iommu/vt-d: Add scalable mode support

142 lines not on this page · raw message

index a58bc05d6798..8c9b6063d275 100644
@@ -177,6 +177,7 @@
  * Extended Capability Register
  */
 
+#define ecap_smts(e)		(((e) >> 43) & 0x1)
 #define ecap_dit(e)		((e >> 41) & 0x1)
 #define ecap_pasid(e)		((e >> 40) & 0x1)
 #define ecap_pss(e)		((e >> 35) & 0x1f)

index c0ffde6cb21a..73d7c15bf737 100644
@@ -425,21 +425,24 @@ static LIST_HEAD(device_domain_list);
 
 /*
  * Iterate over elements in device_domain_list and call the specified
- * callback @fn against each element. This helper should only be used
- * in the context where the device_domain_lock has already been holden.
+ * callback @fn against each element.
  */
 int for_each_device_domain(int (*fn)(struct device_domain_info *info,
 				     void *data), void *data)
 {
 	int ret = 0;
+	unsigned long flags;
 	struct device_domain_info *info;
 
-	assert_spin_locked(&device_domain_lock);
+	spin_lock_irqsave(&device_domain_lock, flags);
 	list_for_each_entry(info, &device_domain_list, global) {
 		ret = fn(info, data);
-		if (ret)
+		if (ret) {
+			spin_unlock_irqrestore(&device_domain_lock, flags);
 			return ret;
+		}
 	}
+	spin_unlock_irqrestore(&device_domain_lock, flags);
 
 	return 0;
 }

@@ -2481,16 +2484,18 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu,
 	list_add(&info->global, &device_domain_list);
 	if (dev)
 		dev->archdata.iommu = info;
+	spin_unlock_irqrestore(&device_domain_lock, flags);
 
-	if (dev && dev_is_pci(dev) && info->pasid_supported) {
+	/* PASID table is mandatory for a PCI device in scalable mode. */
+	if (dev && dev_is_pci(dev) && sm_supported(iommu)) {
 		ret = intel_pasid_alloc_table(dev);
 		if (ret) {
-			pr_warn("No pasid table for %s, pasid disabled\n",
-				dev_name(dev));
-			info->pasid_supported = 0;
+			pr_err("PASID table allocation for %s failed\n",
+			       dev_name(dev));
+			dmar_remove_one_dev_info(domain, dev);
+			return NULL;
 		}
 	}
-	spin_unlock_irqrestore(&device_domain_lock, flags);
 
 	if (dev && domain_context_mapping(domain, dev)) {
 		pr_err("Domain context map for %s failed\n", dev_name(dev));

151 lines not on this page · raw message

index 1fb5e12b029a..12f480c2bb8b 100644
@@ -11,12 +11,20 @@
 #define __INTEL_PASID_H
 
 #define PASID_MIN			0x1
-#define PASID_MAX			0x20000
+#define PASID_MAX			0x100000
+#define PASID_PTE_MASK			0x3F
+#define PASID_PTE_PRESENT		1
+#define PDE_PFN_MASK			PAGE_MASK
+#define PASID_PDE_SHIFT			6
 
-struct pasid_entry {
+struct pasid_dir_entry {
 	u64 val;
 };
 
+struct pasid_entry {
+	u64 val[8];
+};
+
 /* The representative of a PASID table */
 struct pasid_table {
 	void			*table;		/* pasid table pointer */

index 887150907526..9014b07ab975 100644
@@ -65,8 +65,6 @@ int intel_svm_init(struct intel_iommu *iommu)
 
 	order = get_order(sizeof(struct pasid_entry) * iommu->pasid_max);
 	if (ecap_dis(iommu->ecap)) {
-		/* Just making it explicit... */
-		BUILD_BUG_ON(sizeof(struct pasid_entry) != sizeof(struct pasid_state_entry));
 		pages = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
 		if (pages)
 			iommu->pasid_state_table = page_address(pages);

@@ -405,9 +403,7 @@ int intel_svm_bind_mm(struct device *dev, int *pasid, int flags, struct svm_dev_
 			pasid_entry_val |= PASID_ENTRY_FLPM_5LP;
 
 		entry = intel_pasid_get_entry(dev, svm->pasid);
-		entry->val = pasid_entry_val;
-
-		wmb();
+		WRITE_ONCE(entry->val[0], pasid_entry_val);
 
 		/*
 		 * Flush PASID cache when a PASID table entry becomes

index 73d7c15bf737..52cdb0e077f2 100644
@@ -290,49 +290,6 @@ static inline void context_clear_entry(struct context_entry *context)
 	context->hi = 0;
 }
 
-/*
- * 0: readable
- * 1: writable
- * 2-6: reserved
- * 7: super page
- * 8-10: available
- * 11: snoop behavior
- * 12-63: Host physcial address
- */
-struct dma_pte {
-	u64 val;
-};
-
-static inline void dma_clear_pte(struct dma_pte *pte)
-{
-	pte->val = 0;
-}
-
-static inline u64 dma_pte_addr(struct dma_pte *pte)
-{
-#ifdef CONFIG_64BIT
-	return pte->val & VTD_PAGE_MASK;
-#else
-	/* Must have a full atomic 64-bit read */
-	return  __cmpxchg64(&pte->val, 0ULL, 0ULL) & VTD_PAGE_MASK;
-#endif
-}
-
-static inline bool dma_pte_present(struct dma_pte *pte)
-{
-	return (pte->val & 3) != 0;
-}
-
-static inline bool dma_pte_superpage(struct dma_pte *pte)
-{
-	return (pte->val & DMA_PTE_LARGE_PAGE);
-}
-
-static inline int first_pte_in_page(struct dma_pte *pte)
-{
-	return !((unsigned long)pte & ~VTD_PAGE_MASK);
-}
-
 /*
  * This domain is a statically identity mapping domain.
  *	1. This domain creats a static 1:1 mapping to all usable memory.

49 lines not on this page · raw message

index d9c748b6f9e4..9511f9aeb77c 100644
@@ -1160,6 +1160,7 @@ static int qi_check_fault(struct intel_iommu *iommu, int index)
 	int head, tail;
 	struct q_inval *qi = iommu->qi;
 	int wait_index = (index + 1) % QI_LENGTH;
+	int shift = qi_shift(iommu);
 
 	if (qi->desc_status[wait_index] == QI_ABORT)
 		return -EAGAIN;

@@ -1173,13 +1174,19 @@ static int qi_check_fault(struct intel_iommu *iommu, int index)
 	 */
 	if (fault & DMA_FSTS_IQE) {
 		head = readl(iommu->reg + DMAR_IQH_REG);
-		if ((head >> DMAR_IQ_SHIFT) == index) {
-			pr_err("VT-d detected invalid descriptor: "
-				"low=%llx, high=%llx\n",
-				(unsigned long long)qi->desc[index].low,
-				(unsigned long long)qi->desc[index].high);
-			memcpy(&qi->desc[index], &qi->desc[wait_index],
-					sizeof(struct qi_desc));
+		if ((head >> shift) == index) {
+			struct qi_desc *desc = qi->desc + head;
+
+			/*
+			 * desc->qw2 and desc->qw3 are either reserved or
+			 * used by software as private data. We won't print
+			 * out these two qw's for security consideration.
+			 */
+			pr_err("VT-d detected invalid descriptor: qw0 = %llx, qw1 = %llx\n",
+			       (unsigned long long)desc->qw0,
+			       (unsigned long long)desc->qw1);
+			memcpy(desc, qi->desc + (wait_index << shift),
+			       1 << shift);
 			writel(DMA_FSTS_IQE, iommu->reg + DMAR_FSTS_REG);
 			return -EINVAL;
 		}

@@ -1191,10 +1198,10 @@ static int qi_check_fault(struct intel_iommu *iommu, int index)
 	 */
 	if (fault & DMA_FSTS_ITE) {
 		head = readl(iommu->reg + DMAR_IQH_REG);
-		head = ((head >> DMAR_IQ_SHIFT) - 1 + QI_LENGTH) % QI_LENGTH;
+		head = ((head >> shift) - 1 + QI_LENGTH) % QI_LENGTH;
 		head |= 1;
 		tail = readl(iommu->reg + DMAR_IQT_REG);
-		tail = ((tail >> DMAR_IQ_SHIFT) - 1 + QI_LENGTH) % QI_LENGTH;
+		tail = ((tail >> shift) - 1 + QI_LENGTH) % QI_LENGTH;
 
 		writel(DMA_FSTS_ITE, iommu->reg + DMAR_FSTS_REG);
 

@@ -1222,15 +1229,14 @@ int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu)
 {
 	int rc;
 	struct q_inval *qi = iommu->qi;
-	struct qi_desc *hw, wait_desc;
+	int offset, shift, length;
+	struct qi_desc wait_desc;
 	int wait_index, index;
 	unsigned long flags;
 
 	if (!qi)
 		return 0;
 
-	hw = qi->desc;
-
 restart:
 	rc = 0;
 

@@ -1243,16 +1249,21 @@ int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu)
 
 	index = qi->free_head;
 	wait_index = (index + 1) % QI_LENGTH;
+	shift = qi_shift(iommu);
+	length = 1 << shift;
 
 	qi->desc_status[index] = qi->desc_status[wait_index] = QI_IN_USE;
 
-	hw[index] = *desc;
-
-	wait_desc.low = QI_IWD_STATUS_DATA(QI_DONE) |
+	offset = index << shift;
+	memcpy(qi->desc + offset, desc, length);
+	wait_desc.qw0 = QI_IWD_STATUS_DATA(QI_DONE) |
 			QI_IWD_STATUS_WRITE | QI_IWD_TYPE;
-	wait_desc.high = virt_to_phys(&qi->desc_status[wait_index]);
+	wait_desc.qw1 = virt_to_phys(&qi->desc_status[wait_index]);
+	wait_desc.qw2 = 0;
+	wait_desc.qw3 = 0;
 
-	hw[wait_index] = wait_desc;
+	offset = wait_index << shift;
+	memcpy(qi->desc + offset, &wait_desc, length);
 
 	qi->free_head = (qi->free_head + 2) % QI_LENGTH;
 	qi->free_cnt -= 2;

@@ -1261,7 +1272,7 @@ int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu)
 	 * update the HW tail register indicating the presence of
 	 * new descriptors.
 	 */
-	writel(qi->free_head << DMAR_IQ_SHIFT, iommu->reg + DMAR_IQT_REG);
+	writel(qi->free_head << shift, iommu->reg + DMAR_IQT_REG);
 
 	while (qi->desc_status[wait_index] != QI_DONE) {
 		/*

@@ -1298,8 +1309,10 @@ void qi_global_iec(struct intel_iommu *iommu)
 {
 	struct qi_desc desc;
 
-	desc.low = QI_IEC_TYPE;
-	desc.high = 0;
+	desc.qw0 = QI_IEC_TYPE;
+	desc.qw1 = 0;
+	desc.qw2 = 0;
+	desc.qw3 = 0;
 
 	/* should never fail */
 	qi_submit_sync(&desc, iommu);

@@ -1310,9 +1323,11 @@ void qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid, u8 fm,
 {
 	struct qi_desc desc;
 
-	desc.low = QI_CC_FM(fm) | QI_CC_SID(sid) | QI_CC_DID(did)
+	desc.qw0 = QI_CC_FM(fm) | QI_CC_SID(sid) | QI_CC_DID(did)
 			| QI_CC_GRAN(type) | QI_CC_TYPE;
-	desc.high = 0;
+	desc.qw1 = 0;
+	desc.qw2 = 0;
+	desc.qw3 = 0;
 
 	qi_submit_sync(&desc, iommu);
 }

@@ -1331,10 +1346,12 @@ void qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr,
 	if (cap_read_drain(iommu->cap))
 		dr = 1;
 
-	desc.low = QI_IOTLB_DID(did) | QI_IOTLB_DR(dr) | QI_IOTLB_DW(dw)
+	desc.qw0 = QI_IOTLB_DID(did) | QI_IOTLB_DR(dr) | QI_IOTLB_DW(dw)
 		| QI_IOTLB_GRAN(type) | QI_IOTLB_TYPE;
-	desc.high = QI_IOTLB_ADDR(addr) | QI_IOTLB_IH(ih)
+	desc.qw1 = QI_IOTLB_ADDR(addr) | QI_IOTLB_IH(ih)
 		| QI_IOTLB_AM(size_order);
+	desc.qw2 = 0;
+	desc.qw3 = 0;
 
 	qi_submit_sync(&desc, iommu);
 }

@@ -1347,15 +1364,17 @@ void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 pfsid,
 	if (mask) {
 		WARN_ON_ONCE(addr & ((1ULL << (VTD_PAGE_SHIFT + mask)) - 1));
 		addr |= (1ULL << (VTD_PAGE_SHIFT + mask - 1)) - 1;
-		desc.high = QI_DEV_IOTLB_ADDR(addr) | QI_DEV_IOTLB_SIZE;
+		desc.qw1 = QI_DEV_IOTLB_ADDR(addr) | QI_DEV_IOTLB_SIZE;
 	} else
-		desc.high = QI_DEV_IOTLB_ADDR(addr);
+		desc.qw1 = QI_DEV_IOTLB_ADDR(addr);
 
 	if (qdep >= QI_DEV_IOTLB_MAX_INVS)
 		qdep = 0;
 
-	desc.low = QI_DEV_IOTLB_SID(sid) | QI_DEV_IOTLB_QDEP(qdep) |
+	desc.qw0 = QI_DEV_IOTLB_SID(sid) | QI_DEV_IOTLB_QDEP(qdep) |
 		   QI_DIOTLB_TYPE | QI_DEV_IOTLB_PFSID(pfsid);
+	desc.qw2 = 0;
+	desc.qw3 = 0;
 
 	qi_submit_sync(&desc, iommu);
 }

@@ -1403,16 +1422,24 @@ static void __dmar_enable_qi(struct intel_iommu *iommu)
 	u32 sts;
 	unsigned long flags;
 	struct q_inval *qi = iommu->qi;
+	u64 val = virt_to_phys(qi->desc);
 
 	qi->free_head = qi->free_tail = 0;
 	qi->free_cnt = QI_LENGTH;
 
+	/*
+	 * Set DW=1 and QS=1 in IQA_REG when Scalable Mode capability
+	 * is present.
+	 */
+	if (ecap_smts(iommu->ecap))
+		val |= (1 << 11) | 1;
+
 	raw_spin_lock_irqsave(&iommu->register_lock, flags);
 
 	/* write zero to the tail reg */
 	writel(0, iommu->reg + DMAR_IQT_REG);
 
-	dmar_writeq(iommu->reg + DMAR_IQA_REG, virt_to_phys(qi->desc));
+	dmar_writeq(iommu->reg + DMAR_IQA_REG, val);
 
 	iommu->gcmd |= DMA_GCMD_QIE;
 	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);

@@ -1448,8 +1475,12 @@ int dmar_enable_qi(struct intel_iommu *iommu)
 
 	qi = iommu->qi;
 
-
-	desc_page = alloc_pages_node(iommu->node, GFP_ATOMIC | __GFP_ZERO, 0);
+	/*
+	 * Need two pages to accommodate 256 descriptors of 256 bits each
+	 * if the remapping hardware supports scalable mode translation.
+	 */
+	desc_page = alloc_pages_node(iommu->node, GFP_ATOMIC | __GFP_ZERO,
+				     !!ecap_smts(iommu->ecap));
 	if (!desc_page) {
 		kfree(qi);
 		iommu->qi = NULL;

118 lines not on this page · raw message

index c2d6c11431de..24d45b07f425 100644
@@ -145,9 +145,11 @@ static int qi_flush_iec(struct intel_iommu *iommu, int index, int mask)
 {
 	struct qi_desc desc;
 
-	desc.low = QI_IEC_IIDEX(index) | QI_IEC_TYPE | QI_IEC_IM(mask)
+	desc.qw0 = QI_IEC_IIDEX(index) | QI_IEC_TYPE | QI_IEC_IM(mask)
 		   | QI_IEC_SELECTIVE;
-	desc.high = 0;
+	desc.qw1 = 0;
+	desc.qw2 = 0;
+	desc.qw3 = 0;
 
 	return qi_submit_sync(&desc, iommu);
 }

index b4da61385ebf..08ff588a4df7 100644
@@ -401,13 +401,18 @@ enum {
 #define QI_GRAN_NONG_PASID		2
 #define QI_GRAN_PSI_PASID		3
 
+#define qi_shift(iommu)		(DMAR_IQ_SHIFT + !!ecap_smts((iommu)->ecap))
+
 struct qi_desc {
-	u64 low, high;
+	u64 qw0;
+	u64 qw1;
+	u64 qw2;
+	u64 qw3;
 };
 
 struct q_inval {
 	raw_spinlock_t  q_lock;
-	struct qi_desc  *desc;          /* invalidation queue */
+	void		*desc;          /* invalidation queue */
 	int             *desc_status;   /* desc status */
 	int             free_head;      /* first free entry */
 	int             free_tail;      /* last free entry */

index 52cdb0e077f2..5e924bc8ebec 100644
@@ -1621,6 +1621,16 @@ static int iommu_init_domains(struct intel_iommu *iommu)
 	 */
 	set_bit(0, iommu->domain_ids);
 
+	/*
+	 * Vt-d spec rev3.0 (section 6.2.3.1) requires that each pasid
+	 * entry for first-level or pass-through translation modes should
+	 * be programmed with a domain id different from those used for
+	 * second-level or nested translation. We reserve a domain id for
+	 * this purpose.
+	 */
+	if (sm_supported(iommu))
+		set_bit(FLPT_DEFAULT_DID, iommu->domain_ids);
+
 	return 0;
 }
 

index 12f480c2bb8b..03c1612d173c 100644
@@ -17,6 +17,12 @@
 #define PDE_PFN_MASK			PAGE_MASK
 #define PASID_PDE_SHIFT			6
 
+/*
+ * Domain ID reserved for pasid entries programmed for first-level
+ * only and pass-through transfer modes.
+ */
+#define FLPT_DEFAULT_DID		1
+
 struct pasid_dir_entry {
 	u64 val;
 };

index 5e924bc8ebec..e741238e2326 100644
@@ -1210,7 +1210,7 @@ static void iommu_set_root_entry(struct intel_iommu *iommu)
 	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
 }
 
-static void iommu_flush_write_buffer(struct intel_iommu *iommu)
+void iommu_flush_write_buffer(struct intel_iommu *iommu)
 {
 	u32 val;
 	unsigned long flag;

289 lines not on this page · raw message

index 03c1612d173c..3c70522091d3 100644
@@ -49,5 +49,13 @@ struct pasid_table *intel_pasid_get_table(struct device *dev);
 int intel_pasid_get_dev_max_id(struct device *dev);
 struct pasid_entry *intel_pasid_get_entry(struct device *dev, int pasid);
 void intel_pasid_clear_entry(struct device *dev, int pasid);
+int intel_pasid_setup_second_level(struct intel_iommu *iommu,
+				   struct dmar_domain *domain,
+				   struct device *dev, int pasid);
+int intel_pasid_setup_pass_through(struct intel_iommu *iommu,
+				   struct dmar_domain *domain,
+				   struct device *dev, int pasid);
+void intel_pasid_tear_down_entry(struct intel_iommu *iommu,
+				 struct device *dev, int pasid);
 
 #endif /* __INTEL_PASID_H */

index 08ff588a4df7..cb3ebda47fa7 100644
@@ -177,6 +177,8 @@
  * Extended Capability Register
  */
 
+#define ecap_smpwc(e)		(((e) >> 48) & 0x1)
+#define ecap_slts(e)		(((e) >> 46) & 0x1)
 #define ecap_smts(e)		(((e) >> 43) & 0x1)
 #define ecap_dit(e)		((e >> 41) & 0x1)
 #define ecap_pasid(e)		((e >> 40) & 0x1)

@@ -662,6 +664,7 @@ void free_pgtable_page(void *vaddr);
 struct intel_iommu *domain_get_iommu(struct dmar_domain *domain);
 int for_each_device_domain(int (*fn)(struct device_domain_info *info,
 				     void *data), void *data);
+void iommu_flush_write_buffer(struct intel_iommu *iommu);
 
 #ifdef CONFIG_INTEL_IOMMU_SVM
 int intel_svm_init(struct intel_iommu *iommu);

index e741238e2326..a077ff3f67a6 100644
@@ -2462,6 +2462,22 @@ static struct dmar_domain *dmar_insert_one_dev_info(struct intel_iommu *iommu,
 			dmar_remove_one_dev_info(domain, dev);
 			return NULL;
 		}
+
+		/* Setup the PASID entry for requests without PASID: */
+		spin_lock(&iommu->lock);
+		if (hw_pass_through && domain_type_is_si(domain))
+			ret = intel_pasid_setup_pass_through(iommu, domain,
+					dev, PASID_RID2PASID);
+		else
+			ret = intel_pasid_setup_second_level(iommu, domain,
+					dev, PASID_RID2PASID);
+		spin_unlock(&iommu->lock);
+		if (ret) {
+			pr_err("Setup RID2PASID for %s failed\n",
+			       dev_name(dev));
+			dmar_remove_one_dev_info(domain, dev);
+			return NULL;
+		}
 	}
 
 	if (dev && domain_context_mapping(domain, dev)) {

@@ -4825,6 +4841,10 @@ static void __dmar_remove_one_dev_info(struct device_domain_info *info)
 	iommu = info->iommu;
 
 	if (info->dev) {
+		if (dev_is_pci(info->dev) && sm_supported(iommu))
+			intel_pasid_tear_down_entry(iommu, info->dev,
+					PASID_RID2PASID);
+
 		iommu_disable_dev_iotlb(info);
 		domain_context_clear(iommu, info->dev);
 		intel_pasid_free_table(info->dev);

index 3c70522091d3..d6f4fead4491 100644
@@ -10,6 +10,7 @@
 #ifndef __INTEL_PASID_H
 #define __INTEL_PASID_H
 
+#define PASID_RID2PASID			0x0
 #define PASID_MIN			0x1
 #define PASID_MAX			0x100000
 #define PASID_PTE_MASK			0x3F

index a077ff3f67a6..55c4ffda1246 100644
@@ -1920,6 +1920,7 @@ static void domain_exit(struct dmar_domain *domain)
 
 static int domain_context_mapping_one(struct dmar_domain *domain,
 				      struct intel_iommu *iommu,
+				      struct pasid_table *table,
 				      u8 bus, u8 devfn)
 {
 	u16 did = domain->iommu_did[iommu->seq_id];

@@ -2042,6 +2043,7 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
 struct domain_context_mapping_data {
 	struct dmar_domain *domain;
 	struct intel_iommu *iommu;
+	struct pasid_table *table;
 };
 
 static int domain_context_mapping_cb(struct pci_dev *pdev,

@@ -2050,25 +2052,31 @@ static int domain_context_mapping_cb(struct pci_dev *pdev,
 	struct domain_context_mapping_data *data = opaque;
 
 	return domain_context_mapping_one(data->domain, data->iommu,
-					  PCI_BUS_NUM(alias), alias & 0xff);
+					  data->table, PCI_BUS_NUM(alias),
+					  alias & 0xff);
 }
 
 static int
 domain_context_mapping(struct dmar_domain *domain, struct device *dev)
 {
+	struct domain_context_mapping_data data;
+	struct pasid_table *table;
 	struct intel_iommu *iommu;
 	u8 bus, devfn;
-	struct domain_context_mapping_data data;
 
 	iommu = device_to_iommu(dev, &bus, &devfn);
 	if (!iommu)
 		return -ENODEV;
 
+	table = intel_pasid_get_table(dev);
+
 	if (!dev_is_pci(dev))
-		return domain_context_mapping_one(domain, iommu, bus, devfn);
+		return domain_context_mapping_one(domain, iommu, table,
+						  bus, devfn);
 
 	data.domain = domain;
 	data.iommu = iommu;
+	data.table = table;
 
 	return pci_for_each_dma_alias(to_pci_dev(dev),
 				      &domain_context_mapping_cb, &data);

index 55c4ffda1246..21e5f1b9a2ca 100644
@@ -1197,6 +1197,8 @@ static void iommu_set_root_entry(struct intel_iommu *iommu)
 	unsigned long flag;
 
 	addr = virt_to_phys(iommu->root_entry);
+	if (sm_supported(iommu))
+		addr |= DMA_RTADDR_SMT;
 
 	raw_spin_lock_irqsave(&iommu->register_lock, flag);
 	dmar_writeq(iommu->reg + DMAR_RTADDR_REG, addr);

@@ -1918,6 +1920,56 @@ static void domain_exit(struct dmar_domain *domain)
 	free_domain_mem(domain);
 }
 
+/*
+ * Get the PASID directory size for scalable mode context entry.
+ * Value of X in the PDTS field of a scalable mode context entry
+ * indicates PASID directory with 2^(X + 7) entries.
+ */
+static inline unsigned long context_get_sm_pds(struct pasid_table *table)
+{
+	int pds, max_pde;
+
+	max_pde = table->max_pasid >> PASID_PDE_SHIFT;
+	pds = find_first_bit((unsigned long *)&max_pde, MAX_NR_PASID_BITS);
+	if (pds < 7)
+		return 0;
+
+	return pds - 7;
+}
+
+/*
+ * Set the RID_PASID field of a scalable mode context entry. The
+ * IOMMU hardware will use the PASID value set in this field for
+ * DMA translations of DMA requests without PASID.
+ */
+static inline void
+context_set_sm_rid2pasid(struct context_entry *context, unsigned long pasid)
+{
+	context->hi |= pasid & ((1 << 20) - 1);
+	context->hi |= (1 << 20);
+}
+
+/*
+ * Set the DTE(Device-TLB Enable) field of a scalable mode context
+ * entry.
+ */
+static inline void context_set_sm_dte(struct context_entry *context)
+{
+	context->lo |= (1 << 2);
+}
+
+/*
+ * Set the PRE(Page Request Enable) field of a scalable mode context
+ * entry.
+ */
+static inline void context_set_sm_pre(struct context_entry *context)
+{
+	context->lo |= (1 << 4);
+}
+
+/* Convert value to context PASID directory size field coding. */
+#define context_pdts(pds)	(((pds) & 0x7) << 9)
+
 static int domain_context_mapping_one(struct dmar_domain *domain,
 				      struct intel_iommu *iommu,
 				      struct pasid_table *table,

@@ -1928,8 +1980,7 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
 	struct device_domain_info *info = NULL;
 	struct context_entry *context;
 	unsigned long flags;
-	struct dma_pte *pgd;
-	int ret, agaw;
+	int ret;
 
 	WARN_ON(did == 0);
 

@@ -1975,41 +2026,67 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
 		}
 	}
 
-	pgd = domain->pgd;
-
 	context_clear_entry(context);
-	context_set_domain_id(context, did);
 
-	/*
-	 * Skip top levels of page tables for iommu which has less agaw
-	 * than default.  Unnecessary for PT mode.
-	 */
-	if (translation != CONTEXT_TT_PASS_THROUGH) {
-		for (agaw = domain->agaw; agaw > iommu->agaw; agaw--) {
-			ret = -ENOMEM;
-			pgd = phys_to_virt(dma_pte_addr(pgd));
-			if (!dma_pte_present(pgd))
-				goto out_unlock;
-		}
+	if (sm_supported(iommu)) {
+		unsigned long pds;
 
-		info = iommu_support_dev_iotlb(domain, iommu, bus, devfn);
-		if (info && info->ats_supported)
-			translation = CONTEXT_TT_DEV_IOTLB;
-		else
-			translation = CONTEXT_TT_MULTI_LEVEL;
+		WARN_ON(!table);
+
+		/* Setup the PASID DIR pointer: */
+		pds = context_get_sm_pds(table);
+		context->lo = (u64)virt_to_phys(table->table) |
+				context_pdts(pds);
+
+		/* Setup the RID_PASID field: */
+		context_set_sm_rid2pasid(context, PASID_RID2PASID);
 
-		context_set_address_root(context, virt_to_phys(pgd));
-		context_set_address_width(context, agaw);
-	} else {
 		/*
-		 * In pass through mode, AW must be programmed to
-		 * indicate the largest AGAW value supported by
-		 * hardware. And ASR is ignored by hardware.
+		 * Setup the Device-TLB enable bit and Page request
+		 * Enable bit:
 		 */
-		context_set_address_width(context, iommu->msagaw);
+		info = iommu_support_dev_iotlb(domain, iommu, bus, devfn);
+		if (info && info->ats_supported)
+			context_set_sm_dte(context);
+		if (info && info->pri_supported)
+			context_set_sm_pre(context);
+	} else {
+		struct dma_pte *pgd = domain->pgd;
+		int agaw;
+
+		context_set_domain_id(context, did);
+		context_set_translation_type(context, translation);
+
+		if (translation != CONTEXT_TT_PASS_THROUGH) {
+			/*
+			 * Skip top levels of page tables for iommu which has
+			 * less agaw than default. Unnecessary for PT mode.
+			 */
+			for (agaw = domain->agaw; agaw > iommu->agaw; agaw--) {
+				ret = -ENOMEM;
+				pgd = phys_to_virt(dma_pte_addr(pgd));
+				if (!dma_pte_present(pgd))
+					goto out_unlock;
+			}
+
+			info = iommu_support_dev_iotlb(domain, iommu, bus, devfn);
+			if (info && info->ats_supported)
+				translation = CONTEXT_TT_DEV_IOTLB;
+			else
+				translation = CONTEXT_TT_MULTI_LEVEL;
+
+			context_set_address_root(context, virt_to_phys(pgd));
+			context_set_address_width(context, agaw);
+		} else {
+			/*
+			 * 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, translation);
 	context_set_fault_enable(context);
 	context_set_present(context);
 	domain_flush_cache(domain, context, sizeof(*context));

@@ -5180,7 +5257,6 @@ static void intel_iommu_put_resv_regions(struct device *dev,
 }
 
 #ifdef CONFIG_INTEL_IOMMU_SVM
-#define MAX_NR_PASID_BITS (20)
 static inline unsigned long intel_iommu_get_pts(struct device *dev)
 {
 	int pts, max_pasid;

index d6f4fead4491..55bb8715329d 100644
@@ -17,6 +17,7 @@
 #define PASID_PTE_PRESENT		1
 #define PDE_PFN_MASK			PAGE_MASK
 #define PASID_PDE_SHIFT			6
+#define MAX_NR_PASID_BITS		20
 
 /*
  * Domain ID reserved for pasid entries programmed for first-level

index cb3ebda47fa7..5fdd33ed2cce 100644
@@ -258,6 +258,7 @@
 
 /* DMA_RTADDR_REG */
 #define DMA_RTADDR_RTT (((u64)1) << 11)
+#define DMA_RTADDR_SMT (((u64)1) << 10)
 
 /* CCMD_REG */
 #define DMA_CCMD_ICC (((u64)1) << 63)

index 6d2b2e87e6fc..c3dcf4dc2496 100644
@@ -10,6 +10,7 @@
 #define pr_fmt(fmt)	"DMAR: " fmt
 
 #include <linux/bitops.h>
+#include <linux/cpufeature.h>
 #include <linux/dmar.h>
 #include <linux/intel-iommu.h>
 #include <linux/iommu.h>

@@ -389,6 +390,26 @@ static inline void pasid_set_page_snoop(struct pasid_entry *pe, bool value)
 	pasid_set_bits(&pe->val[1], 1 << 23, value);
 }
 
+/*
+ * Setup the First Level Page table Pointer field (Bit 140~191)
+ * of a scalable mode PASID entry.
+ */
+static inline void
+pasid_set_flptr(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[2], VTD_PAGE_MASK, value);
+}
+
+/*
+ * Setup the First Level Paging Mode field (Bit 130~131) of a
+ * scalable mode PASID entry.
+ */
+static inline void
+pasid_set_flpm(struct pasid_entry *pe, u64 value)
+{
+	pasid_set_bits(&pe->val[2], GENMASK_ULL(3, 2), value << 2);
+}
+
 static void
 pasid_cache_invalidation_with_pasid(struct intel_iommu *iommu,
 				    u16 did, int pasid)

@@ -459,6 +480,65 @@ void intel_pasid_tear_down_entry(struct intel_iommu *iommu,
 		devtlb_invalidation_with_pasid(iommu, dev, pasid);
 }
 
+/*
+ * Set up the scalable mode pasid table entry for first only
+ * translation type.
+ */
+int intel_pasid_setup_first_level(struct intel_iommu *iommu,
+				  struct device *dev, pgd_t *pgd,
+				  int pasid, u16 did, int flags)
+{
+	struct pasid_entry *pte;
+
+	if (!ecap_flts(iommu->ecap)) {
+		pr_err("No first level translation support on %s\n",
+		       iommu->name);
+		return -EINVAL;
+	}
+
+	pte = intel_pasid_get_entry(dev, pasid);
+	if (WARN_ON(!pte))
+		return -EINVAL;
+
+	pasid_clear_entry(pte);
+
+	/* Setup the first level page table pointer: */
+	pasid_set_flptr(pte, (u64)__pa(pgd));
+	if (flags & PASID_FLAG_SUPERVISOR_MODE) {
+		if (!ecap_srs(iommu->ecap)) {
+			pr_err("No supervisor request support on %s\n",
+			       iommu->name);
+			return -EINVAL;
+		}
+		pasid_set_sre(pte);
+	}
+
+#ifdef CONFIG_X86
+	if (cpu_feature_enabled(X86_FEATURE_LA57))
+		pasid_set_flpm(pte, 1);
+#endif /* CONFIG_X86 */
+
+	pasid_set_domain_id(pte, did);
+	pasid_set_address_width(pte, iommu->agaw);
+	pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));
+
+	/* Setup Present and PASID Granular Transfer Type: */
+	pasid_set_translation_type(pte, 1);
+	pasid_set_present(pte);
+
+	if (!ecap_coherent(iommu->ecap))
+		clflush_cache_range(pte, sizeof(*pte));
+
+	if (cap_caching_mode(iommu->cap)) {
+		pasid_cache_invalidation_with_pasid(iommu, did, pasid);
+		iotlb_invalidation_with_pasid(iommu, did, pasid);
+	} else {
+		iommu_flush_write_buffer(iommu);
+	}
+
+	return 0;
+}
+
 /*
  * Set up the scalable mode pasid entry for second only translation type.
  */

index 55bb8715329d..512c63ec8a22 100644
@@ -25,6 +25,14 @@
  */
 #define FLPT_DEFAULT_DID		1
 
+/*
+ * The SUPERVISOR_MODE flag indicates a first level translation which
+ * can be used for access to kernel addresses. It is valid only for
+ * access to the kernel's static 1:1 mapping of physical memory — not
+ * to vmalloc or even module mappings.
+ */
+#define PASID_FLAG_SUPERVISOR_MODE	BIT(0)
+
 struct pasid_dir_entry {
 	u64 val;
 };

@@ -51,6 +59,9 @@ struct pasid_table *intel_pasid_get_table(struct device *dev);
 int intel_pasid_get_dev_max_id(struct device *dev);
 struct pasid_entry *intel_pasid_get_entry(struct device *dev, int pasid);
 void intel_pasid_clear_entry(struct device *dev, int pasid);
+int intel_pasid_setup_first_level(struct intel_iommu *iommu,
+				  struct device *dev, pgd_t *pgd,
+				  int pasid, u16 did, int flags);
 int intel_pasid_setup_second_level(struct intel_iommu *iommu,
 				   struct dmar_domain *domain,
 				   struct device *dev, int pasid);

index 5fdd33ed2cce..4ad62396e81e 100644
@@ -178,6 +178,7 @@
  */
 
 #define ecap_smpwc(e)		(((e) >> 48) & 0x1)
+#define ecap_flts(e)		(((e) >> 47) & 0x1)
 #define ecap_slts(e)		(((e) >> 46) & 0x1)
 #define ecap_smts(e)		(((e) >> 43) & 0x1)
 #define ecap_dit(e)		((e >> 41) & 0x1)

index 21e5f1b9a2ca..4552166c553b 100644
@@ -5257,18 +5257,6 @@ static void intel_iommu_put_resv_regions(struct device *dev,
 }
 
 #ifdef CONFIG_INTEL_IOMMU_SVM
-static inline unsigned long intel_iommu_get_pts(struct device *dev)
-{
-	int pts, max_pasid;
-
-	max_pasid = intel_pasid_get_dev_max_id(dev);
-	pts = find_first_bit((unsigned long *)&max_pasid, MAX_NR_PASID_BITS);
-	if (pts < 5)
-		return 0;
-
-	return pts - 5;
-}
-
 int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sdev)
 {
 	struct device_domain_info *info;

@@ -5300,33 +5288,7 @@ int intel_iommu_enable_pasid(struct intel_iommu *iommu, struct intel_svm_dev *sd
 	sdev->sid = PCI_DEVID(info->bus, info->devfn);
 
 	if (!(ctx_lo & CONTEXT_PASIDE)) {
-		if (iommu->pasid_state_table)
-			context[1].hi = (u64)virt_to_phys(iommu->pasid_state_table);
-		context[1].lo = (u64)virt_to_phys(info->pasid_table->table) |
-			intel_iommu_get_pts(sdev->dev);
-
-		wmb();
-		/* CONTEXT_TT_MULTI_LEVEL and CONTEXT_TT_DEV_IOTLB are both
-		 * extended to permit requests-with-PASID if the PASIDE bit
-		 * is set. which makes sense. For CONTEXT_TT_PASS_THROUGH,
-		 * however, the PASIDE bit is ignored and requests-with-PASID
-		 * are unconditionally blocked. Which makes less sense.
-		 * So convert from CONTEXT_TT_PASS_THROUGH to one of the new
-		 * "guest mode" translation types depending on whether ATS
-		 * is available or not. Annoyingly, we can't use the new
-		 * modes *unless* PASIDE is set. */
-		if ((ctx_lo & CONTEXT_TT_MASK) == (CONTEXT_TT_PASS_THROUGH << 2)) {
-			ctx_lo &= ~CONTEXT_TT_MASK;
-			if (info->ats_supported)
-				ctx_lo |= CONTEXT_TT_PT_PASID_DEV_IOTLB << 2;
-			else
-				ctx_lo |= CONTEXT_TT_PT_PASID << 2;
-		}
 		ctx_lo |= CONTEXT_PASIDE;
-		if (iommu->pasid_state_table)
-			ctx_lo |= CONTEXT_DINVE;
-		if (info->pri_supported)
-			ctx_lo |= CONTEXT_PRS;
 		context[0].lo = ctx_lo;
 		wmb();
 		iommu->flush.flush_context(iommu, sdev->did, sdev->sid,

index c3dcf4dc2496..53fe5248d8f1 100644
@@ -286,7 +286,7 @@ static inline void pasid_clear_entry(struct pasid_entry *pe)
 	WRITE_ONCE(pe->val[7], 0);
 }
 
-void intel_pasid_clear_entry(struct device *dev, int pasid)
+static void intel_pasid_clear_entry(struct device *dev, int pasid)
 {
 	struct pasid_entry *pe;
 

index 512c63ec8a22..23537b3f34e3 100644
@@ -58,7 +58,6 @@ void intel_pasid_free_table(struct device *dev);
 struct pasid_table *intel_pasid_get_table(struct device *dev);
 int intel_pasid_get_dev_max_id(struct device *dev);
 struct pasid_entry *intel_pasid_get_entry(struct device *dev, int pasid);
-void intel_pasid_clear_entry(struct device *dev, int pasid);
 int intel_pasid_setup_first_level(struct intel_iommu *iommu,
 				  struct device *dev, pgd_t *pgd,
 				  int pasid, u16 did, int flags);

99 lines not on this page · raw message

index 4ad62396e81e..cfcf9c1e1872 100644
@@ -54,14 +54,7 @@
 #define CONTEXT_TT_MULTI_LEVEL	0
 #define CONTEXT_TT_DEV_IOTLB	1
 #define CONTEXT_TT_PASS_THROUGH 2
-/* Extended context entry types */
-#define CONTEXT_TT_PT_PASID	4
-#define CONTEXT_TT_PT_PASID_DEV_IOTLB 5
-#define CONTEXT_TT_MASK (7ULL << 2)
-
-#define CONTEXT_DINVE		(1ULL << 8)
-#define CONTEXT_PRS		(1ULL << 9)
-#define CONTEXT_PASIDE		(1ULL << 11)
+#define CONTEXT_PASIDE		BIT_ULL(3)
 
 /*
  * Intel IOMMU register specification per version 1.0 public spec.

index 4552166c553b..eb5351e8cde5 100644
@@ -1700,7 +1700,6 @@ static void free_dmar_iommu(struct intel_iommu *iommu)
 	if (pasid_supported(iommu)) {
 		if (ecap_prs(iommu->ecap))
 			intel_svm_finish_prq(iommu);
-		intel_svm_exit(iommu);
 	}
 #endif
 }

65 lines not on this page · raw message

index cfcf9c1e1872..0605f3bf6e79 100644
@@ -541,15 +541,8 @@ struct intel_iommu {
 	struct iommu_flush flush;
 #endif
 #ifdef CONFIG_INTEL_IOMMU_SVM
-	/* These are large and need to be contiguous, so we allocate just
-	 * one for now. We'll maybe want to rethink that if we truly give
-	 * devices away to userspace processes (e.g. for DPDK) and don't
-	 * want to trust that userspace will use *only* the PASID it was
-	 * told to. But while it's all driver-arbitrated, we're fine. */
-	struct pasid_state_entry *pasid_state_table;
 	struct page_req_dsc *prq;
 	unsigned char prq_name[16];    /* Name for PRQ interrupt */
-	u32 pasid_max;
 #endif
 	struct q_inval  *qi;            /* Queued invalidation info */
 	u32 *iommu_state; /* Store iommu states between suspend and resume.*/

@@ -663,7 +656,6 @@ void iommu_flush_write_buffer(struct intel_iommu *iommu);
 
 #ifdef CONFIG_INTEL_IOMMU_SVM
 int intel_svm_init(struct intel_iommu *iommu);
-int intel_svm_exit(struct intel_iommu *iommu);
 extern int intel_svm_enable_prq(struct intel_iommu *iommu);
 extern int intel_svm_finish_prq(struct intel_iommu *iommu);