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, 157 insertions, 0 deletions

diff --git a/drivers/clocksource/timer-ralink.c b/drivers/clocksource/timer-ralink.c
new file mode 100644
index 000000000..68434d9ed
--- /dev/null
+++ b/drivers/clocksource/timer-ralink.c
@@ -0,0 +1,157 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Ralink System Tick Counter driver present on RT3352 and MT7620 SoCs.
+ *
+ * Copyright (C) 2013 by John Crispin <john@phrozen.org>
+ */
+
+#include <linux/clockchips.h>
+#include <linux/clocksource.h>
+#include <linux/interrupt.h>
+#include <linux/reset.h>
+#include <linux/init.h>
+#include <linux/time.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/of_address.h>
+
+#define SYSTICK_FREQ		(50 * 1000)
+
+#define SYSTICK_CONFIG		0x00
+#define SYSTICK_COMPARE		0x04
+#define SYSTICK_COUNT		0x08
+
+/* route systick irq to mips irq 7 instead of the r4k-timer */
+#define CFG_EXT_STK_EN		0x2
+/* enable the counter */
+#define CFG_CNT_EN		0x1
+
+struct systick_device {
+	void __iomem *membase;
+	struct clock_event_device dev;
+	int irq_requested;
+	int freq_scale;
+};
+
+static int systick_set_oneshot(struct clock_event_device *evt);
+static int systick_shutdown(struct clock_event_device *evt);
+
+static int systick_next_event(unsigned long delta,
+			      struct clock_event_device *evt)
+{
+	struct systick_device *sdev;
+	u32 count;
+
+	sdev = container_of(evt, struct systick_device, dev);
+	count = ioread32(sdev->membase + SYSTICK_COUNT);
+	count = (count + delta) % SYSTICK_FREQ;
+	iowrite32(count, sdev->membase + SYSTICK_COMPARE);
+
+	return 0;
+}
+
+static void systick_event_handler(struct clock_event_device *dev)
+{
+	/* noting to do here */
+}
+
+static irqreturn_t systick_interrupt(int irq, void *dev_id)
+{
+	struct clock_event_device *dev = (struct clock_event_device *)dev_id;
+
+	dev->event_handler(dev);
+
+	return IRQ_HANDLED;
+}
+
+static struct systick_device systick = {
+	.dev = {
+		/*
+		 * cevt-r4k uses 300, make sure systick
+		 * gets used if available
+		 */
+		.rating			= 310,
+		.features		= CLOCK_EVT_FEAT_ONESHOT,
+		.set_next_event		= systick_next_event,
+		.set_state_shutdown	= systick_shutdown,
+		.set_state_oneshot	= systick_set_oneshot,
+		.event_handler		= systick_event_handler,
+	},
+};
+
+static int systick_shutdown(struct clock_event_device *evt)
+{
+	struct systick_device *sdev;
+
+	sdev = container_of(evt, struct systick_device, dev);
+
+	if (sdev->irq_requested)
+		free_irq(systick.dev.irq, &systick.dev);
+	sdev->irq_requested = 0;
+	iowrite32(0, systick.membase + SYSTICK_CONFIG);
+
+	return 0;
+}
+
+static int systick_set_oneshot(struct clock_event_device *evt)
+{
+	const char *name = systick.dev.name;
+	struct systick_device *sdev;
+	int irq = systick.dev.irq;
+
+	sdev = container_of(evt, struct systick_device, dev);
+
+	if (!sdev->irq_requested) {
+		if (request_irq(irq, systick_interrupt,
+				IRQF_PERCPU | IRQF_TIMER, name, &systick.dev))
+			pr_err("Failed to request irq %d (%s)\n", irq, name);
+	}
+	sdev->irq_requested = 1;
+	iowrite32(CFG_EXT_STK_EN | CFG_CNT_EN,
+		  systick.membase + SYSTICK_CONFIG);
+
+	return 0;
+}
+
+static int __init ralink_systick_init(struct device_node *np)
+{
+	int ret;
+
+	systick.membase = of_iomap(np, 0);
+	if (!systick.membase)
+		return -ENXIO;
+
+	systick.dev.name = np->name;
+	clockevents_calc_mult_shift(&systick.dev, SYSTICK_FREQ, 60);
+	systick.dev.max_delta_ns = clockevent_delta2ns(0x7fff, &systick.dev);
+	systick.dev.max_delta_ticks = 0x7fff;
+	systick.dev.min_delta_ns = clockevent_delta2ns(0x3, &systick.dev);
+	systick.dev.min_delta_ticks = 0x3;
+	systick.dev.irq = irq_of_parse_and_map(np, 0);
+	if (!systick.dev.irq) {
+		pr_err("%pOFn: request_irq failed", np);
+		ret = -EINVAL;
+		goto err_iounmap;
+	}
+
+	ret = clocksource_mmio_init(systick.membase + SYSTICK_COUNT, np->name,
+				    SYSTICK_FREQ, 301, 16,
+				    clocksource_mmio_readl_up);
+	if (ret)
+		goto err_free_irq;
+
+	clockevents_register_device(&systick.dev);
+
+	pr_info("%pOFn: running - mult: %d, shift: %d\n",
+			np, systick.dev.mult, systick.dev.shift);
+
+	return 0;
+
+err_free_irq:
+	irq_dispose_mapping(systick.dev.irq);
+err_iounmap:
+	iounmap(systick.membase);
+	return ret;
+}
+
+TIMER_OF_DECLARE(systick, "ralink,cevt-systick", ralink_systick_init);