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, 73 insertions, 0 deletions

diff --git a/arch/parisc/lib/memcpy.c b/arch/parisc/lib/memcpy.c
new file mode 100644
index 000000000..03165c82d
--- /dev/null
+++ b/arch/parisc/lib/memcpy.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *    Optimized memory copy routines.
+ *
+ *    Copyright (C) 2004 Randolph Chung <tausq@debian.org>
+ *    Copyright (C) 2013-2017 Helge Deller <deller@gmx.de>
+ *
+ *    Portions derived from the GNU C Library
+ *    Copyright (C) 1991, 1997, 2003 Free Software Foundation, Inc.
+ */
+
+#include <linux/module.h>
+#include <linux/compiler.h>
+#include <linux/uaccess.h>
+#include <linux/mm.h>
+
+#define get_user_space()	mfsp(SR_USER)
+#define get_kernel_space()	SR_KERNEL
+
+/* Returns 0 for success, otherwise, returns number of bytes not transferred. */
+extern unsigned long pa_memcpy(void *dst, const void *src,
+				unsigned long len);
+
+unsigned long raw_copy_to_user(void __user *dst, const void *src,
+			       unsigned long len)
+{
+	mtsp(get_kernel_space(), SR_TEMP1);
+	mtsp(get_user_space(), SR_TEMP2);
+	return pa_memcpy((void __force *)dst, src, len);
+}
+EXPORT_SYMBOL(raw_copy_to_user);
+
+unsigned long raw_copy_from_user(void *dst, const void __user *src,
+			       unsigned long len)
+{
+	unsigned long start = (unsigned long) src;
+	unsigned long end = start + len;
+	unsigned long newlen = len;
+
+	mtsp(get_user_space(), SR_TEMP1);
+	mtsp(get_kernel_space(), SR_TEMP2);
+
+	/* Check region is user accessible */
+	while (start < end) {
+		if (!prober_user(SR_TEMP1, start)) {
+			newlen = (start - (unsigned long) src);
+			break;
+		}
+		start += PAGE_SIZE;
+		/* align to page boundry which may have different permission */
+		start = PAGE_ALIGN_DOWN(start);
+	}
+	return len - newlen + pa_memcpy(dst, (void __force *)src, newlen);
+}
+EXPORT_SYMBOL(raw_copy_from_user);
+
+void * memcpy(void * dst,const void *src, size_t count)
+{
+	mtsp(get_kernel_space(), SR_TEMP1);
+	mtsp(get_kernel_space(), SR_TEMP2);
+	pa_memcpy(dst, src, count);
+	return dst;
+}
+
+EXPORT_SYMBOL(memcpy);
+
+bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
+{
+	if ((unsigned long)unsafe_src < PAGE_SIZE)
+		return false;
+	/* check for I/O space F_EXTEND(0xfff00000) access as well? */
+	return true;
+}