[16/25] mm: avoid null pointer access in vm_struct via /proc/vmallocinfo

From: Greg KH
Date: Tue Nov 22 2011 - 20:03:36 EST


2.6.32-longterm review patch. If anyone has any objections, please let me know.

------------------
Content-Length: 5721
Lines: 166

From: Mitsuo Hayasaka <mitsuo.hayasaka.hu@xxxxxxxxxxx>

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 happen:
In __vmalloc_node() 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.

Patch:
This patch adds 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 <mitsuo.hayasaka.hu@xxxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Namhyung Kim <namhyung@xxxxxxxxx>
Cc: "Paul E. McKenney" <paulmck@xxxxxxxxxxxxxxxxxx>
Cc: Jeremy Fitzhardinge <jeremy.fitzhardinge@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxx>
---

include/linux/vmalloc.h | 1
mm/vmalloc.c | 67 +++++++++++++++++++++++++++++++++++-------------
2 files changed, 51 insertions(+), 17 deletions(-)

--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -13,6 +13,7 @@ struct vm_area_struct; /* vma defining
#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 */

/*
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1203,17 +1203,22 @@ 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) {
@@ -1225,6 +1230,13 @@ static void insert_vmalloc_vm(struct vm_
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)
@@ -1263,7 +1275,18 @@ static struct vm_struct *__get_vm_area_n
return NULL;
}

- insert_vmalloc_vm(area, va, flags, caller);
+ /*
+ * When this function is called from __vmalloc_node,
+ * 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;
}

@@ -1338,17 +1361,20 @@ struct vm_struct *remove_vm_area(const v
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 +1594,9 @@ static void *__vmalloc_node(unsigned lon
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 +1604,12 @@ static void *__vmalloc_node(unsigned lon
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.


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/