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, 148 insertions, 0 deletions

diff --git a/net/batman-adv/log.h b/net/batman-adv/log.h
new file mode 100644
index 000000000..9f3aed826
--- /dev/null
+++ b/net/batman-adv/log.h
@@ -0,0 +1,148 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) B.A.T.M.A.N. contributors:
+ *
+ * Marek Lindner, Simon Wunderlich
+ */
+
+#ifndef _NET_BATMAN_ADV_LOG_H_
+#define _NET_BATMAN_ADV_LOG_H_
+
+#include "main.h"
+
+#include <linux/atomic.h>
+#include <linux/bitops.h>
+#include <linux/compiler.h>
+#include <linux/printk.h>
+
+#ifdef CONFIG_BATMAN_ADV_DEBUG
+
+int batadv_debug_log_setup(struct batadv_priv *bat_priv);
+void batadv_debug_log_cleanup(struct batadv_priv *bat_priv);
+
+#else
+
+static inline int batadv_debug_log_setup(struct batadv_priv *bat_priv)
+{
+	return 0;
+}
+
+static inline void batadv_debug_log_cleanup(struct batadv_priv *bat_priv)
+{
+}
+
+#endif
+
+/**
+ * enum batadv_dbg_level - available log levels
+ */
+enum batadv_dbg_level {
+	/** @BATADV_DBG_BATMAN: OGM and TQ computations related messages */
+	BATADV_DBG_BATMAN	= BIT(0),
+
+	/** @BATADV_DBG_ROUTES: route added / changed / deleted */
+	BATADV_DBG_ROUTES	= BIT(1),
+
+	/** @BATADV_DBG_TT: translation table messages */
+	BATADV_DBG_TT		= BIT(2),
+
+	/** @BATADV_DBG_BLA: bridge loop avoidance messages */
+	BATADV_DBG_BLA		= BIT(3),
+
+	/** @BATADV_DBG_DAT: ARP snooping and DAT related messages */
+	BATADV_DBG_DAT		= BIT(4),
+
+	/** @BATADV_DBG_MCAST: multicast related messages */
+	BATADV_DBG_MCAST	= BIT(6),
+
+	/** @BATADV_DBG_TP_METER: throughput meter messages */
+	BATADV_DBG_TP_METER	= BIT(7),
+
+	/** @BATADV_DBG_ALL: the union of all the above log levels */
+	BATADV_DBG_ALL		= 255,
+};
+
+#ifdef CONFIG_BATMAN_ADV_DEBUG
+int batadv_debug_log(struct batadv_priv *bat_priv, const char *fmt, ...)
+__printf(2, 3);
+
+/**
+ * _batadv_dbg() - Store debug output with(out) rate limiting
+ * @type: type of debug message
+ * @bat_priv: the bat priv with all the mesh interface information
+ * @ratelimited: whether output should be rate limited
+ * @fmt: format string
+ * @arg: variable arguments
+ */
+#define _batadv_dbg(type, bat_priv, ratelimited, fmt, arg...)		\
+	do {								\
+		struct batadv_priv *__batpriv = (bat_priv);		\
+		if (READ_ONCE(__batpriv->log_level) & (type) &&	\
+		    (!(ratelimited) || net_ratelimit()))		\
+			batadv_debug_log(__batpriv, fmt, ## arg);	\
+	}								\
+	while (0)
+#else /* !CONFIG_BATMAN_ADV_DEBUG */
+__printf(4, 5)
+static inline void _batadv_dbg(int type __always_unused,
+			       struct batadv_priv *bat_priv __always_unused,
+			       int ratelimited __always_unused,
+			       const char *fmt __always_unused, ...)
+{
+}
+#endif
+
+/**
+ * batadv_dbg() - Store debug output without rate limiting
+ * @type: type of debug message
+ * @bat_priv: the bat priv with all the mesh interface information
+ * @arg: format string and variable arguments
+ */
+#define batadv_dbg(type, bat_priv, arg...) \
+	_batadv_dbg(type, bat_priv, 0, ## arg)
+
+/**
+ * batadv_dbg_ratelimited() - Store debug output with rate limiting
+ * @type: type of debug message
+ * @bat_priv: the bat priv with all the mesh interface information
+ * @arg: format string and variable arguments
+ */
+#define batadv_dbg_ratelimited(type, bat_priv, arg...) \
+	_batadv_dbg(type, bat_priv, 1, ## arg)
+
+/**
+ * batadv_info() - Store message in debug buffer and print it to kmsg buffer
+ * @net_dev: the mesh interface net device
+ * @fmt: format string
+ * @arg: variable arguments
+ */
+#define batadv_info(net_dev, fmt, arg...)				\
+	do {								\
+		struct batadv_priv *_batpriv;				\
+		struct net_device *_netdev;				\
+									\
+		_netdev = (net_dev);					\
+		_batpriv = netdev_priv(_netdev);			\
+									\
+		batadv_dbg(BATADV_DBG_ALL, _batpriv, fmt, ## arg);	\
+		pr_info("%s: " fmt, _netdev->name, ## arg);		\
+	} while (0)
+
+/**
+ * batadv_err() - Store error in debug buffer and print it to kmsg buffer
+ * @net_dev: the mesh interface net device
+ * @fmt: format string
+ * @arg: variable arguments
+ */
+#define batadv_err(net_dev, fmt, arg...)				\
+	do {								\
+		struct batadv_priv *_batpriv;				\
+		struct net_device *_netdev;				\
+									\
+		_netdev = (net_dev);					\
+		_batpriv = netdev_priv(_netdev);			\
+									\
+		batadv_dbg(BATADV_DBG_ALL, _batpriv, fmt, ## arg);	\
+		pr_err("%s: " fmt, _netdev->name, ## arg);		\
+	} while (0)
+
+#endif /* _NET_BATMAN_ADV_LOG_H_ */