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, 154 insertions, 0 deletions

diff --git a/fs/compat_binfmt_elf.c b/fs/compat_binfmt_elf.c
new file mode 100644
index 000000000..d5ef5469e
--- /dev/null
+++ b/fs/compat_binfmt_elf.c
@@ -0,0 +1,154 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * 32-bit compatibility support for ELF format executables and core dumps.
+ *
+ * Copyright (C) 2007 Red Hat, Inc.  All rights reserved.
+ *
+ * Red Hat Author: Roland McGrath.
+ *
+ * This file is used in a 64-bit kernel that wants to support 32-bit ELF.
+ * asm/elf.h is responsible for defining the compat_* and COMPAT_* macros
+ * used below, with definitions appropriate for 32-bit ABI compatibility.
+ *
+ * We use macros to rename the ABI types and machine-dependent
+ * functions used in binfmt_elf.c to compat versions.
+ */
+
+#include <linux/elfcore-compat.h>
+#include <linux/time.h>
+
+#define ELF_COMPAT	1
+
+/*
+ * Rename the basic ELF layout types to refer to the 32-bit class of files.
+ */
+#undef	ELF_CLASS
+#define ELF_CLASS	ELFCLASS32
+
+#undef	elfhdr
+#undef	elf_phdr
+#undef	elf_shdr
+#undef	elf_note
+#undef	elf_addr_t
+#undef	ELF_GNU_PROPERTY_ALIGN
+#define elfhdr		elf32_hdr
+#define elf_phdr	elf32_phdr
+#define elf_shdr	elf32_shdr
+#define elf_note	elf32_note
+#define elf_addr_t	Elf32_Addr
+#define ELF_GNU_PROPERTY_ALIGN	ELF32_GNU_PROPERTY_ALIGN
+
+/*
+ * Some data types as stored in coredump.
+ */
+#define user_long_t		compat_long_t
+#define user_siginfo_t		compat_siginfo_t
+#define copy_siginfo_to_external	copy_siginfo_to_external32
+
+/*
+ * The machine-dependent core note format types are defined in elfcore-compat.h,
+ * which requires asm/elf.h to define compat_elf_gregset_t et al.
+ */
+#define elf_prstatus	compat_elf_prstatus
+#define elf_prstatus_common	compat_elf_prstatus_common
+#define elf_prpsinfo	compat_elf_prpsinfo
+
+#undef ns_to_kernel_old_timeval
+#define ns_to_kernel_old_timeval ns_to_old_timeval32
+
+/*
+ * To use this file, asm/elf.h must define compat_elf_check_arch.
+ * The other following macros can be defined if the compat versions
+ * differ from the native ones, or omitted when they match.
+ */
+
+#undef	elf_check_arch
+#define	elf_check_arch	compat_elf_check_arch
+
+#ifdef	COMPAT_ELF_PLATFORM
+#undef	ELF_PLATFORM
+#define	ELF_PLATFORM		COMPAT_ELF_PLATFORM
+#endif
+
+#ifdef	COMPAT_ELF_HWCAP
+#undef	ELF_HWCAP
+#define	ELF_HWCAP		COMPAT_ELF_HWCAP
+#endif
+
+#ifdef	COMPAT_ELF_HWCAP2
+#undef	ELF_HWCAP2
+#define	ELF_HWCAP2		COMPAT_ELF_HWCAP2
+#endif
+
+#ifdef	COMPAT_ELF_HWCAP3
+#undef	ELF_HWCAP3
+#define	ELF_HWCAP3		COMPAT_ELF_HWCAP3
+#endif
+
+#ifdef	COMPAT_ELF_HWCAP4
+#undef	ELF_HWCAP4
+#define	ELF_HWCAP4		COMPAT_ELF_HWCAP4
+#endif
+
+#ifdef	COMPAT_ARCH_DLINFO
+#undef	ARCH_DLINFO
+#define	ARCH_DLINFO		COMPAT_ARCH_DLINFO
+#endif
+
+#ifdef	COMPAT_ELF_ET_DYN_BASE
+#undef	ELF_ET_DYN_BASE
+#define	ELF_ET_DYN_BASE		COMPAT_ELF_ET_DYN_BASE
+#endif
+
+#ifdef	COMPAT_ELF_PLAT_INIT
+#undef	ELF_PLAT_INIT
+#define	ELF_PLAT_INIT		COMPAT_ELF_PLAT_INIT
+#endif
+
+#ifdef	COMPAT_SET_PERSONALITY
+#undef	SET_PERSONALITY
+#define	SET_PERSONALITY		COMPAT_SET_PERSONALITY
+#endif
+
+#ifdef	compat_start_thread
+#define COMPAT_START_THREAD(ex, regs, new_ip, new_sp)	\
+	compat_start_thread(regs, new_ip, new_sp)
+#endif
+
+#ifdef	COMPAT_START_THREAD
+#undef	START_THREAD
+#define START_THREAD		COMPAT_START_THREAD
+#endif
+
+#ifdef compat_arch_setup_additional_pages
+#define COMPAT_ARCH_SETUP_ADDITIONAL_PAGES(bprm, ex, interpreter) \
+	compat_arch_setup_additional_pages(bprm, interpreter)
+#endif
+
+#ifdef	COMPAT_ARCH_SETUP_ADDITIONAL_PAGES
+#undef	ARCH_HAS_SETUP_ADDITIONAL_PAGES
+#define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
+#undef	ARCH_SETUP_ADDITIONAL_PAGES
+#define	ARCH_SETUP_ADDITIONAL_PAGES COMPAT_ARCH_SETUP_ADDITIONAL_PAGES
+#endif
+
+#ifdef	compat_elf_read_implies_exec
+#undef	elf_read_implies_exec
+#define	elf_read_implies_exec compat_elf_read_implies_exec
+#endif
+
+/*
+ * Rename a few of the symbols that binfmt_elf.c will define.
+ * These are all local so the names don't really matter, but it
+ * might make some debugging less confusing not to duplicate them.
+ */
+#define elf_format		compat_elf_format
+#define init_elf_binfmt		init_compat_elf_binfmt
+#define exit_elf_binfmt		exit_compat_elf_binfmt
+#define binfmt_elf_test_cases	compat_binfmt_elf_test_cases
+#define binfmt_elf_test_suite	compat_binfmt_elf_test_suite
+
+/*
+ * We share all the actual code with the native (64-bit) version.
+ */
+#include "binfmt_elf.c"