From: Pablo Neira Ayuso <pablo@netfilter.org>
To: netfilter-devel@vger.kernel.org
Cc: davem@davemloft.net, netdev@vger.kernel.org
Subject: [PATCH 18/51] ipvs: convert dh scheduler to rcu
Date: Sat, 6 Apr 2013 14:17:17 +0200 [thread overview]
Message-ID: <1365250670-14993-19-git-send-email-pablo@netfilter.org> (raw)
In-Reply-To: <1365250670-14993-1-git-send-email-pablo@netfilter.org>
From: Julian Anastasov <ja@ssi.bg>
Use the new add_dest and del_dest methods
to reassign dests.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
net/netfilter/ipvs/ip_vs_dh.c | 81 +++++++++++++++++++++++------------------
1 file changed, 45 insertions(+), 36 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_dh.c b/net/netfilter/ipvs/ip_vs_dh.c
index 7f3b0cc..ebe80f4 100644
--- a/net/netfilter/ipvs/ip_vs_dh.c
+++ b/net/netfilter/ipvs/ip_vs_dh.c
@@ -51,7 +51,7 @@
* IPVS DH bucket
*/
struct ip_vs_dh_bucket {
- struct ip_vs_dest *dest; /* real server (cache) */
+ struct ip_vs_dest __rcu *dest; /* real server (cache) */
};
/*
@@ -64,6 +64,10 @@ struct ip_vs_dh_bucket {
#define IP_VS_DH_TAB_SIZE (1 << IP_VS_DH_TAB_BITS)
#define IP_VS_DH_TAB_MASK (IP_VS_DH_TAB_SIZE - 1)
+struct ip_vs_dh_state {
+ struct ip_vs_dh_bucket buckets[IP_VS_DH_TAB_SIZE];
+ struct rcu_head rcu_head;
+};
/*
* Returns hash value for IPVS DH entry
@@ -85,10 +89,9 @@ static inline unsigned int ip_vs_dh_hashkey(int af, const union nf_inet_addr *ad
* Get ip_vs_dest associated with supplied parameters.
*/
static inline struct ip_vs_dest *
-ip_vs_dh_get(int af, struct ip_vs_dh_bucket *tbl,
- const union nf_inet_addr *addr)
+ip_vs_dh_get(int af, struct ip_vs_dh_state *s, const union nf_inet_addr *addr)
{
- return (tbl[ip_vs_dh_hashkey(af, addr)]).dest;
+ return rcu_dereference(s->buckets[ip_vs_dh_hashkey(af, addr)].dest);
}
@@ -96,25 +99,30 @@ ip_vs_dh_get(int af, struct ip_vs_dh_bucket *tbl,
* Assign all the hash buckets of the specified table with the service.
*/
static int
-ip_vs_dh_assign(struct ip_vs_dh_bucket *tbl, struct ip_vs_service *svc)
+ip_vs_dh_reassign(struct ip_vs_dh_state *s, struct ip_vs_service *svc)
{
int i;
struct ip_vs_dh_bucket *b;
struct list_head *p;
struct ip_vs_dest *dest;
+ bool empty;
- b = tbl;
+ b = &s->buckets[0];
p = &svc->destinations;
+ empty = list_empty(p);
for (i=0; i<IP_VS_DH_TAB_SIZE; i++) {
- if (list_empty(p)) {
- b->dest = NULL;
- } else {
+ dest = rcu_dereference_protected(b->dest, 1);
+ if (dest)
+ ip_vs_dest_put(dest);
+ if (empty)
+ RCU_INIT_POINTER(b->dest, NULL);
+ else {
if (p == &svc->destinations)
p = p->next;
dest = list_entry(p, struct ip_vs_dest, n_list);
- atomic_inc(&dest->refcnt);
- b->dest = dest;
+ ip_vs_dest_hold(dest);
+ RCU_INIT_POINTER(b->dest, dest);
p = p->next;
}
@@ -127,16 +135,18 @@ ip_vs_dh_assign(struct ip_vs_dh_bucket *tbl, struct ip_vs_service *svc)
/*
* Flush all the hash buckets of the specified table.
*/
-static void ip_vs_dh_flush(struct ip_vs_dh_bucket *tbl)
+static void ip_vs_dh_flush(struct ip_vs_dh_state *s)
{
int i;
struct ip_vs_dh_bucket *b;
+ struct ip_vs_dest *dest;
- b = tbl;
+ b = &s->buckets[0];
for (i=0; i<IP_VS_DH_TAB_SIZE; i++) {
- if (b->dest) {
- atomic_dec(&b->dest->refcnt);
- b->dest = NULL;
+ dest = rcu_dereference_protected(b->dest, 1);
+ if (dest) {
+ ip_vs_dest_put(dest);
+ RCU_INIT_POINTER(b->dest, NULL);
}
b++;
}
@@ -145,21 +155,20 @@ static void ip_vs_dh_flush(struct ip_vs_dh_bucket *tbl)
static int ip_vs_dh_init_svc(struct ip_vs_service *svc)
{
- struct ip_vs_dh_bucket *tbl;
+ struct ip_vs_dh_state *s;
/* allocate the DH table for this service */
- tbl = kmalloc(sizeof(struct ip_vs_dh_bucket)*IP_VS_DH_TAB_SIZE,
- GFP_KERNEL);
- if (tbl == NULL)
+ s = kzalloc(sizeof(struct ip_vs_dh_state), GFP_KERNEL);
+ if (s == NULL)
return -ENOMEM;
- svc->sched_data = tbl;
+ svc->sched_data = s;
IP_VS_DBG(6, "DH hash table (memory=%Zdbytes) allocated for "
"current service\n",
sizeof(struct ip_vs_dh_bucket)*IP_VS_DH_TAB_SIZE);
- /* assign the hash buckets with the updated service */
- ip_vs_dh_assign(tbl, svc);
+ /* assign the hash buckets with current dests */
+ ip_vs_dh_reassign(s, svc);
return 0;
}
@@ -167,13 +176,13 @@ static int ip_vs_dh_init_svc(struct ip_vs_service *svc)
static int ip_vs_dh_done_svc(struct ip_vs_service *svc)
{
- struct ip_vs_dh_bucket *tbl = svc->sched_data;
+ struct ip_vs_dh_state *s = svc->sched_data;
/* got to clean up hash buckets here */
- ip_vs_dh_flush(tbl);
+ ip_vs_dh_flush(s);
/* release the table itself */
- kfree(svc->sched_data);
+ kfree_rcu(s, rcu_head);
IP_VS_DBG(6, "DH hash table (memory=%Zdbytes) released\n",
sizeof(struct ip_vs_dh_bucket)*IP_VS_DH_TAB_SIZE);
@@ -181,15 +190,13 @@ static int ip_vs_dh_done_svc(struct ip_vs_service *svc)
}
-static int ip_vs_dh_update_svc(struct ip_vs_service *svc)
+static int ip_vs_dh_dest_changed(struct ip_vs_service *svc,
+ struct ip_vs_dest *dest)
{
- struct ip_vs_dh_bucket *tbl = svc->sched_data;
-
- /* got to clean up hash buckets here */
- ip_vs_dh_flush(tbl);
+ struct ip_vs_dh_state *s = svc->sched_data;
/* assign the hash buckets with the updated service */
- ip_vs_dh_assign(tbl, svc);
+ ip_vs_dh_reassign(s, svc);
return 0;
}
@@ -212,19 +219,20 @@ static struct ip_vs_dest *
ip_vs_dh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
{
struct ip_vs_dest *dest;
- struct ip_vs_dh_bucket *tbl;
+ struct ip_vs_dh_state *s;
struct ip_vs_iphdr iph;
ip_vs_fill_iph_addr_only(svc->af, skb, &iph);
IP_VS_DBG(6, "%s(): Scheduling...\n", __func__);
- tbl = (struct ip_vs_dh_bucket *)svc->sched_data;
- dest = ip_vs_dh_get(svc->af, tbl, &iph.daddr);
+ s = (struct ip_vs_dh_state *) svc->sched_data;
+ dest = ip_vs_dh_get(svc->af, s, &iph.daddr);
if (!dest
|| !(dest->flags & IP_VS_DEST_F_AVAILABLE)
|| atomic_read(&dest->weight) <= 0
|| is_overloaded(dest)) {
+ ip_vs_scheduler_err(svc, "no destination available");
return NULL;
}
@@ -248,7 +256,8 @@ static struct ip_vs_scheduler ip_vs_dh_scheduler =
.n_list = LIST_HEAD_INIT(ip_vs_dh_scheduler.n_list),
.init_service = ip_vs_dh_init_svc,
.done_service = ip_vs_dh_done_svc,
- .update_service = ip_vs_dh_update_svc,
+ .add_dest = ip_vs_dh_dest_changed,
+ .del_dest = ip_vs_dh_dest_changed,
.schedule = ip_vs_dh_schedule,
};
--
1.7.10.4
next prev parent reply other threads:[~2013-04-06 12:18 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-04-06 12:16 [PATCH 00/51] netfilter updates for net-next Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 01/51] ipvs: avoid routing by TOS for real server Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 02/51] ipvs: prefer NETDEV_DOWN event to free cached dsts Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 03/51] ipvs: convert the IP_VS_XMIT macros to functions Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 04/51] ipvs: rename functions related to dst_cache reset Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 05/51] ipvs: no need to reroute anymore on DNAT over loopback Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 06/51] ipvs: do not use skb_share_check Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 07/51] ipvs: consolidate all dst checks on transmit in one place Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 08/51] ipvs: optimize dst usage for real server Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 09/51] ipvs: convert app locks Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 10/51] ipvs: remove rs_lock by using RCU Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 11/51] ipvs: convert locks used in persistence engines Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 12/51] ipvs: convert connection locking Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 13/51] ipvs: reorder keys in connection structure Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 14/51] ipvs: avoid kmem_cache_zalloc in ip_vs_conn_new Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 15/51] ipvs: change ip_vs_sched_lock to mutex Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 16/51] ipvs: preparations for using rcu in schedulers Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 17/51] ipvs: add ip_vs_dest_hold and ip_vs_dest_put Pablo Neira Ayuso
2013-04-06 12:17 ` Pablo Neira Ayuso [this message]
2013-04-06 12:17 ` [PATCH 19/51] ipvs: convert lblc scheduler to rcu Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 20/51] ipvs: convert lblcr " Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 21/51] ipvs: convert lc " Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 22/51] ipvs: convert nq " Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 23/51] ipvs: convert rr " Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 24/51] ipvs: convert sed " Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 25/51] ipvs: convert sh " Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 26/51] ipvs: convert wlc " Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 27/51] ipvs: convert wrr " Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 28/51] ipvs: reorganize dest trash Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 29/51] ipvs: do not expect result from done_service Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 30/51] ipvs: convert sched_lock to spin lock Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 31/51] ipvs: convert dests to rcu Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 32/51] ipvs: convert services " Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 33/51] ipvs: do not disable bh for long time Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 34/51] netfilter: use IS_ENABLE to replace if defined in TRACE target Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 35/51] netfilter: xt_NFQUEUE: introduce CPU fanout Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 36/51] netfilter: xt_NFQUEUE: coalesce IPv4 and IPv6 hashing Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 37/51] netfilter: fix struct ip6t_frag field description Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 38/51] netfilter: make /proc/net/netfilter pernet Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 39/51] netfilter: nf_log: prepare net namespace support for loggers Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 40/51] netfilter: ebt_log: add net namespace support for ebt_log Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 41/51] netfilter: xt_LOG: add net namespace support for xt_LOG Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 42/51] netfilter: ebt_ulog: add net namespace support for ebt_ulog Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 43/51] netfilter: ipt_ULOG: add net namespace support for ipt_ULOG Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 44/51] netfilter: nfnetlink_log: add net namespace support for nfnetlink_log Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 45/51] netfilter: enable per netns support for nf_loggers Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 46/51] netfilter: nfnetlink_queue: add net namespace support for nfnetlink_queue Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 47/51] netfilter: remove unneeded variable proc_net_netfilter Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 48/51] netfilter: implement RFC3168 5.3 (ecn protection) for ipv6 fragmentation handling Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 49/51] netfilter: ipv4: propagate routing errors from ip_route_me_harder() Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 50/51] netfilter: ipv6: propagate routing errors from ip6_route_me_harder() Pablo Neira Ayuso
2013-04-06 12:17 ` [PATCH 51/51] netfilter: nat: propagate errors from xfrm_me_harder() Pablo Neira Ayuso
2013-04-06 13:14 ` [PATCH 00/51] netfilter updates for net-next Julian Anastasov
2013-04-06 13:52 ` Pablo Neira Ayuso
2013-04-07 16:27 ` David Miller
2013-04-08 16:06 ` Pablo Neira Ayuso
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1365250670-14993-19-git-send-email-pablo@netfilter.org \
--to=pablo@netfilter.org \
--cc=davem@davemloft.net \
--cc=netdev@vger.kernel.org \
--cc=netfilter-devel@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).