Merge branch 'net-cacheline-optimizations'

Coco Li says:

====================
Analyze and Reorganize core Networking Structs to optimize cacheline consumption

Currently, variable-heavy structs in the networking stack is organized
chronologically, logically and sometimes by cacheline access.

This patch series attempts to reorganize the core networking stack
variables to minimize cacheline consumption during the phase of data
transfer. Specifically, we looked at the TCP/IP stack and the fast
path definition in TCP.

For documentation purposes, we also added new files for each core data
structure we considered, although not all ended up being modified due
to the amount of existing cacheline they span in the fast path. In
the documentation, we recorded all variables we identified on the
fast path and the reasons. We also hope that in the future when
variables are added/modified, the document can be referred to and
updated accordingly to reflect the latest variable organization.

Tested:
Our tests were run with neper tcp_rr using tcp traffic. The tests have $cpu
number of threads and variable number of flows (see below).

Tests were run on 6.5-rc1

Efficiency is computed as cpu seconds / throughput (one tcp_rr round trip).
The following result shows efficiency delta before and after the patch
series is applied.

On AMD platforms with 100Gb/s NIC and 256Mb L3 cache:
IPv4
Flows   with patches    clean kernel      Percent reduction
30k     0.0001736538065 0.0002741191042 -36.65%
20k     0.0001583661752 0.0002712559158 -41.62%
10k     0.0001639148817 0.0002951800751 -44.47%
5k      0.0001859683866 0.0003320642536 -44.00%
1k      0.0002035190546 0.0003152056382 -35.43%

IPv6
Flows   with patches  clean kernel    Percent reduction
30k     0.000202535503  0.0003275329163 -38.16%
20k     0.0002020654777 0.0003411304786 -40.77%
10k     0.0002122427035 0.0003803674705 -44.20%
5k      0.0002348776729 0.0004030403953 -41.72%
1k      0.0002237384583 0.0002813646157 -20.48%

On Intel platforms with 200Gb/s NIC and 105Mb L3 cache:
IPv6
Flows   with patches    clean kernel    Percent reduction
30k     0.0006296537873 0.0006370427753 -1.16%
20k     0.0003451029365 0.0003628016076 -4.88%
10k     0.0003187646958 0.0003346835645 -4.76%
5k      0.0002954676348 0.000311807592  -5.24%
1k      0.0001909169342 0.0001848069709 3.31%

v8 changes:
1. Update net_device_read_txrx cache group maximum
2. Update MAINTAINERS for documentations
3. Skip __cache_group variables in scripts/kernel-doc
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Documentation/networking/index.rst

@@ -75,6 +75,7 @@ Contents:
    mptcp-sysctl
    multiqueue
    napi
+   net_cachelines/index
    netconsole
    netdev-features
    netdevices

Documentation/networking/net_cachelines/index.rst

+.. SPDX-License-Identifier: GPL-2.0
+.. Copyright (C) 2023 Google LLC
+===================================
+Common Networking Struct Cachelines
+===================================
+
+.. toctree::
+   :maxdepth: 1
+
+   inet_connection_sock
+   inet_sock
+   net_device
+   netns_ipv4_sysctl
+   snmp
+   tcp_sock

Documentation/networking/net_cachelines/inet_connection_sock.rst

+.. SPDX-License-Identifier: GPL-2.0
+.. Copyright (C) 2023 Google LLC
+=====================================================
+inet_connection_sock struct fast path usage breakdown
+=====================================================
+
+Type                                Name                   fastpath_tx_access  fastpath_rx_access  comment
+..struct                            ..inet_connection_sock                                         
+struct_inet_sock                    icsk_inet              read_mostly         read_mostly         tcp_init_buffer_space,tcp_init_transfer,tcp_finish_connect,tcp_connect,tcp_send_rcvq,tcp_send_syn_data
+struct_request_sock_queue           icsk_accept_queue      -                   -                   
+struct_inet_bind_bucket             icsk_bind_hash         read_mostly         -                   tcp_set_state
+struct_inet_bind2_bucket            icsk_bind2_hash        read_mostly         -                   tcp_set_state,inet_put_port
+unsigned_long                       icsk_timeout           read_mostly         -                   inet_csk_reset_xmit_timer,tcp_connect
+struct_timer_list                   icsk_retransmit_timer  read_mostly         -                   inet_csk_reset_xmit_timer,tcp_connect
+struct_timer_list                   icsk_delack_timer      read_mostly         -                   inet_csk_reset_xmit_timer,tcp_connect
+u32                                 icsk_rto               read_write          -                   tcp_cwnd_validate,tcp_schedule_loss_probe,tcp_connect_init,tcp_connect,tcp_write_xmit,tcp_push_one
+u32                                 icsk_rto_min           -                   -                   
+u32                                 icsk_delack_max        -                   -                   
+u32                                 icsk_pmtu_cookie       read_write          -                   tcp_sync_mss,tcp_current_mss,tcp_send_syn_data,tcp_connect_init,tcp_connect
+struct_tcp_congestion_ops           icsk_ca_ops            read_write          -                   tcp_cwnd_validate,tcp_tso_segs,tcp_ca_dst_init,tcp_connect_init,tcp_connect,tcp_write_xmit
+struct_inet_connection_sock_af_ops  icsk_af_ops            read_mostly         -                   tcp_finish_connect,tcp_send_syn_data,tcp_mtup_init,tcp_mtu_check_reprobe,tcp_mtu_probe,tcp_connect_init,tcp_connect,__tcp_transmit_skb
+struct_tcp_ulp_ops*                 icsk_ulp_ops           -                   -                   
+void*                               icsk_ulp_data          -                   -                   
+u8:5                                icsk_ca_state          read_write          -                   tcp_cwnd_application_limited,tcp_set_ca_state,tcp_enter_cwr,tcp_tso_should_defer,tcp_mtu_probe,tcp_schedule_loss_probe,tcp_write_xmit,__tcp_transmit_skb
+u8:1                                icsk_ca_initialized    read_write          -                   tcp_init_transfer,tcp_init_congestion_control,tcp_init_transfer,tcp_finish_connect,tcp_connect
+u8:1                                icsk_ca_setsockopt     -                   -                   
+u8:1                                icsk_ca_dst_locked     write_mostly        -                   tcp_ca_dst_init,tcp_connect_init,tcp_connect
+u8                                  icsk_retransmits       write_mostly        -                   tcp_connect_init,tcp_connect
+u8                                  icsk_pending           read_write          -                   inet_csk_reset_xmit_timer,tcp_connect,tcp_check_probe_timer,__tcp_push_pending_frames,tcp_rearm_rto,tcp_event_new_data_sent,tcp_event_new_data_sent
+u8                                  icsk_backoff           write_mostly        -                   tcp_write_queue_purge,tcp_connect_init
+u8                                  icsk_syn_retries       -                   -                   
+u8                                  icsk_probes_out        -                   -                   
+u16                                 icsk_ext_hdr_len       read_mostly         -                   __tcp_mtu_to_mss,tcp_mtu_to_rss,tcp_mtu_probe,tcp_write_xmit,tcp_mtu_to_mss,
+struct_icsk_ack_u8                  pending                read_write          read_write          inet_csk_ack_scheduled,__tcp_cleanup_rbuf,tcp_cleanup_rbuf,inet_csk_clear_xmit_timer,tcp_event_ack-sent,inet_csk_reset_xmit_timer
+struct_icsk_ack_u8                  quick                  read_write          write_mostly        tcp_dec_quickack_mode,tcp_event_ack_sent,__tcp_transmit_skb,__tcp_select_window,__tcp_cleanup_rbuf
+struct_icsk_ack_u8                  pingpong               -                   -                   
+struct_icsk_ack_u8                  retry                  write_mostly        read_write          inet_csk_clear_xmit_timer,tcp_rearm_rto,tcp_event_new_data_sent,tcp_write_xmit,__tcp_send_ack,tcp_send_ack,
+struct_icsk_ack_u8                  ato                    read_mostly         write_mostly        tcp_dec_quickack_mode,tcp_event_ack_sent,__tcp_transmit_skb,__tcp_send_ack,tcp_send_ack
+struct_icsk_ack_unsigned_long       timeout                read_write          read_write          inet_csk_reset_xmit_timer,tcp_connect
+struct_icsk_ack_u32                 lrcvtime               read_write          -                   tcp_finish_connect,tcp_connect,tcp_event_data_sent,__tcp_transmit_skb
+struct_icsk_ack_u16                 rcv_mss                write_mostly        read_mostly         __tcp_select_window,__tcp_cleanup_rbuf,tcp_initialize_rcv_mss,tcp_connect_init
+struct_icsk_mtup_int                search_high            read_write          -                   tcp_mtup_init,tcp_sync_mss,tcp_connect_init,tcp_mtu_check_reprobe,tcp_write_xmit
+struct_icsk_mtup_int                search_low             read_write          -                   tcp_mtu_probe,tcp_mtu_check_reprobe,tcp_write_xmit,tcp_sync_mss,tcp_connect_init,tcp_mtup_init
+struct_icsk_mtup_u32:31             probe_size             read_write          -                   tcp_mtup_init,tcp_connect_init,__tcp_transmit_skb
+struct_icsk_mtup_u32:1              enabled                read_write          -                   tcp_mtup_init,tcp_sync_mss,tcp_connect_init,tcp_mtu_probe,tcp_write_xmit
+struct_icsk_mtup_u32                probe_timestamp        read_write          -                   tcp_mtup_init,tcp_connect_init,tcp_mtu_check_reprobe,tcp_mtu_probe
+u32                                 icsk_probes_tstamp     -                   -                   
+u32                                 icsk_user_timeout      -                   -                   
+u64[104/sizeof(u64)]                icsk_ca_priv           -                   -                   

Documentation/networking/net_cachelines/inet_sock.rst

+.. SPDX-License-Identifier: GPL-2.0
+.. Copyright (C) 2023 Google LLC
+=====================================================
+inet_connection_sock struct fast path usage breakdown
+=====================================================
+
+Type                    Name                  fastpath_tx_access  fastpath_rx_access  comment
+..struct                ..inet_sock                                                     
+struct_sock             sk                    read_mostly         read_mostly         tcp_init_buffer_space,tcp_init_transfer,tcp_finish_connect,tcp_connect,tcp_send_rcvq,tcp_send_syn_data
+struct_ipv6_pinfo*      pinet6                -                   -                   
+be16                    inet_sport            read_mostly         -                   __tcp_transmit_skb
+be32                    inet_daddr            read_mostly         -                   ip_select_ident_segs
+be32                    inet_rcv_saddr        -                   -                   
+be16                    inet_dport            read_mostly         -                   __tcp_transmit_skb
+u16                     inet_num              -                   -                   
+be32                    inet_saddr            -                   -                   
+s16                     uc_ttl                read_mostly         -                   __ip_queue_xmit/ip_select_ttl
+u16                     cmsg_flags            -                   -                   
+struct_ip_options_rcu*  inet_opt              read_mostly         -                   __ip_queue_xmit
+u16                     inet_id               read_mostly         -                   ip_select_ident_segs
+u8                      tos                   read_mostly         -                   ip_queue_xmit
+u8                      min_ttl               -                   -                   
+u8                      mc_ttl                -                   -                   
+u8                      pmtudisc              -                   -                   
+u8:1                    recverr               -                   -                   
+u8:1                    is_icsk               -                   -                   
+u8:1                    freebind              -                   -                   
+u8:1                    hdrincl               -                   -                   
+u8:1                    mc_loop               -                   -                   
+u8:1                    transparent           -                   -                   
+u8:1                    mc_all                -                   -                   
+u8:1                    nodefrag              -                   -                   
+u8:1                    bind_address_no_port  -                   -                   
+u8:1                    recverr_rfc4884       -                   -                   
+u8:1                    defer_connect         read_mostly         -                   tcp_sendmsg_fastopen
+u8                      rcv_tos               -                   -                   
+u8                      convert_csum          -                   -                   
+int                     uc_index              -                   -                   
+int                     mc_index              -                   -                   
+be32                    mc_addr               -                   -                   
+struct_ip_mc_socklist*  mc_list               -                   -                   
+struct_inet_cork_full   cork                  read_mostly         -                   __tcp_transmit_skb
+struct                  local_port_range      -                   -                   

MAINTAINERS

@@ -14986,6 +14986,7 @@ Q:	https://patchwork.kernel.org/project/netdevbpf/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
 F:	Documentation/devicetree/bindings/net/
+F:	Documentation/networking/net_cachelines/net_device.rst
 F:	drivers/connector/
 F:	drivers/net/
 F:	include/dt-bindings/net/
@@ -15041,6 +15042,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git
 F:	Documentation/core-api/netlink.rst
 F:	Documentation/netlink/
 F:	Documentation/networking/
+F:	Documentation/networking/net_cachelines/
 F:	Documentation/process/maintainer-netdev.rst
 F:	Documentation/userspace-api/netlink/
 F:	include/linux/in.h
@@ -15149,6 +15151,7 @@ NETWORKING [TCP]
 M:	Eric Dumazet <edumazet@google.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
+F:	Documentation/networking/net_cachelines/tcp_sock.rst
 F:	include/linux/tcp.h
 F:	include/net/tcp.h
 F:	include/trace/events/tcp.h

include/linux/cache.h

@@ -85,6 +85,31 @@
 #define cache_line_size()	L1_CACHE_BYTES
 #endif
 
+#ifndef __cacheline_group_begin
+#define __cacheline_group_begin(GROUP) \
+	__u8 __cacheline_group_begin__##GROUP[0]
+#endif
+
+#ifndef __cacheline_group_end
+#define __cacheline_group_end(GROUP) \
+	__u8 __cacheline_group_end__##GROUP[0]
+#endif
+
+#ifndef CACHELINE_ASSERT_GROUP_MEMBER
+#define CACHELINE_ASSERT_GROUP_MEMBER(TYPE, GROUP, MEMBER) \
+	BUILD_BUG_ON(!(offsetof(TYPE, MEMBER) >= \
+		       offsetofend(TYPE, __cacheline_group_begin__##GROUP) && \
+		       offsetofend(TYPE, MEMBER) <= \
+		       offsetof(TYPE, __cacheline_group_end__##GROUP)))
+#endif
+
+#ifndef CACHELINE_ASSERT_GROUP_SIZE
+#define CACHELINE_ASSERT_GROUP_SIZE(TYPE, GROUP, SIZE) \
+	BUILD_BUG_ON(offsetof(TYPE, __cacheline_group_end__##GROUP) - \
+		     offsetofend(TYPE, __cacheline_group_begin__##GROUP) > \
+		     SIZE)
+#endif
+
 /*
  * Helper to add padding within a struct to ensure data fall into separate
  * cachelines.

include/net/netns/ipv4.h

@@ -42,6 +42,38 @@ struct inet_timewait_death_row {
 struct tcp_fastopen_context;
 
 struct netns_ipv4 {
+	/* Cacheline organization can be found documented in
+	 * Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst.
+	 * Please update the document when adding new fields.
+	 */
+
+	/* TX readonly hotpath cache lines */
+	__cacheline_group_begin(netns_ipv4_read_tx);
+	u8 sysctl_tcp_early_retrans;
+	u8 sysctl_tcp_tso_win_divisor;
+	u8 sysctl_tcp_tso_rtt_log;
+	u8 sysctl_tcp_autocorking;
+	int sysctl_tcp_min_snd_mss;
+	unsigned int sysctl_tcp_notsent_lowat;
+	int sysctl_tcp_limit_output_bytes;
+	int sysctl_tcp_min_rtt_wlen;
+	int sysctl_tcp_wmem[3];
+	u8 sysctl_ip_fwd_use_pmtu;
+	__cacheline_group_end(netns_ipv4_read_tx);
+
+	/* TXRX readonly hotpath cache lines */
+	__cacheline_group_begin(netns_ipv4_read_txrx);
+	u8 sysctl_tcp_moderate_rcvbuf;
+	__cacheline_group_end(netns_ipv4_read_txrx);
+
+	/* RX readonly hotpath cache line */
+	__cacheline_group_begin(netns_ipv4_read_rx);
+	u8 sysctl_ip_early_demux;
+	u8 sysctl_tcp_early_demux;
+	int sysctl_tcp_reordering;
+	int sysctl_tcp_rmem[3];
+	__cacheline_group_end(netns_ipv4_read_rx);
+
 	struct inet_timewait_death_row tcp_death_row;
 	struct udp_table *udp_table;
 
@@ -96,17 +128,14 @@ struct netns_ipv4 {
 
 	u8 sysctl_ip_default_ttl;
 	u8 sysctl_ip_no_pmtu_disc;
-	u8 sysctl_ip_fwd_use_pmtu;
 	u8 sysctl_ip_fwd_update_priority;
 	u8 sysctl_ip_nonlocal_bind;
 	u8 sysctl_ip_autobind_reuse;
 	/* Shall we try to damage output packets if routing dev changes? */
 	u8 sysctl_ip_dynaddr;
-	u8 sysctl_ip_early_demux;
 #ifdef CONFIG_NET_L3_MASTER_DEV
 	u8 sysctl_raw_l3mdev_accept;
 #endif
-	u8 sysctl_tcp_early_demux;
 	u8 sysctl_udp_early_demux;
 
 	u8 sysctl_nexthop_compat_mode;
@@ -119,7 +148,6 @@ struct netns_ipv4 {
 	u8 sysctl_tcp_mtu_probing;
 	int sysctl_tcp_mtu_probe_floor;
 	int sysctl_tcp_base_mss;
-	int sysctl_tcp_min_snd_mss;
 	int sysctl_tcp_probe_threshold;
 	u32 sysctl_tcp_probe_interval;
 
@@ -135,17 +163,14 @@ struct netns_ipv4 {
 	u8 sysctl_tcp_backlog_ack_defer;
 	u8 sysctl_tcp_pingpong_thresh;
 
-	int sysctl_tcp_reordering;
 	u8 sysctl_tcp_retries1;
 	u8 sysctl_tcp_retries2;
 	u8 sysctl_tcp_orphan_retries;
 	u8 sysctl_tcp_tw_reuse;
 	int sysctl_tcp_fin_timeout;
-	unsigned int sysctl_tcp_notsent_lowat;
 	u8 sysctl_tcp_sack;
 	u8 sysctl_tcp_window_scaling;
 	u8 sysctl_tcp_timestamps;
-	u8 sysctl_tcp_early_retrans;
 	u8 sysctl_tcp_recovery;
 	u8 sysctl_tcp_thin_linear_timeouts;
 	u8 sysctl_tcp_slow_start_after_idle;
@@ -161,21 +186,13 @@ struct netns_ipv4 {
 	u8 sysctl_tcp_frto;
 	u8 sysctl_tcp_nometrics_save;
 	u8 sysctl_tcp_no_ssthresh_metrics_save;
-	u8 sysctl_tcp_moderate_rcvbuf;
-	u8 sysctl_tcp_tso_win_divisor;
 	u8 sysctl_tcp_workaround_signed_windows;
-	int sysctl_tcp_limit_output_bytes;
 	int sysctl_tcp_challenge_ack_limit;
-	int sysctl_tcp_min_rtt_wlen;
 	u8 sysctl_tcp_min_tso_segs;
-	u8 sysctl_tcp_tso_rtt_log;
-	u8 sysctl_tcp_autocorking;
 	u8 sysctl_tcp_reflect_tos;
 	int sysctl_tcp_invalid_ratelimit;
 	int sysctl_tcp_pacing_ss_ratio;
 	int sysctl_tcp_pacing_ca_ratio;
-	int sysctl_tcp_wmem[3];
-	int sysctl_tcp_rmem[3];
 	unsigned int sysctl_tcp_child_ehash_entries;
 	unsigned long sysctl_tcp_comp_sack_delay_ns;
 	unsigned long sysctl_tcp_comp_sack_slack_ns;

net/core/net_namespace.c

@@ -1099,11 +1099,56 @@ static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid,
 	rtnl_set_sk_err(net, RTNLGRP_NSID, err);
 }
 
+#ifdef CONFIG_NET_NS
+static void __init netns_ipv4_struct_check(void)
+{
+	/* TX readonly hotpath cache lines */
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx,
+				      sysctl_tcp_early_retrans);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx,
+				      sysctl_tcp_tso_win_divisor);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx,
+				      sysctl_tcp_tso_rtt_log);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx,
+				      sysctl_tcp_autocorking);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx,
+				      sysctl_tcp_min_snd_mss);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx,
+				      sysctl_tcp_notsent_lowat);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx,
+				      sysctl_tcp_limit_output_bytes);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx,
+				      sysctl_tcp_min_rtt_wlen);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx,
+				      sysctl_tcp_wmem);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx,
+				      sysctl_ip_fwd_use_pmtu);
+	CACHELINE_ASSERT_GROUP_SIZE(struct netns_ipv4, netns_ipv4_read_tx, 33);
+
+	/* TXRX readonly hotpath cache lines */
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_txrx,
+				      sysctl_tcp_moderate_rcvbuf);
+	CACHELINE_ASSERT_GROUP_SIZE(struct netns_ipv4, netns_ipv4_read_txrx, 1);
+
+	/* RX readonly hotpath cache line */
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx,
+				      sysctl_ip_early_demux);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx,
+				      sysctl_tcp_early_demux);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx,
+				      sysctl_tcp_reordering);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx,
+				      sysctl_tcp_rmem);
+	CACHELINE_ASSERT_GROUP_SIZE(struct netns_ipv4, netns_ipv4_read_rx, 18);
+}
+#endif
+
 void __init net_ns_init(void)
 {
 	struct net_generic *ng;
 
 #ifdef CONFIG_NET_NS
+	netns_ipv4_struct_check();
 	net_cachep = kmem_cache_create("net_namespace", sizeof(struct net),
 					SMP_CACHE_BYTES,
 					SLAB_PANIC|SLAB_ACCOUNT, NULL);

scripts/kernel-doc

@@ -1592,6 +1592,11 @@ sub push_parameter($$$$$) {
 		$parameterdescs{$param} = "anonymous\n";
 		$anon_struct_union = 1;
 	}
+	elsif ($param =~ "__cacheline_group" )
+	# handle cache group enforcing variables: they do not need be described in header files
+	{
+		return; # ignore __cacheline_group_begin and __cacheline_group_end
+	}
 
 	# warn if parameter has no description
 	# (but ignore ones starting with # as these are not parameters