OpenCloudOS-Kernel/net/rxrpc/net_ns.c

138 lines
3.9 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);
rxrpc: Fix locking issue There's a locking issue with the per-netns list of calls in rxrpc. The pieces of code that add and remove a call from the list use write_lock() and the calls procfile uses read_lock() to access it. However, the timer callback function may trigger a removal by trying to queue a call for processing and finding that it's already queued - at which point it has a spare refcount that it has to do something with. Unfortunately, if it puts the call and this reduces the refcount to 0, the call will be removed from the list. Unfortunately, since the _bh variants of the locking functions aren't used, this can deadlock. ================================ WARNING: inconsistent lock state 5.18.0-rc3-build4+ #10 Not tainted -------------------------------- inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage. ksoftirqd/2/25 [HC0[0]:SC1[1]:HE1:SE0] takes: ffff888107ac4038 (&rxnet->call_lock){+.?.}-{2:2}, at: rxrpc_put_call+0x103/0x14b {SOFTIRQ-ON-W} state was registered at: ... Possible unsafe locking scenario: CPU0 ---- lock(&rxnet->call_lock); <Interrupt> lock(&rxnet->call_lock); *** DEADLOCK *** 1 lock held by ksoftirqd/2/25: #0: ffff8881008ffdb0 ((&call->timer)){+.-.}-{0:0}, at: call_timer_fn+0x5/0x23d Changes ======= ver #2) - Changed to using list_next_rcu() rather than rcu_dereference() directly. Fixes: 17926a79320a ("[AF_RXRPC]: Provide secure RxRPC sockets for use by userspace and kernel both") Signed-off-by: David Howells <dhowells@redhat.com> cc: Marc Dionne <marc.dionne@auristor.com> cc: linux-afs@lists.infradead.org Signed-off-by: David S. Miller <davem@davemloft.net>
2022-05-21 15:45:28 +08:00
spin_lock_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 18:15:32 +08:00
atomic_set(&rxnet->nr_client_conns, 0);
rxnet->kill_all_client_conns = false;
spin_lock_init(&rxnet->client_conn_cache_lock);
rxrpc: Don't hold a ref for connection workqueue Currently, rxrpc gives the connection's work item a ref on the connection when it queues it - and this is called from the timer expiration function. The problem comes when queue_work() fails (ie. the work item is already queued): the timer routine must put the ref - but this may cause the cleanup code to run. This has the unfortunate effect that the cleanup code may then be run in softirq context - which means that any spinlocks it might need to touch have to be guarded to disable softirqs (ie. they need a "_bh" suffix). (1) Don't give a ref to the work item. (2) Simplify handling of service connections by adding a separate active count so that the refcount isn't also used for this. (3) Connection destruction for both client and service connections can then be cleaned up by putting rxrpc_put_connection() out of line and making a tidy progression through the destruction code (offloaded to a workqueue if put from softirq or processor function context). The RCU part of the cleanup then only deals with the freeing at the end. (4) Make rxrpc_queue_conn() return immediately if it sees the active count is -1 rather then queuing the connection. (5) Make sure that the cleanup routine waits for the work item to complete. (6) Stash the rxrpc_net pointer in the conn struct so that the rcu free routine can use it, even if the local endpoint has been freed. Unfortunately, neither the timer nor the work item can simply get around the problem by just using refcount_inc_not_zero() as the waits would still have to be done, and there would still be the possibility of having to put the ref in the expiration function. Note the connection work item is mostly going to go away with the main event work being transferred to the I/O thread, so the wait in (6) will become obsolete. Signed-off-by: David Howells <dhowells@redhat.com> cc: Marc Dionne <marc.dionne@auristor.com> cc: linux-afs@lists.infradead.org
2022-11-25 20:43:50 +08:00
mutex_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_HLIST_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 18:30:02 +08:00
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 18:30:02 +08:00
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));
proc_create_net("locals", 0444, rxnet->proc_net,
&rxrpc_local_seq_ops,
sizeof(struct seq_net_private));
proc_create_net_single_write("stats", S_IFREG | 0644, rxnet->proc_net,
rxrpc_stats_show, rxrpc_stats_clear, NULL);
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);
/* Remove the timer again as the worker may have restarted it. */
rxrpc: fix a race in rxrpc_exit_net() Current code can lead to the following race: CPU0 CPU1 rxrpc_exit_net() rxrpc_peer_keepalive_worker() if (rxnet->live) rxnet->live = false; del_timer_sync(&rxnet->peer_keepalive_timer); timer_reduce(&rxnet->peer_keepalive_timer, jiffies + delay); cancel_work_sync(&rxnet->peer_keepalive_work); rxrpc_exit_net() exits while peer_keepalive_timer is still armed, leading to use-after-free. syzbot report was: ODEBUG: free active (active state 0) object type: timer_list hint: rxrpc_peer_keepalive_timeout+0x0/0xb0 WARNING: CPU: 0 PID: 3660 at lib/debugobjects.c:505 debug_print_object+0x16e/0x250 lib/debugobjects.c:505 Modules linked in: CPU: 0 PID: 3660 Comm: kworker/u4:6 Not tainted 5.17.0-syzkaller-13993-g88e6c0207623 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Workqueue: netns cleanup_net RIP: 0010:debug_print_object+0x16e/0x250 lib/debugobjects.c:505 Code: ff df 48 89 fa 48 c1 ea 03 80 3c 02 00 0f 85 af 00 00 00 48 8b 14 dd 00 1c 26 8a 4c 89 ee 48 c7 c7 00 10 26 8a e8 b1 e7 28 05 <0f> 0b 83 05 15 eb c5 09 01 48 83 c4 18 5b 5d 41 5c 41 5d 41 5e c3 RSP: 0018:ffffc9000353fb00 EFLAGS: 00010082 RAX: 0000000000000000 RBX: 0000000000000003 RCX: 0000000000000000 RDX: ffff888029196140 RSI: ffffffff815efad8 RDI: fffff520006a7f52 RBP: 0000000000000001 R08: 0000000000000000 R09: 0000000000000000 R10: ffffffff815ea4ae R11: 0000000000000000 R12: ffffffff89ce23e0 R13: ffffffff8a2614e0 R14: ffffffff816628c0 R15: dffffc0000000000 FS: 0000000000000000(0000) GS:ffff8880b9c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fe1f2908924 CR3: 0000000043720000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> __debug_check_no_obj_freed lib/debugobjects.c:992 [inline] debug_check_no_obj_freed+0x301/0x420 lib/debugobjects.c:1023 kfree+0xd6/0x310 mm/slab.c:3809 ops_free_list.part.0+0x119/0x370 net/core/net_namespace.c:176 ops_free_list net/core/net_namespace.c:174 [inline] cleanup_net+0x591/0xb00 net/core/net_namespace.c:598 process_one_work+0x996/0x1610 kernel/workqueue.c:2289 worker_thread+0x665/0x1080 kernel/workqueue.c:2436 kthread+0x2e9/0x3a0 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:298 </TASK> Fixes: ace45bec6d77 ("rxrpc: Fix firewall route keepalive") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: David Howells <dhowells@redhat.com> Cc: Marc Dionne <marc.dionne@auristor.com> Cc: linux-afs@lists.infradead.org Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-04-05 02:34:39 +08:00
del_timer_sync(&rxnet->peer_keepalive_timer);
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),
};