Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:

 - a few hot fixes

 - ocfs2 updates

 - almost all of -mm (slab-generic, slab, slub, kmemleak, kasan,
   cleanups, debug, pagecache, memcg, gup, pagemap, memory-hotplug,
   sparsemem, vmalloc, initialization, z3fold, compaction, mempolicy,
   oom-kill, hugetlb, migration, thp, mmap, madvise, shmem, zswap,
   zsmalloc)

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (132 commits)
  mm/zsmalloc.c: fix a -Wunused-function warning
  zswap: do not map same object twice
  zswap: use movable memory if zpool support allocate movable memory
  zpool: add malloc_support_movable to zpool_driver
  shmem: fix obsolete comment in shmem_getpage_gfp()
  mm/madvise: reduce code duplication in error handling paths
  mm: mmap: increase sockets maximum memory size pgoff for 32bits
  mm/mmap.c: refine find_vma_prev() with rb_last()
  riscv: make mmap allocation top-down by default
  mips: use generic mmap top-down layout and brk randomization
  mips: replace arch specific way to determine 32bit task with generic version
  mips: adjust brk randomization offset to fit generic version
  mips: use STACK_TOP when computing mmap base address
  mips: properly account for stack randomization and stack guard gap
  arm: use generic mmap top-down layout and brk randomization
  arm: use STACK_TOP when computing mmap base address
  arm: properly account for stack randomization and stack guard gap
  arm64, mm: make randomization selected by generic topdown mmap layout
  arm64, mm: move generic mmap layout functions to mm
  arm64: consider stack randomization for mmap base only when necessary
  ...

20 files changed, 172 insertions, 198 deletions

diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h
index 8476175c07e7..6f8cc06ee44e 100644
--- a/include/asm-generic/pgalloc.h
+++ b/include/asm-generic/pgalloc.h
@@ -102,11 +102,6 @@ static inline void pte_free(struct mm_struct *mm, struct page *pte_page)
 	__free_page(pte_page);
 }
 
-#else /* CONFIG_MMU */
-
-/* This is enough for a nommu architecture */
-#define check_pgt_cache()          do { } while (0)
-
 #endif /* CONFIG_MMU */
 
 #endif /* __ASM_GENERIC_PGALLOC_H */
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 75d9d68a6de7..818691846c90 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -1002,9 +1002,8 @@ static inline int pmd_none_or_trans_huge_or_clear_bad(pmd_t *pmd)
  * need this). If THP is not enabled, the pmd can't go away under the
  * code even if MADV_DONTNEED runs, but if THP is enabled we need to
  * run a pmd_trans_unstable before walking the ptes after
- * split_huge_page_pmd returns (because it may have run when the pmd
- * become null, but then a page fault can map in a THP and not a
- * regular page).
+ * split_huge_pmd returns (because it may have run when the pmd become
+ * null, but then a page fault can map in a THP and not a regular page).
  */
 static inline int pmd_trans_unstable(pmd_t *pmd)
 {
@@ -1126,7 +1125,7 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 static inline void init_espfix_bsp(void) { }
 #endif
 
-extern void __init pgd_cache_init(void);
+extern void __init pgtable_cache_init(void);
 
 #ifndef __HAVE_ARCH_PFN_MODIFY_ALLOWED
 static inline bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot)
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 9569e7c786d3..4b898cdbdf05 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -129,11 +129,8 @@ static inline bool compaction_failed(enum compact_result result)
 	return false;
 }
 
-/*
- * Compaction  has backed off for some reason. It might be throttling or
- * lock contention. Retrying is still worthwhile.
- */
-static inline bool compaction_withdrawn(enum compact_result result)
+/* Compaction needs reclaim to be performed first, so it can continue. */
+static inline bool compaction_needs_reclaim(enum compact_result result)
 {
 	/*
 	 * Compaction backed off due to watermark checks for order-0
@@ -142,6 +139,16 @@ static inline bool compaction_withdrawn(enum compact_result result)
 	if (result == COMPACT_SKIPPED)
 		return true;
 
+	return false;
+}
+
+/*
+ * Compaction has backed off for some reason after doing some work or none
+ * at all. It might be throttling or lock contention. Retrying might be still
+ * worthwhile, but with a higher priority if allowed.
+ */
+static inline bool compaction_withdrawn(enum compact_result result)
+{
 	/*
 	 * If compaction is deferred for high-order allocations, it is
 	 * because sync compaction recently failed. If this is the case
@@ -207,6 +214,11 @@ static inline bool compaction_failed(enum compact_result result)
 	return false;
 }
 
+static inline bool compaction_needs_reclaim(enum compact_result result)
+{
+	return false;
+}
+
 static inline bool compaction_withdrawn(enum compact_result result)
 {
 	return true;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 866268c2c6e3..b0c6b0d34d02 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -429,6 +429,7 @@ int pagecache_write_end(struct file *, struct address_space *mapping,
  * @i_pages: Cached pages.
  * @gfp_mask: Memory allocation flags to use for allocating pages.
  * @i_mmap_writable: Number of VM_SHARED mappings.
+ * @nr_thps: Number of THPs in the pagecache (non-shmem only).
  * @i_mmap: Tree of private and shared mappings.
  * @i_mmap_rwsem: Protects @i_mmap and @i_mmap_writable.
  * @nrpages: Number of page entries, protected by the i_pages lock.
@@ -446,6 +447,10 @@ struct address_space {
 	struct xarray		i_pages;
 	gfp_t			gfp_mask;
 	atomic_t		i_mmap_writable;
+#ifdef CONFIG_READ_ONLY_THP_FOR_FS
+	/* number of thp, only for non-shmem files */
+	atomic_t		nr_thps;
+#endif
 	struct rb_root_cached	i_mmap;
 	struct rw_semaphore	i_mmap_rwsem;
 	unsigned long		nrpages;
@@ -2798,6 +2803,33 @@ static inline errseq_t filemap_sample_wb_err(struct address_space *mapping)
 	return errseq_sample(&mapping->wb_err);
 }
 
+static inline int filemap_nr_thps(struct address_space *mapping)
+{
+#ifdef CONFIG_READ_ONLY_THP_FOR_FS
+	return atomic_read(&mapping->nr_thps);
+#else
+	return 0;
+#endif
+}
+
+static inline void filemap_nr_thps_inc(struct address_space *mapping)
+{
+#ifdef CONFIG_READ_ONLY_THP_FOR_FS
+	atomic_inc(&mapping->nr_thps);
+#else
+	WARN_ON_ONCE(1);
+#endif
+}
+
+static inline void filemap_nr_thps_dec(struct address_space *mapping)
+{
+#ifdef CONFIG_READ_ONLY_THP_FOR_FS
+	atomic_dec(&mapping->nr_thps);
+#else
+	WARN_ON_ONCE(1);
+#endif
+}
+
 extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end,
 			   int datasync);
 extern int vfs_fsync(struct file *file, int datasync);
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 45ede62aa85b..61c9ffd89b05 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -267,6 +267,15 @@ static inline bool thp_migration_supported(void)
 	return IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION);
 }
 
+static inline struct list_head *page_deferred_list(struct page *page)
+{
+	/*
+	 * Global or memcg deferred list in the second tail pages is
+	 * occupied by compound_head.
+	 */
+	return &page[2].deferred_list;
+}
+
 #else /* CONFIG_TRANSPARENT_HUGEPAGE */
 #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })
 #define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; })
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index edfca4278319..53fc34f930d0 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -454,7 +454,7 @@ static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
 static inline struct hstate *page_hstate(struct page *page)
 {
 	VM_BUG_ON_PAGE(!PageHuge(page), page);
-	return size_to_hstate(PAGE_SIZE << compound_order(page));
+	return size_to_hstate(page_size(page));
 }
 
 static inline unsigned hstate_index_to_shift(unsigned index)
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index df03825ad1a1..603fbc4e2f70 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1410,8 +1410,6 @@ extern int	   jbd2_journal_clear_err  (journal_t *);
 extern int	   jbd2_journal_bmap(journal_t *, unsigned long, unsigned long long *);
 extern int	   jbd2_journal_force_commit(journal_t *);
 extern int	   jbd2_journal_force_commit_nested(journal_t *);
-extern int	   jbd2_journal_inode_add_write(handle_t *handle, struct jbd2_inode *inode);
-extern int	   jbd2_journal_inode_add_wait(handle_t *handle, struct jbd2_inode *inode);
 extern int	   jbd2_journal_inode_ranged_write(handle_t *handle,
 			struct jbd2_inode *inode, loff_t start_byte,
 			loff_t length);
diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h
index 082d1d2a5216..bc45ea1efbf7 100644
--- a/include/linux/khugepaged.h
+++ b/include/linux/khugepaged.h
@@ -15,6 +15,14 @@ extern int __khugepaged_enter(struct mm_struct *mm);
 extern void __khugepaged_exit(struct mm_struct *mm);
 extern int khugepaged_enter_vma_merge(struct vm_area_struct *vma,
 				      unsigned long vm_flags);
+#ifdef CONFIG_SHMEM
+extern void collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr);
+#else
+static inline void collapse_pte_mapped_thp(struct mm_struct *mm,
+					   unsigned long addr)
+{
+}
+#endif
 
 #define khugepaged_enabled()					       \
 	(transparent_hugepage_flags &				       \
@@ -73,6 +81,10 @@ static inline int khugepaged_enter_vma_merge(struct vm_area_struct *vma,
 {
 	return 0;
 }
+static inline void collapse_pte_mapped_thp(struct mm_struct *mm,
+					   unsigned long addr)
+{
+}
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 #endif /* _LINUX_KHUGEPAGED_H */
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index ad8f1a397ae4..9b60863429cc 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -128,9 +128,8 @@ struct mem_cgroup_per_node {
 
 	struct mem_cgroup_reclaim_iter	iter[DEF_PRIORITY + 1];
 
-#ifdef CONFIG_MEMCG_KMEM
 	struct memcg_shrinker_map __rcu	*shrinker_map;
-#endif
+
 	struct rb_node		tree_node;	/* RB tree node */
 	unsigned long		usage_in_excess;/* Set to the value by which */
 						/* the soft limit is exceeded*/
@@ -331,6 +330,10 @@ struct mem_cgroup {
 	struct list_head event_list;
 	spinlock_t event_list_lock;
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	struct deferred_split deferred_split_queue;
+#endif
+
 	struct mem_cgroup_per_node *nodeinfo[0];
 	/* WARNING: nodeinfo must be the last member here */
 };
@@ -1311,6 +1314,11 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
 	} while ((memcg = parent_mem_cgroup(memcg)));
 	return false;
 }
+
+extern int memcg_expand_shrinker_maps(int new_id);
+
+extern void memcg_set_shrinker_bit(struct mem_cgroup *memcg,
+				   int nid, int shrinker_id);
 #else
 #define mem_cgroup_sockets_enabled 0
 static inline void mem_cgroup_sk_alloc(struct sock *sk) { };
@@ -1319,6 +1327,11 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
 {
 	return false;
 }
+
+static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg,
+					  int nid, int shrinker_id)
+{
+}
 #endif
 
 struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep);
@@ -1390,10 +1403,6 @@ static inline int memcg_cache_id(struct mem_cgroup *memcg)
 	return memcg ? memcg->kmemcg_id : -1;
 }
 
-extern int memcg_expand_shrinker_maps(int new_id);
-
-extern void memcg_set_shrinker_bit(struct mem_cgroup *memcg,
-				   int nid, int shrinker_id);
 #else
 
 static inline int memcg_kmem_charge(struct page *page, gfp_t gfp, int order)
@@ -1435,8 +1444,6 @@ static inline void memcg_put_cache_ids(void)
 {
 }
 
-static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg,
-					  int nid, int shrinker_id) { }
 #endif /* CONFIG_MEMCG_KMEM */
 
 #endif /* _LINUX_MEMCONTROL_H */
diff --git a/include/linux/memory.h b/include/linux/memory.h
index 02e633f3ede0..0ebb105eb261 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -25,7 +25,6 @@
 
 struct memory_block {
 	unsigned long start_section_nr;
-	unsigned long end_section_nr;
 	unsigned long state;		/* serialized by the dev->lock */
 	int section_count;		/* serialized by mem_sysfs_mutex */
 	int online_type;		/* for passing data to online routine */
@@ -80,9 +79,9 @@ struct mem_section;
 #define IPC_CALLBACK_PRI        10
 
 #ifndef CONFIG_MEMORY_HOTPLUG_SPARSE
-static inline int memory_dev_init(void)
+static inline void memory_dev_init(void)
 {
-	return 0;
+	return;
 }
 static inline int register_memory_notifier(struct notifier_block *nb)
 {
@@ -113,7 +112,7 @@ extern int register_memory_isolate_notifier(struct notifier_block *nb);
 extern void unregister_memory_isolate_notifier(struct notifier_block *nb);
 int create_memory_block_devices(unsigned long start, unsigned long size);
 void remove_memory_block_devices(unsigned long start, unsigned long size);
-extern int memory_dev_init(void);
+extern void memory_dev_init(void);
 extern int memory_notify(unsigned long val, void *v);
 extern int memory_isolate_notify(unsigned long val, void *v);
 extern struct memory_block *find_memory_block(struct mem_section *);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 7cf955feb823..294a67b94147 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -805,6 +805,24 @@ static inline void set_compound_order(struct page *page, unsigned int order)
 	page[1].compound_order = order;
 }
 
+/* Returns the number of pages in this potentially compound page. */
+static inline unsigned long compound_nr(struct page *page)
+{
+	return 1UL << compound_order(page);
+}
+
+/* Returns the number of bytes in this potentially compound page. */
+static inline unsigned long page_size(struct page *page)
+{
+	return PAGE_SIZE << compound_order(page);
+}
+
+/* Returns the number of bits needed for the number of bytes in a page */
+static inline unsigned int page_shift(struct page *page)
+{
+	return PAGE_SHIFT + compound_order(page);
+}
+
 void free_compound_page(struct page *page);
 
 #ifdef CONFIG_MMU
@@ -1057,8 +1075,9 @@ static inline void put_user_page(struct page *page)
 	put_page(page);
 }
 
-void put_user_pages_dirty(struct page **pages, unsigned long npages);
-void put_user_pages_dirty_lock(struct page **pages, unsigned long npages);
+void put_user_pages_dirty_lock(struct page **pages, unsigned long npages,
+			       bool make_dirty);
+
 void put_user_pages(struct page **pages, unsigned long npages);
 
 #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
@@ -1405,7 +1424,11 @@ extern void pagefault_out_of_memory(void);
 
 extern void show_free_areas(unsigned int flags, nodemask_t *nodemask);
 
+#ifdef CONFIG_MMU
 extern bool can_do_mlock(void);
+#else
+static inline bool can_do_mlock(void) { return false; }
+#endif
 extern int user_shm_lock(size_t, struct user_struct *);
 extern void user_shm_unlock(size_t, struct user_struct *);
 
@@ -2305,6 +2328,8 @@ extern int install_special_mapping(struct mm_struct *mm,
 				   unsigned long addr, unsigned long len,
 				   unsigned long flags, struct page **pages);
 
+unsigned long randomize_stack_top(unsigned long stack_top);
+
 extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
 
 extern unsigned long mmap_region(struct file *file, unsigned long addr,
@@ -2568,6 +2593,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 #define FOLL_COW	0x4000	/* internal GUP flag */
 #define FOLL_ANON	0x8000	/* don't do file mappings */
 #define FOLL_LONGTERM	0x10000	/* mapping lifetime is indefinite: see below */
+#define FOLL_SPLIT_PMD	0x20000	/* split huge pmd before returning */
 
 /*
  * NOTE on FOLL_LONGTERM:
@@ -2845,5 +2871,12 @@ void __init setup_nr_node_ids(void);
 static inline void setup_nr_node_ids(void) {}
 #endif
 
+extern int memcmp_pages(struct page *page1, struct page *page2);
+
+static inline int pages_identical(struct page *page1, struct page *page2)
+{
+	return !memcmp_pages(page1, page2);
+}
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_MM_H */
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 0b739f360cec..5183e0d77dfa 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -138,6 +138,7 @@ struct page {
 		struct {	/* Second tail page of compound page */
 			unsigned long _compound_pad_1;	/* compound_head */
 			unsigned long _compound_pad_2;
+			/* For both global and memcg */
 			struct list_head deferred_list;
 		};
 		struct {	/* Page table pages */
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 3f38c30d2f13..bda20282746b 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -235,6 +235,8 @@ enum node_stat_item {
 	NR_SHMEM,		/* shmem pages (included tmpfs/GEM pages) */
 	NR_SHMEM_THPS,
 	NR_SHMEM_PMDMAPPED,
+	NR_FILE_THPS,
+	NR_FILE_PMDMAPPED,
 	NR_ANON_THPS,
 	NR_UNSTABLE_NFS,	/* NFS unstable pages */
 	NR_VMSCAN_WRITE,
@@ -677,6 +679,14 @@ struct zonelist {
 extern struct page *mem_map;
 #endif
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+struct deferred_split {
+	spinlock_t split_queue_lock;
+	struct list_head split_queue;
+	unsigned long split_queue_len;
+};
+#endif
+
 /*
  * On NUMA machines, each NUMA node would have a pg_data_t to describe
  * it's memory layout. On UMA machines there is a single pglist_data which
@@ -756,9 +766,7 @@ typedef struct pglist_data {
 #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	spinlock_t split_queue_lock;
-	struct list_head split_queue;
-	unsigned long split_queue_len;
+	struct deferred_split deferred_split_queue;
 #endif
 
 	/* Fields commonly accessed by the page reclaim scanner */
diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h
index 09592951725c..682fd465df06 100644
--- a/include/linux/page_ext.h
+++ b/include/linux/page_ext.h
@@ -18,6 +18,7 @@ struct page_ext_operations {
 
 enum page_ext_flags {
 	PAGE_EXT_OWNER,
+	PAGE_EXT_OWNER_ACTIVE,
 #if defined(CONFIG_IDLE_PAGE_TRACKING) && !defined(CONFIG_64BIT)
 	PAGE_EXT_YOUNG,
 	PAGE_EXT_IDLE,
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index c7552459a15f..37a4d9e32cd3 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -333,6 +333,16 @@ static inline struct page *grab_cache_page_nowait(struct address_space *mapping,
 			mapping_gfp_mask(mapping));
 }
 
+static inline struct page *find_subpage(struct page *page, pgoff_t offset)
+{
+	if (PageHuge(page))
+		return page;
+
+	VM_BUG_ON_PAGE(PageTail(page), page);
+
+	return page + (offset & (compound_nr(page) - 1));
+}
+
 struct page *find_get_entry(struct address_space *mapping, pgoff_t offset);
 struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset);
 unsigned find_get_entries(struct address_space *mapping, pgoff_t start,
diff --git a/include/linux/quicklist.h b/include/linux/quicklist.h
deleted file mode 100644
index 034982c98c8b..000000000000
--- a/include/linux/quicklist.h
+++ /dev/null
@@ -1,94 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef LINUX_QUICKLIST_H
-#define LINUX_QUICKLIST_H
-/*
- * Fast allocations and disposal of pages. Pages must be in the condition
- * as needed after allocation when they are freed. Per cpu lists of pages
- * are kept that only contain node local pages.
- *
- * (C) 2007, SGI. Christoph Lameter <cl@linux.com>
- */
-#include <linux/kernel.h>
-#include <linux/gfp.h>
-#include <linux/percpu.h>
-
-#ifdef CONFIG_QUICKLIST
-
-struct quicklist {
-	void *page;
-	int nr_pages;
-};
-
-DECLARE_PER_CPU(struct quicklist, quicklist)[CONFIG_NR_QUICK];
-
-/*
- * The two key functions quicklist_alloc and quicklist_free are inline so
- * that they may be custom compiled for the platform.
- * Specifying a NULL ctor can remove constructor support. Specifying
- * a constant quicklist allows the determination of the exact address
- * in the per cpu area.
- *
- * The fast patch in quicklist_alloc touched only a per cpu cacheline and
- * the first cacheline of the page itself. There is minmal overhead involved.
- */
-static inline void *quicklist_alloc(int nr, gfp_t flags, void (*ctor)(void *))
-{
-	struct quicklist *q;
-	void **p = NULL;
-
-	q =&get_cpu_var(quicklist)[nr];
-	p = q->page;
-	if (likely(p)) {
-		q->page = p[0];
-		p[0] = NULL;
-		q->nr_pages--;
-	}
-	put_cpu_var(quicklist);
-	if (likely(p))
-		return p;
-
-	p = (void *)__get_free_page(flags | __GFP_ZERO);
-	if (ctor && p)
-		ctor(p);
-	return p;
-}
-
-static inline void __quicklist_free(int nr, void (*dtor)(void *), void *p,
-	struct page *page)
-{
-	struct quicklist *q;
-
-	q = &get_cpu_var(quicklist)[nr];
-	*(void **)p = q->page;
-	q->page = p;
-	q->nr_pages++;
-	put_cpu_var(quicklist);
-}
-
-static inline void quicklist_free(int nr, void (*dtor)(void *), void *pp)
-{
-	__quicklist_free(nr, dtor, pp, virt_to_page(pp));
-}
-
-static inline void quicklist_free_page(int nr, void (*dtor)(void *),
-							struct page *page)
-{
-	__quicklist_free(nr, dtor, page_address(page), page);
-}
-
-void quicklist_trim(int nr, void (*dtor)(void *),
-	unsigned long min_pages, unsigned long max_free);
-
-unsigned long quicklist_total_size(void);
-
-#else
-
-static inline unsigned long quicklist_total_size(void)
-{
-	return 0;
-}
-
-#endif
-
-#endif /* LINUX_QUICKLIST_H */
-
diff --git a/include/linux/shrinker.h b/include/linux/shrinker.h
index 9443cafd1969..0f80123650e2 100644
--- a/include/linux/shrinker.h
+++ b/include/linux/shrinker.h
@@ -69,7 +69,7 @@ struct shrinker {
 
 	/* These are for internal use */
 	struct list_head list;
-#ifdef CONFIG_MEMCG_KMEM
+#ifdef CONFIG_MEMCG
 	/* ID in shrinker_idr */
 	int id;
 #endif
@@ -81,6 +81,11 @@ struct shrinker {
 /* Flags */
 #define SHRINKER_NUMA_AWARE	(1 << 0)
 #define SHRINKER_MEMCG_AWARE	(1 << 1)
+/*
+ * It just makes sense when the shrinker is also MEMCG_AWARE for now,
+ * non-MEMCG_AWARE shrinker should not have this flag set.
+ */
+#define SHRINKER_NONSLAB	(1 << 2)
 
 extern int prealloc_shrinker(struct shrinker *shrinker);
 extern void register_shrinker_prepared(struct shrinker *shrinker);
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 56c9c7eed34e..ab2b98ad76e1 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -595,68 +595,6 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
 	return __kmalloc_node(size, flags, node);
 }
 
-struct memcg_cache_array {
-	struct rcu_head rcu;
-	struct kmem_cache *entries[0];
-};
-
-/*
- * This is the main placeholder for memcg-related information in kmem caches.
- * Both the root cache and the child caches will have it. For the root cache,
- * this will hold a dynamically allocated array large enough to hold
- * information about the currently limited memcgs in the system. To allow the
- * array to be accessed without taking any locks, on relocation we free the old
- * version only after a grace period.
- *
- * Root and child caches hold different metadata.
- *
- * @root_cache:	Common to root and child caches.  NULL for root, pointer to
- *		the root cache for children.
- *
- * The following fields are specific to root caches.
- *
- * @memcg_caches: kmemcg ID indexed table of child caches.  This table is
- *		used to index child cachces during allocation and cleared
- *		early during shutdown.
- *
- * @root_caches_node: List node for slab_root_caches list.
- *
- * @children:	List of all child caches.  While the child caches are also
- *		reachable through @memcg_caches, a child cache remains on
- *		this list until it is actually destroyed.
- *
- * The following fields are specific to child caches.
- *
- * @memcg:	Pointer to the memcg this cache belongs to.
- *
- * @children_node: List node for @root_cache->children list.
- *
- * @kmem_caches_node: List node for @memcg->kmem_caches list.
- */
-struct memcg_cache_params {
-	struct kmem_cache *root_cache;
-	union {
-		struct {
-			struct memcg_cache_array __rcu *memcg_caches;
-			struct list_head __root_caches_node;
-			struct list_head children;
-			bool dying;
-		};
-		struct {
-			struct mem_cgroup *memcg;
-			struct list_head children_node;
-			struct list_head kmem_caches_node;
-			struct percpu_ref refcnt;
-
-			void (*work_fn)(struct kmem_cache *);
-			union {
-				struct rcu_head rcu_head;
-				struct work_struct work;
-			};
-		};
-	};
-};
-
 int memcg_update_all_caches(int num_memcgs);
 
 /**
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index dfa718ffdd4f..4e7809408073 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -53,15 +53,21 @@ struct vmap_area {
 	unsigned long va_start;
 	unsigned long va_end;
 
-	/*
-	 * Largest available free size in subtree.
-	 */
-	unsigned long subtree_max_size;
-	unsigned long flags;
 	struct rb_node rb_node;         /* address sorted rbtree */
 	struct list_head list;          /* address sorted list */
-	struct llist_node purge_list;    /* "lazy purge" list */
-	struct vm_struct *vm;
+
+	/*
+	 * The following three variables can be packed, because
+	 * a vmap_area object is always one of the three states:
+	 *    1) in "free" tree (root is vmap_area_root)
+	 *    2) in "busy" tree (root is free_vmap_area_root)
+	 *    3) in purge list  (head is vmap_purge_list)
+	 */
+	union {
+		unsigned long subtree_max_size; /* in "free" tree */
+		struct vm_struct *vm;           /* in "busy" tree */
+		struct llist_node purge_list;   /* in purge list */
+	};
 };
 
 /*
diff --git a/include/linux/zpool.h b/include/linux/zpool.h
index 7238865e75b0..51bf43076165 100644
--- a/include/linux/zpool.h
+++ b/include/linux/zpool.h
@@ -46,6 +46,8 @@ const char *zpool_get_type(struct zpool *pool);
 
 void zpool_destroy_pool(struct zpool *pool);
 
+bool zpool_malloc_support_movable(struct zpool *pool);
+
 int zpool_malloc(struct zpool *pool, size_t size, gfp_t gfp,
 			unsigned long *handle);
 
@@ -90,6 +92,7 @@ struct zpool_driver {
 			struct zpool *zpool);
 	void (*destroy)(void *pool);
 
+	bool malloc_support_movable;
 	int (*malloc)(void *pool, size_t size, gfp_t gfp,
 				unsigned long *handle);
 	void (*free)(void *pool, unsigned long handle);