Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   nao.horiguchi@gmail.com
To:     linux-mm@kvack.org
Cc:     mhocko@kernel.org, akpm@linux-foundation.org,
        mike.kravetz@oracle.com, osalvador@suse.de, tony.luck@intel.com,
        david@redhat.com, aneesh.kumar@linux.vnet.ibm.com,
        zeil@yandex-team.ru, naoya.horiguchi@nec.com,
        linux-kernel@vger.kernel.org
Subject: [PATCH v3 11/15] mm,hwpoison: Rework soft offline for free pages
Date:   Wed, 24 Jun 2020 15:01:33 +0000
Message-Id: <20200624150137.7052-12-nao.horiguchi@gmail.com>
In-Reply-To: <20200624150137.7052-1-nao.horiguchi@gmail.com>
References: <20200624150137.7052-1-nao.horiguchi@gmail.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

From: Oscar Salvador <osalvador@suse.de>

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: Naoya Horiguchi <naoya.horiguchi@nec.com>
---
ChangeLog v2 -> v3:
- use add_to_free_list() instead of add_to_free_area()
- use del_page_from_free_list() instead of del_page_from_free_area()
- add fast return
- move extern definition to header file as warned by checkpatch.pl
---
 include/linux/page-flags.h |  1 +
 mm/memory-failure.c        | 18 ++++++----
 mm/page_alloc.c            | 68 ++++++++++++++++++++++++++++++++++++++
 3 files changed, 81 insertions(+), 6 deletions(-)

diff --git v5.8-rc1-mmots-2020-06-20-21-44/include/linux/page-flags.h v5.8-rc1-mmots-2020-06-20-21-44_patched/include/linux/page-flags.h
index 6be1aa559b1e..9fa5d4e2d69a 100644
--- v5.8-rc1-mmots-2020-06-20-21-44/include/linux/page-flags.h
+++ v5.8-rc1-mmots-2020-06-20-21-44_patched/include/linux/page-flags.h
@@ -423,6 +423,7 @@ 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 v5.8-rc1-mmots-2020-06-20-21-44/mm/memory-failure.c v5.8-rc1-mmots-2020-06-20-21-44_patched/mm/memory-failure.c
index 2e244d5b83e0..d79e756a97be 100644
--- v5.8-rc1-mmots-2020-06-20-21-44/mm/memory-failure.c
+++ v5.8-rc1-mmots-2020-06-20-21-44_patched/mm/memory-failure.c
@@ -78,6 +78,13 @@ EXPORT_SYMBOL_GPL(hwpoison_filter_dev_minor);
 EXPORT_SYMBOL_GPL(hwpoison_filter_flags_mask);
 EXPORT_SYMBOL_GPL(hwpoison_filter_flags_value);
 
+static void page_handle_poison(struct page *page)
+{
+	SetPageHWPoison(page);
+	page_ref_inc(page);
+	num_poisoned_pages_inc();
+}
+
 static int hwpoison_filter_dev(struct page *p)
 {
 	struct address_space *mapping;
@@ -1876,14 +1883,13 @@ static int soft_offline_in_use_page(struct page *page)
 
 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 v5.8-rc1-mmots-2020-06-20-21-44/mm/page_alloc.c v5.8-rc1-mmots-2020-06-20-21-44_patched/mm/page_alloc.c
index 31c32fe0ecfb..3b145bceb477 100644
--- v5.8-rc1-mmots-2020-06-20-21-44/mm/page_alloc.c
+++ v5.8-rc1-mmots-2020-06-20-21-44_patched/mm/page_alloc.c
@@ -8781,6 +8781,74 @@ 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
-- 
2.17.1