[PATCH v2 3/8] iommupt: Add PT_FEAT_DETAILED_GATHER

[Jason Gunthorpe]

Generating the ARM SMMUv3 and RISC-V invalidation commands optimally
requires some additional details from iommupt:

- leaf_levels_bitmap is used to compute the ARM Range Invalidation
  Table Top Level hint

- leaf_levels_bitmap is also used to compute the stride when
  generating single invalidations to invalidate once per leaf

- table_levels_bitmap also computes the ARM TTL for future cases when
  there are no leaves

Put these under a feature since only two drivers need to calculate
them.

This is also useful for the coming kunit iotlb invalidation test to
know more about what invalidation is happening.

Signed-off-by: Jason Gunthorpe <jgg at nvidia.com>
---
 drivers/iommu/generic_pt/iommu_pt.h | 23 ++++++++++++++++++++++
 include/linux/generic_pt/common.h   |  5 +++++
 include/linux/iommu.h               | 30 ++++++++++++++++++++++++-----
 3 files changed, 53 insertions(+), 5 deletions(-)

diff --git a/drivers/iommu/generic_pt/iommu_pt.h b/drivers/iommu/generic_pt/iommu_pt.h
index 5ec135cf43e2d6..61c6d79c712cfa 100644
--- a/drivers/iommu/generic_pt/iommu_pt.h
+++ b/drivers/iommu/generic_pt/iommu_pt.h
@@ -43,6 +43,8 @@ static void flush_writes_item(const struct pt_state *pts)
 struct iommupt_pending_gather {
 	struct iommu_iotlb_gather *iotlb_gather;
 	struct iommu_pages_list free_list;
+	u8 leaf_levels_bitmap;
+	u8 table_levels_bitmap;
 };
 
 static void gather_add_table(struct iommupt_pending_gather *pending,
@@ -50,6 +52,17 @@ static void gather_add_table(struct iommupt_pending_gather *pending,
 			     struct pt_table_p *table)
 {
 	iommu_pages_list_add(&pending->free_list, table);
+	if (pts_feature(pts, PT_FEAT_DETAILED_GATHER))
+		pending->table_levels_bitmap |= BIT(pts->level);
+}
+
+static void gather_add_leaf(struct iommupt_pending_gather *pending,
+			    const struct pt_state *pts)
+{
+	if (!pts_feature(pts, PT_FEAT_DETAILED_GATHER))
+		return;
+
+	pending->leaf_levels_bitmap |= BIT(pts->level);
 }
 
 static void gather_range_pending(struct iommupt_pending_gather *pending,
@@ -86,6 +99,15 @@ static void gather_range_pending(struct iommupt_pending_gather *pending,
 
 	iommu_pages_list_splice(&pending->free_list, &iotlb_gather->freelist);
 	INIT_LIST_HEAD(&pending->free_list.pages);
+
+	if (pt_feature(common, PT_FEAT_DETAILED_GATHER)) {
+		iotlb_gather->pt.leaf_levels_bitmap |=
+			pending->leaf_levels_bitmap;
+		iotlb_gather->pt.table_levels_bitmap |=
+			pending->table_levels_bitmap;
+		pending->leaf_levels_bitmap = 0;
+		pending->table_levels_bitmap = 0;
+	}
 }
 
 #define DOMAIN_NS(op) CONCATENATE(CONCATENATE(pt_iommu_, PTPFX), op)
@@ -1059,6 +1081,7 @@ 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);
+			gather_add_leaf(&unmap->pending, &pts);
 			num_oas += log2_to_int(num_contig_lg2);
 			if (pts.index < flush_start_index)
 				flush_start_index = pts.index;
diff --git a/include/linux/generic_pt/common.h b/include/linux/generic_pt/common.h
index fc5d0b5edadc08..230347f00353bc 100644
--- a/include/linux/generic_pt/common.h
+++ b/include/linux/generic_pt/common.h
@@ -134,6 +134,11 @@ enum pt_features {
 	 * significant amount of page table.
 	 */
 	PT_FEAT_FLUSH_RANGE_NO_GAPS,
+	/**
+	 * @PT_FEAT_DETAILED_GATHER: Fill in the struct iommu_iotlb_gather pt
+	 * sub structure with information about which levels were changed.
+	 */
+	PT_FEAT_DETAILED_GATHER,
 	/* private: */
 	PT_FEAT_FMT_START,
 };
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index a9e89911c90f24..bf8a77a164e4db 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -360,11 +360,31 @@ struct iommu_iotlb_gather {
 	 *       flushed (inclusive)
 	 */
 	unsigned long		end;
-	/**
-	 * @pgsize: The interval at which to perform the flush, only used
-	 *          by arm-smmu-v3
-	 */
-	size_t			pgsize;
+
+	union {
+		/**
+		 * @pgsize: The interval at which to perform the flush, only
+		 *          used by arm-smmu-v3
+		 */
+		size_t pgsize;
+		struct {
+			/**
+			 * @pt.leaf_levels_bitmap: Bitmap of generic_pt
+			 * levels where leaf entries were unmapped. Bit 0
+			 * means the leaf only level. If 0 no leafs
+			 * were unmapped.
+			 */
+			u8 leaf_levels_bitmap;
+			/**
+			 * @pt.table_levels_bitmap: Bitmap of generic_pt levels
+			 * of table entries that were removed. Bit 0 is never
+			 * set, bit 1 means a table of all leafs was removed.
+			 * When freelist is empty this must be 0.
+			 */
+			u8 table_levels_bitmap;
+		} pt;
+	};
+
 	/**
 	 * @freelist: Removed pages to free after sync, only used by
 	 *            iommupt
-- 
2.43.0