Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Received-SPF: Pass (protection.outlook.com: domain of amd.com designates
 165.204.84.17 as permitted sender) receiver=protection.outlook.com;
 client-ip=165.204.84.17; helo=SATLEXMB04.amd.com; pr=C
From:   Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
To:     <linux-kernel@vger.kernel.org>, <iommu@lists.linux.dev>,
        <kvm@vger.kernel.org>
CC:     <joro@8bytes.org>, <robin.murphy@arm.com>, <yi.l.liu@intel.com>,
        <alex.williamson@redhat.com>, <jgg@nvidia.com>,
        <nicolinc@nvidia.com>, <baolu.lu@linux.intel.com>,
        <eric.auger@redhat.com>, <pandoh@google.com>,
        <kumaranand@google.com>, <jon.grimm@amd.com>,
        <santosh.shukla@amd.com>, <vasant.hegde@amd.com>,
        <jay.chen@amd.com>, <joseph.chung@amd.com>,
        "Suravee Suthikulpanit" <suravee.suthikulpanit@amd.com>
Subject: [RFC PATCH 16/21] iommu/amd: Introduce vIOMMU ioctl for updating device mapping table
Date:   Wed, 21 Jun 2023 18:55:03 -0500
Message-ID: <20230621235508.113949-17-suravee.suthikulpanit@amd.com>
In-Reply-To: <20230621235508.113949-1-suravee.suthikulpanit@amd.com>
References: <20230621235508.113949-1-suravee.suthikulpanit@amd.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 21 Jun 2023 23:55:58.6717
 (UTC)
X-MS-Exchange-CrossTenant-Network-Message-Id: def41212-f7b6-4b3a-ecbe-08db72b30f7f
X-MS-Exchange-CrossTenant-Id: 3dd8961f-e488-4e60-8e11-a82d994e183d
X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp: TenantId=3dd8961f-e488-4e60-8e11-a82d994e183d;Ip=[165.204.84.17];Helo=[SATLEXMB04.amd.com]
X-MS-Exchange-CrossTenant-AuthSource: CY4PEPF0000E9D1.namprd03.prod.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Anonymous
X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem
X-MS-Exchange-Transport-CrossTenantHeadersStamped: BL1PR12MB5127
X-Spam-Status: No, score=-1.1 required=5.0 tests=BAYES_00,DKIM_SIGNED,
        DKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF,FORGED_SPF_HELO,
        RCVD_IN_DNSWL_NONE,RCVD_IN_MSPIKE_H2,SPF_HELO_PASS,SPF_NONE,
        T_SCC_BODY_TEXT_LINE,URIBL_BLOCKED autolearn=no autolearn_force=no
        version=3.4.6
X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on
        lindbergh.monkeyblade.net
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

These ioctl interfaces are used for updating device host-to-guest
device ID mappings.

Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
---
 drivers/iommu/amd/viommu.c | 130 +++++++++++++++++++++++++++++++++++++
 1 file changed, 130 insertions(+)

diff --git a/drivers/iommu/amd/viommu.c b/drivers/iommu/amd/viommu.c
index 2bafa5102ffa..f6f0056c7fe6 100644
--- a/drivers/iommu/amd/viommu.c
+++ b/drivers/iommu/amd/viommu.c
@@ -519,3 +519,133 @@ int amd_viommu_iommu_destroy(struct amd_viommu_iommu_info *data)
 
 }
 EXPORT_SYMBOL(amd_viommu_iommu_destroy);
+
+static void set_dte_viommu(struct amd_iommu *iommu, u16 hDevId, u16 gid, u16 gDevId)
+{
+	u64 tmp, dte;
+	struct dev_table_entry *dev_table = get_dev_table(iommu);
+
+	// vImuEn
+	dte = dev_table[hDevId].data[3];
+	dte |= (1ULL << DTE_VIOMMU_EN_SHIFT);
+
+	// GDeviceID
+	tmp = gDevId & DTE_VIOMMU_GUESTID_MASK;
+	dte |= (tmp << DTE_VIOMMU_GUESTID_SHIFT);
+
+	// GuestID
+	tmp = gid & DTE_VIOMMU_GUESTID_MASK;
+	dte |= (tmp << DTE_VIOMMU_GDEVICEID_SHIFT);
+
+	dev_table[hDevId].data[3] = dte;
+
+	dte = dev_table[hDevId].data[0];
+	dte |= DTE_FLAG_GV;
+	dev_table[hDevId].data[0] = dte;
+
+	iommu_flush_dte(iommu, hDevId);
+}
+
+void dump_device_mapping(struct amd_iommu *iommu, u16 guestId, u16 gdev_id)
+{
+	void *addr;
+	u64 offset, val;
+	struct amd_iommu_vminfo *vminfo;
+
+	vminfo = get_vminfo(iommu, guestId);
+	if (!vminfo)
+		return;
+
+	addr = vminfo->devid_table;
+	offset = gdev_id << 4;
+	val = *((u64 *)(addr + offset));
+
+	pr_debug("%s: guestId=%#x, gdev_id=%#x, base=%#llx, offset=%#llx(val=%#llx)\n", __func__,
+		 guestId, gdev_id, (unsigned long long)iommu_virt_to_phys(vminfo->devid_table),
+		 (unsigned long long)offset, (unsigned long long)val);
+}
+
+/*
+ * Program the DevID via VFCTRL registers
+ * This function will be called during VM init via VFIO.
+ */
+static void set_device_mapping(struct amd_iommu *iommu, u16 hDevId,
+			       u16 guestId, u16 queueId, u16 gDevId)
+{
+	u64 val, tmp1, tmp2;
+	u8 __iomem *vfctrl;
+
+	pr_debug("%s: iommu_id=%#x, gid=%#x, hDevId=%#x, gDevId=%#x\n",
+		__func__, pci_dev_id(iommu->dev), guestId, hDevId, gDevId);
+
+	set_dte_viommu(iommu, hDevId, guestId, gDevId);
+
+	tmp1 = gDevId;
+	tmp1 = ((tmp1 & 0xFFFFULL) << 46);
+	tmp2 = hDevId;
+	tmp2 = ((tmp2 & 0xFFFFULL) << 14);
+	val = tmp1 | tmp2 | 0x8000000000000001ULL;
+	vfctrl = VIOMMU_VFCTRL_MMIO_BASE(iommu, guestId);
+	writeq(val, vfctrl + VIOMMU_VFCTRL_GUEST_DID_MAP_CONTROL0_OFFSET);
+	wbinvd_on_all_cpus();
+
+	tmp1 = hDevId;
+	val = ((tmp1 & 0xFFFFULL) << 16);
+	writeq(val, vfctrl + VIOMMU_VFCTRL_GUEST_MISC_CONTROL_OFFSET);
+}
+
+static void clear_dte_viommu(struct amd_iommu *iommu, u16 hDevId)
+{
+	struct dev_table_entry *dev_table = get_dev_table(iommu);
+	u64 dte = dev_table[hDevId].data[3];
+
+	dte &= ~(1ULL << DTE_VIOMMU_EN_SHIFT);
+	dte &= ~(0xFFFFULL << DTE_VIOMMU_GUESTID_SHIFT);
+	dte &= ~(0xFFFFULL << DTE_VIOMMU_GDEVICEID_SHIFT);
+
+	dev_table[hDevId].data[3] = dte;
+
+	dte = dev_table[hDevId].data[0];
+	dte &= ~DTE_FLAG_GV;
+	dev_table[hDevId].data[0] = dte;
+
+	iommu_flush_dte(iommu, hDevId);
+}
+
+int amd_viommu_device_update(struct amd_viommu_dev_info *data, bool is_set)
+{
+	struct pci_dev *pdev;
+	struct iommu_domain *dom;
+	int gid = data->gid;
+	struct amd_iommu *iommu = get_amd_iommu_from_devid(data->iommu_id);
+
+	if (!iommu)
+		return -ENODEV;
+
+	clear_dte_viommu(iommu, data->hdev_id);
+
+	if (is_set) {
+		set_device_mapping(iommu, data->hdev_id, gid,
+				   data->queue_id, data->gdev_id);
+
+		pdev = pci_get_domain_bus_and_slot(0, PCI_BUS_NUM(data->hdev_id),
+						   data->hdev_id & 0xff);
+		dom = iommu_get_domain_for_dev(&pdev->dev);
+		if (!dom) {
+			pr_err("%s: Domain not found (devid=%#x)\n",
+			       __func__, pci_dev_id(pdev));
+			return -EINVAL;
+		}
+
+		/* TODO: Only support pasid 0 for now */
+		amd_iommu_flush_tlb(dom, 0);
+		dump_device_mapping(iommu, gid, data->gdev_id);
+
+	} else {
+		clear_device_mapping(iommu, data->hdev_id, gid,
+				     data->queue_id, data->gdev_id);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(amd_viommu_device_update);
-- 
2.34.1