* Re: [PATCH net] sock: fix sendmmsg for partial sendmsg
From: Maciej Żenczykowski @ 2016-11-05 3:10 UTC (permalink / raw)
To: Soheil Hassas Yeganeh
Cc: David Miller, Linux NetDev, Eric Dumazet, Willem de Bruijn,
Neal Cardwell, Soheil Hassas Yeganeh
In-Reply-To: <1478288209-30893-1-git-send-email-soheil.kdev@gmail.com>
Acked-by: Maciej Żenczykowski <maze@google.com>
^ permalink raw reply
* [net PATCH] fib_trie: Correct /proc/net/route off by one error
From: Alexander Duyck @ 2016-11-04 19:11 UTC (permalink / raw)
To: netdev, alexander.duyck; +Cc: Andy Whitcroft, Jason Baron, davem
The display of /proc/net/route has had a couple issues due to the fact that
when I originally rewrote most of fib_trie I made it so that the iterator
was tracking the next value to use instead of the current.
In addition it had an off by 1 error where I was tracking the first piece
of data as position 0, even though in reality that belonged to the
SEQ_START_TOKEN.
This patch updates the code so the iterator tracks the last reported
position and key instead of the next expected position and key. In
addition it shifts things so that all of the leaves start at 1 instead of
trying to report leaves starting with offset 0 as being valid. With these
two issues addressed this should resolve any off by one errors that were
present in the display of /proc/net/route.
Fixes: 25b97c016b26 ("ipv4: off-by-one in continuation handling in /proc/net/route")
Cc: Andy Whitcroft <apw@canonical.com>
Reported-by: Jason Baron <jbaron@akamai.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
---
net/ipv4/fib_trie.c | 21 +++++++++------------
1 file changed, 9 insertions(+), 12 deletions(-)
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 31cef36..4cff74d 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -2413,22 +2413,19 @@ static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter,
struct key_vector *l, **tp = &iter->tnode;
t_key key;
- /* use cache location of next-to-find key */
+ /* use cached location of previously found key */
if (iter->pos > 0 && pos >= iter->pos) {
- pos -= iter->pos;
key = iter->key;
} else {
- iter->pos = 0;
+ iter->pos = 1;
key = 0;
}
- while ((l = leaf_walk_rcu(tp, key)) != NULL) {
+ pos -= iter->pos;
+
+ while ((l = leaf_walk_rcu(tp, key)) && (pos-- > 0)) {
key = l->key + 1;
iter->pos++;
-
- if (--pos <= 0)
- break;
-
l = NULL;
/* handle unlikely case of a key wrap */
@@ -2437,7 +2434,7 @@ static struct key_vector *fib_route_get_idx(struct fib_route_iter *iter,
}
if (l)
- iter->key = key; /* remember it */
+ iter->key = l->key; /* remember it */
else
iter->pos = 0; /* forget it */
@@ -2465,7 +2462,7 @@ static void *fib_route_seq_start(struct seq_file *seq, loff_t *pos)
return fib_route_get_idx(iter, *pos);
iter->pos = 0;
- iter->key = 0;
+ iter->key = KEY_MAX;
return SEQ_START_TOKEN;
}
@@ -2474,7 +2471,7 @@ static void *fib_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct fib_route_iter *iter = seq->private;
struct key_vector *l = NULL;
- t_key key = iter->key;
+ t_key key = iter->key + 1;
++*pos;
@@ -2483,7 +2480,7 @@ static void *fib_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
l = leaf_walk_rcu(&iter->tnode, key);
if (l) {
- iter->key = l->key + 1;
+ iter->key = l->key;
iter->pos++;
} else {
iter->pos = 0;
^ permalink raw reply related
* I Hope You Get My Message This Time
From: Dr Friedrich Mayrhofer @ 2016-11-05 0:19 UTC (permalink / raw)
--
This is the second time i am sending you this mail.I, Friedrich Mayrhofer
Donate $ 1,000,000.00 to You, Email Me personally for more details.
Regards.
Friedrich Mayrhofer
^ permalink raw reply
* Re: [PATCH net-next 5/7] vxlan: simplify RTF_LOCAL handling.
From: kbuild test robot @ 2016-11-05 0:01 UTC (permalink / raw)
To: Pravin B Shelar; +Cc: kbuild-all, netdev, Pravin B Shelar
In-Reply-To: <1478292716-54649-6-git-send-email-pshelar@ovn.org>
[-- Attachment #1: Type: text/plain, Size: 1602 bytes --]
Hi Pravin,
[auto build test ERROR on net-next/master]
url: https://github.com/0day-ci/linux/commits/Pravin-B-Shelar/vxlan-General-improvements/20161105-060958
config: i386-randconfig-x077-201644 (attached as .config)
compiler: gcc-6 (Debian 6.2.0-3) 6.2.0 20160901
reproduce:
# save the attached .config to linux build tree
make ARCH=i386
All errors (new ones prefixed by >>):
drivers/net/vxlan.c: In function 'vxlan_group_used':
drivers/net/vxlan.c:947:21: warning: unused variable 'sock6' [-Wunused-variable]
struct vxlan_sock *sock6 = NULL;
^~~~~
drivers/net/vxlan.c: In function 'check_route_rtf_local':
>> drivers/net/vxlan.c:1954:17: error: 'RTF_LOCAL' undeclared (first use in this function)
if (rt_flags & RTF_LOCAL &&
^~~~~~~~~
drivers/net/vxlan.c:1954:17: note: each undeclared identifier is reported only once for each function it appears in
vim +/RTF_LOCAL +1954 drivers/net/vxlan.c
1948 static int check_route_rtf_local(struct sk_buff *skb, struct net_device *dev,
1949 struct vxlan_dev *vxlan, union vxlan_addr *daddr,
1950 __be32 dst_port, __be32 vni, struct dst_entry *dst,
1951 u32 rt_flags)
1952 {
1953 /* Bypass encapsulation if the destination is local */
> 1954 if (rt_flags & RTF_LOCAL &&
1955 !(rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))) {
1956 struct vxlan_dev *dst_vxlan;
1957
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 29764 bytes --]
^ permalink raw reply
* [PATCH iproute2 3/7] l2tp: fix integers with too few significant bits
From: Asbjørn Sloth Tønnesen @ 2016-11-04 23:11 UTC (permalink / raw)
To: Stephen Hemminger; +Cc: James Chapman, netdev
In-Reply-To: <20161104231111.14677-1-asbjorn@asbjorn.st>
udp6_csum{,_tx,_rx}, tunnel and session are the only ones
currently used.
recv_seq, send_seq, lns_mode and data_seq are partially
implemented in a useless way.
Signed-off-by: Asbjørn Sloth Tønnesen <asbjorn@asbjorn.st>
---
ip/ipl2tp.c | 18 +++++++++---------
1 file changed, 9 insertions(+), 9 deletions(-)
diff --git a/ip/ipl2tp.c b/ip/ipl2tp.c
index d3338ac..2e0e9c7 100644
--- a/ip/ipl2tp.c
+++ b/ip/ipl2tp.c
@@ -56,15 +56,15 @@ struct l2tp_parm {
uint16_t pw_type;
uint16_t mtu;
- int udp6_csum_tx:1;
- int udp6_csum_rx:1;
- int udp_csum:1;
- int recv_seq:1;
- int send_seq:1;
- int lns_mode:1;
- int data_seq:2;
- int tunnel:1;
- int session:1;
+ unsigned int udp6_csum_tx:1;
+ unsigned int udp6_csum_rx:1;
+ unsigned int udp_csum:1;
+ unsigned int recv_seq:1;
+ unsigned int send_seq:1;
+ unsigned int lns_mode:1;
+ unsigned int data_seq:2;
+ unsigned int tunnel:1;
+ unsigned int session:1;
int reorder_timeout;
const char *ifname;
uint8_t l2spec_type;
--
2.10.1
^ permalink raw reply related
* [PATCH iproute2 2/7] man: ip-l2tp.8: remove non-existent tunnel parameter name
From: Asbjørn Sloth Tønnesen @ 2016-11-04 23:11 UTC (permalink / raw)
To: Stephen Hemminger; +Cc: James Chapman, netdev
In-Reply-To: <20161104231111.14677-1-asbjorn@asbjorn.st>
The name parameter is only valid for sessions, not tunnels.
Signed-off-by: Asbjørn Sloth Tønnesen <asbjorn@asbjorn.st>
---
man/man8/ip-l2tp.8 | 3 ---
1 file changed, 3 deletions(-)
diff --git a/man/man8/ip-l2tp.8 b/man/man8/ip-l2tp.8
index 4a3bb20..991d097 100644
--- a/man/man8/ip-l2tp.8
+++ b/man/man8/ip-l2tp.8
@@ -154,9 +154,6 @@ tunnels and sessions to be established and provides for detecting and
acting upon network failures.
.SS ip l2tp add tunnel - add a new tunnel
.TP
-.BI name " NAME "
-sets the session network interface name. Default is l2tpethN.
-.TP
.BI tunnel_id " ID"
set the tunnel id, which is a 32-bit integer value. Uniquely
identifies the tunnel. The value used must match the peer_tunnel_id
--
2.10.1
^ permalink raw reply related
* [PATCH iproute2 4/7] l2tp: fix L2TP_ATTR_{RECV,SEND}_SEQ handling
From: Asbjørn Sloth Tønnesen @ 2016-11-04 23:11 UTC (permalink / raw)
To: Stephen Hemminger; +Cc: James Chapman, netdev
In-Reply-To: <20161104231111.14677-1-asbjorn@asbjorn.st>
L2TP_ATTR_RECV_SEQ and L2TP_ATTR_SEND_SEQ are declared as NLA_U8
attributes in the kernel, so let's threat them accordingly.
Signed-off-by: Asbjørn Sloth Tønnesen <asbjorn@asbjorn.st>
---
ip/ipl2tp.c | 10 ++++++----
1 file changed, 6 insertions(+), 4 deletions(-)
diff --git a/ip/ipl2tp.c b/ip/ipl2tp.c
index 2e0e9c7..af89e2f 100644
--- a/ip/ipl2tp.c
+++ b/ip/ipl2tp.c
@@ -160,8 +160,8 @@ static int create_session(struct l2tp_parm *p)
addattr8(&req.n, 1024, L2TP_ATTR_L2SPEC_LEN, p->l2spec_len);
if (p->mtu) addattr16(&req.n, 1024, L2TP_ATTR_MTU, p->mtu);
- if (p->recv_seq) addattr(&req.n, 1024, L2TP_ATTR_RECV_SEQ);
- if (p->send_seq) addattr(&req.n, 1024, L2TP_ATTR_SEND_SEQ);
+ if (p->recv_seq) addattr8(&req.n, 1024, L2TP_ATTR_RECV_SEQ, 1);
+ if (p->send_seq) addattr8(&req.n, 1024, L2TP_ATTR_SEND_SEQ, 1);
if (p->lns_mode) addattr(&req.n, 1024, L2TP_ATTR_LNS_MODE);
if (p->data_seq) addattr8(&req.n, 1024, L2TP_ATTR_DATA_SEQ, p->data_seq);
if (p->reorder_timeout) addattr64(&req.n, 1024, L2TP_ATTR_RECV_TIMEOUT,
@@ -304,8 +304,10 @@ static int get_response(struct nlmsghdr *n, void *arg)
memcpy(p->peer_cookie, RTA_DATA(attrs[L2TP_ATTR_PEER_COOKIE]),
p->peer_cookie_len = RTA_PAYLOAD(attrs[L2TP_ATTR_PEER_COOKIE]));
- p->recv_seq = !!attrs[L2TP_ATTR_RECV_SEQ];
- p->send_seq = !!attrs[L2TP_ATTR_SEND_SEQ];
+ if (attrs[L2TP_ATTR_RECV_SEQ])
+ p->recv_seq = rta_getattr_u8(attrs[L2TP_ATTR_RECV_SEQ]);
+ if (attrs[L2TP_ATTR_SEND_SEQ])
+ p->send_seq = rta_getattr_u8(attrs[L2TP_ATTR_SEND_SEQ]);
if (attrs[L2TP_ATTR_RECV_TIMEOUT])
p->reorder_timeout = rta_getattr_u64(attrs[L2TP_ATTR_RECV_TIMEOUT]);
--
2.10.1
^ permalink raw reply related
* [PATCH iproute2 5/7] l2tp: support sequence numbering
From: Asbjørn Sloth Tønnesen @ 2016-11-04 23:11 UTC (permalink / raw)
To: Stephen Hemminger; +Cc: James Chapman, netdev
In-Reply-To: <20161104231111.14677-1-asbjorn@asbjorn.st>
Signed-off-by: Asbjørn Sloth Tønnesen <asbjorn@asbjorn.st>
---
ip/ipl2tp.c | 23 +++++++++++++++++++++++
man/man8/ip-l2tp.8 | 15 +++++++++++++++
2 files changed, 38 insertions(+)
diff --git a/ip/ipl2tp.c b/ip/ipl2tp.c
index af89e2f..6d00d09 100644
--- a/ip/ipl2tp.c
+++ b/ip/ipl2tp.c
@@ -246,6 +246,12 @@ static void print_session(struct l2tp_data *data)
printf(" reorder timeout: %u\n", p->reorder_timeout);
else
printf("\n");
+ if (p->send_seq || p->recv_seq) {
+ printf(" sequence numbering:");
+ if (p->send_seq) printf(" send");
+ if (p->recv_seq) printf(" recv");
+ printf("\n");
+ }
}
static int get_response(struct nlmsghdr *n, void *arg)
@@ -483,6 +489,7 @@ static void usage(void)
fprintf(stderr, " session_id ID peer_session_id ID\n");
fprintf(stderr, " [ cookie HEXSTR ] [ peer_cookie HEXSTR ]\n");
fprintf(stderr, " [ offset OFFSET ] [ peer_offset OFFSET ]\n");
+ fprintf(stderr, " [ seq { none | send | recv | both } ]\n");
fprintf(stderr, " [ l2spec_type L2SPEC ]\n");
fprintf(stderr, " ip l2tp del tunnel tunnel_id ID\n");
fprintf(stderr, " ip l2tp del session tunnel_id ID session_id ID\n");
@@ -653,6 +660,22 @@ static int parse_args(int argc, char **argv, int cmd, struct l2tp_parm *p)
fprintf(stderr, "Unknown layer2specific header type \"%s\"\n", *argv);
exit(-1);
}
+ } else if (strcmp(*argv, "seq") == 0) {
+ NEXT_ARG();
+ if (strcasecmp(*argv, "both") == 0) {
+ p->recv_seq = 1;
+ p->send_seq = 1;
+ } else if (strcasecmp(*argv, "recv") == 0) {
+ p->recv_seq = 1;
+ } else if (strcasecmp(*argv, "send") == 0) {
+ p->send_seq = 1;
+ } else if (strcasecmp(*argv, "none") == 0) {
+ p->recv_seq = 0;
+ p->send_seq = 0;
+ } else {
+ fprintf(stderr, "Unknown seq value \"%s\"\n", *argv);
+ exit(-1);
+ }
} else if (strcmp(*argv, "tunnel") == 0) {
p->tunnel = 1;
} else if (strcmp(*argv, "session") == 0) {
diff --git a/man/man8/ip-l2tp.8 b/man/man8/ip-l2tp.8
index 991d097..d4e7270 100644
--- a/man/man8/ip-l2tp.8
+++ b/man/man8/ip-l2tp.8
@@ -51,6 +51,8 @@ ip-l2tp - L2TPv3 static unmanaged tunnel configuration
.br
.RB "[ " l2spec_type " { " none " | " default " } ]"
.br
+.RB "[ " seq " { " none " | " send " | " recv " | " both " } ]"
+.br
.RB "[ " offset
.IR OFFSET
.RB " ] [ " peer_offset
@@ -238,6 +240,19 @@ set the layer2specific header type of the session.
Valid values are:
.BR none ", " default "."
.TP
+.BI seq " SEQ"
+controls sequence numbering to prevent or detect out of order packets.
+.B send
+puts a sequence number in the default layer2specific header of each
+outgoing packet.
+.B recv
+reorder packets if they are received out of order.
+Default is
+.BR none "."
+.br
+Valid values are:
+.BR none ", " send ", " recv ", " both "."
+.TP
.BI offset " OFFSET"
sets the byte offset from the L2TP header where user data starts in
transmitted L2TP data packets. This is hardly ever used. If set, the
--
2.10.1
^ permalink raw reply related
* [PATCH iproute2 1/7] man: ip-l2tp.8: fix l2spec_type documentation
From: Asbjørn Sloth Tønnesen @ 2016-11-04 23:11 UTC (permalink / raw)
To: Stephen Hemminger; +Cc: James Chapman, netdev
Signed-off-by: Asbjørn Sloth Tønnesen <asbjorn@asbjorn.st>
---
man/man8/ip-l2tp.8 | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/man/man8/ip-l2tp.8 b/man/man8/ip-l2tp.8
index 5b7041f..4a3bb20 100644
--- a/man/man8/ip-l2tp.8
+++ b/man/man8/ip-l2tp.8
@@ -239,7 +239,7 @@ find in received L2TP packets. Default is to use no cookie.
set the layer2specific header type of the session.
.br
Valid values are:
-.BR none ", " udp "."
+.BR none ", " default "."
.TP
.BI offset " OFFSET"
sets the byte offset from the L2TP header where user data starts in
--
2.10.1
^ permalink raw reply related
* [PATCH iproute2 6/7] l2tp: read IPv6 UDP checksum attributes from kernel
From: Asbjørn Sloth Tønnesen @ 2016-11-04 23:11 UTC (permalink / raw)
To: Stephen Hemminger; +Cc: James Chapman, netdev
In-Reply-To: <20161104231111.14677-1-asbjorn@asbjorn.st>
In case of an older kernel that doesn't set L2TP_ATTR_UDP_ZERO_CSUM6_{R,T}X
the old hard-coded value is being preserved, since the attribute flag will be
missing.
Signed-off-by: Asbjørn Sloth Tønnesen <asbjorn@asbjorn.st>
---
ip/ipl2tp.c | 9 +++------
1 file changed, 3 insertions(+), 6 deletions(-)
diff --git a/ip/ipl2tp.c b/ip/ipl2tp.c
index 6d00d09..8f3268d 100644
--- a/ip/ipl2tp.c
+++ b/ip/ipl2tp.c
@@ -296,12 +296,9 @@ static int get_response(struct nlmsghdr *n, void *arg)
p->l2spec_len = rta_getattr_u8(attrs[L2TP_ATTR_L2SPEC_LEN]);
p->udp_csum = !!attrs[L2TP_ATTR_UDP_CSUM];
- /*
- * Not fetching from L2TP_ATTR_UDP_ZERO_CSUM6_{T,R}X because the
- * kernel doesn't send it so just leave it as default value.
- */
- p->udp6_csum_tx = 1;
- p->udp6_csum_rx = 1;
+ p->udp6_csum_tx = !attrs[L2TP_ATTR_UDP_ZERO_CSUM6_TX];
+ p->udp6_csum_rx = !attrs[L2TP_ATTR_UDP_ZERO_CSUM6_RX];
+
if (attrs[L2TP_ATTR_COOKIE])
memcpy(p->cookie, RTA_DATA(attrs[L2TP_ATTR_COOKIE]),
p->cookie_len = RTA_PAYLOAD(attrs[L2TP_ATTR_COOKIE]));
--
2.10.1
^ permalink raw reply related
* [PATCH iproute2 7/7] l2tp: show tunnel: expose UDP checksum state
From: Asbjørn Sloth Tønnesen @ 2016-11-04 23:11 UTC (permalink / raw)
To: Stephen Hemminger; +Cc: James Chapman, netdev
In-Reply-To: <20161104231111.14677-1-asbjorn@asbjorn.st>
Signed-off-by: Asbjørn Sloth Tønnesen <asbjorn@asbjorn.st>
---
ip/ipl2tp.c | 17 ++++++++++++++++-
1 file changed, 16 insertions(+), 1 deletion(-)
diff --git a/ip/ipl2tp.c b/ip/ipl2tp.c
index 8f3268d..27dc184 100644
--- a/ip/ipl2tp.c
+++ b/ip/ipl2tp.c
@@ -218,9 +218,24 @@ static void print_tunnel(const struct l2tp_data *data)
printf(" Peer tunnel %u\n",
p->peer_tunnel_id);
- if (p->encap == L2TP_ENCAPTYPE_UDP)
+ if (p->encap == L2TP_ENCAPTYPE_UDP) {
printf(" UDP source / dest ports: %hu/%hu\n",
p->local_udp_port, p->peer_udp_port);
+
+ switch (p->local_ip.family) {
+ case AF_INET:
+ printf(" UDP checksum: %s\n",
+ p->udp_csum ? "enabled" : "disabled");
+ break;
+ case AF_INET6:
+ printf(" UDP checksum: %s%s%s%s\n",
+ p->udp6_csum_tx && p->udp6_csum_rx ? "enabled" : "",
+ p->udp6_csum_tx && !p->udp6_csum_rx ? "tx" : "",
+ !p->udp6_csum_tx && p->udp6_csum_rx ? "rx" : "",
+ !p->udp6_csum_tx && !p->udp6_csum_rx ? "disabled" : "");
+ break;
+ }
+ }
}
static void print_session(struct l2tp_data *data)
--
2.10.1
^ permalink raw reply related
* Re: [PATCH net-next RFC WIP] Patch for XDP support for virtio_net
From: John Fastabend @ 2016-11-04 23:05 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: Shrijeet Mukherjee, Jesper Dangaard Brouer, Thomas Graf,
Alexei Starovoitov, Jakub Kicinski, David Miller, alexander.duyck,
shrijeet, tom, netdev, Roopa Prabhu, Nikolay Aleksandrov, aconole
In-Reply-To: <20161104022927-mutt-send-email-mst@kernel.org>
On 16-11-03 05:34 PM, Michael S. Tsirkin wrote:
> On Thu, Nov 03, 2016 at 04:29:22PM -0700, John Fastabend wrote:
>> [...]
>>
>>>>> - when XDP is attached disable all LRO using VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET
>>>>> (not used by driver so far, designed to allow dynamic LRO control with
>>>>> ethtool)
>>>>
>>>> I see there is a UAPI bit for this but I guess we also need to add
>>>> support to vhost as well? Seems otherwise we may just drop a bunch
>>>> of packets on the floor out of handle_rx() when recvmsg returns larger
>>>> than a page size. Or did I read this wrong...
>>>
>>> It's already supported host side. However you might
>>> get some packets that were in flight when you attached.
>>>
>>
>> Really I must have missed it I don't see any *GUEST_FEATURES* flag in
>> ./drivers/vhost/?
>
> It's all done by QEMU catching these commands and calling
> ioctls on the tun/macvtap/packet socket.
>
Well at least for the tap vhost backend in linux that I found here,
./qemu/net/tap-linux.c
there is no LRO feature flag but that is OK I can get it working next
week looks fairly straight forward.
[...]
>> And if I try to merge the last email I sent out here. In mergeable and
>> big_packets modes if LRO is off and MTU < PAGE_SIZE it seems we should
>> always get physically contiguous data on a single page correct?
>
> Unfortunately not in the mergeable buffer case according to spec, even though
> linux hosts will do that, so it's fine to optimize for that
> but need to somehow work in other cases e.g. by doing a data copy.
>
ah OK this makes sense I was looking at vhost implementation in Linux.
>
>> It
>> may be at some offset in a page however. But the offset should not
>> matter to XDP. If I read this right we wouldn't need to add a new
>> XDP mode and could just use the existing merge or big modes. This would
>> seem cleaner to me than adding a new mode and requiring a qemu option.
>>
>> Thanks for all the pointers by the way its very helpful.
>
> So for mergeable we spend cycles trying to make buffers as small
> as possible and I have a patch to avoid copies for that too,
> I'll post it next week hopefully.
>
Good to know. I'll get the XDP stuff wrapped up next week or see
if Srijeet wants to do it.
Thanks,
John
^ permalink raw reply
* [PATCH net-next 4/5] net: l2tp: cleanup: remove redundant condition
From: Asbjoern Sloth Toennesen @ 2016-11-04 22:48 UTC (permalink / raw)
To: David S . Miller; +Cc: James Chapman, netdev, linux-kernel
In-Reply-To: <20161104224838.7925-1-asbjorn@asbjorn.st>
These assignments follow this pattern:
unsigned int foo:1;
struct nlattr *nla = info->attrs[bar];
if (nla)
foo = nla_get_flag(nla); /* expands to: foo = !!nla */
This could be simplified to: if (nla) foo = 1;
but lets just remove the condition and use the macro,
foo = nla_get_flag(nla);
Signed-off-by: Asbjoern Sloth Toennesen <asbjorn@asbjorn.st>
---
net/l2tp/l2tp_netlink.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 1b3fcde..abf6bf1 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -220,14 +220,14 @@ static int l2tp_nl_cmd_tunnel_create(struct sk_buff *skb, struct genl_info *info
cfg.local_udp_port = nla_get_u16(info->attrs[L2TP_ATTR_UDP_SPORT]);
if (info->attrs[L2TP_ATTR_UDP_DPORT])
cfg.peer_udp_port = nla_get_u16(info->attrs[L2TP_ATTR_UDP_DPORT]);
- if (info->attrs[L2TP_ATTR_UDP_CSUM])
- cfg.use_udp_checksums = nla_get_flag(info->attrs[L2TP_ATTR_UDP_CSUM]);
+ cfg.use_udp_checksums = nla_get_flag(
+ info->attrs[L2TP_ATTR_UDP_CSUM]);
#if IS_ENABLED(CONFIG_IPV6)
- if (info->attrs[L2TP_ATTR_UDP_ZERO_CSUM6_TX])
- cfg.udp6_zero_tx_checksums = nla_get_flag(info->attrs[L2TP_ATTR_UDP_ZERO_CSUM6_TX]);
- if (info->attrs[L2TP_ATTR_UDP_ZERO_CSUM6_RX])
- cfg.udp6_zero_rx_checksums = nla_get_flag(info->attrs[L2TP_ATTR_UDP_ZERO_CSUM6_RX]);
+ cfg.udp6_zero_tx_checksums = nla_get_flag(
+ info->attrs[L2TP_ATTR_UDP_ZERO_CSUM6_TX]);
+ cfg.udp6_zero_rx_checksums = nla_get_flag(
+ info->attrs[L2TP_ATTR_UDP_ZERO_CSUM6_RX]);
#endif
}
--
2.10.1
^ permalink raw reply related
* [PATCH net-next 5/5] net: l2tp: fix negative assignment to unsigned int
From: Asbjoern Sloth Toennesen @ 2016-11-04 22:48 UTC (permalink / raw)
To: David S . Miller; +Cc: James Chapman, netdev, linux-kernel
In-Reply-To: <20161104224838.7925-1-asbjorn@asbjorn.st>
recv_seq, send_seq and lns_mode mode are all defined as
unsigned int foo:1;
Signed-off-by: Asbjoern Sloth Toennesen <asbjorn@asbjorn.st>
---
net/l2tp/l2tp_core.c | 2 +-
net/l2tp/l2tp_ppp.c | 6 +++---
2 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index a2ed3bd..85948c6 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -715,7 +715,7 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
l2tp_info(session, L2TP_MSG_SEQ,
"%s: requested to enable seq numbers by LNS\n",
session->name);
- session->send_seq = -1;
+ session->send_seq = 1;
l2tp_session_set_header_len(session, tunnel->version);
}
} else {
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 41d47bf..2ddfec1 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1272,7 +1272,7 @@ static int pppol2tp_session_setsockopt(struct sock *sk,
err = -EINVAL;
break;
}
- session->recv_seq = val ? -1 : 0;
+ session->recv_seq = !!val;
l2tp_info(session, PPPOL2TP_MSG_CONTROL,
"%s: set recv_seq=%d\n",
session->name, session->recv_seq);
@@ -1283,7 +1283,7 @@ static int pppol2tp_session_setsockopt(struct sock *sk,
err = -EINVAL;
break;
}
- session->send_seq = val ? -1 : 0;
+ session->send_seq = !!val;
{
struct sock *ssk = ps->sock;
struct pppox_sock *po = pppox_sk(ssk);
@@ -1301,7 +1301,7 @@ static int pppol2tp_session_setsockopt(struct sock *sk,
err = -EINVAL;
break;
}
- session->lns_mode = val ? -1 : 0;
+ session->lns_mode = !!val;
l2tp_info(session, PPPOL2TP_MSG_CONTROL,
"%s: set lns_mode=%d\n",
session->name, session->lns_mode);
--
2.10.1
^ permalink raw reply related
* [PATCH net-next 3/5] net: l2tp: netlink: l2tp_nl_tunnel_send: set UDP6 checksum flags
From: Asbjoern Sloth Toennesen @ 2016-11-04 22:48 UTC (permalink / raw)
To: David S . Miller; +Cc: James Chapman, netdev, linux-kernel
In-Reply-To: <20161104224838.7925-1-asbjorn@asbjorn.st>
This patch causes the proper attribute flags to be set,
in the case that IPv6 UDP checksums are disabled, so that
userspace ie. `ip l2tp show tunnel` knows about it.
Signed-off-by: Asbjoern Sloth Toennesen <asbjorn@asbjorn.st>
---
net/l2tp/l2tp_netlink.c | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index e45c5409..1b3fcde 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -385,6 +385,16 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla
nla_put_flag(skb, L2TP_ATTR_UDP_CSUM))
goto nla_put_failure;
break;
+#if IS_ENABLED(CONFIG_IPV6)
+ case AF_INET6:
+ if (udp_get_no_check6_tx(sk) &&
+ nla_put_flag(skb, L2TP_ATTR_UDP_ZERO_CSUM6_TX))
+ goto nla_put_failure;
+ if (udp_get_no_check6_rx(sk) &&
+ nla_put_flag(skb, L2TP_ATTR_UDP_ZERO_CSUM6_RX))
+ goto nla_put_failure;
+ break;
+#endif
}
if (nla_put_u16(skb, L2TP_ATTR_UDP_SPORT, ntohs(inet->inet_sport)) ||
nla_put_u16(skb, L2TP_ATTR_UDP_DPORT, ntohs(inet->inet_dport)))
--
2.10.1
^ permalink raw reply related
* [PATCH net-next 2/5] net: l2tp: fix L2TP_ATTR_UDP_ZERO_CSUM6_{RX,TX} attribute types
From: Asbjoern Sloth Toennesen @ 2016-11-04 22:48 UTC (permalink / raw)
To: David S . Miller; +Cc: James Chapman, netdev, linux-kernel, Miao Wang
In-Reply-To: <20161104224838.7925-1-asbjorn@asbjorn.st>
The attributes L2TP_ATTR_UDP_ZERO_CSUM6_RX and
L2TP_ATTR_UDP_ZERO_CSUM6_TX are used as flags,
but is defined as a u8 in a comment.
This patch redocuments them as flags, and adds
them to the nla_policy, so they gets validated.
The only publicly user, iproute2, already treat
these attributes as flags.
CC: Miao Wang <shankerwangmiao@gmail.com>
Signed-off-by: Asbjoern Sloth Toennesen <asbjorn@asbjorn.st>
---
include/uapi/linux/l2tp.h | 4 ++--
net/l2tp/l2tp_netlink.c | 2 ++
2 files changed, 4 insertions(+), 2 deletions(-)
diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h
index 73e3a23..345e49f 100644
--- a/include/uapi/linux/l2tp.h
+++ b/include/uapi/linux/l2tp.h
@@ -124,8 +124,8 @@ enum {
L2TP_ATTR_STATS, /* nested */
L2TP_ATTR_IP6_SADDR, /* struct in6_addr */
L2TP_ATTR_IP6_DADDR, /* struct in6_addr */
- L2TP_ATTR_UDP_ZERO_CSUM6_TX, /* u8 */
- L2TP_ATTR_UDP_ZERO_CSUM6_RX, /* u8 */
+ L2TP_ATTR_UDP_ZERO_CSUM6_TX, /* flag */
+ L2TP_ATTR_UDP_ZERO_CSUM6_RX, /* flag */
L2TP_ATTR_PAD,
__L2TP_ATTR_MAX,
};
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 1fe05da..e45c5409 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -880,6 +880,8 @@ static const struct nla_policy l2tp_nl_policy[L2TP_ATTR_MAX + 1] = {
[L2TP_ATTR_SESSION_ID] = { .type = NLA_U32, },
[L2TP_ATTR_PEER_SESSION_ID] = { .type = NLA_U32, },
[L2TP_ATTR_UDP_CSUM] = { .type = NLA_FLAG, },
+ [L2TP_ATTR_UDP_ZERO_CSUM6_TX] = { .type = NLA_FLAG, },
+ [L2TP_ATTR_UDP_ZERO_CSUM6_RX] = { .type = NLA_FLAG, },
[L2TP_ATTR_VLAN_ID] = { .type = NLA_U16, },
[L2TP_ATTR_DEBUG] = { .type = NLA_U32, },
[L2TP_ATTR_RECV_SEQ] = { .type = NLA_U8, },
--
2.10.1
^ permalink raw reply related
* [PATCH net-next 1/5] net: l2tp: fix L2TP_ATTR_UDP_CSUM attribute type
From: Asbjoern Sloth Toennesen @ 2016-11-04 22:48 UTC (permalink / raw)
To: David S . Miller; +Cc: James Chapman, netdev, linux-kernel, Miao Wang
L2TP_ATTR_UDP_CSUM is a flag, and gets read with
nla_get_flag, but it is defined as NLA_U8 in
the nla_policy.
It appears that this is only publicly used in
iproute2, where it's broken, because it's used as
a NLA_FLAG, and fails validation as a NLA_U8.
The only place it's used as a NLA_U8 is in
l2tp_nl_tunnel_send(), but iproute2 again reads that
as a flag, it's therefore always set. Fortunately
it is never used for anything, just read.
CC: Miao Wang <shankerwangmiao@gmail.com>
Signed-off-by: Asbjoern Sloth Toennesen <asbjorn@asbjorn.st>
---
include/uapi/linux/l2tp.h | 2 +-
net/l2tp/l2tp_netlink.c | 12 +++++++++---
2 files changed, 10 insertions(+), 4 deletions(-)
diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h
index 4bd27d0..73e3a23 100644
--- a/include/uapi/linux/l2tp.h
+++ b/include/uapi/linux/l2tp.h
@@ -104,7 +104,7 @@ enum {
L2TP_ATTR_PEER_CONN_ID, /* u32 */
L2TP_ATTR_SESSION_ID, /* u32 */
L2TP_ATTR_PEER_SESSION_ID, /* u32 */
- L2TP_ATTR_UDP_CSUM, /* u8 */
+ L2TP_ATTR_UDP_CSUM, /* flag */
L2TP_ATTR_VLAN_ID, /* u16 */
L2TP_ATTR_COOKIE, /* 0, 4 or 8 bytes */
L2TP_ATTR_PEER_COOKIE, /* 0, 4 or 8 bytes */
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 59aa2d2..1fe05da 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -379,9 +379,15 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla
switch (tunnel->encap) {
case L2TP_ENCAPTYPE_UDP:
+ switch (sk->sk_family) {
+ case AF_INET:
+ if ((!sk->sk_no_check_tx) &&
+ nla_put_flag(skb, L2TP_ATTR_UDP_CSUM))
+ goto nla_put_failure;
+ break;
+ }
if (nla_put_u16(skb, L2TP_ATTR_UDP_SPORT, ntohs(inet->inet_sport)) ||
- nla_put_u16(skb, L2TP_ATTR_UDP_DPORT, ntohs(inet->inet_dport)) ||
- nla_put_u8(skb, L2TP_ATTR_UDP_CSUM, !sk->sk_no_check_tx))
+ nla_put_u16(skb, L2TP_ATTR_UDP_DPORT, ntohs(inet->inet_dport)))
goto nla_put_failure;
/* NOBREAK */
case L2TP_ENCAPTYPE_IP:
@@ -873,7 +879,7 @@ static const struct nla_policy l2tp_nl_policy[L2TP_ATTR_MAX + 1] = {
[L2TP_ATTR_PEER_CONN_ID] = { .type = NLA_U32, },
[L2TP_ATTR_SESSION_ID] = { .type = NLA_U32, },
[L2TP_ATTR_PEER_SESSION_ID] = { .type = NLA_U32, },
- [L2TP_ATTR_UDP_CSUM] = { .type = NLA_U8, },
+ [L2TP_ATTR_UDP_CSUM] = { .type = NLA_FLAG, },
[L2TP_ATTR_VLAN_ID] = { .type = NLA_U16, },
[L2TP_ATTR_DEBUG] = { .type = NLA_U32, },
[L2TP_ATTR_RECV_SEQ] = { .type = NLA_U8, },
--
2.10.1
^ permalink raw reply related
* [PATCH] net-ipv6: on device mtu change do not add mtu to mtu-less routes
From: Maciej Żenczykowski @ 2016-11-04 21:51 UTC (permalink / raw)
To: Maciej Żenczykowski, David S . Miller; +Cc: netdev, Eric Dumazet
From: Maciej Żenczykowski <maze@google.com>
Routes can specify an mtu explicitly or inherit the mtu from
the underlying device - this inheritance is implemented in
dst->ops->mtu handlers ip6_mtu() and ip6_blackhole_mtu().
Currently changing the mtu of a device adds mtu explicitly
to routes using that device.
ie.
# ip link set dev lo mtu 65536
# ip -6 route add local 2000::1 dev lo
# ip -6 route get 2000::1
local 2000::1 dev lo table local src ... metric 1024 pref medium
# ip link set dev lo mtu 65535
# ip -6 route get 2000::1
local 2000::1 dev lo table local src ... metric 1024 mtu 65535 pref medium
# ip link set dev lo mtu 65536
# ip -6 route get 2000::1
local 2000::1 dev lo table local src ... metric 1024 mtu 65536 pref medium
# ip -6 route del local 2000::1
After this patch the route entry no longer changes unless it already has an mtu.
There is no need: this inheritance is already done in ip6_mtu()
# ip link set dev lo mtu 65536
# ip -6 route add local 2000::1 dev lo
# ip -6 route add local 2000::2 dev lo mtu 2000
# ip -6 route get 2000::1; ip -6 route get 2000::2
local 2000::1 dev lo table local src ... metric 1024 pref medium
local 2000::2 dev lo table local src ... metric 1024 mtu 2000 pref medium
# ip link set dev lo mtu 65535
# ip -6 route get 2000::1; ip -6 route get 2000::2
local 2000::1 dev lo table local src ... metric 1024 pref medium
local 2000::2 dev lo table local src ... metric 1024 mtu 2000 pref medium
# ip link set dev lo mtu 1501
# ip -6 route get 2000::1; ip -6 route get 2000::2
local 2000::1 dev lo table local src ... metric 1024 pref medium
local 2000::2 dev lo table local src ... metric 1024 mtu 1501 pref medium
# ip link set dev lo mtu 65536
# ip -6 route get 2000::1; ip -6 route get 2000::2
local 2000::1 dev lo table local src ... metric 1024 pref medium
local 2000::2 dev lo table local src ... metric 1024 mtu 65536 pref medium
# ip -6 route del local 2000::1
# ip -6 route del local 2000::2
This is desirable because changing device mtu and then resetting it
to the previous value shouldn't change the user visible routing table.
Signed-off-by: Maciej Żenczykowski <maze@google.com>
CC: Eric Dumazet <edumazet@google.com>
---
net/ipv6/route.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 947ed1ded026..fa90d14302f7 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2758,6 +2758,7 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg)
PMTU discouvery.
*/
if (rt->dst.dev == arg->dev &&
+ dst_metric_raw(&rt->dst, RTAX_MTU) &&
!dst_metric_locked(&rt->dst, RTAX_MTU)) {
if (rt->rt6i_flags & RTF_CACHE) {
/* For RTF_CACHE with rt6i_pmtu == 0
--
2.8.0.rc3.226.g39d4020
^ permalink raw reply related
* Re: [PATCH net] ipv4: update comment to document GSO fragmentation cases.
From: Shmulik Ladkani @ 2016-11-04 21:02 UTC (permalink / raw)
To: Lance Richardson; +Cc: netdev
In-Reply-To: <1478276558-10974-1-git-send-email-lrichard@redhat.com>
Hi,
On Fri, 4 Nov 2016 12:22:38 -0400 Lance Richardson <lrichard@redhat.com> wrote:
> This is a follow-up to commit eb96202f1e34 ("ipv4: allow local
> fragmentation in ip_finish_output_gso()"), updating the comment
> documenting cases in which fragmentation is needed for egress
> GSO packets.
>
> Suggested-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
> Signed-off-by: Lance Richardson <lrichard@redhat.com>
Thanks Lance.
Reviewed-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
^ permalink raw reply
* [PATCH net-next 6/7] vxlan: simplify vxlan xmit
From: Pravin B Shelar @ 2016-11-04 20:51 UTC (permalink / raw)
To: netdev; +Cc: Pravin B Shelar
In-Reply-To: <1478292716-54649-1-git-send-email-pshelar@ovn.org>
Existing vxlan xmit function handles two distinct cases.
1. vxlan net device
2. vxlan lwt device.
By seperating initilization these two cases the egress path
looks better.
Signed-off-by: Pravin B Shelar <pshelar@ovn.org>
---
drivers/net/vxlan.c | 79 ++++++++++++++++++++++++-----------------------------
1 file changed, 35 insertions(+), 44 deletions(-)
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index d496763..7bba92b 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1978,8 +1978,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
struct dst_cache *dst_cache;
struct ip_tunnel_info *info;
struct vxlan_dev *vxlan = netdev_priv(dev);
- struct sock *sk;
- const struct iphdr *old_iph;
+ const struct iphdr *old_iph = ip_hdr(skb);
union vxlan_addr *dst;
union vxlan_addr remote_ip, local_ip;
union vxlan_addr *src;
@@ -1987,7 +1986,6 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
struct vxlan_metadata *md = &_md;
__be16 src_port = 0, dst_port;
__be32 vni, label;
- __be16 df = 0;
__u8 tos, ttl;
int err;
u32 flags = vxlan->flags;
@@ -1997,11 +1995,34 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
info = skb_tunnel_info(skb);
if (rdst) {
+ dst = &rdst->remote_ip;
+ if (vxlan_addr_any(dst)) {
+ if (did_rsc) {
+ /* short-circuited back to local bridge */
+ vxlan_encap_bypass(skb, vxlan, vxlan);
+ return;
+ }
+ goto drop;
+ }
+
dst_port = rdst->remote_port ? rdst->remote_port : vxlan->cfg.dst_port;
vni = rdst->remote_vni;
- dst = &rdst->remote_ip;
src = &vxlan->cfg.saddr;
dst_cache = &rdst->dst_cache;
+ md->gbp = skb->mark;
+ ttl = vxlan->cfg.ttl;
+ if (!ttl && vxlan_addr_multicast(dst))
+ ttl = 1;
+
+ tos = vxlan->cfg.tos;
+ if (tos == 1)
+ tos = ip_tunnel_get_dsfield(old_iph, skb);
+
+ if (dst->sa.sa_family == AF_INET)
+ udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM_TX);
+ else
+ udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM6_TX);
+ label = vxlan->cfg.label;
} else {
if (!info) {
WARN_ONCE(1, "%s: Missing encapsulation instructions\n",
@@ -2021,32 +2042,6 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
dst = &remote_ip;
src = &local_ip;
dst_cache = &info->dst_cache;
- }
-
- if (vxlan_addr_any(dst)) {
- if (did_rsc) {
- /* short-circuited back to local bridge */
- vxlan_encap_bypass(skb, vxlan, vxlan);
- return;
- }
- goto drop;
- }
-
- old_iph = ip_hdr(skb);
-
- ttl = vxlan->cfg.ttl;
- if (!ttl && vxlan_addr_multicast(dst))
- ttl = 1;
-
- tos = vxlan->cfg.tos;
- if (tos == 1)
- tos = ip_tunnel_get_dsfield(old_iph, skb);
-
- label = vxlan->cfg.label;
- src_port = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min,
- vxlan->cfg.port_max, true);
-
- if (info) {
ttl = info->key.ttl;
tos = info->key.tos;
label = info->key.label;
@@ -2054,15 +2049,15 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
if (info->options_len)
md = ip_tunnel_info_opts(info);
- } else {
- md->gbp = skb->mark;
}
+ src_port = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min,
+ vxlan->cfg.port_max, true);
+
if (dst->sa.sa_family == AF_INET) {
struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock);
struct rtable *rt;
-
- sk = sock4->sock->sk;
+ __be16 df = 0;
rt = vxlan_get_route(vxlan, dev, sock4, skb,
rdst ? rdst->remote_ifindex : 0, tos,
@@ -2078,18 +2073,17 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
rt->rt_flags);
if (err)
return;
- udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM_TX);
} else if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT) {
df = htons(IP_DF);
}
- tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
- ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
err = vxlan_build_skb(skb, &rt->dst, sizeof(struct iphdr),
vni, md, flags, udp_sum);
if (err < 0)
goto tx_error;
- udp_tunnel_xmit_skb(rt, sk, skb, src->sin.sin_addr.s_addr,
+ tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
+ ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
+ udp_tunnel_xmit_skb(rt, sock4->sock->sk, skb, src->sin.sin_addr.s_addr,
dst->sin.sin_addr.s_addr, tos, ttl, df,
src_port, dst_port, xnet, !udp_sum);
#if IS_ENABLED(CONFIG_IPV6)
@@ -2097,8 +2091,6 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock);
struct dst_entry *ndst;
- sk = sock6->sock->sk;
-
ndst = vxlan6_get_route(vxlan, dev, sock6, skb,
rdst ? rdst->remote_ifindex : 0, tos,
label, &dst->sin6.sin6_addr,
@@ -2115,18 +2107,17 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
rt6i_flags);
if (err)
return;
- udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM6_TX);
}
- tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
- ttl = ttl ? : ip6_dst_hoplimit(ndst);
skb_scrub_packet(skb, xnet);
err = vxlan_build_skb(skb, ndst, sizeof(struct ipv6hdr),
vni, md, flags, udp_sum);
if (err < 0)
goto tx_error;
- udp_tunnel6_xmit_skb(ndst, sk, skb, dev,
+ tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
+ ttl = ttl ? : ip6_dst_hoplimit(ndst);
+ udp_tunnel6_xmit_skb(ndst, sock6->sock->sk, skb, dev,
&src->sin6.sin6_addr,
&dst->sin6.sin6_addr, tos, ttl,
label, src_port, dst_port, !udp_sum);
--
1.9.1
^ permalink raw reply related
* [PATCH net-next 7/7] vxlan: remove unsed vxlan_dev_dst_port()
From: Pravin B Shelar @ 2016-11-04 20:51 UTC (permalink / raw)
To: netdev; +Cc: Pravin B Shelar
In-Reply-To: <1478292716-54649-1-git-send-email-pshelar@ovn.org>
Signed-off-by: Pravin B Shelar <pshelar@ovn.org>
---
include/net/vxlan.h | 10 ----------
1 file changed, 10 deletions(-)
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 308adc4..49a5920 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -281,16 +281,6 @@ struct vxlan_dev {
struct net_device *vxlan_dev_create(struct net *net, const char *name,
u8 name_assign_type, struct vxlan_config *conf);
-static inline __be16 vxlan_dev_dst_port(struct vxlan_dev *vxlan,
- unsigned short family)
-{
-#if IS_ENABLED(CONFIG_IPV6)
- if (family == AF_INET6)
- return inet_sk(vxlan->vn6_sock->sock->sk)->inet_sport;
-#endif
- return inet_sk(vxlan->vn4_sock->sock->sk)->inet_sport;
-}
-
static inline netdev_features_t vxlan_features_check(struct sk_buff *skb,
netdev_features_t features)
{
--
1.9.1
^ permalink raw reply related
* [PATCH net-next 5/7] vxlan: simplify RTF_LOCAL handling.
From: Pravin B Shelar @ 2016-11-04 20:51 UTC (permalink / raw)
To: netdev; +Cc: Pravin B Shelar
In-Reply-To: <1478292716-54649-1-git-send-email-pshelar@ovn.org>
Avoid code duplicate code for handling RTF_LOCAL routes.
Signed-off-by: Pravin B Shelar <pshelar@ovn.org>
---
drivers/net/vxlan.c | 78 +++++++++++++++++++++++++++++------------------------
1 file changed, 43 insertions(+), 35 deletions(-)
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 15319f1..d496763 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1945,6 +1945,33 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan,
}
}
+static int check_route_rtf_local(struct sk_buff *skb, struct net_device *dev,
+ struct vxlan_dev *vxlan, union vxlan_addr *daddr,
+ __be32 dst_port, __be32 vni, struct dst_entry *dst,
+ u32 rt_flags)
+{
+ /* Bypass encapsulation if the destination is local */
+ if (rt_flags & RTF_LOCAL &&
+ !(rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))) {
+ struct vxlan_dev *dst_vxlan;
+
+ dst_release(dst);
+ dst_vxlan = vxlan_find_vni(vxlan->net, vni,
+ daddr->sa.sa_family, dst_port,
+ vxlan->flags);
+ if (!dst_vxlan) {
+ dev->stats.tx_errors++;
+ kfree_skb(skb);
+
+ return -ENOENT;
+ }
+ vxlan_encap_bypass(skb, vxlan, dst_vxlan);
+ return 1;
+ }
+
+ return 0;
+}
+
static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
struct vxlan_rdst *rdst, bool did_rsc)
{
@@ -2045,26 +2072,16 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
if (IS_ERR(rt))
goto tx_error;
- /* Bypass encapsulation if the destination is local */
- if (!info && rt->rt_flags & RTCF_LOCAL &&
- !(rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))) {
- struct vxlan_dev *dst_vxlan;
-
- ip_rt_put(rt);
- dst_vxlan = vxlan_find_vni(vxlan->net, vni,
- dst->sa.sa_family, dst_port,
- vxlan->flags);
- if (!dst_vxlan)
- goto tx_error;
- vxlan_encap_bypass(skb, vxlan, dst_vxlan);
- return;
- }
-
- if (!info)
+ if (!info) {
+ err = check_route_rtf_local(skb, dev, vxlan, dst,
+ dst_port, vni, &rt->dst,
+ rt->rt_flags);
+ if (err)
+ return;
udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM_TX);
- else if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT)
+ } else if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT) {
df = htons(IP_DF);
-
+ }
tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
err = vxlan_build_skb(skb, &rt->dst, sizeof(struct iphdr),
@@ -2079,7 +2096,6 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
} else {
struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock);
struct dst_entry *ndst;
- u32 rt6i_flags;
sk = sock6->sock->sk;
@@ -2091,24 +2107,16 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
if (IS_ERR(ndst))
goto tx_error;
- /* Bypass encapsulation if the destination is local */
- rt6i_flags = ((struct rt6_info *)ndst)->rt6i_flags;
- if (!info && rt6i_flags & RTF_LOCAL &&
- !(rt6i_flags & (RTCF_BROADCAST | RTCF_MULTICAST))) {
- struct vxlan_dev *dst_vxlan;
-
- dst_release(ndst);
- dst_vxlan = vxlan_find_vni(vxlan->net, vni,
- dst->sa.sa_family, dst_port,
- vxlan->flags);
- if (!dst_vxlan)
- goto tx_error;
- vxlan_encap_bypass(skb, vxlan, dst_vxlan);
- return;
- }
+ if (!info) {
+ u32 rt6i_flags = ((struct rt6_info *)ndst)->rt6i_flags;
- if (!info)
+ err = check_route_rtf_local(skb, dev, vxlan, dst,
+ dst_port, vni, ndst,
+ rt6i_flags);
+ if (err)
+ return;
udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM6_TX);
+ }
tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
ttl = ttl ? : ip6_dst_hoplimit(ndst);
--
1.9.1
^ permalink raw reply related
* [PATCH net-next 4/7] vxlan: improve vxlan route lookup checks.
From: Pravin B Shelar @ 2016-11-04 20:51 UTC (permalink / raw)
To: netdev; +Cc: Pravin B Shelar
In-Reply-To: <1478292716-54649-1-git-send-email-pshelar@ovn.org>
Move route sanity check to respective vxlan[4/6]_get_route functions.
This allows us to perform all sanity checks before caching the dst so
that we can avoid these checks on subsequent packets.
This give move accurate metadata information for packet from
fill_metadata_dst().
Signed-off-by: Pravin B Shelar <pshelar@ovn.org>
---
drivers/net/vxlan.c | 71 +++++++++++++++++++++++++----------------------------
1 file changed, 34 insertions(+), 37 deletions(-)
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 6435d6a..15319f1 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1793,7 +1793,8 @@ static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst,
return err;
}
-static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan,
+static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan, struct net_device *dev,
+ struct vxlan_sock *sock4,
struct sk_buff *skb, int oif, u8 tos,
__be32 daddr, __be32 *saddr,
struct dst_cache *dst_cache,
@@ -1803,6 +1804,9 @@ static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan,
struct rtable *rt = NULL;
struct flowi4 fl4;
+ if (!sock4)
+ return ERR_PTR(-EIO);
+
if (tos && !info)
use_cache = false;
if (use_cache) {
@@ -1820,16 +1824,27 @@ static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan,
fl4.saddr = *saddr;
rt = ip_route_output_key(vxlan->net, &fl4);
- if (!IS_ERR(rt)) {
+ if (likely(!IS_ERR(rt))) {
+ if (rt->dst.dev == dev) {
+ netdev_dbg(dev, "circular route to %pI4\n", &daddr);
+ dev->stats.collisions++;
+ ip_rt_put(rt);
+ return ERR_PTR(-ELOOP);
+ }
+
*saddr = fl4.saddr;
if (use_cache)
dst_cache_set_ip4(dst_cache, &rt->dst, fl4.saddr);
+ } else {
+ netdev_dbg(dev, "no route to %pI4\n", &daddr);
+ dev->stats.tx_carrier_errors++;
}
return rt;
}
#if IS_ENABLED(CONFIG_IPV6)
static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan,
+ struct net_device *dev,
struct vxlan_sock *sock6,
struct sk_buff *skb, int oif, u8 tos,
__be32 label,
@@ -1865,8 +1880,18 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan,
err = ipv6_stub->ipv6_dst_lookup(vxlan->net,
sock6->sock->sk,
&ndst, &fl6);
- if (err < 0)
+ if (unlikely(err < 0)) {
+ netdev_dbg(dev, "no route to %pI6\n", daddr);
+ dev->stats.tx_carrier_errors++;
return ERR_PTR(err);
+ }
+
+ if (unlikely(ndst->dev == dev)) {
+ netdev_dbg(dev, "circular route to %pI6\n", daddr);
+ dst_release(ndst);
+ dev->stats.collisions++;
+ return ERR_PTR(-ELOOP);
+ }
*saddr = fl6.saddr;
if (use_cache)
@@ -2010,29 +2035,15 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock);
struct rtable *rt;
- if (!sock4)
- goto drop;
sk = sock4->sock->sk;
- rt = vxlan_get_route(vxlan, skb,
+ rt = vxlan_get_route(vxlan, dev, sock4, skb,
rdst ? rdst->remote_ifindex : 0, tos,
dst->sin.sin_addr.s_addr,
&src->sin.sin_addr.s_addr,
dst_cache, info);
- if (IS_ERR(rt)) {
- netdev_dbg(dev, "no route to %pI4\n",
- &dst->sin.sin_addr.s_addr);
- dev->stats.tx_carrier_errors++;
- goto tx_error;
- }
-
- if (rt->dst.dev == dev) {
- netdev_dbg(dev, "circular route to %pI4\n",
- &dst->sin.sin_addr.s_addr);
- dev->stats.collisions++;
- ip_rt_put(rt);
+ if (IS_ERR(rt))
goto tx_error;
- }
/* Bypass encapsulation if the destination is local */
if (!info && rt->rt_flags & RTCF_LOCAL &&
@@ -2072,25 +2083,13 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
sk = sock6->sock->sk;
- ndst = vxlan6_get_route(vxlan, sock6, skb,
+ ndst = vxlan6_get_route(vxlan, dev, sock6, skb,
rdst ? rdst->remote_ifindex : 0, tos,
label, &dst->sin6.sin6_addr,
&src->sin6.sin6_addr,
dst_cache, info);
- if (IS_ERR(ndst)) {
- netdev_dbg(dev, "no route to %pI6\n",
- &dst->sin6.sin6_addr);
- dev->stats.tx_carrier_errors++;
- goto tx_error;
- }
-
- if (ndst->dev == dev) {
- netdev_dbg(dev, "circular route to %pI6\n",
- &dst->sin6.sin6_addr);
- dst_release(ndst);
- dev->stats.collisions++;
+ if (IS_ERR(ndst))
goto tx_error;
- }
/* Bypass encapsulation if the destination is local */
rt6i_flags = ((struct rt6_info *)ndst)->rt6i_flags;
@@ -2414,9 +2413,7 @@ static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock);
struct rtable *rt;
- if (!sock4)
- return -EINVAL;
- rt = vxlan_get_route(vxlan, skb, 0, info->key.tos,
+ rt = vxlan_get_route(vxlan, dev, sock4, skb, 0, info->key.tos,
info->key.u.ipv4.dst,
&info->key.u.ipv4.src, NULL, info);
if (IS_ERR(rt))
@@ -2427,7 +2424,7 @@ static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock);
struct dst_entry *ndst;
- ndst = vxlan6_get_route(vxlan, sock6, skb, 0, info->key.tos,
+ ndst = vxlan6_get_route(vxlan, dev, sock6, skb, 0, info->key.tos,
info->key.label, &info->key.u.ipv6.dst,
&info->key.u.ipv6.src, NULL, info);
if (IS_ERR(ndst))
--
1.9.1
^ permalink raw reply related
* [PATCH net-next 3/7] vxlan: avoid checking socket multiple times.
From: Pravin B Shelar @ 2016-11-04 20:51 UTC (permalink / raw)
To: netdev; +Cc: Pravin B Shelar
In-Reply-To: <1478292716-54649-1-git-send-email-pshelar@ovn.org>
Check the vxlan socket in vxlan6_getroute().
Signed-off-by: Pravin B Shelar <pshelar@ovn.org>
---
drivers/net/vxlan.c | 9 ++++-----
1 file changed, 4 insertions(+), 5 deletions(-)
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index a1e707f..6435d6a 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1830,6 +1830,7 @@ static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan,
#if IS_ENABLED(CONFIG_IPV6)
static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan,
+ struct vxlan_sock *sock6,
struct sk_buff *skb, int oif, u8 tos,
__be32 label,
const struct in6_addr *daddr,
@@ -1837,7 +1838,6 @@ static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan,
struct dst_cache *dst_cache,
const struct ip_tunnel_info *info)
{
- struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock);
bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
struct dst_entry *ndst;
struct flowi6 fl6;
@@ -2070,11 +2070,9 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
struct dst_entry *ndst;
u32 rt6i_flags;
- if (!sock6)
- goto drop;
sk = sock6->sock->sk;
- ndst = vxlan6_get_route(vxlan, skb,
+ ndst = vxlan6_get_route(vxlan, sock6, skb,
rdst ? rdst->remote_ifindex : 0, tos,
label, &dst->sin6.sin6_addr,
&src->sin6.sin6_addr,
@@ -2426,9 +2424,10 @@ static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
ip_rt_put(rt);
} else {
#if IS_ENABLED(CONFIG_IPV6)
+ struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock);
struct dst_entry *ndst;
- ndst = vxlan6_get_route(vxlan, skb, 0, info->key.tos,
+ ndst = vxlan6_get_route(vxlan, sock6, skb, 0, info->key.tos,
info->key.label, &info->key.u.ipv6.dst,
&info->key.u.ipv6.src, NULL, info);
if (IS_ERR(ndst))
--
1.9.1
^ permalink raw reply related
* [PATCH net-next 2/7] vxlan: simplify exception handling
From: Pravin B Shelar @ 2016-11-04 20:51 UTC (permalink / raw)
To: netdev; +Cc: Pravin B Shelar
In-Reply-To: <1478292716-54649-1-git-send-email-pshelar@ovn.org>
vxlan egress path error handling has became complicated, it
need to handle IPv4 and IPv6 tunnel cases.
Earlier patch removes vlan handling from vxlan_build_skb(), so
vxlan_build_skb does not need to free skb and we can simplify
the xmit path by having single error handling for both type of
tunnels.
Signed-off-by: Pravin B Shelar <pshelar@ovn.org>
---
drivers/net/vxlan.c | 28 +++++++++++-----------------
1 file changed, 11 insertions(+), 17 deletions(-)
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 756d826..a1e707f 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -1789,7 +1789,7 @@ static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst,
return 0;
out_free:
- kfree_skb(skb);
+ dst_release(dst);
return err;
}
@@ -1927,7 +1927,6 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
struct ip_tunnel_info *info;
struct vxlan_dev *vxlan = netdev_priv(dev);
struct sock *sk;
- struct rtable *rt = NULL;
const struct iphdr *old_iph;
union vxlan_addr *dst;
union vxlan_addr remote_ip, local_ip;
@@ -2009,6 +2008,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
if (dst->sa.sa_family == AF_INET) {
struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock);
+ struct rtable *rt;
if (!sock4)
goto drop;
@@ -2030,7 +2030,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
netdev_dbg(dev, "circular route to %pI4\n",
&dst->sin.sin_addr.s_addr);
dev->stats.collisions++;
- goto rt_tx_error;
+ ip_rt_put(rt);
+ goto tx_error;
}
/* Bypass encapsulation if the destination is local */
@@ -2058,7 +2059,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
err = vxlan_build_skb(skb, &rt->dst, sizeof(struct iphdr),
vni, md, flags, udp_sum);
if (err < 0)
- goto xmit_tx_error;
+ goto tx_error;
udp_tunnel_xmit_skb(rt, sk, skb, src->sin.sin_addr.s_addr,
dst->sin.sin_addr.s_addr, tos, ttl, df,
@@ -2117,11 +2118,9 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
skb_scrub_packet(skb, xnet);
err = vxlan_build_skb(skb, ndst, sizeof(struct ipv6hdr),
vni, md, flags, udp_sum);
- if (err < 0) {
- dst_release(ndst);
- dev->stats.tx_errors++;
- return;
- }
+ if (err < 0)
+ goto tx_error;
+
udp_tunnel6_xmit_skb(ndst, sk, skb, dev,
&src->sin6.sin6_addr,
&dst->sin6.sin6_addr, tos, ttl,
@@ -2133,17 +2132,12 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
drop:
dev->stats.tx_dropped++;
- goto tx_free;
+ dev_kfree_skb(skb);
+ return;
-xmit_tx_error:
- /* skb is already freed. */
- skb = NULL;
-rt_tx_error:
- ip_rt_put(rt);
tx_error:
dev->stats.tx_errors++;
-tx_free:
- dev_kfree_skb(skb);
+ kfree_skb(skb);
}
/* Transmit local packets over Vxlan
--
1.9.1
^ 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