linux_dsm_epyc7002/net/rxrpc/peer_event.c

418 lines
10 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/* Peer event handling, typically ICMP messages.
*
* Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*/
#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 *);
static void rxrpc_distribute_error(struct rxrpc_peer *, int,
enum rxrpc_call_completion);
/*
* 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 sockaddr_rxrpc *srx)
{
struct sock_exterr_skb *serr = SKB_EXT_ERR(skb);
_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_len = sizeof(srx->transport.sin);
srx->transport.family = 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:
switch (serr->ee.ee_origin) {
case SO_EE_ORIGIN_ICMP6:
_net("Rx ICMP6");
srx->transport.sin6.sin6_port = serr->port;
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_len = sizeof(srx->transport.sin);
srx->transport.family = AF_INET;
srx->transport.sin.sin_port = serr->port;
memcpy(&srx->transport.sin.sin_addr,
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 sockaddr_rxrpc srx;
struct rxrpc_local *local;
struct rxrpc_peer *peer;
struct sk_buff *skb;
rcu_read_lock();
local = rcu_dereference_sk_user_data(sk);
if (unlikely(!local)) {
rcu_read_unlock();
return;
}
_enter("%p{%d}", sk, local->debug_id);
/* Clear the outstanding error value on the socket so that it doesn't
* cause kernel_sendmsg() to return it later.
*/
sock_error(sk);
skb = sock_dequeue_err_skb(sk);
if (!skb) {
rcu_read_unlock();
_leave("UDP socket errqueue empty");
return;
}
rxrpc_new_skb(skb, rxrpc_skb_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 08:33:22 +07:00
serr = SKB_EXT_ERR(skb);
if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) {
_leave("UDP empty message");
rcu_read_unlock();
rxrpc_free_skb(skb, rxrpc_skb_freed);
return;
}
peer = rxrpc_lookup_peer_icmp_rcu(local, skb, &srx);
if (peer && !rxrpc_get_peer_maybe(peer))
peer = NULL;
if (!peer) {
rcu_read_unlock();
rxrpc_free_skb(skb, rxrpc_skb_freed);
_leave(" [no peer]");
return;
}
trace_rxrpc_rx_icmp(peer, &serr->ee, &srx);
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_freed);
rxrpc_put_peer(peer);
_leave(" [MTU update]");
return;
}
rxrpc_store_error(peer, serr);
rcu_read_unlock();
rxrpc_free_skb(skb, rxrpc_skb_freed);
rxrpc_put_peer(peer);
_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)
{
enum rxrpc_call_completion compl = RXRPC_CALL_NETWORK_ERROR;
struct sock_extended_err *ee;
int err;
_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;
case SO_EE_ORIGIN_NONE:
case SO_EE_ORIGIN_LOCAL:
_proto("Rx Received local error { error=%d }", err);
compl = RXRPC_CALL_LOCAL_ERROR;
break;
case SO_EE_ORIGIN_ICMP6:
if (err == EACCES)
err = EHOSTUNREACH;
fallthrough;
default:
_proto("Rx Received error report { orig=%u }", ee->ee_origin);
break;
}
rxrpc_distribute_error(peer, err, compl);
}
/*
* Distribute an error that occurred on a peer.
*/
static void rxrpc_distribute_error(struct rxrpc_peer *peer, int error,
enum rxrpc_call_completion compl)
{
struct rxrpc_call *call;
hlist_for_each_entry_rcu(call, &peer->error_targets, error_link) {
rxrpc_see_call(call);
rxrpc: Fix missing notification Under some circumstances, rxrpc will fail a transmit a packet through the underlying UDP socket (ie. UDP sendmsg returns an error). This may result in a call getting stuck. In the instance being seen, where AFS tries to send a probe to the Volume Location server, tracepoints show the UDP Tx failure (in this case returing error 99 EADDRNOTAVAIL) and then nothing more: afs_make_vl_call: c=0000015d VL.GetCapabilities rxrpc_call: c=0000015d NWc u=1 sp=rxrpc_kernel_begin_call+0x106/0x170 [rxrpc] a=00000000dd89ee8a rxrpc_call: c=0000015d Gus u=2 sp=rxrpc_new_client_call+0x14f/0x580 [rxrpc] a=00000000e20e4b08 rxrpc_call: c=0000015d SEE u=2 sp=rxrpc_activate_one_channel+0x7b/0x1c0 [rxrpc] a=00000000e20e4b08 rxrpc_call: c=0000015d CON u=2 sp=rxrpc_kernel_begin_call+0x106/0x170 [rxrpc] a=00000000e20e4b08 rxrpc_tx_fail: c=0000015d r=1 ret=-99 CallDataNofrag The problem is that if the initial packet fails and the retransmission timer hasn't been started, the call is set to completed and an error is returned from rxrpc_send_data_packet() to rxrpc_queue_packet(). Though rxrpc_instant_resend() is called, this does nothing because the call is marked completed. So rxrpc_notify_socket() isn't called and the error is passed back up to rxrpc_send_data(), rxrpc_kernel_send_data() and thence to afs_make_call() and afs_vl_get_capabilities() where it is simply ignored because it is assumed that the result of a probe will be collected asynchronously. Fileserver probing is similarly affected via afs_fs_get_capabilities(). Fix this by always issuing a notification in __rxrpc_set_call_completion() if it shifts a call to the completed state, even if an error is also returned to the caller through the function return value. Also put in a little bit of optimisation to avoid taking the call state_lock and disabling softirqs if the call is already in the completed state and remove some now redundant rxrpc_notify_socket() calls. Fixes: f5c17aaeb2ae ("rxrpc: Calls should only have one terminal state") Reported-by: Gerry Seidman <gerry@auristor.com> Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Marc Dionne <marc.dionne@auristor.com>
2020-06-04 04:21:16 +07:00
rxrpc_set_call_completion(call, compl, 0, -error);
}
}
/*
rxrpc: Fix the keepalive generator [ver #2] AF_RXRPC has a keepalive message generator that generates a message for a peer ~20s after the last transmission to that peer to keep firewall ports open. The implementation is incorrect in the following ways: (1) It mixes up ktime_t and time64_t types. (2) It uses ktime_get_real(), the output of which may jump forward or backward due to adjustments to the time of day. (3) If the current time jumps forward too much or jumps backwards, the generator function will crank the base of the time ring round one slot at a time (ie. a 1s period) until it catches up, spewing out VERSION packets as it goes. Fix the problem by: (1) Only using time64_t. There's no need for sub-second resolution. (2) Use ktime_get_seconds() rather than ktime_get_real() so that time isn't perceived to go backwards. (3) Simplifying rxrpc_peer_keepalive_worker() by splitting it into two parts: (a) The "worker" function that manages the buckets and the timer. (b) The "dispatch" function that takes the pending peers and potentially transmits a keepalive packet before putting them back in the ring into the slot appropriate to the revised last-Tx time. (4) Taking everything that's pending out of the ring and splicing it into a temporary collector list for processing. In the case that there's been a significant jump forward, the ring gets entirely emptied and then the time base can be warped forward before the peers are processed. The warping can't happen if the ring isn't empty because the slot a peer is in is keepalive-time dependent, relative to the base time. (5) Limit the number of iterations of the bucket array when scanning it. (6) Set the timer to skip any empty slots as there's no point waking up if there's nothing to do yet. This can be triggered by an incoming call from a server after a reboot with AF_RXRPC and AFS built into the kernel causing a peer record to be set up before userspace is started. The system clock is then adjusted by userspace, thereby potentially causing the keepalive generator to have a meltdown - which leads to a message like: watchdog: BUG: soft lockup - CPU#0 stuck for 23s! [kworker/0:1:23] ... Workqueue: krxrpcd rxrpc_peer_keepalive_worker EIP: lock_acquire+0x69/0x80 ... Call Trace: ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? _raw_spin_lock_bh+0x29/0x60 ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? __lock_acquire+0x3d3/0x870 ? process_one_work+0x110/0x340 ? process_one_work+0x166/0x340 ? process_one_work+0x110/0x340 ? worker_thread+0x39/0x3c0 ? kthread+0xdb/0x110 ? cancel_delayed_work+0x90/0x90 ? kthread_stop+0x70/0x70 ? ret_from_fork+0x19/0x24 Fixes: ace45bec6d77 ("rxrpc: Fix firewall route keepalive") Reported-by: kernel test robot <lkp@intel.com> Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-08 17:30:02 +07:00
* Perform keep-alive pings.
*/
rxrpc: Fix the keepalive generator [ver #2] AF_RXRPC has a keepalive message generator that generates a message for a peer ~20s after the last transmission to that peer to keep firewall ports open. The implementation is incorrect in the following ways: (1) It mixes up ktime_t and time64_t types. (2) It uses ktime_get_real(), the output of which may jump forward or backward due to adjustments to the time of day. (3) If the current time jumps forward too much or jumps backwards, the generator function will crank the base of the time ring round one slot at a time (ie. a 1s period) until it catches up, spewing out VERSION packets as it goes. Fix the problem by: (1) Only using time64_t. There's no need for sub-second resolution. (2) Use ktime_get_seconds() rather than ktime_get_real() so that time isn't perceived to go backwards. (3) Simplifying rxrpc_peer_keepalive_worker() by splitting it into two parts: (a) The "worker" function that manages the buckets and the timer. (b) The "dispatch" function that takes the pending peers and potentially transmits a keepalive packet before putting them back in the ring into the slot appropriate to the revised last-Tx time. (4) Taking everything that's pending out of the ring and splicing it into a temporary collector list for processing. In the case that there's been a significant jump forward, the ring gets entirely emptied and then the time base can be warped forward before the peers are processed. The warping can't happen if the ring isn't empty because the slot a peer is in is keepalive-time dependent, relative to the base time. (5) Limit the number of iterations of the bucket array when scanning it. (6) Set the timer to skip any empty slots as there's no point waking up if there's nothing to do yet. This can be triggered by an incoming call from a server after a reboot with AF_RXRPC and AFS built into the kernel causing a peer record to be set up before userspace is started. The system clock is then adjusted by userspace, thereby potentially causing the keepalive generator to have a meltdown - which leads to a message like: watchdog: BUG: soft lockup - CPU#0 stuck for 23s! [kworker/0:1:23] ... Workqueue: krxrpcd rxrpc_peer_keepalive_worker EIP: lock_acquire+0x69/0x80 ... Call Trace: ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? _raw_spin_lock_bh+0x29/0x60 ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? __lock_acquire+0x3d3/0x870 ? process_one_work+0x110/0x340 ? process_one_work+0x166/0x340 ? process_one_work+0x110/0x340 ? worker_thread+0x39/0x3c0 ? kthread+0xdb/0x110 ? cancel_delayed_work+0x90/0x90 ? kthread_stop+0x70/0x70 ? ret_from_fork+0x19/0x24 Fixes: ace45bec6d77 ("rxrpc: Fix firewall route keepalive") Reported-by: kernel test robot <lkp@intel.com> Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-08 17:30:02 +07:00
static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet,
struct list_head *collector,
time64_t base,
u8 cursor)
{
struct rxrpc_peer *peer;
rxrpc: Fix the keepalive generator [ver #2] AF_RXRPC has a keepalive message generator that generates a message for a peer ~20s after the last transmission to that peer to keep firewall ports open. The implementation is incorrect in the following ways: (1) It mixes up ktime_t and time64_t types. (2) It uses ktime_get_real(), the output of which may jump forward or backward due to adjustments to the time of day. (3) If the current time jumps forward too much or jumps backwards, the generator function will crank the base of the time ring round one slot at a time (ie. a 1s period) until it catches up, spewing out VERSION packets as it goes. Fix the problem by: (1) Only using time64_t. There's no need for sub-second resolution. (2) Use ktime_get_seconds() rather than ktime_get_real() so that time isn't perceived to go backwards. (3) Simplifying rxrpc_peer_keepalive_worker() by splitting it into two parts: (a) The "worker" function that manages the buckets and the timer. (b) The "dispatch" function that takes the pending peers and potentially transmits a keepalive packet before putting them back in the ring into the slot appropriate to the revised last-Tx time. (4) Taking everything that's pending out of the ring and splicing it into a temporary collector list for processing. In the case that there's been a significant jump forward, the ring gets entirely emptied and then the time base can be warped forward before the peers are processed. The warping can't happen if the ring isn't empty because the slot a peer is in is keepalive-time dependent, relative to the base time. (5) Limit the number of iterations of the bucket array when scanning it. (6) Set the timer to skip any empty slots as there's no point waking up if there's nothing to do yet. This can be triggered by an incoming call from a server after a reboot with AF_RXRPC and AFS built into the kernel causing a peer record to be set up before userspace is started. The system clock is then adjusted by userspace, thereby potentially causing the keepalive generator to have a meltdown - which leads to a message like: watchdog: BUG: soft lockup - CPU#0 stuck for 23s! [kworker/0:1:23] ... Workqueue: krxrpcd rxrpc_peer_keepalive_worker EIP: lock_acquire+0x69/0x80 ... Call Trace: ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? _raw_spin_lock_bh+0x29/0x60 ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? __lock_acquire+0x3d3/0x870 ? process_one_work+0x110/0x340 ? process_one_work+0x166/0x340 ? process_one_work+0x110/0x340 ? worker_thread+0x39/0x3c0 ? kthread+0xdb/0x110 ? cancel_delayed_work+0x90/0x90 ? kthread_stop+0x70/0x70 ? ret_from_fork+0x19/0x24 Fixes: ace45bec6d77 ("rxrpc: Fix firewall route keepalive") Reported-by: kernel test robot <lkp@intel.com> Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-08 17:30:02 +07:00
const u8 mask = ARRAY_SIZE(rxnet->peer_keepalive) - 1;
time64_t keepalive_at;
int slot;
rxrpc: Fix the keepalive generator [ver #2] AF_RXRPC has a keepalive message generator that generates a message for a peer ~20s after the last transmission to that peer to keep firewall ports open. The implementation is incorrect in the following ways: (1) It mixes up ktime_t and time64_t types. (2) It uses ktime_get_real(), the output of which may jump forward or backward due to adjustments to the time of day. (3) If the current time jumps forward too much or jumps backwards, the generator function will crank the base of the time ring round one slot at a time (ie. a 1s period) until it catches up, spewing out VERSION packets as it goes. Fix the problem by: (1) Only using time64_t. There's no need for sub-second resolution. (2) Use ktime_get_seconds() rather than ktime_get_real() so that time isn't perceived to go backwards. (3) Simplifying rxrpc_peer_keepalive_worker() by splitting it into two parts: (a) The "worker" function that manages the buckets and the timer. (b) The "dispatch" function that takes the pending peers and potentially transmits a keepalive packet before putting them back in the ring into the slot appropriate to the revised last-Tx time. (4) Taking everything that's pending out of the ring and splicing it into a temporary collector list for processing. In the case that there's been a significant jump forward, the ring gets entirely emptied and then the time base can be warped forward before the peers are processed. The warping can't happen if the ring isn't empty because the slot a peer is in is keepalive-time dependent, relative to the base time. (5) Limit the number of iterations of the bucket array when scanning it. (6) Set the timer to skip any empty slots as there's no point waking up if there's nothing to do yet. This can be triggered by an incoming call from a server after a reboot with AF_RXRPC and AFS built into the kernel causing a peer record to be set up before userspace is started. The system clock is then adjusted by userspace, thereby potentially causing the keepalive generator to have a meltdown - which leads to a message like: watchdog: BUG: soft lockup - CPU#0 stuck for 23s! [kworker/0:1:23] ... Workqueue: krxrpcd rxrpc_peer_keepalive_worker EIP: lock_acquire+0x69/0x80 ... Call Trace: ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? _raw_spin_lock_bh+0x29/0x60 ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? __lock_acquire+0x3d3/0x870 ? process_one_work+0x110/0x340 ? process_one_work+0x166/0x340 ? process_one_work+0x110/0x340 ? worker_thread+0x39/0x3c0 ? kthread+0xdb/0x110 ? cancel_delayed_work+0x90/0x90 ? kthread_stop+0x70/0x70 ? ret_from_fork+0x19/0x24 Fixes: ace45bec6d77 ("rxrpc: Fix firewall route keepalive") Reported-by: kernel test robot <lkp@intel.com> Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-08 17:30:02 +07:00
spin_lock_bh(&rxnet->peer_hash_lock);
rxrpc: Fix the keepalive generator [ver #2] AF_RXRPC has a keepalive message generator that generates a message for a peer ~20s after the last transmission to that peer to keep firewall ports open. The implementation is incorrect in the following ways: (1) It mixes up ktime_t and time64_t types. (2) It uses ktime_get_real(), the output of which may jump forward or backward due to adjustments to the time of day. (3) If the current time jumps forward too much or jumps backwards, the generator function will crank the base of the time ring round one slot at a time (ie. a 1s period) until it catches up, spewing out VERSION packets as it goes. Fix the problem by: (1) Only using time64_t. There's no need for sub-second resolution. (2) Use ktime_get_seconds() rather than ktime_get_real() so that time isn't perceived to go backwards. (3) Simplifying rxrpc_peer_keepalive_worker() by splitting it into two parts: (a) The "worker" function that manages the buckets and the timer. (b) The "dispatch" function that takes the pending peers and potentially transmits a keepalive packet before putting them back in the ring into the slot appropriate to the revised last-Tx time. (4) Taking everything that's pending out of the ring and splicing it into a temporary collector list for processing. In the case that there's been a significant jump forward, the ring gets entirely emptied and then the time base can be warped forward before the peers are processed. The warping can't happen if the ring isn't empty because the slot a peer is in is keepalive-time dependent, relative to the base time. (5) Limit the number of iterations of the bucket array when scanning it. (6) Set the timer to skip any empty slots as there's no point waking up if there's nothing to do yet. This can be triggered by an incoming call from a server after a reboot with AF_RXRPC and AFS built into the kernel causing a peer record to be set up before userspace is started. The system clock is then adjusted by userspace, thereby potentially causing the keepalive generator to have a meltdown - which leads to a message like: watchdog: BUG: soft lockup - CPU#0 stuck for 23s! [kworker/0:1:23] ... Workqueue: krxrpcd rxrpc_peer_keepalive_worker EIP: lock_acquire+0x69/0x80 ... Call Trace: ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? _raw_spin_lock_bh+0x29/0x60 ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? __lock_acquire+0x3d3/0x870 ? process_one_work+0x110/0x340 ? process_one_work+0x166/0x340 ? process_one_work+0x110/0x340 ? worker_thread+0x39/0x3c0 ? kthread+0xdb/0x110 ? cancel_delayed_work+0x90/0x90 ? kthread_stop+0x70/0x70 ? ret_from_fork+0x19/0x24 Fixes: ace45bec6d77 ("rxrpc: Fix firewall route keepalive") Reported-by: kernel test robot <lkp@intel.com> Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-08 17:30:02 +07:00
while (!list_empty(collector)) {
peer = list_entry(collector->next,
struct rxrpc_peer, keepalive_link);
rxrpc: Fix the keepalive generator [ver #2] AF_RXRPC has a keepalive message generator that generates a message for a peer ~20s after the last transmission to that peer to keep firewall ports open. The implementation is incorrect in the following ways: (1) It mixes up ktime_t and time64_t types. (2) It uses ktime_get_real(), the output of which may jump forward or backward due to adjustments to the time of day. (3) If the current time jumps forward too much or jumps backwards, the generator function will crank the base of the time ring round one slot at a time (ie. a 1s period) until it catches up, spewing out VERSION packets as it goes. Fix the problem by: (1) Only using time64_t. There's no need for sub-second resolution. (2) Use ktime_get_seconds() rather than ktime_get_real() so that time isn't perceived to go backwards. (3) Simplifying rxrpc_peer_keepalive_worker() by splitting it into two parts: (a) The "worker" function that manages the buckets and the timer. (b) The "dispatch" function that takes the pending peers and potentially transmits a keepalive packet before putting them back in the ring into the slot appropriate to the revised last-Tx time. (4) Taking everything that's pending out of the ring and splicing it into a temporary collector list for processing. In the case that there's been a significant jump forward, the ring gets entirely emptied and then the time base can be warped forward before the peers are processed. The warping can't happen if the ring isn't empty because the slot a peer is in is keepalive-time dependent, relative to the base time. (5) Limit the number of iterations of the bucket array when scanning it. (6) Set the timer to skip any empty slots as there's no point waking up if there's nothing to do yet. This can be triggered by an incoming call from a server after a reboot with AF_RXRPC and AFS built into the kernel causing a peer record to be set up before userspace is started. The system clock is then adjusted by userspace, thereby potentially causing the keepalive generator to have a meltdown - which leads to a message like: watchdog: BUG: soft lockup - CPU#0 stuck for 23s! [kworker/0:1:23] ... Workqueue: krxrpcd rxrpc_peer_keepalive_worker EIP: lock_acquire+0x69/0x80 ... Call Trace: ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? _raw_spin_lock_bh+0x29/0x60 ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? __lock_acquire+0x3d3/0x870 ? process_one_work+0x110/0x340 ? process_one_work+0x166/0x340 ? process_one_work+0x110/0x340 ? worker_thread+0x39/0x3c0 ? kthread+0xdb/0x110 ? cancel_delayed_work+0x90/0x90 ? kthread_stop+0x70/0x70 ? ret_from_fork+0x19/0x24 Fixes: ace45bec6d77 ("rxrpc: Fix firewall route keepalive") Reported-by: kernel test robot <lkp@intel.com> Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-08 17:30:02 +07:00
list_del_init(&peer->keepalive_link);
if (!rxrpc_get_peer_maybe(peer))
continue;
if (__rxrpc_use_local(peer->local)) {
spin_unlock_bh(&rxnet->peer_hash_lock);
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;
}
rxrpc: Fix the keepalive generator [ver #2] AF_RXRPC has a keepalive message generator that generates a message for a peer ~20s after the last transmission to that peer to keep firewall ports open. The implementation is incorrect in the following ways: (1) It mixes up ktime_t and time64_t types. (2) It uses ktime_get_real(), the output of which may jump forward or backward due to adjustments to the time of day. (3) If the current time jumps forward too much or jumps backwards, the generator function will crank the base of the time ring round one slot at a time (ie. a 1s period) until it catches up, spewing out VERSION packets as it goes. Fix the problem by: (1) Only using time64_t. There's no need for sub-second resolution. (2) Use ktime_get_seconds() rather than ktime_get_real() so that time isn't perceived to go backwards. (3) Simplifying rxrpc_peer_keepalive_worker() by splitting it into two parts: (a) The "worker" function that manages the buckets and the timer. (b) The "dispatch" function that takes the pending peers and potentially transmits a keepalive packet before putting them back in the ring into the slot appropriate to the revised last-Tx time. (4) Taking everything that's pending out of the ring and splicing it into a temporary collector list for processing. In the case that there's been a significant jump forward, the ring gets entirely emptied and then the time base can be warped forward before the peers are processed. The warping can't happen if the ring isn't empty because the slot a peer is in is keepalive-time dependent, relative to the base time. (5) Limit the number of iterations of the bucket array when scanning it. (6) Set the timer to skip any empty slots as there's no point waking up if there's nothing to do yet. This can be triggered by an incoming call from a server after a reboot with AF_RXRPC and AFS built into the kernel causing a peer record to be set up before userspace is started. The system clock is then adjusted by userspace, thereby potentially causing the keepalive generator to have a meltdown - which leads to a message like: watchdog: BUG: soft lockup - CPU#0 stuck for 23s! [kworker/0:1:23] ... Workqueue: krxrpcd rxrpc_peer_keepalive_worker EIP: lock_acquire+0x69/0x80 ... Call Trace: ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? _raw_spin_lock_bh+0x29/0x60 ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? __lock_acquire+0x3d3/0x870 ? process_one_work+0x110/0x340 ? process_one_work+0x166/0x340 ? process_one_work+0x110/0x340 ? worker_thread+0x39/0x3c0 ? kthread+0xdb/0x110 ? cancel_delayed_work+0x90/0x90 ? kthread_stop+0x70/0x70 ? ret_from_fork+0x19/0x24 Fixes: ace45bec6d77 ("rxrpc: Fix firewall route keepalive") Reported-by: kernel test robot <lkp@intel.com> Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-08 17:30:02 +07:00
/* 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_unuse_local(peer->local);
}
rxrpc: Fix potential deadlock There is a potential deadlock in rxrpc_peer_keepalive_dispatch() whereby rxrpc_put_peer() is called with the peer_hash_lock held, but if it reduces the peer's refcount to 0, rxrpc_put_peer() calls __rxrpc_put_peer() - which the tries to take the already held lock. Fix this by providing a version of rxrpc_put_peer() that can be called in situations where the lock is already held. The bug may produce the following lockdep report: ============================================ WARNING: possible recursive locking detected 5.2.0-next-20190718 #41 Not tainted -------------------------------------------- kworker/0:3/21678 is trying to acquire lock: 00000000aa5eecdf (&(&rxnet->peer_hash_lock)->rlock){+.-.}, at: spin_lock_bh /./include/linux/spinlock.h:343 [inline] 00000000aa5eecdf (&(&rxnet->peer_hash_lock)->rlock){+.-.}, at: __rxrpc_put_peer /net/rxrpc/peer_object.c:415 [inline] 00000000aa5eecdf (&(&rxnet->peer_hash_lock)->rlock){+.-.}, at: rxrpc_put_peer+0x2d3/0x6a0 /net/rxrpc/peer_object.c:435 but task is already holding lock: 00000000aa5eecdf (&(&rxnet->peer_hash_lock)->rlock){+.-.}, at: spin_lock_bh /./include/linux/spinlock.h:343 [inline] 00000000aa5eecdf (&(&rxnet->peer_hash_lock)->rlock){+.-.}, at: rxrpc_peer_keepalive_dispatch /net/rxrpc/peer_event.c:378 [inline] 00000000aa5eecdf (&(&rxnet->peer_hash_lock)->rlock){+.-.}, at: rxrpc_peer_keepalive_worker+0x6b3/0xd02 /net/rxrpc/peer_event.c:430 Fixes: 330bdcfadcee ("rxrpc: Fix the keepalive generator [ver #2]") Reported-by: syzbot+72af434e4b3417318f84@syzkaller.appspotmail.com Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Marc Dionne <marc.dionne@auristor.com> Reviewed-by: Jeffrey Altman <jaltman@auristor.com>
2019-07-30 20:42:50 +07:00
rxrpc_put_peer_locked(peer);
}
spin_unlock_bh(&rxnet->peer_hash_lock);
rxrpc: Fix the keepalive generator [ver #2] AF_RXRPC has a keepalive message generator that generates a message for a peer ~20s after the last transmission to that peer to keep firewall ports open. The implementation is incorrect in the following ways: (1) It mixes up ktime_t and time64_t types. (2) It uses ktime_get_real(), the output of which may jump forward or backward due to adjustments to the time of day. (3) If the current time jumps forward too much or jumps backwards, the generator function will crank the base of the time ring round one slot at a time (ie. a 1s period) until it catches up, spewing out VERSION packets as it goes. Fix the problem by: (1) Only using time64_t. There's no need for sub-second resolution. (2) Use ktime_get_seconds() rather than ktime_get_real() so that time isn't perceived to go backwards. (3) Simplifying rxrpc_peer_keepalive_worker() by splitting it into two parts: (a) The "worker" function that manages the buckets and the timer. (b) The "dispatch" function that takes the pending peers and potentially transmits a keepalive packet before putting them back in the ring into the slot appropriate to the revised last-Tx time. (4) Taking everything that's pending out of the ring and splicing it into a temporary collector list for processing. In the case that there's been a significant jump forward, the ring gets entirely emptied and then the time base can be warped forward before the peers are processed. The warping can't happen if the ring isn't empty because the slot a peer is in is keepalive-time dependent, relative to the base time. (5) Limit the number of iterations of the bucket array when scanning it. (6) Set the timer to skip any empty slots as there's no point waking up if there's nothing to do yet. This can be triggered by an incoming call from a server after a reboot with AF_RXRPC and AFS built into the kernel causing a peer record to be set up before userspace is started. The system clock is then adjusted by userspace, thereby potentially causing the keepalive generator to have a meltdown - which leads to a message like: watchdog: BUG: soft lockup - CPU#0 stuck for 23s! [kworker/0:1:23] ... Workqueue: krxrpcd rxrpc_peer_keepalive_worker EIP: lock_acquire+0x69/0x80 ... Call Trace: ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? _raw_spin_lock_bh+0x29/0x60 ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? __lock_acquire+0x3d3/0x870 ? process_one_work+0x110/0x340 ? process_one_work+0x166/0x340 ? process_one_work+0x110/0x340 ? worker_thread+0x39/0x3c0 ? kthread+0xdb/0x110 ? cancel_delayed_work+0x90/0x90 ? kthread_stop+0x70/0x70 ? ret_from_fork+0x19/0x24 Fixes: ace45bec6d77 ("rxrpc: Fix firewall route keepalive") Reported-by: kernel test robot <lkp@intel.com> Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-08 17:30:02 +07:00
}
rxrpc: Fix the keepalive generator [ver #2] AF_RXRPC has a keepalive message generator that generates a message for a peer ~20s after the last transmission to that peer to keep firewall ports open. The implementation is incorrect in the following ways: (1) It mixes up ktime_t and time64_t types. (2) It uses ktime_get_real(), the output of which may jump forward or backward due to adjustments to the time of day. (3) If the current time jumps forward too much or jumps backwards, the generator function will crank the base of the time ring round one slot at a time (ie. a 1s period) until it catches up, spewing out VERSION packets as it goes. Fix the problem by: (1) Only using time64_t. There's no need for sub-second resolution. (2) Use ktime_get_seconds() rather than ktime_get_real() so that time isn't perceived to go backwards. (3) Simplifying rxrpc_peer_keepalive_worker() by splitting it into two parts: (a) The "worker" function that manages the buckets and the timer. (b) The "dispatch" function that takes the pending peers and potentially transmits a keepalive packet before putting them back in the ring into the slot appropriate to the revised last-Tx time. (4) Taking everything that's pending out of the ring and splicing it into a temporary collector list for processing. In the case that there's been a significant jump forward, the ring gets entirely emptied and then the time base can be warped forward before the peers are processed. The warping can't happen if the ring isn't empty because the slot a peer is in is keepalive-time dependent, relative to the base time. (5) Limit the number of iterations of the bucket array when scanning it. (6) Set the timer to skip any empty slots as there's no point waking up if there's nothing to do yet. This can be triggered by an incoming call from a server after a reboot with AF_RXRPC and AFS built into the kernel causing a peer record to be set up before userspace is started. The system clock is then adjusted by userspace, thereby potentially causing the keepalive generator to have a meltdown - which leads to a message like: watchdog: BUG: soft lockup - CPU#0 stuck for 23s! [kworker/0:1:23] ... Workqueue: krxrpcd rxrpc_peer_keepalive_worker EIP: lock_acquire+0x69/0x80 ... Call Trace: ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? _raw_spin_lock_bh+0x29/0x60 ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? __lock_acquire+0x3d3/0x870 ? process_one_work+0x110/0x340 ? process_one_work+0x166/0x340 ? process_one_work+0x110/0x340 ? worker_thread+0x39/0x3c0 ? kthread+0xdb/0x110 ? cancel_delayed_work+0x90/0x90 ? kthread_stop+0x70/0x70 ? ret_from_fork+0x19/0x24 Fixes: ace45bec6d77 ("rxrpc: Fix firewall route keepalive") Reported-by: kernel test robot <lkp@intel.com> Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-08 17:30:02 +07:00
/*
* 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);
rxrpc: Fix the keepalive generator [ver #2] AF_RXRPC has a keepalive message generator that generates a message for a peer ~20s after the last transmission to that peer to keep firewall ports open. The implementation is incorrect in the following ways: (1) It mixes up ktime_t and time64_t types. (2) It uses ktime_get_real(), the output of which may jump forward or backward due to adjustments to the time of day. (3) If the current time jumps forward too much or jumps backwards, the generator function will crank the base of the time ring round one slot at a time (ie. a 1s period) until it catches up, spewing out VERSION packets as it goes. Fix the problem by: (1) Only using time64_t. There's no need for sub-second resolution. (2) Use ktime_get_seconds() rather than ktime_get_real() so that time isn't perceived to go backwards. (3) Simplifying rxrpc_peer_keepalive_worker() by splitting it into two parts: (a) The "worker" function that manages the buckets and the timer. (b) The "dispatch" function that takes the pending peers and potentially transmits a keepalive packet before putting them back in the ring into the slot appropriate to the revised last-Tx time. (4) Taking everything that's pending out of the ring and splicing it into a temporary collector list for processing. In the case that there's been a significant jump forward, the ring gets entirely emptied and then the time base can be warped forward before the peers are processed. The warping can't happen if the ring isn't empty because the slot a peer is in is keepalive-time dependent, relative to the base time. (5) Limit the number of iterations of the bucket array when scanning it. (6) Set the timer to skip any empty slots as there's no point waking up if there's nothing to do yet. This can be triggered by an incoming call from a server after a reboot with AF_RXRPC and AFS built into the kernel causing a peer record to be set up before userspace is started. The system clock is then adjusted by userspace, thereby potentially causing the keepalive generator to have a meltdown - which leads to a message like: watchdog: BUG: soft lockup - CPU#0 stuck for 23s! [kworker/0:1:23] ... Workqueue: krxrpcd rxrpc_peer_keepalive_worker EIP: lock_acquire+0x69/0x80 ... Call Trace: ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? _raw_spin_lock_bh+0x29/0x60 ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? __lock_acquire+0x3d3/0x870 ? process_one_work+0x110/0x340 ? process_one_work+0x166/0x340 ? process_one_work+0x110/0x340 ? worker_thread+0x39/0x3c0 ? kthread+0xdb/0x110 ? cancel_delayed_work+0x90/0x90 ? kthread_stop+0x70/0x70 ? ret_from_fork+0x19/0x24 Fixes: ace45bec6d77 ("rxrpc: Fix firewall route keepalive") Reported-by: kernel test robot <lkp@intel.com> Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-08 17:30:02 +07:00
now = ktime_get_seconds();
base = rxnet->peer_keepalive_base;
cursor = rxnet->peer_keepalive_cursor;
_enter("%lld,%u", base - now, cursor);
rxrpc: Fix the keepalive generator [ver #2] AF_RXRPC has a keepalive message generator that generates a message for a peer ~20s after the last transmission to that peer to keep firewall ports open. The implementation is incorrect in the following ways: (1) It mixes up ktime_t and time64_t types. (2) It uses ktime_get_real(), the output of which may jump forward or backward due to adjustments to the time of day. (3) If the current time jumps forward too much or jumps backwards, the generator function will crank the base of the time ring round one slot at a time (ie. a 1s period) until it catches up, spewing out VERSION packets as it goes. Fix the problem by: (1) Only using time64_t. There's no need for sub-second resolution. (2) Use ktime_get_seconds() rather than ktime_get_real() so that time isn't perceived to go backwards. (3) Simplifying rxrpc_peer_keepalive_worker() by splitting it into two parts: (a) The "worker" function that manages the buckets and the timer. (b) The "dispatch" function that takes the pending peers and potentially transmits a keepalive packet before putting them back in the ring into the slot appropriate to the revised last-Tx time. (4) Taking everything that's pending out of the ring and splicing it into a temporary collector list for processing. In the case that there's been a significant jump forward, the ring gets entirely emptied and then the time base can be warped forward before the peers are processed. The warping can't happen if the ring isn't empty because the slot a peer is in is keepalive-time dependent, relative to the base time. (5) Limit the number of iterations of the bucket array when scanning it. (6) Set the timer to skip any empty slots as there's no point waking up if there's nothing to do yet. This can be triggered by an incoming call from a server after a reboot with AF_RXRPC and AFS built into the kernel causing a peer record to be set up before userspace is started. The system clock is then adjusted by userspace, thereby potentially causing the keepalive generator to have a meltdown - which leads to a message like: watchdog: BUG: soft lockup - CPU#0 stuck for 23s! [kworker/0:1:23] ... Workqueue: krxrpcd rxrpc_peer_keepalive_worker EIP: lock_acquire+0x69/0x80 ... Call Trace: ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? _raw_spin_lock_bh+0x29/0x60 ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? __lock_acquire+0x3d3/0x870 ? process_one_work+0x110/0x340 ? process_one_work+0x166/0x340 ? process_one_work+0x110/0x340 ? worker_thread+0x39/0x3c0 ? kthread+0xdb/0x110 ? cancel_delayed_work+0x90/0x90 ? kthread_stop+0x70/0x70 ? ret_from_fork+0x19/0x24 Fixes: ace45bec6d77 ("rxrpc: Fix firewall route keepalive") Reported-by: kernel test robot <lkp@intel.com> Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-08 17:30:02 +07:00
if (!rxnet->live)
return;
rxrpc: Fix the keepalive generator [ver #2] AF_RXRPC has a keepalive message generator that generates a message for a peer ~20s after the last transmission to that peer to keep firewall ports open. The implementation is incorrect in the following ways: (1) It mixes up ktime_t and time64_t types. (2) It uses ktime_get_real(), the output of which may jump forward or backward due to adjustments to the time of day. (3) If the current time jumps forward too much or jumps backwards, the generator function will crank the base of the time ring round one slot at a time (ie. a 1s period) until it catches up, spewing out VERSION packets as it goes. Fix the problem by: (1) Only using time64_t. There's no need for sub-second resolution. (2) Use ktime_get_seconds() rather than ktime_get_real() so that time isn't perceived to go backwards. (3) Simplifying rxrpc_peer_keepalive_worker() by splitting it into two parts: (a) The "worker" function that manages the buckets and the timer. (b) The "dispatch" function that takes the pending peers and potentially transmits a keepalive packet before putting them back in the ring into the slot appropriate to the revised last-Tx time. (4) Taking everything that's pending out of the ring and splicing it into a temporary collector list for processing. In the case that there's been a significant jump forward, the ring gets entirely emptied and then the time base can be warped forward before the peers are processed. The warping can't happen if the ring isn't empty because the slot a peer is in is keepalive-time dependent, relative to the base time. (5) Limit the number of iterations of the bucket array when scanning it. (6) Set the timer to skip any empty slots as there's no point waking up if there's nothing to do yet. This can be triggered by an incoming call from a server after a reboot with AF_RXRPC and AFS built into the kernel causing a peer record to be set up before userspace is started. The system clock is then adjusted by userspace, thereby potentially causing the keepalive generator to have a meltdown - which leads to a message like: watchdog: BUG: soft lockup - CPU#0 stuck for 23s! [kworker/0:1:23] ... Workqueue: krxrpcd rxrpc_peer_keepalive_worker EIP: lock_acquire+0x69/0x80 ... Call Trace: ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? _raw_spin_lock_bh+0x29/0x60 ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? __lock_acquire+0x3d3/0x870 ? process_one_work+0x110/0x340 ? process_one_work+0x166/0x340 ? process_one_work+0x110/0x340 ? worker_thread+0x39/0x3c0 ? kthread+0xdb/0x110 ? cancel_delayed_work+0x90/0x90 ? kthread_stop+0x70/0x70 ? ret_from_fork+0x19/0x24 Fixes: ace45bec6d77 ("rxrpc: Fix firewall route keepalive") Reported-by: kernel test robot <lkp@intel.com> Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-08 17:30:02 +07:00
/* 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...
*/
spin_lock_bh(&rxnet->peer_hash_lock);
rxrpc: Fix the keepalive generator [ver #2] AF_RXRPC has a keepalive message generator that generates a message for a peer ~20s after the last transmission to that peer to keep firewall ports open. The implementation is incorrect in the following ways: (1) It mixes up ktime_t and time64_t types. (2) It uses ktime_get_real(), the output of which may jump forward or backward due to adjustments to the time of day. (3) If the current time jumps forward too much or jumps backwards, the generator function will crank the base of the time ring round one slot at a time (ie. a 1s period) until it catches up, spewing out VERSION packets as it goes. Fix the problem by: (1) Only using time64_t. There's no need for sub-second resolution. (2) Use ktime_get_seconds() rather than ktime_get_real() so that time isn't perceived to go backwards. (3) Simplifying rxrpc_peer_keepalive_worker() by splitting it into two parts: (a) The "worker" function that manages the buckets and the timer. (b) The "dispatch" function that takes the pending peers and potentially transmits a keepalive packet before putting them back in the ring into the slot appropriate to the revised last-Tx time. (4) Taking everything that's pending out of the ring and splicing it into a temporary collector list for processing. In the case that there's been a significant jump forward, the ring gets entirely emptied and then the time base can be warped forward before the peers are processed. The warping can't happen if the ring isn't empty because the slot a peer is in is keepalive-time dependent, relative to the base time. (5) Limit the number of iterations of the bucket array when scanning it. (6) Set the timer to skip any empty slots as there's no point waking up if there's nothing to do yet. This can be triggered by an incoming call from a server after a reboot with AF_RXRPC and AFS built into the kernel causing a peer record to be set up before userspace is started. The system clock is then adjusted by userspace, thereby potentially causing the keepalive generator to have a meltdown - which leads to a message like: watchdog: BUG: soft lockup - CPU#0 stuck for 23s! [kworker/0:1:23] ... Workqueue: krxrpcd rxrpc_peer_keepalive_worker EIP: lock_acquire+0x69/0x80 ... Call Trace: ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? _raw_spin_lock_bh+0x29/0x60 ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? __lock_acquire+0x3d3/0x870 ? process_one_work+0x110/0x340 ? process_one_work+0x166/0x340 ? process_one_work+0x110/0x340 ? worker_thread+0x39/0x3c0 ? kthread+0xdb/0x110 ? cancel_delayed_work+0x90/0x90 ? kthread_stop+0x70/0x70 ? ret_from_fork+0x19/0x24 Fixes: ace45bec6d77 ("rxrpc: Fix firewall route keepalive") Reported-by: kernel test robot <lkp@intel.com> Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-08 17:30:02 +07:00
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++;
}
rxrpc: Fix the keepalive generator [ver #2] AF_RXRPC has a keepalive message generator that generates a message for a peer ~20s after the last transmission to that peer to keep firewall ports open. The implementation is incorrect in the following ways: (1) It mixes up ktime_t and time64_t types. (2) It uses ktime_get_real(), the output of which may jump forward or backward due to adjustments to the time of day. (3) If the current time jumps forward too much or jumps backwards, the generator function will crank the base of the time ring round one slot at a time (ie. a 1s period) until it catches up, spewing out VERSION packets as it goes. Fix the problem by: (1) Only using time64_t. There's no need for sub-second resolution. (2) Use ktime_get_seconds() rather than ktime_get_real() so that time isn't perceived to go backwards. (3) Simplifying rxrpc_peer_keepalive_worker() by splitting it into two parts: (a) The "worker" function that manages the buckets and the timer. (b) The "dispatch" function that takes the pending peers and potentially transmits a keepalive packet before putting them back in the ring into the slot appropriate to the revised last-Tx time. (4) Taking everything that's pending out of the ring and splicing it into a temporary collector list for processing. In the case that there's been a significant jump forward, the ring gets entirely emptied and then the time base can be warped forward before the peers are processed. The warping can't happen if the ring isn't empty because the slot a peer is in is keepalive-time dependent, relative to the base time. (5) Limit the number of iterations of the bucket array when scanning it. (6) Set the timer to skip any empty slots as there's no point waking up if there's nothing to do yet. This can be triggered by an incoming call from a server after a reboot with AF_RXRPC and AFS built into the kernel causing a peer record to be set up before userspace is started. The system clock is then adjusted by userspace, thereby potentially causing the keepalive generator to have a meltdown - which leads to a message like: watchdog: BUG: soft lockup - CPU#0 stuck for 23s! [kworker/0:1:23] ... Workqueue: krxrpcd rxrpc_peer_keepalive_worker EIP: lock_acquire+0x69/0x80 ... Call Trace: ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? _raw_spin_lock_bh+0x29/0x60 ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? __lock_acquire+0x3d3/0x870 ? process_one_work+0x110/0x340 ? process_one_work+0x166/0x340 ? process_one_work+0x110/0x340 ? worker_thread+0x39/0x3c0 ? kthread+0xdb/0x110 ? cancel_delayed_work+0x90/0x90 ? kthread_stop+0x70/0x70 ? ret_from_fork+0x19/0x24 Fixes: ace45bec6d77 ("rxrpc: Fix firewall route keepalive") Reported-by: kernel test robot <lkp@intel.com> Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-08 17:30:02 +07:00
base = now;
spin_unlock_bh(&rxnet->peer_hash_lock);
rxnet->peer_keepalive_base = base;
rxnet->peer_keepalive_cursor = cursor;
rxrpc: Fix the keepalive generator [ver #2] AF_RXRPC has a keepalive message generator that generates a message for a peer ~20s after the last transmission to that peer to keep firewall ports open. The implementation is incorrect in the following ways: (1) It mixes up ktime_t and time64_t types. (2) It uses ktime_get_real(), the output of which may jump forward or backward due to adjustments to the time of day. (3) If the current time jumps forward too much or jumps backwards, the generator function will crank the base of the time ring round one slot at a time (ie. a 1s period) until it catches up, spewing out VERSION packets as it goes. Fix the problem by: (1) Only using time64_t. There's no need for sub-second resolution. (2) Use ktime_get_seconds() rather than ktime_get_real() so that time isn't perceived to go backwards. (3) Simplifying rxrpc_peer_keepalive_worker() by splitting it into two parts: (a) The "worker" function that manages the buckets and the timer. (b) The "dispatch" function that takes the pending peers and potentially transmits a keepalive packet before putting them back in the ring into the slot appropriate to the revised last-Tx time. (4) Taking everything that's pending out of the ring and splicing it into a temporary collector list for processing. In the case that there's been a significant jump forward, the ring gets entirely emptied and then the time base can be warped forward before the peers are processed. The warping can't happen if the ring isn't empty because the slot a peer is in is keepalive-time dependent, relative to the base time. (5) Limit the number of iterations of the bucket array when scanning it. (6) Set the timer to skip any empty slots as there's no point waking up if there's nothing to do yet. This can be triggered by an incoming call from a server after a reboot with AF_RXRPC and AFS built into the kernel causing a peer record to be set up before userspace is started. The system clock is then adjusted by userspace, thereby potentially causing the keepalive generator to have a meltdown - which leads to a message like: watchdog: BUG: soft lockup - CPU#0 stuck for 23s! [kworker/0:1:23] ... Workqueue: krxrpcd rxrpc_peer_keepalive_worker EIP: lock_acquire+0x69/0x80 ... Call Trace: ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? _raw_spin_lock_bh+0x29/0x60 ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? rxrpc_peer_keepalive_worker+0x5e/0x350 ? __lock_acquire+0x3d3/0x870 ? process_one_work+0x110/0x340 ? process_one_work+0x166/0x340 ? process_one_work+0x110/0x340 ? worker_thread+0x39/0x3c0 ? kthread+0xdb/0x110 ? cancel_delayed_work+0x90/0x90 ? kthread_stop+0x70/0x70 ? ret_from_fork+0x19/0x24 Fixes: ace45bec6d77 ("rxrpc: Fix firewall route keepalive") Reported-by: kernel test robot <lkp@intel.com> Signed-off-by: David Howells <dhowells@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-08-08 17:30:02 +07:00
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);
_leave("");
}