From b63452c11e22382e592d3f7f9ac4966197d3eab6 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 6 Oct 2016 08:11:48 +0100 Subject: [PATCH 01/13] rxrpc: Accesses of rxrpc_local::service need to be RCU managed struct rxrpc_local->service is marked __rcu - this means that accesses of it need to be managed using RCU wrappers. There are two such places in rxrpc_release_sock() where the value is checked and cleared. Fix this by using the appropriate wrappers. Signed-off-by: David Howells --- net/rxrpc/af_rxrpc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 44c9c2b0b190..2d59c9be40e1 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -678,9 +678,9 @@ static int rxrpc_release_sock(struct sock *sk) sk->sk_state = RXRPC_CLOSE; spin_unlock_bh(&sk->sk_receive_queue.lock); - if (rx->local && rx->local->service == rx) { + if (rx->local && rcu_access_pointer(rx->local->service) == rx) { write_lock(&rx->local->services_lock); - rx->local->service = NULL; + rcu_assign_pointer(rx->local->service, NULL); write_unlock(&rx->local->services_lock); } From 19c0dbd5406ddc669ef1516c02c6b0f5a4465628 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 6 Oct 2016 08:11:48 +0100 Subject: [PATCH 02/13] rxrpc: Fix duplicate const Remove a duplicate const keyword. Signed-off-by: David Howells --- net/rxrpc/ar-internal.h | 2 +- net/rxrpc/misc.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index d38dffd78085..4954e6e25819 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -777,7 +777,7 @@ extern const char rxrpc_congest_modes[NR__RXRPC_CONGEST_MODES][10]; extern const char rxrpc_congest_changes[rxrpc_congest__nr_change][9]; extern const char *const rxrpc_pkts[]; -extern const char const rxrpc_ack_names[RXRPC_ACK__INVALID + 1][4]; +extern const char rxrpc_ack_names[RXRPC_ACK__INVALID + 1][4]; #include diff --git a/net/rxrpc/misc.c b/net/rxrpc/misc.c index 9d1c721bc4e8..804a88e28739 100644 --- a/net/rxrpc/misc.c +++ b/net/rxrpc/misc.c @@ -96,7 +96,7 @@ const s8 rxrpc_ack_priority[] = { [RXRPC_ACK_PING] = 9, }; -const char const rxrpc_ack_names[RXRPC_ACK__INVALID + 1][4] = { +const char rxrpc_ack_names[RXRPC_ACK__INVALID + 1][4] = { "---", "REQ", "DUP", "OOS", "WIN", "MEM", "PNG", "PNR", "DLY", "IDL", "-?-" }; From 7212a57e8eaa2572481398532d7be0c2685362b9 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 6 Oct 2016 08:11:49 +0100 Subject: [PATCH 03/13] rxrpc: Fix oops on incoming call to serviceless endpoint If an call comes in to a local endpoint that isn't listening for any incoming calls at the moment, an oops will happen. We need to check that the local endpoint's service pointer isn't NULL before we dereference it. Signed-off-by: David Howells --- net/rxrpc/call_accept.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 3cac231d8405..22cd8a18c481 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -337,7 +337,7 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, /* Get the socket providing the service */ rx = rcu_dereference(local->service); - if (service_id == rx->srx.srx_service) + if (rx && service_id == rx->srx.srx_service) goto found_service; trace_rxrpc_abort("INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, From a9f312d98affab387557e2795d4e11ad82a4e4e8 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 6 Oct 2016 08:11:49 +0100 Subject: [PATCH 04/13] rxrpc: Only ping for lost reply in client call When a reply is deemed lost, we send a ping to find out the other end received all the request data packets we sent. This should be limited to client calls and we shouldn't do this on service calls. Signed-off-by: David Howells --- net/rxrpc/input.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 3ad9f75031e3..103d2b0d4690 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -847,7 +847,8 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb, if (call->rxtx_annotations[call->tx_top & RXRPC_RXTX_BUFF_MASK] & RXRPC_TX_ANNO_LAST && - summary.nr_acks == call->tx_top - hard_ack) + summary.nr_acks == call->tx_top - hard_ack && + rxrpc_is_client_call(call)) rxrpc_propose_ACK(call, RXRPC_ACK_PING, skew, sp->hdr.serial, false, true, rxrpc_propose_ack_ping_for_lost_reply); From 26cb02aa6d3efeb543805ed9ad599dae24f7c6d4 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 6 Oct 2016 08:11:49 +0100 Subject: [PATCH 05/13] rxrpc: Fix warning by splitting rxrpc_send_call_packet() Split rxrpc_send_data_packet() to separate ACK generation (which is more complicated) from ABORT generation. This simplifies the code a bit and fixes the following warning: In file included from ../net/rxrpc/output.c:20:0: net/rxrpc/output.c: In function 'rxrpc_send_call_packet': net/rxrpc/ar-internal.h:1187:27: error: 'top' may be used uninitialized in this function [-Werror=maybe-uninitialized] net/rxrpc/output.c:103:24: note: 'top' was declared here net/rxrpc/output.c:225:25: error: 'hard_ack' may be used uninitialized in this function [-Werror=maybe-uninitialized] Reported-by: Arnd Bergmann Signed-off-by: David Howells --- net/rxrpc/ar-internal.h | 3 +- net/rxrpc/call_accept.c | 2 +- net/rxrpc/call_event.c | 6 +- net/rxrpc/call_object.c | 2 +- net/rxrpc/output.c | 156 ++++++++++++++++++++++------------------ net/rxrpc/recvmsg.c | 4 +- net/rxrpc/rxkad.c | 6 +- net/rxrpc/sendmsg.c | 7 +- 8 files changed, 102 insertions(+), 84 deletions(-) diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 4954e6e25819..ef849a12a0f0 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -1068,7 +1068,8 @@ extern const s8 rxrpc_ack_priority[]; /* * output.c */ -int rxrpc_send_call_packet(struct rxrpc_call *, u8); +int rxrpc_send_ack_packet(struct rxrpc_call *); +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 22cd8a18c481..832d854c2d5c 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -565,7 +565,7 @@ out_discard: write_unlock_bh(&call->state_lock); write_unlock(&rx->call_lock); if (abort) { - rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ABORT); + rxrpc_send_abort_packet(call); rxrpc_release_call(rx, call); rxrpc_put_call(call, rxrpc_call_put); } diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 4f00476630b9..e313099860d5 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -253,7 +253,7 @@ static void rxrpc_resend(struct rxrpc_call *call, ktime_t now) goto out; rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, false, rxrpc_propose_ack_ping_for_lost_ack); - rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ACK); + rxrpc_send_ack_packet(call); goto out; } @@ -328,7 +328,7 @@ void rxrpc_process_call(struct work_struct *work) recheck_state: if (test_and_clear_bit(RXRPC_CALL_EV_ABORT, &call->events)) { - rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ABORT); + rxrpc_send_abort_packet(call); goto recheck_state; } @@ -347,7 +347,7 @@ recheck_state: if (test_and_clear_bit(RXRPC_CALL_EV_ACK, &call->events)) { call->ack_at = call->expire_at; if (call->ackr_reason) { - rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ACK); + rxrpc_send_ack_packet(call); goto recheck_state; } } diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 364b42dc3dce..07094012ac15 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -498,7 +498,7 @@ void rxrpc_release_calls_on_socket(struct rxrpc_sock *rx) struct rxrpc_call, sock_link); rxrpc_get_call(call, rxrpc_call_got); rxrpc_abort_call("SKT", call, 0, RX_CALL_DEAD, ECONNRESET); - rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ABORT); + rxrpc_send_abort_packet(call); rxrpc_release_call(rx, call); rxrpc_put_call(call, rxrpc_call_put); } diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 0d47db886f6e..2dae877c0876 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -19,24 +19,24 @@ #include #include "ar-internal.h" -struct rxrpc_pkt_buffer { +struct rxrpc_ack_buffer { struct rxrpc_wire_header whdr; - union { - struct { - struct rxrpc_ackpacket ack; - u8 acks[255]; - u8 pad[3]; - }; - __be32 abort_code; - }; + struct rxrpc_ackpacket ack; + u8 acks[255]; + u8 pad[3]; struct rxrpc_ackinfo ackinfo; }; +struct rxrpc_abort_buffer { + struct rxrpc_wire_header whdr; + __be32 abort_code; +}; + /* * Fill out an ACK packet. */ static size_t rxrpc_fill_out_ack(struct rxrpc_call *call, - struct rxrpc_pkt_buffer *pkt, + struct rxrpc_ack_buffer *pkt, rxrpc_seq_t *_hard_ack, rxrpc_seq_t *_top) { @@ -91,22 +91,19 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_call *call, } /* - * Send an ACK or ABORT call packet. + * Send an ACK call packet. */ -int rxrpc_send_call_packet(struct rxrpc_call *call, u8 type) +int rxrpc_send_ack_packet(struct rxrpc_call *call) { struct rxrpc_connection *conn = NULL; - struct rxrpc_pkt_buffer *pkt; + struct rxrpc_ack_buffer *pkt; struct msghdr msg; struct kvec iov[2]; rxrpc_serial_t serial; rxrpc_seq_t hard_ack, top; size_t len, n; bool ping = false; - int ioc, ret; - u32 abort_code; - - _enter("%u,%s", call->debug_id, rxrpc_pkts[type]); + int ret; spin_lock_bh(&call->lock); if (call->conn) @@ -131,65 +128,37 @@ int rxrpc_send_call_packet(struct rxrpc_call *call, u8 type) pkt->whdr.cid = htonl(call->cid); pkt->whdr.callNumber = htonl(call->call_id); pkt->whdr.seq = 0; - pkt->whdr.type = type; - pkt->whdr.flags = conn->out_clientflag; + 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); - iov[0].iov_base = pkt; - iov[0].iov_len = sizeof(pkt->whdr); - len = sizeof(pkt->whdr); - - switch (type) { - case RXRPC_PACKET_TYPE_ACK: - spin_lock_bh(&call->lock); - if (!call->ackr_reason) { - spin_unlock_bh(&call->lock); - ret = 0; - goto out; - } - ping = (call->ackr_reason == RXRPC_ACK_PING); - n = rxrpc_fill_out_ack(call, pkt, &hard_ack, &top); - call->ackr_reason = 0; - + spin_lock_bh(&call->lock); + if (!call->ackr_reason) { spin_unlock_bh(&call->lock); - - - pkt->whdr.flags |= RXRPC_SLOW_START_OK; - - iov[0].iov_len += sizeof(pkt->ack) + n; - iov[1].iov_base = &pkt->ackinfo; - iov[1].iov_len = sizeof(pkt->ackinfo); - len += sizeof(pkt->ack) + n + sizeof(pkt->ackinfo); - ioc = 2; - break; - - case RXRPC_PACKET_TYPE_ABORT: - abort_code = call->abort_code; - pkt->abort_code = htonl(abort_code); - iov[0].iov_len += sizeof(pkt->abort_code); - len += sizeof(pkt->abort_code); - ioc = 1; - break; - - default: - BUG(); - ret = -ENOANO; + ret = 0; goto out; } + ping = (call->ackr_reason == RXRPC_ACK_PING); + n = rxrpc_fill_out_ack(call, pkt, &hard_ack, &top); + call->ackr_reason = 0; + + spin_unlock_bh(&call->lock); + + 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; serial = atomic_inc_return(&conn->serial); pkt->whdr.serial = htonl(serial); - switch (type) { - case RXRPC_PACKET_TYPE_ACK: - trace_rxrpc_tx_ack(call, serial, - ntohl(pkt->ack.firstPacket), - ntohl(pkt->ack.serial), - pkt->ack.reason, pkt->ack.nAcks); - break; - } + trace_rxrpc_tx_ack(call, serial, + ntohl(pkt->ack.firstPacket), + ntohl(pkt->ack.serial), + pkt->ack.reason, pkt->ack.nAcks); if (ping) { call->ackr_ping = serial; @@ -205,13 +174,12 @@ int rxrpc_send_call_packet(struct rxrpc_call *call, u8 type) set_bit(RXRPC_CALL_PINGING, &call->flags); trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_ping, serial); } - ret = kernel_sendmsg(conn->params.local->socket, - &msg, iov, ioc, len); + + ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); if (ping) call->ackr_ping_time = ktime_get_real(); - if (type == RXRPC_PACKET_TYPE_ACK && - call->state < RXRPC_CALL_COMPLETE) { + if (call->state < RXRPC_CALL_COMPLETE) { if (ret < 0) { clear_bit(RXRPC_CALL_PINGING, &call->flags); rxrpc_propose_ACK(call, pkt->ack.reason, @@ -235,6 +203,56 @@ out: return ret; } +/* + * Send an ABORT call packet. + */ +int rxrpc_send_abort_packet(struct rxrpc_call *call) +{ + struct rxrpc_connection *conn = NULL; + struct rxrpc_abort_buffer pkt; + struct msghdr msg; + struct kvec iov[1]; + rxrpc_serial_t serial; + int ret; + + spin_lock_bh(&call->lock); + if (call->conn) + conn = rxrpc_get_connection_maybe(call->conn); + spin_unlock_bh(&call->lock); + if (!conn) + return -ECONNRESET; + + msg.msg_name = &call->peer->srx.transport; + msg.msg_namelen = call->peer->srx.transport_len; + msg.msg_control = NULL; + 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_ABORT; + pkt.whdr.flags = conn->out_clientflag; + pkt.whdr.userStatus = 0; + pkt.whdr.securityIndex = call->security_ix; + pkt.whdr._rsvd = 0; + pkt.whdr.serviceId = htons(call->service_id); + pkt.abort_code = htonl(call->abort_code); + + iov[0].iov_base = &pkt; + iov[0].iov_len = sizeof(pkt); + + serial = atomic_inc_return(&conn->serial); + pkt.whdr.serial = htonl(serial); + + ret = kernel_sendmsg(conn->params.local->socket, + &msg, iov, 1, sizeof(pkt)); + + rxrpc_put_connection(conn); + return ret; +} + /* * send a packet through the transport endpoint */ diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index f05ea0a88076..11723bc1c783 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -143,7 +143,7 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY) { rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, 0, serial, true, false, rxrpc_propose_ack_terminal_ack); - rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ACK); + rxrpc_send_ack_packet(call); } write_lock_bh(&call->state_lock); @@ -212,7 +212,7 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) true, false, rxrpc_propose_ack_rotate_rx); if (call->ackr_reason) - rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ACK); + rxrpc_send_ack_packet(call); } } diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index 627abed5f999..4374e7b9c7bf 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -381,7 +381,7 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb, return 0; protocol_error: - rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ABORT); + rxrpc_send_abort_packet(call); _leave(" = -EPROTO"); return -EPROTO; @@ -471,7 +471,7 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb, return 0; protocol_error: - rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ABORT); + rxrpc_send_abort_packet(call); _leave(" = -EPROTO"); return -EPROTO; @@ -523,7 +523,7 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb, if (cksum != expected_cksum) { rxrpc_abort_call("VCK", call, seq, RXKADSEALEDINCON, EPROTO); - rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ABORT); + rxrpc_send_abort_packet(call); _leave(" = -EPROTO [csum failed]"); return -EPROTO; } diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 3322543d460a..901b28ceeff4 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -197,7 +197,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, do { /* Check to see if there's a ping ACK to reply to. */ if (call->ackr_reason == RXRPC_ACK_PING_RESPONSE) - rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ACK); + rxrpc_send_ack_packet(call); if (!skb) { size_t size, chunk, max, space; @@ -514,8 +514,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) } else if (cmd == RXRPC_CMD_SEND_ABORT) { ret = 0; if (rxrpc_abort_call("CMD", call, 0, abort_code, ECONNABORTED)) - ret = rxrpc_send_call_packet(call, - RXRPC_PACKET_TYPE_ABORT); + ret = rxrpc_send_abort_packet(call); } else if (cmd != RXRPC_CMD_SEND_DATA) { ret = -EINVAL; } else if (rxrpc_is_client_call(call) && @@ -597,7 +596,7 @@ void rxrpc_kernel_abort_call(struct socket *sock, struct rxrpc_call *call, lock_sock(sock->sk); if (rxrpc_abort_call(why, call, 0, abort_code, error)) - rxrpc_send_call_packet(call, RXRPC_PACKET_TYPE_ABORT); + rxrpc_send_abort_packet(call); release_sock(sock->sk); _leave(""); From a5af7e1fc69a46f29b977fd4b570e0ac414c2338 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 6 Oct 2016 08:11:49 +0100 Subject: [PATCH 06/13] rxrpc: Fix loss of PING RESPONSE ACK production due to PING ACKs Separate the output of PING ACKs from the output of other sorts of ACK so that if we receive a PING ACK and schedule transmission of a PING RESPONSE ACK, the response doesn't get cancelled by a PING ACK we happen to be scheduling transmission of at the same time. If a PING RESPONSE gets lost, the other side might just sit there waiting for it and refuse to proceed otherwise. Signed-off-by: David Howells --- net/rxrpc/ar-internal.h | 12 ++++++++--- net/rxrpc/call_event.c | 48 +++++++++++++++++++++++++++++++++++++---- net/rxrpc/call_object.c | 1 + net/rxrpc/input.c | 4 ++-- net/rxrpc/misc.c | 2 +- net/rxrpc/output.c | 38 ++++++++++++++++++-------------- net/rxrpc/recvmsg.c | 4 ++-- net/rxrpc/sendmsg.c | 2 +- 8 files changed, 82 insertions(+), 29 deletions(-) diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index ef849a12a0f0..b56676be07c7 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -398,6 +398,7 @@ 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_SEND_PING, /* A ping will need to be sent */ RXRPC_CALL_PINGING, /* Ping in process */ RXRPC_CALL_RETRANS_TIMEOUT, /* Retransmission due to timeout occurred */ }; @@ -410,6 +411,7 @@ enum rxrpc_call_event { RXRPC_CALL_EV_ABORT, /* need to generate abort */ RXRPC_CALL_EV_TIMER, /* Timer expired */ RXRPC_CALL_EV_RESEND, /* Tx resend required */ + RXRPC_CALL_EV_PING, /* Ping send required */ }; /* @@ -466,6 +468,7 @@ struct rxrpc_call { struct rxrpc_sock __rcu *socket; /* socket responsible */ ktime_t ack_at; /* When deferred ACK needs to happen */ ktime_t resend_at; /* When next resend needs to happen */ + ktime_t ping_at; /* When next to send a ping */ ktime_t expire_at; /* When the call times out */ struct timer_list timer; /* Combined event timer */ struct work_struct processor; /* Event processor */ @@ -558,8 +561,10 @@ struct rxrpc_call { rxrpc_seq_t ackr_prev_seq; /* previous sequence number received */ rxrpc_seq_t ackr_consumed; /* Highest packet shown consumed */ rxrpc_seq_t ackr_seen; /* Highest packet shown seen */ - rxrpc_serial_t ackr_ping; /* Last ping sent */ - ktime_t ackr_ping_time; /* Time last ping sent */ + + /* ping management */ + rxrpc_serial_t ping_serial; /* Last ping sent */ + ktime_t ping_time; /* Time last ping sent */ /* transmission-phase ACK management */ ktime_t acks_latest_ts; /* Timestamp of latest ACK received */ @@ -730,6 +735,7 @@ enum rxrpc_timer_trace { rxrpc_timer_init_for_reply, rxrpc_timer_expired, rxrpc_timer_set_for_ack, + rxrpc_timer_set_for_ping, rxrpc_timer_set_for_resend, rxrpc_timer_set_for_send, rxrpc_timer__nr_trace @@ -1068,7 +1074,7 @@ extern const s8 rxrpc_ack_priority[]; /* * output.c */ -int rxrpc_send_ack_packet(struct rxrpc_call *); +int rxrpc_send_ack_packet(struct rxrpc_call *, bool); 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_event.c b/net/rxrpc/call_event.c index e313099860d5..eeea9602cb89 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -54,6 +54,14 @@ void rxrpc_set_timer(struct rxrpc_call *call, enum rxrpc_timer_trace why, t = call->ack_at; } + if (!ktime_after(call->ping_at, now)) { + call->ping_at = call->expire_at; + if (!test_and_set_bit(RXRPC_CALL_EV_PING, &call->events)) + queue = true; + } else if (ktime_before(call->ping_at, t)) { + t = call->ping_at; + } + t_j = nsecs_to_jiffies(ktime_to_ns(ktime_sub(t, now))); t_j += jiffies; @@ -77,6 +85,27 @@ out: read_unlock_bh(&call->state_lock); } +/* + * Propose a PING ACK be sent. + */ +static void rxrpc_propose_ping(struct rxrpc_call *call, + bool immediate, bool background) +{ + if (immediate) { + if (background && + !test_and_set_bit(RXRPC_CALL_EV_PING, &call->events)) + rxrpc_queue_call(call); + } else { + ktime_t now = ktime_get_real(); + ktime_t ping_at = ktime_add_ms(now, rxrpc_idle_ack_delay); + + if (ktime_before(ping_at, call->ping_at)) { + call->ping_at = ping_at; + rxrpc_set_timer(call, rxrpc_timer_set_for_ping, now); + } + } +} + /* * propose an ACK be sent */ @@ -90,6 +119,14 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, ktime_t now, ack_at; s8 prior = rxrpc_ack_priority[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. */ @@ -125,7 +162,6 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, expiry = rxrpc_soft_ack_delay; break; - case RXRPC_ACK_PING: case RXRPC_ACK_IDLE: if (rxrpc_idle_ack_delay < expiry) expiry = rxrpc_idle_ack_delay; @@ -253,7 +289,7 @@ static void rxrpc_resend(struct rxrpc_call *call, ktime_t now) goto out; rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, false, rxrpc_propose_ack_ping_for_lost_ack); - rxrpc_send_ack_packet(call); + rxrpc_send_ack_packet(call, true); goto out; } @@ -345,13 +381,17 @@ recheck_state: } if (test_and_clear_bit(RXRPC_CALL_EV_ACK, &call->events)) { - call->ack_at = call->expire_at; if (call->ackr_reason) { - rxrpc_send_ack_packet(call); + rxrpc_send_ack_packet(call, false); goto recheck_state; } } + if (test_and_clear_bit(RXRPC_CALL_EV_PING, &call->events)) { + rxrpc_send_ack_packet(call, true); + goto recheck_state; + } + if (test_and_clear_bit(RXRPC_CALL_EV_RESEND, &call->events)) { rxrpc_resend(call, now); goto recheck_state; diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 07094012ac15..4353a29f3b57 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -205,6 +205,7 @@ static void rxrpc_start_call_timer(struct rxrpc_call *call) expire_at = ktime_add_ms(now, rxrpc_max_call_lifetime); call->expire_at = expire_at; call->ack_at = expire_at; + call->ping_at = expire_at; call->resend_at = expire_at; call->timer.expires = jiffies + LONG_MAX / 2; rxrpc_set_timer(call, rxrpc_timer_begin, now); diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 103d2b0d4690..a6da83f036d6 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -625,9 +625,9 @@ static void rxrpc_input_ping_response(struct rxrpc_call *call, rxrpc_serial_t ping_serial; ktime_t ping_time; - ping_time = call->ackr_ping_time; + ping_time = call->ping_time; smp_rmb(); - ping_serial = call->ackr_ping; + ping_serial = call->ping_serial; if (!test_bit(RXRPC_CALL_PINGING, &call->flags) || before(orig_serial, ping_serial)) diff --git a/net/rxrpc/misc.c b/net/rxrpc/misc.c index 804a88e28739..1cdcba52f83b 100644 --- a/net/rxrpc/misc.c +++ b/net/rxrpc/misc.c @@ -93,7 +93,6 @@ const s8 rxrpc_ack_priority[] = { [RXRPC_ACK_EXCEEDS_WINDOW] = 6, [RXRPC_ACK_NOSPACE] = 7, [RXRPC_ACK_PING_RESPONSE] = 8, - [RXRPC_ACK_PING] = 9, }; const char rxrpc_ack_names[RXRPC_ACK__INVALID + 1][4] = { @@ -197,6 +196,7 @@ const char rxrpc_timer_traces[rxrpc_timer__nr_trace][8] = { [rxrpc_timer_expired] = "*EXPR*", [rxrpc_timer_init_for_reply] = "IniRpl", [rxrpc_timer_set_for_ack] = "SetAck", + [rxrpc_timer_set_for_ping] = "SetPng", [rxrpc_timer_set_for_send] = "SetTx ", [rxrpc_timer_set_for_resend] = "SetRTx", }; diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index 2dae877c0876..a12cea0cbc05 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -38,7 +38,8 @@ struct rxrpc_abort_buffer { static size_t rxrpc_fill_out_ack(struct rxrpc_call *call, struct rxrpc_ack_buffer *pkt, rxrpc_seq_t *_hard_ack, - rxrpc_seq_t *_top) + rxrpc_seq_t *_top, + u8 reason) { rxrpc_serial_t serial; rxrpc_seq_t hard_ack, top, seq; @@ -58,10 +59,10 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_call *call, pkt->ack.firstPacket = htonl(hard_ack + 1); pkt->ack.previousPacket = htonl(call->ackr_prev_seq); pkt->ack.serial = htonl(serial); - pkt->ack.reason = call->ackr_reason; + pkt->ack.reason = reason; pkt->ack.nAcks = top - hard_ack; - if (pkt->ack.reason == RXRPC_ACK_PING) + if (reason == RXRPC_ACK_PING) pkt->whdr.flags |= RXRPC_REQUEST_ACK; if (after(top, hard_ack)) { @@ -93,7 +94,7 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_call *call, /* * Send an ACK call packet. */ -int rxrpc_send_ack_packet(struct rxrpc_call *call) +int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping) { struct rxrpc_connection *conn = NULL; struct rxrpc_ack_buffer *pkt; @@ -102,8 +103,8 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call) rxrpc_serial_t serial; rxrpc_seq_t hard_ack, top; size_t len, n; - bool ping = false; int ret; + u8 reason; spin_lock_bh(&call->lock); if (call->conn) @@ -136,14 +137,18 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call) pkt->whdr.serviceId = htons(call->service_id); spin_lock_bh(&call->lock); - if (!call->ackr_reason) { - spin_unlock_bh(&call->lock); - ret = 0; - goto out; + 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; } - ping = (call->ackr_reason == RXRPC_ACK_PING); - n = rxrpc_fill_out_ack(call, pkt, &hard_ack, &top); - call->ackr_reason = 0; + n = rxrpc_fill_out_ack(call, pkt, &hard_ack, &top, reason); spin_unlock_bh(&call->lock); @@ -161,7 +166,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call) pkt->ack.reason, pkt->ack.nAcks); if (ping) { - call->ackr_ping = serial; + call->ping_serial = serial; smp_wmb(); /* We need to stick a time in before we send the packet in case * the reply gets back before kernel_sendmsg() completes - but @@ -170,18 +175,19 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call) * the packet transmission is more likely to happen towards the * end of the kernel_sendmsg() call. */ - call->ackr_ping_time = ktime_get_real(); + call->ping_time = ktime_get_real(); set_bit(RXRPC_CALL_PINGING, &call->flags); trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_ping, serial); } ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len); if (ping) - call->ackr_ping_time = ktime_get_real(); + call->ping_time = ktime_get_real(); if (call->state < RXRPC_CALL_COMPLETE) { if (ret < 0) { - clear_bit(RXRPC_CALL_PINGING, &call->flags); + if (ping) + clear_bit(RXRPC_CALL_PINGING, &call->flags); rxrpc_propose_ACK(call, pkt->ack.reason, ntohs(pkt->ack.maxSkew), ntohl(pkt->ack.serial), diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 11723bc1c783..3fa7771c2a9d 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -143,7 +143,7 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY) { rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, 0, serial, true, false, rxrpc_propose_ack_terminal_ack); - rxrpc_send_ack_packet(call); + rxrpc_send_ack_packet(call, false); } write_lock_bh(&call->state_lock); @@ -212,7 +212,7 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) true, false, rxrpc_propose_ack_rotate_rx); if (call->ackr_reason) - rxrpc_send_ack_packet(call); + rxrpc_send_ack_packet(call, false); } } diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 901b28ceeff4..55a2fb2cfc2f 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -197,7 +197,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, 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); + rxrpc_send_ack_packet(call, false); if (!skb) { size_t size, chunk, max, space; From b3156274ca01297b861e912175820e78c9ac4d7c Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 6 Oct 2016 08:11:49 +0100 Subject: [PATCH 07/13] rxrpc: Partially handle OpenAFS's improper termination of calls OpenAFS doesn't always correctly terminate client calls that it makes - this includes calls the OpenAFS servers make to the cache manager service. It should end the client call with either: (1) An ACK that has firstPacket set to one greater than the seq number of the reply DATA packet with the LAST_PACKET flag set (thereby hard-ACK'ing all packets). nAcks should be 0 and acks[] should be empty (ie. no soft-ACKs). (2) An ACKALL packet. OpenAFS, though, may send an ACK packet with firstPacket set to the last seq number or less and soft-ACKs listed for all packets up to and including the last DATA packet. The transmitter, however, is obliged to keep the call live and the soft-ACK'd DATA packets around until they're hard-ACK'd as the receiver is permitted to drop any merely soft-ACK'd packet and request retransmission by sending an ACK packet with a NACK in it. Further, OpenAFS will also terminate a client call by beginning the next client call on the same connection channel. This implicitly completes the previous call. This patch handles implicit ACK of a call on a channel by the reception of the first packet of the next call on that channel. If another call doesn't come along to implicitly ACK a call, then we have to time the call out. There are some bugs there that will be addressed in subsequent patches. Signed-off-by: David Howells --- net/rxrpc/input.c | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index a6da83f036d6..44fb8d893c7d 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -938,6 +938,33 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call, _leave(""); } +/* + * Handle a new call on a channel implicitly completing the preceding call on + * that channel. + * + * TODO: If callNumber > call_id + 1, renegotiate security. + */ +static void rxrpc_input_implicit_end_call(struct rxrpc_connection *conn, + struct rxrpc_call *call) +{ + switch (call->state) { + case RXRPC_CALL_SERVER_AWAIT_ACK: + rxrpc_call_completed(call); + break; + 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); + } + break; + } + + __rxrpc_disconnect_call(conn, call); + rxrpc_notify_socket(call); +} + /* * post connection-level events to the connection * - this includes challenges, responses, some aborts and call terminal packet @@ -1146,6 +1173,16 @@ void rxrpc_data_ready(struct sock *udp_sk) } call = rcu_dereference(chan->call); + + if (sp->hdr.callNumber > chan->call_id) { + if (!(sp->hdr.flags & RXRPC_CLIENT_INITIATED)) { + rcu_read_unlock(); + goto reject_packet; + } + if (call) + rxrpc_input_implicit_end_call(conn, call); + call = NULL; + } } else { skew = 0; call = NULL; From d7833d00915e1fb5743e94d3c207810b30e9fc38 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 6 Oct 2016 08:11:50 +0100 Subject: [PATCH 08/13] rxrpc: Queue the call on expiry When a call expires, it must be queued for the background processor to deal with otherwise a service call that is improperly terminated will just sit there awaiting an ACK and won't expire. Signed-off-by: David Howells --- net/rxrpc/call_event.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index eeea9602cb89..e2a987fd31ce 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -35,8 +35,11 @@ void rxrpc_set_timer(struct rxrpc_call *call, enum rxrpc_timer_trace why, if (call->state < RXRPC_CALL_COMPLETE) { t = call->expire_at; - if (!ktime_after(t, now)) + if (!ktime_after(t, now)) { + trace_rxrpc_timer(call, why, now, now_j); + queue = true; goto out; + } if (!ktime_after(call->resend_at, now)) { call->resend_at = call->expire_at; @@ -76,12 +79,11 @@ void rxrpc_set_timer(struct rxrpc_call *call, enum rxrpc_timer_trace why, mod_timer(&call->timer, t_j); trace_rxrpc_timer(call, why, now, now_j); } - - if (queue) - rxrpc_queue_call(call); } out: + if (queue) + rxrpc_queue_call(call); read_unlock_bh(&call->state_lock); } From 94bc669efa3beb1f6b171f5a3225079bc457d4a2 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 6 Oct 2016 08:11:50 +0100 Subject: [PATCH 09/13] rxrpc: Add missing notification The call's background processor work item needs to notify the socket when it completes a call so that recvmsg() or the AFS fs can deal with it. Without this, call expiry isn't handled. Signed-off-by: David Howells --- net/rxrpc/call_event.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index e2a987fd31ce..0f91d329e910 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -372,6 +372,7 @@ recheck_state: if (call->state == RXRPC_CALL_COMPLETE) { del_timer_sync(&call->timer); + rxrpc_notify_socket(call); goto out_put; } From cf69207afa2a750ba78782bb4ff4d72c1efb8e6b Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 6 Oct 2016 08:11:50 +0100 Subject: [PATCH 10/13] rxrpc: Return negative error code to kernel service In rxrpc_kernel_recv_data(), when we return the error number incurred by a failed call, we must negate it before returning it as it's stored as positive (that's what we have to pass back to userspace). Signed-off-by: David Howells --- net/rxrpc/recvmsg.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 3fa7771c2a9d..db5b02a47518 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -652,7 +652,7 @@ excess_data: goto out; call_complete: *_abort = call->abort_code; - ret = call->error; + ret = -call->error; if (call->completion == RXRPC_CALL_SUCCEEDED) { ret = 1; if (size > 0) From 9008f998a2e992991a5d60656d4573ba4c516c58 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 6 Oct 2016 08:11:50 +0100 Subject: [PATCH 11/13] afs: Check for fatal error when in waiting for ack state When it's in the waiting-for-ACK state, the AFS filesystem needs to check the result of rxrpc_kernel_recv_data() any time it is notified to see if it is indicating a fatal error. If this is the case, it needs to mark the call completed otherwise the call just sits there and never goes away. Signed-off-by: David Howells --- fs/afs/rxrpc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 59bdaa7527b6..477928b25940 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -418,7 +418,7 @@ static void afs_deliver_to_call(struct afs_call *call) &call->abort_code); if (ret == -EINPROGRESS || ret == -EAGAIN) return; - if (ret == 1) { + if (ret == 1 || ret < 0) { call->state = AFS_CALL_COMPLETE; goto done; } From 9749fd2beac42e32cb3e3d85489b52b9cc71a9ac Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 6 Oct 2016 08:11:50 +0100 Subject: [PATCH 12/13] rxrpc: Need to produce an ACK for service op if op takes a long time We need to generate a DELAY ACK from the service end of an operation if we start doing the actual operation work and it takes longer than expected. This will hard-ACK the request data and allow the client to release its resources. To make this work: (1) We have to set the ack timer and propose an ACK when the call moves to the RXRPC_CALL_SERVER_ACK_REQUEST and clear the pending ACK and cancel the timer when we start transmitting the reply (the first DATA packet of the reply implicitly ACKs the request phase). (2) It must be possible to set the timer when the caller is holding call->state_lock, so split the lock-getting part of the timer function out. (3) Add trace notes for the ACK we're requesting and the timer we clear. Signed-off-by: David Howells --- net/rxrpc/ar-internal.h | 3 +++ net/rxrpc/call_event.c | 16 ++++++++++++---- net/rxrpc/misc.c | 2 ++ net/rxrpc/recvmsg.c | 8 ++++++-- net/rxrpc/sendmsg.c | 5 +++++ 5 files changed, 28 insertions(+), 6 deletions(-) diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index b56676be07c7..f60e35576526 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -733,6 +733,7 @@ extern const char rxrpc_rtt_rx_traces[rxrpc_rtt_rx__nr_trace][5]; enum rxrpc_timer_trace { rxrpc_timer_begin, rxrpc_timer_init_for_reply, + rxrpc_timer_init_for_send_reply, rxrpc_timer_expired, rxrpc_timer_set_for_ack, rxrpc_timer_set_for_ping, @@ -749,6 +750,7 @@ enum rxrpc_propose_ack_trace { rxrpc_propose_ack_ping_for_lost_ack, rxrpc_propose_ack_ping_for_lost_reply, rxrpc_propose_ack_ping_for_params, + rxrpc_propose_ack_processing_op, rxrpc_propose_ack_respond_to_ack, rxrpc_propose_ack_respond_to_ping, rxrpc_propose_ack_retry_tx, @@ -811,6 +813,7 @@ int rxrpc_reject_call(struct rxrpc_sock *); /* * call_event.c */ +void __rxrpc_set_timer(struct rxrpc_call *, enum rxrpc_timer_trace, ktime_t); void rxrpc_set_timer(struct rxrpc_call *, enum rxrpc_timer_trace, ktime_t); void rxrpc_propose_ACK(struct rxrpc_call *, u8, u16, u32, bool, bool, enum rxrpc_propose_ack_trace); diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index 0f91d329e910..97a17ada4431 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -24,15 +24,13 @@ /* * Set the timer */ -void rxrpc_set_timer(struct rxrpc_call *call, enum rxrpc_timer_trace why, - ktime_t now) +void __rxrpc_set_timer(struct rxrpc_call *call, enum rxrpc_timer_trace why, + ktime_t now) { unsigned long t_j, now_j = jiffies; ktime_t t; bool queue = false; - read_lock_bh(&call->state_lock); - if (call->state < RXRPC_CALL_COMPLETE) { t = call->expire_at; if (!ktime_after(t, now)) { @@ -84,6 +82,16 @@ void rxrpc_set_timer(struct rxrpc_call *call, enum rxrpc_timer_trace why, out: if (queue) rxrpc_queue_call(call); +} + +/* + * Set the timer + */ +void rxrpc_set_timer(struct rxrpc_call *call, enum rxrpc_timer_trace why, + ktime_t now) +{ + read_lock_bh(&call->state_lock); + __rxrpc_set_timer(call, why, now); read_unlock_bh(&call->state_lock); } diff --git a/net/rxrpc/misc.c b/net/rxrpc/misc.c index 1cdcba52f83b..6dee55fad2d3 100644 --- a/net/rxrpc/misc.c +++ b/net/rxrpc/misc.c @@ -195,6 +195,7 @@ const char rxrpc_timer_traces[rxrpc_timer__nr_trace][8] = { [rxrpc_timer_begin] = "Begin ", [rxrpc_timer_expired] = "*EXPR*", [rxrpc_timer_init_for_reply] = "IniRpl", + [rxrpc_timer_init_for_send_reply] = "SndRpl", [rxrpc_timer_set_for_ack] = "SetAck", [rxrpc_timer_set_for_ping] = "SetPng", [rxrpc_timer_set_for_send] = "SetTx ", @@ -207,6 +208,7 @@ const char rxrpc_propose_ack_traces[rxrpc_propose_ack__nr_trace][8] = { [rxrpc_propose_ack_ping_for_lost_ack] = "LostAck", [rxrpc_propose_ack_ping_for_lost_reply] = "LostRpl", [rxrpc_propose_ack_ping_for_params] = "Params ", + [rxrpc_propose_ack_processing_op] = "ProcOp ", [rxrpc_propose_ack_respond_to_ack] = "Rsp2Ack", [rxrpc_propose_ack_respond_to_ping] = "Rsp2Png", [rxrpc_propose_ack_retry_tx] = "RetryTx", diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index db5b02a47518..c29362d50a92 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -151,17 +151,21 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) switch (call->state) { case RXRPC_CALL_CLIENT_RECV_REPLY: __rxrpc_call_completed(call); + write_unlock_bh(&call->state_lock); break; case RXRPC_CALL_SERVER_RECV_REQUEST: call->tx_phase = true; call->state = RXRPC_CALL_SERVER_ACK_REQUEST; + call->ack_at = call->expire_at; + write_unlock_bh(&call->state_lock); + rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, 0, serial, false, true, + rxrpc_propose_ack_processing_op); break; default: + write_unlock_bh(&call->state_lock); break; } - - write_unlock_bh(&call->state_lock); } /* diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index 55a2fb2cfc2f..b214a4d4a641 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -130,6 +130,11 @@ static void rxrpc_queue_packet(struct rxrpc_call *call, struct sk_buff *skb, break; case RXRPC_CALL_SERVER_ACK_REQUEST: call->state = RXRPC_CALL_SERVER_SEND_REPLY; + call->ack_at = call->expire_at; + if (call->ackr_reason == RXRPC_ACK_DELAY) + call->ackr_reason = 0; + __rxrpc_set_timer(call, rxrpc_timer_init_for_send_reply, + ktime_get_real()); if (!last) break; case RXRPC_CALL_SERVER_SEND_REPLY: From bf7d620abf22c321208a4da4f435e7af52551a21 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 6 Oct 2016 08:11:51 +0100 Subject: [PATCH 13/13] rxrpc: Don't request an ACK on the last DATA packet of a call's Tx phase Don't request an ACK on the last DATA packet of a call's Tx phase as for a client there will be a reply packet or some sort of ACK to shift phase. If the ACK is requested, OpenAFS sends a REQUESTED-ACK ACK with soft-ACKs in it and doesn't follow up with a hard-ACK. If we don't set the flag, OpenAFS will send a DELAY ACK that hard-ACKs the reply data, thereby allowing the call to terminate cleanly. Signed-off-by: David Howells --- net/rxrpc/output.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index a12cea0cbc05..5dab1ff3a6c2 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -307,11 +307,12 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, /* If our RTT cache needs working on, request an ACK. Also request * ACKs if a DATA packet appears to have been lost. */ - if (retrans || - call->cong_mode == RXRPC_CALL_SLOW_START || - (call->peer->rtt_usage < 3 && sp->hdr.seq & 1) || - ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), - ktime_get_real())) + if (!(sp->hdr.flags & RXRPC_LAST_PACKET) && + (retrans || + call->cong_mode == RXRPC_CALL_SLOW_START || + (call->peer->rtt_usage < 3 && sp->hdr.seq & 1) || + ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), + ktime_get_real()))) whdr.flags |= RXRPC_REQUEST_ACK; if (IS_ENABLED(CONFIG_AF_RXRPC_INJECT_LOSS)) {