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, 184 insertions, 0 deletions

diff --git a/drivers/rtc/rtc-imx-sc.c b/drivers/rtc/rtc-imx-sc.c
new file mode 100644
index 000000000..814d51664
--- /dev/null
+++ b/drivers/rtc/rtc-imx-sc.c
@@ -0,0 +1,184 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright 2018 NXP.
+ */
+
+#include <dt-bindings/firmware/imx/rsrc.h>
+#include <linux/arm-smccc.h>
+#include <linux/firmware/imx/sci.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/rtc.h>
+
+#define IMX_SC_TIMER_FUNC_GET_RTC_SEC1970	9
+#define IMX_SC_TIMER_FUNC_SET_RTC_ALARM		8
+#define IMX_SC_TIMER_FUNC_SET_RTC_TIME		6
+
+#define IMX_SIP_SRTC			0xC2000002
+#define IMX_SIP_SRTC_SET_TIME		0x0
+
+#define SC_IRQ_GROUP_RTC    2
+#define SC_IRQ_RTC          1
+
+static struct imx_sc_ipc *rtc_ipc_handle;
+static struct rtc_device *imx_sc_rtc;
+
+struct imx_sc_msg_timer_get_rtc_time {
+	struct imx_sc_rpc_msg hdr;
+	u32 time;
+} __packed;
+
+struct imx_sc_msg_timer_rtc_set_alarm {
+	struct imx_sc_rpc_msg hdr;
+	u16 year;
+	u8 mon;
+	u8 day;
+	u8 hour;
+	u8 min;
+	u8 sec;
+} __packed __aligned(4);
+
+static int imx_sc_rtc_read_time(struct device *dev, struct rtc_time *tm)
+{
+	struct imx_sc_msg_timer_get_rtc_time msg;
+	struct imx_sc_rpc_msg *hdr = &msg.hdr;
+	int ret;
+
+	hdr->ver = IMX_SC_RPC_VERSION;
+	hdr->svc = IMX_SC_RPC_SVC_TIMER;
+	hdr->func = IMX_SC_TIMER_FUNC_GET_RTC_SEC1970;
+	hdr->size = 1;
+
+	ret = imx_scu_call_rpc(rtc_ipc_handle, &msg, true);
+	if (ret) {
+		dev_err(dev, "read rtc time failed, ret %d\n", ret);
+		return ret;
+	}
+
+	rtc_time64_to_tm(msg.time, tm);
+
+	return 0;
+}
+
+static int imx_sc_rtc_set_time(struct device *dev, struct rtc_time *tm)
+{
+	struct arm_smccc_res res;
+
+	/* pack 2 time parameters into 1 register, 16 bits for each */
+	arm_smccc_smc(IMX_SIP_SRTC, IMX_SIP_SRTC_SET_TIME,
+		      ((tm->tm_year + 1900) << 16) | (tm->tm_mon + 1),
+		      (tm->tm_mday << 16) | tm->tm_hour,
+		      (tm->tm_min << 16) | tm->tm_sec,
+		      0, 0, 0, &res);
+
+	return res.a0;
+}
+
+static int imx_sc_rtc_alarm_irq_enable(struct device *dev, unsigned int enable)
+{
+	return imx_scu_irq_group_enable(SC_IRQ_GROUP_RTC, SC_IRQ_RTC, enable);
+}
+
+static int imx_sc_rtc_set_alarm(struct device *dev, struct rtc_wkalrm *alrm)
+{
+	struct imx_sc_msg_timer_rtc_set_alarm msg;
+	struct imx_sc_rpc_msg *hdr = &msg.hdr;
+	int ret;
+	struct rtc_time *alrm_tm = &alrm->time;
+
+	hdr->ver = IMX_SC_RPC_VERSION;
+	hdr->svc = IMX_SC_RPC_SVC_TIMER;
+	hdr->func = IMX_SC_TIMER_FUNC_SET_RTC_ALARM;
+	hdr->size = 3;
+
+	msg.year = alrm_tm->tm_year + 1900;
+	msg.mon = alrm_tm->tm_mon + 1;
+	msg.day = alrm_tm->tm_mday;
+	msg.hour = alrm_tm->tm_hour;
+	msg.min = alrm_tm->tm_min;
+	msg.sec = alrm_tm->tm_sec;
+
+	ret = imx_scu_call_rpc(rtc_ipc_handle, &msg, true);
+	if (ret) {
+		dev_err(dev, "set rtc alarm failed, ret %d\n", ret);
+		return ret;
+	}
+
+	ret = imx_sc_rtc_alarm_irq_enable(dev, alrm->enabled);
+	if (ret) {
+		dev_err(dev, "enable rtc alarm failed, ret %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static const struct rtc_class_ops imx_sc_rtc_ops = {
+	.read_time = imx_sc_rtc_read_time,
+	.set_time = imx_sc_rtc_set_time,
+	.set_alarm = imx_sc_rtc_set_alarm,
+	.alarm_irq_enable = imx_sc_rtc_alarm_irq_enable,
+};
+
+static int imx_sc_rtc_alarm_notify(struct notifier_block *nb,
+					unsigned long event, void *group)
+{
+	/* ignore non-rtc irq */
+	if (!((event & SC_IRQ_RTC) && (*(u8 *)group == SC_IRQ_GROUP_RTC)))
+		return 0;
+
+	rtc_update_irq(imx_sc_rtc, 1, RTC_IRQF | RTC_AF);
+
+	return 0;
+}
+
+static struct notifier_block imx_sc_rtc_alarm_sc_notifier = {
+	.notifier_call = imx_sc_rtc_alarm_notify,
+};
+
+static int imx_sc_rtc_probe(struct platform_device *pdev)
+{
+	int ret;
+
+	ret = imx_scu_get_handle(&rtc_ipc_handle);
+	if (ret)
+		return ret;
+
+	device_init_wakeup(&pdev->dev, true);
+
+	imx_sc_rtc = devm_rtc_allocate_device(&pdev->dev);
+	if (IS_ERR(imx_sc_rtc))
+		return PTR_ERR(imx_sc_rtc);
+
+	imx_sc_rtc->ops = &imx_sc_rtc_ops;
+	imx_sc_rtc->range_min = 0;
+	imx_sc_rtc->range_max = U32_MAX;
+
+	ret = devm_rtc_register_device(imx_sc_rtc);
+	if (ret)
+		return ret;
+
+	imx_scu_irq_register_notifier(&imx_sc_rtc_alarm_sc_notifier);
+
+	return 0;
+}
+
+static const struct of_device_id imx_sc_dt_ids[] = {
+	{ .compatible = "fsl,imx8qxp-sc-rtc", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, imx_sc_dt_ids);
+
+static struct platform_driver imx_sc_rtc_driver = {
+	.driver = {
+		.name	= "imx-sc-rtc",
+		.of_match_table = imx_sc_dt_ids,
+	},
+	.probe		= imx_sc_rtc_probe,
+};
+module_platform_driver(imx_sc_rtc_driver);
+
+MODULE_AUTHOR("Anson Huang <Anson.Huang@nxp.com>");
+MODULE_DESCRIPTION("NXP i.MX System Controller RTC Driver");
+MODULE_LICENSE("GPL");