ipv6: Move ipv6_fl_list from ipv6_pinfo to inet_sock.

[ Upstream commit 1c17f4373d4db1e1f0ebd3ddcd8e7a642927a826 ]

In {tcp6,udp6,raw6}_sock, struct ipv6_pinfo is always placed at
the beginning of a new cache line because

  1. __alignof__(struct tcp_sock) is 64 due to ____cacheline_aligned
     of __cacheline_group_begin(tcp_sock_write_tx)

  2. __alignof__(struct udp_sock) is 64 due to ____cacheline_aligned
     of struct numa_drop_counters

  3. in raw6_sock, struct numa_drop_counters is placed before
     struct ipv6_pinfo

.  struct ipv6_pinfo is 136 bytes, but the last cache line is
only used by ipv6_fl_list:

  $ pahole -C ipv6_pinfo vmlinux
  struct ipv6_pinfo {
  ...
  	/* --- cacheline 2 boundary (128 bytes) --- */
  	struct ipv6_fl_socklist *  ipv6_fl_list;         /*   128     8 */

  	/* size: 136, cachelines: 3, members: 23 */

Let's move ipv6_fl_list from struct ipv6_pinfo to struct inet_sock
to save a full cache line for {tcp6,udp6,raw6}_sock.

Now, struct ipv6_pinfo is 128 bytes, and {tcp6,udp6,raw6}_sock have
64 bytes less, while {tcp,udp,raw}_sock retain the same size.

Before:

  # grep -E "^(RAW|UDP[^L\-]|TCP)" /proc/slabinfo | awk '{print $1, "\t", $4}'
  RAWv6 	 1408
  UDPv6 	 1472
  TCPv6 	 2560
  RAW 		 1152
  UDP	 	 1280
  TCP 		 2368

After:

  # grep -E "^(RAW|UDP[^L\-]|TCP)" /proc/slabinfo | awk '{print $1, "\t", $4}'
  RAWv6 	 1344
  UDPv6 	 1408
  TCPv6 	 2496
  RAW 		 1152
  UDP	 	 1280
  TCP 		 2368

Also, ipv6_fl_list and inet_flags (SNDFLOW bit) are placed in the
same cache line.

  $ pahole -C inet_sock vmlinux
  ...
  	/* --- cacheline 11 boundary (704 bytes) was 56 bytes ago --- */
  	struct ipv6_pinfo *        pinet6;               /*   760     8 */
  	/* --- cacheline 12 boundary (768 bytes) --- */
  	struct ipv6_fl_socklist *  ipv6_fl_list;         /*   768     8 */
  	unsigned long              inet_flags;           /*   776     8 */

Doc churn is due to the insufficient Type column (only 1 space short).

Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20251014224210.2964778-1-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Stable-dep-of: 858d2a4f67ff ("tcp: fix potential race in tcp_v6_syn_recv_sock()")
Signed-off-by: Sasha Levin <sashal@kernel.org>

1 files changed, 7 insertions, 6 deletions

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 2e07dba293b4..0937d6965831 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1387,7 +1387,9 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 		if (!newsk)
 			return NULL;
 
-		inet_sk(newsk)->pinet6 = tcp_inet6_sk(newsk);
+		newinet = inet_sk(newsk);
+		newinet->pinet6 = tcp_inet6_sk(newsk);
+		newinet->ipv6_fl_list = NULL;
 
 		newnp = tcp_inet6_sk(newsk);
 		newtp = tcp_sk(newsk);
@@ -1406,7 +1408,6 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 
 		newnp->ipv6_mc_list = NULL;
 		newnp->ipv6_ac_list = NULL;
-		newnp->ipv6_fl_list = NULL;
 		newnp->pktoptions  = NULL;
 		newnp->opt	   = NULL;
 		newnp->mcast_oif   = inet_iif(skb);
@@ -1454,10 +1455,12 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 	newsk->sk_gso_type = SKB_GSO_TCPV6;
 	inet6_sk_rx_dst_set(newsk, skb);
 
-	inet_sk(newsk)->pinet6 = tcp_inet6_sk(newsk);
+	newinet = inet_sk(newsk);
+	newinet->pinet6 = tcp_inet6_sk(newsk);
+	newinet->ipv6_fl_list = NULL;
+	newinet->inet_opt = NULL;
 
 	newtp = tcp_sk(newsk);
-	newinet = inet_sk(newsk);
 	newnp = tcp_inet6_sk(newsk);
 
 	memcpy(newnp, np, sizeof(struct ipv6_pinfo));
@@ -1470,10 +1473,8 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 
 	   First: no IPv4 options.
 	 */
-	newinet->inet_opt = NULL;
 	newnp->ipv6_mc_list = NULL;
 	newnp->ipv6_ac_list = NULL;
-	newnp->ipv6_fl_list = NULL;
 
 	/* Clone RX bits */
 	newnp->rxopt.all = np->rxopt.all;