* [PATCH V4 1/7] ipvs: Trivial changes, use compressed IPv6 address in output
From: Jesper Dangaard Brouer @ 2012-09-26 12:05 UTC (permalink / raw)
To: Hans Schillstrom, Hans Schillstrom, netdev, Pablo Neira Ayuso,
lvs-devel, Julian Anastasov
Cc: Jesper Dangaard Brouer, Patrick McHardy, Thomas Graf,
Wensong Zhang, netfilter-devel, Simon Horman
In-Reply-To: <20120926120534.24804.78415.stgit@dragon>
Have not converted the proc file output to compressed IPv6 addresses.
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
---
include/net/ip_vs.h | 2 +-
net/netfilter/ipvs/ip_vs_core.c | 2 +-
net/netfilter/ipvs/ip_vs_proto.c | 6 +++---
net/netfilter/ipvs/ip_vs_sched.c | 2 +-
net/netfilter/ipvs/ip_vs_xmit.c | 10 +++++-----
5 files changed, 11 insertions(+), 11 deletions(-)
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index ee75ccd..aba0bb2 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -165,7 +165,7 @@ static inline const char *ip_vs_dbg_addr(int af, char *buf, size_t buf_len,
int len;
#ifdef CONFIG_IP_VS_IPV6
if (af == AF_INET6)
- len = snprintf(&buf[*idx], buf_len - *idx, "[%pI6]",
+ len = snprintf(&buf[*idx], buf_len - *idx, "[%pI6c]",
&addr->in6) + 1;
else
#endif
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 58918e2..4edb654 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1487,7 +1487,7 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum)
if (ic == NULL)
return NF_DROP;
- IP_VS_DBG(12, "Incoming ICMPv6 (%d,%d) %pI6->%pI6\n",
+ IP_VS_DBG(12, "Incoming ICMPv6 (%d,%d) %pI6c->%pI6c\n",
ic->icmp6_type, ntohs(icmpv6_id(ic)),
&iph->saddr, &iph->daddr);
diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c
index 50d8218..939f7fb 100644
--- a/net/netfilter/ipvs/ip_vs_proto.c
+++ b/net/netfilter/ipvs/ip_vs_proto.c
@@ -280,17 +280,17 @@ ip_vs_tcpudp_debug_packet_v6(struct ip_vs_protocol *pp,
if (ih == NULL)
sprintf(buf, "TRUNCATED");
else if (ih->nexthdr == IPPROTO_FRAGMENT)
- sprintf(buf, "%pI6->%pI6 frag", &ih->saddr, &ih->daddr);
+ sprintf(buf, "%pI6c->%pI6c frag", &ih->saddr, &ih->daddr);
else {
__be16 _ports[2], *pptr;
pptr = skb_header_pointer(skb, offset + sizeof(struct ipv6hdr),
sizeof(_ports), _ports);
if (pptr == NULL)
- sprintf(buf, "TRUNCATED %pI6->%pI6",
+ sprintf(buf, "TRUNCATED %pI6c->%pI6c",
&ih->saddr, &ih->daddr);
else
- sprintf(buf, "%pI6:%u->%pI6:%u",
+ sprintf(buf, "%pI6c:%u->%pI6c:%u",
&ih->saddr, ntohs(pptr[0]),
&ih->daddr, ntohs(pptr[1]));
}
diff --git a/net/netfilter/ipvs/ip_vs_sched.c b/net/netfilter/ipvs/ip_vs_sched.c
index 08dbdd5..d6bf20d 100644
--- a/net/netfilter/ipvs/ip_vs_sched.c
+++ b/net/netfilter/ipvs/ip_vs_sched.c
@@ -159,7 +159,7 @@ void ip_vs_scheduler_err(struct ip_vs_service *svc, const char *msg)
svc->fwmark, msg);
#ifdef CONFIG_IP_VS_IPV6
} else if (svc->af == AF_INET6) {
- IP_VS_ERR_RL("%s: %s [%pI6]:%d - %s\n",
+ IP_VS_ERR_RL("%s: %s [%pI6c]:%d - %s\n",
svc->scheduler->name,
ip_vs_proto_name(svc->protocol),
&svc->addr.in6, ntohs(svc->port), msg);
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 56f6d5d..1060bd5 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -335,7 +335,7 @@ __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest,
local = __ip_vs_is_local_route6(rt);
if (!((local ? IP_VS_RT_MODE_LOCAL : IP_VS_RT_MODE_NON_LOCAL) &
rt_mode)) {
- IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI6\n",
+ IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI6c\n",
local ? "local":"non-local", daddr);
dst_release(&rt->dst);
return NULL;
@@ -343,8 +343,8 @@ __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest,
if (local && !(rt_mode & IP_VS_RT_MODE_RDR) &&
!((ort = (struct rt6_info *) skb_dst(skb)) &&
__ip_vs_is_local_route6(ort))) {
- IP_VS_DBG_RL("Redirect from non-local address %pI6 to local "
- "requires NAT method, dest: %pI6\n",
+ IP_VS_DBG_RL("Redirect from non-local address %pI6c to local "
+ "requires NAT method, dest: %pI6c\n",
&ipv6_hdr(skb)->daddr, daddr);
dst_release(&rt->dst);
return NULL;
@@ -352,8 +352,8 @@ __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest,
if (unlikely(!local && (!skb->dev || skb->dev->flags & IFF_LOOPBACK) &&
ipv6_addr_type(&ipv6_hdr(skb)->saddr) &
IPV6_ADDR_LOOPBACK)) {
- IP_VS_DBG_RL("Stopping traffic from loopback address %pI6 "
- "to non-local address, dest: %pI6\n",
+ IP_VS_DBG_RL("Stopping traffic from loopback address %pI6c "
+ "to non-local address, dest: %pI6c\n",
&ipv6_hdr(skb)->saddr, daddr);
dst_release(&rt->dst);
return NULL;
^ permalink raw reply related
* [PATCH V4 0/7] ipvs: IPv6 fragment handling for IPVS
From: Jesper Dangaard Brouer @ 2012-09-26 12:05 UTC (permalink / raw)
To: Hans Schillstrom, Hans Schillstrom, netdev, Pablo Neira Ayuso,
lvs-devel, Julian Anastasov
Cc: Jesper Dangaard Brouer, Patrick McHardy, Thomas Graf,
Wensong Zhang, netfilter-devel, Simon Horman
The following patchset implement IPv6 fragment handling for IPVS.
This work is based upon patches from Hans Schillstrom. I have taken
over the patchset, in close agreement with Hans, because he don't have
(gotten allocated) time to complete his work.
I have cleaned up the patchset significantly, and split the patchset
up into seven patches.
The first 3 patches, are ready to be merged
Patch01: Trivial changes, use compressed IPv6 address in output
Patch02: IPv6 extend ICMPv6 handling for future types
Patch03: Use config macro IS_ENABLED()
The next 4 patches, is V4 of the patches I have submitted earlier.
Where I have incorporated Julian's recent feedback.
- Notice that patch04 of patchset V3, have been dropped.
I have also tried to make the patches easier to review, by
reorganizing the changes, to be more strictly split (exthdr
vs. fragment handling).
I have also removed the API changes, and moved those to patch06. This
is done, (1) to make it easier to review the patches, and (2) to allow
easier integration of Patricks idea and my RFC patch of caching exthdr
info in skb->cb[]. Thus, we can get these patches applied (and later
go back and apply the caching scheme easier).
Patch04: Fix faulty IPv6 extension header handling in IPVS
Patch05: Complete IPv6 fragment handling for IPVS
Patch06: IPVS API change to avoid rescan of IPv6 exthdr
Patch07: IPVS SIP fragment handling
The SIP frag handling have been split into its own patch, as I have
not been able to test this part my self.
This patchset is based upon:
Pablo's nf-next tree: git://1984.lsi.us.es/nf-next
On top of:
commit 2cbc78a29e76a2e92c172651204f3117491877d2
(netfilter: combine ipt_REDIRECT and ip6t_REDIRECT)
---
Jesper Dangaard Brouer (7):
ipvs: SIP fragment handling
ipvs: API change to avoid rescan of IPv6 exthdr
ipvs: Complete IPv6 fragment handling for IPVS
ipvs: Fix faulty IPv6 extension header handling in IPVS
ipvs: Use config macro IS_ENABLED()
ipvs: IPv6 extend ICMPv6 handling for future types
ipvs: Trivial changes, use compressed IPv6 address in output
include/net/ip_vs.h | 194 +++++++++++----
net/netfilter/ipvs/Kconfig | 7 -
net/netfilter/ipvs/ip_vs_conn.c | 15 -
net/netfilter/ipvs/ip_vs_core.c | 404 +++++++++++++++++--------------
net/netfilter/ipvs/ip_vs_dh.c | 2
net/netfilter/ipvs/ip_vs_lblc.c | 2
net/netfilter/ipvs/ip_vs_lblcr.c | 2
net/netfilter/ipvs/ip_vs_pe_sip.c | 21 +-
net/netfilter/ipvs/ip_vs_proto.c | 6
net/netfilter/ipvs/ip_vs_proto_ah_esp.c | 9 -
net/netfilter/ipvs/ip_vs_proto_sctp.c | 42 +--
net/netfilter/ipvs/ip_vs_proto_tcp.c | 40 +--
net/netfilter/ipvs/ip_vs_proto_udp.c | 41 +--
net/netfilter/ipvs/ip_vs_sched.c | 2
net/netfilter/ipvs/ip_vs_sh.c | 2
net/netfilter/ipvs/ip_vs_xmit.c | 73 +++---
net/netfilter/xt_ipvs.c | 4
17 files changed, 504 insertions(+), 362 deletions(-)
--
Best regards,
Jesper Dangaard Brouer
MSc.CS, Sr. Network Kernel Developer at Red Hat
Author of http://www.iptv-analyzer.org
LinkedIn: http://www.linkedin.com/in/brouer
^ permalink raw reply
* [PATCH V4 7/7] ipvs: SIP fragment handling
From: Jesper Dangaard Brouer @ 2012-09-26 12:07 UTC (permalink / raw)
To: Hans Schillstrom, Hans Schillstrom, netdev, Pablo Neira Ayuso,
lvs-devel, Julian Anastasov
Cc: Jesper Dangaard Brouer, Patrick McHardy, Thomas Graf,
Wensong Zhang, netfilter-devel, Simon Horman
In-Reply-To: <20120926120534.24804.78415.stgit@dragon>
Use the nfct_reasm SKB if available.
Based on part of a patch from: Hans Schillstrom
I have left Hans'es comment in the patch (marked /HS)
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
---
V3:
- I have split out the SIP fragment handling into a seperate patch.
As I have not been able to test this part.
- Change the strange SKB swapping reasm = skb, reverse logic to minimize patch
net/netfilter/ipvs/ip_vs_pe_sip.c | 19 +++++++++++++++----
1 files changed, 15 insertions(+), 4 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c
index ee4e2e3..43acba6 100644
--- a/net/netfilter/ipvs/ip_vs_pe_sip.c
+++ b/net/netfilter/ipvs/ip_vs_pe_sip.c
@@ -68,6 +68,7 @@ static int get_callid(const char *dptr, unsigned int dataoff,
static int
ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb)
{
+ struct sk_buff *reasm = skb_nfct_reasm(skb);
struct ip_vs_iphdr iph;
unsigned int dataoff, datalen, matchoff, matchlen;
const char *dptr;
@@ -78,13 +79,23 @@ ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb)
/* Only useful with UDP */
if (iph.protocol != IPPROTO_UDP)
return -EINVAL;
+ /*
+ * todo: IPv6 fragments:
+ * I think this only should be done for the first fragment. /HS
+ */
+ if (reasm) {
+ skb = reasm;
+ dataoff = iph.thoff_reasm + sizeof(struct udphdr);
+ } else
+ dataoff = iph.len + sizeof(struct udphdr);
- /* No Data ? */
- dataoff = iph.len + sizeof(struct udphdr);
if (dataoff >= skb->len)
return -EINVAL;
-
- if ((retc=skb_linearize(skb)) < 0)
+ /*
+ * todo: Check if this will mess-up the reasm skb !!! /HS
+ */
+ retc = skb_linearize(skb);
+ if (retc < 0)
return retc;
dptr = skb->data + dataoff;
datalen = skb->len - dataoff;
^ permalink raw reply related
* Re: [PATCH] tcp: sysctl for initial receive window
From: Eric Dumazet @ 2012-09-26 11:53 UTC (permalink / raw)
To: David Miller; +Cc: brouer, netdev, nanditad
In-Reply-To: <20120921.144808.1893006476597754774.davem@davemloft.net>
On Fri, 2012-09-21 at 14:48 -0400, David Miller wrote:
> From: Jesper Dangaard Brouer <brouer@redhat.com>
> Date: Fri, 21 Sep 2012 20:32:06 +0200
> > The would defeat the purpose of the patch. Perhaps we could, allow a
> > sensible max... (but this max is already being controlled as described).
>
> Any new max which is truly sensible, could be the new default, and we
> would apply the same amount of vetting for such a thing.
We have in linux a very conservative and complex rwin control at the
beginning of a TCP session, only for the very first packets,
if applications are reasonably fast at draining their receive queue.
(They mostly are)
Last time I had to take a look (after truesize changes), I was kind of
worried to not find a good reason why we were doing this.
We now have :
- rcvbuf autotuning, letting rwin growing up to 3MB or so
- Better truesize tracking
- global/cgroup tcp mem accounting/pressure
- TCP coalescing to minimize the effect of bad citizen packets
(very low len/truesize ratio)
- People tracking TCP stack inefficiencies and working on new CCs...
(An example is Joe Touch I-D
http://tools.ietf.org/html/draft-touch-tcpm-automatic-iw-03 that
proposes increasing IW over a longer period of time (as opposed to
revisiting constants every few years).
- ...
TCP congestion control is controlled by the sender, driven by the ACK
coming back from receiver, and initial rwin should not change CC at all,
unless we deliberately constrain rwin to a too small value.
We did the 3 -> 10 change only two years ago.
And 3 was really too small even 5 years ago.
Browsers had to open simultaneous sessions to the same server only to
workaround this limit, and they still do.
I would just remove the 10 'hard constant', (but not so hard, since it
was 3 only 2 years ago), and let tcp_rmem[1]/SO_RCVBUF decide of the
initial receive window.
^ permalink raw reply
* Re: gre: Support GRE over IPv6
From: Eric Dumazet @ 2012-09-26 11:39 UTC (permalink / raw)
To: Dan Carpenter; +Cc: xeb, netdev
In-Reply-To: <20120926110258.GP13767@mwanda>
From: Eric Dumazet <edumazet@google.com>
On Wed, 2012-09-26 at 14:02 +0300, Dan Carpenter wrote:
> Hi Dmitry,
>
> I never heard back on this whether it was memory corruption bug or
> not?
>
> regards,
> dan carpenter
>
> On Thu, Sep 13, 2012 at 07:01:05PM +0300, Dan Carpenter wrote:
> > Hello Dmitry Kozlov,
> >
> > The patch c12b395a4664: "gre: Support GRE over IPv6" from Aug 10,
> > 2012, leads to the following warning:
> > net/ipv6/ip6_gre.c:1299 ip6gre_header_parse()
> > error: memcpy() 'haddr' too small (8 vs 16)
> >
> > net/ipv6/ip6_gre.c
> > 1296 static int ip6gre_header_parse(const struct sk_buff *skb, unsigned char *haddr)
> > 1297 {
> > 1298 const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)skb_mac_header(skb);
> > 1299 memcpy(haddr, &ipv6h->saddr, sizeof(struct in6_addr));
> > ^^^^^
> > Smatch thinks this buffer is only 8 characters sometimes.
> >
> > 1300 return sizeof(struct in6_addr);
> > 1301 }
> >
> > One call tree where this would happen would be the
> > (struct sockaddr_ll *)sll->sll_addr[] in packet_rcv().
> >
> > -> packet_rcv()
> > -> dev_parse_header()
> > -> ip6gre_header_parse()
> >
> > I don't know the code well enough to say if this is a bug or not. Could
> > you take a look?
All dev_parse_header() callers provide 8 bytes of storage.
By the way net/netfilter/nfnetlink_log.c and
net/netfilter/nfnetlink_queue_core.c leaks the _pad field to userspace,
I will send a separate patch to netfilter guys.
I would just remove this stuff, as it was copied/pasted from
ipv4/ip_gre.c without thinking of its use.
Thanks
[PATCH net-next] ipv6: gre: remove ip6gre_header_parse()
dev_parse_header() callers provide 8 bytes of storage,
so it's not possible to store an IPv6 address.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
---
net/ipv6/ip6_gre.c | 8 --------
1 file changed, 8 deletions(-)
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 424d11a..796f5d5 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1293,16 +1293,8 @@ static int ip6gre_header(struct sk_buff *skb, struct net_device *dev,
return -t->hlen;
}
-static int ip6gre_header_parse(const struct sk_buff *skb, unsigned char *haddr)
-{
- const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)skb_mac_header(skb);
- memcpy(haddr, &ipv6h->saddr, sizeof(struct in6_addr));
- return sizeof(struct in6_addr);
-}
-
static const struct header_ops ip6gre_header_ops = {
.create = ip6gre_header,
- .parse = ip6gre_header_parse,
};
static const struct net_device_ops ip6gre_netdev_ops = {
^ permalink raw reply related
* Re: gre: Support GRE over IPv6
From: Dan Carpenter @ 2012-09-26 11:02 UTC (permalink / raw)
To: xeb; +Cc: netdev
In-Reply-To: <20120913160105.GA29205@elgon.mountain>
Hi Dmitry,
I never heard back on this whether it was memory corruption bug or
not?
regards,
dan carpenter
On Thu, Sep 13, 2012 at 07:01:05PM +0300, Dan Carpenter wrote:
> Hello Dmitry Kozlov,
>
> The patch c12b395a4664: "gre: Support GRE over IPv6" from Aug 10,
> 2012, leads to the following warning:
> net/ipv6/ip6_gre.c:1299 ip6gre_header_parse()
> error: memcpy() 'haddr' too small (8 vs 16)
>
> net/ipv6/ip6_gre.c
> 1296 static int ip6gre_header_parse(const struct sk_buff *skb, unsigned char *haddr)
> 1297 {
> 1298 const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)skb_mac_header(skb);
> 1299 memcpy(haddr, &ipv6h->saddr, sizeof(struct in6_addr));
> ^^^^^
> Smatch thinks this buffer is only 8 characters sometimes.
>
> 1300 return sizeof(struct in6_addr);
> 1301 }
>
> One call tree where this would happen would be the
> (struct sockaddr_ll *)sll->sll_addr[] in packet_rcv().
>
> -> packet_rcv()
> -> dev_parse_header()
> -> ip6gre_header_parse()
>
> I don't know the code well enough to say if this is a bug or not. Could
> you take a look?
>
> regards,
> dan carpenter
^ permalink raw reply
* Routing issue
From: Stephen Clark @ 2012-09-26 11:01 UTC (permalink / raw)
To: Linux Kernel Network Developers
Hello,
Because Linux makes routing decisions before SNAT it is causing
problems when trying to use FTP with two upstream providers in
a load balanced setup.
Other than ftp things seem to work OK. Below is my setup and tcpdump
output that shows ftp packets trying to go out the wrong interface.
ip ru sh
0: from all lookup local
200: from y.y.y.174 lookup t1
201: from x.x.x.217 lookup t2
32766: from all lookup main
32767: from all lookup default
ip r s
y.y.y.129 dev eth1 scope link
172.16.0.0/29 dev gre1 proto kernel scope link src 172.16.0.1
y.y.y.128/25 dev eth1 proto kernel scope link src y.y.y.174
10.0.1.0/24 dev eth0 proto kernel scope link src 10.0.1.90
192.168.198.0/24 dev eth0 proto kernel scope link src 192.168.198.92
x.x.x.0/24 dev eth2 proto kernel scope link src x.x.x.217
10.0.128.0/17 dev eth0 proto kernel scope link src 10.0.129.88
default
nexthop via y.y.y.129 dev eth1 weight 1
nexthop via x.x.x.1 dev eth2 weight 1
ip r s tab t1
default via y.y.y.129 dev eth1 src y.y.y.174
ip r s tab t2
default via x.x.x.1 dev eth2 src x.x.x.217
Chain PREROUTING (policy ACCEPT 1050K packets, 128M bytes)
pkts bytes target prot opt in out source
destination
Chain POSTROUTING (policy ACCEPT 423K packets, 35M bytes)
pkts bytes target prot opt in out source
destination
0 0 ACCEPT all -- * eth1 10.0.1.0/24
10.0.0.0/8
0 0 ACCEPT all -- * eth1 10.0.1.0/24
172.16.0.0/12
0 0 ACCEPT all -- * eth1 10.0.1.0/24
192.168.0.0/16
58 3480 SNAT all -- * eth1 10.0.1.0/24
0.0.0.0/0 to:y.y.y.174
4 240 SNAT all -- * eth2 10.0.1.0/24
0.0.0.0/0 to:x.x.x.217
lsmod | grep nf_
nf_conntrack_ipv6 7207 3
nf_defrag_ipv6 9873 1 nf_conntrack_ipv6
nf_nat_ftp 2602 0
nf_nat 18580 2 iptable_nat,nf_nat_ftp
nf_conntrack_ipv4 7694 6 iptable_nat,nf_nat
nf_defrag_ipv4 1039 1 nf_conntrack_ipv4
nf_conntrack_ftp 10475 1 nf_nat_ftp
nf_conntrack 65524 7
iptable_nat,nf_conntrack_ipv6,xt_state,nf_nat_ftp,nf_nat,nf_conntrack_ipv4,nf_conntrack_ftp
ipv6 264769 41
nf_conntrack_ipv6,nf_defrag_ipv6,ip6table_mangle,ip6_tunnel,tunnel6
connection starts out eth2 - but then subsequent packets that should be
routed out eth2 are being sent out eth1 see below.
eth2 x.x.x.217
tcpdump -nli eth2 host 131.247.254.5
16:23:06.062451 IP x.x.x.217.53651 > 131.247.254.5.ftp: Flags [S], seq
1482565198, win 5840, options [mss 1460,sackOK,TS val 423546705 ecr
0,nop,wscale 6], length 0
16:23:06.076788 IP 131.247.254.5.ftp > x.x.x.217.53651: Flags [S.], seq
740341460, ack 1482565199, win 5792, options [mss 1460,sackOK,TS val
2565444838 ecr 423546705,nop,wscale 7], length 0
16:23:06.077224 IP x.x.x.217.53651 > 131.247.254.5.ftp: Flags [.], ack
1, win 92, options [nop,nop,TS val 423546720 ecr 2565444838], length 0
16:23:06.096900 IP 131.247.254.5.ftp > x.x.x.217.53651: Flags [P.], seq
1:97, ack 1, win 46, options [nop,nop,TS val 2565444858 ecr 423546720],
length 96
16:23:06.316866 IP 131.247.254.5.ftp > x.x.x.217.53651: Flags [P.], seq
1:97, ack 1, win 46, options [nop,nop,TS val 2565445077 ecr 423546720],
length 96
16:23:06.764410 IP 131.247.254.5.ftp > x.x.x.217.53651: Flags [P.], seq
1:97, ack 1, win 46, options [nop,nop,TS val 2565445515 ecr 423546720],
length 96
16:23:07.634411 IP 131.247.254.5.ftp > x.x.x.217.53651: Flags [P.], seq
1:97, ack 1, win 46, options [nop,nop,TS val 2565446391 ecr 423546720],
length 96
16:23:09.394482 IP 131.247.254.5.ftp > x.x.x.217.53651: Flags [P.], seq
1:97, ack 1, win 46, options [nop,nop,TS val 2565448143 ecr 423546720],
length 96
16:23:12.886997 IP 131.247.254.5.ftp > x.x.x.217.53651: Flags [P.], seq
1:97, ack 1, win 46, options [nop,nop,TS val 2565451647 ecr 423546720],
length 96
16:23:19.892082 IP 131.247.254.5.ftp > x.x.x.217.53651: Flags [P.], seq
1:97, ack 1, win 46, options [nop,nop,TS val 2565458655 ecr 423546720],
length 96
16:23:33.907303 IP 131.247.254.5.ftp > x.x.x.217.53651: Flags [P.], seq
1:97, ack 1, win 46, options [nop,nop,TS val 2565472671 ecr 423546720],
length 96
16:24:01.935273 IP 131.247.254.5.ftp > x.x.x.217.53651: Flags [P.], seq
1:97, ack 1, win 46, options [nop,nop,TS val 2565500703 ecr 423546720],
length 96
16:24:57.993631 IP 131.247.254.5.ftp > x.x.x.217.53651: Flags [P.], seq
1:97, ack 1, win 46, options [nop,nop,TS val 2565556767 ecr 423546720],
length 96
16:26:50.107951 IP 131.247.254.5.ftp > x.x.x.217.53651: Flags [P.], seq
1:97, ack 1, win 46, options [nop,nop,TS val 2565668895 ecr 423546720],
length 96
16:28:06.104031 IP 131.247.254.5.ftp > x.x.x.217.53651: Flags [FP.], seq
97:111, ack 1, win 46, options [nop,nop,TS val 2565744900 ecr
423546720], length 14
These packets should be going out eth2 not eth1
eth1 y.y.y.174
tcpdump -pnli eth1 host 131.247.254.5
16:23:06.097415 IP x.x.x.217.53651 > 131.247.254.5.ftp: Flags [.], ack
740341557, win 92, options [nop,nop,TS val 423546741 ecr 2565444858],
length 0
16:23:06.317381 IP x.x.x.217.53651 > 131.247.254.5.ftp: Flags [.], ack
1, win 92, options [nop,nop,TS val 423546961 ecr 2565445077,nop,nop,sack
1 {4294967201:1}], length 0
16:23:06.764908 IP x.x.x.217.53651 > 131.247.254.5.ftp: Flags [.], ack
1, win 92, options [nop,nop,TS val 423547408 ecr 2565445515,nop,nop,sack
1 {4294967201:1}], length 0
16:23:07.634894 IP x.x.x.217.53651 > 131.247.254.5.ftp: Flags [.], ack
1, win 92, options [nop,nop,TS val 423548278 ecr 2565446391,nop,nop,sack
1 {4294967201:1}], length 0
16:23:09.394972 IP x.x.x.217.53651 > 131.247.254.5.ftp: Flags [.], ack
1, win 92, options [nop,nop,TS val 423550038 ecr 2565448143,nop,nop,sack
1 {4294967201:1}], length 0
16:23:12.887529 IP x.x.x.217.53651 > 131.247.254.5.ftp: Flags [.], ack
1, win 92, options [nop,nop,TS val 423553531 ecr 2565451647,nop,nop,sack
1 {4294967201:1}], length 0
16:23:19.892616 IP x.x.x.217.53651 > 131.247.254.5.ftp: Flags [.], ack
1, win 92, options [nop,nop,TS val 423560536 ecr 2565458655,nop,nop,sack
1 {4294967201:1}], length 0
16:23:33.907736 IP x.x.x.217.53651 > 131.247.254.5.ftp: Flags [.], ack
1, win 92, options [nop,nop,TS val 423574551 ecr 2565472671,nop,nop,sack
1 {4294967201:1}], length 0
16:23:40.173991 IP x.x.x.217.53651 > 131.247.254.5.ftp: Flags [P.], seq
0:13, ack 1, win 92, options [nop,nop,TS val 423580817 ecr 2565472671],
length 13
16:23:40.388692 IP x.x.x.217.53651 > 131.247.254.5.ftp: Flags [P.], seq
0:13, ack 1, win 92, options [nop,nop,TS val 423581032 ecr 2565472671],
length 13
16:23:40.819714 IP x.x.x.217.53651 > 131.247.254.5.ftp: Flags [P.], seq
0:13, ack 1, win 92, options [nop,nop,TS val 423581463 ecr 2565472671],
length 13
16:23:41.680729 IP x.x.x.217.53651 > 131.247.254.5.ftp: Flags [P.], seq
0:13, ack 1, win 92, options [nop,nop,TS val 423582324 ecr 2565472671],
length 13
16:23:43.404732 IP x.x.x.217.53651 > 131.247.254.5.ftp: Flags [P.], seq
0:13, ack 1, win 92, options [nop,nop,TS val 423584048 ecr 2565472671],
length 13
16:23:46.852787 IP x.x.x.217.53651 > 131.247.254.5.ftp: Flags [P.], seq
0:13, ack 1, win 92, options [nop,nop,TS val 423587496 ecr 2565472671],
length 13
16:23:53.756879 IP x.x.x.217.53651 > 131.247.254.5.ftp: Flags [P.], seq
0:13, ack 1, win 92, options [nop,nop,TS val 423594400 ecr 2565472671],
length 13
16:24:01.935822 IP x.x.x.217.53651 > 131.247.254.5.ftp: Flags [.], ack
1, win 92, options [nop,nop,TS val 423602578 ecr 2565500703,nop,nop,sack
1 {4294967201:1}], length 0
16:24:07.549037 IP x.x.x.217.53651 > 131.247.254.5.ftp: Flags [P.], seq
0:13, ack 1, win 92, options [nop,nop,TS val 423608192 ecr 2565500703],
length 13
16:24:35.133346 IP x.x.x.217.53651 > 131.247.254.5.ftp: Flags [P.], seq
0:13, ack 1, win 92, options [nop,nop,TS val 423635776 ecr 2565500703],
length 13
16:24:57.994150 IP x.x.x.217.53651 > 131.247.254.5.ftp: Flags [.], ack
1, win 92, options [nop,nop,TS val 423658636 ecr 2565556767,nop,nop,sack
1 {4294967201:1}], length 0
16:25:30.365963 IP x.x.x.217.53651 > 131.247.254.5.ftp: Flags [P.], seq
0:13, ack 1, win 92, options [nop,nop,TS val 423691008 ecr 2565556767],
length 13
16:26:50.108488 IP x.x.x.217.53651 > 131.247.254.5.ftp: Flags [.], ack
1, win 92, options [nop,nop,TS val 423770749 ecr 2565668895,nop,nop,sack
1 {4294967201:1}], length 0
16:27:20.703243 IP x.x.x.217.53651 > 131.247.254.5.ftp: Flags [P.], seq
0:13, ack 1, win 92, options [nop,nop,TS val 423801344 ecr 2565668895],
length 13
16:28:06.104578 IP x.x.x.217.53651 > 131.247.254.5.ftp: Flags [F.], seq
13, ack 16, win 92, options [nop,nop,TS val 423846744 ecr 2565744900],
length 0
Is there a way to make this work correctly?
Thanks,
Steve
^ permalink raw reply
* [PATCH v2] ipv6: del unreachable route when an addr is deleted on lo
From: Nicolas Dichtel @ 2012-09-26 10:04 UTC (permalink / raw)
To: eric.dumazet; +Cc: netdev, yoshfuji, davem, Nicolas Dichtel
In-Reply-To: <1348580631.26828.3047.camel@edumazet-glaptop>
When an address is added on loopback (ip -6 a a 2002::1/128 dev lo), two routes
are added:
- one in the local table:
local 2002::1 via :: dev lo proto none metric 0
- one the in main table (for the prefix):
unreachable 2002::1 dev lo proto kernel metric 256 error -101
When the address is deleted, the route inserted in the main table remains
because we use rt6_lookup(), which returns NULL when dst->error is set, which
is the case here! Thus, it is better to use ip6_route_lookup() to avoid this
kind of filter.
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
---
v2: rt cannot be NULL, so adjust the test after ip6_route_lookup()
net/ipv6/addrconf.c | 10 ++++++++--
1 file changed, 8 insertions(+), 2 deletions(-)
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 6bc85f7..ea3e9af 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -788,10 +788,16 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp)
struct in6_addr prefix;
struct rt6_info *rt;
struct net *net = dev_net(ifp->idev->dev);
+ struct flowi6 fl6 = {};
+
ipv6_addr_prefix(&prefix, &ifp->addr, ifp->prefix_len);
- rt = rt6_lookup(net, &prefix, NULL, ifp->idev->dev->ifindex, 1);
+ fl6.flowi6_oif = ifp->idev->dev->ifindex;
+ fl6.daddr = prefix;
+ rt = (struct rt6_info *)ip6_route_lookup(net, &fl6,
+ RT6_LOOKUP_F_IFACE);
- if (rt && addrconf_is_prefix_route(rt)) {
+ if (rt != net->ipv6.ip6_null_entry &&
+ addrconf_is_prefix_route(rt)) {
if (onlink == 0) {
ip6_del_rt(rt);
rt = NULL;
--
1.7.12
^ permalink raw reply related
* Re: [patch v2 04/11] nf_conntrack_netlink: pass nf_conntrack_netlink module to netlink_dump_start
From: Pablo Neira Ayuso @ 2012-09-26 9:58 UTC (permalink / raw)
To: Gao feng
Cc: davem, eric.dumazet, steffen.klassert, netfilter-devel,
linux-rdma, netdev, linux-crypto, stephen.hemminger, jengelh
In-Reply-To: <5062CE07.1080704@cn.fujitsu.com>
On Wed, Sep 26, 2012 at 05:42:31PM +0800, Gao feng wrote:
> Hi Pablo:
>
> 于 2012年09月26日 17:26, Pablo Neira Ayuso 写道:
> > On Wed, Sep 26, 2012 at 04:41:21PM +0800, Gao feng wrote:
> >> use proper netlink_dump_control.done and .module to avoid panic.
> >>
> >> Signed-off-by: Gao feng <gaofeng@cn.fujitsu.com>
> >> ---
> >> net/netfilter/nf_conntrack_netlink.c | 8 ++++++++
> >> 1 files changed, 8 insertions(+), 0 deletions(-)
> >>
> >> diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
> >> index 9807f32..509a257 100644
> >> --- a/net/netfilter/nf_conntrack_netlink.c
> >> +++ b/net/netfilter/nf_conntrack_netlink.c
> >> @@ -706,6 +706,7 @@ static int ctnetlink_done(struct netlink_callback *cb)
> >> nf_ct_put((struct nf_conn *)cb->args[1]);
> >> if (cb->data)
> >> kfree(cb->data);
> >> + netlink_dump_done(cb);
> >
> > I think you can call netlink_dump_done from af_netlink.c:
> >
> > static int netlink_dump(struct sock *sk)
> > ...
> > if (cb->done) {
> > cb->done(cb);
> > netlink_dump_done(...);
> > }
> >
> > Thus, you don't need to change netlink_dump_control in every netlink
> > subsystem.
>
> because cb->done is called by netlink_sock_destruct too,it's very usefully
> when userspace program only send dump request to kernel without reading
> data from kernel.
Then add that to netlink_sock_destruct as well. If possible, I prefer
if this remains in the netlink core to avoid leaking module refcount
if you forget to call netlink_dump_done.
> >
> >> return 0;
> >> }
> >>
> >> @@ -1022,6 +1023,7 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb,
> >> struct netlink_dump_control c = {
> >> .dump = ctnetlink_dump_table,
> >> .done = ctnetlink_done,
> >> + .module = THIS_MODULE,
> >
> > You can do something similar to:
> >
> > 9f00d97 netlink: hide struct module parameter in netlink_kernel_create
> >
> > by definiting netlink_dump_start as static inline and using
> > THIS_MODULE from there.
> >
> > If I'm not missing anything, with those two changes, you will not need
> > to modify any caller and it will result one single patch.
> >
>
> You can see the patch [11/11], THIS_MODULE in infiniband/core/cma.c
> means module rdma_cm,but we call netlink_dump_start in infiniband/core/netlink.c
You can still use __netlink_dump_start for that case, which allows you
to specify a custom struct module * parameter. But for most cases,
netlink_dump_start (which hides THIS_MODULE) should be fine.
> we should make sure the cb.moudle point to the module which cb.dump belongs to.
> we can call netlink_dump_start to set cb->dump everywhere, so I think we still
> need to pass struct module to the netlink_callback.
>
> thanks for your comments!
> --
> To unsubscribe from this list: send the line "unsubscribe netfilter-devel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
To unsubscribe from this list: send the line "unsubscribe netfilter-devel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* RE: removing the timer from cdc-ncm
From: Alexey ORISHKO @ 2012-09-26 9:49 UTC (permalink / raw)
To: Oliver Neukum
Cc: bjorn-yOkvZcmFvRU@public.gmane.org,
netdev-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-usb-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
In-Reply-To: <9022066.PsM0uBqIB8-ugxBuEnWX9yG/4A2pS7c2Q@public.gmane.org>
> -----Original Message-----
> From: Oliver Neukum [mailto:oneukum-l3A5Bk7waGM@public.gmane.org]
> Thank you. Worse than I hoped, but not unexpected. I'll stare at the
> code a bit.
Just a small clarification: on Ellisys trace I see only
ConnectionSpeedChange and NetworkConnection (Connected). No data was
sent on the bulk pipe before it crashed.
/alexey
--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [patch v2 04/11] nf_conntrack_netlink: pass nf_conntrack_netlink module to netlink_dump_start
From: Gao feng @ 2012-09-26 9:42 UTC (permalink / raw)
To: Pablo Neira Ayuso
Cc: davem, eric.dumazet, steffen.klassert, netfilter-devel,
linux-rdma, netdev, linux-crypto, stephen.hemminger, jengelh
In-Reply-To: <20120926092632.GA21589@1984>
Hi Pablo:
于 2012年09月26日 17:26, Pablo Neira Ayuso 写道:
> On Wed, Sep 26, 2012 at 04:41:21PM +0800, Gao feng wrote:
>> use proper netlink_dump_control.done and .module to avoid panic.
>>
>> Signed-off-by: Gao feng <gaofeng@cn.fujitsu.com>
>> ---
>> net/netfilter/nf_conntrack_netlink.c | 8 ++++++++
>> 1 files changed, 8 insertions(+), 0 deletions(-)
>>
>> diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
>> index 9807f32..509a257 100644
>> --- a/net/netfilter/nf_conntrack_netlink.c
>> +++ b/net/netfilter/nf_conntrack_netlink.c
>> @@ -706,6 +706,7 @@ static int ctnetlink_done(struct netlink_callback *cb)
>> nf_ct_put((struct nf_conn *)cb->args[1]);
>> if (cb->data)
>> kfree(cb->data);
>> + netlink_dump_done(cb);
>
> I think you can call netlink_dump_done from af_netlink.c:
>
> static int netlink_dump(struct sock *sk)
> ...
> if (cb->done) {
> cb->done(cb);
> netlink_dump_done(...);
> }
>
> Thus, you don't need to change netlink_dump_control in every netlink
> subsystem.
because cb->done is called by netlink_sock_destruct too,it's very usefully
when userspace program only send dump request to kernel without reading
data from kernel.
>
>> return 0;
>> }
>>
>> @@ -1022,6 +1023,7 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb,
>> struct netlink_dump_control c = {
>> .dump = ctnetlink_dump_table,
>> .done = ctnetlink_done,
>> + .module = THIS_MODULE,
>
> You can do something similar to:
>
> 9f00d97 netlink: hide struct module parameter in netlink_kernel_create
>
> by definiting netlink_dump_start as static inline and using
> THIS_MODULE from there.
>
> If I'm not missing anything, with those two changes, you will not need
> to modify any caller and it will result one single patch.
>
You can see the patch [11/11], THIS_MODULE in infiniband/core/cma.c
means module rdma_cm,but we call netlink_dump_start in infiniband/core/netlink.c
we should make sure the cb.moudle point to the module which cb.dump belongs to.
we can call netlink_dump_start to set cb->dump everywhere, so I think we still
need to pass struct module to the netlink_callback.
thanks for your comments!
^ permalink raw reply
* Re: [patch v2 04/11] nf_conntrack_netlink: pass nf_conntrack_netlink module to netlink_dump_start
From: Pablo Neira Ayuso @ 2012-09-26 9:26 UTC (permalink / raw)
To: Gao feng
Cc: davem, eric.dumazet, steffen.klassert, netfilter-devel,
linux-rdma, netdev, linux-crypto, stephen.hemminger, jengelh
In-Reply-To: <1348648888-24943-4-git-send-email-gaofeng@cn.fujitsu.com>
On Wed, Sep 26, 2012 at 04:41:21PM +0800, Gao feng wrote:
> use proper netlink_dump_control.done and .module to avoid panic.
>
> Signed-off-by: Gao feng <gaofeng@cn.fujitsu.com>
> ---
> net/netfilter/nf_conntrack_netlink.c | 8 ++++++++
> 1 files changed, 8 insertions(+), 0 deletions(-)
>
> diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
> index 9807f32..509a257 100644
> --- a/net/netfilter/nf_conntrack_netlink.c
> +++ b/net/netfilter/nf_conntrack_netlink.c
> @@ -706,6 +706,7 @@ static int ctnetlink_done(struct netlink_callback *cb)
> nf_ct_put((struct nf_conn *)cb->args[1]);
> if (cb->data)
> kfree(cb->data);
> + netlink_dump_done(cb);
I think you can call netlink_dump_done from af_netlink.c:
static int netlink_dump(struct sock *sk)
...
if (cb->done) {
cb->done(cb);
netlink_dump_done(...);
}
Thus, you don't need to change netlink_dump_control in every netlink
subsystem.
> return 0;
> }
>
> @@ -1022,6 +1023,7 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb,
> struct netlink_dump_control c = {
> .dump = ctnetlink_dump_table,
> .done = ctnetlink_done,
> + .module = THIS_MODULE,
You can do something similar to:
9f00d97 netlink: hide struct module parameter in netlink_kernel_create
by definiting netlink_dump_start as static inline and using
THIS_MODULE from there.
If I'm not missing anything, with those two changes, you will not need
to modify any caller and it will result one single patch.
^ permalink raw reply
* Re: [patch v2 04/11] nf_conntrack_netlink: pass nf_conntrack_netlink module to netlink_dump_start
From: Gao feng @ 2012-09-26 9:25 UTC (permalink / raw)
To: Gao feng
Cc: davem, eric.dumazet, steffen.klassert, netfilter-devel,
linux-rdma, netdev, linux-crypto, pablo, stephen.hemminger,
jengelh
In-Reply-To: <1348648888-24943-4-git-send-email-gaofeng@cn.fujitsu.com>
于 2012年09月26日 16:41, Gao feng 写道:
> use proper netlink_dump_control.done and .module to avoid panic.
>
> Signed-off-by: Gao feng <gaofeng@cn.fujitsu.com>
> ---
> net/netfilter/nf_conntrack_netlink.c | 8 ++++++++
> 1 files changed, 8 insertions(+), 0 deletions(-)
>
> diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
> index 9807f32..509a257 100644
> --- a/net/netfilter/nf_conntrack_netlink.c
> +++ b/net/netfilter/nf_conntrack_netlink.c
> @@ -706,6 +706,7 @@ static int ctnetlink_done(struct netlink_callback *cb)
> nf_ct_put((struct nf_conn *)cb->args[1]);
> if (cb->data)
> kfree(cb->data);
> + netlink_dump_done(cb);
> return 0;
> }
>
> @@ -1022,6 +1023,7 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb,
> struct netlink_dump_control c = {
> .dump = ctnetlink_dump_table,
> .done = ctnetlink_done,
> + .module = THIS_MODULE,
> };
> #ifdef CONFIG_NF_CONNTRACK_MARK
> if (cda[CTA_MARK] && cda[CTA_MARK_MASK]) {
> @@ -1706,6 +1708,8 @@ ctnetlink_stat_ct_cpu(struct sock *ctnl, struct sk_buff *skb,
> if (nlh->nlmsg_flags & NLM_F_DUMP) {
> struct netlink_dump_control c = {
> .dump = ctnetlink_ct_stat_cpu_dump,
> + .done = netlink_dump_done,
> + .module = THIS_MODULE,
> };
> return netlink_dump_start(ctnl, skb, nlh, &c);
> }
> @@ -2141,6 +2145,7 @@ static int ctnetlink_exp_done(struct netlink_callback *cb)
> {
> if (cb->args[1])
> nf_ct_expect_put((struct nf_conntrack_expect *)cb->args[1]);
> + netlink_dump_done(cb);
> return 0;
> }
I should do return netlink_dump_done here.
I will reset this patchset.
^ permalink raw reply
* flow control handling in network driver
From: Rayagond K @ 2012-09-26 9:18 UTC (permalink / raw)
To: netdev
Hi All,
What is the use of two macros SUPPORTED_Pause and SUPPORTED_Asym_Pause
which are defined in ethtool.h file.
I have seen amny driver in lxr using above macros, for example tg3
driver - uses these macros to advertise the phy capabilities.
Flow control is MAC feature not PHY, hence when can one use above
macros and what is the use of it. Should we use these macros to
implement flow control in Ethernet driver ?
Thanks in advance.
--
wwr
Rayagond
^ permalink raw reply
* [PATCH net-next] net: use bigger pages in __netdev_alloc_frag
From: Eric Dumazet @ 2012-09-26 9:06 UTC (permalink / raw)
To: David Miller; +Cc: netdev, Alexander Duyck
From: Eric Dumazet <edumazet@google.com>
We currently use percpu order-0 pages in __netdev_alloc_frag
to deliver fragments used by __netdev_alloc_skb()
Depending on NIC driver and arch being 32 or 64 bit, it allows a page to
be split in several fragments (between 1 and 8), assuming PAGE_SIZE=4096
Switching to bigger pages (32768 bytes for PAGE_SIZE=4096 case) allows :
- Better filling of space (the ending hole overhead is less an issue)
- Less calls to page allocator or accesses to page->_count
- Could allow struct skb_shared_info futures changes without major
performance impact.
This patch implements a transparent fallback to smaller
pages in case of memory pressure.
It also uses a standard "struct page_frag" instead of a custom one.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Alexander Duyck <alexander.h.duyck@intel.com>
---
net/core/skbuff.c | 46 ++++++++++++++++++++++++++++----------------
1 file changed, 30 insertions(+), 16 deletions(-)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 2ede3cf..4ab83ce 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -340,43 +340,57 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size)
EXPORT_SYMBOL(build_skb);
struct netdev_alloc_cache {
- struct page *page;
- unsigned int offset;
- unsigned int pagecnt_bias;
+ struct page_frag frag;
+ /* we maintain a pagecount bias, so that we dont dirty cache line
+ * containing page->_count every time we allocate a fragment.
+ */
+ unsigned int pagecnt_bias;
};
static DEFINE_PER_CPU(struct netdev_alloc_cache, netdev_alloc_cache);
-#define NETDEV_PAGECNT_BIAS (PAGE_SIZE / SMP_CACHE_BYTES)
+#define NETDEV_FRAG_PAGE_MAX_ORDER get_order(32768)
+#define NETDEV_FRAG_PAGE_MAX_SIZE (PAGE_SIZE << NETDEV_FRAG_PAGE_MAX_ORDER)
+#define NETDEV_PAGECNT_MAX_BIAS NETDEV_FRAG_PAGE_MAX_SIZE
static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask)
{
struct netdev_alloc_cache *nc;
void *data = NULL;
+ int order;
unsigned long flags;
local_irq_save(flags);
nc = &__get_cpu_var(netdev_alloc_cache);
- if (unlikely(!nc->page)) {
+ if (unlikely(!nc->frag.page)) {
refill:
- nc->page = alloc_page(gfp_mask);
- if (unlikely(!nc->page))
- goto end;
+ for (order = NETDEV_FRAG_PAGE_MAX_ORDER; ;) {
+ gfp_t gfp = gfp_mask;
+
+ if (order)
+ gfp |= __GFP_COMP | __GFP_NOWARN;
+ nc->frag.page = alloc_pages(gfp, order);
+ if (likely(nc->frag.page))
+ break;
+ if (--order <= 0)
+ goto end;
+ }
+ nc->frag.size = PAGE_SIZE << order;
recycle:
- atomic_set(&nc->page->_count, NETDEV_PAGECNT_BIAS);
- nc->pagecnt_bias = NETDEV_PAGECNT_BIAS;
- nc->offset = 0;
+ atomic_set(&nc->frag.page->_count, NETDEV_PAGECNT_MAX_BIAS);
+ nc->pagecnt_bias = NETDEV_PAGECNT_MAX_BIAS;
+ nc->frag.offset = 0;
}
- if (nc->offset + fragsz > PAGE_SIZE) {
+ if (nc->frag.offset + fragsz > nc->frag.size) {
/* avoid unnecessary locked operations if possible */
- if ((atomic_read(&nc->page->_count) == nc->pagecnt_bias) ||
- atomic_sub_and_test(nc->pagecnt_bias, &nc->page->_count))
+ if ((atomic_read(&nc->frag.page->_count) == nc->pagecnt_bias) ||
+ atomic_sub_and_test(nc->pagecnt_bias, &nc->frag.page->_count))
goto recycle;
goto refill;
}
- data = page_address(nc->page) + nc->offset;
- nc->offset += fragsz;
+ data = page_address(nc->frag.page) + nc->frag.offset;
+ nc->frag.offset += fragsz;
nc->pagecnt_bias--;
end:
local_irq_restore(flags);
^ permalink raw reply related
* Re: removing the timer from cdc-ncm
From: Oliver Neukum @ 2012-09-26 8:57 UTC (permalink / raw)
To: Alexey ORISHKO
Cc: bjorn-yOkvZcmFvRU@public.gmane.org,
netdev-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-usb-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
In-Reply-To: <2AC7D4AD8BA1C640B4C60C61C8E520154A8BED59B5-8ZTw5gFVCTjVH5byLeRTJxkTb7+GphCuwzqs5ZKRSiY@public.gmane.org>
On Tuesday 25 September 2012 13:18:10 Alexey ORISHKO wrote:
> > -----Original Message-----
> > From: Oliver Neukum [mailto:oneukum-l3A5Bk7waGM@public.gmane.org]
> >
> > here is the patch that does everything I consider theoretically
> > necessary to have bundling of frames in usbnet and adapting cdc-ncm to
> > it.
> >
> > I'd appreciate any review in case I am doing something stupid.
> >
>
> I had a brief look at cdc_ncm and a few corrections needed:
> - remove the following:
> #include <linux/hrtimer.h>
> ...
> /* Restart the timer, if amount of datagrams is less than given value */
> #define CDC_NCM_RESTART_TIMER_DATAGRAM_CNT 3
> #define CDC_NCM_TIMER_PENDING_CNT 2
> #define CDC_NCM_TIMER_INTERVAL (400UL * NSEC_PER_USEC)
> ...
> In struct cdc_ncm_ctx {
> ...
> struct hrtimer tx_timer;
> struct tasklet_struct bh;
> ...
>
> In cdc_ncm_unbind():
> if (hrtimer_active(&ctx->tx_timer))
> hrtimer_cancel(&ctx->tx_timer);
>
> tasklet_kill(&ctx->bh);
Roger
> I didn't have time to check the new logic for data path, but I've
> tried to run it on Ubuntu 12.04.
> Linux host got panic right after data path has been established
> (i.e. connected to mobile network).
Thank you. Worse than I hoped, but not unexpected. I'll stare at the
code a bit.
Regards
Oliver
--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* [patch v2 09/11] xfrm: pass xfrm_user module to netlink_dump_start
From: Gao feng @ 2012-09-26 8:41 UTC (permalink / raw)
To: davem, eric.dumazet, steffen.klassert
Cc: netfilter-devel, linux-rdma, netdev, linux-crypto, pablo,
stephen.hemminger, jengelh, Gao feng
In-Reply-To: <1348648888-24943-1-git-send-email-gaofeng@cn.fujitsu.com>
use proper netlink_dump_control.done and .module to avoid panic.
Signed-off-by: Gao feng <gaofeng@cn.fujitsu.com>
---
net/xfrm/xfrm_user.c | 12 ++++++++----
1 files changed, 8 insertions(+), 4 deletions(-)
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 289f4bf..852339d 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -867,7 +867,7 @@ static int xfrm_dump_sa_done(struct netlink_callback *cb)
{
struct xfrm_state_walk *walk = (struct xfrm_state_walk *) &cb->args[1];
xfrm_state_walk_done(walk);
- return 0;
+ return netlink_dump_done(cb);
}
static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb)
@@ -1538,7 +1538,7 @@ static int xfrm_dump_policy_done(struct netlink_callback *cb)
struct xfrm_policy_walk *walk = (struct xfrm_policy_walk *) &cb->args[1];
xfrm_policy_walk_done(walk);
- return 0;
+ return netlink_dump_done(cb);
}
static int xfrm_dump_policy(struct sk_buff *skb, struct netlink_callback *cb)
@@ -2308,17 +2308,20 @@ static struct xfrm_link {
int (*doit)(struct sk_buff *, struct nlmsghdr *, struct nlattr **);
int (*dump)(struct sk_buff *, struct netlink_callback *);
int (*done)(struct netlink_callback *);
+ struct module *module;
} xfrm_dispatch[XFRM_NR_MSGTYPES] = {
[XFRM_MSG_NEWSA - XFRM_MSG_BASE] = { .doit = xfrm_add_sa },
[XFRM_MSG_DELSA - XFRM_MSG_BASE] = { .doit = xfrm_del_sa },
[XFRM_MSG_GETSA - XFRM_MSG_BASE] = { .doit = xfrm_get_sa,
.dump = xfrm_dump_sa,
- .done = xfrm_dump_sa_done },
+ .done = xfrm_dump_sa_done,
+ .module = THIS_MODULE },
[XFRM_MSG_NEWPOLICY - XFRM_MSG_BASE] = { .doit = xfrm_add_policy },
[XFRM_MSG_DELPOLICY - XFRM_MSG_BASE] = { .doit = xfrm_get_policy },
[XFRM_MSG_GETPOLICY - XFRM_MSG_BASE] = { .doit = xfrm_get_policy,
.dump = xfrm_dump_policy,
- .done = xfrm_dump_policy_done },
+ .done = xfrm_dump_policy_done,
+ .module = THIS_MODULE },
[XFRM_MSG_ALLOCSPI - XFRM_MSG_BASE] = { .doit = xfrm_alloc_userspi },
[XFRM_MSG_ACQUIRE - XFRM_MSG_BASE] = { .doit = xfrm_add_acquire },
[XFRM_MSG_EXPIRE - XFRM_MSG_BASE] = { .doit = xfrm_add_sa_expire },
@@ -2362,6 +2365,7 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
struct netlink_dump_control c = {
.dump = link->dump,
.done = link->done,
+ .module = link->module,
};
return netlink_dump_start(net->xfrm.nlsk, skb, nlh, &c);
}
--
1.7.7.6
^ permalink raw reply related
* [patch v2 11/11] infiniband: pass rdma_cm module to netlink_dump_start
From: Gao feng @ 2012-09-26 8:41 UTC (permalink / raw)
To: davem-fT/PcQaiUtIeIZ0/mPfg9Q, eric.dumazet-Re5JQEeQqe8AvxtiuMwx3w,
steffen.klassert-opNxpl+3fjRBDgjK7y7TUQ
Cc: netfilter-devel-u79uwXL29TY76Z2rM5mHXA,
linux-rdma-u79uwXL29TY76Z2rM5mHXA, netdev-u79uwXL29TY76Z2rM5mHXA,
linux-crypto-u79uwXL29TY76Z2rM5mHXA, pablo-Cap9r6Oaw4JrovVCs/uTlw,
stephen.hemminger-ZtmgI6mnKB3QT0dZR+AlfA, jengelh-9+2X+4sQBs8,
Gao feng, Roland Dreier, Sean Hefty
In-Reply-To: <1348648888-24943-1-git-send-email-gaofeng-BthXqXjhjHXQFUHtdCDX3A@public.gmane.org>
use proper netlink_dump_control.done and .module to avoid panic.
Signed-off-by: Gao feng <gaofeng-BthXqXjhjHXQFUHtdCDX3A@public.gmane.org>
Cc: Roland Dreier <roland-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
Cc: Sean Hefty <sean.hefty-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
drivers/infiniband/core/cma.c | 3 ++-
drivers/infiniband/core/netlink.c | 2 ++
include/rdma/rdma_netlink.h | 1 +
3 files changed, 5 insertions(+), 1 deletions(-)
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 7172559..d1febf0 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -3495,7 +3495,8 @@ out:
}
static const struct ibnl_client_cbs cma_cb_table[] = {
- [RDMA_NL_RDMA_CM_ID_STATS] = { .dump = cma_get_id_stats },
+ [RDMA_NL_RDMA_CM_ID_STATS] = { .dump = cma_get_id_stats,
+ .module = THIS_MODULE },
};
static int __init cma_init(void)
diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index 3ae2bfd..1468827 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -154,6 +154,8 @@ static int ibnl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
{
struct netlink_dump_control c = {
.dump = client->cb_table[op].dump,
+ .done = netlink_dump_done,
+ .module = client->cb_table[op].module,
};
return netlink_dump_start(nls, skb, nlh, &c);
}
diff --git a/include/rdma/rdma_netlink.h b/include/rdma/rdma_netlink.h
index 3c5363a..bd3d8b2 100644
--- a/include/rdma/rdma_netlink.h
+++ b/include/rdma/rdma_netlink.h
@@ -39,6 +39,7 @@ struct rdma_cm_id_stats {
struct ibnl_client_cbs {
int (*dump)(struct sk_buff *skb, struct netlink_callback *nlcb);
+ struct module *module;
};
int ibnl_init(void);
--
1.7.7.6
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [patch v2 10/11] ipset: pass ipset module to netlink_dump_start
From: Gao feng @ 2012-09-26 8:41 UTC (permalink / raw)
To: davem-fT/PcQaiUtIeIZ0/mPfg9Q, eric.dumazet-Re5JQEeQqe8AvxtiuMwx3w,
steffen.klassert-opNxpl+3fjRBDgjK7y7TUQ
Cc: netfilter-devel-u79uwXL29TY76Z2rM5mHXA,
linux-rdma-u79uwXL29TY76Z2rM5mHXA, netdev-u79uwXL29TY76Z2rM5mHXA,
linux-crypto-u79uwXL29TY76Z2rM5mHXA, pablo-Cap9r6Oaw4JrovVCs/uTlw,
stephen.hemminger-ZtmgI6mnKB3QT0dZR+AlfA, jengelh-9+2X+4sQBs8,
Gao feng, Jozsef Kadlecsik
In-Reply-To: <1348648888-24943-1-git-send-email-gaofeng-BthXqXjhjHXQFUHtdCDX3A@public.gmane.org>
use proper netlink_dump_control.done and .module to avoid panic.
Signed-off-by: Gao feng <gaofeng-BthXqXjhjHXQFUHtdCDX3A@public.gmane.org>
Cc: Jozsef Kadlecsik <kadlec-K40Dz/62t/MgiyqX0sVFJYdd74u8MsAO@public.gmane.org>
---
net/netfilter/ipset/ip_set_core.c | 3 ++-
1 files changed, 2 insertions(+), 1 deletions(-)
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 9730882..c4903dc 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -986,7 +986,7 @@ ip_set_dump_done(struct netlink_callback *cb)
pr_debug("release set %s\n", ip_set_list[cb->args[1]]->name);
ip_set_put_byindex((ip_set_id_t) cb->args[1]);
}
- return 0;
+ return netlink_dump_done(cb);
}
static inline void
@@ -1176,6 +1176,7 @@ ip_set_dump(struct sock *ctnl, struct sk_buff *skb,
struct netlink_dump_control c = {
.dump = ip_set_dump_start,
.done = ip_set_dump_done,
+ .module = THIS_MODULE,
};
return netlink_dump_start(ctnl, skb, nlh, &c);
}
--
1.7.7.6
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [patch v2 08/11] crypto: pass crypto_user module to netlink_dump_start
From: Gao feng @ 2012-09-26 8:41 UTC (permalink / raw)
To: davem, eric.dumazet, steffen.klassert
Cc: netfilter-devel, linux-rdma, netdev, linux-crypto, pablo,
stephen.hemminger, jengelh, Gao feng, Herbert Xu
In-Reply-To: <1348648888-24943-1-git-send-email-gaofeng@cn.fujitsu.com>
use proper netlink_dump_control.done and .module to avoid panic.
Signed-off-by: Gao feng <gaofeng@cn.fujitsu.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
---
crypto/crypto_user.c | 7 +++++--
1 files changed, 5 insertions(+), 2 deletions(-)
diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c
index ba2c611..a9ca2b9 100644
--- a/crypto/crypto_user.c
+++ b/crypto/crypto_user.c
@@ -249,7 +249,7 @@ out_err:
static int crypto_dump_report_done(struct netlink_callback *cb)
{
- return 0;
+ return netlink_dump_done(cb);
}
static int crypto_update_alg(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -430,13 +430,15 @@ static struct crypto_link {
int (*doit)(struct sk_buff *, struct nlmsghdr *, struct nlattr **);
int (*dump)(struct sk_buff *, struct netlink_callback *);
int (*done)(struct netlink_callback *);
+ struct module *module;
} crypto_dispatch[CRYPTO_NR_MSGTYPES] = {
[CRYPTO_MSG_NEWALG - CRYPTO_MSG_BASE] = { .doit = crypto_add_alg},
[CRYPTO_MSG_DELALG - CRYPTO_MSG_BASE] = { .doit = crypto_del_alg},
[CRYPTO_MSG_UPDATEALG - CRYPTO_MSG_BASE] = { .doit = crypto_update_alg},
[CRYPTO_MSG_GETALG - CRYPTO_MSG_BASE] = { .doit = crypto_report,
.dump = crypto_dump_report,
- .done = crypto_dump_report_done},
+ .done = crypto_dump_report_done,
+ .module = THIS_MODULE},
};
static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
@@ -470,6 +472,7 @@ static int crypto_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
struct netlink_dump_control c = {
.dump = link->dump,
.done = link->done,
+ .module = link->module,
.min_dump_alloc = dump_alloc,
};
return netlink_dump_start(crypto_nlsk, skb, nlh, &c);
--
1.7.7.6
^ permalink raw reply related
* [patch v2 07/11] nfnetlink_cttimeout: pass nfnetlink_cttimeout module to netlink_dump_start
From: Gao feng @ 2012-09-26 8:41 UTC (permalink / raw)
To: davem-fT/PcQaiUtIeIZ0/mPfg9Q, eric.dumazet-Re5JQEeQqe8AvxtiuMwx3w,
steffen.klassert-opNxpl+3fjRBDgjK7y7TUQ
Cc: netfilter-devel-u79uwXL29TY76Z2rM5mHXA,
linux-rdma-u79uwXL29TY76Z2rM5mHXA, netdev-u79uwXL29TY76Z2rM5mHXA,
linux-crypto-u79uwXL29TY76Z2rM5mHXA, pablo-Cap9r6Oaw4JrovVCs/uTlw,
stephen.hemminger-ZtmgI6mnKB3QT0dZR+AlfA, jengelh-9+2X+4sQBs8,
Gao feng
In-Reply-To: <1348648888-24943-1-git-send-email-gaofeng-BthXqXjhjHXQFUHtdCDX3A@public.gmane.org>
use proper netlink_dump_control.done and .module to avoid panic.
Signed-off-by: Gao feng <gaofeng-BthXqXjhjHXQFUHtdCDX3A@public.gmane.org>
---
net/netfilter/nfnetlink_cttimeout.c | 2 ++
1 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index cdecbc8..bc3e730 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -248,6 +248,8 @@ cttimeout_get_timeout(struct sock *ctnl, struct sk_buff *skb,
if (nlh->nlmsg_flags & NLM_F_DUMP) {
struct netlink_dump_control c = {
.dump = ctnl_timeout_dump,
+ .done = netlink_dump_done,
+ .module = THIS_MODULE,
};
return netlink_dump_start(ctnl, skb, nlh, &c);
}
--
1.7.7.6
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [patch v2 06/11] nfnetlink_cthelper: pass nfnetlink_cthelper module to netlink_dump_start
From: Gao feng @ 2012-09-26 8:41 UTC (permalink / raw)
To: davem-fT/PcQaiUtIeIZ0/mPfg9Q, eric.dumazet-Re5JQEeQqe8AvxtiuMwx3w,
steffen.klassert-opNxpl+3fjRBDgjK7y7TUQ
Cc: netfilter-devel-u79uwXL29TY76Z2rM5mHXA,
linux-rdma-u79uwXL29TY76Z2rM5mHXA, netdev-u79uwXL29TY76Z2rM5mHXA,
linux-crypto-u79uwXL29TY76Z2rM5mHXA, pablo-Cap9r6Oaw4JrovVCs/uTlw,
stephen.hemminger-ZtmgI6mnKB3QT0dZR+AlfA, jengelh-9+2X+4sQBs8,
Gao feng
In-Reply-To: <1348648888-24943-1-git-send-email-gaofeng-BthXqXjhjHXQFUHtdCDX3A@public.gmane.org>
use proper netlink_dump_control.done and .module to avoid panic.
Signed-off-by: Gao feng <gaofeng-BthXqXjhjHXQFUHtdCDX3A@public.gmane.org>
---
net/netfilter/nfnetlink_cthelper.c | 2 ++
1 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index d683619..117343f 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -501,6 +501,8 @@ nfnl_cthelper_get(struct sock *nfnl, struct sk_buff *skb,
if (nlh->nlmsg_flags & NLM_F_DUMP) {
struct netlink_dump_control c = {
.dump = nfnl_cthelper_dump_table,
+ .done = netlink_dump_done,
+ .module = THIS_MODULE,
};
return netlink_dump_start(nfnl, skb, nlh, &c);
}
--
1.7.7.6
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [patch v2 05/11] nfnetlink_acct: pass nfnetlink_acct module to netlink_dump_start
From: Gao feng @ 2012-09-26 8:41 UTC (permalink / raw)
To: davem, eric.dumazet, steffen.klassert
Cc: netfilter-devel, linux-rdma, netdev, linux-crypto, pablo,
stephen.hemminger, jengelh, Gao feng
In-Reply-To: <1348648888-24943-1-git-send-email-gaofeng@cn.fujitsu.com>
use proper netlink_dump_control.done and .module to avoid panic.
Signed-off-by: Gao feng <gaofeng@cn.fujitsu.com>
---
net/netfilter/nfnetlink_acct.c | 2 ++
1 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c
index b2e7310..1e9cb0f 100644
--- a/net/netfilter/nfnetlink_acct.c
+++ b/net/netfilter/nfnetlink_acct.c
@@ -175,6 +175,8 @@ nfnl_acct_get(struct sock *nfnl, struct sk_buff *skb,
if (nlh->nlmsg_flags & NLM_F_DUMP) {
struct netlink_dump_control c = {
.dump = nfnl_acct_dump,
+ .done = netlink_dump_done,
+ .module = THIS_MODULE,
};
return netlink_dump_start(nfnl, skb, nlh, &c);
}
--
1.7.7.6
^ permalink raw reply related
* [patch v2 04/11] nf_conntrack_netlink: pass nf_conntrack_netlink module to netlink_dump_start
From: Gao feng @ 2012-09-26 8:41 UTC (permalink / raw)
To: davem, eric.dumazet, steffen.klassert
Cc: netfilter-devel, linux-rdma, netdev, linux-crypto, pablo,
stephen.hemminger, jengelh, Gao feng
In-Reply-To: <1348648888-24943-1-git-send-email-gaofeng@cn.fujitsu.com>
use proper netlink_dump_control.done and .module to avoid panic.
Signed-off-by: Gao feng <gaofeng@cn.fujitsu.com>
---
net/netfilter/nf_conntrack_netlink.c | 8 ++++++++
1 files changed, 8 insertions(+), 0 deletions(-)
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 9807f32..509a257 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -706,6 +706,7 @@ static int ctnetlink_done(struct netlink_callback *cb)
nf_ct_put((struct nf_conn *)cb->args[1]);
if (cb->data)
kfree(cb->data);
+ netlink_dump_done(cb);
return 0;
}
@@ -1022,6 +1023,7 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb,
struct netlink_dump_control c = {
.dump = ctnetlink_dump_table,
.done = ctnetlink_done,
+ .module = THIS_MODULE,
};
#ifdef CONFIG_NF_CONNTRACK_MARK
if (cda[CTA_MARK] && cda[CTA_MARK_MASK]) {
@@ -1706,6 +1708,8 @@ ctnetlink_stat_ct_cpu(struct sock *ctnl, struct sk_buff *skb,
if (nlh->nlmsg_flags & NLM_F_DUMP) {
struct netlink_dump_control c = {
.dump = ctnetlink_ct_stat_cpu_dump,
+ .done = netlink_dump_done,
+ .module = THIS_MODULE,
};
return netlink_dump_start(ctnl, skb, nlh, &c);
}
@@ -2141,6 +2145,7 @@ static int ctnetlink_exp_done(struct netlink_callback *cb)
{
if (cb->args[1])
nf_ct_expect_put((struct nf_conntrack_expect *)cb->args[1]);
+ netlink_dump_done(cb);
return 0;
}
@@ -2222,6 +2227,7 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb,
struct netlink_dump_control c = {
.dump = ctnetlink_exp_dump_table,
.done = ctnetlink_exp_done,
+ .module = THIS_MODULE,
};
return netlink_dump_start(ctnl, skb, nlh, &c);
}
@@ -2660,6 +2666,8 @@ ctnetlink_stat_exp_cpu(struct sock *ctnl, struct sk_buff *skb,
if (nlh->nlmsg_flags & NLM_F_DUMP) {
struct netlink_dump_control c = {
.dump = ctnetlink_exp_stat_cpu_dump,
+ .done = netlink_dump_done,
+ .module = THIS_MODULE,
};
return netlink_dump_start(ctnl, skb, nlh, &c);
}
--
1.7.7.6
^ permalink raw reply related
* [patch v2 03/11] unix_diag: pass unix_diag module to netlink_dump_start
From: Gao feng @ 2012-09-26 8:41 UTC (permalink / raw)
To: davem, eric.dumazet, steffen.klassert
Cc: netfilter-devel, linux-rdma, netdev, linux-crypto, pablo,
stephen.hemminger, jengelh, Gao feng
In-Reply-To: <1348648888-24943-1-git-send-email-gaofeng@cn.fujitsu.com>
set netlink_dump_control.done and .module to avoid panic.
Signed-off-by: Gao feng <gaofeng@cn.fujitsu.com>
---
net/unix/diag.c | 2 ++
1 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/net/unix/diag.c b/net/unix/diag.c
index 750b134..5e09553 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -299,6 +299,8 @@ static int unix_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h)
if (h->nlmsg_flags & NLM_F_DUMP) {
struct netlink_dump_control c = {
.dump = unix_diag_dump,
+ .done = netlink_dump_done,
+ .module = THIS_MODULE,
};
return netlink_dump_start(net->diag_nlsk, skb, h, &c);
} else
--
1.7.7.6
^ permalink raw reply related
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