Soft offline events for hugetlb pages return -EBUSY when page migration
succeeded and dissolve_free_huge_page() failed, which can happen when
there're surplus hugepages. We should judge pass/fail of soft offline by
checking whether the raw error page was finally contained or not (i.e.
the result of set_hwpoison_free_buddy_page()), so this behavior is wrong.
This problem was introduced by the following change of commit 6bc9b56433b76
("mm: fix race on soft-offlining"):
if (ret > 0)
ret = -EIO;
} else {
- if (PageHuge(page))
- dissolve_free_huge_page(page);
+ /*
+ * We set PG_hwpoison only when the migration source hugepage
+ * was successfully dissolved, because otherwise hwpoisoned
+ * hugepage remains on free hugepage list, then userspace will
+ * find it as SIGBUS by allocation failure. That's not expected
+ * in soft-offlining.
+ */
+ ret = dissolve_free_huge_page(page);
+ if (!ret) {
+ if (set_hwpoison_free_buddy_page(page))
+ num_poisoned_pages_inc();
+ }
}
return ret;
}
, so a simple fix is to restore the PageHuge precheck, but my code
reading shows that we already have PageHuge check in
dissolve_free_huge_page() with hugetlb_lock, which is better place to
check it. And currently dissolve_free_huge_page() returns -EBUSY for
!PageHuge but that's simply wrong because that that case should be
considered as success (meaning that "the given hugetlb was already
dissolved.")
This change affects other callers of dissolve_free_huge_page(),
which are also cleaned up by this patch.
Reported-by: Chen, Jerry T <jerry.t.chen@xxxxxxxxx>
Signed-off-by: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
Fixes: 6bc9b56433b76 ("mm: fix race on soft-offlining")
Cc: <stable@xxxxxxxxxxxxxxx> # v4.19+
---
mm/hugetlb.c | 15 +++++++++------
mm/memory-failure.c | 7 +++----
2 files changed, 12 insertions(+), 10 deletions(-)
diff --git v5.1-rc6-mmotm-2019-04-25-16-30/mm/hugetlb.c v5.1-rc6-mmotm-2019-04-25-16-30_patched/mm/hugetlb.c
index bf58cee..385899f 100644
--- v5.1-rc6-mmotm-2019-04-25-16-30/mm/hugetlb.c
+++ v5.1-rc6-mmotm-2019-04-25-16-30_patched/mm/hugetlb.c
@@ -1518,7 +1518,12 @@ int dissolve_free_huge_page(struct page *page)
int rc = -EBUSY;
spin_lock(&hugetlb_lock);
- if (PageHuge(page) && !page_count(page)) {
+ if (!PageHuge(page)) {
+ rc = 0;
+ goto out;
+ }
+
+ if (!page_count(page)) {
struct page *head = compound_head(page);
struct hstate *h = page_hstate(head);
int nid = page_to_nid(head);
@@ -1563,11 +1568,9 @@ int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn)
for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << minimum_order) {
page = pfn_to_page(pfn);
- if (PageHuge(page) && !page_count(page)) {
- rc = dissolve_free_huge_page(page);
- if (rc)
- break;
- }
+ rc = dissolve_free_huge_page(page);
+ if (rc)
+ break;
}
return rc;
diff --git v5.1-rc6-mmotm-2019-04-25-16-30/mm/memory-failure.c v5.1-rc6-mmotm-2019-04-25-16-30_patched/mm/memory-failure.c
index fc8b517..3a83e27 100644
--- v5.1-rc6-mmotm-2019-04-25-16-30/mm/memory-failure.c
+++ v5.1-rc6-mmotm-2019-04-25-16-30_patched/mm/memory-failure.c
@@ -1733,6 +1733,8 @@ static int soft_offline_huge_page(struct page *page, int flags)
if (!ret) {
if (set_hwpoison_free_buddy_page(page))
num_poisoned_pages_inc();
+ else
+ ret = -EBUSY;
}
}
return ret;
@@ -1857,11 +1859,8 @@ static int soft_offline_in_use_page(struct page *page, int flags)
static int soft_offline_free_page(struct page *page)
{
- int rc = 0;
- struct page *head = compound_head(page);
+ int rc = dissolve_free_huge_page(page);
- if (PageHuge(head))
- rc = dissolve_free_huge_page(page);
if (!rc) {
if (set_hwpoison_free_buddy_page(page))
num_poisoned_pages_inc();
--
2.7.0
