Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:7 as permitted sender) client-ip=2620:137:e000::3:7;
From:   Lu Baolu <baolu.lu@linux.intel.com>
To:     Joerg Roedel <joro@8bytes.org>, Will Deacon <will@kernel.org>,
        Robin Murphy <robin.murphy@arm.com>,
        Jason Gunthorpe <jgg@ziepe.ca>,
        Kevin Tian <kevin.tian@intel.com>
Cc:     iommu@lists.linux.dev, linux-kernel@vger.kernel.org,
        Lu Baolu <baolu.lu@linux.intel.com>
Subject: [PATCH 4/5] iommu/vt-d: Add support for static identity domain
Date:   Mon, 20 Nov 2023 19:29:43 +0800
Message-Id: <20231120112944.142741-5-baolu.lu@linux.intel.com>
In-Reply-To: <20231120112944.142741-1-baolu.lu@linux.intel.com>
References: <20231120112944.142741-1-baolu.lu@linux.intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Add a global static identity domain with guaranteed attach semantics.

Software determines VT-d hardware support for pass-through translation by
inspecting the capability register. If pass-through translation is not
supported, the device is instructed to use DMA domain for its default
domain. While most recent VT-d hardware implementations support pass-
through translation, this capability is only lacking in some early VT-d
implementations.

With the static identity domain in place, the domain field of per-device
iommu driver data can be either a pointer to a DMA translation domain, or
NULL, indicating that the static identity domain is attached. Refine some
code to accommodate this change.

Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
---
 drivers/iommu/intel/iommu.c | 129 ++++++++++++++++++++++++++++++++++--
 drivers/iommu/intel/svm.c   |   2 +-
 2 files changed, 125 insertions(+), 6 deletions(-)

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 86339dc30243..ad2e53821a05 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -1282,7 +1282,8 @@ static void iommu_enable_pci_caps(struct device_domain_info *info)
 	if (info->ats_supported && pci_ats_page_aligned(pdev) &&
 	    !pci_enable_ats(pdev, VTD_PAGE_SHIFT)) {
 		info->ats_enabled = 1;
-		domain_update_iotlb(info->domain);
+		if (info->domain)
+			domain_update_iotlb(info->domain);
 	}
 }
 
@@ -1298,7 +1299,8 @@ static void iommu_disable_pci_caps(struct device_domain_info *info)
 	if (info->ats_enabled) {
 		pci_disable_ats(pdev);
 		info->ats_enabled = 0;
-		domain_update_iotlb(info->domain);
+		if (info->domain)
+			domain_update_iotlb(info->domain);
 	}
 
 	if (info->pasid_enabled) {
@@ -2301,6 +2303,9 @@ static bool device_rmrr_is_relaxable(struct device *dev)
  */
 static int device_def_domain_type(struct device *dev)
 {
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct intel_iommu *iommu = info->iommu;
+
 	if (dev_is_pci(dev)) {
 		struct pci_dev *pdev = to_pci_dev(dev);
 
@@ -2311,6 +2316,13 @@ static int device_def_domain_type(struct device *dev)
 			return IOMMU_DOMAIN_IDENTITY;
 	}
 
+	/*
+	 * Hardware does not support the passthrough translation mode.
+	 * Always use a dynamaic mapping domain.
+	 */
+	if (!ecap_pass_through(iommu->ecap))
+		return IOMMU_DOMAIN_DMA;
+
 	return 0;
 }
 
@@ -3712,6 +3724,9 @@ static void dmar_remove_one_dev_info(struct device *dev)
 		domain_context_clear(info);
 	}
 
+	if (!domain)
+		return;
+
 	spin_lock_irqsave(&domain->lock, flags);
 	list_del(&info->link);
 	spin_unlock_irqrestore(&domain->lock, flags);
@@ -3920,11 +3935,9 @@ int prepare_domain_attach_device(struct iommu_domain *domain,
 static int intel_iommu_attach_device(struct iommu_domain *domain,
 				     struct device *dev)
 {
-	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	int ret;
 
-	if (info->domain)
-		device_block_translation(dev);
+	device_block_translation(dev);
 
 	ret = prepare_domain_attach_device(domain, dev);
 	if (ret)
@@ -4529,6 +4542,9 @@ static void intel_iommu_remove_dev_pasid(struct device *dev, ioasid_t pasid)
 		goto out_tear_down;
 	}
 
+	if (domain->type == IOMMU_DOMAIN_IDENTITY)
+		goto out_tear_down;
+
 	dmar_domain = to_dmar_domain(domain);
 	spin_lock_irqsave(&dmar_domain->lock, flags);
 	list_for_each_entry(curr, &dmar_domain->dev_pasids, link_domain) {
@@ -4703,8 +4719,111 @@ const struct iommu_dirty_ops intel_dirty_ops = {
 	.read_and_clear_dirty = intel_iommu_read_and_clear_dirty,
 };
 
+static int context_setup_pass_through(struct device *dev, u8 bus, u8 devfn)
+{
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct intel_iommu *iommu = info->iommu;
+	struct context_entry *context;
+
+	spin_lock(&iommu->lock);
+	context = iommu_context_addr(iommu, bus, devfn, 1);
+	if (!context) {
+		spin_unlock(&iommu->lock);
+		return -ENOMEM;
+	}
+
+	if (context_present(context) && !context_copied(iommu, bus, devfn)) {
+		spin_unlock(&iommu->lock);
+		return 0;
+	}
+
+	copied_context_tear_down(iommu, context, bus, devfn);
+	context_clear_entry(context);
+	context_set_domain_id(context, FLPT_DEFAULT_DID);
+
+	/*
+	 * In pass through mode, AW must be programmed to indicate the largest
+	 * AGAW value supported by hardware. And ASR is ignored by hardware.
+	 */
+	context_set_address_width(context, iommu->msagaw);
+	context_set_translation_type(context, CONTEXT_TT_PASS_THROUGH);
+	context_set_fault_enable(context);
+	context_set_present(context);
+	if (!ecap_coherent(iommu->ecap))
+		clflush_cache_range(context, sizeof(*context));
+	context_present_cache_flush(iommu, FLPT_DEFAULT_DID, bus, devfn);
+	spin_unlock(&iommu->lock);
+
+	return 0;
+}
+
+static int context_setup_pass_through_cb(struct pci_dev *pdev, u16 alias, void *data)
+{
+	struct device *dev = data;
+
+	if (dev != &pdev->dev)
+		return 0;
+
+	return context_setup_pass_through(dev, PCI_BUS_NUM(alias), alias & 0xff);
+}
+
+static int device_setup_pass_through(struct device *dev)
+{
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+
+	if (!dev_is_pci(dev))
+		return context_setup_pass_through(dev, info->bus, info->devfn);
+
+	return pci_for_each_dma_alias(to_pci_dev(dev),
+				      context_setup_pass_through_cb, dev);
+}
+
+static int identity_domain_attach_dev(struct iommu_domain *domain,
+				      struct device *dev)
+{
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct intel_iommu *iommu = info->iommu;
+	int ret;
+
+	device_block_translation(dev);
+
+	if (dev_is_real_dma_subdevice(dev))
+		return 0;
+
+	if (sm_supported(iommu)) {
+		ret = intel_pasid_setup_pass_through(iommu, dev, IOMMU_NO_PASID);
+		if (!ret)
+			iommu_enable_pci_caps(info);
+	} else {
+		ret = device_setup_pass_through(dev);
+	}
+
+	return ret;
+}
+
+static int identity_domain_set_dev_pasid(struct iommu_domain *domain,
+					 struct device *dev, ioasid_t pasid)
+{
+	struct device_domain_info *info = dev_iommu_priv_get(dev);
+	struct intel_iommu *iommu = info->iommu;
+
+	if (!pasid_supported(iommu) || dev_is_real_dma_subdevice(dev))
+		return -EOPNOTSUPP;
+
+	return intel_pasid_setup_pass_through(iommu, dev, pasid);
+}
+
+static struct iommu_domain identity_domain = {
+	.type = IOMMU_DOMAIN_IDENTITY,
+	.ops = &(const struct iommu_domain_ops) {
+		.attach_dev	= identity_domain_attach_dev,
+		.set_dev_pasid	= identity_domain_set_dev_pasid,
+	},
+};
+
 const struct iommu_ops intel_iommu_ops = {
 	.blocked_domain		= &blocking_domain,
+	.identity_domain	= &identity_domain,
 	.capable		= intel_iommu_capable,
 	.hw_info		= intel_iommu_hw_info,
 	.domain_alloc		= intel_iommu_domain_alloc,
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index 64c02e6ab1b3..e744f7439e97 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -493,7 +493,7 @@ void intel_drain_pasid_prq(struct device *dev, u32 pasid)
 	domain = info->domain;
 	pdev = to_pci_dev(dev);
 	sid = PCI_DEVID(info->bus, info->devfn);
-	did = domain_id_iommu(domain, iommu);
+	did = domain ? domain_id_iommu(domain, iommu) : FLPT_DEFAULT_DID;
 	qdep = pci_ats_queue_depth(pdev);
 
 	/*
-- 
2.34.1