Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1761338AbbBIT43 (ORCPT ); Mon, 9 Feb 2015 14:56:29 -0500 Received: from mail-qc0-f178.google.com ([209.85.216.178]:56250 "EHLO mail-qc0-f178.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1760614AbbBIT4Z (ORCPT ); Mon, 9 Feb 2015 14:56:25 -0500 MIME-Version: 1.0 In-Reply-To: <54D534FB.1090101@codeaurora.org> References: <1423092164-9145-1-git-send-email-gregory.0xf0@gmail.com> <54D40DAF.4080609@codeaurora.org> <54D534FB.1090101@codeaurora.org> From: Gregory Fong Date: Mon, 9 Feb 2015 11:55:54 -0800 Message-ID: Subject: Re: [PATCH] ARM: print cma-reserved pages from show_mem To: Laura Abbott Cc: Florian Fainelli , Russell King , Kees Cook , Nicolas Pitre , Catalin Marinas , open list , Yalin Wang , "linux-arm-kernel@lists.infradead.org" , vishnu.ps@samsung.com, Marek Szyprowski Content-Type: text/plain; charset=UTF-8 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3784 Lines: 104 On Fri, Feb 6, 2015 at 1:41 PM, Laura Abbott wrote: > On 2/6/2015 1:14 PM, Gregory Fong wrote: >> >> On Thu, Feb 5, 2015 at 4:41 PM, Laura Abbott >> wrote: >>> >>> On 2/4/2015 3:22 PM, Gregory Fong wrote: >>>> >>>> >>>> Add cma reserved information to the ARM-specific show_mem. It was >>>> added to the generic implementation by commit >>>> 49abd8c28046adf77c5ce1949549aa64d7221881 "lib/show_mem.c: add cma >>>> reserved information". >>>> >>>> Signed-off-by: Gregory Fong >>>> --- >>>> arch/arm/mm/init.c | 4 ++++ >>>> 1 file changed, 4 insertions(+) >>>> >>>> diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c >>>> index 2495c8c..da77507 100644 >>>> --- a/arch/arm/mm/init.c >>>> +++ b/arch/arm/mm/init.c >>>> @@ -22,6 +22,7 @@ >>>> #include >>>> #include >>>> #include >>>> +#include >>>> >>>> #include >>>> #include >>>> @@ -130,6 +131,9 @@ void show_mem(unsigned int filter) >>>> printk("%d pages of RAM\n", total); >>>> printk("%d free pages\n", free); >>>> printk("%d reserved pages\n", reserved); >>>> +#ifdef CONFIG_CMA >>>> + printk("%lu cma reserved pages\n", totalcma_pages); >>>> +#endif >>> >>> >>> >>> Nit: 'cma reserved pages' is a bit unclear. Are there some CMA >>> pages that aren't reserved? Dropping the reserved might be >>> clearer. >> >> >> Sure, I was trying to replicate what's in lib/show_mem.c, but it >> doesn't actually make much sense. Maybe it would be better to change >> to "cma pages" here and change the wording in that lib/show_mem.c too. >> >> I'll wait a bit for any other thoughts and send out a v2 with those >> changes. >> > > So it looks like the lib/show_mem.c does something different > #ifdef CONFIG_CMA > printk("%lu pages reserved\n", (reserved - totalcma_pages)); > printk("%lu pages cma reserved\n", totalcma_pages); > #else > printk("%lu pages reserved\n", reserved); > #endif > > > No need to change the name, instead I'd say fix up arm to match what > the generic showmem is doing. The trouble is that lib/show_mem.c and ARM's show_mem use the 'reserved' variable to hold different info, which was not a problem I was aiming to tackle here, and am not sure I understand what's going on well enough to do so. But let's give it a shot: In lib/show_mem.c, reserved is calculated by iterating over all online nodes, then increasing reserved by (zone->present_pages - zone->managed_pages). This count includes CMA pages and so when reserved pages is printed it should be 'reserved' - totalcma_pages, as it currently is. In ARM's show_mem, reserved is counted by iterating over memblocks, and within each one iterating over pfns, checking each page to see if it's reserved, and increasing the counter accordingly. Unlike the generic one, this results in counting reserved pages differently than CMA pages. Unfortunately, I don't see a good way to do the calculation different in the generic implementation that doesn't also count CMA pages in 'reserved'---unless I'm missing something, this isn't available at the zone info level. If this is correct, then I think the correct set of steps is still what I was suggesting: 1. change generic implementation to say 'cma' rather than 'cma reserved' 2. do what I did in this patch except also remove the word 'reserved' like in (1). Does that seem sensible? Thanks, Gregory -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/