Merge branch 'drm-i915-use-ref_tracker-library-for-tracking-wakerefs'

Andrzej Hajda says:

====================
drm/i915: use ref_tracker library for tracking wakerefs

This is reviewed series of ref_tracker patches, ready to merge
via network tree, rebased on net-next/main.
i915 patches will be merged later via intel-gfx tree.
====================

Merge on top of an -rc tag in case it's needed in another tree.

Link: https://lore.kernel.org/r/20230224-track_gt-v9-0-5b47a33f55d1@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

include/linux/ref_tracker.h

@@ -17,12 +17,15 @@ struct ref_tracker_dir {
 	bool			dead;
 	struct list_head	list; /* List of active trackers */
 	struct list_head	quarantine; /* List of dead trackers */
+	char			name[32];
 #endif
 };
 
 #ifdef CONFIG_REF_TRACKER
+
 static inline void ref_tracker_dir_init(struct ref_tracker_dir *dir,
-					unsigned int quarantine_count)
+					unsigned int quarantine_count,
+					const char *name)
 {
 	INIT_LIST_HEAD(&dir->list);
 	INIT_LIST_HEAD(&dir->quarantine);
@@ -31,14 +34,20 @@ static inline void ref_tracker_dir_init(struct ref_tracker_dir *dir,
 	dir->dead = false;
 	refcount_set(&dir->untracked, 1);
 	refcount_set(&dir->no_tracker, 1);
+	strscpy(dir->name, name, sizeof(dir->name));
 	stack_depot_init();
 }
 
 void ref_tracker_dir_exit(struct ref_tracker_dir *dir);
 
+void ref_tracker_dir_print_locked(struct ref_tracker_dir *dir,
+				  unsigned int display_limit);
+
 void ref_tracker_dir_print(struct ref_tracker_dir *dir,
 			   unsigned int display_limit);
 
+int ref_tracker_dir_snprint(struct ref_tracker_dir *dir, char *buf, size_t size);
+
 int ref_tracker_alloc(struct ref_tracker_dir *dir,
 		      struct ref_tracker **trackerp, gfp_t gfp);
 
@@ -48,7 +57,8 @@ int ref_tracker_free(struct ref_tracker_dir *dir,
 #else /* CONFIG_REF_TRACKER */
 
 static inline void ref_tracker_dir_init(struct ref_tracker_dir *dir,
-					unsigned int quarantine_count)
+					unsigned int quarantine_count,
+					const char *name)
 {
 }
 
@@ -56,11 +66,22 @@ static inline void ref_tracker_dir_exit(struct ref_tracker_dir *dir)
 {
 }
 
+static inline void ref_tracker_dir_print_locked(struct ref_tracker_dir *dir,
+						unsigned int display_limit)
+{
+}
+
 static inline void ref_tracker_dir_print(struct ref_tracker_dir *dir,
 					 unsigned int display_limit)
 {
 }
 
+static inline int ref_tracker_dir_snprint(struct ref_tracker_dir *dir,
+					  char *buf, size_t size)
+{
+	return 0;
+}
+
 static inline int ref_tracker_alloc(struct ref_tracker_dir *dir,
 				    struct ref_tracker **trackerp,
 				    gfp_t gfp)

lib/ref_tracker.c

@@ -1,11 +1,16 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
+
+#define pr_fmt(fmt) "ref_tracker: " fmt
+
 #include <linux/export.h>
+#include <linux/list_sort.h>
 #include <linux/ref_tracker.h>
 #include <linux/slab.h>
 #include <linux/stacktrace.h>
 #include <linux/stackdepot.h>
 
 #define REF_TRACKER_STACK_ENTRIES 16
+#define STACK_BUF_SIZE 1024
 
 struct ref_tracker {
 	struct list_head	head;   /* anchor into dir->list or dir->quarantine */
@@ -14,6 +19,141 @@ struct ref_tracker {
 	depot_stack_handle_t	free_stack_handle;
 };
 
+struct ref_tracker_dir_stats {
+	int total;
+	int count;
+	struct {
+		depot_stack_handle_t stack_handle;
+		unsigned int count;
+	} stacks[];
+};
+
+static struct ref_tracker_dir_stats *
+ref_tracker_get_stats(struct ref_tracker_dir *dir, unsigned int limit)
+{
+	struct ref_tracker_dir_stats *stats;
+	struct ref_tracker *tracker;
+
+	stats = kmalloc(struct_size(stats, stacks, limit),
+			GFP_NOWAIT | __GFP_NOWARN);
+	if (!stats)
+		return ERR_PTR(-ENOMEM);
+	stats->total = 0;
+	stats->count = 0;
+
+	list_for_each_entry(tracker, &dir->list, head) {
+		depot_stack_handle_t stack = tracker->alloc_stack_handle;
+		int i;
+
+		++stats->total;
+		for (i = 0; i < stats->count; ++i)
+			if (stats->stacks[i].stack_handle == stack)
+				break;
+		if (i >= limit)
+			continue;
+		if (i >= stats->count) {
+			stats->stacks[i].stack_handle = stack;
+			stats->stacks[i].count = 0;
+			++stats->count;
+		}
+		++stats->stacks[i].count;
+	}
+
+	return stats;
+}
+
+struct ostream {
+	char *buf;
+	int size, used;
+};
+
+#define pr_ostream(stream, fmt, args...) \
+({ \
+	struct ostream *_s = (stream); \
+\
+	if (!_s->buf) { \
+		pr_err(fmt, ##args); \
+	} else { \
+		int ret, len = _s->size - _s->used; \
+		ret = snprintf(_s->buf + _s->used, len, pr_fmt(fmt), ##args); \
+		_s->used += min(ret, len); \
+	} \
+})
+
+static void
+__ref_tracker_dir_pr_ostream(struct ref_tracker_dir *dir,
+			     unsigned int display_limit, struct ostream *s)
+{
+	struct ref_tracker_dir_stats *stats;
+	unsigned int i = 0, skipped;
+	depot_stack_handle_t stack;
+	char *sbuf;
+
+	lockdep_assert_held(&dir->lock);
+
+	if (list_empty(&dir->list))
+		return;
+
+	stats = ref_tracker_get_stats(dir, display_limit);
+	if (IS_ERR(stats)) {
+		pr_ostream(s, "%s@%pK: couldn't get stats, error %pe\n",
+			   dir->name, dir, stats);
+		return;
+	}
+
+	sbuf = kmalloc(STACK_BUF_SIZE, GFP_NOWAIT | __GFP_NOWARN);
+
+	for (i = 0, skipped = stats->total; i < stats->count; ++i) {
+		stack = stats->stacks[i].stack_handle;
+		if (sbuf && !stack_depot_snprint(stack, sbuf, STACK_BUF_SIZE, 4))
+			sbuf[0] = 0;
+		pr_ostream(s, "%s@%pK has %d/%d users at\n%s\n", dir->name, dir,
+			   stats->stacks[i].count, stats->total, sbuf);
+		skipped -= stats->stacks[i].count;
+	}
+
+	if (skipped)
+		pr_ostream(s, "%s@%pK skipped reports about %d/%d users.\n",
+			   dir->name, dir, skipped, stats->total);
+
+	kfree(sbuf);
+
+	kfree(stats);
+}
+
+void ref_tracker_dir_print_locked(struct ref_tracker_dir *dir,
+				  unsigned int display_limit)
+{
+	struct ostream os = {};
+
+	__ref_tracker_dir_pr_ostream(dir, display_limit, &os);
+}
+EXPORT_SYMBOL(ref_tracker_dir_print_locked);
+
+void ref_tracker_dir_print(struct ref_tracker_dir *dir,
+			   unsigned int display_limit)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&dir->lock, flags);
+	ref_tracker_dir_print_locked(dir, display_limit);
+	spin_unlock_irqrestore(&dir->lock, flags);
+}
+EXPORT_SYMBOL(ref_tracker_dir_print);
+
+int ref_tracker_dir_snprint(struct ref_tracker_dir *dir, char *buf, size_t size)
+{
+	struct ostream os = { .buf = buf, .size = size };
+	unsigned long flags;
+
+	spin_lock_irqsave(&dir->lock, flags);
+	__ref_tracker_dir_pr_ostream(dir, 16, &os);
+	spin_unlock_irqrestore(&dir->lock, flags);
+
+	return os.used;
+}
+EXPORT_SYMBOL(ref_tracker_dir_snprint);
+
 void ref_tracker_dir_exit(struct ref_tracker_dir *dir)
 {
 	struct ref_tracker *tracker, *n;
@@ -27,14 +167,14 @@ void ref_tracker_dir_exit(struct ref_tracker_dir *dir)
 		kfree(tracker);
 		dir->quarantine_avail++;
 	}
-	list_for_each_entry_safe(tracker, n, &dir->list, head) {
-		pr_err("leaked reference.\n");
-		if (tracker->alloc_stack_handle)
-			stack_depot_print(tracker->alloc_stack_handle);
+	if (!list_empty(&dir->list)) {
+		ref_tracker_dir_print_locked(dir, 16);
 		leak = true;
+		list_for_each_entry_safe(tracker, n, &dir->list, head) {
 			list_del(&tracker->head);
 			kfree(tracker);
 		}
+	}
 	spin_unlock_irqrestore(&dir->lock, flags);
 	WARN_ON_ONCE(leak);
 	WARN_ON_ONCE(refcount_read(&dir->untracked) != 1);
@@ -42,28 +182,6 @@ void ref_tracker_dir_exit(struct ref_tracker_dir *dir)
 }
 EXPORT_SYMBOL(ref_tracker_dir_exit);
 
-void ref_tracker_dir_print(struct ref_tracker_dir *dir,
-			   unsigned int display_limit)
-{
-	struct ref_tracker *tracker;
-	unsigned long flags;
-	unsigned int i = 0;
-
-	spin_lock_irqsave(&dir->lock, flags);
-	list_for_each_entry(tracker, &dir->list, head) {
-		if (i < display_limit) {
-			pr_err("leaked reference.\n");
-			if (tracker->alloc_stack_handle)
-				stack_depot_print(tracker->alloc_stack_handle);
-			i++;
-		} else {
-			break;
-		}
-	}
-	spin_unlock_irqrestore(&dir->lock, flags);
-}
-EXPORT_SYMBOL(ref_tracker_dir_print);
-
 int ref_tracker_alloc(struct ref_tracker_dir *dir,
 		      struct ref_tracker **trackerp,
 		      gfp_t gfp)
@@ -71,7 +189,7 @@ int ref_tracker_alloc(struct ref_tracker_dir *dir,
 	unsigned long entries[REF_TRACKER_STACK_ENTRIES];
 	struct ref_tracker *tracker;
 	unsigned int nr_entries;
-	gfp_t gfp_mask = gfp;
+	gfp_t gfp_mask = gfp | __GFP_NOWARN;
 	unsigned long flags;
 
 	WARN_ON_ONCE(dir->dead);
@@ -119,7 +237,8 @@ int ref_tracker_free(struct ref_tracker_dir *dir,
 		return -EEXIST;
 	}
 	nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 1);
-	stack_handle = stack_depot_save(entries, nr_entries, GFP_ATOMIC);
+	stack_handle = stack_depot_save(entries, nr_entries,
+					GFP_NOWAIT | __GFP_NOWARN);
 
 	spin_lock_irqsave(&dir->lock, flags);
 	if (tracker->dead) {

lib/test_ref_tracker.c

@@ -64,7 +64,7 @@ static int __init test_ref_tracker_init(void)
 {
 	int i;
 
-	ref_tracker_dir_init(&ref_dir, 100);
+	ref_tracker_dir_init(&ref_dir, 100, "selftest");
 
 	timer_setup(&test_ref_tracker_timer, test_ref_tracker_timer_func, 0);
 	mod_timer(&test_ref_tracker_timer, jiffies + 1);

net/core/dev.c

@@ -10635,7 +10635,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	dev = PTR_ALIGN(p, NETDEV_ALIGN);
 	dev->padded = (char *)dev - (char *)p;
 
-	ref_tracker_dir_init(&dev->refcnt_tracker, 128);
+	ref_tracker_dir_init(&dev->refcnt_tracker, 128, name);
 #ifdef CONFIG_PCPU_DEV_REFCNT
 	dev->pcpu_refcnt = alloc_percpu(int);
 	if (!dev->pcpu_refcnt)

net/core/net_namespace.c

@@ -308,7 +308,7 @@ EXPORT_SYMBOL_GPL(get_net_ns_by_id);
 /* init code that must occur even if setup_net() is not called. */
 static __net_init void preinit_net(struct net *net)
 {
-	ref_tracker_dir_init(&net->notrefcnt_tracker, 128);
+	ref_tracker_dir_init(&net->notrefcnt_tracker, 128, "net notrefcnt");
 }
 
 /*
@@ -322,7 +322,7 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns)
 	LIST_HEAD(net_exit_list);
 
 	refcount_set(&net->ns.count, 1);
-	ref_tracker_dir_init(&net->refcnt_tracker, 128);
+	ref_tracker_dir_init(&net->refcnt_tracker, 128, "net refcnt");
 
 	refcount_set(&net->passive, 1);
 	get_random_bytes(&net->hash_mix, sizeof(u32));