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, 162 insertions, 0 deletions

diff --git a/arch/m68k/coldfire/pit.c b/arch/m68k/coldfire/pit.c
new file mode 100644
index 000000000..de4eaf8db
--- /dev/null
+++ b/arch/m68k/coldfire/pit.c
@@ -0,0 +1,162 @@
+// SPDX-License-Identifier: GPL-2.0
+/***************************************************************************/
+
+/*
+ *	pit.c -- Freescale ColdFire PIT timer. Currently this type of
+ *	         hardware timer only exists in the Freescale ColdFire
+ *		 5270/5271, 5282 and 5208 CPUs. No doubt newer ColdFire
+ *		 family members will probably use it too.
+ *
+ *	Copyright (C) 1999-2008, Greg Ungerer (gerg@snapgear.com)
+ *	Copyright (C) 2001-2004, SnapGear Inc. (www.snapgear.com)
+ */
+
+/***************************************************************************/
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/param.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/clockchips.h>
+#include <asm/machdep.h>
+#include <asm/io.h>
+#include <asm/coldfire.h>
+#include <asm/mcfpit.h>
+#include <asm/mcfsim.h>
+
+/***************************************************************************/
+
+/*
+ *	By default use timer1 as the system clock timer.
+ */
+#define	FREQ	((MCF_CLK / 2) / 64)
+#define	TA(a)	(MCFPIT_BASE1 + (a))
+#define PIT_CYCLES_PER_JIFFY (FREQ / HZ)
+
+static u32 pit_cnt;
+
+/*
+ * Initialize the PIT timer.
+ *
+ * This is also called after resume to bring the PIT into operation again.
+ */
+
+static int cf_pit_set_periodic(struct clock_event_device *evt)
+{
+	mcf_write16(MCFPIT_PCSR_DISABLE, TA(MCFPIT_PCSR));
+	mcf_write16(PIT_CYCLES_PER_JIFFY, TA(MCFPIT_PMR));
+	mcf_write16(MCFPIT_PCSR_EN | MCFPIT_PCSR_PIE |
+		     MCFPIT_PCSR_OVW | MCFPIT_PCSR_RLD |
+		     MCFPIT_PCSR_CLK64, TA(MCFPIT_PCSR));
+	return 0;
+}
+
+static int cf_pit_set_oneshot(struct clock_event_device *evt)
+{
+	mcf_write16(MCFPIT_PCSR_DISABLE, TA(MCFPIT_PCSR));
+	mcf_write16(MCFPIT_PCSR_EN | MCFPIT_PCSR_PIE |
+		     MCFPIT_PCSR_OVW | MCFPIT_PCSR_CLK64, TA(MCFPIT_PCSR));
+	return 0;
+}
+
+static int cf_pit_shutdown(struct clock_event_device *evt)
+{
+	mcf_write16(MCFPIT_PCSR_DISABLE, TA(MCFPIT_PCSR));
+	return 0;
+}
+
+/*
+ * Program the next event in oneshot mode
+ *
+ * Delta is given in PIT ticks
+ */
+static int cf_pit_next_event(unsigned long delta,
+		struct clock_event_device *evt)
+{
+	mcf_write16(delta, TA(MCFPIT_PMR));
+	return 0;
+}
+
+struct clock_event_device cf_pit_clockevent = {
+	.name			= "pit",
+	.features		= CLOCK_EVT_FEAT_PERIODIC |
+				  CLOCK_EVT_FEAT_ONESHOT,
+	.set_state_shutdown	= cf_pit_shutdown,
+	.set_state_periodic	= cf_pit_set_periodic,
+	.set_state_oneshot	= cf_pit_set_oneshot,
+	.set_next_event		= cf_pit_next_event,
+	.shift			= 32,
+	.irq			= MCF_IRQ_PIT1,
+};
+
+
+
+/***************************************************************************/
+
+static irqreturn_t pit_tick(int irq, void *dummy)
+{
+	struct clock_event_device *evt = &cf_pit_clockevent;
+	u16 pcsr;
+
+	/* Reset the ColdFire timer */
+	pcsr = mcf_read16(TA(MCFPIT_PCSR));
+	mcf_write16(pcsr | MCFPIT_PCSR_PIF, TA(MCFPIT_PCSR));
+
+	pit_cnt += PIT_CYCLES_PER_JIFFY;
+	evt->event_handler(evt);
+	return IRQ_HANDLED;
+}
+
+/***************************************************************************/
+
+static u64 pit_read_clk(struct clocksource *cs)
+{
+	unsigned long flags;
+	u32 cycles;
+	u16 pcntr;
+
+	local_irq_save(flags);
+	pcntr = mcf_read16(TA(MCFPIT_PCNTR));
+	cycles = pit_cnt;
+	local_irq_restore(flags);
+
+	return cycles + PIT_CYCLES_PER_JIFFY - pcntr;
+}
+
+/***************************************************************************/
+
+static struct clocksource pit_clk = {
+	.name	= "pit",
+	.rating	= 100,
+	.read	= pit_read_clk,
+	.mask	= CLOCKSOURCE_MASK(32),
+};
+
+/***************************************************************************/
+
+void hw_timer_init(void)
+{
+	int ret;
+
+	cf_pit_clockevent.cpumask = cpumask_of(smp_processor_id());
+	cf_pit_clockevent.mult = div_sc(FREQ, NSEC_PER_SEC, 32);
+	cf_pit_clockevent.max_delta_ns =
+		clockevent_delta2ns(0xFFFF, &cf_pit_clockevent);
+	cf_pit_clockevent.max_delta_ticks = 0xFFFF;
+	cf_pit_clockevent.min_delta_ns =
+		clockevent_delta2ns(0x3f, &cf_pit_clockevent);
+	cf_pit_clockevent.min_delta_ticks = 0x3f;
+	clockevents_register_device(&cf_pit_clockevent);
+
+	ret = request_irq(MCF_IRQ_PIT1, pit_tick, IRQF_TIMER, "timer", NULL);
+	if (ret) {
+		pr_err("Failed to request irq %d (timer): %pe\n", MCF_IRQ_PIT1,
+		       ERR_PTR(ret));
+	}
+
+	clocksource_register_hz(&pit_clk, FREQ);
+}
+
+/***************************************************************************/