From nobody Mon Sep 15 11:37:37 2025 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 9D2C3C54EBE for ; Thu, 12 Jan 2023 17:12:53 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S240017AbjALRMs (ORCPT ); Thu, 12 Jan 2023 12:12:48 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:43682 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S230124AbjALRMK (ORCPT ); Thu, 12 Jan 2023 12:12:10 -0500 Received: from mga14.intel.com (mga14.intel.com [192.55.52.115]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 1D6C17CDF0; Thu, 12 Jan 2023 08:48:48 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1673542136; x=1705078136; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=nIjTfGGdZyqyIE1lEPQNVb+HiQZclRMOxDxgV3JrZtc=; b=T+Hd8tbV8PoTcRCNP9RfLHpdw06LN2dK1aHFATihCwJr2TEKSQuKsCev mCgwewB4NJPyL63wCDZa2p7n+GqoCgnff4vNBjgRzeXIJtZrqfWc9BnIJ Wot1oK/wYIfjaYa4f7aTXPbsqUwoi4Sx8YZAzKd3wmJIl0zyjXmRmFEAB AxDymcwJ0AV4GJN3hXY5ICvPrAkWZ+qcCD38uIP58xw5HTD6gcqBD/emH 7reD/wc4A3XSmu1l11QCveEK/xSE34ZEeJb93+eXE2HD5ydkGytnz77p2 qF6LcSXMOnqF+Kmil1ZrfjkA7YIn9MFL3hzMao1rHCZMn5WvM7dVa7weK Q==; X-IronPort-AV: E=McAfee;i="6500,9779,10588"; a="323816299" X-IronPort-AV: E=Sophos;i="5.97,211,1669104000"; d="scan'208";a="323816299" Received: from fmsmga005.fm.intel.com ([10.253.24.32]) by fmsmga103.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 12 Jan 2023 08:44:17 -0800 X-IronPort-AV: E=McAfee;i="6500,9779,10588"; a="986658338" X-IronPort-AV: E=Sophos;i="5.97,211,1669104000"; d="scan'208";a="986658338" Received: from ls.sc.intel.com (HELO localhost) ([143.183.96.54]) by fmsmga005-auth.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 12 Jan 2023 08:44:16 -0800 From: isaku.yamahata@intel.com To: kvm@vger.kernel.org, linux-kernel@vger.kernel.org Cc: isaku.yamahata@intel.com, isaku.yamahata@gmail.com, Paolo Bonzini , erdemaktas@google.com, Sean Christopherson , Sagi Shahar , David Matlack , Xiaoyao Li Subject: [RFC PATCH v3 06/16] KVM: TDX: Update tdx_sept_{set,drop}_private_spte() to support large page Date: Thu, 12 Jan 2023 08:43:58 -0800 Message-Id: <591f477bd44f0cfbc7475194be32e9f771c3f2f8.1673541292.git.isaku.yamahata@intel.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: References: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" From: Xiaoyao Li Allow large page level AUG and REMOVE for TDX pages. Signed-off-by: Xiaoyao Li Signed-off-by: Isaku Yamahata --- arch/x86/kvm/vmx/tdx.c | 63 +++++++++++++++++++++--------------------- 1 file changed, 32 insertions(+), 31 deletions(-) diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c index 8bc8fd7f28eb..d7be634edf3c 100644 --- a/arch/x86/kvm/vmx/tdx.c +++ b/arch/x86/kvm/vmx/tdx.c @@ -1322,11 +1322,12 @@ static void tdx_measure_page(struct kvm_tdx *kvm_td= x, hpa_t gpa, int size) } } =20 -static void tdx_unpin(struct kvm *kvm, kvm_pfn_t pfn) +static void tdx_unpin(struct kvm *kvm, kvm_pfn_t pfn, int level) { - struct page *page =3D pfn_to_page(pfn); + int i; =20 - put_page(page); + for (i =3D 0; i < KVM_PAGES_PER_HPAGE(level); i++) + put_page(pfn_to_page(pfn + i)); } =20 static int tdx_sept_set_private_spte(struct kvm *kvm, gfn_t gfn, @@ -1340,6 +1341,7 @@ static int tdx_sept_set_private_spte(struct kvm *kvm,= gfn_t gfn, hpa_t source_pa; bool measure; u64 err; + int i; =20 /* * Because restricted mem doesn't support page migration with @@ -1349,22 +1351,19 @@ static int tdx_sept_set_private_spte(struct kvm *kv= m, gfn_t gfn, * TODO: Once restricted mem introduces callback on page migration, * implement it and remove get_page/put_page(). */ - get_page(pfn_to_page(pfn)); + for (i =3D 0; i < KVM_PAGES_PER_HPAGE(level); i++) + get_page(pfn_to_page(pfn + i)); =20 /* Build-time faults are induced and handled via TDH_MEM_PAGE_ADD. */ if (likely(is_td_finalized(kvm_tdx))) { - /* TODO: handle large pages. */ - if (KVM_BUG_ON(level !=3D PG_LEVEL_4K, kvm)) - return -EINVAL; - err =3D tdh_mem_page_aug(kvm_tdx->tdr_pa, gpa, tdx_level, hpa, &out); if (err =3D=3D TDX_ERROR_SEPT_BUSY) { - tdx_unpin(kvm, pfn); + tdx_unpin(kvm, pfn, level); return -EAGAIN; } if (KVM_BUG_ON(err, kvm)) { pr_tdx_error(TDH_MEM_PAGE_AUG, err, &out); - tdx_unpin(kvm, pfn); + tdx_unpin(kvm, pfn, level); return -EIO; } return 0; @@ -1387,7 +1386,7 @@ static int tdx_sept_set_private_spte(struct kvm *kvm,= gfn_t gfn, * always uses vcpu 0's page table and protected by vcpu->mutex). */ if (KVM_BUG_ON(kvm_tdx->source_pa =3D=3D INVALID_PAGE, kvm)) { - tdx_unpin(kvm, pfn); + tdx_unpin(kvm, pfn, level); return -EINVAL; } =20 @@ -1405,7 +1404,7 @@ static int tdx_sept_set_private_spte(struct kvm *kvm,= gfn_t gfn, } while (err =3D=3D TDX_ERROR_SEPT_BUSY); if (KVM_BUG_ON(err, kvm)) { pr_tdx_error(TDH_MEM_PAGE_ADD, err, &out); - tdx_unpin(kvm, pfn); + tdx_unpin(kvm, pfn, level); return -EIO; } else if (measure) tdx_measure_page(kvm_tdx, gpa, KVM_HPAGE_SIZE(level)); @@ -1422,11 +1421,9 @@ static int tdx_sept_drop_private_spte(struct kvm *kv= m, gfn_t gfn, gpa_t gpa =3D gfn_to_gpa(gfn); hpa_t hpa =3D pfn_to_hpa(pfn); hpa_t hpa_with_hkid; + int r =3D 0; u64 err; - - /* TODO: handle large pages. */ - if (KVM_BUG_ON(level !=3D PG_LEVEL_4K, kvm)) - return -EINVAL; + int i; =20 if (!is_hkid_assigned(kvm_tdx)) { /* @@ -1436,7 +1433,7 @@ static int tdx_sept_drop_private_spte(struct kvm *kvm= , gfn_t gfn, err =3D tdx_reclaim_page(hpa, level, false, 0); if (KVM_BUG_ON(err, kvm)) return -EIO; - tdx_unpin(kvm, pfn); + tdx_unpin(kvm, pfn, level); return 0; } =20 @@ -1453,21 +1450,25 @@ static int tdx_sept_drop_private_spte(struct kvm *k= vm, gfn_t gfn, return -EIO; } =20 - hpa_with_hkid =3D set_hkid_to_hpa(hpa, (u16)kvm_tdx->hkid); - do { - /* - * TDX_OPERAND_BUSY can happen on locking PAMT entry. Because - * this page was removed above, other thread shouldn't be - * repeatedly operating on this page. Just retry loop. - */ - err =3D tdh_phymem_page_wbinvd(hpa_with_hkid); - } while (err =3D=3D (TDX_OPERAND_BUSY | TDX_OPERAND_ID_RCX)); - if (KVM_BUG_ON(err, kvm)) { - pr_tdx_error(TDH_PHYMEM_PAGE_WBINVD, err, NULL); - return -EIO; + for (i =3D 0; i < KVM_PAGES_PER_HPAGE(level); i++) { + hpa_with_hkid =3D set_hkid_to_hpa(hpa, (u16)kvm_tdx->hkid); + do { + /* + * TDX_OPERAND_BUSY can happen on locking PAMT entry. + * Because this page was removed above, other thread + * shouldn't be repeatedly operating on this page. + * Simple retry should work. + */ + err =3D tdh_phymem_page_wbinvd(hpa_with_hkid); + } while (err =3D=3D (TDX_OPERAND_BUSY | TDX_OPERAND_ID_RCX)); + if (KVM_BUG_ON(err, kvm)) { + pr_tdx_error(TDH_PHYMEM_PAGE_WBINVD, err, NULL); + r =3D -EIO; + } else + tdx_unpin(kvm, pfn + i, PG_LEVEL_4K); + hpa +=3D PAGE_SIZE; } - tdx_unpin(kvm, pfn); - return 0; + return r; } =20 static int tdx_sept_link_private_spt(struct kvm *kvm, gfn_t gfn, --=20 2.25.1