net/core: Introduce netdev_core_stats_inc()

Although there is a kfree_skb_reason() helper function that can be used to
find the reason why this skb is dropped, but most callers didn't increase
one of rx_dropped, tx_dropped, rx_nohandler and rx_otherhost_dropped.

For the users, people are more concerned about why the dropped in ip
is increasing.

Introduce netdev_core_stats_inc() for trace the caller of
dev_core_stats_*_inc().

Also, add __code to netdev_core_stats_alloc(), as it's called with small
probability. And add noinline make sure netdev_core_stats_inc was never
inlined.
Signed-off-by: Yajun Deng <yajun.deng@linux.dev>
Suggested-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/netdevice.h

@@ -4002,32 +4002,19 @@ static __always_inline bool __is_skb_forwardable(const struct net_device *dev,
 	return false;
 }
 
-struct net_device_core_stats __percpu *netdev_core_stats_alloc(struct net_device *dev);
-
-static inline struct net_device_core_stats __percpu *dev_core_stats(struct net_device *dev)
-{
-	/* This READ_ONCE() pairs with the write in netdev_core_stats_alloc() */
-	struct net_device_core_stats __percpu *p = READ_ONCE(dev->core_stats);
-
-	if (likely(p))
-		return p;
-
-	return netdev_core_stats_alloc(dev);
-}
+void netdev_core_stats_inc(struct net_device *dev, u32 offset);
 
 #define DEV_CORE_STATS_INC(FIELD)						\
 static inline void dev_core_stats_##FIELD##_inc(struct net_device *dev)		\
 {										\
-	struct net_device_core_stats __percpu *p;				\
-										\
-	p = dev_core_stats(dev);						\
-	if (p)									\
-		this_cpu_inc(p->FIELD);						\
+	netdev_core_stats_inc(dev,						\
+			offsetof(struct net_device_core_stats, FIELD));		\
 }
 DEV_CORE_STATS_INC(rx_dropped)
 DEV_CORE_STATS_INC(tx_dropped)
 DEV_CORE_STATS_INC(rx_nohandler)
 DEV_CORE_STATS_INC(rx_otherhost_dropped)
+#undef DEV_CORE_STATS_INC
 
 static __always_inline int ____dev_forward_skb(struct net_device *dev,
 					       struct sk_buff *skb,

net/core/dev.c

@@ -10497,7 +10497,8 @@ void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64,
 }
 EXPORT_SYMBOL(netdev_stats_to_stats64);
 
-struct net_device_core_stats __percpu *netdev_core_stats_alloc(struct net_device *dev)
+static __cold struct net_device_core_stats __percpu *netdev_core_stats_alloc(
+		struct net_device *dev)
 {
 	struct net_device_core_stats __percpu *p;
 
@@ -10510,7 +10511,23 @@ struct net_device_core_stats __percpu *netdev_core_stats_alloc(struct net_device
 	/* This READ_ONCE() pairs with the cmpxchg() above */
 	return READ_ONCE(dev->core_stats);
 }
-EXPORT_SYMBOL(netdev_core_stats_alloc);
+
+noinline void netdev_core_stats_inc(struct net_device *dev, u32 offset)
+{
+	/* This READ_ONCE() pairs with the write in netdev_core_stats_alloc() */
+	struct net_device_core_stats __percpu *p = READ_ONCE(dev->core_stats);
+	unsigned long __percpu *field;
+
+	if (unlikely(!p)) {
+		p = netdev_core_stats_alloc(dev);
+		if (!p)
+			return;
+	}
+
+	field = (__force unsigned long __percpu *)((__force void *)p + offset);
+	this_cpu_inc(*field);
+}
+EXPORT_SYMBOL_GPL(netdev_core_stats_inc);
 
 /**
  *	dev_get_stats	- get network device statistics