Date: Mon, 12 Dec 2016 09:49:03 +0100
From: Peter Zijlstra <peterz@infradead.org>
To: Andres Freund <andres@anarazel.de>
Cc: linux-kernel@vger.kernel.org, Stephane Eranian <eranian@google.com>,
        acme@kernel.org, jolsa@redhat.com, mingo@elte.hu, anton@ozlabs.org,
        namhyung@kernel.org, Stephane Eranian <eranian@gmail.com>
Subject: Re: perf/jit doesn't cope well with mprotect() to jit containing
 pages
Message-ID: <20161212084903.GZ3124@twins.programming.kicks-ass.net>
References: <20161210050218.jw4bak5jf766iqpb@alap3.anarazel.de>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20161210050218.jw4bak5jf766iqpb@alap3.anarazel.de>
User-Agent: Mutt/1.5.23.1 (2014-03-12)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 879
Lines: 26

On Fri, Dec 09, 2016 at 09:02:18PM -0800, Andres Freund wrote:
> 
> I presume the increasing MMAP2 size is triggered by the consecutive
> pages being represented as a single page-range in the kernel?

Yes, we print struct vm_area_struct based information, if vmas get
merged, that shows.

> If I, to work around such consecutive pages, force another page to be
> mmap()ed inbetween, and avoid using MAP_ANONYMOUS, the problem also goes
> away.

This would indeed inhibit vma merging.

> Am I doing something wrong, or is there a bug here?

Expected behaviour afaict

> BTW, it's also a bit weird that those MMAP2 records triggered by
> mprotect/mmap, have prot set to 0...

Yes, mprotect() does: vma->vm_flags = newflags; before calling
perf_event_mmap(vma); which then looks at VM_{READ,WRITE,EXEC} bits in
that word to generate the prot value.

So that being 0 is a bit weird.