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, 86 insertions, 0 deletions

diff --git a/drivers/net/wireguard/peer.h b/drivers/net/wireguard/peer.h
new file mode 100644
index 000000000..718fb42bd
--- /dev/null
+++ b/drivers/net/wireguard/peer.h
@@ -0,0 +1,86 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#ifndef _WG_PEER_H
+#define _WG_PEER_H
+
+#include "device.h"
+#include "noise.h"
+#include "cookie.h"
+
+#include <linux/types.h>
+#include <linux/netfilter.h>
+#include <linux/spinlock.h>
+#include <linux/kref.h>
+#include <net/dst_cache.h>
+
+struct wg_device;
+
+struct endpoint {
+	union {
+		struct sockaddr_inet addr;     /* Large enough for both address families */
+		struct sockaddr_in addr4;
+		struct sockaddr_in6 addr6;
+	};
+	union {
+		struct {
+			struct in_addr src4;
+			/* Essentially the same as addr6->scope_id */
+			int src_if4;
+		};
+		struct in6_addr src6;
+	};
+};
+
+struct wg_peer {
+	struct wg_device *device;
+	struct prev_queue tx_queue, rx_queue;
+	struct sk_buff_head staged_packet_queue;
+	int serial_work_cpu;
+	bool is_dead;
+	struct noise_keypairs keypairs;
+	struct endpoint endpoint;
+	struct dst_cache endpoint_cache;
+	rwlock_t endpoint_lock;
+	struct noise_handshake handshake;
+	atomic64_t last_sent_handshake;
+	struct work_struct transmit_handshake_work, clear_peer_work, transmit_packet_work;
+	struct cookie latest_cookie;
+	struct hlist_node pubkey_hash;
+	u64 rx_bytes, tx_bytes;
+	struct timer_list timer_retransmit_handshake, timer_send_keepalive;
+	struct timer_list timer_new_handshake, timer_zero_key_material;
+	struct timer_list timer_persistent_keepalive;
+	unsigned int timer_handshake_attempts;
+	u16 persistent_keepalive_interval;
+	bool timer_need_another_keepalive;
+	bool sent_lastminute_handshake;
+	struct timespec64 walltime_last_handshake;
+	struct kref refcount;
+	struct rcu_head rcu;
+	struct list_head peer_list;
+	struct list_head allowedips_list;
+	struct napi_struct napi;
+	u64 internal_id;
+};
+
+struct wg_peer *wg_peer_create(struct wg_device *wg,
+			       const u8 public_key[NOISE_PUBLIC_KEY_LEN],
+			       const u8 preshared_key[NOISE_SYMMETRIC_KEY_LEN]);
+
+struct wg_peer *__must_check wg_peer_get_maybe_zero(struct wg_peer *peer);
+static inline struct wg_peer *wg_peer_get(struct wg_peer *peer)
+{
+	kref_get(&peer->refcount);
+	return peer;
+}
+void wg_peer_put(struct wg_peer *peer);
+void wg_peer_remove(struct wg_peer *peer);
+void wg_peer_remove_all(struct wg_device *wg);
+
+int wg_peer_init(void);
+void wg_peer_uninit(void);
+
+#endif /* _WG_PEER_H */