diff options
Diffstat (limited to 'mm/hugetlb.c')
| -rw-r--r-- | mm/hugetlb.c | 30 |
1 files changed, 17 insertions, 13 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c index a088f593a80..cb362f761f1 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -44,14 +44,14 @@ static void clear_huge_page(struct page *page, unsigned long addr) } static void copy_huge_page(struct page *dst, struct page *src, - unsigned long addr) + unsigned long addr, struct vm_area_struct *vma) { int i; might_sleep(); for (i = 0; i < HPAGE_SIZE/PAGE_SIZE; i++) { cond_resched(); - copy_user_highpage(dst + i, src + i, addr + i*PAGE_SIZE); + copy_user_highpage(dst + i, src + i, addr + i*PAGE_SIZE, vma); } } @@ -73,7 +73,7 @@ static struct page *dequeue_huge_page(struct vm_area_struct *vma, for (z = zonelist->zones; *z; z++) { nid = zone_to_nid(*z); - if (cpuset_zone_allowed(*z, GFP_HIGHUSER) && + if (cpuset_zone_allowed_softwall(*z, GFP_HIGHUSER) && !list_empty(&hugepage_freelists[nid])) break; } @@ -109,7 +109,7 @@ static int alloc_fresh_huge_page(void) if (nid == MAX_NUMNODES) nid = first_node(node_online_map); if (page) { - page[1].lru.next = (void *)free_huge_page; /* dtor */ + set_compound_page_dtor(page, free_huge_page); spin_lock(&hugetlb_lock); nr_huge_pages++; nr_huge_pages_node[page_to_nid(page)]++; @@ -344,7 +344,6 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, entry = *src_pte; ptepage = pte_page(entry); get_page(ptepage); - add_mm_counter(dst, file_rss, HPAGE_SIZE / PAGE_SIZE); set_huge_pte_at(dst, addr, dst_pte, entry); } spin_unlock(&src->page_table_lock); @@ -365,6 +364,11 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, pte_t pte; struct page *page; struct page *tmp; + /* + * A page gathering list, protected by per file i_mmap_lock. The + * lock is used to avoid list corruption from multiple unmapping + * of the same page since we are using page->lru. + */ LIST_HEAD(page_list); WARN_ON(!is_vm_hugetlb_page(vma)); @@ -372,24 +376,21 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, BUG_ON(end & ~HPAGE_MASK); spin_lock(&mm->page_table_lock); - - /* Update high watermark before we lower rss */ - update_hiwater_rss(mm); - for (address = start; address < end; address += HPAGE_SIZE) { ptep = huge_pte_offset(mm, address); if (!ptep) continue; + if (huge_pmd_unshare(mm, &address, ptep)) + continue; + pte = huge_ptep_get_and_clear(mm, address, ptep); if (pte_none(pte)) continue; page = pte_page(pte); list_add(&page->lru, &page_list); - add_mm_counter(mm, file_rss, (int) -(HPAGE_SIZE / PAGE_SIZE)); } - spin_unlock(&mm->page_table_lock); flush_tlb_range(vma, start, end); list_for_each_entry_safe(page, tmp, &page_list, lru) { @@ -441,7 +442,7 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, } spin_unlock(&mm->page_table_lock); - copy_huge_page(new_page, old_page, address); + copy_huge_page(new_page, old_page, address, vma); spin_lock(&mm->page_table_lock); ptep = huge_pte_offset(mm, address & HPAGE_MASK); @@ -515,7 +516,6 @@ retry: if (!pte_none(*ptep)) goto backout; - add_mm_counter(mm, file_rss, HPAGE_SIZE / PAGE_SIZE); new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE) && (vma->vm_flags & VM_SHARED))); set_huge_pte_at(mm, address, ptep, new_pte); @@ -653,11 +653,14 @@ void hugetlb_change_protection(struct vm_area_struct *vma, BUG_ON(address >= end); flush_cache_range(vma, address, end); + spin_lock(&vma->vm_file->f_mapping->i_mmap_lock); spin_lock(&mm->page_table_lock); for (; address < end; address += HPAGE_SIZE) { ptep = huge_pte_offset(mm, address); if (!ptep) continue; + if (huge_pmd_unshare(mm, &address, ptep)) + continue; if (!pte_none(*ptep)) { pte = huge_ptep_get_and_clear(mm, address, ptep); pte = pte_mkhuge(pte_modify(pte, newprot)); @@ -666,6 +669,7 @@ void hugetlb_change_protection(struct vm_area_struct *vma, } } spin_unlock(&mm->page_table_lock); + spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock); flush_tlb_range(vma, start, end); } |