_acks = cumulative_acks; trace_rxrpc_congest(call, summary, acked_serial, change); if (resend && !test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events)) - rxrpc_queue_call(call); + rxrpc_queue_call(call, rxrpc_call_queue_resend); return; packet_loss_detected: @@ -678,7 +678,7 @@ static void rxrpc_input_check_for_lost_ack(struct rxrpc_call *call) { if (after(call->acks_lost_top, call->acks_prev_seq) && !test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events)) - rxrpc_queue_call(call); + rxrpc_queue_call(call, rxrpc_call_queue_resend); } /* @@ -1099,7 +1099,7 @@ static void rxrpc_input_implicit_end_call(struct rxrpc_sock *rx, default: if (rxrpc_abort_call("IMP", call, 0, RX_CALL_DEAD, -ESHUTDOWN)) { set_bit(RXRPC_CALL_EV_ABORT, &call->events); - rxrpc_queue_call(call); + rxrpc_queue_call(call, rxrpc_call_queue_abort); } trace_rxrpc_improper_term(call); break; diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 2762b7ada9ae..d324e88f7642 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -310,7 +310,7 @@ void rxrpc_transmit_ack_packets(struct rxrpc_local *local) } list_del_init(&txb->tx_link); - rxrpc_put_call(txb->call, rxrpc_call_put); + rxrpc_put_call(txb->call, rxrpc_call_put_send_ack); rxrpc_put_txbuf(txb, rxrpc_txbuf_put_ack_tx); } } diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index 5e97d321ac38..b28739d10927 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -238,7 +238,7 @@ static void rxrpc_distribute_error(struct rxrpc_peer *peer, int error, struct rxrpc_call *call; hlist_for_each_entry_rcu(call, &peer->error_targets, error_link) { - rxrpc_see_call(call); + rxrpc_see_call(call, rxrpc_call_see_distribute_error); rxrpc_set_call_completion(call, compl, 0, -error); } } diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 134122f5961a..c84d2b620396 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -42,7 +42,7 @@ void rxrpc_notify_socket(struct rxrpc_call *call) } else { write_lock_bh(&rx->recvmsg_lock); if (list_empty(&call->recvmsg_link)) { - rxrpc_get_call(call, rxrpc_call_got); + rxrpc_get_call(call, rxrpc_call_get_notify_socket); list_add_tail(&call->recvmsg_link, &rx->recvmsg_q); } write_unlock_bh(&rx->recvmsg_lock); @@ -451,7 +451,7 @@ try_again: if (!(flags & MSG_PEEK)) list_del_init(&call->recvmsg_link); else - rxrpc_get_call(call, rxrpc_call_got); + rxrpc_get_call(call, rxrpc_call_get_recvmsg); write_unlock_bh(&rx->recvmsg_lock); trace_rxrpc_recvmsg(call, rxrpc_recvmsg_dequeue, 0); @@ -537,7 +537,7 @@ try_again: error_unlock_call: mutex_unlock(&call->user_mutex); - rxrpc_put_call(call, rxrpc_call_put); + rxrpc_put_call(call, rxrpc_call_put_recvmsg); trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, ret); return ret; @@ -548,7 +548,7 @@ error_requeue_call: write_unlock_bh(&rx->recvmsg_lock); trace_rxrpc_recvmsg(call, rxrpc_recvmsg_requeue, 0); } else { - rxrpc_put_call(call, rxrpc_call_put); + rxrpc_put_call(call, rxrpc_call_put_recvmsg); } error_no_call: release_sock(&rx->sk); diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index cfe0badba0b3..76b1e2e89c1e 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -667,7 +667,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) case RXRPC_CALL_CLIENT_AWAIT_CONN: case RXRPC_CALL_SERVER_PREALLOC: case RXRPC_CALL_SERVER_SECURING: - rxrpc_put_call(call, rxrpc_call_put); + rxrpc_put_call(call, rxrpc_call_put_sendmsg); ret = -EBUSY; goto error_release_sock; default: @@ -737,7 +737,7 @@ out_put_unlock: if (!dropped_lock) mutex_unlock(&call->user_mutex); error_put: - rxrpc_put_call(call, rxrpc_call_put); + rxrpc_put_call(call, rxrpc_call_put_sendmsg); _leave(" = %d", ret); return ret; -- cgit v1.2.3 From fa3492abb64b93b2b5d6fdf7a5b687a1fa810d74 Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 2 Nov 2022 21:54:46 +0000 Subject: rxrpc: Trace rxrpc_bundle refcount Add a tracepoint for the rxrpc_bundle refcounting. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 34 ++++++++++++++++++++++++++++++++++ net/rxrpc/ar-internal.h | 4 ++-- net/rxrpc/conn_client.c | 27 ++++++++++++++++----------- net/rxrpc/conn_object.c | 2 +- net/rxrpc/conn_service.c | 3 ++- 5 files changed, 55 insertions(+), 15 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 3f6de4294148..6f5be7ac7f6b 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -81,6 +81,15 @@ EM(rxrpc_peer_put_input_error, "PUT inpt-err") \ E_(rxrpc_peer_put_keepalive, "PUT keepaliv") +#define rxrpc_bundle_traces \ + EM(rxrpc_bundle_free, "FREE ") \ + EM(rxrpc_bundle_get_client_call, "GET clt-call") \ + EM(rxrpc_bundle_get_client_conn, "GET clt-conn") \ + EM(rxrpc_bundle_get_service_conn, "GET svc-conn") \ + EM(rxrpc_bundle_put_conn, "PUT conn ") \ + EM(rxrpc_bundle_put_discard, "PUT discard ") \ + E_(rxrpc_bundle_new, "NEW ") + #define rxrpc_conn_traces \ EM(rxrpc_conn_free, "FREE ") \ EM(rxrpc_conn_get_activate_call, "GET act-call") \ @@ -361,6 +370,7 @@ #define EM(a, b) a, #define E_(a, b) a +enum rxrpc_bundle_trace { rxrpc_bundle_traces } __mode(byte); enum rxrpc_call_trace { rxrpc_call_traces } __mode(byte); enum rxrpc_client_trace { rxrpc_client_traces } __mode(byte); enum rxrpc_congest_change { rxrpc_congest_changes } __mode(byte); @@ -390,6 +400,7 @@ enum rxrpc_txqueue_trace { rxrpc_txqueue_traces } __mode(byte); #define EM(a, b) TRACE_DEFINE_ENUM(a); #define E_(a, b) TRACE_DEFINE_ENUM(a); +rxrpc_bundle_traces; rxrpc_call_traces; rxrpc_client_traces; rxrpc_congest_changes; @@ -467,6 +478,29 @@ TRACE_EVENT(rxrpc_peer, __entry->ref) ); +TRACE_EVENT(rxrpc_bundle, + TP_PROTO(unsigned int bundle_debug_id, int ref, enum rxrpc_bundle_trace why), + + TP_ARGS(bundle_debug_id, ref, why), + + TP_STRUCT__entry( + __field(unsigned int, bundle ) + __field(int, ref ) + __field(int, why ) + ), + + TP_fast_assign( + __entry->bundle = bundle_debug_id; + __entry->ref = ref; + __entry->why = why; + ), + + TP_printk("CB=%08x %s r=%d", + __entry->bundle, + __print_symbolic(__entry->why, rxrpc_bundle_traces), + __entry->ref) + ); + TRACE_EVENT(rxrpc_conn, TP_PROTO(unsigned int conn_debug_id, int ref, enum rxrpc_conn_trace why), diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 82eb09b961a0..c588c0e81f63 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -875,8 +875,8 @@ extern unsigned long rxrpc_conn_idle_client_fast_expiry; extern struct idr rxrpc_client_conn_ids; void rxrpc_destroy_client_conn_ids(void); -struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *); -void rxrpc_put_bundle(struct rxrpc_bundle *); +struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *, enum rxrpc_bundle_trace); +void rxrpc_put_bundle(struct rxrpc_bundle *, enum rxrpc_bundle_trace); int rxrpc_connect_call(struct rxrpc_sock *, struct rxrpc_call *, struct rxrpc_conn_parameters *, struct sockaddr_rxrpc *, gfp_t); diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 4352e777aa2a..34ff6fa85c32 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -133,31 +133,36 @@ static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_conn_parameters *cp, atomic_set(&bundle->active, 1); spin_lock_init(&bundle->channel_lock); INIT_LIST_HEAD(&bundle->waiting_calls); + trace_rxrpc_bundle(bundle->debug_id, 1, rxrpc_bundle_new); } return bundle; } -struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *bundle) +struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *bundle, + enum rxrpc_bundle_trace why) { - refcount_inc(&bundle->ref); + int r; + + __refcount_inc(&bundle->ref, &r); + trace_rxrpc_bundle(bundle->debug_id, r + 1, why); return bundle; } static void rxrpc_free_bundle(struct rxrpc_bundle *bundle) { + trace_rxrpc_bundle(bundle->debug_id, 1, rxrpc_bundle_free); rxrpc_put_peer(bundle->peer, rxrpc_peer_put_bundle); kfree(bundle); } -void rxrpc_put_bundle(struct rxrpc_bundle *bundle) +void rxrpc_put_bundle(struct rxrpc_bundle *bundle, enum rxrpc_bundle_trace why) { - unsigned int d = bundle->debug_id; + unsigned int id = bundle->debug_id; bool dead; int r; dead = __refcount_dec_and_test(&bundle->ref, &r); - - _debug("PUT B=%x %d", d, r - 1); + trace_rxrpc_bundle(id, r - 1, why); if (dead) rxrpc_free_bundle(bundle); } @@ -206,7 +211,7 @@ rxrpc_alloc_client_connection(struct rxrpc_bundle *bundle, gfp_t gfp) list_add_tail(&conn->proc_link, &rxnet->conn_proc_list); write_unlock(&rxnet->conn_lock); - rxrpc_get_bundle(bundle); + rxrpc_get_bundle(bundle, rxrpc_bundle_get_client_conn); rxrpc_get_peer(conn->peer, rxrpc_peer_get_client_conn); rxrpc_get_local(conn->local, rxrpc_local_get_client_conn); key_get(conn->key); @@ -342,7 +347,7 @@ static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *c candidate->debug_id = atomic_inc_return(&rxrpc_bundle_id); rb_link_node(&candidate->local_node, parent, pp); rb_insert_color(&candidate->local_node, &local->client_bundles); - rxrpc_get_bundle(candidate); + rxrpc_get_bundle(candidate, rxrpc_bundle_get_client_call); spin_unlock(&local->client_bundles_lock); _leave(" = %u [new]", candidate->debug_id); return candidate; @@ -350,7 +355,7 @@ static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *c found_bundle_free: rxrpc_free_bundle(candidate); found_bundle: - rxrpc_get_bundle(bundle); + rxrpc_get_bundle(bundle, rxrpc_bundle_get_client_call); atomic_inc(&bundle->active); spin_unlock(&local->client_bundles_lock); _leave(" = %u [found]", bundle->debug_id); @@ -740,7 +745,7 @@ granted_channel: out_put_bundle: rxrpc_deactivate_bundle(bundle); - rxrpc_put_bundle(bundle); + rxrpc_put_bundle(bundle, rxrpc_bundle_get_client_call); out: _leave(" = %d", ret); return ret; @@ -958,7 +963,7 @@ static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle) spin_unlock(&local->client_bundles_lock); if (need_put) - rxrpc_put_bundle(bundle); + rxrpc_put_bundle(bundle, rxrpc_bundle_put_discard); } } diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index bbace8d9953d..f7c271a740ed 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -363,7 +363,7 @@ static void rxrpc_destroy_connection(struct rcu_head *rcu) conn->security->clear(conn); key_put(conn->key); - rxrpc_put_bundle(conn->bundle); + rxrpc_put_bundle(conn->bundle, rxrpc_bundle_put_conn); rxrpc_put_peer(conn->peer, rxrpc_peer_put_conn); if (atomic_dec_and_test(&conn->local->rxnet->nr_conns)) diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c index bf087213bd4d..2c44d67b43dc 100644 --- a/net/rxrpc/conn_service.c +++ b/net/rxrpc/conn_service.c @@ -133,7 +133,8 @@ struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *rxn */ conn->state = RXRPC_CONN_SERVICE_PREALLOC; refcount_set(&conn->ref, 2); - conn->bundle = rxrpc_get_bundle(&rxrpc_service_dummy_bundle); + conn->bundle = rxrpc_get_bundle(&rxrpc_service_dummy_bundle, + rxrpc_bundle_get_service_conn); atomic_inc(&rxnet->nr_conns); write_lock(&rxnet->conn_lock); -- cgit v1.2.3 From 9a36a6bc22ca1c0a9d82228171e05dc785fa1154 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 21 Oct 2022 15:31:21 +0100 Subject: rxrpc: trace: Don't use __builtin_return_address for sk_buff tracing In rxrpc tracing, use enums to generate lists of points of interest rather than __builtin_return_address() for the sk_buff tracepoint. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 57 +++++++++++++++++++++++++------------------- net/rxrpc/call_event.c | 4 ++-- net/rxrpc/call_object.c | 2 +- net/rxrpc/conn_event.c | 6 ++--- net/rxrpc/input.c | 36 ++++++++++++++-------------- net/rxrpc/local_event.c | 4 ++-- net/rxrpc/output.c | 6 ++--- net/rxrpc/peer_event.c | 8 +++---- net/rxrpc/recvmsg.c | 6 ++--- net/rxrpc/skbuff.c | 36 ++++++++++++---------------- 10 files changed, 84 insertions(+), 81 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 6f5be7ac7f6b..5a2292baffc8 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -17,19 +17,31 @@ * Declare tracing information enums and their string mappings for display. */ #define rxrpc_skb_traces \ - EM(rxrpc_skb_ack, "ACK") \ - EM(rxrpc_skb_cleaned, "CLN") \ - EM(rxrpc_skb_cloned_jumbo, "CLJ") \ - EM(rxrpc_skb_freed, "FRE") \ - EM(rxrpc_skb_got, "GOT") \ - EM(rxrpc_skb_lost, "*L*") \ - EM(rxrpc_skb_new, "NEW") \ - EM(rxrpc_skb_purged, "PUR") \ - EM(rxrpc_skb_received, "RCV") \ - EM(rxrpc_skb_rotated, "ROT") \ - EM(rxrpc_skb_seen, "SEE") \ - EM(rxrpc_skb_unshared, "UNS") \ - E_(rxrpc_skb_unshared_nomem, "US0") + EM(rxrpc_skb_eaten_by_unshare, "ETN unshare ") \ + EM(rxrpc_skb_eaten_by_unshare_nomem, "ETN unshar-nm") \ + EM(rxrpc_skb_get_ack, "GET ack ") \ + EM(rxrpc_skb_get_conn_work, "GET conn-work") \ + EM(rxrpc_skb_get_to_recvmsg, "GET to-recv ") \ + EM(rxrpc_skb_get_to_recvmsg_oos, "GET to-recv-o") \ + EM(rxrpc_skb_new_encap_rcv, "NEW encap-rcv") \ + 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_ack, "PUT ack ") \ + 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_lose, "PUT lose ") \ + EM(rxrpc_skb_put_purge, "PUT purge ") \ + EM(rxrpc_skb_put_rotate, "PUT rotate ") \ + EM(rxrpc_skb_put_unknown, "PUT unknown ") \ + EM(rxrpc_skb_see_conn_work, "SEE conn-work") \ + EM(rxrpc_skb_see_local_work, "SEE locl-work") \ + EM(rxrpc_skb_see_recvmsg, "SEE recvmsg ") \ + EM(rxrpc_skb_see_reject, "SEE reject ") \ + EM(rxrpc_skb_see_rotate, "SEE rotate ") \ + E_(rxrpc_skb_see_version, "SEE version ") #define rxrpc_local_traces \ EM(rxrpc_local_free, "FREE ") \ @@ -582,33 +594,30 @@ TRACE_EVENT(rxrpc_call, ); TRACE_EVENT(rxrpc_skb, - TP_PROTO(struct sk_buff *skb, enum rxrpc_skb_trace op, - int usage, int mod_count, const void *where), + TP_PROTO(struct sk_buff *skb, int usage, int mod_count, + enum rxrpc_skb_trace why), - TP_ARGS(skb, op, usage, mod_count, where), + TP_ARGS(skb, usage, mod_count, why), TP_STRUCT__entry( __field(struct sk_buff *, skb ) - __field(enum rxrpc_skb_trace, op ) __field(int, usage ) __field(int, mod_count ) - __field(const void *, where ) + __field(enum rxrpc_skb_trace, why ) ), TP_fast_assign( __entry->skb = skb; - __entry->op = op; __entry->usage = usage; __entry->mod_count = mod_count; - __entry->where = where; + __entry->why = why; ), - TP_printk("s=%p Rx %s u=%d m=%d p=%pSR", + TP_printk("s=%p Rx %s u=%d m=%d", __entry->skb, - __print_symbolic(__entry->op, rxrpc_skb_traces), + __print_symbolic(__entry->why, rxrpc_skb_traces), __entry->usage, - __entry->mod_count, - __entry->where) + __entry->mod_count) ); TRACE_EVENT(rxrpc_rx_packet, diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 0c8d2186cda8..29ca02e53c47 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -153,7 +153,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) spin_lock_bh(&call->acks_ack_lock); ack_skb = call->acks_soft_tbl; if (ack_skb) { - rxrpc_get_skb(ack_skb, rxrpc_skb_ack); + rxrpc_get_skb(ack_skb, rxrpc_skb_get_ack); ack = (void *)ack_skb->data + sizeof(struct rxrpc_wire_header); } spin_unlock_bh(&call->acks_ack_lock); @@ -251,7 +251,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) no_further_resend: spin_unlock(&call->tx_lock); no_resend: - rxrpc_free_skb(ack_skb, rxrpc_skb_freed); + rxrpc_free_skb(ack_skb, rxrpc_skb_put_ack); resend_at = nsecs_to_jiffies(ktime_to_ns(ktime_sub(now, oldest))); resend_at += jiffies + rxrpc_get_rto_backoff(call->peer, diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index afd957f6dc1c..815209673115 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -663,7 +663,7 @@ void rxrpc_cleanup_call(struct rxrpc_call *call) rxrpc_put_txbuf(txb, rxrpc_txbuf_put_cleaned); } rxrpc_put_txbuf(call->tx_pending, rxrpc_txbuf_put_cleaned); - rxrpc_free_skb(call->acks_soft_tbl, rxrpc_skb_cleaned); + rxrpc_free_skb(call->acks_soft_tbl, rxrpc_skb_put_ack); call_rcu(&call->rcu, rxrpc_rcu_destroy_call); } diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 817f895c77ca..49d885f73fa5 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -437,7 +437,7 @@ static void rxrpc_do_process_connection(struct rxrpc_connection *conn) /* go through the conn-level event packets, releasing the ref on this * connection that each one has when we've finished with it */ while ((skb = skb_dequeue(&conn->rx_queue))) { - rxrpc_see_skb(skb, rxrpc_skb_seen); + rxrpc_see_skb(skb, rxrpc_skb_see_conn_work); ret = rxrpc_process_event(conn, skb, &abort_code); switch (ret) { case -EPROTO: @@ -449,7 +449,7 @@ static void rxrpc_do_process_connection(struct rxrpc_connection *conn) goto requeue_and_leave; case -ECONNABORTED: default: - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_conn_work); break; } } @@ -463,7 +463,7 @@ requeue_and_leave: protocol_error: if (rxrpc_abort_connection(conn, ret, abort_code) < 0) goto requeue_and_leave; - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_conn_work); return; } diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 09b44cd11c9b..ab8b7a1be935 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -485,7 +485,7 @@ send_ack: rxrpc_propose_ack_input_data); err_free: - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_input); } /* @@ -513,7 +513,7 @@ static bool rxrpc_input_split_jumbo(struct rxrpc_call *call, struct sk_buff *skb kdebug("couldn't clone"); return false; } - rxrpc_new_skb(jskb, rxrpc_skb_cloned_jumbo); + rxrpc_new_skb(jskb, rxrpc_skb_new_jumbo_subpacket); jsp = rxrpc_skb(jskb); jsp->offset = offset; jsp->len = RXRPC_JUMBO_DATALEN; @@ -553,7 +553,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) state = READ_ONCE(call->state); if (state >= RXRPC_CALL_COMPLETE) { - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_input); return; } @@ -563,14 +563,14 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) if (sp->hdr.securityIndex != 0) { struct sk_buff *nskb = skb_unshare(skb, GFP_ATOMIC); if (!nskb) { - rxrpc_eaten_skb(skb, rxrpc_skb_unshared_nomem); + rxrpc_eaten_skb(skb, rxrpc_skb_eaten_by_unshare_nomem); return; } if (nskb != skb) { - rxrpc_eaten_skb(skb, rxrpc_skb_received); + rxrpc_eaten_skb(skb, rxrpc_skb_eaten_by_unshare); skb = nskb; - rxrpc_new_skb(skb, rxrpc_skb_unshared); + rxrpc_new_skb(skb, rxrpc_skb_new_unshared); sp = rxrpc_skb(skb); } } @@ -609,7 +609,7 @@ out: rxrpc_notify_socket(call); spin_unlock(&call->input_lock); - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_input); _leave(" [queued]"); } @@ -994,8 +994,8 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) out: spin_unlock(&call->input_lock); out_not_locked: - rxrpc_free_skb(skb_put, rxrpc_skb_freed); - rxrpc_free_skb(skb_old, rxrpc_skb_freed); + rxrpc_free_skb(skb_put, rxrpc_skb_put_input); + rxrpc_free_skb(skb_old, rxrpc_skb_put_ack); } /* @@ -1075,7 +1075,7 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call, break; } - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_input); no_free: _leave(""); } @@ -1137,7 +1137,7 @@ static void rxrpc_post_packet_to_local(struct rxrpc_local *local, skb_queue_tail(&local->event_queue, skb); rxrpc_queue_local(local); } else { - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_input); } } @@ -1150,7 +1150,7 @@ static void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) skb_queue_tail(&local->reject_queue, skb); rxrpc_queue_local(local); } else { - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_input); } } @@ -1228,7 +1228,7 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) if (skb->tstamp == 0) skb->tstamp = ktime_get_real(); - rxrpc_new_skb(skb, rxrpc_skb_received); + rxrpc_new_skb(skb, rxrpc_skb_new_encap_rcv); skb_pull(skb, sizeof(struct udphdr)); @@ -1245,7 +1245,7 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) static int lose; if ((lose++ & 7) == 7) { trace_rxrpc_rx_lose(sp); - rxrpc_free_skb(skb, rxrpc_skb_lost); + rxrpc_free_skb(skb, rxrpc_skb_put_lose); return 0; } } @@ -1286,14 +1286,14 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) if (sp->hdr.securityIndex != 0) { struct sk_buff *nskb = skb_unshare(skb, GFP_ATOMIC); if (!nskb) { - rxrpc_eaten_skb(skb, rxrpc_skb_unshared_nomem); + rxrpc_eaten_skb(skb, rxrpc_skb_eaten_by_unshare_nomem); goto out; } if (nskb != skb) { - rxrpc_eaten_skb(skb, rxrpc_skb_received); + rxrpc_eaten_skb(skb, rxrpc_skb_eaten_by_unshare); skb = nskb; - rxrpc_new_skb(skb, rxrpc_skb_unshared); + rxrpc_new_skb(skb, rxrpc_skb_new_unshared); sp = rxrpc_skb(skb); } } @@ -1434,7 +1434,7 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) goto out; discard: - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_input); out: trace_rxrpc_rx_done(0, 0); return 0; diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c index f23a3fbabbda..c344383a20b2 100644 --- a/net/rxrpc/local_event.c +++ b/net/rxrpc/local_event.c @@ -88,7 +88,7 @@ void rxrpc_process_local_events(struct rxrpc_local *local) if (skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - rxrpc_see_skb(skb, rxrpc_skb_seen); + rxrpc_see_skb(skb, rxrpc_skb_see_local_work); _debug("{%d},{%u}", local->debug_id, sp->hdr.type); switch (sp->hdr.type) { @@ -105,7 +105,7 @@ void rxrpc_process_local_events(struct rxrpc_local *local) break; } - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_input); } _leave(""); diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index d324e88f7642..131c7a76fb06 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -615,7 +615,7 @@ void rxrpc_reject_packets(struct rxrpc_local *local) memset(&whdr, 0, sizeof(whdr)); while ((skb = skb_dequeue(&local->reject_queue))) { - rxrpc_see_skb(skb, rxrpc_skb_seen); + rxrpc_see_skb(skb, rxrpc_skb_see_reject); sp = rxrpc_skb(skb); switch (skb->mark) { @@ -631,7 +631,7 @@ void rxrpc_reject_packets(struct rxrpc_local *local) ioc = 2; break; default: - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_input); continue; } @@ -656,7 +656,7 @@ void rxrpc_reject_packets(struct rxrpc_local *local) rxrpc_tx_point_reject); } - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_input); } _leave(""); diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index b28739d10927..f35cfc458dcf 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -158,12 +158,12 @@ void rxrpc_error_report(struct sock *sk) _leave("UDP socket errqueue empty"); return; } - rxrpc_new_skb(skb, rxrpc_skb_received); + rxrpc_new_skb(skb, rxrpc_skb_new_error_report); serr = SKB_EXT_ERR(skb); if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) { _leave("UDP empty message"); rcu_read_unlock(); - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_error_report); return; } @@ -172,7 +172,7 @@ void rxrpc_error_report(struct sock *sk) peer = NULL; if (!peer) { rcu_read_unlock(); - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_error_report); _leave(" [no peer]"); return; } @@ -189,7 +189,7 @@ void rxrpc_error_report(struct sock *sk) rxrpc_store_error(peer, serr); out: rcu_read_unlock(); - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_error_report); rxrpc_put_peer(peer, rxrpc_peer_put_input_error); _leave(""); diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index c84d2b620396..bfac9e09347e 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -229,7 +229,7 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) _enter("%d", call->debug_id); skb = skb_dequeue(&call->recvmsg_queue); - rxrpc_see_skb(skb, rxrpc_skb_rotated); + rxrpc_see_skb(skb, rxrpc_skb_see_rotate); sp = rxrpc_skb(skb); tseq = sp->hdr.seq; @@ -240,7 +240,7 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) if (after(tseq, call->rx_consumed)) smp_store_release(&call->rx_consumed, tseq); - rxrpc_free_skb(skb, rxrpc_skb_freed); + rxrpc_free_skb(skb, rxrpc_skb_put_rotate); trace_rxrpc_receive(call, last ? rxrpc_receive_rotate_last : rxrpc_receive_rotate, serial, call->rx_consumed); @@ -302,7 +302,7 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, */ skb = skb_peek(&call->recvmsg_queue); while (skb) { - rxrpc_see_skb(skb, rxrpc_skb_seen); + rxrpc_see_skb(skb, rxrpc_skb_see_recvmsg); sp = rxrpc_skb(skb); seq = sp->hdr.seq; diff --git a/net/rxrpc/skbuff.c b/net/rxrpc/skbuff.c index 0c827d5bb2b8..ebe0c75e7b07 100644 --- a/net/rxrpc/skbuff.c +++ b/net/rxrpc/skbuff.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-or-later -/* ar-skbuff.c: socket buffer destruction handling +/* Socket buffer accounting * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) @@ -19,56 +19,50 @@ /* * Note the allocation or reception of a socket buffer. */ -void rxrpc_new_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) +void rxrpc_new_skb(struct sk_buff *skb, enum rxrpc_skb_trace why) { - const void *here = __builtin_return_address(0); int n = atomic_inc_return(select_skb_count(skb)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); + trace_rxrpc_skb(skb, refcount_read(&skb->users), n, why); } /* * Note the re-emergence of a socket buffer from a queue or buffer. */ -void rxrpc_see_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) +void rxrpc_see_skb(struct sk_buff *skb, enum rxrpc_skb_trace why) { - const void *here = __builtin_return_address(0); if (skb) { int n = atomic_read(select_skb_count(skb)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); + trace_rxrpc_skb(skb, refcount_read(&skb->users), n, why); } } /* * Note the addition of a ref on a socket buffer. */ -void rxrpc_get_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) +void rxrpc_get_skb(struct sk_buff *skb, enum rxrpc_skb_trace why) { - const void *here = __builtin_return_address(0); int n = atomic_inc_return(select_skb_count(skb)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); + trace_rxrpc_skb(skb, refcount_read(&skb->users), n, why); skb_get(skb); } /* * Note the dropping of a ref on a socket buffer by the core. */ -void rxrpc_eaten_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) +void rxrpc_eaten_skb(struct sk_buff *skb, enum rxrpc_skb_trace why) { - const void *here = __builtin_return_address(0); int n = atomic_inc_return(&rxrpc_n_rx_skbs); - trace_rxrpc_skb(skb, op, 0, n, here); + trace_rxrpc_skb(skb, 0, n, why); } /* * Note the destruction of a socket buffer. */ -void rxrpc_free_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) +void rxrpc_free_skb(struct sk_buff *skb, enum rxrpc_skb_trace why) { - const void *here = __builtin_return_address(0); if (skb) { - int n; - n = atomic_dec_return(select_skb_count(skb)); - trace_rxrpc_skb(skb, op, refcount_read(&skb->users), n, here); + int n = atomic_dec_return(select_skb_count(skb)); + trace_rxrpc_skb(skb, refcount_read(&skb->users), n, why); kfree_skb(skb); } } @@ -78,12 +72,12 @@ void rxrpc_free_skb(struct sk_buff *skb, enum rxrpc_skb_trace op) */ void rxrpc_purge_queue(struct sk_buff_head *list) { - const void *here = __builtin_return_address(0); struct sk_buff *skb; + while ((skb = skb_dequeue((list))) != NULL) { int n = atomic_dec_return(select_skb_count(skb)); - trace_rxrpc_skb(skb, rxrpc_skb_purged, - refcount_read(&skb->users), n, here); + trace_rxrpc_skb(skb, refcount_read(&skb->users), n, + rxrpc_skb_put_purge); kfree_skb(skb); } } -- cgit v1.2.3 From 3feda9d69c83983b530cea6287ba4fea0e5c3b87 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 25 Nov 2022 09:00:55 +0000 Subject: rxrpc: Don't hold a ref for call timer or workqueue Currently, rxrpc gives the call timer a ref on the call when it starts it and this is passed along to the workqueue by the timer expiration function. The problem comes when queue_work() fails (ie. the work item is already queued): the timer routine must put the ref - but this may cause the cleanup code to run. This has the unfortunate effect that the cleanup code may then be run in softirq context - which means that any spinlocks it might need to touch have to be guarded to disable softirqs (ie. they need a "_bh" suffix). Fix this by: (1) Don't give a ref to the timer. (2) Making the expiration function not do anything if the refcount is 0. Note that this is more of an optimisation. (3) Make sure that the cleanup routine waits for timer to complete. However, this has a consequence that timer cannot give a ref to the work item. Therefore the following fixes are also necessary: (4) Don't give a ref to the work item. (5) Make the work item return asap if it sees the ref count is 0. (6) Make sure that the cleanup routine waits for the work item to complete. Unfortunately, neither the timer nor the work item can simply get around the problem by just using refcount_inc_not_zero() as the waits would still have to be done, and there would still be the possibility of having to put the ref in the expiration function. Note the call work item is going to go away with the work being transferred to the I/O thread, so the wait in (6) will become obsolete. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 6 +-- net/rxrpc/ar-internal.h | 6 +-- net/rxrpc/call_event.c | 11 ++--- net/rxrpc/call_object.c | 111 ++++++++++++++++--------------------------- net/rxrpc/txbuf.c | 2 + 5 files changed, 52 insertions(+), 84 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 5a2292baffc8..4538de0079a5 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -155,11 +155,9 @@ EM(rxrpc_call_get_release_sock, "GET rel-sock") \ EM(rxrpc_call_get_sendmsg, "GET sendmsg ") \ EM(rxrpc_call_get_send_ack, "GET send-ack") \ - EM(rxrpc_call_get_timer, "GET timer ") \ EM(rxrpc_call_get_userid, "GET user-id ") \ EM(rxrpc_call_new_client, "NEW client ") \ EM(rxrpc_call_new_prealloc_service, "NEW prealloc") \ - EM(rxrpc_call_put_already_queued, "PUT alreadyq") \ EM(rxrpc_call_put_discard_prealloc, "PUT disc-pre") \ EM(rxrpc_call_put_input, "PUT input ") \ EM(rxrpc_call_put_kernel, "PUT kernel ") \ @@ -168,11 +166,8 @@ EM(rxrpc_call_put_release_sock_tba, "PUT rls-sk-a") \ EM(rxrpc_call_put_send_ack, "PUT send-ack") \ EM(rxrpc_call_put_sendmsg, "PUT sendmsg ") \ - EM(rxrpc_call_put_timer, "PUT timer ") \ - EM(rxrpc_call_put_timer_already, "PUT timer-al") \ EM(rxrpc_call_put_unnotify, "PUT unnotify") \ EM(rxrpc_call_put_userid_exists, "PUT u-exists") \ - EM(rxrpc_call_put_work, "PUT work ") \ EM(rxrpc_call_queue_abort, "QUE abort ") \ EM(rxrpc_call_queue_requeue, "QUE requeue ") \ EM(rxrpc_call_queue_resend, "QUE resend ") \ @@ -368,6 +363,7 @@ 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_out_of_step, "OUT-OF-STEP") \ EM(rxrpc_txbuf_see_send_more, "SEE SEND+ ") \ E_(rxrpc_txbuf_see_unacked, "SEE UNACKED") diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index c588c0e81f63..03523a864c11 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -598,6 +598,7 @@ struct rxrpc_call { u32 next_req_timo; /* Timeout for next Rx request packet (jif) */ struct timer_list timer; /* Combined event timer */ struct work_struct processor; /* Event processor */ + struct work_struct destroyer; /* In-process-context destroyer */ rxrpc_notify_rx_t notify_rx; /* kernel service Rx notification function */ struct list_head link; /* link in master call list */ struct list_head chan_wait_link; /* Link in conn->bundle->waiting_calls */ @@ -827,8 +828,6 @@ void rxrpc_reduce_call_timer(struct rxrpc_call *call, unsigned long now, enum rxrpc_timer_trace why); -void rxrpc_delete_call_timer(struct rxrpc_call *call); - /* * call_object.c */ @@ -847,8 +846,7 @@ void rxrpc_incoming_call(struct rxrpc_sock *, struct rxrpc_call *, struct sk_buff *); void rxrpc_release_call(struct rxrpc_sock *, struct rxrpc_call *); void rxrpc_release_calls_on_socket(struct rxrpc_sock *); -bool __rxrpc_queue_call(struct rxrpc_call *, enum rxrpc_call_trace); -bool rxrpc_queue_call(struct rxrpc_call *, enum rxrpc_call_trace); +void rxrpc_queue_call(struct rxrpc_call *, enum rxrpc_call_trace); void rxrpc_see_call(struct rxrpc_call *, enum rxrpc_call_trace); bool rxrpc_try_get_call(struct rxrpc_call *, enum rxrpc_call_trace); void rxrpc_get_call(struct rxrpc_call *, enum rxrpc_call_trace); diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 29ca02e53c47..049b92b1c040 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -323,8 +323,8 @@ recheck_state: rxrpc_shrink_call_tx_buffer(call); if (call->state == RXRPC_CALL_COMPLETE) { - rxrpc_delete_call_timer(call); - goto out_put; + del_timer_sync(&call->timer); + goto out; } /* Work out if any timeouts tripped */ @@ -432,16 +432,15 @@ recheck_state: rxrpc_reduce_call_timer(call, next, now, rxrpc_timer_restart); /* other events may have been raised since we started checking */ - if (call->events && call->state < RXRPC_CALL_COMPLETE) + if (call->events) goto requeue; -out_put: - rxrpc_put_call(call, rxrpc_call_put_work); out: _leave(""); return; requeue: - __rxrpc_queue_call(call, rxrpc_call_queue_requeue); + if (call->state < RXRPC_CALL_COMPLETE) + rxrpc_queue_call(call, rxrpc_call_queue_requeue); goto out; } diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 815209673115..9cd7e0190ef4 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -53,9 +53,7 @@ static void rxrpc_call_timer_expired(struct timer_list *t) if (call->state < RXRPC_CALL_COMPLETE) { trace_rxrpc_timer_expired(call, jiffies); - __rxrpc_queue_call(call, rxrpc_call_queue_timer); - } else { - rxrpc_put_call(call, rxrpc_call_put_already_queued); + rxrpc_queue_call(call, rxrpc_call_queue_timer); } } @@ -64,21 +62,14 @@ void rxrpc_reduce_call_timer(struct rxrpc_call *call, unsigned long now, enum rxrpc_timer_trace why) { - if (rxrpc_try_get_call(call, rxrpc_call_get_timer)) { - trace_rxrpc_timer(call, why, now); - if (timer_reduce(&call->timer, expire_at)) - rxrpc_put_call(call, rxrpc_call_put_timer_already); - } -} - -void rxrpc_delete_call_timer(struct rxrpc_call *call) -{ - if (del_timer_sync(&call->timer)) - rxrpc_put_call(call, rxrpc_call_put_timer); + trace_rxrpc_timer(call, why, now); + timer_reduce(&call->timer, expire_at); } static struct lock_class_key rxrpc_call_user_mutex_lock_class_key; +static void rxrpc_destroy_call(struct work_struct *); + /* * find an extant server call * - called in process context with IRQs enabled @@ -139,7 +130,8 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, &rxrpc_call_user_mutex_lock_class_key); timer_setup(&call->timer, rxrpc_call_timer_expired, 0); - INIT_WORK(&call->processor, &rxrpc_process_call); + INIT_WORK(&call->processor, rxrpc_process_call); + INIT_WORK(&call->destroyer, rxrpc_destroy_call); INIT_LIST_HEAD(&call->link); INIT_LIST_HEAD(&call->chan_wait_link); INIT_LIST_HEAD(&call->accept_link); @@ -423,34 +415,12 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx, } /* - * Queue a call's work processor, getting a ref to pass to the work queue. + * Queue a call's work processor. */ -bool rxrpc_queue_call(struct rxrpc_call *call, enum rxrpc_call_trace why) +void rxrpc_queue_call(struct rxrpc_call *call, enum rxrpc_call_trace why) { - int n; - - if (!__refcount_inc_not_zero(&call->ref, &n)) - return false; if (rxrpc_queue_work(&call->processor)) - trace_rxrpc_call(call->debug_id, n + 1, 0, why); - else - rxrpc_put_call(call, rxrpc_call_put_already_queued); - return true; -} - -/* - * Queue a call's work processor, passing the callers ref to the work queue. - */ -bool __rxrpc_queue_call(struct rxrpc_call *call, enum rxrpc_call_trace why) -{ - int n = refcount_read(&call->ref); - - ASSERTCMP(n, >=, 1); - if (rxrpc_queue_work(&call->processor)) - trace_rxrpc_call(call->debug_id, n, 0, why); - else - rxrpc_put_call(call, rxrpc_call_put_already_queued); - return true; + trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), 0, why); } /* @@ -514,7 +484,7 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) BUG(); rxrpc_put_call_slot(call); - rxrpc_delete_call_timer(call); + del_timer_sync(&call->timer); /* Make sure we don't get any more notifications */ write_lock_bh(&rx->recvmsg_lock); @@ -612,36 +582,41 @@ void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace why) } /* - * Final call destruction - but must be done in process context. + * Free up the call under RCU. */ -static void rxrpc_destroy_call(struct work_struct *work) +static void rxrpc_rcu_free_call(struct rcu_head *rcu) { - struct rxrpc_call *call = container_of(work, struct rxrpc_call, processor); - struct rxrpc_net *rxnet = call->rxnet; - - rxrpc_delete_call_timer(call); + struct rxrpc_call *call = container_of(rcu, struct rxrpc_call, rcu); + struct rxrpc_net *rxnet = READ_ONCE(call->rxnet); - rxrpc_put_connection(call->conn, rxrpc_conn_put_call); - rxrpc_put_peer(call->peer, rxrpc_peer_put_call); kmem_cache_free(rxrpc_call_jar, call); if (atomic_dec_and_test(&rxnet->nr_calls)) wake_up_var(&rxnet->nr_calls); } /* - * Final call destruction under RCU. + * Final call destruction - but must be done in process context. */ -static void rxrpc_rcu_destroy_call(struct rcu_head *rcu) +static void rxrpc_destroy_call(struct work_struct *work) { - struct rxrpc_call *call = container_of(rcu, struct rxrpc_call, rcu); + struct rxrpc_call *call = container_of(work, struct rxrpc_call, destroyer); + struct rxrpc_txbuf *txb; - if (in_softirq()) { - INIT_WORK(&call->processor, rxrpc_destroy_call); - if (!rxrpc_queue_work(&call->processor)) - BUG(); - } else { - rxrpc_destroy_call(&call->processor); + del_timer_sync(&call->timer); + cancel_work_sync(&call->processor); /* The processor may restart the timer */ + del_timer_sync(&call->timer); + + rxrpc_cleanup_ring(call); + while ((txb = list_first_entry_or_null(&call->tx_buffer, + struct rxrpc_txbuf, call_link))) { + list_del(&txb->call_link); + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_cleaned); } + rxrpc_put_txbuf(call->tx_pending, rxrpc_txbuf_put_cleaned); + rxrpc_free_skb(call->acks_soft_tbl, rxrpc_skb_put_ack); + rxrpc_put_connection(call->conn, rxrpc_conn_put_call); + rxrpc_put_peer(call->peer, rxrpc_peer_put_call); + call_rcu(&call->rcu, rxrpc_rcu_free_call); } /* @@ -649,23 +624,21 @@ static void rxrpc_rcu_destroy_call(struct rcu_head *rcu) */ void rxrpc_cleanup_call(struct rxrpc_call *call) { - struct rxrpc_txbuf *txb; - memset(&call->sock_node, 0xcd, sizeof(call->sock_node)); ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); ASSERT(test_bit(RXRPC_CALL_RELEASED, &call->flags)); - rxrpc_cleanup_ring(call); - while ((txb = list_first_entry_or_null(&call->tx_buffer, - struct rxrpc_txbuf, call_link))) { - list_del(&txb->call_link); - rxrpc_put_txbuf(txb, rxrpc_txbuf_put_cleaned); - } - rxrpc_put_txbuf(call->tx_pending, rxrpc_txbuf_put_cleaned); - rxrpc_free_skb(call->acks_soft_tbl, rxrpc_skb_put_ack); + del_timer_sync(&call->timer); + cancel_work(&call->processor); - call_rcu(&call->rcu, rxrpc_rcu_destroy_call); + if (in_softirq() || work_busy(&call->processor)) + /* Can't use the rxrpc workqueue as we need to cancel/flush + * something that may be running/waiting there. + */ + schedule_work(&call->destroyer); + else + rxrpc_destroy_call(&call->destroyer); } /* diff --git a/net/rxrpc/txbuf.c b/net/rxrpc/txbuf.c index 96bfee89927b..f93dc666a3a0 100644 --- a/net/rxrpc/txbuf.c +++ b/net/rxrpc/txbuf.c @@ -120,6 +120,8 @@ void rxrpc_shrink_call_tx_buffer(struct rxrpc_call *call) if (before(hard_ack, txb->seq)) break; + if (txb->seq != call->tx_bottom + 1) + rxrpc_see_txbuf(txb, rxrpc_txbuf_see_out_of_step); ASSERTCMP(txb->seq, ==, call->tx_bottom + 1); call->tx_bottom++; list_del_rcu(&txb->call_link); -- cgit v1.2.3 From 3cec055c56958c5498eeb3ed9fb2aef2d28c030f Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 25 Nov 2022 12:43:50 +0000 Subject: rxrpc: Don't hold a ref for connection workqueue Currently, rxrpc gives the connection's work item a ref on the connection when it queues it - and this is called from the timer expiration function. The problem comes when queue_work() fails (ie. the work item is already queued): the timer routine must put the ref - but this may cause the cleanup code to run. This has the unfortunate effect that the cleanup code may then be run in softirq context - which means that any spinlocks it might need to touch have to be guarded to disable softirqs (ie. they need a "_bh" suffix). (1) Don't give a ref to the work item. (2) Simplify handling of service connections by adding a separate active count so that the refcount isn't also used for this. (3) Connection destruction for both client and service connections can then be cleaned up by putting rxrpc_put_connection() out of line and making a tidy progression through the destruction code (offloaded to a workqueue if put from softirq or processor function context). The RCU part of the cleanup then only deals with the freeing at the end. (4) Make rxrpc_queue_conn() return immediately if it sees the active count is -1 rather then queuing the connection. (5) Make sure that the cleanup routine waits for the work item to complete. (6) Stash the rxrpc_net pointer in the conn struct so that the rcu free routine can use it, even if the local endpoint has been freed. Unfortunately, neither the timer nor the work item can simply get around the problem by just using refcount_inc_not_zero() as the waits would still have to be done, and there would still be the possibility of having to put the ref in the expiration function. Note the connection work item is mostly going to go away with the main event work being transferred to the I/O thread, so the wait in (6) will become obsolete. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 11 ++- net/rxrpc/ar-internal.h | 25 ++----- net/rxrpc/call_accept.c | 1 + net/rxrpc/conn_client.c | 31 ++------ net/rxrpc/conn_event.c | 4 - net/rxrpc/conn_object.c | 169 ++++++++++++++++++++++++------------------- net/rxrpc/conn_service.c | 4 +- net/rxrpc/net_ns.c | 2 +- net/rxrpc/proc.c | 5 +- 9 files changed, 123 insertions(+), 129 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 4538de0079a5..44a9be9836f9 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -112,7 +112,6 @@ EM(rxrpc_conn_get_service_conn, "GET svc-conn") \ EM(rxrpc_conn_new_client, "NEW client ") \ EM(rxrpc_conn_new_service, "NEW service ") \ - EM(rxrpc_conn_put_already_queued, "PUT alreadyq") \ EM(rxrpc_conn_put_call, "PUT call ") \ EM(rxrpc_conn_put_call_input, "PUT inp-call") \ EM(rxrpc_conn_put_conn_input, "PUT inp-conn") \ @@ -121,13 +120,13 @@ EM(rxrpc_conn_put_local_dead, "PUT loc-dead") \ EM(rxrpc_conn_put_noreuse, "PUT noreuse ") \ EM(rxrpc_conn_put_poke, "PUT poke ") \ + EM(rxrpc_conn_put_service_reaped, "PUT svc-reap") \ EM(rxrpc_conn_put_unbundle, "PUT unbundle") \ EM(rxrpc_conn_put_unidle, "PUT unidle ") \ - EM(rxrpc_conn_put_work, "PUT work ") \ - EM(rxrpc_conn_queue_challenge, "GQ chall ") \ - EM(rxrpc_conn_queue_retry_work, "GQ retry-wk") \ - EM(rxrpc_conn_queue_rx_work, "GQ rx-work ") \ - EM(rxrpc_conn_queue_timer, "GQ timer ") \ + EM(rxrpc_conn_queue_challenge, "QUE chall ") \ + EM(rxrpc_conn_queue_retry_work, "QUE retry-wk") \ + EM(rxrpc_conn_queue_rx_work, "QUE rx-work ") \ + EM(rxrpc_conn_queue_timer, "QUE timer ") \ EM(rxrpc_conn_see_new_service_conn, "SEE new-svc ") \ EM(rxrpc_conn_see_reap_service, "SEE reap-svc") \ E_(rxrpc_conn_see_work, "SEE work ") diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 03523a864c11..41a57c145f2b 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -76,7 +76,7 @@ struct rxrpc_net { bool kill_all_client_conns; atomic_t nr_client_conns; spinlock_t client_conn_cache_lock; /* Lock for ->*_client_conns */ - spinlock_t client_conn_discard_lock; /* Prevent multiple discarders */ + struct mutex client_conn_discard_lock; /* Prevent multiple discarders */ struct list_head idle_client_conns; struct work_struct client_conn_reaper; struct timer_list client_conn_reap_timer; @@ -432,9 +432,11 @@ struct rxrpc_connection { struct rxrpc_conn_proto proto; struct rxrpc_local *local; /* Representation of local endpoint */ struct rxrpc_peer *peer; /* Remote endpoint */ + struct rxrpc_net *rxnet; /* Network namespace to which call belongs */ struct key *key; /* Security details */ refcount_t ref; + atomic_t active; /* Active count for service conns */ struct rcu_head rcu; struct list_head cache_link; @@ -455,6 +457,7 @@ struct rxrpc_connection { struct timer_list timer; /* Conn event timer */ struct work_struct processor; /* connection event processor */ + struct work_struct destructor; /* In-process-context destroyer */ struct rxrpc_bundle *bundle; /* Client connection bundle */ struct rb_node service_node; /* Node in peer->service_conns */ struct list_head proc_link; /* link in procfs list */ @@ -897,20 +900,20 @@ void rxrpc_process_delayed_final_acks(struct rxrpc_connection *, bool); extern unsigned int rxrpc_connection_expiry; extern unsigned int rxrpc_closed_conn_expiry; -struct rxrpc_connection *rxrpc_alloc_connection(gfp_t); +struct rxrpc_connection *rxrpc_alloc_connection(struct rxrpc_net *, gfp_t); struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *, struct sk_buff *, struct rxrpc_peer **); void __rxrpc_disconnect_call(struct rxrpc_connection *, struct rxrpc_call *); void rxrpc_disconnect_call(struct rxrpc_call *); -void rxrpc_kill_connection(struct rxrpc_connection *); -bool rxrpc_queue_conn(struct rxrpc_connection *, enum rxrpc_conn_trace); +void rxrpc_kill_client_conn(struct rxrpc_connection *); +void rxrpc_queue_conn(struct rxrpc_connection *, enum rxrpc_conn_trace); void rxrpc_see_connection(struct rxrpc_connection *, enum rxrpc_conn_trace); struct rxrpc_connection *rxrpc_get_connection(struct rxrpc_connection *, enum rxrpc_conn_trace); struct rxrpc_connection *rxrpc_get_connection_maybe(struct rxrpc_connection *, enum rxrpc_conn_trace); -void rxrpc_put_service_conn(struct rxrpc_connection *, enum rxrpc_conn_trace); +void rxrpc_put_connection(struct rxrpc_connection *, enum rxrpc_conn_trace); void rxrpc_service_connection_reaper(struct work_struct *); void rxrpc_destroy_all_connections(struct rxrpc_net *); @@ -924,18 +927,6 @@ static inline bool rxrpc_conn_is_service(const struct rxrpc_connection *conn) return !rxrpc_conn_is_client(conn); } -static inline void rxrpc_put_connection(struct rxrpc_connection *conn, - enum rxrpc_conn_trace why) -{ - if (!conn) - return; - - if (rxrpc_conn_is_client(conn)) - rxrpc_put_client_conn(conn, why); - else - rxrpc_put_service_conn(conn, why); -} - static inline void rxrpc_reduce_conn_timer(struct rxrpc_connection *conn, unsigned long expire_at) { diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index dd4ca4bee77f..8d106b626aa3 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -308,6 +308,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, rxrpc_new_incoming_connection(rx, conn, sec, skb); } else { rxrpc_get_connection(conn, rxrpc_conn_get_service_conn); + atomic_inc(&conn->active); } /* And now we can allocate and set up a new call */ diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 34ff6fa85c32..9485a3d18f29 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -51,7 +51,7 @@ static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle); static int rxrpc_get_client_connection_id(struct rxrpc_connection *conn, gfp_t gfp) { - struct rxrpc_net *rxnet = conn->local->rxnet; + struct rxrpc_net *rxnet = conn->rxnet; int id; _enter(""); @@ -179,7 +179,7 @@ rxrpc_alloc_client_connection(struct rxrpc_bundle *bundle, gfp_t gfp) _enter(""); - conn = rxrpc_alloc_connection(gfp); + conn = rxrpc_alloc_connection(rxnet, gfp); if (!conn) { _leave(" = -ENOMEM"); return ERR_PTR(-ENOMEM); @@ -243,7 +243,7 @@ static bool rxrpc_may_reuse_conn(struct rxrpc_connection *conn) if (!conn) goto dont_reuse; - rxnet = conn->local->rxnet; + rxnet = conn->rxnet; if (test_bit(RXRPC_CONN_DONT_REUSE, &conn->flags)) goto dont_reuse; @@ -970,7 +970,7 @@ static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle) /* * Clean up a dead client connection. */ -static void rxrpc_kill_client_conn(struct rxrpc_connection *conn) +void rxrpc_kill_client_conn(struct rxrpc_connection *conn) { struct rxrpc_local *local = conn->local; struct rxrpc_net *rxnet = local->rxnet; @@ -981,23 +981,6 @@ static void rxrpc_kill_client_conn(struct rxrpc_connection *conn) atomic_dec(&rxnet->nr_client_conns); rxrpc_put_client_connection_id(conn); - rxrpc_kill_connection(conn); -} - -/* - * Clean up a dead client connections. - */ -void rxrpc_put_client_conn(struct rxrpc_connection *conn, - enum rxrpc_conn_trace why) -{ - unsigned int debug_id = conn->debug_id; - bool dead; - int r; - - dead = __refcount_dec_and_test(&conn->ref, &r); - trace_rxrpc_conn(debug_id, r - 1, why); - if (dead) - rxrpc_kill_client_conn(conn); } /* @@ -1023,7 +1006,7 @@ void rxrpc_discard_expired_client_conns(struct work_struct *work) } /* Don't double up on the discarding */ - if (!spin_trylock(&rxnet->client_conn_discard_lock)) { + if (!mutex_trylock(&rxnet->client_conn_discard_lock)) { _leave(" [already]"); return; } @@ -1061,6 +1044,7 @@ next: goto not_yet_expired; } + atomic_dec(&conn->active); trace_rxrpc_client(conn, -1, rxrpc_client_discard); list_del_init(&conn->cache_link); @@ -1087,7 +1071,7 @@ not_yet_expired: out: spin_unlock(&rxnet->client_conn_cache_lock); - spin_unlock(&rxnet->client_conn_discard_lock); + mutex_unlock(&rxnet->client_conn_discard_lock); _leave(""); } @@ -1127,6 +1111,7 @@ void rxrpc_clean_up_local_conns(struct rxrpc_local *local) list_for_each_entry_safe(conn, tmp, &rxnet->idle_client_conns, cache_link) { if (conn->local == local) { + atomic_dec(&conn->active); trace_rxrpc_client(conn, -1, rxrpc_client_discard); list_move(&conn->cache_link, &graveyard); } diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 49d885f73fa5..23a74e35052d 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -478,8 +478,4 @@ void rxrpc_process_connection(struct work_struct *work) rxrpc_do_process_connection(conn); rxrpc_unuse_local(conn->local, rxrpc_local_unuse_conn_work); } - - rxrpc_put_connection(conn, rxrpc_conn_put_work); - _leave(""); - return; } diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index f7c271a740ed..c2e05ea29f12 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -19,7 +19,9 @@ unsigned int __read_mostly rxrpc_connection_expiry = 10 * 60; unsigned int __read_mostly rxrpc_closed_conn_expiry = 10; -static void rxrpc_destroy_connection(struct rcu_head *); +static void rxrpc_clean_up_connection(struct work_struct *work); +static void rxrpc_set_service_reap_timer(struct rxrpc_net *rxnet, + unsigned long reap_at); static void rxrpc_connection_timer(struct timer_list *timer) { @@ -32,7 +34,8 @@ static void rxrpc_connection_timer(struct timer_list *timer) /* * allocate a new connection */ -struct rxrpc_connection *rxrpc_alloc_connection(gfp_t gfp) +struct rxrpc_connection *rxrpc_alloc_connection(struct rxrpc_net *rxnet, + gfp_t gfp) { struct rxrpc_connection *conn; @@ -42,10 +45,12 @@ struct rxrpc_connection *rxrpc_alloc_connection(gfp_t gfp) if (conn) { INIT_LIST_HEAD(&conn->cache_link); timer_setup(&conn->timer, &rxrpc_connection_timer, 0); - INIT_WORK(&conn->processor, &rxrpc_process_connection); + INIT_WORK(&conn->processor, rxrpc_process_connection); + INIT_WORK(&conn->destructor, rxrpc_clean_up_connection); INIT_LIST_HEAD(&conn->proc_link); INIT_LIST_HEAD(&conn->link); skb_queue_head_init(&conn->rx_queue); + conn->rxnet = rxnet; conn->security = &rxrpc_no_security; spin_lock_init(&conn->state_lock); conn->debug_id = atomic_inc_return(&rxrpc_debug_id); @@ -224,53 +229,20 @@ void rxrpc_disconnect_call(struct rxrpc_call *call) set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); conn->idle_timestamp = jiffies; -} - -/* - * Kill off a connection. - */ -void rxrpc_kill_connection(struct rxrpc_connection *conn) -{ - struct rxrpc_net *rxnet = conn->local->rxnet; - - ASSERT(!rcu_access_pointer(conn->channels[0].call) && - !rcu_access_pointer(conn->channels[1].call) && - !rcu_access_pointer(conn->channels[2].call) && - !rcu_access_pointer(conn->channels[3].call)); - ASSERT(list_empty(&conn->cache_link)); - - write_lock(&rxnet->conn_lock); - list_del_init(&conn->proc_link); - write_unlock(&rxnet->conn_lock); - - /* Drain the Rx queue. Note that even though we've unpublished, an - * incoming packet could still be being added to our Rx queue, so we - * will need to drain it again in the RCU cleanup handler. - */ - rxrpc_purge_queue(&conn->rx_queue); - - /* Leave final destruction to RCU. The connection processor work item - * must carry a ref on the connection to prevent us getting here whilst - * it is queued or running. - */ - call_rcu(&conn->rcu, rxrpc_destroy_connection); + if (atomic_dec_and_test(&conn->active)) + rxrpc_set_service_reap_timer(conn->rxnet, + jiffies + rxrpc_connection_expiry); } /* * Queue a connection's work processor, getting a ref to pass to the work * queue. */ -bool rxrpc_queue_conn(struct rxrpc_connection *conn, enum rxrpc_conn_trace why) +void rxrpc_queue_conn(struct rxrpc_connection *conn, enum rxrpc_conn_trace why) { - int r; - - if (!__refcount_inc_not_zero(&conn->ref, &r)) - return false; - if (rxrpc_queue_work(&conn->processor)) - trace_rxrpc_conn(conn->debug_id, why, r + 1); - else - rxrpc_put_connection(conn, rxrpc_conn_put_already_queued); - return true; + if (atomic_read(&conn->active) >= 0 && + rxrpc_queue_work(&conn->processor)) + rxrpc_see_connection(conn, why); } /* @@ -327,51 +299,96 @@ static void rxrpc_set_service_reap_timer(struct rxrpc_net *rxnet, timer_reduce(&rxnet->service_conn_reap_timer, reap_at); } -/* - * Release a service connection - */ -void rxrpc_put_service_conn(struct rxrpc_connection *conn, - enum rxrpc_conn_trace why) -{ - unsigned int debug_id = conn->debug_id; - int r; - - __refcount_dec(&conn->ref, &r); - trace_rxrpc_conn(debug_id, r - 1, why); - if (r - 1 == 1) - rxrpc_set_service_reap_timer(conn->local->rxnet, - jiffies + rxrpc_connection_expiry); -} - /* * destroy a virtual connection */ -static void rxrpc_destroy_connection(struct rcu_head *rcu) +static void rxrpc_rcu_free_connection(struct rcu_head *rcu) { struct rxrpc_connection *conn = container_of(rcu, struct rxrpc_connection, rcu); + struct rxrpc_net *rxnet = conn->rxnet; _enter("{%d,u=%d}", conn->debug_id, refcount_read(&conn->ref)); trace_rxrpc_conn(conn->debug_id, refcount_read(&conn->ref), rxrpc_conn_free); + kfree(conn); - ASSERTCMP(refcount_read(&conn->ref), ==, 0); + if (atomic_dec_and_test(&rxnet->nr_conns)) + wake_up_var(&rxnet->nr_conns); +} + +/* + * Clean up a dead connection. + */ +static void rxrpc_clean_up_connection(struct work_struct *work) +{ + struct rxrpc_connection *conn = + container_of(work, struct rxrpc_connection, destructor); + struct rxrpc_net *rxnet = conn->rxnet; + + ASSERT(!rcu_access_pointer(conn->channels[0].call) && + !rcu_access_pointer(conn->channels[1].call) && + !rcu_access_pointer(conn->channels[2].call) && + !rcu_access_pointer(conn->channels[3].call)); + ASSERT(list_empty(&conn->cache_link)); del_timer_sync(&conn->timer); + cancel_work_sync(&conn->processor); /* Processing may restart the timer */ + del_timer_sync(&conn->timer); + + write_lock(&rxnet->conn_lock); + list_del_init(&conn->proc_link); + write_unlock(&rxnet->conn_lock); + rxrpc_purge_queue(&conn->rx_queue); + rxrpc_kill_client_conn(conn); + conn->security->clear(conn); key_put(conn->key); rxrpc_put_bundle(conn->bundle, rxrpc_bundle_put_conn); rxrpc_put_peer(conn->peer, rxrpc_peer_put_conn); - - if (atomic_dec_and_test(&conn->local->rxnet->nr_conns)) - wake_up_var(&conn->local->rxnet->nr_conns); rxrpc_put_local(conn->local, rxrpc_local_put_kill_conn); - kfree(conn); - _leave(""); + /* Drain the Rx queue. Note that even though we've unpublished, an + * incoming packet could still be being added to our Rx queue, so we + * will need to drain it again in the RCU cleanup handler. + */ + rxrpc_purge_queue(&conn->rx_queue); + + call_rcu(&conn->rcu, rxrpc_rcu_free_connection); +} + +/* + * Drop a ref on a connection. + */ +void rxrpc_put_connection(struct rxrpc_connection *conn, + enum rxrpc_conn_trace why) +{ + unsigned int debug_id; + bool dead; + int r; + + if (!conn) + return; + + debug_id = conn->debug_id; + dead = __refcount_dec_and_test(&conn->ref, &r); + trace_rxrpc_conn(debug_id, r - 1, why); + if (dead) { + del_timer(&conn->timer); + cancel_work(&conn->processor); + + if (in_softirq() || work_busy(&conn->processor) || + timer_pending(&conn->timer)) + /* Can't use the rxrpc workqueue as we need to cancel/flush + * something that may be running/waiting there. + */ + schedule_work(&conn->destructor); + else + rxrpc_clean_up_connection(&conn->destructor); + } } /* @@ -383,6 +400,7 @@ void rxrpc_service_connection_reaper(struct work_struct *work) struct rxrpc_net *rxnet = container_of(work, struct rxrpc_net, service_conn_reaper); unsigned long expire_at, earliest, idle_timestamp, now; + int active; LIST_HEAD(graveyard); @@ -393,8 +411,8 @@ void rxrpc_service_connection_reaper(struct work_struct *work) write_lock(&rxnet->conn_lock); list_for_each_entry_safe(conn, _p, &rxnet->service_conns, link) { - ASSERTCMP(refcount_read(&conn->ref), >, 0); - if (likely(refcount_read(&conn->ref) > 1)) + ASSERTCMP(atomic_read(&conn->active), >=, 0); + if (likely(atomic_read(&conn->active) > 0)) continue; if (conn->state == RXRPC_CONN_SERVICE_PREALLOC) continue; @@ -405,8 +423,8 @@ void rxrpc_service_connection_reaper(struct work_struct *work) if (conn->local->service_closed) expire_at = idle_timestamp + rxrpc_closed_conn_expiry * HZ; - _debug("reap CONN %d { u=%d,t=%ld }", - conn->debug_id, refcount_read(&conn->ref), + _debug("reap CONN %d { a=%d,t=%ld }", + conn->debug_id, atomic_read(&conn->active), (long)expire_at - (long)now); if (time_before(now, expire_at)) { @@ -416,10 +434,11 @@ void rxrpc_service_connection_reaper(struct work_struct *work) } } - /* The usage count sits at 1 whilst the object is unused on the - * list; we reduce that to 0 to make the object unavailable. + /* The activity count sits at 0 whilst the conn is unused on + * the list; we reduce that to -1 to make the conn unavailable. */ - if (!refcount_dec_if_one(&conn->ref)) + active = 0; + if (!atomic_try_cmpxchg(&conn->active, &active, -1)) continue; rxrpc_see_connection(conn, rxrpc_conn_see_reap_service); @@ -443,8 +462,8 @@ void rxrpc_service_connection_reaper(struct work_struct *work) link); list_del_init(&conn->link); - ASSERTCMP(refcount_read(&conn->ref), ==, 0); - rxrpc_kill_connection(conn); + ASSERTCMP(atomic_read(&conn->active), ==, -1); + rxrpc_put_connection(conn, rxrpc_conn_put_service_reaped); } _leave(""); diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c index 2c44d67b43dc..b5ae7c753fc3 100644 --- a/net/rxrpc/conn_service.c +++ b/net/rxrpc/conn_service.c @@ -125,7 +125,7 @@ replace_old_connection: struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *rxnet, gfp_t gfp) { - struct rxrpc_connection *conn = rxrpc_alloc_connection(gfp); + struct rxrpc_connection *conn = rxrpc_alloc_connection(rxnet, gfp); if (conn) { /* We maintain an extra ref on the connection whilst it is on @@ -181,6 +181,8 @@ void rxrpc_new_incoming_connection(struct rxrpc_sock *rx, conn->service_id == rx->service_upgrade.from) conn->service_id = rx->service_upgrade.to; + atomic_set(&conn->active, 1); + /* Make the connection a target for incoming packets. */ rxrpc_publish_service_conn(conn->peer, conn); } diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c index 84242c0e467c..5905530e2f33 100644 --- a/net/rxrpc/net_ns.c +++ b/net/rxrpc/net_ns.c @@ -65,7 +65,7 @@ static __net_init int rxrpc_init_net(struct net *net) atomic_set(&rxnet->nr_client_conns, 0); rxnet->kill_all_client_conns = false; spin_lock_init(&rxnet->client_conn_cache_lock); - spin_lock_init(&rxnet->client_conn_discard_lock); + mutex_init(&rxnet->client_conn_discard_lock); INIT_LIST_HEAD(&rxnet->idle_client_conns); INIT_WORK(&rxnet->client_conn_reaper, rxrpc_discard_expired_client_conns); diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index bb2edf6db896..d3a6d24cf871 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -159,7 +159,7 @@ static int rxrpc_connection_seq_show(struct seq_file *seq, void *v) seq_puts(seq, "Proto Local " " Remote " - " SvID ConnID End Use State Key " + " SvID ConnID End Ref Act State Key " " Serial ISerial CallId0 CallId1 CallId2 CallId3\n" ); return 0; @@ -177,7 +177,7 @@ static int rxrpc_connection_seq_show(struct seq_file *seq, void *v) sprintf(rbuff, "%pISpc", &conn->peer->srx.transport); print: seq_printf(seq, - "UDP %-47.47s %-47.47s %4x %08x %s %3u" + "UDP %-47.47s %-47.47s %4x %08x %s %3u %3d" " %s %08x %08x %08x %08x %08x %08x %08x\n", lbuff, rbuff, @@ -185,6 +185,7 @@ print: conn->proto.cid, rxrpc_conn_is_service(conn) ? "Svc" : "Clt", refcount_read(&conn->ref), + atomic_read(&conn->active), rxrpc_conn_states[conn->state], key_serial(conn->key), atomic_read(&conn->serial), -- cgit v1.2.3 From 15f661dc95daec9b38e8e4cc931c95afe0ae0cef Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 10 Oct 2022 15:51:39 +0100 Subject: rxrpc: Implement a mechanism to send an event notification to a call Provide a means by which an event notification can be sent to a call such that the I/O thread can process it rather than it being done in a separate workqueue. This will allow a lot of locking to be removed. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 52 ++++++++++++++++++++++++++++++++++++++++++++ net/rxrpc/ar-internal.h | 5 ++++- net/rxrpc/call_object.c | 24 ++++++++++++++++++++ net/rxrpc/input.c | 3 +-- net/rxrpc/io_thread.c | 20 +++++++++++++++-- net/rxrpc/local_object.c | 1 + 6 files changed, 100 insertions(+), 5 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 44a9be9836f9..0b12d96c7921 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -16,6 +16,13 @@ /* * Declare tracing information enums and their string mappings for display. */ +#define rxrpc_call_poke_traces \ + EM(rxrpc_call_poke_error, "Error") \ + EM(rxrpc_call_poke_idle, "Idle") \ + EM(rxrpc_call_poke_start, "Start") \ + EM(rxrpc_call_poke_timer, "Timer") \ + E_(rxrpc_call_poke_timer_now, "Timer-now") + #define rxrpc_skb_traces \ EM(rxrpc_skb_eaten_by_unshare, "ETN unshare ") \ EM(rxrpc_skb_eaten_by_unshare_nomem, "ETN unshar-nm") \ @@ -150,6 +157,7 @@ EM(rxrpc_call_get_input, "GET input ") \ EM(rxrpc_call_get_kernel_service, "GET krnl-srv") \ EM(rxrpc_call_get_notify_socket, "GET notify ") \ + EM(rxrpc_call_get_poke, "GET poke ") \ EM(rxrpc_call_get_recvmsg, "GET recvmsg ") \ EM(rxrpc_call_get_release_sock, "GET rel-sock") \ EM(rxrpc_call_get_sendmsg, "GET sendmsg ") \ @@ -160,6 +168,7 @@ EM(rxrpc_call_put_discard_prealloc, "PUT disc-pre") \ EM(rxrpc_call_put_input, "PUT input ") \ EM(rxrpc_call_put_kernel, "PUT kernel ") \ + EM(rxrpc_call_put_poke, "PUT poke ") \ EM(rxrpc_call_put_recvmsg, "PUT recvmsg ") \ EM(rxrpc_call_put_release_sock, "PUT rls-sock") \ EM(rxrpc_call_put_release_sock_tba, "PUT rls-sk-a") \ @@ -378,6 +387,7 @@ #define E_(a, b) a enum rxrpc_bundle_trace { rxrpc_bundle_traces } __mode(byte); +enum rxrpc_call_poke_trace { rxrpc_call_poke_traces } __mode(byte); enum rxrpc_call_trace { rxrpc_call_traces } __mode(byte); enum rxrpc_client_trace { rxrpc_client_traces } __mode(byte); enum rxrpc_congest_change { rxrpc_congest_changes } __mode(byte); @@ -408,6 +418,7 @@ enum rxrpc_txqueue_trace { rxrpc_txqueue_traces } __mode(byte); #define E_(a, b) TRACE_DEFINE_ENUM(a); rxrpc_bundle_traces; +rxrpc_call_poke_traces; rxrpc_call_traces; rxrpc_client_traces; rxrpc_congest_changes; @@ -1747,6 +1758,47 @@ TRACE_EVENT(rxrpc_txbuf, __entry->ref) ); +TRACE_EVENT(rxrpc_poke_call, + TP_PROTO(struct rxrpc_call *call, bool busy, + enum rxrpc_call_poke_trace what), + + TP_ARGS(call, busy, what), + + TP_STRUCT__entry( + __field(unsigned int, call_debug_id ) + __field(bool, busy ) + __field(enum rxrpc_call_poke_trace, what ) + ), + + TP_fast_assign( + __entry->call_debug_id = call->debug_id; + __entry->busy = busy; + __entry->what = what; + ), + + TP_printk("c=%08x %s%s", + __entry->call_debug_id, + __print_symbolic(__entry->what, rxrpc_call_poke_traces), + __entry->busy ? "!" : "") + ); + +TRACE_EVENT(rxrpc_call_poked, + TP_PROTO(struct rxrpc_call *call), + + TP_ARGS(call), + + TP_STRUCT__entry( + __field(unsigned int, call_debug_id ) + ), + + TP_fast_assign( + __entry->call_debug_id = call->debug_id; + ), + + TP_printk("c=%08x", + __entry->call_debug_id) + ); + #undef EM #undef E_ #endif /* _TRACE_RXRPC_H */ diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 654e9dab107c..a80655fa9dfb 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -292,6 +292,7 @@ struct rxrpc_local { struct sk_buff_head reject_queue; /* packets awaiting rejection */ struct sk_buff_head event_queue; /* endpoint event packets awaiting processing */ struct sk_buff_head rx_queue; /* Received packets */ + struct list_head call_attend_q; /* Calls requiring immediate attention */ struct rb_root client_bundles; /* Client connection bundles by socket params */ spinlock_t client_bundles_lock; /* Lock for client_bundles */ spinlock_t lock; /* access lock */ @@ -616,6 +617,7 @@ struct rxrpc_call { struct list_head recvmsg_link; /* Link in rx->recvmsg_q */ struct list_head sock_link; /* Link in rx->sock_calls */ struct rb_node sock_node; /* Node in rx->calls */ + struct list_head attend_link; /* Link in local->call_attend_q */ struct rxrpc_txbuf *tx_pending; /* Tx buffer being filled */ wait_queue_head_t waitq; /* Wait queue for channel or Tx */ s64 tx_total_len; /* Total length left to be transmitted (or -1) */ @@ -843,6 +845,7 @@ extern const char *const rxrpc_call_states[]; extern const char *const rxrpc_call_completions[]; extern struct kmem_cache *rxrpc_call_jar; +void rxrpc_poke_call(struct rxrpc_call *call, enum rxrpc_call_poke_trace what); struct rxrpc_call *rxrpc_find_call_by_user_ID(struct rxrpc_sock *, unsigned long); struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *, gfp_t, unsigned int); struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *, @@ -951,7 +954,7 @@ void rxrpc_unpublish_service_conn(struct rxrpc_connection *); /* * input.c */ -void rxrpc_input_call_packet(struct rxrpc_call *, struct sk_buff *); +void rxrpc_input_call_event(struct rxrpc_call *, struct sk_buff *); void rxrpc_input_implicit_end_call(struct rxrpc_sock *, struct rxrpc_connection *, struct rxrpc_call *); diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index f6d1b3a6f8c6..997641e3d1c8 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -45,6 +45,29 @@ static struct semaphore rxrpc_call_limiter = static struct semaphore rxrpc_kernel_call_limiter = __SEMAPHORE_INITIALIZER(rxrpc_kernel_call_limiter, 1000); +void rxrpc_poke_call(struct rxrpc_call *call, enum rxrpc_call_poke_trace what) +{ + struct rxrpc_local *local; + struct rxrpc_peer *peer = call->peer; + bool busy; + + if (WARN_ON_ONCE(!peer)) + return; + local = peer->local; + + if (call->state < RXRPC_CALL_COMPLETE) { + spin_lock_bh(&local->lock); + busy = !list_empty(&call->attend_link); + trace_rxrpc_poke_call(call, busy, what); + if (!busy) { + rxrpc_get_call(call, rxrpc_call_get_poke); + list_add_tail(&call->attend_link, &local->call_attend_q); + } + spin_unlock_bh(&local->lock); + rxrpc_wake_up_io_thread(local); + } +} + static void rxrpc_call_timer_expired(struct timer_list *t) { struct rxrpc_call *call = from_timer(call, t, timer); @@ -137,6 +160,7 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, INIT_LIST_HEAD(&call->accept_link); INIT_LIST_HEAD(&call->recvmsg_link); INIT_LIST_HEAD(&call->sock_link); + INIT_LIST_HEAD(&call->attend_link); INIT_LIST_HEAD(&call->tx_buffer); skb_queue_head_init(&call->recvmsg_queue); skb_queue_head_init(&call->rx_oos_queue); diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 13c52145a926..036f02371051 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -1017,8 +1017,7 @@ static void rxrpc_input_abort(struct rxrpc_call *call, struct sk_buff *skb) /* * Process an incoming call packet. */ -void rxrpc_input_call_packet(struct rxrpc_call *call, - struct sk_buff *skb) +void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); unsigned long timo; diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c index 416c6101cf78..cc249bc6b8cd 100644 --- a/net/rxrpc/io_thread.c +++ b/net/rxrpc/io_thread.c @@ -366,7 +366,7 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff *skb) /* Process a call packet; this either discards or passes on the ref * elsewhere. */ - rxrpc_input_call_packet(call, skb); + rxrpc_input_call_event(call, skb); goto out; discard: @@ -413,6 +413,7 @@ int rxrpc_io_thread(void *data) { struct sk_buff_head rx_queue; struct rxrpc_local *local = data; + struct rxrpc_call *call; struct sk_buff *skb; skb_queue_head_init(&rx_queue); @@ -422,6 +423,20 @@ int rxrpc_io_thread(void *data) for (;;) { rxrpc_inc_stat(local->rxnet, stat_io_loop); + /* Deal with calls that want immediate attention. */ + if ((call = list_first_entry_or_null(&local->call_attend_q, + struct rxrpc_call, + attend_link))) { + spin_lock_bh(&local->lock); + list_del_init(&call->attend_link); + spin_unlock_bh(&local->lock); + + trace_rxrpc_call_poked(call); + rxrpc_input_call_event(call, NULL); + rxrpc_put_call(call, rxrpc_call_put_poke); + continue; + } + /* Process received packets and errors. */ if ((skb = __skb_dequeue(&rx_queue))) { switch (skb->mark) { @@ -450,7 +465,8 @@ int rxrpc_io_thread(void *data) } set_current_state(TASK_INTERRUPTIBLE); - if (!skb_queue_empty(&local->rx_queue)) { + if (!skb_queue_empty(&local->rx_queue) || + !list_empty(&local->call_attend_q)) { __set_current_state(TASK_RUNNING); continue; } diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 6b4d77219f36..03f491cc23ef 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -104,6 +104,7 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet, skb_queue_head_init(&local->reject_queue); skb_queue_head_init(&local->event_queue); skb_queue_head_init(&local->rx_queue); + INIT_LIST_HEAD(&local->call_attend_q); local->client_bundles = RB_ROOT; spin_lock_init(&local->client_bundles_lock); spin_lock_init(&local->lock); -- cgit v1.2.3 From f3441d4125fc98995858550a5521b8d7daf0504a Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 20 Oct 2022 21:58:36 +0100 Subject: rxrpc: Copy client call parameters into rxrpc_call earlier Copy client call parameters into rxrpc_call earlier so that that can be used to convey them to the connection code - which can then be offloaded to the I/O thread. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 3 +++ net/rxrpc/ar-internal.h | 7 ++++++- net/rxrpc/call_accept.c | 2 ++ net/rxrpc/call_object.c | 50 +++++++++++++++++++++++++++----------------- net/rxrpc/conn_client.c | 2 +- net/rxrpc/io_thread.c | 4 ++-- net/rxrpc/output.c | 2 +- net/rxrpc/proc.c | 25 +++++++--------------- net/rxrpc/recvmsg.c | 8 +++---- net/rxrpc/security.c | 30 ++++++++++++++++++++++++++ net/rxrpc/txbuf.c | 2 +- 11 files changed, 87 insertions(+), 48 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 0b12d96c7921..8bd48358f757 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -52,6 +52,7 @@ #define rxrpc_local_traces \ EM(rxrpc_local_free, "FREE ") \ + EM(rxrpc_local_get_call, "GET call ") \ EM(rxrpc_local_get_client_conn, "GET conn-cln") \ EM(rxrpc_local_get_for_use, "GET for-use ") \ EM(rxrpc_local_get_peer, "GET peer ") \ @@ -61,6 +62,7 @@ EM(rxrpc_local_processing, "PROCESSING ") \ EM(rxrpc_local_put_already_queued, "PUT alreadyq") \ EM(rxrpc_local_put_bind, "PUT bind ") \ + EM(rxrpc_local_put_call, "PUT call ") \ EM(rxrpc_local_put_for_use, "PUT for-use ") \ EM(rxrpc_local_put_kill_conn, "PUT conn-kil") \ EM(rxrpc_local_put_peer, "PUT peer ") \ @@ -166,6 +168,7 @@ EM(rxrpc_call_new_client, "NEW client ") \ EM(rxrpc_call_new_prealloc_service, "NEW prealloc") \ EM(rxrpc_call_put_discard_prealloc, "PUT disc-pre") \ + EM(rxrpc_call_put_discard_error, "PUT disc-err") \ EM(rxrpc_call_put_input, "PUT input ") \ EM(rxrpc_call_put_kernel, "PUT kernel ") \ EM(rxrpc_call_put_poke, "PUT poke ") \ diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index a80655fa9dfb..3bd6a5eb2fb7 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -530,6 +530,7 @@ enum rxrpc_call_flag { RXRPC_CALL_UPGRADE, /* Service upgrade was requested for the call */ RXRPC_CALL_DELAY_ACK_PENDING, /* DELAY ACK generation is pending */ RXRPC_CALL_IDLE_ACK_PENDING, /* IDLE ACK generation is pending */ + RXRPC_CALL_EXCLUSIVE, /* The call uses a once-only connection */ }; /* @@ -592,10 +593,13 @@ struct rxrpc_call { struct rcu_head rcu; struct rxrpc_connection *conn; /* connection carrying call */ struct rxrpc_peer *peer; /* Peer record for remote address */ + struct rxrpc_local *local; /* Representation of local endpoint */ struct rxrpc_sock __rcu *socket; /* socket responsible */ struct rxrpc_net *rxnet; /* Network namespace to which call belongs */ + struct key *key; /* Security details */ const struct rxrpc_security *security; /* applied security module */ struct mutex user_mutex; /* User access mutex */ + struct sockaddr_rxrpc dest_srx; /* Destination address */ unsigned long delay_ack_at; /* When DELAY ACK needs to happen */ unsigned long ack_lost_at; /* When ACK is figured as lost */ unsigned long resend_at; /* When next resend needs to happen */ @@ -631,11 +635,11 @@ struct rxrpc_call { enum rxrpc_call_state state; /* current state of call */ enum rxrpc_call_completion completion; /* Call completion condition */ refcount_t ref; - u16 service_id; /* service ID */ u8 security_ix; /* Security type */ enum rxrpc_interruptibility interruptibility; /* At what point call may be interrupted */ u32 call_id; /* call ID on connection */ u32 cid; /* connection ID plus channel index */ + u32 security_level; /* Security level selected */ int debug_id; /* debug ID for printks */ unsigned short rx_pkt_offset; /* Current recvmsg packet offset */ unsigned short rx_pkt_len; /* Current recvmsg packet len */ @@ -1147,6 +1151,7 @@ extern const struct rxrpc_security rxkad; int __init rxrpc_init_security(void); const struct rxrpc_security *rxrpc_security_lookup(u8); void rxrpc_exit_security(void); +int rxrpc_init_client_call_security(struct rxrpc_call *); int rxrpc_init_client_conn_security(struct rxrpc_connection *); const struct rxrpc_security *rxrpc_get_incoming_security(struct rxrpc_sock *, struct sk_buff *); diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 8d106b626aa3..8bc327aa2beb 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -318,10 +318,12 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, (call_tail + 1) & (RXRPC_BACKLOG_MAX - 1)); rxrpc_see_call(call, rxrpc_call_see_accept); + call->local = rxrpc_get_local(conn->local, rxrpc_local_get_call); call->conn = conn; call->security = conn->security; call->security_ix = conn->security_ix; call->peer = rxrpc_get_peer(conn->peer, rxrpc_peer_get_accept); + call->dest_srx = peer->srx; call->cong_ssthresh = call->peer->cong_ssthresh; call->tx_last_sent = ktime_get_real(); return call; diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 997641e3d1c8..2622d06bb0d6 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -47,14 +47,9 @@ static struct semaphore rxrpc_kernel_call_limiter = void rxrpc_poke_call(struct rxrpc_call *call, enum rxrpc_call_poke_trace what) { - struct rxrpc_local *local; - struct rxrpc_peer *peer = call->peer; + struct rxrpc_local *local = call->local; bool busy; - if (WARN_ON_ONCE(!peer)) - return; - local = peer->local; - if (call->state < RXRPC_CALL_COMPLETE) { spin_lock_bh(&local->lock); busy = !list_empty(&call->attend_link); @@ -200,22 +195,45 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, */ static struct rxrpc_call *rxrpc_alloc_client_call(struct rxrpc_sock *rx, struct sockaddr_rxrpc *srx, + struct rxrpc_conn_parameters *cp, + struct rxrpc_call_params *p, gfp_t gfp, unsigned int debug_id) { struct rxrpc_call *call; ktime_t now; + int ret; _enter(""); call = rxrpc_alloc_call(rx, gfp, debug_id); if (!call) return ERR_PTR(-ENOMEM); - call->state = RXRPC_CALL_CLIENT_AWAIT_CONN; - call->service_id = srx->srx_service; now = ktime_get_real(); - call->acks_latest_ts = now; - call->cong_tstamp = now; + call->acks_latest_ts = now; + call->cong_tstamp = now; + call->state = RXRPC_CALL_CLIENT_AWAIT_CONN; + call->dest_srx = *srx; + call->interruptibility = p->interruptibility; + call->tx_total_len = p->tx_total_len; + call->key = key_get(cp->key); + call->local = rxrpc_get_local(cp->local, rxrpc_local_get_call); + if (p->kernel) + __set_bit(RXRPC_CALL_KERNEL, &call->flags); + if (cp->upgrade) + __set_bit(RXRPC_CALL_UPGRADE, &call->flags); + if (cp->exclusive) + __set_bit(RXRPC_CALL_EXCLUSIVE, &call->flags); + + ret = rxrpc_init_client_call_security(call); + if (ret < 0) { + __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, 0, ret); + rxrpc_put_call(call, rxrpc_call_put_discard_error); + return ERR_PTR(ret); + } + + trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), + p->user_call_ID, rxrpc_call_new_client); _leave(" = %p", call); return call; @@ -295,7 +313,7 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, return ERR_PTR(-ERESTARTSYS); } - call = rxrpc_alloc_client_call(rx, srx, gfp, debug_id); + call = rxrpc_alloc_client_call(rx, srx, cp, p, gfp, debug_id); if (IS_ERR(call)) { release_sock(&rx->sk); up(limiter); @@ -303,13 +321,6 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, return call; } - call->interruptibility = p->interruptibility; - call->tx_total_len = p->tx_total_len; - trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), - p->user_call_ID, rxrpc_call_new_client); - if (p->kernel) - __set_bit(RXRPC_CALL_KERNEL, &call->flags); - /* We need to protect a partially set up call against the user as we * will be acting outside the socket lock. */ @@ -413,7 +424,7 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx, rcu_assign_pointer(call->socket, rx); call->call_id = sp->hdr.callNumber; - call->service_id = sp->hdr.serviceId; + call->dest_srx.srx_service = sp->hdr.serviceId; call->cid = sp->hdr.cid; call->state = RXRPC_CALL_SERVER_SECURING; call->cong_tstamp = skb->tstamp; @@ -639,6 +650,7 @@ static void rxrpc_destroy_call(struct work_struct *work) rxrpc_free_skb(call->acks_soft_tbl, rxrpc_skb_put_ack); rxrpc_put_connection(call->conn, rxrpc_conn_put_call); rxrpc_put_peer(call->peer, rxrpc_peer_put_call); + rxrpc_put_local(call->local, rxrpc_local_put_call); call_rcu(&call->rcu, rxrpc_rcu_free_call); } diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 9485a3d18f29..ab3dd22fadc0 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -553,7 +553,7 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn, call->call_id = call_id; call->security = conn->security; call->security_ix = conn->security_ix; - call->service_id = conn->service_id; + call->dest_srx.srx_service = conn->service_id; trace_rxrpc_connect_call(call); diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c index cc249bc6b8cd..2119941b6d6c 100644 --- a/net/rxrpc/io_thread.c +++ b/net/rxrpc/io_thread.c @@ -343,8 +343,8 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff *skb) } if (call) { - if (sp->hdr.serviceId != call->service_id) - call->service_id = sp->hdr.serviceId; + if (sp->hdr.serviceId != call->dest_srx.srx_service) + call->dest_srx.srx_service = sp->hdr.serviceId; if ((int)sp->hdr.serial - (int)call->rx_serial > 0) call->rx_serial = sp->hdr.serial; if (!test_bit(RXRPC_CALL_RX_HEARD, &call->flags)) diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 131c7a76fb06..e2ce7dadbb7a 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -357,7 +357,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) pkt.whdr.userStatus = 0; pkt.whdr.securityIndex = call->security_ix; pkt.whdr._rsvd = 0; - pkt.whdr.serviceId = htons(call->service_id); + pkt.whdr.serviceId = htons(call->dest_srx.srx_service); pkt.abort_code = htonl(call->abort_code); iov[0].iov_base = &pkt; diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index 35d5b43c677e..5af7c8ee4b1a 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -49,8 +49,6 @@ static void rxrpc_call_seq_stop(struct seq_file *seq, void *v) static int rxrpc_call_seq_show(struct seq_file *seq, void *v) { struct rxrpc_local *local; - struct rxrpc_sock *rx; - struct rxrpc_peer *peer; struct rxrpc_call *call; struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq)); unsigned long timeout = 0; @@ -69,22 +67,13 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) call = list_entry(v, struct rxrpc_call, link); - rx = rcu_dereference(call->socket); - if (rx) { - local = READ_ONCE(rx->local); - if (local) - sprintf(lbuff, "%pISpc", &local->srx.transport); - else - strcpy(lbuff, "no_local"); - } else { - strcpy(lbuff, "no_socket"); - } - - peer = call->peer; - if (peer) - sprintf(rbuff, "%pISpc", &peer->srx.transport); + local = call->local; + if (local) + sprintf(lbuff, "%pISpc", &local->srx.transport); else - strcpy(rbuff, "no_connection"); + strcpy(lbuff, "no_local"); + + sprintf(rbuff, "%pISpc", &call->dest_srx.transport); if (call->state != RXRPC_CALL_SERVER_PREALLOC) { timeout = READ_ONCE(call->expect_rx_by); @@ -98,7 +87,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) " %-8.8s %08x %08x %08x %02x %08x %02x %08x %06lx\n", lbuff, rbuff, - call->service_id, + call->dest_srx.srx_service, call->cid, call->call_id, rxrpc_is_service_call(call) ? "Svc" : "Clt", diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index bfac9e09347e..5df7f468abed 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -490,11 +490,9 @@ try_again: } if (msg->msg_name && call->peer) { - struct sockaddr_rxrpc *srx = msg->msg_name; - size_t len = sizeof(call->peer->srx); + size_t len = sizeof(call->dest_srx); - memcpy(msg->msg_name, &call->peer->srx, len); - srx->srx_service = call->service_id; + memcpy(msg->msg_name, &call->dest_srx, len); msg->msg_namelen = len; } @@ -639,7 +637,7 @@ read_phase_complete: out: rxrpc_transmit_ack_packets(call->peer->local); if (_service) - *_service = call->service_id; + *_service = call->dest_srx.srx_service; mutex_unlock(&call->user_mutex); _leave(" = %d [%zu,%d]", ret, iov_iter_count(iter), *_abort); return ret; diff --git a/net/rxrpc/security.c b/net/rxrpc/security.c index e6ddac9b3732..209f2c25a0da 100644 --- a/net/rxrpc/security.c +++ b/net/rxrpc/security.c @@ -62,6 +62,36 @@ const struct rxrpc_security *rxrpc_security_lookup(u8 security_index) return rxrpc_security_types[security_index]; } +/* + * Initialise the security on a client call. + */ +int rxrpc_init_client_call_security(struct rxrpc_call *call) +{ + const struct rxrpc_security *sec; + struct rxrpc_key_token *token; + struct key *key = call->key; + int ret; + + if (!key) + return 0; + + ret = key_validate(key); + if (ret < 0) + return ret; + + for (token = key->payload.data[0]; token; token = token->next) { + sec = rxrpc_security_lookup(token->security_index); + if (sec) + goto found; + } + return -EKEYREJECTED; + +found: + call->security = sec; + _leave(" = 0"); + return 0; +} + /* * initialise the security on a client connection */ diff --git a/net/rxrpc/txbuf.c b/net/rxrpc/txbuf.c index f93dc666a3a0..90ff00c340cd 100644 --- a/net/rxrpc/txbuf.c +++ b/net/rxrpc/txbuf.c @@ -44,7 +44,7 @@ struct rxrpc_txbuf *rxrpc_alloc_txbuf(struct rxrpc_call *call, u8 packet_type, txb->wire.userStatus = 0; txb->wire.securityIndex = call->security_ix; txb->wire._rsvd = 0; - txb->wire.serviceId = htons(call->service_id); + txb->wire.serviceId = htons(call->dest_srx.srx_service); trace_rxrpc_txbuf(txb->debug_id, txb->call_debug_id, txb->seq, 1, -- cgit v1.2.3 From cf37b5987508878647161ec3cdba0bb00a1b607a Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 31 Mar 2022 23:55:08 +0100 Subject: rxrpc: Move DATA transmission into call processor work item Move DATA transmission into the call processor work item. In a future patch, this will be called from the I/O thread rather than being itsown work item. This will allow DATA transmission to be driven directly by incoming ACKs, pokes and timers as those are processed. The Tx queue is also split: The queue of packets prepared by sendmsg is now places in call->tx_sendmsg and the packet dispatcher decants the packets into call->tx_buffer as space becomes available in the transmission window. This allows sendmsg to run ahead of the available space to try and prevent an underflow in transmission. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 6 +++- net/rxrpc/ar-internal.h | 5 ++- net/rxrpc/call_event.c | 83 ++++++++++++++++++++++++++++++++++++++++---- net/rxrpc/call_object.c | 6 ++++ net/rxrpc/output.c | 48 +++++++++++++++++++++++++ net/rxrpc/sendmsg.c | 83 +++++++------------------------------------- net/rxrpc/txbuf.c | 10 ++++-- 7 files changed, 161 insertions(+), 80 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 8bd48358f757..c3043fbea0e6 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -183,6 +183,7 @@ EM(rxrpc_call_queue_requeue, "QUE requeue ") \ EM(rxrpc_call_queue_resend, "QUE resend ") \ EM(rxrpc_call_queue_timer, "QUE timer ") \ + EM(rxrpc_call_queue_tx_data, "QUE tx-data ") \ EM(rxrpc_call_see_accept, "SEE accept ") \ EM(rxrpc_call_see_activate_client, "SEE act-clnt") \ EM(rxrpc_call_see_connect_failed, "SEE con-fail") \ @@ -738,6 +739,7 @@ TRACE_EVENT(rxrpc_txqueue, __field(rxrpc_seq_t, acks_hard_ack ) __field(rxrpc_seq_t, tx_bottom ) __field(rxrpc_seq_t, tx_top ) + __field(rxrpc_seq_t, tx_prepared ) __field(int, tx_winsize ) ), @@ -747,16 +749,18 @@ TRACE_EVENT(rxrpc_txqueue, __entry->acks_hard_ack = call->acks_hard_ack; __entry->tx_bottom = call->tx_bottom; __entry->tx_top = call->tx_top; + __entry->tx_prepared = call->tx_prepared; __entry->tx_winsize = call->tx_winsize; ), - TP_printk("c=%08x %s f=%08x h=%08x n=%u/%u/%u", + TP_printk("c=%08x %s f=%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->tx_top - __entry->acks_hard_ack, + __entry->tx_prepared - __entry->tx_bottom, __entry->tx_winsize) ); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 3bd6a5eb2fb7..6af7298af39b 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -646,9 +646,11 @@ struct rxrpc_call { /* Transmitted data tracking. */ spinlock_t tx_lock; /* Transmit queue lock */ + struct list_head tx_sendmsg; /* Sendmsg prepared packets */ struct list_head tx_buffer; /* Buffer of transmissible packets */ rxrpc_seq_t tx_bottom; /* First packet in buffer */ rxrpc_seq_t tx_transmitted; /* Highest packet transmitted */ + rxrpc_seq_t tx_prepared; /* Highest Tx slot prepared. */ rxrpc_seq_t tx_top; /* Highest Tx slot allocated. */ u16 tx_backoff; /* Delay to insert due to Tx failure */ u8 tx_winsize; /* Maximum size of Tx window */ @@ -766,7 +768,7 @@ struct rxrpc_send_params { */ struct rxrpc_txbuf { struct rcu_head rcu; - struct list_head call_link; /* Link in call->tx_queue */ + struct list_head call_link; /* Link in call->tx_sendmsg/tx_buffer */ struct list_head tx_link; /* Link in live Enc queue or Tx queue */ struct rxrpc_call *call; /* Call to which belongs */ ktime_t last_sent; /* Time at which last transmitted */ @@ -1067,6 +1069,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *); int rxrpc_send_data_packet(struct rxrpc_call *, struct rxrpc_txbuf *); void rxrpc_reject_packets(struct rxrpc_local *); void rxrpc_send_keepalive(struct rxrpc_peer *); +void rxrpc_transmit_one(struct rxrpc_call *call, struct rxrpc_txbuf *txb); /* * peer_event.c diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 3925b55e2064..c9f835292f7b 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -291,6 +291,72 @@ out: _leave(""); } +static bool rxrpc_tx_window_has_space(struct rxrpc_call *call) +{ + unsigned int winsize = min_t(unsigned int, call->tx_winsize, + call->cong_cwnd + call->cong_extra); + rxrpc_seq_t window = call->acks_hard_ack, wtop = window + winsize; + rxrpc_seq_t tx_top = call->tx_top; + int space; + + space = wtop - tx_top; + return space > 0; +} + +/* + * Decant some if the sendmsg prepared queue into the transmission buffer. + */ +static void rxrpc_decant_prepared_tx(struct rxrpc_call *call) +{ + struct rxrpc_txbuf *txb; + + if (rxrpc_is_client_call(call) && + !test_bit(RXRPC_CALL_EXPOSED, &call->flags)) + rxrpc_expose_client_call(call); + + while ((txb = list_first_entry_or_null(&call->tx_sendmsg, + struct rxrpc_txbuf, call_link))) { + spin_lock(&call->tx_lock); + list_del(&txb->call_link); + spin_unlock(&call->tx_lock); + + call->tx_top = txb->seq; + list_add_tail(&txb->call_link, &call->tx_buffer); + + rxrpc_transmit_one(call, txb); + + // TODO: Drain the transmission buffers. Do this somewhere better + if (after(call->acks_hard_ack, call->tx_bottom + 16)) + rxrpc_shrink_call_tx_buffer(call); + + if (!rxrpc_tx_window_has_space(call)) + break; + } +} + +static void rxrpc_transmit_some_data(struct rxrpc_call *call) +{ + switch (call->state) { + case RXRPC_CALL_SERVER_ACK_REQUEST: + if (list_empty(&call->tx_sendmsg)) + return; + fallthrough; + + case RXRPC_CALL_SERVER_SEND_REPLY: + case RXRPC_CALL_SERVER_AWAIT_ACK: + case RXRPC_CALL_CLIENT_SEND_REQUEST: + case RXRPC_CALL_CLIENT_AWAIT_REPLY: + if (!rxrpc_tx_window_has_space(call)) + return; + if (list_empty(&call->tx_sendmsg)) + return; + rxrpc_decant_prepared_tx(call); + break; + default: + return; + } +} + /* * Handle retransmission and deferred ACK/abort generation. */ @@ -309,19 +375,22 @@ void rxrpc_process_call(struct work_struct *work) call->debug_id, rxrpc_call_states[call->state], call->events); recheck_state: + if (call->acks_hard_ack != call->tx_bottom) + rxrpc_shrink_call_tx_buffer(call); + /* Limit the number of times we do this before returning to the manager */ - iterations++; - if (iterations > 5) - goto requeue; + if (!rxrpc_tx_window_has_space(call) || + list_empty(&call->tx_sendmsg)) { + iterations++; + if (iterations > 5) + goto requeue; + } if (test_and_clear_bit(RXRPC_CALL_EV_ABORT, &call->events)) { rxrpc_send_abort_packet(call); goto recheck_state; } - if (READ_ONCE(call->acks_hard_ack) != call->tx_bottom) - rxrpc_shrink_call_tx_buffer(call); - if (call->state == RXRPC_CALL_COMPLETE) { del_timer_sync(&call->timer); goto out; @@ -387,6 +456,8 @@ recheck_state: set_bit(RXRPC_CALL_EV_RESEND, &call->events); } + rxrpc_transmit_some_data(call); + /* Process events */ if (test_and_clear_bit(RXRPC_CALL_EV_EXPIRED, &call->events)) { if (test_bit(RXRPC_CALL_RX_HEARD, &call->flags) && diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 2622d06bb0d6..96a7edd3a842 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -156,6 +156,7 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, INIT_LIST_HEAD(&call->recvmsg_link); INIT_LIST_HEAD(&call->sock_link); INIT_LIST_HEAD(&call->attend_link); + INIT_LIST_HEAD(&call->tx_sendmsg); INIT_LIST_HEAD(&call->tx_buffer); skb_queue_head_init(&call->recvmsg_queue); skb_queue_head_init(&call->rx_oos_queue); @@ -641,6 +642,11 @@ static void rxrpc_destroy_call(struct work_struct *work) del_timer_sync(&call->timer); rxrpc_cleanup_ring(call); + while ((txb = list_first_entry_or_null(&call->tx_sendmsg, + struct rxrpc_txbuf, call_link))) { + list_del(&txb->call_link); + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_cleaned); + } while ((txb = list_first_entry_or_null(&call->tx_buffer, struct rxrpc_txbuf, call_link))) { list_del(&txb->call_link); diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index e2ce7dadbb7a..c8147e50060b 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -465,6 +465,14 @@ dont_set_request_ack: trace_rxrpc_tx_data(call, txb->seq, serial, txb->wire.flags, test_bit(RXRPC_TXBUF_RESENT, &txb->flags), false); + + /* Track what we've attempted to transmit at least once so that the + * retransmission algorithm doesn't try to resend what we haven't sent + * yet. However, this can race as we can receive an ACK before we get + * to this point. But, OTOH, if we won't get an ACK mentioning this + * packet unless the far side received it (though it could have + * discarded it anyway and NAK'd it). + */ cmpxchg(&call->tx_transmitted, txb->seq - 1, txb->seq); /* send the packet with the don't fragment bit set if we currently @@ -712,3 +720,43 @@ void rxrpc_send_keepalive(struct rxrpc_peer *peer) peer->last_tx_at = ktime_get_seconds(); _leave(""); } + +/* + * Schedule an instant Tx resend. + */ +static inline void rxrpc_instant_resend(struct rxrpc_call *call, + struct rxrpc_txbuf *txb) +{ + if (call->state < RXRPC_CALL_COMPLETE) + kdebug("resend"); +} + +/* + * Transmit one packet. + */ +void rxrpc_transmit_one(struct rxrpc_call *call, struct rxrpc_txbuf *txb) +{ + int ret; + + ret = rxrpc_send_data_packet(call, txb); + if (ret < 0) { + switch (ret) { + case -ENETUNREACH: + case -EHOSTUNREACH: + case -ECONNREFUSED: + rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, + 0, ret); + break; + default: + _debug("need instant resend %d", ret); + rxrpc_instant_resend(call, txb); + } + } else { + unsigned long now = jiffies; + unsigned long resend_at = now + call->peer->rto_j; + + WRITE_ONCE(call->resend_at, resend_at); + rxrpc_reduce_call_timer(call, resend_at, now, + rxrpc_timer_set_for_send); + } +} diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 76b1e2e89c1e..11af37275d5b 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -22,30 +22,9 @@ */ static bool rxrpc_check_tx_space(struct rxrpc_call *call, rxrpc_seq_t *_tx_win) { - unsigned int win_size; - rxrpc_seq_t tx_win = smp_load_acquire(&call->acks_hard_ack); - - /* If we haven't transmitted anything for >1RTT, we should reset the - * congestion management state. - */ - if (ktime_before(ktime_add_us(call->tx_last_sent, - call->peer->srtt_us >> 3), - ktime_get_real())) { - if (RXRPC_TX_SMSS > 2190) - win_size = 2; - else if (RXRPC_TX_SMSS > 1095) - win_size = 3; - else - win_size = 4; - win_size += call->cong_extra; - } else { - win_size = min_t(unsigned int, call->tx_winsize, - call->cong_cwnd + call->cong_extra); - } - if (_tx_win) - *_tx_win = tx_win; - return call->tx_top - tx_win < win_size; + *_tx_win = call->tx_bottom; + return call->tx_prepared - call->tx_bottom < 256; } /* @@ -66,11 +45,6 @@ static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx, if (signal_pending(current)) return sock_intr_errno(*timeo); - if (READ_ONCE(call->acks_hard_ack) != call->tx_bottom) { - rxrpc_shrink_call_tx_buffer(call); - continue; - } - trace_rxrpc_txqueue(call, rxrpc_txqueue_wait); *timeo = schedule_timeout(*timeo); } @@ -107,11 +81,6 @@ static int rxrpc_wait_for_tx_window_waitall(struct rxrpc_sock *rx, tx_win == tx_start && signal_pending(current)) return -EINTR; - if (READ_ONCE(call->acks_hard_ack) != call->tx_bottom) { - rxrpc_shrink_call_tx_buffer(call); - continue; - } - if (tx_win != tx_start) { timeout = rtt; tx_start = tx_win; @@ -137,11 +106,6 @@ static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx, if (call->state >= RXRPC_CALL_COMPLETE) return call->error; - if (READ_ONCE(call->acks_hard_ack) != call->tx_bottom) { - rxrpc_shrink_call_tx_buffer(call); - continue; - } - trace_rxrpc_txqueue(call, rxrpc_txqueue_wait); *timeo = schedule_timeout(*timeo); } @@ -207,29 +171,27 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, unsigned long now; rxrpc_seq_t seq = txb->seq; bool last = test_bit(RXRPC_TXBUF_LAST, &txb->flags); - int ret; rxrpc_inc_stat(call->rxnet, stat_tx_data); - ASSERTCMP(seq, ==, call->tx_top + 1); + ASSERTCMP(txb->seq, ==, call->tx_prepared + 1); /* We have to set the timestamp before queueing as the retransmit * algorithm can see the packet as soon as we queue it. */ txb->last_sent = ktime_get_real(); - /* Add the packet to the call's output buffer */ - rxrpc_get_txbuf(txb, rxrpc_txbuf_get_buffer); - spin_lock(&call->tx_lock); - list_add_tail(&txb->call_link, &call->tx_buffer); - call->tx_top = seq; - spin_unlock(&call->tx_lock); - if (last) trace_rxrpc_txqueue(call, rxrpc_txqueue_queue_last); else trace_rxrpc_txqueue(call, rxrpc_txqueue_queue); + /* Add the packet to the call's output buffer */ + spin_lock(&call->tx_lock); + list_add_tail(&txb->call_link, &call->tx_sendmsg); + call->tx_prepared = seq; + spin_unlock(&call->tx_lock); + if (last || call->state == RXRPC_CALL_SERVER_ACK_REQUEST) { _debug("________awaiting reply/ACK__________"); write_lock_bh(&call->state_lock); @@ -258,30 +220,11 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, write_unlock_bh(&call->state_lock); } - if (seq == 1 && rxrpc_is_client_call(call)) - rxrpc_expose_client_call(call); - - ret = rxrpc_send_data_packet(call, txb); - if (ret < 0) { - switch (ret) { - case -ENETUNREACH: - case -EHOSTUNREACH: - case -ECONNREFUSED: - rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, - 0, ret); - goto out; - } - } else { - unsigned long now = jiffies; - unsigned long resend_at = now + call->peer->rto_j; - WRITE_ONCE(call->resend_at, resend_at); - rxrpc_reduce_call_timer(call, resend_at, now, - rxrpc_timer_set_for_send); - } - -out: - rxrpc_put_txbuf(txb, rxrpc_txbuf_put_trans); + /* Stick the packet on the crypto queue or the transmission queue as + * appropriate. + */ + rxrpc_queue_call(call, rxrpc_call_queue_tx_data); } /* diff --git a/net/rxrpc/txbuf.c b/net/rxrpc/txbuf.c index 90ff00c340cd..a5054389dfbb 100644 --- a/net/rxrpc/txbuf.c +++ b/net/rxrpc/txbuf.c @@ -34,7 +34,7 @@ struct rxrpc_txbuf *rxrpc_alloc_txbuf(struct rxrpc_call *call, u8 packet_type, txb->offset = 0; txb->flags = 0; txb->ack_why = 0; - txb->seq = call->tx_top + 1; + txb->seq = call->tx_prepared + 1; txb->wire.epoch = htonl(call->conn->proto.epoch); txb->wire.cid = htonl(call->cid); txb->wire.callNumber = htonl(call->call_id); @@ -107,6 +107,7 @@ void rxrpc_shrink_call_tx_buffer(struct rxrpc_call *call) { struct rxrpc_txbuf *txb; rxrpc_seq_t hard_ack = smp_load_acquire(&call->acks_hard_ack); + bool wake = false; _enter("%x/%x/%x", call->tx_bottom, call->acks_hard_ack, call->tx_top); @@ -123,7 +124,7 @@ void rxrpc_shrink_call_tx_buffer(struct rxrpc_call *call) if (txb->seq != call->tx_bottom + 1) rxrpc_see_txbuf(txb, rxrpc_txbuf_see_out_of_step); ASSERTCMP(txb->seq, ==, call->tx_bottom + 1); - call->tx_bottom++; + smp_store_release(&call->tx_bottom, call->tx_bottom + 1); list_del_rcu(&txb->call_link); trace_rxrpc_txqueue(call, rxrpc_txqueue_dequeue); @@ -131,7 +132,12 @@ void rxrpc_shrink_call_tx_buffer(struct rxrpc_call *call) spin_unlock(&call->tx_lock); rxrpc_put_txbuf(txb, rxrpc_txbuf_put_rotated); + if (after(call->acks_hard_ack, call->tx_bottom + 128)) + wake = true; } spin_unlock(&call->tx_lock); + + if (wake) + wake_up(&call->waitq); } -- cgit v1.2.3 From 2d1faf7a0ca3c0b327cf064c80e4e775532c9319 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 6 Oct 2022 15:43:51 +0100 Subject: rxrpc: Simplify skbuff accounting in receive path A received skbuff needs a ref when it gets put on a call data queue or conn packet queue, and rxrpc_input_packet() and co. jump through a lot of hoops to avoid double-dropping the skbuff ref so that we can avoid getting a ref when we queue the packet. Change this so that the skbuff ref is unconditionally dropped by the caller of rxrpc_input_packet(). An additional ref is then taken on the packet if it is pushed onto a queue. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 3 +- net/rxrpc/input.c | 45 ++++++++++++++-------------- net/rxrpc/io_thread.c | 70 ++++++++++++++++++++------------------------ 3 files changed, 56 insertions(+), 62 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index c3043fbea0e6..82b1327c2ba6 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -28,6 +28,8 @@ EM(rxrpc_skb_eaten_by_unshare_nomem, "ETN unshar-nm") \ EM(rxrpc_skb_get_ack, "GET ack ") \ EM(rxrpc_skb_get_conn_work, "GET conn-work") \ + 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 ") \ EM(rxrpc_skb_get_to_recvmsg_oos, "GET to-recv-o") \ EM(rxrpc_skb_new_encap_rcv, "NEW encap-rcv") \ @@ -39,7 +41,6 @@ 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_lose, "PUT lose ") \ EM(rxrpc_skb_put_purge, "PUT purge ") \ EM(rxrpc_skb_put_rotate, "PUT rotate ") \ EM(rxrpc_skb_put_unknown, "PUT unknown ") \ diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 036f02371051..42addbcf59f9 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -338,7 +338,8 @@ static void rxrpc_input_queue_data(struct rxrpc_call *call, struct sk_buff *skb, /* * Process a DATA packet. */ -static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb) +static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb, + bool *_notify) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct sk_buff *oos; @@ -361,7 +362,7 @@ static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb) if (test_and_set_bit(RXRPC_CALL_RX_LAST, &call->flags) && seq + 1 != wtop) { rxrpc_proto_abort("LSN", call, seq); - goto err_free; + return; } } else { if (test_bit(RXRPC_CALL_RX_LAST, &call->flags) && @@ -369,7 +370,7 @@ static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb) pr_warn("Packet beyond last: c=%x q=%x window=%x-%x wlimit=%x\n", call->debug_id, seq, window, wtop, wlimit); rxrpc_proto_abort("LSA", call, seq); - goto err_free; + return; } } @@ -402,9 +403,11 @@ static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb) if (after(window, wtop)) wtop = window; + rxrpc_get_skb(skb, rxrpc_skb_get_to_recvmsg); + spin_lock(&call->recvmsg_queue.lock); rxrpc_input_queue_data(call, skb, window, wtop, rxrpc_receive_queue); - skb = NULL; + *_notify = true; while ((oos = skb_peek(&call->rx_oos_queue))) { struct rxrpc_skb_priv *osp = rxrpc_skb(oos); @@ -456,16 +459,17 @@ static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb) struct rxrpc_skb_priv *osp = rxrpc_skb(oos); if (after(osp->hdr.seq, seq)) { + rxrpc_get_skb(skb, rxrpc_skb_get_to_recvmsg_oos); __skb_queue_before(&call->rx_oos_queue, oos, skb); goto oos_queued; } } + rxrpc_get_skb(skb, rxrpc_skb_get_to_recvmsg_oos); __skb_queue_tail(&call->rx_oos_queue, skb); oos_queued: trace_rxrpc_receive(call, last ? rxrpc_receive_oos_last : rxrpc_receive_oos, sp->hdr.serial, sp->hdr.seq); - skb = NULL; } send_ack: @@ -483,9 +487,6 @@ send_ack: else rxrpc_propose_delay_ACK(call, serial, rxrpc_propose_ack_input_data); - -err_free: - rxrpc_free_skb(skb, rxrpc_skb_put_input); } /* @@ -498,6 +499,7 @@ static bool rxrpc_input_split_jumbo(struct rxrpc_call *call, struct sk_buff *skb struct sk_buff *jskb; unsigned int offset = sizeof(struct rxrpc_wire_header); unsigned int len = skb->len - offset; + bool notify = false; while (sp->hdr.flags & RXRPC_JUMBO_PACKET) { if (len < RXRPC_JUMBO_SUBPKTLEN) @@ -517,7 +519,8 @@ static bool rxrpc_input_split_jumbo(struct rxrpc_call *call, struct sk_buff *skb jsp = rxrpc_skb(jskb); jsp->offset = offset; jsp->len = RXRPC_JUMBO_DATALEN; - rxrpc_input_data_one(call, jskb); + rxrpc_input_data_one(call, jskb, ¬ify); + rxrpc_free_skb(jskb, rxrpc_skb_put_jumbo_subpacket); sp->hdr.flags = jhdr.flags; sp->hdr._rsvd = ntohs(jhdr._rsvd); @@ -529,7 +532,11 @@ static bool rxrpc_input_split_jumbo(struct rxrpc_call *call, struct sk_buff *skb sp->offset = offset; sp->len = len; - rxrpc_input_data_one(call, skb); + rxrpc_input_data_one(call, skb, ¬ify); + if (notify) { + trace_rxrpc_notify_socket(call->debug_id, sp->hdr.serial); + rxrpc_notify_socket(call); + } return true; protocol_error: @@ -552,10 +559,8 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) skb->len, seq0); state = READ_ONCE(call->state); - if (state >= RXRPC_CALL_COMPLETE) { - rxrpc_free_skb(skb, rxrpc_skb_put_input); + if (state >= RXRPC_CALL_COMPLETE) return; - } /* Unshare the packet so that it can be modified for in-place * decryption. @@ -605,7 +610,6 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) out: trace_rxrpc_notify_socket(call->debug_id, serial); rxrpc_notify_socket(call); - rxrpc_free_skb(skb, rxrpc_skb_put_input); _leave(" [queued]"); } @@ -797,7 +801,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) struct rxrpc_ackpacket ack; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_ackinfo info; - struct sk_buff *skb_old = NULL, *skb_put = skb; + struct sk_buff *skb_old = NULL; rxrpc_serial_t ack_serial, acked_serial; rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt; int nr_acks, offset, ioffset; @@ -963,6 +967,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) goto out; } + rxrpc_get_skb(skb, rxrpc_skb_get_ack); spin_lock(&call->acks_ack_lock); skb_old = call->acks_soft_tbl; call->acks_soft_tbl = skb; @@ -970,7 +975,6 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_input_soft_acks(call, skb->data + offset, first_soft_ack, nr_acks, &summary); - skb_put = NULL; } else if (call->acks_soft_tbl) { spin_lock(&call->acks_ack_lock); skb_old = call->acks_soft_tbl; @@ -986,7 +990,6 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_congestion_management(call, skb, &summary, acked_serial); out: - rxrpc_free_skb(skb_put, rxrpc_skb_put_input); rxrpc_free_skb(skb_old, rxrpc_skb_put_ack); } @@ -1037,11 +1040,11 @@ void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) switch (sp->hdr.type) { case RXRPC_PACKET_TYPE_DATA: rxrpc_input_data(call, skb); - goto no_free; + break; case RXRPC_PACKET_TYPE_ACK: rxrpc_input_ack(call, skb); - goto no_free; + break; case RXRPC_PACKET_TYPE_BUSY: /* Just ignore BUSY packets from the server; the retry and @@ -1061,10 +1064,6 @@ void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) default: break; } - - rxrpc_free_skb(skb, rxrpc_skb_put_input); -no_free: - _leave(""); } /* diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c index 2119941b6d6c..91b8ba5b90db 100644 --- a/net/rxrpc/io_thread.c +++ b/net/rxrpc/io_thread.c @@ -72,6 +72,7 @@ static void rxrpc_post_packet_to_conn(struct rxrpc_connection *conn, { _enter("%p,%p", conn, skb); + rxrpc_get_skb(skb, rxrpc_skb_get_conn_work); skb_queue_tail(&conn->rx_queue, skb); rxrpc_queue_conn(conn, rxrpc_conn_queue_rx_work); } @@ -86,10 +87,9 @@ static void rxrpc_post_packet_to_local(struct rxrpc_local *local, _enter("%p,%p", local, skb); if (rxrpc_get_local_maybe(local, rxrpc_local_get_queue)) { + rxrpc_get_skb(skb, rxrpc_skb_get_local_work); skb_queue_tail(&local->event_queue, skb); rxrpc_queue_local(local); - } else { - rxrpc_free_skb(skb, rxrpc_skb_put_input); } } @@ -99,10 +99,9 @@ static void rxrpc_post_packet_to_local(struct rxrpc_local *local, static void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) { if (rxrpc_get_local_maybe(local, rxrpc_local_get_queue)) { + rxrpc_get_skb(skb, rxrpc_skb_get_reject_work); skb_queue_tail(&local->reject_queue, skb); rxrpc_queue_local(local); - } else { - rxrpc_free_skb(skb, rxrpc_skb_put_input); } } @@ -153,7 +152,7 @@ static bool rxrpc_extract_abort(struct sk_buff *skb) /* * Process packets received on the local endpoint */ -static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff *skb) +static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb) { struct rxrpc_connection *conn; struct rxrpc_channel *chan; @@ -161,6 +160,7 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff *skb) struct rxrpc_skb_priv *sp; struct rxrpc_peer *peer = NULL; struct rxrpc_sock *rx = NULL; + struct sk_buff *skb = *_skb; unsigned int channel; if (skb->tstamp == 0) @@ -181,7 +181,6 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff *skb) static int lose; if ((lose++ & 7) == 7) { trace_rxrpc_rx_lose(sp); - rxrpc_free_skb(skb, rxrpc_skb_put_lose); return 0; } } @@ -193,13 +192,13 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff *skb) switch (sp->hdr.type) { case RXRPC_PACKET_TYPE_VERSION: if (rxrpc_to_client(sp)) - goto discard; + return 0; rxrpc_post_packet_to_local(local, skb); - goto out; + return 0; case RXRPC_PACKET_TYPE_BUSY: if (rxrpc_to_server(sp)) - goto discard; + return 0; fallthrough; case RXRPC_PACKET_TYPE_ACK: case RXRPC_PACKET_TYPE_ACKALL: @@ -208,7 +207,7 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff *skb) break; case RXRPC_PACKET_TYPE_ABORT: if (!rxrpc_extract_abort(skb)) - return true; /* Just discard if malformed */ + return 0; /* Just discard if malformed */ break; case RXRPC_PACKET_TYPE_DATA: @@ -220,15 +219,16 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff *skb) * decryption. */ if (sp->hdr.securityIndex != 0) { - struct sk_buff *nskb = skb_unshare(skb, GFP_ATOMIC); - if (!nskb) { - rxrpc_eaten_skb(skb, rxrpc_skb_eaten_by_unshare_nomem); - goto out; + skb = skb_unshare(skb, GFP_ATOMIC); + if (!skb) { + rxrpc_eaten_skb(*_skb, rxrpc_skb_eaten_by_unshare_nomem); + *_skb = NULL; + return 0; } - if (nskb != skb) { - rxrpc_eaten_skb(skb, rxrpc_skb_eaten_by_unshare); - skb = nskb; + if (skb != *_skb) { + rxrpc_eaten_skb(*_skb, rxrpc_skb_eaten_by_unshare); + *_skb = skb; rxrpc_new_skb(skb, rxrpc_skb_new_unshared); sp = rxrpc_skb(skb); } @@ -237,18 +237,18 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff *skb) case RXRPC_PACKET_TYPE_CHALLENGE: if (rxrpc_to_server(sp)) - goto discard; + return 0; break; case RXRPC_PACKET_TYPE_RESPONSE: if (rxrpc_to_client(sp)) - goto discard; + return 0; break; /* Packet types 9-11 should just be ignored. */ case RXRPC_PACKET_TYPE_PARAMS: case RXRPC_PACKET_TYPE_10: case RXRPC_PACKET_TYPE_11: - goto discard; + return 0; default: goto bad_message; @@ -268,7 +268,7 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff *skb) if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA && sp->hdr.seq == 1) goto unsupported_service; - goto discard; + return 0; } } @@ -294,7 +294,7 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff *skb) /* Connection-level packet */ _debug("CONN %p {%d}", conn, conn->debug_id); rxrpc_post_packet_to_conn(conn, skb); - goto out; + return 0; } if ((int)sp->hdr.serial - (int)conn->hi_serial > 0) @@ -306,19 +306,19 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff *skb) /* Ignore really old calls */ if (sp->hdr.callNumber < chan->last_call) - goto discard; + return 0; if (sp->hdr.callNumber == chan->last_call) { if (chan->call || sp->hdr.type == RXRPC_PACKET_TYPE_ABORT) - goto discard; + return 0; /* For the previous service call, if completed * successfully, we discard all further packets. */ if (rxrpc_conn_is_service(conn) && chan->last_type == RXRPC_PACKET_TYPE_ACK) - goto discard; + return 0; /* But otherwise we need to retransmit the final packet * from data cached in the connection record. @@ -329,7 +329,7 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff *skb) sp->hdr.serial, sp->hdr.flags); rxrpc_post_packet_to_conn(conn, skb); - goto out; + return 0; } call = rcu_dereference(chan->call); @@ -357,21 +357,14 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff *skb) sp->hdr.type != RXRPC_PACKET_TYPE_DATA) goto bad_message; if (sp->hdr.seq != 1) - goto discard; + return 0; call = rxrpc_new_incoming_call(local, rx, skb); if (!call) goto reject_packet; } - /* Process a call packet; this either discards or passes on the ref - * elsewhere. - */ + /* Process a call packet. */ rxrpc_input_call_event(call, skb); - goto out; - -discard: - rxrpc_free_skb(skb, rxrpc_skb_put_input); -out: trace_rxrpc_rx_done(0, 0); return 0; @@ -400,9 +393,7 @@ protocol_error: post_abort: skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; reject_packet: - trace_rxrpc_rx_done(skb->mark, skb->priority); rxrpc_reject_packet(local, skb); - _leave(" [badmsg]"); return 0; } @@ -441,9 +432,12 @@ int rxrpc_io_thread(void *data) if ((skb = __skb_dequeue(&rx_queue))) { switch (skb->mark) { case RXRPC_SKB_MARK_PACKET: + skb->priority = 0; rcu_read_lock(); - rxrpc_input_packet(local, skb); + rxrpc_input_packet(local, &skb); rcu_read_unlock(); + trace_rxrpc_rx_done(skb->mark, skb->priority); + rxrpc_free_skb(skb, rxrpc_skb_put_input); break; case RXRPC_SKB_MARK_ERROR: rxrpc_input_error(local, skb); -- cgit v1.2.3 From 5e6ef4f1017c7f844e305283bbd8875af475e2fc Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 23 Jan 2020 13:13:41 +0000 Subject: rxrpc: Make the I/O thread take over the call and local processor work Move the functions from the call->processor and local->processor work items into the domain of the I/O thread. The call event processor, now called from the I/O thread, then takes over the job of cranking the call state machine, processing incoming packets and transmitting DATA, ACK and ABORT packets. In a future patch, rxrpc_send_ACK() will transmit the ACK on the spot rather than queuing it for later transmission. The call event processor becomes purely received-skb driven. It only transmits things in response to events. We use "pokes" to queue a dummy skb to make it do things like start/resume transmitting data. Timer expiry also results in pokes. The connection event processor, becomes similar, though crypto events, such as dealing with CHALLENGE and RESPONSE packets is offloaded to a work item to avoid doing crypto in the I/O thread. The local event processor is removed and VERSION response packets are generated directly from the packet parser. Similarly, ABORTs generated in response to protocol errors will be transmitted immediately rather than being pushed onto a queue for later transmission. Changes: ======== ver #2) - Fix a couple of introduced lock context imbalances. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 42 +++--- net/rxrpc/ar-internal.h | 50 +++---- net/rxrpc/call_accept.c | 126 ++++++++--------- net/rxrpc/call_event.c | 171 ++++++++++------------- net/rxrpc/call_object.c | 56 +++++--- net/rxrpc/conn_event.c | 60 ++++++++ net/rxrpc/conn_object.c | 93 +++++-------- net/rxrpc/input.c | 167 ++++++---------------- net/rxrpc/io_thread.c | 319 ++++++++++++++++++++----------------------- net/rxrpc/local_event.c | 43 +----- net/rxrpc/local_object.c | 69 +--------- net/rxrpc/output.c | 92 +++++-------- net/rxrpc/peer_event.c | 29 ++-- net/rxrpc/recvmsg.c | 9 +- net/rxrpc/sendmsg.c | 10 +- 15 files changed, 545 insertions(+), 791 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 82b1327c2ba6..c49b0c233594 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -26,7 +26,6 @@ #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_ack, "GET ack ") \ EM(rxrpc_skb_get_conn_work, "GET conn-work") \ EM(rxrpc_skb_get_local_work, "GET locl-work") \ EM(rxrpc_skb_get_reject_work, "GET rej-work ") \ @@ -36,7 +35,6 @@ 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_ack, "PUT ack ") \ 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 ") \ @@ -45,7 +43,6 @@ EM(rxrpc_skb_put_rotate, "PUT rotate ") \ EM(rxrpc_skb_put_unknown, "PUT unknown ") \ EM(rxrpc_skb_see_conn_work, "SEE conn-work") \ - EM(rxrpc_skb_see_local_work, "SEE locl-work") \ EM(rxrpc_skb_see_recvmsg, "SEE recvmsg ") \ EM(rxrpc_skb_see_reject, "SEE reject ") \ EM(rxrpc_skb_see_rotate, "SEE rotate ") \ @@ -58,10 +55,7 @@ EM(rxrpc_local_get_for_use, "GET for-use ") \ EM(rxrpc_local_get_peer, "GET peer ") \ EM(rxrpc_local_get_prealloc_conn, "GET conn-pre") \ - EM(rxrpc_local_get_queue, "GET queue ") \ EM(rxrpc_local_new, "NEW ") \ - EM(rxrpc_local_processing, "PROCESSING ") \ - EM(rxrpc_local_put_already_queued, "PUT alreadyq") \ EM(rxrpc_local_put_bind, "PUT bind ") \ EM(rxrpc_local_put_call, "PUT call ") \ EM(rxrpc_local_put_for_use, "PUT for-use ") \ @@ -69,8 +63,6 @@ EM(rxrpc_local_put_peer, "PUT peer ") \ EM(rxrpc_local_put_prealloc_conn, "PUT conn-pre") \ EM(rxrpc_local_put_release_sock, "PUT rel-sock") \ - EM(rxrpc_local_put_queue, "PUT queue ") \ - EM(rxrpc_local_queued, "QUEUED ") \ EM(rxrpc_local_see_tx_ack, "SEE tx-ack ") \ EM(rxrpc_local_stop, "STOP ") \ EM(rxrpc_local_stopped, "STOPPED ") \ @@ -78,11 +70,9 @@ EM(rxrpc_local_unuse_conn_work, "UNU conn-wrk") \ EM(rxrpc_local_unuse_peer_keepalive, "UNU peer-kpa") \ EM(rxrpc_local_unuse_release_sock, "UNU rel-sock") \ - EM(rxrpc_local_unuse_work, "UNU work ") \ EM(rxrpc_local_use_conn_work, "USE conn-wrk") \ EM(rxrpc_local_use_lookup, "USE lookup ") \ - EM(rxrpc_local_use_peer_keepalive, "USE peer-kpa") \ - E_(rxrpc_local_use_work, "USE work ") + E_(rxrpc_local_use_peer_keepalive, "USE peer-kpa") #define rxrpc_peer_traces \ EM(rxrpc_peer_free, "FREE ") \ @@ -90,6 +80,7 @@ EM(rxrpc_peer_get_activate_call, "GET act-call") \ EM(rxrpc_peer_get_bundle, "GET bundle ") \ EM(rxrpc_peer_get_client_conn, "GET cln-conn") \ + EM(rxrpc_peer_get_input, "GET input ") \ EM(rxrpc_peer_get_input_error, "GET inpt-err") \ EM(rxrpc_peer_get_keepalive, "GET keepaliv") \ EM(rxrpc_peer_get_lookup_client, "GET look-cln") \ @@ -100,6 +91,7 @@ EM(rxrpc_peer_put_call, "PUT call ") \ EM(rxrpc_peer_put_conn, "PUT conn ") \ EM(rxrpc_peer_put_discard_tmp, "PUT disc-tmp") \ + EM(rxrpc_peer_put_input, "PUT input ") \ EM(rxrpc_peer_put_input_error, "PUT inpt-err") \ E_(rxrpc_peer_put_keepalive, "PUT keepaliv") @@ -180,11 +172,6 @@ EM(rxrpc_call_put_sendmsg, "PUT sendmsg ") \ EM(rxrpc_call_put_unnotify, "PUT unnotify") \ EM(rxrpc_call_put_userid_exists, "PUT u-exists") \ - EM(rxrpc_call_queue_abort, "QUE abort ") \ - EM(rxrpc_call_queue_requeue, "QUE requeue ") \ - EM(rxrpc_call_queue_resend, "QUE resend ") \ - EM(rxrpc_call_queue_timer, "QUE timer ") \ - EM(rxrpc_call_queue_tx_data, "QUE tx-data ") \ EM(rxrpc_call_see_accept, "SEE accept ") \ EM(rxrpc_call_see_activate_client, "SEE act-clnt") \ EM(rxrpc_call_see_connect_failed, "SEE con-fail") \ @@ -282,6 +269,7 @@ EM(rxrpc_propose_ack_respond_to_ping, "Rsp2Png") \ 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 \ @@ -1532,6 +1520,7 @@ TRACE_EVENT(rxrpc_connect_call, __field(unsigned long, user_call_ID ) __field(u32, cid ) __field(u32, call_id ) + __field_struct(struct sockaddr_rxrpc, srx ) ), TP_fast_assign( @@ -1539,33 +1528,42 @@ TRACE_EVENT(rxrpc_connect_call, __entry->user_call_ID = call->user_call_ID; __entry->cid = call->cid; __entry->call_id = call->call_id; + __entry->srx = call->dest_srx; ), - TP_printk("c=%08x u=%p %08x:%08x", + TP_printk("c=%08x u=%p %08x:%08x dst=%pISp", __entry->call, (void *)__entry->user_call_ID, __entry->cid, - __entry->call_id) + __entry->call_id, + &__entry->srx.transport) ); TRACE_EVENT(rxrpc_resend, - TP_PROTO(struct rxrpc_call *call), + TP_PROTO(struct rxrpc_call *call, struct sk_buff *ack), - TP_ARGS(call), + TP_ARGS(call, ack), TP_STRUCT__entry( __field(unsigned int, call ) __field(rxrpc_seq_t, seq ) + __field(rxrpc_seq_t, transmitted ) + __field(rxrpc_serial_t, ack_serial ) ), 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; ), - TP_printk("c=%08x q=%x", + TP_printk("c=%08x r=%x q=%x tq=%x", __entry->call, - __entry->seq) + __entry->ack_serial, + __entry->seq, + __entry->transmitted) ); TRACE_EVENT(rxrpc_rx_icmp, diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index c3c915a05627..6b993a3d4186 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -283,14 +283,11 @@ struct rxrpc_local { struct rxrpc_net *rxnet; /* The network ns in which this resides */ struct hlist_node link; struct socket *socket; /* my UDP socket */ - struct work_struct processor; struct task_struct *io_thread; struct list_head ack_tx_queue; /* List of ACKs that need sending */ spinlock_t ack_tx_lock; /* ACK list lock */ struct rxrpc_sock __rcu *service; /* Service(s) listening on this endpoint */ struct rw_semaphore defrag_sem; /* control re-enablement of IP DF bit */ - struct sk_buff_head reject_queue; /* packets awaiting rejection */ - struct sk_buff_head event_queue; /* endpoint event packets awaiting processing */ struct sk_buff_head rx_queue; /* Received packets */ struct list_head call_attend_q; /* Calls requiring immediate attention */ struct rb_root client_bundles; /* Client connection bundles by socket params */ @@ -524,23 +521,19 @@ enum rxrpc_call_flag { RXRPC_CALL_RETRANS_TIMEOUT, /* Retransmission due to timeout occurred */ RXRPC_CALL_BEGAN_RX_TIMER, /* We began the expect_rx_by timer */ RXRPC_CALL_RX_HEARD, /* The peer responded at least once to this call */ - RXRPC_CALL_RX_UNDERRUN, /* Got data underrun */ RXRPC_CALL_DISCONNECTED, /* The call has been disconnected */ RXRPC_CALL_KERNEL, /* The call was made by the kernel */ RXRPC_CALL_UPGRADE, /* Service upgrade was requested for the call */ - RXRPC_CALL_DELAY_ACK_PENDING, /* DELAY ACK generation is pending */ - RXRPC_CALL_IDLE_ACK_PENDING, /* IDLE ACK generation is pending */ RXRPC_CALL_EXCLUSIVE, /* The call uses a once-only connection */ + RXRPC_CALL_RX_IS_IDLE, /* Reception is idle - send an ACK */ }; /* * Events that can be raised on a call. */ enum rxrpc_call_event { - RXRPC_CALL_EV_ABORT, /* need to generate abort */ - RXRPC_CALL_EV_RESEND, /* Tx resend required */ - RXRPC_CALL_EV_EXPIRED, /* Expiry occurred */ RXRPC_CALL_EV_ACK_LOST, /* ACK may be lost, send ping */ + RXRPC_CALL_EV_INITIAL_PING, /* Send initial ping for a new service call */ }; /* @@ -611,7 +604,6 @@ struct rxrpc_call { u32 next_rx_timo; /* Timeout for next Rx packet (jif) */ u32 next_req_timo; /* Timeout for next Rx request packet (jif) */ struct timer_list timer; /* Combined event timer */ - struct work_struct processor; /* Event processor */ struct work_struct destroyer; /* In-process-context destroyer */ rxrpc_notify_rx_t notify_rx; /* kernel service Rx notification function */ struct list_head link; /* link in master call list */ @@ -705,11 +697,7 @@ struct rxrpc_call { rxrpc_seq_t acks_prev_seq; /* Highest previousPacket received */ rxrpc_seq_t acks_hard_ack; /* Latest hard-ack point */ rxrpc_seq_t acks_lowest_nak; /* Lowest NACK in the buffer (or ==tx_hard_ack) */ - rxrpc_seq_t acks_lost_top; /* tx_top at the time lost-ack ping sent */ - rxrpc_serial_t acks_lost_ping; /* Serial number of probe ACK */ rxrpc_serial_t acks_highest_serial; /* Highest serial number ACK'd */ - struct sk_buff *acks_soft_tbl; /* The last ACK packet with NAKs in it */ - spinlock_t acks_ack_lock; /* Access to ->acks_last_ack */ }; /* @@ -822,10 +810,9 @@ extern struct workqueue_struct *rxrpc_workqueue; */ int rxrpc_service_prealloc(struct rxrpc_sock *, gfp_t); void rxrpc_discard_prealloc(struct rxrpc_sock *); -struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *, - struct rxrpc_sock *, - struct sockaddr_rxrpc *, - struct sk_buff *); +bool rxrpc_new_incoming_call(struct rxrpc_local *, struct rxrpc_peer *, + struct rxrpc_connection *, struct sockaddr_rxrpc *, + struct sk_buff *); void rxrpc_accept_incoming_calls(struct rxrpc_local *); int rxrpc_user_charge_accept(struct rxrpc_sock *, unsigned long); @@ -838,13 +825,15 @@ void rxrpc_send_ACK(struct rxrpc_call *, u8, rxrpc_serial_t, enum rxrpc_propose_ void rxrpc_propose_delay_ACK(struct rxrpc_call *, rxrpc_serial_t, enum rxrpc_propose_ack_trace); void rxrpc_shrink_call_tx_buffer(struct rxrpc_call *); -void rxrpc_process_call(struct work_struct *); +void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb); void rxrpc_reduce_call_timer(struct rxrpc_call *call, unsigned long expire_at, unsigned long now, enum rxrpc_timer_trace why); +void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb); + /* * call_object.c */ @@ -864,9 +853,8 @@ void rxrpc_incoming_call(struct rxrpc_sock *, struct rxrpc_call *, struct sk_buff *); void rxrpc_release_call(struct rxrpc_sock *, struct rxrpc_call *); void rxrpc_release_calls_on_socket(struct rxrpc_sock *); -void rxrpc_queue_call(struct rxrpc_call *, enum rxrpc_call_trace); void rxrpc_see_call(struct rxrpc_call *, enum rxrpc_call_trace); -bool rxrpc_try_get_call(struct rxrpc_call *, enum rxrpc_call_trace); +struct rxrpc_call *rxrpc_try_get_call(struct rxrpc_call *, enum rxrpc_call_trace); void rxrpc_get_call(struct rxrpc_call *, enum rxrpc_call_trace); void rxrpc_put_call(struct rxrpc_call *, enum rxrpc_call_trace); void rxrpc_cleanup_call(struct rxrpc_call *); @@ -908,6 +896,7 @@ void rxrpc_clean_up_local_conns(struct rxrpc_local *); */ void rxrpc_process_connection(struct work_struct *); void rxrpc_process_delayed_final_acks(struct rxrpc_connection *, bool); +int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb); /* * conn_object.c @@ -916,10 +905,9 @@ extern unsigned int rxrpc_connection_expiry; extern unsigned int rxrpc_closed_conn_expiry; struct rxrpc_connection *rxrpc_alloc_connection(struct rxrpc_net *, gfp_t); -struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *, - struct sockaddr_rxrpc *, - struct sk_buff *, - struct rxrpc_peer **); +struct rxrpc_connection *rxrpc_find_client_connection_rcu(struct rxrpc_local *, + struct sockaddr_rxrpc *, + struct sk_buff *); void __rxrpc_disconnect_call(struct rxrpc_connection *, struct rxrpc_call *); void rxrpc_disconnect_call(struct rxrpc_call *); void rxrpc_kill_client_conn(struct rxrpc_connection *); @@ -962,8 +950,8 @@ void rxrpc_unpublish_service_conn(struct rxrpc_connection *); /* * input.c */ -void rxrpc_input_call_event(struct rxrpc_call *, struct sk_buff *); -void rxrpc_input_implicit_end_call(struct rxrpc_connection *, struct rxrpc_call *); +void rxrpc_input_call_packet(struct rxrpc_call *, struct sk_buff *); +void rxrpc_implicit_end_call(struct rxrpc_call *, struct sk_buff *); /* * io_thread.c @@ -993,7 +981,9 @@ int rxrpc_get_server_data_key(struct rxrpc_connection *, const void *, time64_t, /* * local_event.c */ -extern void rxrpc_process_local_events(struct rxrpc_local *); +void rxrpc_send_version_request(struct rxrpc_local *local, + struct rxrpc_host_header *hdr, + struct sk_buff *skb); /* * local_object.c @@ -1004,7 +994,6 @@ struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *, enum rxrpc_local void rxrpc_put_local(struct rxrpc_local *, enum rxrpc_local_trace); struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *, enum rxrpc_local_trace); void rxrpc_unuse_local(struct rxrpc_local *, enum rxrpc_local_trace); -void rxrpc_queue_local(struct rxrpc_local *); void rxrpc_destroy_local(struct rxrpc_local *local); void rxrpc_destroy_all_locals(struct rxrpc_net *); @@ -1068,7 +1057,7 @@ static inline struct rxrpc_net *rxrpc_net(struct net *net) void rxrpc_transmit_ack_packets(struct rxrpc_local *); int rxrpc_send_abort_packet(struct rxrpc_call *); int rxrpc_send_data_packet(struct rxrpc_call *, struct rxrpc_txbuf *); -void rxrpc_reject_packets(struct rxrpc_local *); +void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb); void rxrpc_send_keepalive(struct rxrpc_peer *); void rxrpc_transmit_one(struct rxrpc_call *call, struct rxrpc_txbuf *txb); @@ -1178,7 +1167,6 @@ int rxrpc_server_keyring(struct rxrpc_sock *, sockptr_t, int); * skbuff.c */ void rxrpc_kernel_data_consumed(struct rxrpc_call *, struct sk_buff *); -void rxrpc_packet_destructor(struct sk_buff *); void rxrpc_new_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_see_skb(struct sk_buff *, enum rxrpc_skb_trace); void rxrpc_eaten_skb(struct sk_buff *, enum rxrpc_skb_trace); diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 11134b7cec17..87b46c2a1985 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -100,6 +100,7 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, return -ENOMEM; call->flags |= (1 << RXRPC_CALL_IS_SERVICE); call->state = RXRPC_CALL_SERVER_PREALLOC; + __set_bit(RXRPC_CALL_EV_INITIAL_PING, &call->events); trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), user_call_ID, rxrpc_call_new_prealloc_service); @@ -234,21 +235,6 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx) kfree(b); } -/* - * Ping the other end to fill our RTT cache and to retrieve the rwind - * and MTU parameters. - */ -static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb) -{ - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - ktime_t now = skb->tstamp; - - if (call->peer->rtt_count < 3 || - ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), now)) - rxrpc_send_ACK(call, RXRPC_ACK_PING, sp->hdr.serial, - rxrpc_propose_ack_ping_for_params); -} - /* * Allocate a new incoming call from the prealloc pool, along with a connection * and a peer as necessary. @@ -330,33 +316,56 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, } /* - * Set up a new incoming call. Called in BH context with the RCU read lock - * held. + * Set up a new incoming call. Called from the I/O thread. * * If this is for a kernel service, when we allocate the call, it will have * three refs on it: (1) the kernel service, (2) the user_call_ID tree, (3) the * retainer ref obtained from the backlog buffer. Prealloc calls for userspace - * services only have the ref from the backlog buffer. We pass this ref to the - * caller. + * services only have the ref from the backlog buffer. * * If we want to report an error, we mark the skb with the packet type and - * abort code and return NULL. - * - * The call is returned with the user access mutex held and a ref on it. + * abort code and return false. */ -struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, - struct rxrpc_sock *rx, - struct sockaddr_rxrpc *peer_srx, - struct sk_buff *skb) +bool rxrpc_new_incoming_call(struct rxrpc_local *local, + struct rxrpc_peer *peer, + struct rxrpc_connection *conn, + struct sockaddr_rxrpc *peer_srx, + struct sk_buff *skb) { - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); const struct rxrpc_security *sec = NULL; - struct rxrpc_connection *conn; - struct rxrpc_peer *peer = NULL; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_call *call = NULL; + struct rxrpc_sock *rx; _enter(""); + /* Don't set up a call for anything other than the first DATA packet. */ + if (sp->hdr.seq != 1 || + sp->hdr.type != RXRPC_PACKET_TYPE_DATA) + return true; /* Just discard */ + + rcu_read_lock(); + + /* Weed out packets to services we're not offering. Packets that would + * begin a call are explicitly rejected and the rest are just + * discarded. + */ + rx = rcu_dereference(local->service); + if (!rx || (sp->hdr.serviceId != rx->srx.srx_service && + sp->hdr.serviceId != rx->second_service) + ) { + if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA && + sp->hdr.seq == 1) + goto unsupported_service; + goto discard; + } + + if (!conn) { + sec = rxrpc_get_incoming_security(rx, skb); + if (!sec) + goto reject; + } + spin_lock(&rx->incoming_lock); if (rx->sk.sk_state == RXRPC_SERVER_LISTEN_DISABLED || rx->sk.sk_state == RXRPC_CLOSE) { @@ -367,19 +376,6 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, goto no_call; } - /* The peer, connection and call may all have sprung into existence due - * to a duplicate packet being handled on another CPU in parallel, so - * we have to recheck the routing. However, we're now holding - * rx->incoming_lock, so the values should remain stable. - */ - conn = rxrpc_find_connection_rcu(local, peer_srx, skb, &peer); - - if (!conn) { - sec = rxrpc_get_incoming_security(rx, skb); - if (!sec) - goto no_call; - } - call = rxrpc_alloc_incoming_call(rx, local, peer, conn, sec, peer_srx, skb); if (!call) { @@ -398,35 +394,15 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, rx->notify_new_call(&rx->sk, call, call->user_call_ID); spin_lock(&conn->state_lock); - switch (conn->state) { - case RXRPC_CONN_SERVICE_UNSECURED: + if (conn->state == RXRPC_CONN_SERVICE_UNSECURED) { conn->state = RXRPC_CONN_SERVICE_CHALLENGING; set_bit(RXRPC_CONN_EV_CHALLENGE, &call->conn->events); rxrpc_queue_conn(call->conn, rxrpc_conn_queue_challenge); - break; - - case RXRPC_CONN_SERVICE: - write_lock(&call->state_lock); - if (call->state < RXRPC_CALL_COMPLETE) - call->state = RXRPC_CALL_SERVER_RECV_REQUEST; - write_unlock(&call->state_lock); - break; - - case RXRPC_CONN_REMOTELY_ABORTED: - rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED, - conn->abort_code, conn->error); - break; - case RXRPC_CONN_LOCALLY_ABORTED: - rxrpc_abort_call("CON", call, sp->hdr.seq, - conn->abort_code, conn->error); - break; - default: - BUG(); } spin_unlock(&conn->state_lock); - spin_unlock(&rx->incoming_lock); - rxrpc_send_ping(call, skb); + spin_unlock(&rx->incoming_lock); + rcu_read_unlock(); if (hlist_unhashed(&call->error_link)) { spin_lock(&call->peer->lock); @@ -435,12 +411,24 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, } _leave(" = %p{%d}", call, call->debug_id); - return call; - + rxrpc_input_call_event(call, skb); + rxrpc_put_call(call, rxrpc_call_put_input); + return true; + +unsupported_service: + trace_rxrpc_abort(0, "INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, + RX_INVALID_OPERATION, EOPNOTSUPP); + skb->priority = RX_INVALID_OPERATION; + goto reject; no_call: spin_unlock(&rx->incoming_lock); - _leave(" = NULL [%u]", skb->mark); - return NULL; +reject: + rcu_read_unlock(); + _leave(" = f [%u]", skb->mark); + return false; +discard: + rcu_read_unlock(); + return true; } /* diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index c9f835292f7b..9db62fa55c62 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -74,11 +74,6 @@ void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason, if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) return; - if (ack_reason == RXRPC_ACK_DELAY && - test_and_set_bit(RXRPC_CALL_DELAY_ACK_PENDING, &call->flags)) { - trace_rxrpc_drop_ack(call, why, ack_reason, serial, false); - return; - } rxrpc_inc_stat(call->rxnet, stat_tx_acks[ack_reason]); @@ -111,12 +106,7 @@ void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason, spin_unlock_bh(&local->ack_tx_lock); trace_rxrpc_send_ack(call, why, ack_reason, serial); - if (!rcu_read_lock_held()) { - rxrpc_transmit_ack_packets(call->peer->local); - } else { - rxrpc_get_local(local, rxrpc_local_get_queue); - rxrpc_queue_local(local); - } + rxrpc_wake_up_io_thread(local); } /* @@ -130,11 +120,10 @@ static void rxrpc_congestion_timeout(struct rxrpc_call *call) /* * Perform retransmission of NAK'd and unack'd packets. */ -static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) +void rxrpc_resend(struct rxrpc_call *call, struct sk_buff *ack_skb) { struct rxrpc_ackpacket *ack = NULL; struct rxrpc_txbuf *txb; - struct sk_buff *ack_skb = NULL; unsigned long resend_at; rxrpc_seq_t transmitted = READ_ONCE(call->tx_transmitted); ktime_t now, max_age, oldest, ack_ts; @@ -148,32 +137,21 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) max_age = ktime_sub_us(now, jiffies_to_usecs(call->peer->rto_j)); oldest = now; - /* See if there's an ACK saved with a soft-ACK table in it. */ - if (call->acks_soft_tbl) { - spin_lock_bh(&call->acks_ack_lock); - ack_skb = call->acks_soft_tbl; - if (ack_skb) { - rxrpc_get_skb(ack_skb, rxrpc_skb_get_ack); - ack = (void *)ack_skb->data + sizeof(struct rxrpc_wire_header); - } - spin_unlock_bh(&call->acks_ack_lock); - } - if (list_empty(&call->tx_buffer)) goto no_resend; - spin_lock(&call->tx_lock); - if (list_empty(&call->tx_buffer)) goto no_further_resend; - trace_rxrpc_resend(call); + trace_rxrpc_resend(call, ack_skb); txb = list_first_entry(&call->tx_buffer, struct rxrpc_txbuf, call_link); /* Scan the soft ACK table without dropping the lock and resend any * explicitly NAK'd packets. */ - if (ack) { + if (ack_skb) { + ack = (void *)ack_skb->data + sizeof(struct rxrpc_wire_header); + for (i = 0; i < ack->nAcks; i++) { rxrpc_seq_t seq; @@ -197,7 +175,6 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) rxrpc_see_txbuf(txb, rxrpc_txbuf_see_unacked); if (list_empty(&txb->tx_link)) { - rxrpc_get_txbuf(txb, rxrpc_txbuf_get_retrans); list_add_tail(&txb->tx_link, &retrans_queue); set_bit(RXRPC_TXBUF_RESENT, &txb->flags); } @@ -241,7 +218,6 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) do_resend: unacked = true; if (list_empty(&txb->tx_link)) { - rxrpc_get_txbuf(txb, rxrpc_txbuf_get_retrans); list_add_tail(&txb->tx_link, &retrans_queue); set_bit(RXRPC_TXBUF_RESENT, &txb->flags); rxrpc_inc_stat(call->rxnet, stat_tx_data_retrans); @@ -249,10 +225,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) } no_further_resend: - spin_unlock(&call->tx_lock); no_resend: - rxrpc_free_skb(ack_skb, rxrpc_skb_put_ack); - resend_at = nsecs_to_jiffies(ktime_to_ns(ktime_sub(now, oldest))); resend_at += jiffies + rxrpc_get_rto_backoff(call->peer, !list_empty(&retrans_queue)); @@ -266,7 +239,7 @@ no_resend: * retransmitting data. */ if (list_empty(&retrans_queue)) { - rxrpc_reduce_call_timer(call, resend_at, now_j, + rxrpc_reduce_call_timer(call, resend_at, jiffies, rxrpc_timer_set_for_resend); ack_ts = ktime_sub(now, call->acks_latest_ts); if (ktime_to_us(ack_ts) < (call->peer->srtt_us >> 3)) @@ -276,15 +249,11 @@ no_resend: goto out; } + /* Retransmit the queue */ while ((txb = list_first_entry_or_null(&retrans_queue, struct rxrpc_txbuf, tx_link))) { list_del_init(&txb->tx_link); - rxrpc_send_data_packet(call, txb); - rxrpc_put_txbuf(txb, rxrpc_txbuf_put_trans); - - trace_rxrpc_retransmit(call, txb->seq, - ktime_to_ns(ktime_sub(txb->last_sent, - max_age))); + rxrpc_transmit_one(call, txb); } out: @@ -357,16 +326,27 @@ static void rxrpc_transmit_some_data(struct rxrpc_call *call) } } +/* + * Ping the other end to fill our RTT cache and to retrieve the rwind + * and MTU parameters. + */ +static void rxrpc_send_initial_ping(struct rxrpc_call *call) +{ + if (call->peer->rtt_count < 3 || + ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), + ktime_get_real())) + rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, + rxrpc_propose_ack_ping_for_params); +} + /* * Handle retransmission and deferred ACK/abort generation. */ -void rxrpc_process_call(struct work_struct *work) +void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) { - struct rxrpc_call *call = - container_of(work, struct rxrpc_call, processor); unsigned long now, next, t; - unsigned int iterations = 0; rxrpc_serial_t ackr_serial; + bool resend = false, expired = false; rxrpc_see_call(call, rxrpc_call_see_input); @@ -374,47 +354,31 @@ void rxrpc_process_call(struct work_struct *work) _enter("{%d,%s,%lx}", call->debug_id, rxrpc_call_states[call->state], call->events); -recheck_state: - if (call->acks_hard_ack != call->tx_bottom) - rxrpc_shrink_call_tx_buffer(call); - - /* Limit the number of times we do this before returning to the manager */ - if (!rxrpc_tx_window_has_space(call) || - list_empty(&call->tx_sendmsg)) { - iterations++; - if (iterations > 5) - goto requeue; - } - - if (test_and_clear_bit(RXRPC_CALL_EV_ABORT, &call->events)) { - rxrpc_send_abort_packet(call); - goto recheck_state; - } + if (call->state == RXRPC_CALL_COMPLETE) + goto out; - if (call->state == RXRPC_CALL_COMPLETE) { - del_timer_sync(&call->timer); + if (skb && skb->mark == RXRPC_SKB_MARK_ERROR) goto out; - } - /* Work out if any timeouts tripped */ + /* If we see our async-event poke, check for timeout trippage. */ now = jiffies; t = READ_ONCE(call->expect_rx_by); if (time_after_eq(now, t)) { trace_rxrpc_timer(call, rxrpc_timer_exp_normal, now); - set_bit(RXRPC_CALL_EV_EXPIRED, &call->events); + expired = true; } t = READ_ONCE(call->expect_req_by); if (call->state == RXRPC_CALL_SERVER_RECV_REQUEST && time_after_eq(now, t)) { trace_rxrpc_timer(call, rxrpc_timer_exp_idle, now); - set_bit(RXRPC_CALL_EV_EXPIRED, &call->events); + expired = true; } t = READ_ONCE(call->expect_term_by); if (time_after_eq(now, t)) { trace_rxrpc_timer(call, rxrpc_timer_exp_hard, now); - set_bit(RXRPC_CALL_EV_EXPIRED, &call->events); + expired = true; } t = READ_ONCE(call->delay_ack_at); @@ -453,13 +417,19 @@ recheck_state: if (time_after_eq(now, t)) { trace_rxrpc_timer(call, rxrpc_timer_exp_resend, now); cmpxchg(&call->resend_at, t, now + MAX_JIFFY_OFFSET); - set_bit(RXRPC_CALL_EV_RESEND, &call->events); + resend = true; } + if (skb) + rxrpc_input_call_packet(call, skb); + rxrpc_transmit_some_data(call); + if (test_and_clear_bit(RXRPC_CALL_EV_INITIAL_PING, &call->events)) + rxrpc_send_initial_ping(call); + /* Process events */ - if (test_and_clear_bit(RXRPC_CALL_EV_EXPIRED, &call->events)) { + if (expired) { if (test_bit(RXRPC_CALL_RX_HEARD, &call->flags) && (int)call->conn->hi_serial - (int)call->rx_serial > 0) { trace_rxrpc_call_reset(call); @@ -467,51 +437,50 @@ recheck_state: } else { rxrpc_abort_call("EXP", call, 0, RX_CALL_TIMEOUT, -ETIME); } - set_bit(RXRPC_CALL_EV_ABORT, &call->events); - goto recheck_state; + rxrpc_send_abort_packet(call); + goto out; } - if (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events)) { - call->acks_lost_top = call->tx_top; + if (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events)) rxrpc_send_ACK(call, RXRPC_ACK_PING, 0, rxrpc_propose_ack_ping_for_lost_ack); - } - if (test_and_clear_bit(RXRPC_CALL_EV_RESEND, &call->events) && - call->state != RXRPC_CALL_CLIENT_RECV_REPLY) { - rxrpc_resend(call, now); - goto recheck_state; - } + if (resend && call->state != RXRPC_CALL_CLIENT_RECV_REPLY) + rxrpc_resend(call, NULL); + + if (test_and_clear_bit(RXRPC_CALL_RX_IS_IDLE, &call->flags)) + rxrpc_send_ACK(call, RXRPC_ACK_IDLE, 0, + rxrpc_propose_ack_rx_idle); + + if (atomic_read(&call->ackr_nr_unacked) > 2) + rxrpc_send_ACK(call, RXRPC_ACK_IDLE, 0, + rxrpc_propose_ack_input_data); /* Make sure the timer is restarted */ - next = call->expect_rx_by; + if (call->state != RXRPC_CALL_COMPLETE) { + next = call->expect_rx_by; #define set(T) { t = READ_ONCE(T); if (time_before(t, next)) next = t; } - set(call->expect_req_by); - set(call->expect_term_by); - set(call->delay_ack_at); - set(call->ack_lost_at); - set(call->resend_at); - set(call->keepalive_at); - set(call->ping_at); - - now = jiffies; - if (time_after_eq(now, next)) - goto recheck_state; + set(call->expect_req_by); + set(call->expect_term_by); + set(call->delay_ack_at); + set(call->ack_lost_at); + set(call->resend_at); + set(call->keepalive_at); + set(call->ping_at); - rxrpc_reduce_call_timer(call, next, now, rxrpc_timer_restart); + now = jiffies; + if (time_after_eq(now, next)) + rxrpc_poke_call(call, rxrpc_call_poke_timer_now); - /* other events may have been raised since we started checking */ - if (call->events) - goto requeue; + rxrpc_reduce_call_timer(call, next, now, rxrpc_timer_restart); + } out: + if (call->state == RXRPC_CALL_COMPLETE) + del_timer_sync(&call->timer); + if (call->acks_hard_ack != call->tx_bottom) + rxrpc_shrink_call_tx_buffer(call); _leave(""); - return; - -requeue: - if (call->state < RXRPC_CALL_COMPLETE) - rxrpc_queue_call(call, rxrpc_call_queue_requeue); - goto out; } diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 7570b4e67bc5..d441a715d988 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -71,7 +71,7 @@ static void rxrpc_call_timer_expired(struct timer_list *t) if (call->state < RXRPC_CALL_COMPLETE) { trace_rxrpc_timer_expired(call, jiffies); - rxrpc_queue_call(call, rxrpc_call_queue_timer); + rxrpc_poke_call(call, rxrpc_call_poke_timer); } } @@ -148,7 +148,6 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, &rxrpc_call_user_mutex_lock_class_key); timer_setup(&call->timer, rxrpc_call_timer_expired, 0); - INIT_WORK(&call->processor, rxrpc_process_call); INIT_WORK(&call->destroyer, rxrpc_destroy_call); INIT_LIST_HEAD(&call->link); INIT_LIST_HEAD(&call->chan_wait_link); @@ -163,7 +162,6 @@ struct rxrpc_call *rxrpc_alloc_call(struct rxrpc_sock *rx, gfp_t gfp, init_waitqueue_head(&call->waitq); spin_lock_init(&call->notify_lock); spin_lock_init(&call->tx_lock); - spin_lock_init(&call->acks_ack_lock); rwlock_init(&call->state_lock); refcount_set(&call->ref, 1); call->debug_id = debug_id; @@ -252,6 +250,7 @@ static void rxrpc_start_call_timer(struct rxrpc_call *call) call->ack_lost_at = j; call->resend_at = j; call->ping_at = j; + call->keepalive_at = j; call->expect_rx_by = j; call->expect_req_by = j; call->expect_term_by = j; @@ -430,6 +429,29 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx, call->state = RXRPC_CALL_SERVER_SECURING; call->cong_tstamp = skb->tstamp; + spin_lock(&conn->state_lock); + + switch (conn->state) { + case RXRPC_CONN_SERVICE_UNSECURED: + case RXRPC_CONN_SERVICE_CHALLENGING: + call->state = RXRPC_CALL_SERVER_SECURING; + break; + case RXRPC_CONN_SERVICE: + call->state = RXRPC_CALL_SERVER_RECV_REQUEST; + break; + + case RXRPC_CONN_REMOTELY_ABORTED: + __rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED, + conn->abort_code, conn->error); + break; + case RXRPC_CONN_LOCALLY_ABORTED: + __rxrpc_abort_call("CON", call, 1, + conn->abort_code, conn->error); + break; + default: + BUG(); + } + /* Set the channel for this call. We don't get channel_lock as we're * only defending against the data_ready handler (which we're called * from) and the RESPONSE packet parser (which is only really @@ -440,6 +462,7 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx, conn->channels[chan].call_counter = call->call_id; conn->channels[chan].call_id = call->call_id; rcu_assign_pointer(conn->channels[chan].call, call); + spin_unlock(&conn->state_lock); spin_lock(&conn->peer->lock); hlist_add_head(&call->error_link, &conn->peer->error_targets); @@ -449,15 +472,6 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx, _leave(""); } -/* - * Queue a call's work processor. - */ -void rxrpc_queue_call(struct rxrpc_call *call, enum rxrpc_call_trace why) -{ - if (rxrpc_queue_work(&call->processor)) - trace_rxrpc_call(call->debug_id, refcount_read(&call->ref), 0, why); -} - /* * Note the re-emergence of a call. */ @@ -470,14 +484,15 @@ void rxrpc_see_call(struct rxrpc_call *call, enum rxrpc_call_trace why) } } -bool rxrpc_try_get_call(struct rxrpc_call *call, enum rxrpc_call_trace why) +struct rxrpc_call *rxrpc_try_get_call(struct rxrpc_call *call, + enum rxrpc_call_trace why) { int r; - if (!__refcount_inc_not_zero(&call->ref, &r)) - return false; + if (!call || !__refcount_inc_not_zero(&call->ref, &r)) + return NULL; trace_rxrpc_call(call->debug_id, r + 1, 0, why); - return true; + return call; } /* @@ -637,8 +652,6 @@ static void rxrpc_destroy_call(struct work_struct *work) struct rxrpc_call *call = container_of(work, struct rxrpc_call, destroyer); struct rxrpc_txbuf *txb; - del_timer_sync(&call->timer); - cancel_work_sync(&call->processor); /* The processor may restart the timer */ del_timer_sync(&call->timer); rxrpc_cleanup_ring(call); @@ -652,8 +665,8 @@ static void rxrpc_destroy_call(struct work_struct *work) list_del(&txb->call_link); rxrpc_put_txbuf(txb, rxrpc_txbuf_put_cleaned); } + rxrpc_put_txbuf(call->tx_pending, rxrpc_txbuf_put_cleaned); - rxrpc_free_skb(call->acks_soft_tbl, rxrpc_skb_put_ack); rxrpc_put_connection(call->conn, rxrpc_conn_put_call); rxrpc_put_peer(call->peer, rxrpc_peer_put_call); rxrpc_put_local(call->local, rxrpc_local_put_call); @@ -670,10 +683,9 @@ void rxrpc_cleanup_call(struct rxrpc_call *call) ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); ASSERT(test_bit(RXRPC_CALL_RELEASED, &call->flags)); - del_timer_sync(&call->timer); - cancel_work(&call->processor); + del_timer(&call->timer); - if (rcu_read_lock_held() || work_busy(&call->processor)) + if (rcu_read_lock_held()) /* Can't use the rxrpc workqueue as we need to cancel/flush * something that may be running/waiting there. */ diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index 23a74e35052d..643a56322224 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -479,3 +479,63 @@ void rxrpc_process_connection(struct work_struct *work) rxrpc_unuse_local(conn->local, rxrpc_local_unuse_conn_work); } } + +/* + * post connection-level events to the connection + * - this includes challenges, responses, some aborts and call terminal packet + * retransmission. + */ +static void rxrpc_post_packet_to_conn(struct rxrpc_connection *conn, + struct sk_buff *skb) +{ + _enter("%p,%p", conn, skb); + + rxrpc_get_skb(skb, rxrpc_skb_get_conn_work); + skb_queue_tail(&conn->rx_queue, skb); + rxrpc_queue_conn(conn, rxrpc_conn_queue_rx_work); +} + +/* + * Input a connection-level packet. + */ +int rxrpc_input_conn_packet(struct rxrpc_connection *conn, struct sk_buff *skb) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + + if (conn->state >= RXRPC_CONN_REMOTELY_ABORTED) { + _leave(" = -ECONNABORTED [%u]", conn->state); + return -ECONNABORTED; + } + + _enter("{%d},{%u,%%%u},", conn->debug_id, sp->hdr.type, sp->hdr.serial); + + switch (sp->hdr.type) { + case RXRPC_PACKET_TYPE_DATA: + case RXRPC_PACKET_TYPE_ACK: + rxrpc_conn_retransmit_call(conn, skb, + sp->hdr.cid & RXRPC_CHANNELMASK); + return 0; + + case RXRPC_PACKET_TYPE_BUSY: + /* Just ignore BUSY packets for now. */ + return 0; + + case RXRPC_PACKET_TYPE_ABORT: + conn->error = -ECONNABORTED; + conn->abort_code = skb->priority; + conn->state = RXRPC_CONN_REMOTELY_ABORTED; + set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags); + rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED, sp->hdr.serial); + return -ECONNABORTED; + + case RXRPC_PACKET_TYPE_CHALLENGE: + case RXRPC_PACKET_TYPE_RESPONSE: + rxrpc_post_packet_to_conn(conn, skb); + return 0; + + default: + trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, + tracepoint_string("bad_conn_pkt")); + return -EPROTO; + } +} diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 98e49646ca1d..3c8f83dacb2b 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -72,76 +72,55 @@ struct rxrpc_connection *rxrpc_alloc_connection(struct rxrpc_net *rxnet, * * The caller must be holding the RCU read lock. */ -struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local, - struct sockaddr_rxrpc *srx, - struct sk_buff *skb, - struct rxrpc_peer **_peer) +struct rxrpc_connection *rxrpc_find_client_connection_rcu(struct rxrpc_local *local, + struct sockaddr_rxrpc *srx, + struct sk_buff *skb) { struct rxrpc_connection *conn; - struct rxrpc_conn_proto k; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_peer *peer; _enter(",%x", sp->hdr.cid & RXRPC_CIDMASK); - k.epoch = sp->hdr.epoch; - k.cid = sp->hdr.cid & RXRPC_CIDMASK; - - if (rxrpc_to_server(sp)) { - /* We need to look up service connections by the full protocol - * parameter set. We look up the peer first as an intermediate - * step and then the connection from the peer's tree. - */ - peer = rxrpc_lookup_peer_rcu(local, srx); - if (!peer) - goto not_found; - *_peer = peer; - conn = rxrpc_find_service_conn_rcu(peer, skb); - if (!conn || refcount_read(&conn->ref) == 0) - goto not_found; - _leave(" = %p", conn); - return conn; - } else { - /* Look up client connections by connection ID alone as their - * IDs are unique for this machine. - */ - conn = idr_find(&rxrpc_client_conn_ids, sp->hdr.cid >> RXRPC_CIDSHIFT); - if (!conn || refcount_read(&conn->ref) == 0) { - _debug("no conn"); - goto not_found; - } + /* Look up client connections by connection ID alone as their IDs are + * unique for this machine. + */ + conn = idr_find(&rxrpc_client_conn_ids, sp->hdr.cid >> RXRPC_CIDSHIFT); + if (!conn || refcount_read(&conn->ref) == 0) { + _debug("no conn"); + goto not_found; + } - if (conn->proto.epoch != k.epoch || - conn->local != local) + if (conn->proto.epoch != sp->hdr.epoch || + conn->local != local) + goto not_found; + + peer = conn->peer; + switch (srx->transport.family) { + case AF_INET: + if (peer->srx.transport.sin.sin_port != + srx->transport.sin.sin_port || + peer->srx.transport.sin.sin_addr.s_addr != + srx->transport.sin.sin_addr.s_addr) goto not_found; - - peer = conn->peer; - switch (srx->transport.family) { - case AF_INET: - if (peer->srx.transport.sin.sin_port != - srx->transport.sin.sin_port || - peer->srx.transport.sin.sin_addr.s_addr != - srx->transport.sin.sin_addr.s_addr) - goto not_found; - break; + break; #ifdef CONFIG_AF_RXRPC_IPV6 - case AF_INET6: - if (peer->srx.transport.sin6.sin6_port != - srx->transport.sin6.sin6_port || - memcmp(&peer->srx.transport.sin6.sin6_addr, - &srx->transport.sin6.sin6_addr, - sizeof(struct in6_addr)) != 0) - goto not_found; - break; + case AF_INET6: + if (peer->srx.transport.sin6.sin6_port != + srx->transport.sin6.sin6_port || + memcmp(&peer->srx.transport.sin6.sin6_addr, + &srx->transport.sin6.sin6_addr, + sizeof(struct in6_addr)) != 0) + goto not_found; + break; #endif - default: - BUG(); - } - - _leave(" = %p", conn); - return conn; + default: + BUG(); } + _leave(" = %p", conn); + return conn; + not_found: _leave(" = NULL"); return NULL; diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 01d32f817a7a..7ae7046f0b03 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -12,10 +12,8 @@ static void rxrpc_proto_abort(const char *why, struct rxrpc_call *call, rxrpc_seq_t seq) { - if (rxrpc_abort_call(why, call, seq, RX_PROTOCOL_ERROR, -EBADMSG)) { - set_bit(RXRPC_CALL_EV_ABORT, &call->events); - rxrpc_queue_call(call, rxrpc_call_queue_abort); - } + if (rxrpc_abort_call(why, call, seq, RX_PROTOCOL_ERROR, -EBADMSG)) + rxrpc_send_abort_packet(call); } /* @@ -174,8 +172,8 @@ out_no_clear_ca: call->cong_cwnd = cwnd; call->cong_cumul_acks = cumulative_acks; trace_rxrpc_congest(call, summary, acked_serial, change); - if (resend && !test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events)) - rxrpc_queue_call(call, rxrpc_call_queue_resend); + if (resend) + rxrpc_resend(call, skb); return; packet_loss_detected: @@ -398,6 +396,8 @@ static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb, /* Send an immediate ACK if we fill in a hole */ else if (!skb_queue_empty(&call->rx_oos_queue)) ack_reason = RXRPC_ACK_DELAY; + else + atomic_inc_return(&call->ackr_nr_unacked); window++; if (after(window, wtop)) @@ -473,14 +473,6 @@ static void rxrpc_input_data_one(struct rxrpc_call *call, struct sk_buff *skb, } send_ack: - if (ack_reason < 0 && - atomic_inc_return(&call->ackr_nr_unacked) > 2 && - test_and_set_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags)) { - ack_reason = RXRPC_ACK_IDLE; - } else if (ack_reason >= 0) { - set_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags); - } - if (ack_reason >= 0) rxrpc_send_ACK(call, ack_reason, serial, rxrpc_propose_ack_input_data); @@ -510,7 +502,7 @@ static bool rxrpc_input_split_jumbo(struct rxrpc_call *call, struct sk_buff *skb &jhdr, sizeof(jhdr)) < 0) goto protocol_error; - jskb = skb_clone(skb, GFP_ATOMIC); + jskb = skb_clone(skb, GFP_NOFS); if (!jskb) { kdebug("couldn't clone"); return false; @@ -562,24 +554,6 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) if (state >= RXRPC_CALL_COMPLETE) return; - /* Unshare the packet so that it can be modified for in-place - * decryption. - */ - if (sp->hdr.securityIndex != 0) { - struct sk_buff *nskb = skb_unshare(skb, GFP_ATOMIC); - if (!nskb) { - rxrpc_eaten_skb(skb, rxrpc_skb_eaten_by_unshare_nomem); - return; - } - - if (nskb != skb) { - rxrpc_eaten_skb(skb, rxrpc_skb_eaten_by_unshare); - skb = nskb; - rxrpc_new_skb(skb, rxrpc_skb_new_unshared); - sp = rxrpc_skb(skb); - } - } - if (state == RXRPC_CALL_SERVER_RECV_REQUEST) { unsigned long timo = READ_ONCE(call->next_req_timo); unsigned long now, expect_req_by; @@ -599,15 +573,15 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) if ((state == RXRPC_CALL_CLIENT_SEND_REQUEST || state == RXRPC_CALL_CLIENT_AWAIT_REPLY) && !rxrpc_receiving_reply(call)) - goto out; + goto out_notify; if (!rxrpc_input_split_jumbo(call, skb)) { rxrpc_proto_abort("VLD", call, sp->hdr.seq); - goto out; + goto out_notify; } skb = NULL; -out: +out_notify: trace_rxrpc_notify_socket(call->debug_id, serial); rxrpc_notify_socket(call); _leave(" [queued]"); @@ -667,32 +641,6 @@ static void rxrpc_complete_rtt_probe(struct rxrpc_call *call, trace_rxrpc_rtt_rx(call, rxrpc_rtt_rx_lost, 9, 0, acked_serial, 0, 0); } -/* - * Process the response to a ping that we sent to find out if we lost an ACK. - * - * If we got back a ping response that indicates a lower tx_top than what we - * had at the time of the ping transmission, we adjudge all the DATA packets - * sent between the response tx_top and the ping-time tx_top to have been lost. - */ -static void rxrpc_input_check_for_lost_ack(struct rxrpc_call *call) -{ - if (after(call->acks_lost_top, call->acks_prev_seq) && - !test_and_set_bit(RXRPC_CALL_EV_RESEND, &call->events)) - rxrpc_queue_call(call, rxrpc_call_queue_resend); -} - -/* - * Process a ping response. - */ -static void rxrpc_input_ping_response(struct rxrpc_call *call, - ktime_t resp_time, - rxrpc_serial_t acked_serial, - rxrpc_serial_t ack_serial) -{ - if (acked_serial == call->acks_lost_ping) - rxrpc_input_check_for_lost_ack(call); -} - /* * Process the extra information that may be appended to an ACK packet */ @@ -801,7 +749,6 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) struct rxrpc_ackpacket ack; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rxrpc_ackinfo info; - struct sk_buff *skb_old = NULL; rxrpc_serial_t ack_serial, acked_serial; rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt; int nr_acks, offset, ioffset; @@ -809,10 +756,8 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) _enter(""); offset = sizeof(struct rxrpc_wire_header); - if (skb_copy_bits(skb, offset, &ack, sizeof(ack)) < 0) { - rxrpc_proto_abort("XAK", call, 0); - goto out; - } + if (skb_copy_bits(skb, offset, &ack, sizeof(ack)) < 0) + return rxrpc_proto_abort("XAK", call, 0); offset += sizeof(ack); ack_serial = sp->hdr.serial; @@ -863,7 +808,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_is_client_call(call)) { rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED, 0, -ENETRESET); - goto out; + return; } /* If we get an OUT_OF_SEQUENCE ACK from the server, that can also @@ -877,7 +822,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_is_client_call(call)) { rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED, 0, -ENETRESET); - goto out; + return; } /* Discard any out-of-order or duplicate ACKs (outside lock). */ @@ -885,39 +830,25 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) trace_rxrpc_rx_discard_ack(call->debug_id, ack_serial, first_soft_ack, call->acks_first_seq, prev_pkt, call->acks_prev_seq); - goto out; + return; } info.rxMTU = 0; ioffset = offset + nr_acks + 3; if (skb->len >= ioffset + sizeof(info) && - skb_copy_bits(skb, ioffset, &info, sizeof(info)) < 0) { - rxrpc_proto_abort("XAI", call, 0); - goto out; - } + skb_copy_bits(skb, ioffset, &info, sizeof(info)) < 0) + return rxrpc_proto_abort("XAI", call, 0); if (nr_acks > 0) skb_condense(skb); - /* Discard any out-of-order or duplicate ACKs (inside lock). */ - if (!rxrpc_is_ack_valid(call, first_soft_ack, prev_pkt)) { - trace_rxrpc_rx_discard_ack(call->debug_id, ack_serial, - first_soft_ack, call->acks_first_seq, - prev_pkt, call->acks_prev_seq); - goto out; - } call->acks_latest_ts = skb->tstamp; - call->acks_first_seq = first_soft_ack; call->acks_prev_seq = prev_pkt; switch (ack.reason) { case RXRPC_ACK_PING: break; - case RXRPC_ACK_PING_RESPONSE: - rxrpc_input_ping_response(call, skb->tstamp, acked_serial, - ack_serial); - fallthrough; default: if (after(acked_serial, call->acks_highest_serial)) call->acks_highest_serial = acked_serial; @@ -928,10 +859,8 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) if (info.rxMTU) rxrpc_input_ackinfo(call, skb, &info); - if (first_soft_ack == 0) { - rxrpc_proto_abort("AK0", call, 0); - goto out; - } + if (first_soft_ack == 0) + return rxrpc_proto_abort("AK0", call, 0); /* Ignore ACKs unless we are or have just been transmitting. */ switch (READ_ONCE(call->state)) { @@ -941,45 +870,27 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) case RXRPC_CALL_SERVER_AWAIT_ACK: break; default: - goto out; + return; } if (before(hard_ack, call->acks_hard_ack) || - after(hard_ack, call->tx_top)) { - rxrpc_proto_abort("AKW", call, 0); - goto out; - } - if (nr_acks > call->tx_top - hard_ack) { - rxrpc_proto_abort("AKN", call, 0); - goto out; - } + after(hard_ack, call->tx_top)) + return rxrpc_proto_abort("AKW", call, 0); + if (nr_acks > call->tx_top - hard_ack) + return rxrpc_proto_abort("AKN", call, 0); if (after(hard_ack, call->acks_hard_ack)) { if (rxrpc_rotate_tx_window(call, hard_ack, &summary)) { rxrpc_end_tx_phase(call, false, "ETA"); - goto out; + return; } } if (nr_acks > 0) { - if (offset > (int)skb->len - nr_acks) { - rxrpc_proto_abort("XSA", call, 0); - goto out; - } - - rxrpc_get_skb(skb, rxrpc_skb_get_ack); - spin_lock(&call->acks_ack_lock); - skb_old = call->acks_soft_tbl; - call->acks_soft_tbl = skb; - spin_unlock(&call->acks_ack_lock); - + if (offset > (int)skb->len - nr_acks) + return rxrpc_proto_abort("XSA", call, 0); rxrpc_input_soft_acks(call, skb->data + offset, first_soft_ack, nr_acks, &summary); - } else if (call->acks_soft_tbl) { - spin_lock(&call->acks_ack_lock); - skb_old = call->acks_soft_tbl; - call->acks_soft_tbl = NULL; - spin_unlock(&call->acks_ack_lock); } if (test_bit(RXRPC_CALL_TX_LAST, &call->flags) && @@ -989,8 +900,6 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_propose_ack_ping_for_lost_reply); rxrpc_congestion_management(call, skb, &summary, acked_serial); -out: - rxrpc_free_skb(skb_old, rxrpc_skb_put_ack); } /* @@ -1020,13 +929,20 @@ static void rxrpc_input_abort(struct rxrpc_call *call, struct sk_buff *skb) /* * Process an incoming call packet. */ -void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) +void rxrpc_input_call_packet(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); unsigned long timo; _enter("%p,%p", call, skb); + if (sp->hdr.serviceId != call->dest_srx.srx_service) + call->dest_srx.srx_service = sp->hdr.serviceId; + if ((int)sp->hdr.serial - (int)call->rx_serial > 0) + call->rx_serial = sp->hdr.serial; + if (!test_bit(RXRPC_CALL_RX_HEARD, &call->flags)) + set_bit(RXRPC_CALL_RX_HEARD, &call->flags); + timo = READ_ONCE(call->next_rx_timo); if (timo) { unsigned long now = jiffies, expect_rx_by; @@ -1072,9 +988,10 @@ void rxrpc_input_call_event(struct rxrpc_call *call, struct sk_buff *skb) * * TODO: If callNumber > call_id + 1, renegotiate security. */ -void rxrpc_input_implicit_end_call(struct rxrpc_connection *conn, - struct rxrpc_call *call) +void rxrpc_implicit_end_call(struct rxrpc_call *call, struct sk_buff *skb) { + struct rxrpc_connection *conn = call->conn; + switch (READ_ONCE(call->state)) { case RXRPC_CALL_SERVER_AWAIT_ACK: rxrpc_call_completed(call); @@ -1082,14 +999,14 @@ void rxrpc_input_implicit_end_call(struct rxrpc_connection *conn, case RXRPC_CALL_COMPLETE: break; default: - if (rxrpc_abort_call("IMP", call, 0, RX_CALL_DEAD, -ESHUTDOWN)) { - set_bit(RXRPC_CALL_EV_ABORT, &call->events); - rxrpc_queue_call(call, rxrpc_call_queue_abort); - } + if (rxrpc_abort_call("IMP", call, 0, RX_CALL_DEAD, -ESHUTDOWN)) + rxrpc_send_abort_packet(call); trace_rxrpc_improper_term(call); break; } + rxrpc_input_call_event(call, skb); + spin_lock(&conn->bundle->channel_lock); __rxrpc_disconnect_call(conn, call); spin_unlock(&conn->bundle->channel_lock); diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c index bc65d83fab88..19aa315eddf5 100644 --- a/net/rxrpc/io_thread.c +++ b/net/rxrpc/io_thread.c @@ -9,6 +9,10 @@ #include "ar-internal.h" +static int rxrpc_input_packet_on_conn(struct rxrpc_connection *conn, + struct sockaddr_rxrpc *peer_srx, + struct sk_buff *skb); + /* * handle data received on the local endpoint * - may be called in interrupt context @@ -63,45 +67,19 @@ void rxrpc_error_report(struct sock *sk) } /* - * post connection-level events to the connection - * - this includes challenges, responses, some aborts and call terminal packet - * retransmission. + * Process event packets targeted at a local endpoint. */ -static void rxrpc_post_packet_to_conn(struct rxrpc_connection *conn, - struct sk_buff *skb) +static void rxrpc_input_version(struct rxrpc_local *local, struct sk_buff *skb) { - _enter("%p,%p", conn, skb); - - rxrpc_get_skb(skb, rxrpc_skb_get_conn_work); - skb_queue_tail(&conn->rx_queue, skb); - rxrpc_queue_conn(conn, rxrpc_conn_queue_rx_work); -} + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + char v; -/* - * post endpoint-level events to the local endpoint - * - this includes debug and version messages - */ -static void rxrpc_post_packet_to_local(struct rxrpc_local *local, - struct sk_buff *skb) -{ - _enter("%p,%p", local, skb); + _enter(""); - if (rxrpc_get_local_maybe(local, rxrpc_local_get_queue)) { - rxrpc_get_skb(skb, rxrpc_skb_get_local_work); - skb_queue_tail(&local->event_queue, skb); - rxrpc_queue_local(local); - } -} - -/* - * put a packet up for transport-level abort - */ -static void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) -{ - if (rxrpc_get_local_maybe(local, rxrpc_local_get_queue)) { - rxrpc_get_skb(skb, rxrpc_skb_get_reject_work); - skb_queue_tail(&local->reject_queue, skb); - rxrpc_queue_local(local); + rxrpc_see_skb(skb, rxrpc_skb_see_version); + if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header), &v, 1) >= 0) { + if (v == 0) + rxrpc_send_version_request(local, &sp->hdr, skb); } } @@ -156,22 +134,13 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb) { struct rxrpc_connection *conn; struct sockaddr_rxrpc peer_srx; - struct rxrpc_channel *chan; - struct rxrpc_call *call = NULL; struct rxrpc_skb_priv *sp; struct rxrpc_peer *peer = NULL; - struct rxrpc_sock *rx = NULL; struct sk_buff *skb = *_skb; - unsigned int channel; - - if (skb->tstamp == 0) - skb->tstamp = ktime_get_real(); + int ret = 0; skb_pull(skb, sizeof(struct udphdr)); - /* The UDP protocol already released all skb resources; - * we are free to add our own data there. - */ sp = rxrpc_skb(skb); /* dig out the RxRPC connection details */ @@ -186,15 +155,13 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb) } } - if (skb->tstamp == 0) - skb->tstamp = ktime_get_real(); trace_rxrpc_rx_packet(sp); switch (sp->hdr.type) { case RXRPC_PACKET_TYPE_VERSION: if (rxrpc_to_client(sp)) return 0; - rxrpc_post_packet_to_local(local, skb); + rxrpc_input_version(local, skb); return 0; case RXRPC_PACKET_TYPE_BUSY: @@ -259,7 +226,7 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb) goto bad_message; if (WARN_ON_ONCE(rxrpc_extract_addr_from_skb(&peer_srx, skb) < 0)) - return 0; /* Unsupported address type - discard. */ + return true; /* Unsupported address type - discard. */ if (peer_srx.transport.family != local->srx.transport.family && (peer_srx.transport.family == AF_INET && @@ -267,171 +234,172 @@ static int rxrpc_input_packet(struct rxrpc_local *local, struct sk_buff **_skb) pr_warn_ratelimited("AF_RXRPC: Protocol mismatch %u not %u\n", peer_srx.transport.family, local->srx.transport.family); - return 0; /* Wrong address type - discard. */ + return true; /* Wrong address type - discard. */ + } + + if (rxrpc_to_client(sp)) { + rcu_read_lock(); + conn = rxrpc_find_client_connection_rcu(local, &peer_srx, skb); + conn = rxrpc_get_connection_maybe(conn, rxrpc_conn_get_call_input); + rcu_read_unlock(); + if (!conn) { + trace_rxrpc_abort(0, "NCC", sp->hdr.cid, + sp->hdr.callNumber, sp->hdr.seq, + RXKADINCONSISTENCY, EBADMSG); + goto protocol_error; + } + + ret = rxrpc_input_packet_on_conn(conn, &peer_srx, skb); + rxrpc_put_connection(conn, rxrpc_conn_put_call_input); + return ret; } + /* We need to look up service connections by the full protocol + * parameter set. We look up the peer first as an intermediate step + * and then the connection from the peer's tree. + */ rcu_read_lock(); - if (rxrpc_to_server(sp)) { - /* Weed out packets to services we're not offering. Packets - * that would begin a call are explicitly rejected and the rest - * are just discarded. - */ - rx = rcu_dereference(local->service); - if (!rx || (sp->hdr.serviceId != rx->srx.srx_service && - sp->hdr.serviceId != rx->second_service) - ) { - rcu_read_unlock(); - if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA && - sp->hdr.seq == 1) - goto unsupported_service; - return 0; - } + peer = rxrpc_lookup_peer_rcu(local, &peer_srx); + if (!peer) { + rcu_read_unlock(); + return rxrpc_new_incoming_call(local, NULL, NULL, &peer_srx, skb); } - conn = rxrpc_find_connection_rcu(local, &peer_srx, skb, &peer); + conn = rxrpc_find_service_conn_rcu(peer, skb); + conn = rxrpc_get_connection_maybe(conn, rxrpc_conn_get_call_input); if (conn) { - if (sp->hdr.securityIndex != conn->security_ix) - goto wrong_security; + rcu_read_unlock(); + ret = rxrpc_input_packet_on_conn(conn, &peer_srx, skb); + rxrpc_put_connection(conn, rxrpc_conn_put_call_input); + return ret; + } - if (sp->hdr.serviceId != conn->service_id) { - int old_id; + peer = rxrpc_get_peer_maybe(peer, rxrpc_peer_get_input); + rcu_read_unlock(); - if (!test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags)) - goto reupgrade; - old_id = cmpxchg(&conn->service_id, conn->orig_service_id, - sp->hdr.serviceId); + ret = rxrpc_new_incoming_call(local, peer, NULL, &peer_srx, skb); + rxrpc_put_peer(peer, rxrpc_peer_put_input); + if (ret < 0) + goto reject_packet; + return 0; - if (old_id != conn->orig_service_id && - old_id != sp->hdr.serviceId) - goto reupgrade; - } +bad_message: + trace_rxrpc_abort(0, "BAD", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, + RX_PROTOCOL_ERROR, EBADMSG); +protocol_error: + skb->priority = RX_PROTOCOL_ERROR; + skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; +reject_packet: + rxrpc_reject_packet(local, skb); + return ret; +} - if (sp->hdr.callNumber == 0) { - /* Connection-level packet */ - _debug("CONN %p {%d}", conn, conn->debug_id); - conn = rxrpc_get_connection_maybe(conn, rxrpc_conn_get_conn_input); - rcu_read_unlock(); - if (conn) { - rxrpc_post_packet_to_conn(conn, skb); - rxrpc_put_connection(conn, rxrpc_conn_put_conn_input); - } - return 0; - } +/* + * Deal with a packet that's associated with an extant connection. + */ +static int rxrpc_input_packet_on_conn(struct rxrpc_connection *conn, + struct sockaddr_rxrpc *peer_srx, + struct sk_buff *skb) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + struct rxrpc_channel *chan; + struct rxrpc_call *call = NULL; + unsigned int channel; - if ((int)sp->hdr.serial - (int)conn->hi_serial > 0) - conn->hi_serial = sp->hdr.serial; + if (sp->hdr.securityIndex != conn->security_ix) + goto wrong_security; - /* Call-bound packets are routed by connection channel. */ - channel = sp->hdr.cid & RXRPC_CHANNELMASK; - chan = &conn->channels[channel]; + if (sp->hdr.serviceId != conn->service_id) { + int old_id; - /* Ignore really old calls */ - if (sp->hdr.callNumber < chan->last_call) { - rcu_read_unlock(); - return 0; - } + if (!test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags)) + goto reupgrade; + old_id = cmpxchg(&conn->service_id, conn->orig_service_id, + sp->hdr.serviceId); - if (sp->hdr.callNumber == chan->last_call) { - if (chan->call || - sp->hdr.type == RXRPC_PACKET_TYPE_ABORT) { - rcu_read_unlock(); - return 0; - } + if (old_id != conn->orig_service_id && + old_id != sp->hdr.serviceId) + goto reupgrade; + } - /* For the previous service call, if completed - * successfully, we discard all further packets. - */ - if (rxrpc_conn_is_service(conn) && - chan->last_type == RXRPC_PACKET_TYPE_ACK) { - rcu_read_unlock(); - return 0; - } + if (after(sp->hdr.serial, conn->hi_serial)) + conn->hi_serial = sp->hdr.serial; - /* But otherwise we need to retransmit the final packet - * from data cached in the connection record. - */ - if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA) - trace_rxrpc_rx_data(chan->call_debug_id, - sp->hdr.seq, - sp->hdr.serial, - sp->hdr.flags); - conn = rxrpc_get_connection_maybe(conn, rxrpc_conn_get_call_input); - rcu_read_unlock(); - if (conn) { - rxrpc_post_packet_to_conn(conn, skb); - rxrpc_put_connection(conn, rxrpc_conn_put_call_input); - } + /* It's a connection-level packet if the call number is 0. */ + if (sp->hdr.callNumber == 0) + return rxrpc_input_conn_packet(conn, skb); + + /* Call-bound packets are routed by connection channel. */ + channel = sp->hdr.cid & RXRPC_CHANNELMASK; + chan = &conn->channels[channel]; + + /* Ignore really old calls */ + if (sp->hdr.callNumber < chan->last_call) + return 0; + + if (sp->hdr.callNumber == chan->last_call) { + if (chan->call || + sp->hdr.type == RXRPC_PACKET_TYPE_ABORT) return 0; - } - call = rcu_dereference(chan->call); + /* For the previous service call, if completed successfully, we + * discard all further packets. + */ + if (rxrpc_conn_is_service(conn) && + chan->last_type == RXRPC_PACKET_TYPE_ACK) + return 0; - if (sp->hdr.callNumber > chan->call_id) { - if (rxrpc_to_client(sp)) { - rcu_read_unlock(); - goto reject_packet; - } - if (call) { - rxrpc_input_implicit_end_call(conn, call); - chan->call = NULL; - call = NULL; - } - } + /* But otherwise we need to retransmit the final packet from + * data cached in the connection record. + */ + if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA) + trace_rxrpc_rx_data(chan->call_debug_id, + sp->hdr.seq, + sp->hdr.serial, + sp->hdr.flags); + rxrpc_input_conn_packet(conn, skb); + return 0; + } - if (call && !rxrpc_try_get_call(call, rxrpc_call_get_input)) - call = NULL; + rcu_read_lock(); + call = rxrpc_try_get_call(rcu_dereference(chan->call), + rxrpc_call_get_input); + rcu_read_unlock(); + + if (sp->hdr.callNumber > chan->call_id) { + if (rxrpc_to_client(sp)) { + rxrpc_put_call(call, rxrpc_call_put_input); + goto reject_packet; + } if (call) { - if (sp->hdr.serviceId != call->dest_srx.srx_service) - call->dest_srx.srx_service = sp->hdr.serviceId; - if ((int)sp->hdr.serial - (int)call->rx_serial > 0) - call->rx_serial = sp->hdr.serial; - if (!test_bit(RXRPC_CALL_RX_HEARD, &call->flags)) - set_bit(RXRPC_CALL_RX_HEARD, &call->flags); + rxrpc_implicit_end_call(call, skb); + rxrpc_put_call(call, rxrpc_call_put_input); + call = NULL; } } if (!call) { - if (rxrpc_to_client(sp) || - sp->hdr.type != RXRPC_PACKET_TYPE_DATA) { - rcu_read_unlock(); + if (rxrpc_to_client(sp)) goto bad_message; - } - if (sp->hdr.seq != 1) { - rcu_read_unlock(); + if (rxrpc_new_incoming_call(conn->local, conn->peer, conn, + peer_srx, skb)) return 0; - } - call = rxrpc_new_incoming_call(local, rx, &peer_srx, skb); - if (!call) { - rcu_read_unlock(); - goto reject_packet; - } + goto reject_packet; } - rcu_read_unlock(); - - /* Process a call packet. */ rxrpc_input_call_event(call, skb); rxrpc_put_call(call, rxrpc_call_put_input); - trace_rxrpc_rx_done(0, 0); return 0; wrong_security: - rcu_read_unlock(); trace_rxrpc_abort(0, "SEC", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, RXKADINCONSISTENCY, EBADMSG); skb->priority = RXKADINCONSISTENCY; goto post_abort; -unsupported_service: - trace_rxrpc_abort(0, "INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, - RX_INVALID_OPERATION, EOPNOTSUPP); - skb->priority = RX_INVALID_OPERATION; - goto post_abort; - reupgrade: - rcu_read_unlock(); trace_rxrpc_abort(0, "UPG", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, RX_PROTOCOL_ERROR, EBADMSG); goto protocol_error; @@ -444,7 +412,7 @@ protocol_error: post_abort: skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; reject_packet: - rxrpc_reject_packet(local, skb); + rxrpc_reject_packet(conn->local, skb); return 0; } @@ -479,6 +447,11 @@ int rxrpc_io_thread(void *data) continue; } + if (!list_empty(&local->ack_tx_queue)) { + rxrpc_transmit_ack_packets(local); + continue; + } + /* Process received packets and errors. */ if ((skb = __skb_dequeue(&rx_queue))) { switch (skb->mark) { diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c index c344383a20b2..5e69ea6b233d 100644 --- a/net/rxrpc/local_event.c +++ b/net/rxrpc/local_event.c @@ -21,9 +21,9 @@ static const char rxrpc_version_string[65] = "linux-" UTS_RELEASE " AF_RXRPC"; /* * Reply to a version request */ -static void rxrpc_send_version_request(struct rxrpc_local *local, - struct rxrpc_host_header *hdr, - struct sk_buff *skb) +void rxrpc_send_version_request(struct rxrpc_local *local, + struct rxrpc_host_header *hdr, + struct sk_buff *skb) { struct rxrpc_wire_header whdr; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); @@ -73,40 +73,3 @@ static void rxrpc_send_version_request(struct rxrpc_local *local, _leave(""); } - -/* - * Process event packets targeted at a local endpoint. - */ -void rxrpc_process_local_events(struct rxrpc_local *local) -{ - struct sk_buff *skb; - char v; - - _enter(""); - - skb = skb_dequeue(&local->event_queue); - if (skb) { - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - - rxrpc_see_skb(skb, rxrpc_skb_see_local_work); - _debug("{%d},{%u}", local->debug_id, sp->hdr.type); - - switch (sp->hdr.type) { - case RXRPC_PACKET_TYPE_VERSION: - if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header), - &v, 1) < 0) - return; - if (v == 0) - rxrpc_send_version_request(local, &sp->hdr, skb); - break; - - default: - /* Just ignore anything we don't understand */ - break; - } - - rxrpc_free_skb(skb, rxrpc_skb_put_input); - } - - _leave(""); -} diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 03f491cc23ef..c73a5a1bc088 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -20,7 +20,6 @@ #include #include "ar-internal.h" -static void rxrpc_local_processor(struct work_struct *); static void rxrpc_local_rcu(struct rcu_head *); /* @@ -97,12 +96,9 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet, atomic_set(&local->active_users, 1); local->rxnet = rxnet; INIT_HLIST_NODE(&local->link); - INIT_WORK(&local->processor, rxrpc_local_processor); INIT_LIST_HEAD(&local->ack_tx_queue); spin_lock_init(&local->ack_tx_lock); init_rwsem(&local->defrag_sem); - skb_queue_head_init(&local->reject_queue); - skb_queue_head_init(&local->event_queue); skb_queue_head_init(&local->rx_queue); INIT_LIST_HEAD(&local->call_attend_q); local->client_bundles = RB_ROOT; @@ -318,21 +314,6 @@ struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local, return NULL; } -/* - * Queue a local endpoint and pass the caller's reference to the work item. - */ -void rxrpc_queue_local(struct rxrpc_local *local) -{ - unsigned int debug_id = local->debug_id; - int r = refcount_read(&local->ref); - int u = atomic_read(&local->active_users); - - if (rxrpc_queue_work(&local->processor)) - trace_rxrpc_local(debug_id, rxrpc_local_queued, r, u); - else - rxrpc_put_local(local, rxrpc_local_put_already_queued); -} - /* * Drop a ref on a local endpoint. */ @@ -374,7 +355,7 @@ struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *local, /* * Cease using a local endpoint. Once the number of active users reaches 0, we - * start the closure of the transport in the work processor. + * start the closure of the transport in the I/O thread.. */ void rxrpc_unuse_local(struct rxrpc_local *local, enum rxrpc_local_trace why) { @@ -416,52 +397,9 @@ void rxrpc_destroy_local(struct rxrpc_local *local) /* At this point, there should be no more packets coming in to the * local endpoint. */ - rxrpc_purge_queue(&local->reject_queue); - rxrpc_purge_queue(&local->event_queue); rxrpc_purge_queue(&local->rx_queue); } -/* - * Process events on an endpoint. The work item carries a ref which - * we must release. - */ -static void rxrpc_local_processor(struct work_struct *work) -{ - struct rxrpc_local *local = - container_of(work, struct rxrpc_local, processor); - bool again; - - if (local->dead) - return; - - rxrpc_see_local(local, rxrpc_local_processing); - - do { - again = false; - if (!__rxrpc_use_local(local, rxrpc_local_use_work)) - break; - - if (!list_empty(&local->ack_tx_queue)) { - rxrpc_transmit_ack_packets(local); - again = true; - } - - if (!skb_queue_empty(&local->reject_queue)) { - rxrpc_reject_packets(local); - again = true; - } - - if (!skb_queue_empty(&local->event_queue)) { - rxrpc_process_local_events(local); - again = true; - } - - __rxrpc_unuse_local(local, rxrpc_local_unuse_work); - } while (again); - - rxrpc_put_local(local, rxrpc_local_put_queue); -} - /* * Destroy a local endpoint after the RCU grace period expires. */ @@ -469,13 +407,8 @@ static void rxrpc_local_rcu(struct rcu_head *rcu) { struct rxrpc_local *local = container_of(rcu, struct rxrpc_local, rcu); - _enter("%d", local->debug_id); - - ASSERT(!work_pending(&local->processor)); - rxrpc_see_local(local, rxrpc_local_free); kfree(local); - _leave(""); } /* diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 71963b4523be..2ea1fa1b8a6f 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -229,11 +229,6 @@ static int rxrpc_send_ack_packet(struct rxrpc_local *local, struct rxrpc_txbuf * if (txb->ack.reason == RXRPC_ACK_PING) txb->wire.flags |= RXRPC_REQUEST_ACK; - if (txb->ack.reason == RXRPC_ACK_DELAY) - clear_bit(RXRPC_CALL_DELAY_ACK_PENDING, &call->flags); - if (txb->ack.reason == RXRPC_ACK_IDLE) - clear_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags); - n = rxrpc_fill_out_ack(conn, call, txb); if (n == 0) return 0; @@ -247,8 +242,6 @@ static int rxrpc_send_ack_packet(struct rxrpc_local *local, struct rxrpc_txbuf * trace_rxrpc_tx_ack(call->debug_id, serial, ntohl(txb->ack.firstPacket), ntohl(txb->ack.serial), txb->ack.reason, txb->ack.nAcks); - if (txb->ack_why == rxrpc_propose_ack_ping_for_lost_ack) - call->acks_lost_ping = serial; if (txb->ack.reason == RXRPC_ACK_PING) rtt_slot = rxrpc_begin_rtt_probe(call, serial, rxrpc_rtt_tx_ping); @@ -588,21 +581,20 @@ send_fragmentable: } /* - * reject packets through the local endpoint + * Reject a packet through the local endpoint. */ -void rxrpc_reject_packets(struct rxrpc_local *local) +void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb) { - struct sockaddr_rxrpc srx; - struct rxrpc_skb_priv *sp; struct rxrpc_wire_header whdr; - struct sk_buff *skb; + struct sockaddr_rxrpc srx; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct msghdr msg; struct kvec iov[2]; size_t size; __be32 code; int ret, ioc; - _enter("%d", local->debug_id); + rxrpc_see_skb(skb, rxrpc_skb_see_reject); iov[0].iov_base = &whdr; iov[0].iov_len = sizeof(whdr); @@ -616,52 +608,42 @@ void rxrpc_reject_packets(struct rxrpc_local *local) memset(&whdr, 0, sizeof(whdr)); - while ((skb = skb_dequeue(&local->reject_queue))) { - rxrpc_see_skb(skb, rxrpc_skb_see_reject); - sp = rxrpc_skb(skb); + switch (skb->mark) { + case RXRPC_SKB_MARK_REJECT_BUSY: + whdr.type = RXRPC_PACKET_TYPE_BUSY; + size = sizeof(whdr); + ioc = 1; + break; + case RXRPC_SKB_MARK_REJECT_ABORT: + whdr.type = RXRPC_PACKET_TYPE_ABORT; + code = htonl(skb->priority); + size = sizeof(whdr) + sizeof(code); + ioc = 2; + break; + default: + return; + } - switch (skb->mark) { - case RXRPC_SKB_MARK_REJECT_BUSY: - whdr.type = RXRPC_PACKET_TYPE_BUSY; - size = sizeof(whdr); - ioc = 1; - break; - case RXRPC_SKB_MARK_REJECT_ABORT: - whdr.type = RXRPC_PACKET_TYPE_ABORT; - code = htonl(skb->priority); - size = sizeof(whdr) + sizeof(code); - ioc = 2; - break; - default: - rxrpc_free_skb(skb, rxrpc_skb_put_input); - continue; - } + if (rxrpc_extract_addr_from_skb(&srx, skb) == 0) { + msg.msg_namelen = srx.transport_len; - if (rxrpc_extract_addr_from_skb(&srx, skb) == 0) { - msg.msg_namelen = srx.transport_len; - - whdr.epoch = htonl(sp->hdr.epoch); - whdr.cid = htonl(sp->hdr.cid); - whdr.callNumber = htonl(sp->hdr.callNumber); - whdr.serviceId = htons(sp->hdr.serviceId); - whdr.flags = sp->hdr.flags; - whdr.flags ^= RXRPC_CLIENT_INITIATED; - whdr.flags &= RXRPC_CLIENT_INITIATED; - - iov_iter_kvec(&msg.msg_iter, WRITE, iov, ioc, size); - ret = do_udp_sendmsg(local->socket, &msg, size); - if (ret < 0) - trace_rxrpc_tx_fail(local->debug_id, 0, ret, - rxrpc_tx_point_reject); - else - trace_rxrpc_tx_packet(local->debug_id, &whdr, - rxrpc_tx_point_reject); - } + whdr.epoch = htonl(sp->hdr.epoch); + whdr.cid = htonl(sp->hdr.cid); + whdr.callNumber = htonl(sp->hdr.callNumber); + whdr.serviceId = htons(sp->hdr.serviceId); + whdr.flags = sp->hdr.flags; + whdr.flags ^= RXRPC_CLIENT_INITIATED; + whdr.flags &= RXRPC_CLIENT_INITIATED; - rxrpc_free_skb(skb, rxrpc_skb_put_input); + iov_iter_kvec(&msg.msg_iter, WRITE, iov, ioc, size); + ret = do_udp_sendmsg(local->socket, &msg, size); + if (ret < 0) + trace_rxrpc_tx_fail(local->debug_id, 0, ret, + rxrpc_tx_point_reject); + else + trace_rxrpc_tx_packet(local->debug_id, &whdr, + rxrpc_tx_point_reject); } - - _leave(""); } /* diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index 97d017ca3dc4..fb8096e93d2c 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -18,9 +18,9 @@ #include #include "ar-internal.h" -static void rxrpc_store_error(struct rxrpc_peer *, struct sock_exterr_skb *); -static void rxrpc_distribute_error(struct rxrpc_peer *, int, - enum rxrpc_call_completion); +static void rxrpc_store_error(struct rxrpc_peer *, struct sk_buff *); +static void rxrpc_distribute_error(struct rxrpc_peer *, struct sk_buff *, + enum rxrpc_call_completion, int); /* * Find the peer associated with a local error. @@ -161,7 +161,7 @@ void rxrpc_input_error(struct rxrpc_local *local, struct sk_buff *skb) goto out; } - rxrpc_store_error(peer, serr); + rxrpc_store_error(peer, skb); out: rxrpc_put_peer(peer, rxrpc_peer_put_input_error); } @@ -169,19 +169,15 @@ out: /* * Map an error report to error codes on the peer record. */ -static void rxrpc_store_error(struct rxrpc_peer *peer, - struct sock_exterr_skb *serr) +static void rxrpc_store_error(struct rxrpc_peer *peer, struct sk_buff *skb) { enum rxrpc_call_completion compl = RXRPC_CALL_NETWORK_ERROR; - struct sock_extended_err *ee; - int err; + struct sock_exterr_skb *serr = SKB_EXT_ERR(skb); + struct sock_extended_err *ee = &serr->ee; + int err = ee->ee_errno; _enter(""); - ee = &serr->ee; - - err = ee->ee_errno; - switch (ee->ee_origin) { case SO_EE_ORIGIN_NONE: case SO_EE_ORIGIN_LOCAL: @@ -197,14 +193,14 @@ static void rxrpc_store_error(struct rxrpc_peer *peer, break; } - rxrpc_distribute_error(peer, err, compl); + rxrpc_distribute_error(peer, skb, compl, err); } /* * Distribute an error that occurred on a peer. */ -static void rxrpc_distribute_error(struct rxrpc_peer *peer, int error, - enum rxrpc_call_completion compl) +static void rxrpc_distribute_error(struct rxrpc_peer *peer, struct sk_buff *skb, + enum rxrpc_call_completion compl, int err) { struct rxrpc_call *call; HLIST_HEAD(error_targets); @@ -219,7 +215,8 @@ static void rxrpc_distribute_error(struct rxrpc_peer *peer, int error, spin_unlock(&peer->lock); rxrpc_see_call(call, rxrpc_call_see_distribute_error); - rxrpc_set_call_completion(call, compl, 0, -error); + rxrpc_set_call_completion(call, compl, 0, -err); + rxrpc_input_call_event(call, skb); spin_lock(&peer->lock); } diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 5df7f468abed..77d03b9e4c4c 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -253,11 +253,8 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) acked = atomic_add_return(call->rx_consumed - old_consumed, &call->ackr_nr_consumed); if (acked > 2 && - !test_and_set_bit(RXRPC_CALL_IDLE_ACK_PENDING, &call->flags)) { - rxrpc_send_ACK(call, RXRPC_ACK_IDLE, serial, - rxrpc_propose_ack_rotate_rx); - rxrpc_transmit_ack_packets(call->peer->local); - } + !test_and_set_bit(RXRPC_CALL_RX_IS_IDLE, &call->flags)) + rxrpc_poke_call(call, rxrpc_call_poke_idle); } /* @@ -377,7 +374,7 @@ done: trace_rxrpc_recvdata(call, rxrpc_recvmsg_data_return, seq, rx_pkt_offset, rx_pkt_len, ret); if (ret == -EAGAIN) - set_bit(RXRPC_CALL_RX_UNDERRUN, &call->flags); + set_bit(RXRPC_CALL_RX_IS_IDLE, &call->flags); return ret; } diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 11af37275d5b..58e0a36f6aa9 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -170,7 +170,7 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, { unsigned long now; rxrpc_seq_t seq = txb->seq; - bool last = test_bit(RXRPC_TXBUF_LAST, &txb->flags); + bool last = test_bit(RXRPC_TXBUF_LAST, &txb->flags), poke; rxrpc_inc_stat(call->rxnet, stat_tx_data); @@ -188,6 +188,7 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, /* Add the packet to the call's output buffer */ spin_lock(&call->tx_lock); + poke = list_empty(&call->tx_sendmsg); list_add_tail(&txb->call_link, &call->tx_sendmsg); call->tx_prepared = seq; spin_unlock(&call->tx_lock); @@ -220,11 +221,8 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, write_unlock_bh(&call->state_lock); } - - /* Stick the packet on the crypto queue or the transmission queue as - * appropriate. - */ - rxrpc_queue_call(call, rxrpc_call_queue_tx_data); + if (poke) + rxrpc_poke_call(call, rxrpc_call_poke_start); } /* -- cgit v1.2.3 From 32cf8edb079a6a687a2b5dba39a813a0bbd0ddf9 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 11 Nov 2022 13:47:35 +0000 Subject: rxrpc: Trace/count transmission underflows and cwnd resets Add a tracepoint to log when a cwnd reset occurs due to lack of transmission on a call. Add stat counters to count transmission underflows (ie. when we have tx window space, but sendmsg doesn't manage to keep up), cwnd resets and transmission failures. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 38 ++++++++++++++++++++++++++++++++++++++ net/rxrpc/ar-internal.h | 3 +++ net/rxrpc/call_event.c | 4 +++- net/rxrpc/input.c | 7 +++++-- net/rxrpc/output.c | 2 ++ net/rxrpc/proc.c | 14 ++++++++++---- 6 files changed, 61 insertions(+), 7 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index c49b0c233594..b41e913ae78a 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -1446,6 +1446,44 @@ TRACE_EVENT(rxrpc_congest, __entry->sum.retrans_timeo ? " rTxTo" : "") ); +TRACE_EVENT(rxrpc_reset_cwnd, + TP_PROTO(struct rxrpc_call *call, ktime_t now), + + TP_ARGS(call, now), + + TP_STRUCT__entry( + __field(unsigned int, call ) + __field(enum rxrpc_congest_mode, mode ) + __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(bool, has_data ) + ), + + TP_fast_assign( + __entry->call = call->debug_id; + __entry->mode = call->cong_mode; + __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); + ), + + TP_printk("c=%08x q=%08x %s cw=%u+%u pr=%u tm=%llu d=%u", + __entry->call, + __entry->hard_ack, + __print_symbolic(__entry->mode, rxrpc_congest_modes), + __entry->cwnd, + __entry->extra, + __entry->prepared, + ktime_to_ns(__entry->since_last_tx), + __entry->has_data) + ); + TRACE_EVENT(rxrpc_disconnect_call, TP_PROTO(struct rxrpc_call *call), diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 6b993a3d4186..6cfe366ee224 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -101,6 +101,9 @@ struct rxrpc_net { atomic_t stat_tx_data_retrans; atomic_t stat_tx_data_send; atomic_t stat_tx_data_send_frag; + atomic_t stat_tx_data_send_fail; + atomic_t stat_tx_data_underflow; + atomic_t stat_tx_data_cwnd_reset; atomic_t stat_rx_data; atomic_t stat_rx_data_reqack; atomic_t stat_rx_data_jumbo; diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 18591f9ecc6a..9f1e490ab976 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -317,8 +317,10 @@ static void rxrpc_transmit_some_data(struct rxrpc_call *call) case RXRPC_CALL_CLIENT_AWAIT_REPLY: if (!rxrpc_tx_window_has_space(call)) return; - if (list_empty(&call->tx_sendmsg)) + if (list_empty(&call->tx_sendmsg)) { + rxrpc_inc_stat(call->rxnet, stat_tx_data_underflow); return; + } rxrpc_decant_prepared_tx(call); break; default: diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index dd2ac5d55e1c..2988e3d0c1f6 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -27,6 +27,7 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, enum rxrpc_congest_change change = rxrpc_cong_no_change; unsigned int cumulative_acks = call->cong_cumul_acks; unsigned int cwnd = call->cong_cwnd; + ktime_t now; bool resend = false; summary->flight_size = @@ -59,13 +60,15 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, /* If we haven't transmitted anything for >1RTT, we should reset the * congestion management state. */ + now = ktime_get_real(); if ((call->cong_mode == RXRPC_CALL_SLOW_START || call->cong_mode == RXRPC_CALL_CONGEST_AVOIDANCE) && ktime_before(ktime_add_us(call->tx_last_sent, - call->peer->srtt_us >> 3), - ktime_get_real()) + call->peer->srtt_us >> 3), now) ) { + trace_rxrpc_reset_cwnd(call, now); change = rxrpc_cong_idle_reset; + rxrpc_inc_stat(call->rxnet, stat_tx_data_cwnd_reset); summary->mode = RXRPC_CALL_SLOW_START; if (RXRPC_TX_SMSS > 2190) summary->cwnd = 2; diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index e5d715b855fc..8147a47d1702 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -485,6 +485,7 @@ dont_set_request_ack: up_read(&conn->local->defrag_sem); if (ret < 0) { + rxrpc_inc_stat(call->rxnet, stat_tx_data_send_fail); rxrpc_cancel_rtt_probe(call, serial, rtt_slot); trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_data_nofrag); @@ -567,6 +568,7 @@ send_fragmentable: } if (ret < 0) { + rxrpc_inc_stat(call->rxnet, stat_tx_data_send_fail); rxrpc_cancel_rtt_probe(call, serial, rtt_slot); trace_rxrpc_tx_fail(call->debug_id, serial, ret, rxrpc_tx_point_call_data_frag); diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index 5af7c8ee4b1a..6816934cb4cf 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -398,13 +398,16 @@ int rxrpc_stats_show(struct seq_file *seq, void *v) struct rxrpc_net *rxnet = rxrpc_net(seq_file_single_net(seq)); seq_printf(seq, - "Data : send=%u sendf=%u\n", + "Data : send=%u sendf=%u fail=%u\n", atomic_read(&rxnet->stat_tx_data_send), - atomic_read(&rxnet->stat_tx_data_send_frag)); + atomic_read(&rxnet->stat_tx_data_send_frag), + atomic_read(&rxnet->stat_tx_data_send_fail)); seq_printf(seq, - "Data-Tx : nr=%u retrans=%u\n", + "Data-Tx : nr=%u retrans=%u uf=%u cwr=%u\n", atomic_read(&rxnet->stat_tx_data), - atomic_read(&rxnet->stat_tx_data_retrans)); + atomic_read(&rxnet->stat_tx_data_retrans), + atomic_read(&rxnet->stat_tx_data_underflow), + atomic_read(&rxnet->stat_tx_data_cwnd_reset)); seq_printf(seq, "Data-Rx : nr=%u reqack=%u jumbo=%u\n", atomic_read(&rxnet->stat_rx_data), @@ -472,8 +475,11 @@ int rxrpc_stats_clear(struct file *file, char *buf, size_t size) atomic_set(&rxnet->stat_tx_data, 0); atomic_set(&rxnet->stat_tx_data_retrans, 0); + atomic_set(&rxnet->stat_tx_data_underflow, 0); + atomic_set(&rxnet->stat_tx_data_cwnd_reset, 0); atomic_set(&rxnet->stat_tx_data_send, 0); atomic_set(&rxnet->stat_tx_data_send_frag, 0); + atomic_set(&rxnet->stat_tx_data_send_fail, 0); atomic_set(&rxnet->stat_rx_data, 0); atomic_set(&rxnet->stat_rx_data_reqack, 0); atomic_set(&rxnet->stat_rx_data_jumbo, 0); -- cgit v1.2.3 From b0346843b1076b34a0278ff601f8f287535cb064 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 30 Jan 2020 21:48:13 +0000 Subject: rxrpc: Transmit ACKs at the point of generation For ACKs generated inside the I/O thread, transmit the ACK at the point of generation. Where the ACK is generated outside of the I/O thread, it's offloaded to the I/O thread to transmit it. Signed-off-by: David Howells cc: Marc Dionne cc: linux-afs@lists.infradead.org --- include/trace/events/rxrpc.h | 3 --- net/rxrpc/ar-internal.h | 5 +---- net/rxrpc/call_event.c | 17 ++--------------- net/rxrpc/io_thread.c | 5 ----- net/rxrpc/local_object.c | 2 -- net/rxrpc/output.c | 42 ++---------------------------------------- net/rxrpc/recvmsg.c | 3 --- net/rxrpc/sendmsg.c | 2 -- net/rxrpc/txbuf.c | 1 - 9 files changed, 5 insertions(+), 75 deletions(-) (limited to 'include/trace') diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index b41e913ae78a..049b52e7aa6a 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -63,7 +63,6 @@ EM(rxrpc_local_put_peer, "PUT peer ") \ EM(rxrpc_local_put_prealloc_conn, "PUT conn-pre") \ EM(rxrpc_local_put_release_sock, "PUT rel-sock") \ - EM(rxrpc_local_see_tx_ack, "SEE tx-ack ") \ EM(rxrpc_local_stop, "STOP ") \ EM(rxrpc_local_stopped, "STOPPED ") \ EM(rxrpc_local_unuse_bind, "UNU bind ") \ @@ -156,7 +155,6 @@ EM(rxrpc_call_get_recvmsg, "GET recvmsg ") \ EM(rxrpc_call_get_release_sock, "GET rel-sock") \ EM(rxrpc_call_get_sendmsg, "GET sendmsg ") \ - EM(rxrpc_call_get_send_ack, "GET send-ack") \ EM(rxrpc_call_get_userid, "GET user-id ") \ EM(rxrpc_call_new_client, "NEW client ") \ EM(rxrpc_call_new_prealloc_service, "NEW prealloc") \ @@ -168,7 +166,6 @@ EM(rxrpc_call_put_recvmsg, "PUT recvmsg ") \ EM(rxrpc_call_put_release_sock, "PUT rls-sock") \ EM(rxrpc_call_put_release_sock_tba, "PUT rls-sk-a") \ - EM(rxrpc_call_put_send_ack, "PUT send-ack") \ EM(rxrpc_call_put_sendmsg, "PUT sendmsg ") \ EM(rxrpc_call_put_unnotify, "PUT unnotify") \ EM(rxrpc_call_put_userid_exists, "PUT u-exists") \ diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 2a4928249a64..e7dccab7b741 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -287,8 +287,6 @@ struct rxrpc_local { struct hlist_node link; struct socket *socket; /* my UDP socket */ struct task_struct *io_thread; - struct list_head ack_tx_queue; /* List of ACKs that need sending */ - spinlock_t ack_tx_lock; /* ACK list lock */ struct rxrpc_sock __rcu *service; /* Service(s) listening on this endpoint */ struct rw_semaphore defrag_sem; /* control re-enablement of IP DF bit */ struct sk_buff_head rx_queue; /* Received packets */ @@ -762,7 +760,6 @@ struct rxrpc_txbuf { struct rcu_head rcu; struct list_head call_link; /* Link in call->tx_sendmsg/tx_buffer */ struct list_head tx_link; /* Link in live Enc queue or Tx queue */ - struct rxrpc_call *call; /* Call to which belongs */ ktime_t last_sent; /* Time at which last transmitted */ refcount_t ref; rxrpc_seq_t seq; /* Sequence number of this packet */ @@ -1047,7 +1044,7 @@ static inline struct rxrpc_net *rxrpc_net(struct net *net) /* * output.c */ -void rxrpc_transmit_ack_packets(struct rxrpc_local *); +int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb); int rxrpc_send_abort_packet(struct rxrpc_call *); int rxrpc_send_data_packet(struct rxrpc_call *, struct rxrpc_txbuf *); void rxrpc_reject_packet(struct rxrpc_local *local, struct sk_buff *skb); diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index fd122e3726bd..b2cf448fb02c 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -69,7 +69,6 @@ void rxrpc_propose_delay_ACK(struct rxrpc_call *call, rxrpc_serial_t serial, void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason, rxrpc_serial_t serial, enum rxrpc_propose_ack_trace why) { - struct rxrpc_local *local = call->conn->local; struct rxrpc_txbuf *txb; if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) @@ -96,17 +95,9 @@ void rxrpc_send_ACK(struct rxrpc_call *call, u8 ack_reason, txb->ack.reason = ack_reason; txb->ack.nAcks = 0; - if (!rxrpc_try_get_call(call, rxrpc_call_get_send_ack)) { - rxrpc_put_txbuf(txb, rxrpc_txbuf_put_nomem); - return; - } - - spin_lock(&local->ack_tx_lock); - list_add_tail(&txb->tx_link, &local->ack_tx_queue); - spin_unlock(&local->ack_tx_lock); trace_rxrpc_send_ack(call, why, ack_reason, serial); - - rxrpc_wake_up_io_thread(local); + rxrpc_send_ack_packet(call, txb); + rxrpc_put_txbuf(txb, rxrpc_txbuf_put_ack_tx); } /* @@ -294,10 +285,6 @@ static void rxrpc_decant_prepared_tx(struct rxrpc_call *call) rxrpc_transmit_one(call, txb); - // TODO: Drain the transmission buffers. Do this somewhere better - if (after(call->acks_hard_ack, call->tx_bottom + 16)) - rxrpc_shrink_call_tx_buffer(call); - if (!rxrpc_tx_window_has_space(call)) break; } diff --git a/net/rxrpc/io_thread.c b/net/rxrpc/io_thread.c index 19aa315eddf5..d83ae3193032 100644 --- a/net/rxrpc/io_thread.c +++ b/net/rxrpc/io_thread.c @@ -447,11 +447,6 @@ int rxrpc_io_thread(void *data) continue; } - if (!list_empty(&local->ack_tx_queue)) { - rxrpc_transmit_ack_packets(local); - continue; - } - /* Process received packets and errors. */ if ((skb = __skb_dequeue(&rx_queue))) { switch (skb->mark) { diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 1e994a83db2b..44222923c0d1 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -96,8 +96,6 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet, atomic_set(&local->active_users, 1); local->rxnet = rxnet; INIT_HLIST_NODE(&local->link); - INIT_LIST_HEAD(&local->ack_tx_queue); - spin_lock_init(&local->ack_tx_lock); init_rwsem(&local->defrag_sem); skb_queue_head_init(&local->rx_queue); INIT_LIST_HEAD(&local->call_attend_q); diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 8147a47d1702..3d8c9f830ee0 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -203,12 +203,11 @@ static void rxrpc_cancel_rtt_probe(struct rxrpc_call *call, } /* - * Send an ACK call packet. + * Transmit an ACK packet. */ -static int rxrpc_send_ack_packet(struct rxrpc_local *local, struct rxrpc_txbuf *txb) +int rxrpc_send_ack_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb) { struct rxrpc_connection *conn; - struct rxrpc_call *call = txb->call; struct msghdr msg; struct kvec iov[1]; rxrpc_serial_t serial; @@ -271,43 +270,6 @@ static int rxrpc_send_ack_packet(struct rxrpc_local *local, struct rxrpc_txbuf * return ret; } -/* - * ACK transmitter for a local endpoint. The UDP socket locks around each - * transmission, so we can only transmit one packet at a time, ACK, DATA or - * otherwise. - */ -void rxrpc_transmit_ack_packets(struct rxrpc_local *local) -{ - LIST_HEAD(queue); - int ret; - - rxrpc_see_local(local, rxrpc_local_see_tx_ack); - - if (list_empty(&local->ack_tx_queue)) - return; - - spin_lock(&local->ack_tx_lock); - list_splice_tail_init(&local->ack_tx_queue, &queue); - spin_unlock(&local->ack_tx_lock); - - while (!list_empty(&queue)) { - struct rxrpc_txbuf *txb = - list_entry(queue.next, struct rxrpc_txbuf, tx_link); - - ret = rxrpc_send_ack_packet(local, txb); - if (ret < 0 && ret != -ECONNRESET) { - spin_lock(&local->ack_tx_lock); - list_splice_init(&queue, &local->ack_tx_queue); - spin_unlock(&local->ack_tx_lock); - break; - } - - list_del_init(&txb->tx_link); - rxrpc_put_call(txb->call, rxrpc_call_put_send_ack); - rxrpc_put_txbuf(txb, rxrpc_txbuf_put_ack_tx); - } -} - /* * Send an ABORT call packet. */ diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 3a8576e9daf3..36b25d003cf0 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -320,7 +320,6 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call, ret = ret2; goto out; } - rxrpc_transmit_ack_packets(call->peer->local); } else { trace_rxrpc_recvdata(call, rxrpc_recvmsg_cont, seq, rx_pkt_offset, rx_pkt_len, 0); @@ -502,7 +501,6 @@ try_again: if (ret == -EAGAIN) ret = 0; - rxrpc_transmit_ack_packets(call->peer->local); if (!skb_queue_empty(&call->recvmsg_queue)) rxrpc_notify_socket(call); break; @@ -632,7 +630,6 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call, read_phase_complete: ret = 1; out: - rxrpc_transmit_ack_packets(call->peer->local); if (_service) *_service = call->dest_srx.srx_service; mutex_unlock(&call->user_mutex); diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 2c861c55ed70..9fa7e37f7155 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -276,8 +276,6 @@ reload: rxrpc_see_txbuf(txb, rxrpc_txbuf_see_send_more); do { - rxrpc_transmit_ack_packets(call->peer->local); - if (!txb) { size_t remain, bufsize, chunk, offset; diff --git a/net/rxrpc/txbuf.c b/net/rxrpc/txbuf.c index a5054389dfbb..d2cf2aac3adb 100644 --- a/net/rxrpc/txbuf.c +++ b/net/rxrpc/txbuf.c @@ -26,7 +26,6 @@ struct rxrpc_txbuf *rxrpc_alloc_txbuf(struct rxrpc_call *call, u8 packet_type, INIT_LIST_HEAD(&txb->call_link); INIT_LIST_HEAD(&txb->tx_link); refcount_set(&txb->ref, 1); - txb->call = call; txb->call_debug_id = call->debug_id; txb->debug_id = atomic_inc_return(&rxrpc_txbuf_debug_ids); txb->space = sizeof(txb->data); -- cgit v1.2.3