* [net-next PATCH v2 3/6] net sched: mirred action fix late binding
From: Jamal Hadi Salim @ 2016-05-08 17:26 UTC (permalink / raw)
To: davem; +Cc: netdev, Jamal Hadi Salim
In-Reply-To: <1462728392-28489-1-git-send-email-jhs@emojatatu.com>
From: Jamal Hadi Salim <jhs@mojatatu.com>
The process below was broken and is fixed with this patch.
//add an mirred action and give it an instance id of 1
sudo tc actions add action mirred egress mirror dev $MDEV index 1
//create a filter which binds to mirred action id 1
sudo tc filter add dev $DEV parent ffff: protocol ip prio 1 u32\
match ip dst 17.0.0.1/32 flowid 1:10 action mirred index 1
Message before bug fix was:
RTNETLINK answers: Invalid argument
We have an error talking to the kernel
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
---
net/sched/act_mirred.c | 22 +++++++++++++++-------
1 file changed, 15 insertions(+), 7 deletions(-)
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index dea57c1..9e682c8 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -61,7 +61,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
struct tc_mirred *parm;
struct tcf_mirred *m;
struct net_device *dev;
- int ret, ok_push = 0;
+ int ret, ok_push = 0, aexists = 0;
if (nla == NULL)
return -EINVAL;
@@ -71,17 +71,27 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
if (tb[TCA_MIRRED_PARMS] == NULL)
return -EINVAL;
parm = nla_data(tb[TCA_MIRRED_PARMS]);
+
+ aexists = tcf_hash_check(tn, parm->index, a, bind);
+ if (aexists && bind)
+ return 0;
+
switch (parm->eaction) {
case TCA_EGRESS_MIRROR:
case TCA_EGRESS_REDIR:
break;
default:
+ if (aexists)
+ tcf_hash_release(a, bind);
return -EINVAL;
}
if (parm->ifindex) {
dev = __dev_get_by_index(net, parm->ifindex);
- if (dev == NULL)
+ if (dev == NULL) {
+ if (aexists)
+ tcf_hash_release(a, bind);
return -ENODEV;
+ }
switch (dev->type) {
case ARPHRD_TUNNEL:
case ARPHRD_TUNNEL6:
@@ -99,7 +109,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
dev = NULL;
}
- if (!tcf_hash_check(tn, parm->index, a, bind)) {
+ if (!aexists) {
if (dev == NULL)
return -EINVAL;
ret = tcf_hash_create(tn, parm->index, est, a,
@@ -108,9 +118,6 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
return ret;
ret = ACT_P_CREATED;
} else {
- if (bind)
- return 0;
-
tcf_hash_release(a, bind);
if (!ovr)
return -EEXIST;
@@ -195,7 +202,8 @@ out:
return retval;
}
-static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
+static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind,
+ int ref)
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_mirred *m = a->priv;
--
1.9.1
^ permalink raw reply related
* [net-next PATCH v2 4/6] net sched: simple action fix late binding
From: Jamal Hadi Salim @ 2016-05-08 17:26 UTC (permalink / raw)
To: davem; +Cc: netdev, Jamal Hadi Salim
In-Reply-To: <1462728392-28489-1-git-send-email-jhs@emojatatu.com>
From: Jamal Hadi Salim <jhs@mojatatu.com>
The process below was broken and is fixed with this patch.
//add a simple action and give it an instance id of 1
sudo tc actions add action simple sdata "foobar" index 1
//create a filter which binds to simple action id 1
sudo tc filter add dev $DEV parent ffff: protocol ip prio 1 u32\
match ip dst 17.0.0.1/32 flowid 1:10 action simple index 1
Message before fix was:
RTNETLINK answers: Invalid argument
We have an error talking to the kernel
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
---
net/sched/act_simple.c | 18 ++++++++++++------
1 file changed, 12 insertions(+), 6 deletions(-)
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 2057fd56..d9f44be 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -87,7 +87,7 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
struct tc_defact *parm;
struct tcf_defact *d;
char *defdata;
- int ret = 0, err;
+ int ret = 0, err, aexists = 0;
if (nla == NULL)
return -EINVAL;
@@ -99,13 +99,21 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
if (tb[TCA_DEF_PARMS] == NULL)
return -EINVAL;
- if (tb[TCA_DEF_DATA] == NULL)
- return -EINVAL;
parm = nla_data(tb[TCA_DEF_PARMS]);
+ aexists = tcf_hash_check(tn, parm->index, a, bind);
+ if (aexists && bind)
+ return 0;
+
+ if (tb[TCA_DEF_DATA] == NULL) {
+ if (aexists)
+ tcf_hash_release(a, bind);
+ return -EINVAL;
+ }
+
defdata = nla_data(tb[TCA_DEF_DATA]);
- if (!tcf_hash_check(tn, parm->index, a, bind)) {
+ if (!aexists) {
ret = tcf_hash_create(tn, parm->index, est, a,
sizeof(*d), bind, false);
if (ret)
@@ -122,8 +130,6 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
} else {
d = to_defact(a);
- if (bind)
- return 0;
tcf_hash_release(a, bind);
if (!ovr)
return -EEXIST;
--
1.9.1
^ permalink raw reply related
* [net-next PATCH v2 5/6] net sched: skbedit action fix late binding
From: Jamal Hadi Salim @ 2016-05-08 17:26 UTC (permalink / raw)
To: davem; +Cc: netdev, Jamal Hadi Salim
In-Reply-To: <1462728392-28489-1-git-send-email-jhs@emojatatu.com>
From: Jamal Hadi Salim <jhs@mojatatu.com>
The process below was broken and is fixed with this patch.
//add a skbedit action and give it an instance id of 1
sudo tc actions add action skbedit mark 10 index 1
//create a filter which binds to skbedit action id 1
sudo tc filter add dev $DEV parent ffff: protocol ip prio 1 u32\
match ip dst 17.0.0.1/32 flowid 1:10 action skbedit index 1
Message before fix was:
RTNETLINK answers: Invalid argument
We have an error talking to the kernel
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
---
net/sched/act_skbedit.c | 22 +++++++++++++++-------
1 file changed, 15 insertions(+), 7 deletions(-)
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 51b2499..784b478 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -69,7 +69,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
struct tcf_skbedit *d;
u32 flags = 0, *priority = NULL, *mark = NULL;
u16 *queue_mapping = NULL;
- int ret = 0, err;
+ int ret = 0, err, aexists = 0;
if (nla == NULL)
return -EINVAL;
@@ -96,12 +96,22 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
mark = nla_data(tb[TCA_SKBEDIT_MARK]);
}
- if (!flags)
- return -EINVAL;
-
parm = nla_data(tb[TCA_SKBEDIT_PARMS]);
- if (!tcf_hash_check(tn, parm->index, a, bind)) {
+ aexists = tcf_hash_check(tn, parm->index, a, bind);
+
+ /* if action exists and this is a late filter bind, no need
+ * to continue processing
+ */
+ if (aexists && bind)
+ return 0;
+
+ if (!flags) {
+ tcf_hash_release(a, bind);
+ return -EINVAL;
+ }
+
+ if (!aexists) {
ret = tcf_hash_create(tn, parm->index, est, a,
sizeof(*d), bind, false);
if (ret)
@@ -111,8 +121,6 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
ret = ACT_P_CREATED;
} else {
d = to_skbedit(a);
- if (bind)
- return 0;
tcf_hash_release(a, bind);
if (!ovr)
return -EEXIST;
--
1.9.1
^ permalink raw reply related
* [net-next PATCH v2 6/6] net sched: ife action fix late binding
From: Jamal Hadi Salim @ 2016-05-08 17:26 UTC (permalink / raw)
To: davem; +Cc: netdev, Jamal Hadi Salim
In-Reply-To: <1462728392-28489-1-git-send-email-jhs@emojatatu.com>
From: Jamal Hadi Salim <jhs@mojatatu.com>
The process below was broken and is fixed with this patch.
//add an ife action and give it an instance id of 1
sudo tc actions add action ife encode \
type 0xDEAD allow mark dst 02:15:15:15:15:15 index 1
//create a filter which binds to skbedit action id 1
sudo tc filter add dev $DEV parent ffff: protocol ip prio 1 u32\
match ip dst 17.0.0.1/32 flowid 1:11 action ife index 1
Message before fix was:
RTNETLINK answers: Invalid argument
We have an error talking to the kernel
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
---
net/sched/act_ife.c | 16 +++++++++++-----
1 file changed, 11 insertions(+), 5 deletions(-)
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 556f44c..17520ed 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -423,7 +423,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
u16 ife_type = 0;
u8 *daddr = NULL;
u8 *saddr = NULL;
- int ret = 0;
+ int ret = 0, aexists = 0;
int err;
err = nla_parse_nested(tb, TCA_IFE_MAX, nla, ife_policy);
@@ -435,25 +435,29 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
parm = nla_data(tb[TCA_IFE_PARMS]);
+ aexists = tcf_hash_check(tn, parm->index, a, bind);
+ if (aexists && bind)
+ return 0;
+
if (parm->flags & IFE_ENCODE) {
/* Until we get issued the ethertype, we cant have
* a default..
**/
if (!tb[TCA_IFE_TYPE]) {
+ if (aexists)
+ tcf_hash_release(a, bind);
pr_info("You MUST pass etherype for encoding\n");
return -EINVAL;
}
}
- if (!tcf_hash_check(tn, parm->index, a, bind)) {
+ if (!aexists) {
ret = tcf_hash_create(tn, parm->index, est, a, sizeof(*ife),
bind, false);
if (ret)
return ret;
ret = ACT_P_CREATED;
} else {
- if (bind) /* dont override defaults */
- return 0;
tcf_hash_release(a, bind);
if (!ovr)
return -EEXIST;
@@ -495,6 +499,8 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
NULL);
if (err) {
metadata_parse_err:
+ if (aexists)
+ tcf_hash_release(a, bind);
if (ret == ACT_P_CREATED)
_tcf_ife_cleanup(a, bind);
@@ -689,7 +695,7 @@ static int tcf_ife_encode(struct sk_buff *skb, const struct tc_action *a,
/*
OUTERHDR:TOTMETALEN:{TLVHDR:Metadatum:TLVHDR..}:ORIGDATA
where ORIGDATA = original ethernet header ...
- */
+ */
u16 metalen = ife_get_sz(skb, ife);
int hdrm = metalen + skb->dev->hard_header_len + IFE_METAHDRLEN;
unsigned int skboff = skb->dev->hard_header_len;
--
1.9.1
^ permalink raw reply related
* Re: [net-next PATCH v2 0/6] net sched: Fix broken late binding of actions
From: Jamal Hadi Salim @ 2016-05-08 17:29 UTC (permalink / raw)
To: davem; +Cc: netdev
In-Reply-To: <1462728392-28489-1-git-send-email-jhs@emojatatu.com>
On 16-05-08 01:26 PM, Jamal Hadi Salim wrote:
> From: Jamal Hadi Salim <jhs@mojatatu.com>
>
> Some actions were broken in allowing for late binding of actions.
Dave, these deserve to go into -stable as well.
cheers,
jamal
^ permalink raw reply
* Re: [PATCH v2 net-next] ifb: support more features
From: Eric Dumazet @ 2016-05-08 17:35 UTC (permalink / raw)
To: David Miller; +Cc: Vlad Yasevich, Alexander Duyck, netdev, Tom Herbert
In-Reply-To: <1462723712.23934.18.camel@edumazet-glaptop3.roam.corp.google.com>
On Sun, 2016-05-08 at 09:08 -0700, Eric Dumazet wrote:
> So we probably need to make sure the network header is properly set for
> the segments. Then skb_reset_mac_len(nskb); would work as intended.
>
> Since skb_segment() is called from the deepest point in GSO path,
> it always see the inner network header.
>
> Sounds like skb_reset_network_header() calls done in inet_gso_segment()
> and ipv6_gso_segment() should only be done for the outer header, (when
> SKB_GSO_CB(skb)->encap_level == 0), or even better, only done in
> skb_mac_gso_segment()
>
> Then we need to use the proper (inner) network header in
> tcp4_gso_segment() and tcp6_gso_segment(), as they currently use
> ip_hdr() and ipv6_hdr()
>
Prototype patch works for me (but GRE/UDP offloads might need some
work), and would even save few cycles...
Unfortunately GSO for GRE/UDP is kind of mess.
net/core/dev.c | 1 +
net/ipv4/af_inet.c | 9 +++------
net/ipv4/tcp_offload.c | 2 +-
net/ipv6/ip6_offload.c | 9 +++------
net/ipv6/tcpv6_offload.c | 2 +-
5 files changed, 9 insertions(+), 14 deletions(-)
diff --git a/net/core/dev.c b/net/core/dev.c
index 5c925ac50b95..3a9035ec862b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2658,6 +2658,7 @@ struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb,
return ERR_PTR(-EINVAL);
__skb_pull(skb, vlan_depth);
+ skb_reset_network_header(skb);
rcu_read_lock();
list_for_each_entry_rcu(ptype, &offload_base, list) {
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 9e481992dbae..fef6335a75bc 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1220,12 +1220,12 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
0)))
goto out;
- skb_reset_network_header(skb);
- nhoff = skb_network_header(skb) - skb_mac_header(skb);
+ skb_reset_inner_network_header(skb);
+ nhoff = skb->data - skb_mac_header(skb);
if (unlikely(!pskb_may_pull(skb, sizeof(*iph))))
goto out;
- iph = ip_hdr(skb);
+ iph = inner_ip_hdr(skb);
ihl = iph->ihl * 4;
if (ihl < sizeof(*iph))
goto out;
@@ -1274,9 +1274,6 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
}
iph->tot_len = htons(skb->len - nhoff);
ip_send_check(iph);
- if (encap)
- skb_reset_inner_headers(skb);
- skb->network_header = (u8 *)iph - skb->head;
} while ((skb = skb->next));
out:
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 773083b7f1e9..f0650b50680e 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -36,7 +36,7 @@ static struct sk_buff *tcp4_gso_segment(struct sk_buff *skb,
return ERR_PTR(-EINVAL);
if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) {
- const struct iphdr *iph = ip_hdr(skb);
+ const struct iphdr *iph = inner_ip_hdr(skb);
struct tcphdr *th = tcp_hdr(skb);
/* Set up checksum pseudo header, usually expect stack to
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 82e9f3076028..8d27299f86e4 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -84,8 +84,8 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
0)))
goto out;
- skb_reset_network_header(skb);
- nhoff = skb_network_header(skb) - skb_mac_header(skb);
+ skb_reset_inner_network_header(skb);
+ nhoff = skb->data - skb_mac_header(skb);
if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
goto out;
@@ -94,7 +94,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
features &= skb->dev->hw_enc_features;
SKB_GSO_CB(skb)->encap_level += sizeof(*ipv6h);
- ipv6h = ipv6_hdr(skb);
+ ipv6h = inner_ipv6_hdr(skb);
__skb_pull(skb, sizeof(*ipv6h));
segs = ERR_PTR(-EPROTONOSUPPORT);
@@ -118,7 +118,6 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
for (skb = segs; skb; skb = skb->next) {
ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff);
ipv6h->payload_len = htons(skb->len - nhoff - sizeof(*ipv6h));
- skb->network_header = (u8 *)ipv6h - skb->head;
if (udpfrag) {
unfrag_ip6hlen = ip6_find_1stfragopt(skb, &prevhdr);
@@ -129,8 +128,6 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
offset += (ntohs(ipv6h->payload_len) -
sizeof(struct frag_hdr));
}
- if (encap)
- skb_reset_inner_headers(skb);
}
out:
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index d883c9204c01..8e747a295bce 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -50,7 +50,7 @@ static struct sk_buff *tcp6_gso_segment(struct sk_buff *skb,
return ERR_PTR(-EINVAL);
if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) {
- const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+ const struct ipv6hdr *ipv6h = inner_ipv6_hdr(skb);
struct tcphdr *th = tcp_hdr(skb);
/* Set up pseudo header, usually expect stack to have done
^ permalink raw reply related
* Re: [PATCH v9 net-next 1/2] hv_sock: introduce Hyper-V Sockets
From: David Miller @ 2016-05-08 17:45 UTC (permalink / raw)
To: decui
Cc: olaf, gregkh, jasowang, linux-kernel, joe, netdev, apw, devel,
haiyangz
In-Reply-To: <BLUPR03MB141044B2FC50DE43401C8C17BF7F0@BLUPR03MB1410.namprd03.prod.outlook.com>
From: Dexuan Cui <decui@microsoft.com>
Date: Sun, 8 May 2016 06:11:04 +0000
> Thanks for pointing this out!
> I understand, so I think I should add a module parameter, e.g.,
> "hv_sock.max_socket_number" with a default value, say, 1024?
No, you should get rid of the huge multi-page buffers.
^ permalink raw reply
* Re: [PATCH 1/2] net: phy: add ethtool_phy_{get|set}_link_ksettings
From: Florian Fainelli @ 2016-05-08 18:19 UTC (permalink / raw)
To: Philippe Reynes, Ben Hutchings; +Cc: fugang.duan, davem, netdev, linux-kernel
In-Reply-To: <572E72A2.9010004@gmail.com>
On May 7, 2016 3:56:34 PM PDT, Philippe Reynes <tremyfr@gmail.com> wrote:
>On 07/05/16 13:59, Ben Hutchings wrote:
>> On Sat, 2016-05-07 at 01:18 +0200, Philippe Reynes wrote:
>>> The callback {get|set}_link_ksettings are often defined
>>> in a very close way. There are mainly two differences in
>>> those callback:
>>> - the name of the netdev private structure
>>> - the name of the struct phydev in the private structure
>>>
>>> We add two defines ethtool_phy_{get|set}_link_ksettings
>>> to avoid writing severals times almost the same function.
>> [...]
>>
>> I don't think there's no need to access a private structure, as
>there's
>> a phydev pointer in struct net_device. If some drivers don't
>maintain
>> that pointer, they should be changed to do so. Then they can
>> use generic implementations of {get,set}_link_ksettings provided by
>> phylib.
>
>If we could use the phydev in the struct net_device, we could write a
>generic function for {get|set}_link_ksettings. It's a good idea.
>
>But I've quickly looked and a lot of ethernet driver use the private
>structure to store the phydev. If the ethernet driver may use the
>struct net_device for phydev, do you know why so many drivers use
>the private structure ?
The introduction of a phy_device pointer in net_device came much later than the introduction and use of PHYLIB by most drivers so it is probably just an oversight.
>
>If everybody agree, I can send a new version with a generic
>{get|set}_link_ksettings
>and a update of fec to use the phydev store in the structure
>net_device.
Yes, that sounds very reasonable. It might be possible to cook a coccinelle patch which replaces the use of a private phy_device pointer and utilize the one from net_device.
--
Florian
^ permalink raw reply
* Re: [PATCH net-next 5/7] Driver: Vmxnet3: Add support for get_coalesce, set_coalesce ethtool operations
From: Shrikrishna Khare @ 2016-05-08 20:55 UTC (permalink / raw)
To: Ben Hutchings; +Cc: netdev, linux-kernel, pv-drivers, Keyong Sun, Manoj Tammali
In-Reply-To: <1462622686.19332.33.camel@decadent.org.uk>
[-- Attachment #1: Type: TEXT/PLAIN, Size: 1816 bytes --]
On Sat, 7 May 2016, Ben Hutchings wrote:
> On Fri, 2016-05-06 at 16:12 -0700, Shrikrishna Khare wrote:
> [...]
> > +static int
> > +vmxnet3_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec)
> > +{
> [...]
> > + switch (ec->rx_coalesce_usecs) {
> > + case VMXNET3_COALESCE_DEFAULT:
> > + case VMXNET3_COALESCE_DISABLED:
> > + case VMXNET3_COALESCE_ADAPT:
> > + if (ec->tx_max_coalesced_frames ||
> > + ec->tx_max_coalesced_frames_irq ||
> > + ec->rx_max_coalesced_frames_irq) {
> > + return -EINVAL;
> > + }
> > + memset(adapter->coal_conf, 0, sizeof(*adapter->coal_conf));
> > + adapter->coal_conf->coalMode = ec->rx_coalesce_usecs;
> > + break;
> > + case VMXNET3_COALESCE_STATIC:
> [...]
>
> I don't want to see drivers introducing magic values for fields that
> are denominated in microseconds (especially not for 0, which is the
> correct way to specify 'no coalescing'). If the current
> ethtool_coalesce structure is inadequate, propose an extension.
For vmxnet3, we need an ethtool mechanism to indicate coalescing mode to
the device.
Would a patch that maps 0 to 'no coalescing' be acceptable? That is:
rx-usecs = 0 -> coalescing disabled.
rx-usecs = 1 -> default (chosen by the device).
rx-usecs = 2 -> adaptive coalescing.
rx-usecs = 3 -> static coalescing.
all other rx-usecs values -> rate based coalescing where rx-usecs denotes
rate.
Alternatively: I don't think new members could be added to struct
ethtool_coalesce without breaking compatibility. Thus, I could extend
coalescing as follows:
- new struct ethtool_coalesce_v2 with coalesce_mode (along with all the
members of struct ethtool_coalesce).
- introduce new ETHTOOL_{G,S}COALESCE_V2 commands.
- extend userspace ethtool to invoke new commands.
Could you please advice?
Thanks,
Shri
^ permalink raw reply
* [PATCH v2 0/3] net: ethtool: add ethtool_op_{get|set}_link_ksettings
From: Philippe Reynes @ 2016-05-08 21:44 UTC (permalink / raw)
To: fugang.duan, davem, ben, kan.liang, decot, aduyck, jiri,
jacob.e.keller, tom, andrew
Cc: netdev, linux-kernel, Philippe Reynes
Ethtool callbacks {get|set}_link_ksettings may be the
same for many drivers. So we add two generics callbacks
ethtool_op_{get|set}_link_ksettings.
To use those generics callbacks, the ethernet driver must
use the pointer phydev contained in struct net_device, and
not use a private structure to store this pointer.
Changelog:
v2:
- use generic function instead of macro
- ethernet driver use the pointer phydev provided by struct net_device
Those idea were provided by Ben Hutchings,
and Florian Fainelli acknowledge them.
Philippe Reynes (3):
net: core: ethtool: add ethtool_op_{get|set}_link_ksettings
net: ethernet: fec: use phydev from struct net_device
net: ethernet: fec: use ethtool_op_{get|set}_link_ksettings
drivers/net/ethernet/freescale/fec.h | 1 -
drivers/net/ethernet/freescale/fec_main.c | 71 +++++++++--------------------
include/linux/ethtool.h | 5 ++
net/core/ethtool.c | 24 ++++++++++
4 files changed, 50 insertions(+), 51 deletions(-)
--
1.7.4.4
^ permalink raw reply
* [PATCH v2 1/3] net: core: ethtool: add ethtool_op_{get|set}_link_ksettings
From: Philippe Reynes @ 2016-05-08 21:44 UTC (permalink / raw)
To: fugang.duan, davem, ben, kan.liang, decot, aduyck, jiri,
jacob.e.keller, tom, andrew
Cc: netdev, linux-kernel, Philippe Reynes
In-Reply-To: <1462743877-31738-1-git-send-email-tremyfr@gmail.com>
Ethtool callbacks {get|set}_link_ksettings are often the same, so
we add two generics functions ethtool_op_{get|set}_link_ksettings
to avoid writing severals times the same function.
Signed-off-by: Philippe Reynes <tremyfr@gmail.com>
---
include/linux/ethtool.h | 5 +++++
net/core/ethtool.c | 24 ++++++++++++++++++++++++
2 files changed, 29 insertions(+), 0 deletions(-)
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 9ded8c6..9a55836 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -157,6 +157,11 @@ void ethtool_convert_legacy_u32_to_link_mode(unsigned long *dst,
bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32,
const unsigned long *src);
+int ethtool_op_get_link_ksettings(struct net_device *ndev,
+ struct ethtool_link_ksettings *cmd);
+int ethtool_op_set_link_ksettings(struct net_device *ndev,
+ const struct ethtool_link_ksettings *cmd);
+
/**
* struct ethtool_ops - optional netdev operations
* @get_settings: DEPRECATED, use %get_link_ksettings/%set_link_ksettings
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index bdb4013..b605fb1 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -852,6 +852,30 @@ static int ethtool_set_settings(struct net_device *dev, void __user *useraddr)
return dev->ethtool_ops->set_settings(dev, &cmd);
}
+int ethtool_op_get_link_ksettings(struct net_device *ndev,
+ struct ethtool_link_ksettings *cmd)
+{
+ struct phy_device *phydev = ndev->phydev;
+
+ if (!phydev)
+ return -ENODEV;
+
+ return phy_ethtool_ksettings_get(phydev, cmd);
+}
+EXPORT_SYMBOL(ethtool_op_get_link_ksettings);
+
+int ethtool_op_set_link_ksettings(struct net_device *ndev,
+ const struct ethtool_link_ksettings *cmd)
+{
+ struct phy_device *phydev = ndev->phydev;
+
+ if (!phydev)
+ return -ENODEV;
+
+ return phy_ethtool_ksettings_set(phydev, cmd);
+}
+EXPORT_SYMBOL(ethtool_op_set_link_ksettings);
+
static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev,
void __user *useraddr)
{
--
1.7.4.4
^ permalink raw reply related
* [PATCH v2 2/3] net: ethernet: fec: use phydev from struct net_device
From: Philippe Reynes @ 2016-05-08 21:44 UTC (permalink / raw)
To: fugang.duan, davem, ben, kan.liang, decot, aduyck, jiri,
jacob.e.keller, tom, andrew
Cc: netdev, linux-kernel, Philippe Reynes
In-Reply-To: <1462743877-31738-1-git-send-email-tremyfr@gmail.com>
The private structure contain a pointer to phydev, but the structure
net_device already contain such pointer. So we can remove the pointer
phydev in the private structure, and update the driver to use the one
contained in struct net_device.
Signed-off-by: Philippe Reynes <tremyfr@gmail.com>
---
drivers/net/ethernet/freescale/fec.h | 1 -
drivers/net/ethernet/freescale/fec_main.c | 49 ++++++++++++----------------
2 files changed, 21 insertions(+), 29 deletions(-)
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 195122e..f58f9ea 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -517,7 +517,6 @@ struct fec_enet_private {
/* Phylib and MDIO interface */
struct mii_bus *mii_bus;
- struct phy_device *phy_dev;
int mii_timeout;
uint phy_speed;
phy_interface_t phy_interface;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index bfa10c3..e1d24ff 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -967,10 +967,10 @@ fec_restart(struct net_device *ndev)
rcntl &= ~(1 << 8);
/* 1G, 100M or 10M */
- if (fep->phy_dev) {
- if (fep->phy_dev->speed == SPEED_1000)
+ if (ndev->phydev) {
+ if (ndev->phydev->speed == SPEED_1000)
ecntl |= (1 << 5);
- else if (fep->phy_dev->speed == SPEED_100)
+ else if (ndev->phydev->speed == SPEED_100)
rcntl &= ~(1 << 9);
else
rcntl |= (1 << 9);
@@ -991,7 +991,7 @@ fec_restart(struct net_device *ndev)
*/
cfgr = (fep->phy_interface == PHY_INTERFACE_MODE_RMII)
? BM_MIIGSK_CFGR_RMII : BM_MIIGSK_CFGR_MII;
- if (fep->phy_dev && fep->phy_dev->speed == SPEED_10)
+ if (ndev->phydev && ndev->phydev->speed == SPEED_10)
cfgr |= BM_MIIGSK_CFGR_FRCONT_10M;
writel(cfgr, fep->hwp + FEC_MIIGSK_CFGR);
@@ -1005,7 +1005,7 @@ fec_restart(struct net_device *ndev)
/* enable pause frame*/
if ((fep->pause_flag & FEC_PAUSE_FLAG_ENABLE) ||
((fep->pause_flag & FEC_PAUSE_FLAG_AUTONEG) &&
- fep->phy_dev && fep->phy_dev->pause)) {
+ ndev->phydev && ndev->phydev->pause)) {
rcntl |= FEC_ENET_FCE;
/* set FIFO threshold parameter to reduce overrun */
@@ -1679,7 +1679,7 @@ static void fec_get_mac(struct net_device *ndev)
static void fec_enet_adjust_link(struct net_device *ndev)
{
struct fec_enet_private *fep = netdev_priv(ndev);
- struct phy_device *phy_dev = fep->phy_dev;
+ struct phy_device *phy_dev = ndev->phydev;
int status_change = 0;
/* Prevent a state halted on mii error */
@@ -1879,8 +1879,6 @@ static int fec_enet_mii_probe(struct net_device *ndev)
int phy_id;
int dev_id = fep->dev_id;
- fep->phy_dev = NULL;
-
if (fep->phy_node) {
phy_dev = of_phy_connect(ndev, fep->phy_node,
&fec_enet_adjust_link, 0,
@@ -1928,7 +1926,6 @@ static int fec_enet_mii_probe(struct net_device *ndev)
phy_dev->advertising = phy_dev->supported;
- fep->phy_dev = phy_dev;
fep->link = 0;
fep->full_duplex = 0;
@@ -2061,8 +2058,7 @@ static void fec_enet_mii_remove(struct fec_enet_private *fep)
static int fec_enet_get_link_ksettings(struct net_device *ndev,
struct ethtool_link_ksettings *cmd)
{
- struct fec_enet_private *fep = netdev_priv(ndev);
- struct phy_device *phydev = fep->phy_dev;
+ struct phy_device *phydev = ndev->phydev;
if (!phydev)
return -ENODEV;
@@ -2073,8 +2069,7 @@ static int fec_enet_get_link_ksettings(struct net_device *ndev,
static int fec_enet_set_link_ksettings(struct net_device *ndev,
const struct ethtool_link_ksettings *cmd)
{
- struct fec_enet_private *fep = netdev_priv(ndev);
- struct phy_device *phydev = fep->phy_dev;
+ struct phy_device *phydev = ndev->phydev;
if (!phydev)
return -ENODEV;
@@ -2214,7 +2209,7 @@ static int fec_enet_set_pauseparam(struct net_device *ndev,
{
struct fec_enet_private *fep = netdev_priv(ndev);
- if (!fep->phy_dev)
+ if (!ndev->phydev)
return -ENODEV;
if (pause->tx_pause != pause->rx_pause) {
@@ -2230,17 +2225,17 @@ static int fec_enet_set_pauseparam(struct net_device *ndev,
fep->pause_flag |= pause->autoneg ? FEC_PAUSE_FLAG_AUTONEG : 0;
if (pause->rx_pause || pause->autoneg) {
- fep->phy_dev->supported |= ADVERTISED_Pause;
- fep->phy_dev->advertising |= ADVERTISED_Pause;
+ ndev->phydev->supported |= ADVERTISED_Pause;
+ ndev->phydev->advertising |= ADVERTISED_Pause;
} else {
- fep->phy_dev->supported &= ~ADVERTISED_Pause;
- fep->phy_dev->advertising &= ~ADVERTISED_Pause;
+ ndev->phydev->supported &= ~ADVERTISED_Pause;
+ ndev->phydev->advertising &= ~ADVERTISED_Pause;
}
if (pause->autoneg) {
if (netif_running(ndev))
fec_stop(ndev);
- phy_start_aneg(fep->phy_dev);
+ phy_start_aneg(ndev->phydev);
}
if (netif_running(ndev)) {
napi_disable(&fep->napi);
@@ -2356,8 +2351,7 @@ static int fec_enet_get_sset_count(struct net_device *dev, int sset)
static int fec_enet_nway_reset(struct net_device *dev)
{
- struct fec_enet_private *fep = netdev_priv(dev);
- struct phy_device *phydev = fep->phy_dev;
+ struct phy_device *phydev = dev->phydev;
if (!phydev)
return -ENODEV;
@@ -2588,7 +2582,7 @@ static const struct ethtool_ops fec_enet_ethtool_ops = {
static int fec_enet_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd)
{
struct fec_enet_private *fep = netdev_priv(ndev);
- struct phy_device *phydev = fep->phy_dev;
+ struct phy_device *phydev = ndev->phydev;
if (!netif_running(ndev))
return -EINVAL;
@@ -2843,7 +2837,7 @@ fec_enet_open(struct net_device *ndev)
goto err_enet_mii_probe;
napi_enable(&fep->napi);
- phy_start(fep->phy_dev);
+ phy_start(ndev->phydev);
netif_tx_start_all_queues(ndev);
device_set_wakeup_enable(&ndev->dev, fep->wol_flag &
@@ -2867,7 +2861,7 @@ fec_enet_close(struct net_device *ndev)
{
struct fec_enet_private *fep = netdev_priv(ndev);
- phy_stop(fep->phy_dev);
+ phy_stop(ndev->phydev);
if (netif_device_present(ndev)) {
napi_disable(&fep->napi);
@@ -2875,8 +2869,7 @@ fec_enet_close(struct net_device *ndev)
fec_stop(ndev);
}
- phy_disconnect(fep->phy_dev);
- fep->phy_dev = NULL;
+ phy_disconnect(ndev->phydev);
fec_enet_clk_enable(ndev, false);
pinctrl_pm_select_sleep_state(&fep->pdev->dev);
@@ -3504,7 +3497,7 @@ static int __maybe_unused fec_suspend(struct device *dev)
if (netif_running(ndev)) {
if (fep->wol_flag & FEC_WOL_FLAG_ENABLE)
fep->wol_flag |= FEC_WOL_FLAG_SLEEP_ON;
- phy_stop(fep->phy_dev);
+ phy_stop(ndev->phydev);
napi_disable(&fep->napi);
netif_tx_lock_bh(ndev);
netif_device_detach(ndev);
@@ -3564,7 +3557,7 @@ static int __maybe_unused fec_resume(struct device *dev)
netif_device_attach(ndev);
netif_tx_unlock_bh(ndev);
napi_enable(&fep->napi);
- phy_start(fep->phy_dev);
+ phy_start(ndev->phydev);
}
rtnl_unlock();
--
1.7.4.4
^ permalink raw reply related
* [PATCH v2 3/3] net: ethernet: fec: use ethtool_op_{get|set}_link_ksettings
From: Philippe Reynes @ 2016-05-08 21:44 UTC (permalink / raw)
To: fugang.duan, davem, ben, kan.liang, decot, aduyck, jiri,
jacob.e.keller, tom, andrew
Cc: netdev, linux-kernel, Philippe Reynes
In-Reply-To: <1462743877-31738-1-git-send-email-tremyfr@gmail.com>
There are two generics functions ethtool_op_{get|set}_link_ksettings,
so we can use them instead of defining the same code in the driver.
Signed-off-by: Philippe Reynes <tremyfr@gmail.com>
---
drivers/net/ethernet/freescale/fec_main.c | 26 ++------------------------
1 files changed, 2 insertions(+), 24 deletions(-)
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index e1d24ff..f2dae6c 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -2055,28 +2055,6 @@ static void fec_enet_mii_remove(struct fec_enet_private *fep)
}
}
-static int fec_enet_get_link_ksettings(struct net_device *ndev,
- struct ethtool_link_ksettings *cmd)
-{
- struct phy_device *phydev = ndev->phydev;
-
- if (!phydev)
- return -ENODEV;
-
- return phy_ethtool_ksettings_get(phydev, cmd);
-}
-
-static int fec_enet_set_link_ksettings(struct net_device *ndev,
- const struct ethtool_link_ksettings *cmd)
-{
- struct phy_device *phydev = ndev->phydev;
-
- if (!phydev)
- return -ENODEV;
-
- return phy_ethtool_ksettings_set(phydev, cmd);
-}
-
static void fec_enet_get_drvinfo(struct net_device *ndev,
struct ethtool_drvinfo *info)
{
@@ -2575,8 +2553,8 @@ static const struct ethtool_ops fec_enet_ethtool_ops = {
.set_tunable = fec_enet_set_tunable,
.get_wol = fec_enet_get_wol,
.set_wol = fec_enet_set_wol,
- .get_link_ksettings = fec_enet_get_link_ksettings,
- .set_link_ksettings = fec_enet_set_link_ksettings,
+ .get_link_ksettings = ethtool_op_get_link_ksettings,
+ .set_link_ksettings = ethtool_op_set_link_ksettings,
};
static int fec_enet_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd)
--
1.7.4.4
^ permalink raw reply related
* [PATCH net-next] gtp: add initial driver for datapath of GPRS Tunneling Protocol (GTP-U)
From: Pablo Neira Ayuso @ 2016-05-08 21:59 UTC (permalink / raw)
To: netdev; +Cc: davem, Andreas Schultz, Harald Welte, openbsc
This is an initial implementation of a netdev driver for GTP datapath
(GTP-U) v0 and v1, according to the GSM TS 09.60 and 3GPP TS 29.060
standards. This tunneling protocol is used to prevent subscribers from
accessing mobile carrier core network infrastructure.
This implementation requires a GGSN userspace daemon that implements the
signaling protocol (GTP-C), such as OpenGGSN [1]. This userspace daemon
updates the PDP context database that represents active subscriber
sessions through a genetlink interface.
For more context on this tunneling protocol, you can check the slides
that were presented during the NetDev 1.1 [2].
Only IPv4 is supported at this time.
[1] http://git.osmocom.org/openggsn/
[2] http://www.netdevconf.org/1.1/proceedings/slides/schultz-welte-osmocom-gtp.pdf
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
drivers/net/Kconfig | 17 +
drivers/net/Makefile | 1 +
drivers/net/gtp.c | 1364 ++++++++++++++++++++++++++++++++++++++++++
include/net/gtp.h | 34 ++
include/uapi/linux/Kbuild | 1 +
include/uapi/linux/gtp.h | 33 +
include/uapi/linux/if_link.h | 10 +
include/uapi/linux/udp.h | 3 +-
8 files changed, 1462 insertions(+), 1 deletion(-)
create mode 100644 drivers/net/gtp.c
create mode 100644 include/net/gtp.h
create mode 100644 include/uapi/linux/gtp.h
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index a24c18e..4f13c5c 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -193,6 +193,23 @@ config GENEVE
To compile this driver as a module, choose M here: the module
will be called geneve.
+config GTP
+ tristate "GPRS Tunneling Protocol datapath (GTP-U)"
+ depends on INET && NET_UDP_TUNNEL
+ select NET_IP_TUNNEL
+ ---help---
+ This allows one to create gtp virtual interfaces that provide
+ the GPRS Tunneling Protocol datapath (GTP-U). This tunneling protocol
+ is used to prevent subscribers from accessing mobile carrier core
+ network infrastructure. This driver requires a userspace software that
+ implements the signaling protocol (GTP-C) to update its PDP context
+ base, such as OpenGGSN <http://git.osmocom.org/openggsn/). This
+ tunneling protocol is implemented according to the GSM TS 09.60 and
+ 3GPP TS 29.060 standards.
+
+ To compile this drivers as a module, choose M here: the module
+ wil be called gtp.
+
config MACSEC
tristate "IEEE 802.1AE MAC-level encryption (MACsec)"
select CRYPTO
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 1aa7cb8..7336cbd 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -25,6 +25,7 @@ obj-$(CONFIG_VETH) += veth.o
obj-$(CONFIG_VIRTIO_NET) += virtio_net.o
obj-$(CONFIG_VXLAN) += vxlan.o
obj-$(CONFIG_GENEVE) += geneve.o
+obj-$(CONFIG_GTP) += gtp.o
obj-$(CONFIG_NLMON) += nlmon.o
obj-$(CONFIG_NET_VRF) += vrf.o
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
new file mode 100644
index 0000000..8ce1104
--- /dev/null
+++ b/drivers/net/gtp.c
@@ -0,0 +1,1364 @@
+/* GTP according to GSM TS 09.60 / 3GPP TS 29.060
+ *
+ * (C) 2012-2014 by sysmocom - s.f.m.c. GmbH
+ * (C) 2016 by Pablo Neira Ayuso <pablo@netfilter.org>
+ *
+ * Author: Harald Welte <hwelte@sysmocom.de>
+ * Pablo Neira Ayuso <pablo@netfilter.org>
+ * Andreas Schultz <aschultz@travelping.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/version.h>
+#include <linux/skbuff.h>
+#include <linux/udp.h>
+#include <linux/rculist.h>
+#include <linux/jhash.h>
+#include <linux/if_tunnel.h>
+#include <linux/net.h>
+#include <linux/file.h>
+#include <linux/gtp.h>
+
+#include <net/net_namespace.h>
+#include <net/protocol.h>
+#include <net/ip.h>
+#include <net/udp.h>
+#include <net/udp_tunnel.h>
+#include <net/icmp.h>
+#include <net/xfrm.h>
+#include <net/genetlink.h>
+#include <net/netns/generic.h>
+#include <net/gtp.h>
+
+/* An active session for the subscriber. */
+struct pdp_ctx {
+ struct hlist_node hlist_tid;
+ struct hlist_node hlist_addr;
+
+ union {
+ u64 tid;
+ struct {
+ u64 tid;
+ u16 flow;
+ } v0;
+ struct {
+ u32 i_tei;
+ u32 o_tei;
+ } v1;
+ } u;
+ u8 gtp_version;
+ u16 af;
+
+ struct in_addr ms_addr_ip4;
+ struct in_addr sgsn_addr_ip4;
+
+ atomic_t tx_seq;
+ struct rcu_head rcu_head;
+};
+
+/* One instance of the GTP device. */
+struct gtp_dev {
+ struct list_head list;
+
+ struct socket *sock0;
+ struct socket *sock1u;
+
+ struct net *net;
+ struct net_device *dev;
+
+ unsigned int hash_size;
+ struct hlist_head *tid_hash;
+ struct hlist_head *addr_hash;
+};
+
+static int gtp_net_id __read_mostly;
+
+struct gtp_net {
+ struct list_head gtp_dev_list;
+};
+
+static u32 gtp_h_initval;
+
+static inline u32 gtp0_hashfn(u64 tid)
+{
+ u32 *tid32 = (u32 *) &tid;
+ return jhash_2words(tid32[0], tid32[1], gtp_h_initval);
+}
+
+static inline u32 gtp1u_hashfn(u32 tid)
+{
+ return jhash_1word(tid, gtp_h_initval);
+}
+
+static inline u32 ipv4_hashfn(__be32 ip)
+{
+ return jhash_1word((__force u32)ip, gtp_h_initval);
+}
+
+/* Resolve a PDP context structure based on the 64bit TID. */
+static struct pdp_ctx *gtp0_pdp_find(struct gtp_dev *gtp, u64 tid)
+{
+ struct hlist_head *head;
+ struct pdp_ctx *pdp;
+
+ head = >p->tid_hash[gtp0_hashfn(tid) % gtp->hash_size];
+
+ hlist_for_each_entry_rcu(pdp, head, hlist_tid) {
+ if (pdp->gtp_version == GTP_V0 &&
+ pdp->u.v0.tid == tid)
+ return pdp;
+ }
+ return NULL;
+}
+
+/* Resolve a PDP context structure based on the 32bit TEI. */
+static struct pdp_ctx *gtp1_pdp_find(struct gtp_dev *gtp, u32 tid)
+{
+ struct hlist_head *head;
+ struct pdp_ctx *pdp;
+
+ head = >p->tid_hash[gtp1u_hashfn(tid) % gtp->hash_size];
+
+ hlist_for_each_entry_rcu(pdp, head, hlist_tid) {
+ if (pdp->gtp_version == GTP_V1 &&
+ pdp->u.v1.i_tei == tid)
+ return pdp;
+ }
+ return NULL;
+}
+
+/* Resolve a PDP context based on IPv4 address of MS. */
+static struct pdp_ctx *ipv4_pdp_find(struct gtp_dev *gtp, __be32 ms_addr)
+{
+ struct hlist_head *head;
+ struct pdp_ctx *pdp;
+
+ head = >p->addr_hash[ipv4_hashfn(ms_addr) % gtp->hash_size];
+
+ hlist_for_each_entry_rcu(pdp, head, hlist_addr) {
+ if (pdp->af == AF_INET &&
+ pdp->ms_addr_ip4.s_addr == ms_addr)
+ return pdp;
+ }
+
+ return NULL;
+}
+
+static bool gtp_check_src_ms_ipv4(struct sk_buff *skb, struct pdp_ctx *pctx,
+ unsigned int hdrlen)
+{
+ struct iphdr *iph;
+
+ if (!pskb_may_pull(skb, hdrlen + sizeof(struct iphdr)))
+ return false;
+
+ iph = (struct iphdr *)(skb->data + hdrlen + sizeof(struct iphdr));
+
+ return iph->saddr != pctx->ms_addr_ip4.s_addr;
+}
+
+/* Check if the inner IP source address in this packet is assigned to any
+ * existing mobile subscriber.
+ */
+static bool gtp_check_src_ms(struct sk_buff *skb, struct pdp_ctx *pctx,
+ unsigned int hdrlen)
+{
+ switch (ntohs(skb->protocol)) {
+ case ETH_P_IP:
+ return gtp_check_src_ms_ipv4(skb, pctx, hdrlen);
+ }
+ return false;
+}
+
+/* 1 means pass up to the stack, -1 means drop and 0 means decapsulated. */
+static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb,
+ bool xnet)
+{
+ unsigned int hdrlen = sizeof(struct udphdr) +
+ sizeof(struct gtp0_header);
+ struct gtp0_header *gtp0;
+ struct pdp_ctx *pctx;
+ int ret = 0;
+
+ if (!pskb_may_pull(skb, hdrlen))
+ return -1;
+
+ gtp0 = (struct gtp0_header *)(skb->data + sizeof(struct udphdr));
+
+ if ((gtp0->flags >> 5) != GTP_V0)
+ return 1;
+
+ if (gtp0->type != GTP_TPDU)
+ return 1;
+
+ rcu_read_lock();
+ pctx = gtp0_pdp_find(gtp, be64_to_cpu(gtp0->tid));
+ if (!pctx) {
+ netdev_dbg(gtp->dev, "No PDP ctx to decap skb=%p\n", skb);
+ ret = -1;
+ goto out_rcu;
+ }
+
+ if (!gtp_check_src_ms(skb, pctx, hdrlen)) {
+ netdev_dbg(gtp->dev, "No PDP ctx for this MS\n");
+ ret = -1;
+ goto out_rcu;
+ }
+ rcu_read_unlock();
+
+ /* Get rid of the GTP + UDP headers. */
+ return iptunnel_pull_header(skb, hdrlen, skb->protocol, xnet);
+out_rcu:
+ rcu_read_unlock();
+ return ret;
+}
+
+static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb,
+ bool xnet)
+{
+ unsigned int hdrlen = sizeof(struct udphdr) +
+ sizeof(struct gtp1_header);
+ struct gtp1_header *gtp1;
+ struct pdp_ctx *pctx;
+ int ret = 0;
+
+ if (!pskb_may_pull(skb, hdrlen))
+ return -1;
+
+ gtp1 = (struct gtp1_header *)(skb->data + sizeof(struct udphdr));
+
+ if ((gtp1->flags >> 5) != GTP_V1)
+ return 1;
+
+ if (gtp1->type != GTP_TPDU)
+ return 1;
+
+ /* From 29.060: "This field shall be present if and only if any one or
+ * more of the S, PN and E flags are set.".
+ *
+ * If any of the bit is set, then the remaining ones also have to be
+ * set.
+ */
+ if (gtp1->flags & GTP1_F_MASK)
+ hdrlen += 4;
+
+ /* Make sure the header is larger enough, including extensions. */
+ if (!pskb_may_pull(skb, hdrlen))
+ return -1;
+
+ rcu_read_lock();
+ pctx = gtp1_pdp_find(gtp, ntohl(gtp1->tid));
+ if (!pctx) {
+ netdev_dbg(gtp->dev, "No PDP ctx to decap skb=%p\n", skb);
+ ret = -1;
+ goto out_rcu;
+ }
+
+ if (!gtp_check_src_ms(skb, pctx, hdrlen)) {
+ netdev_dbg(gtp->dev, "No PDP ctx for this MS\n");
+ ret = -1;
+ goto out_rcu;
+ }
+ rcu_read_unlock();
+
+ /* Get rid of the GTP + UDP headers. */
+ return iptunnel_pull_header(skb, hdrlen, skb->protocol, xnet);
+out_rcu:
+ rcu_read_unlock();
+ return ret;
+}
+
+static void gtp_encap_disable(struct gtp_dev *gtp)
+{
+ if (gtp->sock0 && gtp->sock0->sk) {
+ udp_sk(gtp->sock0->sk)->encap_type = 0;
+ rcu_assign_sk_user_data(gtp->sock0->sk, NULL);
+ }
+ if (gtp->sock1u && gtp->sock1u->sk) {
+ udp_sk(gtp->sock1u->sk)->encap_type = 0;
+ rcu_assign_sk_user_data(gtp->sock1u->sk, NULL);
+ }
+
+ gtp->sock0 = NULL;
+ gtp->sock1u = NULL;
+}
+
+static void gtp_encap_destroy(struct sock *sk)
+{
+ struct gtp_dev *gtp;
+
+ gtp = rcu_dereference_sk_user_data(sk);
+ if (gtp)
+ gtp_encap_disable(gtp);
+}
+
+/* UDP encapsulation receive handler. See net/ipv4/udp.c.
+ * Return codes: 0: success, <0: error, >0: pass up to userspace UDP socket.
+ */
+static int gtp_encap_recv(struct sock *sk, struct sk_buff *skb)
+{
+ struct pcpu_sw_netstats *stats;
+ struct gtp_dev *gtp;
+ bool xnet;
+ int ret;
+
+ gtp = rcu_dereference_sk_user_data(sk);
+ if (!gtp)
+ return 1;
+
+ netdev_dbg(gtp->dev, "encap_recv sk=%p\n", sk);
+
+ xnet = !net_eq(gtp->net, dev_net(gtp->dev));
+
+ switch (udp_sk(sk)->encap_type) {
+ case UDP_ENCAP_GTP0:
+ netdev_dbg(gtp->dev, "received GTP0 packet\n");
+ ret = gtp0_udp_encap_recv(gtp, skb, xnet);
+ break;
+ case UDP_ENCAP_GTP1U:
+ netdev_dbg(gtp->dev, "received GTP1U packet\n");
+ ret = gtp1u_udp_encap_recv(gtp, skb, xnet);
+ break;
+ default:
+ ret = -1; /* Shouldn't happen. */
+ }
+
+ switch (ret) {
+ case 1:
+ netdev_dbg(gtp->dev, "pass up to the process\n");
+ return 1;
+ case 0:
+ netdev_dbg(gtp->dev, "forwarding packet from GGSN to uplink\n");
+ break;
+ case -1:
+ netdev_dbg(gtp->dev, "GTP packet has been dropped\n");
+ kfree_skb(skb);
+ return 0;
+ }
+
+ /* Now that the UDP and the GTP header have been removed, set up the
+ * new network header. This is required by the upper layer to
+ * calculate the transport header.
+ */
+ skb_reset_network_header(skb);
+
+ skb->dev = gtp->dev;
+
+ stats = this_cpu_ptr(gtp->dev->tstats);
+ u64_stats_update_begin(&stats->syncp);
+ stats->rx_packets++;
+ stats->rx_bytes += skb->len;
+ u64_stats_update_end(&stats->syncp);
+
+ netif_rx(skb);
+
+ return 0;
+}
+
+static int gtp_dev_init(struct net_device *dev)
+{
+ struct gtp_dev *gtp = netdev_priv(dev);
+
+ gtp->dev = dev;
+
+ dev->tstats = alloc_percpu(struct pcpu_sw_netstats);
+ if (!dev->tstats)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static void gtp_dev_uninit(struct net_device *dev)
+{
+ struct gtp_dev *gtp = netdev_priv(dev);
+
+ gtp_encap_disable(gtp);
+ free_percpu(dev->tstats);
+}
+
+static struct rtable *ip4_route_output_gtp(struct net *net, struct flowi4 *fl4,
+ const struct sock *sk, __be32 daddr)
+{
+ memset(fl4, 0, sizeof(*fl4));
+ fl4->flowi4_oif = sk->sk_bound_dev_if;
+ fl4->daddr = daddr;
+ fl4->saddr = inet_sk(sk)->inet_saddr;
+ fl4->flowi4_tos = RT_CONN_FLAGS(sk);
+ fl4->flowi4_proto = sk->sk_protocol;
+
+ return ip_route_output_key(net, fl4);
+}
+
+static inline void gtp0_push_header(struct sk_buff *skb, struct pdp_ctx *pctx)
+{
+ int payload_len = skb->len;
+ struct gtp0_header *gtp0;
+
+ gtp0 = (struct gtp0_header *) skb_push(skb, sizeof(*gtp0));
+
+ gtp0->flags = 0x1e; /* v0, GTP-non-prime. */
+ gtp0->type = GTP_TPDU;
+ gtp0->length = htons(payload_len);
+ gtp0->seq = htons((atomic_inc_return(&pctx->tx_seq) - 1) % 0xffff);
+ gtp0->flow = htons(pctx->u.v0.flow);
+ gtp0->number = 0xff;
+ gtp0->spare[0] = gtp0->spare[1] = gtp0->spare[2] = 0xff;
+ gtp0->tid = cpu_to_be64(pctx->u.v0.tid);
+}
+
+static inline void gtp1_push_header(struct sk_buff *skb, struct pdp_ctx *pctx)
+{
+ int payload_len = skb->len;
+ struct gtp1_header *gtp1;
+
+ gtp1 = (struct gtp1_header *) skb_push(skb, sizeof(*gtp1));
+
+ /* Bits 8 7 6 5 4 3 2 1
+ * +--+--+--+--+--+--+--+--+
+ * |version |PT| 1| E| S|PN|
+ * +--+--+--+--+--+--+--+--+
+ * 0 0 1 1 1 0 0 0
+ */
+ gtp1->flags = 0x38; /* v1, GTP-non-prime. */
+ gtp1->type = GTP_TPDU;
+ gtp1->length = htons(payload_len);
+ gtp1->tid = htonl(pctx->u.v1.o_tei);
+
+ /* TODO: Suppport for extension header, sequence number and N-PDU.
+ * Update the length field if any of them is available.
+ */
+}
+
+struct gtp_pktinfo {
+ struct sock *sk;
+ struct iphdr *iph;
+ struct flowi4 fl4;
+ struct rtable *rt;
+ struct pdp_ctx *pctx;
+ struct net_device *dev;
+ __be16 gtph_port;
+};
+
+static void gtp_push_header(struct sk_buff *skb, struct gtp_pktinfo *pktinfo)
+{
+ switch (pktinfo->pctx->gtp_version) {
+ case GTP_V0:
+ pktinfo->gtph_port = htons(GTP0_PORT);
+ gtp0_push_header(skb, pktinfo->pctx);
+ break;
+ case GTP_V1:
+ pktinfo->gtph_port = htons(GTP1U_PORT);
+ gtp1_push_header(skb, pktinfo->pctx);
+ break;
+ }
+}
+
+static inline void gtp_set_pktinfo_ipv4(struct gtp_pktinfo *pktinfo,
+ struct sock *sk, struct iphdr *iph,
+ struct pdp_ctx *pctx, struct rtable *rt,
+ struct flowi4 *fl4,
+ struct net_device *dev)
+{
+ pktinfo->sk = sk;
+ pktinfo->iph = iph;
+ pktinfo->pctx = pctx;
+ pktinfo->rt = rt;
+ pktinfo->fl4 = *fl4;
+ pktinfo->dev = dev;
+}
+
+static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev,
+ struct gtp_pktinfo *pktinfo)
+{
+ struct gtp_dev *gtp = netdev_priv(dev);
+ struct pdp_ctx *pctx;
+ struct rtable *rt;
+ struct flowi4 fl4;
+ struct iphdr *iph;
+ struct sock *sk;
+ __be16 df;
+ int mtu;
+
+ /* Read the IP destination address and resolve the PDP context.
+ * Prepend PDP header with TEI/TID from PDP ctx.
+ */
+ iph = ip_hdr(skb);
+ pctx = ipv4_pdp_find(gtp, iph->daddr);
+ if (!pctx) {
+ netdev_dbg(dev, "no PDP ctx found for %pI4, skip\n",
+ &iph->daddr);
+ return -ENOENT;
+ }
+ netdev_dbg(dev, "found PDP context %p\n", pctx);
+
+ switch (pctx->gtp_version) {
+ case GTP_V0:
+ if (gtp->sock0)
+ sk = gtp->sock0->sk;
+ else
+ sk = NULL;
+ break;
+ case GTP_V1:
+ if (gtp->sock1u)
+ sk = gtp->sock1u->sk;
+ else
+ sk = NULL;
+ break;
+ default:
+ return -ENOENT;
+ }
+
+ if (!sk) {
+ netdev_dbg(dev, "no userspace socket is available, skip\n");
+ return -ENOENT;
+ }
+
+ rt = ip4_route_output_gtp(sock_net(sk), &fl4, gtp->sock0->sk,
+ pctx->sgsn_addr_ip4.s_addr);
+ if (IS_ERR(rt)) {
+ netdev_dbg(dev, "no route to SSGN %pI4\n",
+ &pctx->sgsn_addr_ip4.s_addr);
+ dev->stats.tx_carrier_errors++;
+ goto err;
+ }
+
+ if (rt->dst.dev == dev) {
+ netdev_dbg(dev, "circular route to SSGN %pI4\n",
+ &pctx->sgsn_addr_ip4.s_addr);
+ dev->stats.collisions++;
+ goto err_rt;
+ }
+
+ skb_dst_drop(skb);
+
+ /* This is similar to tnl_update_pmtu(). */
+ df = iph->frag_off;
+ if (df) {
+ mtu = dst_mtu(&rt->dst) - dev->hard_header_len -
+ sizeof(struct iphdr) - sizeof(struct udphdr);
+ switch (pctx->gtp_version) {
+ case GTP_V0:
+ mtu -= sizeof(struct gtp0_header);
+ break;
+ case GTP_V1:
+ mtu -= sizeof(struct gtp1_header);
+ break;
+ }
+ } else {
+ mtu = dst_mtu(&rt->dst);
+ }
+
+ rt->dst.ops->update_pmtu(&rt->dst, NULL, skb, mtu);
+
+ if (!skb_is_gso(skb) && (iph->frag_off & htons(IP_DF)) &&
+ mtu < ntohs(iph->tot_len)) {
+ netdev_dbg(dev, "packet too big, fragmentation needed\n");
+ memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+ icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
+ htonl(mtu));
+ goto err_rt;
+ }
+
+ gtp_set_pktinfo_ipv4(pktinfo, sk, iph, pctx, rt, &fl4, dev);
+ gtp_push_header(skb, pktinfo);
+
+ return 0;
+err_rt:
+ ip_rt_put(rt);
+err:
+ return -EBADMSG;
+}
+
+static netdev_tx_t gtp_dev_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ unsigned int proto = ntohs(skb->protocol);
+ struct gtp_pktinfo pktinfo;
+ int err;
+
+ /* Ensure there is sufficient headroom. */
+ if (skb_cow_head(skb, dev->needed_headroom))
+ goto tx_err;
+
+ skb_reset_inner_headers(skb);
+
+ /* PDP context lookups in gtp_build_skb_*() need rcu read-side lock. */
+ rcu_read_lock();
+ switch (proto) {
+ case ETH_P_IP:
+ err = gtp_build_skb_ip4(skb, dev, &pktinfo);
+ break;
+ default:
+ err = -EOPNOTSUPP;
+ break;
+ }
+ rcu_read_unlock();
+
+ if (err < 0)
+ goto tx_err;
+
+ switch (proto) {
+ case ETH_P_IP:
+ netdev_dbg(pktinfo.dev, "gtp -> IP src: %pI4 dst: %pI4\n",
+ &pktinfo.iph->saddr, &pktinfo.iph->daddr);
+ udp_tunnel_xmit_skb(pktinfo.rt, pktinfo.sk, skb,
+ pktinfo.fl4.saddr, pktinfo.fl4.daddr,
+ pktinfo.iph->tos,
+ ip4_dst_hoplimit(&pktinfo.rt->dst),
+ htons(IP_DF),
+ pktinfo.gtph_port, pktinfo.gtph_port,
+ true, false);
+ break;
+ }
+
+ return NETDEV_TX_OK;
+tx_err:
+ dev->stats.tx_errors++;
+ dev_kfree_skb(skb);
+ return NETDEV_TX_OK;
+}
+
+static const struct net_device_ops gtp_netdev_ops = {
+ .ndo_init = gtp_dev_init,
+ .ndo_uninit = gtp_dev_uninit,
+ .ndo_start_xmit = gtp_dev_xmit,
+ .ndo_get_stats64 = ip_tunnel_get_stats64,
+};
+
+static void gtp_link_setup(struct net_device *dev)
+{
+ dev->netdev_ops = >p_netdev_ops;
+ dev->destructor = free_netdev;
+
+ dev->hard_header_len = 0;
+ dev->addr_len = 0;
+
+ /* Zero header length. */
+ dev->type = ARPHRD_NONE;
+ dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST;
+
+ dev->priv_flags |= IFF_NO_QUEUE;
+ dev->features |= NETIF_F_LLTX;
+ netif_keep_dst(dev);
+
+ /* Assume largest header, ie. GTPv0. */
+ dev->needed_headroom = LL_MAX_HEADER +
+ sizeof(struct iphdr) +
+ sizeof(struct udphdr) +
+ sizeof(struct gtp0_header);
+}
+
+static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize);
+static void gtp_hashtable_free(struct gtp_dev *gtp);
+static int gtp_encap_enable(struct net_device *dev, struct gtp_dev *gtp,
+ int fd_gtp0, int fd_gtp1, struct net *src_net);
+
+static int gtp_newlink(struct net *src_net, struct net_device *dev,
+ struct nlattr *tb[], struct nlattr *data[])
+{
+ int hashsize, err, fd0, fd1;
+ struct gtp_dev *gtp;
+ struct gtp_net *gn;
+
+ if (!data[IFLA_GTP_FD0] || !data[IFLA_GTP_FD1])
+ return -EINVAL;
+
+ gtp = netdev_priv(dev);
+
+ fd0 = nla_get_u32(data[IFLA_GTP_FD0]);
+ fd1 = nla_get_u32(data[IFLA_GTP_FD1]);
+
+ err = gtp_encap_enable(dev, gtp, fd0, fd1, src_net);
+ if (err < 0)
+ goto out_err;
+
+ if (!data[IFLA_GTP_PDP_HASHSIZE])
+ hashsize = 1024;
+ else
+ hashsize = nla_get_u32(data[IFLA_GTP_PDP_HASHSIZE]);
+
+ err = gtp_hashtable_new(gtp, hashsize);
+ if (err < 0)
+ goto out_encap;
+
+ err = register_netdevice(dev);
+ if (err < 0) {
+ netdev_dbg(dev, "failed to register new netdev %d\n", err);
+ goto out_hashtable;
+ }
+
+ gn = net_generic(dev_net(dev), gtp_net_id);
+ list_add_rcu(>p->list, &gn->gtp_dev_list);
+
+ netdev_dbg(dev, "registered new GTP interface\n");
+
+ return 0;
+
+out_hashtable:
+ gtp_hashtable_free(gtp);
+out_encap:
+ gtp_encap_disable(gtp);
+out_err:
+ return err;
+}
+
+static void gtp_dellink(struct net_device *dev, struct list_head *head)
+{
+ struct gtp_dev *gtp = netdev_priv(dev);
+
+ gtp_encap_disable(gtp);
+ gtp_hashtable_free(gtp);
+ list_del_rcu(>p->list);
+ unregister_netdevice_queue(dev, head);
+}
+
+static const struct nla_policy gtp_policy[IFLA_GTP_MAX + 1] = {
+ [IFLA_GTP_FD0] = { .type = NLA_U32 },
+ [IFLA_GTP_FD1] = { .type = NLA_U32 },
+ [IFLA_GTP_PDP_HASHSIZE] = { .type = NLA_U32 },
+};
+
+static int gtp_validate(struct nlattr *tb[], struct nlattr *data[])
+{
+ if (!data)
+ return -EINVAL;
+
+ return 0;
+}
+
+static size_t gtp_get_size(const struct net_device *dev)
+{
+ return nla_total_size(sizeof(__u32)); /* IFLA_GTP_PDP_HASHSIZE */
+}
+
+static int gtp_fill_info(struct sk_buff *skb, const struct net_device *dev)
+{
+ struct gtp_dev *gtp = netdev_priv(dev);
+
+ if (nla_put_u32(skb, IFLA_GTP_PDP_HASHSIZE, gtp->hash_size))
+ goto nla_put_failure;
+
+ return 0;
+
+nla_put_failure:
+ return -EMSGSIZE;
+}
+
+static struct rtnl_link_ops gtp_link_ops __read_mostly = {
+ .kind = "gtp",
+ .maxtype = IFLA_GTP_MAX,
+ .policy = gtp_policy,
+ .priv_size = sizeof(struct gtp_dev),
+ .setup = gtp_link_setup,
+ .validate = gtp_validate,
+ .newlink = gtp_newlink,
+ .dellink = gtp_dellink,
+ .get_size = gtp_get_size,
+ .fill_info = gtp_fill_info,
+};
+
+static struct net *gtp_genl_get_net(struct net *src_net, struct nlattr *tb[])
+{
+ struct net *net;
+
+ /* Examine the link attributes and figure out which network namespace
+ * we are talking about.
+ */
+ if (tb[GTPA_NET_NS_FD])
+ net = get_net_ns_by_fd(nla_get_u32(tb[GTPA_NET_NS_FD]));
+ else
+ net = get_net(src_net);
+
+ return net;
+}
+
+static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize)
+{
+ int i;
+
+ gtp->addr_hash = kmalloc(sizeof(struct hlist_head) * hsize, GFP_KERNEL);
+ if (gtp->addr_hash == NULL)
+ return -ENOMEM;
+
+ gtp->tid_hash = kmalloc(sizeof(struct hlist_head) * hsize, GFP_KERNEL);
+ if (gtp->tid_hash == NULL)
+ goto err1;
+
+ gtp->hash_size = hsize;
+
+ for (i = 0; i < hsize; i++) {
+ INIT_HLIST_HEAD(>p->addr_hash[i]);
+ INIT_HLIST_HEAD(>p->tid_hash[i]);
+ }
+ return 0;
+err1:
+ kfree(gtp->addr_hash);
+ return -ENOMEM;
+}
+
+static void gtp_hashtable_free(struct gtp_dev *gtp)
+{
+ struct pdp_ctx *pctx;
+ int i;
+
+ for (i = 0; i < gtp->hash_size; i++) {
+ hlist_for_each_entry_rcu(pctx, >p->tid_hash[i], hlist_tid) {
+ hlist_del_rcu(&pctx->hlist_tid);
+ hlist_del_rcu(&pctx->hlist_addr);
+ kfree_rcu(pctx, rcu_head);
+ }
+ }
+ synchronize_rcu();
+ kfree(gtp->addr_hash);
+ kfree(gtp->tid_hash);
+}
+
+static int gtp_encap_enable(struct net_device *dev, struct gtp_dev *gtp,
+ int fd_gtp0, int fd_gtp1, struct net *src_net)
+{
+ struct udp_tunnel_sock_cfg tuncfg = {NULL};
+ struct socket *sock0, *sock1u;
+ int err;
+
+ netdev_dbg(dev, "enable gtp on %d, %d\n", fd_gtp0, fd_gtp1);
+
+ sock0 = sockfd_lookup(fd_gtp0, &err);
+ if (sock0 == NULL) {
+ netdev_dbg(dev, "socket fd=%d not found (gtp0)\n", fd_gtp0);
+ return -ENOENT;
+ }
+
+ if (sock0->sk->sk_protocol != IPPROTO_UDP) {
+ netdev_dbg(dev, "socket fd=%d not UDP\n", fd_gtp0);
+ err = -EINVAL;
+ goto err1;
+ }
+
+ sock1u = sockfd_lookup(fd_gtp1, &err);
+ if (sock1u == NULL) {
+ netdev_dbg(dev, "socket fd=%d not found (gtp1u)\n", fd_gtp1);
+ err = -ENOENT;
+ goto err1;
+ }
+
+ if (sock1u->sk->sk_protocol != IPPROTO_UDP) {
+ netdev_dbg(dev, "socket fd=%d not UDP\n", fd_gtp1);
+ err = -EINVAL;
+ goto err2;
+ }
+
+ netdev_dbg(dev, "enable gtp on %p, %p\n", sock0, sock1u);
+
+ gtp->sock0 = sock0;
+ gtp->sock1u = sock1u;
+ gtp->net = src_net;
+
+ tuncfg.sk_user_data = gtp;
+ tuncfg.encap_rcv = gtp_encap_recv;
+ tuncfg.encap_destroy = gtp_encap_destroy;
+
+ tuncfg.encap_type = UDP_ENCAP_GTP0;
+ setup_udp_tunnel_sock(sock_net(gtp->sock0->sk), gtp->sock0, &tuncfg);
+
+ tuncfg.encap_type = UDP_ENCAP_GTP1U;
+ setup_udp_tunnel_sock(sock_net(gtp->sock1u->sk), gtp->sock1u, &tuncfg);
+
+ err = 0;
+err2:
+ sockfd_put(sock1u);
+err1:
+ sockfd_put(sock0);
+ return err;
+}
+
+static struct net_device *gtp_find_dev(struct net *net, int ifindex)
+{
+ struct gtp_net *gn = net_generic(net, gtp_net_id);
+ struct gtp_dev *gtp;
+
+ list_for_each_entry_rcu(gtp, &gn->gtp_dev_list, list) {
+ if (ifindex == gtp->dev->ifindex)
+ return gtp->dev;
+ }
+ return NULL;
+}
+
+static void ipv4_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info)
+{
+ pctx->gtp_version = nla_get_u32(info->attrs[GTPA_VERSION]);
+ pctx->af = AF_INET;
+ pctx->sgsn_addr_ip4.s_addr =
+ nla_get_be32(info->attrs[GTPA_SGSN_ADDRESS]);
+ pctx->ms_addr_ip4.s_addr =
+ nla_get_be32(info->attrs[GTPA_MS_ADDRESS]);
+
+ switch (pctx->gtp_version) {
+ case GTP_V0:
+ /* According to TS 09.60, sections 7.5.1 and 7.5.2, the flow
+ * label needs to be the same for uplink and downlink packets,
+ * so let's annotate this.
+ */
+ pctx->u.v0.tid = nla_get_u64(info->attrs[GTPA_TID]);
+ pctx->u.v0.flow = nla_get_u16(info->attrs[GTPA_FLOW]);
+ break;
+ case GTP_V1:
+ pctx->u.v1.i_tei = nla_get_u32(info->attrs[GTPA_I_TEI]);
+ pctx->u.v1.o_tei = nla_get_u32(info->attrs[GTPA_O_TEI]);
+ break;
+ default:
+ break;
+ }
+}
+
+static int ipv4_pdp_add(struct net_device *dev, struct genl_info *info)
+{
+ struct gtp_dev *gtp = netdev_priv(dev);
+ u32 hash_ms, hash_tid = 0;
+ struct pdp_ctx *pctx;
+ bool found = false;
+ __be32 ms_addr;
+
+ ms_addr = nla_get_be32(info->attrs[GTPA_MS_ADDRESS]);
+ hash_ms = ipv4_hashfn(ms_addr) % gtp->hash_size;
+
+ hlist_for_each_entry_rcu(pctx, >p->addr_hash[hash_ms], hlist_addr) {
+ if (pctx->ms_addr_ip4.s_addr == ms_addr) {
+ found = true;
+ break;
+ }
+ }
+
+ if (found) {
+ if (info->nlhdr->nlmsg_flags & NLM_F_EXCL)
+ return -EEXIST;
+ if (info->nlhdr->nlmsg_flags & NLM_F_REPLACE)
+ return -EOPNOTSUPP;
+
+ ipv4_pdp_fill(pctx, info);
+
+ if (pctx->gtp_version == GTP_V0)
+ netdev_dbg(dev, "GTPv0-U: update tunnel id = %llx (pdp %p)\n",
+ pctx->u.v0.tid, pctx);
+ else if (pctx->gtp_version == GTP_V1)
+ netdev_dbg(dev, "GTPv1-U: update tunnel id = %x/%x (pdp %p)\n",
+ pctx->u.v1.i_tei, pctx->u.v1.o_tei, pctx);
+
+ return 0;
+
+ }
+
+ pctx = kmalloc(sizeof(struct pdp_ctx), GFP_KERNEL);
+ if (pctx == NULL)
+ return -ENOMEM;
+
+ ipv4_pdp_fill(pctx, info);
+ atomic_set(&pctx->tx_seq, 0);
+
+ switch (pctx->gtp_version) {
+ case GTP_V0:
+ /* TS 09.60: "The flow label identifies unambiguously a GTP
+ * flow.". We use the tid for this instead, I cannot find a
+ * situation in which this doesn't unambiguosly identify the
+ * PDP context.
+ */
+ hash_tid = gtp0_hashfn(pctx->u.v0.tid) % gtp->hash_size;
+ break;
+ case GTP_V1:
+ hash_tid = gtp1u_hashfn(pctx->u.v1.i_tei) % gtp->hash_size;
+ break;
+ }
+
+ hlist_add_head_rcu(&pctx->hlist_addr, >p->addr_hash[hash_ms]);
+ hlist_add_head_rcu(&pctx->hlist_tid, >p->tid_hash[hash_tid]);
+
+ switch (pctx->gtp_version) {
+ case GTP_V0:
+ netdev_dbg(dev, "GTPv0-U: new PDP ctx id=%llx ssgn=%pI4 ms=%pI4 (pdp=%p)\n",
+ pctx->u.v0.tid, &pctx->sgsn_addr_ip4,
+ &pctx->ms_addr_ip4, pctx);
+ break;
+ case GTP_V1:
+ netdev_dbg(dev, "GTPv1-U: new PDP ctx id=%x/%x ssgn=%pI4 ms=%pI4 (pdp=%p)\n",
+ pctx->u.v1.i_tei, pctx->u.v1.o_tei,
+ &pctx->sgsn_addr_ip4, &pctx->ms_addr_ip4, pctx);
+ break;
+ }
+
+ return 0;
+}
+
+static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info)
+{
+ struct net_device *dev;
+ struct net *net;
+
+ if (!info->attrs[GTPA_VERSION] ||
+ !info->attrs[GTPA_LINK] ||
+ !info->attrs[GTPA_SGSN_ADDRESS] ||
+ !info->attrs[GTPA_MS_ADDRESS])
+ return -EINVAL;
+
+ switch (nla_get_u32(info->attrs[GTPA_VERSION])) {
+ case GTP_V0:
+ if (!info->attrs[GTPA_TID] ||
+ !info->attrs[GTPA_FLOW])
+ return -EINVAL;
+ break;
+ case GTP_V1:
+ if (!info->attrs[GTPA_I_TEI] ||
+ !info->attrs[GTPA_O_TEI])
+ return -EINVAL;
+ break;
+
+ default:
+ return -EINVAL;
+ }
+
+ net = gtp_genl_get_net(sock_net(skb->sk), info->attrs);
+ if (IS_ERR(net))
+ return PTR_ERR(net);
+
+ /* Check if there's an existing gtpX device to configure */
+ dev = gtp_find_dev(net, nla_get_u32(info->attrs[GTPA_LINK]));
+ if (dev == NULL)
+ return -ENODEV;
+
+ return ipv4_pdp_add(dev, info);
+}
+
+static int gtp_genl_del_pdp(struct sk_buff *skb, struct genl_info *info)
+{
+ struct net_device *dev;
+ struct pdp_ctx *pctx;
+ struct gtp_dev *gtp;
+ struct net *net;
+
+ if (!info->attrs[GTPA_VERSION] ||
+ !info->attrs[GTPA_LINK])
+ return -EINVAL;
+
+ net = gtp_genl_get_net(sock_net(skb->sk), info->attrs);
+ if (IS_ERR(net))
+ return PTR_ERR(net);
+
+ /* Check if there's an existing gtpX device to configure */
+ dev = gtp_find_dev(net, nla_get_u32(info->attrs[GTPA_LINK]));
+ if (dev == NULL)
+ return -ENODEV;
+
+ gtp = netdev_priv(dev);
+
+ switch (nla_get_u32(info->attrs[GTPA_VERSION])) {
+ case GTP_V0:
+ if (!info->attrs[GTPA_TID])
+ return -EINVAL;
+ pctx = gtp0_pdp_find(gtp, nla_get_u64(info->attrs[GTPA_TID]));
+ break;
+ case GTP_V1:
+ if (!info->attrs[GTPA_I_TEI])
+ return -EINVAL;
+ pctx = gtp1_pdp_find(gtp, nla_get_u64(info->attrs[GTPA_I_TEI]));
+ break;
+
+ default:
+ return -EINVAL;
+ }
+
+ if (pctx == NULL)
+ return -ENOENT;
+
+ if (pctx->gtp_version == GTP_V0)
+ netdev_dbg(dev, "GTPv0-U: deleting tunnel id = %llx (pdp %p)\n",
+ pctx->u.v0.tid, pctx);
+ else if (pctx->gtp_version == GTP_V1)
+ netdev_dbg(dev, "GTPv1-U: deleting tunnel id = %x/%x (pdp %p)\n",
+ pctx->u.v1.i_tei, pctx->u.v1.o_tei, pctx);
+
+ hlist_del_rcu(&pctx->hlist_tid);
+ hlist_del_rcu(&pctx->hlist_addr);
+ kfree_rcu(pctx, rcu_head);
+
+ return 0;
+}
+
+static struct genl_family gtp_genl_family = {
+ .id = GENL_ID_GENERATE,
+ .name = "gtp",
+ .version = 0,
+ .hdrsize = 0,
+ .maxattr = GTPA_MAX,
+ .netnsok = true,
+};
+
+static int gtp_genl_fill_info(struct sk_buff *skb, u32 snd_portid, u32 snd_seq,
+ u32 type, struct pdp_ctx *pctx)
+{
+ void *genlh;
+
+ genlh = genlmsg_put(skb, snd_portid, snd_seq, >p_genl_family, 0,
+ type);
+ if (genlh == NULL)
+ goto nlmsg_failure;
+
+ if (nla_put_u32(skb, GTPA_VERSION, pctx->gtp_version) ||
+ nla_put_be32(skb, GTPA_SGSN_ADDRESS, pctx->sgsn_addr_ip4.s_addr) ||
+ nla_put_be32(skb, GTPA_MS_ADDRESS, pctx->ms_addr_ip4.s_addr))
+ goto nla_put_failure;
+
+ switch (pctx->gtp_version) {
+ case GTP_V0:
+ if (nla_put_u64_64bit(skb, GTPA_TID, pctx->u.v0.tid, GTPA_PAD) ||
+ nla_put_u16(skb, GTPA_FLOW, pctx->u.v0.flow))
+ goto nla_put_failure;
+ break;
+ case GTP_V1:
+ if (nla_put_u32(skb, GTPA_I_TEI, pctx->u.v1.i_tei) ||
+ nla_put_u32(skb, GTPA_O_TEI, pctx->u.v1.o_tei))
+ goto nla_put_failure;
+ break;
+ }
+ genlmsg_end(skb, genlh);
+ return 0;
+
+nlmsg_failure:
+nla_put_failure:
+ genlmsg_cancel(skb, genlh);
+ return -EMSGSIZE;
+}
+
+static int gtp_genl_get_pdp(struct sk_buff *skb, struct genl_info *info)
+{
+ struct pdp_ctx *pctx = NULL;
+ struct net_device *dev;
+ struct sk_buff *skb2;
+ struct gtp_dev *gtp;
+ u32 gtp_version;
+ struct net *net;
+ int err;
+
+ if (!info->attrs[GTPA_VERSION] ||
+ !info->attrs[GTPA_LINK])
+ return -EINVAL;
+
+ gtp_version = nla_get_u32(info->attrs[GTPA_VERSION]);
+ switch (gtp_version) {
+ case GTP_V0:
+ case GTP_V1:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ net = gtp_genl_get_net(sock_net(skb->sk), info->attrs);
+ if (IS_ERR(net))
+ return PTR_ERR(net);
+
+ /* Check if there's an existing gtpX device to configure */
+ dev = gtp_find_dev(net, nla_get_u32(info->attrs[GTPA_LINK]));
+ if (dev == NULL)
+ return -ENODEV;
+
+ gtp = netdev_priv(dev);
+
+ rcu_read_lock();
+ if (gtp_version == GTP_V0 &&
+ info->attrs[GTPA_TID]) {
+ u64 tid = nla_get_u64(info->attrs[GTPA_TID]);
+
+ pctx = gtp0_pdp_find(gtp, tid);
+ } else if (gtp_version == GTP_V1 &&
+ info->attrs[GTPA_I_TEI]) {
+ u32 tid = nla_get_u32(info->attrs[GTPA_I_TEI]);
+
+ pctx = gtp1_pdp_find(gtp, tid);
+ } else if (info->attrs[GTPA_MS_ADDRESS]) {
+ __be32 ip = nla_get_be32(info->attrs[GTPA_MS_ADDRESS]);
+
+ pctx = ipv4_pdp_find(gtp, ip);
+ }
+
+ if (pctx == NULL) {
+ err = -ENOENT;
+ goto err_unlock;
+ }
+
+ skb2 = genlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC);
+ if (skb2 == NULL) {
+ err = -ENOMEM;
+ goto err_unlock;
+ }
+
+ err = gtp_genl_fill_info(skb2, NETLINK_CB(skb).portid,
+ info->snd_seq, info->nlhdr->nlmsg_type, pctx);
+ if (err < 0)
+ goto err_unlock_free;
+
+ rcu_read_unlock();
+ return genlmsg_unicast(genl_info_net(info), skb2, info->snd_portid);
+
+err_unlock_free:
+ kfree_skb(skb2);
+err_unlock:
+ rcu_read_unlock();
+ return err;
+}
+
+static int gtp_genl_dump_pdp(struct sk_buff *skb,
+ struct netlink_callback *cb)
+{
+ struct gtp_dev *last_gtp = (struct gtp_dev *)cb->args[2], *gtp;
+ struct net *net = sock_net(skb->sk);
+ struct gtp_net *gn = net_generic(net, gtp_net_id);
+ unsigned long tid = cb->args[1];
+ int i, k = cb->args[0], ret;
+ struct pdp_ctx *pctx;
+
+ if (cb->args[4])
+ return 0;
+
+ list_for_each_entry_rcu(gtp, &gn->gtp_dev_list, list) {
+ if (last_gtp && last_gtp != gtp)
+ continue;
+ else
+ last_gtp = NULL;
+
+ for (i = k; i < gtp->hash_size; i++) {
+ hlist_for_each_entry_rcu(pctx, >p->tid_hash[i], hlist_tid) {
+ if (tid && tid != pctx->u.tid)
+ continue;
+ else
+ tid = 0;
+
+ ret = gtp_genl_fill_info(skb,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ cb->nlh->nlmsg_type, pctx);
+ if (ret < 0) {
+ cb->args[0] = i;
+ cb->args[1] = pctx->u.tid;
+ cb->args[2] = (unsigned long)gtp;
+ goto out;
+ }
+ }
+ }
+ }
+ cb->args[4] = 1;
+out:
+ return skb->len;
+}
+
+static struct nla_policy gtp_genl_policy[GTPA_MAX + 1] = {
+ [GTPA_LINK] = { .type = NLA_U32, },
+ [GTPA_VERSION] = { .type = NLA_U32, },
+ [GTPA_TID] = { .type = NLA_U64, },
+ [GTPA_SGSN_ADDRESS] = { .type = NLA_U32, },
+ [GTPA_MS_ADDRESS] = { .type = NLA_U32, },
+ [GTPA_FLOW] = { .type = NLA_U16, },
+ [GTPA_NET_NS_FD] = { .type = NLA_U32, },
+ [GTPA_I_TEI] = { .type = NLA_U32, },
+ [GTPA_O_TEI] = { .type = NLA_U32, },
+};
+
+static const struct genl_ops gtp_genl_ops[] = {
+ {
+ .cmd = GTP_CMD_NEWPDP,
+ .doit = gtp_genl_new_pdp,
+ .policy = gtp_genl_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+ {
+ .cmd = GTP_CMD_DELPDP,
+ .doit = gtp_genl_del_pdp,
+ .policy = gtp_genl_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+ {
+ .cmd = GTP_CMD_GETPDP,
+ .doit = gtp_genl_get_pdp,
+ .dumpit = gtp_genl_dump_pdp,
+ .policy = gtp_genl_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+};
+
+static int __net_init gtp_net_init(struct net *net)
+{
+ struct gtp_net *gn = net_generic(net, gtp_net_id);
+
+ INIT_LIST_HEAD(&gn->gtp_dev_list);
+ return 0;
+}
+
+static void __net_exit gtp_net_exit(struct net *net)
+{
+ struct gtp_net *gn = net_generic(net, gtp_net_id);
+ struct gtp_dev *gtp;
+ LIST_HEAD(list);
+
+ rtnl_lock();
+ list_for_each_entry(gtp, &gn->gtp_dev_list, list)
+ gtp_dellink(gtp->dev, &list);
+
+ unregister_netdevice_many(&list);
+ rtnl_unlock();
+}
+
+static struct pernet_operations gtp_net_ops = {
+ .init = gtp_net_init,
+ .exit = gtp_net_exit,
+ .id = >p_net_id,
+ .size = sizeof(struct gtp_net),
+};
+
+static int __init gtp_init(void)
+{
+ int err;
+
+ get_random_bytes(>p_h_initval, sizeof(gtp_h_initval));
+
+ err = rtnl_link_register(>p_link_ops);
+ if (err < 0)
+ goto error_out;
+
+ err = genl_register_family_with_ops(>p_genl_family, gtp_genl_ops);
+ if (err < 0)
+ goto unreg_rtnl_link;
+
+ err = register_pernet_subsys(>p_net_ops);
+ if (err < 0)
+ goto unreg_genl_family;
+
+ pr_info("GTP module loaded (pdp ctx size %Zd bytes)\n",
+ sizeof(struct pdp_ctx));
+ return 0;
+
+unreg_genl_family:
+ genl_unregister_family(>p_genl_family);
+unreg_rtnl_link:
+ rtnl_link_unregister(>p_link_ops);
+error_out:
+ pr_err("error loading GTP module loaded\n");
+ return err;
+}
+late_initcall(gtp_init);
+
+static void __exit gtp_fini(void)
+{
+ unregister_pernet_subsys(>p_net_ops);
+ genl_unregister_family(>p_genl_family);
+ rtnl_link_unregister(>p_link_ops);
+
+ pr_info("GTP module unloaded\n");
+}
+module_exit(gtp_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Harald Welte <hwelte@sysmocom.de>");
+MODULE_DESCRIPTION("Interface driver for GTP encapsulated traffic");
+MODULE_ALIAS_RTNL_LINK("gtp");
diff --git a/include/net/gtp.h b/include/net/gtp.h
new file mode 100644
index 0000000..894a37b
--- /dev/null
+++ b/include/net/gtp.h
@@ -0,0 +1,34 @@
+#ifndef _GTP_H_
+#define _GTP_H
+
+/* General GTP protocol related definitions. */
+
+#define GTP0_PORT 3386
+#define GTP1U_PORT 2152
+
+#define GTP_TPDU 255
+
+struct gtp0_header { /* According to GSM TS 09.60. */
+ __u8 flags;
+ __u8 type;
+ __be16 length;
+ __be16 seq;
+ __be16 flow;
+ __u8 number;
+ __u8 spare[3];
+ __be64 tid;
+} __attribute__ ((packed));
+
+struct gtp1_header { /* According to 3GPP TS 29.060. */
+ __u8 flags;
+ __u8 type;
+ __be16 length;
+ __be32 tid;
+} __attribute__ ((packed));
+
+#define GTP1_F_NPDU 0x01
+#define GTP1_F_SEQ 0x02
+#define GTP1_F_EXTHDR 0x04
+#define GTP1_F_MASK 0x07
+
+#endif
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 813ffb2e..8bdae34 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -141,6 +141,7 @@ header-y += gfs2_ondisk.h
header-y += gigaset_dev.h
header-y += gpio.h
header-y += gsmmux.h
+header-y += gtp.h
header-y += hdlcdrv.h
header-y += hdlc.h
header-y += hdreg.h
diff --git a/include/uapi/linux/gtp.h b/include/uapi/linux/gtp.h
new file mode 100644
index 0000000..ca1054d
--- /dev/null
+++ b/include/uapi/linux/gtp.h
@@ -0,0 +1,33 @@
+#ifndef _UAPI_LINUX_GTP_H_
+#define _UAPI_LINUX_GTP_H__
+
+enum gtp_genl_cmds {
+ GTP_CMD_NEWPDP,
+ GTP_CMD_DELPDP,
+ GTP_CMD_GETPDP,
+
+ GTP_CMD_MAX,
+};
+
+enum gtp_version {
+ GTP_V0 = 0,
+ GTP_V1,
+};
+
+enum gtp_attrs {
+ GTPA_UNSPEC = 0,
+ GTPA_LINK,
+ GTPA_VERSION,
+ GTPA_TID, /* for GTPv0 only */
+ GTPA_SGSN_ADDRESS,
+ GTPA_MS_ADDRESS,
+ GTPA_FLOW,
+ GTPA_NET_NS_FD,
+ GTPA_I_TEI, /* for GTPv1 only */
+ GTPA_O_TEI, /* for GTPv1 only */
+ GTPA_PAD,
+ __GTPA_MAX,
+};
+#define GTPA_MAX (__GTPA_MAX + 1)
+
+#endif /* _UAPI_LINUX_GTP_H_ */
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index ba69d44..a3f53c9 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -517,6 +517,16 @@ enum {
};
#define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1)
+/* GTP section */
+enum {
+ IFLA_GTP_UNSPEC,
+ IFLA_GTP_FD0,
+ IFLA_GTP_FD1,
+ IFLA_GTP_PDP_HASHSIZE,
+ __IFLA_GTP_MAX,
+};
+#define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1)
+
/* Bonding section */
enum {
diff --git a/include/uapi/linux/udp.h b/include/uapi/linux/udp.h
index 16574ea..2c8180f 100644
--- a/include/uapi/linux/udp.h
+++ b/include/uapi/linux/udp.h
@@ -36,6 +36,7 @@ struct udphdr {
#define UDP_ENCAP_ESPINUDP_NON_IKE 1 /* draft-ietf-ipsec-nat-t-ike-00/01 */
#define UDP_ENCAP_ESPINUDP 2 /* draft-ietf-ipsec-udp-encaps-06 */
#define UDP_ENCAP_L2TPINUDP 3 /* rfc2661 */
-
+#define UDP_ENCAP_GTP0 4 /* GSM TS 09.60 */
+#define UDP_ENCAP_GTP1U 5 /* 3GPP TS 29.060 */
#endif /* _UAPI_LINUX_UDP_H */
--
2.1.4
^ permalink raw reply related
* Re: [GIT PULL nf-next 0/1] Second Round of IPVS Updates for v4.7
From: Pablo Neira Ayuso @ 2016-05-08 22:19 UTC (permalink / raw)
To: Simon Horman
Cc: lvs-devel, netdev, netfilter-devel, Wensong Zhang,
Julian Anastasov
In-Reply-To: <1462519959-22382-1-git-send-email-horms@verge.net.au>
On Fri, May 06, 2016 at 04:32:38PM +0900, Simon Horman wrote:
> Hi Pablo,
>
> please consider these enhancements to the IPVS. They allow its
> DoS mitigation strategy effective in conjunction with the SIP persistence
> engine.
>
> The following changes since commit cb39ad8b8ef224c544074962780bf763077d6141:
>
> netfilter: nf_tables: allow set names up to 32 bytes (2016-05-05 16:39:51 +0200)
>
> are available in the git repository at:
>
> https://git.kernel.org/pub/scm/linux/kernel/git/horms/ipvs-next.git tags/ipvs2-for-v4.7
Pulled, thanks Simon.
^ permalink raw reply
* Re: [PATCH v2 2/3] net: ethernet: fec: use phydev from struct net_device
From: Ben Hutchings @ 2016-05-08 22:22 UTC (permalink / raw)
To: Philippe Reynes, fugang.duan, davem, kan.liang, decot, aduyck,
jiri, jacob.e.keller, tom, andrew
Cc: netdev, linux-kernel
In-Reply-To: <1462743877-31738-3-git-send-email-tremyfr@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 936 bytes --]
On Sun, 2016-05-08 at 23:44 +0200, Philippe Reynes wrote:
> The private structure contain a pointer to phydev, but the structure
> net_device already contain such pointer. So we can remove the pointer
> phydev in the private structure, and update the driver to use the one
> contained in struct net_device.
But there is no central code that updates the pointer, so:
[...]
> @@ -1928,7 +1926,6 @@ static int fec_enet_mii_probe(struct net_device *ndev)
>
> phy_dev->advertising = phy_dev->supported;
>
> - fep->phy_dev = phy_dev;
you need to assign ndev->phydev here
[...]
> @@ -2875,8 +2869,7 @@ fec_enet_close(struct net_device *ndev)
> fec_stop(ndev);
> }
>
> - phy_disconnect(fep->phy_dev);
> - fep->phy_dev = NULL;
> + phy_disconnect(ndev->phydev);
[...]
and you need to set it to NULL here.
Ben.
--
Ben Hutchings
I haven't lost my mind; it's backed up on tape somewhere.
[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 819 bytes --]
^ permalink raw reply
* [PATCH 1/1] net: thunderx: avoid exposing kernel stack
From: Heinrich Schuchardt @ 2016-05-08 22:46 UTC (permalink / raw)
To: Sunil Goutham, Robert Richter
Cc: linux-arm-kernel, netdev, linux-kernel, Heinrich Schuchardt
Reserved fields should be set to zero to avoid exposing
bits from the kernel stack.
Signed-off-by: Heinrich Schuchardt <xypron.glpk@gmx.de>
---
drivers/net/ethernet/cavium/thunder/nicvf_queues.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index 8acd7c0..0ff8e60 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -533,6 +533,7 @@ static void nicvf_rcv_queue_config(struct nicvf *nic, struct queue_set *qs,
nicvf_config_vlan_stripping(nic, nic->netdev->features);
/* Enable Receive queue */
+ memset(&rq_cfg, 0, sizeof(struct rq_cfg));
rq_cfg.ena = 1;
rq_cfg.tcp_ena = 0;
nicvf_queue_reg_write(nic, NIC_QSET_RQ_0_7_CFG, qidx, *(u64 *)&rq_cfg);
@@ -565,6 +566,7 @@ void nicvf_cmp_queue_config(struct nicvf *nic, struct queue_set *qs,
qidx, (u64)(cq->dmem.phys_base));
/* Enable Completion queue */
+ memset(&cq_cfg, 0, sizeof(struct cq_cfg));
cq_cfg.ena = 1;
cq_cfg.reset = 0;
cq_cfg.caching = 0;
@@ -613,6 +615,7 @@ static void nicvf_snd_queue_config(struct nicvf *nic, struct queue_set *qs,
qidx, (u64)(sq->dmem.phys_base));
/* Enable send queue & set queue size */
+ memset(&sq_cfg, 0, sizeof(struct sq_cfg));
sq_cfg.ena = 1;
sq_cfg.reset = 0;
sq_cfg.ldwb = 0;
@@ -649,6 +652,7 @@ static void nicvf_rbdr_config(struct nicvf *nic, struct queue_set *qs,
/* Enable RBDR & set queue size */
/* Buffer size should be in multiples of 128 bytes */
+ memset(&rbdr_cfg, 0, sizeof(struct rbdr_cfg));
rbdr_cfg.ena = 1;
rbdr_cfg.reset = 0;
rbdr_cfg.ldwb = 0;
--
2.1.4
^ permalink raw reply related
* Re: [PATCH v2 2/3] net: ethernet: fec: use phydev from struct net_device
From: Philippe Reynes @ 2016-05-08 22:47 UTC (permalink / raw)
To: Ben Hutchings
Cc: fugang.duan, davem, kan.liang, decot, aduyck, jiri,
jacob.e.keller, tom, andrew, netdev, linux-kernel
In-Reply-To: <1462746137.2634.67.camel@decadent.org.uk>
On 09/05/16 00:22, Ben Hutchings wrote:
> On Sun, 2016-05-08 at 23:44 +0200, Philippe Reynes wrote:
>> The private structure contain a pointer to phydev, but the structure
>> net_device already contain such pointer. So we can remove the pointer
>> phydev in the private structure, and update the driver to use the one
>> contained in struct net_device.
>
> But there is no central code that updates the pointer, so:
The function phy_attach_direct and phy_detach update the pointer
phydev in the struct net_device.
>
> [...]
>> @@ -1928,7 +1926,6 @@ static int fec_enet_mii_probe(struct net_device *ndev)
>>
>> phy_dev->advertising = phy_dev->supported;
>>
>> - fep->phy_dev = phy_dev;
>
> you need to assign ndev->phydev here
The function fec_enet_mii_probe call of_phy_connect,
which call phy_connect_direct, which call phy_attach_direct.
This last function update the pointer phydev of struct net_device.
> [...]
>> @@ -2875,8 +2869,7 @@ fec_enet_close(struct net_device *ndev)
>> fec_stop(ndev);
>> }
>>
>> - phy_disconnect(fep->phy_dev);
>> - fep->phy_dev = NULL;
>> + phy_disconnect(ndev->phydev);
> [...]
>
> and you need to set it to NULL here.
The function fec_enet_close call phy_disconnect, which call phy_detach.
This last function set the pointer phydev in the struct net_device to NULL.
So from my understanding, those two lines aren't usefull.
May you confirm that I'm on the right way please ?
> Ben.
>
Philippe
^ permalink raw reply
* [PATCH nf-next,v2] gtp: add initial driver for datapath of GPRS Tunneling Protocol (GTP-U)
From: Pablo Neira Ayuso @ 2016-05-08 22:55 UTC (permalink / raw)
To: netdev; +Cc: davem, laforge, aschultz, openbsc
This is an initial implementation of a netdev driver for GTP datapath
(GTP-U) v0 and v1, according to the GSM TS 09.60 and 3GPP TS 29.060
standards. This tunneling protocol is used to prevent subscribers from
accessing mobile carrier core network infrastructure.
This implementation requires a GGSN userspace daemon that implements the
signaling protocol (GTP-C), such as OpenGGSN [1]. This userspace daemon
updates the PDP context database that represents active subscriber
sessions through a genetlink interface.
For more context on this tunneling protocol, you can check the slides
that were presented during the NetDev 1.1 [2].
Only IPv4 is supported at this time.
[1] http://git.osmocom.org/openggsn/
[2] http://www.netdevconf.org/1.1/proceedings/slides/schultz-welte-osmocom-gtp.pdf
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
v2: Rebase on top of current HEAD to resolve minor conflict with recent PPP
updates in include/uapi/linux/if_link.h so this applies cleanly.
drivers/net/Kconfig | 17 +
drivers/net/Makefile | 1 +
drivers/net/gtp.c | 1364 ++++++++++++++++++++++++++++++++++++++++++
include/net/gtp.h | 34 ++
include/uapi/linux/Kbuild | 1 +
include/uapi/linux/gtp.h | 33 +
include/uapi/linux/if_link.h | 10 +
include/uapi/linux/udp.h | 3 +-
8 files changed, 1462 insertions(+), 1 deletion(-)
create mode 100644 drivers/net/gtp.c
create mode 100644 include/net/gtp.h
create mode 100644 include/uapi/linux/gtp.h
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index befd67d..0c5415b 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -192,6 +192,23 @@ config GENEVE
To compile this driver as a module, choose M here: the module
will be called geneve.
+config GTP
+ tristate "GPRS Tunneling Protocol datapath (GTP-U)"
+ depends on INET && NET_UDP_TUNNEL
+ select NET_IP_TUNNEL
+ ---help---
+ This allows one to create gtp virtual interfaces that provide
+ the GPRS Tunneling Protocol datapath (GTP-U). This tunneling protocol
+ is used to prevent subscribers from accessing mobile carrier core
+ network infrastructure. This driver requires a userspace software that
+ implements the signaling protocol (GTP-C) to update its PDP context
+ base, such as OpenGGSN <http://git.osmocom.org/openggsn/). This
+ tunneling protocol is implemented according to the GSM TS 09.60 and
+ 3GPP TS 29.060 standards.
+
+ To compile this drivers as a module, choose M here: the module
+ wil be called gtp.
+
config MACSEC
tristate "IEEE 802.1AE MAC-level encryption (MACsec)"
select CRYPTO
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 1aa7cb8..7336cbd 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -25,6 +25,7 @@ obj-$(CONFIG_VETH) += veth.o
obj-$(CONFIG_VIRTIO_NET) += virtio_net.o
obj-$(CONFIG_VXLAN) += vxlan.o
obj-$(CONFIG_GENEVE) += geneve.o
+obj-$(CONFIG_GTP) += gtp.o
obj-$(CONFIG_NLMON) += nlmon.o
obj-$(CONFIG_NET_VRF) += vrf.o
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
new file mode 100644
index 0000000..8ce1104
--- /dev/null
+++ b/drivers/net/gtp.c
@@ -0,0 +1,1364 @@
+/* GTP according to GSM TS 09.60 / 3GPP TS 29.060
+ *
+ * (C) 2012-2014 by sysmocom - s.f.m.c. GmbH
+ * (C) 2016 by Pablo Neira Ayuso <pablo@netfilter.org>
+ *
+ * Author: Harald Welte <hwelte@sysmocom.de>
+ * Pablo Neira Ayuso <pablo@netfilter.org>
+ * Andreas Schultz <aschultz@travelping.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/version.h>
+#include <linux/skbuff.h>
+#include <linux/udp.h>
+#include <linux/rculist.h>
+#include <linux/jhash.h>
+#include <linux/if_tunnel.h>
+#include <linux/net.h>
+#include <linux/file.h>
+#include <linux/gtp.h>
+
+#include <net/net_namespace.h>
+#include <net/protocol.h>
+#include <net/ip.h>
+#include <net/udp.h>
+#include <net/udp_tunnel.h>
+#include <net/icmp.h>
+#include <net/xfrm.h>
+#include <net/genetlink.h>
+#include <net/netns/generic.h>
+#include <net/gtp.h>
+
+/* An active session for the subscriber. */
+struct pdp_ctx {
+ struct hlist_node hlist_tid;
+ struct hlist_node hlist_addr;
+
+ union {
+ u64 tid;
+ struct {
+ u64 tid;
+ u16 flow;
+ } v0;
+ struct {
+ u32 i_tei;
+ u32 o_tei;
+ } v1;
+ } u;
+ u8 gtp_version;
+ u16 af;
+
+ struct in_addr ms_addr_ip4;
+ struct in_addr sgsn_addr_ip4;
+
+ atomic_t tx_seq;
+ struct rcu_head rcu_head;
+};
+
+/* One instance of the GTP device. */
+struct gtp_dev {
+ struct list_head list;
+
+ struct socket *sock0;
+ struct socket *sock1u;
+
+ struct net *net;
+ struct net_device *dev;
+
+ unsigned int hash_size;
+ struct hlist_head *tid_hash;
+ struct hlist_head *addr_hash;
+};
+
+static int gtp_net_id __read_mostly;
+
+struct gtp_net {
+ struct list_head gtp_dev_list;
+};
+
+static u32 gtp_h_initval;
+
+static inline u32 gtp0_hashfn(u64 tid)
+{
+ u32 *tid32 = (u32 *) &tid;
+ return jhash_2words(tid32[0], tid32[1], gtp_h_initval);
+}
+
+static inline u32 gtp1u_hashfn(u32 tid)
+{
+ return jhash_1word(tid, gtp_h_initval);
+}
+
+static inline u32 ipv4_hashfn(__be32 ip)
+{
+ return jhash_1word((__force u32)ip, gtp_h_initval);
+}
+
+/* Resolve a PDP context structure based on the 64bit TID. */
+static struct pdp_ctx *gtp0_pdp_find(struct gtp_dev *gtp, u64 tid)
+{
+ struct hlist_head *head;
+ struct pdp_ctx *pdp;
+
+ head = >p->tid_hash[gtp0_hashfn(tid) % gtp->hash_size];
+
+ hlist_for_each_entry_rcu(pdp, head, hlist_tid) {
+ if (pdp->gtp_version == GTP_V0 &&
+ pdp->u.v0.tid == tid)
+ return pdp;
+ }
+ return NULL;
+}
+
+/* Resolve a PDP context structure based on the 32bit TEI. */
+static struct pdp_ctx *gtp1_pdp_find(struct gtp_dev *gtp, u32 tid)
+{
+ struct hlist_head *head;
+ struct pdp_ctx *pdp;
+
+ head = >p->tid_hash[gtp1u_hashfn(tid) % gtp->hash_size];
+
+ hlist_for_each_entry_rcu(pdp, head, hlist_tid) {
+ if (pdp->gtp_version == GTP_V1 &&
+ pdp->u.v1.i_tei == tid)
+ return pdp;
+ }
+ return NULL;
+}
+
+/* Resolve a PDP context based on IPv4 address of MS. */
+static struct pdp_ctx *ipv4_pdp_find(struct gtp_dev *gtp, __be32 ms_addr)
+{
+ struct hlist_head *head;
+ struct pdp_ctx *pdp;
+
+ head = >p->addr_hash[ipv4_hashfn(ms_addr) % gtp->hash_size];
+
+ hlist_for_each_entry_rcu(pdp, head, hlist_addr) {
+ if (pdp->af == AF_INET &&
+ pdp->ms_addr_ip4.s_addr == ms_addr)
+ return pdp;
+ }
+
+ return NULL;
+}
+
+static bool gtp_check_src_ms_ipv4(struct sk_buff *skb, struct pdp_ctx *pctx,
+ unsigned int hdrlen)
+{
+ struct iphdr *iph;
+
+ if (!pskb_may_pull(skb, hdrlen + sizeof(struct iphdr)))
+ return false;
+
+ iph = (struct iphdr *)(skb->data + hdrlen + sizeof(struct iphdr));
+
+ return iph->saddr != pctx->ms_addr_ip4.s_addr;
+}
+
+/* Check if the inner IP source address in this packet is assigned to any
+ * existing mobile subscriber.
+ */
+static bool gtp_check_src_ms(struct sk_buff *skb, struct pdp_ctx *pctx,
+ unsigned int hdrlen)
+{
+ switch (ntohs(skb->protocol)) {
+ case ETH_P_IP:
+ return gtp_check_src_ms_ipv4(skb, pctx, hdrlen);
+ }
+ return false;
+}
+
+/* 1 means pass up to the stack, -1 means drop and 0 means decapsulated. */
+static int gtp0_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb,
+ bool xnet)
+{
+ unsigned int hdrlen = sizeof(struct udphdr) +
+ sizeof(struct gtp0_header);
+ struct gtp0_header *gtp0;
+ struct pdp_ctx *pctx;
+ int ret = 0;
+
+ if (!pskb_may_pull(skb, hdrlen))
+ return -1;
+
+ gtp0 = (struct gtp0_header *)(skb->data + sizeof(struct udphdr));
+
+ if ((gtp0->flags >> 5) != GTP_V0)
+ return 1;
+
+ if (gtp0->type != GTP_TPDU)
+ return 1;
+
+ rcu_read_lock();
+ pctx = gtp0_pdp_find(gtp, be64_to_cpu(gtp0->tid));
+ if (!pctx) {
+ netdev_dbg(gtp->dev, "No PDP ctx to decap skb=%p\n", skb);
+ ret = -1;
+ goto out_rcu;
+ }
+
+ if (!gtp_check_src_ms(skb, pctx, hdrlen)) {
+ netdev_dbg(gtp->dev, "No PDP ctx for this MS\n");
+ ret = -1;
+ goto out_rcu;
+ }
+ rcu_read_unlock();
+
+ /* Get rid of the GTP + UDP headers. */
+ return iptunnel_pull_header(skb, hdrlen, skb->protocol, xnet);
+out_rcu:
+ rcu_read_unlock();
+ return ret;
+}
+
+static int gtp1u_udp_encap_recv(struct gtp_dev *gtp, struct sk_buff *skb,
+ bool xnet)
+{
+ unsigned int hdrlen = sizeof(struct udphdr) +
+ sizeof(struct gtp1_header);
+ struct gtp1_header *gtp1;
+ struct pdp_ctx *pctx;
+ int ret = 0;
+
+ if (!pskb_may_pull(skb, hdrlen))
+ return -1;
+
+ gtp1 = (struct gtp1_header *)(skb->data + sizeof(struct udphdr));
+
+ if ((gtp1->flags >> 5) != GTP_V1)
+ return 1;
+
+ if (gtp1->type != GTP_TPDU)
+ return 1;
+
+ /* From 29.060: "This field shall be present if and only if any one or
+ * more of the S, PN and E flags are set.".
+ *
+ * If any of the bit is set, then the remaining ones also have to be
+ * set.
+ */
+ if (gtp1->flags & GTP1_F_MASK)
+ hdrlen += 4;
+
+ /* Make sure the header is larger enough, including extensions. */
+ if (!pskb_may_pull(skb, hdrlen))
+ return -1;
+
+ rcu_read_lock();
+ pctx = gtp1_pdp_find(gtp, ntohl(gtp1->tid));
+ if (!pctx) {
+ netdev_dbg(gtp->dev, "No PDP ctx to decap skb=%p\n", skb);
+ ret = -1;
+ goto out_rcu;
+ }
+
+ if (!gtp_check_src_ms(skb, pctx, hdrlen)) {
+ netdev_dbg(gtp->dev, "No PDP ctx for this MS\n");
+ ret = -1;
+ goto out_rcu;
+ }
+ rcu_read_unlock();
+
+ /* Get rid of the GTP + UDP headers. */
+ return iptunnel_pull_header(skb, hdrlen, skb->protocol, xnet);
+out_rcu:
+ rcu_read_unlock();
+ return ret;
+}
+
+static void gtp_encap_disable(struct gtp_dev *gtp)
+{
+ if (gtp->sock0 && gtp->sock0->sk) {
+ udp_sk(gtp->sock0->sk)->encap_type = 0;
+ rcu_assign_sk_user_data(gtp->sock0->sk, NULL);
+ }
+ if (gtp->sock1u && gtp->sock1u->sk) {
+ udp_sk(gtp->sock1u->sk)->encap_type = 0;
+ rcu_assign_sk_user_data(gtp->sock1u->sk, NULL);
+ }
+
+ gtp->sock0 = NULL;
+ gtp->sock1u = NULL;
+}
+
+static void gtp_encap_destroy(struct sock *sk)
+{
+ struct gtp_dev *gtp;
+
+ gtp = rcu_dereference_sk_user_data(sk);
+ if (gtp)
+ gtp_encap_disable(gtp);
+}
+
+/* UDP encapsulation receive handler. See net/ipv4/udp.c.
+ * Return codes: 0: success, <0: error, >0: pass up to userspace UDP socket.
+ */
+static int gtp_encap_recv(struct sock *sk, struct sk_buff *skb)
+{
+ struct pcpu_sw_netstats *stats;
+ struct gtp_dev *gtp;
+ bool xnet;
+ int ret;
+
+ gtp = rcu_dereference_sk_user_data(sk);
+ if (!gtp)
+ return 1;
+
+ netdev_dbg(gtp->dev, "encap_recv sk=%p\n", sk);
+
+ xnet = !net_eq(gtp->net, dev_net(gtp->dev));
+
+ switch (udp_sk(sk)->encap_type) {
+ case UDP_ENCAP_GTP0:
+ netdev_dbg(gtp->dev, "received GTP0 packet\n");
+ ret = gtp0_udp_encap_recv(gtp, skb, xnet);
+ break;
+ case UDP_ENCAP_GTP1U:
+ netdev_dbg(gtp->dev, "received GTP1U packet\n");
+ ret = gtp1u_udp_encap_recv(gtp, skb, xnet);
+ break;
+ default:
+ ret = -1; /* Shouldn't happen. */
+ }
+
+ switch (ret) {
+ case 1:
+ netdev_dbg(gtp->dev, "pass up to the process\n");
+ return 1;
+ case 0:
+ netdev_dbg(gtp->dev, "forwarding packet from GGSN to uplink\n");
+ break;
+ case -1:
+ netdev_dbg(gtp->dev, "GTP packet has been dropped\n");
+ kfree_skb(skb);
+ return 0;
+ }
+
+ /* Now that the UDP and the GTP header have been removed, set up the
+ * new network header. This is required by the upper layer to
+ * calculate the transport header.
+ */
+ skb_reset_network_header(skb);
+
+ skb->dev = gtp->dev;
+
+ stats = this_cpu_ptr(gtp->dev->tstats);
+ u64_stats_update_begin(&stats->syncp);
+ stats->rx_packets++;
+ stats->rx_bytes += skb->len;
+ u64_stats_update_end(&stats->syncp);
+
+ netif_rx(skb);
+
+ return 0;
+}
+
+static int gtp_dev_init(struct net_device *dev)
+{
+ struct gtp_dev *gtp = netdev_priv(dev);
+
+ gtp->dev = dev;
+
+ dev->tstats = alloc_percpu(struct pcpu_sw_netstats);
+ if (!dev->tstats)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static void gtp_dev_uninit(struct net_device *dev)
+{
+ struct gtp_dev *gtp = netdev_priv(dev);
+
+ gtp_encap_disable(gtp);
+ free_percpu(dev->tstats);
+}
+
+static struct rtable *ip4_route_output_gtp(struct net *net, struct flowi4 *fl4,
+ const struct sock *sk, __be32 daddr)
+{
+ memset(fl4, 0, sizeof(*fl4));
+ fl4->flowi4_oif = sk->sk_bound_dev_if;
+ fl4->daddr = daddr;
+ fl4->saddr = inet_sk(sk)->inet_saddr;
+ fl4->flowi4_tos = RT_CONN_FLAGS(sk);
+ fl4->flowi4_proto = sk->sk_protocol;
+
+ return ip_route_output_key(net, fl4);
+}
+
+static inline void gtp0_push_header(struct sk_buff *skb, struct pdp_ctx *pctx)
+{
+ int payload_len = skb->len;
+ struct gtp0_header *gtp0;
+
+ gtp0 = (struct gtp0_header *) skb_push(skb, sizeof(*gtp0));
+
+ gtp0->flags = 0x1e; /* v0, GTP-non-prime. */
+ gtp0->type = GTP_TPDU;
+ gtp0->length = htons(payload_len);
+ gtp0->seq = htons((atomic_inc_return(&pctx->tx_seq) - 1) % 0xffff);
+ gtp0->flow = htons(pctx->u.v0.flow);
+ gtp0->number = 0xff;
+ gtp0->spare[0] = gtp0->spare[1] = gtp0->spare[2] = 0xff;
+ gtp0->tid = cpu_to_be64(pctx->u.v0.tid);
+}
+
+static inline void gtp1_push_header(struct sk_buff *skb, struct pdp_ctx *pctx)
+{
+ int payload_len = skb->len;
+ struct gtp1_header *gtp1;
+
+ gtp1 = (struct gtp1_header *) skb_push(skb, sizeof(*gtp1));
+
+ /* Bits 8 7 6 5 4 3 2 1
+ * +--+--+--+--+--+--+--+--+
+ * |version |PT| 1| E| S|PN|
+ * +--+--+--+--+--+--+--+--+
+ * 0 0 1 1 1 0 0 0
+ */
+ gtp1->flags = 0x38; /* v1, GTP-non-prime. */
+ gtp1->type = GTP_TPDU;
+ gtp1->length = htons(payload_len);
+ gtp1->tid = htonl(pctx->u.v1.o_tei);
+
+ /* TODO: Suppport for extension header, sequence number and N-PDU.
+ * Update the length field if any of them is available.
+ */
+}
+
+struct gtp_pktinfo {
+ struct sock *sk;
+ struct iphdr *iph;
+ struct flowi4 fl4;
+ struct rtable *rt;
+ struct pdp_ctx *pctx;
+ struct net_device *dev;
+ __be16 gtph_port;
+};
+
+static void gtp_push_header(struct sk_buff *skb, struct gtp_pktinfo *pktinfo)
+{
+ switch (pktinfo->pctx->gtp_version) {
+ case GTP_V0:
+ pktinfo->gtph_port = htons(GTP0_PORT);
+ gtp0_push_header(skb, pktinfo->pctx);
+ break;
+ case GTP_V1:
+ pktinfo->gtph_port = htons(GTP1U_PORT);
+ gtp1_push_header(skb, pktinfo->pctx);
+ break;
+ }
+}
+
+static inline void gtp_set_pktinfo_ipv4(struct gtp_pktinfo *pktinfo,
+ struct sock *sk, struct iphdr *iph,
+ struct pdp_ctx *pctx, struct rtable *rt,
+ struct flowi4 *fl4,
+ struct net_device *dev)
+{
+ pktinfo->sk = sk;
+ pktinfo->iph = iph;
+ pktinfo->pctx = pctx;
+ pktinfo->rt = rt;
+ pktinfo->fl4 = *fl4;
+ pktinfo->dev = dev;
+}
+
+static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev,
+ struct gtp_pktinfo *pktinfo)
+{
+ struct gtp_dev *gtp = netdev_priv(dev);
+ struct pdp_ctx *pctx;
+ struct rtable *rt;
+ struct flowi4 fl4;
+ struct iphdr *iph;
+ struct sock *sk;
+ __be16 df;
+ int mtu;
+
+ /* Read the IP destination address and resolve the PDP context.
+ * Prepend PDP header with TEI/TID from PDP ctx.
+ */
+ iph = ip_hdr(skb);
+ pctx = ipv4_pdp_find(gtp, iph->daddr);
+ if (!pctx) {
+ netdev_dbg(dev, "no PDP ctx found for %pI4, skip\n",
+ &iph->daddr);
+ return -ENOENT;
+ }
+ netdev_dbg(dev, "found PDP context %p\n", pctx);
+
+ switch (pctx->gtp_version) {
+ case GTP_V0:
+ if (gtp->sock0)
+ sk = gtp->sock0->sk;
+ else
+ sk = NULL;
+ break;
+ case GTP_V1:
+ if (gtp->sock1u)
+ sk = gtp->sock1u->sk;
+ else
+ sk = NULL;
+ break;
+ default:
+ return -ENOENT;
+ }
+
+ if (!sk) {
+ netdev_dbg(dev, "no userspace socket is available, skip\n");
+ return -ENOENT;
+ }
+
+ rt = ip4_route_output_gtp(sock_net(sk), &fl4, gtp->sock0->sk,
+ pctx->sgsn_addr_ip4.s_addr);
+ if (IS_ERR(rt)) {
+ netdev_dbg(dev, "no route to SSGN %pI4\n",
+ &pctx->sgsn_addr_ip4.s_addr);
+ dev->stats.tx_carrier_errors++;
+ goto err;
+ }
+
+ if (rt->dst.dev == dev) {
+ netdev_dbg(dev, "circular route to SSGN %pI4\n",
+ &pctx->sgsn_addr_ip4.s_addr);
+ dev->stats.collisions++;
+ goto err_rt;
+ }
+
+ skb_dst_drop(skb);
+
+ /* This is similar to tnl_update_pmtu(). */
+ df = iph->frag_off;
+ if (df) {
+ mtu = dst_mtu(&rt->dst) - dev->hard_header_len -
+ sizeof(struct iphdr) - sizeof(struct udphdr);
+ switch (pctx->gtp_version) {
+ case GTP_V0:
+ mtu -= sizeof(struct gtp0_header);
+ break;
+ case GTP_V1:
+ mtu -= sizeof(struct gtp1_header);
+ break;
+ }
+ } else {
+ mtu = dst_mtu(&rt->dst);
+ }
+
+ rt->dst.ops->update_pmtu(&rt->dst, NULL, skb, mtu);
+
+ if (!skb_is_gso(skb) && (iph->frag_off & htons(IP_DF)) &&
+ mtu < ntohs(iph->tot_len)) {
+ netdev_dbg(dev, "packet too big, fragmentation needed\n");
+ memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+ icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
+ htonl(mtu));
+ goto err_rt;
+ }
+
+ gtp_set_pktinfo_ipv4(pktinfo, sk, iph, pctx, rt, &fl4, dev);
+ gtp_push_header(skb, pktinfo);
+
+ return 0;
+err_rt:
+ ip_rt_put(rt);
+err:
+ return -EBADMSG;
+}
+
+static netdev_tx_t gtp_dev_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ unsigned int proto = ntohs(skb->protocol);
+ struct gtp_pktinfo pktinfo;
+ int err;
+
+ /* Ensure there is sufficient headroom. */
+ if (skb_cow_head(skb, dev->needed_headroom))
+ goto tx_err;
+
+ skb_reset_inner_headers(skb);
+
+ /* PDP context lookups in gtp_build_skb_*() need rcu read-side lock. */
+ rcu_read_lock();
+ switch (proto) {
+ case ETH_P_IP:
+ err = gtp_build_skb_ip4(skb, dev, &pktinfo);
+ break;
+ default:
+ err = -EOPNOTSUPP;
+ break;
+ }
+ rcu_read_unlock();
+
+ if (err < 0)
+ goto tx_err;
+
+ switch (proto) {
+ case ETH_P_IP:
+ netdev_dbg(pktinfo.dev, "gtp -> IP src: %pI4 dst: %pI4\n",
+ &pktinfo.iph->saddr, &pktinfo.iph->daddr);
+ udp_tunnel_xmit_skb(pktinfo.rt, pktinfo.sk, skb,
+ pktinfo.fl4.saddr, pktinfo.fl4.daddr,
+ pktinfo.iph->tos,
+ ip4_dst_hoplimit(&pktinfo.rt->dst),
+ htons(IP_DF),
+ pktinfo.gtph_port, pktinfo.gtph_port,
+ true, false);
+ break;
+ }
+
+ return NETDEV_TX_OK;
+tx_err:
+ dev->stats.tx_errors++;
+ dev_kfree_skb(skb);
+ return NETDEV_TX_OK;
+}
+
+static const struct net_device_ops gtp_netdev_ops = {
+ .ndo_init = gtp_dev_init,
+ .ndo_uninit = gtp_dev_uninit,
+ .ndo_start_xmit = gtp_dev_xmit,
+ .ndo_get_stats64 = ip_tunnel_get_stats64,
+};
+
+static void gtp_link_setup(struct net_device *dev)
+{
+ dev->netdev_ops = >p_netdev_ops;
+ dev->destructor = free_netdev;
+
+ dev->hard_header_len = 0;
+ dev->addr_len = 0;
+
+ /* Zero header length. */
+ dev->type = ARPHRD_NONE;
+ dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST;
+
+ dev->priv_flags |= IFF_NO_QUEUE;
+ dev->features |= NETIF_F_LLTX;
+ netif_keep_dst(dev);
+
+ /* Assume largest header, ie. GTPv0. */
+ dev->needed_headroom = LL_MAX_HEADER +
+ sizeof(struct iphdr) +
+ sizeof(struct udphdr) +
+ sizeof(struct gtp0_header);
+}
+
+static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize);
+static void gtp_hashtable_free(struct gtp_dev *gtp);
+static int gtp_encap_enable(struct net_device *dev, struct gtp_dev *gtp,
+ int fd_gtp0, int fd_gtp1, struct net *src_net);
+
+static int gtp_newlink(struct net *src_net, struct net_device *dev,
+ struct nlattr *tb[], struct nlattr *data[])
+{
+ int hashsize, err, fd0, fd1;
+ struct gtp_dev *gtp;
+ struct gtp_net *gn;
+
+ if (!data[IFLA_GTP_FD0] || !data[IFLA_GTP_FD1])
+ return -EINVAL;
+
+ gtp = netdev_priv(dev);
+
+ fd0 = nla_get_u32(data[IFLA_GTP_FD0]);
+ fd1 = nla_get_u32(data[IFLA_GTP_FD1]);
+
+ err = gtp_encap_enable(dev, gtp, fd0, fd1, src_net);
+ if (err < 0)
+ goto out_err;
+
+ if (!data[IFLA_GTP_PDP_HASHSIZE])
+ hashsize = 1024;
+ else
+ hashsize = nla_get_u32(data[IFLA_GTP_PDP_HASHSIZE]);
+
+ err = gtp_hashtable_new(gtp, hashsize);
+ if (err < 0)
+ goto out_encap;
+
+ err = register_netdevice(dev);
+ if (err < 0) {
+ netdev_dbg(dev, "failed to register new netdev %d\n", err);
+ goto out_hashtable;
+ }
+
+ gn = net_generic(dev_net(dev), gtp_net_id);
+ list_add_rcu(>p->list, &gn->gtp_dev_list);
+
+ netdev_dbg(dev, "registered new GTP interface\n");
+
+ return 0;
+
+out_hashtable:
+ gtp_hashtable_free(gtp);
+out_encap:
+ gtp_encap_disable(gtp);
+out_err:
+ return err;
+}
+
+static void gtp_dellink(struct net_device *dev, struct list_head *head)
+{
+ struct gtp_dev *gtp = netdev_priv(dev);
+
+ gtp_encap_disable(gtp);
+ gtp_hashtable_free(gtp);
+ list_del_rcu(>p->list);
+ unregister_netdevice_queue(dev, head);
+}
+
+static const struct nla_policy gtp_policy[IFLA_GTP_MAX + 1] = {
+ [IFLA_GTP_FD0] = { .type = NLA_U32 },
+ [IFLA_GTP_FD1] = { .type = NLA_U32 },
+ [IFLA_GTP_PDP_HASHSIZE] = { .type = NLA_U32 },
+};
+
+static int gtp_validate(struct nlattr *tb[], struct nlattr *data[])
+{
+ if (!data)
+ return -EINVAL;
+
+ return 0;
+}
+
+static size_t gtp_get_size(const struct net_device *dev)
+{
+ return nla_total_size(sizeof(__u32)); /* IFLA_GTP_PDP_HASHSIZE */
+}
+
+static int gtp_fill_info(struct sk_buff *skb, const struct net_device *dev)
+{
+ struct gtp_dev *gtp = netdev_priv(dev);
+
+ if (nla_put_u32(skb, IFLA_GTP_PDP_HASHSIZE, gtp->hash_size))
+ goto nla_put_failure;
+
+ return 0;
+
+nla_put_failure:
+ return -EMSGSIZE;
+}
+
+static struct rtnl_link_ops gtp_link_ops __read_mostly = {
+ .kind = "gtp",
+ .maxtype = IFLA_GTP_MAX,
+ .policy = gtp_policy,
+ .priv_size = sizeof(struct gtp_dev),
+ .setup = gtp_link_setup,
+ .validate = gtp_validate,
+ .newlink = gtp_newlink,
+ .dellink = gtp_dellink,
+ .get_size = gtp_get_size,
+ .fill_info = gtp_fill_info,
+};
+
+static struct net *gtp_genl_get_net(struct net *src_net, struct nlattr *tb[])
+{
+ struct net *net;
+
+ /* Examine the link attributes and figure out which network namespace
+ * we are talking about.
+ */
+ if (tb[GTPA_NET_NS_FD])
+ net = get_net_ns_by_fd(nla_get_u32(tb[GTPA_NET_NS_FD]));
+ else
+ net = get_net(src_net);
+
+ return net;
+}
+
+static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize)
+{
+ int i;
+
+ gtp->addr_hash = kmalloc(sizeof(struct hlist_head) * hsize, GFP_KERNEL);
+ if (gtp->addr_hash == NULL)
+ return -ENOMEM;
+
+ gtp->tid_hash = kmalloc(sizeof(struct hlist_head) * hsize, GFP_KERNEL);
+ if (gtp->tid_hash == NULL)
+ goto err1;
+
+ gtp->hash_size = hsize;
+
+ for (i = 0; i < hsize; i++) {
+ INIT_HLIST_HEAD(>p->addr_hash[i]);
+ INIT_HLIST_HEAD(>p->tid_hash[i]);
+ }
+ return 0;
+err1:
+ kfree(gtp->addr_hash);
+ return -ENOMEM;
+}
+
+static void gtp_hashtable_free(struct gtp_dev *gtp)
+{
+ struct pdp_ctx *pctx;
+ int i;
+
+ for (i = 0; i < gtp->hash_size; i++) {
+ hlist_for_each_entry_rcu(pctx, >p->tid_hash[i], hlist_tid) {
+ hlist_del_rcu(&pctx->hlist_tid);
+ hlist_del_rcu(&pctx->hlist_addr);
+ kfree_rcu(pctx, rcu_head);
+ }
+ }
+ synchronize_rcu();
+ kfree(gtp->addr_hash);
+ kfree(gtp->tid_hash);
+}
+
+static int gtp_encap_enable(struct net_device *dev, struct gtp_dev *gtp,
+ int fd_gtp0, int fd_gtp1, struct net *src_net)
+{
+ struct udp_tunnel_sock_cfg tuncfg = {NULL};
+ struct socket *sock0, *sock1u;
+ int err;
+
+ netdev_dbg(dev, "enable gtp on %d, %d\n", fd_gtp0, fd_gtp1);
+
+ sock0 = sockfd_lookup(fd_gtp0, &err);
+ if (sock0 == NULL) {
+ netdev_dbg(dev, "socket fd=%d not found (gtp0)\n", fd_gtp0);
+ return -ENOENT;
+ }
+
+ if (sock0->sk->sk_protocol != IPPROTO_UDP) {
+ netdev_dbg(dev, "socket fd=%d not UDP\n", fd_gtp0);
+ err = -EINVAL;
+ goto err1;
+ }
+
+ sock1u = sockfd_lookup(fd_gtp1, &err);
+ if (sock1u == NULL) {
+ netdev_dbg(dev, "socket fd=%d not found (gtp1u)\n", fd_gtp1);
+ err = -ENOENT;
+ goto err1;
+ }
+
+ if (sock1u->sk->sk_protocol != IPPROTO_UDP) {
+ netdev_dbg(dev, "socket fd=%d not UDP\n", fd_gtp1);
+ err = -EINVAL;
+ goto err2;
+ }
+
+ netdev_dbg(dev, "enable gtp on %p, %p\n", sock0, sock1u);
+
+ gtp->sock0 = sock0;
+ gtp->sock1u = sock1u;
+ gtp->net = src_net;
+
+ tuncfg.sk_user_data = gtp;
+ tuncfg.encap_rcv = gtp_encap_recv;
+ tuncfg.encap_destroy = gtp_encap_destroy;
+
+ tuncfg.encap_type = UDP_ENCAP_GTP0;
+ setup_udp_tunnel_sock(sock_net(gtp->sock0->sk), gtp->sock0, &tuncfg);
+
+ tuncfg.encap_type = UDP_ENCAP_GTP1U;
+ setup_udp_tunnel_sock(sock_net(gtp->sock1u->sk), gtp->sock1u, &tuncfg);
+
+ err = 0;
+err2:
+ sockfd_put(sock1u);
+err1:
+ sockfd_put(sock0);
+ return err;
+}
+
+static struct net_device *gtp_find_dev(struct net *net, int ifindex)
+{
+ struct gtp_net *gn = net_generic(net, gtp_net_id);
+ struct gtp_dev *gtp;
+
+ list_for_each_entry_rcu(gtp, &gn->gtp_dev_list, list) {
+ if (ifindex == gtp->dev->ifindex)
+ return gtp->dev;
+ }
+ return NULL;
+}
+
+static void ipv4_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info)
+{
+ pctx->gtp_version = nla_get_u32(info->attrs[GTPA_VERSION]);
+ pctx->af = AF_INET;
+ pctx->sgsn_addr_ip4.s_addr =
+ nla_get_be32(info->attrs[GTPA_SGSN_ADDRESS]);
+ pctx->ms_addr_ip4.s_addr =
+ nla_get_be32(info->attrs[GTPA_MS_ADDRESS]);
+
+ switch (pctx->gtp_version) {
+ case GTP_V0:
+ /* According to TS 09.60, sections 7.5.1 and 7.5.2, the flow
+ * label needs to be the same for uplink and downlink packets,
+ * so let's annotate this.
+ */
+ pctx->u.v0.tid = nla_get_u64(info->attrs[GTPA_TID]);
+ pctx->u.v0.flow = nla_get_u16(info->attrs[GTPA_FLOW]);
+ break;
+ case GTP_V1:
+ pctx->u.v1.i_tei = nla_get_u32(info->attrs[GTPA_I_TEI]);
+ pctx->u.v1.o_tei = nla_get_u32(info->attrs[GTPA_O_TEI]);
+ break;
+ default:
+ break;
+ }
+}
+
+static int ipv4_pdp_add(struct net_device *dev, struct genl_info *info)
+{
+ struct gtp_dev *gtp = netdev_priv(dev);
+ u32 hash_ms, hash_tid = 0;
+ struct pdp_ctx *pctx;
+ bool found = false;
+ __be32 ms_addr;
+
+ ms_addr = nla_get_be32(info->attrs[GTPA_MS_ADDRESS]);
+ hash_ms = ipv4_hashfn(ms_addr) % gtp->hash_size;
+
+ hlist_for_each_entry_rcu(pctx, >p->addr_hash[hash_ms], hlist_addr) {
+ if (pctx->ms_addr_ip4.s_addr == ms_addr) {
+ found = true;
+ break;
+ }
+ }
+
+ if (found) {
+ if (info->nlhdr->nlmsg_flags & NLM_F_EXCL)
+ return -EEXIST;
+ if (info->nlhdr->nlmsg_flags & NLM_F_REPLACE)
+ return -EOPNOTSUPP;
+
+ ipv4_pdp_fill(pctx, info);
+
+ if (pctx->gtp_version == GTP_V0)
+ netdev_dbg(dev, "GTPv0-U: update tunnel id = %llx (pdp %p)\n",
+ pctx->u.v0.tid, pctx);
+ else if (pctx->gtp_version == GTP_V1)
+ netdev_dbg(dev, "GTPv1-U: update tunnel id = %x/%x (pdp %p)\n",
+ pctx->u.v1.i_tei, pctx->u.v1.o_tei, pctx);
+
+ return 0;
+
+ }
+
+ pctx = kmalloc(sizeof(struct pdp_ctx), GFP_KERNEL);
+ if (pctx == NULL)
+ return -ENOMEM;
+
+ ipv4_pdp_fill(pctx, info);
+ atomic_set(&pctx->tx_seq, 0);
+
+ switch (pctx->gtp_version) {
+ case GTP_V0:
+ /* TS 09.60: "The flow label identifies unambiguously a GTP
+ * flow.". We use the tid for this instead, I cannot find a
+ * situation in which this doesn't unambiguosly identify the
+ * PDP context.
+ */
+ hash_tid = gtp0_hashfn(pctx->u.v0.tid) % gtp->hash_size;
+ break;
+ case GTP_V1:
+ hash_tid = gtp1u_hashfn(pctx->u.v1.i_tei) % gtp->hash_size;
+ break;
+ }
+
+ hlist_add_head_rcu(&pctx->hlist_addr, >p->addr_hash[hash_ms]);
+ hlist_add_head_rcu(&pctx->hlist_tid, >p->tid_hash[hash_tid]);
+
+ switch (pctx->gtp_version) {
+ case GTP_V0:
+ netdev_dbg(dev, "GTPv0-U: new PDP ctx id=%llx ssgn=%pI4 ms=%pI4 (pdp=%p)\n",
+ pctx->u.v0.tid, &pctx->sgsn_addr_ip4,
+ &pctx->ms_addr_ip4, pctx);
+ break;
+ case GTP_V1:
+ netdev_dbg(dev, "GTPv1-U: new PDP ctx id=%x/%x ssgn=%pI4 ms=%pI4 (pdp=%p)\n",
+ pctx->u.v1.i_tei, pctx->u.v1.o_tei,
+ &pctx->sgsn_addr_ip4, &pctx->ms_addr_ip4, pctx);
+ break;
+ }
+
+ return 0;
+}
+
+static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info)
+{
+ struct net_device *dev;
+ struct net *net;
+
+ if (!info->attrs[GTPA_VERSION] ||
+ !info->attrs[GTPA_LINK] ||
+ !info->attrs[GTPA_SGSN_ADDRESS] ||
+ !info->attrs[GTPA_MS_ADDRESS])
+ return -EINVAL;
+
+ switch (nla_get_u32(info->attrs[GTPA_VERSION])) {
+ case GTP_V0:
+ if (!info->attrs[GTPA_TID] ||
+ !info->attrs[GTPA_FLOW])
+ return -EINVAL;
+ break;
+ case GTP_V1:
+ if (!info->attrs[GTPA_I_TEI] ||
+ !info->attrs[GTPA_O_TEI])
+ return -EINVAL;
+ break;
+
+ default:
+ return -EINVAL;
+ }
+
+ net = gtp_genl_get_net(sock_net(skb->sk), info->attrs);
+ if (IS_ERR(net))
+ return PTR_ERR(net);
+
+ /* Check if there's an existing gtpX device to configure */
+ dev = gtp_find_dev(net, nla_get_u32(info->attrs[GTPA_LINK]));
+ if (dev == NULL)
+ return -ENODEV;
+
+ return ipv4_pdp_add(dev, info);
+}
+
+static int gtp_genl_del_pdp(struct sk_buff *skb, struct genl_info *info)
+{
+ struct net_device *dev;
+ struct pdp_ctx *pctx;
+ struct gtp_dev *gtp;
+ struct net *net;
+
+ if (!info->attrs[GTPA_VERSION] ||
+ !info->attrs[GTPA_LINK])
+ return -EINVAL;
+
+ net = gtp_genl_get_net(sock_net(skb->sk), info->attrs);
+ if (IS_ERR(net))
+ return PTR_ERR(net);
+
+ /* Check if there's an existing gtpX device to configure */
+ dev = gtp_find_dev(net, nla_get_u32(info->attrs[GTPA_LINK]));
+ if (dev == NULL)
+ return -ENODEV;
+
+ gtp = netdev_priv(dev);
+
+ switch (nla_get_u32(info->attrs[GTPA_VERSION])) {
+ case GTP_V0:
+ if (!info->attrs[GTPA_TID])
+ return -EINVAL;
+ pctx = gtp0_pdp_find(gtp, nla_get_u64(info->attrs[GTPA_TID]));
+ break;
+ case GTP_V1:
+ if (!info->attrs[GTPA_I_TEI])
+ return -EINVAL;
+ pctx = gtp1_pdp_find(gtp, nla_get_u64(info->attrs[GTPA_I_TEI]));
+ break;
+
+ default:
+ return -EINVAL;
+ }
+
+ if (pctx == NULL)
+ return -ENOENT;
+
+ if (pctx->gtp_version == GTP_V0)
+ netdev_dbg(dev, "GTPv0-U: deleting tunnel id = %llx (pdp %p)\n",
+ pctx->u.v0.tid, pctx);
+ else if (pctx->gtp_version == GTP_V1)
+ netdev_dbg(dev, "GTPv1-U: deleting tunnel id = %x/%x (pdp %p)\n",
+ pctx->u.v1.i_tei, pctx->u.v1.o_tei, pctx);
+
+ hlist_del_rcu(&pctx->hlist_tid);
+ hlist_del_rcu(&pctx->hlist_addr);
+ kfree_rcu(pctx, rcu_head);
+
+ return 0;
+}
+
+static struct genl_family gtp_genl_family = {
+ .id = GENL_ID_GENERATE,
+ .name = "gtp",
+ .version = 0,
+ .hdrsize = 0,
+ .maxattr = GTPA_MAX,
+ .netnsok = true,
+};
+
+static int gtp_genl_fill_info(struct sk_buff *skb, u32 snd_portid, u32 snd_seq,
+ u32 type, struct pdp_ctx *pctx)
+{
+ void *genlh;
+
+ genlh = genlmsg_put(skb, snd_portid, snd_seq, >p_genl_family, 0,
+ type);
+ if (genlh == NULL)
+ goto nlmsg_failure;
+
+ if (nla_put_u32(skb, GTPA_VERSION, pctx->gtp_version) ||
+ nla_put_be32(skb, GTPA_SGSN_ADDRESS, pctx->sgsn_addr_ip4.s_addr) ||
+ nla_put_be32(skb, GTPA_MS_ADDRESS, pctx->ms_addr_ip4.s_addr))
+ goto nla_put_failure;
+
+ switch (pctx->gtp_version) {
+ case GTP_V0:
+ if (nla_put_u64_64bit(skb, GTPA_TID, pctx->u.v0.tid, GTPA_PAD) ||
+ nla_put_u16(skb, GTPA_FLOW, pctx->u.v0.flow))
+ goto nla_put_failure;
+ break;
+ case GTP_V1:
+ if (nla_put_u32(skb, GTPA_I_TEI, pctx->u.v1.i_tei) ||
+ nla_put_u32(skb, GTPA_O_TEI, pctx->u.v1.o_tei))
+ goto nla_put_failure;
+ break;
+ }
+ genlmsg_end(skb, genlh);
+ return 0;
+
+nlmsg_failure:
+nla_put_failure:
+ genlmsg_cancel(skb, genlh);
+ return -EMSGSIZE;
+}
+
+static int gtp_genl_get_pdp(struct sk_buff *skb, struct genl_info *info)
+{
+ struct pdp_ctx *pctx = NULL;
+ struct net_device *dev;
+ struct sk_buff *skb2;
+ struct gtp_dev *gtp;
+ u32 gtp_version;
+ struct net *net;
+ int err;
+
+ if (!info->attrs[GTPA_VERSION] ||
+ !info->attrs[GTPA_LINK])
+ return -EINVAL;
+
+ gtp_version = nla_get_u32(info->attrs[GTPA_VERSION]);
+ switch (gtp_version) {
+ case GTP_V0:
+ case GTP_V1:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ net = gtp_genl_get_net(sock_net(skb->sk), info->attrs);
+ if (IS_ERR(net))
+ return PTR_ERR(net);
+
+ /* Check if there's an existing gtpX device to configure */
+ dev = gtp_find_dev(net, nla_get_u32(info->attrs[GTPA_LINK]));
+ if (dev == NULL)
+ return -ENODEV;
+
+ gtp = netdev_priv(dev);
+
+ rcu_read_lock();
+ if (gtp_version == GTP_V0 &&
+ info->attrs[GTPA_TID]) {
+ u64 tid = nla_get_u64(info->attrs[GTPA_TID]);
+
+ pctx = gtp0_pdp_find(gtp, tid);
+ } else if (gtp_version == GTP_V1 &&
+ info->attrs[GTPA_I_TEI]) {
+ u32 tid = nla_get_u32(info->attrs[GTPA_I_TEI]);
+
+ pctx = gtp1_pdp_find(gtp, tid);
+ } else if (info->attrs[GTPA_MS_ADDRESS]) {
+ __be32 ip = nla_get_be32(info->attrs[GTPA_MS_ADDRESS]);
+
+ pctx = ipv4_pdp_find(gtp, ip);
+ }
+
+ if (pctx == NULL) {
+ err = -ENOENT;
+ goto err_unlock;
+ }
+
+ skb2 = genlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC);
+ if (skb2 == NULL) {
+ err = -ENOMEM;
+ goto err_unlock;
+ }
+
+ err = gtp_genl_fill_info(skb2, NETLINK_CB(skb).portid,
+ info->snd_seq, info->nlhdr->nlmsg_type, pctx);
+ if (err < 0)
+ goto err_unlock_free;
+
+ rcu_read_unlock();
+ return genlmsg_unicast(genl_info_net(info), skb2, info->snd_portid);
+
+err_unlock_free:
+ kfree_skb(skb2);
+err_unlock:
+ rcu_read_unlock();
+ return err;
+}
+
+static int gtp_genl_dump_pdp(struct sk_buff *skb,
+ struct netlink_callback *cb)
+{
+ struct gtp_dev *last_gtp = (struct gtp_dev *)cb->args[2], *gtp;
+ struct net *net = sock_net(skb->sk);
+ struct gtp_net *gn = net_generic(net, gtp_net_id);
+ unsigned long tid = cb->args[1];
+ int i, k = cb->args[0], ret;
+ struct pdp_ctx *pctx;
+
+ if (cb->args[4])
+ return 0;
+
+ list_for_each_entry_rcu(gtp, &gn->gtp_dev_list, list) {
+ if (last_gtp && last_gtp != gtp)
+ continue;
+ else
+ last_gtp = NULL;
+
+ for (i = k; i < gtp->hash_size; i++) {
+ hlist_for_each_entry_rcu(pctx, >p->tid_hash[i], hlist_tid) {
+ if (tid && tid != pctx->u.tid)
+ continue;
+ else
+ tid = 0;
+
+ ret = gtp_genl_fill_info(skb,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ cb->nlh->nlmsg_type, pctx);
+ if (ret < 0) {
+ cb->args[0] = i;
+ cb->args[1] = pctx->u.tid;
+ cb->args[2] = (unsigned long)gtp;
+ goto out;
+ }
+ }
+ }
+ }
+ cb->args[4] = 1;
+out:
+ return skb->len;
+}
+
+static struct nla_policy gtp_genl_policy[GTPA_MAX + 1] = {
+ [GTPA_LINK] = { .type = NLA_U32, },
+ [GTPA_VERSION] = { .type = NLA_U32, },
+ [GTPA_TID] = { .type = NLA_U64, },
+ [GTPA_SGSN_ADDRESS] = { .type = NLA_U32, },
+ [GTPA_MS_ADDRESS] = { .type = NLA_U32, },
+ [GTPA_FLOW] = { .type = NLA_U16, },
+ [GTPA_NET_NS_FD] = { .type = NLA_U32, },
+ [GTPA_I_TEI] = { .type = NLA_U32, },
+ [GTPA_O_TEI] = { .type = NLA_U32, },
+};
+
+static const struct genl_ops gtp_genl_ops[] = {
+ {
+ .cmd = GTP_CMD_NEWPDP,
+ .doit = gtp_genl_new_pdp,
+ .policy = gtp_genl_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+ {
+ .cmd = GTP_CMD_DELPDP,
+ .doit = gtp_genl_del_pdp,
+ .policy = gtp_genl_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+ {
+ .cmd = GTP_CMD_GETPDP,
+ .doit = gtp_genl_get_pdp,
+ .dumpit = gtp_genl_dump_pdp,
+ .policy = gtp_genl_policy,
+ .flags = GENL_ADMIN_PERM,
+ },
+};
+
+static int __net_init gtp_net_init(struct net *net)
+{
+ struct gtp_net *gn = net_generic(net, gtp_net_id);
+
+ INIT_LIST_HEAD(&gn->gtp_dev_list);
+ return 0;
+}
+
+static void __net_exit gtp_net_exit(struct net *net)
+{
+ struct gtp_net *gn = net_generic(net, gtp_net_id);
+ struct gtp_dev *gtp;
+ LIST_HEAD(list);
+
+ rtnl_lock();
+ list_for_each_entry(gtp, &gn->gtp_dev_list, list)
+ gtp_dellink(gtp->dev, &list);
+
+ unregister_netdevice_many(&list);
+ rtnl_unlock();
+}
+
+static struct pernet_operations gtp_net_ops = {
+ .init = gtp_net_init,
+ .exit = gtp_net_exit,
+ .id = >p_net_id,
+ .size = sizeof(struct gtp_net),
+};
+
+static int __init gtp_init(void)
+{
+ int err;
+
+ get_random_bytes(>p_h_initval, sizeof(gtp_h_initval));
+
+ err = rtnl_link_register(>p_link_ops);
+ if (err < 0)
+ goto error_out;
+
+ err = genl_register_family_with_ops(>p_genl_family, gtp_genl_ops);
+ if (err < 0)
+ goto unreg_rtnl_link;
+
+ err = register_pernet_subsys(>p_net_ops);
+ if (err < 0)
+ goto unreg_genl_family;
+
+ pr_info("GTP module loaded (pdp ctx size %Zd bytes)\n",
+ sizeof(struct pdp_ctx));
+ return 0;
+
+unreg_genl_family:
+ genl_unregister_family(>p_genl_family);
+unreg_rtnl_link:
+ rtnl_link_unregister(>p_link_ops);
+error_out:
+ pr_err("error loading GTP module loaded\n");
+ return err;
+}
+late_initcall(gtp_init);
+
+static void __exit gtp_fini(void)
+{
+ unregister_pernet_subsys(>p_net_ops);
+ genl_unregister_family(>p_genl_family);
+ rtnl_link_unregister(>p_link_ops);
+
+ pr_info("GTP module unloaded\n");
+}
+module_exit(gtp_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Harald Welte <hwelte@sysmocom.de>");
+MODULE_DESCRIPTION("Interface driver for GTP encapsulated traffic");
+MODULE_ALIAS_RTNL_LINK("gtp");
diff --git a/include/net/gtp.h b/include/net/gtp.h
new file mode 100644
index 0000000..894a37b
--- /dev/null
+++ b/include/net/gtp.h
@@ -0,0 +1,34 @@
+#ifndef _GTP_H_
+#define _GTP_H
+
+/* General GTP protocol related definitions. */
+
+#define GTP0_PORT 3386
+#define GTP1U_PORT 2152
+
+#define GTP_TPDU 255
+
+struct gtp0_header { /* According to GSM TS 09.60. */
+ __u8 flags;
+ __u8 type;
+ __be16 length;
+ __be16 seq;
+ __be16 flow;
+ __u8 number;
+ __u8 spare[3];
+ __be64 tid;
+} __attribute__ ((packed));
+
+struct gtp1_header { /* According to 3GPP TS 29.060. */
+ __u8 flags;
+ __u8 type;
+ __be16 length;
+ __be32 tid;
+} __attribute__ ((packed));
+
+#define GTP1_F_NPDU 0x01
+#define GTP1_F_SEQ 0x02
+#define GTP1_F_EXTHDR 0x04
+#define GTP1_F_MASK 0x07
+
+#endif
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 813ffb2e..8bdae34 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -141,6 +141,7 @@ header-y += gfs2_ondisk.h
header-y += gigaset_dev.h
header-y += gpio.h
header-y += gsmmux.h
+header-y += gtp.h
header-y += hdlcdrv.h
header-y += hdlc.h
header-y += hdreg.h
diff --git a/include/uapi/linux/gtp.h b/include/uapi/linux/gtp.h
new file mode 100644
index 0000000..ca1054d
--- /dev/null
+++ b/include/uapi/linux/gtp.h
@@ -0,0 +1,33 @@
+#ifndef _UAPI_LINUX_GTP_H_
+#define _UAPI_LINUX_GTP_H__
+
+enum gtp_genl_cmds {
+ GTP_CMD_NEWPDP,
+ GTP_CMD_DELPDP,
+ GTP_CMD_GETPDP,
+
+ GTP_CMD_MAX,
+};
+
+enum gtp_version {
+ GTP_V0 = 0,
+ GTP_V1,
+};
+
+enum gtp_attrs {
+ GTPA_UNSPEC = 0,
+ GTPA_LINK,
+ GTPA_VERSION,
+ GTPA_TID, /* for GTPv0 only */
+ GTPA_SGSN_ADDRESS,
+ GTPA_MS_ADDRESS,
+ GTPA_FLOW,
+ GTPA_NET_NS_FD,
+ GTPA_I_TEI, /* for GTPv1 only */
+ GTPA_O_TEI, /* for GTPv1 only */
+ GTPA_PAD,
+ __GTPA_MAX,
+};
+#define GTPA_MAX (__GTPA_MAX + 1)
+
+#endif /* _UAPI_LINUX_GTP_H_ */
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index d2d7fd4..bb36bd5 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -529,6 +529,16 @@ enum {
};
#define IFLA_PPP_MAX (__IFLA_PPP_MAX - 1)
+/* GTP section */
+enum {
+ IFLA_GTP_UNSPEC,
+ IFLA_GTP_FD0,
+ IFLA_GTP_FD1,
+ IFLA_GTP_PDP_HASHSIZE,
+ __IFLA_GTP_MAX,
+};
+#define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1)
+
/* Bonding section */
enum {
diff --git a/include/uapi/linux/udp.h b/include/uapi/linux/udp.h
index 16574ea..2c8180f 100644
--- a/include/uapi/linux/udp.h
+++ b/include/uapi/linux/udp.h
@@ -36,6 +36,7 @@ struct udphdr {
#define UDP_ENCAP_ESPINUDP_NON_IKE 1 /* draft-ietf-ipsec-nat-t-ike-00/01 */
#define UDP_ENCAP_ESPINUDP 2 /* draft-ietf-ipsec-udp-encaps-06 */
#define UDP_ENCAP_L2TPINUDP 3 /* rfc2661 */
-
+#define UDP_ENCAP_GTP0 4 /* GSM TS 09.60 */
+#define UDP_ENCAP_GTP1U 5 /* 3GPP TS 29.060 */
#endif /* _UAPI_LINUX_UDP_H */
--
2.1.4
^ permalink raw reply related
* Re: [PATCH v2 2/3] net: ethernet: fec: use phydev from struct net_device
From: Ben Hutchings @ 2016-05-08 23:01 UTC (permalink / raw)
To: Philippe Reynes
Cc: fugang.duan, davem, kan.liang, decot, aduyck, jiri,
jacob.e.keller, tom, andrew, netdev, linux-kernel
In-Reply-To: <572FC20A.5030805@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 849 bytes --]
On Mon, 2016-05-09 at 00:47 +0200, Philippe Reynes wrote:
> On 09/05/16 00:22, Ben Hutchings wrote:
> >
> > On Sun, 2016-05-08 at 23:44 +0200, Philippe Reynes wrote:
> > >
> > > The private structure contain a pointer to phydev, but the structure
> > > net_device already contain such pointer. So we can remove the pointer
> > > phydev in the private structure, and update the driver to use the one
> > > contained in struct net_device.
> > But there is no central code that updates the pointer, so:
> The function phy_attach_direct and phy_detach update the pointer
> phydev in the struct net_device.
[...]
> So from my understanding, those two lines aren't usefull.
> May you confirm that I'm on the right way please ?
Sorry, you're right.
Ben.
--
Ben Hutchings
I haven't lost my mind; it's backed up on tape somewhere.
[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 819 bytes --]
^ permalink raw reply
* Re: [PATCH net-next 5/7] Driver: Vmxnet3: Add support for get_coalesce, set_coalesce ethtool operations
From: Ben Hutchings @ 2016-05-09 0:17 UTC (permalink / raw)
To: Shrikrishna Khare
Cc: netdev, linux-kernel, pv-drivers, Keyong Sun, Manoj Tammali
In-Reply-To: <alpine.DEB.2.10.1605081335140.13942@shri-linux.eng.vmware.com>
[-- Attachment #1: Type: text/plain, Size: 3079 bytes --]
On Sun, 2016-05-08 at 13:55 -0700, Shrikrishna Khare wrote:
>
> On Sat, 7 May 2016, Ben Hutchings wrote:
>
> > On Fri, 2016-05-06 at 16:12 -0700, Shrikrishna Khare wrote:
> > [...]
> > > +static int
> > > +vmxnet3_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec)
> > > +{
> > [...]
> > > + switch (ec->rx_coalesce_usecs) {
> > > + case VMXNET3_COALESCE_DEFAULT:
> > > + case VMXNET3_COALESCE_DISABLED:
> > > + case VMXNET3_COALESCE_ADAPT:
> > > + if (ec->tx_max_coalesced_frames ||
> > > + ec->tx_max_coalesced_frames_irq ||
> > > + ec->rx_max_coalesced_frames_irq) {
> > > + return -EINVAL;
> > > + }
> > > + memset(adapter->coal_conf, 0, sizeof(*adapter->coal_conf));
> > > + adapter->coal_conf->coalMode = ec->rx_coalesce_usecs;
> > > + break;
> > > + case VMXNET3_COALESCE_STATIC:
> > [...]
> >
> > I don't want to see drivers introducing magic values for fields that
> > are denominated in microseconds (especially not for 0, which is the
> > correct way to specify 'no coalescing'). If the current
> > ethtool_coalesce structure is inadequate, propose an extension.
>
> For vmxnet3, we need an ethtool mechanism to indicate coalescing mode to
> the device.
>
> Would a patch that maps 0 to 'no coalescing' be acceptable? That is:
>
> rx-usecs = 0 -> coalescing disabled.
> rx-usecs = 1 -> default (chosen by the device).
> rx-usecs = 2 -> adaptive coalescing.
> rx-usecs = 3 -> static coalescing.
I still don't like it much. For the 3 special values (0 isn't really
special):
1 = default: When the driver sets the virtual device to this mode, can it then read back what the actual settings are, or are they hidden? If it can, then userland can also read the defaults and explicitly return to them later. But I do see the usefulness of an explicit request to reset to defaults.
2 = adaptive coalescing: There are already fields to request adaptive coalescing; you should support them.
3 = static coalescing: I don't understand what this means.
> all other rx-usecs values -> rate based coalescing where rx-usecs denotes
> rate.
>
> Alternatively: I don't think new members could be added to struct
> ethtool_coalesce without breaking compatibility.
That's right, unfortunately.
> Thus, I could extend coalescing as follows:
> - new struct ethtool_coalesce_v2 with coalesce_mode (along with all the
> members of struct ethtool_coalesce).
> - introduce new ETHTOOL_{G,S}COALESCE_V2 commands.
> - extend userspace ethtool to invoke new commands.
>
> Could you please advice?
That's roughly how you would extend it. Though we would probably want
to consider making other extensions to interrupt coalescing control at
the same time.
Ben.
>
Ben Hutchings
If you seem to know what you are doing, you'll be given more to do.
[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 819 bytes --]
^ permalink raw reply
* linux-next: manual merge of the net-next tree with the wireless-drivers tree
From: Stephen Rothwell @ 2016-05-09 0:39 UTC (permalink / raw)
To: David Miller, netdev, Kalle Valo
Cc: linux-next, linux-kernel, Emmanuel Grumbach, Sara Sharon
Hi all,
Today's linux-next merge of the net-next tree got a conflict in:
drivers/net/wireless/intel/iwlwifi/mvm/tx.c
between commit:
5c08b0f5026f ("iwlwifi: mvm: don't override the rate with the AMSDU len")
from the wireless-drivers tree and commit:
d8fe484470dd ("iwlwifi: mvm: add support for new TX CMD API")
from the net-next tree.
I fixed it up (see below) and can carry the fix as necessary. This
is now fixed as far as linux-next is concerned, but any non trivial
conflicts should be mentioned to your upstream maintainer when your tree
is submitted for merging. You may also want to consider cooperating
with the maintainer of the conflicting tree to minimise any particularly
complex conflicts.
--
Cheers,
Stephen Rothwell
diff --cc drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index 34731e29c589,bd286fca3776..000000000000
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@@ -186,10 -294,16 +295,16 @@@ void iwl_mvm_set_tx_cmd(struct iwl_mvm
tx_cmd->tx_flags = cpu_to_le32(tx_flags);
/* Total # bytes to be transmitted */
tx_cmd->len = cpu_to_le16((u16)skb->len +
- (uintptr_t)info->driver_data[0]);
+ (uintptr_t)skb_info->driver_data[0]);
- tx_cmd->next_frame_len = 0;
tx_cmd->life_time = cpu_to_le32(TX_CMD_LIFE_TIME_INFINITE);
tx_cmd->sta_id = sta_id;
+
+ /* padding is inserted later in transport */
+ if (ieee80211_hdrlen(fc) % 4 &&
+ !(tx_cmd->offload_assist & cpu_to_le16(BIT(TX_CMD_OFFLD_AMSDU))))
+ tx_cmd->offload_assist |= cpu_to_le16(BIT(TX_CMD_OFFLD_PAD));
+
+ iwl_mvm_tx_csum(mvm, skb, hdr, info, tx_cmd);
}
/*
^ permalink raw reply
* linux-next: manual merge of the net-next tree with the net tree
From: Stephen Rothwell @ 2016-05-09 0:43 UTC (permalink / raw)
To: David Miller, netdev
Cc: linux-next, linux-kernel, Jarno Rajahalme, Tom Herbert
Hi all,
Today's linux-next merge of the net-next tree got a conflict in:
include/linux/netdevice.h
between commit:
229740c63169 ("udp_offload: Set encapsulation before inner completes.")
from the net tree and commit:
46aa2f30aa7f ("udp: Remove udp_offloads")
from the net-next tree.
I fixed it up (the latter removed the struct that was commented in the
former) and can carry the fix as necessary. This is now fixed as far as
linux-next is concerned, but any non trivial conflicts should be mentioned
to your upstream maintainer when your tree is submitted for merging.
You may also want to consider cooperating with the maintainer of the
conflicting tree to minimise any particularly complex conflicts.
--
Cheers,
Stephen Rothwell
^ permalink raw reply
* networking/ip-sysctl.txt: SRR or SSRR
From: Christian Kujau @ 2016-05-09 1:23 UTC (permalink / raw)
To: netdev
In Documentation/networking/ip-sysctl.txt, the accept_source_route
parameter is described with:
Accept packets with SRR option.
I could not find anything describing an "SRR option". The closest thing
was something called "SSR - Strict Source Route"[0] - is that what is
meant here? If so, RFC791 then refers to the same as "SSRR", as in "strict
source and record route". Does the patch below clears that up or did I
confuse it with something else?
Thanks,
Christian.
Signed-off-by: Christian Kujau <lists@nerdbynature.de>
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index b183e2b..db6b538 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1057,9 +1057,9 @@ bootp_relay - BOOLEAN
Not Implemented Yet.
accept_source_route - BOOLEAN
- Accept packets with SRR option.
+ Accept packets with SSRR option (RFC791 3.1).
conf/all/accept_source_route must also be set to TRUE to accept packets
- with SRR option on the interface
+ with SSRR option on the interface
default TRUE (router)
FALSE (host)
[0] https://www.iana.org/assignments/ip-parameters/ip-parameters.xhtml
--
BOFH excuse #224:
Jan 9 16:41:27 huber su: 'su root' succeeded for .... on /dev/pts/1
^ permalink raw reply related
* RE: [PATCH v2 0/3] net: ethtool: add ethtool_op_{get|set}_link_ksettings
From: Fugang Duan @ 2016-05-09 1:57 UTC (permalink / raw)
To: Philippe Reynes, davem@davemloft.net, ben@decadent.org.uk,
kan.liang@intel.com, decot@googlers.com, aduyck@mirantis.com,
jiri@mellanox.com, jacob.e.keller@intel.com, tom@herbertland.com,
andrew@lunn.ch
Cc: netdev@vger.kernel.org, linux-kernel@vger.kernel.org
In-Reply-To: <1462743877-31738-1-git-send-email-tremyfr@gmail.com>
Fom: Philippe Reynes <tremyfr@gmail.com> Sent: Monday, May 09, 2016 5:45 AM
> To: Fugang Duan <fugang.duan@nxp.com>; davem@davemloft.net;
> ben@decadent.org.uk; kan.liang@intel.com; decot@googlers.com;
> aduyck@mirantis.com; jiri@mellanox.com; jacob.e.keller@intel.com;
> tom@herbertland.com; andrew@lunn.ch
> Cc: netdev@vger.kernel.org; linux-kernel@vger.kernel.org; Philippe Reynes
> <tremyfr@gmail.com>
> Subject: [PATCH v2 0/3] net: ethtool: add ethtool_op_{get|set}_link_ksettings
>
> Ethtool callbacks {get|set}_link_ksettings may be the same for many drivers. So
> we add two generics callbacks ethtool_op_{get|set}_link_ksettings.
>
> To use those generics callbacks, the ethernet driver must use the pointer
> phydev contained in struct net_device, and not use a private structure to store
> this pointer.
>
> Changelog:
> v2:
> - use generic function instead of macro
> - ethernet driver use the pointer phydev provided by struct net_device
> Those idea were provided by Ben Hutchings,
> and Florian Fainelli acknowledge them.
>
> Philippe Reynes (3):
> net: core: ethtool: add ethtool_op_{get|set}_link_ksettings
> net: ethernet: fec: use phydev from struct net_device
> net: ethernet: fec: use ethtool_op_{get|set}_link_ksettings
>
> drivers/net/ethernet/freescale/fec.h | 1 -
> drivers/net/ethernet/freescale/fec_main.c | 71 +++++++++--------------------
> include/linux/ethtool.h | 5 ++
> net/core/ethtool.c | 24 ++++++++++
> 4 files changed, 50 insertions(+), 51 deletions(-)
>
> --
> 1.7.4.4
Acked-by: Fugang Duan <fugang.duan@nxp.com>
^ 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