On Wed, May 11, 2022 at 04:15:17PM -0700, Minchan Kim wrote:
> On Wed, May 11, 2022 at 04:13:10PM -0700, John Hubbard wrote:
> > On 5/11/22 16:08, Minchan Kim wrote:
> > > > OK, so the code checks the wrong item each time. But the code really
> > > > only needs to know "is either _CMA or _ISOLATE set?". And so you
> > >
> > > Yes.
> > >
> > > > can just sidestep the entire question by writing it like this:
> > > >
> > > > int mt = get_pageblock_migratetype(page);
> > > >
> > > > if (mt & (MIGRATE_ISOLATE | MIGRATE_CMA))
> > > > return false;
> > >
> > > I am confused. Isn't it same question?
> > >
> > > set_pageblock_migratetype(MIGRATE_ISOLATE)
> > > if (get_pageblock_migrate(page) & MIGRATE_CMA)
> > >
> > > set_pageblock_migratetype(MIGRATE_CMA)
> > >
> > > if (get_pageblock_migrate(page) & MIGRATE_ISOLATE)
> >
> > Well no, because the "&" operation is a single operation on the CPU, and
> > isn't going to get split up like that.
>
> Oh, if that's true, yeah, I could live with it.
>
> Thanks, let me post next revision with commenting about that.
This is delta to confirm before posting next revision.
Are you okay with this one?
diff --git a/include/linux/mm.h b/include/linux/mm.h
index cbf79eb790e0..7b2df6780552 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1626,14 +1626,14 @@ static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma,
static inline bool is_pinnable_page(struct page *page)
{
#ifdef CONFIG_CMA
+ int mt = get_pageblock_migratetype(page);
+
/*
- * use volatile to use local variable mt instead of
- * refetching mt value.
+ * "&" operation would prevent compiler split up
+ * get_pageblock_migratetype two times for each
+ * condition check: refetching mt value two times.
*/
- int __mt = get_pageblock_migratetype(page);
- int mt = __READ_ONCE(__mt);
-
- if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE)
+ if (mt & (MIGRATE_ISOLATE | MIGRATE_CMA))
return false;
#endif
