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, 157 insertions, 0 deletions

diff --git a/drivers/iio/buffer/industrialio-buffer-cb.c b/drivers/iio/buffer/industrialio-buffer-cb.c
new file mode 100644
index 000000000..b58263bcf
--- /dev/null
+++ b/drivers/iio/buffer/industrialio-buffer-cb.c
@@ -0,0 +1,157 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* The industrial I/O callback buffer
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/export.h>
+#include <linux/iio/iio.h>
+#include <linux/iio/buffer_impl.h>
+#include <linux/iio/consumer.h>
+
+struct iio_cb_buffer {
+	struct iio_buffer buffer;
+	/* Must be safe to call from any context (e.g. must not sleep). */
+	int (*cb)(const void *data, void *private);
+	void *private;
+	struct iio_channel *channels;
+	struct iio_dev *indio_dev;
+};
+
+static struct iio_cb_buffer *buffer_to_cb_buffer(struct iio_buffer *buffer)
+{
+	return container_of(buffer, struct iio_cb_buffer, buffer);
+}
+
+static int iio_buffer_cb_store_to(struct iio_buffer *buffer, const void *data)
+{
+	struct iio_cb_buffer *cb_buff = buffer_to_cb_buffer(buffer);
+	return cb_buff->cb(data, cb_buff->private);
+}
+
+static void iio_buffer_cb_release(struct iio_buffer *buffer)
+{
+	struct iio_cb_buffer *cb_buff = buffer_to_cb_buffer(buffer);
+
+	bitmap_free(cb_buff->buffer.scan_mask);
+	kfree(cb_buff);
+}
+
+static const struct iio_buffer_access_funcs iio_cb_access = {
+	.store_to = &iio_buffer_cb_store_to,
+	.release = &iio_buffer_cb_release,
+
+	.modes = INDIO_BUFFER_SOFTWARE | INDIO_BUFFER_TRIGGERED,
+};
+
+struct iio_cb_buffer *iio_channel_get_all_cb(struct device *dev,
+					     int (*cb)(const void *data,
+						       void *private),
+					     void *private)
+{
+	int ret;
+	struct iio_cb_buffer *cb_buff;
+	struct iio_channel *chan;
+
+	if (!cb) {
+		dev_err(dev, "Invalid arguments: A callback must be provided!\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	cb_buff = kzalloc_obj(*cb_buff);
+	if (cb_buff == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	iio_buffer_init(&cb_buff->buffer);
+
+	cb_buff->private = private;
+	cb_buff->cb = cb;
+	cb_buff->buffer.access = &iio_cb_access;
+
+	cb_buff->channels = iio_channel_get_all(dev);
+	if (IS_ERR(cb_buff->channels)) {
+		ret = PTR_ERR(cb_buff->channels);
+		goto error_free_cb_buff;
+	}
+
+	cb_buff->indio_dev = cb_buff->channels[0].indio_dev;
+	cb_buff->buffer.scan_mask = bitmap_zalloc(iio_get_masklength(cb_buff->indio_dev),
+						  GFP_KERNEL);
+	if (cb_buff->buffer.scan_mask == NULL) {
+		ret = -ENOMEM;
+		goto error_release_channels;
+	}
+	chan = &cb_buff->channels[0];
+	while (chan->indio_dev) {
+		if (chan->indio_dev != cb_buff->indio_dev) {
+			ret = -EINVAL;
+			goto error_free_scan_mask;
+		}
+		set_bit(chan->channel->scan_index,
+			cb_buff->buffer.scan_mask);
+		chan++;
+	}
+
+	return cb_buff;
+
+error_free_scan_mask:
+	bitmap_free(cb_buff->buffer.scan_mask);
+error_release_channels:
+	iio_channel_release_all(cb_buff->channels);
+error_free_cb_buff:
+	kfree(cb_buff);
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(iio_channel_get_all_cb);
+
+int iio_channel_cb_set_buffer_watermark(struct iio_cb_buffer *cb_buff,
+					size_t watermark)
+{
+	if (!watermark)
+		return -EINVAL;
+	cb_buff->buffer.watermark = watermark;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iio_channel_cb_set_buffer_watermark);
+
+int iio_channel_start_all_cb(struct iio_cb_buffer *cb_buff)
+{
+	return iio_update_buffers(cb_buff->indio_dev, &cb_buff->buffer,
+				  NULL);
+}
+EXPORT_SYMBOL_GPL(iio_channel_start_all_cb);
+
+void iio_channel_stop_all_cb(struct iio_cb_buffer *cb_buff)
+{
+	iio_update_buffers(cb_buff->indio_dev, NULL, &cb_buff->buffer);
+}
+EXPORT_SYMBOL_GPL(iio_channel_stop_all_cb);
+
+void iio_channel_release_all_cb(struct iio_cb_buffer *cb_buff)
+{
+	iio_channel_release_all(cb_buff->channels);
+	iio_buffer_put(&cb_buff->buffer);
+}
+EXPORT_SYMBOL_GPL(iio_channel_release_all_cb);
+
+struct iio_channel
+*iio_channel_cb_get_channels(const struct iio_cb_buffer *cb_buffer)
+{
+	return cb_buffer->channels;
+}
+EXPORT_SYMBOL_GPL(iio_channel_cb_get_channels);
+
+struct iio_dev
+*iio_channel_cb_get_iio_dev(const struct iio_cb_buffer *cb_buffer)
+{
+	return cb_buffer->indio_dev;
+}
+EXPORT_SYMBOL_GPL(iio_channel_cb_get_iio_dev);
+
+MODULE_AUTHOR("Jonathan Cameron <jic23@kernel.org>");
+MODULE_DESCRIPTION("Industrial I/O callback buffer");
+MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS("IIO_CONSUMER");