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/cpufreq/sh-cpufreq.c b/drivers/cpufreq/sh-cpufreq.c
new file mode 100644
index 000000000..3c99d7009
--- /dev/null
+++ b/drivers/cpufreq/sh-cpufreq.c
@@ -0,0 +1,168 @@
+/*
+ * cpufreq driver for the SuperH processors.
+ *
+ * Copyright (C) 2002 - 2012 Paul Mundt
+ * Copyright (C) 2002 M. R. Brown
+ *
+ * Clock framework bits from arch/avr32/mach-at32ap/cpufreq.c
+ *
+ *   Copyright (C) 2004-2007 Atmel Corporation
+ *
+ * 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.
+ */
+#define pr_fmt(fmt) "cpufreq: " fmt
+
+#include <linux/types.h>
+#include <linux/cpufreq.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/err.h>
+#include <linux/cpumask.h>
+#include <linux/cpu.h>
+#include <linux/smp.h>
+#include <linux/clk.h>
+#include <linux/percpu.h>
+#include <linux/sh_clk.h>
+
+static DEFINE_PER_CPU(struct clk, sh_cpuclk);
+
+struct cpufreq_target {
+	struct cpufreq_policy	*policy;
+	unsigned int		freq;
+};
+
+static unsigned int sh_cpufreq_get(unsigned int cpu)
+{
+	return (clk_get_rate(&per_cpu(sh_cpuclk, cpu)) + 500) / 1000;
+}
+
+static long __sh_cpufreq_target(void *arg)
+{
+	struct cpufreq_target *target = arg;
+	struct cpufreq_policy *policy = target->policy;
+	int cpu = policy->cpu;
+	struct clk *cpuclk = &per_cpu(sh_cpuclk, cpu);
+	struct cpufreq_freqs freqs;
+	struct device *dev;
+	long freq;
+
+	if (smp_processor_id() != cpu)
+		return -ENODEV;
+
+	dev = get_cpu_device(cpu);
+
+	/* Convert target_freq from kHz to Hz */
+	freq = clk_round_rate(cpuclk, target->freq * 1000);
+
+	if (freq < (policy->min * 1000) || freq > (policy->max * 1000))
+		return -EINVAL;
+
+	dev_dbg(dev, "requested frequency %u Hz\n", target->freq * 1000);
+
+	freqs.old	= sh_cpufreq_get(cpu);
+	freqs.new	= (freq + 500) / 1000;
+	freqs.flags	= 0;
+
+	cpufreq_freq_transition_begin(target->policy, &freqs);
+	clk_set_rate(cpuclk, freq);
+	cpufreq_freq_transition_end(target->policy, &freqs, 0);
+
+	dev_dbg(dev, "set frequency %lu Hz\n", freq);
+	return 0;
+}
+
+/*
+ * Here we notify other drivers of the proposed change and the final change.
+ */
+static int sh_cpufreq_target(struct cpufreq_policy *policy,
+			     unsigned int target_freq,
+			     unsigned int relation)
+{
+	struct cpufreq_target data = { .policy = policy, .freq = target_freq };
+
+	return work_on_cpu(policy->cpu, __sh_cpufreq_target, &data);
+}
+
+static int sh_cpufreq_verify(struct cpufreq_policy_data *policy)
+{
+	struct clk *cpuclk = &per_cpu(sh_cpuclk, policy->cpu);
+
+	if (policy->freq_table)
+		return cpufreq_frequency_table_verify(policy);
+
+	cpufreq_verify_within_cpu_limits(policy);
+
+	policy->min = (clk_round_rate(cpuclk, 1) + 500) / 1000;
+	policy->max = (clk_round_rate(cpuclk, ~0UL) + 500) / 1000;
+
+	cpufreq_verify_within_cpu_limits(policy);
+	return 0;
+}
+
+static int sh_cpufreq_cpu_init(struct cpufreq_policy *policy)
+{
+	unsigned int cpu = policy->cpu;
+	struct clk *cpuclk = &per_cpu(sh_cpuclk, cpu);
+	struct cpufreq_frequency_table *freq_table;
+	struct device *dev;
+
+	dev = get_cpu_device(cpu);
+
+	cpuclk = clk_get(dev, "cpu_clk");
+	if (IS_ERR(cpuclk)) {
+		dev_err(dev, "couldn't get CPU clk\n");
+		return PTR_ERR(cpuclk);
+	}
+
+	freq_table = cpuclk->nr_freqs ? cpuclk->freq_table : NULL;
+	if (freq_table) {
+		policy->freq_table = freq_table;
+	} else {
+		dev_notice(dev, "no frequency table found, falling back "
+			   "to rate rounding.\n");
+
+		policy->cpuinfo.min_freq = (clk_round_rate(cpuclk, 1) + 500) / 1000;
+		policy->cpuinfo.max_freq = (clk_round_rate(cpuclk, ~0UL) + 500) / 1000;
+	}
+
+	return 0;
+}
+
+static void sh_cpufreq_cpu_exit(struct cpufreq_policy *policy)
+{
+	unsigned int cpu = policy->cpu;
+	struct clk *cpuclk = &per_cpu(sh_cpuclk, cpu);
+
+	clk_put(cpuclk);
+}
+
+static struct cpufreq_driver sh_cpufreq_driver = {
+	.name		= "sh",
+	.flags		= CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING,
+	.get		= sh_cpufreq_get,
+	.target		= sh_cpufreq_target,
+	.verify		= sh_cpufreq_verify,
+	.init		= sh_cpufreq_cpu_init,
+	.exit		= sh_cpufreq_cpu_exit,
+};
+
+static int __init sh_cpufreq_module_init(void)
+{
+	pr_notice("SuperH CPU frequency driver.\n");
+	return cpufreq_register_driver(&sh_cpufreq_driver);
+}
+
+static void __exit sh_cpufreq_module_exit(void)
+{
+	cpufreq_unregister_driver(&sh_cpufreq_driver);
+}
+
+module_init(sh_cpufreq_module_init);
+module_exit(sh_cpufreq_module_exit);
+
+MODULE_AUTHOR("Paul Mundt <lethal@linux-sh.org>");
+MODULE_DESCRIPTION("cpufreq driver for SuperH");
+MODULE_LICENSE("GPL");