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, 145 insertions, 0 deletions

diff --git a/drivers/rtc/rtc-r9701.c b/drivers/rtc/rtc-r9701.c
new file mode 100644
index 000000000..60a3c3d74
--- /dev/null
+++ b/drivers/rtc/rtc-r9701.c
@@ -0,0 +1,145 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Driver for Epson RTC-9701JE
+ *
+ * Copyright (C) 2008 Magnus Damm
+ *
+ * Based on rtc-max6902.c
+ *
+ * Copyright (C) 2006 8D Technologies inc.
+ * Copyright (C) 2004 Compulab Ltd.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/device.h>
+#include <linux/init.h>
+#include <linux/rtc.h>
+#include <linux/spi/spi.h>
+#include <linux/bcd.h>
+#include <linux/delay.h>
+#include <linux/bitops.h>
+
+#define RSECCNT	0x00	/* Second Counter */
+#define RMINCNT	0x01	/* Minute Counter */
+#define RHRCNT	0x02	/* Hour Counter */
+#define RWKCNT	0x03	/* Week Counter */
+#define RDAYCNT	0x04	/* Day Counter */
+#define RMONCNT	0x05	/* Month Counter */
+#define RYRCNT	0x06	/* Year Counter */
+#define R100CNT	0x07	/* Y100 Counter */
+#define RMINAR	0x08	/* Minute Alarm */
+#define RHRAR	0x09	/* Hour Alarm */
+#define RWKAR	0x0a	/* Week/Day Alarm */
+#define RTIMCNT	0x0c	/* Interval Timer */
+#define REXT	0x0d	/* Extension Register */
+#define RFLAG	0x0e	/* RTC Flag Register */
+#define RCR	0x0f	/* RTC Control Register */
+
+static int write_reg(struct device *dev, int address, unsigned char data)
+{
+	struct spi_device *spi = to_spi_device(dev);
+	unsigned char buf[2];
+
+	buf[0] = address & 0x7f;
+	buf[1] = data;
+
+	return spi_write(spi, buf, ARRAY_SIZE(buf));
+}
+
+static int read_regs(struct device *dev, unsigned char *regs, int no_regs)
+{
+	struct spi_device *spi = to_spi_device(dev);
+	u8 txbuf[1], rxbuf[1];
+	int k, ret;
+
+	ret = 0;
+
+	for (k = 0; ret == 0 && k < no_regs; k++) {
+		txbuf[0] = 0x80 | regs[k];
+		ret = spi_write_then_read(spi, txbuf, 1, rxbuf, 1);
+		regs[k] = rxbuf[0];
+	}
+
+	return ret;
+}
+
+static int r9701_get_datetime(struct device *dev, struct rtc_time *dt)
+{
+	int ret;
+	unsigned char buf[] = { RSECCNT, RMINCNT, RHRCNT,
+				RDAYCNT, RMONCNT, RYRCNT };
+
+	ret = read_regs(dev, buf, ARRAY_SIZE(buf));
+	if (ret)
+		return ret;
+
+	dt->tm_sec = bcd2bin(buf[0]); /* RSECCNT */
+	dt->tm_min = bcd2bin(buf[1]); /* RMINCNT */
+	dt->tm_hour = bcd2bin(buf[2]); /* RHRCNT */
+
+	dt->tm_mday = bcd2bin(buf[3]); /* RDAYCNT */
+	dt->tm_mon = bcd2bin(buf[4]) - 1; /* RMONCNT */
+	dt->tm_year = bcd2bin(buf[5]) + 100; /* RYRCNT */
+
+	return 0;
+}
+
+static int r9701_set_datetime(struct device *dev, struct rtc_time *dt)
+{
+	int ret;
+
+	ret = write_reg(dev, RHRCNT, bin2bcd(dt->tm_hour));
+	ret = ret ? ret : write_reg(dev, RMINCNT, bin2bcd(dt->tm_min));
+	ret = ret ? ret : write_reg(dev, RSECCNT, bin2bcd(dt->tm_sec));
+	ret = ret ? ret : write_reg(dev, RDAYCNT, bin2bcd(dt->tm_mday));
+	ret = ret ? ret : write_reg(dev, RMONCNT, bin2bcd(dt->tm_mon + 1));
+	ret = ret ? ret : write_reg(dev, RYRCNT, bin2bcd(dt->tm_year - 100));
+
+	return ret;
+}
+
+static const struct rtc_class_ops r9701_rtc_ops = {
+	.read_time	= r9701_get_datetime,
+	.set_time	= r9701_set_datetime,
+};
+
+static int r9701_probe(struct spi_device *spi)
+{
+	struct rtc_device *rtc;
+	unsigned char tmp;
+	int res;
+
+	tmp = R100CNT;
+	res = read_regs(&spi->dev, &tmp, 1);
+	if (res || tmp != 0x20) {
+		dev_err(&spi->dev, "cannot read RTC register\n");
+		return -ENODEV;
+	}
+
+	rtc = devm_rtc_allocate_device(&spi->dev);
+	if (IS_ERR(rtc))
+		return PTR_ERR(rtc);
+
+	spi_set_drvdata(spi, rtc);
+	rtc->ops = &r9701_rtc_ops;
+	rtc->range_min = RTC_TIMESTAMP_BEGIN_2000;
+	rtc->range_max = RTC_TIMESTAMP_END_2099;
+
+	return devm_rtc_register_device(rtc);
+}
+
+static struct spi_driver r9701_driver = {
+	.driver = {
+		.name	= "rtc-r9701",
+	},
+	.probe	= r9701_probe,
+};
+
+module_spi_driver(r9701_driver);
+
+MODULE_DESCRIPTION("r9701 spi RTC driver");
+MODULE_AUTHOR("Magnus Damm <damm@opensource.se>");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("spi:rtc-r9701");