raw: use net_hash_mix() in hash function
Some applications seem to rely on RAW sockets. If they use private netns, we can avoid piling all RAW sockets bound to a given protocol into a single bucket. Also place (struct raw_hashinfo).lock into its own cache line to limit false sharing. Alternative would be to have per-netns hashtables, but this seems too expensive for most netns where RAW sockets are not used. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This commit is contained in:
parent
42186e6c00
commit
6579f5bacc
|
@ -15,6 +15,8 @@
|
||||||
|
|
||||||
#include <net/inet_sock.h>
|
#include <net/inet_sock.h>
|
||||||
#include <net/protocol.h>
|
#include <net/protocol.h>
|
||||||
|
#include <net/netns/hash.h>
|
||||||
|
#include <linux/hash.h>
|
||||||
#include <linux/icmp.h>
|
#include <linux/icmp.h>
|
||||||
|
|
||||||
extern struct proto raw_prot;
|
extern struct proto raw_prot;
|
||||||
|
@ -29,13 +31,20 @@ int raw_local_deliver(struct sk_buff *, int);
|
||||||
|
|
||||||
int raw_rcv(struct sock *, struct sk_buff *);
|
int raw_rcv(struct sock *, struct sk_buff *);
|
||||||
|
|
||||||
#define RAW_HTABLE_SIZE MAX_INET_PROTOS
|
#define RAW_HTABLE_LOG 8
|
||||||
|
#define RAW_HTABLE_SIZE (1U << RAW_HTABLE_LOG)
|
||||||
|
|
||||||
struct raw_hashinfo {
|
struct raw_hashinfo {
|
||||||
spinlock_t lock;
|
spinlock_t lock;
|
||||||
struct hlist_nulls_head ht[RAW_HTABLE_SIZE];
|
|
||||||
|
struct hlist_nulls_head ht[RAW_HTABLE_SIZE] ____cacheline_aligned;
|
||||||
};
|
};
|
||||||
|
|
||||||
|
static inline u32 raw_hashfunc(const struct net *net, u32 proto)
|
||||||
|
{
|
||||||
|
return hash_32(net_hash_mix(net) ^ proto, RAW_HTABLE_LOG);
|
||||||
|
}
|
||||||
|
|
||||||
static inline void raw_hashinfo_init(struct raw_hashinfo *hashinfo)
|
static inline void raw_hashinfo_init(struct raw_hashinfo *hashinfo)
|
||||||
{
|
{
|
||||||
int i;
|
int i;
|
||||||
|
|
|
@ -93,7 +93,7 @@ int raw_hash_sk(struct sock *sk)
|
||||||
struct raw_hashinfo *h = sk->sk_prot->h.raw_hash;
|
struct raw_hashinfo *h = sk->sk_prot->h.raw_hash;
|
||||||
struct hlist_nulls_head *hlist;
|
struct hlist_nulls_head *hlist;
|
||||||
|
|
||||||
hlist = &h->ht[inet_sk(sk)->inet_num & (RAW_HTABLE_SIZE - 1)];
|
hlist = &h->ht[raw_hashfunc(sock_net(sk), inet_sk(sk)->inet_num)];
|
||||||
|
|
||||||
spin_lock(&h->lock);
|
spin_lock(&h->lock);
|
||||||
__sk_nulls_add_node_rcu(sk, hlist);
|
__sk_nulls_add_node_rcu(sk, hlist);
|
||||||
|
@ -160,9 +160,9 @@ static int icmp_filter(const struct sock *sk, const struct sk_buff *skb)
|
||||||
* RFC 1122: SHOULD pass TOS value up to the transport layer.
|
* RFC 1122: SHOULD pass TOS value up to the transport layer.
|
||||||
* -> It does. And not only TOS, but all IP header.
|
* -> It does. And not only TOS, but all IP header.
|
||||||
*/
|
*/
|
||||||
static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash)
|
static int raw_v4_input(struct net *net, struct sk_buff *skb,
|
||||||
|
const struct iphdr *iph, int hash)
|
||||||
{
|
{
|
||||||
struct net *net = dev_net(skb->dev);
|
|
||||||
struct hlist_nulls_head *hlist;
|
struct hlist_nulls_head *hlist;
|
||||||
struct hlist_nulls_node *hnode;
|
struct hlist_nulls_node *hnode;
|
||||||
int sdif = inet_sdif(skb);
|
int sdif = inet_sdif(skb);
|
||||||
|
@ -193,9 +193,10 @@ static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash)
|
||||||
|
|
||||||
int raw_local_deliver(struct sk_buff *skb, int protocol)
|
int raw_local_deliver(struct sk_buff *skb, int protocol)
|
||||||
{
|
{
|
||||||
int hash = protocol & (RAW_HTABLE_SIZE - 1);
|
struct net *net = dev_net(skb->dev);
|
||||||
|
|
||||||
return raw_v4_input(skb, ip_hdr(skb), hash);
|
return raw_v4_input(net, skb, ip_hdr(skb),
|
||||||
|
raw_hashfunc(net, protocol));
|
||||||
}
|
}
|
||||||
|
|
||||||
static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info)
|
static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info)
|
||||||
|
@ -271,7 +272,7 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info)
|
||||||
struct sock *sk;
|
struct sock *sk;
|
||||||
int hash;
|
int hash;
|
||||||
|
|
||||||
hash = protocol & (RAW_HTABLE_SIZE - 1);
|
hash = raw_hashfunc(net, protocol);
|
||||||
hlist = &raw_v4_hashinfo.ht[hash];
|
hlist = &raw_v4_hashinfo.ht[hash];
|
||||||
|
|
||||||
rcu_read_lock();
|
rcu_read_lock();
|
||||||
|
|
|
@ -152,7 +152,7 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr)
|
||||||
saddr = &ipv6_hdr(skb)->saddr;
|
saddr = &ipv6_hdr(skb)->saddr;
|
||||||
daddr = saddr + 1;
|
daddr = saddr + 1;
|
||||||
|
|
||||||
hash = nexthdr & (RAW_HTABLE_SIZE - 1);
|
hash = raw_hashfunc(net, nexthdr);
|
||||||
hlist = &raw_v6_hashinfo.ht[hash];
|
hlist = &raw_v6_hashinfo.ht[hash];
|
||||||
rcu_read_lock();
|
rcu_read_lock();
|
||||||
sk_nulls_for_each(sk, hnode, hlist) {
|
sk_nulls_for_each(sk, hnode, hlist) {
|
||||||
|
@ -338,7 +338,7 @@ void raw6_icmp_error(struct sk_buff *skb, int nexthdr,
|
||||||
struct sock *sk;
|
struct sock *sk;
|
||||||
int hash;
|
int hash;
|
||||||
|
|
||||||
hash = nexthdr & (RAW_HTABLE_SIZE - 1);
|
hash = raw_hashfunc(net, nexthdr);
|
||||||
hlist = &raw_v6_hashinfo.ht[hash];
|
hlist = &raw_v6_hashinfo.ht[hash];
|
||||||
rcu_read_lock();
|
rcu_read_lock();
|
||||||
sk_nulls_for_each(sk, hnode, hlist) {
|
sk_nulls_for_each(sk, hnode, hlist) {
|
||||||
|
|
Loading…
Reference in New Issue