From 1c59827d1da9bcd6970800d4f8a031b5859e8b4c Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Wed, 19 Oct 2005 21:23:43 -0700 Subject: [PATCH] mm: hugetlb truncation fixes hugetlbfs allows truncation of its files (should it?), but hugetlb.c often forgets that: crashes and misaccounting ensue. copy_hugetlb_page_range better grab the src page_table_lock since we don't want to guess what happens if concurrently truncated. unmap_hugepage_range rss accounting must not assume the full range was mapped. follow_hugetlb_page must guard with page_table_lock and be prepared to exit early. Restyle copy_hugetlb_page_range with a for loop like the others there. Signed-off-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 35 +++++++++++++++++++++-------------- 1 file changed, 21 insertions(+), 14 deletions(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 901ac523a1c3..a1b30d45459e 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -274,21 +274,22 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, { pte_t *src_pte, *dst_pte, entry; struct page *ptepage; - unsigned long addr = vma->vm_start; - unsigned long end = vma->vm_end; + unsigned long addr; - while (addr < end) { + for (addr = vma->vm_start; addr < vma->vm_end; addr += HPAGE_SIZE) { dst_pte = huge_pte_alloc(dst, addr); if (!dst_pte) goto nomem; + spin_lock(&src->page_table_lock); src_pte = huge_pte_offset(src, addr); - BUG_ON(!src_pte || pte_none(*src_pte)); /* prefaulted */ - entry = *src_pte; - ptepage = pte_page(entry); - get_page(ptepage); - add_mm_counter(dst, rss, HPAGE_SIZE / PAGE_SIZE); - set_huge_pte_at(dst, addr, dst_pte, entry); - addr += HPAGE_SIZE; + if (src_pte && !pte_none(*src_pte)) { + entry = *src_pte; + ptepage = pte_page(entry); + get_page(ptepage); + add_mm_counter(dst, rss, HPAGE_SIZE / PAGE_SIZE); + set_huge_pte_at(dst, addr, dst_pte, entry); + } + spin_unlock(&src->page_table_lock); } return 0; @@ -323,8 +324,8 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, page = pte_page(pte); put_page(page); + add_mm_counter(mm, rss, - (HPAGE_SIZE / PAGE_SIZE)); } - add_mm_counter(mm, rss, -((end - start) >> PAGE_SHIFT)); flush_tlb_range(vma, start, end); } @@ -403,6 +404,7 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, BUG_ON(!is_vm_hugetlb_page(vma)); vpfn = vaddr/PAGE_SIZE; + spin_lock(&mm->page_table_lock); while (vaddr < vma->vm_end && remainder) { if (pages) { @@ -415,8 +417,13 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, * indexing below to work. */ pte = huge_pte_offset(mm, vaddr & HPAGE_MASK); - /* hugetlb should be locked, and hence, prefaulted */ - WARN_ON(!pte || pte_none(*pte)); + /* the hugetlb file might have been truncated */ + if (!pte || pte_none(*pte)) { + remainder = 0; + if (!i) + i = -EFAULT; + break; + } page = &pte_page(*pte)[vpfn % (HPAGE_SIZE/PAGE_SIZE)]; @@ -434,7 +441,7 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, --remainder; ++i; } - + spin_unlock(&mm->page_table_lock); *length = remainder; *position = vaddr; -- cgit v1.2.3-59-g8ed1b