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, 101 insertions, 0 deletions

diff --git a/include/asm-generic/fixmap.h b/include/asm-generic/fixmap.h
new file mode 100644
index 000000000..3ff832ebc
--- /dev/null
+++ b/include/asm-generic/fixmap.h
@@ -0,0 +1,101 @@
+/*
+ * fixmap.h: compile-time virtual memory allocation
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1998 Ingo Molnar
+ *
+ * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
+ * x86_32 and x86_64 integration by Gustavo F. Padovan, February 2009
+ * Break out common bits to asm-generic by Mark Salter, November 2013
+ */
+
+#ifndef __ASM_GENERIC_FIXMAP_H
+#define __ASM_GENERIC_FIXMAP_H
+
+#include <linux/bug.h>
+#include <linux/mm_types.h>
+
+#define __fix_to_virt(x)	(FIXADDR_TOP - ((x) << PAGE_SHIFT))
+#define __virt_to_fix(x)	((FIXADDR_TOP - ((x)&PAGE_MASK)) >> PAGE_SHIFT)
+
+#ifndef __ASSEMBLER__
+/*
+ * 'index to address' translation. If anyone tries to use the idx
+ * directly without translation, we catch the bug with a NULL-deference
+ * kernel oops. Illegal ranges of incoming indices are caught too.
+ */
+static __always_inline unsigned long fix_to_virt(const unsigned int idx)
+{
+	BUILD_BUG_ON(idx >= __end_of_fixed_addresses);
+	return __fix_to_virt(idx);
+}
+
+static inline unsigned long virt_to_fix(const unsigned long vaddr)
+{
+	BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START);
+	return __virt_to_fix(vaddr);
+}
+
+/*
+ * Provide some reasonable defaults for page flags.
+ * Not all architectures use all of these different types and some
+ * architectures use different names.
+ */
+#ifndef FIXMAP_PAGE_NORMAL
+#define FIXMAP_PAGE_NORMAL PAGE_KERNEL
+#endif
+#if !defined(FIXMAP_PAGE_RO) && defined(PAGE_KERNEL_RO)
+#define FIXMAP_PAGE_RO PAGE_KERNEL_RO
+#endif
+#ifndef FIXMAP_PAGE_NOCACHE
+#define FIXMAP_PAGE_NOCACHE PAGE_KERNEL_NOCACHE
+#endif
+#ifndef FIXMAP_PAGE_IO
+#define FIXMAP_PAGE_IO PAGE_KERNEL_IO
+#endif
+#ifndef FIXMAP_PAGE_CLEAR
+#define FIXMAP_PAGE_CLEAR __pgprot(0)
+#endif
+
+#ifndef set_fixmap
+#define set_fixmap(idx, phys)				\
+	__set_fixmap(idx, phys, FIXMAP_PAGE_NORMAL)
+#endif
+
+#ifndef clear_fixmap
+#define clear_fixmap(idx)			\
+	__set_fixmap(idx, 0, FIXMAP_PAGE_CLEAR)
+#endif
+
+/* Return a pointer with offset calculated */
+#define __set_fixmap_offset(idx, phys, flags)				\
+({									\
+	unsigned long ________addr;					\
+	__set_fixmap(idx, phys, flags);					\
+	________addr = fix_to_virt(idx) + ((phys) & (PAGE_SIZE - 1));	\
+	________addr;							\
+})
+
+#define set_fixmap_offset(idx, phys) \
+	__set_fixmap_offset(idx, phys, FIXMAP_PAGE_NORMAL)
+
+/*
+ * Some hardware wants to get fixmapped without caching.
+ */
+#define set_fixmap_nocache(idx, phys) \
+	__set_fixmap(idx, phys, FIXMAP_PAGE_NOCACHE)
+
+#define set_fixmap_offset_nocache(idx, phys) \
+	__set_fixmap_offset(idx, phys, FIXMAP_PAGE_NOCACHE)
+
+/*
+ * Some fixmaps are for IO
+ */
+#define set_fixmap_io(idx, phys) \
+	__set_fixmap(idx, phys, FIXMAP_PAGE_IO)
+
+#endif /* __ASSEMBLER__ */
+#endif /* __ASM_GENERIC_FIXMAP_H */