Merge tag 'slab-for-5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/vbabka/slab

Pull slab updates from Vlastimil Babka:

 - Conversion of slub_debug stack traces to stackdepot, allowing more
   useful debugfs-based inspection for e.g. memory leak debugging.
   Allocation and free debugfs info now includes full traces and is
   sorted by the unique trace frequency.

   The stackdepot conversion was already attempted last year but
   reverted by ae14c63a9f20. The memory overhead (while not actually
   enabled on boot) has been meanwhile solved by making the large
   stackdepot allocation dynamic. The xfstest issues haven't been
   reproduced on current kernel locally nor in -next, so the slab cache
   layout changes that originally made that bug manifest were probably
   not the root cause.

 - Refactoring of dma-kmalloc caches creation.

 - Trivial cleanups such as removal of unused parameters, fixes and
   clarifications of comments.

 - Hyeonggon Yoo joins as a reviewer.

* tag 'slab-for-5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/vbabka/slab:
  MAINTAINERS: add myself as reviewer for slab
  mm/slub: remove unused kmem_cache_order_objects max
  mm: slab: fix comment for __assume_kmalloc_alignment
  mm: slab: fix comment for ARCH_KMALLOC_MINALIGN
  mm/slub: remove unneeded return value of slab_pad_check
  mm/slab_common: move dma-kmalloc caches creation into new_kmalloc_cache()
  mm/slub: remove meaningless node check in ___slab_alloc()
  mm/slub: remove duplicate flag in allocate_slab()
  mm/slub: remove unused parameter in setup_object*()
  mm/slab.c: fix comments
  slab, documentation: add description of debugfs files for SLUB caches
  mm/slub: sort debugfs output by frequency of stack traces
  mm/slub: distinguish and print stack traces in debugfs files
  mm/slub: use stackdepot to save stack trace in objects
  mm/slub: move struct track init out of set_track()
  lib/stackdepot: allow requesting early initialization dynamically
  mm/slub, kunit: Make slub_kunit unaffected by user specified flags
  mm/slab: remove some unused functions

1 files changed, 108 insertions, 66 deletions

diff --git a/mm/slub.c b/mm/slub.c
index ed5c2c03a47a..e5535020e0fd 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -26,6 +26,7 @@
 #include <linux/cpuset.h>
 #include <linux/mempolicy.h>
 #include <linux/ctype.h>
+#include <linux/stackdepot.h>
 #include <linux/debugobjects.h>
 #include <linux/kallsyms.h>
 #include <linux/kfence.h>
@@ -37,6 +38,7 @@
 #include <linux/memcontrol.h>
 #include <linux/random.h>
 #include <kunit/test.h>
+#include <linux/sort.h>
 
 #include <linux/debugfs.h>
 #include <trace/events/kmem.h>
@@ -264,8 +266,8 @@ static inline bool kmem_cache_has_cpu_partial(struct kmem_cache *s)
 #define TRACK_ADDRS_COUNT 16
 struct track {
 	unsigned long addr;	/* Called from address */
-#ifdef CONFIG_STACKTRACE
-	unsigned long addrs[TRACK_ADDRS_COUNT];	/* Called from address */
+#ifdef CONFIG_STACKDEPOT
+	depot_stack_handle_t handle;
 #endif
 	int cpu;		/* Was running on cpu */
 	int pid;		/* Pid context */
@@ -724,57 +726,51 @@ static struct track *get_track(struct kmem_cache *s, void *object,
 	return kasan_reset_tag(p + alloc);
 }
 
-static void set_track(struct kmem_cache *s, void *object,
+static void noinline set_track(struct kmem_cache *s, void *object,
 			enum track_item alloc, unsigned long addr)
 {
 	struct track *p = get_track(s, object, alloc);
 
-	if (addr) {
-#ifdef CONFIG_STACKTRACE
-		unsigned int nr_entries;
-
-		metadata_access_enable();
-		nr_entries = stack_trace_save(kasan_reset_tag(p->addrs),
-					      TRACK_ADDRS_COUNT, 3);
-		metadata_access_disable();
+#ifdef CONFIG_STACKDEPOT
+	unsigned long entries[TRACK_ADDRS_COUNT];
+	unsigned int nr_entries;
 
-		if (nr_entries < TRACK_ADDRS_COUNT)
-			p->addrs[nr_entries] = 0;
+	nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 3);
+	p->handle = stack_depot_save(entries, nr_entries, GFP_NOWAIT);
 #endif
-		p->addr = addr;
-		p->cpu = smp_processor_id();
-		p->pid = current->pid;
-		p->when = jiffies;
-	} else {
-		memset(p, 0, sizeof(struct track));
-	}
+
+	p->addr = addr;
+	p->cpu = smp_processor_id();
+	p->pid = current->pid;
+	p->when = jiffies;
 }
 
 static void init_tracking(struct kmem_cache *s, void *object)
 {
+	struct track *p;
+
 	if (!(s->flags & SLAB_STORE_USER))
 		return;
 
-	set_track(s, object, TRACK_FREE, 0UL);
-	set_track(s, object, TRACK_ALLOC, 0UL);
+	p = get_track(s, object, TRACK_ALLOC);
+	memset(p, 0, 2*sizeof(struct track));
 }
 
 static void print_track(const char *s, struct track *t, unsigned long pr_time)
 {
+	depot_stack_handle_t handle __maybe_unused;
+
 	if (!t->addr)
 		return;
 
 	pr_err("%s in %pS age=%lu cpu=%u pid=%d\n",
 	       s, (void *)t->addr, pr_time - t->when, t->cpu, t->pid);
-#ifdef CONFIG_STACKTRACE
-	{
-		int i;
-		for (i = 0; i < TRACK_ADDRS_COUNT; i++)
-			if (t->addrs[i])
-				pr_err("\t%pS\n", (void *)t->addrs[i]);
-			else
-				break;
-	}
+#ifdef CONFIG_STACKDEPOT
+	handle = READ_ONCE(t->handle);
+	if (handle)
+		stack_depot_print(handle);
+	else
+		pr_err("object allocation/free stack trace missing\n");
 #endif
 }
 
@@ -1021,7 +1017,7 @@ static int check_pad_bytes(struct kmem_cache *s, struct slab *slab, u8 *p)
 }
 
 /* Check the pad bytes at the end of a slab page */
-static int slab_pad_check(struct kmem_cache *s, struct slab *slab)
+static void slab_pad_check(struct kmem_cache *s, struct slab *slab)
 {
 	u8 *start;
 	u8 *fault;
@@ -1031,21 +1027,21 @@ static int slab_pad_check(struct kmem_cache *s, struct slab *slab)
 	int remainder;
 
 	if (!(s->flags & SLAB_POISON))
-		return 1;
+		return;
 
 	start = slab_address(slab);
 	length = slab_size(slab);
 	end = start + length;
 	remainder = length % s->size;
 	if (!remainder)
-		return 1;
+		return;
 
 	pad = end - remainder;
 	metadata_access_enable();
 	fault = memchr_inv(kasan_reset_tag(pad), POISON_INUSE, remainder);
 	metadata_access_disable();
 	if (!fault)
-		return 1;
+		return;
 	while (end > fault && end[-1] == POISON_INUSE)
 		end--;
 
@@ -1054,7 +1050,6 @@ static int slab_pad_check(struct kmem_cache *s, struct slab *slab)
 	print_section(KERN_ERR, "Padding ", pad, remainder);
 
 	restore_bytes(s, "slab padding", POISON_INUSE, fault, end);
-	return 0;
 }
 
 static int check_object(struct kmem_cache *s, struct slab *slab,
@@ -1268,8 +1263,7 @@ static inline void dec_slabs_node(struct kmem_cache *s, int node, int objects)
 }
 
 /* Object debug checks for alloc/free paths */
-static void setup_object_debug(struct kmem_cache *s, struct slab *slab,
-								void *object)
+static void setup_object_debug(struct kmem_cache *s, void *object)
 {
 	if (!kmem_cache_debug_flags(s, SLAB_STORE_USER|SLAB_RED_ZONE|__OBJECT_POISON))
 		return;
@@ -1534,6 +1528,8 @@ static int __init setup_slub_debug(char *str)
 			global_slub_debug_changed = true;
 		} else {
 			slab_list_specified = true;
+			if (flags & SLAB_STORE_USER)
+				stack_depot_want_early_init();
 		}
 	}
 
@@ -1551,6 +1547,8 @@ static int __init setup_slub_debug(char *str)
 	}
 out:
 	slub_debug = global_flags;
+	if (slub_debug & SLAB_STORE_USER)
+		stack_depot_want_early_init();
 	if (slub_debug != 0 || slub_debug_string)
 		static_branch_enable(&slub_debug_enabled);
 	else
@@ -1584,6 +1582,9 @@ slab_flags_t kmem_cache_flags(unsigned int object_size,
 	slab_flags_t block_flags;
 	slab_flags_t slub_debug_local = slub_debug;
 
+	if (flags & SLAB_NO_USER_FLAGS)
+		return flags;
+
 	/*
 	 * If the slab cache is for debugging (e.g. kmemleak) then
 	 * don't store user (stack trace) information by default,
@@ -1628,8 +1629,7 @@ slab_flags_t kmem_cache_flags(unsigned int object_size,
 	return flags | slub_debug_local;
 }
 #else /* !CONFIG_SLUB_DEBUG */
-static inline void setup_object_debug(struct kmem_cache *s,
-			struct slab *slab, void *object) {}
+static inline void setup_object_debug(struct kmem_cache *s, void *object) {}
 static inline
 void setup_slab_debug(struct kmem_cache *s, struct slab *slab, void *addr) {}
 
@@ -1641,8 +1641,7 @@ static inline int free_debug_processing(
 	void *head, void *tail, int bulk_cnt,
 	unsigned long addr) { return 0; }
 
-static inline int slab_pad_check(struct kmem_cache *s, struct slab *slab)
-			{ return 1; }
+static inline void slab_pad_check(struct kmem_cache *s, struct slab *slab) {}
 static inline int check_object(struct kmem_cache *s, struct slab *slab,
 			void *object, u8 val) { return 1; }
 static inline void add_full(struct kmem_cache *s, struct kmem_cache_node *n,
@@ -1772,10 +1771,9 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s,
 	return *head != NULL;
 }
 
-static void *setup_object(struct kmem_cache *s, struct slab *slab,
-				void *object)
+static void *setup_object(struct kmem_cache *s, void *object)
 {
-	setup_object_debug(s, slab, object);
+	setup_object_debug(s, object);
 	object = kasan_init_slab_obj(s, object);
 	if (unlikely(s->ctor)) {
 		kasan_unpoison_object_data(s, object);
@@ -1894,13 +1892,13 @@ static bool shuffle_freelist(struct kmem_cache *s, struct slab *slab)
 	/* First entry is used as the base of the freelist */
 	cur = next_freelist_entry(s, slab, &pos, start, page_limit,
 				freelist_count);
-	cur = setup_object(s, slab, cur);
+	cur = setup_object(s, cur);
 	slab->freelist = cur;
 
 	for (idx = 1; idx < slab->objects; idx++) {
 		next = next_freelist_entry(s, slab, &pos, start, page_limit,
 			freelist_count);
-		next = setup_object(s, slab, next);
+		next = setup_object(s, next);
 		set_freepointer(s, cur, next);
 		cur = next;
 	}
@@ -1939,7 +1937,7 @@ static struct slab *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 	 */
 	alloc_gfp = (flags | __GFP_NOWARN | __GFP_NORETRY) & ~__GFP_NOFAIL;
 	if ((alloc_gfp & __GFP_DIRECT_RECLAIM) && oo_order(oo) > oo_order(s->min))
-		alloc_gfp = (alloc_gfp | __GFP_NOMEMALLOC) & ~(__GFP_RECLAIM|__GFP_NOFAIL);
+		alloc_gfp = (alloc_gfp | __GFP_NOMEMALLOC) & ~__GFP_RECLAIM;
 
 	slab = alloc_slab_page(alloc_gfp, node, oo);
 	if (unlikely(!slab)) {
@@ -1971,11 +1969,11 @@ static struct slab *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 
 	if (!shuffle) {
 		start = fixup_red_left(s, start);
-		start = setup_object(s, slab, start);
+		start = setup_object(s, start);
 		slab->freelist = start;
 		for (idx = 0, p = start; idx < slab->objects - 1; idx++) {
 			next = p + s->size;
-			next = setup_object(s, slab, next);
+			next = setup_object(s, next);
 			set_freepointer(s, p, next);
 			p = next;
 		}
@@ -2910,7 +2908,6 @@ redo:
 		 */
 		if (!node_isset(node, slab_nodes)) {
 			node = NUMA_NO_NODE;
-			goto redo;
 		} else {
 			stat(s, ALLOC_NODE_MISMATCH);
 			goto deactivate_slab;
@@ -4165,8 +4162,6 @@ static int calculate_sizes(struct kmem_cache *s)
 	 */
 	s->oo = oo_make(order, size);
 	s->min = oo_make(get_order(size), size);
-	if (oo_objects(s->oo) > oo_objects(s->max))
-		s->max = s->oo;
 
 	return !!oo_objects(s->oo);
 }
@@ -4344,18 +4339,26 @@ void __kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *slab)
 	objp = fixup_red_left(s, objp);
 	trackp = get_track(s, objp, TRACK_ALLOC);
 	kpp->kp_ret = (void *)trackp->addr;
-#ifdef CONFIG_STACKTRACE
-	for (i = 0; i < KS_ADDRS_COUNT && i < TRACK_ADDRS_COUNT; i++) {
-		kpp->kp_stack[i] = (void *)trackp->addrs[i];
-		if (!kpp->kp_stack[i])
-			break;
-	}
+#ifdef CONFIG_STACKDEPOT
+	{
+		depot_stack_handle_t handle;
+		unsigned long *entries;
+		unsigned int nr_entries;
 
-	trackp = get_track(s, objp, TRACK_FREE);
-	for (i = 0; i < KS_ADDRS_COUNT && i < TRACK_ADDRS_COUNT; i++) {
-		kpp->kp_free_stack[i] = (void *)trackp->addrs[i];
-		if (!kpp->kp_free_stack[i])
-			break;
+		handle = READ_ONCE(trackp->handle);
+		if (handle) {
+			nr_entries = stack_depot_fetch(handle, &entries);
+			for (i = 0; i < KS_ADDRS_COUNT && i < nr_entries; i++)
+				kpp->kp_stack[i] = (void *)entries[i];
+		}
+
+		trackp = get_track(s, objp, TRACK_FREE);
+		handle = READ_ONCE(trackp->handle);
+		if (handle) {
+			nr_entries = stack_depot_fetch(handle, &entries);
+			for (i = 0; i < KS_ADDRS_COUNT && i < nr_entries; i++)
+				kpp->kp_free_stack[i] = (void *)entries[i];
+		}
 	}
 #endif
 #endif
@@ -5057,6 +5060,7 @@ EXPORT_SYMBOL(validate_slab_cache);
  */
 
 struct location {
+	depot_stack_handle_t handle;
 	unsigned long count;
 	unsigned long addr;
 	long long sum_time;
@@ -5109,9 +5113,13 @@ static int add_location(struct loc_track *t, struct kmem_cache *s,
 {
 	long start, end, pos;
 	struct location *l;
-	unsigned long caddr;
+	unsigned long caddr, chandle;
 	unsigned long age = jiffies - track->when;
+	depot_stack_handle_t handle = 0;
 
+#ifdef CONFIG_STACKDEPOT
+	handle = READ_ONCE(track->handle);
+#endif
 	start = -1;
 	end = t->count;
 
@@ -5126,7 +5134,8 @@ static int add_location(struct loc_track *t, struct kmem_cache *s,
 			break;
 
 		caddr = t->loc[pos].addr;
-		if (track->addr == caddr) {
+		chandle = t->loc[pos].handle;
+		if ((track->addr == caddr) && (handle == chandle)) {
 
 			l = &t->loc[pos];
 			l->count++;
@@ -5151,6 +5160,8 @@ static int add_location(struct loc_track *t, struct kmem_cache *s,
 
 		if (track->addr < caddr)
 			end = pos;
+		else if (track->addr == caddr && handle < chandle)
+			end = pos;
 		else
 			start = pos;
 	}
@@ -5173,6 +5184,7 @@ static int add_location(struct loc_track *t, struct kmem_cache *s,
 	l->max_time = age;
 	l->min_pid = track->pid;
 	l->max_pid = track->pid;
+	l->handle = handle;
 	cpumask_clear(to_cpumask(l->cpus));
 	cpumask_set_cpu(track->cpu, to_cpumask(l->cpus));
 	nodes_clear(l->nodes);
@@ -6082,6 +6094,21 @@ static int slab_debugfs_show(struct seq_file *seq, void *v)
 			seq_printf(seq, " nodes=%*pbl",
 				 nodemask_pr_args(&l->nodes));
 
+#ifdef CONFIG_STACKDEPOT
+		{
+			depot_stack_handle_t handle;
+			unsigned long *entries;
+			unsigned int nr_entries, j;
+
+			handle = READ_ONCE(l->handle);
+			if (handle) {
+				nr_entries = stack_depot_fetch(handle, &entries);
+				seq_puts(seq, "\n");
+				for (j = 0; j < nr_entries; j++)
+					seq_printf(seq, "        %pS\n", (void *)entries[j]);
+			}
+		}
+#endif
 		seq_puts(seq, "\n");
 	}
 
@@ -6106,6 +6133,17 @@ static void *slab_debugfs_next(struct seq_file *seq, void *v, loff_t *ppos)
 	return NULL;
 }
 
+static int cmp_loc_by_count(const void *a, const void *b, const void *data)
+{
+	struct location *loc1 = (struct location *)a;
+	struct location *loc2 = (struct location *)b;
+
+	if (loc1->count > loc2->count)
+		return -1;
+	else
+		return 1;
+}
+
 static void *slab_debugfs_start(struct seq_file *seq, loff_t *ppos)
 {
 	struct loc_track *t = seq->private;
@@ -6167,6 +6205,10 @@ static int slab_debug_trace_open(struct inode *inode, struct file *filep)
 		spin_unlock_irqrestore(&n->list_lock, flags);
 	}
 
+	/* Sort locations by count */
+	sort_r(t->loc, t->count, sizeof(struct location),
+		cmp_loc_by_count, NULL, NULL);
+
 	bitmap_free(obj_map);
 	return 0;
 }