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, 139 insertions, 0 deletions

diff --git a/drivers/iio/buffer/industrialio-triggered-buffer.c b/drivers/iio/buffer/industrialio-triggered-buffer.c
new file mode 100644
index 000000000..9bf75dee7
--- /dev/null
+++ b/drivers/iio/buffer/industrialio-triggered-buffer.c
@@ -0,0 +1,139 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2012 Analog Devices, Inc.
+ *  Author: Lars-Peter Clausen <lars@metafoo.de>
+ */
+
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/module.h>
+#include <linux/iio/iio.h>
+#include <linux/iio/buffer.h>
+#include <linux/iio/buffer_impl.h>
+#include <linux/iio/kfifo_buf.h>
+#include <linux/iio/triggered_buffer.h>
+#include <linux/iio/trigger_consumer.h>
+
+/**
+ * iio_triggered_buffer_setup_ext() - Setup triggered buffer and pollfunc
+ * @indio_dev:		IIO device structure
+ * @h:			Function which will be used as pollfunc top half
+ * @thread:		Function which will be used as pollfunc bottom half
+ * @direction:		Direction of the data stream (in/out).
+ * @setup_ops:		Buffer setup functions to use for this device.
+ *			If NULL the default setup functions for triggered
+ *			buffers will be used.
+ * @buffer_attrs:	Extra sysfs buffer attributes for this IIO buffer
+ *
+ * This function combines some common tasks which will normally be performed
+ * when setting up a triggered buffer. It will allocate the buffer and the
+ * pollfunc.
+ *
+ * Before calling this function the indio_dev structure should already be
+ * completely initialized, but not yet registered. In practice this means that
+ * this function should be called right before iio_device_register().
+ *
+ * To free the resources allocated by this function call
+ * iio_triggered_buffer_cleanup().
+ */
+int iio_triggered_buffer_setup_ext(struct iio_dev *indio_dev,
+	irqreturn_t (*h)(int irq, void *p),
+	irqreturn_t (*thread)(int irq, void *p),
+	enum iio_buffer_direction direction,
+	const struct iio_buffer_setup_ops *setup_ops,
+	const struct iio_dev_attr **buffer_attrs)
+{
+	struct iio_buffer *buffer;
+	int ret;
+
+	/*
+	 * iio_triggered_buffer_cleanup() assumes that the buffer allocated here
+	 * is assigned to indio_dev->buffer but this is only the case if this
+	 * function is the first caller to iio_device_attach_buffer(). If
+	 * indio_dev->buffer is already set then we can't proceed otherwise the
+	 * cleanup function will try to free a buffer that was not allocated here.
+	 */
+	if (indio_dev->buffer)
+		return -EADDRINUSE;
+
+	buffer = iio_kfifo_allocate();
+	if (!buffer) {
+		ret = -ENOMEM;
+		goto error_ret;
+	}
+
+	indio_dev->pollfunc = iio_alloc_pollfunc(h,
+						 thread,
+						 IRQF_ONESHOT,
+						 indio_dev,
+						 "%s_consumer%d",
+						 indio_dev->name,
+						 iio_device_id(indio_dev));
+	if (indio_dev->pollfunc == NULL) {
+		ret = -ENOMEM;
+		goto error_kfifo_free;
+	}
+
+	/* Ring buffer functions - here trigger setup related */
+	indio_dev->setup_ops = setup_ops;
+
+	/* Flag that polled ring buffering is possible */
+	indio_dev->modes |= INDIO_BUFFER_TRIGGERED;
+
+	buffer->direction = direction;
+	buffer->attrs = buffer_attrs;
+
+	ret = iio_device_attach_buffer(indio_dev, buffer);
+	if (ret < 0)
+		goto error_dealloc_pollfunc;
+
+	return 0;
+
+error_dealloc_pollfunc:
+	iio_dealloc_pollfunc(indio_dev->pollfunc);
+error_kfifo_free:
+	iio_kfifo_free(buffer);
+error_ret:
+	return ret;
+}
+EXPORT_SYMBOL(iio_triggered_buffer_setup_ext);
+
+/**
+ * iio_triggered_buffer_cleanup() - Free resources allocated by iio_triggered_buffer_setup_ext()
+ * @indio_dev: IIO device structure
+ */
+void iio_triggered_buffer_cleanup(struct iio_dev *indio_dev)
+{
+	iio_dealloc_pollfunc(indio_dev->pollfunc);
+	iio_kfifo_free(indio_dev->buffer);
+}
+EXPORT_SYMBOL(iio_triggered_buffer_cleanup);
+
+static void devm_iio_triggered_buffer_clean(void *indio_dev)
+{
+	iio_triggered_buffer_cleanup(indio_dev);
+}
+
+int devm_iio_triggered_buffer_setup_ext(struct device *dev,
+					struct iio_dev *indio_dev,
+					irqreturn_t (*h)(int irq, void *p),
+					irqreturn_t (*thread)(int irq, void *p),
+					enum iio_buffer_direction direction,
+					const struct iio_buffer_setup_ops *ops,
+					const struct iio_dev_attr **buffer_attrs)
+{
+	int ret;
+
+	ret = iio_triggered_buffer_setup_ext(indio_dev, h, thread, direction,
+					     ops, buffer_attrs);
+	if (ret)
+		return ret;
+
+	return devm_add_action_or_reset(dev, devm_iio_triggered_buffer_clean,
+					indio_dev);
+}
+EXPORT_SYMBOL_GPL(devm_iio_triggered_buffer_setup_ext);
+
+MODULE_AUTHOR("Lars-Peter Clausen <lars@metafoo.de>");
+MODULE_DESCRIPTION("IIO helper functions for setting up triggered buffers");
+MODULE_LICENSE("GPL");