diff options
Diffstat (limited to 'mm/hugetlb.c')
| -rw-r--r-- | mm/hugetlb.c | 156 |
1 files changed, 145 insertions, 11 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 249c92917eb4..931525822396 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1322,6 +1322,106 @@ int PageHeadHuge(struct page *page_head) return get_compound_page_dtor(page_head) == free_huge_page; } +/* + * Find address_space associated with hugetlbfs page. + * Upon entry page is locked and page 'was' mapped although mapped state + * could change. If necessary, use anon_vma to find vma and associated + * address space. The returned mapping may be stale, but it can not be + * invalid as page lock (which is held) is required to destroy mapping. + */ +static struct address_space *_get_hugetlb_page_mapping(struct page *hpage) +{ + struct anon_vma *anon_vma; + pgoff_t pgoff_start, pgoff_end; + struct anon_vma_chain *avc; + struct address_space *mapping = page_mapping(hpage); + + /* Simple file based mapping */ + if (mapping) + return mapping; + + /* + * Even anonymous hugetlbfs mappings are associated with an + * underlying hugetlbfs file (see hugetlb_file_setup in mmap + * code). Find a vma associated with the anonymous vma, and + * use the file pointer to get address_space. + */ + anon_vma = page_lock_anon_vma_read(hpage); + if (!anon_vma) + return mapping; /* NULL */ + + /* Use first found vma */ + pgoff_start = page_to_pgoff(hpage); + pgoff_end = pgoff_start + hpage_nr_pages(hpage) - 1; + anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, + pgoff_start, pgoff_end) { + struct vm_area_struct *vma = avc->vma; + + mapping = vma->vm_file->f_mapping; + break; + } + + anon_vma_unlock_read(anon_vma); + return mapping; +} + +/* + * Find and lock address space (mapping) in write mode. + * + * Upon entry, the page is locked which allows us to find the mapping + * even in the case of an anon page. However, locking order dictates + * the i_mmap_rwsem be acquired BEFORE the page lock. This is hugetlbfs + * specific. So, we first try to lock the sema while still holding the + * page lock. If this works, great! If not, then we need to drop the + * page lock and then acquire i_mmap_rwsem and reacquire page lock. Of + * course, need to revalidate state along the way. + */ +struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage) +{ + struct address_space *mapping, *mapping2; + + mapping = _get_hugetlb_page_mapping(hpage); +retry: + if (!mapping) + return mapping; + + /* + * If no contention, take lock and return + */ + if (i_mmap_trylock_write(mapping)) + return mapping; + + /* + * Must drop page lock and wait on mapping sema. + * Note: Once page lock is dropped, mapping could become invalid. + * As a hack, increase map count until we lock page again. + */ + atomic_inc(&hpage->_mapcount); + unlock_page(hpage); + i_mmap_lock_write(mapping); + lock_page(hpage); + atomic_add_negative(-1, &hpage->_mapcount); + + /* verify page is still mapped */ + if (!page_mapped(hpage)) { + i_mmap_unlock_write(mapping); + return NULL; + } + + /* + * Get address space again and verify it is the same one + * we locked. If not, drop lock and retry. + */ + mapping2 = _get_hugetlb_page_mapping(hpage); + if (mapping2 != mapping) { + i_mmap_unlock_write(mapping); + mapping = mapping2; + goto retry; + } + + return mapping; +} + pgoff_t __basepage_index(struct page *page) { struct page *page_head = compound_head(page); @@ -3312,6 +3412,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, int cow; struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); + struct address_space *mapping = vma->vm_file->f_mapping; struct mmu_notifier_range range; int ret = 0; @@ -3322,6 +3423,14 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, vma->vm_start, vma->vm_end); mmu_notifier_invalidate_range_start(&range); + } else { + /* + * For shared mappings i_mmap_rwsem must be held to call + * huge_pte_alloc, otherwise the returned ptep could go + * away if part of a shared pmd and another thread calls + * huge_pmd_unshare. + */ + i_mmap_lock_read(mapping); } for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) { @@ -3399,6 +3508,8 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, if (cow) mmu_notifier_invalidate_range_end(&range); + else + i_mmap_unlock_read(mapping); return ret; } @@ -3847,13 +3958,15 @@ retry: }; /* - * hugetlb_fault_mutex must be dropped before - * handling userfault. Reacquire after handling - * fault to make calling code simpler. + * hugetlb_fault_mutex and i_mmap_rwsem must be + * dropped before handling userfault. Reacquire + * after handling fault to make calling code simpler. */ hash = hugetlb_fault_mutex_hash(mapping, idx); mutex_unlock(&hugetlb_fault_mutex_table[hash]); + i_mmap_unlock_read(mapping); ret = handle_userfault(&vmf, VM_UFFD_MISSING); + i_mmap_lock_read(mapping); mutex_lock(&hugetlb_fault_mutex_table[hash]); goto out; } @@ -4018,6 +4131,11 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, ptep = huge_pte_offset(mm, haddr, huge_page_size(h)); if (ptep) { + /* + * Since we hold no locks, ptep could be stale. That is + * OK as we are only making decisions based on content and + * not actually modifying content here. + */ entry = huge_ptep_get(ptep); if (unlikely(is_hugetlb_entry_migration(entry))) { migration_entry_wait_huge(vma, mm, ptep); @@ -4031,14 +4149,29 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, return VM_FAULT_OOM; } + /* + * Acquire i_mmap_rwsem before calling huge_pte_alloc and hold + * until finished with ptep. This prevents huge_pmd_unshare from + * being called elsewhere and making the ptep no longer valid. + * + * ptep could have already be assigned via huge_pte_offset. That + * is OK, as huge_pte_alloc will return the same value unless + * something has changed. + */ mapping = vma->vm_file->f_mapping; - idx = vma_hugecache_offset(h, vma, haddr); + i_mmap_lock_read(mapping); + ptep = huge_pte_alloc(mm, haddr, huge_page_size(h)); + if (!ptep) { + i_mmap_unlock_read(mapping); + return VM_FAULT_OOM; + } /* * Serialize hugepage allocation and instantiation, so that we don't * get spurious allocation failures if two CPUs race to instantiate * the same page in the page cache. */ + idx = vma_hugecache_offset(h, vma, haddr); hash = hugetlb_fault_mutex_hash(mapping, idx); mutex_lock(&hugetlb_fault_mutex_table[hash]); @@ -4126,6 +4259,7 @@ out_ptl: } out_mutex: mutex_unlock(&hugetlb_fault_mutex_table[hash]); + i_mmap_unlock_read(mapping); /* * Generally it's safe to hold refcount during waiting page lock. But * here we just wait to defer the next page fault to avoid busy loop and @@ -4776,10 +4910,12 @@ void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc() * and returns the corresponding pte. While this is not necessary for the * !shared pmd case because we can allocate the pmd later as well, it makes the - * code much cleaner. pmd allocation is essential for the shared case because - * pud has to be populated inside the same i_mmap_rwsem section - otherwise - * racing tasks could either miss the sharing (see huge_pte_offset) or select a - * bad pmd for sharing. + * code much cleaner. + * + * This routine must be called with i_mmap_rwsem held in at least read mode. + * For hugetlbfs, this prevents removal of any page table entries associated + * with the address space. This is important as we are setting up sharing + * based on existing page table entries (mappings). */ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) { @@ -4796,7 +4932,6 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) if (!vma_shareable(vma, addr)) return (pte_t *)pmd_alloc(mm, pud, addr); - i_mmap_lock_read(mapping); vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) { if (svma == vma) continue; @@ -4826,7 +4961,6 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) spin_unlock(ptl); out: pte = (pte_t *)pmd_alloc(mm, pud, addr); - i_mmap_unlock_read(mapping); return pte; } @@ -4837,7 +4971,7 @@ out: * 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. + * Called with page table lock held and i_mmap_rwsem held in write mode. * * returns: 1 successfully unmapped a shared pte page * 0 the underlying pte page is not shared, or it is the last user |