From nobody Thu Nov 6 16:12:02 2025 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) client-ip=208.118.235.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zohomail.com; spf=pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail(p=none dis=none) header.from=linux.intel.com Return-Path: Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) by mx.zohomail.com with SMTPS id 1542175737070849.0748260456022; Tue, 13 Nov 2018 22:08:57 -0800 (PST) Received: from localhost ([::1]:58430 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1gMoM8-0005Et-83 for importer@patchew.org; Wed, 14 Nov 2018 01:08:52 -0500 Received: from eggs.gnu.org ([2001:4830:134:3::10]:49072) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1gMoKN-0003xA-Vb for qemu-devel@nongnu.org; Wed, 14 Nov 2018 01:07:05 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1gMoKL-0007cg-L7 for qemu-devel@nongnu.org; Wed, 14 Nov 2018 01:07:03 -0500 Received: from mga07.intel.com ([134.134.136.100]:25615) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1gMoKL-0007bU-Cp for qemu-devel@nongnu.org; Wed, 14 Nov 2018 01:07:01 -0500 Received: from fmsmga005.fm.intel.com ([10.253.24.32]) by orsmga105.jf.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 13 Nov 2018 22:07:00 -0800 Received: from zhangyu-optiplex-9020.bj.intel.com ([10.238.135.159]) by fmsmga005.fm.intel.com with ESMTP; 13 Nov 2018 22:06:58 -0800 X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.56,231,1539673200"; d="scan'208";a="279668574" From: Yu Zhang To: qemu-devel@nongnu.org Date: Wed, 14 Nov 2018 14:04:43 +0800 Message-Id: <1542175484-2742-3-git-send-email-yu.c.zhang@linux.intel.com> X-Mailer: git-send-email 1.9.1 In-Reply-To: <1542175484-2742-1-git-send-email-yu.c.zhang@linux.intel.com> References: <1542175484-2742-1-git-send-email-yu.c.zhang@linux.intel.com> X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 134.134.136.100 Subject: [Qemu-devel] [PATCH v2 2/3] intel-iommu: extend VTD emulation to allow 57-bit IOVA address width. X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: Eduardo Habkost , "Michael S. Tsirkin" , Peter Xu , Paolo Bonzini , Richard Henderson Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" A 5-level paging capable VM may choose to use 57-bit IOVA address width. E.g. guest applications may prefer to use its VA as IOVA when performing VFIO map/unmap operations, to avoid the burden of managing the IOVA space. This patch extends the current vIOMMU logic to cover the extended address width. When creating a VM with 5-level paging feature, one can choose to create a virtual VTD with 5-level paging capability, with configurations like "-device intel-iommu,x-aw-bits=3D57". Signed-off-by: Yu Zhang Reviewed-by: Peter Xu --- Cc: "Michael S. Tsirkin" Cc: Marcel Apfelbaum Cc: Paolo Bonzini Cc: Richard Henderson Cc: Eduardo Habkost Cc: Peter Xu --- hw/i386/intel_iommu.c | 53 ++++++++++++++++++++++++++++++++------= ---- hw/i386/intel_iommu_internal.h | 6 +++++ include/hw/i386/intel_iommu.h | 1 + 3 files changed, 48 insertions(+), 12 deletions(-) diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c index 0e88c63..871110c 100644 --- a/hw/i386/intel_iommu.c +++ b/hw/i386/intel_iommu.c @@ -664,16 +664,16 @@ static inline bool vtd_iova_range_check(uint64_t iova= , VTDContextEntry *ce, =20 /* * Rsvd field masks for spte: - * Index [1] to [4] 4k pages - * Index [5] to [8] large pages + * Index [1] to [5] 4k pages + * Index [6] to [10] large pages */ -static uint64_t vtd_paging_entry_rsvd_field[9]; +static uint64_t vtd_paging_entry_rsvd_field[11]; =20 static bool vtd_slpte_nonzero_rsvd(uint64_t slpte, uint32_t level) { if (slpte & VTD_SL_PT_PAGE_SIZE_MASK) { /* Maybe large page */ - return slpte & vtd_paging_entry_rsvd_field[level + 4]; + return slpte & vtd_paging_entry_rsvd_field[level + 5]; } else { return slpte & vtd_paging_entry_rsvd_field[level]; } @@ -3127,6 +3127,8 @@ static void vtd_init(IntelIOMMUState *s) VTD_CAP_SAGAW_39bit | VTD_CAP_MGAW(s->aw_bits); if (s->aw_bits =3D=3D VTD_AW_48BIT) { s->cap |=3D VTD_CAP_SAGAW_48bit; + } else if (s->aw_bits =3D=3D VTD_AW_57BIT) { + s->cap |=3D VTD_CAP_SAGAW_57bit | VTD_CAP_SAGAW_48bit; } s->ecap =3D VTD_ECAP_QI | VTD_ECAP_IRO; s->haw_bits =3D cpu->phys_bits; @@ -3139,10 +3141,12 @@ static void vtd_init(IntelIOMMUState *s) vtd_paging_entry_rsvd_field[2] =3D VTD_SPTE_PAGE_L2_RSVD_MASK(s->haw_b= its); vtd_paging_entry_rsvd_field[3] =3D VTD_SPTE_PAGE_L3_RSVD_MASK(s->haw_b= its); vtd_paging_entry_rsvd_field[4] =3D VTD_SPTE_PAGE_L4_RSVD_MASK(s->haw_b= its); - vtd_paging_entry_rsvd_field[5] =3D VTD_SPTE_LPAGE_L1_RSVD_MASK(s->haw_= bits); - vtd_paging_entry_rsvd_field[6] =3D VTD_SPTE_LPAGE_L2_RSVD_MASK(s->haw_= bits); - vtd_paging_entry_rsvd_field[7] =3D VTD_SPTE_LPAGE_L3_RSVD_MASK(s->haw_= bits); - vtd_paging_entry_rsvd_field[8] =3D VTD_SPTE_LPAGE_L4_RSVD_MASK(s->haw_= bits); + vtd_paging_entry_rsvd_field[5] =3D VTD_SPTE_PAGE_L5_RSVD_MASK(s->haw_b= its); + vtd_paging_entry_rsvd_field[6] =3D VTD_SPTE_LPAGE_L1_RSVD_MASK(s->haw_= bits); + vtd_paging_entry_rsvd_field[7] =3D VTD_SPTE_LPAGE_L2_RSVD_MASK(s->haw_= bits); + vtd_paging_entry_rsvd_field[8] =3D VTD_SPTE_LPAGE_L3_RSVD_MASK(s->haw_= bits); + vtd_paging_entry_rsvd_field[9] =3D VTD_SPTE_LPAGE_L4_RSVD_MASK(s->haw_= bits); + vtd_paging_entry_rsvd_field[10] =3D VTD_SPTE_LPAGE_L5_RSVD_MASK(s->haw= _bits); =20 if (x86_iommu->intr_supported) { s->ecap |=3D VTD_ECAP_IR | VTD_ECAP_MHMV; @@ -3241,6 +3245,23 @@ static AddressSpace *vtd_host_dma_iommu(PCIBus *bus,= void *opaque, int devfn) return &vtd_as->as; } =20 +static bool host_has_la57(void) +{ + uint32_t ecx, unused; + + host_cpuid(7, 0, &unused, &unused, &ecx, &unused); + return ecx & CPUID_7_0_ECX_LA57; +} + +static bool guest_has_la57(void) +{ + CPUState *cs =3D first_cpu; + X86CPU *cpu =3D X86_CPU(cs); + CPUX86State *env =3D &cpu->env; + + return env->features[FEAT_7_0_ECX] & CPUID_7_0_ECX_LA57; +} + static bool vtd_decide_config(IntelIOMMUState *s, Error **errp) { X86IOMMUState *x86_iommu =3D X86_IOMMU_DEVICE(s); @@ -3267,11 +3288,19 @@ static bool vtd_decide_config(IntelIOMMUState *s, E= rror **errp) } } =20 - /* Currently only address widths supported are 39 and 48 bits */ + /* Currently address widths supported are 39, 48, and 57 bits */ if ((s->aw_bits !=3D VTD_AW_39BIT) && - (s->aw_bits !=3D VTD_AW_48BIT)) { - error_setg(errp, "Supported values for x-aw-bits are: %d, %d", - VTD_AW_39BIT, VTD_AW_48BIT); + (s->aw_bits !=3D VTD_AW_48BIT) && + (s->aw_bits !=3D VTD_AW_57BIT)) { + error_setg(errp, "Supported values for x-aw-bits are: %d, %d, %d", + VTD_AW_39BIT, VTD_AW_48BIT, VTD_AW_57BIT); + return false; + } + + if ((s->aw_bits =3D=3D VTD_AW_57BIT) && + !(host_has_la57() && guest_has_la57())) { + error_setg(errp, "Do not support 57-bit DMA address, unless both " + "host and guest are capable of 5-level paging"); return false; } =20 diff --git a/hw/i386/intel_iommu_internal.h b/hw/i386/intel_iommu_internal.h index d084099..a7ef24b 100644 --- a/hw/i386/intel_iommu_internal.h +++ b/hw/i386/intel_iommu_internal.h @@ -212,6 +212,8 @@ #define VTD_CAP_SAGAW_39bit (0x2ULL << VTD_CAP_SAGAW_SHIFT) /* 48-bit AGAW, 4-level page-table */ #define VTD_CAP_SAGAW_48bit (0x4ULL << VTD_CAP_SAGAW_SHIFT) + /* 57-bit AGAW, 5-level page-table */ +#define VTD_CAP_SAGAW_57bit (0x8ULL << VTD_CAP_SAGAW_SHIFT) =20 /* IQT_REG */ #define VTD_IQT_QT(val) (((val) >> 4) & 0x7fffULL) @@ -379,6 +381,8 @@ typedef union VTDInvDesc VTDInvDesc; (0x800ULL | ~(VTD_HAW_MASK(aw) | VTD_SL_IGN_COM)) #define VTD_SPTE_PAGE_L4_RSVD_MASK(aw) \ (0x880ULL | ~(VTD_HAW_MASK(aw) | VTD_SL_IGN_COM)) +#define VTD_SPTE_PAGE_L5_RSVD_MASK(aw) \ + (0x880ULL | ~(VTD_HAW_MASK(aw) | VTD_SL_IGN_COM)) #define VTD_SPTE_LPAGE_L1_RSVD_MASK(aw) \ (0x800ULL | ~(VTD_HAW_MASK(aw) | VTD_SL_IGN_COM)) #define VTD_SPTE_LPAGE_L2_RSVD_MASK(aw) \ @@ -387,6 +391,8 @@ typedef union VTDInvDesc VTDInvDesc; (0x3ffff800ULL | ~(VTD_HAW_MASK(aw) | VTD_SL_IGN_COM)) #define VTD_SPTE_LPAGE_L4_RSVD_MASK(aw) \ (0x880ULL | ~(VTD_HAW_MASK(aw) | VTD_SL_IGN_COM)) +#define VTD_SPTE_LPAGE_L5_RSVD_MASK(aw) \ + (0x880ULL | ~(VTD_HAW_MASK(aw) | VTD_SL_IGN_COM)) =20 /* Information about page-selective IOTLB invalidate */ struct VTDIOTLBPageInvInfo { diff --git a/include/hw/i386/intel_iommu.h b/include/hw/i386/intel_iommu.h index 820451c..7474c4f 100644 --- a/include/hw/i386/intel_iommu.h +++ b/include/hw/i386/intel_iommu.h @@ -49,6 +49,7 @@ #define DMAR_REG_SIZE 0x230 #define VTD_AW_39BIT 39 #define VTD_AW_48BIT 48 +#define VTD_AW_57BIT 57 #define VTD_ADDRESS_WIDTH VTD_AW_39BIT #define VTD_HAW_MASK(aw) ((1ULL << (aw)) - 1) =20 --=20 1.9.1