* [PATCH 20/24] IPVS: Conditional ip_vs_conntrack_enabled()
From: Simon Horman @ 2011-03-15 5:27 UTC (permalink / raw)
To: netdev, netfilter-devel, netfilter, lvs-devel
Cc: Eric Dumazet, Julian Anastasov, Hans Schillstrom, Patrick McHardy,
Simon Horman
In-Reply-To: <1300166852-725-1-git-send-email-horms@verge.net.au>
ip_vs_conntrack_enabled() becomes a noop when CONFIG_SYSCTL is undefined.
In preparation for not including sysctl_conntrack in
struct netns_ipvs when CONFIG_SYCTL is not defined.
Signed-off-by: Simon Horman <horms@verge.net.au>
---
include/net/ip_vs.h | 4 ++++
1 files changed, 4 insertions(+), 0 deletions(-)
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 77ebece..299aeb5 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1359,7 +1359,11 @@ static inline void ip_vs_notrack(struct sk_buff *skb)
*/
static inline int ip_vs_conntrack_enabled(struct netns_ipvs *ipvs)
{
+#ifdef CONFIG_SYSCTL
return ipvs->sysctl_conntrack;
+#else
+ return 0;
+#endif
}
extern void ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp,
--
1.7.2.3
^ permalink raw reply related
* [PATCH 22/24] IPVS: Conditionally define and use ip_vs_lblc{r}_table
From: Simon Horman @ 2011-03-15 5:27 UTC (permalink / raw)
To: netdev, netfilter-devel, netfilter, lvs-devel
Cc: Eric Dumazet, Julian Anastasov, Hans Schillstrom, Patrick McHardy,
Simon Horman
In-Reply-To: <1300166852-725-1-git-send-email-horms@verge.net.au>
ip_vs_lblc_table and ip_vs_lblcr_table, and code that uses them
are unnecessary when CONFIG_SYSCTL is undefined.
Signed-off-by: Simon Horman <horms@verge.net.au>
---
net/netfilter/ipvs/ip_vs_lblc.c | 15 ++++++++++-----
net/netfilter/ipvs/ip_vs_lblcr.c | 14 ++++++++++----
2 files changed, 20 insertions(+), 9 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c
index 51a27f5..f276df9 100644
--- a/net/netfilter/ipvs/ip_vs_lblc.c
+++ b/net/netfilter/ipvs/ip_vs_lblc.c
@@ -114,7 +114,7 @@ struct ip_vs_lblc_table {
/*
* IPVS LBLC sysctl table
*/
-
+#ifdef CONFIG_SYSCTL
static ctl_table vs_vars_table[] = {
{
.procname = "lblc_expiration",
@@ -125,6 +125,7 @@ static ctl_table vs_vars_table[] = {
},
{ }
};
+#endif
static inline void ip_vs_lblc_free(struct ip_vs_lblc_entry *en)
{
@@ -548,6 +549,7 @@ static struct ip_vs_scheduler ip_vs_lblc_scheduler =
/*
* per netns init.
*/
+#ifdef CONFIG_SYSCTL
static int __net_init __ip_vs_lblc_init(struct net *net)
{
struct netns_ipvs *ipvs = net_ipvs(net);
@@ -563,7 +565,6 @@ static int __net_init __ip_vs_lblc_init(struct net *net)
ipvs->sysctl_lblc_expiration = DEFAULT_EXPIRATION;
ipvs->lblc_ctl_table[0].data = &ipvs->sysctl_lblc_expiration;
-#ifdef CONFIG_SYSCTL
ipvs->lblc_ctl_header =
register_net_sysctl_table(net, net_vs_ctl_path,
ipvs->lblc_ctl_table);
@@ -572,7 +573,6 @@ static int __net_init __ip_vs_lblc_init(struct net *net)
kfree(ipvs->lblc_ctl_table);
return -ENOMEM;
}
-#endif
return 0;
}
@@ -581,14 +581,19 @@ static void __net_exit __ip_vs_lblc_exit(struct net *net)
{
struct netns_ipvs *ipvs = net_ipvs(net);
-#ifdef CONFIG_SYSCTL
unregister_net_sysctl_table(ipvs->lblc_ctl_header);
-#endif
if (!net_eq(net, &init_net))
kfree(ipvs->lblc_ctl_table);
}
+#else
+
+static int __net_init __ip_vs_lblc_init(struct net *net) { return 0; }
+static void __net_exit __ip_vs_lblc_exit(struct net *net) { }
+
+#endif
+
static struct pernet_operations ip_vs_lblc_ops = {
.init = __ip_vs_lblc_init,
.exit = __ip_vs_lblc_exit,
diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c
index 7fb9190..cb1c991 100644
--- a/net/netfilter/ipvs/ip_vs_lblcr.c
+++ b/net/netfilter/ipvs/ip_vs_lblcr.c
@@ -285,6 +285,7 @@ struct ip_vs_lblcr_table {
};
+#ifdef CONFIG_SYSCTL
/*
* IPVS LBLCR sysctl table
*/
@@ -299,6 +300,7 @@ static ctl_table vs_vars_table[] = {
},
{ }
};
+#endif
static inline void ip_vs_lblcr_free(struct ip_vs_lblcr_entry *en)
{
@@ -743,6 +745,7 @@ static struct ip_vs_scheduler ip_vs_lblcr_scheduler =
/*
* per netns init.
*/
+#ifdef CONFIG_SYSCTL
static int __net_init __ip_vs_lblcr_init(struct net *net)
{
struct netns_ipvs *ipvs = net_ipvs(net);
@@ -758,7 +761,6 @@ static int __net_init __ip_vs_lblcr_init(struct net *net)
ipvs->sysctl_lblcr_expiration = DEFAULT_EXPIRATION;
ipvs->lblcr_ctl_table[0].data = &ipvs->sysctl_lblcr_expiration;
-#ifdef CONFIG_SYSCTL
ipvs->lblcr_ctl_header =
register_net_sysctl_table(net, net_vs_ctl_path,
ipvs->lblcr_ctl_table);
@@ -767,7 +769,6 @@ static int __net_init __ip_vs_lblcr_init(struct net *net)
kfree(ipvs->lblcr_ctl_table);
return -ENOMEM;
}
-#endif
return 0;
}
@@ -776,14 +777,19 @@ static void __net_exit __ip_vs_lblcr_exit(struct net *net)
{
struct netns_ipvs *ipvs = net_ipvs(net);
-#ifdef CONFIG_SYSCTL
unregister_net_sysctl_table(ipvs->lblcr_ctl_header);
-#endif
if (!net_eq(net, &init_net))
kfree(ipvs->lblcr_ctl_table);
}
+#else
+
+static int __net_init __ip_vs_lblcr_init(struct net *net) { return 0; }
+static void __net_exit __ip_vs_lblcr_exit(struct net *net) { }
+
+#endif
+
static struct pernet_operations ip_vs_lblcr_ops = {
.init = __ip_vs_lblcr_init,
.exit = __ip_vs_lblcr_exit,
--
1.7.2.3
^ permalink raw reply related
* [PATCH 23/24] IPVS: Add __ip_vs_control_{init,cleanup}_sysctl()
From: Simon Horman @ 2011-03-15 5:27 UTC (permalink / raw)
To: netdev, netfilter-devel, netfilter, lvs-devel
Cc: Eric Dumazet, Julian Anastasov, Hans Schillstrom, Patrick McHardy,
Simon Horman
In-Reply-To: <1300166852-725-1-git-send-email-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
* ECN + pfifo_fast borked? (Was Re: [Bloat] shaper team forming up)
From: Dave Täht @ 2011-03-15 5:27 UTC (permalink / raw)
To: Eric Dumazet; +Cc: Jonathan Morton, David Miller, netdev
In-Reply-To: <1300164166.2649.70.camel@edumazet-laptop>
Eric Dumazet <eric.dumazet@gmail.com> writes:
> Le lundi 14 mars 2011 à 21:24 +0100, Eric Dumazet a écrit :
>
> remove CC to bloat lists for now, adding David Miller to thread.
>
>> Le lundi 14 mars 2011 à 21:55 +0200, Jonathan Morton a écrit :
>> > On 14 Mar, 2011, at 9:26 pm, Dave Täht wrote:
>> >
>> > > Over the weekend, Dan Siemon uncovered a possible bad interaction
>> > > between ECN and the default pfifo_fast qdisc in Linux.
>> > >
>> > > http://www.coverfire.com/archives/2011/03/13/pfifo_fast-and-ecn/
>> >
Totally irrelevant bit elided
>> CC netdev, where linux network dev can take a look.
>>
>> I would say that this is a wrong analysis :
>>
>> 1) ECN uses two low order bits of TOS byte
>>
>> 2) pfifo_fast uses skb->priority
>>
>>
>> skb->priority = rt_tos2priority(iph->tos);
>>
>> #define IPTOS_TOS_MASK 0x1E
>> #define IPTOS_TOS(tos) ((tos)&IPTOS_TOS_MASK)
>>
>> static inline char rt_tos2priority(u8 tos)
>> {
>> return ip_tos2prio[IPTOS_TOS(tos)>>1];
>> }
>>
>> No interference between two mechanisms, unless sysadmin messed up things
>> (skb_edit)
>>
>>
>
> David, it seems ip_tos2prio is wrong on its 2nd entry :
>
> #define TC_PRIO_BESTEFFORT 0
> #define TC_PRIO_FILLER 1
> #define TC_PRIO_BULK 2
> #define TC_PRIO_INTERACTIVE_BULK 4
> #define TC_PRIO_INTERACTIVE 6
> #define TC_PRIO_CONTROL 7
>
> #define TC_PRIO_MAX 15
>
> net/ipv4/route.c:170:#define ECN_OR_COST(class) TC_PRIO_##class
>
> const __u8 ip_tos2prio[16] = {
> TC_PRIO_BESTEFFORT, /* 0 : for flow without ECN */
> ECN_OR_COST(FILLER), /* 1 : flow with ECN */
> ...
> };
>
>
>
>
> This means ECN enabled flows got TC_PRIO_FILLER (what the hell is
> that ?)
>
> pfifo_fast has :
>
> static const u8 prio2band[TC_PRIO_MAX+1] =
> { 1, 2, 2, 2, 1, 2, 0, 0 , 1, 1, 1, 1, 1, 1, 1, 1 };
>
> So a non ECN enabled flow goes to band 1, while an ECN enabled one is in
> band 2 (!). Thus, ECN enabled flows have a chance being droped more
> often than non ECN flows. Thats not fair...
>
> What do you think ?
Well, that makes 3 of us that think it's wrong. Can we get more?
(I'll run through the math again in the morning)
It's most often not actually "enablement" but "assertion", when for
example an ECN bit is put on an ACK packet (by an application, or qdisc)
, it drops that ACK packet into the 2 queue - leaving all the other
non-ECN asserted packets in that flow to flow out ahead of it.
Or so dan siemon & I & now you, think. It's late and I really want to recheck
the math and the shifts in the morning. However, if true... this would
explain much ECN related weirdness precisely where it has been hard to
measure, on heavily loaded systems.
>
> Thanks
>
> diff --git a/net/ipv4/route.c b/net/ipv4/route.c
> index 6ed6603..fabfe81 100644
> --- a/net/ipv4/route.c
> +++ b/net/ipv4/route.c
> @@ -171,7 +171,7 @@ static struct dst_ops ipv4_dst_ops = {
>
> const __u8 ip_tos2prio[16] = {
> TC_PRIO_BESTEFFORT,
> - ECN_OR_COST(FILLER),
> + ECN_OR_COST(BESTEFFORT),
> TC_PRIO_BESTEFFORT,
> ECN_OR_COST(BESTEFFORT),
> TC_PRIO_BULK,
>
I think this is a good short term fix, but it will mildly upset people
that actually still use minimum cost and don't use ECN. That said,
RFC1349 has been obsolete for a decade now, and ECN enabled servers are
at 12% penetration according to MIT.
Still, long term, doing a sch_pfifo_dscp that would be fully compliant
with the relevant modern RFCs and eventually making that the standard
would be good.
--
Dave Taht
http://nex-6.taht.net
^ permalink raw reply
* [GIT PULL nf-next-2.6] IPVS
From: Simon Horman @ 2011-03-15 5:27 UTC (permalink / raw)
To: netdev, netfilter-devel, netfilter, lvs-devel
Cc: Eric Dumazet, Julian Anastasov, Hans Schillstrom, Patrick McHardy
Hi Patrick,
please consider pulling
git://git.kernel.org/pub/scm/linux/kernel/git/horms/lvs-test-2.6.git for-patrick
to get the changes listed below.
This replaces the pull requests that I sent yesterday, sorry for messing
that up.
Also, sorry for letting the number of patches grow so much, Julian and I
were working on patches that conflicted with each other. But regardless, I
should have done something about getting a request to you earlier.
Jesper Juhl (1):
IPVS: Fix variable assignment in ip_vs_notrack
Julian Anastasov (8):
ipvs: avoid lookup for fwmark 0
ipvs: remove _bh from percpu stats reading
ipvs: move struct netns_ipvs
ipvs: reorganize tot_stats
ipvs: properly zero stats and rates
ipvs: remove unused seqcount stats
ipvs: optimize rates reading
ipvs: rename estimator functions
Shan Wei (1):
netfilter:ipvs: use kmemdup
Simon Horman (14):
IPVS: Add ip_vs_route_me_harder()
IPVS: Add sysctl_snat_reroute()
IPVS: Add sysctl_nat_icmp_send()
IPVS: Add {sysctl_sync_threshold,period}()
IPVS: Add sysctl_sync_ver()
IPVS: Add sysctl_expire_nodest_conn()
IPVS: Add expire_quiescent_template()
IPVS: Conditinally use sysctl_lblc{r}_expiration
IPVS: ip_vs_todrop() becomes a noop when CONFIG_SYSCTL is undefined
IPVS: Conditional ip_vs_conntrack_enabled()
IPVS: Minimise ip_vs_leave when CONFIG_SYSCTL is undefined
IPVS: Conditionally define and use ip_vs_lblc{r}_table
IPVS: Add __ip_vs_control_{init,cleanup}_sysctl()
IPVS: Conditionally include sysctl members of struct netns_ipvs
include/net/ip_vs.h | 198 ++++++++++++++++++++++++++---
include/net/net_namespace.h | 2 +-
include/net/netns/ip_vs.h | 143 ---------------------
net/netfilter/ipvs/ip_vs_conn.c | 13 ++-
net/netfilter/ipvs/ip_vs_core.c | 104 +++++++++------
net/netfilter/ipvs/ip_vs_ctl.c | 256 ++++++++++++++++++++++---------------
net/netfilter/ipvs/ip_vs_est.c | 63 ++++-----
net/netfilter/ipvs/ip_vs_lblc.c | 31 ++++-
net/netfilter/ipvs/ip_vs_lblcr.c | 35 ++++--
net/netfilter/ipvs/ip_vs_pe_sip.c | 9 +-
net/netfilter/ipvs/ip_vs_sync.c | 11 +-
11 files changed, 492 insertions(+), 373 deletions(-)
delete mode 100644 include/net/netns/ip_vs.h
^ permalink raw reply
* [PATCH 04/24] IPVS: Fix variable assignment in ip_vs_notrack
From: Simon Horman @ 2011-03-15 5:27 UTC (permalink / raw)
To: netdev, netfilter-devel, netfilter, lvs-devel
Cc: Eric Dumazet, Julian Anastasov, Hans Schillstrom, Patrick McHardy,
Jesper Juhl, Simon Horman
In-Reply-To: <1300166852-725-1-git-send-email-horms@verge.net.au>
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 03/24] netfilter:ipvs: use kmemdup
From: Simon Horman @ 2011-03-15 5:27 UTC (permalink / raw)
To: netdev, netfilter-devel, netfilter, lvs-devel
Cc: Eric Dumazet, Julian Anastasov, Hans Schillstrom, Patrick McHardy,
Shan Wei, Simon Horman
In-Reply-To: <1300166852-725-1-git-send-email-horms@verge.net.au>
From: Shan Wei <shanwei@cn.fujitsu.com>
The semantic patch that makes this output is available
in scripts/coccinelle/api/memdup.cocci.
More information about semantic patching is available at
http://coccinelle.lip6.fr/
Signed-off-by: Shan Wei <shanwei@cn.fujitsu.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
net/netfilter/ipvs/ip_vs_pe_sip.c | 9 ++++-----
net/netfilter/ipvs/ip_vs_sync.c | 3 +--
2 files changed, 5 insertions(+), 7 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c
index 0d83bc0..13d607a 100644
--- a/net/netfilter/ipvs/ip_vs_pe_sip.c
+++ b/net/netfilter/ipvs/ip_vs_pe_sip.c
@@ -92,14 +92,13 @@ ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb)
if (get_callid(dptr, dataoff, datalen, &matchoff, &matchlen))
return -EINVAL;
- p->pe_data = kmalloc(matchlen, GFP_ATOMIC);
- if (!p->pe_data)
- return -ENOMEM;
-
/* N.B: pe_data is only set on success,
* this allows fallback to the default persistence logic on failure
*/
- memcpy(p->pe_data, dptr + matchoff, matchlen);
+ p->pe_data = kmemdup(dptr + matchoff, matchlen, GFP_ATOMIC);
+ if (!p->pe_data)
+ return -ENOMEM;
+
p->pe_data_len = matchlen;
return 0;
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index fecf24d..c5d13b0 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -697,13 +697,12 @@ ip_vs_conn_fill_param_sync(struct net *net, int af, union ip_vs_sync_conn *sc,
return 1;
}
- p->pe_data = kmalloc(pe_data_len, GFP_ATOMIC);
+ p->pe_data = kmemdup(pe_data, pe_data_len, GFP_ATOMIC);
if (!p->pe_data) {
if (p->pe->module)
module_put(p->pe->module);
return -ENOMEM;
}
- memcpy(p->pe_data, pe_data, pe_data_len);
p->pe_data_len = pe_data_len;
}
return 0;
--
1.7.2.3
^ permalink raw reply related
* [PATCH 09/24] ipvs: optimize rates reading
From: Simon Horman @ 2011-03-15 5:27 UTC (permalink / raw)
To: netdev, netfilter-devel, netfilter, lvs-devel
Cc: Eric Dumazet, Julian Anastasov, Hans Schillstrom, Patrick McHardy,
Simon Horman
In-Reply-To: <1300166852-725-1-git-send-email-horms@verge.net.au>
From: Julian Anastasov <ja@ssi.bg>
Move the estimator reading from estimation_timer to user
context. ip_vs_read_estimator() will be used to decode the rate
values. As the decoded rates are not set by estimation timer
there is no need to reset them in ip_vs_zero_stats.
There is no need ip_vs_new_estimator() to encode stats
to rates, if the destination is in trash both the stats and the
rates are inactive.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
---
include/net/ip_vs.h | 2 ++
net/netfilter/ipvs/ip_vs_ctl.c | 31 ++++++++++++-------------------
net/netfilter/ipvs/ip_vs_est.c | 33 +++++++++++++--------------------
3 files changed, 27 insertions(+), 39 deletions(-)
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index cf014ab..e4a39c4 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1179,6 +1179,8 @@ 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_zero_estimator(struct ip_vs_stats *stats);
+extern void ip_vs_read_estimator(struct ip_vs_stats_user *dst,
+ struct ip_vs_stats *stats);
/*
* Various IPVS packet transmitters (from ip_vs_xmit.c)
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 804fee7..c93d806 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -715,7 +715,6 @@ static void
ip_vs_copy_stats(struct ip_vs_stats_user *dst, struct ip_vs_stats *src)
{
#define IP_VS_SHOW_STATS_COUNTER(c) dst->c = src->ustats.c - src->ustats0.c
-#define IP_VS_SHOW_STATS_RATE(r) dst->r = src->ustats.r
spin_lock_bh(&src->lock);
@@ -725,11 +724,7 @@ ip_vs_copy_stats(struct ip_vs_stats_user *dst, struct ip_vs_stats *src)
IP_VS_SHOW_STATS_COUNTER(inbytes);
IP_VS_SHOW_STATS_COUNTER(outbytes);
- IP_VS_SHOW_STATS_RATE(cps);
- IP_VS_SHOW_STATS_RATE(inpps);
- IP_VS_SHOW_STATS_RATE(outpps);
- IP_VS_SHOW_STATS_RATE(inbps);
- IP_VS_SHOW_STATS_RATE(outbps);
+ ip_vs_read_estimator(dst, src);
spin_unlock_bh(&src->lock);
}
@@ -742,7 +737,6 @@ ip_vs_zero_stats(struct ip_vs_stats *stats)
/* get current counters as zero point, rates are zeroed */
#define IP_VS_ZERO_STATS_COUNTER(c) stats->ustats0.c = stats->ustats.c
-#define IP_VS_ZERO_STATS_RATE(r) stats->ustats.r = 0
IP_VS_ZERO_STATS_COUNTER(conns);
IP_VS_ZERO_STATS_COUNTER(inpkts);
@@ -750,12 +744,6 @@ ip_vs_zero_stats(struct ip_vs_stats *stats)
IP_VS_ZERO_STATS_COUNTER(inbytes);
IP_VS_ZERO_STATS_COUNTER(outbytes);
- IP_VS_ZERO_STATS_RATE(cps);
- IP_VS_ZERO_STATS_RATE(inpps);
- IP_VS_ZERO_STATS_RATE(outpps);
- IP_VS_ZERO_STATS_RATE(inbps);
- IP_VS_ZERO_STATS_RATE(outbps);
-
ip_vs_zero_estimator(stats);
spin_unlock_bh(&stats->lock);
@@ -2043,6 +2031,7 @@ 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_cpu_stats *cpustats = tot_stats->cpustats;
+ struct ip_vs_stats_user rates;
int i;
/* 01234567 01234567 01234567 0123456701234567 0123456701234567 */
@@ -2069,22 +2058,26 @@ static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v)
}
spin_lock_bh(&tot_stats->lock);
+
seq_printf(seq, " ~ %8X %8X %8X %16LX %16LX\n\n",
tot_stats->ustats.conns, tot_stats->ustats.inpkts,
tot_stats->ustats.outpkts,
(unsigned long long) tot_stats->ustats.inbytes,
(unsigned long long) tot_stats->ustats.outbytes);
+ ip_vs_read_estimator(&rates, tot_stats);
+
+ spin_unlock_bh(&tot_stats->lock);
+
/* 01234567 01234567 01234567 0123456701234567 0123456701234567 */
seq_puts(seq,
" Conns/s Pkts/s Pkts/s Bytes/s Bytes/s\n");
seq_printf(seq, " %8X %8X %8X %16X %16X\n",
- tot_stats->ustats.cps,
- tot_stats->ustats.inpps,
- tot_stats->ustats.outpps,
- tot_stats->ustats.inbps,
- tot_stats->ustats.outbps);
- spin_unlock_bh(&tot_stats->lock);
+ rates.cps,
+ rates.inpps,
+ rates.outpps,
+ rates.inbps,
+ rates.outbps);
return 0;
}
diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c
index a850087..fda75be 100644
--- a/net/netfilter/ipvs/ip_vs_est.c
+++ b/net/netfilter/ipvs/ip_vs_est.c
@@ -117,27 +117,22 @@ static void estimation_timer(unsigned long arg)
rate = (n_conns - e->last_conns) << 9;
e->last_conns = n_conns;
e->cps += ((long)rate - (long)e->cps) >> 2;
- s->ustats.cps = (e->cps + 0x1FF) >> 10;
rate = (n_inpkts - e->last_inpkts) << 9;
e->last_inpkts = n_inpkts;
e->inpps += ((long)rate - (long)e->inpps) >> 2;
- s->ustats.inpps = (e->inpps + 0x1FF) >> 10;
rate = (n_outpkts - e->last_outpkts) << 9;
e->last_outpkts = n_outpkts;
e->outpps += ((long)rate - (long)e->outpps) >> 2;
- s->ustats.outpps = (e->outpps + 0x1FF) >> 10;
rate = (n_inbytes - e->last_inbytes) << 4;
e->last_inbytes = n_inbytes;
e->inbps += ((long)rate - (long)e->inbps) >> 2;
- s->ustats.inbps = (e->inbps + 0xF) >> 5;
rate = (n_outbytes - e->last_outbytes) << 4;
e->last_outbytes = n_outbytes;
e->outbps += ((long)rate - (long)e->outbps) >> 2;
- s->ustats.outbps = (e->outbps + 0xF) >> 5;
spin_unlock(&s->lock);
}
spin_unlock(&ipvs->est_lock);
@@ -151,21 +146,6 @@ void ip_vs_new_estimator(struct net *net, struct ip_vs_stats *stats)
INIT_LIST_HEAD(&est->list);
- est->last_conns = stats->ustats.conns;
- est->cps = stats->ustats.cps<<10;
-
- est->last_inpkts = stats->ustats.inpkts;
- est->inpps = stats->ustats.inpps<<10;
-
- est->last_outpkts = stats->ustats.outpkts;
- est->outpps = stats->ustats.outpps<<10;
-
- est->last_inbytes = stats->ustats.inbytes;
- est->inbps = stats->ustats.inbps<<5;
-
- est->last_outbytes = stats->ustats.outbytes;
- est->outbps = stats->ustats.outbps<<5;
-
spin_lock_bh(&ipvs->est_lock);
list_add(&est->list, &ipvs->est_list);
spin_unlock_bh(&ipvs->est_lock);
@@ -199,6 +179,19 @@ void ip_vs_zero_estimator(struct ip_vs_stats *stats)
est->outbps = 0;
}
+/* Get decoded rates */
+void ip_vs_read_estimator(struct ip_vs_stats_user *dst,
+ struct ip_vs_stats *stats)
+{
+ struct ip_vs_estimator *e = &stats->est;
+
+ dst->cps = (e->cps + 0x1FF) >> 10;
+ dst->inpps = (e->inpps + 0x1FF) >> 10;
+ dst->outpps = (e->outpps + 0x1FF) >> 10;
+ dst->inbps = (e->inbps + 0xF) >> 5;
+ dst->outbps = (e->outbps + 0xF) >> 5;
+}
+
static int __net_init __ip_vs_estimator_init(struct net *net)
{
struct netns_ipvs *ipvs = net_ipvs(net);
--
1.7.2.3
^ permalink raw reply related
* [PATCH 05/24] ipvs: move struct netns_ipvs
From: Simon Horman @ 2011-03-15 5:27 UTC (permalink / raw)
To: netdev, netfilter-devel, netfilter, lvs-devel
Cc: Eric Dumazet, Julian Anastasov, Hans Schillstrom, Patrick McHardy,
Simon Horman
In-Reply-To: <1300166852-725-1-git-send-email-horms@verge.net.au>
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 24/24] IPVS: Conditionally include sysctl members of struct netns_ipvs
From: Simon Horman @ 2011-03-15 5:27 UTC (permalink / raw)
To: netdev, netfilter-devel, netfilter, lvs-devel
Cc: Eric Dumazet, Julian Anastasov, Hans Schillstrom, Patrick McHardy,
Simon Horman
In-Reply-To: <1300166852-725-1-git-send-email-horms@verge.net.au>
There is now no need to include sysctl members of struct netns_ipvs
unless CONFIG_SYSCTL is defined.
Signed-off-by: Simon Horman <horms@verge.net.au>
---
include/net/ip_vs.h | 21 +++++++++++++--------
1 files changed, 13 insertions(+), 8 deletions(-)
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 299aeb5..272f593 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -839,6 +839,17 @@ struct netns_ipvs {
struct ip_vs_stats tot_stats; /* Statistics & est. */
int num_services; /* no of virtual services */
+
+ 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;
+
+#ifdef CONFIG_SYSCTL
/* 1/rate drop and drop-entry variables */
struct delayed_work defense_work; /* Work handler */
int drop_rate;
@@ -848,18 +859,12 @@ struct netns_ipvs {
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;
+#endif
+
/* sysctl variables */
int sysctl_amemthresh;
int sysctl_am_droprate;
--
1.7.2.3
^ permalink raw reply related
* [PATCH 16/24] IPVS: Add sysctl_expire_nodest_conn()
From: Simon Horman @ 2011-03-15 5:27 UTC (permalink / raw)
To: netdev, netfilter-devel, netfilter, lvs-devel
Cc: Eric Dumazet, Julian Anastasov, Hans Schillstrom, Patrick McHardy,
Simon Horman
In-Reply-To: <1300166852-725-1-git-send-email-horms@verge.net.au>
In preparation for not including sysctl_expire_nodest_conn 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 | 8 +++++++-
1 files changed, 7 insertions(+), 1 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 6a0053d..d418bc6 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -613,10 +613,16 @@ static int sysctl_nat_icmp_send(struct net *net)
return ipvs->sysctl_nat_icmp_send;
}
+static int sysctl_expire_nodest_conn(struct netns_ipvs *ipvs)
+{
+ return ipvs->sysctl_expire_nodest_conn;
+}
+
#else
static int sysctl_snat_reroute(struct sk_buff *skb) { return 0; }
static int sysctl_nat_icmp_send(struct net *net) { return 0; }
+static int sysctl_expire_nodest_conn(struct netns_ipvs *ipvs) { return 0; }
#endif
@@ -1583,7 +1589,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) {
/* the destination server is not available */
- if (ipvs->sysctl_expire_nodest_conn) {
+ if (sysctl_expire_nodest_conn(ipvs)) {
/* try to expire the connection immediately */
ip_vs_conn_expire_now(cp);
}
--
1.7.2.3
^ permalink raw reply related
* [PATCH 21/24] IPVS: Minimise ip_vs_leave when CONFIG_SYSCTL is undefined
From: Simon Horman @ 2011-03-15 5:27 UTC (permalink / raw)
To: netdev, netfilter-devel, netfilter, lvs-devel
Cc: Eric Dumazet, Julian Anastasov, Hans Schillstrom, Patrick McHardy,
Simon Horman
In-Reply-To: <1300166852-725-1-git-send-email-horms@verge.net.au>
Much of ip_vs_leave() is unnecessary if CONFIG_SYSCTL is undefined.
I tried an approach of breaking the now #ifdef'ed portions out
into a separate function. However this appeared to grow the
compiled code on x86_64 by about 200 bytes in the case where
CONFIG_SYSCTL is defined. So I have gone with the simpler though
less elegant #ifdef'ed solution for now.
Signed-off-by: Simon Horman <horms@verge.net.au>
---
net/netfilter/ipvs/ip_vs_core.c | 9 +++++++--
1 files changed, 7 insertions(+), 2 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index d418bc6..07accf6 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -499,11 +499,13 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb,
int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
struct ip_vs_proto_data *pd)
{
- struct net *net;
- struct netns_ipvs *ipvs;
__be16 _ports[2], *pptr;
struct ip_vs_iphdr iph;
+#ifdef CONFIG_SYSCTL
+ struct net *net;
+ struct netns_ipvs *ipvs;
int unicast;
+#endif
ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph);
@@ -512,6 +514,8 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
ip_vs_service_put(svc);
return NF_DROP;
}
+
+#ifdef CONFIG_SYSCTL
net = skb_net(skb);
#ifdef CONFIG_IP_VS_IPV6
@@ -563,6 +567,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
ip_vs_conn_put(cp);
return ret;
}
+#endif
/*
* When the virtual ftp service is presented, packets destined
--
1.7.2.3
^ permalink raw reply related
* [PATCH] smsc911x: Fix build error when SMSC_TRACE() used
From: Jeongtae Park @ 2011-03-15 5:16 UTC (permalink / raw)
To: Jeongtae Park, netdev; +Cc: Jeongtae Park, Steve Glendinning, Denis Kirjanov
This patch fixes build error when SMSC_TRACE() used.
Signed-off-by: Jeongtae Park <jtp.park@samsung.com>
Cc: Steve Glendinning <steve.glendinning@smsc.com>
Cc: Denis Kirjanov <kirjanov@gmail.com>
---
drivers/net/smsc911x.c | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/smsc911x.c b/drivers/net/smsc911x.c
index 64bfdae..abf4482 100644
--- a/drivers/net/smsc911x.c
+++ b/drivers/net/smsc911x.c
@@ -791,8 +791,8 @@ static int smsc911x_mii_probe(struct net_device *dev)
return -ENODEV;
}
- SMSC_TRACE(PROBE, "PHY %d: addr %d, phy_id 0x%08X",
- phy_addr, phydev->addr, phydev->phy_id);
+ SMSC_TRACE(PROBE, "PHY: addr %d, phy_id 0x%08X",
+ phydev->addr, phydev->phy_id);
ret = phy_connect_direct(dev, phydev,
&smsc911x_phy_adjust_link, 0,
--
1.7.1
^ permalink raw reply related
* [net-next-2.6 0/2][pull request] Intel Wired LAN Driver Update
From: Jeff Kirsher @ 2011-03-15 5:54 UTC (permalink / raw)
To: davem; +Cc: Jeff Kirsher, netdev, gospo, bphilips
The following series contains a fix for timestamping and the
addition of thermal sensor support for igb.
The following are changes since commit 0c0217b016ba8a970a6f6ab62ad0d858f39881ca:
net: dcbnl: Add IEEE app selector value definitions
and are available in the git repository at:
master.kernel.org:/pub/scm/linux/kernel/git/jkirsher/net-next-2.6 master
Anders Berggren (1):
igb: fix hw timestamping
Carolyn Wyborny (1):
igb: Add messaging for thermal sensor events on i350 devices
drivers/net/igb/e1000_defines.h | 5 ++++
drivers/net/igb/e1000_regs.h | 3 ++
drivers/net/igb/igb_main.c | 42 +++++++++++++++++++++++++++++++++++++-
3 files changed, 48 insertions(+), 2 deletions(-)
--
1.7.4
^ permalink raw reply
* [net-next-2.6 1/2] igb: fix hw timestamping
From: Jeff Kirsher @ 2011-03-15 5:54 UTC (permalink / raw)
To: davem
Cc: Anders Berggren, netdev, gospo, bphilips, Anders Berggren,
Jeff Kirsher
In-Reply-To: <1300168464-29546-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Anders Berggren <anders@halon.se>
Hardware timestamping for Intel 82580 didn't work in either 2.6.36 or
2.6.37. Comparing it to Intel's igb-2.4.12 I found that the
timecounter_init clock/counter initialization was done too early.
Signed-off-by: Anders Berggren <andfers@halon.se>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/igb/igb_main.c | 5 ++++-
1 files changed, 4 insertions(+), 1 deletions(-)
diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index b4f92b0..5366f2a 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -106,6 +106,7 @@ static void igb_free_all_rx_resources(struct igb_adapter *);
static void igb_setup_mrqc(struct igb_adapter *);
static int igb_probe(struct pci_dev *, const struct pci_device_id *);
static void __devexit igb_remove(struct pci_dev *pdev);
+static void igb_init_hw_timer(struct igb_adapter *adapter);
static int igb_sw_init(struct igb_adapter *);
static int igb_open(struct net_device *);
static int igb_close(struct net_device *);
@@ -2048,6 +2049,9 @@ static int __devinit igb_probe(struct pci_dev *pdev,
}
#endif
+ /* do hw tstamp init after resetting */
+ igb_init_hw_timer(adapter);
+
dev_info(&pdev->dev, "Intel(R) Gigabit Ethernet Network Connection\n");
/* print bus type/speed/width info */
dev_info(&pdev->dev, "%s: (PCIe:%s:%s) %pM\n",
@@ -2384,7 +2388,6 @@ static int __devinit igb_sw_init(struct igb_adapter *adapter)
return -ENOMEM;
}
- igb_init_hw_timer(adapter);
igb_probe_vfs(adapter);
/* Explicitly disable IRQ since the NIC can be in any state. */
--
1.7.4
^ permalink raw reply related
* [net-next-2.6 2/2] igb: Add messaging for thermal sensor events on i350 devices
From: Jeff Kirsher @ 2011-03-15 5:54 UTC (permalink / raw)
To: davem; +Cc: Carolyn Wyborny, netdev, gospo, bphilips, Jeff Kirsher
In-Reply-To: <1300168464-29546-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Carolyn Wyborny <carolyn.wyborny@intel.com>
This feature adds messaging to the link status change to notify
the user if the device returned from a downshift or power off
event due to the Thermal Sensor feature in i350 parts. Feature
is only available on internal copper ports.
Signed-off-by: Carolyn Wyborny <carolyn.wyborny@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/igb/e1000_defines.h | 5 +++++
drivers/net/igb/e1000_regs.h | 3 +++
drivers/net/igb/igb_main.c | 37 ++++++++++++++++++++++++++++++++++++-
3 files changed, 44 insertions(+), 1 deletions(-)
diff --git a/drivers/net/igb/e1000_defines.h b/drivers/net/igb/e1000_defines.h
index 9bb1928..6b80d40 100644
--- a/drivers/net/igb/e1000_defines.h
+++ b/drivers/net/igb/e1000_defines.h
@@ -51,6 +51,7 @@
#define E1000_CTRL_EXT_LINK_MODE_PCIE_SERDES 0x00C00000
#define E1000_CTRL_EXT_LINK_MODE_1000BASE_KX 0x00400000
#define E1000_CTRL_EXT_LINK_MODE_SGMII 0x00800000
+#define E1000_CTRL_EXT_LINK_MODE_GMII 0x00000000
#define E1000_CTRL_EXT_EIAME 0x01000000
#define E1000_CTRL_EXT_IRCA 0x00000001
/* Interrupt delay cancellation */
@@ -788,6 +789,10 @@
#define E1000_MDIC_ERROR 0x40000000
#define E1000_MDIC_DEST 0x80000000
+/* Thermal Sensor */
+#define E1000_THSTAT_PWR_DOWN 0x00000001 /* Power Down Event */
+#define E1000_THSTAT_LINK_THROTTLE 0x00000002 /* Link Speed Throttle Event */
+
/* Energy Efficient Ethernet */
#define E1000_IPCNFG_EEE_1G_AN 0x00000008 /* EEE Enable 1G AN */
#define E1000_IPCNFG_EEE_100M_AN 0x00000004 /* EEE Enable 100M AN */
diff --git a/drivers/net/igb/e1000_regs.h b/drivers/net/igb/e1000_regs.h
index ad77ed5..958ca3b 100644
--- a/drivers/net/igb/e1000_regs.h
+++ b/drivers/net/igb/e1000_regs.h
@@ -342,6 +342,9 @@
#define E1000_IPCNFG 0x0E38 /* Internal PHY Configuration */
#define E1000_EEER 0x0E30 /* Energy Efficient Ethernet */
+/* Thermal Sensor Register */
+#define E1000_THSTAT 0x08110 /* Thermal Sensor Status */
+
/* OS2BMC Registers */
#define E1000_B2OSPC 0x08FE0 /* BMC2OS packets sent by BMC */
#define E1000_B2OGPRC 0x04158 /* BMC2OS packets received by host */
diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index 5366f2a..3d850af 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -3550,7 +3550,7 @@ static void igb_watchdog_task(struct work_struct *work)
watchdog_task);
struct e1000_hw *hw = &adapter->hw;
struct net_device *netdev = adapter->netdev;
- u32 link;
+ u32 link, ctrl_ext, thstat;
int i;
link = igb_has_link(adapter);
@@ -3574,6 +3574,25 @@ static void igb_watchdog_task(struct work_struct *work)
((ctrl & E1000_CTRL_RFCE) ? "RX" :
((ctrl & E1000_CTRL_TFCE) ? "TX" : "None")));
+ /* check for thermal sensor event on i350,
+ * copper only */
+ if (hw->mac.type == e1000_i350) {
+ thstat = rd32(E1000_THSTAT);
+ ctrl_ext = rd32(E1000_CTRL_EXT);
+ if ((hw->phy.media_type ==
+ e1000_media_type_copper) && !(ctrl_ext &
+ E1000_CTRL_EXT_LINK_MODE_SGMII)) {
+ if (thstat &
+ E1000_THSTAT_LINK_THROTTLE) {
+ printk(KERN_INFO "igb: %s The "
+ "network adapter link "
+ "speed was downshifted "
+ "because it "
+ "overheated.\n",
+ netdev->name);
+ }
+ }
+ }
/* adjust timeout factor according to speed/duplex */
adapter->tx_timeout_factor = 1;
switch (adapter->link_speed) {
@@ -3599,6 +3618,22 @@ static void igb_watchdog_task(struct work_struct *work)
if (netif_carrier_ok(netdev)) {
adapter->link_speed = 0;
adapter->link_duplex = 0;
+ /* check for thermal sensor event on i350
+ * copper only*/
+ if (hw->mac.type == e1000_i350) {
+ thstat = rd32(E1000_THSTAT);
+ ctrl_ext = rd32(E1000_CTRL_EXT);
+ if ((hw->phy.media_type ==
+ e1000_media_type_copper) && !(ctrl_ext &
+ E1000_CTRL_EXT_LINK_MODE_SGMII)) {
+ if (thstat & E1000_THSTAT_PWR_DOWN) {
+ printk(KERN_ERR "igb: %s The "
+ "network adapter was stopped "
+ "because it overheated.\n",
+ netdev->name);
+ }
+ }
+ }
/* Links status message must follow this format */
printk(KERN_INFO "igb: %s NIC Link is Down\n",
netdev->name);
--
1.7.4
^ permalink raw reply related
* Re: ECN + pfifo_fast borked? (Was Re: [Bloat] shaper team forming up)
From: Eric Dumazet @ 2011-03-15 6:15 UTC (permalink / raw)
To: Dave Täht; +Cc: Jonathan Morton, David Miller, netdev
In-Reply-To: <87ipvlosvz.fsf_-_@cruithne.co.teklibre.org>
Le lundi 14 mars 2011 à 23:27 -0600, Dave Täht a écrit :
> Well, that makes 3 of us that think it's wrong. Can we get more?
>
> (I'll run through the math again in the morning)
>
> It's most often not actually "enablement" but "assertion", when for
> example an ECN bit is put on an ACK packet (by an application, or qdisc)
> , it drops that ACK packet into the 2 queue - leaving all the other
> non-ECN asserted packets in that flow to flow out ahead of it.
>
There are two ECN bits, not one.
The low order bit is not taken into account by skb->priority mapping.
The high order bit cannot be changed during flow lifetime.
(So : no OOO (Out Of Order) problems on say TCP flows)
> Or so dan siemon & I & now you, think. It's late and I really want to recheck
> the math and the shifts in the morning. However, if true... this would
> explain much ECN related weirdness precisely where it has been hard to
> measure, on heavily loaded systems.
>
> >
> > Thanks
> >
> > diff --git a/net/ipv4/route.c b/net/ipv4/route.c
> > index 6ed6603..fabfe81 100644
> > --- a/net/ipv4/route.c
> > +++ b/net/ipv4/route.c
> > @@ -171,7 +171,7 @@ static struct dst_ops ipv4_dst_ops = {
> >
> > const __u8 ip_tos2prio[16] = {
> > TC_PRIO_BESTEFFORT,
> > - ECN_OR_COST(FILLER),
> > + ECN_OR_COST(BESTEFFORT),
> > TC_PRIO_BESTEFFORT,
> > ECN_OR_COST(BESTEFFORT),
> > TC_PRIO_BULK,
> >
>
> I think this is a good short term fix, but it will mildly upset people
> that actually still use minimum cost and don't use ECN. That said,
> RFC1349 has been obsolete for a decade now, and ECN enabled servers are
> at 12% penetration according to MIT.
>
If minimum cost was asked by people, their packets had chance being
dropped. Why should they be upset ?
ECN should be favored anyway in 2011, now everybody is ready.
> Still, long term, doing a sch_pfifo_dscp that would be fully compliant
> with the relevant modern RFCs and eventually making that the standard
> would be good.
>
sch_pfifo_fast is not the place we perform the TOS -> priority mapping.
Its done in another layer.
That is of litle effect, given TOS values are meaningfull only inside a
domain. Nobody can force everyone to use same semantics on the Internet,
even with a standard RFC. I doubt people using linux machines at home
really need DSCP at all.
What we could do instead is to favor a bit ECN enabled connections,
using 4 bands instead of 3 for pfifo_fast (linux default qdisc, probably
the most used qdisc)
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)
Note : pfifo_fast is mostly used on end hosts, not on routers (where
admins setup non default qdiscs), and typical end hosts never experiment
packet drops on their qdiscs, because they are now plugged to Gigabit
LANS, and device queuelength is so big.
^ permalink raw reply
* Re: linux-next: build failure after merge of the net tree
From: Stephen Rothwell @ 2011-03-15 6:25 UTC (permalink / raw)
To: David Miller
Cc: tglx, bhutchings, netdev, linux-next, linux-kernel, mingo, hpa,
peterz
In-Reply-To: <20110314.210712.226761233.davem@davemloft.net>
[-- Attachment #1: Type: text/plain, Size: 1152 bytes --]
Hi Dave,
On Mon, 14 Mar 2011 21:07:12 -0700 (PDT) David Miller <davem@davemloft.net> wrote:
>
> From: Stephen Rothwell <sfr@canb.auug.org.au>
> Date: Tue, 15 Mar 2011 11:30:49 +1100
>
> > So, if you merge the commit 1fb0ef31f428 ("genirq: Fix affinity notifier
> > fallout") from the tip tree, you will get exactly one new commit and will
> > fix your tree properly with no adverse effect on anyone else.
>
> Thomas, how would you like me to do this? Do you want to put that
> commit on a branch for me to pull from or should I apply it
> directly?
That commit is already the head of the irq/numa branch in the tip tree
(it is also on the irq/core branch).
Please merge that rather than cherry-picking the commit as that will
minimise the possibility of conflicts. Pulling the irq/numa branch will
get you just that one fixup commit (as you have already merged up to the
immediately preceding commit).
I assume this makes sense, Thomas? I just did a merge of the actual
fixup commit after merging the net tree.
--
Cheers,
Stephen Rothwell sfr@canb.auug.org.au
http://www.canb.auug.org.au/~sfr/
[-- Attachment #2: Type: application/pgp-signature, Size: 490 bytes --]
^ permalink raw reply
* [PATCHv2 NEXT 0/1]nexten: bug fixes
From: Amit Kumar Salecha @ 2011-03-15 6:52 UTC (permalink / raw)
To: davem; +Cc: netdev, ameen.rahman, anirban.chakraborty
Hi
Sending you revised patch, removing all prints.
Apply this on net-next.
Thanks
-Amit
^ permalink raw reply
* [PATCHv2 NEXT 1/1] netxen: support for GbE port settings
From: Amit Kumar Salecha @ 2011-03-15 6:56 UTC (permalink / raw)
To: davem; +Cc: netdev, ameen.rahman, anirban.chakraborty, Sony Chacko
From: Sony Chacko <sony.chacko@qlogic.com>
o Enable setting speed and auto negotiation parameters for GbE ports.
o Hardware do not support half duplex setting currently.
David Miller:
Amit please update your patch to silently reject link setting
attempts that are unsupported by the device.
Signed-off-by: Sony Chacko <sony.chacko@qlogic.com>
Signed-off-by: Amit Kumar Salecha <amit.salecha@qlogic.com>
---
drivers/net/netxen/netxen_nic.h | 6 ++-
drivers/net/netxen/netxen_nic_ctx.c | 15 +++++++
drivers/net/netxen/netxen_nic_ethtool.c | 62 ++++++++-----------------------
3 files changed, 36 insertions(+), 47 deletions(-)
diff --git a/drivers/net/netxen/netxen_nic.h b/drivers/net/netxen/netxen_nic.h
index a113805..d7299f1 100644
--- a/drivers/net/netxen/netxen_nic.h
+++ b/drivers/net/netxen/netxen_nic.h
@@ -739,7 +739,8 @@ struct netxen_recv_context {
#define NX_CDRP_CMD_READ_PEXQ_PARAMETERS 0x0000001c
#define NX_CDRP_CMD_GET_LIC_CAPABILITIES 0x0000001d
#define NX_CDRP_CMD_READ_MAX_LRO_PER_BOARD 0x0000001e
-#define NX_CDRP_CMD_MAX 0x0000001f
+#define NX_CDRP_CMD_CONFIG_GBE_PORT 0x0000001f
+#define NX_CDRP_CMD_MAX 0x00000020
#define NX_RCODE_SUCCESS 0
#define NX_RCODE_NO_HOST_MEM 1
@@ -1054,6 +1055,7 @@ typedef struct {
#define NX_FW_CAPABILITY_BDG (1 << 8)
#define NX_FW_CAPABILITY_FVLANTX (1 << 9)
#define NX_FW_CAPABILITY_HW_LRO (1 << 10)
+#define NX_FW_CAPABILITY_GBE_LINK_CFG (1 << 11)
/* module types */
#define LINKEVENT_MODULE_NOT_PRESENT 1
@@ -1349,6 +1351,8 @@ void netxen_advert_link_change(struct netxen_adapter *adapter, int linkup);
void netxen_pci_camqm_read_2M(struct netxen_adapter *, u64, u64 *);
void netxen_pci_camqm_write_2M(struct netxen_adapter *, u64, u64);
+int nx_fw_cmd_set_gbe_port(struct netxen_adapter *adapter,
+ u32 speed, u32 duplex, u32 autoneg);
int nx_fw_cmd_set_mtu(struct netxen_adapter *adapter, int mtu);
int netxen_nic_change_mtu(struct net_device *netdev, int new_mtu);
int netxen_config_hw_lro(struct netxen_adapter *adapter, int enable);
diff --git a/drivers/net/netxen/netxen_nic_ctx.c b/drivers/net/netxen/netxen_nic_ctx.c
index f7d06cb..f16966a 100644
--- a/drivers/net/netxen/netxen_nic_ctx.c
+++ b/drivers/net/netxen/netxen_nic_ctx.c
@@ -112,6 +112,21 @@ nx_fw_cmd_set_mtu(struct netxen_adapter *adapter, int mtu)
return 0;
}
+int
+nx_fw_cmd_set_gbe_port(struct netxen_adapter *adapter,
+ u32 speed, u32 duplex, u32 autoneg)
+{
+
+ return netxen_issue_cmd(adapter,
+ adapter->ahw.pci_func,
+ NXHAL_VERSION,
+ speed,
+ duplex,
+ autoneg,
+ NX_CDRP_CMD_CONFIG_GBE_PORT);
+
+}
+
static int
nx_fw_cmd_create_rx_ctx(struct netxen_adapter *adapter)
{
diff --git a/drivers/net/netxen/netxen_nic_ethtool.c b/drivers/net/netxen/netxen_nic_ethtool.c
index 587498e..653d308 100644
--- a/drivers/net/netxen/netxen_nic_ethtool.c
+++ b/drivers/net/netxen/netxen_nic_ethtool.c
@@ -214,7 +214,6 @@ skip:
check_sfp_module = netif_running(dev) &&
adapter->has_link_events;
} else {
- ecmd->autoneg = AUTONEG_ENABLE;
ecmd->supported |= (SUPPORTED_TP |SUPPORTED_Autoneg);
ecmd->advertising |=
(ADVERTISED_TP | ADVERTISED_Autoneg);
@@ -252,53 +251,24 @@ static int
netxen_nic_set_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
{
struct netxen_adapter *adapter = netdev_priv(dev);
- __u32 status;
+ int ret;
- /* read which mode */
- if (adapter->ahw.port_type == NETXEN_NIC_GBE) {
- /* autonegotiation */
- if (adapter->phy_write &&
- adapter->phy_write(adapter,
- NETXEN_NIU_GB_MII_MGMT_ADDR_AUTONEG,
- ecmd->autoneg) != 0)
- return -EIO;
- else
- adapter->link_autoneg = ecmd->autoneg;
+ if (adapter->ahw.port_type != NETXEN_NIC_GBE)
+ return -EOPNOTSUPP;
- if (adapter->phy_read &&
- adapter->phy_read(adapter,
- NETXEN_NIU_GB_MII_MGMT_ADDR_PHY_STATUS,
- &status) != 0)
- return -EIO;
+ if (!(adapter->capabilities & NX_FW_CAPABILITY_GBE_LINK_CFG))
+ return -EOPNOTSUPP;
- /* speed */
- switch (ecmd->speed) {
- case SPEED_10:
- netxen_set_phy_speed(status, 0);
- break;
- case SPEED_100:
- netxen_set_phy_speed(status, 1);
- break;
- case SPEED_1000:
- netxen_set_phy_speed(status, 2);
- break;
- }
- /* set duplex mode */
- if (ecmd->duplex == DUPLEX_HALF)
- netxen_clear_phy_duplex(status);
- if (ecmd->duplex == DUPLEX_FULL)
- netxen_set_phy_duplex(status);
- if (adapter->phy_write &&
- adapter->phy_write(adapter,
- NETXEN_NIU_GB_MII_MGMT_ADDR_PHY_STATUS,
- *((int *)&status)) != 0)
- return -EIO;
- else {
- adapter->link_speed = ecmd->speed;
- adapter->link_duplex = ecmd->duplex;
- }
- } else
+ ret = nx_fw_cmd_set_gbe_port(adapter, ecmd->speed, ecmd->duplex,
+ ecmd->autoneg);
+ if (ret == NX_RCODE_NOT_SUPPORTED)
return -EOPNOTSUPP;
+ else if (ret)
+ return -EIO;
+
+ adapter->link_speed = ecmd->speed;
+ adapter->link_duplex = ecmd->duplex;
+ adapter->link_autoneg = ecmd->autoneg;
if (!netif_running(dev))
return 0;
--
1.7.3.2
^ permalink raw reply related
* [PATCHv2 NEXT 1/1] netxen: support for GbE port settings
From: Amit Kumar Salecha @ 2011-03-15 6:52 UTC (permalink / raw)
To: davem; +Cc: netdev, ameen.rahman, anirban.chakraborty, Sony Chacko
In-Reply-To: <1300171967-16576-1-git-send-email-amit.salecha@qlogic.com>
From: Sony Chacko <sony.chacko@qlogic.com>
o Enable setting speed and auto negotiation parameters for GbE ports.
o Hardware do not support half duplex setting currently.
David Miller:
Amit please update your patch to silently reject link setting
attempts that are unsupported by the device.
Signed-off-by: Sony Chacko <sony.chacko@qlogic.com>
Signed-off-by: Amit Kumar Salecha <amit.salecha@qlogic.com>
---
drivers/net/netxen/netxen_nic.h | 6 ++-
drivers/net/netxen/netxen_nic_ctx.c | 15 +++++++
drivers/net/netxen/netxen_nic_ethtool.c | 62 ++++++++-----------------------
3 files changed, 36 insertions(+), 47 deletions(-)
diff --git a/drivers/net/netxen/netxen_nic.h b/drivers/net/netxen/netxen_nic.h
index a113805..d7299f1 100644
--- a/drivers/net/netxen/netxen_nic.h
+++ b/drivers/net/netxen/netxen_nic.h
@@ -739,7 +739,8 @@ struct netxen_recv_context {
#define NX_CDRP_CMD_READ_PEXQ_PARAMETERS 0x0000001c
#define NX_CDRP_CMD_GET_LIC_CAPABILITIES 0x0000001d
#define NX_CDRP_CMD_READ_MAX_LRO_PER_BOARD 0x0000001e
-#define NX_CDRP_CMD_MAX 0x0000001f
+#define NX_CDRP_CMD_CONFIG_GBE_PORT 0x0000001f
+#define NX_CDRP_CMD_MAX 0x00000020
#define NX_RCODE_SUCCESS 0
#define NX_RCODE_NO_HOST_MEM 1
@@ -1054,6 +1055,7 @@ typedef struct {
#define NX_FW_CAPABILITY_BDG (1 << 8)
#define NX_FW_CAPABILITY_FVLANTX (1 << 9)
#define NX_FW_CAPABILITY_HW_LRO (1 << 10)
+#define NX_FW_CAPABILITY_GBE_LINK_CFG (1 << 11)
/* module types */
#define LINKEVENT_MODULE_NOT_PRESENT 1
@@ -1349,6 +1351,8 @@ void netxen_advert_link_change(struct netxen_adapter *adapter, int linkup);
void netxen_pci_camqm_read_2M(struct netxen_adapter *, u64, u64 *);
void netxen_pci_camqm_write_2M(struct netxen_adapter *, u64, u64);
+int nx_fw_cmd_set_gbe_port(struct netxen_adapter *adapter,
+ u32 speed, u32 duplex, u32 autoneg);
int nx_fw_cmd_set_mtu(struct netxen_adapter *adapter, int mtu);
int netxen_nic_change_mtu(struct net_device *netdev, int new_mtu);
int netxen_config_hw_lro(struct netxen_adapter *adapter, int enable);
diff --git a/drivers/net/netxen/netxen_nic_ctx.c b/drivers/net/netxen/netxen_nic_ctx.c
index f7d06cb..f16966a 100644
--- a/drivers/net/netxen/netxen_nic_ctx.c
+++ b/drivers/net/netxen/netxen_nic_ctx.c
@@ -112,6 +112,21 @@ nx_fw_cmd_set_mtu(struct netxen_adapter *adapter, int mtu)
return 0;
}
+int
+nx_fw_cmd_set_gbe_port(struct netxen_adapter *adapter,
+ u32 speed, u32 duplex, u32 autoneg)
+{
+
+ return netxen_issue_cmd(adapter,
+ adapter->ahw.pci_func,
+ NXHAL_VERSION,
+ speed,
+ duplex,
+ autoneg,
+ NX_CDRP_CMD_CONFIG_GBE_PORT);
+
+}
+
static int
nx_fw_cmd_create_rx_ctx(struct netxen_adapter *adapter)
{
diff --git a/drivers/net/netxen/netxen_nic_ethtool.c b/drivers/net/netxen/netxen_nic_ethtool.c
index 587498e..653d308 100644
--- a/drivers/net/netxen/netxen_nic_ethtool.c
+++ b/drivers/net/netxen/netxen_nic_ethtool.c
@@ -214,7 +214,6 @@ skip:
check_sfp_module = netif_running(dev) &&
adapter->has_link_events;
} else {
- ecmd->autoneg = AUTONEG_ENABLE;
ecmd->supported |= (SUPPORTED_TP |SUPPORTED_Autoneg);
ecmd->advertising |=
(ADVERTISED_TP | ADVERTISED_Autoneg);
@@ -252,53 +251,24 @@ static int
netxen_nic_set_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
{
struct netxen_adapter *adapter = netdev_priv(dev);
- __u32 status;
+ int ret;
- /* read which mode */
- if (adapter->ahw.port_type == NETXEN_NIC_GBE) {
- /* autonegotiation */
- if (adapter->phy_write &&
- adapter->phy_write(adapter,
- NETXEN_NIU_GB_MII_MGMT_ADDR_AUTONEG,
- ecmd->autoneg) != 0)
- return -EIO;
- else
- adapter->link_autoneg = ecmd->autoneg;
+ if (adapter->ahw.port_type != NETXEN_NIC_GBE)
+ return -EOPNOTSUPP;
- if (adapter->phy_read &&
- adapter->phy_read(adapter,
- NETXEN_NIU_GB_MII_MGMT_ADDR_PHY_STATUS,
- &status) != 0)
- return -EIO;
+ if (!(adapter->capabilities & NX_FW_CAPABILITY_GBE_LINK_CFG))
+ return -EOPNOTSUPP;
- /* speed */
- switch (ecmd->speed) {
- case SPEED_10:
- netxen_set_phy_speed(status, 0);
- break;
- case SPEED_100:
- netxen_set_phy_speed(status, 1);
- break;
- case SPEED_1000:
- netxen_set_phy_speed(status, 2);
- break;
- }
- /* set duplex mode */
- if (ecmd->duplex == DUPLEX_HALF)
- netxen_clear_phy_duplex(status);
- if (ecmd->duplex == DUPLEX_FULL)
- netxen_set_phy_duplex(status);
- if (adapter->phy_write &&
- adapter->phy_write(adapter,
- NETXEN_NIU_GB_MII_MGMT_ADDR_PHY_STATUS,
- *((int *)&status)) != 0)
- return -EIO;
- else {
- adapter->link_speed = ecmd->speed;
- adapter->link_duplex = ecmd->duplex;
- }
- } else
+ ret = nx_fw_cmd_set_gbe_port(adapter, ecmd->speed, ecmd->duplex,
+ ecmd->autoneg);
+ if (ret == NX_RCODE_NOT_SUPPORTED)
return -EOPNOTSUPP;
+ else if (ret)
+ return -EIO;
+
+ adapter->link_speed = ecmd->speed;
+ adapter->link_duplex = ecmd->duplex;
+ adapter->link_autoneg = ecmd->autoneg;
if (!netif_running(dev))
return 0;
--
1.7.3.2
^ permalink raw reply related
* Re: [GIT/PATCH v5] xen network backend driver
From: Ian Campbell @ 2011-03-15 7:09 UTC (permalink / raw)
To: David Miller
Cc: bhutchings@solarflare.com, netdev@vger.kernel.org,
xen-devel@lists.xensource.com, jeremy@goop.org,
herbert@gondor.apana.org.au, konrad.wilk@oracle.com,
romieu@fr.zoreil.com, shemminger@vyatta.com, mirqus@gmail.com
In-Reply-To: <20110314.152255.68135182.davem@davemloft.net>
On Mon, 2011-03-14 at 22:22 +0000, David Miller wrote:
> From: Ian Campbell <Ian.Campbell@eu.citrix.com>
> Date: Mon, 14 Mar 2011 22:17:40 +0000
>
> > Would you consider a commit patch which imports the baseline driver as
> > is from xen.git (this builds and is functional but needed clean up)
> > followed by the cleanup series? I made sure the cleanup part builds and
> > works at each step as I went (but I will run through it again to be
> > sure).
> >
> > There is real value (to me at least) in keeping the cleanup separate and
> > being able to (even manually) associate the first upstream commit with
> > an equivalent point in the historical code.
>
> Do you have any idea what that thing is going to do for poor souls trying
> to bisect?
>
> GIT is going to hop in and out of your line of development for any GIT
> bisect that traverses any period of time in which those driver commits
> exists.
>
> It's too messy.
It's exactly the same as any other patch series in this respect though,
isn't it?
But... I'd forgotten that up until "xen: netback: Make dependency on
PageForeign conditional" I was running with a local non-upstreamable
branch containing the PageForeign infrastructure merged which I removed
once I removed the PageForeign dependency was gone, so the series isn't
actually fully buildable upstream like I thought.
So I'll resend a single patch version of the driver today.
> You can keep your tree online somewhere to publish the history, just
> like we do for the old bitkeeper import and similar.
Sure.
Ian.
^ permalink raw reply
* Re: [PATCH] xen: netfront: ethtool stats fields should be unsigned long
From: Ian Campbell @ 2011-03-15 7:12 UTC (permalink / raw)
To: David Miller
Cc: eric.dumazet@gmail.com, netdev@vger.kernel.org, jeremy@goop.org,
bhutchings@solarflare.com
In-Reply-To: <20110314.210615.193717284.davem@davemloft.net>
On Tue, 2011-03-15 at 04:06 +0000, David Miller wrote:
> From: Eric Dumazet <eric.dumazet@gmail.com>
> Date: Tue, 15 Mar 2011 04:50:43 +0100
>
> > Le lundi 14 mars 2011 à 15:10 -0700, David Miller a écrit :
> >> From: Ian Campbell <ian.campbell@citrix.com>
> >> Date: Thu, 10 Mar 2011 17:04:18 +0000
> >>
> >> > Fixup the rx_gso_checksum_fixup field added in e0ce4af920eb to be
> >> > unsigned long as suggested by Ben Hutchings in
> >> > <1298919198.2569.14.camel@bwh-desktop>
> >> >
> >> > Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
> >>
> >> Applied, thanks Ian.
> >
> > Hmm, this needs this followup patch then.
> >
> > Thanks
> >
> > [PATCH] xen: netfront: fix xennet_get_ethtool_stats()
> >
> > commit e9a799ea4a5551d2 (xen: netfront: ethtool stats fields should be
> > unsigned long) made rx_gso_checksum_fixup an unsigned long.
> >
> > Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
>
> I even saw your feedback but for some reason I still applied
> his patch, sorry about that :-)
>
> Applied, thanks.
His feed back was for netback and this was a netfront patch, but I
didn't make the link either.
Thanks for picking it up Eric.
Ian.
^ permalink raw reply
* Re: [GIT] Networking
From: david @ 2011-03-15 7:20 UTC (permalink / raw)
To: Steven Rostedt
Cc: J. Bruce Fields, Ben Hutchings, David Miller, torvalds, akpm,
netdev, linux-kernel
In-Reply-To: <20110312040941.GA15526@home.goodmis.org>
On Fri, 11 Mar 2011, Steven Rostedt wrote:
> On Fri, Mar 11, 2011 at 04:42:09PM -0500, J. Bruce Fields wrote:
>>
>> But assume you only did this in cases where the merge was trivial.
>> Would it be worth it, or would people be annoyed by the additional
>> branching?
>>
>
> I would be annoyed by it ;)
>
> It really is meaningless to do so, as all you are doing is documenting
> what commit caused this bug, and producing more problems by branching
> off of the broken commit. It wont matter till it is merged, but then if
> there are a lot of simple bug fixes, then you will have a lot of single
> merges of branches that fix those bugs.
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.
David Lang
> It's just better to say in the change log of the fix:
>
> "commit abcdef1234 foo: add bar"
>
> Broke this, and this fixes it.
>
> Having the broken commit SHA1 and description in the change log is just
> as helpful as having the bug commit being its parent.
>
> -- Steve
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
>
^ permalink raw reply
* Re: sky2, vlan and nat/masquerading
From: Christian Hesse @ 2011-03-15 7:53 UTC (permalink / raw)
To: Jesse Gross; +Cc: netdev
In-Reply-To: <AANLkTikXBz6ZpuSgqaAV-=Jr3qtDQ3T_We42R65Sd20O@mail.gmail.com>
[-- Attachment #1: Type: text/plain, Size: 1805 bytes --]
On Mon, 14 Mar 2011 18:55:17 -0700 Jesse Gross <jesse@nicira.com> wrote:
> On Mon, Mar 14, 2011 at 3:11 AM, Christian Hesse <mail@eworm.de> wrote:
> > Ok, let me explain step by step:
>
> Thank you, this helps a lot in understanding your setup.
>
> >
> > * Host sends icmp echo request (172.16.0.21 -> 192.168.100.3) to router
> > 172.16.0.1, the packet is untagged.
> > * Switch receives the packet on native interface with vid 2, tags it and
> > sends it to the trunk)
> > * Netbook receives the packet from trunk, untags it an queues it to vlan
> > interface 2.
> > * Netbook nats the packet (192.168.x.140 > 192.168.100.3), tags it with
> > vlan 2 and sends it to the trunk.
>
> For clarity, I'm assuming that this is supposed to be vlan 1?
Sorry, little typo. Yes, you are right.
> > * Switch receives the packet from trunk, untags it and sends it to native
> > interface with vlan 1.
> > * The packet and its answer (192.168.100.3 -> 192.168.x.140) make their
> > way through the network.
> > * Switch receives the icmp echo reply on native interface with vlan 1,
> > tags it and sends it to the trunk
> > * Netbook receives the packet from trunk, untags it an queues it to vlan
> > interface 1.
> > * Netbooks restores the original addresses from nat (192.168.100.3 ->
> > 172.16.0.21), _tags_it_with_vlan_0_, tags it with vlan 2 and sends it to
> > the trunk
>
> Can you capture a packet trace on the netbook's Ethernet interface to
> see what it thinks it is sending?
Ok, I have two traces for you: from the vlan interface and from the native
interface. First ping to 172.16.0.65 is ok, second one to 192.168.100.3 fails.
Please don't be confused, vlan 1 is vlan 3 this time and addresses
changed a little bit. ;)
--
Schoene Gruesse
Chris
[-- Attachment #2: tcpdump-eth.2.log --]
[-- Type: application/octet-stream, Size: 480 bytes --]
[-- Attachment #3: tcpdump-eth.log --]
[-- Type: application/octet-stream, Size: 740 bytes --]
^ 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