4 files changed, 54 insertions, 8 deletions

diff --git a/drivers/iommu/amd/Kconfig b/drivers/iommu/amd/Kconfig
index 1f061d91e0b8..626b97d0dd21 100644
--- a/drivers/iommu/amd/Kconfig
+++ b/drivers/iommu/amd/Kconfig
@@ -10,7 +10,7 @@ config AMD_IOMMU
 	select IOMMU_API
 	select IOMMU_IOVA
 	select IOMMU_DMA
-	depends on X86_64 && PCI && ACPI
+	depends on X86_64 && PCI && ACPI && HAVE_CMPXCHG_DOUBLE
 	help
 	  With this option you can enable support for AMD IOMMU hardware in
 	  your system. An IOMMU is a hardware component which provides
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index c652f16eb702..445a08d23fed 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -1511,7 +1511,14 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
 			iommu->mmio_phys_end = MMIO_REG_END_OFFSET;
 		else
 			iommu->mmio_phys_end = MMIO_CNTR_CONF_OFFSET;
-		if (((h->efr_attr & (0x1 << IOMMU_FEAT_GASUP_SHIFT)) == 0))
+
+		/*
+		 * Note: GA (128-bit IRTE) mode requires cmpxchg16b supports.
+		 * GAM also requires GA mode. Therefore, we need to
+		 * check cmpxchg16b support before enabling it.
+		 */
+		if (!boot_cpu_has(X86_FEATURE_CX16) ||
+		    ((h->efr_attr & (0x1 << IOMMU_FEAT_GASUP_SHIFT)) == 0))
 			amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY;
 		break;
 	case 0x11:
@@ -1520,8 +1527,18 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
 			iommu->mmio_phys_end = MMIO_REG_END_OFFSET;
 		else
 			iommu->mmio_phys_end = MMIO_CNTR_CONF_OFFSET;
-		if (((h->efr_reg & (0x1 << IOMMU_EFR_GASUP_SHIFT)) == 0))
+
+		/*
+		 * Note: GA (128-bit IRTE) mode requires cmpxchg16b supports.
+		 * XT, GAM also requires GA mode. Therefore, we need to
+		 * check cmpxchg16b support before enabling them.
+		 */
+		if (!boot_cpu_has(X86_FEATURE_CX16) ||
+		    ((h->efr_reg & (0x1 << IOMMU_EFR_GASUP_SHIFT)) == 0)) {
 			amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY;
+			break;
+		}
+
 		/*
 		 * Note: Since iommu_update_intcapxt() leverages
 		 * the IOMMU MMIO access to MSI capability block registers
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index ba9f3dbc5b94..10e4200d3552 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;
 
@@ -3826,14 +3840,18 @@ int amd_iommu_activate_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;
+	u64 valid;
 
 	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) ||
 	    !entry || entry->lo.fields_vapic.guest_mode)
 		return 0;
 
+	valid = entry->lo.fields_vapic.valid;
+
 	entry->lo.val = 0;
 	entry->hi.val = 0;
 
+	entry->lo.fields_vapic.valid       = valid;
 	entry->lo.fields_vapic.guest_mode  = 1;
 	entry->lo.fields_vapic.ga_log_intr = 1;
 	entry->hi.fields.ga_root_ptr       = ir_data->ga_root_ptr;
@@ -3850,14 +3868,18 @@ 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;
 
 	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) ||
 	    !entry || !entry->lo.fields_vapic.guest_mode)
 		return 0;
 
+	valid = entry->lo.fields_remap.valid;
+
 	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;
diff --git a/drivers/iommu/amd/iommu_v2.c b/drivers/iommu/amd/iommu_v2.c
index c259108ab6dd..0d175aed1d92 100644
--- a/drivers/iommu/amd/iommu_v2.c
+++ b/drivers/iommu/amd/iommu_v2.c
@@ -737,6 +737,13 @@ int amd_iommu_init_device(struct pci_dev *pdev, int pasids)
 
 	might_sleep();
 
+	/*
+	 * When memory encryption is active the device is likely not in a
+	 * direct-mapped domain. Forbid using IOMMUv2 functionality for now.
+	 */
+	if (mem_encrypt_active())
+		return -ENODEV;
+
 	if (!amd_iommu_v2_supported())
 		return -ENODEV;