From patchwork Tue Dec 13 07:25:03 2016 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Xu X-Patchwork-Id: 9471863 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork.web.codeaurora.org (Postfix) with ESMTP id 69554607EE for ; Tue, 13 Dec 2016 07:28:45 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 5AE51284F3 for ; Tue, 13 Dec 2016 07:28:45 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 4DC5728515; Tue, 13 Dec 2016 07:28:45 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-6.9 required=2.0 tests=BAYES_00,RCVD_IN_DNSWL_HI autolearn=ham version=3.3.1 Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) (using TLSv1 with cipher AES256-SHA (256/256 bits)) (No client certificate requested) by mail.wl.linuxfoundation.org (Postfix) with ESMTPS id 9B58E284F3 for ; Tue, 13 Dec 2016 07:28:44 +0000 (UTC) Received: from localhost ([::1]:35869 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1cGhVz-0005Xc-31 for patchwork-qemu-devel@patchwork.kernel.org; Tue, 13 Dec 2016 02:28:43 -0500 Received: from eggs.gnu.org ([2001:4830:134:3::10]:41200) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1cGhSh-0003F1-0s for qemu-devel@nongnu.org; Tue, 13 Dec 2016 02:25:20 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1cGhSf-0005wl-I3 for qemu-devel@nongnu.org; Tue, 13 Dec 2016 02:25:19 -0500 Received: from mx1.redhat.com ([209.132.183.28]:41594) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1cGhSf-0005wZ-9d for qemu-devel@nongnu.org; Tue, 13 Dec 2016 02:25:17 -0500 Received: from int-mx09.intmail.prod.int.phx2.redhat.com (int-mx09.intmail.prod.int.phx2.redhat.com [10.5.11.22]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mx1.redhat.com (Postfix) with ESMTPS id 7940812B6; Tue, 13 Dec 2016 07:25:16 +0000 (UTC) Received: from pxdev.xzpeter.org.com (dhcp-14-171.nay.redhat.com [10.66.14.171]) by int-mx09.intmail.prod.int.phx2.redhat.com (8.14.4/8.14.4) with ESMTP id uBD7P6Zx022859; Tue, 13 Dec 2016 02:25:13 -0500 From: Peter Xu To: qemu-devel@nongnu.org Date: Tue, 13 Dec 2016 15:25:03 +0800 Message-Id: <1481613903-17467-3-git-send-email-peterx@redhat.com> In-Reply-To: <1481613903-17467-1-git-send-email-peterx@redhat.com> References: <1481613903-17467-1-git-send-email-peterx@redhat.com> X-Scanned-By: MIMEDefang 2.68 on 10.5.11.22 X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.29]); Tue, 13 Dec 2016 07:25:16 +0000 (UTC) X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.2.x-3.x [generic] [fuzzy] X-Received-From: 209.132.183.28 Subject: [Qemu-devel] [PATCH for-2.9 v2 2/2] intel_iommu: provide "aw-bits" parameter 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: kevin.tian@intel.com, famz@redhat.com, mst@redhat.com, jasowang@redhat.com, peterx@redhat.com, alex.williamson@redhat.com Errors-To: qemu-devel-bounces+patchwork-qemu-devel=patchwork.kernel.org@nongnu.org Sender: "Qemu-devel" X-Virus-Scanned: ClamAV using ClamSMTP Previously vt-d codes only supports 39 bits iova address width. This patch provide a new parameter for Intel IOMMU to extend its address width to 48 bits. After enabling larger address width (48), we should be able to map larger iova addresses in the guest. To check whether 48 bits aw is enabled, we can grep in the guest dmesg with line: "dmar: Host address width 48". To keep compatibility with old QEMU and most hosts, default aw bits are set to 39 bits. Signed-off-by: Peter Xu --- hw/i386/acpi-build.c | 8 +++++++- hw/i386/intel_iommu.c | 21 ++++++++++++++++----- hw/i386/intel_iommu_internal.h | 11 ++++------- include/hw/i386/intel_iommu.h | 1 + 4 files changed, 28 insertions(+), 13 deletions(-) diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c index 9708cdc..9dd06fd 100644 --- a/hw/i386/acpi-build.c +++ b/hw/i386/acpi-build.c @@ -2576,6 +2576,7 @@ build_dmar_q35(GArray *table_data, BIOSLinker *linker) AcpiTableDmar *dmar; AcpiDmarHardwareUnit *drhd; uint8_t dmar_flags = 0; + uint8_t aw_bits = VTD_HOST_ADDRESS_WIDTH; X86IOMMUState *iommu = x86_iommu_get_default(); AcpiDmarDeviceScope *scope = NULL; /* Root complex IOAPIC use one path[0] only */ @@ -2586,8 +2587,13 @@ build_dmar_q35(GArray *table_data, BIOSLinker *linker) dmar_flags |= 0x1; /* Flags: 0x1: INT_REMAP */ } + if (iommu->type == TYPE_INTEL) { + IntelIOMMUState *intel_iommu = INTEL_IOMMU_DEVICE(iommu); + aw_bits = intel_iommu->aw_bits; + } + dmar = acpi_data_push(table_data, sizeof(*dmar)); - dmar->host_address_width = VTD_HOST_ADDRESS_WIDTH - 1; + dmar->host_address_width = aw_bits - 1; dmar->flags = dmar_flags; /* DMAR Remapping Hardware Unit Definition structure */ diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c index 517a2a3..5d4b7f8 100644 --- a/hw/i386/intel_iommu.c +++ b/hw/i386/intel_iommu.c @@ -643,7 +643,7 @@ static bool vtd_slpte_nonzero_rsvd(uint64_t slpte, uint32_t level) */ static int vtd_gpa_to_slpte(VTDContextEntry *ce, uint64_t gpa, bool is_write, uint64_t *slptep, uint32_t *slpte_level, - bool *reads, bool *writes) + bool *reads, bool *writes, uint8_t aw_bits) { dma_addr_t addr = vtd_get_slpt_base_from_context(ce); uint32_t level = vtd_get_level_from_context_entry(ce); @@ -660,7 +660,7 @@ static int vtd_gpa_to_slpte(VTDContextEntry *ce, uint64_t gpa, bool is_write, /* Check if @gpa is above 2^X-1, where X is the minimum of MGAW in CAP_REG * and AW in context-entry. */ - if (gpa & ~((1ULL << MIN(ce_agaw, VTD_MGAW)) - 1)) { + if (gpa & ~((1ULL << MIN(ce_agaw, aw_bits)) - 1)) { VTD_DPRINTF(GENERAL, "error: gpa 0x%"PRIx64 " exceeds limits", gpa); return -VTD_FR_ADDR_BEYOND_MGAW; } @@ -892,7 +892,7 @@ static void vtd_do_iommu_translate(VTDAddressSpace *vtd_as, PCIBus *bus, } ret_fr = vtd_gpa_to_slpte(&ce, addr, is_write, &slpte, &level, - &reads, &writes); + &reads, &writes, s->aw_bits); if (ret_fr) { ret_fr = -ret_fr; if (is_fpd_set && vtd_is_qualified_fault(ret_fr)) { @@ -2033,6 +2033,7 @@ static Property vtd_properties[] = { DEFINE_PROP_ON_OFF_AUTO("eim", IntelIOMMUState, intr_eim, ON_OFF_AUTO_AUTO), DEFINE_PROP_BOOL("x-buggy-eim", IntelIOMMUState, buggy_eim, false), + DEFINE_PROP_UINT32("aw-bits", IntelIOMMUState, aw_bits, 39), DEFINE_PROP_END_OF_LIST(), }; @@ -2395,8 +2396,12 @@ static void vtd_init(IntelIOMMUState *s) s->qi_enabled = false; s->iq_last_desc_type = VTD_INV_DESC_NONE; s->next_frcd_reg = 0; - s->cap = VTD_CAP_FRO | VTD_CAP_NFR | VTD_CAP_ND | VTD_CAP_MGAW | - VTD_CAP_SAGAW | VTD_CAP_MAMV | VTD_CAP_PSI | VTD_CAP_SLLPS; + s->cap = VTD_CAP_FRO | VTD_CAP_NFR | VTD_CAP_ND | + VTD_CAP_MAMV | VTD_CAP_PSI | VTD_CAP_SLLPS | + VTD_CAP_SAGAW_39bit | VTD_CAP_MGAW(s->aw_bits); + if (s->aw_bits == 48) { + s->cap |= VTD_CAP_SAGAW_48bit; + } s->ecap = VTD_ECAP_QI | VTD_ECAP_IRO; if (x86_iommu->intr_supported) { @@ -2518,6 +2523,12 @@ static bool vtd_decide_config(IntelIOMMUState *s, Error **errp) } } + if (s->aw_bits != 39 && s->aw_bits != 48) { + error_setg(errp, "Illegal aw-bits %d (allowed values: 39, 48)", + s->aw_bits); + return false; + } + return true; } diff --git a/hw/i386/intel_iommu_internal.h b/hw/i386/intel_iommu_internal.h index e808c67..035268d 100644 --- a/hw/i386/intel_iommu_internal.h +++ b/hw/i386/intel_iommu_internal.h @@ -131,7 +131,7 @@ #define VTD_TLB_DID(val) (((val) >> 32) & VTD_DOMAIN_ID_MASK) /* IVA_REG */ -#define VTD_IVA_ADDR(val) ((val) & ~0xfffULL & ((1ULL << VTD_MGAW) - 1)) +#define VTD_IVA_ADDR(val) ((val) & ~0xfffULL) #define VTD_IVA_AM(val) ((val) & 0x3fULL) /* GCMD_REG */ @@ -195,8 +195,7 @@ #define VTD_DOMAIN_ID_SHIFT 16 /* 16-bit domain id for 64K domains */ #define VTD_DOMAIN_ID_MASK ((1UL << VTD_DOMAIN_ID_SHIFT) - 1) #define VTD_CAP_ND (((VTD_DOMAIN_ID_SHIFT - 4) / 2) & 7ULL) -#define VTD_MGAW 39 /* Maximum Guest Address Width */ -#define VTD_CAP_MGAW (((VTD_MGAW - 1) & 0x3fULL) << 16) +#define VTD_CAP_MGAW(bits) ((((bits) - 1) & 0x3fULL) << 16) #define VTD_MAMV 18ULL #define VTD_CAP_MAMV (VTD_MAMV << 48) #define VTD_CAP_PSI (1ULL << 39) @@ -209,7 +208,6 @@ #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) -#define VTD_CAP_SAGAW VTD_CAP_SAGAW_39bit /* IQT_REG */ #define VTD_IQT_QT(val) (((val) >> 4) & 0x7fffULL) @@ -248,7 +246,7 @@ #define VTD_FRCD_SID_MASK 0xffffULL #define VTD_FRCD_SID(val) ((val) & VTD_FRCD_SID_MASK) /* For the low 64-bit of 128-bit */ -#define VTD_FRCD_FI(val) ((val) & (((1ULL << VTD_MGAW) - 1) ^ 0xfffULL)) +#define VTD_FRCD_FI(val) ((val) & ~0xfffULL) /* DMA Remapping Fault Conditions */ typedef enum VTDFaultReason { @@ -355,8 +353,7 @@ typedef union VTDInvDesc VTDInvDesc; #define VTD_INV_DESC_IOTLB_DOMAIN (2ULL << 4) #define VTD_INV_DESC_IOTLB_PAGE (3ULL << 4) #define VTD_INV_DESC_IOTLB_DID(val) (((val) >> 16) & VTD_DOMAIN_ID_MASK) -#define VTD_INV_DESC_IOTLB_ADDR(val) ((val) & ~0xfffULL & \ - ((1ULL << VTD_MGAW) - 1)) +#define VTD_INV_DESC_IOTLB_ADDR(val) ((val) & ~0xfffULL) #define VTD_INV_DESC_IOTLB_AM(val) ((val) & 0x3fULL) #define VTD_INV_DESC_IOTLB_RSVD_LO 0xffffffff0000ff00ULL #define VTD_INV_DESC_IOTLB_RSVD_HI 0xf80ULL diff --git a/include/hw/i386/intel_iommu.h b/include/hw/i386/intel_iommu.h index 405c9d1..b0bb53a 100644 --- a/include/hw/i386/intel_iommu.h +++ b/include/hw/i386/intel_iommu.h @@ -290,6 +290,7 @@ struct IntelIOMMUState { bool intr_eime; /* Extended interrupt mode enabled */ OnOffAuto intr_eim; /* Toggle for EIM cabability */ bool buggy_eim; /* Force buggy EIM unless eim=off */ + uint32_t aw_bits; /* IOVA address width (in bits) */ }; /* Find the VTD Address space associated with the given bus pointer,