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 <[email protected]>:
  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
@@ -388,18 +388,15 @@ 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
 
  or if empty, the mapping is anonymous.
 
 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 <[email protected]>
+M:	Seth Jennings <[email protected]>
 L:	[email protected]
 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 <[email protected]>
+M:	Seth Jennings <[email protected]>
 L:	[email protected]
 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)
 {
-	struct inode *inode = priv->inode;
-	struct task_struct *task;
-	pid_t ret = 0;
+	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;
 
-	rcu_read_lock();
-	task = pid_task(proc_pid(inode), PIDTYPE_PID);
-	if (task) {
-		task = task_of_stack(task, vma, is_pid);
+		rcu_read_lock();
+		task = pid_task(proc_pid(inode), PIDTYPE_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();
 	}
-	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)) {
-				name = "[stack]";
-			} else {
-				/* Thread stack in /proc/PID/maps */
-				seq_pad(m, ' ');
-				seq_printf(m, "[stack:%d]", tid);
-			}
-		}
+		if (is_stack(priv, vma, is_pid))
+			name = "[stack]";
 	}
 
 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))
-				seq_puts(m, " stack");
-			else
-				seq_printf(m, " stack:%d", tid);
-		}
+	} else if (is_stack(proc_priv, vma, is_pid)) {
+		seq_puts(m, " stack");
 	}
 
 	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 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);
+	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;
+
+		rcu_read_lock();
+		task = pid_task(proc_pid(inode), PIDTYPE_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();
 	}
-	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) {
-			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);
-		}
+	} else if (mm && is_stack(priv, vma, is_pid)) {
+		seq_pad(m, ' ');
+		seq_printf(m, "[stack]");
 	}
 
 	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)