diff --git a/mm/filemap.c b/mm/filemap.c
index 58d8ba867b52..98434acc69c1 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3313,14 +3313,26 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
 	struct file *fpin = NULL;
 	vm_flags_t vm_flags = vmf->vma->vm_flags;
 	bool force_thp_readahead = false;
+	unsigned int thp_order = 0;
 	unsigned short mmap_miss;
 
 	ractl._max_index = vmf->vma->vm_pgoff + vma_pages(vmf->vma) - 1;
 
 	/* Use the readahead code, even if readahead is disabled */
-	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
-	    (vm_flags & VM_HUGEPAGE) && HPAGE_PMD_ORDER <= MAX_PAGECACHE_ORDER)
-		force_thp_readahead = true;
+	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && (vm_flags & VM_HUGEPAGE)) {
+		/*
+		 * Cap max THP order at 2MB: this is the common PMD-sized
+		 * hugepage size, and it avoids memory pressure from very
+		 * large forced readahead when mapping_max_folio_order() is
+		 * high (for example, 128MB with 64K base pages on arm64).
+		 */
+		if (mapping_large_folio_support(mapping)) {
+			force_thp_readahead = true;
+			thp_order = min_t(unsigned int,
+					  mapping_max_folio_order(mapping),
+					  get_order(SZ_2M));
+		}
+	}
 
 	if (!force_thp_readahead) {
 		/*
@@ -3355,17 +3367,19 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
 	}
 
 	if (force_thp_readahead) {
+		unsigned long folio_nr_pages = 1UL << thp_order;
+
 		fpin = maybe_unlock_mmap_for_io(vmf, fpin);
-		ractl._index &= ~((unsigned long)HPAGE_PMD_NR - 1);
-		ra->size = HPAGE_PMD_NR;
+		ractl._index &= ~(folio_nr_pages - 1);
+		ra->size = folio_nr_pages;
 		/*
-		 * Fetch two PMD folios, so we get the chance to actually
+		 * Fetch two folios so we get the chance to actually
 		 * readahead, unless we've been told not to.
 		 */
 		if (!(vm_flags & VM_RAND_READ))
 			ra->size *= 2;
-		ra->async_size = HPAGE_PMD_NR;
-		ra->order = HPAGE_PMD_ORDER;
+		ra->async_size = folio_nr_pages;
+		ra->order = thp_order;
 		page_cache_ra_order(&ractl, ra);
 		return fpin;
 	}