For that, we need to introduce:
- a new config: ARCH_HAS_CONTPTE,
- a new arch specific function which returns the number of contiguous PTE
in a mapping and its base page size,
- a pte_cont() helper, only introduced for riscv since we keep the arm64
naming (contpte) which is more explicit than the riscv's (napot).
Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
---
arch/arm64/Kconfig | 1 +
arch/arm64/include/asm/pgtable.h | 31 ++++++++++++++++++
arch/arm64/mm/hugetlbpage.c | 55 ++------------------------------
arch/riscv/Kconfig | 1 +
arch/riscv/include/asm/hugetlb.h | 2 +-
arch/riscv/include/asm/pgtable.h | 1 +
arch/riscv/mm/hugetlbpage.c | 24 --------------
mm/Kconfig | 3 ++
mm/Makefile | 1 +
mm/contpte.c | 45 ++++++++++++++++++++++++++
10 files changed, 86 insertions(+), 78 deletions(-)
create mode 100644 mm/contpte.c
@@ -20,6 +20,7 @@ config ARM64
select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2
select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
select ARCH_HAS_CACHE_LINE_SIZE
+ select ARCH_HAS_CONTPTE
select ARCH_HAS_CURRENT_STACK_POINTER
select ARCH_HAS_DEBUG_VIRTUAL
select ARCH_HAS_DEBUG_VM_PGTABLE
@@ -1124,6 +1124,37 @@ extern pte_t ptep_modify_prot_start(struct vm_area_struct *vma,
extern void ptep_modify_prot_commit(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
pte_t old_pte, pte_t new_pte);
+
+static inline int arch_contpte_get_num_contig(pte_t *ptep, unsigned long size,
+ size_t *pgsize)
+{
+ int contig_ptes = 0;
+
+ *pgsize = size;
+
+ switch (size) {
+#ifndef __PAGETABLE_PMD_FOLDED
+ case PUD_SIZE:
+ if (pud_sect_supported())
+ contig_ptes = 1;
+ break;
+#endif
+ case PMD_SIZE:
+ contig_ptes = 1;
+ break;
+ case CONT_PMD_SIZE:
+ *pgsize = PMD_SIZE;
+ contig_ptes = CONT_PMDS;
+ break;
+ case CONT_PTE_SIZE:
+ *pgsize = PAGE_SIZE;
+ contig_ptes = CONT_PTES;
+ break;
+ }
+
+ return contig_ptes;
+}
+
#endif /* !__ASSEMBLY__ */
#endif /* __ASM_PGTABLE_H */
@@ -119,57 +119,6 @@ static int find_num_contig(struct mm_struct *mm, unsigned long addr,
return CONT_PTES;
}
-static inline int num_contig_ptes(unsigned long size, size_t *pgsize)
-{
- int contig_ptes = 0;
-
- *pgsize = size;
-
- switch (size) {
-#ifndef __PAGETABLE_PMD_FOLDED
- case PUD_SIZE:
- if (pud_sect_supported())
- contig_ptes = 1;
- break;
-#endif
- case PMD_SIZE:
- contig_ptes = 1;
- break;
- case CONT_PMD_SIZE:
- *pgsize = PMD_SIZE;
- contig_ptes = CONT_PMDS;
- break;
- case CONT_PTE_SIZE:
- *pgsize = PAGE_SIZE;
- contig_ptes = CONT_PTES;
- break;
- }
-
- return contig_ptes;
-}
-
-pte_t huge_ptep_get(pte_t *ptep)
-{
- int ncontig, i;
- size_t pgsize;
- pte_t orig_pte = ptep_get(ptep);
-
- if (!pte_present(orig_pte) || !pte_cont(orig_pte))
- return orig_pte;
-
- ncontig = num_contig_ptes(page_size(pte_page(orig_pte)), &pgsize);
- for (i = 0; i < ncontig; i++, ptep++) {
- pte_t pte = ptep_get(ptep);
-
- if (pte_dirty(pte))
- orig_pte = pte_mkdirty(orig_pte);
-
- if (pte_young(pte))
- orig_pte = pte_mkyoung(orig_pte);
- }
- return orig_pte;
-}
-
/*
* Changing some bits of contiguous entries requires us to follow a
* Break-Before-Make approach, breaking the whole contiguous set
@@ -250,7 +199,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
unsigned long pfn, dpfn;
pgprot_t hugeprot;
- ncontig = num_contig_ptes(sz, &pgsize);
+ ncontig = arch_contpte_get_num_contig(ptep, sz, &pgsize);
if (!pte_present(pte)) {
for (i = 0; i < ncontig; i++, ptep++, addr += pgsize)
@@ -397,7 +346,7 @@ void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
int i, ncontig;
size_t pgsize;
- ncontig = num_contig_ptes(sz, &pgsize);
+ ncontig = arch_contpte_get_num_contig(NULL, sz, &pgsize);
for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
pte_clear(mm, addr, ptep);
@@ -19,6 +19,7 @@ config RISCV
select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2
select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
select ARCH_HAS_BINFMT_FLAT
+ select ARCH_HAS_CONTPTE if RISCV_ISA_SVNAPOT
select ARCH_HAS_CURRENT_STACK_POINTER
select ARCH_HAS_DEBUG_VIRTUAL if MMU
select ARCH_HAS_DEBUG_VM_PGTABLE
@@ -47,7 +47,7 @@ pte_t huge_ptep_get(pte_t *ptep);
pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags);
#define arch_make_huge_pte arch_make_huge_pte
-#endif /*CONFIG_RISCV_ISA_SVNAPOT*/
+#endif /* CONFIG_RISCV_ISA_SVNAPOT */
#include <asm-generic/hugetlb.h>
@@ -302,6 +302,7 @@ static inline unsigned long pte_napot(pte_t pte)
{
return pte_val(pte) & _PAGE_NAPOT;
}
+#define pte_cont pte_napot
#define pte_valid_napot(pte) (pte_present(pte) && pte_napot(pte))
@@ -3,30 +3,6 @@
#include <linux/err.h>
#ifdef CONFIG_RISCV_ISA_SVNAPOT
-pte_t huge_ptep_get(pte_t *ptep)
-{
- unsigned long pte_num;
- int i;
- pte_t orig_pte = ptep_get(ptep);
-
- if (!pte_present(orig_pte) || !pte_napot(orig_pte))
- return orig_pte;
-
- pte_num = napot_pte_num(napot_cont_order(orig_pte));
-
- for (i = 0; i < pte_num; i++, ptep++) {
- pte_t pte = ptep_get(ptep);
-
- 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_pte_alloc(struct mm_struct *mm,
struct vm_area_struct *vma,
unsigned long addr,
@@ -1001,6 +1001,9 @@ config IDLE_PAGE_TRACKING
config ARCH_HAS_CACHE_LINE_SIZE
bool
+config ARCH_HAS_CONTPTE
+ bool
+
config ARCH_HAS_CURRENT_STACK_POINTER
bool
help
@@ -90,6 +90,7 @@ obj-$(CONFIG_MIGRATION) += migrate.o
obj-$(CONFIG_NUMA) += memory-tiers.o
obj-$(CONFIG_DEVICE_MIGRATION) += migrate_device.o
obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += huge_memory.o khugepaged.o
+obj-$(CONFIG_ARCH_HAS_CONTPTE) += contpte.o
obj-$(CONFIG_PAGE_COUNTER) += page_counter.o
obj-$(CONFIG_MEMCG) += memcontrol.o vmpressure.o
ifdef CONFIG_SWAP
new file mode 100644
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2024 Rivos Inc.
+ */
+
+#include <linux/mm.h>
+#include <linux/pgtable.h>
+#include <linux/hugetlb.h>
+
+/*
+ * Any arch that wants to use that needs to define:
+ * * contpte macros
+ * - pte_cont()
+ * - arch_contpte_get_num_contig()
+ */
+
+/*
+ * This file implements the following contpte aware API:
+ * huge_ptep_get()
+ */
+
+pte_t huge_ptep_get(pte_t *ptep)
+{
+ int ncontig, i;
+ size_t pgsize;
+ pte_t orig_pte = ptep_get(ptep);
+
+ if (!pte_present(orig_pte) || !pte_cont(orig_pte))
+ return orig_pte;
+
+ ncontig = arch_contpte_get_num_contig(ptep,
+ page_size(pte_page(orig_pte)),
+ &pgsize);
+
+ for (i = 0; i < ncontig; i++, ptep++) {
+ pte_t pte = ptep_get(ptep);
+
+ if (pte_dirty(pte))
+ orig_pte = pte_mkdirty(orig_pte);
+
+ if (pte_young(pte))
+ orig_pte = pte_mkyoung(orig_pte);
+ }
+ return orig_pte;
+}