@@ -31,9 +31,6 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags);
extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
pte_t pte, int dirty);
-#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
-extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
- unsigned long addr, pte_t *ptep);
#define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
extern void huge_ptep_set_wrprotect(struct mm_struct *mm,
unsigned long addr, pte_t *ptep);
@@ -1766,12 +1766,23 @@ static inline void clear_young_dirty_ptes(struct vm_area_struct *vma,
#endif /* CONFIG_ARM64_CONTPTE */
-static inline int arch_contpte_get_num_contig(pte_t *ptep,
- unsigned long size,
+extern int find_num_contig(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, size_t *pgsize);
+
+static inline int arch_contpte_get_num_contig(struct mm_struct *mm,
+ unsigned long addr,
+ pte_t *ptep, unsigned long size,
size_t *pgsize)
{
int contig_ptes = 0;
+ /*
+ * If the size is not passed, we need to go through the page table to
+ * find out the number of contiguous ptes.
+ */
+ if (size == 0)
+ return find_num_contig(mm, addr, ptep, pgsize);
+
if (pgsize)
*pgsize = size;
@@ -79,8 +79,8 @@ bool arch_hugetlb_migration_supported(struct hstate *h)
}
#endif
-static int find_num_contig(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep, size_t *pgsize)
+int find_num_contig(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, size_t *pgsize)
{
pgd_t *pgdp = pgd_offset(mm, addr);
p4d_t *p4dp;
@@ -266,21 +266,6 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags)
return entry;
}
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
- unsigned long addr, pte_t *ptep)
-{
- int ncontig;
- size_t pgsize;
- pte_t orig_pte = __ptep_get(ptep);
-
- if (!pte_cont(orig_pte))
- return __ptep_get_and_clear(mm, addr, ptep);
-
- ncontig = find_num_contig(mm, addr, ptep, &pgsize);
-
- return get_clear_contig(mm, addr, ptep, pgsize, ncontig);
-}
-
/*
* huge_ptep_set_access_flags will update access flags (dirty, accesssed)
* and write permission.
@@ -20,10 +20,6 @@ bool arch_hugetlb_migration_supported(struct hstate *h);
#endif
#ifdef CONFIG_RISCV_ISA_SVNAPOT
-#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
- unsigned long addr, pte_t *ptep);
-
#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep);
@@ -584,7 +584,9 @@ static inline void __set_ptes(struct mm_struct *mm, unsigned long addr,
}
#ifdef CONFIG_RISCV_ISA_SVNAPOT
-static inline int arch_contpte_get_num_contig(pte_t *ptep, unsigned long size,
+static inline int arch_contpte_get_num_contig(struct mm_struct *mm,
+ unsigned long addr,
+ pte_t *ptep, unsigned long size,
size_t *pgsize)
{
unsigned long hugepage_shift;
@@ -186,7 +186,8 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
if (!pte_napot(pte))
return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
- pte_num = arch_contpte_get_num_contig(ptep, 0, NULL);
+ pte_num = arch_contpte_get_num_contig(vma->vm_mm, addr, ptep, 0, NULL);
+
orig_pte = get_clear_contig_flush(mm, addr, ptep, pte_num);
if (pte_dirty(orig_pte))
@@ -200,21 +201,6 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
return true;
}
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
- unsigned long addr,
- pte_t *ptep)
-{
- pte_t orig_pte = ptep_get(ptep);
- int pte_num;
-
- if (!pte_napot(orig_pte))
- return ptep_get_and_clear(mm, addr, ptep);
-
- pte_num = arch_contpte_get_num_contig(ptep, 0, NULL);
-
- return get_clear_contig(mm, addr, ptep, pte_num);
-}
-
void huge_ptep_set_wrprotect(struct mm_struct *mm,
unsigned long addr,
pte_t *ptep)
@@ -228,7 +214,8 @@ void huge_ptep_set_wrprotect(struct mm_struct *mm,
return;
}
- pte_num = arch_contpte_get_num_contig(ptep, 0, NULL);
+ pte_num = arch_contpte_get_num_contig(mm, addr, ptep, 0, NULL);
+
orig_pte = get_clear_contig_flush(mm, addr, ptep, pte_num);
orig_pte = pte_wrprotect(orig_pte);
@@ -246,7 +233,7 @@ pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
if (!pte_napot(pte))
return ptep_clear_flush(vma, addr, ptep);
- pte_num = arch_contpte_get_num_contig(ptep, 0, NULL);
+ pte_num = arch_contpte_get_num_contig(vma->vm_mm, addr, ptep, 0, NULL);
return get_clear_contig_flush(vma->vm_mm, addr, ptep, pte_num);
}
@@ -18,4 +18,8 @@ extern void set_huge_pte_at(struct mm_struct *mm,
extern void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, unsigned long sz);
+#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
+extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep);
+
#endif /* _LINUX_HUGETLB_CONTPTE_H */
@@ -22,6 +22,7 @@
* - huge_ptep_get()
* - set_huge_pte_at()
* - huge_pte_clear()
+ * - huge_ptep_get_and_clear()
*/
pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
@@ -32,7 +33,7 @@ pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
if (!pte_present(orig_pte) || !pte_cont(orig_pte))
return orig_pte;
- ncontig = arch_contpte_get_num_contig(ptep,
+ ncontig = arch_contpte_get_num_contig(mm, addr, ptep,
page_size(pte_page(orig_pte)),
NULL);
@@ -86,7 +87,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
int i;
int ncontig;
- ncontig = arch_contpte_get_num_contig(ptep, sz, &pgsize);
+ ncontig = arch_contpte_get_num_contig(mm, addr, ptep, sz, &pgsize);
if (!pte_present(pte)) {
for (i = 0; i < ncontig; i++, ptep++, addr += pgsize)
@@ -110,8 +111,49 @@ void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
int i, ncontig;
size_t pgsize;
- ncontig = arch_contpte_get_num_contig(ptep, sz, &pgsize);
+ ncontig = arch_contpte_get_num_contig(mm, addr, ptep, sz, &pgsize);
for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
__pte_clear(mm, addr, ptep);
}
+
+static pte_t get_clear_contig(struct mm_struct *mm,
+ unsigned long addr,
+ pte_t *ptep,
+ unsigned long pgsize,
+ unsigned long ncontig)
+{
+ pte_t orig_pte = __ptep_get(ptep);
+ unsigned long i;
+
+ for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) {
+ pte_t pte = __ptep_get_and_clear(mm, addr, ptep);
+
+ /*
+ * If HW_AFDBM (arm64) or Svadu (riscv) is enabled, then the HW
+ * could turn on the dirty or accessed bit for any page in the
+ * set, so check them all.
+ */
+ if (pte_dirty(pte))
+ orig_pte = pte_mkdirty(orig_pte);
+
+ if (pte_young(pte))
+ orig_pte = pte_mkyoung(orig_pte);
+ }
+ return orig_pte;
+}
+
+pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep)
+{
+ int ncontig;
+ size_t pgsize;
+ pte_t orig_pte = __ptep_get(ptep);
+
+ if (!pte_cont(orig_pte))
+ return __ptep_get_and_clear(mm, addr, ptep);
+
+ ncontig = arch_contpte_get_num_contig(mm, addr, ptep, 0, &pgsize);
+
+ return get_clear_contig(mm, addr, ptep, pgsize, ncontig);
+}
After some adjustments, both architectures have the same implementation so move it to the generic code. Note that get_clear_contig() function is duplicated in the generic and the arm64 code because it is still used by some arm64 functions that will, in the next commits, be moved to the generic code. Once all have been moved, the arm64 version will be removed. Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com> --- arch/arm64/include/asm/hugetlb.h | 3 -- arch/arm64/include/asm/pgtable.h | 15 ++++++++-- arch/arm64/mm/hugetlbpage.c | 19 ++----------- arch/riscv/include/asm/hugetlb.h | 4 --- arch/riscv/include/asm/pgtable.h | 4 ++- arch/riscv/mm/hugetlbpage.c | 23 ++++----------- include/linux/hugetlb_contpte.h | 4 +++ mm/hugetlb_contpte.c | 48 ++++++++++++++++++++++++++++++-- 8 files changed, 72 insertions(+), 48 deletions(-)