x86/kprobes: Fix crash when probing CS CALL instructionsgrafted

When using eBPF to probe CS CALL instructions within a function,
a crash can be triggered.

The eBPF tool probes offset 257 of the __hrtimer_run_queues()
function:

<__hrtimer_run_queues+249>:  nopl   0x0(%rax,%rax,1)
<__hrtimer_run_queues+254>:  mov    %r14,%rdi
<__hrtimer_run_queues+257>:  cs call <__x86_indirect_thunk_r12>
<__hrtimer_run_queues+263>:  mov    %eax,%r12d
<__hrtimer_run_queues+266>:  xchg   %ax,%ax
<__hrtimer_run_queues+268>:  mov    %r13,%rdi

Which triggers this crash:

  BUG: unable to handle page fault for address: 00000000000f41c9
  #PF: supervisor write access in kernel mode
  #PF: error_code(0x0002) - not-present page
  PGD 0 P4D 0
  Oops: 0002 [#1] SMP NOPTI
  CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P
  RIP: 0010:__hrtimer_run_queues+0x106/0x230

Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is
at the 6th byte of the above CS CALL instruction. Since the CS CALL
instruction occupies 6 bytes, the exception occurred in the middle of that
call instruction.

The root cause is that when using eBPF tools to probe in the middle of a
function, a kprobe with INT3 is used as the underlying implementation.

During single-step emulation of the original CALL instruction,
int3_emulate_call() assumes that the probed CALL instruction is 5 bytes
long. However, the actual CS-prefixed CALL instruction occupies 6 bytes,
so it constructs an incorrect exception return address. When the CPU
returns from the kprobe handler, the next instruction to be executed is at
the address of the last byte of that CS CALL instruction. Coincidentally,
starting from that address, the CPU fetches and decodes a completely
different instruction, which ultimately triggers a kernel crash.

Fix the issue by using the actual instruction length obtained from
the instruction decoder when constructing the exception return
address, rather than relying on the hardcoded CALL_INSN_SIZE macro.

[ mingo: Refined the changelog ]

Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step")
Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Jinke Han <jinkehan@didiglobal.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000

1 files changed, 124 insertions, 0 deletions

diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c
new file mode 100644
index 000000000..9a9834145
--- /dev/null
+++ b/net/rxrpc/net_ns.c
@@ -0,0 +1,124 @@
+// 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_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);
+	spin_lock_init(&rxnet->call_lock);
+	atomic_set(&rxnet->nr_calls, 1);
+
+	atomic_set(&rxnet->nr_conns, 1);
+	INIT_LIST_HEAD(&rxnet->bundle_proc_list);
+	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);
+
+	atomic_set(&rxnet->nr_client_conns, 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++)
+		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);
+	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("bundles", 0444, rxnet->proc_net,
+			&rxrpc_bundle_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;
+	timer_delete_sync(&rxnet->peer_keepalive_timer);
+	cancel_work_sync(&rxnet->peer_keepalive_work);
+	/* Remove the timer again as the worker may have restarted it. */
+	timer_delete_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),
+};