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, 354 insertions, 0 deletions

diff --git a/drivers/rtc/rtc-mt6397.c b/drivers/rtc/rtc-mt6397.c
new file mode 100644
index 000000000..3d857681f
--- /dev/null
+++ b/drivers/rtc/rtc-mt6397.c
@@ -0,0 +1,354 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+* Copyright (c) 2014-2015 MediaTek Inc.
+* Author: Tianping.Fang <tianping.fang@mediatek.com>
+*/
+
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/mfd/mt6397/core.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/rtc.h>
+#include <linux/mfd/mt6397/rtc.h>
+
+static int mtk_rtc_write_trigger(struct mt6397_rtc *rtc)
+{
+	int ret;
+	u32 data;
+
+	ret = regmap_write(rtc->regmap, rtc->addr_base + rtc->data->wrtgr, 1);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_read_poll_timeout(rtc->regmap,
+					rtc->addr_base + RTC_BBPU, data,
+					!(data & RTC_BBPU_CBUSY),
+					MTK_RTC_POLL_DELAY_US,
+					MTK_RTC_POLL_TIMEOUT);
+	if (ret < 0)
+		dev_err(rtc->rtc_dev->dev.parent,
+			"failed to write WRTGR: %d\n", ret);
+
+	return ret;
+}
+
+static irqreturn_t mtk_rtc_irq_handler_thread(int irq, void *data)
+{
+	struct mt6397_rtc *rtc = data;
+	u32 irqsta, irqen;
+	int ret;
+
+	ret = regmap_read(rtc->regmap, rtc->addr_base + RTC_IRQ_STA, &irqsta);
+	if ((ret >= 0) && (irqsta & RTC_IRQ_STA_AL)) {
+		rtc_update_irq(rtc->rtc_dev, 1, RTC_IRQF | RTC_AF);
+		irqen = irqsta & ~RTC_IRQ_EN_AL;
+		mutex_lock(&rtc->lock);
+		if (regmap_write(rtc->regmap, rtc->addr_base + RTC_IRQ_EN,
+				 irqen) == 0)
+			mtk_rtc_write_trigger(rtc);
+		mutex_unlock(&rtc->lock);
+
+		return IRQ_HANDLED;
+	}
+
+	return IRQ_NONE;
+}
+
+static int __mtk_rtc_read_time(struct mt6397_rtc *rtc,
+			       struct rtc_time *tm, int *sec)
+{
+	int ret;
+	u16 data[RTC_OFFSET_COUNT];
+
+	mutex_lock(&rtc->lock);
+	ret = regmap_bulk_read(rtc->regmap, rtc->addr_base + RTC_TC_SEC,
+			       data, RTC_OFFSET_COUNT);
+	if (ret < 0)
+		goto exit;
+
+	tm->tm_sec = data[RTC_OFFSET_SEC];
+	tm->tm_min = data[RTC_OFFSET_MIN];
+	tm->tm_hour = data[RTC_OFFSET_HOUR];
+	tm->tm_mday = data[RTC_OFFSET_DOM];
+	tm->tm_wday = data[RTC_OFFSET_DOW];
+	tm->tm_mon = data[RTC_OFFSET_MTH] & RTC_TC_MTH_MASK;
+	tm->tm_year = data[RTC_OFFSET_YEAR];
+
+	ret = regmap_read(rtc->regmap, rtc->addr_base + RTC_TC_SEC, sec);
+exit:
+	mutex_unlock(&rtc->lock);
+	return ret;
+}
+
+static int mtk_rtc_read_time(struct device *dev, struct rtc_time *tm)
+{
+	struct mt6397_rtc *rtc = dev_get_drvdata(dev);
+	int sec, ret;
+
+	do {
+		ret = __mtk_rtc_read_time(rtc, tm, &sec);
+		if (ret < 0)
+			goto exit;
+	} while (sec < tm->tm_sec);
+
+	/* HW register start mon/wday from one, but tm_mon/tm_wday start from zero. */
+	tm->tm_mon--;
+	tm->tm_wday--;
+
+exit:
+	return ret;
+}
+
+static int mtk_rtc_set_time(struct device *dev, struct rtc_time *tm)
+{
+	struct mt6397_rtc *rtc = dev_get_drvdata(dev);
+	int ret;
+	u16 data[RTC_OFFSET_COUNT];
+
+	tm->tm_mon++;
+	tm->tm_wday++;
+
+	data[RTC_OFFSET_SEC] = tm->tm_sec;
+	data[RTC_OFFSET_MIN] = tm->tm_min;
+	data[RTC_OFFSET_HOUR] = tm->tm_hour;
+	data[RTC_OFFSET_DOM] = tm->tm_mday;
+	data[RTC_OFFSET_DOW] = tm->tm_wday;
+	data[RTC_OFFSET_MTH] = tm->tm_mon;
+	data[RTC_OFFSET_YEAR] = tm->tm_year;
+
+	mutex_lock(&rtc->lock);
+	ret = regmap_bulk_write(rtc->regmap, rtc->addr_base + RTC_TC_SEC,
+				data, RTC_OFFSET_COUNT);
+	if (ret < 0)
+		goto exit;
+
+	/* Time register write to hardware after call trigger function */
+	ret = mtk_rtc_write_trigger(rtc);
+
+exit:
+	mutex_unlock(&rtc->lock);
+	return ret;
+}
+
+static int mtk_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *alm)
+{
+	struct rtc_time *tm = &alm->time;
+	struct mt6397_rtc *rtc = dev_get_drvdata(dev);
+	u32 irqen, pdn2;
+	int ret;
+	u16 data[RTC_OFFSET_COUNT];
+
+	mutex_lock(&rtc->lock);
+	ret = regmap_read(rtc->regmap, rtc->addr_base + RTC_IRQ_EN, &irqen);
+	if (ret < 0)
+		goto err_exit;
+	ret = regmap_read(rtc->regmap, rtc->addr_base + RTC_PDN2, &pdn2);
+	if (ret < 0)
+		goto err_exit;
+
+	ret = regmap_bulk_read(rtc->regmap, rtc->addr_base + RTC_AL_SEC,
+			       data, RTC_OFFSET_COUNT);
+	if (ret < 0)
+		goto err_exit;
+
+	alm->enabled = !!(irqen & RTC_IRQ_EN_AL);
+	alm->pending = !!(pdn2 & RTC_PDN2_PWRON_ALARM);
+	mutex_unlock(&rtc->lock);
+
+	tm->tm_sec = data[RTC_OFFSET_SEC] & RTC_AL_SEC_MASK;
+	tm->tm_min = data[RTC_OFFSET_MIN] & RTC_AL_MIN_MASK;
+	tm->tm_hour = data[RTC_OFFSET_HOUR] & RTC_AL_HOU_MASK;
+	tm->tm_mday = data[RTC_OFFSET_DOM] & RTC_AL_DOM_MASK;
+	tm->tm_mon = data[RTC_OFFSET_MTH] & RTC_AL_MTH_MASK;
+	tm->tm_year = data[RTC_OFFSET_YEAR] & RTC_AL_YEA_MASK;
+
+	tm->tm_mon--;
+
+	return 0;
+err_exit:
+	mutex_unlock(&rtc->lock);
+	return ret;
+}
+
+static int mtk_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alm)
+{
+	struct rtc_time *tm = &alm->time;
+	struct mt6397_rtc *rtc = dev_get_drvdata(dev);
+	int ret;
+	u16 data[RTC_OFFSET_COUNT];
+
+	tm->tm_mon++;
+
+	mutex_lock(&rtc->lock);
+	ret = regmap_bulk_read(rtc->regmap, rtc->addr_base + RTC_AL_SEC,
+			       data, RTC_OFFSET_COUNT);
+	if (ret < 0)
+		goto exit;
+
+	data[RTC_OFFSET_SEC] = ((data[RTC_OFFSET_SEC] & ~(RTC_AL_SEC_MASK)) |
+				(tm->tm_sec & RTC_AL_SEC_MASK));
+	data[RTC_OFFSET_MIN] = ((data[RTC_OFFSET_MIN] & ~(RTC_AL_MIN_MASK)) |
+				(tm->tm_min & RTC_AL_MIN_MASK));
+	data[RTC_OFFSET_HOUR] = ((data[RTC_OFFSET_HOUR] & ~(RTC_AL_HOU_MASK)) |
+				(tm->tm_hour & RTC_AL_HOU_MASK));
+	data[RTC_OFFSET_DOM] = ((data[RTC_OFFSET_DOM] & ~(RTC_AL_DOM_MASK)) |
+				(tm->tm_mday & RTC_AL_DOM_MASK));
+	data[RTC_OFFSET_MTH] = ((data[RTC_OFFSET_MTH] & ~(RTC_AL_MTH_MASK)) |
+				(tm->tm_mon & RTC_AL_MTH_MASK));
+	data[RTC_OFFSET_YEAR] = ((data[RTC_OFFSET_YEAR] & ~(RTC_AL_YEA_MASK)) |
+				(tm->tm_year & RTC_AL_YEA_MASK));
+
+	if (alm->enabled) {
+		ret = regmap_bulk_write(rtc->regmap,
+					rtc->addr_base + RTC_AL_SEC,
+					data, RTC_OFFSET_COUNT);
+		if (ret < 0)
+			goto exit;
+		ret = regmap_write(rtc->regmap, rtc->addr_base + RTC_AL_MASK,
+				   RTC_AL_MASK_DOW);
+		if (ret < 0)
+			goto exit;
+		ret = regmap_update_bits(rtc->regmap,
+					 rtc->addr_base + RTC_IRQ_EN,
+					 RTC_IRQ_EN_ONESHOT_AL,
+					 RTC_IRQ_EN_ONESHOT_AL);
+		if (ret < 0)
+			goto exit;
+	} else {
+		ret = regmap_update_bits(rtc->regmap,
+					 rtc->addr_base + RTC_IRQ_EN,
+					 RTC_IRQ_EN_ONESHOT_AL, 0);
+		if (ret < 0)
+			goto exit;
+	}
+
+	/* All alarm time register write to hardware after calling
+	 * mtk_rtc_write_trigger. This can avoid race condition if alarm
+	 * occur happen during writing alarm time register.
+	 */
+	ret = mtk_rtc_write_trigger(rtc);
+exit:
+	mutex_unlock(&rtc->lock);
+	return ret;
+}
+
+static const struct rtc_class_ops mtk_rtc_ops = {
+	.read_time  = mtk_rtc_read_time,
+	.set_time   = mtk_rtc_set_time,
+	.read_alarm = mtk_rtc_read_alarm,
+	.set_alarm  = mtk_rtc_set_alarm,
+};
+
+static int mtk_rtc_probe(struct platform_device *pdev)
+{
+	struct resource *res;
+	struct mt6397_chip *mt6397_chip = dev_get_drvdata(pdev->dev.parent);
+	struct mt6397_rtc *rtc;
+	int ret;
+
+	rtc = devm_kzalloc(&pdev->dev, sizeof(struct mt6397_rtc), GFP_KERNEL);
+	if (!rtc)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -EINVAL;
+	rtc->addr_base = res->start;
+
+	rtc->data = of_device_get_match_data(&pdev->dev);
+
+	rtc->irq = platform_get_irq(pdev, 0);
+	if (rtc->irq < 0)
+		return rtc->irq;
+
+	rtc->regmap = mt6397_chip->regmap;
+	mutex_init(&rtc->lock);
+
+	platform_set_drvdata(pdev, rtc);
+
+	rtc->rtc_dev = devm_rtc_allocate_device(&pdev->dev);
+	if (IS_ERR(rtc->rtc_dev))
+		return PTR_ERR(rtc->rtc_dev);
+
+	ret = devm_request_threaded_irq(&pdev->dev, rtc->irq, NULL,
+					mtk_rtc_irq_handler_thread,
+					IRQF_ONESHOT | IRQF_TRIGGER_HIGH,
+					"mt6397-rtc", rtc);
+
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to request alarm IRQ: %d: %d\n",
+			rtc->irq, ret);
+		return ret;
+	}
+
+	device_init_wakeup(&pdev->dev, true);
+
+	rtc->rtc_dev->ops = &mtk_rtc_ops;
+	rtc->rtc_dev->range_min = RTC_TIMESTAMP_BEGIN_1900;
+	rtc->rtc_dev->range_max = mktime64(2027, 12, 31, 23, 59, 59);
+	rtc->rtc_dev->start_secs = mktime64(1968, 1, 2, 0, 0, 0);
+	rtc->rtc_dev->set_start_time = true;
+
+	return devm_rtc_register_device(rtc->rtc_dev);
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int mt6397_rtc_suspend(struct device *dev)
+{
+	struct mt6397_rtc *rtc = dev_get_drvdata(dev);
+
+	if (device_may_wakeup(dev))
+		enable_irq_wake(rtc->irq);
+
+	return 0;
+}
+
+static int mt6397_rtc_resume(struct device *dev)
+{
+	struct mt6397_rtc *rtc = dev_get_drvdata(dev);
+
+	if (device_may_wakeup(dev))
+		disable_irq_wake(rtc->irq);
+
+	return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(mt6397_pm_ops, mt6397_rtc_suspend,
+			mt6397_rtc_resume);
+
+static const struct mtk_rtc_data mt6358_rtc_data = {
+	.wrtgr = RTC_WRTGR_MT6358,
+};
+
+static const struct mtk_rtc_data mt6397_rtc_data = {
+	.wrtgr = RTC_WRTGR_MT6397,
+};
+
+static const struct of_device_id mt6397_rtc_of_match[] = {
+	{ .compatible = "mediatek,mt6323-rtc", .data = &mt6397_rtc_data },
+	{ .compatible = "mediatek,mt6357-rtc", .data = &mt6358_rtc_data },
+	{ .compatible = "mediatek,mt6358-rtc", .data = &mt6358_rtc_data },
+	{ .compatible = "mediatek,mt6397-rtc", .data = &mt6397_rtc_data },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, mt6397_rtc_of_match);
+
+static struct platform_driver mtk_rtc_driver = {
+	.driver = {
+		.name = "mt6397-rtc",
+		.of_match_table = mt6397_rtc_of_match,
+		.pm = &mt6397_pm_ops,
+	},
+	.probe	= mtk_rtc_probe,
+};
+
+module_platform_driver(mtk_rtc_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Tianping Fang <tianping.fang@mediatek.com>");
+MODULE_DESCRIPTION("RTC Driver for MediaTek MT6397 PMIC");