* [PATCH net-next v5 5/9] net: fix raw socket lookup device bind matching with VRFs
From: Mike Manning @ 2018-11-07 15:36 UTC (permalink / raw)
To: netdev; +Cc: Duncan Eastoe
In-Reply-To: <20181107153610.7526-1-mmanning@vyatta.att-mail.com>
From: Duncan Eastoe <deastoe@vyatta.att-mail.com>
When there exist a pair of raw sockets one unbound and one bound
to a VRF but equal in all other respects, when a packet is received
in the VRF context, __raw_v4_lookup() matches on both sockets.
This results in the packet being delivered over both sockets,
instead of only the raw socket bound to the VRF. The bound device
checks in __raw_v4_lookup() are replaced with a call to
raw_sk_bound_dev_eq() which correctly handles whether the packet
should be delivered over the unbound socket in such cases.
In __raw_v6_lookup() the match on the device binding of the socket is
similarly updated to use raw_sk_bound_dev_eq() which matches the
handling in __raw_v4_lookup().
Importantly raw_sk_bound_dev_eq() takes the raw_l3mdev_accept sysctl
into account.
Signed-off-by: Duncan Eastoe <deastoe@vyatta.att-mail.com>
Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com>
---
include/net/raw.h | 13 ++++++++++++-
net/ipv4/raw.c | 3 +--
net/ipv6/raw.c | 5 ++---
3 files changed, 15 insertions(+), 6 deletions(-)
diff --git a/include/net/raw.h b/include/net/raw.h
index 20ebf0b3dfa8..821ff4887f77 100644
--- a/include/net/raw.h
+++ b/include/net/raw.h
@@ -17,7 +17,7 @@
#ifndef _RAW_H
#define _RAW_H
-
+#include <net/inet_sock.h>
#include <net/protocol.h>
#include <linux/icmp.h>
@@ -75,4 +75,15 @@ static inline struct raw_sock *raw_sk(const struct sock *sk)
return (struct raw_sock *)sk;
}
+static inline bool raw_sk_bound_dev_eq(struct net *net, int bound_dev_if,
+ int dif, int sdif)
+{
+#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
+ return inet_bound_dev_eq(!!net->ipv4.sysctl_raw_l3mdev_accept,
+ bound_dev_if, dif, sdif);
+#else
+ return inet_bound_dev_eq(true, bound_dev_if, dif, sdif);
+#endif
+}
+
#endif /* _RAW_H */
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 1ebd29abe79c..fb1f02015a15 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -131,8 +131,7 @@ struct sock *__raw_v4_lookup(struct net *net, struct sock *sk,
if (net_eq(sock_net(sk), net) && inet->inet_num == num &&
!(inet->inet_daddr && inet->inet_daddr != raddr) &&
!(inet->inet_rcv_saddr && inet->inet_rcv_saddr != laddr) &&
- !(sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif &&
- sk->sk_bound_dev_if != sdif))
+ raw_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif))
goto found; /* gotcha */
}
sk = NULL;
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 5e0efd3954e9..aed7eb5c2123 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -86,9 +86,8 @@ struct sock *__raw_v6_lookup(struct net *net, struct sock *sk,
!ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr))
continue;
- if (sk->sk_bound_dev_if &&
- sk->sk_bound_dev_if != dif &&
- sk->sk_bound_dev_if != sdif)
+ if (!raw_sk_bound_dev_eq(net, sk->sk_bound_dev_if,
+ dif, sdif))
continue;
if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
--
2.11.0
^ permalink raw reply related
* [PATCH net-next v5 9/9] ipv6: do not drop vrf udp multicast packets
From: Mike Manning @ 2018-11-07 15:36 UTC (permalink / raw)
To: netdev; +Cc: Dewi Morgan
In-Reply-To: <20181107153610.7526-1-mmanning@vyatta.att-mail.com>
From: Dewi Morgan <morgand@vyatta.att-mail.com>
For bound udp sockets in a vrf, also check the sdif to get the index
for ingress devices enslaved to an l3mdev.
Signed-off-by: Dewi Morgan <morgand@vyatta.att-mail.com>
Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com>
---
net/ipv6/udp.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 895fa77bde90..a905bf9ed906 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -637,7 +637,7 @@ static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk,
__be16 loc_port, const struct in6_addr *loc_addr,
__be16 rmt_port, const struct in6_addr *rmt_addr,
- int dif, unsigned short hnum)
+ int dif, int sdif, unsigned short hnum)
{
struct inet_sock *inet = inet_sk(sk);
@@ -649,7 +649,7 @@ static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk,
(inet->inet_dport && inet->inet_dport != rmt_port) ||
(!ipv6_addr_any(&sk->sk_v6_daddr) &&
!ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) ||
- (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) ||
+ !udp_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif) ||
(!ipv6_addr_any(&sk->sk_v6_rcv_saddr) &&
!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)))
return false;
@@ -683,6 +683,7 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
unsigned int offset = offsetof(typeof(*sk), sk_node);
unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10);
int dif = inet6_iif(skb);
+ int sdif = inet6_sdif(skb);
struct hlist_node *node;
struct sk_buff *nskb;
@@ -697,7 +698,8 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
sk_for_each_entry_offset_rcu(sk, node, &hslot->head, offset) {
if (!__udp_v6_is_mcast_sock(net, sk, uh->dest, daddr,
- uh->source, saddr, dif, hnum))
+ uh->source, saddr, dif, sdif,
+ hnum))
continue;
/* If zero checksum and no_check is not on for
* the socket then skip it.
--
2.11.0
^ permalink raw reply related
* [PATCH net-next v5 4/9] net: provide a sysctl raw_l3mdev_accept for raw socket lookup with VRFs
From: Mike Manning @ 2018-11-07 15:36 UTC (permalink / raw)
To: netdev
In-Reply-To: <20181107153610.7526-1-mmanning@vyatta.att-mail.com>
Add a sysctl raw_l3mdev_accept to control raw socket lookup in a manner
similar to use of tcp_l3mdev_accept for stream and of udp_l3mdev_accept
for datagram sockets. Have this default to enabled for reasons of
backwards compatibility. This is so as to specify the output device
with cmsg and IP_PKTINFO, but using a socket not bound to the
corresponding VRF. This allows e.g. older ping implementations to be
run with specifying the device but without executing it in the VRF.
If the option is disabled, packets received in a VRF context are only
handled by a raw socket bound to the VRF, and correspondingly packets
in the default VRF are only handled by a socket not bound to any VRF.
Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com>
---
Documentation/networking/ip-sysctl.txt | 12 ++++++++++++
Documentation/networking/vrf.txt | 13 +++++++++++++
include/net/netns/ipv4.h | 3 +++
include/net/raw.h | 1 +
net/ipv4/af_inet.c | 2 ++
net/ipv4/raw.c | 28 ++++++++++++++++++++++++++--
net/ipv4/sysctl_net_ipv4.c | 11 +++++++++++
7 files changed, 68 insertions(+), 2 deletions(-)
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 163b5ff1073c..e0e72e2ff6b2 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -359,6 +359,7 @@ tcp_l3mdev_accept - BOOLEAN
derived from the listen socket to be bound to the L3 domain in
which the packets originated. Only valid when the kernel was
compiled with CONFIG_NET_L3_MASTER_DEV.
+ Default: 0 (disabled)
tcp_low_latency - BOOLEAN
This is a legacy option, it has no effect anymore.
@@ -762,6 +763,7 @@ udp_l3mdev_accept - BOOLEAN
being received regardless of the L3 domain in which they
originated. Only valid when the kernel was compiled with
CONFIG_NET_L3_MASTER_DEV.
+ Default: 0 (disabled)
udp_mem - vector of 3 INTEGERs: min, pressure, max
Number of pages allowed for queueing by all UDP sockets.
@@ -788,6 +790,16 @@ udp_wmem_min - INTEGER
total pages of UDP sockets exceed udp_mem pressure. The unit is byte.
Default: 4K
+RAW variables:
+
+raw_l3mdev_accept - BOOLEAN
+ Enabling this option allows a "global" bound socket to work
+ across L3 master domains (e.g., VRFs) with packets capable of
+ being received regardless of the L3 domain in which they
+ originated. Only valid when the kernel was compiled with
+ CONFIG_NET_L3_MASTER_DEV.
+ Default: 1 (enabled)
+
CIPSOv4 Variables:
cipso_cache_enable - BOOLEAN
diff --git a/Documentation/networking/vrf.txt b/Documentation/networking/vrf.txt
index d4b129402d57..a5f103b083a0 100644
--- a/Documentation/networking/vrf.txt
+++ b/Documentation/networking/vrf.txt
@@ -111,9 +111,22 @@ the same port if they bind to an l3mdev.
TCP & UDP services running in the default VRF context (ie., not bound
to any VRF device) can work across all VRF domains by enabling the
tcp_l3mdev_accept and udp_l3mdev_accept sysctl options:
+
sysctl -w net.ipv4.tcp_l3mdev_accept=1
sysctl -w net.ipv4.udp_l3mdev_accept=1
+These options are disabled by default so that a socket in a VRF is only
+selected for packets in that VRF. There is a similar option for RAW
+sockets, which is enabled by default for reasons of backwards compatibility.
+This is so as to specify the output device with cmsg and IP_PKTINFO, but
+using a socket not bound to the corresponding VRF. This allows e.g. older ping
+implementations to be run with specifying the device but without executing it
+in the VRF. This option can be disabled so that packets received in a VRF
+context are only handled by a raw socket bound to the VRF, and packets in the
+default VRF are only handled by a socket not bound to any VRF:
+
+ sysctl -w net.ipv4.raw_l3mdev_accept=0
+
netfilter rules on the VRF device can be used to limit access to services
running in the default VRF context as well.
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index e47503b4e4d1..104a6669e344 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -103,6 +103,9 @@ struct netns_ipv4 {
/* Shall we try to damage output packets if routing dev changes? */
int sysctl_ip_dynaddr;
int sysctl_ip_early_demux;
+#ifdef CONFIG_NET_L3_MASTER_DEV
+ int sysctl_raw_l3mdev_accept;
+#endif
int sysctl_tcp_early_demux;
int sysctl_udp_early_demux;
diff --git a/include/net/raw.h b/include/net/raw.h
index 9c9fa98a91a4..20ebf0b3dfa8 100644
--- a/include/net/raw.h
+++ b/include/net/raw.h
@@ -61,6 +61,7 @@ void raw_seq_stop(struct seq_file *seq, void *v);
int raw_hash_sk(struct sock *sk);
void raw_unhash_sk(struct sock *sk);
+void raw_init(void);
struct raw_sock {
/* inet_sock has to be the first member */
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 1fbe2f815474..07749c5b0a50 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1964,6 +1964,8 @@ static int __init inet_init(void)
/* Add UDP-Lite (RFC 3828) */
udplite4_register();
+ raw_init();
+
ping_init();
/*
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 8ca3eb06ba04..1ebd29abe79c 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -805,7 +805,7 @@ static int raw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
return copied;
}
-static int raw_init(struct sock *sk)
+static int raw_sk_init(struct sock *sk)
{
struct raw_sock *rp = raw_sk(sk);
@@ -970,7 +970,7 @@ struct proto raw_prot = {
.connect = ip4_datagram_connect,
.disconnect = __udp_disconnect,
.ioctl = raw_ioctl,
- .init = raw_init,
+ .init = raw_sk_init,
.setsockopt = raw_setsockopt,
.getsockopt = raw_getsockopt,
.sendmsg = raw_sendmsg,
@@ -1133,4 +1133,28 @@ void __init raw_proc_exit(void)
{
unregister_pernet_subsys(&raw_net_ops);
}
+
+static void raw_sysctl_init_net(struct net *net)
+{
+#ifdef CONFIG_NET_L3_MASTER_DEV
+ net->ipv4.sysctl_raw_l3mdev_accept = 1;
+#endif
+}
+
+static int __net_init raw_sysctl_init(struct net *net)
+{
+ raw_sysctl_init_net(net);
+ return 0;
+}
+
+static struct pernet_operations __net_initdata raw_sysctl_ops = {
+ .init = raw_sysctl_init,
+};
+
+void __init raw_init(void)
+{
+ raw_sysctl_init_net(&init_net);
+ if (register_pernet_subsys(&raw_sysctl_ops))
+ panic("RAW: failed to init sysctl parameters.\n");
+}
#endif /* CONFIG_PROC_FS */
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 891ed2f91467..ba0fc4b18465 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -602,6 +602,17 @@ static struct ctl_table ipv4_net_table[] = {
.mode = 0644,
.proc_handler = ipv4_ping_group_range,
},
+#ifdef CONFIG_NET_L3_MASTER_DEV
+ {
+ .procname = "raw_l3mdev_accept",
+ .data = &init_net.ipv4.sysctl_raw_l3mdev_accept,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
+#endif
{
.procname = "tcp_ecn",
.data = &init_net.ipv4.sysctl_tcp_ecn,
--
2.11.0
^ permalink raw reply related
* [PATCH net-next v5 3/9] net: ensure unbound datagram socket to be chosen when not in a VRF
From: Mike Manning @ 2018-11-07 15:36 UTC (permalink / raw)
To: netdev
In-Reply-To: <20181107153610.7526-1-mmanning@vyatta.att-mail.com>
Ensure an unbound datagram skt is chosen when not in a VRF. The check
for a device match in compute_score() for UDP must be performed when
there is no device match. For this, a failure is returned when there is
no device match. This ensures that bound sockets are never selected,
even if there is no unbound socket.
Allow IPv6 packets to be sent over a datagram skt bound to a VRF. These
packets are currently blocked, as flowi6_oif was set to that of the
master vrf device, and the ipi6_ifindex is that of the slave device.
Allow these packets to be sent by checking the device with ipi6_ifindex
has the same L3 scope as that of the bound device of the skt, which is
the master vrf device. Note that this check always succeeds if the skt
is unbound.
Even though the right datagram skt is now selected by compute_score(),
a different skt is being returned that is bound to the wrong vrf. The
difference between these and stream sockets is the handling of the skt
option for SO_REUSEPORT. While the handling when adding a skt for reuse
correctly checks that the bound device of the skt is a match, the skts
in the hashslot are already incorrect. So for the same hash, a skt for
the wrong vrf may be selected for the required port. The root cause is
that the skt is immediately placed into a slot when it is created,
but when the skt is then bound using SO_BINDTODEVICE, it remains in the
same slot. The solution is to move the skt to the correct slot by
forcing a rehash.
Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com>
---
include/net/udp.h | 11 +++++++++++
net/core/sock.c | 2 ++
net/ipv4/udp.c | 15 ++++++---------
net/ipv6/datagram.c | 10 +++++++---
net/ipv6/udp.c | 14 +++++---------
5 files changed, 31 insertions(+), 21 deletions(-)
diff --git a/include/net/udp.h b/include/net/udp.h
index 9e82cb391dea..a496e441645e 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -252,6 +252,17 @@ static inline int udp_rqueue_get(struct sock *sk)
return sk_rmem_alloc_get(sk) - READ_ONCE(udp_sk(sk)->forward_deficit);
}
+static inline bool udp_sk_bound_dev_eq(struct net *net, int bound_dev_if,
+ int dif, int sdif)
+{
+#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
+ return inet_bound_dev_eq(!!net->ipv4.sysctl_udp_l3mdev_accept,
+ bound_dev_if, dif, sdif);
+#else
+ return inet_bound_dev_eq(true, bound_dev_if, dif, sdif);
+#endif
+}
+
/* net/ipv4/udp.c */
void udp_destruct_sock(struct sock *sk);
void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len);
diff --git a/net/core/sock.c b/net/core/sock.c
index 7e8796a6a089..2fff1796dcba 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -567,6 +567,8 @@ static int sock_setbindtodevice(struct sock *sk, char __user *optval,
lock_sock(sk);
sk->sk_bound_dev_if = index;
+ if (sk->sk_prot->rehash)
+ sk->sk_prot->rehash(sk);
sk_dst_reset(sk);
release_sock(sk);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 07d6fb80f433..2c01d52a8dd9 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -371,6 +371,7 @@ static int compute_score(struct sock *sk, struct net *net,
{
int score;
struct inet_sock *inet;
+ bool dev_match;
if (!net_eq(sock_net(sk), net) ||
udp_sk(sk)->udp_port_hash != hnum ||
@@ -398,15 +399,11 @@ static int compute_score(struct sock *sk, struct net *net,
score += 4;
}
- if (sk->sk_bound_dev_if || exact_dif) {
- bool dev_match = (sk->sk_bound_dev_if == dif ||
- sk->sk_bound_dev_if == sdif);
-
- if (!dev_match)
- return -1;
- if (sk->sk_bound_dev_if)
- score += 4;
- }
+ dev_match = udp_sk_bound_dev_eq(net, sk->sk_bound_dev_if,
+ dif, sdif);
+ if (!dev_match)
+ return -1;
+ score += 4;
if (sk->sk_incoming_cpu == raw_smp_processor_id())
score++;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 1ede7a16a0be..bde08aa549f3 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -772,6 +772,7 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
case IPV6_2292PKTINFO:
{
struct net_device *dev = NULL;
+ int src_idx;
if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct in6_pktinfo))) {
err = -EINVAL;
@@ -779,12 +780,15 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
}
src_info = (struct in6_pktinfo *)CMSG_DATA(cmsg);
+ src_idx = src_info->ipi6_ifindex;
- if (src_info->ipi6_ifindex) {
+ if (src_idx) {
if (fl6->flowi6_oif &&
- src_info->ipi6_ifindex != fl6->flowi6_oif)
+ src_idx != fl6->flowi6_oif &&
+ (sk->sk_bound_dev_if != fl6->flowi6_oif ||
+ !sk_dev_equal_l3scope(sk, src_idx)))
return -EINVAL;
- fl6->flowi6_oif = src_info->ipi6_ifindex;
+ fl6->flowi6_oif = src_idx;
}
addr_type = __ipv6_addr_type(&src_info->ipi6_addr);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 5dc6949ed956..895fa77bde90 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -117,6 +117,7 @@ static int compute_score(struct sock *sk, struct net *net,
{
int score;
struct inet_sock *inet;
+ bool dev_match;
if (!net_eq(sock_net(sk), net) ||
udp_sk(sk)->udp_port_hash != hnum ||
@@ -144,15 +145,10 @@ static int compute_score(struct sock *sk, struct net *net,
score++;
}
- if (sk->sk_bound_dev_if || exact_dif) {
- bool dev_match = (sk->sk_bound_dev_if == dif ||
- sk->sk_bound_dev_if == sdif);
-
- if (!dev_match)
- return -1;
- if (sk->sk_bound_dev_if)
- score++;
- }
+ dev_match = udp_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif);
+ if (!dev_match)
+ return -1;
+ score++;
if (sk->sk_incoming_cpu == raw_smp_processor_id())
score++;
--
2.11.0
^ permalink raw reply related
* [PATCH net-next v5 1/9] net: allow binding socket in a VRF when there's an unbound socket
From: Mike Manning @ 2018-11-07 15:36 UTC (permalink / raw)
To: netdev; +Cc: Robert Shearman
In-Reply-To: <20181107153610.7526-1-mmanning@vyatta.att-mail.com>
From: Robert Shearman <rshearma@vyatta.att-mail.com>
Change the inet socket lookup to avoid packets arriving on a device
enslaved to an l3mdev from matching unbound sockets by removing the
wildcard for non sk_bound_dev_if and instead relying on check against
the secondary device index, which will be 0 when the input device is
not enslaved to an l3mdev and so match against an unbound socket and
not match when the input device is enslaved.
Change the socket binding to take the l3mdev into account to allow an
unbound socket to not conflict sockets bound to an l3mdev given the
datapath isolation now guaranteed.
Signed-off-by: Robert Shearman <rshearma@vyatta.att-mail.com>
Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com>
---
Documentation/networking/vrf.txt | 9 +++++----
include/net/inet6_hashtables.h | 5 ++---
include/net/inet_hashtables.h | 13 ++++++-------
include/net/inet_sock.h | 13 +++++++++++++
net/ipv4/inet_connection_sock.c | 13 ++++++++++---
net/ipv4/inet_hashtables.c | 20 +++++++++++++++-----
6 files changed, 51 insertions(+), 22 deletions(-)
diff --git a/Documentation/networking/vrf.txt b/Documentation/networking/vrf.txt
index 8ff7b4c8f91b..d4b129402d57 100644
--- a/Documentation/networking/vrf.txt
+++ b/Documentation/networking/vrf.txt
@@ -103,6 +103,11 @@ VRF device:
or to specify the output device using cmsg and IP_PKTINFO.
+By default the scope of the port bindings for unbound sockets is
+limited to the default VRF. That is, it will not be matched by packets
+arriving on interfaces enslaved to an l3mdev and processes may bind to
+the same port if they bind to an l3mdev.
+
TCP & UDP services running in the default VRF context (ie., not bound
to any VRF device) can work across all VRF domains by enabling the
tcp_l3mdev_accept and udp_l3mdev_accept sysctl options:
@@ -112,10 +117,6 @@ tcp_l3mdev_accept and udp_l3mdev_accept sysctl options:
netfilter rules on the VRF device can be used to limit access to services
running in the default VRF context as well.
-The default VRF does not have limited scope with respect to port bindings.
-That is, if a process does a wildcard bind to a port in the default VRF it
-owns the port across all VRF domains within the network namespace.
-
################################################################################
Using iproute2 for VRFs
diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index 6e91e38a31da..9db98af46985 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -115,9 +115,8 @@ int inet6_hash(struct sock *sk);
((__sk)->sk_family == AF_INET6) && \
ipv6_addr_equal(&(__sk)->sk_v6_daddr, (__saddr)) && \
ipv6_addr_equal(&(__sk)->sk_v6_rcv_saddr, (__daddr)) && \
- (!(__sk)->sk_bound_dev_if || \
- ((__sk)->sk_bound_dev_if == (__dif)) || \
- ((__sk)->sk_bound_dev_if == (__sdif))) && \
+ (((__sk)->sk_bound_dev_if == (__dif)) || \
+ ((__sk)->sk_bound_dev_if == (__sdif))) && \
net_eq(sock_net(__sk), (__net)))
#endif /* _INET6_HASHTABLES_H */
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 9141e95529e7..4ae060b4bac2 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -79,6 +79,7 @@ struct inet_ehash_bucket {
struct inet_bind_bucket {
possible_net_t ib_net;
+ int l3mdev;
unsigned short port;
signed char fastreuse;
signed char fastreuseport;
@@ -191,7 +192,7 @@ static inline void inet_ehash_locks_free(struct inet_hashinfo *hashinfo)
struct inet_bind_bucket *
inet_bind_bucket_create(struct kmem_cache *cachep, struct net *net,
struct inet_bind_hashbucket *head,
- const unsigned short snum);
+ const unsigned short snum, int l3mdev);
void inet_bind_bucket_destroy(struct kmem_cache *cachep,
struct inet_bind_bucket *tb);
@@ -282,9 +283,8 @@ static inline struct sock *inet_lookup_listener(struct net *net,
#define INET_MATCH(__sk, __net, __cookie, __saddr, __daddr, __ports, __dif, __sdif) \
(((__sk)->sk_portpair == (__ports)) && \
((__sk)->sk_addrpair == (__cookie)) && \
- (!(__sk)->sk_bound_dev_if || \
- ((__sk)->sk_bound_dev_if == (__dif)) || \
- ((__sk)->sk_bound_dev_if == (__sdif))) && \
+ (((__sk)->sk_bound_dev_if == (__dif)) || \
+ ((__sk)->sk_bound_dev_if == (__sdif))) && \
net_eq(sock_net(__sk), (__net)))
#else /* 32-bit arch */
#define INET_ADDR_COOKIE(__name, __saddr, __daddr) \
@@ -294,9 +294,8 @@ static inline struct sock *inet_lookup_listener(struct net *net,
(((__sk)->sk_portpair == (__ports)) && \
((__sk)->sk_daddr == (__saddr)) && \
((__sk)->sk_rcv_saddr == (__daddr)) && \
- (!(__sk)->sk_bound_dev_if || \
- ((__sk)->sk_bound_dev_if == (__dif)) || \
- ((__sk)->sk_bound_dev_if == (__sdif))) && \
+ (((__sk)->sk_bound_dev_if == (__dif)) || \
+ ((__sk)->sk_bound_dev_if == (__sdif))) && \
net_eq(sock_net(__sk), (__net)))
#endif /* 64-bit arch */
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index a80fd0ac4563..ed3f723af00b 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -130,6 +130,19 @@ static inline int inet_request_bound_dev_if(const struct sock *sk,
return sk->sk_bound_dev_if;
}
+static inline int inet_sk_bound_l3mdev(const struct sock *sk)
+{
+#ifdef CONFIG_NET_L3_MASTER_DEV
+ struct net *net = sock_net(sk);
+
+ if (!net->ipv4.sysctl_tcp_l3mdev_accept)
+ return l3mdev_master_ifindex_by_index(net,
+ sk->sk_bound_dev_if);
+#endif
+
+ return 0;
+}
+
struct inet_cork {
unsigned int flags;
__be32 addr;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 15e7f7915a21..5c63449130d9 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -183,7 +183,9 @@ inet_csk_find_open_port(struct sock *sk, struct inet_bind_bucket **tb_ret, int *
int i, low, high, attempt_half;
struct inet_bind_bucket *tb;
u32 remaining, offset;
+ int l3mdev;
+ l3mdev = inet_sk_bound_l3mdev(sk);
attempt_half = (sk->sk_reuse == SK_CAN_REUSE) ? 1 : 0;
other_half_scan:
inet_get_local_port_range(net, &low, &high);
@@ -219,7 +221,8 @@ inet_csk_find_open_port(struct sock *sk, struct inet_bind_bucket **tb_ret, int *
hinfo->bhash_size)];
spin_lock_bh(&head->lock);
inet_bind_bucket_for_each(tb, &head->chain)
- if (net_eq(ib_net(tb), net) && tb->port == port) {
+ if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev &&
+ tb->port == port) {
if (!inet_csk_bind_conflict(sk, tb, false, false))
goto success;
goto next_port;
@@ -293,6 +296,9 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
struct net *net = sock_net(sk);
struct inet_bind_bucket *tb = NULL;
kuid_t uid = sock_i_uid(sk);
+ int l3mdev;
+
+ l3mdev = inet_sk_bound_l3mdev(sk);
if (!port) {
head = inet_csk_find_open_port(sk, &tb, &port);
@@ -306,11 +312,12 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
hinfo->bhash_size)];
spin_lock_bh(&head->lock);
inet_bind_bucket_for_each(tb, &head->chain)
- if (net_eq(ib_net(tb), net) && tb->port == port)
+ if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev &&
+ tb->port == port)
goto tb_found;
tb_not_found:
tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep,
- net, head, port);
+ net, head, port, l3mdev);
if (!tb)
goto fail_unlock;
tb_found:
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index f5c9ef2586de..260531dc6458 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -65,12 +65,14 @@ static u32 sk_ehashfn(const struct sock *sk)
struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep,
struct net *net,
struct inet_bind_hashbucket *head,
- const unsigned short snum)
+ const unsigned short snum,
+ int l3mdev)
{
struct inet_bind_bucket *tb = kmem_cache_alloc(cachep, GFP_ATOMIC);
if (tb) {
write_pnet(&tb->ib_net, net);
+ tb->l3mdev = l3mdev;
tb->port = snum;
tb->fastreuse = 0;
tb->fastreuseport = 0;
@@ -135,6 +137,7 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child)
table->bhash_size);
struct inet_bind_hashbucket *head = &table->bhash[bhash];
struct inet_bind_bucket *tb;
+ int l3mdev;
spin_lock(&head->lock);
tb = inet_csk(sk)->icsk_bind_hash;
@@ -143,6 +146,8 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child)
return -ENOENT;
}
if (tb->port != port) {
+ l3mdev = inet_sk_bound_l3mdev(sk);
+
/* NOTE: using tproxy and redirecting skbs to a proxy
* on a different listener port breaks the assumption
* that the listener socket's icsk_bind_hash is the same
@@ -150,12 +155,13 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child)
* create a new bind bucket for the child here. */
inet_bind_bucket_for_each(tb, &head->chain) {
if (net_eq(ib_net(tb), sock_net(sk)) &&
- tb->port == port)
+ tb->l3mdev == l3mdev && tb->port == port)
break;
}
if (!tb) {
tb = inet_bind_bucket_create(table->bind_bucket_cachep,
- sock_net(sk), head, port);
+ sock_net(sk), head, port,
+ l3mdev);
if (!tb) {
spin_unlock(&head->lock);
return -ENOMEM;
@@ -675,6 +681,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
u32 remaining, offset;
int ret, i, low, high;
static u32 hint;
+ int l3mdev;
if (port) {
head = &hinfo->bhash[inet_bhashfn(net, port,
@@ -693,6 +700,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
return ret;
}
+ l3mdev = inet_sk_bound_l3mdev(sk);
+
inet_get_local_port_range(net, &low, &high);
high++; /* [32768, 60999] -> [32768, 61000[ */
remaining = high - low;
@@ -719,7 +728,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
* the established check is already unique enough.
*/
inet_bind_bucket_for_each(tb, &head->chain) {
- if (net_eq(ib_net(tb), net) && tb->port == port) {
+ if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev &&
+ tb->port == port) {
if (tb->fastreuse >= 0 ||
tb->fastreuseport >= 0)
goto next_port;
@@ -732,7 +742,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
}
tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep,
- net, head, port);
+ net, head, port, l3mdev);
if (!tb) {
spin_unlock_bh(&head->lock);
return -ENOMEM;
--
2.11.0
^ permalink raw reply related
* [PATCH net-next v5 7/9] ipv6: allow ping to link-local address in VRF
From: Mike Manning @ 2018-11-07 15:36 UTC (permalink / raw)
To: netdev
In-Reply-To: <20181107153610.7526-1-mmanning@vyatta.att-mail.com>
If link-local packets are marked as enslaved to a VRF, then to allow
ping to the link-local from a vrf, the error handling for IPV6_PKTINFO
needs to be relaxed to also allow the pkt ipi6_ifindex to be that of a
slave device to the vrf.
Note that the real device also needs to be retrieved in icmp6_iif()
to set the ipv6 flow oif to this for icmp echo reply handling. The
recent commit 24b711edfc34 ("net/ipv6: Fix linklocal to global address
with VRF") takes care of this, so the sdif does not need checking here.
This fix makes ping to link-local consistent with that to global
addresses, in that this can now be done from within the same VRF that
the address is in.
Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com>
---
net/ipv6/ipv6_sockglue.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 381ce38940ae..973e215c3114 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -486,7 +486,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
retv = -EFAULT;
break;
}
- if (sk->sk_bound_dev_if && pkt.ipi6_ifindex != sk->sk_bound_dev_if)
+ if (!sk_dev_equal_l3scope(sk, pkt.ipi6_ifindex))
goto e_inval;
np->sticky_pktinfo.ipi6_ifindex = pkt.ipi6_ifindex;
--
2.11.0
^ permalink raw reply related
* [PATCH net-next v5 8/9] ipv6: handling of multicast packets received in VRF
From: Mike Manning @ 2018-11-07 15:36 UTC (permalink / raw)
To: netdev; +Cc: Dewi Morgan
In-Reply-To: <20181107153610.7526-1-mmanning@vyatta.att-mail.com>
If the skb for multicast packets marked as enslaved to a VRF are
received, then the secondary device index should be used to obtain
the real device. And verify the multicast address against the
enslaved rather than the l3mdev device.
Signed-off-by: Dewi Morgan <morgand@vyatta.att-mail.com>
Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com>
---
net/ipv6/ip6_input.c | 35 ++++++++++++++++++++++++++++++++---
1 file changed, 32 insertions(+), 3 deletions(-)
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 96577e742afd..df58e1100226 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -359,6 +359,8 @@ static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *sk
}
} else if (ipprot->flags & INET6_PROTO_FINAL) {
const struct ipv6hdr *hdr;
+ int sdif = inet6_sdif(skb);
+ struct net_device *dev;
/* Only do this once for first final protocol */
have_final = true;
@@ -371,9 +373,19 @@ static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *sk
skb_postpull_rcsum(skb, skb_network_header(skb),
skb_network_header_len(skb));
hdr = ipv6_hdr(skb);
+
+ /* skb->dev passed may be master dev for vrfs. */
+ if (sdif) {
+ dev = dev_get_by_index_rcu(net, sdif);
+ if (!dev)
+ goto discard;
+ } else {
+ dev = skb->dev;
+ }
+
if (ipv6_addr_is_multicast(&hdr->daddr) &&
- !ipv6_chk_mcast_addr(skb->dev, &hdr->daddr,
- &hdr->saddr) &&
+ !ipv6_chk_mcast_addr(dev, &hdr->daddr,
+ &hdr->saddr) &&
!ipv6_is_mld(skb, nexthdr, skb_network_header_len(skb)))
goto discard;
}
@@ -432,15 +444,32 @@ EXPORT_SYMBOL_GPL(ip6_input);
int ip6_mc_input(struct sk_buff *skb)
{
+ int sdif = inet6_sdif(skb);
const struct ipv6hdr *hdr;
+ struct net_device *dev;
bool deliver;
__IP6_UPD_PO_STATS(dev_net(skb_dst(skb)->dev),
__in6_dev_get_safely(skb->dev), IPSTATS_MIB_INMCAST,
skb->len);
+ /* skb->dev passed may be master dev for vrfs. */
+ if (sdif) {
+ rcu_read_lock();
+ dev = dev_get_by_index_rcu(dev_net(skb->dev), sdif);
+ if (!dev) {
+ rcu_read_unlock();
+ kfree_skb(skb);
+ return -ENODEV;
+ }
+ } else {
+ dev = skb->dev;
+ }
+
hdr = ipv6_hdr(skb);
- deliver = ipv6_chk_mcast_addr(skb->dev, &hdr->daddr, NULL);
+ deliver = ipv6_chk_mcast_addr(dev, &hdr->daddr, NULL);
+ if (sdif)
+ rcu_read_unlock();
#ifdef CONFIG_IPV6_MROUTE
/*
--
2.11.0
^ permalink raw reply related
* Re: [PATCH net-next v2 3/5] virtio_ring: add packed ring support
From: Tiwei Bie @ 2018-11-08 1:38 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: jasowang, virtualization, linux-kernel, netdev, virtio-dev, wexu,
jfreimann
In-Reply-To: <20181107123933-mutt-send-email-mst@kernel.org>
On Wed, Nov 07, 2018 at 12:48:46PM -0500, Michael S. Tsirkin wrote:
> On Wed, Jul 11, 2018 at 10:27:09AM +0800, Tiwei Bie wrote:
> > This commit introduces the support (without EVENT_IDX) for
> > packed ring.
> >
> > Signed-off-by: Tiwei Bie <tiwei.bie@intel.com>
> > ---
> > drivers/virtio/virtio_ring.c | 495 ++++++++++++++++++++++++++++++++++-
> > 1 file changed, 487 insertions(+), 8 deletions(-)
[...]
> >
> > +static void vring_unmap_state_packed(const struct vring_virtqueue *vq,
> > + struct vring_desc_state_packed *state)
> > +{
> > + u16 flags;
> > +
> > + if (!vring_use_dma_api(vq->vq.vdev))
> > + return;
> > +
> > + flags = state->flags;
> > +
> > + if (flags & VRING_DESC_F_INDIRECT) {
> > + dma_unmap_single(vring_dma_dev(vq),
> > + state->addr, state->len,
> > + (flags & VRING_DESC_F_WRITE) ?
> > + DMA_FROM_DEVICE : DMA_TO_DEVICE);
> > + } else {
> > + dma_unmap_page(vring_dma_dev(vq),
> > + state->addr, state->len,
> > + (flags & VRING_DESC_F_WRITE) ?
> > + DMA_FROM_DEVICE : DMA_TO_DEVICE);
> > + }
> > +}
> > +
> > +static void vring_unmap_desc_packed(const struct vring_virtqueue *vq,
> > + struct vring_packed_desc *desc)
> > +{
> > + u16 flags;
> > +
> > + if (!vring_use_dma_api(vq->vq.vdev))
> > + return;
> > +
> > + flags = virtio16_to_cpu(vq->vq.vdev, desc->flags);
>
> BTW this stuff is only used on error etc. Is there a way to
> reuse vring_unmap_state_packed?
It's also used by the INDIRECT path. We don't allocate desc
state for INDIRECT descriptors to save DMA addr/len etc.
>
> > +
> > + if (flags & VRING_DESC_F_INDIRECT) {
> > + dma_unmap_single(vring_dma_dev(vq),
> > + virtio64_to_cpu(vq->vq.vdev, desc->addr),
> > + virtio32_to_cpu(vq->vq.vdev, desc->len),
> > + (flags & VRING_DESC_F_WRITE) ?
> > + DMA_FROM_DEVICE : DMA_TO_DEVICE);
> > + } else {
> > + dma_unmap_page(vring_dma_dev(vq),
> > + virtio64_to_cpu(vq->vq.vdev, desc->addr),
> > + virtio32_to_cpu(vq->vq.vdev, desc->len),
> > + (flags & VRING_DESC_F_WRITE) ?
> > + DMA_FROM_DEVICE : DMA_TO_DEVICE);
> > + }
> > +}
[...]
> > @@ -766,47 +840,449 @@ static inline int virtqueue_add_packed(struct virtqueue *_vq,
> > void *ctx,
> > gfp_t gfp)
> > {
> > + struct vring_virtqueue *vq = to_vvq(_vq);
> > + struct vring_packed_desc *desc;
> > + struct scatterlist *sg;
> > + unsigned int i, n, descs_used, uninitialized_var(prev), err_idx;
> > + __virtio16 uninitialized_var(head_flags), flags;
> > + u16 head, avail_wrap_counter, id, curr;
> > + bool indirect;
> > +
> > + START_USE(vq);
> > +
> > + BUG_ON(data == NULL);
> > + BUG_ON(ctx && vq->indirect);
> > +
> > + if (unlikely(vq->broken)) {
> > + END_USE(vq);
> > + return -EIO;
> > + }
> > +
> > +#ifdef DEBUG
> > + {
> > + ktime_t now = ktime_get();
> > +
> > + /* No kick or get, with .1 second between? Warn. */
> > + if (vq->last_add_time_valid)
> > + WARN_ON(ktime_to_ms(ktime_sub(now, vq->last_add_time))
> > + > 100);
> > + vq->last_add_time = now;
> > + vq->last_add_time_valid = true;
> > + }
> > +#endif
> > +
> > + BUG_ON(total_sg == 0);
> > +
> > + head = vq->next_avail_idx;
> > + avail_wrap_counter = vq->avail_wrap_counter;
> > +
> > + if (virtqueue_use_indirect(_vq, total_sg))
> > + desc = alloc_indirect_packed(_vq, total_sg, gfp);
> > + else {
> > + desc = NULL;
> > + WARN_ON_ONCE(total_sg > vq->vring_packed.num && !vq->indirect);
> > + }
> > +
> > + if (desc) {
> > + /* Use a single buffer which doesn't continue */
> > + indirect = true;
> > + /* Set up rest to use this indirect table. */
> > + i = 0;
> > + descs_used = 1;
> > + } else {
> > + indirect = false;
> > + desc = vq->vring_packed.desc;
> > + i = head;
> > + descs_used = total_sg;
> > + }
> > +
> > + if (vq->vq.num_free < descs_used) {
> > + pr_debug("Can't add buf len %i - avail = %i\n",
> > + descs_used, vq->vq.num_free);
> > + /* FIXME: for historical reasons, we force a notify here if
> > + * there are outgoing parts to the buffer. Presumably the
> > + * host should service the ring ASAP. */
>
> I don't think we have a reason to do this for packed ring.
> No historical baggage there, right?
Based on the original commit log, it seems that the notify here
is just an "optimization". But I don't quite understand what does
the "the heuristics which KVM uses" refer to. If it's safe to drop
this in packed ring, I'd like to do it.
commit 44653eae1407f79dff6f52fcf594ae84cb165ec4
Author: Rusty Russell <rusty@rustcorp.com.au>
Date: Fri Jul 25 12:06:04 2008 -0500
virtio: don't always force a notification when ring is full
We force notification when the ring is full, even if the host has
indicated it doesn't want to know. This seemed like a good idea at
the time: if we fill the transmit ring, we should tell the host
immediately.
Unfortunately this logic also applies to the receiving ring, which is
refilled constantly. We should introduce real notification thesholds
to replace this logic. Meanwhile, removing the logic altogether breaks
the heuristics which KVM uses, so we use a hack: only notify if there are
outgoing parts of the new buffer.
Here are the number of exits with lguest's crappy network implementation:
Before:
network xmit 7859051 recv 236420
After:
network xmit 7858610 recv 118136
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 72bf8bc09014..21d9a62767af 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -87,8 +87,11 @@ static int vring_add_buf(struct virtqueue *_vq,
if (vq->num_free < out + in) {
pr_debug("Can't add buf len %i - avail = %i\n",
out + in, vq->num_free);
- /* We notify *even if* VRING_USED_F_NO_NOTIFY is set here. */
- vq->notify(&vq->vq);
+ /* FIXME: for historical reasons, we force a notify here if
+ * there are outgoing parts to the buffer. Presumably the
+ * host should service the ring ASAP. */
+ if (out)
+ vq->notify(&vq->vq);
END_USE(vq);
return -ENOSPC;
}
>
> > + if (out_sgs)
> > + vq->notify(&vq->vq);
> > + if (indirect)
> > + kfree(desc);
> > + END_USE(vq);
> > + return -ENOSPC;
> > + }
> > +
[...]
^ permalink raw reply related
* Re: [PATCH net-next] tcp: minor optimization in tcp ack fast path processing
From: Yafang Shao @ 2018-11-08 1:45 UTC (permalink / raw)
To: Eric Dumazet; +Cc: David Miller, Eric Dumazet, netdev, LKML, Joe Perches
In-Reply-To: <560b2828-cb1b-5ab5-f98b-b042a7e483f8@gmail.com>
On Wed, Nov 7, 2018 at 11:16 PM Eric Dumazet <eric.dumazet@gmail.com> wrote:
>
>
>
> On 11/07/2018 03:20 AM, Yafang Shao wrote:
> > Bitwise operation is a little faster.
>
>
> > So I replace after() with (flag & FLAG_SND_UNA_ADVANCED) as this flag is
> > already set before.
> >
> > Cc: Joe Perches <joe@perches.com>
> > Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
> > ---
> > net/ipv4/tcp_input.c | 2 +-
> > 1 file changed, 1 insertion(+), 1 deletion(-)
> >
> > diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
> > index 2868ef2..0167015 100644
> > --- a/net/ipv4/tcp_input.c
> > +++ b/net/ipv4/tcp_input.c
> > @@ -3610,7 +3610,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
> > if (flag & FLAG_UPDATE_TS_RECENT)
> > tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq);
> >
> > - if (!(flag & FLAG_SLOWPATH) && after(ack, prior_snd_una)) {
> > + if (!(flag & FLAG_SLOWPATH) && (flag & FLAG_SND_UNA_ADVANCED)) {
> > /* Window is constant, pure forward advance.
> > * No more checks are required.
> > * Note, we use the fact that SND.UNA>=SND.WL2.
> >
>
> What about reducing this to a single conditional jump ?
>
> if ((flag & (FLAG_SLOWPATH | FLAG_SND_UNA_ADVANCED)) == FLAG_SND_UNA_ADVANCED) {
>
That's better.
Will change it.
Thanks
Yafang
^ permalink raw reply
* [PATCH net-next] net: bcmgenet: return correct value 'ret' from bcmgenet_power_down
From: YueHaibing @ 2018-11-08 2:08 UTC (permalink / raw)
To: Doug Berger, Florian Fainelli, davem
Cc: YueHaibing, netdev, kernel-janitors, linux-kernel
Fixes gcc '-Wunused-but-set-variable' warning:
drivers/net/ethernet/broadcom/genet/bcmgenet.c: In function 'bcmgenet_power_down':
drivers/net/ethernet/broadcom/genet/bcmgenet.c:1136:6: warning:
variable 'ret' set but not used [-Wunused-but-set-variable]
bcmgenet_power_down should return 'ret' instead of 0.
Fixes: ca8cf341903f ("net: bcmgenet: propagate errors from bcmgenet_power_down")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
---
drivers/net/ethernet/broadcom/genet/bcmgenet.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 2d6f090..bf88749 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1169,7 +1169,7 @@ static int bcmgenet_power_down(struct bcmgenet_priv *priv,
break;
}
- return 0;
+ return ret;
}
static void bcmgenet_power_up(struct bcmgenet_priv *priv,
^ permalink raw reply related
* [Patch net] net: hns3: bugfix for not checking return value
From: Huazhong Tan @ 2018-11-08 2:13 UTC (permalink / raw)
To: davem; +Cc: netdev, linux-kernel, salil.mehta, yisen.zhuang, linuxarm
hns3_reset_notify_init_enet() only return error early if the return
value of hns3_restore_vlan() is not 0.
This patch adds checking for the return value of hns3_restore_vlan.
Fixes: 7fa6be4fd2f6 ("net: hns3: fix incorrect return value/type of some functions")
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
---
drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 3f96aa3..20fcf0d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -3760,7 +3760,8 @@ static int hns3_reset_notify_init_enet(struct hnae3_handle *handle)
/* Hardware table is only clear when pf resets */
if (!(handle->flags & HNAE3_SUPPORT_VF)) {
ret = hns3_restore_vlan(netdev);
- return ret;
+ if (ret)
+ return ret;
}
ret = hns3_restore_fd_rules(netdev);
--
2.7.4
^ permalink raw reply related
* Re: [PATCH bpf-next] tools: bpftool: adjust rlimit RLIMIT_MEMLOCK when loading programs, maps
From: Martin Lau @ 2018-11-07 16:59 UTC (permalink / raw)
To: Quentin Monnet
Cc: Alexei Starovoitov, Daniel Borkmann, netdev@vger.kernel.org,
oss-drivers@netronome.com
In-Reply-To: <1541593770-28089-1-git-send-email-quentin.monnet@netronome.com>
On Wed, Nov 07, 2018 at 12:29:30PM +0000, Quentin Monnet wrote:
> The limit for memory locked in the kernel by a process is usually set to
> 64 bytes by default. This can be an issue when creating large BPF maps
hmm... 64 _k_bytes?
> and/or loading many programs. A workaround is to raise this limit for
> the current process before trying to create a new BPF map. Changing the
> hard limit requires the CAP_SYS_RESOURCE and can usually only be done by
> root user (for non-root users, a call to setrlimit fails (and sets
> errno) and the program simply goes on with its rlimit unchanged).
>
> There is no API to get the current amount of memory locked for a user,
> therefore we cannot raise the limit only when required. One solution,
> used by bcc, is to try to create the map, and on getting a EPERM error,
> raising the limit to infinity before giving another try. Another
> approach, used in iproute2, is to raise the limit in all cases, before
> trying to create the map.
>
> Here we do the same as in iproute2: the rlimit is raised to infinity
> before trying to load programs or to create maps with bpftool.
>
> Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
> Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Patch LGTM.
Acked-by: Martin KaFai Lau <kafai@fb.com>
^ permalink raw reply
* [PATCH net] ibmvnic: fix accelerated VLAN handling
From: Michał Mirosław @ 2018-11-07 16:50 UTC (permalink / raw)
To: netdev; +Cc: Thomas Falcon, John Allen
Don't request tag insertion when it isn't present in outgoing skb.
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
---
drivers/net/ethernet/ibm/ibmvnic.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 7893beffcc71..c9d5d0a7fbf1 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -1545,7 +1545,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
tx_crq.v1.sge_len = cpu_to_be32(skb->len);
tx_crq.v1.ioba = cpu_to_be64(data_dma_addr);
- if (adapter->vlan_header_insertion) {
+ if (adapter->vlan_header_insertion && skb_vlan_tag_present(skb)) {
tx_crq.v1.flags2 |= IBMVNIC_TX_VLAN_INSERT;
tx_crq.v1.vlan_id = cpu_to_be16(skb->vlan_tci);
}
--
2.19.1
^ permalink raw reply related
* [PATCH net] qlcnic: remove assumption that vlan_tci != 0
From: Michał Mirosław @ 2018-11-07 16:50 UTC (permalink / raw)
To: netdev; +Cc: Shahed Shaikh, Manish Chopra, Dept-GELinuxNICDev
VLAN.TCI == 0 is perfectly valid (802.1p), so allow it to be accelerated.
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
---
drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
index 9647578cbe6a..14f26bf3b388 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
@@ -459,7 +459,7 @@ static int qlcnic_tx_pkt(struct qlcnic_adapter *adapter,
struct cmd_desc_type0 *first_desc, struct sk_buff *skb,
struct qlcnic_host_tx_ring *tx_ring)
{
- u8 l4proto, opcode = 0, hdr_len = 0;
+ u8 l4proto, opcode = 0, hdr_len = 0, tag_vlan = 0;
u16 flags = 0, vlan_tci = 0;
int copied, offset, copy_len, size;
struct cmd_desc_type0 *hwdesc;
@@ -472,14 +472,16 @@ static int qlcnic_tx_pkt(struct qlcnic_adapter *adapter,
flags = QLCNIC_FLAGS_VLAN_TAGGED;
vlan_tci = ntohs(vh->h_vlan_TCI);
protocol = ntohs(vh->h_vlan_encapsulated_proto);
+ tag_vlan = 1;
} else if (skb_vlan_tag_present(skb)) {
flags = QLCNIC_FLAGS_VLAN_OOB;
vlan_tci = skb_vlan_tag_get(skb);
+ tag_vlan = 1;
}
if (unlikely(adapter->tx_pvid)) {
- if (vlan_tci && !(adapter->flags & QLCNIC_TAGGING_ENABLED))
+ if (tag_vlan && !(adapter->flags & QLCNIC_TAGGING_ENABLED))
return -EIO;
- if (vlan_tci && (adapter->flags & QLCNIC_TAGGING_ENABLED))
+ if (tag_vlan && (adapter->flags & QLCNIC_TAGGING_ENABLED))
goto set_flags;
flags = QLCNIC_FLAGS_VLAN_OOB;
--
2.19.1
^ permalink raw reply related
* Re: [PATCH bpf-next] tools: bpftool: adjust rlimit RLIMIT_MEMLOCK when loading programs, maps
From: Quentin Monnet @ 2018-11-07 17:03 UTC (permalink / raw)
To: Martin Lau
Cc: Alexei Starovoitov, Daniel Borkmann, netdev@vger.kernel.org,
oss-drivers@netronome.com
In-Reply-To: <20181107165943.x6vj5e4qlsym3jub@kafai-mbp.dhcp.thefacebook.com>
2018-11-07 16:59 UTC+0000 ~ Martin Lau <kafai@fb.com>
> On Wed, Nov 07, 2018 at 12:29:30PM +0000, Quentin Monnet wrote:
>> The limit for memory locked in the kernel by a process is usually set to
>> 64 bytes by default. This can be an issue when creating large BPF maps
> hmm... 64 _k_bytes?
Ouch. That's true. Thanks! I can respin to fix the commit log if needed.
>> and/or loading many programs. A workaround is to raise this limit for
>> the current process before trying to create a new BPF map. Changing the
>> hard limit requires the CAP_SYS_RESOURCE and can usually only be done by
>> root user (for non-root users, a call to setrlimit fails (and sets
>> errno) and the program simply goes on with its rlimit unchanged).
>>
>> There is no API to get the current amount of memory locked for a user,
>> therefore we cannot raise the limit only when required. One solution,
>> used by bcc, is to try to create the map, and on getting a EPERM error,
>> raising the limit to infinity before giving another try. Another
>> approach, used in iproute2, is to raise the limit in all cases, before
>> trying to create the map.
>>
>> Here we do the same as in iproute2: the rlimit is raised to infinity
>> before trying to load programs or to create maps with bpftool.
>>
>> Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
>> Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
> Patch LGTM.
>
> Acked-by: Martin KaFai Lau <kafai@fb.com>
>
Thanks for this as well.
Quentin
^ permalink raw reply
* [PATCH net-next 0/4] net/vlan: prepare for removal of VLAN_TAG_PRESENT
From: Michał Mirosław @ 2018-11-07 17:07 UTC (permalink / raw)
To: netdev
This is a preparatory patchset before removing the use of VLAN_TAG_PRESENT
bit in skb->vlan_tci as indication of VLAN offload. This set includes
only cleanups that allow abstracting of code testing VLAN tag presence
in drivers and networking code.
Michał Mirosław (4):
net/vlan: introduce __vlan_hwaccel_clear_tag() helper
net/vlan: introduce __vlan_hwaccel_copy_tag() helper
net/vlan: include the shift in skb_vlan_tag_get_prio()
net/vlan: remove unused #define HAVE_VLAN_GET_TAG
include/linux/if_vlan.h | 30 ++++++++++++++++++++++++++----
net/core/flow_dissector.c | 3 +--
2 files changed, 27 insertions(+), 6 deletions(-)
--
2.19.1
^ permalink raw reply
* [PATCH net-next 2/4] net/vlan: introduce __vlan_hwaccel_copy_tag() helper
From: Michał Mirosław @ 2018-11-07 17:07 UTC (permalink / raw)
To: netdev
In-Reply-To: <cover.1541610138.git.mirq-linux@rere.qmqm.pl>
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
---
include/linux/if_vlan.h | 13 +++++++++++++
1 file changed, 13 insertions(+)
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index c438fa0a1c6a..941da4bf3929 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -472,6 +472,19 @@ static inline void __vlan_hwaccel_clear_tag(struct sk_buff *skb)
skb->vlan_tci = 0;
}
+/**
+ * __vlan_hwaccel_copy_tag - copy hardware accelerated VLAN info from another skb
+ * @dst: skbuff to copy to
+ * @src: skbuff to copy from
+ *
+ * Copies VLAN information from @src to @dst (for branchless code)
+ */
+static inline void __vlan_hwaccel_copy_tag(struct sk_buff *dst, const struct sk_buff *src)
+{
+ dst->vlan_proto = src->vlan_proto;
+ dst->vlan_tci = src->vlan_tci;
+}
+
/*
* __vlan_hwaccel_push_inside - pushes vlan tag to the payload
* @skb: skbuff to tag
--
2.19.1
^ permalink raw reply related
* [PATCH net-next 1/4] net/vlan: introduce __vlan_hwaccel_clear_tag() helper
From: Michał Mirosław @ 2018-11-07 17:07 UTC (permalink / raw)
To: netdev
In-Reply-To: <cover.1541610138.git.mirq-linux@rere.qmqm.pl>
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
---
include/linux/if_vlan.h | 13 ++++++++++++-
1 file changed, 12 insertions(+), 1 deletion(-)
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 83ea4df6ab81..c438fa0a1c6a 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -461,6 +461,17 @@ static inline struct sk_buff *vlan_insert_tag_set_proto(struct sk_buff *skb,
return skb;
}
+/**
+ * __vlan_hwaccel_clear_tag - clear hardware accelerated VLAN info
+ * @skb: skbuff to clear
+ *
+ * Clears the VLAN information from @skb
+ */
+static inline void __vlan_hwaccel_clear_tag(struct sk_buff *skb)
+{
+ skb->vlan_tci = 0;
+}
+
/*
* __vlan_hwaccel_push_inside - pushes vlan tag to the payload
* @skb: skbuff to tag
@@ -475,7 +486,7 @@ static inline struct sk_buff *__vlan_hwaccel_push_inside(struct sk_buff *skb)
skb = vlan_insert_tag_set_proto(skb, skb->vlan_proto,
skb_vlan_tag_get(skb));
if (likely(skb))
- skb->vlan_tci = 0;
+ __vlan_hwaccel_clear_tag(skb);
return skb;
}
--
2.19.1
^ permalink raw reply related
* [PATCH net-next 4/4] net/vlan: remove unused #define HAVE_VLAN_GET_TAG
From: Michał Mirosław @ 2018-11-07 17:07 UTC (permalink / raw)
To: netdev
In-Reply-To: <cover.1541610138.git.mirq-linux@rere.qmqm.pl>
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
---
include/linux/if_vlan.h | 2 --
1 file changed, 2 deletions(-)
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index b14bf87999aa..03b08ffded07 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -555,8 +555,6 @@ static inline int __vlan_hwaccel_get_tag(const struct sk_buff *skb,
}
}
-#define HAVE_VLAN_GET_TAG
-
/**
* vlan_get_tag - get the VLAN ID from the skb
* @skb: skbuff to query
--
2.19.1
^ permalink raw reply related
* [PATCH net-next 3/4] net/vlan: include the shift in skb_vlan_tag_get_prio()
From: Michał Mirosław @ 2018-11-07 17:07 UTC (permalink / raw)
To: netdev
In-Reply-To: <cover.1541610138.git.mirq-linux@rere.qmqm.pl>
Signed-off-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
---
include/linux/if_vlan.h | 2 +-
net/core/flow_dissector.c | 3 +--
2 files changed, 2 insertions(+), 3 deletions(-)
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 941da4bf3929..b14bf87999aa 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -81,7 +81,7 @@ static inline bool is_vlan_dev(const struct net_device *dev)
#define skb_vlan_tag_present(__skb) ((__skb)->vlan_tci & VLAN_TAG_PRESENT)
#define skb_vlan_tag_get(__skb) ((__skb)->vlan_tci & ~VLAN_TAG_PRESENT)
#define skb_vlan_tag_get_id(__skb) ((__skb)->vlan_tci & VLAN_VID_MASK)
-#define skb_vlan_tag_get_prio(__skb) ((__skb)->vlan_tci & VLAN_PRIO_MASK)
+#define skb_vlan_tag_get_prio(__skb) (((__skb)->vlan_tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT)
static inline int vlan_get_rx_ctag_filter_info(struct net_device *dev)
{
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 676f3ad629f9..56d1e9b73142 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -952,8 +952,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
if (!vlan) {
key_vlan->vlan_id = skb_vlan_tag_get_id(skb);
- key_vlan->vlan_priority =
- (skb_vlan_tag_get_prio(skb) >> VLAN_PRIO_SHIFT);
+ key_vlan->vlan_priority = skb_vlan_tag_get_prio(skb);
} else {
key_vlan->vlan_id = ntohs(vlan->h_vlan_TCI) &
VLAN_VID_MASK;
--
2.19.1
^ permalink raw reply related
* [PATCH net-next v3 0/6] net/ncsi: Allow enabling multiple packages & channels
From: Samuel Mendoza-Jonas @ 2018-11-08 2:49 UTC (permalink / raw)
To: netdev
Cc: Samuel Mendoza-Jonas, David S . Miller, Justin.Lee1, linux-kernel,
openbmc
This series extends the NCSI driver to configure multiple packages
and/or channels simultaneously. Since the RFC series this includes a few
extra changes to fix areas in the driver that either made this harder or
were roadblocks due to deviations from the NCSI specification.
Patches 1 & 2 fix two issues where the driver made assumptions about the
capabilities of the NCSI topology.
Patches 3 & 4 change some internal semantics slightly to make multi-mode
easier.
Patch 5 introduces a cleaner way of reconfiguring the NCSI configuration
and keeping track of channel states.
Patch 6 implements the main multi-package/multi-channel configuration,
configured via the Netlink interface.
Readers who have an interesting NCSI setup - especially multi-package
with HWA - please test! I think I've covered all permutations but I
don't have infinite hardware to test on.
Changes in v2:
- Updated use of the channel lock in ncsi_reset_dev(), making the
channel invisible and leaving the monitor check to
ncsi_stop_channel_monitor().
- Fixed ncsi_channel_is_tx() to consider the state of channels in other
packages.
Changes in v3:
- Fixed bisectability bug in patch 1
- Consider channels on all packages in a few places when multi-package
is enabled.
- Avoid doubling up reset operations, and check the current driver state
before reset to let any running operations complete.
- Reorganise the LSC handler slightly to avoid enabling Tx twice.
Samuel Mendoza-Jonas (6):
net/ncsi: Don't enable all channels when HWA available
net/ncsi: Probe single packages to avoid conflict
net/ncsi: Don't deselect package in suspend if active
net/ncsi: Don't mark configured channels inactive
net/ncsi: Reset channel state in ncsi_start_dev()
net/ncsi: Configure multi-package, multi-channel modes with failover
include/uapi/linux/ncsi.h | 15 ++
net/ncsi/internal.h | 19 +-
net/ncsi/ncsi-aen.c | 72 ++++--
net/ncsi/ncsi-manage.c | 511 ++++++++++++++++++++++++++------------
net/ncsi/ncsi-netlink.c | 233 ++++++++++++++---
net/ncsi/ncsi-rsp.c | 2 +-
6 files changed, 646 insertions(+), 206 deletions(-)
--
2.19.1
^ permalink raw reply
* [PATCH net-next v3 2/6] net/ncsi: Probe single packages to avoid conflict
From: Samuel Mendoza-Jonas @ 2018-11-08 2:49 UTC (permalink / raw)
To: netdev
Cc: Samuel Mendoza-Jonas, David S . Miller, Justin.Lee1, linux-kernel,
openbmc
In-Reply-To: <20181108024909.9897-1-sam@mendozajonas.com>
Currently the NCSI driver sends a select-package command to all possible
packages simultaneously to discover what packages are available. However
at this stage in the probe process the driver does not know if
hardware arbitration is available: if it isn't then this process could
cause collisions on the RMII bus when packages try to respond.
Update the probe loop to probe each package one by one, and once
complete check if HWA is universally supported.
Signed-off-by: Samuel Mendoza-Jonas <sam@mendozajonas.com>
---
net/ncsi/internal.h | 1 +
net/ncsi/ncsi-manage.c | 85 +++++++++++++++---------------------------
2 files changed, 31 insertions(+), 55 deletions(-)
diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h
index 1dae77c54009..ec65778c41f3 100644
--- a/net/ncsi/internal.h
+++ b/net/ncsi/internal.h
@@ -292,6 +292,7 @@ struct ncsi_dev_priv {
#if IS_ENABLED(CONFIG_IPV6)
unsigned int inet6_addr_num; /* Number of IPv6 addresses */
#endif
+ unsigned int package_probe_id;/* Current ID during probe */
unsigned int package_num; /* Number of packages */
struct list_head packages; /* List of packages */
struct ncsi_channel *hot_channel; /* Channel was ever active */
diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c
index d4e6e0f99097..02421d1a22c9 100644
--- a/net/ncsi/ncsi-manage.c
+++ b/net/ncsi/ncsi-manage.c
@@ -1079,67 +1079,28 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp)
nd->state = ncsi_dev_state_probe_package;
break;
case ncsi_dev_state_probe_package:
- ndp->pending_req_num = 16;
+ ndp->pending_req_num = 1;
- /* Select all possible packages */
nca.type = NCSI_PKT_CMD_SP;
nca.bytes[0] = 1;
+ nca.package = ndp->package_probe_id;
nca.channel = NCSI_RESERVED_CHANNEL;
- for (index = 0; index < 8; index++) {
- nca.package = index;
- ret = ncsi_xmit_cmd(&nca);
- if (ret)
- goto error;
- }
-
- /* Disable all possible packages */
- nca.type = NCSI_PKT_CMD_DP;
- for (index = 0; index < 8; index++) {
- nca.package = index;
- ret = ncsi_xmit_cmd(&nca);
- if (ret)
- goto error;
- }
-
+ ret = ncsi_xmit_cmd(&nca);
+ if (ret)
+ goto error;
nd->state = ncsi_dev_state_probe_channel;
break;
case ncsi_dev_state_probe_channel:
- if (!ndp->active_package)
- ndp->active_package = list_first_or_null_rcu(
- &ndp->packages, struct ncsi_package, node);
- else if (list_is_last(&ndp->active_package->node,
- &ndp->packages))
- ndp->active_package = NULL;
- else
- ndp->active_package = list_next_entry(
- ndp->active_package, node);
-
- /* All available packages and channels are enumerated. The
- * enumeration happens for once when the NCSI interface is
- * started. So we need continue to start the interface after
- * the enumeration.
- *
- * We have to choose an active channel before configuring it.
- * Note that we possibly don't have active channel in extreme
- * situation.
- */
+ ndp->active_package = ncsi_find_package(ndp,
+ ndp->package_probe_id);
if (!ndp->active_package) {
- ndp->flags |= NCSI_DEV_PROBED;
- ncsi_choose_active_channel(ndp);
- return;
+ /* No response */
+ nd->state = ncsi_dev_state_probe_dp;
+ schedule_work(&ndp->work);
+ break;
}
-
- /* Select the active package */
- ndp->pending_req_num = 1;
- nca.type = NCSI_PKT_CMD_SP;
- nca.bytes[0] = 1;
- nca.package = ndp->active_package->id;
- nca.channel = NCSI_RESERVED_CHANNEL;
- ret = ncsi_xmit_cmd(&nca);
- if (ret)
- goto error;
-
nd->state = ncsi_dev_state_probe_cis;
+ schedule_work(&ndp->work);
break;
case ncsi_dev_state_probe_cis:
ndp->pending_req_num = NCSI_RESERVED_CHANNEL;
@@ -1188,22 +1149,35 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp)
case ncsi_dev_state_probe_dp:
ndp->pending_req_num = 1;
- /* Deselect the active package */
+ /* Deselect the current package */
nca.type = NCSI_PKT_CMD_DP;
- nca.package = ndp->active_package->id;
+ nca.package = ndp->package_probe_id;
nca.channel = NCSI_RESERVED_CHANNEL;
ret = ncsi_xmit_cmd(&nca);
if (ret)
goto error;
- /* Scan channels in next package */
- nd->state = ncsi_dev_state_probe_channel;
+ /* Probe next package */
+ ndp->package_probe_id++;
+ if (ndp->package_probe_id >= 8) {
+ /* Probe finished */
+ ndp->flags |= NCSI_DEV_PROBED;
+ break;
+ }
+ nd->state = ncsi_dev_state_probe_package;
+ ndp->active_package = NULL;
break;
default:
netdev_warn(nd->dev, "Wrong NCSI state 0x%0x in enumeration\n",
nd->state);
}
+ if (ndp->flags & NCSI_DEV_PROBED) {
+ /* Check if all packages have HWA support */
+ ncsi_check_hwa(ndp);
+ ncsi_choose_active_channel(ndp);
+ }
+
return;
error:
netdev_err(ndp->ndev.dev,
@@ -1564,6 +1538,7 @@ int ncsi_start_dev(struct ncsi_dev *nd)
return -ENOTTY;
if (!(ndp->flags & NCSI_DEV_PROBED)) {
+ ndp->package_probe_id = 0;
nd->state = ncsi_dev_state_probe;
schedule_work(&ndp->work);
return 0;
--
2.19.1
^ permalink raw reply related
* [PATCH net-next v3 3/6] net/ncsi: Don't deselect package in suspend if active
From: Samuel Mendoza-Jonas @ 2018-11-08 2:49 UTC (permalink / raw)
To: netdev
Cc: Samuel Mendoza-Jonas, David S . Miller, Justin.Lee1, linux-kernel,
openbmc
In-Reply-To: <20181108024909.9897-1-sam@mendozajonas.com>
When a package is deselected all channels of that package cease
communication. If there are other channels active on the package of the
suspended channel this will disable them as well, so only send a
deselect-package command if no other channels are active.
Signed-off-by: Samuel Mendoza-Jonas <sam@mendozajonas.com>
---
net/ncsi/ncsi-manage.c | 15 +++++++++++++--
1 file changed, 13 insertions(+), 2 deletions(-)
diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c
index 02421d1a22c9..b8b4e765a04c 100644
--- a/net/ncsi/ncsi-manage.c
+++ b/net/ncsi/ncsi-manage.c
@@ -440,12 +440,14 @@ static void ncsi_request_timeout(struct timer_list *t)
static void ncsi_suspend_channel(struct ncsi_dev_priv *ndp)
{
struct ncsi_dev *nd = &ndp->ndev;
- struct ncsi_package *np = ndp->active_package;
- struct ncsi_channel *nc = ndp->active_channel;
+ struct ncsi_package *np;
+ struct ncsi_channel *nc, *tmp;
struct ncsi_cmd_arg nca;
unsigned long flags;
int ret;
+ np = ndp->active_package;
+ nc = ndp->active_channel;
nca.ndp = ndp;
nca.req_flags = NCSI_REQ_FLAG_EVENT_DRIVEN;
switch (nd->state) {
@@ -521,6 +523,15 @@ static void ncsi_suspend_channel(struct ncsi_dev_priv *ndp)
if (ret)
goto error;
+ NCSI_FOR_EACH_CHANNEL(np, tmp) {
+ /* If there is another channel active on this package
+ * do not deselect the package.
+ */
+ if (tmp != nc && tmp->state == NCSI_CHANNEL_ACTIVE) {
+ nd->state = ncsi_dev_state_suspend_done;
+ break;
+ }
+ }
break;
case ncsi_dev_state_suspend_deselect:
ndp->pending_req_num = 1;
--
2.19.1
^ permalink raw reply related
* [PATCH net-next v3 5/6] net/ncsi: Reset channel state in ncsi_start_dev()
From: Samuel Mendoza-Jonas @ 2018-11-08 2:49 UTC (permalink / raw)
To: netdev
Cc: Samuel Mendoza-Jonas, David S . Miller, Justin.Lee1, linux-kernel,
openbmc
In-Reply-To: <20181108024909.9897-1-sam@mendozajonas.com>
When the NCSI driver is stopped with ncsi_stop_dev() the channel
monitors are stopped and the state set to "inactive". However the
channels are still configured and active from the perspective of the
network controller. We should suspend each active channel but in the
context of ncsi_stop_dev() the transmit queue has been or is about to be
stopped so we won't have time to do so.
Instead when ncsi_start_dev() is called if the NCSI topology has already
been probed then call ncsi_reset_dev() to suspend any channels that were
previously active. This resets the network controller to a known state,
provides an up to date view of channel link state, and makes sure that
mode flags such as NCSI_MODE_TX_ENABLE are properly reset.
In addition to ncsi_start_dev() use ncsi_reset_dev() in ncsi-netlink.c
to update the channel configuration more cleanly.
Signed-off-by: Samuel Mendoza-Jonas <sam@mendozajonas.com>
---
net/ncsi/internal.h | 2 +
net/ncsi/ncsi-manage.c | 98 ++++++++++++++++++++++++++++++++++++++---
net/ncsi/ncsi-netlink.c | 12 ++---
3 files changed, 101 insertions(+), 11 deletions(-)
diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h
index ec65778c41f3..bda51cb179fe 100644
--- a/net/ncsi/internal.h
+++ b/net/ncsi/internal.h
@@ -287,6 +287,7 @@ struct ncsi_dev_priv {
#define NCSI_DEV_PROBED 1 /* Finalized NCSI topology */
#define NCSI_DEV_HWA 2 /* Enabled HW arbitration */
#define NCSI_DEV_RESHUFFLE 4
+#define NCSI_DEV_RESET 8 /* Reset state of NC */
unsigned int gma_flag; /* OEM GMA flag */
spinlock_t lock; /* Protect the NCSI device */
#if IS_ENABLED(CONFIG_IPV6)
@@ -342,6 +343,7 @@ extern spinlock_t ncsi_dev_lock;
list_for_each_entry_rcu(nc, &np->channels, node)
/* Resources */
+int ncsi_reset_dev(struct ncsi_dev *nd);
void ncsi_start_channel_monitor(struct ncsi_channel *nc);
void ncsi_stop_channel_monitor(struct ncsi_channel *nc);
struct ncsi_channel *ncsi_find_channel(struct ncsi_package *np,
diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c
index b9de5b78c4e9..4b07f5701186 100644
--- a/net/ncsi/ncsi-manage.c
+++ b/net/ncsi/ncsi-manage.c
@@ -550,8 +550,10 @@ static void ncsi_suspend_channel(struct ncsi_dev_priv *ndp)
spin_lock_irqsave(&nc->lock, flags);
nc->state = NCSI_CHANNEL_INACTIVE;
spin_unlock_irqrestore(&nc->lock, flags);
- ncsi_process_next_channel(ndp);
-
+ if (ndp->flags & NCSI_DEV_RESET)
+ ncsi_reset_dev(nd);
+ else
+ ncsi_process_next_channel(ndp);
break;
default:
netdev_warn(nd->dev, "Wrong NCSI state 0x%x in suspend\n",
@@ -897,6 +899,16 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp)
case ncsi_dev_state_config_done:
netdev_dbg(ndp->ndev.dev, "NCSI: channel %u config done\n",
nc->id);
+ if (ndp->flags & NCSI_DEV_RESET) {
+ /* A reset event happened during config, start it now */
+ spin_lock_irqsave(&nc->lock, flags);
+ nc->reconfigure_needed = false;
+ spin_unlock_irqrestore(&nc->lock, flags);
+ nd->state = ncsi_dev_state_functional;
+ ncsi_reset_dev(nd);
+ break;
+ }
+
spin_lock_irqsave(&nc->lock, flags);
if (nc->reconfigure_needed) {
/* This channel's configuration has been updated
@@ -1554,7 +1566,7 @@ int ncsi_start_dev(struct ncsi_dev *nd)
return 0;
}
- return ncsi_choose_active_channel(ndp);
+ return ncsi_reset_dev(nd);
}
EXPORT_SYMBOL_GPL(ncsi_start_dev);
@@ -1567,7 +1579,10 @@ void ncsi_stop_dev(struct ncsi_dev *nd)
int old_state;
unsigned long flags;
- /* Stop the channel monitor and reset channel's state */
+ /* Stop the channel monitor on any active channels. Don't reset the
+ * channel state so we know which were active when ncsi_start_dev()
+ * is next called.
+ */
NCSI_FOR_EACH_PACKAGE(ndp, np) {
NCSI_FOR_EACH_CHANNEL(np, nc) {
ncsi_stop_channel_monitor(nc);
@@ -1575,7 +1590,6 @@ void ncsi_stop_dev(struct ncsi_dev *nd)
spin_lock_irqsave(&nc->lock, flags);
chained = !list_empty(&nc->link);
old_state = nc->state;
- nc->state = NCSI_CHANNEL_INACTIVE;
spin_unlock_irqrestore(&nc->lock, flags);
WARN_ON_ONCE(chained ||
@@ -1588,6 +1602,80 @@ void ncsi_stop_dev(struct ncsi_dev *nd)
}
EXPORT_SYMBOL_GPL(ncsi_stop_dev);
+int ncsi_reset_dev(struct ncsi_dev *nd)
+{
+ struct ncsi_dev_priv *ndp = TO_NCSI_DEV_PRIV(nd);
+ struct ncsi_channel *nc, *active, *tmp;
+ struct ncsi_package *np;
+ unsigned long flags;
+
+ spin_lock_irqsave(&ndp->lock, flags);
+
+ if (!(ndp->flags & NCSI_DEV_RESET)) {
+ /* Haven't been called yet, check states */
+ switch (nd->state & ncsi_dev_state_major) {
+ case ncsi_dev_state_registered:
+ case ncsi_dev_state_probe:
+ /* Not even probed yet - do nothing */
+ spin_unlock_irqrestore(&ndp->lock, flags);
+ return 0;
+ case ncsi_dev_state_suspend:
+ case ncsi_dev_state_config:
+ /* Wait for the channel to finish its suspend/config
+ * operation; once it finishes it will check for
+ * NCSI_DEV_RESET and reset the state.
+ */
+ ndp->flags |= NCSI_DEV_RESET;
+ spin_unlock_irqrestore(&ndp->lock, flags);
+ return 0;
+ }
+ }
+
+ if (!list_empty(&ndp->channel_queue)) {
+ /* Clear any channel queue we may have interrupted */
+ list_for_each_entry_safe(nc, tmp, &ndp->channel_queue, link)
+ list_del_init(&nc->link);
+ }
+ spin_unlock_irqrestore(&ndp->lock, flags);
+
+ active = NULL;
+ NCSI_FOR_EACH_PACKAGE(ndp, np) {
+ NCSI_FOR_EACH_CHANNEL(np, nc) {
+ spin_lock_irqsave(&nc->lock, flags);
+
+ if (nc->state == NCSI_CHANNEL_ACTIVE) {
+ active = nc;
+ nc->state = NCSI_CHANNEL_INVISIBLE;
+ spin_unlock_irqrestore(&nc->lock, flags);
+ ncsi_stop_channel_monitor(nc);
+ break;
+ }
+
+ spin_unlock_irqrestore(&nc->lock, flags);
+ }
+ if (active)
+ break;
+ }
+
+ if (!active) {
+ /* Done */
+ spin_lock_irqsave(&ndp->lock, flags);
+ ndp->flags &= ~NCSI_DEV_RESET;
+ spin_unlock_irqrestore(&ndp->lock, flags);
+ return ncsi_choose_active_channel(ndp);
+ }
+
+ spin_lock_irqsave(&ndp->lock, flags);
+ ndp->flags |= NCSI_DEV_RESET;
+ ndp->active_channel = active;
+ ndp->active_package = active->package;
+ spin_unlock_irqrestore(&ndp->lock, flags);
+
+ nd->state = ncsi_dev_state_suspend;
+ schedule_work(&ndp->work);
+ return 0;
+}
+
void ncsi_unregister_dev(struct ncsi_dev *nd)
{
struct ncsi_dev_priv *ndp = TO_NCSI_DEV_PRIV(nd);
diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c
index 33314381b4f5..cde48fe43dba 100644
--- a/net/ncsi/ncsi-netlink.c
+++ b/net/ncsi/ncsi-netlink.c
@@ -330,9 +330,9 @@ static int ncsi_set_interface_nl(struct sk_buff *msg, struct genl_info *info)
package_id, channel_id,
channel_id == NCSI_RESERVED_CHANNEL ? " (any)" : "");
- /* Bounce the NCSI channel to set changes */
- ncsi_stop_dev(&ndp->ndev);
- ncsi_start_dev(&ndp->ndev);
+ /* Update channel configuration */
+ if (!(ndp->flags & NCSI_DEV_RESET))
+ ncsi_reset_dev(&ndp->ndev);
return 0;
}
@@ -360,9 +360,9 @@ static int ncsi_clear_interface_nl(struct sk_buff *msg, struct genl_info *info)
spin_unlock_irqrestore(&ndp->lock, flags);
netdev_info(ndp->ndev.dev, "NCSI: Cleared preferred package/channel\n");
- /* Bounce the NCSI channel to set changes */
- ncsi_stop_dev(&ndp->ndev);
- ncsi_start_dev(&ndp->ndev);
+ /* Update channel configuration */
+ if (!(ndp->flags & NCSI_DEV_RESET))
+ ncsi_reset_dev(&ndp->ndev);
return 0;
}
--
2.19.1
^ permalink raw reply related
* [PATCH net-next v3 6/6] net/ncsi: Configure multi-package, multi-channel modes with failover
From: Samuel Mendoza-Jonas @ 2018-11-08 2:49 UTC (permalink / raw)
To: netdev
Cc: Samuel Mendoza-Jonas, David S . Miller, Justin.Lee1, linux-kernel,
openbmc
In-Reply-To: <20181108024909.9897-1-sam@mendozajonas.com>
This patch extends the ncsi-netlink interface with two new commands and
three new attributes to configure multiple packages and/or channels at
once, and configure specific failover modes.
NCSI_CMD_SET_PACKAGE mask and NCSI_CMD_SET_CHANNEL_MASK set a whitelist
of packages or channels allowed to be configured with the
NCSI_ATTR_PACKAGE_MASK and NCSI_ATTR_CHANNEL_MASK attributes
respectively. If one of these whitelists is set only packages or
channels matching the whitelist are considered for the channel queue in
ncsi_choose_active_channel().
These commands may also use the NCSI_ATTR_MULTI_FLAG to signal that
multiple packages or channels may be configured simultaneously. NCSI
hardware arbitration (HWA) must be available in order to enable
multi-package mode. Multi-channel mode is always available.
If the NCSI_ATTR_CHANNEL_ID attribute is present in the
NCSI_CMD_SET_CHANNEL_MASK command the it sets the preferred channel as
with the NCSI_CMD_SET_INTERFACE command. The combination of preferred
channel and channel whitelist defines a primary channel and the allowed
failover channels.
If the NCSI_ATTR_MULTI_FLAG attribute is also present then the preferred
channel is configured for Tx/Rx and the other channels are enabled only
for Rx.
Signed-off-by: Samuel Mendoza-Jonas <sam@mendozajonas.com>
---
include/uapi/linux/ncsi.h | 15 +++
net/ncsi/internal.h | 16 ++-
net/ncsi/ncsi-aen.c | 60 +++++++--
net/ncsi/ncsi-manage.c | 264 +++++++++++++++++++++++++++++++-------
net/ncsi/ncsi-netlink.c | 221 +++++++++++++++++++++++++++----
net/ncsi/ncsi-rsp.c | 2 +-
6 files changed, 490 insertions(+), 88 deletions(-)
diff --git a/include/uapi/linux/ncsi.h b/include/uapi/linux/ncsi.h
index 0a26a5576645..a3f87c54fdb3 100644
--- a/include/uapi/linux/ncsi.h
+++ b/include/uapi/linux/ncsi.h
@@ -26,6 +26,12 @@
* @NCSI_CMD_SEND_CMD: send NC-SI command to network card.
* Requires NCSI_ATTR_IFINDEX, NCSI_ATTR_PACKAGE_ID
* and NCSI_ATTR_CHANNEL_ID.
+ * @NCSI_CMD_SET_PACKAGE_MASK: set a whitelist of allowed packages.
+ * Requires NCSI_ATTR_IFINDEX and NCSI_ATTR_PACKAGE_MASK.
+ * @NCSI_CMD_SET_CHANNEL_MASK: set a whitelist of allowed channels.
+ * Requires NCSI_ATTR_IFINDEX, NCSI_ATTR_PACKAGE_ID, and
+ * NCSI_ATTR_CHANNEL_MASK. If NCSI_ATTR_CHANNEL_ID is present it sets
+ * the primary channel.
* @NCSI_CMD_MAX: highest command number
*/
enum ncsi_nl_commands {
@@ -34,6 +40,8 @@ enum ncsi_nl_commands {
NCSI_CMD_SET_INTERFACE,
NCSI_CMD_CLEAR_INTERFACE,
NCSI_CMD_SEND_CMD,
+ NCSI_CMD_SET_PACKAGE_MASK,
+ NCSI_CMD_SET_CHANNEL_MASK,
__NCSI_CMD_AFTER_LAST,
NCSI_CMD_MAX = __NCSI_CMD_AFTER_LAST - 1
@@ -48,6 +56,10 @@ enum ncsi_nl_commands {
* @NCSI_ATTR_PACKAGE_ID: package ID
* @NCSI_ATTR_CHANNEL_ID: channel ID
* @NCSI_ATTR_DATA: command payload
+ * @NCSI_ATTR_MULTI_FLAG: flag to signal that multi-mode should be enabled with
+ * NCSI_CMD_SET_PACKAGE_MASK or NCSI_CMD_SET_CHANNEL_MASK.
+ * @NCSI_ATTR_PACKAGE_MASK: 32-bit mask of allowed packages.
+ * @NCSI_ATTR_CHANNEL_MASK: 32-bit mask of allowed channels.
* @NCSI_ATTR_MAX: highest attribute number
*/
enum ncsi_nl_attrs {
@@ -57,6 +69,9 @@ enum ncsi_nl_attrs {
NCSI_ATTR_PACKAGE_ID,
NCSI_ATTR_CHANNEL_ID,
NCSI_ATTR_DATA,
+ NCSI_ATTR_MULTI_FLAG,
+ NCSI_ATTR_PACKAGE_MASK,
+ NCSI_ATTR_CHANNEL_MASK,
__NCSI_ATTR_AFTER_LAST,
NCSI_ATTR_MAX = __NCSI_ATTR_AFTER_LAST - 1
diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h
index bda51cb179fe..9e3642b802c4 100644
--- a/net/ncsi/internal.h
+++ b/net/ncsi/internal.h
@@ -222,6 +222,10 @@ struct ncsi_package {
unsigned int channel_num; /* Number of channels */
struct list_head channels; /* List of chanels */
struct list_head node; /* Form list of packages */
+
+ bool multi_channel; /* Enable multiple channels */
+ u32 channel_whitelist; /* Channels to configure */
+ struct ncsi_channel *preferred_channel; /* Primary channel */
};
struct ncsi_request {
@@ -297,8 +301,6 @@ struct ncsi_dev_priv {
unsigned int package_num; /* Number of packages */
struct list_head packages; /* List of packages */
struct ncsi_channel *hot_channel; /* Channel was ever active */
- struct ncsi_package *force_package; /* Force a specific package */
- struct ncsi_channel *force_channel; /* Force a specific channel */
struct ncsi_request requests[256]; /* Request table */
unsigned int request_id; /* Last used request ID */
#define NCSI_REQ_START_IDX 1
@@ -311,6 +313,9 @@ struct ncsi_dev_priv {
struct list_head node; /* Form NCSI device list */
#define NCSI_MAX_VLAN_VIDS 15
struct list_head vlan_vids; /* List of active VLAN IDs */
+
+ bool multi_package; /* Enable multiple packages */
+ u32 package_whitelist; /* Packages to configure */
};
struct ncsi_cmd_arg {
@@ -364,6 +369,13 @@ struct ncsi_request *ncsi_alloc_request(struct ncsi_dev_priv *ndp,
void ncsi_free_request(struct ncsi_request *nr);
struct ncsi_dev *ncsi_find_dev(struct net_device *dev);
int ncsi_process_next_channel(struct ncsi_dev_priv *ndp);
+bool ncsi_channel_has_link(struct ncsi_channel *channel);
+bool ncsi_channel_is_last(struct ncsi_dev_priv *ndp,
+ struct ncsi_channel *channel);
+int ncsi_update_tx_channel(struct ncsi_dev_priv *ndp,
+ struct ncsi_package *np,
+ struct ncsi_channel *disable,
+ struct ncsi_channel *enable);
/* Packet handlers */
u32 ncsi_calculate_checksum(unsigned char *data, int len);
diff --git a/net/ncsi/ncsi-aen.c b/net/ncsi/ncsi-aen.c
index 57f77e5d381a..39c2e9eea2ba 100644
--- a/net/ncsi/ncsi-aen.c
+++ b/net/ncsi/ncsi-aen.c
@@ -50,14 +50,15 @@ static int ncsi_validate_aen_pkt(struct ncsi_aen_pkt_hdr *h,
static int ncsi_aen_handler_lsc(struct ncsi_dev_priv *ndp,
struct ncsi_aen_pkt_hdr *h)
{
- struct ncsi_aen_lsc_pkt *lsc;
- struct ncsi_channel *nc;
+ struct ncsi_channel *nc, *tmp;
struct ncsi_channel_mode *ncm;
- bool chained;
- int state;
unsigned long old_data, data;
- unsigned long flags;
+ struct ncsi_aen_lsc_pkt *lsc;
+ struct ncsi_package *np;
bool had_link, has_link;
+ unsigned long flags;
+ bool chained;
+ int state;
/* Find the NCSI channel */
ncsi_find_package_and_channel(ndp, h->common.channel, NULL, &nc);
@@ -92,14 +93,49 @@ static int ncsi_aen_handler_lsc(struct ncsi_dev_priv *ndp,
if ((had_link == has_link) || chained)
return 0;
- if (had_link)
- ndp->flags |= NCSI_DEV_RESHUFFLE;
- ncsi_stop_channel_monitor(nc);
- spin_lock_irqsave(&ndp->lock, flags);
- list_add_tail_rcu(&nc->link, &ndp->channel_queue);
- spin_unlock_irqrestore(&ndp->lock, flags);
+ if (!ndp->multi_package && !nc->package->multi_channel) {
+ if (had_link)
+ ndp->flags |= NCSI_DEV_RESHUFFLE;
+ ncsi_stop_channel_monitor(nc);
+ spin_lock_irqsave(&ndp->lock, flags);
+ list_add_tail_rcu(&nc->link, &ndp->channel_queue);
+ spin_unlock_irqrestore(&ndp->lock, flags);
+ return ncsi_process_next_channel(ndp);
+ }
- return ncsi_process_next_channel(ndp);
+ if (had_link) {
+ ncm = &nc->modes[NCSI_MODE_TX_ENABLE];
+ if (ncsi_channel_is_last(ndp, nc)) {
+ /* No channels left, reconfigure */
+ return ncsi_reset_dev(&ndp->ndev);
+ } else if (ncm->enable) {
+ /* Need to failover Tx channel */
+ ncsi_update_tx_channel(ndp, nc->package, nc, NULL);
+ }
+ } else if (has_link && nc->package->preferred_channel == nc) {
+ /* Return Tx to preferred channel */
+ ncsi_update_tx_channel(ndp, nc->package, NULL, nc);
+ } else if (has_link) {
+ NCSI_FOR_EACH_PACKAGE(ndp, np) {
+ NCSI_FOR_EACH_CHANNEL(np, tmp) {
+ /* Enable Tx on this channel if the current Tx
+ * channel is down.
+ */
+ ncm = &tmp->modes[NCSI_MODE_TX_ENABLE];
+ if (ncm->enable &&
+ !ncsi_channel_has_link(tmp)) {
+ ncsi_update_tx_channel(ndp, nc->package,
+ tmp, nc);
+ break;
+ }
+ }
+ }
+ }
+
+ /* Leave configured channels active in a multi-channel scenario so
+ * AEN events are still received.
+ */
+ return 0;
}
static int ncsi_aen_handler_cr(struct ncsi_dev_priv *ndp,
diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c
index 4b07f5701186..fa3c2144f5ba 100644
--- a/net/ncsi/ncsi-manage.c
+++ b/net/ncsi/ncsi-manage.c
@@ -28,6 +28,29 @@
LIST_HEAD(ncsi_dev_list);
DEFINE_SPINLOCK(ncsi_dev_lock);
+bool ncsi_channel_has_link(struct ncsi_channel *channel)
+{
+ return !!(channel->modes[NCSI_MODE_LINK].data[2] & 0x1);
+}
+
+bool ncsi_channel_is_last(struct ncsi_dev_priv *ndp,
+ struct ncsi_channel *channel)
+{
+ struct ncsi_package *np;
+ struct ncsi_channel *nc;
+
+ NCSI_FOR_EACH_PACKAGE(ndp, np)
+ NCSI_FOR_EACH_CHANNEL(np, nc) {
+ if (nc == channel)
+ continue;
+ if (nc->state == NCSI_CHANNEL_ACTIVE &&
+ ncsi_channel_has_link(nc))
+ return false;
+ }
+
+ return true;
+}
+
static void ncsi_report_link(struct ncsi_dev_priv *ndp, bool force_down)
{
struct ncsi_dev *nd = &ndp->ndev;
@@ -52,7 +75,7 @@ static void ncsi_report_link(struct ncsi_dev_priv *ndp, bool force_down)
continue;
}
- if (nc->modes[NCSI_MODE_LINK].data[2] & 0x1) {
+ if (ncsi_channel_has_link(nc)) {
spin_unlock_irqrestore(&nc->lock, flags);
nd->link_up = 1;
goto report;
@@ -267,6 +290,7 @@ struct ncsi_package *ncsi_add_package(struct ncsi_dev_priv *ndp,
np->ndp = ndp;
spin_lock_init(&np->lock);
INIT_LIST_HEAD(&np->channels);
+ np->channel_whitelist = UINT_MAX;
spin_lock_irqsave(&ndp->lock, flags);
tmp = ncsi_find_package(ndp, id);
@@ -728,13 +752,144 @@ static int ncsi_gma_handler(struct ncsi_cmd_arg *nca, unsigned int mf_id)
#endif /* CONFIG_NCSI_OEM_CMD_GET_MAC */
+/* Determine if a given channel from the channel_queue should be used for Tx */
+static bool ncsi_channel_is_tx(struct ncsi_dev_priv *ndp,
+ struct ncsi_channel *nc)
+{
+ struct ncsi_channel_mode *ncm;
+ struct ncsi_channel *channel;
+ struct ncsi_package *np;
+
+ /* Check if any other channel has Tx enabled; a channel may have already
+ * been configured and removed from the channel queue.
+ */
+ NCSI_FOR_EACH_PACKAGE(ndp, np) {
+ if (!ndp->multi_package && np != nc->package)
+ continue;
+ NCSI_FOR_EACH_CHANNEL(np, channel) {
+ ncm = &channel->modes[NCSI_MODE_TX_ENABLE];
+ if (ncm->enable)
+ return false;
+ }
+ }
+
+ /* This channel is the preferred channel and has link */
+ list_for_each_entry_rcu(channel, &ndp->channel_queue, link) {
+ np = channel->package;
+ if (np->preferred_channel &&
+ ncsi_channel_has_link(np->preferred_channel)) {
+ return np->preferred_channel == nc;
+ }
+ }
+
+ /* This channel has link */
+ if (ncsi_channel_has_link(nc))
+ return true;
+
+ list_for_each_entry_rcu(channel, &ndp->channel_queue, link)
+ if (ncsi_channel_has_link(channel))
+ return false;
+
+ /* No other channel has link; default to this one */
+ return true;
+}
+
+/* Change the active Tx channel in a multi-channel setup */
+int ncsi_update_tx_channel(struct ncsi_dev_priv *ndp,
+ struct ncsi_package *package,
+ struct ncsi_channel *disable,
+ struct ncsi_channel *enable)
+{
+ struct ncsi_cmd_arg nca;
+ struct ncsi_channel *nc;
+ struct ncsi_package *np;
+ int ret = 0;
+
+ if (!package->multi_channel && !ndp->multi_package)
+ netdev_warn(ndp->ndev.dev,
+ "NCSI: Trying to update Tx channel in single-channel mode\n");
+ nca.ndp = ndp;
+ nca.req_flags = 0;
+
+ /* Find current channel with Tx enabled */
+ NCSI_FOR_EACH_PACKAGE(ndp, np) {
+ if (disable)
+ break;
+ if (!ndp->multi_package && np != package)
+ continue;
+
+ NCSI_FOR_EACH_CHANNEL(np, nc)
+ if (nc->modes[NCSI_MODE_TX_ENABLE].enable) {
+ disable = nc;
+ break;
+ }
+ }
+
+ /* Find a suitable channel for Tx */
+ NCSI_FOR_EACH_PACKAGE(ndp, np) {
+ if (enable)
+ break;
+ if (!ndp->multi_package && np != package)
+ continue;
+ if (!(ndp->package_whitelist & (0x1 << np->id)))
+ continue;
+
+ if (np->preferred_channel &&
+ ncsi_channel_has_link(np->preferred_channel)) {
+ enable = np->preferred_channel;
+ break;
+ }
+
+ NCSI_FOR_EACH_CHANNEL(np, nc) {
+ if (!(np->channel_whitelist & 0x1 << nc->id))
+ continue;
+ if (nc->state != NCSI_CHANNEL_ACTIVE)
+ continue;
+ if (ncsi_channel_has_link(nc)) {
+ enable = nc;
+ break;
+ }
+ }
+ }
+
+ if (disable == enable)
+ return -1;
+
+ if (!enable)
+ return -1;
+
+ if (disable) {
+ nca.channel = disable->id;
+ nca.package = disable->package->id;
+ nca.type = NCSI_PKT_CMD_DCNT;
+ ret = ncsi_xmit_cmd(&nca);
+ if (ret)
+ netdev_err(ndp->ndev.dev,
+ "Error %d sending DCNT\n",
+ ret);
+ }
+
+ netdev_info(ndp->ndev.dev, "NCSI: channel %u enables Tx\n", enable->id);
+
+ nca.channel = enable->id;
+ nca.package = enable->package->id;
+ nca.type = NCSI_PKT_CMD_ECNT;
+ ret = ncsi_xmit_cmd(&nca);
+ if (ret)
+ netdev_err(ndp->ndev.dev,
+ "Error %d sending ECNT\n",
+ ret);
+
+ return ret;
+}
+
static void ncsi_configure_channel(struct ncsi_dev_priv *ndp)
{
- struct ncsi_dev *nd = &ndp->ndev;
- struct net_device *dev = nd->dev;
struct ncsi_package *np = ndp->active_package;
struct ncsi_channel *nc = ndp->active_channel;
struct ncsi_channel *hot_nc = NULL;
+ struct ncsi_dev *nd = &ndp->ndev;
+ struct net_device *dev = nd->dev;
struct ncsi_cmd_arg nca;
unsigned char index;
unsigned long flags;
@@ -856,20 +1011,29 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp)
} else if (nd->state == ncsi_dev_state_config_ebf) {
nca.type = NCSI_PKT_CMD_EBF;
nca.dwords[0] = nc->caps[NCSI_CAP_BC].cap;
- nd->state = ncsi_dev_state_config_ecnt;
+ if (ncsi_channel_is_tx(ndp, nc))
+ nd->state = ncsi_dev_state_config_ecnt;
+ else
+ nd->state = ncsi_dev_state_config_ec;
#if IS_ENABLED(CONFIG_IPV6)
if (ndp->inet6_addr_num > 0 &&
(nc->caps[NCSI_CAP_GENERIC].cap &
NCSI_CAP_GENERIC_MC))
nd->state = ncsi_dev_state_config_egmf;
- else
- nd->state = ncsi_dev_state_config_ecnt;
} else if (nd->state == ncsi_dev_state_config_egmf) {
nca.type = NCSI_PKT_CMD_EGMF;
nca.dwords[0] = nc->caps[NCSI_CAP_MC].cap;
- nd->state = ncsi_dev_state_config_ecnt;
+ if (ncsi_channel_is_tx(ndp, nc))
+ nd->state = ncsi_dev_state_config_ecnt;
+ else
+ nd->state = ncsi_dev_state_config_ec;
#endif /* CONFIG_IPV6 */
} else if (nd->state == ncsi_dev_state_config_ecnt) {
+ if (np->preferred_channel &&
+ nc != np->preferred_channel)
+ netdev_info(ndp->ndev.dev,
+ "NCSI: Tx failed over to channel %u\n",
+ nc->id);
nca.type = NCSI_PKT_CMD_ECNT;
nd->state = ncsi_dev_state_config_ec;
} else if (nd->state == ncsi_dev_state_config_ec) {
@@ -960,43 +1124,35 @@ static void ncsi_configure_channel(struct ncsi_dev_priv *ndp)
static int ncsi_choose_active_channel(struct ncsi_dev_priv *ndp)
{
- struct ncsi_package *np, *force_package;
- struct ncsi_channel *nc, *found, *hot_nc, *force_channel;
+ struct ncsi_channel *nc, *found, *hot_nc;
struct ncsi_channel_mode *ncm;
- unsigned long flags;
+ unsigned long flags, cflags;
+ struct ncsi_package *np;
+ bool with_link;
spin_lock_irqsave(&ndp->lock, flags);
hot_nc = ndp->hot_channel;
- force_channel = ndp->force_channel;
- force_package = ndp->force_package;
spin_unlock_irqrestore(&ndp->lock, flags);
- /* Force a specific channel whether or not it has link if we have been
- * configured to do so
- */
- if (force_package && force_channel) {
- found = force_channel;
- ncm = &found->modes[NCSI_MODE_LINK];
- if (!(ncm->data[2] & 0x1))
- netdev_info(ndp->ndev.dev,
- "NCSI: Channel %u forced, but it is link down\n",
- found->id);
- goto out;
- }
-
- /* The search is done once an inactive channel with up
- * link is found.
+ /* By default the search is done once an inactive channel with up
+ * link is found, unless a preferred channel is set.
+ * If multi_package or multi_channel are configured all channels in the
+ * whitelist are added to the channel queue.
*/
found = NULL;
+ with_link = false;
NCSI_FOR_EACH_PACKAGE(ndp, np) {
- if (ndp->force_package && np != ndp->force_package)
+ if (!(ndp->package_whitelist & (0x1 << np->id)))
continue;
NCSI_FOR_EACH_CHANNEL(np, nc) {
- spin_lock_irqsave(&nc->lock, flags);
+ if (!(np->channel_whitelist & (0x1 << nc->id)))
+ continue;
+
+ spin_lock_irqsave(&nc->lock, cflags);
if (!list_empty(&nc->link) ||
nc->state != NCSI_CHANNEL_INACTIVE) {
- spin_unlock_irqrestore(&nc->lock, flags);
+ spin_unlock_irqrestore(&nc->lock, cflags);
continue;
}
@@ -1008,32 +1164,49 @@ static int ncsi_choose_active_channel(struct ncsi_dev_priv *ndp)
ncm = &nc->modes[NCSI_MODE_LINK];
if (ncm->data[2] & 0x1) {
- spin_unlock_irqrestore(&nc->lock, flags);
found = nc;
- goto out;
+ with_link = true;
}
- spin_unlock_irqrestore(&nc->lock, flags);
+ /* If multi_channel is enabled configure all valid
+ * channels whether or not they currently have link
+ * so they will have AENs enabled.
+ */
+ if (with_link || np->multi_channel) {
+ spin_lock_irqsave(&ndp->lock, flags);
+ list_add_tail_rcu(&nc->link,
+ &ndp->channel_queue);
+ spin_unlock_irqrestore(&ndp->lock, flags);
+
+ netdev_dbg(ndp->ndev.dev,
+ "NCSI: Channel %u added to queue (link %s)\n",
+ nc->id,
+ ncm->data[2] & 0x1 ? "up" : "down");
+ }
+
+ spin_unlock_irqrestore(&nc->lock, cflags);
+
+ if (with_link && !np->multi_channel)
+ break;
}
+ if (with_link && !ndp->multi_package)
+ break;
}
- if (!found) {
+ if (list_empty(&ndp->channel_queue) && found) {
+ netdev_info(ndp->ndev.dev,
+ "NCSI: No channel with link found, configuring channel %u\n",
+ found->id);
+ spin_lock_irqsave(&ndp->lock, flags);
+ list_add_tail_rcu(&found->link, &ndp->channel_queue);
+ spin_unlock_irqrestore(&ndp->lock, flags);
+ } else if (!found) {
netdev_warn(ndp->ndev.dev,
- "NCSI: No channel found with link\n");
+ "NCSI: No channel found to configure!\n");
ncsi_report_link(ndp, true);
return -ENODEV;
}
- ncm = &found->modes[NCSI_MODE_LINK];
- netdev_dbg(ndp->ndev.dev,
- "NCSI: Channel %u added to queue (link %s)\n",
- found->id, ncm->data[2] & 0x1 ? "up" : "down");
-
-out:
- spin_lock_irqsave(&ndp->lock, flags);
- list_add_tail_rcu(&found->link, &ndp->channel_queue);
- spin_unlock_irqrestore(&ndp->lock, flags);
-
return ncsi_process_next_channel(ndp);
}
@@ -1518,6 +1691,7 @@ struct ncsi_dev *ncsi_register_dev(struct net_device *dev,
INIT_LIST_HEAD(&ndp->channel_queue);
INIT_LIST_HEAD(&ndp->vlan_vids);
INIT_WORK(&ndp->work, ncsi_dev_work);
+ ndp->package_whitelist = UINT_MAX;
/* Initialize private NCSI device */
spin_lock_init(&ndp->lock);
diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c
index cde48fe43dba..5d782445d2fc 100644
--- a/net/ncsi/ncsi-netlink.c
+++ b/net/ncsi/ncsi-netlink.c
@@ -30,6 +30,9 @@ static const struct nla_policy ncsi_genl_policy[NCSI_ATTR_MAX + 1] = {
[NCSI_ATTR_PACKAGE_ID] = { .type = NLA_U32 },
[NCSI_ATTR_CHANNEL_ID] = { .type = NLA_U32 },
[NCSI_ATTR_DATA] = { .type = NLA_BINARY, .len = 2048 },
+ [NCSI_ATTR_MULTI_FLAG] = { .type = NLA_FLAG },
+ [NCSI_ATTR_PACKAGE_MASK] = { .type = NLA_U32 },
+ [NCSI_ATTR_CHANNEL_MASK] = { .type = NLA_U32 },
};
static struct ncsi_dev_priv *ndp_from_ifindex(struct net *net, u32 ifindex)
@@ -69,7 +72,7 @@ static int ncsi_write_channel_info(struct sk_buff *skb,
nla_put_u32(skb, NCSI_CHANNEL_ATTR_LINK_STATE, m->data[2]);
if (nc->state == NCSI_CHANNEL_ACTIVE)
nla_put_flag(skb, NCSI_CHANNEL_ATTR_ACTIVE);
- if (ndp->force_channel == nc)
+ if (nc == nc->package->preferred_channel)
nla_put_flag(skb, NCSI_CHANNEL_ATTR_FORCED);
nla_put_u32(skb, NCSI_CHANNEL_ATTR_VERSION_MAJOR, nc->version.version);
@@ -114,7 +117,7 @@ static int ncsi_write_package_info(struct sk_buff *skb,
if (!pnest)
return -ENOMEM;
nla_put_u32(skb, NCSI_PKG_ATTR_ID, np->id);
- if (ndp->force_package == np)
+ if ((0x1 << np->id) == ndp->package_whitelist)
nla_put_flag(skb, NCSI_PKG_ATTR_FORCED);
cnest = nla_nest_start(skb, NCSI_PKG_ATTR_CHANNEL_LIST);
if (!cnest) {
@@ -290,45 +293,54 @@ static int ncsi_set_interface_nl(struct sk_buff *msg, struct genl_info *info)
package_id = nla_get_u32(info->attrs[NCSI_ATTR_PACKAGE_ID]);
package = NULL;
- spin_lock_irqsave(&ndp->lock, flags);
-
NCSI_FOR_EACH_PACKAGE(ndp, np)
if (np->id == package_id)
package = np;
if (!package) {
/* The user has set a package that does not exist */
- spin_unlock_irqrestore(&ndp->lock, flags);
return -ERANGE;
}
channel = NULL;
- if (!info->attrs[NCSI_ATTR_CHANNEL_ID]) {
- /* Allow any channel */
- channel_id = NCSI_RESERVED_CHANNEL;
- } else {
+ if (info->attrs[NCSI_ATTR_CHANNEL_ID]) {
channel_id = nla_get_u32(info->attrs[NCSI_ATTR_CHANNEL_ID]);
NCSI_FOR_EACH_CHANNEL(package, nc)
- if (nc->id == channel_id)
+ if (nc->id == channel_id) {
channel = nc;
+ break;
+ }
+ if (!channel) {
+ netdev_info(ndp->ndev.dev,
+ "NCSI: Channel %u does not exist!\n",
+ channel_id);
+ return -ERANGE;
+ }
}
- if (channel_id != NCSI_RESERVED_CHANNEL && !channel) {
- /* The user has set a channel that does not exist on this
- * package
- */
- spin_unlock_irqrestore(&ndp->lock, flags);
- netdev_info(ndp->ndev.dev, "NCSI: Channel %u does not exist!\n",
- channel_id);
- return -ERANGE;
- }
-
- ndp->force_package = package;
- ndp->force_channel = channel;
+ spin_lock_irqsave(&ndp->lock, flags);
+ ndp->package_whitelist = 0x1 << package->id;
+ ndp->multi_package = false;
spin_unlock_irqrestore(&ndp->lock, flags);
- netdev_info(ndp->ndev.dev, "Set package 0x%x, channel 0x%x%s as preferred\n",
- package_id, channel_id,
- channel_id == NCSI_RESERVED_CHANNEL ? " (any)" : "");
+ spin_lock_irqsave(&package->lock, flags);
+ package->multi_channel = false;
+ if (channel) {
+ package->channel_whitelist = 0x1 << channel->id;
+ package->preferred_channel = channel;
+ } else {
+ /* Allow any channel */
+ package->channel_whitelist = UINT_MAX;
+ package->preferred_channel = NULL;
+ }
+ spin_unlock_irqrestore(&package->lock, flags);
+
+ if (channel)
+ netdev_info(ndp->ndev.dev,
+ "Set package 0x%x, channel 0x%x as preferred\n",
+ package_id, channel_id);
+ else
+ netdev_info(ndp->ndev.dev, "Set package 0x%x as preferred\n",
+ package_id);
/* Update channel configuration */
if (!(ndp->flags & NCSI_DEV_RESET))
@@ -340,6 +352,7 @@ static int ncsi_set_interface_nl(struct sk_buff *msg, struct genl_info *info)
static int ncsi_clear_interface_nl(struct sk_buff *msg, struct genl_info *info)
{
struct ncsi_dev_priv *ndp;
+ struct ncsi_package *np;
unsigned long flags;
if (!info || !info->attrs)
@@ -353,11 +366,19 @@ static int ncsi_clear_interface_nl(struct sk_buff *msg, struct genl_info *info)
if (!ndp)
return -ENODEV;
- /* Clear any override */
+ /* Reset any whitelists and disable multi mode */
spin_lock_irqsave(&ndp->lock, flags);
- ndp->force_package = NULL;
- ndp->force_channel = NULL;
+ ndp->package_whitelist = UINT_MAX;
+ ndp->multi_package = false;
spin_unlock_irqrestore(&ndp->lock, flags);
+
+ NCSI_FOR_EACH_PACKAGE(ndp, np) {
+ spin_lock_irqsave(&np->lock, flags);
+ np->multi_channel = false;
+ np->channel_whitelist = UINT_MAX;
+ np->preferred_channel = NULL;
+ spin_unlock_irqrestore(&np->lock, flags);
+ }
netdev_info(ndp->ndev.dev, "NCSI: Cleared preferred package/channel\n");
/* Update channel configuration */
@@ -563,6 +584,138 @@ int ncsi_send_netlink_err(struct net_device *dev,
return nlmsg_unicast(net->genl_sock, skb, snd_portid);
}
+static int ncsi_set_package_mask_nl(struct sk_buff *msg,
+ struct genl_info *info)
+{
+ struct ncsi_dev_priv *ndp;
+ unsigned long flags;
+ int rc;
+
+ if (!info || !info->attrs)
+ return -EINVAL;
+
+ if (!info->attrs[NCSI_ATTR_IFINDEX])
+ return -EINVAL;
+
+ if (!info->attrs[NCSI_ATTR_PACKAGE_MASK])
+ return -EINVAL;
+
+ ndp = ndp_from_ifindex(get_net(sock_net(msg->sk)),
+ nla_get_u32(info->attrs[NCSI_ATTR_IFINDEX]));
+ if (!ndp)
+ return -ENODEV;
+
+ spin_lock_irqsave(&ndp->lock, flags);
+ if (nla_get_flag(info->attrs[NCSI_ATTR_MULTI_FLAG])) {
+ if (ndp->flags & NCSI_DEV_HWA) {
+ ndp->multi_package = true;
+ rc = 0;
+ } else {
+ netdev_err(ndp->ndev.dev,
+ "NCSI: Can't use multiple packages without HWA\n");
+ rc = -EPERM;
+ }
+ } else {
+ ndp->multi_package = false;
+ rc = 0;
+ }
+
+ if (!rc)
+ ndp->package_whitelist =
+ nla_get_u32(info->attrs[NCSI_ATTR_PACKAGE_MASK]);
+ spin_unlock_irqrestore(&ndp->lock, flags);
+
+ if (!rc) {
+ /* Update channel configuration */
+ if (!(ndp->flags & NCSI_DEV_RESET))
+ ncsi_reset_dev(&ndp->ndev);
+ }
+
+ return rc;
+}
+
+static int ncsi_set_channel_mask_nl(struct sk_buff *msg,
+ struct genl_info *info)
+{
+ struct ncsi_package *np, *package;
+ struct ncsi_channel *nc, *channel;
+ u32 package_id, channel_id;
+ struct ncsi_dev_priv *ndp;
+ unsigned long flags;
+
+ if (!info || !info->attrs)
+ return -EINVAL;
+
+ if (!info->attrs[NCSI_ATTR_IFINDEX])
+ return -EINVAL;
+
+ if (!info->attrs[NCSI_ATTR_PACKAGE_ID])
+ return -EINVAL;
+
+ if (!info->attrs[NCSI_ATTR_CHANNEL_MASK])
+ return -EINVAL;
+
+ ndp = ndp_from_ifindex(get_net(sock_net(msg->sk)),
+ nla_get_u32(info->attrs[NCSI_ATTR_IFINDEX]));
+ if (!ndp)
+ return -ENODEV;
+
+ package_id = nla_get_u32(info->attrs[NCSI_ATTR_PACKAGE_ID]);
+ package = NULL;
+ NCSI_FOR_EACH_PACKAGE(ndp, np)
+ if (np->id == package_id) {
+ package = np;
+ break;
+ }
+ if (!package)
+ return -ERANGE;
+
+ spin_lock_irqsave(&package->lock, flags);
+
+ channel = NULL;
+ if (info->attrs[NCSI_ATTR_CHANNEL_ID]) {
+ channel_id = nla_get_u32(info->attrs[NCSI_ATTR_CHANNEL_ID]);
+ NCSI_FOR_EACH_CHANNEL(np, nc)
+ if (nc->id == channel_id) {
+ channel = nc;
+ break;
+ }
+ if (!channel) {
+ spin_unlock_irqrestore(&package->lock, flags);
+ return -ERANGE;
+ }
+ netdev_dbg(ndp->ndev.dev,
+ "NCSI: Channel %u set as preferred channel\n",
+ channel->id);
+ }
+
+ package->channel_whitelist =
+ nla_get_u32(info->attrs[NCSI_ATTR_CHANNEL_MASK]);
+ if (package->channel_whitelist == 0)
+ netdev_dbg(ndp->ndev.dev,
+ "NCSI: Package %u set to all channels disabled\n",
+ package->id);
+
+ package->preferred_channel = channel;
+
+ if (nla_get_flag(info->attrs[NCSI_ATTR_MULTI_FLAG])) {
+ package->multi_channel = true;
+ netdev_info(ndp->ndev.dev,
+ "NCSI: Multi-channel enabled on package %u\n",
+ package_id);
+ } else {
+ package->multi_channel = false;
+ }
+
+ spin_unlock_irqrestore(&package->lock, flags);
+
+ /* Update channel configuration */
+ if (!(ndp->flags & NCSI_DEV_RESET))
+ ncsi_reset_dev(&ndp->ndev);
+
+ return 0;
+}
+
static const struct genl_ops ncsi_ops[] = {
{
.cmd = NCSI_CMD_PKG_INFO,
@@ -589,6 +742,18 @@ static const struct genl_ops ncsi_ops[] = {
.doit = ncsi_send_cmd_nl,
.flags = GENL_ADMIN_PERM,
},
+ {
+ .cmd = NCSI_CMD_SET_PACKAGE_MASK,
+ .policy = ncsi_genl_policy,
+ .doit = ncsi_set_package_mask_nl,
+ .flags = GENL_ADMIN_PERM,
+ },
+ {
+ .cmd = NCSI_CMD_SET_CHANNEL_MASK,
+ .policy = ncsi_genl_policy,
+ .doit = ncsi_set_channel_mask_nl,
+ .flags = GENL_ADMIN_PERM,
+ },
};
static struct genl_family ncsi_genl_family __ro_after_init = {
diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c
index 77e07ba3f493..de7737a27889 100644
--- a/net/ncsi/ncsi-rsp.c
+++ b/net/ncsi/ncsi-rsp.c
@@ -256,7 +256,7 @@ static int ncsi_rsp_handler_dcnt(struct ncsi_request *nr)
if (!ncm->enable)
return 0;
- ncm->enable = 1;
+ ncm->enable = 0;
return 0;
}
--
2.19.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox