Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Message-ID: <a678504c-3468-12e5-b51d-5670bdf165e5@redhat.com>
Date:   Thu, 2 Jun 2022 10:39:59 +0200
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:91.0) Gecko/20100101
 Thunderbird/91.9.0
Subject: Re: [PATCHv6 10/15] x86/mm: Report unaccepted memory in /proc/meminfo
Content-Language: en-US
To:     "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
        Borislav Petkov <bp@alien8.de>,
        Andy Lutomirski <luto@kernel.org>,
        Sean Christopherson <seanjc@google.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Joerg Roedel <jroedel@suse.de>,
        Ard Biesheuvel <ardb@kernel.org>
Cc:     Andi Kleen <ak@linux.intel.com>,
        Kuppuswamy Sathyanarayanan 
        <sathyanarayanan.kuppuswamy@linux.intel.com>,
        David Rientjes <rientjes@google.com>,
        Vlastimil Babka <vbabka@suse.cz>,
        Tom Lendacky <thomas.lendacky@amd.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        Peter Zijlstra <peterz@infradead.org>,
        Paolo Bonzini <pbonzini@redhat.com>,
        Ingo Molnar <mingo@redhat.com>,
        Varad Gautam <varad.gautam@suse.com>,
        Dario Faggioli <dfaggioli@suse.com>,
        Dave Hansen <dave.hansen@intel.com>,
        Mike Rapoport <rppt@kernel.org>, marcelo.cerri@canonical.com,
        tim.gardner@canonical.com, khalid.elmously@canonical.com,
        philip.cox@canonical.com, x86@kernel.org, linux-mm@kvack.org,
        linux-coco@lists.linux.dev, linux-efi@vger.kernel.org,
        linux-kernel@vger.kernel.org
References: <20220517153444.11195-1-kirill.shutemov@linux.intel.com>
 <20220517153444.11195-11-kirill.shutemov@linux.intel.com>
From:   David Hildenbrand <david@redhat.com>
Organization: Red Hat
In-Reply-To: <20220517153444.11195-11-kirill.shutemov@linux.intel.com>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 7bit
Precedence: bulk

On 17.05.22 17:34, Kirill A. Shutemov wrote:
> Track amount of unaccepted memory and report it in /proc/meminfo.

I feel like instead of doing this arch specific tracking here, we should
simply report the total number of unaccepted (base) pages in the buddy.

When the system boots up, the number will rise as unaccepted memory gets
exposed to the buddy. But especially once user space is up and running,
that number should only go down.

Once it hits zero, there is no unaccepted memory left in the buddy and
there won't be any performance surprises anymote -- and AFAIKT, that's
what we really care about.

-- 
Thanks,

David / dhildenb