* Re: [PATCH net-next 6/8] tun: implement byte queue limits
From: Stephen Hemminger @ 2012-10-30 1:09 UTC (permalink / raw)
To: Stephen Hemminger; +Cc: davem, netdev
In-Reply-To: <20121030005835.726919547@vyatta.com>
On Mon, 29 Oct 2012 17:57:37 -0700
Stephen Hemminger <shemminger@vyatta.com> wrote:
> Add byte queue limits for tun device transmit.
>
> Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Unrelated patch, that was being tested at same time.
Ignore it.
^ permalink raw reply
* Re: [Patch net-next] ipv6: fix a potential NULL deref
From: Cong Wang @ 2012-10-30 1:44 UTC (permalink / raw)
To: David Miller; +Cc: eric.dumazet, netdev
In-Reply-To: <20121029.132936.191100167150004535.davem@davemloft.net>
On Mon, 2012-10-29 at 13:29 -0400, David Miller wrote:
> From: Cong Wang <amwang@redhat.com>
> Date: Mon, 29 Oct 2012 15:25:23 +0800
>
> > But this will be a problem if someone moved dst inside rt, as there
> > is no comment saying dst has to be the first one?
>
> If we move the initial dst member, many things that depend upon it
> being first will have to change.
>
> Your change was unnecessary and inappropriate, and let's just leave
> it at that.
Yeah, that is why I sent:
http://marc.info/?l=linux-netdev&m=135150561014916&w=2
:)
^ permalink raw reply
* [Patch net-next] ipv6: use IS_ENABLED()
From: Cong Wang @ 2012-10-30 2:23 UTC (permalink / raw)
To: netdev; +Cc: David S. Miller, Cong Wang
#if defined(CONFIG_FOO) || defined(CONFIG_FOO_MODULE)
can be replaced by
#if IS_ENABLED(CONFIG_FOO)
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: Cong Wang <amwang@redhat.com>
---
net/ipv6/addrconf.c | 20 ++++++++++----------
net/ipv6/ah6.c | 10 +++++-----
net/ipv6/datagram.c | 2 +-
net/ipv6/exthdrs.c | 18 +++++++++---------
net/ipv6/icmp.c | 2 +-
net/ipv6/ip6_output.c | 5 ++---
net/ipv6/ipv6_sockglue.c | 2 +-
net/ipv6/netfilter/ip6_tables.c | 6 ++----
net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c | 4 ++--
net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c | 4 ++--
net/ipv6/netfilter/nf_defrag_ipv6_hooks.c | 6 +++---
net/ipv6/netfilter/nf_nat_proto_icmpv6.c | 2 +-
net/ipv6/raw.c | 6 +++---
net/ipv6/xfrm6_policy.c | 4 ++--
net/ipv6/xfrm6_state.c | 4 ++--
15 files changed, 46 insertions(+), 49 deletions(-)
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 8f0b12a..387b813 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -402,7 +402,7 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
if (dev->flags & (IFF_NOARP | IFF_LOOPBACK))
ndev->cnf.accept_dad = -1;
-#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_SIT)
if (dev->type == ARPHRD_SIT && (dev->priv_flags & IFF_ISATAP)) {
pr_info("%s: Disabled Multicast RS\n", dev->name);
ndev->cnf.rtr_solicits = 0;
@@ -1838,7 +1838,7 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev,
This thing is done here expecting that the whole
class of non-broadcast devices need not cloning.
*/
-#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_SIT)
if (dev->type == ARPHRD_SIT && (dev->flags & IFF_POINTOPOINT))
cfg.fc_flags |= RTF_NONEXTHOP;
#endif
@@ -1898,7 +1898,7 @@ static void addrconf_add_mroute(struct net_device *dev)
ip6_route_add(&cfg);
}
-#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_SIT)
static void sit_route_add(struct net_device *dev)
{
struct fib6_config cfg = {
@@ -2250,7 +2250,7 @@ int addrconf_set_dstaddr(struct net *net, void __user *arg)
if (dev == NULL)
goto err_exit;
-#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_SIT)
if (dev->type == ARPHRD_SIT) {
const struct net_device_ops *ops = dev->netdev_ops;
struct ifreq ifr;
@@ -2461,7 +2461,7 @@ static void add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
}
}
-#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_SIT)
static void sit_add_v4_addrs(struct inet6_dev *idev)
{
struct in6_addr addr;
@@ -2580,7 +2580,7 @@ static void addrconf_dev_config(struct net_device *dev)
addrconf_add_linklocal(idev, &addr);
}
-#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_SIT)
static void addrconf_sit_config(struct net_device *dev)
{
struct inet6_dev *idev;
@@ -2617,7 +2617,7 @@ static void addrconf_sit_config(struct net_device *dev)
}
#endif
-#if defined(CONFIG_NET_IPGRE) || defined(CONFIG_NET_IPGRE_MODULE)
+#if IS_ENABLED(CONFIG_NET_IPGRE)
static void addrconf_gre_config(struct net_device *dev)
{
struct inet6_dev *idev;
@@ -2747,12 +2747,12 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
}
switch (dev->type) {
-#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_SIT)
case ARPHRD_SIT:
addrconf_sit_config(dev);
break;
#endif
-#if defined(CONFIG_NET_IPGRE) || defined(CONFIG_NET_IPGRE_MODULE)
+#if IS_ENABLED(CONFIG_NET_IPGRE)
case ARPHRD_IPGRE:
addrconf_gre_config(dev);
break;
@@ -3340,7 +3340,7 @@ void if6_proc_exit(void)
}
#endif /* CONFIG_PROC_FS */
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
/* Check if address is a home address configured on any interface. */
int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr)
{
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index 7e61395..ecc35b9 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -44,7 +44,7 @@
#define IPV6HDR_BASELEN 8
struct tmp_ext {
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
struct in6_addr saddr;
#endif
struct in6_addr daddr;
@@ -152,7 +152,7 @@ bad:
return false;
}
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
/**
* ipv6_rearrange_destopt - rearrange IPv6 destination options header
* @iph: IPv6 header
@@ -320,7 +320,7 @@ static void ah6_output_done(struct crypto_async_request *base, int err)
memcpy(top_iph, iph_base, IPV6HDR_BASELEN);
if (extlen) {
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
memcpy(&top_iph->saddr, iph_ext, extlen);
#else
memcpy(&top_iph->daddr, iph_ext, extlen);
@@ -385,7 +385,7 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb)
memcpy(iph_base, top_iph, IPV6HDR_BASELEN);
if (extlen) {
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
memcpy(iph_ext, &top_iph->saddr, extlen);
#else
memcpy(iph_ext, &top_iph->daddr, extlen);
@@ -434,7 +434,7 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb)
memcpy(top_iph, iph_base, IPV6HDR_BASELEN);
if (extlen) {
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
memcpy(&top_iph->saddr, iph_ext, extlen);
#else
memcpy(&top_iph->daddr, iph_ext, extlen);
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index be2b67d6..93cbad2 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -769,7 +769,7 @@ int datagram_send_ctl(struct net *net, struct sock *sk,
rthdr = (struct ipv6_rt_hdr *)CMSG_DATA(cmsg);
switch (rthdr->type) {
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
case IPV6_SRCRT_TYPE_2:
if (rthdr->hdrlen != 2 ||
rthdr->segments_left != 1) {
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index fa3d9c3..f005acc 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -43,7 +43,7 @@
#include <net/ndisc.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
#include <net/xfrm.h>
#endif
@@ -224,7 +224,7 @@ bad:
Destination options header.
*****************************/
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
static bool ipv6_dest_hao(struct sk_buff *skb, int optoff)
{
struct ipv6_destopt_hao *hao;
@@ -288,7 +288,7 @@ static bool ipv6_dest_hao(struct sk_buff *skb, int optoff)
#endif
static const struct tlvtype_proc tlvprocdestopt_lst[] = {
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
{
.type = IPV6_TLV_HAO,
.func = ipv6_dest_hao,
@@ -300,7 +300,7 @@ static const struct tlvtype_proc tlvprocdestopt_lst[] = {
static int ipv6_destopt_rcv(struct sk_buff *skb)
{
struct inet6_skb_parm *opt = IP6CB(skb);
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
__u16 dstbuf;
#endif
struct dst_entry *dst = skb_dst(skb);
@@ -315,14 +315,14 @@ static int ipv6_destopt_rcv(struct sk_buff *skb)
}
opt->lastopt = opt->dst1 = skb_network_header_len(skb);
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
dstbuf = opt->dst1;
#endif
if (ip6_parse_tlv(tlvprocdestopt_lst, skb)) {
skb->transport_header += (skb_transport_header(skb)[1] + 1) << 3;
opt = IP6CB(skb);
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
opt->nhoff = dstbuf;
#else
opt->nhoff = opt->dst1;
@@ -378,7 +378,7 @@ static int ipv6_rthdr_rcv(struct sk_buff *skb)
looped_back:
if (hdr->segments_left == 0) {
switch (hdr->type) {
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
case IPV6_SRCRT_TYPE_2:
/* Silently discard type 2 header unless it was
* processed by own
@@ -404,7 +404,7 @@ looped_back:
}
switch (hdr->type) {
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
case IPV6_SRCRT_TYPE_2:
if (accept_source_route < 0)
goto unknown_rh;
@@ -461,7 +461,7 @@ looped_back:
addr += i - 1;
switch (hdr->type) {
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
case IPV6_SRCRT_TYPE_2:
if (xfrm6_input_addr(skb, (xfrm_address_t *)addr,
(xfrm_address_t *)&ipv6_hdr(skb)->saddr,
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 24d69db..b4a9fd5 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -280,7 +280,7 @@ static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, st
return 0;
}
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
static void mip6_addr_swap(struct sk_buff *skb)
{
struct ipv6hdr *iph = ipv6_hdr(skb);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index aece3e7..e10c77b 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -538,8 +538,7 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
to->tc_index = from->tc_index;
#endif
nf_copy(to, from);
-#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
- defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE)
+#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
to->nf_trace = from->nf_trace;
#endif
skb_copy_secmark(to, from);
@@ -564,7 +563,7 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
found_rhdr = 1;
break;
case NEXTHDR_DEST:
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0)
break;
#endif
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index ba6d13d..a7bee6a 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -397,7 +397,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
if (optname == IPV6_RTHDR && opt && opt->srcrt) {
struct ipv6_rt_hdr *rthdr = opt->srcrt;
switch (rthdr->type) {
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
case IPV6_SRCRT_TYPE_2:
if (rthdr->hdrlen != 2 ||
rthdr->segments_left != 1)
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index d7cb045..10ce76a 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -207,8 +207,7 @@ ip6t_get_target_c(const struct ip6t_entry *e)
return ip6t_get_target((struct ip6t_entry *)e);
}
-#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
- defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE)
+#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
/* This cries for unification! */
static const char *const hooknames[] = {
[NF_INET_PRE_ROUTING] = "PREROUTING",
@@ -381,8 +380,7 @@ ip6t_do_table(struct sk_buff *skb,
t = ip6t_get_target_c(e);
IP_NF_ASSERT(t->u.kernel.target);
-#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
- defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE)
+#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
/* The packet is traced: log it */
if (unlikely(skb->nf_trace))
trace_packet(skb, hook, in, out,
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index 8860d23..ccb5cbe 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -295,7 +295,7 @@ static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = {
},
};
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
#include <linux/netfilter/nfnetlink.h>
#include <linux/netfilter/nfnetlink_conntrack.h>
@@ -346,7 +346,7 @@ struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 __read_mostly = {
.invert_tuple = ipv6_invert_tuple,
.print_tuple = ipv6_print_tuple,
.get_l4proto = ipv6_get_l4proto,
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
.tuple_to_nlattr = ipv6_tuple_to_nlattr,
.nlattr_tuple_size = ipv6_nlattr_tuple_size,
.nlattr_to_tuple = ipv6_nlattr_to_tuple,
diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
index 2d54b20..24df3dd 100644
--- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
@@ -232,7 +232,7 @@ icmpv6_error(struct net *net, struct nf_conn *tmpl,
return icmpv6_error_message(net, tmpl, skb, dataoff, ctinfo, hooknum);
}
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
#include <linux/netfilter/nfnetlink.h>
#include <linux/netfilter/nfnetlink_conntrack.h>
@@ -375,7 +375,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 __read_mostly =
.get_timeouts = icmpv6_get_timeouts,
.new = icmpv6_new,
.error = icmpv6_error,
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
.tuple_to_nlattr = icmpv6_tuple_to_nlattr,
.nlattr_tuple_size = icmpv6_nlattr_tuple_size,
.nlattr_to_tuple = icmpv6_nlattr_to_tuple,
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index cdd6d04..aacd121 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -19,7 +19,7 @@
#include <linux/netfilter_ipv6.h>
#include <linux/netfilter_bridge.h>
-#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/nf_conntrack_l4proto.h>
@@ -35,7 +35,7 @@ static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum,
{
u16 zone = NF_CT_DEFAULT_ZONE;
-#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
if (skb->nfct)
zone = nf_ct_zone((struct nf_conn *)skb->nfct);
#endif
@@ -60,7 +60,7 @@ static unsigned int ipv6_defrag(unsigned int hooknum,
{
struct sk_buff *reasm;
-#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
/* Previously seen (loopback)? */
if (skb->nfct && !nf_ct_is_template((struct nf_conn *)skb->nfct))
return NF_ACCEPT;
diff --git a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c
index 5d6da78..61aaf70 100644
--- a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c
+++ b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c
@@ -84,7 +84,7 @@ const struct nf_nat_l4proto nf_nat_l4proto_icmpv6 = {
.manip_pkt = icmpv6_manip_pkt,
.in_range = icmpv6_in_range,
.unique_tuple = icmpv6_unique_tuple,
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
.nlattr_to_range = nf_nat_l4proto_nlattr_to_range,
#endif
};
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index d8e95c7..6cd29b1 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -50,7 +50,7 @@
#include <net/udp.h>
#include <net/inet_common.h>
#include <net/tcp_states.h>
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
#include <net/mip6.h>
#endif
#include <linux/mroute6.h>
@@ -123,7 +123,7 @@ static int icmpv6_filter(const struct sock *sk, const struct sk_buff *skb)
return 1;
}
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
typedef int mh_filter_t(struct sock *sock, struct sk_buff *skb);
static mh_filter_t __rcu *mh_filter __read_mostly;
@@ -184,7 +184,7 @@ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr)
filtered = icmpv6_filter(sk, skb);
break;
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
case IPPROTO_MH:
{
/* XXX: To validate MH only once for each packet,
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index f8c4c08..f3ed8ca 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -20,7 +20,7 @@
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/ip6_route.h>
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
#include <net/mip6.h>
#endif
@@ -182,7 +182,7 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
fl6->flowi6_proto = nexthdr;
return;
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
case IPPROTO_MH:
if (!onlyproto && pskb_may_pull(skb, nh + offset + 3 - skb->data)) {
struct ip6_mh *mh;
diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c
index 3f2f7c4..d8c70b8 100644
--- a/net/ipv6/xfrm6_state.c
+++ b/net/ipv6/xfrm6_state.c
@@ -101,7 +101,7 @@ static int __xfrm6_state_sort_cmp(void *p)
return 1;
else
return 3;
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
case XFRM_MODE_ROUTEOPTIMIZATION:
case XFRM_MODE_IN_TRIGGER:
return 2;
@@ -134,7 +134,7 @@ static int __xfrm6_tmpl_sort_cmp(void *p)
switch (v->mode) {
case XFRM_MODE_TRANSPORT:
return 1;
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
case XFRM_MODE_ROUTEOPTIMIZATION:
case XFRM_MODE_IN_TRIGGER:
return 2;
^ permalink raw reply related
* [PATCH] bonding: fix bond 6 mode change MAC of arp reply from vif to cause Domu's network unreachable intermittently
From: Zheng Li @ 2012-10-30 2:47 UTC (permalink / raw)
To: netdev, fubar, andy; +Cc: linux-kernel, davem, joe.jin, zheng.x.li
This is a fix for a bug in bond_alb.c
Rate of reproduced:100%
Scenario: set Dom0 to bond 6 mode, Domu communicate with Dom0 through vif which
is in bridge mode. The Dom0's bridge of xenbr0 contains vif and bond0, bond0
contains eth0 and eth1. You can just need to ping a host which is in same LAN on
Domu, some of packets will be lost intermittently.
Analyse: When Dom0 set bond mode to 6, the bond alb will change MAC of every arp
reply in rlb_arp_xmit function to affect receive packets, it is ok for normal
NIC, but it's wrong to Domu, when Domu send arp reply through vif of Dom0, bond
of alb replace Domu's MAC in arp reply with NIC's MAC address, that will cause
remote host send packets to Domu using real NIC's MAC instead of Domu's MAC. Domu
can't receive the packets whose dst MAC is not Domu's MAC.
Cc: Jay Vosburgh <fubar@us.ibm.com>
Cc: Andy Gospodarek <andy@greyhouse.net>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Zheng Li <zheng.x.li@oracle.com>
---
drivers/net/bonding/bond_alb.c | 13 ++++++++++++-
1 files changed, 12 insertions(+), 1 deletions(-)
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index e15cc11..d6b134a 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -700,7 +700,18 @@ static struct slave *rlb_arp_xmit(struct sk_buff *skb, struct bonding *bond)
*/
tx_slave = rlb_choose_channel(skb, bond);
if (tx_slave) {
- memcpy(arp->mac_src,tx_slave->dev->dev_addr, ETH_ALEN);
+ struct slave *tmp_slave = NULL;
+ int i = 0, found_mac = 0;
+ bond_for_each_slave(bond, tmp_slave, i) {
+ if (ether_addr_equal_64bits(arp->mac_src,
+ tmp_slave->dev->dev_addr)) {
+ found_mac = 1;
+ break;
+ }
+ }
+ if (found_mac)
+ memcpy(arp->mac_src, tx_slave->dev->dev_addr,
+ ETH_ALEN);
}
pr_debug("Server sent ARP Reply packet\n");
} else if (arp->op_code == htons(ARPOP_REQUEST)) {
--
1.7.6.5
^ permalink raw reply related
* Re: [PATCH] bonding: fix bond 6 mode change MAC of arp reply from vif to cause Domu's network unreachable intermittently
From: Cong Wang @ 2012-10-30 3:03 UTC (permalink / raw)
To: linux-kernel; +Cc: netdev
In-Reply-To: <1351565271-5888-1-git-send-email-zheng.x.li@oracle.com>
On Tue, 30 Oct 2012 at 02:47 GMT, Zheng Li <zheng.x.li@oracle.com> wrote:
> + struct slave *tmp_slave = NULL;
> + int i = 0, found_mac = 0;
> + bond_for_each_slave(bond, tmp_slave, i) {
> + if (ether_addr_equal_64bits(arp->mac_src,
> + tmp_slave->dev->dev_addr)) {
> + found_mac = 1;
> + break;
> + }
> + }
> + if (found_mac)
> + memcpy(arp->mac_src, tx_slave->dev->dev_addr,
> + ETH_ALEN);
A nitpick: found_mac can be a bool.
^ permalink raw reply
* Re: [PATCH v3 2/6] PM / Runtime: introduce pm_runtime_set[get]_memalloc_noio()
From: Ming Lei @ 2012-10-30 3:21 UTC (permalink / raw)
To: Alan Stern
Cc: linux-kernel, Oliver Neukum, Minchan Kim, Greg Kroah-Hartman,
Rafael J. Wysocki, Jens Axboe, David S. Miller, Andrew Morton,
netdev, linux-usb, linux-pm, linux-mm
In-Reply-To: <Pine.LNX.4.44L0.1210291125590.22882-100000@netrider.rowland.org>
On Mon, Oct 29, 2012 at 11:41 PM, Alan Stern <stern@rowland.harvard.edu> wrote:
> On Mon, 29 Oct 2012, Ming Lei wrote:
>
>> The patch introduces the flag of memalloc_noio_resume in
>> 'struct dev_pm_info' to help PM core to teach mm not allocating
>> memory with GFP_KERNEL flag for avoiding probable deadlock
>> problem.
>>
>> As explained in the comment, any GFP_KERNEL allocation inside
>> runtime_resume on any one of device in the path from one block
>> or network device to the root device in the device tree may cause
>> deadlock, the introduced pm_runtime_set_memalloc_noio() sets or
>> clears the flag on device of the path recursively.
>>
>> This patch also introduces pm_runtime_get_memalloc_noio() because
>> the flag may be accessed in block device's error handling path
>> (for example, usb device reset)
>
>> +/*
>> + * pm_runtime_get_memalloc_noio - Get a device's memalloc_noio flag.
>> + * @dev: Device to handle.
>> + *
>> + * Return the device's memalloc_noio flag.
>> + *
>> + * The device power lock is held because bitfield is not SMP-safe.
>> + */
>> +bool pm_runtime_get_memalloc_noio(struct device *dev)
>> +{
>> + bool ret;
>> + spin_lock_irq(&dev->power.lock);
>> + ret = dev->power.memalloc_noio_resume;
>> + spin_unlock_irq(&dev->power.lock);
>> + return ret;
>> +}
>
> You don't need to acquire and release a spinlock just to read the
> value. Reading bitfields _is_ SMP-safe; writing them is not.
Thanks for your review.
As you pointed out before, the flag need to be checked before
resetting usb devices, so the lock should be held to make another
context(CPU) see the updated value suppose one context(CPU)
call pm_runtime_set_memalloc_noio() to change the flag at the
same time.
The lock needn't to be held when the function is called inside
pm_runtime_set_memalloc_noio(), so the bitfield flag should
be checked directly without holding power lock in dev_memalloc_noio().
>
>> +/*
>> + * pm_runtime_set_memalloc_noio - Set a device's memalloc_noio flag.
>> + * @dev: Device to handle.
>> + * @enable: True for setting the flag and False for clearing the flag.
>> + *
>> + * Set the flag for all devices in the path from the device to the
>> + * root device in the device tree if @enable is true, otherwise clear
>> + * the flag for devices in the path which sibliings don't set the flag.
>
> s/which/whose/
> s/ii/i
Will fix it in -v4.
>> + *
>> + * The function should only be called by block device, or network
>> + * device driver for solving the deadlock problem during runtime
>> + * resume:
>> + * if memory allocation with GFP_KERNEL is called inside runtime
>> + * resume callback of any one of its ancestors(or the block device
>> + * itself), the deadlock may be triggered inside the memory
>> + * allocation since it might not complete until the block device
>> + * becomes active and the involed page I/O finishes. The situation
>> + * is pointed out first by Alan Stern. Network device are involved
>> + * in iSCSI kind of situation.
>> + *
>> + * The lock of dev_hotplug_mutex is held in the function for handling
>> + * hotplug race because pm_runtime_set_memalloc_noio() may be called
>> + * in async probe().
>> + */
>> +void pm_runtime_set_memalloc_noio(struct device *dev, bool enable)
>> +{
>> + static DEFINE_MUTEX(dev_hotplug_mutex);
>> +
>> + mutex_lock(&dev_hotplug_mutex);
>> + while (dev) {
>
> Unless you think somebody is likely to call this function with dev
> equal to NULL, this can simply be
>
> for (;;) {
>
>> + /* hold power lock since bitfield is not SMP-safe. */
>> + spin_lock_irq(&dev->power.lock);
>> + dev->power.memalloc_noio_resume = enable;
>> + spin_unlock_irq(&dev->power.lock);
>> +
>> + dev = dev->parent;
>> +
>> + /* only clear the flag for one device if all
>> + * children of the device don't set the flag.
>> + */
>> + if (!dev || (!enable &&
>
> ... thanks to this test.
>
>> + device_for_each_child(dev, NULL,
>> + dev_memalloc_noio)))
>> + break;
>> + }
>> + mutex_unlock(&dev_hotplug_mutex);
>> +}
>
> This might not work if somebody calls pm_runtime_set_memalloc_noio(dev,
> true) and then afterwards registers dev at the same time as someone
> else calls pm_runtime_set_memalloc_noio(dev2, false), if dev and dev2
> have the same parent.
Good catch, pm_runtime_set_memalloc_noio() should be called between
device_add() and device_del() on block/network device.
> Perhaps the kerneldoc should mention that this function must not be
> called until after dev is registered.
Yes, it should be added in -v4.
Thanks,
--
Ming Lei
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply
* [Patch net-next] vlan: use IS_ENABLED()
From: Cong Wang @ 2012-10-30 3:22 UTC (permalink / raw)
To: netdev; +Cc: David S. Miller, Cong Wang
#if defined(CONFIG_FOO) || defined(CONFIG_FOO_MODULE)
can be replaced by
#if IS_ENABLED(CONFIG_FOO)
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: Cong Wang <amwang@redhat.com>
---
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index ee07072..30ee4bc 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -294,7 +294,7 @@ static void vlan_transfer_features(struct net_device *dev,
else
vlandev->hard_header_len = dev->hard_header_len + VLAN_HLEN;
-#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
+#if IS_ENABLED(CONFIG_FCOE)
vlandev->fcoe_ddp_xid = dev->fcoe_ddp_xid;
#endif
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 4024424..6da96d4 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -409,7 +409,7 @@ static int vlan_dev_neigh_setup(struct net_device *dev, struct neigh_parms *pa)
return err;
}
-#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
+#if IS_ENABLED(CONFIG_FCOE)
static int vlan_dev_fcoe_ddp_setup(struct net_device *dev, u16 xid,
struct scatterlist *sgl, unsigned int sgc)
{
@@ -564,7 +564,7 @@ static int vlan_dev_init(struct net_device *dev)
if (is_zero_ether_addr(dev->broadcast))
memcpy(dev->broadcast, real_dev->broadcast, dev->addr_len);
-#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
+#if IS_ENABLED(CONFIG_FCOE)
dev->fcoe_ddp_xid = real_dev->fcoe_ddp_xid;
#endif
@@ -741,7 +741,7 @@ static const struct net_device_ops vlan_netdev_ops = {
.ndo_do_ioctl = vlan_dev_ioctl,
.ndo_neigh_setup = vlan_dev_neigh_setup,
.ndo_get_stats64 = vlan_dev_get_stats64,
-#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
+#if IS_ENABLED(CONFIG_FCOE)
.ndo_fcoe_ddp_setup = vlan_dev_fcoe_ddp_setup,
.ndo_fcoe_ddp_done = vlan_dev_fcoe_ddp_done,
.ndo_fcoe_enable = vlan_dev_fcoe_enable,
^ permalink raw reply related
* Re: [PATCH 3/4] arm: mvebu: add Ethernet controllers using mvneta driver for Armada 370/XP
From: Nobuhiro Iwamatsu @ 2012-10-30 4:19 UTC (permalink / raw)
To: Thomas Petazzoni
Cc: David S. Miller, Lennert Buytenhek, Lior Amsalem, Andrew Lunn,
Jason Cooper, netdev, Maen Suleiman, Gregory Clement,
linux-arm-kernel
In-Reply-To: <1351245804-31478-4-git-send-email-thomas.petazzoni@free-electrons.com>
On Fri, Oct 26, 2012 at 7:03 PM, Thomas Petazzoni
<thomas.petazzoni@free-electrons.com> wrote:
> The Armada 370 SoC has two network units, while the Armada XP has four
> network units. The first two network units are common to both the
> Armada XP and Armada 370, so they are added to armada-370-xp.dtsi,
> while the other two network units are specific to the Armada XP and
> therefore added to armada-xp.dtsi.
>
> Signed-off-by: Thomas Petazzoni <thomas.petazzoni@free-electrons.com>
> ---
> arch/arm/boot/dts/armada-370-xp.dtsi | 14 ++++++++++++++
> arch/arm/boot/dts/armada-xp.dtsi | 14 ++++++++++++++
> 2 files changed, 28 insertions(+)
>
> diff --git a/arch/arm/boot/dts/armada-370-xp.dtsi b/arch/arm/boot/dts/armada-370-xp.dtsi
> index 16cc82c..d484492 100644
> --- a/arch/arm/boot/dts/armada-370-xp.dtsi
> +++ b/arch/arm/boot/dts/armada-370-xp.dtsi
> @@ -68,6 +68,20 @@
> compatible = "marvell,armada-addr-decoding-controller";
> reg = <0xd0020000 0x258>;
> };
> +
> + ethernet@d0070000 {
> + compatible = "marvell,armada-370-neta";
> + reg = <0xd0070000 0x2500>;
> + interrupts = <8>;
> + status = "disabled";
> + };
> +
> + ethernet@d0074000 {
> + compatible = "marvell,armada-370-neta";
> + reg = <0xd0074000 0x2500>;
> + interrupts = <10>;
> + status = "disabled";
> + };
Could you fit an indent?
> };
> };
>
> diff --git a/arch/arm/boot/dts/armada-xp.dtsi b/arch/arm/boot/dts/armada-xp.dtsi
> index 71d6b5d..c77a43e 100644
> --- a/arch/arm/boot/dts/armada-xp.dtsi
> +++ b/arch/arm/boot/dts/armada-xp.dtsi
> @@ -51,5 +51,19 @@
> compatible = "marvell,armada-370-xp-system-controller";
> reg = <0xd0018200 0x500>;
> };
> +
> + ethernet@d0030000 {
> + compatible = "marvell,armada-370-neta";
> + reg = <0xd0030000 0x2500>;
> + interrupts = <12>;
> + status = "disabled";
> + };
> +
> + ethernet@d0034000 {
> + compatible = "marvell,armada-370-neta";
> + reg = <0xd0034000 0x2500>;
> + interrupts = <14>;
> + status = "disabled";
> + };
likewise.
--
Nobuhiro Iwamatsu
iwamatsu at {nigauri.org / debian.org}
GPG ID: 40AD1FA6
^ permalink raw reply
* NETDEV WATCHDOG: eth2 (tg3): transmit queue 0 timed out
From: Paul Thompson @ 2012-10-30 4:32 UTC (permalink / raw)
To: netdev; +Cc: Matt Carlson, Michael Chan
Hi;
Just noticed this in my logs after 10 days uptime. The interface
is reset and continues to work fine. Looking back through the logs, I
see it happened in 3.3.0-rc4 for the first time. No occurance from
2.6.35.5 util then, and I have run all versions in between. Load on
the interface is light; just connects to a cable modem.
Paul
set.mailinglist@gmail.com
After this, there is a large dump of hex numbers. If this is signifigant
let me know and I will supply any more information or testing.
2012 Oct 29 08:37:25: ------------[ cut here ]------------
2012 Oct 29 08:37:25: WARNING: at net/sched/sch_generic.c:255 dev_watchdog+0x22f/0x240()
2012 Oct 29 08:37:25: Hardware name: To Be Filled By O.E.M.
2012 Oct 29 08:37:25: NETDEV WATCHDOG: eth2 (tg3): transmit queue 0 timed out
2012 Oct 29 08:37:25: Modules linked in: hid_logitech_dj serpent_sse2_x86_64 ablk_helper cryptd glue_helper lrw serpent_generic xts gf128mul cpufreq_ondemand btrfs lzo_decompress lzo_compress libcrc32c dm_crypt dm_mod radeon ttm drm_kms_helper drm backlight i2c_algo_bit cfbcopyarea cfbimgblt cfbfillrect snd_ens1371 snd_rawmidi snd_ac97_codec snd_pcm snd_page_alloc ac97_bus pcspkr [last unloaded: hid_logitech_dj]
2012 Oct 29 08:37:25: Pid: 0, comm: swapper/1 Not tainted 3.6.2-low-lat #13
2012 Oct 29 08:37:25: Call Trace:
2012 Oct 29 08:37:25: <IRQ> [<ffffffff8134a300>] ? dev_watchdog+0x1c0/0x240
2012 Oct 29 08:37:25: [<ffffffff81030329>] ? warn_slowpath_common+0x79/0xc0
2012 Oct 29 08:37:25: [<ffffffff81030425>] ? warn_slowpath_fmt+0x45/0x50
2012 Oct 29 08:37:25: [<ffffffff8134a36f>] ? dev_watchdog+0x22f/0x240
2012 Oct 29 08:37:25: [<ffffffff8134a140>] ? dev_graft_qdisc+0x90/0x90
2012 Oct 29 08:37:25: [<ffffffff8103c9cd>] ? run_timer_softirq+0x12d/0x270
2012 Oct 29 08:37:25: [<ffffffff810374f4>] ? __do_softirq+0xa4/0x150
2012 Oct 29 08:37:25: [<ffffffff813d976c>] ? call_softirq+0x1c/0x30
2012 Oct 29 08:37:25: [<ffffffff81003e6d>] ? do_softirq+0x4d/0x80
2012 Oct 29 08:37:25: [<ffffffff810378a5>] ? irq_exit+0xa5/0xb0
2012 Oct 29 08:37:25: [<ffffffff810202e8>] ? smp_apic_timer_interrupt+0x68/0xa0
2012 Oct 29 08:37:25: [<ffffffff813d9087>] ? apic_timer_interrupt+0x67/0x70
2012 Oct 29 08:37:25: <EOI> [<ffffffff8100a25e>] ? default_idle+0x2e/0x50
2012 Oct 29 08:37:25: [<ffffffff8100a23e>] ? default_idle+0xe/0x50
2012 Oct 29 08:37:25: [<ffffffff8100a3ab>] ? amd_e400_idle+0x7b/0xf0
2012 Oct 29 08:37:25: [<ffffffff8100ac56>] ? cpu_idle+0xc6/0xe0
2012 Oct 29 08:37:25: ---[ end trace ff857795a2d2309a ]---
^ permalink raw reply
* [PATCH RFC] pkt_sched: enable QFQ to support TSO/GSO
From: Paolo Valente @ 2012-10-30 6:00 UTC (permalink / raw)
To: jhs, davem, shemminger
Cc: linux-kernel, netdev, rizzo, fchecconi, paolo.valente
[new version modified according to the suggestions received]
Hi,
if the max packet size for some class (configured through tc) is
violated by the actual size of the packets of that class, then QFQ
would not schedule classes correctly, and the data structures
implementing the bucket lists may get corrupted. This problem occurs
with TSO/GSO even if the max packet size is set to the MTU, and is,
e.g., the cause of the failure reported in [1]. Two patches have been
proposed to solve this problem in [2], one of them is a preliminary
version of this patch.
This patch addresses the above issues by: 1) setting QFQ parameters to
proper values for supporting TSO/GSO (in particular, setting the
maximum possible packet size to 64KB), 2) automatically increasing the
max packet size for a class, lmax, when a packet with a larger size
than the current value of lmax arrives.
The drawback of the first point is that the maximum weight for a class
is now limited to 4096, which is equal to 1/16 of the maximum weight
sum.
Finally, this patch also forcibly caps the timestamps of a class if
they are too high to be stored in the bucket list. This capping, taken
from QFQ+ [3], handles the unfrequent case described in the comment to
the function slot_insert.
[1] http://marc.info/?l=linux-netdev&m=134968777902077&w=2
[2] http://marc.info/?l=linux-netdev&m=135096573507936&w=2
[3] http://marc.info/?l=linux-netdev&m=134902691421670&w=2
Signed-off-by: Paolo Valente <paolo.valente@unimore.it>
Tested-by: Cong Wang <amwang@redhat.com>
---
net/sched/sch_qfq.c | 109 +++++++++++++++++++++++++++++++++++++--------------
1 file changed, 79 insertions(+), 30 deletions(-)
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index f0dd83c..9687fa1 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -84,18 +84,19 @@
* grp->index is the index of the group; and grp->slot_shift
* is the shift for the corresponding (scaled) sigma_i.
*/
-#define QFQ_MAX_INDEX 19
-#define QFQ_MAX_WSHIFT 16
+#define QFQ_MAX_INDEX 24
+#define QFQ_MAX_WSHIFT 12
#define QFQ_MAX_WEIGHT (1<<QFQ_MAX_WSHIFT)
-#define QFQ_MAX_WSUM (2*QFQ_MAX_WEIGHT)
+#define QFQ_MAX_WSUM (16*QFQ_MAX_WEIGHT)
#define FRAC_BITS 30 /* fixed point arithmetic */
#define ONE_FP (1UL << FRAC_BITS)
#define IWSUM (ONE_FP/QFQ_MAX_WSUM)
-#define QFQ_MTU_SHIFT 11
+#define QFQ_MTU_SHIFT 16 /* to support TSO/GSO */
#define QFQ_MIN_SLOT_SHIFT (FRAC_BITS + QFQ_MTU_SHIFT - QFQ_MAX_INDEX)
+#define QFQ_MIN_LMAX 256 /* min possible lmax for a class */
/*
* Possible group states. These values are used as indexes for the bitmaps
@@ -231,6 +232,32 @@ static void qfq_update_class_params(struct qfq_sched *q, struct qfq_class *cl,
q->wsum += delta_w;
}
+static void qfq_update_reactivate_class(struct qfq_sched *q,
+ struct qfq_class *cl,
+ u32 inv_w, u32 lmax, int delta_w)
+{
+ bool need_reactivation = false;
+ int i = qfq_calc_index(inv_w, lmax);
+
+ if (&q->groups[i] != cl->grp && cl->qdisc->q.qlen > 0) {
+ /*
+ * shift cl->F back, to not charge the
+ * class for the not-yet-served head
+ * packet
+ */
+ cl->F = cl->S;
+ /* remove class from its slot in the old group */
+ qfq_deactivate_class(q, cl);
+ need_reactivation = true;
+ }
+
+ qfq_update_class_params(q, cl, lmax, inv_w, delta_w);
+
+ if (need_reactivation) /* activate in new group */
+ qfq_activate_class(q, cl, qdisc_peek_len(cl->qdisc));
+}
+
+
static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
struct nlattr **tca, unsigned long *arg)
{
@@ -238,7 +265,7 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
struct qfq_class *cl = (struct qfq_class *)*arg;
struct nlattr *tb[TCA_QFQ_MAX + 1];
u32 weight, lmax, inv_w;
- int i, err;
+ int err;
int delta_w;
if (tca[TCA_OPTIONS] == NULL) {
@@ -270,16 +297,14 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
if (tb[TCA_QFQ_LMAX]) {
lmax = nla_get_u32(tb[TCA_QFQ_LMAX]);
- if (!lmax || lmax > (1UL << QFQ_MTU_SHIFT)) {
+ if (lmax < QFQ_MIN_LMAX || lmax > (1UL << QFQ_MTU_SHIFT)) {
pr_notice("qfq: invalid max length %u\n", lmax);
return -EINVAL;
}
} else
- lmax = 1UL << QFQ_MTU_SHIFT;
+ lmax = psched_mtu(qdisc_dev(sch));
if (cl != NULL) {
- bool need_reactivation = false;
-
if (tca[TCA_RATE]) {
err = gen_replace_estimator(&cl->bstats, &cl->rate_est,
qdisc_root_sleeping_lock(sch),
@@ -291,24 +316,8 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
if (lmax == cl->lmax && inv_w == cl->inv_w)
return 0; /* nothing to update */
- i = qfq_calc_index(inv_w, lmax);
sch_tree_lock(sch);
- if (&q->groups[i] != cl->grp && cl->qdisc->q.qlen > 0) {
- /*
- * shift cl->F back, to not charge the
- * class for the not-yet-served head
- * packet
- */
- cl->F = cl->S;
- /* remove class from its slot in the old group */
- qfq_deactivate_class(q, cl);
- need_reactivation = true;
- }
-
- qfq_update_class_params(q, cl, lmax, inv_w, delta_w);
-
- if (need_reactivation) /* activate in new group */
- qfq_activate_class(q, cl, qdisc_peek_len(cl->qdisc));
+ qfq_update_reactivate_class(q, cl, inv_w, lmax, delta_w);
sch_tree_unlock(sch);
return 0;
@@ -663,15 +672,48 @@ static void qfq_make_eligible(struct qfq_sched *q, u64 old_V)
/*
- * XXX we should make sure that slot becomes less than 32.
- * This is guaranteed by the input values.
- * roundedS is always cl->S rounded on grp->slot_shift bits.
+ * If the weight and lmax (max_pkt_size) of the classes do not change,
+ * then QFQ guarantees that the slot index is never higher than
+ * 2 + ((1<<QFQ_MTU_SHIFT)/QFQ_MIN_LMAX) * (QFQ_MAX_WEIGHT/QFQ_MAX_WSUM).
+ *
+ * With the current values of the above constants, the index is
+ * then guaranteed to never be higher than 2 + 256 * (1 / 16) = 18.
+ *
+ * When the weight of a class is increased or the lmax of the class is
+ * decreased, a new class with smaller slot size may happen to be
+ * activated. The activation of this class should be properly delayed
+ * to when the service of the class has finished in the ideal system
+ * tracked by QFQ. If the activation of the class is not delayed to
+ * this reference time instant, then this class may be unjustly served
+ * before other classes waiting for service. This may cause
+ * (unfrequently) the above bound to the slot index to be violated for
+ * some of these unlucky classes.
+ *
+ * Instead of delaying the activation of the new class, which is quite
+ * complex, the following inaccurate but simple solution is used: if
+ * the slot index is higher than QFQ_MAX_SLOTS-2, then the timestamps
+ * of the class are shifted backward so as to let the slot index
+ * become equal to QFQ_MAX_SLOTS-2. This threshold is used because, if
+ * the slot index is above it, then the data structure implementing
+ * the bucket list either gets immediately corrupted or may get
+ * corrupted on a possible next packet arrival that causes the start
+ * time of the group to be shifted backward.
*/
static void qfq_slot_insert(struct qfq_group *grp, struct qfq_class *cl,
u64 roundedS)
{
u64 slot = (roundedS - grp->S) >> grp->slot_shift;
- unsigned int i = (grp->front + slot) % QFQ_MAX_SLOTS;
+ unsigned int i; /* slot index in the bucket list */
+
+ if (unlikely(slot > QFQ_MAX_SLOTS - 2)) {
+ u64 deltaS = roundedS - grp->S -
+ ((u64)(QFQ_MAX_SLOTS - 2)<<grp->slot_shift);
+ cl->S -= deltaS;
+ cl->F -= deltaS;
+ slot = QFQ_MAX_SLOTS - 2;
+ }
+
+ i = (grp->front + slot) % QFQ_MAX_SLOTS;
hlist_add_head(&cl->next, &grp->slots[i]);
__set_bit(slot, &grp->full_slots);
@@ -892,6 +934,13 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
}
pr_debug("qfq_enqueue: cl = %x\n", cl->common.classid);
+ if (unlikely(cl->lmax < qdisc_pkt_len(skb))) {
+ pr_debug("qfq: increasing maxpkt from %u to %u for class %u",
+ cl->lmax, qdisc_pkt_len(skb), cl->common.classid);
+ qfq_update_reactivate_class(q, cl, cl->inv_w,
+ qdisc_pkt_len(skb), 0);
+ }
+
err = qdisc_enqueue(skb, cl->qdisc);
if (unlikely(err != NET_XMIT_SUCCESS)) {
pr_debug("qfq_enqueue: enqueue failed %d\n", err);
--
1.7.9.5
^ permalink raw reply related
* Re: [PATCH] net: dsa/slave: Fix compilation warnings
From: Viresh Kumar @ 2012-10-30 6:45 UTC (permalink / raw)
To: Ben Hutchings; +Cc: davem, linaro-dev, patches, netdev, linux-kernel
In-Reply-To: <1351540778.2721.7.camel@bwh-desktop.uk.solarflarecom.com>
On 30 October 2012 01:29, Ben Hutchings <bhutchings@solarflare.com> wrote:
> On Mon, 2012-10-29 at 22:27 +0530, Viresh Kumar wrote:
>> Currently when none of CONFIG_NET_DSA_TAG_DSA, CONFIG_NET_DSA_TAG_EDSA and
>> CONFIG_NET_DSA_TAG_TRAILER is defined, we get following compilation warnings:
>>
>> net/dsa/slave.c:51:12: warning: 'dsa_slave_init' defined but not used [-Wunused-function]
>> net/dsa/slave.c:60:12: warning: 'dsa_slave_open' defined but not used [-Wunused-function]
>> net/dsa/slave.c:98:12: warning: 'dsa_slave_close' defined but not used [-Wunused-function]
>> net/dsa/slave.c:116:13: warning: 'dsa_slave_change_rx_flags' defined but not used [-Wunused-function]
>> net/dsa/slave.c:127:13: warning: 'dsa_slave_set_rx_mode' defined but not used [-Wunused-function]
>> net/dsa/slave.c:136:12: warning: 'dsa_slave_set_mac_address' defined but not used [-Wunused-function]
>> net/dsa/slave.c:164:12: warning: 'dsa_slave_ioctl' defined but not used [-Wunused-function]
>>
>> Fix them by enclosing these routines under #ifdef,endif.
> [...]
>
> This is not a useful configuration. It might make more sense to make
> NET_DSA a hidden option and have the DSA drivers (in drivers/net/dsa)
> select it rather than depending on it.
I don't have any idea about net/dsa/***. I just wanted to fix this
awkward looking warning :)
What i understood from your comment is: Atleast one of the tagging
formats must be
always enabled if we want to use net/dsa/ stuff ??
And so the functions i have enclosed under ifdefs will always be used
if net/dsa/ is
used.
And so, if we select NET_DSA from these tagging drivers, then only slave.c will
get compiled. Otherwise slave.c dsa.c dsa_core.c wouldn't be compiled and so
no warnings.
Correct??
--
viresh
^ permalink raw reply
* Re: NETDEV WATCHDOG: eth2 (tg3): transmit queue 0 timed out
From: Michael Chan @ 2012-10-30 6:57 UTC (permalink / raw)
To: Paul Thompson; +Cc: netdev, Matt Carlson
In-Reply-To: <20121030043213.GE2604@squish.home.loc>
On Tue, 2012-10-30 at 00:32 -0400, Paul Thompson wrote:
> Hi;
>
> Just noticed this in my logs after 10 days uptime. The interface
> is reset and continues to work fine. Looking back through the logs, I
> see it happened in 3.3.0-rc4 for the first time. No occurance from
> 2.6.35.5 util then, and I have run all versions in between. Load on
> the interface is light; just connects to a cable modem.
>
> Paul
> set.mailinglist@gmail.com
>
> After this, there is a large dump of hex numbers. If this is signifigant
> let me know and I will supply any more information or testing.
Please provide the full message log from a few seconds before what you
provided below and include those hex numbers. Please also include the
tg3 signon message for eth2 so that we know what device it is.
Did you run any ethtool command or MTU change around the time of the
watchdog? Thanks.
>
> 2012 Oct 29 08:37:25: ------------[ cut here ]------------
> 2012 Oct 29 08:37:25: WARNING: at net/sched/sch_generic.c:255 dev_watchdog+0x22f/0x240()
> 2012 Oct 29 08:37:25: Hardware name: To Be Filled By O.E.M.
> 2012 Oct 29 08:37:25: NETDEV WATCHDOG: eth2 (tg3): transmit queue 0 timed out
> 2012 Oct 29 08:37:25: Modules linked in: hid_logitech_dj serpent_sse2_x86_64 ablk_helper cryptd glue_helper lrw serpent_generic xts gf128mul cpufreq_ondemand btrfs lzo_decompress lzo_compress libcrc32c dm_crypt dm_mod radeon ttm drm_kms_helper drm backlight i2c_algo_bit cfbcopyarea cfbimgblt cfbfillrect snd_ens1371 snd_rawmidi snd_ac97_codec snd_pcm snd_page_alloc ac97_bus pcspkr [last unloaded: hid_logitech_dj]
> 2012 Oct 29 08:37:25: Pid: 0, comm: swapper/1 Not tainted 3.6.2-low-lat #13
> 2012 Oct 29 08:37:25: Call Trace:
> 2012 Oct 29 08:37:25: <IRQ> [<ffffffff8134a300>] ? dev_watchdog+0x1c0/0x240
> 2012 Oct 29 08:37:25: [<ffffffff81030329>] ? warn_slowpath_common+0x79/0xc0
> 2012 Oct 29 08:37:25: [<ffffffff81030425>] ? warn_slowpath_fmt+0x45/0x50
> 2012 Oct 29 08:37:25: [<ffffffff8134a36f>] ? dev_watchdog+0x22f/0x240
> 2012 Oct 29 08:37:25: [<ffffffff8134a140>] ? dev_graft_qdisc+0x90/0x90
> 2012 Oct 29 08:37:25: [<ffffffff8103c9cd>] ? run_timer_softirq+0x12d/0x270
> 2012 Oct 29 08:37:25: [<ffffffff810374f4>] ? __do_softirq+0xa4/0x150
> 2012 Oct 29 08:37:25: [<ffffffff813d976c>] ? call_softirq+0x1c/0x30
> 2012 Oct 29 08:37:25: [<ffffffff81003e6d>] ? do_softirq+0x4d/0x80
> 2012 Oct 29 08:37:25: [<ffffffff810378a5>] ? irq_exit+0xa5/0xb0
> 2012 Oct 29 08:37:25: [<ffffffff810202e8>] ? smp_apic_timer_interrupt+0x68/0xa0
> 2012 Oct 29 08:37:25: [<ffffffff813d9087>] ? apic_timer_interrupt+0x67/0x70
> 2012 Oct 29 08:37:25: <EOI> [<ffffffff8100a25e>] ? default_idle+0x2e/0x50
> 2012 Oct 29 08:37:25: [<ffffffff8100a23e>] ? default_idle+0xe/0x50
> 2012 Oct 29 08:37:25: [<ffffffff8100a3ab>] ? amd_e400_idle+0x7b/0xf0
> 2012 Oct 29 08:37:25: [<ffffffff8100ac56>] ? cpu_idle+0xc6/0xe0
> 2012 Oct 29 08:37:25: ---[ end trace ff857795a2d2309a ]---
>
>
^ permalink raw reply
* [net-next 02/13] ixgbe: Fix return value from macvlan filter function
From: Jeff Kirsher @ 2012-10-30 7:04 UTC (permalink / raw)
To: davem; +Cc: Greg Rose, netdev, gospo, sassmann, Jeff Kirsher
In-Reply-To: <1351580670-8292-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Greg Rose <gregory.v.rose@intel.com>
The function to set the macvlan filter should return success or failure
instead of the index of the filter. The message processing function was
misinterpreting the index as a non-zero return code indicating failure and
NACKing MAC filter set messages that actually succeeded.
Signed-off-by: Greg Rose <gregory.v.rose@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
index 96876b7..8bdb341 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
@@ -742,7 +742,8 @@ static int ixgbe_set_vf_macvlan_msg(struct ixgbe_adapter *adapter,
e_warn(drv,
"VF %d has requested a MACVLAN filter but there is no space for it\n",
vf);
- return err;
+
+ return err < 0;
}
static int ixgbe_negotiate_vf_api(struct ixgbe_adapter *adapter,
--
1.7.11.7
^ permalink raw reply related
* [net-next 04/13] ixgbe: clean up the condition for turning on/off the laser
From: Jeff Kirsher @ 2012-10-30 7:04 UTC (permalink / raw)
To: davem; +Cc: Emil Tantilov, netdev, gospo, sassmann, Jeff Kirsher
In-Reply-To: <1351580670-8292-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Emil Tantilov <emil.s.tantilov@intel.com>
This patch simplifies the check for calling en/disable_tx_laser() function
pointer. The pointer is only set on parts that can use it.
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 31 +++++++--------------------
1 file changed, 8 insertions(+), 23 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 97bab45..ceab142 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -4087,11 +4087,8 @@ static void ixgbe_up_complete(struct ixgbe_adapter *adapter)
else
ixgbe_configure_msi_and_legacy(adapter);
- /* enable the optics for both mult-speed fiber and 82599 SFP+ fiber */
- if (hw->mac.ops.enable_tx_laser &&
- ((hw->phy.multispeed_fiber) ||
- ((hw->mac.ops.get_media_type(hw) == ixgbe_media_type_fiber) &&
- (hw->mac.type == ixgbe_mac_82599EB))))
+ /* enable the optics for 82599 SFP+ fiber */
+ if (hw->mac.ops.enable_tx_laser)
hw->mac.ops.enable_tx_laser(hw);
clear_bit(__IXGBE_DOWN, &adapter->state);
@@ -4413,11 +4410,8 @@ void ixgbe_down(struct ixgbe_adapter *adapter)
if (!pci_channel_offline(adapter->pdev))
ixgbe_reset(adapter);
- /* power down the optics for multispeed fiber and 82599 SFP+ fiber */
- if (hw->mac.ops.disable_tx_laser &&
- ((hw->phy.multispeed_fiber) ||
- ((hw->mac.ops.get_media_type(hw) == ixgbe_media_type_fiber) &&
- (hw->mac.type == ixgbe_mac_82599EB))))
+ /* power down the optics for 82599 SFP+ fiber */
+ if (hw->mac.ops.disable_tx_laser)
hw->mac.ops.disable_tx_laser(hw);
ixgbe_clean_all_tx_rings(adapter);
@@ -5050,14 +5044,8 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake)
if (wufc) {
ixgbe_set_rx_mode(netdev);
- /*
- * enable the optics for both mult-speed fiber and
- * 82599 SFP+ fiber as we can WoL.
- */
- if (hw->mac.ops.enable_tx_laser &&
- (hw->phy.multispeed_fiber ||
- (hw->mac.ops.get_media_type(hw) == ixgbe_media_type_fiber &&
- hw->mac.type == ixgbe_mac_82599EB)))
+ /* enable the optics for 82599 SFP+ fiber as we can WoL */
+ if (hw->mac.ops.enable_tx_laser)
hw->mac.ops.enable_tx_laser(hw);
/* turn on all-multi mode if wake on multicast is enabled */
@@ -7468,11 +7456,8 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev,
if (err)
goto err_register;
- /* power down the optics for multispeed fiber and 82599 SFP+ fiber */
- if (hw->mac.ops.disable_tx_laser &&
- ((hw->phy.multispeed_fiber) ||
- ((hw->mac.ops.get_media_type(hw) == ixgbe_media_type_fiber) &&
- (hw->mac.type == ixgbe_mac_82599EB))))
+ /* power down the optics for 82599 SFP+ fiber */
+ if (hw->mac.ops.disable_tx_laser)
hw->mac.ops.disable_tx_laser(hw);
/* carrier off reporting is important to ethtool even BEFORE open */
--
1.7.11.7
^ permalink raw reply related
* [net-next 05/13] ixgbe: Return success or failure on VF MAC filter set
From: Jeff Kirsher @ 2012-10-30 7:04 UTC (permalink / raw)
To: davem; +Cc: Greg Rose, netdev, gospo, sassmann, Jeff Kirsher
In-Reply-To: <1351580670-8292-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Greg Rose <gregory.v.rose@intel.com>
When setting a MAC filter for the VF the function should return a success
or failure code, not the index of the new filter. It causes spurious NACK
returns to the VF driver.
Signed-off-by: Greg Rose <gregory.v.rose@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Tested-by: Sibai Li <sibai.li@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
index 8bdb341..bfeb7ec 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
@@ -675,7 +675,7 @@ static int ixgbe_set_vf_mac_addr(struct ixgbe_adapter *adapter,
return -1;
}
- return ixgbe_set_vf_mac(adapter, vf, new_mac);
+ return ixgbe_set_vf_mac(adapter, vf, new_mac) < 0;
}
static int ixgbe_set_vf_vlan_msg(struct ixgbe_adapter *adapter,
--
1.7.11.7
^ permalink raw reply related
* [net-next 03/13] net, ixgbe: handle link local multicast addresses in SR-IOV mode
From: Jeff Kirsher @ 2012-10-30 7:04 UTC (permalink / raw)
To: davem; +Cc: John Fastabend, netdev, gospo, sassmann, Jeff Kirsher
In-Reply-To: <1351580670-8292-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: John Fastabend <john.r.fastabend@intel.com>
In SR-IOV mode the PF driver acts as the uplink port and is
used to send control packets e.g. lldpad, stp, etc.
eth0.1 eth0.2 eth0
VF VF PF
| | | <-- stand-in for uplink
| | |
--------------------------
| Embedded Switch |
--------------------------
|
MAC <-- uplink
But the embedded switch is setup to forward multicast addresses
to all interfaces both VFs and PF and onto the physical link.
This results in reserved MAC addresses used by control protocols
to be forwarded over the switch onto the VF.
In the LLDP case the PF sends an LLDPDU and it is currently
being forwarded to all the VFs who then see the PF as a peer.
This is incorrect.
This patch adds the multicast addresses to the RAR table in the
hardware to prevent this behavior.
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Tested-by: Sibai Li <sibai.li@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 2 +-
drivers/net/ethernet/intel/ixgbevf/vf.c | 3 +++
include/linux/etherdevice.h | 19 +++++++++++++++++++
net/bridge/br_device.c | 2 +-
net/bridge/br_input.c | 15 ---------------
net/bridge/br_private.h | 1 -
net/bridge/br_sysfs_br.c | 3 ++-
7 files changed, 26 insertions(+), 19 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 88d636a..97bab45 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -6967,7 +6967,7 @@ static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
return -EINVAL;
}
- if (is_unicast_ether_addr(addr)) {
+ if (is_unicast_ether_addr(addr) || is_link_local(addr)) {
u32 rar_uc_entries = IXGBE_MAX_PF_MACVLANS;
if (netdev_uc_count(dev) < rar_uc_entries)
diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c
index 5fa397b..c0fd1ef 100644
--- a/drivers/net/ethernet/intel/ixgbevf/vf.c
+++ b/drivers/net/ethernet/intel/ixgbevf/vf.c
@@ -331,6 +331,9 @@ static s32 ixgbevf_update_mc_addr_list_vf(struct ixgbe_hw *hw,
netdev_for_each_mc_addr(ha, netdev) {
if (i == cnt)
break;
+ if (is_link_local(ha->addr))
+ continue;
+
vector_list[i++] = ixgbevf_mta_vector(hw, ha->addr);
}
diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index b006ba0..45ded4b 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -51,6 +51,25 @@ extern struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs,
#define alloc_etherdev(sizeof_priv) alloc_etherdev_mq(sizeof_priv, 1)
#define alloc_etherdev_mq(sizeof_priv, count) alloc_etherdev_mqs(sizeof_priv, count, count)
+/* Reserved Ethernet Addresses per IEEE 802.1Q */
+static const u8 br_reserved_address[ETH_ALEN] = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 };
+
+/**
+ * is_link_local - Determine if given Eth addr is a link local mcast address.
+ * @addr: Pointer to a six-byte array containing the Ethernet address
+ *
+ * Return true if address is link local reserved addr (01:80:c2:00:00:0X) per
+ * IEEE 802.1Q 8.6.3 Frame filtering.
+ */
+static inline int is_link_local(const unsigned char *dest)
+{
+ __be16 *a = (__be16 *)dest;
+ static const __be16 *b = (const __be16 *)br_reserved_address;
+ static const __be16 m = cpu_to_be16(0xfff0);
+
+ return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | ((a[2] ^ b[2]) & m)) == 0;
+}
+
/**
* is_zero_ether_addr - Determine if give Ethernet address is all zeros.
* @addr: Pointer to a six-byte array containing the Ethernet address
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 070e8a6..d41b6f9 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -356,7 +356,7 @@ void br_dev_setup(struct net_device *dev)
br->bridge_id.prio[0] = 0x80;
br->bridge_id.prio[1] = 0x00;
- memcpy(br->group_addr, br_group_address, ETH_ALEN);
+ memcpy(br->group_addr, br_reserved_address, ETH_ALEN);
br->stp_enabled = BR_NO_STP;
br->group_fwd_mask = BR_GROUPFWD_DEFAULT;
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 76f15fd..d047978 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -19,9 +19,6 @@
#include <linux/export.h>
#include "br_private.h"
-/* Bridge group multicast address 802.1d (pg 51). */
-const u8 br_group_address[ETH_ALEN] = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 };
-
/* Hook for brouter */
br_should_route_hook_t __rcu *br_should_route_hook __read_mostly;
EXPORT_SYMBOL(br_should_route_hook);
@@ -127,18 +124,6 @@ static int br_handle_local_finish(struct sk_buff *skb)
return 0; /* process further */
}
-/* Does address match the link local multicast address.
- * 01:80:c2:00:00:0X
- */
-static inline int is_link_local(const unsigned char *dest)
-{
- __be16 *a = (__be16 *)dest;
- static const __be16 *b = (const __be16 *)br_group_address;
- static const __be16 m = cpu_to_be16(0xfff0);
-
- return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | ((a[2] ^ b[2]) & m)) == 0;
-}
-
/*
* Return NULL if skb is handled
* note: already called with rcu_read_lock
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 9b278c4..65b191a 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -288,7 +288,6 @@ struct br_input_skb_cb {
pr_debug("%s: " format, (br)->dev->name, ##args)
extern struct notifier_block br_device_notifier;
-extern const u8 br_group_address[ETH_ALEN];
/* called under bridge lock */
static inline int br_is_root_bridge(const struct net_bridge *br)
diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c
index c5c0593..e157b0d 100644
--- a/net/bridge/br_sysfs_br.c
+++ b/net/bridge/br_sysfs_br.c
@@ -14,6 +14,7 @@
#include <linux/capability.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
#include <linux/if_bridge.h>
#include <linux/rtnetlink.h>
#include <linux/spinlock.h>
@@ -310,7 +311,7 @@ static ssize_t store_group_addr(struct device *d,
/* Must be 01:80:c2:00:00:0X */
for (i = 0; i < 5; i++)
- if (new_addr[i] != br_group_address[i])
+ if (new_addr[i] != br_reserved_address[i])
return -EINVAL;
if (new_addr[5] & ~0xf)
--
1.7.11.7
^ permalink raw reply related
* [net-next 07/13] ixgbe: add/update descriptor maps in comments
From: Jeff Kirsher @ 2012-10-30 7:04 UTC (permalink / raw)
To: davem; +Cc: Josh Hay, netdev, gospo, sassmann, Jeff Kirsher
In-Reply-To: <1351580670-8292-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Josh Hay <joshua.a.hay@intel.com>
Adds/updates ASCII descriptor maps for 82598 and 82599 Tx/Rx descriptors.
Current descriptor maps were out of date for 82598 and incorrect for
82599.
Signed-off-by: Josh Hay <joshua.a.hay@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 61 ++++++++++++++++++++++++---
1 file changed, 55 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index a34ee7d..6035674 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -355,13 +355,37 @@ static void ixgbe_dump(struct ixgbe_adapter *adapter)
/* Transmit Descriptor Formats
*
- * Advanced Transmit Descriptor
+ * 82598 Advanced Transmit Descriptor
* +--------------------------------------------------------------+
* 0 | Buffer Address [63:0] |
* +--------------------------------------------------------------+
- * 8 | PAYLEN | PORTS | IDX | STA | DCMD |DTYP | RSV | DTALEN |
+ * 8 | PAYLEN | POPTS | IDX | STA | DCMD |DTYP | RSV | DTALEN |
* +--------------------------------------------------------------+
* 63 46 45 40 39 36 35 32 31 24 23 20 19 0
+ *
+ * 82598 Advanced Transmit Descriptor (Write-Back Format)
+ * +--------------------------------------------------------------+
+ * 0 | RSV [63:0] |
+ * +--------------------------------------------------------------+
+ * 8 | RSV | STA | NXTSEQ |
+ * +--------------------------------------------------------------+
+ * 63 36 35 32 31 0
+ *
+ * 82599+ Advanced Transmit Descriptor
+ * +--------------------------------------------------------------+
+ * 0 | Buffer Address [63:0] |
+ * +--------------------------------------------------------------+
+ * 8 |PAYLEN |POPTS|CC|IDX |STA |DCMD |DTYP |MAC |RSV |DTALEN |
+ * +--------------------------------------------------------------+
+ * 63 46 45 40 39 38 36 35 32 31 24 23 20 19 18 17 16 15 0
+ *
+ * 82599+ Advanced Transmit Descriptor (Write-Back Format)
+ * +--------------------------------------------------------------+
+ * 0 | RSV [63:0] |
+ * +--------------------------------------------------------------+
+ * 8 | RSV | STA | RSV |
+ * +--------------------------------------------------------------+
+ * 63 36 35 32 31 0
*/
for (n = 0; n < adapter->num_tx_queues; n++) {
@@ -422,7 +446,9 @@ rx_ring_summary:
dev_info(&adapter->pdev->dev, "RX Rings Dump\n");
- /* Advanced Receive Descriptor (Read) Format
+ /* Receive Descriptor Formats
+ *
+ * 82598 Advanced Receive Descriptor (Read) Format
* 63 1 0
* +-----------------------------------------------------+
* 0 | Packet Buffer Address [63:1] |A0/NSE|
@@ -431,17 +457,40 @@ rx_ring_summary:
* +-----------------------------------------------------+
*
*
- * Advanced Receive Descriptor (Write-Back) Format
+ * 82598 Advanced Receive Descriptor (Write-Back) Format
*
* 63 48 47 32 31 30 21 20 16 15 4 3 0
* +------------------------------------------------------+
- * 0 | Packet IP |SPH| HDR_LEN | RSV|Packet| RSS |
- * | Checksum Ident | | | | Type | Type |
+ * 0 | RSS Hash / |SPH| HDR_LEN | RSV |Packet| RSS |
+ * | Packet | IP | | | | Type | Type |
+ * | Checksum | Ident | | | | | |
* +------------------------------------------------------+
* 8 | VLAN Tag | Length | Extended Error | Extended Status |
* +------------------------------------------------------+
* 63 48 47 32 31 20 19 0
+ *
+ * 82599+ Advanced Receive Descriptor (Read) Format
+ * 63 1 0
+ * +-----------------------------------------------------+
+ * 0 | Packet Buffer Address [63:1] |A0/NSE|
+ * +----------------------------------------------+------+
+ * 8 | Header Buffer Address [63:1] | DD |
+ * +-----------------------------------------------------+
+ *
+ *
+ * 82599+ Advanced Receive Descriptor (Write-Back) Format
+ *
+ * 63 48 47 32 31 30 21 20 17 16 4 3 0
+ * +------------------------------------------------------+
+ * 0 |RSS / Frag Checksum|SPH| HDR_LEN |RSC- |Packet| RSS |
+ * |/ RTT / PCoE_PARAM | | | CNT | Type | Type |
+ * |/ Flow Dir Flt ID | | | | | |
+ * +------------------------------------------------------+
+ * 8 | VLAN Tag | Length |Extended Error| Xtnd Status/NEXTP |
+ * +------------------------------------------------------+
+ * 63 48 47 32 31 20 19 0
*/
+
for (n = 0; n < adapter->num_rx_queues; n++) {
rx_ring = adapter->rx_ring[n];
pr_info("------------------------------------\n");
--
1.7.11.7
^ permalink raw reply related
* [net-next 06/13] ixgbe: Do not decrement budget in ixgbe_clean_rx_irq
From: Jeff Kirsher @ 2012-10-30 7:04 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, sassmann, Jeff Kirsher
In-Reply-To: <1351580670-8292-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
This change makes it so that compare the total_rx_packets cleaned to budget
instead of decrementing budget. The advantage to this approach is that budget
can now be const and we only end up modifying total_rx_packets instead of
modifying both it and budget.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 9 ++++-----
1 file changed, 4 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index ceab142..a34ee7d 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -1794,7 +1794,7 @@ dma_sync:
**/
static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
struct ixgbe_ring *rx_ring,
- int budget)
+ const int budget)
{
unsigned int total_rx_bytes = 0, total_rx_packets = 0;
#ifdef IXGBE_FCOE
@@ -1845,7 +1845,6 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
/* probably a little skewed due to removing CRC */
total_rx_bytes += skb->len;
- total_rx_packets++;
/* populate checksum, timestamp, VLAN, and protocol */
ixgbe_process_skb_fields(rx_ring, rx_desc, skb);
@@ -1878,8 +1877,8 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
ixgbe_rx_skb(q_vector, skb);
/* update budget accounting */
- budget--;
- } while (likely(budget));
+ total_rx_packets++;
+ } while (likely(total_rx_packets < budget));
u64_stats_update_begin(&rx_ring->syncp);
rx_ring->stats.packets += total_rx_packets;
@@ -1891,7 +1890,7 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
if (cleaned_count)
ixgbe_alloc_rx_buffers(rx_ring, cleaned_count);
- return !!budget;
+ return (total_rx_packets < budget);
}
/**
--
1.7.11.7
^ permalink raw reply related
* [net-next 08/13] ixgbe: reduce PTP rx path overhead
From: Jeff Kirsher @ 2012-10-30 7:04 UTC (permalink / raw)
To: davem; +Cc: Jiri Benc, netdev, gospo, sassmann, Jeff Kirsher
In-Reply-To: <1351580670-8292-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Jiri Benc <jbenc@redhat.com>
Hw timestamping code caused performance regression in ixgbe driver when the
timestamping is not enabled. The culprit is IXGBE_READ_REG call in the Rx
path which is executed for every received skb. This call is not needed when
the timestamping is disabled or for non-ptp packets.
netperf results:
The ixgbe side of the connection was acting as a server, the netperf command
line on the other side was:
netperf -H 192.168.1.23 -T0,0 -t UDP_STREAM -l 20
The values below mean throughput as reported by netperf (local/remote), for
3 runs, with timestamping not enabled.
3.7.0-rc1+ with CONFIG_IXGBE_PTP off:
5373.83 / 3329.32
5721.88 / 3033.89
5653.42 / 3112.38
3.7.0-rc1+ with CONFIG_IXGBE_PTP on:
5233.64 / 1226.85
5448.67 / 1039.32
5421.36 / 1095.66
Patched 3.7.0-rc1+ with CONFIG_IXGBE_PTP on:
5594.72 / 2942.53
5428.95 / 3110.16
5343.56 / 3200.48
Reported-by: Jesper Brouer <jbrouer@redhat.com>
Signed-off-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: Andy Gospodarek <gospo@redhat.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
index 5e71ddb..842ba15 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
@@ -554,12 +554,14 @@ void ixgbe_ptp_rx_hwtstamp(struct ixgbe_q_vector *q_vector,
adapter = q_vector->adapter;
hw = &adapter->hw;
+ if (likely(!ixgbe_ptp_match(skb, adapter->rx_hwtstamp_filter)))
+ return;
+
tsyncrxctl = IXGBE_READ_REG(hw, IXGBE_TSYNCRXCTL);
/* Check if we have a valid timestamp and make sure the skb should
* have been timestamped */
- if (likely(!(tsyncrxctl & IXGBE_TSYNCRXCTL_VALID) ||
- !ixgbe_ptp_match(skb, adapter->rx_hwtstamp_filter)))
+ if (!(tsyncrxctl & IXGBE_TSYNCRXCTL_VALID))
return;
/*
--
1.7.11.7
^ permalink raw reply related
* [net-next 11/13] igb: Enable auto-crossover during forced operation on 82580 and above.
From: Jeff Kirsher @ 2012-10-30 7:04 UTC (permalink / raw)
To: davem; +Cc: Matthew Vick, netdev, gospo, sassmann, Jeff Kirsher
In-Reply-To: <1351580670-8292-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Matthew Vick <matthew.vick@intel.com>
Newer devices supported by igb can support auto-crossover detection in
forced operation modes. Enable this in the driver, rather than clobbering
this functionality in forced operation.
Signed-off-by: Matthew Vick <matthew.vick@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/igb/e1000_mac.c | 4 ++++
drivers/net/ethernet/intel/igb/e1000_phy.c | 29 +++++++++++++++++------------
2 files changed, 21 insertions(+), 12 deletions(-)
diff --git a/drivers/net/ethernet/intel/igb/e1000_mac.c b/drivers/net/ethernet/intel/igb/e1000_mac.c
index 819c145..7acddfe 100644
--- a/drivers/net/ethernet/intel/igb/e1000_mac.c
+++ b/drivers/net/ethernet/intel/igb/e1000_mac.c
@@ -1391,6 +1391,10 @@ s32 igb_validate_mdi_setting(struct e1000_hw *hw)
{
s32 ret_val = 0;
+ /* All MDI settings are supported on 82580 and newer. */
+ if (hw->mac.type >= e1000_82580)
+ goto out;
+
if (!hw->mac.autoneg && (hw->phy.mdix == 0 || hw->phy.mdix == 3)) {
hw_dbg("Invalid MDI setting detected\n");
hw->phy.mdix = 1;
diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.c b/drivers/net/ethernet/intel/igb/e1000_phy.c
index c62a4c3..fe76004 100644
--- a/drivers/net/ethernet/intel/igb/e1000_phy.c
+++ b/drivers/net/ethernet/intel/igb/e1000_phy.c
@@ -1207,20 +1207,25 @@ s32 igb_phy_force_speed_duplex_m88(struct e1000_hw *hw)
u16 phy_data;
bool link;
- /*
- * Clear Auto-Crossover to force MDI manually. M88E1000 requires MDI
- * forced whenever speed and duplex are forced.
- */
- ret_val = phy->ops.read_reg(hw, M88E1000_PHY_SPEC_CTRL, &phy_data);
- if (ret_val)
- goto out;
+ /* I210 and I211 devices support Auto-Crossover in forced operation. */
+ if (phy->type != e1000_phy_i210) {
+ /*
+ * Clear Auto-Crossover to force MDI manually. M88E1000
+ * requires MDI forced whenever speed and duplex are forced.
+ */
+ ret_val = phy->ops.read_reg(hw, M88E1000_PHY_SPEC_CTRL,
+ &phy_data);
+ if (ret_val)
+ goto out;
- phy_data &= ~M88E1000_PSCR_AUTO_X_MODE;
- ret_val = phy->ops.write_reg(hw, M88E1000_PHY_SPEC_CTRL, phy_data);
- if (ret_val)
- goto out;
+ phy_data &= ~M88E1000_PSCR_AUTO_X_MODE;
+ ret_val = phy->ops.write_reg(hw, M88E1000_PHY_SPEC_CTRL,
+ phy_data);
+ if (ret_val)
+ goto out;
- hw_dbg("M88E1000 PSCR: %X\n", phy_data);
+ hw_dbg("M88E1000 PSCR: %X\n", phy_data);
+ }
ret_val = phy->ops.read_reg(hw, PHY_CONTROL, &phy_data);
if (ret_val)
--
1.7.11.7
^ permalink raw reply related
* [net-next 09/13] ixgbevf: Do not forward LLDP type frames
From: Jeff Kirsher @ 2012-10-30 7:04 UTC (permalink / raw)
To: davem; +Cc: Greg Rose, netdev, gospo, sassmann, Jeff Kirsher
In-Reply-To: <1351580670-8292-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Greg Rose <gregory.v.rose@intel.com>
The driver should not forward LLDP type frames. Inspect the ether type and
do not send if it is an LLDP ethertype frame.
Signed-off-by: Greg Rose <gregory.v.rose@intel.com>
Tested-by: Sibai Li <sibai.li@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 07d7eab..b5979ba 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -2968,6 +2968,11 @@ static int ixgbevf_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
#if PAGE_SIZE > IXGBE_MAX_DATA_PER_TXD
unsigned short f;
#endif
+ u8 *dst_mac = skb_header_pointer(skb, 0, 0, NULL);
+ if (!dst_mac || is_link_local(dst_mac)) {
+ dev_kfree_skb(skb);
+ return NETDEV_TX_OK;
+ }
tx_ring = &adapter->tx_ring[r_idx];
--
1.7.11.7
^ permalink raw reply related
* [net-next 10/13] igbvf: Check for error on dma_map_single call
From: Jeff Kirsher @ 2012-10-30 7:04 UTC (permalink / raw)
To: davem; +Cc: Greg Rose, netdev, gospo, sassmann, Jeff Kirsher
In-Reply-To: <1351580670-8292-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Greg Rose <gregory.v.rose@intel.com>
Ignoring the return value from a call to the kernel dma_map API functions
can cause data corruption and system instability. Check the return value
and take appropriate action.
Signed-off-by: Greg Rose <gregory.v.rose@intel.com>
Tested-by: Sibai Li <sibai.li@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/igbvf/netdev.c | 13 +++++++++++++
1 file changed, 13 insertions(+)
diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c
index 0ac11f5..4051ec4 100644
--- a/drivers/net/ethernet/intel/igbvf/netdev.c
+++ b/drivers/net/ethernet/intel/igbvf/netdev.c
@@ -184,6 +184,13 @@ static void igbvf_alloc_rx_buffers(struct igbvf_ring *rx_ring,
buffer_info->page_offset,
PAGE_SIZE / 2,
DMA_FROM_DEVICE);
+ if (dma_mapping_error(&pdev->dev,
+ buffer_info->page_dma)) {
+ __free_page(buffer_info->page);
+ buffer_info->page = NULL;
+ dev_err(&pdev->dev, "RX DMA map failed\n");
+ break;
+ }
}
if (!buffer_info->skb) {
@@ -197,6 +204,12 @@ static void igbvf_alloc_rx_buffers(struct igbvf_ring *rx_ring,
buffer_info->dma = dma_map_single(&pdev->dev, skb->data,
bufsz,
DMA_FROM_DEVICE);
+ if (dma_mapping_error(&pdev->dev, buffer_info->dma)) {
+ dev_kfree_skb(buffer_info->skb);
+ buffer_info->skb = NULL;
+ dev_err(&pdev->dev, "RX DMA map failed\n");
+ goto no_buffers;
+ }
}
/* Refresh the desc even if buffer_addrs didn't change because
* each write-back erases this info. */
--
1.7.11.7
^ permalink raw reply related
* [net-next 12/13] igb: Update firmware version info for ethtool output.
From: Jeff Kirsher @ 2012-10-30 7:04 UTC (permalink / raw)
To: davem; +Cc: Carolyn Wyborny, netdev, gospo, sassmann, Jeff Kirsher
In-Reply-To: <1351580670-8292-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Carolyn Wyborny <carolyn.wyborny@intel.com>
There are multiple places in our device nvm where the version is stored.
This update fixes some output errors with some types of images and
refactors the way the version data is gathered and stored for ethtool output.
Signed-off-by: Carolyn Wyborny <carolyn.wyborny@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/igb/e1000_defines.h | 14 +++++
drivers/net/ethernet/intel/igb/e1000_nvm.c | 70 ++++++++++++++++++++++++
drivers/net/ethernet/intel/igb/e1000_nvm.h | 16 ++++++
drivers/net/ethernet/intel/igb/igb_main.c | 76 +++++++++-----------------
4 files changed, 126 insertions(+), 50 deletions(-)
diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h
index de4b41e..e647cff 100644
--- a/drivers/net/ethernet/intel/igb/e1000_defines.h
+++ b/drivers/net/ethernet/intel/igb/e1000_defines.h
@@ -636,6 +636,7 @@
/* NVM Word Offsets */
#define NVM_COMPAT 0x0003
#define NVM_ID_LED_SETTINGS 0x0004 /* SERDES output amplitude */
+#define NVM_VERSION 0x0005
#define NVM_INIT_CONTROL2_REG 0x000F
#define NVM_INIT_CONTROL3_PORT_B 0x0014
#define NVM_INIT_CONTROL3_PORT_A 0x0024
@@ -653,6 +654,19 @@
#define NVM_LED_1_CFG 0x001C
#define NVM_LED_0_2_CFG 0x001F
+/* NVM version defines */
+#define NVM_ETRACK_WORD 0x0042
+#define NVM_COMB_VER_OFF 0x0083
+#define NVM_COMB_VER_PTR 0x003d
+#define NVM_MAJOR_MASK 0xF000
+#define NVM_MINOR_MASK 0x0FF0
+#define NVM_BUILD_MASK 0x000F
+#define NVM_COMB_VER_MASK 0x00FF
+#define NVM_MAJOR_SHIFT 12
+#define NVM_MINOR_SHIFT 4
+#define NVM_COMB_VER_SHFT 8
+#define NVM_VER_INVALID 0xFFFF
+#define NVM_ETRACK_SHIFT 16
#define E1000_NVM_CFG_DONE_PORT_0 0x040000 /* MNG config cycle done */
#define E1000_NVM_CFG_DONE_PORT_1 0x080000 /* ...for second port */
diff --git a/drivers/net/ethernet/intel/igb/e1000_nvm.c b/drivers/net/ethernet/intel/igb/e1000_nvm.c
index aa5fcdf..54ff539 100644
--- a/drivers/net/ethernet/intel/igb/e1000_nvm.c
+++ b/drivers/net/ethernet/intel/igb/e1000_nvm.c
@@ -710,3 +710,73 @@ s32 igb_update_nvm_checksum(struct e1000_hw *hw)
out:
return ret_val;
}
+
+/**
+ * igb_get_fw_version - Get firmware version information
+ * @hw: pointer to the HW structure
+ * @fw_vers: pointer to output structure
+ *
+ * unsupported MAC types will return all 0 version structure
+ **/
+void igb_get_fw_version(struct e1000_hw *hw, struct e1000_fw_version *fw_vers)
+{
+ u16 eeprom_verh, eeprom_verl, comb_verh, comb_verl, comb_offset;
+ u16 fw_version;
+
+ memset(fw_vers, 0, sizeof(struct e1000_fw_version));
+
+ switch (hw->mac.type) {
+ case e1000_i211:
+ return;
+ case e1000_82575:
+ case e1000_82576:
+ case e1000_82580:
+ case e1000_i350:
+ case e1000_i210:
+ break;
+ default:
+ return;
+ }
+ /* basic eeprom version numbers */
+ hw->nvm.ops.read(hw, NVM_VERSION, 1, &fw_version);
+ fw_vers->eep_major = (fw_version & NVM_MAJOR_MASK) >> NVM_MAJOR_SHIFT;
+ fw_vers->eep_minor = (fw_version & NVM_MINOR_MASK);
+
+ /* etrack id */
+ hw->nvm.ops.read(hw, NVM_ETRACK_WORD, 1, &eeprom_verl);
+ hw->nvm.ops.read(hw, (NVM_ETRACK_WORD + 1), 1, &eeprom_verh);
+ fw_vers->etrack_id = (eeprom_verh << NVM_ETRACK_SHIFT) | eeprom_verl;
+
+ switch (hw->mac.type) {
+ case e1000_i210:
+ case e1000_i350:
+ /* find combo image version */
+ hw->nvm.ops.read(hw, NVM_COMB_VER_PTR, 1, &comb_offset);
+ if ((comb_offset != 0x0) && (comb_offset != NVM_VER_INVALID)) {
+
+ hw->nvm.ops.read(hw, (NVM_COMB_VER_OFF + comb_offset
+ + 1), 1, &comb_verh);
+ hw->nvm.ops.read(hw, (NVM_COMB_VER_OFF + comb_offset),
+ 1, &comb_verl);
+
+ /* get Option Rom version if it exists and is valid */
+ if ((comb_verh && comb_verl) &&
+ ((comb_verh != NVM_VER_INVALID) &&
+ (comb_verl != NVM_VER_INVALID))) {
+
+ fw_vers->or_valid = true;
+ fw_vers->or_major =
+ comb_verl >> NVM_COMB_VER_SHFT;
+ fw_vers->or_build =
+ ((comb_verl << NVM_COMB_VER_SHFT)
+ | (comb_verh >> NVM_COMB_VER_SHFT));
+ fw_vers->or_patch =
+ comb_verh & NVM_COMB_VER_MASK;
+ }
+ }
+ break;
+ default:
+ break;
+ }
+ return;
+}
diff --git a/drivers/net/ethernet/intel/igb/e1000_nvm.h b/drivers/net/ethernet/intel/igb/e1000_nvm.h
index 825b022..7012d45 100644
--- a/drivers/net/ethernet/intel/igb/e1000_nvm.h
+++ b/drivers/net/ethernet/intel/igb/e1000_nvm.h
@@ -40,4 +40,20 @@ s32 igb_write_nvm_spi(struct e1000_hw *hw, u16 offset, u16 words, u16 *data);
s32 igb_validate_nvm_checksum(struct e1000_hw *hw);
s32 igb_update_nvm_checksum(struct e1000_hw *hw);
+struct e1000_fw_version {
+ u32 etrack_id;
+ u16 eep_major;
+ u16 eep_minor;
+
+ u8 invm_major;
+ u8 invm_minor;
+ u8 invm_img_type;
+
+ bool or_valid;
+ u16 or_major;
+ u16 or_build;
+ u16 or_patch;
+};
+void igb_get_fw_version(struct e1000_hw *hw, struct e1000_fw_version *fw_vers);
+
#endif
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index b07d679..df1e790 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -1785,58 +1785,34 @@ static const struct net_device_ops igb_netdev_ops = {
void igb_set_fw_version(struct igb_adapter *adapter)
{
struct e1000_hw *hw = &adapter->hw;
- u16 eeprom_verh, eeprom_verl, comb_verh, comb_verl, comb_offset;
- u16 major, build, patch, fw_version;
- u32 etrack_id;
-
- hw->nvm.ops.read(hw, 5, 1, &fw_version);
- if (adapter->hw.mac.type != e1000_i211) {
- hw->nvm.ops.read(hw, NVM_ETRACK_WORD, 1, &eeprom_verh);
- hw->nvm.ops.read(hw, (NVM_ETRACK_WORD + 1), 1, &eeprom_verl);
- etrack_id = (eeprom_verh << IGB_ETRACK_SHIFT) | eeprom_verl;
-
- /* combo image version needs to be found */
- hw->nvm.ops.read(hw, NVM_COMB_VER_PTR, 1, &comb_offset);
- if ((comb_offset != 0x0) &&
- (comb_offset != IGB_NVM_VER_INVALID)) {
- hw->nvm.ops.read(hw, (NVM_COMB_VER_OFF + comb_offset
- + 1), 1, &comb_verh);
- hw->nvm.ops.read(hw, (NVM_COMB_VER_OFF + comb_offset),
- 1, &comb_verl);
-
- /* Only display Option Rom if it exists and is valid */
- if ((comb_verh && comb_verl) &&
- ((comb_verh != IGB_NVM_VER_INVALID) &&
- (comb_verl != IGB_NVM_VER_INVALID))) {
- major = comb_verl >> IGB_COMB_VER_SHFT;
- build = (comb_verl << IGB_COMB_VER_SHFT) |
- (comb_verh >> IGB_COMB_VER_SHFT);
- patch = comb_verh & IGB_COMB_VER_MASK;
- snprintf(adapter->fw_version,
- sizeof(adapter->fw_version),
- "%d.%d%d, 0x%08x, %d.%d.%d",
- (fw_version & IGB_MAJOR_MASK) >>
- IGB_MAJOR_SHIFT,
- (fw_version & IGB_MINOR_MASK) >>
- IGB_MINOR_SHIFT,
- (fw_version & IGB_BUILD_MASK),
- etrack_id, major, build, patch);
- goto out;
- }
- }
- snprintf(adapter->fw_version, sizeof(adapter->fw_version),
- "%d.%d%d, 0x%08x",
- (fw_version & IGB_MAJOR_MASK) >> IGB_MAJOR_SHIFT,
- (fw_version & IGB_MINOR_MASK) >> IGB_MINOR_SHIFT,
- (fw_version & IGB_BUILD_MASK), etrack_id);
- } else {
+ struct e1000_fw_version fw;
+
+ igb_get_fw_version(hw, &fw);
+
+ switch (hw->mac.type) {
+ case e1000_i211:
snprintf(adapter->fw_version, sizeof(adapter->fw_version),
- "%d.%d%d",
- (fw_version & IGB_MAJOR_MASK) >> IGB_MAJOR_SHIFT,
- (fw_version & IGB_MINOR_MASK) >> IGB_MINOR_SHIFT,
- (fw_version & IGB_BUILD_MASK));
+ "%2d.%2d-%d",
+ fw.invm_major, fw.invm_minor, fw.invm_img_type);
+ break;
+
+ default:
+ /* if option is rom valid, display its version too */
+ if (fw.or_valid) {
+ snprintf(adapter->fw_version,
+ sizeof(adapter->fw_version),
+ "%d.%d, 0x%08x, %d.%d.%d",
+ fw.eep_major, fw.eep_minor, fw.etrack_id,
+ fw.or_major, fw.or_build, fw.or_patch);
+ /* no option rom */
+ } else {
+ snprintf(adapter->fw_version,
+ sizeof(adapter->fw_version),
+ "%d.%d, 0x%08x",
+ fw.eep_major, fw.eep_minor, fw.etrack_id);
+ }
+ break;
}
-out:
return;
}
--
1.7.11.7
^ permalink raw reply related
* [net-next 13/13] igb: Fix sparse warning in igb_ptp_rx_pktstamp
From: Jeff Kirsher @ 2012-10-30 7:04 UTC (permalink / raw)
To: davem; +Cc: Alexander Duyck, netdev, gospo, sassmann, Jeff Kirsher
In-Reply-To: <1351580670-8292-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Alexander Duyck <alexander.h.duyck@intel.com>
This change fixes a sparse warning triggered by us casting the timestamp in
the packet as a u64 instead of as a __le64. This change corrects that in
order to resolve the sparse warning.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/igb/igb_ptp.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c
index a7db4ce..aa10f69 100644
--- a/drivers/net/ethernet/intel/igb/igb_ptp.c
+++ b/drivers/net/ethernet/intel/igb/igb_ptp.c
@@ -455,7 +455,7 @@ void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector,
unsigned char *va,
struct sk_buff *skb)
{
- u64 *regval = (u64 *)va;
+ __le64 *regval = (__le64 *)va;
/*
* The timestamp is recorded in little endian format.
--
1.7.11.7
^ permalink raw reply related
* [net-next 00/13][pull request] Intel Wired LAN Driver Updates
From: Jeff Kirsher @ 2012-10-30 7:04 UTC (permalink / raw)
To: davem; +Cc: Jeff Kirsher, netdev, gospo, sassmann
This series contains updates to ixgbe, ixgbevf, igbvf, igb and
networking core (bridge). Most notably is the addition of support
for local link multicast addresses in SR-IOV mode to the networking
core.
Also note, the ixgbe patch "ixgbe: Add support for pipeline reset" and
"ixgbe: Fix return value from macvlan filter function" is revised based
on community feedback.
The following are changes since commit a932657f51eadb8280166e82dc7034dfbff3985a:
net: sierra: shut up sparse restricted type warnings
and are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-next master
Alexander Duyck (2):
ixgbe: Do not decrement budget in ixgbe_clean_rx_irq
igb: Fix sparse warning in igb_ptp_rx_pktstamp
Carolyn Wyborny (1):
igb: Update firmware version info for ethtool output.
Don Skidmore (1):
ixgbe: Add support for pipeline reset
Emil Tantilov (1):
ixgbe: clean up the condition for turning on/off the laser
Greg Rose (4):
ixgbe: Fix return value from macvlan filter function
ixgbe: Return success or failure on VF MAC filter set
ixgbevf: Do not forward LLDP type frames
igbvf: Check for error on dma_map_single call
Jiri Benc (1):
ixgbe: reduce PTP rx path overhead
John Fastabend (1):
net, ixgbe: handle link local multicast addresses in SR-IOV mode
Josh Hay (1):
ixgbe: add/update descriptor maps in comments
Matthew Vick (1):
igb: Enable auto-crossover during forced operation on 82580 and
above.
drivers/net/ethernet/intel/igb/e1000_defines.h | 14 +++
drivers/net/ethernet/intel/igb/e1000_mac.c | 4 +
drivers/net/ethernet/intel/igb/e1000_nvm.c | 70 +++++++++++++
drivers/net/ethernet/intel/igb/e1000_nvm.h | 16 +++
drivers/net/ethernet/intel/igb/e1000_phy.c | 29 +++---
drivers/net/ethernet/intel/igb/igb_main.c | 76 +++++----------
drivers/net/ethernet/intel/igb/igb_ptp.c | 2 +-
drivers/net/ethernet/intel/igbvf/netdev.c | 13 +++
drivers/net/ethernet/intel/ixgbe/ixgbe.h | 1 +
drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c | 114 ++++++++++++++++------
drivers/net/ethernet/intel/ixgbe/ixgbe_common.c | 70 ++++++++++++-
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 103 ++++++++++++-------
drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c | 6 +-
drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c | 5 +-
drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c | 5 +
drivers/net/ethernet/intel/ixgbevf/vf.c | 3 +
include/linux/etherdevice.h | 19 ++++
net/bridge/br_device.c | 2 +-
net/bridge/br_input.c | 15 ---
net/bridge/br_private.h | 1 -
net/bridge/br_sysfs_br.c | 3 +-
21 files changed, 419 insertions(+), 152 deletions(-)
--
1.7.11.7
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox