* [PATCH 27/37] IPVS: Add __ip_vs_control_{init,cleanup}_sysctl()
From: kaber @ 2011-03-15 19:44 UTC (permalink / raw)
To: davem; +Cc: netfilter-devel, netdev
In-Reply-To: <1300218257-26953-1-git-send-email-kaber@trash.net>
From: Simon Horman <horms@verge.net.au>
Break out the portions of __ip_vs_control_init() and
__ip_vs_control_cleanup() where aren't necessary when
CONFIG_SYSCTL is undefined.
Signed-off-by: Simon Horman <horms@verge.net.au>
---
net/netfilter/ipvs/ip_vs_ctl.c | 98 +++++++++++++++++++++++++---------------
1 files changed, 62 insertions(+), 36 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 364520f..fa6d44c 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -88,6 +88,8 @@ static int __ip_vs_addr_is_local_v6(struct net *net,
return 0;
}
#endif
+
+#ifdef CONFIG_SYSCTL
/*
* update_defense_level is called from keventd and from sysctl,
* so it needs to protect itself from softirqs
@@ -229,6 +231,7 @@ static void defense_work_handler(struct work_struct *work)
ip_vs_random_dropentry(ipvs->net);
schedule_delayed_work(&ipvs->defense_work, DEFENSE_TIMER_PERIOD);
}
+#endif
int
ip_vs_use_count_inc(void)
@@ -1511,7 +1514,7 @@ static int ip_vs_zero_all(struct net *net)
return 0;
}
-
+#ifdef CONFIG_SYSCTL
static int
proc_do_defense_mode(ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
@@ -1533,7 +1536,6 @@ proc_do_defense_mode(ctl_table *table, int write,
return rc;
}
-
static int
proc_do_sync_threshold(ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
@@ -1767,6 +1769,7 @@ const struct ctl_path net_vs_ctl_path[] = {
{ }
};
EXPORT_SYMBOL_GPL(net_vs_ctl_path);
+#endif
#ifdef CONFIG_PROC_FS
@@ -3511,7 +3514,8 @@ static void ip_vs_genl_unregister(void)
/*
* per netns intit/exit func.
*/
-int __net_init __ip_vs_control_init(struct net *net)
+#ifdef CONFIG_SYSCTL
+int __net_init __ip_vs_control_init_sysctl(struct net *net)
{
int idx;
struct netns_ipvs *ipvs = net_ipvs(net);
@@ -3521,33 +3525,11 @@ int __net_init __ip_vs_control_init(struct net *net)
spin_lock_init(&ipvs->dropentry_lock);
spin_lock_init(&ipvs->droppacket_lock);
spin_lock_init(&ipvs->securetcp_lock);
- ipvs->rs_lock = __RW_LOCK_UNLOCKED(ipvs->rs_lock);
-
- /* Initialize rs_table */
- for (idx = 0; idx < IP_VS_RTAB_SIZE; idx++)
- INIT_LIST_HEAD(&ipvs->rs_table[idx]);
-
- INIT_LIST_HEAD(&ipvs->dest_trash);
- atomic_set(&ipvs->ftpsvc_counter, 0);
- atomic_set(&ipvs->nullsvc_counter, 0);
-
- /* procfs stats */
- ipvs->tot_stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats);
- if (!ipvs->tot_stats.cpustats) {
- pr_err("%s() alloc_percpu failed\n", __func__);
- goto err_alloc;
- }
- spin_lock_init(&ipvs->tot_stats.lock);
-
- proc_net_fops_create(net, "ip_vs", 0, &ip_vs_info_fops);
- proc_net_fops_create(net, "ip_vs_stats", 0, &ip_vs_stats_fops);
- proc_net_fops_create(net, "ip_vs_stats_percpu", 0,
- &ip_vs_stats_percpu_fops);
if (!net_eq(net, &init_net)) {
tbl = kmemdup(vs_vars, sizeof(vs_vars), GFP_KERNEL);
if (tbl == NULL)
- goto err_dup;
+ return -ENOMEM;
} else
tbl = vs_vars;
/* Initialize sysctl defaults */
@@ -3576,25 +3558,73 @@ int __net_init __ip_vs_control_init(struct net *net)
tbl[idx++].data = &ipvs->sysctl_nat_icmp_send;
-#ifdef CONFIG_SYSCTL
ipvs->sysctl_hdr = register_net_sysctl_table(net, net_vs_ctl_path,
tbl);
if (ipvs->sysctl_hdr == NULL) {
if (!net_eq(net, &init_net))
kfree(tbl);
- goto err_dup;
+ return -ENOMEM;
}
-#endif
ip_vs_start_estimator(net, &ipvs->tot_stats);
ipvs->sysctl_tbl = tbl;
/* Schedule defense work */
INIT_DELAYED_WORK(&ipvs->defense_work, defense_work_handler);
schedule_delayed_work(&ipvs->defense_work, DEFENSE_TIMER_PERIOD);
+
return 0;
+}
+
+void __net_init __ip_vs_control_cleanup_sysctl(struct net *net)
+{
+ struct netns_ipvs *ipvs = net_ipvs(net);
+
+ cancel_delayed_work_sync(&ipvs->defense_work);
+ cancel_work_sync(&ipvs->defense_work.work);
+ unregister_net_sysctl_table(ipvs->sysctl_hdr);
+}
-err_dup:
+#else
+
+int __net_init __ip_vs_control_init_sysctl(struct net *net) { return 0; }
+void __net_init __ip_vs_control_cleanup_sysctl(struct net *net) { }
+
+#endif
+
+int __net_init __ip_vs_control_init(struct net *net)
+{
+ int idx;
+ struct netns_ipvs *ipvs = net_ipvs(net);
+
+ ipvs->rs_lock = __RW_LOCK_UNLOCKED(ipvs->rs_lock);
+
+ /* Initialize rs_table */
+ for (idx = 0; idx < IP_VS_RTAB_SIZE; idx++)
+ INIT_LIST_HEAD(&ipvs->rs_table[idx]);
+
+ INIT_LIST_HEAD(&ipvs->dest_trash);
+ atomic_set(&ipvs->ftpsvc_counter, 0);
+ atomic_set(&ipvs->nullsvc_counter, 0);
+
+ /* procfs stats */
+ ipvs->tot_stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats);
+ if (ipvs->tot_stats.cpustats) {
+ pr_err("%s(): alloc_percpu.\n", __func__);
+ return -ENOMEM;
+ }
+ spin_lock_init(&ipvs->tot_stats.lock);
+
+ proc_net_fops_create(net, "ip_vs", 0, &ip_vs_info_fops);
+ proc_net_fops_create(net, "ip_vs_stats", 0, &ip_vs_stats_fops);
+ proc_net_fops_create(net, "ip_vs_stats_percpu", 0,
+ &ip_vs_stats_percpu_fops);
+
+ if (__ip_vs_control_init_sysctl(net))
+ goto err;
+
+ return 0;
+
+err:
free_percpu(ipvs->tot_stats.cpustats);
-err_alloc:
return -ENOMEM;
}
@@ -3604,11 +3634,7 @@ static void __net_exit __ip_vs_control_cleanup(struct net *net)
ip_vs_trash_cleanup(net);
ip_vs_stop_estimator(net, &ipvs->tot_stats);
- cancel_delayed_work_sync(&ipvs->defense_work);
- cancel_work_sync(&ipvs->defense_work.work);
-#ifdef CONFIG_SYSCTL
- unregister_net_sysctl_table(ipvs->sysctl_hdr);
-#endif
+ __ip_vs_control_cleanup_sysctl(net);
proc_net_remove(net, "ip_vs_stats_percpu");
proc_net_remove(net, "ip_vs_stats");
proc_net_remove(net, "ip_vs");
--
1.7.2.3
^ permalink raw reply related
* [PATCH 22/37] IPVS: Conditinally use sysctl_lblc{r}_expiration
From: kaber @ 2011-03-15 19:44 UTC (permalink / raw)
To: davem; +Cc: netfilter-devel, netdev
In-Reply-To: <1300218257-26953-1-git-send-email-kaber@trash.net>
From: Simon Horman <horms@verge.net.au>
In preparation for not including sysctl_lblc{r}_expiration in
struct netns_ipvs when CONFIG_SYCTL is not defined.
Signed-off-by: Simon Horman <horms@verge.net.au>
---
net/netfilter/ipvs/ip_vs_lblc.c | 16 +++++++++++++---
net/netfilter/ipvs/ip_vs_lblcr.c | 21 +++++++++++++++------
2 files changed, 28 insertions(+), 9 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index 6bf7a80..51a27f5 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -63,6 +63,8 @@
#define CHECK_EXPIRE_INTERVAL (60*HZ)
#define ENTRY_TIMEOUT (6*60*HZ)
+#define DEFAULT_EXPIRATION (24*60*60*HZ)
+
/*
* It is for full expiration check.
* When there is no partial expiration check (garbage collection)
@@ -238,6 +240,15 @@ static void ip_vs_lblc_flush(struct ip_vs_lblc_table *tbl)
}
}
+static int sysctl_lblc_expiration(struct ip_vs_service *svc)
+{
+#ifdef CONFIG_SYSCTL
+ struct netns_ipvs *ipvs = net_ipvs(svc->net);
+ return ipvs->sysctl_lblc_expiration;
+#else
+ return DEFAULT_EXPIRATION;
+#endif
+}
static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc)
{
@@ -245,7 +256,6 @@ static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc)
struct ip_vs_lblc_entry *en, *nxt;
unsigned long now = jiffies;
int i, j;
- struct netns_ipvs *ipvs = net_ipvs(svc->net);
for (i=0, j=tbl->rover; i<IP_VS_LBLC_TAB_SIZE; i++) {
j = (j + 1) & IP_VS_LBLC_TAB_MASK;
@@ -254,7 +264,7 @@ static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc)
list_for_each_entry_safe(en, nxt, &tbl->bucket[j], list) {
if (time_before(now,
en->lastuse +
- ipvs->sysctl_lblc_expiration))
+ sysctl_lblc_expiration(svc)))
continue;
ip_vs_lblc_free(en);
@@ -550,7 +560,7 @@ static int __net_init __ip_vs_lblc_init(struct net *net)
return -ENOMEM;
} else
ipvs->lblc_ctl_table = vs_vars_table;
- ipvs->sysctl_lblc_expiration = 24*60*60*HZ;
+ ipvs->sysctl_lblc_expiration = DEFAULT_EXPIRATION;
ipvs->lblc_ctl_table[0].data = &ipvs->sysctl_lblc_expiration;
#ifdef CONFIG_SYSCTL
diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c
index 0063176..7fb9190 100644
--- a/net/netfilter/ipvs/ip_vs_lblcr.c
+++ b/net/netfilter/ipvs/ip_vs_lblcr.c
@@ -63,6 +63,8 @@
#define CHECK_EXPIRE_INTERVAL (60*HZ)
#define ENTRY_TIMEOUT (6*60*HZ)
+#define DEFAULT_EXPIRATION (24*60*60*HZ)
+
/*
* It is for full expiration check.
* When there is no partial expiration check (garbage collection)
@@ -410,6 +412,15 @@ static void ip_vs_lblcr_flush(struct ip_vs_lblcr_table *tbl)
}
}
+static int sysctl_lblcr_expiration(struct ip_vs_service *svc)
+{
+#ifdef CONFIG_SYSCTL
+ struct netns_ipvs *ipvs = net_ipvs(svc->net);
+ return ipvs->sysctl_lblcr_expiration;
+#else
+ return DEFAULT_EXPIRATION;
+#endif
+}
static inline void ip_vs_lblcr_full_check(struct ip_vs_service *svc)
{
@@ -417,15 +428,14 @@ static inline void ip_vs_lblcr_full_check(struct ip_vs_service *svc)
unsigned long now = jiffies;
int i, j;
struct ip_vs_lblcr_entry *en, *nxt;
- struct netns_ipvs *ipvs = net_ipvs(svc->net);
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) {
- if (time_after(en->lastuse
- + ipvs->sysctl_lblcr_expiration, now))
+ if (time_after(en->lastuse +
+ sysctl_lblcr_expiration(svc), now))
continue;
ip_vs_lblcr_free(en);
@@ -650,7 +660,6 @@ ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
read_lock(&svc->sched_lock);
en = ip_vs_lblcr_get(svc->af, tbl, &iph.daddr);
if (en) {
- struct netns_ipvs *ipvs = net_ipvs(svc->net);
/* We only hold a read lock, but this is atomic */
en->lastuse = jiffies;
@@ -662,7 +671,7 @@ ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb)
/* More than one destination + enough time passed by, cleanup */
if (atomic_read(&en->set.size) > 1 &&
time_after(jiffies, en->set.lastmod +
- ipvs->sysctl_lblcr_expiration)) {
+ sysctl_lblcr_expiration(svc))) {
struct ip_vs_dest *m;
write_lock(&en->set.lock);
@@ -746,7 +755,7 @@ static int __net_init __ip_vs_lblcr_init(struct net *net)
return -ENOMEM;
} else
ipvs->lblcr_ctl_table = vs_vars_table;
- ipvs->sysctl_lblcr_expiration = 24*60*60*HZ;
+ ipvs->sysctl_lblcr_expiration = DEFAULT_EXPIRATION;
ipvs->lblcr_ctl_table[0].data = &ipvs->sysctl_lblcr_expiration;
#ifdef CONFIG_SYSCTL
--
1.7.2.3
^ permalink raw reply related
* [PATCH 18/37] IPVS: Add {sysctl_sync_threshold,period}()
From: kaber @ 2011-03-15 19:43 UTC (permalink / raw)
To: davem; +Cc: netfilter-devel, netdev
In-Reply-To: <1300218257-26953-1-git-send-email-kaber@trash.net>
From: Simon Horman <horms@verge.net.au>
In preparation for not including sysctl_sync_threshold in
struct netns_ipvs when CONFIG_SYCTL is not defined.
Signed-off-by: Simon Horman <horms@verge.net.au>
---
include/net/ip_vs.h | 29 +++++++++++++++++++++++++++++
net/netfilter/ipvs/ip_vs_core.c | 10 +++++-----
net/netfilter/ipvs/ip_vs_ctl.c | 4 ++--
net/netfilter/ipvs/ip_vs_sync.c | 4 ++--
4 files changed, 38 insertions(+), 9 deletions(-)
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 7ca5be2..253736d 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -909,6 +909,35 @@ struct netns_ipvs {
struct net *net; /* Needed by timer routines */
};
+#define DEFAULT_SYNC_THRESHOLD 3
+#define DEFAULT_SYNC_PERIOD 50
+
+#ifdef CONFIG_SYSCTL
+
+static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs)
+{
+ return ipvs->sysctl_sync_threshold[0];
+}
+
+static inline int sysctl_sync_period(struct netns_ipvs *ipvs)
+{
+ return ipvs->sysctl_sync_threshold[1];
+}
+
+#else
+
+static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs)
+{
+ return DEFAULT_SYNC_THRESHOLD;
+}
+
+static inline int sysctl_sync_period(struct netns_ipvs *ipvs)
+{
+ return DEFAULT_SYNC_PERIOD;
+}
+
+#endif
+
/*
* IPVS core functions
* (from ip_vs_core.c)
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index c9b8372..6a0053d 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1613,15 +1613,15 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
*/
if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
- pkts = ipvs->sysctl_sync_threshold[0];
+ pkts = sysctl_sync_threshold(ipvs);
else
pkts = atomic_add_return(1, &cp->in_pkts);
if ((ipvs->sync_state & IP_VS_STATE_MASTER) &&
cp->protocol == IPPROTO_SCTP) {
if ((cp->state == IP_VS_SCTP_S_ESTABLISHED &&
- (pkts % ipvs->sysctl_sync_threshold[1]
- == ipvs->sysctl_sync_threshold[0])) ||
+ (pkts % sysctl_sync_period(ipvs)
+ == sysctl_sync_threshold(ipvs))) ||
(cp->old_state != cp->state &&
((cp->state == IP_VS_SCTP_S_CLOSED) ||
(cp->state == IP_VS_SCTP_S_SHUT_ACK_CLI) ||
@@ -1635,8 +1635,8 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
else if ((ipvs->sync_state & IP_VS_STATE_MASTER) &&
(((cp->protocol != IPPROTO_TCP ||
cp->state == IP_VS_TCP_S_ESTABLISHED) &&
- (pkts % ipvs->sysctl_sync_threshold[1]
- == ipvs->sysctl_sync_threshold[0])) ||
+ (pkts % sysctl_sync_period(ipvs)
+ == sysctl_sync_threshold(ipvs))) ||
((cp->protocol == IPPROTO_TCP) && (cp->old_state != cp->state) &&
((cp->state == IP_VS_TCP_S_FIN_WAIT) ||
(cp->state == IP_VS_TCP_S_CLOSE) ||
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index c5b1234..364520f 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -3569,8 +3569,8 @@ int __net_init __ip_vs_control_init(struct net *net)
tbl[idx++].data = &ipvs->sysctl_cache_bypass;
tbl[idx++].data = &ipvs->sysctl_expire_nodest_conn;
tbl[idx++].data = &ipvs->sysctl_expire_quiescent_template;
- ipvs->sysctl_sync_threshold[0] = 3;
- ipvs->sysctl_sync_threshold[1] = 50;
+ ipvs->sysctl_sync_threshold[0] = DEFAULT_SYNC_THRESHOLD;
+ ipvs->sysctl_sync_threshold[1] = DEFAULT_SYNC_PERIOD;
tbl[idx].data = &ipvs->sysctl_sync_threshold;
tbl[idx++].maxlen = sizeof(ipvs->sysctl_sync_threshold);
tbl[idx++].data = &ipvs->sysctl_nat_icmp_send;
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index c5d13b0..e84987f 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -650,7 +650,7 @@ control:
if (cp->flags & IP_VS_CONN_F_TEMPLATE) {
int pkts = atomic_add_return(1, &cp->in_pkts);
- if (pkts % ipvs->sysctl_sync_threshold[1] != 1)
+ if (pkts % sysctl_sync_period(ipvs) != 1)
return;
}
goto sloop;
@@ -794,7 +794,7 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param,
if (opt)
memcpy(&cp->in_seq, opt, sizeof(*opt));
- atomic_set(&cp->in_pkts, ipvs->sysctl_sync_threshold[0]);
+ atomic_set(&cp->in_pkts, sysctl_sync_threshold(ipvs));
cp->state = state;
cp->old_state = cp->state;
/*
--
1.7.2.3
^ permalink raw reply related
* [PATCH 17/37] IPVS: Add sysctl_nat_icmp_send()
From: kaber @ 2011-03-15 19:43 UTC (permalink / raw)
To: davem; +Cc: netfilter-devel, netdev
In-Reply-To: <1300218257-26953-1-git-send-email-kaber@trash.net>
From: Simon Horman <horms@verge.net.au>
In preparation for not including sysctl_nat_icmp_send in
struct netns_ipvs when CONFIG_SYCTL is not defined.
Signed-off-by: Simon Horman <horms@verge.net.au>
---
net/netfilter/ipvs/ip_vs_core.c | 11 ++++++++---
1 files changed, 8 insertions(+), 3 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 1d8a2a2..c9b8372 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -607,9 +607,16 @@ static int sysctl_snat_reroute(struct sk_buff *skb)
return ipvs->sysctl_snat_reroute;
}
+static int sysctl_nat_icmp_send(struct net *net)
+{
+ struct netns_ipvs *ipvs = net_ipvs(net);
+ return ipvs->sysctl_nat_icmp_send;
+}
+
#else
static int sysctl_snat_reroute(struct sk_buff *skb) { return 0; }
+static int sysctl_nat_icmp_send(struct net *net) { return 0; }
#endif
@@ -1074,7 +1081,6 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
struct ip_vs_protocol *pp;
struct ip_vs_proto_data *pd;
struct ip_vs_conn *cp;
- struct netns_ipvs *ipvs;
EnterFunction(11);
@@ -1149,11 +1155,10 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
* Check if the packet belongs to an existing entry
*/
cp = pp->conn_out_get(af, skb, &iph, iph.len, 0);
- ipvs = net_ipvs(net);
if (likely(cp))
return handle_response(af, skb, pd, cp, iph.len);
- if (ipvs->sysctl_nat_icmp_send &&
+ if (sysctl_nat_icmp_send(net) &&
(pp->protocol == IPPROTO_TCP ||
pp->protocol == IPPROTO_UDP ||
pp->protocol == IPPROTO_SCTP)) {
--
1.7.2.3
^ permalink raw reply related
* [PATCH 16/37] IPVS: Add sysctl_snat_reroute()
From: kaber @ 2011-03-15 19:43 UTC (permalink / raw)
To: davem; +Cc: netfilter-devel, netdev
In-Reply-To: <1300218257-26953-1-git-send-email-kaber@trash.net>
From: Simon Horman <horms@verge.net.au>
In preparation for not including sysctl_snat_reroute in
struct netns_ipvs when CONFIG_SYCTL is not defined.
Signed-off-by: Simon Horman <horms@verge.net.au>
---
net/netfilter/ipvs/ip_vs_core.c | 20 ++++++++++++++++----
1 files changed, 16 insertions(+), 4 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 299c7f3..1d8a2a2 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -599,6 +599,20 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
return NF_DROP;
}
+#ifdef CONFIG_SYSCTL
+
+static int sysctl_snat_reroute(struct sk_buff *skb)
+{
+ struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
+ return ipvs->sysctl_snat_reroute;
+}
+
+#else
+
+static int sysctl_snat_reroute(struct sk_buff *skb) { return 0; }
+
+#endif
+
__sum16 ip_vs_checksum_complete(struct sk_buff *skb, int offset)
{
return csum_fold(skb_checksum(skb, offset, skb->len - offset, 0));
@@ -633,15 +647,13 @@ static inline int ip_vs_gather_frags_v6(struct sk_buff *skb, u_int32_t user)
static int ip_vs_route_me_harder(int af, struct sk_buff *skb)
{
- struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
-
#ifdef CONFIG_IP_VS_IPV6
if (af == AF_INET6) {
- if (ipvs->sysctl_snat_reroute && ip6_route_me_harder(skb) != 0)
+ if (sysctl_snat_reroute(skb) && ip6_route_me_harder(skb) != 0)
return 1;
} else
#endif
- if ((ipvs->sysctl_snat_reroute ||
+ if ((sysctl_snat_reroute(skb) ||
skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
ip_route_me_harder(skb, RTN_LOCAL) != 0)
return 1;
--
1.7.2.3
^ permalink raw reply related
* [PATCH 15/37] IPVS: Add ip_vs_route_me_harder()
From: kaber @ 2011-03-15 19:43 UTC (permalink / raw)
To: davem; +Cc: netfilter-devel, netdev
In-Reply-To: <1300218257-26953-1-git-send-email-kaber@trash.net>
From: Simon Horman <horms@verge.net.au>
Add ip_vs_route_me_harder() to avoid repeating the same code twice.
Signed-off-by: Simon Horman <horms@verge.net.au>
---
net/netfilter/ipvs/ip_vs_core.c | 48 +++++++++++++++++---------------------
1 files changed, 22 insertions(+), 26 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 6f4940e..299c7f3 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -631,6 +631,24 @@ static inline int ip_vs_gather_frags_v6(struct sk_buff *skb, u_int32_t user)
}
#endif
+static int ip_vs_route_me_harder(int af, struct sk_buff *skb)
+{
+ struct netns_ipvs *ipvs = net_ipvs(skb_net(skb));
+
+#ifdef CONFIG_IP_VS_IPV6
+ if (af == AF_INET6) {
+ if (ipvs->sysctl_snat_reroute && ip6_route_me_harder(skb) != 0)
+ return 1;
+ } else
+#endif
+ if ((ipvs->sysctl_snat_reroute ||
+ skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
+ ip_route_me_harder(skb, RTN_LOCAL) != 0)
+ return 1;
+
+ return 0;
+}
+
/*
* Packet has been made sufficiently writable in caller
* - inout: 1=in->out, 0=out->in
@@ -737,7 +755,6 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
struct ip_vs_protocol *pp,
unsigned int offset, unsigned int ihl)
{
- struct netns_ipvs *ipvs;
unsigned int verdict = NF_DROP;
if (IP_VS_FWD_METHOD(cp) != 0) {
@@ -759,8 +776,6 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
if (!skb_make_writable(skb, offset))
goto out;
- ipvs = net_ipvs(skb_net(skb));
-
#ifdef CONFIG_IP_VS_IPV6
if (af == AF_INET6)
ip_vs_nat_icmp_v6(skb, pp, cp, 1);
@@ -768,16 +783,8 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
#endif
ip_vs_nat_icmp(skb, pp, cp, 1);
-#ifdef CONFIG_IP_VS_IPV6
- if (af == AF_INET6) {
- if (ipvs->sysctl_snat_reroute && ip6_route_me_harder(skb) != 0)
- goto out;
- } else
-#endif
- if ((ipvs->sysctl_snat_reroute ||
- skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
- ip_route_me_harder(skb, RTN_LOCAL) != 0)
- goto out;
+ if (ip_vs_route_me_harder(af, skb))
+ goto out;
/* do the statistics and put it back */
ip_vs_out_stats(cp, skb);
@@ -985,7 +992,6 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
struct ip_vs_conn *cp, int ihl)
{
struct ip_vs_protocol *pp = pd->pp;
- struct netns_ipvs *ipvs;
IP_VS_DBG_PKT(11, af, pp, skb, 0, "Outgoing packet");
@@ -1021,18 +1027,8 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
* if it came from this machine itself. So re-compute
* the routing information.
*/
- ipvs = net_ipvs(skb_net(skb));
-
-#ifdef CONFIG_IP_VS_IPV6
- if (af == AF_INET6) {
- if (ipvs->sysctl_snat_reroute && ip6_route_me_harder(skb) != 0)
- goto drop;
- } else
-#endif
- if ((ipvs->sysctl_snat_reroute ||
- skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
- ip_route_me_harder(skb, RTN_LOCAL) != 0)
- goto drop;
+ if (ip_vs_route_me_harder(af, skb))
+ goto drop;
IP_VS_DBG_PKT(10, af, pp, skb, 0, "After SNAT");
--
1.7.2.3
^ permalink raw reply related
* [PATCH 14/37] ipvs: rename estimator functions
From: kaber @ 2011-03-15 19:43 UTC (permalink / raw)
To: davem; +Cc: netfilter-devel, netdev
In-Reply-To: <1300218257-26953-1-git-send-email-kaber@trash.net>
From: Julian Anastasov <ja@ssi.bg>
Rename ip_vs_new_estimator to ip_vs_start_estimator
and ip_vs_kill_estimator to ip_vs_stop_estimator to better
match their logic.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
include/net/ip_vs.h | 4 ++--
net/netfilter/ipvs/ip_vs_ctl.c | 12 ++++++------
net/netfilter/ipvs/ip_vs_est.c | 4 ++--
3 files changed, 10 insertions(+), 10 deletions(-)
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index e4a39c4..7ca5be2 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1176,8 +1176,8 @@ extern void ip_vs_sync_cleanup(void);
*/
extern int ip_vs_estimator_init(void);
extern void ip_vs_estimator_cleanup(void);
-extern void ip_vs_new_estimator(struct net *net, struct ip_vs_stats *stats);
-extern void ip_vs_kill_estimator(struct net *net, struct ip_vs_stats *stats);
+extern void ip_vs_start_estimator(struct net *net, struct ip_vs_stats *stats);
+extern void ip_vs_stop_estimator(struct net *net, struct ip_vs_stats *stats);
extern void ip_vs_zero_estimator(struct ip_vs_stats *stats);
extern void ip_vs_read_estimator(struct ip_vs_stats_user *dst,
struct ip_vs_stats *stats);
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index c93d806..c5b1234 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -802,7 +802,7 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
spin_unlock(&dest->dst_lock);
if (add)
- ip_vs_new_estimator(svc->net, &dest->stats);
+ ip_vs_start_estimator(svc->net, &dest->stats);
write_lock_bh(&__ip_vs_svc_lock);
@@ -1008,7 +1008,7 @@ static void __ip_vs_del_dest(struct net *net, struct ip_vs_dest *dest)
{
struct netns_ipvs *ipvs = net_ipvs(net);
- ip_vs_kill_estimator(net, &dest->stats);
+ ip_vs_stop_estimator(net, &dest->stats);
/*
* Remove it from the d-linked list with the real services.
@@ -1201,7 +1201,7 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u,
else if (svc->port == 0)
atomic_inc(&ipvs->nullsvc_counter);
- ip_vs_new_estimator(net, &svc->stats);
+ ip_vs_start_estimator(net, &svc->stats);
/* Count only IPv4 services for old get/setsockopt interface */
if (svc->af == AF_INET)
@@ -1353,7 +1353,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc)
if (svc->af == AF_INET)
ipvs->num_services--;
- ip_vs_kill_estimator(svc->net, &svc->stats);
+ ip_vs_stop_estimator(svc->net, &svc->stats);
/* Unbind scheduler */
old_sched = svc->scheduler;
@@ -3585,7 +3585,7 @@ int __net_init __ip_vs_control_init(struct net *net)
goto err_dup;
}
#endif
- ip_vs_new_estimator(net, &ipvs->tot_stats);
+ ip_vs_start_estimator(net, &ipvs->tot_stats);
ipvs->sysctl_tbl = tbl;
/* Schedule defense work */
INIT_DELAYED_WORK(&ipvs->defense_work, defense_work_handler);
@@ -3603,7 +3603,7 @@ static void __net_exit __ip_vs_control_cleanup(struct net *net)
struct netns_ipvs *ipvs = net_ipvs(net);
ip_vs_trash_cleanup(net);
- ip_vs_kill_estimator(net, &ipvs->tot_stats);
+ ip_vs_stop_estimator(net, &ipvs->tot_stats);
cancel_delayed_work_sync(&ipvs->defense_work);
cancel_work_sync(&ipvs->defense_work.work);
#ifdef CONFIG_SYSCTL
diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c
index fda75be..8c8766c 100644
--- a/net/netfilter/ipvs/ip_vs_est.c
+++ b/net/netfilter/ipvs/ip_vs_est.c
@@ -139,7 +139,7 @@ static void estimation_timer(unsigned long arg)
mod_timer(&ipvs->est_timer, jiffies + 2*HZ);
}
-void ip_vs_new_estimator(struct net *net, struct ip_vs_stats *stats)
+void ip_vs_start_estimator(struct net *net, struct ip_vs_stats *stats)
{
struct netns_ipvs *ipvs = net_ipvs(net);
struct ip_vs_estimator *est = &stats->est;
@@ -151,7 +151,7 @@ void ip_vs_new_estimator(struct net *net, struct ip_vs_stats *stats)
spin_unlock_bh(&ipvs->est_lock);
}
-void ip_vs_kill_estimator(struct net *net, struct ip_vs_stats *stats)
+void ip_vs_stop_estimator(struct net *net, struct ip_vs_stats *stats)
{
struct netns_ipvs *ipvs = net_ipvs(net);
struct ip_vs_estimator *est = &stats->est;
--
1.7.2.3
^ permalink raw reply related
* [PATCH 10/37] ipvs: reorganize tot_stats
From: kaber @ 2011-03-15 19:43 UTC (permalink / raw)
To: davem; +Cc: netfilter-devel, netdev
In-Reply-To: <1300218257-26953-1-git-send-email-kaber@trash.net>
From: Julian Anastasov <ja@ssi.bg>
The global tot_stats contains cpustats field just like the
stats for dest and svc, so better use it to simplify the usage
in estimation_timer. As tot_stats is registered as estimator
we can remove the special ip_vs_read_cpu_stats call for
tot_stats. Fix ip_vs_read_cpu_stats to be called under
stats lock because it is still used as synchronization between
estimation timer and user context (the stats readers).
Also, make sure ip_vs_stats_percpu_show reads properly
the u64 stats from user context.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
include/net/ip_vs.h | 3 +-
net/netfilter/ipvs/ip_vs_core.c | 6 ++--
net/netfilter/ipvs/ip_vs_ctl.c | 45 ++++++++++++++++++++------------------
net/netfilter/ipvs/ip_vs_est.c | 3 +-
4 files changed, 29 insertions(+), 28 deletions(-)
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 091ca1f..9db750d 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -851,8 +851,7 @@ struct netns_ipvs {
atomic_t conn_count; /* connection counter */
/* ip_vs_ctl */
- struct ip_vs_stats *tot_stats; /* Statistics & est. */
- struct ip_vs_cpu_stats __percpu *cpustats; /* Stats per cpu */
+ struct ip_vs_stats tot_stats; /* Statistics & est. */
seqcount_t *ustats_seq; /* u64 read retry */
int num_services; /* no of virtual services */
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 2d1f932..6f4940e 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -132,7 +132,7 @@ ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
s->ustats.inbytes += skb->len;
u64_stats_update_end(&s->syncp);
- s = this_cpu_ptr(ipvs->cpustats);
+ s = this_cpu_ptr(ipvs->tot_stats.cpustats);
s->ustats.inpkts++;
u64_stats_update_begin(&s->syncp);
s->ustats.inbytes += skb->len;
@@ -162,7 +162,7 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb)
s->ustats.outbytes += skb->len;
u64_stats_update_end(&s->syncp);
- s = this_cpu_ptr(ipvs->cpustats);
+ s = this_cpu_ptr(ipvs->tot_stats.cpustats);
s->ustats.outpkts++;
u64_stats_update_begin(&s->syncp);
s->ustats.outbytes += skb->len;
@@ -183,7 +183,7 @@ ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc)
s = this_cpu_ptr(svc->stats.cpustats);
s->ustats.conns++;
- s = this_cpu_ptr(ipvs->cpustats);
+ s = this_cpu_ptr(ipvs->tot_stats.cpustats);
s->ustats.conns++;
}
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index f0369d6..a2a67ad 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1481,7 +1481,7 @@ static int ip_vs_zero_all(struct net *net)
}
}
- ip_vs_zero_stats(net_ipvs(net)->tot_stats);
+ ip_vs_zero_stats(&net_ipvs(net)->tot_stats);
return 0;
}
@@ -1963,7 +1963,7 @@ static const struct file_operations ip_vs_info_fops = {
static int ip_vs_stats_show(struct seq_file *seq, void *v)
{
struct net *net = seq_file_single_net(seq);
- struct ip_vs_stats *tot_stats = net_ipvs(net)->tot_stats;
+ struct ip_vs_stats *tot_stats = &net_ipvs(net)->tot_stats;
/* 01234567 01234567 01234567 0123456701234567 0123456701234567 */
seq_puts(seq,
@@ -2007,7 +2007,8 @@ static const struct file_operations ip_vs_stats_fops = {
static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v)
{
struct net *net = seq_file_single_net(seq);
- struct ip_vs_stats *tot_stats = net_ipvs(net)->tot_stats;
+ struct ip_vs_stats *tot_stats = &net_ipvs(net)->tot_stats;
+ struct ip_vs_cpu_stats *cpustats = tot_stats->cpustats;
int i;
/* 01234567 01234567 01234567 0123456701234567 0123456701234567 */
@@ -2017,11 +2018,20 @@ static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v)
"CPU Conns Packets Packets Bytes Bytes\n");
for_each_possible_cpu(i) {
- struct ip_vs_cpu_stats *u = per_cpu_ptr(net->ipvs->cpustats, i);
+ struct ip_vs_cpu_stats *u = per_cpu_ptr(cpustats, i);
+ unsigned int start;
+ __u64 inbytes, outbytes;
+
+ do {
+ start = u64_stats_fetch_begin_bh(&u->syncp);
+ inbytes = u->ustats.inbytes;
+ outbytes = u->ustats.outbytes;
+ } while (u64_stats_fetch_retry_bh(&u->syncp, start));
+
seq_printf(seq, "%3X %8X %8X %8X %16LX %16LX\n",
- i, u->ustats.conns, u->ustats.inpkts,
- u->ustats.outpkts, (__u64)u->ustats.inbytes,
- (__u64)u->ustats.outbytes);
+ i, u->ustats.conns, u->ustats.inpkts,
+ u->ustats.outpkts, (__u64)inbytes,
+ (__u64)outbytes);
}
spin_lock_bh(&tot_stats->lock);
@@ -3505,17 +3515,12 @@ int __net_init __ip_vs_control_init(struct net *net)
atomic_set(&ipvs->nullsvc_counter, 0);
/* procfs stats */
- ipvs->tot_stats = kzalloc(sizeof(struct ip_vs_stats), GFP_KERNEL);
- if (ipvs->tot_stats == NULL) {
- pr_err("%s(): no memory.\n", __func__);
- return -ENOMEM;
- }
- ipvs->cpustats = alloc_percpu(struct ip_vs_cpu_stats);
- if (!ipvs->cpustats) {
+ ipvs->tot_stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats);
+ if (!ipvs->tot_stats.cpustats) {
pr_err("%s() alloc_percpu failed\n", __func__);
goto err_alloc;
}
- spin_lock_init(&ipvs->tot_stats->lock);
+ spin_lock_init(&ipvs->tot_stats.lock);
proc_net_fops_create(net, "ip_vs", 0, &ip_vs_info_fops);
proc_net_fops_create(net, "ip_vs_stats", 0, &ip_vs_stats_fops);
@@ -3563,7 +3568,7 @@ int __net_init __ip_vs_control_init(struct net *net)
goto err_dup;
}
#endif
- ip_vs_new_estimator(net, ipvs->tot_stats);
+ ip_vs_new_estimator(net, &ipvs->tot_stats);
ipvs->sysctl_tbl = tbl;
/* Schedule defense work */
INIT_DELAYED_WORK(&ipvs->defense_work, defense_work_handler);
@@ -3571,9 +3576,8 @@ int __net_init __ip_vs_control_init(struct net *net)
return 0;
err_dup:
- free_percpu(ipvs->cpustats);
+ free_percpu(ipvs->tot_stats.cpustats);
err_alloc:
- kfree(ipvs->tot_stats);
return -ENOMEM;
}
@@ -3582,7 +3586,7 @@ static void __net_exit __ip_vs_control_cleanup(struct net *net)
struct netns_ipvs *ipvs = net_ipvs(net);
ip_vs_trash_cleanup(net);
- ip_vs_kill_estimator(net, ipvs->tot_stats);
+ ip_vs_kill_estimator(net, &ipvs->tot_stats);
cancel_delayed_work_sync(&ipvs->defense_work);
cancel_work_sync(&ipvs->defense_work.work);
#ifdef CONFIG_SYSCTL
@@ -3591,8 +3595,7 @@ static void __net_exit __ip_vs_control_cleanup(struct net *net)
proc_net_remove(net, "ip_vs_stats_percpu");
proc_net_remove(net, "ip_vs_stats");
proc_net_remove(net, "ip_vs");
- free_percpu(ipvs->cpustats);
- kfree(ipvs->tot_stats);
+ free_percpu(ipvs->tot_stats.cpustats);
}
static struct pernet_operations ipvs_control_ops = {
diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c
index 88bd716..b3751cf 100644
--- a/net/netfilter/ipvs/ip_vs_est.c
+++ b/net/netfilter/ipvs/ip_vs_est.c
@@ -101,13 +101,12 @@ static void estimation_timer(unsigned long arg)
struct netns_ipvs *ipvs;
ipvs = net_ipvs(net);
- ip_vs_read_cpu_stats(&ipvs->tot_stats->ustats, ipvs->cpustats);
spin_lock(&ipvs->est_lock);
list_for_each_entry(e, &ipvs->est_list, list) {
s = container_of(e, struct ip_vs_stats, est);
- ip_vs_read_cpu_stats(&s->ustats, s->cpustats);
spin_lock(&s->lock);
+ ip_vs_read_cpu_stats(&s->ustats, s->cpustats);
n_conns = s->ustats.conns;
n_inpkts = s->ustats.inpkts;
n_outpkts = s->ustats.outpkts;
--
1.7.2.3
^ permalink raw reply related
* [PATCH 09/37] ipvs: move struct netns_ipvs
From: kaber @ 2011-03-15 19:43 UTC (permalink / raw)
To: davem; +Cc: netfilter-devel, netdev
In-Reply-To: <1300218257-26953-1-git-send-email-kaber@trash.net>
From: Julian Anastasov <ja@ssi.bg>
Remove include/net/netns/ip_vs.h because it depends on
structures from include/net/ip_vs.h. As ipvs is pointer in
struct net it is better to move struct netns_ipvs into
include/net/ip_vs.h, so that we can easily use other structures
in struct netns_ipvs.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
include/net/ip_vs.h | 122 ++++++++++++++++++++++++++++++++++++
include/net/net_namespace.h | 2 +-
include/net/netns/ip_vs.h | 143 -------------------------------------------
3 files changed, 123 insertions(+), 144 deletions(-)
delete mode 100644 include/net/netns/ip_vs.h
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 1dcb75d..091ca1f 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -803,6 +803,128 @@ struct ip_vs_app {
void (*timeout_change)(struct ip_vs_app *app, int flags);
};
+/* IPVS in network namespace */
+struct netns_ipvs {
+ int gen; /* Generation */
+ /*
+ * Hash table: for real service lookups
+ */
+ #define IP_VS_RTAB_BITS 4
+ #define IP_VS_RTAB_SIZE (1 << IP_VS_RTAB_BITS)
+ #define IP_VS_RTAB_MASK (IP_VS_RTAB_SIZE - 1)
+
+ struct list_head rs_table[IP_VS_RTAB_SIZE];
+ /* ip_vs_app */
+ struct list_head app_list;
+ struct mutex app_mutex;
+ struct lock_class_key app_key; /* mutex debuging */
+
+ /* ip_vs_proto */
+ #define IP_VS_PROTO_TAB_SIZE 32 /* must be power of 2 */
+ struct ip_vs_proto_data *proto_data_table[IP_VS_PROTO_TAB_SIZE];
+ /* ip_vs_proto_tcp */
+#ifdef CONFIG_IP_VS_PROTO_TCP
+ #define TCP_APP_TAB_BITS 4
+ #define TCP_APP_TAB_SIZE (1 << TCP_APP_TAB_BITS)
+ #define TCP_APP_TAB_MASK (TCP_APP_TAB_SIZE - 1)
+ struct list_head tcp_apps[TCP_APP_TAB_SIZE];
+ spinlock_t tcp_app_lock;
+#endif
+ /* ip_vs_proto_udp */
+#ifdef CONFIG_IP_VS_PROTO_UDP
+ #define UDP_APP_TAB_BITS 4
+ #define UDP_APP_TAB_SIZE (1 << UDP_APP_TAB_BITS)
+ #define UDP_APP_TAB_MASK (UDP_APP_TAB_SIZE - 1)
+ struct list_head udp_apps[UDP_APP_TAB_SIZE];
+ spinlock_t udp_app_lock;
+#endif
+ /* ip_vs_proto_sctp */
+#ifdef CONFIG_IP_VS_PROTO_SCTP
+ #define SCTP_APP_TAB_BITS 4
+ #define SCTP_APP_TAB_SIZE (1 << SCTP_APP_TAB_BITS)
+ #define SCTP_APP_TAB_MASK (SCTP_APP_TAB_SIZE - 1)
+ /* Hash table for SCTP application incarnations */
+ struct list_head sctp_apps[SCTP_APP_TAB_SIZE];
+ spinlock_t sctp_app_lock;
+#endif
+ /* ip_vs_conn */
+ atomic_t conn_count; /* connection counter */
+
+ /* ip_vs_ctl */
+ struct ip_vs_stats *tot_stats; /* Statistics & est. */
+ struct ip_vs_cpu_stats __percpu *cpustats; /* Stats per cpu */
+ seqcount_t *ustats_seq; /* u64 read retry */
+
+ int num_services; /* no of virtual services */
+ /* 1/rate drop and drop-entry variables */
+ struct delayed_work defense_work; /* Work handler */
+ int drop_rate;
+ int drop_counter;
+ atomic_t dropentry;
+ /* locks in ctl.c */
+ spinlock_t dropentry_lock; /* drop entry handling */
+ spinlock_t droppacket_lock; /* drop packet handling */
+ spinlock_t securetcp_lock; /* state and timeout tables */
+ rwlock_t rs_lock; /* real services table */
+ /* semaphore for IPVS sockopts. And, [gs]etsockopt may sleep. */
+ struct lock_class_key ctl_key; /* ctl_mutex debuging */
+ /* Trash for destinations */
+ struct list_head dest_trash;
+ /* Service counters */
+ atomic_t ftpsvc_counter;
+ atomic_t nullsvc_counter;
+
+ /* sys-ctl struct */
+ struct ctl_table_header *sysctl_hdr;
+ struct ctl_table *sysctl_tbl;
+ /* sysctl variables */
+ int sysctl_amemthresh;
+ int sysctl_am_droprate;
+ int sysctl_drop_entry;
+ int sysctl_drop_packet;
+ int sysctl_secure_tcp;
+#ifdef CONFIG_IP_VS_NFCT
+ int sysctl_conntrack;
+#endif
+ int sysctl_snat_reroute;
+ int sysctl_sync_ver;
+ int sysctl_cache_bypass;
+ int sysctl_expire_nodest_conn;
+ int sysctl_expire_quiescent_template;
+ int sysctl_sync_threshold[2];
+ int sysctl_nat_icmp_send;
+
+ /* ip_vs_lblc */
+ int sysctl_lblc_expiration;
+ struct ctl_table_header *lblc_ctl_header;
+ struct ctl_table *lblc_ctl_table;
+ /* ip_vs_lblcr */
+ int sysctl_lblcr_expiration;
+ struct ctl_table_header *lblcr_ctl_header;
+ struct ctl_table *lblcr_ctl_table;
+ /* ip_vs_est */
+ struct list_head est_list; /* estimator list */
+ spinlock_t est_lock;
+ struct timer_list est_timer; /* Estimation timer */
+ /* ip_vs_sync */
+ struct list_head sync_queue;
+ spinlock_t sync_lock;
+ struct ip_vs_sync_buff *sync_buff;
+ spinlock_t sync_buff_lock;
+ struct sockaddr_in sync_mcast_addr;
+ struct task_struct *master_thread;
+ struct task_struct *backup_thread;
+ int send_mesg_maxlen;
+ int recv_mesg_maxlen;
+ volatile int sync_state;
+ volatile int master_syncid;
+ volatile int backup_syncid;
+ /* multicast interface name */
+ char master_mcast_ifn[IP_VS_IFNAME_MAXLEN];
+ char backup_mcast_ifn[IP_VS_IFNAME_MAXLEN];
+ /* net name space ptr */
+ struct net *net; /* Needed by timer routines */
+};
/*
* IPVS core functions
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index b3b4a34..3ae4919 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -20,7 +20,6 @@
#include <net/netns/conntrack.h>
#endif
#include <net/netns/xfrm.h>
-#include <net/netns/ip_vs.h>
struct proc_dir_entry;
struct net_device;
@@ -28,6 +27,7 @@ struct sock;
struct ctl_table_header;
struct net_generic;
struct sock;
+struct netns_ipvs;
#define NETDEV_HASHBITS 8
diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h
deleted file mode 100644
index 259ebac..0000000
--- a/include/net/netns/ip_vs.h
+++ /dev/null
@@ -1,143 +0,0 @@
-/*
- * IP Virtual Server
- * Data structure for network namspace
- *
- */
-
-#ifndef IP_VS_H_
-#define IP_VS_H_
-
-#include <linux/list.h>
-#include <linux/mutex.h>
-#include <linux/list_nulls.h>
-#include <linux/ip_vs.h>
-#include <asm/atomic.h>
-#include <linux/in.h>
-
-struct ip_vs_stats;
-struct ip_vs_sync_buff;
-struct ctl_table_header;
-
-struct netns_ipvs {
- int gen; /* Generation */
- /*
- * Hash table: for real service lookups
- */
- #define IP_VS_RTAB_BITS 4
- #define IP_VS_RTAB_SIZE (1 << IP_VS_RTAB_BITS)
- #define IP_VS_RTAB_MASK (IP_VS_RTAB_SIZE - 1)
-
- struct list_head rs_table[IP_VS_RTAB_SIZE];
- /* ip_vs_app */
- struct list_head app_list;
- struct mutex app_mutex;
- struct lock_class_key app_key; /* mutex debuging */
-
- /* ip_vs_proto */
- #define IP_VS_PROTO_TAB_SIZE 32 /* must be power of 2 */
- struct ip_vs_proto_data *proto_data_table[IP_VS_PROTO_TAB_SIZE];
- /* ip_vs_proto_tcp */
-#ifdef CONFIG_IP_VS_PROTO_TCP
- #define TCP_APP_TAB_BITS 4
- #define TCP_APP_TAB_SIZE (1 << TCP_APP_TAB_BITS)
- #define TCP_APP_TAB_MASK (TCP_APP_TAB_SIZE - 1)
- struct list_head tcp_apps[TCP_APP_TAB_SIZE];
- spinlock_t tcp_app_lock;
-#endif
- /* ip_vs_proto_udp */
-#ifdef CONFIG_IP_VS_PROTO_UDP
- #define UDP_APP_TAB_BITS 4
- #define UDP_APP_TAB_SIZE (1 << UDP_APP_TAB_BITS)
- #define UDP_APP_TAB_MASK (UDP_APP_TAB_SIZE - 1)
- struct list_head udp_apps[UDP_APP_TAB_SIZE];
- spinlock_t udp_app_lock;
-#endif
- /* ip_vs_proto_sctp */
-#ifdef CONFIG_IP_VS_PROTO_SCTP
- #define SCTP_APP_TAB_BITS 4
- #define SCTP_APP_TAB_SIZE (1 << SCTP_APP_TAB_BITS)
- #define SCTP_APP_TAB_MASK (SCTP_APP_TAB_SIZE - 1)
- /* Hash table for SCTP application incarnations */
- struct list_head sctp_apps[SCTP_APP_TAB_SIZE];
- spinlock_t sctp_app_lock;
-#endif
- /* ip_vs_conn */
- atomic_t conn_count; /* connection counter */
-
- /* ip_vs_ctl */
- struct ip_vs_stats *tot_stats; /* Statistics & est. */
- struct ip_vs_cpu_stats __percpu *cpustats; /* Stats per cpu */
- seqcount_t *ustats_seq; /* u64 read retry */
-
- int num_services; /* no of virtual services */
- /* 1/rate drop and drop-entry variables */
- struct delayed_work defense_work; /* Work handler */
- int drop_rate;
- int drop_counter;
- atomic_t dropentry;
- /* locks in ctl.c */
- spinlock_t dropentry_lock; /* drop entry handling */
- spinlock_t droppacket_lock; /* drop packet handling */
- spinlock_t securetcp_lock; /* state and timeout tables */
- rwlock_t rs_lock; /* real services table */
- /* semaphore for IPVS sockopts. And, [gs]etsockopt may sleep. */
- struct lock_class_key ctl_key; /* ctl_mutex debuging */
- /* Trash for destinations */
- struct list_head dest_trash;
- /* Service counters */
- atomic_t ftpsvc_counter;
- atomic_t nullsvc_counter;
-
- /* sys-ctl struct */
- struct ctl_table_header *sysctl_hdr;
- struct ctl_table *sysctl_tbl;
- /* sysctl variables */
- int sysctl_amemthresh;
- int sysctl_am_droprate;
- int sysctl_drop_entry;
- int sysctl_drop_packet;
- int sysctl_secure_tcp;
-#ifdef CONFIG_IP_VS_NFCT
- int sysctl_conntrack;
-#endif
- int sysctl_snat_reroute;
- int sysctl_sync_ver;
- int sysctl_cache_bypass;
- int sysctl_expire_nodest_conn;
- int sysctl_expire_quiescent_template;
- int sysctl_sync_threshold[2];
- int sysctl_nat_icmp_send;
-
- /* ip_vs_lblc */
- int sysctl_lblc_expiration;
- struct ctl_table_header *lblc_ctl_header;
- struct ctl_table *lblc_ctl_table;
- /* ip_vs_lblcr */
- int sysctl_lblcr_expiration;
- struct ctl_table_header *lblcr_ctl_header;
- struct ctl_table *lblcr_ctl_table;
- /* ip_vs_est */
- struct list_head est_list; /* estimator list */
- spinlock_t est_lock;
- struct timer_list est_timer; /* Estimation timer */
- /* ip_vs_sync */
- struct list_head sync_queue;
- spinlock_t sync_lock;
- struct ip_vs_sync_buff *sync_buff;
- spinlock_t sync_buff_lock;
- struct sockaddr_in sync_mcast_addr;
- struct task_struct *master_thread;
- struct task_struct *backup_thread;
- int send_mesg_maxlen;
- int recv_mesg_maxlen;
- volatile int sync_state;
- volatile int master_syncid;
- volatile int backup_syncid;
- /* multicast interface name */
- char master_mcast_ifn[IP_VS_IFNAME_MAXLEN];
- char backup_mcast_ifn[IP_VS_IFNAME_MAXLEN];
- /* net name space ptr */
- struct net *net; /* Needed by timer routines */
-};
-
-#endif /* IP_VS_H_ */
--
1.7.2.3
^ permalink raw reply related
* [PATCH 08/37] IPVS: Fix variable assignment in ip_vs_notrack
From: kaber @ 2011-03-15 19:43 UTC (permalink / raw)
To: davem; +Cc: netfilter-devel, netdev
In-Reply-To: <1300218257-26953-1-git-send-email-kaber@trash.net>
From: Jesper Juhl <jj@chaosbits.net>
There's no sense to 'ct = ct = ' in ip_vs_notrack(). Just assign
nf_ct_get()'s return value directly to the pointer variable 'ct' once.
Signed-off-by: Jesper Juhl <jj@chaosbits.net>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
include/net/ip_vs.h | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index e74da41e..1dcb75d 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1190,7 +1190,7 @@ static inline void ip_vs_notrack(struct sk_buff *skb)
{
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
enum ip_conntrack_info ctinfo;
- struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo);
+ struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
if (!ct || !nf_ct_is_untracked(ct)) {
nf_reset(skb);
--
1.7.2.3
^ permalink raw reply related
* [PATCH 05/37] ipvs: avoid lookup for fwmark 0
From: kaber @ 2011-03-15 19:43 UTC (permalink / raw)
To: davem; +Cc: netfilter-devel, netdev
In-Reply-To: <1300218257-26953-1-git-send-email-kaber@trash.net>
From: Julian Anastasov <ja@ssi.bg>
Restore the previous behaviour to lookup for fwmark
service only when fwmark is non-null. This saves only CPU.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Hans Schillstrom <hans@schillstrom.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
net/netfilter/ipvs/ip_vs_ctl.c | 8 +++++---
1 files changed, 5 insertions(+), 3 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index c73b0c8..f0369d6 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -411,9 +411,11 @@ ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol,
/*
* Check the table hashed by fwmark first
*/
- svc = __ip_vs_svc_fwm_find(net, af, fwmark);
- if (fwmark && svc)
- goto out;
+ if (fwmark) {
+ svc = __ip_vs_svc_fwm_find(net, af, fwmark);
+ if (svc)
+ goto out;
+ }
/*
* Check the table hashed by <protocol,addr,port>
--
1.7.2.3
^ permalink raw reply related
* [PATCH 03/37] netfilter: x_tables: return -ENOENT for non-existant matches/targets
From: kaber @ 2011-03-15 19:43 UTC (permalink / raw)
To: davem; +Cc: netfilter-devel, netdev
In-Reply-To: <1300218257-26953-1-git-send-email-kaber@trash.net>
From: Patrick McHardy <kaber@trash.net>
As Stephen correctly points out, we need to return -ENOENT in
xt_find_match()/xt_find_target() after the patch "netfilter: x_tables:
misuse of try_then_request_module" in order to properly indicate
a non-existant module to the caller.
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
net/netfilter/x_tables.c | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 271eed3..a9adf4c 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -190,7 +190,7 @@ EXPORT_SYMBOL(xt_unregister_matches);
struct xt_match *xt_find_match(u8 af, const char *name, u8 revision)
{
struct xt_match *m;
- int err = 0;
+ int err = -ENOENT;
if (mutex_lock_interruptible(&xt[af].mutex) != 0)
return ERR_PTR(-EINTR);
@@ -235,7 +235,7 @@ EXPORT_SYMBOL_GPL(xt_request_find_match);
struct xt_target *xt_find_target(u8 af, const char *name, u8 revision)
{
struct xt_target *t;
- int err = 0;
+ int err = -ENOENT;
if (mutex_lock_interruptible(&xt[af].mutex) != 0)
return ERR_PTR(-EINTR);
--
1.7.2.3
^ permalink raw reply related
* [PATCH 00/37] netfilter: netfilter update
From: kaber @ 2011-03-15 19:43 UTC (permalink / raw)
To: davem; +Cc: netfilter-devel, netdev
Hi Dave,
[appologies if this reaches you twice, my mail settings were misconfigured]
following is a final netfilter update for net-next, containing:
- a fix for misuse of try_then_request_module(), from Stephen
- a fix for a sysctl memory leak, from Stephen
- IPVS updates from Simon, mainly consisting of exclusion of control code
when CONFIG_SYSCTL=n
- xt_connlimit cleanups and fixes, from Changli
- conversion of xt_connlimit to hlists, from Changli
- fixes for some information leaks in {ip,ip6,arp}_tables, from Vasiliy Kulikov
- an IPv6 capable version of the addrtype match, from Florian Westphal
Please pull from:
git://git.kernel.org/pub/scm/linux/kernel/git/kaber/nf-next-2.6.git master
Thanks!
^ permalink raw reply
* pull request: wireless-next-2.6 2011-03-15
From: John W. Linville @ 2011-03-15 19:31 UTC (permalink / raw)
To: davem; +Cc: linux-wireless, netdev
Dave,
One last non-fix pull for 2.6.39 -- hooray!
Not a lot here, since we just had a pull towards the end of last week.
There are a handfule of ath9k bits, a couple of wl1251 patches,
a couple of mac80211 bits, etc. Nothing too troublesome. :-)
Please let me know if there are problems!
Thanks,
John
---
The following changes since commit 0c0217b016ba8a970a6f6ab62ad0d858f39881ca:
net: dcbnl: Add IEEE app selector value definitions (2011-03-14 17:02:43 -0700)
are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-next-2.6.git for-davem
Dan Carpenter (1):
libertas: fix write past end of array in mesh_id_get()
Felix Fietkau (7):
ath9k: remove support for the FIF_PROMISC_IN_BSS filter flag
ath9k_hw: fix REG_SET_BIT and REG_CLR_BIT for multiple bits
ath9k: fix stopping tx dma on reset
ath9k: fix the .flush driver op implementation
ath9k: improve reliability of beacon transmission and stuck beacon handling
mac80211: fix channel type recalculation with HT and non-HT interfaces
ath9k: fix aggregation related interoperability issues
Grazvydas Ignotas (2):
wl1251: remove wl1251_ps_set_elp function
wl1251: fix elp_work race condition
Helmut Schaa (1):
mac80211: Shortcut minstrel_ht rate setup for non-MRR capable devices
Jason Young (1):
mac80211: do not enable ps if 802.1x controlled port is unblocked
Johannes Berg (1):
iwlagn: support off-channel TX
John W. Linville (4):
wireless: add support for ethtool_ops->{get,set}_ringparam
mac80211: implement support for cfg80211_ops->{get,set}_ringparam
ath5k: implement ieee80211_ops->{get,set}_ringparam
Merge branch 'master' of git://git.kernel.org/.../linville/wireless-next-2.6 into for-davem
Vivek Natarajan (3):
ath9k_hw: Improve idle power consumption for AR9485.
ath9k_hw: Fix PLL initialization for AR9485.
ath9k_hw: Increase the wait count for nf load.
drivers/net/wireless/ath/ath5k/base.c | 3 +-
drivers/net/wireless/ath/ath5k/base.h | 1 +
drivers/net/wireless/ath/ath5k/mac80211-ops.c | 43 +++++++
drivers/net/wireless/ath/ath9k/ar9485_initvals.h | 2 +
drivers/net/wireless/ath/ath9k/ath9k.h | 1 -
drivers/net/wireless/ath/ath9k/beacon.c | 13 +--
drivers/net/wireless/ath/ath9k/calib.c | 4 +-
drivers/net/wireless/ath/ath9k/hw.c | 4 +-
drivers/net/wireless/ath/ath9k/hw.h | 4 +-
drivers/net/wireless/ath/ath9k/mac.c | 91 ++++++---------
drivers/net/wireless/ath/ath9k/mac.h | 3 +-
drivers/net/wireless/ath/ath9k/main.c | 56 ++++------
drivers/net/wireless/ath/ath9k/recv.c | 4 +-
drivers/net/wireless/ath/ath9k/xmit.c | 44 +++----
drivers/net/wireless/iwlwifi/iwl-agn-lib.c | 135 ++++++++++++++++-----
drivers/net/wireless/iwlwifi/iwl-agn.c | 87 ++++++++++++++
drivers/net/wireless/iwlwifi/iwl-commands.h | 8 +-
drivers/net/wireless/iwlwifi/iwl-core.h | 6 +
drivers/net/wireless/iwlwifi/iwl-dev.h | 12 ++-
drivers/net/wireless/iwlwifi/iwl-scan.c | 41 ++++---
drivers/net/wireless/libertas/mesh.c | 11 +-
drivers/net/wireless/wl1251/ps.c | 41 +------
include/net/cfg80211.h | 8 ++
include/net/mac80211.h | 7 +
net/mac80211/cfg.c | 21 ++++
net/mac80211/chan.c | 3 +
net/mac80211/driver-ops.h | 26 ++++
net/mac80211/driver-trace.h | 52 ++++++++
net/mac80211/mlme.c | 37 +++++-
net/mac80211/rc80211_minstrel_ht.c | 41 ++++++-
net/wireless/ethtool.c | 33 ++++++
31 files changed, 597 insertions(+), 245 deletions(-)
diff --git a/drivers/net/wireless/ath/ath5k/base.c b/drivers/net/wireless/ath/ath5k/base.c
index e6ff62e..4d7f21e 100644
--- a/drivers/net/wireless/ath/ath5k/base.c
+++ b/drivers/net/wireless/ath/ath5k/base.c
@@ -943,6 +943,7 @@ ath5k_txq_setup(struct ath5k_softc *sc,
spin_lock_init(&txq->lock);
txq->setup = true;
txq->txq_len = 0;
+ txq->txq_max = ATH5K_TXQ_LEN_MAX;
txq->txq_poll_mark = false;
txq->txq_stuck = 0;
}
@@ -1534,7 +1535,7 @@ ath5k_tx_queue(struct ieee80211_hw *hw, struct sk_buff *skb,
goto drop_packet;
}
- if (txq->txq_len >= ATH5K_TXQ_LEN_MAX)
+ if (txq->txq_len >= txq->txq_max)
ieee80211_stop_queue(hw, txq->qnum);
spin_lock_irqsave(&sc->txbuflock, flags);
diff --git a/drivers/net/wireless/ath/ath5k/base.h b/drivers/net/wireless/ath/ath5k/base.h
index 8d1df1f..978f1f4 100644
--- a/drivers/net/wireless/ath/ath5k/base.h
+++ b/drivers/net/wireless/ath/ath5k/base.h
@@ -86,6 +86,7 @@ struct ath5k_txq {
spinlock_t lock; /* lock on q and link */
bool setup;
int txq_len; /* number of queued buffers */
+ int txq_max; /* max allowed num of queued buffers */
bool txq_poll_mark;
unsigned int txq_stuck; /* informational counter */
};
diff --git a/drivers/net/wireless/ath/ath5k/mac80211-ops.c b/drivers/net/wireless/ath/ath5k/mac80211-ops.c
index c9b0b67..9be29b7 100644
--- a/drivers/net/wireless/ath/ath5k/mac80211-ops.c
+++ b/drivers/net/wireless/ath/ath5k/mac80211-ops.c
@@ -740,6 +740,47 @@ ath5k_get_antenna(struct ieee80211_hw *hw, u32 *tx_ant, u32 *rx_ant)
}
+static void ath5k_get_ringparam(struct ieee80211_hw *hw,
+ u32 *tx, u32 *tx_max, u32 *rx, u32 *rx_max)
+{
+ struct ath5k_softc *sc = hw->priv;
+
+ *tx = sc->txqs[AR5K_TX_QUEUE_ID_DATA_MIN].txq_max;
+
+ *tx_max = ATH5K_TXQ_LEN_MAX;
+ *rx = *rx_max = ATH_RXBUF;
+}
+
+
+static int ath5k_set_ringparam(struct ieee80211_hw *hw, u32 tx, u32 rx)
+{
+ struct ath5k_softc *sc = hw->priv;
+ u16 qnum;
+
+ /* only support setting tx ring size for now */
+ if (rx != ATH_RXBUF)
+ return -EINVAL;
+
+ /* restrict tx ring size min/max */
+ if (!tx || tx > ATH5K_TXQ_LEN_MAX)
+ return -EINVAL;
+
+ for (qnum = 0; qnum < ARRAY_SIZE(sc->txqs); qnum++) {
+ if (!sc->txqs[qnum].setup)
+ continue;
+ if (sc->txqs[qnum].qnum < AR5K_TX_QUEUE_ID_DATA_MIN ||
+ sc->txqs[qnum].qnum > AR5K_TX_QUEUE_ID_DATA_MAX)
+ continue;
+
+ sc->txqs[qnum].txq_max = tx;
+ if (sc->txqs[qnum].txq_len >= sc->txqs[qnum].txq_max)
+ ieee80211_stop_queue(hw, sc->txqs[qnum].qnum);
+ }
+
+ return 0;
+}
+
+
const struct ieee80211_ops ath5k_hw_ops = {
.tx = ath5k_tx,
.start = ath5k_start,
@@ -778,4 +819,6 @@ const struct ieee80211_ops ath5k_hw_ops = {
/* .napi_poll = not implemented */
.set_antenna = ath5k_set_antenna,
.get_antenna = ath5k_get_antenna,
+ .set_ringparam = ath5k_set_ringparam,
+ .get_ringparam = ath5k_get_ringparam,
};
diff --git a/drivers/net/wireless/ath/ath9k/ar9485_initvals.h b/drivers/net/wireless/ath/ath9k/ar9485_initvals.h
index eac4d8526..71cc0a3 100644
--- a/drivers/net/wireless/ath/ath9k/ar9485_initvals.h
+++ b/drivers/net/wireless/ath/ath9k/ar9485_initvals.h
@@ -667,6 +667,7 @@ static const u32 ar9485_1_0_pcie_phy_clkreq_enable_L1[][2] = {
static const u32 ar9485_1_0_soc_preamble[][2] = {
/* Addr allmodes */
+ {0x00004090, 0x00aa10aa},
{0x000040a4, 0x00a0c9c9},
{0x00007048, 0x00000004},
};
@@ -1708,6 +1709,7 @@ static const u32 ar9485_1_1_pcie_phy_clkreq_disable_L1[][2] = {
static const u32 ar9485_1_1_soc_preamble[][2] = {
/* Addr allmodes */
{0x00004014, 0xba280400},
+ {0x00004090, 0x00aa10aa},
{0x000040a4, 0x00a0c9c9},
{0x00007010, 0x00000022},
{0x00007020, 0x00000000},
diff --git a/drivers/net/wireless/ath/ath9k/ath9k.h b/drivers/net/wireless/ath/ath9k/ath9k.h
index c718ab5..099bd41 100644
--- a/drivers/net/wireless/ath/ath9k/ath9k.h
+++ b/drivers/net/wireless/ath/ath9k/ath9k.h
@@ -189,7 +189,6 @@ struct ath_txq {
u32 axq_ampdu_depth;
bool stopped;
bool axq_tx_inprogress;
- bool txq_flush_inprogress;
struct list_head axq_acq;
struct list_head txq_fifo[ATH_TXFIFO_DEPTH];
struct list_head txq_fifo_pending;
diff --git a/drivers/net/wireless/ath/ath9k/beacon.c b/drivers/net/wireless/ath/ath9k/beacon.c
index a4bdfdb..6d2a545f 100644
--- a/drivers/net/wireless/ath/ath9k/beacon.c
+++ b/drivers/net/wireless/ath/ath9k/beacon.c
@@ -373,6 +373,7 @@ void ath_beacon_tasklet(unsigned long data)
ath_dbg(common, ATH_DBG_BSTUCK,
"missed %u consecutive beacons\n",
sc->beacon.bmisscnt);
+ ath9k_hw_stop_dma_queue(ah, sc->beacon.beaconq);
ath9k_hw_bstuck_nfcal(ah);
} else if (sc->beacon.bmisscnt >= BSTUCK_THRESH) {
ath_dbg(common, ATH_DBG_BSTUCK,
@@ -450,16 +451,6 @@ void ath_beacon_tasklet(unsigned long data)
sc->beacon.updateslot = OK;
}
if (bfaddr != 0) {
- /*
- * Stop any current dma and put the new frame(s) on the queue.
- * This should never fail since we check above that no frames
- * are still pending on the queue.
- */
- if (!ath9k_hw_stoptxdma(ah, sc->beacon.beaconq)) {
- ath_err(common, "beacon queue %u did not stop?\n",
- sc->beacon.beaconq);
- }
-
/* NB: cabq traffic should already be queued and primed */
ath9k_hw_puttxbuf(ah, sc->beacon.beaconq, bfaddr);
ath9k_hw_txstart(ah, sc->beacon.beaconq);
@@ -780,7 +771,7 @@ void ath9k_set_beaconing_status(struct ath_softc *sc, bool status)
ah->imask &= ~ATH9K_INT_SWBA;
ath9k_hw_set_interrupts(ah, ah->imask);
tasklet_kill(&sc->bcon_tasklet);
- ath9k_hw_stoptxdma(ah, sc->beacon.beaconq);
+ ath9k_hw_stop_dma_queue(ah, sc->beacon.beaconq);
}
ath9k_ps_restore(sc);
}
diff --git a/drivers/net/wireless/ath/ath9k/calib.c b/drivers/net/wireless/ath/ath9k/calib.c
index b4a92a4..8649581 100644
--- a/drivers/net/wireless/ath/ath9k/calib.c
+++ b/drivers/net/wireless/ath/ath9k/calib.c
@@ -262,7 +262,7 @@ void ath9k_hw_loadnf(struct ath_hw *ah, struct ath9k_channel *chan)
* since 250us often results in NF load timeout and causes deaf
* condition during stress testing 12/12/2009
*/
- for (j = 0; j < 1000; j++) {
+ for (j = 0; j < 10000; j++) {
if ((REG_READ(ah, AR_PHY_AGC_CONTROL) &
AR_PHY_AGC_CONTROL_NF) == 0)
break;
@@ -278,7 +278,7 @@ void ath9k_hw_loadnf(struct ath_hw *ah, struct ath9k_channel *chan)
* here, the baseband nf cal will just be capped by our present
* noisefloor until the next calibration timer.
*/
- if (j == 1000) {
+ if (j == 10000) {
ath_dbg(common, ATH_DBG_ANY,
"Timeout while waiting for nf to load: AR_PHY_AGC_CONTROL=0x%x\n",
REG_READ(ah, AR_PHY_AGC_CONTROL));
diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c
index 9a34381..338b075 100644
--- a/drivers/net/wireless/ath/ath9k/hw.c
+++ b/drivers/net/wireless/ath/ath9k/hw.c
@@ -701,7 +701,7 @@ static void ath9k_hw_init_pll(struct ath_hw *ah,
AR_CH0_DPLL3_PHASE_SHIFT, DPLL3_PHASE_SHIFT_VAL);
REG_WRITE(ah, AR_RTC_PLL_CONTROL, 0x1142c);
- udelay(100);
+ udelay(1000);
REG_WRITE(ah, AR_RTC_PLL_CONTROL2, 0x886666);
@@ -713,7 +713,7 @@ static void ath9k_hw_init_pll(struct ath_hw *ah,
REG_RMW_FIELD(ah, AR_CH0_BB_DPLL3,
AR_CH0_DPLL3_PHASE_SHIFT, DPLL3_PHASE_SHIFT_VAL);
REG_WRITE(ah, AR_RTC_PLL_CONTROL, 0x142c);
- udelay(110);
+ udelay(1000);
}
pll = ath9k_hw_compute_pll_control(ah, chan);
diff --git a/drivers/net/wireless/ath/ath9k/hw.h b/drivers/net/wireless/ath/ath9k/hw.h
index ef79f4c..6650fd4 100644
--- a/drivers/net/wireless/ath/ath9k/hw.h
+++ b/drivers/net/wireless/ath/ath9k/hw.h
@@ -95,9 +95,9 @@
#define REG_READ_FIELD(_a, _r, _f) \
(((REG_READ(_a, _r) & _f) >> _f##_S))
#define REG_SET_BIT(_a, _r, _f) \
- REG_WRITE(_a, _r, REG_READ(_a, _r) | _f)
+ REG_WRITE(_a, _r, REG_READ(_a, _r) | (_f))
#define REG_CLR_BIT(_a, _r, _f) \
- REG_WRITE(_a, _r, REG_READ(_a, _r) & ~_f)
+ REG_WRITE(_a, _r, REG_READ(_a, _r) & ~(_f))
#define DO_DELAY(x) do { \
if ((++(x) % 64) == 0) \
diff --git a/drivers/net/wireless/ath/ath9k/mac.c b/drivers/net/wireless/ath/ath9k/mac.c
index 5efc869..562257a 100644
--- a/drivers/net/wireless/ath/ath9k/mac.c
+++ b/drivers/net/wireless/ath/ath9k/mac.c
@@ -143,84 +143,59 @@ bool ath9k_hw_updatetxtriglevel(struct ath_hw *ah, bool bIncTrigLevel)
}
EXPORT_SYMBOL(ath9k_hw_updatetxtriglevel);
-bool ath9k_hw_stoptxdma(struct ath_hw *ah, u32 q)
+void ath9k_hw_abort_tx_dma(struct ath_hw *ah)
{
-#define ATH9K_TX_STOP_DMA_TIMEOUT 4000 /* usec */
-#define ATH9K_TIME_QUANTUM 100 /* usec */
- struct ath_common *common = ath9k_hw_common(ah);
- struct ath9k_hw_capabilities *pCap = &ah->caps;
- struct ath9k_tx_queue_info *qi;
- u32 tsfLow, j, wait;
- u32 wait_time = ATH9K_TX_STOP_DMA_TIMEOUT / ATH9K_TIME_QUANTUM;
+ int i, q;
- if (q >= pCap->total_queues) {
- ath_dbg(common, ATH_DBG_QUEUE,
- "Stopping TX DMA, invalid queue: %u\n", q);
- return false;
- }
+ REG_WRITE(ah, AR_Q_TXD, AR_Q_TXD_M);
- qi = &ah->txq[q];
- if (qi->tqi_type == ATH9K_TX_QUEUE_INACTIVE) {
- ath_dbg(common, ATH_DBG_QUEUE,
- "Stopping TX DMA, inactive queue: %u\n", q);
- return false;
- }
+ REG_SET_BIT(ah, AR_PCU_MISC, AR_PCU_FORCE_QUIET_COLL | AR_PCU_CLEAR_VMF);
+ REG_SET_BIT(ah, AR_DIAG_SW, AR_DIAG_FORCE_CH_IDLE_HIGH);
+ REG_SET_BIT(ah, AR_D_GBL_IFS_MISC, AR_D_GBL_IFS_MISC_IGNORE_BACKOFF);
- REG_WRITE(ah, AR_Q_TXD, 1 << q);
+ for (q = 0; q < AR_NUM_QCU; q++) {
+ for (i = 0; i < 1000; i++) {
+ if (i)
+ udelay(5);
- for (wait = wait_time; wait != 0; wait--) {
- if (ath9k_hw_numtxpending(ah, q) == 0)
- break;
- udelay(ATH9K_TIME_QUANTUM);
+ if (!ath9k_hw_numtxpending(ah, q))
+ break;
+ }
}
- if (ath9k_hw_numtxpending(ah, q)) {
- ath_dbg(common, ATH_DBG_QUEUE,
- "%s: Num of pending TX Frames %d on Q %d\n",
- __func__, ath9k_hw_numtxpending(ah, q), q);
-
- for (j = 0; j < 2; j++) {
- tsfLow = REG_READ(ah, AR_TSF_L32);
- REG_WRITE(ah, AR_QUIET2,
- SM(10, AR_QUIET2_QUIET_DUR));
- REG_WRITE(ah, AR_QUIET_PERIOD, 100);
- REG_WRITE(ah, AR_NEXT_QUIET_TIMER, tsfLow >> 10);
- REG_SET_BIT(ah, AR_TIMER_MODE,
- AR_QUIET_TIMER_EN);
-
- if ((REG_READ(ah, AR_TSF_L32) >> 10) == (tsfLow >> 10))
- break;
+ REG_CLR_BIT(ah, AR_PCU_MISC, AR_PCU_FORCE_QUIET_COLL | AR_PCU_CLEAR_VMF);
+ REG_CLR_BIT(ah, AR_DIAG_SW, AR_DIAG_FORCE_CH_IDLE_HIGH);
+ REG_CLR_BIT(ah, AR_D_GBL_IFS_MISC, AR_D_GBL_IFS_MISC_IGNORE_BACKOFF);
- ath_dbg(common, ATH_DBG_QUEUE,
- "TSF has moved while trying to set quiet time TSF: 0x%08x\n",
- tsfLow);
- }
+ REG_WRITE(ah, AR_Q_TXD, 0);
+}
+EXPORT_SYMBOL(ath9k_hw_abort_tx_dma);
- REG_SET_BIT(ah, AR_DIAG_SW, AR_DIAG_FORCE_CH_IDLE_HIGH);
+bool ath9k_hw_stop_dma_queue(struct ath_hw *ah, u32 q)
+{
+#define ATH9K_TX_STOP_DMA_TIMEOUT 1000 /* usec */
+#define ATH9K_TIME_QUANTUM 100 /* usec */
+ int wait_time = ATH9K_TX_STOP_DMA_TIMEOUT / ATH9K_TIME_QUANTUM;
+ int wait;
- udelay(200);
- REG_CLR_BIT(ah, AR_TIMER_MODE, AR_QUIET_TIMER_EN);
+ REG_WRITE(ah, AR_Q_TXD, 1 << q);
- wait = wait_time;
- while (ath9k_hw_numtxpending(ah, q)) {
- if ((--wait) == 0) {
- ath_err(common,
- "Failed to stop TX DMA in 100 msec after killing last frame\n");
- break;
- }
+ for (wait = wait_time; wait != 0; wait--) {
+ if (wait != wait_time)
udelay(ATH9K_TIME_QUANTUM);
- }
- REG_CLR_BIT(ah, AR_DIAG_SW, AR_DIAG_FORCE_CH_IDLE_HIGH);
+ if (ath9k_hw_numtxpending(ah, q) == 0)
+ break;
}
REG_WRITE(ah, AR_Q_TXD, 0);
+
return wait != 0;
#undef ATH9K_TX_STOP_DMA_TIMEOUT
#undef ATH9K_TIME_QUANTUM
}
-EXPORT_SYMBOL(ath9k_hw_stoptxdma);
+EXPORT_SYMBOL(ath9k_hw_stop_dma_queue);
void ath9k_hw_gettxintrtxqs(struct ath_hw *ah, u32 *txqs)
{
diff --git a/drivers/net/wireless/ath/ath9k/mac.h b/drivers/net/wireless/ath/ath9k/mac.h
index 04d58ae..b2b2ff8 100644
--- a/drivers/net/wireless/ath/ath9k/mac.h
+++ b/drivers/net/wireless/ath/ath9k/mac.h
@@ -676,7 +676,8 @@ void ath9k_hw_txstart(struct ath_hw *ah, u32 q);
void ath9k_hw_cleartxdesc(struct ath_hw *ah, void *ds);
u32 ath9k_hw_numtxpending(struct ath_hw *ah, u32 q);
bool ath9k_hw_updatetxtriglevel(struct ath_hw *ah, bool bIncTrigLevel);
-bool ath9k_hw_stoptxdma(struct ath_hw *ah, u32 q);
+bool ath9k_hw_stop_dma_queue(struct ath_hw *ah, u32 q);
+void ath9k_hw_abort_tx_dma(struct ath_hw *ah);
void ath9k_hw_gettxintrtxqs(struct ath_hw *ah, u32 *txqs);
bool ath9k_hw_set_txq_props(struct ath_hw *ah, int q,
const struct ath9k_tx_queue_info *qinfo);
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index 2e228aa..115f162 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -2128,56 +2128,42 @@ static void ath9k_set_coverage_class(struct ieee80211_hw *hw, u8 coverage_class)
static void ath9k_flush(struct ieee80211_hw *hw, bool drop)
{
-#define ATH_FLUSH_TIMEOUT 60 /* ms */
struct ath_softc *sc = hw->priv;
- struct ath_txq *txq = NULL;
- struct ath_hw *ah = sc->sc_ah;
- struct ath_common *common = ath9k_hw_common(ah);
- int i, j, npend = 0;
+ int timeout = 200; /* ms */
+ int i, j;
+ ath9k_ps_wakeup(sc);
mutex_lock(&sc->mutex);
cancel_delayed_work_sync(&sc->tx_complete_work);
- for (i = 0; i < ATH9K_NUM_TX_QUEUES; i++) {
- if (!ATH_TXQ_SETUP(sc, i))
- continue;
- txq = &sc->tx.txq[i];
+ if (drop)
+ timeout = 1;
- if (!drop) {
- for (j = 0; j < ATH_FLUSH_TIMEOUT; j++) {
- if (!ath9k_has_pending_frames(sc, txq))
- break;
- usleep_range(1000, 2000);
- }
- }
+ for (j = 0; j < timeout; j++) {
+ int npend = 0;
+
+ if (j)
+ usleep_range(1000, 2000);
- if (drop || ath9k_has_pending_frames(sc, txq)) {
- ath_dbg(common, ATH_DBG_QUEUE, "Drop frames from hw queue:%d\n",
- txq->axq_qnum);
- spin_lock_bh(&txq->axq_lock);
- txq->txq_flush_inprogress = true;
- spin_unlock_bh(&txq->axq_lock);
-
- ath9k_ps_wakeup(sc);
- ath9k_hw_stoptxdma(ah, txq->axq_qnum);
- npend = ath9k_hw_numtxpending(ah, txq->axq_qnum);
- ath9k_ps_restore(sc);
- if (npend)
- break;
-
- ath_draintxq(sc, txq, false);
- txq->txq_flush_inprogress = false;
+ for (i = 0; i < ATH9K_NUM_TX_QUEUES; i++) {
+ if (!ATH_TXQ_SETUP(sc, i))
+ continue;
+
+ npend += ath9k_has_pending_frames(sc, &sc->tx.txq[i]);
}
+
+ if (!npend)
+ goto out;
}
- if (npend) {
+ if (!ath_drain_all_txq(sc, false))
ath_reset(sc, false);
- txq->txq_flush_inprogress = false;
- }
+out:
ieee80211_queue_delayed_work(hw, &sc->tx_complete_work, 0);
mutex_unlock(&sc->mutex);
+ ath9k_ps_restore(sc);
}
struct ieee80211_ops ath9k_ops = {
diff --git a/drivers/net/wireless/ath/ath9k/recv.c b/drivers/net/wireless/ath/ath9k/recv.c
index cb559e3..a9c3f46 100644
--- a/drivers/net/wireless/ath/ath9k/recv.c
+++ b/drivers/net/wireless/ath/ath9k/recv.c
@@ -413,9 +413,7 @@ u32 ath_calcrxfilter(struct ath_softc *sc)
* mode interface or when in monitor mode. AP mode does not need this
* since it receives all in-BSS frames anyway.
*/
- if (((sc->sc_ah->opmode != NL80211_IFTYPE_AP) &&
- (sc->rx.rxfilter & FIF_PROMISC_IN_BSS)) ||
- (sc->sc_ah->is_monitoring))
+ if (sc->sc_ah->is_monitoring)
rfilt |= ATH9K_RX_FILTER_PROM;
if (sc->rx.rxfilter & FIF_CONTROL)
diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c
index e16136d..ef22096 100644
--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -166,7 +166,7 @@ static void ath_tx_flush_tid(struct ath_softc *sc, struct ath_atx_tid *tid)
fi = get_frame_info(bf->bf_mpdu);
if (fi->retries) {
ath_tx_update_baw(sc, tid, fi->seqno);
- ath_tx_complete_buf(sc, bf, txq, &bf_head, &ts, 0, 0);
+ ath_tx_complete_buf(sc, bf, txq, &bf_head, &ts, 0, 1);
} else {
ath_tx_send_normal(sc, txq, NULL, &bf_head);
}
@@ -1194,16 +1194,14 @@ bool ath_drain_all_txq(struct ath_softc *sc, bool retry_tx)
if (sc->sc_flags & SC_OP_INVALID)
return true;
- /* Stop beacon queue */
- ath9k_hw_stoptxdma(sc->sc_ah, sc->beacon.beaconq);
+ ath9k_hw_abort_tx_dma(ah);
- /* Stop data queues */
+ /* Check if any queue remains active */
for (i = 0; i < ATH9K_NUM_TX_QUEUES; i++) {
- if (ATH_TXQ_SETUP(sc, i)) {
- txq = &sc->tx.txq[i];
- ath9k_hw_stoptxdma(ah, txq->axq_qnum);
- npend += ath9k_hw_numtxpending(ah, txq->axq_qnum);
- }
+ if (!ATH_TXQ_SETUP(sc, i))
+ continue;
+
+ npend += ath9k_hw_numtxpending(ah, sc->tx.txq[i].axq_qnum);
}
if (npend)
@@ -2014,8 +2012,7 @@ static void ath_tx_processq(struct ath_softc *sc, struct ath_txq *txq)
spin_lock_bh(&txq->axq_lock);
if (list_empty(&txq->axq_q)) {
txq->axq_link = NULL;
- if (sc->sc_flags & SC_OP_TXAGGR &&
- !txq->txq_flush_inprogress)
+ if (sc->sc_flags & SC_OP_TXAGGR)
ath_txq_schedule(sc, txq);
spin_unlock_bh(&txq->axq_lock);
break;
@@ -2096,7 +2093,7 @@ static void ath_tx_processq(struct ath_softc *sc, struct ath_txq *txq)
spin_lock_bh(&txq->axq_lock);
- if (sc->sc_flags & SC_OP_TXAGGR && !txq->txq_flush_inprogress)
+ if (sc->sc_flags & SC_OP_TXAGGR)
ath_txq_schedule(sc, txq);
spin_unlock_bh(&txq->axq_lock);
}
@@ -2267,18 +2264,17 @@ void ath_tx_edma_tasklet(struct ath_softc *sc)
spin_lock_bh(&txq->axq_lock);
- if (!txq->txq_flush_inprogress) {
- if (!list_empty(&txq->txq_fifo_pending)) {
- INIT_LIST_HEAD(&bf_head);
- bf = list_first_entry(&txq->txq_fifo_pending,
- struct ath_buf, list);
- list_cut_position(&bf_head,
- &txq->txq_fifo_pending,
- &bf->bf_lastbf->list);
- ath_tx_txqaddbuf(sc, txq, &bf_head);
- } else if (sc->sc_flags & SC_OP_TXAGGR)
- ath_txq_schedule(sc, txq);
- }
+ if (!list_empty(&txq->txq_fifo_pending)) {
+ INIT_LIST_HEAD(&bf_head);
+ bf = list_first_entry(&txq->txq_fifo_pending,
+ struct ath_buf, list);
+ list_cut_position(&bf_head,
+ &txq->txq_fifo_pending,
+ &bf->bf_lastbf->list);
+ ath_tx_txqaddbuf(sc, txq, &bf_head);
+ } else if (sc->sc_flags & SC_OP_TXAGGR)
+ ath_txq_schedule(sc, txq);
+
spin_unlock_bh(&txq->axq_lock);
}
}
diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-lib.c b/drivers/net/wireless/iwlwifi/iwl-agn-lib.c
index 25fccf9..2003c1d 100644
--- a/drivers/net/wireless/iwlwifi/iwl-agn-lib.c
+++ b/drivers/net/wireless/iwlwifi/iwl-agn-lib.c
@@ -1115,6 +1115,18 @@ static int iwl_get_channels_for_scan(struct iwl_priv *priv,
return added;
}
+static int iwl_fill_offch_tx(struct iwl_priv *priv, void *data, size_t maxlen)
+{
+ struct sk_buff *skb = priv->_agn.offchan_tx_skb;
+
+ if (skb->len < maxlen)
+ maxlen = skb->len;
+
+ memcpy(data, skb->data, maxlen);
+
+ return maxlen;
+}
+
int iwlagn_request_scan(struct iwl_priv *priv, struct ieee80211_vif *vif)
{
struct iwl_host_cmd cmd = {
@@ -1157,17 +1169,25 @@ int iwlagn_request_scan(struct iwl_priv *priv, struct ieee80211_vif *vif)
scan->quiet_plcp_th = IWL_PLCP_QUIET_THRESH;
scan->quiet_time = IWL_ACTIVE_QUIET_TIME;
- if (iwl_is_any_associated(priv)) {
+ if (priv->scan_type != IWL_SCAN_OFFCH_TX &&
+ iwl_is_any_associated(priv)) {
u16 interval = 0;
u32 extra;
u32 suspend_time = 100;
u32 scan_suspend_time = 100;
IWL_DEBUG_INFO(priv, "Scanning while associated...\n");
- if (priv->is_internal_short_scan)
+ switch (priv->scan_type) {
+ case IWL_SCAN_OFFCH_TX:
+ WARN_ON(1);
+ break;
+ case IWL_SCAN_RADIO_RESET:
interval = 0;
- else
+ break;
+ case IWL_SCAN_NORMAL:
interval = vif->bss_conf.beacon_int;
+ break;
+ }
scan->suspend_time = 0;
scan->max_out_time = cpu_to_le32(200 * 1024);
@@ -1180,29 +1200,41 @@ int iwlagn_request_scan(struct iwl_priv *priv, struct ieee80211_vif *vif)
scan->suspend_time = cpu_to_le32(scan_suspend_time);
IWL_DEBUG_SCAN(priv, "suspend_time 0x%X beacon interval %d\n",
scan_suspend_time, interval);
+ } else if (priv->scan_type == IWL_SCAN_OFFCH_TX) {
+ scan->suspend_time = 0;
+ scan->max_out_time =
+ cpu_to_le32(1024 * priv->_agn.offchan_tx_timeout);
}
- if (priv->is_internal_short_scan) {
+ switch (priv->scan_type) {
+ case IWL_SCAN_RADIO_RESET:
IWL_DEBUG_SCAN(priv, "Start internal passive scan.\n");
- } else if (priv->scan_request->n_ssids) {
- int i, p = 0;
- IWL_DEBUG_SCAN(priv, "Kicking off active scan\n");
- for (i = 0; i < priv->scan_request->n_ssids; i++) {
- /* always does wildcard anyway */
- if (!priv->scan_request->ssids[i].ssid_len)
- continue;
- scan->direct_scan[p].id = WLAN_EID_SSID;
- scan->direct_scan[p].len =
- priv->scan_request->ssids[i].ssid_len;
- memcpy(scan->direct_scan[p].ssid,
- priv->scan_request->ssids[i].ssid,
- priv->scan_request->ssids[i].ssid_len);
- n_probes++;
- p++;
- }
- is_active = true;
- } else
- IWL_DEBUG_SCAN(priv, "Start passive scan.\n");
+ break;
+ case IWL_SCAN_NORMAL:
+ if (priv->scan_request->n_ssids) {
+ int i, p = 0;
+ IWL_DEBUG_SCAN(priv, "Kicking off active scan\n");
+ for (i = 0; i < priv->scan_request->n_ssids; i++) {
+ /* always does wildcard anyway */
+ if (!priv->scan_request->ssids[i].ssid_len)
+ continue;
+ scan->direct_scan[p].id = WLAN_EID_SSID;
+ scan->direct_scan[p].len =
+ priv->scan_request->ssids[i].ssid_len;
+ memcpy(scan->direct_scan[p].ssid,
+ priv->scan_request->ssids[i].ssid,
+ priv->scan_request->ssids[i].ssid_len);
+ n_probes++;
+ p++;
+ }
+ is_active = true;
+ } else
+ IWL_DEBUG_SCAN(priv, "Start passive scan.\n");
+ break;
+ case IWL_SCAN_OFFCH_TX:
+ IWL_DEBUG_SCAN(priv, "Start offchannel TX scan.\n");
+ break;
+ }
scan->tx_cmd.tx_flags = TX_CMD_FLG_SEQ_CTL_MSK;
scan->tx_cmd.sta_id = ctx->bcast_sta_id;
@@ -1300,38 +1332,77 @@ int iwlagn_request_scan(struct iwl_priv *priv, struct ieee80211_vif *vif)
rx_chain |= rx_ant << RXON_RX_CHAIN_FORCE_SEL_POS;
rx_chain |= 0x1 << RXON_RX_CHAIN_DRIVER_FORCE_POS;
scan->rx_chain = cpu_to_le16(rx_chain);
- if (!priv->is_internal_short_scan) {
+ switch (priv->scan_type) {
+ case IWL_SCAN_NORMAL:
cmd_len = iwl_fill_probe_req(priv,
(struct ieee80211_mgmt *)scan->data,
vif->addr,
priv->scan_request->ie,
priv->scan_request->ie_len,
IWL_MAX_SCAN_SIZE - sizeof(*scan));
- } else {
+ break;
+ case IWL_SCAN_RADIO_RESET:
/* use bcast addr, will not be transmitted but must be valid */
cmd_len = iwl_fill_probe_req(priv,
(struct ieee80211_mgmt *)scan->data,
iwl_bcast_addr, NULL, 0,
IWL_MAX_SCAN_SIZE - sizeof(*scan));
-
+ break;
+ case IWL_SCAN_OFFCH_TX:
+ cmd_len = iwl_fill_offch_tx(priv, scan->data,
+ IWL_MAX_SCAN_SIZE
+ - sizeof(*scan)
+ - sizeof(struct iwl_scan_channel));
+ scan->scan_flags |= IWL_SCAN_FLAGS_ACTION_FRAME_TX;
+ break;
+ default:
+ BUG();
}
scan->tx_cmd.len = cpu_to_le16(cmd_len);
scan->filter_flags |= (RXON_FILTER_ACCEPT_GRP_MSK |
RXON_FILTER_BCON_AWARE_MSK);
- if (priv->is_internal_short_scan) {
+ switch (priv->scan_type) {
+ case IWL_SCAN_RADIO_RESET:
scan->channel_count =
iwl_get_single_channel_for_scan(priv, vif, band,
- (void *)&scan->data[le16_to_cpu(
- scan->tx_cmd.len)]);
- } else {
+ (void *)&scan->data[cmd_len]);
+ break;
+ case IWL_SCAN_NORMAL:
scan->channel_count =
iwl_get_channels_for_scan(priv, vif, band,
is_active, n_probes,
- (void *)&scan->data[le16_to_cpu(
- scan->tx_cmd.len)]);
+ (void *)&scan->data[cmd_len]);
+ break;
+ case IWL_SCAN_OFFCH_TX: {
+ struct iwl_scan_channel *scan_ch;
+
+ scan->channel_count = 1;
+
+ scan_ch = (void *)&scan->data[cmd_len];
+ scan_ch->type = SCAN_CHANNEL_TYPE_ACTIVE;
+ scan_ch->channel =
+ cpu_to_le16(priv->_agn.offchan_tx_chan->hw_value);
+ scan_ch->active_dwell =
+ cpu_to_le16(priv->_agn.offchan_tx_timeout);
+ scan_ch->passive_dwell = 0;
+
+ /* Set txpower levels to defaults */
+ scan_ch->dsp_atten = 110;
+
+ /* NOTE: if we were doing 6Mb OFDM for scans we'd use
+ * power level:
+ * scan_ch->tx_gain = ((1 << 5) | (2 << 3)) | 3;
+ */
+ if (priv->_agn.offchan_tx_chan->band == IEEE80211_BAND_5GHZ)
+ scan_ch->tx_gain = ((1 << 5) | (3 << 3)) | 3;
+ else
+ scan_ch->tx_gain = ((1 << 5) | (5 << 3));
+ }
+ break;
}
+
if (scan->channel_count == 0) {
IWL_DEBUG_SCAN(priv, "channel count %d\n", scan->channel_count);
return -EIO;
diff --git a/drivers/net/wireless/iwlwifi/iwl-agn.c b/drivers/net/wireless/iwlwifi/iwl-agn.c
index e0cd3e2..581dc9f 100644
--- a/drivers/net/wireless/iwlwifi/iwl-agn.c
+++ b/drivers/net/wireless/iwlwifi/iwl-agn.c
@@ -2937,6 +2937,91 @@ static void iwl_bg_rx_replenish(struct work_struct *data)
mutex_unlock(&priv->mutex);
}
+static int iwl_mac_offchannel_tx(struct ieee80211_hw *hw, struct sk_buff *skb,
+ struct ieee80211_channel *chan,
+ enum nl80211_channel_type channel_type,
+ unsigned int wait)
+{
+ struct iwl_priv *priv = hw->priv;
+ int ret;
+
+ /* Not supported if we don't have PAN */
+ if (!(priv->valid_contexts & BIT(IWL_RXON_CTX_PAN))) {
+ ret = -EOPNOTSUPP;
+ goto free;
+ }
+
+ /* Not supported on pre-P2P firmware */
+ if (!(priv->contexts[IWL_RXON_CTX_PAN].interface_modes &
+ BIT(NL80211_IFTYPE_P2P_CLIENT))) {
+ ret = -EOPNOTSUPP;
+ goto free;
+ }
+
+ mutex_lock(&priv->mutex);
+
+ if (!priv->contexts[IWL_RXON_CTX_PAN].is_active) {
+ /*
+ * If the PAN context is free, use the normal
+ * way of doing remain-on-channel offload + TX.
+ */
+ ret = 1;
+ goto out;
+ }
+
+ /* TODO: queue up if scanning? */
+ if (test_bit(STATUS_SCANNING, &priv->status) ||
+ priv->_agn.offchan_tx_skb) {
+ ret = -EBUSY;
+ goto out;
+ }
+
+ /*
+ * max_scan_ie_len doesn't include the blank SSID or the header,
+ * so need to add that again here.
+ */
+ if (skb->len > hw->wiphy->max_scan_ie_len + 24 + 2) {
+ ret = -ENOBUFS;
+ goto out;
+ }
+
+ priv->_agn.offchan_tx_skb = skb;
+ priv->_agn.offchan_tx_timeout = wait;
+ priv->_agn.offchan_tx_chan = chan;
+
+ ret = iwl_scan_initiate(priv, priv->contexts[IWL_RXON_CTX_PAN].vif,
+ IWL_SCAN_OFFCH_TX, chan->band);
+ if (ret)
+ priv->_agn.offchan_tx_skb = NULL;
+ out:
+ mutex_unlock(&priv->mutex);
+ free:
+ if (ret < 0)
+ kfree_skb(skb);
+
+ return ret;
+}
+
+static int iwl_mac_offchannel_tx_cancel_wait(struct ieee80211_hw *hw)
+{
+ struct iwl_priv *priv = hw->priv;
+ int ret;
+
+ mutex_lock(&priv->mutex);
+
+ if (!priv->_agn.offchan_tx_skb)
+ return -EINVAL;
+
+ priv->_agn.offchan_tx_skb = NULL;
+
+ ret = iwl_scan_cancel_timeout(priv, 200);
+ if (ret)
+ ret = -EIO;
+ mutex_unlock(&priv->mutex);
+
+ return ret;
+}
+
/*****************************************************************************
*
* mac80211 entry point functions
@@ -3815,6 +3900,8 @@ struct ieee80211_ops iwlagn_hw_ops = {
.tx_last_beacon = iwl_mac_tx_last_beacon,
.remain_on_channel = iwl_mac_remain_on_channel,
.cancel_remain_on_channel = iwl_mac_cancel_remain_on_channel,
+ .offchannel_tx = iwl_mac_offchannel_tx,
+ .offchannel_tx_cancel_wait = iwl_mac_offchannel_tx_cancel_wait,
};
static void iwl_hw_detect(struct iwl_priv *priv)
diff --git a/drivers/net/wireless/iwlwifi/iwl-commands.h b/drivers/net/wireless/iwlwifi/iwl-commands.h
index 03cfb74..ca42ffa 100644
--- a/drivers/net/wireless/iwlwifi/iwl-commands.h
+++ b/drivers/net/wireless/iwlwifi/iwl-commands.h
@@ -2964,9 +2964,15 @@ struct iwl3945_scan_cmd {
u8 data[0];
} __packed;
+enum iwl_scan_flags {
+ /* BIT(0) currently unused */
+ IWL_SCAN_FLAGS_ACTION_FRAME_TX = BIT(1),
+ /* bits 2-7 reserved */
+};
+
struct iwl_scan_cmd {
__le16 len;
- u8 reserved0;
+ u8 scan_flags; /* scan flags: see enum iwl_scan_flags */
u8 channel_count; /* # channels in channel list */
__le16 quiet_time; /* dwell only this # millisecs on quiet channel
* (only for active scan) */
diff --git a/drivers/net/wireless/iwlwifi/iwl-core.h b/drivers/net/wireless/iwlwifi/iwl-core.h
index af47750..b316d83 100644
--- a/drivers/net/wireless/iwlwifi/iwl-core.h
+++ b/drivers/net/wireless/iwlwifi/iwl-core.h
@@ -63,6 +63,8 @@
#ifndef __iwl_core_h__
#define __iwl_core_h__
+#include "iwl-dev.h"
+
/************************
* forward declarations *
************************/
@@ -551,6 +553,10 @@ u16 iwl_get_passive_dwell_time(struct iwl_priv *priv,
struct ieee80211_vif *vif);
void iwl_setup_scan_deferred_work(struct iwl_priv *priv);
void iwl_cancel_scan_deferred_work(struct iwl_priv *priv);
+int __must_check iwl_scan_initiate(struct iwl_priv *priv,
+ struct ieee80211_vif *vif,
+ enum iwl_scan_type scan_type,
+ enum ieee80211_band band);
/* For faster active scanning, scan will move to the next channel if fewer than
* PLCP_QUIET_THRESH packets are heard on this channel within
diff --git a/drivers/net/wireless/iwlwifi/iwl-dev.h b/drivers/net/wireless/iwlwifi/iwl-dev.h
index 6a41deb..68b953f 100644
--- a/drivers/net/wireless/iwlwifi/iwl-dev.h
+++ b/drivers/net/wireless/iwlwifi/iwl-dev.h
@@ -1230,6 +1230,12 @@ struct iwl_rxon_context {
} ht;
};
+enum iwl_scan_type {
+ IWL_SCAN_NORMAL,
+ IWL_SCAN_RADIO_RESET,
+ IWL_SCAN_OFFCH_TX,
+};
+
struct iwl_priv {
/* ieee device used by generic ieee processing code */
@@ -1290,7 +1296,7 @@ struct iwl_priv {
enum ieee80211_band scan_band;
struct cfg80211_scan_request *scan_request;
struct ieee80211_vif *scan_vif;
- bool is_internal_short_scan;
+ enum iwl_scan_type scan_type;
u8 scan_tx_ant[IEEE80211_NUM_BANDS];
u8 mgmt_tx_ant;
@@ -1504,6 +1510,10 @@ struct iwl_priv {
struct delayed_work hw_roc_work;
enum nl80211_channel_type hw_roc_chantype;
int hw_roc_duration;
+
+ struct sk_buff *offchan_tx_skb;
+ int offchan_tx_timeout;
+ struct ieee80211_channel *offchan_tx_chan;
} _agn;
#endif
};
diff --git a/drivers/net/wireless/iwlwifi/iwl-scan.c b/drivers/net/wireless/iwlwifi/iwl-scan.c
index faa6d34..3a4d9e6 100644
--- a/drivers/net/wireless/iwlwifi/iwl-scan.c
+++ b/drivers/net/wireless/iwlwifi/iwl-scan.c
@@ -101,7 +101,7 @@ static void iwl_complete_scan(struct iwl_priv *priv, bool aborted)
ieee80211_scan_completed(priv->hw, aborted);
}
- priv->is_internal_short_scan = false;
+ priv->scan_type = IWL_SCAN_NORMAL;
priv->scan_vif = NULL;
priv->scan_request = NULL;
}
@@ -339,10 +339,10 @@ void iwl_init_scan_params(struct iwl_priv *priv)
priv->scan_tx_ant[IEEE80211_BAND_2GHZ] = ant_idx;
}
-static int __must_check iwl_scan_initiate(struct iwl_priv *priv,
- struct ieee80211_vif *vif,
- bool internal,
- enum ieee80211_band band)
+int __must_check iwl_scan_initiate(struct iwl_priv *priv,
+ struct ieee80211_vif *vif,
+ enum iwl_scan_type scan_type,
+ enum ieee80211_band band)
{
int ret;
@@ -370,17 +370,19 @@ static int __must_check iwl_scan_initiate(struct iwl_priv *priv,
}
IWL_DEBUG_SCAN(priv, "Starting %sscan...\n",
- internal ? "internal short " : "");
+ scan_type == IWL_SCAN_NORMAL ? "" :
+ scan_type == IWL_SCAN_OFFCH_TX ? "offchan TX " :
+ "internal short ");
set_bit(STATUS_SCANNING, &priv->status);
- priv->is_internal_short_scan = internal;
+ priv->scan_type = scan_type;
priv->scan_start = jiffies;
priv->scan_band = band;
ret = priv->cfg->ops->utils->request_scan(priv, vif);
if (ret) {
clear_bit(STATUS_SCANNING, &priv->status);
- priv->is_internal_short_scan = false;
+ priv->scan_type = IWL_SCAN_NORMAL;
return ret;
}
@@ -405,7 +407,7 @@ int iwl_mac_hw_scan(struct ieee80211_hw *hw,
mutex_lock(&priv->mutex);
if (test_bit(STATUS_SCANNING, &priv->status) &&
- !priv->is_internal_short_scan) {
+ priv->scan_type != IWL_SCAN_NORMAL) {
IWL_DEBUG_SCAN(priv, "Scan already in progress.\n");
ret = -EAGAIN;
goto out_unlock;
@@ -419,11 +421,11 @@ int iwl_mac_hw_scan(struct ieee80211_hw *hw,
* If an internal scan is in progress, just set
* up the scan_request as per above.
*/
- if (priv->is_internal_short_scan) {
+ if (priv->scan_type != IWL_SCAN_NORMAL) {
IWL_DEBUG_SCAN(priv, "SCAN request during internal scan\n");
ret = 0;
} else
- ret = iwl_scan_initiate(priv, vif, false,
+ ret = iwl_scan_initiate(priv, vif, IWL_SCAN_NORMAL,
req->channels[0]->band);
IWL_DEBUG_MAC80211(priv, "leave\n");
@@ -452,7 +454,7 @@ static void iwl_bg_start_internal_scan(struct work_struct *work)
mutex_lock(&priv->mutex);
- if (priv->is_internal_short_scan == true) {
+ if (priv->scan_type == IWL_SCAN_RADIO_RESET) {
IWL_DEBUG_SCAN(priv, "Internal scan already in progress\n");
goto unlock;
}
@@ -462,7 +464,7 @@ static void iwl_bg_start_internal_scan(struct work_struct *work)
goto unlock;
}
- if (iwl_scan_initiate(priv, NULL, true, priv->band))
+ if (iwl_scan_initiate(priv, NULL, IWL_SCAN_RADIO_RESET, priv->band))
IWL_DEBUG_SCAN(priv, "failed to start internal short scan\n");
unlock:
mutex_unlock(&priv->mutex);
@@ -549,8 +551,7 @@ static void iwl_bg_scan_completed(struct work_struct *work)
container_of(work, struct iwl_priv, scan_completed);
bool aborted;
- IWL_DEBUG_SCAN(priv, "Completed %sscan.\n",
- priv->is_internal_short_scan ? "internal short " : "");
+ IWL_DEBUG_SCAN(priv, "Completed scan.\n");
cancel_delayed_work(&priv->scan_check);
@@ -565,7 +566,13 @@ static void iwl_bg_scan_completed(struct work_struct *work)
goto out_settings;
}
- if (priv->is_internal_short_scan && !aborted) {
+ if (priv->scan_type == IWL_SCAN_OFFCH_TX && priv->_agn.offchan_tx_skb) {
+ ieee80211_tx_status_irqsafe(priv->hw,
+ priv->_agn.offchan_tx_skb);
+ priv->_agn.offchan_tx_skb = NULL;
+ }
+
+ if (priv->scan_type != IWL_SCAN_NORMAL && !aborted) {
int err;
/* Check if mac80211 requested scan during our internal scan */
@@ -573,7 +580,7 @@ static void iwl_bg_scan_completed(struct work_struct *work)
goto out_complete;
/* If so request a new scan */
- err = iwl_scan_initiate(priv, priv->scan_vif, false,
+ err = iwl_scan_initiate(priv, priv->scan_vif, IWL_SCAN_NORMAL,
priv->scan_request->channels[0]->band);
if (err) {
IWL_DEBUG_SCAN(priv,
diff --git a/drivers/net/wireless/libertas/mesh.c b/drivers/net/wireless/libertas/mesh.c
index acf3bf6..9d097b9 100644
--- a/drivers/net/wireless/libertas/mesh.c
+++ b/drivers/net/wireless/libertas/mesh.c
@@ -918,7 +918,6 @@ static ssize_t mesh_id_get(struct device *dev, struct device_attribute *attr,
char *buf)
{
struct mrvl_mesh_defaults defs;
- int maxlen;
int ret;
ret = mesh_get_default_parameters(dev, &defs);
@@ -931,13 +930,11 @@ static ssize_t mesh_id_get(struct device *dev, struct device_attribute *attr,
defs.meshie.val.mesh_id_len = IEEE80211_MAX_SSID_LEN;
}
- /* SSID not null terminated: reserve room for \0 + \n */
- maxlen = defs.meshie.val.mesh_id_len + 2;
- maxlen = (PAGE_SIZE > maxlen) ? maxlen : PAGE_SIZE;
+ memcpy(buf, defs.meshie.val.mesh_id, defs.meshie.val.mesh_id_len);
+ buf[defs.meshie.val.mesh_id_len] = '\n';
+ buf[defs.meshie.val.mesh_id_len + 1] = '\0';
- defs.meshie.val.mesh_id[defs.meshie.val.mesh_id_len] = '\0';
-
- return snprintf(buf, maxlen, "%s\n", defs.meshie.val.mesh_id);
+ return defs.meshie.val.mesh_id_len + 1;
}
/**
diff --git a/drivers/net/wireless/wl1251/ps.c b/drivers/net/wireless/wl1251/ps.c
index 9ba23ed..9cc5147 100644
--- a/drivers/net/wireless/wl1251/ps.c
+++ b/drivers/net/wireless/wl1251/ps.c
@@ -58,7 +58,6 @@ void wl1251_ps_elp_sleep(struct wl1251 *wl)
unsigned long delay;
if (wl->psm) {
- cancel_delayed_work(&wl->elp_work);
delay = msecs_to_jiffies(ELP_ENTRY_DELAY);
ieee80211_queue_delayed_work(wl->hw, &wl->elp_work, delay);
}
@@ -69,6 +68,9 @@ int wl1251_ps_elp_wakeup(struct wl1251 *wl)
unsigned long timeout, start;
u32 elp_reg;
+ if (delayed_work_pending(&wl->elp_work))
+ cancel_delayed_work(&wl->elp_work);
+
if (!wl->elp)
return 0;
@@ -102,38 +104,6 @@ int wl1251_ps_elp_wakeup(struct wl1251 *wl)
return 0;
}
-static int wl1251_ps_set_elp(struct wl1251 *wl, bool enable)
-{
- int ret;
-
- if (enable) {
- wl1251_debug(DEBUG_PSM, "sleep auth psm/elp");
-
- ret = wl1251_acx_sleep_auth(wl, WL1251_PSM_ELP);
- if (ret < 0)
- return ret;
-
- wl1251_ps_elp_sleep(wl);
- } else {
- wl1251_debug(DEBUG_PSM, "sleep auth cam");
-
- /*
- * When the target is in ELP, we can only
- * access the ELP control register. Thus,
- * we have to wake the target up before
- * changing the power authorization.
- */
-
- wl1251_ps_elp_wakeup(wl);
-
- ret = wl1251_acx_sleep_auth(wl, WL1251_PSM_CAM);
- if (ret < 0)
- return ret;
- }
-
- return 0;
-}
-
int wl1251_ps_set_mode(struct wl1251 *wl, enum wl1251_cmd_ps_mode mode)
{
int ret;
@@ -162,7 +132,7 @@ int wl1251_ps_set_mode(struct wl1251 *wl, enum wl1251_cmd_ps_mode mode)
if (ret < 0)
return ret;
- ret = wl1251_ps_set_elp(wl, true);
+ ret = wl1251_acx_sleep_auth(wl, WL1251_PSM_ELP);
if (ret < 0)
return ret;
@@ -171,7 +141,8 @@ int wl1251_ps_set_mode(struct wl1251 *wl, enum wl1251_cmd_ps_mode mode)
case STATION_ACTIVE_MODE:
default:
wl1251_debug(DEBUG_PSM, "leaving psm");
- ret = wl1251_ps_set_elp(wl, false);
+
+ ret = wl1251_acx_sleep_auth(wl, WL1251_PSM_CAM);
if (ret < 0)
return ret;
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 1ac5786..60f7876 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1197,6 +1197,10 @@ struct cfg80211_pmksa {
* (also see nl80211.h @NL80211_ATTR_WIPHY_ANTENNA_TX).
*
* @get_antenna: Get current antenna configuration from device (tx_ant, rx_ant).
+ *
+ * @set_ringparam: Set tx and rx ring sizes.
+ *
+ * @get_ringparam: Get tx and rx ring current and maximum sizes.
*/
struct cfg80211_ops {
int (*suspend)(struct wiphy *wiphy);
@@ -1364,6 +1368,10 @@ struct cfg80211_ops {
int (*set_antenna)(struct wiphy *wiphy, u32 tx_ant, u32 rx_ant);
int (*get_antenna)(struct wiphy *wiphy, u32 *tx_ant, u32 *rx_ant);
+
+ int (*set_ringparam)(struct wiphy *wiphy, u32 tx, u32 rx);
+ void (*get_ringparam)(struct wiphy *wiphy,
+ u32 *tx, u32 *tx_max, u32 *rx, u32 *rx_max);
};
/*
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 2b072fa..8650e7b 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -1804,6 +1804,10 @@ enum ieee80211_ampdu_mlme_action {
* return value is 1, then the @remain_on_channel will be used with a
* regular transmission (if supported.)
* @offchannel_tx_cancel_wait: cancel wait associated with offchannel TX
+ *
+ * @set_ringparam: Set tx and rx ring sizes.
+ *
+ * @get_ringparam: Get tx and rx ring current and maximum sizes.
*/
struct ieee80211_ops {
void (*tx)(struct ieee80211_hw *hw, struct sk_buff *skb);
@@ -1888,6 +1892,9 @@ struct ieee80211_ops {
enum nl80211_channel_type channel_type,
unsigned int wait);
int (*offchannel_tx_cancel_wait)(struct ieee80211_hw *hw);
+ int (*set_ringparam)(struct ieee80211_hw *hw, u32 tx, u32 rx);
+ void (*get_ringparam)(struct ieee80211_hw *hw,
+ u32 *tx, u32 *tx_max, u32 *rx, u32 *rx_max);
};
/**
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 7b701dc..3342135 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -834,6 +834,10 @@ static int ieee80211_change_station(struct wiphy *wiphy,
rcu_read_unlock();
+ if (sdata->vif.type == NL80211_IFTYPE_STATION &&
+ params->sta_flags_mask & BIT(NL80211_STA_FLAG_AUTHORIZED))
+ ieee80211_recalc_ps(local, -1);
+
return 0;
}
@@ -2008,6 +2012,21 @@ static int ieee80211_get_antenna(struct wiphy *wiphy, u32 *tx_ant, u32 *rx_ant)
return drv_get_antenna(local, tx_ant, rx_ant);
}
+static int ieee80211_set_ringparam(struct wiphy *wiphy, u32 tx, u32 rx)
+{
+ struct ieee80211_local *local = wiphy_priv(wiphy);
+
+ return drv_set_ringparam(local, tx, rx);
+}
+
+static void ieee80211_get_ringparam(struct wiphy *wiphy,
+ u32 *tx, u32 *tx_max, u32 *rx, u32 *rx_max)
+{
+ struct ieee80211_local *local = wiphy_priv(wiphy);
+
+ drv_get_ringparam(local, tx, tx_max, rx, rx_max);
+}
+
struct cfg80211_ops mac80211_config_ops = {
.add_virtual_intf = ieee80211_add_iface,
.del_virtual_intf = ieee80211_del_iface,
@@ -2065,4 +2084,6 @@ struct cfg80211_ops mac80211_config_ops = {
.mgmt_frame_register = ieee80211_mgmt_frame_register,
.set_antenna = ieee80211_set_antenna,
.get_antenna = ieee80211_get_antenna,
+ .set_ringparam = ieee80211_set_ringparam,
+ .get_ringparam = ieee80211_get_ringparam,
};
diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
index 5b24740..889c3e9 100644
--- a/net/mac80211/chan.c
+++ b/net/mac80211/chan.c
@@ -77,6 +77,9 @@ bool ieee80211_set_channel_type(struct ieee80211_local *local,
switch (tmp->vif.bss_conf.channel_type) {
case NL80211_CHAN_NO_HT:
case NL80211_CHAN_HT20:
+ if (superchan > tmp->vif.bss_conf.channel_type)
+ break;
+
superchan = tmp->vif.bss_conf.channel_type;
break;
case NL80211_CHAN_HT40PLUS:
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 3729296..9c0d62b 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -526,4 +526,30 @@ static inline int drv_offchannel_tx_cancel_wait(struct ieee80211_local *local)
return ret;
}
+static inline int drv_set_ringparam(struct ieee80211_local *local,
+ u32 tx, u32 rx)
+{
+ int ret = -ENOTSUPP;
+
+ might_sleep();
+
+ trace_drv_set_ringparam(local, tx, rx);
+ if (local->ops->set_ringparam)
+ ret = local->ops->set_ringparam(&local->hw, tx, rx);
+ trace_drv_return_int(local, ret);
+
+ return ret;
+}
+
+static inline void drv_get_ringparam(struct ieee80211_local *local,
+ u32 *tx, u32 *tx_max, u32 *rx, u32 *rx_max)
+{
+ might_sleep();
+
+ trace_drv_get_ringparam(local, tx, tx_max, rx, rx_max);
+ if (local->ops->get_ringparam)
+ local->ops->get_ringparam(&local->hw, tx, tx_max, rx, rx_max);
+ trace_drv_return_void(local);
+}
+
#endif /* __MAC80211_DRIVER_OPS */
diff --git a/net/mac80211/driver-trace.h b/net/mac80211/driver-trace.h
index 520fe24..45aab80 100644
--- a/net/mac80211/driver-trace.h
+++ b/net/mac80211/driver-trace.h
@@ -912,6 +912,58 @@ TRACE_EVENT(drv_offchannel_tx,
)
);
+TRACE_EVENT(drv_set_ringparam,
+ TP_PROTO(struct ieee80211_local *local, u32 tx, u32 rx),
+
+ TP_ARGS(local, tx, rx),
+
+ TP_STRUCT__entry(
+ LOCAL_ENTRY
+ __field(u32, tx)
+ __field(u32, rx)
+ ),
+
+ TP_fast_assign(
+ LOCAL_ASSIGN;
+ __entry->tx = tx;
+ __entry->rx = rx;
+ ),
+
+ TP_printk(
+ LOCAL_PR_FMT " tx:%d rx %d",
+ LOCAL_PR_ARG, __entry->tx, __entry->rx
+ )
+);
+
+TRACE_EVENT(drv_get_ringparam,
+ TP_PROTO(struct ieee80211_local *local, u32 *tx, u32 *tx_max,
+ u32 *rx, u32 *rx_max),
+
+ TP_ARGS(local, tx, tx_max, rx, rx_max),
+
+ TP_STRUCT__entry(
+ LOCAL_ENTRY
+ __field(u32, tx)
+ __field(u32, tx_max)
+ __field(u32, rx)
+ __field(u32, rx_max)
+ ),
+
+ TP_fast_assign(
+ LOCAL_ASSIGN;
+ __entry->tx = *tx;
+ __entry->tx_max = *tx_max;
+ __entry->rx = *rx;
+ __entry->rx_max = *rx_max;
+ ),
+
+ TP_printk(
+ LOCAL_PR_FMT " tx:%d tx_max %d rx %d rx_max %d",
+ LOCAL_PR_ARG,
+ __entry->tx, __entry->tx_max, __entry->rx, __entry->rx_max
+ )
+);
+
DEFINE_EVENT(local_only_evt, drv_offchannel_tx_cancel_wait,
TP_PROTO(struct ieee80211_local *local),
TP_ARGS(local)
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index cc984bd..64d92d5 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -613,6 +613,37 @@ static void ieee80211_change_ps(struct ieee80211_local *local)
}
}
+static bool ieee80211_powersave_allowed(struct ieee80211_sub_if_data *sdata)
+{
+ struct ieee80211_if_managed *mgd = &sdata->u.mgd;
+ struct sta_info *sta = NULL;
+ u32 sta_flags = 0;
+
+ if (!mgd->powersave)
+ return false;
+
+ if (!mgd->associated)
+ return false;
+
+ if (!mgd->associated->beacon_ies)
+ return false;
+
+ if (mgd->flags & (IEEE80211_STA_BEACON_POLL |
+ IEEE80211_STA_CONNECTION_POLL))
+ return false;
+
+ rcu_read_lock();
+ sta = sta_info_get(sdata, mgd->bssid);
+ if (sta)
+ sta_flags = get_sta_flags(sta);
+ rcu_read_unlock();
+
+ if (!(sta_flags & WLAN_STA_AUTHORIZED))
+ return false;
+
+ return true;
+}
+
/* need to hold RTNL or interface lock */
void ieee80211_recalc_ps(struct ieee80211_local *local, s32 latency)
{
@@ -647,11 +678,7 @@ void ieee80211_recalc_ps(struct ieee80211_local *local, s32 latency)
count++;
}
- if (count == 1 && found->u.mgd.powersave &&
- found->u.mgd.associated &&
- found->u.mgd.associated->beacon_ies &&
- !(found->u.mgd.flags & (IEEE80211_STA_BEACON_POLL |
- IEEE80211_STA_CONNECTION_POLL))) {
+ if (count == 1 && ieee80211_powersave_allowed(found)) {
struct ieee80211_conf *conf = &local->hw.conf;
s32 beaconint_us;
diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c
index bce14fb..8212a8b 100644
--- a/net/mac80211/rc80211_minstrel_ht.c
+++ b/net/mac80211/rc80211_minstrel_ht.c
@@ -598,19 +598,46 @@ minstrel_ht_get_rate(void *priv, struct ieee80211_sta *sta, void *priv_sta,
sample = true;
minstrel_ht_set_rate(mp, mi, &ar[0], sample_idx,
txrc, true, false);
- minstrel_ht_set_rate(mp, mi, &ar[1], mi->max_tp_rate,
- txrc, false, false);
info->flags |= IEEE80211_TX_CTL_RATE_CTRL_PROBE;
} else {
minstrel_ht_set_rate(mp, mi, &ar[0], mi->max_tp_rate,
txrc, false, false);
- minstrel_ht_set_rate(mp, mi, &ar[1], mi->max_tp_rate2,
- txrc, false, true);
}
- minstrel_ht_set_rate(mp, mi, &ar[2], mi->max_prob_rate, txrc, false, !sample);
- ar[3].count = 0;
- ar[3].idx = -1;
+ if (mp->hw->max_rates >= 3) {
+ /*
+ * At least 3 tx rates supported, use
+ * sample_rate -> max_tp_rate -> max_prob_rate for sampling and
+ * max_tp_rate -> max_tp_rate2 -> max_prob_rate by default.
+ */
+ if (sample_idx >= 0)
+ minstrel_ht_set_rate(mp, mi, &ar[1], mi->max_tp_rate,
+ txrc, false, false);
+ else
+ minstrel_ht_set_rate(mp, mi, &ar[1], mi->max_tp_rate2,
+ txrc, false, true);
+
+ minstrel_ht_set_rate(mp, mi, &ar[2], mi->max_prob_rate,
+ txrc, false, !sample);
+
+ ar[3].count = 0;
+ ar[3].idx = -1;
+ } else if (mp->hw->max_rates == 2) {
+ /*
+ * Only 2 tx rates supported, use
+ * sample_rate -> max_prob_rate for sampling and
+ * max_tp_rate -> max_prob_rate by default.
+ */
+ minstrel_ht_set_rate(mp, mi, &ar[1], mi->max_prob_rate,
+ txrc, false, !sample);
+
+ ar[2].count = 0;
+ ar[2].idx = -1;
+ } else {
+ /* Not using MRR, only use the first rate */
+ ar[1].count = 0;
+ ar[1].idx = -1;
+ }
mi->total_packets++;
diff --git a/net/wireless/ethtool.c b/net/wireless/ethtool.c
index ca4c825..9bde4d1 100644
--- a/net/wireless/ethtool.c
+++ b/net/wireless/ethtool.c
@@ -1,5 +1,6 @@
#include <linux/utsname.h>
#include <net/cfg80211.h>
+#include "core.h"
#include "ethtool.h"
static void cfg80211_get_drvinfo(struct net_device *dev,
@@ -37,9 +38,41 @@ static void cfg80211_get_regs(struct net_device *dev, struct ethtool_regs *regs,
regs->len = 0;
}
+static void cfg80211_get_ringparam(struct net_device *dev,
+ struct ethtool_ringparam *rp)
+{
+ struct wireless_dev *wdev = dev->ieee80211_ptr;
+ struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+
+ memset(rp, 0, sizeof(*rp));
+
+ if (rdev->ops->get_ringparam)
+ rdev->ops->get_ringparam(wdev->wiphy,
+ &rp->tx_pending, &rp->tx_max_pending,
+ &rp->rx_pending, &rp->rx_max_pending);
+}
+
+static int cfg80211_set_ringparam(struct net_device *dev,
+ struct ethtool_ringparam *rp)
+{
+ struct wireless_dev *wdev = dev->ieee80211_ptr;
+ struct cfg80211_registered_device *rdev = wiphy_to_dev(wdev->wiphy);
+
+ if (rp->rx_mini_pending != 0 || rp->rx_jumbo_pending != 0)
+ return -EINVAL;
+
+ if (rdev->ops->set_ringparam)
+ return rdev->ops->set_ringparam(wdev->wiphy,
+ rp->tx_pending, rp->rx_pending);
+
+ return -ENOTSUPP;
+}
+
const struct ethtool_ops cfg80211_ethtool_ops = {
.get_drvinfo = cfg80211_get_drvinfo,
.get_regs_len = cfg80211_get_regs_len,
.get_regs = cfg80211_get_regs,
.get_link = ethtool_op_get_link,
+ .get_ringparam = cfg80211_get_ringparam,
+ .set_ringparam = cfg80211_set_ringparam,
};
--
John W. Linville Someday the world will need a hero, and you
linville@tuxdriver.com might be all we have. Be ready.
^ permalink raw reply related
* Re: [PATCH] tcp: avoid cwnd moderation in undo
From: Alexander Zimmermann @ 2011-03-15 18:50 UTC (permalink / raw)
To: John Heffner
Cc: Carsten Wolff, Yuchung Cheng, David Miller, Ilpo Jarvinen,
Nandita Dukkipati, netdev
In-Reply-To: <AANLkTim_U9CySFQimQ8cG_iHdXCYXSALi9E6ticKztnk@mail.gmail.com>
-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1
Hi John,
Am 15.03.2011 um 11:50 schrieb John Heffner:
>
> While I'm adding to my wish list ;-), I will also say that the undo
> logic seems unnecessarily complicated. If you expect you might have
> to undo what you just did, why not wait a bit? Something like rfc4653
> seems like it might be a better approach and might make the cwnd
> moderation discussion moot.
>
actually, our group (including Carsten) implemented RFC4653 for Linux.
At the moment, we run our final measurements. However, since I leave
the university, the work is not making much progress. Nevertheless I
I hope that we can finish this in the next couple of months. Besides the
Linux patch, we will bring an rfc4653bis as well as a reordering detection
draft to tcpm.
Alex
//
// Dipl.-Inform. Alexander Zimmermann
// Department of Computer Science, Informatik 4
// RWTH Aachen University
// Ahornstr. 55, 52056 Aachen, Germany
// phone: (49-241) 80-21422, fax: (49-241) 80-22222
// email: zimmermann@cs.rwth-aachen.de
// web: http://www.umic-mesh.net
//
-----BEGIN PGP SIGNATURE-----
Version: GnuPG/MacGPG2 v2.0.17 (Darwin)
Comment: GPGTools - http://gpgtools.org
iEYEARECAAYFAk1/tQsACgkQdyiq39b9uS7cFACeLaNsGVWoiVzAnUjXOnz8Y/Lk
fp0An0IlprotGMbtl1nXC62oyVEHcHv1
=zxT9
-----END PGP SIGNATURE-----
^ permalink raw reply
* Re: ECN + pfifo_fast borked? (Was Re: [Bloat] shaper team forming up)
From: Jonathan Morton @ 2011-03-15 18:37 UTC (permalink / raw)
To: Eric Dumazet; +Cc: Dave Täht, David Miller, netdev
In-Reply-To: <1300213714.2927.37.camel@edumazet-laptop>
On 15 Mar, 2011, at 8:28 pm, Eric Dumazet wrote:
>>> band 0 : high priority packets (like now)
>>> band 1 : (old band 1, ECN capable flows)
>>> band 2 : (old band 1, no ECN flows)
>>> band 3 : low priority packets (old band 2)
>>
>> This seems good to me. It would provide a concrete (if minor) enticement to turn ECN on.
>
> Here is a patch to implement that, on top of net-next-2.6 git tree
Does this take both ECN bits into account? The ECT(0), ECT(1) and ECE codepoints all need to be recognised equally.
- Jonathan
^ permalink raw reply
* IPsec tunnel forwarding in net-next-2.6 since 452edd59
From: Michael Smith @ 2011-03-15 18:30 UTC (permalink / raw)
To: netdev
Hi,
I'm able to ping across a tunnel to a peer running net-next-2.6, but
only to an interface on the peer; trying to ping a host behind the peer
fails. The incoming packet shows up in encrypted and decrypted form in
tcpdump, but it's not forwarded. None of the XFRM error counters are
incremented; the packets just silently fail to be forwarded.
There are no iptables rules and net.ipv4.ip_forward=1. The same config
works on 2.6.38-rc8. git bisect pointed me to commit 452edd59 from March 2:
xfrm: Return dst directly from xfrm_lookup()
Instead of on the stack.
ip xfrm policy:
src 192.168.136.0/24 dst 192.168.137.0/24
dir out priority 2344 ptype main
tmpl src 1.1.1.136 dst 1.1.1.137
proto esp reqid 16385 mode tunnel
src 192.168.137.0/24 dst 192.168.136.0/24
dir fwd priority 2344 ptype main
tmpl src 1.1.1.137 dst 1.1.1.136
proto esp reqid 16385 mode tunnel
src 192.168.137.0/24 dst 192.168.136.0/24
dir in priority 2344 ptype main
tmpl src 1.1.1.137 dst 1.1.1.136
proto esp reqid 16385 mode tunnel
net-next-2.6 host is at 1.1.1.136 and 192.168.136.1. 2.6.35.10 host is
at 1.1.1.137 and 192.168.137.1. From that host:
ping -I 192.168.137.1 192.168.136.1 -> success
ping -I 192.168.137.1 192.168.136.2 -> silent failure
Thanks,
Mike
^ permalink raw reply
* Re: ECN + pfifo_fast borked? (Was Re: [Bloat] shaper team forming up)
From: Eric Dumazet @ 2011-03-15 18:28 UTC (permalink / raw)
To: Jonathan Morton; +Cc: Dave Täht, David Miller, netdev
In-Reply-To: <3D05C1F1-B75E-426B-8267-6DB5323A839D@gmail.com>
Le mardi 15 mars 2011 à 19:09 +0200, Jonathan Morton a écrit :
> On 15 Mar, 2011, at 8:15 am, Eric Dumazet wrote:
>
> > band 0 : high priority packets (like now)
> > band 1 : (old band 1, ECN capable flows)
> > band 2 : (old band 1, no ECN flows)
> > band 3 : low priority packets (old band 2)
>
> This seems good to me. It would provide a concrete (if minor) enticement to turn ECN on.
>
>
Here is a patch to implement that, on top of net-next-2.6 git tree
qdisc pfifo_fast 0: dev eth1 root refcnt 2 bands 4 priomap 2 1 3 3 2 3 0 0 2 2 2 2 2 2 2 2
Sent 168 bytes 2 pkt (dropped 0, overlimits 0 requeues 0)
backlog 0b 0p requeues 0
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index c84b659..95ddf54 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -412,19 +412,39 @@ static struct Qdisc noqueue_qdisc = {
};
-static const u8 prio2band[TC_PRIO_MAX + 1] = {
- 1, 2, 2, 2, 1, 2, 0, 0 , 1, 1, 1, 1, 1, 1, 1, 1
+/* 4-band FIFO queue: old style, but should be a bit faster than
+ generic prio+fifo combination.
+ */
+
+enum {
+ BAND_HIGH_PRIO,
+ BAND_MEDIUM_ECN_PRIO,
+ BAND_MEDIUM_PRIO,
+ BAND_LOW_PRIO,
+
+ PFIFO_FAST_BANDS
};
-/* 3-band FIFO queue: old style, but should be a bit faster than
- generic prio+fifo combination.
+/*
+ * We give a litle incent to ECN flows
*/
+static const u8 prio2band[TC_PRIO_MAX + 1] = {
+ [TC_PRIO_BESTEFFORT] = BAND_MEDIUM_PRIO,
+ [TC_PRIO_FILLER] = BAND_MEDIUM_ECN_PRIO,
+ [TC_PRIO_BULK] = BAND_LOW_PRIO,
+ [TC_PRIO_BULK + 1] = BAND_LOW_PRIO,
+ [TC_PRIO_INTERACTIVE_BULK] = BAND_MEDIUM_PRIO,
+ [TC_PRIO_INTERACTIVE_BULK + 1] = BAND_LOW_PRIO,
+ [TC_PRIO_INTERACTIVE] = BAND_HIGH_PRIO,
+ [TC_PRIO_CONTROL] = BAND_HIGH_PRIO,
+
+ [TC_PRIO_CONTROL+1 ... TC_PRIO_MAX] = BAND_MEDIUM_PRIO,
+};
-#define PFIFO_FAST_BANDS 3
/*
* Private data for a pfifo_fast scheduler containing:
- * - queues for the three band
+ * - queues for the four bands
* - bitmap indicating which of the bands contain skbs
*/
struct pfifo_fast_priv {
@@ -436,9 +456,13 @@ struct pfifo_fast_priv {
* Convert a bitmap to the first band number where an skb is queued, where:
* bitmap=0 means there are no skbs on any band.
* bitmap=1 means there is an skb on band 0.
- * bitmap=7 means there are skbs on all 3 bands, etc.
+ * bitmap=2 means there is an skb on band 1.
+ * bitmap=15 means there are skbs on all 4 bands.
*/
-static const int bitmap2band[] = {-1, 0, 1, 0, 2, 0, 1, 0};
+static const int bitmap2band[1 << PFIFO_FAST_BANDS] = {
+ -1, 0, 1, 0, 2, 0, 1, 0,
+ 3, 0, 1, 0, 2, 0, 1, 0
+};
static inline struct sk_buff_head *band2list(struct pfifo_fast_priv *priv,
int band)
^ permalink raw reply related
* Re: Multicast Fails Over Multipoint GRE Tunnel
From: Timo Teräs @ 2011-03-15 18:28 UTC (permalink / raw)
To: Eric Dumazet; +Cc: Doug Kehn, netdev
In-Reply-To: <4D7F9592.5050408@iki.fi>
On 03/15/2011 06:36 PM, Timo Teräs wrote:
> On 03/15/2011 05:34 PM, Eric Dumazet wrote:
>> (Timo mentioned :
>> If the NOARP packets are not dropped, ipgre_tunnel_xmit() will
>> take rt->rt_gateway (= NBMA IP) and use that for route
>> look up (and may lead to bogus xfrm acquires).)
>>
>> Is the following works for you ?
>
> I have memory that _header() is called with daddr being valid pointer,
> but pointing to zero memory. So basically my situation would break with
> this.
Ok, I've gone through now the code paths. And I believe I made
originally the assumption that ipgre_tunnel_xmit would should not ever
get tiph->daddr == 0 if we got ipgre_header() call.
However, what actually happens is for (NOARP interfaces) in arp.c:
- unicast traffic gets NOARP entries mapped to dev->dev_addr (in gre
case it's the tunnel 'local' address)
- multicast gets mapped to dev->broadcast
And if we create gre tunnel without local or remote address we end up
getting the NOARP entries with hwaddr 0.0.0.0.
Now, for unicast traffic it's mostly pointless. If the tunnel was
locally bound the packets would never leave: they'd get NOARP entry for
local address. And if it's locally unbound, the packets get rt_gateway,
which is pretty confusing routing wise (it apparently assumes your link
device has same ipv4 subnet as the gre device).
On multicast side it makes a bit more sense to map multicast groups. And
this happened implicitly.
IMHO, we should fix the arp code in ipv4 and ipv6 to do proper
ARPHRD_IPGRE mappings so that the _header() gets called with proper
data. I think the multicast-to-same-multicast group mapping makes sense.
But do not really know what to do with unicast packets sent to gre
interface with NOARP and no link broadcast IP address.
Actually this was my problem: the unicast packets for gre interface with
NOARP flag resulted in trying to send packets out. So I could probably
just fix this by creating my gre interface *with* the ARP flag in the
first place.
But is there any sensible thing to do with the unicast packets in above
case? I think those should be just dropped. Or does someone think that
it'd ever make sense to take the inner unicast address and use it as the
outer address too? If so, my patch should be just reverted.
My honest thought is to keep the ip_gre header check as it is currently
and fix arp code in ipv4 / neighbour code in ipv6 to do the proper NOARP
mappings as needed. We might be able to get rid of the huge protocol
dependent "tiph->daddr == 0" check in xmit path this way, and make sure
that the header is set properly.
This would also allow us to see proper NOARP entries when doing "ip
neigh show nud noarp". Now it will just show 0.0.0.0 entries with gre
devices without telling where to the packets are actually being sent to.
Any thoughts?
Cheers,
Timo
^ permalink raw reply
* Re: [PATCH][v3] dev : fix mtu check when TSO is enabled
From: Stephen Hemminger @ 2011-03-15 18:17 UTC (permalink / raw)
To: Daniel Lezcano; +Cc: David Miller, eric.dumazet, kaber, nightnord, netdev
In-Reply-To: <4D7F7054.70409@free.fr>
On Tue, 15 Mar 2011 14:57:40 +0100
Daniel Lezcano <daniel.lezcano@free.fr> wrote:
> On 03/15/2011 12:59 AM, David Miller wrote:
> > From: Daniel Lezcano<daniel.lezcano@free.fr>
> > Date: Mon, 14 Mar 2011 21:39:50 +0100
> >
> >> + len = dev->mtu + dev->hard_header_len + VLAN_HLEN;
> >> + if (skb->len< len)
> >> + return true;
> > This is not a correct translation of the original test:
> >
> >> - (skb->len> (dev->mtu + dev->hard_header_len + VLAN_HLEN)))) {
> > You need to use "<=" in your version, which currently rejects all
> > full sized frames. :-)
>
> Right, thanks.
>
> >> +
> >> + /* if TSO is enabled, we don't care about the length as the packet
> >> + * could be forwarded without being segmented before
> >> + */
> >> + if (skb->dev&& skb->dev->features& NETIF_F_TSO)
> >> + return true;
> > I am trying to understand why you aren't simply checking also if this
> > is a segmented frame? Perhaps skb_is_gso()&& device has NETIF_F_TSO
> > set?
>
> Maybe I am misunderstanding but the packet was forwarded by another device.
> In our case from macvlan:
>
> macvlan_start_xmit
> macvlan_queue_xmit
> dest->forward
> dev_skb_forward
>
> When we reached dev_skb_forward, that means we passed through
> dev_hard_start_xmit where the packet was already segmented so we should
> exit at the first test (skb->len < len). I don't see the point of adding
> the skb_is_gso.
> But maybe I am missing something, can you explain ?
The macvlan device only has one downstream device (slave).
If kernel is working properly, macvlan device should have a subset
of the features of the underlying device and macvlan device should
have same MTU as underlying device. If the feature/MTU flags
were correct, then the path calling macvlan should be respecting
the MTU.
--
^ permalink raw reply
* ethtool 2.6.38 released
From: Ben Hutchings @ 2011-03-15 17:45 UTC (permalink / raw)
To: netdev
[-- Attachment #1: Type: text/plain, Size: 928 bytes --]
ethtool version 2.6.38 has been released.
Home page: https://ftp.kernel.org/pub/software/network/ethtool/
Download link:
https://ftp.kernel.org/pub/software/network/ethtool/ethtool-2.6.38.tar.gz
Release notes:
* Doc: Fix spelling and spacing in online help
* Doc: Update date, version and web site reference in manual page
* Doc: Fix spelling, capitalisation, consistency and style in
manual page
* Doc: Generalise some references to network devices rather than
Ethernet devices
* Fix: Don't silently ignore speed/duplex when autoneg is on
* Fix: Report an error (rather than full usage information) if
given an unrecognised option
* Feature: Add --version option
Ben.
--
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.
[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 490 bytes --]
^ permalink raw reply
* Re: ECN + pfifo_fast borked? (Was Re: [Bloat] shaper team forming up)
From: Jonathan Morton @ 2011-03-15 17:09 UTC (permalink / raw)
To: Eric Dumazet; +Cc: Dave Täht, David Miller, netdev
In-Reply-To: <1300169749.2649.142.camel@edumazet-laptop>
On 15 Mar, 2011, at 8:15 am, Eric Dumazet wrote:
> band 0 : high priority packets (like now)
> band 1 : (old band 1, ECN capable flows)
> band 2 : (old band 1, no ECN flows)
> band 3 : low priority packets (old band 2)
This seems good to me. It would provide a concrete (if minor) enticement to turn ECN on.
- Jonathan
^ permalink raw reply
* Re: Multicast Fails Over Multipoint GRE Tunnel
From: Timo Teräs @ 2011-03-15 16:36 UTC (permalink / raw)
To: Eric Dumazet; +Cc: Doug Kehn, netdev
In-Reply-To: <1300203277.2927.9.camel@edumazet-laptop>
On 03/15/2011 05:34 PM, Eric Dumazet wrote:
> Le lundi 14 mars 2011 à 16:34 -0700, Doug Kehn a écrit :
>> I'm running kernel version 2.6.36 on ARM XSCALE (big-endian) and multicast over a multipoint GRE tunnel isn't working. For my architecture, this worked on 2.6.26.8. For x86, multicast over a multipoint GRE tunnel worked with kernel version 2.6.31 but failed with version 2.6.35. Multicast over a multipoint GRE tunnel fails because ipgre_header() fails the 'if (iph->daddr)' check and reutrns -t->hlen. ipgre_header() is being called, from neigh_connected_output(), with a non-null daddr; the contents of daddr is zero.
>>
>> Reverting the ip_gre.c patch posted in http://marc.info/?l=linux-netdev&m=126762491525281&w=2 resolves the problem. (Reviewing the HEAD of net-next-2.6 it appears that ipgre_header() remains unchanged from 2.6.36.)
>>
>> The configuration used to discover/diagnose the problem:
>>
>> ip tunnel add tun1 mode gre key 11223344 ttl 64 csum remote any
>> ip link set dev tun1 up
>> ip link set dev tun1 multicast on
>> ip addr flush dev tun1
>> ip addr add 10.40.92.114/24 broadcast 10.40.92.255 dev tun1
>>
>> 12: tun1: <MULTICAST,NOARP,UP,10000> mtu 1468 qdisc noqueue
>> link/gre 0.0.0.0 brd 0.0.0.0
>> inet 10.40.92.114/24 brd 10.40.92.255 scope global tun1
>>
>> Then attempt:
>> ping -I tun1 224.0.0.9
>>
>> Are additional configuration steps now required for multicast over multipoint GRE tunnel or is ipgre_header() in error?
>
> Hi Doug
>
> CC Timo Teras <timo.teras@iki.fi>
>
> I would do a partial revert of Timo patch, but this means initial
> concern should be addressed ?
>
> (Timo mentioned :
> If the NOARP packets are not dropped, ipgre_tunnel_xmit() will
> take rt->rt_gateway (= NBMA IP) and use that for route
> look up (and may lead to bogus xfrm acquires).)
>
>
> Is the following works for you ?
I have memory that _header() is called with daddr being valid pointer,
but pointing to zero memory. So basically my situation would break with
this.
The above configuration would be fixable by setting broadcast to tun1
interface explicitly. But I'm not sure if the above configuration is
somehow different that it'd need to work.
Basically how things work on send path is:
1. arp_constructor maps multicast address to NUD_NOARP
2. arp_mc_map in turn copies dev->broadcast to haddr
(so you get the ip packet pointing to zero ip)
- i assumed normally gre tunnels would have the
broadcast address set
3. ipgre_tunnel_xmit checks for daddr==0 and uses the
rt_gateway then, which would map to the multicast
address
So I assume that the above ping command not working would end up sending
gre encapsulated packet where both the inner and outer IP address is the
same multicast address?
Looks like my patch also broke the default behaviour that if one has
such GRE tunnel, and you send unicast packets, it would default the link
destination to be same as the inner destination. Not sure if this would
be useful.
So basically my situation is undistinguishable from the above one. The
only difference is that the above problems only with multicast, and I'm
having with unicast.
I think the fundamental problem is that arp_mc_map maps the multicast
address to zeroes (due to device broadcast being zero).
Could we instead maybe do something like:
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 7927589..372448a 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -215,6 +215,12 @@ int arp_mc_map(__be32 addr, u8 *haddr, struct
net_device *dev, int dir)
case ARPHRD_INFINIBAND:
ip_ib_mc_map(addr, dev->broadcast, haddr);
return 0;
+ case ARPHRD_IPGRE:
+ if (dev->broadcast)
+ memcpy(haddr, dev->broadcast, dev->addr_len);
+ else
+ memcpy(haddr, &addr, sizeof(addr));
+ return 0;
default:
if (dir) {
memcpy(haddr, dev->broadcast, dev->addr_len);
^ permalink raw reply related
* [ANNOUNCE] pymnl 0.1
From: Sean Robinson @ 2011-03-15 16:11 UTC (permalink / raw)
To: netdev
pymnl is an LGPL-licensed pure Python re-implementation of libmnl for
working with Linux Netlink sockets and messages.
Information about pymnl 0.1 is at http://pymnl.wikispot.org Downloads
are hosted at Pypi <http://pypi.python.org/pypi/pymnl> and TuxFamily
<http://downloads.tuxfamily.org/pymnl/>.
--
Sean Robinson
WiFi Radar - http://wifi-radar.berlios.de
Python WiFi - http://pythonwifi.wikispot.org
pymnl - http://pymnl.wikispot.org
^ permalink raw reply
* Re: [GIT] Networking
From: Linus Torvalds @ 2011-03-15 15:43 UTC (permalink / raw)
To: david
Cc: Steven Rostedt, J. Bruce Fields, Ben Hutchings, David Miller,
akpm, netdev, linux-kernel
In-Reply-To: <alpine.DEB.2.00.1103150019060.5340@asgard.lang.hm>
On Tue, Mar 15, 2011 at 12:20 AM, <david@lang.hm> wrote:
>
> what effect would this have on bisecting? if this helped people avoid
> bisecting in between the bad commit and the fix for it, it may be worth it.
The biggest impact on bisecting would be to just make it slower due to
extra merge commits. It's probably not a hugely noticeable thing,
though - we have merges for lots of other reasons.
Merges make bisecting a bit less efficient not only because they are
an extra commit, but because merges - by not being linear - end up
making it harder to find the "perfect" half-way point. IOW, the
bisection algorithm may not be able to pick a commit exactly midway,
because if it picks a merge it will obviously include both branches
(which may be "too much"), but if it picks the last commit of either
branch it may be too little.
And not picking a good half-way point makes bisection less efficient
(it's no longer "log2()", but maybe "log1.7()").
In practice, though, I suspect it's not really a big issue.
The other issue with bisecting merges is obviously that it can be
really nasty to figure out a bug that is introduced by the merge
itself (which is usually due to some interaction between the things
being merged, rather than any real mis-merge itself, although
mis-merges can obviously happen).
Again, that's pretty rare, although it does happen (and is often quite
"interesting" when it happens).
But in practice, I think the biggest argument against trying to fix
things as patches on top of the original bug and then merging it in is
that it's just extra work for fairly small gain. In particular:
- not all bugs get bisected. In fact, it's the minority - most
bug-fixes are "obvious", and no-one even bothers bisecting them
- not all bugs are as clearly the result of a single commit. Many are
a commit series. Sure, you'd just make it the last one in the series,
but it would kind of defeat the "parent introduced the bug" point of
it all.
- putting the "commit xyz caused this problem" in the changelog (and
then just follow the chain that way) isn't really all that much worse.
The reason I talked about doing this for _merges_ is that I think
developers should think a lot more about merging, but I don't think
people need to think a lot about "let's fix this obvious bug".
- bugfixes are often sent out as emails etc. Just applying the
bug-fix would be a _lot_ more work if it involved "create new branch
at original bug, apply, merge" than just "apply". That's especially
true for series of patches, like the ones I get from Andrew and Al.
In particular, that last thing is a killer for me personally. It
(together with the first point) would mean that it would be done only
for a very small subset of bugs, which really defeats the whole
purpose, and then makes that "merge it on top of its parent" thing be
the unusual case rather than some general rule.
And merges do end up being more complicated than plain patches. Not
just in the "extra commit" sense, but also simply in the sense of
making the history more complex.
They do have advantages too. We could just merge the same branch into
multiple branches, for example (-stable comes to mind). That said,
once more, it would really complicate things for everybody (no longer
can the stable people just apply a series of patches), so...
So on the whole, I don't think it would be worth it. I don't think
it's _wrong_, mind you, I just think that the way we work, it's more
pain than gain.
For doing a backwards merge, I think the "more pain" is a _good_ thing
(it really shouldn't _ever_ be a mindless "let's merge whatever
upstream is today" and I definitely made that mindless action too easy
to do in git). For most bug-fixes, more pain is just that - more pain.
Linus
^ 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