From mboxrd@z Thu Jan 1 00:00:00 1970 From: Sean Christopherson Date: Wed, 1 Nov 2023 06:41:45 -0700 Subject: [PATCH v13 17/35] KVM: Add transparent hugepage support for dedicated guest memory In-Reply-To: <92ba7ddd-2bc8-4a8d-bd67-d6614b21914f@intel.com> References: <20231027182217.3615211-1-seanjc@google.com> <20231027182217.3615211-18-seanjc@google.com> <7c0844d8-6f97-4904-a140-abeabeb552c1@intel.com> <92ba7ddd-2bc8-4a8d-bd67-d6614b21914f@intel.com> Message-ID: List-Id: To: kvm-riscv@lists.infradead.org MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit On Wed, Nov 01, 2023, Xiaoyao Li wrote: > On 10/31/2023 10:16 PM, Sean Christopherson wrote: > > On Tue, Oct 31, 2023, Xiaoyao Li wrote: > > > On 10/28/2023 2:21 AM, Sean Christopherson wrote: > > > > Extended guest_memfd to allow backing guest memory with transparent > > > > hugepages. Require userspace to opt-in via a flag even though there's no > > > > known/anticipated use case for forcing small pages as THP is optional, > > > > i.e. to avoid ending up in a situation where userspace is unaware that > > > > KVM can't provide hugepages. > > > > > > Personally, it seems not so "transparent" if requiring userspace to opt-in. > > > > > > People need to 1) check if the kernel built with TRANSPARENT_HUGEPAGE > > > support, or check is the sysfs of transparent hugepage exists; 2)get the > > > maximum support hugepage size 3) ensure the size satisfies the alignment; > > > before opt-in it. > > > > > > Even simpler, userspace can blindly try to create guest memfd with > > > transparent hugapage flag. If getting error, fallback to create without the > > > transparent hugepage flag. > > > > > > However, it doesn't look transparent to me. > > > > The "transparent" part is referring to the underlying kernel mechanism, it's not > > saying anything about the API. The "transparent" part of THP is that the kernel > > doesn't guarantee hugepages, i.e. whether or not hugepages are actually used is > > (mostly) transparent to userspace. > > > > Paolo also isn't the biggest fan[*], but there are also downsides to always > > allowing hugepages, e.g. silent failure due to lack of THP or unaligned size, > > and there's precedent in the form of MADV_HUGEPAGE. > > > > [*] https://lore.kernel.org/all/84a908ae-04c7-51c7-c9a8-119e1933a189 at redhat.com > > But it's different than MADV_HUGEPAGE, in a way. Per my understanding, the > failure of MADV_HUGEPAGE is not fatal, user space can ignore it and > continue. > > However, the failure of KVM_GUEST_MEMFD_ALLOW_HUGEPAGE is fatal, which leads > to failure of guest memfd creation. Failing KVM_CREATE_GUEST_MEMFD isn't truly fatal, it just requires different action from userspace, i.e. instead of ignoring the error, userspace could redo KVM_CREATE_GUEST_MEMFD with KVM_GUEST_MEMFD_ALLOW_HUGEPAGE=0. We could make the behavior more like MADV_HUGEPAGE, e.g. theoretically we could extend fadvise() with FADV_HUGEPAGE, or add a guest_memfd knob/ioctl() to let userspace provide advice/hints after creating a guest_memfd. But I suspect that guest_memfd would be the only user of FADV_HUGEPAGE, and IMO a post-creation hint is actually less desirable. KVM_GUEST_MEMFD_ALLOW_HUGEPAGE will fail only if userspace didn't provide a compatible size or the kernel doesn't support THP. An incompatible size is likely a userspace bug, and for most setups that want to utilize guest_memfd, lack of THP support is likely a configuration bug. I.e. many/most uses *want* failures due to KVM_GUEST_MEMFD_ALLOW_HUGEPAGE to be fatal. > For current implementation, I think maybe KVM_GUEST_MEMFD_DESIRE_HUGEPAGE > fits better than KVM_GUEST_MEMFD_ALLOW_HUGEPAGE? or maybe *PREFER*? Why? Verbs like "prefer" and "desire" aren't a good fit IMO because they suggest the flag is a hint, and hints are usually best effort only, i.e. are ignored if there is a fundamental incompatibility. "Allow" isn't perfect, e.g. I would much prefer a straight KVM_GUEST_MEMFD_USE_HUGEPAGES or KVM_GUEST_MEMFD_HUGEPAGES flag, but I wanted the name to convey that KVM doesn't (yet) guarantee hugepages. I.e. KVM_GUEST_MEMFD_ALLOW_HUGEPAGE is stronger than a hint, but weaker than a requirement. And if/when KVM supports a dedicated memory pool of some kind, then we can add KVM_GUEST_MEMFD_REQUIRE_HUGEPAGE. From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mail-yw1-f202.google.com (mail-yw1-f202.google.com [209.85.128.202]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id C72AD101D7 for ; Wed, 1 Nov 2023 13:41:47 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=google.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=flex--seanjc.bounces.google.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=google.com header.i=@google.com header.b="1JC8HtH7" Received: by mail-yw1-f202.google.com with SMTP id 00721157ae682-5b02ed0f886so61967917b3.0 for ; Wed, 01 Nov 2023 06:41:47 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20230601; t=1698846106; x=1699450906; darn=lists.linux.dev; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:from:to:cc:subject:date:message-id:reply-to; bh=nFf6aEaGwk5ej5JezQy0IgMN87WPAcTCXufwbiE3fug=; b=1JC8HtH7blzgtlXiz0gAALeFlMpdjIq11K23Xc1QGXvxRbe7LW8gsIvi/ksYq0aX4t iNTmPt1Xs4TSMCb4zl0A/m+vEiwIvS/QG2vlNiPM08/liuJlYE4cnl56lkN1k+YDBKHZ ndNh0pb1Ebx5GAiH0uEfNHrlrZSKLMN5yDLnUlijkpK5/5d9MzqPCvvSbSjpY7HoEoCs Y/aCpb/Qxc6XRGbosup7f/CI5CmBnM3OpO0q571863w3JkLUeftqLYhYajWgHK1uGqGY ylxkL88yCprcPYHvmJ2PAgntEwBzUc7qD4AA8RIG5+s+uJWHAI0Hfx7TK6aaI/l8A73F O0YQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1698846106; x=1699450906; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:x-gm-message-state:from:to:cc:subject:date:message-id:reply-to; bh=nFf6aEaGwk5ej5JezQy0IgMN87WPAcTCXufwbiE3fug=; b=Rp+xRkojwOPEKuH2ZvVJHp7Y/Dec+02pxgMM/sdP7HprblcIiC75naOA1e0thnfaTN vIhNfbaMT1Jpnh0kqnEhlu3AdYvbcu6fVvj54XJjpjTtQrlaYfXYucwGX6GQDt1BP2ME dyaUzMwTaFYypzOPUTiKQ8vmTcLsnb3Q14w7kFQIcHKP0EKAdZvkH4o1oZjhFwcqUeMj hlCKoPUDkLFyKS6umzFr0qpKiTwzf3tfx4QCJWxzScIcNnFfzvARf0qX7pv1IewX2/2v 06sxcyKLxlq7nXZM5EsREW3KvVWt9H28rHX25y1pyQxLynF0ySTKb47D8G0x0w5plNOe vbVA== X-Gm-Message-State: AOJu0YyYwDNMs/3c0JX2ylfqqK8bKMmrlSdRecspEuX7+M9PJpAk56Bd u6qy7EY3/xOH/khrp1vM1nx9RjsrTEc= X-Google-Smtp-Source: AGHT+IEsRM1yQnQClQeVqyoNLxT9cYgRny7PWezkHcY0wXTm/cdeLyJgnrb+5OZENHYJQKvQlFBt8yx8E+I= X-Received: from zagreus.c.googlers.com ([fda3:e722:ac3:cc00:7f:e700:c0a8:5c37]) (user=seanjc job=sendgmr) by 2002:a0d:e689:0:b0:5a7:bfcf:2cb8 with SMTP id p131-20020a0de689000000b005a7bfcf2cb8mr314827ywe.1.1698846106686; Wed, 01 Nov 2023 06:41:46 -0700 (PDT) Date: Wed, 1 Nov 2023 06:41:45 -0700 In-Reply-To: <92ba7ddd-2bc8-4a8d-bd67-d6614b21914f@intel.com> Precedence: bulk X-Mailing-List: kvmarm@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: Mime-Version: 1.0 References: <20231027182217.3615211-1-seanjc@google.com> <20231027182217.3615211-18-seanjc@google.com> <7c0844d8-6f97-4904-a140-abeabeb552c1@intel.com> <92ba7ddd-2bc8-4a8d-bd67-d6614b21914f@intel.com> Message-ID: Subject: Re: [PATCH v13 17/35] KVM: Add transparent hugepage support for dedicated guest memory From: Sean Christopherson To: Xiaoyao Li Cc: Paolo Bonzini , Marc Zyngier , Oliver Upton , Huacai Chen , Michael Ellerman , Anup Patel , Paul Walmsley , Palmer Dabbelt , Albert Ou , Alexander Viro , Christian Brauner , "Matthew Wilcox (Oracle)" , Andrew Morton , kvm@vger.kernel.org, linux-arm-kernel@lists.infradead.org, kvmarm@lists.linux.dev, linux-mips@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, kvm-riscv@lists.infradead.org, linux-riscv@lists.infradead.org, linux-fsdevel@vger.kernel.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org, Xu Yilun , Chao Peng , Fuad Tabba , Jarkko Sakkinen , Anish Moorthy , David Matlack , Yu Zhang , Isaku Yamahata , "=?utf-8?Q?Micka=C3=ABl_Sala=C3=BCn?=" , Vlastimil Babka , Vishal Annapurve , Ackerley Tng , Maciej Szmigiero , David Hildenbrand , Quentin Perret , Michael Roth , Wang , Liam Merwick , Isaku Yamahata , "Kirill A . Shutemov" Content-Type: text/plain; charset="us-ascii" On Wed, Nov 01, 2023, Xiaoyao Li wrote: > On 10/31/2023 10:16 PM, Sean Christopherson wrote: > > On Tue, Oct 31, 2023, Xiaoyao Li wrote: > > > On 10/28/2023 2:21 AM, Sean Christopherson wrote: > > > > Extended guest_memfd to allow backing guest memory with transparent > > > > hugepages. Require userspace to opt-in via a flag even though there's no > > > > known/anticipated use case for forcing small pages as THP is optional, > > > > i.e. to avoid ending up in a situation where userspace is unaware that > > > > KVM can't provide hugepages. > > > > > > Personally, it seems not so "transparent" if requiring userspace to opt-in. > > > > > > People need to 1) check if the kernel built with TRANSPARENT_HUGEPAGE > > > support, or check is the sysfs of transparent hugepage exists; 2)get the > > > maximum support hugepage size 3) ensure the size satisfies the alignment; > > > before opt-in it. > > > > > > Even simpler, userspace can blindly try to create guest memfd with > > > transparent hugapage flag. If getting error, fallback to create without the > > > transparent hugepage flag. > > > > > > However, it doesn't look transparent to me. > > > > The "transparent" part is referring to the underlying kernel mechanism, it's not > > saying anything about the API. The "transparent" part of THP is that the kernel > > doesn't guarantee hugepages, i.e. whether or not hugepages are actually used is > > (mostly) transparent to userspace. > > > > Paolo also isn't the biggest fan[*], but there are also downsides to always > > allowing hugepages, e.g. silent failure due to lack of THP or unaligned size, > > and there's precedent in the form of MADV_HUGEPAGE. > > > > [*] https://lore.kernel.org/all/84a908ae-04c7-51c7-c9a8-119e1933a189@redhat.com > > But it's different than MADV_HUGEPAGE, in a way. Per my understanding, the > failure of MADV_HUGEPAGE is not fatal, user space can ignore it and > continue. > > However, the failure of KVM_GUEST_MEMFD_ALLOW_HUGEPAGE is fatal, which leads > to failure of guest memfd creation. Failing KVM_CREATE_GUEST_MEMFD isn't truly fatal, it just requires different action from userspace, i.e. instead of ignoring the error, userspace could redo KVM_CREATE_GUEST_MEMFD with KVM_GUEST_MEMFD_ALLOW_HUGEPAGE=0. We could make the behavior more like MADV_HUGEPAGE, e.g. theoretically we could extend fadvise() with FADV_HUGEPAGE, or add a guest_memfd knob/ioctl() to let userspace provide advice/hints after creating a guest_memfd. But I suspect that guest_memfd would be the only user of FADV_HUGEPAGE, and IMO a post-creation hint is actually less desirable. KVM_GUEST_MEMFD_ALLOW_HUGEPAGE will fail only if userspace didn't provide a compatible size or the kernel doesn't support THP. An incompatible size is likely a userspace bug, and for most setups that want to utilize guest_memfd, lack of THP support is likely a configuration bug. I.e. many/most uses *want* failures due to KVM_GUEST_MEMFD_ALLOW_HUGEPAGE to be fatal. > For current implementation, I think maybe KVM_GUEST_MEMFD_DESIRE_HUGEPAGE > fits better than KVM_GUEST_MEMFD_ALLOW_HUGEPAGE? or maybe *PREFER*? Why? Verbs like "prefer" and "desire" aren't a good fit IMO because they suggest the flag is a hint, and hints are usually best effort only, i.e. are ignored if there is a fundamental incompatibility. "Allow" isn't perfect, e.g. I would much prefer a straight KVM_GUEST_MEMFD_USE_HUGEPAGES or KVM_GUEST_MEMFD_HUGEPAGES flag, but I wanted the name to convey that KVM doesn't (yet) guarantee hugepages. I.e. KVM_GUEST_MEMFD_ALLOW_HUGEPAGE is stronger than a hint, but weaker than a requirement. And if/when KVM supports a dedicated memory pool of some kind, then we can add KVM_GUEST_MEMFD_REQUIRE_HUGEPAGE. From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from bombadil.infradead.org (bombadil.infradead.org [198.137.202.133]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id 069E4C4332F for ; Wed, 1 Nov 2023 13:42:00 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=lists.infradead.org; s=bombadil.20210309; h=Sender: Content-Transfer-Encoding:Content-Type:List-Subscribe:List-Help:List-Post: List-Archive:List-Unsubscribe:List-Id:Cc:To:From:Subject:Message-ID: References:Mime-Version:In-Reply-To:Date:Reply-To:Content-ID: Content-Description:Resent-Date:Resent-From:Resent-Sender:Resent-To:Resent-Cc :Resent-Message-ID:List-Owner; bh=Hjn1RfLiuun4VEdxdgzhmH2XZhvi94IIeSw+MZnZC0M=; b=kRqAj4BI9cv5us0MoWQE1I1BTd 7gOkrS5AXMDLhJAOdYnCc7ZGluOfTEduCeivtLxukjFckrPQJsW4LWcsaawd53aqUmEaL0FEIHwqi QCo5zfEe1ZB/zVF7xRXmu+j4NomyfvFgYIL/55v7L+dAEG6AkXUVceNaCC6i+lX7m39n+sNpnewIH naBv5nGUoEbd9Jav1wxW5yDh5NNHzS3LcZ5wGgQnnHJ3kiP5WKd645hPqM4TOL5tWd8A/3cBm7Ede LIaupQTHVZpk/F1GapGVXcb8UmWH4r19XAHP60Xfi37fZKfT/HSLwW5yuaJQXJbzloLBW8Qzlpx0I ky4pJpHQ==; Received: from localhost ([::1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.96 #2 (Red Hat Linux)) id 1qyBTm-007alF-2S; Wed, 01 Nov 2023 13:41:54 +0000 Received: from mail-yw1-x114a.google.com ([2607:f8b0:4864:20::114a]) by bombadil.infradead.org with esmtps (Exim 4.96 #2 (Red Hat Linux)) id 1qyBTi-007aiq-1n for linux-riscv@lists.infradead.org; Wed, 01 Nov 2023 13:41:52 +0000 Received: by mail-yw1-x114a.google.com with SMTP id 00721157ae682-5b02ed0f886so61967957b3.0 for ; Wed, 01 Nov 2023 06:41:47 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20230601; t=1698846107; x=1699450907; darn=lists.infradead.org; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:from:to:cc:subject:date:message-id:reply-to; bh=nFf6aEaGwk5ej5JezQy0IgMN87WPAcTCXufwbiE3fug=; b=TxdC4ML5TuMh93VSDIBzefA8qXHE98Qp7DkzFy+i+0QcJgxEmBgxKmoMnY31GfO9Ts gDtoNMplscagESRttUr450U4+LUtViT8OE7gacG5SirW+Je8Jxobnh6HNWmst3ZDiPgG uour4Nxl6HgnqdaCxqzqyMhSSObKEf5sh71j2AtfIrV51wqqi8qXrYDV9ljHdB4x05jI MguS6b4M/dRvOLlkrbFJxPU1ei6wJ2Cxa5+mdwGLD8clMhJhMrY2LHUjsAYHAwx73ur9 1s4EPR6dpmavK9dahKPREYfcNgrCv0ISEmhCQgOF2Jmx2py+HHhJsBEL6SLIlemGekp9 KtAg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1698846107; x=1699450907; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:x-gm-message-state:from:to:cc:subject:date:message-id:reply-to; bh=nFf6aEaGwk5ej5JezQy0IgMN87WPAcTCXufwbiE3fug=; b=B50LeeS3w6zIjXeaJ/Rz/QsC4/vuzlqo6/IJL3pxpkKKUziUOv0hi+quP3MKkL3Gim TK0iH3nsgi2w5+jksJNpIm/frt5MeDmwh1WXk5/jZu88m+stacLXQL2YP7a5rXZZYvtz be16KaKBmp1Yli9eIJVn/tH/bCpx3o1LnIRXhGbp75/vU7T28iy6jTLyBLNoyZ9cC1i9 hF2kRU7dgM8rx4ddLmr+xvL92iQPcb/Y1PeEz6/unVomxoRYRQv5AI4p3auCfTcbbc7Q tb/GzozXwOVeLVdfCd182gm+6mJIw28P/u+zGRKczyNJPL9OnEypSb6WB1RJsOLlAtqZ AfWA== X-Gm-Message-State: AOJu0YwZ+xbaqrWwJowKSVx42A9K+BuBHjgnI6IKt6b526QU/+XfV24R FepRxlsRlIeXiyOWMpPnEHU1th5WMMY= X-Google-Smtp-Source: AGHT+IEsRM1yQnQClQeVqyoNLxT9cYgRny7PWezkHcY0wXTm/cdeLyJgnrb+5OZENHYJQKvQlFBt8yx8E+I= X-Received: from zagreus.c.googlers.com ([fda3:e722:ac3:cc00:7f:e700:c0a8:5c37]) (user=seanjc job=sendgmr) by 2002:a0d:e689:0:b0:5a7:bfcf:2cb8 with SMTP id p131-20020a0de689000000b005a7bfcf2cb8mr314827ywe.1.1698846106686; Wed, 01 Nov 2023 06:41:46 -0700 (PDT) Date: Wed, 1 Nov 2023 06:41:45 -0700 In-Reply-To: <92ba7ddd-2bc8-4a8d-bd67-d6614b21914f@intel.com> Mime-Version: 1.0 References: <20231027182217.3615211-1-seanjc@google.com> <20231027182217.3615211-18-seanjc@google.com> <7c0844d8-6f97-4904-a140-abeabeb552c1@intel.com> <92ba7ddd-2bc8-4a8d-bd67-d6614b21914f@intel.com> Message-ID: Subject: Re: [PATCH v13 17/35] KVM: Add transparent hugepage support for dedicated guest memory From: Sean Christopherson To: Xiaoyao Li Cc: Paolo Bonzini , Marc Zyngier , Oliver Upton , Huacai Chen , Michael Ellerman , Anup Patel , Paul Walmsley , Palmer Dabbelt , Albert Ou , Alexander Viro , Christian Brauner , "Matthew Wilcox (Oracle)" , Andrew Morton , kvm@vger.kernel.org, linux-arm-kernel@lists.infradead.org, kvmarm@lists.linux.dev, linux-mips@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, kvm-riscv@lists.infradead.org, linux-riscv@lists.infradead.org, linux-fsdevel@vger.kernel.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org, Xu Yilun , Chao Peng , Fuad Tabba , Jarkko Sakkinen , Anish Moorthy , David Matlack , Yu Zhang , Isaku Yamahata , "=?utf-8?Q?Micka=C3=ABl_Sala=C3=BCn?=" , Vlastimil Babka , Vishal Annapurve , Ackerley Tng , Maciej Szmigiero , David Hildenbrand , Quentin Perret , Michael Roth , Wang , Liam Merwick , Isaku Yamahata , "Kirill A . Shutemov" X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20231101_064150_592553_ED7CC8B9 X-CRM114-Status: GOOD ( 28.97 ) X-BeenThere: linux-riscv@lists.infradead.org X-Mailman-Version: 2.1.34 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Sender: "linux-riscv" Errors-To: linux-riscv-bounces+linux-riscv=archiver.kernel.org@lists.infradead.org On Wed, Nov 01, 2023, Xiaoyao Li wrote: > On 10/31/2023 10:16 PM, Sean Christopherson wrote: > > On Tue, Oct 31, 2023, Xiaoyao Li wrote: > > > On 10/28/2023 2:21 AM, Sean Christopherson wrote: > > > > Extended guest_memfd to allow backing guest memory with transparent > > > > hugepages. Require userspace to opt-in via a flag even though there's no > > > > known/anticipated use case for forcing small pages as THP is optional, > > > > i.e. to avoid ending up in a situation where userspace is unaware that > > > > KVM can't provide hugepages. > > > > > > Personally, it seems not so "transparent" if requiring userspace to opt-in. > > > > > > People need to 1) check if the kernel built with TRANSPARENT_HUGEPAGE > > > support, or check is the sysfs of transparent hugepage exists; 2)get the > > > maximum support hugepage size 3) ensure the size satisfies the alignment; > > > before opt-in it. > > > > > > Even simpler, userspace can blindly try to create guest memfd with > > > transparent hugapage flag. If getting error, fallback to create without the > > > transparent hugepage flag. > > > > > > However, it doesn't look transparent to me. > > > > The "transparent" part is referring to the underlying kernel mechanism, it's not > > saying anything about the API. The "transparent" part of THP is that the kernel > > doesn't guarantee hugepages, i.e. whether or not hugepages are actually used is > > (mostly) transparent to userspace. > > > > Paolo also isn't the biggest fan[*], but there are also downsides to always > > allowing hugepages, e.g. silent failure due to lack of THP or unaligned size, > > and there's precedent in the form of MADV_HUGEPAGE. > > > > [*] https://lore.kernel.org/all/84a908ae-04c7-51c7-c9a8-119e1933a189@redhat.com > > But it's different than MADV_HUGEPAGE, in a way. Per my understanding, the > failure of MADV_HUGEPAGE is not fatal, user space can ignore it and > continue. > > However, the failure of KVM_GUEST_MEMFD_ALLOW_HUGEPAGE is fatal, which leads > to failure of guest memfd creation. Failing KVM_CREATE_GUEST_MEMFD isn't truly fatal, it just requires different action from userspace, i.e. instead of ignoring the error, userspace could redo KVM_CREATE_GUEST_MEMFD with KVM_GUEST_MEMFD_ALLOW_HUGEPAGE=0. We could make the behavior more like MADV_HUGEPAGE, e.g. theoretically we could extend fadvise() with FADV_HUGEPAGE, or add a guest_memfd knob/ioctl() to let userspace provide advice/hints after creating a guest_memfd. But I suspect that guest_memfd would be the only user of FADV_HUGEPAGE, and IMO a post-creation hint is actually less desirable. KVM_GUEST_MEMFD_ALLOW_HUGEPAGE will fail only if userspace didn't provide a compatible size or the kernel doesn't support THP. An incompatible size is likely a userspace bug, and for most setups that want to utilize guest_memfd, lack of THP support is likely a configuration bug. I.e. many/most uses *want* failures due to KVM_GUEST_MEMFD_ALLOW_HUGEPAGE to be fatal. > For current implementation, I think maybe KVM_GUEST_MEMFD_DESIRE_HUGEPAGE > fits better than KVM_GUEST_MEMFD_ALLOW_HUGEPAGE? or maybe *PREFER*? Why? Verbs like "prefer" and "desire" aren't a good fit IMO because they suggest the flag is a hint, and hints are usually best effort only, i.e. are ignored if there is a fundamental incompatibility. "Allow" isn't perfect, e.g. I would much prefer a straight KVM_GUEST_MEMFD_USE_HUGEPAGES or KVM_GUEST_MEMFD_HUGEPAGES flag, but I wanted the name to convey that KVM doesn't (yet) guarantee hugepages. I.e. KVM_GUEST_MEMFD_ALLOW_HUGEPAGE is stronger than a hint, but weaker than a requirement. And if/when KVM supports a dedicated memory pool of some kind, then we can add KVM_GUEST_MEMFD_REQUIRE_HUGEPAGE. _______________________________________________ linux-riscv mailing list linux-riscv@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-riscv From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from lists.ozlabs.org (lists.ozlabs.org [112.213.38.117]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id 92A9EC4167D for ; Wed, 1 Nov 2023 13:42:45 +0000 (UTC) Authentication-Results: lists.ozlabs.org; dkim=fail reason="signature verification failed" (2048-bit key; unprotected) header.d=google.com header.i=@google.com header.a=rsa-sha256 header.s=20230601 header.b=jRcODWVN; dkim-atps=neutral Received: from boromir.ozlabs.org (localhost [IPv6:::1]) by lists.ozlabs.org (Postfix) with ESMTP id 4SL7VX1jCjz3cST for ; Thu, 2 Nov 2023 00:42:44 +1100 (AEDT) Authentication-Results: lists.ozlabs.org; dkim=pass (2048-bit key; unprotected) header.d=google.com header.i=@google.com header.a=rsa-sha256 header.s=20230601 header.b=jRcODWVN; dkim-atps=neutral Authentication-Results: lists.ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=flex--seanjc.bounces.google.com (client-ip=2607:f8b0:4864:20::114a; helo=mail-yw1-x114a.google.com; envelope-from=3mlvczqykdh8vhdqmfjrrjoh.frpolqx0ssf-ghyolvwv.r2odev.ruj@flex--seanjc.bounces.google.com; receiver=lists.ozlabs.org) Received: from mail-yw1-x114a.google.com (mail-yw1-x114a.google.com [IPv6:2607:f8b0:4864:20::114a]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest SHA256) (No client certificate requested) by lists.ozlabs.org (Postfix) with ESMTPS id 4SL7TX027xz2xl6 for ; Thu, 2 Nov 2023 00:41:50 +1100 (AEDT) Received: by mail-yw1-x114a.google.com with SMTP id 00721157ae682-5a8ee6a1801so80240987b3.3 for ; Wed, 01 Nov 2023 06:41:50 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20230601; t=1698846107; x=1699450907; darn=lists.ozlabs.org; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:from:to:cc:subject:date:message-id:reply-to; bh=nFf6aEaGwk5ej5JezQy0IgMN87WPAcTCXufwbiE3fug=; b=jRcODWVNf4HPt/va7ieM1Oezre/1ZPdWH79NhBnmGGB0VJmJ3hpXQvFc6coh8/MsQL d2SU7kvYsXJLZag7WMVg1YXuLvXHUtOogOmTMKcwFemUEa3qujknBlcHhgYgExmILi5T ce0DaHXHXVME3BI2k7ph5v8wy7Qt/OMS02Tc+BwAihA4v3HkTdOx8x3HXQGzPELXFqo7 9rOk30vPGydMWBqkK3IrX29JukAqCgKLTATyDYnZnsdSd+dQEbPTxF7LS7jxm7NIriX+ ETQX5uXCuilPmIUErywWyRr+g1zPYrFAWzHQoa+SyINAHUwePmvk7gv/gU6QQ0sGBpHY y7qg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1698846107; x=1699450907; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:x-gm-message-state:from:to:cc:subject:date:message-id:reply-to; bh=nFf6aEaGwk5ej5JezQy0IgMN87WPAcTCXufwbiE3fug=; b=srG2NrmsOiDtSsWL7VfR+CyCV05eOCmvbDs6G+gOC4LCB1WhrrbnaMXeCMccB37gGT GC3LxIwA8EN2rDQXjeyWM4ZNlsi9UaBiAtZ495Eq6yk5X6fpPVp+qOhmfn90wLhfEhqW wTEUE9vcVcfmhsloyG5XqvwzUl7RRSR7FLQg9MrHVH/55qhxjVM8ajK/GtLcTtKcscfx DBRblF88iBXrTySJdrn5cv/pXgEaEAnxwb1dqhswwKd+JmjsWiiNg0WxLa0TCzsm7bdx tKIst8wx33uCSmlar4fxOTVaJXSkwE6QBJ/dWWkUSPqml+H76S2mwyUTa62KVpBRhCYg 4rww== X-Gm-Message-State: AOJu0YwUyQTRYOdiahf4hxpkrPH3dnVwRDCfRrBk63dRZL5Cs2C9SrK1 zCvJ+pgDKZG+EVA0o/du4vd7MbXmj+c= X-Google-Smtp-Source: AGHT+IEsRM1yQnQClQeVqyoNLxT9cYgRny7PWezkHcY0wXTm/cdeLyJgnrb+5OZENHYJQKvQlFBt8yx8E+I= X-Received: from zagreus.c.googlers.com ([fda3:e722:ac3:cc00:7f:e700:c0a8:5c37]) (user=seanjc job=sendgmr) by 2002:a0d:e689:0:b0:5a7:bfcf:2cb8 with SMTP id p131-20020a0de689000000b005a7bfcf2cb8mr314827ywe.1.1698846106686; Wed, 01 Nov 2023 06:41:46 -0700 (PDT) Date: Wed, 1 Nov 2023 06:41:45 -0700 In-Reply-To: <92ba7ddd-2bc8-4a8d-bd67-d6614b21914f@intel.com> Mime-Version: 1.0 References: <20231027182217.3615211-1-seanjc@google.com> <20231027182217.3615211-18-seanjc@google.com> <7c0844d8-6f97-4904-a140-abeabeb552c1@intel.com> <92ba7ddd-2bc8-4a8d-bd67-d6614b21914f@intel.com> Message-ID: Subject: Re: [PATCH v13 17/35] KVM: Add transparent hugepage support for dedicated guest memory From: Sean Christopherson To: Xiaoyao Li Content-Type: text/plain; charset="us-ascii" X-BeenThere: linuxppc-dev@lists.ozlabs.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: kvm@vger.kernel.org, David Hildenbrand , linux-kernel@vger.kernel.org, linux-mm@kvack.org, Chao Peng , linux-riscv@lists.infradead.org, Isaku Yamahata , Marc Zyngier , Huacai Chen , "Matthew Wilcox \(Oracle\)" , Wang , Fuad Tabba , Yu Zhang , Maciej Szmigiero , Albert Ou , Vlastimil Babka , Michael Roth , Ackerley Tng , Alexander Viro , Paul Walmsley , kvmarm@lists.linux.dev, linux-arm-kernel@lists.infradead.org, =?utf-8?Q?Micka=C3=ABl_Sala=C3=BCn?= , Isaku Yamahata , Christian Brauner , Quentin Perret , Liam Merwick , linux-mips@vger.kernel.org, Oliver Upton , David Matlack , Jarkko Sakkinen , Palmer Dabbelt , "Kirill A . Shutemov" , kvm-riscv@lists.infradead.org, Anup Patel , linux-fsdevel@vger.kernel.org, Paolo Bonzini , Andrew Morton , Vishal Annapurve , linuxppc-dev@lists.ozlabs.org, Xu Yilun , Anish Moorthy Errors-To: linuxppc-dev-bounces+linuxppc-dev=archiver.kernel.org@lists.ozlabs.org Sender: "Linuxppc-dev" On Wed, Nov 01, 2023, Xiaoyao Li wrote: > On 10/31/2023 10:16 PM, Sean Christopherson wrote: > > On Tue, Oct 31, 2023, Xiaoyao Li wrote: > > > On 10/28/2023 2:21 AM, Sean Christopherson wrote: > > > > Extended guest_memfd to allow backing guest memory with transparent > > > > hugepages. Require userspace to opt-in via a flag even though there's no > > > > known/anticipated use case for forcing small pages as THP is optional, > > > > i.e. to avoid ending up in a situation where userspace is unaware that > > > > KVM can't provide hugepages. > > > > > > Personally, it seems not so "transparent" if requiring userspace to opt-in. > > > > > > People need to 1) check if the kernel built with TRANSPARENT_HUGEPAGE > > > support, or check is the sysfs of transparent hugepage exists; 2)get the > > > maximum support hugepage size 3) ensure the size satisfies the alignment; > > > before opt-in it. > > > > > > Even simpler, userspace can blindly try to create guest memfd with > > > transparent hugapage flag. If getting error, fallback to create without the > > > transparent hugepage flag. > > > > > > However, it doesn't look transparent to me. > > > > The "transparent" part is referring to the underlying kernel mechanism, it's not > > saying anything about the API. The "transparent" part of THP is that the kernel > > doesn't guarantee hugepages, i.e. whether or not hugepages are actually used is > > (mostly) transparent to userspace. > > > > Paolo also isn't the biggest fan[*], but there are also downsides to always > > allowing hugepages, e.g. silent failure due to lack of THP or unaligned size, > > and there's precedent in the form of MADV_HUGEPAGE. > > > > [*] https://lore.kernel.org/all/84a908ae-04c7-51c7-c9a8-119e1933a189@redhat.com > > But it's different than MADV_HUGEPAGE, in a way. Per my understanding, the > failure of MADV_HUGEPAGE is not fatal, user space can ignore it and > continue. > > However, the failure of KVM_GUEST_MEMFD_ALLOW_HUGEPAGE is fatal, which leads > to failure of guest memfd creation. Failing KVM_CREATE_GUEST_MEMFD isn't truly fatal, it just requires different action from userspace, i.e. instead of ignoring the error, userspace could redo KVM_CREATE_GUEST_MEMFD with KVM_GUEST_MEMFD_ALLOW_HUGEPAGE=0. We could make the behavior more like MADV_HUGEPAGE, e.g. theoretically we could extend fadvise() with FADV_HUGEPAGE, or add a guest_memfd knob/ioctl() to let userspace provide advice/hints after creating a guest_memfd. But I suspect that guest_memfd would be the only user of FADV_HUGEPAGE, and IMO a post-creation hint is actually less desirable. KVM_GUEST_MEMFD_ALLOW_HUGEPAGE will fail only if userspace didn't provide a compatible size or the kernel doesn't support THP. An incompatible size is likely a userspace bug, and for most setups that want to utilize guest_memfd, lack of THP support is likely a configuration bug. I.e. many/most uses *want* failures due to KVM_GUEST_MEMFD_ALLOW_HUGEPAGE to be fatal. > For current implementation, I think maybe KVM_GUEST_MEMFD_DESIRE_HUGEPAGE > fits better than KVM_GUEST_MEMFD_ALLOW_HUGEPAGE? or maybe *PREFER*? Why? Verbs like "prefer" and "desire" aren't a good fit IMO because they suggest the flag is a hint, and hints are usually best effort only, i.e. are ignored if there is a fundamental incompatibility. "Allow" isn't perfect, e.g. I would much prefer a straight KVM_GUEST_MEMFD_USE_HUGEPAGES or KVM_GUEST_MEMFD_HUGEPAGES flag, but I wanted the name to convey that KVM doesn't (yet) guarantee hugepages. I.e. KVM_GUEST_MEMFD_ALLOW_HUGEPAGE is stronger than a hint, but weaker than a requirement. And if/when KVM supports a dedicated memory pool of some kind, then we can add KVM_GUEST_MEMFD_REQUIRE_HUGEPAGE. From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from bombadil.infradead.org (bombadil.infradead.org [198.137.202.133]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id C88D0C4167D for ; Wed, 1 Nov 2023 13:42:29 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=lists.infradead.org; s=bombadil.20210309; h=Sender: Content-Transfer-Encoding:Content-Type:List-Subscribe:List-Help:List-Post: List-Archive:List-Unsubscribe:List-Id:Cc:To:From:Subject:Message-ID: References:Mime-Version:In-Reply-To:Date:Reply-To:Content-ID: Content-Description:Resent-Date:Resent-From:Resent-Sender:Resent-To:Resent-Cc :Resent-Message-ID:List-Owner; bh=wPogpYqDAXQX8HTgsmMEdNXOqDtslJJ+T/19tSicFMI=; b=0uM7q+8Oa+KzYIqeXrMFHHwrqN +Hq4vI5DJUhIxkKcFVFkTc1UGjrWV6dSba84qrIA0WXFiTOtZkgACtP+w7YviETcIvhgU+J7KU++Q jtUzgXR9QuMnRP23bGUhnDsjwO2dGwHUdLVp9winsyPfcz7B4sCjLxL1pdWVEAO4FBNg4Dod+lwoS U2CTApFXcRV0pCCp9d4yLg8NDP9/sV0ePTIcWxEZWGrRVkEf7AE1tSr9FjYdT2xmdoak9/yeTkoJD inVaksIvTyXKDfTp3rjOASlW2NcIq4H6EWZVbZS20IxYzvFF87G7kV/SyDgTk7wFzu+tAIyEYkPn3 oxvK0QrA==; Received: from localhost ([::1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.96 #2 (Red Hat Linux)) id 1qyBTm-007alA-0o; Wed, 01 Nov 2023 13:41:54 +0000 Received: from mail-yw1-x114a.google.com ([2607:f8b0:4864:20::114a]) by bombadil.infradead.org with esmtps (Exim 4.96 #2 (Red Hat Linux)) id 1qyBTi-007ais-2P for linux-arm-kernel@lists.infradead.org; Wed, 01 Nov 2023 13:41:52 +0000 Received: by mail-yw1-x114a.google.com with SMTP id 00721157ae682-5a7aa161b2fso80286597b3.2 for ; Wed, 01 Nov 2023 06:41:47 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20230601; t=1698846107; x=1699450907; darn=lists.infradead.org; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:from:to:cc:subject:date:message-id:reply-to; bh=nFf6aEaGwk5ej5JezQy0IgMN87WPAcTCXufwbiE3fug=; b=TxdC4ML5TuMh93VSDIBzefA8qXHE98Qp7DkzFy+i+0QcJgxEmBgxKmoMnY31GfO9Ts gDtoNMplscagESRttUr450U4+LUtViT8OE7gacG5SirW+Je8Jxobnh6HNWmst3ZDiPgG uour4Nxl6HgnqdaCxqzqyMhSSObKEf5sh71j2AtfIrV51wqqi8qXrYDV9ljHdB4x05jI MguS6b4M/dRvOLlkrbFJxPU1ei6wJ2Cxa5+mdwGLD8clMhJhMrY2LHUjsAYHAwx73ur9 1s4EPR6dpmavK9dahKPREYfcNgrCv0ISEmhCQgOF2Jmx2py+HHhJsBEL6SLIlemGekp9 KtAg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1698846107; x=1699450907; h=cc:to:from:subject:message-id:references:mime-version:in-reply-to :date:x-gm-message-state:from:to:cc:subject:date:message-id:reply-to; bh=nFf6aEaGwk5ej5JezQy0IgMN87WPAcTCXufwbiE3fug=; b=p5s+0OEoH1sw1dJE8l2teMZKjS6CCzCCm9w6V5/959tfOgXRh2U4VNlyb1Zqdihq6D ucWAI6sRT6Nk27CeNcfOmcL993GfSdMpC8icLvA0axhXvga6tiOY0FZ5oJz2BNeARHuB ErtSB/XAVoV2z8jesH6eWZMQhjd10BlACcr7RLDX8RVq3pdNHbTOV+2Xhm7+/QFuy6Eq WNnJogndaE/gMjYpclihrrsVwD2vqTUFrON6dYAID0pg7LblzcfzH0GSyghcdoFwK1n3 zD49fnmyZHuI3ylC5acAII2QwZg3tv3nbodS8rBObxC3iLQOjJ0weJmtp3x8QPBH6CHB FBew== X-Gm-Message-State: AOJu0YxvWpqwmk7DmD0CKDLwKCL70EeeRyFdddSveoYwWgsmb3NpWDA/ hemZ/b5gY9KZoFInAUFFZxfWslEg4hs= X-Google-Smtp-Source: AGHT+IEsRM1yQnQClQeVqyoNLxT9cYgRny7PWezkHcY0wXTm/cdeLyJgnrb+5OZENHYJQKvQlFBt8yx8E+I= X-Received: from zagreus.c.googlers.com ([fda3:e722:ac3:cc00:7f:e700:c0a8:5c37]) (user=seanjc job=sendgmr) by 2002:a0d:e689:0:b0:5a7:bfcf:2cb8 with SMTP id p131-20020a0de689000000b005a7bfcf2cb8mr314827ywe.1.1698846106686; Wed, 01 Nov 2023 06:41:46 -0700 (PDT) Date: Wed, 1 Nov 2023 06:41:45 -0700 In-Reply-To: <92ba7ddd-2bc8-4a8d-bd67-d6614b21914f@intel.com> Mime-Version: 1.0 References: <20231027182217.3615211-1-seanjc@google.com> <20231027182217.3615211-18-seanjc@google.com> <7c0844d8-6f97-4904-a140-abeabeb552c1@intel.com> <92ba7ddd-2bc8-4a8d-bd67-d6614b21914f@intel.com> Message-ID: Subject: Re: [PATCH v13 17/35] KVM: Add transparent hugepage support for dedicated guest memory From: Sean Christopherson To: Xiaoyao Li Cc: Paolo Bonzini , Marc Zyngier , Oliver Upton , Huacai Chen , Michael Ellerman , Anup Patel , Paul Walmsley , Palmer Dabbelt , Albert Ou , Alexander Viro , Christian Brauner , "Matthew Wilcox (Oracle)" , Andrew Morton , kvm@vger.kernel.org, linux-arm-kernel@lists.infradead.org, kvmarm@lists.linux.dev, linux-mips@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, kvm-riscv@lists.infradead.org, linux-riscv@lists.infradead.org, linux-fsdevel@vger.kernel.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org, Xu Yilun , Chao Peng , Fuad Tabba , Jarkko Sakkinen , Anish Moorthy , David Matlack , Yu Zhang , Isaku Yamahata , "=?utf-8?Q?Micka=C3=ABl_Sala=C3=BCn?=" , Vlastimil Babka , Vishal Annapurve , Ackerley Tng , Maciej Szmigiero , David Hildenbrand , Quentin Perret , Michael Roth , Wang , Liam Merwick , Isaku Yamahata , "Kirill A . Shutemov" X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20231101_064150_790856_A6C07250 X-CRM114-Status: GOOD ( 30.59 ) X-BeenThere: linux-arm-kernel@lists.infradead.org X-Mailman-Version: 2.1.34 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Sender: "linux-arm-kernel" Errors-To: linux-arm-kernel-bounces+linux-arm-kernel=archiver.kernel.org@lists.infradead.org On Wed, Nov 01, 2023, Xiaoyao Li wrote: > On 10/31/2023 10:16 PM, Sean Christopherson wrote: > > On Tue, Oct 31, 2023, Xiaoyao Li wrote: > > > On 10/28/2023 2:21 AM, Sean Christopherson wrote: > > > > Extended guest_memfd to allow backing guest memory with transparent > > > > hugepages. Require userspace to opt-in via a flag even though there's no > > > > known/anticipated use case for forcing small pages as THP is optional, > > > > i.e. to avoid ending up in a situation where userspace is unaware that > > > > KVM can't provide hugepages. > > > > > > Personally, it seems not so "transparent" if requiring userspace to opt-in. > > > > > > People need to 1) check if the kernel built with TRANSPARENT_HUGEPAGE > > > support, or check is the sysfs of transparent hugepage exists; 2)get the > > > maximum support hugepage size 3) ensure the size satisfies the alignment; > > > before opt-in it. > > > > > > Even simpler, userspace can blindly try to create guest memfd with > > > transparent hugapage flag. If getting error, fallback to create without the > > > transparent hugepage flag. > > > > > > However, it doesn't look transparent to me. > > > > The "transparent" part is referring to the underlying kernel mechanism, it's not > > saying anything about the API. The "transparent" part of THP is that the kernel > > doesn't guarantee hugepages, i.e. whether or not hugepages are actually used is > > (mostly) transparent to userspace. > > > > Paolo also isn't the biggest fan[*], but there are also downsides to always > > allowing hugepages, e.g. silent failure due to lack of THP or unaligned size, > > and there's precedent in the form of MADV_HUGEPAGE. > > > > [*] https://lore.kernel.org/all/84a908ae-04c7-51c7-c9a8-119e1933a189@redhat.com > > But it's different than MADV_HUGEPAGE, in a way. Per my understanding, the > failure of MADV_HUGEPAGE is not fatal, user space can ignore it and > continue. > > However, the failure of KVM_GUEST_MEMFD_ALLOW_HUGEPAGE is fatal, which leads > to failure of guest memfd creation. Failing KVM_CREATE_GUEST_MEMFD isn't truly fatal, it just requires different action from userspace, i.e. instead of ignoring the error, userspace could redo KVM_CREATE_GUEST_MEMFD with KVM_GUEST_MEMFD_ALLOW_HUGEPAGE=0. We could make the behavior more like MADV_HUGEPAGE, e.g. theoretically we could extend fadvise() with FADV_HUGEPAGE, or add a guest_memfd knob/ioctl() to let userspace provide advice/hints after creating a guest_memfd. But I suspect that guest_memfd would be the only user of FADV_HUGEPAGE, and IMO a post-creation hint is actually less desirable. KVM_GUEST_MEMFD_ALLOW_HUGEPAGE will fail only if userspace didn't provide a compatible size or the kernel doesn't support THP. An incompatible size is likely a userspace bug, and for most setups that want to utilize guest_memfd, lack of THP support is likely a configuration bug. I.e. many/most uses *want* failures due to KVM_GUEST_MEMFD_ALLOW_HUGEPAGE to be fatal. > For current implementation, I think maybe KVM_GUEST_MEMFD_DESIRE_HUGEPAGE > fits better than KVM_GUEST_MEMFD_ALLOW_HUGEPAGE? or maybe *PREFER*? Why? Verbs like "prefer" and "desire" aren't a good fit IMO because they suggest the flag is a hint, and hints are usually best effort only, i.e. are ignored if there is a fundamental incompatibility. "Allow" isn't perfect, e.g. I would much prefer a straight KVM_GUEST_MEMFD_USE_HUGEPAGES or KVM_GUEST_MEMFD_HUGEPAGES flag, but I wanted the name to convey that KVM doesn't (yet) guarantee hugepages. I.e. KVM_GUEST_MEMFD_ALLOW_HUGEPAGE is stronger than a hint, but weaker than a requirement. And if/when KVM supports a dedicated memory pool of some kind, then we can add KVM_GUEST_MEMFD_REQUIRE_HUGEPAGE. _______________________________________________ linux-arm-kernel mailing list linux-arm-kernel@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-arm-kernel