Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:
 "191 patches.

  Subsystems affected by this patch series: kthread, ia64, scripts,
  ntfs, squashfs, ocfs2, kernel/watchdog, and mm (gup, pagealloc, slab,
  slub, kmemleak, dax, debug, pagecache, gup, swap, memcg, pagemap,
  mprotect, bootmem, dma, tracing, vmalloc, kasan, initialization,
  pagealloc, and memory-failure)"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (191 commits)
  mm,hwpoison: make get_hwpoison_page() call get_any_page()
  mm,hwpoison: send SIGBUS with error virutal address
  mm/page_alloc: split pcp->high across all online CPUs for cpuless nodes
  mm/page_alloc: allow high-order pages to be stored on the per-cpu lists
  mm: replace CONFIG_FLAT_NODE_MEM_MAP with CONFIG_FLATMEM
  mm: replace CONFIG_NEED_MULTIPLE_NODES with CONFIG_NUMA
  docs: remove description of DISCONTIGMEM
  arch, mm: remove stale mentions of DISCONIGMEM
  mm: remove CONFIG_DISCONTIGMEM
  m68k: remove support for DISCONTIGMEM
  arc: remove support for DISCONTIGMEM
  arc: update comment about HIGHMEM implementation
  alpha: remove DISCONTIGMEM and NUMA
  mm/page_alloc: move free_the_page
  mm/page_alloc: fix counting of managed_pages
  mm/page_alloc: improve memmap_pages dbg msg
  mm: drop SECTION_SHIFT in code comments
  mm/page_alloc: introduce vm.percpu_pagelist_high_fraction
  mm/page_alloc: limit the number of pages on PCP lists when reclaim is active
  mm/page_alloc: scale the number of pages that are batch freed
  ...

1 files changed, 252 insertions, 166 deletions

diff --git a/mm/slub.c b/mm/slub.c
index 61bd40e3eb9a..3bc8b940c933 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -36,7 +36,9 @@
 #include <linux/prefetch.h>
 #include <linux/memcontrol.h>
 #include <linux/random.h>
+#include <kunit/test.h>
 
+#include <linux/debugfs.h>
 #include <trace/events/kmem.h>
 
 #include "internal.h"
@@ -117,12 +119,26 @@
  */
 
 #ifdef CONFIG_SLUB_DEBUG
+
 #ifdef CONFIG_SLUB_DEBUG_ON
 DEFINE_STATIC_KEY_TRUE(slub_debug_enabled);
 #else
 DEFINE_STATIC_KEY_FALSE(slub_debug_enabled);
 #endif
-#endif
+
+static inline bool __slub_debug_enabled(void)
+{
+	return static_branch_unlikely(&slub_debug_enabled);
+}
+
+#else		/* CONFIG_SLUB_DEBUG */
+
+static inline bool __slub_debug_enabled(void)
+{
+	return false;
+}
+
+#endif		/* CONFIG_SLUB_DEBUG */
 
 static inline bool kmem_cache_debug(struct kmem_cache *s)
 {
@@ -154,9 +170,6 @@ static inline bool kmem_cache_has_cpu_partial(struct kmem_cache *s)
  * - Variable sizing of the per node arrays
  */
 
-/* Enable to test recovery from slab corruption on boot */
-#undef SLUB_RESILIENCY_TEST
-
 /* Enable to log cmpxchg failures */
 #undef SLUB_DEBUG_CMPXCHG
 
@@ -226,6 +239,12 @@ static inline int sysfs_slab_alias(struct kmem_cache *s, const char *p)
 							{ return 0; }
 #endif
 
+#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_SLUB_DEBUG)
+static void debugfs_slab_add(struct kmem_cache *);
+#else
+static inline void debugfs_slab_add(struct kmem_cache *s) { }
+#endif
+
 static inline void stat(const struct kmem_cache *s, enum stat_item si)
 {
 #ifdef CONFIG_SLUB_STATS
@@ -449,6 +468,26 @@ static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page,
 static unsigned long object_map[BITS_TO_LONGS(MAX_OBJS_PER_PAGE)];
 static DEFINE_SPINLOCK(object_map_lock);
 
+#if IS_ENABLED(CONFIG_KUNIT)
+static bool slab_add_kunit_errors(void)
+{
+	struct kunit_resource *resource;
+
+	if (likely(!current->kunit_test))
+		return false;
+
+	resource = kunit_find_named_resource(current->kunit_test, "slab_errors");
+	if (!resource)
+		return false;
+
+	(*(int *)resource->data)++;
+	kunit_put_resource(resource);
+	return true;
+}
+#else
+static inline bool slab_add_kunit_errors(void) { return false; }
+#endif
+
 /*
  * Determine a map of object in use on a page.
  *
@@ -669,16 +708,18 @@ static void slab_bug(struct kmem_cache *s, char *fmt, ...)
 	pr_err("=============================================================================\n");
 	pr_err("BUG %s (%s): %pV\n", s->name, print_tainted(), &vaf);
 	pr_err("-----------------------------------------------------------------------------\n\n");
-
-	add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
 	va_end(args);
 }
 
+__printf(2, 3)
 static void slab_fix(struct kmem_cache *s, char *fmt, ...)
 {
 	struct va_format vaf;
 	va_list args;
 
+	if (slab_add_kunit_errors())
+		return;
+
 	va_start(args, fmt);
 	vaf.fmt = fmt;
 	vaf.va = &args;
@@ -742,8 +783,12 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p)
 void object_err(struct kmem_cache *s, struct page *page,
 			u8 *object, char *reason)
 {
+	if (slab_add_kunit_errors())
+		return;
+
 	slab_bug(s, "%s", reason);
 	print_trailer(s, page, object);
+	add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
 }
 
 static __printf(3, 4) void slab_err(struct kmem_cache *s, struct page *page,
@@ -752,12 +797,16 @@ static __printf(3, 4) void slab_err(struct kmem_cache *s, struct page *page,
 	va_list args;
 	char buf[100];
 
+	if (slab_add_kunit_errors())
+		return;
+
 	va_start(args, fmt);
 	vsnprintf(buf, sizeof(buf), fmt, args);
 	va_end(args);
 	slab_bug(s, "%s", buf);
 	print_page_info(page);
 	dump_stack();
+	add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
 }
 
 static void init_object(struct kmem_cache *s, void *object, u8 val)
@@ -779,7 +828,7 @@ static void init_object(struct kmem_cache *s, void *object, u8 val)
 static void restore_bytes(struct kmem_cache *s, char *message, u8 data,
 						void *from, void *to)
 {
-	slab_fix(s, "Restoring 0x%p-0x%p=0x%x\n", from, to - 1, data);
+	slab_fix(s, "Restoring %s 0x%p-0x%p=0x%x", message, from, to - 1, data);
 	memset(from, data, to - from);
 }
 
@@ -801,12 +850,17 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page,
 	while (end > fault && end[-1] == value)
 		end--;
 
+	if (slab_add_kunit_errors())
+		goto skip_bug_print;
+
 	slab_bug(s, "%s overwritten", what);
 	pr_err("0x%p-0x%p @offset=%tu. First byte 0x%x instead of 0x%x\n",
 					fault, end - 1, fault - addr,
 					fault[0], value);
 	print_trailer(s, page, object);
+	add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
 
+skip_bug_print:
 	restore_bytes(s, what, value, fault, end);
 	return 0;
 }
@@ -1028,13 +1082,13 @@ static int on_freelist(struct kmem_cache *s, struct page *page, void *search)
 		slab_err(s, page, "Wrong number of objects. Found %d but should be %d",
 			 page->objects, max_objects);
 		page->objects = max_objects;
-		slab_fix(s, "Number of objects adjusted.");
+		slab_fix(s, "Number of objects adjusted");
 	}
 	if (page->inuse != page->objects - nr) {
 		slab_err(s, page, "Wrong object count. Counter is %d but counted were %d",
 			 page->inuse, page->objects - nr);
 		page->inuse = page->objects - nr;
-		slab_fix(s, "Object count adjusted.");
+		slab_fix(s, "Object count adjusted");
 	}
 	return search == NULL;
 }
@@ -1398,6 +1452,8 @@ static int __init setup_slub_debug(char *str)
 out:
 	if (slub_debug != 0 || slub_debug_string)
 		static_branch_enable(&slub_debug_enabled);
+	else
+		static_branch_disable(&slub_debug_enabled);
 	if ((static_branch_unlikely(&init_on_alloc) ||
 	     static_branch_unlikely(&init_on_free)) &&
 	    (slub_debug & SLAB_POISON))
@@ -4453,6 +4509,10 @@ void __init kmem_cache_init(void)
 	if (debug_guardpage_minorder())
 		slub_max_order = 0;
 
+	/* Print slub debugging pointers without hashing */
+	if (__slub_debug_enabled())
+		no_hash_pointers_enable(NULL);
+
 	kmem_cache_node = &boot_kmem_cache_node;
 	kmem_cache = &boot_kmem_cache;
 
@@ -4541,6 +4601,9 @@ int __kmem_cache_create(struct kmem_cache *s, slab_flags_t flags)
 	if (err)
 		__kmem_cache_release(s);
 
+	if (s->flags & SLAB_STORE_USER)
+		debugfs_slab_add(s);
+
 	return err;
 }
 
@@ -4649,9 +4712,11 @@ static int validate_slab_node(struct kmem_cache *s,
 		validate_slab(s, page);
 		count++;
 	}
-	if (count != n->nr_partial)
+	if (count != n->nr_partial) {
 		pr_err("SLUB %s: %ld partial slabs counted but counter=%ld\n",
 		       s->name, count, n->nr_partial);
+		slab_add_kunit_errors();
+	}
 
 	if (!(s->flags & SLAB_STORE_USER))
 		goto out;
@@ -4660,16 +4725,18 @@ static int validate_slab_node(struct kmem_cache *s,
 		validate_slab(s, page);
 		count++;
 	}
-	if (count != atomic_long_read(&n->nr_slabs))
+	if (count != atomic_long_read(&n->nr_slabs)) {
 		pr_err("SLUB: %s %ld slabs counted but counter=%ld\n",
 		       s->name, count, atomic_long_read(&n->nr_slabs));
+		slab_add_kunit_errors();
+	}
 
 out:
 	spin_unlock_irqrestore(&n->list_lock, flags);
 	return count;
 }
 
-static long validate_slab_cache(struct kmem_cache *s)
+long validate_slab_cache(struct kmem_cache *s)
 {
 	int node;
 	unsigned long count = 0;
@@ -4681,6 +4748,9 @@ static long validate_slab_cache(struct kmem_cache *s)
 
 	return count;
 }
+EXPORT_SYMBOL(validate_slab_cache);
+
+#ifdef CONFIG_DEBUG_FS
 /*
  * Generate lists of code addresses where slabcache objects are allocated
  * and freed.
@@ -4704,6 +4774,8 @@ struct loc_track {
 	struct location *loc;
 };
 
+static struct dentry *slab_debugfs_root;
+
 static void free_loc_track(struct loc_track *t)
 {
 	if (t->max)
@@ -4820,144 +4892,9 @@ static void process_slab(struct loc_track *t, struct kmem_cache *s,
 			add_location(t, s, get_track(s, p, alloc));
 	put_map(map);
 }
-
-static int list_locations(struct kmem_cache *s, char *buf,
-			  enum track_item alloc)
-{
-	int len = 0;
-	unsigned long i;
-	struct loc_track t = { 0, 0, NULL };
-	int node;
-	struct kmem_cache_node *n;
-
-	if (!alloc_loc_track(&t, PAGE_SIZE / sizeof(struct location),
-			     GFP_KERNEL)) {
-		return sysfs_emit(buf, "Out of memory\n");
-	}
-	/* Push back cpu slabs */
-	flush_all(s);
-
-	for_each_kmem_cache_node(s, node, n) {
-		unsigned long flags;
-		struct page *page;
-
-		if (!atomic_long_read(&n->nr_slabs))
-			continue;
-
-		spin_lock_irqsave(&n->list_lock, flags);
-		list_for_each_entry(page, &n->partial, slab_list)
-			process_slab(&t, s, page, alloc);
-		list_for_each_entry(page, &n->full, slab_list)
-			process_slab(&t, s, page, alloc);
-		spin_unlock_irqrestore(&n->list_lock, flags);
-	}
-
-	for (i = 0; i < t.count; i++) {
-		struct location *l = &t.loc[i];
-
-		len += sysfs_emit_at(buf, len, "%7ld ", l->count);
-
-		if (l->addr)
-			len += sysfs_emit_at(buf, len, "%pS", (void *)l->addr);
-		else
-			len += sysfs_emit_at(buf, len, "<not-available>");
-
-		if (l->sum_time != l->min_time)
-			len += sysfs_emit_at(buf, len, " age=%ld/%ld/%ld",
-					     l->min_time,
-					     (long)div_u64(l->sum_time,
-							   l->count),
-					     l->max_time);
-		else
-			len += sysfs_emit_at(buf, len, " age=%ld", l->min_time);
-
-		if (l->min_pid != l->max_pid)
-			len += sysfs_emit_at(buf, len, " pid=%ld-%ld",
-					     l->min_pid, l->max_pid);
-		else
-			len += sysfs_emit_at(buf, len, " pid=%ld",
-					     l->min_pid);
-
-		if (num_online_cpus() > 1 &&
-		    !cpumask_empty(to_cpumask(l->cpus)))
-			len += sysfs_emit_at(buf, len, " cpus=%*pbl",
-					     cpumask_pr_args(to_cpumask(l->cpus)));
-
-		if (nr_online_nodes > 1 && !nodes_empty(l->nodes))
-			len += sysfs_emit_at(buf, len, " nodes=%*pbl",
-					     nodemask_pr_args(&l->nodes));
-
-		len += sysfs_emit_at(buf, len, "\n");
-	}
-
-	free_loc_track(&t);
-	if (!t.count)
-		len += sysfs_emit_at(buf, len, "No data\n");
-
-	return len;
-}
+#endif  /* CONFIG_DEBUG_FS   */
 #endif	/* CONFIG_SLUB_DEBUG */
 
-#ifdef SLUB_RESILIENCY_TEST
-static void __init resiliency_test(void)
-{
-	u8 *p;
-	int type = KMALLOC_NORMAL;
-
-	BUILD_BUG_ON(KMALLOC_MIN_SIZE > 16 || KMALLOC_SHIFT_HIGH < 10);
-
-	pr_err("SLUB resiliency testing\n");
-	pr_err("-----------------------\n");
-	pr_err("A. Corruption after allocation\n");
-
-	p = kzalloc(16, GFP_KERNEL);
-	p[16] = 0x12;
-	pr_err("\n1. kmalloc-16: Clobber Redzone/next pointer 0x12->0x%p\n\n",
-	       p + 16);
-
-	validate_slab_cache(kmalloc_caches[type][4]);
-
-	/* Hmmm... The next two are dangerous */
-	p = kzalloc(32, GFP_KERNEL);
-	p[32 + sizeof(void *)] = 0x34;
-	pr_err("\n2. kmalloc-32: Clobber next pointer/next slab 0x34 -> -0x%p\n",
-	       p);
-	pr_err("If allocated object is overwritten then not detectable\n\n");
-
-	validate_slab_cache(kmalloc_caches[type][5]);
-	p = kzalloc(64, GFP_KERNEL);
-	p += 64 + (get_cycles() & 0xff) * sizeof(void *);
-	*p = 0x56;
-	pr_err("\n3. kmalloc-64: corrupting random byte 0x56->0x%p\n",
-	       p);
-	pr_err("If allocated object is overwritten then not detectable\n\n");
-	validate_slab_cache(kmalloc_caches[type][6]);
-
-	pr_err("\nB. Corruption after free\n");
-	p = kzalloc(128, GFP_KERNEL);
-	kfree(p);
-	*p = 0x78;
-	pr_err("1. kmalloc-128: Clobber first word 0x78->0x%p\n\n", p);
-	validate_slab_cache(kmalloc_caches[type][7]);
-
-	p = kzalloc(256, GFP_KERNEL);
-	kfree(p);
-	p[50] = 0x9a;
-	pr_err("\n2. kmalloc-256: Clobber 50th byte 0x9a->0x%p\n\n", p);
-	validate_slab_cache(kmalloc_caches[type][8]);
-
-	p = kzalloc(512, GFP_KERNEL);
-	kfree(p);
-	p[512] = 0xab;
-	pr_err("\n3. kmalloc-512: Clobber redzone 0xab->0x%p\n\n", p);
-	validate_slab_cache(kmalloc_caches[type][9]);
-}
-#else
-#ifdef CONFIG_SYSFS
-static void resiliency_test(void) {};
-#endif
-#endif	/* SLUB_RESILIENCY_TEST */
-
 #ifdef CONFIG_SYSFS
 enum slab_stat_type {
 	SL_ALL,			/* All slabs */
@@ -5345,21 +5282,6 @@ static ssize_t validate_store(struct kmem_cache *s,
 }
 SLAB_ATTR(validate);
 
-static ssize_t alloc_calls_show(struct kmem_cache *s, char *buf)
-{
-	if (!(s->flags & SLAB_STORE_USER))
-		return -ENOSYS;
-	return list_locations(s, buf, TRACK_ALLOC);
-}
-SLAB_ATTR_RO(alloc_calls);
-
-static ssize_t free_calls_show(struct kmem_cache *s, char *buf)
-{
-	if (!(s->flags & SLAB_STORE_USER))
-		return -ENOSYS;
-	return list_locations(s, buf, TRACK_FREE);
-}
-SLAB_ATTR_RO(free_calls);
 #endif /* CONFIG_SLUB_DEBUG */
 
 #ifdef CONFIG_FAILSLAB
@@ -5523,8 +5445,6 @@ static struct attribute *slab_attrs[] = {
 	&poison_attr.attr,
 	&store_user_attr.attr,
 	&validate_attr.attr,
-	&alloc_calls_attr.attr,
-	&free_calls_attr.attr,
 #endif
 #ifdef CONFIG_ZONE_DMA
 	&cache_dma_attr.attr,
@@ -5806,13 +5726,179 @@ static int __init slab_sysfs_init(void)
 	}
 
 	mutex_unlock(&slab_mutex);
-	resiliency_test();
 	return 0;
 }
 
 __initcall(slab_sysfs_init);
 #endif /* CONFIG_SYSFS */
 
+#if defined(CONFIG_SLUB_DEBUG) && defined(CONFIG_DEBUG_FS)
+static int slab_debugfs_show(struct seq_file *seq, void *v)
+{
+
+	struct location *l;
+	unsigned int idx = *(unsigned int *)v;
+	struct loc_track *t = seq->private;
+
+	if (idx < t->count) {
+		l = &t->loc[idx];
+
+		seq_printf(seq, "%7ld ", l->count);
+
+		if (l->addr)
+			seq_printf(seq, "%pS", (void *)l->addr);
+		else
+			seq_puts(seq, "<not-available>");
+
+		if (l->sum_time != l->min_time) {
+			seq_printf(seq, " age=%ld/%llu/%ld",
+				l->min_time, div_u64(l->sum_time, l->count),
+				l->max_time);
+		} else
+			seq_printf(seq, " age=%ld", l->min_time);
+
+		if (l->min_pid != l->max_pid)
+			seq_printf(seq, " pid=%ld-%ld", l->min_pid, l->max_pid);
+		else
+			seq_printf(seq, " pid=%ld",
+				l->min_pid);
+
+		if (num_online_cpus() > 1 && !cpumask_empty(to_cpumask(l->cpus)))
+			seq_printf(seq, " cpus=%*pbl",
+				 cpumask_pr_args(to_cpumask(l->cpus)));
+
+		if (nr_online_nodes > 1 && !nodes_empty(l->nodes))
+			seq_printf(seq, " nodes=%*pbl",
+				 nodemask_pr_args(&l->nodes));
+
+		seq_puts(seq, "\n");
+	}
+
+	if (!idx && !t->count)
+		seq_puts(seq, "No data\n");
+
+	return 0;
+}
+
+static void slab_debugfs_stop(struct seq_file *seq, void *v)
+{
+}
+
+static void *slab_debugfs_next(struct seq_file *seq, void *v, loff_t *ppos)
+{
+	struct loc_track *t = seq->private;
+
+	v = ppos;
+	++*ppos;
+	if (*ppos <= t->count)
+		return v;
+
+	return NULL;
+}
+
+static void *slab_debugfs_start(struct seq_file *seq, loff_t *ppos)
+{
+	return ppos;
+}
+
+static const struct seq_operations slab_debugfs_sops = {
+	.start  = slab_debugfs_start,
+	.next   = slab_debugfs_next,
+	.stop   = slab_debugfs_stop,
+	.show   = slab_debugfs_show,
+};
+
+static int slab_debug_trace_open(struct inode *inode, struct file *filep)
+{
+
+	struct kmem_cache_node *n;
+	enum track_item alloc;
+	int node;
+	struct loc_track *t = __seq_open_private(filep, &slab_debugfs_sops,
+						sizeof(struct loc_track));
+	struct kmem_cache *s = file_inode(filep)->i_private;
+
+	if (strcmp(filep->f_path.dentry->d_name.name, "alloc_traces") == 0)
+		alloc = TRACK_ALLOC;
+	else
+		alloc = TRACK_FREE;
+
+	if (!alloc_loc_track(t, PAGE_SIZE / sizeof(struct location), GFP_KERNEL))
+		return -ENOMEM;
+
+	/* Push back cpu slabs */
+	flush_all(s);
+
+	for_each_kmem_cache_node(s, node, n) {
+		unsigned long flags;
+		struct page *page;
+
+		if (!atomic_long_read(&n->nr_slabs))
+			continue;
+
+		spin_lock_irqsave(&n->list_lock, flags);
+		list_for_each_entry(page, &n->partial, slab_list)
+			process_slab(t, s, page, alloc);
+		list_for_each_entry(page, &n->full, slab_list)
+			process_slab(t, s, page, alloc);
+		spin_unlock_irqrestore(&n->list_lock, flags);
+	}
+
+	return 0;
+}
+
+static int slab_debug_trace_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = file->private_data;
+	struct loc_track *t = seq->private;
+
+	free_loc_track(t);
+	return seq_release_private(inode, file);
+}
+
+static const struct file_operations slab_debugfs_fops = {
+	.open    = slab_debug_trace_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = slab_debug_trace_release,
+};
+
+static void debugfs_slab_add(struct kmem_cache *s)
+{
+	struct dentry *slab_cache_dir;
+
+	if (unlikely(!slab_debugfs_root))
+		return;
+
+	slab_cache_dir = debugfs_create_dir(s->name, slab_debugfs_root);
+
+	debugfs_create_file("alloc_traces", 0400,
+		slab_cache_dir, s, &slab_debugfs_fops);
+
+	debugfs_create_file("free_traces", 0400,
+		slab_cache_dir, s, &slab_debugfs_fops);
+}
+
+void debugfs_slab_release(struct kmem_cache *s)
+{
+	debugfs_remove_recursive(debugfs_lookup(s->name, slab_debugfs_root));
+}
+
+static int __init slab_debugfs_init(void)
+{
+	struct kmem_cache *s;
+
+	slab_debugfs_root = debugfs_create_dir("slab", NULL);
+
+	list_for_each_entry(s, &slab_caches, list)
+		if (s->flags & SLAB_STORE_USER)
+			debugfs_slab_add(s);
+
+	return 0;
+
+}
+__initcall(slab_debugfs_init);
+#endif
 /*
  * The /proc/slabinfo ABI
  */