riscv: Improve flush_tlb_range() for hugetlb pages

flush_tlb_range() uses a fixed stride of PAGE_SIZE and in its current form,
when a hugetlb mapping needs to be flushed, flush_tlb_range() flushes the
whole tlb: so set a stride of the size of the hugetlb mapping in order to
only flush the hugetlb mapping. However, if the hugepage is a NAPOT region,
all PTEs that constitute this mapping must be invalidated, so the stride
size must actually be the size of the PTE.

Note that THPs are directly handled by flush_pmd_tlb_range().

Signed-off-by: Alexandre Ghiti <[email protected]>
Reviewed-by: Samuel Holland <[email protected]>
Tested-by: Lad Prabhakar <[email protected]> # On RZ/Five SMARC
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Palmer Dabbelt <[email protected]>

Author: Alexandre Ghiti

arch/riscv/mm/tlbflush.c

@@ -3,6 +3,7 @@
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/sched.h>
+#include <linux/hugetlb.h>
 #include <asm/sbi.h>
 #include <asm/mmu_context.h>
 
@@ -147,7 +148,33 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
 void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 		     unsigned long end)
 {
-	__flush_tlb_range(vma->vm_mm, start, end - start, PAGE_SIZE);
+	unsigned long stride_size;
+
+	if (!is_vm_hugetlb_page(vma)) {
+		stride_size = PAGE_SIZE;
+	} else {
+		stride_size = huge_page_size(hstate_vma(vma));
+
+		/*
+		 * As stated in the privileged specification, every PTE in a
+		 * NAPOT region must be invalidated, so reset the stride in that
+		 * case.
+		 */
+		if (has_svnapot()) {
+			if (stride_size >= PGDIR_SIZE)
+				stride_size = PGDIR_SIZE;
+			else if (stride_size >= P4D_SIZE)
+				stride_size = P4D_SIZE;
+			else if (stride_size >= PUD_SIZE)
+				stride_size = PUD_SIZE;
+			else if (stride_size >= PMD_SIZE)
+				stride_size = PMD_SIZE;
+			else
+				stride_size = PAGE_SIZE;
+		}
+	}
+
+	__flush_tlb_range(vma->vm_mm, start, end - start, stride_size);
 }
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,