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, 141 insertions, 0 deletions

diff --git a/drivers/iio/trigger/iio-trig-loop.c b/drivers/iio/trigger/iio-trig-loop.c
new file mode 100644
index 000000000..580a46503
--- /dev/null
+++ b/drivers/iio/trigger/iio-trig-loop.c
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2016 Jonathan Cameron <jic23@kernel.org>
+ *
+ * Based on a mashup of the hrtimer trigger and continuous sampling proposal of
+ * Gregor Boirie <gregor.boirie@parrot.com>
+ *
+ * Note this is still rather experimental and may eat babies.
+ *
+ * Todo
+ * * Protect against connection of devices that 'need' the top half
+ *   handler.
+ * * Work out how to run top half handlers in this context if it is
+ *   safe to do so (timestamp grabbing for example)
+ *
+ * Tested against a max1363. Used about 33% cpu for the thread and 20%
+ * for generic_buffer piping to /dev/null. Watermark set at 64 on a 128
+ * element kfifo buffer.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/irq_work.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+
+#include <linux/iio/iio.h>
+#include <linux/iio/trigger.h>
+#include <linux/iio/sw_trigger.h>
+
+struct iio_loop_info {
+	struct iio_sw_trigger swt;
+	struct task_struct *task;
+};
+
+static const struct config_item_type iio_loop_type = {
+	.ct_owner = THIS_MODULE,
+};
+
+static int iio_loop_thread(void *data)
+{
+	struct iio_trigger *trig = data;
+
+	set_freezable();
+
+	do {
+		iio_trigger_poll_nested(trig);
+	} while (likely(!kthread_freezable_should_stop(NULL)));
+
+	return 0;
+}
+
+static int iio_loop_trigger_set_state(struct iio_trigger *trig, bool state)
+{
+	struct iio_loop_info *loop_trig = iio_trigger_get_drvdata(trig);
+
+	if (state) {
+		loop_trig->task = kthread_run(iio_loop_thread,
+					      trig, trig->name);
+		if (IS_ERR(loop_trig->task)) {
+			dev_err(&trig->dev,
+				"failed to create trigger loop thread\n");
+			return PTR_ERR(loop_trig->task);
+		}
+	} else {
+		kthread_stop(loop_trig->task);
+	}
+
+	return 0;
+}
+
+static const struct iio_trigger_ops iio_loop_trigger_ops = {
+	.set_trigger_state = iio_loop_trigger_set_state,
+};
+
+static struct iio_sw_trigger *iio_trig_loop_probe(const char *name)
+{
+	struct iio_loop_info *trig_info;
+	int ret;
+
+	trig_info = kzalloc_obj(*trig_info);
+	if (!trig_info)
+		return ERR_PTR(-ENOMEM);
+
+	trig_info->swt.trigger = iio_trigger_alloc(NULL, "%s", name);
+	if (!trig_info->swt.trigger) {
+		ret = -ENOMEM;
+		goto err_free_trig_info;
+	}
+
+	iio_trigger_set_drvdata(trig_info->swt.trigger, trig_info);
+	trig_info->swt.trigger->ops = &iio_loop_trigger_ops;
+
+	ret = iio_trigger_register(trig_info->swt.trigger);
+	if (ret)
+		goto err_free_trigger;
+
+	iio_swt_group_init_type_name(&trig_info->swt, name, &iio_loop_type);
+
+	return &trig_info->swt;
+
+err_free_trigger:
+	iio_trigger_free(trig_info->swt.trigger);
+err_free_trig_info:
+	kfree(trig_info);
+
+	return ERR_PTR(ret);
+}
+
+static int iio_trig_loop_remove(struct iio_sw_trigger *swt)
+{
+	struct iio_loop_info *trig_info;
+
+	trig_info = iio_trigger_get_drvdata(swt->trigger);
+
+	iio_trigger_unregister(swt->trigger);
+	iio_trigger_free(swt->trigger);
+	kfree(trig_info);
+
+	return 0;
+}
+
+static const struct iio_sw_trigger_ops iio_trig_loop_ops = {
+	.probe = iio_trig_loop_probe,
+	.remove = iio_trig_loop_remove,
+};
+
+static struct iio_sw_trigger_type iio_trig_loop = {
+	.name = "loop",
+	.owner = THIS_MODULE,
+	.ops = &iio_trig_loop_ops,
+};
+
+module_iio_sw_trigger_driver(iio_trig_loop);
+
+MODULE_AUTHOR("Jonathan Cameron <jic23@kernel.org>");
+MODULE_DESCRIPTION("Loop based trigger for the iio subsystem");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:iio-trig-loop");