* [PATCH net-next 14/19] ipvs: reorganize dest trash
From: Julian Anastasov @ 2013-03-22 9:46 UTC (permalink / raw)
To: Simon Horman; +Cc: lvs-devel, netdev
In-Reply-To: <1363945614-11752-1-git-send-email-ja@ssi.bg>
All dests will go to trash, no exceptions.
But we have to use new list node t_list for this, due
to RCU changes in following patches. Dests will wait there
initial grace period and later all conns and schedulers to
put their reference. The dests don't get reference for
staying in dest trash as before.
As result, we do not load ip_vs_dest_put with
extra checks for last refcnt and the schedulers do not
need to play games with atomic_inc_not_zero while
selecting best destination.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
---
include/net/ip_vs.h | 9 ++
net/netfilter/ipvs/ip_vs_ctl.c | 178 +++++++++++++++++++++++-----------------
2 files changed, 113 insertions(+), 74 deletions(-)
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 2752c86..76747d9 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -749,6 +749,8 @@ struct ip_vs_dest_dst {
struct rcu_head rcu_head;
};
+/* In grace period after removing */
+#define IP_VS_DEST_STATE_REMOVING 0x01
/*
* The real server destination forwarding entry
* with ip address, port number, and so on.
@@ -766,6 +768,7 @@ struct ip_vs_dest {
atomic_t refcnt; /* reference counter */
struct ip_vs_stats stats; /* statistics */
+ unsigned long state; /* state flags */
/* connection counters and thresholds */
atomic_t activeconns; /* active connections */
@@ -785,6 +788,7 @@ struct ip_vs_dest {
union nf_inet_addr vaddr; /* virtual IP address */
__u32 vfwmark; /* firewall mark of service */
+ struct list_head t_list; /* in dest_trash */
struct rcu_head rcu_head;
unsigned int in_rs_table:1; /* we are in rs_table */
};
@@ -912,6 +916,9 @@ struct ipvs_master_sync_state {
struct netns_ipvs *ipvs;
};
+/* How much time to keep dests in trash */
+#define IP_VS_DEST_TRASH_PERIOD (120 * HZ)
+
/* IPVS in network namespace */
struct netns_ipvs {
int gen; /* Generation */
@@ -961,6 +968,8 @@ struct netns_ipvs {
/* Trash for destinations */
struct list_head dest_trash;
+ spinlock_t dest_trash_lock;
+ struct timer_list dest_trash_timer; /* expiration timer */
/* Service counters */
atomic_t ftpsvc_counter;
atomic_t nullsvc_counter;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 36d9cd8..a6c206f 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -71,7 +71,7 @@ int ip_vs_get_debug_level(void)
/* Protos */
-static void __ip_vs_del_service(struct ip_vs_service *svc);
+static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup);
#ifdef CONFIG_IP_VS_IPV6
@@ -655,19 +655,25 @@ static struct ip_vs_dest *
ip_vs_trash_get_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr,
__be16 dport)
{
- struct ip_vs_dest *dest, *nxt;
+ struct ip_vs_dest *dest;
struct netns_ipvs *ipvs = net_ipvs(svc->net);
/*
* Find the destination in trash
*/
- list_for_each_entry_safe(dest, nxt, &ipvs->dest_trash, n_list) {
+ spin_lock_bh(&ipvs->dest_trash_lock);
+ list_for_each_entry(dest, &ipvs->dest_trash, t_list) {
IP_VS_DBG_BUF(3, "Destination %u/%s:%u still in trash, "
"dest->refcnt=%d\n",
dest->vfwmark,
IP_VS_DBG_ADDR(svc->af, &dest->addr),
ntohs(dest->port),
atomic_read(&dest->refcnt));
+ /* We can not reuse dest while in grace period
+ * because conns still can use dest->svc
+ */
+ if (test_bit(IP_VS_DEST_STATE_REMOVING, &dest->state))
+ continue;
if (dest->af == svc->af &&
ip_vs_addr_equal(svc->af, &dest->addr, daddr) &&
dest->port == dport &&
@@ -677,29 +683,27 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr,
(ip_vs_addr_equal(svc->af, &dest->vaddr, &svc->addr) &&
dest->vport == svc->port))) {
/* HIT */
- return dest;
- }
-
- /*
- * Try to purge the destination from trash if not referenced
- */
- if (atomic_read(&dest->refcnt) == 1) {
- IP_VS_DBG_BUF(3, "Removing destination %u/%s:%u "
- "from trash\n",
- dest->vfwmark,
- IP_VS_DBG_ADDR(svc->af, &dest->addr),
- ntohs(dest->port));
- list_del(&dest->n_list);
- __ip_vs_dst_cache_reset(dest);
- __ip_vs_unbind_svc(dest);
- free_percpu(dest->stats.cpustats);
- kfree_rcu(dest, rcu_head);
+ list_del(&dest->t_list);
+ ip_vs_dest_hold(dest);
+ goto out;
}
}
- return NULL;
+ dest = NULL;
+
+out:
+ spin_unlock_bh(&ipvs->dest_trash_lock);
+
+ return dest;
}
+static void ip_vs_dest_free(struct ip_vs_dest *dest)
+{
+ __ip_vs_dst_cache_reset(dest);
+ __ip_vs_unbind_svc(dest);
+ free_percpu(dest->stats.cpustats);
+ kfree(dest);
+}
/*
* Clean up all the destinations in the trash
@@ -708,19 +712,18 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr,
* When the ip_vs_control_clearup is activated by ipvs module exit,
* the service tables must have been flushed and all the connections
* are expired, and the refcnt of each destination in the trash must
- * be 1, so we simply release them here.
+ * be 0, so we simply release them here.
*/
static void ip_vs_trash_cleanup(struct net *net)
{
struct ip_vs_dest *dest, *nxt;
struct netns_ipvs *ipvs = net_ipvs(net);
- list_for_each_entry_safe(dest, nxt, &ipvs->dest_trash, n_list) {
- list_del(&dest->n_list);
- __ip_vs_dst_cache_reset(dest);
- __ip_vs_unbind_svc(dest);
- free_percpu(dest->stats.cpustats);
- kfree_rcu(dest, rcu_head);
+ del_timer_sync(&ipvs->dest_trash_timer);
+ /* No need to use dest_trash_lock */
+ list_for_each_entry_safe(dest, nxt, &ipvs->dest_trash, t_list) {
+ list_del(&dest->t_list);
+ ip_vs_dest_free(dest);
}
}
@@ -953,11 +956,6 @@ ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
IP_VS_DBG_ADDR(svc->af, &dest->vaddr),
ntohs(dest->vport));
- /*
- * Get the destination from the trash
- */
- list_del(&dest->n_list);
-
__ip_vs_update_dest(svc, dest, udest, 1);
ret = 0;
} else {
@@ -1013,11 +1011,21 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
return 0;
}
+static void ip_vs_dest_wait_readers(struct rcu_head *head)
+{
+ struct ip_vs_dest *dest = container_of(head, struct ip_vs_dest,
+ rcu_head);
+
+ /* End of grace period after unlinking */
+ clear_bit(IP_VS_DEST_STATE_REMOVING, &dest->state);
+}
+
/*
* Delete a destination (must be already unlinked from the service)
*/
-static void __ip_vs_del_dest(struct net *net, struct ip_vs_dest *dest)
+static void __ip_vs_del_dest(struct net *net, struct ip_vs_dest *dest,
+ bool cleanup)
{
struct netns_ipvs *ipvs = net_ipvs(net);
@@ -1028,34 +1036,22 @@ static void __ip_vs_del_dest(struct net *net, struct ip_vs_dest *dest)
*/
ip_vs_rs_unhash(dest);
- /*
- * Decrease the refcnt of the dest, and free the dest
- * if nobody refers to it (refcnt=0). Otherwise, throw
- * the destination into the trash.
- */
- if (atomic_dec_and_test(&dest->refcnt)) {
- IP_VS_DBG_BUF(3, "Removing destination %u/%s:%u\n",
- dest->vfwmark,
- IP_VS_DBG_ADDR(dest->af, &dest->addr),
- ntohs(dest->port));
- __ip_vs_dst_cache_reset(dest);
- /* simply decrease svc->refcnt here, let the caller check
- and release the service if nobody refers to it.
- Only user context can release destination and service,
- and only one user context can update virtual service at a
- time, so the operation here is OK */
- atomic_dec(&dest->svc->refcnt);
- free_percpu(dest->stats.cpustats);
- kfree_rcu(dest, rcu_head);
- } else {
- IP_VS_DBG_BUF(3, "Moving dest %s:%u into trash, "
- "dest->refcnt=%d\n",
- IP_VS_DBG_ADDR(dest->af, &dest->addr),
- ntohs(dest->port),
- atomic_read(&dest->refcnt));
- list_add(&dest->n_list, &ipvs->dest_trash);
- ip_vs_dest_hold(dest);
+ if (!cleanup) {
+ set_bit(IP_VS_DEST_STATE_REMOVING, &dest->state);
+ call_rcu(&dest->rcu_head, ip_vs_dest_wait_readers);
}
+
+ spin_lock_bh(&ipvs->dest_trash_lock);
+ IP_VS_DBG_BUF(3, "Moving dest %s:%u into trash, dest->refcnt=%d\n",
+ IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port),
+ atomic_read(&dest->refcnt));
+ if (list_empty(&ipvs->dest_trash) && !cleanup)
+ mod_timer(&ipvs->dest_trash_timer,
+ jiffies + IP_VS_DEST_TRASH_PERIOD);
+ /* dest lives in trash without reference */
+ list_add(&dest->t_list, &ipvs->dest_trash);
+ spin_unlock_bh(&ipvs->dest_trash_lock);
+ ip_vs_dest_put(dest);
}
@@ -1120,13 +1116,38 @@ ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest)
/*
* Delete the destination
*/
- __ip_vs_del_dest(svc->net, dest);
+ __ip_vs_del_dest(svc->net, dest, false);
LeaveFunction(2);
return 0;
}
+static void ip_vs_dest_trash_expire(unsigned long data)
+{
+ struct net *net = (struct net *) data;
+ struct netns_ipvs *ipvs = net_ipvs(net);
+ struct ip_vs_dest *dest, *next;
+
+ spin_lock(&ipvs->dest_trash_lock);
+ list_for_each_entry_safe(dest, next, &ipvs->dest_trash, t_list) {
+ /* Skip if dest is in grace period */
+ if (test_bit(IP_VS_DEST_STATE_REMOVING, &dest->state))
+ continue;
+ if (atomic_read(&dest->refcnt) > 0)
+ continue;
+ IP_VS_DBG_BUF(3, "Removing destination %u/%s:%u from trash\n",
+ dest->vfwmark,
+ IP_VS_DBG_ADDR(dest->svc->af, &dest->addr),
+ ntohs(dest->port));
+ list_del(&dest->t_list);
+ ip_vs_dest_free(dest);
+ }
+ if (!list_empty(&ipvs->dest_trash))
+ mod_timer(&ipvs->dest_trash_timer,
+ jiffies + IP_VS_DEST_TRASH_PERIOD);
+ spin_unlock(&ipvs->dest_trash_lock);
+}
/*
* Add a service into the service hash table
@@ -1356,7 +1377,7 @@ out:
* - The service must be unlinked, unlocked and not referenced!
* - We are called under _bh lock
*/
-static void __ip_vs_del_service(struct ip_vs_service *svc)
+static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup)
{
struct ip_vs_dest *dest, *nxt;
struct ip_vs_scheduler *old_sched;
@@ -1392,7 +1413,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc)
*/
list_for_each_entry_safe(dest, nxt, &svc->destinations, n_list) {
__ip_vs_unlink_dest(svc, dest, 0);
- __ip_vs_del_dest(svc->net, dest);
+ __ip_vs_del_dest(svc->net, dest, cleanup);
}
/*
@@ -1422,7 +1443,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc)
/*
* Unlink a service from list and try to delete it if its refcnt reached 0
*/
-static void ip_vs_unlink_service(struct ip_vs_service *svc)
+static void ip_vs_unlink_service(struct ip_vs_service *svc, bool cleanup)
{
/*
* Unhash it from the service table
@@ -1436,7 +1457,7 @@ static void ip_vs_unlink_service(struct ip_vs_service *svc)
*/
IP_VS_WAIT_WHILE(atomic_read(&svc->usecnt) > 0);
- __ip_vs_del_service(svc);
+ __ip_vs_del_service(svc, cleanup);
write_unlock_bh(&__ip_vs_svc_lock);
}
@@ -1448,7 +1469,7 @@ static int ip_vs_del_service(struct ip_vs_service *svc)
{
if (svc == NULL)
return -EEXIST;
- ip_vs_unlink_service(svc);
+ ip_vs_unlink_service(svc, false);
return 0;
}
@@ -1457,7 +1478,7 @@ static int ip_vs_del_service(struct ip_vs_service *svc)
/*
* Flush all the virtual services
*/
-static int ip_vs_flush(struct net *net)
+static int ip_vs_flush(struct net *net, bool cleanup)
{
int idx;
struct ip_vs_service *svc, *nxt;
@@ -1469,7 +1490,7 @@ static int ip_vs_flush(struct net *net)
list_for_each_entry_safe(svc, nxt, &ip_vs_svc_table[idx],
s_list) {
if (net_eq(svc->net, net))
- ip_vs_unlink_service(svc);
+ ip_vs_unlink_service(svc, cleanup);
}
}
@@ -1480,7 +1501,7 @@ static int ip_vs_flush(struct net *net)
list_for_each_entry_safe(svc, nxt,
&ip_vs_svc_fwm_table[idx], f_list) {
if (net_eq(svc->net, net))
- ip_vs_unlink_service(svc);
+ ip_vs_unlink_service(svc, cleanup);
}
}
@@ -1496,7 +1517,7 @@ void ip_vs_service_net_cleanup(struct net *net)
EnterFunction(2);
/* Check for "full" addressed entries */
mutex_lock(&__ip_vs_mutex);
- ip_vs_flush(net);
+ ip_vs_flush(net, true);
mutex_unlock(&__ip_vs_mutex);
LeaveFunction(2);
}
@@ -1556,9 +1577,11 @@ static int ip_vs_dst_event(struct notifier_block *this, unsigned long event,
}
}
- list_for_each_entry(dest, &ipvs->dest_trash, n_list) {
+ spin_lock_bh(&ipvs->dest_trash_lock);
+ list_for_each_entry(dest, &ipvs->dest_trash, t_list) {
ip_vs_forget_dev(dest, dev);
}
+ spin_unlock_bh(&ipvs->dest_trash_lock);
mutex_unlock(&__ip_vs_mutex);
LeaveFunction(2);
return NOTIFY_DONE;
@@ -2392,7 +2415,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
if (cmd == IP_VS_SO_SET_FLUSH) {
/* Flush the virtual service */
- ret = ip_vs_flush(net);
+ ret = ip_vs_flush(net, false);
goto out_unlock;
} else if (cmd == IP_VS_SO_SET_TIMEOUT) {
/* Set timeout values for (tcp tcpfin udp) */
@@ -3401,7 +3424,7 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info)
mutex_lock(&__ip_vs_mutex);
if (cmd == IPVS_CMD_FLUSH) {
- ret = ip_vs_flush(net);
+ ret = ip_vs_flush(net, false);
goto out;
} else if (cmd == IPVS_CMD_SET_CONFIG) {
ret = ip_vs_genl_set_config(net, info->attrs);
@@ -3798,6 +3821,9 @@ int __net_init ip_vs_control_net_init(struct net *net)
INIT_HLIST_HEAD(&ipvs->rs_table[idx]);
INIT_LIST_HEAD(&ipvs->dest_trash);
+ spin_lock_init(&ipvs->dest_trash_lock);
+ setup_timer(&ipvs->dest_trash_timer, ip_vs_dest_trash_expire,
+ (unsigned long) net);
atomic_set(&ipvs->ftpsvc_counter, 0);
atomic_set(&ipvs->nullsvc_counter, 0);
@@ -3827,6 +3853,10 @@ void __net_exit ip_vs_control_net_cleanup(struct net *net)
{
struct netns_ipvs *ipvs = net_ipvs(net);
+ /* Some dest can be in grace period even before cleanup, we have to
+ * defer ip_vs_trash_cleanup until ip_vs_dest_wait_readers is called.
+ */
+ rcu_barrier();
ip_vs_trash_cleanup(net);
ip_vs_stop_estimator(net, &ipvs->tot_stats);
ip_vs_control_net_cleanup_sysctl(net);
--
1.7.3.4
^ permalink raw reply related
* [PATCH net-next 13/19] ipvs: convert wrr scheduler to rcu
From: Julian Anastasov @ 2013-03-22 9:46 UTC (permalink / raw)
To: Simon Horman; +Cc: lvs-devel, netdev
In-Reply-To: <1363945614-11752-1-git-send-email-ja@ssi.bg>
The schedule method now needs _rcu list-traversal
primitive for svc->destinations. As the weight for some
dest can be reduced during dest selection, change the
algorithm to check weights by using minimum weights in the
1 .. max_weight-(di-1) range, with the same step (di). By this
way we ensure that there will be always a weight >= 1 check
before claiming that all destinations are overloaded.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
---
net/netfilter/ipvs/ip_vs_wrr.c | 167 ++++++++++++++++++++++++---------------
1 files changed, 103 insertions(+), 64 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_wrr.c b/net/netfilter/ipvs/ip_vs_wrr.c
index 231be7d..98cb05e 100644
--- a/net/netfilter/ipvs/ip_vs_wrr.c
+++ b/net/netfilter/ipvs/ip_vs_wrr.c
@@ -29,14 +29,45 @@
#include <net/ip_vs.h>
+/* The WRR algorithm depends on some caclulations:
+ * - mw: maximum weight
+ * - di: weight step, greatest common divisor from all weights
+ * - cw: current required weight
+ * As result, all weights are in the [di..mw] range with a step=di.
+ *
+ * First, we start with cw = mw and select dests with weight >= cw.
+ * Then cw is reduced with di and all dests are checked again.
+ * Last pass should be with cw = di. We have mw/di passes in total:
+ *
+ * pass 1: cw = max weight
+ * pass 2: cw = max weight - di
+ * pass 3: cw = max weight - 2 * di
+ * ...
+ * last pass: cw = di
+ *
+ * Weights are supposed to be >= di but we run in parallel with
+ * weight changes, it is possible some dest weight to be reduced
+ * below di, bad if it is the only available dest.
+ *
+ * So, we modify how mw is calculated, now it is reduced with (di - 1),
+ * so that last cw is 1 to catch such dests with weight below di:
+ * pass 1: cw = max weight - (di - 1)
+ * pass 2: cw = max weight - di - (di - 1)
+ * pass 3: cw = max weight - 2 * di - (di - 1)
+ * ...
+ * last pass: cw = 1
+ *
+ */
+
/*
* current destination pointer for weighted round-robin scheduling
*/
struct ip_vs_wrr_mark {
- struct list_head *cl; /* current list head */
+ struct ip_vs_dest *cl; /* current dest or head */
int cw; /* current weight */
int mw; /* maximum weight */
int di; /* decreasing interval */
+ struct rcu_head rcu_head;
};
@@ -88,10 +119,10 @@ static int ip_vs_wrr_init_svc(struct ip_vs_service *svc)
if (mark == NULL)
return -ENOMEM;
- mark->cl = &svc->destinations;
- mark->cw = 0;
- mark->mw = ip_vs_wrr_max_weight(svc);
+ mark->cl = list_entry(&svc->destinations, struct ip_vs_dest, n_list);
mark->di = ip_vs_wrr_gcd_weight(svc);
+ mark->mw = ip_vs_wrr_max_weight(svc) - (mark->di - 1);
+ mark->cw = mark->mw;
svc->sched_data = mark;
return 0;
@@ -100,24 +131,31 @@ static int ip_vs_wrr_init_svc(struct ip_vs_service *svc)
static int ip_vs_wrr_done_svc(struct ip_vs_service *svc)
{
+ struct ip_vs_wrr_mark *mark = svc->sched_data;
+
/*
* Release the mark variable
*/
- kfree(svc->sched_data);
+ kfree_rcu(mark, rcu_head);
return 0;
}
-static int ip_vs_wrr_update_svc(struct ip_vs_service *svc)
+static int ip_vs_wrr_dest_changed(struct ip_vs_service *svc,
+ struct ip_vs_dest *dest)
{
struct ip_vs_wrr_mark *mark = svc->sched_data;
- mark->cl = &svc->destinations;
- mark->mw = ip_vs_wrr_max_weight(svc);
+ write_lock_bh(&svc->sched_lock);
+ mark->cl = list_entry(&svc->destinations, struct ip_vs_dest, n_list);
mark->di = ip_vs_wrr_gcd_weight(svc);
- if (mark->cw > mark->mw)
- mark->cw = 0;
+ mark->mw = ip_vs_wrr_max_weight(svc) - (mark->di - 1);
+ if (mark->cw > mark->mw || !mark->cw)
+ mark->cw = mark->mw;
+ else if (mark->di > 1)
+ mark->cw = (mark->cw / mark->di) * mark->di + 1;
+ write_unlock_bh(&svc->sched_lock);
return 0;
}
@@ -128,80 +166,79 @@ static int ip_vs_wrr_update_svc(struct ip_vs_service *svc)
static struct ip_vs_dest *
ip_vs_wrr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
{
- struct ip_vs_dest *dest;
+ struct ip_vs_dest *dest, *last, *stop = NULL;
struct ip_vs_wrr_mark *mark = svc->sched_data;
- struct list_head *p;
+ bool last_pass = false, restarted = false;
IP_VS_DBG(6, "%s(): Scheduling...\n", __func__);
- /*
- * This loop will always terminate, because mark->cw in (0, max_weight]
- * and at least one server has its weight equal to max_weight.
- */
write_lock(&svc->sched_lock);
- p = mark->cl;
+ dest = mark->cl;
+ /* No available dests? */
+ if (mark->mw == 0)
+ goto err_noavail;
+ last = dest;
+ /* Stop only after all dests were checked for weight >= 1 (last pass) */
while (1) {
- if (mark->cl == &svc->destinations) {
- /* it is at the head of the destination list */
-
- if (mark->cl == mark->cl->next) {
- /* no dest entry */
- ip_vs_scheduler_err(svc,
- "no destination available: "
- "no destinations present");
- dest = NULL;
- goto out;
- }
-
- mark->cl = svc->destinations.next;
- mark->cw -= mark->di;
- if (mark->cw <= 0) {
- mark->cw = mark->mw;
- /*
- * Still zero, which means no available servers.
- */
- if (mark->cw == 0) {
- mark->cl = &svc->destinations;
- ip_vs_scheduler_err(svc,
- "no destination available");
- dest = NULL;
- goto out;
- }
- }
- } else
- mark->cl = mark->cl->next;
-
- if (mark->cl != &svc->destinations) {
- /* not at the head of the list */
- dest = list_entry(mark->cl, struct ip_vs_dest, n_list);
+ list_for_each_entry_continue_rcu(dest,
+ &svc->destinations,
+ n_list) {
if (!(dest->flags & IP_VS_DEST_F_OVERLOAD) &&
- atomic_read(&dest->weight) >= mark->cw) {
- /* got it */
- break;
- }
+ atomic_read(&dest->weight) >= mark->cw)
+ goto found;
+ if (dest == stop)
+ goto err_over;
}
-
- if (mark->cl == p && mark->cw == mark->di) {
- /* back to the start, and no dest is found.
- It is only possible when all dests are OVERLOADED */
- dest = NULL;
- ip_vs_scheduler_err(svc,
- "no destination available: "
- "all destinations are overloaded");
- goto out;
+ mark->cw -= mark->di;
+ if (mark->cw <= 0) {
+ mark->cw = mark->mw;
+ /* Stop if we tried last pass from first dest:
+ * 1. last_pass: we started checks when cw > di but
+ * then all dests were checked for w >= 1
+ * 2. last was head: the first and only traversal
+ * was for weight >= 1, for all dests.
+ */
+ if (last_pass ||
+ &last->n_list == &svc->destinations)
+ goto err_over;
+ restarted = true;
+ }
+ last_pass = mark->cw <= mark->di;
+ if (last_pass && restarted &&
+ &last->n_list != &svc->destinations) {
+ /* First traversal was for w >= 1 but only
+ * for dests after 'last', now do the same
+ * for all dests up to 'last'.
+ */
+ stop = last;
}
}
+found:
IP_VS_DBG_BUF(6, "WRR: server %s:%u "
"activeconns %d refcnt %d weight %d\n",
IP_VS_DBG_ADDR(svc->af, &dest->addr), ntohs(dest->port),
atomic_read(&dest->activeconns),
atomic_read(&dest->refcnt),
atomic_read(&dest->weight));
+ mark->cl = dest;
out:
write_unlock(&svc->sched_lock);
return dest;
+
+err_noavail:
+ mark->cl = dest;
+ dest = NULL;
+ ip_vs_scheduler_err(svc, "no destination available");
+ goto out;
+
+err_over:
+ mark->cl = dest;
+ dest = NULL;
+ ip_vs_scheduler_err(svc, "no destination available: "
+ "all destinations are overloaded");
+ goto out;
}
@@ -212,7 +249,9 @@ static struct ip_vs_scheduler ip_vs_wrr_scheduler = {
.n_list = LIST_HEAD_INIT(ip_vs_wrr_scheduler.n_list),
.init_service = ip_vs_wrr_init_svc,
.done_service = ip_vs_wrr_done_svc,
- .update_service = ip_vs_wrr_update_svc,
+ .add_dest = ip_vs_wrr_dest_changed,
+ .del_dest = ip_vs_wrr_dest_changed,
+ .upd_dest = ip_vs_wrr_dest_changed,
.schedule = ip_vs_wrr_schedule,
};
--
1.7.3.4
^ permalink raw reply related
* [PATCH net-next 16/19] ipvs: convert sched_lock to spin lock
From: Julian Anastasov @ 2013-03-22 9:46 UTC (permalink / raw)
To: Simon Horman; +Cc: lvs-devel, netdev
In-Reply-To: <1363945614-11752-1-git-send-email-ja@ssi.bg>
As all read_locks are gone spin lock is preferred.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
---
include/net/ip_vs.h | 2 +-
net/netfilter/ipvs/ip_vs_ctl.c | 2 +-
net/netfilter/ipvs/ip_vs_lblc.c | 18 +++++++++---------
net/netfilter/ipvs/ip_vs_lblcr.c | 26 +++++++++++++-------------
net/netfilter/ipvs/ip_vs_rr.c | 10 +++++-----
net/netfilter/ipvs/ip_vs_wrr.c | 8 ++++----
6 files changed, 33 insertions(+), 33 deletions(-)
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 8597a71..034ce38 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -734,7 +734,7 @@ struct ip_vs_service {
/* for scheduling */
struct ip_vs_scheduler *scheduler; /* bound scheduler object */
- rwlock_t sched_lock; /* lock sched_data */
+ spinlock_t sched_lock; /* lock sched_data */
void *sched_data; /* scheduler application data */
/* alternate persistence engine */
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index e010deb..ada61a8 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1217,7 +1217,7 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
svc->net = net;
INIT_LIST_HEAD(&svc->destinations);
- rwlock_init(&svc->sched_lock);
+ spin_lock_init(&svc->sched_lock);
spin_lock_init(&svc->stats.lock);
/* Bind the scheduler */
diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index c7ff978..ffef8a1 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -194,7 +194,7 @@ ip_vs_lblc_get(int af, struct ip_vs_lblc_table *tbl,
/*
* Create or update an ip_vs_lblc_entry, which is a mapping of a destination IP
- * address to a server. Called under write lock.
+ * address to a server. Called under spin lock.
*/
static inline struct ip_vs_lblc_entry *
ip_vs_lblc_new(struct ip_vs_lblc_table *tbl, const union nf_inet_addr *daddr,
@@ -242,7 +242,7 @@ static void ip_vs_lblc_flush(struct ip_vs_service *svc)
struct hlist_node *next;
int i;
- write_lock_bh(&svc->sched_lock);
+ spin_lock_bh(&svc->sched_lock);
tbl->dead = 1;
for (i=0; i<IP_VS_LBLC_TAB_SIZE; i++) {
hlist_for_each_entry_safe(en, next, &tbl->bucket[i], list) {
@@ -250,7 +250,7 @@ static void ip_vs_lblc_flush(struct ip_vs_service *svc)
atomic_dec(&tbl->entries);
}
}
- write_unlock_bh(&svc->sched_lock);
+ spin_unlock_bh(&svc->sched_lock);
}
static int sysctl_lblc_expiration(struct ip_vs_service *svc)
@@ -274,7 +274,7 @@ static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc)
for (i=0, j=tbl->rover; i<IP_VS_LBLC_TAB_SIZE; i++) {
j = (j + 1) & IP_VS_LBLC_TAB_MASK;
- write_lock(&svc->sched_lock);
+ spin_lock(&svc->sched_lock);
hlist_for_each_entry_safe(en, next, &tbl->bucket[j], list) {
if (time_before(now,
en->lastuse +
@@ -284,7 +284,7 @@ static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc)
ip_vs_lblc_free(en);
atomic_dec(&tbl->entries);
}
- write_unlock(&svc->sched_lock);
+ spin_unlock(&svc->sched_lock);
}
tbl->rover = j;
}
@@ -330,7 +330,7 @@ static void ip_vs_lblc_check_expire(unsigned long data)
for (i=0, j=tbl->rover; i<IP_VS_LBLC_TAB_SIZE; i++) {
j = (j + 1) & IP_VS_LBLC_TAB_MASK;
- write_lock(&svc->sched_lock);
+ spin_lock(&svc->sched_lock);
hlist_for_each_entry_safe(en, next, &tbl->bucket[j], list) {
if (time_before(now, en->lastuse + ENTRY_TIMEOUT))
continue;
@@ -339,7 +339,7 @@ static void ip_vs_lblc_check_expire(unsigned long data)
atomic_dec(&tbl->entries);
goal--;
}
- write_unlock(&svc->sched_lock);
+ spin_unlock(&svc->sched_lock);
if (goal <= 0)
break;
}
@@ -527,10 +527,10 @@ ip_vs_lblc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
}
/* If we fail to create a cache entry, we'll just use the valid dest */
- write_lock(&svc->sched_lock);
+ spin_lock(&svc->sched_lock);
if (!tbl->dead)
ip_vs_lblc_new(tbl, &iph.daddr, dest);
- write_unlock(&svc->sched_lock);
+ spin_unlock(&svc->sched_lock);
out:
IP_VS_DBG_BUF(6, "LBLC: destination IP address %s --> server %s:%d\n",
diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c
index 6049b85..cdfe6a9 100644
--- a/net/netfilter/ipvs/ip_vs_lblcr.c
+++ b/net/netfilter/ipvs/ip_vs_lblcr.c
@@ -368,7 +368,7 @@ ip_vs_lblcr_get(int af, struct ip_vs_lblcr_table *tbl,
/*
* Create or update an ip_vs_lblcr_entry, which is a mapping of a destination
- * IP address to a server. Called under write lock.
+ * IP address to a server. Called under spin lock.
*/
static inline struct ip_vs_lblcr_entry *
ip_vs_lblcr_new(struct ip_vs_lblcr_table *tbl, const union nf_inet_addr *daddr,
@@ -412,14 +412,14 @@ static void ip_vs_lblcr_flush(struct ip_vs_service *svc)
struct ip_vs_lblcr_entry *en;
struct hlist_node *next;
- write_lock_bh(&svc->sched_lock);
+ spin_lock_bh(&svc->sched_lock);
tbl->dead = 1;
for (i=0; i<IP_VS_LBLCR_TAB_SIZE; i++) {
hlist_for_each_entry_safe(en, next, &tbl->bucket[i], list) {
ip_vs_lblcr_free(en);
}
}
- write_unlock_bh(&svc->sched_lock);
+ spin_unlock_bh(&svc->sched_lock);
}
static int sysctl_lblcr_expiration(struct ip_vs_service *svc)
@@ -443,7 +443,7 @@ static inline void ip_vs_lblcr_full_check(struct ip_vs_service *svc)
for (i=0, j=tbl->rover; i<IP_VS_LBLCR_TAB_SIZE; i++) {
j = (j + 1) & IP_VS_LBLCR_TAB_MASK;
- write_lock(&svc->sched_lock);
+ spin_lock(&svc->sched_lock);
hlist_for_each_entry_safe(en, next, &tbl->bucket[j], list) {
if (time_after(en->lastuse +
sysctl_lblcr_expiration(svc), now))
@@ -452,7 +452,7 @@ static inline void ip_vs_lblcr_full_check(struct ip_vs_service *svc)
ip_vs_lblcr_free(en);
atomic_dec(&tbl->entries);
}
- write_unlock(&svc->sched_lock);
+ spin_unlock(&svc->sched_lock);
}
tbl->rover = j;
}
@@ -498,7 +498,7 @@ static void ip_vs_lblcr_check_expire(unsigned long data)
for (i=0, j=tbl->rover; i<IP_VS_LBLCR_TAB_SIZE; i++) {
j = (j + 1) & IP_VS_LBLCR_TAB_MASK;
- write_lock(&svc->sched_lock);
+ spin_lock(&svc->sched_lock);
hlist_for_each_entry_safe(en, next, &tbl->bucket[j], list) {
if (time_before(now, en->lastuse+ENTRY_TIMEOUT))
continue;
@@ -507,7 +507,7 @@ static void ip_vs_lblcr_check_expire(unsigned long data)
atomic_dec(&tbl->entries);
goal--;
}
- write_unlock(&svc->sched_lock);
+ spin_unlock(&svc->sched_lock);
if (goal <= 0)
break;
}
@@ -678,7 +678,7 @@ ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
if (atomic_read(&en->set.size) > 1 &&
time_after(jiffies, en->set.lastmod +
sysctl_lblcr_expiration(svc))) {
- write_lock(&svc->sched_lock);
+ spin_lock(&svc->sched_lock);
if (atomic_read(&en->set.size) > 1) {
struct ip_vs_dest *m;
@@ -686,7 +686,7 @@ ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
if (m)
ip_vs_dest_set_erase(&en->set, m);
}
- write_unlock(&svc->sched_lock);
+ spin_unlock(&svc->sched_lock);
}
/* If the destination is not overloaded, use it */
@@ -701,10 +701,10 @@ ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
}
/* Update our cache entry */
- write_lock(&svc->sched_lock);
+ spin_lock(&svc->sched_lock);
if (!tbl->dead)
ip_vs_dest_set_insert(&en->set, dest, true);
- write_unlock(&svc->sched_lock);
+ spin_unlock(&svc->sched_lock);
goto out;
}
@@ -716,10 +716,10 @@ ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
}
/* If we fail to create a cache entry, we'll just use the valid dest */
- write_lock(&svc->sched_lock);
+ spin_lock(&svc->sched_lock);
if (!tbl->dead)
ip_vs_lblcr_new(tbl, &iph.daddr, dest);
- write_unlock(&svc->sched_lock);
+ spin_unlock(&svc->sched_lock);
out:
IP_VS_DBG_BUF(6, "LBLCR: destination IP address %s --> server %s:%d\n",
diff --git a/net/netfilter/ipvs/ip_vs_rr.c b/net/netfilter/ipvs/ip_vs_rr.c
index 3942890..aa4601f 100644
--- a/net/netfilter/ipvs/ip_vs_rr.c
+++ b/net/netfilter/ipvs/ip_vs_rr.c
@@ -39,14 +39,14 @@ static int ip_vs_rr_del_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest)
{
struct list_head *p;
- write_lock_bh(&svc->sched_lock);
+ spin_lock_bh(&svc->sched_lock);
p = (struct list_head *) svc->sched_data;
/* dest is already unlinked, so p->prev is not valid but
* p->next is valid, use it to reach previous entry.
*/
if (p == &dest->n_list)
svc->sched_data = p->next->prev;
- write_unlock_bh(&svc->sched_lock);
+ spin_unlock_bh(&svc->sched_lock);
return 0;
}
@@ -63,7 +63,7 @@ ip_vs_rr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
IP_VS_DBG(6, "%s(): Scheduling...\n", __func__);
- write_lock(&svc->sched_lock);
+ spin_lock(&svc->sched_lock);
p = (struct list_head *) svc->sched_data;
last = dest = list_entry(p, struct ip_vs_dest, n_list);
@@ -85,13 +85,13 @@ ip_vs_rr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
} while (pass < 2 && p != &svc->destinations);
stop:
- write_unlock(&svc->sched_lock);
+ spin_unlock(&svc->sched_lock);
ip_vs_scheduler_err(svc, "no destination available");
return NULL;
out:
svc->sched_data = &dest->n_list;
- write_unlock(&svc->sched_lock);
+ spin_unlock(&svc->sched_lock);
IP_VS_DBG_BUF(6, "RR: server %s:%u "
"activeconns %d refcnt %d weight %d\n",
IP_VS_DBG_ADDR(svc->af, &dest->addr), ntohs(dest->port),
diff --git a/net/netfilter/ipvs/ip_vs_wrr.c b/net/netfilter/ipvs/ip_vs_wrr.c
index a74fd9b..b173ef9 100644
--- a/net/netfilter/ipvs/ip_vs_wrr.c
+++ b/net/netfilter/ipvs/ip_vs_wrr.c
@@ -145,7 +145,7 @@ static int ip_vs_wrr_dest_changed(struct ip_vs_service *svc,
{
struct ip_vs_wrr_mark *mark = svc->sched_data;
- write_lock_bh(&svc->sched_lock);
+ spin_lock_bh(&svc->sched_lock);
mark->cl = list_entry(&svc->destinations, struct ip_vs_dest, n_list);
mark->di = ip_vs_wrr_gcd_weight(svc);
mark->mw = ip_vs_wrr_max_weight(svc) - (mark->di - 1);
@@ -153,7 +153,7 @@ static int ip_vs_wrr_dest_changed(struct ip_vs_service *svc,
mark->cw = mark->mw;
else if (mark->di > 1)
mark->cw = (mark->cw / mark->di) * mark->di + 1;
- write_unlock_bh(&svc->sched_lock);
+ spin_unlock_bh(&svc->sched_lock);
return 0;
}
@@ -170,7 +170,7 @@ ip_vs_wrr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
IP_VS_DBG(6, "%s(): Scheduling...\n", __func__);
- write_lock(&svc->sched_lock);
+ spin_lock(&svc->sched_lock);
dest = mark->cl;
/* No available dests? */
if (mark->mw == 0)
@@ -222,7 +222,7 @@ found:
mark->cl = dest;
out:
- write_unlock(&svc->sched_lock);
+ spin_unlock(&svc->sched_lock);
return dest;
err_noavail:
--
1.7.3.4
^ permalink raw reply related
* [PATCH net-next 12/19] ipvs: convert wlc scheduler to rcu
From: Julian Anastasov @ 2013-03-22 9:46 UTC (permalink / raw)
To: Simon Horman; +Cc: lvs-devel, netdev
In-Reply-To: <1363945614-11752-1-git-send-email-ja@ssi.bg>
The schedule method now needs _rcu list-traversal
primitive for svc->destinations.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
---
net/netfilter/ipvs/ip_vs_wlc.c | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_wlc.c b/net/netfilter/ipvs/ip_vs_wlc.c
index bc1bfc4..dafae88 100644
--- a/net/netfilter/ipvs/ip_vs_wlc.c
+++ b/net/netfilter/ipvs/ip_vs_wlc.c
@@ -51,7 +51,7 @@ ip_vs_wlc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
* new connections.
*/
- list_for_each_entry(dest, &svc->destinations, n_list) {
+ list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
if (!(dest->flags & IP_VS_DEST_F_OVERLOAD) &&
atomic_read(&dest->weight) > 0) {
least = dest;
@@ -66,7 +66,7 @@ ip_vs_wlc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
* Find the destination with the least load.
*/
nextstage:
- list_for_each_entry_continue(dest, &svc->destinations, n_list) {
+ list_for_each_entry_continue_rcu(dest, &svc->destinations, n_list) {
if (dest->flags & IP_VS_DEST_F_OVERLOAD)
continue;
doh = ip_vs_dest_conn_overhead(dest);
--
1.7.3.4
^ permalink raw reply related
* [PATCH net-next 07/19] ipvs: convert lc scheduler to rcu
From: Julian Anastasov @ 2013-03-22 9:46 UTC (permalink / raw)
To: Simon Horman; +Cc: lvs-devel, netdev
In-Reply-To: <1363945614-11752-1-git-send-email-ja@ssi.bg>
The schedule method now needs _rcu list-traversal
primitive for svc->destinations.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
---
net/netfilter/ipvs/ip_vs_lc.c | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_lc.c b/net/netfilter/ipvs/ip_vs_lc.c
index f391819..0cabf78 100644
--- a/net/netfilter/ipvs/ip_vs_lc.c
+++ b/net/netfilter/ipvs/ip_vs_lc.c
@@ -42,7 +42,7 @@ ip_vs_lc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
* served, but no new connection is assigned to the server.
*/
- list_for_each_entry(dest, &svc->destinations, n_list) {
+ list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
if ((dest->flags & IP_VS_DEST_F_OVERLOAD) ||
atomic_read(&dest->weight) == 0)
continue;
--
1.7.3.4
^ permalink raw reply related
* [PATCH net-next 15/19] ipvs: do not expect result from done_service
From: Julian Anastasov @ 2013-03-22 9:46 UTC (permalink / raw)
To: Simon Horman; +Cc: lvs-devel, netdev
In-Reply-To: <1363945614-11752-1-git-send-email-ja@ssi.bg>
This method releases the scheduler state,
it can not fail. Such change will help to properly
replace the scheduler in following patch.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
---
include/net/ip_vs.h | 4 ++--
net/netfilter/ipvs/ip_vs_ctl.c | 5 +----
net/netfilter/ipvs/ip_vs_dh.c | 4 +---
net/netfilter/ipvs/ip_vs_lblc.c | 4 +---
net/netfilter/ipvs/ip_vs_lblcr.c | 4 +---
net/netfilter/ipvs/ip_vs_sched.c | 13 ++++---------
net/netfilter/ipvs/ip_vs_sh.c | 4 +---
net/netfilter/ipvs/ip_vs_wrr.c | 4 +---
8 files changed, 12 insertions(+), 30 deletions(-)
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 76747d9..8597a71 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -806,7 +806,7 @@ struct ip_vs_scheduler {
/* scheduler initializing service */
int (*init_service)(struct ip_vs_service *svc);
/* scheduling service finish */
- int (*done_service)(struct ip_vs_service *svc);
+ void (*done_service)(struct ip_vs_service *svc);
/* scheduler updating service */
int (*update_service)(struct ip_vs_service *svc);
/* dest is linked */
@@ -1392,7 +1392,7 @@ extern int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler);
extern int unregister_ip_vs_scheduler(struct ip_vs_scheduler *scheduler);
extern int ip_vs_bind_scheduler(struct ip_vs_service *svc,
struct ip_vs_scheduler *scheduler);
-extern int ip_vs_unbind_scheduler(struct ip_vs_service *svc);
+extern void ip_vs_unbind_scheduler(struct ip_vs_service *svc);
extern struct ip_vs_scheduler *ip_vs_scheduler_get(const char *sched_name);
extern void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler);
extern struct ip_vs_conn *
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index a6c206f..e010deb 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1332,10 +1332,7 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u)
/*
* Unbind the old scheduler
*/
- if ((ret = ip_vs_unbind_scheduler(svc))) {
- old_sched = sched;
- goto out_unlock;
- }
+ ip_vs_unbind_scheduler(svc);
/*
* Bind the new scheduler
diff --git a/net/netfilter/ipvs/ip_vs_dh.c b/net/netfilter/ipvs/ip_vs_dh.c
index ebe80f4..89c2723 100644
--- a/net/netfilter/ipvs/ip_vs_dh.c
+++ b/net/netfilter/ipvs/ip_vs_dh.c
@@ -174,7 +174,7 @@ static int ip_vs_dh_init_svc(struct ip_vs_service *svc)
}
-static int ip_vs_dh_done_svc(struct ip_vs_service *svc)
+static void ip_vs_dh_done_svc(struct ip_vs_service *svc)
{
struct ip_vs_dh_state *s = svc->sched_data;
@@ -185,8 +185,6 @@ static int ip_vs_dh_done_svc(struct ip_vs_service *svc)
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);
-
- return 0;
}
diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index b873e17..c7ff978 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -388,7 +388,7 @@ static int ip_vs_lblc_init_svc(struct ip_vs_service *svc)
}
-static int ip_vs_lblc_done_svc(struct ip_vs_service *svc)
+static void ip_vs_lblc_done_svc(struct ip_vs_service *svc)
{
struct ip_vs_lblc_table *tbl = svc->sched_data;
@@ -402,8 +402,6 @@ static int ip_vs_lblc_done_svc(struct ip_vs_service *svc)
kfree_rcu(tbl, rcu_head);
IP_VS_DBG(6, "LBLC hash table (memory=%Zdbytes) released\n",
sizeof(*tbl));
-
- return 0;
}
diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c
index c22f173..6049b85 100644
--- a/net/netfilter/ipvs/ip_vs_lblcr.c
+++ b/net/netfilter/ipvs/ip_vs_lblcr.c
@@ -555,7 +555,7 @@ static int ip_vs_lblcr_init_svc(struct ip_vs_service *svc)
}
-static int ip_vs_lblcr_done_svc(struct ip_vs_service *svc)
+static void ip_vs_lblcr_done_svc(struct ip_vs_service *svc)
{
struct ip_vs_lblcr_table *tbl = svc->sched_data;
@@ -569,8 +569,6 @@ static int ip_vs_lblcr_done_svc(struct ip_vs_service *svc)
kfree_rcu(tbl, rcu_head);
IP_VS_DBG(6, "LBLCR hash table (memory=%Zdbytes) released\n",
sizeof(*tbl));
-
- return 0;
}
diff --git a/net/netfilter/ipvs/ip_vs_sched.c b/net/netfilter/ipvs/ip_vs_sched.c
index 7f11d3d..1b715d0 100644
--- a/net/netfilter/ipvs/ip_vs_sched.c
+++ b/net/netfilter/ipvs/ip_vs_sched.c
@@ -64,22 +64,17 @@ int ip_vs_bind_scheduler(struct ip_vs_service *svc,
/*
* Unbind a service with its scheduler
*/
-int ip_vs_unbind_scheduler(struct ip_vs_service *svc)
+void ip_vs_unbind_scheduler(struct ip_vs_service *svc)
{
struct ip_vs_scheduler *sched = svc->scheduler;
if (!sched)
- return 0;
+ return;
- if (sched->done_service) {
- if (sched->done_service(svc) != 0) {
- pr_err("%s(): done error\n", __func__);
- return -EINVAL;
- }
- }
+ if (sched->done_service)
+ sched->done_service(svc);
svc->scheduler = NULL;
- return 0;
}
diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c
index 55e76d8..81c1a10 100644
--- a/net/netfilter/ipvs/ip_vs_sh.c
+++ b/net/netfilter/ipvs/ip_vs_sh.c
@@ -187,7 +187,7 @@ static int ip_vs_sh_init_svc(struct ip_vs_service *svc)
}
-static int ip_vs_sh_done_svc(struct ip_vs_service *svc)
+static void ip_vs_sh_done_svc(struct ip_vs_service *svc)
{
struct ip_vs_sh_state *s = svc->sched_data;
@@ -198,8 +198,6 @@ static int ip_vs_sh_done_svc(struct ip_vs_service *svc)
kfree_rcu(s, rcu_head);
IP_VS_DBG(6, "SH hash table (memory=%Zdbytes) released\n",
sizeof(struct ip_vs_sh_bucket)*IP_VS_SH_TAB_SIZE);
-
- return 0;
}
diff --git a/net/netfilter/ipvs/ip_vs_wrr.c b/net/netfilter/ipvs/ip_vs_wrr.c
index 98cb05e..a74fd9b 100644
--- a/net/netfilter/ipvs/ip_vs_wrr.c
+++ b/net/netfilter/ipvs/ip_vs_wrr.c
@@ -129,7 +129,7 @@ static int ip_vs_wrr_init_svc(struct ip_vs_service *svc)
}
-static int ip_vs_wrr_done_svc(struct ip_vs_service *svc)
+static void ip_vs_wrr_done_svc(struct ip_vs_service *svc)
{
struct ip_vs_wrr_mark *mark = svc->sched_data;
@@ -137,8 +137,6 @@ static int ip_vs_wrr_done_svc(struct ip_vs_service *svc)
* Release the mark variable
*/
kfree_rcu(mark, rcu_head);
-
- return 0;
}
--
1.7.3.4
^ permalink raw reply related
* [PATCH net-next 02/19] ipvs: preparations for using rcu in schedulers
From: Julian Anastasov @ 2013-03-22 9:46 UTC (permalink / raw)
To: Simon Horman; +Cc: lvs-devel, netdev
In-Reply-To: <1363945614-11752-1-git-send-email-ja@ssi.bg>
Allow schedulers to use rcu_dereference when
returning destination on lookup. The RCU read-side critical
section will allow ip_vs_bind_dest to get dest refcnt as
preparation for the step where destinations will be
deleted without an IP_VS_WAIT_WHILE guard that holds the
packet processing during update.
Add new optional scheduler methods add_dest,
del_dest and upd_dest. For now the methods are called
together with update_service but update_service will be
removed in a following change.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
---
include/net/ip_vs.h | 6 ++++++
net/netfilter/ipvs/ip_vs_core.c | 6 ++++++
net/netfilter/ipvs/ip_vs_ctl.c | 8 ++++++++
3 files changed, 20 insertions(+), 0 deletions(-)
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 5ed8939..5af338b 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -805,6 +805,12 @@ struct ip_vs_scheduler {
int (*done_service)(struct ip_vs_service *svc);
/* scheduler updating service */
int (*update_service)(struct ip_vs_service *svc);
+ /* dest is linked */
+ int (*add_dest)(struct ip_vs_service *svc, struct ip_vs_dest *dest);
+ /* dest is unlinked */
+ int (*del_dest)(struct ip_vs_service *svc, struct ip_vs_dest *dest);
+ /* dest is updated */
+ int (*upd_dest)(struct ip_vs_service *svc, struct ip_vs_dest *dest);
/* selecting a server from the given service */
struct ip_vs_dest* (*schedule)(struct ip_vs_service *svc,
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 207c3b9..7bf62d0 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -304,8 +304,10 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
* template is not available.
* return *ignored=0 i.e. ICMP and NF_DROP
*/
+ rcu_read_lock();
dest = svc->scheduler->schedule(svc, skb);
if (!dest) {
+ rcu_read_unlock();
IP_VS_DBG(1, "p-schedule: no dest found.\n");
kfree(param.pe_data);
*ignored = 0;
@@ -321,6 +323,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
* when the template expires */
ct = ip_vs_conn_new(¶m, &dest->addr, dport,
IP_VS_CONN_F_TEMPLATE, dest, skb->mark);
+ rcu_read_unlock();
if (ct == NULL) {
kfree(param.pe_data);
*ignored = -1;
@@ -449,8 +452,10 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
return NULL;
}
+ rcu_read_lock();
dest = svc->scheduler->schedule(svc, skb);
if (dest == NULL) {
+ rcu_read_unlock();
IP_VS_DBG(1, "Schedule: no dest found.\n");
return NULL;
}
@@ -471,6 +476,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
cp = ip_vs_conn_new(&p, &dest->addr,
dest->port ? dest->port : pptr[1],
flags, dest, skb->mark);
+ rcu_read_unlock();
if (!cp) {
*ignored = -1;
return NULL;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index a66b1c7..ae765b8 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -823,6 +823,11 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
if (add) {
list_add(&dest->n_list, &svc->destinations);
svc->num_dests++;
+ if (svc->scheduler->add_dest)
+ svc->scheduler->add_dest(svc, dest);
+ } else {
+ if (svc->scheduler->upd_dest)
+ svc->scheduler->upd_dest(svc, dest);
}
/* call the update_service, because server weight may be changed */
@@ -1069,6 +1074,9 @@ static void __ip_vs_unlink_dest(struct ip_vs_service *svc,
list_del(&dest->n_list);
svc->num_dests--;
+ if (svcupd && svc->scheduler->del_dest)
+ svc->scheduler->del_dest(svc, dest);
+
/*
* Call the update_service function of its scheduler
*/
--
1.7.3.4
^ permalink raw reply related
* [PATCH net-next 05/19] ipvs: convert lblc scheduler to rcu
From: Julian Anastasov @ 2013-03-22 9:46 UTC (permalink / raw)
To: Simon Horman; +Cc: lvs-devel, netdev
In-Reply-To: <1363945614-11752-1-git-send-email-ja@ssi.bg>
The schedule method now needs _rcu list-traversal
primitive for svc->destinations. The read_lock for sched_lock is
removed. Use a dead flag to prevent new entries to be created
while scheduler is reclaimed. Use hlist for the hash table.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
---
net/netfilter/ipvs/ip_vs_lblc.c | 96 ++++++++++++++++++++++-----------------
1 files changed, 55 insertions(+), 41 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index fdd89b9..b873e17 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -90,11 +90,12 @@
* IP address and its destination server
*/
struct ip_vs_lblc_entry {
- struct list_head list;
+ struct hlist_node list;
int af; /* address family */
union nf_inet_addr addr; /* destination IP address */
- struct ip_vs_dest *dest; /* real server (cache) */
+ struct ip_vs_dest __rcu *dest; /* real server (cache) */
unsigned long lastuse; /* last used time */
+ struct rcu_head rcu_head;
};
@@ -102,12 +103,14 @@ struct ip_vs_lblc_entry {
* IPVS lblc hash table
*/
struct ip_vs_lblc_table {
- struct list_head bucket[IP_VS_LBLC_TAB_SIZE]; /* hash bucket */
+ struct rcu_head rcu_head;
+ struct hlist_head __rcu bucket[IP_VS_LBLC_TAB_SIZE]; /* hash bucket */
+ struct timer_list periodic_timer; /* collect stale entries */
atomic_t entries; /* number of entries */
int max_size; /* maximum size of entries */
- struct timer_list periodic_timer; /* collect stale entries */
int rover; /* rover for expire check */
int counter; /* counter for no expire */
+ bool dead;
};
@@ -129,13 +132,16 @@ static ctl_table vs_vars_table[] = {
static inline void ip_vs_lblc_free(struct ip_vs_lblc_entry *en)
{
- list_del(&en->list);
+ struct ip_vs_dest *dest;
+
+ hlist_del_rcu(&en->list);
/*
* We don't kfree dest because it is referred either by its service
* or the trash dest list.
*/
- atomic_dec(&en->dest->refcnt);
- kfree(en);
+ dest = rcu_dereference_protected(en->dest, 1);
+ ip_vs_dest_put(dest);
+ kfree_rcu(en, rcu_head);
}
@@ -165,15 +171,12 @@ ip_vs_lblc_hash(struct ip_vs_lblc_table *tbl, struct ip_vs_lblc_entry *en)
{
unsigned int hash = ip_vs_lblc_hashkey(en->af, &en->addr);
- list_add(&en->list, &tbl->bucket[hash]);
+ hlist_add_head_rcu(&en->list, &tbl->bucket[hash]);
atomic_inc(&tbl->entries);
}
-/*
- * Get ip_vs_lblc_entry associated with supplied parameters. Called under read
- * lock
- */
+/* Get ip_vs_lblc_entry associated with supplied parameters. */
static inline struct ip_vs_lblc_entry *
ip_vs_lblc_get(int af, struct ip_vs_lblc_table *tbl,
const union nf_inet_addr *addr)
@@ -181,7 +184,7 @@ ip_vs_lblc_get(int af, struct ip_vs_lblc_table *tbl,
unsigned int hash = ip_vs_lblc_hashkey(af, addr);
struct ip_vs_lblc_entry *en;
- list_for_each_entry(en, &tbl->bucket[hash], list)
+ hlist_for_each_entry_rcu(en, &tbl->bucket[hash], list)
if (ip_vs_addr_equal(af, &en->addr, addr))
return en;
@@ -209,14 +212,20 @@ ip_vs_lblc_new(struct ip_vs_lblc_table *tbl, const union nf_inet_addr *daddr,
ip_vs_addr_copy(dest->af, &en->addr, daddr);
en->lastuse = jiffies;
- atomic_inc(&dest->refcnt);
- en->dest = dest;
+ ip_vs_dest_hold(dest);
+ RCU_INIT_POINTER(en->dest, dest);
ip_vs_lblc_hash(tbl, en);
- } else if (en->dest != dest) {
- atomic_dec(&en->dest->refcnt);
- atomic_inc(&dest->refcnt);
- en->dest = dest;
+ } else {
+ struct ip_vs_dest *old_dest;
+
+ old_dest = rcu_dereference_protected(en->dest, 1);
+ if (old_dest != dest) {
+ ip_vs_dest_put(old_dest);
+ ip_vs_dest_hold(dest);
+ /* No ordering constraints for refcnt */
+ RCU_INIT_POINTER(en->dest, dest);
+ }
}
return en;
@@ -226,17 +235,22 @@ ip_vs_lblc_new(struct ip_vs_lblc_table *tbl, const union nf_inet_addr *daddr,
/*
* Flush all the entries of the specified table.
*/
-static void ip_vs_lblc_flush(struct ip_vs_lblc_table *tbl)
+static void ip_vs_lblc_flush(struct ip_vs_service *svc)
{
- struct ip_vs_lblc_entry *en, *nxt;
+ struct ip_vs_lblc_table *tbl = svc->sched_data;
+ struct ip_vs_lblc_entry *en;
+ struct hlist_node *next;
int i;
+ write_lock_bh(&svc->sched_lock);
+ tbl->dead = 1;
for (i=0; i<IP_VS_LBLC_TAB_SIZE; i++) {
- list_for_each_entry_safe(en, nxt, &tbl->bucket[i], list) {
+ hlist_for_each_entry_safe(en, next, &tbl->bucket[i], list) {
ip_vs_lblc_free(en);
atomic_dec(&tbl->entries);
}
}
+ write_unlock_bh(&svc->sched_lock);
}
static int sysctl_lblc_expiration(struct ip_vs_service *svc)
@@ -252,7 +266,8 @@ static int sysctl_lblc_expiration(struct ip_vs_service *svc)
static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc)
{
struct ip_vs_lblc_table *tbl = svc->sched_data;
- struct ip_vs_lblc_entry *en, *nxt;
+ struct ip_vs_lblc_entry *en;
+ struct hlist_node *next;
unsigned long now = jiffies;
int i, j;
@@ -260,7 +275,7 @@ static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc)
j = (j + 1) & IP_VS_LBLC_TAB_MASK;
write_lock(&svc->sched_lock);
- list_for_each_entry_safe(en, nxt, &tbl->bucket[j], list) {
+ hlist_for_each_entry_safe(en, next, &tbl->bucket[j], list) {
if (time_before(now,
en->lastuse +
sysctl_lblc_expiration(svc)))
@@ -293,7 +308,8 @@ static void ip_vs_lblc_check_expire(unsigned long data)
unsigned long now = jiffies;
int goal;
int i, j;
- struct ip_vs_lblc_entry *en, *nxt;
+ struct ip_vs_lblc_entry *en;
+ struct hlist_node *next;
if ((tbl->counter % COUNT_FOR_FULL_EXPIRATION) == 0) {
/* do full expiration check */
@@ -315,7 +331,7 @@ static void ip_vs_lblc_check_expire(unsigned long data)
j = (j + 1) & IP_VS_LBLC_TAB_MASK;
write_lock(&svc->sched_lock);
- list_for_each_entry_safe(en, nxt, &tbl->bucket[j], list) {
+ hlist_for_each_entry_safe(en, next, &tbl->bucket[j], list) {
if (time_before(now, en->lastuse + ENTRY_TIMEOUT))
continue;
@@ -354,11 +370,12 @@ static int ip_vs_lblc_init_svc(struct ip_vs_service *svc)
* Initialize the hash buckets
*/
for (i=0; i<IP_VS_LBLC_TAB_SIZE; i++) {
- INIT_LIST_HEAD(&tbl->bucket[i]);
+ INIT_HLIST_HEAD(&tbl->bucket[i]);
}
tbl->max_size = IP_VS_LBLC_TAB_SIZE*16;
tbl->rover = 0;
tbl->counter = 1;
+ tbl->dead = 0;
/*
* Hook periodic timer for garbage collection
@@ -379,10 +396,10 @@ static int ip_vs_lblc_done_svc(struct ip_vs_service *svc)
del_timer_sync(&tbl->periodic_timer);
/* got to clean up table entries here */
- ip_vs_lblc_flush(tbl);
+ ip_vs_lblc_flush(svc);
/* release the table itself */
- kfree(tbl);
+ kfree_rcu(tbl, rcu_head);
IP_VS_DBG(6, "LBLC hash table (memory=%Zdbytes) released\n",
sizeof(*tbl));
@@ -408,7 +425,7 @@ __ip_vs_lblc_schedule(struct ip_vs_service *svc)
* The server with weight=0 is quiesced and will not receive any
* new connection.
*/
- list_for_each_entry(dest, &svc->destinations, n_list) {
+ list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
if (dest->flags & IP_VS_DEST_F_OVERLOAD)
continue;
if (atomic_read(&dest->weight) > 0) {
@@ -423,7 +440,7 @@ __ip_vs_lblc_schedule(struct ip_vs_service *svc)
* Find the destination with the least load.
*/
nextstage:
- list_for_each_entry_continue(dest, &svc->destinations, n_list) {
+ list_for_each_entry_continue_rcu(dest, &svc->destinations, n_list) {
if (dest->flags & IP_VS_DEST_F_OVERLOAD)
continue;
@@ -457,7 +474,7 @@ is_overloaded(struct ip_vs_dest *dest, struct ip_vs_service *svc)
if (atomic_read(&dest->activeconns) > atomic_read(&dest->weight)) {
struct ip_vs_dest *d;
- list_for_each_entry(d, &svc->destinations, n_list) {
+ list_for_each_entry_rcu(d, &svc->destinations, n_list) {
if (atomic_read(&d->activeconns)*2
< atomic_read(&d->weight)) {
return 1;
@@ -484,7 +501,6 @@ ip_vs_lblc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
IP_VS_DBG(6, "%s(): Scheduling...\n", __func__);
/* First look in our cache */
- read_lock(&svc->sched_lock);
en = ip_vs_lblc_get(svc->af, tbl, &iph.daddr);
if (en) {
/* We only hold a read lock, but this is atomic */
@@ -499,14 +515,11 @@ ip_vs_lblc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
* free up entries from the trash at any time.
*/
- if (en->dest->flags & IP_VS_DEST_F_AVAILABLE)
- dest = en->dest;
+ dest = rcu_dereference(en->dest);
+ if ((dest->flags & IP_VS_DEST_F_AVAILABLE) &&
+ atomic_read(&dest->weight) > 0 && !is_overloaded(dest, svc))
+ goto out;
}
- read_unlock(&svc->sched_lock);
-
- /* If the destination has a weight and is not overloaded, use it */
- if (dest && atomic_read(&dest->weight) > 0 && !is_overloaded(dest, svc))
- goto out;
/* No cache entry or it is invalid, time to schedule */
dest = __ip_vs_lblc_schedule(svc);
@@ -517,7 +530,8 @@ ip_vs_lblc_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
/* If we fail to create a cache entry, we'll just use the valid dest */
write_lock(&svc->sched_lock);
- ip_vs_lblc_new(tbl, &iph.daddr, dest);
+ if (!tbl->dead)
+ ip_vs_lblc_new(tbl, &iph.daddr, dest);
write_unlock(&svc->sched_lock);
out:
--
1.7.3.4
^ permalink raw reply related
* [PATCH net-next 09/19] ipvs: convert rr scheduler to rcu
From: Julian Anastasov @ 2013-03-22 9:46 UTC (permalink / raw)
To: Simon Horman; +Cc: lvs-devel, netdev
In-Reply-To: <1363945614-11752-1-git-send-email-ja@ssi.bg>
The schedule method now needs _rcu list-traversal
primitive for svc->destinations. As the previous entry
could be unlinked, limit the list traversals to 2 when
lookup started from previous entry.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
---
net/netfilter/ipvs/ip_vs_rr.c | 55 ++++++++++++++++++++++++++---------------
1 files changed, 35 insertions(+), 20 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_rr.c b/net/netfilter/ipvs/ip_vs_rr.c
index c49b388..3942890 100644
--- a/net/netfilter/ipvs/ip_vs_rr.c
+++ b/net/netfilter/ipvs/ip_vs_rr.c
@@ -35,9 +35,18 @@ static int ip_vs_rr_init_svc(struct ip_vs_service *svc)
}
-static int ip_vs_rr_update_svc(struct ip_vs_service *svc)
+static int ip_vs_rr_del_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest)
{
- svc->sched_data = &svc->destinations;
+ struct list_head *p;
+
+ write_lock_bh(&svc->sched_lock);
+ p = (struct list_head *) svc->sched_data;
+ /* dest is already unlinked, so p->prev is not valid but
+ * p->next is valid, use it to reach previous entry.
+ */
+ if (p == &dest->n_list)
+ svc->sched_data = p->next->prev;
+ write_unlock_bh(&svc->sched_lock);
return 0;
}
@@ -48,35 +57,40 @@ static int ip_vs_rr_update_svc(struct ip_vs_service *svc)
static struct ip_vs_dest *
ip_vs_rr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
{
- struct list_head *p, *q;
- struct ip_vs_dest *dest;
+ struct list_head *p;
+ struct ip_vs_dest *dest, *last;
+ int pass = 0;
IP_VS_DBG(6, "%s(): Scheduling...\n", __func__);
write_lock(&svc->sched_lock);
- p = (struct list_head *)svc->sched_data;
- p = p->next;
- q = p;
+ p = (struct list_head *) svc->sched_data;
+ last = dest = list_entry(p, struct ip_vs_dest, n_list);
+
do {
- /* skip list head */
- if (q == &svc->destinations) {
- q = q->next;
- continue;
+ list_for_each_entry_continue_rcu(dest,
+ &svc->destinations,
+ n_list) {
+ if (!(dest->flags & IP_VS_DEST_F_OVERLOAD) &&
+ atomic_read(&dest->weight) > 0)
+ /* HIT */
+ goto out;
+ if (dest == last)
+ goto stop;
}
+ pass++;
+ /* Previous dest could be unlinked, do not loop forever.
+ * If we stay at head there is no need for 2nd pass.
+ */
+ } while (pass < 2 && p != &svc->destinations);
- dest = list_entry(q, struct ip_vs_dest, n_list);
- if (!(dest->flags & IP_VS_DEST_F_OVERLOAD) &&
- atomic_read(&dest->weight) > 0)
- /* HIT */
- goto out;
- q = q->next;
- } while (q != p);
+stop:
write_unlock(&svc->sched_lock);
ip_vs_scheduler_err(svc, "no destination available");
return NULL;
out:
- svc->sched_data = q;
+ svc->sched_data = &dest->n_list;
write_unlock(&svc->sched_lock);
IP_VS_DBG_BUF(6, "RR: server %s:%u "
"activeconns %d refcnt %d weight %d\n",
@@ -94,7 +108,8 @@ static struct ip_vs_scheduler ip_vs_rr_scheduler = {
.module = THIS_MODULE,
.n_list = LIST_HEAD_INIT(ip_vs_rr_scheduler.n_list),
.init_service = ip_vs_rr_init_svc,
- .update_service = ip_vs_rr_update_svc,
+ .add_dest = NULL,
+ .del_dest = ip_vs_rr_del_dest,
.schedule = ip_vs_rr_schedule,
};
--
1.7.3.4
^ permalink raw reply related
* [PATCH net-next 06/19] ipvs: convert lblcr scheduler to rcu
From: Julian Anastasov @ 2013-03-22 9:46 UTC (permalink / raw)
To: Simon Horman; +Cc: lvs-devel, netdev
In-Reply-To: <1363945614-11752-1-git-send-email-ja@ssi.bg>
The schedule method now needs _rcu list-traversal
primitive for svc->destinations. The read_lock for sched_lock is
removed. The set.lock is removed because now it is used in
rare cases, mostly under sched_lock.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
---
net/netfilter/ipvs/ip_vs_lblcr.c | 171 ++++++++++++++++++++------------------
1 files changed, 90 insertions(+), 81 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c
index c03b6a3..c22f173 100644
--- a/net/netfilter/ipvs/ip_vs_lblcr.c
+++ b/net/netfilter/ipvs/ip_vs_lblcr.c
@@ -89,40 +89,44 @@
*/
struct ip_vs_dest_set_elem {
struct list_head list; /* list link */
- struct ip_vs_dest *dest; /* destination server */
+ struct ip_vs_dest __rcu *dest; /* destination server */
+ struct rcu_head rcu_head;
};
struct ip_vs_dest_set {
atomic_t size; /* set size */
unsigned long lastmod; /* last modified time */
struct list_head list; /* destination list */
- rwlock_t lock; /* lock for this list */
};
-static struct ip_vs_dest_set_elem *
-ip_vs_dest_set_insert(struct ip_vs_dest_set *set, struct ip_vs_dest *dest)
+static void ip_vs_dest_set_insert(struct ip_vs_dest_set *set,
+ struct ip_vs_dest *dest, bool check)
{
struct ip_vs_dest_set_elem *e;
- list_for_each_entry(e, &set->list, list) {
- if (e->dest == dest)
- /* already existed */
- return NULL;
+ if (check) {
+ list_for_each_entry(e, &set->list, list) {
+ struct ip_vs_dest *d;
+
+ d = rcu_dereference_protected(e->dest, 1);
+ if (d == dest)
+ /* already existed */
+ return;
+ }
}
e = kmalloc(sizeof(*e), GFP_ATOMIC);
if (e == NULL)
- return NULL;
+ return;
- atomic_inc(&dest->refcnt);
- e->dest = dest;
+ ip_vs_dest_hold(dest);
+ RCU_INIT_POINTER(e->dest, dest);
- list_add(&e->list, &set->list);
+ list_add_rcu(&e->list, &set->list);
atomic_inc(&set->size);
set->lastmod = jiffies;
- return e;
}
static void
@@ -131,13 +135,16 @@ ip_vs_dest_set_erase(struct ip_vs_dest_set *set, struct ip_vs_dest *dest)
struct ip_vs_dest_set_elem *e;
list_for_each_entry(e, &set->list, list) {
- if (e->dest == dest) {
+ struct ip_vs_dest *d;
+
+ d = rcu_dereference_protected(e->dest, 1);
+ if (d == dest) {
/* HIT */
atomic_dec(&set->size);
set->lastmod = jiffies;
- atomic_dec(&e->dest->refcnt);
- list_del(&e->list);
- kfree(e);
+ ip_vs_dest_put(dest);
+ list_del_rcu(&e->list);
+ kfree_rcu(e, rcu_head);
break;
}
}
@@ -147,17 +154,18 @@ static void ip_vs_dest_set_eraseall(struct ip_vs_dest_set *set)
{
struct ip_vs_dest_set_elem *e, *ep;
- write_lock(&set->lock);
list_for_each_entry_safe(e, ep, &set->list, list) {
+ struct ip_vs_dest *d;
+
+ d = rcu_dereference_protected(e->dest, 1);
/*
* We don't kfree dest because it is referred either
* by its service or by the trash dest list.
*/
- atomic_dec(&e->dest->refcnt);
- list_del(&e->list);
- kfree(e);
+ ip_vs_dest_put(d);
+ list_del_rcu(&e->list);
+ kfree_rcu(e, rcu_head);
}
- write_unlock(&set->lock);
}
/* get weighted least-connection node in the destination set */
@@ -171,8 +179,8 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set)
return NULL;
/* select the first destination server, whose weight > 0 */
- list_for_each_entry(e, &set->list, list) {
- least = e->dest;
+ list_for_each_entry_rcu(e, &set->list, list) {
+ least = rcu_dereference(e->dest);
if (least->flags & IP_VS_DEST_F_OVERLOAD)
continue;
@@ -186,8 +194,8 @@ static inline struct ip_vs_dest *ip_vs_dest_set_min(struct ip_vs_dest_set *set)
/* find the destination with the weighted least load */
nextstage:
- list_for_each_entry(e, &set->list, list) {
- dest = e->dest;
+ list_for_each_entry_continue_rcu(e, &set->list, list) {
+ dest = rcu_dereference(e->dest);
if (dest->flags & IP_VS_DEST_F_OVERLOAD)
continue;
@@ -224,7 +232,7 @@ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set)
/* select the first destination server, whose weight > 0 */
list_for_each_entry(e, &set->list, list) {
- most = e->dest;
+ most = rcu_dereference_protected(e->dest, 1);
if (atomic_read(&most->weight) > 0) {
moh = ip_vs_dest_conn_overhead(most);
goto nextstage;
@@ -234,8 +242,8 @@ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set)
/* find the destination with the weighted most load */
nextstage:
- list_for_each_entry(e, &set->list, list) {
- dest = e->dest;
+ list_for_each_entry_continue(e, &set->list, list) {
+ dest = rcu_dereference_protected(e->dest, 1);
doh = ip_vs_dest_conn_overhead(dest);
/* moh/mw < doh/dw ==> moh*dw < doh*mw, where mw,dw>0 */
if ((moh * atomic_read(&dest->weight) <
@@ -262,11 +270,12 @@ static inline struct ip_vs_dest *ip_vs_dest_set_max(struct ip_vs_dest_set *set)
* IP address and its destination server set
*/
struct ip_vs_lblcr_entry {
- struct list_head list;
+ struct hlist_node list;
int af; /* address family */
union nf_inet_addr addr; /* destination IP address */
struct ip_vs_dest_set set; /* destination server set */
unsigned long lastuse; /* last used time */
+ struct rcu_head rcu_head;
};
@@ -274,12 +283,14 @@ struct ip_vs_lblcr_entry {
* IPVS lblcr hash table
*/
struct ip_vs_lblcr_table {
- struct list_head bucket[IP_VS_LBLCR_TAB_SIZE]; /* hash bucket */
+ struct rcu_head rcu_head;
+ struct hlist_head __rcu bucket[IP_VS_LBLCR_TAB_SIZE]; /* hash bucket */
atomic_t entries; /* number of entries */
int max_size; /* maximum size of entries */
struct timer_list periodic_timer; /* collect stale entries */
int rover; /* rover for expire check */
int counter; /* counter for no expire */
+ bool dead;
};
@@ -302,9 +313,9 @@ static ctl_table vs_vars_table[] = {
static inline void ip_vs_lblcr_free(struct ip_vs_lblcr_entry *en)
{
- list_del(&en->list);
+ hlist_del_rcu(&en->list);
ip_vs_dest_set_eraseall(&en->set);
- kfree(en);
+ kfree_rcu(en, rcu_head);
}
@@ -334,15 +345,12 @@ ip_vs_lblcr_hash(struct ip_vs_lblcr_table *tbl, struct ip_vs_lblcr_entry *en)
{
unsigned int hash = ip_vs_lblcr_hashkey(en->af, &en->addr);
- list_add(&en->list, &tbl->bucket[hash]);
+ hlist_add_head_rcu(&en->list, &tbl->bucket[hash]);
atomic_inc(&tbl->entries);
}
-/*
- * Get ip_vs_lblcr_entry associated with supplied parameters. Called under
- * read lock.
- */
+/* Get ip_vs_lblcr_entry associated with supplied parameters. */
static inline struct ip_vs_lblcr_entry *
ip_vs_lblcr_get(int af, struct ip_vs_lblcr_table *tbl,
const union nf_inet_addr *addr)
@@ -350,7 +358,7 @@ ip_vs_lblcr_get(int af, struct ip_vs_lblcr_table *tbl,
unsigned int hash = ip_vs_lblcr_hashkey(af, addr);
struct ip_vs_lblcr_entry *en;
- list_for_each_entry(en, &tbl->bucket[hash], list)
+ hlist_for_each_entry_rcu(en, &tbl->bucket[hash], list)
if (ip_vs_addr_equal(af, &en->addr, addr))
return en;
@@ -381,14 +389,14 @@ ip_vs_lblcr_new(struct ip_vs_lblcr_table *tbl, const union nf_inet_addr *daddr,
/* initialize its dest set */
atomic_set(&(en->set.size), 0);
INIT_LIST_HEAD(&en->set.list);
- rwlock_init(&en->set.lock);
+
+ ip_vs_dest_set_insert(&en->set, dest, false);
ip_vs_lblcr_hash(tbl, en);
+ return en;
}
- write_lock(&en->set.lock);
- ip_vs_dest_set_insert(&en->set, dest);
- write_unlock(&en->set.lock);
+ ip_vs_dest_set_insert(&en->set, dest, true);
return en;
}
@@ -397,17 +405,21 @@ ip_vs_lblcr_new(struct ip_vs_lblcr_table *tbl, const union nf_inet_addr *daddr,
/*
* Flush all the entries of the specified table.
*/
-static void ip_vs_lblcr_flush(struct ip_vs_lblcr_table *tbl)
+static void ip_vs_lblcr_flush(struct ip_vs_service *svc)
{
+ struct ip_vs_lblcr_table *tbl = svc->sched_data;
int i;
- struct ip_vs_lblcr_entry *en, *nxt;
+ struct ip_vs_lblcr_entry *en;
+ struct hlist_node *next;
- /* No locking required, only called during cleanup. */
+ write_lock_bh(&svc->sched_lock);
+ tbl->dead = 1;
for (i=0; i<IP_VS_LBLCR_TAB_SIZE; i++) {
- list_for_each_entry_safe(en, nxt, &tbl->bucket[i], list) {
+ hlist_for_each_entry_safe(en, next, &tbl->bucket[i], list) {
ip_vs_lblcr_free(en);
}
}
+ write_unlock_bh(&svc->sched_lock);
}
static int sysctl_lblcr_expiration(struct ip_vs_service *svc)
@@ -425,13 +437,14 @@ static inline void ip_vs_lblcr_full_check(struct ip_vs_service *svc)
struct ip_vs_lblcr_table *tbl = svc->sched_data;
unsigned long now = jiffies;
int i, j;
- struct ip_vs_lblcr_entry *en, *nxt;
+ struct ip_vs_lblcr_entry *en;
+ struct hlist_node *next;
for (i=0, j=tbl->rover; i<IP_VS_LBLCR_TAB_SIZE; i++) {
j = (j + 1) & IP_VS_LBLCR_TAB_MASK;
write_lock(&svc->sched_lock);
- list_for_each_entry_safe(en, nxt, &tbl->bucket[j], list) {
+ hlist_for_each_entry_safe(en, next, &tbl->bucket[j], list) {
if (time_after(en->lastuse +
sysctl_lblcr_expiration(svc), now))
continue;
@@ -463,7 +476,8 @@ static void ip_vs_lblcr_check_expire(unsigned long data)
unsigned long now = jiffies;
int goal;
int i, j;
- struct ip_vs_lblcr_entry *en, *nxt;
+ struct ip_vs_lblcr_entry *en;
+ struct hlist_node *next;
if ((tbl->counter % COUNT_FOR_FULL_EXPIRATION) == 0) {
/* do full expiration check */
@@ -485,7 +499,7 @@ static void ip_vs_lblcr_check_expire(unsigned long data)
j = (j + 1) & IP_VS_LBLCR_TAB_MASK;
write_lock(&svc->sched_lock);
- list_for_each_entry_safe(en, nxt, &tbl->bucket[j], list) {
+ hlist_for_each_entry_safe(en, next, &tbl->bucket[j], list) {
if (time_before(now, en->lastuse+ENTRY_TIMEOUT))
continue;
@@ -523,11 +537,12 @@ static int ip_vs_lblcr_init_svc(struct ip_vs_service *svc)
* Initialize the hash buckets
*/
for (i=0; i<IP_VS_LBLCR_TAB_SIZE; i++) {
- INIT_LIST_HEAD(&tbl->bucket[i]);
+ INIT_HLIST_HEAD(&tbl->bucket[i]);
}
tbl->max_size = IP_VS_LBLCR_TAB_SIZE*16;
tbl->rover = 0;
tbl->counter = 1;
+ tbl->dead = 0;
/*
* Hook periodic timer for garbage collection
@@ -548,10 +563,10 @@ static int ip_vs_lblcr_done_svc(struct ip_vs_service *svc)
del_timer_sync(&tbl->periodic_timer);
/* got to clean up table entries here */
- ip_vs_lblcr_flush(tbl);
+ ip_vs_lblcr_flush(svc);
/* release the table itself */
- kfree(tbl);
+ kfree_rcu(tbl, rcu_head);
IP_VS_DBG(6, "LBLCR hash table (memory=%Zdbytes) released\n",
sizeof(*tbl));
@@ -577,7 +592,7 @@ __ip_vs_lblcr_schedule(struct ip_vs_service *svc)
* The server with weight=0 is quiesced and will not receive any
* new connection.
*/
- list_for_each_entry(dest, &svc->destinations, n_list) {
+ list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
if (dest->flags & IP_VS_DEST_F_OVERLOAD)
continue;
@@ -593,7 +608,7 @@ __ip_vs_lblcr_schedule(struct ip_vs_service *svc)
* Find the destination with the least load.
*/
nextstage:
- list_for_each_entry_continue(dest, &svc->destinations, n_list) {
+ list_for_each_entry_continue_rcu(dest, &svc->destinations, n_list) {
if (dest->flags & IP_VS_DEST_F_OVERLOAD)
continue;
@@ -627,7 +642,7 @@ is_overloaded(struct ip_vs_dest *dest, struct ip_vs_service *svc)
if (atomic_read(&dest->activeconns) > atomic_read(&dest->weight)) {
struct ip_vs_dest *d;
- list_for_each_entry(d, &svc->destinations, n_list) {
+ list_for_each_entry_rcu(d, &svc->destinations, n_list) {
if (atomic_read(&d->activeconns)*2
< atomic_read(&d->weight)) {
return 1;
@@ -646,7 +661,7 @@ ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
{
struct ip_vs_lblcr_table *tbl = svc->sched_data;
struct ip_vs_iphdr iph;
- struct ip_vs_dest *dest = NULL;
+ struct ip_vs_dest *dest;
struct ip_vs_lblcr_entry *en;
ip_vs_fill_iph_addr_only(svc->af, skb, &iph);
@@ -654,53 +669,46 @@ ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
IP_VS_DBG(6, "%s(): Scheduling...\n", __func__);
/* First look in our cache */
- read_lock(&svc->sched_lock);
en = ip_vs_lblcr_get(svc->af, tbl, &iph.daddr);
if (en) {
- /* We only hold a read lock, but this is atomic */
en->lastuse = jiffies;
/* Get the least loaded destination */
- read_lock(&en->set.lock);
dest = ip_vs_dest_set_min(&en->set);
- read_unlock(&en->set.lock);
/* More than one destination + enough time passed by, cleanup */
if (atomic_read(&en->set.size) > 1 &&
- time_after(jiffies, en->set.lastmod +
+ time_after(jiffies, en->set.lastmod +
sysctl_lblcr_expiration(svc))) {
- struct ip_vs_dest *m;
+ write_lock(&svc->sched_lock);
+ if (atomic_read(&en->set.size) > 1) {
+ struct ip_vs_dest *m;
- write_lock(&en->set.lock);
- m = ip_vs_dest_set_max(&en->set);
- if (m)
- ip_vs_dest_set_erase(&en->set, m);
- write_unlock(&en->set.lock);
+ m = ip_vs_dest_set_max(&en->set);
+ if (m)
+ ip_vs_dest_set_erase(&en->set, m);
+ }
+ write_unlock(&svc->sched_lock);
}
/* If the destination is not overloaded, use it */
- if (dest && !is_overloaded(dest, svc)) {
- read_unlock(&svc->sched_lock);
+ if (dest && !is_overloaded(dest, svc))
goto out;
- }
/* The cache entry is invalid, time to schedule */
dest = __ip_vs_lblcr_schedule(svc);
if (!dest) {
ip_vs_scheduler_err(svc, "no destination available");
- read_unlock(&svc->sched_lock);
return NULL;
}
/* Update our cache entry */
- write_lock(&en->set.lock);
- ip_vs_dest_set_insert(&en->set, dest);
- write_unlock(&en->set.lock);
- }
- read_unlock(&svc->sched_lock);
-
- if (dest)
+ write_lock(&svc->sched_lock);
+ if (!tbl->dead)
+ ip_vs_dest_set_insert(&en->set, dest, true);
+ write_unlock(&svc->sched_lock);
goto out;
+ }
/* No cache entry, time to schedule */
dest = __ip_vs_lblcr_schedule(svc);
@@ -711,7 +719,8 @@ ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
/* If we fail to create a cache entry, we'll just use the valid dest */
write_lock(&svc->sched_lock);
- ip_vs_lblcr_new(tbl, &iph.daddr, dest);
+ if (!tbl->dead)
+ ip_vs_lblcr_new(tbl, &iph.daddr, dest);
write_unlock(&svc->sched_lock);
out:
--
1.7.3.4
^ permalink raw reply related
* [PATCH net-next 10/19] ipvs: convert sed scheduler to rcu
From: Julian Anastasov @ 2013-03-22 9:46 UTC (permalink / raw)
To: Simon Horman; +Cc: lvs-devel, netdev
In-Reply-To: <1363945614-11752-1-git-send-email-ja@ssi.bg>
The schedule method now needs _rcu list-traversal
primitive for svc->destinations.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
---
net/netfilter/ipvs/ip_vs_sed.c | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_sed.c b/net/netfilter/ipvs/ip_vs_sed.c
index 89ead246..d011870 100644
--- a/net/netfilter/ipvs/ip_vs_sed.c
+++ b/net/netfilter/ipvs/ip_vs_sed.c
@@ -79,7 +79,7 @@ ip_vs_sed_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
* new connections.
*/
- list_for_each_entry(dest, &svc->destinations, n_list) {
+ list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
if (!(dest->flags & IP_VS_DEST_F_OVERLOAD) &&
atomic_read(&dest->weight) > 0) {
least = dest;
@@ -94,7 +94,7 @@ ip_vs_sed_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
* Find the destination with the least load.
*/
nextstage:
- list_for_each_entry_continue(dest, &svc->destinations, n_list) {
+ list_for_each_entry_continue_rcu(dest, &svc->destinations, n_list) {
if (dest->flags & IP_VS_DEST_F_OVERLOAD)
continue;
doh = ip_vs_sed_dest_overhead(dest);
--
1.7.3.4
^ permalink raw reply related
* [PATCH net-next 01/19] ipvs: change ip_vs_sched_lock to mutex
From: Julian Anastasov @ 2013-03-22 9:46 UTC (permalink / raw)
To: Simon Horman; +Cc: lvs-devel, netdev
In-Reply-To: <1363945614-11752-1-git-send-email-ja@ssi.bg>
The global list with schedulers ip_vs_schedulers
is accessed only from user context - configuration and
scheduler module [un]registration. Use ip_vs_sched_mutex
instead.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
---
net/netfilter/ipvs/ip_vs_sched.c | 24 ++++++++++++------------
1 files changed, 12 insertions(+), 12 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_sched.c b/net/netfilter/ipvs/ip_vs_sched.c
index d6bf20d..7f11d3d 100644
--- a/net/netfilter/ipvs/ip_vs_sched.c
+++ b/net/netfilter/ipvs/ip_vs_sched.c
@@ -35,8 +35,8 @@ EXPORT_SYMBOL(ip_vs_scheduler_err);
*/
static LIST_HEAD(ip_vs_schedulers);
-/* lock for service table */
-static DEFINE_SPINLOCK(ip_vs_sched_lock);
+/* semaphore for schedulers */
+static DEFINE_MUTEX(ip_vs_sched_mutex);
/*
@@ -92,7 +92,7 @@ static struct ip_vs_scheduler *ip_vs_sched_getbyname(const char *sched_name)
IP_VS_DBG(2, "%s(): sched_name \"%s\"\n", __func__, sched_name);
- spin_lock_bh(&ip_vs_sched_lock);
+ mutex_lock(&ip_vs_sched_mutex);
list_for_each_entry(sched, &ip_vs_schedulers, n_list) {
/*
@@ -106,14 +106,14 @@ static struct ip_vs_scheduler *ip_vs_sched_getbyname(const char *sched_name)
}
if (strcmp(sched_name, sched->name)==0) {
/* HIT */
- spin_unlock_bh(&ip_vs_sched_lock);
+ mutex_unlock(&ip_vs_sched_mutex);
return sched;
}
if (sched->module)
module_put(sched->module);
}
- spin_unlock_bh(&ip_vs_sched_lock);
+ mutex_unlock(&ip_vs_sched_mutex);
return NULL;
}
@@ -192,10 +192,10 @@ int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler)
/* increase the module use count */
ip_vs_use_count_inc();
- spin_lock_bh(&ip_vs_sched_lock);
+ mutex_lock(&ip_vs_sched_mutex);
if (!list_empty(&scheduler->n_list)) {
- spin_unlock_bh(&ip_vs_sched_lock);
+ mutex_unlock(&ip_vs_sched_mutex);
ip_vs_use_count_dec();
pr_err("%s(): [%s] scheduler already linked\n",
__func__, scheduler->name);
@@ -208,7 +208,7 @@ int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler)
*/
list_for_each_entry(sched, &ip_vs_schedulers, n_list) {
if (strcmp(scheduler->name, sched->name) == 0) {
- spin_unlock_bh(&ip_vs_sched_lock);
+ mutex_unlock(&ip_vs_sched_mutex);
ip_vs_use_count_dec();
pr_err("%s(): [%s] scheduler already existed "
"in the system\n", __func__, scheduler->name);
@@ -219,7 +219,7 @@ int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler)
* Add it into the d-linked scheduler list
*/
list_add(&scheduler->n_list, &ip_vs_schedulers);
- spin_unlock_bh(&ip_vs_sched_lock);
+ mutex_unlock(&ip_vs_sched_mutex);
pr_info("[%s] scheduler registered.\n", scheduler->name);
@@ -237,9 +237,9 @@ int unregister_ip_vs_scheduler(struct ip_vs_scheduler *scheduler)
return -EINVAL;
}
- spin_lock_bh(&ip_vs_sched_lock);
+ mutex_lock(&ip_vs_sched_mutex);
if (list_empty(&scheduler->n_list)) {
- spin_unlock_bh(&ip_vs_sched_lock);
+ mutex_unlock(&ip_vs_sched_mutex);
pr_err("%s(): [%s] scheduler is not in the list. failed\n",
__func__, scheduler->name);
return -EINVAL;
@@ -249,7 +249,7 @@ int unregister_ip_vs_scheduler(struct ip_vs_scheduler *scheduler)
* Remove it from the d-linked scheduler list
*/
list_del(&scheduler->n_list);
- spin_unlock_bh(&ip_vs_sched_lock);
+ mutex_unlock(&ip_vs_sched_mutex);
/* decrease the module use count */
ip_vs_use_count_dec();
--
1.7.3.4
^ permalink raw reply related
* [PATCH net-next 04/19] ipvs: convert dh scheduler to rcu
From: Julian Anastasov @ 2013-03-22 9:46 UTC (permalink / raw)
To: Simon Horman; +Cc: lvs-devel, netdev
In-Reply-To: <1363945614-11752-1-git-send-email-ja@ssi.bg>
Use the new add_dest and del_dest methods
to reassign dests.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
---
net/netfilter/ipvs/ip_vs_dh.c | 81 +++++++++++++++++++++++------------------
1 files 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,
};
--
1.7.3.4
^ permalink raw reply related
* [PATCH net-next 08/19] ipvs: convert nq scheduler to rcu
From: Julian Anastasov @ 2013-03-22 9:46 UTC (permalink / raw)
To: Simon Horman; +Cc: lvs-devel, netdev
In-Reply-To: <1363945614-11752-1-git-send-email-ja@ssi.bg>
The schedule method now needs _rcu list-traversal
primitive for svc->destinations.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
---
net/netfilter/ipvs/ip_vs_nq.c | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_nq.c b/net/netfilter/ipvs/ip_vs_nq.c
index 984d9c1..51dc0cf 100644
--- a/net/netfilter/ipvs/ip_vs_nq.c
+++ b/net/netfilter/ipvs/ip_vs_nq.c
@@ -75,7 +75,7 @@ ip_vs_nq_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
* new connections.
*/
- list_for_each_entry(dest, &svc->destinations, n_list) {
+ list_for_each_entry_rcu(dest, &svc->destinations, n_list) {
if (dest->flags & IP_VS_DEST_F_OVERLOAD ||
!atomic_read(&dest->weight))
--
1.7.3.4
^ permalink raw reply related
* [PATCH net-next 11/19] ipvs: convert sh scheduler to rcu
From: Julian Anastasov @ 2013-03-22 9:46 UTC (permalink / raw)
To: Simon Horman; +Cc: lvs-devel, netdev
In-Reply-To: <1363945614-11752-1-git-send-email-ja@ssi.bg>
Use the 3 new methods to reassign dests.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
---
net/netfilter/ipvs/ip_vs_sh.c | 81 +++++++++++++++++++++++------------------
1 files changed, 45 insertions(+), 36 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c
index e331269..55e76d8 100644
--- a/net/netfilter/ipvs/ip_vs_sh.c
+++ b/net/netfilter/ipvs/ip_vs_sh.c
@@ -53,7 +53,7 @@
* IPVS SH bucket
*/
struct ip_vs_sh_bucket {
- struct ip_vs_dest *dest; /* real server (cache) */
+ struct ip_vs_dest __rcu *dest; /* real server (cache) */
};
/*
@@ -66,6 +66,10 @@ struct ip_vs_sh_bucket {
#define IP_VS_SH_TAB_SIZE (1 << IP_VS_SH_TAB_BITS)
#define IP_VS_SH_TAB_MASK (IP_VS_SH_TAB_SIZE - 1)
+struct ip_vs_sh_state {
+ struct ip_vs_sh_bucket buckets[IP_VS_SH_TAB_SIZE];
+ struct rcu_head rcu_head;
+};
/*
* Returns hash value for IPVS SH entry
@@ -87,10 +91,9 @@ static inline unsigned int ip_vs_sh_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_sh_get(int af, struct ip_vs_sh_bucket *tbl,
- const union nf_inet_addr *addr)
+ip_vs_sh_get(int af, struct ip_vs_sh_state *s, const union nf_inet_addr *addr)
{
- return (tbl[ip_vs_sh_hashkey(af, addr)]).dest;
+ return rcu_dereference(s->buckets[ip_vs_sh_hashkey(af, addr)].dest);
}
@@ -98,27 +101,32 @@ ip_vs_sh_get(int af, struct ip_vs_sh_bucket *tbl,
* Assign all the hash buckets of the specified table with the service.
*/
static int
-ip_vs_sh_assign(struct ip_vs_sh_bucket *tbl, struct ip_vs_service *svc)
+ip_vs_sh_reassign(struct ip_vs_sh_state *s, struct ip_vs_service *svc)
{
int i;
struct ip_vs_sh_bucket *b;
struct list_head *p;
struct ip_vs_dest *dest;
int d_count;
+ bool empty;
- b = tbl;
+ b = &s->buckets[0];
p = &svc->destinations;
+ empty = list_empty(p);
d_count = 0;
for (i=0; i<IP_VS_SH_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);
IP_VS_DBG_BUF(6, "assigned i: %d dest: %s weight: %d\n",
i, IP_VS_DBG_ADDR(svc->af, &dest->addr),
@@ -140,16 +148,18 @@ ip_vs_sh_assign(struct ip_vs_sh_bucket *tbl, struct ip_vs_service *svc)
/*
* Flush all the hash buckets of the specified table.
*/
-static void ip_vs_sh_flush(struct ip_vs_sh_bucket *tbl)
+static void ip_vs_sh_flush(struct ip_vs_sh_state *s)
{
int i;
struct ip_vs_sh_bucket *b;
+ struct ip_vs_dest *dest;
- b = tbl;
+ b = &s->buckets[0];
for (i=0; i<IP_VS_SH_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++;
}
@@ -158,21 +168,20 @@ static void ip_vs_sh_flush(struct ip_vs_sh_bucket *tbl)
static int ip_vs_sh_init_svc(struct ip_vs_service *svc)
{
- struct ip_vs_sh_bucket *tbl;
+ struct ip_vs_sh_state *s;
/* allocate the SH table for this service */
- tbl = kmalloc(sizeof(struct ip_vs_sh_bucket)*IP_VS_SH_TAB_SIZE,
- GFP_KERNEL);
- if (tbl == NULL)
+ s = kzalloc(sizeof(struct ip_vs_sh_state), GFP_KERNEL);
+ if (s == NULL)
return -ENOMEM;
- svc->sched_data = tbl;
+ svc->sched_data = s;
IP_VS_DBG(6, "SH hash table (memory=%Zdbytes) allocated for "
"current service\n",
sizeof(struct ip_vs_sh_bucket)*IP_VS_SH_TAB_SIZE);
- /* assign the hash buckets with the updated service */
- ip_vs_sh_assign(tbl, svc);
+ /* assign the hash buckets with current dests */
+ ip_vs_sh_reassign(s, svc);
return 0;
}
@@ -180,13 +189,13 @@ static int ip_vs_sh_init_svc(struct ip_vs_service *svc)
static int ip_vs_sh_done_svc(struct ip_vs_service *svc)
{
- struct ip_vs_sh_bucket *tbl = svc->sched_data;
+ struct ip_vs_sh_state *s = svc->sched_data;
/* got to clean up hash buckets here */
- ip_vs_sh_flush(tbl);
+ ip_vs_sh_flush(s);
/* release the table itself */
- kfree(svc->sched_data);
+ kfree_rcu(s, rcu_head);
IP_VS_DBG(6, "SH hash table (memory=%Zdbytes) released\n",
sizeof(struct ip_vs_sh_bucket)*IP_VS_SH_TAB_SIZE);
@@ -194,15 +203,13 @@ static int ip_vs_sh_done_svc(struct ip_vs_service *svc)
}
-static int ip_vs_sh_update_svc(struct ip_vs_service *svc)
+static int ip_vs_sh_dest_changed(struct ip_vs_service *svc,
+ struct ip_vs_dest *dest)
{
- struct ip_vs_sh_bucket *tbl = svc->sched_data;
-
- /* got to clean up hash buckets here */
- ip_vs_sh_flush(tbl);
+ struct ip_vs_sh_state *s = svc->sched_data;
/* assign the hash buckets with the updated service */
- ip_vs_sh_assign(tbl, svc);
+ ip_vs_sh_reassign(s, svc);
return 0;
}
@@ -225,15 +232,15 @@ static struct ip_vs_dest *
ip_vs_sh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
{
struct ip_vs_dest *dest;
- struct ip_vs_sh_bucket *tbl;
+ struct ip_vs_sh_state *s;
struct ip_vs_iphdr iph;
ip_vs_fill_iph_addr_only(svc->af, skb, &iph);
IP_VS_DBG(6, "ip_vs_sh_schedule(): Scheduling...\n");
- tbl = (struct ip_vs_sh_bucket *)svc->sched_data;
- dest = ip_vs_sh_get(svc->af, tbl, &iph.saddr);
+ s = (struct ip_vs_sh_state *) svc->sched_data;
+ dest = ip_vs_sh_get(svc->af, s, &iph.saddr);
if (!dest
|| !(dest->flags & IP_VS_DEST_F_AVAILABLE)
|| atomic_read(&dest->weight) <= 0
@@ -262,7 +269,9 @@ static struct ip_vs_scheduler ip_vs_sh_scheduler =
.n_list = LIST_HEAD_INIT(ip_vs_sh_scheduler.n_list),
.init_service = ip_vs_sh_init_svc,
.done_service = ip_vs_sh_done_svc,
- .update_service = ip_vs_sh_update_svc,
+ .add_dest = ip_vs_sh_dest_changed,
+ .del_dest = ip_vs_sh_dest_changed,
+ .upd_dest = ip_vs_sh_dest_changed,
.schedule = ip_vs_sh_schedule,
};
--
1.7.3.4
^ permalink raw reply related
* [PATCH net-next 03/19] ipvs: add ip_vs_dest_hold and ip_vs_dest_put
From: Julian Anastasov @ 2013-03-22 9:46 UTC (permalink / raw)
To: Simon Horman; +Cc: lvs-devel, netdev
In-Reply-To: <1363945614-11752-1-git-send-email-ja@ssi.bg>
ip_vs_dest_hold will be used under RCU lock
while ip_vs_dest_put can be called even after dest
is removed from service, as it happens for conns and
some schedulers.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
---
include/net/ip_vs.h | 10 ++++++++++
net/netfilter/ipvs/ip_vs_conn.c | 9 ++-------
net/netfilter/ipvs/ip_vs_ctl.c | 4 ++--
net/netfilter/ipvs/ip_vs_sync.c | 4 ++--
4 files changed, 16 insertions(+), 11 deletions(-)
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 5af338b..2752c86 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1427,6 +1427,16 @@ ip_vs_find_dest(struct net *net, int af, const union nf_inet_addr *daddr,
__u16 protocol, __u32 fwmark, __u32 flags);
extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp);
+static inline void ip_vs_dest_hold(struct ip_vs_dest *dest)
+{
+ atomic_inc(&dest->refcnt);
+}
+
+static inline void ip_vs_dest_put(struct ip_vs_dest *dest)
+{
+ smp_mb__before_atomic_dec();
+ atomic_dec(&dest->refcnt);
+}
/*
* IPVS sync daemon data and function prototypes
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index e3e2b4d..1b29e4a 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -554,7 +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)
@@ -700,12 +700,7 @@ 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,
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index ae765b8..36d9cd8 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -614,7 +614,7 @@ struct ip_vs_dest *ip_vs_find_dest(struct net *net, int af,
if (!dest)
dest = ip_vs_lookup_dest(svc, daddr, port ^ dport);
if (dest)
- atomic_inc(&dest->refcnt);
+ ip_vs_dest_hold(dest);
ip_vs_service_put(svc);
return dest;
}
@@ -1054,7 +1054,7 @@ static void __ip_vs_del_dest(struct net *net, struct ip_vs_dest *dest)
ntohs(dest->port),
atomic_read(&dest->refcnt));
list_add(&dest->n_list, &ipvs->dest_trash);
- atomic_inc(&dest->refcnt);
+ ip_vs_dest_hold(dest);
}
}
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 44fd10c..6cc3e52 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -861,7 +861,7 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
if (!dest) {
dest = ip_vs_try_bind_dest(cp);
if (dest)
- atomic_dec(&dest->refcnt);
+ ip_vs_dest_put(dest);
}
} else {
/*
@@ -874,7 +874,7 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
cp = ip_vs_conn_new(param, daddr, dport, flags, dest, fwmark);
if (dest)
- atomic_dec(&dest->refcnt);
+ ip_vs_dest_put(dest);
if (!cp) {
if (param->pe_data)
kfree(param->pe_data);
--
1.7.3.4
^ permalink raw reply related
* Re: [PATCH] ath9k : Fix ieee80211 work while going to suspend
From: Stanislaw Gruszka @ 2013-03-22 9:13 UTC (permalink / raw)
To: Luis R. Rodriguez
Cc: John W. Linville, Parag Warudkar, Jouni Malinen,
Vasanthakumar Thiagarajan, linux-wireless-u79uwXL29TY76Z2rM5mHXA,
ath9k-devel-juf53994utBLZpfksSYvnA, netdev-u79uwXL29TY76Z2rM5mHXA,
LKML, senthilb-A+ZNKFmMK5xy9aJCnZT0Uw
In-Reply-To: <20130321193331.GB32416@pogo>
On Thu, Mar 21, 2013 at 12:33:31PM -0700, Luis R. Rodriguez wrote:
> So when does this work get called?
>
> Given the trace this is hit when the timer rx_poll_timer runs,
> which in turn calls ath_rx_poll() to schedule hw_check_work work.
> The rx_poll_timer however was originally only set at the end of
> the routine that hw_check_work sets off but also at other entry
> points (ath_start_rx_poll() callers). Once ath_start_rx_poll()
> gets called though we can go on looping as follows:
>
> work timer work
> hw_check_work --> rx_poll_timer --> hw_check_work
>
> At suspend time we do this though:
>
> ath_cancel_work(sc);
> del_timer_sync(&sc->rx_poll_timer);
>
> + del_timer_sync(&sc->rx_poll_timer);
> ath_cancel_work(sc);
> ath_stop_ani(sc);
> - del_timer_sync(&sc->rx_poll_timer);
[snip]
> But then we have the chicken and the egg problem, as the work item
> could fire off the timer so it would seem to be good to prevent
> adding new work when suspending.
Yup, this is egg and chicken problem, I think it can not be fixed by
changing ordering of del_timer and cancel_work, it would be like:
del_timer_sync(&sc->rx_poll_timer);
/* but timer could schedule work */
ath_cancel_work(sc);
/* but work could schedule timer */
del_timer_sync(&sc->rx_poll_timer);
/* but timer could schedule work */
ath_cancel_work(sc);
/* And so on ... */
Check is needed in work or timer callback, depending what is canceled
last, to fix the problem ...
> > In mac80211 we use local->suspended and local->quiesce booleans to
> > prevent reschedule of timers when going to suspend for example.
> > Works use ifmgd->associted to prevent reschedule when we are
> > disassociating.
> >
> > I think on ath9k also some boolean variable should be used, not only
> > for rx_poll_timer but also for other works i.e. tx_complete_work.
> > Is possible to use SC_OP_INVALID flags, since mac80211 call ath9k_stop
> > on suspend and ath9k_start on resume.
>
> Indeed however ieee80211_queue_work() already does a suspend check for
> us, it just complains as many drivers including mac80211 were setting
> up work incorrectly. The warning was put in place to help us find the
> issues. Using SC_OP_INVALID seems fair but we could also add a routine
> ieee80211_queue_work_safe() that silently fails if we are quiescing or
> suspended and not resuming but I can see that creating very sloppy
> driver writing and everyone abusing it.
We also have to reliable cancel works on ath9k_stop() if device goes
down for other reason than suspend, new mac80211 ieee80211_queue_work_safe()
routine will not help with that.
> OK how about this for stable for now:
>
> diff --git a/drivers/net/wireless/ath/ath9k/link.c b/drivers/net/wireless/ath/ath9k/link.c
> index 39c84ec..7fdac6c 100644
> --- a/drivers/net/wireless/ath/ath9k/link.c
> +++ b/drivers/net/wireless/ath/ath9k/link.c
> @@ -170,7 +170,8 @@ void ath_rx_poll(unsigned long data)
> {
> struct ath_softc *sc = (struct ath_softc *)data;
>
> - ieee80211_queue_work(sc->hw, &sc->hw_check_work);
> + if (!test_bit(SC_OP_INVALID, &sc->sc_flags))
> + ieee80211_queue_work(sc->hw, &sc->hw_check_work);
> }
That looks ok for me as -stable fix
Reviewed-by: Stanislaw Gruszka <sgruszka-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
Stanislaw
--
To unsubscribe from this list: send the line "unsubscribe linux-wireless" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: virtio: remove obsolete virtqueue_get_queue_index()
From: Cornelia Huck @ 2013-03-22 9:10 UTC (permalink / raw)
To: Rusty Russell; +Cc: mst, netdev
In-Reply-To: <87ehf8fftt.fsf@rustcorp.com.au>
On Fri, 22 Mar 2013 10:47:34 +1030
Rusty Russell <rusty@rustcorp.com.au> wrote:
> virtio: remove obsolete virtqueue_get_queue_index()
>
> You can access it directly now, since 3.8: v3.7-rc1-13-g06ca287
> 'virtio: move queue_index and num_free fields into core struct
> virtqueue.'
>
> Cc: Cornelia Huck <cornelia.huck@de.ibm.com>
Acked-by: Cornelia Huck <cornelia.huck@de.ibm.com>
> Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
>
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index d88d436..24fc9f5 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -153,7 +153,7 @@ struct padded_vnet_hdr {
> */
> static int vq2txq(struct virtqueue *vq)
> {
> - return (virtqueue_get_queue_index(vq) - 1) / 2;
> + return (vq->index - 1) / 2;
> }
>
> static int txq2vq(int txq)
> @@ -163,7 +163,7 @@ static int txq2vq(int txq)
>
> static int vq2rxq(struct virtqueue *vq)
> {
> - return virtqueue_get_queue_index(vq) / 2;
> + return vq->index / 2;
> }
>
> static int rxq2vq(int rxq)
> diff --git a/drivers/s390/kvm/virtio_ccw.c b/drivers/s390/kvm/virtio_ccw.c
> index 2029b6c..a7eddc7 100644
> --- a/drivers/s390/kvm/virtio_ccw.c
> +++ b/drivers/s390/kvm/virtio_ccw.c
> @@ -166,7 +166,7 @@ static void virtio_ccw_kvm_notify(struct virtqueue *vq)
>
> vcdev = to_vc_device(info->vq->vdev);
> ccw_device_get_schid(vcdev->cdev, &schid);
> - do_kvm_notify(schid, virtqueue_get_queue_index(vq));
> + do_kvm_notify(schid, vq->index);
> }
>
> static int virtio_ccw_read_vq_conf(struct virtio_ccw_device *vcdev,
> @@ -188,7 +188,7 @@ static void virtio_ccw_del_vq(struct virtqueue *vq, struct ccw1 *ccw)
> unsigned long flags;
> unsigned long size;
> int ret;
> - unsigned int index = virtqueue_get_queue_index(vq);
> + unsigned int index = vq->index;
>
> /* Remove from our list. */
> spin_lock_irqsave(&vcdev->lock, flags);
> @@ -610,7 +610,7 @@ static struct virtqueue *virtio_ccw_vq_by_ind(struct virtio_ccw_device *vcdev,
> vq = NULL;
> spin_lock_irqsave(&vcdev->lock, flags);
> list_for_each_entry(info, &vcdev->virtqueues, node) {
> - if (virtqueue_get_queue_index(info->vq) == index) {
> + if (info->vq->index == index) {
> vq = info->vq;
> break;
> }
> diff --git a/include/linux/virtio.h b/include/linux/virtio.h
> index 833f17b..9ff8645 100644
> --- a/include/linux/virtio.h
> +++ b/include/linux/virtio.h
> @@ -76,12 +76,6 @@ void *virtqueue_detach_unused_buf(struct virtqueue *vq);
>
> unsigned int virtqueue_get_vring_size(struct virtqueue *vq);
>
> -/* FIXME: Obsolete accessor, but required for virtio_net merge. */
> -static inline unsigned int virtqueue_get_queue_index(struct virtqueue *vq)
> -{
> - return vq->index;
> -}
> -
> /**
> * virtio_device - representation of a device using virtio
> * @index: unique position on the virtio bus
>
^ permalink raw reply
* Re: [BUG] bisected: PandaBoard smsc95xx ethernet driver error from USB timeout
From: Roger Quadros @ 2013-03-22 8:42 UTC (permalink / raw)
To: frank.rowand
Cc: Alan Stern, gregkh@linuxfoundation.org, linux-usb@vger.kernel.org,
linux-kernel@vger.kernel.org, linux-omap@vger.kernel.org,
balbi@ti.com, netdev@vger.kernel.org
In-Reply-To: <514BC5C3.9080808@am.sony.com>
Hi Frank,
On 03/22/2013 04:45 AM, Frank Rowand wrote:
> On 03/21/13 07:41, Alan Stern wrote:
>> On Wed, 20 Mar 2013, Frank Rowand wrote:
>>
>>> Hi All,
>>>
>>> Not quite sure quite where the problem is (USB, OMAP, smsc95xx driver, other???),
>>> so casting the nets wide...
>>>
>>> The PandaBoard frequently fails to boot with an eth0 error when mounting
>>> the root file system via NFS (ethernet driver fails due to a USB timeout;
>>> no ethernet means NFS won't work). A typical set of error messages is:
>>>
>>> [ 3.264373] smsc95xx 1-1.1:1.0: usb_probe_interface
>>> [ 3.269500] smsc95xx 1-1.1:1.0: usb_probe_interface - got id
>>> [ 3.275543] smsc95xx v1.0.4
>>> [ 8.078674] smsc95xx 1-1.1:1.0: eth0: register 'smsc95xx' at usb-ehci-omap.0-1.1, smsc95xx USB 2.0 Ethernet, 82:b9:1d:fa:67:0d
>>> [ 8.091003] hub 1-1:1.0: state 7 ports 5 chg 0000 evt 0002
>>> [ 13.509918] usb 1-1.1: swapper/0 timed out on ep0out len=0/4
>>> [ 13.515869] smsc95xx 1-1.1:1.0: eth0: Failed to write register index 0x00000108
>>> [ 13.523559] smsc95xx 1-1.1:1.0: eth0: Failed to write ADDRL: -110
>>> [ 13.529998] IP-Config: Failed to open eth0
>>>
>>> I have bisected this to:
>>>
>>> commit 18aafe64d75d0e27dae206cacf4171e4e485d285
>>> Author: Alan Stern <stern@rowland.harvard.edu>
>>> Date: Wed Jul 11 11:23:04 2012 -0400
>>>
>>> USB: EHCI: use hrtimer for the I/O watchdog
>>
>> I don't understand how that commit could cause a timeout unless there
>> are at least two other bugs present in your system.
>>
>>> Note that to compile this version of the kernel, an additional fix must
>>> also be applied:
>>>
>>> commit ba5952e0711b14d8d4fe172671f8aa6091ace3ee
>>> Author: Ming Lei <ming.lei@canonical.com>
>>> Date: Fri Jul 13 17:25:24 2012 +0800
>>>
>>> USB: ehci-omap: fix compile failure(v1)
>>>
>>> The symptom can be worked around by retrying the USB access if a timeout
>>> occurs. This is clearly _not_ the fix, just a hack that I used to
>>> investigate the problem:
>>>
>>> http://article.gmane.org/gmane.linux.rt.user/9773
>>>
>>> My kernel configuration is:
>>>
>>> arch/arm/configs/omap2plus_defconfig
>>>
>>> plus to get the ethernet driver I add:
>>>
>>> CONFIG_USB_EHCI_HCD
>>> CONFIG_USB_NET_SMSC95XX
>>>
>>> I found the problem on 3.6.11, but have not replicated it on 3.9-rcX
>>> yet because my config fails to build on 3.9-rc1 and 3.9-rc2. I'll try
>>> to work on that issue tomorrow.
>>
>> Let me know how it works out.
>
> My PandaBoard builds fail on 3.9-rcX due to ARM multiplatform issues.
> Either there is something I need to change about the way I build it,
> or it is broken (that is a side issue). My simple expedient was to
> hack around multiplatform, and just make it build (patch below if
> anyone else wants a _temporary_ hack).
This is a known issue and will be resolved the proper way in 3.10.
For 3.9 you could also use a temporary fix posted here
http://thread.gmane.org/gmane.linux.usb.general/82693/
>
> The problem appears to not be present in 3.9-rc3. In older kernel versions,
> the worst case to see the problem was 18 boots. For 3.9-rc3 I booted 42
> times without seeing the problem.
This is good to hear.
>
> The problem occurs at least up through 3.8. I'll try to reverse bisect
> between 3.8 and 3.9-rc3 to see when the problem disappeared (I'm running
> short of time, so no promises for a near term result).
Thanks for the tests. There were a lot of OMAP EHCI related cleanup/fixes [1]
that went into 3.9. It would be interesting to know what fixed it.
[1] - https://lkml.org/lkml/2013/1/23/155
cheers,
-roger
^ permalink raw reply
* Re: [Patch net-next] ip_gre: increase inner ip header ID during segmentation
From: Cong Wang @ 2013-03-22 7:57 UTC (permalink / raw)
To: netdev; +Cc: Pravin B Shelar, Eric Dumazet, David S. Miller
In-Reply-To: <1363938600-26129-1-git-send-email-amwang@redhat.com>
On Fri, 2013-03-22 at 15:50 +0800, Cong Wang wrote:
> + iph = (struct iphdr *)skb->data;
> + iph->id = id++;
Oops, seems I missed its endian...
^ permalink raw reply
* [Patch net-next] ip_gre: increase inner ip header ID during segmentation
From: Cong Wang @ 2013-03-22 7:50 UTC (permalink / raw)
To: netdev; +Cc: Pravin B Shelar, Eric Dumazet, David S. Miller, Cong Wang
From: Cong Wang <amwang@redhat.com>
According to the previous discussion [1] on netdev list, DaveM insists
we should increase the IP header ID for each segmented packets.
This patch fixes it.
Cc: Pravin B Shelar <pshelar@nicira.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Cong Wang <amwang@redhat.com>
1. http://marc.info/?t=136384172700001&r=1&w=2
---
diff --git a/net/ipv4/gre.c b/net/ipv4/gre.c
index 7a4c710..3cf20a4 100644
--- a/net/ipv4/gre.c
+++ b/net/ipv4/gre.c
@@ -125,9 +125,11 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
netdev_features_t enc_features;
int ghl = GRE_HEADER_SECTION;
struct gre_base_hdr *greh;
+ struct iphdr *iph;
int mac_len = skb->mac_len;
int tnl_hlen;
bool csum;
+ __be16 id;
if (unlikely(skb_shinfo(skb)->gso_type &
~(SKB_GSO_TCPV4 |
@@ -170,6 +172,8 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
skb_set_network_header(skb, skb_inner_network_offset(skb));
skb->mac_len = skb_inner_network_offset(skb);
+ iph = (struct iphdr *)skb->data;
+ id = iph->id;
/* segment inner packet. */
enc_features = skb->dev->hw_enc_features & netif_skb_features(skb);
segs = skb_mac_gso_segment(skb, enc_features);
@@ -179,6 +183,8 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
skb = segs;
tnl_hlen = skb_tnl_header_len(skb);
do {
+ iph = (struct iphdr *)skb->data;
+ iph->id = id++;
__skb_push(skb, ghl);
if (csum) {
__be32 *pcsum;
^ permalink raw reply related
* Re: regression: tethering fails in 3.5 with iwlwifi
From: Artem Bityutskiy @ 2013-03-22 7:01 UTC (permalink / raw)
To: Johannes Berg
Cc: patrik.flykt-ral2JQCrhuEAvxtiuMwx3w, Eric Dumazet,
linux-wireless-u79uwXL29TY76Z2rM5mHXA,
netdev-u79uwXL29TY76Z2rM5mHXA, stable-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <1363894451.8181.4.camel-8Nb76shvtaUJvtFkdXX2HixXY32XiHfO@public.gmane.org>
On Thu, 2013-03-21 at 20:34 +0100, Johannes Berg wrote:
> On Mon, 2012-09-17 at 17:41 +0300, Artem Bityutskiy wrote:
>
> > OK, finally I got it. After 3 days of hardcore intelligent bisecting
> > I've found out that tethering in 3.5 works for me if I revert
> > these 2
> > patches:
> >
> > 56138f5 iwlwifi: dont pull too much payload in skb head
>
> I got back to this for a customer running 3.5, and after many failed
> attempts realized that you have to have iptables for this problem to
> actually happen. I reverse-bisected that the *fix* is
> 6caab7b0544e83e6c160b5e80f5a4a7dd69545c7, in 3.7.
>
> Is there still any stable kernel 3.5/3.6 (or possibly before, though for
> iwlwifi before doesn't matter) that this should be applied to?
Hi Johannes,
thanks for remembering about this. We've switched to the 3.8 kernel
recently, and we are pulling stable kernels in regularly. Now we are
at 3.8.3.
--
Best Regards,
Artem Bityutskiy
--
To unsubscribe from this list: send the line "unsubscribe linux-wireless" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* [PATCH 1/2] netfilter: reset nf_trace in nf_reset
From: Gao feng @ 2013-03-22 5:48 UTC (permalink / raw)
To: netfilter-devel, netdev; +Cc: Gao feng
We forgot to clear the nf_trace of sk_buff in nf_reset,
When we use veth device, this nf_trace information will
be leaked from one net namespace to another net namespace.
Signed-off-by: Gao feng <gaofeng@cn.fujitsu.com>
---
include/linux/skbuff.h | 3 +++
1 file changed, 3 insertions(+)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 441f5bf..72b3967 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2641,6 +2641,9 @@ static inline void nf_reset(struct sk_buff *skb)
nf_bridge_put(skb->nf_bridge);
skb->nf_bridge = NULL;
#endif
+#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
+ skb->nf_trace = 0;
+#endif
}
/* Note: This doesn't put any conntrack and bridge info in dst. */
--
1.7.11.7
^ permalink raw reply related
* [PATCH 2/2] netfilter: TRACE: use IS_ENABLE to replace if defined
From: Gao feng @ 2013-03-22 5:48 UTC (permalink / raw)
To: netfilter-devel, netdev; +Cc: Gao feng
In-Reply-To: <1363931322-2286-1-git-send-email-gaofeng@cn.fujitsu.com>
Inder to reduce codes, Use IS_ENABLE to replace the
if defined.
Signed-off-by: Gao feng <gaofeng@cn.fujitsu.com>
---
net/ipv4/ip_output.c | 3 +--
net/ipv4/netfilter/ip_tables.c | 6 ++----
2 files changed, 3 insertions(+), 6 deletions(-)
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 5e12dca..147abf5 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -430,8 +430,7 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
to->tc_index = from->tc_index;
#endif
nf_copy(to, from);
-#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
- defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE)
+#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
to->nf_trace = from->nf_trace;
#endif
#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 3efcf87..1b433aa 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -182,8 +182,7 @@ ipt_get_target_c(const struct ipt_entry *e)
return ipt_get_target((struct ipt_entry *)e);
}
-#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
- defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE)
+#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
static const char *const hooknames[] = {
[NF_INET_PRE_ROUTING] = "PREROUTING",
[NF_INET_LOCAL_IN] = "INPUT",
@@ -361,8 +360,7 @@ ipt_do_table(struct sk_buff *skb,
t = ipt_get_target(e);
IP_NF_ASSERT(t->u.kernel.target);
-#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
- defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE)
+#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
/* The packet is traced: log it */
if (unlikely(skb->nf_trace))
trace_packet(skb, hook, in, out,
--
1.7.11.7
^ permalink raw reply related
* Re: RFC: mac802154 Packet Queueing and Slave Devices
From: Alan Ott @ 2013-03-22 5:33 UTC (permalink / raw)
To: Alexander Smirnov, Dmitry Eremin-Solenikov, Tony Cheneau
Cc: linux-zigbee-devel, netdev, Eric Dumazet
In-Reply-To: <514B30BC.4040802@signal11.us>
On 03/21/2013 12:09 PM, Alan Ott wrote:
> On 09/09/2012 08:43 PM, Alan Ott wrote:
>> Tony and I were recently talking about packet queueing on 802.15.4. What
>> currently happens (in net/mac802154/tx.c) is that each tx packet (skb)
>> is stuck on a work queue, and the worker function then sends each packet
>> to the hardware driver in order.
>>
>> The problem with this is that it defeats the netif flow control. The
>> networking layer thinks the packet is sent as soon as it's put on the
>> workqueue (because the function that queues it returns NETDEV_TX_OK to
>> the networking layer), and the workqueue can then get arbitrarily large
>> if an application tries to send a lot of data. (Tony has shown this with
>> iperf)
>>
> So I tried fixing this using netif_stop_queue() and netif_wake_queue(),
> the standard way. The flow control works, but I'm now losing packets.
>
> It happens like this:
>
> ipv6 -> 6lowpan -> net core -> mac802154 -> hardware
> single packet fragment netif_stop_queue()
> fragment
> fragment
> fragment
>
> Above: a single ipv6 packet is split into fragments by 6lowpan. Each
> fragment is sent through the networking core where it ends up in
> mac802154, which will call netif_stop_queue() and netif_wake_queue()
> for flow control as packets are sent.
>
>
> The problem is that since many ieee802154 hardware devices can only hold
> one packet at a time in their tx buffer, netif_stop_queue() gets called
> after the first fragment. Since the 6lowpan code is trying to, in the
> above case, send 4 packets, the remaining 3 will get dropped when
> they're handed to the networking core (dev_queue_xmit()) when the queue
> is stopped.
>
> So as a solution, one could envision 6lowpan putting the fragments into
> a queue, and submitting one at a time, as the queue gets woken. The
> problem with this is that there's no way to get notification for when a
> queue is woken. I checked both ppp and ax25 (which would seem to have
> this same issue), and they both have a fragment queue, but they rely on
> external events (mostly unrelated to the queue being woken) to trigger
> sending packets from the queue (see calls to ax25_kick()). That seems
> hacky at best.
>
> A thread from pppoe[1] talks about what's a similar issue. The patch
> from that email was never merged. Even so, their solution seems a bit
> hacky too (because it would basically cause a kick to (in this case)
> 6lowpan, whenever an skb gets destroyed (ie: after it's sent). With the
> desire for 6lowpan to be a generic protocol[2], one would want it to be
> efficient on MAC layers which do support longer queues[3].
>
> What am I missing here? What's the right way to do this?
>
> Alan.
>
> [1] http://thread.gmane.org/gmane.linux.network/233089
> [2] There has been some discussion about using 6lowpan on Bluetooth
> low-energy.
> [3] There's also the case where 2 6lowpan instances are on attached to
> the same hardware, or where 6lowpan and raw are being used concurrently.
I guess the more condensed question is, as a protocol which generates
fragments, what's the right way to handle queue management from the device?
Alan.
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox