iommu/vt-d: Remove global page flush support

Global pages support is removed from VT-d spec 3.0. Since global pages G
flag only affects first-level paging structures and because DMA request
with PASID are only supported by VT-d spec. 3.0 and onward, we can
safely remove global pages support.

For kernel shared virtual address IOTLB invalidation, PASID
granularity and page selective within PASID will be used. There is
no global granularity supported. Without this fix, IOTLB invalidation
will cause invalid descriptor error in the queued invalidation (QI)
interface.

Fixes: 1c4f88b7f1f9 ("iommu/vt-d: Shared virtual address in scalable mode")
Reported-by: Sanjay K Kumar <sanjay.k.kumar@intel.com>
Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>

1 files changed, 15 insertions, 21 deletions

diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c
index 780de0caafe8..9b159132405d 100644
--- a/drivers/iommu/intel-svm.c
+++ b/drivers/iommu/intel-svm.c
@@ -100,24 +100,19 @@ int intel_svm_finish_prq(struct intel_iommu *iommu)
 }
 
 static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_dev *sdev,
-				       unsigned long address, unsigned long pages, int ih, int gl)
+				unsigned long address, unsigned long pages, int ih)
 {
 	struct qi_desc desc;
 
-	if (pages == -1) {
-		/* For global kernel pages we have to flush them in *all* PASIDs
-		 * because that's the only option the hardware gives us. Despite
-		 * the fact that they are actually only accessible through one. */
-		if (gl)
-			desc.qw0 = QI_EIOTLB_PASID(svm->pasid) |
-					QI_EIOTLB_DID(sdev->did) |
-					QI_EIOTLB_GRAN(QI_GRAN_ALL_ALL) |
-					QI_EIOTLB_TYPE;
-		else
-			desc.qw0 = QI_EIOTLB_PASID(svm->pasid) |
-					QI_EIOTLB_DID(sdev->did) |
-					QI_EIOTLB_GRAN(QI_GRAN_NONG_PASID) |
-					QI_EIOTLB_TYPE;
+	/*
+	 * Do PASID granu IOTLB invalidation if page selective capability is
+	 * not available.
+	 */
+	if (pages == -1 || !cap_pgsel_inv(svm->iommu->cap)) {
+		desc.qw0 = QI_EIOTLB_PASID(svm->pasid) |
+			QI_EIOTLB_DID(sdev->did) |
+			QI_EIOTLB_GRAN(QI_GRAN_NONG_PASID) |
+			QI_EIOTLB_TYPE;
 		desc.qw1 = 0;
 	} else {
 		int mask = ilog2(__roundup_pow_of_two(pages));
@@ -127,7 +122,6 @@ static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_d
 				QI_EIOTLB_GRAN(QI_GRAN_PSI_PASID) |
 				QI_EIOTLB_TYPE;
 		desc.qw1 = QI_EIOTLB_ADDR(address) |
-				QI_EIOTLB_GL(gl) |
 				QI_EIOTLB_IH(ih) |
 				QI_EIOTLB_AM(mask);
 	}
@@ -162,13 +156,13 @@ static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_d
 }
 
 static void intel_flush_svm_range(struct intel_svm *svm, unsigned long address,
-				  unsigned long pages, int ih, int gl)
+				unsigned long pages, int ih)
 {
 	struct intel_svm_dev *sdev;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(sdev, &svm->devs, list)
-		intel_flush_svm_range_dev(svm, sdev, address, pages, ih, gl);
+		intel_flush_svm_range_dev(svm, sdev, address, pages, ih);
 	rcu_read_unlock();
 }
 
@@ -180,7 +174,7 @@ static void intel_invalidate_range(struct mmu_notifier *mn,
 	struct intel_svm *svm = container_of(mn, struct intel_svm, notifier);
 
 	intel_flush_svm_range(svm, start,
-			      (end - start + PAGE_SIZE - 1) >> VTD_PAGE_SHIFT, 0, 0);
+			      (end - start + PAGE_SIZE - 1) >> VTD_PAGE_SHIFT, 0);
 }
 
 static void intel_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
@@ -203,7 +197,7 @@ static void intel_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
 	rcu_read_lock();
 	list_for_each_entry_rcu(sdev, &svm->devs, list) {
 		intel_pasid_tear_down_entry(svm->iommu, sdev->dev, svm->pasid);
-		intel_flush_svm_range_dev(svm, sdev, 0, -1, 0, !svm->mm);
+		intel_flush_svm_range_dev(svm, sdev, 0, -1, 0);
 	}
 	rcu_read_unlock();
 
@@ -425,7 +419,7 @@ int intel_svm_unbind_mm(struct device *dev, int pasid)
 				 * large and has to be physically contiguous. So it's
 				 * hard to be as defensive as we might like. */
 				intel_pasid_tear_down_entry(iommu, dev, svm->pasid);
-				intel_flush_svm_range_dev(svm, sdev, 0, -1, 0, !svm->mm);
+				intel_flush_svm_range_dev(svm, sdev, 0, -1, 0);
 				kfree_rcu(sdev, rcu);
 
 				if (list_empty(&svm->devs)) {