iommu/vt-d: support extended root and context entries

Add a new function iommu_context_addr() which takes care of the
differences and returns a pointer to a context entry which may be
in either format. The formats are binary compatible for all the old
fields anyway; the new one is just larger and some of the reserved
bits in the original 128 are now meaningful.

So far, nothing actually uses the new fields in the extended context
entry. Modulo hardware bugs with interpreting the new-style tables,
this should basically be a no-op.
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>

drivers/iommu/intel-iommu.c

@@ -182,32 +182,11 @@ static int force_on = 0;
  * 64-127: Reserved
  */
 struct root_entry {
-	u64	val;
-	u64	rsvd1;
+	u64	lo;
+	u64	hi;
 };
 #define ROOT_ENTRY_NR (VTD_PAGE_SIZE/sizeof(struct root_entry))
-static inline bool root_present(struct root_entry *root)
-{
-	return (root->val & 1);
-}
-static inline void set_root_present(struct root_entry *root)
-{
-	root->val |= 1;
-}
-static inline void set_root_value(struct root_entry *root, unsigned long value)
-{
-	root->val &= ~VTD_PAGE_MASK;
-	root->val |= value & VTD_PAGE_MASK;
-}
 
-static inline struct context_entry *
-get_context_addr_from_root(struct root_entry *root)
-{
-	return (struct context_entry *)
-		(root_present(root)?phys_to_virt(
-		root->val & VTD_PAGE_MASK) :
-		NULL);
-}
 
 /*
  * low 64 bits:
@@ -681,6 +660,40 @@ static void domain_update_iommu_cap(struct dmar_domain *domain)
 	domain->iommu_superpage = domain_update_iommu_superpage(NULL);
 }
 
+static inline struct context_entry *iommu_context_addr(struct intel_iommu *iommu,
+						       u8 bus, u8 devfn, int alloc)
+{
+	struct root_entry *root = &iommu->root_entry[bus];
+	struct context_entry *context;
+	u64 *entry;
+
+	if (ecap_ecs(iommu->ecap)) {
+		if (devfn >= 0x80) {
+			devfn -= 0x80;
+			entry = &root->hi;
+		}
+		devfn *= 2;
+	}
+	entry = &root->lo;
+	if (*entry & 1)
+		context = phys_to_virt(*entry & VTD_PAGE_MASK);
+	else {
+		unsigned long phy_addr;
+		if (!alloc)
+			return NULL;
+
+		context = alloc_pgtable_page(iommu->node);
+		if (!context)
+			return NULL;
+
+		__iommu_flush_cache(iommu, (void *)context, CONTEXT_SIZE);
+		phy_addr = virt_to_phys((void *)context);
+		*entry = phy_addr | 1;
+		__iommu_flush_cache(iommu, entry, sizeof(*entry));
+	}
+	return &context[devfn];
+}
+
 static struct intel_iommu *device_to_iommu(struct device *dev, u8 *bus, u8 *devfn)
 {
 	struct dmar_drhd_unit *drhd = NULL;
@@ -740,75 +753,36 @@ static void domain_flush_cache(struct dmar_domain *domain,
 		clflush_cache_range(addr, size);
 }
 
-/* Gets context entry for a given bus and devfn */
-static struct context_entry * device_to_context_entry(struct intel_iommu *iommu,
-		u8 bus, u8 devfn)
-{
-	struct root_entry *root;
-	struct context_entry *context;
-	unsigned long phy_addr;
-	unsigned long flags;
-
-	spin_lock_irqsave(&iommu->lock, flags);
-	root = &iommu->root_entry[bus];
-	context = get_context_addr_from_root(root);
-	if (!context) {
-		context = (struct context_entry *)
-				alloc_pgtable_page(iommu->node);
-		if (!context) {
-			spin_unlock_irqrestore(&iommu->lock, flags);
-			return NULL;
-		}
-		__iommu_flush_cache(iommu, (void *)context, CONTEXT_SIZE);
-		phy_addr = virt_to_phys((void *)context);
-		set_root_value(root, phy_addr);
-		set_root_present(root);
-		__iommu_flush_cache(iommu, root, sizeof(*root));
-	}
-	spin_unlock_irqrestore(&iommu->lock, flags);
-	return &context[devfn];
-}
-
 static int device_context_mapped(struct intel_iommu *iommu, u8 bus, u8 devfn)
 {
-	struct root_entry *root;
 	struct context_entry *context;
-	int ret;
+	int ret = 0;
 	unsigned long flags;
 
 	spin_lock_irqsave(&iommu->lock, flags);
-	root = &iommu->root_entry[bus];
-	context = get_context_addr_from_root(root);
-	if (!context) {
-		ret = 0;
-		goto out;
-	}
-	ret = context_present(&context[devfn]);
-out:
+	context = iommu_context_addr(iommu, bus, devfn, 0);
+	if (context)
+		ret = context_present(context);
 	spin_unlock_irqrestore(&iommu->lock, flags);
 	return ret;
 }
 
 static void clear_context_table(struct intel_iommu *iommu, u8 bus, u8 devfn)
 {
-	struct root_entry *root;
 	struct context_entry *context;
 	unsigned long flags;
 
 	spin_lock_irqsave(&iommu->lock, flags);
-	root = &iommu->root_entry[bus];
-	context = get_context_addr_from_root(root);
+	context = iommu_context_addr(iommu, bus, devfn, 0);
 	if (context) {
-		context_clear_entry(&context[devfn]);
-		__iommu_flush_cache(iommu, &context[devfn], \
-			sizeof(*context));
+		context_clear_entry(context);
+		__iommu_flush_cache(iommu, context, sizeof(*context));
 	}
 	spin_unlock_irqrestore(&iommu->lock, flags);
 }
 
 static void free_context_table(struct intel_iommu *iommu)
 {
-	struct root_entry *root;
 	int i;
 	unsigned long flags;
 	struct context_entry *context;
@@ -818,10 +792,17 @@ static void free_context_table(struct intel_iommu *iommu)
 		goto out;
 	}
 	for (i = 0; i < ROOT_ENTRY_NR; i++) {
-		root = &iommu->root_entry[i];
-		context = get_context_addr_from_root(root);
+		context = iommu_context_addr(iommu, i, 0, 0);
+		if (context)
+			free_pgtable_page(context);
+
+		if (!ecap_ecs(iommu->ecap))
+			continue;
+
+		context = iommu_context_addr(iommu, i, 0x80, 0);
 		if (context)
 			free_pgtable_page(context);
+
 	}
 	free_pgtable_page(iommu->root_entry);
 	iommu->root_entry = NULL;
@@ -1145,14 +1126,16 @@ static int iommu_alloc_root_entry(struct intel_iommu *iommu)
 
 static void iommu_set_root_entry(struct intel_iommu *iommu)
 {
-	void *addr;
+	u64 addr;
 	u32 sts;
 	unsigned long flag;
 
-	addr = iommu->root_entry;
+	addr = virt_to_phys(iommu->root_entry);
+	if (ecap_ecs(iommu->ecap))
+		addr |= DMA_RTADDR_RTT;
 
 	raw_spin_lock_irqsave(&iommu->register_lock, flag);
-	dmar_writeq(iommu->reg + DMAR_RTADDR_REG, virt_to_phys(addr));
+	dmar_writeq(iommu->reg + DMAR_RTADDR_REG, addr);
 
 	writel(iommu->gcmd | DMA_GCMD_SRTP, iommu->reg + DMAR_GCMD_REG);
 
@@ -1798,7 +1781,9 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
 	BUG_ON(translation != CONTEXT_TT_PASS_THROUGH &&
 	       translation != CONTEXT_TT_MULTI_LEVEL);
 
-	context = device_to_context_entry(iommu, bus, devfn);
+	spin_lock_irqsave(&iommu->lock, flags);
+	context = iommu_context_addr(iommu, bus, devfn, 1);
+	spin_unlock_irqrestore(&iommu->lock, flags);
 	if (!context)
 		return -ENOMEM;
 	spin_lock_irqsave(&iommu->lock, flags);