diff --git a/Documentation/accounting/delay-accounting.rst b/Documentation/accounting/delay-accounting.rst
index 241d1a87f2cd..7103b62ba6d7 100644
--- a/Documentation/accounting/delay-accounting.rst
+++ b/Documentation/accounting/delay-accounting.rst
@@ -13,7 +13,7 @@ a) waiting for a CPU (while being runnable)
 b) completion of synchronous block I/O initiated by the task
 c) swapping in pages
 d) memory reclaim
-e) thrashing page cache
+e) thrashing
 f) direct compact
 g) write-protect copy
 
diff --git a/arch/Kconfig b/arch/Kconfig
index 266862428a84..8f138e580d1a 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -1416,6 +1416,14 @@ config DYNAMIC_SIGFRAME
 config HAVE_ARCH_NODE_DEV_GROUP
 	bool
 
+config ARCH_HAS_NONLEAF_PMD_YOUNG
+	bool
+	help
+	  Architectures that select this option are capable of setting the
+	  accessed bit in non-leaf PMD entries when using them as part of linear
+	  address translations. Page table walkers that clear the accessed bit
+	  may use this capability to reduce their search space.
+
 source "kernel/gcov/Kconfig"
 
 source "scripts/gcc-plugins/Kconfig"
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index b5df82aa99e6..71a1af42f0e8 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -1082,24 +1082,13 @@ static inline void update_mmu_cache(struct vm_area_struct *vma,
  * page after fork() + CoW for pfn mappings. We don't always have a
  * hardware-managed access flag on arm64.
  */
-static inline bool arch_faults_on_old_pte(void)
-{
-	/* The register read below requires a stable CPU to make any sense */
-	cant_migrate();
-
-	return !cpu_has_hw_af();
-}
-#define arch_faults_on_old_pte		arch_faults_on_old_pte
+#define arch_has_hw_pte_young		cpu_has_hw_af
 
 /*
  * Experimentally, it's cheap to set the access flag in hardware and we
  * benefit from prefaulting mappings as 'old' to start with.
  */
-static inline bool arch_wants_old_prefaulted_pte(void)
-{
-	return !arch_faults_on_old_pte();
-}
-#define arch_wants_old_prefaulted_pte	arch_wants_old_prefaulted_pte
+#define arch_wants_old_prefaulted_pte	cpu_has_hw_af
 
 static inline bool pud_sect_supported(void)
 {
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 088af7c84e5d..2aa0941cfe66 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -85,6 +85,7 @@ config X86
 	select ARCH_HAS_PMEM_API		if X86_64
 	select ARCH_HAS_PTE_DEVMAP		if X86_64
 	select ARCH_HAS_PTE_SPECIAL
+	select ARCH_HAS_NONLEAF_PMD_YOUNG	if PGTABLE_LEVELS > 2
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if X86_64
 	select ARCH_HAS_COPY_MC			if X86_64
 	select ARCH_HAS_SET_MEMORY
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 44e2d6f1dbaa..5059799bebe3 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -815,7 +815,8 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
 
 static inline int pmd_bad(pmd_t pmd)
 {
-	return (pmd_flags(pmd) & ~_PAGE_USER) != _KERNPG_TABLE;
+	return (pmd_flags(pmd) & ~(_PAGE_USER | _PAGE_ACCESSED)) !=
+	       (_KERNPG_TABLE & ~_PAGE_ACCESSED);
 }
 
 static inline unsigned long pages_to_mb(unsigned long npg)
@@ -1431,10 +1432,10 @@ static inline bool arch_has_pfn_modify_check(void)
 	return boot_cpu_has_bug(X86_BUG_L1TF);
 }
 
-#define arch_faults_on_old_pte arch_faults_on_old_pte
-static inline bool arch_faults_on_old_pte(void)
+#define arch_has_hw_pte_young arch_has_hw_pte_young
+static inline bool arch_has_hw_pte_young(void)
 {
-	return false;
+	return true;
 }
 
 #ifdef CONFIG_PAGE_TABLE_CHECK
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index a932d7712d85..8525f2876fb4 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -550,7 +550,7 @@ int ptep_test_and_clear_young(struct vm_area_struct *vma,
 	return ret;
 }
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG)
 int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 			      unsigned long addr, pmd_t *pmdp)
 {
@@ -562,6 +562,9 @@ int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 
 	return ret;
 }
+#endif
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 int pudp_test_and_clear_young(struct vm_area_struct *vma,
 			      unsigned long addr, pud_t *pudp)
 {
diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h
index 58aea2d7385c..0da97dba9ef8 100644
--- a/include/linux/delayacct.h
+++ b/include/linux/delayacct.h
@@ -73,8 +73,8 @@ extern int delayacct_add_tsk(struct taskstats *, struct task_struct *);
 extern __u64 __delayacct_blkio_ticks(struct task_struct *);
 extern void __delayacct_freepages_start(void);
 extern void __delayacct_freepages_end(void);
-extern void __delayacct_thrashing_start(void);
-extern void __delayacct_thrashing_end(void);
+extern void __delayacct_thrashing_start(bool *in_thrashing);
+extern void __delayacct_thrashing_end(bool *in_thrashing);
 extern void __delayacct_swapin_start(void);
 extern void __delayacct_swapin_end(void);
 extern void __delayacct_compact_start(void);
@@ -143,22 +143,22 @@ static inline void delayacct_freepages_end(void)
 		__delayacct_freepages_end();
 }
 
-static inline void delayacct_thrashing_start(void)
+static inline void delayacct_thrashing_start(bool *in_thrashing)
 {
 	if (!static_branch_unlikely(&delayacct_key))
 		return;
 
 	if (current->delays)
-		__delayacct_thrashing_start();
+		__delayacct_thrashing_start(in_thrashing);
 }
 
-static inline void delayacct_thrashing_end(void)
+static inline void delayacct_thrashing_end(bool *in_thrashing)
 {
 	if (!static_branch_unlikely(&delayacct_key))
 		return;
 
 	if (current->delays)
-		__delayacct_thrashing_end();
+		__delayacct_thrashing_end(in_thrashing);
 }
 
 static inline void delayacct_swapin_start(void)
@@ -237,9 +237,9 @@ static inline void delayacct_freepages_start(void)
 {}
 static inline void delayacct_freepages_end(void)
 {}
-static inline void delayacct_thrashing_start(void)
+static inline void delayacct_thrashing_start(bool *in_thrashing)
 {}
-static inline void delayacct_thrashing_end(void)
+static inline void delayacct_thrashing_end(bool *in_thrashing)
 {}
 static inline void delayacct_swapin_start(void)
 {}
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 7b25b53c474a..fb8aadb81cd6 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -34,7 +34,7 @@ static inline int page_is_file_lru(struct page *page)
 	return folio_is_file_lru(page_folio(page));
 }
 
-static __always_inline void update_lru_size(struct lruvec *lruvec,
+static __always_inline void __update_lru_size(struct lruvec *lruvec,
 				enum lru_list lru, enum zone_type zid,
 				long nr_pages)
 {
@@ -43,6 +43,13 @@ static __always_inline void update_lru_size(struct lruvec *lruvec,
 	__mod_lruvec_state(lruvec, NR_LRU_BASE + lru, nr_pages);
 	__mod_zone_page_state(&pgdat->node_zones[zid],
 				NR_ZONE_LRU_BASE + lru, nr_pages);
+}
+
+static __always_inline void update_lru_size(struct lruvec *lruvec,
+				enum lru_list lru, enum zone_type zid,
+				long nr_pages)
+{
+	__update_lru_size(lruvec, lru, zid, nr_pages);
 #ifdef CONFIG_MEMCG
 	mem_cgroup_update_lru_size(lruvec, lru, zid, nr_pages);
 #endif
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index d13b4f7cc5be..a108b60a6962 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -213,7 +213,7 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
 #endif
 
 #ifndef __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG)
 static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 					    unsigned long address,
 					    pmd_t *pmdp)
@@ -234,7 +234,7 @@ static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 	BUILD_BUG();
 	return 0;
 }
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG */
 #endif
 
 #ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
@@ -260,6 +260,19 @@ static inline int pmdp_clear_flush_young(struct vm_area_struct *vma,
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif
 
+#ifndef arch_has_hw_pte_young
+/*
+ * Return whether the accessed bit is supported on the local CPU.
+ *
+ * This stub assumes accessing through an old PTE triggers a page fault.
+ * Architectures that automatically set the access bit should overwrite it.
+ */
+static inline bool arch_has_hw_pte_young(void)
+{
+	return false;
+}
+#endif
+
 #ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR
 static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 				       unsigned long address,
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 7a769122fcd2..894bce129d21 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -956,6 +956,10 @@ struct task_struct {
 #ifdef	CONFIG_CPU_SUP_INTEL
 	unsigned			reported_split_lock:1;
 #endif
+#ifdef CONFIG_TASK_DELAY_ACCT
+	/* delay due to memory thrashing */
+	unsigned                        in_thrashing:1;
+#endif
 
 	unsigned long			atomic_flags; /* Flags requiring atomic access. */
 
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index 164ed9ef77a3..e39cb696cfbd 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -214,13 +214,22 @@ void __delayacct_freepages_end(void)
 		      &current->delays->freepages_count);
 }
 
-void __delayacct_thrashing_start(void)
+void __delayacct_thrashing_start(bool *in_thrashing)
 {
+	*in_thrashing = !!current->in_thrashing;
+	if (*in_thrashing)
+		return;
+
+	current->in_thrashing = 1;
 	current->delays->thrashing_start = local_clock();
 }
 
-void __delayacct_thrashing_end(void)
+void __delayacct_thrashing_end(bool *in_thrashing)
 {
+	if (*in_thrashing)
+		return;
+
+	current->in_thrashing = 0;
 	delayacct_end(&current->delays->lock,
 		      &current->delays->thrashing_start,
 		      &current->delays->thrashing_delay,
diff --git a/mm/filemap.c b/mm/filemap.c
index 8cb832af31ff..4ba6eab0f0e9 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1221,15 +1221,12 @@ static inline int folio_wait_bit_common(struct folio *folio, int bit_nr,
 	struct wait_page_queue wait_page;
 	wait_queue_entry_t *wait = &wait_page.wait;
 	bool thrashing = false;
-	bool delayacct = false;
 	unsigned long pflags;
+	bool in_thrashing;
 
 	if (bit_nr == PG_locked &&
 	    !folio_test_uptodate(folio) && folio_test_workingset(folio)) {
-		if (!folio_test_swapbacked(folio)) {
-			delayacct_thrashing_start();
-			delayacct = true;
-		}
+		delayacct_thrashing_start(&in_thrashing);
 		psi_memstall_enter(&pflags);
 		thrashing = true;
 	}
@@ -1329,8 +1326,7 @@ static inline int folio_wait_bit_common(struct folio *folio, int bit_nr,
 	finish_wait(q, wait);
 
 	if (thrashing) {
-		if (delayacct)
-			delayacct_thrashing_end();
+		delayacct_thrashing_end(&in_thrashing);
 		psi_memstall_leave(&pflags);
 	}
 
@@ -1378,17 +1374,14 @@ void migration_entry_wait_on_locked(swp_entry_t entry, pte_t *ptep,
 	struct wait_page_queue wait_page;
 	wait_queue_entry_t *wait = &wait_page.wait;
 	bool thrashing = false;
-	bool delayacct = false;
 	unsigned long pflags;
+	bool in_thrashing;
 	wait_queue_head_t *q;
 	struct folio *folio = page_folio(pfn_swap_entry_to_page(entry));
 
 	q = folio_waitqueue(folio);
 	if (!folio_test_uptodate(folio) && folio_test_workingset(folio)) {
-		if (!folio_test_swapbacked(folio)) {
-			delayacct_thrashing_start();
-			delayacct = true;
-		}
+		delayacct_thrashing_start(&in_thrashing);
 		psi_memstall_enter(&pflags);
 		thrashing = true;
 	}
@@ -1435,8 +1428,7 @@ void migration_entry_wait_on_locked(swp_entry_t entry, pte_t *ptep,
 	finish_wait(q, wait);
 
 	if (thrashing) {
-		if (delayacct)
-			delayacct_thrashing_end();
+		delayacct_thrashing_end(&in_thrashing);
 		psi_memstall_leave(&pflags);
 	}
 }
diff --git a/mm/memory.c b/mm/memory.c
index b1be9a0f541e..6755855c67e4 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -126,18 +126,6 @@ int randomize_va_space __read_mostly =
 					2;
 #endif
 
-#ifndef arch_faults_on_old_pte
-static inline bool arch_faults_on_old_pte(void)
-{
-	/*
-	 * Those arches which don't have hw access flag feature need to
-	 * implement their own helper. By default, "true" means pagefault
-	 * will be hit on old pte.
-	 */
-	return true;
-}
-#endif
-
 #ifndef arch_wants_old_prefaulted_pte
 static inline bool arch_wants_old_prefaulted_pte(void)
 {
@@ -2872,7 +2860,7 @@ static inline bool __wp_page_copy_user(struct page *dst, struct page *src,
 	 * On architectures with software "accessed" bits, we would
 	 * take a double page fault, so mark it accessed here.
 	 */
-	if (arch_faults_on_old_pte() && !pte_young(vmf->orig_pte)) {
+	if (!arch_has_hw_pte_young() && !pte_young(vmf->orig_pte)) {
 		pte_t entry;
 
 		vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl);
diff --git a/mm/migrate.c b/mm/migrate.c
index a35eba462e61..06a653977835 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1260,10 +1260,8 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
 	 * tables or check whether the hugepage is pmd-based or not before
 	 * kicking migration.
 	 */
-	if (!hugepage_migration_supported(page_hstate(hpage))) {
-		list_move_tail(&hpage->lru, ret);
+	if (!hugepage_migration_supported(page_hstate(hpage)))
 		return -ENOSYS;
-	}
 
 	if (page_count(hpage) == 1) {
 		/* page was freed from under us. So we are done. */
@@ -1369,16 +1367,15 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
 	return rc;
 }
 
-static inline int try_split_thp(struct page *page, struct page **page2,
-				struct list_head *from)
+static inline int try_split_thp(struct page *page, struct list_head *split_pages)
 {
-	int rc = 0;
+	int rc;
 
 	lock_page(page);
-	rc = split_huge_page_to_list(page, from);
+	rc = split_huge_page_to_list(page, split_pages);
 	unlock_page(page);
 	if (!rc)
-		list_safe_reset_next(page, *page2, lru);
+		list_move_tail(&page->lru, split_pages);
 
 	return rc;
 }
@@ -1416,6 +1413,7 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
 	int thp_retry = 1;
 	int nr_failed = 0;
 	int nr_failed_pages = 0;
+	int nr_retry_pages = 0;
 	int nr_succeeded = 0;
 	int nr_thp_succeeded = 0;
 	int nr_thp_failed = 0;
@@ -1436,9 +1434,9 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
 	for (pass = 0; pass < 10 && (retry || thp_retry); pass++) {
 		retry = 0;
 		thp_retry = 0;
+		nr_retry_pages = 0;
 
 		list_for_each_entry_safe(page, page2, from, lru) {
-retry:
 			/*
 			 * THP statistics is based on the source huge page.
 			 * Capture required information that might get lost
@@ -1463,6 +1461,7 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
 			 *		 page will be put back
 			 *	-EAGAIN: stay on the from list
 			 *	-ENOMEM: stay on the from list
+			 *	-ENOSYS: stay on the from list
 			 *	Other errno: put on ret_pages list then splice to
 			 *		     from list
 			 */
@@ -1473,18 +1472,17 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
 			 * retry on the same page with the THP split
 			 * to base pages.
 			 *
-			 * Head page is retried immediately and tail
-			 * pages are added to the tail of the list so
-			 * we encounter them after the rest of the list
-			 * is processed.
+			 * Sub-pages are put in thp_split_pages, and
+			 * we will migrate them after the rest of the
+			 * list is processed.
 			 */
 			case -ENOSYS:
 				/* THP migration is unsupported */
 				if (is_thp) {
 					nr_thp_failed++;
-					if (!try_split_thp(page, &page2, &thp_split_pages)) {
+					if (!try_split_thp(page, &thp_split_pages)) {
 						nr_thp_split++;
-						goto retry;
+						break;
 					}
 				/* Hugetlb migration is unsupported */
 				} else if (!no_subpage_counting) {
@@ -1492,24 +1490,25 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
 				}
 
 				nr_failed_pages += nr_subpages;
+				list_move_tail(&page->lru, &ret_pages);
 				break;
 			case -ENOMEM:
 				/*
 				 * When memory is low, don't bother to try to migrate
 				 * other pages, just exit.
-				 * THP NUMA faulting doesn't split THP to retry.
 				 */
-				if (is_thp && !nosplit) {
+				if (is_thp) {
 					nr_thp_failed++;
-					if (!try_split_thp(page, &page2, &thp_split_pages)) {
+					/* THP NUMA faulting doesn't split THP to retry. */
+					if (!nosplit && !try_split_thp(page, &thp_split_pages)) {
 						nr_thp_split++;
-						goto retry;
+						break;
 					}
 				} else if (!no_subpage_counting) {
 					nr_failed++;
 				}
 
-				nr_failed_pages += nr_subpages;
+				nr_failed_pages += nr_subpages + nr_retry_pages;
 				/*
 				 * There might be some subpages of fail-to-migrate THPs
 				 * left in thp_split_pages list. Move them back to migration
@@ -1517,13 +1516,15 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
 				 * the caller otherwise the page refcnt will be leaked.
 				 */
 				list_splice_init(&thp_split_pages, from);
+				/* nr_failed isn't updated for not used */
 				nr_thp_failed += thp_retry;
 				goto out;
 			case -EAGAIN:
 				if (is_thp)
 					thp_retry++;
-				else
+				else if (!no_subpage_counting)
 					retry++;
+				nr_retry_pages += nr_subpages;
 				break;
 			case MIGRATEPAGE_SUCCESS:
 				nr_succeeded += nr_subpages;
@@ -1549,6 +1550,7 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
 	}
 	nr_failed += retry;
 	nr_thp_failed += thp_retry;
+	nr_failed_pages += nr_retry_pages;
 	/*
 	 * Try to migrate subpages of fail-to-migrate THPs, no nr_failed
 	 * counting in this round, since all subpages of a THP is counted
@@ -1751,7 +1753,7 @@ static int move_pages_and_store_status(struct mm_struct *mm, int node,
 		 * well.
 		 */
 		if (err > 0)
-			err += nr_pages - i - 1;
+			err += nr_pages - i;
 		return err;
 	}
 	return store_status(status, start, node, i - start);
@@ -1837,8 +1839,12 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
 
 		err = move_pages_and_store_status(mm, current_node, &pagelist,
 				status, start, i, nr_pages);
-		if (err)
+		if (err) {
+			/* We have accounted for page i */
+			if (err > 0)
+				err--;
 			goto out;
+		}
 		current_node = NUMA_NO_NODE;
 	}
 out_flush:
diff --git a/mm/page_io.c b/mm/page_io.c
index 68d53fc27598..fc6b3fb1f7c5 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -452,18 +452,21 @@ int swap_readpage(struct page *page, bool synchronous,
 	struct swap_info_struct *sis = page_swap_info(page);
 	bool workingset = PageWorkingset(page);
 	unsigned long pflags;
+	bool in_thrashing;
 
 	VM_BUG_ON_PAGE(!PageSwapCache(page) && !synchronous, page);
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	VM_BUG_ON_PAGE(PageUptodate(page), page);
 
 	/*
-	 * Count submission time as memory stall. When the device is congested,
-	 * or the submitting cgroup IO-throttled, submission can be a
-	 * significant part of overall IO time.
+	 * Count submission time as memory stall and delay. When the device
+	 * is congested, or the submitting cgroup IO-throttled, submission
+	 * can be a significant part of overall IO time.
 	 */
-	if (workingset)
+	if (workingset) {
+		delayacct_thrashing_start(&in_thrashing);
 		psi_memstall_enter(&pflags);
+	}
 	delayacct_swapin_start();
 
 	if (frontswap_load(page) == 0) {
@@ -512,8 +515,10 @@ int swap_readpage(struct page *page, bool synchronous,
 	bio_put(bio);
 
 out:
-	if (workingset)
+	if (workingset) {
+		delayacct_thrashing_end(&in_thrashing);
 		psi_memstall_leave(&pflags);
+	}
 	delayacct_swapin_end();
 	return ret;
 }
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 0358d87196e9..ca1c2089f904 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2731,6 +2731,109 @@ enum scan_balance {
 	SCAN_FILE,
 };
 
+static void prepare_scan_count(pg_data_t *pgdat, struct scan_control *sc)
+{
+	unsigned long file;
+	struct lruvec *target_lruvec;
+
+	target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat);
+
+	/*
+	 * Flush the memory cgroup stats, so that we read accurate per-memcg
+	 * lruvec stats for heuristics.
+	 */
+	mem_cgroup_flush_stats();
+
+	/*
+	 * Determine the scan balance between anon and file LRUs.
+	 */
+	spin_lock_irq(&target_lruvec->lru_lock);
+	sc->anon_cost = target_lruvec->anon_cost;
+	sc->file_cost = target_lruvec->file_cost;
+	spin_unlock_irq(&target_lruvec->lru_lock);
+
+	/*
+	 * Target desirable inactive:active list ratios for the anon
+	 * and file LRU lists.
+	 */
+	if (!sc->force_deactivate) {
+		unsigned long refaults;
+
+		/*
+		 * When refaults are being observed, it means a new
+		 * workingset is being established. Deactivate to get
+		 * rid of any stale active pages quickly.
+		 */
+		refaults = lruvec_page_state(target_lruvec,
+				WORKINGSET_ACTIVATE_ANON);
+		if (refaults != target_lruvec->refaults[WORKINGSET_ANON] ||
+			inactive_is_low(target_lruvec, LRU_INACTIVE_ANON))
+			sc->may_deactivate |= DEACTIVATE_ANON;
+		else
+			sc->may_deactivate &= ~DEACTIVATE_ANON;
+
+		refaults = lruvec_page_state(target_lruvec,
+				WORKINGSET_ACTIVATE_FILE);
+		if (refaults != target_lruvec->refaults[WORKINGSET_FILE] ||
+		    inactive_is_low(target_lruvec, LRU_INACTIVE_FILE))
+			sc->may_deactivate |= DEACTIVATE_FILE;
+		else
+			sc->may_deactivate &= ~DEACTIVATE_FILE;
+	} else
+		sc->may_deactivate = DEACTIVATE_ANON | DEACTIVATE_FILE;
+
+	/*
+	 * If we have plenty of inactive file pages that aren't
+	 * thrashing, try to reclaim those first before touching
+	 * anonymous pages.
+	 */
+	file = lruvec_page_state(target_lruvec, NR_INACTIVE_FILE);
+	if (file >> sc->priority && !(sc->may_deactivate & DEACTIVATE_FILE))
+		sc->cache_trim_mode = 1;
+	else
+		sc->cache_trim_mode = 0;
+
+	/*
+	 * Prevent the reclaimer from falling into the cache trap: as
+	 * cache pages start out inactive, every cache fault will tip
+	 * the scan balance towards the file LRU.  And as the file LRU
+	 * shrinks, so does the window for rotation from references.
+	 * This means we have a runaway feedback loop where a tiny
+	 * thrashing file LRU becomes infinitely more attractive than
+	 * anon pages.  Try to detect this based on file LRU size.
+	 */
+	if (!cgroup_reclaim(sc)) {
+		unsigned long total_high_wmark = 0;
+		unsigned long free, anon;
+		int z;
+
+		free = sum_zone_node_page_state(pgdat->node_id, NR_FREE_PAGES);
+		file = node_page_state(pgdat, NR_ACTIVE_FILE) +
+			   node_page_state(pgdat, NR_INACTIVE_FILE);
+
+		for (z = 0; z < MAX_NR_ZONES; z++) {
+			struct zone *zone = &pgdat->node_zones[z];
+
+			if (!managed_zone(zone))
+				continue;
+
+			total_high_wmark += high_wmark_pages(zone);
+		}
+
+		/*
+		 * Consider anon: if that's low too, this isn't a
+		 * runaway file reclaim problem, but rather just
+		 * extreme pressure. Reclaim as per usual then.
+		 */
+		anon = node_page_state(pgdat, NR_INACTIVE_ANON);
+
+		sc->file_is_tiny =
+			file + free <= total_high_wmark &&
+			!(sc->may_deactivate & DEACTIVATE_ANON) &&
+			anon >> sc->priority;
+	}
+}
+
 /*
  * Determine how aggressively the anon and file LRU lists should be
  * scanned.
@@ -3205,109 +3308,16 @@ static void shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 	unsigned long nr_reclaimed, nr_scanned;
 	struct lruvec *target_lruvec;
 	bool reclaimable = false;
-	unsigned long file;
 
 	target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat);
 
 again:
-	/*
-	 * Flush the memory cgroup stats, so that we read accurate per-memcg
-	 * lruvec stats for heuristics.
-	 */
-	mem_cgroup_flush_stats();
-
 	memset(&sc->nr, 0, sizeof(sc->nr));
 
 	nr_reclaimed = sc->nr_reclaimed;
 	nr_scanned = sc->nr_scanned;
 
-	/*
-	 * Determine the scan balance between anon and file LRUs.
-	 */
-	spin_lock_irq(&target_lruvec->lru_lock);
-	sc->anon_cost = target_lruvec->anon_cost;
-	sc->file_cost = target_lruvec->file_cost;
-	spin_unlock_irq(&target_lruvec->lru_lock);
-
-	/*
-	 * Target desirable inactive:active list ratios for the anon
-	 * and file LRU lists.
-	 */
-	if (!sc->force_deactivate) {
-		unsigned long refaults;
-
-		/*
-		 * When refaults are being observed, it means a new
-		 * workingset is being established. Deactivate to get
-		 * rid of any stale active pages quickly.
-		 */
-		refaults = lruvec_page_state(target_lruvec,
-				WORKINGSET_ACTIVATE_ANON);
-		if (refaults != target_lruvec->refaults[WORKINGSET_ANON] ||
-			inactive_is_low(target_lruvec, LRU_INACTIVE_ANON))
-			sc->may_deactivate |= DEACTIVATE_ANON;
-		else
-			sc->may_deactivate &= ~DEACTIVATE_ANON;
-
-		refaults = lruvec_page_state(target_lruvec,
-				WORKINGSET_ACTIVATE_FILE);
-		if (refaults != target_lruvec->refaults[WORKINGSET_FILE] ||
-		    inactive_is_low(target_lruvec, LRU_INACTIVE_FILE))
-			sc->may_deactivate |= DEACTIVATE_FILE;
-		else
-			sc->may_deactivate &= ~DEACTIVATE_FILE;
-	} else
-		sc->may_deactivate = DEACTIVATE_ANON | DEACTIVATE_FILE;
-
-	/*
-	 * If we have plenty of inactive file pages that aren't
-	 * thrashing, try to reclaim those first before touching
-	 * anonymous pages.
-	 */
-	file = lruvec_page_state(target_lruvec, NR_INACTIVE_FILE);
-	if (file >> sc->priority && !(sc->may_deactivate & DEACTIVATE_FILE))
-		sc->cache_trim_mode = 1;
-	else
-		sc->cache_trim_mode = 0;
-
-	/*
-	 * Prevent the reclaimer from falling into the cache trap: as
-	 * cache pages start out inactive, every cache fault will tip
-	 * the scan balance towards the file LRU.  And as the file LRU
-	 * shrinks, so does the window for rotation from references.
-	 * This means we have a runaway feedback loop where a tiny
-	 * thrashing file LRU becomes infinitely more attractive than
-	 * anon pages.  Try to detect this based on file LRU size.
-	 */
-	if (!cgroup_reclaim(sc)) {
-		unsigned long total_high_wmark = 0;
-		unsigned long free, anon;
-		int z;
-
-		free = sum_zone_node_page_state(pgdat->node_id, NR_FREE_PAGES);
-		file = node_page_state(pgdat, NR_ACTIVE_FILE) +
-			   node_page_state(pgdat, NR_INACTIVE_FILE);
-
-		for (z = 0; z < MAX_NR_ZONES; z++) {
-			struct zone *zone = &pgdat->node_zones[z];
-			if (!managed_zone(zone))
-				continue;
-
-			total_high_wmark += high_wmark_pages(zone);
-		}
-
-		/*
-		 * Consider anon: if that's low too, this isn't a
-		 * runaway file reclaim problem, but rather just
-		 * extreme pressure. Reclaim as per usual then.
-		 */
-		anon = node_page_state(pgdat, NR_INACTIVE_ANON);
-
-		sc->file_is_tiny =
-			file + free <= total_high_wmark &&
-			!(sc->may_deactivate & DEACTIVATE_ANON) &&
-			anon >> sc->priority;
-	}
+	prepare_scan_count(pgdat, sc);
 
 	shrink_node_memcgs(pgdat, sc);