[PATCH 1/2] Encode huge page size for VM_FAULT_HWPOISON errors

[Andi Kleen]

From: Andi Kleen <ak@xxxxxxxxxxxxxxx>

This fixes a problem introduced with the hugetlb hwpoison handling

The user space SIGBUS signalling wants to know the size of the hugepage
that caused a HWPOISON fault.

Unfortunately the architecture page fault handlers do not have easy
access to the struct page.

Pass the information out in the fault error code instead.

I added a separate VM_FAULT_HWPOISON_LARGE bit for this case and encode
the hpage index in some free upper bits of the fault code. The small
page hwpoison keeps stays with the VM_FAULT_HWPOISON name to minimize
changes.

Also add code to hugetlb.h to convert that index into a page shift.

Will be used in a further patch.

Cc: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
Cc: fengguang.wu@xxxxxxxxx
Signed-off-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
---
 include/linux/hugetlb.h |    6 ++++++
 include/linux/mm.h      |   12 ++++++++++--
 mm/hugetlb.c            |    6 ++++--
 mm/memory.c             |    3 ++-
 4 files changed, 22 insertions(+), 5 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 796f30e..943c76b 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -307,6 +307,11 @@ static inline struct hstate *page_hstate(struct page *page)
 	return size_to_hstate(PAGE_SIZE << compound_order(page));
 }
 
+static inline unsigned hstate_index_to_shift(unsigned index)
+{
+	return hstates[index].order + PAGE_SHIFT;
+}
+
 #else
 struct hstate {};
 #define alloc_huge_page_node(h, nid) NULL
@@ -324,6 +329,7 @@ static inline unsigned int pages_per_huge_page(struct hstate *h)
 {
 	return 1;
 }
+#define hstate_index_to_shift(index) 0
 #endif
 
 #endif /* _LINUX_HUGETLB_H */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 74949fb..f7e9efc 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -718,12 +718,20 @@ static inline int page_mapped(struct page *page)
 #define VM_FAULT_SIGBUS	0x0002
 #define VM_FAULT_MAJOR	0x0004
 #define VM_FAULT_WRITE	0x0008	/* Special case for get_user_pages */
-#define VM_FAULT_HWPOISON 0x0010	/* Hit poisoned page */
+#define VM_FAULT_HWPOISON 0x0010	/* Hit poisoned small page */
+#define VM_FAULT_HWPOISON_LARGE 0x0020  /* Hit poisoned large page. Index encoded in upper bits */
 
 #define VM_FAULT_NOPAGE	0x0100	/* ->fault installed the pte, not return page */
 #define VM_FAULT_LOCKED	0x0200	/* ->fault locked the returned page */
 
-#define VM_FAULT_ERROR	(VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON)
+#define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */
+
+#define VM_FAULT_ERROR	(VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | \
+			 VM_FAULT_HWPOISON_LARGE)
+
+/* Encode hstate index for a hwpoisoned large page */
+#define VM_FAULT_SET_HINDEX(x) ((x) << 12)
+#define VM_FAULT_GET_HINDEX(x) (((x) >> 12) & 0xf)
 
 /*
  * Can be called by the pagefault handler when it gets a VM_FAULT_OOM.
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 67cd032..96991de 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2589,7 +2589,8 @@ retry:
 		 * So we need to block hugepage fault by PG_hwpoison bit check.
 		 */
 		if (unlikely(PageHWPoison(page))) {
-			ret = VM_FAULT_HWPOISON;
+			ret = VM_FAULT_HWPOISON | 
+			      VM_FAULT_SET_HINDEX(h - hstates);
 			goto backout_unlocked;
 		}
 		page_dup_rmap(page);
@@ -2656,7 +2657,8 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 			migration_entry_wait(mm, (pmd_t *)ptep, address);
 			return 0;
 		} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
-			return VM_FAULT_HWPOISON;
+			return VM_FAULT_HWPOISON_LARGE | 
+			       VM_FAULT_SET_HINDEX(h - hstates);
 	}
 
 	ptep = huge_pte_alloc(mm, address, huge_page_size(h));
diff --git a/mm/memory.c b/mm/memory.c
index 71b161b..8cea8f3 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1450,7 +1450,8 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 					if (ret & VM_FAULT_OOM)
 						return i ? i : -ENOMEM;
 					if (ret &
-					    (VM_FAULT_HWPOISON|VM_FAULT_SIGBUS))
+					    (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE|
+					     VM_FAULT_SIGBUS))
 						return i ? i : -EFAULT;
 					BUG();
 				}
-- 
1.7.1

--
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/