Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Thu, 15 Aug 2019 16:18:10 -0300
From:   Jason Gunthorpe <jgg@ziepe.ca>
To:     Michal Hocko <mhocko@kernel.org>
Cc:     LKML <linux-kernel@vger.kernel.org>, linux-mm@kvack.org,
        DRI Development <dri-devel@lists.freedesktop.org>,
        Intel Graphics Development <intel-gfx@lists.freedesktop.org>,
        Peter Zijlstra <peterz@infradead.org>,
        Ingo Molnar <mingo@redhat.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        David Rientjes <rientjes@google.com>,
        Christian =?utf-8?B?S8O2bmln?= <christian.koenig@amd.com>,
        =?utf-8?B?SsOpcsO0bWU=?= Glisse <jglisse@redhat.com>,
        Masahiro Yamada <yamada.masahiro@socionext.com>,
        Wei Wang <wvw@google.com>,
        Andy Shevchenko <andriy.shevchenko@linux.intel.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        Jann Horn <jannh@google.com>, Feng Tang <feng.tang@intel.com>,
        Kees Cook <keescook@chromium.org>,
        Randy Dunlap <rdunlap@infradead.org>,
        Daniel Vetter <daniel.vetter@intel.com>
Subject: Re: [PATCH 2/5] kernel.h: Add non_block_start/end()
Message-ID: <20190815191810.GR21596@ziepe.ca>
References: <20190814235805.GB11200@ziepe.ca>
 <20190815065829.GA7444@phenom.ffwll.local>
 <20190815122344.GA21596@ziepe.ca>
 <20190815132127.GI9477@dhcp22.suse.cz>
 <20190815141219.GF21596@ziepe.ca>
 <20190815155950.GN9477@dhcp22.suse.cz>
 <20190815165631.GK21596@ziepe.ca>
 <20190815174207.GR9477@dhcp22.suse.cz>
 <20190815182448.GP21596@ziepe.ca>
 <20190815190525.GS9477@dhcp22.suse.cz>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20190815190525.GS9477@dhcp22.suse.cz>
User-Agent: Mutt/1.9.4 (2018-02-28)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Thu, Aug 15, 2019 at 09:05:25PM +0200, Michal Hocko wrote:

> This is what you claim and I am saying that fs_reclaim is about a
> restricted reclaim context and it is an ugly hack. It has proven to
> report false positives. Maybe it can be extended to a generic reclaim.
> I haven't tried that. Do not aim to try it.

Okay, great, I think this has been very helpful, at least for me,
thanks. I did not know fs_reclaim was so problematic, or the special
cases about OOM 'reclaim'. 

On this patch, I have no general objection to enforcing drivers to be
non-blocking, I'd just like to see it done with the existing lockdep
can't sleep detection rather than inventing some new debugging for it.

I understand this means the debugging requires lockdep enabled and
will not run in production, but I'm of the view that is OK and in line
with general kernel practice.

The last detail is I'm still unclear what a GFP flags a blockable
invalidate_range_start() should use. Is GFP_KERNEL OK? Lockdep has
complained on that in past due to fs_reclaim - how do you know if it
is a false positive?

Thanks again,
Jason