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, 198 insertions, 0 deletions

diff --git a/drivers/leds/trigger/ledtrig-transient.c b/drivers/leds/trigger/ledtrig-transient.c
new file mode 100644
index 000000000..8d928bb2a
--- /dev/null
+++ b/drivers/leds/trigger/ledtrig-transient.c
@@ -0,0 +1,198 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// LED Kernel Transient Trigger
+//
+// Transient trigger allows one shot timer activation. Please refer to
+// Documentation/leds/ledtrig-transient.rst for details
+// Copyright (C) 2012 Shuah Khan <shuahkhan@gmail.com>
+//
+// Based on Richard Purdie's ledtrig-timer.c and Atsushi Nemoto's
+// ledtrig-heartbeat.c
+// Design and use-case input from Jonas Bonn <jonas@southpole.se> and
+// Neil Brown <neilb@suse.de>
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/slab.h>
+#include <linux/timer.h>
+#include <linux/leds.h>
+#include "../leds.h"
+
+struct transient_trig_data {
+	int activate;
+	int state;
+	int restore_state;
+	unsigned long duration;
+	struct timer_list timer;
+	struct led_classdev *led_cdev;
+};
+
+static void transient_timer_function(struct timer_list *t)
+{
+	struct transient_trig_data *transient_data =
+		timer_container_of(transient_data, t, timer);
+	struct led_classdev *led_cdev = transient_data->led_cdev;
+
+	transient_data->activate = 0;
+	led_set_brightness_nosleep(led_cdev, transient_data->restore_state);
+}
+
+static ssize_t transient_activate_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct transient_trig_data *transient_data =
+		led_trigger_get_drvdata(dev);
+
+	return sprintf(buf, "%d\n", transient_data->activate);
+}
+
+static ssize_t transient_activate_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t size)
+{
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
+	struct transient_trig_data *transient_data =
+		led_trigger_get_drvdata(dev);
+	unsigned long state;
+	ssize_t ret;
+
+	ret = kstrtoul(buf, 10, &state);
+	if (ret)
+		return ret;
+
+	if (state != 1 && state != 0)
+		return -EINVAL;
+
+	/* cancel the running timer */
+	if (state == 0 && transient_data->activate == 1) {
+		timer_delete(&transient_data->timer);
+		transient_data->activate = state;
+		led_set_brightness_nosleep(led_cdev,
+					transient_data->restore_state);
+		return size;
+	}
+
+	/* start timer if there is no active timer */
+	if (state == 1 && transient_data->activate == 0 &&
+	    transient_data->duration != 0) {
+		transient_data->activate = state;
+		led_set_brightness_nosleep(led_cdev, transient_data->state);
+		transient_data->restore_state =
+		    (transient_data->state == LED_FULL) ? LED_OFF : LED_FULL;
+		mod_timer(&transient_data->timer,
+			  jiffies + msecs_to_jiffies(transient_data->duration));
+	}
+
+	/* state == 0 && transient_data->activate == 0
+		timer is not active - just return */
+	/* state == 1 && transient_data->activate == 1
+		timer is already active - just return */
+
+	return size;
+}
+
+static ssize_t transient_duration_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct transient_trig_data *transient_data = led_trigger_get_drvdata(dev);
+
+	return sprintf(buf, "%lu\n", transient_data->duration);
+}
+
+static ssize_t transient_duration_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t size)
+{
+	struct transient_trig_data *transient_data =
+		led_trigger_get_drvdata(dev);
+	unsigned long state;
+	ssize_t ret;
+
+	ret = kstrtoul(buf, 10, &state);
+	if (ret)
+		return ret;
+
+	transient_data->duration = state;
+	return size;
+}
+
+static ssize_t transient_state_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct transient_trig_data *transient_data =
+		led_trigger_get_drvdata(dev);
+	int state;
+
+	state = (transient_data->state == LED_FULL) ? 1 : 0;
+	return sprintf(buf, "%d\n", state);
+}
+
+static ssize_t transient_state_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t size)
+{
+	struct transient_trig_data *transient_data =
+		led_trigger_get_drvdata(dev);
+	unsigned long state;
+	ssize_t ret;
+
+	ret = kstrtoul(buf, 10, &state);
+	if (ret)
+		return ret;
+
+	if (state != 1 && state != 0)
+		return -EINVAL;
+
+	transient_data->state = (state == 1) ? LED_FULL : LED_OFF;
+	return size;
+}
+
+static DEVICE_ATTR(activate, 0644, transient_activate_show,
+		   transient_activate_store);
+static DEVICE_ATTR(duration, 0644, transient_duration_show,
+		   transient_duration_store);
+static DEVICE_ATTR(state, 0644, transient_state_show, transient_state_store);
+
+static struct attribute *transient_trig_attrs[] = {
+	&dev_attr_activate.attr,
+	&dev_attr_duration.attr,
+	&dev_attr_state.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(transient_trig);
+
+static int transient_trig_activate(struct led_classdev *led_cdev)
+{
+	struct transient_trig_data *tdata;
+
+	tdata = kzalloc_obj(struct transient_trig_data);
+	if (!tdata)
+		return -ENOMEM;
+
+	led_set_trigger_data(led_cdev, tdata);
+	tdata->led_cdev = led_cdev;
+
+	timer_setup(&tdata->timer, transient_timer_function, 0);
+
+	return 0;
+}
+
+static void transient_trig_deactivate(struct led_classdev *led_cdev)
+{
+	struct transient_trig_data *transient_data = led_get_trigger_data(led_cdev);
+
+	timer_shutdown_sync(&transient_data->timer);
+	led_set_brightness_nosleep(led_cdev, transient_data->restore_state);
+	kfree(transient_data);
+}
+
+static struct led_trigger transient_trigger = {
+	.name     = "transient",
+	.activate = transient_trig_activate,
+	.deactivate = transient_trig_deactivate,
+	.groups = transient_trig_groups,
+};
+module_led_trigger(transient_trigger);
+
+MODULE_AUTHOR("Shuah Khan <shuahkhan@gmail.com>");
+MODULE_DESCRIPTION("Transient LED trigger");
+MODULE_LICENSE("GPL v2");