* [net-next 2/6] openvswitch: Eliminate memset() from flow_extract.
From: Andy Zhou @ 2014-10-02 8:04 UTC (permalink / raw)
To: davem; +Cc: netdev, Jesse Gross, Andy Zhou
In-Reply-To: <1412237085-27215-1-git-send-email-azhou@nicira.com>
From: Jesse Gross <jesse@nicira.com>
As new protocols are added, the size of the flow key tends to
increase although few protocols care about all of the fields. In
order to optimize this for hashing and matching, OVS uses a variable
length portion of the key. However, when fields are extracted from
the packet we must still zero out the entire key.
This is no longer necessary now that OVS implements masking. Any
fields (or holes in the structure) which are not part of a given
protocol will be by definition not part of the mask and zeroed out
during lookup. Furthermore, since masking already uses variable
length keys this zeroing operation automatically benefits as well.
In principle, the only thing that needs to be done at this point
is remove the memset() at the beginning of flow. However, some
fields assume that they are initialized to zero, which now must be
done explicitly. In addition, in the event of an error we must also
zero out corresponding fields to signal that there is no valid data
present. These increase the total amount of code but very little of
it is executed in non-error situations.
Removing the memset() reduces the profile of ovs_flow_extract()
from 0.64% to 0.56% when tested with large packets on a 10G link.
Suggested-by: Pravin Shelar <pshelar@nicira.com>
Signed-off-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: Andy Zhou <azhou@nicira.com>
---
net/openvswitch/flow.c | 54 ++++++++++++++++++++++++++++++++++++++++--------
1 file changed, 45 insertions(+), 9 deletions(-)
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 4010423..913bdc1 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -462,6 +462,7 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
* update skb->csum here.
*/
+ key->eth.tci = 0;
if (vlan_tx_tag_present(skb))
key->eth.tci = htons(skb->vlan_tci);
else if (eth->h_proto == htons(ETH_P_8021Q))
@@ -482,6 +483,8 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
error = check_iphdr(skb);
if (unlikely(error)) {
+ memset(&key->ip, 0, sizeof(key->ip));
+ memset(&key->ipv4, 0, sizeof(key->ipv4));
if (error == -EINVAL) {
skb->transport_header = skb->network_header;
error = 0;
@@ -503,8 +506,10 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
return 0;
}
if (nh->frag_off & htons(IP_MF) ||
- skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
+ skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
key->ip.frag = OVS_FRAG_TYPE_FIRST;
+ else
+ key->ip.frag = OVS_FRAG_TYPE_NONE;
/* Transport layer. */
if (key->ip.proto == IPPROTO_TCP) {
@@ -513,18 +518,25 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
key->tp.src = tcp->source;
key->tp.dst = tcp->dest;
key->tp.flags = TCP_FLAGS_BE16(tcp);
+ } else {
+ memset(&key->tp, 0, sizeof(key->tp));
}
+
} else if (key->ip.proto == IPPROTO_UDP) {
if (udphdr_ok(skb)) {
struct udphdr *udp = udp_hdr(skb);
key->tp.src = udp->source;
key->tp.dst = udp->dest;
+ } else {
+ memset(&key->tp, 0, sizeof(key->tp));
}
} else if (key->ip.proto == IPPROTO_SCTP) {
if (sctphdr_ok(skb)) {
struct sctphdr *sctp = sctp_hdr(skb);
key->tp.src = sctp->source;
key->tp.dst = sctp->dest;
+ } else {
+ memset(&key->tp, 0, sizeof(key->tp));
}
} else if (key->ip.proto == IPPROTO_ICMP) {
if (icmphdr_ok(skb)) {
@@ -534,33 +546,44 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
* them in 16-bit network byte order. */
key->tp.src = htons(icmp->type);
key->tp.dst = htons(icmp->code);
+ } else {
+ memset(&key->tp, 0, sizeof(key->tp));
}
}
- } else if ((key->eth.type == htons(ETH_P_ARP) ||
- key->eth.type == htons(ETH_P_RARP)) && arphdr_ok(skb)) {
+ } else if (key->eth.type == htons(ETH_P_ARP) ||
+ key->eth.type == htons(ETH_P_RARP)) {
struct arp_eth_header *arp;
arp = (struct arp_eth_header *)skb_network_header(skb);
- if (arp->ar_hrd == htons(ARPHRD_ETHER)
- && arp->ar_pro == htons(ETH_P_IP)
- && arp->ar_hln == ETH_ALEN
- && arp->ar_pln == 4) {
+ if (arphdr_ok(skb) &&
+ arp->ar_hrd == htons(ARPHRD_ETHER) &&
+ arp->ar_pro == htons(ETH_P_IP) &&
+ arp->ar_hln == ETH_ALEN &&
+ arp->ar_pln == 4) {
/* We only match on the lower 8 bits of the opcode. */
if (ntohs(arp->ar_op) <= 0xff)
key->ip.proto = ntohs(arp->ar_op);
+ else
+ key->ip.proto = 0;
+
memcpy(&key->ipv4.addr.src, arp->ar_sip, sizeof(key->ipv4.addr.src));
memcpy(&key->ipv4.addr.dst, arp->ar_tip, sizeof(key->ipv4.addr.dst));
ether_addr_copy(key->ipv4.arp.sha, arp->ar_sha);
ether_addr_copy(key->ipv4.arp.tha, arp->ar_tha);
+ } else {
+ memset(&key->ip, 0, sizeof(key->ip));
+ memset(&key->ipv4, 0, sizeof(key->ipv4));
}
} else if (key->eth.type == htons(ETH_P_IPV6)) {
int nh_len; /* IPv6 Header + Extensions */
nh_len = parse_ipv6hdr(skb, key);
if (unlikely(nh_len < 0)) {
+ memset(&key->ip, 0, sizeof(key->ip));
+ memset(&key->ipv6.addr, 0, sizeof(key->ipv6.addr));
if (nh_len == -EINVAL) {
skb->transport_header = skb->network_header;
error = 0;
@@ -582,24 +605,32 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
key->tp.src = tcp->source;
key->tp.dst = tcp->dest;
key->tp.flags = TCP_FLAGS_BE16(tcp);
+ } else {
+ memset(&key->tp, 0, sizeof(key->tp));
}
} else if (key->ip.proto == NEXTHDR_UDP) {
if (udphdr_ok(skb)) {
struct udphdr *udp = udp_hdr(skb);
key->tp.src = udp->source;
key->tp.dst = udp->dest;
+ } else {
+ memset(&key->tp, 0, sizeof(key->tp));
}
} else if (key->ip.proto == NEXTHDR_SCTP) {
if (sctphdr_ok(skb)) {
struct sctphdr *sctp = sctp_hdr(skb);
key->tp.src = sctp->source;
key->tp.dst = sctp->dest;
+ } else {
+ memset(&key->tp, 0, sizeof(key->tp));
}
} else if (key->ip.proto == NEXTHDR_ICMP) {
if (icmp6hdr_ok(skb)) {
error = parse_icmpv6(skb, key, nh_len);
if (error)
return error;
+ } else {
+ memset(&key->tp, 0, sizeof(key->tp));
}
}
}
@@ -615,13 +646,19 @@ int ovs_flow_key_extract(struct ovs_key_ipv4_tunnel *tun_key,
struct sk_buff *skb, struct sw_flow_key *key)
{
/* Extract metadata from packet. */
- memset(key, 0, sizeof(*key));
if (tun_key)
memcpy(&key->tun_key, tun_key, sizeof(key->tun_key));
+ else
+ memset(&key->tun_key, 0, sizeof(key->tun_key));
key->phy.priority = skb->priority;
key->phy.in_port = OVS_CB(skb)->input_vport->port_no;
key->phy.skb_mark = skb->mark;
+ key->ovs_flow_hash = 0;
+ key->recirc_id = 0;
+
+ /* Flags are always used as part of stats */
+ key->tp.flags = 0;
return key_extract(skb, key);
}
@@ -632,7 +669,6 @@ int ovs_flow_key_extract_userspace(const struct nlattr *attr,
{
int err;
- memset(key, 0, sizeof(*key));
/* Extract metadata from netlink attributes. */
err = ovs_nla_get_flow_metadata(attr, key);
if (err)
--
1.7.9.5
^ permalink raw reply related
* [net-next 3/6] openvswitch: Add support for matching on OAM packets.
From: Andy Zhou @ 2014-10-02 8:04 UTC (permalink / raw)
To: davem; +Cc: netdev, Jesse Gross, Andy Zhou
In-Reply-To: <1412237085-27215-1-git-send-email-azhou@nicira.com>
From: Jesse Gross <jesse@nicira.com>
Some tunnel formats have mechanisms for indicating that packets are
OAM frames that should be handled specially (either as high priority or
not forwarded beyond an endpoint). This provides support for allowing
those types of packets to be matched.
Signed-off-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: Andy Zhou <azhou@nicira.com>
---
include/uapi/linux/openvswitch.h | 1 +
net/openvswitch/datapath.c | 1 +
net/openvswitch/flow_netlink.c | 17 ++++++++++++-----
3 files changed, 14 insertions(+), 5 deletions(-)
diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index f7fc507..7c06106 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -309,6 +309,7 @@ enum ovs_tunnel_key_attr {
OVS_TUNNEL_KEY_ATTR_TTL, /* u8 Tunnel IP TTL. */
OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT, /* No argument, set DF. */
OVS_TUNNEL_KEY_ATTR_CSUM, /* No argument. CSUM packet. */
+ OVS_TUNNEL_KEY_ATTR_OAM, /* No argument. OAM frame. */
__OVS_TUNNEL_KEY_ATTR_MAX
};
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 9e3a2fa..f6bd93d 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -369,6 +369,7 @@ static size_t key_attr_size(void)
+ nla_total_size(1) /* OVS_TUNNEL_KEY_ATTR_TTL */
+ nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT */
+ nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_CSUM */
+ + nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_OAM */
+ nla_total_size(4) /* OVS_KEY_ATTR_IN_PORT */
+ nla_total_size(4) /* OVS_KEY_ATTR_SKB_MARK */
+ nla_total_size(12) /* OVS_KEY_ATTR_ETHERNET */
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index f4c8daa..22c855f 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -346,6 +346,7 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
[OVS_TUNNEL_KEY_ATTR_TTL] = 1,
[OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT] = 0,
[OVS_TUNNEL_KEY_ATTR_CSUM] = 0,
+ [OVS_TUNNEL_KEY_ATTR_OAM] = 0,
};
if (type > OVS_TUNNEL_KEY_ATTR_MAX) {
@@ -390,6 +391,9 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
case OVS_TUNNEL_KEY_ATTR_CSUM:
tun_flags |= TUNNEL_CSUM;
break;
+ case OVS_TUNNEL_KEY_ATTR_OAM:
+ tun_flags |= TUNNEL_OAM;
+ break;
default:
return -EINVAL;
}
@@ -431,21 +435,24 @@ static int ipv4_tun_to_nlattr(struct sk_buff *skb,
nla_put_be64(skb, OVS_TUNNEL_KEY_ATTR_ID, output->tun_id))
return -EMSGSIZE;
if (output->ipv4_src &&
- nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC, output->ipv4_src))
+ nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC, output->ipv4_src))
return -EMSGSIZE;
if (output->ipv4_dst &&
- nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST, output->ipv4_dst))
+ nla_put_be32(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST, output->ipv4_dst))
return -EMSGSIZE;
if (output->ipv4_tos &&
- nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TOS, output->ipv4_tos))
+ nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TOS, output->ipv4_tos))
return -EMSGSIZE;
if (nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TTL, output->ipv4_ttl))
return -EMSGSIZE;
if ((output->tun_flags & TUNNEL_DONT_FRAGMENT) &&
- nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT))
+ nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT))
return -EMSGSIZE;
if ((output->tun_flags & TUNNEL_CSUM) &&
- nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_CSUM))
+ nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_CSUM))
+ return -EMSGSIZE;
+ if ((output->tun_flags & TUNNEL_OAM) &&
+ nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_OAM))
return -EMSGSIZE;
nla_nest_end(skb, nla);
--
1.7.9.5
^ permalink raw reply related
* [net-next 4/6] openvswitch: Wrap struct ovs_key_ipv4_tunnel in a new structure.
From: Andy Zhou @ 2014-10-02 8:04 UTC (permalink / raw)
To: davem; +Cc: netdev, Jesse Gross, Andy Zhou
In-Reply-To: <1412237085-27215-1-git-send-email-azhou@nicira.com>
From: Jesse Gross <jesse@nicira.com>
Currently, the flow information that is matched for tunnels and
the tunnel data passed around with packets is the same. However,
as additional information is added this is not necessarily desirable,
as in the case of pointers.
This adds a new structure for tunnel metadata which currently contains
only the existing struct. This change is purely internal to the kernel
since the current OVS_KEY_ATTR_IPV4_TUNNEL is simply a compressed version
of OVS_KEY_ATTR_TUNNEL that is translated at flow setup.
Signed-off-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: Andy Zhou <azhou@nicira.com>
---
include/uapi/linux/openvswitch.h | 2 +-
net/openvswitch/actions.c | 5 +++--
net/openvswitch/datapath.h | 2 +-
net/openvswitch/flow.c | 6 +++---
net/openvswitch/flow.h | 30 +++++++++++++++++-------------
net/openvswitch/flow_netlink.c | 38 +++++++++++++++++++++++++++++++-------
net/openvswitch/vport-gre.c | 16 +++++++++-------
net/openvswitch/vport-vxlan.c | 10 +++++-----
net/openvswitch/vport.c | 6 +++---
net/openvswitch/vport.h | 2 +-
10 files changed, 74 insertions(+), 43 deletions(-)
diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index 7c06106..6753032 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -294,7 +294,7 @@ enum ovs_key_attr {
OVS_KEY_ATTR_RECIRC_ID, /* u32 recirc id */
#ifdef __KERNEL__
- OVS_KEY_ATTR_IPV4_TUNNEL, /* struct ovs_key_ipv4_tunnel */
+ OVS_KEY_ATTR_TUNNEL_INFO, /* struct ovs_tunnel_info */
#endif
__OVS_KEY_ATTR_MAX
};
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 6932a42..006886d 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -590,8 +590,8 @@ static int execute_set_action(struct sk_buff *skb,
skb->mark = nla_get_u32(nested_attr);
break;
- case OVS_KEY_ATTR_IPV4_TUNNEL:
- OVS_CB(skb)->egress_tun_key = nla_data(nested_attr);
+ case OVS_KEY_ATTR_TUNNEL_INFO:
+ OVS_CB(skb)->egress_tun_info = nla_data(nested_attr);
break;
case OVS_KEY_ATTR_ETHERNET:
@@ -778,6 +778,7 @@ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
acts = rcu_dereference(OVS_CB(skb)->flow->sf_acts);
this_cpu_inc(exec_actions_level);
+ OVS_CB(skb)->egress_tun_info = NULL;
err = do_execute_actions(dp, skb, key,
acts->actions, acts->actions_len);
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index ac3f3df..9741354 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -102,8 +102,8 @@ struct datapath {
*/
struct ovs_skb_cb {
struct sw_flow *flow;
+ struct ovs_tunnel_info *egress_tun_info;
struct vport *input_vport;
- struct ovs_key_ipv4_tunnel *egress_tun_key;
};
#define OVS_CB(skb) ((struct ovs_skb_cb *)(skb)->cb)
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 913bdc1..2924cb3 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -642,12 +642,12 @@ int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key)
return key_extract(skb, key);
}
-int ovs_flow_key_extract(struct ovs_key_ipv4_tunnel *tun_key,
+int ovs_flow_key_extract(struct ovs_tunnel_info *tun_info,
struct sk_buff *skb, struct sw_flow_key *key)
{
/* Extract metadata from packet. */
- if (tun_key)
- memcpy(&key->tun_key, tun_key, sizeof(key->tun_key));
+ if (tun_info)
+ memcpy(&key->tun_key, &tun_info->tunnel, sizeof(key->tun_key));
else
memset(&key->tun_key, 0, sizeof(key->tun_key));
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index 0f5db4e..fe5a71b 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -49,20 +49,24 @@ struct ovs_key_ipv4_tunnel {
u8 ipv4_ttl;
} __packed __aligned(4); /* Minimize padding. */
-static inline void ovs_flow_tun_key_init(struct ovs_key_ipv4_tunnel *tun_key,
- const struct iphdr *iph, __be64 tun_id,
- __be16 tun_flags)
+struct ovs_tunnel_info {
+ struct ovs_key_ipv4_tunnel tunnel;
+};
+
+static inline void ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info,
+ const struct iphdr *iph,
+ __be64 tun_id, __be16 tun_flags)
{
- tun_key->tun_id = tun_id;
- tun_key->ipv4_src = iph->saddr;
- tun_key->ipv4_dst = iph->daddr;
- tun_key->ipv4_tos = iph->tos;
- tun_key->ipv4_ttl = iph->ttl;
- tun_key->tun_flags = tun_flags;
+ tun_info->tunnel.tun_id = tun_id;
+ tun_info->tunnel.ipv4_src = iph->saddr;
+ tun_info->tunnel.ipv4_dst = iph->daddr;
+ tun_info->tunnel.ipv4_tos = iph->tos;
+ tun_info->tunnel.ipv4_ttl = iph->ttl;
+ tun_info->tunnel.tun_flags = tun_flags;
/* clear struct padding. */
- memset((unsigned char *) tun_key + OVS_TUNNEL_KEY_SIZE, 0,
- sizeof(*tun_key) - OVS_TUNNEL_KEY_SIZE);
+ memset((unsigned char *)&tun_info->tunnel + OVS_TUNNEL_KEY_SIZE, 0,
+ sizeof(tun_info->tunnel) - OVS_TUNNEL_KEY_SIZE);
}
struct sw_flow_key {
@@ -190,8 +194,8 @@ void ovs_flow_stats_clear(struct sw_flow *);
u64 ovs_flow_used_time(unsigned long flow_jiffies);
int ovs_flow_key_update(struct sk_buff *skb, struct sw_flow_key *key);
-int ovs_flow_key_extract(struct ovs_key_ipv4_tunnel *tun_key,
- struct sk_buff *skb, struct sw_flow_key *key);
+int ovs_flow_key_extract(struct ovs_tunnel_info *tun_info, struct sk_buff *skb,
+ struct sw_flow_key *key);
/* Extract key from packet coming from userspace. */
int ovs_flow_key_extract_userspace(const struct nlattr *attr,
struct sk_buff *skb,
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 22c855f..5d6194d 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -1148,13 +1148,14 @@ out:
return (struct nlattr *) ((unsigned char *)(*sfa) + next_offset);
}
-static int add_action(struct sw_flow_actions **sfa, int attrtype, void *data, int len)
+static struct nlattr *__add_action(struct sw_flow_actions **sfa,
+ int attrtype, void *data, int len)
{
struct nlattr *a;
a = reserve_sfa_size(sfa, nla_attr_size(len));
if (IS_ERR(a))
- return PTR_ERR(a);
+ return a;
a->nla_type = attrtype;
a->nla_len = nla_attr_size(len);
@@ -1163,6 +1164,18 @@ static int add_action(struct sw_flow_actions **sfa, int attrtype, void *data, in
memcpy(nla_data(a), data, len);
memset((unsigned char *) a + a->nla_len, 0, nla_padlen(len));
+ return a;
+}
+
+static int add_action(struct sw_flow_actions **sfa, int attrtype,
+ void *data, int len)
+{
+ struct nlattr *a;
+
+ a = __add_action(sfa, attrtype, data, len);
+ if (IS_ERR(a))
+ return PTR_ERR(a);
+
return 0;
}
@@ -1268,6 +1281,8 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
{
struct sw_flow_match match;
struct sw_flow_key key;
+ struct ovs_tunnel_info *tun_info;
+ struct nlattr *a;
int err, start;
ovs_match_init(&match, &key, NULL);
@@ -1279,8 +1294,14 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
if (start < 0)
return start;
- err = add_action(sfa, OVS_KEY_ATTR_IPV4_TUNNEL, &match.key->tun_key,
- sizeof(match.key->tun_key));
+ a = __add_action(sfa, OVS_KEY_ATTR_TUNNEL_INFO, NULL,
+ sizeof(*tun_info));
+ if (IS_ERR(a))
+ return PTR_ERR(a);
+
+ tun_info = nla_data(a);
+ tun_info->tunnel = key.tun_key;
+
add_nested_action_end(*sfa, start);
return err;
@@ -1563,17 +1584,20 @@ static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb)
int err;
switch (key_type) {
- case OVS_KEY_ATTR_IPV4_TUNNEL:
+ case OVS_KEY_ATTR_TUNNEL_INFO: {
+ struct ovs_tunnel_info *tun_info = nla_data(ovs_key);
+
start = nla_nest_start(skb, OVS_ACTION_ATTR_SET);
if (!start)
return -EMSGSIZE;
- err = ipv4_tun_to_nlattr(skb, nla_data(ovs_key),
- nla_data(ovs_key));
+ err = ipv4_tun_to_nlattr(skb, &tun_info->tunnel,
+ nla_data(ovs_key));
if (err)
return err;
nla_nest_end(skb, start);
break;
+ }
default:
if (nla_put(skb, OVS_ACTION_ATTR_SET, nla_len(a), ovs_key))
return -EMSGSIZE;
diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c
index 309cca6..fe768bd 100644
--- a/net/openvswitch/vport-gre.c
+++ b/net/openvswitch/vport-gre.c
@@ -63,8 +63,10 @@ static __be16 filter_tnl_flags(__be16 flags)
static struct sk_buff *__build_header(struct sk_buff *skb,
int tunnel_hlen)
{
- const struct ovs_key_ipv4_tunnel *tun_key = OVS_CB(skb)->egress_tun_key;
struct tnl_ptk_info tpi;
+ const struct ovs_key_ipv4_tunnel *tun_key;
+
+ tun_key = &OVS_CB(skb)->egress_tun_info->tunnel;
skb = gre_handle_offloads(skb, !!(tun_key->tun_flags & TUNNEL_CSUM));
if (IS_ERR(skb))
@@ -92,7 +94,7 @@ static __be64 key_to_tunnel_id(__be32 key, __be32 seq)
static int gre_rcv(struct sk_buff *skb,
const struct tnl_ptk_info *tpi)
{
- struct ovs_key_ipv4_tunnel tun_key;
+ struct ovs_tunnel_info tun_info;
struct ovs_net *ovs_net;
struct vport *vport;
__be64 key;
@@ -103,10 +105,10 @@ static int gre_rcv(struct sk_buff *skb,
return PACKET_REJECT;
key = key_to_tunnel_id(tpi->key, tpi->seq);
- ovs_flow_tun_key_init(&tun_key, ip_hdr(skb), key,
- filter_tnl_flags(tpi->flags));
+ ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), key,
+ filter_tnl_flags(tpi->flags));
- ovs_vport_receive(vport, skb, &tun_key);
+ ovs_vport_receive(vport, skb, &tun_info);
return PACKET_RCVD;
}
@@ -137,12 +139,12 @@ static int gre_tnl_send(struct vport *vport, struct sk_buff *skb)
__be16 df;
int err;
- if (unlikely(!OVS_CB(skb)->egress_tun_key)) {
+ if (unlikely(!OVS_CB(skb)->egress_tun_info)) {
err = -EINVAL;
goto error;
}
- tun_key = OVS_CB(skb)->egress_tun_key;
+ tun_key = &OVS_CB(skb)->egress_tun_info->tunnel;
/* Route lookup */
memset(&fl, 0, sizeof(fl));
fl.daddr = tun_key->ipv4_dst;
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index f19539b..5fbff2c 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -58,7 +58,7 @@ static inline struct vxlan_port *vxlan_vport(const struct vport *vport)
/* Called with rcu_read_lock and BH disabled. */
static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, __be32 vx_vni)
{
- struct ovs_key_ipv4_tunnel tun_key;
+ struct ovs_tunnel_info tun_info;
struct vport *vport = vs->data;
struct iphdr *iph;
__be64 key;
@@ -66,9 +66,9 @@ static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, __be32 vx_vni)
/* Save outer tunnel values */
iph = ip_hdr(skb);
key = cpu_to_be64(ntohl(vx_vni) >> 8);
- ovs_flow_tun_key_init(&tun_key, iph, key, TUNNEL_KEY);
+ ovs_flow_tun_info_init(&tun_info, iph, key, TUNNEL_KEY);
- ovs_vport_receive(vport, skb, &tun_key);
+ ovs_vport_receive(vport, skb, &tun_info);
}
static int vxlan_get_options(const struct vport *vport, struct sk_buff *skb)
@@ -147,12 +147,12 @@ static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
__be16 df;
int err;
- if (unlikely(!OVS_CB(skb)->egress_tun_key)) {
+ if (unlikely(!OVS_CB(skb)->egress_tun_info)) {
err = -EINVAL;
goto error;
}
- tun_key = OVS_CB(skb)->egress_tun_key;
+ tun_key = &OVS_CB(skb)->egress_tun_info->tunnel;
/* Route lookup */
memset(&fl, 0, sizeof(fl));
fl.daddr = tun_key->ipv4_dst;
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index 5df8377..3e50ee8 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -432,7 +432,7 @@ u32 ovs_vport_find_upcall_portid(const struct vport *p, struct sk_buff *skb)
* skb->data should point to the Ethernet header.
*/
void ovs_vport_receive(struct vport *vport, struct sk_buff *skb,
- struct ovs_key_ipv4_tunnel *tun_key)
+ struct ovs_tunnel_info *tun_info)
{
struct pcpu_sw_netstats *stats;
struct sw_flow_key key;
@@ -445,9 +445,9 @@ void ovs_vport_receive(struct vport *vport, struct sk_buff *skb,
u64_stats_update_end(&stats->syncp);
OVS_CB(skb)->input_vport = vport;
- OVS_CB(skb)->egress_tun_key = NULL;
+ OVS_CB(skb)->egress_tun_info = NULL;
/* Extract flow from 'skb' into 'key'. */
- error = ovs_flow_key_extract(tun_key, skb, &key);
+ error = ovs_flow_key_extract(tun_info, skb, &key);
if (unlikely(error)) {
kfree_skb(skb);
return;
diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h
index 0efd62f..e28964a 100644
--- a/net/openvswitch/vport.h
+++ b/net/openvswitch/vport.h
@@ -207,7 +207,7 @@ static inline struct vport *vport_from_priv(void *priv)
}
void ovs_vport_receive(struct vport *, struct sk_buff *,
- struct ovs_key_ipv4_tunnel *);
+ struct ovs_tunnel_info *);
/* List of statically compiled vport implementations. Don't forget to also
* add yours to the list at the top of vport.c. */
--
1.7.9.5
^ permalink raw reply related
* [net-next 5/6] openvswitch: Factor out allocation and verification of actions.
From: Andy Zhou @ 2014-10-02 8:04 UTC (permalink / raw)
To: davem; +Cc: netdev, Jesse Gross, Andy Zhou
In-Reply-To: <1412237085-27215-1-git-send-email-azhou@nicira.com>
From: Jesse Gross <jesse@nicira.com>
As the size of the flow key grows, it can put some pressure on the
stack. This is particularly true in ovs_flow_cmd_set(), which needs several
copies of the key on the stack. One of those uses is logically separate,
so this factors it out to reduce stack pressure and improve readibility.
Signed-off-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: Andy Zhou <azhou@nicira.com>
---
net/openvswitch/datapath.c | 38 +++++++++++++++++++++++++++-----------
1 file changed, 27 insertions(+), 11 deletions(-)
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index f6bd93d..010125c 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -933,11 +933,34 @@ error:
return error;
}
+static struct sw_flow_actions *get_flow_actions(const struct nlattr *a,
+ const struct sw_flow_key *key,
+ const struct sw_flow_mask *mask)
+{
+ struct sw_flow_actions *acts;
+ struct sw_flow_key masked_key;
+ int error;
+
+ acts = ovs_nla_alloc_flow_actions(nla_len(a));
+ if (IS_ERR(acts))
+ return acts;
+
+ ovs_flow_mask_key(&masked_key, key, mask);
+ error = ovs_nla_copy_actions(a, &masked_key, 0, &acts);
+ if (error) {
+ OVS_NLERR("Flow actions may not be safe on all matching packets.\n");
+ kfree(acts);
+ return ERR_PTR(error);
+ }
+
+ return acts;
+}
+
static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info)
{
struct nlattr **a = info->attrs;
struct ovs_header *ovs_header = info->userhdr;
- struct sw_flow_key key, masked_key;
+ struct sw_flow_key key;
struct sw_flow *flow;
struct sw_flow_mask mask;
struct sk_buff *reply = NULL;
@@ -959,17 +982,10 @@ static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info)
/* Validate actions. */
if (a[OVS_FLOW_ATTR_ACTIONS]) {
- acts = ovs_nla_alloc_flow_actions(nla_len(a[OVS_FLOW_ATTR_ACTIONS]));
- error = PTR_ERR(acts);
- if (IS_ERR(acts))
+ acts = get_flow_actions(a[OVS_FLOW_ATTR_ACTIONS], &key, &mask);
+ if (IS_ERR(acts)) {
+ error = PTR_ERR(acts);
goto error;
-
- ovs_flow_mask_key(&masked_key, &key, &mask);
- error = ovs_nla_copy_actions(a[OVS_FLOW_ATTR_ACTIONS],
- &masked_key, 0, &acts);
- if (error) {
- OVS_NLERR("Flow actions may not be safe on all matching packets.\n");
- goto err_kfree_acts;
}
}
--
1.7.9.5
^ permalink raw reply related
* [net-next 6/6] openvswitch: Add support for Geneve tunneling.
From: Andy Zhou @ 2014-10-02 8:04 UTC (permalink / raw)
To: davem; +Cc: netdev, Jesse Gross, Andy Zhou
In-Reply-To: <1412237085-27215-1-git-send-email-azhou@nicira.com>
From: Jesse Gross <jesse@nicira.com>
The Openvswitch implementation is completely agnostic to the options
that are in use and can handle newly defined options without
further work. It does this by simply matching on a byte array
of options and allowing userspace to setup flows on this array.
Signed-off-by: Jesse Gross <jesse@nicira.com>
Signed-off-by: Andy Zhou <azhou@nicira.com>
---
include/net/ip_tunnels.h | 21 ++--
include/uapi/linux/openvswitch.h | 2 +
net/openvswitch/Kconfig | 11 ++
net/openvswitch/Makefile | 4 +
net/openvswitch/datapath.c | 5 +-
net/openvswitch/flow.c | 20 +++-
net/openvswitch/flow.h | 20 +++-
net/openvswitch/flow_netlink.c | 176 +++++++++++++++++++++++-----
net/openvswitch/vport-geneve.c | 236 ++++++++++++++++++++++++++++++++++++++
net/openvswitch/vport-gre.c | 2 +-
net/openvswitch/vport-vxlan.c | 2 +-
net/openvswitch/vport.c | 3 +
net/openvswitch/vport.h | 1 +
13 files changed, 461 insertions(+), 42 deletions(-)
create mode 100644 net/openvswitch/vport-geneve.c
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index a9ce155..5bc6ede 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -86,17 +86,18 @@ struct ip_tunnel {
struct gro_cells gro_cells;
};
-#define TUNNEL_CSUM __cpu_to_be16(0x01)
-#define TUNNEL_ROUTING __cpu_to_be16(0x02)
-#define TUNNEL_KEY __cpu_to_be16(0x04)
-#define TUNNEL_SEQ __cpu_to_be16(0x08)
-#define TUNNEL_STRICT __cpu_to_be16(0x10)
-#define TUNNEL_REC __cpu_to_be16(0x20)
-#define TUNNEL_VERSION __cpu_to_be16(0x40)
-#define TUNNEL_NO_KEY __cpu_to_be16(0x80)
+#define TUNNEL_CSUM __cpu_to_be16(0x01)
+#define TUNNEL_ROUTING __cpu_to_be16(0x02)
+#define TUNNEL_KEY __cpu_to_be16(0x04)
+#define TUNNEL_SEQ __cpu_to_be16(0x08)
+#define TUNNEL_STRICT __cpu_to_be16(0x10)
+#define TUNNEL_REC __cpu_to_be16(0x20)
+#define TUNNEL_VERSION __cpu_to_be16(0x40)
+#define TUNNEL_NO_KEY __cpu_to_be16(0x80)
#define TUNNEL_DONT_FRAGMENT __cpu_to_be16(0x0100)
-#define TUNNEL_OAM __cpu_to_be16(0x0200)
-#define TUNNEL_CRIT_OPT __cpu_to_be16(0x0400)
+#define TUNNEL_OAM __cpu_to_be16(0x0200)
+#define TUNNEL_CRIT_OPT __cpu_to_be16(0x0400)
+#define TUNNEL_OPTIONS_PRESENT __cpu_to_be16(0x0800)
struct tnl_ptk_info {
__be16 flags;
diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index 6753032..435eabc 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -192,6 +192,7 @@ enum ovs_vport_type {
OVS_VPORT_TYPE_INTERNAL, /* network device implemented by datapath */
OVS_VPORT_TYPE_GRE, /* GRE tunnel. */
OVS_VPORT_TYPE_VXLAN, /* VXLAN tunnel. */
+ OVS_VPORT_TYPE_GENEVE, /* Geneve tunnel. */
__OVS_VPORT_TYPE_MAX
};
@@ -310,6 +311,7 @@ enum ovs_tunnel_key_attr {
OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT, /* No argument, set DF. */
OVS_TUNNEL_KEY_ATTR_CSUM, /* No argument. CSUM packet. */
OVS_TUNNEL_KEY_ATTR_OAM, /* No argument. OAM frame. */
+ OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS, /* Array of Geneve options. */
__OVS_TUNNEL_KEY_ATTR_MAX
};
diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig
index 6ecf491..ba3bb82 100644
--- a/net/openvswitch/Kconfig
+++ b/net/openvswitch/Kconfig
@@ -54,3 +54,14 @@ config OPENVSWITCH_VXLAN
Say N to exclude this support and reduce the binary size.
If unsure, say Y.
+
+config OPENVSWITCH_GENEVE
+ bool "Open vSwitch Geneve tunneling support"
+ depends on INET
+ depends on OPENVSWITCH
+ depends on GENEVE && !(OPENVSWITCH=y && GENEVE=m)
+ default y
+ ---help---
+ If you say Y here, then the Open vSwitch will be able create geneve vport.
+
+ Say N to exclude this support and reduce the binary size.
diff --git a/net/openvswitch/Makefile b/net/openvswitch/Makefile
index 3591cb5..9a33a27 100644
--- a/net/openvswitch/Makefile
+++ b/net/openvswitch/Makefile
@@ -15,6 +15,10 @@ openvswitch-y := \
vport-internal_dev.o \
vport-netdev.o
+ifneq ($(CONFIG_OPENVSWITCH_GENEVE),)
+openvswitch-y += vport-geneve.o
+endif
+
ifneq ($(CONFIG_OPENVSWITCH_VXLAN),)
openvswitch-y += vport-vxlan.o
endif
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 010125c..2e31d9e 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -370,6 +370,7 @@ static size_t key_attr_size(void)
+ nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT */
+ nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_CSUM */
+ nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_OAM */
+ + nla_total_size(256) /* OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS */
+ nla_total_size(4) /* OVS_KEY_ATTR_IN_PORT */
+ nla_total_size(4) /* OVS_KEY_ATTR_SKB_MARK */
+ nla_total_size(12) /* OVS_KEY_ATTR_ETHERNET */
@@ -556,10 +557,12 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
err = ovs_nla_copy_actions(a[OVS_PACKET_ATTR_ACTIONS],
&flow->key, 0, &acts);
- rcu_assign_pointer(flow->sf_acts, acts);
if (err)
goto err_flow_free;
+ rcu_assign_pointer(flow->sf_acts, acts);
+
+ OVS_CB(packet)->egress_tun_info = NULL;
OVS_CB(packet)->flow = flow;
packet->priority = flow->key.phy.priority;
packet->mark = flow->key.phy.skb_mark;
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index 2924cb3..62db02b 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -448,6 +448,9 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
int error;
struct ethhdr *eth;
+ /* Flags are always used as part of stats */
+ key->tp.flags = 0;
+
skb_reset_mac_header(skb);
/* Link layer. We are guaranteed to have at least the 14 byte Ethernet
@@ -646,10 +649,23 @@ int ovs_flow_key_extract(struct ovs_tunnel_info *tun_info,
struct sk_buff *skb, struct sw_flow_key *key)
{
/* Extract metadata from packet. */
- if (tun_info)
+ if (tun_info) {
memcpy(&key->tun_key, &tun_info->tunnel, sizeof(key->tun_key));
- else
+
+ if (tun_info->options) {
+ BUILD_BUG_ON((1 << (sizeof(tun_info->options_len) *
+ 8)) - 1
+ > sizeof(key->tun_opts));
+ memcpy(GENEVE_OPTS(key, tun_info->options_len),
+ tun_info->options, tun_info->options_len);
+ key->tun_opts_len = tun_info->options_len;
+ } else {
+ key->tun_opts_len = 0;
+ }
+ } else {
+ key->tun_opts_len = 0;
memset(&key->tun_key, 0, sizeof(key->tun_key));
+ }
key->phy.priority = skb->priority;
key->phy.in_port = OVS_CB(skb)->input_vport->port_no;
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index fe5a71b..7181331 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -51,11 +51,24 @@ struct ovs_key_ipv4_tunnel {
struct ovs_tunnel_info {
struct ovs_key_ipv4_tunnel tunnel;
+ struct geneve_opt *options;
+ u8 options_len;
};
+/* Store options at the end of the array if they are less than the
+ * maximum size. This allows us to get the benefits of variable length
+ * matching for small options.
+ */
+#define GENEVE_OPTS(flow_key, opt_len) \
+ ((struct geneve_opt *)((flow_key)->tun_opts + \
+ FIELD_SIZEOF(struct sw_flow_key, tun_opts) - \
+ opt_len))
+
static inline void ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info,
const struct iphdr *iph,
- __be64 tun_id, __be16 tun_flags)
+ __be64 tun_id, __be16 tun_flags,
+ struct geneve_opt *opts,
+ u8 opts_len)
{
tun_info->tunnel.tun_id = tun_id;
tun_info->tunnel.ipv4_src = iph->saddr;
@@ -67,9 +80,14 @@ static inline void ovs_flow_tun_info_init(struct ovs_tunnel_info *tun_info,
/* clear struct padding. */
memset((unsigned char *)&tun_info->tunnel + OVS_TUNNEL_KEY_SIZE, 0,
sizeof(tun_info->tunnel) - OVS_TUNNEL_KEY_SIZE);
+
+ tun_info->options = opts;
+ tun_info->options_len = opts_len;
}
struct sw_flow_key {
+ u8 tun_opts[255];
+ u8 tun_opts_len;
struct ovs_key_ipv4_tunnel tun_key; /* Encapsulating tunnel key. */
struct {
u32 priority; /* Packet QoS priority. */
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 5d6194d..368f233 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -42,6 +42,7 @@
#include <linux/icmp.h>
#include <linux/icmpv6.h>
#include <linux/rculist.h>
+#include <net/geneve.h>
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/ndisc.h>
@@ -88,18 +89,20 @@ static void update_range__(struct sw_flow_match *match,
} \
} while (0)
-#define SW_FLOW_KEY_MEMCPY(match, field, value_p, len, is_mask) \
- do { \
- update_range__(match, offsetof(struct sw_flow_key, field), \
- len, is_mask); \
- if (is_mask) { \
- if ((match)->mask) \
- memcpy(&(match)->mask->key.field, value_p, len);\
- } else { \
- memcpy(&(match)->key->field, value_p, len); \
- } \
+#define SW_FLOW_KEY_MEMCPY_OFFSET(match, offset, value_p, len, is_mask) \
+ do { \
+ update_range__(match, offset, len, is_mask); \
+ if (is_mask) \
+ memcpy((u8 *)&(match)->mask->key + offset, value_p, \
+ len); \
+ else \
+ memcpy((u8 *)(match)->key + offset, value_p, len); \
} while (0)
+#define SW_FLOW_KEY_MEMCPY(match, field, value_p, len, is_mask) \
+ SW_FLOW_KEY_MEMCPY_OFFSET(match, offsetof(struct sw_flow_key, field), \
+ value_p, len, is_mask)
+
static u16 range_n_bytes(const struct sw_flow_key_range *range)
{
return range->end - range->start;
@@ -335,6 +338,7 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
int rem;
bool ttl = false;
__be16 tun_flags = 0;
+ unsigned long opt_key_offset;
nla_for_each_nested(a, attr, rem) {
int type = nla_type(a);
@@ -347,6 +351,7 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
[OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT] = 0,
[OVS_TUNNEL_KEY_ATTR_CSUM] = 0,
[OVS_TUNNEL_KEY_ATTR_OAM] = 0,
+ [OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS] = -1,
};
if (type > OVS_TUNNEL_KEY_ATTR_MAX) {
@@ -355,7 +360,8 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
return -EINVAL;
}
- if (ovs_tunnel_key_lens[type] != nla_len(a)) {
+ if (ovs_tunnel_key_lens[type] != nla_len(a) &&
+ ovs_tunnel_key_lens[type] != -1) {
OVS_NLERR("IPv4 tunnel attribute type has unexpected "
" length (type=%d, length=%d, expected=%d).\n",
type, nla_len(a), ovs_tunnel_key_lens[type]);
@@ -394,7 +400,60 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
case OVS_TUNNEL_KEY_ATTR_OAM:
tun_flags |= TUNNEL_OAM;
break;
+ case OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS:
+ tun_flags |= TUNNEL_OPTIONS_PRESENT;
+ if (nla_len(a) > sizeof(match->key->tun_opts)) {
+ OVS_NLERR("Geneve option length exceeds maximum size (len %d, max %zu).\n",
+ nla_len(a),
+ sizeof(match->key->tun_opts));
+ return -EINVAL;
+ }
+
+ if (nla_len(a) % 4 != 0) {
+ OVS_NLERR("Geneve option length is not a multiple of 4 (len %d).\n",
+ nla_len(a));
+ return -EINVAL;
+ }
+
+ /* We need to record the length of the options passed
+ * down, otherwise packets with the same format but
+ * additional options will be silently matched.
+ */
+ if (!is_mask) {
+ SW_FLOW_KEY_PUT(match, tun_opts_len, nla_len(a),
+ false);
+ } else {
+ /* This is somewhat unusual because it looks at
+ * both the key and mask while parsing the
+ * attributes (and by extension assumes the key
+ * is parsed first). Normally, we would verify
+ * that each is the correct length and that the
+ * attributes line up in the validate function.
+ * However, that is difficult because this is
+ * variable length and we won't have the
+ * information later.
+ */
+ if (match->key->tun_opts_len != nla_len(a)) {
+ OVS_NLERR("Geneve option key length (%d) is different from mask length (%d).",
+ match->key->tun_opts_len,
+ nla_len(a));
+ return -EINVAL;
+ }
+
+ SW_FLOW_KEY_PUT(match, tun_opts_len, 0xff,
+ true);
+ }
+
+ opt_key_offset = (unsigned long)GENEVE_OPTS(
+ (struct sw_flow_key *)0,
+ nla_len(a));
+ SW_FLOW_KEY_MEMCPY_OFFSET(match, opt_key_offset,
+ nla_data(a), nla_len(a),
+ is_mask);
+ break;
default:
+ OVS_NLERR("Unknown IPv4 tunnel attribute (%d).\n",
+ type);
return -EINVAL;
}
}
@@ -421,16 +480,11 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr,
return 0;
}
-static int ipv4_tun_to_nlattr(struct sk_buff *skb,
- const struct ovs_key_ipv4_tunnel *tun_key,
- const struct ovs_key_ipv4_tunnel *output)
+static int __ipv4_tun_to_nlattr(struct sk_buff *skb,
+ const struct ovs_key_ipv4_tunnel *output,
+ const struct geneve_opt *tun_opts,
+ int swkey_tun_opts_len)
{
- struct nlattr *nla;
-
- nla = nla_nest_start(skb, OVS_KEY_ATTR_TUNNEL);
- if (!nla)
- return -EMSGSIZE;
-
if (output->tun_flags & TUNNEL_KEY &&
nla_put_be64(skb, OVS_TUNNEL_KEY_ATTR_ID, output->tun_id))
return -EMSGSIZE;
@@ -454,12 +508,35 @@ static int ipv4_tun_to_nlattr(struct sk_buff *skb,
if ((output->tun_flags & TUNNEL_OAM) &&
nla_put_flag(skb, OVS_TUNNEL_KEY_ATTR_OAM))
return -EMSGSIZE;
+ if (tun_opts &&
+ nla_put(skb, OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS,
+ swkey_tun_opts_len, tun_opts))
+ return -EMSGSIZE;
- nla_nest_end(skb, nla);
return 0;
}
+static int ipv4_tun_to_nlattr(struct sk_buff *skb,
+ const struct ovs_key_ipv4_tunnel *output,
+ const struct geneve_opt *tun_opts,
+ int swkey_tun_opts_len)
+{
+ struct nlattr *nla;
+ int err;
+
+ nla = nla_nest_start(skb, OVS_KEY_ATTR_TUNNEL);
+ if (!nla)
+ return -EMSGSIZE;
+
+ err = __ipv4_tun_to_nlattr(skb, output, tun_opts, swkey_tun_opts_len);
+ if (err)
+ return err;
+
+ nla_nest_end(skb, nla);
+ return 0;
+}
+
static int metadata_from_nlattrs(struct sw_flow_match *match, u64 *attrs,
const struct nlattr **a, bool is_mask)
{
@@ -905,9 +982,16 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey,
if (nla_put_u32(skb, OVS_KEY_ATTR_PRIORITY, output->phy.priority))
goto nla_put_failure;
- if ((swkey->tun_key.ipv4_dst || is_mask) &&
- ipv4_tun_to_nlattr(skb, &swkey->tun_key, &output->tun_key))
- goto nla_put_failure;
+ if ((swkey->tun_key.ipv4_dst || is_mask)) {
+ const struct geneve_opt *opts = NULL;
+
+ if (output->tun_key.tun_flags & TUNNEL_OPTIONS_PRESENT)
+ opts = GENEVE_OPTS(output, swkey->tun_opts_len);
+
+ if (ipv4_tun_to_nlattr(skb, &output->tun_key, opts,
+ swkey->tun_opts_len))
+ goto nla_put_failure;
+ }
if (swkey->phy.in_port == DP_MAX_PORTS) {
if (is_mask && (output->phy.in_port == 0xffff))
@@ -1290,17 +1374,55 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
if (err)
return err;
+ if (key.tun_opts_len) {
+ struct geneve_opt *option = GENEVE_OPTS(&key,
+ key.tun_opts_len);
+ int opts_len = key.tun_opts_len;
+ bool crit_opt = false;
+
+ while (opts_len > 0) {
+ int len;
+
+ if (opts_len < sizeof(*option))
+ return -EINVAL;
+
+ len = sizeof(*option) + option->length * 4;
+ if (len > opts_len)
+ return -EINVAL;
+
+ crit_opt |= !!(option->type & GENEVE_CRIT_OPT_TYPE);
+
+ option = (struct geneve_opt *)((u8 *)option + len);
+ opts_len -= len;
+ };
+
+ key.tun_key.tun_flags |= crit_opt ? TUNNEL_CRIT_OPT : 0;
+ };
+
start = add_nested_action_start(sfa, OVS_ACTION_ATTR_SET);
if (start < 0)
return start;
a = __add_action(sfa, OVS_KEY_ATTR_TUNNEL_INFO, NULL,
- sizeof(*tun_info));
+ sizeof(*tun_info) + key.tun_opts_len);
if (IS_ERR(a))
return PTR_ERR(a);
tun_info = nla_data(a);
tun_info->tunnel = key.tun_key;
+ tun_info->options_len = key.tun_opts_len;
+
+ if (tun_info->options_len) {
+ /* We need to store the options in the action itself since
+ * everything else will go away after flow setup. We can append
+ * it to tun_info and then point there.
+ */
+ memcpy((tun_info + 1), GENEVE_OPTS(&key, key.tun_opts_len),
+ key.tun_opts_len);
+ tun_info->options = (struct geneve_opt *)(tun_info + 1);
+ } else {
+ tun_info->options = NULL;
+ }
add_nested_action_end(*sfa, start);
@@ -1592,7 +1714,9 @@ static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb)
return -EMSGSIZE;
err = ipv4_tun_to_nlattr(skb, &tun_info->tunnel,
- nla_data(ovs_key));
+ tun_info->options_len ?
+ tun_info->options : NULL,
+ tun_info->options_len);
if (err)
return err;
nla_nest_end(skb, start);
diff --git a/net/openvswitch/vport-geneve.c b/net/openvswitch/vport-geneve.c
new file mode 100644
index 0000000..5572d48
--- /dev/null
+++ b/net/openvswitch/vport-geneve.c
@@ -0,0 +1,236 @@
+/*
+ * Copyright (c) 2014 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/version.h>
+
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/net.h>
+#include <linux/rculist.h>
+#include <linux/udp.h>
+#include <linux/if_vlan.h>
+
+#include <net/geneve.h>
+#include <net/icmp.h>
+#include <net/ip.h>
+#include <net/route.h>
+#include <net/udp.h>
+#include <net/xfrm.h>
+
+#include "datapath.h"
+#include "vport.h"
+
+/**
+ * struct geneve_port - Keeps track of open UDP ports
+ * @sock: The socket created for this port number.
+ * @name: vport name.
+ */
+struct geneve_port {
+ struct geneve_sock *gs;
+ char name[IFNAMSIZ];
+};
+
+static LIST_HEAD(geneve_ports);
+
+static inline struct geneve_port *geneve_vport(const struct vport *vport)
+{
+ return vport_priv(vport);
+}
+
+static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb)
+{
+ return (struct genevehdr *)(udp_hdr(skb) + 1);
+}
+
+/* Convert 64 bit tunnel ID to 24 bit VNI. */
+static void tunnel_id_to_vni(__be64 tun_id, __u8 *vni)
+{
+#ifdef __BIG_ENDIAN
+ vni[0] = (__force __u8)(tun_id >> 16);
+ vni[1] = (__force __u8)(tun_id >> 8);
+ vni[2] = (__force __u8)tun_id;
+#else
+ vni[0] = (__force __u8)((__force u64)tun_id >> 40);
+ vni[1] = (__force __u8)((__force u64)tun_id >> 48);
+ vni[2] = (__force __u8)((__force u64)tun_id >> 56);
+#endif
+}
+
+/* Convert 24 bit VNI to 64 bit tunnel ID. */
+static __be64 vni_to_tunnel_id(__u8 *vni)
+{
+#ifdef __BIG_ENDIAN
+ return (vni[0] << 16) | (vni[1] << 8) | vni[2];
+#else
+ return (__force __be64)(((__force u64)vni[0] << 40) |
+ ((__force u64)vni[1] << 48) |
+ ((__force u64)vni[2] << 56));
+#endif
+}
+
+static void geneve_rcv(struct geneve_sock *gs, struct sk_buff *skb)
+{
+ struct vport *vport = gs->rcv_data;
+ struct genevehdr *geneveh = geneve_hdr(skb);
+ int opts_len;
+ struct ovs_tunnel_info tun_info;
+ __be64 key;
+ __be16 flags;
+
+ opts_len = geneveh->opt_len * 4;
+
+ flags = TUNNEL_KEY | TUNNEL_OPTIONS_PRESENT |
+ (udp_hdr(skb)->check != 0 ? TUNNEL_CSUM : 0) |
+ (geneveh->oam ? TUNNEL_OAM : 0) |
+ (geneveh->critical ? TUNNEL_CRIT_OPT : 0);
+
+ key = vni_to_tunnel_id(geneveh->vni);
+
+ ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), key, flags,
+ geneveh->options, opts_len);
+
+ ovs_vport_receive(vport, skb, &tun_info);
+}
+
+static int geneve_get_options(const struct vport *vport,
+ struct sk_buff *skb)
+{
+ struct geneve_port *geneve_port = geneve_vport(vport);
+ __be16 sport;
+
+ sport = ntohs(inet_sk(geneve_port->gs->sock->sk)->inet_sport);
+ if (nla_put_u16(skb, OVS_TUNNEL_ATTR_DST_PORT, sport))
+ return -EMSGSIZE;
+ return 0;
+}
+
+static void geneve_tnl_destroy(struct vport *vport)
+{
+ struct geneve_port *geneve_port = geneve_vport(vport);
+
+ geneve_sock_release(geneve_port->gs);
+
+ ovs_vport_deferred_free(vport);
+}
+
+static struct vport *geneve_tnl_create(const struct vport_parms *parms)
+{
+ struct net *net = ovs_dp_get_net(parms->dp);
+ struct nlattr *options = parms->options;
+ struct geneve_port *geneve_port;
+ struct geneve_sock *gs;
+ struct vport *vport;
+ struct nlattr *a;
+ int err;
+ u16 dst_port;
+
+ if (!options) {
+ err = -EINVAL;
+ goto error;
+ }
+
+ a = nla_find_nested(options, OVS_TUNNEL_ATTR_DST_PORT);
+ if (a && nla_len(a) == sizeof(u16)) {
+ dst_port = nla_get_u16(a);
+ } else {
+ /* Require destination port from userspace. */
+ err = -EINVAL;
+ goto error;
+ }
+
+ vport = ovs_vport_alloc(sizeof(struct geneve_port),
+ &ovs_geneve_vport_ops, parms);
+ if (IS_ERR(vport))
+ return vport;
+
+ geneve_port = geneve_vport(vport);
+ strncpy(geneve_port->name, parms->name, IFNAMSIZ);
+
+ gs = geneve_sock_add(net, htons(dst_port), geneve_rcv, vport, true, 0);
+ if (IS_ERR(gs)) {
+ ovs_vport_free(vport);
+ return (void *)gs;
+ }
+ geneve_port->gs = gs;
+
+ return vport;
+error:
+ return ERR_PTR(err);
+}
+
+static int geneve_tnl_send(struct vport *vport, struct sk_buff *skb)
+{
+ struct ovs_key_ipv4_tunnel *tun_key;
+ struct ovs_tunnel_info *tun_info;
+ struct net *net = ovs_dp_get_net(vport->dp);
+ struct geneve_port *geneve_port = geneve_vport(vport);
+ __be16 dport = inet_sk(geneve_port->gs->sock->sk)->inet_sport;
+ __be16 sport;
+ struct rtable *rt;
+ struct flowi4 fl;
+ u8 vni[3];
+ __be16 df;
+ int err;
+
+ tun_info = OVS_CB(skb)->egress_tun_info;
+ if (unlikely(!tun_info)) {
+ err = -EINVAL;
+ goto error;
+ }
+
+ tun_key = &tun_info->tunnel;
+
+ /* Route lookup */
+ memset(&fl, 0, sizeof(fl));
+ fl.daddr = tun_key->ipv4_dst;
+ fl.saddr = tun_key->ipv4_src;
+ fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos);
+ fl.flowi4_mark = skb->mark;
+ fl.flowi4_proto = IPPROTO_UDP;
+
+ rt = ip_route_output_key(net, &fl);
+ if (IS_ERR(rt)) {
+ err = PTR_ERR(rt);
+ goto error;
+ }
+
+ df = tun_key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0;
+ sport = udp_flow_src_port(net, skb, 1, USHRT_MAX, true);
+ tunnel_id_to_vni(tun_key->tun_id, vni);
+ skb->ignore_df = 1;
+
+ err = geneve_xmit_skb(geneve_port->gs, rt, skb, fl.saddr,
+ tun_key->ipv4_dst, tun_key->ipv4_tos,
+ tun_key->ipv4_ttl, df, sport, dport,
+ tun_key->tun_flags, vni,
+ tun_info->options_len, (u8 *)tun_info->options,
+ false);
+ if (err < 0)
+ ip_rt_put(rt);
+error:
+ return err;
+}
+
+static const char *geneve_get_name(const struct vport *vport)
+{
+ struct geneve_port *geneve_port = geneve_vport(vport);
+
+ return geneve_port->name;
+}
+
+const struct vport_ops ovs_geneve_vport_ops = {
+ .type = OVS_VPORT_TYPE_GENEVE,
+ .create = geneve_tnl_create,
+ .destroy = geneve_tnl_destroy,
+ .get_name = geneve_get_name,
+ .get_options = geneve_get_options,
+ .send = geneve_tnl_send,
+};
diff --git a/net/openvswitch/vport-gre.c b/net/openvswitch/vport-gre.c
index fe768bd..108b82d 100644
--- a/net/openvswitch/vport-gre.c
+++ b/net/openvswitch/vport-gre.c
@@ -106,7 +106,7 @@ static int gre_rcv(struct sk_buff *skb,
key = key_to_tunnel_id(tpi->key, tpi->seq);
ovs_flow_tun_info_init(&tun_info, ip_hdr(skb), key,
- filter_tnl_flags(tpi->flags));
+ filter_tnl_flags(tpi->flags), NULL, 0);
ovs_vport_receive(vport, skb, &tun_info);
return PACKET_RCVD;
diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c
index 5fbff2c..2735e01 100644
--- a/net/openvswitch/vport-vxlan.c
+++ b/net/openvswitch/vport-vxlan.c
@@ -66,7 +66,7 @@ static void vxlan_rcv(struct vxlan_sock *vs, struct sk_buff *skb, __be32 vx_vni)
/* Save outer tunnel values */
iph = ip_hdr(skb);
key = cpu_to_be64(ntohl(vx_vni) >> 8);
- ovs_flow_tun_info_init(&tun_info, iph, key, TUNNEL_KEY);
+ ovs_flow_tun_info_init(&tun_info, iph, key, TUNNEL_KEY, NULL, 0);
ovs_vport_receive(vport, skb, &tun_info);
}
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index 3e50ee8..53001b0 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -48,6 +48,9 @@ static const struct vport_ops *vport_ops_list[] = {
#ifdef CONFIG_OPENVSWITCH_VXLAN
&ovs_vxlan_vport_ops,
#endif
+#ifdef CONFIG_OPENVSWITCH_GENEVE
+ &ovs_geneve_vport_ops,
+#endif
};
/* Protected by RCU read lock for reading, ovs_mutex for writing. */
diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h
index e28964a..8942125 100644
--- a/net/openvswitch/vport.h
+++ b/net/openvswitch/vport.h
@@ -215,6 +215,7 @@ extern const struct vport_ops ovs_netdev_vport_ops;
extern const struct vport_ops ovs_internal_vport_ops;
extern const struct vport_ops ovs_gre_vport_ops;
extern const struct vport_ops ovs_vxlan_vport_ops;
+extern const struct vport_ops ovs_geneve_vport_ops;
static inline void ovs_skb_postpush_rcsum(struct sk_buff *skb,
const void *start, unsigned int len)
--
1.7.9.5
^ permalink raw reply related
* Bridge IGMP snooping question
From: Thomas Martitz @ 2014-10-02 8:13 UTC (permalink / raw)
To: herbert, netdev
Hello Linux folks,
I have one question regarding IGMP snooping on bridges, specifically
about leaving multicast groups.
br_multicast_leave_group() has this check early on:
if (!netif_running(br->dev) ||
(port && port->state == BR_STATE_DISABLED) ||
timer_pending(&querier->timer)) /* <- THIS */
goto out;
I'm wondering why the bridge code prevents group leaves if if the
querier timer is pending. From my understanding the timer acts as an
indication whether the local system is the network's querier or not (if
pending then another router is querier). Therefore this check prevents
to leave groups if there is another querier.
I'm wondering what's the rationale for this, if any. It seems to be that
the decision whether an attached client gets mc forwarded is independent
on whether the local system is querier or not. Git log does not reveal
the answer as this check is there from the beginning.
PS: This behavior conflicts with something I'm working.
Thank you very much in advance.
Best regards.
^ permalink raw reply
* [PATCH] net: ethernet: Remove superfluous ether_setup after alloc_etherdev
From: Tobias Klauser @ 2014-10-02 8:15 UTC (permalink / raw)
To: David S. Miller, netdev
Cc: Maxime Ripard, Vince Bridgers, Nicolas Ferre, Wan ZongShun,
Nicolas Pitre, Steve Glendinning, Giuseppe Cavallaro
There is no need to call ether_setup after alloc_ethdev since it was
already called there.
Follow commits c706471b2601 ("net: axienet: remove unnecessary
ether_setup after alloc_etherdev") and 3c87dcbfb36c ("net: ll_temac:
Remove unnecessary ether_setup after alloc_etherdev") and fix the
pattern in all remaining ethernet drivers.
Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
---
drivers/net/ethernet/adi/bfin_mac.c | 3 ---
drivers/net/ethernet/allwinner/sun4i-emac.c | 2 --
drivers/net/ethernet/altera/altera_tse_main.c | 1 -
drivers/net/ethernet/cadence/at91_ether.c | 1 -
drivers/net/ethernet/calxeda/xgmac.c | 1 -
drivers/net/ethernet/davicom/dm9000.c | 3 ---
drivers/net/ethernet/ethoc.c | 2 --
drivers/net/ethernet/lantiq_etop.c | 1 -
drivers/net/ethernet/moxa/moxart_ether.c | 1 -
drivers/net/ethernet/netx-eth.c | 2 --
drivers/net/ethernet/nuvoton/w90p910_ether.c | 1 -
drivers/net/ethernet/nxp/lpc_eth.c | 3 ---
drivers/net/ethernet/qualcomm/qca_spi.c | 2 --
drivers/net/ethernet/smsc/smc911x.c | 3 ---
drivers/net/ethernet/smsc/smc91x.c | 3 ---
drivers/net/ethernet/smsc/smsc911x.c | 1 -
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 2 --
drivers/net/ethernet/wiznet/w5100.c | 1 -
drivers/net/ethernet/wiznet/w5300.c | 1 -
19 files changed, 34 deletions(-)
diff --git a/drivers/net/ethernet/adi/bfin_mac.c b/drivers/net/ethernet/adi/bfin_mac.c
index afa6684..8ed4d340 100644
--- a/drivers/net/ethernet/adi/bfin_mac.c
+++ b/drivers/net/ethernet/adi/bfin_mac.c
@@ -1692,9 +1692,6 @@ static int bfin_mac_probe(struct platform_device *pdev)
lp->vlan1_mask = ETH_P_8021Q | mii_bus_data->vlan1_mask;
lp->vlan2_mask = ETH_P_8021Q | mii_bus_data->vlan2_mask;
- /* Fill in the fields of the device structure with ethernet values. */
- ether_setup(ndev);
-
ndev->netdev_ops = &bfin_mac_netdev_ops;
ndev->ethtool_ops = &bfin_mac_ethtool_ops;
diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c
index 29b9f08..1fcd556 100644
--- a/drivers/net/ethernet/allwinner/sun4i-emac.c
+++ b/drivers/net/ethernet/allwinner/sun4i-emac.c
@@ -878,8 +878,6 @@ static int emac_probe(struct platform_device *pdev)
emac_powerup(ndev);
emac_reset(db);
- ether_setup(ndev);
-
ndev->netdev_ops = &emac_netdev_ops;
ndev->watchdog_timeo = msecs_to_jiffies(watchdog);
ndev->ethtool_ops = &emac_ethtool_ops;
diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c
index 7330681..fc2d555 100644
--- a/drivers/net/ethernet/altera/altera_tse_main.c
+++ b/drivers/net/ethernet/altera/altera_tse_main.c
@@ -1433,7 +1433,6 @@ static int altera_tse_probe(struct platform_device *pdev)
goto err_free_netdev;
/* initialize netdev */
- ether_setup(ndev);
ndev->mem_start = control_port->start;
ndev->mem_end = control_port->end;
ndev->netdev_ops = &altera_tse_netdev_ops;
diff --git a/drivers/net/ethernet/cadence/at91_ether.c b/drivers/net/ethernet/cadence/at91_ether.c
index 4a79eda..4a24b9a 100644
--- a/drivers/net/ethernet/cadence/at91_ether.c
+++ b/drivers/net/ethernet/cadence/at91_ether.c
@@ -351,7 +351,6 @@ static int __init at91ether_probe(struct platform_device *pdev)
if (res)
goto err_disable_clock;
- ether_setup(dev);
dev->netdev_ops = &at91ether_netdev_ops;
dev->ethtool_ops = &macb_ethtool_ops;
platform_set_drvdata(pdev, dev);
diff --git a/drivers/net/ethernet/calxeda/xgmac.c b/drivers/net/ethernet/calxeda/xgmac.c
index 25d6b2a..47bfea2 100644
--- a/drivers/net/ethernet/calxeda/xgmac.c
+++ b/drivers/net/ethernet/calxeda/xgmac.c
@@ -1735,7 +1735,6 @@ static int xgmac_probe(struct platform_device *pdev)
SET_NETDEV_DEV(ndev, &pdev->dev);
priv = netdev_priv(ndev);
platform_set_drvdata(pdev, ndev);
- ether_setup(ndev);
ndev->netdev_ops = &xgmac_netdev_ops;
ndev->ethtool_ops = &xgmac_ethtool_ops;
spin_lock_init(&priv->stats_lock);
diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c
index 70089c2..f3ba840 100644
--- a/drivers/net/ethernet/davicom/dm9000.c
+++ b/drivers/net/ethernet/davicom/dm9000.c
@@ -1613,9 +1613,6 @@ dm9000_probe(struct platform_device *pdev)
/* from this point we assume that we have found a DM9000 */
- /* driver system function */
- ether_setup(ndev);
-
ndev->netdev_ops = &dm9000_netdev_ops;
ndev->watchdog_timeo = msecs_to_jiffies(watchdog);
ndev->ethtool_ops = &dm9000_ethtool_ops;
diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c
index f3658bd..0bc6c10 100644
--- a/drivers/net/ethernet/ethoc.c
+++ b/drivers/net/ethernet/ethoc.c
@@ -1222,8 +1222,6 @@ static int ethoc_probe(struct platform_device *pdev)
goto error;
}
- ether_setup(netdev);
-
/* setup the net_device structure */
netdev->netdev_ops = ðoc_netdev_ops;
netdev->watchdog_timeo = ETHOC_TIMEOUT;
diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c
index fd4b6ae..2dad4d5 100644
--- a/drivers/net/ethernet/lantiq_etop.c
+++ b/drivers/net/ethernet/lantiq_etop.c
@@ -633,7 +633,6 @@ ltq_etop_init(struct net_device *dev)
int err;
bool random_mac = false;
- ether_setup(dev);
dev->watchdog_timeo = 10 * HZ;
err = ltq_etop_hw_init(dev);
if (err)
diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c
index 2f12c88..bde1b70 100644
--- a/drivers/net/ethernet/moxa/moxart_ether.c
+++ b/drivers/net/ethernet/moxa/moxart_ether.c
@@ -511,7 +511,6 @@ static int moxart_mac_probe(struct platform_device *pdev)
goto init_fail;
}
- ether_setup(ndev);
ndev->netdev_ops = &moxart_netdev_ops;
netif_napi_add(ndev, &priv->napi, moxart_rx_poll, RX_DESC_NUM);
ndev->priv_flags |= IFF_UNICAST_FLT;
diff --git a/drivers/net/ethernet/netx-eth.c b/drivers/net/ethernet/netx-eth.c
index 31eb911..8176c8a 100644
--- a/drivers/net/ethernet/netx-eth.c
+++ b/drivers/net/ethernet/netx-eth.c
@@ -315,8 +315,6 @@ static int netx_eth_enable(struct net_device *ndev)
unsigned int mac4321, mac65;
int running, i;
- ether_setup(ndev);
-
ndev->netdev_ops = &netx_eth_netdev_ops;
ndev->watchdog_timeo = msecs_to_jiffies(5000);
diff --git a/drivers/net/ethernet/nuvoton/w90p910_ether.c b/drivers/net/ethernet/nuvoton/w90p910_ether.c
index 79645f7..379b7fb 100644
--- a/drivers/net/ethernet/nuvoton/w90p910_ether.c
+++ b/drivers/net/ethernet/nuvoton/w90p910_ether.c
@@ -943,7 +943,6 @@ static int w90p910_ether_setup(struct net_device *dev)
{
struct w90p910_ether *ether = netdev_priv(dev);
- ether_setup(dev);
dev->netdev_ops = &w90p910_ether_netdev_ops;
dev->ethtool_ops = &w90p910_ether_ethtool_ops;
diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c
index a44a03c..66fd868 100644
--- a/drivers/net/ethernet/nxp/lpc_eth.c
+++ b/drivers/net/ethernet/nxp/lpc_eth.c
@@ -1377,9 +1377,6 @@ static int lpc_eth_drv_probe(struct platform_device *pdev)
goto err_out_iounmap;
}
- /* Fill in the fields of the device structure with ethernet values. */
- ether_setup(ndev);
-
/* Setup driver functions */
ndev->netdev_ops = &lpc_netdev_ops;
ndev->ethtool_ops = &lpc_eth_ethtool_ops;
diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index 74eb520..2c811f6 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -810,8 +810,6 @@ qcaspi_netdev_setup(struct net_device *dev)
{
struct qcaspi *qca = NULL;
- ether_setup(dev);
-
dev->netdev_ops = &qcaspi_netdev_ops;
qcaspi_set_ethtool_ops(dev);
dev->watchdog_timeo = QCASPI_TX_TIMEOUT;
diff --git a/drivers/net/ethernet/smsc/smc911x.c b/drivers/net/ethernet/smsc/smc911x.c
index 9778cba..e88df9c 100644
--- a/drivers/net/ethernet/smsc/smc911x.c
+++ b/drivers/net/ethernet/smsc/smc911x.c
@@ -1927,9 +1927,6 @@ static int smc911x_probe(struct net_device *dev)
}
dev->irq = irq_canonicalize(dev->irq);
- /* Fill in the fields of the device structure with ethernet values. */
- ether_setup(dev);
-
dev->netdev_ops = &smc911x_netdev_ops;
dev->watchdog_timeo = msecs_to_jiffies(watchdog);
dev->ethtool_ops = &smc911x_ethtool_ops;
diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c
index bcaa41a..5e94d00 100644
--- a/drivers/net/ethernet/smsc/smc91x.c
+++ b/drivers/net/ethernet/smsc/smc91x.c
@@ -1967,9 +1967,6 @@ static int smc_probe(struct net_device *dev, void __iomem *ioaddr,
}
dev->irq = irq_canonicalize(dev->irq);
- /* Fill in the fields of the device structure with ethernet values. */
- ether_setup(dev);
-
dev->watchdog_timeo = msecs_to_jiffies(watchdog);
dev->netdev_ops = &smc_netdev_ops;
dev->ethtool_ops = &smc_ethtool_ops;
diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c
index 5e13fa5..affb29d 100644
--- a/drivers/net/ethernet/smsc/smsc911x.c
+++ b/drivers/net/ethernet/smsc/smsc911x.c
@@ -2255,7 +2255,6 @@ static int smsc911x_init(struct net_device *dev)
if (smsc911x_soft_reset(pdata))
return -ENODEV;
- ether_setup(dev);
dev->flags |= IFF_MULTICAST;
netif_napi_add(dev, &pdata->napi, smsc911x_poll, SMSC_NAPI_WEIGHT);
dev->netdev_ops = &smsc911x_netdev_ops;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 9979f67..6f77a46 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2765,8 +2765,6 @@ struct stmmac_priv *stmmac_dvr_probe(struct device *device,
priv->device = device;
priv->dev = ndev;
- ether_setup(ndev);
-
stmmac_set_ethtool_ops(ndev);
priv->pause = pause;
priv->plat = plat_dat;
diff --git a/drivers/net/ethernet/wiznet/w5100.c b/drivers/net/ethernet/wiznet/w5100.c
index 104d46f..0f56b1c 100644
--- a/drivers/net/ethernet/wiznet/w5100.c
+++ b/drivers/net/ethernet/wiznet/w5100.c
@@ -708,7 +708,6 @@ static int w5100_probe(struct platform_device *pdev)
priv = netdev_priv(ndev);
priv->ndev = ndev;
- ether_setup(ndev);
ndev->netdev_ops = &w5100_netdev_ops;
ndev->ethtool_ops = &w5100_ethtool_ops;
ndev->watchdog_timeo = HZ;
diff --git a/drivers/net/ethernet/wiznet/w5300.c b/drivers/net/ethernet/wiznet/w5300.c
index 1f33c4c..f961f14 100644
--- a/drivers/net/ethernet/wiznet/w5300.c
+++ b/drivers/net/ethernet/wiznet/w5300.c
@@ -620,7 +620,6 @@ static int w5300_probe(struct platform_device *pdev)
priv = netdev_priv(ndev);
priv->ndev = ndev;
- ether_setup(ndev);
ndev->netdev_ops = &w5300_netdev_ops;
ndev->ethtool_ops = &w5300_ethtool_ops;
ndev->watchdog_timeo = HZ;
--
2.0.1
^ permalink raw reply related
* Re: ASIX 88772
From: Christian Riesch @ 2014-10-02 8:16 UTC (permalink / raw)
To: Stam, Michel [FINT]
Cc: netdev@vger.kernel.org, Grant Grundler, Freddy Xin, olofj
In-Reply-To: <C89EFD3CD56F64468D3D206D683A8D2203864153@ldam-msx2.fugro-nl.local>
Hi Michel,
On Thu, Oct 2, 2014 at 9:50 AM, Stam, Michel [FINT] <M.Stam@fugro.nl> wrote:
> LS,
>
> Is it possible for someone to apply this patch?
Patches must be sent in the email body, not as an attachment. Please
use git send-email to send the patch, other mail clients will most
likely break the patch as you already noted. Please send the patch
again.
You should also take the authors of the patch that made the change
(4ad1438f) that you would like to revert on cc, Freddy Xin
<freddy@asix.com.tw> and Grant Grundler <grundler@chromium.org> in
this case.
Regards,
Christian
^ permalink raw reply
* Re: [PATCH] net: ethernet: Remove superfluous ether_setup after alloc_etherdev
From: Tobias Klauser @ 2014-10-02 8:20 UTC (permalink / raw)
To: David S. Miller, netdev
Cc: Maxime Ripard, Vince Bridgers, Nicolas Ferre, Wan ZongShun,
Nicolas Pitre, Steve Glendinning, Giuseppe Cavallaro
In-Reply-To: <1412237730-5811-1-git-send-email-tklauser@distanz.ch>
On 2014-10-02 at 10:15:30 +0200, Tobias Klauser <tklauser@distanz.ch> wrote:
> There is no need to call ether_setup after alloc_ethdev since it was
> already called there.
>
> Follow commits c706471b2601 ("net: axienet: remove unnecessary
> ether_setup after alloc_etherdev") and 3c87dcbfb36c ("net: ll_temac:
> Remove unnecessary ether_setup after alloc_etherdev") and fix the
> pattern in all remaining ethernet drivers.
>
> Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
This patch is for net-next. Sorry for not mentioning this in the subject
right away.
^ permalink raw reply
* [PATCH net] r8152: autoresume before setting MAC address
From: Hayes Wang @ 2014-10-02 8:26 UTC (permalink / raw)
To: netdev-u79uwXL29TY76Z2rM5mHXA
Cc: nic_swsd-Rasf1IRRPZFBDgjK7y7TUQ,
linux-kernel-u79uwXL29TY76Z2rM5mHXA,
linux-usb-u79uwXL29TY76Z2rM5mHXA, Hayes Wang
Resume the device before setting the MAC address.
Signed-off-by: Hayes Wang <hayeswang-Rasf1IRRPZFBDgjK7y7TUQ@public.gmane.org>
---
drivers/net/usb/r8152.c | 16 +++++++++++++---
1 file changed, 13 insertions(+), 3 deletions(-)
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 604ef21..e823358 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -1007,9 +1007,16 @@ static int rtl8152_set_mac_address(struct net_device *netdev, void *p)
{
struct r8152 *tp = netdev_priv(netdev);
struct sockaddr *addr = p;
+ int ret;
+
+ ret = usb_autopm_get_interface(tp->intf);
+ if (ret < 0)
+ goto out1;
- if (!is_valid_ether_addr(addr->sa_data))
- return -EADDRNOTAVAIL;
+ if (!is_valid_ether_addr(addr->sa_data)) {
+ ret = -EADDRNOTAVAIL;
+ goto out2;
+ }
memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
@@ -1017,7 +1024,10 @@ static int rtl8152_set_mac_address(struct net_device *netdev, void *p)
pla_ocp_write(tp, PLA_IDR, BYTE_EN_SIX_BYTES, 8, addr->sa_data);
ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_NORAML);
- return 0;
+out2:
+ usb_autopm_put_interface(tp->intf);
+out1:
+ return ret;
}
static void read_bulk_callback(struct urb *urb)
--
1.9.3
--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH] Don't reset PHY on if_up for ASIX 88772
From: Michel Stam @ 2014-10-02 8:22 UTC (permalink / raw)
To: netdev; +Cc: freddy, grundler, Michel Stam
I've noticed every time the interface is set to 'up,', the kernel
reports that the link speed is set to 100 Mbps/Full Duplex, even
when ethtool is used to set autonegotiation to 'off', half
duplex, 10 Mbps.
It can be tested by:
ifconfig eth0 down
ethtool -s eth0 autoneg off speed 10 duplex half
ifconfig eth0 up
Then checking 'dmesg' for the link speed.
Signed-off-by: Michel Stam <m.stam@fugro.nl>
---
drivers/net/usb/asix_devices.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c
index 5d19409..2c05f6c 100644
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -890,7 +890,7 @@ static const struct driver_info ax88772_info = {
.unbind = ax88772_unbind,
.status = asix_status,
.link_reset = ax88772_link_reset,
- .reset = ax88772_reset,
+ .reset = ax88772_link_reset,
.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR | FLAG_MULTI_PACKET,
.rx_fixup = asix_rx_fixup_common,
.tx_fixup = asix_tx_fixup,
--
1.7.12.1
^ permalink raw reply related
* Re: [PATCH v2 net-next] mlx4: optimize xmit path
From: Jesper Dangaard Brouer @ 2014-10-02 8:29 UTC (permalink / raw)
To: Amir Vadai
Cc: brouer, Eric Dumazet, Or Gerlitz, Alexei Starovoitov,
David S. Miller, Eric Dumazet, John Fastabend, Linux Netdev List,
Or Gerlitz, amira, idos, Yevgeny Petrilin, eyalpe
In-Reply-To: <542D06C1.6090802@mellanox.com>
On Thu, 2 Oct 2014 11:03:13 +0300
Amir Vadai <amirv@mellanox.com> wrote:
> I'm still working on it, but I can't reproduce the numbers that you
> show. On my development machine, I get ~5.5Mpps with burst=8 and ~2Mpps
> with burst=1.
For pktgen it sounds like you either missing:
1) flag QUEUE_MAP_CPU
and/or
2) clone_skb $BIGNUMBER
My usage of pktgen:
http://netoptimizer.blogspot.dk/2014/06/pktgen-for-network-overload-testing.html
--
Best regards,
Jesper Dangaard Brouer
MSc.CS, Sr. Network Kernel Developer at Red Hat
Author of http://www.iptv-analyzer.org
LinkedIn: http://www.linkedin.com/in/brouer
^ permalink raw reply
* Re: [PATCH] net: dsa: Fix build warning for !PM_SLEEP
From: Thierry Reding @ 2014-10-02 8:35 UTC (permalink / raw)
To: David Miller; +Cc: f.fainelli, netdev, linux-kernel
In-Reply-To: <20141001.152452.1973501659924138094.davem@davemloft.net>
[-- Attachment #1: Type: text/plain, Size: 992 bytes --]
On Wed, Oct 01, 2014 at 03:24:52PM -0400, David Miller wrote:
> From: Thierry Reding <thierry.reding@gmail.com>
> Date: Wed, 1 Oct 2014 13:59:00 +0200
>
> > From: Thierry Reding <treding@nvidia.com>
> >
> > The dsa_switch_suspend() and dsa_switch_resume() functions are only used
> > when PM_SLEEP is enabled, so they need #ifdef CONFIG_PM_SLEEP protection
> > to avoid a compiler warning.
> >
> > Signed-off-by: Thierry Reding <treding@nvidia.com>
>
> Applied.
>
> Please, in the future, explicitly indicate what tree your changes
> are against. Through trial and error I figured out that this could
> only apply to net-next, but that's not a good use of my time.
I had assumed that working on top of linux-next is what most people were
doing anyway therefore net-next would be the default to apply patches to
unless otherwise stated.
But if this inconveniences you I'll try to remember to explicitly state
which tree it's based on in the future.
Thierry
[-- Attachment #2: Type: application/pgp-signature, Size: 819 bytes --]
^ permalink raw reply
* Re: [PATCH iproute2] tests: Dont fail cls-testbed.t if tests/cls dir is empty
From: Vadim Kochan @ 2014-10-02 8:35 UTC (permalink / raw)
To: netdev@vger.kernel.org, Stephen Hemminger; +Cc: Vadim Kochan
In-Reply-To: <1412031436-14492-1-git-send-email-vadim4j@gmail.com>
Hi,
Please ignore this patch, I will send modified one with another sibject.
On Tue, Sep 30, 2014 at 1:57 AM, Vadim Kochan <vadim4j@gmail.com> wrote:
> Curently tests/cls-testbed.t tries to run any *.t in
> tests/cls/ folder but such folder does not exist.
>
> The better solution can be like having a generic mechanism which
> allows to SKIP some tests (by return code?).
>
> Signed-off-by: Vadim Kochan <vadim4j@gmail.com>
> ---
> testsuite/tests/cls-testbed.t | 5 +++++
> 1 file changed, 5 insertions(+)
>
> diff --git a/testsuite/tests/cls-testbed.t b/testsuite/tests/cls-testbed.t
> index efae2a5..be32d79 100755
> --- a/testsuite/tests/cls-testbed.t
> +++ b/testsuite/tests/cls-testbed.t
> @@ -5,6 +5,11 @@ source lib/generic.sh
>
> QDISCS="cbq htb dsmark"
>
> +if [ ! -d tests/cls ]; then
> + ts_log "tests/cls folder is empty"
> + exit 0
> +fi
> +
> for q in ${QDISCS}; do
> ts_log "Preparing classifier testbed with qdisc $q"
>
> --
> 2.1.0
>
^ permalink raw reply
* Re: [PATCH 1/2] iproute2: Add support for IPv6 VTI tunnels to ip6tunnel
From: Jiri Pirko @ 2014-10-02 8:41 UTC (permalink / raw)
To: Steffen Klassert; +Cc: Stephen Hemminger, netdev
In-Reply-To: <20140926071056.GB6390@secunet.com>
Fri, Sep 26, 2014 at 09:10:56AM CEST, steffen.klassert@secunet.com wrote:
>
>Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
>---
> ip/ip6tunnel.c | 15 ++++++++++++---
> 1 file changed, 12 insertions(+), 3 deletions(-)
>
>diff --git a/ip/ip6tunnel.c b/ip/ip6tunnel.c
>index 66f9f2a..4b73ec6 100644
>--- a/ip/ip6tunnel.c
>+++ b/ip/ip6tunnel.c
>@@ -47,7 +47,7 @@ static void usage(void) __attribute__((noreturn));
> static void usage(void)
> {
> fprintf(stderr, "Usage: ip -f inet6 tunnel { add | change | del | show } [ NAME ]\n");
>- fprintf(stderr, " [ mode { ip6ip6 | ipip6 | ip6gre | any } ]\n");
>+ fprintf(stderr, " [ mode { ip6ip6 | ipip6 | ip6gre | vti6 | any } ]\n");
> fprintf(stderr, " [ remote ADDR local ADDR ] [ dev PHYS_DEV ]\n");
> fprintf(stderr, " [ encaplimit ELIM ]\n");
> fprintf(stderr ," [ hoplimit TTL ] [ tclass TCLASS ] [ flowlabel FLOWLABEL ]\n");
>@@ -140,7 +140,10 @@ static int parse_args(int argc, char **argv, int cmd, struct ip6_tnl_parm2 *p)
> if (strcmp(*argv, "ipv6/ipv6") == 0 ||
> strcmp(*argv, "ip6ip6") == 0)
> p->proto = IPPROTO_IPV6;
>- else if (strcmp(*argv, "ip/ipv6") == 0 ||
>+ else if (strcmp(*argv, "vti6") == 0) {
>+ p->proto = IPPROTO_IPV6;
>+ p->i_flags |= VTI_ISVTI;
>+ } else if (strcmp(*argv, "ip/ipv6") == 0 ||
> strcmp(*argv, "ipv4/ipv6") == 0 ||
> strcmp(*argv, "ipip6") == 0 ||
> strcmp(*argv, "ip4ip6") == 0)
>@@ -459,11 +462,14 @@ static int do_add(int cmd, int argc, char **argv)
> switch (p.proto) {
> case IPPROTO_IPIP:
> case IPPROTO_IPV6:
>+ if (p.i_flags != VTI_ISVTI)
>+ return tnl_add_ioctl(cmd, "ip6_vti0", p.name, &p);
^ Wouldn't it be more
consistent to not to use
the underscore?
>+ else
> return tnl_add_ioctl(cmd, "ip6tnl0", p.name, &p);
> case IPPROTO_GRE:
> return tnl_add_ioctl(cmd, "ip6gre0", p.name, &p);
> default:
>- fprintf(stderr, "cannot determine tunnel mode (ip6ip6, ipip6 or gre)\n");
>+ fprintf(stderr, "cannot determine tunnel mode (ip6ip6, ipip6, vti6 or gre)\n");
> }
> return -1;
> }
>@@ -480,6 +486,9 @@ static int do_del(int argc, char **argv)
> switch (p.proto) {
> case IPPROTO_IPIP:
> case IPPROTO_IPV6:
>+ if (p.i_flags != VTI_ISVTI)
>+ return tnl_del_ioctl("ip6_vti0", p.name, &p);
>+ else
> return tnl_del_ioctl("ip6tnl0", p.name, &p);
> case IPPROTO_GRE:
> return tnl_del_ioctl("ip6gre0", p.name, &p);
>--
>1.9.1
>
>--
>To unsubscribe from this list: send the line "unsubscribe netdev" in
>the body of a message to majordomo@vger.kernel.org
>More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH net] r8152: autoresume before setting MAC address
From: Oliver Neukum @ 2014-10-02 8:44 UTC (permalink / raw)
To: Hayes Wang
Cc: netdev-u79uwXL29TY76Z2rM5mHXA, nic_swsd-Rasf1IRRPZFBDgjK7y7TUQ,
linux-kernel-u79uwXL29TY76Z2rM5mHXA,
linux-usb-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <1394712342-15778-55-Taiwan-albertk-Rasf1IRRPZFBDgjK7y7TUQ@public.gmane.org>
On Thu, 2014-10-02 at 16:26 +0800, Hayes Wang wrote:
> Resume the device before setting the MAC address.
>
> Signed-off-by: Hayes Wang <hayeswang-Rasf1IRRPZFBDgjK7y7TUQ@public.gmane.org>
> ---
> drivers/net/usb/r8152.c | 16 +++++++++++++---
> 1 file changed, 13 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
> index 604ef21..e823358 100644
> --- a/drivers/net/usb/r8152.c
> +++ b/drivers/net/usb/r8152.c
> @@ -1007,9 +1007,16 @@ static int rtl8152_set_mac_address(struct net_device *netdev, void *p)
> {
> struct r8152 *tp = netdev_priv(netdev);
> struct sockaddr *addr = p;
> + int ret;
> +
> + ret = usb_autopm_get_interface(tp->intf);
> + if (ret < 0)
> + goto out1;
>
> - if (!is_valid_ether_addr(addr->sa_data))
> - return -EADDRNOTAVAIL;
It would be more legant to check validity before you do
the pm operation. Error handling would be simpler.
Regards
Oliver
--
To unsubscribe from this list: send the line "unsubscribe linux-usb" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH 1/2] iproute2: Add support for IPv6 VTI tunnels to ip6tunnel
From: Steffen Klassert @ 2014-10-02 8:48 UTC (permalink / raw)
To: Jiri Pirko; +Cc: Stephen Hemminger, netdev
In-Reply-To: <20141002084109.GI1844@nanopsycho.orion>
On Thu, Oct 02, 2014 at 10:41:09AM +0200, Jiri Pirko wrote:
> Fri, Sep 26, 2014 at 09:10:56AM CEST, steffen.klassert@secunet.com wrote:
> >
> >@@ -459,11 +462,14 @@ static int do_add(int cmd, int argc, char **argv)
> > switch (p.proto) {
> > case IPPROTO_IPIP:
> > case IPPROTO_IPV6:
> >+ if (p.i_flags != VTI_ISVTI)
> >+ return tnl_add_ioctl(cmd, "ip6_vti0", p.name, &p);
> ^ Wouldn't it be more
> consistent to not to use
> the underscore?
The ipv4 version of vti uses ip_vti0, so I tried to be consistent
with that.
^ permalink raw reply
* Re: [PATCH v2 net-next] mlx4: optimize xmit path
From: Amir Vadai @ 2014-10-02 8:57 UTC (permalink / raw)
To: Jesper Dangaard Brouer
Cc: Eric Dumazet, Or Gerlitz, Alexei Starovoitov, David S. Miller,
Eric Dumazet, John Fastabend, Linux Netdev List, Or Gerlitz,
amira, idos, Yevgeny Petrilin, eyalpe
In-Reply-To: <20141002102950.2b209373@redhat.com>
On 10/2/2014 11:29 AM, Jesper Dangaard Brouer wrote:
> On Thu, 2 Oct 2014 11:03:13 +0300
> Amir Vadai <amirv@mellanox.com> wrote:
>
>> I'm still working on it, but I can't reproduce the numbers that you
>> show. On my development machine, I get ~5.5Mpps with burst=8 and ~2Mpps
>> with burst=1.
>
> For pktgen it sounds like you either missing:
>
> 1) flag QUEUE_MAP_CPU
> and/or
> 2) clone_skb $BIGNUMBER
Thanks,
This improved the numbers to ~7Mpps with burst=8 and ~4Mpps with burst=1
- still far away from 15Mpps, but in the direction.
>
> My usage of pktgen:
> http://netoptimizer.blogspot.dk/2014/06/pktgen-for-network-overload-testing.html
>
^ permalink raw reply
* Re: [PATCH] net: ethernet: Remove superfluous ether_setup after alloc_etherdev
From: Nicolas Ferre @ 2014-10-02 8:59 UTC (permalink / raw)
To: Tobias Klauser, David S. Miller, netdev
Cc: Maxime Ripard, Vince Bridgers, Wan ZongShun, Nicolas Pitre,
Steve Glendinning, Giuseppe Cavallaro
In-Reply-To: <1412237730-5811-1-git-send-email-tklauser@distanz.ch>
On 02/10/2014 10:15, Tobias Klauser :
> There is no need to call ether_setup after alloc_ethdev since it was
> already called there.
>
> Follow commits c706471b2601 ("net: axienet: remove unnecessary
> ether_setup after alloc_etherdev") and 3c87dcbfb36c ("net: ll_temac:
> Remove unnecessary ether_setup after alloc_etherdev") and fix the
> pattern in all remaining ethernet drivers.
>
> Signed-off-by: Tobias Klauser <tklauser@distanz.ch>
> ---
> drivers/net/ethernet/adi/bfin_mac.c | 3 ---
> drivers/net/ethernet/allwinner/sun4i-emac.c | 2 --
> drivers/net/ethernet/altera/altera_tse_main.c | 1 -
> drivers/net/ethernet/cadence/at91_ether.c | 1 -
If needed for this driver ^^
Acked-by: Nicolas Ferre <nicolas.ferre@atmel.com>
Thanks.
> drivers/net/ethernet/calxeda/xgmac.c | 1 -
> drivers/net/ethernet/davicom/dm9000.c | 3 ---
> drivers/net/ethernet/ethoc.c | 2 --
> drivers/net/ethernet/lantiq_etop.c | 1 -
> drivers/net/ethernet/moxa/moxart_ether.c | 1 -
> drivers/net/ethernet/netx-eth.c | 2 --
> drivers/net/ethernet/nuvoton/w90p910_ether.c | 1 -
> drivers/net/ethernet/nxp/lpc_eth.c | 3 ---
> drivers/net/ethernet/qualcomm/qca_spi.c | 2 --
> drivers/net/ethernet/smsc/smc911x.c | 3 ---
> drivers/net/ethernet/smsc/smc91x.c | 3 ---
> drivers/net/ethernet/smsc/smsc911x.c | 1 -
> drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 2 --
> drivers/net/ethernet/wiznet/w5100.c | 1 -
> drivers/net/ethernet/wiznet/w5300.c | 1 -
> 19 files changed, 34 deletions(-)
>
> diff --git a/drivers/net/ethernet/adi/bfin_mac.c b/drivers/net/ethernet/adi/bfin_mac.c
> index afa6684..8ed4d340 100644
> --- a/drivers/net/ethernet/adi/bfin_mac.c
> +++ b/drivers/net/ethernet/adi/bfin_mac.c
> @@ -1692,9 +1692,6 @@ static int bfin_mac_probe(struct platform_device *pdev)
> lp->vlan1_mask = ETH_P_8021Q | mii_bus_data->vlan1_mask;
> lp->vlan2_mask = ETH_P_8021Q | mii_bus_data->vlan2_mask;
>
> - /* Fill in the fields of the device structure with ethernet values. */
> - ether_setup(ndev);
> -
> ndev->netdev_ops = &bfin_mac_netdev_ops;
> ndev->ethtool_ops = &bfin_mac_ethtool_ops;
>
> diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c
> index 29b9f08..1fcd556 100644
> --- a/drivers/net/ethernet/allwinner/sun4i-emac.c
> +++ b/drivers/net/ethernet/allwinner/sun4i-emac.c
> @@ -878,8 +878,6 @@ static int emac_probe(struct platform_device *pdev)
> emac_powerup(ndev);
> emac_reset(db);
>
> - ether_setup(ndev);
> -
> ndev->netdev_ops = &emac_netdev_ops;
> ndev->watchdog_timeo = msecs_to_jiffies(watchdog);
> ndev->ethtool_ops = &emac_ethtool_ops;
> diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c
> index 7330681..fc2d555 100644
> --- a/drivers/net/ethernet/altera/altera_tse_main.c
> +++ b/drivers/net/ethernet/altera/altera_tse_main.c
> @@ -1433,7 +1433,6 @@ static int altera_tse_probe(struct platform_device *pdev)
> goto err_free_netdev;
>
> /* initialize netdev */
> - ether_setup(ndev);
> ndev->mem_start = control_port->start;
> ndev->mem_end = control_port->end;
> ndev->netdev_ops = &altera_tse_netdev_ops;
> diff --git a/drivers/net/ethernet/cadence/at91_ether.c b/drivers/net/ethernet/cadence/at91_ether.c
> index 4a79eda..4a24b9a 100644
> --- a/drivers/net/ethernet/cadence/at91_ether.c
> +++ b/drivers/net/ethernet/cadence/at91_ether.c
> @@ -351,7 +351,6 @@ static int __init at91ether_probe(struct platform_device *pdev)
> if (res)
> goto err_disable_clock;
>
> - ether_setup(dev);
> dev->netdev_ops = &at91ether_netdev_ops;
> dev->ethtool_ops = &macb_ethtool_ops;
> platform_set_drvdata(pdev, dev);
> diff --git a/drivers/net/ethernet/calxeda/xgmac.c b/drivers/net/ethernet/calxeda/xgmac.c
> index 25d6b2a..47bfea2 100644
> --- a/drivers/net/ethernet/calxeda/xgmac.c
> +++ b/drivers/net/ethernet/calxeda/xgmac.c
> @@ -1735,7 +1735,6 @@ static int xgmac_probe(struct platform_device *pdev)
> SET_NETDEV_DEV(ndev, &pdev->dev);
> priv = netdev_priv(ndev);
> platform_set_drvdata(pdev, ndev);
> - ether_setup(ndev);
> ndev->netdev_ops = &xgmac_netdev_ops;
> ndev->ethtool_ops = &xgmac_ethtool_ops;
> spin_lock_init(&priv->stats_lock);
> diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c
> index 70089c2..f3ba840 100644
> --- a/drivers/net/ethernet/davicom/dm9000.c
> +++ b/drivers/net/ethernet/davicom/dm9000.c
> @@ -1613,9 +1613,6 @@ dm9000_probe(struct platform_device *pdev)
>
> /* from this point we assume that we have found a DM9000 */
>
> - /* driver system function */
> - ether_setup(ndev);
> -
> ndev->netdev_ops = &dm9000_netdev_ops;
> ndev->watchdog_timeo = msecs_to_jiffies(watchdog);
> ndev->ethtool_ops = &dm9000_ethtool_ops;
> diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c
> index f3658bd..0bc6c10 100644
> --- a/drivers/net/ethernet/ethoc.c
> +++ b/drivers/net/ethernet/ethoc.c
> @@ -1222,8 +1222,6 @@ static int ethoc_probe(struct platform_device *pdev)
> goto error;
> }
>
> - ether_setup(netdev);
> -
> /* setup the net_device structure */
> netdev->netdev_ops = ðoc_netdev_ops;
> netdev->watchdog_timeo = ETHOC_TIMEOUT;
> diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c
> index fd4b6ae..2dad4d5 100644
> --- a/drivers/net/ethernet/lantiq_etop.c
> +++ b/drivers/net/ethernet/lantiq_etop.c
> @@ -633,7 +633,6 @@ ltq_etop_init(struct net_device *dev)
> int err;
> bool random_mac = false;
>
> - ether_setup(dev);
> dev->watchdog_timeo = 10 * HZ;
> err = ltq_etop_hw_init(dev);
> if (err)
> diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c
> index 2f12c88..bde1b70 100644
> --- a/drivers/net/ethernet/moxa/moxart_ether.c
> +++ b/drivers/net/ethernet/moxa/moxart_ether.c
> @@ -511,7 +511,6 @@ static int moxart_mac_probe(struct platform_device *pdev)
> goto init_fail;
> }
>
> - ether_setup(ndev);
> ndev->netdev_ops = &moxart_netdev_ops;
> netif_napi_add(ndev, &priv->napi, moxart_rx_poll, RX_DESC_NUM);
> ndev->priv_flags |= IFF_UNICAST_FLT;
> diff --git a/drivers/net/ethernet/netx-eth.c b/drivers/net/ethernet/netx-eth.c
> index 31eb911..8176c8a 100644
> --- a/drivers/net/ethernet/netx-eth.c
> +++ b/drivers/net/ethernet/netx-eth.c
> @@ -315,8 +315,6 @@ static int netx_eth_enable(struct net_device *ndev)
> unsigned int mac4321, mac65;
> int running, i;
>
> - ether_setup(ndev);
> -
> ndev->netdev_ops = &netx_eth_netdev_ops;
> ndev->watchdog_timeo = msecs_to_jiffies(5000);
>
> diff --git a/drivers/net/ethernet/nuvoton/w90p910_ether.c b/drivers/net/ethernet/nuvoton/w90p910_ether.c
> index 79645f7..379b7fb 100644
> --- a/drivers/net/ethernet/nuvoton/w90p910_ether.c
> +++ b/drivers/net/ethernet/nuvoton/w90p910_ether.c
> @@ -943,7 +943,6 @@ static int w90p910_ether_setup(struct net_device *dev)
> {
> struct w90p910_ether *ether = netdev_priv(dev);
>
> - ether_setup(dev);
> dev->netdev_ops = &w90p910_ether_netdev_ops;
> dev->ethtool_ops = &w90p910_ether_ethtool_ops;
>
> diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c
> index a44a03c..66fd868 100644
> --- a/drivers/net/ethernet/nxp/lpc_eth.c
> +++ b/drivers/net/ethernet/nxp/lpc_eth.c
> @@ -1377,9 +1377,6 @@ static int lpc_eth_drv_probe(struct platform_device *pdev)
> goto err_out_iounmap;
> }
>
> - /* Fill in the fields of the device structure with ethernet values. */
> - ether_setup(ndev);
> -
> /* Setup driver functions */
> ndev->netdev_ops = &lpc_netdev_ops;
> ndev->ethtool_ops = &lpc_eth_ethtool_ops;
> diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
> index 74eb520..2c811f6 100644
> --- a/drivers/net/ethernet/qualcomm/qca_spi.c
> +++ b/drivers/net/ethernet/qualcomm/qca_spi.c
> @@ -810,8 +810,6 @@ qcaspi_netdev_setup(struct net_device *dev)
> {
> struct qcaspi *qca = NULL;
>
> - ether_setup(dev);
> -
> dev->netdev_ops = &qcaspi_netdev_ops;
> qcaspi_set_ethtool_ops(dev);
> dev->watchdog_timeo = QCASPI_TX_TIMEOUT;
> diff --git a/drivers/net/ethernet/smsc/smc911x.c b/drivers/net/ethernet/smsc/smc911x.c
> index 9778cba..e88df9c 100644
> --- a/drivers/net/ethernet/smsc/smc911x.c
> +++ b/drivers/net/ethernet/smsc/smc911x.c
> @@ -1927,9 +1927,6 @@ static int smc911x_probe(struct net_device *dev)
> }
> dev->irq = irq_canonicalize(dev->irq);
>
> - /* Fill in the fields of the device structure with ethernet values. */
> - ether_setup(dev);
> -
> dev->netdev_ops = &smc911x_netdev_ops;
> dev->watchdog_timeo = msecs_to_jiffies(watchdog);
> dev->ethtool_ops = &smc911x_ethtool_ops;
> diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c
> index bcaa41a..5e94d00 100644
> --- a/drivers/net/ethernet/smsc/smc91x.c
> +++ b/drivers/net/ethernet/smsc/smc91x.c
> @@ -1967,9 +1967,6 @@ static int smc_probe(struct net_device *dev, void __iomem *ioaddr,
> }
> dev->irq = irq_canonicalize(dev->irq);
>
> - /* Fill in the fields of the device structure with ethernet values. */
> - ether_setup(dev);
> -
> dev->watchdog_timeo = msecs_to_jiffies(watchdog);
> dev->netdev_ops = &smc_netdev_ops;
> dev->ethtool_ops = &smc_ethtool_ops;
> diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c
> index 5e13fa5..affb29d 100644
> --- a/drivers/net/ethernet/smsc/smsc911x.c
> +++ b/drivers/net/ethernet/smsc/smsc911x.c
> @@ -2255,7 +2255,6 @@ static int smsc911x_init(struct net_device *dev)
> if (smsc911x_soft_reset(pdata))
> return -ENODEV;
>
> - ether_setup(dev);
> dev->flags |= IFF_MULTICAST;
> netif_napi_add(dev, &pdata->napi, smsc911x_poll, SMSC_NAPI_WEIGHT);
> dev->netdev_ops = &smsc911x_netdev_ops;
> diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
> index 9979f67..6f77a46 100644
> --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
> +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
> @@ -2765,8 +2765,6 @@ struct stmmac_priv *stmmac_dvr_probe(struct device *device,
> priv->device = device;
> priv->dev = ndev;
>
> - ether_setup(ndev);
> -
> stmmac_set_ethtool_ops(ndev);
> priv->pause = pause;
> priv->plat = plat_dat;
> diff --git a/drivers/net/ethernet/wiznet/w5100.c b/drivers/net/ethernet/wiznet/w5100.c
> index 104d46f..0f56b1c 100644
> --- a/drivers/net/ethernet/wiznet/w5100.c
> +++ b/drivers/net/ethernet/wiznet/w5100.c
> @@ -708,7 +708,6 @@ static int w5100_probe(struct platform_device *pdev)
> priv = netdev_priv(ndev);
> priv->ndev = ndev;
>
> - ether_setup(ndev);
> ndev->netdev_ops = &w5100_netdev_ops;
> ndev->ethtool_ops = &w5100_ethtool_ops;
> ndev->watchdog_timeo = HZ;
> diff --git a/drivers/net/ethernet/wiznet/w5300.c b/drivers/net/ethernet/wiznet/w5300.c
> index 1f33c4c..f961f14 100644
> --- a/drivers/net/ethernet/wiznet/w5300.c
> +++ b/drivers/net/ethernet/wiznet/w5300.c
> @@ -620,7 +620,6 @@ static int w5300_probe(struct platform_device *pdev)
> priv = netdev_priv(ndev);
> priv->ndev = ndev;
>
> - ether_setup(ndev);
> ndev->netdev_ops = &w5300_netdev_ops;
> ndev->ethtool_ops = &w5300_ethtool_ops;
> ndev->watchdog_timeo = HZ;
>
--
Nicolas Ferre
^ permalink raw reply
* [PATCH net v2] r8152: autoresume before setting MAC address
From: Hayes Wang @ 2014-10-02 9:03 UTC (permalink / raw)
To: netdev; +Cc: nic_swsd, linux-kernel, linux-usb, Hayes Wang
In-Reply-To: <1394712342-15778-55-Taiwan-albertk@realtek.com>
Resume the device before setting the MAC address.
Signed-off-by: Hayes Wang <hayeswang@realtek.com>
---
drivers/net/usb/r8152.c | 11 +++++++++--
1 file changed, 9 insertions(+), 2 deletions(-)
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 604ef21..5ee7582 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -1007,9 +1007,14 @@ static int rtl8152_set_mac_address(struct net_device *netdev, void *p)
{
struct r8152 *tp = netdev_priv(netdev);
struct sockaddr *addr = p;
+ int ret = -EADDRNOTAVAIL;
if (!is_valid_ether_addr(addr->sa_data))
- return -EADDRNOTAVAIL;
+ goto out1;
+
+ ret = usb_autopm_get_interface(tp->intf);
+ if (ret < 0)
+ goto out1;
memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
@@ -1017,7 +1022,9 @@ static int rtl8152_set_mac_address(struct net_device *netdev, void *p)
pla_ocp_write(tp, PLA_IDR, BYTE_EN_SIX_BYTES, 8, addr->sa_data);
ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_NORAML);
- return 0;
+ usb_autopm_put_interface(tp->intf);
+out1:
+ return ret;
}
static void read_bulk_callback(struct urb *urb)
--
1.9.3
^ permalink raw reply related
* RE: [PATCHv9 net-next 2/4] sunvnet: make transmit path zero-copy in the kernel
From: David Laight @ 2014-10-02 9:06 UTC (permalink / raw)
To: 'Raghuram Kothakota', David L Stevens
Cc: David Miller, netdev@vger.kernel.org, Sowmini Varadhan
In-Reply-To: <77E6695E-58F8-4D10-8ED7-EEC4A487339E@oracle.com>
From: Raghuram Kothakota
> Sorry I am late in providing my comments, but I feel it is important
> to share this comment.
A comment on the original patch...
...
> > @@ -811,14 +930,27 @@ static int vnet_start_xmit(struct sk_buff *skb, struct net_device *dev)
> >
> > d = vio_dring_cur(dr);
> >
> > - tx_buf = port->tx_bufs[dr->prod].buf;
> > - skb_copy_from_linear_data(skb, tx_buf + VNET_PACKET_SKIP, skb->len);
> > + txi = dr->prod;
> > +
> > + freeskbs = vnet_clean_tx_ring(port, &pending);
> > +
> > + BUG_ON(port->tx_bufs[txi].skb);
> >
> > len = skb->len;
> > - if (len < ETH_ZLEN) {
> > + if (len < ETH_ZLEN)
> > len = ETH_ZLEN;
> > - memset(tx_buf+VNET_PACKET_SKIP+skb->len, 0, len - skb->len);
> > +
Aren't you transmitting 'random' bytes from the end of the data?
Plausibly they might not even be mapped.
Also, for short frames the copy could well be faster - especially on systems
with non-trivial iommu.
It is also worth checking whether the original copy was aligned.
David
^ permalink raw reply
* Re: [PATCH 1/2] iproute2: Add support for IPv6 VTI tunnels to ip6tunnel
From: Jiri Pirko @ 2014-10-02 9:11 UTC (permalink / raw)
To: Steffen Klassert; +Cc: Stephen Hemminger, netdev
In-Reply-To: <20141002084820.GF6390@secunet.com>
Thu, Oct 02, 2014 at 10:48:20AM CEST, steffen.klassert@secunet.com wrote:
>On Thu, Oct 02, 2014 at 10:41:09AM +0200, Jiri Pirko wrote:
>> Fri, Sep 26, 2014 at 09:10:56AM CEST, steffen.klassert@secunet.com wrote:
>> >
>> >@@ -459,11 +462,14 @@ static int do_add(int cmd, int argc, char **argv)
>> > switch (p.proto) {
>> > case IPPROTO_IPIP:
>> > case IPPROTO_IPV6:
>> >+ if (p.i_flags != VTI_ISVTI)
>> >+ return tnl_add_ioctl(cmd, "ip6_vti0", p.name, &p);
>> ^ Wouldn't it be more
>> consistent to not to use
>> the underscore?
>
>The ipv4 version of vti uses ip_vti0, so I tried to be consistent
>with that.
Okay, fine with me.
^ permalink raw reply
* RE: [PATCH net-next v6 2/2] bonding: Simplify the xmit function for modes that use xmit_hash
From: David Laight @ 2014-10-02 9:12 UTC (permalink / raw)
To: 'Mahesh Bandewar', Jay Vosburgh
Cc: Veaceslav Falico, Andy Gospodarek, David Miller, netdev,
Eric Dumazet, Maciej Zenczykowski
In-Reply-To: <CAF2d9jioDfj+qmvrQBQcaHnvXbL+Fnsh3-jxwn2KU+zvV=xgJQ@mail.gmail.com>
From: Mahesh Bandewar
> On Wed, Oct 1, 2014 at 9:49 PM, Jay Vosburgh <jay.vosburgh@canonical.com> wrote:
> > Mahesh Bandewar <maheshb@google.com> wrote:
...
> >> * Select aggregation groups, and assign each port for it's aggregetor. The
> >> * selection logic is called in the inititalization (after all the handshkes),
> >> * and after every lacpdu receive (if selected is off).
> >> */
> >>-static void ad_port_selection_logic(struct port *port)
> >>+static void ad_port_selection_logic(struct port *port, bool *update_slave_arr)
> >
> > Since this function is void, why not have it return a value
> > instead of the bool *update_slave_arr? That would eliminate the need
> > for some call sites to pass a "dummy" to the function. This comment
> > applies to ad_agg_selection_logic and ad_enable_collecting_distributing
> > as well.
> >
> Yes, I had similar discussion with Nik earlier and overloading the
> return value did not feel clean and future-proof and hence decided to
> take this approach.
What overload?
Returning values by reference parameters isn't really a good idea.
It kills performance and optimisations.
If you ever need a second return value then solve the problem then.
David
^ permalink raw reply
* [PATCH V2 net-next 0/5] mlx5 update for 3.18
From: Eli Cohen @ 2014-10-02 9:19 UTC (permalink / raw)
To: davem; +Cc: netdev, ogerlitz, yevgenyp, Eli Cohen
Hi Dave,
This series integrates a new mechanism for populating and extracting field values
used in the driver/firmware interaction around command mailboxes.
Changes from V1:
- Remove unused definition of memcpy_cpu_to_be32()
- Remove definitions of non_existent_*() and use BUILD_BUG_ON() instead.
- Added a patch one line patch to add support for ConnectX-4 devices.
Changes from V0:
- trimmed the auto-generated file to a minimum, as required by the reviewers.
Eli
Eli Cohen (5):
net/mlx5_core: Update device capabilities handling
net/mlx5_core: Use hardware registers description header file
net/mlx5_core: use set/get macros in device caps
net/mlx5_core: Identify resources by their type
net/mlx5_core: Add ConnectX-4 to list of supported devices
drivers/infiniband/hw/mlx5/cq.c | 8 +-
drivers/infiniband/hw/mlx5/mad.c | 2 +-
drivers/infiniband/hw/mlx5/main.c | 83 +++---
drivers/infiniband/hw/mlx5/qp.c | 72 +++--
drivers/infiniband/hw/mlx5/srq.c | 6 +-
drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 77 +++---
drivers/net/ethernet/mellanox/mlx5/core/eq.c | 14 +-
drivers/net/ethernet/mellanox/mlx5/core/fw.c | 81 +-----
drivers/net/ethernet/mellanox/mlx5/core/main.c | 230 ++++++++++++----
drivers/net/ethernet/mellanox/mlx5/core/qp.c | 60 +++--
drivers/net/ethernet/mellanox/mlx5/core/uar.c | 4 +-
include/linux/mlx5/device.h | 152 ++++-------
include/linux/mlx5/driver.h | 118 +++------
include/linux/mlx5/mlx5_ifc.h | 349 +++++++++++++++++++++++++
include/linux/mlx5/qp.h | 3 +-
15 files changed, 804 insertions(+), 455 deletions(-)
create mode 100644 include/linux/mlx5/mlx5_ifc.h
--
2.1.1
^ permalink raw reply
* [PATCH V2 net-next 4/5] net/mlx5_core: Identify resources by their type
From: Eli Cohen @ 2014-10-02 9:19 UTC (permalink / raw)
To: davem; +Cc: netdev, ogerlitz, yevgenyp, Eli Cohen
In-Reply-To: <1412241586-10108-1-git-send-email-eli@mellanox.com>
This patch puts a common part as the first field of mlx5_core_qp. This field is
used to identify which resource generated an event. This is required since upcoming
new resource types such as DC targets are allocated for the same numerical space
as regular QPs and may generate the same events. By searching the resource in the
same table we can then look at the common field to identify the resource.
Signed-off-by: Eli Cohen <eli@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/eq.c | 12 +++---
drivers/net/ethernet/mellanox/mlx5/core/qp.c | 57 ++++++++++++++++++++--------
include/linux/mlx5/driver.h | 13 ++++++-
include/linux/mlx5/qp.h | 3 +-
4 files changed, 60 insertions(+), 25 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 11b9b840ad4d..ed53291468f3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -198,7 +198,7 @@ static int mlx5_eq_int(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
int eqes_found = 0;
int set_ci = 0;
u32 cqn;
- u32 srqn;
+ u32 rsn;
u8 port;
while ((eqe = next_eqe_sw(eq))) {
@@ -224,18 +224,18 @@ static int mlx5_eq_int(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
case MLX5_EVENT_TYPE_PATH_MIG_FAILED:
case MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR:
case MLX5_EVENT_TYPE_WQ_ACCESS_ERROR:
+ rsn = be32_to_cpu(eqe->data.qp_srq.qp_srq_n) & 0xffffff;
mlx5_core_dbg(dev, "event %s(%d) arrived\n",
eqe_type_str(eqe->type), eqe->type);
- mlx5_qp_event(dev, be32_to_cpu(eqe->data.qp_srq.qp_srq_n) & 0xffffff,
- eqe->type);
+ mlx5_rsc_event(dev, rsn, eqe->type);
break;
case MLX5_EVENT_TYPE_SRQ_RQ_LIMIT:
case MLX5_EVENT_TYPE_SRQ_CATAS_ERROR:
- srqn = be32_to_cpu(eqe->data.qp_srq.qp_srq_n) & 0xffffff;
+ rsn = be32_to_cpu(eqe->data.qp_srq.qp_srq_n) & 0xffffff;
mlx5_core_dbg(dev, "SRQ event %s(%d): srqn 0x%x\n",
- eqe_type_str(eqe->type), eqe->type, srqn);
- mlx5_srq_event(dev, srqn, eqe->type);
+ eqe_type_str(eqe->type), eqe->type, rsn);
+ mlx5_srq_event(dev, rsn, eqe->type);
break;
case MLX5_EVENT_TYPE_CMD:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
index 415b67ce379e..5261a2b0da43 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
@@ -39,28 +39,53 @@
#include "mlx5_core.h"
-void mlx5_qp_event(struct mlx5_core_dev *dev, u32 qpn, int event_type)
+static struct mlx5_core_rsc_common *mlx5_get_rsc(struct mlx5_core_dev *dev,
+ u32 rsn)
{
struct mlx5_qp_table *table = &dev->priv.qp_table;
- struct mlx5_core_qp *qp;
+ struct mlx5_core_rsc_common *common;
spin_lock(&table->lock);
- qp = radix_tree_lookup(&table->tree, qpn);
- if (qp)
- atomic_inc(&qp->refcount);
+ common = radix_tree_lookup(&table->tree, rsn);
+ if (common)
+ atomic_inc(&common->refcount);
spin_unlock(&table->lock);
- if (!qp) {
- mlx5_core_warn(dev, "Async event for bogus QP 0x%x\n", qpn);
- return;
+ if (!common) {
+ mlx5_core_warn(dev, "Async event for bogus resource 0x%x\n",
+ rsn);
+ return NULL;
}
+ return common;
+}
- qp->event(qp, event_type);
+void mlx5_core_put_rsc(struct mlx5_core_rsc_common *common)
+{
+ if (atomic_dec_and_test(&common->refcount))
+ complete(&common->free);
+}
+
+void mlx5_rsc_event(struct mlx5_core_dev *dev, u32 rsn, int event_type)
+{
+ struct mlx5_core_rsc_common *common = mlx5_get_rsc(dev, rsn);
+ struct mlx5_core_qp *qp;
+
+ if (!common)
+ return;
+
+ switch (common->res) {
+ case MLX5_RES_QP:
+ qp = (struct mlx5_core_qp *)common;
+ qp->event(qp, event_type);
+ break;
+
+ default:
+ mlx5_core_warn(dev, "invalid resource type for 0x%x\n", rsn);
+ }
- if (atomic_dec_and_test(&qp->refcount))
- complete(&qp->free);
+ mlx5_core_put_rsc(common);
}
int mlx5_core_create_qp(struct mlx5_core_dev *dev,
@@ -92,6 +117,7 @@ int mlx5_core_create_qp(struct mlx5_core_dev *dev,
qp->qpn = be32_to_cpu(out.qpn) & 0xffffff;
mlx5_core_dbg(dev, "qpn = 0x%x\n", qp->qpn);
+ qp->common.res = MLX5_RES_QP;
spin_lock_irq(&table->lock);
err = radix_tree_insert(&table->tree, qp->qpn, qp);
spin_unlock_irq(&table->lock);
@@ -106,9 +132,9 @@ int mlx5_core_create_qp(struct mlx5_core_dev *dev,
qp->qpn);
qp->pid = current->pid;
- atomic_set(&qp->refcount, 1);
+ atomic_set(&qp->common.refcount, 1);
atomic_inc(&dev->num_qps);
- init_completion(&qp->free);
+ init_completion(&qp->common.free);
return 0;
@@ -138,9 +164,8 @@ int mlx5_core_destroy_qp(struct mlx5_core_dev *dev,
radix_tree_delete(&table->tree, qp->qpn);
spin_unlock_irqrestore(&table->lock, flags);
- if (atomic_dec_and_test(&qp->refcount))
- complete(&qp->free);
- wait_for_completion(&qp->free);
+ mlx5_core_put_rsc((struct mlx5_core_rsc_common *)qp);
+ wait_for_completion(&qp->common.free);
memset(&in, 0, sizeof(in));
memset(&out, 0, sizeof(out));
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index c439f9c59b93..246310dc8bef 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -375,6 +375,16 @@ struct mlx5_core_mr {
u32 pd;
};
+enum mlx5_res_type {
+ MLX5_RES_QP,
+};
+
+struct mlx5_core_rsc_common {
+ enum mlx5_res_type res;
+ atomic_t refcount;
+ struct completion free;
+};
+
struct mlx5_core_srq {
u32 srqn;
int max;
@@ -700,7 +710,7 @@ int mlx5_eq_init(struct mlx5_core_dev *dev);
void mlx5_eq_cleanup(struct mlx5_core_dev *dev);
void mlx5_fill_page_array(struct mlx5_buf *buf, __be64 *pas);
void mlx5_cq_completion(struct mlx5_core_dev *dev, u32 cqn);
-void mlx5_qp_event(struct mlx5_core_dev *dev, u32 qpn, int event_type);
+void mlx5_rsc_event(struct mlx5_core_dev *dev, u32 rsn, int event_type);
void mlx5_srq_event(struct mlx5_core_dev *dev, u32 srqn, int event_type);
struct mlx5_core_srq *mlx5_core_get_srq(struct mlx5_core_dev *dev, u32 srqn);
void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, unsigned long vector);
@@ -737,6 +747,7 @@ void mlx5_cmdif_debugfs_cleanup(struct mlx5_core_dev *dev);
int mlx5_core_create_psv(struct mlx5_core_dev *dev, u32 pdn,
int npsvs, u32 *sig_index);
int mlx5_core_destroy_psv(struct mlx5_core_dev *dev, int psv_num);
+void mlx5_core_put_rsc(struct mlx5_core_rsc_common *common);
static inline u32 mlx5_mkey_to_idx(u32 mkey)
{
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index 9709b30e2d69..7c4c0f1f5805 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -342,10 +342,9 @@ struct mlx5_stride_block_ctrl_seg {
};
struct mlx5_core_qp {
+ struct mlx5_core_rsc_common common; /* must be first */
void (*event) (struct mlx5_core_qp *, int);
int qpn;
- atomic_t refcount;
- struct completion free;
struct mlx5_rsc_debug *dbg;
int pid;
};
--
2.1.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox