From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from psmtp.com (na3sys010amx137.postini.com [74.125.245.137]) by kanga.kvack.org (Postfix) with SMTP id 584B16B0032 for ; Fri, 12 Jul 2013 04:15:09 -0400 (EDT) Date: Fri, 12 Jul 2013 10:13:48 +0200 From: Peter Zijlstra Subject: Re: [PATCH 2/2] mm: add a field to store names for private anonymous memory Message-ID: <20130712081348.GM25631@dyad.programming.kicks-ass.net> References: <1373596462-27115-1-git-send-email-ccross@android.com> <1373596462-27115-2-git-send-email-ccross@android.com> <51DF9682.9040301@kernel.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <51DF9682.9040301@kernel.org> Sender: owner-linux-mm@kvack.org List-ID: To: Pekka Enberg Cc: Colin Cross , linux-kernel@vger.kernel.org, Kyungmin Park , Christoph Hellwig , John Stultz , "Eric W. Biederman" , Dave Hansen , Rob Landley , Andrew Morton , Cyrill Gorcunov , David Rientjes , Davidlohr Bueso , Kees Cook , Al Viro , Hugh Dickins , Mel Gorman , Michel Lespinasse , Rik van Riel , Konstantin Khlebnikov , "Paul E. McKenney" , David Howells , Arnd Bergmann , Dave Jones , "Rafael J. Wysocki" , Oleg Nesterov , Shaohua Li , Sasha Levin , KOSAKI Motohiro , Johannes Weiner , Ingo Molnar , linux-doc@vger.kernel.org, linux-mm@kvack.org On Fri, Jul 12, 2013 at 08:39:14AM +0300, Pekka Enberg wrote: > On 07/12/2013 05:34 AM, Colin Cross wrote: > >Userspace processes often have multiple allocators that each do > >anonymous mmaps to get memory. When examining memory usage of > >individual processes or systems as a whole, it is useful to be > >able to break down the various heaps that were allocated by > >each layer and examine their size, RSS, and physical memory > >usage. > > > >This patch adds a user pointer to the shared union in > >vm_area_struct that points to a null terminated string inside > >the user process containing a name for the vma. vmas that > >point to the same address will be merged, but vmas that > >point to equivalent strings at different addresses will > >not be merged. > > > >Userspace can set the name for a region of memory by calling > >prctl(PR_SET_VMA, PR_SET_VMA_ANON_NAME, start, len, (unsigned long)name); > >Setting the name to NULL clears it. > > > >The names of named anonymous vmas are shown in /proc/pid/maps > >as [anon:] and in /proc/pid/smaps in a new "Name" field > >that is only present for named vmas. If the userspace pointer > >is no longer valid all or part of the name will be replaced > >with "". > > > >The idea to store a userspace pointer to reduce the complexity > >within mm (at the expense of the complexity of reading > >/proc/pid/mem) came from Dave Hansen. This results in no > >runtime overhead in the mm subsystem other than comparing > >the anon_name pointers when considering vma merging. The pointer > >is stored in a union with fieds that are only used on file-backed > >mappings, so it does not increase memory usage. > > > >Signed-off-by: Colin Cross > > Ingo, PeterZ, is this something worthwhile for replacing our > current JIT symbol hack with perf? I really don't see the point of this stuff; in fact I intensely dislike it as I don't think this is something the kernel needs to do at all. Why can't these allocators Collin talks about use file maps and/or write their own meta-data to file? He is after all only interested in Android and they have complete control over the entire userspace stack. I also don't see it helping with the JIT stuff; you still need to write out a file with symbol information, we still need to find the file. A less hacky solution for the entire JIT thing is you writing a proper ELF-DSO and mmap()'ing that :-) Storing a JIT specific userspace pointer in the VMA doesn't help with any of that. -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org