From nobody Wed Dec 17 09:50:20 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 066CFCDB465 for ; Mon, 16 Oct 2023 16:40:40 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1343538AbjJPQkh (ORCPT ); Mon, 16 Oct 2023 12:40:37 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:55722 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1343572AbjJPQjP (ORCPT ); Mon, 16 Oct 2023 12:39:15 -0400 Received: from mgamail.intel.com (mgamail.intel.com [192.55.52.43]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id EC83C8258; Mon, 16 Oct 2023 09:23:15 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1697473396; x=1729009396; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=y35oJUPopyeRbTd34DdLXBVXFicmHGF9J0ehvEF/xG0=; b=mKbBevXv1+UXK5+Lsljn5cYtREcta7uXcH6+Mw16+WEPw0I8zc5XF+S5 jypaqru9S3EyPfQ1TUz3tfyzKtEPhi821/k3792SeRJqLPrWmO/MARkrT 69/XrBgx5hVQQw/zbs+WIGGNtMI7XaxYOsoRIBVsmdXjRJh2S/99rFGck sEmXOXHGuMefECxPsX12bjtoU57eauEnNIV5DaBizMCjJGASzAtqT2WJM xCIe+dthNCitIY677Taq2lRfEx76583nArLvTLUELJCprTmTkIhc4Cb2D U6RSlwwyZukvRQOR8o1A1F9pyU/OPK4WaLxijCH9pry8l7N5uUiNllRUh g==; X-IronPort-AV: E=McAfee;i="6600,9927,10865"; a="471793146" X-IronPort-AV: E=Sophos;i="6.03,229,1694761200"; d="scan'208";a="471793146" Received: from fmsmga001.fm.intel.com ([10.253.24.23]) by fmsmga105.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 16 Oct 2023 09:21:13 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6600,9927,10865"; a="899569231" X-IronPort-AV: E=Sophos;i="6.03,229,1694761200"; d="scan'208";a="899569231" Received: from ls.sc.intel.com (HELO localhost) ([172.25.112.31]) by fmsmga001-auth.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 16 Oct 2023 09:19:14 -0700 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 , Kai Huang , Zhi Wang , chen.bo@intel.com, hang.yuan@intel.com, tina.zhang@intel.com, Xiaoyao Li Subject: [RFC PATCH v5 06/16] KVM: TDX: Update tdx_sept_{set,drop}_private_spte() to support large page Date: Mon, 16 Oct 2023 09:20:57 -0700 Message-Id: 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 | 70 ++++++++++++++++++++++-------------------- 1 file changed, 36 insertions(+), 34 deletions(-) diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c index 72672b2c30a1..992cf3ed02f2 100644 --- a/arch/x86/kvm/vmx/tdx.c +++ b/arch/x86/kvm/vmx/tdx.c @@ -1435,11 +1435,12 @@ 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_page_aug(struct kvm *kvm, gfn_t gfn, @@ -1456,7 +1457,7 @@ static int tdx_sept_page_aug(struct kvm *kvm, gfn_t g= fn, =20 err =3D tdh_mem_page_aug(kvm_tdx->tdr_pa, gpa, tdx_level, hpa, &out); if (unlikely(err =3D=3D TDX_ERROR_SEPT_BUSY)) { - tdx_unpin(kvm, pfn); + tdx_unpin(kvm, pfn, level); return -EAGAIN; } if (unlikely(err =3D=3D (TDX_EPT_ENTRY_NOT_FREE | TDX_OPERAND_ID_RCX))) { @@ -1472,7 +1473,7 @@ static int tdx_sept_page_aug(struct kvm *kvm, gfn_t g= fn, &tmpout); if (KVM_BUG_ON(tmp, kvm)) { pr_tdx_error(TDH_MEM_SEPT_RD, tmp, &tmpout); - tdx_unpin(kvm, pfn); + tdx_unpin(kvm, pfn, level); return -EIO; } pr_debug_ratelimited("gfn 0x%llx pg_level %d pfn 0x%llx entry 0x%llx lev= el_stat 0x%llx\n", @@ -1483,7 +1484,7 @@ static int tdx_sept_page_aug(struct kvm *kvm, gfn_t g= fn, if (level_state.level =3D=3D tdx_level && level_state.state =3D=3D TDX_SEPT_PENDING && entry.leaf && entry.pfn =3D=3D pfn && entry.sve) { - tdx_unpin(kvm, pfn); + tdx_unpin(kvm, pfn, level); WARN_ON_ONCE(!(to_kvm_tdx(kvm)->attributes & TDX_TD_ATTR_SEPT_VE_DISABLE)); return -EAGAIN; @@ -1491,7 +1492,7 @@ static int tdx_sept_page_aug(struct kvm *kvm, gfn_t g= fn, } 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; } =20 @@ -1527,7 +1528,7 @@ static int tdx_sept_page_add(struct kvm *kvm, gfn_t g= fn, * 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 @@ -1545,7 +1546,7 @@ static int tdx_sept_page_add(struct kvm *kvm, gfn_t g= fn, } while (unlikely(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)); @@ -1558,10 +1559,7 @@ static int tdx_sept_set_private_spte(struct kvm *kvm= , gfn_t gfn, enum pg_level level, kvm_pfn_t pfn) { struct kvm_tdx *kvm_tdx =3D to_kvm_tdx(kvm); - - /* TODO: handle large pages. */ - if (KVM_BUG_ON(level !=3D PG_LEVEL_4K, kvm)) - return -EINVAL; + int i; =20 /* * Because restricted mem doesn't support page migration with @@ -1571,7 +1569,8 @@ static int tdx_sept_set_private_spte(struct kvm *kvm,= 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 if (likely(is_td_finalized(kvm_tdx))) return tdx_sept_page_aug(kvm, gfn, level, pfn); @@ -1588,11 +1587,9 @@ 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 (unlikely(!is_hkid_assigned(kvm_tdx))) { /* @@ -1602,7 +1599,7 @@ static int tdx_sept_drop_private_spte(struct kvm *kvm= , gfn_t gfn, err =3D tdx_reclaim_page(hpa, level); if (KVM_BUG_ON(err, kvm)) return -EIO; - tdx_unpin(kvm, pfn); + tdx_unpin(kvm, pfn, level); return 0; } =20 @@ -1619,22 +1616,27 @@ 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 (unlikely(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 (unlikely(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_clear_page(hpa, PAGE_SIZE); + tdx_unpin(kvm, pfn + i, PG_LEVEL_4K); + } + hpa +=3D PAGE_SIZE; } - tdx_clear_page(hpa, 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