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, 214 insertions, 0 deletions

diff --git a/drivers/pinctrl/pinconf.h b/drivers/pinctrl/pinconf.h
new file mode 100644
index 000000000..fc2d6cce9
--- /dev/null
+++ b/drivers/pinctrl/pinconf.h
@@ -0,0 +1,214 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Internal interface between the core pin control system and the
+ * pin config portions
+ *
+ * Copyright (C) 2011 ST-Ericsson SA
+ * Written on behalf of Linaro for ST-Ericsson
+ * Based on bits of regulator core, gpio core and clk core
+ *
+ * Author: Linus Walleij <linus.walleij@linaro.org>
+ */
+
+#include <linux/errno.h>
+
+struct dentry;
+struct device_node;
+struct seq_file;
+
+struct pinctrl_dev;
+struct pinctrl_map;
+struct pinctrl_setting;
+
+#ifdef CONFIG_PINCONF
+
+int pinconf_check_ops(struct pinctrl_dev *pctldev);
+int pinconf_validate_map(const struct pinctrl_map *map, int i);
+int pinconf_map_to_setting(const struct pinctrl_map *map,
+			  struct pinctrl_setting *setting);
+void pinconf_free_setting(const struct pinctrl_setting *setting);
+int pinconf_apply_setting(const struct pinctrl_setting *setting);
+
+int pinconf_set_config(struct pinctrl_dev *pctldev, unsigned int pin,
+		       unsigned long *configs, size_t nconfigs);
+
+/*
+ * You will only be interested in these if you're using PINCONF
+ * so don't supply any stubs for these.
+ */
+int pin_config_get_for_pin(struct pinctrl_dev *pctldev, unsigned int pin,
+			   unsigned long *config);
+int pin_config_group_get(const char *dev_name, const char *pin_group,
+			 unsigned long *config);
+
+#else
+
+static inline int pinconf_check_ops(struct pinctrl_dev *pctldev)
+{
+	return 0;
+}
+
+static inline int pinconf_validate_map(const struct pinctrl_map *map, int i)
+{
+	return 0;
+}
+
+static inline int pinconf_map_to_setting(const struct pinctrl_map *map,
+			  struct pinctrl_setting *setting)
+{
+	return 0;
+}
+
+static inline void pinconf_free_setting(const struct pinctrl_setting *setting)
+{
+}
+
+static inline int pinconf_apply_setting(const struct pinctrl_setting *setting)
+{
+	return 0;
+}
+
+static inline int pinconf_set_config(struct pinctrl_dev *pctldev, unsigned int pin,
+				     unsigned long *configs, size_t nconfigs)
+{
+	return -ENOTSUPP;
+}
+
+static inline int pin_config_get_for_pin(struct pinctrl_dev *pctldev, unsigned int pin,
+			   unsigned long *config)
+{
+	return -ENOTSUPP;
+}
+
+#endif
+
+#if defined(CONFIG_PINCONF) && defined(CONFIG_DEBUG_FS)
+
+void pinconf_show_map(struct seq_file *s, const struct pinctrl_map *map);
+void pinconf_show_setting(struct seq_file *s,
+			  const struct pinctrl_setting *setting);
+void pinconf_init_device_debugfs(struct dentry *devroot,
+				 struct pinctrl_dev *pctldev);
+
+#else
+
+static inline void pinconf_show_map(struct seq_file *s,
+				    const struct pinctrl_map *map)
+{
+}
+
+static inline void pinconf_show_setting(struct seq_file *s,
+					const struct pinctrl_setting *setting)
+{
+}
+
+static inline void pinconf_init_device_debugfs(struct dentry *devroot,
+					       struct pinctrl_dev *pctldev)
+{
+}
+
+#endif
+
+/*
+ * The following functions are available if the driver uses the generic
+ * pin config.
+ */
+
+#if defined(CONFIG_GENERIC_PINCONF) && defined(CONFIG_DEBUG_FS)
+
+void pinconf_generic_dump_pins(struct pinctrl_dev *pctldev,
+			       struct seq_file *s, const char *gname,
+			       unsigned int pin);
+
+void pinconf_generic_dump_config(struct pinctrl_dev *pctldev,
+				 struct seq_file *s, unsigned long config);
+#else
+
+static inline void pinconf_generic_dump_pins(struct pinctrl_dev *pctldev,
+					     struct seq_file *s,
+					     const char *gname, unsigned int pin)
+{
+	return;
+}
+
+static inline void pinconf_generic_dump_config(struct pinctrl_dev *pctldev,
+					       struct seq_file *s,
+					       unsigned long config)
+{
+	return;
+}
+#endif
+
+#if defined(CONFIG_GENERIC_PINCONF) && defined(CONFIG_OF)
+int pinconf_generic_parse_dt_config(struct device_node *np,
+				    struct pinctrl_dev *pctldev,
+				    unsigned long **configs,
+				    unsigned int *nconfigs);
+
+int pinconf_generic_parse_dt_pinmux(struct device_node *np, struct device *dev,
+				    unsigned int **pid, unsigned int **pmux,
+				    unsigned int *npins);
+#else
+static inline int
+pinconf_generic_parse_dt_config(struct device_node *np,
+				struct pinctrl_dev *pctldev,
+				unsigned long **configs,
+				unsigned int *nconfigs)
+{
+	return -ENOTSUPP;
+}
+
+static inline int
+pinconf_generic_parse_dt_pinmux(struct device_node *np, struct device *dev,
+				unsigned int **pid, unsigned int **pmux,
+				unsigned int *npins)
+{
+	return -ENOTSUPP;
+}
+#endif
+
+#if defined(CONFIG_GENERIC_PINCTRL)
+int pinctrl_generic_pins_function_dt_node_to_map(struct pinctrl_dev *pctldev,
+						 struct device_node *np,
+						 struct pinctrl_map **maps,
+						 unsigned int *num_maps);
+
+int pinctrl_generic_pinmux_dt_node_to_map(struct pinctrl_dev *pctldev,
+					  struct device_node *np,
+					  struct pinctrl_map **maps,
+					  unsigned int *num_maps);
+
+int pinctrl_generic_to_map(struct pinctrl_dev *pctldev, struct device_node *parent,
+			   struct device_node *np, struct pinctrl_map **maps,
+			   unsigned int *num_maps, unsigned int *num_reserved_maps,
+			   const char **group_name, unsigned int ngroups,
+			   void *data, unsigned int *pins, unsigned int npins);
+#else
+static inline int
+pinctrl_generic_pins_function_dt_node_to_map(struct pinctrl_dev *pctldev,
+					     struct device_node *np,
+					     struct pinctrl_map **maps,
+					     unsigned int *num_maps)
+{
+	return -ENOTSUPP;
+}
+
+static inline int
+pinctrl_generic_pinmux_dt_node_to_map(struct pinctrl_dev *pctldev,
+				      struct device_node *np,
+				      struct pinctrl_map **maps,
+				      unsigned int *num_maps)
+{
+	return -ENOTSUPP;
+}
+
+static inline int
+pinctrl_generic_to_map(struct pinctrl_dev *pctldev, struct device_node *parent,
+		       struct device_node *np, struct pinctrl_map **maps,
+		       unsigned int *num_maps, unsigned int *num_reserved_maps,
+		       const char **group_name, unsigned int ngroups,
+		       void *data, unsigned int *pins, unsigned int npins)
+{
+	return -ENOTSUPP;
+}
+#endif