From: "Ken Chen" __unmap_hugepage_range() is buggy that it does not preserve dirty state of huge_pte when unmapping hugepage range. It causes data corruption in the event of dop_caches being used by sys admin. For example, an application creates a hugetlb file, modify pages, then unmap it. While leaving the hugetlb file alive, comes along sys admin doing a "echo 3 > /proc/sys/vm/drop_caches". drop_pagecache_sb() will happily free all pages that aren't marked dirty if there are no active mapping. Later when application remaps the hugetlb file back and all data are gone, triggering catastrophic flip over on application. Not only that, the internal resv_huge_pages count will also get all messed up. Fix it up by marking page dirty appropriately. Signed-off-by: Ken Chen Cc: "Nish Aravamudan" Cc: Adam Litke Cc: David Gibson Acked-by: William Irwin Cc: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- fs/hugetlbfs/inode.c | 5 ++++- mm/hugetlb.c | 2 ++ 2 files changed, 6 insertions(+), 1 deletion(-) --- linux-2.6.20.1.orig/fs/hugetlbfs/inode.c +++ linux-2.6.20.1/fs/hugetlbfs/inode.c @@ -449,10 +449,13 @@ static int hugetlbfs_symlink(struct inod } /* - * For direct-IO reads into hugetlb pages + * mark the head page dirty */ static int hugetlbfs_set_page_dirty(struct page *page) { + struct page *head = (struct page *)page_private(page); + + SetPageDirty(head); return 0; } --- linux-2.6.20.1.orig/mm/hugetlb.c +++ linux-2.6.20.1/mm/hugetlb.c @@ -389,6 +389,8 @@ void __unmap_hugepage_range(struct vm_ar continue; page = pte_page(pte); + if (pte_dirty(pte)) + set_page_dirty(page); list_add(&page->lru, &page_list); } spin_unlock(&mm->page_table_lock); -- - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/