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, 67 insertions, 0 deletions

diff --git a/fs/efivarfs/internal.h b/fs/efivarfs/internal.h
new file mode 100644
index 000000000..f913b6824
--- /dev/null
+++ b/fs/efivarfs/internal.h
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2012 Red Hat, Inc.
+ * Copyright (C) 2012 Jeremy Kerr <jeremy.kerr@canonical.com>
+ */
+#ifndef EFIVAR_FS_INTERNAL_H
+#define EFIVAR_FS_INTERNAL_H
+
+#include <linux/efi.h>
+
+struct efivarfs_mount_opts {
+	kuid_t uid;
+	kgid_t gid;
+};
+
+struct efivarfs_fs_info {
+	struct efivarfs_mount_opts mount_opts;
+	struct super_block *sb;
+	struct notifier_block nb;
+};
+
+struct efi_variable {
+	efi_char16_t  VariableName[EFI_VAR_NAME_LEN/sizeof(efi_char16_t)];
+	efi_guid_t    VendorGuid;
+};
+
+struct efivar_entry {
+	struct efi_variable var;
+	struct inode vfs_inode;
+	unsigned long open_count;
+	bool removed;
+};
+
+static inline struct efivar_entry *efivar_entry(struct inode *inode)
+{
+	return container_of(inode, struct efivar_entry, vfs_inode);
+}
+
+int efivar_init(int (*func)(efi_char16_t *, efi_guid_t, unsigned long, void *),
+		void *data, bool duplicate_check);
+
+int efivar_entry_delete(struct efivar_entry *entry);
+
+int efivar_entry_size(struct efivar_entry *entry, unsigned long *size);
+int __efivar_entry_get(struct efivar_entry *entry, u32 *attributes,
+		       unsigned long *size, void *data);
+int efivar_entry_get(struct efivar_entry *entry, u32 *attributes,
+		     unsigned long *size, void *data);
+int efivar_entry_set_get_size(struct efivar_entry *entry, u32 attributes,
+			      unsigned long *size, void *data, bool *set);
+
+
+bool efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data,
+		     unsigned long data_size);
+bool efivar_variable_is_removable(efi_guid_t vendor, const char *name,
+				  size_t len);
+char *efivar_get_utf8name(const efi_char16_t *name16, efi_guid_t *vendor);
+bool efivarfs_variable_is_present(efi_char16_t *variable_name,
+				  efi_guid_t *vendor, void *data);
+
+extern const struct file_operations efivarfs_file_operations;
+extern const struct inode_operations efivarfs_dir_inode_operations;
+extern struct inode *efivarfs_get_inode(struct super_block *sb,
+			const struct inode *dir, int mode, dev_t dev,
+			bool is_removable);
+
+#endif /* EFIVAR_FS_INTERNAL_H */