iommu/amd: Selective flush on unmap

Recent patch attempted to enable selective page flushes on AMD IOMMU but
neglected to adapt amd_iommu_iotlb_sync() to use the selective flushes.

Adapt amd_iommu_iotlb_sync() to use selective flushes and change
amd_iommu_unmap() to collect the flushes. As a defensive measure, to
avoid potential issues as those that the Intel IOMMU driver encountered
recently, flush the page-walk caches by always setting the "pde"
parameter. This can be removed later.

Cc: Joerg Roedel <joro@8bytes.org>
Cc: Will Deacon <will@kernel.org>
Cc: Jiajun Cao <caojiajun@vmware.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: Lu Baolu <baolu.lu@linux.intel.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Nadav Amit <namit@vmware.com>
Link: https://lore.kernel.org/r/20210723093209.714328-2-namit@vmware.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>

drivers/iommu/amd/iommu.c

@@ -2060,12 +2060,17 @@ static size_t amd_iommu_unmap(struct iommu_domain *dom, unsigned long iova,
 {
 	struct protection_domain *domain = to_pdomain(dom);
 	struct io_pgtable_ops *ops = &domain->iop.iop.ops;
+	size_t r;
 
 	if ((amd_iommu_pgtable == AMD_IOMMU_V1) &&
 	    (domain->iop.mode == PAGE_MODE_NONE))
 		return 0;
 
-	return (ops->unmap) ? ops->unmap(ops, iova, page_size, gather) : 0;
+	r = (ops->unmap) ? ops->unmap(ops, iova, page_size, gather) : 0;
+
+	iommu_iotlb_gather_add_page(dom, gather, iova, page_size);
+
+	return r;
 }
 
 static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom,
@@ -2168,7 +2173,13 @@ static void amd_iommu_flush_iotlb_all(struct iommu_domain *domain)
 static void amd_iommu_iotlb_sync(struct iommu_domain *domain,
 				 struct iommu_iotlb_gather *gather)
 {
-	amd_iommu_flush_iotlb_all(domain);
+	struct protection_domain *dom = to_pdomain(domain);
+	unsigned long flags;
+
+	spin_lock_irqsave(&dom->lock, flags);
+	__domain_flush_pages(dom, gather->start, gather->end - gather->start, 1);
+	amd_iommu_domain_flush_complete(dom);
+	spin_unlock_irqrestore(&dom->lock, flags);
 }
 
 static int amd_iommu_def_domain_type(struct device *dev)