Re: [PATCH] mm: kmemleak: Treat vm_struct as alternative reference to vmalloc'ed objects

[Catalin Marinas]

On Mon, May 22, 2017 at 11:19:08AM -0700, Andy Lutomirski wrote:
> On Mon, May 22, 2017 at 10:35 AM, Catalin Marinas
> <catalin.marinas@xxxxxxx> wrote:
> > Kmemleak requires that vmalloc'ed objects have a minimum reference count
> > of 2: one in the corresponding vm_struct object and the other owned by
> > the vmalloc() caller. There are cases, however, where the original
> > vmalloc() returned pointer is lost and, instead, a pointer to vm_struct
> > is stored (see free_thread_stack()). Kmemleak currently reports such
> > objects as leaks.
> >
> > This patch adds support for treating any surplus references to an object
> > as additional references to a specified object. It introduces the
> > kmemleak_vmalloc() API function which takes a vm_struct pointer and sets
> > its surplus reference passing to the actual vmalloc() returned pointer.
> > The __vmalloc_node_range() calling site has been modified accordingly.
> >
> > An unrelated minor change is included in this patch to change the type
> > of kmemleak_object.flags to unsigned int (previously unsigned long).
> >
> > Reported-by: "Luis R. Rodriguez" <mcgrof@xxxxxxxxxx>
> > Cc: Michal Hocko <mhocko@xxxxxxxxxx>
> > Cc: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
> > Signed-off-by: Catalin Marinas <catalin.marinas@xxxxxxx>
> > ---
> >
> > As per [1], I added support to use pointers to vm_struct as an
> > alternative way to avoid false positives when the original vmalloc()
> > pointer has been lost. This is slightly harder to reason about but it
> > seems to work for this use-case. I'm not aware of other cases (than
> > free_thread_stack()) where the original vmalloc() pointer is removed in
> > favour of a vm_struct one.
> >
> > An alternative implementation (simpler to understand), if preferred, is
> > to annotate alloc_thread_stack_node() and free_thread_stack() with
> > kmemleak_unignore()/kmemleak_ignore() calls and proper comments.
> >
> 
> I personally prefer the option in this patch.  It keeps the special
> case in kmemleak and the allocation code rather than putting it in the
> consumer code.
> 
> Also, I want to add an API at some point that vmallocs some memory and
> returns the vm_struct directly.  That won't work with explicit
> annotations in the caller because kmemleak might think it's leaked
> before the caller can execute the annotations.

While kmemleak delays the reporting of newly allocated objects to avoid
such race, we need to keep annotations to a minimum anyway (only for
special cases, definitely not for each caller of an allocation API). The
proposed kmemleak_vmalloc() API in this patch would cover your case
without any additional annotation.

-- 
Catalin