* [PATCH net-next 2/3] {IPv4,xfrm} Add Extended Sequence Number (ESN) support for AH ingress part
From: Fan Du @ 2014-01-08 8:53 UTC (permalink / raw)
To: steffen.klassert; +Cc: davem, netdev
In-Reply-To: <1389171192-28091-1-git-send-email-fan.du@windriver.com>
This patch add esn support for AH input stage by attaching upper 32bits
sequence number right after packet payload as specified by RFC 4302.
Then the ICV value will guard upper 32bits sequence number as well when
packet getting in.
Signed-off-by: Fan Du <fan.du@windriver.com>
---
net/ipv4/ah4.c | 24 +++++++++++++++++++++---
1 file changed, 21 insertions(+), 3 deletions(-)
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index a7fac03..169d9a5 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -312,6 +312,10 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb)
struct ip_auth_hdr *ah;
struct ah_data *ahp;
int err = -ENOMEM;
+ int seqhi_len = 0;
+ __be32 *seqhi;
+ int sglists = 0;
+ struct scatterlist *seqhisg;
if (!pskb_may_pull(skb, sizeof(*ah)))
goto out;
@@ -352,14 +356,21 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb)
iph = ip_hdr(skb);
ihl = ip_hdrlen(skb);
- work_iph = ah_alloc_tmp(ahash, nfrags, ihl + ahp->icv_trunc_len);
+ if (x->props.flags & XFRM_STATE_ESN) {
+ sglists = 1;
+ seqhi_len = sizeof(*seqhi);
+ }
+
+ work_iph = ah_alloc_tmp(ahash, nfrags + sglists, ihl + ahp->icv_trunc_len + seqhi_len);
if (!work_iph)
goto out;
- auth_data = ah_tmp_auth(work_iph, ihl);
+ seqhi = (__be32 *)((char *)work_iph + ihl);
+ auth_data = ah_tmp_auth(seqhi, seqhi_len);
icv = ah_tmp_icv(ahash, auth_data, ahp->icv_trunc_len);
req = ah_tmp_req(ahash, icv);
sg = ah_req_sg(ahash, req);
+ seqhisg = sg + nfrags;
memcpy(work_iph, iph, ihl);
memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len);
@@ -381,7 +392,14 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb)
sg_init_table(sg, nfrags);
skb_to_sgvec(skb, sg, 0, skb->len);
- ahash_request_set_crypt(req, sg, icv, skb->len);
+ if ((x->props.flags & XFRM_STATE_ESN)) {
+ sg_unmark_end(&sg[nfrags - 1]);
+ /* Attach seqhi sg right after packet payload */
+ *seqhi = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
+ sg_init_table(seqhisg, sglists);
+ sg_set_buf(seqhisg, seqhi, seqhi_len);
+ }
+ ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len);
ahash_request_set_callback(req, 0, ah_input_done, skb);
AH_SKB_CB(skb)->tmp = work_iph;
--
1.7.9.5
^ permalink raw reply related
* [PATCH net-next 1/3] {IPv4,xfrm} Add Extended Sequence Number (ESN) support for AH egress part
From: Fan Du @ 2014-01-08 8:53 UTC (permalink / raw)
To: steffen.klassert; +Cc: davem, netdev
In-Reply-To: <1389171192-28091-1-git-send-email-fan.du@windriver.com>
This patch add esn support for AH output stage by attaching upper 32bits
sequence number right after packet payload as specified by RFC 4302.
Then the ICV value will guard upper 32bits sequence number as well when
packet going out.
Signed-off-by: Fan Du <fan.du@windriver.com>
---
net/ipv4/ah4.c | 25 +++++++++++++++++++++----
1 file changed, 21 insertions(+), 4 deletions(-)
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index 7179026..a7fac03 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -12,6 +12,7 @@
#include <linux/scatterlist.h>
#include <net/icmp.h>
#include <net/protocol.h>
+#include <crypto/scatterwalk.h>
struct ah_skb_cb {
struct xfrm_skb_cb xfrm;
@@ -155,6 +156,10 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb)
struct iphdr *iph, *top_iph;
struct ip_auth_hdr *ah;
struct ah_data *ahp;
+ int seqhi_len = 0;
+ __be32 *seqhi;
+ int sglists = 0;
+ struct scatterlist *seqhisg;
ahp = x->data;
ahash = ahp->ahash;
@@ -167,14 +172,19 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb)
ah = ip_auth_hdr(skb);
ihl = ip_hdrlen(skb);
+ if (x->props.flags & XFRM_STATE_ESN) {
+ sglists = 1;
+ seqhi_len = sizeof(*seqhi);
+ }
err = -ENOMEM;
- iph = ah_alloc_tmp(ahash, nfrags, ihl);
+ iph = ah_alloc_tmp(ahash, nfrags + sglists, ihl + seqhi_len);
if (!iph)
goto out;
-
- icv = ah_tmp_icv(ahash, iph, ihl);
+ seqhi = (__be32 *)((char *)iph + ihl);
+ icv = ah_tmp_icv(ahash, seqhi, seqhi_len);
req = ah_tmp_req(ahash, icv);
sg = ah_req_sg(ahash, req);
+ seqhisg = sg + nfrags;
memset(ah->auth_data, 0, ahp->icv_trunc_len);
@@ -213,7 +223,14 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb)
sg_init_table(sg, nfrags);
skb_to_sgvec(skb, sg, 0, skb->len);
- ahash_request_set_crypt(req, sg, icv, skb->len);
+ if ((x->props.flags & XFRM_STATE_ESN)) {
+ sg_unmark_end(&sg[nfrags - 1]);
+ /* Attach seqhi sg right after packet payload */
+ *seqhi = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
+ sg_init_table(seqhisg, sglists);
+ sg_set_buf(seqhisg, seqhi, seqhi_len);
+ }
+ ahash_request_set_crypt(req, sg, icv, skb->len + seqhi_len);
ahash_request_set_callback(req, 0, ah_output_done, skb);
AH_SKB_CB(skb)->tmp = iph;
--
1.7.9.5
^ permalink raw reply related
* [PATCH net-next 3/3] xfrm: Don't prohibit AH from using ESN feature
From: Fan Du @ 2014-01-08 8:53 UTC (permalink / raw)
To: steffen.klassert; +Cc: davem, netdev
In-Reply-To: <1389171192-28091-1-git-send-email-fan.du@windriver.com>
Clear checking when user try to use ESN through netlink keymgr for AH.
Signed-off-by: Fan Du <fan.du@windriver.com>
---
net/xfrm/xfrm_user.c | 4 ----
1 file changed, 4 deletions(-)
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 97681a3..f362a78 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -141,10 +141,6 @@ static inline int verify_replay(struct xfrm_usersa_info *p,
if (!rt)
return 0;
-
- if (p->id.proto != IPPROTO_ESP)
- return -EINVAL;
-
if (p->replay_window != 0)
return -EINVAL;
--
1.7.9.5
^ permalink raw reply related
* Re: [PATCH] ipv6: don't call addrconf_dst_alloc again when enable lo
From: Hannes Frederic Sowa @ 2014-01-08 8:55 UTC (permalink / raw)
To: Gao feng; +Cc: chenweilong, David Miller, kumaran.4353, netdev
In-Reply-To: <52CD0F86.30605@cn.fujitsu.com>
On Wed, Jan 08, 2014 at 04:42:46PM +0800, Gao feng wrote:
> On 01/08/2014 04:05 PM, Hannes Frederic Sowa wrote:
> > On Wed, Jan 08, 2014 at 03:50:09PM +0800, Gao feng wrote:
> >> On 01/03/2014 02:53 PM, Hannes Frederic Sowa wrote:
> >>> On Thu, Jan 02, 2014 at 05:33:15PM +0800, chenweilong wrote:
> >>>> diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
> >>>> index 62d1799..d2f8c0a 100644
> >>>> --- a/net/ipv6/addrconf.c
> >>>> +++ b/net/ipv6/addrconf.c
> >>>> @@ -2422,8 +2422,9 @@ static void init_loopback(struct net_device *dev)
> >>>> if (sp_ifa->flags & (IFA_F_DADFAILED | IFA_F_TENTATIVE))
> >>>> continue;
> >>>>
> >>>> - if (sp_ifa->rt)
> >>>> - continue;
> >>>> + if (sp_ifa->rt && sp_ifa->rt->dst.dev == dev) {
> >>>> + ip6_del_rt(sp_ifa->rt);
> >>>> + }
> >>>>
> >>>> sp_rt = addrconf_dst_alloc(idev, &sp_ifa->addr, 0);
> >>>>
> >>>
> >>> Maybe this change would not be that bad after all, as those ifa attached dsts
> >>> are already dead and queued up for gc and should not get inserted back.
> >>
> >> I like this idea, maybe the below patch is better. we only need to delete this
> >> route when it has been added to garbage list.
> >>
> >> diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
> >> index 1a341f7..4dca886 100644
> >> --- a/net/ipv6/addrconf.c
> >> +++ b/net/ipv6/addrconf.c
> >> @@ -2610,8 +2610,16 @@ static void init_loopback(struct net_device *dev)
> >> if (sp_ifa->flags & (IFA_F_DADFAILED | IFA_F_TENTATIVE))
> >> continue;
> >>
> >> - if (sp_ifa->rt)
> >> - continue;
> >> + if (sp_ifa->rt) {
> >> + /* This dst has been added to garbage list when
> >> + * lo device down, delete this obsolete dst and
> >> + * reallocate new router for ifa. */
> >> + if (sp_ifa->rt->dst.obsolete > 0) {
> >> + ip6_del_rt(sp_ifa->rt);
> >> + sp_ifa->rt = NULL;
> >> + } else
> >> + continue;
> >> + }
> >>
> >> sp_rt = addrconf_dst_alloc(idev, &sp_ifa->addr, false);
> >
> > It looks like it can work but I don't know if we should just fix this the
> > clean way (see below).
> >
> >>> I'll try to just disable routes without removing them at all when we set an
> >>> interface to down at the weekend.
> >>>
> >>
> >> How do you decide which route should be disabled? use rt6_flags? I don't know
> >> if your way will cause miscarriage.
> >
> > What I did so far is that I added a new function next to rt6_ifdown that
> > only gets called if interface gets shutdown but not unregistered (from
> > addrconf_ifdown).
> >
>
> rt6_ifdown has alreay put this device related routes to the garbage list.
>
> > fib6_clean_all then iterates over the whole routing table with a new predicate
> > function which checks in the same way like fib6_ifdown, if it is a matching route
> > (the interfaces match up) and if so, toggles a new "DEAD" flag in rt6i_flags.
> >
> > When bringing up the interface I distinguish between up and register and just
> > clear this death flag from the routes on bringing it up.
> >
> > fib lookup code then does not honour those routes.
> >
> > I had no time to test this thoroughly at the weekend and still have some code
> > paths were I am unsure. Do you see any problems with this so far? We could
> > then delete the special cases on loopback interface init.
>
> So you add a special case in the general network interface down logic. I think this
> is more complex...
The problem is, that we only have a reference to ifp->rt, the loopback
RTF_LOCAL route. Currently we silently remove all other routes this interface
has. Sure, they come back soon with RAs and such, but this is not the way this
should work.
Greetings,
Hannes
^ permalink raw reply
* [PATCH net 1/2] be2net: Fix be_vlan_add/rem_vid() routines
From: Somnath Kotur @ 2014-01-08 9:21 UTC (permalink / raw)
To: netdev; +Cc: davem, Somnath Kotur, Kalesh AP
The current logic to put interface into VLAN Promiscous mode is not correct.
We should increment "adapter->vlans_added" before calling be_vid_config().
Also removed some unwanted log messages.
Signed-off-by: Kalesh AP <kalesh.purayil@emulex.com>
Signed-off-by: Somnath Kotur <somnath.kotur@emulex.com>
---
drivers/net/ethernet/emulex/benet/be_main.c | 21 ++++++++-------------
1 files changed, 8 insertions(+), 13 deletions(-)
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index bf40fda..2fada24 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -1096,8 +1096,6 @@ static int be_vid_config(struct be_adapter *adapter)
dev_info(&adapter->pdev->dev,
"Disabling VLAN Promiscuous mode.\n");
adapter->flags &= ~BE_FLAGS_VLAN_PROMISC;
- dev_info(&adapter->pdev->dev,
- "Re-Enabling HW VLAN filtering\n");
}
}
}
@@ -1105,12 +1103,12 @@ static int be_vid_config(struct be_adapter *adapter)
return status;
set_vlan_promisc:
- dev_warn(&adapter->pdev->dev, "Exhausted VLAN HW filters.\n");
+ if (adapter->flags & BE_FLAGS_VLAN_PROMISC)
+ return 0;
status = be_cmd_rx_filter(adapter, BE_FLAGS_VLAN_PROMISC, ON);
if (!status) {
dev_info(&adapter->pdev->dev, "Enable VLAN Promiscuous mode\n");
- dev_info(&adapter->pdev->dev, "Disabling HW VLAN filtering\n");
adapter->flags |= BE_FLAGS_VLAN_PROMISC;
} else
dev_err(&adapter->pdev->dev,
@@ -1123,19 +1121,18 @@ static int be_vlan_add_vid(struct net_device *netdev, __be16 proto, u16 vid)
struct be_adapter *adapter = netdev_priv(netdev);
int status = 0;
-
/* Packets with VID 0 are always received by Lancer by default */
if (lancer_chip(adapter) && vid == 0)
goto ret;
adapter->vlan_tag[vid] = 1;
- if (adapter->vlans_added <= (be_max_vlans(adapter) + 1))
- status = be_vid_config(adapter);
+ adapter->vlans_added++;
- if (!status)
- adapter->vlans_added++;
- else
+ status = be_vid_config(adapter);
+ if (status) {
+ adapter->vlans_added--;
adapter->vlan_tag[vid] = 0;
+ }
ret:
return status;
}
@@ -1150,9 +1147,7 @@ static int be_vlan_rem_vid(struct net_device *netdev, __be16 proto, u16 vid)
goto ret;
adapter->vlan_tag[vid] = 0;
- if (adapter->vlans_added <= be_max_vlans(adapter))
- status = be_vid_config(adapter);
-
+ status = be_vid_config(adapter);
if (!status)
adapter->vlans_added--;
else
--
1.6.0.2
^ permalink raw reply related
* [PATCH net 2/2] be2net: Need a delay before processing CQE after 2nd mbox register write
From: Somnath Kotur @ 2014-01-08 9:22 UTC (permalink / raw)
To: netdev; +Cc: davem, Somnath Kotur, Kalesh AP
Due to Host platform synchronization issues between the mbox RDY bit polled
status and the completion of the DMA for the CQE, it is preferable that the
Host always wait for the RDY bit to transition to 1 after the 2nd mbox register
write and always follow that with a short wait for the valid bit in the CQE,
before processing the CQE.
Signed-off-by: Kalesh AP <kalesh.purayil@emulex.com>
Signed-off-by: Somnath Kotur <somnath.kotur@emulex.com>
---
drivers/net/ethernet/emulex/benet/be_cmds.c | 3 +++
1 files changed, 3 insertions(+), 0 deletions(-)
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 94c35c8..78560f2 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -502,6 +502,9 @@ static int be_mbox_notify_wait(struct be_adapter *adapter)
if (status != 0)
return status;
+ /* Need a delay before processing CQE after 2nd mbox register write */
+ udelay(1);
+
/* A cq entry has been made now */
if (be_mcc_compl_is_new(compl)) {
status = be_mcc_compl_process(adapter, &mbox->compl);
--
1.6.0.2
^ permalink raw reply related
* Re: [PATCH net 1/2] bonding: ensure that the TSO being set on bond master
From: Ding Tianhong @ 2014-01-08 9:25 UTC (permalink / raw)
To: Veaceslav Falico; +Cc: Jay Vosburgh, Eric Dumazet, David S. Miller, Netdev
In-Reply-To: <20140108083303.GA28509@redhat.com>
On 2014/1/8 16:33, Veaceslav Falico wrote:
> On Wed, Jan 08, 2014 at 03:28:24PM +0800, Ding Tianhong wrote:
>> The commit b0ce3508(bonding: allow TSO being set on bonding master)
>> has make the TSO being set for bond dev, but in some situation, if
>> the slave did not have the NETIF_F_SG features, the bond master will
>> miss the TSO features in netdev_fix_features because the TSO is
>> depended on SG. So I have to add SG and TSO features on bond master
>> together.
>
> Do you know why TSO depends on SG? And what will happen if bonding supports
> SG, but one of its slaves doesn't?
Yes, I miss it, something terrible will happen, thanks.
I think if the slave's hw_features support the SG and TSO, but not set, the bond
maybe could set them and then performance will be better, otherwise, the bond should
not do anything for it.
Regards
Ding
>
>>
>> The netdev_add_tso_features() was only used for bonding, so I think no
>> need to export it to netdevice.h.
>>
>> Cc: Eric Dumazet <edumazet@google.com>
>> Signed-off-by: Ding Tianhong <dingtianhong@huawei.com>
>> ---
>> drivers/net/bonding/bond_main.c | 16 +++++++++++++++-
>> 1 file changed, 15 insertions(+), 1 deletion(-)
>>
>> diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
>> index e06c445..8ce67ed 100644
>> --- a/drivers/net/bonding/bond_main.c
>> +++ b/drivers/net/bonding/bond_main.c
>> @@ -1045,6 +1045,20 @@ static void bond_netpoll_cleanup(struct net_device *bond_dev)
>>
>> /*---------------------------------- IOCTL ----------------------------------*/
>>
>> +/* Allow TSO being used on stacked device:
>> + * Performing the GSO segmentation before last device
>> + * is a performance improvement.
>> + * The TSO is depended on SG, so add SG and TSO together,
>> + * otherwise the netdev_fix_features() may clean the TSO.
>> + */
>> +static netdev_features_t bond_add_tso_features(netdev_features_t features,
>> + netdev_features_t mask)
>> +{
>> + return netdev_increment_features(features,
>> + NETIF_F_ALL_TSO | NETIF_F_SG,
>> + mask);
>> +}
>> +
>> static netdev_features_t bond_fix_features(struct net_device *dev,
>> netdev_features_t features)
>> {
>> @@ -1068,7 +1082,7 @@ static netdev_features_t bond_fix_features(struct net_device *dev,
>> slave->dev->features,
>> mask);
>> }
>> - features = netdev_add_tso_features(features, mask);
>> + features = bond_add_tso_features(features, mask);
>>
>> return features;
>> }
>> --
>> 1.8.0
>>
>>
>>
>
> .
>
^ permalink raw reply
* RE: [PATCH net 2/2] be2net: Need a delay before processing CQE after 2nd mbox register write
From: David Laight @ 2014-01-08 9:32 UTC (permalink / raw)
To: 'Somnath Kotur', netdev@vger.kernel.org
Cc: davem@davemloft.net, Kalesh AP
In-Reply-To: <4b4fd4cb-9d23-4900-a20c-f2c2bef70849@CMEXHTCAS2.ad.emulex.com>
> From: Somnath Kotur
> Due to Host platform synchronization issues between the mbox RDY bit polled
> status and the completion of the DMA for the CQE, it is preferable that the
> Host always wait for the RDY bit to transition to 1 after the 2nd mbox register
> write and always follow that with a short wait for the valid bit in the CQE,
> before processing the CQE.
While I don't doubt that a delay(1) fixes the problem it doesn't
seem an ideal solution.
I've not looked at what the code is doing (or how often it does it)
but either delay(1) is far, far longer than is necessary or it might
not be long enough and some kind of retry loop is required.
It might even be that the driver is just missing a memory barrier.
David
> Signed-off-by: Kalesh AP <kalesh.purayil@emulex.com>
> Signed-off-by: Somnath Kotur <somnath.kotur@emulex.com>
> ---
> drivers/net/ethernet/emulex/benet/be_cmds.c | 3 +++
> 1 files changed, 3 insertions(+), 0 deletions(-)
>
> diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
> index 94c35c8..78560f2 100644
> --- a/drivers/net/ethernet/emulex/benet/be_cmds.c
> +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
> @@ -502,6 +502,9 @@ static int be_mbox_notify_wait(struct be_adapter *adapter)
> if (status != 0)
> return status;
>
> + /* Need a delay before processing CQE after 2nd mbox register write */
> + udelay(1);
> +
> /* A cq entry has been made now */
> if (be_mcc_compl_is_new(compl)) {
> status = be_mcc_compl_process(adapter, &mbox->compl);
> --
> 1.6.0.2
^ permalink raw reply
* Re: [PATCH 2/2] utils: add test for nfq_get_uid and nfq_get_gid
From: Valentina Giusti @ 2014-01-08 9:36 UTC (permalink / raw)
To: Pablo Neira Ayuso; +Cc: netfilter-devel, netdev, fw, daniel.wagner
In-Reply-To: <20140107234319.GB17986@localhost>
On 01/08/2014 12:43 AM, Pablo Neira Ayuso wrote:
> Applied, but mangled the error message to avoid confusing users in
> case they use an old kernel.
>
Thanks Pablo!
BR,
- Val
^ permalink raw reply
* [PATCH net-next] ipv6: move IPV6_TCLASS_SHIFT into ipv6.h
From: roy.qing.li @ 2014-01-08 9:37 UTC (permalink / raw)
To: netdev
From: Li RongQing <roy.qing.li@gmail.com>
Two places defined IPV6_TCLASS_SHIFT, so we should move it into ipv6.h,
and use this macro as possible.
Signed-off-by: Li RongQing <roy.qing.li@gmail.com>
---
include/net/ipv6.h | 1 +
net/ipv6/fib6_rules.c | 4 +++-
net/ipv6/ip6_gre.c | 2 --
net/ipv6/ip6_tunnel.c | 2 --
net/ipv6/ipv6_sockglue.c | 4 +++-
5 files changed, 7 insertions(+), 6 deletions(-)
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 12079c6..d819f7a 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -239,6 +239,7 @@ struct ip6_flowlabel {
#define IPV6_FLOWINFO_MASK cpu_to_be32(0x0FFFFFFF)
#define IPV6_FLOWLABEL_MASK cpu_to_be32(0x000FFFFF)
#define IPV6_TCLASS_MASK (IPV6_FLOWINFO_MASK & ~IPV6_FLOWLABEL_MASK)
+#define IPV6_TCLASS_SHIFT 20
struct ipv6_fl_socklist {
struct ipv6_fl_socklist __rcu *next;
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index 3fd0a57..d50c5ca 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -150,6 +150,8 @@ static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags)
{
struct fib6_rule *r = (struct fib6_rule *) rule;
struct flowi6 *fl6 = &fl->u.ip6;
+ u8 tclass = (ntohl(fl6->flowlabel) & IPV6_TCLASS_MASK) >>
+ IPV6_TCLASS_SHIFT;
if (r->dst.plen &&
!ipv6_prefix_equal(&fl6->daddr, &r->dst.addr, r->dst.plen))
@@ -169,7 +171,7 @@ static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags)
return 0;
}
- if (r->tclass && r->tclass != ((ntohl(fl6->flowlabel) >> 20) & 0xff))
+ if (r->tclass && r->tclass != tclass)
return 0;
return 1;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index e7a440d..f3ffb43 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -61,8 +61,6 @@ static bool log_ecn_error = true;
module_param(log_ecn_error, bool, 0644);
MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");
-#define IPV6_TCLASS_SHIFT 20
-
#define HASH_SIZE_SHIFT 5
#define HASH_SIZE (1 << HASH_SIZE_SHIFT)
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 1e5e240..5db8d31 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -69,8 +69,6 @@ MODULE_ALIAS_NETDEV("ip6tnl0");
#define IP6_TNL_TRACE(x...) do {;} while(0)
#endif
-#define IPV6_TCLASS_SHIFT 20
-
#define HASH_SIZE_SHIFT 5
#define HASH_SIZE (1 << HASH_SIZE_SHIFT)
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index af0ecb9..1c9aa35 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -1019,7 +1019,9 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
put_cmsg(&msg, SOL_IPV6, IPV6_HOPLIMIT, sizeof(hlim), &hlim);
}
if (np->rxopt.bits.rxtclass) {
- int tclass = ntohl(np->rcv_flowinfo & IPV6_TCLASS_MASK) >> 20;
+ int tclass = ntohl(np->rcv_flowinfo &
+ IPV6_TCLASS_MASK) >>
+ IPV6_TCLASS_SHIFT;
put_cmsg(&msg, SOL_IPV6, IPV6_TCLASS, sizeof(tclass), &tclass);
}
if (np->rxopt.bits.rxoinfo) {
--
1.7.10.4
^ permalink raw reply related
* Re: [PATCH -next] net/mlx4_en: fix error return code in mlx4_en_get_qp()
From: Or Gerlitz @ 2014-01-08 9:40 UTC (permalink / raw)
To: weiyj.lk; +Cc: David Miller, amirv, yongjun_wei, netdev
In-Reply-To: <20140107.154328.116165277036485786.davem@davemloft.net>
On 07/01/2014 22:43, David Miller wrote:
> From: Wei Yongjun <weiyj.lk@gmail.com>
> Date: Tue, 7 Jan 2014 16:56:07 +0800
>
>> From: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
>>
>> Fix to return a negative error code from the error handling
>> case instead of 0.
>>
>> Fixes: 837052d0ccc5 ('net/mlx4_en: Add netdev support for TCP/IP offloads of vxlan tunneling')
>> Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
> Looks good, applied, thanks.
Indeed, thanks for spotting and fixing.
Or.
^ permalink raw reply
* Re: [PATCH net-next V2 3/3] net: Add GRO support for vxlan traffic
From: Or Gerlitz @ 2014-01-08 9:45 UTC (permalink / raw)
To: Tom Herbert
Cc: Eric Dumazet, Jerry Chu, Eric Dumazet, Herbert Xu,
Linux Netdev List, Yan Burman, Shlomo Pongratz
In-Reply-To: <CA+mtBx_Zctape7mAA=d-bvrFJbzn8f6tW5jBnPUcL5Cfhfai-g@mail.gmail.com>
On 07/01/2014 23:09, Tom Herbert wrote:
> On Tue, Jan 7, 2014 at 12:12 PM, Or Gerlitz <or.gerlitz@gmail.com> wrote:
>> On Tue, Jan 7, 2014 at 10:02 PM, Eric Dumazet <eric.dumazet@gmail.com> wrote:
>>> On Tue, 2014-01-07 at 21:43 +0200, Or Gerlitz wrote:
>>>> On Tue, Jan 7, 2014 at 8:08 PM, Tom Herbert <therbert@google.com> wrote:
>>>>> Why ^ instead of != ?
>>>> The XOR approach is very popular in the GRO stack, e.g see the IPv4 chain
>>>> of inet_gro_receive() && tcp_gro_receive(), I guess this might relates
>>>> to more efficient assembly code for ^ vs. != and/or the fast/elegant
>>>> transitive nature of that operator
>>> This trick is only needed/used when many compares are folded into a
>>> single conditional :
>>>
>>> if (a->f1 != b->f1 || a->f2 != b->f2)
>>>
>>> ->
>>>
>>> if (((a->f1 ^ b->f1) | (a->f2 ^ b->f2)) != 0)
>>>
>>> Please do not use XOR for a single compare.
>> OK, but just out of curiosity -- what's the reasoning? clarity or
>> efficiency or both?
> Both. Compiling a simple program and comparing alternatives: gcc
> produced the identical code for the single conditional (^ vs !=)
> using the cmp instruction. Testing the two conditional case like Eric
> provided; the second method (using ^) resulted in 4 more instructions,
> but only one branch as opposed to two in the first method (!=). Method
> #1 has the advantage of short circuiting when the first condition is
> true, so organizing the conditionals to maximize the probability of
> short circuit could be beneficial.
OK, I will follow that.
Or.
^ permalink raw reply
* RE: [PATCH net-next] xen-netback: stop vif thread spinning if frontend is unresponsive
From: Paul Durrant @ 2014-01-08 9:49 UTC (permalink / raw)
To: David Miller
Cc: netdev@vger.kernel.org, xen-devel@lists.xen.org, Wei Liu,
Ian Campbell, David Vrabel
In-Reply-To: <20140107.162956.1062166230525232035.davem@davemloft.net>
> -----Original Message-----
> From: netdev-owner@vger.kernel.org [mailto:netdev-
> owner@vger.kernel.org] On Behalf Of David Miller
> Sent: 07 January 2014 21:30
> To: Paul Durrant
> Cc: netdev@vger.kernel.org; xen-devel@lists.xen.org; Wei Liu; Ian Campbell;
> David Vrabel
> Subject: Re: [PATCH net-next] xen-netback: stop vif thread spinning if
> frontend is unresponsive
>
> From: Paul Durrant <paul.durrant@citrix.com>
> Date: Tue, 7 Jan 2014 16:25:29 +0000
>
> > @@ -477,6 +477,7 @@ static void xenvif_rx_action(struct xenvif *vif)
> > unsigned long offset;
> > struct skb_cb_overlay *sco;
> > int need_to_notify = 0;
> > + int ring_full = 0;
>
> Please use bool, false, and true.
>
> >
> > - if (!npo.copy_prod)
> > + if (!npo.copy_prod) {
> > + if (ring_full)
> > + vif->rx_queue_stopped = true;
> > goto done;
> > + }
> > +
> > + vif->rx_queue_stopped = false;
>
> And then you can code this as:
>
> vif->rx_queue_stopped = (!npo.copy_prod && ring_full);
> if (!npo.copy_prod)
> goto done;
Sure. I was just following style (of need_to_notify). If you prefer bool then I'll use that and also convert need_to_notify.
Paul
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* RE: [PATCH net-next] xen-netback: stop vif thread spinning if frontend is unresponsive
From: David Laight @ 2014-01-08 9:55 UTC (permalink / raw)
To: 'David Miller', paul.durrant@citrix.com
Cc: netdev@vger.kernel.org, xen-devel@lists.xen.org,
wei.liu2@citrix.com, ian.campbell@citrix.com,
david.vrabel@citrix.com
In-Reply-To: <20140107.162956.1062166230525232035.davem@davemloft.net>
> From: David Miller
...
> > - if (!npo.copy_prod)
> > + if (!npo.copy_prod) {
> > + if (ring_full)
> > + vif->rx_queue_stopped = true;
> > goto done;
> > + }
> > +
> > + vif->rx_queue_stopped = false;
>
> And then you can code this as:
>
> vif->rx_queue_stopped = (!npo.copy_prod && ring_full);
> if (!npo.copy_prod)
> goto done;
Which isn't quite the same...
1) It always writes vif->rx_queue_stopped, the old code could
leave it unchanged.
2) If 'npo' is global then the compiler can't assume that 'vif'
doesn't alias it so may have to re-read it following the
write to 'vif->rx_queue_stopped'.
David
^ permalink raw reply
* Re: [PATCH net-next v5] IPv6: add the option to use anycast addresses as source addresses in echo reply
From: François-Xavier Le Bail @ 2014-01-08 9:56 UTC (permalink / raw)
To: Bill Fink, netdev, David S. Miller, Alexey Kuznetsov,
James Morris, Hideaki Yoshifuji, Patrick McHardy,
Hannes Frederic Sowa
In-Reply-To: <20140107231737.GM30393@order.stressinduktion.org>
On Tue, 1/7/14, Hannes Frederic Sowa <hannes@stressinduktion.org> wrote:
> I forgot to mention, rest of kernel followes the old RFC
> advise to never
> use anycast addresses as source addresses.
> I guess this will be weakend with upcoming patches so in
> future this
> depends on socket settings and other tweaks. If that's the
> case default will
> be to also respond with anycast source if original
> destination was anycast.
The next patch will address the datagrams case.
BR
Francois-Xavier
^ permalink raw reply
* [PATCH -next] openvswitch: Use kmem_cache_free() instead of kfree()
From: Wei Yongjun @ 2014-01-08 10:13 UTC (permalink / raw)
To: jesse, pshelar, davem; +Cc: yongjun_wei, dev, netdev
From: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
memory allocated by kmem_cache_alloc() should be freed using
kmem_cache_free(), not kfree().
Fixes: e298e5057006 ('openvswitch: Per cpu flow stats.')
Signed-off-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
---
net/openvswitch/flow_table.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index b430d42..c58a0fe 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -104,7 +104,7 @@ struct sw_flow *ovs_flow_alloc(bool percpu_stats)
}
return flow;
err:
- kfree(flow);
+ kmem_cache_free(flow_cache, flow);
return ERR_PTR(-ENOMEM);
}
^ permalink raw reply related
* [PATCH 1/3] ss: handle seqpacket type of unix domain socket
From: Masatake YAMATO @ 2014-01-08 11:13 UTC (permalink / raw)
To: netdev; +Cc: yamato
ss didn't distignish seqpacket type from dgram type.
With this patch ss can distignish it.
$ misc/ss -x -a | grep seq
u_seq LISTEN 0 128 /run/udev/control 10966 * 0
u_seq ESTAB 0 0 * 115103 * 115104
u_seq ESTAB 0 0 * 115104 * 115103
Signed-off-by: Masatake YAMATO <yamato@redhat.com>
---
misc/ss.c | 31 ++++++++++++++++++++++++++++---
1 file changed, 28 insertions(+), 3 deletions(-)
diff --git a/misc/ss.c b/misc/ss.c
index e59ca5c..bac1f9e 100644
--- a/misc/ss.c
+++ b/misc/ss.c
@@ -71,6 +71,7 @@ enum
RAW_DB,
UNIX_DG_DB,
UNIX_ST_DB,
+ UNIX_SQ_DB,
PACKET_DG_DB,
PACKET_R_DB,
NETLINK_DB,
@@ -78,7 +79,7 @@ enum
};
#define PACKET_DBM ((1<<PACKET_DG_DB)|(1<<PACKET_R_DB))
-#define UNIX_DBM ((1<<UNIX_DG_DB)|(1<<UNIX_ST_DB))
+#define UNIX_DBM ((1<<UNIX_DG_DB)|(1<<UNIX_ST_DB)|(1<<UNIX_SQ_DB))
#define ALL_DB ((1<<MAX_DB)-1)
enum {
@@ -2114,6 +2115,25 @@ static void unix_list_free(struct unixstat *list)
}
}
+static const char *unix_netid_name(int type)
+{
+ const char *netid;
+
+ switch (type) {
+ case SOCK_STREAM:
+ netid = "u_str";
+ break;
+ case SOCK_SEQPACKET:
+ netid = "u_seq";
+ break;
+ case SOCK_DGRAM:
+ default:
+ netid = "u_dgr";
+ break;
+ }
+ return netid;
+}
+
static void unix_list_print(struct unixstat *list, struct filter *f)
{
struct unixstat *s;
@@ -2126,6 +2146,8 @@ static void unix_list_print(struct unixstat *list, struct filter *f)
continue;
if (s->type == SOCK_DGRAM && !(f->dbs&(1<<UNIX_DG_DB)))
continue;
+ if (s->type == SOCK_SEQPACKET && !(f->dbs&(1<<UNIX_SQ_DB)))
+ continue;
peer = "*";
if (s->peer) {
@@ -2156,7 +2178,7 @@ static void unix_list_print(struct unixstat *list, struct filter *f)
if (netid_width)
printf("%-*s ", netid_width,
- s->type == SOCK_STREAM ? "u_str" : "u_dgr");
+ unix_netid_name(s->type));
if (state_width)
printf("%-*s ", state_width, sstate_name[s->state]);
printf("%-6d %-6d ", s->rq, s->wq);
@@ -2185,7 +2207,7 @@ static int unix_show_sock(struct nlmsghdr *nlh, struct filter *f)
if (netid_width)
printf("%-*s ", netid_width,
- r->udiag_type == SOCK_STREAM ? "u_str" : "u_dgr");
+ unix_netid_name(r->udiag_type));
if (state_width)
printf("%-*s ", state_width, sstate_name[r->udiag_state]);
@@ -3253,6 +3275,9 @@ int main(int argc, char *argv[])
} else if (strcasecmp(p, "unix_dgram") == 0 ||
strcmp(p, "u_dgr") == 0) {
current_filter.dbs |= (1<<UNIX_DG_DB);
+ } else if (strcasecmp(p, "unix_seqpacket") == 0 ||
+ strcmp(p, "u_seq") == 0) {
+ current_filter.dbs |= (1<<UNIX_SQ_DB);
} else if (strcmp(p, "packet") == 0) {
current_filter.dbs |= PACKET_DBM;
} else if (strcmp(p, "packet_raw") == 0 ||
--
1.8.4.2
^ permalink raw reply related
* [PATCH 2/3] ss: enable query by type in unix domain related socket
From: Masatake YAMATO @ 2014-01-08 11:13 UTC (permalink / raw)
To: netdev; +Cc: yamato
In-Reply-To: <1389179628-22147-1-git-send-email-yamato@redhat.com>
This patch enables -A unix_stream, -A unix_dgram and
-A unix_seqpacket option even if ss gets socket information
via netlink.
Signed-off-by: Masatake YAMATO <yamato@redhat.com>
---
misc/ss.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/misc/ss.c b/misc/ss.c
index bac1f9e..cea3f2e 100644
--- a/misc/ss.c
+++ b/misc/ss.c
@@ -2205,6 +2205,13 @@ static int unix_show_sock(struct nlmsghdr *nlh, struct filter *f)
parse_rtattr(tb, UNIX_DIAG_MAX, (struct rtattr*)(r+1),
nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*r)));
+ if (r->udiag_type == SOCK_STREAM && !(f->dbs&(1<<UNIX_ST_DB)))
+ return 0;
+ if (r->udiag_type == SOCK_DGRAM && !(f->dbs&(1<<UNIX_DG_DB)))
+ return 0;
+ if (r->udiag_type == SOCK_SEQPACKET && !(f->dbs&(1<<UNIX_SQ_DB)))
+ return 0;
+
if (netid_width)
printf("%-*s ", netid_width,
unix_netid_name(r->udiag_type));
--
1.8.4.2
^ permalink raw reply related
* [PATCH 3/3] ss: add unix_seqpacket to the help message and the man page
From: Masatake YAMATO @ 2014-01-08 11:13 UTC (permalink / raw)
To: netdev; +Cc: yamato
In-Reply-To: <1389179628-22147-1-git-send-email-yamato@redhat.com>
Signed-off-by: Masatake YAMATO <yamato@redhat.com>
---
man/man8/ss.8 | 2 +-
misc/ss.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/man/man8/ss.8 b/man/man8/ss.8
index e55dd0c..807d9dc 100644
--- a/man/man8/ss.8
+++ b/man/man8/ss.8
@@ -87,7 +87,7 @@ Currently the following families are supported: unix, inet, inet6, link, netlink
.B \-A QUERY, \-\-query=QUERY, \-\-socket=QUERY
List of socket tables to dump, separated by commas. The following identifiers
are understood: all, inet, tcp, udp, raw, unix, packet, netlink, unix_dgram,
-unix_stream, packet_raw, packet_dgram.
+unix_stream, unix_seqpacket, packet_raw, packet_dgram.
.TP
.B \-D FILE, \-\-diag=FILE
Do not display anything, just dump raw information about TCP sockets to FILE after applying filters. If FILE is - stdout is used.
diff --git a/misc/ss.c b/misc/ss.c
index cea3f2e..675f7c5 100644
--- a/misc/ss.c
+++ b/misc/ss.c
@@ -3072,7 +3072,7 @@ static void _usage(FILE *dest)
" -f, --family=FAMILY display sockets of type FAMILY\n"
"\n"
" -A, --query=QUERY, --socket=QUERY\n"
-" QUERY := {all|inet|tcp|udp|raw|unix|packet|netlink}[,QUERY]\n"
+" QUERY := {all|inet|tcp|udp|raw|unix|unix_dgram|unix_stream|unix_seqpacket|packet|netlink}[,QUERY]\n"
"\n"
" -D, --diag=FILE Dump raw information about TCP sockets to FILE\n"
" -F, --filter=FILE read filter information from FILE\n"
--
1.8.4.2
^ permalink raw reply related
* Re: [PATCH 1/2] net/mlx4_core: clean up cq_res_start_move_to()
From: Or Gerlitz @ 2014-01-08 11:18 UTC (permalink / raw)
To: Paul Bolle, Jack Morgenstein, Rony Efraim, Hadar Hen Zion,
David S. Miller
Cc: netdev, linux-kernel
In-Reply-To: <1389099678.15032.19.camel@x41>
On 07/01/2014 15:01, Paul Bolle wrote:
> Building resource_tracker.o triggers a GCC warning:
> drivers/net/ethernet/mellanox/mlx4/resource_tracker.c: In function 'mlx4_HW2SW_CQ_wrapper':
> drivers/net/ethernet/mellanox/mlx4/resource_tracker.c:3019:16: warning: 'cq' may be used uninitialized in this function [-Wmaybe-uninitialized]
> atomic_dec(&cq->mtt->ref_count);
> ^
>
> This is a false positive. But a cleanup of cq_res_start_move_to() can
> help GCC here. The code currently uses a switch statement where a plain
> if/else would do, since only two of the switch's four cases can ever
> occur. Dropping that switch makes the warning go away.
>
> While we're at it, do some coding style cleanups (missing braces), and
> drop a test that always evaluates to true.
>
Hi Paul,
Our maintainer of that area of the code (SRIOV resource tracker) is busy
now, but we will definitely look on these two patches in the coming
days, thanks for posting them!
^ permalink raw reply
* Re: [PATCH net-next 1/2] cxgb4: Fix namespace collision issue.
From: Hariprasad S @ 2014-01-08 11:19 UTC (permalink / raw)
To: David Miller; +Cc: netdev, dm, leedom, nirranjan, kumaras, santosh
In-Reply-To: <20140107.154813.1483946457674959301.davem@davemloft.net>
On Tue, Jan 07, 2014 at 15:48:13 -0500, David Miller wrote:
> From: Hariprasad Shenai <hariprasad@chelsio.com>
> Date: Tue, 7 Jan 2014 16:58:07 +0530
>
> > Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com>
> ...
>
> > -int t4_init_tp_params(struct adapter *adap)
>
> There is no reason that an already exported function must be moved
> to solve a namespace issue.
>
> If you want to move this function for another reason, fine, but do
> it in a seperate change with a clear description of that reason in
> your commit message.
>
> I'm not applying this series.
I will drop this patch series. I will send an independent patch for FW version
check.
^ permalink raw reply
* [PATCH net-next] cxgb4: Changed FW check version to match FW binary version
From: Hariprasad Shenai @ 2014-01-08 11:24 UTC (permalink / raw)
To: netdev; +Cc: davem, dm, leedom, nirranjan, kumaras, santosh, hariprasad
Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com>
---
drivers/net/ethernet/chelsio/cxgb4/cxgb4.h | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index b97e35c..16782b2 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -50,13 +50,13 @@
#include "cxgb4_uld.h"
#define T4FW_VERSION_MAJOR 0x01
-#define T4FW_VERSION_MINOR 0x06
-#define T4FW_VERSION_MICRO 0x18
+#define T4FW_VERSION_MINOR 0x09
+#define T4FW_VERSION_MICRO 0x17
#define T4FW_VERSION_BUILD 0x00
#define T5FW_VERSION_MAJOR 0x01
-#define T5FW_VERSION_MINOR 0x08
-#define T5FW_VERSION_MICRO 0x1C
+#define T5FW_VERSION_MINOR 0x09
+#define T5FW_VERSION_MICRO 0x17
#define T5FW_VERSION_BUILD 0x00
#define CH_WARN(adap, fmt, ...) dev_warn(adap->pdev_dev, fmt, ## __VA_ARGS__)
--
1.8.0
^ permalink raw reply related
* Re: [PATCH net-next V2 1/3] net: Add GRO support for UDP encapsulating protocols
From: Or Gerlitz @ 2014-01-08 12:15 UTC (permalink / raw)
To: Eric Dumazet; +Cc: Or Gerlitz, netdev
In-Reply-To: <1389182291.26646.79.camel@edumazet-glaptop2.roam.corp.google.com>
On 08/01/2014 13:58, Eric Dumazet wrote:
> On Wed, 2014-01-08 at 10:04 +0200, Or Gerlitz wrote:
>> On 07/01/2014 23:38, Eric Dumazet wrote:
>>> On Tue, 2014-01-07 at 22:37 +0200, Or Gerlitz wrote:
>>>
>>>> So here's the thing, per my understanding we want to GRO only received
>>>> **encapsulated** packets whose checksum status is != CHECKSUM_NONE
>>>> which means the NIC has some support for doing RX checksum of
>>>> encapsulated packets. Per the current convension, in that case the NIC
>>>> RX code has to set skb->encapsulation see 6a674e9c75b17 "net: Add
>>>> support for hardware-offloaded encapsulation" this convension is
>>>> implemented in the current drivers that have HW offloads for
>>>> encapsulated packets (bnx2x, i40e and mlx4)
>>> I do not think its true.
>>>
>>> Some drivers set CHECKSUM_COMPLETE even for regular UDP frames...
>>>
>>> git grep -n CHECKSUM_COMPLETE -- drivers/net
>>>
>>>
>>>
>> Eric, the point I was trying to make is that as long as the driver set a
>> value which is different from CHECKSUM_NONE
>> for an skb who carry encapsulated packet, we want skb->encapsulation to
>> be set, per the architecture dictated by the above commit.
> Then this point is obviously wrong. Your interpretation is wrong, I am very sorry.
> skb->encapsulation _might_ be set, only if the NIC is performing header
> analysis. CHECKSUM_COMPLETE support doesn't require header analysis.
>
>
>
>
fair enough && thanks for shedding more light on this - so in that
respect, the gro handler for udp encapsulated packets will not flush skb
who is either marked with CHECKSUM_COMPLETE or has skb->encapsulation set.
Or.
^ permalink raw reply
* Re: Possible to add netfilter hooks to IFB driver?
From: Jamal Hadi Salim @ 2014-01-08 12:28 UTC (permalink / raw)
To: Alban Crequy, Andrew Collins
Cc: Stephen Hemminger, Brad Johnson, netdev@vger.kernel.org
In-Reply-To: <20140107111807.38624f74@rainbow.cbg.collabora.co.uk>
On 01/07/14 06:18, Alban Crequy wrote:
> On Mon, 6 Jan 2014 15:51:37 -0700
> Andrew Collins <bsderandrew@gmail.com> wrote:
>
>> On Mon, Jan 6, 2014 at 2:51 PM, Stephen Hemminger
>> <stephen@networkplumber.org> wrote:
>>>
>>> The risk is creating the same races that made IMQ unacceptable.
>>> --
>>
>> I believe openwrt nowadays uses a TC action which runs the packet
>> through prerouting then pulls in the mark off the ct entry into the
>> skb, so ingress+IFB can take action on it.
>
> Thanks for the info. I guess the implementation is this one:
>
> https://dev.openwrt.org/browser/trunk/target/linux/generic/patches-3.12/621-sched_act_connmark.patch
> https://dev.openwrt.org/browser/trunk/package/network/utils/iproute2/patches/210-add-act_connmark.patch
> https://dev.openwrt.org/browser/trunk/package/network/config/qos-scripts/files/usr/lib/qos/generate.sh#L343
>
>> Perhaps a cleaned up version of this would be suitable for upstream?
>
> I don't know but this seems a useful feature to me.
>
I like that approach - discussion was had here on netdev
about a year ago refer to:
http://marc.info/?t=135591832200007&r=1&w=2
since it is a long thread, jump to here:
http://marc.info/?l=linux-netdev&m=135634890120552&w=2
I believe Pablo brought it up at the last netfilter meeting
and there was no disagreement to get it going.
I dont know if kids still use these expressions - but send him
some virtual beer and he may return the love.
cheers,
jamal
^ permalink raw reply
* [PATCH net-next v2] xen-netback: stop vif thread spinning if frontend is unresponsive
From: Paul Durrant @ 2014-01-08 12:41 UTC (permalink / raw)
To: netdev, xen-devel; +Cc: Paul Durrant, Wei Liu, Ian Campbell, David Vrabel
The recent patch to improve guest receive side flow control (ca2f09f2) had a
slight flaw in the wait condition for the vif thread in that any remaining
skbs in the guest receive side netback internal queue would prevent the
thread from sleeping. An unresponsive frontend can lead to a permanently
non-empty internal queue and thus the thread will spin. In this case the
thread should really sleep until the frontend becomes responsive again.
This patch adds an extra flag to the vif which is set if the shared ring
is full and cleared when skbs are drained into the shared ring. Thus,
if the thread runs, finds the shared ring full and can make no progress the
flag remains set. If the flag remains set then the thread will sleep,
regardless of a non-empty queue, until the next event from the frontend.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Cc: Wei Liu <wei.liu2@citrix.com>
Cc: Ian Campbell <ian.campbell@citrix.com>
Cc: David Vrabel <david.vrabel@citrix.com>
---
v2:
- Use bool for ring_full
- Convert need_to_notify to bool for consistency
drivers/net/xen-netback/common.h | 1 +
drivers/net/xen-netback/netback.c | 14 +++++++++-----
2 files changed, 10 insertions(+), 5 deletions(-)
diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index c955fc3..4c76bcb 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -143,6 +143,7 @@ struct xenvif {
char rx_irq_name[IFNAMSIZ+4]; /* DEVNAME-rx */
struct xen_netif_rx_back_ring rx;
struct sk_buff_head rx_queue;
+ bool rx_queue_stopped;
/* Set when the RX interrupt is triggered by the frontend.
* The worker thread may need to wake the queue.
*/
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 4f81ac0..2738563 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -476,7 +476,8 @@ static void xenvif_rx_action(struct xenvif *vif)
int ret;
unsigned long offset;
struct skb_cb_overlay *sco;
- int need_to_notify = 0;
+ bool need_to_notify = false;
+ bool ring_full = false;
struct netrx_pending_operations npo = {
.copy = vif->grant_copy_op,
@@ -508,7 +509,8 @@ static void xenvif_rx_action(struct xenvif *vif)
/* If the skb may not fit then bail out now */
if (!xenvif_rx_ring_slots_available(vif, max_slots_needed)) {
skb_queue_head(&vif->rx_queue, skb);
- need_to_notify = 1;
+ need_to_notify = true;
+ ring_full = true;
break;
}
@@ -521,6 +523,8 @@ static void xenvif_rx_action(struct xenvif *vif)
BUG_ON(npo.meta_prod > ARRAY_SIZE(vif->meta));
+ vif->rx_queue_stopped = !npo.copy_prod && ring_full;
+
if (!npo.copy_prod)
goto done;
@@ -592,8 +596,7 @@ static void xenvif_rx_action(struct xenvif *vif)
RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&vif->rx, ret);
- if (ret)
- need_to_notify = 1;
+ need_to_notify |= !!ret;
npo.meta_cons += sco->meta_slots_used;
dev_kfree_skb(skb);
@@ -1724,7 +1727,8 @@ static struct xen_netif_rx_response *make_rx_response(struct xenvif *vif,
static inline int rx_work_todo(struct xenvif *vif)
{
- return !skb_queue_empty(&vif->rx_queue) || vif->rx_event;
+ return (!skb_queue_empty(&vif->rx_queue) && !vif->rx_queue_stopped) ||
+ vif->rx_event;
}
static inline int tx_work_todo(struct xenvif *vif)
--
1.7.10.4
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox