mm,hwpoison: rework soft offline for free pages

When trying to soft-offline a free page, we need to first take it off the
buddy allocator.  Once we know is out of reach, we can safely flag it as
poisoned.

take_page_off_buddy will be used to take a page meant to be poisoned off
the buddy allocator.  take_page_off_buddy calls break_down_buddy_pages,
which splits a higher-order page in case our page belongs to one.

Once the page is under our control, we call page_handle_poison to set it
as poisoned and grab a refcount on it.

Signed-off-by: Oscar Salvador <osalvador@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Aristeu Rozanski <aris@ruivo.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dmitry Yakunin <zeil@yandex-team.ru>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Oscar Salvador <osalvador@suse.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Tony Luck <tony.luck@intel.com>
Link: https://lkml.kernel.org/r/20200922135650.1634-9-osalvador@suse.de
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 81 insertions, 6 deletions

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 38ded408bd4c..a02b6d0221db 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -432,6 +432,7 @@ PAGEFLAG(HWPoison, hwpoison, PF_ANY)
 TESTSCFLAG(HWPoison, hwpoison, PF_ANY)
 #define __PG_HWPOISON (1UL << PG_hwpoison)
 extern bool set_hwpoison_free_buddy_page(struct page *page);
+extern bool take_page_off_buddy(struct page *page);
 #else
 PAGEFLAG_FALSE(HWPoison)
 static inline bool set_hwpoison_free_buddy_page(struct page *page)
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 2ff4ba7fa99f..af7fb23b93ae 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -65,6 +65,13 @@ int sysctl_memory_failure_recovery __read_mostly = 1;
 
 atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);
 
+static void page_handle_poison(struct page *page)
+{
+	SetPageHWPoison(page);
+	page_ref_inc(page);
+	num_poisoned_pages_inc();
+}
+
 #if defined(CONFIG_HWPOISON_INJECT) || defined(CONFIG_HWPOISON_INJECT_MODULE)
 
 u32 hwpoison_filter_enable = 0;
@@ -1884,14 +1891,13 @@ static int soft_offline_in_use_page(struct page *page, int flags)
 
 static int soft_offline_free_page(struct page *page)
 {
-	int rc = dissolve_free_huge_page(page);
+	int rc = -EBUSY;
 
-	if (!rc) {
-		if (set_hwpoison_free_buddy_page(page))
-			num_poisoned_pages_inc();
-		else
-			rc = -EBUSY;
+	if (!dissolve_free_huge_page(page) && take_page_off_buddy(page)) {
+		page_handle_poison(page);
+		rc = 0;
 	}
+
 	return rc;
 }
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index febb2d731f9e..12dcfb3dc588 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -8778,6 +8778,74 @@ bool is_free_buddy_page(struct page *page)
 
 #ifdef CONFIG_MEMORY_FAILURE
 /*
+ * Break down a higher-order page in sub-pages, and keep our target out of
+ * buddy allocator.
+ */
+static void break_down_buddy_pages(struct zone *zone, struct page *page,
+				   struct page *target, int low, int high,
+				   int migratetype)
+{
+	unsigned long size = 1 << high;
+	struct page *current_buddy, *next_page;
+
+	while (high > low) {
+		high--;
+		size >>= 1;
+
+		if (target >= &page[size]) {
+			next_page = page + size;
+			current_buddy = page;
+		} else {
+			next_page = page;
+			current_buddy = page + size;
+		}
+
+		if (set_page_guard(zone, current_buddy, high, migratetype))
+			continue;
+
+		if (current_buddy != target) {
+			add_to_free_list(current_buddy, zone, high, migratetype);
+			set_page_order(current_buddy, high);
+			page = next_page;
+		}
+	}
+}
+
+/*
+ * Take a page that will be marked as poisoned off the buddy allocator.
+ */
+bool take_page_off_buddy(struct page *page)
+{
+	struct zone *zone = page_zone(page);
+	unsigned long pfn = page_to_pfn(page);
+	unsigned long flags;
+	unsigned int order;
+	bool ret = false;
+
+	spin_lock_irqsave(&zone->lock, flags);
+	for (order = 0; order < MAX_ORDER; order++) {
+		struct page *page_head = page - (pfn & ((1 << order) - 1));
+		int buddy_order = page_order(page_head);
+
+		if (PageBuddy(page_head) && buddy_order >= order) {
+			unsigned long pfn_head = page_to_pfn(page_head);
+			int migratetype = get_pfnblock_migratetype(page_head,
+								   pfn_head);
+
+			del_page_from_free_list(page_head, zone, buddy_order);
+			break_down_buddy_pages(zone, page_head, page, 0,
+						buddy_order, migratetype);
+			ret = true;
+			break;
+		}
+		if (page_count(page_head) > 0)
+			break;
+	}
+	spin_unlock_irqrestore(&zone->lock, flags);
+	return ret;
+}
+
+/*
  * 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.