mm: fix race on soft-offlining free huge pages
Patch series "mm: soft-offline: fix race against page allocation".
Xishi recently reported the issue about race on reusing the target pages
of soft offlining. Discussion and analysis showed that we need make
sure that setting PG_hwpoison should be done in the right place under
zone->lock for soft offline. 1/2 handles free hugepage's case, and 2/2
hanldes free buddy page's case.
This patch (of 2):
There's a race condition between soft offline and hugetlb_fault which
causes unexpected process killing and/or hugetlb allocation failure.
The process killing is caused by the following flow:
CPU 0 CPU 1 CPU 2
soft offline
get_any_page
// find the hugetlb is free
mmap a hugetlb file
page fault
...
hugetlb_fault
hugetlb_no_page
alloc_huge_page
// succeed
soft_offline_free_page
// set hwpoison flag
mmap the hugetlb file
page fault
...
hugetlb_fault
hugetlb_no_page
find_lock_page
return VM_FAULT_HWPOISON
mm_fault_error
do_sigbus
// kill the process
The hugetlb allocation failure comes from the following flow:
CPU 0 CPU 1
mmap a hugetlb file
// reserve all free page but don't fault-in
soft offline
get_any_page
// find the hugetlb is free
soft_offline_free_page
// set hwpoison flag
dissolve_free_huge_page
// fail because all free hugepages are reserved
page fault
...
hugetlb_fault
hugetlb_no_page
alloc_huge_page
...
dequeue_huge_page_node_exact
// ignore hwpoisoned hugepage
// and finally fail due to no-mem
The root cause of this is that current soft-offline code is written based
on an assumption that PageHWPoison flag should be set at first to avoid
accessing the corrupted data. This makes sense for memory_failure() or
hard offline, but does not for soft offline because soft offline is about
corrected (not uncorrected) error and is safe from data lost. This patch
changes soft offline semantics where it sets PageHWPoison flag only after
containment of the error page completes successfully.
Link: http://lkml.kernel.org/r/1531452366-11661-2-git-send-email-n-horiguchi@ah.jp.nec.com
Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Reported-by: Xishi Qiu <xishi.qiuxishi@alibaba-inc.com>
Suggested-by: Xishi Qiu <xishi.qiuxishi@alibaba-inc.com>
Tested-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: <zy.zhengyi@alibaba-inc.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
Naoya Horiguchi
Linus Torvalds
parent
30aba6656f
commit
6bc9b56433
11
mm/hugetlb.c
11
mm/hugetlb.c
|
|
@ -1479,22 +1479,20 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
|
|||
/*
|
||||
* Dissolve a given free hugepage into free buddy pages. This function does
|
||||
* nothing for in-use (including surplus) hugepages. Returns -EBUSY if the
|
||||
* number of free hugepages would be reduced below the number of reserved
|
||||
* hugepages.
|
||||
* dissolution fails because a give page is not a free hugepage, or because
|
||||
* free hugepages are fully reserved.
|
||||
*/
|
||||
int dissolve_free_huge_page(struct page *page)
|
||||
{
|
||||
int rc = 0;
|
||||
int rc = -EBUSY;
|
||||
|
||||
spin_lock(&hugetlb_lock);
|
||||
if (PageHuge(page) && !page_count(page)) {
|
||||
struct page *head = compound_head(page);
|
||||
struct hstate *h = page_hstate(head);
|
||||
int nid = page_to_nid(head);
|
||||
if (h->free_huge_pages - h->resv_huge_pages == 0) {
|
||||
rc = -EBUSY;
|
||||
if (h->free_huge_pages - h->resv_huge_pages == 0)
|
||||
goto out;
|
||||
}
|
||||
/*
|
||||
* Move PageHWPoison flag from head page to the raw error page,
|
||||
* which makes any subpages rather than the error page reusable.
|
||||
|
|
@ -1508,6 +1506,7 @@ int dissolve_free_huge_page(struct page *page)
|
|||
h->free_huge_pages_node[nid]--;
|
||||
h->max_huge_pages--;
|
||||
update_and_free_page(h, head);
|
||||
rc = 0;
|
||||
}
|
||||
out:
|
||||
spin_unlock(&hugetlb_lock);
|
||||
|
|
|
|||
|
|
@ -1598,8 +1598,18 @@ static int soft_offline_huge_page(struct page *page, int flags)
|
|||
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;
|
||||
}
|
||||
|
|
@ -1715,13 +1725,13 @@ static int soft_offline_in_use_page(struct page *page, int flags)
|
|||
|
||||
static void soft_offline_free_page(struct page *page)
|
||||
{
|
||||
int rc = 0;
|
||||
struct page *head = compound_head(page);
|
||||
|
||||
if (!TestSetPageHWPoison(head)) {
|
||||
if (PageHuge(head))
|
||||
rc = dissolve_free_huge_page(page);
|
||||
if (!rc && !TestSetPageHWPoison(page))
|
||||
num_poisoned_pages_inc();
|
||||
if (PageHuge(head))
|
||||
dissolve_free_huge_page(page);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
|
|
|
|||
|
|
@ -1331,8 +1331,6 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
|
|||
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
|
||||
|
|
|
|||
Loading…
Reference in New Issue