[PATCH] Fix futexes in huge pages

Using a futex in a large page causes a kernel lockup in __pin_page() -
because __pin_page's page revalidation uses follow_page(), and follow_page()
doesn't work for hugepages.

The patch fixes up follow_page() to return the appropriate 4k page for
hugepages.

This incurs a vma lookup for each follow_page(), which is considerable
overhead in some situations.  We only _need_ to do this if the architecture
cannot determin a page's hugeness from the contents of the PMD.

So this patch is a "reference" implementation for, say, PPC BAT-based
hugepages.

2 files changed, 19 insertions, 3 deletions

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 325d91ba012a..6b2f606c08f7 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -20,16 +20,28 @@ int hugetlb_prefault(struct address_space *, struct vm_area_struct *);
 void huge_page_release(struct page *);
 int hugetlb_report_meminfo(char *);
 int is_hugepage_mem_enough(size_t);
-
+struct page *follow_huge_addr(struct mm_struct *mm, struct vm_area_struct *vma,
+			unsigned long address, int write);
+struct vm_area_struct *hugepage_vma(struct mm_struct *mm,
+					unsigned long address);
 extern int htlbpage_max;
 
+static inline void
+mark_mm_hugetlb(struct mm_struct *mm, struct vm_area_struct *vma)
+{
+	if (is_vm_hugetlb_page(vma))
+		mm->used_hugetlb = 1;
+}
+
 #else /* !CONFIG_HUGETLB_PAGE */
+
 static inline int is_vm_hugetlb_page(struct vm_area_struct *vma)
 {
 	return 0;
 }
 
-#define follow_hugetlb_page(m,v,p,vs,a,b,i)		({ BUG(); 0; })
+#define follow_hugetlb_page(m,v,p,vs,a,b,i)	({ BUG(); 0; })
+#define follow_huge_addr(mm, vma, addr, write)	0
 #define copy_hugetlb_page_range(src, dst, vma)	({ BUG(); 0; })
 #define hugetlb_prefault(mapping, vma)		({ BUG(); 0; })
 #define zap_hugepage_range(vma, start, len)	BUG()
@@ -37,6 +49,8 @@ static inline int is_vm_hugetlb_page(struct vm_area_struct *vma)
 #define huge_page_release(page)			BUG()
 #define is_hugepage_mem_enough(size)		0
 #define hugetlb_report_meminfo(buf)		0
+#define hugepage_vma(mm, addr)			0
+#define mark_mm_hugetlb(mm, vma)		do { } while (0)
 
 #endif /* !CONFIG_HUGETLB_PAGE */
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 3a1367bacd1c..648d4d3ace3c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -201,7 +201,9 @@ struct mm_struct {
 	unsigned long swap_address;
 
 	unsigned dumpable:1;
-
+#ifdef CONFIG_HUGETLB_PAGE
+	int used_hugetlb;
+#endif
 	/* Architecture-specific MM context */
 	mm_context_t context;