From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932207Ab2HOUGJ (ORCPT ); Wed, 15 Aug 2012 16:06:09 -0400 Received: from mail.windriver.com ([147.11.1.11]:37100 "EHLO mail.windriver.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757048Ab2HOTwW (ORCPT ); Wed, 15 Aug 2012 15:52:22 -0400 From: Paul Gortmaker To: , CC: Mitsuo Hayasaka , Andrew Morton , David Rientjes , Namhyung Kim , "Paul E. McKenney" , Jeremy Fitzhardinge , Linus Torvalds , Paul Gortmaker Subject: [v2.6.34-stable 134/165] mm: avoid null pointer access in vm_struct via /proc/vmallocinfo Date: Wed, 15 Aug 2012 15:47:58 -0400 Message-ID: <1345060109-9187-135-git-send-email-paul.gortmaker@windriver.com> X-Mailer: git-send-email 1.7.12.rc2 In-Reply-To: <1345060109-9187-1-git-send-email-paul.gortmaker@windriver.com> References: <1345060109-9187-1-git-send-email-paul.gortmaker@windriver.com> MIME-Version: 1.0 Content-Type: text/plain Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Mitsuo Hayasaka ------------------- This is a commit scheduled for the next v2.6.34 longterm release. http://git.kernel.org/?p=linux/kernel/git/paulg/longterm-queue-2.6.34.git If you see a problem with using this for longterm, please comment. ------------------- commit f5252e009d5b87071a919221e4f6624184005368 upstream. The /proc/vmallocinfo shows information about vmalloc allocations in vmlist that is a linklist of vm_struct. It, however, may access pages field of vm_struct where a page was not allocated. This results in a null pointer access and leads to a kernel panic. Why this happens: In __vmalloc_node_range() called from vmalloc(), newly allocated vm_struct is added to vmlist at __get_vm_area_node() and then, some fields of vm_struct such as nr_pages and pages are set at __vmalloc_area_node(). In other words, it is added to vmlist before it is fully initialized. At the same time, when the /proc/vmallocinfo is read, it accesses the pages field of vm_struct according to the nr_pages field at show_numa_info(). Thus, a null pointer access happens. The patch adds the newly allocated vm_struct to the vmlist *after* it is fully initialized. So, it can avoid accessing the pages field with unallocated page when show_numa_info() is called. Signed-off-by: Mitsuo Hayasaka Cc: Andrew Morton Cc: David Rientjes Cc: Namhyung Kim Cc: "Paul E. McKenney" Cc: Jeremy Fitzhardinge Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds [PG: .34 has VMALLOC_START/END vs. start/end in f5252e009d5] Signed-off-by: Paul Gortmaker --- include/linux/vmalloc.h | 1 + mm/vmalloc.c | 66 ++++++++++++++++++++++++++++++++++++------------- 2 files changed, 50 insertions(+), 17 deletions(-) diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 227c2a5..346df02 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -13,6 +13,7 @@ struct vm_area_struct; /* vma defining user mapping in mm_types.h */ #define VM_MAP 0x00000004 /* vmap()ed pages */ #define VM_USERMAP 0x00000008 /* suitable for remap_vmalloc_range */ #define VM_VPAGES 0x00000010 /* buffer for pages was vmalloc'ed */ +#define VM_UNLIST 0x00000020 /* vm_struct is not listed in vmlist */ /* bits [20..32] reserved for arch specific ioremap internals */ /* diff --git a/mm/vmalloc.c b/mm/vmalloc.c index d44abdd..3843789 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1204,18 +1204,22 @@ EXPORT_SYMBOL_GPL(map_vm_area); DEFINE_RWLOCK(vmlist_lock); struct vm_struct *vmlist; -static void insert_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, +static void setup_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, unsigned long flags, void *caller) { - struct vm_struct *tmp, **p; - vm->flags = flags; vm->addr = (void *)va->va_start; vm->size = va->va_end - va->va_start; vm->caller = caller; va->private = vm; va->flags |= VM_VM_AREA; +} + +static void insert_vmalloc_vmlist(struct vm_struct *vm) +{ + struct vm_struct *tmp, **p; + vm->flags &= ~VM_UNLIST; write_lock(&vmlist_lock); for (p = &vmlist; (tmp = *p) != NULL; p = &tmp->next) { if (tmp->addr >= vm->addr) @@ -1226,6 +1230,13 @@ static void insert_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, write_unlock(&vmlist_lock); } +static void insert_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, + unsigned long flags, void *caller) +{ + setup_vmalloc_vm(vm, va, flags, caller); + insert_vmalloc_vmlist(vm); +} + static struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long align, unsigned long flags, unsigned long start, unsigned long end, int node, gfp_t gfp_mask, void *caller) @@ -1264,7 +1275,18 @@ static struct vm_struct *__get_vm_area_node(unsigned long size, return NULL; } - insert_vmalloc_vm(area, va, flags, caller); + /* + * When this function is called from __vmalloc_node_range, + * we do not add vm_struct to vmlist here to avoid + * accessing uninitialized members of vm_struct such as + * pages and nr_pages fields. They will be set later. + * To distinguish it from others, we use a VM_UNLIST flag. + */ + if (flags & VM_UNLIST) + setup_vmalloc_vm(area, va, flags, caller); + else + insert_vmalloc_vm(area, va, flags, caller); + return area; } @@ -1339,17 +1361,20 @@ struct vm_struct *remove_vm_area(const void *addr) va = find_vmap_area((unsigned long)addr); if (va && va->flags & VM_VM_AREA) { struct vm_struct *vm = va->private; - struct vm_struct *tmp, **p; - /* - * remove from list and disallow access to this vm_struct - * before unmap. (address range confliction is maintained by - * vmap.) - */ - write_lock(&vmlist_lock); - for (p = &vmlist; (tmp = *p) != vm; p = &tmp->next) - ; - *p = tmp->next; - write_unlock(&vmlist_lock); + + if (!(vm->flags & VM_UNLIST)) { + struct vm_struct *tmp, **p; + /* + * remove from list and disallow access to + * this vm_struct before unmap. (address range + * confliction is maintained by vmap.) + */ + write_lock(&vmlist_lock); + for (p = &vmlist; (tmp = *p) != vm; p = &tmp->next) + ; + *p = tmp->next; + write_unlock(&vmlist_lock); + } vmap_debug_free_range(va->va_start, va->va_end); free_unmap_vmap_area(va); @@ -1568,8 +1593,9 @@ static void *__vmalloc_node(unsigned long size, unsigned long align, if (!size || (size >> PAGE_SHIFT) > totalram_pages) return NULL; - area = __get_vm_area_node(size, align, VM_ALLOC, VMALLOC_START, - VMALLOC_END, node, gfp_mask, caller); + area = __get_vm_area_node(size, align, VM_ALLOC | VM_UNLIST, + VMALLOC_START, VMALLOC_END, node, + gfp_mask, caller); if (!area) return NULL; @@ -1577,6 +1603,12 @@ static void *__vmalloc_node(unsigned long size, unsigned long align, addr = __vmalloc_area_node(area, gfp_mask, prot, node, caller); /* + * In this function, newly allocated vm_struct is not added + * to vmlist at __get_vm_area_node(). so, it is added here. + */ + insert_vmalloc_vmlist(area); + + /* * A ref_count = 3 is needed because the vm_struct and vmap_area * structures allocated in the __get_vm_area_node() function contain * references to the virtual address of the vmalloc'ed block. -- 1.7.12.rc2