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, 68 insertions, 0 deletions

diff --git a/arch/mips/lib/delay.c b/arch/mips/lib/delay.c
new file mode 100644
index 000000000..ccdb1fc1e
--- /dev/null
+++ b/arch/mips/lib/delay.c
@@ -0,0 +1,68 @@
+/*
+ * 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) 1994 by Waldorf Electronics
+ * Copyright (C) 1995 - 2000, 01, 03 by Ralf Baechle
+ * Copyright (C) 1999, 2000 Silicon Graphics, Inc.
+ * Copyright (C) 2007, 2014 Maciej W. Rozycki
+ */
+#include <linux/delay.h>
+#include <linux/export.h>
+#include <linux/param.h>
+#include <linux/smp.h>
+#include <linux/stringify.h>
+
+#include <asm/asm.h>
+#include <asm/compiler.h>
+
+#ifndef CONFIG_CPU_DADDI_WORKAROUNDS
+#define GCC_DADDI_IMM_ASM() "I"
+#else
+#define GCC_DADDI_IMM_ASM() "r"
+#endif
+
+#ifndef CONFIG_HAVE_PLAT_DELAY
+
+void __delay(unsigned long loops)
+{
+	__asm__ __volatile__ (
+	"	.set	noreorder				\n"
+	"	.align	3					\n"
+	"1:	bnez	%0, 1b					\n"
+	"	 " __stringify(LONG_SUBU) "	%0, %1		\n"
+	"	.set	reorder					\n"
+	: "=r" (loops)
+	: GCC_DADDI_IMM_ASM() (1), "0" (loops));
+}
+EXPORT_SYMBOL(__delay);
+
+/*
+ * Division by multiplication: you don't have to worry about
+ * loss of precision.
+ *
+ * Use only for very small delays ( < 1 msec).	Should probably use a
+ * lookup table, really, as the multiplications take much too long with
+ * short delays.  This is a "reasonable" implementation, though (and the
+ * first constant multiplications gets optimized away if the delay is
+ * a constant)
+ */
+
+void __udelay(unsigned long us)
+{
+	unsigned int lpj = raw_current_cpu_data.udelay_val;
+
+	__delay((us * 0x000010c7ull * HZ * lpj) >> 32);
+}
+EXPORT_SYMBOL(__udelay);
+
+void __ndelay(unsigned long ns)
+{
+	unsigned int lpj = raw_current_cpu_data.udelay_val;
+
+	__delay((ns * 0x00000005ull * HZ * lpj) >> 32);
+}
+EXPORT_SYMBOL(__ndelay);
+
+#endif