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, 99 insertions, 0 deletions

diff --git a/drivers/reset/reset-gpio.c b/drivers/reset/reset-gpio.c
new file mode 100644
index 000000000..bf95296a5
--- /dev/null
+++ b/drivers/reset/reset-gpio.c
@@ -0,0 +1,99 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/auxiliary_bus.h>
+#include <linux/gpio/consumer.h>
+#include <linux/module.h>
+#include <linux/property.h>
+#include <linux/reset-controller.h>
+
+struct reset_gpio_priv {
+	struct reset_controller_dev rc;
+	struct gpio_desc *reset;
+};
+
+static inline struct reset_gpio_priv
+*rc_to_reset_gpio(struct reset_controller_dev *rc)
+{
+	return container_of(rc, struct reset_gpio_priv, rc);
+}
+
+static int reset_gpio_assert(struct reset_controller_dev *rc, unsigned long id)
+{
+	struct reset_gpio_priv *priv = rc_to_reset_gpio(rc);
+
+	return gpiod_set_value_cansleep(priv->reset, 1);
+}
+
+static int reset_gpio_deassert(struct reset_controller_dev *rc,
+			       unsigned long id)
+{
+	struct reset_gpio_priv *priv = rc_to_reset_gpio(rc);
+
+	return gpiod_set_value_cansleep(priv->reset, 0);
+}
+
+static int reset_gpio_status(struct reset_controller_dev *rc, unsigned long id)
+{
+	struct reset_gpio_priv *priv = rc_to_reset_gpio(rc);
+
+	return gpiod_get_value_cansleep(priv->reset);
+}
+
+static const struct reset_control_ops reset_gpio_ops = {
+	.assert = reset_gpio_assert,
+	.deassert = reset_gpio_deassert,
+	.status = reset_gpio_status,
+};
+
+static int reset_gpio_fwnode_xlate(struct reset_controller_dev *rcdev,
+				   const struct fwnode_reference_args *reset_spec)
+{
+	return reset_spec->args[0];
+}
+
+static int reset_gpio_probe(struct auxiliary_device *adev,
+			    const struct auxiliary_device_id *id)
+{
+	struct device *dev = &adev->dev;
+	struct reset_gpio_priv *priv;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->reset = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH);
+	if (IS_ERR(priv->reset))
+		return dev_err_probe(dev, PTR_ERR(priv->reset),
+				     "Could not get reset gpios\n");
+
+	priv->rc.ops = &reset_gpio_ops;
+	priv->rc.owner = THIS_MODULE;
+	priv->rc.dev = dev;
+
+	/* Cells to match GPIO specifier, but it's not really used */
+	priv->rc.fwnode_reset_n_cells = 2;
+	priv->rc.fwnode_xlate = reset_gpio_fwnode_xlate;
+	priv->rc.nr_resets = 1;
+
+	return devm_reset_controller_register(dev, &priv->rc);
+}
+
+static const struct auxiliary_device_id reset_gpio_ids[] = {
+	{ .name = "reset.gpio" },
+	{}
+};
+MODULE_DEVICE_TABLE(auxiliary, reset_gpio_ids);
+
+static struct auxiliary_driver reset_gpio_driver = {
+	.probe		= reset_gpio_probe,
+	.id_table	= reset_gpio_ids,
+	.driver	= {
+		.name = "reset-gpio",
+		.suppress_bind_attrs = true,
+	},
+};
+module_auxiliary_driver(reset_gpio_driver);
+
+MODULE_AUTHOR("Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>");
+MODULE_DESCRIPTION("Generic GPIO reset driver");
+MODULE_LICENSE("GPL");