Re: [PATCH] net/udp: do not touch skb->peeked unless really needed

@@ -49,7 +49,11 @@ struct udp_sock {
 	unsigned int	 corkflag;	/* Cork is required */
 	__u8		 encap_type;	/* Is this an Encapsulation socket? */
 	unsigned char	 no_check6_tx:1,/* Send zero UDP6 checksums on TX? */
-			 no_check6_rx:1;/* Allow zero UDP6 checksums on RX? */
+			 no_check6_rx:1,/* Allow zero UDP6 checksums on RX? */
+			 pcflag:6;	/* UDP-Lite specific, moved here to */
+					/* fill an hole, marks socket as */
+					/* UDP-Lite if > 0    */
+
 	/*
 	 * Following member retains the information to create a UDP header
 	 * when the socket is uncorked.

@@ -64,8 +68,7 @@ struct udp_sock {
 #define UDPLITE_BIT      0x1  		/* set by udplite proto init function */
 #define UDPLITE_SEND_CC  0x2  		/* set via udplite setsockopt         */
 #define UDPLITE_RECV_CC  0x4		/* set via udplite setsocktopt        */
-	__u8		 pcflag;        /* marks socket as UDP-Lite if > 0    */
-	__u8		 unused[3];
+
 	/*
 	 * For encapsulation sockets.
 	 */

@@ -79,6 +82,9 @@ struct udp_sock {
 	int			(*gro_complete)(struct sock *sk,
 						struct sk_buff *skb,
 						int nhoff);
+
+	/* since we are prone to drops, avoid dirtying any sk cacheline */
+	atomic_t		drops ____cacheline_aligned_in_smp;
 };
 
 static inline struct udp_sock *udp_sk(const struct sock *sk)

@@ -106,6 +112,17 @@ static inline bool udp_get_no_check6_rx(struct sock *sk)
 	return udp_sk(sk)->no_check6_rx;
 }
 
+static inline int udp_drops_read(const struct sock *sk)
+{
      * +	return atomic_read(&udp_sk(sk)->drops);
+}
+
+static inline void
+udp_skb_set_dropcount(const struct sock *sk, struct sk_buff *skb)
+{
+	SOCK_SKB_CB(skb)->dropcount = udp_drops_read(sk);
+}
+
 #define udp_portaddr_for_each_entry(__sk, list) \
 	hlist_for_each_entry(__sk, list, __sk_common.skc_portaddr_node)
 

@@ -2138,6 +2138,8 @@ struct sock_skb_cb {
 	SOCK_SKB_CB(skb)->dropcount = atomic_read(&sk->sk_drops);
 }
 
+int sk_drops_read(const struct sock *sk);
+
 static inline void sk_drops_add(struct sock *sk, const struct sk_buff *skb)
 {
 	int segs = max_t(u16, 1, skb_shinfo(skb)->gso_segs);

@@ -9,6 +9,7 @@
 #include <net/sock.h>
 #include <linux/kernel.h>
 #include <linux/tcp.h>
+#include <linux/udp.h>
 #include <linux/workqueue.h>
 
 #include <linux/inet_diag.h>

@@ -19,6 +20,14 @@
 static DEFINE_MUTEX(sock_diag_table_mutex);
 static struct workqueue_struct *broadcast_wq;
 
+int sk_drops_read(const struct sock *sk)
+{
+	if (sk->sk_protocol == IPPROTO_UDP)
+		return udp_drops_read(sk);
+	else
+		return atomic_read(&sk->sk_drops);
+}
+
 static u64 sock_gen_cookie(struct sock *sk)
 {
 	while (1) {

@@ -67,7 +76,7 @@ int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype)
 	mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued;
 	mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc);
 	mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len;
-	mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops);
+	mem[SK_MEMINFO_DROPS] = sk_drops_read(sk);
 
 	return nla_put(skb, attrtype, sizeof(mem), &mem);
 }

@@ -1174,6 +1174,11 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset,
 	return ret;
 }
 
+static void udp_drops_inc(struct sock *sk)
+{
+	atomic_inc(&udp_sk(sk)->drops);
+}
+
 /* fully reclaim rmem/fwd memory allocated for skb */
 static void udp_rmem_release(struct sock *sk, int size, int partial)
 {

@@ -1244,7 +1249,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
 	/* no need to setup a destructor, we will explicitly release the
 	 * forward allocated memory on dequeue
 	 */
-	sock_skb_set_dropcount(sk, skb);
+	udp_skb_set_dropcount(sk, skb);
 
 	__skb_queue_tail(list, skb);
 	spin_unlock(&list->lock);

@@ -1258,7 +1263,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
 	atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
 
 drop:
-	atomic_inc(&sk->sk_drops);
+	udp_drops_inc(sk);
 	return err;
 }
 EXPORT_SYMBOL_GPL(__udp_enqueue_schedule_skb);

@@ -1319,7 +1324,7 @@ static int first_packet_length(struct sock *sk)
 				IS_UDPLITE(sk));
 		__UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS,
 				IS_UDPLITE(sk));
-		atomic_inc(&sk->sk_drops);
+		udp_drops_inc(sk);
 		__skb_unlink(skb, rcvq);
 		total += skb->truesize;
 		kfree_skb(skb);

@@ -1417,7 +1422,7 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
 
 	if (unlikely(err)) {
 		if (!peeked) {
-			atomic_inc(&sk->sk_drops);
+			udp_drops_inc(sk);
 			UDP_INC_STATS(sock_net(sk),
 				      UDP_MIB_INERRORS, is_udplite);
 		}

@@ -1714,7 +1719,7 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	__UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite);
 drop:
 	__UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
-	atomic_inc(&sk->sk_drops);
+	udp_drops_inc(sk);
 	kfree_skb(skb);
 	return -1;
 }

@@ -1772,7 +1777,7 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
 		nskb = skb_clone(skb, GFP_ATOMIC);
 
 		if (unlikely(!nskb)) {
-			atomic_inc(&sk->sk_drops);
+			udp_drops_inc(sk);
 			__UDP_INC_STATS(net, UDP_MIB_RCVBUFERRORS,
 					IS_UDPLITE(sk));
 			__UDP_INC_STATS(net, UDP_MIB_INERRORS,

@@ -2491,7 +2496,7 @@ static void udp4_format_sock(struct sock *sp, struct seq_file *f,
 		from_kuid_munged(seq_user_ns(f), sock_i_uid(sp)),
 		0, sock_i_ino(sp),
 		atomic_read(&sp->sk_refcnt), sp,
-		atomic_read(&sp->sk_drops));
+		udp_drops_read(sp));
 }
 
 int udp4_seq_show(struct seq_file *seq, void *v)

@@ -1038,5 +1038,5 @@ void ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp,
 		   0,
 		   sock_i_ino(sp),
 		   atomic_read(&sp->sk_refcnt), sp,
-		   atomic_read(&sp->sk_drops));
+		   sk_drops_read(sp));
 }