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, 138 insertions, 0 deletions

diff --git a/drivers/regulator/internal.h b/drivers/regulator/internal.h
new file mode 100644
index 000000000..b3d48dc38
--- /dev/null
+++ b/drivers/regulator/internal.h
@@ -0,0 +1,138 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * internal.h  --  Voltage/Current Regulator framework internal code
+ *
+ * Copyright 2007, 2008 Wolfson Microelectronics PLC.
+ * Copyright 2008 SlimLogic Ltd.
+ *
+ * Author: Liam Girdwood <lrg@slimlogic.co.uk>
+ */
+
+#ifndef __REGULATOR_INTERNAL_H
+#define __REGULATOR_INTERNAL_H
+
+#include <linux/suspend.h>
+
+#define REGULATOR_STATES_NUM	(PM_SUSPEND_MAX + 1)
+
+#define rdev_crit(rdev, fmt, ...)					\
+	pr_crit("%s: " fmt, rdev_get_name(rdev), ##__VA_ARGS__)
+#define rdev_err(rdev, fmt, ...)					\
+	pr_err("%s: " fmt, rdev_get_name(rdev), ##__VA_ARGS__)
+#define rdev_warn(rdev, fmt, ...)					\
+	pr_warn("%s: " fmt, rdev_get_name(rdev), ##__VA_ARGS__)
+#define rdev_info(rdev, fmt, ...)					\
+	pr_info("%s: " fmt, rdev_get_name(rdev), ##__VA_ARGS__)
+#define rdev_dbg(rdev, fmt, ...)					\
+	pr_debug("%s: " fmt, rdev_get_name(rdev), ##__VA_ARGS__)
+
+struct regulator_voltage {
+	int min_uV;
+	int max_uV;
+};
+
+/*
+ * struct regulator
+ *
+ * One for each consumer device.
+ * @voltage - a voltage array for each state of runtime, i.e.:
+ *            PM_SUSPEND_ON
+ *            PM_SUSPEND_TO_IDLE
+ *            PM_SUSPEND_STANDBY
+ *            PM_SUSPEND_MEM
+ *            PM_SUSPEND_MAX
+ */
+struct regulator {
+	struct device *dev;
+	struct list_head list;
+	unsigned int always_on:1;
+	unsigned int bypass:1;
+	unsigned int device_link:1;
+	int uA_load;
+	unsigned int enable_count;
+	unsigned int deferred_disables;
+	struct regulator_voltage voltage[REGULATOR_STATES_NUM];
+	const char *supply_name;
+	struct device_attribute dev_attr;
+	struct regulator_dev *rdev;
+	struct dentry *debugfs;
+};
+
+extern const struct class regulator_class;
+
+static inline struct regulator_dev *dev_to_rdev(struct device *dev)
+{
+	return container_of(dev, struct regulator_dev, dev);
+}
+
+enum regulator_get_type {
+	NORMAL_GET,
+	EXCLUSIVE_GET,
+	OPTIONAL_GET,
+	MAX_GET_TYPE
+};
+
+#ifdef CONFIG_OF
+struct regulator_dev *of_regulator_dev_lookup(struct device *dev,
+					      struct device_node *np,
+					      const char *supply);
+struct regulator_init_data *regulator_of_get_init_data(struct device *dev,
+			         const struct regulator_desc *desc,
+				 struct regulator_config *config,
+				 struct device_node **node);
+
+struct regulator *_of_regulator_get(struct device *dev, struct device_node *node,
+				    const char *id, enum regulator_get_type get_type);
+
+struct regulator_dev *of_parse_coupled_regulator(struct regulator_dev *rdev,
+						 int index);
+
+int of_get_n_coupled(struct regulator_dev *rdev);
+
+bool of_check_coupling_data(struct regulator_dev *rdev);
+
+#else
+static inline struct regulator_dev *of_regulator_dev_lookup(struct device *dev,
+							    struct device_node *np,
+							    const char *supply)
+{
+	return ERR_PTR(-ENODEV);
+}
+
+static inline struct regulator_init_data *
+regulator_of_get_init_data(struct device *dev,
+			   const struct regulator_desc *desc,
+			   struct regulator_config *config,
+			   struct device_node **node)
+{
+	return NULL;
+}
+
+static inline struct regulator_dev *
+of_parse_coupled_regulator(struct regulator_dev *rdev,
+			   int index)
+{
+	return NULL;
+}
+
+static inline int of_get_n_coupled(struct regulator_dev *rdev)
+{
+	return 0;
+}
+
+static inline bool of_check_coupling_data(struct regulator_dev *rdev)
+{
+	return false;
+}
+
+#endif
+
+int _regulator_get_common_check(struct device *dev, const char *id,
+				enum regulator_get_type get_type);
+struct regulator *_regulator_get_common(struct regulator_dev *rdev, struct device *dev,
+					const char *id, enum regulator_get_type get_type);
+struct regulator *_regulator_get(struct device *dev, const char *id,
+				 enum regulator_get_type get_type);
+int _regulator_bulk_get(struct device *dev, int num_consumers,
+			struct regulator_bulk_data *consumers, enum regulator_get_type get_type);
+#endif