diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2013-05-01 14:08:52 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2013-05-01 14:08:52 -0700 |
commit | 73287a43cc79ca06629a88d1a199cd283f42456a (patch) | |
tree | acf4456e260115bea77ee31a29f10ce17f0db45c /net/netfilter/ipvs/ip_vs_conn.c | |
parent | 251df49db3327c64bf917bfdba94491fde2b4ee0 (diff) | |
parent | 20074f357da4a637430aec2879c9d864c5d2c23c (diff) | |
download | linux-73287a43cc79ca06629a88d1a199cd283f42456a.tar.bz2 |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
"Highlights (1721 non-merge commits, this has to be a record of some
sort):
1) Add 'random' mode to team driver, from Jiri Pirko and Eric
Dumazet.
2) Make it so that any driver that supports configuration of multiple
MAC addresses can provide the forwarding database add and del
calls by providing a default implementation and hooking that up if
the driver doesn't have an explicit set of handlers. From Vlad
Yasevich.
3) Support GSO segmentation over tunnels and other encapsulating
devices such as VXLAN, from Pravin B Shelar.
4) Support L2 GRE tunnels in the flow dissector, from Michael Dalton.
5) Implement Tail Loss Probe (TLP) detection in TCP, from Nandita
Dukkipati.
6) In the PHY layer, allow supporting wake-on-lan in situations where
the PHY registers have to be written for it to be configured.
Use it to support wake-on-lan in mv643xx_eth.
From Michael Stapelberg.
7) Significantly improve firewire IPV6 support, from YOSHIFUJI
Hideaki.
8) Allow multiple packets to be sent in a single transmission using
network coding in batman-adv, from Martin Hundebøll.
9) Add support for T5 cxgb4 chips, from Santosh Rastapur.
10) Generalize the VXLAN forwarding tables so that there is more
flexibility in configurating various aspects of the endpoints.
From David Stevens.
11) Support RSS and TSO in hardware over GRE tunnels in bxn2x driver,
from Dmitry Kravkov.
12) Zero copy support in nfnelink_queue, from Eric Dumazet and Pablo
Neira Ayuso.
13) Start adding networking selftests.
14) In situations of overload on the same AF_PACKET fanout socket, or
per-cpu packet receive queue, minimize drop by distributing the
load to other cpus/fanouts. From Willem de Bruijn and Eric
Dumazet.
15) Add support for new payload offset BPF instruction, from Daniel
Borkmann.
16) Convert several drivers over to mdoule_platform_driver(), from
Sachin Kamat.
17) Provide a minimal BPF JIT image disassembler userspace tool, from
Daniel Borkmann.
18) Rewrite F-RTO implementation in TCP to match the final
specification of it in RFC4138 and RFC5682. From Yuchung Cheng.
19) Provide netlink socket diag of netlink sockets ("Yo dawg, I hear
you like netlink, so I implemented netlink dumping of netlink
sockets.") From Andrey Vagin.
20) Remove ugly passing of rtnetlink attributes into rtnl_doit
functions, from Thomas Graf.
21) Allow userspace to be able to see if a configuration change occurs
in the middle of an address or device list dump, from Nicolas
Dichtel.
22) Support RFC3168 ECN protection for ipv6 fragments, from Hannes
Frederic Sowa.
23) Increase accuracy of packet length used by packet scheduler, from
Jason Wang.
24) Beginning set of changes to make ipv4/ipv6 fragment handling more
scalable and less susceptible to overload and locking contention,
from Jesper Dangaard Brouer.
25) Get rid of using non-type-safe NLMSG_* macros and use nlmsg_*()
instead. From Hong Zhiguo.
26) Optimize route usage in IPVS by avoiding reference counting where
possible, from Julian Anastasov.
27) Convert IPVS schedulers to RCU, also from Julian Anastasov.
28) Support cpu fanouts in xt_NFQUEUE netfilter target, from Holger
Eitzenberger.
29) Network namespace support for nf_log, ebt_log, xt_LOG, ipt_ULOG,
nfnetlink_log, and nfnetlink_queue. From Gao feng.
30) Implement RFC3168 ECN protection, from Hannes Frederic Sowa.
31) Support several new r8169 chips, from Hayes Wang.
32) Support tokenized interface identifiers in ipv6, from Daniel
Borkmann.
33) Use usbnet_link_change() helper in USB net driver, from Ming Lei.
34) Add 802.1ad vlan offload support, from Patrick McHardy.
35) Support mmap() based netlink communication, also from Patrick
McHardy.
36) Support HW timestamping in mlx4 driver, from Amir Vadai.
37) Rationalize AF_PACKET packet timestamping when transmitting, from
Willem de Bruijn and Daniel Borkmann.
38) Bring parity to what's provided by /proc/net/packet socket dumping
and the info provided by netlink socket dumping of AF_PACKET
sockets. From Nicolas Dichtel.
39) Fix peeking beyond zero sized SKBs in AF_UNIX, from Benjamin
Poirier"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1722 commits)
filter: fix va_list build error
af_unix: fix a fatal race with bit fields
bnx2x: Prevent memory leak when cnic is absent
bnx2x: correct reading of speed capabilities
net: sctp: attribute printl with __printf for gcc fmt checks
netlink: kconfig: move mmap i/o into netlink kconfig
netpoll: convert mutex into a semaphore
netlink: Fix skb ref counting.
net_sched: act_ipt forward compat with xtables
mlx4_en: fix a build error on 32bit arches
Revert "bnx2x: allow nvram test to run when device is down"
bridge: avoid OOPS if root port not found
drivers: net: cpsw: fix kernel warn on cpsw irq enable
sh_eth: use random MAC address if no valid one supplied
3c509.c: call SET_NETDEV_DEV for all device types (ISA/ISAPnP/EISA)
tg3: fix to append hardware time stamping flags
unix/stream: fix peeking with an offset larger than data in queue
unix/dgram: fix peeking with an offset larger than data in queue
unix/dgram: peek beyond 0-sized skbs
openvswitch: Remove unneeded ovs_netdev_get_ifindex()
...
Diffstat (limited to 'net/netfilter/ipvs/ip_vs_conn.c')
-rw-r--r-- | net/netfilter/ipvs/ip_vs_conn.c | 312 |
1 files changed, 168 insertions, 144 deletions
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 704e514e02ab..a083bda322b6 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -79,51 +79,21 @@ static unsigned int ip_vs_conn_rnd __read_mostly; struct ip_vs_aligned_lock { - rwlock_t l; + spinlock_t l; } __attribute__((__aligned__(SMP_CACHE_BYTES))); /* lock array for conn table */ static struct ip_vs_aligned_lock __ip_vs_conntbl_lock_array[CT_LOCKARRAY_SIZE] __cacheline_aligned; -static inline void ct_read_lock(unsigned int key) -{ - read_lock(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l); -} - -static inline void ct_read_unlock(unsigned int key) -{ - read_unlock(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l); -} - -static inline void ct_write_lock(unsigned int key) -{ - write_lock(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l); -} - -static inline void ct_write_unlock(unsigned int key) -{ - write_unlock(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l); -} - -static inline void ct_read_lock_bh(unsigned int key) -{ - read_lock_bh(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l); -} - -static inline void ct_read_unlock_bh(unsigned int key) -{ - read_unlock_bh(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l); -} - static inline void ct_write_lock_bh(unsigned int key) { - write_lock_bh(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l); + spin_lock_bh(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l); } static inline void ct_write_unlock_bh(unsigned int key) { - write_unlock_bh(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l); + spin_unlock_bh(&__ip_vs_conntbl_lock_array[key&CT_LOCKARRAY_MASK].l); } @@ -197,13 +167,13 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp) /* Hash by protocol, client address and port */ hash = ip_vs_conn_hashkey_conn(cp); - ct_write_lock(hash); + ct_write_lock_bh(hash); spin_lock(&cp->lock); if (!(cp->flags & IP_VS_CONN_F_HASHED)) { - hlist_add_head(&cp->c_list, &ip_vs_conn_tab[hash]); cp->flags |= IP_VS_CONN_F_HASHED; atomic_inc(&cp->refcnt); + hlist_add_head_rcu(&cp->c_list, &ip_vs_conn_tab[hash]); ret = 1; } else { pr_err("%s(): request for already hashed, called from %pF\n", @@ -212,7 +182,7 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp) } spin_unlock(&cp->lock); - ct_write_unlock(hash); + ct_write_unlock_bh(hash); return ret; } @@ -220,7 +190,7 @@ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp) /* * UNhashes ip_vs_conn from ip_vs_conn_tab. - * returns bool success. + * returns bool success. Caller should hold conn reference. */ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp) { @@ -230,11 +200,11 @@ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp) /* unhash it and decrease its reference counter */ hash = ip_vs_conn_hashkey_conn(cp); - ct_write_lock(hash); + ct_write_lock_bh(hash); spin_lock(&cp->lock); if (cp->flags & IP_VS_CONN_F_HASHED) { - hlist_del(&cp->c_list); + hlist_del_rcu(&cp->c_list); cp->flags &= ~IP_VS_CONN_F_HASHED; atomic_dec(&cp->refcnt); ret = 1; @@ -242,7 +212,37 @@ static inline int ip_vs_conn_unhash(struct ip_vs_conn *cp) ret = 0; spin_unlock(&cp->lock); - ct_write_unlock(hash); + ct_write_unlock_bh(hash); + + return ret; +} + +/* Try to unlink ip_vs_conn from ip_vs_conn_tab. + * returns bool success. + */ +static inline bool ip_vs_conn_unlink(struct ip_vs_conn *cp) +{ + unsigned int hash; + bool ret; + + hash = ip_vs_conn_hashkey_conn(cp); + + ct_write_lock_bh(hash); + spin_lock(&cp->lock); + + if (cp->flags & IP_VS_CONN_F_HASHED) { + ret = false; + /* Decrease refcnt and unlink conn only if we are last user */ + if (atomic_cmpxchg(&cp->refcnt, 1, 0) == 1) { + hlist_del_rcu(&cp->c_list); + cp->flags &= ~IP_VS_CONN_F_HASHED; + ret = true; + } + } else + ret = atomic_read(&cp->refcnt) ? false : true; + + spin_unlock(&cp->lock); + ct_write_unlock_bh(hash); return ret; } @@ -262,24 +262,25 @@ __ip_vs_conn_in_get(const struct ip_vs_conn_param *p) hash = ip_vs_conn_hashkey_param(p, false); - ct_read_lock(hash); + rcu_read_lock(); - hlist_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { - if (cp->af == p->af && - p->cport == cp->cport && p->vport == cp->vport && + hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[hash], c_list) { + if (p->cport == cp->cport && p->vport == cp->vport && + cp->af == p->af && ip_vs_addr_equal(p->af, p->caddr, &cp->caddr) && ip_vs_addr_equal(p->af, p->vaddr, &cp->vaddr) && ((!p->cport) ^ (!(cp->flags & IP_VS_CONN_F_NO_CPORT))) && p->protocol == cp->protocol && ip_vs_conn_net_eq(cp, p->net)) { + if (!__ip_vs_conn_get(cp)) + continue; /* HIT */ - atomic_inc(&cp->refcnt); - ct_read_unlock(hash); + rcu_read_unlock(); return cp; } } - ct_read_unlock(hash); + rcu_read_unlock(); return NULL; } @@ -346,14 +347,16 @@ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p) hash = ip_vs_conn_hashkey_param(p, false); - ct_read_lock(hash); + rcu_read_lock(); - hlist_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { - if (!ip_vs_conn_net_eq(cp, p->net)) - continue; - if (p->pe_data && p->pe->ct_match) { - if (p->pe == cp->pe && p->pe->ct_match(p, cp)) - goto out; + hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[hash], c_list) { + if (unlikely(p->pe_data && p->pe->ct_match)) { + if (!ip_vs_conn_net_eq(cp, p->net)) + continue; + if (p->pe == cp->pe && p->pe->ct_match(p, cp)) { + if (__ip_vs_conn_get(cp)) + goto out; + } continue; } @@ -363,17 +366,18 @@ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p) * p->vaddr is a fwmark */ ip_vs_addr_equal(p->protocol == IPPROTO_IP ? AF_UNSPEC : p->af, p->vaddr, &cp->vaddr) && - p->cport == cp->cport && p->vport == cp->vport && + p->vport == cp->vport && p->cport == cp->cport && cp->flags & IP_VS_CONN_F_TEMPLATE && - p->protocol == cp->protocol) - goto out; + p->protocol == cp->protocol && + ip_vs_conn_net_eq(cp, p->net)) { + if (__ip_vs_conn_get(cp)) + goto out; + } } cp = NULL; out: - if (cp) - atomic_inc(&cp->refcnt); - ct_read_unlock(hash); + rcu_read_unlock(); IP_VS_DBG_BUF(9, "template lookup/in %s %s:%d->%s:%d %s\n", ip_vs_proto_name(p->protocol), @@ -398,23 +402,24 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p) */ hash = ip_vs_conn_hashkey_param(p, true); - ct_read_lock(hash); + rcu_read_lock(); - hlist_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { - if (cp->af == p->af && - p->vport == cp->cport && p->cport == cp->dport && + hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[hash], c_list) { + if (p->vport == cp->cport && p->cport == cp->dport && + cp->af == p->af && ip_vs_addr_equal(p->af, p->vaddr, &cp->caddr) && ip_vs_addr_equal(p->af, p->caddr, &cp->daddr) && p->protocol == cp->protocol && ip_vs_conn_net_eq(cp, p->net)) { + if (!__ip_vs_conn_get(cp)) + continue; /* HIT */ - atomic_inc(&cp->refcnt); ret = cp; break; } } - ct_read_unlock(hash); + rcu_read_unlock(); IP_VS_DBG_BUF(9, "lookup/out %s %s:%d->%s:%d %s\n", ip_vs_proto_name(p->protocol), @@ -457,13 +462,13 @@ void ip_vs_conn_put(struct ip_vs_conn *cp) void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport) { if (ip_vs_conn_unhash(cp)) { - spin_lock(&cp->lock); + spin_lock_bh(&cp->lock); if (cp->flags & IP_VS_CONN_F_NO_CPORT) { atomic_dec(&ip_vs_conn_no_cport_cnt); cp->flags &= ~IP_VS_CONN_F_NO_CPORT; cp->cport = cport; } - spin_unlock(&cp->lock); + spin_unlock_bh(&cp->lock); /* hash on new dport */ ip_vs_conn_hash(cp); @@ -549,7 +554,7 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest) return; /* Increase the refcnt counter of the dest */ - atomic_inc(&dest->refcnt); + ip_vs_dest_hold(dest); conn_flags = atomic_read(&dest->conn_flags); if (cp->protocol != IPPROTO_UDP) @@ -606,20 +611,22 @@ ip_vs_bind_dest(struct ip_vs_conn *cp, struct ip_vs_dest *dest) * Check if there is a destination for the connection, if so * bind the connection to the destination. */ -struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp) +void ip_vs_try_bind_dest(struct ip_vs_conn *cp) { struct ip_vs_dest *dest; + rcu_read_lock(); dest = ip_vs_find_dest(ip_vs_conn_net(cp), cp->af, &cp->daddr, cp->dport, &cp->vaddr, cp->vport, cp->protocol, cp->fwmark, cp->flags); if (dest) { struct ip_vs_proto_data *pd; - spin_lock(&cp->lock); + spin_lock_bh(&cp->lock); if (cp->dest) { - spin_unlock(&cp->lock); - return dest; + spin_unlock_bh(&cp->lock); + rcu_read_unlock(); + return; } /* Applications work depending on the forwarding method @@ -628,7 +635,7 @@ struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp) ip_vs_unbind_app(cp); ip_vs_bind_dest(cp, dest); - spin_unlock(&cp->lock); + spin_unlock_bh(&cp->lock); /* Update its packet transmitter */ cp->packet_xmit = NULL; @@ -643,7 +650,7 @@ struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp) if (pd && atomic_read(&pd->appcnt)) ip_vs_bind_app(cp, pd->pp); } - return dest; + rcu_read_unlock(); } @@ -695,12 +702,7 @@ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp) dest->flags &= ~IP_VS_DEST_F_OVERLOAD; } - /* - * Simply decrease the refcnt of the dest, because the - * dest will be either in service's destination list - * or in the trash. - */ - atomic_dec(&dest->refcnt); + ip_vs_dest_put(dest); } static int expire_quiescent_template(struct netns_ipvs *ipvs, @@ -757,41 +759,36 @@ int ip_vs_check_template(struct ip_vs_conn *ct) * Simply decrease the refcnt of the template, * don't restart its timer. */ - atomic_dec(&ct->refcnt); + __ip_vs_conn_put(ct); return 0; } return 1; } +static void ip_vs_conn_rcu_free(struct rcu_head *head) +{ + struct ip_vs_conn *cp = container_of(head, struct ip_vs_conn, + rcu_head); + + ip_vs_pe_put(cp->pe); + kfree(cp->pe_data); + kmem_cache_free(ip_vs_conn_cachep, cp); +} + static void ip_vs_conn_expire(unsigned long data) { struct ip_vs_conn *cp = (struct ip_vs_conn *)data; struct net *net = ip_vs_conn_net(cp); struct netns_ipvs *ipvs = net_ipvs(net); - cp->timeout = 60*HZ; - - /* - * hey, I'm using it - */ - atomic_inc(&cp->refcnt); - /* * do I control anybody? */ if (atomic_read(&cp->n_control)) goto expire_later; - /* - * unhash it if it is hashed in the conn table - */ - if (!ip_vs_conn_unhash(cp) && !(cp->flags & IP_VS_CONN_F_ONE_PACKET)) - goto expire_later; - - /* - * refcnt==1 implies I'm the only one referrer - */ - if (likely(atomic_read(&cp->refcnt) == 1)) { + /* Unlink conn if not referenced anymore */ + if (likely(ip_vs_conn_unlink(cp))) { /* delete the timer if it is activated by other users */ del_timer(&cp->timer); @@ -810,38 +807,41 @@ static void ip_vs_conn_expire(unsigned long data) ip_vs_conn_drop_conntrack(cp); } - ip_vs_pe_put(cp->pe); - kfree(cp->pe_data); if (unlikely(cp->app != NULL)) ip_vs_unbind_app(cp); ip_vs_unbind_dest(cp); if (cp->flags & IP_VS_CONN_F_NO_CPORT) atomic_dec(&ip_vs_conn_no_cport_cnt); + call_rcu(&cp->rcu_head, ip_vs_conn_rcu_free); atomic_dec(&ipvs->conn_count); - - kmem_cache_free(ip_vs_conn_cachep, cp); return; } - /* hash it back to the table */ - ip_vs_conn_hash(cp); - expire_later: - IP_VS_DBG(7, "delayed: conn->refcnt-1=%d conn->n_control=%d\n", - atomic_read(&cp->refcnt)-1, + IP_VS_DBG(7, "delayed: conn->refcnt=%d conn->n_control=%d\n", + atomic_read(&cp->refcnt), atomic_read(&cp->n_control)); + atomic_inc(&cp->refcnt); + cp->timeout = 60*HZ; + if (ipvs->sync_state & IP_VS_STATE_MASTER) ip_vs_sync_conn(net, cp, sysctl_sync_threshold(ipvs)); ip_vs_conn_put(cp); } - +/* Modify timer, so that it expires as soon as possible. + * Can be called without reference only if under RCU lock. + */ void ip_vs_conn_expire_now(struct ip_vs_conn *cp) { - if (del_timer(&cp->timer)) - mod_timer(&cp->timer, jiffies); + /* Using mod_timer_pending will ensure the timer is not + * modified after the final del_timer in ip_vs_conn_expire. + */ + if (timer_pending(&cp->timer) && + time_after(cp->timer.expires, jiffies)) + mod_timer_pending(&cp->timer, jiffies); } @@ -858,7 +858,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, struct ip_vs_proto_data *pd = ip_vs_proto_data_get(p->net, p->protocol); - cp = kmem_cache_zalloc(ip_vs_conn_cachep, GFP_ATOMIC); + cp = kmem_cache_alloc(ip_vs_conn_cachep, GFP_ATOMIC); if (cp == NULL) { IP_VS_ERR_RL("%s(): no memory\n", __func__); return NULL; @@ -869,13 +869,13 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, ip_vs_conn_net_set(cp, p->net); cp->af = p->af; cp->protocol = p->protocol; - ip_vs_addr_copy(p->af, &cp->caddr, p->caddr); + ip_vs_addr_set(p->af, &cp->caddr, p->caddr); cp->cport = p->cport; - ip_vs_addr_copy(p->af, &cp->vaddr, p->vaddr); + ip_vs_addr_set(p->af, &cp->vaddr, p->vaddr); cp->vport = p->vport; /* proto should only be IPPROTO_IP if d_addr is a fwmark */ - ip_vs_addr_copy(p->protocol == IPPROTO_IP ? AF_UNSPEC : p->af, - &cp->daddr, daddr); + ip_vs_addr_set(p->protocol == IPPROTO_IP ? AF_UNSPEC : p->af, + &cp->daddr, daddr); cp->dport = dport; cp->flags = flags; cp->fwmark = fwmark; @@ -884,6 +884,10 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, cp->pe = p->pe; cp->pe_data = p->pe_data; cp->pe_data_len = p->pe_data_len; + } else { + cp->pe = NULL; + cp->pe_data = NULL; + cp->pe_data_len = 0; } spin_lock_init(&cp->lock); @@ -894,18 +898,28 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, */ atomic_set(&cp->refcnt, 1); + cp->control = NULL; atomic_set(&cp->n_control, 0); atomic_set(&cp->in_pkts, 0); + cp->packet_xmit = NULL; + cp->app = NULL; + cp->app_data = NULL; + /* reset struct ip_vs_seq */ + cp->in_seq.delta = 0; + cp->out_seq.delta = 0; + atomic_inc(&ipvs->conn_count); if (flags & IP_VS_CONN_F_NO_CPORT) atomic_inc(&ip_vs_conn_no_cport_cnt); /* Bind the connection with a destination server */ + cp->dest = NULL; ip_vs_bind_dest(cp, dest); /* Set its state and timeout */ cp->state = 0; + cp->old_state = 0; cp->timeout = 3*HZ; cp->sync_endtime = jiffies & ~3UL; @@ -952,24 +966,29 @@ static void *ip_vs_conn_array(struct seq_file *seq, loff_t pos) struct ip_vs_iter_state *iter = seq->private; for (idx = 0; idx < ip_vs_conn_tab_size; idx++) { - ct_read_lock_bh(idx); - hlist_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) { + hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[idx], c_list) { + /* __ip_vs_conn_get() is not needed by + * ip_vs_conn_seq_show and ip_vs_conn_sync_seq_show + */ if (pos-- == 0) { iter->l = &ip_vs_conn_tab[idx]; return cp; } } - ct_read_unlock_bh(idx); + rcu_read_unlock(); + rcu_read_lock(); } return NULL; } static void *ip_vs_conn_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(RCU) { struct ip_vs_iter_state *iter = seq->private; iter->l = NULL; + rcu_read_lock(); return *pos ? ip_vs_conn_array(seq, *pos - 1) :SEQ_START_TOKEN; } @@ -977,6 +996,7 @@ static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ip_vs_conn *cp = v; struct ip_vs_iter_state *iter = seq->private; + struct hlist_node *e; struct hlist_head *l = iter->l; int idx; @@ -985,31 +1005,27 @@ static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos) return ip_vs_conn_array(seq, 0); /* more on same hash chain? */ - if (cp->c_list.next) - return hlist_entry(cp->c_list.next, struct ip_vs_conn, c_list); + e = rcu_dereference(hlist_next_rcu(&cp->c_list)); + if (e) + return hlist_entry(e, struct ip_vs_conn, c_list); idx = l - ip_vs_conn_tab; - ct_read_unlock_bh(idx); - while (++idx < ip_vs_conn_tab_size) { - ct_read_lock_bh(idx); - hlist_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) { + hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[idx], c_list) { iter->l = &ip_vs_conn_tab[idx]; return cp; } - ct_read_unlock_bh(idx); + rcu_read_unlock(); + rcu_read_lock(); } iter->l = NULL; return NULL; } static void ip_vs_conn_seq_stop(struct seq_file *seq, void *v) + __releases(RCU) { - struct ip_vs_iter_state *iter = seq->private; - struct hlist_head *l = iter->l; - - if (l) - ct_read_unlock_bh(l - ip_vs_conn_tab); + rcu_read_unlock(); } static int ip_vs_conn_seq_show(struct seq_file *seq, void *v) @@ -1188,7 +1204,7 @@ static inline int todrop_entry(struct ip_vs_conn *cp) void ip_vs_random_dropentry(struct net *net) { int idx; - struct ip_vs_conn *cp; + struct ip_vs_conn *cp, *cp_c; /* * Randomly scan 1/32 of the whole table every second @@ -1199,9 +1215,9 @@ void ip_vs_random_dropentry(struct net *net) /* * Lock is actually needed in this loop. */ - ct_write_lock_bh(hash); + rcu_read_lock(); - hlist_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { + hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[hash], c_list) { if (cp->flags & IP_VS_CONN_F_TEMPLATE) /* connection template */ continue; @@ -1228,12 +1244,15 @@ void ip_vs_random_dropentry(struct net *net) IP_VS_DBG(4, "del connection\n"); ip_vs_conn_expire_now(cp); - if (cp->control) { + cp_c = cp->control; + /* cp->control is valid only with reference to cp */ + if (cp_c && __ip_vs_conn_get(cp)) { IP_VS_DBG(4, "del conn template\n"); - ip_vs_conn_expire_now(cp->control); + ip_vs_conn_expire_now(cp_c); + __ip_vs_conn_put(cp); } } - ct_write_unlock_bh(hash); + rcu_read_unlock(); } } @@ -1244,7 +1263,7 @@ void ip_vs_random_dropentry(struct net *net) static void ip_vs_conn_flush(struct net *net) { int idx; - struct ip_vs_conn *cp; + struct ip_vs_conn *cp, *cp_c; struct netns_ipvs *ipvs = net_ipvs(net); flush_again: @@ -1252,19 +1271,22 @@ flush_again: /* * Lock is actually needed in this loop. */ - ct_write_lock_bh(idx); + rcu_read_lock(); - hlist_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) { + hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[idx], c_list) { if (!ip_vs_conn_net_eq(cp, net)) continue; IP_VS_DBG(4, "del connection\n"); ip_vs_conn_expire_now(cp); - if (cp->control) { + cp_c = cp->control; + /* cp->control is valid only with reference to cp */ + if (cp_c && __ip_vs_conn_get(cp)) { IP_VS_DBG(4, "del conn template\n"); - ip_vs_conn_expire_now(cp->control); + ip_vs_conn_expire_now(cp_c); + __ip_vs_conn_put(cp); } } - ct_write_unlock_bh(idx); + rcu_read_unlock(); } /* the counter may be not NULL, because maybe some conn entries @@ -1331,7 +1353,7 @@ int __init ip_vs_conn_init(void) INIT_HLIST_HEAD(&ip_vs_conn_tab[idx]); for (idx = 0; idx < CT_LOCKARRAY_SIZE; idx++) { - rwlock_init(&__ip_vs_conntbl_lock_array[idx].l); + spin_lock_init(&__ip_vs_conntbl_lock_array[idx].l); } /* calculate the random value for connection hash */ @@ -1342,6 +1364,8 @@ int __init ip_vs_conn_init(void) void ip_vs_conn_cleanup(void) { + /* Wait all ip_vs_conn_rcu_free() callbacks to complete */ + rcu_barrier(); /* Release the empty cache */ kmem_cache_destroy(ip_vs_conn_cachep); vfree(ip_vs_conn_tab); |