On (01/18/16 15:36), Minchan Kim wrote:
[..]
> > --- a/mm/zsmalloc.c
> > +++ b/mm/zsmalloc.c
> > @@ -1635,8 +1635,8 @@ static int migrate_zspage(struct zs_pool *pool, struct size_class *class,
> > free_obj = obj_malloc(d_page, class, handle);
> > zs_object_copy(free_obj, used_obj, class);
> > index++;
> > + /* This also effectively unpins the handle */
>
> As reply of Vlastimil, I relied that I guess it doesn't work.
> We shouldn't omit unpin_tag and we should add WRITE_ONCE in
> record_obj.
>
> As well, it's worth to dobule check with locking guys.
> I will send updated version.
but would WRITE_ONCE() tell the compiler that there is a dependency?
__write_once_size() does not even issue a barrier for sizes <= 8 (our
case).
include/linux/compiler.h
static __always_inline void __write_once_size(volatile void *p, void *res, int size)
{
switch (size) {
case 1: *(volatile __u8 *)p = *(__u8 *)res; break;
case 2: *(volatile __u16 *)p = *(__u16 *)res; break;
case 4: *(volatile __u32 *)p = *(__u32 *)res; break;
case 8: *(volatile __u64 *)p = *(__u64 *)res; break;
default:
barrier();
__builtin_memcpy((void *)p, (const void *)res, size);
barrier();
}
}
#define WRITE_ONCE(x, val) \
({ \
union { typeof(x) __val; char __c[1]; } __u = \
{ .__val = (__force typeof(x)) (val) }; \
__write_once_size(&(x), __u.__c, sizeof(x)); \
__u.__val; \
})
so, even if clear_bit_unlock/test_and_set_bit_lock do smp_mb or
barrier(), there is no corresponding barrier from record_obj()->WRITE_ONCE().
so I don't think WRITE_ONCE() will help the compiler, or am I missing
something?
.... add a barrier() to record_obj()?
-ss
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>