iommupt: Only cache flush memory changed by unmap

The cache flush was happening on every level across the whole range of
iteration, even if no leafs or tables were cleared. Instead flush only the
sub range that was actually written.

Overflushing isn't a correctness problem but it does impact the
performance of unmap.

After this series the performance compared to the original VT-d
implementation with cache flushing turned on is:

map_pages
   pgsz  ,avg new,old ns, min new,old ns  , min % (+ve is better)
     2^12,    253,266   ,     213,227     ,   6.06
     2^21,    246,244   ,     221,219     ,   0.00
     2^30,    231,240   ,     209,217     ,   3.03
 256*2^12,   2604,2668  ,    2415,2540    ,   4.04
 256*2^21,   2495,2824  ,    2390,2734    ,  12.12
 256*2^30,   2542,2845  ,    2380,2718    ,  12.12

unmap_pages
   pgsz  ,avg new,old ns, min new,old ns  , min % (+ve is better)
     2^12,    259,292   ,     222,251     ,  11.11
     2^21,    255,259   ,     227,236     ,   3.03
     2^30,    238,254   ,     217,230     ,   5.05
 256*2^12,   2751,2620  ,    2417,2437    ,   0.00
 256*2^21,   2461,2526  ,    2377,2423    ,   1.01
 256*2^30,   2498,2543  ,    2370,2404    ,   1.01

Fixes: efa03da ("iommupt: Flush the CPU cache after any writes to the page table")
Reported-by: Francois Dugast <francois.dugast@intel.com>
Closes: https://lore.kernel.org/all/20260121130233.257428-1-francois.dugast@intel.com/
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Tested-by: Francois Dugast <francois.dugast@intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>

Author: jgunthorpe

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;
 }