iommu/arm-smmu: Support non-strict mode

All we need is to wire up .flush_iotlb_all properly and implement the
domain attribute, and iommu-dma and io-pgtable will do the rest for us.
The only real subtlety is documenting the barrier semantics we're
introducing between io-pgtable and the drivers for non-strict flushes.
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>

drivers/iommu/arm-smmu.c

@@ -246,6 +246,7 @@ struct arm_smmu_domain {
 	const struct iommu_gather_ops	*tlb_ops;
 	struct arm_smmu_cfg		cfg;
 	enum arm_smmu_domain_stage	stage;
+	bool				non_strict;
 	struct mutex			init_mutex; /* Protects smmu pointer */
 	spinlock_t			cb_lock; /* Serialises ATS1* ops and TLB syncs */
 	struct iommu_domain		domain;
@@ -447,7 +448,11 @@ static void arm_smmu_tlb_inv_context_s1(void *cookie)
 	struct arm_smmu_cfg *cfg = &smmu_domain->cfg;
 	void __iomem *base = ARM_SMMU_CB(smmu_domain->smmu, cfg->cbndx);
 
-	writel_relaxed(cfg->asid, base + ARM_SMMU_CB_S1_TLBIASID);
+	/*
+	 * NOTE: this is not a relaxed write; it needs to guarantee that PTEs
+	 * cleared by the current CPU are visible to the SMMU before the TLBI.
+	 */
+	writel(cfg->asid, base + ARM_SMMU_CB_S1_TLBIASID);
 	arm_smmu_tlb_sync_context(cookie);
 }
 
@@ -457,7 +462,8 @@ static void arm_smmu_tlb_inv_context_s2(void *cookie)
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	void __iomem *base = ARM_SMMU_GR0(smmu);
 
-	writel_relaxed(smmu_domain->cfg.vmid, base + ARM_SMMU_GR0_TLBIVMID);
+	/* NOTE: see above */
+	writel(smmu_domain->cfg.vmid, base + ARM_SMMU_GR0_TLBIVMID);
 	arm_smmu_tlb_sync_global(smmu);
 }
 
@@ -869,6 +875,9 @@ static int arm_smmu_init_domain_context(struct iommu_domain *domain,
 	if (smmu->features & ARM_SMMU_FEAT_COHERENT_WALK)
 		pgtbl_cfg.quirks = IO_PGTABLE_QUIRK_NO_DMA;
 
+	if (smmu_domain->non_strict)
+		pgtbl_cfg.quirks |= IO_PGTABLE_QUIRK_NON_STRICT;
+
 	smmu_domain->smmu = smmu;
 	pgtbl_ops = alloc_io_pgtable_ops(fmt, &pgtbl_cfg, smmu_domain);
 	if (!pgtbl_ops) {
@@ -1258,6 +1267,14 @@ static size_t arm_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
 	return ops->unmap(ops, iova, size);
 }
 
+static void arm_smmu_flush_iotlb_all(struct iommu_domain *domain)
+{
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+
+	if (smmu_domain->tlb_ops)
+		smmu_domain->tlb_ops->tlb_flush_all(smmu_domain);
+}
+
 static void arm_smmu_iotlb_sync(struct iommu_domain *domain)
 {
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
@@ -1476,9 +1493,8 @@ static int arm_smmu_domain_get_attr(struct iommu_domain *domain,
 {
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 
-	if (domain->type != IOMMU_DOMAIN_UNMANAGED)
-		return -EINVAL;
-
+	switch(domain->type) {
+	case IOMMU_DOMAIN_UNMANAGED:
 		switch (attr) {
 		case DOMAIN_ATTR_NESTING:
 			*(int *)data = (smmu_domain->stage == ARM_SMMU_DOMAIN_NESTED);
@@ -1486,6 +1502,19 @@ static int arm_smmu_domain_get_attr(struct iommu_domain *domain,
 		default:
 			return -ENODEV;
 		}
+		break;
+	case IOMMU_DOMAIN_DMA:
+		switch (attr) {
+		case DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE:
+			*(int *)data = smmu_domain->non_strict;
+			return 0;
+		default:
+			return -ENODEV;
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
 }
 
 static int arm_smmu_domain_set_attr(struct iommu_domain *domain,
@@ -1494,11 +1523,10 @@ static int arm_smmu_domain_set_attr(struct iommu_domain *domain,
 	int ret = 0;
 	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
 
-	if (domain->type != IOMMU_DOMAIN_UNMANAGED)
-		return -EINVAL;
-
 	mutex_lock(&smmu_domain->init_mutex);
 
+	switch(domain->type) {
+	case IOMMU_DOMAIN_UNMANAGED:
 		switch (attr) {
 		case DOMAIN_ATTR_NESTING:
 			if (smmu_domain->smmu) {
@@ -1510,12 +1538,23 @@ static int arm_smmu_domain_set_attr(struct iommu_domain *domain,
 				smmu_domain->stage = ARM_SMMU_DOMAIN_NESTED;
 			else
 				smmu_domain->stage = ARM_SMMU_DOMAIN_S1;
-
 			break;
 		default:
 			ret = -ENODEV;
 		}
-
+		break;
+	case IOMMU_DOMAIN_DMA:
+		switch (attr) {
+		case DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE:
+			smmu_domain->non_strict = *(int *)data;
+			break;
+		default:
+			ret = -ENODEV;
+		}
+		break;
+	default:
+		ret = -EINVAL;
+	}
 out_unlock:
 	mutex_unlock(&smmu_domain->init_mutex);
 	return ret;
@@ -1568,7 +1607,7 @@ static struct iommu_ops arm_smmu_ops = {
 	.attach_dev		= arm_smmu_attach_dev,
 	.map			= arm_smmu_map,
 	.unmap			= arm_smmu_unmap,
-	.flush_iotlb_all	= arm_smmu_iotlb_sync,
+	.flush_iotlb_all	= arm_smmu_flush_iotlb_all,
 	.iotlb_sync		= arm_smmu_iotlb_sync,
 	.iova_to_phys		= arm_smmu_iova_to_phys,
 	.add_device		= arm_smmu_add_device,