The patch titled
Subject: mm: hugetlb: soft-offline: dissolve source hugepage after successful migration
has been added to the -mm tree. Its filename is
mm-hugetlb-soft-offline-dissolve-source-hugepage-after-successful-migration.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-hugetlb-soft-offline-dissolve-source-hugepage-after-successful-migration.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-hugetlb-soft-offline-dissolve-source-hugepage-after-successful-migration.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: Anshuman Khandual <khandual@xxxxxxxxxxxxxxxxxx>
Subject: mm: hugetlb: soft-offline: dissolve source hugepage after successful migration
Currently hugepage migrated by soft-offline (i.e. due to correctable
memory errors) is contained as a hugepage, which means many non-error
pages in it are unreusable, i.e. wasted.
This patch solves this issue by dissolving source hugepages into buddy.
As done in previous patch, PageHWPoison is set only on a head page of the
error hugepage. Then in dissoliving we move the PageHWPoison flag to the
raw error page so that all healthy subpages return back to buddy.
Link: http://lkml.kernel.org/r/1496305019-5493-5-git-send-email-n-horiguchi@xxxxxxxxxxxxx
Signed-off-by: Anshuman Khandual <khandual@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/hugetlb.h | 2 ++
mm/hugetlb.c | 10 +++++++++-
mm/memory-failure.c | 5 +----
mm/migrate.c | 2 ++
4 files changed, 14 insertions(+), 5 deletions(-)
diff -puN include/linux/hugetlb.h~mm-hugetlb-soft-offline-dissolve-source-hugepage-after-successful-migration include/linux/hugetlb.h
--- a/include/linux/hugetlb.h~mm-hugetlb-soft-offline-dissolve-source-hugepage-after-successful-migration
+++ a/include/linux/hugetlb.h
@@ -472,6 +472,7 @@ static inline pgoff_t basepage_index(str
return __basepage_index(page);
}
+extern int dissolve_free_huge_page(struct page *page);
extern int dissolve_free_huge_pages(unsigned long start_pfn,
unsigned long end_pfn);
static inline bool hugepage_migration_supported(struct hstate *h)
@@ -557,6 +558,7 @@ static inline pgoff_t basepage_index(str
{
return page->index;
}
+#define dissolve_free_huge_page(p) 0
#define dissolve_free_huge_pages(s, e) 0
#define hugepage_migration_supported(h) false
diff -puN mm/hugetlb.c~mm-hugetlb-soft-offline-dissolve-source-hugepage-after-successful-migration mm/hugetlb.c
--- a/mm/hugetlb.c~mm-hugetlb-soft-offline-dissolve-source-hugepage-after-successful-migration
+++ a/mm/hugetlb.c
@@ -1459,7 +1459,7 @@ static int free_pool_huge_page(struct hs
* number of free hugepages would be reduced below the number of reserved
* hugepages.
*/
-static int dissolve_free_huge_page(struct page *page)
+int dissolve_free_huge_page(struct page *page)
{
int rc = 0;
@@ -1472,6 +1472,14 @@ static int dissolve_free_huge_page(struc
rc = -EBUSY;
goto out;
}
+ /*
+ * Move PageHWPoison flag from head page to the raw error page,
+ * which makes any subpages rather than the error page reusable.
+ */
+ if (PageHWPoison(head) && page != head) {
+ SetPageHWPoison(page);
+ ClearPageHWPoison(head);
+ }
list_del(&head->lru);
h->free_huge_pages--;
h->free_huge_pages_node[nid]--;
diff -puN mm/memory-failure.c~mm-hugetlb-soft-offline-dissolve-source-hugepage-after-successful-migration mm/memory-failure.c
--- a/mm/memory-failure.c~mm-hugetlb-soft-offline-dissolve-source-hugepage-after-successful-migration
+++ a/mm/memory-failure.c
@@ -1572,11 +1572,8 @@ static int soft_offline_huge_page(struct
if (ret > 0)
ret = -EIO;
} else {
- /* overcommit hugetlb page will be freed to buddy */
- SetPageHWPoison(page);
if (PageHuge(page))
- dequeue_hwpoisoned_huge_page(hpage);
- num_poisoned_pages_inc();
+ dissolve_free_huge_page(page);
}
return ret;
}
diff -puN mm/migrate.c~mm-hugetlb-soft-offline-dissolve-source-hugepage-after-successful-migration mm/migrate.c
--- a/mm/migrate.c~mm-hugetlb-soft-offline-dissolve-source-hugepage-after-successful-migration
+++ a/mm/migrate.c
@@ -1252,6 +1252,8 @@ put_anon:
out:
if (rc != -EAGAIN)
putback_active_hugepage(hpage);
+ if (reason == MR_MEMORY_FAILURE && !test_set_page_hwpoison(hpage))
+ num_poisoned_pages_inc();
/*
* If migration was not successful and there's a freeing callback, use
_
Patches currently in -mm which might be from khandual@xxxxxxxxxxxxxxxxxx are
mm-vmstat-standardize-file-operations-variable-names.patch
mm-madvise-enable-softhard-offline-of-hugetlb-pages-at-pgd-level.patch
mm-follow_page_mask-add-support-for-hugetlb-pgd-entries.patch
mm-hugetlb-soft-offline-dissolve-source-hugepage-after-successful-migration.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
