diff options
Diffstat (limited to 'mm/hugetlb.c')
| -rw-r--r-- | mm/hugetlb.c | 81 |
1 files changed, 57 insertions, 24 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 01a685963a99..bca110617f51 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -83,7 +83,7 @@ struct mutex *hugetlb_fault_mutex_table ____cacheline_aligned_in_smp; /* Forward declaration */ static int hugetlb_acct_memory(struct hstate *h, long delta); static void hugetlb_unshare_pmds(struct vm_area_struct *vma, - unsigned long start, unsigned long end); + unsigned long start, unsigned long end, bool take_locks); static inline bool subpool_is_free(struct hugepage_subpool *spool) { @@ -4165,26 +4165,40 @@ static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr) { if (addr & ~(huge_page_mask(hstate_vma(vma)))) return -EINVAL; + return 0; +} +void hugetlb_split(struct vm_area_struct *vma, unsigned long addr) +{ /* * PMD sharing is only possible for PUD_SIZE-aligned address ranges * in HugeTLB VMAs. If we will lose PUD_SIZE alignment due to this * split, unshare PMDs in the PUD_SIZE interval surrounding addr now. + * This function is called in the middle of a VMA split operation, with + * MM, VMA and rmap all write-locked to prevent concurrent page table + * walks (except hardware and gup_fast()). */ + mmap_assert_write_locked(vma->vm_mm); + i_mmap_assert_write_locked(vma->vm_file->f_mapping); + if (addr & ~PUD_MASK) { - /* - * hugetlb_vm_op_split is called right before we attempt to - * split the VMA. We will need to unshare PMDs in the old and - * new VMAs, so let's unshare before we split. - */ unsigned long floor = addr & PUD_MASK; unsigned long ceil = floor + PUD_SIZE; - if (floor >= vma->vm_start && ceil <= vma->vm_end) - hugetlb_unshare_pmds(vma, floor, ceil); + if (floor >= vma->vm_start && ceil <= vma->vm_end) { + /* + * Locking: + * Use take_locks=false here. + * The file rmap lock is already held. + * The hugetlb VMA lock can't be taken when we already + * hold the file rmap lock, and we don't need it because + * its purpose is to synchronize against concurrent page + * table walks, which are not possible thanks to the + * locks held by our caller. + */ + hugetlb_unshare_pmds(vma, floor, ceil, /* take_locks = */ false); + } } - - return 0; } static unsigned long hugetlb_vm_op_pagesize(struct vm_area_struct *vma) @@ -6032,7 +6046,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, spte = huge_pte_offset(svma->vm_mm, saddr, vma_mmu_pagesize(svma)); if (spte) { - get_page(virt_to_page(spte)); + atomic_inc(&virt_to_page(spte)->pt_share_count); break; } } @@ -6047,7 +6061,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, (pmd_t *)((unsigned long)spte & PAGE_MASK)); mm_inc_nr_pmds(mm); } else { - put_page(virt_to_page(spte)); + atomic_dec(&virt_to_page(spte)->pt_share_count); } spin_unlock(ptl); out: @@ -6058,11 +6072,7 @@ out: /* * unmap huge page backed by shared pte. * - * Hugetlb pte page is ref counted at the time of mapping. If pte is shared - * indicated by page_count > 1, unmap is achieved by clearing pud and - * decrementing the ref count. If count == 1, the pte page is not shared. - * - * Called with page table lock held and i_mmap_rwsem held in write mode. + * Called with page table lock held. * * returns: 1 successfully unmapped a shared pte page * 0 the underlying pte page is not shared, or it is the last user @@ -6070,17 +6080,26 @@ out: int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long *addr, pte_t *ptep) { + unsigned long sz = huge_page_size(hstate_vma(vma)); pgd_t *pgd = pgd_offset(mm, *addr); p4d_t *p4d = p4d_offset(pgd, *addr); pud_t *pud = pud_offset(p4d, *addr); i_mmap_assert_write_locked(vma->vm_file->f_mapping); - BUG_ON(page_count(virt_to_page(ptep)) == 0); - if (page_count(virt_to_page(ptep)) == 1) + if (sz != PMD_SIZE) + return 0; + if (!atomic_read(&virt_to_page(ptep)->pt_share_count)) return 0; pud_clear(pud); - put_page(virt_to_page(ptep)); + /* + * Once our caller drops the rmap lock, some other process might be + * using this page table as a normal, non-hugetlb page table. + * Wait for pending gup_fast() in other threads to finish before letting + * that happen. + */ + tlb_remove_table_sync_one(); + atomic_dec(&virt_to_page(ptep)->pt_share_count); mm_dec_nr_pmds(mm); /* * This update of passed address optimizes loops sequentially @@ -6369,9 +6388,16 @@ void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason) } } +/* + * If @take_locks is false, the caller must ensure that no concurrent page table + * access can happen (except for gup_fast() and hardware page walks). + * If @take_locks is true, we take the hugetlb VMA lock (to lock out things like + * concurrent page fault handling) and the file rmap lock. + */ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, unsigned long start, - unsigned long end) + unsigned long end, + bool take_locks) { struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); @@ -6394,7 +6420,11 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, start, end); mmu_notifier_invalidate_range_start(&range); - i_mmap_lock_write(vma->vm_file->f_mapping); + if (take_locks) { + i_mmap_lock_write(vma->vm_file->f_mapping); + } else { + i_mmap_assert_write_locked(vma->vm_file->f_mapping); + } for (address = start; address < end; address += PUD_SIZE) { unsigned long tmp = address; @@ -6407,7 +6437,9 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, spin_unlock(ptl); } flush_hugetlb_tlb_range(vma, start, end); - i_mmap_unlock_write(vma->vm_file->f_mapping); + if (take_locks) { + i_mmap_unlock_write(vma->vm_file->f_mapping); + } /* * No need to call mmu_notifier_invalidate_range(), see * Documentation/vm/mmu_notifier.rst. @@ -6422,7 +6454,8 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { hugetlb_unshare_pmds(vma, ALIGN(vma->vm_start, PUD_SIZE), - ALIGN_DOWN(vma->vm_end, PUD_SIZE)); + ALIGN_DOWN(vma->vm_end, PUD_SIZE), + /* take_locks = */ true); } #ifdef CONFIG_CMA |