diff options
| author | Kuniyuki Iwashima <kuniyu@google.com> | 2025-10-14 22:42:07 +0000 |
|---|---|---|
| committer | Jakub Kicinski <kuba@kernel.org> | 2025-10-17 16:06:52 -0700 |
| commit | 1c17f4373d4db1e1f0ebd3ddcd8e7a642927a826 (patch) | |
| tree | 5e0f389d4c438634f8ede1c10435739d34cea71c /include | |
| parent | 0746da01767e8a0df97ae5d031d852e932e03682 (diff) | |
ipv6: Move ipv6_fl_list from ipv6_pinfo to inet_sock.
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>
Diffstat (limited to 'include')
| -rw-r--r-- | include/linux/ipv6.h | 1 | ||||
| -rw-r--r-- | include/net/inet_sock.h | 1 |
2 files changed, 1 insertions, 1 deletions
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 43b7bb828738..7294e4e89b79 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -271,7 +271,6 @@ struct ipv6_pinfo { struct ipv6_mc_socklist __rcu *ipv6_mc_list; struct ipv6_ac_socklist *ipv6_ac_list; - struct ipv6_fl_socklist __rcu *ipv6_fl_list; }; /* We currently use available bits from inet_sk(sk)->inet_flags, diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 1086256549fa..b6ec08072533 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -214,6 +214,7 @@ struct inet_sock { struct sock sk; #if IS_ENABLED(CONFIG_IPV6) struct ipv6_pinfo *pinet6; + struct ipv6_fl_socklist __rcu *ipv6_fl_list; #endif /* Socket demultiplex comparisons on incoming packets. */ #define inet_daddr sk.__sk_common.skc_daddr |