diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index af002425aa65..5decaca14058 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -617,7 +617,6 @@ static unsigned long domain_super_pgsize_bitmap(struct dmar_domain *domain)
 static void domain_update_iommu_cap(struct dmar_domain *domain)
 {
 	domain_update_iommu_coherency(domain);
-	domain->iommu_snooping = domain_update_iommu_snooping(NULL);
 	domain->iommu_superpage = domain_update_iommu_superpage(domain, NULL);
 
 	/*
@@ -4280,7 +4279,6 @@ static int md_domain_init(struct dmar_domain *domain, int guest_width)
 	domain->agaw = width_to_agaw(adjust_width);
 
 	domain->iommu_coherency = false;
-	domain->iommu_snooping = false;
 	domain->iommu_superpage = 0;
 	domain->max_addr = 0;
 
@@ -4419,8 +4417,7 @@ 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) ||
-	    dmar_domain->force_snooping)
+	if (dmar_domain->force_snooping)
 		prot |= DMA_PTE_SNP;
 
 	max_addr = iova + size;
@@ -4547,7 +4544,7 @@ 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)
+	if (!domain_update_iommu_snooping(NULL))
 		return false;
 	dmar_domain->force_snooping = true;
 	return true;
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index a85c95e7db6b..aa5e94c2f4e6 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -85,8 +85,8 @@ struct vfio_domain {
 	struct iommu_domain	*domain;
 	struct list_head	next;
 	struct list_head	group_list;
-	int			prot;		/* IOMMU_CACHE */
-	bool			fgsp;		/* Fine-grained super pages */
+	bool			fgsp : 1;	/* Fine-grained super pages */
+	bool			enforce_cache_coherency : 1;
 };
 
 struct vfio_dma {
@@ -1475,7 +1475,7 @@ static int vfio_iommu_map(struct vfio_iommu *iommu, dma_addr_t iova,
 
 	list_for_each_entry(d, &iommu->domain_list, next) {
 		ret = iommu_map(d->domain, iova, (phys_addr_t)pfn << PAGE_SHIFT,
-				npage << PAGE_SHIFT, prot | d->prot);
+				npage << PAGE_SHIFT, prot | IOMMU_CACHE);
 		if (ret)
 			goto unwind;
 
@@ -1785,7 +1785,7 @@ static int vfio_iommu_replay(struct vfio_iommu *iommu,
 			}
 
 			ret = iommu_map(domain->domain, iova, phys,
-					size, dma->prot | domain->prot);
+					size, dma->prot | IOMMU_CACHE);
 			if (ret) {
 				if (!dma->iommu_mapped) {
 					vfio_unpin_pages_remote(dma, iova,
@@ -1873,7 +1873,7 @@ static void vfio_test_domain_fgsp(struct vfio_domain *domain)
 		return;
 
 	ret = iommu_map(domain->domain, 0, page_to_phys(pages), PAGE_SIZE * 2,
-			IOMMU_READ | IOMMU_WRITE | domain->prot);
+			IOMMU_READ | IOMMU_WRITE | IOMMU_CACHE);
 	if (!ret) {
 		size_t unmapped = iommu_unmap(domain->domain, 0, PAGE_SIZE);
 
@@ -2378,8 +2378,15 @@ rhel_mdev_iommu_device:
 		goto out_detach;
 	}
 
-	if (iommu_capable(bus, IOMMU_CAP_CACHE_COHERENCY))
-		domain->prot |= IOMMU_CACHE;
+	/*
+	 * If the IOMMU can block non-coherent operations (ie PCIe TLPs with
+	 * no-snoop set) then VFIO always turns this feature on because on Intel
+	 * platforms it optimizes KVM to disable wbinvd emulation.
+	 */
+	if (domain->domain->ops->enforce_cache_coherency)
+		domain->enforce_cache_coherency =
+			domain->domain->ops->enforce_cache_coherency(
+				domain->domain);
 
 	/*
 	 * Try to match an existing compatible domain.  We don't want to
@@ -2390,7 +2397,8 @@ rhel_mdev_iommu_device:
 	 */
 	list_for_each_entry(d, &iommu->domain_list, next) {
 		if (d->domain->ops == domain->domain->ops &&
-		    d->prot == domain->prot) {
+		    d->enforce_cache_coherency ==
+			    domain->enforce_cache_coherency) {
 			vfio_iommu_detach_group(domain, group);
 			if (!vfio_iommu_attach_group(d, group)) {
 				list_add(&group->next, &d->group_list);
@@ -2720,14 +2728,14 @@ static void vfio_iommu_type1_release(void *iommu_data)
 	kfree(iommu);
 }
 
-static int vfio_domains_have_iommu_cache(struct vfio_iommu *iommu)
+static int vfio_domains_have_enforce_cache_coherency(struct vfio_iommu *iommu)
 {
 	struct vfio_domain *domain;
 	int ret = 1;
 
 	mutex_lock(&iommu->lock);
 	list_for_each_entry(domain, &iommu->domain_list, next) {
-		if (!(domain->prot & IOMMU_CACHE)) {
+		if (!(domain->enforce_cache_coherency)) {
 			ret = 0;
 			break;
 		}
@@ -2750,7 +2758,7 @@ static int vfio_iommu_type1_check_extension(struct vfio_iommu *iommu,
 	case VFIO_DMA_CC_IOMMU:
 		if (!iommu)
 			return 0;
-		return vfio_domains_have_iommu_cache(iommu);
+		return vfio_domains_have_enforce_cache_coherency(iommu);
 	default:
 		return 0;
 	}
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index a4f43d3f1be8..d3f21369691e 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -539,7 +539,6 @@ 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 */