2016-04-04 07:00:34 -06:00
|
|
|
/* Peer event handling, typically ICMP messages.
|
2007-04-26 16:48:28 -06:00
|
|
|
*
|
|
|
|
* Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
|
|
|
|
* Written by David Howells (dhowells@redhat.com)
|
|
|
|
*
|
|
|
|
* This program is free software; you can redistribute it and/or
|
|
|
|
* modify it under the terms of the GNU General Public License
|
|
|
|
* as published by the Free Software Foundation; either version
|
|
|
|
* 2 of the License, or (at your option) any later version.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/module.h>
|
|
|
|
#include <linux/net.h>
|
|
|
|
#include <linux/skbuff.h>
|
|
|
|
#include <linux/errqueue.h>
|
|
|
|
#include <linux/udp.h>
|
|
|
|
#include <linux/in.h>
|
|
|
|
#include <linux/in6.h>
|
|
|
|
#include <linux/icmp.h>
|
|
|
|
#include <net/sock.h>
|
|
|
|
#include <net/af_rxrpc.h>
|
|
|
|
#include <net/ip.h>
|
|
|
|
#include "ar-internal.h"
|
|
|
|
|
2016-04-04 07:00:34 -06:00
|
|
|
static void rxrpc_store_error(struct rxrpc_peer *, struct sock_exterr_skb *);
|
2018-09-27 08:13:09 -06:00
|
|
|
static void rxrpc_distribute_error(struct rxrpc_peer *, int,
|
|
|
|
enum rxrpc_call_completion);
|
2016-04-04 07:00:34 -06:00
|
|
|
|
2016-04-04 07:00:32 -06:00
|
|
|
/*
|
|
|
|
* Find the peer associated with an ICMP packet.
|
|
|
|
*/
|
|
|
|
static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
|
2018-05-10 16:26:01 -06:00
|
|
|
const struct sk_buff *skb,
|
|
|
|
struct sockaddr_rxrpc *srx)
|
2016-04-04 07:00:32 -06:00
|
|
|
{
|
|
|
|
struct sock_exterr_skb *serr = SKB_EXT_ERR(skb);
|
|
|
|
|
|
|
|
_enter("");
|
|
|
|
|
2018-05-10 16:26:01 -06:00
|
|
|
memset(srx, 0, sizeof(*srx));
|
|
|
|
srx->transport_type = local->srx.transport_type;
|
|
|
|
srx->transport_len = local->srx.transport_len;
|
|
|
|
srx->transport.family = local->srx.transport.family;
|
2016-04-04 07:00:32 -06:00
|
|
|
|
|
|
|
/* Can we see an ICMP4 packet on an ICMP6 listening socket? and vice
|
|
|
|
* versa?
|
|
|
|
*/
|
2018-05-10 16:26:01 -06:00
|
|
|
switch (srx->transport.family) {
|
2016-04-04 07:00:32 -06:00
|
|
|
case AF_INET:
|
2018-10-04 02:32:28 -06:00
|
|
|
srx->transport_len = sizeof(srx->transport.sin);
|
|
|
|
srx->transport.family = AF_INET;
|
2018-05-10 16:26:01 -06:00
|
|
|
srx->transport.sin.sin_port = serr->port;
|
2016-04-04 07:00:32 -06:00
|
|
|
switch (serr->ee.ee_origin) {
|
|
|
|
case SO_EE_ORIGIN_ICMP:
|
|
|
|
_net("Rx ICMP");
|
2018-05-10 16:26:01 -06:00
|
|
|
memcpy(&srx->transport.sin.sin_addr,
|
2016-04-04 07:00:32 -06:00
|
|
|
skb_network_header(skb) + serr->addr_offset,
|
|
|
|
sizeof(struct in_addr));
|
|
|
|
break;
|
|
|
|
case SO_EE_ORIGIN_ICMP6:
|
|
|
|
_net("Rx ICMP6 on v4 sock");
|
2018-05-10 16:26:01 -06:00
|
|
|
memcpy(&srx->transport.sin.sin_addr,
|
2016-04-04 07:00:32 -06:00
|
|
|
skb_network_header(skb) + serr->addr_offset + 12,
|
|
|
|
sizeof(struct in_addr));
|
|
|
|
break;
|
|
|
|
default:
|
2018-05-10 16:26:01 -06:00
|
|
|
memcpy(&srx->transport.sin.sin_addr, &ip_hdr(skb)->saddr,
|
2016-04-04 07:00:32 -06:00
|
|
|
sizeof(struct in_addr));
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
|
2016-09-17 00:26:01 -06:00
|
|
|
#ifdef CONFIG_AF_RXRPC_IPV6
|
2016-09-13 01:49:05 -06:00
|
|
|
case AF_INET6:
|
|
|
|
switch (serr->ee.ee_origin) {
|
|
|
|
case SO_EE_ORIGIN_ICMP6:
|
|
|
|
_net("Rx ICMP6");
|
2018-10-04 02:32:28 -06:00
|
|
|
srx->transport.sin6.sin6_port = serr->port;
|
2018-05-10 16:26:01 -06:00
|
|
|
memcpy(&srx->transport.sin6.sin6_addr,
|
2016-09-13 01:49:05 -06:00
|
|
|
skb_network_header(skb) + serr->addr_offset,
|
|
|
|
sizeof(struct in6_addr));
|
|
|
|
break;
|
|
|
|
case SO_EE_ORIGIN_ICMP:
|
|
|
|
_net("Rx ICMP on v6 sock");
|
2018-10-04 02:32:28 -06:00
|
|
|
srx->transport_len = sizeof(srx->transport.sin);
|
|
|
|
srx->transport.family = AF_INET;
|
|
|
|
srx->transport.sin.sin_port = serr->port;
|
|
|
|
memcpy(&srx->transport.sin.sin_addr,
|
2016-09-13 01:49:05 -06:00
|
|
|
skb_network_header(skb) + serr->addr_offset,
|
|
|
|
sizeof(struct in_addr));
|
|
|
|
break;
|
|
|
|
default:
|
2018-05-10 16:26:01 -06:00
|
|
|
memcpy(&srx->transport.sin6.sin6_addr,
|
2016-09-13 01:49:05 -06:00
|
|
|
&ipv6_hdr(skb)->saddr,
|
|
|
|
sizeof(struct in6_addr));
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
break;
|
2016-09-17 00:26:01 -06:00
|
|
|
#endif
|
2016-09-13 01:49:05 -06:00
|
|
|
|
2016-04-04 07:00:32 -06:00
|
|
|
default:
|
|
|
|
BUG();
|
|
|
|
}
|
|
|
|
|
2018-05-10 16:26:01 -06:00
|
|
|
return rxrpc_lookup_peer_rcu(local, srx);
|
2016-04-04 07:00:32 -06:00
|
|
|
}
|
|
|
|
|
2016-04-04 07:00:33 -06:00
|
|
|
/*
|
|
|
|
* Handle an MTU/fragmentation problem.
|
|
|
|
*/
|
|
|
|
static void rxrpc_adjust_mtu(struct rxrpc_peer *peer, struct sock_exterr_skb *serr)
|
|
|
|
{
|
|
|
|
u32 mtu = serr->ee.ee_info;
|
|
|
|
|
|
|
|
_net("Rx ICMP Fragmentation Needed (%d)", mtu);
|
|
|
|
|
|
|
|
/* wind down the local interface MTU */
|
|
|
|
if (mtu > 0 && peer->if_mtu == 65535 && mtu < peer->if_mtu) {
|
|
|
|
peer->if_mtu = mtu;
|
|
|
|
_net("I/F MTU %u", mtu);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (mtu == 0) {
|
|
|
|
/* they didn't give us a size, estimate one */
|
|
|
|
mtu = peer->if_mtu;
|
|
|
|
if (mtu > 1500) {
|
|
|
|
mtu >>= 1;
|
|
|
|
if (mtu < 1500)
|
|
|
|
mtu = 1500;
|
|
|
|
} else {
|
|
|
|
mtu -= 100;
|
|
|
|
if (mtu < peer->hdrsize)
|
|
|
|
mtu = peer->hdrsize + 4;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (mtu < peer->mtu) {
|
|
|
|
spin_lock_bh(&peer->lock);
|
|
|
|
peer->mtu = mtu;
|
|
|
|
peer->maxdata = peer->mtu - peer->hdrsize;
|
|
|
|
spin_unlock_bh(&peer->lock);
|
|
|
|
_net("Net MTU %u (maxdata %u)",
|
|
|
|
peer->mtu, peer->maxdata);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2007-04-26 16:48:28 -06:00
|
|
|
/*
|
2016-04-04 07:00:34 -06:00
|
|
|
* Handle an error received on the local endpoint.
|
2007-04-26 16:48:28 -06:00
|
|
|
*/
|
2016-04-04 07:00:32 -06:00
|
|
|
void rxrpc_error_report(struct sock *sk)
|
2007-04-26 16:48:28 -06:00
|
|
|
{
|
|
|
|
struct sock_exterr_skb *serr;
|
2018-05-10 16:26:01 -06:00
|
|
|
struct sockaddr_rxrpc srx;
|
2007-04-26 16:48:28 -06:00
|
|
|
struct rxrpc_local *local = sk->sk_user_data;
|
|
|
|
struct rxrpc_peer *peer;
|
|
|
|
struct sk_buff *skb;
|
|
|
|
|
|
|
|
_enter("%p{%d}", sk, local->debug_id);
|
|
|
|
|
2014-08-31 19:30:27 -06:00
|
|
|
skb = sock_dequeue_err_skb(sk);
|
2007-04-26 16:48:28 -06:00
|
|
|
if (!skb) {
|
|
|
|
_leave("UDP socket errqueue empty");
|
|
|
|
return;
|
|
|
|
}
|
2016-09-17 03:49:14 -06:00
|
|
|
rxrpc_new_skb(skb, rxrpc_skb_rx_received);
|
2015-03-07 18:33:22 -07:00
|
|
|
serr = SKB_EXT_ERR(skb);
|
|
|
|
if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) {
|
2015-01-30 11:29:31 -07:00
|
|
|
_leave("UDP empty message");
|
2016-09-17 03:49:14 -06:00
|
|
|
rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
|
2015-01-30 11:29:31 -07:00
|
|
|
return;
|
|
|
|
}
|
2007-04-26 16:48:28 -06:00
|
|
|
|
2016-04-04 07:00:32 -06:00
|
|
|
rcu_read_lock();
|
2018-05-10 16:26:01 -06:00
|
|
|
peer = rxrpc_lookup_peer_icmp_rcu(local, skb, &srx);
|
2016-04-04 07:00:32 -06:00
|
|
|
if (peer && !rxrpc_get_peer_maybe(peer))
|
|
|
|
peer = NULL;
|
|
|
|
if (!peer) {
|
|
|
|
rcu_read_unlock();
|
2016-09-17 03:49:14 -06:00
|
|
|
rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
|
2007-04-26 16:48:28 -06:00
|
|
|
_leave(" [no peer]");
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
2018-05-10 16:26:01 -06:00
|
|
|
trace_rxrpc_rx_icmp(peer, &serr->ee, &srx);
|
|
|
|
|
2016-04-04 07:00:33 -06:00
|
|
|
if ((serr->ee.ee_origin == SO_EE_ORIGIN_ICMP &&
|
|
|
|
serr->ee.ee_type == ICMP_DEST_UNREACH &&
|
|
|
|
serr->ee.ee_code == ICMP_FRAG_NEEDED)) {
|
|
|
|
rxrpc_adjust_mtu(peer, serr);
|
2016-04-04 07:00:34 -06:00
|
|
|
rcu_read_unlock();
|
2016-09-17 03:49:14 -06:00
|
|
|
rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
|
2016-04-04 07:00:34 -06:00
|
|
|
rxrpc_put_peer(peer);
|
|
|
|
_leave(" [MTU update]");
|
|
|
|
return;
|
2007-04-26 16:48:28 -06:00
|
|
|
}
|
|
|
|
|
2016-04-04 07:00:34 -06:00
|
|
|
rxrpc_store_error(peer, serr);
|
2016-04-04 07:00:32 -06:00
|
|
|
rcu_read_unlock();
|
2016-09-17 03:49:14 -06:00
|
|
|
rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
|
2018-10-15 15:37:21 -06:00
|
|
|
rxrpc_put_peer(peer);
|
2007-04-26 16:48:28 -06:00
|
|
|
|
|
|
|
_leave("");
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2016-04-04 07:00:34 -06:00
|
|
|
* Map an error report to error codes on the peer record.
|
2007-04-26 16:48:28 -06:00
|
|
|
*/
|
2016-04-04 07:00:34 -06:00
|
|
|
static void rxrpc_store_error(struct rxrpc_peer *peer,
|
|
|
|
struct sock_exterr_skb *serr)
|
2007-04-26 16:48:28 -06:00
|
|
|
{
|
2018-09-27 08:13:09 -06:00
|
|
|
enum rxrpc_call_completion compl = RXRPC_CALL_NETWORK_ERROR;
|
2007-04-26 16:48:28 -06:00
|
|
|
struct sock_extended_err *ee;
|
2011-05-19 16:37:11 -06:00
|
|
|
int err;
|
2007-04-26 16:48:28 -06:00
|
|
|
|
|
|
|
_enter("");
|
|
|
|
|
|
|
|
ee = &serr->ee;
|
|
|
|
|
|
|
|
err = ee->ee_errno;
|
|
|
|
|
|
|
|
switch (ee->ee_origin) {
|
|
|
|
case SO_EE_ORIGIN_ICMP:
|
|
|
|
switch (ee->ee_type) {
|
|
|
|
case ICMP_DEST_UNREACH:
|
|
|
|
switch (ee->ee_code) {
|
|
|
|
case ICMP_NET_UNREACH:
|
|
|
|
_net("Rx Received ICMP Network Unreachable");
|
|
|
|
break;
|
|
|
|
case ICMP_HOST_UNREACH:
|
|
|
|
_net("Rx Received ICMP Host Unreachable");
|
|
|
|
break;
|
|
|
|
case ICMP_PORT_UNREACH:
|
|
|
|
_net("Rx Received ICMP Port Unreachable");
|
|
|
|
break;
|
|
|
|
case ICMP_NET_UNKNOWN:
|
|
|
|
_net("Rx Received ICMP Unknown Network");
|
|
|
|
break;
|
|
|
|
case ICMP_HOST_UNKNOWN:
|
|
|
|
_net("Rx Received ICMP Unknown Host");
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
_net("Rx Received ICMP DestUnreach code=%u",
|
|
|
|
ee->ee_code);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
|
|
|
|
case ICMP_TIME_EXCEEDED:
|
|
|
|
_net("Rx Received ICMP TTL Exceeded");
|
|
|
|
break;
|
|
|
|
|
|
|
|
default:
|
|
|
|
_proto("Rx Received ICMP error { type=%u code=%u }",
|
|
|
|
ee->ee_type, ee->ee_code);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
break;
|
|
|
|
|
2016-04-04 07:00:34 -06:00
|
|
|
case SO_EE_ORIGIN_NONE:
|
2007-04-26 16:48:28 -06:00
|
|
|
case SO_EE_ORIGIN_LOCAL:
|
2016-04-04 07:00:34 -06:00
|
|
|
_proto("Rx Received local error { error=%d }", err);
|
2018-09-27 08:13:09 -06:00
|
|
|
compl = RXRPC_CALL_LOCAL_ERROR;
|
2007-04-26 16:48:28 -06:00
|
|
|
break;
|
|
|
|
|
|
|
|
case SO_EE_ORIGIN_ICMP6:
|
|
|
|
default:
|
2016-04-04 07:00:34 -06:00
|
|
|
_proto("Rx Received error report { orig=%u }", ee->ee_origin);
|
2007-04-26 16:48:28 -06:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
2018-09-27 08:13:09 -06:00
|
|
|
rxrpc_distribute_error(peer, err, compl);
|
2016-04-04 07:00:34 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2018-09-27 08:13:09 -06:00
|
|
|
* Distribute an error that occurred on a peer.
|
2016-04-04 07:00:34 -06:00
|
|
|
*/
|
2018-09-27 08:13:09 -06:00
|
|
|
static void rxrpc_distribute_error(struct rxrpc_peer *peer, int error,
|
|
|
|
enum rxrpc_call_completion compl)
|
2016-04-04 07:00:34 -06:00
|
|
|
{
|
|
|
|
struct rxrpc_call *call;
|
2007-04-26 16:48:28 -06:00
|
|
|
|
2018-09-27 08:13:09 -06:00
|
|
|
hlist_for_each_entry_rcu(call, &peer->error_targets, error_link) {
|
2016-08-30 02:49:29 -06:00
|
|
|
rxrpc_see_call(call);
|
2018-09-27 08:13:09 -06:00
|
|
|
if (call->state < RXRPC_CALL_COMPLETE &&
|
|
|
|
rxrpc_set_call_completion(call, compl, 0, -error))
|
rxrpc: Rewrite the data and ack handling code
Rewrite the data and ack handling code such that:
(1) Parsing of received ACK and ABORT packets and the distribution and the
filing of DATA packets happens entirely within the data_ready context
called from the UDP socket. This allows us to process and discard ACK
and ABORT packets much more quickly (they're no longer stashed on a
queue for a background thread to process).
(2) We avoid calling skb_clone(), pskb_pull() and pskb_trim(). We instead
keep track of the offset and length of the content of each packet in
the sk_buff metadata. This means we don't do any allocation in the
receive path.
(3) Jumbo DATA packet parsing is now done in data_ready context. Rather
than cloning the packet once for each subpacket and pulling/trimming
it, we file the packet multiple times with an annotation for each
indicating which subpacket is there. From that we can directly
calculate the offset and length.
(4) A call's receive queue can be accessed without taking locks (memory
barriers do have to be used, though).
(5) Incoming calls are set up from preallocated resources and immediately
made live. They can than have packets queued upon them and ACKs
generated. If insufficient resources exist, DATA packet #1 is given a
BUSY reply and other DATA packets are discarded).
(6) sk_buffs no longer take a ref on their parent call.
To make this work, the following changes are made:
(1) Each call's receive buffer is now a circular buffer of sk_buff
pointers (rxtx_buffer) rather than a number of sk_buff_heads spread
between the call and the socket. This permits each sk_buff to be in
the buffer multiple times. The receive buffer is reused for the
transmit buffer.
(2) A circular buffer of annotations (rxtx_annotations) is kept parallel
to the data buffer. Transmission phase annotations indicate whether a
buffered packet has been ACK'd or not and whether it needs
retransmission.
Receive phase annotations indicate whether a slot holds a whole packet
or a jumbo subpacket and, if the latter, which subpacket. They also
note whether the packet has been decrypted in place.
(3) DATA packet window tracking is much simplified. Each phase has just
two numbers representing the window (rx_hard_ack/rx_top and
tx_hard_ack/tx_top).
The hard_ack number is the sequence number before base of the window,
representing the last packet the other side says it has consumed.
hard_ack starts from 0 and the first packet is sequence number 1.
The top number is the sequence number of the highest-numbered packet
residing in the buffer. Packets between hard_ack+1 and top are
soft-ACK'd to indicate they've been received, but not yet consumed.
Four macros, before(), before_eq(), after() and after_eq() are added
to compare sequence numbers within the window. This allows for the
top of the window to wrap when the hard-ack sequence number gets close
to the limit.
Two flags, RXRPC_CALL_RX_LAST and RXRPC_CALL_TX_LAST, are added also
to indicate when rx_top and tx_top point at the packets with the
LAST_PACKET bit set, indicating the end of the phase.
(4) Calls are queued on the socket 'receive queue' rather than packets.
This means that we don't need have to invent dummy packets to queue to
indicate abnormal/terminal states and we don't have to keep metadata
packets (such as ABORTs) around
(5) The offset and length of a (sub)packet's content are now passed to
the verify_packet security op. This is currently expected to decrypt
the packet in place and validate it.
However, there's now nowhere to store the revised offset and length of
the actual data within the decrypted blob (there may be a header and
padding to skip) because an sk_buff may represent multiple packets, so
a locate_data security op is added to retrieve these details from the
sk_buff content when needed.
(6) recvmsg() now has to handle jumbo subpackets, where each subpacket is
individually secured and needs to be individually decrypted. The code
to do this is broken out into rxrpc_recvmsg_data() and shared with the
kernel API. It now iterates over the call's receive buffer rather
than walking the socket receive queue.
Additional changes:
(1) The timers are condensed to a single timer that is set for the soonest
of three timeouts (delayed ACK generation, DATA retransmission and
call lifespan).
(2) Transmission of ACK and ABORT packets is effected immediately from
process-context socket ops/kernel API calls that cause them instead of
them being punted off to a background work item. The data_ready
handler still has to defer to the background, though.
(3) A shutdown op is added to the AF_RXRPC socket so that the AFS
filesystem can shut down the socket and flush its own work items
before closing the socket to deal with any in-progress service calls.
Future additional changes that will need to be considered:
(1) Make sure that a call doesn't hog the front of the queue by receiving
data from the network as fast as userspace is consuming it to the
exclusion of other calls.
(2) Transmit delayed ACKs from within recvmsg() when we've consumed
sufficiently more packets to avoid the background work item needing to
run.
Signed-off-by: David Howells <dhowells@redhat.com>
2016-09-08 04:10:12 -06:00
|
|
|
rxrpc_notify_socket(call);
|
2007-04-26 16:48:28 -06:00
|
|
|
}
|
|
|
|
}
|
2016-09-21 17:41:53 -06:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Add RTT information to cache. This is called in softirq mode and has
|
|
|
|
* exclusive access to the peer RTT data.
|
|
|
|
*/
|
|
|
|
void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why,
|
|
|
|
rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial,
|
|
|
|
ktime_t send_time, ktime_t resp_time)
|
|
|
|
{
|
|
|
|
struct rxrpc_peer *peer = call->peer;
|
|
|
|
s64 rtt;
|
|
|
|
u64 sum = peer->rtt_sum, avg;
|
|
|
|
u8 cursor = peer->rtt_cursor, usage = peer->rtt_usage;
|
|
|
|
|
|
|
|
rtt = ktime_to_ns(ktime_sub(resp_time, send_time));
|
|
|
|
if (rtt < 0)
|
|
|
|
return;
|
|
|
|
|
rxrpc: Fix the packet reception routine
The rxrpc_input_packet() function and its call tree was built around the
assumption that data_ready() handler called from UDP to inform a kernel
service that there is data to be had was non-reentrant. This means that
certain locking could be dispensed with.
This, however, turns out not to be the case with a multi-queue network card
that can deliver packets to multiple cpus simultaneously. Each of those
cpus can be in the rxrpc_input_packet() function at the same time.
Fix by adding or changing some structure members:
(1) Add peer->rtt_input_lock to serialise access to the RTT buffer.
(2) Make conn->service_id into a 32-bit variable so that it can be
cmpxchg'd on all arches.
(3) Add call->input_lock to serialise access to the Rx/Tx state. Note
that although the Rx and Tx states are (almost) entirely separate,
there's no point completing the separation and having separate locks
since it's a bi-phasal RPC protocol rather than a bi-direction
streaming protocol. Data transmission and data reception do not take
place simultaneously on any particular call.
and making the following functional changes:
(1) In rxrpc_input_data(), hold call->input_lock around the core to
prevent simultaneous producing of packets into the Rx ring and
updating of tracking state for a particular call.
(2) In rxrpc_input_ping_response(), only read call->ping_serial once, and
check it before checking RXRPC_CALL_PINGING as that's a cheaper test.
The bit test and bit clear can then be combined. No further locking
is needed here.
(3) In rxrpc_input_ack(), take call->input_lock after we've parsed much of
the ACK packet. The superseded ACK check is then done both before and
after the lock is taken.
The handing of ackinfo data is split, parsing before the lock is taken
and processing with it held. This is keyed on rxMTU being non-zero.
Congestion management is also done within the locked section.
(4) In rxrpc_input_ackall(), take call->input_lock around the Tx window
rotation. The ACKALL packet carries no information and is only really
useful after all packets have been transmitted since it's imprecise.
(5) In rxrpc_input_implicit_end_call(), we use rx->incoming_lock to
prevent calls being simultaneously implicitly ended on two cpus and
also to prevent any races with incoming call setup.
(6) In rxrpc_input_packet(), use cmpxchg() to effect the service upgrade
on a connection. It is only permitted to happen once for a
connection.
(7) In rxrpc_new_incoming_call(), we have to recheck the routing inside
rx->incoming_lock to see if someone else set up the call, connection
or peer whilst we were getting there. We can't trust the values from
the earlier routing check unless we pin refs on them - which we want
to avoid.
Further, we need to allow for an incoming call to have its state
changed on another CPU between us making it live and us adjusting it
because the conn is now in the RXRPC_CONN_SERVICE state.
(8) In rxrpc_peer_add_rtt(), take peer->rtt_input_lock around the access
to the RTT buffer. Don't need to lock around setting peer->rtt.
For reference, the inventory of state-accessing or state-altering functions
used by the packet input procedure is:
> rxrpc_input_packet()
* PACKET CHECKING
* ROUTING
> rxrpc_post_packet_to_local()
> rxrpc_find_connection_rcu() - uses RCU
> rxrpc_lookup_peer_rcu() - uses RCU
> rxrpc_find_service_conn_rcu() - uses RCU
> idr_find() - uses RCU
* CONNECTION-LEVEL PROCESSING
- Service upgrade
- Can only happen once per conn
! Changed to use cmpxchg
> rxrpc_post_packet_to_conn()
- Setting conn->hi_serial
- Probably safe not using locks
- Maybe use cmpxchg
* CALL-LEVEL PROCESSING
> Old-call checking
> rxrpc_input_implicit_end_call()
> rxrpc_call_completed()
> rxrpc_queue_call()
! Need to take rx->incoming_lock
> __rxrpc_disconnect_call()
> rxrpc_notify_socket()
> rxrpc_new_incoming_call()
- Uses rx->incoming_lock for the entire process
- Might be able to drop this earlier in favour of the call lock
> rxrpc_incoming_call()
! Conflicts with rxrpc_input_implicit_end_call()
> rxrpc_send_ping()
- Don't need locks to check rtt state
> rxrpc_propose_ACK
* PACKET DISTRIBUTION
> rxrpc_input_call_packet()
> rxrpc_input_data()
* QUEUE DATA PACKET ON CALL
> rxrpc_reduce_call_timer()
- Uses timer_reduce()
! Needs call->input_lock()
> rxrpc_receiving_reply()
! Needs locking around ack state
> rxrpc_rotate_tx_window()
> rxrpc_end_tx_phase()
> rxrpc_proto_abort()
> rxrpc_input_dup_data()
- Fills the Rx buffer
- rxrpc_propose_ACK()
- rxrpc_notify_socket()
> rxrpc_input_ack()
* APPLY ACK PACKET TO CALL AND DISCARD PACKET
> rxrpc_input_ping_response()
- Probably doesn't need any extra locking
! Need READ_ONCE() on call->ping_serial
> rxrpc_input_check_for_lost_ack()
- Takes call->lock to consult Tx buffer
> rxrpc_peer_add_rtt()
! Needs to take a lock (peer->rtt_input_lock)
! Could perhaps manage with cmpxchg() and xadd() instead
> rxrpc_input_requested_ack
- Consults Tx buffer
! Probably needs a lock
> rxrpc_peer_add_rtt()
> rxrpc_propose_ack()
> rxrpc_input_ackinfo()
- Changes call->tx_winsize
! Use cmpxchg to handle change
! Should perhaps track serial number
- Uses peer->lock to record MTU specification changes
> rxrpc_proto_abort()
! Need to take call->input_lock
> rxrpc_rotate_tx_window()
> rxrpc_end_tx_phase()
> rxrpc_input_soft_acks()
- Consults the Tx buffer
> rxrpc_congestion_management()
- Modifies the Tx annotations
! Needs call->input_lock()
> rxrpc_queue_call()
> rxrpc_input_abort()
* APPLY ABORT PACKET TO CALL AND DISCARD PACKET
> rxrpc_set_call_completion()
> rxrpc_notify_socket()
> rxrpc_input_ackall()
* APPLY ACKALL PACKET TO CALL AND DISCARD PACKET
! Need to take call->input_lock
> rxrpc_rotate_tx_window()
> rxrpc_end_tx_phase()
> rxrpc_reject_packet()
There are some functions used by the above that queue the packet, after
which the procedure is terminated:
- rxrpc_post_packet_to_local()
- local->event_queue is an sk_buff_head
- local->processor is a work_struct
- rxrpc_post_packet_to_conn()
- conn->rx_queue is an sk_buff_head
- conn->processor is a work_struct
- rxrpc_reject_packet()
- local->reject_queue is an sk_buff_head
- local->processor is a work_struct
And some that offload processing to process context:
- rxrpc_notify_socket()
- Uses RCU lock
- Uses call->notify_lock to call call->notify_rx
- Uses call->recvmsg_lock to queue recvmsg side
- rxrpc_queue_call()
- call->processor is a work_struct
- rxrpc_propose_ACK()
- Uses call->lock to wrap __rxrpc_propose_ACK()
And a bunch that complete a call, all of which use call->state_lock to
protect the call state:
- rxrpc_call_completed()
- rxrpc_set_call_completion()
- rxrpc_abort_call()
- rxrpc_proto_abort()
- Also uses rxrpc_queue_call()
Fixes: 17926a79320a ("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both")
Signed-off-by: David Howells <dhowells@redhat.com>
2018-10-08 08:46:25 -06:00
|
|
|
spin_lock(&peer->rtt_input_lock);
|
|
|
|
|
2016-09-21 17:41:53 -06:00
|
|
|
/* Replace the oldest datum in the RTT buffer */
|
|
|
|
sum -= peer->rtt_cache[cursor];
|
|
|
|
sum += rtt;
|
|
|
|
peer->rtt_cache[cursor] = rtt;
|
|
|
|
peer->rtt_cursor = (cursor + 1) & (RXRPC_RTT_CACHE_SIZE - 1);
|
|
|
|
peer->rtt_sum = sum;
|
|
|
|
if (usage < RXRPC_RTT_CACHE_SIZE) {
|
|
|
|
usage++;
|
|
|
|
peer->rtt_usage = usage;
|
|
|
|
}
|
|
|
|
|
rxrpc: Fix the packet reception routine
The rxrpc_input_packet() function and its call tree was built around the
assumption that data_ready() handler called from UDP to inform a kernel
service that there is data to be had was non-reentrant. This means that
certain locking could be dispensed with.
This, however, turns out not to be the case with a multi-queue network card
that can deliver packets to multiple cpus simultaneously. Each of those
cpus can be in the rxrpc_input_packet() function at the same time.
Fix by adding or changing some structure members:
(1) Add peer->rtt_input_lock to serialise access to the RTT buffer.
(2) Make conn->service_id into a 32-bit variable so that it can be
cmpxchg'd on all arches.
(3) Add call->input_lock to serialise access to the Rx/Tx state. Note
that although the Rx and Tx states are (almost) entirely separate,
there's no point completing the separation and having separate locks
since it's a bi-phasal RPC protocol rather than a bi-direction
streaming protocol. Data transmission and data reception do not take
place simultaneously on any particular call.
and making the following functional changes:
(1) In rxrpc_input_data(), hold call->input_lock around the core to
prevent simultaneous producing of packets into the Rx ring and
updating of tracking state for a particular call.
(2) In rxrpc_input_ping_response(), only read call->ping_serial once, and
check it before checking RXRPC_CALL_PINGING as that's a cheaper test.
The bit test and bit clear can then be combined. No further locking
is needed here.
(3) In rxrpc_input_ack(), take call->input_lock after we've parsed much of
the ACK packet. The superseded ACK check is then done both before and
after the lock is taken.
The handing of ackinfo data is split, parsing before the lock is taken
and processing with it held. This is keyed on rxMTU being non-zero.
Congestion management is also done within the locked section.
(4) In rxrpc_input_ackall(), take call->input_lock around the Tx window
rotation. The ACKALL packet carries no information and is only really
useful after all packets have been transmitted since it's imprecise.
(5) In rxrpc_input_implicit_end_call(), we use rx->incoming_lock to
prevent calls being simultaneously implicitly ended on two cpus and
also to prevent any races with incoming call setup.
(6) In rxrpc_input_packet(), use cmpxchg() to effect the service upgrade
on a connection. It is only permitted to happen once for a
connection.
(7) In rxrpc_new_incoming_call(), we have to recheck the routing inside
rx->incoming_lock to see if someone else set up the call, connection
or peer whilst we were getting there. We can't trust the values from
the earlier routing check unless we pin refs on them - which we want
to avoid.
Further, we need to allow for an incoming call to have its state
changed on another CPU between us making it live and us adjusting it
because the conn is now in the RXRPC_CONN_SERVICE state.
(8) In rxrpc_peer_add_rtt(), take peer->rtt_input_lock around the access
to the RTT buffer. Don't need to lock around setting peer->rtt.
For reference, the inventory of state-accessing or state-altering functions
used by the packet input procedure is:
> rxrpc_input_packet()
* PACKET CHECKING
* ROUTING
> rxrpc_post_packet_to_local()
> rxrpc_find_connection_rcu() - uses RCU
> rxrpc_lookup_peer_rcu() - uses RCU
> rxrpc_find_service_conn_rcu() - uses RCU
> idr_find() - uses RCU
* CONNECTION-LEVEL PROCESSING
- Service upgrade
- Can only happen once per conn
! Changed to use cmpxchg
> rxrpc_post_packet_to_conn()
- Setting conn->hi_serial
- Probably safe not using locks
- Maybe use cmpxchg
* CALL-LEVEL PROCESSING
> Old-call checking
> rxrpc_input_implicit_end_call()
> rxrpc_call_completed()
> rxrpc_queue_call()
! Need to take rx->incoming_lock
> __rxrpc_disconnect_call()
> rxrpc_notify_socket()
> rxrpc_new_incoming_call()
- Uses rx->incoming_lock for the entire process
- Might be able to drop this earlier in favour of the call lock
> rxrpc_incoming_call()
! Conflicts with rxrpc_input_implicit_end_call()
> rxrpc_send_ping()
- Don't need locks to check rtt state
> rxrpc_propose_ACK
* PACKET DISTRIBUTION
> rxrpc_input_call_packet()
> rxrpc_input_data()
* QUEUE DATA PACKET ON CALL
> rxrpc_reduce_call_timer()
- Uses timer_reduce()
! Needs call->input_lock()
> rxrpc_receiving_reply()
! Needs locking around ack state
> rxrpc_rotate_tx_window()
> rxrpc_end_tx_phase()
> rxrpc_proto_abort()
> rxrpc_input_dup_data()
- Fills the Rx buffer
- rxrpc_propose_ACK()
- rxrpc_notify_socket()
> rxrpc_input_ack()
* APPLY ACK PACKET TO CALL AND DISCARD PACKET
> rxrpc_input_ping_response()
- Probably doesn't need any extra locking
! Need READ_ONCE() on call->ping_serial
> rxrpc_input_check_for_lost_ack()
- Takes call->lock to consult Tx buffer
> rxrpc_peer_add_rtt()
! Needs to take a lock (peer->rtt_input_lock)
! Could perhaps manage with cmpxchg() and xadd() instead
> rxrpc_input_requested_ack
- Consults Tx buffer
! Probably needs a lock
> rxrpc_peer_add_rtt()
> rxrpc_propose_ack()
> rxrpc_input_ackinfo()
- Changes call->tx_winsize
! Use cmpxchg to handle change
! Should perhaps track serial number
- Uses peer->lock to record MTU specification changes
> rxrpc_proto_abort()
! Need to take call->input_lock
> rxrpc_rotate_tx_window()
> rxrpc_end_tx_phase()
> rxrpc_input_soft_acks()
- Consults the Tx buffer
> rxrpc_congestion_management()
- Modifies the Tx annotations
! Needs call->input_lock()
> rxrpc_queue_call()
> rxrpc_input_abort()
* APPLY ABORT PACKET TO CALL AND DISCARD PACKET
> rxrpc_set_call_completion()
> rxrpc_notify_socket()
> rxrpc_input_ackall()
* APPLY ACKALL PACKET TO CALL AND DISCARD PACKET
! Need to take call->input_lock
> rxrpc_rotate_tx_window()
> rxrpc_end_tx_phase()
> rxrpc_reject_packet()
There are some functions used by the above that queue the packet, after
which the procedure is terminated:
- rxrpc_post_packet_to_local()
- local->event_queue is an sk_buff_head
- local->processor is a work_struct
- rxrpc_post_packet_to_conn()
- conn->rx_queue is an sk_buff_head
- conn->processor is a work_struct
- rxrpc_reject_packet()
- local->reject_queue is an sk_buff_head
- local->processor is a work_struct
And some that offload processing to process context:
- rxrpc_notify_socket()
- Uses RCU lock
- Uses call->notify_lock to call call->notify_rx
- Uses call->recvmsg_lock to queue recvmsg side
- rxrpc_queue_call()
- call->processor is a work_struct
- rxrpc_propose_ACK()
- Uses call->lock to wrap __rxrpc_propose_ACK()
And a bunch that complete a call, all of which use call->state_lock to
protect the call state:
- rxrpc_call_completed()
- rxrpc_set_call_completion()
- rxrpc_abort_call()
- rxrpc_proto_abort()
- Also uses rxrpc_queue_call()
Fixes: 17926a79320a ("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both")
Signed-off-by: David Howells <dhowells@redhat.com>
2018-10-08 08:46:25 -06:00
|
|
|
spin_unlock(&peer->rtt_input_lock);
|
|
|
|
|
2016-09-21 17:41:53 -06:00
|
|
|
/* Now recalculate the average */
|
|
|
|
if (usage == RXRPC_RTT_CACHE_SIZE) {
|
|
|
|
avg = sum / RXRPC_RTT_CACHE_SIZE;
|
|
|
|
} else {
|
|
|
|
avg = sum;
|
|
|
|
do_div(avg, usage);
|
|
|
|
}
|
|
|
|
|
rxrpc: Fix the packet reception routine
The rxrpc_input_packet() function and its call tree was built around the
assumption that data_ready() handler called from UDP to inform a kernel
service that there is data to be had was non-reentrant. This means that
certain locking could be dispensed with.
This, however, turns out not to be the case with a multi-queue network card
that can deliver packets to multiple cpus simultaneously. Each of those
cpus can be in the rxrpc_input_packet() function at the same time.
Fix by adding or changing some structure members:
(1) Add peer->rtt_input_lock to serialise access to the RTT buffer.
(2) Make conn->service_id into a 32-bit variable so that it can be
cmpxchg'd on all arches.
(3) Add call->input_lock to serialise access to the Rx/Tx state. Note
that although the Rx and Tx states are (almost) entirely separate,
there's no point completing the separation and having separate locks
since it's a bi-phasal RPC protocol rather than a bi-direction
streaming protocol. Data transmission and data reception do not take
place simultaneously on any particular call.
and making the following functional changes:
(1) In rxrpc_input_data(), hold call->input_lock around the core to
prevent simultaneous producing of packets into the Rx ring and
updating of tracking state for a particular call.
(2) In rxrpc_input_ping_response(), only read call->ping_serial once, and
check it before checking RXRPC_CALL_PINGING as that's a cheaper test.
The bit test and bit clear can then be combined. No further locking
is needed here.
(3) In rxrpc_input_ack(), take call->input_lock after we've parsed much of
the ACK packet. The superseded ACK check is then done both before and
after the lock is taken.
The handing of ackinfo data is split, parsing before the lock is taken
and processing with it held. This is keyed on rxMTU being non-zero.
Congestion management is also done within the locked section.
(4) In rxrpc_input_ackall(), take call->input_lock around the Tx window
rotation. The ACKALL packet carries no information and is only really
useful after all packets have been transmitted since it's imprecise.
(5) In rxrpc_input_implicit_end_call(), we use rx->incoming_lock to
prevent calls being simultaneously implicitly ended on two cpus and
also to prevent any races with incoming call setup.
(6) In rxrpc_input_packet(), use cmpxchg() to effect the service upgrade
on a connection. It is only permitted to happen once for a
connection.
(7) In rxrpc_new_incoming_call(), we have to recheck the routing inside
rx->incoming_lock to see if someone else set up the call, connection
or peer whilst we were getting there. We can't trust the values from
the earlier routing check unless we pin refs on them - which we want
to avoid.
Further, we need to allow for an incoming call to have its state
changed on another CPU between us making it live and us adjusting it
because the conn is now in the RXRPC_CONN_SERVICE state.
(8) In rxrpc_peer_add_rtt(), take peer->rtt_input_lock around the access
to the RTT buffer. Don't need to lock around setting peer->rtt.
For reference, the inventory of state-accessing or state-altering functions
used by the packet input procedure is:
> rxrpc_input_packet()
* PACKET CHECKING
* ROUTING
> rxrpc_post_packet_to_local()
> rxrpc_find_connection_rcu() - uses RCU
> rxrpc_lookup_peer_rcu() - uses RCU
> rxrpc_find_service_conn_rcu() - uses RCU
> idr_find() - uses RCU
* CONNECTION-LEVEL PROCESSING
- Service upgrade
- Can only happen once per conn
! Changed to use cmpxchg
> rxrpc_post_packet_to_conn()
- Setting conn->hi_serial
- Probably safe not using locks
- Maybe use cmpxchg
* CALL-LEVEL PROCESSING
> Old-call checking
> rxrpc_input_implicit_end_call()
> rxrpc_call_completed()
> rxrpc_queue_call()
! Need to take rx->incoming_lock
> __rxrpc_disconnect_call()
> rxrpc_notify_socket()
> rxrpc_new_incoming_call()
- Uses rx->incoming_lock for the entire process
- Might be able to drop this earlier in favour of the call lock
> rxrpc_incoming_call()
! Conflicts with rxrpc_input_implicit_end_call()
> rxrpc_send_ping()
- Don't need locks to check rtt state
> rxrpc_propose_ACK
* PACKET DISTRIBUTION
> rxrpc_input_call_packet()
> rxrpc_input_data()
* QUEUE DATA PACKET ON CALL
> rxrpc_reduce_call_timer()
- Uses timer_reduce()
! Needs call->input_lock()
> rxrpc_receiving_reply()
! Needs locking around ack state
> rxrpc_rotate_tx_window()
> rxrpc_end_tx_phase()
> rxrpc_proto_abort()
> rxrpc_input_dup_data()
- Fills the Rx buffer
- rxrpc_propose_ACK()
- rxrpc_notify_socket()
> rxrpc_input_ack()
* APPLY ACK PACKET TO CALL AND DISCARD PACKET
> rxrpc_input_ping_response()
- Probably doesn't need any extra locking
! Need READ_ONCE() on call->ping_serial
> rxrpc_input_check_for_lost_ack()
- Takes call->lock to consult Tx buffer
> rxrpc_peer_add_rtt()
! Needs to take a lock (peer->rtt_input_lock)
! Could perhaps manage with cmpxchg() and xadd() instead
> rxrpc_input_requested_ack
- Consults Tx buffer
! Probably needs a lock
> rxrpc_peer_add_rtt()
> rxrpc_propose_ack()
> rxrpc_input_ackinfo()
- Changes call->tx_winsize
! Use cmpxchg to handle change
! Should perhaps track serial number
- Uses peer->lock to record MTU specification changes
> rxrpc_proto_abort()
! Need to take call->input_lock
> rxrpc_rotate_tx_window()
> rxrpc_end_tx_phase()
> rxrpc_input_soft_acks()
- Consults the Tx buffer
> rxrpc_congestion_management()
- Modifies the Tx annotations
! Needs call->input_lock()
> rxrpc_queue_call()
> rxrpc_input_abort()
* APPLY ABORT PACKET TO CALL AND DISCARD PACKET
> rxrpc_set_call_completion()
> rxrpc_notify_socket()
> rxrpc_input_ackall()
* APPLY ACKALL PACKET TO CALL AND DISCARD PACKET
! Need to take call->input_lock
> rxrpc_rotate_tx_window()
> rxrpc_end_tx_phase()
> rxrpc_reject_packet()
There are some functions used by the above that queue the packet, after
which the procedure is terminated:
- rxrpc_post_packet_to_local()
- local->event_queue is an sk_buff_head
- local->processor is a work_struct
- rxrpc_post_packet_to_conn()
- conn->rx_queue is an sk_buff_head
- conn->processor is a work_struct
- rxrpc_reject_packet()
- local->reject_queue is an sk_buff_head
- local->processor is a work_struct
And some that offload processing to process context:
- rxrpc_notify_socket()
- Uses RCU lock
- Uses call->notify_lock to call call->notify_rx
- Uses call->recvmsg_lock to queue recvmsg side
- rxrpc_queue_call()
- call->processor is a work_struct
- rxrpc_propose_ACK()
- Uses call->lock to wrap __rxrpc_propose_ACK()
And a bunch that complete a call, all of which use call->state_lock to
protect the call state:
- rxrpc_call_completed()
- rxrpc_set_call_completion()
- rxrpc_abort_call()
- rxrpc_proto_abort()
- Also uses rxrpc_queue_call()
Fixes: 17926a79320a ("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both")
Signed-off-by: David Howells <dhowells@redhat.com>
2018-10-08 08:46:25 -06:00
|
|
|
/* Don't need to update this under lock */
|
2016-09-21 17:41:53 -06:00
|
|
|
peer->rtt = avg;
|
|
|
|
trace_rxrpc_rtt_rx(call, why, send_serial, resp_serial, rtt,
|
|
|
|
usage, avg);
|
|
|
|
}
|
2018-03-30 14:04:43 -06:00
|
|
|
|
|
|
|
/*
|
2018-08-08 04:30:02 -06:00
|
|
|
* Perform keep-alive pings.
|
2018-03-30 14:04:43 -06:00
|
|
|
*/
|
2018-08-08 04:30:02 -06:00
|
|
|
static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet,
|
|
|
|
struct list_head *collector,
|
|
|
|
time64_t base,
|
|
|
|
u8 cursor)
|
2018-03-30 14:04:43 -06:00
|
|
|
{
|
|
|
|
struct rxrpc_peer *peer;
|
2018-08-08 04:30:02 -06:00
|
|
|
const u8 mask = ARRAY_SIZE(rxnet->peer_keepalive) - 1;
|
|
|
|
time64_t keepalive_at;
|
|
|
|
int slot;
|
2018-03-30 14:04:43 -06:00
|
|
|
|
2018-08-08 04:30:02 -06:00
|
|
|
spin_lock_bh(&rxnet->peer_hash_lock);
|
2018-03-30 14:04:43 -06:00
|
|
|
|
2018-08-08 04:30:02 -06:00
|
|
|
while (!list_empty(collector)) {
|
|
|
|
peer = list_entry(collector->next,
|
|
|
|
struct rxrpc_peer, keepalive_link);
|
2018-03-30 14:04:43 -06:00
|
|
|
|
2018-08-08 04:30:02 -06:00
|
|
|
list_del_init(&peer->keepalive_link);
|
|
|
|
if (!rxrpc_get_peer_maybe(peer))
|
|
|
|
continue;
|
2018-03-30 14:04:43 -06:00
|
|
|
|
|
|
|
spin_unlock_bh(&rxnet->peer_hash_lock);
|
|
|
|
|
2018-08-08 04:30:02 -06:00
|
|
|
keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME;
|
|
|
|
slot = keepalive_at - base;
|
|
|
|
_debug("%02x peer %u t=%d {%pISp}",
|
|
|
|
cursor, peer->debug_id, slot, &peer->srx.transport);
|
|
|
|
|
|
|
|
if (keepalive_at <= base ||
|
|
|
|
keepalive_at > base + RXRPC_KEEPALIVE_TIME) {
|
|
|
|
rxrpc_send_keepalive(peer);
|
|
|
|
slot = RXRPC_KEEPALIVE_TIME;
|
2018-03-30 14:04:43 -06:00
|
|
|
}
|
|
|
|
|
2018-08-08 04:30:02 -06:00
|
|
|
/* A transmission to this peer occurred since last we examined
|
|
|
|
* it so put it into the appropriate future bucket.
|
|
|
|
*/
|
|
|
|
slot += cursor;
|
|
|
|
slot &= mask;
|
|
|
|
spin_lock_bh(&rxnet->peer_hash_lock);
|
|
|
|
list_add_tail(&peer->keepalive_link,
|
|
|
|
&rxnet->peer_keepalive[slot & mask]);
|
|
|
|
rxrpc_put_peer(peer);
|
2018-03-30 14:04:43 -06:00
|
|
|
}
|
|
|
|
|
|
|
|
spin_unlock_bh(&rxnet->peer_hash_lock);
|
2018-08-08 04:30:02 -06:00
|
|
|
}
|
2018-03-30 14:04:43 -06:00
|
|
|
|
2018-08-08 04:30:02 -06:00
|
|
|
/*
|
|
|
|
* Perform keep-alive pings with VERSION packets to keep any NAT alive.
|
|
|
|
*/
|
|
|
|
void rxrpc_peer_keepalive_worker(struct work_struct *work)
|
|
|
|
{
|
|
|
|
struct rxrpc_net *rxnet =
|
|
|
|
container_of(work, struct rxrpc_net, peer_keepalive_work);
|
|
|
|
const u8 mask = ARRAY_SIZE(rxnet->peer_keepalive) - 1;
|
|
|
|
time64_t base, now, delay;
|
|
|
|
u8 cursor, stop;
|
|
|
|
LIST_HEAD(collector);
|
2018-03-30 14:04:43 -06:00
|
|
|
|
2018-08-08 04:30:02 -06:00
|
|
|
now = ktime_get_seconds();
|
|
|
|
base = rxnet->peer_keepalive_base;
|
|
|
|
cursor = rxnet->peer_keepalive_cursor;
|
|
|
|
_enter("%lld,%u", base - now, cursor);
|
2018-03-30 14:04:43 -06:00
|
|
|
|
2018-08-08 04:30:02 -06:00
|
|
|
if (!rxnet->live)
|
|
|
|
return;
|
2018-03-30 14:04:43 -06:00
|
|
|
|
2018-08-08 04:30:02 -06:00
|
|
|
/* Remove to a temporary list all the peers that are currently lodged
|
|
|
|
* in expired buckets plus all new peers.
|
|
|
|
*
|
|
|
|
* Everything in the bucket at the cursor is processed this
|
|
|
|
* second; the bucket at cursor + 1 goes at now + 1s and so
|
|
|
|
* on...
|
2018-03-30 14:04:43 -06:00
|
|
|
*/
|
|
|
|
spin_lock_bh(&rxnet->peer_hash_lock);
|
2018-08-08 04:30:02 -06:00
|
|
|
list_splice_init(&rxnet->peer_keepalive_new, &collector);
|
|
|
|
|
|
|
|
stop = cursor + ARRAY_SIZE(rxnet->peer_keepalive);
|
|
|
|
while (base <= now && (s8)(cursor - stop) < 0) {
|
|
|
|
list_splice_tail_init(&rxnet->peer_keepalive[cursor & mask],
|
|
|
|
&collector);
|
|
|
|
base++;
|
|
|
|
cursor++;
|
|
|
|
}
|
2018-03-30 14:04:43 -06:00
|
|
|
|
2018-08-08 04:30:02 -06:00
|
|
|
base = now;
|
|
|
|
spin_unlock_bh(&rxnet->peer_hash_lock);
|
2018-03-30 14:04:43 -06:00
|
|
|
|
|
|
|
rxnet->peer_keepalive_base = base;
|
|
|
|
rxnet->peer_keepalive_cursor = cursor;
|
2018-08-08 04:30:02 -06:00
|
|
|
rxrpc_peer_keepalive_dispatch(rxnet, &collector, base, cursor);
|
|
|
|
ASSERT(list_empty(&collector));
|
|
|
|
|
|
|
|
/* Schedule the timer for the next occupied timeslot. */
|
|
|
|
cursor = rxnet->peer_keepalive_cursor;
|
|
|
|
stop = cursor + RXRPC_KEEPALIVE_TIME - 1;
|
|
|
|
for (; (s8)(cursor - stop) < 0; cursor++) {
|
|
|
|
if (!list_empty(&rxnet->peer_keepalive[cursor & mask]))
|
|
|
|
break;
|
|
|
|
base++;
|
|
|
|
}
|
|
|
|
|
|
|
|
now = ktime_get_seconds();
|
|
|
|
delay = base - now;
|
|
|
|
if (delay < 1)
|
|
|
|
delay = 1;
|
|
|
|
delay *= HZ;
|
|
|
|
if (rxnet->live)
|
|
|
|
timer_reduce(&rxnet->peer_keepalive_timer, jiffies + delay);
|
|
|
|
|
2018-03-30 14:04:43 -06:00
|
|
|
_leave("");
|
|
|
|
}
|