[PATCH] x86: fix get_wchan() not support the ORC unwinder

[PATCH] x86: fix get_wchan() not support the ORC unwinder

[Qi Zheng]

Currently, the kernel CONFIG_UNWINDER_ORC option is enabled by
default on x86, but the implementation of get_wchan() is still
based on the frame pointer unwinder, so the /proc/<pid>/wchan
always return 0 regardless of whether the task <pid> is running.

We reimplement the get_wchan() by calling stack_trace_save_tsk(),
which is adapted to the ORC and frame pointer unwinders.

Fixes: ee9f8fce9964(x86/unwind: Add the ORC unwinder)
Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
---
 arch/x86/kernel/process.c | 51 +++--------------------------------------------
 1 file changed, 3 insertions(+), 48 deletions(-)

diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 5e1f38179f49..976a36918ed7 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -928,58 +928,13 @@ unsigned long arch_randomize_brk(struct mm_struct *mm)
  */
 unsigned long get_wchan(struct task_struct *p)
 {
-	unsigned long start, bottom, top, sp, fp, ip, ret = 0;
-	int count = 0;
+	unsigned long entry = 0;
 
 	if (p == current || p->state == TASK_RUNNING)
 		return 0;
 
-	if (!try_get_task_stack(p))
-		return 0;
-
-	start = (unsigned long)task_stack_page(p);
-	if (!start)
-		goto out;
-
-	/*
-	 * Layout of the stack page:
-	 *
-	 * ----------- topmax = start + THREAD_SIZE - sizeof(unsigned long)
-	 * PADDING
-	 * ----------- top = topmax - TOP_OF_KERNEL_STACK_PADDING
-	 * stack
-	 * ----------- bottom = start
-	 *
-	 * The tasks stack pointer points at the location where the
-	 * framepointer is stored. The data on the stack is:
-	 * ... IP FP ... IP FP
-	 *
-	 * We need to read FP and IP, so we need to adjust the upper
-	 * bound by another unsigned long.
-	 */
-	top = start + THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING;
-	top -= 2 * sizeof(unsigned long);
-	bottom = start;
-
-	sp = READ_ONCE(p->thread.sp);
-	if (sp < bottom || sp > top)
-		goto out;
-
-	fp = READ_ONCE_NOCHECK(((struct inactive_task_frame *)sp)->bp);
-	do {
-		if (fp < bottom || fp > top)
-			goto out;
-		ip = READ_ONCE_NOCHECK(*(unsigned long *)(fp + sizeof(unsigned long)));
-		if (!in_sched_functions(ip)) {
-			ret = ip;
-			goto out;
-		}
-		fp = READ_ONCE_NOCHECK(*(unsigned long *)fp);
-	} while (count++ < 16 && p->state != TASK_RUNNING);
-
-out:
-	put_task_stack(p);
-	return ret;
+	stack_trace_save_tsk(p, &entry, 1, 0);
+	return entry;
 }
 
 long do_arch_prctl_common(struct task_struct *task, int option,
-- 
2.11.0

Re: [PATCH] x86: fix get_wchan() not support the ORC unwinder

[Andy Lutomirski]

On 6/11/21 5:46 AM, Qi Zheng wrote:
> Currently, the kernel CONFIG_UNWINDER_ORC option is enabled by
> default on x86, but the implementation of get_wchan() is still
> based on the frame pointer unwinder, so the /proc/<pid>/wchan
> always return 0 regardless of whether the task <pid> is running.
> 
> We reimplement the get_wchan() by calling stack_trace_save_tsk(),
> which is adapted to the ORC and frame pointer unwinders.

How much slower does this make ps?

--Andy

Re: [External] Re: [PATCH] x86: fix get_wchan() not support the ORC unwinder

[郑琦]

On Tue, Jun 15, 2021 at 12:21 AM Andy Lutomirski <luto@kernel.org> wrote:
>
> On 6/11/21 5:46 AM, Qi Zheng wrote:
> > Currently, the kernel CONFIG_UNWINDER_ORC option is enabled by
> > default on x86, but the implementation of get_wchan() is still
> > based on the frame pointer unwinder, so the /proc/<pid>/wchan
> > always return 0 regardless of whether the task <pid> is running.
> >
> > We reimplement the get_wchan() by calling stack_trace_save_tsk(),
> > which is adapted to the ORC and frame pointer unwinders.
>
> How much slower does this make ps?

I used the bpftrace tool to test the running time of get_wchan() in the two
cases of the ORC and frame pointer unwinders, the test script and
the result are as follows:

the test script:
bpftrace -e 'kprobe:get_wchan { @start[tid] = nsecs; } kretprobe: get_wchan
/@start[tid]/ { @ns[comm] = hist(nsecs - @start[tid]); delete(@start[tid]); }'

the result:
1) ORC unwinder ( before applying this patch )

@ns[ps]:
[512, 1K)     4609   |@@@@@@@@@@@@ |
[1K, 2K)      18599  |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
[2K, 4K)      1848    |@@@@@ |
[4K, 8K)       307     | |
[8K, 16K)     74       | |
[16K, 32K)   12       | |

73% of the cases are in the [1K, 2K) range.
Notice: In this case, the get_wchan() always returns the wrong value of 0.

2) ORC unwinder ( after applying this patch )

@ns[ps]:
[512, 1K)    536      |@ |
[1K, 2K)     19945   |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
[2K, 4K)     5604     |@@@@@@@@@@@@@@ |
[4K, 8K)     246       | |
[8K, 16K)   154       | |
[16K, 32K) 18         | |

75% of the cases are in the [1K, 2K) range.

3) frame point unwinder ( before applying this patch )

@ns[ps]:
[512, 1K)    245      | |
[1K, 2K)     16577   |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
[2K, 4K)     2788     |@@@@@@@@ |
[4K, 8K)     190       | |
[8K, 16K)   74         | |
[16K, 32K) 9           | |

83% of the cases are in the [1K, 2K) range.

4) frame point unwinder ( after applying this patch )

@ns[ps]:
[512, 1K)    85        | |
[1K, 2K)     12023  |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
[2K, 4K)     7418    |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ |
[4K, 8K)     232      |@ |
[8K, 16K)   104      | |
[16K, 32K) 18        | |

60% of the cases are in the [1K, 2K) range.

In summary, the running time of get_wchan() has increased after applying this
patch. But the get_wchan() is not the hotspot function, and this is a bug in the
default ORC option, so I think these increased runtimes are acceptable.

In addition, this issue has existed for nearly 4 years and no one has
fixed it, if
nobody cares about the return value of the get_wchan(), maybe we can return
0 or remove this function directly. What do you think?

Best regards,
Qi Zheng

>
> --Andy