@@ -341,9 +341,10 @@ static inline void __sync_cache_and_tags(pte_t pte, unsigned int nr_pages)
mte_sync_tags(pte, nr_pages);
}
-static inline void set_ptes(struct mm_struct *mm,
- unsigned long __always_unused addr,
- pte_t *ptep, pte_t pte, unsigned int nr)
+static inline void __set_ptes(struct mm_struct *mm,
+ unsigned long __always_unused addr,
+ pte_t *ptep, pte_t pte, unsigned int nr,
+ unsigned long pgsize)
{
page_table_check_ptes_set(mm, ptep, pte, nr);
__sync_cache_and_tags(pte, nr);
@@ -354,10 +355,15 @@ static inline void set_ptes(struct mm_struct *mm,
if (--nr == 0)
break;
ptep++;
- pte_val(pte) += PAGE_SIZE;
+ pte_val(pte) += pgsize;
}
}
-#define set_ptes set_ptes
+
+#define set_ptes(mm, addr, ptep, pte, nr) \
+ __set_ptes(mm, addr, ptep, pte, nr, PAGE_SIZE)
+
+#define set_contptes(mm, addr, ptep, pte, nr, pgsize) \
+ __set_ptes(mm, addr, ptep, pte, nr, pgsize)
/*
* Huge pte definitions.
@@ -166,62 +166,6 @@ static pte_t get_clear_contig_flush(struct mm_struct *mm,
return orig_pte;
}
-/*
- * Changing some bits of contiguous entries requires us to follow a
- * Break-Before-Make approach, breaking the whole contiguous set
- * before we can change any entries. See ARM DDI 0487A.k_iss10775,
- * "Misprogramming of the Contiguous bit", page D4-1762.
- *
- * This helper performs the break step for use cases where the
- * original pte is not needed.
- */
-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_clear(mm, addr, ptep);
-
- flush_tlb_range(&vma, saddr, addr);
-}
-
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep, pte_t pte, unsigned long sz)
-{
- size_t pgsize;
- int i;
- int ncontig;
- unsigned long pfn, dpfn;
- pgprot_t hugeprot;
-
- ncontig = arch_contpte_get_num_contig(ptep, sz, &pgsize);
-
- if (!pte_present(pte)) {
- for (i = 0; i < ncontig; i++, ptep++, addr += pgsize)
- set_pte_at(mm, addr, ptep, pte);
- return;
- }
-
- if (!pte_cont(pte)) {
- set_pte_at(mm, addr, ptep, pte);
- return;
- }
-
- pfn = pte_pfn(pte);
- dpfn = pgsize >> PAGE_SHIFT;
- hugeprot = pte_pgprot(pte);
-
- clear_flush(mm, addr, ptep, pgsize, ncontig);
-
- for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
- set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
-}
-
pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, unsigned long sz)
{
@@ -533,29 +533,39 @@ static inline void __set_pte_at(pte_t *ptep, pte_t pteval)
static inline int arch_contpte_get_num_contig(pte_t *ptep, unsigned long size,
size_t *pgsize)
{
+ unsigned long hugepage_shift;
pte_t __pte;
/* We must read the raw value of the pte to get the size of the mapping */
__pte = READ_ONCE(*ptep);
- if (pgsize) {
- if (size >= PGDIR_SIZE)
+ if (size >= PGDIR_SIZE) {
+ if (pgsize)
*pgsize = PGDIR_SIZE;
- else if (size >= P4D_SIZE)
+ hugepage_shift = PGDIR_SHIFT;
+ } else if (size >= P4D_SIZE) {
+ if (pgsize)
*pgsize = P4D_SIZE;
- else if (size >= PUD_SIZE)
+ hugepage_shift = P4D_SHIFT;
+ } else if (size >= PUD_SIZE) {
+ if (pgsize)
*pgsize = PUD_SIZE;
- else if (size >= PMD_SIZE)
+ hugepage_shift = PUD_SHIFT;
+ } else if (size >= PMD_SIZE) {
+ if (pgsize)
*pgsize = PMD_SIZE;
- else
+ hugepage_shift = PMD_SHIFT;
+ } else {
+ if (pgsize)
*pgsize = PAGE_SIZE;
+ hugepage_shift = PAGE_SHIFT;
}
/* Make sure __pte is not a swap entry */
if (pte_valid_napot(__pte))
return napot_pte_num(napot_cont_order(__pte));
- return 1;
+ return size >> hugepage_shift;
}
#endif
@@ -631,6 +641,8 @@ static inline void set_ptes(struct mm_struct *mm, unsigned long addr,
}
}
#define set_ptes set_ptes
+#define set_contptes(mm, addr, ptep, pte, nr, pgsize) \
+ set_ptes(mm, addr, ptep, pte, nr)
static inline void pte_clear(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
@@ -173,68 +173,6 @@ 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_ptes(mm, addr, ptep, pte, 1);
- return;
- }
-
- clear_flush(mm, addr, ptep, pgsize, pte_num);
-
- set_ptes(mm, addr, ptep, pte, pte_num);
-}
-
int huge_ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long addr,
pte_t *ptep,
@@ -12,11 +12,13 @@
* * contpte macros
* - pte_cont()
* - arch_contpte_get_num_contig()
+ * - set_contptes()
*/
/*
* This file implements the following contpte aware API:
* huge_ptep_get()
+ * set_huge_pte_at()
*/
pte_t huge_ptep_get(pte_t *ptep)
@@ -43,3 +45,59 @@ pte_t huge_ptep_get(pte_t *ptep)
}
return orig_pte;
}
+
+/*
+ * ARM64: Changing some bits of contiguous entries requires us to follow a
+ * Break-Before-Make approach, breaking the whole contiguous set
+ * before we can change any entries. See ARM DDI 0487A.k_iss10775,
+ * "Misprogramming of the Contiguous bit", page D4-1762.
+ *
+ * RISCV: 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.
+ *
+ * This helper performs the break step for use cases where the
+ * original pte is not needed.
+ */
+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_clear(mm, addr, ptep);
+
+ flush_tlb_range(&vma, saddr, addr);
+}
+
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t pte, unsigned long sz)
+{
+ size_t pgsize;
+ int i;
+ int ncontig;
+
+ ncontig = arch_contpte_get_num_contig(ptep, sz, &pgsize);
+
+ if (!pte_present(pte)) {
+ for (i = 0; i < ncontig; i++, ptep++, addr += pgsize)
+ set_pte_at(mm, addr, ptep, pte);
+ return;
+ }
+
+ if (!pte_cont(pte)) {
+ set_pte_at(mm, addr, ptep, pte);
+ return;
+ }
+
+ clear_flush(mm, addr, ptep, pgsize, ncontig);
+
+ set_contptes(mm, addr, ptep, pte, ncontig, pgsize);
+}
After some adjustments, both architectures have the same implementation so move it to generic code. Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com> --- arch/arm64/include/asm/pgtable.h | 16 ++++++--- arch/arm64/mm/hugetlbpage.c | 56 ----------------------------- arch/riscv/include/asm/pgtable.h | 26 ++++++++++---- arch/riscv/mm/hugetlbpage.c | 62 -------------------------------- mm/contpte.c | 58 ++++++++++++++++++++++++++++++ 5 files changed, 88 insertions(+), 130 deletions(-)