From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Sat, 16 Oct 2021 10:49:02 +0200
Subject: [PATCH 1/9] gen_stats: Add instead Set the value in
 __gnet_stats_copy_basic().

__gnet_stats_copy_basic() always assigns the value to the bstats
argument overwriting the previous value. The later added per-CPU version
always accumulated the values in the returning gnet_stats_basic_packed
argument.

Based on review there are five users of that function as of today:
- est_fetch_counters(), ___gnet_stats_copy_basic()
  memsets() bstats to zero, single invocation.

- mq_dump(), mqprio_dump(), mqprio_dump_class_stats()
  memsets() bstats to zero, multiple invocation but does not use the
  function due to !qdisc_is_percpu_stats().

Add the values in __gnet_stats_copy_basic() instead overwriting. Rename
the function to gnet_stats_add_basic() to make it more obvious.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/gen_stats.h  |    8 ++++----
 net/core/gen_estimator.c |    2 +-
 net/core/gen_stats.c     |   29 ++++++++++++++++-------------
 net/sched/sch_mq.c       |    5 ++---
 net/sched/sch_mqprio.c   |   11 +++++------
 5 files changed, 28 insertions(+), 27 deletions(-)

--- a/include/net/gen_stats.h
+++ b/include/net/gen_stats.h
@@ -46,10 +46,10 @@ int gnet_stats_copy_basic(const seqcount
 			  struct gnet_dump *d,
 			  struct gnet_stats_basic_cpu __percpu *cpu,
 			  struct gnet_stats_basic_packed *b);
-void __gnet_stats_copy_basic(const seqcount_t *running,
-			     struct gnet_stats_basic_packed *bstats,
-			     struct gnet_stats_basic_cpu __percpu *cpu,
-			     struct gnet_stats_basic_packed *b);
+void gnet_stats_add_basic(const seqcount_t *running,
+			  struct gnet_stats_basic_packed *bstats,
+			  struct gnet_stats_basic_cpu __percpu *cpu,
+			  struct gnet_stats_basic_packed *b);
 int gnet_stats_copy_basic_hw(const seqcount_t *running,
 			     struct gnet_dump *d,
 			     struct gnet_stats_basic_cpu __percpu *cpu,
--- a/net/core/gen_estimator.c
+++ b/net/core/gen_estimator.c
@@ -66,7 +66,7 @@ static void est_fetch_counters(struct ne
 	if (e->stats_lock)
 		spin_lock(e->stats_lock);
 
-	__gnet_stats_copy_basic(e->running, b, e->cpu_bstats, e->bstats);
+	gnet_stats_add_basic(e->running, b, e->cpu_bstats, e->bstats);
 
 	if (e->stats_lock)
 		spin_unlock(e->stats_lock);
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -114,9 +114,8 @@ gnet_stats_start_copy(struct sk_buff *sk
 }
 EXPORT_SYMBOL(gnet_stats_start_copy);
 
-static void
-__gnet_stats_copy_basic_cpu(struct gnet_stats_basic_packed *bstats,
-			    struct gnet_stats_basic_cpu __percpu *cpu)
+static void gnet_stats_add_basic_cpu(struct gnet_stats_basic_packed *bstats,
+				     struct gnet_stats_basic_cpu __percpu *cpu)
 {
 	int i;
 
@@ -136,26 +135,30 @@ static void
 	}
 }
 
-void
-__gnet_stats_copy_basic(const seqcount_t *running,
-			struct gnet_stats_basic_packed *bstats,
-			struct gnet_stats_basic_cpu __percpu *cpu,
-			struct gnet_stats_basic_packed *b)
+void gnet_stats_add_basic(const seqcount_t *running,
+			  struct gnet_stats_basic_packed *bstats,
+			  struct gnet_stats_basic_cpu __percpu *cpu,
+			  struct gnet_stats_basic_packed *b)
 {
 	unsigned int seq;
+	u64 bytes = 0;
+	u64 packets = 0;
 
 	if (cpu) {
-		__gnet_stats_copy_basic_cpu(bstats, cpu);
+		gnet_stats_add_basic_cpu(bstats, cpu);
 		return;
 	}
 	do {
 		if (running)
 			seq = read_seqcount_begin(running);
-		bstats->bytes = b->bytes;
-		bstats->packets = b->packets;
+		bytes = b->bytes;
+		packets = b->packets;
 	} while (running && read_seqcount_retry(running, seq));
+
+	bstats->bytes += bytes;
+	bstats->packets += packets;
 }
-EXPORT_SYMBOL(__gnet_stats_copy_basic);
+EXPORT_SYMBOL(gnet_stats_add_basic);
 
 static int
 ___gnet_stats_copy_basic(const seqcount_t *running,
@@ -166,7 +169,7 @@ static int
 {
 	struct gnet_stats_basic_packed bstats = {0};
 
-	__gnet_stats_copy_basic(running, &bstats, cpu, b);
+	gnet_stats_add_basic(running, &bstats, cpu, b);
 
 	if (d->compat_tc_stats && type == TCA_STATS_BASIC) {
 		d->tc_stats.bytes = bstats.bytes;
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -147,9 +147,8 @@ static int mq_dump(struct Qdisc *sch, st
 
 		if (qdisc_is_percpu_stats(qdisc)) {
 			qlen = qdisc_qlen_sum(qdisc);
-			__gnet_stats_copy_basic(NULL, &sch->bstats,
-						qdisc->cpu_bstats,
-						&qdisc->bstats);
+			gnet_stats_add_basic(NULL, &sch->bstats,
+					     qdisc->cpu_bstats, &qdisc->bstats);
 			__gnet_stats_copy_queue(&sch->qstats,
 						qdisc->cpu_qstats,
 						&qdisc->qstats, qlen);
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -405,9 +405,8 @@ static int mqprio_dump(struct Qdisc *sch
 		if (qdisc_is_percpu_stats(qdisc)) {
 			__u32 qlen = qdisc_qlen_sum(qdisc);
 
-			__gnet_stats_copy_basic(NULL, &sch->bstats,
-						qdisc->cpu_bstats,
-						&qdisc->bstats);
+			gnet_stats_add_basic(NULL, &sch->bstats,
+					     qdisc->cpu_bstats, &qdisc->bstats);
 			__gnet_stats_copy_queue(&sch->qstats,
 						qdisc->cpu_qstats,
 						&qdisc->qstats, qlen);
@@ -535,9 +534,9 @@ static int mqprio_dump_class_stats(struc
 			if (qdisc_is_percpu_stats(qdisc)) {
 				qlen = qdisc_qlen_sum(qdisc);
 
-				__gnet_stats_copy_basic(NULL, &bstats,
-							qdisc->cpu_bstats,
-							&qdisc->bstats);
+				gnet_stats_add_basic(NULL, &bstats,
+						     qdisc->cpu_bstats,
+						     &qdisc->bstats);
 				__gnet_stats_copy_queue(&qstats,
 							qdisc->cpu_qstats,
 							&qdisc->qstats,