mm: soft-offline: close the race against page allocation

A process can be killed with SIGBUS(BUS_MCEERR_AR) when it tries to
allocate a page that was just freed on the way of soft-offline.  This is
undesirable because soft-offline (which is about corrected error) is
less aggressive than hard-offline (which is about uncorrected error),
and we can make soft-offline fail and keep using the page for good
reason like "system is busy."

Two main changes of this patch are:

- setting migrate type of the target page to MIGRATE_ISOLATE. As done
  in free_unref_page_commit(), this makes kernel bypass pcplist when
  freeing the page. So we can assume that the page is in freelist just
  after put_page() returns,

- setting PG_hwpoison on free page under zone->lock which protects
  freelists, so this allows us to avoid setting PG_hwpoison on a page
  that is decided to be allocated soon.

[akpm@linux-foundation.org: tweak set_hwpoison_free_buddy_page() comment]
Link: http://lkml.kernel.org/r/1531452366-11661-3-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>
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>

3 files changed, 52 insertions, 6 deletions

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 49dc32c61137..192d0bbfc9ea 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -57,6 +57,7 @@
 #include <linux/mm_inline.h>
 #include <linux/kfifo.h>
 #include <linux/ratelimit.h>
+#include <linux/page-isolation.h>
 #include "internal.h"
 #include "ras/ras_event.h"
 
@@ -1697,6 +1698,7 @@ static int __soft_offline_page(struct page *page, int flags)
 static int soft_offline_in_use_page(struct page *page, int flags)
 {
         int ret;
+        int mt;
         struct page *hpage = compound_head(page);
 
         if (!PageHuge(page) && PageTransHuge(hpage)) {
@@ -1715,23 +1717,37 @@ static int soft_offline_in_use_page(struct page *page, int flags)
                 put_hwpoison_page(hpage);
         }
 
+        /*
+         * Setting MIGRATE_ISOLATE here ensures that the page will be linked
+         * to free list immediately (not via pcplist) when released after
+         * successful page migration. Otherwise we can't guarantee that the
+         * page is really free after put_page() returns, so
+         * set_hwpoison_free_buddy_page() highly likely fails.
+         */
+        mt = get_pageblock_migratetype(page);
+        set_pageblock_migratetype(page, MIGRATE_ISOLATE);
         if (PageHuge(page))
                 ret = soft_offline_huge_page(page, flags);
         else
                 ret = __soft_offline_page(page, flags);
-
+        set_pageblock_migratetype(page, mt);
         return ret;
 }
 
-static void soft_offline_free_page(struct page *page)
+static int soft_offline_free_page(struct page *page)
 {
         int rc = 0;
         struct page *head = compound_head(page);
 
         if (PageHuge(head))
                 rc = dissolve_free_huge_page(page);
-        if (!rc && !TestSetPageHWPoison(page))
-                num_poisoned_pages_inc();
+        if (!rc) {
+                if (set_hwpoison_free_buddy_page(page))
+                        num_poisoned_pages_inc();
+                else
+                        rc = -EBUSY;
+        }
+        return rc;
 }
 
 /**
@@ -1775,7 +1791,7 @@ int soft_offline_page(struct page *page, int flags)
         if (ret > 0)
                 ret = soft_offline_in_use_page(page, flags);
         else if (ret == 0)
-                soft_offline_free_page(page);
+                ret = soft_offline_free_page(page);
 
         return ret;
 }
diff --git a/mm/migrate.c b/mm/migrate.c
index 91a99457127c..d6a2e89b086a 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1212,7 +1212,7 @@ out:
                          * intentionally. Although it's rather weird,
                          * it's how HWPoison flag works at the moment.
                          */
-                        if (!test_set_page_hwpoison(page))
+                        if (set_hwpoison_free_buddy_page(page))
                                 num_poisoned_pages_inc();
                 }
         } else {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c677c1506d73..e75865d58ba7 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -8096,3 +8096,33 @@ bool is_free_buddy_page(struct page *page)
 
         return order < MAX_ORDER;
 }
+
+#ifdef CONFIG_MEMORY_FAILURE
+/*
+ * Set PG_hwpoison flag if a given page is confirmed to be a free page.  This
+ * test is performed under the zone lock to prevent a race against page
+ * allocation.
+ */
+bool set_hwpoison_free_buddy_page(struct page *page)
+{
+        struct zone *zone = page_zone(page);
+        unsigned long pfn = page_to_pfn(page);
+        unsigned long flags;
+        unsigned int order;
+        bool hwpoisoned = false;
+
+        spin_lock_irqsave(&zone->lock, flags);
+        for (order = 0; order < MAX_ORDER; order++) {
+                struct page *page_head = page - (pfn & ((1 << order) - 1));
+
+                if (PageBuddy(page_head) && page_order(page_head) >= order) {
+                        if (!TestSetPageHWPoison(page))
+                                hwpoisoned = true;
+                        break;
+                }
+        }
+        spin_unlock_irqrestore(&zone->lock, flags);
+
+        return hwpoisoned;
+}
+#endif