linux/net/rxrpc/peer_event.c

351 lines
8.4 KiB
C
Raw Normal View History

/* Peer event handling, typically ICMP messages.
*
* 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"
static void rxrpc_store_error(struct rxrpc_peer *, struct sock_exterr_skb *);
/*
* Find the peer associated with an ICMP packet.
*/
static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
const struct sk_buff *skb)
{
struct sock_exterr_skb *serr = SKB_EXT_ERR(skb);
struct sockaddr_rxrpc srx;
_enter("");
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;
/* Can we see an ICMP4 packet on an ICMP6 listening socket? and vice
* versa?
*/
switch (srx.transport.family) {
case AF_INET:
srx.transport.sin.sin_port = serr->port;
switch (serr->ee.ee_origin) {
case SO_EE_ORIGIN_ICMP:
_net("Rx ICMP");
memcpy(&srx.transport.sin.sin_addr,
skb_network_header(skb) + serr->addr_offset,
sizeof(struct in_addr));
break;
case SO_EE_ORIGIN_ICMP6:
_net("Rx ICMP6 on v4 sock");
memcpy(&srx.transport.sin.sin_addr,
skb_network_header(skb) + serr->addr_offset + 12,
sizeof(struct in_addr));
break;
default:
memcpy(&srx.transport.sin.sin_addr, &ip_hdr(skb)->saddr,
sizeof(struct in_addr));
break;
}
break;
#ifdef CONFIG_AF_RXRPC_IPV6
case AF_INET6:
srx.transport.sin6.sin6_port = serr->port;
switch (serr->ee.ee_origin) {
case SO_EE_ORIGIN_ICMP6:
_net("Rx ICMP6");
memcpy(&srx.transport.sin6.sin6_addr,
skb_network_header(skb) + serr->addr_offset,
sizeof(struct in6_addr));
break;
case SO_EE_ORIGIN_ICMP:
_net("Rx ICMP on v6 sock");
srx.transport.sin6.sin6_addr.s6_addr32[0] = 0;
srx.transport.sin6.sin6_addr.s6_addr32[1] = 0;
srx.transport.sin6.sin6_addr.s6_addr32[2] = htonl(0xffff);
memcpy(srx.transport.sin6.sin6_addr.s6_addr + 12,
skb_network_header(skb) + serr->addr_offset,
sizeof(struct in_addr));
break;
default:
memcpy(&srx.transport.sin6.sin6_addr,
&ipv6_hdr(skb)->saddr,
sizeof(struct in6_addr));
break;
}
break;
#endif
default:
BUG();
}
return rxrpc_lookup_peer_rcu(local, &srx);
}
/*
* 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);
}
}
/*
* Handle an error received on the local endpoint.
*/
void rxrpc_error_report(struct sock *sk)
{
struct sock_exterr_skb *serr;
struct rxrpc_local *local = sk->sk_user_data;
struct rxrpc_peer *peer;
struct sk_buff *skb;
_enter("%p{%d}", sk, local->debug_id);
skb = sock_dequeue_err_skb(sk);
if (!skb) {
_leave("UDP socket errqueue empty");
return;
}
rxrpc_new_skb(skb, rxrpc_skb_rx_received);
ip: fix error queue empty skb handling When reading from the error queue, msg_name and msg_control are only populated for some errors. A new exception for empty timestamp skbs added a false positive on icmp errors without payload. `traceroute -M udpconn` only displayed gateways that return payload with the icmp error: the embedded network headers are pulled before sock_queue_err_skb, leaving an skb with skb->len == 0 otherwise. Fix this regression by refining when msg_name and msg_control branches are taken. The solutions for the two fields are independent. msg_name only makes sense for errors that configure serr->port and serr->addr_offset. Test the first instead of skb->len. This also fixes another issue. saddr could hold the wrong data, as serr->addr_offset is not initialized in some code paths, pointing to the start of the network header. It is only valid when serr->port is set (non-zero). msg_control support differs between IPv4 and IPv6. IPv4 only honors requests for ICMP and timestamps with SOF_TIMESTAMPING_OPT_CMSG. The skb->len test can simply be removed, because skb->dev is also tested and never true for empty skbs. IPv6 honors requests for all errors aside from local errors and timestamps on empty skbs. In both cases, make the policy more explicit by moving this logic to a new function that decides whether to process msg_control and that optionally prepares the necessary fields in skb->cb[]. After this change, the IPv4 and IPv6 paths are more similar. The last case is rxrpc. Here, simply refine to only match timestamps. Fixes: 49ca0d8bfaf3 ("net-timestamp: no-payload option") Reported-by: Jan Niehusmann <jan@gondor.com> Signed-off-by: Willem de Bruijn <willemb@google.com> ---- Changes v1->v2 - fix local origin test inversion in ip6_datagram_support_cmsg - make v4 and v6 code paths more similar by introducing analogous ipv4_datagram_support_cmsg - fix compile bug in rxrpc Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-08 09:33:22 +08:00
serr = SKB_EXT_ERR(skb);
if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) {
_leave("UDP empty message");
rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
return;
}
rcu_read_lock();
peer = rxrpc_lookup_peer_icmp_rcu(local, skb);
if (peer && !rxrpc_get_peer_maybe(peer))
peer = NULL;
if (!peer) {
rcu_read_unlock();
rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
_leave(" [no peer]");
return;
}
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);
rcu_read_unlock();
rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
rxrpc_put_peer(peer);
_leave(" [MTU update]");
return;
}
rxrpc_store_error(peer, serr);
rcu_read_unlock();
rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
/* The ref we obtained is passed off to the work item */
rxrpc_queue_work(&peer->error_distributor);
_leave("");
}
/*
* 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)
{
struct sock_extended_err *ee;
int err;
_enter("");
ee = &serr->ee;
_net("Rx Error o=%d t=%d c=%d e=%d",
ee->ee_origin, ee->ee_type, ee->ee_code, ee->ee_errno);
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;
case SO_EE_ORIGIN_NONE:
case SO_EE_ORIGIN_LOCAL:
_proto("Rx Received local error { error=%d }", err);
err += RXRPC_LOCAL_ERROR_OFFSET;
break;
case SO_EE_ORIGIN_ICMP6:
default:
_proto("Rx Received error report { orig=%u }", ee->ee_origin);
break;
}
peer->error_report = err;
}
/*
* Distribute an error that occurred on a peer
*/
void rxrpc_peer_error_distributor(struct work_struct *work)
{
struct rxrpc_peer *peer =
container_of(work, struct rxrpc_peer, error_distributor);
struct rxrpc_call *call;
enum rxrpc_call_completion compl;
int error;
_enter("");
error = READ_ONCE(peer->error_report);
if (error < RXRPC_LOCAL_ERROR_OFFSET) {
compl = RXRPC_CALL_NETWORK_ERROR;
} else {
compl = RXRPC_CALL_LOCAL_ERROR;
error -= RXRPC_LOCAL_ERROR_OFFSET;
}
_debug("ISSUE ERROR %s %d", rxrpc_call_completions[compl], error);
spin_lock_bh(&peer->lock);
while (!hlist_empty(&peer->error_targets)) {
call = hlist_entry(peer->error_targets.first,
struct rxrpc_call, error_link);
hlist_del_init(&call->error_link);
rxrpc_see_call(call);
if (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 18:10:12 +08:00
rxrpc_notify_socket(call);
}
spin_unlock_bh(&peer->lock);
rxrpc_put_peer(peer);
_leave("");
}
/*
* 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;
/* 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;
}
/* Now recalculate the average */
if (usage == RXRPC_RTT_CACHE_SIZE) {
avg = sum / RXRPC_RTT_CACHE_SIZE;
} else {
avg = sum;
do_div(avg, usage);
}
peer->rtt = avg;
trace_rxrpc_rtt_rx(call, why, send_serial, resp_serial, rtt,
usage, avg);
}