Merge tag 'iommu-fixes-v6.19-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/iommu/linux

Pull iommu fixes from Joerg Roedel:

 - Fix a performance regression cause by the new Generic IO-Page-Table
   code detected in Intel VT-d driver

 - Command queue flushing fix for NVidia version of the ARM-SMMU-v3

* tag 'iommu-fixes-v6.19-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/iommu/linux:
  iommu/tegra241-cmdqv: Reset VCMDQ in tegra241_vcmdq_hw_init_user()
  iommupt: Only cache flush memory changed by unmap

Author: torvalds

drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c

@@ -1078,6 +1078,9 @@ static int tegra241_vcmdq_hw_init_user(struct tegra241_vcmdq *vcmdq)
 {
 	char header[64];
 
+	/* Reset VCMDQ */
+	tegra241_vcmdq_hw_deinit(vcmdq);
+
 	/* Configure the vcmdq only; User space does the enabling */
 	writeq_relaxed(vcmdq->cmdq.q.q_base, REG_VCMDQ_PAGE1(vcmdq, BASE));
 

drivers/iommu/generic_pt/iommu_pt.h

@@ -931,6 +931,8 @@ static __maybe_unused int __unmap_range(struct pt_range *range, void *arg,
 					struct pt_table_p *table)
 {
 	struct pt_state pts = pt_init(range, level, table);
+	unsigned int flush_start_index = UINT_MAX;
+	unsigned int flush_end_index = UINT_MAX;
 	struct pt_unmap_args *unmap = arg;
 	unsigned int num_oas = 0;
 	unsigned int start_index;
@@ -986,6 +988,9 @@ static __maybe_unused int __unmap_range(struct pt_range *range, void *arg,
 				iommu_pages_list_add(&unmap->free_list,
 						     pts.table_lower);
 				pt_clear_entries(&pts, ilog2(1));
+				if (pts.index < flush_start_index)
+					flush_start_index = pts.index;
+				flush_end_index = pts.index + 1;
 			}
 			pts.index++;
 		} else {
@@ -999,15 +1004,19 @@ static __maybe_unused int __unmap_range(struct pt_range *range, void *arg,
 			num_contig_lg2 = pt_entry_num_contig_lg2(&pts);
 			pt_clear_entries(&pts, num_contig_lg2);
 			num_oas += log2_to_int(num_contig_lg2);
+			if (pts.index < flush_start_index)
+				flush_start_index = pts.index;
 			pts.index += log2_to_int(num_contig_lg2);
+			flush_end_index = pts.index;
 		}
 		if (pts.index >= pts.end_index)
 			break;
 		pts.type = pt_load_entry_raw(&pts);
 	} while (true);
 
 	unmap->unmapped += log2_mul(num_oas, pt_table_item_lg2sz(&pts));
-	flush_writes_range(&pts, start_index, pts.index);
+	if (flush_start_index != flush_end_index)
+		flush_writes_range(&pts, flush_start_index, flush_end_index);
 
 	return ret;
 }