riscv: Fix set_huge_pte_at() for NAPOT mapping

[platform/kernel/linux-starfive.git] / arch / riscv / mm / hugetlbpage.c

diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c
index e4a2ace..24c0179 100644 (file)
--- a/arch/riscv/mm/hugetlbpage.c
+++ b/arch/riscv/mm/hugetlbpage.c
@@ -177,21 +177,66 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags)
        return entry;
 }
 
+static void clear_flush(struct mm_struct *mm,
+                       unsigned long addr,
+                       pte_t *ptep,
+                       unsigned long pgsize,
+                       unsigned long ncontig)
+{
+       struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0);
+       unsigned long i, saddr = addr;
+
+       for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
+               ptep_get_and_clear(mm, addr, ptep);
+
+       flush_tlb_range(&vma, saddr, addr);
+}
+
+/*
+ * When dealing with NAPOT mappings, the privileged specification indicates that
+ * "if an update needs to be made, the OS generally should first mark all of the
+ * PTEs invalid, then issue SFENCE.VMA instruction(s) covering all 4 KiB regions
+ * within the range, [...] then update the PTE(s), as described in Section
+ * 4.2.1.". That's the equivalent of the Break-Before-Make approach used by
+ * arm64.
+ */
 void set_huge_pte_at(struct mm_struct *mm,
                     unsigned long addr,
                     pte_t *ptep,
                     pte_t pte,
                     unsigned long sz)
 {
+       unsigned long hugepage_shift, pgsize;
        int i, pte_num;
 
+       if (sz >= PGDIR_SIZE)
+               hugepage_shift = PGDIR_SHIFT;
+       else if (sz >= P4D_SIZE)
+               hugepage_shift = P4D_SHIFT;
+       else if (sz >= PUD_SIZE)
+               hugepage_shift = PUD_SHIFT;
+       else if (sz >= PMD_SIZE)
+               hugepage_shift = PMD_SHIFT;
+       else
+               hugepage_shift = PAGE_SHIFT;
+
+       pte_num = sz >> hugepage_shift;
+       pgsize = 1 << hugepage_shift;
+
+       if (!pte_present(pte)) {
+               for (i = 0; i < pte_num; i++, ptep++, addr += pgsize)
+                       set_ptes(mm, addr, ptep, pte, 1);
+               return;
+       }
+
        if (!pte_napot(pte)) {
-               set_pte_at(mm, addr, ptep, pte);
+               set_ptes(mm, addr, ptep, pte, 1);
                return;
        }
 
-       pte_num = napot_pte_num(napot_cont_order(pte));
-       for (i = 0; i < pte_num; i++, ptep++, addr += PAGE_SIZE)
+       clear_flush(mm, addr, ptep, pgsize, pte_num);
+
+       for (i = 0; i < pte_num; i++, ptep++, addr += pgsize)
                set_pte_at(mm, addr, ptep, pte);
 }