linux/net/rxrpc/net_ns.c

131 lines
3.6 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/* rxrpc network namespace handling.
*
* Copyright (C) 2017 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*/
#include <linux/proc_fs.h>
#include "ar-internal.h"
unsigned int rxrpc_net_id;
static void rxrpc_client_conn_reap_timeout(struct timer_list *timer)
{
struct rxrpc_net *rxnet =
container_of(timer, struct rxrpc_net, client_conn_reap_timer);
if (rxnet->live)
rxrpc_queue_work(&rxnet->client_conn_reaper);
}
static void rxrpc_service_conn_reap_timeout(struct timer_list *timer)
{
struct rxrpc_net *rxnet =
container_of(timer, struct rxrpc_net, service_conn_reap_timer);
if (rxnet->live)
rxrpc_queue_work(&rxnet->service_conn_reaper);
}
static void rxrpc_peer_keepalive_timeout(struct timer_list *timer)
{
struct rxrpc_net *rxnet =
container_of(timer, struct rxrpc_net, peer_keepalive_timer);
if (rxnet->live)
rxrpc_queue_work(&rxnet->peer_keepalive_work);
}
/*
* Initialise a per-network namespace record.
*/
static __net_init int rxrpc_init_net(struct net *net)
{
struct rxrpc_net *rxnet = rxrpc_net(net);
int ret, i;
rxnet->live = true;
get_random_bytes(&rxnet->epoch, sizeof(rxnet->epoch));
rxnet->epoch |= RXRPC_RANDOM_EPOCH;
INIT_LIST_HEAD(&rxnet->calls);
rwlock_init(&rxnet->call_lock);
atomic_set(&rxnet->nr_calls, 1);
atomic_set(&rxnet->nr_conns, 1);
INIT_LIST_HEAD(&rxnet->conn_proc_list);
INIT_LIST_HEAD(&rxnet->service_conns);
rwlock_init(&rxnet->conn_lock);
INIT_WORK(&rxnet->service_conn_reaper,
rxrpc_service_connection_reaper);
timer_setup(&rxnet->service_conn_reap_timer,
rxrpc_service_conn_reap_timeout, 0);
rxrpc: Rewrite the client connection manager Rewrite the rxrpc client connection manager so that it can support multiple connections for a given security key to a peer. The following changes are made: (1) For each open socket, the code currently maintains an rbtree with the connections placed into it, keyed by communications parameters. This is tricky to maintain as connections can be culled from the tree or replaced within it. Connections can require replacement for a number of reasons, e.g. their IDs span too great a range for the IDR data type to represent efficiently, the call ID numbers on that conn would overflow or the conn got aborted. This is changed so that there's now a connection bundle object placed in the tree, keyed on the same parameters. The bundle, however, does not need to be replaced. (2) An rxrpc_bundle object can now manage the available channels for a set of parallel connections. The lock that manages this is moved there from the rxrpc_connection struct (channel_lock). (3) There'a a dummy bundle for all incoming connections to share so that they have a channel_lock too. It might be better to give each incoming connection its own bundle. This bundle is not needed to manage which channels incoming calls are made on because that's the solely at whim of the client. (4) The restrictions on how many client connections are around are removed. Instead, a previous patch limits the number of client calls that can be allocated. Ordinarily, client connections are reaped after 2 minutes on the idle queue, but when more than a certain number of connections are in existence, the reaper starts reaping them after 2s of idleness instead to get the numbers back down. It could also be made such that new call allocations are forced to wait until the number of outstanding connections subsides. Signed-off-by: David Howells <dhowells@redhat.com>
2020-07-01 10:15:32 +00:00
atomic_set(&rxnet->nr_client_conns, 0);
rxnet->kill_all_client_conns = false;
spin_lock_init(&rxnet->client_conn_cache_lock);
spin_lock_init(&rxnet->client_conn_discard_lock);
INIT_LIST_HEAD(&rxnet->idle_client_conns);
INIT_WORK(&rxnet->client_conn_reaper,
rxrpc_discard_expired_client_conns);
timer_setup(&rxnet->client_conn_reap_timer,
rxrpc_client_conn_reap_timeout, 0);
INIT_LIST_HEAD(&rxnet->local_endpoints);
mutex_init(&rxnet->local_mutex);
hash_init(rxnet->peer_hash);
spin_lock_init(&rxnet->peer_hash_lock);
for (i = 0; i < ARRAY_SIZE(rxnet->peer_keepalive); i++)
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 10:30:02 +00:00
INIT_LIST_HEAD(&rxnet->peer_keepalive[i]);
INIT_LIST_HEAD(&rxnet->peer_keepalive_new);
timer_setup(&rxnet->peer_keepalive_timer,
rxrpc_peer_keepalive_timeout, 0);
INIT_WORK(&rxnet->peer_keepalive_work, rxrpc_peer_keepalive_worker);
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 10:30:02 +00:00
rxnet->peer_keepalive_base = ktime_get_seconds();
ret = -ENOMEM;
rxnet->proc_net = proc_net_mkdir(net, "rxrpc", net->proc_net);
if (!rxnet->proc_net)
goto err_proc;
proc_create_net("calls", 0444, rxnet->proc_net, &rxrpc_call_seq_ops,
sizeof(struct seq_net_private));
proc_create_net("conns", 0444, rxnet->proc_net,
&rxrpc_connection_seq_ops,
sizeof(struct seq_net_private));
proc_create_net("peers", 0444, rxnet->proc_net,
&rxrpc_peer_seq_ops,
sizeof(struct seq_net_private));
return 0;
err_proc:
rxnet->live = false;
return ret;
}
/*
* Clean up a per-network namespace record.
*/
static __net_exit void rxrpc_exit_net(struct net *net)
{
struct rxrpc_net *rxnet = rxrpc_net(net);
rxnet->live = false;
del_timer_sync(&rxnet->peer_keepalive_timer);
cancel_work_sync(&rxnet->peer_keepalive_work);
rxrpc_destroy_all_calls(rxnet);
rxrpc_destroy_all_connections(rxnet);
rxrpc_destroy_all_peers(rxnet);
rxrpc_destroy_all_locals(rxnet);
proc_remove(rxnet->proc_net);
}
struct pernet_operations rxrpc_net_ops = {
.init = rxrpc_init_net,
.exit = rxrpc_exit_net,
.id = &rxrpc_net_id,
.size = sizeof(struct rxrpc_net),
};