netdev - Re: [4.15-rc9] fs_reclaim lockdep trace

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Sun, 28 Jan 2018 13:25:29 +0900
From:   Tetsuo Handa <penguin-kernel@...ove.SAKURA.ne.jp>
To:     Linus Torvalds <torvalds@...ux-foundation.org>,
        Dave Jones <davej@...emonkey.org.uk>,
        Peter Zijlstra <peterz@...radead.org>
Cc:     Linux Kernel <linux-kernel@...r.kernel.org>,
        linux-mm <linux-mm@...ck.org>,
        Network Development <netdev@...r.kernel.org>
Subject: Re: [4.15-rc9] fs_reclaim lockdep trace

On 2018/01/28 10:16, Tetsuo Handa wrote:
> Linus Torvalds wrote:
>> On Sat, Jan 27, 2018 at 2:24 PM, Dave Jones <davej@...emonkey.org.uk> wrote:
>>> On Tue, Jan 23, 2018 at 08:36:51PM -0500, Dave Jones wrote:
>>>  > Just triggered this on a server I was rsync'ing to.
>>>
>>> Actually, I can trigger this really easily, even with an rsync from one
>>> disk to another.  Though that also smells a little like networking in
>>> the traces. Maybe netdev has ideas.
>>
>> Is this new to 4.15? Or is it just that you're testing something new?
>>
>> If it's new and easy to repro, can you just bisect it? And if it isn't
>> new, can you perhaps check whether it's new to 4.14 (ie 4.13 being
>> ok)?
>>
>> Because that fs_reclaim_acquire/release() debugging isn't new to 4.15,
>> but it was rewritten for 4.14.. I'm wondering if that remodeling ended
>> up triggering something.
> 
> --- linux-4.13.16/mm/page_alloc.c
> +++ linux-4.14.15/mm/page_alloc.c

Oops. This output was inverted.

> @@ -3527,53 +3519,12 @@
>  			return true;
>  	}
>  	return false;
>  }
>  #endif /* CONFIG_COMPACTION */
>  
> -#ifdef CONFIG_LOCKDEP
> -struct lockdep_map __fs_reclaim_map =
> -	STATIC_LOCKDEP_MAP_INIT("fs_reclaim", &__fs_reclaim_map);
> -
> -static bool __need_fs_reclaim(gfp_t gfp_mask)
> -{
> -	gfp_mask = current_gfp_context(gfp_mask);
> -
> -	/* no reclaim without waiting on it */
> -	if (!(gfp_mask & __GFP_DIRECT_RECLAIM))
> -		return false;
> -
> -	/* this guy won't enter reclaim */
> -	if ((current->flags & PF_MEMALLOC) && !(gfp_mask & __GFP_NOMEMALLOC))
> -		return false;

Since __kmalloc_reserve() from __alloc_skb() adds __GFP_NOMEMALLOC | __GFP_NOWARN
to gfp_mask, __need_fs_reclaim() is failing to return false here.

But why checking __GFP_NOMEMALLOC here? __alloc_pages_slowpath() skips direct
reclaim if !(gfp_mask & __GFP_DIRECT_RECLAIM) or (current->flags & PF_MEMALLOC),
doesn't it?

----------
static inline struct page *
__alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
                                                struct alloc_context *ac)
{
(...snipped...)
        /* Caller is not willing to reclaim, we can't balance anything */
        if (!can_direct_reclaim)
                goto nopage;

        /* Avoid recursion of direct reclaim */
        if (current->flags & PF_MEMALLOC)
                goto nopage;

        /* Try direct reclaim and then allocating */
        page = __alloc_pages_direct_reclaim(gfp_mask, order, alloc_flags, ac,
                                                        &did_some_progress);
        if (page)
                goto got_pg;
(...snipped...)
}
----------