Merge branch 'akpm' (patches from Andrew)

Merge fixes from Andrew Morton:
 "18 fixes"

[ The 18 fixes turned into 17 commits, because one of the fixes was a
  fix for another patch in the series that I just folded in by editing
  the patch manually - hopefully correctly     - Linus ]

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  mm: fix memory leak in copy_huge_pmd()
  drivers/hwspinlock: fix race between radix tree insertion and lookup
  radix-tree: fix race in gang lookup
  mm/vmpressure.c: fix subtree pressure detection
  mm: polish virtual memory accounting
  mm: warn about VmData over RLIMIT_DATA
  Documentation: cgroup-v2: add memory.stat::sock description
  mm: memcontrol: drop superfluous entry in the per-memcg stats array
  drivers/scsi/sg.c: mark VMA as VM_IO to prevent migration
  proc: revert /proc/<pid>/maps [stack:TID] annotation
  numa: fix /proc/<pid>/numa_maps for hugetlbfs on s390
  MAINTAINERS: update Seth email
  ocfs2/cluster: fix memory leak in o2hb_region_release
  lib/test-string_helpers.c: fix and improve string_get_size() tests
  thp: limit number of object to scan on deferred_split_scan()
  thp: change deferred_split_count() to return number of THP in queue
  thp: make split_queue per-node

Documentation/cgroup-v2.txt

@@ -843,6 +843,10 @@ PAGE_SIZE multiple when read back.
 		Amount of memory used to cache filesystem data,
 		including tmpfs and shared memory.
 
+	  sock
+
+		Amount of memory used in network transmission buffers
+
 	  file_mapped
 
 		Amount of cached filesystem data mapped with mmap()

Documentation/filesystems/proc.txt

@@ -240,8 +240,8 @@ Table 1-2: Contents of the status files (as of 4.1)
  RssFile                     size of resident file mappings
  RssShmem                    size of resident shmem memory (includes SysV shm,
                              mapping of tmpfs and shared anonymous mappings)
- VmData                      size of data, stack, and text segments
- VmStk                       size of data, stack, and text segments
+ VmData                      size of private data segments
+ VmStk                       size of stack segments
  VmExe                       size of text segment
  VmLib                       size of shared library code
  VmPTE                       size of page table entries
@@ -356,7 +356,7 @@ address           perms offset  dev   inode      pathname
 a7cb1000-a7cb2000 ---p 00000000 00:00 0
 a7cb2000-a7eb2000 rw-p 00000000 00:00 0
 a7eb2000-a7eb3000 ---p 00000000 00:00 0
-a7eb3000-a7ed5000 rw-p 00000000 00:00 0          [stack:1001]
+a7eb3000-a7ed5000 rw-p 00000000 00:00 0
 a7ed5000-a8008000 r-xp 00000000 03:00 4222       /lib/libc.so.6
 a8008000-a800a000 r--p 00133000 03:00 4222       /lib/libc.so.6
 a800a000-a800b000 rw-p 00135000 03:00 4222       /lib/libc.so.6
@@ -388,7 +388,6 @@ is not associated with a file:
 
  [heap]                   = the heap of the program
  [stack]                  = the stack of the main process
- [stack:1001]             = the stack of the thread with tid 1001
  [vdso]                   = the "virtual dynamic shared object",
                             the kernel system call handler
 
@@ -396,10 +395,8 @@ is not associated with a file:
 
 The /proc/PID/task/TID/maps is a view of the virtual memory from the viewpoint
 of the individual tasks of a process. In this file you will see a mapping marked
-as [stack] if that task sees it as a stack. This is a key difference from the
-content of /proc/PID/maps, where you will see all mappings that are being used
-as stack by all of those tasks. Hence, for the example above, the task-level
-map, i.e. /proc/PID/task/TID/maps for thread 1001 will look like this:
+as [stack] if that task sees it as a stack. Hence, for the example above, the
+task-level map, i.e. /proc/PID/task/TID/maps for thread 1001 will look like this:
 
 08048000-08049000 r-xp 00000000 03:00 8312       /opt/test
 08049000-0804a000 rw-p 00001000 03:00 8312       /opt/test

Documentation/kernel-parameters.txt

@@ -1496,6 +1496,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			could change it dynamically, usually by
 			/sys/module/printk/parameters/ignore_loglevel.
 
+	ignore_rlimit_data
+			Ignore RLIMIT_DATA setting for data mappings,
+			print warning at first misuse.  Can be changed via
+			/sys/module/kernel/parameters/ignore_rlimit_data.
+
 	ihash_entries=	[KNL]
 			Set number of hash buckets for inode cache.
 

MAINTAINERS

@@ -12150,7 +12150,7 @@ F:	drivers/net/hamradio/*scc.c
 F:	drivers/net/hamradio/z8530.h
 
 ZBUD COMPRESSED PAGE ALLOCATOR
-M:	Seth Jennings <sjennings@variantweb.net>
+M:	Seth Jennings <sjenning@redhat.com>
 L:	linux-mm@kvack.org
 S:	Maintained
 F:	mm/zbud.c
@@ -12205,7 +12205,7 @@ F:	include/linux/zsmalloc.h
 F:	Documentation/vm/zsmalloc.txt
 
 ZSWAP COMPRESSED SWAP CACHING
-M:	Seth Jennings <sjennings@variantweb.net>
+M:	Seth Jennings <sjenning@redhat.com>
 L:	linux-mm@kvack.org
 S:	Maintained
 F:	mm/zswap.c

drivers/hwspinlock/hwspinlock_core.c

@@ -313,6 +313,10 @@ int of_hwspin_lock_get_id(struct device_node *np, int index)
 		hwlock = radix_tree_deref_slot(slot);
 		if (unlikely(!hwlock))
 			continue;
+		if (radix_tree_is_indirect_ptr(hwlock)) {
+			slot = radix_tree_iter_retry(&iter);
+			continue;
+		}
 
 		if (hwlock->bank->dev->of_node == args.np) {
 			ret = 0;

drivers/scsi/sg.c

@@ -1261,7 +1261,7 @@ sg_mmap(struct file *filp, struct vm_area_struct *vma)
 	}
 
 	sfp->mmap_called = 1;
-	vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;
+	vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP;
 	vma->vm_private_data = sfp;
 	vma->vm_ops = &sg_mmap_vm_ops;
 	return 0;

fs/ocfs2/cluster/heartbeat.c

@@ -1254,15 +1254,15 @@ static const struct file_operations o2hb_debug_fops = {
 
 void o2hb_exit(void)
 {
-	kfree(o2hb_db_livenodes);
-	kfree(o2hb_db_liveregions);
-	kfree(o2hb_db_quorumregions);
-	kfree(o2hb_db_failedregions);
 	debugfs_remove(o2hb_debug_failedregions);
 	debugfs_remove(o2hb_debug_quorumregions);
 	debugfs_remove(o2hb_debug_liveregions);
 	debugfs_remove(o2hb_debug_livenodes);
 	debugfs_remove(o2hb_debug_dir);
+	kfree(o2hb_db_livenodes);
+	kfree(o2hb_db_liveregions);
+	kfree(o2hb_db_quorumregions);
+	kfree(o2hb_db_failedregions);
 }
 
 static struct dentry *o2hb_debug_create(const char *name, struct dentry *dir,
@@ -1438,13 +1438,15 @@ static void o2hb_region_release(struct config_item *item)
 
 	kfree(reg->hr_slots);
 
-	kfree(reg->hr_db_regnum);
-	kfree(reg->hr_db_livenodes);
 	debugfs_remove(reg->hr_debug_livenodes);
 	debugfs_remove(reg->hr_debug_regnum);
 	debugfs_remove(reg->hr_debug_elapsed_time);
 	debugfs_remove(reg->hr_debug_pinned);
 	debugfs_remove(reg->hr_debug_dir);
+	kfree(reg->hr_db_livenodes);
+	kfree(reg->hr_db_regnum);
+	kfree(reg->hr_debug_elapsed_time);
+	kfree(reg->hr_debug_pinned);
 
 	spin_lock(&o2hb_live_lock);
 	list_del(&reg->hr_all_item);

fs/proc/task_mmu.c

@@ -259,23 +259,29 @@ static int do_maps_open(struct inode *inode, struct file *file,
 				sizeof(struct proc_maps_private));
 }
 
-static pid_t pid_of_stack(struct proc_maps_private *priv,
-				struct vm_area_struct *vma, bool is_pid)
+/*
+ * Indicate if the VMA is a stack for the given task; for
+ * /proc/PID/maps that is the stack of the main task.
+ */
+static int is_stack(struct proc_maps_private *priv,
+		    struct vm_area_struct *vma, int is_pid)
 {
+	int stack = 0;
+
+	if (is_pid) {
+		stack = vma->vm_start <= vma->vm_mm->start_stack &&
+			vma->vm_end >= vma->vm_mm->start_stack;
+	} else {
 		struct inode *inode = priv->inode;
 		struct task_struct *task;
-	pid_t ret = 0;
 
 		rcu_read_lock();
 		task = pid_task(proc_pid(inode), PIDTYPE_PID);
-	if (task) {
-		task = task_of_stack(task, vma, is_pid);
 		if (task)
-			ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info);
-	}
+			stack = vma_is_stack_for_task(vma, task);
 		rcu_read_unlock();
-
-	return ret;
+	}
+	return stack;
 }
 
 static void
@@ -335,8 +341,6 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 
 	name = arch_vma_name(vma);
 	if (!name) {
-		pid_t tid;
-
 		if (!mm) {
 			name = "[vdso]";
 			goto done;
@@ -348,21 +352,8 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 			goto done;
 		}
 
-		tid = pid_of_stack(priv, vma, is_pid);
-		if (tid != 0) {
-			/*
-			 * Thread stack in /proc/PID/task/TID/maps or
-			 * the main process stack.
-			 */
-			if (!is_pid || (vma->vm_start <= mm->start_stack &&
-			    vma->vm_end >= mm->start_stack)) {
+		if (is_stack(priv, vma, is_pid))
 			name = "[stack]";
-			} else {
-				/* Thread stack in /proc/PID/maps */
-				seq_pad(m, ' ');
-				seq_printf(m, "[stack:%d]", tid);
-			}
-		}
 	}
 
 done:
@@ -1552,18 +1543,19 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask,
 		unsigned long addr, unsigned long end, struct mm_walk *walk)
 {
+	pte_t huge_pte = huge_ptep_get(pte);
 	struct numa_maps *md;
 	struct page *page;
 
-	if (!pte_present(*pte))
+	if (!pte_present(huge_pte))
 		return 0;
 
-	page = pte_page(*pte);
+	page = pte_page(huge_pte);
 	if (!page)
 		return 0;
 
 	md = walk->private;
-	gather_stats(page, md, pte_dirty(*pte), 1);
+	gather_stats(page, md, pte_dirty(huge_pte), 1);
 	return 0;
 }
 
@@ -1617,19 +1609,8 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
 		seq_file_path(m, file, "\n\t= ");
 	} else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) {
 		seq_puts(m, " heap");
-	} else {
-		pid_t tid = pid_of_stack(proc_priv, vma, is_pid);
-		if (tid != 0) {
-			/*
-			 * Thread stack in /proc/PID/task/TID/maps or
-			 * the main process stack.
-			 */
-			if (!is_pid || (vma->vm_start <= mm->start_stack &&
-			    vma->vm_end >= mm->start_stack))
+	} else if (is_stack(proc_priv, vma, is_pid)) {
 		seq_puts(m, " stack");
-			else
-				seq_printf(m, " stack:%d", tid);
-		}
 	}
 
 	if (is_vm_hugetlb_page(vma))

fs/proc/task_nommu.c

@@ -123,23 +123,26 @@ unsigned long task_statm(struct mm_struct *mm,
 	return size;
 }
 
-static pid_t pid_of_stack(struct proc_maps_private *priv,
-				struct vm_area_struct *vma, bool is_pid)
+static int is_stack(struct proc_maps_private *priv,
+		    struct vm_area_struct *vma, int is_pid)
 {
+	struct mm_struct *mm = vma->vm_mm;
+	int stack = 0;
+
+	if (is_pid) {
+		stack = vma->vm_start <= mm->start_stack &&
+			vma->vm_end >= mm->start_stack;
+	} else {
 		struct inode *inode = priv->inode;
 		struct task_struct *task;
-	pid_t ret = 0;
 
 		rcu_read_lock();
 		task = pid_task(proc_pid(inode), PIDTYPE_PID);
-	if (task) {
-		task = task_of_stack(task, vma, is_pid);
 		if (task)
-			ret = task_pid_nr_ns(task, inode->i_sb->s_fs_info);
-	}
+			stack = vma_is_stack_for_task(vma, task);
 		rcu_read_unlock();
-
-	return ret;
+	}
+	return stack;
 }
 
 /*
@@ -181,21 +184,9 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma,
 	if (file) {
 		seq_pad(m, ' ');
 		seq_file_path(m, file, "");
-	} else if (mm) {
-		pid_t tid = pid_of_stack(priv, vma, is_pid);
-
-		if (tid != 0) {
+	} else if (mm && is_stack(priv, vma, is_pid)) {
 		seq_pad(m, ' ');
-			/*
-			 * Thread stack in /proc/PID/task/TID/maps or
-			 * the main process stack.
-			 */
-			if (!is_pid || (vma->vm_start <= mm->start_stack &&
-			    vma->vm_end >= mm->start_stack))
 		seq_printf(m, "[stack]");
-			else
-				seq_printf(m, "[stack:%d]", tid);
-		}
 	}
 
 	seq_putc(m, '\n');

include/linux/memcontrol.h

@@ -51,7 +51,7 @@ enum mem_cgroup_stat_index {
 	MEM_CGROUP_STAT_SWAP,		/* # of pages, swapped out */
 	MEM_CGROUP_STAT_NSTATS,
 	/* default hierarchy stats */
-	MEMCG_SOCK,
+	MEMCG_SOCK = MEM_CGROUP_STAT_NSTATS,
 	MEMCG_NR_STAT,
 };
 

include/linux/mm.h

@@ -201,11 +201,13 @@ extern unsigned int kobjsize(const void *objp);
 #endif
 
 #ifdef CONFIG_STACK_GROWSUP
-#define VM_STACK_FLAGS	(VM_GROWSUP | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT)
+#define VM_STACK	VM_GROWSUP
 #else
-#define VM_STACK_FLAGS	(VM_GROWSDOWN | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT)
+#define VM_STACK	VM_GROWSDOWN
 #endif
 
+#define VM_STACK_FLAGS	(VM_STACK | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT)
+
 /*
  * Special vmas that are non-mergable, non-mlock()able.
  * Note: mm/huge_memory.c VM_NO_THP depends on this definition.
@@ -1341,8 +1343,7 @@ static inline int stack_guard_page_end(struct vm_area_struct *vma,
 		!vma_growsup(vma->vm_next, addr);
 }
 
-extern struct task_struct *task_of_stack(struct task_struct *task,
-				struct vm_area_struct *vma, bool in_group);
+int vma_is_stack_for_task(struct vm_area_struct *vma, struct task_struct *t);
 
 extern unsigned long move_page_tables(struct vm_area_struct *vma,
 		unsigned long old_addr, struct vm_area_struct *new_vma,

include/linux/mm_types.h

@@ -424,9 +424,9 @@ struct mm_struct {
 	unsigned long total_vm;		/* Total pages mapped */
 	unsigned long locked_vm;	/* Pages that have PG_mlocked set */
 	unsigned long pinned_vm;	/* Refcount permanently increased */
-	unsigned long data_vm;		/* VM_WRITE & ~VM_SHARED/GROWSDOWN */
-	unsigned long exec_vm;		/* VM_EXEC & ~VM_WRITE */
-	unsigned long stack_vm;		/* VM_GROWSUP/DOWN */
+	unsigned long data_vm;		/* VM_WRITE & ~VM_SHARED & ~VM_STACK */
+	unsigned long exec_vm;		/* VM_EXEC & ~VM_WRITE & ~VM_STACK */
+	unsigned long stack_vm;		/* VM_STACK */
 	unsigned long def_flags;
 	unsigned long start_code, end_code, start_data, end_data;
 	unsigned long start_brk, brk, start_stack;

include/linux/mmzone.h

@@ -682,6 +682,12 @@ typedef struct pglist_data {
 	 */
 	unsigned long first_deferred_pfn;
 #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;
+#endif
 } pg_data_t;
 
 #define node_present_pages(nid)	(NODE_DATA(nid)->node_present_pages)

include/linux/radix-tree.h

@@ -378,6 +378,22 @@ radix_tree_iter_init(struct radix_tree_iter *iter, unsigned long start)
 void **radix_tree_next_chunk(struct radix_tree_root *root,
 			     struct radix_tree_iter *iter, unsigned flags);
 
+/**
+ * radix_tree_iter_retry - retry this chunk of the iteration
+ * @iter:	iterator state
+ *
+ * If we iterate over a tree protected only by the RCU lock, a race
+ * against deletion or creation may result in seeing a slot for which
+ * radix_tree_deref_retry() returns true.  If so, call this function
+ * and continue the iteration.
+ */
+static inline __must_check
+void **radix_tree_iter_retry(struct radix_tree_iter *iter)
+{
+	iter->next_index = iter->index;
+	return NULL;
+}
+
 /**
  * radix_tree_chunk_size - get current chunk size
  *

lib/radix-tree.c

@@ -1019,9 +1019,13 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results,
 		return 0;
 
 	radix_tree_for_each_slot(slot, root, &iter, first_index) {
-		results[ret] = indirect_to_ptr(rcu_dereference_raw(*slot));
+		results[ret] = rcu_dereference_raw(*slot);
 		if (!results[ret])
 			continue;
+		if (radix_tree_is_indirect_ptr(results[ret])) {
+			slot = radix_tree_iter_retry(&iter);
+			continue;
+		}
 		if (++ret == max_items)
 			break;
 	}
@@ -1098,9 +1102,13 @@ radix_tree_gang_lookup_tag(struct radix_tree_root *root, void **results,
 		return 0;
 
 	radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) {
-		results[ret] = indirect_to_ptr(rcu_dereference_raw(*slot));
+		results[ret] = rcu_dereference_raw(*slot);
 		if (!results[ret])
 			continue;
+		if (radix_tree_is_indirect_ptr(results[ret])) {
+			slot = radix_tree_iter_retry(&iter);
+			continue;
+		}
 		if (++ret == max_items)
 			break;
 	}

lib/test-string_helpers.c

@@ -327,36 +327,67 @@ static __init void test_string_escape(const char *name,
 }
 
 #define string_get_size_maxbuf 16
-#define test_string_get_size_one(size, blk_size, units, exp_result)            \
+#define test_string_get_size_one(size, blk_size, exp_result10, exp_result2)    \
 	do {                                                                   \
-		BUILD_BUG_ON(sizeof(exp_result) >= string_get_size_maxbuf);    \
-		__test_string_get_size((size), (blk_size), (units),            \
-				       (exp_result));                          \
+		BUILD_BUG_ON(sizeof(exp_result10) >= string_get_size_maxbuf);  \
+		BUILD_BUG_ON(sizeof(exp_result2) >= string_get_size_maxbuf);   \
+		__test_string_get_size((size), (blk_size), (exp_result10),     \
+				       (exp_result2));                         \
 	} while (0)
 
 
-static __init void __test_string_get_size(const u64 size, const u64 blk_size,
-					  const enum string_size_units units,
-					  const char *exp_result)
+static __init void test_string_get_size_check(const char *units,
+					      const char *exp,
+					      char *res,
+					      const u64 size,
+					      const u64 blk_size)
 {
-	char buf[string_get_size_maxbuf];
-
-	string_get_size(size, blk_size, units, buf, sizeof(buf));
-	if (!memcmp(buf, exp_result, strlen(exp_result) + 1))
+	if (!memcmp(res, exp, strlen(exp) + 1))
 		return;
 
-	buf[sizeof(buf) - 1] = '\0';
-	pr_warn("Test 'test_string_get_size_one' failed!\n");
-	pr_warn("string_get_size(size = %llu, blk_size = %llu, units = %d\n",
+	res[string_get_size_maxbuf - 1] = '\0';
+
+	pr_warn("Test 'test_string_get_size' failed!\n");
+	pr_warn("string_get_size(size = %llu, blk_size = %llu, units = %s)\n",
 		size, blk_size, units);
-	pr_warn("expected: '%s', got '%s'\n", exp_result, buf);
+	pr_warn("expected: '%s', got '%s'\n", exp, res);
+}
+
+static __init void __test_string_get_size(const u64 size, const u64 blk_size,
+					  const char *exp_result10,
+					  const char *exp_result2)
+{
+	char buf10[string_get_size_maxbuf];
+	char buf2[string_get_size_maxbuf];
+
+	string_get_size(size, blk_size, STRING_UNITS_10, buf10, sizeof(buf10));
+	string_get_size(size, blk_size, STRING_UNITS_2, buf2, sizeof(buf2));
+
+	test_string_get_size_check("STRING_UNITS_10", exp_result10, buf10,
+				   size, blk_size);
+
+	test_string_get_size_check("STRING_UNITS_2", exp_result2, buf2,
+				   size, blk_size);
 }
 
 static __init void test_string_get_size(void)
 {
-	test_string_get_size_one(16384, 512, STRING_UNITS_2, "8.00 MiB");
-	test_string_get_size_one(8192, 4096, STRING_UNITS_10, "32.7 MB");
-	test_string_get_size_one(1, 512, STRING_UNITS_10, "512 B");
+	/* small values */
+	test_string_get_size_one(0, 512, "0 B", "0 B");
+	test_string_get_size_one(1, 512, "512 B", "512 B");
+	test_string_get_size_one(1100, 1, "1.10 kB", "1.07 KiB");
+
+	/* normal values */
+	test_string_get_size_one(16384, 512, "8.39 MB", "8.00 MiB");
+	test_string_get_size_one(500118192, 512, "256 GB", "238 GiB");
+	test_string_get_size_one(8192, 4096, "33.6 MB", "32.0 MiB");
+
+	/* weird block sizes */
+	test_string_get_size_one(3000, 1900, "5.70 MB", "5.44 MiB");
+
+	/* huge values */
+	test_string_get_size_one(U64_MAX, 4096, "75.6 ZB", "64.0 ZiB");
+	test_string_get_size_one(4096, U64_MAX, "75.6 ZB", "64.0 ZiB");
 }
 
 static int __init test_string_helpers_init(void)

mm/huge_memory.c

@@ -138,9 +138,6 @@ static struct khugepaged_scan khugepaged_scan = {
 	.mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head),
 };
 
-static DEFINE_SPINLOCK(split_queue_lock);
-static LIST_HEAD(split_queue);
-static unsigned long split_queue_len;
 static struct shrinker deferred_split_shrinker;
 
 static void set_recommended_min_free_kbytes(void)
@@ -861,6 +858,7 @@ static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm,
 		return false;
 	entry = mk_pmd(zero_page, vma->vm_page_prot);
 	entry = pmd_mkhuge(entry);
+	if (pgtable)
 		pgtable_trans_huge_deposit(mm, pmd, pgtable);
 	set_pmd_at(mm, haddr, pmd, entry);
 	atomic_long_inc(&mm->nr_ptes);
@@ -1039,13 +1037,15 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	spinlock_t *dst_ptl, *src_ptl;
 	struct page *src_page;
 	pmd_t pmd;
-	pgtable_t pgtable;
+	pgtable_t pgtable = NULL;
 	int ret;
 
+	if (!vma_is_dax(vma)) {
 		ret = -ENOMEM;
 		pgtable = pte_alloc_one(dst_mm, addr);
 		if (unlikely(!pgtable))
 			goto out;
+	}
 
 	dst_ptl = pmd_lock(dst_mm, dst_pmd);
 	src_ptl = pmd_lockptr(src_mm, src_pmd);
@@ -1076,7 +1076,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		goto out_unlock;
 	}
 
-	if (pmd_trans_huge(pmd)) {
+	if (!vma_is_dax(vma)) {
 		/* thp accounting separate from pmd_devmap accounting */
 		src_page = pmd_page(pmd);
 		VM_BUG_ON_PAGE(!PageHead(src_page), src_page);
@@ -3358,6 +3358,7 @@ int total_mapcount(struct page *page)
 int split_huge_page_to_list(struct page *page, struct list_head *list)
 {
 	struct page *head = compound_head(page);
+	struct pglist_data *pgdata = NODE_DATA(page_to_nid(head));
 	struct anon_vma *anon_vma;
 	int count, mapcount, ret;
 	bool mlocked;
@@ -3401,19 +3402,19 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 		lru_add_drain();
 
 	/* Prevent deferred_split_scan() touching ->_count */
-	spin_lock_irqsave(&split_queue_lock, flags);
+	spin_lock_irqsave(&pgdata->split_queue_lock, flags);
 	count = page_count(head);
 	mapcount = total_mapcount(head);
 	if (!mapcount && count == 1) {
 		if (!list_empty(page_deferred_list(head))) {
-			split_queue_len--;
+			pgdata->split_queue_len--;
 			list_del(page_deferred_list(head));
 		}
-		spin_unlock_irqrestore(&split_queue_lock, flags);
+		spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
 		__split_huge_page(page, list);
 		ret = 0;
 	} else if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) {
-		spin_unlock_irqrestore(&split_queue_lock, flags);
+		spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
 		pr_alert("total_mapcount: %u, page_count(): %u\n",
 				mapcount, count);
 		if (PageTail(page))
@@ -3421,7 +3422,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 		dump_page(page, "total_mapcount(head) > 0");
 		BUG();
 	} else {
-		spin_unlock_irqrestore(&split_queue_lock, flags);
+		spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
 		unfreeze_page(anon_vma, head);
 		ret = -EBUSY;
 	}
@@ -3436,64 +3437,65 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 
 void free_transhuge_page(struct page *page)
 {
+	struct pglist_data *pgdata = NODE_DATA(page_to_nid(page));
 	unsigned long flags;
 
-	spin_lock_irqsave(&split_queue_lock, flags);
+	spin_lock_irqsave(&pgdata->split_queue_lock, flags);
 	if (!list_empty(page_deferred_list(page))) {
-		split_queue_len--;
+		pgdata->split_queue_len--;
 		list_del(page_deferred_list(page));
 	}
-	spin_unlock_irqrestore(&split_queue_lock, flags);
+	spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
 	free_compound_page(page);
 }
 
 void deferred_split_huge_page(struct page *page)
 {
+	struct pglist_data *pgdata = NODE_DATA(page_to_nid(page));
 	unsigned long flags;
 
 	VM_BUG_ON_PAGE(!PageTransHuge(page), page);
 
-	spin_lock_irqsave(&split_queue_lock, flags);
+	spin_lock_irqsave(&pgdata->split_queue_lock, flags);
 	if (list_empty(page_deferred_list(page))) {
-		list_add_tail(page_deferred_list(page), &split_queue);
-		split_queue_len++;
+		list_add_tail(page_deferred_list(page), &pgdata->split_queue);
+		pgdata->split_queue_len++;
 	}
-	spin_unlock_irqrestore(&split_queue_lock, flags);
+	spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
 }
 
 static unsigned long deferred_split_count(struct shrinker *shrink,
 		struct shrink_control *sc)
 {
-	/*
-	 * Split a page from split_queue will free up at least one page,
-	 * at most HPAGE_PMD_NR - 1. We don't track exact number.
-	 * Let's use HPAGE_PMD_NR / 2 as ballpark.
-	 */
-	return ACCESS_ONCE(split_queue_len) * HPAGE_PMD_NR / 2;
+	struct pglist_data *pgdata = NODE_DATA(sc->nid);
+	return ACCESS_ONCE(pgdata->split_queue_len);
 }
 
 static unsigned long deferred_split_scan(struct shrinker *shrink,
 		struct shrink_control *sc)
 {
+	struct pglist_data *pgdata = NODE_DATA(sc->nid);
 	unsigned long flags;
 	LIST_HEAD(list), *pos, *next;
 	struct page *page;
 	int split = 0;
 
-	spin_lock_irqsave(&split_queue_lock, flags);
-	list_splice_init(&split_queue, &list);
-
+	spin_lock_irqsave(&pgdata->split_queue_lock, flags);
 	/* Take pin on all head pages to avoid freeing them under us */
 	list_for_each_safe(pos, next, &list) {
 		page = list_entry((void *)pos, struct page, mapping);
 		page = compound_head(page);
-		/* race with put_compound_page() */
-		if (!get_page_unless_zero(page)) {
+		if (get_page_unless_zero(page)) {
+			list_move(page_deferred_list(page), &list);
+		} else {
+			/* We lost race with put_compound_page() */
 			list_del_init(page_deferred_list(page));
-			split_queue_len--;
+			pgdata->split_queue_len--;
 		}
+		if (!--sc->nr_to_scan)
+			break;
 	}
-	spin_unlock_irqrestore(&split_queue_lock, flags);
+	spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
 
 	list_for_each_safe(pos, next, &list) {
 		page = list_entry((void *)pos, struct page, mapping);
@@ -3505,17 +3507,24 @@ static unsigned long deferred_split_scan(struct shrinker *shrink,
 		put_page(page);
 	}
 
-	spin_lock_irqsave(&split_queue_lock, flags);
-	list_splice_tail(&list, &split_queue);
-	spin_unlock_irqrestore(&split_queue_lock, flags);
+	spin_lock_irqsave(&pgdata->split_queue_lock, flags);
+	list_splice_tail(&list, &pgdata->split_queue);
+	spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
 
-	return split * HPAGE_PMD_NR / 2;
+	/*
+	 * Stop shrinker if we didn't split any page, but the queue is empty.
+	 * This can happen if pages were freed under us.
+	 */
+	if (!split && list_empty(&pgdata->split_queue))
+		return SHRINK_STOP;
+	return split;
 }
 
 static struct shrinker deferred_split_shrinker = {
 	.count_objects = deferred_split_count,
 	.scan_objects = deferred_split_scan,
 	.seeks = DEFAULT_SEEKS,
+	.flags = SHRINKER_NUMA_AWARE,
 };
 
 #ifdef CONFIG_DEBUG_FS

mm/internal.h

@@ -216,6 +216,37 @@ static inline bool is_cow_mapping(vm_flags_t flags)
 	return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
 }
 
+/*
+ * These three helpers classifies VMAs for virtual memory accounting.
+ */
+
+/*
+ * Executable code area - executable, not writable, not stack
+ */
+static inline bool is_exec_mapping(vm_flags_t flags)
+{
+	return (flags & (VM_EXEC | VM_WRITE | VM_STACK)) == VM_EXEC;
+}
+
+/*
+ * Stack area - atomatically grows in one direction
+ *
+ * VM_GROWSUP / VM_GROWSDOWN VMAs are always private anonymous:
+ * do_mmap() forbids all other combinations.
+ */
+static inline bool is_stack_mapping(vm_flags_t flags)
+{
+	return (flags & VM_STACK) == VM_STACK;
+}
+
+/*
+ * Data area - private, writable, not stack
+ */
+static inline bool is_data_mapping(vm_flags_t flags)
+{
+	return (flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE;
+}
+
 /* mm/util.c */
 void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
 		struct vm_area_struct *prev, struct rb_node *rb_parent);

mm/mmap.c

@@ -42,6 +42,7 @@
 #include <linux/memory.h>
 #include <linux/printk.h>
 #include <linux/userfaultfd_k.h>
+#include <linux/moduleparam.h>
 
 #include <asm/uaccess.h>
 #include <asm/cacheflush.h>
@@ -69,6 +70,8 @@ const int mmap_rnd_compat_bits_max = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MAX;
 int mmap_rnd_compat_bits __read_mostly = CONFIG_ARCH_MMAP_RND_COMPAT_BITS;
 #endif
 
+static bool ignore_rlimit_data = true;
+core_param(ignore_rlimit_data, ignore_rlimit_data, bool, 0644);
 
 static void unmap_region(struct mm_struct *mm,
 		struct vm_area_struct *vma, struct vm_area_struct *prev,
@@ -2982,9 +2985,17 @@ bool may_expand_vm(struct mm_struct *mm, vm_flags_t flags, unsigned long npages)
 	if (mm->total_vm + npages > rlimit(RLIMIT_AS) >> PAGE_SHIFT)
 		return false;
 
-	if ((flags & (VM_WRITE | VM_SHARED | (VM_STACK_FLAGS &
-				(VM_GROWSUP | VM_GROWSDOWN)))) == VM_WRITE)
-		return mm->data_vm + npages <= rlimit(RLIMIT_DATA);
+	if (is_data_mapping(flags) &&
+	    mm->data_vm + npages > rlimit(RLIMIT_DATA) >> PAGE_SHIFT) {
+		if (ignore_rlimit_data)
+			pr_warn_once("%s (%d): VmData %lu exceed data ulimit "
+				     "%lu. Will be forbidden soon.\n",
+				     current->comm, current->pid,
+				     (mm->data_vm + npages) << PAGE_SHIFT,
+				     rlimit(RLIMIT_DATA));
+		else
+			return false;
+	}
 
 	return true;
 }
@@ -2993,11 +3004,11 @@ void vm_stat_account(struct mm_struct *mm, vm_flags_t flags, long npages)
 {
 	mm->total_vm += npages;
 
-	if ((flags & (VM_EXEC | VM_WRITE)) == VM_EXEC)
+	if (is_exec_mapping(flags))
 		mm->exec_vm += npages;
-	else if (flags & (VM_STACK_FLAGS & (VM_GROWSUP | VM_GROWSDOWN)))
+	else if (is_stack_mapping(flags))
 		mm->stack_vm += npages;
-	else if ((flags & (VM_WRITE | VM_SHARED)) == VM_WRITE)
+	else if (is_data_mapping(flags))
 		mm->data_vm += npages;
 }
 

mm/page_alloc.c

@@ -5209,6 +5209,11 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 	spin_lock_init(&pgdat->numabalancing_migrate_lock);
 	pgdat->numabalancing_migrate_nr_pages = 0;
 	pgdat->numabalancing_migrate_next_window = jiffies;
+#endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	spin_lock_init(&pgdat->split_queue_lock);
+	INIT_LIST_HEAD(&pgdat->split_queue);
+	pgdat->split_queue_len = 0;
 #endif
 	init_waitqueue_head(&pgdat->kswapd_wait);
 	init_waitqueue_head(&pgdat->pfmemalloc_wait);

mm/util.c

@@ -230,36 +230,11 @@ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
 }
 
 /* Check if the vma is being used as a stack by this task */
-static int vm_is_stack_for_task(struct task_struct *t,
-				struct vm_area_struct *vma)
+int vma_is_stack_for_task(struct vm_area_struct *vma, struct task_struct *t)
 {
 	return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t));
 }
 
-/*
- * Check if the vma is being used as a stack.
- * If is_group is non-zero, check in the entire thread group or else
- * just check in the current task. Returns the task_struct of the task
- * that the vma is stack for. Must be called under rcu_read_lock().
- */
-struct task_struct *task_of_stack(struct task_struct *task,
-				struct vm_area_struct *vma, bool in_group)
-{
-	if (vm_is_stack_for_task(task, vma))
-		return task;
-
-	if (in_group) {
-		struct task_struct *t;
-
-		for_each_thread(task, t) {
-			if (vm_is_stack_for_task(t, vma))
-				return t;
-		}
-	}
-
-	return NULL;
-}
-
 #if defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT)
 void arch_pick_mmap_layout(struct mm_struct *mm)
 {

mm/vmpressure.c

@@ -248,9 +248,8 @@ void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree,
 
 	if (tree) {
 		spin_lock(&vmpr->sr_lock);
-		vmpr->tree_scanned += scanned;
+		scanned = vmpr->tree_scanned += scanned;
 		vmpr->tree_reclaimed += reclaimed;
-		scanned = vmpr->scanned;
 		spin_unlock(&vmpr->sr_lock);
 
 		if (scanned < vmpressure_win)