X-Git-Url: http://git.monstr.eu/?a=blobdiff_plain;f=drivers%2Fiommu%2Famd%2Fiommu.c;h=cf26b735922b969fe95b1e5319fdb75aac248693;hb=801b5e4c4eec7b6c7f968d4bbce43da7cacffae4;hp=ba9f3dbc5b94796adb199006390bdbcad8741963;hpb=e9e3086b3d791532be1ee8dc7412bfc1596e6871;p=linux-2.6-microblaze.git

diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index ba9f3dbc5b94..cf26b735922b 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -2659,7 +2659,12 @@ static int amd_iommu_def_domain_type(struct device *dev)
 	if (!dev_data)
 		return 0;
 
-	if (dev_data->iommu_v2)
+	/*
+	 * Do not identity map IOMMUv2 capable devices when memory encryption is
+	 * active, because some of those devices (AMD GPUs) don't have the
+	 * encryption bit in their DMA-mask and require remapping.
+	 */
+	if (!mem_encrypt_active() && dev_data->iommu_v2)
 		return IOMMU_DOMAIN_IDENTITY;
 
 	return 0;
@@ -3292,6 +3297,7 @@ out:
 static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte,
 			  struct amd_ir_data *data)
 {
+	bool ret;
 	struct irq_remap_table *table;
 	struct amd_iommu *iommu;
 	unsigned long flags;
@@ -3309,10 +3315,18 @@ static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte,
 
 	entry = (struct irte_ga *)table->table;
 	entry = &entry[index];
-	entry->lo.fields_remap.valid = 0;
-	entry->hi.val = irte->hi.val;
-	entry->lo.val = irte->lo.val;
-	entry->lo.fields_remap.valid = 1;
+
+	ret = cmpxchg_double(&entry->lo.val, &entry->hi.val,
+			     entry->lo.val, entry->hi.val,
+			     irte->lo.val, irte->hi.val);
+	/*
+	 * We use cmpxchg16 to atomically update the 128-bit IRTE,
+	 * and it cannot be updated by the hardware or other processors
+	 * behind us, so the return value of cmpxchg16 should be the
+	 * same as the old value.
+	 */
+	WARN_ON(!ret);
+
 	if (data)
 		data->ref = entry;
 
@@ -3514,8 +3528,8 @@ static int get_devid(struct irq_alloc_info *info)
 	case X86_IRQ_ALLOC_TYPE_HPET:
 		devid     = get_hpet_devid(info->hpet_id);
 		break;
-	case X86_IRQ_ALLOC_TYPE_MSI:
-	case X86_IRQ_ALLOC_TYPE_MSIX:
+	case X86_IRQ_ALLOC_TYPE_PCI_MSI:
+	case X86_IRQ_ALLOC_TYPE_PCI_MSIX:
 		devid = get_device_id(&info->msi_dev->dev);
 		break;
 	default:
@@ -3553,8 +3567,8 @@ static struct irq_domain *get_irq_domain(struct irq_alloc_info *info)
 		return NULL;
 
 	switch (info->type) {
-	case X86_IRQ_ALLOC_TYPE_MSI:
-	case X86_IRQ_ALLOC_TYPE_MSIX:
+	case X86_IRQ_ALLOC_TYPE_PCI_MSI:
+	case X86_IRQ_ALLOC_TYPE_PCI_MSIX:
 		devid = get_device_id(&info->msi_dev->dev);
 		if (devid < 0)
 			return NULL;
@@ -3615,8 +3629,8 @@ static void irq_remapping_prepare_irte(struct amd_ir_data *data,
 		break;
 
 	case X86_IRQ_ALLOC_TYPE_HPET:
-	case X86_IRQ_ALLOC_TYPE_MSI:
-	case X86_IRQ_ALLOC_TYPE_MSIX:
+	case X86_IRQ_ALLOC_TYPE_PCI_MSI:
+	case X86_IRQ_ALLOC_TYPE_PCI_MSIX:
 		msg->address_hi = MSI_ADDR_BASE_HI;
 		msg->address_lo = MSI_ADDR_BASE_LO;
 		msg->data = irte_info->index;
@@ -3660,15 +3674,15 @@ static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq,
 
 	if (!info)
 		return -EINVAL;
-	if (nr_irqs > 1 && info->type != X86_IRQ_ALLOC_TYPE_MSI &&
-	    info->type != X86_IRQ_ALLOC_TYPE_MSIX)
+	if (nr_irqs > 1 && info->type != X86_IRQ_ALLOC_TYPE_PCI_MSI &&
+	    info->type != X86_IRQ_ALLOC_TYPE_PCI_MSIX)
 		return -EINVAL;
 
 	/*
 	 * With IRQ remapping enabled, don't need contiguous CPU vectors
 	 * to support multiple MSI interrupts.
 	 */
-	if (info->type == X86_IRQ_ALLOC_TYPE_MSI)
+	if (info->type == X86_IRQ_ALLOC_TYPE_PCI_MSI)
 		info->flags &= ~X86_IRQ_ALLOC_CONTIGUOUS_VECTORS;
 
 	devid = get_devid(info);
@@ -3700,9 +3714,9 @@ static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq,
 		} else {
 			index = -ENOMEM;
 		}
-	} else if (info->type == X86_IRQ_ALLOC_TYPE_MSI ||
-		   info->type == X86_IRQ_ALLOC_TYPE_MSIX) {
-		bool align = (info->type == X86_IRQ_ALLOC_TYPE_MSI);
+	} else if (info->type == X86_IRQ_ALLOC_TYPE_PCI_MSI ||
+		   info->type == X86_IRQ_ALLOC_TYPE_PCI_MSIX) {
+		bool align = (info->type == X86_IRQ_ALLOC_TYPE_PCI_MSI);
 
 		index = alloc_irq_index(devid, nr_irqs, align, info->msi_dev);
 	} else {
@@ -3717,8 +3731,8 @@ static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq,
 
 	for (i = 0; i < nr_irqs; i++) {
 		irq_data = irq_domain_get_irq_data(domain, virq + i);
-		cfg = irqd_cfg(irq_data);
-		if (!irq_data || !cfg) {
+		cfg = irq_data ? irqd_cfg(irq_data) : NULL;
+		if (!cfg) {
 			ret = -EINVAL;
 			goto out_free_data;
 		}
@@ -3850,6 +3864,7 @@ int amd_iommu_deactivate_guest_mode(void *data)
 	struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
 	struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
 	struct irq_cfg *cfg = ir_data->cfg;
+	u64 valid = entry->lo.fields_remap.valid;
 
 	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) ||
 	    !entry || !entry->lo.fields_vapic.guest_mode)
@@ -3858,6 +3873,7 @@ int amd_iommu_deactivate_guest_mode(void *data)
 	entry->lo.val = 0;
 	entry->hi.val = 0;
 
+	entry->lo.fields_remap.valid       = valid;
 	entry->lo.fields_remap.dm          = apic->irq_dest_mode;
 	entry->lo.fields_remap.int_type    = apic->irq_delivery_mode;
 	entry->hi.fields.vector            = cfg->vector;