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, 242 insertions, 0 deletions

diff --git a/drivers/pps/clients/pps-gpio.c b/drivers/pps/clients/pps-gpio.c
new file mode 100644
index 000000000..73ec2c733
--- /dev/null
+++ b/drivers/pps/clients/pps-gpio.c
@@ -0,0 +1,242 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * pps-gpio.c -- PPS client driver using GPIO
+ *
+ * Copyright (C) 2010 Ricardo Martins <rasm@fe.up.pt>
+ * Copyright (C) 2011 James Nuss <jamesnuss@nanometrics.ca>
+ */
+
+#define PPS_GPIO_NAME "pps-gpio"
+#define pr_fmt(fmt) PPS_GPIO_NAME ": " fmt
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/pps_kernel.h>
+#include <linux/gpio/consumer.h>
+#include <linux/list.h>
+#include <linux/property.h>
+#include <linux/timer.h>
+#include <linux/jiffies.h>
+
+/* Info for each registered platform device */
+struct pps_gpio_device_data {
+	int irq;			/* IRQ used as PPS source */
+	struct pps_device *pps;		/* PPS source device */
+	struct pps_source_info info;	/* PPS source information */
+	struct gpio_desc *gpio_pin;	/* GPIO port descriptors */
+	struct gpio_desc *echo_pin;
+	struct timer_list echo_timer;	/* timer to reset echo active state */
+	bool assert_falling_edge;
+	unsigned int echo_active_ms;	/* PPS echo active duration */
+	unsigned long echo_timeout;	/* timer timeout value in jiffies */
+	struct pps_event_time ts;	/* timestamp captured in hardirq */
+};
+
+/*
+ * Report the PPS event
+ */
+
+/*
+ * Primary hardirq handler -- runs in hardirq context even on PREEMPT_RT.
+ * Only captures the timestamp; all other work is deferred to the thread.
+ */
+static irqreturn_t pps_gpio_irq_hardirq(int irq, void *data)
+{
+	struct pps_gpio_device_data *info = data;
+
+	pps_get_ts(&info->ts);
+
+	return IRQ_WAKE_THREAD;
+}
+
+/*
+ * Threaded handler -- processes the PPS event using the timestamp
+ * captured in hardirq context above.
+ */
+static irqreturn_t pps_gpio_irq_thread(int irq, void *data)
+{
+	struct pps_gpio_device_data *info = data;
+
+	pps_event(info->pps, &info->ts, PPS_CAPTUREASSERT, data);
+
+	return IRQ_HANDLED;
+}
+
+/* This function will only be called when an ECHO GPIO is defined */
+static void pps_gpio_echo(struct pps_device *pps, int event, void *data)
+{
+	/* add_timer() needs to write into info->echo_timer */
+	struct pps_gpio_device_data *info = data;
+
+	switch (event) {
+	case PPS_CAPTUREASSERT:
+		if (pps->params.mode & PPS_ECHOASSERT)
+			gpiod_set_value(info->echo_pin, 1);
+		break;
+	}
+
+	/* fire the timer */
+	if (info->pps->params.mode & (PPS_ECHOASSERT | PPS_ECHOCLEAR)) {
+		info->echo_timer.expires = jiffies + info->echo_timeout;
+		add_timer(&info->echo_timer);
+	}
+}
+
+/* Timer callback to reset the echo pin to the inactive state */
+static void pps_gpio_echo_timer_callback(struct timer_list *t)
+{
+	const struct pps_gpio_device_data *info;
+
+	info = timer_container_of(info, t, echo_timer);
+
+	gpiod_set_value(info->echo_pin, 0);
+}
+
+static int pps_gpio_setup(struct device *dev)
+{
+	struct pps_gpio_device_data *data = dev_get_drvdata(dev);
+	int ret;
+	u32 value;
+
+	data->gpio_pin = devm_gpiod_get(dev, NULL, GPIOD_IN);
+	if (IS_ERR(data->gpio_pin))
+		return dev_err_probe(dev, PTR_ERR(data->gpio_pin),
+				     "failed to request PPS GPIO\n");
+
+	data->assert_falling_edge =
+		device_property_read_bool(dev, "assert-falling-edge");
+
+	data->echo_pin = devm_gpiod_get_optional(dev, "echo", GPIOD_OUT_LOW);
+	if (IS_ERR(data->echo_pin))
+		return dev_err_probe(dev, PTR_ERR(data->echo_pin),
+				     "failed to request ECHO GPIO\n");
+
+	if (!data->echo_pin)
+		return 0;
+
+	ret = device_property_read_u32(dev, "echo-active-ms", &value);
+	if (ret) {
+		dev_err(dev, "failed to get echo-active-ms from FW\n");
+		return ret;
+	}
+
+	/* sanity check on echo_active_ms */
+	if (!value || value > 999) {
+		dev_err(dev, "echo-active-ms: %u - bad value from FW\n", value);
+		return -EINVAL;
+	}
+
+	data->echo_active_ms = value;
+
+	return 0;
+}
+
+static unsigned long
+get_irqf_trigger_flags(const struct pps_gpio_device_data *data)
+{
+	return data->assert_falling_edge ? IRQF_TRIGGER_FALLING :
+					   IRQF_TRIGGER_RISING;
+}
+
+static int pps_gpio_probe(struct platform_device *pdev)
+{
+	struct pps_gpio_device_data *data;
+	struct device *dev = &pdev->dev;
+	int ret;
+	int pps_default_params;
+
+	/* allocate space for device info */
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	dev_set_drvdata(dev, data);
+
+	/* GPIO setup */
+	ret = pps_gpio_setup(dev);
+	if (ret)
+		return ret;
+
+	/* IRQ setup */
+	ret = gpiod_to_irq(data->gpio_pin);
+	if (ret < 0) {
+		dev_err(dev, "failed to map GPIO to IRQ: %d\n", ret);
+		return -EINVAL;
+	}
+	data->irq = ret;
+
+	/* initialize PPS specific parts of the bookkeeping data structure. */
+	data->info.mode = PPS_CAPTUREASSERT | PPS_OFFSETASSERT |
+		PPS_ECHOASSERT | PPS_CANWAIT | PPS_TSFMT_TSPEC;
+	data->info.owner = THIS_MODULE;
+	snprintf(data->info.name, PPS_MAX_NAME_LEN - 1, "%s.%d",
+		 pdev->name, pdev->id);
+	if (data->echo_pin) {
+		data->info.echo = pps_gpio_echo;
+		data->echo_timeout = msecs_to_jiffies(data->echo_active_ms);
+		timer_setup(&data->echo_timer, pps_gpio_echo_timer_callback, 0);
+	}
+
+	/* register PPS source */
+	pps_default_params = PPS_CAPTUREASSERT | PPS_OFFSETASSERT;
+	data->pps = pps_register_source(&data->info, pps_default_params);
+	if (IS_ERR(data->pps)) {
+		dev_err(dev, "failed to register IRQ %d as PPS source\n",
+			data->irq);
+		return PTR_ERR(data->pps);
+	}
+
+	/* register IRQ interrupt handler */
+	ret = request_threaded_irq(data->irq,
+			  pps_gpio_irq_hardirq, pps_gpio_irq_thread,
+			  get_irqf_trigger_flags(data) | IRQF_ONESHOT,
+			  data->info.name, data);
+	if (ret) {
+		pps_unregister_source(data->pps);
+		dev_err(dev, "failed to acquire IRQ %d\n", data->irq);
+		return -EINVAL;
+	}
+
+	dev_dbg(&data->pps->dev, "Registered IRQ %d as PPS source\n",
+		data->irq);
+
+	return 0;
+}
+
+static void pps_gpio_remove(struct platform_device *pdev)
+{
+	struct pps_gpio_device_data *data = platform_get_drvdata(pdev);
+
+	free_irq(data->irq, data);
+	pps_unregister_source(data->pps);
+	timer_delete_sync(&data->echo_timer);
+	/* reset echo pin in any case */
+	gpiod_set_value(data->echo_pin, 0);
+	dev_info(&pdev->dev, "removed IRQ %d as PPS source\n", data->irq);
+}
+
+static const struct of_device_id pps_gpio_dt_ids[] = {
+	{ .compatible = "pps-gpio", },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, pps_gpio_dt_ids);
+
+static struct platform_driver pps_gpio_driver = {
+	.probe		= pps_gpio_probe,
+	.remove		= pps_gpio_remove,
+	.driver		= {
+		.name	= PPS_GPIO_NAME,
+		.of_match_table	= pps_gpio_dt_ids,
+	},
+};
+
+module_platform_driver(pps_gpio_driver);
+MODULE_AUTHOR("Ricardo Martins <rasm@fe.up.pt>");
+MODULE_AUTHOR("James Nuss <jamesnuss@nanometrics.ca>");
+MODULE_DESCRIPTION("Use GPIO pin as PPS source");
+MODULE_LICENSE("GPL");
+MODULE_VERSION("1.2.0");