iommu/arm-smmu-v3: Report IOMMU_CAP_ENFORCE_CACHE_COHERENCY for CANWBS

HW with CANWBS is always cache coherent and ignores PCI No Snoop requests
as well. This meets the requirement for IOMMU_CAP_ENFORCE_CACHE_COHERENCY,
so let's return it.

Implement the enforce_cache_coherency() op to reject attaching devices
that don't have CANWBS.

Reviewed-by: Nicolin Chen <nicolinc@nvidia.com>
Reviewed-by: Mostafa Saleh <smostafa@google.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Jerry Snitselaar <jsnitsel@redhat.com>
Reviewed-by: Donald Dutile <ddutile@redhat.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/4-v4-9e99b76f3518+3a8-smmuv3_nesting_jgg@nvidia.com
Signed-off-by: Will Deacon <will@kernel.org>

Author: jgunthorpe

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c

@@ -2293,6 +2293,8 @@ static bool arm_smmu_capable(struct device *dev, enum iommu_cap cap)
 	case IOMMU_CAP_CACHE_COHERENCY:
 		/* Assume that a coherent TCU implies coherent TBUs */
 		return master->smmu->features & ARM_SMMU_FEAT_COHERENCY;
+	case IOMMU_CAP_ENFORCE_CACHE_COHERENCY:
+		return arm_smmu_master_canwbs(master);
 	case IOMMU_CAP_NOEXEC:
 	case IOMMU_CAP_DEFERRED_FLUSH:
 		return true;
@@ -2303,6 +2305,26 @@ static bool arm_smmu_capable(struct device *dev, enum iommu_cap cap)
 	}
 }
 
+static bool arm_smmu_enforce_cache_coherency(struct iommu_domain *domain)
+{
+	struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain);
+	struct arm_smmu_master_domain *master_domain;
+	unsigned long flags;
+	bool ret = true;
+
+	spin_lock_irqsave(&smmu_domain->devices_lock, flags);
+	list_for_each_entry(master_domain, &smmu_domain->devices,
+			    devices_elm) {
+		if (!arm_smmu_master_canwbs(master_domain->master)) {
+			ret = false;
+			break;
+		}
+	}
+	smmu_domain->enforce_cache_coherency = ret;
+	spin_unlock_irqrestore(&smmu_domain->devices_lock, flags);
+	return ret;
+}
+
 struct arm_smmu_domain *arm_smmu_domain_alloc(void)
 {
 	struct arm_smmu_domain *smmu_domain;
@@ -2731,6 +2753,14 @@ static int arm_smmu_attach_prepare(struct arm_smmu_attach_state *state,
 		 * one of them.
 		 */
 		spin_lock_irqsave(&smmu_domain->devices_lock, flags);
+		if (smmu_domain->enforce_cache_coherency &&
+		    !arm_smmu_master_canwbs(master)) {
+			spin_unlock_irqrestore(&smmu_domain->devices_lock,
+					       flags);
+			kfree(master_domain);
+			return -EINVAL;
+		}
+
 		if (state->ats_enabled)
 			atomic_inc(&smmu_domain->nr_ats_masters);
 		list_add(&master_domain->devices_elm, &smmu_domain->devices);
@@ -3493,6 +3523,7 @@ static struct iommu_ops arm_smmu_ops = {
 	.owner			= THIS_MODULE,
 	.default_domain_ops = &(const struct iommu_domain_ops) {
 		.attach_dev		= arm_smmu_attach_dev,
+		.enforce_cache_coherency = arm_smmu_enforce_cache_coherency,
 		.set_dev_pasid		= arm_smmu_s1_set_dev_pasid,
 		.map_pages		= arm_smmu_map_pages,
 		.unmap_pages		= arm_smmu_unmap_pages,

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h

@@ -811,6 +811,7 @@ struct arm_smmu_domain {
 	/* List of struct arm_smmu_master_domain */
 	struct list_head		devices;
 	spinlock_t			devices_lock;
+	bool				enforce_cache_coherency : 1;
 
 	struct mmu_notifier		mmu_notifier;
 };
@@ -893,6 +894,12 @@ int arm_smmu_init_one_queue(struct arm_smmu_device *smmu,
 int arm_smmu_cmdq_init(struct arm_smmu_device *smmu,
 		       struct arm_smmu_cmdq *cmdq);
 
+static inline bool arm_smmu_master_canwbs(struct arm_smmu_master *master)
+{
+	return dev_iommu_fwspec_get(master->dev)->flags &
+	       IOMMU_FWSPEC_PCI_RC_CANWBS;
+}
+
 #ifdef CONFIG_ARM_SMMU_V3_SVA
 bool arm_smmu_sva_supported(struct arm_smmu_device *smmu);
 bool arm_smmu_master_sva_supported(struct arm_smmu_master *master);