[PATCH 7/9] mm: Use common huge_ptep_set_access_flags() function for riscv/arm64

From: Alexandre Ghiti
Date: Fri Mar 01 2024 - 04:22:28 EST


Both architectures have almost the same implementation:
__cont_access_flags_changed() is also correct on riscv and brings the
same benefits (ie don't do anything if the flags are unchanged).

As in the previous commit, get_clear_contig_flush() is duplicated in both
the arch and the generic codes, it will be removed from the arch code when
the last reference there gets moved to the generic code.

Signed-off-by: Alexandre Ghiti <alexghiti@xxxxxxxxxxxx>
---
arch/arm64/mm/hugetlbpage.c | 65 --------------------------------
arch/riscv/mm/hugetlbpage.c | 29 ---------------
mm/contpte.c | 74 +++++++++++++++++++++++++++++++++++++
3 files changed, 74 insertions(+), 94 deletions(-)

diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index a2d33cbc7da5..b8abbd5ace4f 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -284,71 +284,6 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags)
return entry;
}

-/*
- * huge_ptep_set_access_flags will update access flags (dirty, accesssed)
- * and write permission.
- *
- * For a contiguous huge pte range we need to check whether or not write
- * permission has to change only on the first pte in the set. Then for
- * all the contiguous ptes we need to check whether or not there is a
- * discrepancy between dirty or young.
- */
-static int __cont_access_flags_changed(pte_t *ptep, pte_t pte, int ncontig)
-{
- int i;
-
- if (pte_write(pte) != pte_write(ptep_get(ptep)))
- return 1;
-
- for (i = 0; i < ncontig; i++) {
- pte_t orig_pte = ptep_get(ptep + i);
-
- if (pte_dirty(pte) != pte_dirty(orig_pte))
- return 1;
-
- if (pte_young(pte) != pte_young(orig_pte))
- return 1;
- }
-
- return 0;
-}
-
-int huge_ptep_set_access_flags(struct vm_area_struct *vma,
- unsigned long addr, pte_t *ptep,
- pte_t pte, int dirty)
-{
- int ncontig, i;
- size_t pgsize = 0;
- unsigned long pfn = pte_pfn(pte), dpfn;
- struct mm_struct *mm = vma->vm_mm;
- pgprot_t hugeprot;
- pte_t orig_pte;
-
- if (!pte_cont(pte))
- return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
-
- ncontig = find_num_contig(mm, addr, ptep, &pgsize);
- dpfn = pgsize >> PAGE_SHIFT;
-
- if (!__cont_access_flags_changed(ptep, pte, ncontig))
- return 0;
-
- orig_pte = get_clear_contig_flush(mm, addr, ptep, pgsize, ncontig);
-
- /* Make sure we don't lose the dirty or young state */
- if (pte_dirty(orig_pte))
- pte = pte_mkdirty(pte);
-
- if (pte_young(orig_pte))
- pte = pte_mkyoung(pte);
-
- hugeprot = pte_pgprot(pte);
- for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
- set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
-
- return 1;
-}
-
void huge_ptep_set_wrprotect(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c
index 4c441664db8a..fdb633844d4b 100644
--- a/arch/riscv/mm/hugetlbpage.c
+++ b/arch/riscv/mm/hugetlbpage.c
@@ -173,35 +173,6 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags)
return entry;
}

-int huge_ptep_set_access_flags(struct vm_area_struct *vma,
- unsigned long addr,
- pte_t *ptep,
- pte_t pte,
- int dirty)
-{
- struct mm_struct *mm = vma->vm_mm;
- size_t pgsize;
- pte_t orig_pte;
- int pte_num;
-
- if (!pte_napot(pte))
- return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
-
- pte_num = arch_contpte_get_num_contig(vma->vm_mm, addr, ptep, 0, &pgsize);
-
- orig_pte = get_clear_contig_flush(mm, addr, ptep, pte_num);
-
- if (pte_dirty(orig_pte))
- pte = pte_mkdirty(pte);
-
- if (pte_young(orig_pte))
- pte = pte_mkyoung(pte);
-
- set_ptes(mm, addr, ptep, pte, pte_num);
-
- return true;
-}
-
void huge_ptep_set_wrprotect(struct mm_struct *mm,
unsigned long addr,
pte_t *ptep)
diff --git a/mm/contpte.c b/mm/contpte.c
index 8d2ab391e0d8..3b65c49c6d4b 100644
--- a/mm/contpte.c
+++ b/mm/contpte.c
@@ -21,6 +21,7 @@
* set_huge_pte_at()
* huge_pte_clear()
* huge_ptep_get_and_clear()
+ * huge_ptep_set_access_flags()
*/

pte_t huge_ptep_get(pte_t *ptep)
@@ -156,3 +157,76 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm,

return get_clear_contig(mm, addr, ptep, pgsize, ncontig);
}
+
+/*
+ * huge_ptep_set_access_flags will update access flags (dirty, accesssed)
+ * and write permission.
+ *
+ * For a contiguous huge pte range we need to check whether or not write
+ * permission has to change only on the first pte in the set. Then for
+ * all the contiguous ptes we need to check whether or not there is a
+ * discrepancy between dirty or young.
+ */
+static int __cont_access_flags_changed(pte_t *ptep, pte_t pte, int ncontig)
+{
+ int i;
+
+ if (pte_write(pte) != pte_write(ptep_get(ptep)))
+ return 1;
+
+ for (i = 0; i < ncontig; i++) {
+ pte_t orig_pte = ptep_get(ptep + i);
+
+ if (pte_dirty(pte) != pte_dirty(orig_pte))
+ return 1;
+
+ if (pte_young(pte) != pte_young(orig_pte))
+ return 1;
+ }
+
+ return 0;
+}
+
+static pte_t get_clear_contig_flush(struct mm_struct *mm,
+ unsigned long addr,
+ pte_t *ptep,
+ unsigned long pgsize,
+ unsigned long ncontig)
+{
+ pte_t orig_pte = get_clear_contig(mm, addr, ptep, pgsize, ncontig);
+ struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0);
+
+ flush_tlb_range(&vma, addr, addr + (pgsize * ncontig));
+ return orig_pte;
+}
+
+int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+ unsigned long addr, pte_t *ptep,
+ pte_t pte, int dirty)
+{
+ int ncontig;
+ size_t pgsize = 0;
+ struct mm_struct *mm = vma->vm_mm;
+ pte_t orig_pte;
+
+ if (!pte_cont(pte))
+ return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
+
+ ncontig = arch_contpte_get_num_contig(vma->vm_mm, addr, ptep, 0, &pgsize);
+
+ if (!__cont_access_flags_changed(ptep, pte, ncontig))
+ return 0;
+
+ orig_pte = get_clear_contig_flush(mm, addr, ptep, pgsize, ncontig);
+
+ /* Make sure we don't lose the dirty or young state */
+ if (pte_dirty(orig_pte))
+ pte = pte_mkdirty(pte);
+
+ if (pte_young(orig_pte))
+ pte = pte_mkyoung(pte);
+
+ set_contptes(mm, addr, ptep, pte, ncontig, pgsize);
+
+ return 1;
+}
--
2.39.2