@@ -149,6 +149,7 @@ bool hugetlb_reserve_pages(struct inode
long hugetlb_unreserve_pages(struct inode *inode, long start, long end,
long freed);
bool isolate_huge_page(struct page *page, struct list_head *list);
+int get_hwpoison_huge_page(struct page *page, bool *hugetlb);
void putback_active_hugepage(struct page *page);
void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason);
void free_huge_page(struct page *page);
@@ -339,6 +340,11 @@ static inline bool isolate_huge_page(str
return false;
}
+static inline int get_hwpoison_huge_page(struct page *page, bool *hugetlb)
+{
+ return 0;
+}
+
static inline void putback_active_hugepage(struct page *page)
{
}
@@ -5847,6 +5847,21 @@ unlock:
return ret;
}
+int get_hwpoison_huge_page(struct page *page, bool *hugetlb)
+{
+ int ret = 0;
+
+ *hugetlb = false;
+ spin_lock_irq(&hugetlb_lock);
+ if (PageHeadHuge(page)) {
+ *hugetlb = true;
+ if (HPageFreed(page) || HPageMigratable(page))
+ ret = get_page_unless_zero(page);
+ }
+ spin_unlock_irq(&hugetlb_lock);
+ return ret;
+}
+
void putback_active_hugepage(struct page *page)
{
spin_lock_irq(&hugetlb_lock);
@@ -959,8 +959,14 @@ static int page_action(struct page_state
static int __get_hwpoison_page(struct page *page)
{
struct page *head = compound_head(page);
+ int ret = 0;
+ bool hugetlb = false;
- if (!PageHuge(head) && PageTransHuge(head)) {
+ ret = get_hwpoison_huge_page(head, &hugetlb);
+ if (hugetlb)
+ return ret;
+
+ if (PageTransHuge(head)) {
/*
* Non anonymous thp exists only in allocation/free time. We
* can't handle such a case correctly, so let's give it up.
The patch titled Subject: mm,hwpoison: fix race with hugetlb page allocation has been added to the -mm tree. Its filename is mmhwpoison-fix-race-with-hugetlb-page-allocation.patch This patch should soon appear at https://ozlabs.org/~akpm/mmots/broken-out/mmhwpoison-fix-race-with-hugetlb-page-allocation.patch and later at https://ozlabs.org/~akpm/mmotm/broken-out/mmhwpoison-fix-race-with-hugetlb-page-allocation.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/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next and is updated there every 3-4 working days ------------------------------------------------------ From: Naoya Horiguchi <naoya.horiguchi@nec.com> Subject: mm,hwpoison: fix race with hugetlb page allocation When hugetlb page fault (under overcommitting situation) and memory_failure() race, VM_BUG_ON_PAGE() is triggered by the following race: CPU0: CPU1: gather_surplus_pages() page = alloc_surplus_huge_page() memory_failure_hugetlb() get_hwpoison_page(page) __get_hwpoison_page(page) get_page_unless_zero(page) zero = put_page_testzero(page) VM_BUG_ON_PAGE(!zero, page) enqueue_huge_page(h, page) put_page(page) __get_hwpoison_page() only checks the page refcount before taking an additional one for memory error handling, which is wrong because there's a time window where compound pages have non-zero refcount during initialization. So make __get_hwpoison_page() check page status a bit more for hugetlb pages. Link: https://lkml.kernel.org/r/20210518231259.2553203-2-nao.horiguchi@gmail.com Fixes: ead07f6a867b ("mm/memory-failure: introduce get_hwpoison_page() for consistent refcount handling") Signed-off-by: Naoya Horiguchi <naoya.horiguchi@nec.com> Reported-by: Muchun Song <songmuchun@bytedance.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Tony Luck <tony.luck@intel.com> Cc: <stable@vger.kernel.org> [5.12+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> --- include/linux/hugetlb.h | 6 ++++++ mm/hugetlb.c | 15 +++++++++++++++ mm/memory-failure.c | 8 +++++++- 3 files changed, 28 insertions(+), 1 deletion(-)