Linux-mm Archive on lore.kernel.org
 help / color / Atom feed
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> (raw)
In-Reply-To: <20200624150137.7052-1-nao.horiguchi@gmail.com>

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



  parent reply index

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-06-24 15:01 [PATCH v3 00/15] HWPOISON: soft offline rework nao.horiguchi
2020-06-24 15:01 ` [PATCH v3 01/15] mm,hwpoison: cleanup unused PageHuge() check nao.horiguchi
2020-06-30 23:28   ` Mike Kravetz
2020-06-24 15:01 ` [PATCH v3 02/15] mm, hwpoison: remove recalculating hpage nao.horiguchi
2020-06-30 23:45   ` Mike Kravetz
2020-06-24 15:01 ` [PATCH v3 03/15] mm,madvise: call soft_offline_page() without MF_COUNT_INCREASED nao.horiguchi
2020-06-24 15:01 ` [PATCH v3 04/15] mm,madvise: Refactor madvise_inject_error nao.horiguchi
2020-06-24 15:01 ` [PATCH v3 05/15] mm,hwpoison-inject: don't pin for hwpoison_filter nao.horiguchi
2020-06-24 15:01 ` [PATCH v3 06/15] mm,hwpoison: Un-export get_hwpoison_page and make it static nao.horiguchi
2020-06-24 15:01 ` [PATCH v3 07/15] mm,hwpoison: Kill put_hwpoison_page nao.horiguchi
2020-06-24 15:01 ` [PATCH v3 08/15] mm,hwpoison: remove MF_COUNT_INCREASED nao.horiguchi
2020-06-24 15:01 ` [PATCH v3 09/15] mm,hwpoison: remove flag argument from soft offline functions nao.horiguchi
2020-06-24 15:01 ` [PATCH v3 10/15] mm,hwpoison: Unify THP handling for hard and soft offline nao.horiguchi
2020-06-24 15:01 ` nao.horiguchi [this message]
2020-06-24 15:01 ` [PATCH v3 12/15] mm,hwpoison: Rework soft offline for in-use pages nao.horiguchi
2020-06-24 15:01 ` [PATCH v3 13/15] mm,hwpoison: Refactor soft_offline_huge_page and __soft_offline_page nao.horiguchi
2020-06-26 16:53   ` Naresh Kamboju
2020-06-28  6:54     ` Naoya Horiguchi
2020-06-29  7:22       ` Stephen Rothwell
2020-06-29  7:33         ` HORIGUCHI NAOYA(堀口 直也)
2020-06-24 15:01 ` [PATCH v3 14/15] mm,hwpoison: Return 0 if the page is already poisoned in soft-offline nao.horiguchi
2020-06-24 15:01 ` [PATCH v3 15/15] mm,hwpoison: introduce MF_MSG_UNSPLIT_THP nao.horiguchi
2020-06-24 19:17 ` [PATCH v3 00/15] HWPOISON: soft offline rework Andrew Morton
2020-06-24 22:36   ` HORIGUCHI NAOYA(堀口 直也)
2020-06-24 22:49     ` Andrew Morton
2020-06-24 23:01       ` HORIGUCHI NAOYA(堀口 直也)
2020-06-26 13:35 ` Qian Cai
2020-06-29 10:29 ` Oscar Salvador
2020-06-30  6:50   ` HORIGUCHI NAOYA(堀口 直也)
2020-06-30  5:08 ` Qian Cai
2020-06-30  6:35   ` Oscar Salvador
2020-07-01  8:22     ` Oscar Salvador
2020-07-01  9:07       ` HORIGUCHI NAOYA(堀口 直也)
2020-07-14 10:08   ` Oscar Salvador

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=20200624150137.7052-12-nao.horiguchi@gmail.com \
    --to=nao.horiguchi@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=aneesh.kumar@linux.vnet.ibm.com \
    --cc=david@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@kernel.org \
    --cc=mike.kravetz@oracle.com \
    --cc=naoya.horiguchi@nec.com \
    --cc=osalvador@suse.de \
    --cc=tony.luck@intel.com \
    --cc=zeil@yandex-team.ru \
    /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

Linux-mm Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-mm/0 linux-mm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-mm linux-mm/ https://lore.kernel.org/linux-mm \
		linux-mm@kvack.org
	public-inbox-index linux-mm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kvack.linux-mm


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git