5 files changed, 26 insertions, 4 deletions
diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h
index f696ac7c5f89..89647700bab2 100644
--- a/drivers/iommu/amd/amd_iommu_types.h
+++ b/drivers/iommu/amd/amd_iommu_types.h
@@ -409,7 +409,11 @@ extern bool amd_iommu_np_cache;
 /* Only true if all IOMMUs support device IOTLBs */
 extern bool amd_iommu_iotlb_sup;
 
-#define MAX_IRQS_PER_TABLE	256
+/*
+ * AMD IOMMU hardware only support 512 IRTEs despite
+ * the architectural limitation of 2048 entries.
+ */
+#define MAX_IRQS_PER_TABLE	512
 #define IRQ_TABLE_ALIGNMENT	128
 
 struct irq_remap_table {
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 8651f6d4dfa0..1b1ca63e6bbe 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -2525,6 +2525,9 @@ struct dmar_domain *find_domain(struct device *dev)
 {
 	struct device_domain_info *info;
 
+	if (unlikely(!dev || !dev->iommu))
+		return NULL;
+
 	if (unlikely(attach_deferred(dev)))
 		return NULL;
 
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index f1861fa3d0e4..3242ebd0bca3 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -279,6 +279,7 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
 	struct intel_iommu *iommu = device_to_iommu(dev, NULL, NULL);
 	struct intel_svm_dev *sdev = NULL;
 	struct dmar_domain *dmar_domain;
+	struct device_domain_info *info;
 	struct intel_svm *svm = NULL;
 	int ret = 0;
 
@@ -310,6 +311,10 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
 	if (data->hpasid <= 0 || data->hpasid >= PASID_MAX)
 		return -EINVAL;
 
+	info = get_domain_info(dev);
+	if (!info)
+		return -EINVAL;
+
 	dmar_domain = to_dmar_domain(domain);
 
 	mutex_lock(&pasid_mutex);
@@ -357,6 +362,7 @@ int intel_svm_bind_gpasid(struct iommu_domain *domain, struct device *dev,
 		goto out;
 	}
 	sdev->dev = dev;
+	sdev->sid = PCI_DEVID(info->bus, info->devfn);
 
 	/* Only count users if device has aux domains */
 	if (iommu_dev_feature_enabled(dev, IOMMU_DEV_FEAT_AUX))
@@ -1029,7 +1035,7 @@ no_pasid:
 			resp.qw0 = QI_PGRP_PASID(req->pasid) |
 				QI_PGRP_DID(req->rid) |
 				QI_PGRP_PASID_P(req->pasid_present) |
-				QI_PGRP_PDP(req->pasid_present) |
+				QI_PGRP_PDP(req->priv_data_present) |
 				QI_PGRP_RESP_CODE(result) |
 				QI_PGRP_RESP_TYPE;
 			resp.qw1 = QI_PGRP_IDX(req->prg_index) |
diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 7c9ea9d7874a..b34b00fadc45 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -417,7 +417,13 @@ static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data,
 				<< ARM_LPAE_PTE_ATTRINDX_SHIFT);
 	}
 
-	if (prot & IOMMU_CACHE)
+	/*
+	 * Also Mali has its own notions of shareability wherein its Inner
+	 * domain covers the cores within the GPU, and its Outer domain is
+	 * "outside the GPU" (i.e. either the Inner or System domain in CPU
+	 * terms, depending on coherency).
+	 */
+	if (prot & IOMMU_CACHE && data->iop.fmt != ARM_MALI_LPAE)
 		pte |= ARM_LPAE_PTE_SH_IS;
 	else
 		pte |= ARM_LPAE_PTE_SH_OS;
@@ -1027,6 +1033,9 @@ arm_mali_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
 	cfg->arm_mali_lpae_cfg.transtab = virt_to_phys(data->pgd) |
 					  ARM_MALI_LPAE_TTBR_READ_INNER |
 					  ARM_MALI_LPAE_TTBR_ADRMODE_TABLE;
+	if (cfg->coherent_walk)
+		cfg->arm_mali_lpae_cfg.transtab |= ARM_MALI_LPAE_TTBR_SHARE_OUTER;
+
 	return &data->iop;
 
 out_free_data:
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 8c470f451a32..b53446bb8c6b 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -2071,7 +2071,7 @@ EXPORT_SYMBOL_GPL(iommu_uapi_cache_invalidate);
 
 static int iommu_check_bind_data(struct iommu_gpasid_bind_data *data)
 {
-	u32 mask;
+	u64 mask;
 	int i;
 
 	if (data->version != IOMMU_GPASID_BIND_VERSION_1)