Merge branch 'mm-everything' of git://git.kernel.org/pub/scm/linux/ke…

…rnel/git/akpm/mm

# Conflicts:
#	Documentation/translations/zh_CN/accounting/delay-accounting.rst
#	include/linux/memcontrol.h
#	mm/filemap.c
#	mm/memcontrol.c

Documentation/accounting/delay-accounting.rst

@@ -109,17 +109,17 @@ Get sum of delays, since system boot, for all pids with tgid 5::
 	CPU             count     real total  virtual total    delay total  delay average
 	                    8        7000000        6872122        3382277          0.423ms
 	IO              count    delay total  delay average
-		            0              0              0ms
+                   0              0          0.000ms
 	SWAP            count    delay total  delay average
-	                    0              0              0ms
+                       0              0          0.000ms
 	RECLAIM         count    delay total  delay average
-		            0              0              0ms
+                   0              0          0.000ms
 	THRASHING       count    delay total  delay average
-	                    0              0              0ms
+                       0              0          0.000ms
 	COMPACT         count    delay total  delay average
-	                    0              0              0ms
-        WPCOPY          count    delay total  delay average
-                            0              0              0ms
+                       0              0          0.000ms
+   WPCOPY          count    delay total  delay average
+                       0              0          0.000ms
 
 Get IO accounting for pid 1, it works only with -p::
 

Documentation/admin-guide/mm/ksm.rst

@@ -171,6 +171,13 @@ stable_node_chains
         the number of KSM pages that hit the ``max_page_sharing`` limit
 stable_node_dups
         number of duplicated KSM pages
+zero_pages_sharing
+        how many empty pages are sharing kernel zero page(s) instead of
+        with each other as it would happen normally. Only effective when
+        enabling ``use_zero_pages`` knob.
+
+When enabling ``use_zero_pages``, the sum of ``pages_sharing`` +
+``zero_pages_sharing`` represents how much really saved by KSM.
 
 A high ratio of ``pages_sharing`` to ``pages_shared`` indicates good
 sharing, but a high ratio of ``pages_unshared`` to ``pages_sharing``

Documentation/translations/zh_CN/accounting/delay-accounting.rst

@@ -92,17 +92,17 @@ getdelays命令的一般格式::
 	CPU             count     real total  virtual total    delay total  delay average
 	                    8        7000000        6872122        3382277          0.423ms
 	IO              count    delay total  delay average
-	                    0              0              0ms
+	                    0              0              0.000ms
 	SWAP            count    delay total  delay average
-	                    0              0              0ms
+	                    0              0              0.000ms
 	RECLAIM         count    delay total  delay average
-	                    0              0              0ms
+	                    0              0              0.000ms
 	THRASHING       count    delay total  delay average
-	                    0              0              0ms
+	                    0              0              0.000ms
 	COMPACT         count    delay total  delay average
-	                    0              0              0ms
-    WPCOPY          count    delay total  delay average
-                       0              0              0ms
+	                    0              0              0.000ms
+	WPCOPY          count    delay total  delay average
+	                    0              0              0.000ms
 
 获取pid为1的IO计数，它只和-p一起使用::
 	# ./getdelays -i -p 1

arch/m68k/include/asm/page_no.h

@@ -28,6 +28,8 @@ extern unsigned long memory_end;
 #define	virt_addr_valid(kaddr)	(((unsigned long)(kaddr) >= PAGE_OFFSET) && \
 				((unsigned long)(kaddr) < memory_end))
 
+#define ARCH_PFN_OFFSET PHYS_PFN(PAGE_OFFSET_RAW)
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _M68K_PAGE_NO_H */

arch/sh/mm/init.c

@@ -301,6 +301,7 @@ void __init paging_init(void)
 	 */
 	max_low_pfn = max_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT;
 	min_low_pfn = __MEMORY_START >> PAGE_SHIFT;
+	set_max_mapnr(max_low_pfn - min_low_pfn);
 
 	nodes_clear(node_online_map);
 

fs/nilfs2/ioctl.c

@@ -1114,7 +1114,14 @@ static int nilfs_ioctl_set_alloc_range(struct inode *inode, void __user *argp)
 
 	minseg = range[0] + segbytes - 1;
 	do_div(minseg, segbytes);
+
+	if (range[1] < 4096)
+		goto out;
+
 	maxseg = NILFS_SB2_OFFSET_BYTES(range[1]);
+	if (maxseg < segbytes)
+		goto out;
+
 	do_div(maxseg, segbytes);
 	maxseg--;
 

fs/nilfs2/super.c

@@ -408,6 +408,15 @@ int nilfs_resize_fs(struct super_block *sb, __u64 newsize)
 	if (newsize > devsize)
 		goto out;
 
+	/*
+	 * Prevent underflow in second superblock position calculation.
+	 * The exact minimum size check is done in nilfs_sufile_resize().
+	 */
+	if (newsize < 4096) {
+		ret = -ENOSPC;
+		goto out;
+	}
+
 	/*
 	 * Write lock is required to protect some functions depending
 	 * on the number of segments, the number of reserved segments,

fs/nilfs2/the_nilfs.c

@@ -544,9 +544,15 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs,
 {
 	struct nilfs_super_block **sbp = nilfs->ns_sbp;
 	struct buffer_head **sbh = nilfs->ns_sbh;
-	u64 sb2off = NILFS_SB2_OFFSET_BYTES(bdev_nr_bytes(nilfs->ns_bdev));
+	u64 sb2off, devsize = bdev_nr_bytes(nilfs->ns_bdev);
 	int valid[2], swp = 0;
 
+	if (devsize < NILFS_SEG_MIN_BLOCKS * NILFS_MIN_BLOCK_SIZE + 4096) {
+		nilfs_err(sb, "device size too small");
+		return -EINVAL;
+	}
+	sb2off = NILFS_SB2_OFFSET_BYTES(devsize);
+
 	sbp[0] = nilfs_read_super_block(sb, NILFS_SB_OFFSET_BYTES, blocksize,
 					&sbh[0]);
 	sbp[1] = nilfs_read_super_block(sb, sb2off, blocksize, &sbh[1]);

fs/proc/base.c

@@ -3211,6 +3211,7 @@ static int proc_pid_ksm_stat(struct seq_file *m, struct pid_namespace *ns,
 	mm = get_task_mm(task);
 	if (mm) {
 		seq_printf(m, "ksm_rmap_items %lu\n", mm->ksm_rmap_items);
+		seq_printf(m, "zero_pages_sharing %lu\n", mm->ksm_zero_pages_sharing);
 		mmput(mm);
 	}
 

include/linux/hugetlb.h

@@ -171,7 +171,7 @@ bool hugetlb_reserve_pages(struct inode *inode, long from, long to,
 						vm_flags_t vm_flags);
 long hugetlb_unreserve_pages(struct inode *inode, long start, long end,
 						long freed);
-int isolate_hugetlb(struct folio *folio, struct list_head *list);
+bool isolate_hugetlb(struct folio *folio, struct list_head *list);
 int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison);
 int get_huge_page_for_hwpoison(unsigned long pfn, int flags,
 				bool *migratable_cleared);
@@ -413,9 +413,9 @@ static inline pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr,
 	return NULL;
 }
 
-static inline int isolate_hugetlb(struct folio *folio, struct list_head *list)
+static inline bool isolate_hugetlb(struct folio *folio, struct list_head *list)
 {
-	return -EBUSY;
+	return false;
 }
 
 static inline int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison)
@@ -781,7 +781,10 @@ static inline struct hstate *hstate_sizelog(int page_size_log)
 	if (!page_size_log)
 		return &default_hstate;
 
-	return size_to_hstate(1UL << page_size_log);
+	if (page_size_log < BITS_PER_LONG)
+		return size_to_hstate(1UL << page_size_log);
+
+	return NULL;
 }
 
 static inline struct hstate *hstate_vma(struct vm_area_struct *vma)

include/linux/memcontrol.h

@@ -1782,24 +1782,24 @@ static inline bool memcg_bpf_enabled(void)
 	return static_branch_likely(&memcg_bpf_enabled_key);
 }
 
-extern struct static_key_false memcg_kmem_enabled_key;
+extern struct static_key_false memcg_kmem_online_key;
 
-static inline bool memcg_kmem_enabled(void)
+static inline bool memcg_kmem_online(void)
 {
-	return static_branch_likely(&memcg_kmem_enabled_key);
+	return static_branch_likely(&memcg_kmem_online_key);
 }
 
 static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp,
 					 int order)
 {
-	if (memcg_kmem_enabled())
+	if (memcg_kmem_online())
 		return __memcg_kmem_charge_page(page, gfp, order);
 	return 0;
 }
 
 static inline void memcg_kmem_uncharge_page(struct page *page, int order)
 {
-	if (memcg_kmem_enabled())
+	if (memcg_kmem_online())
 		__memcg_kmem_uncharge_page(page, order);
 }
 
@@ -1820,7 +1820,7 @@ static inline void count_objcg_event(struct obj_cgroup *objcg,
 {
 	struct mem_cgroup *memcg;
 
-	if (!memcg_kmem_enabled())
+	if (!memcg_kmem_online())
 		return;
 
 	rcu_read_lock();
@@ -1865,7 +1865,7 @@ static inline bool memcg_bpf_enabled(void)
 	return false;
 }
 
-static inline bool memcg_kmem_enabled(void)
+static inline bool memcg_kmem_online(void)
 {
 	return false;
 }

include/linux/migrate.h

@@ -18,6 +18,7 @@ struct migration_target_control;
  * - zero on page migration success;
  */
 #define MIGRATEPAGE_SUCCESS		0
+#define MIGRATEPAGE_UNMAP		1
 
 /**
  * struct movable_operations - Driver page migration
@@ -61,16 +62,16 @@ extern const char *migrate_reason_names[MR_TYPES];
 
 #ifdef CONFIG_MIGRATION
 
-extern void putback_movable_pages(struct list_head *l);
+void putback_movable_pages(struct list_head *l);
 int migrate_folio_extra(struct address_space *mapping, struct folio *dst,
 		struct folio *src, enum migrate_mode mode, int extra_count);
 int migrate_folio(struct address_space *mapping, struct folio *dst,
 		struct folio *src, enum migrate_mode mode);
-extern int migrate_pages(struct list_head *l, new_page_t new, free_page_t free,
-		unsigned long private, enum migrate_mode mode, int reason,
-		unsigned int *ret_succeeded);
-extern struct page *alloc_migration_target(struct page *page, unsigned long private);
-extern int isolate_movable_page(struct page *page, isolate_mode_t mode);
+int migrate_pages(struct list_head *l, new_page_t new, free_page_t free,
+		  unsigned long private, enum migrate_mode mode, int reason,
+		  unsigned int *ret_succeeded);
+struct page *alloc_migration_target(struct page *page, unsigned long private);
+bool isolate_movable_page(struct page *page, isolate_mode_t mode);
 
 int migrate_huge_page_move_mapping(struct address_space *mapping,
 		struct folio *dst, struct folio *src);
@@ -91,8 +92,8 @@ static inline int migrate_pages(struct list_head *l, new_page_t new,
 static inline struct page *alloc_migration_target(struct page *page,
 		unsigned long private)
 	{ return NULL; }
-static inline int isolate_movable_page(struct page *page, isolate_mode_t mode)
-	{ return -EBUSY; }
+static inline bool isolate_movable_page(struct page *page, isolate_mode_t mode)
+	{ return false; }
 
 static inline int migrate_huge_page_move_mapping(struct address_space *mapping,
 				  struct folio *dst, struct folio *src)
@@ -141,8 +142,8 @@ const struct movable_operations *page_movable_ops(struct page *page)
 }
 
 #ifdef CONFIG_NUMA_BALANCING
-extern int migrate_misplaced_page(struct page *page,
-				  struct vm_area_struct *vma, int node);
+int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
+			   int node);
 #else
 static inline int migrate_misplaced_page(struct page *page,
 					 struct vm_area_struct *vma, int node)

include/linux/mm_types.h

@@ -740,14 +740,19 @@ struct mm_struct {
 #ifdef CONFIG_KSM
 		/*
 		 * Represent how many pages of this process are involved in KSM
-		 * merging.
+		 * merging (not including ksm_zero_pages_sharing).
 		 */
 		unsigned long ksm_merging_pages;
 		/*
 		 * Represent how many pages are checked for ksm merging
 		 * including merged and not merged.
 		 */
 		unsigned long ksm_rmap_items;
+		/*
+		 * Represent how many empty pages are merged with kernel zero
+		 * pages when enabling KSM use_zero_pages.
+		 */
+		unsigned long ksm_zero_pages_sharing;
 #endif
 #ifdef CONFIG_LRU_GEN
 		struct {