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, 94 insertions, 0 deletions

diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c
new file mode 100644
index 000000000..0b39046bd
--- /dev/null
+++ b/net/rxrpc/insecure.c
@@ -0,0 +1,94 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Null security operations.
+ *
+ * Copyright (C) 2016 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <net/af_rxrpc.h>
+#include "ar-internal.h"
+
+static int none_init_connection_security(struct rxrpc_connection *conn,
+					 struct rxrpc_key_token *token)
+{
+	return 0;
+}
+
+/*
+ * Allocate an appropriately sized buffer for the amount of data remaining.
+ */
+static struct rxrpc_txbuf *none_alloc_txbuf(struct rxrpc_call *call, size_t remain, gfp_t gfp)
+{
+	return rxrpc_alloc_data_txbuf(call, umin(remain, RXRPC_JUMBO_DATALEN), 1, gfp);
+}
+
+static int none_secure_packet(struct rxrpc_call *call, struct rxrpc_txbuf *txb)
+{
+	txb->pkt_len = txb->len;
+	if (txb->len == RXRPC_JUMBO_DATALEN)
+		txb->jumboable = true;
+	return 0;
+}
+
+static int none_verify_packet(struct rxrpc_call *call, struct sk_buff *skb)
+{
+	return 0;
+}
+
+static void none_free_call_crypto(struct rxrpc_call *call)
+{
+}
+
+static bool none_validate_challenge(struct rxrpc_connection *conn,
+				    struct sk_buff *skb)
+{
+	rxrpc_abort_conn(conn, skb, RX_PROTOCOL_ERROR, -EPROTO,
+			 rxrpc_eproto_rxnull_challenge);
+	return true;
+}
+
+static int none_sendmsg_respond_to_challenge(struct sk_buff *challenge,
+					     struct msghdr *msg)
+{
+	return -EINVAL;
+}
+
+static int none_verify_response(struct rxrpc_connection *conn,
+				struct sk_buff *response_skb,
+				void *response, unsigned int len)
+{
+	return rxrpc_abort_conn(conn, response_skb, RX_PROTOCOL_ERROR, -EPROTO,
+				rxrpc_eproto_rxnull_response);
+}
+
+static void none_clear(struct rxrpc_connection *conn)
+{
+}
+
+static int none_init(void)
+{
+	return 0;
+}
+
+static void none_exit(void)
+{
+}
+
+/*
+ * RxRPC Kerberos-based security
+ */
+const struct rxrpc_security rxrpc_no_security = {
+	.name				= "none",
+	.security_index			= RXRPC_SECURITY_NONE,
+	.init				= none_init,
+	.exit				= none_exit,
+	.init_connection_security	= none_init_connection_security,
+	.free_call_crypto		= none_free_call_crypto,
+	.alloc_txbuf			= none_alloc_txbuf,
+	.secure_packet			= none_secure_packet,
+	.verify_packet			= none_verify_packet,
+	.validate_challenge		= none_validate_challenge,
+	.sendmsg_respond_to_challenge	= none_sendmsg_respond_to_challenge,
+	.verify_response		= none_verify_response,
+	.clear				= none_clear,
+};