Merge branch 'net-misplaced-fields'

Eric Dumazet says:

====================
net: more three misplaced fields

We recently reorganized some structures for better data locality
in networking fast paths.

This series moves three fields that were not correctly classified.

There probably more to come.

Reference : https://lwn.net/Articles/951321/
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Documentation/networking/net_cachelines/net_device.rst

@@ -136,8 +136,8 @@ struct_netpoll_info*                npinfo                  -
 possible_net_t                      nd_net                  -                   read_mostly         (dev_net)napi_busy_loop,tcp_v(4/6)_rcv,ip(v6)_rcv,ip(6)_input,ip(6)_input_finish
 void*                               ml_priv                                                         
 enum_netdev_ml_priv_type            ml_priv_type                                                    
-struct_pcpu_lstats__percpu*         lstats                                                          
-struct_pcpu_sw_netstats__percpu*    tstats                                                          
+struct_pcpu_lstats__percpu*         lstats                  read_mostly                             dev_lstats_add()
+struct_pcpu_sw_netstats__percpu*    tstats                  read_mostly                             dev_sw_netstats_tx_add()
 struct_pcpu_dstats__percpu*         dstats                                                          
 struct_garp_port*                   garp_port                                                       
 struct_mrp_port*                    mrp_port                                                        

Documentation/networking/net_cachelines/tcp_sock.rst

@@ -38,13 +38,13 @@ u32                           max_window              read_mostly         -
 u32                           mss_cache               read_mostly         read_mostly         tcp_rate_check_app_limited,tcp_current_mss,tcp_sync_mss,tcp_sndbuf_expand,tcp_tso_should_defer(tx);tcp_update_pacing_rate,tcp_clean_rtx_queue(rx)
 u32                           window_clamp            read_mostly         read_write          tcp_rcv_space_adjust,__tcp_select_window
 u32                           rcv_ssthresh            read_mostly         -                   __tcp_select_window
-u82                           scaling_ratio                                                   
+u8                            scaling_ratio           read_mostly         read_mostly         tcp_win_from_space
 struct                        tcp_rack                                                        
 u16                           advmss                  -                   read_mostly         tcp_rcv_space_adjust
 u8                            compressed_ack                                                  
 u8:2                          dup_ack_counter                                                 
 u8:1                          tlp_retrans                                                     
-u8:1                          tcp_usec_ts                                                     
+u8:1                          tcp_usec_ts             read_mostly         read_mostly
 u32                           chrono_start            read_write          -                   tcp_chrono_start/stop(tcp_write_xmit,tcp_cwnd_validate,tcp_send_syn_data)
 u32[3]                        chrono_stat             read_write          -                   tcp_chrono_start/stop(tcp_write_xmit,tcp_cwnd_validate,tcp_send_syn_data)
 u8:2                          chrono_type             read_write          -                   tcp_chrono_start/stop(tcp_write_xmit,tcp_cwnd_validate,tcp_send_syn_data)

include/linux/netdevice.h

@@ -2141,6 +2141,11 @@ struct net_device {
 
 	/* TXRX read-mostly hotpath */
 	__cacheline_group_begin(net_device_read_txrx);
+	union {
+		struct pcpu_lstats __percpu		*lstats;
+		struct pcpu_sw_netstats __percpu	*tstats;
+		struct pcpu_dstats __percpu		*dstats;
+	};
 	unsigned int		flags;
 	unsigned short		hard_header_len;
 	netdev_features_t	features;
@@ -2395,11 +2400,6 @@ struct net_device {
 	enum netdev_ml_priv_type	ml_priv_type;
 
 	enum netdev_stat_type		pcpu_stat_type:8;
-	union {
-		struct pcpu_lstats __percpu		*lstats;
-		struct pcpu_sw_netstats __percpu	*tstats;
-		struct pcpu_dstats __percpu		*dstats;
-	};
 
 #if IS_ENABLED(CONFIG_GARP)
 	struct garp_port __rcu	*garp_port;

include/linux/tcp.h

@@ -221,8 +221,10 @@ struct tcp_sock {
 	u32	lost_out;	/* Lost packets			*/
 	u32	sacked_out;	/* SACK'd packets			*/
 	u16	tcp_header_len;	/* Bytes of tcp header to send		*/
+	u8	scaling_ratio;	/* see tcp_win_from_space() */
 	u8	chrono_type : 2,	/* current chronograph type */
 		repair      : 1,
+		tcp_usec_ts : 1, /* TSval values in usec */
 		is_sack_reneg:1,    /* in recovery from loss with SACK reneg? */
 		is_cwnd_limited:1;/* forward progress limited by snd_cwnd? */
 	__cacheline_group_end(tcp_sock_read_txrx);
@@ -352,7 +354,6 @@ struct tcp_sock {
 	u32	compressed_ack_rcv_nxt;
 	struct list_head tsq_node; /* anchor in tsq_tasklet.head list */
 
-	u8	scaling_ratio;	/* see tcp_win_from_space() */
 	/* Information of the most recently (s)acked skb */
 	struct tcp_rack {
 		u64 mstamp; /* (Re)sent time of the skb */
@@ -368,8 +369,7 @@ struct tcp_sock {
 	u8	compressed_ack;
 	u8	dup_ack_counter:2,
 		tlp_retrans:1,	/* TLP is a retransmission */
-		tcp_usec_ts:1, /* TSval values in usec */
-		unused:4;
+		unused:5;
 	u8	thin_lto    : 1,/* Use linear timeouts for thin streams */
 		recvmsg_inq : 1,/* Indicate # of bytes in queue upon recvmsg */
 		fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */

net/core/dev.c

@@ -11652,11 +11652,12 @@ static void __init net_dev_struct_check(void)
 	CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_tx, 160);
 
 	/* TXRX read-mostly hotpath */
+	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, lstats);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, flags);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, hard_header_len);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, features);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, ip6_ptr);
-	CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 30);
+	CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 38);
 
 	/* RX read-mostly hotpath */
 	CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ptype_specific);

net/ipv4/tcp.c

@@ -4615,7 +4615,8 @@ static void __init tcp_struct_check(void)
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, prr_out);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, lost_out);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, sacked_out);
-	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_txrx, 31);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, scaling_ratio);
+	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_txrx, 32);
 
 	/* RX read-mostly hotpath cache lines */
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, copied_seq);