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, 124 insertions, 0 deletions

diff --git a/drivers/edac/edac_module.h b/drivers/edac/edac_module.h
new file mode 100644
index 000000000..eceef5539
--- /dev/null
+++ b/drivers/edac/edac_module.h
@@ -0,0 +1,124 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * edac_module.h
+ *
+ * For defining functions/data for within the EDAC_CORE module only
+ *
+ * written by doug thompson <norsk5@xmission.h>
+ */
+
+#ifndef	__EDAC_MODULE_H__
+#define	__EDAC_MODULE_H__
+
+#include <acpi/ghes.h>
+#include "edac_mc.h"
+#include "edac_pci.h"
+#include "edac_device.h"
+
+/*
+ * INTERNAL EDAC MODULE:
+ * EDAC memory controller sysfs create/remove functions
+ * and setup/teardown functions
+ *
+ * edac_mc objects
+ */
+	/* on edac_mc_sysfs.c */
+int edac_mc_sysfs_init(void);
+void edac_mc_sysfs_exit(void);
+extern int edac_create_sysfs_mci_device(struct mem_ctl_info *mci,
+					const struct attribute_group **groups);
+extern void edac_remove_sysfs_mci_device(struct mem_ctl_info *mci);
+extern int edac_mc_get_log_ue(void);
+extern int edac_mc_get_log_ce(void);
+extern int edac_mc_get_panic_on_ue(void);
+extern unsigned int edac_mc_get_poll_msec(void);
+
+unsigned edac_dimm_info_location(struct dimm_info *dimm, char *buf,
+				 unsigned len);
+
+	/* on edac_device.c */
+extern int edac_device_register_sysfs_main_kobj(
+				struct edac_device_ctl_info *edac_dev);
+extern void edac_device_unregister_sysfs_main_kobj(
+				struct edac_device_ctl_info *edac_dev);
+extern int edac_device_create_sysfs(struct edac_device_ctl_info *edac_dev);
+extern void edac_device_remove_sysfs(struct edac_device_ctl_info *edac_dev);
+
+/* edac core workqueue: single CPU mode */
+int edac_workqueue_setup(void);
+void edac_workqueue_teardown(void);
+bool edac_queue_work(struct delayed_work *work, unsigned long delay);
+bool edac_stop_work(struct delayed_work *work);
+bool edac_mod_work(struct delayed_work *work, unsigned long delay);
+
+extern void edac_device_reset_delay_period(struct edac_device_ctl_info *edac_dev, unsigned int msec);
+extern void edac_mc_reset_delay_period(unsigned long value);
+
+/*
+ * EDAC debugfs functions
+ */
+
+#define edac_debugfs_remove_recursive debugfs_remove_recursive
+#define edac_debugfs_remove debugfs_remove
+#ifdef CONFIG_EDAC_DEBUG
+void edac_debugfs_init(void);
+void edac_debugfs_exit(void);
+void edac_create_debugfs_nodes(struct mem_ctl_info *mci);
+struct dentry *edac_debugfs_create_dir(const char *dirname);
+struct dentry *
+edac_debugfs_create_dir_at(const char *dirname, struct dentry *parent);
+struct dentry *
+edac_debugfs_create_file(const char *name, umode_t mode, struct dentry *parent,
+			 void *data, const struct file_operations *fops);
+void edac_debugfs_create_x8(const char *name, umode_t mode,
+			    struct dentry *parent, u8 *value);
+void edac_debugfs_create_x16(const char *name, umode_t mode,
+			     struct dentry *parent, u16 *value);
+void edac_debugfs_create_x32(const char *name, umode_t mode,
+			     struct dentry *parent, u32 *value);
+#else
+static inline void edac_debugfs_init(void)					{ }
+static inline void edac_debugfs_exit(void)					{ }
+static inline void edac_create_debugfs_nodes(struct mem_ctl_info *mci)		{ }
+static inline struct dentry *edac_debugfs_create_dir(const char *dirname)	{ return NULL; }
+static inline struct dentry *
+edac_debugfs_create_dir_at(const char *dirname, struct dentry *parent)		{ return NULL; }
+static inline struct dentry *
+edac_debugfs_create_file(const char *name, umode_t mode, struct dentry *parent,
+			 void *data, const struct file_operations *fops)	{ return NULL; }
+static inline void edac_debugfs_create_x8(const char *name, umode_t mode,
+					  struct dentry *parent, u8 *value)	{ }
+static inline void edac_debugfs_create_x16(const char *name, umode_t mode,
+					   struct dentry *parent, u16 *value)	{ }
+static inline void edac_debugfs_create_x32(const char *name, umode_t mode,
+		       struct dentry *parent, u32 *value)			{ }
+#endif
+
+/*
+ * EDAC PCI functions
+ */
+#ifdef	CONFIG_PCI
+extern void edac_pci_do_parity_check(void);
+extern void edac_pci_clear_parity_errors(void);
+extern int edac_sysfs_pci_setup(void);
+extern void edac_sysfs_pci_teardown(void);
+extern int edac_pci_get_check_errors(void);
+extern int edac_pci_get_poll_msec(void);
+extern void edac_pci_remove_sysfs(struct edac_pci_ctl_info *pci);
+extern void edac_pci_handle_pe(struct edac_pci_ctl_info *pci, const char *msg);
+extern void edac_pci_handle_npe(struct edac_pci_ctl_info *pci,
+				const char *msg);
+#else				/* CONFIG_PCI */
+/* pre-process these away */
+#define edac_pci_do_parity_check()
+#define edac_pci_clear_parity_errors()
+#define edac_sysfs_pci_setup()  (0)
+#define edac_sysfs_pci_teardown()
+#define edac_pci_get_check_errors()
+#define edac_pci_get_poll_msec()
+#define edac_pci_handle_pe()
+#define edac_pci_handle_npe()
+#endif				/* CONFIG_PCI */
+
+#endif				/* __EDAC_MODULE_H__ */