diff options
| author | Eric Dumazet <edumazet@google.com> | 2015-10-08 19:33:21 -0700 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2015-10-12 19:28:20 -0700 |
| commit | 70da268b569d32a9fddeea85dc18043de9d89f89 (patch) | |
| tree | 6c698924212dcbfbb155e794f6089d2226889f0f /include/net | |
| parent | c7d39e32632e5db9dc4da51198b76d8c315946ff (diff) | |
| download | linux-70da268b569d32a9fddeea85dc18043de9d89f89.tar.bz2 | |
net: SO_INCOMING_CPU setsockopt() support
SO_INCOMING_CPU as added in commit 2c8c56e15df3 was a getsockopt() command
to fetch incoming cpu handling a particular TCP flow after accept()
This commits adds setsockopt() support and extends SO_REUSEPORT selection
logic : If a TCP listener or UDP socket has this option set, a packet is
delivered to this socket only if CPU handling the packet matches the specified
one.
This allows to build very efficient TCP servers, using one listener per
RX queue, as the associated TCP listener should only accept flows handled
in softirq by the same cpu.
This provides optimal NUMA behavior and keep cpu caches hot.
Note that __inet_lookup_listener() still has to iterate over the list of
all listeners. Following patch puts sk_refcnt in a different cache line
to let this iteration hit only shared and read mostly cache lines.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'include/net')
| -rw-r--r-- | include/net/sock.h | 10 |
1 files changed, 4 insertions, 6 deletions
diff --git a/include/net/sock.h b/include/net/sock.h index 9322cafd191b..cf54739f30d5 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -150,6 +150,7 @@ typedef __u64 __bitwise __addrpair; * @skc_node: main hash linkage for various protocol lookup tables * @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol * @skc_tx_queue_mapping: tx queue number for this connection + * @skc_incoming_cpu: record/match cpu processing incoming packets * @skc_refcnt: reference count * * This is the minimal network layer representation of sockets, the header @@ -212,6 +213,8 @@ struct sock_common { struct hlist_nulls_node skc_nulls_node; }; int skc_tx_queue_mapping; + int skc_incoming_cpu; + atomic_t skc_refcnt; /* private: */ int skc_dontcopy_end[0]; @@ -274,7 +277,6 @@ struct cg_proto; * @sk_rcvtimeo: %SO_RCVTIMEO setting * @sk_sndtimeo: %SO_SNDTIMEO setting * @sk_rxhash: flow hash received from netif layer - * @sk_incoming_cpu: record cpu processing incoming packets * @sk_txhash: computed flow hash for use on transmit * @sk_filter: socket filtering instructions * @sk_timer: sock cleanup timer @@ -331,6 +333,7 @@ struct sock { #define sk_v6_daddr __sk_common.skc_v6_daddr #define sk_v6_rcv_saddr __sk_common.skc_v6_rcv_saddr #define sk_cookie __sk_common.skc_cookie +#define sk_incoming_cpu __sk_common.skc_incoming_cpu socket_lock_t sk_lock; struct sk_buff_head sk_receive_queue; @@ -353,11 +356,6 @@ struct sock { #ifdef CONFIG_RPS __u32 sk_rxhash; #endif - u16 sk_incoming_cpu; - /* 16bit hole - * Warned : sk_incoming_cpu can be set from softirq, - * Do not use this hole without fully understanding possible issues. - */ __u32 sk_txhash; #ifdef CONFIG_NET_RX_BUSY_POLL |