diff options
Diffstat (limited to 'arch/riscv/mm/hugetlbpage.c')
| -rw-r--r-- | arch/riscv/mm/hugetlbpage.c | 166 |
1 files changed, 124 insertions, 42 deletions
diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c index 96225a8533ad..375dd96bb4a0 100644 --- a/arch/riscv/mm/hugetlbpage.c +++ b/arch/riscv/mm/hugetlbpage.c @@ -3,7 +3,7 @@ #include <linux/err.h> #ifdef CONFIG_RISCV_ISA_SVNAPOT -pte_t huge_ptep_get(pte_t *ptep) +pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { unsigned long pte_num; int i; @@ -54,7 +54,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, } if (sz == PMD_SIZE) { - if (want_pmd_share(vma, addr) && pud_none(*pud)) + if (want_pmd_share(vma, addr) && pud_none(pudp_get(pud))) pte = huge_pmd_share(mm, vma, addr, pud); else pte = (pte_t *)pmd_alloc(mm, pud, addr); @@ -93,11 +93,11 @@ pte_t *huge_pte_offset(struct mm_struct *mm, pmd_t *pmd; pgd = pgd_offset(mm, addr); - if (!pgd_present(*pgd)) + if (!pgd_present(pgdp_get(pgd))) return NULL; p4d = p4d_offset(pgd, addr); - if (!p4d_present(*p4d)) + if (!p4d_present(p4dp_get(p4d))) return NULL; pud = pud_offset(p4d, addr); @@ -105,7 +105,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm, /* must be pud huge, non-present or none */ return (pte_t *)pud; - if (!pud_present(*pud)) + if (!pud_present(pudp_get(pud))) return NULL; pmd = pmd_offset(pud, addr); @@ -113,7 +113,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm, /* must be pmd huge, non-present or none */ return (pte_t *)pmd; - if (!pmd_present(*pmd)) + if (!pmd_present(pmdp_get(pmd))) return NULL; for_each_napot_order(order) { @@ -125,25 +125,48 @@ pte_t *huge_pte_offset(struct mm_struct *mm, return pte; } -static pte_t get_clear_contig(struct mm_struct *mm, - unsigned long addr, - pte_t *ptep, - unsigned long pte_num) +unsigned long hugetlb_mask_last_page(struct hstate *h) { - pte_t orig_pte = ptep_get(ptep); - unsigned long i; + unsigned long hp_size = huge_page_size(h); - for (i = 0; i < pte_num; i++, addr += PAGE_SIZE, ptep++) { - pte_t pte = ptep_get_and_clear(mm, addr, ptep); + switch (hp_size) { +#ifndef __PAGETABLE_PMD_FOLDED + case PUD_SIZE: + return P4D_SIZE - PUD_SIZE; +#endif + case PMD_SIZE: + return PUD_SIZE - PMD_SIZE; + case napot_cont_size(NAPOT_CONT64KB_ORDER): + return PMD_SIZE - napot_cont_size(NAPOT_CONT64KB_ORDER); + default: + break; + } - if (pte_dirty(pte)) - orig_pte = pte_mkdirty(orig_pte); + return 0UL; +} - if (pte_young(pte)) - orig_pte = pte_mkyoung(orig_pte); +static pte_t get_clear_contig(struct mm_struct *mm, + unsigned long addr, + pte_t *ptep, + unsigned long ncontig) +{ + pte_t pte, tmp_pte; + bool present; + + pte = ptep_get_and_clear(mm, addr, ptep); + present = pte_present(pte); + while (--ncontig) { + ptep++; + addr += PAGE_SIZE; + tmp_pte = ptep_get_and_clear(mm, addr, ptep); + if (present) { + if (pte_dirty(tmp_pte)) + pte = pte_mkdirty(pte); + if (pte_young(tmp_pte)) + pte = pte_mkyoung(pte); + } } - - return orig_pte; + return pte; } static pte_t get_clear_contig_flush(struct mm_struct *mm, @@ -177,20 +200,74 @@ 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); +} + +static int num_contig_ptes_from_size(unsigned long sz, size_t *pgsize) +{ + unsigned long hugepage_shift; + + 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; + + *pgsize = 1 << hugepage_shift; + + return sz >> hugepage_shift; +} + +/* + * 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) + pte_t pte, + unsigned long sz) { + size_t pgsize; int i, pte_num; + pte_num = num_contig_ptes_from_size(sz, &pgsize); + + 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); } @@ -227,15 +304,16 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma, pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, - pte_t *ptep) + pte_t *ptep, unsigned long sz) { + size_t pgsize; 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 = napot_pte_num(napot_cont_order(orig_pte)); + pte_num = num_contig_ptes_from_size(sz, &pgsize); return get_clear_contig(mm, addr, ptep, pte_num); } @@ -285,7 +363,8 @@ void huge_pte_clear(struct mm_struct *mm, pte_t *ptep, unsigned long sz) { - pte_t pte = READ_ONCE(*ptep); + size_t pgsize; + pte_t pte = ptep_get(ptep); int i, pte_num; if (!pte_napot(pte)) { @@ -293,12 +372,13 @@ void huge_pte_clear(struct mm_struct *mm, return; } - pte_num = napot_pte_num(napot_cont_order(pte)); - for (i = 0; i < pte_num; i++, addr += PAGE_SIZE, ptep++) + pte_num = num_contig_ptes_from_size(sz, &pgsize); + + for (i = 0; i < pte_num; i++, addr += pgsize, ptep++) pte_clear(mm, addr, ptep); } -static __init bool is_napot_size(unsigned long size) +static bool is_napot_size(unsigned long size) { unsigned long order; @@ -326,24 +406,14 @@ arch_initcall(napot_hugetlbpages_init); #else -static __init bool is_napot_size(unsigned long size) +static bool is_napot_size(unsigned long size) { return false; } #endif /*CONFIG_RISCV_ISA_SVNAPOT*/ -int pud_huge(pud_t pud) -{ - return pud_leaf(pud); -} - -int pmd_huge(pmd_t pmd) -{ - return pmd_leaf(pmd); -} - -bool __init arch_hugetlb_valid_size(unsigned long size) +static bool __hugetlb_valid_size(unsigned long size) { if (size == HPAGE_SIZE) return true; @@ -355,6 +425,18 @@ bool __init arch_hugetlb_valid_size(unsigned long size) return false; } +bool __init arch_hugetlb_valid_size(unsigned long size) +{ + return __hugetlb_valid_size(size); +} + +#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION +bool arch_hugetlb_migration_supported(struct hstate *h) +{ + return __hugetlb_valid_size(huge_page_size(h)); +} +#endif + #ifdef CONFIG_CONTIG_ALLOC static __init int gigantic_pages_init(void) { |