* [PATCH net-next v2 04/11] selftests: pmtu: Introduce tests for IPv4/IPv6 over VXLAN over IPv4/IPv6
From: Stefano Brivio @ 2018-11-08 11:19 UTC (permalink / raw)
To: David S. Miller
Cc: Sabrina Dubroca, Xin Long, Stephen Hemminger, Jiri Benc,
David Ahern, netdev
In-Reply-To: <cover.1541675666.git.sbrivio@redhat.com>
Use a router between endpoints, implemented via namespaces, set a low MTU
between router and destination endpoint, exceed it and check PMTU value in
route exceptions.
v2:
- Change all occurrences of VxLAN to VXLAN (Jiri Benc)
- Introduce IPv4 tests right away, if iproute2 doesn't support the 'df'
link option they will be skipped (David Ahern)
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
---
tools/testing/selftests/net/pmtu.sh | 143 ++++++++++++++++++++++++----
1 file changed, 125 insertions(+), 18 deletions(-)
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index a369d616b390..33cba295ad45 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -26,6 +26,23 @@
# - pmtu_ipv6
# Same as pmtu_ipv4, except for locked PMTU tests, using IPv6
#
+# - pmtu_ipv4_vxlan4_exception
+# Set up the same network topology as pmtu_ipv4, create a VXLAN tunnel
+# over IPv4 between A and B, routed via R1. On the link between R1 and B,
+# set a MTU lower than the VXLAN MTU and the MTU on the link between A and
+# R1. Send IPv4 packets, exceeding the MTU between R1 and B, over VXLAN
+# from A to B and check that the PMTU exception is created with the right
+# value on A
+#
+# - pmtu_ipv6_vxlan4_exception
+# Same as pmtu_ipv4_vxlan4_exception, but send IPv6 packets from A to B
+#
+# - pmtu_ipv4_vxlan6_exception
+# Same as pmtu_ipv4_vxlan4_exception, but use IPv6 transport from A to B
+#
+# - pmtu_ipv6_vxlan6_exception
+# Same as pmtu_ipv4_vxlan6_exception, but send IPv6 packets from A to B
+#
# - pmtu_vti4_exception
# Set up vti tunnel on top of veth, with xfrm states and policies, in two
# namespaces with matching endpoints. Check that route exception is not
@@ -72,6 +89,10 @@ which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping)
tests="
pmtu_ipv4_exception ipv4: PMTU exceptions
pmtu_ipv6_exception ipv6: PMTU exceptions
+ pmtu_ipv4_vxlan4_exception IPv4 over vxlan4: PMTU exceptions
+ pmtu_ipv6_vxlan4_exception IPv6 over vxlan4: PMTU exceptions
+ pmtu_ipv4_vxlan6_exception IPv4 over vxlan6: PMTU exceptions
+ pmtu_ipv6_vxlan6_exception IPv6 over vxlan6: PMTU exceptions
pmtu_vti6_exception vti6: PMTU exceptions
pmtu_vti4_exception vti4: PMTU exceptions
pmtu_vti4_default_mtu vti4: default MTU assignment
@@ -95,8 +116,8 @@ ns_r2="ip netns exec ${NS_R2}"
# Addresses are:
# - IPv4: PREFIX4.SEGMENT.ID (/24)
# - IPv6: PREFIX6:SEGMENT::ID (/64)
-prefix4="192.168"
-prefix6="fd00"
+prefix4="10.0"
+prefix6="fc00"
a_r1=1
a_r2=2
b_r1=3
@@ -129,12 +150,12 @@ veth6_a_addr="fd00:1::a"
veth6_b_addr="fd00:1::b"
veth6_mask="64"
-vti4_a_addr="192.168.2.1"
-vti4_b_addr="192.168.2.2"
-vti4_mask="24"
-vti6_a_addr="fd00:2::a"
-vti6_b_addr="fd00:2::b"
-vti6_mask="64"
+tunnel4_a_addr="192.168.2.1"
+tunnel4_b_addr="192.168.2.2"
+tunnel4_mask="24"
+tunnel6_a_addr="fd00:2::a"
+tunnel6_b_addr="fd00:2::b"
+tunnel6_mask="64"
dummy6_0_addr="fc00:1000::0"
dummy6_1_addr="fc00:1001::0"
@@ -202,11 +223,39 @@ setup_vti() {
}
setup_vti4() {
- setup_vti 4 ${veth4_a_addr} ${veth4_b_addr} ${vti4_a_addr} ${vti4_b_addr} ${vti4_mask}
+ setup_vti 4 ${veth4_a_addr} ${veth4_b_addr} ${tunnel4_a_addr} ${tunnel4_b_addr} ${tunnel4_mask}
}
setup_vti6() {
- setup_vti 6 ${veth6_a_addr} ${veth6_b_addr} ${vti6_a_addr} ${vti6_b_addr} ${vti6_mask}
+ setup_vti 6 ${veth6_a_addr} ${veth6_b_addr} ${tunnel6_a_addr} ${tunnel6_b_addr} ${tunnel6_mask}
+}
+
+setup_vxlan() {
+ a_addr="${1}"
+ b_addr="${2}"
+ opts="${3}"
+
+ ${ns_a} ip link add vxlan_a type vxlan id 1 local ${a_addr} remote ${b_addr} ttl 64 dstport 4789 ${opts} || return 1
+ ${ns_b} ip link add vxlan_b type vxlan id 1 local ${b_addr} remote ${a_addr} ttl 64 dstport 4789 ${opts}
+
+ ${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev vxlan_a
+ ${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev vxlan_b
+
+ ${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev vxlan_a
+ ${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev vxlan_b
+
+ ${ns_a} ip link set vxlan_a up
+ ${ns_b} ip link set vxlan_b up
+
+ sleep 1
+}
+
+setup_vxlan4() {
+ setup_vxlan ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "df set"
+}
+
+setup_vxlan6() {
+ setup_vxlan ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 ""
}
setup_xfrm() {
@@ -465,6 +514,64 @@ test_pmtu_ipv6_exception() {
test_pmtu_ipvX 6
}
+test_pmtu_ipvX_over_vxlanY_exception() {
+ family=${1}
+ outer_family=${2}
+ ll_mtu=4000
+
+ if [ ${outer_family} -eq 4 ]; then
+ setup namespaces routing vxlan4 || return 2
+ # IPv4 header UDP header VXLAN header Ethernet header
+ exp_mtu=$((${ll_mtu} - 20 - 8 - 8 - 14))
+ else
+ setup namespaces routing vxlan6 || return 2
+ # IPv6 header UDP header VXLAN header Ethernet header
+ exp_mtu=$((${ll_mtu} - 40 - 8 - 8 - 14))
+ fi
+
+ trace "${ns_a}" vxlan_a "${ns_b}" vxlan_b \
+ "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \
+ "${ns_b}" veth_B-R1 "${ns_r1}" veth_R1-B
+
+ if [ ${family} -eq 4 ]; then
+ ping=ping
+ dst=${tunnel4_b_addr}
+ else
+ ping=${ping6}
+ dst=${tunnel6_b_addr}
+ fi
+
+ # Create route exception by exceeding link layer MTU
+ mtu "${ns_a}" veth_A-R1 $((${ll_mtu} + 1000))
+ mtu "${ns_r1}" veth_R1-A $((${ll_mtu} + 1000))
+ mtu "${ns_b}" veth_B-R1 ${ll_mtu}
+ mtu "${ns_r1}" veth_R1-B ${ll_mtu}
+
+ mtu "${ns_a}" vxlan_a $((${ll_mtu} + 1000))
+ mtu "${ns_b}" vxlan_b $((${ll_mtu} + 1000))
+ ${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s $((${ll_mtu} + 500)) ${dst} > /dev/null
+
+ # Check that exception was created
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})"
+ check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on VXLAN interface"
+}
+
+test_pmtu_ipv4_vxlan4_exception() {
+ test_pmtu_ipvX_over_vxlanY_exception 4 4
+}
+
+test_pmtu_ipv6_vxlan4_exception() {
+ test_pmtu_ipvX_over_vxlanY_exception 6 4
+}
+
+test_pmtu_ipv4_vxlan6_exception() {
+ test_pmtu_ipvX_over_vxlanY_exception 4 6
+}
+
+test_pmtu_ipv6_vxlan6_exception() {
+ test_pmtu_ipvX_over_vxlanY_exception 6 6
+}
+
test_pmtu_vti4_exception() {
setup namespaces veth vti4 xfrm4 || return 2
trace "${ns_a}" veth_a "${ns_b}" veth_b \
@@ -484,14 +591,14 @@ test_pmtu_vti4_exception() {
# Send DF packet without exceeding link layer MTU, check that no
# exception is created
- ${ns_a} ping -q -M want -i 0.1 -w 2 -s ${ping_payload} ${vti4_b_addr} > /dev/null
- pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti4_b_addr})"
+ ${ns_a} ping -q -M want -i 0.1 -w 2 -s ${ping_payload} ${tunnel4_b_addr} > /dev/null
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1
# Now exceed link layer MTU by one byte, check that exception is created
# with the right PMTU value
- ${ns_a} ping -q -M want -i 0.1 -w 2 -s $((ping_payload + 1)) ${vti4_b_addr} > /dev/null
- pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti4_b_addr})"
+ ${ns_a} ping -q -M want -i 0.1 -w 2 -s $((ping_payload + 1)) ${tunnel4_b_addr} > /dev/null
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
check_pmtu_value "${esp_payload_rfc4106}" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106 + 1)))"
}
@@ -506,20 +613,20 @@ test_pmtu_vti6_exception() {
mtu "${ns_b}" veth_b 4000
mtu "${ns_a}" vti6_a 5000
mtu "${ns_b}" vti6_b 5000
- ${ns_a} ${ping6} -q -i 0.1 -w 2 -s 60000 ${vti6_b_addr} > /dev/null
+ ${ns_a} ${ping6} -q -i 0.1 -w 2 -s 60000 ${tunnel6_b_addr} > /dev/null
# Check that exception was created
- pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})"
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
check_pmtu_value any "${pmtu}" "creating tunnel exceeding link layer MTU" || return 1
# Decrease tunnel MTU, check for PMTU decrease in route exception
mtu "${ns_a}" vti6_a 3000
- pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})"
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
check_pmtu_value "3000" "${pmtu}" "decreasing tunnel MTU" || fail=1
# Increase tunnel MTU, check for PMTU increase in route exception
mtu "${ns_a}" vti6_a 9000
- pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})"
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
check_pmtu_value "9000" "${pmtu}" "increasing tunnel MTU" || fail=1
return ${fail}
--
2.19.1
^ permalink raw reply related
* [PATCH net-next v2 05/11] geneve: ICMP error lookup handler
From: Stefano Brivio @ 2018-11-08 11:19 UTC (permalink / raw)
To: David S. Miller
Cc: Sabrina Dubroca, Xin Long, Stephen Hemminger, Jiri Benc,
David Ahern, netdev
In-Reply-To: <cover.1541675666.git.sbrivio@redhat.com>
Export an encap_err_lookup() operation to match an ICMP error against a
valid VNI.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
---
v2: no changes
drivers/net/geneve.c | 52 ++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 52 insertions(+)
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index fbfc13d81f66..4dc457489770 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -387,6 +387,57 @@ static int geneve_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
return 0;
}
+/* Callback from net/ipv{4,6}/udp.c to check that we have a tunnel for errors */
+static int geneve_udp_encap_err_lookup(struct sock *sk, struct sk_buff *skb)
+{
+ struct genevehdr *geneveh;
+ struct geneve_sock *gs;
+ u8 zero_vni[3] = { 0 };
+ u8 *vni = zero_vni;
+
+ if (skb->len < GENEVE_BASE_HLEN)
+ return -EINVAL;
+
+ geneveh = geneve_hdr(skb);
+ if (geneveh->ver != GENEVE_VER)
+ return -EINVAL;
+
+ if (geneveh->proto_type != htons(ETH_P_TEB))
+ return -EINVAL;
+
+ gs = rcu_dereference_sk_user_data(sk);
+ if (!gs)
+ return -ENOENT;
+
+ if (geneve_get_sk_family(gs) == AF_INET) {
+ struct iphdr *iph = ip_hdr(skb);
+ __be32 addr4 = 0;
+
+ if (!gs->collect_md) {
+ vni = geneve_hdr(skb)->vni;
+ addr4 = iph->daddr;
+ }
+
+ return geneve_lookup(gs, addr4, vni) ? 0 : -ENOENT;
+ }
+
+#if IS_ENABLED(CONFIG_IPV6)
+ if (geneve_get_sk_family(gs) == AF_INET6) {
+ struct ipv6hdr *ip6h = ipv6_hdr(skb);
+ struct in6_addr addr6 = { 0 };
+
+ if (!gs->collect_md) {
+ vni = geneve_hdr(skb)->vni;
+ addr6 = ip6h->daddr;
+ }
+
+ return geneve6_lookup(gs, addr6, vni) ? 0 : -ENOENT;
+ }
+#endif
+
+ return -EPFNOSUPPORT;
+}
+
static struct socket *geneve_create_sock(struct net *net, bool ipv6,
__be16 port, bool ipv6_rx_csum)
{
@@ -544,6 +595,7 @@ static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port,
tunnel_cfg.gro_receive = geneve_gro_receive;
tunnel_cfg.gro_complete = geneve_gro_complete;
tunnel_cfg.encap_rcv = geneve_udp_encap_recv;
+ tunnel_cfg.encap_err_lookup = geneve_udp_encap_err_lookup;
tunnel_cfg.encap_destroy = NULL;
setup_udp_tunnel_sock(net, sock, &tunnel_cfg);
list_add(&gs->list, &gn->sock_list);
--
2.19.1
^ permalink raw reply related
* [PATCH net-next v2 06/11] geneve: Allow configuration of DF behaviour
From: Stefano Brivio @ 2018-11-08 11:19 UTC (permalink / raw)
To: David S. Miller
Cc: Sabrina Dubroca, Xin Long, Stephen Hemminger, Jiri Benc,
David Ahern, netdev
In-Reply-To: <cover.1541675666.git.sbrivio@redhat.com>
draft-ietf-nvo3-geneve-08 says:
It is strongly RECOMMENDED that Path MTU Discovery ([RFC1191],
[RFC1981]) be used by setting the DF bit in the IP header when Geneve
packets are transmitted over IPv4 (this is the default with IPv6).
Now that ICMP error handling is working for GENEVE, we can comply with
this recommendation.
Make this configurable, though, to avoid breaking existing setups. By
default, DF won't be set. It can be set or inherited from inner IPv4
packets. If it's configured to be inherited and we are encapsulating IPv6,
it will be set.
This only applies to non-lwt tunnels: if an external control plane is
used, tunnel key will still control the DF flag.
v2:
- DF behaviour configuration only applies for non-lwt tunnels, apply DF
setting only if (!geneve->collect_md) in geneve_xmit_skb()
(Stephen Hemminger)
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
---
drivers/net/geneve.c | 55 ++++++++++++++++++++++++++++++------
include/uapi/linux/if_link.h | 9 ++++++
2 files changed, 56 insertions(+), 8 deletions(-)
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 4dc457489770..7c53e06b31c3 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -70,6 +70,7 @@ struct geneve_dev {
bool collect_md;
bool use_udp6_rx_checksums;
bool ttl_inherit;
+ enum ifla_geneve_df df;
};
struct geneve_sock {
@@ -875,8 +876,8 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
struct rtable *rt;
struct flowi4 fl4;
__u8 tos, ttl;
+ __be16 df = 0;
__be16 sport;
- __be16 df;
int err;
rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info);
@@ -890,6 +891,8 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
if (geneve->collect_md) {
tos = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb);
ttl = key->ttl;
+
+ df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0;
} else {
tos = ip_tunnel_ecn_encap(fl4.flowi4_tos, ip_hdr(skb), skb);
if (geneve->ttl_inherit)
@@ -897,8 +900,22 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
else
ttl = key->ttl;
ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
+
+ if (geneve->df == GENEVE_DF_SET) {
+ df = htons(IP_DF);
+ } else if (geneve->df == GENEVE_DF_INHERIT) {
+ struct ethhdr *eth = eth_hdr(skb);
+
+ if (ntohs(eth->h_proto) == ETH_P_IPV6) {
+ df = htons(IP_DF);
+ } else if (ntohs(eth->h_proto) == ETH_P_IP) {
+ struct iphdr *iph = ip_hdr(skb);
+
+ if (iph->frag_off & htons(IP_DF))
+ df = htons(IP_DF);
+ }
+ }
}
- df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0;
err = geneve_build_skb(&rt->dst, skb, info, xnet, sizeof(struct iphdr));
if (unlikely(err))
@@ -1145,6 +1162,7 @@ static const struct nla_policy geneve_policy[IFLA_GENEVE_MAX + 1] = {
[IFLA_GENEVE_UDP_ZERO_CSUM6_TX] = { .type = NLA_U8 },
[IFLA_GENEVE_UDP_ZERO_CSUM6_RX] = { .type = NLA_U8 },
[IFLA_GENEVE_TTL_INHERIT] = { .type = NLA_U8 },
+ [IFLA_GENEVE_DF] = { .type = NLA_U8 },
};
static int geneve_validate(struct nlattr *tb[], struct nlattr *data[],
@@ -1180,6 +1198,16 @@ static int geneve_validate(struct nlattr *tb[], struct nlattr *data[],
}
}
+ if (data[IFLA_GENEVE_DF]) {
+ enum ifla_geneve_df df = nla_get_u8(data[IFLA_GENEVE_DF]);
+
+ if (df < 0 || df > GENEVE_DF_MAX) {
+ NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_GENEVE_DF],
+ "Invalid DF attribute");
+ return -EINVAL;
+ }
+ }
+
return 0;
}
@@ -1225,7 +1253,7 @@ static int geneve_configure(struct net *net, struct net_device *dev,
struct netlink_ext_ack *extack,
const struct ip_tunnel_info *info,
bool metadata, bool ipv6_rx_csum,
- bool ttl_inherit)
+ bool ttl_inherit, enum ifla_geneve_df df)
{
struct geneve_net *gn = net_generic(net, geneve_net_id);
struct geneve_dev *t, *geneve = netdev_priv(dev);
@@ -1275,6 +1303,7 @@ static int geneve_configure(struct net *net, struct net_device *dev,
geneve->collect_md = metadata;
geneve->use_udp6_rx_checksums = ipv6_rx_csum;
geneve->ttl_inherit = ttl_inherit;
+ geneve->df = df;
err = register_netdevice(dev);
if (err)
@@ -1294,7 +1323,7 @@ static int geneve_nl2info(struct nlattr *tb[], struct nlattr *data[],
struct netlink_ext_ack *extack,
struct ip_tunnel_info *info, bool *metadata,
bool *use_udp6_rx_checksums, bool *ttl_inherit,
- bool changelink)
+ enum ifla_geneve_df *df, bool changelink)
{
int attrtype;
@@ -1382,6 +1411,9 @@ static int geneve_nl2info(struct nlattr *tb[], struct nlattr *data[],
if (data[IFLA_GENEVE_TOS])
info->key.tos = nla_get_u8(data[IFLA_GENEVE_TOS]);
+ if (data[IFLA_GENEVE_DF])
+ *df = nla_get_u8(data[IFLA_GENEVE_DF]);
+
if (data[IFLA_GENEVE_LABEL]) {
info->key.label = nla_get_be32(data[IFLA_GENEVE_LABEL]) &
IPV6_FLOWLABEL_MASK;
@@ -1500,6 +1532,7 @@ static int geneve_newlink(struct net *net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[],
struct netlink_ext_ack *extack)
{
+ enum ifla_geneve_df df = GENEVE_DF_UNSET;
bool use_udp6_rx_checksums = false;
struct ip_tunnel_info info;
bool ttl_inherit = false;
@@ -1508,12 +1541,12 @@ static int geneve_newlink(struct net *net, struct net_device *dev,
init_tnl_info(&info, GENEVE_UDP_PORT);
err = geneve_nl2info(tb, data, extack, &info, &metadata,
- &use_udp6_rx_checksums, &ttl_inherit, false);
+ &use_udp6_rx_checksums, &ttl_inherit, &df, false);
if (err)
return err;
err = geneve_configure(net, dev, extack, &info, metadata,
- use_udp6_rx_checksums, ttl_inherit);
+ use_udp6_rx_checksums, ttl_inherit, df);
if (err)
return err;
@@ -1576,6 +1609,7 @@ static int geneve_changelink(struct net_device *dev, struct nlattr *tb[],
struct ip_tunnel_info info;
bool metadata;
bool use_udp6_rx_checksums;
+ enum ifla_geneve_df df;
bool ttl_inherit;
int err;
@@ -1591,7 +1625,7 @@ static int geneve_changelink(struct net_device *dev, struct nlattr *tb[],
use_udp6_rx_checksums = geneve->use_udp6_rx_checksums;
ttl_inherit = geneve->ttl_inherit;
err = geneve_nl2info(tb, data, extack, &info, &metadata,
- &use_udp6_rx_checksums, &ttl_inherit, true);
+ &use_udp6_rx_checksums, &ttl_inherit, &df, true);
if (err)
return err;
@@ -1624,6 +1658,7 @@ static size_t geneve_get_size(const struct net_device *dev)
nla_total_size(sizeof(struct in6_addr)) + /* IFLA_GENEVE_REMOTE{6} */
nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TTL */
nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TOS */
+ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_DF */
nla_total_size(sizeof(__be32)) + /* IFLA_GENEVE_LABEL */
nla_total_size(sizeof(__be16)) + /* IFLA_GENEVE_PORT */
nla_total_size(0) + /* IFLA_GENEVE_COLLECT_METADATA */
@@ -1672,6 +1707,9 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev)
nla_put_be32(skb, IFLA_GENEVE_LABEL, info->key.label))
goto nla_put_failure;
+ if (nla_put_u8(skb, IFLA_GENEVE_DF, geneve->df))
+ goto nla_put_failure;
+
if (nla_put_be16(skb, IFLA_GENEVE_PORT, info->key.tp_dst))
goto nla_put_failure;
@@ -1723,7 +1761,8 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name,
return dev;
init_tnl_info(&info, dst_port);
- err = geneve_configure(net, dev, NULL, &info, true, true, false);
+ err = geneve_configure(net, dev, NULL, &info,
+ true, true, false, GENEVE_DF_UNSET);
if (err) {
free_netdev(dev);
return ERR_PTR(err);
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index efc588949431..f42c069d81db 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -566,10 +566,19 @@ enum {
IFLA_GENEVE_UDP_ZERO_CSUM6_RX,
IFLA_GENEVE_LABEL,
IFLA_GENEVE_TTL_INHERIT,
+ IFLA_GENEVE_DF,
__IFLA_GENEVE_MAX
};
#define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1)
+enum ifla_geneve_df {
+ GENEVE_DF_UNSET = 0,
+ GENEVE_DF_SET,
+ GENEVE_DF_INHERIT,
+ __GENEVE_DF_END,
+ GENEVE_DF_MAX = __GENEVE_DF_END - 1,
+};
+
/* PPP section */
enum {
IFLA_PPP_UNSPEC,
--
2.19.1
^ permalink raw reply related
* [PATCH net-next v2 07/11] selftests: pmtu: Introduce tests for IPv4/IPv6 over GENEVE over IPv4/IPv6
From: Stefano Brivio @ 2018-11-08 11:19 UTC (permalink / raw)
To: David S. Miller
Cc: Sabrina Dubroca, Xin Long, Stephen Hemminger, Jiri Benc,
David Ahern, netdev
In-Reply-To: <cover.1541675666.git.sbrivio@redhat.com>
Use a router between endpoints, implemented via namespaces, set a low MTU
between router and destination endpoint, exceed it and check PMTU value in
route exceptions.
v2:
- Introduce IPv4 tests right away, if iproute2 doesn't support the 'df'
link option they will be skipped (David Ahern)
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
---
tools/testing/selftests/net/pmtu.sh | 117 ++++++++++++++++++++--------
1 file changed, 86 insertions(+), 31 deletions(-)
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 33cba295ad45..14d20782ccb7 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -43,6 +43,22 @@
# - pmtu_ipv6_vxlan6_exception
# Same as pmtu_ipv4_vxlan6_exception, but send IPv6 packets from A to B
#
+# - pmtu_ipv4_geneve4_exception
+# Same as pmtu_ipv4_vxlan4_exception, but using a GENEVE tunnel instead of
+# VXLAN
+#
+# - pmtu_ipv6_geneve4_exception
+# Same as pmtu_ipv6_vxlan4_exception, but using a GENEVE tunnel instead of
+# VXLAN
+#
+# - pmtu_ipv4_geneve6_exception
+# Same as pmtu_ipv4_vxlan6_exception, but using a GENEVE tunnel instead of
+# VXLAN
+#
+# - pmtu_ipv6_geneve6_exception
+# Same as pmtu_ipv6_vxlan6_exception, but using a GENEVE tunnel instead of
+# VXLAN
+#
# - pmtu_vti4_exception
# Set up vti tunnel on top of veth, with xfrm states and policies, in two
# namespaces with matching endpoints. Check that route exception is not
@@ -93,6 +109,10 @@ tests="
pmtu_ipv6_vxlan4_exception IPv6 over vxlan4: PMTU exceptions
pmtu_ipv4_vxlan6_exception IPv4 over vxlan6: PMTU exceptions
pmtu_ipv6_vxlan6_exception IPv6 over vxlan6: PMTU exceptions
+ pmtu_ipv4_geneve4_exception IPv4 over geneve4: PMTU exceptions
+ pmtu_ipv6_geneve4_exception IPv6 over geneve4: PMTU exceptions
+ pmtu_ipv4_geneve6_exception IPv4 over geneve6: PMTU exceptions
+ pmtu_ipv6_geneve6_exception IPv6 over geneve6: PMTU exceptions
pmtu_vti6_exception vti6: PMTU exceptions
pmtu_vti4_exception vti4: PMTU exceptions
pmtu_vti4_default_mtu vti4: default MTU assignment
@@ -230,32 +250,50 @@ setup_vti6() {
setup_vti 6 ${veth6_a_addr} ${veth6_b_addr} ${tunnel6_a_addr} ${tunnel6_b_addr} ${tunnel6_mask}
}
-setup_vxlan() {
- a_addr="${1}"
- b_addr="${2}"
- opts="${3}"
+setup_vxlan_or_geneve() {
+ type="${1}"
+ a_addr="${2}"
+ b_addr="${3}"
+ opts="${4}"
+
+ if [ "${type}" = "vxlan" ]; then
+ opts="${opts} ttl 64 dstport 4789"
+ opts_a="local ${a_addr}"
+ opts_b="local ${b_addr}"
+ else
+ opts_a=""
+ opts_b=""
+ fi
- ${ns_a} ip link add vxlan_a type vxlan id 1 local ${a_addr} remote ${b_addr} ttl 64 dstport 4789 ${opts} || return 1
- ${ns_b} ip link add vxlan_b type vxlan id 1 local ${b_addr} remote ${a_addr} ttl 64 dstport 4789 ${opts}
+ ${ns_a} ip link add ${type}_a type ${type} id 1 ${opts_a} remote ${b_addr} ${opts} || return 1
+ ${ns_b} ip link add ${type}_b type ${type} id 1 ${opts_b} remote ${a_addr} ${opts}
- ${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev vxlan_a
- ${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev vxlan_b
+ ${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ${type}_a
+ ${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ${type}_b
- ${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev vxlan_a
- ${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev vxlan_b
+ ${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ${type}_a
+ ${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev ${type}_b
- ${ns_a} ip link set vxlan_a up
- ${ns_b} ip link set vxlan_b up
+ ${ns_a} ip link set ${type}_a up
+ ${ns_b} ip link set ${type}_b up
sleep 1
}
+setup_geneve4() {
+ setup_vxlan_or_geneve geneve ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "df set"
+}
+
setup_vxlan4() {
- setup_vxlan ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "df set"
+ setup_vxlan_or_geneve vxlan ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "df set"
+}
+
+setup_geneve6() {
+ setup_vxlan_or_geneve geneve ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1
}
setup_vxlan6() {
- setup_vxlan ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 ""
+ setup_vxlan_or_geneve vxlan ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1
}
setup_xfrm() {
@@ -514,22 +552,23 @@ test_pmtu_ipv6_exception() {
test_pmtu_ipvX 6
}
-test_pmtu_ipvX_over_vxlanY_exception() {
- family=${1}
- outer_family=${2}
+test_pmtu_ipvX_over_vxlanY_or_geneveY_exception() {
+ type=${1}
+ family=${2}
+ outer_family=${3}
ll_mtu=4000
if [ ${outer_family} -eq 4 ]; then
- setup namespaces routing vxlan4 || return 2
- # IPv4 header UDP header VXLAN header Ethernet header
- exp_mtu=$((${ll_mtu} - 20 - 8 - 8 - 14))
+ setup namespaces routing ${type}4 || return 2
+ # IPv4 header UDP header VXLAN/GENEVE header Ethernet header
+ exp_mtu=$((${ll_mtu} - 20 - 8 - 8 - 14))
else
- setup namespaces routing vxlan6 || return 2
- # IPv6 header UDP header VXLAN header Ethernet header
- exp_mtu=$((${ll_mtu} - 40 - 8 - 8 - 14))
+ setup namespaces routing ${type}6 || return 2
+ # IPv6 header UDP header VXLAN/GENEVE header Ethernet header
+ exp_mtu=$((${ll_mtu} - 40 - 8 - 8 - 14))
fi
- trace "${ns_a}" vxlan_a "${ns_b}" vxlan_b \
+ trace "${ns_a}" ${type}_a "${ns_b}" ${type}_b \
"${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \
"${ns_b}" veth_B-R1 "${ns_r1}" veth_R1-B
@@ -547,29 +586,45 @@ test_pmtu_ipvX_over_vxlanY_exception() {
mtu "${ns_b}" veth_B-R1 ${ll_mtu}
mtu "${ns_r1}" veth_R1-B ${ll_mtu}
- mtu "${ns_a}" vxlan_a $((${ll_mtu} + 1000))
- mtu "${ns_b}" vxlan_b $((${ll_mtu} + 1000))
+ mtu "${ns_a}" ${type}_a $((${ll_mtu} + 1000))
+ mtu "${ns_b}" ${type}_b $((${ll_mtu} + 1000))
${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s $((${ll_mtu} + 500)) ${dst} > /dev/null
# Check that exception was created
pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})"
- check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on VXLAN interface"
+ check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on ${type} interface"
}
test_pmtu_ipv4_vxlan4_exception() {
- test_pmtu_ipvX_over_vxlanY_exception 4 4
+ test_pmtu_ipvX_over_vxlanY_or_geneveY_exception vxlan 4 4
}
test_pmtu_ipv6_vxlan4_exception() {
- test_pmtu_ipvX_over_vxlanY_exception 6 4
+ test_pmtu_ipvX_over_vxlanY_or_geneveY_exception vxlan 6 4
+}
+
+test_pmtu_ipv4_geneve4_exception() {
+ test_pmtu_ipvX_over_vxlanY_or_geneveY_exception geneve 4 4
+}
+
+test_pmtu_ipv6_geneve4_exception() {
+ test_pmtu_ipvX_over_vxlanY_or_geneveY_exception geneve 6 4
}
test_pmtu_ipv4_vxlan6_exception() {
- test_pmtu_ipvX_over_vxlanY_exception 4 6
+ test_pmtu_ipvX_over_vxlanY_or_geneveY_exception vxlan 4 6
}
test_pmtu_ipv6_vxlan6_exception() {
- test_pmtu_ipvX_over_vxlanY_exception 6 6
+ test_pmtu_ipvX_over_vxlanY_or_geneveY_exception vxlan 6 6
+}
+
+test_pmtu_ipv4_geneve6_exception() {
+ test_pmtu_ipvX_over_vxlanY_or_geneveY_exception geneve 4 6
+}
+
+test_pmtu_ipv6_geneve6_exception() {
+ test_pmtu_ipvX_over_vxlanY_or_geneveY_exception geneve 6 6
}
test_pmtu_vti4_exception() {
--
2.19.1
^ permalink raw reply related
* [PATCH net-next v2 08/11] net: Convert protocol error handlers from void to int
From: Stefano Brivio @ 2018-11-08 11:19 UTC (permalink / raw)
To: David S. Miller
Cc: Sabrina Dubroca, Xin Long, Stephen Hemminger, Jiri Benc,
David Ahern, netdev
In-Reply-To: <cover.1541675666.git.sbrivio@redhat.com>
We'll need this to handle ICMP errors for tunnels without a sending socket
(i.e. FoU and GUE). There, we might have to look up different types of IP
tunnels, registered as network protocols, before we get a match, so we
want this for the error handlers of IPPROTO_IPIP and IPPROTO_IPV6 in both
inet_protos and inet6_protos. These error codes will be used in the next
patch.
For consistency, return sensible error codes in protocol error handlers
whenever handlers can't handle errors because, even if valid, they don't
match a protocol or any of its states.
This has no effect on existing error handling paths.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
---
v2: no changes
include/net/icmp.h | 2 +-
include/net/protocol.h | 9 ++++++--
include/net/sctp/sctp.h | 2 +-
include/net/tcp.h | 2 +-
include/net/udp.h | 2 +-
net/dccp/ipv4.c | 13 +++++++----
net/dccp/ipv6.c | 13 +++++++----
net/ipv4/gre_demux.c | 9 ++++++--
net/ipv4/icmp.c | 6 +++--
net/ipv4/ip_gre.c | 48 ++++++++++++++++++++-------------------
net/ipv4/ipip.c | 14 ++++++------
net/ipv4/tcp_ipv4.c | 22 ++++++++++--------
net/ipv4/tunnel4.c | 18 ++++++++++-----
net/ipv4/udp.c | 10 ++++----
net/ipv4/udp_impl.h | 2 +-
net/ipv4/udplite.c | 4 ++--
net/ipv4/xfrm4_protocol.c | 18 ++++++++++-----
net/ipv6/icmp.c | 4 +++-
net/ipv6/ip6_gre.c | 18 ++++++++-------
net/ipv6/tcp_ipv6.c | 13 +++++++----
net/ipv6/tunnel6.c | 12 ++++++----
net/ipv6/udp.c | 18 +++++++--------
net/ipv6/udp_impl.h | 4 ++--
net/ipv6/udplite.c | 5 ++--
net/ipv6/xfrm6_protocol.c | 18 ++++++++++-----
net/sctp/input.c | 5 ++--
net/sctp/ipv6.c | 7 ++++--
27 files changed, 177 insertions(+), 121 deletions(-)
diff --git a/include/net/icmp.h b/include/net/icmp.h
index 3ef2743a8eec..6ac3a5bd0117 100644
--- a/include/net/icmp.h
+++ b/include/net/icmp.h
@@ -41,7 +41,7 @@ struct net;
void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info);
int icmp_rcv(struct sk_buff *skb);
-void icmp_err(struct sk_buff *skb, u32 info);
+int icmp_err(struct sk_buff *skb, u32 info);
int icmp_init(void);
void icmp_out_count(struct net *net, unsigned char type);
diff --git a/include/net/protocol.h b/include/net/protocol.h
index 4fc75f7ae23b..92b3eaad6088 100644
--- a/include/net/protocol.h
+++ b/include/net/protocol.h
@@ -42,7 +42,10 @@ struct net_protocol {
int (*early_demux)(struct sk_buff *skb);
int (*early_demux_handler)(struct sk_buff *skb);
int (*handler)(struct sk_buff *skb);
- void (*err_handler)(struct sk_buff *skb, u32 info);
+
+ /* This returns an error if we weren't able to handle the error. */
+ int (*err_handler)(struct sk_buff *skb, u32 info);
+
unsigned int no_policy:1,
netns_ok:1,
/* does the protocol do more stringent
@@ -58,10 +61,12 @@ struct inet6_protocol {
void (*early_demux_handler)(struct sk_buff *skb);
int (*handler)(struct sk_buff *skb);
- void (*err_handler)(struct sk_buff *skb,
+ /* This returns an error if we weren't able to handle the error. */
+ int (*err_handler)(struct sk_buff *skb,
struct inet6_skb_parm *opt,
u8 type, u8 code, int offset,
__be32 info);
+
unsigned int flags; /* INET6_PROTO_xxx */
};
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 8c2caa370e0f..9a3b48a35e90 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -151,7 +151,7 @@ int sctp_primitive_RECONF(struct net *net, struct sctp_association *asoc,
* sctp/input.c
*/
int sctp_rcv(struct sk_buff *skb);
-void sctp_v4_err(struct sk_buff *skb, u32 info);
+int sctp_v4_err(struct sk_buff *skb, u32 info);
void sctp_hash_endpoint(struct sctp_endpoint *);
void sctp_unhash_endpoint(struct sctp_endpoint *);
struct sock *sctp_err_lookup(struct net *net, int family, struct sk_buff *,
diff --git a/include/net/tcp.h b/include/net/tcp.h
index a18914d20486..4743836bed2e 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -313,7 +313,7 @@ extern struct proto tcp_prot;
void tcp_tasklet_init(void);
-void tcp_v4_err(struct sk_buff *skb, u32);
+int tcp_v4_err(struct sk_buff *skb, u32);
void tcp_shutdown(struct sock *sk, int how);
diff --git a/include/net/udp.h b/include/net/udp.h
index eccca2325ee6..fd6d948755c8 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -283,7 +283,7 @@ bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst);
int udp_get_port(struct sock *sk, unsigned short snum,
int (*saddr_cmp)(const struct sock *,
const struct sock *));
-void udp_err(struct sk_buff *, u32);
+int udp_err(struct sk_buff *, u32);
int udp_abort(struct sock *sk, int err);
int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len);
int udp_push_pending_frames(struct sock *sk);
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 8e08cea6f178..26a21d97b6b0 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -231,7 +231,7 @@ EXPORT_SYMBOL(dccp_req_err);
* check at all. A more general error queue to queue errors for later handling
* is probably better.
*/
-static void dccp_v4_err(struct sk_buff *skb, u32 info)
+static int dccp_v4_err(struct sk_buff *skb, u32 info)
{
const struct iphdr *iph = (struct iphdr *)skb->data;
const u8 offset = iph->ihl << 2;
@@ -259,16 +259,18 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
inet_iif(skb), 0);
if (!sk) {
__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
- return;
+ return -ENOENT;
}
if (sk->sk_state == DCCP_TIME_WAIT) {
inet_twsk_put(inet_twsk(sk));
- return;
+ return 0;
}
seq = dccp_hdr_seq(dh);
- if (sk->sk_state == DCCP_NEW_SYN_RECV)
- return dccp_req_err(sk, seq);
+ if (sk->sk_state == DCCP_NEW_SYN_RECV) {
+ dccp_req_err(sk, seq);
+ return 0;
+ }
bh_lock_sock(sk);
/* If too many ICMPs get dropped on busy
@@ -357,6 +359,7 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
out:
bh_unlock_sock(sk);
sock_put(sk);
+ return 0;
}
static inline __sum16 dccp_v4_csum_finish(struct sk_buff *skb,
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 6344f1b18a6a..d5740bad5b18 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -68,7 +68,7 @@ static inline __u64 dccp_v6_init_sequence(struct sk_buff *skb)
}
-static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
@@ -96,16 +96,18 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
if (!sk) {
__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
ICMP6_MIB_INERRORS);
- return;
+ return -ENOENT;
}
if (sk->sk_state == DCCP_TIME_WAIT) {
inet_twsk_put(inet_twsk(sk));
- return;
+ return 0;
}
seq = dccp_hdr_seq(dh);
- if (sk->sk_state == DCCP_NEW_SYN_RECV)
- return dccp_req_err(sk, seq);
+ if (sk->sk_state == DCCP_NEW_SYN_RECV) {
+ dccp_req_err(sk, seq);
+ return 0;
+ }
bh_lock_sock(sk);
if (sock_owned_by_user(sk))
@@ -183,6 +185,7 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
out:
bh_unlock_sock(sk);
sock_put(sk);
+ return 0;
}
diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
index 7efe740c06eb..a4bf22ee3aed 100644
--- a/net/ipv4/gre_demux.c
+++ b/net/ipv4/gre_demux.c
@@ -151,20 +151,25 @@ static int gre_rcv(struct sk_buff *skb)
return NET_RX_DROP;
}
-static void gre_err(struct sk_buff *skb, u32 info)
+static int gre_err(struct sk_buff *skb, u32 info)
{
const struct gre_protocol *proto;
const struct iphdr *iph = (const struct iphdr *)skb->data;
u8 ver = skb->data[(iph->ihl<<2) + 1]&0x7f;
+ int err = 0;
if (ver >= GREPROTO_MAX)
- return;
+ return -EINVAL;
rcu_read_lock();
proto = rcu_dereference(gre_proto[ver]);
if (proto && proto->err_handler)
proto->err_handler(skb, info);
+ else
+ err = -EPROTONOSUPPORT;
rcu_read_unlock();
+
+ return err;
}
static const struct net_protocol net_gre_protocol = {
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index d832beed6e3a..065997f414e6 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -1079,7 +1079,7 @@ int icmp_rcv(struct sk_buff *skb)
goto drop;
}
-void icmp_err(struct sk_buff *skb, u32 info)
+int icmp_err(struct sk_buff *skb, u32 info)
{
struct iphdr *iph = (struct iphdr *)skb->data;
int offset = iph->ihl<<2;
@@ -1094,13 +1094,15 @@ void icmp_err(struct sk_buff *skb, u32 info)
*/
if (icmph->type != ICMP_ECHOREPLY) {
ping_err(skb, offset, info);
- return;
+ return 0;
}
if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)
ipv4_update_pmtu(skb, net, info, 0, IPPROTO_ICMP);
else if (type == ICMP_REDIRECT)
ipv4_redirect(skb, net, 0, IPPROTO_ICMP);
+
+ return 0;
}
/*
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 2c67af644e64..76a9a5f7a40e 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -121,8 +121,8 @@ static unsigned int ipgre_net_id __read_mostly;
static unsigned int gre_tap_net_id __read_mostly;
static unsigned int erspan_net_id __read_mostly;
-static void ipgre_err(struct sk_buff *skb, u32 info,
- const struct tnl_ptk_info *tpi)
+static int ipgre_err(struct sk_buff *skb, u32 info,
+ const struct tnl_ptk_info *tpi)
{
/* All the routers (except for Linux) return only
@@ -146,17 +146,32 @@ static void ipgre_err(struct sk_buff *skb, u32 info,
unsigned int data_len = 0;
struct ip_tunnel *t;
+ if (tpi->proto == htons(ETH_P_TEB))
+ itn = net_generic(net, gre_tap_net_id);
+ else if (tpi->proto == htons(ETH_P_ERSPAN) ||
+ tpi->proto == htons(ETH_P_ERSPAN2))
+ itn = net_generic(net, erspan_net_id);
+ else
+ itn = net_generic(net, ipgre_net_id);
+
+ iph = (const struct iphdr *)(icmp_hdr(skb) + 1);
+ t = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags,
+ iph->daddr, iph->saddr, tpi->key);
+
+ if (!t)
+ return -ENOENT;
+
switch (type) {
default:
case ICMP_PARAMETERPROB:
- return;
+ return 0;
case ICMP_DEST_UNREACH:
switch (code) {
case ICMP_SR_FAILED:
case ICMP_PORT_UNREACH:
/* Impossible event. */
- return;
+ return 0;
default:
/* All others are translated to HOST_UNREACH.
rfc2003 contains "deep thoughts" about NET_UNREACH,
@@ -168,7 +183,7 @@ static void ipgre_err(struct sk_buff *skb, u32 info,
case ICMP_TIME_EXCEEDED:
if (code != ICMP_EXC_TTL)
- return;
+ return 0;
data_len = icmp_hdr(skb)->un.reserved[1] * 4; /* RFC 4884 4.1 */
break;
@@ -176,40 +191,27 @@ static void ipgre_err(struct sk_buff *skb, u32 info,
break;
}
- if (tpi->proto == htons(ETH_P_TEB))
- itn = net_generic(net, gre_tap_net_id);
- else if (tpi->proto == htons(ETH_P_ERSPAN) ||
- tpi->proto == htons(ETH_P_ERSPAN2))
- itn = net_generic(net, erspan_net_id);
- else
- itn = net_generic(net, ipgre_net_id);
-
- iph = (const struct iphdr *)(icmp_hdr(skb) + 1);
- t = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags,
- iph->daddr, iph->saddr, tpi->key);
-
- if (!t)
- return;
-
#if IS_ENABLED(CONFIG_IPV6)
if (tpi->proto == htons(ETH_P_IPV6) &&
!ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4 + tpi->hdr_len,
type, data_len))
- return;
+ return 0;
#endif
if (t->parms.iph.daddr == 0 ||
ipv4_is_multicast(t->parms.iph.daddr))
- return;
+ return 0;
if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
- return;
+ return 0;
if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO))
t->err_count++;
else
t->err_count = 1;
t->err_time = jiffies;
+
+ return 0;
}
static void gre_err(struct sk_buff *skb, u32 info)
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index e65287c27e3d..57c5dd283a2c 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -140,6 +140,13 @@ static int ipip_err(struct sk_buff *skb, u32 info)
struct ip_tunnel *t;
int err = 0;
+ t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
+ iph->daddr, iph->saddr, 0);
+ if (!t) {
+ err = -ENOENT;
+ goto out;
+ }
+
switch (type) {
case ICMP_DEST_UNREACH:
switch (code) {
@@ -167,13 +174,6 @@ static int ipip_err(struct sk_buff *skb, u32 info)
goto out;
}
- t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
- iph->daddr, iph->saddr, 0);
- if (!t) {
- err = -ENOENT;
- goto out;
- }
-
if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
ipv4_update_pmtu(skb, net, info, t->parms.link, iph->protocol);
goto out;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index de47038afdf0..a336787d75e5 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -423,7 +423,7 @@ EXPORT_SYMBOL(tcp_req_err);
*
*/
-void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
+int tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
{
const struct iphdr *iph = (const struct iphdr *)icmp_skb->data;
struct tcphdr *th = (struct tcphdr *)(icmp_skb->data + (iph->ihl << 2));
@@ -446,20 +446,21 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
inet_iif(icmp_skb), 0);
if (!sk) {
__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
- return;
+ return -ENOENT;
}
if (sk->sk_state == TCP_TIME_WAIT) {
inet_twsk_put(inet_twsk(sk));
- return;
+ return 0;
}
seq = ntohl(th->seq);
- if (sk->sk_state == TCP_NEW_SYN_RECV)
- return tcp_req_err(sk, seq,
- type == ICMP_PARAMETERPROB ||
- type == ICMP_TIME_EXCEEDED ||
- (type == ICMP_DEST_UNREACH &&
- (code == ICMP_NET_UNREACH ||
- code == ICMP_HOST_UNREACH)));
+ if (sk->sk_state == TCP_NEW_SYN_RECV) {
+ tcp_req_err(sk, seq, type == ICMP_PARAMETERPROB ||
+ type == ICMP_TIME_EXCEEDED ||
+ (type == ICMP_DEST_UNREACH &&
+ (code == ICMP_NET_UNREACH ||
+ code == ICMP_HOST_UNREACH)));
+ return 0;
+ }
bh_lock_sock(sk);
/* If too many ICMPs get dropped on busy
@@ -613,6 +614,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
out:
bh_unlock_sock(sk);
sock_put(sk);
+ return 0;
}
void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr)
diff --git a/net/ipv4/tunnel4.c b/net/ipv4/tunnel4.c
index c0630013c1ae..33bf8e9c8663 100644
--- a/net/ipv4/tunnel4.c
+++ b/net/ipv4/tunnel4.c
@@ -149,34 +149,40 @@ static int tunnelmpls4_rcv(struct sk_buff *skb)
}
#endif
-static void tunnel4_err(struct sk_buff *skb, u32 info)
+static int tunnel4_err(struct sk_buff *skb, u32 info)
{
struct xfrm_tunnel *handler;
for_each_tunnel_rcu(tunnel4_handlers, handler)
if (!handler->err_handler(skb, info))
- break;
+ return 0;
+
+ return -ENOENT;
}
#if IS_ENABLED(CONFIG_IPV6)
-static void tunnel64_err(struct sk_buff *skb, u32 info)
+static int tunnel64_err(struct sk_buff *skb, u32 info)
{
struct xfrm_tunnel *handler;
for_each_tunnel_rcu(tunnel64_handlers, handler)
if (!handler->err_handler(skb, info))
- break;
+ return 0;
+
+ return -ENOENT;
}
#endif
#if IS_ENABLED(CONFIG_MPLS)
-static void tunnelmpls4_err(struct sk_buff *skb, u32 info)
+static int tunnelmpls4_err(struct sk_buff *skb, u32 info)
{
struct xfrm_tunnel *handler;
for_each_tunnel_rcu(tunnelmpls4_handlers, handler)
if (!handler->err_handler(skb, info))
- break;
+ return 0;
+
+ return -ENOENT;
}
#endif
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index ce759b61f6cd..a505ee5eb92c 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -650,7 +650,7 @@ static struct sock *__udp4_lib_err_encap(struct net *net,
* to find the appropriate port.
*/
-void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
+int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
{
struct inet_sock *inet;
const struct iphdr *iph = (const struct iphdr *)skb->data;
@@ -673,7 +673,7 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
if (!sk) {
__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
- return;
+ return -ENOENT;
}
tunnel = true;
}
@@ -731,12 +731,12 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
sk->sk_err = err;
sk->sk_error_report(sk);
out:
- return;
+ return 0;
}
-void udp_err(struct sk_buff *skb, u32 info)
+int udp_err(struct sk_buff *skb, u32 info)
{
- __udp4_lib_err(skb, info, &udp_table);
+ return __udp4_lib_err(skb, info, &udp_table);
}
/*
diff --git a/net/ipv4/udp_impl.h b/net/ipv4/udp_impl.h
index e7d18b140287..322672655419 100644
--- a/net/ipv4/udp_impl.h
+++ b/net/ipv4/udp_impl.h
@@ -7,7 +7,7 @@
#include <net/inet_common.h>
int __udp4_lib_rcv(struct sk_buff *, struct udp_table *, int);
-void __udp4_lib_err(struct sk_buff *, u32, struct udp_table *);
+int __udp4_lib_err(struct sk_buff *, u32, struct udp_table *);
int udp_v4_get_port(struct sock *sk, unsigned short snum);
diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c
index 8545457752fb..39c7f17d916f 100644
--- a/net/ipv4/udplite.c
+++ b/net/ipv4/udplite.c
@@ -25,9 +25,9 @@ static int udplite_rcv(struct sk_buff *skb)
return __udp4_lib_rcv(skb, &udplite_table, IPPROTO_UDPLITE);
}
-static void udplite_err(struct sk_buff *skb, u32 info)
+static int udplite_err(struct sk_buff *skb, u32 info)
{
- __udp4_lib_err(skb, info, &udplite_table);
+ return __udp4_lib_err(skb, info, &udplite_table);
}
static const struct net_protocol udplite_protocol = {
diff --git a/net/ipv4/xfrm4_protocol.c b/net/ipv4/xfrm4_protocol.c
index 8dd0e6ab8606..35c54865dc42 100644
--- a/net/ipv4/xfrm4_protocol.c
+++ b/net/ipv4/xfrm4_protocol.c
@@ -106,13 +106,15 @@ static int xfrm4_esp_rcv(struct sk_buff *skb)
return 0;
}
-static void xfrm4_esp_err(struct sk_buff *skb, u32 info)
+static int xfrm4_esp_err(struct sk_buff *skb, u32 info)
{
struct xfrm4_protocol *handler;
for_each_protocol_rcu(esp4_handlers, handler)
if (!handler->err_handler(skb, info))
- break;
+ return 0;
+
+ return -ENOENT;
}
static int xfrm4_ah_rcv(struct sk_buff *skb)
@@ -132,13 +134,15 @@ static int xfrm4_ah_rcv(struct sk_buff *skb)
return 0;
}
-static void xfrm4_ah_err(struct sk_buff *skb, u32 info)
+static int xfrm4_ah_err(struct sk_buff *skb, u32 info)
{
struct xfrm4_protocol *handler;
for_each_protocol_rcu(ah4_handlers, handler)
if (!handler->err_handler(skb, info))
- break;
+ return 0;
+
+ return -ENOENT;
}
static int xfrm4_ipcomp_rcv(struct sk_buff *skb)
@@ -158,13 +162,15 @@ static int xfrm4_ipcomp_rcv(struct sk_buff *skb)
return 0;
}
-static void xfrm4_ipcomp_err(struct sk_buff *skb, u32 info)
+static int xfrm4_ipcomp_err(struct sk_buff *skb, u32 info)
{
struct xfrm4_protocol *handler;
for_each_protocol_rcu(ipcomp4_handlers, handler)
if (!handler->err_handler(skb, info))
- break;
+ return 0;
+
+ return -ENOENT;
}
static const struct net_protocol esp4_protocol = {
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index c9c53ade55c3..5d7aa2c2770c 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -84,7 +84,7 @@ static inline struct sock *icmpv6_sk(struct net *net)
return net->ipv6.icmp_sk[smp_processor_id()];
}
-static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
/* icmpv6_notify checks 8 bytes can be pulled, icmp6hdr is 8 bytes */
@@ -100,6 +100,8 @@ static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
if (!(type & ICMPV6_INFOMSG_MASK))
if (icmp6->icmp6_type == ICMPV6_ECHO_REQUEST)
ping_err(skb, offset, ntohl(info));
+
+ return 0;
}
static int icmpv6_rcv(struct sk_buff *skb);
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 515adbdba1d2..81b69bcee714 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -423,7 +423,7 @@ static void ip6gre_tunnel_uninit(struct net_device *dev)
}
-static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
struct net *net = dev_net(skb->dev);
@@ -433,13 +433,13 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
if (gre_parse_header(skb, &tpi, NULL, htons(ETH_P_IPV6),
offset) < 0)
- return;
+ return -EINVAL;
ipv6h = (const struct ipv6hdr *)skb->data;
t = ip6gre_tunnel_lookup(skb->dev, &ipv6h->daddr, &ipv6h->saddr,
tpi.key, tpi.proto);
if (!t)
- return;
+ return -ENOENT;
switch (type) {
struct ipv6_tlv_tnl_enc_lim *tel;
@@ -449,14 +449,14 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
t->parms.name);
if (code != ICMPV6_PORT_UNREACH)
break;
- return;
+ return 0;
case ICMPV6_TIME_EXCEED:
if (code == ICMPV6_EXC_HOPLIMIT) {
net_dbg_ratelimited("%s: Too small hop limit or routing loop in tunnel!\n",
t->parms.name);
break;
}
- return;
+ return 0;
case ICMPV6_PARAMPROB:
teli = 0;
if (code == ICMPV6_HDR_FIELD)
@@ -472,14 +472,14 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
net_dbg_ratelimited("%s: Recipient unable to parse tunneled packet!\n",
t->parms.name);
}
- return;
+ return 0;
case ICMPV6_PKT_TOOBIG:
ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
- return;
+ return 0;
case NDISC_REDIRECT:
ip6_redirect(skb, net, skb->dev->ifindex, 0,
sock_net_uid(net, NULL));
- return;
+ return 0;
}
if (time_before(jiffies, t->err_time + IP6TUNNEL_ERR_TIMEO))
@@ -487,6 +487,8 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
else
t->err_count = 1;
t->err_time = jiffies;
+
+ return 0;
}
static int ip6gre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi)
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 03e6b7a2bc53..a3f559162521 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -349,7 +349,7 @@ static void tcp_v6_mtu_reduced(struct sock *sk)
}
}
-static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
@@ -371,17 +371,19 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
if (!sk) {
__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
ICMP6_MIB_INERRORS);
- return;
+ return -ENOENT;
}
if (sk->sk_state == TCP_TIME_WAIT) {
inet_twsk_put(inet_twsk(sk));
- return;
+ return 0;
}
seq = ntohl(th->seq);
fatal = icmpv6_err_convert(type, code, &err);
- if (sk->sk_state == TCP_NEW_SYN_RECV)
- return tcp_req_err(sk, seq, fatal);
+ if (sk->sk_state == TCP_NEW_SYN_RECV) {
+ tcp_req_err(sk, seq, fatal);
+ return 0;
+ }
bh_lock_sock(sk);
if (sock_owned_by_user(sk) && type != ICMPV6_PKT_TOOBIG)
@@ -467,6 +469,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
out:
bh_unlock_sock(sk);
sock_put(sk);
+ return 0;
}
diff --git a/net/ipv6/tunnel6.c b/net/ipv6/tunnel6.c
index dae25cad05cd..1991dede7367 100644
--- a/net/ipv6/tunnel6.c
+++ b/net/ipv6/tunnel6.c
@@ -134,24 +134,28 @@ static int tunnel46_rcv(struct sk_buff *skb)
return 0;
}
-static void tunnel6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int tunnel6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
struct xfrm6_tunnel *handler;
for_each_tunnel_rcu(tunnel6_handlers, handler)
if (!handler->err_handler(skb, opt, type, code, offset, info))
- break;
+ return 0;
+
+ return -ENOENT;
}
-static void tunnel46_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int tunnel46_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
struct xfrm6_tunnel *handler;
for_each_tunnel_rcu(tunnel46_handlers, handler)
if (!handler->err_handler(skb, opt, type, code, offset, info))
- break;
+ return 0;
+
+ return -ENOENT;
}
static const struct inet6_protocol tunnel6_protocol = {
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 1216c920f945..61316ec48b51 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -517,9 +517,9 @@ static struct sock *__udp6_lib_err_encap(struct net *net,
return sk;
}
-void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
- u8 type, u8 code, int offset, __be32 info,
- struct udp_table *udptable)
+int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+ u8 type, u8 code, int offset, __be32 info,
+ struct udp_table *udptable)
{
struct ipv6_pinfo *np;
const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
@@ -544,7 +544,7 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
if (!sk) {
__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
ICMP6_MIB_INERRORS);
- return;
+ return -ENOENT;
}
tunnel = true;
}
@@ -583,7 +583,7 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
sk->sk_err = err;
sk->sk_error_report(sk);
out:
- return;
+ return 0;
}
static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
@@ -614,11 +614,11 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
return 0;
}
-static __inline__ void udpv6_err(struct sk_buff *skb,
- struct inet6_skb_parm *opt, u8 type,
- u8 code, int offset, __be32 info)
+static __inline__ int udpv6_err(struct sk_buff *skb,
+ struct inet6_skb_parm *opt, u8 type,
+ u8 code, int offset, __be32 info)
{
- __udp6_lib_err(skb, opt, type, code, offset, info, &udp_table);
+ return __udp6_lib_err(skb, opt, type, code, offset, info, &udp_table);
}
static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
diff --git a/net/ipv6/udp_impl.h b/net/ipv6/udp_impl.h
index 7903e21c178b..5730e6503cb4 100644
--- a/net/ipv6/udp_impl.h
+++ b/net/ipv6/udp_impl.h
@@ -9,8 +9,8 @@
#include <net/transp_v6.h>
int __udp6_lib_rcv(struct sk_buff *, struct udp_table *, int);
-void __udp6_lib_err(struct sk_buff *, struct inet6_skb_parm *, u8, u8, int,
- __be32, struct udp_table *);
+int __udp6_lib_err(struct sk_buff *, struct inet6_skb_parm *, u8, u8, int,
+ __be32, struct udp_table *);
int udp_v6_get_port(struct sock *sk, unsigned short snum);
diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c
index 5000ad6878e6..a125aebc29e5 100644
--- a/net/ipv6/udplite.c
+++ b/net/ipv6/udplite.c
@@ -20,11 +20,12 @@ static int udplitev6_rcv(struct sk_buff *skb)
return __udp6_lib_rcv(skb, &udplite_table, IPPROTO_UDPLITE);
}
-static void udplitev6_err(struct sk_buff *skb,
+static int udplitev6_err(struct sk_buff *skb,
struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
- __udp6_lib_err(skb, opt, type, code, offset, info, &udplite_table);
+ return __udp6_lib_err(skb, opt, type, code, offset, info,
+ &udplite_table);
}
static const struct inet6_protocol udplitev6_protocol = {
diff --git a/net/ipv6/xfrm6_protocol.c b/net/ipv6/xfrm6_protocol.c
index b2dc8ce49378..cc979b702c89 100644
--- a/net/ipv6/xfrm6_protocol.c
+++ b/net/ipv6/xfrm6_protocol.c
@@ -80,14 +80,16 @@ static int xfrm6_esp_rcv(struct sk_buff *skb)
return 0;
}
-static void xfrm6_esp_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int xfrm6_esp_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
struct xfrm6_protocol *handler;
for_each_protocol_rcu(esp6_handlers, handler)
if (!handler->err_handler(skb, opt, type, code, offset, info))
- break;
+ return 0;
+
+ return -ENOENT;
}
static int xfrm6_ah_rcv(struct sk_buff *skb)
@@ -107,14 +109,16 @@ static int xfrm6_ah_rcv(struct sk_buff *skb)
return 0;
}
-static void xfrm6_ah_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int xfrm6_ah_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
struct xfrm6_protocol *handler;
for_each_protocol_rcu(ah6_handlers, handler)
if (!handler->err_handler(skb, opt, type, code, offset, info))
- break;
+ return 0;
+
+ return -ENOENT;
}
static int xfrm6_ipcomp_rcv(struct sk_buff *skb)
@@ -134,14 +138,16 @@ static int xfrm6_ipcomp_rcv(struct sk_buff *skb)
return 0;
}
-static void xfrm6_ipcomp_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int xfrm6_ipcomp_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
struct xfrm6_protocol *handler;
for_each_protocol_rcu(ipcomp6_handlers, handler)
if (!handler->err_handler(skb, opt, type, code, offset, info))
- break;
+ return 0;
+
+ return -ENOENT;
}
static const struct inet6_protocol esp6_protocol = {
diff --git a/net/sctp/input.c b/net/sctp/input.c
index 5c36a99882ed..7ab08a5b36dc 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -574,7 +574,7 @@ void sctp_err_finish(struct sock *sk, struct sctp_transport *t)
* is probably better.
*
*/
-void sctp_v4_err(struct sk_buff *skb, __u32 info)
+int sctp_v4_err(struct sk_buff *skb, __u32 info)
{
const struct iphdr *iph = (const struct iphdr *)skb->data;
const int ihlen = iph->ihl * 4;
@@ -599,7 +599,7 @@ void sctp_v4_err(struct sk_buff *skb, __u32 info)
skb->transport_header = savesctp;
if (!sk) {
__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
- return;
+ return -ENOENT;
}
/* Warning: The sock lock is held. Remember to call
* sctp_err_finish!
@@ -653,6 +653,7 @@ void sctp_v4_err(struct sk_buff *skb, __u32 info)
out_unlock:
sctp_err_finish(sk, transport);
+ return 0;
}
/*
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index fc6c5e4bffa5..6e27c62646e9 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -138,7 +138,7 @@ static struct notifier_block sctp_inet6addr_notifier = {
};
/* ICMP error handler. */
-static void sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+static int sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
struct inet6_dev *idev;
@@ -147,7 +147,7 @@ static void sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
struct sctp_transport *transport;
struct ipv6_pinfo *np;
__u16 saveip, savesctp;
- int err;
+ int err, ret = 0;
struct net *net = dev_net(skb->dev);
idev = in6_dev_get(skb->dev);
@@ -163,6 +163,7 @@ static void sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
skb->transport_header = savesctp;
if (!sk) {
__ICMP6_INC_STATS(net, idev, ICMP6_MIB_INERRORS);
+ ret = -ENOENT;
goto out;
}
@@ -202,6 +203,8 @@ static void sctp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
out:
if (likely(idev != NULL))
in6_dev_put(idev);
+
+ return ret;
}
static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport)
--
2.19.1
^ permalink raw reply related
* [PATCH net-next v2 09/11] udp: Support for error handlers of tunnels with arbitrary destination port
From: Stefano Brivio @ 2018-11-08 11:19 UTC (permalink / raw)
To: David S. Miller
Cc: Sabrina Dubroca, Xin Long, Stephen Hemminger, Jiri Benc,
David Ahern, netdev
In-Reply-To: <cover.1541675666.git.sbrivio@redhat.com>
ICMP error handling is currently not possible for UDP tunnels not
employing a receiving socket with local destination port matching the
remote one, because we have no way to look them up.
Add an err_handler tunnel encapsulation operation that can be exported by
tunnels in order to pass the error to the protocol implementing the
encapsulation. We can't easily use a lookup function as we did for VXLAN
and GENEVE, as protocol error handlers, which would be in turn called by
implementations of this new operation, handle the errors themselves,
together with the tunnel lookup.
Without a socket, we can't be sure which encapsulation error handler is
the appropriate one: encapsulation handlers (the ones for FoU and GUE
introduced in the next patch, e.g.) will need to check the new error codes
returned by protocol handlers to figure out if errors match the given
encapsulation, and, in turn, report this error back, so that we can try
all of them in __udp{4,6}_lib_err_encap_no_sk() until we have a match.
v2:
- Name all arguments in err_handler prototypes (David Miller)
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
---
include/net/ip6_tunnel.h | 2 ++
include/net/ip_tunnels.h | 1 +
net/ipv4/udp.c | 70 +++++++++++++++++++++++++++----------
net/ipv6/udp.c | 75 +++++++++++++++++++++++++++++++---------
4 files changed, 113 insertions(+), 35 deletions(-)
diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index 236e40ba06bf..69b4bcf880c9 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -69,6 +69,8 @@ struct ip6_tnl_encap_ops {
size_t (*encap_hlen)(struct ip_tunnel_encap *e);
int (*build_header)(struct sk_buff *skb, struct ip_tunnel_encap *e,
u8 *protocol, struct flowi6 *fl6);
+ int (*err_handler)(struct sk_buff *skb, struct inet6_skb_parm *opt,
+ u8 type, u8 code, int offset, __be32 info);
};
#ifdef CONFIG_INET
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index b0d022ff6ea1..db6b2218a2ad 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -311,6 +311,7 @@ struct ip_tunnel_encap_ops {
size_t (*encap_hlen)(struct ip_tunnel_encap *e);
int (*build_header)(struct sk_buff *skb, struct ip_tunnel_encap *e,
u8 *protocol, struct flowi4 *fl4);
+ int (*err_handler)(struct sk_buff *skb, u32 info);
};
#define MAX_IPTUN_ENCAP_OPS 8
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index a505ee5eb92c..6f8890c5bc7e 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -105,6 +105,7 @@
#include <net/net_namespace.h>
#include <net/icmp.h>
#include <net/inet_hashtables.h>
+#include <net/ip_tunnels.h>
#include <net/route.h>
#include <net/checksum.h>
#include <net/xfrm.h>
@@ -590,6 +591,26 @@ void udp_encap_enable(void)
}
EXPORT_SYMBOL(udp_encap_enable);
+/* Handler for tunnels with arbitrary destination ports: no socket lookup, go
+ * through error handlers in encapsulations looking for a match.
+ */
+static int __udp4_lib_err_encap_no_sk(struct sk_buff *skb, u32 info)
+{
+ int i;
+
+ for (i = 0; i < MAX_IPTUN_ENCAP_OPS; i++) {
+ int (*handler)(struct sk_buff *skb, u32 info);
+
+ if (!iptun_encaps[i])
+ continue;
+ handler = rcu_dereference(iptun_encaps[i]->err_handler);
+ if (handler && !handler(skb, info))
+ return 0;
+ }
+
+ return -ENOENT;
+}
+
/* Try to match ICMP errors to UDP tunnels by looking up a socket without
* reversing source and destination port: this will match tunnels that force the
* same destination port on both endpoints (e.g. VXLAN, GENEVE). Note that
@@ -597,28 +618,25 @@ EXPORT_SYMBOL(udp_encap_enable);
* different destination ports on endpoints, in this case we won't be able to
* trace ICMP messages back to them.
*
+ * If this doesn't match any socket, probe tunnels with arbitrary destination
+ * ports (e.g. FoU, GUE): there, the receiving socket is useless, as the port
+ * we've sent packets to won't necessarily match the local destination port.
+ *
* Then ask the tunnel implementation to match the error against a valid
* association.
*
- * Return the socket if we have a match.
+ * Return an error if we can't find a match, the socket if we need further
+ * processing, zero otherwise.
*/
static struct sock *__udp4_lib_err_encap(struct net *net,
const struct iphdr *iph,
struct udphdr *uh,
struct udp_table *udptable,
- struct sk_buff *skb)
+ struct sk_buff *skb, u32 info)
{
- int (*lookup)(struct sock *sk, struct sk_buff *skb);
int network_offset, transport_offset;
- struct udp_sock *up;
struct sock *sk;
- sk = __udp4_lib_lookup(net, iph->daddr, uh->source,
- iph->saddr, uh->dest, skb->dev->ifindex, 0,
- udptable, NULL);
- if (!sk)
- return NULL;
-
network_offset = skb_network_offset(skb);
transport_offset = skb_transport_offset(skb);
@@ -628,10 +646,20 @@ static struct sock *__udp4_lib_err_encap(struct net *net,
/* Transport header needs to point to the UDP header */
skb_set_transport_header(skb, iph->ihl << 2);
- up = udp_sk(sk);
- lookup = READ_ONCE(up->encap_err_lookup);
- if (!lookup || lookup(sk, skb))
- sk = NULL;
+ sk = __udp4_lib_lookup(net, iph->daddr, uh->source,
+ iph->saddr, uh->dest, skb->dev->ifindex, 0,
+ udptable, NULL);
+ if (sk) {
+ int (*lookup)(struct sock *sk, struct sk_buff *skb);
+ struct udp_sock *up = udp_sk(sk);
+
+ lookup = READ_ONCE(up->encap_err_lookup);
+ if (!lookup || lookup(sk, skb))
+ sk = NULL;
+ }
+
+ if (!sk)
+ sk = ERR_PTR(__udp4_lib_err_encap_no_sk(skb, info));
skb_set_transport_header(skb, transport_offset);
skb_set_network_header(skb, network_offset);
@@ -668,13 +696,19 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
inet_sdif(skb), udptable, NULL);
if (!sk) {
/* No socket for error: try tunnels before discarding */
- if (static_branch_unlikely(&udp_encap_needed_key))
- sk = __udp4_lib_err_encap(net, iph, uh, udptable, skb);
+ sk = ERR_PTR(-ENOENT);
+ if (static_branch_unlikely(&udp_encap_needed_key)) {
+ sk = __udp4_lib_err_encap(net, iph, uh, udptable, skb,
+ info);
+ if (!sk)
+ return 0;
+ }
- if (!sk) {
+ if (IS_ERR(sk)) {
__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
- return -ENOENT;
+ return PTR_ERR(sk);
}
+
tunnel = true;
}
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 61316ec48b51..0c0cb1611aef 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -45,6 +45,7 @@
#include <net/raw.h>
#include <net/tcp_states.h>
#include <net/ip6_checksum.h>
+#include <net/ip6_tunnel.h>
#include <net/xfrm.h>
#include <net/inet_hashtables.h>
#include <net/inet6_hashtables.h>
@@ -469,6 +470,29 @@ void udpv6_encap_enable(void)
}
EXPORT_SYMBOL(udpv6_encap_enable);
+/* Handler for tunnels with arbitrary destination ports: no socket lookup, go
+ * through error handlers in encapsulations looking for a match.
+ */
+static int __udp6_lib_err_encap_no_sk(struct sk_buff *skb,
+ struct inet6_skb_parm *opt,
+ u8 type, u8 code, int offset, u32 info)
+{
+ int i;
+
+ for (i = 0; i < MAX_IPTUN_ENCAP_OPS; i++) {
+ int (*handler)(struct sk_buff *skb, struct inet6_skb_parm *opt,
+ u8 type, u8 code, int offset, u32 info);
+
+ if (!ip6tun_encaps[i])
+ continue;
+ handler = rcu_dereference(ip6tun_encaps[i]->err_handler);
+ if (handler && !handler(skb, opt, type, code, offset, info))
+ return 0;
+ }
+
+ return -ENOENT;
+}
+
/* Try to match ICMP errors to UDP tunnels by looking up a socket without
* reversing source and destination port: this will match tunnels that force the
* same destination port on both endpoints (e.g. VXLAN, GENEVE). Note that
@@ -476,28 +500,27 @@ EXPORT_SYMBOL(udpv6_encap_enable);
* different destination ports on endpoints, in this case we won't be able to
* trace ICMP messages back to them.
*
+ * If this doesn't match any socket, probe tunnels with arbitrary destination
+ * ports (e.g. FoU, GUE): there, the receiving socket is useless, as the port
+ * we've sent packets to won't necessarily match the local destination port.
+ *
* Then ask the tunnel implementation to match the error against a valid
* association.
*
- * Return the socket if we have a match.
+ * Return an error if we can't find a match, the socket if we need further
+ * processing, zero otherwise.
*/
static struct sock *__udp6_lib_err_encap(struct net *net,
const struct ipv6hdr *hdr, int offset,
struct udphdr *uh,
struct udp_table *udptable,
- struct sk_buff *skb)
+ struct sk_buff *skb,
+ struct inet6_skb_parm *opt,
+ u8 type, u8 code, __be32 info)
{
- int (*lookup)(struct sock *sk, struct sk_buff *skb);
int network_offset, transport_offset;
- struct udp_sock *up;
struct sock *sk;
- sk = __udp6_lib_lookup(net, &hdr->daddr, uh->source,
- &hdr->saddr, uh->dest,
- inet6_iif(skb), 0, udptable, skb);
- if (!sk)
- return NULL;
-
network_offset = skb_network_offset(skb);
transport_offset = skb_transport_offset(skb);
@@ -507,13 +530,26 @@ static struct sock *__udp6_lib_err_encap(struct net *net,
/* Transport header needs to point to the UDP header */
skb_set_transport_header(skb, offset);
- up = udp_sk(sk);
- lookup = READ_ONCE(up->encap_err_lookup);
- if (!lookup || lookup(sk, skb))
- sk = NULL;
+ sk = __udp6_lib_lookup(net, &hdr->daddr, uh->source,
+ &hdr->saddr, uh->dest,
+ inet6_iif(skb), 0, udptable, skb);
+ if (sk) {
+ int (*lookup)(struct sock *sk, struct sk_buff *skb);
+ struct udp_sock *up = udp_sk(sk);
+
+ lookup = READ_ONCE(up->encap_err_lookup);
+ if (!lookup || lookup(sk, skb))
+ sk = NULL;
+ }
+
+ if (!sk) {
+ sk = ERR_PTR(__udp6_lib_err_encap_no_sk(skb, opt, type, code,
+ offset, info));
+ }
skb_set_transport_header(skb, transport_offset);
skb_set_network_header(skb, network_offset);
+
return sk;
}
@@ -536,16 +572,21 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
inet6_iif(skb), inet6_sdif(skb), udptable, skb);
if (!sk) {
/* No socket for error: try tunnels before discarding */
+ sk = ERR_PTR(-ENOENT);
if (static_branch_unlikely(&udpv6_encap_needed_key)) {
sk = __udp6_lib_err_encap(net, hdr, offset, uh,
- udptable, skb);
+ udptable, skb,
+ opt, type, code, info);
+ if (!sk)
+ return 0;
}
- if (!sk) {
+ if (IS_ERR(sk)) {
__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
ICMP6_MIB_INERRORS);
- return -ENOENT;
+ return PTR_ERR(sk);
}
+
tunnel = true;
}
--
2.19.1
^ permalink raw reply related
* [PATCH net-next v2 10/11] fou, fou6: ICMP error handlers for FoU and GUE
From: Stefano Brivio @ 2018-11-08 11:19 UTC (permalink / raw)
To: David S. Miller
Cc: Sabrina Dubroca, Xin Long, Stephen Hemminger, Jiri Benc,
David Ahern, netdev
In-Reply-To: <cover.1541675666.git.sbrivio@redhat.com>
As the destination port in FoU and GUE receiving sockets doesn't
necessarily match the remote destination port, we can't associate errors
to the encapsulating tunnels with a socket lookup -- we need to blindly
try them instead. This means we don't even know if we are handling errors
for FoU or GUE without digging into the packets.
Hence, implement a single handler for both, one for IPv4 and one for IPv6,
that will check whether the packet that generated the ICMP error used a
direct IP encapsulation or if it had a GUE header, and send the error to
the matching protocol handler, if any.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
---
v2: no changes
net/ipv4/fou.c | 68 +++++++++++++++++++++++++++++++++++++++++
net/ipv4/protocol.c | 1 +
net/ipv6/fou6.c | 74 +++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 143 insertions(+)
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 500a59906b87..0d0ad19ecb87 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -3,6 +3,7 @@
#include <linux/socket.h>
#include <linux/skbuff.h>
#include <linux/ip.h>
+#include <linux/icmp.h>
#include <linux/udp.h>
#include <linux/types.h>
#include <linux/kernel.h>
@@ -1003,15 +1004,82 @@ static int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
return 0;
}
+static int gue_err_proto_handler(int proto, struct sk_buff *skb, u32 info)
+{
+ const struct net_protocol *ipprot = rcu_dereference(inet_protos[proto]);
+
+ if (ipprot && ipprot->err_handler) {
+ if (!ipprot->err_handler(skb, info))
+ return 0;
+ }
+
+ return -ENOENT;
+}
+
+static int gue_err(struct sk_buff *skb, u32 info)
+{
+ int transport_offset = skb_transport_offset(skb);
+ struct guehdr *guehdr;
+ size_t optlen;
+ int ret;
+
+ if (skb->len < sizeof(struct udphdr) + sizeof(struct guehdr))
+ return -EINVAL;
+
+ guehdr = (struct guehdr *)&udp_hdr(skb)[1];
+
+ switch (guehdr->version) {
+ case 0: /* Full GUE header present */
+ break;
+ case 1: {
+ /* Direct encasulation of IPv4 or IPv6 */
+ skb_set_transport_header(skb, -(int)sizeof(struct icmphdr));
+
+ switch (((struct iphdr *)guehdr)->version) {
+ case 4:
+ ret = gue_err_proto_handler(IPPROTO_IPIP, skb, info);
+ goto out;
+#if IS_ENABLED(CONFIG_IPV6)
+ case 6:
+ ret = gue_err_proto_handler(IPPROTO_IPV6, skb, info);
+ goto out;
+#endif
+ default:
+ ret = -EOPNOTSUPP;
+ goto out;
+ }
+ }
+ default: /* Undefined version */
+ return -EOPNOTSUPP;
+ }
+
+ if (guehdr->control)
+ return -ENOENT;
+
+ optlen = guehdr->hlen << 2;
+
+ if (validate_gue_flags(guehdr, optlen))
+ return -EINVAL;
+
+ skb_set_transport_header(skb, -(int)sizeof(struct icmphdr));
+ ret = gue_err_proto_handler(guehdr->proto_ctype, skb, info);
+
+out:
+ skb_set_transport_header(skb, transport_offset);
+ return ret;
+}
+
static const struct ip_tunnel_encap_ops fou_iptun_ops = {
.encap_hlen = fou_encap_hlen,
.build_header = fou_build_header,
+ .err_handler = gue_err,
};
static const struct ip_tunnel_encap_ops gue_iptun_ops = {
.encap_hlen = gue_encap_hlen,
.build_header = gue_build_header,
+ .err_handler = gue_err,
};
static int ip_tunnel_encap_add_fou_ops(void)
diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c
index 32a691b7ce2c..92d249e053be 100644
--- a/net/ipv4/protocol.c
+++ b/net/ipv4/protocol.c
@@ -29,6 +29,7 @@
#include <net/protocol.h>
struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS] __read_mostly;
+EXPORT_SYMBOL(inet_protos);
const struct net_offload __rcu *inet_offloads[MAX_INET_PROTOS] __read_mostly;
EXPORT_SYMBOL(inet_offloads);
diff --git a/net/ipv6/fou6.c b/net/ipv6/fou6.c
index 6de3c04b0f30..bd675c61deb1 100644
--- a/net/ipv6/fou6.c
+++ b/net/ipv6/fou6.c
@@ -4,6 +4,7 @@
#include <linux/skbuff.h>
#include <linux/ip.h>
#include <linux/udp.h>
+#include <linux/icmpv6.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <net/fou.h>
@@ -69,14 +70,87 @@ static int gue6_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
return 0;
}
+static int gue6_err_proto_handler(int proto, struct sk_buff *skb,
+ struct inet6_skb_parm *opt,
+ u8 type, u8 code, int offset, u32 info)
+{
+ const struct inet6_protocol *ipprot;
+
+ ipprot = rcu_dereference(inet6_protos[proto]);
+ if (ipprot && ipprot->err_handler) {
+ if (!ipprot->err_handler(skb, opt, type, code, offset, info))
+ return 0;
+ }
+
+ return -ENOENT;
+}
+
+static int gue6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+ u8 type, u8 code, int offset, __be32 info)
+{
+ int transport_offset = skb_transport_offset(skb);
+ struct guehdr *guehdr;
+ size_t optlen;
+ int ret;
+
+ if (skb->len < sizeof(struct udphdr) + sizeof(struct guehdr))
+ return -EINVAL;
+
+ guehdr = (struct guehdr *)&udp_hdr(skb)[1];
+
+ switch (guehdr->version) {
+ case 0: /* Full GUE header present */
+ break;
+ case 1: {
+ /* Direct encasulation of IPv4 or IPv6 */
+ skb_set_transport_header(skb, -(int)sizeof(struct icmp6hdr));
+
+ switch (((struct iphdr *)guehdr)->version) {
+ case 4:
+ ret = gue6_err_proto_handler(IPPROTO_IPIP, skb, opt,
+ type, code, offset, info);
+ goto out;
+ case 6:
+ ret = gue6_err_proto_handler(IPPROTO_IPV6, skb, opt,
+ type, code, offset, info);
+ goto out;
+ default:
+ ret = -EOPNOTSUPP;
+ goto out;
+ }
+ }
+ default: /* Undefined version */
+ return -EOPNOTSUPP;
+ }
+
+ if (guehdr->control)
+ return -ENOENT;
+
+ optlen = guehdr->hlen << 2;
+
+ if (validate_gue_flags(guehdr, optlen))
+ return -EINVAL;
+
+ skb_set_transport_header(skb, -(int)sizeof(struct icmp6hdr));
+ ret = gue6_err_proto_handler(guehdr->proto_ctype, skb,
+ opt, type, code, offset, info);
+
+out:
+ skb_set_transport_header(skb, transport_offset);
+ return ret;
+}
+
+
static const struct ip6_tnl_encap_ops fou_ip6tun_ops = {
.encap_hlen = fou_encap_hlen,
.build_header = fou6_build_header,
+ .err_handler = gue6_err,
};
static const struct ip6_tnl_encap_ops gue_ip6tun_ops = {
.encap_hlen = gue_encap_hlen,
.build_header = gue6_build_header,
+ .err_handler = gue6_err,
};
static int ip6_tnl_encap_add_fou_ops(void)
--
2.19.1
^ permalink raw reply related
* [PATCH net-next v2 11/11] selftests: pmtu: Introduce FoU and GUE PMTU exceptions tests
From: Stefano Brivio @ 2018-11-08 11:19 UTC (permalink / raw)
To: David S. Miller
Cc: Sabrina Dubroca, Xin Long, Stephen Hemminger, Jiri Benc,
David Ahern, netdev
In-Reply-To: <cover.1541675666.git.sbrivio@redhat.com>
Introduce eight tests, for FoU and GUE, with IPv4 and IPv6 payload,
on IPv4 and IPv6 transport, that check that PMTU exceptions are created
with the right value when exceeding the MTU on a link of the path.
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
---
v2: no changes
tools/testing/selftests/net/pmtu.sh | 179 ++++++++++++++++++++++++++++
1 file changed, 179 insertions(+)
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 14d20782ccb7..e2c94e47707c 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -59,6 +59,14 @@
# Same as pmtu_ipv6_vxlan6_exception, but using a GENEVE tunnel instead of
# VXLAN
#
+# - pmtu_ipv{4,6}_fou{4,6}_exception
+# Same as pmtu_ipv4_vxlan4, but using a direct IPv4/IPv6 encapsulation
+# (FoU) over IPv4/IPv6, instead of VXLAN
+#
+# - pmtu_ipv{4,6}_fou{4,6}_exception
+# Same as pmtu_ipv4_vxlan4, but using a generic UDP IPv4/IPv6
+# encapsulation (GUE) over IPv4/IPv6, instead of VXLAN
+#
# - pmtu_vti4_exception
# Set up vti tunnel on top of veth, with xfrm states and policies, in two
# namespaces with matching endpoints. Check that route exception is not
@@ -113,6 +121,14 @@ tests="
pmtu_ipv6_geneve4_exception IPv6 over geneve4: PMTU exceptions
pmtu_ipv4_geneve6_exception IPv4 over geneve6: PMTU exceptions
pmtu_ipv6_geneve6_exception IPv6 over geneve6: PMTU exceptions
+ pmtu_ipv4_fou4_exception IPv4 over fou4: PMTU exceptions
+ pmtu_ipv6_fou4_exception IPv6 over fou4: PMTU exceptions
+ pmtu_ipv4_fou6_exception IPv4 over fou6: PMTU exceptions
+ pmtu_ipv6_fou6_exception IPv6 over fou6: PMTU exceptions
+ pmtu_ipv4_gue4_exception IPv4 over gue4: PMTU exceptions
+ pmtu_ipv6_gue4_exception IPv6 over gue4: PMTU exceptions
+ pmtu_ipv4_gue6_exception IPv4 over gue6: PMTU exceptions
+ pmtu_ipv6_gue6_exception IPv6 over gue6: PMTU exceptions
pmtu_vti6_exception vti6: PMTU exceptions
pmtu_vti4_exception vti4: PMTU exceptions
pmtu_vti4_default_mtu vti4: default MTU assignment
@@ -200,6 +216,89 @@ nsname() {
eval echo \$NS_$1
}
+setup_fou_or_gue() {
+ outer="${1}"
+ inner="${2}"
+ encap="${3}"
+
+ if [ "${outer}" = "4" ]; then
+ modprobe fou || return 2
+ a_addr="${prefix4}.${a_r1}.1"
+ b_addr="${prefix4}.${b_r1}.1"
+ if [ "${inner}" = "4" ]; then
+ type="ipip"
+ ipproto="4"
+ else
+ type="sit"
+ ipproto="41"
+ fi
+ else
+ modprobe fou6 || return 2
+ a_addr="${prefix6}:${a_r1}::1"
+ b_addr="${prefix6}:${b_r1}::1"
+ if [ "${inner}" = "4" ]; then
+ type="ip6tnl"
+ mode="mode ipip6"
+ ipproto="4 -6"
+ else
+ type="ip6tnl"
+ mode="mode ip6ip6"
+ ipproto="41 -6"
+ fi
+ fi
+
+ ${ns_a} ip fou add port 5555 ipproto ${ipproto} || return 2
+ ${ns_a} ip link add ${encap}_a type ${type} ${mode} local ${a_addr} remote ${b_addr} encap ${encap} encap-sport auto encap-dport 5556 || return 2
+
+ ${ns_b} ip fou add port 5556 ipproto ${ipproto}
+ ${ns_b} ip link add ${encap}_b type ${type} ${mode} local ${b_addr} remote ${a_addr} encap ${encap} encap-sport auto encap-dport 5555
+
+ if [ "${inner}" = "4" ]; then
+ ${ns_a} ip addr add ${tunnel4_a_addr}/${tunnel4_mask} dev ${encap}_a
+ ${ns_b} ip addr add ${tunnel4_b_addr}/${tunnel4_mask} dev ${encap}_b
+ else
+ ${ns_a} ip addr add ${tunnel6_a_addr}/${tunnel6_mask} dev ${encap}_a
+ ${ns_b} ip addr add ${tunnel6_b_addr}/${tunnel6_mask} dev ${encap}_b
+ fi
+
+ ${ns_a} ip link set ${encap}_a up
+ ${ns_b} ip link set ${encap}_b up
+
+ sleep 1
+}
+
+setup_fou44() {
+ setup_fou_or_gue 4 4 fou
+}
+
+setup_fou46() {
+ setup_fou_or_gue 4 6 fou
+}
+
+setup_fou64() {
+ setup_fou_or_gue 6 4 fou
+}
+
+setup_fou66() {
+ setup_fou_or_gue 6 6 fou
+}
+
+setup_gue44() {
+ setup_fou_or_gue 4 4 gue
+}
+
+setup_gue46() {
+ setup_fou_or_gue 4 6 gue
+}
+
+setup_gue64() {
+ setup_fou_or_gue 6 4 gue
+}
+
+setup_gue66() {
+ setup_fou_or_gue 6 6 gue
+}
+
setup_namespaces() {
for n in ${NS_A} ${NS_B} ${NS_R1} ${NS_R2}; do
ip netns add ${n} || return 1
@@ -627,6 +726,86 @@ test_pmtu_ipv6_geneve6_exception() {
test_pmtu_ipvX_over_vxlanY_or_geneveY_exception geneve 6 6
}
+test_pmtu_ipvX_over_fouY_or_gueY() {
+ inner_family=${1}
+ outer_family=${2}
+ encap=${3}
+ ll_mtu=4000
+
+ setup namespaces routing ${encap}${outer_family}${inner_family} || return 2
+ trace "${ns_a}" ${encap}_a "${ns_b}" ${encap}_b \
+ "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \
+ "${ns_b}" veth_B-R1 "${ns_r1}" veth_R1-B
+
+ if [ ${inner_family} -eq 4 ]; then
+ ping=ping
+ dst=${tunnel4_b_addr}
+ else
+ ping=${ping6}
+ dst=${tunnel6_b_addr}
+ fi
+
+ if [ "${encap}" = "gue" ]; then
+ encap_overhead=4
+ else
+ encap_overhead=0
+ fi
+
+ if [ ${outer_family} -eq 4 ]; then
+ # IPv4 header UDP header
+ exp_mtu=$((${ll_mtu} - 20 - 8 - ${encap_overhead}))
+ else
+ # IPv6 header Option 4 UDP header
+ exp_mtu=$((${ll_mtu} - 40 - 8 - 8 - ${encap_overhead}))
+ fi
+
+ # Create route exception by exceeding link layer MTU
+ mtu "${ns_a}" veth_A-R1 $((${ll_mtu} + 1000))
+ mtu "${ns_r1}" veth_R1-A $((${ll_mtu} + 1000))
+ mtu "${ns_b}" veth_B-R1 ${ll_mtu}
+ mtu "${ns_r1}" veth_R1-B ${ll_mtu}
+
+ mtu "${ns_a}" ${encap}_a $((${ll_mtu} + 1000))
+ mtu "${ns_b}" ${encap}_b $((${ll_mtu} + 1000))
+ ${ns_a} ${ping} -q -M want -i 0.1 -w 2 -s $((${ll_mtu} + 500)) ${dst} > /dev/null
+
+ # Check that exception was created
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${dst})"
+ check_pmtu_value ${exp_mtu} "${pmtu}" "exceeding link layer MTU on ${encap} interface"
+}
+
+test_pmtu_ipv4_fou4_exception() {
+ test_pmtu_ipvX_over_fouY_or_gueY 4 4 fou
+}
+
+test_pmtu_ipv6_fou4_exception() {
+ test_pmtu_ipvX_over_fouY_or_gueY 6 4 fou
+}
+
+test_pmtu_ipv4_fou6_exception() {
+ test_pmtu_ipvX_over_fouY_or_gueY 4 6 fou
+}
+
+test_pmtu_ipv6_fou6_exception() {
+ test_pmtu_ipvX_over_fouY_or_gueY 6 6 fou
+}
+
+test_pmtu_ipv4_gue4_exception() {
+ test_pmtu_ipvX_over_fouY_or_gueY 4 4 gue
+}
+
+test_pmtu_ipv6_gue4_exception() {
+ test_pmtu_ipvX_over_fouY_or_gueY 6 4 gue
+}
+
+test_pmtu_ipv4_gue6_exception() {
+ test_pmtu_ipvX_over_fouY_or_gueY 4 6 gue
+}
+
+test_pmtu_ipv6_gue6_exception() {
+ test_pmtu_ipvX_over_fouY_or_gueY 6 6 gue
+}
+
test_pmtu_vti4_exception() {
setup namespaces veth vti4 xfrm4 || return 2
trace "${ns_a}" veth_a "${ns_b}" veth_b \
--
2.19.1
^ permalink raw reply related
* [PATCH iproute2 net-next v2 0/2] Add DF configuration for VXLAN and GENEVE link types
From: Stefano Brivio @ 2018-11-08 11:21 UTC (permalink / raw)
To: David Ahern; +Cc: Stephen Hemminger, netdev
This series adds configuration of the DF bit in outgoing IPv4 packets for
VXLAN and GENEVE link types.
Stefano Brivio (2):
iplink_vxlan: Add DF configuration
iplink_geneve: Add DF configuration
include/uapi/linux/if_link.h | 18 ++++++++++++++++++
ip/iplink_geneve.c | 29 +++++++++++++++++++++++++++++
ip/iplink_vxlan.c | 29 +++++++++++++++++++++++++++++
man/man8/ip-link.8.in | 28 ++++++++++++++++++++++++++++
4 files changed, 104 insertions(+)
--
2.19.1
^ permalink raw reply
* [PATCH iproute2 net-next v2 1/2] iplink_vxlan: Add DF configuration
From: Stefano Brivio @ 2018-11-08 11:21 UTC (permalink / raw)
To: David Ahern; +Cc: Stephen Hemminger, netdev
In-Reply-To: <cover.1541641480.git.sbrivio@redhat.com>
Allow to set the DF bit behaviour for outgoing IPv4 packets: it can be
always on, inherited from the inner header, or, by default, always off,
which is the current behaviour.
v2:
- Indicate in the man page what DF refers to, using RFC 791 wording
(David Ahern)
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
---
include/uapi/linux/if_link.h | 9 +++++++++
ip/iplink_vxlan.c | 29 +++++++++++++++++++++++++++++
man/man8/ip-link.8.in | 14 ++++++++++++++
3 files changed, 52 insertions(+)
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 9c254603ebda..4caf683ce546 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -530,6 +530,7 @@ enum {
IFLA_VXLAN_LABEL,
IFLA_VXLAN_GPE,
IFLA_VXLAN_TTL_INHERIT,
+ IFLA_VXLAN_DF,
__IFLA_VXLAN_MAX
};
#define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1)
@@ -539,6 +540,14 @@ struct ifla_vxlan_port_range {
__be16 high;
};
+enum ifla_vxlan_df {
+ VXLAN_DF_UNSET = 0,
+ VXLAN_DF_SET,
+ VXLAN_DF_INHERIT,
+ __VXLAN_DF_END,
+ VXLAN_DF_MAX = __VXLAN_DF_END - 1,
+};
+
/* GENEVE section */
enum {
IFLA_GENEVE_UNSPEC,
diff --git a/ip/iplink_vxlan.c b/ip/iplink_vxlan.c
index 7fc0e2b4eb06..86afbe1334f0 100644
--- a/ip/iplink_vxlan.c
+++ b/ip/iplink_vxlan.c
@@ -31,6 +31,7 @@ static void print_explain(FILE *f)
" [ local ADDR ]\n"
" [ ttl TTL ]\n"
" [ tos TOS ]\n"
+ " [ df DF ]\n"
" [ flowlabel LABEL ]\n"
" [ dev PHYS_DEV ]\n"
" [ dstport PORT ]\n"
@@ -52,6 +53,7 @@ static void print_explain(FILE *f)
" ADDR := { IP_ADDRESS | any }\n"
" TOS := { NUMBER | inherit }\n"
" TTL := { 1..255 | auto | inherit }\n"
+ " DF := { unset | set | inherit }\n"
" LABEL := 0-1048575\n"
);
}
@@ -170,6 +172,22 @@ static int vxlan_parse_opt(struct link_util *lu, int argc, char **argv,
} else
tos = 1;
addattr8(n, 1024, IFLA_VXLAN_TOS, tos);
+ } else if (!matches(*argv, "df")) {
+ enum ifla_vxlan_df df;
+
+ NEXT_ARG();
+ check_duparg(&attrs, IFLA_VXLAN_DF, "df", *argv);
+ if (strcmp(*argv, "unset") == 0)
+ df = VXLAN_DF_UNSET;
+ else if (strcmp(*argv, "set") == 0)
+ df = VXLAN_DF_SET;
+ else if (strcmp(*argv, "inherit") == 0)
+ df = VXLAN_DF_INHERIT;
+ else
+ invarg("DF must be 'unset', 'set' or 'inherit'",
+ *argv);
+
+ addattr8(n, 1024, IFLA_VXLAN_DF, df);
} else if (!matches(*argv, "label") ||
!matches(*argv, "flowlabel")) {
__u32 uval;
@@ -538,6 +556,17 @@ static void vxlan_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
print_string(PRINT_FP, NULL, "ttl %s ", "auto");
}
+ if (tb[IFLA_VXLAN_DF]) {
+ enum ifla_vxlan_df df = rta_getattr_u8(tb[IFLA_VXLAN_DF]);
+
+ if (df == VXLAN_DF_UNSET)
+ print_string(PRINT_JSON, "df", "df %s ", "unset");
+ else if (df == VXLAN_DF_SET)
+ print_string(PRINT_ANY, "df", "df %s ", "set");
+ else if (df == VXLAN_DF_INHERIT)
+ print_string(PRINT_ANY, "df", "df %s ", "inherit");
+ }
+
if (tb[IFLA_VXLAN_LABEL]) {
__u32 label = rta_getattr_u32(tb[IFLA_VXLAN_LABEL]);
diff --git a/man/man8/ip-link.8.in b/man/man8/ip-link.8.in
index 5132f514b279..a94cf4f19f1e 100644
--- a/man/man8/ip-link.8.in
+++ b/man/man8/ip-link.8.in
@@ -496,6 +496,8 @@ the following additional arguments are supported:
] [
.BI tos " TOS "
] [
+.BI df " DF "
+] [
.BI flowlabel " FLOWLABEL "
] [
.BI dstport " PORT "
@@ -565,6 +567,18 @@ parameter.
.BI tos " TOS"
- specifies the TOS value to use in outgoing packets.
+.sp
+.BI df " DF"
+- specifies the usage of the Don't Fragment flag (DF) bit in outgoing packets
+with IPv4 headers. The value
+.B inherit
+causes the bit to be copied from the original IP header. The values
+.B unset
+and
+.B set
+cause the bit to be always unset or always set, respectively. By default, the
+bit is not set.
+
.sp
.BI flowlabel " FLOWLABEL"
- specifies the flow label to use in outgoing packets.
--
2.19.1
^ permalink raw reply related
* [PATCH iproute2 net-next v2 2/2] iplink_geneve: Add DF configuration
From: Stefano Brivio @ 2018-11-08 11:21 UTC (permalink / raw)
To: David Ahern; +Cc: Stephen Hemminger, netdev
In-Reply-To: <cover.1541641480.git.sbrivio@redhat.com>
Allow to set the DF bit behaviour for outgoing IPv4 packets: it can be
always on, inherited from the inner header, or, by default, always off,
which is the current behaviour.
v2:
- Indicate in the man page what DF refers to, using RFC 791 wording
(David Ahern)
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
---
include/uapi/linux/if_link.h | 9 +++++++++
ip/iplink_geneve.c | 29 +++++++++++++++++++++++++++++
man/man8/ip-link.8.in | 14 ++++++++++++++
3 files changed, 52 insertions(+)
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 4caf683ce546..183ca7527178 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -563,10 +563,19 @@ enum {
IFLA_GENEVE_UDP_ZERO_CSUM6_RX,
IFLA_GENEVE_LABEL,
IFLA_GENEVE_TTL_INHERIT,
+ IFLA_GENEVE_DF,
__IFLA_GENEVE_MAX
};
#define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1)
+enum ifla_geneve_df {
+ GENEVE_DF_UNSET = 0,
+ GENEVE_DF_SET,
+ GENEVE_DF_INHERIT,
+ __GENEVE_DF_END,
+ GENEVE_DF_MAX = __GENEVE_DF_END - 1,
+};
+
/* PPP section */
enum {
IFLA_PPP_UNSPEC,
diff --git a/ip/iplink_geneve.c b/ip/iplink_geneve.c
index c417842b2a5b..1872b74c5d70 100644
--- a/ip/iplink_geneve.c
+++ b/ip/iplink_geneve.c
@@ -24,6 +24,7 @@ static void print_explain(FILE *f)
" remote ADDR\n"
" [ ttl TTL ]\n"
" [ tos TOS ]\n"
+ " [ df DF ]\n"
" [ flowlabel LABEL ]\n"
" [ dstport PORT ]\n"
" [ [no]external ]\n"
@@ -35,6 +36,7 @@ static void print_explain(FILE *f)
" ADDR := IP_ADDRESS\n"
" TOS := { NUMBER | inherit }\n"
" TTL := { 1..255 | auto | inherit }\n"
+ " DF := { unset | set | inherit }\n"
" LABEL := 0-1048575\n"
);
}
@@ -115,6 +117,22 @@ static int geneve_parse_opt(struct link_util *lu, int argc, char **argv,
tos = uval;
} else
tos = 1;
+ } else if (!matches(*argv, "df")) {
+ enum ifla_geneve_df df;
+
+ NEXT_ARG();
+ check_duparg(&attrs, IFLA_GENEVE_DF, "df", *argv);
+ if (strcmp(*argv, "unset") == 0)
+ df = GENEVE_DF_UNSET;
+ else if (strcmp(*argv, "set") == 0)
+ df = GENEVE_DF_SET;
+ else if (strcmp(*argv, "inherit") == 0)
+ df = GENEVE_DF_INHERIT;
+ else
+ invarg("DF must be 'unset', 'set' or 'inherit'",
+ *argv);
+
+ addattr8(n, 1024, IFLA_GENEVE_DF, df);
} else if (!matches(*argv, "label") ||
!matches(*argv, "flowlabel")) {
__u32 uval;
@@ -287,6 +305,17 @@ static void geneve_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
print_string(PRINT_FP, NULL, "tos %s ", "inherit");
}
+ if (tb[IFLA_GENEVE_DF]) {
+ enum ifla_geneve_df df = rta_getattr_u8(tb[IFLA_GENEVE_DF]);
+
+ if (df == GENEVE_DF_UNSET)
+ print_string(PRINT_JSON, "df", "df %s ", "unset");
+ else if (df == GENEVE_DF_SET)
+ print_string(PRINT_ANY, "df", "df %s ", "set");
+ else if (df == GENEVE_DF_INHERIT)
+ print_string(PRINT_ANY, "df", "df %s ", "inherit");
+ }
+
if (tb[IFLA_GENEVE_LABEL]) {
__u32 label = rta_getattr_u32(tb[IFLA_GENEVE_LABEL]);
diff --git a/man/man8/ip-link.8.in b/man/man8/ip-link.8.in
index a94cf4f19f1e..73d37c190fff 100644
--- a/man/man8/ip-link.8.in
+++ b/man/man8/ip-link.8.in
@@ -1180,6 +1180,8 @@ the following additional arguments are supported:
] [
.BI tos " TOS "
] [
+.BI df " DF "
+] [
.BI flowlabel " FLOWLABEL "
] [
.BI dstport " PORT"
@@ -1212,6 +1214,18 @@ ttl. Default option is "0".
.BI tos " TOS"
- specifies the TOS value to use in outgoing packets.
+.sp
+.BI df " DF"
+- specifies the usage of the Don't Fragment flag (DF) bit in outgoing packets
+with IPv4 headers. The value
+.B inherit
+causes the bit to be copied from the original IP header. The values
+.B unset
+and
+.B set
+cause the bit to be always unset or always set, respectively. By default, the
+bit is not set.
+
.sp
.BI flowlabel " FLOWLABEL"
- specifies the flow label to use in outgoing packets.
--
2.19.1
^ permalink raw reply related
* RE: [PATCH v2 2/3] dt-bindings: can: rcar_can: Add r8a774a1 support
From: Fabrizio Castro @ 2018-11-08 11:25 UTC (permalink / raw)
To: Fabrizio Castro, Wolfgang Grandegger, Marc Kleine-Budde,
Rob Herring, Mark Rutland
Cc: David S. Miller, Sergei Shtylyov, linux-can@vger.kernel.org,
linux-kernel@vger.kernel.org, netdev@vger.kernel.org,
devicetree@vger.kernel.org, Simon Horman, Geert Uytterhoeven,
Chris Paterson, Biju Das, linux-renesas-soc@vger.kernel.org
In-Reply-To: <1536576195-11520-3-git-send-email-fabrizio.castro@bp.renesas.com>
Dear All,
Who is the best person to take this patch?
Thanks,
Fab
> From: Fabrizio Castro <fabrizio.castro@bp.renesas.com>
> Sent: 10 September 2018 11:43
> Subject: [PATCH v2 2/3] dt-bindings: can: rcar_can: Add r8a774a1 support
>
> Document RZ/G2M (r8a774a1) SoC specific bindings.
>
> Signed-off-by: Fabrizio Castro <fabrizio.castro@bp.renesas.com>
> Signed-off-by: Chris Paterson <Chris.Paterson2@renesas.com>
> Reviewed-by: Biju Das <biju.das@bp.renesas.com>
> ---
> v1->v2:
> * dropped "renesas,rzg-gen2-can" and fixed "clocks" property description
> as per Geert's comments.
>
> This patch applies on top of next-20180910.
>
> Documentation/devicetree/bindings/net/can/rcar_can.txt | 18 +++++++++++++-----
> 1 file changed, 13 insertions(+), 5 deletions(-)
>
> diff --git a/Documentation/devicetree/bindings/net/can/rcar_can.txt b/Documentation/devicetree/bindings/net/can/rcar_can.txt
> index 94a7f33..f3b160c 100644
> --- a/Documentation/devicetree/bindings/net/can/rcar_can.txt
> +++ b/Documentation/devicetree/bindings/net/can/rcar_can.txt
> @@ -4,6 +4,7 @@ Renesas R-Car CAN controller Device Tree Bindings
> Required properties:
> - compatible: "renesas,can-r8a7743" if CAN controller is a part of R8A7743 SoC.
> "renesas,can-r8a7745" if CAN controller is a part of R8A7745 SoC.
> + "renesas,can-r8a774a1" if CAN controller is a part of R8A774A1 SoC.
> "renesas,can-r8a7778" if CAN controller is a part of R8A7778 SoC.
> "renesas,can-r8a7779" if CAN controller is a part of R8A7779 SoC.
> "renesas,can-r8a7790" if CAN controller is a part of R8A7790 SoC.
> @@ -16,15 +17,21 @@ Required properties:
> "renesas,rcar-gen1-can" for a generic R-Car Gen1 compatible device.
> "renesas,rcar-gen2-can" for a generic R-Car Gen2 or RZ/G1
> compatible device.
> - "renesas,rcar-gen3-can" for a generic R-Car Gen3 compatible device.
> + "renesas,rcar-gen3-can" for a generic R-Car Gen3 or RZ/G2
> + compatible device.
> When compatible with the generic version, nodes must list the
> SoC-specific version corresponding to the platform first
> followed by the generic version.
>
> - reg: physical base address and size of the R-Car CAN register map.
> - interrupts: interrupt specifier for the sole interrupt.
> -- clocks: phandles and clock specifiers for 3 CAN clock inputs.
> -- clock-names: 3 clock input name strings: "clkp1", "clkp2", "can_clk".
> +- clocks: phandles and clock specifiers for 2 CAN clock inputs for RZ/G2
> + devices.
> + phandles and clock specifiers for 3 CAN clock inputs for every other
> + SoC.
> +- clock-names: 2 clock input name strings for RZ/G2: "clkp1", "can_clk".
> + 3 clock input name strings for every other SoC: "clkp1", "clkp2",
> + "can_clk".
> - pinctrl-0: pin control group to be used for this controller.
> - pinctrl-names: must be "default".
>
> @@ -41,8 +48,9 @@ using the below properties:
> Optional properties:
> - renesas,can-clock-select: R-Car CAN Clock Source Select. Valid values are:
> <0x0> (default) : Peripheral clock (clkp1)
> - <0x1> : Peripheral clock (clkp2)
> - <0x3> : Externally input clock
> + <0x1> : Peripheral clock (clkp2) (not supported by
> + RZ/G2 devices)
> + <0x3> : External input clock
>
> Example
> -------
> --
> 2.7.4
Renesas Electronics Europe Ltd, Dukes Meadow, Millboard Road, Bourne End, Buckinghamshire, SL8 5FH, UK. Registered in England & Wales under Registered No. 04586709.
^ permalink raw reply
* [PATCH v2] net: phy: leds: Don't make our own link speed names
From: Kyle Roeschley @ 2018-11-08 21:03 UTC (permalink / raw)
To: Andrew Lunn, Florian Fainelli
Cc: David S . Miller, netdev, linux-kernel, Kyle Roeschley
The phy core provides a handy phy_speed_to_str() helper, so use that
instead of doing our own formatting of the different known link speeds.
To do this, increase PHY_LED_TRIGGER_SPEED_SUFFIX_SIZE to 11 so we can fit
'Unsupported' if necessary.
Signed-off-by: Kyle Roeschley <kyle.roeschley@ni.com>
---
v2: Increase PHY_LED_TRIGGER_SPEED_SUFFIX_SIZE to fit 'Unsupported'.
drivers/net/phy/phy_led_triggers.c | 13 +------------
include/linux/phy_led_triggers.h | 2 +-
2 files changed, 2 insertions(+), 13 deletions(-)
diff --git a/drivers/net/phy/phy_led_triggers.c b/drivers/net/phy/phy_led_triggers.c
index 491efc1bf5c4..2827eb413c9c 100644
--- a/drivers/net/phy/phy_led_triggers.c
+++ b/drivers/net/phy/phy_led_triggers.c
@@ -77,20 +77,9 @@ static int phy_led_trigger_register(struct phy_device *phy,
struct phy_led_trigger *plt,
unsigned int speed)
{
- char name_suffix[PHY_LED_TRIGGER_SPEED_SUFFIX_SIZE];
-
plt->speed = speed;
-
- if (speed < SPEED_1000)
- snprintf(name_suffix, sizeof(name_suffix), "%dMbps", speed);
- else if (speed == SPEED_2500)
- snprintf(name_suffix, sizeof(name_suffix), "2.5Gbps");
- else
- snprintf(name_suffix, sizeof(name_suffix), "%dGbps",
- DIV_ROUND_CLOSEST(speed, 1000));
-
phy_led_trigger_format_name(phy, plt->name, sizeof(plt->name),
- name_suffix);
+ phy_speed_to_str(speed));
plt->trigger.name = plt->name;
return led_trigger_register(&plt->trigger);
diff --git a/include/linux/phy_led_triggers.h b/include/linux/phy_led_triggers.h
index b37b05bfd1a6..4587ce362535 100644
--- a/include/linux/phy_led_triggers.h
+++ b/include/linux/phy_led_triggers.h
@@ -20,7 +20,7 @@ struct phy_device;
#include <linux/leds.h>
#include <linux/phy.h>
-#define PHY_LED_TRIGGER_SPEED_SUFFIX_SIZE 10
+#define PHY_LED_TRIGGER_SPEED_SUFFIX_SIZE 11
#define PHY_LINK_LED_TRIGGER_NAME_SIZE (MII_BUS_ID_SIZE + \
FIELD_SIZEOF(struct mdio_device, addr)+\
--
2.19.1
^ permalink raw reply related
* Re: [PATCH net-next 0/7] net: sched: prepare for more Qdisc offloads
From: Toke Høiland-Jørgensen @ 2018-11-08 11:48 UTC (permalink / raw)
To: Jakub Kicinski, davem
Cc: netdev, oss-drivers, jiri, xiyou.wangcong, jhs, nogah.frankel,
yuvalm, Jakub Kicinski
In-Reply-To: <20181108013340.20983-1-jakub.kicinski@netronome.com>
Jakub Kicinski <jakub.kicinski@netronome.com> writes:
> Hi!
>
> This series refactors the "switchdev" Qdisc offloads a little. We have
> a few Qdiscs which can be fully offloaded today to the forwarding plane
> of switching devices.
>
> First patch adds a helper for handing statistic dumps, the code seems
> to be copy pasted between PRIO and RED.
Hi Jakub
I didn't know there was offload capabilities for AQMs, that's cool! Do
you have any plans to add offloads for any of the modern AQMs (CoDel or
PIE)?
-Toke
^ permalink raw reply
* [PATCH bpf 0/4] tools: bpftool: bring several minor fixes to bpftool
From: Quentin Monnet @ 2018-11-08 11:52 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann; +Cc: netdev, oss-drivers, Quentin Monnet
Hi,
This set contains minor fixes for bpftool code and documentation.
Please refer to individual patches for details.
Quentin Monnet (4):
tools: bpftool: prevent infinite loop in get_fdinfo()
tools: bpftool: fix plain output and doc for --bpffs option
tools: bpftool: pass an argument to silence open_obj_pinned()
tools: bpftool: update references to other man pages in documentation
tools/bpf/bpftool/Documentation/bpftool-cgroup.rst | 8 +++++++-
tools/bpf/bpftool/Documentation/bpftool-map.rst | 8 +++++++-
tools/bpf/bpftool/Documentation/bpftool-net.rst | 8 +++++++-
tools/bpf/bpftool/Documentation/bpftool-perf.rst | 8 +++++++-
tools/bpf/bpftool/Documentation/bpftool-prog.rst | 11 +++++++++--
tools/bpf/bpftool/Documentation/bpftool.rst | 9 +++++++--
tools/bpf/bpftool/common.c | 17 +++++++++--------
tools/bpf/bpftool/main.h | 2 +-
tools/bpf/bpftool/prog.c | 3 +--
9 files changed, 55 insertions(+), 19 deletions(-)
--
2.7.4
^ permalink raw reply
* [PATCH bpf 1/4] tools: bpftool: prevent infinite loop in get_fdinfo()
From: Quentin Monnet @ 2018-11-08 11:52 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann; +Cc: netdev, oss-drivers, Quentin Monnet
In-Reply-To: <1541677948-12473-1-git-send-email-quentin.monnet@netronome.com>
Function getline() returns -1 on failure to read a line, thus creating
an infinite loop in get_fdinfo() if the key is not found. Fix it by
calling the function only as long as we get a strictly positive return
value.
Found by copying the code for a key which is not always present...
Fixes: 71bb428fe2c1 ("tools: bpf: add bpftool")
Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
tools/bpf/bpftool/common.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 1149565be4b1..acd839e0e801 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -312,7 +312,7 @@ char *get_fdinfo(int fd, const char *key)
return NULL;
}
- while ((n = getline(&line, &line_n, fdi))) {
+ while ((n = getline(&line, &line_n, fdi)) > 0) {
char *value;
int len;
--
2.7.4
^ permalink raw reply related
* [PATCH bpf 2/4] tools: bpftool: fix plain output and doc for --bpffs option
From: Quentin Monnet @ 2018-11-08 11:52 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann; +Cc: netdev, oss-drivers, Quentin Monnet
In-Reply-To: <1541677948-12473-1-git-send-email-quentin.monnet@netronome.com>
Edit the documentation of the -f|--bpffs option to make it explicit that
it dumps paths of pinned programs when bpftool is used to list the
programs only, so that users do not believe they will see the name of
the newly pinned program with "bpftool prog pin" or "bpftool prog load".
Also fix the plain output: do not add a blank line after each program
block, in order to remain consistent with what bpftool does when the
option is not passed.
Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
tools/bpf/bpftool/Documentation/bpftool-prog.rst | 3 ++-
tools/bpf/bpftool/prog.c | 3 +--
2 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index ac4e904b10fb..81fb97acfaeb 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -124,7 +124,8 @@ OPTIONS
Generate human-readable JSON output. Implies **-j**.
-f, --bpffs
- Show file names of pinned programs.
+ When showing BPF programs, show file names of pinned
+ programs.
EXAMPLES
========
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index b9b84553bec4..763ddfa29045 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -357,10 +357,9 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd)
if (!hash_empty(prog_table.table)) {
struct pinned_obj *obj;
- printf("\n");
hash_for_each_possible(prog_table.table, obj, hash, info->id) {
if (obj->id == info->id)
- printf("\tpinned %s\n", obj->path);
+ printf("\n\tpinned %s", obj->path);
}
}
--
2.7.4
^ permalink raw reply related
* [PATCH bpf 3/4] tools: bpftool: pass an argument to silence open_obj_pinned()
From: Quentin Monnet @ 2018-11-08 11:52 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann; +Cc: netdev, oss-drivers, Quentin Monnet
In-Reply-To: <1541677948-12473-1-git-send-email-quentin.monnet@netronome.com>
Function open_obj_pinned() prints error messages when it fails to open a
link in the BPF virtual file system. However, in some occasions it is
not desirable to print an error, for example when we parse all links
under the bpffs root, and the error is due to some paths actually being
symbolic links.
Example output:
# ls -l /sys/fs/bpf/
lrwxrwxrwx 1 root root 0 Oct 18 19:00 ip -> /sys/fs/bpf/tc/
drwx------ 3 root root 0 Oct 18 19:00 tc
lrwxrwxrwx 1 root root 0 Oct 18 19:00 xdp -> /sys/fs/bpf/tc/
# bpftool --bpffs prog show
Error: bpf obj get (/sys/fs/bpf): Permission denied
Error: bpf obj get (/sys/fs/bpf): Permission denied
# strace -e bpf bpftool --bpffs prog show
bpf(BPF_OBJ_GET, {pathname="/sys/fs/bpf/ip", bpf_fd=0}, 72) = -1 EACCES (Permission denied)
Error: bpf obj get (/sys/fs/bpf): Permission denied
bpf(BPF_OBJ_GET, {pathname="/sys/fs/bpf/xdp", bpf_fd=0}, 72) = -1 EACCES (Permission denied)
Error: bpf obj get (/sys/fs/bpf): Permission denied
...
To fix it, pass a bool as a second argument to the function, and prevent
it from printing an error when the argument is set to true.
Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
tools/bpf/bpftool/common.c | 15 ++++++++-------
tools/bpf/bpftool/main.h | 2 +-
2 files changed, 9 insertions(+), 8 deletions(-)
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index acd839e0e801..7b2388bec4a9 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -138,16 +138,17 @@ static int mnt_bpffs(const char *target, char *buff, size_t bufflen)
return 0;
}
-int open_obj_pinned(char *path)
+int open_obj_pinned(char *path, bool quiet)
{
int fd;
fd = bpf_obj_get(path);
if (fd < 0) {
- p_err("bpf obj get (%s): %s", path,
- errno == EACCES && !is_bpffs(dirname(path)) ?
- "directory not in bpf file system (bpffs)" :
- strerror(errno));
+ if (!quiet)
+ p_err("bpf obj get (%s): %s", path,
+ errno == EACCES && !is_bpffs(dirname(path)) ?
+ "directory not in bpf file system (bpffs)" :
+ strerror(errno));
return -1;
}
@@ -159,7 +160,7 @@ int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type)
enum bpf_obj_type type;
int fd;
- fd = open_obj_pinned(path);
+ fd = open_obj_pinned(path, false);
if (fd < 0)
return -1;
@@ -392,7 +393,7 @@ int build_pinned_obj_table(struct pinned_obj_table *tab,
while ((ftse = fts_read(fts))) {
if (!(ftse->fts_info & FTS_F))
continue;
- fd = open_obj_pinned(ftse->fts_path);
+ fd = open_obj_pinned(ftse->fts_path, true);
if (fd < 0)
continue;
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 14857c273bf6..6d33baa51273 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -129,7 +129,7 @@ int cmd_select(const struct cmd *cmds, int argc, char **argv,
int get_fd_type(int fd);
const char *get_fd_type_name(enum bpf_obj_type type);
char *get_fdinfo(int fd, const char *key);
-int open_obj_pinned(char *path);
+int open_obj_pinned(char *path, bool quiet);
int open_obj_pinned_any(char *path, enum bpf_obj_type exp_type);
int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32));
int do_pin_fd(int fd, const char *name);
--
2.7.4
^ permalink raw reply related
* [PATCH bpf 4/4] tools: bpftool: update references to other man pages in documentation
From: Quentin Monnet @ 2018-11-08 11:52 UTC (permalink / raw)
To: Alexei Starovoitov, Daniel Borkmann; +Cc: netdev, oss-drivers, Quentin Monnet
In-Reply-To: <1541677948-12473-1-git-send-email-quentin.monnet@netronome.com>
Update references to other bpftool man pages at the bottom of each
manual page. Also reference the "bpf(2)" and "bpf-helpers(7)" man pages.
References are sorted by number of man section, then by
"prog-and-map-go-first", the other pages in alphabetical order.
Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
tools/bpf/bpftool/Documentation/bpftool-cgroup.rst | 8 +++++++-
tools/bpf/bpftool/Documentation/bpftool-map.rst | 8 +++++++-
tools/bpf/bpftool/Documentation/bpftool-net.rst | 8 +++++++-
tools/bpf/bpftool/Documentation/bpftool-perf.rst | 8 +++++++-
tools/bpf/bpftool/Documentation/bpftool-prog.rst | 8 +++++++-
tools/bpf/bpftool/Documentation/bpftool.rst | 9 +++++++--
6 files changed, 42 insertions(+), 7 deletions(-)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
index edbe81534c6d..d07ccf8a23f7 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
@@ -137,4 +137,10 @@ EXAMPLES
SEE ALSO
========
- **bpftool**\ (8), **bpftool-prog**\ (8), **bpftool-map**\ (8)
+ **bpf**\ (2),
+ **bpf-helpers**\ (7),
+ **bpftool**\ (8),
+ **bpftool-prog**\ (8),
+ **bpftool-map**\ (8),
+ **bpftool-net**\ (8),
+ **bpftool-perf**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst
index f55a2daed59b..7bb787cfa971 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-map.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst
@@ -171,4 +171,10 @@ The following three commands are equivalent:
SEE ALSO
========
- **bpftool**\ (8), **bpftool-prog**\ (8), **bpftool-cgroup**\ (8)
+ **bpf**\ (2),
+ **bpf-helpers**\ (7),
+ **bpftool**\ (8),
+ **bpftool-prog**\ (8),
+ **bpftool-cgroup**\ (8),
+ **bpftool-net**\ (8),
+ **bpftool-perf**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-net.rst b/tools/bpf/bpftool/Documentation/bpftool-net.rst
index 408ec30d8872..ed87c9b619ad 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-net.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-net.rst
@@ -136,4 +136,10 @@ EXAMPLES
SEE ALSO
========
- **bpftool**\ (8), **bpftool-prog**\ (8), **bpftool-map**\ (8)
+ **bpf**\ (2),
+ **bpf-helpers**\ (7),
+ **bpftool**\ (8),
+ **bpftool-prog**\ (8),
+ **bpftool-map**\ (8),
+ **bpftool-cgroup**\ (8),
+ **bpftool-perf**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-perf.rst b/tools/bpf/bpftool/Documentation/bpftool-perf.rst
index e3eb0eab7641..f4c5e5538bb8 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-perf.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-perf.rst
@@ -78,4 +78,10 @@ EXAMPLES
SEE ALSO
========
- **bpftool**\ (8), **bpftool-prog**\ (8), **bpftool-map**\ (8)
+ **bpf**\ (2),
+ **bpf-helpers**\ (7),
+ **bpftool**\ (8),
+ **bpftool-prog**\ (8),
+ **bpftool-map**\ (8),
+ **bpftool-cgroup**\ (8),
+ **bpftool-net**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index 81fb97acfaeb..ecf618807125 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -207,4 +207,10 @@ EXAMPLES
SEE ALSO
========
- **bpftool**\ (8), **bpftool-map**\ (8), **bpftool-cgroup**\ (8)
+ **bpf**\ (2),
+ **bpf-helpers**\ (7),
+ **bpftool**\ (8),
+ **bpftool-map**\ (8),
+ **bpftool-cgroup**\ (8),
+ **bpftool-net**\ (8),
+ **bpftool-perf**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst
index 04cd4f92ab89..129b7a9c0f9b 100644
--- a/tools/bpf/bpftool/Documentation/bpftool.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool.rst
@@ -63,5 +63,10 @@ OPTIONS
SEE ALSO
========
- **bpftool-map**\ (8), **bpftool-prog**\ (8), **bpftool-cgroup**\ (8)
- **bpftool-perf**\ (8), **bpftool-net**\ (8)
+ **bpf**\ (2),
+ **bpf-helpers**\ (7),
+ **bpftool-prog**\ (8),
+ **bpftool-map**\ (8),
+ **bpftool-cgroup**\ (8),
+ **bpftool-net**\ (8),
+ **bpftool-perf**\ (8)
--
2.7.4
^ permalink raw reply related
* Re: [net-next 12/12] igc: Clean up code
From: Neftin, Sasha @ 2018-11-08 12:09 UTC (permalink / raw)
To: Joe Perches, Jeff Kirsher, davem; +Cc: netdev, nhorman, sassmann, Neftin, Sasha
In-Reply-To: <3f712fcf9f86cc3cdca3d6f937d1d1af165a11af.camel@perches.com>
On 11/8/2018 13:00, Joe Perches wrote:
> On Wed, 2018-11-07 at 14:48 -0800, Jeff Kirsher wrote:
>> From: Sasha Neftin <sasha.neftin@intel.com>
>>
>> Address few community comments.
>> Remove unused code, will be added per demand.
>> Remove blank lines and unneeded includes.
>>
>> Signed-off-by: Sasha Neftin <sasha.neftin@intel.com>
>> Tested-by: Aaron Brown <aaron.f.brown@intel.com>
>> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
>> ---
>> drivers/net/ethernet/intel/igc/igc.h | 9 ---------
>> drivers/net/ethernet/intel/igc/igc_main.c | 15 ---------------
>> 2 files changed, 24 deletions(-)
>>
>> diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
> []
>> #define IGC_ERR(args...) pr_err("igc: " args)
>
> This is used just once and should probably be removed.
>
> maybe:
>
> ---
> drivers/net/ethernet/intel/igc/igc_main.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
> index 9d85707e8a81..b58542b20623 100644
> --- a/drivers/net/ethernet/intel/igc/igc_main.c
> +++ b/drivers/net/ethernet/intel/igc/igc_main.c
> @@ -3551,7 +3551,7 @@ static int igc_probe(struct pci_dev *pdev,
> err = dma_set_coherent_mask(&pdev->dev,
> DMA_BIT_MASK(32));
> if (err) {
> - IGC_ERR("Wrong DMA configuration, aborting\n");
> + dev_err(&pdev->dev, "igc: Wrong DMA configuration, aborting\n");
> goto err_dma;
> }
> }
>
>
Good note, thanks. I will process another patch address this suggestion.
^ permalink raw reply
* RE: [PATCH v2 1/3][can-next] can: rcar_can: Fix erroneous registration
From: Fabrizio Castro @ 2018-11-08 12:39 UTC (permalink / raw)
To: Fabrizio Castro, Wolfgang Grandegger, Marc Kleine-Budde
Cc: David S. Miller, Sergei Shtylyov, Chris Paterson,
linux-can@vger.kernel.org, netdev@vger.kernel.org, Simon Horman,
Geert Uytterhoeven, Biju Das, linux-renesas-soc@vger.kernel.org
In-Reply-To: <1536576195-11520-2-git-send-email-fabrizio.castro@bp.renesas.com>
Dear All,
Is this patch ok?
Thanks,
Fab
> From: Fabrizio Castro <fabrizio.castro@bp.renesas.com>
> Sent: 10 September 2018 11:43
> Subject: [PATCH v2 1/3][can-next] can: rcar_can: Fix erroneous registration
>
> Assigning 2 to "renesas,can-clock-select" tricks the driver into
> registering the CAN interface, even though we don't want that.
> This patch improves one of the checks to prevent that from happening.
>
> Fixes: 862e2b6af9413b43 ("can: rcar_can: support all input clocks")
> Signed-off-by: Fabrizio Castro <fabrizio.castro@bp.renesas.com>
> Signed-off-by: Chris Paterson <Chris.Paterson2@renesas.com>
> ---
>
> v1->v2:
> * dropped id specific data as per Geert's comments
>
> This patch applies on top of linux-can-next-for-4.19-20180727.
>
> drivers/net/can/rcar/rcar_can.c | 5 ++++-
> 1 file changed, 4 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/net/can/rcar/rcar_can.c b/drivers/net/can/rcar/rcar_can.c
> index 11662f4..771a460 100644
> --- a/drivers/net/can/rcar/rcar_can.c
> +++ b/drivers/net/can/rcar/rcar_can.c
> @@ -24,6 +24,9 @@
>
> #define RCAR_CAN_DRV_NAME"rcar_can"
>
> +#define RCAR_SUPPORTED_CLOCKS(BIT(CLKR_CLKP1) | BIT(CLKR_CLKP2) | \
> + BIT(CLKR_CLKEXT))
> +
> /* Mailbox configuration:
> * mailbox 60 - 63 - Rx FIFO mailboxes
> * mailbox 56 - 59 - Tx FIFO mailboxes
> @@ -789,7 +792,7 @@ static int rcar_can_probe(struct platform_device *pdev)
> goto fail_clk;
> }
>
> -if (clock_select >= ARRAY_SIZE(clock_names)) {
> +if (!(BIT(clock_select) & RCAR_SUPPORTED_CLOCKS)) {
> err = -EINVAL;
> dev_err(&pdev->dev, "invalid CAN clock selected\n");
> goto fail_clk;
> --
> 2.7.4
Renesas Electronics Europe Ltd, Dukes Meadow, Millboard Road, Bourne End, Buckinghamshire, SL8 5FH, UK. Registered in England & Wales under Registered No. 04586709.
^ permalink raw reply
* Re: [PATCH 4/5] phy: mvebu-cp110-comphy: convert to use eth phy mode and submode
From: Grygorii Strashko @ 2018-11-08 22:42 UTC (permalink / raw)
To: Russell King - ARM Linux
Cc: David S. Miller, Kishon Vijay Abraham I, Alexandre Belloni,
Quentin Schulz, Manu Gautam, Tony Lindgren, netdev,
Antoine Tenart, Sekhar Nori, linux-kernel, Maxime Ripard,
Chen-Yu Tsai, Chunfeng Yun, linux-mediatek, Vivek Gautam,
Carlo Caione, linux-amlogic, linux-arm-kernel, Matthias Brugger
In-Reply-To: <20181108222123.GZ30658@n2100.armlinux.org.uk>
hi Russell,
On 11/8/18 4:21 PM, Russell King - ARM Linux wrote:
> On Wed, Nov 07, 2018 at 06:36:16PM -0600, Grygorii Strashko wrote:
>> diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
>> index 7a37a37..fb28b71 100644
>> --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
>> +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
>> @@ -1165,28 +1165,17 @@ static void mvpp22_gop_setup_irq(struct mvpp2_port *port)
>> */
>> static int mvpp22_comphy_init(struct mvpp2_port *port)
>> {
>> - enum phy_mode mode;
>> + int submode;
>> int ret;
>>
>> if (!port->comphy)
>> return 0;
>>
>> - switch (port->phy_interface) {
>> - case PHY_INTERFACE_MODE_SGMII:
>> - case PHY_INTERFACE_MODE_1000BASEX:
>> - mode = PHY_MODE_SGMII;
>> - break;
>> - case PHY_INTERFACE_MODE_2500BASEX:
>> - mode = PHY_MODE_2500SGMII;
>> - break;
>> - case PHY_INTERFACE_MODE_10GKR:
>> - mode = PHY_MODE_10GKR;
>> - break;
>> - default:
>> - return -EINVAL;
>> - }
>> + submode = port->phy_interface;
>> + if (submode == PHY_INTERFACE_MODE_1000BASEX)
>> + submode = PHY_INTERFACE_MODE_SGMII;
>
> If the intention is to move the ethernet PHY mode into the generic PHY
> layer, I'd suggest that the equivalence of 1000base-X and SGMII is
> handled in the generic PHY driver rather than ethernet drivers. Just
> move this into this hunk of the comphy driver:
sure, will do
>
>> @@ -517,10 +519,14 @@ static int mvebu_comphy_set_mode(struct phy *phy,
>> {
>> struct mvebu_comphy_lane *lane = phy_get_drvdata(phy);
>>
>> - if (mvebu_comphy_get_mux(lane->id, lane->port, mode) < 0)
>> + if (mode != PHY_MODE_ETHERNET)
>> + return -EINVAL;
>> +
>> + if (mvebu_comphy_get_mux(lane->id, lane->port, mode, submode) < 0)
>> return -EINVAL;
>>
>> lane->mode = mode;
>> + lane->submode = submode;
>> return 0;
>> }
>
--
regards,
-grygorii
^ permalink raw reply
* RE: [PATCH net-next v3 6/6] net/ncsi: Configure multi-package, multi-channel modes with failover
From: Justin.Lee1 @ 2018-11-08 22:48 UTC (permalink / raw)
To: sam, netdev; +Cc: davem, linux-kernel, openbmc
In-Reply-To: <20181108024909.9897-7-sam@mendozajonas.com>
Hi Samuel,
For multi-package and multi-channel case, channel seems to be select correctly. Expect that,
I still see the timing issue for back-to-back netlink command. Due to that, channel might be
set to invisible state. Please refer to ncsi0 and ncsi2 below. The channel state is set to 3.
cat /sys/kernel/debug/ncsi_protocol/ncsi_device_status
IFIDX IFNAME NAME PID CID RX TX MP MC WP WC PC CS PS LS RU CR NQ HA
=====================================================================
2 eth2 ncsi0 000 000 1 1 1 1 1 0 0 3 0 1 1 1 0 1
2 eth2 ncsi1 000 001 0 0 1 1 1 0 0 1 0 1 1 1 0 1
2 eth2 ncsi2 001 000 1 0 1 1 1 1 0 3 0 1 1 1 0 1
2 eth2 ncsi3 001 001 1 0 1 1 1 1 0 2 1 1 1 1 0 1
=====================================================================
MP: Multi-mode Package WP: Whitelist Package
MC: Multi-mode Channel WC: Whitelist Channel
PC: Primary Channel CS: Channel State IA/A/IV 1/2/3
PS: Poll Status LS: Link Status
RU: Running CR: Carrier OK
NQ: Queue Stopped HA: Hardware Arbitration
The timing issue is not only happening in application. If I use using the following way
to send the request, I can see the issue as well.
ncsi_netlink -l 2 -a 0x01 -m; ncsi_netlink -l 2 -p 0 -b 0x03 -m; ncsi_netlink -l 2 -p 1 -b 0x00 -m;
ncsi_netlink -l 2 -a 0x03 -m; ncsi_netlink -l 2 -p 0 -b 0x00 -m; ncsi_netlink -l 2 -p 1 -b 0x03 -m;
Also, there is one issue below for non-multi-package/non-multi-channel case.
Thanks,
Justin
> @@ -1008,32 +1164,49 @@ static int ncsi_choose_active_channel(struct ncsi_dev_priv *ndp)
>
> ncm = &nc->modes[NCSI_MODE_LINK];
> if (ncm->data[2] & 0x1) {
> - spin_unlock_irqrestore(&nc->lock, flags);
> found = nc;
> - goto out;
> + with_link = true;
> }
>
> - spin_unlock_irqrestore(&nc->lock, flags);
> + /* If multi_channel is enabled configure all valid
> + * channels whether or not they currently have link
> + * so they will have AENs enabled.
> + */
> + if (with_link || np->multi_channel) {
> + spin_lock_irqsave(&ndp->lock, flags);
> + list_add_tail_rcu(&nc->link,
> + &ndp->channel_queue);
> + spin_unlock_irqrestore(&ndp->lock, flags);
> +
> + netdev_dbg(ndp->ndev.dev,
> + "NCSI: Channel %u added to queue (link %s)\n",
> + nc->id,
> + ncm->data[2] & 0x1 ? "up" : "down");
> + }
> +
> + spin_unlock_irqrestore(&nc->lock, cflags);
> +
> + if (with_link && !np->multi_channel)
> + break;
The line needs to change to "goto found". If not, all channels with link will be added
even if the multi-channel is not enabled for that package. The ncsi1 below is enabled.
There is no netlink command sent to enable multi-package or multi-channel.
IFIDX IFNAME NAME PID CID RX TX MP MC WP WC PC CS PS LS RU CR NQ HA
=====================================================================
2 eth2 ncsi0 000 000 1 1 0 0 1 1 0 2 1 1 1 1 0 1
2 eth2 ncsi1 000 001 1 0 0 0 1 1 0 2 1 1 1 1 0 1
2 eth2 ncsi2 001 000 0 0 0 0 1 1 0 1 0 1 1 1 0 1
2 eth2 ncsi3 001 001 0 0 0 0 1 1 0 1 0 1 1 1 0 1
=====================================================================
MP: Multi-mode Package WP: Whitelist Package
MC: Multi-mode Channel WC: Whitelist Channel
PC: Primary Channel CS: Channel State IA/A/IV 1/2/3
PS: Poll Status LS: Link Status
RU: Running CR: Carrier OK
NQ: Queue Stopped HA: Hardware Arbitration
> }
> + if (with_link && !ndp->multi_package)
> + break;
> }
found:
After applying this change, I notice that if there is no link available to BMC when BMC
starts, NC-SI can't properly configure channel once I plug in the Ethernet cable.
npcm7xx-emc f0825000.eth eth2: NCSI: ncsi_aen_handler_lsc() - pkg 0 ch 0 state up
npcm7xx-emc f0825000.eth eth2: NCSI: ncsi_aen_handler_lsc() - had_link 0, has_link 1, chained 0
npcm7xx-emc f0825000.eth eth2: NCSI: ncsi_stop_channel_monitor() - pkg 0 ch 0
npcm7xx-emc f0825000.eth eth2: NCSI: ncsi_process_next_channel()
npcm7xx-emc f0825000.eth eth2: NCSI: ncsi_process_next_channel() - pkg 0 ch 0 INVISIBLE
npcm7xx-emc f0825000.eth eth2: NCSI: ncsi_process_next_channel() - suspending pkg 0 ch 0
npcm7xx-emc f0825000.eth eth2: NCSI: ncsi_suspend_channel() - pkg 0 ch 0 state 0400 select
npcm7xx-emc f0825000.eth eth2: NCSI: ncsi_dev_work()
npcm7xx-emc f0825000.eth eth2: NCSI: ncsi_suspend_channel() - pkg 0 ch 0 state 0403 dc
npcm7xx-emc f0825000.eth eth2: NCSI: ncsi_dev_work()
npcm7xx-emc f0825000.eth eth2: NCSI: ncsi_suspend_channel() - pkg 0 ch 0 state 0404 deselect
npcm7xx-emc f0825000.eth eth2: NCSI: ncsi_dev_work()
npcm7xx-emc f0825000.eth eth2: NCSI: ncsi_suspend_channel() - pkg 0 ch 0 state 0405 done
npcm7xx-emc f0825000.eth eth2: NCSI: ncsi_rsp_handler_dp() - pkg 0 ch 0 INACTIVE
npcm7xx-emc f0825000.eth eth2: NCSI: ncsi_rsp_handler_dp() - pkg 0 ch 1 INACTIVE
npcm7xx-emc f0825000.eth eth2: NCSI: ncsi_dev_work()
npcm7xx-emc f0825000.eth eth2: NCSI: ncsi_suspend_channel() - pkg 0 ch 0 state 0406 deselect
npcm7xx-emc f0825000.eth eth2: NCSI: ncsi_suspend_channel() - pkg 0 ch 0 INACTIVE
npcm7xx-emc f0825000.eth eth2: NCSI: ncsi_process_next_channel()
npcm7xx-emc f0825000.eth eth2: NCSI: ncsi_process_next_channel() - No more channels to process
npcm7xx-emc f0825000.eth eth2: NCSI interface down
>
> - if (!found) {
> + if (list_empty(&ndp->channel_queue) && found) {
> + netdev_info(ndp->ndev.dev,
> + "NCSI: No channel with link found, configuring channel %u\n",
> + found->id);
> + spin_lock_irqsave(&ndp->lock, flags);
> + list_add_tail_rcu(&found->link, &ndp->channel_queue);
> + spin_unlock_irqrestore(&ndp->lock, flags);
> + } else if (!found) {
> netdev_warn(ndp->ndev.dev,
> - "NCSI: No channel found with link\n");
> + "NCSI: No channel found to configure!\n");
> ncsi_report_link(ndp, true);
> return -ENODEV;
> }
>
> - ncm = &found->modes[NCSI_MODE_LINK];
> - netdev_dbg(ndp->ndev.dev,
> - "NCSI: Channel %u added to queue (link %s)\n",
> - found->id, ncm->data[2] & 0x1 ? "up" : "down");
> -
> -out:
> - spin_lock_irqsave(&ndp->lock, flags);
> - list_add_tail_rcu(&found->link, &ndp->channel_queue);
> - spin_unlock_irqrestore(&ndp->lock, flags);
> -
> return ncsi_process_next_channel(ndp);
> }
^ permalink raw reply
* [PATCH net-next 1/2] dpaa2-eth: defer probe on object allocate
From: Ioana Ciornei @ 2018-11-08 13:17 UTC (permalink / raw)
To: netdev@vger.kernel.org, davem@davemloft.net
Cc: Ioana Ciocoi Radulescu, Ioana Ciornei
In-Reply-To: <1541683054-22273-1-git-send-email-ioana.ciornei@nxp.com>
The fsl_mc_object_allocate function can fail because not all allocatable
objects are probed by the fsl_mc_allocator at the call time. Defer the
dpaa2-eth probe when this happens.
Signed-off-by: Ioana Ciornei <ioana.ciornei@nxp.com>
---
drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 30 +++++++++++++++++-------
1 file changed, 21 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 88f7acc..71f5cd4 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -1434,8 +1434,11 @@ static struct fsl_mc_device *setup_dpcon(struct dpaa2_eth_priv *priv)
err = fsl_mc_object_allocate(to_fsl_mc_device(dev),
FSL_MC_POOL_DPCON, &dpcon);
if (err) {
- dev_info(dev, "Not enough DPCONs, will go on as-is\n");
- return NULL;
+ if (err == -ENXIO)
+ err = -EPROBE_DEFER;
+ else
+ dev_info(dev, "Not enough DPCONs, will go on as-is\n");
+ return ERR_PTR(err);
}
err = dpcon_open(priv->mc_io, 0, dpcon->obj_desc.id, &dpcon->mc_handle);
@@ -1493,8 +1496,10 @@ static void free_dpcon(struct dpaa2_eth_priv *priv,
return NULL;
channel->dpcon = setup_dpcon(priv);
- if (!channel->dpcon)
+ if (IS_ERR_OR_NULL(channel->dpcon)) {
+ err = PTR_ERR(channel->dpcon);
goto err_setup;
+ }
err = dpcon_get_attributes(priv->mc_io, 0, channel->dpcon->mc_handle,
&attr);
@@ -1513,7 +1518,7 @@ static void free_dpcon(struct dpaa2_eth_priv *priv,
free_dpcon(priv, channel->dpcon);
err_setup:
kfree(channel);
- return NULL;
+ return ERR_PTR(err);
}
static void free_channel(struct dpaa2_eth_priv *priv,
@@ -1547,10 +1552,11 @@ static int setup_dpio(struct dpaa2_eth_priv *priv)
for_each_online_cpu(i) {
/* Try to allocate a channel */
channel = alloc_channel(priv);
- if (!channel) {
- dev_info(dev,
- "No affine channel for cpu %d and above\n", i);
- err = -ENODEV;
+ if (IS_ERR_OR_NULL(channel)) {
+ err = PTR_ERR(channel);
+ if (err != -EPROBE_DEFER)
+ dev_info(dev,
+ "No affine channel for cpu %d and above\n", i);
goto err_alloc_ch;
}
@@ -1608,6 +1614,9 @@ static int setup_dpio(struct dpaa2_eth_priv *priv)
err_service_reg:
free_channel(priv, channel);
err_alloc_ch:
+ if (err == -EPROBE_DEFER)
+ return err;
+
if (cpumask_empty(&priv->dpio_cpumask)) {
dev_err(dev, "No cpu with an affine DPIO/DPCON\n");
return err;
@@ -1732,7 +1741,10 @@ static int setup_dpbp(struct dpaa2_eth_priv *priv)
err = fsl_mc_object_allocate(to_fsl_mc_device(dev), FSL_MC_POOL_DPBP,
&dpbp_dev);
if (err) {
- dev_err(dev, "DPBP device allocation failed\n");
+ if (err == -ENXIO)
+ err = -EPROBE_DEFER;
+ else
+ dev_err(dev, "DPBP device allocation failed\n");
return err;
}
--
1.9.1
^ permalink raw reply related
* [PATCH net-next 0/2] dpaa2-eth: defer probe on object allocate
From: Ioana Ciornei @ 2018-11-08 13:17 UTC (permalink / raw)
To: netdev@vger.kernel.org, davem@davemloft.net
Cc: Ioana Ciocoi Radulescu, Ioana Ciornei
Allocatable objects on the fsl-mc bus may be probed by the fsl_mc_allocator
after the first attempts of other drivers to use them. Defer the probe when
this situation happens.
Ioana Ciornei (2):
dpaa2-eth: defer probe on object allocate
dpaa2-ptp: defer probe when portal allocation failed
drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c | 30 +++++++++++++++++-------
drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c | 5 +++-
2 files changed, 25 insertions(+), 10 deletions(-)
--
1.9.1
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox