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, 143 insertions, 0 deletions

diff --git a/samples/ftrace/sample-trace-array.c b/samples/ftrace/sample-trace-array.c
new file mode 100644
index 000000000..414761610
--- /dev/null
+++ b/samples/ftrace/sample-trace-array.c
@@ -0,0 +1,143 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/module.h>
+#include <linux/kthread.h>
+#include <linux/trace.h>
+#include <linux/trace_events.h>
+#include <linux/timer.h>
+#include <linux/err.h>
+#include <linux/jiffies.h>
+#include <linux/workqueue.h>
+
+/*
+ * Any file that uses trace points, must include the header.
+ * But only one file, must include the header by defining
+ * CREATE_TRACE_POINTS first.  This will make the C code that
+ * creates the handles for the trace points.
+ */
+#define CREATE_TRACE_POINTS
+#include "sample-trace-array.h"
+
+struct trace_array *tr;
+static void mytimer_handler(struct timer_list *unused);
+static struct task_struct *simple_tsk;
+
+static void trace_work_fn(struct work_struct *work)
+{
+	/*
+	 * Disable tracing for event "sample_event".
+	 */
+	trace_array_set_clr_event(tr, "sample-subsystem", "sample_event",
+			false);
+}
+static DECLARE_WORK(trace_work, trace_work_fn);
+
+/*
+ * mytimer: Timer setup to disable tracing for event "sample_event". This
+ * timer is only for the purposes of the sample module to demonstrate access of
+ * Ftrace instances from within kernel.
+ */
+static DEFINE_TIMER(mytimer, mytimer_handler);
+
+static void mytimer_handler(struct timer_list *unused)
+{
+	schedule_work(&trace_work);
+}
+
+static void simple_thread_func(int count)
+{
+	set_current_state(TASK_INTERRUPTIBLE);
+	schedule_timeout(HZ);
+
+	/*
+	 * Printing count value using trace_array_printk() - trace_printk()
+	 * equivalent for the instance buffers.
+	 */
+	trace_array_printk(tr, _THIS_IP_, "trace_array_printk: count=%d\n",
+			count);
+	/*
+	 * Tracepoint for event "sample_event". This will print the
+	 * current value of count and current jiffies.
+	 */
+	trace_sample_event(count, jiffies);
+}
+
+static int simple_thread(void *arg)
+{
+	int count = 0;
+	unsigned long delay = msecs_to_jiffies(5000);
+
+	/*
+	 * Enable tracing for "sample_event".
+	 */
+	trace_array_set_clr_event(tr, "sample-subsystem", "sample_event", true);
+
+	/*
+	 * Adding timer - mytimer. This timer will disable tracing after
+	 * delay seconds.
+	 *
+	 */
+	add_timer(&mytimer);
+	mod_timer(&mytimer, jiffies+delay);
+
+	while (!kthread_should_stop())
+		simple_thread_func(count++);
+
+	timer_delete(&mytimer);
+	cancel_work_sync(&trace_work);
+
+	/*
+	 * trace_array_put() decrements the reference counter associated with
+	 * the trace array - "tr". We are done using the trace array, hence
+	 * decrement the reference counter so that it can be destroyed using
+	 * trace_array_destroy().
+	 */
+	trace_array_put(tr);
+
+	return 0;
+}
+
+static int __init sample_trace_array_init(void)
+{
+	/*
+	 * Return a pointer to the trace array with name "sample-instance" if it
+	 * exists, else create a new trace array.
+	 *
+	 * NOTE: This function increments the reference counter
+	 * associated with the trace array - "tr".
+	 */
+	tr = trace_array_get_by_name("sample-instance", "sched,timer,kprobes");
+
+	if (!tr)
+		return -1;
+	/*
+	 * If context specific per-cpu buffers havent already been allocated.
+	 */
+	trace_array_init_printk(tr);
+
+	simple_tsk = kthread_run(simple_thread, NULL, "sample-instance");
+	if (IS_ERR(simple_tsk)) {
+		trace_array_put(tr);
+		trace_array_destroy(tr);
+		return -1;
+	}
+
+	return 0;
+}
+
+static void __exit sample_trace_array_exit(void)
+{
+	kthread_stop(simple_tsk);
+
+	/*
+	 * We are unloading our module and no longer require the trace array.
+	 * Remove/destroy "tr" using trace_array_destroy()
+	 */
+	trace_array_destroy(tr);
+}
+
+module_init(sample_trace_array_init);
+module_exit(sample_trace_array_exit);
+
+MODULE_AUTHOR("Divya Indi");
+MODULE_DESCRIPTION("Sample module for kernel access to Ftrace instances");
+MODULE_LICENSE("GPL");