mm/hwpoison: fix unpoison_memory()

After recent soft-offline rework, error pages can be taken off from
buddy allocator, but the existing unpoison_memory() does not properly
undo the operation.  Moreover, due to the recent change on
__get_hwpoison_page(), get_page_unless_zero() is hardly called for
hwpoisoned pages.  So __get_hwpoison_page() highly likely returns -EBUSY
(meaning to fail to grab page refcount) and unpoison just clears
PG_hwpoison without releasing a refcount.  That does not lead to a
critical issue like kernel panic, but unpoisoned pages never get back to
buddy (leaked permanently), which is not good.

To (partially) fix this, we need to identify "taken off" pages from
other types of hwpoisoned pages.  We can't use refcount or page flags
for this purpose, so a pseudo flag is defined by hacking ->private
field.  Someone might think that put_page() is enough to cancel
taken-off pages, but the normal free path contains some operations not
suitable for the current purpose, and can fire VM_BUG_ON().

Note that unpoison_memory() is now supposed to be cancel hwpoison events
injected only by madvise() or
/sys/devices/system/memory/{hard,soft}_offline_page, not by MCE
injection, so please don't try to use unpoison when testing with MCE
injection.

[lkp@intel.com: report build failure for ARCH=i386]

Link: https://lkml.kernel.org/r/20211115084006.3728254-4-naoya.horiguchi@linux.dev
Signed-off-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Reviewed-by: Yang Shi <shy828301@gmail.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Ding Hui <dinghui@sangfor.com.cn>
Cc: Tony Luck <tony.luck@intel.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 117 insertions, 19 deletions

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 810328fe8adb..6a2b4b86b679 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1160,6 +1160,22 @@ static int page_action(struct page_state *ps, struct page *p,
 	return (result == MF_RECOVERED || result == MF_DELAYED) ? 0 : -EBUSY;
 }
 
+static inline bool PageHWPoisonTakenOff(struct page *page)
+{
+	return PageHWPoison(page) && page_private(page) == MAGIC_HWPOISON;
+}
+
+void SetPageHWPoisonTakenOff(struct page *page)
+{
+	set_page_private(page, MAGIC_HWPOISON);
+}
+
+void ClearPageHWPoisonTakenOff(struct page *page)
+{
+	if (PageHWPoison(page))
+		set_page_private(page, 0);
+}
+
 /*
  * Return true if a page type of a given page is supported by hwpoison
  * mechanism (while handling could fail), otherwise false.  This function
@@ -1262,6 +1278,27 @@ out:
 	return ret;
 }
 
+static int __get_unpoison_page(struct page *page)
+{
+	struct page *head = compound_head(page);
+	int ret = 0;
+	bool hugetlb = false;
+
+	ret = get_hwpoison_huge_page(head, &hugetlb);
+	if (hugetlb)
+		return ret;
+
+	/*
+	 * PageHWPoisonTakenOff pages are not only marked as PG_hwpoison,
+	 * but also isolated from buddy freelist, so need to identify the
+	 * state and have to cancel both operations to unpoison.
+	 */
+	if (PageHWPoisonTakenOff(page))
+		return -EHWPOISON;
+
+	return get_page_unless_zero(page) ? 1 : 0;
+}
+
 /**
  * get_hwpoison_page() - Get refcount for memory error handling
  * @p:		Raw error page (hit by memory error)
@@ -1278,18 +1315,26 @@ out:
  * extra care for the error page's state (as done in __get_hwpoison_page()),
  * and has some retry logic in get_any_page().
  *
+ * When called from unpoison_memory(), the caller should already ensure that
+ * the given page has PG_hwpoison. So it's never reused for other page
+ * allocations, and __get_unpoison_page() never races with them.
+ *
  * Return: 0 on failure,
  *         1 on success for in-use pages in a well-defined state,
  *         -EIO for pages on which we can not handle memory errors,
  *         -EBUSY when get_hwpoison_page() has raced with page lifecycle
- *         operations like allocation and free.
+ *         operations like allocation and free,
+ *         -EHWPOISON when the page is hwpoisoned and taken off from buddy.
  */
 static int get_hwpoison_page(struct page *p, unsigned long flags)
 {
 	int ret;
 
 	zone_pcp_disable(page_zone(p));
-	ret = get_any_page(p, flags);
+	if (flags & MF_UNPOISON)
+		ret = __get_unpoison_page(p);
+	else
+		ret = get_any_page(p, flags);
 	zone_pcp_enable(page_zone(p));
 
 	return ret;
@@ -1937,6 +1982,28 @@ core_initcall(memory_failure_init);
 		pr_info(fmt, pfn);			\
 })
 
+static inline int clear_page_hwpoison(struct ratelimit_state *rs, struct page *p)
+{
+	if (TestClearPageHWPoison(p)) {
+		unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n",
+				 page_to_pfn(p), rs);
+		num_poisoned_pages_dec();
+		return 1;
+	}
+	return 0;
+}
+
+static inline int unpoison_taken_off_page(struct ratelimit_state *rs,
+					  struct page *p)
+{
+	if (put_page_back_buddy(p)) {
+		unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n",
+				 page_to_pfn(p), rs);
+		return 0;
+	}
+	return -EBUSY;
+}
+
 /**
  * unpoison_memory - Unpoison a previously poisoned page
  * @pfn: Page number of the to be unpoisoned page
@@ -1953,9 +2020,7 @@ int unpoison_memory(unsigned long pfn)
 {
 	struct page *page;
 	struct page *p;
-	int freeit = 0;
-	int ret = 0;
-	unsigned long flags = 0;
+	int ret = -EBUSY;
 	static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL,
 					DEFAULT_RATELIMIT_BURST);
 
@@ -1991,24 +2056,30 @@ int unpoison_memory(unsigned long pfn)
 		goto unlock_mutex;
 	}
 
-	if (!get_hwpoison_page(p, flags)) {
-		if (TestClearPageHWPoison(p))
-			num_poisoned_pages_dec();
-		unpoison_pr_info("Unpoison: Software-unpoisoned free page %#lx\n",
-				 pfn, &unpoison_rs);
+	if (PageSlab(page) || PageTable(page))
 		goto unlock_mutex;
-	}
 
-	if (TestClearPageHWPoison(page)) {
-		unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n",
-				 pfn, &unpoison_rs);
-		num_poisoned_pages_dec();
-		freeit = 1;
-	}
+	ret = get_hwpoison_page(p, MF_UNPOISON);
+	if (!ret) {
+		if (clear_page_hwpoison(&unpoison_rs, page))
+			ret = 0;
+		else
+			ret = -EBUSY;
+	} else if (ret < 0) {
+		if (ret == -EHWPOISON) {
+			ret = unpoison_taken_off_page(&unpoison_rs, p);
+		} else
+			unpoison_pr_info("Unpoison: failed to grab page %#lx\n",
+					 pfn, &unpoison_rs);
+	} else {
+		int freeit = clear_page_hwpoison(&unpoison_rs, p);
 
-	put_page(page);
-	if (freeit && !(pfn == my_zero_pfn(0) && page_count(p) == 1))
 		put_page(page);
+		if (freeit && !(pfn == my_zero_pfn(0) && page_count(p) == 1)) {
+			put_page(page);
+			ret = 0;
+		}
+	}
 
 unlock_mutex:
 	mutex_unlock(&mf_mutex);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 99fc65c532f0..d4205e5e41d1 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -19,6 +19,7 @@
 #include <linux/mm.h>
 #include <linux/highmem.h>
 #include <linux/swap.h>
+#include <linux/swapops.h>
 #include <linux/interrupt.h>
 #include <linux/pagemap.h>
 #include <linux/jiffies.h>
@@ -9508,6 +9509,7 @@ bool take_page_off_buddy(struct page *page)
 			del_page_from_free_list(page_head, zone, page_order);
 			break_down_buddy_pages(zone, page_head, page, 0,
 						page_order, migratetype);
+			SetPageHWPoisonTakenOff(page);
 			if (!is_migrate_isolate(migratetype))
 				__mod_zone_freepage_state(zone, -1, migratetype);
 			ret = true;
@@ -9519,6 +9521,31 @@ bool take_page_off_buddy(struct page *page)
 	spin_unlock_irqrestore(&zone->lock, flags);
 	return ret;
 }
+
+/*
+ * Cancel takeoff done by take_page_off_buddy().
+ */
+bool put_page_back_buddy(struct page *page)
+{
+	struct zone *zone = page_zone(page);
+	unsigned long pfn = page_to_pfn(page);
+	unsigned long flags;
+	int migratetype = get_pfnblock_migratetype(page, pfn);
+	bool ret = false;
+
+	spin_lock_irqsave(&zone->lock, flags);
+	if (put_page_testzero(page)) {
+		ClearPageHWPoisonTakenOff(page);
+		__free_one_page(page, pfn, zone, 0, migratetype, FPI_NONE);
+		if (TestClearPageHWPoison(page)) {
+			num_poisoned_pages_dec();
+			ret = true;
+		}
+	}
+	spin_unlock_irqrestore(&zone->lock, flags);
+
+	return ret;
+}
 #endif
 
 #ifdef CONFIG_ZONE_DMA