From: Andrew Morton <akpm@linux-foundation.org>
To: akpm@linux-foundation.org, david@redhat.com, linux-mm@kvack.org,
mhocko@suse.com, mike.kravetz@oracle.com,
mm-commits@vger.kernel.org, osalvador@suse.de,
shy828301@gmail.com, songmuchun@bytedance.com,
stable@vger.kernel.org, torvalds@linux-foundation.org
Subject: [patch 02/18] mm: hugetlb: fix a race between freeing and dissolving the page
Date: Thu, 04 Feb 2021 18:32:06 -0800 [thread overview]
Message-ID: <20210205023206.qxjmf4Zwv%akpm@linux-foundation.org> (raw)
In-Reply-To: <20210204183135.e123f0d6027529f2cf500cf2@linux-foundation.org>
From: Muchun Song <songmuchun@bytedance.com>
Subject: mm: hugetlb: fix a race between freeing and dissolving the page
There is a race condition between __free_huge_page()
and dissolve_free_huge_page().
CPU0: CPU1:
// page_count(page) == 1
put_page(page)
__free_huge_page(page)
dissolve_free_huge_page(page)
spin_lock(&hugetlb_lock)
// PageHuge(page) && !page_count(page)
update_and_free_page(page)
// page is freed to the buddy
spin_unlock(&hugetlb_lock)
spin_lock(&hugetlb_lock)
clear_page_huge_active(page)
enqueue_huge_page(page)
// It is wrong, the page is already freed
spin_unlock(&hugetlb_lock)
The race windows is between put_page() and dissolve_free_huge_page().
We should make sure that the page is already on the free list
when it is dissolved.
As a result __free_huge_page would corrupt page(s) already in the buddy
allocator.
Link: https://lkml.kernel.org/r/20210115124942.46403-4-songmuchun@bytedance.com
Fixes: c8721bbbdd36 ("mm: memory-hotplug: enable memory hotplug to handle hugepage")
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
mm/hugetlb.c | 39 +++++++++++++++++++++++++++++++++++++++
1 file changed, 39 insertions(+)
--- a/mm/hugetlb.c~mm-hugetlb-fix-a-race-between-freeing-and-dissolving-the-page
+++ a/mm/hugetlb.c
@@ -79,6 +79,21 @@ DEFINE_SPINLOCK(hugetlb_lock);
static int num_fault_mutexes;
struct mutex *hugetlb_fault_mutex_table ____cacheline_aligned_in_smp;
+static inline bool PageHugeFreed(struct page *head)
+{
+ return page_private(head + 4) == -1UL;
+}
+
+static inline void SetPageHugeFreed(struct page *head)
+{
+ set_page_private(head + 4, -1UL);
+}
+
+static inline void ClearPageHugeFreed(struct page *head)
+{
+ set_page_private(head + 4, 0);
+}
+
/* Forward declaration */
static int hugetlb_acct_memory(struct hstate *h, long delta);
@@ -1028,6 +1043,7 @@ static void enqueue_huge_page(struct hst
list_move(&page->lru, &h->hugepage_freelists[nid]);
h->free_huge_pages++;
h->free_huge_pages_node[nid]++;
+ SetPageHugeFreed(page);
}
static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
@@ -1044,6 +1060,7 @@ static struct page *dequeue_huge_page_no
list_move(&page->lru, &h->hugepage_activelist);
set_page_refcounted(page);
+ ClearPageHugeFreed(page);
h->free_huge_pages--;
h->free_huge_pages_node[nid]--;
return page;
@@ -1505,6 +1522,7 @@ static void prep_new_huge_page(struct hs
spin_lock(&hugetlb_lock);
h->nr_huge_pages++;
h->nr_huge_pages_node[nid]++;
+ ClearPageHugeFreed(page);
spin_unlock(&hugetlb_lock);
}
@@ -1755,6 +1773,7 @@ int dissolve_free_huge_page(struct page
{
int rc = -EBUSY;
+retry:
/* Not to disrupt normal path by vainly holding hugetlb_lock */
if (!PageHuge(page))
return 0;
@@ -1771,6 +1790,26 @@ int dissolve_free_huge_page(struct page
int nid = page_to_nid(head);
if (h->free_huge_pages - h->resv_huge_pages == 0)
goto out;
+
+ /*
+ * We should make sure that the page is already on the free list
+ * when it is dissolved.
+ */
+ if (unlikely(!PageHugeFreed(head))) {
+ spin_unlock(&hugetlb_lock);
+ cond_resched();
+
+ /*
+ * Theoretically, we should return -EBUSY when we
+ * encounter this race. In fact, we have a chance
+ * to successfully dissolve the page if we do a
+ * retry. Because the race window is quite small.
+ * If we seize this opportunity, it is an optimization
+ * for increasing the success rate of dissolving page.
+ */
+ goto retry;
+ }
+
/*
* Move PageHWPoison flag from head page to the raw error page,
* which makes any subpages rather than the error page reusable.
_
next prev parent reply other threads:[~2021-02-05 2:33 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-02-05 2:31 incoming Andrew Morton
2021-02-05 2:32 ` [patch 01/18] mm: hugetlbfs: fix cannot migrate the fallocated HugeTLB page Andrew Morton
2021-02-05 2:32 ` Andrew Morton [this message]
2021-02-05 2:32 ` [patch 03/18] mm: hugetlb: fix a race between isolating and freeing page Andrew Morton
2021-02-05 2:32 ` [patch 04/18] mm: hugetlb: remove VM_BUG_ON_PAGE from page_huge_active Andrew Morton
2021-02-05 2:32 ` [patch 05/18] mm: migrate: do not migrate HugeTLB page whose refcount is one Andrew Morton
2021-02-05 2:32 ` [patch 06/18] mm, compaction: move high_pfn to the for loop scope Andrew Morton
2021-02-05 2:32 ` [patch 07/18] mm/vmalloc: separate put pages and flush VM flags Andrew Morton
2021-02-05 2:32 ` [patch 08/18] init/gcov: allow CONFIG_CONSTRUCTORS on UML to fix module gcov Andrew Morton
2021-02-05 2:32 ` [patch 09/18] mm: thp: fix MADV_REMOVE deadlock on shmem THP Andrew Morton
2021-02-05 2:32 ` [patch 10/18] memblock: do not start bottom-up allocations with kernel_end Andrew Morton
2021-02-05 2:32 ` [patch 11/18] mailmap: fix name/email for Viresh Kumar Andrew Morton
2021-02-05 2:32 ` [patch 12/18] mailmap: add entries for Manivannan Sadhasivam Andrew Morton
2021-02-05 2:32 ` [patch 13/18] mm/filemap: add missing mem_cgroup_uncharge() to __add_to_page_cache_locked() Andrew Morton
2021-02-05 2:32 ` [patch 14/18] kasan: add explicit preconditions to kasan_report() Andrew Morton
2021-02-05 2:32 ` [patch 15/18] kasan: make addr_has_metadata() return true for valid addresses Andrew Morton
2021-02-05 2:32 ` [patch 16/18] ubsan: implement __ubsan_handle_alignment_assumption Andrew Morton
2021-02-05 2:33 ` [patch 17/18] mm: hugetlb: fix missing put_page in gather_surplus_pages() Andrew Morton
2021-02-05 2:33 ` [patch 18/18] MAINTAINERS/.mailmap: use my @kernel.org address Andrew Morton
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210205023206.qxjmf4Zwv%akpm@linux-foundation.org \
--to=akpm@linux-foundation.org \
--cc=david@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhocko@suse.com \
--cc=mike.kravetz@oracle.com \
--cc=mm-commits@vger.kernel.org \
--cc=osalvador@suse.de \
--cc=shy828301@gmail.com \
--cc=songmuchun@bytedance.com \
--cc=stable@vger.kernel.org \
--cc=torvalds@linux-foundation.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).