* Re: [PATCH v6] net: ip, diag -- Add diag interface for raw sockets
From: David Miller @ 2016-10-12 23:55 UTC (permalink / raw)
To: gorcunov
Cc: netdev, eric.dumazet, jhs, dsa, linux-kernel, kuznet, jmorris,
yoshfuji, kaber, avagin, stephen
In-Reply-To: <20161012065329.GH1941@uranus.lan>
From: Cyrill Gorcunov <gorcunov@gmail.com>
Date: Wed, 12 Oct 2016 09:53:29 +0300
> I can't rename the field, neither a can use union.
Remind me again what is wrong with using an anonymous union?
^ permalink raw reply
* [PATCH net-next 5/5] fou: Support flow dissection
From: Tom Herbert @ 2016-10-12 23:25 UTC (permalink / raw)
To: davem, netdev; +Cc: kernel-team
In-Reply-To: <20161012232547.2383961-1-tom@herbertland.com>
This patch performs flow dissection for GUE and FOU. This is an
optional feature on the receiver and is set by FOU_ATTR_DEEP_HASH
netlink configuration. When enable the UDP socket flow_dissect
function is set to fou_flow_dissect or gue_flow_dissect as
appropriate. These functions return FLOW_DIS_RET_IPPROTO and
set ip protocol argument. In the case of GUE the header is
parsed to find the protocol number.
Signed-off-by: Tom Herbert <tom@herbertland.com>
---
include/uapi/linux/fou.h | 1 +
net/ipv4/fou.c | 68 +++++++++++++++++++++++++++++++++++++++++++++++-
2 files changed, 68 insertions(+), 1 deletion(-)
diff --git a/include/uapi/linux/fou.h b/include/uapi/linux/fou.h
index d2947c5..2c837eb 100644
--- a/include/uapi/linux/fou.h
+++ b/include/uapi/linux/fou.h
@@ -15,6 +15,7 @@ enum {
FOU_ATTR_IPPROTO, /* u8 */
FOU_ATTR_TYPE, /* u8 */
FOU_ATTR_REMCSUM_NOPARTIAL, /* flag */
+ FOU_ATTR_DEEP_HASH, /* flag */
__FOU_ATTR_MAX,
};
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index cf50f7e..95ac5a8 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -27,7 +27,8 @@ struct fou {
struct rcu_head rcu;
};
-#define FOU_F_REMCSUM_NOPARTIAL BIT(0)
+#define FOU_F_REMCSUM_NOPARTIAL BIT(0)
+#define FOU_F_DEEP_HASH BIT(1)
struct fou_cfg {
u16 type;
@@ -281,6 +282,16 @@ static int fou_gro_complete(struct sock *sk, struct sk_buff *skb,
return err;
}
+static int fou_flow_dissect(struct sock *sk, const struct sk_buff *skb,
+ void *data, int hlen, int *nhoff, u8 *ip_proto,
+ __be16 *proto)
+{
+ *ip_proto = fou_from_sock(sk)->protocol;
+ *nhoff += sizeof(struct udphdr);
+
+ return FLOW_DIS_RET_IPPROTO;
+}
+
static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off,
struct guehdr *guehdr, void *data,
size_t hdrlen, struct gro_remcsum *grc,
@@ -498,6 +509,48 @@ static int gue_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff)
return err;
}
+static int gue_flow_dissect(struct sock *sk, const struct sk_buff *skb,
+ void *data, int hlen, int *nhoff, u8 *ip_proto,
+ __be16 *proto)
+{
+ struct guehdr _hdr, *hdr;
+
+ hdr = __skb_header_pointer(skb, *nhoff + sizeof(struct udphdr),
+ sizeof(_hdr), data, hlen, &_hdr);
+ if (!hdr)
+ return FLOW_DIS_RET_BAD;
+
+ switch (hdr->version) {
+ case 0: /* Full GUE header present */
+ if (hdr->control)
+ return FLOW_DIS_RET_PASS;
+
+ *nhoff += sizeof(struct udphdr) + sizeof(_hdr) +
+ (hdr->hlen << 2);
+ *ip_proto = hdr->proto_ctype;
+
+ return FLOW_DIS_RET_IPPROTO;
+ case 1:
+ /* Direct encasulation of IPv4 or IPv6 */
+
+ switch (((struct iphdr *)hdr)->version) {
+ case 4:
+ *nhoff += sizeof(struct udphdr);
+ *ip_proto = IPPROTO_IPIP;
+ return FLOW_DIS_RET_IPPROTO;
+ case 6:
+ *nhoff += sizeof(struct udphdr);
+ *ip_proto = IPPROTO_IPV6;
+ return FLOW_DIS_RET_IPPROTO;
+ default:
+ return FLOW_DIS_RET_PASS;
+ }
+
+ default:
+ return FLOW_DIS_RET_PASS;
+ }
+}
+
static int fou_add_to_port_list(struct net *net, struct fou *fou)
{
struct fou_net *fn = net_generic(net, fou_net_id);
@@ -568,12 +621,16 @@ static int fou_create(struct net *net, struct fou_cfg *cfg,
tunnel_cfg.encap_rcv = fou_udp_recv;
tunnel_cfg.gro_receive = fou_gro_receive;
tunnel_cfg.gro_complete = fou_gro_complete;
+ if (cfg->flags & FOU_F_DEEP_HASH)
+ tunnel_cfg.flow_dissect = fou_flow_dissect;
fou->protocol = cfg->protocol;
break;
case FOU_ENCAP_GUE:
tunnel_cfg.encap_rcv = gue_udp_recv;
tunnel_cfg.gro_receive = gue_gro_receive;
tunnel_cfg.gro_complete = gue_gro_complete;
+ if (cfg->flags & FOU_F_DEEP_HASH)
+ tunnel_cfg.flow_dissect = gue_flow_dissect;
break;
default:
err = -EINVAL;
@@ -637,6 +694,7 @@ static const struct nla_policy fou_nl_policy[FOU_ATTR_MAX + 1] = {
[FOU_ATTR_IPPROTO] = { .type = NLA_U8, },
[FOU_ATTR_TYPE] = { .type = NLA_U8, },
[FOU_ATTR_REMCSUM_NOPARTIAL] = { .type = NLA_FLAG, },
+ [FOU_ATTR_DEEP_HASH] = { .type = NLA_FLAG },
};
static int parse_nl_config(struct genl_info *info,
@@ -677,6 +735,9 @@ static int parse_nl_config(struct genl_info *info,
if (info->attrs[FOU_ATTR_REMCSUM_NOPARTIAL])
cfg->flags |= FOU_F_REMCSUM_NOPARTIAL;
+ if (info->attrs[FOU_ATTR_DEEP_HASH])
+ cfg->flags |= FOU_F_DEEP_HASH;
+
return 0;
}
@@ -717,6 +778,11 @@ static int fou_fill_info(struct fou *fou, struct sk_buff *msg)
if (fou->flags & FOU_F_REMCSUM_NOPARTIAL)
if (nla_put_flag(msg, FOU_ATTR_REMCSUM_NOPARTIAL))
return -1;
+
+ if (fou->flags & FOU_F_DEEP_HASH)
+ if (nla_put_flag(msg, FOU_ATTR_DEEP_HASH))
+ return -1;
+
return 0;
}
--
2.9.3
^ permalink raw reply related
* [PATCH net-next 4/5] udp: UDP tunnel flow dissection infrastructure
From: Tom Herbert @ 2016-10-12 23:25 UTC (permalink / raw)
To: davem, netdev; +Cc: kernel-team
In-Reply-To: <20161012232547.2383961-1-tom@herbertland.com>
Add infrastructure to allow UDP tunnels to setup flow dissection.
Signed-off-by: Tom Herbert <tom@herbertland.com>
---
include/net/udp_tunnel.h | 5 +++++
net/ipv4/udp_tunnel.c | 5 +++++
2 files changed, 10 insertions(+)
diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index 02c5be0..81d2584 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -69,6 +69,10 @@ typedef struct sk_buff **(*udp_tunnel_gro_receive_t)(struct sock *sk,
struct sk_buff *skb);
typedef int (*udp_tunnel_gro_complete_t)(struct sock *sk, struct sk_buff *skb,
int nhoff);
+typedef int (*udp_tunnel_flow_dissect_t)(struct sock *sk,
+ const struct sk_buff *skb,
+ void *data, int hlen, int *nhoff,
+ u8 *ip_proto, __be16 *proto);
struct udp_tunnel_sock_cfg {
void *sk_user_data; /* user data used by encap_rcv call back */
@@ -78,6 +82,7 @@ struct udp_tunnel_sock_cfg {
udp_tunnel_encap_destroy_t encap_destroy;
udp_tunnel_gro_receive_t gro_receive;
udp_tunnel_gro_complete_t gro_complete;
+ udp_tunnel_flow_dissect_t flow_dissect;
};
/* Setup the given (UDP) sock to receive UDP encapsulated packets */
diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c
index 58bd39f..4459288 100644
--- a/net/ipv4/udp_tunnel.c
+++ b/net/ipv4/udp_tunnel.c
@@ -72,6 +72,11 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
udp_sk(sk)->gro_receive = cfg->gro_receive;
udp_sk(sk)->gro_complete = cfg->gro_complete;
+ if (cfg->flow_dissect) {
+ udp_sk(sk)->flow_dissect = cfg->flow_dissect;
+ udp_flow_dissect_enable();
+ }
+
udp_tunnel_encap_enable(sock);
}
EXPORT_SYMBOL_GPL(setup_udp_tunnel_sock);
--
2.9.3
^ permalink raw reply related
* [PATCH net-next 3/5] udp: Add UDP flow dissection functions to IPv4 and IPv6
From: Tom Herbert @ 2016-10-12 23:25 UTC (permalink / raw)
To: davem, netdev; +Cc: kernel-team
In-Reply-To: <20161012232547.2383961-1-tom@herbertland.com>
Add per protocol offload callbacks for flow_dissect to UDP for
IPv4 and IPv6. The callback functions extract the port number
information and with the packet addresses (given in an argument with
type flow_dissector_key_addrs) it performs a lookup on the UDP
socket. If a socket is found and flow_dissect is set for the
socket then that function is called.
Signed-off-by: Tom Herbert <tom@herbertland.com>
---
net/ipv4/udp_offload.c | 39 +++++++++++++++++++++++++++++++++++++++
net/ipv6/udp_offload.c | 38 ++++++++++++++++++++++++++++++++++++++
2 files changed, 77 insertions(+)
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index f9333c9..c7753ba 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -377,11 +377,50 @@ static int udp4_gro_complete(struct sk_buff *skb, int nhoff)
return udp_gro_complete(skb, nhoff, udp4_lib_lookup_skb);
}
+/* Assumes rcu lock is held */
+static int udp4_flow_dissect(const struct sk_buff *skb, void *data, int hlen,
+ int *nhoff, u8 *ip_proto, __be16 *proto,
+ struct flow_dissector_key_addrs *key_addrs)
+{
+ u16 _ports[2], *ports;
+ struct net *net;
+ struct sock *sk;
+ int dif = -1;
+
+ /* See if there is a flow dissector in the UDP socket */
+
+ if (skb->dev) {
+ net = dev_net(skb->dev);
+ dif = skb->dev->ifindex;
+ } else if (skb->sk) {
+ net = sock_net(skb->sk);
+ } else {
+ return FLOW_DIS_RET_PASS;
+ }
+
+ ports = __skb_header_pointer(skb, *nhoff, sizeof(_ports),
+ data, hlen, &_ports);
+ if (!ports)
+ return FLOW_DIS_RET_BAD;
+
+ sk = udp4_lib_lookup_noref(net,
+ key_addrs->v4addrs.src, ports[0],
+ key_addrs->v4addrs.dst, ports[1],
+ dif);
+
+ if (sk && udp_sk(sk)->flow_dissect)
+ return udp_sk(sk)->flow_dissect(sk, skb, data, hlen, nhoff,
+ ip_proto, proto);
+ else
+ return FLOW_DIS_RET_PASS;
+}
+
static const struct net_offload udpv4_offload = {
.callbacks = {
.gso_segment = udp4_ufo_fragment,
.gro_receive = udp4_gro_receive,
.gro_complete = udp4_gro_complete,
+ .flow_dissect = udp4_flow_dissect,
},
};
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index ac858c4..b3f4a6c 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -163,11 +163,49 @@ static int udp6_gro_complete(struct sk_buff *skb, int nhoff)
return udp_gro_complete(skb, nhoff, udp6_lib_lookup_skb);
}
+/* Assumes rcu lock is held */
+static int udp6_flow_dissect(const struct sk_buff *skb, void *data, int hlen,
+ int *nhoff, u8 *ip_proto, __be16 *proto,
+ const struct flow_dissector_key_addrs *key_addrs)
+{
+ u16 _ports[2], *ports;
+ struct net *net;
+ struct sock *sk;
+ int dif = -1;
+
+ /* See if there is a flow dissector in the UDP socket */
+
+ if (skb->dev) {
+ net = dev_net(skb->dev);
+ dif = skb->dev->ifindex;
+ } else if (skb->sk) {
+ net = sock_net(skb->sk);
+ } else {
+ return FLOW_DIS_RET_PASS;
+ }
+
+ ports = __skb_header_pointer(skb, *nhoff, sizeof(_ports),
+ data, hlen, &_ports);
+ if (!ports)
+ return FLOW_DIS_RET_BAD;
+
+ sk = udp6_lib_lookup_noref(net,
+ &key_addrs->v6addrs.src, ports[0],
+ &key_addrs->v6addrs.dst, ports[1],
+ dif);
+
+ if (sk && udp_sk(sk)->flow_dissect)
+ return udp_sk(sk)->flow_dissect(sk, skb, data, hlen, nhoff,
+ ip_proto, proto);
+ return FLOW_DIS_RET_PASS;
+}
+
static const struct net_offload udpv6_offload = {
.callbacks = {
.gso_segment = udp6_ufo_fragment,
.gro_receive = udp6_gro_receive,
.gro_complete = udp6_gro_complete,
+ .flow_dissect = udp6_flow_dissect,
},
};
--
2.9.3
^ permalink raw reply related
* [PATCH net-next 2/5] udp: UDP flow dissector
From: Tom Herbert @ 2016-10-12 23:25 UTC (permalink / raw)
To: davem, netdev; +Cc: kernel-team
In-Reply-To: <20161012232547.2383961-1-tom@herbertland.com>
Add infrastructure for performing per protocol flow dissection and
support flow dissection in UDP payloads (e.g. flow dissection on a
UDP encapsulated tunnel.
The per protocol flow dissector is called by flow_dissect function
in the offload_callbacks of a protocol. The arguments of this function
include the necessary information to do flow dissection as derived
from __skb_flow_dissect which is where the callback is intended to be
called from. There are return codes from the callback in the form
FLOW_DIS_RET_* that indicate the result. FLOW_DIS_RET_IPPROTO
means that the payload should be dissected as an IP proto, the
specific protocol is returned in a pointer argument. Likewise,
FLOW_DIS_RET_PROTO indicate the payload should be processed as
an ethertype which is returned in another argument.
A case for IPPROTO_UDP was added to __skb_flow_dissect. Since
UDP flow dissector involves a relatively expensive socket lookup
there is a static key check first to see if there are any sockets
that have enabled flow dissection. After this check, the offload
ops for UDP for either IPv4 or IPv6 is considered. If the
flow_dissect function is it is called. Upon return the result
is processed (pass, out_bad, process as IP protocol, process
as ethertype). Note that if the result indicates a protocol must
be processed it is expected that nhoff has been updated to the
encapsulated protocol header.
Signed-off-by: Tom Herbert <tom@herbertland.com>
---
include/linux/netdevice.h | 5 +++
include/linux/udp.h | 7 +++++
include/net/flow_dissector.h | 8 +++++
include/net/udp.h | 4 +++
net/core/flow_dissector.c | 73 ++++++++++++++++++++++++++++++++++++++++++--
net/ipv4/udp.c | 3 ++
6 files changed, 98 insertions(+), 2 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 136ae6bb..51b43fb1 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2199,6 +2199,11 @@ struct offload_callbacks {
struct sk_buff **(*gro_receive)(struct sk_buff **head,
struct sk_buff *skb);
int (*gro_complete)(struct sk_buff *skb, int nhoff);
+ int (*flow_dissect)(const struct sk_buff *skb,
+ void *data, int hlen,
+ int *nhoff, u8 *ip_proto,
+ __be16 *proto,
+ struct flow_dissector_key_addrs *key_addrs);
};
struct packet_offload {
diff --git a/include/linux/udp.h b/include/linux/udp.h
index d1fd8cd..608ebf4 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -79,6 +79,13 @@ struct udp_sock {
int (*gro_complete)(struct sock *sk,
struct sk_buff *skb,
int nhoff);
+
+ /* Flow dissector function for UDP socket */
+ int (*flow_dissect)(struct sock *sk,
+ const struct sk_buff *skb,
+ void *data, int hlen,
+ int *nhoff, u8 *ip_proto,
+ __be16 *proto);
};
static inline struct udp_sock *udp_sk(const struct sock *sk)
diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index d953492..9de4904 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -203,4 +203,12 @@ static inline void *skb_flow_dissector_target(struct flow_dissector *flow_dissec
return ((char *)target_container) + flow_dissector->offset[key_id];
}
+/* Return codes from per socket flow dissector (e.g. UDP) */
+enum {
+ FLOW_DIS_RET_PASS = 0,
+ FLOW_DIS_RET_BAD,
+ FLOW_DIS_RET_IPPROTO,
+ FLOW_DIS_RET_PROTO,
+};
+
#endif
diff --git a/include/net/udp.h b/include/net/udp.h
index 717a972..8d364e8 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -360,4 +360,8 @@ void udp_encap_enable(void);
#if IS_ENABLED(CONFIG_IPV6)
void udpv6_encap_enable(void);
#endif
+
+void udp_flow_dissect_enable(void);
+void udp_flow_dissect_disable(void);
+
#endif /* _UDP_H */
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 1a7b80f..5a4dfaf 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -8,6 +8,8 @@
#include <net/ipv6.h>
#include <net/gre.h>
#include <net/pptp.h>
+#include <net/protocol.h>
+#include <net/udp.h>
#include <linux/igmp.h>
#include <linux/icmp.h>
#include <linux/sctp.h>
@@ -57,6 +59,20 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector,
}
EXPORT_SYMBOL(skb_flow_dissector_init);
+static struct static_key udp_flow_dissect __read_mostly;
+
+void udp_flow_dissect_enable(void)
+{
+ static_key_slow_inc(&udp_flow_dissect);
+}
+EXPORT_SYMBOL(udp_flow_dissect_enable);
+
+void udp_flow_dissect_disable(void)
+{
+ static_key_slow_dec(&udp_flow_dissect);
+}
+EXPORT_SYMBOL(udp_flow_dissect_disable);
+
/**
* __skb_flow_get_ports - extract the upper layer ports and return them
* @skb: sk_buff to extract the ports from
@@ -115,7 +131,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
{
struct flow_dissector_key_control *key_control;
struct flow_dissector_key_basic *key_basic;
- struct flow_dissector_key_addrs *key_addrs;
+ struct flow_dissector_key_addrs *key_addrs = NULL;
struct flow_dissector_key_ports *key_ports;
struct flow_dissector_key_tags *key_tags;
struct flow_dissector_key_vlan *key_vlan;
@@ -245,7 +261,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
}
case htons(ETH_P_8021AD):
case htons(ETH_P_8021Q): {
- const struct vlan_hdr *vlan;
+ const struct vlan_hdr *vlan = NULL;
if (skb_vlan_tag_present(skb))
proto = skb->protocol;
@@ -535,6 +551,59 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
case IPPROTO_MPLS:
proto = htons(ETH_P_MPLS_UC);
goto mpls;
+ case IPPROTO_UDP:
+ {
+ const struct net_offload **offloads;
+ const struct net_offload *ops;
+ int ret;
+
+ if (!static_key_false(&udp_flow_dissect))
+ break;
+
+ if (!key_addrs)
+ break;
+
+ /* See if there is a flow dissector for UDP protocol */
+
+ switch (key_control->addr_type) {
+ case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
+ offloads = inet_offloads;
+ break;
+ case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
+ offloads = inet6_offloads;
+ break;
+ default:
+ goto udp_finish;
+ }
+
+ rcu_read_lock();
+
+ ops = rcu_dereference(offloads[IPPROTO_UDP]);
+
+ if (!ops || !ops->callbacks.flow_dissect) {
+ rcu_read_unlock();
+ break;
+ }
+
+ ret = ops->callbacks.flow_dissect(skb, data, hlen, &nhoff,
+ &ip_proto, &proto, key_addrs);
+
+ rcu_read_unlock();
+
+ switch (ret) {
+ case FLOW_DIS_RET_IPPROTO:
+ goto ip_proto_again;
+ case FLOW_DIS_RET_PROTO:
+ goto again;
+ case FLOW_DIS_RET_BAD:
+ goto out_bad;
+ case FLOW_DIS_RET_PASS:
+ default:
+ break;
+ }
+udp_finish:
+ break;
+ }
default:
break;
}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 7f84c51..b4b528e 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1977,6 +1977,9 @@ void udp_destroy_sock(struct sock *sk)
if (encap_destroy)
encap_destroy(sk);
}
+
+ if (up->flow_dissect)
+ udp_flow_dissect_disable();
}
/*
--
2.9.3
^ permalink raw reply related
* [PATCH net-next 1/5] udp: Add socket lookup functions with noref
From: Tom Herbert @ 2016-10-12 23:25 UTC (permalink / raw)
To: davem, netdev; +Cc: kernel-team
In-Reply-To: <20161012232547.2383961-1-tom@herbertland.com>
Create udp4_lib_lookup_noref and udp6_lib_lookup_noref. These perfrom
a socket lookup on addresses and ports without taking a reference.
Signed-off-by: Tom Herbert <tom@herbertland.com>
---
include/net/udp.h | 8 ++++++++
net/ipv4/udp.c | 8 ++++++++
net/ipv6/udp.c | 10 ++++++++++
3 files changed, 26 insertions(+)
diff --git a/include/net/udp.h b/include/net/udp.h
index ea53a87..717a972 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -275,6 +275,10 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
struct udp_table *tbl, struct sk_buff *skb);
struct sock *udp4_lib_lookup_skb(struct sk_buff *skb,
__be16 sport, __be16 dport);
+struct sock *udp4_lib_lookup_noref(struct net *net,
+ __be32 saddr, __be16 sport,
+ __be32 daddr, __be16 dport,
+ int dif);
struct sock *udp6_lib_lookup(struct net *net,
const struct in6_addr *saddr, __be16 sport,
const struct in6_addr *daddr, __be16 dport,
@@ -286,6 +290,10 @@ struct sock *__udp6_lib_lookup(struct net *net,
struct sk_buff *skb);
struct sock *udp6_lib_lookup_skb(struct sk_buff *skb,
__be16 sport, __be16 dport);
+struct sock *udp6_lib_lookup_noref(struct net *net,
+ const struct in6_addr *saddr, __be16 sport,
+ const struct in6_addr *daddr, __be16 dport,
+ int dif);
/*
* SNMP statistics for UDP and UDP-Lite
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 7d96dc2..7f84c51 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -595,6 +595,14 @@ struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
EXPORT_SYMBOL_GPL(udp4_lib_lookup);
#endif
+struct sock *udp4_lib_lookup_noref(struct net *net, __be32 saddr, __be16 sport,
+ __be32 daddr, __be16 dport, int dif)
+{
+ return __udp4_lib_lookup(net, saddr, sport, daddr, dport,
+ dif, &udp_table, NULL);
+}
+EXPORT_SYMBOL_GPL(udp4_lib_lookup_noref);
+
static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk,
__be16 loc_port, __be32 loc_addr,
__be16 rmt_port, __be32 rmt_addr,
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 9aa7c1c..6e382d9 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -317,6 +317,16 @@ struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be
EXPORT_SYMBOL_GPL(udp6_lib_lookup);
#endif
+struct sock *udp6_lib_lookup_noref(struct net *net,
+ const struct in6_addr *saddr, __be16 sport,
+ const struct in6_addr *daddr, __be16 dport,
+ int dif)
+{
+ return __udp6_lib_lookup(net, saddr, sport, daddr, dport,
+ dif, &udp_table, NULL);
+}
+EXPORT_SYMBOL_GPL(udp6_lib_lookup_noref);
+
/*
* This should be easy, if there is something there we
* return it, otherwise we block.
--
2.9.3
^ permalink raw reply related
* [PATCH net-next 0/5] udp: Flow dissection for tunnels
From: Tom Herbert @ 2016-10-12 23:25 UTC (permalink / raw)
To: davem, netdev; +Cc: kernel-team
Now that we have a means to perform a UDP socket lookup without taking
a reference, it is feasible to have flow dissector crack open UDP
encapsulated packets. Generally, we would expect that the UDP source
port or the flow label in IPv6 would contain enough entropy about
the encapsulated flow. However, there will be cases, such as a static
UDP tunnel with fixed ports, where dissecting the encapsulated packet
is valuable.
The model is here is similar to that implemented for UDP GRO. A
tunnel implementation (e.g. GUE) may set a flow_dissect function
in the udp_sk. In __skb_flow_dissect a case has been added for
UDP to check if there is a socket with flow_dissect set. If there
is the function is called. The (per tunnel implementation)
function can parse the encapsulation headers and return the
next protocol for __skb_flow_dissect to process and it's position
in nhoff.
Since performing a UDP lookup on every packet might be expensive
I added a static key check to bypass the lookup if there are no
sockets with flow_dissect set. I should mention that doing the
lookup wasn't particularly a big hit anyway.
Fou/gue was modified to perform tunnel dissection. This is enabled
on each listener socket via a netlink configuration option.
Tested:
Running 200 streams with TCP_RR.
GRE/GUE variable source port (baseline)
RSS distributes packets, RFS is effective
1211702 tps
147/241/442 50/90/99% latencies
87.95 CPU utilization
GRE/GUE fixed source port
All packets to one CPU, RFS is ineffective
173680 tps
1170/1377/1853 50/90/99% latencies
7.42 CPU utilization
GRE/GUE fixed source port with deep hash enabled
All packets to one CPU, but now RFS is effective
730359 tps
263/325/464 50/90/99% latencies
38.25% CPU utilization (Interrupting CPU is maxed out)
Tom Herbert (5):
udp: Add socket lookup functions with noref
udp: UDP flow dissector
udp: Add UDP flow dissection functions to IPv4 and IPv6
udp: UDP tunnel flow dissection infrastructure
fou: Support flow dissection
include/linux/netdevice.h | 5 +++
include/linux/udp.h | 7 +++++
include/net/flow_dissector.h | 8 +++++
include/net/udp.h | 12 ++++++++
include/net/udp_tunnel.h | 5 +++
include/uapi/linux/fou.h | 1 +
net/core/flow_dissector.c | 73 ++++++++++++++++++++++++++++++++++++++++++--
net/ipv4/fou.c | 68 ++++++++++++++++++++++++++++++++++++++++-
net/ipv4/udp.c | 11 +++++++
net/ipv4/udp_offload.c | 39 +++++++++++++++++++++++
net/ipv4/udp_tunnel.c | 5 +++
net/ipv6/udp.c | 10 ++++++
net/ipv6/udp_offload.c | 38 +++++++++++++++++++++++
13 files changed, 279 insertions(+), 3 deletions(-)
--
2.9.3
^ permalink raw reply
* Re: [PATCH v3] iproute2: macvlan: add "source" mode
From: Stephen Hemminger @ 2016-10-12 22:27 UTC (permalink / raw)
To: Michael Braun; +Cc: netdev, projekt-wlan, steweg
In-Reply-To: <1474830535-12689-1-git-send-email-michael-dev@fami-braun.de>
On Sun, 25 Sep 2016 21:08:55 +0200
Michael Braun <michael-dev@fami-braun.de> wrote:
> Adjusting iproute2 utility to support new macvlan link type mode called
> "source".
>
> Example of commands that can be applied:
> ip link add link eth0 name macvlan0 type macvlan mode source
> ip link set link dev macvlan0 type macvlan macaddr add 00:11:11:11:11:11
> ip link set link dev macvlan0 type macvlan macaddr del 00:11:11:11:11:11
> ip link set link dev macvlan0 type macvlan macaddr flush
> ip -details link show dev macvlan0
>
> Based on previous work of Stefan Gula <steweg@gmail.com>
>
> Signed-off-by: Michael Braun <michael-dev@fami-braun.de>
>
> Cc: steweg@gmail.com
Applied.
^ permalink raw reply
* Re: [PATCH iproute2 1/1] tc filters: add support to get individual filters by handle
From: Stephen Hemminger @ 2016-10-12 22:26 UTC (permalink / raw)
To: Jamal Hadi Salim; +Cc: netdev, edumazet, mrv
In-Reply-To: <1476117914-32207-1-git-send-email-jhs@emojatatu.com>
On Mon, 10 Oct 2016 12:45:14 -0400
Jamal Hadi Salim <jhs@mojatatu.com> wrote:
> From: Jamal Hadi Salim <jhs@mojatatu.com>
>
> sudo $TC filter add dev $ETH parent ffff: prio 2 protocol ip \
> u32 match u32 0 0 flowid 1:1 \
> action ok
> sudo $TC filter add dev $ETH parent ffff: prio 1 protocol ip \
> u32 match ip protocol 1 0xff flowid 1:10 \
> action ok
>
> now dump to see all rules..
> $TC -s filter ls dev $ETH parent ffff: protocol ip
> ....
> filter pref 1 u32
> filter pref 1 u32 fh 801: ht divisor 1
> filter pref 1 u32 fh 801::800 order 2048 key ht 801 bkt 0 flowid 1:10 (rule hit 0 success 0)
> match 00010000/00ff0000 at 8 (success 0 )
> action order 1: gact action drop
> random type none pass val 0
> index 6 ref 1 bind 1 installed 4 sec used 4 sec
> Action statistics:
> Sent 0 bytes 0 pkt (dropped 0, overlimits 0 requeues 0)
> backlog 0b 0p requeues 0
>
> filter pref 2 u32
> filter pref 2 u32 fh 800: ht divisor 1
> filter pref 2 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:1 (rule hit 336 success 336)
> match 00000000/00000000 at 0 (success 336 )
> action order 1: gact action pass
> random type none pass val 0
> index 5 ref 1 bind 1 installed 38 sec used 4 sec
> Action statistics:
> Sent 24864 bytes 336 pkt (dropped 0, overlimits 0 requeues 0)
> backlog 0b 0p requeues 0
> ....
>
> ..get filter 801::800
> $TC -s filter get dev $ETH parent ffff: protocol ip \
> handle 801:0:800 prio 2 u32
>
> ....
> filter parent ffff: protocol ip pref 1 u32 fh 801::800 order 2048 key ht 801 bkt 0 flowid 1:10 (rule hit 260 success 130)
> match 00010000/00ff0000 at 8 (success 130 )
> action order 1: gact action drop
> random type none pass val 0
> index 6 ref 1 bind 1 installed 348 sec used 0 sec
> Action statistics:
> Sent 11440 bytes 130 pkt (dropped 130, overlimits 0 requeues 0)
> backlog 0b 0p requeues 0
> ....
>
> ..get other one
> $TC -s filter get dev $ETH parent ffff: protocol ip \
> handle 800:0:800 prio 2 u32
>
> ....
> filter parent ffff: protocol ip pref 2 u32 fh 800::800 order 2048 key ht 800 bkt 0 flowid 1:1 (rule hit 514 success 514)
> match 00000000/00000000 at 0 (success 514 )
> action order 1: gact action pass
> random type none pass val 0
> index 5 ref 1 bind 1 installed 506 sec used 4 sec
> Action statistics:
> Sent 35544 bytes 514 pkt (dropped 0, overlimits 0 requeues 0)
> backlog 0b 0p requeues 0
> ....
>
> ..try something that doesnt exist
> $TC -s filter get dev $ETH parent ffff: protocol ip handle 800:0:803 prio 2 u32
>
> .....
> RTNETLINK answers: No such file or directory
> We have an error talking to the kernel
> .....
>
> Note, added NLM_F_ECHO is for backward compatibility. old kernels never
> before Eric's patch will not respond without it and newer kernels (after Erics patch)
> will ignore it.
> In old kernels there is a side effect:
> In addition to a response to the GET you will receive an event (if you do tc mon).
> But this is still better than what it was before (not working at all).
>
> Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Applied
^ permalink raw reply
* Re: [PATCH v2 iproute2 0/9] Cleanup backlog
From: Stephen Hemminger @ 2016-10-12 22:26 UTC (permalink / raw)
To: Jamal Hadi Salim; +Cc: netdev, mrv, cdillaba, lucasb
In-Reply-To: <1476183648-25850-1-git-send-email-jhs@emojatatu.com>
On Tue, 11 Oct 2016 07:00:39 -0400
Jamal Hadi Salim <jhs@mojatatu.com> wrote:
> From: Jamal Hadi Salim <jhs@mojatatu.com>
>
>
> Variety of cleanup and new functionality I had sitting around on my
> private tree
>
> Craig Dillabaugh (1):
> action gact: list pipe as a valid action
>
> Jamal Hadi Salim (3):
> actions ife: Introduce encoding and decoding of tcindex metadata
> actions: add skbmod action
> man pages: Add tc-ife to Makefile
>
> Lucas Bates (2):
> man pages: update ife action to include tcindex
> man pages: add man page for skbmod action
>
> Roman Mashak (3):
> ife action: allow specifying index in hex
> ife: print prio, mark and hash as unsigned
> ife: improve help text
>
> include/linux/tc_act/tc_ife.h | 3 +-
> man/man8/Makefile | 2 +-
> man/man8/tc-ife.8 | 29 ++++-
> tc/m_gact.c | 4 +-
> tc/m_ife.c | 38 ++++--
> tc/m_skbmod.c | 260 ++++++++++++++++++++++++++++++++++++++++++
> 6 files changed, 319 insertions(+), 17 deletions(-)
> create mode 100644 tc/m_skbmod.c
>
Applied. Then went through and cleaned up minor checkpatch style issues.
^ permalink raw reply
* Re: [PATCH net-next] net: phy: Trigger state machine on state change and not polling.
From: Kyle Roeschley @ 2016-10-12 21:44 UTC (permalink / raw)
To: Andrew Lunn; +Cc: David Miller, netdev, Florian Fainelli
In-Reply-To: <1476303294-14944-1-git-send-email-andrew@lunn.ch>
On Wed, Oct 12, 2016 at 10:14:53PM +0200, Andrew Lunn wrote:
> The phy_start() is used to indicate the PHY is now ready to do its
> work. The state is changed, normally to PHY_UP which means that both
> the MAC and the PHY are ready.
>
> If the phy driver is using polling, when the next poll happens, the
> state machine notices the PHY is now in PHY_UP, and kicks off
> auto-negotiation, if needed.
>
> If however, the PHY is using interrupts, there is no polling. The phy
> is stuck in PHY_UP until the next interrupt comes along. And there is
> no reason for the PHY to interrupt.
>
> Have phy_start() schedule the state machine to run, which both speeds
> up the polling use case, and makes the interrupt use case actually
> work.
>
> This problems exists whenever there is a state change which will not
> cause an interrupt. Trigger the state machine in these cases,
> e.g. phy_error().
>
> Signed-off-by: Andrew Lunn <andrew@lunn.ch>
> Cc: Kyle Roeschley <kyle.roeschley@ni.com>
> ---
>
> This should be applied to stable, but i've no idea what fixes: tag to
> use. It could be phylib has been broken since interrupts were added?
>
This patched fixed another problem had with the phy state machine which was
caused by d5c3d8465 ("net: phy: Avoid polling PHY with PHY_IGNORE_INTERRUPTS").
That might be the commit you're looking for. Also,
Tested-by: Kyle Roeschley <kyle.roeschley@ni.com>
> drivers/net/phy/phy.c | 22 ++++++++++++++++++++--
> 1 file changed, 20 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
> index c6f66832a1a6..f424b867f73e 100644
> --- a/drivers/net/phy/phy.c
> +++ b/drivers/net/phy/phy.c
> @@ -608,6 +608,21 @@ void phy_start_machine(struct phy_device *phydev)
> }
>
> /**
> + * phy_trigger_machine - trigger the state machine to run
> + *
> + * @phydev: the phy_device struct
> + *
> + * Description: There has been a change in state which requires that the
> + * state machine runs.
> + */
> +
You've got a bonus newline here.
> +static void phy_trigger_machine(struct phy_device *phydev)
> +{
> + cancel_delayed_work_sync(&phydev->state_queue);
> + queue_delayed_work(system_power_efficient_wq, &phydev->state_queue, 0);
> +}
> +
> +/**
> * phy_stop_machine - stop the PHY state machine tracking
> * @phydev: target phy_device struct
> *
> @@ -639,6 +654,8 @@ static void phy_error(struct phy_device *phydev)
> mutex_lock(&phydev->lock);
> phydev->state = PHY_HALTED;
> mutex_unlock(&phydev->lock);
> +
> + phy_trigger_machine(phydev);
> }
>
> /**
> @@ -800,8 +817,7 @@ void phy_change(struct work_struct *work)
> }
>
> /* reschedule state queue work to run as soon as possible */
> - cancel_delayed_work_sync(&phydev->state_queue);
> - queue_delayed_work(system_power_efficient_wq, &phydev->state_queue, 0);
> + phy_trigger_machine(phydev);
> return;
>
> ignore:
> @@ -890,6 +906,8 @@ void phy_start(struct phy_device *phydev)
> /* if phy was suspended, bring the physical link up again */
> if (do_resume)
> phy_resume(phydev);
> +
> + phy_trigger_machine(phydev);
> }
> EXPORT_SYMBOL(phy_start);
>
> --
> 2.9.3
>
--
Kyle Roeschley
Software Engineer
National Instruments
^ permalink raw reply
* [PATCH net-next 09/11] net: Remove all_adj_list and its references
From: David Ahern @ 2016-10-12 20:51 UTC (permalink / raw)
To: jiri, netdev, davem
Cc: dledford, sean.hefty, hal.rosenstock, linux-rdma, j.vosburgh,
vfalico, andy, jeffrey.t.kirsher, intel-wired-lan, David Ahern
In-Reply-To: <1476305519-28833-1-git-send-email-dsa@cumulusnetworks.com>
Only direct adjacencies are maintained. All upper or lower devices can
be learned via the new walk API which recursively walks the adj_list for
upper devices or lower devices.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
include/linux/netdevice.h | 25 -----
net/core/dev.c | 229 +++++-----------------------------------------
2 files changed, 21 insertions(+), 233 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 053f6f75f26a..8215908556ec 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1456,7 +1456,6 @@ enum netdev_priv_flags {
* @ptype_specific: Device-specific, protocol-specific packet handlers
*
* @adj_list: Directly linked devices, like slaves for bonding
- * @all_adj_list: All linked devices, *including* neighbours
* @features: Currently active device features
* @hw_features: User-changeable features
*
@@ -1673,11 +1672,6 @@ struct net_device {
struct list_head lower;
} adj_list;
- struct {
- struct list_head upper;
- struct list_head lower;
- } all_adj_list;
-
netdev_features_t features;
netdev_features_t hw_features;
netdev_features_t wanted_features;
@@ -3832,13 +3826,6 @@ struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
updev; \
updev = netdev_upper_get_next_dev_rcu(dev, &(iter)))
-/* iterate through upper list, must be called under RCU read lock */
-#define netdev_for_each_all_upper_dev_rcu(dev, updev, iter) \
- for (iter = &(dev)->all_adj_list.upper, \
- updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter)); \
- updev; \
- updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter)))
-
int netdev_walk_all_upper_dev_rcu(struct net_device *dev,
int (*fn)(struct net_device *lower_dev,
void *data),
@@ -3878,18 +3865,6 @@ struct net_device *netdev_all_lower_get_next(struct net_device *dev,
struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev,
struct list_head **iter);
-#define netdev_for_each_all_lower_dev(dev, ldev, iter) \
- for (iter = (dev)->all_adj_list.lower.next, \
- ldev = netdev_all_lower_get_next(dev, &(iter)); \
- ldev; \
- ldev = netdev_all_lower_get_next(dev, &(iter)))
-
-#define netdev_for_each_all_lower_dev_rcu(dev, ldev, iter) \
- for (iter = (dev)->all_adj_list.lower.next, \
- ldev = netdev_all_lower_get_next_rcu(dev, &(iter)); \
- ldev; \
- ldev = netdev_all_lower_get_next_rcu(dev, &(iter)))
-
int netdev_walk_all_lower_dev(struct net_device *dev,
int (*fn)(struct net_device *lower_dev,
void *data),
diff --git a/net/core/dev.c b/net/core/dev.c
index fcf3641db783..0f9b0985a84c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5273,6 +5273,16 @@ static struct netdev_adjacent *__netdev_find_adj(struct net_device *adj_dev,
return NULL;
}
+static int __netdev_has_upper_dev(struct net_device *upper_dev, void *data)
+{
+ struct net_device *dev = (struct net_device *)data;
+
+ if (upper_dev == dev)
+ return 1;
+
+ return 0;
+}
+
/**
* netdev_has_upper_dev - Check if device is linked to an upper device
* @dev: device
@@ -5287,7 +5297,8 @@ bool netdev_has_upper_dev(struct net_device *dev,
{
ASSERT_RTNL();
- return __netdev_find_adj(upper_dev, &dev->all_adj_list.upper);
+ return netdev_walk_all_upper_dev_rcu(dev, __netdev_has_upper_dev,
+ upper_dev);
}
EXPORT_SYMBOL(netdev_has_upper_dev);
@@ -5301,16 +5312,6 @@ EXPORT_SYMBOL(netdev_has_upper_dev);
* The caller must hold rcu lock.
*/
-static int __netdev_has_upper_dev(struct net_device *upper_dev, void *data)
-{
- struct net_device *dev = (struct net_device *)data;
-
- if (upper_dev == dev)
- return 1;
-
- return 0;
-}
-
bool netdev_has_upper_dev_all_rcu(struct net_device *dev,
struct net_device *upper_dev)
{
@@ -5333,7 +5334,7 @@ static bool netdev_has_any_upper_dev(struct net_device *dev)
{
ASSERT_RTNL();
- return !list_empty(&dev->all_adj_list.upper);
+ return !list_empty(&dev->adj_list.upper);
}
/**
@@ -5396,32 +5397,6 @@ struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
}
EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu);
-/**
- * netdev_all_upper_get_next_dev_rcu - Get the next dev from upper list
- * @dev: device
- * @iter: list_head ** of the current position
- *
- * Gets the next device from the dev's upper list, starting from iter
- * position. The caller must hold RCU read lock.
- */
-struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
- struct list_head **iter)
-{
- struct netdev_adjacent *upper;
-
- WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held());
-
- upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list);
-
- if (&upper->list == &dev->all_adj_list.upper)
- return NULL;
-
- *iter = &upper->list;
-
- return upper->dev;
-}
-EXPORT_SYMBOL(netdev_all_upper_get_next_dev_rcu);
-
static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev,
struct list_head **iter)
{
@@ -5548,31 +5523,6 @@ void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter)
}
EXPORT_SYMBOL(netdev_lower_get_next);
-/**
- * netdev_all_lower_get_next - Get the next device from all lower neighbour list
- * @dev: device
- * @iter: list_head ** of the current position
- *
- * Gets the next netdev_adjacent from the dev's all lower neighbour
- * list, starting from iter position. The caller must hold RTNL lock or
- * its own locking that guarantees that the neighbour all lower
- * list will remain unchanged.
- */
-struct net_device *netdev_all_lower_get_next(struct net_device *dev, struct list_head **iter)
-{
- struct netdev_adjacent *lower;
-
- lower = list_entry(*iter, struct netdev_adjacent, list);
-
- if (&lower->list == &dev->all_adj_list.lower)
- return NULL;
-
- *iter = lower->list.next;
-
- return lower->dev;
-}
-EXPORT_SYMBOL(netdev_all_lower_get_next);
-
static struct net_device *netdev_next_lower_dev(struct net_device *dev,
struct list_head **iter)
{
@@ -5616,27 +5566,6 @@ int netdev_walk_all_lower_dev(struct net_device *dev,
}
EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev);
-/**
- * netdev_all_lower_get_next_rcu - Get the next device from all
- * lower neighbour list, RCU variant
- * @dev: device
- * @iter: list_head ** of the current position
- *
- * Gets the next netdev_adjacent from the dev's all lower neighbour
- * list, starting from iter position. The caller must hold RCU read lock.
- */
-struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev,
- struct list_head **iter)
-{
- struct netdev_adjacent *lower;
-
- lower = list_first_or_null_rcu(&dev->all_adj_list.lower,
- struct netdev_adjacent, list);
-
- return lower ? lower->dev : NULL;
-}
-EXPORT_SYMBOL(netdev_all_lower_get_next_rcu);
-
static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
struct list_head **iter)
{
@@ -5861,15 +5790,6 @@ static int __netdev_adjacent_dev_link_lists(struct net_device *dev,
return 0;
}
-static int __netdev_adjacent_dev_link(struct net_device *dev,
- struct net_device *upper_dev)
-{
- return __netdev_adjacent_dev_link_lists(dev, upper_dev,
- &dev->all_adj_list.upper,
- &upper_dev->all_adj_list.lower,
- NULL, false);
-}
-
static void __netdev_adjacent_dev_unlink_lists(struct net_device *dev,
struct net_device *upper_dev,
u16 ref_nr,
@@ -5880,40 +5800,19 @@ static void __netdev_adjacent_dev_unlink_lists(struct net_device *dev,
__netdev_adjacent_dev_remove(upper_dev, dev, ref_nr, down_list);
}
-static void __netdev_adjacent_dev_unlink(struct net_device *dev,
- struct net_device *upper_dev,
- u16 ref_nr)
-{
- __netdev_adjacent_dev_unlink_lists(dev, upper_dev, ref_nr,
- &dev->all_adj_list.upper,
- &upper_dev->all_adj_list.lower);
-}
-
static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
struct net_device *upper_dev,
void *private, bool master)
{
- int ret = __netdev_adjacent_dev_link(dev, upper_dev);
-
- if (ret)
- return ret;
-
- ret = __netdev_adjacent_dev_link_lists(dev, upper_dev,
- &dev->adj_list.upper,
- &upper_dev->adj_list.lower,
- private, master);
- if (ret) {
- __netdev_adjacent_dev_unlink(dev, upper_dev, 1);
- return ret;
- }
-
- return 0;
+ return __netdev_adjacent_dev_link_lists(dev, upper_dev,
+ &dev->adj_list.upper,
+ &upper_dev->adj_list.lower,
+ private, master);
}
static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev,
struct net_device *upper_dev)
{
- __netdev_adjacent_dev_unlink(dev, upper_dev, 1);
__netdev_adjacent_dev_unlink_lists(dev, upper_dev, 1,
&dev->adj_list.upper,
&upper_dev->adj_list.lower);
@@ -5924,7 +5823,6 @@ static int __netdev_upper_dev_link(struct net_device *dev,
void *upper_priv, void *upper_info)
{
struct netdev_notifier_changeupper_info changeupper_info;
- struct netdev_adjacent *i, *j, *to_i, *to_j;
int ret = 0;
ASSERT_RTNL();
@@ -5933,10 +5831,10 @@ static int __netdev_upper_dev_link(struct net_device *dev,
return -EBUSY;
/* To prevent loops, check if dev is not upper device to upper_dev. */
- if (__netdev_find_adj(dev, &upper_dev->all_adj_list.upper))
+ if (netdev_has_upper_dev(upper_dev, dev))
return -EBUSY;
- if (__netdev_find_adj(upper_dev, &dev->adj_list.upper))
+ if (netdev_has_upper_dev(dev, upper_dev))
return -EEXIST;
if (master && netdev_master_upper_dev_get(dev))
@@ -5958,80 +5856,15 @@ static int __netdev_upper_dev_link(struct net_device *dev,
if (ret)
return ret;
- /* Now that we linked these devs, make all the upper_dev's
- * all_adj_list.upper visible to every dev's all_adj_list.lower an
- * versa, and don't forget the devices itself. All of these
- * links are non-neighbours.
- */
- list_for_each_entry(i, &dev->all_adj_list.lower, list) {
- list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) {
- pr_debug("Interlinking %s with %s, non-neighbour\n",
- i->dev->name, j->dev->name);
- ret = __netdev_adjacent_dev_link(i->dev, j->dev);
- if (ret)
- goto rollback_mesh;
- }
- }
-
- /* add dev to every upper_dev's upper device */
- list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) {
- pr_debug("linking %s's upper device %s with %s\n",
- upper_dev->name, i->dev->name, dev->name);
- ret = __netdev_adjacent_dev_link(dev, i->dev);
- if (ret)
- goto rollback_upper_mesh;
- }
-
- /* add upper_dev to every dev's lower device */
- list_for_each_entry(i, &dev->all_adj_list.lower, list) {
- pr_debug("linking %s's lower device %s with %s\n", dev->name,
- i->dev->name, upper_dev->name);
- ret = __netdev_adjacent_dev_link(i->dev, upper_dev);
- if (ret)
- goto rollback_lower_mesh;
- }
-
ret = call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev,
&changeupper_info.info);
ret = notifier_to_errno(ret);
if (ret)
- goto rollback_lower_mesh;
+ goto rollback;
return 0;
-rollback_lower_mesh:
- to_i = i;
- list_for_each_entry(i, &dev->all_adj_list.lower, list) {
- if (i == to_i)
- break;
- __netdev_adjacent_dev_unlink(i->dev, upper_dev, i->ref_nr);
- }
-
- i = NULL;
-
-rollback_upper_mesh:
- to_i = i;
- list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) {
- if (i == to_i)
- break;
- __netdev_adjacent_dev_unlink(dev, i->dev, i->ref_nr);
- }
-
- i = j = NULL;
-
-rollback_mesh:
- to_i = i;
- to_j = j;
- list_for_each_entry(i, &dev->all_adj_list.lower, list) {
- list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) {
- if (i == to_i && j == to_j)
- break;
- __netdev_adjacent_dev_unlink(i->dev, j->dev, i->ref_nr);
- }
- if (i == to_i)
- break;
- }
-
+rollback:
__netdev_adjacent_dev_unlink_neighbour(dev, upper_dev);
return ret;
@@ -6088,7 +5921,6 @@ void netdev_upper_dev_unlink(struct net_device *dev,
struct net_device *upper_dev)
{
struct netdev_notifier_changeupper_info changeupper_info;
- struct netdev_adjacent *i, *j;
ASSERT_RTNL();
changeupper_info.upper_dev = upper_dev;
@@ -6100,23 +5932,6 @@ void netdev_upper_dev_unlink(struct net_device *dev,
__netdev_adjacent_dev_unlink_neighbour(dev, upper_dev);
- /* Here is the tricky part. We must remove all dev's lower
- * devices from all upper_dev's upper devices and vice
- * versa, to maintain the graph relationship.
- */
- list_for_each_entry(i, &dev->all_adj_list.lower, list)
- list_for_each_entry(j, &upper_dev->all_adj_list.upper, list)
- __netdev_adjacent_dev_unlink(i->dev, j->dev, i->ref_nr);
-
- /* remove also the devices itself from lower/upper device
- * list
- */
- list_for_each_entry(i, &dev->all_adj_list.lower, list)
- __netdev_adjacent_dev_unlink(i->dev, upper_dev, i->ref_nr);
-
- list_for_each_entry(i, &upper_dev->all_adj_list.upper, list)
- __netdev_adjacent_dev_unlink(dev, i->dev, i->ref_nr);
-
call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev,
&changeupper_info.info);
}
@@ -7809,8 +7624,6 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
INIT_LIST_HEAD(&dev->link_watch_list);
INIT_LIST_HEAD(&dev->adj_list.upper);
INIT_LIST_HEAD(&dev->adj_list.lower);
- INIT_LIST_HEAD(&dev->all_adj_list.upper);
- INIT_LIST_HEAD(&dev->all_adj_list.lower);
INIT_LIST_HEAD(&dev->ptype_all);
INIT_LIST_HEAD(&dev->ptype_specific);
#ifdef CONFIG_NET_SCHED
--
2.1.4
^ permalink raw reply related
* [PATCH net-next 10/11] net: Add warning if any lower device is still in adjacency list
From: David Ahern @ 2016-10-12 20:51 UTC (permalink / raw)
To: jiri, netdev, davem
Cc: dledford, sean.hefty, hal.rosenstock, linux-rdma, j.vosburgh,
vfalico, andy, jeffrey.t.kirsher, intel-wired-lan, David Ahern
In-Reply-To: <1476305519-28833-1-git-send-email-dsa@cumulusnetworks.com>
Lower list should be empty just like upper.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
net/core/dev.c | 15 +++++++++++++++
1 file changed, 15 insertions(+)
diff --git a/net/core/dev.c b/net/core/dev.c
index 0f9b0985a84c..52e70a3d61a4 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5361,6 +5361,20 @@ struct net_device *netdev_master_upper_dev_get(struct net_device *dev)
}
EXPORT_SYMBOL(netdev_master_upper_dev_get);
+/**
+ * netdev_has_any_lower_dev - Check if device is linked to some device
+ * @dev: device
+ *
+ * Find out if a device is linked to a lower device and return true in case
+ * it is. The caller must hold the RTNL lock.
+ */
+static bool netdev_has_any_lower_dev(struct net_device *dev)
+{
+ ASSERT_RTNL();
+
+ return !list_empty(&dev->adj_list.lower);
+}
+
void *netdev_adjacent_get_private(struct list_head *adj_list)
{
struct netdev_adjacent *adj;
@@ -6746,6 +6760,7 @@ static void rollback_registered_many(struct list_head *head)
/* Notifier chain MUST detach us all upper devices. */
WARN_ON(netdev_has_any_upper_dev(dev));
+ WARN_ON(netdev_has_any_lower_dev(dev));
/* Remove entries from kobject tree */
netdev_unregister_kobject(dev);
--
2.1.4
^ permalink raw reply related
* [PATCH net-next 07/11] mlxsw: Flip to the new dev walk API
From: David Ahern @ 2016-10-12 20:51 UTC (permalink / raw)
To: jiri, netdev, davem
Cc: dledford, sean.hefty, hal.rosenstock, linux-rdma, j.vosburgh,
vfalico, andy, jeffrey.t.kirsher, intel-wired-lan, David Ahern
In-Reply-To: <1476305519-28833-1-git-send-email-dsa@cumulusnetworks.com>
Convert mlxsw users to new dev walk API. This is just a move to the
new API; no functional change is intended.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 37 ++++++++++++++++----------
1 file changed, 23 insertions(+), 14 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 1ec0a4ce3c46..1d5434ff02bb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -3090,19 +3090,30 @@ static bool mlxsw_sp_port_dev_check(const struct net_device *dev)
return dev->netdev_ops == &mlxsw_sp_port_netdev_ops;
}
+static int mlxsw_lower_dev_walk(struct net_device *lower_dev, void *data)
+{
+ struct mlxsw_sp_port **port = data;
+ int ret = 0;
+
+ if (mlxsw_sp_port_dev_check(lower_dev)) {
+ *port = netdev_priv(lower_dev);
+ ret = 1;
+ }
+
+ return ret;
+}
+
static struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find(struct net_device *dev)
{
- struct net_device *lower_dev;
- struct list_head *iter;
+ struct mlxsw_sp_port *port;
if (mlxsw_sp_port_dev_check(dev))
return netdev_priv(dev);
- netdev_for_each_all_lower_dev(dev, lower_dev, iter) {
- if (mlxsw_sp_port_dev_check(lower_dev))
- return netdev_priv(lower_dev);
- }
- return NULL;
+ port = NULL;
+ netdev_walk_all_lower_dev(dev, mlxsw_lower_dev_walk, &port);
+
+ return port;
}
static struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev)
@@ -3115,17 +3126,15 @@ static struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev)
static struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find_rcu(struct net_device *dev)
{
- struct net_device *lower_dev;
- struct list_head *iter;
+ struct mlxsw_sp_port *port;
if (mlxsw_sp_port_dev_check(dev))
return netdev_priv(dev);
- netdev_for_each_all_lower_dev_rcu(dev, lower_dev, iter) {
- if (mlxsw_sp_port_dev_check(lower_dev))
- return netdev_priv(lower_dev);
- }
- return NULL;
+ port = NULL;
+ netdev_walk_all_lower_dev_rcu(dev, mlxsw_lower_dev_walk, &port);
+
+ return port;
}
struct mlxsw_sp_port *mlxsw_sp_port_lower_dev_hold(struct net_device *dev)
--
2.1.4
^ permalink raw reply related
* [PATCH net-next 06/11] ixgbe: Flip to the new dev walk API
From: David Ahern @ 2016-10-12 20:51 UTC (permalink / raw)
To: jiri, netdev, davem
Cc: dledford, sean.hefty, hal.rosenstock, linux-rdma, j.vosburgh,
vfalico, andy, jeffrey.t.kirsher, intel-wired-lan, David Ahern
In-Reply-To: <1476305519-28833-1-git-send-email-dsa@cumulusnetworks.com>
Convert ixgbe users of the old macros to new dev walk API.
This is just a move to the new API; no functional change is intended.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 132 ++++++++++++++++----------
1 file changed, 82 insertions(+), 50 deletions(-)
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index a244d9a67264..aae5e0349d93 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -5012,24 +5012,23 @@ static int ixgbe_fwd_ring_up(struct net_device *vdev,
return err;
}
-static void ixgbe_configure_dfwd(struct ixgbe_adapter *adapter)
+static int ixgbe_upper_dev_walk(struct net_device *upper, void *data)
{
- struct net_device *upper;
- struct list_head *iter;
- int err;
-
- netdev_for_each_all_upper_dev_rcu(adapter->netdev, upper, iter) {
- if (netif_is_macvlan(upper)) {
- struct macvlan_dev *dfwd = netdev_priv(upper);
- struct ixgbe_fwd_adapter *vadapter = dfwd->fwd_priv;
+ if (netif_is_macvlan(upper)) {
+ struct macvlan_dev *dfwd = netdev_priv(upper);
+ struct ixgbe_fwd_adapter *vadapter = dfwd->fwd_priv;
- if (dfwd->fwd_priv) {
- err = ixgbe_fwd_ring_up(upper, vadapter);
- if (err)
- continue;
- }
- }
+ if (dfwd->fwd_priv)
+ ixgbe_fwd_ring_up(upper, vadapter);
}
+
+ return 0;
+}
+
+static void ixgbe_configure_dfwd(struct ixgbe_adapter *adapter)
+{
+ netdev_walk_all_upper_dev_rcu(adapter->netdev,
+ ixgbe_upper_dev_walk, NULL);
}
static void ixgbe_configure(struct ixgbe_adapter *adapter)
@@ -5448,12 +5447,25 @@ static void ixgbe_fdir_filter_exit(struct ixgbe_adapter *adapter)
spin_unlock(&adapter->fdir_perfect_lock);
}
+static int ixgbe_disable_macvlan(struct net_device *upper, void *data)
+{
+ if (netif_is_macvlan(upper)) {
+ struct macvlan_dev *vlan = netdev_priv(upper);
+
+ if (vlan->fwd_priv) {
+ netif_tx_stop_all_queues(upper);
+ netif_carrier_off(upper);
+ netif_tx_disable(upper);
+ }
+ }
+
+ return 0;
+}
+
void ixgbe_down(struct ixgbe_adapter *adapter)
{
struct net_device *netdev = adapter->netdev;
struct ixgbe_hw *hw = &adapter->hw;
- struct net_device *upper;
- struct list_head *iter;
int i;
/* signal that we are down to the interrupt handler */
@@ -5477,17 +5489,8 @@ void ixgbe_down(struct ixgbe_adapter *adapter)
netif_tx_disable(netdev);
/* disable any upper devices */
- netdev_for_each_all_upper_dev_rcu(adapter->netdev, upper, iter) {
- if (netif_is_macvlan(upper)) {
- struct macvlan_dev *vlan = netdev_priv(upper);
-
- if (vlan->fwd_priv) {
- netif_tx_stop_all_queues(upper);
- netif_carrier_off(upper);
- netif_tx_disable(upper);
- }
- }
- }
+ netdev_walk_all_upper_dev_rcu(adapter->netdev,
+ ixgbe_disable_macvlan, NULL);
ixgbe_irq_disable(adapter);
@@ -6728,6 +6731,18 @@ static void ixgbe_update_default_up(struct ixgbe_adapter *adapter)
#endif
}
+static int ixgbe_enable_macvlan(struct net_device *upper, void *data)
+{
+ if (netif_is_macvlan(upper)) {
+ struct macvlan_dev *vlan = netdev_priv(upper);
+
+ if (vlan->fwd_priv)
+ netif_tx_wake_all_queues(upper);
+ }
+
+ return 0;
+}
+
/**
* ixgbe_watchdog_link_is_up - update netif_carrier status and
* print link up message
@@ -6737,8 +6752,6 @@ static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *adapter)
{
struct net_device *netdev = adapter->netdev;
struct ixgbe_hw *hw = &adapter->hw;
- struct net_device *upper;
- struct list_head *iter;
u32 link_speed = adapter->link_speed;
const char *speed_str;
bool flow_rx, flow_tx;
@@ -6809,14 +6822,8 @@ static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *adapter)
/* enable any upper devices */
rtnl_lock();
- netdev_for_each_all_upper_dev_rcu(adapter->netdev, upper, iter) {
- if (netif_is_macvlan(upper)) {
- struct macvlan_dev *vlan = netdev_priv(upper);
-
- if (vlan->fwd_priv)
- netif_tx_wake_all_queues(upper);
- }
- }
+ netdev_walk_all_upper_dev_rcu(adapter->netdev,
+ ixgbe_enable_macvlan, NULL);
rtnl_unlock();
/* update the default user priority for VFs */
@@ -8350,12 +8357,38 @@ static int ixgbe_configure_clsu32_del_hnode(struct ixgbe_adapter *adapter,
}
#ifdef CONFIG_NET_CLS_ACT
+struct upper_walk_data {
+ struct ixgbe_adapter *adapter;
+ int ifindex;
+ u64 action;
+ u8 queue;
+};
+
+static int get_macvlan_queue(struct net_device *upper, void *_data)
+{
+ if (netif_is_macvlan(upper)) {
+ struct macvlan_dev *dfwd = netdev_priv(upper);
+ struct ixgbe_fwd_adapter *vadapter = dfwd->fwd_priv;
+ struct upper_walk_data *data = _data;
+ struct ixgbe_adapter *adapter = data->adapter;
+ int ifindex = data->ifindex;
+
+ if (vadapter && vadapter->netdev->ifindex == ifindex) {
+ data->queue = adapter->rx_ring[vadapter->rx_base_queue]->reg_idx;
+ data->action = data->queue;
+ return 1;
+ }
+ }
+
+ return 0;
+}
+
static int handle_redirect_action(struct ixgbe_adapter *adapter, int ifindex,
u8 *queue, u64 *action)
{
unsigned int num_vfs = adapter->num_vfs, vf;
+ struct upper_walk_data data;
struct net_device *upper;
- struct list_head *iter;
/* redirect to a SRIOV VF */
for (vf = 0; vf < num_vfs; ++vf) {
@@ -8373,17 +8406,16 @@ static int handle_redirect_action(struct ixgbe_adapter *adapter, int ifindex,
}
/* redirect to a offloaded macvlan netdev */
- netdev_for_each_all_upper_dev_rcu(adapter->netdev, upper, iter) {
- if (netif_is_macvlan(upper)) {
- struct macvlan_dev *dfwd = netdev_priv(upper);
- struct ixgbe_fwd_adapter *vadapter = dfwd->fwd_priv;
-
- if (vadapter && vadapter->netdev->ifindex == ifindex) {
- *queue = adapter->rx_ring[vadapter->rx_base_queue]->reg_idx;
- *action = *queue;
- return 0;
- }
- }
+ data.adapter = adapter;
+ data.ifindex = ifindex;
+ data.action = 0;
+ data.queue = 0;
+ if (netdev_walk_all_upper_dev_rcu(adapter->netdev,
+ get_macvlan_queue, &data)) {
+ *action = data.action;
+ *queue = data.queue;
+
+ return 0;
}
return -EINVAL;
--
2.1.4
^ permalink raw reply related
* [PATCH net-next 04/11] IB/core: Flip to the new dev walk API
From: David Ahern @ 2016-10-12 20:51 UTC (permalink / raw)
To: jiri, netdev, davem
Cc: dledford, sean.hefty, hal.rosenstock, linux-rdma, j.vosburgh,
vfalico, andy, jeffrey.t.kirsher, intel-wired-lan, David Ahern
In-Reply-To: <1476305519-28833-1-git-send-email-dsa@cumulusnetworks.com>
Convert rdma_is_upper_dev_rcu, handle_netdev_upper and
ipoib_get_net_dev_match_addr to the new upper device walk API.
This is just a move to the new API; no functional change is intended.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
drivers/infiniband/core/core_priv.h | 9 +------
drivers/infiniband/core/roce_gid_mgmt.c | 42 ++++++++++++++++++---------------
2 files changed, 24 insertions(+), 27 deletions(-)
diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index 19d499dcab76..0c0bea091de8 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -127,14 +127,7 @@ void ib_cache_release_one(struct ib_device *device);
static inline bool rdma_is_upper_dev_rcu(struct net_device *dev,
struct net_device *upper)
{
- struct net_device *_upper = NULL;
- struct list_head *iter;
-
- netdev_for_each_all_upper_dev_rcu(dev, _upper, iter)
- if (_upper == upper)
- break;
-
- return _upper == upper;
+ return netdev_has_upper_dev_all_rcu(dev, upper);
}
int addr_init(void);
diff --git a/drivers/infiniband/core/roce_gid_mgmt.c b/drivers/infiniband/core/roce_gid_mgmt.c
index 06556c34606d..db759a68d948 100644
--- a/drivers/infiniband/core/roce_gid_mgmt.c
+++ b/drivers/infiniband/core/roce_gid_mgmt.c
@@ -437,6 +437,28 @@ static void callback_for_addr_gid_device_scan(struct ib_device *device,
&parsed->gid_attr);
}
+struct upper_list {
+ struct list_head list;
+ struct net_device *upper;
+};
+
+static int netdev_upper_walk(struct net_device *upper, void *data)
+{
+ struct upper_list *entry = kmalloc(sizeof(*entry), GFP_ATOMIC);
+ struct list_head *upper_list = (struct list_head *)data;
+
+ if (!entry) {
+ pr_info("roce_gid_mgmt: couldn't allocate entry to delete ndev\n");
+ return 0;
+ }
+
+ list_add_tail(&entry->list, upper_list);
+ dev_hold(upper);
+ entry->upper = upper;
+
+ return 0;
+}
+
static void handle_netdev_upper(struct ib_device *ib_dev, u8 port,
void *cookie,
void (*handle_netdev)(struct ib_device *ib_dev,
@@ -444,30 +466,12 @@ static void handle_netdev_upper(struct ib_device *ib_dev, u8 port,
struct net_device *ndev))
{
struct net_device *ndev = (struct net_device *)cookie;
- struct upper_list {
- struct list_head list;
- struct net_device *upper;
- };
- struct net_device *upper;
- struct list_head *iter;
struct upper_list *upper_iter;
struct upper_list *upper_temp;
LIST_HEAD(upper_list);
rcu_read_lock();
- netdev_for_each_all_upper_dev_rcu(ndev, upper, iter) {
- struct upper_list *entry = kmalloc(sizeof(*entry),
- GFP_ATOMIC);
-
- if (!entry) {
- pr_info("roce_gid_mgmt: couldn't allocate entry to delete ndev\n");
- continue;
- }
-
- list_add_tail(&entry->list, &upper_list);
- dev_hold(upper);
- entry->upper = upper;
- }
+ netdev_walk_all_upper_dev_rcu(ndev, netdev_upper_walk, &upper_list);
rcu_read_unlock();
handle_netdev(ib_dev, port, ndev);
--
2.1.4
^ permalink raw reply related
* [PATCH net-next 03/11] net: bonding: Flip to the new dev walk API
From: David Ahern @ 2016-10-12 20:51 UTC (permalink / raw)
To: jiri, netdev, davem
Cc: dledford, sean.hefty, hal.rosenstock, linux-rdma, j.vosburgh,
vfalico, andy, jeffrey.t.kirsher, intel-wired-lan, David Ahern
In-Reply-To: <1476305519-28833-1-git-send-email-dsa@cumulusnetworks.com>
Convert alb_send_learning_packets and bond_has_this_ip to use the new
netdev_walk_all_upper_dev_rcu API. In both cases this is just a move
to the new API; no functional change is intended.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
drivers/net/bonding/bond_alb.c | 82 ++++++++++++++++++++++++++---------------
drivers/net/bonding/bond_main.c | 21 +++++++----
2 files changed, 65 insertions(+), 38 deletions(-)
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 551f0f8dead3..1ddedec61900 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -950,13 +950,61 @@ static void alb_send_lp_vid(struct slave *slave, u8 mac_addr[],
dev_queue_xmit(skb);
}
+struct alb_walk_data {
+ struct bonding *bond;
+ struct slave *slave;
+ u8 *mac_addr;
+ bool strict_match;
+};
+
+static int alb_upper_dev_walk(struct net_device *upper, void *data)
+{
+ struct alb_walk_data *_data = (struct alb_walk_data *)data;
+ bool strict_match = _data->strict_match;
+ struct bonding *bond = _data->bond;
+ struct slave *slave = _data->slave;
+ u8 *mac_addr = _data->mac_addr;
+ struct bond_vlan_tag *tags;
+
+ if (is_vlan_dev(upper) && vlan_get_encap_level(upper) == 0) {
+ if (strict_match &&
+ ether_addr_equal_64bits(mac_addr,
+ upper->dev_addr)) {
+ alb_send_lp_vid(slave, mac_addr,
+ vlan_dev_vlan_proto(upper),
+ vlan_dev_vlan_id(upper));
+ } else if (!strict_match) {
+ alb_send_lp_vid(slave, upper->dev_addr,
+ vlan_dev_vlan_proto(upper),
+ vlan_dev_vlan_id(upper));
+ }
+ }
+
+ /* If this is a macvlan device, then only send updates
+ * when strict_match is turned off.
+ */
+ if (netif_is_macvlan(upper) && !strict_match) {
+ tags = bond_verify_device_path(bond->dev, upper, 0);
+ if (IS_ERR_OR_NULL(tags))
+ BUG();
+ alb_send_lp_vid(slave, upper->dev_addr,
+ tags[0].vlan_proto, tags[0].vlan_id);
+ kfree(tags);
+ }
+
+ return 0;
+}
+
static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[],
bool strict_match)
{
struct bonding *bond = bond_get_bond_by_slave(slave);
- struct net_device *upper;
- struct list_head *iter;
- struct bond_vlan_tag *tags;
+ struct alb_walk_data data = {
+ .strict_match = strict_match,
+ .mac_addr = mac_addr,
+ .slave = slave,
+ .bond = bond,
+ };
/* send untagged */
alb_send_lp_vid(slave, mac_addr, 0, 0);
@@ -965,33 +1013,7 @@ static void alb_send_learning_packets(struct slave *slave, u8 mac_addr[],
* for that device.
*/
rcu_read_lock();
- netdev_for_each_all_upper_dev_rcu(bond->dev, upper, iter) {
- if (is_vlan_dev(upper) && vlan_get_encap_level(upper) == 0) {
- if (strict_match &&
- ether_addr_equal_64bits(mac_addr,
- upper->dev_addr)) {
- alb_send_lp_vid(slave, mac_addr,
- vlan_dev_vlan_proto(upper),
- vlan_dev_vlan_id(upper));
- } else if (!strict_match) {
- alb_send_lp_vid(slave, upper->dev_addr,
- vlan_dev_vlan_proto(upper),
- vlan_dev_vlan_id(upper));
- }
- }
-
- /* If this is a macvlan device, then only send updates
- * when strict_match is turned off.
- */
- if (netif_is_macvlan(upper) && !strict_match) {
- tags = bond_verify_device_path(bond->dev, upper, 0);
- if (IS_ERR_OR_NULL(tags))
- BUG();
- alb_send_lp_vid(slave, upper->dev_addr,
- tags[0].vlan_proto, tags[0].vlan_id);
- kfree(tags);
- }
- }
+ netdev_walk_all_upper_dev_rcu(bond->dev, alb_upper_dev_walk, &data);
rcu_read_unlock();
}
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 3f31ca32f52b..2b4134d5e081 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2270,22 +2270,27 @@ static void bond_mii_monitor(struct work_struct *work)
}
}
+static int bond_upper_dev_walk(struct net_device *upper, void *data)
+{
+ __be32 ip = *((__be32 *)data);
+ int ret = 0;
+
+ if (ip == bond_confirm_addr(upper, 0, ip))
+ ret = 1;
+
+ return ret;
+}
+
static bool bond_has_this_ip(struct bonding *bond, __be32 ip)
{
- struct net_device *upper;
- struct list_head *iter;
bool ret = false;
if (ip == bond_confirm_addr(bond->dev, 0, ip))
return true;
rcu_read_lock();
- netdev_for_each_all_upper_dev_rcu(bond->dev, upper, iter) {
- if (ip == bond_confirm_addr(upper, 0, ip)) {
- ret = true;
- break;
- }
- }
+ if (netdev_walk_all_upper_dev_rcu(bond->dev, bond_upper_dev_walk, &ip))
+ ret = true;
rcu_read_unlock();
return ret;
--
2.1.4
^ permalink raw reply related
* [PATCH net-next 02/11] net: Introduce new api for walking upper and lower devices
From: David Ahern @ 2016-10-12 20:51 UTC (permalink / raw)
To: jiri, netdev, davem
Cc: dledford, sean.hefty, hal.rosenstock, linux-rdma, j.vosburgh,
vfalico, andy, jeffrey.t.kirsher, intel-wired-lan, David Ahern
In-Reply-To: <1476305519-28833-1-git-send-email-dsa@cumulusnetworks.com>
This patch introduces netdev_walk_all_upper_dev_rcu,
netdev_walk_all_lower_dev and netdev_walk_all_lower_dev_rcu. These
functions recursively walk the adj_list of devices to determine all upper
and lower devices.
The functions take a callback function that is invoked for each device
in the list. If the callback returns non-0, the walk is terminated and
the functions return that code back to callers.
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
include/linux/netdevice.h | 17 +++++
net/core/dev.c | 158 ++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 175 insertions(+)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 136ae6bbe81e..053f6f75f26a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3839,6 +3839,14 @@ struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
updev; \
updev = netdev_all_upper_get_next_dev_rcu(dev, &(iter)))
+int netdev_walk_all_upper_dev_rcu(struct net_device *dev,
+ int (*fn)(struct net_device *lower_dev,
+ void *data),
+ void *data);
+
+bool netdev_has_upper_dev_all_rcu(struct net_device *dev,
+ struct net_device *upper_dev);
+
void *netdev_lower_get_next_private(struct net_device *dev,
struct list_head **iter);
void *netdev_lower_get_next_private_rcu(struct net_device *dev,
@@ -3882,6 +3890,15 @@ struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev,
ldev; \
ldev = netdev_all_lower_get_next_rcu(dev, &(iter)))
+int netdev_walk_all_lower_dev(struct net_device *dev,
+ int (*fn)(struct net_device *lower_dev,
+ void *data),
+ void *data);
+int netdev_walk_all_lower_dev_rcu(struct net_device *dev,
+ int (*fn)(struct net_device *lower_dev,
+ void *data),
+ void *data);
+
void *netdev_adjacent_get_private(struct list_head *adj_list);
void *netdev_lower_get_first_private_rcu(struct net_device *dev);
struct net_device *netdev_master_upper_dev_get(struct net_device *dev);
diff --git a/net/core/dev.c b/net/core/dev.c
index 5aaa12a9e369..fcf3641db783 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5292,6 +5292,37 @@ bool netdev_has_upper_dev(struct net_device *dev,
EXPORT_SYMBOL(netdev_has_upper_dev);
/**
+ * netdev_has_upper_dev_all - Check if device is linked to an upper device
+ * @dev: device
+ * @upper_dev: upper device to check
+ *
+ * Find out if a device is linked to specified upper device and return true
+ * in case it is. Note that this checks the entire upper device chain.
+ * The caller must hold rcu lock.
+ */
+
+static int __netdev_has_upper_dev(struct net_device *upper_dev, void *data)
+{
+ struct net_device *dev = (struct net_device *)data;
+
+ if (upper_dev == dev)
+ return 1;
+
+ return 0;
+}
+
+bool netdev_has_upper_dev_all_rcu(struct net_device *dev,
+ struct net_device *upper_dev)
+{
+ if (netdev_walk_all_upper_dev_rcu(dev, __netdev_has_upper_dev,
+ upper_dev))
+ return true;
+
+ return false;
+}
+EXPORT_SYMBOL(netdev_has_upper_dev_all_rcu);
+
+/**
* netdev_has_any_upper_dev - Check if device is linked to some device
* @dev: device
*
@@ -5391,6 +5422,51 @@ struct net_device *netdev_all_upper_get_next_dev_rcu(struct net_device *dev,
}
EXPORT_SYMBOL(netdev_all_upper_get_next_dev_rcu);
+static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev,
+ struct list_head **iter)
+{
+ struct netdev_adjacent *upper;
+
+ WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held());
+
+ upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list);
+
+ if (&upper->list == &dev->adj_list.upper)
+ return NULL;
+
+ *iter = &upper->list;
+
+ return upper->dev;
+}
+
+int netdev_walk_all_upper_dev_rcu(struct net_device *dev,
+ int (*fn)(struct net_device *dev,
+ void *data),
+ void *data)
+{
+ struct list_head *iter;
+ struct net_device *udev;
+ int ret;
+
+ for (iter = &(dev)->adj_list.upper,
+ udev = netdev_next_upper_dev_rcu(dev, &(iter));
+ udev;
+ udev = netdev_next_upper_dev_rcu(dev, &(iter))) {
+ /* first is the upper device itself */
+ ret = fn(udev, data);
+ if (ret)
+ return ret;
+
+ /* then look at all of its upper devices */
+ ret = netdev_walk_all_upper_dev_rcu(udev, fn, data);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(netdev_walk_all_upper_dev_rcu);
+
/**
* netdev_lower_get_next_private - Get the next ->private from the
* lower neighbour list
@@ -5497,6 +5573,49 @@ struct net_device *netdev_all_lower_get_next(struct net_device *dev, struct list
}
EXPORT_SYMBOL(netdev_all_lower_get_next);
+static struct net_device *netdev_next_lower_dev(struct net_device *dev,
+ struct list_head **iter)
+{
+ struct netdev_adjacent *lower;
+
+ lower = list_entry(*iter, struct netdev_adjacent, list);
+
+ if (&lower->list == &dev->adj_list.lower)
+ return NULL;
+
+ *iter = lower->list.next;
+
+ return lower->dev;
+}
+
+int netdev_walk_all_lower_dev(struct net_device *dev,
+ int (*fn)(struct net_device *dev,
+ void *data),
+ void *data)
+{
+ struct list_head *iter;
+ struct net_device *ldev;
+ int ret;
+
+ for (iter = &(dev)->adj_list.lower,
+ ldev = netdev_next_lower_dev(dev, &(iter));
+ ldev;
+ ldev = netdev_next_lower_dev(dev, &(iter))) {
+ /* first is the lower device itself */
+ ret = fn(ldev, data);
+ if (ret)
+ return ret;
+
+ /* then look at all of its lower devices */
+ ret = netdev_walk_all_lower_dev(ldev, fn, data);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev);
+
/**
* netdev_all_lower_get_next_rcu - Get the next device from all
* lower neighbour list, RCU variant
@@ -5518,6 +5637,45 @@ struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev,
}
EXPORT_SYMBOL(netdev_all_lower_get_next_rcu);
+static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
+ struct list_head **iter)
+{
+ struct netdev_adjacent *lower;
+
+ lower = list_first_or_null_rcu(&dev->adj_list.lower,
+ struct netdev_adjacent, list);
+
+ return lower ? lower->dev : NULL;
+}
+
+int netdev_walk_all_lower_dev_rcu(struct net_device *dev,
+ int (*fn)(struct net_device *dev,
+ void *data),
+ void *data)
+{
+ struct list_head *iter;
+ struct net_device *ldev;
+ int ret;
+
+ for (iter = &(dev)->adj_list.lower,
+ ldev = netdev_next_lower_dev_rcu(dev, &(iter));
+ ldev;
+ ldev = netdev_next_lower_dev_rcu(dev, &(iter))) {
+ /* first is the lower device itself */
+ ret = fn(ldev, data);
+ if (ret)
+ return ret;
+
+ /* then look at all of its lower devices */
+ ret = netdev_walk_all_lower_dev_rcu(ldev, fn, data);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev_rcu);
+
/**
* netdev_lower_get_first_private_rcu - Get the first ->private from the
* lower neighbour list, RCU
--
2.1.4
^ permalink raw reply related
* [PATCH net-next 11/11] net: dev: Improve debug statements for adjacency tracking
From: David Ahern @ 2016-10-12 20:51 UTC (permalink / raw)
To: jiri-VPRAkNaXOzVWk0Htik3J/w, netdev-u79uwXL29TY76Z2rM5mHXA,
davem-fT/PcQaiUtIeIZ0/mPfg9Q
Cc: dledford-H+wXaHxf7aLQT0dZR+AlfA,
sean.hefty-ral2JQCrhuEAvxtiuMwx3w,
hal.rosenstock-Re5JQEeQqe8AvxtiuMwx3w,
linux-rdma-u79uwXL29TY76Z2rM5mHXA,
j.vosburgh-Re5JQEeQqe8AvxtiuMwx3w, vfalico-Re5JQEeQqe8AvxtiuMwx3w,
andy-QlMahl40kYEqcZcGjlUOXw,
jeffrey.t.kirsher-ral2JQCrhuEAvxtiuMwx3w,
intel-wired-lan-qjLDD68F18P21nG7glBr7A, David Ahern
In-Reply-To: <1476305519-28833-1-git-send-email-dsa-qUQiAmfTcIp+XZJcv9eMoEEOCMrvLtNR@public.gmane.org>
Adjacency code only has debugs for the insert case. Add debugs for
the remove path and make both consistently worded to make it easier
to follow the insert and removal with reference counts.
In addition, change the BUG to a WARN_ON. A missing adjacency at
removal time is not cause for a panic.
Signed-off-by: David Ahern <dsa-qUQiAmfTcIp+XZJcv9eMoEEOCMrvLtNR@public.gmane.org>
---
net/core/dev.c | 22 +++++++++++++++-------
1 file changed, 15 insertions(+), 7 deletions(-)
diff --git a/net/core/dev.c b/net/core/dev.c
index 52e70a3d61a4..ad5e7bfda403 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5700,6 +5700,9 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev,
if (adj) {
adj->ref_nr += 1;
+ pr_debug("Insert adjacency: dev %s adj_dev %s adj->ref_nr %d\n",
+ dev->name, adj_dev->name, adj->ref_nr);
+
return 0;
}
@@ -5713,8 +5716,8 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev,
adj->private = private;
dev_hold(adj_dev);
- pr_debug("dev_hold for %s, because of link added from %s to %s\n",
- adj_dev->name, dev->name, adj_dev->name);
+ pr_debug("Insert adjacency: dev %s adj_dev %s adj->ref_nr %d; dev_hold on %s\n",
+ dev->name, adj_dev->name, adj->ref_nr, adj_dev->name);
if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list)) {
ret = netdev_adjacent_sysfs_add(dev, adj_dev, dev_list);
@@ -5753,17 +5756,22 @@ static void __netdev_adjacent_dev_remove(struct net_device *dev,
{
struct netdev_adjacent *adj;
+ pr_debug("Remove adjacency: dev %s adj_dev %s ref_nr %d\n",
+ dev->name, adj_dev->name, ref_nr);
+
adj = __netdev_find_adj(adj_dev, dev_list);
if (!adj) {
- pr_err("tried to remove device %s from %s\n",
+ pr_err("Adjacency does not exist for device %s from %s\n",
dev->name, adj_dev->name);
- BUG();
+ WARN_ON(1);
+ return;
}
if (adj->ref_nr > ref_nr) {
- pr_debug("%s to %s ref_nr-%d = %d\n", dev->name, adj_dev->name,
- ref_nr, adj->ref_nr-ref_nr);
+ pr_debug("adjacency: %s to %s ref_nr - %d = %d\n",
+ dev->name, adj_dev->name, ref_nr,
+ adj->ref_nr - ref_nr);
adj->ref_nr -= ref_nr;
return;
}
@@ -5775,7 +5783,7 @@ static void __netdev_adjacent_dev_remove(struct net_device *dev,
netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list);
list_del_rcu(&adj->list);
- pr_debug("dev_put for %s, because link removed from %s to %s\n",
+ pr_debug("adjacency: dev_put for %s, because link removed from %s to %s\n",
adj_dev->name, dev->name, adj_dev->name);
dev_put(adj_dev);
kfree_rcu(adj, rcu);
--
2.1.4
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" 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 net-next 08/11] rocker: Flip to the new dev walk API
From: David Ahern @ 2016-10-12 20:51 UTC (permalink / raw)
To: jiri-VPRAkNaXOzVWk0Htik3J/w, netdev-u79uwXL29TY76Z2rM5mHXA,
davem-fT/PcQaiUtIeIZ0/mPfg9Q
Cc: dledford-H+wXaHxf7aLQT0dZR+AlfA,
sean.hefty-ral2JQCrhuEAvxtiuMwx3w,
hal.rosenstock-Re5JQEeQqe8AvxtiuMwx3w,
linux-rdma-u79uwXL29TY76Z2rM5mHXA,
j.vosburgh-Re5JQEeQqe8AvxtiuMwx3w, vfalico-Re5JQEeQqe8AvxtiuMwx3w,
andy-QlMahl40kYEqcZcGjlUOXw,
jeffrey.t.kirsher-ral2JQCrhuEAvxtiuMwx3w,
intel-wired-lan-qjLDD68F18P21nG7glBr7A, David Ahern
In-Reply-To: <1476305519-28833-1-git-send-email-dsa-qUQiAmfTcIp+XZJcv9eMoEEOCMrvLtNR@public.gmane.org>
Convert rocker to the new dev walk API. This is just a code conversion;
no functional change is intended.
Signed-off-by: David Ahern <dsa-qUQiAmfTcIp+XZJcv9eMoEEOCMrvLtNR@public.gmane.org>
---
drivers/net/ethernet/rocker/rocker_main.c | 31 ++++++++++++++++++++++++-------
1 file changed, 24 insertions(+), 7 deletions(-)
diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index 5424fb341613..9310adc0bcbb 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -2839,20 +2839,37 @@ static bool rocker_port_dev_check_under(const struct net_device *dev,
return true;
}
+struct rocker_walk_data {
+ struct rocker *rocker;
+ struct rocker_port *port;
+};
+
+static int rocker_lower_dev_walk(struct net_device *lower_dev, void *_data)
+{
+ struct rocker_walk_data *data = (struct rocker_walk_data *)_data;
+ int ret = 0;
+
+ if (rocker_port_dev_check_under(lower_dev, data->rocker)) {
+ data->port = netdev_priv(lower_dev);
+ ret = 1;
+ }
+
+ return ret;
+}
+
struct rocker_port *rocker_port_dev_lower_find(struct net_device *dev,
struct rocker *rocker)
{
- struct net_device *lower_dev;
- struct list_head *iter;
+ struct rocker_walk_data data;
if (rocker_port_dev_check_under(dev, rocker))
return netdev_priv(dev);
- netdev_for_each_all_lower_dev(dev, lower_dev, iter) {
- if (rocker_port_dev_check_under(lower_dev, rocker))
- return netdev_priv(lower_dev);
- }
- return NULL;
+ data.rocker = rocker;
+ data.port = NULL;
+ netdev_walk_all_lower_dev(dev, rocker_lower_dev_walk, &data);
+
+ return data.port;
}
static int rocker_netdevice_event(struct notifier_block *unused,
--
2.1.4
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" 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 net-next 05/11] IB/ipoib: Flip to new dev walk API
From: David Ahern @ 2016-10-12 20:51 UTC (permalink / raw)
To: jiri-VPRAkNaXOzVWk0Htik3J/w, netdev-u79uwXL29TY76Z2rM5mHXA,
davem-fT/PcQaiUtIeIZ0/mPfg9Q
Cc: dledford-H+wXaHxf7aLQT0dZR+AlfA,
sean.hefty-ral2JQCrhuEAvxtiuMwx3w,
hal.rosenstock-Re5JQEeQqe8AvxtiuMwx3w,
linux-rdma-u79uwXL29TY76Z2rM5mHXA,
j.vosburgh-Re5JQEeQqe8AvxtiuMwx3w, vfalico-Re5JQEeQqe8AvxtiuMwx3w,
andy-QlMahl40kYEqcZcGjlUOXw,
jeffrey.t.kirsher-ral2JQCrhuEAvxtiuMwx3w,
intel-wired-lan-qjLDD68F18P21nG7glBr7A, David Ahern
In-Reply-To: <1476305519-28833-1-git-send-email-dsa-qUQiAmfTcIp+XZJcv9eMoEEOCMrvLtNR@public.gmane.org>
Convert ipoib_get_net_dev_match_addr to the new upper device walk API.
This is just a move to the new API; no functional change is intended.
Signed-off-by: David Ahern <dsa-qUQiAmfTcIp+XZJcv9eMoEEOCMrvLtNR@public.gmane.org>
---
drivers/infiniband/ulp/ipoib/ipoib_main.c | 37 +++++++++++++++++++++----------
1 file changed, 25 insertions(+), 12 deletions(-)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 5636fc3da6b8..624855ab7205 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -292,6 +292,25 @@ static struct net_device *ipoib_get_master_net_dev(struct net_device *dev)
return dev;
}
+struct ipoib_walk_data {
+ const struct sockaddr *addr;
+ struct net_device *result;
+};
+
+static int ipoib_upper_walk(struct net_device *upper, void *_data)
+{
+ struct ipoib_walk_data *data = (struct ipoib_walk_data *)_data;
+ int ret = 0;
+
+ if (ipoib_is_dev_match_addr_rcu(data->addr, upper)) {
+ dev_hold(upper);
+ data->result = upper;
+ ret = 1;
+ }
+
+ return ret;
+}
+
/**
* Find a net_device matching the given address, which is an upper device of
* the given net_device.
@@ -304,27 +323,21 @@ static struct net_device *ipoib_get_master_net_dev(struct net_device *dev)
static struct net_device *ipoib_get_net_dev_match_addr(
const struct sockaddr *addr, struct net_device *dev)
{
- struct net_device *upper,
- *result = NULL;
- struct list_head *iter;
+ struct ipoib_walk_data data = {
+ .addr = addr,
+ };
rcu_read_lock();
if (ipoib_is_dev_match_addr_rcu(addr, dev)) {
dev_hold(dev);
- result = dev;
+ data.result = dev;
goto out;
}
- netdev_for_each_all_upper_dev_rcu(dev, upper, iter) {
- if (ipoib_is_dev_match_addr_rcu(addr, upper)) {
- dev_hold(upper);
- result = upper;
- break;
- }
- }
+ netdev_walk_all_upper_dev_rcu(dev, ipoib_upper_walk, &data);
out:
rcu_read_unlock();
- return result;
+ return data.result;
}
/* returns the number of IPoIB netdevs on top a given ipoib device matching a
--
2.1.4
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" 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 net-next 01/11] net: Remove refnr arg when inserting link adjacencies
From: David Ahern @ 2016-10-12 20:51 UTC (permalink / raw)
To: jiri-VPRAkNaXOzVWk0Htik3J/w, netdev-u79uwXL29TY76Z2rM5mHXA,
davem-fT/PcQaiUtIeIZ0/mPfg9Q
Cc: dledford-H+wXaHxf7aLQT0dZR+AlfA,
sean.hefty-ral2JQCrhuEAvxtiuMwx3w,
hal.rosenstock-Re5JQEeQqe8AvxtiuMwx3w,
linux-rdma-u79uwXL29TY76Z2rM5mHXA,
j.vosburgh-Re5JQEeQqe8AvxtiuMwx3w, vfalico-Re5JQEeQqe8AvxtiuMwx3w,
andy-QlMahl40kYEqcZcGjlUOXw,
jeffrey.t.kirsher-ral2JQCrhuEAvxtiuMwx3w,
intel-wired-lan-qjLDD68F18P21nG7glBr7A, David Ahern
In-Reply-To: <1476305519-28833-1-git-send-email-dsa-qUQiAmfTcIp+XZJcv9eMoEEOCMrvLtNR@public.gmane.org>
Commit 93409033ae65 ("net: Add netdev all_adj_list refcnt propagation to
fix panic") propagated the refnr to insert and remove functions tracking
the netdev adjacency graph. However, for the insert path the refnr can
only be 1. Accordingly, remove the refnr argument to make that clear.
ie., the refnr arg in 93409033ae65 was only needed for the remove path.
Signed-off-by: David Ahern <dsa-qUQiAmfTcIp+XZJcv9eMoEEOCMrvLtNR@public.gmane.org>
---
net/core/dev.c | 27 ++++++++++++---------------
1 file changed, 12 insertions(+), 15 deletions(-)
diff --git a/net/core/dev.c b/net/core/dev.c
index f1fe26f66458..5aaa12a9e369 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5589,7 +5589,6 @@ static inline bool netdev_adjacent_is_neigh_list(struct net_device *dev,
static int __netdev_adjacent_dev_insert(struct net_device *dev,
struct net_device *adj_dev,
- u16 ref_nr,
struct list_head *dev_list,
void *private, bool master)
{
@@ -5599,7 +5598,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev,
adj = __netdev_find_adj(adj_dev, dev_list);
if (adj) {
- adj->ref_nr += ref_nr;
+ adj->ref_nr += 1;
return 0;
}
@@ -5609,7 +5608,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev,
adj->dev = adj_dev;
adj->master = master;
- adj->ref_nr = ref_nr;
+ adj->ref_nr = 1;
adj->private = private;
dev_hold(adj_dev);
@@ -5683,22 +5682,21 @@ static void __netdev_adjacent_dev_remove(struct net_device *dev,
static int __netdev_adjacent_dev_link_lists(struct net_device *dev,
struct net_device *upper_dev,
- u16 ref_nr,
struct list_head *up_list,
struct list_head *down_list,
void *private, bool master)
{
int ret;
- ret = __netdev_adjacent_dev_insert(dev, upper_dev, ref_nr, up_list,
+ ret = __netdev_adjacent_dev_insert(dev, upper_dev, up_list,
private, master);
if (ret)
return ret;
- ret = __netdev_adjacent_dev_insert(upper_dev, dev, ref_nr, down_list,
+ ret = __netdev_adjacent_dev_insert(upper_dev, dev, down_list,
private, false);
if (ret) {
- __netdev_adjacent_dev_remove(dev, upper_dev, ref_nr, up_list);
+ __netdev_adjacent_dev_remove(dev, upper_dev, 1, up_list);
return ret;
}
@@ -5706,10 +5704,9 @@ static int __netdev_adjacent_dev_link_lists(struct net_device *dev,
}
static int __netdev_adjacent_dev_link(struct net_device *dev,
- struct net_device *upper_dev,
- u16 ref_nr)
+ struct net_device *upper_dev)
{
- return __netdev_adjacent_dev_link_lists(dev, upper_dev, ref_nr,
+ return __netdev_adjacent_dev_link_lists(dev, upper_dev,
&dev->all_adj_list.upper,
&upper_dev->all_adj_list.lower,
NULL, false);
@@ -5738,12 +5735,12 @@ static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev,
struct net_device *upper_dev,
void *private, bool master)
{
- int ret = __netdev_adjacent_dev_link(dev, upper_dev, 1);
+ int ret = __netdev_adjacent_dev_link(dev, upper_dev);
if (ret)
return ret;
- ret = __netdev_adjacent_dev_link_lists(dev, upper_dev, 1,
+ ret = __netdev_adjacent_dev_link_lists(dev, upper_dev,
&dev->adj_list.upper,
&upper_dev->adj_list.lower,
private, master);
@@ -5812,7 +5809,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
list_for_each_entry(j, &upper_dev->all_adj_list.upper, list) {
pr_debug("Interlinking %s with %s, non-neighbour\n",
i->dev->name, j->dev->name);
- ret = __netdev_adjacent_dev_link(i->dev, j->dev, i->ref_nr);
+ ret = __netdev_adjacent_dev_link(i->dev, j->dev);
if (ret)
goto rollback_mesh;
}
@@ -5822,7 +5819,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
list_for_each_entry(i, &upper_dev->all_adj_list.upper, list) {
pr_debug("linking %s's upper device %s with %s\n",
upper_dev->name, i->dev->name, dev->name);
- ret = __netdev_adjacent_dev_link(dev, i->dev, i->ref_nr);
+ ret = __netdev_adjacent_dev_link(dev, i->dev);
if (ret)
goto rollback_upper_mesh;
}
@@ -5831,7 +5828,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
list_for_each_entry(i, &dev->all_adj_list.lower, list) {
pr_debug("linking %s's lower device %s with %s\n", dev->name,
i->dev->name, upper_dev->name);
- ret = __netdev_adjacent_dev_link(i->dev, upper_dev, i->ref_nr);
+ ret = __netdev_adjacent_dev_link(i->dev, upper_dev);
if (ret)
goto rollback_lower_mesh;
}
--
2.1.4
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" 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 net-next 00/11] net: Fix netdev adjacency tracking
From: David Ahern @ 2016-10-12 20:51 UTC (permalink / raw)
To: jiri-VPRAkNaXOzVWk0Htik3J/w, netdev-u79uwXL29TY76Z2rM5mHXA,
davem-fT/PcQaiUtIeIZ0/mPfg9Q
Cc: dledford-H+wXaHxf7aLQT0dZR+AlfA,
sean.hefty-ral2JQCrhuEAvxtiuMwx3w,
hal.rosenstock-Re5JQEeQqe8AvxtiuMwx3w,
linux-rdma-u79uwXL29TY76Z2rM5mHXA,
j.vosburgh-Re5JQEeQqe8AvxtiuMwx3w, vfalico-Re5JQEeQqe8AvxtiuMwx3w,
andy-QlMahl40kYEqcZcGjlUOXw,
jeffrey.t.kirsher-ral2JQCrhuEAvxtiuMwx3w,
intel-wired-lan-qjLDD68F18P21nG7glBr7A, David Ahern
The netdev adjacency tracking is failing to create proper dependencies
for some topologies. For example this topology
+--------+
| myvrf |
+--------+
| |
| +---------+
| | macvlan |
| +---------+
| |
+----------+
| bridge |
+----------+
|
+--------+
| bond0 |
+--------+
|
+--------+
| eth3 |
+--------+
hits 1 of 2 problems depending on the order of enslavement. The base set of
commands for both cases:
ip link add bond1 type bond
ip link set bond1 up
ip link set eth3 down
ip link set eth3 master bond1
ip link set eth3 up
ip link add bridge type bridge
ip link set bridge up
ip link add macvlan link bridge type macvlan
ip link set macvlan up
ip link add myvrf type vrf table 1234
ip link set myvrf up
ip link set bridge master myvrf
Case 1 enslave macvlan to the vrf before enslaving the bond to the bridge:
ip link set macvlan master myvrf
ip link set bond1 master bridge
Attempts to delete the VRF:
ip link delete myvrf
trigger the BUG in __netdev_adjacent_dev_remove:
[ 587.405260] tried to remove device eth3 from myvrf
[ 587.407269] ------------[ cut here ]------------
[ 587.408918] kernel BUG at /home/dsa/kernel.git/net/core/dev.c:5661!
[ 587.411113] invalid opcode: 0000 [#1] SMP
[ 587.412454] Modules linked in: macvlan bridge stp llc bonding vrf
[ 587.414765] CPU: 0 PID: 726 Comm: ip Not tainted 4.8.0+ #109
[ 587.416766] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014
[ 587.420241] task: ffff88013ab6eec0 task.stack: ffffc90000628000
[ 587.422163] RIP: 0010:[<ffffffff813cef03>] [<ffffffff813cef03>] __netdev_adjacent_dev_remove+0x40/0x12c
...
[ 587.446053] Call Trace:
[ 587.446424] [<ffffffff813d1542>] __netdev_adjacent_dev_unlink+0x20/0x3c
[ 587.447390] [<ffffffff813d16a3>] netdev_upper_dev_unlink+0xfa/0x15e
[ 587.448297] [<ffffffffa00003a3>] vrf_del_slave+0x13/0x2a [vrf]
[ 587.449153] [<ffffffffa00004a4>] vrf_dev_uninit+0xea/0x114 [vrf]
[ 587.450036] [<ffffffff813d19b0>] rollback_registered_many+0x22b/0x2da
[ 587.450974] [<ffffffff813d1aac>] unregister_netdevice_many+0x17/0x48
[ 587.451903] [<ffffffff813de444>] rtnl_delete_link+0x3c/0x43
[ 587.452719] [<ffffffff813dedcd>] rtnl_dellink+0x180/0x194
When the BUG is converted to a WARN_ON it shows 4 missing adjacencies:
eth3 - myvrf, mvrf - eth3, bond1 - myvrf and myvrf - bond1
All of those are because the __netdev_upper_dev_link function does not
properly link macvlan lower devices to myvrf when it is enslaved.
The second case just flips the ordering of the enslavements:
ip link set bond1 master bridge
ip link set macvlan master myvrf
Then run:
ip link delete bond1
ip link delete myvrf
The vrf delete command hangs because myvrf has a reference that has not
been released. In this case the removal code does not account for 2 paths
between eth3 and myvrf - one from bridge to vrf and the other through the
macvlan.
Rather than try to maintain a linked list of all upper and lower devices
per netdevice, only track the direct neighbors. The remaining stack can
be determined by recursively walking the neighbors.
The existing netdev_for_each_all_upper_dev_rcu,
netdev_for_each_all_lower_dev and netdev_for_each_all_lower_dev_rcu macros
are replaced with APIs that walk the upper and lower device lists. The
new APIs take a callback function and a data arg that is passed to the
callback for each device in the list. Drivers using the old macros are
converted in separate patches to make it easier on reviewers. It is an
API conversion only; no functional change is intended.
DaveM: Given the impact of this bug (both cases requiring a reboot) I
would like to get this backported to at least the 4.8 tree which as I
understand it has been targeted as the next LTS.
David Ahern (11):
net: Remove refnr arg when inserting link adjacencies
net: Introduce new api for walking upper and lower devices
net: bonding: Flip to the new dev walk API
IB/core: Flip to the new dev walk API
IB/ipoib: Flip to new dev walk API
ixgbe: Flip to the new dev walk API
mlxsw: Flip to the new dev walk API
rocker: Flip to the new dev walk API
net: Remove all_adj_list and its references
net: Add warning if any lower device is still in adjacency list
net: dev: Improve debug statements for adjacency tracking
drivers/infiniband/core/core_priv.h | 9 +-
drivers/infiniband/core/roce_gid_mgmt.c | 42 +--
drivers/infiniband/ulp/ipoib/ipoib_main.c | 37 ++-
drivers/net/bonding/bond_alb.c | 82 +++---
drivers/net/bonding/bond_main.c | 21 +-
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 132 ++++++----
drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 37 ++-
drivers/net/ethernet/rocker/rocker_main.c | 31 ++-
include/linux/netdevice.h | 38 ++-
net/core/dev.c | 349 ++++++++++++-------------
10 files changed, 428 insertions(+), 350 deletions(-)
--
2.1.4
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" 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
* [PATCH] net: ipv4: Do not drop to make_route if oif is l3mdev
From: David Ahern @ 2016-10-12 20:20 UTC (permalink / raw)
To: netdev; +Cc: David Ahern
Commit e0d56fdd7342 was a bit aggressive removing l3mdev calls in
the IPv4 stack. If the fib_lookup fails we do not want to drop to
make_route if the oif is an l3mdev device.
Also reverts 19664c6a0009 ("net: l3mdev: Remove netif_index_is_l3_master")
which removed netif_index_is_l3_master.
Fixes: e0d56fdd7342 ("net: l3mdev: remove redundant calls")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
include/net/l3mdev.h | 24 ++++++++++++++++++++++++
net/ipv4/route.c | 3 ++-
2 files changed, 26 insertions(+), 1 deletion(-)
diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h
index b220dabeab45..3832099289c5 100644
--- a/include/net/l3mdev.h
+++ b/include/net/l3mdev.h
@@ -114,6 +114,25 @@ static inline u32 l3mdev_fib_table(const struct net_device *dev)
return tb_id;
}
+static inline bool netif_index_is_l3_master(struct net *net, int ifindex)
+{
+ struct net_device *dev;
+ bool rc = false;
+
+ if (ifindex == 0)
+ return false;
+
+ rcu_read_lock();
+
+ dev = dev_get_by_index_rcu(net, ifindex);
+ if (dev)
+ rc = netif_is_l3_master(dev);
+
+ rcu_read_unlock();
+
+ return rc;
+}
+
struct dst_entry *l3mdev_link_scope_lookup(struct net *net, struct flowi6 *fl6);
static inline
@@ -207,6 +226,11 @@ static inline u32 l3mdev_fib_table_by_index(struct net *net, int ifindex)
return 0;
}
+static inline bool netif_index_is_l3_master(struct net *net, int ifindex)
+{
+ return false;
+}
+
static inline
struct dst_entry *l3mdev_link_scope_lookup(struct net *net, struct flowi6 *fl6)
{
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index f2be689a6c85..62d4d90c1389 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2265,7 +2265,8 @@ struct rtable *__ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
if (err) {
res.fi = NULL;
res.table = NULL;
- if (fl4->flowi4_oif) {
+ if (fl4->flowi4_oif &&
+ !netif_index_is_l3_master(net, fl4->flowi4_oif)) {
/* Apparently, routing tables are wrong. Assume,
that the destination is on link.
--
2.1.4
^ permalink raw reply related
* [PATCH net-next] net: phy: Trigger state machine on state change and not polling.
From: Andrew Lunn @ 2016-10-12 20:14 UTC (permalink / raw)
To: David Miller; +Cc: netdev, Florian Fainelli, Andrew Lunn, Kyle Roeschley
The phy_start() is used to indicate the PHY is now ready to do its
work. The state is changed, normally to PHY_UP which means that both
the MAC and the PHY are ready.
If the phy driver is using polling, when the next poll happens, the
state machine notices the PHY is now in PHY_UP, and kicks off
auto-negotiation, if needed.
If however, the PHY is using interrupts, there is no polling. The phy
is stuck in PHY_UP until the next interrupt comes along. And there is
no reason for the PHY to interrupt.
Have phy_start() schedule the state machine to run, which both speeds
up the polling use case, and makes the interrupt use case actually
work.
This problems exists whenever there is a state change which will not
cause an interrupt. Trigger the state machine in these cases,
e.g. phy_error().
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Cc: Kyle Roeschley <kyle.roeschley@ni.com>
---
This should be applied to stable, but i've no idea what fixes: tag to
use. It could be phylib has been broken since interrupts were added?
drivers/net/phy/phy.c | 22 ++++++++++++++++++++--
1 file changed, 20 insertions(+), 2 deletions(-)
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index c6f66832a1a6..f424b867f73e 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -608,6 +608,21 @@ void phy_start_machine(struct phy_device *phydev)
}
/**
+ * phy_trigger_machine - trigger the state machine to run
+ *
+ * @phydev: the phy_device struct
+ *
+ * Description: There has been a change in state which requires that the
+ * state machine runs.
+ */
+
+static void phy_trigger_machine(struct phy_device *phydev)
+{
+ cancel_delayed_work_sync(&phydev->state_queue);
+ queue_delayed_work(system_power_efficient_wq, &phydev->state_queue, 0);
+}
+
+/**
* phy_stop_machine - stop the PHY state machine tracking
* @phydev: target phy_device struct
*
@@ -639,6 +654,8 @@ static void phy_error(struct phy_device *phydev)
mutex_lock(&phydev->lock);
phydev->state = PHY_HALTED;
mutex_unlock(&phydev->lock);
+
+ phy_trigger_machine(phydev);
}
/**
@@ -800,8 +817,7 @@ void phy_change(struct work_struct *work)
}
/* reschedule state queue work to run as soon as possible */
- cancel_delayed_work_sync(&phydev->state_queue);
- queue_delayed_work(system_power_efficient_wq, &phydev->state_queue, 0);
+ phy_trigger_machine(phydev);
return;
ignore:
@@ -890,6 +906,8 @@ void phy_start(struct phy_device *phydev)
/* if phy was suspended, bring the physical link up again */
if (do_resume)
phy_resume(phydev);
+
+ phy_trigger_machine(phydev);
}
EXPORT_SYMBOL(phy_start);
--
2.9.3
^ 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