diff options
| author | Eric Dumazet <eric.dumazet@gmail.com> | 2010-11-30 19:04:07 +0000 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2010-12-09 20:05:58 -0800 |
| commit | 68835aba4d9b74e2f94106d13b6a4bddc447c4c8 (patch) | |
| tree | 468a9465acfa027791facef13fb6ef5129dda257 /include/net/inet_timewait_sock.h | |
| parent | defb3519a64141608725e2dac5a5aa9a3c644bae (diff) | |
net: optimize INET input path further
Followup of commit b178bb3dfc30 (net: reorder struct sock fields)
Optimize INET input path a bit further, by :
1) moving sk_refcnt close to sk_lock.
This reduces number of dirtied cache lines by one on 64bit arches (and
64 bytes cache line size).
2) moving inet_daddr & inet_rcv_saddr at the beginning of sk
(same cache line than hash / family / bound_dev_if / nulls_node)
This reduces number of accessed cache lines in lookups by one, and dont
increase size of inet and timewait socks.
inet and tw sockets now share same place-holder for these fields.
Before patch :
offsetof(struct sock, sk_refcnt) = 0x10
offsetof(struct sock, sk_lock) = 0x40
offsetof(struct sock, sk_receive_queue) = 0x60
offsetof(struct inet_sock, inet_daddr) = 0x270
offsetof(struct inet_sock, inet_rcv_saddr) = 0x274
After patch :
offsetof(struct sock, sk_refcnt) = 0x44
offsetof(struct sock, sk_lock) = 0x48
offsetof(struct sock, sk_receive_queue) = 0x68
offsetof(struct inet_sock, inet_daddr) = 0x0
offsetof(struct inet_sock, inet_rcv_saddr) = 0x4
compute_score() (udp or tcp) now use a single cache line per ignored
item, instead of two.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'include/net/inet_timewait_sock.h')
| -rw-r--r-- | include/net/inet_timewait_sock.h | 20 |
1 files changed, 7 insertions, 13 deletions
diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index a066fdd50da..17404b5388a 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -88,12 +88,6 @@ extern void inet_twdr_hangman(unsigned long data); extern void inet_twdr_twkill_work(struct work_struct *work); extern void inet_twdr_twcal_tick(unsigned long data); -#if (BITS_PER_LONG == 64) -#define INET_TIMEWAIT_ADDRCMP_ALIGN_BYTES 8 -#else -#define INET_TIMEWAIT_ADDRCMP_ALIGN_BYTES 4 -#endif - struct inet_bind_bucket; /* @@ -117,15 +111,15 @@ struct inet_timewait_sock { #define tw_hash __tw_common.skc_hash #define tw_prot __tw_common.skc_prot #define tw_net __tw_common.skc_net +#define tw_daddr __tw_common.skc_daddr +#define tw_rcv_saddr __tw_common.skc_rcv_saddr int tw_timeout; volatile unsigned char tw_substate; - /* 3 bits hole, try to pack */ unsigned char tw_rcv_wscale; + /* Socket demultiplex comparisons on incoming packets. */ - /* these five are in inet_sock */ + /* these three are in inet_sock */ __be16 tw_sport; - __be32 tw_daddr __attribute__((aligned(INET_TIMEWAIT_ADDRCMP_ALIGN_BYTES))); - __be32 tw_rcv_saddr; __be16 tw_dport; __u16 tw_num; kmemcheck_bitfield_begin(flags); @@ -191,10 +185,10 @@ static inline struct inet_timewait_sock *inet_twsk(const struct sock *sk) return (struct inet_timewait_sock *)sk; } -static inline __be32 inet_rcv_saddr(const struct sock *sk) +static inline __be32 sk_rcv_saddr(const struct sock *sk) { - return likely(sk->sk_state != TCP_TIME_WAIT) ? - inet_sk(sk)->inet_rcv_saddr : inet_twsk(sk)->tw_rcv_saddr; +/* both inet_sk() and inet_twsk() store rcv_saddr in skc_rcv_saddr */ + return sk->__sk_common.skc_rcv_saddr; } extern void inet_twsk_put(struct inet_timewait_sock *tw); |