Merge tag 'iommu-updates-v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu updates from Joerg Roedel:
 "Core changes:
   - iova_magazine_alloc() optimization
   - Make flush-queue an IOMMU driver capability
   - Consolidate the error handling around device attachment

  AMD IOMMU changes:
   - AVIC Interrupt Remapping Improvements
   - Some minor fixes and cleanups

  Intel VT-d changes from Lu Baolu:
   - Small and misc cleanups

  ARM-SMMU changes from Will Deacon:
   - Device-tree binding updates:
      - Add missing clocks for SC8280XP and SA8775 Adreno SMMUs
      - Add two new Qualcomm SMMUs in SDX75 and SM6375
   - Workarounds for Arm MMU-700 errata:
      - 1076982: Avoid use of SEV-based cmdq wakeup
      - 2812531: Terminate command batches with a CMD_SYNC
      - Enforce single-stage translation to avoid nesting-related errata
   - Set the correct level hint for range TLB invalidation on teardown

  .. and some other minor fixes and cleanups (including Freescale PAMU
  and virtio-iommu changes)"

* tag 'iommu-updates-v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (50 commits)
  iommu/vt-d: Remove commented-out code
  iommu/vt-d: Remove two WARN_ON in domain_context_mapping_one()
  iommu/vt-d: Handle the failure case of dmar_reenable_qi()
  iommu/vt-d: Remove unnecessary (void*) conversions
  iommu/amd: Remove extern from function prototypes
  iommu/amd: Use BIT/BIT_ULL macro to define bit fields
  iommu/amd: Fix DTE_IRQ_PHYS_ADDR_MASK macro
  iommu/amd: Fix compile error for unused function
  iommu/amd: Improving Interrupt Remapping Table Invalidation
  iommu/amd: Do not Invalidate IRT when IRTE caching is disabled
  iommu/amd: Introduce Disable IRTE Caching Support
  iommu/amd: Remove the unused struct amd_ir_data.ref
  iommu/amd: Switch amd_iommu_update_ga() to use modify_irte_ga()
  iommu/arm-smmu-v3: Set TTL invalidation hint better
  iommu/arm-smmu-v3: Document nesting-related errata
  iommu/arm-smmu-v3: Add explicit feature for nesting
  iommu/arm-smmu-v3: Document MMU-700 erratum 2812531
  iommu/arm-smmu-v3: Work around MMU-600 erratum 1076982
  dt-bindings: arm-smmu: Add SDX75 SMMU compatible
  dt-bindings: arm-smmu: Add SM6375 GPU SMMU
  ...

drivers/iommu/amd/iommu.c

@@ -1182,11 +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;
@@ -1273,6 +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);
 
@@ -2313,6 +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;
 	}
@@ -2822,6 +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)
 {
@@ -3021,7 +3052,7 @@ 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)
 {
 	struct irq_remap_table *table;
 	struct irte_ga *entry;
@@ -3046,13 +3077,9 @@ static int modify_irte_ga(struct amd_iommu *iommu, u16 devid, int index,
 	old = entry->irte;
 	WARN_ON(!try_cmpxchg128(&entry->irte, &old, irte->irte));
 
-	if (data)
-		data->ref = entry;
-
 	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;
 }
@@ -3071,8 +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;
 }
@@ -3090,8 +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,
@@ -3137,7 +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)
@@ -3153,7 +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,
@@ -3177,7 +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);
 	}
 }
 
@@ -3527,7 +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);
 
@@ -3557,7 +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);
 
@@ -3719,44 +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)
+	if (!ir_data->iommu)
 		return -ENODEV;
 
-	table = get_irq_table(iommu, devid);
-	if (!table)
-		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