1 files changed, 86 insertions, 62 deletions

diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 4a314647d1f7..c3b58a8389b9 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -845,6 +845,7 @@ amd_iommu_set_pci_msi_domain(struct device *dev, struct amd_iommu *iommu) { }
 	(MMIO_STATUS_EVT_OVERFLOW_INT_MASK | \
 	 MMIO_STATUS_EVT_INT_MASK | \
 	 MMIO_STATUS_PPR_INT_MASK | \
+	 MMIO_STATUS_GALOG_OVERFLOW_MASK | \
 	 MMIO_STATUS_GALOG_INT_MASK)
 
 irqreturn_t amd_iommu_int_thread(int irq, void *data)
@@ -868,10 +869,16 @@ irqreturn_t amd_iommu_int_thread(int irq, void *data)
 		}
 
 #ifdef CONFIG_IRQ_REMAP
-		if (status & MMIO_STATUS_GALOG_INT_MASK) {
+		if (status & (MMIO_STATUS_GALOG_INT_MASK |
+			      MMIO_STATUS_GALOG_OVERFLOW_MASK)) {
 			pr_devel("Processing IOMMU GA Log\n");
 			iommu_poll_ga_log(iommu);
 		}
+
+		if (status & MMIO_STATUS_GALOG_OVERFLOW_MASK) {
+			pr_info_ratelimited("IOMMU GA Log overflow\n");
+			amd_iommu_restart_ga_log(iommu);
+		}
 #endif
 
 		if (status & MMIO_STATUS_EVT_OVERFLOW_INT_MASK) {
@@ -1175,11 +1182,11 @@ static int iommu_completion_wait(struct amd_iommu *iommu)
 	if (!iommu->need_sync)
 		return 0;
 
-	raw_spin_lock_irqsave(&iommu->lock, flags);
-
-	data = ++iommu->cmd_sem_val;
+	data = atomic64_add_return(1, &iommu->cmd_sem_val);
 	build_completion_wait(&cmd, iommu, data);
 
+	raw_spin_lock_irqsave(&iommu->lock, flags);
+
 	ret = __iommu_queue_command_sync(iommu, &cmd, false);
 	if (ret)
 		goto out_unlock;
@@ -1266,6 +1273,9 @@ static void amd_iommu_flush_irt_all(struct amd_iommu *iommu)
 	u32 devid;
 	u16 last_bdf = iommu->pci_seg->last_bdf;
 
+	if (iommu->irtcachedis_enabled)
+		return;
+
 	for (devid = 0; devid <= last_bdf; devid++)
 		iommu_flush_irt(iommu, devid);
 
@@ -2067,14 +2077,10 @@ static struct protection_domain *protection_domain_alloc(unsigned int type)
 {
 	struct io_pgtable_ops *pgtbl_ops;
 	struct protection_domain *domain;
-	int pgtable = amd_iommu_pgtable;
+	int pgtable;
 	int mode = DEFAULT_PGTABLE_LEVEL;
 	int ret;
 
-	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
-	if (!domain)
-		return NULL;
-
 	/*
 	 * Force IOMMU v1 page table when iommu=pt and
 	 * when allocating domain for pass-through devices.
@@ -2084,8 +2090,16 @@ static struct protection_domain *protection_domain_alloc(unsigned int type)
 		mode = PAGE_MODE_NONE;
 	} else if (type == IOMMU_DOMAIN_UNMANAGED) {
 		pgtable = AMD_IOMMU_V1;
+	} else if (type == IOMMU_DOMAIN_DMA || type == IOMMU_DOMAIN_DMA_FQ) {
+		pgtable = amd_iommu_pgtable;
+	} else {
+		return NULL;
 	}
 
+	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
+	if (!domain)
+		return NULL;
+
 	switch (pgtable) {
 	case AMD_IOMMU_V1:
 		ret = protection_domain_init_v1(domain, mode);
@@ -2118,6 +2132,15 @@ out_err:
 	return NULL;
 }
 
+static inline u64 dma_max_address(void)
+{
+	if (amd_iommu_pgtable == AMD_IOMMU_V1)
+		return ~0ULL;
+
+	/* V2 with 4/5 level page table */
+	return ((1ULL << PM_LEVEL_SHIFT(amd_iommu_gpt_level)) - 1);
+}
+
 static struct iommu_domain *amd_iommu_domain_alloc(unsigned type)
 {
 	struct protection_domain *domain;
@@ -2134,7 +2157,7 @@ static struct iommu_domain *amd_iommu_domain_alloc(unsigned type)
 		return NULL;
 
 	domain->domain.geometry.aperture_start = 0;
-	domain->domain.geometry.aperture_end   = ~0ULL;
+	domain->domain.geometry.aperture_end   = dma_max_address();
 	domain->domain.geometry.force_aperture = true;
 
 	return &domain->domain;
@@ -2293,6 +2316,8 @@ static bool amd_iommu_capable(struct device *dev, enum iommu_cap cap)
 		return amdr_ivrs_remap_support;
 	case IOMMU_CAP_ENFORCE_CACHE_COHERENCY:
 		return true;
+	case IOMMU_CAP_DEFERRED_FLUSH:
+		return true;
 	default:
 		break;
 	}
@@ -2387,7 +2412,7 @@ static void amd_iommu_iotlb_sync(struct iommu_domain *domain,
 	unsigned long flags;
 
 	spin_lock_irqsave(&dom->lock, flags);
-	domain_flush_pages(dom, gather->start, gather->end - gather->start, 1);
+	domain_flush_pages(dom, gather->start, gather->end - gather->start + 1, 1);
 	amd_iommu_domain_flush_complete(dom);
 	spin_unlock_irqrestore(&dom->lock, flags);
 }
@@ -2802,6 +2827,32 @@ EXPORT_SYMBOL(amd_iommu_device_info);
 static struct irq_chip amd_ir_chip;
 static DEFINE_SPINLOCK(iommu_table_lock);
 
+static void iommu_flush_irt_and_complete(struct amd_iommu *iommu, u16 devid)
+{
+	int ret;
+	u64 data;
+	unsigned long flags;
+	struct iommu_cmd cmd, cmd2;
+
+	if (iommu->irtcachedis_enabled)
+		return;
+
+	build_inv_irt(&cmd, devid);
+	data = atomic64_add_return(1, &iommu->cmd_sem_val);
+	build_completion_wait(&cmd2, iommu, data);
+
+	raw_spin_lock_irqsave(&iommu->lock, flags);
+	ret = __iommu_queue_command_sync(iommu, &cmd, true);
+	if (ret)
+		goto out;
+	ret = __iommu_queue_command_sync(iommu, &cmd2, false);
+	if (ret)
+		goto out;
+	wait_on_sem(iommu, data);
+out:
+	raw_spin_unlock_irqrestore(&iommu->lock, flags);
+}
+
 static void set_dte_irq_entry(struct amd_iommu *iommu, u16 devid,
 			      struct irq_remap_table *table)
 {
@@ -3001,12 +3052,12 @@ out:
 }
 
 static int modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index,
-			  struct irte_ga *irte, struct amd_ir_data *data)
+			  struct irte_ga *irte)
 {
-	bool ret;
 	struct irq_remap_table *table;
-	unsigned long flags;
 	struct irte_ga *entry;
+	unsigned long flags;
+	u128 old;
 
 	table = get_irq_table(iommu, devid);
 	if (!table)
@@ -3017,24 +3068,18 @@ static int modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index,
 	entry = (struct irte_ga *)table->table;
 	entry = &entry[index];
 
-	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;
+	old = entry->irte;
+	WARN_ON(!try_cmpxchg128(&entry->irte, &old, irte->irte));
 
 	raw_spin_unlock_irqrestore(&table->lock, flags);
 
-	iommu_flush_irt(iommu, devid);
-	iommu_completion_wait(iommu);
+	iommu_flush_irt_and_complete(iommu, devid);
 
 	return 0;
 }
@@ -3053,8 +3098,7 @@ static int modify_irte(struct amd_iommu *iommu,
 	table->table[index] = irte->val;
 	raw_spin_unlock_irqrestore(&table->lock, flags);
 
-	iommu_flush_irt(iommu, devid);
-	iommu_completion_wait(iommu);
+	iommu_flush_irt_and_complete(iommu, devid);
 
 	return 0;
 }
@@ -3072,8 +3116,7 @@ static void free_irte(struct amd_iommu *iommu, u16 devid, int index)
 	iommu->irte_ops->clear_allocated(table, index);
 	raw_spin_unlock_irqrestore(&table->lock, flags);
 
-	iommu_flush_irt(iommu, devid);
-	iommu_completion_wait(iommu);
+	iommu_flush_irt_and_complete(iommu, devid);
 }
 
 static void irte_prepare(void *entry,
@@ -3119,7 +3162,7 @@ static void irte_ga_activate(struct amd_iommu *iommu, void *entry, u16 devid, u1
 	struct irte_ga *irte = (struct irte_ga *) entry;
 
 	irte->lo.fields_remap.valid = 1;
-	modify_irte_ga(iommu, devid, index, irte, NULL);
+	modify_irte_ga(iommu, devid, index, irte);
 }
 
 static void irte_deactivate(struct amd_iommu *iommu, void *entry, u16 devid, u16 index)
@@ -3135,7 +3178,7 @@ static void irte_ga_deactivate(struct amd_iommu *iommu, void *entry, u16 devid,
 	struct irte_ga *irte = (struct irte_ga *) entry;
 
 	irte->lo.fields_remap.valid = 0;
-	modify_irte_ga(iommu, devid, index, irte, NULL);
+	modify_irte_ga(iommu, devid, index, irte);
 }
 
 static void irte_set_affinity(struct amd_iommu *iommu, void *entry, u16 devid, u16 index,
@@ -3159,7 +3202,7 @@ static void irte_ga_set_affinity(struct amd_iommu *iommu, void *entry, u16 devid
 					APICID_TO_IRTE_DEST_LO(dest_apicid);
 		irte->hi.fields.destination =
 					APICID_TO_IRTE_DEST_HI(dest_apicid);
-		modify_irte_ga(iommu, devid, index, irte, NULL);
+		modify_irte_ga(iommu, devid, index, irte);
 	}
 }
 
@@ -3493,8 +3536,7 @@ int amd_iommu_activate_guest_mode(void *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)
+	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) || !entry)
 		return 0;
 
 	valid = entry->lo.fields_vapic.valid;
@@ -3510,7 +3552,7 @@ int amd_iommu_activate_guest_mode(void *data)
 	entry->lo.fields_vapic.ga_tag      = ir_data->ga_tag;
 
 	return modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid,
-			      ir_data->irq_2_irte.index, entry, ir_data);
+			      ir_data->irq_2_irte.index, entry);
 }
 EXPORT_SYMBOL(amd_iommu_activate_guest_mode);
 
@@ -3540,7 +3582,7 @@ int amd_iommu_deactivate_guest_mode(void *data)
 				APICID_TO_IRTE_DEST_HI(cfg->dest_apicid);
 
 	return modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid,
-			      ir_data->irq_2_irte.index, entry, ir_data);
+			      ir_data->irq_2_irte.index, entry);
 }
 EXPORT_SYMBOL(amd_iommu_deactivate_guest_mode);
 
@@ -3702,44 +3744,26 @@ int amd_iommu_create_irq_domain(struct amd_iommu *iommu)
 
 int amd_iommu_update_ga(int cpu, bool is_run, void *data)
 {
-	unsigned long flags;
-	struct amd_iommu *iommu;
-	struct irq_remap_table *table;
 	struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
-	int devid = ir_data->irq_2_irte.devid;
 	struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
-	struct irte_ga *ref = (struct irte_ga *) ir_data->ref;
 
 	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) ||
-	    !ref || !entry || !entry->lo.fields_vapic.guest_mode)
+	    !entry || !entry->lo.fields_vapic.guest_mode)
 		return 0;
 
-	iommu = ir_data->iommu;
-	if (!iommu)
-		return -ENODEV;
-
-	table = get_irq_table(iommu, devid);
-	if (!table)
+	if (!ir_data->iommu)
 		return -ENODEV;
 
-	raw_spin_lock_irqsave(&table->lock, flags);
-
-	if (ref->lo.fields_vapic.guest_mode) {
-		if (cpu >= 0) {
-			ref->lo.fields_vapic.destination =
-						APICID_TO_IRTE_DEST_LO(cpu);
-			ref->hi.fields.destination =
-						APICID_TO_IRTE_DEST_HI(cpu);
-		}
-		ref->lo.fields_vapic.is_run = is_run;
-		barrier();
+	if (cpu >= 0) {
+		entry->lo.fields_vapic.destination =
+					APICID_TO_IRTE_DEST_LO(cpu);
+		entry->hi.fields.destination =
+					APICID_TO_IRTE_DEST_HI(cpu);
 	}
+	entry->lo.fields_vapic.is_run = is_run;
 
-	raw_spin_unlock_irqrestore(&table->lock, flags);
-
-	iommu_flush_irt(iommu, devid);
-	iommu_completion_wait(iommu);
-	return 0;
+	return modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid,
+			      ir_data->irq_2_irte.index, entry);
 }
 EXPORT_SYMBOL(amd_iommu_update_ga);
 #endif