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, 150 insertions, 0 deletions

diff --git a/drivers/clocksource/timer-vt8500.c b/drivers/clocksource/timer-vt8500.c
new file mode 100644
index 000000000..a469b1b5f
--- /dev/null
+++ b/drivers/clocksource/timer-vt8500.c
@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *  arch/arm/mach-vt8500/timer.c
+ *
+ *  Copyright (C) 2012 Tony Prisk <linux@prisktech.co.nz>
+ *  Copyright (C) 2010 Alexey Charkov <alchark@gmail.com>
+ */
+
+/*
+ * This file is copied and modified from the original timer.c provided by
+ * Alexey Charkov. Minor changes have been made for Device Tree Support.
+ */
+
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/clocksource.h>
+#include <linux/clockchips.h>
+#include <linux/delay.h>
+
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+
+#define VT8500_TIMER_OFFSET	0x0100
+#define VT8500_TIMER_HZ		3000000
+#define TIMER_MATCH_VAL		0x0000
+#define TIMER_COUNT_VAL		0x0010
+#define TIMER_STATUS_VAL	0x0014
+#define TIMER_IER_VAL		0x001c		/* interrupt enable */
+#define TIMER_CTRL_VAL		0x0020
+#define TIMER_AS_VAL		0x0024		/* access status */
+#define TIMER_COUNT_R_ACTIVE	(1 << 5)	/* not ready for read */
+#define TIMER_COUNT_W_ACTIVE	(1 << 4)	/* not ready for write */
+#define TIMER_MATCH_W_ACTIVE	(1 << 0)	/* not ready for write */
+
+#define msecs_to_loops(t) (loops_per_jiffy / 1000 * HZ * t)
+
+#define MIN_OSCR_DELTA		16
+
+static void __iomem *regbase;
+
+static u64 vt8500_timer_read(struct clocksource *cs)
+{
+	int loops = msecs_to_loops(10);
+	writel(3, regbase + TIMER_CTRL_VAL);
+	while ((readl((regbase + TIMER_AS_VAL)) & TIMER_COUNT_R_ACTIVE)
+						&& --loops)
+		cpu_relax();
+	return readl(regbase + TIMER_COUNT_VAL);
+}
+
+static struct clocksource clocksource = {
+	.name           = "vt8500_timer",
+	.rating         = 200,
+	.read           = vt8500_timer_read,
+	.mask           = CLOCKSOURCE_MASK(32),
+	.flags          = CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+static int vt8500_timer_set_next_event(unsigned long cycles,
+				    struct clock_event_device *evt)
+{
+	int loops = msecs_to_loops(10);
+	u64 alarm = clocksource.read(&clocksource) + cycles;
+	while ((readl(regbase + TIMER_AS_VAL) & TIMER_MATCH_W_ACTIVE)
+						&& --loops)
+		cpu_relax();
+	writel((unsigned long)alarm, regbase + TIMER_MATCH_VAL);
+
+	if ((signed)(alarm - clocksource.read(&clocksource)) <= MIN_OSCR_DELTA)
+		return -ETIME;
+
+	writel(1, regbase + TIMER_IER_VAL);
+
+	return 0;
+}
+
+static int vt8500_shutdown(struct clock_event_device *evt)
+{
+	writel(readl(regbase + TIMER_CTRL_VAL) | 1, regbase + TIMER_CTRL_VAL);
+	writel(0, regbase + TIMER_IER_VAL);
+	return 0;
+}
+
+static struct clock_event_device clockevent = {
+	.name			= "vt8500_timer",
+	.features		= CLOCK_EVT_FEAT_ONESHOT,
+	.rating			= 200,
+	.set_next_event		= vt8500_timer_set_next_event,
+	.set_state_shutdown	= vt8500_shutdown,
+	.set_state_oneshot	= vt8500_shutdown,
+};
+
+static irqreturn_t vt8500_timer_interrupt(int irq, void *dev_id)
+{
+	struct clock_event_device *evt = dev_id;
+	writel(0xf, regbase + TIMER_STATUS_VAL);
+	evt->event_handler(evt);
+
+	return IRQ_HANDLED;
+}
+
+static int __init vt8500_timer_init(struct device_node *np)
+{
+	int timer_irq, ret;
+
+	regbase = of_iomap(np, 0);
+	if (!regbase) {
+		pr_err("%s: Missing iobase description in Device Tree\n",
+								__func__);
+		return -ENXIO;
+	}
+
+	timer_irq = irq_of_parse_and_map(np, 0);
+	if (!timer_irq) {
+		pr_err("%s: Missing irq description in Device Tree\n",
+								__func__);
+		return -EINVAL;
+	}
+
+	writel(1, regbase + TIMER_CTRL_VAL);
+	writel(0xf, regbase + TIMER_STATUS_VAL);
+	writel(~0, regbase + TIMER_MATCH_VAL);
+
+	ret = clocksource_register_hz(&clocksource, VT8500_TIMER_HZ);
+	if (ret) {
+		pr_err("%s: clocksource_register failed for %s\n",
+		       __func__, clocksource.name);
+		return ret;
+	}
+
+	clockevent.cpumask = cpumask_of(0);
+
+	ret = request_irq(timer_irq, vt8500_timer_interrupt,
+			  IRQF_TIMER | IRQF_IRQPOLL, "vt8500_timer",
+			  &clockevent);
+	if (ret) {
+		pr_err("%s: setup_irq failed for %s\n", __func__,
+							clockevent.name);
+		return ret;
+	}
+
+	clockevents_config_and_register(&clockevent, VT8500_TIMER_HZ,
+					MIN_OSCR_DELTA * 2, 0xf0000000);
+
+	return 0;
+}
+
+TIMER_OF_DECLARE(vt8500, "via,vt8500-timer", vt8500_timer_init);