Subject: + mm-thp-give-transparent-hugepage-code-a-separate-copy_page.patch added to -mm tree
To: dave.hansen@xxxxxxxxxxxxxxx,dhillf@xxxxxxxxx,mgorman@xxxxxxx,n-horiguchi@xxxxxxxxxxxxx,stable@xxxxxxxxxxxxxxx
From: akpm@xxxxxxxxxxxxxxxxxxxx
Date: Mon, 18 Nov 2013 13:25:15 -0800
The patch titled
Subject: mm: thp: give transparent hugepage code a separate copy_page()
has been added to the -mm tree. Its filename is
mm-thp-give-transparent-hugepage-code-a-separate-copy_page.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-thp-give-transparent-hugepage-code-a-separate-copy_page.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-thp-give-transparent-hugepage-code-a-separate-copy_page.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Subject: mm: thp: give transparent hugepage code a separate copy_page()
Right now, the migration code in migrate_page_copy() uses copy_huge_page()
for hugetlbfs and thp pages:
if (PageHuge(page) || PageTransHuge(page))
copy_huge_page(newpage, page);
So, yay for code reuse. But:
void copy_huge_page(struct page *dst, struct page *src)
{
struct hstate *h = page_hstate(src);
and a non-hugetlbfs page has no page_hstate(). This works 99% of the time
because page_hstate() determines the hstate from the page order alone.
Since the page order of a THP page matches the default hugetlbfs page
order, it works.
But, if you change the default huge page size on the boot command-line
(say default_hugepagesz=1G), then we might not even *have* a 2MB hstate so
page_hstate() returns null and copy_huge_page() oopses pretty fast since
copy_huge_page() dereferences the hstate:
void copy_huge_page(struct page *dst, struct page *src)
{
struct hstate *h = page_hstate(src);
if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES)) {
...
This patch creates a copy_high_order_page() which can
be used on THP pages.
I believe the bug was introduced in b32967ff101:
Author: Mel Gorman <mgorman@xxxxxxx>
Date: Mon Nov 19 12:35:47 2012 +0000
mm: numa: Add THP migration for the NUMA working set scanning fault case.
Signed-off-by: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Hillf Danton <dhillf@xxxxxxxxx>
Cc: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
Cc: <stable@xxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/huge_mm.h | 16 ++++++++++++++++
mm/huge_memory.c | 12 ++++++++++++
mm/migrate.c | 6 ++++--
3 files changed, 32 insertions(+), 2 deletions(-)
diff -puN include/linux/huge_mm.h~mm-thp-give-transparent-hugepage-code-a-separate-copy_page include/linux/huge_mm.h
--- a/include/linux/huge_mm.h~mm-thp-give-transparent-hugepage-code-a-separate-copy_page
+++ a/include/linux/huge_mm.h
@@ -178,6 +178,10 @@ static inline struct page *compound_tran
extern int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, pmd_t pmd, pmd_t *pmdp);
+extern void copy_high_order_page(struct page *newpage,
+ struct page *oldpage,
+ int order);
+
#else /* CONFIG_TRANSPARENT_HUGEPAGE */
#define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })
#define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; })
@@ -228,6 +232,18 @@ static inline int do_huge_pmd_numa_page(
return 0;
}
+/*
+ * The non-stub version of this code is probably usable
+ * generically but its only user is thp at the moment,
+ * so enforce that with a BUG()
+ */
+static inline void copy_high_order_page(struct page *newpage,
+ struct page *oldpage,
+ int order)
+{
+ BUG();
+}
+
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif /* _LINUX_HUGE_MM_H */
diff -puN mm/huge_memory.c~mm-thp-give-transparent-hugepage-code-a-separate-copy_page mm/huge_memory.c
--- a/mm/huge_memory.c~mm-thp-give-transparent-hugepage-code-a-separate-copy_page
+++ a/mm/huge_memory.c
@@ -2927,3 +2927,15 @@ void __vma_adjust_trans_huge(struct vm_a
split_huge_page_address(next->vm_mm, nstart);
}
}
+
+void copy_high_order_page(struct page *newpage,
+ struct page *oldpage,
+ int order)
+{
+ int i;
+
+ for (i = 0; i < (1<<order); i++) {
+ cond_resched();
+ copy_highpage(newpage + i, oldpage + i);
+ }
+}
diff -puN mm/migrate.c~mm-thp-give-transparent-hugepage-code-a-separate-copy_page mm/migrate.c
--- a/mm/migrate.c~mm-thp-give-transparent-hugepage-code-a-separate-copy_page
+++ a/mm/migrate.c
@@ -448,8 +448,10 @@ void migrate_page_copy(struct page *newp
{
int cpupid;
- if (PageHuge(page) || PageTransHuge(page))
- copy_huge_page(newpage, page);
+ if (PageHuge(page))
+ copy_huge_page(newpage, page);
+ else if(PageTransHuge(page))
+ copy_high_order_page(newpage, page, HPAGE_PMD_ORDER);
else
copy_highpage(newpage, page);
_
Patches currently in -mm which might be from dave.hansen@xxxxxxxxxxxxxxx are
origin.patch
mm-thp-give-transparent-hugepage-code-a-separate-copy_page.patch
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html