Merge branch 'listener_refactor'
Eric Dumazet says: ==================== inet: tcp listener refactoring, part 8 These patches prepare request socks being hashed into general ehash table : We declare 3 aliases (ireq_state, ireq_refcnt, ireq_family) Note that refcnt is not yet handled, this will be done later. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
commit
5ff0d16aac
|
@ -27,6 +27,7 @@
|
|||
#include <net/sock.h>
|
||||
#include <net/request_sock.h>
|
||||
#include <net/netns/hash.h>
|
||||
#include <net/tcp_states.h>
|
||||
|
||||
/** struct ip_options - IP Options
|
||||
*
|
||||
|
@ -79,6 +80,9 @@ struct inet_request_sock {
|
|||
#define ir_iif req.__req_common.skc_bound_dev_if
|
||||
#define ir_cookie req.__req_common.skc_cookie
|
||||
#define ireq_net req.__req_common.skc_net
|
||||
#define ireq_state req.__req_common.skc_state
|
||||
#define ireq_refcnt req.__req_common.skc_refcnt
|
||||
#define ireq_family req.__req_common.skc_family
|
||||
|
||||
kmemcheck_bitfield_begin(flags);
|
||||
u16 snd_wscale : 4,
|
||||
|
@ -249,6 +253,8 @@ static inline struct request_sock *inet_reqsk_alloc(struct request_sock_ops *ops
|
|||
if (req != NULL) {
|
||||
kmemcheck_annotate_bitfield(ireq, flags);
|
||||
ireq->opt = NULL;
|
||||
atomic64_set(&ireq->ir_cookie, 0);
|
||||
ireq->ireq_state = TCP_NEW_SYN_RECV;
|
||||
}
|
||||
|
||||
return req;
|
||||
|
|
|
@ -49,6 +49,8 @@ int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req);
|
|||
*/
|
||||
struct request_sock {
|
||||
struct sock_common __req_common;
|
||||
#define rsk_refcnt __req_common.skc_refcnt
|
||||
|
||||
struct request_sock *dl_next;
|
||||
u16 mss;
|
||||
u8 num_retrans; /* number of retransmits */
|
||||
|
@ -75,6 +77,11 @@ static inline struct request_sock *reqsk_alloc(const struct request_sock_ops *op
|
|||
return req;
|
||||
}
|
||||
|
||||
static inline struct request_sock *inet_reqsk(struct sock *sk)
|
||||
{
|
||||
return (struct request_sock *)sk;
|
||||
}
|
||||
|
||||
static inline void __reqsk_free(struct request_sock *req)
|
||||
{
|
||||
kmem_cache_free(req->rsk_ops->slab, req);
|
||||
|
@ -86,6 +93,12 @@ static inline void reqsk_free(struct request_sock *req)
|
|||
__reqsk_free(req);
|
||||
}
|
||||
|
||||
static inline void reqsk_put(struct request_sock *req)
|
||||
{
|
||||
if (atomic_dec_and_test(&req->rsk_refcnt))
|
||||
reqsk_free(req);
|
||||
}
|
||||
|
||||
extern int sysctl_max_syn_backlog;
|
||||
|
||||
/** struct listen_sock - listen state
|
||||
|
|
|
@ -1625,7 +1625,7 @@ static inline void sock_put(struct sock *sk)
|
|||
sk_free(sk);
|
||||
}
|
||||
/* Generic version of sock_put(), dealing with all sockets
|
||||
* (TCP_TIMEWAIT, ESTABLISHED...)
|
||||
* (TCP_TIMEWAIT, TCP_NEW_SYN_RECV, ESTABLISHED...)
|
||||
*/
|
||||
void sock_gen_put(struct sock *sk);
|
||||
|
||||
|
|
|
@ -25,6 +25,7 @@ enum {
|
|||
TCP_LAST_ACK,
|
||||
TCP_LISTEN,
|
||||
TCP_CLOSING, /* Now a valid state */
|
||||
TCP_NEW_SYN_RECV,
|
||||
|
||||
TCP_MAX_STATES /* Leave at the end! */
|
||||
};
|
||||
|
@ -44,7 +45,8 @@ enum {
|
|||
TCPF_CLOSE_WAIT = (1 << 8),
|
||||
TCPF_LAST_ACK = (1 << 9),
|
||||
TCPF_LISTEN = (1 << 10),
|
||||
TCPF_CLOSING = (1 << 11)
|
||||
TCPF_CLOSING = (1 << 11),
|
||||
TCPF_NEW_SYN_RECV = (1 << 12),
|
||||
};
|
||||
|
||||
#endif /* _LINUX_TCP_STATES_H */
|
||||
|
|
|
@ -1668,6 +1668,8 @@ void sock_edemux(struct sk_buff *skb)
|
|||
|
||||
if (sk->sk_state == TCP_TIME_WAIT)
|
||||
inet_twsk_put(inet_twsk(sk));
|
||||
else if (sk->sk_state == TCP_NEW_SYN_RECV)
|
||||
reqsk_put(inet_reqsk(sk));
|
||||
else
|
||||
sock_put(sk);
|
||||
}
|
||||
|
@ -2726,6 +2728,42 @@ static inline void release_proto_idx(struct proto *prot)
|
|||
}
|
||||
#endif
|
||||
|
||||
static void req_prot_cleanup(struct request_sock_ops *rsk_prot)
|
||||
{
|
||||
if (!rsk_prot)
|
||||
return;
|
||||
kfree(rsk_prot->slab_name);
|
||||
rsk_prot->slab_name = NULL;
|
||||
if (rsk_prot->slab) {
|
||||
kmem_cache_destroy(rsk_prot->slab);
|
||||
rsk_prot->slab = NULL;
|
||||
}
|
||||
}
|
||||
|
||||
static int req_prot_init(const struct proto *prot)
|
||||
{
|
||||
struct request_sock_ops *rsk_prot = prot->rsk_prot;
|
||||
|
||||
if (!rsk_prot)
|
||||
return 0;
|
||||
|
||||
rsk_prot->slab_name = kasprintf(GFP_KERNEL, "request_sock_%s",
|
||||
prot->name);
|
||||
if (!rsk_prot->slab_name)
|
||||
return -ENOMEM;
|
||||
|
||||
rsk_prot->slab = kmem_cache_create(rsk_prot->slab_name,
|
||||
rsk_prot->obj_size, 0,
|
||||
SLAB_HWCACHE_ALIGN, NULL);
|
||||
|
||||
if (!rsk_prot->slab) {
|
||||
pr_crit("%s: Can't create request sock SLAB cache!\n",
|
||||
prot->name);
|
||||
return -ENOMEM;
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
int proto_register(struct proto *prot, int alloc_slab)
|
||||
{
|
||||
if (alloc_slab) {
|
||||
|
@ -2739,21 +2777,8 @@ int proto_register(struct proto *prot, int alloc_slab)
|
|||
goto out;
|
||||
}
|
||||
|
||||
if (prot->rsk_prot != NULL) {
|
||||
prot->rsk_prot->slab_name = kasprintf(GFP_KERNEL, "request_sock_%s", prot->name);
|
||||
if (prot->rsk_prot->slab_name == NULL)
|
||||
goto out_free_sock_slab;
|
||||
|
||||
prot->rsk_prot->slab = kmem_cache_create(prot->rsk_prot->slab_name,
|
||||
prot->rsk_prot->obj_size, 0,
|
||||
SLAB_HWCACHE_ALIGN, NULL);
|
||||
|
||||
if (prot->rsk_prot->slab == NULL) {
|
||||
pr_crit("%s: Can't create request sock SLAB cache!\n",
|
||||
prot->name);
|
||||
goto out_free_request_sock_slab_name;
|
||||
}
|
||||
}
|
||||
if (req_prot_init(prot))
|
||||
goto out_free_request_sock_slab;
|
||||
|
||||
if (prot->twsk_prot != NULL) {
|
||||
prot->twsk_prot->twsk_slab_name = kasprintf(GFP_KERNEL, "tw_sock_%s", prot->name);
|
||||
|
@ -2782,14 +2807,8 @@ int proto_register(struct proto *prot, int alloc_slab)
|
|||
out_free_timewait_sock_slab_name:
|
||||
kfree(prot->twsk_prot->twsk_slab_name);
|
||||
out_free_request_sock_slab:
|
||||
if (prot->rsk_prot && prot->rsk_prot->slab) {
|
||||
kmem_cache_destroy(prot->rsk_prot->slab);
|
||||
prot->rsk_prot->slab = NULL;
|
||||
}
|
||||
out_free_request_sock_slab_name:
|
||||
if (prot->rsk_prot)
|
||||
kfree(prot->rsk_prot->slab_name);
|
||||
out_free_sock_slab:
|
||||
req_prot_cleanup(prot->rsk_prot);
|
||||
|
||||
kmem_cache_destroy(prot->slab);
|
||||
prot->slab = NULL;
|
||||
out:
|
||||
|
@ -2809,11 +2828,7 @@ void proto_unregister(struct proto *prot)
|
|||
prot->slab = NULL;
|
||||
}
|
||||
|
||||
if (prot->rsk_prot != NULL && prot->rsk_prot->slab != NULL) {
|
||||
kmem_cache_destroy(prot->rsk_prot->slab);
|
||||
kfree(prot->rsk_prot->slab_name);
|
||||
prot->rsk_prot->slab = NULL;
|
||||
}
|
||||
req_prot_cleanup(prot->rsk_prot);
|
||||
|
||||
if (prot->twsk_prot != NULL && prot->twsk_prot->twsk_slab != NULL) {
|
||||
kmem_cache_destroy(prot->twsk_prot->twsk_slab);
|
||||
|
|
|
@ -642,7 +642,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
|
|||
ireq->ir_loc_addr = ip_hdr(skb)->daddr;
|
||||
ireq->ir_rmt_addr = ip_hdr(skb)->saddr;
|
||||
write_pnet(&ireq->ireq_net, sock_net(sk));
|
||||
atomic64_set(&ireq->ir_cookie, 0);
|
||||
ireq->ireq_family = AF_INET;
|
||||
|
||||
/*
|
||||
* Step 3: Process LISTEN state
|
||||
|
|
|
@ -403,6 +403,8 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
|
|||
ireq = inet_rsk(req);
|
||||
ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
|
||||
ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
|
||||
write_pnet(&ireq->ireq_net, sock_net(sk));
|
||||
ireq->ireq_family = AF_INET6;
|
||||
|
||||
if (ipv6_opt_accepted(sk, skb, IP6CB(skb)) ||
|
||||
np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
|
||||
|
|
|
@ -718,7 +718,6 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk,
|
|||
const struct nlmsghdr *unlh)
|
||||
{
|
||||
const struct inet_request_sock *ireq = inet_rsk(req);
|
||||
struct inet_sock *inet = inet_sk(sk);
|
||||
struct inet_diag_msg *r;
|
||||
struct nlmsghdr *nlh;
|
||||
long tmo;
|
||||
|
@ -729,7 +728,7 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk,
|
|||
return -EMSGSIZE;
|
||||
|
||||
r = nlmsg_data(nlh);
|
||||
r->idiag_family = sk->sk_family;
|
||||
r->idiag_family = ireq->ireq_family;
|
||||
r->idiag_state = TCP_SYN_RECV;
|
||||
r->idiag_timer = 1;
|
||||
r->idiag_retrans = req->num_retrans;
|
||||
|
@ -744,7 +743,7 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk,
|
|||
if (tmo < 0)
|
||||
tmo = 0;
|
||||
|
||||
r->id.idiag_sport = inet->inet_sport;
|
||||
r->id.idiag_sport = htons(ireq->ir_num);
|
||||
r->id.idiag_dport = ireq->ir_rmt_port;
|
||||
|
||||
memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src));
|
||||
|
|
|
@ -262,6 +262,8 @@ void sock_gen_put(struct sock *sk)
|
|||
|
||||
if (sk->sk_state == TCP_TIME_WAIT)
|
||||
inet_twsk_free(inet_twsk(sk));
|
||||
else if (sk->sk_state == TCP_NEW_SYN_RECV)
|
||||
reqsk_free(inet_reqsk(sk));
|
||||
else
|
||||
sk_free(sk);
|
||||
}
|
||||
|
|
|
@ -347,6 +347,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
|
|||
treq->snt_synack = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsecr : 0;
|
||||
treq->listener = NULL;
|
||||
write_pnet(&ireq->ireq_net, sock_net(sk));
|
||||
ireq->ireq_family = AF_INET;
|
||||
|
||||
/* We throwed the options of the initial SYN away, so we hope
|
||||
* the ACK carries the same options again (see RFC1122 4.2.3.8)
|
||||
|
|
|
@ -5966,7 +5966,6 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
|
|||
tmp_opt.tstamp_ok = tmp_opt.saw_tstamp;
|
||||
tcp_openreq_init(req, &tmp_opt, skb, sk);
|
||||
write_pnet(&inet_rsk(req)->ireq_net, sock_net(sk));
|
||||
atomic64_set(&inet_rsk(req)->ir_cookie, 0);
|
||||
|
||||
af_ops->init_req(req, sk, skb);
|
||||
|
||||
|
|
|
@ -1228,6 +1228,7 @@ static void tcp_v4_init_req(struct request_sock *req, struct sock *sk,
|
|||
ireq->ir_rmt_addr = ip_hdr(skb)->saddr;
|
||||
ireq->no_srccheck = inet_sk(sk)->transparent;
|
||||
ireq->opt = tcp_v4_save_options(skb);
|
||||
ireq->ireq_family = AF_INET;
|
||||
}
|
||||
|
||||
static struct dst_entry *tcp_v4_route_req(struct sock *sk, struct flowi *fl,
|
||||
|
@ -2204,7 +2205,7 @@ void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo)
|
|||
}
|
||||
EXPORT_SYMBOL(tcp_proc_unregister);
|
||||
|
||||
static void get_openreq4(const struct sock *sk, const struct request_sock *req,
|
||||
static void get_openreq4(const struct request_sock *req,
|
||||
struct seq_file *f, int i, kuid_t uid)
|
||||
{
|
||||
const struct inet_request_sock *ireq = inet_rsk(req);
|
||||
|
@ -2214,7 +2215,7 @@ static void get_openreq4(const struct sock *sk, const struct request_sock *req,
|
|||
" %02X %08X:%08X %02X:%08lX %08X %5u %8d %u %d %pK",
|
||||
i,
|
||||
ireq->ir_loc_addr,
|
||||
ntohs(inet_sk(sk)->inet_sport),
|
||||
ireq->ir_num,
|
||||
ireq->ir_rmt_addr,
|
||||
ntohs(ireq->ir_rmt_port),
|
||||
TCP_SYN_RECV,
|
||||
|
@ -2225,7 +2226,7 @@ static void get_openreq4(const struct sock *sk, const struct request_sock *req,
|
|||
from_kuid_munged(seq_user_ns(f), uid),
|
||||
0, /* non standard timer */
|
||||
0, /* open_requests have no inode */
|
||||
atomic_read(&sk->sk_refcnt),
|
||||
0,
|
||||
req);
|
||||
}
|
||||
|
||||
|
@ -2332,7 +2333,7 @@ static int tcp4_seq_show(struct seq_file *seq, void *v)
|
|||
get_tcp4_sock(v, seq, st->num);
|
||||
break;
|
||||
case TCP_SEQ_STATE_OPENREQ:
|
||||
get_openreq4(st->syn_wait_sk, v, seq, st->num, st->uid);
|
||||
get_openreq4(v, seq, st->num, st->uid);
|
||||
break;
|
||||
}
|
||||
out:
|
||||
|
|
|
@ -196,6 +196,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
|
|||
ireq = inet_rsk(req);
|
||||
treq = tcp_rsk(req);
|
||||
treq->listener = NULL;
|
||||
write_pnet(&ireq->ireq_net, sock_net(sk));
|
||||
ireq->ireq_family = AF_INET6;
|
||||
|
||||
if (security_inet_conn_request(sk, skb, req))
|
||||
goto out_free;
|
||||
|
|
|
@ -749,6 +749,7 @@ static void tcp_v6_init_req(struct request_sock *req, struct sock *sk,
|
|||
atomic_inc(&skb->users);
|
||||
ireq->pktopts = skb;
|
||||
}
|
||||
ireq->ireq_family = AF_INET6;
|
||||
}
|
||||
|
||||
static struct dst_entry *tcp_v6_route_req(struct sock *sk, struct flowi *fl,
|
||||
|
@ -1689,7 +1690,7 @@ static void tcp_v6_destroy_sock(struct sock *sk)
|
|||
#ifdef CONFIG_PROC_FS
|
||||
/* Proc filesystem TCPv6 sock list dumping. */
|
||||
static void get_openreq6(struct seq_file *seq,
|
||||
const struct sock *sk, struct request_sock *req, int i, kuid_t uid)
|
||||
struct request_sock *req, int i, kuid_t uid)
|
||||
{
|
||||
int ttd = req->expires - jiffies;
|
||||
const struct in6_addr *src = &inet_rsk(req)->ir_v6_loc_addr;
|
||||
|
@ -1827,7 +1828,7 @@ static int tcp6_seq_show(struct seq_file *seq, void *v)
|
|||
get_tcp6_sock(seq, v, st->num);
|
||||
break;
|
||||
case TCP_SEQ_STATE_OPENREQ:
|
||||
get_openreq6(seq, st->syn_wait_sk, v, st->num, st->uid);
|
||||
get_openreq6(seq, v, st->num, st->uid);
|
||||
break;
|
||||
}
|
||||
out:
|
||||
|
|
Loading…
Reference in New Issue