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>,
	jroedel@suse.de, x86@kernel.org
Subject: Re: [PATCH] x86/dumpstack/64: Add guard pages to stack_info
Date: Thu, 16 Sep 2021 11:47:49 +0800	[thread overview]
Message-ID: <76de02b7-4d87-4a3a-e4d4-048829749887@linux.alibaba.com> (raw)
In-Reply-To: <YUIOgmOfnOqPrE+z@hirez.programming.kicks-ass.net>



On 2021/9/15 下午11:17, Peter Zijlstra wrote:
> On Wed, Sep 15, 2021 at 09:51:57AM +0800, 王贇 wrote:
> 
>>> +
>>> +	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?
> 
> Could you please test this?

I did some debug and found the issue, we are missing:

@@ -122,7 +137,10 @@ static __always_inline bool in_exception_stack(unsigned long *stack, struct stac
        info->type      = ep->type;
        info->begin     = (unsigned long *)begin;
        info->end       = (unsigned long *)end;
-       info->next_sp   = (unsigned long *)regs->sp;
+
+       if (!(ep->type & STACK_TYPE_GUARD))
+               info->next_sp   = (unsigned long *)regs->sp;
+
        return true;
 }

as the guard page are not working as real stack I guess?

With that one things going on correctly, and some trivials below.

> 
> ---
> Subject: x86/dumpstack/64: Add guard pages to stack_info
> From: Peter Zijlstra <peterz@infradead.org>
> Date: Wed Sep 15 17:12:59 CEST 2021
> 
> Explicitly add the exception stack guard pages to stack_info and
> report on them from #DF.
> 
> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
> ---
>  arch/x86/include/asm/cpu_entry_area.h |    3 +++
>  arch/x86/include/asm/stacktrace.h     |    3 ++-
>  arch/x86/kernel/dumpstack_64.c        |   17 ++++++++++++++++-
>  arch/x86/kernel/traps.c               |   17 ++++++++++++++++-
>  4 files changed, 37 insertions(+), 3 deletions(-)
> 
> --- a/arch/x86/include/asm/cpu_entry_area.h
> +++ b/arch/x86/include/asm/cpu_entry_area.h
> @@ -61,6 +61,9 @@ enum exception_stack_ordering {
>  #define CEA_ESTACK_OFFS(st)					\
>  	offsetof(struct cea_exception_stacks, st## _stack)
>  
> +#define CEA_EGUARD_OFFS(st)					\
> +	offsetof(struct cea_exception_stacks, st## _stack_guard)
> +
>  #define CEA_ESTACK_PAGES					\
>  	(sizeof(struct cea_exception_stacks) / PAGE_SIZE)
>  
> --- a/arch/x86/include/asm/stacktrace.h
> +++ b/arch/x86/include/asm/stacktrace.h
> @@ -14,13 +14,14 @@
>  #include <asm/switch_to.h>
>  
>  enum stack_type {
> -	STACK_TYPE_UNKNOWN,
> +	STACK_TYPE_UNKNOWN = 0,

Is this necessary?

>  	STACK_TYPE_TASK,
>  	STACK_TYPE_IRQ,
>  	STACK_TYPE_SOFTIRQ,
>  	STACK_TYPE_ENTRY,
>  	STACK_TYPE_EXCEPTION,
>  	STACK_TYPE_EXCEPTION_LAST = STACK_TYPE_EXCEPTION + N_EXCEPTION_STACKS-1,
> +	STACK_TYPE_GUARD = 0x80,
>  };
>  
>  struct stack_info {
> --- a/arch/x86/kernel/dumpstack_64.c
> +++ b/arch/x86/kernel/dumpstack_64.c
> @@ -32,9 +32,15 @@ const char *stack_type_name(enum stack_t
>  {
>  	BUILD_BUG_ON(N_EXCEPTION_STACKS != 6);
>  
> +	if (type == STACK_TYPE_TASK)
> +		return "TASK";
> +
>  	if (type == STACK_TYPE_IRQ)
>  		return "IRQ";
>  
> +	if (type == STACK_TYPE_SOFTIRQ)
> +		return "SOFTIRQ";
> +

Do we need one for GUARD too?

>  	if (type == STACK_TYPE_ENTRY) {
>  		/*
>  		 * On 64-bit, we have a generic entry stack that we
> @@ -63,6 +69,11 @@ struct estack_pages {
>  };
>  
>  #define EPAGERANGE(st)							\
> +	[PFN_DOWN(CEA_EGUARD_OFFS(st))] = {				\
> +		.offs	= CEA_EGUARD_OFFS(st),				\
> +		.size	= PAGE_SIZE,					\
> +		.type	= STACK_TYPE_GUARD +				\
> +			  STACK_TYPE_EXCEPTION + ESTACK_ ##st, },	\
>  	[PFN_DOWN(CEA_ESTACK_OFFS(st)) ...				\
>  	 PFN_DOWN(CEA_ESTACK_OFFS(st) + CEA_ESTACK_SIZE(st) - 1)] = {	\
>  		.offs	= CEA_ESTACK_OFFS(st),				\
> @@ -111,10 +122,11 @@ static __always_inline bool in_exception
>  	k = (stk - begin) >> PAGE_SHIFT;
>  	/* Lookup the page descriptor */
>  	ep = &estack_pages[k];
> -	/* Guard page? */
> +	/* unknown entry */
>  	if (!ep->size)
>  		return false;
>  
> +

Extra line?

Regards,
Michael Wang

>  	begin += (unsigned long)ep->offs;
>  	end = begin + (unsigned long)ep->size;
>  	regs = (struct pt_regs *)end - 1;
> @@ -193,6 +205,9 @@ int get_stack_info(unsigned long *stack,
>  	if (!get_stack_info_noinstr(stack, task, info))
>  		goto unknown;
>  
> +	if (info->type & STACK_TYPE_GUARD)
> +		goto unknown;
> +
>  	/*
>  	 * Make sure we don't iterate through any given stack more than once.
>  	 * If it comes up a second time then there's something wrong going on:
> --- a/arch/x86/kernel/traps.c
> +++ b/arch/x86/kernel/traps.c
> @@ -461,6 +461,19 @@ DEFINE_IDTENTRY_DF(exc_double_fault)
>  	}
>  #endif
>  
> +#ifdef CONFIG_X86_64
> +	{
> +		struct stack_info info;
> +
> +		if (get_stack_info_noinstr((void *)address, current, &info) &&
> +		    info.type & STACK_TYPE_GUARD) {
> +			const char *name = stack_type_name(info.type & ~STACK_TYPE_GUARD);
> +			pr_emerg("BUG: %s stack guard hit at %p (stack is %p..%p)\n",
> +				 name, (void *)address, info.begin, info.end);
> +		}
> +	}
> +#endif
> +
>  	pr_emerg("PANIC: double fault, error_code: 0x%lx\n", error_code);
>  	die("double fault", regs, error_code);
>  	panic("Machine halted.");
> @@ -708,7 +721,9 @@ asmlinkage __visible noinstr struct pt_r
>  	sp    = regs->sp;
>  	stack = (unsigned long *)sp;
>  
> -	if (!get_stack_info_noinstr(stack, current, &info) || info.type == STACK_TYPE_ENTRY ||
> +	if (!get_stack_info_noinstr(stack, current, &info) ||
> +	    info.type & STACK_TYPE_GUARD ||
> +	    info.type == STACK_TYPE_ENTRY ||
>  	    info.type >= STACK_TYPE_EXCEPTION_LAST)
>  		sp = __this_cpu_ist_top_va(VC2);
>  
> 

  parent reply	other threads:[~2021-09-16  3:48 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
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 [this message]
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=76de02b7-4d87-4a3a-e4d4-048829749887@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=jroedel@suse.de \
    --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=x86@kernel.org \
    --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).