The patch titled Subject: hugetlb: fix race condition in hugetlb_fault() has been added to the -mm tree. Its filename is hugetlb-fix-race-condition-in-hugetlb_fault.patch Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/SubmitChecklist when testing your code *** The -mm tree is included into linux-next and is updated there every 3-4 working days ------------------------------------------------------ From: Chris Metcalf <cmetcalf@xxxxxxxxxx> Subject: hugetlb: fix race condition in hugetlb_fault() The race is as follows. Suppose a multi-threaded task forks a new process (on cpu A), thus bumping up the ref count on all the pages. While the fork is occurring (and thus we have marked all the PTEs as read-only), another thread in the original process (on cpu B) tries to write to a huge page, taking an access violation from the write-protect and calling hugetlb_cow(). Now, suppose the fork() fails. It will undo the COW and decrement the ref count on the pages, so the ref count on the huge page drops back to 1. Meanwhile hugetlb_cow() also decrements the ref count by one on the original page, since the original address space doesn't need it any more, having copied a new page to replace the original page. This leaves the ref count at zero, and when we call unlock_page(), we panic. fork on CPU A fault on CPU B ============= ============== ... down_write(&parent->mmap_sem); down_write_nested(&child->mmap_sem); ... while duplicating vmas if error break; ... up_write(&child->mmap_sem); up_write(&parent->mmap_sem); ... down_read(&parent->mmap_sem); ... lock_page(page); handle COW page_mapcount(old_page) == 2 alloc and prepare new_page ... handle error page_remove_rmap(page); put_page(page); ... fold new_page into pte page_remove_rmap(page); put_page(page); ... oops ==> unlock_page(page); up_read(&parent->mmap_sem); The solution is to take an extra reference to the page while we are holding the lock on it. Signed-off-by: Chris Metcalf <cmetcalf@xxxxxxxxxx> Reviewed-by: Hillf Danton <dhillf@xxxxxxxxx> Cc: Michal Hocko <mhocko@xxxxxxx> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx> Cc: Hugh Dickins <hughd@xxxxxxxxxx> Cc: <stable@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- mm/hugetlb.c | 2 ++ 1 file changed, 2 insertions(+) diff -puN mm/hugetlb.c~hugetlb-fix-race-condition-in-hugetlb_fault mm/hugetlb.c --- a/mm/hugetlb.c~hugetlb-fix-race-condition-in-hugetlb_fault +++ a/mm/hugetlb.c @@ -2792,6 +2792,7 @@ int hugetlb_fault(struct mm_struct *mm, * so no worry about deadlock. */ page = pte_page(entry); + get_page(page); if (page != pagecache_page) lock_page(page); @@ -2823,6 +2824,7 @@ out_page_table_lock: } if (page != pagecache_page) unlock_page(page); + put_page(page); out_mutex: mutex_unlock(&hugetlb_instantiation_mutex); _ Subject: Subject: hugetlb: fix race condition in hugetlb_fault() Patches currently in -mm which might be from cmetcalf@xxxxxxxxxx are origin.patch linux-next.patch hugetlb-fix-race-condition-in-hugetlb_fault.patch list_debug-warn-for-adding-something-already-in-the-list.patch c-r-ipc-message-queue-receive-cleanup.patch c-r-ipc-message-queue-stealing-feature-introduced.patch -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html