diff options
| -rw-r--r-- | include/linux/hugetlb.h | 6 | ||||
| -rw-r--r-- | mm/Kconfig | 10 | ||||
| -rw-r--r-- | mm/gup.c | 194 | ||||
| -rw-r--r-- | mm/pagewalk.c | 57 |
4 files changed, 9 insertions, 258 deletions
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index a951c0d06061..ecd0ceeea206 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -20,12 +20,6 @@ struct user_struct; struct mmu_gather; struct node; -#ifndef CONFIG_ARCH_HAS_HUGEPD -typedef struct { unsigned long pd; } hugepd_t; -#define is_hugepd(hugepd) (0) -#define __hugepd(x) ((hugepd_t) { (x) }) -#endif - void free_huge_folio(struct folio *folio); #ifdef CONFIG_HUGETLB_PAGE diff --git a/mm/Kconfig b/mm/Kconfig index 991fa9cf6137..60796402850e 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -1126,16 +1126,6 @@ config DMAPOOL_TEST config ARCH_HAS_PTE_SPECIAL bool -# -# Some architectures require a special hugepage directory format that is -# required to support multiple hugepage sizes. For example a4fe3ce76 -# "powerpc/mm: Allow more flexible layouts for hugepage pagetables" -# introduced it on powerpc. This allows for a more flexible hugepage -# pagetable layouts. -# -config ARCH_HAS_HUGEPD - bool - config MAPPING_DIRTY_HELPERS bool @@ -462,7 +462,7 @@ static inline void mm_set_has_pinned_flag(unsigned long *mm_flags) #ifdef CONFIG_MMU -#if defined(CONFIG_ARCH_HAS_HUGEPD) || defined(CONFIG_HAVE_GUP_FAST) +#ifdef CONFIG_HAVE_GUP_FAST static int record_subpages(struct page *page, unsigned long sz, unsigned long addr, unsigned long end, struct page **pages) @@ -572,154 +572,7 @@ static struct folio *try_grab_folio_fast(struct page *page, int refs, return folio; } -#endif /* CONFIG_ARCH_HAS_HUGEPD || CONFIG_HAVE_GUP_FAST */ - -#ifdef CONFIG_ARCH_HAS_HUGEPD -static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end, - unsigned long sz) -{ - unsigned long __boundary = (addr + sz) & ~(sz-1); - return (__boundary - 1 < end - 1) ? __boundary : end; -} - -/* - * Returns 1 if succeeded, 0 if failed, -EMLINK if unshare needed. - * - * NOTE: for the same entry, gup-fast and gup-slow can return different - * results (0 v.s. -EMLINK) depending on whether vma is available. This is - * the expected behavior, where we simply want gup-fast to fallback to - * gup-slow to take the vma reference first. - */ -static int gup_hugepte(struct vm_area_struct *vma, pte_t *ptep, unsigned long sz, - unsigned long addr, unsigned long end, unsigned int flags, - struct page **pages, int *nr, bool fast) -{ - unsigned long pte_end; - struct page *page; - struct folio *folio; - pte_t pte; - int refs; - - pte_end = (addr + sz) & ~(sz-1); - if (pte_end < end) - end = pte_end; - - pte = huge_ptep_get(vma->vm_mm, addr, ptep); - - if (!pte_access_permitted(pte, flags & FOLL_WRITE)) - return 0; - - /* hugepages are never "special" */ - VM_BUG_ON(!pfn_valid(pte_pfn(pte))); - - page = pte_page(pte); - refs = record_subpages(page, sz, addr, end, pages + *nr); - - if (fast) { - folio = try_grab_folio_fast(page, refs, flags); - if (!folio) - return 0; - } else { - folio = page_folio(page); - if (try_grab_folio(folio, refs, flags)) - return 0; - } - - if (unlikely(pte_val(pte) != pte_val(ptep_get(ptep)))) { - gup_put_folio(folio, refs, flags); - return 0; - } - - if (!pte_write(pte) && gup_must_unshare(vma, flags, &folio->page)) { - gup_put_folio(folio, refs, flags); - return -EMLINK; - } - - *nr += refs; - folio_set_referenced(folio); - return 1; -} - -/* - * NOTE: currently GUP for a hugepd is only possible on hugetlbfs file - * systems on Power, which does not have issue with folio writeback against - * GUP updates. When hugepd will be extended to support non-hugetlbfs or - * even anonymous memory, we need to do extra check as what we do with most - * of the other folios. See writable_file_mapping_allowed() and - * gup_fast_folio_allowed() for more information. - */ -static int gup_hugepd(struct vm_area_struct *vma, hugepd_t hugepd, - unsigned long addr, unsigned int pdshift, - unsigned long end, unsigned int flags, - struct page **pages, int *nr, bool fast) -{ - pte_t *ptep; - unsigned long sz = 1UL << hugepd_shift(hugepd); - unsigned long next; - int ret; - - ptep = hugepte_offset(hugepd, addr, pdshift); - do { - next = hugepte_addr_end(addr, end, sz); - ret = gup_hugepte(vma, ptep, sz, addr, end, flags, pages, nr, - fast); - if (ret != 1) - return ret; - } while (ptep++, addr = next, addr != end); - - return 1; -} - -static struct page *follow_hugepd(struct vm_area_struct *vma, hugepd_t hugepd, - unsigned long addr, unsigned int pdshift, - unsigned int flags, - struct follow_page_context *ctx) -{ - struct page *page; - struct hstate *h; - spinlock_t *ptl; - int nr = 0, ret; - pte_t *ptep; - - /* Only hugetlb supports hugepd */ - if (WARN_ON_ONCE(!is_vm_hugetlb_page(vma))) - return ERR_PTR(-EFAULT); - - h = hstate_vma(vma); - ptep = hugepte_offset(hugepd, addr, pdshift); - ptl = huge_pte_lock(h, vma->vm_mm, ptep); - ret = gup_hugepd(vma, hugepd, addr, pdshift, addr + PAGE_SIZE, - flags, &page, &nr, false); - spin_unlock(ptl); - - if (ret == 1) { - /* GUP succeeded */ - WARN_ON_ONCE(nr != 1); - ctx->page_mask = (1U << huge_page_order(h)) - 1; - return page; - } - - /* ret can be either 0 (translates to NULL) or negative */ - return ERR_PTR(ret); -} -#else /* CONFIG_ARCH_HAS_HUGEPD */ -static inline int gup_hugepd(struct vm_area_struct *vma, hugepd_t hugepd, - unsigned long addr, unsigned int pdshift, - unsigned long end, unsigned int flags, - struct page **pages, int *nr, bool fast) -{ - return 0; -} - -static struct page *follow_hugepd(struct vm_area_struct *vma, hugepd_t hugepd, - unsigned long addr, unsigned int pdshift, - unsigned int flags, - struct follow_page_context *ctx) -{ - return NULL; -} -#endif /* CONFIG_ARCH_HAS_HUGEPD */ - +#endif /* CONFIG_HAVE_GUP_FAST */ static struct page *no_page_table(struct vm_area_struct *vma, unsigned int flags, unsigned long address) @@ -1089,9 +942,6 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma, return no_page_table(vma, flags, address); if (!pmd_present(pmdval)) return no_page_table(vma, flags, address); - if (unlikely(is_hugepd(__hugepd(pmd_val(pmdval))))) - return follow_hugepd(vma, __hugepd(pmd_val(pmdval)), - address, PMD_SHIFT, flags, ctx); if (pmd_devmap(pmdval)) { ptl = pmd_lock(mm, pmd); page = follow_devmap_pmd(vma, address, pmd, flags, &ctx->pgmap); @@ -1142,9 +992,6 @@ static struct page *follow_pud_mask(struct vm_area_struct *vma, pud = READ_ONCE(*pudp); if (!pud_present(pud)) return no_page_table(vma, flags, address); - if (unlikely(is_hugepd(__hugepd(pud_val(pud))))) - return follow_hugepd(vma, __hugepd(pud_val(pud)), - address, PUD_SHIFT, flags, ctx); if (pud_leaf(pud)) { ptl = pud_lock(mm, pudp); page = follow_huge_pud(vma, address, pudp, flags, ctx); @@ -1170,10 +1017,6 @@ static struct page *follow_p4d_mask(struct vm_area_struct *vma, p4d = READ_ONCE(*p4dp); BUILD_BUG_ON(p4d_leaf(p4d)); - if (unlikely(is_hugepd(__hugepd(p4d_val(p4d))))) - return follow_hugepd(vma, __hugepd(p4d_val(p4d)), - address, P4D_SHIFT, flags, ctx); - if (!p4d_present(p4d) || p4d_bad(p4d)) return no_page_table(vma, flags, address); @@ -1217,10 +1060,7 @@ static struct page *follow_page_mask(struct vm_area_struct *vma, ctx->page_mask = 0; pgd = pgd_offset(mm, address); - if (unlikely(is_hugepd(__hugepd(pgd_val(*pgd))))) - page = follow_hugepd(vma, __hugepd(pgd_val(*pgd)), - address, PGDIR_SHIFT, flags, ctx); - else if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) + if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) page = no_page_table(vma, flags, address); else page = follow_p4d_mask(vma, address, pgd, flags, ctx); @@ -3362,15 +3202,6 @@ static int gup_fast_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, pages, nr)) return 0; - } else if (unlikely(is_hugepd(__hugepd(pmd_val(pmd))))) { - /* - * architecture have different format for hugetlbfs - * pmd format and THP pmd format - */ - if (gup_hugepd(NULL, __hugepd(pmd_val(pmd)), addr, - PMD_SHIFT, next, flags, pages, nr, - true) != 1) - return 0; } else if (!gup_fast_pte_range(pmd, pmdp, addr, next, flags, pages, nr)) return 0; @@ -3397,11 +3228,6 @@ static int gup_fast_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr, if (!gup_fast_pud_leaf(pud, pudp, addr, next, flags, pages, nr)) return 0; - } else if (unlikely(is_hugepd(__hugepd(pud_val(pud))))) { - if (gup_hugepd(NULL, __hugepd(pud_val(pud)), addr, - PUD_SHIFT, next, flags, pages, nr, - true) != 1) - return 0; } else if (!gup_fast_pmd_range(pudp, pud, addr, next, flags, pages, nr)) return 0; @@ -3425,13 +3251,8 @@ static int gup_fast_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr, if (!p4d_present(p4d)) return 0; BUILD_BUG_ON(p4d_leaf(p4d)); - if (unlikely(is_hugepd(__hugepd(p4d_val(p4d))))) { - if (gup_hugepd(NULL, __hugepd(p4d_val(p4d)), addr, - P4D_SHIFT, next, flags, pages, nr, - true) != 1) - return 0; - } else if (!gup_fast_pud_range(p4dp, p4d, addr, next, flags, - pages, nr)) + if (!gup_fast_pud_range(p4dp, p4d, addr, next, flags, + pages, nr)) return 0; } while (p4dp++, addr = next, addr != end); @@ -3455,11 +3276,6 @@ static void gup_fast_pgd_range(unsigned long addr, unsigned long end, if (!gup_fast_pgd_leaf(pgd, pgdp, addr, next, flags, pages, nr)) return; - } else if (unlikely(is_hugepd(__hugepd(pgd_val(pgd))))) { - if (gup_hugepd(NULL, __hugepd(pgd_val(pgd)), addr, - PGDIR_SHIFT, next, flags, pages, nr, - true) != 1) - return; } else if (!gup_fast_p4d_range(pgdp, pgd, addr, next, flags, pages, nr)) return; diff --git a/mm/pagewalk.c b/mm/pagewalk.c index f46c80b18ce4..ae2f08ce991b 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -73,45 +73,6 @@ static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, return err; } -#ifdef CONFIG_ARCH_HAS_HUGEPD -static int walk_hugepd_range(hugepd_t *phpd, unsigned long addr, - unsigned long end, struct mm_walk *walk, int pdshift) -{ - int err = 0; - const struct mm_walk_ops *ops = walk->ops; - int shift = hugepd_shift(*phpd); - int page_size = 1 << shift; - - if (!ops->pte_entry) - return 0; - - if (addr & (page_size - 1)) - return 0; - - for (;;) { - pte_t *pte; - - spin_lock(&walk->mm->page_table_lock); - pte = hugepte_offset(*phpd, addr, pdshift); - err = ops->pte_entry(pte, addr, addr + page_size, walk); - spin_unlock(&walk->mm->page_table_lock); - - if (err) - break; - if (addr >= end - page_size) - break; - addr += page_size; - } - return err; -} -#else -static int walk_hugepd_range(hugepd_t *phpd, unsigned long addr, - unsigned long end, struct mm_walk *walk, int pdshift) -{ - return 0; -} -#endif - static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, struct mm_walk *walk) { @@ -159,10 +120,7 @@ again: if (walk->vma) split_huge_pmd(walk->vma, pmd, addr); - if (is_hugepd(__hugepd(pmd_val(*pmd)))) - err = walk_hugepd_range((hugepd_t *)pmd, addr, next, walk, PMD_SHIFT); - else - err = walk_pte_range(pmd, addr, next, walk); + err = walk_pte_range(pmd, addr, next, walk); if (err) break; @@ -215,10 +173,7 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end, if (pud_none(*pud)) goto again; - if (is_hugepd(__hugepd(pud_val(*pud)))) - err = walk_hugepd_range((hugepd_t *)pud, addr, next, walk, PUD_SHIFT); - else - err = walk_pmd_range(pud, addr, next, walk); + err = walk_pmd_range(pud, addr, next, walk); if (err) break; } while (pud++, addr = next, addr != end); @@ -250,9 +205,7 @@ static int walk_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end, if (err) break; } - if (is_hugepd(__hugepd(p4d_val(*p4d)))) - err = walk_hugepd_range((hugepd_t *)p4d, addr, next, walk, P4D_SHIFT); - else if (ops->pud_entry || ops->pmd_entry || ops->pte_entry) + if (ops->pud_entry || ops->pmd_entry || ops->pte_entry) err = walk_pud_range(p4d, addr, next, walk); if (err) break; @@ -287,9 +240,7 @@ static int walk_pgd_range(unsigned long addr, unsigned long end, if (err) break; } - if (is_hugepd(__hugepd(pgd_val(*pgd)))) - err = walk_hugepd_range((hugepd_t *)pgd, addr, next, walk, PGDIR_SHIFT); - else if (ops->p4d_entry || ops->pud_entry || ops->pmd_entry || ops->pte_entry) + if (ops->p4d_entry || ops->pud_entry || ops->pmd_entry || ops->pte_entry) err = walk_p4d_range(pgd, addr, next, walk); if (err) break; |