3 files changed, 52 insertions, 5 deletions

diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index 004feaed3c72..02e7c10a4224 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -1496,7 +1496,7 @@ void qi_flush_dev_iotlb_pasid(struct intel_iommu *iommu, u16 sid, u16 pfsid,
 	 * Max Invs Pending (MIP) is set to 0 for now until we have DIT in
 	 * ECAP.
 	 */
-	if (addr & GENMASK_ULL(size_order + VTD_PAGE_SHIFT, 0))
+	if (!IS_ALIGNED(addr, VTD_PAGE_SIZE << size_order))
 		pr_warn_ratelimited("Invalidate non-aligned address %llx, order %d\n",
 				    addr, size_order);
 
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 65cf06d70bf4..06b00b5363d8 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -38,7 +38,6 @@
 #include <linux/dmi.h>
 #include <linux/pci-ats.h>
 #include <linux/memblock.h>
-#include <linux/dma-map-ops.h>
 #include <linux/dma-direct.h>
 #include <linux/crash_dump.h>
 #include <linux/numa.h>
@@ -5441,6 +5440,36 @@ intel_iommu_domain_set_attr(struct iommu_domain *domain,
 	return ret;
 }
 
+static bool domain_use_flush_queue(void)
+{
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
+	bool r = true;
+
+	if (intel_iommu_strict)
+		return false;
+
+	/*
+	 * The flush queue implementation does not perform page-selective
+	 * invalidations that are required for efficient TLB flushes in virtual
+	 * environments. The benefit of batching is likely to be much lower than
+	 * the overhead of synchronizing the virtual and physical IOMMU
+	 * page-tables.
+	 */
+	rcu_read_lock();
+	for_each_active_iommu(iommu, drhd) {
+		if (!cap_caching_mode(iommu->cap))
+			continue;
+
+		pr_warn_once("IOMMU batching is disabled due to virtualization");
+		r = false;
+		break;
+	}
+	rcu_read_unlock();
+
+	return r;
+}
+
 static int
 intel_iommu_domain_get_attr(struct iommu_domain *domain,
 			    enum iommu_attr attr, void *data)
@@ -5451,7 +5480,7 @@ intel_iommu_domain_get_attr(struct iommu_domain *domain,
 	case IOMMU_DOMAIN_DMA:
 		switch (attr) {
 		case DOMAIN_ATTR_DMA_USE_FLUSH_QUEUE:
-			*(int *)data = !intel_iommu_strict;
+			*(int *)data = domain_use_flush_queue();
 			return 0;
 		default:
 			return -ENODEV;
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index 790ef3497e7e..18a9f05df407 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -118,8 +118,10 @@ void intel_svm_check(struct intel_iommu *iommu)
 	iommu->flags |= VTD_FLAG_SVM_CAPABLE;
 }
 
-static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_dev *sdev,
-				unsigned long address, unsigned long pages, int ih)
+static void __flush_svm_range_dev(struct intel_svm *svm,
+				  struct intel_svm_dev *sdev,
+				  unsigned long address,
+				  unsigned long pages, int ih)
 {
 	struct qi_desc desc;
 
@@ -170,6 +172,22 @@ static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_d
 	}
 }
 
+static void intel_flush_svm_range_dev(struct intel_svm *svm,
+				      struct intel_svm_dev *sdev,
+				      unsigned long address,
+				      unsigned long pages, int ih)
+{
+	unsigned long shift = ilog2(__roundup_pow_of_two(pages));
+	unsigned long align = (1ULL << (VTD_PAGE_SHIFT + shift));
+	unsigned long start = ALIGN_DOWN(address, align);
+	unsigned long end = ALIGN(address + (pages << VTD_PAGE_SHIFT), align);
+
+	while (start < end) {
+		__flush_svm_range_dev(svm, sdev, start, align >> VTD_PAGE_SHIFT, ih);
+		start += align;
+	}
+}
+
 static void intel_flush_svm_range(struct intel_svm *svm, unsigned long address,
 				unsigned long pages, int ih)
 {