2016-04-04 16:00:34 +03:00
|
|
|
/* Peer event handling, typically ICMP messages.
|
2007-04-27 02:48:28 +04:00
|
|
|
*
|
|
|
|
|
* 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 16:00:34 +03:00
|
|
|
static void rxrpc_store_error(struct rxrpc_peer *, struct sock_exterr_skb *);
|
|
|
|
|
|
2016-04-04 16:00:32 +03:00
|
|
|
/*
|
|
|
|
|
* 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.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;
|
|
|
|
|
srx.transport_len = sizeof(struct sockaddr_in);
|
|
|
|
|
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;
|
|
|
|
|
|
|
|
|
|
default:
|
|
|
|
|
BUG();
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
return rxrpc_lookup_peer_rcu(local, &srx);
|
|
|
|
|
}
|
|
|
|
|
|
2016-04-04 16:00:33 +03:00
|
|
|
/*
|
|
|
|
|
* 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);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2007-04-27 02:48:28 +04:00
|
|
|
/*
|
2016-04-04 16:00:34 +03:00
|
|
|
* Handle an error received on the local endpoint.
|
2007-04-27 02:48:28 +04:00
|
|
|
*/
|
2016-04-04 16:00:32 +03:00
|
|
|
void rxrpc_error_report(struct sock *sk)
|
2007-04-27 02:48:28 +04:00
|
|
|
{
|
|
|
|
|
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);
|
|
|
|
|
|
2014-09-01 05:30:27 +04:00
|
|
|
skb = sock_dequeue_err_skb(sk);
|
2007-04-27 02:48:28 +04:00
|
|
|
if (!skb) {
|
|
|
|
|
_leave("UDP socket errqueue empty");
|
|
|
|
|
return;
|
|
|
|
|
}
|
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 13:10:12 +03:00
|
|
|
rxrpc_new_skb(skb);
|
2015-03-08 04:33:22 +03:00
|
|
|
serr = SKB_EXT_ERR(skb);
|
|
|
|
|
if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) {
|
2015-01-30 21:29:31 +03:00
|
|
|
_leave("UDP empty message");
|
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 13:10:12 +03:00
|
|
|
rxrpc_free_skb(skb);
|
2015-01-30 21:29:31 +03:00
|
|
|
return;
|
|
|
|
|
}
|
2007-04-27 02:48:28 +04:00
|
|
|
|
2016-04-04 16:00:32 +03:00
|
|
|
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();
|
2007-04-27 02:48:28 +04:00
|
|
|
rxrpc_free_skb(skb);
|
|
|
|
|
_leave(" [no peer]");
|
|
|
|
|
return;
|
|
|
|
|
}
|
|
|
|
|
|
2016-04-04 16:00:33 +03:00
|
|
|
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 16:00:34 +03:00
|
|
|
rcu_read_unlock();
|
2016-04-04 16:00:33 +03:00
|
|
|
rxrpc_free_skb(skb);
|
2016-04-04 16:00:34 +03:00
|
|
|
rxrpc_put_peer(peer);
|
|
|
|
|
_leave(" [MTU update]");
|
|
|
|
|
return;
|
2007-04-27 02:48:28 +04:00
|
|
|
}
|
|
|
|
|
|
2016-04-04 16:00:34 +03:00
|
|
|
rxrpc_store_error(peer, serr);
|
2016-04-04 16:00:32 +03:00
|
|
|
rcu_read_unlock();
|
2016-04-04 16:00:34 +03:00
|
|
|
rxrpc_free_skb(skb);
|
2007-04-27 02:48:28 +04:00
|
|
|
|
2016-04-04 16:00:34 +03:00
|
|
|
/* The ref we obtained is passed off to the work item */
|
|
|
|
|
rxrpc_queue_work(&peer->error_distributor);
|
2007-04-27 02:48:28 +04:00
|
|
|
_leave("");
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/*
|
2016-04-04 16:00:34 +03:00
|
|
|
* Map an error report to error codes on the peer record.
|
2007-04-27 02:48:28 +04:00
|
|
|
*/
|
2016-04-04 16:00:34 +03:00
|
|
|
static void rxrpc_store_error(struct rxrpc_peer *peer,
|
|
|
|
|
struct sock_exterr_skb *serr)
|
2007-04-27 02:48:28 +04:00
|
|
|
{
|
|
|
|
|
struct sock_extended_err *ee;
|
2011-05-20 02:37:11 +04:00
|
|
|
int err;
|
2007-04-27 02:48:28 +04:00
|
|
|
|
|
|
|
|
_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;
|
|
|
|
|
|
2016-04-04 16:00:34 +03:00
|
|
|
case SO_EE_ORIGIN_NONE:
|
2007-04-27 02:48:28 +04:00
|
|
|
case SO_EE_ORIGIN_LOCAL:
|
2016-04-04 16:00:34 +03:00
|
|
|
_proto("Rx Received local error { error=%d }", err);
|
2016-04-04 16:00:34 +03:00
|
|
|
err += RXRPC_LOCAL_ERROR_OFFSET;
|
2007-04-27 02:48:28 +04:00
|
|
|
break;
|
|
|
|
|
|
|
|
|
|
case SO_EE_ORIGIN_ICMP6:
|
|
|
|
|
default:
|
2016-04-04 16:00:34 +03:00
|
|
|
_proto("Rx Received error report { orig=%u }", ee->ee_origin);
|
2007-04-27 02:48:28 +04:00
|
|
|
break;
|
|
|
|
|
}
|
|
|
|
|
|
2016-04-04 16:00:34 +03:00
|
|
|
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;
|
2016-08-30 11:49:28 +03:00
|
|
|
enum rxrpc_call_completion compl;
|
|
|
|
|
int error;
|
2016-04-04 16:00:34 +03:00
|
|
|
|
|
|
|
|
_enter("");
|
2007-04-27 02:48:28 +04:00
|
|
|
|
2016-08-30 11:49:28 +03:00
|
|
|
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;
|
|
|
|
|
}
|
2007-04-27 02:48:28 +04:00
|
|
|
|
2016-08-30 11:49:28 +03:00
|
|
|
_debug("ISSUE ERROR %s %d", rxrpc_call_completions[compl], error);
|
2007-04-27 02:48:28 +04:00
|
|
|
|
2016-04-04 16:00:34 +03:00
|
|
|
spin_lock_bh(&peer->lock);
|
2007-04-27 02:48:28 +04:00
|
|
|
|
2016-04-04 16:00:34 +03:00
|
|
|
while (!hlist_empty(&peer->error_targets)) {
|
|
|
|
|
call = hlist_entry(peer->error_targets.first,
|
|
|
|
|
struct rxrpc_call, error_link);
|
|
|
|
|
hlist_del_init(&call->error_link);
|
2016-08-30 11:49:29 +03:00
|
|
|
rxrpc_see_call(call);
|
2016-04-04 16:00:34 +03:00
|
|
|
|
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 13:10:12 +03:00
|
|
|
if (rxrpc_set_call_completion(call, compl, 0, error))
|
|
|
|
|
rxrpc_notify_socket(call);
|
2007-04-27 02:48:28 +04:00
|
|
|
}
|
|
|
|
|
|
2016-04-04 16:00:34 +03:00
|
|
|
spin_unlock_bh(&peer->lock);
|
2007-04-27 02:48:28 +04:00
|
|
|
|
2016-04-04 16:00:34 +03:00
|
|
|
rxrpc_put_peer(peer);
|
2007-04-27 02:48:28 +04:00
|
|
|
_leave("");
|
|
|
|
|
}
|
