Re: [PATCH v1 04/12] mm: vmscan: rework move_pages_to_lru()

Re: [PATCH v1 04/12] mm: vmscan: rework move_pages_to_lru()

[kernel test robot]

[-- Attachment #1: Type: text/plain, Size: 2331 bytes --]

In-Reply-To: <20210814052519.86679-5-songmuchun@bytedance.com>
References: <20210814052519.86679-5-songmuchun@bytedance.com>
TO: Muchun Song <songmuchun@bytedance.com>
TO: guro(a)fb.com
TO: hannes(a)cmpxchg.org
TO: mhocko(a)kernel.org
TO: akpm(a)linux-foundation.org
TO: shakeelb(a)google.com
TO: vdavydov.dev(a)gmail.com
CC: linux-kernel(a)vger.kernel.org
CC: linux-mm(a)kvack.org
CC: duanxiongchun(a)bytedance.com
CC: fam.zheng(a)bytedance.com

Hi Muchun,

Thank you for the patch! Perhaps something to improve:

[auto build test WARNING on next-20210813]
[cannot apply to hnaz-linux-mm/master cgroup/for-next linus/master v5.14-rc5 v5.14-rc4 v5.14-rc3 v5.14-rc5]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]

url:    https://github.com/0day-ci/linux/commits/Muchun-Song/Use-obj_cgroup-APIs-to-charge-the-LRU-pages/20210814-132844
base:    4b358aabb93a2c654cd1dcab1a25a589f6e2b153
config: x86_64-randconfig-a003-20210815 (attached as .config)
compiler: clang version 14.0.0 (https://github.com/llvm/llvm-project 1f7b25ea76a925aca690da28de9d78db7ca99d0c)
reproduce (this is a W=1 build):
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # https://github.com/0day-ci/linux/commit/5bfd087eec36fc94c75ba192b1101caea430cde0
        git remote add linux-review https://github.com/0day-ci/linux
        git fetch --no-tags linux-review Muchun-Song/Use-obj_cgroup-APIs-to-charge-the-LRU-pages/20210814-132844
        git checkout 5bfd087eec36fc94c75ba192b1101caea430cde0
        # save the attached .config to linux build tree
        mkdir build_dir
        COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross O=build_dir ARCH=x86_64 SHELL=/bin/bash

If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>

All warnings (new ones prefixed by >>):

>> mm/vmscan.o: warning: objtool: shrink_lruvec()+0x6a6: sibling call from callable instruction with modified stack frame

---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all(a)lists.01.org

[-- Attachment #2: config.gz --]
[-- Type: application/gzip, Size: 36778 bytes --]

[PATCH v1 04/12] mm: vmscan: rework move_pages_to_lru()

[Muchun Song]

In the later patch, we will reparent the LRU pages. The pages moved to
appropriate LRU list can be reparented during the process of the
move_pages_to_lru(). So holding a lruvec lock by the caller is wrong, we
should use the more general interface of folio_lruvec_relock_irq() to
acquire the correct lruvec lock.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 include/linux/mm.h |  1 +
 mm/vmscan.c        | 49 +++++++++++++++++++++++++------------------------
 2 files changed, 26 insertions(+), 24 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index ce8fc0fd6d6e..1e7f06bc5f2d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -227,6 +227,7 @@ int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *,
 #define PAGE_ALIGNED(addr)	IS_ALIGNED((unsigned long)(addr), PAGE_SIZE)
 
 #define lru_to_page(head) (list_entry((head)->prev, struct page, lru))
+#define lru_to_folio(head) (list_entry((head)->prev, struct folio, lru))
 
 void setup_initial_init_mm(void *start_code, void *end_code,
 			   void *end_data, void *brk);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 403a175a720f..8ce42858ad5d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2153,23 +2153,28 @@ static int too_many_isolated(struct pglist_data *pgdat, int file,
  * move_pages_to_lru() moves pages from private @list to appropriate LRU list.
  * On return, @list is reused as a list of pages to be freed by the caller.
  *
- * Returns the number of pages moved to the given lruvec.
+ * Returns the number of pages moved to the appropriate LRU list.
+ *
+ * Note: The caller must not hold any lruvec lock.
  */
-static unsigned int move_pages_to_lru(struct lruvec *lruvec,
-				      struct list_head *list)
+static unsigned int move_pages_to_lru(struct list_head *list)
 {
-	int nr_pages, nr_moved = 0;
+	int nr_moved = 0;
+	struct lruvec *lruvec = NULL;
 	LIST_HEAD(pages_to_free);
-	struct page *page;
 
 	while (!list_empty(list)) {
-		page = lru_to_page(list);
+		int nr_pages;
+		struct folio *folio = lru_to_folio(list);
+		struct page *page = &folio->page;
+
+		lruvec = folio_lruvec_relock_irq(folio, lruvec);
 		VM_BUG_ON_PAGE(PageLRU(page), page);
 		list_del(&page->lru);
 		if (unlikely(!page_evictable(page))) {
-			spin_unlock_irq(&lruvec->lru_lock);
+			unlock_page_lruvec_irq(lruvec);
 			putback_lru_page(page);
-			spin_lock_irq(&lruvec->lru_lock);
+			lruvec = NULL;
 			continue;
 		}
 
@@ -2190,20 +2195,16 @@ static unsigned int move_pages_to_lru(struct lruvec *lruvec,
 			__clear_page_lru_flags(page);
 
 			if (unlikely(PageCompound(page))) {
-				spin_unlock_irq(&lruvec->lru_lock);
+				unlock_page_lruvec_irq(lruvec);
 				destroy_compound_page(page);
-				spin_lock_irq(&lruvec->lru_lock);
+				lruvec = NULL;
 			} else
 				list_add(&page->lru, &pages_to_free);
 
 			continue;
 		}
 
-		/*
-		 * All pages were isolated from the same lruvec (and isolation
-		 * inhibits memcg migration).
-		 */
-		VM_BUG_ON_PAGE(!folio_matches_lruvec(page_folio(page), lruvec), page);
+		VM_BUG_ON_PAGE(!folio_matches_lruvec(folio, lruvec), page);
 		add_page_to_lru_list(page, lruvec);
 		nr_pages = thp_nr_pages(page);
 		nr_moved += nr_pages;
@@ -2211,6 +2212,8 @@ static unsigned int move_pages_to_lru(struct lruvec *lruvec,
 			workingset_age_nonresident(lruvec, nr_pages);
 	}
 
+	if (lruvec)
+		unlock_page_lruvec_irq(lruvec);
 	/*
 	 * To save our caller's stack, now use input list for pages to free.
 	 */
@@ -2284,16 +2287,16 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 
 	nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, &stat, false);
 
-	spin_lock_irq(&lruvec->lru_lock);
-	move_pages_to_lru(lruvec, &page_list);
+	move_pages_to_lru(&page_list);
 
+	local_irq_disable();
 	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
 	item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT;
 	if (!cgroup_reclaim(sc))
 		__count_vm_events(item, nr_reclaimed);
 	__count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed);
 	__count_vm_events(PGSTEAL_ANON + file, nr_reclaimed);
-	spin_unlock_irq(&lruvec->lru_lock);
+	local_irq_enable();
 
 	lru_note_cost(lruvec, file, stat.nr_pageout);
 	mem_cgroup_uncharge_list(&page_list);
@@ -2420,18 +2423,16 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	/*
 	 * Move pages back to the lru list.
 	 */
-	spin_lock_irq(&lruvec->lru_lock);
-
-	nr_activate = move_pages_to_lru(lruvec, &l_active);
-	nr_deactivate = move_pages_to_lru(lruvec, &l_inactive);
+	nr_activate = move_pages_to_lru(&l_active);
+	nr_deactivate = move_pages_to_lru(&l_inactive);
 	/* Keep all free pages in l_active list */
 	list_splice(&l_inactive, &l_active);
 
+	local_irq_disable();
 	__count_vm_events(PGDEACTIVATE, nr_deactivate);
 	__count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_deactivate);
-
 	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
-	spin_unlock_irq(&lruvec->lru_lock);
+	local_irq_enable();
 
 	mem_cgroup_uncharge_list(&l_active);
 	free_unref_page_list(&l_active);
-- 
2.11.0