iommupt: Fix the end_index calculation in __map_range_leaf()

Sashiko noticed a mismatch of units in this math: num_leaves is
actually the number of leaf *entries* (so a 16-item contiguous leaf
is one num_leaves), while index is in items. The mismatch in maths
causes __map_range_leaf() to exit early instead of efficiently
filling a larger range of contiguous PTEs.

The early exit is caught by the functions above and then
__map_range_leaf() is re-invoked, so there is no functional issue.

Correct the misuse of units by adjusting num_leaves with the leaf
size and avoid the performance cost of looping externally.

There are also some mismatched types for num_leaves; simplify
things to remove the duplicated calculations.

Fixes: d6c65b0fd621 ("iommupt: Avoid rewalking during map")
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Samiullah Khawaja <skhawaja@google.com>
Reviewd-by: Pranjal Shrivastava <praan@google.com>
Tested-by: Josua Mayer <josua@solid-run.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>

diff --git a/drivers/iommu/generic_pt/iommu_pt.h b/drivers/iommu/generic_pt/iommu_pt.h
index 4877b05291c9d48d0a51888237560b10e477e3a5..dc91fb4e2f61cb79b375154d429feb4b71c7a871 100644 (file)
--- a/drivers/iommu/generic_pt/iommu_pt.h
+++ b/drivers/iommu/generic_pt/iommu_pt.h
@@ -534,10 +534,12 @@ static int __map_range_leaf(struct pt_range *range, void *arg,
        struct pt_state pts = pt_init(range, level, table);
        struct pt_iommu_map_args *map = arg;
        unsigned int leaf_pgsize_lg2 = map->leaf_pgsize_lg2;
+       unsigned int leaves_avail;
        unsigned int start_index;
        pt_oaddr_t oa = map->oa;
-       unsigned int num_leaves;
+       pt_vaddr_t num_leaves;
        unsigned int orig_end;
+       unsigned int step_lg2;
        pt_vaddr_t last_va;
        unsigned int step;
        bool need_contig;
@@ -546,21 +548,25 @@ static int __map_range_leaf(struct pt_range *range, void *arg,
        PT_WARN_ON(map->leaf_level != level);
        PT_WARN_ON(!pt_can_have_leaf(&pts));
 
-       step = log2_to_int_t(unsigned int,
-                            leaf_pgsize_lg2 - pt_table_item_lg2sz(&pts));
-       need_contig = leaf_pgsize_lg2 != pt_table_item_lg2sz(&pts);
+       step_lg2 = leaf_pgsize_lg2 - pt_table_item_lg2sz(&pts);
+       step = log2_to_int_t(unsigned int, step_lg2);
+       need_contig = step_lg2 != 0;
 
        _pt_iter_first(&pts);
        start_index = pts.index;
        orig_end = pts.end_index;
-       if (pts.index + map->num_leaves < pts.end_index) {
+       leaves_avail =
+               log2_div_t(unsigned int, pts.end_index - pts.index, step_lg2);
+       if (map->num_leaves <= leaves_avail) {
                /* Need to stop in the middle of the table to change sizes */
-               pts.end_index = pts.index + map->num_leaves;
+               pts.end_index = pts.index + log2_mul(map->num_leaves, step_lg2);
                num_leaves = 0;
        } else {
-               num_leaves = map->num_leaves - (pts.end_index - pts.index);
+               num_leaves = map->num_leaves - leaves_avail;
        }
 
+       PT_WARN_ON(
+               log2_mod_t(unsigned int, pts.end_index - pts.index, step_lg2));
        do {
                pts.type = pt_load_entry_raw(&pts);
                if (pts.type != PT_ENTRY_EMPTY || need_contig) {