1 files changed, 101 insertions, 81 deletions

diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index ba9f3dbc5b94..9e231caa5012 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -513,10 +513,11 @@ static void amd_iommu_report_page_fault(u16 devid, u16 domain_id,
 static void iommu_print_event(struct amd_iommu *iommu, void *__evt)
 {
 	struct device *dev = iommu->iommu.dev;
-	int type, devid, pasid, flags, tag;
+	int type, devid, flags, tag;
 	volatile u32 *event = __evt;
 	int count = 0;
 	u64 address;
+	u32 pasid;
 
 retry:
 	type    = (event[1] >> EVENT_TYPE_SHIFT)  & EVENT_TYPE_MASK;
@@ -729,7 +730,21 @@ static void iommu_poll_ga_log(struct amd_iommu *iommu)
 		}
 	}
 }
-#endif /* CONFIG_IRQ_REMAP */
+
+static void
+amd_iommu_set_pci_msi_domain(struct device *dev, struct amd_iommu *iommu)
+{
+	if (!irq_remapping_enabled || !dev_is_pci(dev) ||
+	    pci_dev_has_special_msi_domain(to_pci_dev(dev)))
+		return;
+
+	dev_set_msi_domain(dev, iommu->msi_domain);
+}
+
+#else /* CONFIG_IRQ_REMAP */
+static inline void
+amd_iommu_set_pci_msi_domain(struct device *dev, struct amd_iommu *iommu) { }
+#endif /* !CONFIG_IRQ_REMAP */
 
 #define AMD_IOMMU_INT_MASK	\
 	(MMIO_STATUS_EVT_INT_MASK | \
@@ -909,7 +924,7 @@ static void build_inv_iotlb_pages(struct iommu_cmd *cmd, u16 devid, int qdep,
 		cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK;
 }
 
-static void build_inv_iommu_pasid(struct iommu_cmd *cmd, u16 domid, int pasid,
+static void build_inv_iommu_pasid(struct iommu_cmd *cmd, u16 domid, u32 pasid,
 				  u64 address, bool size)
 {
 	memset(cmd, 0, sizeof(*cmd));
@@ -927,7 +942,7 @@ static void build_inv_iommu_pasid(struct iommu_cmd *cmd, u16 domid, int pasid,
 	CMD_SET_TYPE(cmd, CMD_INV_IOMMU_PAGES);
 }
 
-static void build_inv_iotlb_pasid(struct iommu_cmd *cmd, u16 devid, int pasid,
+static void build_inv_iotlb_pasid(struct iommu_cmd *cmd, u16 devid, u32 pasid,
 				  int qdep, u64 address, bool size)
 {
 	memset(cmd, 0, sizeof(*cmd));
@@ -947,7 +962,7 @@ static void build_inv_iotlb_pasid(struct iommu_cmd *cmd, u16 devid, int pasid,
 	CMD_SET_TYPE(cmd, CMD_INV_IOTLB_PAGES);
 }
 
-static void build_complete_ppr(struct iommu_cmd *cmd, u16 devid, int pasid,
+static void build_complete_ppr(struct iommu_cmd *cmd, u16 devid, u32 pasid,
 			       int status, int tag, bool gn)
 {
 	memset(cmd, 0, sizeof(*cmd));
@@ -2157,6 +2172,7 @@ static struct iommu_device *amd_iommu_probe_device(struct device *dev)
 		iommu_dev = ERR_PTR(ret);
 		iommu_ignore_device(dev);
 	} else {
+		amd_iommu_set_pci_msi_domain(dev, iommu);
 		iommu_dev = &iommu->iommu;
 	}
 
@@ -2659,7 +2675,12 @@ 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;
@@ -2781,7 +2802,7 @@ out:
 }
 EXPORT_SYMBOL(amd_iommu_domain_enable_v2);
 
-static int __flush_pasid(struct protection_domain *domain, int pasid,
+static int __flush_pasid(struct protection_domain *domain, u32 pasid,
 			 u64 address, bool size)
 {
 	struct iommu_dev_data *dev_data;
@@ -2842,13 +2863,13 @@ out:
 	return ret;
 }
 
-static int __amd_iommu_flush_page(struct protection_domain *domain, int pasid,
+static int __amd_iommu_flush_page(struct protection_domain *domain, u32 pasid,
 				  u64 address)
 {
 	return __flush_pasid(domain, pasid, address, false);
 }
 
-int amd_iommu_flush_page(struct iommu_domain *dom, int pasid,
+int amd_iommu_flush_page(struct iommu_domain *dom, u32 pasid,
 			 u64 address)
 {
 	struct protection_domain *domain = to_pdomain(dom);
@@ -2863,13 +2884,13 @@ int amd_iommu_flush_page(struct iommu_domain *dom, int pasid,
 }
 EXPORT_SYMBOL(amd_iommu_flush_page);
 
-static int __amd_iommu_flush_tlb(struct protection_domain *domain, int pasid)
+static int __amd_iommu_flush_tlb(struct protection_domain *domain, u32 pasid)
 {
 	return __flush_pasid(domain, pasid, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
 			     true);
 }
 
-int amd_iommu_flush_tlb(struct iommu_domain *dom, int pasid)
+int amd_iommu_flush_tlb(struct iommu_domain *dom, u32 pasid)
 {
 	struct protection_domain *domain = to_pdomain(dom);
 	unsigned long flags;
@@ -2883,7 +2904,7 @@ int amd_iommu_flush_tlb(struct iommu_domain *dom, int pasid)
 }
 EXPORT_SYMBOL(amd_iommu_flush_tlb);
 
-static u64 *__get_gcr3_pte(u64 *root, int level, int pasid, bool alloc)
+static u64 *__get_gcr3_pte(u64 *root, int level, u32 pasid, bool alloc)
 {
 	int index;
 	u64 *pte;
@@ -2915,7 +2936,7 @@ static u64 *__get_gcr3_pte(u64 *root, int level, int pasid, bool alloc)
 	return pte;
 }
 
-static int __set_gcr3(struct protection_domain *domain, int pasid,
+static int __set_gcr3(struct protection_domain *domain, u32 pasid,
 		      unsigned long cr3)
 {
 	struct domain_pgtable pgtable;
@@ -2934,7 +2955,7 @@ static int __set_gcr3(struct protection_domain *domain, int pasid,
 	return __amd_iommu_flush_tlb(domain, pasid);
 }
 
-static int __clear_gcr3(struct protection_domain *domain, int pasid)
+static int __clear_gcr3(struct protection_domain *domain, u32 pasid)
 {
 	struct domain_pgtable pgtable;
 	u64 *pte;
@@ -2952,7 +2973,7 @@ static int __clear_gcr3(struct protection_domain *domain, int pasid)
 	return __amd_iommu_flush_tlb(domain, pasid);
 }
 
-int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, int pasid,
+int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, u32 pasid,
 			      unsigned long cr3)
 {
 	struct protection_domain *domain = to_pdomain(dom);
@@ -2967,7 +2988,7 @@ int amd_iommu_domain_set_gcr3(struct iommu_domain *dom, int pasid,
 }
 EXPORT_SYMBOL(amd_iommu_domain_set_gcr3);
 
-int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, int pasid)
+int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, u32 pasid)
 {
 	struct protection_domain *domain = to_pdomain(dom);
 	unsigned long flags;
@@ -2981,7 +3002,7 @@ int amd_iommu_domain_clear_gcr3(struct iommu_domain *dom, int pasid)
 }
 EXPORT_SYMBOL(amd_iommu_domain_clear_gcr3);
 
-int amd_iommu_complete_ppr(struct pci_dev *pdev, int pasid,
+int amd_iommu_complete_ppr(struct pci_dev *pdev, u32 pasid,
 			   int status, int tag)
 {
 	struct iommu_dev_data *dev_data;
@@ -3292,6 +3313,7 @@ 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 +3331,18 @@ 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;
 
@@ -3505,69 +3535,51 @@ static void irte_ga_clear_allocated(struct irq_remap_table *table, int index)
 
 static int get_devid(struct irq_alloc_info *info)
 {
-	int devid = -1;
-
 	switch (info->type) {
 	case X86_IRQ_ALLOC_TYPE_IOAPIC:
-		devid     = get_ioapic_devid(info->ioapic_id);
-		break;
+	case X86_IRQ_ALLOC_TYPE_IOAPIC_GET_PARENT:
+		return get_ioapic_devid(info->devid);
 	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:
-		devid = get_device_id(&info->msi_dev->dev);
-		break;
+	case X86_IRQ_ALLOC_TYPE_HPET_GET_PARENT:
+		return get_hpet_devid(info->devid);
+	case X86_IRQ_ALLOC_TYPE_PCI_MSI:
+	case X86_IRQ_ALLOC_TYPE_PCI_MSIX:
+		return get_device_id(msi_desc_to_dev(info->desc));
 	default:
-		BUG_ON(1);
-		break;
+		WARN_ON_ONCE(1);
+		return -1;
 	}
-
-	return devid;
 }
 
-static struct irq_domain *get_ir_irq_domain(struct irq_alloc_info *info)
+static struct irq_domain *get_irq_domain_for_devid(struct irq_alloc_info *info,
+						   int devid)
 {
-	struct amd_iommu *iommu;
-	int devid;
+	struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];
 
-	if (!info)
+	if (!iommu)
 		return NULL;
 
-	devid = get_devid(info);
-	if (devid >= 0) {
-		iommu = amd_iommu_rlookup_table[devid];
-		if (iommu)
-			return iommu->ir_domain;
+	switch (info->type) {
+	case X86_IRQ_ALLOC_TYPE_IOAPIC_GET_PARENT:
+	case X86_IRQ_ALLOC_TYPE_HPET_GET_PARENT:
+		return iommu->ir_domain;
+	default:
+		WARN_ON_ONCE(1);
+		return NULL;
 	}
-
-	return NULL;
 }
 
 static struct irq_domain *get_irq_domain(struct irq_alloc_info *info)
 {
-	struct amd_iommu *iommu;
 	int devid;
 
 	if (!info)
 		return NULL;
 
-	switch (info->type) {
-	case X86_IRQ_ALLOC_TYPE_MSI:
-	case X86_IRQ_ALLOC_TYPE_MSIX:
-		devid = get_device_id(&info->msi_dev->dev);
-		if (devid < 0)
-			return NULL;
-
-		iommu = amd_iommu_rlookup_table[devid];
-		if (iommu)
-			return iommu->msi_domain;
-		break;
-	default:
-		break;
-	}
-
-	return NULL;
+	devid = get_devid(info);
+	if (devid < 0)
+		return NULL;
+	return get_irq_domain_for_devid(info, devid);
 }
 
 struct irq_remap_ops amd_iommu_irq_ops = {
@@ -3576,7 +3588,6 @@ struct irq_remap_ops amd_iommu_irq_ops = {
 	.disable		= amd_iommu_disable,
 	.reenable		= amd_iommu_reenable,
 	.enable_faulting	= amd_iommu_enable_faulting,
-	.get_ir_irq_domain	= get_ir_irq_domain,
 	.get_irq_domain		= get_irq_domain,
 };
 
@@ -3602,21 +3613,21 @@ static void irq_remapping_prepare_irte(struct amd_ir_data *data,
 	switch (info->type) {
 	case X86_IRQ_ALLOC_TYPE_IOAPIC:
 		/* Setup IOAPIC entry */
-		entry = info->ioapic_entry;
-		info->ioapic_entry = NULL;
+		entry = info->ioapic.entry;
+		info->ioapic.entry = NULL;
 		memset(entry, 0, sizeof(*entry));
 		entry->vector        = index;
 		entry->mask          = 0;
-		entry->trigger       = info->ioapic_trigger;
-		entry->polarity      = info->ioapic_polarity;
+		entry->trigger       = info->ioapic.trigger;
+		entry->polarity      = info->ioapic.polarity;
 		/* Mask level triggered irqs. */
-		if (info->ioapic_trigger)
+		if (info->ioapic.trigger)
 			entry->mask = 1;
 		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 +3671,15 @@ 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);
@@ -3696,15 +3707,16 @@ static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq,
 					iommu->irte_ops->set_allocated(table, i);
 			}
 			WARN_ON(table->min_index != 32);
-			index = info->ioapic_pin;
+			index = info->ioapic.pin;
 		} 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);
+		index = alloc_irq_index(devid, nr_irqs, align,
+					msi_desc_to_pci_dev(info->desc));
 	} else {
 		index = alloc_irq_index(devid, nr_irqs, false, NULL);
 	}
@@ -3717,8 +3729,8 @@ 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;
 		}
@@ -3826,14 +3838,18 @@ 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 +3866,18 @@ 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;