[PATCH v8 net-next 3/5] netns-ipv4: reorganize netns_ipv4 fast path variables

[Coco Li <lixiaoyan@google.com>]

Reorganize fast path variables on tx-txrx-rx order.
Fastpath cacheline ends after sysctl_tcp_rmem.
There are only read-only variables here. (write is on the control path
and not considered in this case)

Below data generated with pahole on x86 architecture.
Fast path variables span cache lines before change: 4
Fast path variables span cache lines after change: 2

Suggested-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Wei Wang <weiwan@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Coco Li <lixiaoyan@google.com>
---
 include/net/netns/ipv4.h | 47 +++++++++++++++++++++++++++-------------
 net/core/net_namespace.c | 45 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 77 insertions(+), 15 deletions(-)

diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 73f43f6991999..ea882964c71ee 100644
--- a/include/net/netns/ipv4.h
+++ b/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;
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index f4183c4c1ec82..cb8bcbff9e83a 100644
--- a/net/core/net_namespace.c
+++ b/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);
-- 
2.43.0.rc1.413.gea7ed67945-goog