diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 038e104b922c..840831d5d2ad 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -2266,6 +2266,12 @@ static int amd_iommu_def_domain_type(struct device *dev)
 	return 0;
 }
 
+static bool amd_iommu_enforce_cache_coherency(struct iommu_domain *domain)
+{
+	/* IOMMU_PTE_FC is always set */
+	return true;
+}
+
 const struct iommu_ops amd_iommu_ops = {
 	.capable = amd_iommu_capable,
 	.domain_alloc = amd_iommu_domain_alloc,
@@ -2288,6 +2294,7 @@ const struct iommu_ops amd_iommu_ops = {
 		.flush_iotlb_all = amd_iommu_flush_iotlb_all,
 		.iotlb_sync	= amd_iommu_iotlb_sync,
 		.free		= amd_iommu_domain_free,
+		.enforce_cache_coherency = amd_iommu_enforce_cache_coherency,
 	}
 };
 
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 0edf6084dc14..161199f62270 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -4422,7 +4422,8 @@ static int intel_iommu_map(struct iommu_domain *domain,
 		prot |= DMA_PTE_READ;
 	if (iommu_prot & IOMMU_WRITE)
 		prot |= DMA_PTE_WRITE;
-	if ((iommu_prot & IOMMU_CACHE) && dmar_domain->iommu_snooping)
+	if (((iommu_prot & IOMMU_CACHE) && dmar_domain->iommu_snooping) ||
+	    dmar_domain->force_snooping)
 		prot |= DMA_PTE_SNP;
 
 	max_addr = iova + size;
@@ -4545,6 +4546,16 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
 	return phys;
 }
 
+static bool intel_iommu_enforce_cache_coherency(struct iommu_domain *domain)
+{
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+
+	if (!dmar_domain->iommu_snooping)
+		return false;
+	dmar_domain->force_snooping = true;
+	return true;
+}
+
 static bool intel_iommu_capable(enum iommu_cap cap)
 {
 	if (cap == IOMMU_CAP_CACHE_COHERENCY)
@@ -4900,6 +4911,7 @@ const struct iommu_ops intel_iommu_ops = {
 		.iotlb_sync		= intel_iommu_tlb_sync,
 		.iova_to_phys		= intel_iommu_iova_to_phys,
 		.free			= intel_iommu_domain_free,
+		.enforce_cache_coherency = intel_iommu_enforce_cache_coherency,
 	}
 };
 
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 2f9891cb3d00..4c2baf2446c2 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -540,6 +540,7 @@ struct dmar_domain {
 	u8 has_iotlb_device: 1;
 	u8 iommu_coherency: 1;		/* indicate coherency of iommu access */
 	u8 iommu_snooping: 1;		/* indicate snooping control feature */
+	u8 force_snooping : 1;		/* Create IOPTEs with snoop control */
 
 	struct list_head devices;	/* all devices' list */
 	struct iova_domain iovad;	/* iova's that belong to this domain */
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 4123693ae319..c7ad6b10e261 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -274,6 +274,9 @@ struct iommu_ops {
  * @iotlb_sync: Flush all queued ranges from the hardware TLBs and empty flush
  *            queue
  * @iova_to_phys: translate iova to physical address
+ * @enforce_cache_coherency: Prevent any kind of DMA from bypassing IOMMU_CACHE,
+ *                           including no-snoop TLPs on PCIe or other platform
+ *                           specific mechanisms.
  * @enable_nesting: Enable nesting
  * @set_pgtable_quirks: Set io page table quirks (IO_PGTABLE_QUIRK_*)
  * @free: Release the domain after use.
@@ -302,6 +305,7 @@ struct iommu_domain_ops {
 	phys_addr_t (*iova_to_phys)(struct iommu_domain *domain,
 				    dma_addr_t iova);
 
+	bool (*enforce_cache_coherency)(struct iommu_domain *domain);
 	int (*enable_nesting)(struct iommu_domain *domain);
 	int (*set_pgtable_quirks)(struct iommu_domain *domain,
 				  unsigned long quirks);