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, 148 insertions, 0 deletions

diff --git a/drivers/cpufreq/airoha-cpufreq.c b/drivers/cpufreq/airoha-cpufreq.c
new file mode 100644
index 000000000..3e7770860
--- /dev/null
+++ b/drivers/cpufreq/airoha-cpufreq.c
@@ -0,0 +1,148 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bitfield.h>
+#include <linux/cpufreq.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/pm_domain.h>
+#include <linux/pm_runtime.h>
+#include <linux/slab.h>
+
+#include "cpufreq-dt.h"
+
+struct airoha_cpufreq_priv {
+	int opp_token;
+	struct dev_pm_domain_list *pd_list;
+	struct platform_device *cpufreq_dt;
+};
+
+static struct platform_device *cpufreq_pdev;
+
+/* NOP function to disable OPP from setting clock */
+static int airoha_cpufreq_config_clks_nop(struct device *dev,
+					  struct opp_table *opp_table,
+					  struct dev_pm_opp *opp,
+					  void *data, bool scaling_down)
+{
+	return 0;
+}
+
+static const char * const airoha_cpufreq_clk_names[] = { "cpu", NULL };
+static const char * const airoha_cpufreq_pd_names[] = { "perf" };
+
+static int airoha_cpufreq_probe(struct platform_device *pdev)
+{
+	const struct dev_pm_domain_attach_data attach_data = {
+		.pd_names = airoha_cpufreq_pd_names,
+		.num_pd_names = ARRAY_SIZE(airoha_cpufreq_pd_names),
+		.pd_flags = PD_FLAG_DEV_LINK_ON | PD_FLAG_REQUIRED_OPP,
+	};
+	struct dev_pm_opp_config config = {
+		.clk_names = airoha_cpufreq_clk_names,
+		.config_clks = airoha_cpufreq_config_clks_nop,
+	};
+	struct platform_device *cpufreq_dt;
+	struct airoha_cpufreq_priv *priv;
+	struct device *dev = &pdev->dev;
+	struct device *cpu_dev;
+	int ret;
+
+	/* CPUs refer to the same OPP table */
+	cpu_dev = get_cpu_device(0);
+	if (!cpu_dev)
+		return -ENODEV;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	/* Set OPP table conf with NOP config_clks */
+	priv->opp_token = dev_pm_opp_set_config(cpu_dev, &config);
+	if (priv->opp_token < 0)
+		return dev_err_probe(dev, priv->opp_token, "Failed to set OPP config\n");
+
+	/* Attach PM for OPP */
+	ret = dev_pm_domain_attach_list(cpu_dev, &attach_data,
+					&priv->pd_list);
+	if (ret)
+		goto clear_opp_config;
+
+	cpufreq_dt = platform_device_register_simple("cpufreq-dt", -1, NULL, 0);
+	ret = PTR_ERR_OR_ZERO(cpufreq_dt);
+	if (ret) {
+		dev_err(dev, "failed to create cpufreq-dt device: %d\n", ret);
+		goto detach_pm;
+	}
+
+	priv->cpufreq_dt = cpufreq_dt;
+	platform_set_drvdata(pdev, priv);
+
+	return 0;
+
+detach_pm:
+	dev_pm_domain_detach_list(priv->pd_list);
+clear_opp_config:
+	dev_pm_opp_clear_config(priv->opp_token);
+
+	return ret;
+}
+
+static void airoha_cpufreq_remove(struct platform_device *pdev)
+{
+	struct airoha_cpufreq_priv *priv = platform_get_drvdata(pdev);
+
+	platform_device_unregister(priv->cpufreq_dt);
+
+	dev_pm_domain_detach_list(priv->pd_list);
+
+	dev_pm_opp_clear_config(priv->opp_token);
+}
+
+static struct platform_driver airoha_cpufreq_driver = {
+	.probe = airoha_cpufreq_probe,
+	.remove = airoha_cpufreq_remove,
+	.driver = {
+		.name = "airoha-cpufreq",
+	},
+};
+
+static const struct of_device_id airoha_cpufreq_match_list[] __initconst = {
+	{ .compatible = "airoha,an7583" },
+	{ .compatible = "airoha,en7581" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, airoha_cpufreq_match_list);
+
+static int __init airoha_cpufreq_init(void)
+{
+	const struct of_device_id *match;
+	int ret;
+
+	match = of_machine_get_match(airoha_cpufreq_match_list);
+	if (!match)
+		return -ENODEV;
+
+	ret = platform_driver_register(&airoha_cpufreq_driver);
+	if (unlikely(ret < 0))
+		return ret;
+
+	cpufreq_pdev = platform_device_register_data(NULL, "airoha-cpufreq",
+						     -1, match, sizeof(*match));
+	ret = PTR_ERR_OR_ZERO(cpufreq_pdev);
+	if (ret)
+		platform_driver_unregister(&airoha_cpufreq_driver);
+
+	return ret;
+}
+module_init(airoha_cpufreq_init);
+
+static void __exit airoha_cpufreq_exit(void)
+{
+	platform_device_unregister(cpufreq_pdev);
+	platform_driver_unregister(&airoha_cpufreq_driver);
+}
+module_exit(airoha_cpufreq_exit);
+
+MODULE_AUTHOR("Christian Marangi <ansuelsmth@gmail.com>");
+MODULE_DESCRIPTION("CPUfreq driver for Airoha SoCs");
+MODULE_LICENSE("GPL");