* [PATCH net-next 01/11] net-next: Add netif_get_num_default_rss_queues
From: Yuval Mintz @ 2012-07-01 13:18 UTC (permalink / raw)
To: davem, netdev; +Cc: eilong, Yuval Mintz
In-Reply-To: <1341148740-7375-1-git-send-email-yuvalmin@broadcom.com>
Most multi-queue networking driver consider the number of online cpus when
configuring RSS queues.
This patch adds a wrapper to the number of cpus, setting an upper limit on the
number of cpus a driver should consider (by default) when allocating resources
for his queues.
Signed-off-by: Yuval Mintz <yuvalmin@broadcom.com>
Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
---
include/linux/netdevice.h | 3 +++
net/core/dev.c | 11 +++++++++++
2 files changed, 14 insertions(+), 0 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 2c2ecea..ab0251d 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2119,6 +2119,9 @@ static inline int netif_copy_real_num_queues(struct net_device *to_dev,
#endif
}
+#define DEFAULT_MAX_NUM_RSS_QUEUES (8)
+extern int netif_get_num_default_rss_queues(void);
+
/* Use this variant when it is known for sure that it
* is executing from hardware interrupt context or with hardware interrupts
* disabled.
diff --git a/net/core/dev.c b/net/core/dev.c
index ed674e2..69f7a1a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1793,6 +1793,17 @@ int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq)
EXPORT_SYMBOL(netif_set_real_num_rx_queues);
#endif
+/* netif_get_num_default_rss_queues - default number of RSS queues
+ *
+ * This routine should set an upper limit on the number of RSS queues
+ * used by default by multiqueue devices.
+ */
+int netif_get_num_default_rss_queues()
+{
+ return min_t(int, DEFAULT_MAX_NUM_RSS_QUEUES, num_online_cpus());
+}
+EXPORT_SYMBOL(netif_get_num_default_rss_queues);
+
static inline void __netif_reschedule(struct Qdisc *q)
{
struct softnet_data *sd;
--
1.7.9.rc2
^ permalink raw reply related
* [PATCH net-next 02/11] mlx4: set maximal number of default RSS queues
From: Yuval Mintz @ 2012-07-01 13:18 UTC (permalink / raw)
To: davem, netdev; +Cc: eilong, Yuval Mintz, Or Gerlitz
In-Reply-To: <1341148740-7375-1-git-send-email-yuvalmin@broadcom.com>
Signed-off-by: Yuval Mintz <yuvalmin@broadcom.com>
Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
Cc: Or Gerlitz <ogerlitz@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/main.c | 5 +++--
1 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index a0313de..14d9c76 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -41,6 +41,7 @@
#include <linux/slab.h>
#include <linux/io-mapping.h>
#include <linux/delay.h>
+#include <linux/netdevice.h>
#include <linux/mlx4/device.h>
#include <linux/mlx4/doorbell.h>
@@ -1539,8 +1540,8 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev)
struct mlx4_priv *priv = mlx4_priv(dev);
struct msix_entry *entries;
int nreq = min_t(int, dev->caps.num_ports *
- min_t(int, num_online_cpus() + 1, MAX_MSIX_P_PORT)
- + MSIX_LEGACY_SZ, MAX_MSIX);
+ min_t(int, netif_get_num_default_rss_queues() + 1,
+ MAX_MSIX_P_PORT) + MSIX_LEGACY_SZ, MAX_MSIX);
int err;
int i;
--
1.7.9.rc2
^ permalink raw reply related
* [PATCH net-next 00/11] default maximal number of RSS queues in mq drivers
From: Yuval Mintz @ 2012-07-01 13:18 UTC (permalink / raw)
To: davem, netdev
Cc: eilong, Yuval Mintz, Divy Le Ray, Or Gerlitz, Jon Mason,
Anirban Chakraborty, Jitendra Kalsaria, Ron Mercer, Jeff Kirsher,
Jon Mason, Andrew Gallatin, Sathya Perla, Subbu Seetharaman,
Ajit Khaparde, Matt Carlson, Michael Chan, Eric Dumazet,
Ben Hutchings
Different vendors support different number of RSS queues by default. Today,
there exists an ethtool API through which users can change the number of
channels their driver supports; This enables us to pursue the goal of using
a default number of RSS queues in various multi-queue drivers.
This patch intendeds to achieve the above default, by upper-limiting the number
of interrupts multi-queue drivers request (by default, not via the new API)
with correlation to the number of cpus on the machine.
After examining multi-queue drivers that call alloc_etherdev_mq[s],
it became evident that most drivers allocate their devices using hard-coded
values. Changing those defaults directly will most likely cause a regression.
However, (most) multi-queue driver look at the number of online cpus when
requesting for interrupts. We assume that the number of interrupts the
driver manages to request is propagated across the driver, and the number
of RSS queues it configures is based upon it.
This patch modifies said logic - if the number of cpus is large enough, use
a smaller default value instead. This serves 2 main purposes:
1. A step forward unity in the number of RSS queues of various drivers.
2. It prevents wasteful requests for memory on machines with many cpus.
Notice no testing was made on this patch (other than on the bnx2x driver)
except for compilation test. This patch is based on RFC:
http://marc.info/?l=linux-netdev&m=134062509310404&w=2
Drivers identified as multi-queue, handled in this patch:
* mellanox mlx4
* neterion vxge
* qlogic qlge
* chelsio cxgb3, cxgb4
* myricom myri10ge
* emulex benet
* broadcom tg3, bnx2, bnx2x
The guys at Intel requested to change their drivers' behaviour on their own,
in order to support ethtool's [g|s]et_channels. Thus, igb, igbx2, and igbxevf
were not handled in this patch.
Driver identified as multi-queue, no reference to number of online cpus found,
and thus unhandled in this patch:
* neterion s2io
* marvell mv643xx
* freescale gianfar
* ibm ehea
* ti cpmac
* sun niu
* sfc efx
* chelsio cxgb4vf
Cheers,
Yuval Mintz
Cc: Divy Le Ray <divy@chelsio.com>
Cc: Or Gerlitz <ogerlitz@mellanox.com>
Cc: Jon Mason <jdmason@kudzu.us>
Cc: Anirban Chakraborty <anirban.chakraborty@qlogic.com>
Cc: Jitendra Kalsaria <jitendra.kalsaria@qlogic.com>
Cc: Ron Mercer <ron.mercer@qlogic.com>
Cc: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Cc: Jon Mason <mason@myri.com>
Cc: Andrew Gallatin <gallatin@myri.com>
Cc: Sathya Perla <sathya.perla@emulex.com>
Cc: Subbu Seetharaman <subbu.seetharaman@emulex.com>
Cc: Ajit Khaparde <ajit.khaparde@emulex.com>
Cc: Matt Carlson <mcarlson@broadcom.com>
Cc: Michael Chan <mchan@broadcom.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Ben Hutchings <bhutchings@solarflare.com>
^ permalink raw reply
* Re: [PATCH v6] sctp: be more restrictive in transport selection on bundled sacks
From: Neil Horman @ 2012-07-01 12:47 UTC (permalink / raw)
To: David Miller; +Cc: netdev, vyasevich, linux-sctp
In-Reply-To: <20120630.173945.173993639982489712.davem@davemloft.net>
On Sat, Jun 30, 2012 at 05:39:45PM -0700, David Miller wrote:
> From: Neil Horman <nhorman@tuxdriver.com>
> Date: Sat, 30 Jun 2012 09:04:26 -0400
>
> > It was noticed recently that when we send data on a transport, its possible that
> > we might bundle a sack that arrived on a different transport. While this isn't
> > a major problem, it does go against the SHOULD requirement in section 6.4 of RFC
> > 2960:
> >
> > An endpoint SHOULD transmit reply chunks (e.g., SACK, HEARTBEAT ACK,
> > etc.) to the same destination transport address from which it
> > received the DATA or control chunk to which it is replying. This
> > rule should also be followed if the endpoint is bundling DATA chunks
> > together with the reply chunk.
> >
> > This patch seeks to correct that. It restricts the bundling of sack operations
> > to only those transports which have moved the ctsn of the association forward
> > since the last sack. By doing this we guarantee that we only bundle outbound
> > saks on a transport that has received a chunk since the last sack. This brings
> > us into stricter compliance with the RFC.
> >
> > Vlad had initially suggested that we strictly allow only sack bundling on the
> > transport that last moved the ctsn forward. While this makes sense, I was
> > concerned that doing so prevented us from bundling in the case where we had
> > received chunks that moved the ctsn on multiple transports. In those cases, the
> > RFC allows us to select any of the transports having received chunks to bundle
> > the sack on. so I've modified the approach to allow for that, by adding a state
> > variable to each transport that tracks weather it has moved the ctsn since the
> > last sack. This I think keeps our behavior (and performance), close enough to
> > our current profile that I think we can do this without a sysctl knob to
> > enable/disable it.
> >
> > Signed-off-by: Neil Horman <nhorman@tuxdriver.com>
> > CC: Vlad Yaseivch <vyasevich@gmail.com>
> > CC: David S. Miller <davem@davemloft.net>
> > CC: linux-sctp@vger.kernel.org
> > Reported-by: Michele Baldessari <michele@redhat.com>
> > Reported-by: sorin serban <sserban@redhat.com>
>
> Once this has Vlad's ACK I'll apply it.
>
Thanks!
> There has to be a better way to handle this situation, wherein the
> responsible party has ACK'd the patch but I just ask for a few coding
> style fixups and whatnot. As it stands now I have to twiddle my
> thumbs waiting for the new ACK.
>
Perhaps we could modify the SubmittingPatches document to indicate that an
Acked-by from a subsystem maintainer implicitly confers authority on the
upstream receiver to request reasonable stylistic changes that don't affect the
functionality of the patch in the interests of maintaining coding conventions.
i.e. Since vlad applied an acked-by to v5 of this patch, that would give you the
right to carry that ack forward to v6 because you only asked for style changes.
Thoughts?
Neil
>
^ permalink raw reply
* Re: [PATCH net-next 06/10] {NET,IB}/mlx4: Add device managed flow steering firmware API
From: Or Gerlitz @ 2012-07-01 12:29 UTC (permalink / raw)
To: David Miller; +Cc: roland, yevgenyp, oren, netdev, hadarh
In-Reply-To: <20120701.033055.489908836962064737.davem@davemloft.net>
On 7/1/2012 1:30 PM, David Miller wrote:
[...]
> @@ -136,6 +138,11 @@ module_param_array(port_type_array, int, &arr_argc, 0444);
> MODULE_PARM_DESC(port_type_array, "Array of port types: HW_DEFAULT (0) is default "
> "1 for IB, 2 for Ethernet");
>
> +static int mlx4_flow_steering_hash;
> +module_param_named(flow_steering_hash, mlx4_flow_steering_hash, int, 0444);
> +MODULE_PARM_DESC(flow_steering_hash,
> + "Flow steering hash function configuration. Config options: L2 = 0, L2_L3_L4 = 1 (default: L2).");
> +
>
> No module paramters, do it via ethtool or similar.
>
Dave,
We'll be handling the indentation, comments and other syntax issues you
have pointed out
and submit V1, hopefully which would be clean from such errors.
Re the usage of the module param - as was pointed out in the change-log,
please note that
this policy is **global** to the HCA, that is effects all the Ethernet
(and down the road,
also IPoIB flow-steering, when we run a card with one IB port and one
Eth port) net-devices
that relate to that device.
The module param is for mlx4_core and not for mlx4_en. In that respect,
per net-device
ethtool directive wouldn't work, even when there is a dedicated firmware
command that
allows changing this in run-time, which we don't have now.
My thinking was that once we have this command at hand, we can add
sysfs/etc entry at
the mlx4_core level to provide a different hash function to the device.
And for the
time being use the module param, makes sense?
Or.
^ permalink raw reply
* Re: [PATCH 0/5] rtcache remove respin
From: David Miller @ 2012-07-01 12:15 UTC (permalink / raw)
To: netdev
In-Reply-To: <20120701.050243.908285695895815999.davem@davemloft.net>
From: David Miller <davem@davemloft.net>
Date: Sun, 01 Jul 2012 05:02:43 -0700 (PDT)
> On a SPARC T3-1:
>
> 1) Output route lookup: ~2800 cycles
> 2) Input route lookups: ~3000 cycles (rpfilter=0)
> ~4300 cycles (rpfilter=1)
Out of curiosity I got rid of the local table and made all routes
go into the main table and those numbers above become:
1) Output route lookup: ~2500 cycles
2) Input route lookups: ~2800 cycles (rpfilter=0)
~4100 cycles (rpfilter=1)
====================
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 3dc7c96..5a103a9 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -186,9 +186,7 @@ static inline struct fib_table *fib_get_table(struct net *net, u32 id)
{
struct hlist_head *ptr;
- ptr = id == RT_TABLE_LOCAL ?
- &net->ipv4.fib_table_hash[TABLE_LOCAL_INDEX] :
- &net->ipv4.fib_table_hash[TABLE_MAIN_INDEX];
+ ptr = &net->ipv4.fib_table_hash[TABLE_MAIN_INDEX];
return hlist_entry(ptr->first, struct fib_table, tb_hlist);
}
@@ -202,10 +200,6 @@ static inline int fib_lookup(struct net *net, const struct flowi4 *flp,
{
struct fib_table *table;
- table = fib_get_table(net, RT_TABLE_LOCAL);
- if (!fib_table_lookup(table, flp, res, FIB_LOOKUP_NOREF))
- return 0;
-
table = fib_get_table(net, RT_TABLE_MAIN);
if (!fib_table_lookup(table, flp, res, FIB_LOOKUP_NOREF))
return 0;
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 44bf82e..bdc0231 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -160,7 +160,7 @@ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref)
/* Fallback to FIB local table so that communication
* over loopback subnets work.
*/
- local = fib_get_table(net, RT_TABLE_LOCAL);
+ local = fib_get_table(net, RT_TABLE_MAIN);
if (local &&
!fib_table_lookup(local, &fl4, &res, FIB_LOOKUP_NOREF) &&
res.type == RTN_LOCAL)
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index a658fb4..0056542 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -52,16 +52,10 @@ static int __net_init fib4_rules_init(struct net *net)
{
struct fib_table *local_table, *main_table;
- local_table = fib_trie_table(RT_TABLE_LOCAL);
- if (local_table == NULL)
- return -ENOMEM;
-
main_table = fib_trie_table(RT_TABLE_MAIN);
if (main_table == NULL)
goto fail;
- hlist_add_head_rcu(&local_table->tb_hlist,
- &net->ipv4.fib_table_hash[TABLE_LOCAL_INDEX]);
hlist_add_head_rcu(&main_table->tb_hlist,
&net->ipv4.fib_table_hash[TABLE_MAIN_INDEX]);
return 0;
@@ -155,7 +149,7 @@ static inline unsigned int __inet_dev_addr_type(struct net *net,
res.r = NULL;
#endif
- local_table = fib_get_table(net, RT_TABLE_LOCAL);
+ local_table = fib_get_table(net, RT_TABLE_MAIN);
if (local_table) {
ret = RTN_UNICAST;
rcu_read_lock();
@@ -702,11 +696,7 @@ static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifad
},
};
- if (type == RTN_UNICAST)
- tb = fib_new_table(net, RT_TABLE_MAIN);
- else
- tb = fib_new_table(net, RT_TABLE_LOCAL);
-
+ tb = fib_new_table(net, RT_TABLE_MAIN);
if (tb == NULL)
return;
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index b23fd95..41a53b0 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -284,9 +284,6 @@ static int fib_default_rules_init(struct fib_rules_ops *ops)
{
int err;
- err = fib_default_rule_add(ops, 0, RT_TABLE_LOCAL, 0);
- if (err < 0)
- return err;
err = fib_default_rule_add(ops, 0x7FFE, RT_TABLE_MAIN, 0);
if (err < 0)
return err;
^ permalink raw reply related
* [PATCH 5/5] ipv4: Remove 'rt_mark' from 'struct rtable'
From: David Miller @ 2012-07-01 12:03 UTC (permalink / raw)
To: netdev
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/route.h | 1 -
net/ipv4/ipmr.c | 2 +-
net/ipv4/route.c | 9 ++-------
net/ipv4/xfrm4_policy.c | 1 -
4 files changed, 3 insertions(+), 10 deletions(-)
diff --git a/include/net/route.h b/include/net/route.h
index ad387d2..9face41 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -53,7 +53,6 @@ struct rtable {
int rt_route_iif;
int rt_iif;
int rt_oif;
- __u32 rt_mark;
/* Info on neighbour */
__be32 rt_gateway;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index b4ac39f..d472d1d 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1797,7 +1797,7 @@ static struct mr_table *ipmr_rt_fib_lookup(struct net *net, struct sk_buff *skb)
.flowi4_tos = RT_TOS(iph->tos),
.flowi4_oif = rt->rt_oif,
.flowi4_iif = rt->rt_iif,
- .flowi4_mark = rt->rt_mark,
+ .flowi4_mark = skb->mark,
};
struct mr_table *mrt;
int err;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index a43a39b..f7ad8fd 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1226,7 +1226,6 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
rth->rt_route_iif = dev->ifindex;
rth->rt_iif = dev->ifindex;
rth->rt_oif = 0;
- rth->rt_mark = skb->mark;
rth->rt_gateway = daddr;
rth->rt_peer_genid = 0;
rt_init_peer(rth, dev_net(dev)->ipv4.peers);
@@ -1347,7 +1346,6 @@ static int __mkroute_input(struct sk_buff *skb,
rth->rt_route_iif = in_dev->dev->ifindex;
rth->rt_iif = in_dev->dev->ifindex;
rth->rt_oif = 0;
- rth->rt_mark = skb->mark;
rth->rt_gateway = daddr;
rth->rt_peer_genid = 0;
rt_init_peer(rth, &res->table->tb_peers);
@@ -1517,7 +1515,6 @@ local_input:
rth->rt_route_iif = dev->ifindex;
rth->rt_iif = dev->ifindex;
rth->rt_oif = 0;
- rth->rt_mark = skb->mark;
rth->rt_gateway = daddr;
rth->rt_peer_genid = 0;
rt_init_peer(rth, net->ipv4.peers);
@@ -1672,7 +1669,6 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
rth->rt_route_iif = 0;
rth->rt_iif = orig_oif ? : dev_out->ifindex;
rth->rt_oif = orig_oif;
- rth->rt_mark = fl4->flowi4_mark;
rth->rt_gateway = fl4->daddr;
rth->rt_peer_genid = 0;
rt_init_peer(rth, (res->table ?
@@ -1953,7 +1949,6 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
rt->rt_route_iif = ort->rt_route_iif;
rt->rt_iif = ort->rt_iif;
rt->rt_oif = ort->rt_oif;
- rt->rt_mark = ort->rt_mark;
rt->rt_genid = rt_genid(net);
rt->rt_flags = ort->rt_flags;
@@ -2046,8 +2041,8 @@ static int rt_fill_info(struct net *net, __be32 src, struct flowi4 *fl4,
if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0)
goto nla_put_failure;
- if (rt->rt_mark &&
- nla_put_be32(skb, RTA_MARK, rt->rt_mark))
+ if (fl4->flowi4_mark &&
+ nla_put_be32(skb, RTA_MARK, fl4->flowi4_mark))
goto nla_put_failure;
error = rt->dst.error;
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 679f4fd..d59eaec 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -82,7 +82,6 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
xdst->u.rt.rt_route_iif = fl4->flowi4_iif;
xdst->u.rt.rt_iif = fl4->flowi4_iif;
xdst->u.rt.rt_oif = fl4->flowi4_oif;
- xdst->u.rt.rt_mark = fl4->flowi4_mark;
xdst->u.dst.dev = dev;
dev_hold(dev);
--
1.7.10
^ permalink raw reply related
* [PATCH 4/5] ipv4: Kill 'rt_src' from 'struct rtable'
From: David Miller @ 2012-07-01 12:02 UTC (permalink / raw)
To: netdev
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/route.h | 1 -
net/ipv4/route.c | 34 +++++++++++++++-------------------
net/ipv4/xfrm4_policy.c | 1 -
3 files changed, 15 insertions(+), 21 deletions(-)
diff --git a/include/net/route.h b/include/net/route.h
index c5f2955..ad387d2 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -50,7 +50,6 @@ struct rtable {
__u16 rt_type;
__be32 rt_dst; /* Path destination */
- __be32 rt_src; /* Path source */
int rt_route_iif;
int rt_iif;
int rt_oif;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index ec38892..a43a39b 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1223,7 +1223,6 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
rth->rt_flags = RTCF_MULTICAST;
rth->rt_type = RTN_MULTICAST;
rth->rt_dst = daddr;
- rth->rt_src = saddr;
rth->rt_route_iif = dev->ifindex;
rth->rt_iif = dev->ifindex;
rth->rt_oif = 0;
@@ -1345,7 +1344,6 @@ static int __mkroute_input(struct sk_buff *skb,
rth->rt_flags = flags;
rth->rt_type = res->type;
rth->rt_dst = daddr;
- rth->rt_src = saddr;
rth->rt_route_iif = in_dev->dev->ifindex;
rth->rt_iif = in_dev->dev->ifindex;
rth->rt_oif = 0;
@@ -1516,7 +1514,6 @@ local_input:
rth->rt_flags = flags|RTCF_LOCAL;
rth->rt_type = res.type;
rth->rt_dst = daddr;
- rth->rt_src = saddr;
rth->rt_route_iif = dev->ifindex;
rth->rt_iif = dev->ifindex;
rth->rt_oif = 0;
@@ -1672,7 +1669,6 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
rth->rt_flags = flags;
rth->rt_type = type;
rth->rt_dst = fl4->daddr;
- rth->rt_src = fl4->saddr;
rth->rt_route_iif = 0;
rth->rt_iif = orig_oif ? : dev_out->ifindex;
rth->rt_oif = orig_oif;
@@ -1963,7 +1959,6 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
rt->rt_flags = ort->rt_flags;
rt->rt_type = ort->rt_type;
rt->rt_dst = ort->rt_dst;
- rt->rt_src = ort->rt_src;
rt->rt_gateway = ort->rt_gateway;
rt_transfer_peer(rt, ort);
rt->fi = ort->fi;
@@ -1995,7 +1990,7 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4,
}
EXPORT_SYMBOL_GPL(ip_route_output_flow);
-static int rt_fill_info(struct net *net, __be32 src, u8 tos,
+static int rt_fill_info(struct net *net, __be32 src, struct flowi4 *fl4,
struct sk_buff *skb, u32 pid, u32 seq, int event,
int nowait, unsigned int flags)
{
@@ -2013,7 +2008,7 @@ static int rt_fill_info(struct net *net, __be32 src, u8 tos,
r->rtm_family = AF_INET;
r->rtm_dst_len = 32;
r->rtm_src_len = 0;
- r->rtm_tos = tos;
+ r->rtm_tos = fl4->flowi4_tos;
r->rtm_table = RT_TABLE_MAIN;
if (nla_put_u32(skb, RTA_TABLE, RT_TABLE_MAIN))
goto nla_put_failure;
@@ -2040,11 +2035,11 @@ static int rt_fill_info(struct net *net, __be32 src, u8 tos,
goto nla_put_failure;
#endif
if (!rt_is_input_route(rt) &&
- rt->rt_src != src) {
- if (nla_put_be32(skb, RTA_PREFSRC, rt->rt_src))
+ fl4->saddr != src) {
+ if (nla_put_be32(skb, RTA_PREFSRC, fl4->saddr))
goto nla_put_failure;
}
- if (rt->rt_dst != rt->rt_gateway &&
+ if (fl4->daddr != rt->rt_gateway &&
nla_put_be32(skb, RTA_GATEWAY, rt->rt_gateway))
goto nla_put_failure;
@@ -2080,7 +2075,7 @@ static int rt_fill_info(struct net *net, __be32 src, u8 tos,
if (ipv4_is_multicast(dst) && !ipv4_is_local_multicast(dst) &&
IPV4_DEVCONF_ALL(net, MC_FORWARDING)) {
int err = ipmr_get_route(net, skb,
- rt->rt_src, rt->rt_dst,
+ fl4->saddr, fl4->daddr,
r, nowait);
if (err <= 0) {
if (!nowait) {
@@ -2116,6 +2111,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void
struct rtmsg *rtm;
struct nlattr *tb[RTA_MAX+1];
struct rtable *rt = NULL;
+ struct flowi4 fl4;
__be32 dst = 0;
__be32 src = 0;
u32 iif;
@@ -2150,6 +2146,13 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void
iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0;
mark = tb[RTA_MARK] ? nla_get_u32(tb[RTA_MARK]) : 0;
+ memset(&fl4, 0, sizeof(fl4));
+ fl4.daddr = dst;
+ fl4.saddr = src;
+ fl4.flowi4_tos = rtm->rtm_tos;
+ fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0;
+ fl4.flowi4_mark = mark;
+
if (iif) {
struct net_device *dev;
@@ -2170,13 +2173,6 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void
if (err == 0 && rt->dst.error)
err = -rt->dst.error;
} else {
- struct flowi4 fl4 = {
- .daddr = dst,
- .saddr = src,
- .flowi4_tos = rtm->rtm_tos,
- .flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0,
- .flowi4_mark = mark,
- };
rt = ip_route_output_key(net, &fl4);
err = 0;
@@ -2191,7 +2187,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void
if (rtm->rtm_flags & RTM_F_NOTIFY)
rt->rt_flags |= RTCF_NOTIFY;
- err = rt_fill_info(net, src, rtm->rtm_tos, skb,
+ err = rt_fill_info(net, src, &fl4, skb,
NETLINK_CB(in_skb).pid, nlh->nlmsg_seq,
RTM_NEWROUTE, 0, 0);
if (err <= 0)
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 01808c5..679f4fd 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -94,7 +94,6 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
xdst->u.rt.rt_flags = rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST |
RTCF_LOCAL);
xdst->u.rt.rt_type = rt->rt_type;
- xdst->u.rt.rt_src = rt->rt_src;
xdst->u.rt.rt_dst = rt->rt_dst;
xdst->u.rt.rt_gateway = rt->rt_gateway;
--
1.7.10
^ permalink raw reply related
* [PATCH 3/5] ipv4: Remove rt_key_{src,dst,tos} from struct rtable.
From: David Miller @ 2012-07-01 12:02 UTC (permalink / raw)
To: netdev
They are always used in contexts where they can be reconstituted,
or where the finally resolved rt->rt_{src,dst} is semantically
equivalent.
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/route.h | 5 -----
net/ipv4/route.c | 39 +++++++++------------------------------
net/ipv4/xfrm4_policy.c | 3 ---
3 files changed, 9 insertions(+), 38 deletions(-)
diff --git a/include/net/route.h b/include/net/route.h
index 04c1b7f..c5f2955 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -45,14 +45,9 @@ struct fib_info;
struct rtable {
struct dst_entry dst;
- /* Lookup key. */
- __be32 rt_key_dst;
- __be32 rt_key_src;
-
int rt_genid;
unsigned int rt_flags;
__u16 rt_type;
- __u8 rt_key_tos;
__be32 rt_dst; /* Path destination */
__be32 rt_src; /* Path source */
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 4377e01..ec38892 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1219,12 +1219,9 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
#endif
rth->dst.output = ip_rt_bug;
- rth->rt_key_dst = daddr;
- rth->rt_key_src = saddr;
rth->rt_genid = rt_genid(dev_net(dev));
rth->rt_flags = RTCF_MULTICAST;
rth->rt_type = RTN_MULTICAST;
- rth->rt_key_tos = tos;
rth->rt_dst = daddr;
rth->rt_src = saddr;
rth->rt_route_iif = dev->ifindex;
@@ -1344,12 +1341,9 @@ static int __mkroute_input(struct sk_buff *skb,
goto cleanup;
}
- rth->rt_key_dst = daddr;
- rth->rt_key_src = saddr;
rth->rt_genid = rt_genid(dev_net(rth->dst.dev));
rth->rt_flags = flags;
rth->rt_type = res->type;
- rth->rt_key_tos = tos;
rth->rt_dst = daddr;
rth->rt_src = saddr;
rth->rt_route_iif = in_dev->dev->ifindex;
@@ -1518,12 +1512,9 @@ local_input:
rth->dst.tclassid = itag;
#endif
- rth->rt_key_dst = daddr;
- rth->rt_key_src = saddr;
rth->rt_genid = rt_genid(net);
rth->rt_flags = flags|RTCF_LOCAL;
rth->rt_type = res.type;
- rth->rt_key_tos = tos;
rth->rt_dst = daddr;
rth->rt_src = saddr;
rth->rt_route_iif = dev->ifindex;
@@ -1626,9 +1617,7 @@ EXPORT_SYMBOL(ip_route_input);
/* called with rcu_read_lock() */
static struct rtable *__mkroute_output(const struct fib_result *res,
- const struct flowi4 *fl4,
- __be32 orig_daddr, __be32 orig_saddr,
- int orig_oif, __u8 orig_rtos,
+ const struct flowi4 *fl4, int orig_oif,
struct net_device *dev_out,
unsigned int flags)
{
@@ -1679,12 +1668,9 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
rth->dst.output = ip_output;
- rth->rt_key_dst = orig_daddr;
- rth->rt_key_src = orig_saddr;
rth->rt_genid = rt_genid(dev_net(dev_out));
rth->rt_flags = flags;
rth->rt_type = type;
- rth->rt_key_tos = orig_rtos;
rth->rt_dst = fl4->daddr;
rth->rt_src = fl4->saddr;
rth->rt_route_iif = 0;
@@ -1738,8 +1724,6 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
unsigned int flags = 0;
struct fib_result res;
struct rtable *rth;
- __be32 orig_daddr;
- __be32 orig_saddr;
int orig_oif;
res.fi = NULL;
@@ -1748,8 +1732,6 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
res.r = NULL;
#endif
- orig_daddr = fl4->daddr;
- orig_saddr = fl4->saddr;
orig_oif = fl4->flowi4_oif;
fl4->flowi4_iif = net->loopback_dev->ifindex;
@@ -1911,8 +1893,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
make_route:
- rth = __mkroute_output(&res, fl4, orig_daddr, orig_saddr, orig_oif,
- tos, dev_out, flags);
+ rth = __mkroute_output(&res, fl4, orig_oif, dev_out, flags);
if (!IS_ERR(rth))
rth = rt_finalize(rth, NULL);
@@ -1973,9 +1954,6 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
if (new->dev)
dev_hold(new->dev);
- rt->rt_key_dst = ort->rt_key_dst;
- rt->rt_key_src = ort->rt_key_src;
- rt->rt_key_tos = ort->rt_key_tos;
rt->rt_route_iif = ort->rt_route_iif;
rt->rt_iif = ort->rt_iif;
rt->rt_oif = ort->rt_oif;
@@ -2017,7 +1995,7 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4,
}
EXPORT_SYMBOL_GPL(ip_route_output_flow);
-static int rt_fill_info(struct net *net,
+static int rt_fill_info(struct net *net, __be32 src, u8 tos,
struct sk_buff *skb, u32 pid, u32 seq, int event,
int nowait, unsigned int flags)
{
@@ -2035,7 +2013,7 @@ static int rt_fill_info(struct net *net,
r->rtm_family = AF_INET;
r->rtm_dst_len = 32;
r->rtm_src_len = 0;
- r->rtm_tos = rt->rt_key_tos;
+ r->rtm_tos = tos;
r->rtm_table = RT_TABLE_MAIN;
if (nla_put_u32(skb, RTA_TABLE, RT_TABLE_MAIN))
goto nla_put_failure;
@@ -2048,9 +2026,9 @@ static int rt_fill_info(struct net *net,
if (nla_put_be32(skb, RTA_DST, rt->rt_dst))
goto nla_put_failure;
- if (rt->rt_key_src) {
+ if (src) {
r->rtm_src_len = 32;
- if (nla_put_be32(skb, RTA_SRC, rt->rt_key_src))
+ if (nla_put_be32(skb, RTA_SRC, src))
goto nla_put_failure;
}
if (rt->dst.dev &&
@@ -2062,7 +2040,7 @@ static int rt_fill_info(struct net *net,
goto nla_put_failure;
#endif
if (!rt_is_input_route(rt) &&
- rt->rt_src != rt->rt_key_src) {
+ rt->rt_src != src) {
if (nla_put_be32(skb, RTA_PREFSRC, rt->rt_src))
goto nla_put_failure;
}
@@ -2213,7 +2191,8 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void
if (rtm->rtm_flags & RTM_F_NOTIFY)
rt->rt_flags |= RTCF_NOTIFY;
- err = rt_fill_info(net, skb, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq,
+ err = rt_fill_info(net, src, rtm->rtm_tos, skb,
+ NETLINK_CB(in_skb).pid, nlh->nlmsg_seq,
RTM_NEWROUTE, 0, 0);
if (err <= 0)
goto errout_free;
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 9815ea0..01808c5 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -79,9 +79,6 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
struct rtable *rt = (struct rtable *)xdst->route;
const struct flowi4 *fl4 = &fl->u.ip4;
- xdst->u.rt.rt_key_dst = fl4->daddr;
- xdst->u.rt.rt_key_src = fl4->saddr;
- xdst->u.rt.rt_key_tos = fl4->flowi4_tos;
xdst->u.rt.rt_route_iif = fl4->flowi4_iif;
xdst->u.rt.rt_iif = fl4->flowi4_iif;
xdst->u.rt.rt_oif = fl4->flowi4_oif;
--
1.7.10
^ permalink raw reply related
* [PATCH 2/5] ipv4: Kill ip_route_input_noref().
From: David Miller @ 2012-07-01 12:02 UTC (permalink / raw)
To: netdev
The "noref" argument to ip_route_input_common() is now always ignored
because we do not cache routes, and in that case we must always grab
a reference to the resulting 'dst'.
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/route.h | 16 ++--------------
net/ipv4/arp.c | 2 +-
net/ipv4/ip_fragment.c | 4 ++--
net/ipv4/ip_input.c | 4 ++--
net/ipv4/route.c | 6 +++---
net/ipv4/xfrm4_input.c | 4 ++--
6 files changed, 12 insertions(+), 24 deletions(-)
diff --git a/include/net/route.h b/include/net/route.h
index 23d8026..04c1b7f 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -198,20 +198,8 @@ static inline struct rtable *ip_route_output_gre(struct net *net, struct flowi4
return ip_route_output_key(net, fl4);
}
-extern int ip_route_input_common(struct sk_buff *skb, __be32 dst, __be32 src,
- u8 tos, struct net_device *devin, bool noref);
-
-static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src,
- u8 tos, struct net_device *devin)
-{
- return ip_route_input_common(skb, dst, src, tos, devin, false);
-}
-
-static inline int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src,
- u8 tos, struct net_device *devin)
-{
- return ip_route_input_common(skb, dst, src, tos, devin, true);
-}
+extern int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src,
+ u8 tos, struct net_device *devin);
extern void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
int oif, u32 mark, u8 protocol, int flow_flags);
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 2e560f0..c38293f 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -828,7 +828,7 @@ static int arp_process(struct sk_buff *skb)
}
if (arp->ar_op == htons(ARPOP_REQUEST) &&
- ip_route_input_noref(skb, tip, sip, 0, dev) == 0) {
+ ip_route_input(skb, tip, sip, 0, dev) == 0) {
rt = skb_rtable(skb);
addr_type = rt->rt_type;
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 8d07c97..7ad88e5 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -258,8 +258,8 @@ static void ip_expire(unsigned long arg)
/* skb dst is stale, drop it, and perform route lookup again */
skb_dst_drop(head);
iph = ip_hdr(head);
- err = ip_route_input_noref(head, iph->daddr, iph->saddr,
- iph->tos, head->dev);
+ err = ip_route_input(head, iph->daddr, iph->saddr,
+ iph->tos, head->dev);
if (err)
goto out_rcu_unlock;
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index b27d444..4ebc6fe 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -336,8 +336,8 @@ static int ip_rcv_finish(struct sk_buff *skb)
* how the packet travels inside Linux networking.
*/
if (!skb_dst(skb)) {
- int err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
- iph->tos, skb->dev);
+ int err = ip_route_input(skb, iph->daddr, iph->saddr,
+ iph->tos, skb->dev);
if (unlikely(err)) {
if (err == -EXDEV)
NET_INC_STATS_BH(dev_net(skb->dev),
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index e7650c5..4377e01 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1578,8 +1578,8 @@ martian_source_keep_err:
goto out;
}
-int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr,
- u8 tos, struct net_device *dev, bool noref)
+int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr,
+ u8 tos, struct net_device *dev)
{
int res;
@@ -1622,7 +1622,7 @@ int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr,
rcu_read_unlock();
return res;
}
-EXPORT_SYMBOL(ip_route_input_common);
+EXPORT_SYMBOL(ip_route_input);
/* called with rcu_read_lock() */
static struct rtable *__mkroute_output(const struct fib_result *res,
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index 06814b6..58d23a5 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -27,8 +27,8 @@ static inline int xfrm4_rcv_encap_finish(struct sk_buff *skb)
if (skb_dst(skb) == NULL) {
const struct iphdr *iph = ip_hdr(skb);
- if (ip_route_input_noref(skb, iph->daddr, iph->saddr,
- iph->tos, skb->dev))
+ if (ip_route_input(skb, iph->daddr, iph->saddr,
+ iph->tos, skb->dev))
goto drop;
}
return dst_input(skb);
--
1.7.10
^ permalink raw reply related
* [PATCH 1/5] ipv4: Delete routing cache.
From: David Miller @ 2012-07-01 12:02 UTC (permalink / raw)
To: netdev
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/route.h | 5 +-
net/ipv4/fib_frontend.c | 5 -
net/ipv4/icmp.c | 5 +-
net/ipv4/route.c | 1053 +++--------------------------------------------
4 files changed, 52 insertions(+), 1016 deletions(-)
diff --git a/include/net/route.h b/include/net/route.h
index 211e266..23d8026 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -144,10 +144,9 @@ extern struct ip_rt_acct __percpu *ip_rt_acct;
struct in_device;
extern int ip_rt_init(void);
-extern void ip_rt_redirect(__be32 old_gw, __be32 dst, __be32 new_gw,
- __be32 src, struct net_device *dev);
+extern void ip_rt_redirect(struct sk_buff *skb, __be32 old_gw,
+ __be32 new_gw);
extern void rt_cache_flush(struct net *net, int how);
-extern void rt_cache_flush_batch(struct net *net);
extern struct rtable *__ip_route_output_key(struct net *, struct flowi4 *flp);
extern struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp,
struct sock *sk);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 3e11ea2..a658fb4 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1065,11 +1065,6 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo
rt_cache_flush(dev_net(dev), 0);
break;
case NETDEV_UNREGISTER_BATCH:
- /* The batch unregister is only called on the first
- * device in the list of devices being unregistered.
- * Therefore we should not pass dev_net(dev) in here.
- */
- rt_cache_flush_batch(NULL);
break;
}
return NOTIFY_DONE;
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 4bce5a2..7ad960a 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -774,9 +774,8 @@ static void icmp_redirect(struct sk_buff *skb)
*/
case ICMP_REDIR_HOST:
case ICMP_REDIR_HOSTTOS:
- ip_rt_redirect(ip_hdr(skb)->saddr, iph->daddr,
- icmp_hdr(skb)->un.gateway,
- iph->saddr, skb->dev);
+ ip_rt_redirect(skb, ip_hdr(skb)->saddr,
+ icmp_hdr(skb)->un.gateway);
break;
}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 6a5afc7..e7650c5 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -133,10 +133,6 @@ static int ip_rt_gc_elasticity __read_mostly = 8;
static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ;
static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20;
static int ip_rt_min_advmss __read_mostly = 256;
-static int rt_chain_length_max __read_mostly = 20;
-
-static struct delayed_work expires_work;
-static unsigned long expires_ljiffies;
/*
* Interface to generic destination cache.
@@ -149,7 +145,6 @@ static void ipv4_dst_destroy(struct dst_entry *dst);
static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst);
static void ipv4_link_failure(struct sk_buff *skb);
static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu);
-static int rt_garbage_collect(struct dst_ops *ops);
static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
int how)
@@ -193,7 +188,6 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, const vo
static struct dst_ops ipv4_dst_ops = {
.family = AF_INET,
.protocol = cpu_to_be16(ETH_P_IP),
- .gc = rt_garbage_collect,
.check = ipv4_dst_check,
.default_advmss = ipv4_default_advmss,
.mtu = ipv4_mtu,
@@ -229,184 +223,30 @@ const __u8 ip_tos2prio[16] = {
};
EXPORT_SYMBOL(ip_tos2prio);
-/*
- * Route cache.
- */
-
-/* The locking scheme is rather straight forward:
- *
- * 1) Read-Copy Update protects the buckets of the central route hash.
- * 2) Only writers remove entries, and they hold the lock
- * as they look at rtable reference counts.
- * 3) Only readers acquire references to rtable entries,
- * they do so with atomic increments and with the
- * lock held.
- */
-
-struct rt_hash_bucket {
- struct rtable __rcu *chain;
-};
-
-#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) || \
- defined(CONFIG_PROVE_LOCKING)
-/*
- * Instead of using one spinlock for each rt_hash_bucket, we use a table of spinlocks
- * The size of this table is a power of two and depends on the number of CPUS.
- * (on lockdep we have a quite big spinlock_t, so keep the size down there)
- */
-#ifdef CONFIG_LOCKDEP
-# define RT_HASH_LOCK_SZ 256
-#else
-# if NR_CPUS >= 32
-# define RT_HASH_LOCK_SZ 4096
-# elif NR_CPUS >= 16
-# define RT_HASH_LOCK_SZ 2048
-# elif NR_CPUS >= 8
-# define RT_HASH_LOCK_SZ 1024
-# elif NR_CPUS >= 4
-# define RT_HASH_LOCK_SZ 512
-# else
-# define RT_HASH_LOCK_SZ 256
-# endif
-#endif
-
-static spinlock_t *rt_hash_locks;
-# define rt_hash_lock_addr(slot) &rt_hash_locks[(slot) & (RT_HASH_LOCK_SZ - 1)]
-
-static __init void rt_hash_lock_init(void)
-{
- int i;
-
- rt_hash_locks = kmalloc(sizeof(spinlock_t) * RT_HASH_LOCK_SZ,
- GFP_KERNEL);
- if (!rt_hash_locks)
- panic("IP: failed to allocate rt_hash_locks\n");
-
- for (i = 0; i < RT_HASH_LOCK_SZ; i++)
- spin_lock_init(&rt_hash_locks[i]);
-}
-#else
-# define rt_hash_lock_addr(slot) NULL
-
-static inline void rt_hash_lock_init(void)
-{
-}
-#endif
-
-static struct rt_hash_bucket *rt_hash_table __read_mostly;
-static unsigned int rt_hash_mask __read_mostly;
-static unsigned int rt_hash_log __read_mostly;
-
static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat);
#define RT_CACHE_STAT_INC(field) __this_cpu_inc(rt_cache_stat.field)
-static inline unsigned int rt_hash(__be32 daddr, __be32 saddr, int idx,
- int genid)
-{
- return jhash_3words((__force u32)daddr, (__force u32)saddr,
- idx, genid)
- & rt_hash_mask;
-}
-
static inline int rt_genid(struct net *net)
{
return atomic_read(&net->ipv4.rt_genid);
}
#ifdef CONFIG_PROC_FS
-struct rt_cache_iter_state {
- struct seq_net_private p;
- int bucket;
- int genid;
-};
-
-static struct rtable *rt_cache_get_first(struct seq_file *seq)
-{
- struct rt_cache_iter_state *st = seq->private;
- struct rtable *r = NULL;
-
- for (st->bucket = rt_hash_mask; st->bucket >= 0; --st->bucket) {
- if (!rcu_access_pointer(rt_hash_table[st->bucket].chain))
- continue;
- rcu_read_lock_bh();
- r = rcu_dereference_bh(rt_hash_table[st->bucket].chain);
- while (r) {
- if (dev_net(r->dst.dev) == seq_file_net(seq) &&
- r->rt_genid == st->genid)
- return r;
- r = rcu_dereference_bh(r->dst.rt_next);
- }
- rcu_read_unlock_bh();
- }
- return r;
-}
-
-static struct rtable *__rt_cache_get_next(struct seq_file *seq,
- struct rtable *r)
-{
- struct rt_cache_iter_state *st = seq->private;
-
- r = rcu_dereference_bh(r->dst.rt_next);
- while (!r) {
- rcu_read_unlock_bh();
- do {
- if (--st->bucket < 0)
- return NULL;
- } while (!rcu_access_pointer(rt_hash_table[st->bucket].chain));
- rcu_read_lock_bh();
- r = rcu_dereference_bh(rt_hash_table[st->bucket].chain);
- }
- return r;
-}
-
-static struct rtable *rt_cache_get_next(struct seq_file *seq,
- struct rtable *r)
-{
- struct rt_cache_iter_state *st = seq->private;
- while ((r = __rt_cache_get_next(seq, r)) != NULL) {
- if (dev_net(r->dst.dev) != seq_file_net(seq))
- continue;
- if (r->rt_genid == st->genid)
- break;
- }
- return r;
-}
-
-static struct rtable *rt_cache_get_idx(struct seq_file *seq, loff_t pos)
-{
- struct rtable *r = rt_cache_get_first(seq);
-
- if (r)
- while (pos && (r = rt_cache_get_next(seq, r)))
- --pos;
- return pos ? NULL : r;
-}
-
static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos)
{
- struct rt_cache_iter_state *st = seq->private;
if (*pos)
- return rt_cache_get_idx(seq, *pos - 1);
- st->genid = rt_genid(seq_file_net(seq));
+ return NULL;
return SEQ_START_TOKEN;
}
static void *rt_cache_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
- struct rtable *r;
-
- if (v == SEQ_START_TOKEN)
- r = rt_cache_get_first(seq);
- else
- r = rt_cache_get_next(seq, v);
++*pos;
- return r;
+ return NULL;
}
static void rt_cache_seq_stop(struct seq_file *seq, void *v)
{
- if (v && v != SEQ_START_TOKEN)
- rcu_read_unlock_bh();
}
static int rt_cache_seq_show(struct seq_file *seq, void *v)
@@ -416,34 +256,6 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v)
"Iface\tDestination\tGateway \tFlags\t\tRefCnt\tUse\t"
"Metric\tSource\t\tMTU\tWindow\tIRTT\tTOS\tHHRef\t"
"HHUptod\tSpecDst");
- else {
- struct rtable *r = v;
- struct neighbour *n;
- int len, HHUptod;
-
- rcu_read_lock();
- n = dst_get_neighbour_noref(&r->dst);
- HHUptod = (n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0;
- rcu_read_unlock();
-
- seq_printf(seq, "%s\t%08X\t%08X\t%8X\t%d\t%u\t%d\t"
- "%08X\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n",
- r->dst.dev ? r->dst.dev->name : "*",
- (__force u32)r->rt_dst,
- (__force u32)r->rt_gateway,
- r->rt_flags, atomic_read(&r->dst.__refcnt),
- r->dst.__use, 0, (__force u32)r->rt_src,
- dst_metric_advmss(&r->dst) + 40,
- dst_metric(&r->dst, RTAX_WINDOW),
- (int)((dst_metric(&r->dst, RTAX_RTT) >> 3) +
- dst_metric(&r->dst, RTAX_RTTVAR)),
- r->rt_key_tos,
- -1,
- HHUptod,
- 0, &len);
-
- seq_printf(seq, "%*s\n", 127 - len, "");
- }
return 0;
}
@@ -456,8 +268,7 @@ static const struct seq_operations rt_cache_seq_ops = {
static int rt_cache_seq_open(struct inode *inode, struct file *file)
{
- return seq_open_net(inode, file, &rt_cache_seq_ops,
- sizeof(struct rt_cache_iter_state));
+ return seq_open(file, &rt_cache_seq_ops);
}
static const struct file_operations rt_cache_seq_fops = {
@@ -465,7 +276,7 @@ static const struct file_operations rt_cache_seq_fops = {
.open = rt_cache_seq_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release_net,
+ .release = seq_release,
};
@@ -655,263 +466,12 @@ static inline int ip_rt_proc_init(void)
}
#endif /* CONFIG_PROC_FS */
-static inline void rt_free(struct rtable *rt)
-{
- call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free);
-}
-
-static inline void rt_drop(struct rtable *rt)
-{
- ip_rt_put(rt);
- call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free);
-}
-
-static inline int rt_fast_clean(struct rtable *rth)
-{
- /* Kill broadcast/multicast entries very aggresively, if they
- collide in hash table with more useful entries */
- return (rth->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) &&
- rt_is_input_route(rth) && rth->dst.rt_next;
-}
-
-static inline int rt_valuable(struct rtable *rth)
-{
- return (rth->rt_flags & (RTCF_REDIRECTED | RTCF_NOTIFY)) ||
- (rt_has_peer(rth) && rt_peer_ptr(rth)->pmtu_expires);
-}
-
-static int rt_may_expire(struct rtable *rth, unsigned long tmo1, unsigned long tmo2)
-{
- unsigned long age;
- int ret = 0;
-
- if (atomic_read(&rth->dst.__refcnt))
- goto out;
-
- age = jiffies - rth->dst.lastuse;
- if ((age <= tmo1 && !rt_fast_clean(rth)) ||
- (age <= tmo2 && rt_valuable(rth)))
- goto out;
- ret = 1;
-out: return ret;
-}
-
-/* Bits of score are:
- * 31: very valuable
- * 30: not quite useless
- * 29..0: usage counter
- */
-static inline u32 rt_score(struct rtable *rt)
-{
- u32 score = jiffies - rt->dst.lastuse;
-
- score = ~score & ~(3<<30);
-
- if (rt_valuable(rt))
- score |= (1<<31);
-
- if (rt_is_output_route(rt) ||
- !(rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST|RTCF_LOCAL)))
- score |= (1<<30);
-
- return score;
-}
-
-static inline bool rt_caching(const struct net *net)
-{
- return net->ipv4.current_rt_cache_rebuild_count <=
- net->ipv4.sysctl_rt_cache_rebuild_count;
-}
-
-static inline bool compare_hash_inputs(const struct rtable *rt1,
- const struct rtable *rt2)
-{
- return ((((__force u32)rt1->rt_key_dst ^ (__force u32)rt2->rt_key_dst) |
- ((__force u32)rt1->rt_key_src ^ (__force u32)rt2->rt_key_src) |
- (rt1->rt_route_iif ^ rt2->rt_route_iif)) == 0);
-}
-
-static inline int compare_keys(struct rtable *rt1, struct rtable *rt2)
-{
- return (((__force u32)rt1->rt_key_dst ^ (__force u32)rt2->rt_key_dst) |
- ((__force u32)rt1->rt_key_src ^ (__force u32)rt2->rt_key_src) |
- (rt1->rt_mark ^ rt2->rt_mark) |
- (rt1->rt_key_tos ^ rt2->rt_key_tos) |
- (rt1->rt_route_iif ^ rt2->rt_route_iif) |
- (rt1->rt_oif ^ rt2->rt_oif)) == 0;
-}
-
-static inline int compare_netns(struct rtable *rt1, struct rtable *rt2)
-{
- return net_eq(dev_net(rt1->dst.dev), dev_net(rt2->dst.dev));
-}
-
static inline int rt_is_expired(struct rtable *rth)
{
return rth->rt_genid != rt_genid(dev_net(rth->dst.dev));
}
/*
- * Perform a full scan of hash table and free all entries.
- * Can be called by a softirq or a process.
- * In the later case, we want to be reschedule if necessary
- */
-static void rt_do_flush(struct net *net, int process_context)
-{
- unsigned int i;
- struct rtable *rth, *next;
-
- for (i = 0; i <= rt_hash_mask; i++) {
- struct rtable __rcu **pprev;
- struct rtable *list;
-
- if (process_context && need_resched())
- cond_resched();
- rth = rcu_access_pointer(rt_hash_table[i].chain);
- if (!rth)
- continue;
-
- spin_lock_bh(rt_hash_lock_addr(i));
-
- list = NULL;
- pprev = &rt_hash_table[i].chain;
- rth = rcu_dereference_protected(*pprev,
- lockdep_is_held(rt_hash_lock_addr(i)));
-
- while (rth) {
- next = rcu_dereference_protected(rth->dst.rt_next,
- lockdep_is_held(rt_hash_lock_addr(i)));
-
- if (!net ||
- net_eq(dev_net(rth->dst.dev), net)) {
- rcu_assign_pointer(*pprev, next);
- rcu_assign_pointer(rth->dst.rt_next, list);
- list = rth;
- } else {
- pprev = &rth->dst.rt_next;
- }
- rth = next;
- }
-
- spin_unlock_bh(rt_hash_lock_addr(i));
-
- for (; list; list = next) {
- next = rcu_dereference_protected(list->dst.rt_next, 1);
- rt_free(list);
- }
- }
-}
-
-/*
- * While freeing expired entries, we compute average chain length
- * and standard deviation, using fixed-point arithmetic.
- * This to have an estimation of rt_chain_length_max
- * rt_chain_length_max = max(elasticity, AVG + 4*SD)
- * We use 3 bits for frational part, and 29 (or 61) for magnitude.
- */
-
-#define FRACT_BITS 3
-#define ONE (1UL << FRACT_BITS)
-
-/*
- * Given a hash chain and an item in this hash chain,
- * find if a previous entry has the same hash_inputs
- * (but differs on tos, mark or oif)
- * Returns 0 if an alias is found.
- * Returns ONE if rth has no alias before itself.
- */
-static int has_noalias(const struct rtable *head, const struct rtable *rth)
-{
- const struct rtable *aux = head;
-
- while (aux != rth) {
- if (compare_hash_inputs(aux, rth))
- return 0;
- aux = rcu_dereference_protected(aux->dst.rt_next, 1);
- }
- return ONE;
-}
-
-static void rt_check_expire(void)
-{
- static unsigned int rover;
- unsigned int i = rover, goal;
- struct rtable *rth;
- struct rtable __rcu **rthp;
- unsigned long samples = 0;
- unsigned long sum = 0, sum2 = 0;
- unsigned long delta;
- u64 mult;
-
- delta = jiffies - expires_ljiffies;
- expires_ljiffies = jiffies;
- mult = ((u64)delta) << rt_hash_log;
- if (ip_rt_gc_timeout > 1)
- do_div(mult, ip_rt_gc_timeout);
- goal = (unsigned int)mult;
- if (goal > rt_hash_mask)
- goal = rt_hash_mask + 1;
- for (; goal > 0; goal--) {
- unsigned long tmo = ip_rt_gc_timeout;
- unsigned long length;
-
- i = (i + 1) & rt_hash_mask;
- rthp = &rt_hash_table[i].chain;
-
- if (need_resched())
- cond_resched();
-
- samples++;
-
- if (rcu_dereference_raw(*rthp) == NULL)
- continue;
- length = 0;
- spin_lock_bh(rt_hash_lock_addr(i));
- while ((rth = rcu_dereference_protected(*rthp,
- lockdep_is_held(rt_hash_lock_addr(i)))) != NULL) {
- prefetch(rth->dst.rt_next);
- if (rt_is_expired(rth) ||
- rt_may_expire(rth, tmo, ip_rt_gc_timeout)) {
- *rthp = rth->dst.rt_next;
- rt_free(rth);
- continue;
- }
-
- /* We only count entries on a chain with equal
- * hash inputs once so that entries for
- * different QOS levels, and other non-hash
- * input attributes don't unfairly skew the
- * length computation
- */
- tmo >>= 1;
- rthp = &rth->dst.rt_next;
- length += has_noalias(rt_hash_table[i].chain, rth);
- }
- spin_unlock_bh(rt_hash_lock_addr(i));
- sum += length;
- sum2 += length*length;
- }
- if (samples) {
- unsigned long avg = sum / samples;
- unsigned long sd = int_sqrt(sum2 / samples - avg*avg);
- rt_chain_length_max = max_t(unsigned long,
- ip_rt_gc_elasticity,
- (avg + 4*sd) >> FRACT_BITS);
- }
- rover = i;
-}
-
-/*
- * rt_worker_func() is run in process context.
- * we call rt_check_expire() to scan part of the hash table
- */
-static void rt_worker_func(struct work_struct *work)
-{
- rt_check_expire();
- schedule_delayed_work(&expires_work, ip_rt_gc_interval);
-}
-
-/*
* Perturbation of rt_genid by a small quantity [1..256]
* Using 8 bits of shuffling ensure we can call rt_cache_invalidate()
* many times (2^24) without giving recent rt_genid.
@@ -933,167 +493,6 @@ static void rt_cache_invalidate(struct net *net)
void rt_cache_flush(struct net *net, int delay)
{
rt_cache_invalidate(net);
- if (delay >= 0)
- rt_do_flush(net, !in_softirq());
-}
-
-/* Flush previous cache invalidated entries from the cache */
-void rt_cache_flush_batch(struct net *net)
-{
- rt_do_flush(net, !in_softirq());
-}
-
-static void rt_emergency_hash_rebuild(struct net *net)
-{
- net_warn_ratelimited("Route hash chain too long!\n");
- rt_cache_invalidate(net);
-}
-
-/*
- Short description of GC goals.
-
- We want to build algorithm, which will keep routing cache
- at some equilibrium point, when number of aged off entries
- is kept approximately equal to newly generated ones.
-
- Current expiration strength is variable "expire".
- We try to adjust it dynamically, so that if networking
- is idle expires is large enough to keep enough of warm entries,
- and when load increases it reduces to limit cache size.
- */
-
-static int rt_garbage_collect(struct dst_ops *ops)
-{
- static unsigned long expire = RT_GC_TIMEOUT;
- static unsigned long last_gc;
- static int rover;
- static int equilibrium;
- struct rtable *rth;
- struct rtable __rcu **rthp;
- unsigned long now = jiffies;
- int goal;
- int entries = dst_entries_get_fast(&ipv4_dst_ops);
-
- /*
- * Garbage collection is pretty expensive,
- * do not make it too frequently.
- */
-
- RT_CACHE_STAT_INC(gc_total);
-
- if (now - last_gc < ip_rt_gc_min_interval &&
- entries < ip_rt_max_size) {
- RT_CACHE_STAT_INC(gc_ignored);
- goto out;
- }
-
- entries = dst_entries_get_slow(&ipv4_dst_ops);
- /* Calculate number of entries, which we want to expire now. */
- goal = entries - (ip_rt_gc_elasticity << rt_hash_log);
- if (goal <= 0) {
- if (equilibrium < ipv4_dst_ops.gc_thresh)
- equilibrium = ipv4_dst_ops.gc_thresh;
- goal = entries - equilibrium;
- if (goal > 0) {
- equilibrium += min_t(unsigned int, goal >> 1, rt_hash_mask + 1);
- goal = entries - equilibrium;
- }
- } else {
- /* We are in dangerous area. Try to reduce cache really
- * aggressively.
- */
- goal = max_t(unsigned int, goal >> 1, rt_hash_mask + 1);
- equilibrium = entries - goal;
- }
-
- if (now - last_gc >= ip_rt_gc_min_interval)
- last_gc = now;
-
- if (goal <= 0) {
- equilibrium += goal;
- goto work_done;
- }
-
- do {
- int i, k;
-
- for (i = rt_hash_mask, k = rover; i >= 0; i--) {
- unsigned long tmo = expire;
-
- k = (k + 1) & rt_hash_mask;
- rthp = &rt_hash_table[k].chain;
- spin_lock_bh(rt_hash_lock_addr(k));
- while ((rth = rcu_dereference_protected(*rthp,
- lockdep_is_held(rt_hash_lock_addr(k)))) != NULL) {
- if (!rt_is_expired(rth) &&
- !rt_may_expire(rth, tmo, expire)) {
- tmo >>= 1;
- rthp = &rth->dst.rt_next;
- continue;
- }
- *rthp = rth->dst.rt_next;
- rt_free(rth);
- goal--;
- }
- spin_unlock_bh(rt_hash_lock_addr(k));
- if (goal <= 0)
- break;
- }
- rover = k;
-
- if (goal <= 0)
- goto work_done;
-
- /* Goal is not achieved. We stop process if:
-
- - if expire reduced to zero. Otherwise, expire is halfed.
- - if table is not full.
- - if we are called from interrupt.
- - jiffies check is just fallback/debug loop breaker.
- We will not spin here for long time in any case.
- */
-
- RT_CACHE_STAT_INC(gc_goal_miss);
-
- if (expire == 0)
- break;
-
- expire >>= 1;
-
- if (dst_entries_get_fast(&ipv4_dst_ops) < ip_rt_max_size)
- goto out;
- } while (!in_softirq() && time_before_eq(jiffies, now));
-
- if (dst_entries_get_fast(&ipv4_dst_ops) < ip_rt_max_size)
- goto out;
- if (dst_entries_get_slow(&ipv4_dst_ops) < ip_rt_max_size)
- goto out;
- net_warn_ratelimited("dst cache overflow\n");
- RT_CACHE_STAT_INC(gc_dst_overflow);
- return 1;
-
-work_done:
- expire += ip_rt_gc_min_interval;
- if (expire > ip_rt_gc_timeout ||
- dst_entries_get_fast(&ipv4_dst_ops) < ipv4_dst_ops.gc_thresh ||
- dst_entries_get_slow(&ipv4_dst_ops) < ipv4_dst_ops.gc_thresh)
- expire = ip_rt_gc_timeout;
-out: return 0;
-}
-
-/*
- * Returns number of entries in a hash chain that have different hash_inputs
- */
-static int slow_chain_length(const struct rtable *head)
-{
- int length = 0;
- const struct rtable *rth = head;
-
- while (rth) {
- length += has_noalias(head, rth);
- rth = rcu_dereference_protected(rth->dst.rt_next, 1);
- }
- return length >> FRACT_BITS;
}
static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, const void *daddr)
@@ -1127,178 +526,17 @@ static int rt_bind_neighbour(struct rtable *rt)
return 0;
}
-static struct rtable *rt_intern_hash(unsigned int hash, struct rtable *rt,
- struct sk_buff *skb, int ifindex)
+static struct rtable *rt_finalize(struct rtable *rt, struct sk_buff *skb)
{
- struct rtable *rth, *cand;
- struct rtable __rcu **rthp, **candp;
- unsigned long now;
- u32 min_score;
- int chain_length;
- int attempts = !in_softirq();
-
-restart:
- chain_length = 0;
- min_score = ~(u32)0;
- cand = NULL;
- candp = NULL;
- now = jiffies;
-
- if (!rt_caching(dev_net(rt->dst.dev)) || (rt->dst.flags & DST_NOCACHE)) {
- /*
- * If we're not caching, just tell the caller we
- * were successful and don't touch the route. The
- * caller hold the sole reference to the cache entry, and
- * it will be released when the caller is done with it.
- * If we drop it here, the callers have no way to resolve routes
- * when we're not caching. Instead, just point *rp at rt, so
- * the caller gets a single use out of the route
- * Note that we do rt_free on this new route entry, so that
- * once its refcount hits zero, we are still able to reap it
- * (Thanks Alexey)
- * Note: To avoid expensive rcu stuff for this uncached dst,
- * we set DST_NOCACHE so that dst_release() can free dst without
- * waiting a grace period.
- */
-
- rt->dst.flags |= DST_NOCACHE;
- if (rt->rt_type == RTN_UNICAST || rt_is_output_route(rt)) {
- int err = rt_bind_neighbour(rt);
- if (err) {
- net_warn_ratelimited("Neighbour table failure & not caching routes\n");
- ip_rt_put(rt);
- return ERR_PTR(err);
- }
- }
-
- goto skip_hashing;
- }
-
- rthp = &rt_hash_table[hash].chain;
-
- spin_lock_bh(rt_hash_lock_addr(hash));
- while ((rth = rcu_dereference_protected(*rthp,
- lockdep_is_held(rt_hash_lock_addr(hash)))) != NULL) {
- if (rt_is_expired(rth)) {
- *rthp = rth->dst.rt_next;
- rt_free(rth);
- continue;
- }
- if (compare_keys(rth, rt) && compare_netns(rth, rt)) {
- /* Put it first */
- *rthp = rth->dst.rt_next;
- /*
- * Since lookup is lockfree, the deletion
- * must be visible to another weakly ordered CPU before
- * the insertion at the start of the hash chain.
- */
- rcu_assign_pointer(rth->dst.rt_next,
- rt_hash_table[hash].chain);
- /*
- * Since lookup is lockfree, the update writes
- * must be ordered for consistency on SMP.
- */
- rcu_assign_pointer(rt_hash_table[hash].chain, rth);
-
- dst_use(&rth->dst, now);
- spin_unlock_bh(rt_hash_lock_addr(hash));
-
- rt_drop(rt);
- if (skb)
- skb_dst_set(skb, &rth->dst);
- return rth;
- }
-
- if (!atomic_read(&rth->dst.__refcnt)) {
- u32 score = rt_score(rth);
-
- if (score <= min_score) {
- cand = rth;
- candp = rthp;
- min_score = score;
- }
- }
-
- chain_length++;
-
- rthp = &rth->dst.rt_next;
- }
-
- if (cand) {
- /* ip_rt_gc_elasticity used to be average length of chain
- * length, when exceeded gc becomes really aggressive.
- *
- * The second limit is less certain. At the moment it allows
- * only 2 entries per bucket. We will see.
- */
- if (chain_length > ip_rt_gc_elasticity) {
- *candp = cand->dst.rt_next;
- rt_free(cand);
- }
- } else {
- if (chain_length > rt_chain_length_max &&
- slow_chain_length(rt_hash_table[hash].chain) > rt_chain_length_max) {
- struct net *net = dev_net(rt->dst.dev);
- int num = ++net->ipv4.current_rt_cache_rebuild_count;
- if (!rt_caching(net)) {
- pr_warn("%s: %d rebuilds is over limit, route caching disabled\n",
- rt->dst.dev->name, num);
- }
- rt_emergency_hash_rebuild(net);
- spin_unlock_bh(rt_hash_lock_addr(hash));
-
- hash = rt_hash(rt->rt_key_dst, rt->rt_key_src,
- ifindex, rt_genid(net));
- goto restart;
- }
- }
-
- /* Try to bind route to arp only if it is output
- route or unicast forwarding path.
- */
if (rt->rt_type == RTN_UNICAST || rt_is_output_route(rt)) {
int err = rt_bind_neighbour(rt);
if (err) {
- spin_unlock_bh(rt_hash_lock_addr(hash));
-
- if (err != -ENOBUFS) {
- rt_drop(rt);
- return ERR_PTR(err);
- }
-
- /* Neighbour tables are full and nothing
- can be released. Try to shrink route cache,
- it is most likely it holds some neighbour records.
- */
- if (attempts-- > 0) {
- int saved_elasticity = ip_rt_gc_elasticity;
- int saved_int = ip_rt_gc_min_interval;
- ip_rt_gc_elasticity = 1;
- ip_rt_gc_min_interval = 0;
- rt_garbage_collect(&ipv4_dst_ops);
- ip_rt_gc_min_interval = saved_int;
- ip_rt_gc_elasticity = saved_elasticity;
- goto restart;
- }
-
- net_warn_ratelimited("Neighbour table overflow\n");
- rt_drop(rt);
- return ERR_PTR(-ENOBUFS);
+ net_warn_ratelimited("Neighbour table failure\n");
+ ip_rt_put(rt);
+ return ERR_PTR(err);
}
}
- rt->dst.rt_next = rt_hash_table[hash].chain;
-
- /*
- * Since lookup is lockfree, we must make sure
- * previous writes to rt are committed to memory
- * before making rt visible to other CPUS.
- */
- rcu_assign_pointer(rt_hash_table[hash].chain, rt);
-
- spin_unlock_bh(rt_hash_lock_addr(hash));
-
-skip_hashing:
if (skb)
skb_dst_set(skb, &rt->dst);
return rt;
@@ -1370,26 +608,6 @@ void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more)
}
EXPORT_SYMBOL(__ip_select_ident);
-static void rt_del(unsigned int hash, struct rtable *rt)
-{
- struct rtable __rcu **rthp;
- struct rtable *aux;
-
- rthp = &rt_hash_table[hash].chain;
- spin_lock_bh(rt_hash_lock_addr(hash));
- ip_rt_put(rt);
- while ((aux = rcu_dereference_protected(*rthp,
- lockdep_is_held(rt_hash_lock_addr(hash)))) != NULL) {
- if (aux == rt || rt_is_expired(aux)) {
- *rthp = aux->dst.rt_next;
- rt_free(aux);
- continue;
- }
- rthp = &aux->dst.rt_next;
- }
- spin_unlock_bh(rt_hash_lock_addr(hash));
-}
-
static void check_peer_redir(struct dst_entry *dst, struct inet_peer *peer)
{
struct rtable *rt = (struct rtable *) dst;
@@ -1417,16 +635,16 @@ static void check_peer_redir(struct dst_entry *dst, struct inet_peer *peer)
}
/* called in rcu_read_lock() section */
-void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
- __be32 saddr, struct net_device *dev)
+void ip_rt_redirect(struct sk_buff *skb, __be32 old_gw, __be32 new_gw)
{
- int s, i;
- struct in_device *in_dev = __in_dev_get_rcu(dev);
- __be32 skeys[2] = { saddr, 0 };
- int ikeys[2] = { dev->ifindex, 0 };
- struct inet_peer *peer;
+ struct net_device *dev = skb->dev;
+ struct in_device *in_dev;
+ const struct iphdr *iph;
+ struct fib_result res;
+ struct flowi4 fl4;
struct net *net;
+ in_dev = __in_dev_get_rcu(dev);
if (!in_dev)
return;
@@ -1446,41 +664,32 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
goto reject_redirect;
}
- for (s = 0; s < 2; s++) {
- for (i = 0; i < 2; i++) {
- unsigned int hash;
- struct rtable __rcu **rthp;
- struct rtable *rt;
-
- hash = rt_hash(daddr, skeys[s], ikeys[i], rt_genid(net));
-
- rthp = &rt_hash_table[hash].chain;
-
- while ((rt = rcu_dereference(*rthp)) != NULL) {
- rthp = &rt->dst.rt_next;
-
- if (rt->rt_key_dst != daddr ||
- rt->rt_key_src != skeys[s] ||
- rt->rt_oif != ikeys[i] ||
- rt_is_input_route(rt) ||
- rt_is_expired(rt) ||
- !net_eq(dev_net(rt->dst.dev), net) ||
- rt->dst.error ||
- rt->dst.dev != dev ||
- rt->rt_gateway != old_gw)
- continue;
-
- peer = rt_get_peer_create(rt, rt->rt_dst);
- if (peer) {
- if (peer->redirect_learned.a4 != new_gw) {
- peer->redirect_learned.a4 = new_gw;
- atomic_inc(&__rt_peer_genid);
- }
- check_peer_redir(&rt->dst, peer);
- }
+ iph = (const struct iphdr *) skb->data;
+
+ memset(&fl4, 0, sizeof(fl4));
+ fl4.daddr = iph->daddr;
+ fl4.saddr = iph->saddr;
+ fl4.flowi4_tos = RT_TOS(iph->tos);
+
+ rcu_read_lock();
+ if (fib_lookup(net, &fl4, &res) == 0) {
+ struct inet_peer_base *base;
+ struct inet_peer *peer;
+
+ base = (res.table ?
+ &res.table->tb_peers :
+ net->ipv4.peers);
+ peer = inet_getpeer_v4(base, iph->daddr, 1);
+ if (peer) {
+ if (peer->redirect_learned.a4 != new_gw) {
+ peer->redirect_learned.a4 = new_gw;
+ atomic_inc(&__rt_peer_genid);
}
+ inet_putpeer(peer);
}
}
+ rcu_read_unlock();
+
return;
reject_redirect:
@@ -1521,10 +730,7 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst)
ip_rt_put(rt);
ret = NULL;
} else if (rt->rt_flags & RTCF_REDIRECTED) {
- unsigned int hash = rt_hash(rt->rt_key_dst, rt->rt_key_src,
- rt->rt_oif,
- rt_genid(dev_net(dst->dev)));
- rt_del(hash, rt);
+ ip_rt_put(rt);
ret = NULL;
} else if (rt_has_peer(rt)) {
struct inet_peer *peer = rt_peer_ptr(rt);
@@ -1967,7 +1173,7 @@ static struct rtable *rt_dst_alloc(struct net_device *dev,
bool nopolicy, bool noxfrm)
{
return dst_alloc(&ipv4_dst_ops, dev, 1, -1,
- DST_HOST |
+ DST_HOST | DST_NOCACHE |
(nopolicy ? DST_NOPOLICY : 0) |
(noxfrm ? DST_NOXFRM : 0));
}
@@ -1976,7 +1182,6 @@ static struct rtable *rt_dst_alloc(struct net_device *dev,
static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
u8 tos, struct net_device *dev, int our)
{
- unsigned int hash;
struct rtable *rth;
struct in_device *in_dev = __in_dev_get_rcu(dev);
u32 itag = 0;
@@ -2041,8 +1246,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
#endif
RT_CACHE_STAT_INC(in_slow_mc);
- hash = rt_hash(daddr, saddr, dev->ifindex, rt_genid(dev_net(dev)));
- rth = rt_intern_hash(hash, rth, skb, dev->ifindex);
+ rth = rt_finalize(rth, skb);
return IS_ERR(rth) ? PTR_ERR(rth) : 0;
e_nobufs:
@@ -2176,7 +1380,6 @@ static int ip_mkroute_input(struct sk_buff *skb,
{
struct rtable *rth = NULL;
int err;
- unsigned int hash;
#ifdef CONFIG_IP_ROUTE_MULTIPATH
if (res->fi && res->fi->fib_nhs > 1)
@@ -2188,10 +1391,7 @@ static int ip_mkroute_input(struct sk_buff *skb,
if (err)
return err;
- /* put it into the cache */
- hash = rt_hash(daddr, saddr, fl4->flowi4_iif,
- rt_genid(dev_net(rth->dst.dev)));
- rth = rt_intern_hash(hash, rth, skb, fl4->flowi4_iif);
+ rth = rt_finalize(rth, skb);
if (IS_ERR(rth))
return PTR_ERR(rth);
return 0;
@@ -2217,7 +1417,6 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
unsigned int flags = 0;
u32 itag = 0;
struct rtable *rth;
- unsigned int hash;
int err = -EINVAL;
struct net *net = dev_net(dev);
@@ -2340,8 +1539,7 @@ local_input:
rth->dst.error= -err;
rth->rt_flags &= ~RTCF_LOCAL;
}
- hash = rt_hash(daddr, saddr, fl4.flowi4_iif, rt_genid(net));
- rth = rt_intern_hash(hash, rth, skb, fl4.flowi4_iif);
+ rth = rt_finalize(rth, skb);
err = 0;
if (IS_ERR(rth))
err = PTR_ERR(rth);
@@ -2383,47 +1581,10 @@ martian_source_keep_err:
int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr,
u8 tos, struct net_device *dev, bool noref)
{
- struct rtable *rth;
- unsigned int hash;
- int iif = dev->ifindex;
- struct net *net;
int res;
- net = dev_net(dev);
-
rcu_read_lock();
- if (!rt_caching(net))
- goto skip_cache;
-
- tos &= IPTOS_RT_MASK;
- hash = rt_hash(daddr, saddr, iif, rt_genid(net));
-
- for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
- rth = rcu_dereference(rth->dst.rt_next)) {
- if ((((__force u32)rth->rt_key_dst ^ (__force u32)daddr) |
- ((__force u32)rth->rt_key_src ^ (__force u32)saddr) |
- (rth->rt_route_iif ^ iif) |
- (rth->rt_key_tos ^ tos)) == 0 &&
- rth->rt_mark == skb->mark &&
- net_eq(dev_net(rth->dst.dev), net) &&
- !rt_is_expired(rth)) {
- ipv4_validate_peer(rth);
- if (noref) {
- dst_use_noref(&rth->dst, jiffies);
- skb_dst_set_noref(skb, &rth->dst);
- } else {
- dst_use(&rth->dst, jiffies);
- skb_dst_set(skb, &rth->dst);
- }
- RT_CACHE_STAT_INC(in_hit);
- rcu_read_unlock();
- return 0;
- }
- RT_CACHE_STAT_INC(in_hlist_search);
- }
-
-skip_cache:
/* Multicast recognition logic is moved from route cache to here.
The problem was that too many Ethernet cards have broken/missing
hardware multicast filters :-( As result the host on multicasting
@@ -2568,10 +1729,9 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
/*
* Major route resolver routine.
- * called with rcu_read_lock();
*/
-static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4)
+struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
{
struct net_device *dev_out = NULL;
__u8 tos = RT_FL_TOS(fl4);
@@ -2753,58 +1913,13 @@ static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4)
make_route:
rth = __mkroute_output(&res, fl4, orig_daddr, orig_saddr, orig_oif,
tos, dev_out, flags);
- if (!IS_ERR(rth)) {
- unsigned int hash;
-
- hash = rt_hash(orig_daddr, orig_saddr, orig_oif,
- rt_genid(dev_net(dev_out)));
- rth = rt_intern_hash(hash, rth, NULL, orig_oif);
- }
+ if (!IS_ERR(rth))
+ rth = rt_finalize(rth, NULL);
out:
rcu_read_unlock();
return rth;
}
-
-struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *flp4)
-{
- struct rtable *rth;
- unsigned int hash;
-
- if (!rt_caching(net))
- goto slow_output;
-
- hash = rt_hash(flp4->daddr, flp4->saddr, flp4->flowi4_oif, rt_genid(net));
-
- rcu_read_lock_bh();
- for (rth = rcu_dereference_bh(rt_hash_table[hash].chain); rth;
- rth = rcu_dereference_bh(rth->dst.rt_next)) {
- if (rth->rt_key_dst == flp4->daddr &&
- rth->rt_key_src == flp4->saddr &&
- rt_is_output_route(rth) &&
- rth->rt_oif == flp4->flowi4_oif &&
- rth->rt_mark == flp4->flowi4_mark &&
- !((rth->rt_key_tos ^ flp4->flowi4_tos) &
- (IPTOS_RT_MASK | RTO_ONLINK)) &&
- net_eq(dev_net(rth->dst.dev), net) &&
- !rt_is_expired(rth)) {
- ipv4_validate_peer(rth);
- dst_use(&rth->dst, jiffies);
- RT_CACHE_STAT_INC(out_hit);
- rcu_read_unlock_bh();
- if (!flp4->saddr)
- flp4->saddr = rth->rt_src;
- if (!flp4->daddr)
- flp4->daddr = rth->rt_dst;
- return rth;
- }
- RT_CACHE_STAT_INC(out_hlist_search);
- }
- rcu_read_unlock_bh();
-
-slow_output:
- return ip_route_output_slow(net, flp4);
-}
EXPORT_SYMBOL_GPL(__ip_route_output_key);
static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie)
@@ -3114,43 +2229,6 @@ errout_free:
int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
- struct rtable *rt;
- int h, s_h;
- int idx, s_idx;
- struct net *net;
-
- net = sock_net(skb->sk);
-
- s_h = cb->args[0];
- if (s_h < 0)
- s_h = 0;
- s_idx = idx = cb->args[1];
- for (h = s_h; h <= rt_hash_mask; h++, s_idx = 0) {
- if (!rt_hash_table[h].chain)
- continue;
- rcu_read_lock_bh();
- for (rt = rcu_dereference_bh(rt_hash_table[h].chain), idx = 0; rt;
- rt = rcu_dereference_bh(rt->dst.rt_next), idx++) {
- if (!net_eq(dev_net(rt->dst.dev), net) || idx < s_idx)
- continue;
- if (rt_is_expired(rt))
- continue;
- skb_dst_set_noref(skb, &rt->dst);
- if (rt_fill_info(net, skb, NETLINK_CB(cb->skb).pid,
- cb->nlh->nlmsg_seq, RTM_NEWROUTE,
- 1, NLM_F_MULTI) <= 0) {
- skb_dst_drop(skb);
- rcu_read_unlock_bh();
- goto done;
- }
- skb_dst_drop(skb);
- }
- rcu_read_unlock_bh();
- }
-
-done:
- cb->args[0] = h;
- cb->args[1] = idx;
return skb->len;
}
@@ -3384,22 +2462,6 @@ static __net_initdata struct pernet_operations ipv4_inetpeer_ops = {
struct ip_rt_acct __percpu *ip_rt_acct __read_mostly;
#endif /* CONFIG_IP_ROUTE_CLASSID */
-static __initdata unsigned long rhash_entries;
-static int __init set_rhash_entries(char *str)
-{
- ssize_t ret;
-
- if (!str)
- return 0;
-
- ret = kstrtoul(str, 0, &rhash_entries);
- if (ret)
- return 0;
-
- return 1;
-}
-__setup("rhash_entries=", set_rhash_entries);
-
int __init ip_rt_init(void)
{
int rc = 0;
@@ -3422,31 +2484,12 @@ int __init ip_rt_init(void)
if (dst_entries_init(&ipv4_dst_blackhole_ops) < 0)
panic("IP: failed to allocate ipv4_dst_blackhole_ops counter\n");
- rt_hash_table = (struct rt_hash_bucket *)
- alloc_large_system_hash("IP route cache",
- sizeof(struct rt_hash_bucket),
- rhash_entries,
- (totalram_pages >= 128 * 1024) ?
- 15 : 17,
- 0,
- &rt_hash_log,
- &rt_hash_mask,
- 0,
- rhash_entries ? 0 : 512 * 1024);
- memset(rt_hash_table, 0, (rt_hash_mask + 1) * sizeof(struct rt_hash_bucket));
- rt_hash_lock_init();
-
- ipv4_dst_ops.gc_thresh = (rt_hash_mask + 1);
- ip_rt_max_size = (rt_hash_mask + 1) * 16;
+ ipv4_dst_ops.gc_thresh = ~0;
+ ip_rt_max_size = INT_MAX;
devinet_init();
ip_fib_init();
- INIT_DELAYED_WORK_DEFERRABLE(&expires_work, rt_worker_func);
- expires_ljiffies = jiffies;
- schedule_delayed_work(&expires_work,
- net_random() % ip_rt_gc_interval + ip_rt_gc_interval);
-
if (ip_rt_proc_init())
pr_err("Unable to create route proc files\n");
#ifdef CONFIG_XFRM
--
1.7.10
^ permalink raw reply related
* [PATCH 0/5] rtcache remove respin
From: David Miller @ 2012-07-01 12:02 UTC (permalink / raw)
To: netdev
It's been a while and there were of course a lot of merge hassles with
the most recent set I posted, so I respun these patches tonight
because I wanted to see the effects of the recent rpfilter hacks on an
rtcache-less system.
On a SPARC T3-1:
1) Output route lookup: ~2800 cycles
2) Input route lookups: ~3000 cycles (rpfilter=0)
~4300 cycles (rpfilter=1)
Another nice part is how small struct rtable is after this patch set:
struct rtable {
struct dst_entry dst;
int rt_genid;
unsigned int rt_flags;
__u16 rt_type;
__be32 rt_dst;
int rt_route_iif;
int rt_iif;
int rt_oif;
__be32 rt_gateway;
u32 rt_peer_genid;
unsigned long _peer;
struct fib_info *fi;
};
which is about 208 bytes on sparc64.
Signed-off-by: David S. Miller <davem@davemloft.net>
^ permalink raw reply
* [net-next:master 294/295] drivers/net/ethernet/stmicro/stmmac/stmmac_main.c:287:3: error: implicit declaration of function 'phy_init_eee'
From: wfg @ 2012-07-01 11:35 UTC (permalink / raw)
To: Giuseppe CAVALLARO; +Cc: David S. Miller, netdev
[-- Attachment #1: Type: text/plain, Size: 1958 bytes --]
Hi Giuseppe,
Here is a build dependency: the below commit used some functions
provided by the immediate next commit "phy: add the EEE support and
the way to access to the MMD registers."
---
Kernel build failed on
tree: git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next.git master
head: a59a4d1921664da63d801ba477950114c71c88c9
commit: d765955d2ae0b88781a0db3a5bacfe4241925e09 [294/295] stmmac: add the Energy Efficient Ethernet support
config: x86_64-allmodconfig
All related error/warning messages:
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c: In function 'stmmac_eee_init':
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c:287:3: error: implicit declaration of function 'phy_init_eee' [-Werror=implicit-function-declaration]
drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c: In function 'stmmac_get_ethtool_stats':
drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c:380:4: error: implicit declaration of function 'phy_get_eee_err' [-Werror=implicit-function-declaration]
drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c: In function 'stmmac_ethtool_op_get_eee':
drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c:494:2: error: implicit declaration of function 'phy_ethtool_get_eee' [-Werror=implicit-function-declaration]
drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c: In function 'stmmac_ethtool_op_set_eee':
drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c:519:2: error: implicit declaration of function 'phy_ethtool_set_eee' [-Werror=implicit-function-declaration]
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c:287:
284 /* MAC core supports the EEE feature. */
285 if (priv->dma_cap.eee) {
286 /* Check if the PHY supports EEE */
> 287 if (phy_init_eee(priv->phydev, 1))
288 goto out;
289
290 priv->eee_active = 1;
---
0-DAY kernel build testing backend Open Source Technology Centre
Fengguang Wu <wfg@linux.intel.com> Intel Corporation
[-- Attachment #2: 0001-stmmac-add-the-Energy-Efficient-Ethernet-support.patch --]
[-- Type: text/x-diff, Size: 36081 bytes --]
>From d765955d2ae0b88781a0db3a5bacfe4241925e09 Mon Sep 17 00:00:00 2001
From: Giuseppe CAVALLARO <peppe.cavallaro@st.com>
Date: Wed, 27 Jun 2012 21:14:37 +0000
Subject: [PATCH] stmmac: add the Energy Efficient Ethernet support
This patch adds the Energy Efficient Ethernet support to the stmmac.
Please see the driver's documentation for further details about this support
in the driver.
Thanks also goes to Rayagond Kokatanur for his first implementation.
Note:
to clearly manage and expose the lpi interrupt status and eee ethtool
stats I've had to do some modifications to the driver's design and I
found really useful to move other parts of the code (e.g. mmc irq stat)
in the main directly. So this means that some core has been reworked
to introduce the EEE.
v1: initial patch
v2: fixed some sparse issues (typos)
v3: erroneously sent the v2 renamed as v3
v4:
o Fixed the return value of the stmmac_eee_init as suggested by D.Miller
o Totally reviewed the ethtool support for EEE
o Added a new internal parameter to tune the SW timer for TX LPI.
v5: do not change any eee setting in case of the stmmac_ethtool_op_set_eee fails
(it has to return -EOPNOTSUPP in that case).
Signed-off-by: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
drivers/net/ethernet/stmicro/stmmac/common.h | 31 +++-
drivers/net/ethernet/stmicro/stmmac/dwmac1000.h | 20 +++
.../net/ethernet/stmicro/stmmac/dwmac1000_core.c | 101 +++++++++++-
.../net/ethernet/stmicro/stmmac/dwmac100_core.c | 4 +-
drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h | 1 +
drivers/net/ethernet/stmicro/stmmac/stmmac.h | 8 +
.../net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 57 +++++++
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 166 +++++++++++++++++++-
.../net/ethernet/stmicro/stmmac/stmmac_platform.c | 2 +
9 files changed, 372 insertions(+), 18 deletions(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index bcd54d6..e2d0832 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -89,18 +89,28 @@ struct stmmac_extra_stats {
unsigned long tx_early_irq;
unsigned long fatal_bus_error_irq;
/* Extra info */
unsigned long threshold;
unsigned long tx_pkt_n;
unsigned long rx_pkt_n;
unsigned long poll_n;
unsigned long sched_timer_n;
unsigned long normal_irq_n;
+ unsigned long mmc_tx_irq_n;
+ unsigned long mmc_rx_irq_n;
+ unsigned long mmc_rx_csum_offload_irq_n;
+ /* EEE */
+ unsigned long irq_receive_pmt_irq_n;
+ unsigned long irq_tx_path_in_lpi_mode_n;
+ unsigned long irq_tx_path_exit_lpi_mode_n;
+ unsigned long irq_rx_path_in_lpi_mode_n;
+ unsigned long irq_rx_path_exit_lpi_mode_n;
+ unsigned long phy_eee_wakeup_error_n;
};
/* CSR Frequency Access Defines*/
#define CSR_F_35M 35000000
#define CSR_F_60M 60000000
#define CSR_F_100M 100000000
#define CSR_F_150M 150000000
#define CSR_F_250M 250000000
#define CSR_F_300M 300000000
@@ -156,18 +166,29 @@ enum rx_frame_status { /* IPC status */
llc_snap = 4,
};
enum tx_dma_irq_status {
tx_hard_error = 1,
tx_hard_error_bump_tc = 2,
handle_tx_rx = 3,
};
+enum core_specific_irq_mask {
+ core_mmc_tx_irq = 1,
+ core_mmc_rx_irq = 2,
+ core_mmc_rx_csum_offload_irq = 4,
+ core_irq_receive_pmt_irq = 8,
+ core_irq_tx_path_in_lpi_mode = 16,
+ core_irq_tx_path_exit_lpi_mode = 32,
+ core_irq_rx_path_in_lpi_mode = 64,
+ core_irq_rx_path_exit_lpi_mode = 128,
+};
+
/* DMA HW capabilities */
struct dma_features {
unsigned int mbps_10_100;
unsigned int mbps_1000;
unsigned int half_duplex;
unsigned int hash_filter;
unsigned int multi_addr;
unsigned int pcs;
unsigned int sma_mdio;
@@ -202,18 +223,22 @@ struct dma_features {
/* Power Down and WOL */
#define PMT_NOT_SUPPORTED 0
#define PMT_SUPPORTED 1
/* Common MAC defines */
#define MAC_CTRL_REG 0x00000000 /* MAC Control */
#define MAC_ENABLE_TX 0x00000008 /* Transmitter Enable */
#define MAC_RNABLE_RX 0x00000004 /* Receiver Enable */
+/* Default LPI timers */
+#define STMMAC_DEFAULT_LIT_LS_TIMER 0x3E8
+#define STMMAC_DEFAULT_TWT_LS_TIMER 0x0
+
struct stmmac_desc_ops {
/* DMA RX descriptor ring initialization */
void (*init_rx_desc) (struct dma_desc *p, unsigned int ring_size,
int disable_rx_ic);
/* DMA TX descriptor ring initialization */
void (*init_tx_desc) (struct dma_desc *p, unsigned int ring_size);
/* Invoked by the xmit function to prepare the tx descriptor */
void (*prepare_tx_desc) (struct dma_desc *p, int is_fs, int len,
@@ -272,31 +297,35 @@ struct stmmac_dma_ops {
struct stmmac_ops {
/* MAC core initialization */
void (*core_init) (void __iomem *ioaddr) ____cacheline_aligned;
/* Enable and verify that the IPC module is supported */
int (*rx_ipc) (void __iomem *ioaddr);
/* Dump MAC registers */
void (*dump_regs) (void __iomem *ioaddr);
/* Handle extra events on specific interrupts hw dependent */
- void (*host_irq_status) (void __iomem *ioaddr);
+ int (*host_irq_status) (void __iomem *ioaddr);
/* Multicast filter setting */
void (*set_filter) (struct net_device *dev, int id);
/* Flow control setting */
void (*flow_ctrl) (void __iomem *ioaddr, unsigned int duplex,
unsigned int fc, unsigned int pause_time);
/* Set power management mode (e.g. magic frame) */
void (*pmt) (void __iomem *ioaddr, unsigned long mode);
/* Set/Get Unicast MAC addresses */
void (*set_umac_addr) (void __iomem *ioaddr, unsigned char *addr,
unsigned int reg_n);
void (*get_umac_addr) (void __iomem *ioaddr, unsigned char *addr,
unsigned int reg_n);
+ void (*set_eee_mode) (void __iomem *ioaddr);
+ void (*reset_eee_mode) (void __iomem *ioaddr);
+ void (*set_eee_timer) (void __iomem *ioaddr, int ls, int tw);
+ void (*set_eee_pls) (void __iomem *ioaddr, int link);
};
struct mac_link {
int port;
int duplex;
int speed;
};
struct mii_regs {
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
index 23478bf..f90fcb5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
@@ -30,18 +30,19 @@
#define GMAC_MII_ADDR 0x00000010 /* MII Address */
#define GMAC_MII_DATA 0x00000014 /* MII Data */
#define GMAC_FLOW_CTRL 0x00000018 /* Flow Control */
#define GMAC_VLAN_TAG 0x0000001c /* VLAN Tag */
#define GMAC_VERSION 0x00000020 /* GMAC CORE Version */
#define GMAC_WAKEUP_FILTER 0x00000028 /* Wake-up Frame Filter */
#define GMAC_INT_STATUS 0x00000038 /* interrupt status register */
enum dwmac1000_irq_status {
+ lpiis_irq = 0x400,
time_stamp_irq = 0x0200,
mmc_rx_csum_offload_irq = 0x0080,
mmc_tx_irq = 0x0040,
mmc_rx_irq = 0x0020,
mmc_irq = 0x0010,
pmt_irq = 0x0008,
pcs_ane_irq = 0x0004,
pcs_link_irq = 0x0002,
rgmii_irq = 0x0001,
@@ -54,18 +55,37 @@ enum power_event {
pointer_reset = 0x80000000,
global_unicast = 0x00000200,
wake_up_rx_frame = 0x00000040,
magic_frame = 0x00000020,
wake_up_frame_en = 0x00000004,
magic_pkt_en = 0x00000002,
power_down = 0x00000001,
};
+/* Energy Efficient Ethernet (EEE)
+ *
+ * LPI status, timer and control register offset
+ */
+#define LPI_CTRL_STATUS 0x0030
+#define LPI_TIMER_CTRL 0x0034
+
+/* LPI control and status defines */
+#define LPI_CTRL_STATUS_LPITXA 0x00080000 /* Enable LPI TX Automate */
+#define LPI_CTRL_STATUS_PLSEN 0x00040000 /* Enable PHY Link Status */
+#define LPI_CTRL_STATUS_PLS 0x00020000 /* PHY Link Status */
+#define LPI_CTRL_STATUS_LPIEN 0x00010000 /* LPI Enable */
+#define LPI_CTRL_STATUS_RLPIST 0x00000200 /* Receive LPI state */
+#define LPI_CTRL_STATUS_TLPIST 0x00000100 /* Transmit LPI state */
+#define LPI_CTRL_STATUS_RLPIEX 0x00000008 /* Receive LPI Exit */
+#define LPI_CTRL_STATUS_RLPIEN 0x00000004 /* Receive LPI Entry */
+#define LPI_CTRL_STATUS_TLPIEX 0x00000002 /* Transmit LPI Exit */
+#define LPI_CTRL_STATUS_TLPIEN 0x00000001 /* Transmit LPI Entry */
+
/* GMAC HW ADDR regs */
#define GMAC_ADDR_HIGH(reg) (((reg > 15) ? 0x00000800 : 0x00000040) + \
(reg * 8))
#define GMAC_ADDR_LOW(reg) (((reg > 15) ? 0x00000804 : 0x00000044) + \
(reg * 8))
#define GMAC_MAX_PERFECT_ADDRESSES 32
#define GMAC_AN_CTRL 0x000000c0 /* AN control */
#define GMAC_AN_STATUS 0x000000c4 /* AN status */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index b5e4d02..bfe0226 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -188,50 +188,135 @@ static void dwmac1000_pmt(void __iomem *ioaddr, unsigned long mode)
if (mode & WAKE_UCAST) {
CHIP_DBG(KERN_DEBUG "GMAC: WOL on global unicast\n");
pmt |= global_unicast;
}
writel(pmt, ioaddr + GMAC_PMT);
}
-static void dwmac1000_irq_status(void __iomem *ioaddr)
+static int dwmac1000_irq_status(void __iomem *ioaddr)
{
u32 intr_status = readl(ioaddr + GMAC_INT_STATUS);
+ int status = 0;
/* Not used events (e.g. MMC interrupts) are not handled. */
- if ((intr_status & mmc_tx_irq))
- CHIP_DBG(KERN_DEBUG "GMAC: MMC tx interrupt: 0x%08x\n",
+ if ((intr_status & mmc_tx_irq)) {
+ CHIP_DBG(KERN_INFO "GMAC: MMC tx interrupt: 0x%08x\n",
readl(ioaddr + GMAC_MMC_TX_INTR));
- if (unlikely(intr_status & mmc_rx_irq))
- CHIP_DBG(KERN_DEBUG "GMAC: MMC rx interrupt: 0x%08x\n",
+ status |= core_mmc_tx_irq;
+ }
+ if (unlikely(intr_status & mmc_rx_irq)) {
+ CHIP_DBG(KERN_INFO "GMAC: MMC rx interrupt: 0x%08x\n",
readl(ioaddr + GMAC_MMC_RX_INTR));
- if (unlikely(intr_status & mmc_rx_csum_offload_irq))
- CHIP_DBG(KERN_DEBUG "GMAC: MMC rx csum offload: 0x%08x\n",
+ status |= core_mmc_rx_irq;
+ }
+ if (unlikely(intr_status & mmc_rx_csum_offload_irq)) {
+ CHIP_DBG(KERN_INFO "GMAC: MMC rx csum offload: 0x%08x\n",
readl(ioaddr + GMAC_MMC_RX_CSUM_OFFLOAD));
+ status |= core_mmc_rx_csum_offload_irq;
+ }
if (unlikely(intr_status & pmt_irq)) {
- CHIP_DBG(KERN_DEBUG "GMAC: received Magic frame\n");
+ CHIP_DBG(KERN_INFO "GMAC: received Magic frame\n");
/* clear the PMT bits 5 and 6 by reading the PMT
* status register. */
readl(ioaddr + GMAC_PMT);
+ status |= core_irq_receive_pmt_irq;
}
+ /* MAC trx/rx EEE LPI entry/exit interrupts */
+ if (intr_status & lpiis_irq) {
+ /* Clean LPI interrupt by reading the Reg 12 */
+ u32 lpi_status = readl(ioaddr + LPI_CTRL_STATUS);
+
+ if (lpi_status & LPI_CTRL_STATUS_TLPIEN) {
+ CHIP_DBG(KERN_INFO "GMAC TX entered in LPI\n");
+ status |= core_irq_tx_path_in_lpi_mode;
+ }
+ if (lpi_status & LPI_CTRL_STATUS_TLPIEX) {
+ CHIP_DBG(KERN_INFO "GMAC TX exit from LPI\n");
+ status |= core_irq_tx_path_exit_lpi_mode;
+ }
+ if (lpi_status & LPI_CTRL_STATUS_RLPIEN) {
+ CHIP_DBG(KERN_INFO "GMAC RX entered in LPI\n");
+ status |= core_irq_rx_path_in_lpi_mode;
+ }
+ if (lpi_status & LPI_CTRL_STATUS_RLPIEX) {
+ CHIP_DBG(KERN_INFO "GMAC RX exit from LPI\n");
+ status |= core_irq_rx_path_exit_lpi_mode;
+ }
+ }
+
+ return status;
+}
+
+static void dwmac1000_set_eee_mode(void __iomem *ioaddr)
+{
+ u32 value;
+
+ /* Enable the link status receive on RGMII, SGMII ore SMII
+ * receive path and instruct the transmit to enter in LPI
+ * state. */
+ value = readl(ioaddr + LPI_CTRL_STATUS);
+ value |= LPI_CTRL_STATUS_LPIEN | LPI_CTRL_STATUS_LPITXA;
+ writel(value, ioaddr + LPI_CTRL_STATUS);
+}
+
+static void dwmac1000_reset_eee_mode(void __iomem *ioaddr)
+{
+ u32 value;
+
+ value = readl(ioaddr + LPI_CTRL_STATUS);
+ value &= ~(LPI_CTRL_STATUS_LPIEN | LPI_CTRL_STATUS_LPITXA);
+ writel(value, ioaddr + LPI_CTRL_STATUS);
+}
+
+static void dwmac1000_set_eee_pls(void __iomem *ioaddr, int link)
+{
+ u32 value;
+
+ value = readl(ioaddr + LPI_CTRL_STATUS);
+
+ if (link)
+ value |= LPI_CTRL_STATUS_PLS;
+ else
+ value &= ~LPI_CTRL_STATUS_PLS;
+
+ writel(value, ioaddr + LPI_CTRL_STATUS);
+}
+
+static void dwmac1000_set_eee_timer(void __iomem *ioaddr, int ls, int tw)
+{
+ int value = ((tw & 0xffff)) | ((ls & 0x7ff) << 16);
+
+ /* Program the timers in the LPI timer control register:
+ * LS: minimum time (ms) for which the link
+ * status from PHY should be ok before transmitting
+ * the LPI pattern.
+ * TW: minimum time (us) for which the core waits
+ * after it has stopped transmitting the LPI pattern.
+ */
+ writel(value, ioaddr + LPI_TIMER_CTRL);
}
static const struct stmmac_ops dwmac1000_ops = {
.core_init = dwmac1000_core_init,
.rx_ipc = dwmac1000_rx_ipc_enable,
.dump_regs = dwmac1000_dump_regs,
.host_irq_status = dwmac1000_irq_status,
.set_filter = dwmac1000_set_filter,
.flow_ctrl = dwmac1000_flow_ctrl,
.pmt = dwmac1000_pmt,
.set_umac_addr = dwmac1000_set_umac_addr,
.get_umac_addr = dwmac1000_get_umac_addr,
+ .set_eee_mode = dwmac1000_set_eee_mode,
+ .reset_eee_mode = dwmac1000_reset_eee_mode,
+ .set_eee_timer = dwmac1000_set_eee_timer,
+ .set_eee_pls = dwmac1000_set_eee_pls,
};
struct mac_device_info *dwmac1000_setup(void __iomem *ioaddr)
{
struct mac_device_info *mac;
u32 hwid = readl(ioaddr + GMAC_VERSION);
mac = kzalloc(sizeof(const struct mac_device_info), GFP_KERNEL);
if (!mac)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
index 19e0f4e..f83210e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
@@ -66,21 +66,21 @@ static void dwmac100_dump_mac_regs(void __iomem *ioaddr)
pr_info("\tVLAN2 tag (offset 0x%x): 0x%08x\n", MAC_VLAN2,
readl(ioaddr + MAC_VLAN2));
}
static int dwmac100_rx_ipc_enable(void __iomem *ioaddr)
{
return 0;
}
-static void dwmac100_irq_status(void __iomem *ioaddr)
+static int dwmac100_irq_status(void __iomem *ioaddr)
{
- return;
+ return 0;
}
static void dwmac100_set_umac_addr(void __iomem *ioaddr, unsigned char *addr,
unsigned int reg_n)
{
stmmac_set_mac_addr(ioaddr, addr, MAC_ADDR_HIGH, MAC_ADDR_LOW);
}
static void dwmac100_get_umac_addr(void __iomem *ioaddr, unsigned char *addr,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
index 6e0360f..e678ce3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
@@ -64,18 +64,19 @@
#define DMA_INTR_ENA_TSE 0x00000002 /* Transmit Stopped */
#define DMA_INTR_ABNORMAL (DMA_INTR_ENA_AIE | DMA_INTR_ENA_FBE | \
DMA_INTR_ENA_UNE)
/* DMA default interrupt mask */
#define DMA_INTR_DEFAULT_MASK (DMA_INTR_NORMAL | DMA_INTR_ABNORMAL)
/* DMA Status register defines */
+#define DMA_STATUS_GLPII 0x40000000 /* GMAC LPI interrupt */
#define DMA_STATUS_GPI 0x10000000 /* PMT interrupt */
#define DMA_STATUS_GMI 0x08000000 /* MMC interrupt */
#define DMA_STATUS_GLI 0x04000000 /* GMAC Line interface int */
#define DMA_STATUS_GMI 0x08000000
#define DMA_STATUS_GLI 0x04000000
#define DMA_STATUS_EB_MASK 0x00380000 /* Error Bits Mask */
#define DMA_STATUS_EB_TX_ABORT 0x00080000 /* Error Bits - TX Abort */
#define DMA_STATUS_EB_RX_ABORT 0x00100000 /* Error Bits - RX Abort */
#define DMA_STATUS_TS_MASK 0x00700000 /* Transmit Process State */
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index dc20c56..ab4c376 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -81,35 +81,43 @@ struct stmmac_priv {
struct plat_stmmacenet_data *plat;
struct stmmac_counters mmc;
struct dma_features dma_cap;
int hw_cap_support;
#ifdef CONFIG_HAVE_CLK
struct clk *stmmac_clk;
#endif
int clk_csr;
int synopsys_id;
+ struct timer_list eee_ctrl_timer;
+ bool tx_path_in_lpi_mode;
+ int lpi_irq;
+ int eee_enabled;
+ int eee_active;
+ int tx_lpi_timer;
};
extern int phyaddr;
extern int stmmac_mdio_unregister(struct net_device *ndev);
extern int stmmac_mdio_register(struct net_device *ndev);
extern void stmmac_set_ethtool_ops(struct net_device *netdev);
extern const struct stmmac_desc_ops enh_desc_ops;
extern const struct stmmac_desc_ops ndesc_ops;
int stmmac_freeze(struct net_device *ndev);
int stmmac_restore(struct net_device *ndev);
int stmmac_resume(struct net_device *ndev);
int stmmac_suspend(struct net_device *ndev);
int stmmac_dvr_remove(struct net_device *ndev);
struct stmmac_priv *stmmac_dvr_probe(struct device *device,
struct plat_stmmacenet_data *plat_dat,
void __iomem *addr);
+void stmmac_disable_eee_mode(struct stmmac_priv *priv);
+bool stmmac_eee_init(struct stmmac_priv *priv);
#ifdef CONFIG_HAVE_CLK
static inline int stmmac_clk_enable(struct stmmac_priv *priv)
{
if (!IS_ERR(priv->stmmac_clk))
return clk_prepare_enable(priv->stmmac_clk);
return 0;
}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index ce43184..76fd61a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -87,18 +87,28 @@ static const struct stmmac_stats stmmac_gstrings_stats[] = {
STMMAC_STAT(tx_early_irq),
STMMAC_STAT(fatal_bus_error_irq),
/* Extra info */
STMMAC_STAT(threshold),
STMMAC_STAT(tx_pkt_n),
STMMAC_STAT(rx_pkt_n),
STMMAC_STAT(poll_n),
STMMAC_STAT(sched_timer_n),
STMMAC_STAT(normal_irq_n),
+ STMMAC_STAT(normal_irq_n),
+ STMMAC_STAT(mmc_tx_irq_n),
+ STMMAC_STAT(mmc_rx_irq_n),
+ STMMAC_STAT(mmc_rx_csum_offload_irq_n),
+ STMMAC_STAT(irq_receive_pmt_irq_n),
+ STMMAC_STAT(irq_tx_path_in_lpi_mode_n),
+ STMMAC_STAT(irq_tx_path_exit_lpi_mode_n),
+ STMMAC_STAT(irq_rx_path_in_lpi_mode_n),
+ STMMAC_STAT(irq_rx_path_exit_lpi_mode_n),
+ STMMAC_STAT(phy_eee_wakeup_error_n),
};
#define STMMAC_STATS_LEN ARRAY_SIZE(stmmac_gstrings_stats)
/* HW MAC Management counters (if supported) */
#define STMMAC_MMC_STAT(m) \
{ #m, FIELD_SIZEOF(struct stmmac_counters, m), \
offsetof(struct stmmac_priv, mmc.m)}
static const struct stmmac_stats stmmac_mmc[] = {
@@ -360,18 +370,23 @@ static void stmmac_get_ethtool_stats(struct net_device *dev,
for (i = 0; i < STMMAC_MMC_STATS_LEN; i++) {
char *p;
p = (char *)priv + stmmac_mmc[i].stat_offset;
data[j++] = (stmmac_mmc[i].sizeof_stat ==
sizeof(u64)) ? (*(u64 *)p) :
(*(u32 *)p);
}
}
+ if (priv->eee_enabled) {
+ int val = phy_get_eee_err(priv->phydev);
+ if (val)
+ priv->xstats.phy_eee_wakeup_error_n = val;
+ }
}
for (i = 0; i < STMMAC_STATS_LEN; i++) {
char *p = (char *)priv + stmmac_gstrings_stats[i].stat_offset;
data[j++] = (stmmac_gstrings_stats[i].sizeof_stat ==
sizeof(u64)) ? (*(u64 *)p) : (*(u32 *)p);
}
}
static int stmmac_get_sset_count(struct net_device *netdev, int sset)
@@ -458,33 +473,75 @@ static int stmmac_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
}
spin_lock_irq(&priv->lock);
priv->wolopts = wol->wolopts;
spin_unlock_irq(&priv->lock);
return 0;
}
+static int stmmac_ethtool_op_get_eee(struct net_device *dev,
+ struct ethtool_eee *edata)
+{
+ struct stmmac_priv *priv = netdev_priv(dev);
+
+ if (!priv->dma_cap.eee)
+ return -EOPNOTSUPP;
+
+ edata->eee_enabled = priv->eee_enabled;
+ edata->eee_active = priv->eee_active;
+ edata->tx_lpi_timer = priv->tx_lpi_timer;
+
+ return phy_ethtool_get_eee(priv->phydev, edata);
+}
+
+static int stmmac_ethtool_op_set_eee(struct net_device *dev,
+ struct ethtool_eee *edata)
+{
+ struct stmmac_priv *priv = netdev_priv(dev);
+
+ priv->eee_enabled = edata->eee_enabled;
+
+ if (!priv->eee_enabled)
+ stmmac_disable_eee_mode(priv);
+ else {
+ /* We are asking for enabling the EEE but it is safe
+ * to verify all by invoking the eee_init function.
+ * In case of failure it will return an error.
+ */
+ priv->eee_enabled = stmmac_eee_init(priv);
+ if (!priv->eee_enabled)
+ return -EOPNOTSUPP;
+
+ /* Do not change tx_lpi_timer in case of failure */
+ priv->tx_lpi_timer = edata->tx_lpi_timer;
+ }
+
+ return phy_ethtool_set_eee(priv->phydev, edata);
+}
+
static const struct ethtool_ops stmmac_ethtool_ops = {
.begin = stmmac_check_if_running,
.get_drvinfo = stmmac_ethtool_getdrvinfo,
.get_settings = stmmac_ethtool_getsettings,
.set_settings = stmmac_ethtool_setsettings,
.get_msglevel = stmmac_ethtool_getmsglevel,
.set_msglevel = stmmac_ethtool_setmsglevel,
.get_regs = stmmac_ethtool_gregs,
.get_regs_len = stmmac_ethtool_get_regs_len,
.get_link = ethtool_op_get_link,
.get_pauseparam = stmmac_get_pauseparam,
.set_pauseparam = stmmac_set_pauseparam,
.get_ethtool_stats = stmmac_get_ethtool_stats,
.get_strings = stmmac_get_strings,
.get_wol = stmmac_get_wol,
.set_wol = stmmac_set_wol,
+ .get_eee = stmmac_ethtool_op_get_eee,
+ .set_eee = stmmac_ethtool_op_set_eee,
.get_sset_count = stmmac_get_sset_count,
.get_ts_info = ethtool_op_get_ts_info,
};
void stmmac_set_ethtool_ops(struct net_device *netdev)
{
SET_ETHTOOL_OPS(netdev, &stmmac_ethtool_ops);
}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index eba49cb..ea3bc09 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -127,18 +127,24 @@ MODULE_PARM_DESC(tmrate, "External timer freq. (default: 256Hz)");
#define DMA_BUFFER_SIZE BUF_SIZE_2KiB
static int buf_sz = DMA_BUFFER_SIZE;
module_param(buf_sz, int, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(buf_sz, "DMA buffer size");
static const u32 default_msg_level = (NETIF_MSG_DRV | NETIF_MSG_PROBE |
NETIF_MSG_LINK | NETIF_MSG_IFUP |
NETIF_MSG_IFDOWN | NETIF_MSG_TIMER);
+#define STMMAC_DEFAULT_LPI_TIMER 1000
+static int eee_timer = STMMAC_DEFAULT_LPI_TIMER;
+module_param(eee_timer, int, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(eee_timer, "LPI tx expiration time in msec");
+#define STMMAC_LPI_TIMER(x) (jiffies + msecs_to_jiffies(x))
+
static irqreturn_t stmmac_interrupt(int irq, void *dev_id);
#ifdef CONFIG_STMMAC_DEBUG_FS
static int stmmac_init_fs(struct net_device *dev);
static void stmmac_exit_fs(void);
#endif
/**
* stmmac_verify_args - verify the driver parameters.
@@ -155,18 +161,20 @@ static void stmmac_verify_args(void)
dma_txsize = DMA_TX_SIZE;
if (unlikely((buf_sz < DMA_BUFFER_SIZE) || (buf_sz > BUF_SIZE_16KiB)))
buf_sz = DMA_BUFFER_SIZE;
if (unlikely(flow_ctrl > 1))
flow_ctrl = FLOW_AUTO;
else if (likely(flow_ctrl < 0))
flow_ctrl = FLOW_OFF;
if (unlikely((pause < 0) || (pause > 0xffff)))
pause = PAUSE_TIME;
+ if (eee_timer < 0)
+ eee_timer = STMMAC_DEFAULT_LPI_TIMER;
}
static void stmmac_clk_csr_set(struct stmmac_priv *priv)
{
#ifdef CONFIG_HAVE_CLK
u32 clk_rate;
if (IS_ERR(priv->stmmac_clk))
return;
@@ -223,18 +231,97 @@ static inline u32 stmmac_tx_avail(struct stmmac_priv *priv)
static inline void stmmac_hw_fix_mac_speed(struct stmmac_priv *priv)
{
struct phy_device *phydev = priv->phydev;
if (likely(priv->plat->fix_mac_speed))
priv->plat->fix_mac_speed(priv->plat->bsp_priv,
phydev->speed);
}
+static void stmmac_enable_eee_mode(struct stmmac_priv *priv)
+{
+ /* Check and enter in LPI mode */
+ if ((priv->dirty_tx == priv->cur_tx) &&
+ (priv->tx_path_in_lpi_mode == false))
+ priv->hw->mac->set_eee_mode(priv->ioaddr);
+}
+
+void stmmac_disable_eee_mode(struct stmmac_priv *priv)
+{
+ /* Exit and disable EEE in case of we are are in LPI state. */
+ priv->hw->mac->reset_eee_mode(priv->ioaddr);
+ del_timer_sync(&priv->eee_ctrl_timer);
+ priv->tx_path_in_lpi_mode = false;
+}
+
+/**
+ * stmmac_eee_ctrl_timer
+ * @arg : data hook
+ * Description:
+ * If there is no data transfer and if we are not in LPI state,
+ * then MAC Transmitter can be moved to LPI state.
+ */
+static void stmmac_eee_ctrl_timer(unsigned long arg)
+{
+ struct stmmac_priv *priv = (struct stmmac_priv *)arg;
+
+ stmmac_enable_eee_mode(priv);
+ mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_TIMER(eee_timer));
+}
+
+/**
+ * stmmac_eee_init
+ * @priv: private device pointer
+ * Description:
+ * If the EEE support has been enabled while configuring the driver,
+ * if the GMAC actually supports the EEE (from the HW cap reg) and the
+ * phy can also manage EEE, so enable the LPI state and start the timer
+ * to verify if the tx path can enter in LPI state.
+ */
+bool stmmac_eee_init(struct stmmac_priv *priv)
+{
+ bool ret = false;
+
+ /* MAC core supports the EEE feature. */
+ if (priv->dma_cap.eee) {
+ /* Check if the PHY supports EEE */
+ if (phy_init_eee(priv->phydev, 1))
+ goto out;
+
+ priv->eee_active = 1;
+ init_timer(&priv->eee_ctrl_timer);
+ priv->eee_ctrl_timer.function = stmmac_eee_ctrl_timer;
+ priv->eee_ctrl_timer.data = (unsigned long)priv;
+ priv->eee_ctrl_timer.expires = STMMAC_LPI_TIMER(eee_timer);
+ add_timer(&priv->eee_ctrl_timer);
+
+ priv->hw->mac->set_eee_timer(priv->ioaddr,
+ STMMAC_DEFAULT_LIT_LS_TIMER,
+ priv->tx_lpi_timer);
+
+ pr_info("stmmac: Energy-Efficient Ethernet initialized\n");
+
+ ret = true;
+ }
+out:
+ return ret;
+}
+
+static void stmmac_eee_adjust(struct stmmac_priv *priv)
+{
+ /* When the EEE has been already initialised we have to
+ * modify the PLS bit in the LPI ctrl & status reg according
+ * to the PHY link status. For this reason.
+ */
+ if (priv->eee_enabled)
+ priv->hw->mac->set_eee_pls(priv->ioaddr, priv->phydev->link);
+}
+
/**
* stmmac_adjust_link
* @dev: net device structure
* Description: it adjusts the link parameters.
*/
static void stmmac_adjust_link(struct net_device *dev)
{
struct stmmac_priv *priv = netdev_priv(dev);
struct phy_device *phydev = priv->phydev;
@@ -243,18 +330,19 @@ static void stmmac_adjust_link(struct net_device *dev)
unsigned int fc = priv->flow_ctrl, pause_time = priv->pause;
if (phydev == NULL)
return;
DBG(probe, DEBUG, "stmmac_adjust_link: called. address %d link %d\n",
phydev->addr, phydev->link);
spin_lock_irqsave(&priv->lock, flags);
+
if (phydev->link) {
u32 ctrl = readl(priv->ioaddr + MAC_CTRL_REG);
/* Now we make sure that we can be in full duplex mode.
* If not, we operate in half-duplex mode. */
if (phydev->duplex != priv->oldduplex) {
new_state = 1;
if (!(phydev->duplex))
ctrl &= ~priv->hw->link.duplex;
@@ -309,54 +397,57 @@ static void stmmac_adjust_link(struct net_device *dev)
new_state = 1;
priv->oldlink = 0;
priv->speed = 0;
priv->oldduplex = -1;
}
if (new_state && netif_msg_link(priv))
phy_print_status(phydev);
+ stmmac_eee_adjust(priv);
+
spin_unlock_irqrestore(&priv->lock, flags);
DBG(probe, DEBUG, "stmmac_adjust_link: exiting\n");
}
/**
* stmmac_init_phy - PHY initialization
* @dev: net device structure
* Description: it initializes the driver's PHY state, and attaches the PHY
* to the mac driver.
* Return value:
* 0 on success
*/
static int stmmac_init_phy(struct net_device *dev)
{
struct stmmac_priv *priv = netdev_priv(dev);
struct phy_device *phydev;
- char phy_id[MII_BUS_ID_SIZE + 3];
+ char phy_id_fmt[MII_BUS_ID_SIZE + 3];
char bus_id[MII_BUS_ID_SIZE];
int interface = priv->plat->interface;
priv->oldlink = 0;
priv->speed = 0;
priv->oldduplex = -1;
if (priv->plat->phy_bus_name)
snprintf(bus_id, MII_BUS_ID_SIZE, "%s-%x",
priv->plat->phy_bus_name, priv->plat->bus_id);
else
snprintf(bus_id, MII_BUS_ID_SIZE, "stmmac-%x",
priv->plat->bus_id);
- snprintf(phy_id, MII_BUS_ID_SIZE + 3, PHY_ID_FMT, bus_id,
+ snprintf(phy_id_fmt, MII_BUS_ID_SIZE + 3, PHY_ID_FMT, bus_id,
priv->plat->phy_addr);
- pr_debug("stmmac_init_phy: trying to attach to %s\n", phy_id);
+ pr_debug("stmmac_init_phy: trying to attach to %s\n", phy_id_fmt);
- phydev = phy_connect(dev, phy_id, &stmmac_adjust_link, 0, interface);
+ phydev = phy_connect(dev, phy_id_fmt, &stmmac_adjust_link, 0,
+ interface);
if (IS_ERR(phydev)) {
pr_err("%s: Could not attach to PHY\n", dev->name);
return PTR_ERR(phydev);
}
/* Stop Advertising 1000BASE Capability if interface is not GMII */
if ((interface == PHY_INTERFACE_MODE_MII) ||
(interface == PHY_INTERFACE_MODE_RMII))
@@ -683,18 +774,23 @@ static void stmmac_tx(struct stmmac_priv *priv)
stmmac_tx_avail(priv) > STMMAC_TX_THRESH(priv))) {
netif_tx_lock(priv->dev);
if (netif_queue_stopped(priv->dev) &&
stmmac_tx_avail(priv) > STMMAC_TX_THRESH(priv)) {
TX_DBG("%s: restart transmit\n", __func__);
netif_wake_queue(priv->dev);
}
netif_tx_unlock(priv->dev);
}
+
+ if ((priv->eee_enabled) && (!priv->tx_path_in_lpi_mode)) {
+ stmmac_enable_eee_mode(priv);
+ mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_TIMER(eee_timer));
+ }
spin_unlock(&priv->tx_lock);
}
static inline void stmmac_enable_irq(struct stmmac_priv *priv)
{
#ifdef CONFIG_STMMAC_TIMER
if (likely(priv->tm->enable))
priv->tm->timer_start(tmrate);
else
@@ -1021,18 +1117,29 @@ static int stmmac_open(struct net_device *dev)
ret = request_irq(priv->wol_irq, stmmac_interrupt,
IRQF_SHARED, dev->name, dev);
if (unlikely(ret < 0)) {
pr_err("%s: ERROR: allocating the ext WoL IRQ %d "
"(error: %d)\n", __func__, priv->wol_irq, ret);
goto open_error_wolirq;
}
}
+ /* Request the IRQ lines */
+ if (priv->lpi_irq != -ENXIO) {
+ ret = request_irq(priv->lpi_irq, stmmac_interrupt, IRQF_SHARED,
+ dev->name, dev);
+ if (unlikely(ret < 0)) {
+ pr_err("%s: ERROR: allocating the LPI IRQ %d (%d)\n",
+ __func__, priv->lpi_irq, ret);
+ goto open_error_lpiirq;
+ }
+ }
+
/* Enable the MAC Rx/Tx */
stmmac_set_mac(priv->ioaddr, true);
/* Set the HW DMA mode and the COE */
stmmac_dma_operation_mode(priv);
/* Extra statistics */
memset(&priv->xstats, 0, sizeof(struct stmmac_extra_stats));
priv->xstats.threshold = tc;
@@ -1056,24 +1163,31 @@ static int stmmac_open(struct net_device *dev)
/* Dump DMA/MAC registers */
if (netif_msg_hw(priv)) {
priv->hw->mac->dump_regs(priv->ioaddr);
priv->hw->dma->dump_regs(priv->ioaddr);
}
if (priv->phydev)
phy_start(priv->phydev);
+ priv->tx_lpi_timer = STMMAC_DEFAULT_TWT_LS_TIMER;
+ priv->eee_enabled = stmmac_eee_init(priv);
+
napi_enable(&priv->napi);
skb_queue_head_init(&priv->rx_recycle);
netif_start_queue(dev);
return 0;
+open_error_lpiirq:
+ if (priv->wol_irq != dev->irq)
+ free_irq(priv->wol_irq, dev);
+
open_error_wolirq:
free_irq(dev->irq, dev);
open_error:
#ifdef CONFIG_STMMAC_TIMER
kfree(priv->tm);
#endif
if (priv->phydev)
phy_disconnect(priv->phydev);
@@ -1087,18 +1201,21 @@ open_error:
* stmmac_release - close entry point of the driver
* @dev : device pointer.
* Description:
* This is the stop entry point of the driver.
*/
static int stmmac_release(struct net_device *dev)
{
struct stmmac_priv *priv = netdev_priv(dev);
+ if (priv->eee_enabled)
+ del_timer_sync(&priv->eee_ctrl_timer);
+
/* Stop and disconnect the PHY */
if (priv->phydev) {
phy_stop(priv->phydev);
phy_disconnect(priv->phydev);
priv->phydev = NULL;
}
netif_stop_queue(dev);
@@ -1109,18 +1226,20 @@ static int stmmac_release(struct net_device *dev)
kfree(priv->tm);
#endif
napi_disable(&priv->napi);
skb_queue_purge(&priv->rx_recycle);
/* Free the IRQ lines */
free_irq(dev->irq, dev);
if (priv->wol_irq != dev->irq)
free_irq(priv->wol_irq, dev);
+ if (priv->lpi_irq != -ENXIO)
+ free_irq(priv->lpi_irq, dev);
/* Stop TX/RX DMA and clear the descriptors */
priv->hw->dma->stop_tx(priv->ioaddr);
priv->hw->dma->stop_rx(priv->ioaddr);
/* Release and free the Rx/Tx resources */
free_dma_desc_resources(priv);
/* Disable the MAC Rx/Tx */
@@ -1158,18 +1277,21 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
/* This is a hard error, log it. */
pr_err("%s: BUG! Tx Ring full when queue awake\n",
__func__);
}
return NETDEV_TX_BUSY;
}
spin_lock(&priv->tx_lock);
+ if (priv->tx_path_in_lpi_mode)
+ stmmac_disable_eee_mode(priv);
+
entry = priv->cur_tx % txsize;
#ifdef STMMAC_XMIT_DEBUG
if ((skb->len > ETH_FRAME_LEN) || nfrags)
pr_info("stmmac xmit:\n"
"\tskb addr %p - len: %d - nopaged_len: %d\n"
"\tn_frags: %d - ip_summed: %d - %s gso\n",
skb, skb->len, nopaged_len, nfrags, skb->ip_summed,
!skb_is_gso(skb) ? "isn't" : "is");
@@ -1534,22 +1656,49 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id)
{
struct net_device *dev = (struct net_device *)dev_id;
struct stmmac_priv *priv = netdev_priv(dev);
if (unlikely(!dev)) {
pr_err("%s: invalid dev pointer\n", __func__);
return IRQ_NONE;
}
- if (priv->plat->has_gmac)
- /* To handle GMAC own interrupts */
- priv->hw->mac->host_irq_status((void __iomem *) dev->base_addr);
+ /* To handle GMAC own interrupts */
+ if (priv->plat->has_gmac) {
+ int status = priv->hw->mac->host_irq_status((void __iomem *)
+ dev->base_addr);
+ if (unlikely(status)) {
+ if (status & core_mmc_tx_irq)
+ priv->xstats.mmc_tx_irq_n++;
+ if (status & core_mmc_rx_irq)
+ priv->xstats.mmc_rx_irq_n++;
+ if (status & core_mmc_rx_csum_offload_irq)
+ priv->xstats.mmc_rx_csum_offload_irq_n++;
+ if (status & core_irq_receive_pmt_irq)
+ priv->xstats.irq_receive_pmt_irq_n++;
+
+ /* For LPI we need to save the tx status */
+ if (status & core_irq_tx_path_in_lpi_mode) {
+ priv->xstats.irq_tx_path_in_lpi_mode_n++;
+ priv->tx_path_in_lpi_mode = true;
+ }
+ if (status & core_irq_tx_path_exit_lpi_mode) {
+ priv->xstats.irq_tx_path_exit_lpi_mode_n++;
+ priv->tx_path_in_lpi_mode = false;
+ }
+ if (status & core_irq_rx_path_in_lpi_mode)
+ priv->xstats.irq_rx_path_in_lpi_mode_n++;
+ if (status & core_irq_rx_path_exit_lpi_mode)
+ priv->xstats.irq_rx_path_exit_lpi_mode_n++;
+ }
+ }
+ /* To handle DMA interrupts */
stmmac_dma_interrupt(priv);
return IRQ_HANDLED;
}
#ifdef CONFIG_NET_POLL_CONTROLLER
/* Polling receive - used by NETCONSOLE and other diagnostic tools
* to allow network I/O with interrupts disabled. */
static void stmmac_poll_controller(struct net_device *dev)
@@ -2149,18 +2298,21 @@ static int __init stmmac_cmdline_opt(char *str)
} else if (!strncmp(opt, "watchdog:", 9)) {
if (kstrtoint(opt + 9, 0, &watchdog))
goto err;
} else if (!strncmp(opt, "flow_ctrl:", 10)) {
if (kstrtoint(opt + 10, 0, &flow_ctrl))
goto err;
} else if (!strncmp(opt, "pause:", 6)) {
if (kstrtoint(opt + 6, 0, &pause))
goto err;
+ } else if (!strncmp(opt, "eee_timer:", 6)) {
+ if (kstrtoint(opt + 10, 0, &eee_timer))
+ goto err;
#ifdef CONFIG_STMMAC_TIMER
} else if (!strncmp(opt, "tmrate:", 7)) {
if (kstrtoint(opt + 7, 0, &tmrate))
goto err;
#endif
}
}
return 0;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 20eb502..7d36163 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -150,18 +150,20 @@ static int stmmac_pltfr_probe(struct platform_device *pdev)
* named as "eth_wake_irq"
*
* In case the wake up interrupt is not passed from the platform
* so the driver will continue to use the mac irq (ndev->irq)
*/
priv->wol_irq = platform_get_irq_byname(pdev, "eth_wake_irq");
if (priv->wol_irq == -ENXIO)
priv->wol_irq = priv->dev->irq;
+ priv->lpi_irq = platform_get_irq_byname(pdev, "eth_lpi");
+
platform_set_drvdata(pdev, priv->dev);
pr_debug("STMMAC platform driver registration completed");
return 0;
out_unmap:
iounmap(addr);
platform_set_drvdata(pdev, NULL);
--
1.7.10
^ permalink raw reply related
* Re: New commands to configure IOV features
From: Yuval Mintz @ 2012-07-01 11:09 UTC (permalink / raw)
To: linux-pci; +Cc: Greg Rose, Ben Hutchings, netdev@vger.kernel.org
In-Reply-To: <20120626101903.0000791c@unknown>
>>>> I've tried to figure out if there was a standard interface
>>>> (ethtool/iproute) through which a user could configure the number
>>>> of vfs in his system.
>>>>
>>>> I've seen the RFC suggested in
>>>> http://markmail.org/thread/qblfcv7zbxsxp7q6, and
>>>> http://markmail.org/thread/fw54dcppmxuxoe6n, but failed to see any
>>>> later references to it (commits or further discussion on this
>>>> topic).
>>>>
>>>> How exactly are things standing with these RFCs? Were they
>>>> abandoned?
>>>
>>> The only way to configure the number of VFs continues to be through
>>> the max_vfs module parameter. I've got a patch to do it through
>>> ethtool sitting on the back burner but due to other requirements of
>>> my day job I've not been able to work on it since last fall.
>>>
>>> - Greg
>>
>>
>> Hi Ben,
>>
>> If I want to pick the RFCs and add support for configuring the number
>> of VFs - do you think ethtool's the right place for such added
>> support?
>>
>> I'm asking since as far as I can see, ethtool (today) doesn't contain
>> any features related to virtual functions.
>
> I think a PCI utility tool would be better, SR-IOV is not limited to
> network devices. That's one of the reasons I dropped the RFC. I
> haven't gotten back to the idea since then due to my day job keeping me
> pretty busy.
>
> - Greg
I'm adding the linux-pci guys, since they (obviously) are the experts in
these topics.
Is there any PCI utility (or at least an existing kernel API) which is
suitable for adding this sort of functionality?
Thanks,
Yuval
^ permalink raw reply
* Re: [net-next.git 0/4] EEE for PAL and stmmac (V7)
From: David Miller @ 2012-07-01 10:37 UTC (permalink / raw)
To: peppe.cavallaro; +Cc: netdev, eric.dumazet, rayagond, yuvalmin, bhutchings
In-Reply-To: <1340867678-18375-1-git-send-email-peppe.cavallaro@st.com>
From: Giuseppe CAVALLARO <peppe.cavallaro@st.com>
Date: Thu, 28 Jun 2012 09:14:34 +0200
> Giuseppe Cavallaro (4):
> stmmac: do not use strict_strtoul but kstrtoint
> stmmac: update the driver Documentation and add EEE
> stmmac: add the Energy Efficient Ethernet support
> phy: add the EEE support and the way to access to the MMD registers.
Series applied, thanks.
^ permalink raw reply
* Re: [PATCH v5] bonding support for IPv6 transmit hashing
From: David Miller @ 2012-07-01 10:33 UTC (permalink / raw)
To: linux; +Cc: netdev
In-Reply-To: <c390ff662ede0f304398a88ca1a96e3773065c60.1341129744.git.linux@8192.net>
From: John Eaglesham <linux@8192.net>
Date: Sun, 1 Jul 2012 01:07:43 -0700
> + v6hash =
> + (ipv6h->saddr.s6_addr32[1] ^ ipv6h->daddr.s6_addr32[1]) ^
> + (ipv6h->saddr.s6_addr32[2] ^ ipv6h->daddr.s6_addr32[2]) ^
> + (ipv6h->saddr.s6_addr32[3] ^ ipv6h->daddr.s6_addr32[3]);
You completely ignored my feedback:
This is rediculous, just put &ipv6h->saddr into a local
pointer named 's' and then you won't have use such gymnastics
to indent the code.
^ permalink raw reply
* Re: [PATCH net-next 03/10] net/mlx4_en: Re-design multicast attachments flow
From: David Miller @ 2012-07-01 10:32 UTC (permalink / raw)
To: ogerlitz; +Cc: roland, yevgenyp, oren, netdev, yevgenyp, sbohrer, hadarh
In-Reply-To: <1341135823-29039-4-git-send-email-ogerlitz@mellanox.com>
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Sun, 1 Jul 2012 12:43:36 +0300
> + /* Find all the entries that should be removed from dst,
> + * These are the entries that are not found in src */
Improperly formatted comment.
> + new_mc = kmalloc(sizeof(struct mlx4_en_mc_list),
> + GFP_KERNEL);
Improperly indented second line.
^ permalink raw reply
* Re: [PATCH net-next 06/10] {NET,IB}/mlx4: Add device managed flow steering firmware API
From: David Miller @ 2012-07-01 10:30 UTC (permalink / raw)
To: ogerlitz; +Cc: roland, yevgenyp, oren, netdev, hadarh
In-Reply-To: <1341135823-29039-7-git-send-email-ogerlitz@mellanox.com>
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Sun, 1 Jul 2012 12:43:39 +0300
> + /* Enable Ethernet flow steering
> + * with udp unicast and tcp unicast */
Improperly formatted comment, do it like this:
/* Enable Ethernet flow steering
* with udp unicast and tcp unicast
*/
> + /* Enable IPoIB flow steering
> + * with udp unicast and tcp unicast */
Likewise.
> @@ -136,6 +138,11 @@ module_param_array(port_type_array, int, &arr_argc, 0444);
> MODULE_PARM_DESC(port_type_array, "Array of port types: HW_DEFAULT (0) is default "
> "1 for IB, 2 for Ethernet");
>
> +static int mlx4_flow_steering_hash;
> +module_param_named(flow_steering_hash, mlx4_flow_steering_hash, int, 0444);
> +MODULE_PARM_DESC(flow_steering_hash,
> + "Flow steering hash function configuration. Config options: L2 = 0, L2_L3_L4 = 1 (default: L2).");
> +
No module paramters, do it via ethtool or similar.
> + if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER &&
> + dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER) {
> + dev->caps.steering_mode = MLX4_STEERING_MODE_B0;
> +
> + } else {
Get rid of that pointless empty line
> +
> + dev->caps.steering_mode = MLX4_STEERING_MODE_A0;
Likewise.
> + /* Enable flow steering with
> + udp unicast and tcp unicast*/
Comment formatting.
> +static void trans_rule_ctrl_to_hw(struct mlx4_net_trans_rule *ctrl,
> + struct mlx4_net_trans_rule_hw_ctrl *hw)
Second line improperly indented.
> + memcpy(rule_hw->eth.dst_mac_msk, spec->eth.dst_mac_msk,
> + ETH_ALEN);
Don't make us barf, other people have to read this stuff. This looks
terrible, indent it properly.
> + memcpy(rule_hw->eth.src_mac_msk, spec->eth.src_mac_msk,
> + ETH_ALEN);
Likewise.
> + mlx4_err(dev, "Fail to detach network rule. registration id = 0x%llx\n"
> + , reg_id);
Please format this properly.
^ permalink raw reply
* Re: [PATCH net-next 09/10] net/mlx4_en: Manage flow steering rules with ethtool
From: David Miller @ 2012-07-01 10:23 UTC (permalink / raw)
To: ogerlitz; +Cc: roland, yevgenyp, oren, netdev, hadarh
In-Reply-To: <1341135823-29039-10-git-send-email-ogerlitz@mellanox.com>
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Sun, 1 Jul 2012 12:43:42 +0300
> + en_err(priv, "Fail to detach network rule at location %d. registration id = 0x%llx\n"
> + , cmd->fs.location, rule->id);
Put that first comma at the end of the first line, this is very ugly.
^ permalink raw reply
* Re: [PATCH net-next 07/10] net/mlx4_core: Add resource tracking for device managed flow steering rules
From: David Miller @ 2012-07-01 10:22 UTC (permalink / raw)
To: ogerlitz; +Cc: roland, yevgenyp, oren, netdev, hadarh
In-Reply-To: <1341135823-29039-8-git-send-email-ogerlitz@mellanox.com>
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Sun, 1 Jul 2012 12:43:40 +0300
> + err = mlx4_cmd(dev, base, 0, 0,
> + MLX4_QP_FLOW_STEERING_DETACH,
> + MLX4_CMD_TIME_CLASS_A,
> + MLX4_CMD_NATIVE);
This is improperly formatted, line up the arguments with the first column
after the openning parenthesis on the first line.
^ permalink raw reply
* Re: [PATCH net-next 04/10] net/mlx4: Set steering mode according to device capabilities
From: David Miller @ 2012-07-01 10:20 UTC (permalink / raw)
To: ogerlitz; +Cc: roland, yevgenyp, oren, netdev, hadarh
In-Reply-To: <1341135823-29039-5-git-send-email-ogerlitz@mellanox.com>
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Sun, 1 Jul 2012 12:43:37 +0300
> + /* Add the default qp number as multicast
> + * promisc */
This is not the correct way to format a comment, do it:
/* Like
* this.
*/
> + if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER &&
> + dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER) {
> + dev->caps.steering_mode = MLX4_STEERING_MODE_B0;
> +
> + } else {
That empty line is extraneous and ugly, remove it.
> +/* Driver supports 2 diffrent device methods to manage traffic steering:
> + - B0 steering mode - Common low level API for ib and (if supported) eth.
> + - A0 steering mode - Limited low level API for eth. In case of IB,
> + B0 mode is in use.
> + */
Improperly formatted, do it like this:
/* Driver supports 2 diffrent device methods to manage traffic steering:
* - B0 steering mode - Common low level API for ib and (if supported) eth.
* - A0 steering mode - Limited low level API for eth. In case of IB,
* B0 mode is in use.
*/
^ permalink raw reply
* Re: [PATCH net-next 01/10] net/mlx4_core: Change resource tracking mechanism to use red-black tree
From: David Miller @ 2012-07-01 10:17 UTC (permalink / raw)
To: ogerlitz; +Cc: roland, yevgenyp, oren, netdev, hadarh
In-Reply-To: <1341135823-29039-2-git-send-email-ogerlitz@mellanox.com>
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Sun, 1 Jul 2012 12:43:34 +0300
> @@ -733,7 +776,7 @@ static int qp_res_start_move_to(struct mlx4_dev *dev, int slave, int qpn,
> int err = 0;
>
> spin_lock_irq(mlx4_tlock(dev));
> - r = radix_tree_lookup(&tracker->res_tree[RES_QP], qpn);
> + r = (struct res_qp *)res_tracker_lookup(&tracker->res_tree[RES_QP], qpn);
> if (!r)
> err = -ENOENT;
> else if (r->com.owner != slave)
Casts are terrible, return "void *" from res_tracker_lookup() just as
radix_tree_lookup() does.
Also you have indentation problems all over this patch. When you have
a multi-line function call the first non-whitespace character on the
second and subsequent lines should line up with the first column after
the openning parenthesis on the first line.
^ permalink raw reply
* [PATCH net-next 05/10] net/mlx4_core: Add firmware commands to support device managed flow steering
From: Or Gerlitz @ 2012-07-01 9:43 UTC (permalink / raw)
To: davem; +Cc: roland, yevgenyp, oren, netdev, Hadar Hen Zion, Or Gerlitz
In-Reply-To: <1341135823-29039-1-git-send-email-ogerlitz@mellanox.com>
From: Hadar Hen Zion <hadarh@mellanox.co.il>
Add support for firmware commands to attach/detach a new device managed
steering mode. Such network steering rules allow the user to provide an
L2/L3/L4 flow specification to the firmware and have the device to steer
traffic that matches that specification to the provided QP.
Signed-off-by: Hadar Hen Zion <hadarh@mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx4/cmd.c | 19 +++++++++++++
drivers/net/ethernet/mellanox/mlx4/mcg.c | 29 ++++++++++++++++++++
drivers/net/ethernet/mellanox/mlx4/mlx4.h | 10 +++++++
.../net/ethernet/mellanox/mlx4/resource_tracker.c | 24 ++++++++++++++++
include/linux/mlx4/cmd.h | 4 +++
5 files changed, 86 insertions(+), 0 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 842c8ce..7e94987 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -1080,6 +1080,25 @@ static struct mlx4_cmd_info cmd_info[] = {
.verify = NULL,
.wrapper = NULL
},
+ /* flow steering commands */
+ {
+ .opcode = MLX4_QP_FLOW_STEERING_ATTACH,
+ .has_inbox = true,
+ .has_outbox = false,
+ .out_is_imm = true,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_QP_FLOW_STEERING_ATTACH_wrapper
+ },
+ {
+ .opcode = MLX4_QP_FLOW_STEERING_DETACH,
+ .has_inbox = false,
+ .has_outbox = false,
+ .out_is_imm = false,
+ .encode_slave_id = false,
+ .verify = NULL,
+ .wrapper = mlx4_QP_FLOW_STEERING_DETACH_wrapper
+ },
};
static int mlx4_master_process_vhcr(struct mlx4_dev *dev, int slave,
diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c
index 319c9d4..3c59a33 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mcg.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c
@@ -62,6 +62,35 @@ int mlx4_get_qp_per_mgm(struct mlx4_dev *dev)
return 4 * (mlx4_get_mgm_entry_size(dev) / 16 - 2);
}
+static int mlx4_QP_FLOW_STEERING_ATTACH(struct mlx4_dev *dev,
+ struct mlx4_cmd_mailbox *mailbox,
+ u32 size,
+ u64 *reg_id)
+{
+ u64 imm;
+ int err = 0;
+
+ err = mlx4_cmd_imm(dev, mailbox->dma, &imm, size, 0,
+ MLX4_QP_FLOW_STEERING_ATTACH, MLX4_CMD_TIME_CLASS_A,
+ MLX4_CMD_NATIVE);
+ if (err)
+ return err;
+ *reg_id = imm;
+
+ return err;
+}
+
+static int mlx4_QP_FLOW_STEERING_DETACH(struct mlx4_dev *dev, u64 regid)
+{
+ int err = 0;
+
+ err = mlx4_cmd(dev, regid, 0, 0,
+ MLX4_QP_FLOW_STEERING_DETACH, MLX4_CMD_TIME_CLASS_A,
+ MLX4_CMD_NATIVE);
+
+ return err;
+}
+
static int mlx4_READ_ENTRY(struct mlx4_dev *dev, int index,
struct mlx4_cmd_mailbox *mailbox)
{
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index a425a98..c07e882 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -1118,6 +1118,16 @@ int mlx4_QUERY_IF_STAT_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_cmd_mailbox *inbox,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd);
+int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
+int mlx4_QP_FLOW_STEERING_DETACH_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd);
int mlx4_get_mgm_entry_size(struct mlx4_dev *dev);
int mlx4_get_qp_per_mgm(struct mlx4_dev *dev);
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index b8e8969..4301aa5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -2740,6 +2740,30 @@ ex_put:
return err;
}
+int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ return mlx4_cmd_imm(dev, inbox->dma, &vhcr->out_param,
+ vhcr->in_modifier, 0,
+ MLX4_QP_FLOW_STEERING_ATTACH,
+ MLX4_CMD_TIME_CLASS_A,
+ MLX4_CMD_NATIVE);
+}
+
+int mlx4_QP_FLOW_STEERING_DETACH_wrapper(struct mlx4_dev *dev, int slave,
+ struct mlx4_vhcr *vhcr,
+ struct mlx4_cmd_mailbox *inbox,
+ struct mlx4_cmd_mailbox *outbox,
+ struct mlx4_cmd_info *cmd)
+{
+ return mlx4_cmd(dev, vhcr->in_param, 0, 0,
+ MLX4_QP_FLOW_STEERING_DETACH, MLX4_CMD_TIME_CLASS_A,
+ MLX4_CMD_NATIVE);
+}
+
enum {
BUSY_MAX_RETRIES = 10
};
diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h
index 1f3860a..2606951 100644
--- a/include/linux/mlx4/cmd.h
+++ b/include/linux/mlx4/cmd.h
@@ -154,6 +154,10 @@ enum {
/* set port opcode modifiers */
MLX4_SET_PORT_PRIO2TC = 0x8,
MLX4_SET_PORT_SCHEDULER = 0x9,
+
+ /* register/delete flow steering network rules */
+ MLX4_QP_FLOW_STEERING_ATTACH = 0x65,
+ MLX4_QP_FLOW_STEERING_DETACH = 0x66,
};
enum {
--
1.7.1
^ permalink raw reply related
* [PATCH net-next 03/10] net/mlx4_en: Re-design multicast attachments flow
From: Or Gerlitz @ 2012-07-01 9:43 UTC (permalink / raw)
To: davem
Cc: roland, yevgenyp, oren, netdev, Yevgeny Petrilin, Shawn Bohrer,
Hadar Hen Zion
In-Reply-To: <1341135823-29039-1-git-send-email-ogerlitz@mellanox.com>
From: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Currently, for every change in the net device multicast list, the driver
detaches all the addresses from the HW device, and then attaches the
updated list. This behavior is wrong from two aspects: first, it causes
a load of firmware commands and second, there is period of time where
the correct addresses are not attached, which turned into packet loss.
To improve - a copy of the multicast list is saved by the driver. For
every change in the multicast list, the multicast list copy is used
to find the delta between those two lists and add or remove multicast
addresses as needed.
Reported-by: Shawn Bohrer <sbohrer@rgmadvisors.com>
Cc: Shawn Bohrer <sbohrer@rgmadvisors.com>
Signed-off-by: Hadar Hen Zion <hadarh@mellanox.co.il>
Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
---
drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 141 ++++++++++++++++++------
drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 16 +++-
2 files changed, 122 insertions(+), 35 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 073b85b..35c64f2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -170,33 +170,79 @@ static void mlx4_en_do_set_mac(struct work_struct *work)
static void mlx4_en_clear_list(struct net_device *dev)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
+ struct mlx4_en_mc_list *tmp, *mc_to_del;
- kfree(priv->mc_addrs);
- priv->mc_addrs = NULL;
- priv->mc_addrs_cnt = 0;
+ list_for_each_entry_safe(mc_to_del, tmp, &priv->mc_list, list) {
+ list_del(&mc_to_del->list);
+ kfree(mc_to_del);
+ }
}
static void mlx4_en_cache_mclist(struct net_device *dev)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
struct netdev_hw_addr *ha;
- char *mc_addrs;
- int mc_addrs_cnt = netdev_mc_count(dev);
- int i;
+ struct mlx4_en_mc_list *tmp;
- mc_addrs = kmalloc(mc_addrs_cnt * ETH_ALEN, GFP_ATOMIC);
- if (!mc_addrs) {
- en_err(priv, "failed to allocate multicast list\n");
- return;
- }
- i = 0;
- netdev_for_each_mc_addr(ha, dev)
- memcpy(mc_addrs + i++ * ETH_ALEN, ha->addr, ETH_ALEN);
mlx4_en_clear_list(dev);
- priv->mc_addrs = mc_addrs;
- priv->mc_addrs_cnt = mc_addrs_cnt;
+ netdev_for_each_mc_addr(ha, dev) {
+ tmp = kzalloc(sizeof(struct mlx4_en_mc_list), GFP_ATOMIC);
+ if (!tmp) {
+ en_err(priv, "failed to allocate multicast list\n");
+ mlx4_en_clear_list(dev);
+ return;
+ }
+ memcpy(tmp->addr, ha->addr, ETH_ALEN);
+ list_add_tail(&tmp->list, &priv->mc_list);
+ }
}
+static void update_mclist_flags(struct mlx4_en_priv *priv,
+ struct list_head *dst,
+ struct list_head *src)
+{
+ struct mlx4_en_mc_list *dst_tmp, *src_tmp, *new_mc;
+ bool found;
+
+ /* Find all the entries that should be removed from dst,
+ * These are the entries that are not found in src */
+ list_for_each_entry(dst_tmp, dst, list) {
+ found = false;
+ list_for_each_entry(src_tmp, src, list) {
+ if (!memcmp(dst_tmp->addr, src_tmp->addr, ETH_ALEN)) {
+ found = true;
+ break;
+ }
+ }
+ if (!found)
+ dst_tmp->action = MCLIST_REM;
+ }
+
+ /* Add entries that exist in src but not in dst
+ * mark them as need to add */
+ list_for_each_entry(src_tmp, src, list) {
+ found = false;
+ list_for_each_entry(dst_tmp, dst, list) {
+ if (!memcmp(dst_tmp->addr, src_tmp->addr, ETH_ALEN)) {
+ dst_tmp->action = MCLIST_NONE;
+ found = true;
+ break;
+ }
+ }
+ if (!found) {
+ new_mc = kmalloc(sizeof(struct mlx4_en_mc_list),
+ GFP_KERNEL);
+ if (!new_mc) {
+ en_err(priv, "Failed to allocate current multicast list\n");
+ return;
+ }
+ memcpy(new_mc, src_tmp,
+ sizeof(struct mlx4_en_mc_list));
+ new_mc->action = MCLIST_ADD;
+ list_add_tail(&new_mc->list, dst);
+ }
+ }
+}
static void mlx4_en_set_multicast(struct net_device *dev)
{
@@ -214,6 +260,7 @@ static void mlx4_en_do_set_multicast(struct work_struct *work)
mcast_task);
struct mlx4_en_dev *mdev = priv->mdev;
struct net_device *dev = priv->dev;
+ struct mlx4_en_mc_list *mclist, *tmp;
u64 mcast_addr = 0;
u8 mc_list[16] = {0};
int err;
@@ -336,7 +383,6 @@ static void mlx4_en_do_set_multicast(struct work_struct *work)
priv->flags |= MLX4_EN_FLAG_MC_PROMISC;
}
} else {
- int i;
/* Disable Multicast promisc */
if (priv->flags & MLX4_EN_FLAG_MC_PROMISC) {
err = mlx4_multicast_promisc_remove(mdev->dev, priv->base_qpn,
@@ -351,13 +397,6 @@ static void mlx4_en_do_set_multicast(struct work_struct *work)
if (err)
en_err(priv, "Failed disabling multicast filter\n");
- /* Detach our qp from all the multicast addresses */
- for (i = 0; i < priv->mc_addrs_cnt; i++) {
- memcpy(&mc_list[10], priv->mc_addrs + i * ETH_ALEN, ETH_ALEN);
- mc_list[5] = priv->port;
- mlx4_multicast_detach(mdev->dev, &priv->rss_map.indir_qp,
- mc_list, MLX4_PROT_ETH);
- }
/* Flush mcast filter and init it with broadcast address */
mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, ETH_BCAST,
1, MLX4_MCAST_CONFIG);
@@ -367,13 +406,8 @@ static void mlx4_en_do_set_multicast(struct work_struct *work)
netif_tx_lock_bh(dev);
mlx4_en_cache_mclist(dev);
netif_tx_unlock_bh(dev);
- for (i = 0; i < priv->mc_addrs_cnt; i++) {
- mcast_addr =
- mlx4_en_mac_to_u64(priv->mc_addrs + i * ETH_ALEN);
- memcpy(&mc_list[10], priv->mc_addrs + i * ETH_ALEN, ETH_ALEN);
- mc_list[5] = priv->port;
- mlx4_multicast_attach(mdev->dev, &priv->rss_map.indir_qp,
- mc_list, 0, MLX4_PROT_ETH);
+ list_for_each_entry(mclist, &priv->mc_list, list) {
+ mcast_addr = mlx4_en_mac_to_u64(mclist->addr);
mlx4_SET_MCAST_FLTR(mdev->dev, priv->port,
mcast_addr, 0, MLX4_MCAST_CONFIG);
}
@@ -381,6 +415,38 @@ static void mlx4_en_do_set_multicast(struct work_struct *work)
0, MLX4_MCAST_ENABLE);
if (err)
en_err(priv, "Failed enabling multicast filter\n");
+
+ update_mclist_flags(priv, &priv->curr_list, &priv->mc_list);
+ list_for_each_entry_safe(mclist, tmp, &priv->curr_list, list) {
+ if (mclist->action == MCLIST_REM) {
+ /* detach this address and delete from list */
+ memcpy(&mc_list[10], mclist->addr, ETH_ALEN);
+ mc_list[5] = priv->port;
+ err = mlx4_multicast_detach(mdev->dev,
+ &priv->rss_map.indir_qp,
+ mc_list,
+ MLX4_PROT_ETH);
+ if (err)
+ en_err(priv, "Fail to detach multicast address\n");
+
+ /* remove from list */
+ list_del(&mclist->list);
+ kfree(mclist);
+ }
+
+ if (mclist->action == MCLIST_ADD) {
+ /* attach the address */
+ memcpy(&mc_list[10], mclist->addr, ETH_ALEN);
+ mc_list[5] = priv->port;
+ err = mlx4_multicast_attach(mdev->dev,
+ &priv->rss_map.indir_qp,
+ mc_list, 0,
+ MLX4_PROT_ETH);
+ if (err)
+ en_err(priv, "Fail to attach multicast address\n");
+
+ }
+ }
}
out:
mutex_unlock(&mdev->state_lock);
@@ -605,6 +671,9 @@ int mlx4_en_start_port(struct net_device *dev)
return 0;
}
+ INIT_LIST_HEAD(&priv->mc_list);
+ INIT_LIST_HEAD(&priv->curr_list);
+
/* Calculate Rx buf size */
dev->mtu = min(dev->mtu, priv->max_mtu);
mlx4_en_calc_rx_buf(dev);
@@ -760,6 +829,7 @@ void mlx4_en_stop_port(struct net_device *dev)
{
struct mlx4_en_priv *priv = netdev_priv(dev);
struct mlx4_en_dev *mdev = priv->mdev;
+ struct mlx4_en_mc_list *mclist, *tmp;
int i;
u8 mc_list[16] = {0};
@@ -781,13 +851,18 @@ void mlx4_en_stop_port(struct net_device *dev)
mc_list[5] = priv->port;
mlx4_multicast_detach(mdev->dev, &priv->rss_map.indir_qp, mc_list,
MLX4_PROT_ETH);
- for (i = 0; i < priv->mc_addrs_cnt; i++) {
- memcpy(&mc_list[10], priv->mc_addrs + i * ETH_ALEN, ETH_ALEN);
+ list_for_each_entry(mclist, &priv->curr_list, list) {
+ memcpy(&mc_list[10], mclist->addr, ETH_ALEN);
mc_list[5] = priv->port;
mlx4_multicast_detach(mdev->dev, &priv->rss_map.indir_qp,
mc_list, MLX4_PROT_ETH);
}
mlx4_en_clear_list(dev);
+ list_for_each_entry_safe(mclist, tmp, &priv->curr_list, list) {
+ list_del(&mclist->list);
+ kfree(mclist);
+ }
+
/* Flush multicast filter */
mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, 0, 1, MLX4_MCAST_CONFIG);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 225c20d..1bb00cd 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -404,6 +404,18 @@ struct mlx4_en_perf_stats {
#define NUM_PERF_COUNTERS 6
};
+enum mlx4_en_mclist_act {
+ MCLIST_NONE,
+ MCLIST_REM,
+ MCLIST_ADD,
+};
+
+struct mlx4_en_mc_list {
+ struct list_head list;
+ enum mlx4_en_mclist_act action;
+ u8 addr[ETH_ALEN];
+};
+
struct mlx4_en_frag_info {
u16 frag_size;
u16 frag_prefix_size;
@@ -489,8 +501,8 @@ struct mlx4_en_priv {
struct mlx4_en_pkt_stats pkstats;
struct mlx4_en_port_stats port_stats;
u64 stats_bitmap;
- char *mc_addrs;
- int mc_addrs_cnt;
+ struct list_head mc_list;
+ struct list_head curr_list;
struct mlx4_en_stat_out_mbox hw_stats;
int vids[128];
bool wol;
--
1.7.1
^ permalink raw reply related
* [PATCH net-next 06/10] {NET,IB}/mlx4: Add device managed flow steering firmware API
From: Or Gerlitz @ 2012-07-01 9:43 UTC (permalink / raw)
To: davem; +Cc: roland, yevgenyp, oren, netdev, Hadar Hen Zion, Or Gerlitz
In-Reply-To: <1341135823-29039-1-git-send-email-ogerlitz@mellanox.com>
From: Hadar Hen Zion <hadarh@mellanox.co.il>
The driver is modified to support three operation modes.
If supported by firmware use the device managed flow steering
API, that which we call device managed steering mode. Else, if
the firmware supports the B0 steering mode use it, and finally,
if none of the above, use the A0 steering mode.
When the steering mode is device managed, the code is modified
such that L2 based rules set by the mlx4_en driver for Ethernet
unicast and multicast, and the IB stack multicast attach calls
done through the mlx4_ib driver are all routed to use the device
managed API.
When attaching rule using device managed flow steering API,
the firmware returns a 64 bit registration id, which is to be
provided during detach.
Set the firmware to use either standard L2 or L3/L4 optimized flow
steering configuration. Currently there's no dedicated firmware
command to set this, and it has to be provided to the device during
initialization, hence a module param was used here.
Signed-off-by: Hadar Hen Zion <hadarh@mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
drivers/infiniband/hw/mlx4/main.c | 62 +++-
drivers/infiniband/hw/mlx4/mlx4_ib.h | 1 +
drivers/infiniband/hw/mlx4/qp.c | 1 +
drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 21 +-
drivers/net/ethernet/mellanox/mlx4/fw.c | 90 ++++-
drivers/net/ethernet/mellanox/mlx4/fw.h | 3 +
drivers/net/ethernet/mellanox/mlx4/main.c | 63 +++-
drivers/net/ethernet/mellanox/mlx4/mcg.c | 365 +++++++++++++++++++-
drivers/net/ethernet/mellanox/mlx4/mlx4.h | 13 +
drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 2 +
drivers/net/ethernet/mellanox/mlx4/port.c | 102 ++++--
drivers/net/ethernet/mellanox/mlx4/profile.c | 12 +-
.../net/ethernet/mellanox/mlx4/resource_tracker.c | 6 +
include/linux/mlx4/device.h | 108 ++++++-
14 files changed, 766 insertions(+), 83 deletions(-)
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 3530c41..8a3a203 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -718,26 +718,53 @@ int mlx4_ib_add_mc(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp,
return ret;
}
+struct mlx4_ib_steering {
+ struct list_head list;
+ u64 reg_id;
+ union ib_gid gid;
+};
+
static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
{
int err;
struct mlx4_ib_dev *mdev = to_mdev(ibqp->device);
struct mlx4_ib_qp *mqp = to_mqp(ibqp);
+ u64 reg_id;
+ struct mlx4_ib_steering *ib_steering = NULL;
+
+ if (mdev->dev->caps.steering_mode ==
+ MLX4_STEERING_MODE_DEVICE_MANAGED) {
+ ib_steering = kmalloc(sizeof(*ib_steering), GFP_KERNEL);
+ if (!ib_steering)
+ return -ENOMEM;
+ }
- err = mlx4_multicast_attach(mdev->dev, &mqp->mqp, gid->raw,
- !!(mqp->flags & MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK),
- MLX4_PROT_IB_IPV6);
+ err = mlx4_multicast_attach(mdev->dev, &mqp->mqp, gid->raw, mqp->port,
+ !!(mqp->flags &
+ MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK),
+ MLX4_PROT_IB_IPV6, ®_id);
if (err)
- return err;
+ goto err_malloc;
err = add_gid_entry(ibqp, gid);
if (err)
goto err_add;
+ if (ib_steering) {
+ memcpy(ib_steering->gid.raw, gid->raw, 16);
+ ib_steering->reg_id = reg_id;
+ mutex_lock(&mqp->mutex);
+ list_add(&ib_steering->list, &mqp->steering_rules);
+ mutex_unlock(&mqp->mutex);
+ }
return 0;
err_add:
- mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw, MLX4_PROT_IB_IPV6);
+ mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw,
+ MLX4_PROT_IB_IPV6, reg_id);
+err_malloc:
+ kfree(ib_steering);
+
return err;
}
@@ -765,9 +792,30 @@ static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
u8 mac[6];
struct net_device *ndev;
struct mlx4_ib_gid_entry *ge;
+ u64 reg_id = 0;
+
+ if (mdev->dev->caps.steering_mode ==
+ MLX4_STEERING_MODE_DEVICE_MANAGED) {
+ struct mlx4_ib_steering *ib_steering;
+
+ mutex_lock(&mqp->mutex);
+ list_for_each_entry(ib_steering, &mqp->steering_rules, list) {
+ if (!memcmp(ib_steering->gid.raw, gid->raw, 16)) {
+ list_del(&ib_steering->list);
+ break;
+ }
+ }
+ mutex_unlock(&mqp->mutex);
+ if (&ib_steering->list == &mqp->steering_rules) {
+ pr_err("Couldn't find reg_id for mgid. Steering rule is left attached\n");
+ return -EINVAL;
+ }
+ reg_id = ib_steering->reg_id;
+ kfree(ib_steering);
+ }
- err = mlx4_multicast_detach(mdev->dev,
- &mqp->mqp, gid->raw, MLX4_PROT_IB_IPV6);
+ err = mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw,
+ MLX4_PROT_IB_IPV6, reg_id);
if (err)
return err;
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index ff36655..42df4f7 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -163,6 +163,7 @@ struct mlx4_ib_qp {
u8 state;
int mlx_type;
struct list_head gid_list;
+ struct list_head steering_rules;
};
struct mlx4_ib_srq {
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 8d4ed24..6af19f6 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -495,6 +495,7 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
spin_lock_init(&qp->sq.lock);
spin_lock_init(&qp->rq.lock);
INIT_LIST_HEAD(&qp->gid_list);
+ INIT_LIST_HEAD(&qp->steering_rules);
qp->state = IB_QPS_RESET;
if (init_attr->sq_sig_type == IB_SIGNAL_ALL_WR)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index f9a4a00..62f0601 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -460,7 +460,8 @@ static void mlx4_en_do_set_multicast(struct work_struct *work)
err = mlx4_multicast_detach(mdev->dev,
&priv->rss_map.indir_qp,
mc_list,
- MLX4_PROT_ETH);
+ MLX4_PROT_ETH,
+ mclist->reg_id);
if (err)
en_err(priv, "Fail to detach multicast address\n");
@@ -472,11 +473,14 @@ static void mlx4_en_do_set_multicast(struct work_struct *work)
if (mclist->action == MCLIST_ADD) {
/* attach the address */
memcpy(&mc_list[10], mclist->addr, ETH_ALEN);
+ /* needed for B0 steering support */
mc_list[5] = priv->port;
err = mlx4_multicast_attach(mdev->dev,
&priv->rss_map.indir_qp,
- mc_list, 0,
- MLX4_PROT_ETH);
+ mc_list,
+ priv->port, 0,
+ MLX4_PROT_ETH,
+ &mclist->reg_id);
if (err)
en_err(priv, "Fail to attach multicast address\n");
@@ -824,9 +828,10 @@ int mlx4_en_start_port(struct net_device *dev)
/* Attach rx QP to bradcast address */
memset(&mc_list[10], 0xff, ETH_ALEN);
- mc_list[5] = priv->port;
+ mc_list[5] = priv->port; /* needed for B0 steering support */
if (mlx4_multicast_attach(mdev->dev, &priv->rss_map.indir_qp, mc_list,
- 0, MLX4_PROT_ETH))
+ priv->port, 0, MLX4_PROT_ETH,
+ &priv->broadcast_id))
mlx4_warn(mdev, "Failed Attaching Broadcast\n");
/* Must redo promiscuous mode setup. */
@@ -883,14 +888,14 @@ void mlx4_en_stop_port(struct net_device *dev)
/* Detach All multicasts */
memset(&mc_list[10], 0xff, ETH_ALEN);
- mc_list[5] = priv->port;
+ mc_list[5] = priv->port; /* needed for B0 steering support */
mlx4_multicast_detach(mdev->dev, &priv->rss_map.indir_qp, mc_list,
- MLX4_PROT_ETH);
+ MLX4_PROT_ETH, priv->broadcast_id);
list_for_each_entry(mclist, &priv->curr_list, list) {
memcpy(&mc_list[10], mclist->addr, ETH_ALEN);
mc_list[5] = priv->port;
mlx4_multicast_detach(mdev->dev, &priv->rss_map.indir_qp,
- mc_list, MLX4_PROT_ETH);
+ mc_list, MLX4_PROT_ETH, mclist->reg_id);
}
mlx4_en_clear_list(dev);
list_for_each_entry_safe(mclist, tmp, &priv->curr_list, list) {
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 40e048b..c7fb921 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -123,7 +123,8 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags)
static const char * const fname[] = {
[0] = "RSS support",
[1] = "RSS Toeplitz Hash Function support",
- [2] = "RSS XOR Hash Function support"
+ [2] = "RSS XOR Hash Function support",
+ [3] = "Device manage flow steering support"
};
int i;
@@ -391,6 +392,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
#define QUERY_DEV_CAP_RSVD_XRC_OFFSET 0x66
#define QUERY_DEV_CAP_MAX_XRC_OFFSET 0x67
#define QUERY_DEV_CAP_MAX_COUNTERS_OFFSET 0x68
+#define QUERY_DEV_CAP_FLOW_STEERING_RANGE_EN_OFFSET 0x76
+#define QUERY_DEV_CAP_FLOW_STEERING_MAX_QP_OFFSET 0x77
#define QUERY_DEV_CAP_RDMARC_ENTRY_SZ_OFFSET 0x80
#define QUERY_DEV_CAP_QPC_ENTRY_SZ_OFFSET 0x82
#define QUERY_DEV_CAP_AUX_ENTRY_SZ_OFFSET 0x84
@@ -474,6 +477,12 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
dev_cap->num_ports = field & 0xf;
MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_MSG_SZ_OFFSET);
dev_cap->max_msg_sz = 1 << (field & 0x1f);
+ MLX4_GET(field, outbox, QUERY_DEV_CAP_FLOW_STEERING_RANGE_EN_OFFSET);
+ if (field & 0x80)
+ dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_FS_EN;
+ dev_cap->fs_log_max_ucast_qp_range_size = field & 0x1f;
+ MLX4_GET(field, outbox, QUERY_DEV_CAP_FLOW_STEERING_MAX_QP_OFFSET);
+ dev_cap->fs_max_num_qp_per_entry = field;
MLX4_GET(stat_rate, outbox, QUERY_DEV_CAP_RATE_SUPPORT_OFFSET);
dev_cap->stat_rate_support = stat_rate;
MLX4_GET(ext_flags, outbox, QUERY_DEV_CAP_EXT_FLAGS_OFFSET);
@@ -1061,6 +1070,15 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
#define INIT_HCA_LOG_MC_HASH_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x16)
#define INIT_HCA_UC_STEERING_OFFSET (INIT_HCA_MCAST_OFFSET + 0x18)
#define INIT_HCA_LOG_MC_TABLE_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x1b)
+#define INIT_HCA_DEVICE_MANAGED_FLOW_STEERING_EN 0x6
+#define INIT_HCA_FS_PARAM_OFFSET 0x1d0
+#define INIT_HCA_FS_BASE_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x00)
+#define INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x12)
+#define INIT_HCA_FS_LOG_TABLE_SZ_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x1b)
+#define INIT_HCA_FS_ETH_BITS_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x21)
+#define INIT_HCA_FS_ETH_NUM_ADDRS_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x22)
+#define INIT_HCA_FS_IB_BITS_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x25)
+#define INIT_HCA_FS_IB_NUM_ADDRS_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x26)
#define INIT_HCA_TPT_OFFSET 0x0f0
#define INIT_HCA_DMPT_BASE_OFFSET (INIT_HCA_TPT_OFFSET + 0x00)
#define INIT_HCA_LOG_MPT_SZ_OFFSET (INIT_HCA_TPT_OFFSET + 0x0b)
@@ -1119,14 +1137,44 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
MLX4_PUT(inbox, param->rdmarc_base, INIT_HCA_RDMARC_BASE_OFFSET);
MLX4_PUT(inbox, param->log_rd_per_qp, INIT_HCA_LOG_RD_OFFSET);
- /* multicast attributes */
+ /* steering attributes */
+ if (dev->caps.steering_mode ==
+ MLX4_STEERING_MODE_DEVICE_MANAGED) {
+ *(inbox + INIT_HCA_FLAGS_OFFSET / 4) |=
+ cpu_to_be32(1 <<
+ INIT_HCA_DEVICE_MANAGED_FLOW_STEERING_EN);
+
+ MLX4_PUT(inbox, param->mc_base, INIT_HCA_FS_BASE_OFFSET);
+ MLX4_PUT(inbox, param->log_mc_entry_sz,
+ INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET);
+ MLX4_PUT(inbox, param->log_mc_table_sz,
+ INIT_HCA_FS_LOG_TABLE_SZ_OFFSET);
+ /* Enable Ethernet flow steering
+ * with udp unicast and tcp unicast */
+ MLX4_PUT(inbox, param->fs_hash_enable_bits,
+ INIT_HCA_FS_ETH_BITS_OFFSET);
+ MLX4_PUT(inbox, (u16) MLX4_FS_NUM_OF_L2_ADDR,
+ INIT_HCA_FS_ETH_NUM_ADDRS_OFFSET);
+ /* Enable IPoIB flow steering
+ * with udp unicast and tcp unicast */
+ MLX4_PUT(inbox, param->fs_hash_enable_bits,
+ INIT_HCA_FS_IB_BITS_OFFSET);
+ MLX4_PUT(inbox, (u16) MLX4_FS_NUM_OF_L2_ADDR,
+ INIT_HCA_FS_IB_NUM_ADDRS_OFFSET);
- MLX4_PUT(inbox, param->mc_base, INIT_HCA_MC_BASE_OFFSET);
- MLX4_PUT(inbox, param->log_mc_entry_sz, INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET);
- MLX4_PUT(inbox, param->log_mc_hash_sz, INIT_HCA_LOG_MC_HASH_SZ_OFFSET);
- if (dev->caps.steering_mode == MLX4_STEERING_MODE_B0)
- MLX4_PUT(inbox, (u8) (1 << 3), INIT_HCA_UC_STEERING_OFFSET);
- MLX4_PUT(inbox, param->log_mc_table_sz, INIT_HCA_LOG_MC_TABLE_SZ_OFFSET);
+ } else {
+
+ MLX4_PUT(inbox, param->mc_base, INIT_HCA_MC_BASE_OFFSET);
+ MLX4_PUT(inbox, param->log_mc_entry_sz,
+ INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET);
+ MLX4_PUT(inbox, param->log_mc_hash_sz,
+ INIT_HCA_LOG_MC_HASH_SZ_OFFSET);
+ MLX4_PUT(inbox, param->log_mc_table_sz,
+ INIT_HCA_LOG_MC_TABLE_SZ_OFFSET);
+ if (dev->caps.steering_mode == MLX4_STEERING_MODE_B0)
+ MLX4_PUT(inbox, (u8) (1 << 3),
+ INIT_HCA_UC_STEERING_OFFSET);
+ }
/* TPT attributes */
@@ -1188,15 +1236,25 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
MLX4_GET(param->rdmarc_base, outbox, INIT_HCA_RDMARC_BASE_OFFSET);
MLX4_GET(param->log_rd_per_qp, outbox, INIT_HCA_LOG_RD_OFFSET);
- /* multicast attributes */
+ /* steering attributes */
+ if (dev->caps.steering_mode ==
+ MLX4_STEERING_MODE_DEVICE_MANAGED) {
- MLX4_GET(param->mc_base, outbox, INIT_HCA_MC_BASE_OFFSET);
- MLX4_GET(param->log_mc_entry_sz, outbox,
- INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET);
- MLX4_GET(param->log_mc_hash_sz, outbox,
- INIT_HCA_LOG_MC_HASH_SZ_OFFSET);
- MLX4_GET(param->log_mc_table_sz, outbox,
- INIT_HCA_LOG_MC_TABLE_SZ_OFFSET);
+ MLX4_GET(param->mc_base, outbox, INIT_HCA_FS_BASE_OFFSET);
+ MLX4_GET(param->log_mc_entry_sz, outbox,
+ INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET);
+ MLX4_GET(param->log_mc_table_sz, outbox,
+ INIT_HCA_FS_LOG_TABLE_SZ_OFFSET);
+ } else {
+
+ MLX4_GET(param->mc_base, outbox, INIT_HCA_MC_BASE_OFFSET);
+ MLX4_GET(param->log_mc_entry_sz, outbox,
+ INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET);
+ MLX4_GET(param->log_mc_hash_sz, outbox,
+ INIT_HCA_LOG_MC_HASH_SZ_OFFSET);
+ MLX4_GET(param->log_mc_table_sz, outbox,
+ INIT_HCA_LOG_MC_TABLE_SZ_OFFSET);
+ }
/* TPT attributes */
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h
index 64c0399..83fcbbf 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.h
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.h
@@ -78,6 +78,8 @@ struct mlx4_dev_cap {
u16 wavelength[MLX4_MAX_PORTS + 1];
u64 trans_code[MLX4_MAX_PORTS + 1];
u16 stat_rate_support;
+ int fs_log_max_ucast_qp_range_size;
+ int fs_max_num_qp_per_entry;
u64 flags;
u64 flags2;
int reserved_uars;
@@ -165,6 +167,7 @@ struct mlx4_init_hca_param {
u8 log_mpt_sz;
u8 log_uar_sz;
u8 uar_page_sz; /* log pg sz in 4k chunks */
+ u8 fs_hash_enable_bits;
};
struct mlx4_init_ib_param {
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 7df0517..cf5eb2c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -90,7 +90,9 @@ module_param_named(log_num_mgm_entry_size,
MODULE_PARM_DESC(log_num_mgm_entry_size, "log mgm size, that defines the num"
" of qp per mcg, for example:"
" 10 gives 248.range: 9<="
- " log_num_mgm_entry_size <= 12");
+ " log_num_mgm_entry_size <= 12."
+ " Not in use with device managed"
+ " flow steering");
#define MLX4_VF (1 << 0)
@@ -136,6 +138,11 @@ module_param_array(port_type_array, int, &arr_argc, 0444);
MODULE_PARM_DESC(port_type_array, "Array of port types: HW_DEFAULT (0) is default "
"1 for IB, 2 for Ethernet");
+static int mlx4_flow_steering_hash;
+module_param_named(flow_steering_hash, mlx4_flow_steering_hash, int, 0444);
+MODULE_PARM_DESC(flow_steering_hash,
+ "Flow steering hash function configuration. Config options: L2 = 0, L2_L3_L4 = 1 (default: L2).");
+
struct mlx4_port_config {
struct list_head list;
enum mlx4_port_type port_type[MLX4_MAX_PORTS + 1];
@@ -273,21 +280,29 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
dev->caps.max_gso_sz = dev_cap->max_gso_sz;
dev->caps.max_rss_tbl_sz = dev_cap->max_rss_tbl_sz;
- if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER &&
- dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER) {
- dev->caps.steering_mode = MLX4_STEERING_MODE_B0;
-
+ if (dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_FS_EN) {
+ dev->caps.steering_mode = MLX4_STEERING_MODE_DEVICE_MANAGED;
+ dev->caps.num_qp_per_mgm = dev_cap->fs_max_num_qp_per_entry;
+ dev->caps.fs_log_max_ucast_qp_range_size =
+ dev_cap->fs_log_max_ucast_qp_range_size;
} else {
- dev->caps.steering_mode = MLX4_STEERING_MODE_A0;
+ if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER &&
+ dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER) {
+ dev->caps.steering_mode = MLX4_STEERING_MODE_B0;
+
+ } else {
+
+ dev->caps.steering_mode = MLX4_STEERING_MODE_A0;
- if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER ||
- dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER)
- mlx4_warn(dev, "Must have UC_STEER and MC_STEER flags "
- "set to use B0 steering. Falling back to A0 steering mode.\n");
+ if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER ||
+ dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER)
+ mlx4_warn(dev, "Must have UC_STEER and MC_STEER flags "
+ "set to use B0 steering. Falling back to A0 steering mode.\n");
+ }
+ dev->caps.num_qp_per_mgm = mlx4_get_qp_per_mgm(dev);
}
mlx4_dbg(dev, "Steering mode is: %s\n",
mlx4_steering_mode_str(dev->caps.steering_mode));
- dev->caps.num_qp_per_mgm = mlx4_get_qp_per_mgm(dev);
/* Sense port always allowed on supported devices for ConnectX1 and 2 */
if (dev->pdev->device != 0x1003)
@@ -982,9 +997,11 @@ static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
}
/*
- * It's not strictly required, but for simplicity just map the
- * whole multicast group table now. The table isn't very big
- * and it's a lot easier than trying to track ref counts.
+ * For flow steering device managed mode it is required to use
+ * mlx4_init_icm_table. For B0 steering mode it's not strictly
+ * required, but for simplicity just map the whole multicast
+ * group table now. The table isn't very big and it's a lot
+ * easier than trying to track ref counts.
*/
err = mlx4_init_icm_table(dev, &priv->mcg_table.table,
init_hca->mc_base,
@@ -1220,7 +1237,25 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
goto err_stop_fw;
}
+ priv->fs_hash_mode = mlx4_flow_steering_hash;
+
+ switch (priv->fs_hash_mode) {
+ case MLX4_FS_L2_HASH:
+ init_hca.fs_hash_enable_bits = 0;
+ break;
+
+ case MLX4_FS_L2_L3_L4_HASH:
+ /* Enable flow steering with
+ udp unicast and tcp unicast*/
+ init_hca.fs_hash_enable_bits =
+ MLX4_FS_UDP_UC_EN | MLX4_FS_TCP_UC_EN;
+ break;
+ }
+
profile = default_profile;
+ if (dev->caps.steering_mode ==
+ MLX4_STEERING_MODE_DEVICE_MANAGED)
+ profile.num_mcg = MLX4_FS_NUM_MCG;
icm_size = mlx4_make_profile(dev, &profile, &dev_cap,
&init_hca);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c
index 3c59a33..c567655 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mcg.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c
@@ -41,6 +41,7 @@
#define MGM_QPN_MASK 0x00FFFFFF
#define MGM_BLCK_LB_BIT 30
+#define MLX4_MAC_MASK 0xffffffffffffULL
static const u8 zero_gid[16]; /* automatically initialized to 0 */
@@ -54,7 +55,12 @@ struct mlx4_mgm {
int mlx4_get_mgm_entry_size(struct mlx4_dev *dev)
{
- return min((1 << mlx4_log_num_mgm_entry_size), MLX4_MAX_MGM_ENTRY_SIZE);
+ if (dev->caps.steering_mode ==
+ MLX4_STEERING_MODE_DEVICE_MANAGED)
+ return 1 << MLX4_FS_MGM_LOG_ENTRY_SIZE;
+ else
+ return min((1 << mlx4_log_num_mgm_entry_size),
+ MLX4_MAX_MGM_ENTRY_SIZE);
}
int mlx4_get_qp_per_mgm(struct mlx4_dev *dev)
@@ -643,6 +649,311 @@ static int find_entry(struct mlx4_dev *dev, u8 port,
return err;
}
+struct mlx4_net_trans_rule_hw_ctrl {
+ __be32 ctrl;
+ __be32 vf_vep_port;
+ __be32 qpn;
+ __be32 reserved;
+};
+
+static void trans_rule_ctrl_to_hw(struct mlx4_net_trans_rule *ctrl,
+ struct mlx4_net_trans_rule_hw_ctrl *hw)
+{
+ static const u8 __promisc_mode[] = {
+ [MLX4_FS_PROMISC_NONE] = 0x0,
+ [MLX4_FS_PROMISC_UPLINK] = 0x1,
+ [MLX4_FS_PROMISC_FUNCTION_PORT] = 0x2,
+ [MLX4_FS_PROMISC_ALL_MULTI] = 0x3,
+ };
+
+ u32 dw = 0;
+
+ dw = ctrl->queue_mode == MLX4_NET_TRANS_Q_LIFO ? 1 : 0;
+ dw |= ctrl->exclusive ? (1 << 2) : 0;
+ dw |= ctrl->allow_loopback ? (1 << 3) : 0;
+ dw |= __promisc_mode[ctrl->promisc_mode] << 8;
+ dw |= ctrl->priority << 16;
+
+ hw->ctrl = cpu_to_be32(dw);
+ hw->vf_vep_port = cpu_to_be32(ctrl->port);
+ hw->qpn = cpu_to_be32(ctrl->qpn);
+}
+
+struct mlx4_net_trans_rule_hw_ib {
+ u8 size;
+ u8 rsvd1;
+ __be16 id;
+ u32 rsvd2;
+ __be32 qpn;
+ __be32 qpn_mask;
+ u8 dst_gid[16];
+ u8 dst_gid_msk[16];
+} __packed;
+
+struct mlx4_net_trans_rule_hw_eth {
+ u8 size;
+ u8 rsvd;
+ __be16 id;
+ u8 rsvd1[6];
+ u8 dst_mac[6];
+ u16 rsvd2;
+ u8 dst_mac_msk[6];
+ u16 rsvd3;
+ u8 src_mac[6];
+ u16 rsvd4;
+ u8 src_mac_msk[6];
+ u8 rsvd5;
+ u8 ether_type_enable;
+ __be16 ether_type;
+ __be16 vlan_id_msk;
+ __be16 vlan_id;
+} __packed;
+
+struct mlx4_net_trans_rule_hw_tcp_udp {
+ u8 size;
+ u8 rsvd;
+ __be16 id;
+ __be16 rsvd1[3];
+ __be16 dst_port;
+ __be16 rsvd2;
+ __be16 dst_port_msk;
+ __be16 rsvd3;
+ __be16 src_port;
+ __be16 rsvd4;
+ __be16 src_port_msk;
+} __packed;
+
+struct mlx4_net_trans_rule_hw_ipv4 {
+ u8 size;
+ u8 rsvd;
+ __be16 id;
+ __be32 rsvd1;
+ __be32 dst_ip;
+ __be32 dst_ip_msk;
+ __be32 src_ip;
+ __be32 src_ip_msk;
+} __packed;
+
+struct _rule_hw {
+ union {
+ struct {
+ u8 size;
+ u8 rsvd;
+ __be16 id;
+ };
+ struct mlx4_net_trans_rule_hw_eth eth;
+ struct mlx4_net_trans_rule_hw_ib ib;
+ struct mlx4_net_trans_rule_hw_ipv4 ipv4;
+ struct mlx4_net_trans_rule_hw_tcp_udp tcp_udp;
+ };
+};
+
+static int parse_trans_rule(struct mlx4_dev *dev, struct mlx4_spec_list *spec,
+ struct _rule_hw *rule_hw)
+{
+ static const u16 __sw_id_hw[] = {
+ [MLX4_NET_TRANS_RULE_ID_ETH] = 0xE001,
+ [MLX4_NET_TRANS_RULE_ID_IB] = 0xE005,
+ [MLX4_NET_TRANS_RULE_ID_IPV6] = 0xE003,
+ [MLX4_NET_TRANS_RULE_ID_IPV4] = 0xE002,
+ [MLX4_NET_TRANS_RULE_ID_TCP] = 0xE004,
+ [MLX4_NET_TRANS_RULE_ID_UDP] = 0xE006
+ };
+
+ static const size_t __rule_hw_sz[] = {
+ [MLX4_NET_TRANS_RULE_ID_ETH] =
+ sizeof(struct mlx4_net_trans_rule_hw_eth),
+ [MLX4_NET_TRANS_RULE_ID_IB] =
+ sizeof(struct mlx4_net_trans_rule_hw_ib),
+ [MLX4_NET_TRANS_RULE_ID_IPV6] = 0,
+ [MLX4_NET_TRANS_RULE_ID_IPV4] =
+ sizeof(struct mlx4_net_trans_rule_hw_ipv4),
+ [MLX4_NET_TRANS_RULE_ID_TCP] =
+ sizeof(struct mlx4_net_trans_rule_hw_tcp_udp),
+ [MLX4_NET_TRANS_RULE_ID_UDP] =
+ sizeof(struct mlx4_net_trans_rule_hw_tcp_udp)
+ };
+ if (spec->id > MLX4_NET_TRANS_RULE_NUM) {
+ mlx4_err(dev, "Invalid network rule id. id = %d\n", spec->id);
+ return -EINVAL;
+ }
+ memset(rule_hw, 0, __rule_hw_sz[spec->id]);
+ rule_hw->id = cpu_to_be16(__sw_id_hw[spec->id]);
+ rule_hw->size = __rule_hw_sz[spec->id] >> 2;
+
+ switch (spec->id) {
+ case MLX4_NET_TRANS_RULE_ID_ETH:
+ memcpy(rule_hw->eth.dst_mac, spec->eth.dst_mac, ETH_ALEN);
+ memcpy(rule_hw->eth.dst_mac_msk, spec->eth.dst_mac_msk,
+ ETH_ALEN);
+ memcpy(rule_hw->eth.src_mac, spec->eth.src_mac, ETH_ALEN);
+ memcpy(rule_hw->eth.src_mac_msk, spec->eth.src_mac_msk,
+ ETH_ALEN);
+ if (spec->eth.ether_type_enable) {
+ rule_hw->eth.ether_type_enable = 1;
+ rule_hw->eth.ether_type = spec->eth.ether_type;
+ }
+ rule_hw->eth.vlan_id = spec->eth.vlan_id;
+ rule_hw->eth.vlan_id_msk = spec->eth.vlan_id_msk;
+ break;
+
+ case MLX4_NET_TRANS_RULE_ID_IB:
+ rule_hw->ib.qpn = spec->ib.r_qpn;
+ rule_hw->ib.qpn_mask = spec->ib.qpn_msk;
+ memcpy(&rule_hw->ib.dst_gid, &spec->ib.dst_gid, 16);
+ memcpy(&rule_hw->ib.dst_gid_msk, &spec->ib.dst_gid_msk, 16);
+ break;
+
+ case MLX4_NET_TRANS_RULE_ID_IPV6:
+ return -EOPNOTSUPP;
+
+ case MLX4_NET_TRANS_RULE_ID_IPV4:
+ rule_hw->ipv4.src_ip = spec->ipv4.src_ip;
+ rule_hw->ipv4.src_ip_msk = spec->ipv4.src_ip_msk;
+ rule_hw->ipv4.dst_ip = spec->ipv4.dst_ip;
+ rule_hw->ipv4.dst_ip_msk = spec->ipv4.dst_ip_msk;
+ break;
+
+ case MLX4_NET_TRANS_RULE_ID_TCP:
+ case MLX4_NET_TRANS_RULE_ID_UDP:
+ rule_hw->tcp_udp.dst_port = spec->tcp_udp.dst_port;
+ rule_hw->tcp_udp.dst_port_msk = spec->tcp_udp.dst_port_msk;
+ rule_hw->tcp_udp.src_port = spec->tcp_udp.src_port;
+ rule_hw->tcp_udp.src_port_msk = spec->tcp_udp.src_port_msk;
+ break;
+
+ default:
+ return -EINVAL;
+ }
+
+ return __rule_hw_sz[spec->id];
+}
+
+static void mlx4_err_rule(struct mlx4_dev *dev, char *str,
+ struct mlx4_net_trans_rule *rule)
+{
+#define BUF_SIZE 256
+ struct mlx4_spec_list *cur;
+ char buf[BUF_SIZE];
+ int len = 0;
+
+ mlx4_err(dev, "%s", str);
+ len += snprintf(buf + len, BUF_SIZE - len,
+ "port = %d prio = 0x%x qp = 0x%x ",
+ rule->port, rule->priority, rule->qpn);
+
+ list_for_each_entry(cur, &rule->list, list) {
+ switch (cur->id) {
+ case MLX4_NET_TRANS_RULE_ID_ETH:
+ len += snprintf(buf + len, BUF_SIZE - len,
+ "dmac = %pM ", &cur->eth.dst_mac);
+ if (cur->eth.ether_type)
+ len += snprintf(buf + len, BUF_SIZE - len,
+ "ethertype = 0x%x ",
+ be16_to_cpu(cur->eth.ether_type));
+ if (cur->eth.vlan_id)
+ len += snprintf(buf + len, BUF_SIZE - len,
+ "vlan-id = %d ",
+ be16_to_cpu(cur->eth.vlan_id));
+ break;
+
+ case MLX4_NET_TRANS_RULE_ID_IPV4:
+ if (cur->ipv4.src_ip)
+ len += snprintf(buf + len, BUF_SIZE - len,
+ "src-ip = %pI4 ",
+ &cur->ipv4.src_ip);
+ if (cur->ipv4.dst_ip)
+ len += snprintf(buf + len, BUF_SIZE - len,
+ "dst-ip = %pI4 ",
+ &cur->ipv4.dst_ip);
+ break;
+
+ case MLX4_NET_TRANS_RULE_ID_TCP:
+ case MLX4_NET_TRANS_RULE_ID_UDP:
+ if (cur->tcp_udp.src_port)
+ len += snprintf(buf + len, BUF_SIZE - len,
+ "src-port = %d ",
+ be16_to_cpu(cur->tcp_udp.src_port));
+ if (cur->tcp_udp.dst_port)
+ len += snprintf(buf + len, BUF_SIZE - len,
+ "dst-port = %d ",
+ be16_to_cpu(cur->tcp_udp.dst_port));
+ break;
+
+ case MLX4_NET_TRANS_RULE_ID_IB:
+ len += snprintf(buf + len, BUF_SIZE - len,
+ "dst-gid = %pI6\n", cur->ib.dst_gid);
+ len += snprintf(buf + len, BUF_SIZE - len,
+ "dst-gid-mask = %pI6\n",
+ cur->ib.dst_gid_msk);
+ break;
+
+ case MLX4_NET_TRANS_RULE_ID_IPV6:
+ break;
+
+ default:
+ break;
+ }
+ }
+ len += snprintf(buf + len, BUF_SIZE - len, "\n");
+ mlx4_err(dev, "%s", buf);
+
+ if (len >= BUF_SIZE)
+ mlx4_err(dev, "Network rule error message was truncated, print buffer is too small.\n");
+}
+
+int mlx4_flow_attach(struct mlx4_dev *dev,
+ struct mlx4_net_trans_rule *rule, u64 *reg_id)
+{
+ struct mlx4_cmd_mailbox *mailbox;
+ struct mlx4_spec_list *cur;
+ u32 size = 0;
+ int ret;
+
+ mailbox = mlx4_alloc_cmd_mailbox(dev);
+ if (IS_ERR(mailbox))
+ return PTR_ERR(mailbox);
+
+ memset(mailbox->buf, 0, sizeof(struct mlx4_net_trans_rule_hw_ctrl));
+ trans_rule_ctrl_to_hw(rule, mailbox->buf);
+
+ size += sizeof(struct mlx4_net_trans_rule_hw_ctrl);
+
+ list_for_each_entry(cur, &rule->list, list) {
+ ret = parse_trans_rule(dev, cur, mailbox->buf + size);
+ if (ret < 0) {
+ mlx4_free_cmd_mailbox(dev, mailbox);
+ return -EINVAL;
+ }
+ size += ret;
+ }
+
+ ret = mlx4_QP_FLOW_STEERING_ATTACH(dev, mailbox, size >> 2, reg_id);
+ if (ret == -ENOMEM)
+ mlx4_err_rule(dev,
+ "mcg table is full. Fail to register network rule.\n",
+ rule);
+ else if (ret)
+ mlx4_err_rule(dev, "Fail to register network rule.\n", rule);
+
+ mlx4_free_cmd_mailbox(dev, mailbox);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(mlx4_flow_attach);
+
+int mlx4_flow_detach(struct mlx4_dev *dev, u64 reg_id)
+{
+ int err;
+
+ err = mlx4_QP_FLOW_STEERING_DETACH(dev, reg_id);
+ if (err)
+ mlx4_err(dev, "Fail to detach network rule. registration id = 0x%llx\n"
+ , reg_id);
+ return err;
+}
+EXPORT_SYMBOL_GPL(mlx4_flow_detach);
+
int mlx4_qp_attach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
int block_mcast_loopback, enum mlx4_protocol prot,
enum mlx4_steer_type steer)
@@ -895,7 +1206,8 @@ static int mlx4_QP_ATTACH(struct mlx4_dev *dev, struct mlx4_qp *qp,
}
int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
- int block_mcast_loopback, enum mlx4_protocol prot)
+ u8 port, int block_mcast_loopback,
+ enum mlx4_protocol prot, u64 *reg_id)
{
switch (dev->caps.steering_mode) {
@@ -914,6 +1226,42 @@ int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
block_mcast_loopback, prot,
MLX4_MC_STEER);
+ case MLX4_STEERING_MODE_DEVICE_MANAGED: {
+ struct mlx4_spec_list spec = { {NULL} };
+ __be64 mac_mask = cpu_to_be64(MLX4_MAC_MASK << 16);
+
+ struct mlx4_net_trans_rule rule = {
+ .queue_mode = MLX4_NET_TRANS_Q_FIFO,
+ .exclusive = 0,
+ .promisc_mode = MLX4_FS_PROMISC_NONE,
+ .priority = MLX4_DOMAIN_NIC,
+ };
+
+ rule.allow_loopback = ~block_mcast_loopback;
+ rule.port = port;
+ rule.qpn = qp->qpn;
+ INIT_LIST_HEAD(&rule.list);
+
+ switch (prot) {
+ case MLX4_PROT_ETH:
+ spec.id = MLX4_NET_TRANS_RULE_ID_ETH;
+ memcpy(spec.eth.dst_mac, &gid[10], ETH_ALEN);
+ memcpy(spec.eth.dst_mac_msk, &mac_mask, ETH_ALEN);
+ break;
+
+ case MLX4_PROT_IB_IPV6:
+ spec.id = MLX4_NET_TRANS_RULE_ID_IB;
+ memcpy(spec.ib.dst_gid, gid, 16);
+ memset(&spec.ib.dst_gid_msk, 0xff, 16);
+ break;
+ default:
+ return -EINVAL;
+ }
+ list_add_tail(&spec.list, &rule.list);
+
+ return mlx4_flow_attach(dev, &rule, reg_id);
+ }
+
default:
return -EINVAL;
}
@@ -921,7 +1269,7 @@ int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
EXPORT_SYMBOL_GPL(mlx4_multicast_attach);
int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
- enum mlx4_protocol prot)
+ enum mlx4_protocol prot, u64 reg_id)
{
switch (dev->caps.steering_mode) {
case MLX4_STEERING_MODE_A0:
@@ -938,6 +1286,9 @@ int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
return mlx4_qp_detach_common(dev, qp, gid, prot,
MLX4_MC_STEER);
+ case MLX4_STEERING_MODE_DEVICE_MANAGED:
+ return mlx4_flow_detach(dev, reg_id);
+
default:
return -EINVAL;
}
@@ -1042,6 +1393,10 @@ int mlx4_init_mcg_table(struct mlx4_dev *dev)
struct mlx4_priv *priv = mlx4_priv(dev);
int err;
+ /* No need for mcg_table when fw managed the mcg table*/
+ if (dev->caps.steering_mode ==
+ MLX4_STEERING_MODE_DEVICE_MANAGED)
+ return 0;
err = mlx4_bitmap_init(&priv->mcg_table.bitmap, dev->caps.num_amgms,
dev->caps.num_amgms - 1, 0, 0);
if (err)
@@ -1054,5 +1409,7 @@ int mlx4_init_mcg_table(struct mlx4_dev *dev)
void mlx4_cleanup_mcg_table(struct mlx4_dev *dev)
{
- mlx4_bitmap_cleanup(&mlx4_priv(dev)->mcg_table.bitmap);
+ if (dev->caps.steering_mode !=
+ MLX4_STEERING_MODE_DEVICE_MANAGED)
+ mlx4_bitmap_cleanup(&mlx4_priv(dev)->mcg_table.bitmap);
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index c07e882..0084967 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -54,6 +54,17 @@
#define DRV_VERSION "1.1"
#define DRV_RELDATE "Dec, 2011"
+#define MLX4_FS_UDP_UC_EN (1 << 1)
+#define MLX4_FS_TCP_UC_EN (1 << 2)
+#define MLX4_FS_NUM_OF_L2_ADDR 8
+#define MLX4_FS_MGM_LOG_ENTRY_SIZE 7
+#define MLX4_FS_NUM_MCG (1 << 17)
+
+enum {
+ MLX4_FS_L2_HASH = 0,
+ MLX4_FS_L2_L3_L4_HASH,
+};
+
#define MLX4_NUM_UP 8
#define MLX4_NUM_TC 8
#define MLX4_RATELIMIT_UNITS 3 /* 100 Mbps */
@@ -704,6 +715,7 @@ struct mlx4_set_port_rqp_calc_context {
struct mlx4_mac_entry {
u64 mac;
+ u64 reg_id;
};
struct mlx4_port_info {
@@ -777,6 +789,7 @@ struct mlx4_priv {
struct mutex bf_mutex;
struct io_mapping *bf_mapping;
int reserved_mtts;
+ int fs_hash_mode;
};
static inline struct mlx4_priv *mlx4_priv(struct mlx4_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 1bb00cd..2d6dabe 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -414,6 +414,7 @@ struct mlx4_en_mc_list {
struct list_head list;
enum mlx4_en_mclist_act action;
u8 addr[ETH_ALEN];
+ u64 reg_id;
};
struct mlx4_en_frag_info {
@@ -503,6 +504,7 @@ struct mlx4_en_priv {
u64 stats_bitmap;
struct list_head mc_list;
struct list_head curr_list;
+ u64 broadcast_id;
struct mlx4_en_stat_out_mbox hw_stats;
int vids[128];
bool wol;
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index 58de723..a51d1b9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -75,21 +75,54 @@ void mlx4_init_vlan_table(struct mlx4_dev *dev, struct mlx4_vlan_table *table)
table->total = 0;
}
-static int mlx4_uc_steer_add(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn)
+static int mlx4_uc_steer_add(struct mlx4_dev *dev, u8 port,
+ u64 mac, int *qpn, u64 *reg_id)
{
- struct mlx4_qp qp;
- u8 gid[16] = {0};
__be64 be_mac;
int err;
- qp.qpn = *qpn;
-
- mac &= 0xffffffffffffULL;
+ mac &= MLX4_MAC_MASK;
be_mac = cpu_to_be64(mac << 16);
- memcpy(&gid[10], &be_mac, ETH_ALEN);
- gid[5] = port;
- err = mlx4_unicast_attach(dev, &qp, gid, 0, MLX4_PROT_ETH);
+ switch (dev->caps.steering_mode) {
+ case MLX4_STEERING_MODE_B0: {
+ struct mlx4_qp qp;
+ u8 gid[16] = {0};
+
+ qp.qpn = *qpn;
+ memcpy(&gid[10], &be_mac, ETH_ALEN);
+ gid[5] = port;
+
+ err = mlx4_unicast_attach(dev, &qp, gid, 0, MLX4_PROT_ETH);
+ break;
+ }
+ case MLX4_STEERING_MODE_DEVICE_MANAGED: {
+ struct mlx4_spec_list spec_eth = { {NULL} };
+ __be64 mac_mask = cpu_to_be64(MLX4_MAC_MASK << 16);
+
+ struct mlx4_net_trans_rule rule = {
+ .queue_mode = MLX4_NET_TRANS_Q_FIFO,
+ .exclusive = 0,
+ .allow_loopback = 1,
+ .promisc_mode = MLX4_FS_PROMISC_NONE,
+ .priority = MLX4_DOMAIN_NIC,
+ };
+
+ rule.port = port;
+ rule.qpn = *qpn;
+ INIT_LIST_HEAD(&rule.list);
+
+ spec_eth.id = MLX4_NET_TRANS_RULE_ID_ETH;
+ memcpy(spec_eth.eth.dst_mac, &be_mac, ETH_ALEN);
+ memcpy(spec_eth.eth.dst_mac_msk, &mac_mask, ETH_ALEN);
+ list_add_tail(&spec_eth.list, &rule.list);
+
+ err = mlx4_flow_attach(dev, &rule, reg_id);
+ break;
+ }
+ default:
+ return -EINVAL;
+ }
if (err)
mlx4_warn(dev, "Failed Attaching Unicast\n");
@@ -97,19 +130,30 @@ static int mlx4_uc_steer_add(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn)
}
static void mlx4_uc_steer_release(struct mlx4_dev *dev, u8 port,
- u64 mac, int qpn)
+ u64 mac, int qpn, u64 reg_id)
{
- struct mlx4_qp qp;
- u8 gid[16] = {0};
- __be64 be_mac;
+ switch (dev->caps.steering_mode) {
+ case MLX4_STEERING_MODE_B0: {
+ struct mlx4_qp qp;
+ u8 gid[16] = {0};
+ __be64 be_mac;
- qp.qpn = qpn;
- mac &= 0xffffffffffffULL;
- be_mac = cpu_to_be64(mac << 16);
- memcpy(&gid[10], &be_mac, ETH_ALEN);
- gid[5] = port;
+ qp.qpn = qpn;
+ mac &= MLX4_MAC_MASK;
+ be_mac = cpu_to_be64(mac << 16);
+ memcpy(&gid[10], &be_mac, ETH_ALEN);
+ gid[5] = port;
- mlx4_unicast_detach(dev, &qp, gid, MLX4_PROT_ETH);
+ mlx4_unicast_detach(dev, &qp, gid, MLX4_PROT_ETH);
+ break;
+ }
+ case MLX4_STEERING_MODE_DEVICE_MANAGED: {
+ mlx4_flow_detach(dev, reg_id);
+ break;
+ }
+ default:
+ mlx4_err(dev, "Invalid steering mode.\n");
+ }
}
static int validate_index(struct mlx4_dev *dev,
@@ -144,6 +188,7 @@ int mlx4_get_eth_qp(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn)
struct mlx4_mac_entry *entry;
int index = 0;
int err = 0;
+ u64 reg_id;
mlx4_dbg(dev, "Registering MAC: 0x%llx for adding\n",
(unsigned long long) mac);
@@ -167,7 +212,7 @@ int mlx4_get_eth_qp(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn)
goto qp_err;
}
- err = mlx4_uc_steer_add(dev, port, mac, qpn);
+ err = mlx4_uc_steer_add(dev, port, mac, qpn, ®_id);
if (err)
goto steer_err;
@@ -177,6 +222,7 @@ int mlx4_get_eth_qp(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn)
goto alloc_err;
}
entry->mac = mac;
+ entry->reg_id = reg_id;
err = radix_tree_insert(&info->mac_tree, *qpn, entry);
if (err)
goto insert_err;
@@ -186,7 +232,7 @@ insert_err:
kfree(entry);
alloc_err:
- mlx4_uc_steer_release(dev, port, mac, *qpn);
+ mlx4_uc_steer_release(dev, port, mac, *qpn, reg_id);
steer_err:
mlx4_qp_release_range(dev, *qpn, 1);
@@ -212,7 +258,8 @@ void mlx4_put_eth_qp(struct mlx4_dev *dev, u8 port, u64 mac, int qpn)
mlx4_dbg(dev, "Releasing qp: port %d, mac 0x%llx,"
" qpn %d\n", port,
(unsigned long long) mac, qpn);
- mlx4_uc_steer_release(dev, port, entry->mac, qpn);
+ mlx4_uc_steer_release(dev, port, entry->mac,
+ qpn, entry->reg_id);
mlx4_qp_release_range(dev, qpn, 1);
radix_tree_delete(&info->mac_tree, qpn);
kfree(entry);
@@ -363,11 +410,14 @@ int mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac)
entry = radix_tree_lookup(&info->mac_tree, qpn);
if (!entry)
return -EINVAL;
- mlx4_uc_steer_release(dev, port, entry->mac, qpn);
+ mlx4_uc_steer_release(dev, port, entry->mac,
+ qpn, entry->reg_id);
mlx4_unregister_mac(dev, port, entry->mac);
entry->mac = new_mac;
+ entry->reg_id = 0;
mlx4_register_mac(dev, port, new_mac);
- err = mlx4_uc_steer_add(dev, port, entry->mac, &qpn);
+ err = mlx4_uc_steer_add(dev, port, entry->mac,
+ &qpn, &entry->reg_id);
return err;
}
diff --git a/drivers/net/ethernet/mellanox/mlx4/profile.c b/drivers/net/ethernet/mellanox/mlx4/profile.c
index b83bc92..9ee4725 100644
--- a/drivers/net/ethernet/mellanox/mlx4/profile.c
+++ b/drivers/net/ethernet/mellanox/mlx4/profile.c
@@ -237,13 +237,19 @@ u64 mlx4_make_profile(struct mlx4_dev *dev,
init_hca->mtt_base = profile[i].start;
break;
case MLX4_RES_MCG:
- dev->caps.num_mgms = profile[i].num >> 1;
- dev->caps.num_amgms = profile[i].num >> 1;
init_hca->mc_base = profile[i].start;
init_hca->log_mc_entry_sz =
ilog2(mlx4_get_mgm_entry_size(dev));
init_hca->log_mc_table_sz = profile[i].log_num;
- init_hca->log_mc_hash_sz = profile[i].log_num - 1;
+ if (dev->caps.steering_mode ==
+ MLX4_STEERING_MODE_DEVICE_MANAGED) {
+ dev->caps.num_mgms = profile[i].num;
+ } else {
+ init_hca->log_mc_hash_sz =
+ profile[i].log_num - 1;
+ dev->caps.num_mgms = profile[i].num >> 1;
+ dev->caps.num_amgms = profile[i].num >> 1;
+ }
break;
default:
break;
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 4301aa5..ce73772 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -2746,6 +2746,9 @@ int mlx4_QP_FLOW_STEERING_ATTACH_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd)
{
+ if (dev->caps.steering_mode !=
+ MLX4_STEERING_MODE_DEVICE_MANAGED)
+ return -EOPNOTSUPP;
return mlx4_cmd_imm(dev, inbox->dma, &vhcr->out_param,
vhcr->in_modifier, 0,
MLX4_QP_FLOW_STEERING_ATTACH,
@@ -2759,6 +2762,9 @@ int mlx4_QP_FLOW_STEERING_DETACH_wrapper(struct mlx4_dev *dev, int slave,
struct mlx4_cmd_mailbox *outbox,
struct mlx4_cmd_info *cmd)
{
+ if (dev->caps.steering_mode !=
+ MLX4_STEERING_MODE_DEVICE_MANAGED)
+ return -EOPNOTSUPP;
return mlx4_cmd(dev, vhcr->in_param, 0, 0,
MLX4_QP_FLOW_STEERING_DETACH, MLX4_CMD_TIME_CLASS_A,
MLX4_CMD_NATIVE);
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 80891a4..a22a851 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -70,14 +70,17 @@ enum {
MLX4_MFUNC_EQE_MASK = (MLX4_MFUNC_MAX_EQES - 1)
};
-/* Driver supports 2 diffrent device methods to manage traffic steering:
+/* Driver supports 3 diffrent device methods to manage traffic steering:
+ -device managed - High level API for ib and eth flow steering. FW is
+ managing flow steering tables.
- B0 steering mode - Common low level API for ib and (if supported) eth.
- A0 steering mode - Limited low level API for eth. In case of IB,
B0 mode is in use.
*/
enum {
MLX4_STEERING_MODE_A0,
- MLX4_STEERING_MODE_B0
+ MLX4_STEERING_MODE_B0,
+ MLX4_STEERING_MODE_DEVICE_MANAGED
};
static inline const char *mlx4_steering_mode_str(int steering_mode)
@@ -88,6 +91,10 @@ static inline const char *mlx4_steering_mode_str(int steering_mode)
case MLX4_STEERING_MODE_B0:
return "B0 steering";
+
+ case MLX4_STEERING_MODE_DEVICE_MANAGED:
+ return "Device managed flow steering";
+
default:
return "Unrecognize steering mode";
}
@@ -125,7 +132,8 @@ enum {
enum {
MLX4_DEV_CAP_FLAG2_RSS = 1LL << 0,
MLX4_DEV_CAP_FLAG2_RSS_TOP = 1LL << 1,
- MLX4_DEV_CAP_FLAG2_RSS_XOR = 1LL << 2
+ MLX4_DEV_CAP_FLAG2_RSS_XOR = 1LL << 2,
+ MLX4_DEV_CAP_FLAG2_FS_EN = 1LL << 3
};
#define MLX4_ATTR_EXTENDED_PORT_INFO cpu_to_be16(0xff90)
@@ -319,6 +327,7 @@ struct mlx4_caps {
int reserved_mcgs;
int num_qp_per_mgm;
int steering_mode;
+ int fs_log_max_ucast_qp_range_size;
int num_pds;
int reserved_pds;
int max_xrcds;
@@ -647,9 +656,94 @@ int mlx4_unicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
int mlx4_unicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
enum mlx4_protocol prot);
int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
- int block_mcast_loopback, enum mlx4_protocol protocol);
+ u8 port, int block_mcast_loopback,
+ enum mlx4_protocol protocol, u64 *reg_id);
int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
- enum mlx4_protocol protocol);
+ enum mlx4_protocol protocol, u64 reg_id);
+
+enum {
+ MLX4_DOMAIN_UVERBS = 0x1000,
+ MLX4_DOMAIN_ETHTOOL = 0x2000,
+ MLX4_DOMAIN_RFS = 0x3000,
+ MLX4_DOMAIN_NIC = 0x5000,
+};
+
+enum mlx4_net_trans_rule_id {
+ MLX4_NET_TRANS_RULE_ID_ETH = 0,
+ MLX4_NET_TRANS_RULE_ID_IB,
+ MLX4_NET_TRANS_RULE_ID_IPV6,
+ MLX4_NET_TRANS_RULE_ID_IPV4,
+ MLX4_NET_TRANS_RULE_ID_TCP,
+ MLX4_NET_TRANS_RULE_ID_UDP,
+ MLX4_NET_TRANS_RULE_NUM, /* should be last */
+};
+
+enum mlx4_net_trans_promisc_mode {
+ MLX4_FS_PROMISC_NONE = 0,
+ MLX4_FS_PROMISC_UPLINK,
+ MLX4_FS_PROMISC_FUNCTION_PORT,
+ MLX4_FS_PROMISC_ALL_MULTI,
+};
+
+struct mlx4_spec_eth {
+ u8 dst_mac[6];
+ u8 dst_mac_msk[6];
+ u8 src_mac[6];
+ u8 src_mac_msk[6];
+ u8 ether_type_enable;
+ __be16 ether_type;
+ __be16 vlan_id_msk;
+ __be16 vlan_id;
+};
+
+struct mlx4_spec_tcp_udp {
+ __be16 dst_port;
+ __be16 dst_port_msk;
+ __be16 src_port;
+ __be16 src_port_msk;
+};
+
+struct mlx4_spec_ipv4 {
+ __be32 dst_ip;
+ __be32 dst_ip_msk;
+ __be32 src_ip;
+ __be32 src_ip_msk;
+};
+
+struct mlx4_spec_ib {
+ __be32 r_qpn;
+ __be32 qpn_msk;
+ u8 dst_gid[16];
+ u8 dst_gid_msk[16];
+};
+
+struct mlx4_spec_list {
+ struct list_head list;
+ enum mlx4_net_trans_rule_id id;
+ union {
+ struct mlx4_spec_eth eth;
+ struct mlx4_spec_ib ib;
+ struct mlx4_spec_ipv4 ipv4;
+ struct mlx4_spec_tcp_udp tcp_udp;
+ };
+};
+
+enum mlx4_net_trans_hw_rule_queue {
+ MLX4_NET_TRANS_Q_FIFO,
+ MLX4_NET_TRANS_Q_LIFO,
+};
+
+struct mlx4_net_trans_rule {
+ struct list_head list;
+ enum mlx4_net_trans_hw_rule_queue queue_mode;
+ bool exclusive;
+ bool allow_loopback;
+ enum mlx4_net_trans_promisc_mode promisc_mode;
+ u8 port;
+ u16 priority;
+ u32 qpn;
+};
+
int mlx4_multicast_promisc_add(struct mlx4_dev *dev, u32 qpn, u8 port);
int mlx4_multicast_promisc_remove(struct mlx4_dev *dev, u32 qpn, u8 port);
int mlx4_unicast_promisc_add(struct mlx4_dev *dev, u32 qpn, u8 port);
@@ -692,4 +786,8 @@ int mlx4_wol_write(struct mlx4_dev *dev, u64 config, int port);
int mlx4_counter_alloc(struct mlx4_dev *dev, u32 *idx);
void mlx4_counter_free(struct mlx4_dev *dev, u32 idx);
+int mlx4_flow_attach(struct mlx4_dev *dev,
+ struct mlx4_net_trans_rule *rule, u64 *reg_id);
+int mlx4_flow_detach(struct mlx4_dev *dev, u64 reg_id);
+
#endif /* MLX4_DEVICE_H */
--
1.7.1
^ 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