2 files changed, 31 insertions, 38 deletions

diff --git a/drivers/iommu/intel/cache.c b/drivers/iommu/intel/cache.c
index be8410f0e841..fdc88817709f 100644
--- a/drivers/iommu/intel/cache.c
+++ b/drivers/iommu/intel/cache.c
@@ -254,37 +254,29 @@ void cache_tag_unassign_domain(struct dmar_domain *domain,
 }
 
 static unsigned long calculate_psi_aligned_address(unsigned long start,
-						   unsigned long end,
-						   unsigned long *_mask)
+						   unsigned long last,
+						   unsigned long *size_order)
 {
-	unsigned long pages = aligned_nrpages(start, end - start + 1);
-	unsigned long aligned_pages = __roundup_pow_of_two(pages);
-	unsigned long bitmask = aligned_pages - 1;
-	unsigned long mask = ilog2(aligned_pages);
-	unsigned long pfn = IOVA_PFN(start);
-
-	/*
-	 * PSI masks the low order bits of the base address. If the
-	 * address isn't aligned to the mask, then compute a mask value
-	 * needed to ensure the target range is flushed.
-	 */
-	if (unlikely(bitmask & pfn)) {
-		unsigned long end_pfn = pfn + pages - 1, shared_bits;
-
+	unsigned int sz_lg2;
+
+	/* Compute a sz_lg2 that spans start and last */
+	start &= GENMASK(BITS_PER_LONG - 1, VTD_PAGE_SHIFT);
+	sz_lg2 = fls_long(start ^ last);
+	if (sz_lg2 <= 12) {
+		*size_order = 0;
+		return start;
+	}
+	if (unlikely(sz_lg2 >= BITS_PER_LONG)) {
 		/*
-		 * Since end_pfn <= pfn + bitmask, the only way bits
-		 * higher than bitmask can differ in pfn and end_pfn is
-		 * by carrying. This means after masking out bitmask,
-		 * high bits starting with the first set bit in
-		 * shared_bits are all equal in both pfn and end_pfn.
+		 * MAX_AGAW_PFN_WIDTH triggers full invalidation in all
+		 * downstream users.
 		 */
-		shared_bits = ~(pfn ^ end_pfn) & ~bitmask;
-		mask = shared_bits ? __ffs(shared_bits) : MAX_AGAW_PFN_WIDTH;
+		*size_order = MAX_AGAW_PFN_WIDTH;
+		return 0;
 	}
 
-	*_mask = mask;
-
-	return ALIGN_DOWN(start, VTD_PAGE_SIZE << mask);
+	*size_order = sz_lg2 - VTD_PAGE_SHIFT;
+	return start & GENMASK(BITS_PER_LONG - 1, sz_lg2);
 }
 
 static void qi_batch_flush_descs(struct intel_iommu *iommu, struct qi_batch *batch)
@@ -441,12 +433,7 @@ void cache_tag_flush_range(struct dmar_domain *domain, unsigned long start,
 	struct cache_tag *tag;
 	unsigned long flags;
 
-	if (start == 0 && end == ULONG_MAX) {
-		addr = 0;
-		mask = MAX_AGAW_PFN_WIDTH;
-	} else {
-		addr = calculate_psi_aligned_address(start, end, &mask);
-	}
+	addr = calculate_psi_aligned_address(start, end, &mask);
 
 	spin_lock_irqsave(&domain->cache_lock, flags);
 	list_for_each_entry(tag, &domain->cache_tags, node) {
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index 40e33257d3c2..1dbef8c55007 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -777,21 +777,27 @@ struct io_pgtable_init_fns io_pgtable_arm_v7s_init_fns = {
 
 static struct io_pgtable_cfg *cfg_cookie __initdata;
 
-static void __init dummy_tlb_flush_all(void *cookie)
+/*
+ * __noipa prevents gcc from turning indirect iommu_flush_ops calls
+ * into direct calls from a specialized __arm_v7s_unmap() that triggers
+ * a build time section mismatch assertion.
+ */
+static __noipa void __init dummy_tlb_flush_all(void *cookie)
 {
 	WARN_ON(cookie != cfg_cookie);
 }
 
-static void __init dummy_tlb_flush(unsigned long iova, size_t size,
-				   size_t granule, void *cookie)
+static __noipa void __init dummy_tlb_flush(unsigned long iova, size_t size,
+					   size_t granule, void *cookie)
 {
 	WARN_ON(cookie != cfg_cookie);
 	WARN_ON(!(size & cfg_cookie->pgsize_bitmap));
 }
 
-static void __init dummy_tlb_add_page(struct iommu_iotlb_gather *gather,
-				      unsigned long iova, size_t granule,
-				      void *cookie)
+static __noipa void __init dummy_tlb_add_page(struct iommu_iotlb_gather *gather,
+					      unsigned long iova,
+					      size_t granule,
+					      void *cookie)
 {
 	dummy_tlb_flush(iova, granule, granule, cookie);
 }