lib/ref_tracker: improve printing stats

In case the library is tracking busy subsystem, simply
printing stack for every active reference will spam log
with long, hard to read, redundant stack traces. To improve
readabilty following changes have been made:
- reports are printed per stack_handle - log is more compact,
- added display name for ref_tracker_dir - it will differentiate
  multiple subsystems,
- stack trace is printed indented, in the same printk call,
- info about dropped references is printed as well.

Signed-off-by: Andrzej Hajda <andrzej.hajda@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 80 insertions, 12 deletions

diff --git a/lib/ref_tracker.c b/lib/ref_tracker.c
index d4eb0929af8f..2ffe79c90c17 100644
--- a/lib/ref_tracker.c
+++ b/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 */
@@ -14,24 +19,87 @@ struct ref_tracker {
 	depot_stack_handle_t	free_stack_handle;
 };
 
-void ref_tracker_dir_print_locked(struct ref_tracker_dir *dir,
-				  unsigned int display_limit)
+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;
-	unsigned int i = 0;
 
-	lockdep_assert_held(&dir->lock);
+	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) {
-		if (i < display_limit) {
-			pr_err("leaked reference.\n");
-			if (tracker->alloc_stack_handle)
-				stack_depot_print(tracker->alloc_stack_handle);
-			i++;
-		} else {
-			break;
+		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;
+}
+
+void ref_tracker_dir_print_locked(struct ref_tracker_dir *dir,
+				  unsigned int display_limit)
+{
+	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_err("%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_err("%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_err("%s@%pK skipped reports about %d/%d users.\n",
+		       dir->name, dir, skipped, stats->total);
+
+	kfree(sbuf);
+
+	kfree(stats);
 }
 EXPORT_SYMBOL(ref_tracker_dir_print_locked);
 
diff --git a/lib/test_ref_tracker.c b/lib/test_ref_tracker.c
index 19d7dec70cc6..49970a7c96f3 100644
--- a/lib/test_ref_tracker.c
+++ b/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);