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, 168 insertions, 0 deletions

diff --git a/drivers/bus/simple-pm-bus.c b/drivers/bus/simple-pm-bus.c
new file mode 100644
index 000000000..c920bd6fb
--- /dev/null
+++ b/drivers/bus/simple-pm-bus.c
@@ -0,0 +1,168 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Simple Power-Managed Bus Driver
+ *
+ * Copyright (C) 2014-2015 Glider bvba
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/clk.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+
+struct simple_pm_bus {
+	struct clk_bulk_data *clks;
+	int num_clks;
+};
+
+static int simple_pm_bus_probe(struct platform_device *pdev)
+{
+	const struct device *dev = &pdev->dev;
+	const struct of_dev_auxdata *lookup = dev_get_platdata(dev);
+	struct device_node *np = dev->of_node;
+	const struct of_device_id *match;
+	struct simple_pm_bus *bus;
+
+	/*
+	 * Allow user to use driver_override to bind this driver to a
+	 * transparent bus device which has a different compatible string
+	 * that's not listed in simple_pm_bus_of_match. We don't want to do any
+	 * of the simple-pm-bus tasks for these devices, so return early.
+	 */
+	if (device_has_driver_override(&pdev->dev))
+		return 0;
+
+	match = of_match_device(dev->driver->of_match_table, dev);
+	/*
+	 * These are transparent bus devices (not simple-pm-bus matches) that
+	 * have their child nodes populated automatically.  So, don't need to
+	 * do anything more. We only match with the device if this driver is
+	 * the most specific match because we don't want to incorrectly bind to
+	 * a device that has a more specific driver.
+	 */
+	if (match && match->data) {
+		if (of_property_match_string(np, "compatible", match->compatible) == 0)
+			return 0;
+		else
+			return -ENODEV;
+	}
+
+	bus = devm_kzalloc(&pdev->dev, sizeof(*bus), GFP_KERNEL);
+	if (!bus)
+		return -ENOMEM;
+
+	bus->num_clks = devm_clk_bulk_get_all(&pdev->dev, &bus->clks);
+	if (bus->num_clks < 0)
+		return dev_err_probe(&pdev->dev, bus->num_clks, "failed to get clocks\n");
+
+	dev_set_drvdata(&pdev->dev, bus);
+
+	dev_dbg(&pdev->dev, "%s\n", __func__);
+
+	pm_runtime_enable(&pdev->dev);
+
+	if (np)
+		of_platform_populate(np, NULL, lookup, &pdev->dev);
+
+	return 0;
+}
+
+static void simple_pm_bus_remove(struct platform_device *pdev)
+{
+	const void *data = of_device_get_match_data(&pdev->dev);
+
+	if (device_has_driver_override(&pdev->dev) || data)
+		return;
+
+	dev_dbg(&pdev->dev, "%s\n", __func__);
+
+	pm_runtime_disable(&pdev->dev);
+}
+
+static int simple_pm_bus_runtime_suspend(struct device *dev)
+{
+	struct simple_pm_bus *bus = dev_get_drvdata(dev);
+
+	clk_bulk_disable_unprepare(bus->num_clks, bus->clks);
+
+	return 0;
+}
+
+static int simple_pm_bus_runtime_resume(struct device *dev)
+{
+	struct simple_pm_bus *bus = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_bulk_prepare_enable(bus->num_clks, bus->clks);
+	if (ret) {
+		dev_err(dev, "failed to enable clocks: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int simple_pm_bus_suspend(struct device *dev)
+{
+	struct simple_pm_bus *bus = dev_get_drvdata(dev);
+
+	if (!bus)
+		return 0;
+
+	return pm_runtime_force_suspend(dev);
+}
+
+static int simple_pm_bus_resume(struct device *dev)
+{
+	struct simple_pm_bus *bus = dev_get_drvdata(dev);
+
+	if (!bus)
+		return 0;
+
+	return pm_runtime_force_resume(dev);
+}
+
+static const struct dev_pm_ops simple_pm_bus_pm_ops = {
+	RUNTIME_PM_OPS(simple_pm_bus_runtime_suspend, simple_pm_bus_runtime_resume, NULL)
+	NOIRQ_SYSTEM_SLEEP_PM_OPS(simple_pm_bus_suspend, simple_pm_bus_resume)
+};
+
+#define ONLY_BUS	((void *) 1) /* Match if the device is only a bus. */
+
+static const struct of_device_id simple_pm_bus_of_match[] = {
+	{ .compatible = "simple-pm-bus", },
+	{ .compatible = "simple-bus",	.data = ONLY_BUS },
+	{ .compatible = "simple-mfd",	.data = ONLY_BUS },
+	{ .compatible = "isa",		.data = ONLY_BUS },
+	{ .compatible = "arm,amba-bus",	.data = ONLY_BUS },
+	{ .compatible = "fsl,ls1021a-scfg", },
+	{ .compatible = "fsl,ls1043a-scfg", },
+	{ .compatible = "fsl,ls1046a-scfg", },
+	{ .compatible = "fsl,ls1088a-isc", },
+	{ .compatible = "fsl,ls2080a-isc", },
+	{ .compatible = "fsl,lx2160a-isc", },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, simple_pm_bus_of_match);
+
+static struct platform_driver simple_pm_bus_driver = {
+	.probe = simple_pm_bus_probe,
+	.remove = simple_pm_bus_remove,
+	.driver = {
+		.name = "simple-pm-bus",
+		.of_match_table = simple_pm_bus_of_match,
+		.pm = pm_ptr(&simple_pm_bus_pm_ops),
+	},
+};
+
+module_platform_driver(simple_pm_bus_driver);
+
+MODULE_DESCRIPTION("Simple Power-Managed Bus Driver");
+MODULE_AUTHOR("Geert Uytterhoeven <geert+renesas@glider.be>");