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, 147 insertions, 0 deletions

diff --git a/drivers/hwmon/kbatt.c b/drivers/hwmon/kbatt.c
new file mode 100644
index 000000000..501b8f4de
--- /dev/null
+++ b/drivers/hwmon/kbatt.c
@@ -0,0 +1,147 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2025 KEBA Industrial Automation GmbH
+ *
+ * Driver for KEBA battery monitoring controller FPGA IP core
+ */
+
+#include <linux/hwmon.h>
+#include <linux/io.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/auxiliary_bus.h>
+#include <linux/misc/keba.h>
+#include <linux/mutex.h>
+
+#define KBATT "kbatt"
+
+#define KBATT_CONTROL_REG		0x4
+#define   KBATT_CONTROL_BAT_TEST	0x01
+
+#define KBATT_STATUS_REG		0x8
+#define   KBATT_STATUS_BAT_OK		0x01
+
+#define KBATT_MAX_UPD_INTERVAL	(10 * HZ)
+#define KBATT_SETTLE_TIME_US	(100 * USEC_PER_MSEC)
+
+struct kbatt {
+	/* update lock */
+	struct mutex lock;
+	void __iomem *base;
+
+	unsigned long next_update; /* in jiffies */
+	bool alarm;
+};
+
+static bool kbatt_alarm(struct kbatt *kbatt)
+{
+	mutex_lock(&kbatt->lock);
+
+	if (!kbatt->next_update || time_after(jiffies, kbatt->next_update)) {
+		/* switch load on */
+		iowrite8(KBATT_CONTROL_BAT_TEST,
+			 kbatt->base + KBATT_CONTROL_REG);
+
+		/* wait some time to let things settle */
+		fsleep(KBATT_SETTLE_TIME_US);
+
+		/* check battery state */
+		if (ioread8(kbatt->base + KBATT_STATUS_REG) &
+		    KBATT_STATUS_BAT_OK)
+			kbatt->alarm = false;
+		else
+			kbatt->alarm = true;
+
+		/* switch load off */
+		iowrite8(0, kbatt->base + KBATT_CONTROL_REG);
+
+		kbatt->next_update = jiffies + KBATT_MAX_UPD_INTERVAL;
+	}
+
+	mutex_unlock(&kbatt->lock);
+
+	return kbatt->alarm;
+}
+
+static int kbatt_read(struct device *dev, enum hwmon_sensor_types type,
+		      u32 attr, int channel, long *val)
+{
+	struct kbatt *kbatt = dev_get_drvdata(dev);
+
+	*val = kbatt_alarm(kbatt) ? 1 : 0;
+
+	return 0;
+}
+
+static umode_t kbatt_is_visible(const void *data, enum hwmon_sensor_types type,
+				u32 attr, int channel)
+{
+	if (channel == 0 && attr == hwmon_in_min_alarm)
+		return 0444;
+
+	return 0;
+}
+
+static const struct hwmon_channel_info *kbatt_info[] = {
+	HWMON_CHANNEL_INFO(in,
+			   /* 0: input minimum alarm channel */
+			   HWMON_I_MIN_ALARM),
+	NULL
+};
+
+static const struct hwmon_ops kbatt_hwmon_ops = {
+	.is_visible = kbatt_is_visible,
+	.read = kbatt_read,
+};
+
+static const struct hwmon_chip_info kbatt_chip_info = {
+	.ops = &kbatt_hwmon_ops,
+	.info = kbatt_info,
+};
+
+static int kbatt_probe(struct auxiliary_device *auxdev,
+		       const struct auxiliary_device_id *id)
+{
+	struct keba_batt_auxdev *kbatt_auxdev =
+		container_of(auxdev, struct keba_batt_auxdev, auxdev);
+	struct device *dev = &auxdev->dev;
+	struct device *hwmon_dev;
+	struct kbatt *kbatt;
+	int retval;
+
+	kbatt = devm_kzalloc(dev, sizeof(*kbatt), GFP_KERNEL);
+	if (!kbatt)
+		return -ENOMEM;
+
+	retval = devm_mutex_init(dev, &kbatt->lock);
+	if (retval)
+		return retval;
+
+	kbatt->base = devm_ioremap_resource(dev, &kbatt_auxdev->io);
+	if (IS_ERR(kbatt->base))
+		return PTR_ERR(kbatt->base);
+
+	hwmon_dev = devm_hwmon_device_register_with_info(dev, KBATT, kbatt,
+							 &kbatt_chip_info,
+							 NULL);
+	return PTR_ERR_OR_ZERO(hwmon_dev);
+}
+
+static const struct auxiliary_device_id kbatt_devtype_aux[] = {
+	{ .name = "keba.batt" },
+	{}
+};
+MODULE_DEVICE_TABLE(auxiliary, kbatt_devtype_aux);
+
+static struct auxiliary_driver kbatt_driver_aux = {
+	.name = KBATT,
+	.id_table = kbatt_devtype_aux,
+	.probe = kbatt_probe,
+};
+module_auxiliary_driver(kbatt_driver_aux);
+
+MODULE_AUTHOR("Petar Bojanic <boja@keba.com>");
+MODULE_AUTHOR("Gerhard Engleder <eg@keba.com>");
+MODULE_DESCRIPTION("KEBA battery monitoring controller driver");
+MODULE_LICENSE("GPL");