linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: 王贇 <yun.wang@linux.alibaba.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Mark Rutland <mark.rutland@arm.com>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Jiri Olsa <jolsa@redhat.com>, Namhyung Kim <namhyung@kernel.org>,
	Alexei Starovoitov <ast@kernel.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	Andrii Nakryiko <andrii@kernel.org>,
	Martin KaFai Lau <kafai@fb.com>, Song Liu <songliubraving@fb.com>,
	Yonghong Song <yhs@fb.com>,
	John Fastabend <john.fastabend@gmail.com>,
	KP Singh <kpsingh@kernel.org>,
	"open list:PERFORMANCE EVENTS SUBSYSTEM" 
	<linux-perf-users@vger.kernel.org>,
	"open list:PERFORMANCE EVENTS SUBSYSTEM" 
	<linux-kernel@vger.kernel.org>,
	"open list:BPF (Safe dynamic programs and tools)" 
	<netdev@vger.kernel.org>,
	"open list:BPF (Safe dynamic programs and tools)" 
	<bpf@vger.kernel.org>
Subject: Re: [RFC PATCH] perf: fix panic by mark recursion inside perf_log_throttle
Date: Wed, 15 Sep 2021 09:51:57 +0800	[thread overview]
Message-ID: <3f26f7a2-0a09-056a-3a7a-4795b6723b60@linux.alibaba.com> (raw)
In-Reply-To: <YUB5VchM3a/MiZpX@hirez.programming.kicks-ass.net>



On 2021/9/14 下午6:28, Peter Zijlstra wrote:
[snip]
> 
> You can simply increase the exception stack size to test this:
> 
> diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
> index a8d4ad856568..e9e2c3ba5923 100644
> --- a/arch/x86/include/asm/page_64_types.h
> +++ b/arch/x86/include/asm/page_64_types.h
> @@ -15,7 +15,7 @@
>  #define THREAD_SIZE_ORDER	(2 + KASAN_STACK_ORDER)
>  #define THREAD_SIZE  (PAGE_SIZE << THREAD_SIZE_ORDER)
>  
> -#define EXCEPTION_STACK_ORDER (0 + KASAN_STACK_ORDER)
> +#define EXCEPTION_STACK_ORDER (1 + KASAN_STACK_ORDER)
>  #define EXCEPTION_STKSZ (PAGE_SIZE << EXCEPTION_STACK_ORDER)
>  
>  #define IRQ_STACK_ORDER (2 + KASAN_STACK_ORDER)

It's working in this case, no more panic.

> 
> 
> 
> Also, something like this might be useful:
> 
> 
> diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
> index f248eb2ac2d4..4dfdbb9395eb 100644
> --- a/arch/x86/include/asm/stacktrace.h
> +++ b/arch/x86/include/asm/stacktrace.h
> @@ -33,6 +33,8 @@ bool in_task_stack(unsigned long *stack, struct task_struct *task,
>  
>  bool in_entry_stack(unsigned long *stack, struct stack_info *info);
>  
> +bool in_exception_stack_guard(unsigned long *stack);
> +
>  int get_stack_info(unsigned long *stack, struct task_struct *task,
>  		   struct stack_info *info, unsigned long *visit_mask);
>  bool get_stack_info_noinstr(unsigned long *stack, struct task_struct *task,
> diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
> index 5601b95944fa..056cf4f31599 100644
> --- a/arch/x86/kernel/dumpstack_64.c
> +++ b/arch/x86/kernel/dumpstack_64.c
> @@ -126,6 +126,39 @@ static __always_inline bool in_exception_stack(unsigned long *stack, struct stac
>  	return true;
>  }
>  
> +noinstr bool in_exception_stack_guard(unsigned long *stack)
> +{
> +	unsigned long begin, end, stk = (unsigned long)stack;
> +	const struct estack_pages *ep;
> +	unsigned int k;
> +
> +	BUILD_BUG_ON(N_EXCEPTION_STACKS != 6);
> +
> +	begin = (unsigned long)__this_cpu_read(cea_exception_stacks);
> +	/*
> +	 * Handle the case where stack trace is collected _before_
> +	 * cea_exception_stacks had been initialized.
> +	 */
> +	if (!begin)
> +		return false;
> +
> +	end = begin + sizeof(struct cea_exception_stacks);
> +	/* Bail if @stack is outside the exception stack area. */
> +	if (stk < begin || stk >= end)
> +		return false;
> +
> +	/* Calc page offset from start of exception stacks */
> +	k = (stk - begin) >> PAGE_SHIFT;
> +	/* Lookup the page descriptor */
> +	ep = &estack_pages[k];
> +	/* Guard page? */
> +	if (!ep->size)
> +		return true;
> +
> +	return false;
> +}
> +
> +
>  static __always_inline bool in_irq_stack(unsigned long *stack, struct stack_info *info)
>  {
>  	unsigned long *end = (unsigned long *)this_cpu_read(hardirq_stack_ptr);
> diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
> index a58800973aed..8b043ed02c0d 100644
> --- a/arch/x86/kernel/traps.c
> +++ b/arch/x86/kernel/traps.c
> @@ -459,6 +459,9 @@ DEFINE_IDTENTRY_DF(exc_double_fault)
>  		handle_stack_overflow("kernel stack overflow (double-fault)",
>  				      regs, address);
>  	}
> +
> +	if (in_exception_stack_guard((void *)address))
> +		pr_emerg("PANIC: exception stack guard: 0x%lx\n", address);
>  #endif
>  
>  	pr_emerg("PANIC: double fault, error_code: 0x%lx\n", error_code);
> 

The panic triggered as below after the stack size recovered, I found this info
could be helpful, maybe we should keep it?

Regards,
Michael Wang

[   30.515200][    C0] traps: PANIC: exception stack guard: 0xfffffe000000aff8
[   30.515206][    C0] traps: PANIC: double fault, error_code: 0x0
[   30.515216][    C0] double fault: 0000 [#1] SMP PTI
[   30.515223][    C0] CPU: 0 PID: 702 Comm: a.out Not tainted 5.14.0-next-20210913+ #524
[   30.515230][    C0] Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
[   30.515233][    C0] RIP: 0010:perf_swevent_get_recursion_context+0x0/0x70
[   30.515246][    C0] Code: 48 03 43 28 48 8b 0c 24 bb 01 00 00 00 4c 29 f0 48 39 c8 48 0f 47 c1 49 89 45 08 e9 48 ff ff ff 66 2e 0f 1f 84 00 00 00 00 00 <55> 53 e8 09 20 f2 ff 48 c7 c2 20 4d 03 00 65 48 03 15 5a 3b d2 7e
[   30.515253][    C0] RSP: 0018:fffffe000000b000 EFLAGS: 00010046
[   30.515259][    C0] RAX: 0000000080120008 RBX: fffffe000000b050 RCX: 0000000000000000
[   30.515264][    C0] RDX: ffff88810cbf2180 RSI: ffffffff81269031 RDI: 000000000000001c
[   30.515268][    C0] RBP: 000000000000001c R08: 0000000000000001 R09: 0000000000000000
[   30.515272][    C0] R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
[   30.515275][    C0] R13: fffffe000000b044 R14: 0000000000000001 R15: 0000000000000001
[   30.515280][    C0] FS:  00007fa1b01f4740(0000) GS:ffff88813bc00000(0000) knlGS:0000000000000000
[   30.515286][    C0] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   30.515290][    C0] CR2: fffffe000000aff8 CR3: 000000010e26a003 CR4: 00000000003606f0
[   30.515294][    C0] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[   30.515298][    C0] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[   30.515302][    C0] Call Trace:
[   30.515305][    C0]  <NMI>
[   30.515308][    C0]  perf_trace_buf_alloc+0x26/0xd0
[   30.515321][    C0]  ? is_prefetch.isra.25+0x260/0x260
[   30.515329][    C0]  ? __bad_area_nosemaphore+0x1b8/0x280
[   30.515336][    C0]  perf_ftrace_function_call+0x18f/0x2e0
[   30.515347][    C0]  ? perf_trace_buf_alloc+0xbf/0xd0
[   30.515385][    C0]  ? 0xffffffffa0106083
[   30.515412][    C0]  0xffffffffa0106083
[   30.515431][    C0]  ? 0xffffffffa0106083
[   30.515452][    C0]  ? kernelmode_fixup_or_oops+0x5/0x120
[   30.515465][    C0]  kernelmode_fixup_or_oops+0x5/0x120
[   30.515472][    C0]  __bad_area_nosemaphore+0x1b8/0x280
[   30.515492][    C0]  do_user_addr_fault+0x410/0x920
[   30.515508][    C0]  ? 0xffffffffa0106083
[   30.515525][    C0]  exc_page_fault+0x92/0x300
[   30.515542][    C0]  asm_exc_page_fault+0x1e/0x30
[   30.515551][    C0] RIP: 0010:__get_user_nocheck_8+0x6/0x13


  reply	other threads:[~2021-09-15  1:52 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-09-09  3:13 [RFC PATCH] perf: fix panic by mark recursion inside perf_log_throttle 王贇
2021-09-09  6:10 ` 王贇
2021-09-10 15:38 ` Peter Zijlstra
2021-09-13  3:00   ` 王贇
2021-09-13  3:21     ` 王贇
2021-09-13 10:24     ` Peter Zijlstra
2021-09-13 10:36       ` Peter Zijlstra
2021-09-14  2:02         ` 王贇
2021-09-14  1:58       ` 王贇
2021-09-14 10:28         ` Peter Zijlstra
2021-09-15  1:51           ` 王贇 [this message]
2021-09-15 15:17             ` [PATCH] x86/dumpstack/64: Add guard pages to stack_info Peter Zijlstra
2021-09-16  3:34               ` 王贇
2021-09-16  3:47               ` 王贇
2021-09-16  8:00                 ` Peter Zijlstra
2021-09-16  8:03                   ` Peter Zijlstra
2021-09-16 10:02                     ` Peter Zijlstra
2021-09-17  2:15                       ` 王贇
2021-09-17  3:02                       ` 王贇
2021-09-17 10:21                         ` Peter Zijlstra
2021-09-17 16:40                           ` Peter Zijlstra
2021-09-18  2:30                             ` 王贇
2021-09-18  6:56                               ` Peter Zijlstra
2021-09-18  2:38                             ` 王贇
2021-09-13  3:30 ` [PATCH] perf: fix panic by disable ftrace on fault.c 王贇
2021-09-13 14:49   ` Dave Hansen
2021-09-14  1:52     ` 王贇
2021-09-14  3:02       ` 王贇
2021-09-14  7:23         ` 王贇
2021-09-14 16:16           ` Dave Hansen
2021-09-15  1:56             ` 王贇
2021-09-15  3:27               ` Dave Hansen
2021-09-15  7:22                 ` 王贇
2021-09-15  7:34                   ` 王贇
2021-09-15 15:19                     ` [PATCH] x86: Increase exception stack sizes Peter Zijlstra
2021-09-16  3:42                       ` 王贇
2021-09-21  7:28                       ` [tip: x86/core] " tip-bot2 for Peter Zijlstra
2021-09-21 12:41                       ` tip-bot2 for Peter Zijlstra
2021-09-14  2:08     ` [PATCH] perf: fix panic by disable ftrace on fault.c 王贇

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=3f26f7a2-0a09-056a-3a7a-4795b6723b60@linux.alibaba.com \
    --to=yun.wang@linux.alibaba.com \
    --cc=acme@kernel.org \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=john.fastabend@gmail.com \
    --cc=jolsa@redhat.com \
    --cc=kafai@fb.com \
    --cc=kpsingh@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=peterz@infradead.org \
    --cc=songliubraving@fb.com \
    --cc=yhs@fb.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).