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, 72 insertions, 0 deletions

diff --git a/drivers/clocksource/timer-of.h b/drivers/clocksource/timer-of.h
new file mode 100644
index 000000000..74a632b85
--- /dev/null
+++ b/drivers/clocksource/timer-of.h
@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __TIMER_OF_H__
+#define __TIMER_OF_H__
+
+#include <linux/clockchips.h>
+
+#define TIMER_OF_BASE	0x1
+#define TIMER_OF_CLOCK	0x2
+#define TIMER_OF_IRQ	0x4
+
+struct of_timer_irq {
+	int irq;
+	int index;
+	const char *name;
+	unsigned long flags;
+	irq_handler_t handler;
+};
+
+struct of_timer_base {
+	void __iomem *base;
+	const char *name;
+	int index;
+};
+
+struct of_timer_clk {
+	struct clk *clk;
+	const char *name;
+	int index;
+	unsigned long rate;
+	unsigned long period;
+};
+
+struct timer_of {
+	unsigned int flags;
+	struct device_node *np;
+	struct clock_event_device clkevt;
+	struct of_timer_base of_base;
+	struct of_timer_irq  of_irq;
+	struct of_timer_clk  of_clk;
+	void *private_data;
+};
+
+static inline struct timer_of *to_timer_of(struct clock_event_device *clkevt)
+{
+	return container_of(clkevt, struct timer_of, clkevt);
+}
+
+static inline void __iomem *timer_of_base(struct timer_of *to)
+{
+	return to->of_base.base;
+}
+
+static inline int timer_of_irq(struct timer_of *to)
+{
+	return to->of_irq.irq;
+}
+
+static inline unsigned long timer_of_rate(struct timer_of *to)
+{
+	return to->of_clk.rate;
+}
+
+static inline unsigned long timer_of_period(struct timer_of *to)
+{
+	return to->of_clk.period;
+}
+
+int timer_of_init(struct device_node *np, struct timer_of *to);
+
+void timer_of_cleanup(struct timer_of *to);
+
+#endif