* [PATCH V2 03/12] include/linux: Add private flags for IPoIB interfaces
From: Or Gerlitz @ 2012-08-01 17:09 UTC (permalink / raw)
To: davem; +Cc: roland, netdev, ali, sean.hefty, Erez Shitrit, Or Gerlitz
In-Reply-To: <1343840975-3252-1-git-send-email-ogerlitz@mellanox.com>
From: Erez Shitrit <erezsh@mellanox.co.il>
The new 2 bits indicates whenever a device is considered PIF interface,
which means the "main" interfaces (ib0, ib1 etc), or cloned interfaces
(ib0.1, ib1.2 etc.) that is now in use by the eIPoIB driver.
Signed-off-by: Erez Shitrit <erezsh@mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
include/linux/if.h | 2 ++
1 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/include/linux/if.h b/include/linux/if.h
index 1ec407b..f50dbf2 100644
--- a/include/linux/if.h
+++ b/include/linux/if.h
@@ -84,6 +84,8 @@
#define IFF_LIVE_ADDR_CHANGE 0x100000 /* device supports hardware address
* change when it's running */
+#define IFF_EIPOIB_PIF 0x200000 /* IPoIB PIF intf (ib0, ib1 etc.) */
+#define IFF_EIPOIB_VIF 0x400000 /* IPoIB VIF intf (ib0.x, ib1.x etc.) */
#define IF_GET_IFACE 0x0001 /* for querying only */
#define IF_GET_PROTO 0x0002
--
1.7.1
^ permalink raw reply related
* [PATCH V2 06/12] net/core: Add rtnetlink support to vif parameters
From: Or Gerlitz @ 2012-08-01 17:09 UTC (permalink / raw)
To: davem; +Cc: roland, netdev, ali, sean.hefty, Erez Shitrit, Or Gerlitz
In-Reply-To: <1343840975-3252-1-git-send-email-ogerlitz@mellanox.com>
From: Erez Shitrit <erezsh@mellanox.co.il>
Add IFLA_VIF_INFO which allows user space to configure mac/vlan for a VIF
Signed-off-by: Erez Shitrit <erezsh@mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
include/linux/if_link.h | 16 ++++++++++++++++
net/core/rtnetlink.c | 42 +++++++++++++++++++++++++++++++++++++++++-
2 files changed, 57 insertions(+), 1 deletions(-)
diff --git a/include/linux/if_link.h b/include/linux/if_link.h
index ac173bd..2a401f3 100644
--- a/include/linux/if_link.h
+++ b/include/linux/if_link.h
@@ -142,6 +142,7 @@ enum {
#define IFLA_PROMISCUITY IFLA_PROMISCUITY
IFLA_NUM_TX_QUEUES,
IFLA_NUM_RX_QUEUES,
+ IFLA_VIFINFO_LIST,/* config virtual interface, gives it mac/vlan */
__IFLA_MAX
};
@@ -398,4 +399,19 @@ struct ifla_port_vsi {
__u8 pad[3];
};
+/* support vif configuration. */
+enum {
+ IFLA_VIF_INFO_UNSPEC,
+ IFLA_VIF_INFO,
+ __IFLA_VIF_INFO_MAX,
+};
+
+#define IFLA_VIF_INFO_MAX (__IFLA_VIF_INFO_MAX - 1)
+
+struct ifla_vif_param {
+ __u32 vif;
+ __u8 mac[32]; /* MAX_ADDR_LEN */
+ __u16 vlan;
+};
+
#endif /* _LINUX_IF_LINK_H */
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 334b930..751e55d 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -780,7 +780,8 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
+ rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */
+ rtnl_port_size(dev) /* IFLA_VF_PORTS + IFLA_PORT_SELF */
+ rtnl_link_get_size(dev) /* IFLA_LINKINFO */
- + rtnl_link_get_af_size(dev); /* IFLA_AF_SPEC */
+ + rtnl_link_get_af_size(dev) /* IFLA_AF_SPEC */
+ + nla_total_size(sizeof(struct ifla_vif_param)); /* IFLA_VIF_INFO */
}
static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev)
@@ -1114,6 +1115,7 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = {
[IFLA_PROMISCUITY] = { .type = NLA_U32 },
[IFLA_NUM_TX_QUEUES] = { .type = NLA_U32 },
[IFLA_NUM_RX_QUEUES] = { .type = NLA_U32 },
+ [IFLA_VIFINFO_LIST] = {. type = NLA_NESTED },
};
EXPORT_SYMBOL(ifla_policy);
@@ -1137,6 +1139,11 @@ static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = {
.len = sizeof(struct ifla_vf_spoofchk) },
};
+static const struct nla_policy ifla_vifinfo_policy[IFLA_VIF_INFO_MAX+1] = {
+ [IFLA_VIF_INFO] = { .type = NLA_BINARY,
+ .len = sizeof(struct ifla_vif_param)},
+};
+
static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = {
[IFLA_PORT_VF] = { .type = NLA_U32 },
[IFLA_PORT_PROFILE] = { .type = NLA_STRING,
@@ -1258,6 +1265,22 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr *attr)
return err;
}
+static int do_setvifinfo(struct net_device *dev, struct ifla_vif_param *ivp)
+{
+ int err = -EINVAL;
+ struct net_device *vif_dev = __dev_get_by_index(dev_net(dev),
+ ivp->vif);
+ const struct net_device_ops *ops = dev->netdev_ops;
+
+ if (ops->ndo_set_vif_param)
+ err = ops->ndo_set_vif_param(dev,
+ vif_dev,
+ ivp->vlan,
+ ivp->mac);
+
+ return err;
+}
+
static int do_set_master(struct net_device *dev, int ifindex)
{
struct net_device *master_dev;
@@ -1449,8 +1472,25 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
modified = 1;
}
}
+
err = 0;
+ if (tb[IFLA_VIFINFO_LIST]) {
+ struct nlattr *vif_param_info[IFLA_VIF_INFO_MAX + 1];
+ struct ifla_vif_param ivp;
+ err = nla_parse_nested(vif_param_info, IFLA_VIF_INFO_MAX,
+ tb[IFLA_VIFINFO_LIST], ifla_vifinfo_policy);
+ if (err < 0)
+ return err;
+ if (vif_param_info[IFLA_VIF_INFO]) {
+ nla_memcpy(&ivp, vif_param_info[IFLA_VIF_INFO], sizeof(ivp));
+ err = do_setvifinfo(dev, &ivp);
+ if (err < 0)
+ goto errout;
+ modified = 1;
+ }
+ }
+ err = 0;
if (tb[IFLA_VF_PORTS]) {
struct nlattr *port[IFLA_PORT_MAX+1];
struct nlattr *attr;
--
1.7.1
^ permalink raw reply related
* [PATCH V2 04/12] IB/ipoib: Add support for acting as VIF
From: Or Gerlitz @ 2012-08-01 17:09 UTC (permalink / raw)
To: davem; +Cc: roland, netdev, ali, sean.hefty, Erez Shitrit, Or Gerlitz
In-Reply-To: <1343840975-3252-1-git-send-email-ogerlitz@mellanox.com>
From: Erez Shitrit <erezsh@mellanox.co.il>
When IPoIB interface acts as a VIF for an eIPoIB interface, it uses
the skb cb storage area on the RX flow, to place information which
can be of use to the upper layer device.
One such usage example, is when an eIPoIB inteface needs to generate
a source mac for incoming Ethernet frames.
The IPoIB code checks the VIF private flag on the RX path, and according
to the value of the flag prepares the skb CB data, etc.
Signed-off-by: Erez Shitrit <erezsh@mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
drivers/infiniband/ulp/ipoib/ipoib.h | 5 +++
drivers/infiniband/ulp/ipoib/ipoib_cm.c | 9 +++++
drivers/infiniband/ulp/ipoib/ipoib_ib.c | 8 ++++-
drivers/infiniband/ulp/ipoib/ipoib_main.c | 21 +++++++++++
include/rdma/e_ipoib.h | 54 +++++++++++++++++++++++++++++
5 files changed, 96 insertions(+), 1 deletions(-)
create mode 100644 include/rdma/e_ipoib.h
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index 0df6668..3235033 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -52,6 +52,7 @@
#include <rdma/ib_pack.h>
#include <rdma/ib_sa.h>
#include <linux/sched.h>
+#include <rdma/e_ipoib.h>
/* constants */
@@ -209,6 +210,7 @@ struct ipoib_cm_rx {
unsigned long jiffies;
enum ipoib_cm_state state;
int recv_count;
+ u32 qpn;
};
struct ipoib_cm_tx {
@@ -703,6 +705,9 @@ extern int ipoib_recvq_size;
extern struct ib_sa_client ipoib_sa_client;
+void set_skb_oob_cb_data(struct sk_buff *skb, struct ib_wc *wc,
+ struct napi_struct *napi);
+
#ifdef CONFIG_INFINIBAND_IPOIB_DEBUG
extern int ipoib_debug_level;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 6d66ab0..c561956 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -440,6 +440,7 @@ static int ipoib_cm_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *even
struct net_device *dev = cm_id->context;
struct ipoib_dev_priv *priv = netdev_priv(dev);
struct ipoib_cm_rx *p;
+ struct ipoib_cm_data *data = event->private_data;
unsigned psn;
int ret;
@@ -452,6 +453,10 @@ static int ipoib_cm_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *even
cm_id->context = p;
p->state = IPOIB_CM_RX_LIVE;
p->jiffies = jiffies;
+
+ /* used to keep track of base qpn in CM mode */
+ p->qpn = be32_to_cpu(data->qpn);
+
INIT_LIST_HEAD(&p->list);
p->qp = ipoib_cm_create_rx_qp(dev, p);
@@ -669,6 +674,10 @@ copied:
skb->dev = dev;
/* XXX get correct PACKET_ type here */
skb->pkt_type = PACKET_HOST;
+ /* if handler is registered on top of ipoib, set skb oob data. */
+ if (skb->dev->priv_flags & IFF_EIPOIB_VIF)
+ set_skb_oob_cb_data(skb, wc, NULL);
+
netif_receive_skb(skb);
repost:
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index f10221f..f248e6e 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -304,7 +304,13 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
likely(wc->wc_flags & IB_WC_IP_CSUM_OK))
skb->ip_summed = CHECKSUM_UNNECESSARY;
- napi_gro_receive(&priv->napi, skb);
+ /* if handler is registered on top of ipoib, set skb oob data */
+ if (dev->priv_flags & IFF_EIPOIB_VIF) {
+ set_skb_oob_cb_data(skb, wc, &priv->napi);
+ /* the registered handler will take care of the skb */
+ netif_receive_skb(skb);
+ } else
+ napi_gro_receive(&priv->napi, skb);
repost:
if (unlikely(ipoib_ib_post_receive(dev, wr_id)))
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 637980b..47034b4 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -91,6 +91,24 @@ static struct ib_client ipoib_client = {
.remove = ipoib_remove_one
};
+void set_skb_oob_cb_data(struct sk_buff *skb, struct ib_wc *wc,
+ struct napi_struct *napi)
+{
+ struct ipoib_cm_rx *p_cm_ctx = NULL;
+ struct eipoib_cb_data *data = NULL;
+
+ p_cm_ctx = wc->qp->qp_context;
+ data = IPOIB_HANDLER_CB(skb);
+
+ data->rx.slid = wc->slid;
+ data->rx.sqpn = wc->src_qp;
+ data->rx.napi = napi;
+
+ /* in CM mode, use the "base" qpn as sqpn */
+ if (p_cm_ctx)
+ data->rx.sqpn = p_cm_ctx->qpn;
+}
+
int ipoib_open(struct net_device *dev)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
@@ -1253,6 +1271,9 @@ static struct net_device *ipoib_add_port(const char *format,
goto event_failed;
}
+ /* indicates pif port */
+ priv->dev->priv_flags |= IFF_EIPOIB_PIF;
+
result = register_netdev(priv->dev);
if (result) {
printk(KERN_WARNING "%s: couldn't register ipoib port %d; error %d\n",
diff --git a/include/rdma/e_ipoib.h b/include/rdma/e_ipoib.h
new file mode 100644
index 0000000..7249334
--- /dev/null
+++ b/include/rdma/e_ipoib.h
@@ -0,0 +1,54 @@
+/*
+ * Copyright (c) 2012 Mellanox Technologies. All rights reserved
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * openfabric.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _LINUX_ETH_IB_IPOIB_H
+#define _LINUX_ETH_IB_IPOIB_H
+
+#include <net/sch_generic.h>
+
+struct eipoib_cb_data {
+ /*
+ * extra care taken not to collide with the usage done
+ * by the qdisc layer in struct skb cb data.
+ */
+ struct qdisc_skb_cb qdisc_cb;
+ struct { /* must be <= 20 bytes */
+ u32 sqpn;
+ struct napi_struct *napi;
+ u16 slid;
+ u8 data[6];
+ } __packed rx;
+};
+
+#define IPOIB_HANDLER_CB(skb) ((struct eipoib_cb_data *)(skb)->cb)
+
+#endif /* _LINUX_ETH_IB_IPOIB_H */
--
1.7.1
^ permalink raw reply related
* [PATCH V2 11/12] net/eipoib: Add Makefile, Kconfig and MAINTAINERS entries
From: Or Gerlitz @ 2012-08-01 17:09 UTC (permalink / raw)
To: davem; +Cc: roland, netdev, ali, sean.hefty, Erez Shitrit, Or Gerlitz
In-Reply-To: <1343840975-3252-1-git-send-email-ogerlitz@mellanox.com>
From: Erez Shitrit <erezsh@mellanox.co.il>
Add Kconfig entry under drivers/net and MAINTAINERS entry for eIPoIB, also
add the driver makefile.
Signed-off-by: Erez Shitrit <erezsh@mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
MAINTAINERS | 6 ++++++
drivers/net/Kconfig | 15 +++++++++++++++
drivers/net/Makefile | 1 +
drivers/net/eipoib/Makefile | 4 ++++
4 files changed, 26 insertions(+), 0 deletions(-)
create mode 100644 drivers/net/eipoib/Makefile
diff --git a/MAINTAINERS b/MAINTAINERS
index bd45164..09cc33a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2645,6 +2645,12 @@ L: netdev@vger.kernel.org
S: Maintained
F: drivers/net/ethernet/ibm/ehea/
+EIPoIB (Ethernet services over IPoIB) DRIVER
+M: Erez Shitrit <erezsh@mellanox.com>
+L: netdev@vger.kernel.org
+S: Supported
+F: drivers/net/eipoib/
+
EMBEDDED LINUX
M: Paul Gortmaker <paul.gortmaker@windriver.com>
M: Matt Mackall <mpm@selenic.com>
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 0c2bd80..ba98f61 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -68,6 +68,21 @@ config DUMMY
To compile this driver as a module, choose M here: the module
will be called dummy.
+config E_IPOIB
+ tristate "Ethernet Services over IPoIB"
+ depends on INFINIBAND_IPOIB
+ ---help---
+ This driver supports Ethernet protocol over InfiniBand IPoIB devices.
+ Some services can run only on top of Ethernet L2 interfaces, and
+ cannot be bound to an IPoIB interface.
+ With this new driver, these services can run seamlessly.
+
+ Main use case of the driver is the Ethernet Virtual Switching used in
+ virtualized environments, where an eipoib netdevice can be used as a
+ Physical Interface (PIF) in the hypervisor domain, and allow other guests
+ Virtual Interfaces (VIF) connected to the same Virtual Switch to run over
+ the InfiniBand fabric.
+
config EQUALIZER
tristate "EQL (serial line load balancing) support"
---help---
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 3d375ca..2c3409e 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -31,6 +31,7 @@ obj-$(CONFIG_CAIF) += caif/
obj-$(CONFIG_CAN) += can/
obj-$(CONFIG_ETRAX_ETHERNET) += cris/
obj-$(CONFIG_NET_DSA) += dsa/
+obj-$(CONFIG_E_IPOIB) += eipoib/
obj-$(CONFIG_ETHERNET) += ethernet/
obj-$(CONFIG_FDDI) += fddi/
obj-$(CONFIG_HIPPI) += hippi/
diff --git a/drivers/net/eipoib/Makefile b/drivers/net/eipoib/Makefile
new file mode 100644
index 0000000..b64e96e
--- /dev/null
+++ b/drivers/net/eipoib/Makefile
@@ -0,0 +1,4 @@
+obj-$(CONFIG_E_IPOIB) := eth_ipoib.o
+eth_ipoib-y := eth_ipoib_main.o \
+ eth_ipoib_sysfs.o \
+ eth_ipoib_ethtool.o
--
1.7.1
^ permalink raw reply related
* [PATCH V2 02/12] IB/ipoib: Add support for clones / multiple childs on the same partition
From: Or Gerlitz @ 2012-08-01 17:09 UTC (permalink / raw)
To: davem; +Cc: roland, netdev, ali, sean.hefty, Or Gerlitz, Erez Shitrit
In-Reply-To: <1343840975-3252-1-git-send-email-ogerlitz@mellanox.com>
Allow creating "clone" child interfaces which further partition an
IPoIB interface to sub interfaces who either use the same pkey as
their parent or use the same pkey as already created child interface.
Each child now has a child index, which together with the pkey is
used as the identifier of the created network device.
Clone interfaces can only be created using rtnl_link_ops, where the user
is allowed to provide a pkey and index. If no pkey is provided, the
parent pkey is used and if no index is provided an index of zero
is used.
A major use case for clone childs is for virtualization purposes, where
a per VM NIC is desired at the hypervisor level, such as the solution
provided by the newly introduced Ethernet IPoIB driver.
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Erez Shitrit <erezsh@mellanox.co.il>
---
Documentation/infiniband/ipoib.txt | 12 ++++++++++++
drivers/infiniband/ulp/ipoib/ipoib.h | 7 +++++--
drivers/infiniband/ulp/ipoib/ipoib_netlink.c | 21 +++++++++++++++------
drivers/infiniband/ulp/ipoib/ipoib_vlan.c | 19 +++++++++++--------
4 files changed, 43 insertions(+), 16 deletions(-)
diff --git a/Documentation/infiniband/ipoib.txt b/Documentation/infiniband/ipoib.txt
index f2cfe26..6ef87bb 100644
--- a/Documentation/infiniband/ipoib.txt
+++ b/Documentation/infiniband/ipoib.txt
@@ -27,6 +27,18 @@ Partitions and P_Keys
Child interface create/delete can also be done using IPoIB's
rtnl_link_ops, where childs created using either way behave the same.
+Clones
+ Its possible to further partition an IPoIB interfaces, and create
+ "clone" child interfaces which either use the same pkey as their
+ parent, or as an already created child interface. Each child now has
+ a child index, which together with the pkey is used as the identifier
+ of the created network device.
+
+ Clone interfaces can only be created using rtnl_link_ops, where the user
+ is allowed to provide a pkey and index. If no pkey is provided, the
+ parent pkey is used and if no index is provided an index of zero
+ is used.
+
Datagram vs Connected modes
The IPoIB driver supports two modes of operation: datagram and
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index adcfa66..0df6668 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -332,6 +332,7 @@ struct ipoib_dev_priv {
struct net_device *parent;
struct list_head child_intfs;
struct list_head list;
+ u16 child_index;
#ifdef CONFIG_INFINIBAND_IPOIB_CM
struct ipoib_cm_dev_priv cm;
@@ -493,8 +494,10 @@ void ipoib_event(struct ib_event_handler *handler,
int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey);
int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey);
-int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv, u16 pkey);
-struct net_device * __ipoib_vlan_delete(struct net_device *pdev, u16 pkey);
+int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv,
+ u16 pkey, u16 child_index);
+struct net_device * __ipoib_vlan_delete(struct net_device *pdev, u16 pkey,
+ u16 child_index);
int __init ipoib_netlink_init(void);
void __exit ipoib_netlink_fini(void);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c
index 2b8905e..d902e04 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c
@@ -38,6 +38,7 @@
enum {
IFLA_IPOIB_UNSPEC,
IFLA_IPOIB_CHILD_PKEY,
+ IFLA_IPOIB_CHILD_INDEX,
__IFLA_IPOIB_MAX
};
@@ -45,6 +46,7 @@ enum {
static const struct nla_policy ipoib_policy[IFLA_IPOIB_MAX + 1] = {
[IFLA_IPOIB_CHILD_PKEY] = { .type = NLA_U16 },
+ [IFLA_IPOIB_CHILD_INDEX] = { .type = NLA_U16 },
};
static int ipoib_new_child_link(struct net *src_net, struct net_device *dev,
@@ -52,7 +54,7 @@ static int ipoib_new_child_link(struct net *src_net, struct net_device *dev,
{
struct net_device *pdev;
struct ipoib_dev_priv *ppriv;
- u16 child_pkey;
+ u16 child_pkey, child_index;
int err;
if (!tb[IFLA_LINK])
@@ -64,12 +66,18 @@ static int ipoib_new_child_link(struct net *src_net, struct net_device *dev,
ppriv = netdev_priv(pdev);
if (!data || !data[IFLA_IPOIB_CHILD_PKEY]) {
- ipoib_warn(ppriv, "no pkey specified, failing request\n");
- return -EINVAL;
+ ipoib_warn(ppriv, "no pkey specified, using parent pkey\n");
+ child_pkey = ppriv->pkey;
} else
child_pkey = nla_get_u16(data[IFLA_IPOIB_CHILD_PKEY]);
- err = __ipoib_vlan_add(ppriv, netdev_priv(dev), child_pkey);
+ if (!data || !data[IFLA_IPOIB_CHILD_INDEX]) {
+ ipoib_warn(ppriv, "no index specified, using 0\n");
+ child_index = 0;
+ } else
+ child_index = nla_get_u16(data[IFLA_IPOIB_CHILD_INDEX]);
+
+ err = __ipoib_vlan_add(ppriv, netdev_priv(dev), child_pkey, child_index);
return err;
}
@@ -78,12 +86,13 @@ static void ipoib_unregister_child_dev(struct net_device *dev, struct list_head
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
- (void)__ipoib_vlan_delete(priv->parent, priv->pkey);
+ (void)__ipoib_vlan_delete(priv->parent, priv->pkey, priv->child_index);
}
static size_t ipoib_get_size(const struct net_device *dev)
{
- return nla_total_size(2); /* IFLA_IPOIB_CHILD_PKEY */
+ return nla_total_size(2) + /* IFLA_IPOIB_CHILD_PKEY */
+ nla_total_size(2); /* IFLA_IPOIB_CHILD_INDEX */
}
static struct rtnl_link_ops ipoib_link_ops __read_mostly = {
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
index 4a9b7e6..5f6e07d 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
@@ -51,7 +51,7 @@ static DEVICE_ATTR(parent, S_IRUGO, show_parent, NULL);
int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv,
- u16 pkey)
+ u16 pkey, u16 child_index)
{
int result;
struct ipoib_dev_priv *tpriv;
@@ -60,15 +60,16 @@ int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv,
/*
* First ensure this isn't a duplicate. We check the parent device and
- * then all of the child interfaces to make sure the Pkey doesn't match.
+ * then all of the child interfaces to make sure the Pkey AND the child
+ * index don't match.
*/
- if (ppriv->pkey == pkey) {
+ if (ppriv->pkey == pkey && ppriv->child_index == child_index) {
result = -ENOTUNIQ;
goto err;
}
list_for_each_entry(tpriv, &ppriv->child_intfs, list) {
- if (tpriv->pkey == pkey) {
+ if (tpriv->pkey == pkey && tpriv->child_index == child_index) {
result = -ENOTUNIQ;
goto err;
}
@@ -85,6 +86,7 @@ int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv,
goto err;
priv->pkey = pkey;
+ priv->child_index = child_index;
memcpy(priv->dev->dev_addr, ppriv->dev->dev_addr, INFINIBAND_ALEN);
priv->dev->broadcast[8] = pkey >> 8;
@@ -156,7 +158,7 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
if (!rtnl_trylock())
return restart_syscall();
- result = __ipoib_vlan_add(ppriv, priv, pkey);
+ result = __ipoib_vlan_add(ppriv, priv, pkey, 0);
if (result)
free_netdev(priv->dev);
@@ -166,7 +168,8 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
return result;
}
-struct net_device * __ipoib_vlan_delete(struct net_device *pdev, u16 pkey)
+struct net_device * __ipoib_vlan_delete(struct net_device *pdev, u16 pkey,
+ u16 child_index)
{
struct ipoib_dev_priv *ppriv, *priv, *tpriv;
struct net_device *dev = NULL;
@@ -175,7 +178,7 @@ struct net_device * __ipoib_vlan_delete(struct net_device *pdev, u16 pkey)
mutex_lock(&ppriv->vlan_mutex);
list_for_each_entry_safe(priv, tpriv, &ppriv->child_intfs, list) {
- if (priv->pkey == pkey) {
+ if (priv->pkey == pkey && priv->child_index == child_index) {
unregister_netdevice(priv->dev);
ipoib_dev_cleanup(priv->dev);
list_del(&priv->list);
@@ -197,7 +200,7 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey)
if (!rtnl_trylock())
return restart_syscall();
- dev = __ipoib_vlan_delete(pdev, pkey);
+ dev = __ipoib_vlan_delete(pdev, pkey, 0);
rtnl_unlock();
if (dev) {
--
1.7.1
^ permalink raw reply related
* [PATCH V2 05/12] net: Add ndo_set_vif_param operation to serve eIPoIB VIFs
From: Or Gerlitz @ 2012-08-01 17:09 UTC (permalink / raw)
To: davem; +Cc: roland, netdev, ali, sean.hefty, Erez Shitrit, Or Gerlitz
In-Reply-To: <1343840975-3252-1-git-send-email-ogerlitz@mellanox.com>
From: Erez Shitrit <erezsh@mellanox.co.il>
The Ethernet IPoIB driver enslaves IPoIB devices and uses them as
VIFs (Virtual Interface) which serve an Ethernet NIC e.g present in a
guest OS. For each such slave that acts as a VIF, eIPoIB needs to know
the mac and optionally the vlan uses by that NIC, the new ndo opertaion
is used to associate the mac/vlan for that slave.
Signed-off-by: Erez Shitrit <erezsh@mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
include/linux/netdevice.h | 5 ++++-
1 files changed, 4 insertions(+), 1 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index eb06e58..2709551 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1013,7 +1013,10 @@ struct net_device_ops {
netdev_features_t features);
int (*ndo_neigh_construct)(struct neighbour *n);
void (*ndo_neigh_destroy)(struct neighbour *n);
-
+ int (*ndo_set_vif_param) (struct net_device *dev,
+ struct net_device *vif,
+ u16 vlan,
+ u8 *mac);
int (*ndo_fdb_add)(struct ndmsg *ndm,
struct net_device *dev,
unsigned char *addr,
--
1.7.1
^ permalink raw reply related
* [PATCH V2 01/12] IB/ipoib: Add rtnl_link_ops support
From: Or Gerlitz @ 2012-08-01 17:09 UTC (permalink / raw)
To: davem; +Cc: roland, netdev, ali, sean.hefty, Or Gerlitz, Erez Shitrit
In-Reply-To: <1343840975-3252-1-git-send-email-ogerlitz@mellanox.com>
Add rtnl_link_ops to IPoIB, with the first usage being child device
create/delete through them. For that end, did little refactoring
of the ipoib_vlan_add/delete code which is now used by both the
sysfs and the rtnl_link_ops code.
Signed-off-by: Erez Shitrit <erezsh@mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
Documentation/infiniband/ipoib.txt | 3 +
drivers/infiniband/ulp/ipoib/Makefile | 3 +-
drivers/infiniband/ulp/ipoib/ipoib.h | 8 ++
drivers/infiniband/ulp/ipoib/ipoib_main.c | 10 ++-
drivers/infiniband/ulp/ipoib/ipoib_netlink.c | 110 ++++++++++++++++++++++++++
drivers/infiniband/ulp/ipoib/ipoib_vlan.c | 80 ++++++++++++-------
6 files changed, 181 insertions(+), 33 deletions(-)
create mode 100644 drivers/infiniband/ulp/ipoib/ipoib_netlink.c
diff --git a/Documentation/infiniband/ipoib.txt b/Documentation/infiniband/ipoib.txt
index 64eeb55..f2cfe26 100644
--- a/Documentation/infiniband/ipoib.txt
+++ b/Documentation/infiniband/ipoib.txt
@@ -24,6 +24,9 @@ Partitions and P_Keys
The P_Key for any interface is given by the "pkey" file, and the
main interface for a subinterface is in "parent."
+ Child interface create/delete can also be done using IPoIB's
+ rtnl_link_ops, where childs created using either way behave the same.
+
Datagram vs Connected modes
The IPoIB driver supports two modes of operation: datagram and
diff --git a/drivers/infiniband/ulp/ipoib/Makefile b/drivers/infiniband/ulp/ipoib/Makefile
index 3090100..e5430dd 100644
--- a/drivers/infiniband/ulp/ipoib/Makefile
+++ b/drivers/infiniband/ulp/ipoib/Makefile
@@ -5,7 +5,8 @@ ib_ipoib-y := ipoib_main.o \
ipoib_multicast.o \
ipoib_verbs.o \
ipoib_vlan.o \
- ipoib_ethtool.o
+ ipoib_ethtool.o \
+ ipoib_netlink.o
ib_ipoib-$(CONFIG_INFINIBAND_IPOIB_CM) += ipoib_cm.o
ib_ipoib-$(CONFIG_INFINIBAND_IPOIB_DEBUG) += ipoib_fs.o
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index 86df632..adcfa66 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -493,6 +493,14 @@ void ipoib_event(struct ib_event_handler *handler,
int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey);
int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey);
+int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv, u16 pkey);
+struct net_device * __ipoib_vlan_delete(struct net_device *pdev, u16 pkey);
+
+int __init ipoib_netlink_init(void);
+void __exit ipoib_netlink_fini(void);
+
+void ipoib_setup(struct net_device *dev);
+
void ipoib_pkey_poll(struct work_struct *work);
int ipoib_pkey_dev_delay_open(struct net_device *dev);
void ipoib_drain_cq(struct net_device *dev);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index bbee4b2..637980b 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -995,7 +995,7 @@ static const struct net_device_ops ipoib_netdev_ops = {
.ndo_neigh_setup = ipoib_neigh_setup_dev,
};
-static void ipoib_setup(struct net_device *dev)
+void ipoib_setup(struct net_device *dev)
{
struct ipoib_dev_priv *priv = netdev_priv(dev);
@@ -1402,8 +1402,15 @@ static int __init ipoib_init_module(void)
if (ret)
goto err_sa;
+ ret = ipoib_netlink_init();
+ if (ret)
+ goto err_client;
+
return 0;
+err_client:
+ ib_unregister_client(&ipoib_client);
+
err_sa:
ib_sa_unregister_client(&ipoib_sa_client);
destroy_workqueue(ipoib_workqueue);
@@ -1416,6 +1423,7 @@ err_fs:
static void __exit ipoib_cleanup_module(void)
{
+ ipoib_netlink_fini();
ib_unregister_client(&ipoib_client);
ib_sa_unregister_client(&ipoib_sa_client);
ipoib_unregister_debugfs();
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c
new file mode 100644
index 0000000..2b8905e
--- /dev/null
+++ b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c
@@ -0,0 +1,110 @@
+/*
+ * Copyright (c) 2012 Mellanox Technologies. - All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/netdevice.h>
+#include <linux/module.h>
+#include <net/rtnetlink.h>
+#include "ipoib.h"
+
+enum {
+ IFLA_IPOIB_UNSPEC,
+ IFLA_IPOIB_CHILD_PKEY,
+ __IFLA_IPOIB_MAX
+};
+
+#define IFLA_IPOIB_MAX (__IFLA_IPOIB_MAX - 1)
+
+static const struct nla_policy ipoib_policy[IFLA_IPOIB_MAX + 1] = {
+ [IFLA_IPOIB_CHILD_PKEY] = { .type = NLA_U16 },
+};
+
+static int ipoib_new_child_link(struct net *src_net, struct net_device *dev,
+ struct nlattr *tb[], struct nlattr *data[])
+{
+ struct net_device *pdev;
+ struct ipoib_dev_priv *ppriv;
+ u16 child_pkey;
+ int err;
+
+ if (!tb[IFLA_LINK])
+ return -EINVAL;
+
+ pdev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK]));
+ if (!pdev)
+ return -ENODEV;
+ ppriv = netdev_priv(pdev);
+
+ if (!data || !data[IFLA_IPOIB_CHILD_PKEY]) {
+ ipoib_warn(ppriv, "no pkey specified, failing request\n");
+ return -EINVAL;
+ } else
+ child_pkey = nla_get_u16(data[IFLA_IPOIB_CHILD_PKEY]);
+
+ err = __ipoib_vlan_add(ppriv, netdev_priv(dev), child_pkey);
+
+ return err;
+}
+
+static void ipoib_unregister_child_dev(struct net_device *dev, struct list_head *head)
+{
+ struct ipoib_dev_priv *priv = netdev_priv(dev);
+
+ (void)__ipoib_vlan_delete(priv->parent, priv->pkey);
+}
+
+static size_t ipoib_get_size(const struct net_device *dev)
+{
+ return nla_total_size(2); /* IFLA_IPOIB_CHILD_PKEY */
+}
+
+static struct rtnl_link_ops ipoib_link_ops __read_mostly = {
+ .kind = "ipoib",
+ .maxtype = IFLA_IPOIB_MAX,
+ .policy = ipoib_policy,
+ .priv_size = sizeof(struct ipoib_dev_priv),
+ .setup = ipoib_setup,
+ .newlink = ipoib_new_child_link,
+ .dellink = ipoib_unregister_child_dev,
+ .get_size = ipoib_get_size,
+};
+
+int __init ipoib_netlink_init(void)
+{
+ return rtnl_link_register(&ipoib_link_ops);
+}
+
+void __exit ipoib_netlink_fini(void)
+{
+ rtnl_link_unregister(&ipoib_link_ops);
+}
+
+MODULE_ALIAS_RTNL_LINK("ipoib");
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
index d7e9740..4a9b7e6 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
@@ -49,19 +49,13 @@ static ssize_t show_parent(struct device *d, struct device_attribute *attr,
}
static DEVICE_ATTR(parent, S_IRUGO, show_parent, NULL);
-int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
+
+int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv,
+ u16 pkey)
{
- struct ipoib_dev_priv *ppriv, *priv;
- char intf_name[IFNAMSIZ];
int result;
+ struct ipoib_dev_priv *tpriv;
- if (!capable(CAP_NET_ADMIN))
- return -EPERM;
-
- ppriv = netdev_priv(pdev);
-
- if (!rtnl_trylock())
- return restart_syscall();
mutex_lock(&ppriv->vlan_mutex);
/*
@@ -70,26 +64,16 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
*/
if (ppriv->pkey == pkey) {
result = -ENOTUNIQ;
- priv = NULL;
goto err;
}
- list_for_each_entry(priv, &ppriv->child_intfs, list) {
- if (priv->pkey == pkey) {
+ list_for_each_entry(tpriv, &ppriv->child_intfs, list) {
+ if (tpriv->pkey == pkey) {
result = -ENOTUNIQ;
- priv = NULL;
goto err;
}
}
- snprintf(intf_name, sizeof intf_name, "%s.%04x",
- ppriv->dev->name, pkey);
- priv = ipoib_intf_alloc(intf_name);
- if (!priv) {
- result = -ENOMEM;
- goto err;
- }
-
priv->max_ib_mtu = ppriv->max_ib_mtu;
/* MTU will be reset when mcast join happens */
priv->dev->mtu = IPOIB_UD_MTU(priv->max_ib_mtu);
@@ -137,11 +121,10 @@ int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
list_add_tail(&priv->list, &ppriv->child_intfs);
mutex_unlock(&ppriv->vlan_mutex);
- rtnl_unlock();
-
return 0;
sysfs_failed:
+ result = -ENOMEM;
ipoib_delete_debug_files(priv->dev);
unregister_netdevice(priv->dev);
@@ -150,25 +133,46 @@ register_failed:
err:
mutex_unlock(&ppriv->vlan_mutex);
- rtnl_unlock();
- if (priv)
- free_netdev(priv->dev);
-
return result;
}
-int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey)
+int ipoib_vlan_add(struct net_device *pdev, unsigned short pkey)
{
- struct ipoib_dev_priv *ppriv, *priv, *tpriv;
- struct net_device *dev = NULL;
+ struct ipoib_dev_priv *ppriv, *priv;
+ char intf_name[IFNAMSIZ];
+ int result;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
ppriv = netdev_priv(pdev);
+ snprintf(intf_name, sizeof intf_name, "%s.%04x",
+ ppriv->dev->name, pkey);
+ priv = ipoib_intf_alloc(intf_name);
+ if (!priv)
+ return -ENOMEM;
+
if (!rtnl_trylock())
return restart_syscall();
+
+ result = __ipoib_vlan_add(ppriv, priv, pkey);
+
+ if (result)
+ free_netdev(priv->dev);
+
+ rtnl_unlock();
+
+ return result;
+}
+
+struct net_device * __ipoib_vlan_delete(struct net_device *pdev, u16 pkey)
+{
+ struct ipoib_dev_priv *ppriv, *priv, *tpriv;
+ struct net_device *dev = NULL;
+
+ ppriv = netdev_priv(pdev);
+
mutex_lock(&ppriv->vlan_mutex);
list_for_each_entry_safe(priv, tpriv, &ppriv->child_intfs, list) {
if (priv->pkey == pkey) {
@@ -180,6 +184,20 @@ int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey)
}
}
mutex_unlock(&ppriv->vlan_mutex);
+
+ return dev;
+}
+
+int ipoib_vlan_delete(struct net_device *pdev, unsigned short pkey)
+{
+ struct net_device *dev;
+
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+
+ if (!rtnl_trylock())
+ return restart_syscall();
+ dev = __ipoib_vlan_delete(pdev, pkey);
rtnl_unlock();
if (dev) {
--
1.7.1
^ permalink raw reply related
* [PATCH V2 08/12] net/eipoib: Add ethtool file support
From: Or Gerlitz @ 2012-08-01 17:09 UTC (permalink / raw)
To: davem; +Cc: roland, netdev, ali, sean.hefty, Erez Shitrit, Or Gerlitz
In-Reply-To: <1343840975-3252-1-git-send-email-ogerlitz@mellanox.com>
From: Erez Shitrit <erezsh@mellanox.co.il>
Via ethtool the driver describes its version, ABI version, on what PIF
interface it runs and various statistics.
Signed-off-by: Erez Shitrit <erezsh@mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
drivers/net/eipoib/eth_ipoib_ethtool.c | 114 ++++++++++++++++++++++++++++++++
1 files changed, 114 insertions(+), 0 deletions(-)
create mode 100644 drivers/net/eipoib/eth_ipoib_ethtool.c
diff --git a/drivers/net/eipoib/eth_ipoib_ethtool.c b/drivers/net/eipoib/eth_ipoib_ethtool.c
new file mode 100644
index 0000000..0731d94
--- /dev/null
+++ b/drivers/net/eipoib/eth_ipoib_ethtool.c
@@ -0,0 +1,114 @@
+/*
+ * Copyright (c) 2012 Mellanox Technologies. All rights reserved
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * openfabric.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include "eth_ipoib.h"
+
+static void parent_ethtool_get_drvinfo(struct net_device *parent_dev,
+ struct ethtool_drvinfo *drvinfo)
+{
+ struct parent *parent = netdev_priv(parent_dev);
+
+ strncpy(drvinfo->driver, DRV_NAME, 32);
+
+ strncpy(drvinfo->version, DRV_VERSION, 32);
+
+ strncpy(drvinfo->bus_info, parent->ipoib_main_interface,
+ ETHTOOL_BUSINFO_LEN);
+
+ /* indicates ABI version */
+ snprintf(drvinfo->fw_version, 32, "%d", EIPOIB_ABI_VER);
+}
+
+static const char parent_strings[][ETH_GSTRING_LEN] = {
+ /* private statistics */
+ "tx_parent_dropped",
+ "tx_vif_miss",
+ "tx_neigh_miss",
+ "tx_vlan",
+ "tx_shared",
+ "tx_proto_errors",
+ "tx_skb_errors",
+ "tx_slave_err",
+
+ "rx_parent_dropped",
+ "rx_vif_miss",
+ "rx_neigh_miss",
+ "rx_vlan",
+ "rx_shared",
+ "rx_proto_errors",
+ "rx_skb_errors",
+ "rx_slave_err",
+};
+
+#define PORT_STATS_LEN (sizeof(parent_strings) / ETH_GSTRING_LEN)
+
+static void parent_get_strings(struct net_device *parent_dev,
+ uint32_t stringset, uint8_t *data)
+{
+ if (stringset != ETH_SS_STATS)
+ return;
+ memcpy(data, parent_strings, sizeof(parent_strings));
+}
+
+static void parent_get_ethtool_stats(struct net_device *parent_dev,
+ struct ethtool_stats *stats,
+ uint64_t *data)
+{
+ struct parent *parent = netdev_priv(parent_dev);
+
+ read_lock_bh(&parent->lock);
+ memcpy(data, &parent->port_stats, sizeof(parent->port_stats));
+ read_unlock_bh(&parent->lock);
+}
+
+static int parent_get_sset_count(struct net_device *parent_dev, int sset)
+{
+ switch (sset) {
+ case ETH_SS_STATS:
+ return PORT_STATS_LEN;
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
+static const struct ethtool_ops parent_ethtool_ops = {
+ .get_drvinfo = parent_ethtool_get_drvinfo,
+ .get_strings = parent_get_strings,
+ .get_ethtool_stats = parent_get_ethtool_stats,
+ .get_sset_count = parent_get_sset_count,
+ .get_link = ethtool_op_get_link,
+};
+
+void parent_set_ethtool_ops(struct net_device *dev)
+{
+ SET_ETHTOOL_OPS(dev, &parent_ethtool_ops);
+}
--
1.7.1
^ permalink raw reply related
* [PATCH V2 07/12] net/eipoib: Add private header file
From: Or Gerlitz @ 2012-08-01 17:09 UTC (permalink / raw)
To: davem; +Cc: roland, netdev, ali, sean.hefty, Erez Shitrit, Or Gerlitz
In-Reply-To: <1343840975-3252-1-git-send-email-ogerlitz@mellanox.com>
From: Erez Shitrit <erezsh@mellanox.co.il>
The header file includes all structures, macros and non-static
functions which are of use by the driver.
Signed-off-by: Erez Shitrit <erezsh@mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
drivers/net/eipoib/eth_ipoib.h | 215 ++++++++++++++++++++++++++++++++++++++++
1 files changed, 215 insertions(+), 0 deletions(-)
create mode 100644 drivers/net/eipoib/eth_ipoib.h
diff --git a/drivers/net/eipoib/eth_ipoib.h b/drivers/net/eipoib/eth_ipoib.h
new file mode 100644
index 0000000..9a23f7d
--- /dev/null
+++ b/drivers/net/eipoib/eth_ipoib.h
@@ -0,0 +1,215 @@
+/*
+ * Copyright (c) 2012 Mellanox Technologies. All rights reserved
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * openfabric.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef _LINUX_ETH_IPOIB_H
+#define _LINUX_ETH_IPOIB_H
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+#include <net/arp.h>
+#include <linux/if_vlan.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <linux/if_infiniband.h>
+#include <rdma/ib_verbs.h>
+
+#include <rdma/e_ipoib.h>
+
+/* macros and definitions */
+#define DRV_VERSION "1.0.0"
+#define DRV_RELDATE "June 1, 2012"
+#define DRV_NAME "eth_ipoib"
+#define SDRV_NAME "ipoib"
+#define DRV_DESCRIPTION "IP-over-InfiniBand Para Virtualized Driver"
+#define EIPOIB_ABI_VER 1
+
+#undef pr_fmt
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#define GID_LEN 16
+#define GUID_LEN 8
+
+#define PARENT_VLAN_FEATURES (NETIF_F_HW_VLAN_RX | NETIF_F_HW_VLAN_TX)
+
+#define parent_for_each_slave(_parent, slave) \
+ list_for_each_entry(slave, &(_parent)->slave_list, list)\
+
+#define PARENT_IS_OK(_parent) \
+ (((_parent)->dev->flags & IFF_UP) && \
+ netif_running((_parent)->dev) && \
+ ((_parent)->slave_cnt > 0))
+
+#define IS_E_IPOIB_PROTO(_proto) \
+ (((_proto) == htons(ETH_P_ARP)) || \
+ ((_proto) == htons(ETH_P_RARP)) || \
+ ((_proto) == htons(ETH_P_IP)))
+
+enum eipoib_emac_guest_info {
+ VALID,
+ MIGRATED_OUT,
+ INVALID,
+};
+
+/* structs */
+struct eth_arp_data {
+ u8 arp_sha[ETH_ALEN];
+ __be32 arp_sip;
+ u8 arp_dha[ETH_ALEN];
+ __be32 arp_dip;
+} __packed;
+
+struct ipoib_arp_data {
+ u8 arp_sha[INFINIBAND_ALEN];
+ __be32 arp_sip;
+ u8 arp_dha[INFINIBAND_ALEN];
+ __be32 arp_dip;
+} __packed;
+
+/* live migration support structures: */
+struct ip_member {
+ __be32 ip;
+ struct list_head list;
+};
+
+/*
+ * for each slave (emac) saves all the ip over that mac.
+ * the parent keeps that list for live migration.
+ */
+struct guest_emac_info {
+ u8 emac[ETH_ALEN];
+ u16 vlan;
+ struct list_head ip_list;
+ struct list_head list;
+ enum eipoib_emac_guest_info rec_state;
+ int num_of_retries;
+};
+
+struct neigh {
+ struct list_head list;
+ u8 emac[ETH_ALEN];
+ u8 imac[INFINIBAND_ALEN];
+ /* this part is used for neigh_add_list */
+ char cmd[PAGE_SIZE];
+};
+
+struct slave {
+ struct net_device *dev;
+ struct list_head list;
+ u16 pkey;
+ u16 vlan;
+ u8 emac[ETH_ALEN];
+ u8 imac[INFINIBAND_ALEN];
+ struct list_head neigh_list;
+};
+
+struct port_stats {
+ /* update PORT_STATS_LEN (number of stat fields)accordingly */
+ uint64_t tx_parent_dropped;
+ uint64_t tx_vif_miss;
+ uint64_t tx_neigh_miss;
+ uint64_t tx_vlan;
+ uint64_t tx_shared;
+ uint64_t tx_proto_errors;
+ uint64_t tx_skb_errors;
+ uint64_t tx_slave_err;
+
+ uint64_t rx_parent_dropped;
+ uint64_t rx_vif_miss;
+ uint64_t rx_neigh_miss;
+ uint64_t rx_vlan;
+ uint64_t rx_shared;
+ uint64_t rx_proto_errors;
+ uint64_t rx_skb_errors;
+ uint64_t rx_slave_err;
+};
+
+struct parent {
+ struct net_device *dev;
+ int index;
+ struct neigh_parms nparms;
+ struct list_head slave_list;
+ /* never change this value outside the attach/detach wrappers */
+ s32 slave_cnt;
+ rwlock_t lock;
+ struct port_stats port_stats;
+ struct list_head parent_list;
+ u16 flags;
+ struct workqueue_struct *wq;
+ s8 kill_timers;
+ struct delayed_work neigh_learn_work;
+ struct delayed_work vif_learn_work;
+ struct list_head neigh_add_list;
+ union ib_gid gid;
+ char ipoib_main_interface[IFNAMSIZ];
+ /* live migration and bonding support */
+ struct list_head emac_ip_list;
+ struct delayed_work emac_ip_work;
+ struct delayed_work migrate_out_work;
+};
+
+#define eipoib_slave_get_rcu(dev) \
+ ((struct slave *) rcu_dereference(dev->rx_handler_data))
+
+/* name space support for sys/fs */
+struct eipoib_net {
+ struct net *net; /* Associated network namespace */
+ struct class_attribute class_attr_eipoib_interfaces;
+};
+
+/* exported from main.c */
+extern int eipoib_net_id;
+extern struct list_head parent_dev_list;
+
+/* functions prototypes */
+int mod_create_sysfs(struct eipoib_net *eipoib_n);
+void mod_destroy_sysfs(struct eipoib_net *eipoib_n);
+void parent_destroy_sysfs_entry(struct parent *parent);
+int parent_create_sysfs_entry(struct parent *parent);
+int create_slave_symlinks(struct net_device *master,
+ struct net_device *slave);
+void destroy_slave_symlinks(struct net_device *master,
+ struct net_device *slave);
+int parent_enslave(struct net_device *parent_dev,
+ struct net_device *slave_dev);
+int parent_release_slave(struct net_device *parent_dev,
+ struct net_device *slave_dev);
+struct neigh *parent_get_neigh_cmd(char op, char *ifname,
+ u8 *remac, u8 *rimac);
+struct slave *parent_get_vif_cmd(char op, char *ifname, u8 *lemac);
+ssize_t __parent_store_neighs(struct device *d,
+ struct device_attribute *attr,
+ const char *buffer, size_t count);
+void parent_set_ethtool_ops(struct net_device *dev);
+
+#endif /* _LINUX_ETH_IPOIB_H */
--
1.7.1
^ permalink raw reply related
* [PATCH V2 00/12] Add Ethernet IPoIB driver
From: Or Gerlitz @ 2012-08-01 17:09 UTC (permalink / raw)
To: davem; +Cc: roland, netdev, ali, sean.hefty, Or Gerlitz, Erez Shitrit
Changes from V1:
- applied feedback from Ben H.
- add stats64
- use memcpy on ethtool
- remove double indexing on ethtool and unused variables
- remove extra tab ...
- remove HW_VLAN_FILTER and the add/kill_vid ndo entries
- applied feedback from Dave Miller to avoid using sysfs
- added rtnl_link_ops support in ipoib and use them to add/delete childs
- added usage to ndo_add/remove_slave in eipoib
- added support for eipoib VIFs in rtnetlink and new ndo op to configure
that to the eipoib device
- some more little cleanups of unused variables
changes from V0:
- applied feedback from Eric/Dave - RX flow uses only the last 20 bytes of skb->cb[]
- applied feedback from Ben H. on ethtool changes
- fix sparse error on function which should be made static
- made the netdev features related code of the driver more elegant/robust
- used _bh locking in some paths which used plain rw locking in V0
- some code rearrangements in flows that send ARPs
The eIPoIB driver provides a standard Ethernet netdevice over
the InfiniBand IPoIB interface.
Some services can run only on top of Ethernet L2 interfaces, and cannot be
bound to an IPoIB interface. With this new driver, these services can run
seamlessly.
Main use case of the driver is the Ethernet Virtual Switching used in
virtualized environments, where an eipoib netdevice can be used as a
Physical Interface (PIF) in the hypervisor domain, and allow other
guests Virtual Interfaces (VIF) connected to the same Virtual Switch
to run over the InfiniBand fabric.
This driver supports L2 Switching (Direct Bridging) as well as other L3
Switching modes (e.g. NAT).
Whenever an IPoIB interface is created, one eIPoIB PIF netdevice
will be created. The default naming scheme is as in other Ethernet
interfaces: ethX, for example, on a system with two IPoIB interfaces,
ib0 and ib1, two interfaces will be created ethX and ethX+1 When "X"
is the next free Ethernet number in the system.
Using "ethtool -i " over the new interface can tell on which IPoIB
PIF interface that interface is above. For example: driver: eth_ipoib:ib0
indicates that eth3 is the Ethernet interface over the ib0 IPoIB interface.
The driver can be used as independent interface or to serve in
virtualization environment as the physical layer for the virtual
interfaces on the virtual guest.
The driver interface (eipoib interface or which is also referred to as parent)
uses slave interfaces, IPoIB clones, which are the VIFs described above.
VIFs interfaces are enslaved/released from the eipoib driver on demand, according
to the management interface provided to user space.
The management interface for the driver uses rtnl interface. Via these interfaces
the driver gets details on new VIF's to manage. The driver can
enslave new VIF (IPoIB cloned interface) or detaches from it.
The driver can also configure the slave to support specific mac/vlan of virtual guest.
Here's an example script on how the managment interface looks
like with the new rtnetlink code we added, this is based
on a patch to iproute2 which will be posted once the interface
is agreed.
#!/bin/bash
# create IPoIB clone (ib0.1), enslave it to eIPoIB (eth4), add VIF to
# serve the master, the provided MAC is the master's one
ip link add link ib0 name ib0.1 type ipoib index 1
ip link set dev ib0.1 master eth4
ip link set dev eth4 vif ib0.1 mac 00:02:C9:43:3B:F1
# add a bridge whose uplink is the eIPOIB device
brctl addbr br2
brctl addif br2 eth4
ifconfig br2 12.134.41.1/16 up
# create IPoIB clone (ib0.2), enslave it to eIPoIB (eth4), add VIF to
# serve a guest, the provided MAC is the guest's one, vnet1 is a hypervisor
# NIC (e.g tap) that serves that guest
ip link add link ib0 name ib0.2 type ipoib index 2
ip link set dev ib0.2 master eth4
ip link set dev eth4 vif ib0.2 mac 52:54:00:67:E9:BD
brctl addif br2 vnet1
# repeat the above with vlan
ip link add link ib0 name ib0.8003 type ipoib pkey 0x8003
ip link set dev ib0.8003 master eth4
ip link set dev eth4 vif ib0.8003 mac 00:02:C9:43:3B:F1 vlan 3
vconfig add eth4 3
ifconfig eth4.3 up
brctl addbr br3
brctl addif br3 eth4.3
ifconfig br3 13.134.41.1/16 up
ip link add link ib0 name ib0.8003.1 type ipoib pkey 0x8003 index 1
ip link set dev ib0.8003.1 master eth4
ip link set dev eth4 vif ib0.8003.1 mac 52:54:00:DE:3A:23 vlan 3
cat /sys/class/net/eth4/eth/vifs
============= END OF SCRIPT =======
Note: Each ethX interface has at least one ibX.Y slave to serve the PIF
itself, in the VIFs list of ethX you'll notice that ibX.1 is always created
to serve applications running from the Hypervisor on top of ethX interface directly.
For IB applications that require native IPoIB interfaces (e.g. RDMA-CM), the
original ipoib interfaces ibX can still be used. For example, RDMA-CM and
eth_ipoib drivers can co-exist and make use of IPoIB
The last patch of this series was made such that the series works as is over net-next.
In parallel to effort a patch to modify IPoIB such that it doesn't assume dst/neighbour
on the skb was pushed upstream, its commit b63b70d87741 "IPoIB: Use a private hash table
for path lookup in xmit path", once present in net-next this patch can simply be dropped.
Erez Shitrit (10):
include/linux: Add private flags for IPoIB interfaces
IB/ipoib: Add support for acting as VIF
net: Add ndo_set_vif_param operation to serve eIPoIB VIFs
net/core: Add rtnetlink support to vif parameters
net/eipoib: Add private header file
net/eipoib: Add ethtool file support
net/eipoib: Add main driver functionality
net/eipoib: Add sysfs support
net/eipoib: Add Makefile, Kconfig and MAINTAINERS entries
IB/ipoib: Add support for transmission of skbs w.o dst/neighbour
Or Gerlitz (2):
IB/ipoib: Add rtnl_link_ops support
IB/ipoib: Add support for clones / multiple childs on the same partition
Documentation/infiniband/ipoib.txt | 15 +
MAINTAINERS | 6 +
drivers/infiniband/ulp/ipoib/Makefile | 3 +-
drivers/infiniband/ulp/ipoib/ipoib.h | 16 +
drivers/infiniband/ulp/ipoib/ipoib_cm.c | 9 +
drivers/infiniband/ulp/ipoib/ipoib_ib.c | 8 +-
drivers/infiniband/ulp/ipoib/ipoib_main.c | 38 +-
drivers/infiniband/ulp/ipoib/ipoib_netlink.c | 119 ++
drivers/infiniband/ulp/ipoib/ipoib_vlan.c | 89 +-
drivers/net/Kconfig | 15 +
drivers/net/Makefile | 1 +
drivers/net/eipoib/Makefile | 4 +
drivers/net/eipoib/eth_ipoib.h | 215 +++
drivers/net/eipoib/eth_ipoib_ethtool.c | 114 ++
drivers/net/eipoib/eth_ipoib_main.c | 1953 ++++++++++++++++++++++++++
drivers/net/eipoib/eth_ipoib_sysfs.c | 435 ++++++
include/linux/if.h | 2 +
include/linux/if_link.h | 16 +
include/linux/netdevice.h | 5 +-
include/rdma/e_ipoib.h | 54 +
net/core/rtnetlink.c | 42 +-
21 files changed, 3117 insertions(+), 42 deletions(-)
create mode 100644 drivers/infiniband/ulp/ipoib/ipoib_netlink.c
create mode 100644 drivers/net/eipoib/Makefile
create mode 100644 drivers/net/eipoib/eth_ipoib.h
create mode 100644 drivers/net/eipoib/eth_ipoib_ethtool.c
create mode 100644 drivers/net/eipoib/eth_ipoib_main.c
create mode 100644 drivers/net/eipoib/eth_ipoib_sysfs.c
create mode 100644 include/rdma/e_ipoib.h
Cc: Erez Shitrit <erezsh@mellanox.co.il>
^ permalink raw reply
* [PATCH V2 12/12] IB/ipoib: Add support for transmission of skbs w.o dst/neighbour
From: Or Gerlitz @ 2012-08-01 17:09 UTC (permalink / raw)
To: davem; +Cc: roland, netdev, ali, sean.hefty, Erez Shitrit, Or Gerlitz
In-Reply-To: <1343840975-3252-1-git-send-email-ogerlitz@mellanox.com>
From: Erez Shitrit <erezsh@mellanox.co.il>
Guest IP packets sent by eIPoIB over an IPoIB VIF interface do not point
to dst or neighbour. This patch modifies IPoIB such that trasnmission
of such packets is possible. It does so by extending an already existing
path in the driver which was used so far only for unicast ARP probes.
This patch was made such that the series works as is over net-next, in
parallel to this driver a patch to modify IPoIB such that it doesn't
assume dst/neighbour on the skb was pushed upstream, its commit b63b70d87741
"IPoIB: Use a private hash table for path lookup in xmit path", once
present in net-next this patch can simply be dropped.
Signed-off-by: Erez Shitrit <erezsh@mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
drivers/infiniband/ulp/ipoib/ipoib_main.c | 7 ++++---
1 files changed, 4 insertions(+), 3 deletions(-)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 47034b4..fc4a1f0 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -732,7 +732,7 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
unsigned long flags;
rcu_read_lock();
- if (likely(skb_dst(skb))) {
+ if (likely(skb_dst(skb)) && !(dev->priv_flags & IFF_EIPOIB_VIF)) {
n = dst_neigh_lookup_skb(skb_dst(skb), skb);
if (!n) {
++dev->stats.tx_dropped;
@@ -800,7 +800,8 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
/* unicast GID -- should be ARP or RARP reply */
if ((be16_to_cpup((__be16 *) skb->data) != ETH_P_ARP) &&
- (be16_to_cpup((__be16 *) skb->data) != ETH_P_RARP)) {
+ (be16_to_cpup((__be16 *) skb->data) != ETH_P_RARP) &&
+ !(dev->priv_flags & IFF_EIPOIB_VIF)) {
ipoib_warn(priv, "Unicast, no %s: type %04x, QPN %06x %pI6\n",
skb_dst(skb) ? "neigh" : "dst",
be16_to_cpup((__be16 *) skb->data),
@@ -850,7 +851,7 @@ static int ipoib_hard_header(struct sk_buff *skb,
* destination address into skb->cb so we can figure out where
* to send the packet later.
*/
- if (!skb_dst(skb)) {
+ if (!skb_dst(skb) || dev->priv_flags & IFF_EIPOIB_VIF) {
struct ipoib_cb *cb = (struct ipoib_cb *) skb->cb;
memcpy(cb->hwaddr, daddr, INFINIBAND_ALEN);
}
--
1.7.1
^ permalink raw reply related
* [PATCH V2 09/12] net/eipoib: Add main driver functionality
From: Or Gerlitz @ 2012-08-01 17:09 UTC (permalink / raw)
To: davem; +Cc: roland, netdev, ali, sean.hefty, Erez Shitrit, Or Gerlitz
In-Reply-To: <1343840975-3252-1-git-send-email-ogerlitz@mellanox.com>
From: Erez Shitrit <erezsh@mellanox.co.il>
The eipoib driver provides a standard Ethernet netdevice over
the InfiniBand IPoIB interface .
Some services can run only on top of Ethernet L2 interfaces, and cannot be
bound to an IPoIB interface. With this new driver, these services can run
seamlessly.
Main use case of the driver is the Ethernet Virtual Switching used in
virtualized environments, where an eipoib netdevice can be used as a
Physical Interface (PIF) in the hypervisor domain, and allow other
guests Virtual Interfaces (VIF) connected to the same Virtual Switch
to run over the InfiniBand fabric.
This driver supports L2 Switching (Direct Bridging) as well as other L3
Switching modes (e.g. NAT).
Whenever an IPoIB interface is created, one eIPoIB PIF netdevice
will be created. The default naming scheme is as in other Ethernet
interfaces: ethX, for example, on a system with two IPoIB interfaces,
ib0 and ib1, two interfaces will be created ethX and ethX+1 When "X"
is the next free Ethernet number in the system.
Using "ethtool -i " over the new interface can tell on which IPoIB
PIF interface that interface is above. For example: driver: eth_ipoib:ib0
indicates that eth3 is the Ethernet interface over the ib0 IPoIB interface.
The driver can be used as independent interface or to serve in
virtualization environment as the physical layer for the virtual
interfaces on the virtual guest.
The driver interface (eipoib interface or which is also referred to as parent)
uses slave interfaces, IPoIB clones, which are the VIFs described above.
VIFs interfaces are enslaved/released from the eipoib driver on demand, according
to the management interface provided to user space.
Note: Each ethX interface has at least one ibX.Y slave to serve the PIF
itself, in the VIFs list of ethX you'll notice that ibX.1 is always created
to serve applications running from the Hypervisor on top of ethX interface directly.
For IB applications that require native IPoIB interfaces (e.g. RDMA-CM), the
original ipoib interfaces ibX can still be used. For example, RDMA-CM and
eth_ipoib drivers can co-exist and make use of IPoIB
Support for Live migration:
The driver expose sysfs interface through which the manager can notify on
migrated out guests ("detached VIF"). The abandoned eIPoIB driver instance
sends ARP requests (defined number) to the network in order to triger the migrated
guest to publish its mac address of the new VIF that hosts it. When the guest
responds to that ARP, the eIPoIB driver on the host that owns that guest, sends
Gratuitous ARP in behalf of that guest such that all the peers on the network
which communicate with this VM are noticed on the new VIF address which is
used by the guest.
Signed-off-by: Erez Shitrit <erezsh@mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
drivers/net/eipoib/eth_ipoib_main.c | 1953 +++++++++++++++++++++++++++++++++++
1 files changed, 1953 insertions(+), 0 deletions(-)
create mode 100644 drivers/net/eipoib/eth_ipoib_main.c
diff --git a/drivers/net/eipoib/eth_ipoib_main.c b/drivers/net/eipoib/eth_ipoib_main.c
new file mode 100644
index 0000000..0a8e7f4
--- /dev/null
+++ b/drivers/net/eipoib/eth_ipoib_main.c
@@ -0,0 +1,1953 @@
+/*
+ * Copyright (c) 2012 Mellanox Technologies. All rights reserved
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * openfabric.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include "eth_ipoib.h"
+#include <net/ip.h>
+#include <linux/if_link.h>
+
+#define EMAC_IP_GC_TIME (10 * HZ)
+
+#define MIG_OUT_ARP_REQ_ISSUE_TIME (0.5 * HZ)
+
+#define MIG_OUT_MAX_ARP_RETRIES 5
+
+#define LIVE_MIG_PACKET 1
+
+#define PARENT_MAC_MASK 0xe7
+
+/* forward declaration */
+static rx_handler_result_t eipoib_handle_frame(struct sk_buff **pskb);
+static int eipoib_device_event(struct notifier_block *unused,
+ unsigned long event, void *ptr);
+static void free_ip_mem_in_rec(struct guest_emac_info *emac_info);
+
+static const char * const version =
+ DRV_DESCRIPTION ": v" DRV_VERSION " (" DRV_RELDATE ")\n";
+
+LIST_HEAD(parent_dev_list);
+
+/* name space sys/fs functions */
+int eipoib_net_id __read_mostly;
+
+static int __net_init eipoib_net_init(struct net *net)
+{
+ int rc;
+ struct eipoib_net *eipoib_n = net_generic(net, eipoib_net_id);
+
+ eipoib_n->net = net;
+ rc = mod_create_sysfs(eipoib_n);
+
+ return rc;
+}
+
+static void __net_exit eipoib_net_exit(struct net *net)
+{
+ struct eipoib_net *eipoib_n = net_generic(net, eipoib_net_id);
+
+ mod_destroy_sysfs(eipoib_n);
+}
+
+static struct pernet_operations eipoib_net_ops = {
+ .init = eipoib_net_init,
+ .exit = eipoib_net_exit,
+ .id = &eipoib_net_id,
+ .size = sizeof(struct eipoib_net),
+};
+
+/* set mac fields emac=<qpn><lid> */
+static inline
+void build_neigh_mac(u8 *_mac, u32 _qpn, u16 _lid)
+{
+ /* _qpn: 3B _lid: 2B */
+ *((__be32 *)(_mac)) = cpu_to_be32(_qpn);
+ *(u8 *)(_mac) = 0x2; /* set LG bit */
+ *(__be16 *)(_mac + sizeof(_qpn)) = cpu_to_be16(_lid);
+}
+
+static inline
+struct slave *get_slave_by_dev(struct parent *parent,
+ struct net_device *slave_dev)
+{
+ struct slave *slave, *slave_tmp;
+ int found = 0;
+
+ parent_for_each_slave(parent, slave_tmp) {
+ if (slave_tmp->dev == slave_dev) {
+ found = 1;
+ slave = slave_tmp;
+ break;
+ }
+ }
+
+ return found ? slave : NULL;
+}
+
+static inline
+struct slave *get_slave_by_mac_and_vlan(struct parent *parent, u8 *mac,
+ u16 vlan)
+{
+ struct slave *slave, *slave_tmp;
+ int found = 0;
+
+ parent_for_each_slave(parent, slave_tmp) {
+ if ((!memcmp(slave_tmp->emac, mac, ETH_ALEN)) &&
+ (slave_tmp->vlan == vlan)) {
+ found = 1;
+ slave = slave_tmp;
+ break;
+ }
+ }
+
+ return found ? slave : NULL;
+}
+
+
+static inline
+struct guest_emac_info *get_mac_ip_info_by_mac_and_vlan(struct parent *parent,
+ u8 *mac, u16 vlan)
+{
+ struct guest_emac_info *emac_info, *emac_info_ret;
+ int found = 0;
+
+ list_for_each_entry(emac_info, &parent->emac_ip_list, list) {
+ if ((!memcmp(emac_info->emac, mac, ETH_ALEN)) &&
+ vlan == emac_info->vlan) {
+ found = 1;
+ emac_info_ret = emac_info;
+ break;
+ }
+ }
+
+ return found ? emac_info_ret : NULL;
+}
+
+/*
+ * searches for the relevant guest_emac_info in the parent.
+ * if found it, check if it contains the required ip
+ * if no such guest_emac_info object or no ip return 0,
+ * otherwise return 1 and if exist set the guest_emac_info obj.
+ */
+static inline
+int is_mac_info_contain_ip(struct parent *parent, u8 *mac, __be32 ip,
+ struct guest_emac_info *emac_info, u16 vlan)
+{
+ struct ip_member *ipm;
+ int found = 0;
+
+ emac_info = get_mac_ip_info_by_mac_and_vlan(parent, mac, vlan);
+ if (!emac_info)
+ return 0;
+
+ list_for_each_entry(ipm, &emac_info->ip_list, list) {
+ if (ipm->ip == ip) {
+ found = 1;
+ break;
+ }
+ }
+
+ return found;
+}
+
+static inline int netdev_set_parent_master(struct net_device *slave,
+ struct net_device *master)
+{
+ int err;
+
+ ASSERT_RTNL();
+
+ err = netdev_set_master(slave, master);
+ if (err)
+ return err;
+ if (master) {
+ slave->priv_flags |= IFF_EIPOIB_VIF;
+ /* deny bonding from enslaving it. */;
+ slave->flags |= IFF_SLAVE;
+ } else {
+ slave->priv_flags &= ~(IFF_EIPOIB_VIF);
+ slave->flags &= ~(IFF_SLAVE);
+ }
+
+ return 0;
+}
+
+static inline int is_driver_owner(struct net_device *dev, char *name)
+{
+ struct ethtool_drvinfo drvinfo;
+
+ if (dev->ethtool_ops && dev->ethtool_ops->get_drvinfo) {
+ memset(&drvinfo, 0, sizeof(drvinfo));
+ dev->ethtool_ops->get_drvinfo(dev, &drvinfo);
+ if (!strstr(drvinfo.driver, name))
+ return 0;
+ } else
+ return 0;
+
+ return 1;
+}
+
+static inline int is_parent(struct net_device *dev)
+{
+ return (dev->priv_flags & IFF_EIPOIB_PIF) &&
+ is_driver_owner(dev, DRV_NAME);
+}
+
+static inline int is_parent_mac(struct net_device *dev, u8 *mac)
+{
+ return is_parent(dev) && !memcmp(mac, dev->dev_addr, dev->addr_len);
+}
+
+static inline int __is_slave(struct net_device *dev)
+{
+ return dev->master && is_parent(dev->master);
+}
+
+static inline int is_slave(struct net_device *dev)
+{
+ return (dev->priv_flags & IFF_EIPOIB_VIF) &&
+ is_driver_owner(dev, SDRV_NAME) && __is_slave(dev);
+}
+
+/*
+ * ------------------------------- Link status ------------------
+ * set parent carrier:
+ * link is up if at least one slave has link up
+ * otherwise, bring link down
+ * return 1 if parent carrier changed, zero otherwise
+ */
+static int parent_set_carrier(struct parent *parent)
+{
+ struct slave *slave;
+
+ if (parent->slave_cnt == 0)
+ goto down;
+
+ /* bring parent link up if one slave (at least) is up */
+ parent_for_each_slave(parent, slave) {
+ if (netif_carrier_ok(slave->dev)) {
+ if (!netif_carrier_ok(parent->dev)) {
+ netif_carrier_on(parent->dev);
+ return 1;
+ }
+ return 0;
+ }
+ }
+
+down:
+ if (netif_carrier_ok(parent->dev)) {
+ pr_info("bring down carrier\n");
+ netif_carrier_off(parent->dev);
+ return 1;
+ }
+ return 0;
+}
+
+static int parent_set_mtu(struct parent *parent)
+{
+ struct slave *slave, *f_slave;
+ unsigned int mtu;
+
+ if (parent->slave_cnt == 0)
+ return 0;
+
+ /* find min mtu */
+ f_slave = list_first_entry(&parent->slave_list, struct slave, list);
+ mtu = f_slave->dev->mtu;
+
+ parent_for_each_slave(parent, slave)
+ mtu = min(slave->dev->mtu, mtu);
+
+ if (parent->dev->mtu != mtu) {
+ dev_set_mtu(parent->dev, mtu);
+ return 1;
+ }
+
+ return 0;
+}
+
+/*
+ *--------------------------- slave list handling ------
+ *
+ * This function attaches the slave to the end of list.
+ * pay attention, the caller should held paren->lock
+ */
+static void parent_attach_slave(struct parent *parent,
+ struct slave *new_slave)
+{
+ list_add_tail(&new_slave->list, &parent->slave_list);
+ parent->slave_cnt++;
+}
+
+static void parent_detach_slave(struct parent *parent, struct slave *slave)
+{
+ list_del(&slave->list);
+ parent->slave_cnt--;
+}
+
+static netdev_features_t parent_fix_features(struct net_device *dev,
+ netdev_features_t features)
+{
+ struct slave *slave;
+ struct parent *parent = netdev_priv(dev);
+ netdev_features_t mask;
+
+ read_lock_bh(&parent->lock);
+
+ mask = features;
+ features &= ~NETIF_F_ONE_FOR_ALL;
+ features |= NETIF_F_ALL_FOR_ALL;
+
+ parent_for_each_slave(parent, slave)
+ features = netdev_increment_features(features,
+ slave->dev->features,
+ mask);
+
+ features &= ~NETIF_F_VLAN_CHALLENGED;
+ read_unlock_bh(&parent->lock);
+ return features;
+}
+
+static int parent_compute_features(struct parent *parent)
+{
+ struct net_device *parent_dev = parent->dev;
+ u64 hw_features, features;
+ struct slave *slave;
+
+ if (list_empty(&parent->slave_list))
+ goto done;
+
+ /* starts with the max set of features mask */
+ hw_features = features = ~0LL;
+
+ /* gets the common features from all slaves */
+ parent_for_each_slave(parent, slave) {
+ features &= slave->dev->features;
+ hw_features &= slave->dev->hw_features;
+ }
+
+ features = features | PARENT_VLAN_FEATURES;
+ hw_features = hw_features | PARENT_VLAN_FEATURES;
+
+ hw_features &= ~NETIF_F_VLAN_CHALLENGED;
+ features &= hw_features;
+
+ parent_dev->hw_features = hw_features;
+ parent_dev->features = features;
+ parent_dev->vlan_features = parent_dev->features & ~PARENT_VLAN_FEATURES;
+done:
+ pr_info("%s: %s: Features: 0x%llx\n",
+ __func__, parent_dev->name, parent_dev->features);
+
+ return 0;
+}
+
+static inline u16 slave_get_pkey(struct net_device *dev)
+{
+ u16 pkey = (dev->broadcast[8] << 8) + dev->broadcast[9];
+
+ return pkey;
+}
+
+static void parent_setup_by_slave(struct net_device *parent_dev,
+ struct net_device *slave_dev)
+{
+ struct parent *parent = netdev_priv(parent_dev);
+ const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
+
+ parent_dev->mtu = slave_dev->mtu;
+ parent_dev->hard_header_len = slave_dev->hard_header_len;
+
+ slave_ops->ndo_neigh_setup(slave_dev, &parent->nparms);
+
+}
+
+/* enslave device <slave> to parent device <master> */
+int parent_enslave(struct net_device *parent_dev, struct net_device *slave_dev)
+{
+ struct parent *parent = netdev_priv(parent_dev);
+ struct slave *new_slave = NULL;
+ int old_features = parent_dev->features;
+ int res = 0;
+ /* slave must be claimed by ipoib */
+ if (!is_driver_owner(slave_dev, SDRV_NAME))
+ return -EOPNOTSUPP;
+
+ /* parent must be initialized by parent_open() before enslaving */
+ if (!(parent_dev->flags & IFF_UP)) {
+ pr_warn("%s parent is not up in "
+ "parent_enslave\n",
+ parent_dev->name);
+ return -EPERM;
+ }
+
+ /* already enslaved */
+ if ((slave_dev->flags & IFF_SLAVE) ||
+ (slave_dev->priv_flags & IFF_EIPOIB_VIF)) {
+ pr_err("%s was already enslaved!!!\n", slave_dev->name);
+ return -EBUSY;
+ }
+
+ /* mark it as ipoib clone vif */
+ slave_dev->priv_flags |= IFF_EIPOIB_VIF;
+
+ /* set parent netdev attributes */
+ if (parent->slave_cnt == 0)
+ parent_setup_by_slave(parent_dev, slave_dev);
+ else {
+ /* check netdev attr match */
+ if (slave_dev->hard_header_len != parent_dev->hard_header_len) {
+ pr_err("%s slave %s has different HDR len %d != %d\n",
+ parent_dev->name, slave_dev->name,
+ slave_dev->hard_header_len,
+ parent_dev->hard_header_len);
+ res = -EINVAL;
+ goto err_undo_flags;
+ }
+
+ if (slave_dev->type != ARPHRD_INFINIBAND ||
+ slave_dev->addr_len != INFINIBAND_ALEN) {
+ pr_err("%s slave type/addr_len is invalid (%d/%d)\n",
+ parent_dev->name, slave_dev->type,
+ slave_dev->addr_len);
+ res = -EINVAL;
+ goto err_undo_flags;
+ }
+ }
+ /*
+ * verfiy that this (slave) device belongs to the relevant PIF
+ * abort if the name of the slave is not as the regular way in ipoib
+ */
+ if (!strstr(slave_dev->name, parent->ipoib_main_interface)) {
+ pr_err("%s slave name (%s) doesn't contain parent name (%s) ",
+ parent_dev->name, slave_dev->name,
+ parent->ipoib_main_interface);
+ res = -EINVAL;
+ goto err_undo_flags;
+ }
+
+ new_slave = kzalloc(sizeof(struct slave), GFP_KERNEL);
+ if (!new_slave) {
+ res = -ENOMEM;
+ goto err_undo_flags;
+ }
+
+ INIT_LIST_HEAD(&new_slave->neigh_list);
+
+ /* save slave's vlan */
+ new_slave->pkey = slave_get_pkey(slave_dev);
+
+ res = netdev_set_parent_master(slave_dev, parent_dev);
+ if (res) {
+ pr_err("%s %d calling netdev_set_master\n",
+ slave_dev->name, res);
+ goto err_free;
+ }
+
+ res = dev_open(slave_dev);
+ if (res) {
+ pr_info("open failed %s\n",
+ slave_dev->name);
+ goto err_unset_master;
+ }
+
+ new_slave->dev = slave_dev;
+
+ write_lock_bh(&parent->lock);
+
+ parent_attach_slave(parent, new_slave);
+
+ parent_compute_features(parent);
+
+ write_unlock_bh(&parent->lock);
+
+ read_lock_bh(&parent->lock);
+
+ parent_set_carrier(parent);
+
+ read_unlock_bh(&parent->lock);
+
+ res = create_slave_symlinks(parent_dev, slave_dev);
+ if (res)
+ goto err_close;
+
+ /* register handler */
+ res = netdev_rx_handler_register(slave_dev, eipoib_handle_frame,
+ new_slave);
+ if (res) {
+ pr_warn("%s %d calling netdev_rx_handler_register\n",
+ parent_dev->name, res);
+ goto err_close;
+ }
+
+ pr_info("%s: enslaving %s\n", parent_dev->name, slave_dev->name);
+
+ /* enslave is successful */
+ return 0;
+
+/* Undo stages on error */
+err_close:
+ dev_close(slave_dev);
+
+err_unset_master:
+ netdev_set_parent_master(slave_dev, NULL);
+
+err_free:
+ kfree(new_slave);
+
+err_undo_flags:
+ parent_dev->features = old_features;
+
+ return res;
+}
+
+static void slave_free(struct parent *parent, struct slave *slave)
+{
+ struct neigh *neigh, *neigh_tmp;
+
+ list_for_each_entry_safe(neigh, neigh_tmp, &slave->neigh_list, list) {
+ list_del(&neigh->list);
+ kfree(neigh);
+ }
+
+ netdev_rx_handler_unregister(slave->dev);
+
+ kfree(slave);
+}
+
+int parent_release_slave(struct net_device *parent_dev,
+ struct net_device *slave_dev)
+{
+ struct parent *parent = netdev_priv(parent_dev);
+ struct slave *slave;
+ struct guest_emac_info *emac_info;
+
+ /* slave is not a slave or master is not master of this slave */
+ if (!(slave_dev->flags & IFF_SLAVE) ||
+ (slave_dev->master != parent_dev)) {
+ pr_err("%s cannot release %s.\n",
+ parent_dev->name, slave_dev->name);
+ return -EINVAL;
+ }
+
+ write_lock_bh(&parent->lock);
+
+ slave = get_slave_by_dev(parent, slave_dev);
+ if (!slave) {
+ /* not a slave of this parent */
+ pr_warn("%s not enslaved %s\n",
+ parent_dev->name, slave_dev->name);
+ write_unlock_bh(&parent->lock);
+ return -EINVAL;
+ }
+
+ pr_info("%s: releasing interface %s\n", parent_dev->name,
+ slave_dev->name);
+
+ /* for live migration, mark its mac_ip record as invalid */
+ emac_info = get_mac_ip_info_by_mac_and_vlan(parent, slave->emac, slave->vlan);
+ if (!emac_info)
+ pr_warn("%s %s didn't find emac: %pM\n",
+ parent_dev->name, slave_dev->name, slave->emac);
+ else {
+ emac_info->rec_state = MIGRATED_OUT;
+ /* start GC work */
+ pr_info("%s: sending clean task for slave mac: %pM\n",
+ __func__, slave->emac);
+ queue_delayed_work(parent->wq, &parent->migrate_out_work, 0);
+ queue_delayed_work(parent->wq, &parent->emac_ip_work,
+ EMAC_IP_GC_TIME);
+ }
+
+ /* release the slave from its parent */
+ parent_detach_slave(parent, slave);
+
+ parent_compute_features(parent);
+
+ if (parent->slave_cnt == 0)
+ parent_set_carrier(parent);
+
+ write_unlock_bh(&parent->lock);
+
+ /* must do this from outside any spinlocks */
+ destroy_slave_symlinks(parent_dev, slave_dev);
+
+ netdev_set_parent_master(slave_dev, NULL);
+
+ dev_close(slave_dev);
+
+ slave_free(parent, slave);
+
+ return 0; /* deletion OK */
+}
+
+static int parent_release_all(struct net_device *parent_dev)
+{
+ struct parent *parent = netdev_priv(parent_dev);
+ struct slave *slave, *slave_tmp;
+ struct net_device *slave_dev;
+ struct neigh *neigh_cmd, *neigh_cmd_tmp;
+ struct guest_emac_info *emac_info, *emac_info_tmp;
+ struct slave;
+
+ write_lock_bh(&parent->lock);
+
+ netif_carrier_off(parent_dev);
+
+ if (parent->slave_cnt == 0)
+ goto out;
+
+ list_for_each_entry_safe(slave, slave_tmp, &parent->slave_list, list) {
+ slave_dev = slave->dev;
+
+ /* remove slave from parent's slave-list */
+ parent_detach_slave(parent, slave);
+
+ parent_compute_features(parent);
+
+ write_unlock_bh(&parent->lock);
+
+ destroy_slave_symlinks(parent_dev, slave_dev);
+
+ netdev_set_parent_master(slave_dev, NULL);
+
+ dev_close(slave_dev);
+
+ slave_free(parent, slave);
+
+ write_lock_bh(&parent->lock);
+ }
+
+ list_for_each_entry_safe(neigh_cmd, neigh_cmd_tmp,
+ &parent->neigh_add_list, list) {
+ list_del(&neigh_cmd->list);
+ kfree(neigh_cmd);
+ }
+
+ list_for_each_entry_safe(emac_info, emac_info_tmp,
+ &parent->emac_ip_list, list) {
+ free_ip_mem_in_rec(emac_info);
+ list_del(&emac_info->list);
+ kfree(emac_info);
+ }
+
+ pr_info("%s: released all slaves\n", parent_dev->name);
+
+out:
+ write_unlock_bh(&parent->lock);
+
+ return 0;
+}
+
+/* -------------------------- Device entry points --------------------------- */
+static struct rtnl_link_stats64 *parent_get_stats(struct net_device *parent_dev,
+ struct rtnl_link_stats64 *stats)
+{
+ struct parent *parent = netdev_priv(parent_dev);
+ struct slave *slave;
+ struct rtnl_link_stats64 temp;
+
+ memset(stats, 0, sizeof(*stats));
+
+ read_lock_bh(&parent->lock);
+
+ parent_for_each_slave(parent, slave) {
+ const struct rtnl_link_stats64 *sstats =
+ dev_get_stats(slave->dev, &temp);
+
+ stats->rx_packets += sstats->rx_packets;
+ stats->rx_bytes += sstats->rx_bytes;
+ stats->rx_errors += sstats->rx_errors;
+ stats->rx_dropped += sstats->rx_dropped;
+
+ stats->tx_packets += sstats->tx_packets;
+ stats->tx_bytes += sstats->tx_bytes;
+ stats->tx_errors += sstats->tx_errors;
+ stats->tx_dropped += sstats->tx_dropped;
+
+ stats->multicast += sstats->multicast;
+ stats->collisions += sstats->collisions;
+
+ stats->rx_length_errors += sstats->rx_length_errors;
+ stats->rx_over_errors += sstats->rx_over_errors;
+ stats->rx_crc_errors += sstats->rx_crc_errors;
+ stats->rx_frame_errors += sstats->rx_frame_errors;
+ stats->rx_fifo_errors += sstats->rx_fifo_errors;
+ stats->rx_missed_errors += sstats->rx_missed_errors;
+
+ stats->tx_aborted_errors += sstats->tx_aborted_errors;
+ stats->tx_carrier_errors += sstats->tx_carrier_errors;
+ stats->tx_fifo_errors += sstats->tx_fifo_errors;
+ stats->tx_heartbeat_errors += sstats->tx_heartbeat_errors;
+ stats->tx_window_errors += sstats->tx_window_errors;
+ }
+
+ read_unlock_bh(&parent->lock);
+
+ return stats;
+}
+
+/* ---------------------------- Main funcs ---------------------------------- */
+static struct neigh *neigh_cmd_find_by_mac(struct slave *slave, u8 *mac)
+{
+ struct net_device *dev = slave->dev;
+ struct net_device *parent_dev = dev->master;
+ struct parent *parent = netdev_priv(parent_dev);
+ struct neigh *neigh;
+ int found = 0;
+
+ list_for_each_entry(neigh, &parent->neigh_add_list, list) {
+ if (!memcmp(neigh->emac, mac, ETH_ALEN)) {
+ found = 1;
+ break;
+ }
+ }
+
+ return found ? neigh : NULL;
+}
+
+static struct neigh *neigh_find_by_mac(struct slave *slave, u8 *mac)
+{
+ struct neigh *neigh;
+ int found = 0;
+
+ list_for_each_entry(neigh, &slave->neigh_list, list) {
+ if (!memcmp(neigh->emac, mac, ETH_ALEN)) {
+ found = 1;
+ break;
+ }
+ }
+
+ return found ? neigh : NULL;
+}
+
+static int neigh_learn(struct slave *slave, struct sk_buff *skb, u8 *remac)
+{
+ struct net_device *dev = slave->dev;
+ struct net_device *parent_dev = dev->master;
+ struct parent *parent = netdev_priv(parent_dev);
+ struct neigh *neigh_cmd;
+ u8 *rimac;
+ int rc;
+
+ /* linearize to easy on reading the arp payload */
+ rc = skb_linearize(skb);
+ if (rc) {
+ pr_err("%s: skb_linearize failed rc %d\n", dev->name, rc);
+ goto out;
+ } else
+ rimac = skb->data + sizeof(struct arphdr);
+
+ /* check if entry is being processed or already exists */
+ if (neigh_find_by_mac(slave, remac))
+ goto out;
+
+ if (neigh_cmd_find_by_mac(slave, remac))
+ goto out;
+
+ neigh_cmd = parent_get_neigh_cmd('+', slave->dev->name, remac, rimac);
+ if (!neigh_cmd) {
+ pr_err("%s cannot build neigh cmd\n", slave->dev->name);
+ rc = -ENOMEM;
+ goto out;
+ }
+
+ list_add_tail(&neigh_cmd->list, &parent->neigh_add_list);
+
+ /* calls neigh_learn_task() */
+ queue_delayed_work(parent->wq, &parent->neigh_learn_work, 0);
+
+out:
+ return rc;
+}
+
+static void neigh_learn_task(struct work_struct *work)
+{
+ struct parent *parent = container_of(work, struct parent,
+ neigh_learn_work.work);
+ struct neigh *neigh_cmd, *neigh_cmd_tmp;
+
+ write_lock_bh(&parent->lock);
+
+ if (parent->kill_timers)
+ goto out;
+
+ list_for_each_entry_safe(neigh_cmd, neigh_cmd_tmp,
+ &parent->neigh_add_list, list) {
+ __parent_store_neighs(&parent->dev->dev, NULL,
+ neigh_cmd->cmd, PAGE_SIZE);
+ list_del(&neigh_cmd->list);
+ kfree(neigh_cmd);
+ }
+
+out:
+ write_unlock_bh(&parent->lock);
+ return;
+}
+
+static void parent_work_cancel_all(struct parent *parent)
+{
+ write_lock_bh(&parent->lock);
+ parent->kill_timers = 1;
+ write_unlock_bh(&parent->lock);
+
+ if (delayed_work_pending(&parent->neigh_learn_work))
+ cancel_delayed_work(&parent->neigh_learn_work);
+
+ if (delayed_work_pending(&parent->emac_ip_work))
+ cancel_delayed_work(&parent->emac_ip_work);
+
+ if (delayed_work_pending(&parent->migrate_out_work))
+ cancel_delayed_work(&parent->migrate_out_work);
+}
+
+static struct parent *get_parent_by_pif_name(char *pif_name)
+{
+ struct parent *parent, *nxt;
+
+ list_for_each_entry_safe(parent, nxt, &parent_dev_list, parent_list) {
+ if (!strcmp(parent->ipoib_main_interface, pif_name))
+ return parent;
+ }
+ return NULL;
+}
+
+static void free_ip_mem_in_rec(struct guest_emac_info *emac_info)
+{
+ struct ip_member *ipm, *tmp_ipm;
+ list_for_each_entry_safe(ipm, tmp_ipm, &emac_info->ip_list, list) {
+ list_del(&ipm->list);
+ kfree(ipm);
+ }
+}
+
+static inline void free_invalid_emac_ip_det(struct parent *parent)
+{
+ struct guest_emac_info *emac_info, *emac_info_tmp;
+
+ list_for_each_entry_safe(emac_info, emac_info_tmp,
+ &parent->emac_ip_list, list) {
+ if (emac_info->rec_state == INVALID) {
+ free_ip_mem_in_rec(emac_info);
+ list_del(&emac_info->list);
+ kfree(emac_info);
+ }
+ }
+}
+
+static void emac_info_clean_task(struct work_struct *work)
+{
+ struct parent *parent = container_of(work, struct parent,
+ emac_ip_work.work);
+
+ write_lock_bh(&parent->lock);
+
+ if (parent->kill_timers)
+ goto out;
+
+ free_invalid_emac_ip_det(parent);
+
+out:
+ write_unlock_bh(&parent->lock);
+ return;
+}
+
+static int migrate_out_gen_arp_req(struct parent *parent, u8 *emac,
+ u16 vlan)
+{
+ struct guest_emac_info *emac_info;
+ struct ip_member *ipm;
+ struct slave *slave;
+ struct sk_buff *nskb;
+ int ret = 0;
+
+ slave = get_slave_by_mac_and_vlan(parent, parent->dev->dev_addr, vlan);
+ if (unlikely(!slave)) {
+ pr_info("%s: Failed to find parent slave !!! %pM\n",
+ __func__, parent->dev->dev_addr);
+ return -ENODEV;
+ }
+
+ emac_info = get_mac_ip_info_by_mac_and_vlan(parent, emac, vlan);
+
+ if (!emac_info)
+ return 0;
+
+ /* go over all ip's attached to that mac */
+ list_for_each_entry(ipm, &emac_info->ip_list, list) {
+ /* create and send arp request to that ip.*/
+ pr_info("%s: Sending arp For migrate_out event, to %pI4 "
+ "from 0.0.0.0\n", parent->dev->name, &(ipm->ip));
+
+ nskb = arp_create(ARPOP_REQUEST,
+ ETH_P_ARP,
+ ipm->ip,
+ slave->dev,
+ 0,
+ slave->dev->broadcast,
+ slave->dev->broadcast,
+ slave->dev->broadcast);
+ if (nskb)
+ arp_xmit(nskb);
+ else {
+ pr_err("%s: %s failed creating skb\n",
+ __func__, slave->dev->name);
+ ret = -ENOMEM;
+ }
+ }
+ return ret;
+}
+
+static void migrate_out_work_task(struct work_struct *work)
+{
+ struct parent *parent = container_of(work, struct parent,
+ migrate_out_work.work);
+ struct guest_emac_info *emac_info;
+ int is_reschedule = 0;
+ int ret;
+
+ write_lock_bh(&parent->lock);
+
+ if (parent->kill_timers)
+ goto out;
+
+ list_for_each_entry(emac_info, &parent->emac_ip_list, list) {
+ if (emac_info->rec_state == MIGRATED_OUT) {
+ if (emac_info->num_of_retries <
+ MIG_OUT_MAX_ARP_RETRIES) {
+ ret = migrate_out_gen_arp_req(parent, emac_info->emac,
+ emac_info->vlan);
+ if (ret)
+ pr_err("%s: migrate_out_gen_arp failed: %d\n",
+ __func__, ret);
+
+ emac_info->num_of_retries =
+ emac_info->num_of_retries + 1;
+ is_reschedule = 1;
+ } else
+ emac_info->rec_state = INVALID;
+ }
+ }
+ /* issue arp request till the device removed that entry from list */
+ if (is_reschedule)
+ queue_delayed_work(parent->wq, &parent->migrate_out_work,
+ MIG_OUT_ARP_REQ_ISSUE_TIME);
+out:
+ write_unlock_bh(&parent->lock);
+ return;
+}
+
+static inline int add_emac_ip_info(struct net_device *slave_dev, __be32 ip,
+ u8 *mac, u16 vlan)
+{
+ struct net_device *parent_dev = slave_dev->master;
+ struct parent *parent = netdev_priv(parent_dev);
+ struct guest_emac_info *emac_info = NULL;
+ struct ip_member *ipm;
+ int ret;
+ int is_just_alloc_emac_info = 0;
+
+ ret = is_mac_info_contain_ip(parent, mac, ip, emac_info, vlan);
+ if (ret)
+ return 0;
+
+ /* new ip add it to the emc_ip obj */
+ if (!emac_info) {
+ emac_info = kzalloc(sizeof *emac_info, GFP_ATOMIC);
+ if (!emac_info) {
+ pr_err("%s: Failed allocating emac_info\n",
+ parent_dev->name);
+ return -ENOMEM;
+ }
+ memcpy(emac_info->emac, mac, ETH_ALEN);
+ INIT_LIST_HEAD(&emac_info->ip_list);
+ emac_info->rec_state = VALID;
+ emac_info->vlan = vlan;
+ emac_info->num_of_retries = 0;
+ list_add_tail(&emac_info->list, &parent->emac_ip_list);
+ is_just_alloc_emac_info = 1;
+ }
+
+ ipm = kzalloc(sizeof *ipm, GFP_ATOMIC);
+ if (!ipm) {
+ pr_err(" %s Failed allocating emac_info (ipm)\n",
+ parent_dev->name);
+ if (is_just_alloc_emac_info)
+ kfree(emac_info);
+ return -ENOMEM;
+ }
+
+ ipm->ip = ip;
+ list_add_tail(&ipm->list, &emac_info->ip_list);
+
+ return 0;
+}
+
+/* build ipoib arp/rarp request/reply packet */
+static struct sk_buff *get_slave_skb_arp(struct slave *slave,
+ struct sk_buff *skb,
+ u8 *rimac, int *ret)
+{
+ struct sk_buff *nskb;
+ struct arphdr *arphdr = (struct arphdr *)
+ (skb->data + sizeof(struct ethhdr));
+ struct eth_arp_data *arp_data = (struct eth_arp_data *)
+ (skb->data + sizeof(struct ethhdr) +
+ sizeof(struct arphdr));
+ u8 t_addr[ETH_ALEN] = {0};
+ int err = 0;
+ /* mark regular packet handling */
+ *ret = 0;
+
+ /*
+ * live-migration support: keeps the new mac/ip address:
+ * In that way each driver knows which mac/vlan - IP's where on the
+ * guests above, whenever migrate_out event comes it will send
+ * arp request for all these IP's.
+ */
+ if (skb->protocol == htons(ETH_P_ARP))
+ err = add_emac_ip_info(slave->dev, arp_data->arp_sip,
+ arp_data->arp_sha, slave->vlan);
+ if (err)
+ pr_warn("%s: Failed creating: emac_ip_info for ip: %pI4",
+ __func__, &arp_data->arp_sip);
+ /*
+ * live migration support:
+ * 1.checck if we are in live migration process
+ * 2.check if the arp response is for the parent
+ * 3.ignore local-administrated bit, which was set to make sure
+ * that the bridge will not drop it.
+ */
+ arp_data->arp_dha[0] = arp_data->arp_dha[0] & 0xFD;
+ if (htons(ARPOP_REPLY) == (arphdr->ar_op) &&
+ !memcmp(arp_data->arp_dha, slave->dev->master->dev_addr, ETH_ALEN)) {
+ /*
+ * when the source is the parent interface, assumes
+ * that we are in the middle of live migration process,
+ * so, we will send gratuitous arp.
+ */
+ pr_info("%s: Arp packet for parent: %s",
+ __func__, slave->dev->master->name);
+ /* create gratuitous ARP on behalf of the guest */
+ nskb = arp_create(ARPOP_REQUEST,
+ be16_to_cpu(skb->protocol),
+ arp_data->arp_sip,
+ slave->dev,
+ arp_data->arp_sip,
+ NULL,
+ slave->dev->dev_addr,
+ t_addr);
+ if (unlikely(!nskb))
+ pr_err("%s: %s live migration: failed creating skb\n",
+ __func__, slave->dev->name);
+ } else {
+ nskb = arp_create(be16_to_cpu(arphdr->ar_op),
+ be16_to_cpu(skb->protocol),
+ arp_data->arp_dip,
+ slave->dev,
+ arp_data->arp_sip,
+ rimac,
+ slave->dev->dev_addr,
+ NULL);
+ }
+
+ return nskb;
+}
+
+/*
+ * build ipoib arp request packet according to ip header.
+ * uses for live-migration, or missing neigh for new vif.
+ */
+static void get_slave_skb_arp_by_ip(struct slave *slave,
+ struct sk_buff *skb)
+{
+ struct sk_buff *nskb = NULL;
+ struct iphdr *iph = ip_hdr(skb);
+
+ pr_info("Sending arp on behalf of slave %s, from %pI4"
+ " to %pI4" , slave->dev->name, &(iph->saddr),
+ &(iph->daddr));
+
+ nskb = arp_create(ARPOP_REQUEST,
+ ETH_P_ARP,
+ iph->daddr,
+ slave->dev,
+ iph->saddr,
+ slave->dev->broadcast,
+ slave->dev->dev_addr,
+ NULL);
+ if (nskb)
+ arp_xmit(nskb);
+ else
+ pr_err("%s: %s failed creating skb\n",
+ __func__, slave->dev->name);
+}
+
+/* build ipoib ipv4/ipv6 packet */
+static struct sk_buff *get_slave_skb_ip(struct slave *slave,
+ struct sk_buff *skb)
+{
+
+ skb_pull(skb, ETH_HLEN);
+ skb_reset_network_header(skb);
+
+ return skb;
+}
+
+/*
+ * get_slave_skb -- called in TX flow
+ * get skb that can be sent thru slave xmit func,
+ * if skb was adjusted (cloned, pulled, etc..) successfully
+ * the old skb (if any) is freed here.
+ */
+static struct sk_buff *get_slave_skb(struct slave *slave, struct sk_buff *skb)
+{
+ struct net_device *dev = slave->dev;
+ struct net_device *parent_dev = dev->master;
+ struct parent *parent = netdev_priv(parent_dev);
+ struct sk_buff *nskb = NULL;
+ struct ethhdr *ethh = (struct ethhdr *)(skb->data);
+ struct neigh *neigh = NULL;
+ u8 rimac[INFINIBAND_ALEN];
+ int ret = 0;
+
+ /* set neigh mac */
+ if (is_multicast_ether_addr(ethh->h_dest)) {
+ memcpy(rimac, dev->broadcast, INFINIBAND_ALEN);
+ } else {
+ neigh = neigh_find_by_mac(slave, ethh->h_dest);
+ if (neigh) {
+ memcpy(rimac, neigh->imac, INFINIBAND_ALEN);
+ } else {
+ ++parent->port_stats.tx_neigh_miss;
+ /*
+ * assume VIF migration, tries to get the neigh by
+ * issue arp request on behalf of the vif.
+ */
+ if (skb->protocol == htons(ETH_P_IP)) {
+ pr_info("Missed neigh for slave: %s,"
+ "issue ARP request\n",
+ slave->dev->name);
+ get_slave_skb_arp_by_ip(slave, skb);
+ goto out_arp_sent_instead;
+ }
+ }
+ }
+
+ if (skb->protocol == htons(ETH_P_ARP) ||
+ skb->protocol == htons(ETH_P_RARP)) {
+ nskb = get_slave_skb_arp(slave, skb, rimac, &ret);
+ if (!nskb && LIVE_MIG_PACKET == ret) {
+ pr_info("%s: live migration packets\n", __func__);
+ goto err;
+ }
+ } else {
+ if (!neigh)
+ goto err;
+ /* pull ethernet header here */
+ nskb = get_slave_skb_ip(slave, skb);
+ }
+
+ /* if new skb could not be adjusted/allocated, abort */
+ if (!nskb) {
+ pr_err("%s get_slave_skb_ip/arp failed 0x%x\n",
+ dev->name, skb->protocol);
+ goto err;
+ }
+
+ if (neigh && nskb == skb) { /* ucast & non-arp/rarp */
+ /* dev_hard_header only for ucast, for arp done already.*/
+ if (dev_hard_header(nskb, dev, ntohs(skb->protocol), rimac,
+ dev->dev_addr, nskb->len) < 0) {
+ pr_warn("%s: dev_hard_header failed\n",
+ dev->name);
+ goto err;
+ }
+ }
+
+ /*
+ * new skb is ready to be sent, clean old skb if we hold a clone
+ * (old skb is not shared, already checked that.)
+ */
+ if ((nskb != skb))
+ dev_kfree_skb(skb);
+
+ nskb->dev = slave->dev;
+ return nskb;
+
+out_arp_sent_instead:/* whenever sent arp instead of ip packet */
+err:
+ /* got error after nskb was adjusted/allocated */
+ if (nskb && (nskb != skb))
+ dev_kfree_skb(nskb);
+
+ return NULL;
+}
+
+static struct sk_buff *get_parent_skb_arp(struct slave *slave,
+ struct sk_buff *skb,
+ u8 *remac)
+{
+ struct net_device *dev = slave->dev->master;
+ struct sk_buff *nskb;
+ struct arphdr *arphdr = (struct arphdr *)(skb->data);
+ struct ipoib_arp_data *arp_data = (struct ipoib_arp_data *)
+ (skb->data + sizeof(struct arphdr));
+ u8 *target_hw = slave->emac;
+ u8 *dst_hw = slave->emac;
+ u8 local_eth_addr[ETH_ALEN];
+
+ /* live migration: gets arp with broadcast src and dst */
+ if (!memcmp(arp_data->arp_sha, slave->dev->broadcast, INFINIBAND_ALEN) &&
+ !memcmp(arp_data->arp_dha, slave->dev->broadcast, INFINIBAND_ALEN)) {
+ pr_info("%s: ARP with bcast src and dest send from src_hw: %pM\n",
+ __func__, slave->dev->master->dev_addr);
+ /* replace the src with the parent src: */
+ memcpy(local_eth_addr, slave->dev->master->dev_addr, ETH_ALEN);
+ /*
+ * set local administrated bit,
+ * that way the bridge will not throws it
+ */
+ local_eth_addr[0] = local_eth_addr[0] | 0x2;
+ memcpy(remac, local_eth_addr, ETH_ALEN);
+ target_hw = NULL;
+ dst_hw = NULL;
+ }
+
+ nskb = arp_create(be16_to_cpu(arphdr->ar_op),
+ be16_to_cpu(skb->protocol),
+ arp_data->arp_dip,
+ dev,
+ arp_data->arp_sip,
+ dst_hw,
+ remac,
+ target_hw);
+
+ /* prepare place for the headers. */
+ if (nskb)
+ skb_reserve(nskb, ETH_HLEN);
+
+ return nskb;
+}
+
+static struct sk_buff *get_parent_skb_ip(struct slave *slave,
+ struct sk_buff *skb)
+{
+ /* nop */
+ return skb;
+}
+
+/* get_parent_skb -- called in RX flow */
+static struct sk_buff *get_parent_skb(struct slave *slave,
+ struct sk_buff *skb, u8 *remac)
+{
+ struct net_device *dev = slave->dev->master;
+ struct sk_buff *nskb = NULL;
+ struct ethhdr *ethh;
+
+ if (skb->protocol == htons(ETH_P_ARP) ||
+ skb->protocol == htons(ETH_P_RARP))
+ nskb = get_parent_skb_arp(slave, skb, remac);
+ else
+ nskb = get_parent_skb_ip(slave, skb);
+
+ /* if new skb could not be adjusted/allocated, abort */
+ if (!nskb)
+ goto err;
+
+ /* at this point, we can free old skb if it was cloned */
+ if (nskb && (nskb != skb))
+ dev_kfree_skb(skb);
+
+ skb = nskb;
+
+ /* build ethernet header */
+ ethh = (struct ethhdr *)skb_push(skb, ETH_HLEN);
+ ethh->h_proto = skb->protocol;
+ memcpy(ethh->h_source, remac, ETH_ALEN);
+ memcpy(ethh->h_dest, slave->emac, ETH_ALEN);
+
+ /* zero padding whenever is needed (arp for example).to ETH_ZLEN size */
+ if (unlikely((skb->len < ETH_ZLEN))) {
+ if ((skb->tail + (ETH_ZLEN - skb->len) > skb->end) ||
+ skb_is_nonlinear(skb))
+ /* nothing */;
+ else
+ memset(skb_put(skb, ETH_ZLEN - skb->len), 0,
+ ETH_ZLEN - skb->len);
+ }
+
+ /* set new skb fields */
+ skb->pkt_type = PACKET_HOST;
+ /*
+ * use master dev, to allow netpoll_receive_skb()
+ * in netif_receive_skb()
+ */
+ skb->dev = dev;
+
+ /* pull the Ethernet header and update other fields */
+ skb->protocol = eth_type_trans(skb, skb->dev);
+
+ return skb;
+
+err:
+ /* got error after nskb was adjusted/allocated */
+ if (nskb && (nskb != skb))
+ dev_kfree_skb(nskb);
+
+ return NULL;
+}
+
+static int parent_rx(struct sk_buff *skb, struct slave *slave)
+{
+ struct net_device *slave_dev = skb->dev;
+ struct net_device *parent_dev = slave_dev->master;
+ struct parent *parent = netdev_priv(parent_dev);
+ struct eipoib_cb_data *data = IPOIB_HANDLER_CB(skb);
+ struct napi_struct *napi = data->rx.napi;
+ struct sk_buff *nskb;
+ int rc = 0;
+ u8 remac[ETH_ALEN];
+ int vlan_tag;
+
+ build_neigh_mac(remac, data->rx.sqpn, data->rx.slid);
+
+ read_lock_bh(&parent->lock);
+
+ if (unlikely(skb_headroom(skb) < ETH_HLEN)) {
+ pr_warn("%s: small headroom %d < %d\n",
+ skb->dev->name, skb_headroom(skb), ETH_HLEN);
+ ++parent->port_stats.rx_skb_errors;
+ goto drop;
+ }
+
+ /* learn neighs based on ARP snooping */
+ if (unlikely(ntohs(skb->protocol) == ETH_P_ARP)) {
+ read_unlock_bh(&parent->lock);
+ write_lock_bh(&parent->lock);
+ neigh_learn(slave, skb, remac);
+ write_unlock_bh(&parent->lock);
+ read_lock_bh(&parent->lock);
+ }
+
+ nskb = get_parent_skb(slave, skb, remac);
+ if (unlikely(!nskb)) {
+ ++parent->port_stats.rx_skb_errors;
+ pr_warn("%s: failed to create parent_skb\n",
+ skb->dev->name);
+ goto drop;
+ } else
+ skb = nskb;
+
+ vlan_tag = slave->vlan & 0xfff;
+ if (vlan_tag) {
+ skb = __vlan_hwaccel_put_tag(skb, vlan_tag);
+ if (!skb) {
+ pr_err("%s failed to insert VLAN tag\n",
+ skb->dev->name);
+ goto drop;
+ }
+ ++parent->port_stats.rx_vlan;
+ }
+
+ if (napi)
+ rc = napi_gro_receive(napi, skb);
+ else
+ rc = netif_receive_skb(skb);
+
+ read_unlock_bh(&parent->lock);
+
+ return rc;
+
+drop:
+ dev_kfree_skb_any(skb);
+ read_unlock_bh(&parent->lock);
+
+ return NET_RX_DROP;
+}
+
+static rx_handler_result_t eipoib_handle_frame(struct sk_buff **pskb)
+{
+ struct sk_buff *skb = *pskb;
+ struct slave *slave;
+
+ slave = eipoib_slave_get_rcu(skb->dev);
+
+ parent_rx(skb, slave);
+
+ return RX_HANDLER_CONSUMED;
+}
+
+static netdev_tx_t parent_tx(struct sk_buff *skb, struct net_device *dev)
+{
+ struct parent *parent = netdev_priv(dev);
+ struct slave *slave = NULL;
+ struct ethhdr *ethh = (struct ethhdr *)(skb->data);
+ struct sk_buff *nskb;
+ int rc;
+ u16 vlan;
+ u8 mac_no_admin_bit[ETH_ALEN];
+
+ read_lock_bh(&parent->lock);
+
+ if (unlikely(!IS_E_IPOIB_PROTO(ethh->h_proto))) {
+ ++parent->port_stats.tx_proto_errors;
+ goto drop;
+ }
+ /* assume: only orphan skb's */
+ if (unlikely(skb_shared(skb))) {
+ ++parent->port_stats.tx_shared;
+ goto drop;
+ }
+
+ /* obtain VLAN information if present */
+ if (vlan_tx_tag_present(skb)) {
+ vlan = vlan_tx_tag_get(skb) & 0xfff;
+ ++parent->port_stats.tx_vlan;
+ } else {
+ vlan = VLAN_N_VID;
+ }
+
+ /*
+ * for live migration: mask the admin bit if exists.
+ * only in ARP packets that came from parent's VIF interface.
+ */
+ if (unlikely((htons(ETH_P_ARP) == ethh->h_proto) &&
+ !memcmp(parent->dev->dev_addr + 1, ethh->h_source + 1, ETH_ALEN - 1))) {
+ /* parent's VIF: */
+ memcpy(mac_no_admin_bit, ethh->h_source, ETH_ALEN);
+ mac_no_admin_bit[0] = mac_no_admin_bit[0] & 0xFD;
+ /* get slave, and queue packet */
+ slave = get_slave_by_mac_and_vlan(parent, mac_no_admin_bit, vlan);
+ }
+ /* get slave, and queue packet */
+ if (!slave)
+ slave = get_slave_by_mac_and_vlan(parent, ethh->h_source, vlan);
+ if (unlikely(!slave)) {
+ pr_info("vif: %pM with vlan: %d miss for parent: %s\n",
+ ethh->h_source, vlan, parent->ipoib_main_interface);
+ ++parent->port_stats.tx_vif_miss;
+ goto drop;
+ }
+
+ nskb = get_slave_skb(slave, skb);
+ if (unlikely(!nskb)) {
+ ++parent->port_stats.tx_skb_errors;
+ goto drop;
+ } else
+ skb = nskb;
+
+ /*
+ * VST mode: removes the vlan tag in the tx (will add it in the rx)
+ * the slave is from IPoIB and it is NETIF_F_VLAN_CHALLENGED,
+ * so must remove the vlan tag.
+ */
+ if (vlan != VLAN_N_VID)
+ skb->vlan_tci = 0;
+
+ /* arp packets: */
+ if (skb->protocol == htons(ETH_P_ARP) ||
+ skb->protocol == htons(ETH_P_RARP)) {
+ arp_xmit(skb);
+ goto out;
+ }
+
+ /* ip packets */
+ skb_record_rx_queue(skb, skb_get_queue_mapping(skb));
+
+ rc = dev_queue_xmit(skb);
+ if (unlikely(rc)) {
+ pr_err("slave tx method failed %d\n", rc);
+ ++parent->port_stats.tx_slave_err;
+ dev_kfree_skb(skb);
+ }
+
+ goto out;
+
+drop:
+ ++parent->port_stats.tx_parent_dropped;
+ dev_kfree_skb(skb);
+
+out:
+ read_unlock_bh(&parent->lock);
+ return NETDEV_TX_OK;
+}
+
+static int parent_open(struct net_device *parent_dev)
+{
+ struct parent *parent = netdev_priv(parent_dev);
+
+ parent->kill_timers = 0;
+ INIT_DELAYED_WORK(&parent->neigh_learn_work, neigh_learn_task);
+ INIT_DELAYED_WORK(&parent->emac_ip_work, emac_info_clean_task);
+ INIT_DELAYED_WORK(&parent->migrate_out_work, migrate_out_work_task);
+ return 0;
+}
+
+static int parent_close(struct net_device *parent_dev)
+{
+ struct parent *parent = netdev_priv(parent_dev);
+
+ write_lock_bh(&parent->lock);
+ parent->kill_timers = 1;
+ write_unlock_bh(&parent->lock);
+
+ cancel_delayed_work(&parent->neigh_learn_work);
+ cancel_delayed_work(&parent->emac_ip_work);
+ cancel_delayed_work(&parent->migrate_out_work);
+
+ return 0;
+}
+
+
+static void parent_deinit(struct net_device *parent_dev)
+{
+ struct parent *parent = netdev_priv(parent_dev);
+
+ list_del(&parent->parent_list);
+
+ parent_work_cancel_all(parent);
+}
+
+static void parent_uninit(struct net_device *parent_dev)
+{
+ struct parent *parent = netdev_priv(parent_dev);
+
+ parent_deinit(parent_dev);
+ parent_destroy_sysfs_entry(parent);
+
+ if (parent->wq)
+ destroy_workqueue(parent->wq);
+}
+
+static struct lock_class_key parent_netdev_xmit_lock_key;
+static struct lock_class_key parent_netdev_addr_lock_key;
+
+static void parent_set_lockdep_class_one(struct net_device *dev,
+ struct netdev_queue *txq,
+ void *_unused)
+{
+ lockdep_set_class(&txq->_xmit_lock,
+ &parent_netdev_xmit_lock_key);
+}
+
+static void parent_set_lockdep_class(struct net_device *dev)
+{
+ lockdep_set_class(&dev->addr_list_lock,
+ &parent_netdev_addr_lock_key);
+ netdev_for_each_tx_queue(dev, parent_set_lockdep_class_one, NULL);
+}
+
+static int parent_init(struct net_device *parent_dev)
+{
+ struct parent *parent = netdev_priv(parent_dev);
+
+ parent->wq = create_singlethread_workqueue(parent_dev->name);
+ if (!parent->wq)
+ return -ENOMEM;
+
+ parent_set_lockdep_class(parent_dev);
+
+ list_add_tail(&parent->parent_list, &parent_dev_list);
+
+ return 0;
+}
+
+static u16 parent_select_q(struct net_device *dev, struct sk_buff *skb)
+{
+ return skb_tx_hash(dev, skb);
+}
+
+static int parent_add_vif_param(struct net_device *parent_dev,
+ struct net_device *new_vif_dev,
+ u16 vlan, u8 *mac)
+{
+ struct parent *parent = netdev_priv(parent_dev);
+ struct slave *new_slave, *slave_tmp;
+ int ret = 0;
+
+ if (!is_valid_ether_addr(mac)) {
+ pr_err("Invalid mac input for slave:%pM \n", mac);
+ return -EINVAL;
+ }
+
+ write_lock_bh(&parent->lock);
+
+ new_slave = get_slave_by_dev(parent, new_vif_dev);
+ if (!new_slave) {
+ pr_err("%s: ERROR no slave:%s.!!!! \n",
+ __func__, new_vif_dev->name);
+ ret = -EINVAL;
+ goto out;
+ }
+
+ if (!is_zero_ether_addr(new_slave->emac)) {
+ pr_err("slave %s mac already set to %pM\n",
+ new_slave->dev->name, new_slave->emac);
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /* check another slave has this mac/vlan */
+ parent_for_each_slave(parent, slave_tmp) {
+ if (!memcmp(slave_tmp->emac, mac, ETH_ALEN) &&
+ slave_tmp->vlan == new_slave->vlan) {
+ pr_err("cannot update %s, slave %s already has"
+ " vlan 0x%x mac %pM\n",
+ parent->dev->name, new_slave->dev->name,
+ slave_tmp->vlan,
+ mac);
+ ret = -EINVAL;
+ goto out;
+ }
+ }
+
+ /* ready to go */
+ pr_info("slave %s mac is set to %pM, vlan set to: %d\n",
+ new_slave->dev->name, mac, vlan);
+
+ memcpy(new_slave->emac, mac, ETH_ALEN);
+
+ new_slave->vlan = vlan;
+
+out:
+ write_unlock_bh(&parent->lock);
+
+ return ret;
+}
+
+static const struct net_device_ops parent_netdev_ops = {
+ .ndo_init = parent_init,
+ .ndo_uninit = parent_uninit,
+ .ndo_open = parent_open,
+ .ndo_stop = parent_close,
+ .ndo_start_xmit = parent_tx,
+ .ndo_select_queue = parent_select_q,
+ /* parnt mtu is min(slaves_mtus) */
+ .ndo_change_mtu = NULL,
+ .ndo_fix_features = parent_fix_features,
+ /*
+ * initial mac address is randomized, can be changed
+ * thru this func later
+ */
+ .ndo_set_mac_address = eth_mac_addr,
+ .ndo_get_stats64 = parent_get_stats,
+ .ndo_add_slave = parent_enslave,
+ .ndo_del_slave = parent_release_slave,
+ .ndo_set_vif_param = parent_add_vif_param,
+};
+
+static void parent_setup(struct net_device *parent_dev)
+{
+ struct parent *parent = netdev_priv(parent_dev);
+
+ /* initialize rwlocks */
+ rwlock_init(&parent->lock);
+
+ /* Initialize pointers */
+ parent->dev = parent_dev;
+ INIT_LIST_HEAD(&parent->neigh_add_list);
+ INIT_LIST_HEAD(&parent->slave_list);
+ INIT_LIST_HEAD(&parent->emac_ip_list);
+ /* Initialize the device entry points */
+ ether_setup(parent_dev);
+ /* parent_dev->hard_header_len is adjusted later */
+ parent_dev->netdev_ops = &parent_netdev_ops;
+ parent_set_ethtool_ops(parent_dev);
+
+ /* Initialize the device options */
+ parent_dev->tx_queue_len = 0;
+ /* mark the parent intf as pif (master of other vifs.) */
+ parent_dev->priv_flags = IFF_EIPOIB_PIF;
+
+ parent_dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM |
+ NETIF_F_RXCSUM | NETIF_F_GRO | NETIF_F_TSO;
+
+ parent_dev->features = parent_dev->hw_features;
+ parent_dev->vlan_features = parent_dev->hw_features;
+
+ parent_dev->features |= PARENT_VLAN_FEATURES;
+}
+
+/*
+ * Create a new parent based on the specified name and parent parameters.
+ * Caller must NOT hold rtnl_lock; we need to release it here before we
+ * set up our sysfs entries.
+ */
+static struct parent *parent_create(struct net_device *ibd)
+{
+ struct net_device *parent_dev;
+ u32 num_queues;
+ int rc;
+ union ib_gid gid;
+ struct parent *parent = NULL;
+ int i, j;
+
+ memcpy(&gid, ibd->dev_addr + 4, sizeof(union ib_gid));
+ num_queues = num_online_cpus();
+ num_queues = roundup_pow_of_two(num_queues);
+
+ parent_dev = alloc_netdev_mq(sizeof(struct parent), "",
+ parent_setup, num_queues);
+ if (!parent_dev) {
+ pr_err("%s failed to alloc netdev!\n", ibd->name);
+ rc = -ENOMEM;
+ goto out_rtnl;
+ }
+
+ rc = dev_alloc_name(parent_dev, "eth%d");
+ if (rc < 0)
+ goto out_netdev;
+
+ /* eIPoIB interface mac format. */
+ for (i = 0, j = 0; i < 8; i++) {
+ if ((PARENT_MAC_MASK >> i) & 0x1) {
+ if (j < 6) /* only 6 bytes eth address */
+ parent_dev->dev_addr[j] =
+ gid.raw[GUID_LEN + i];
+ j++;
+ }
+ }
+
+ /* assuming that the ibd->dev.parent was alreadey been set. */
+ SET_NETDEV_DEV(parent_dev, ibd->dev.parent);
+
+ rc = register_netdevice(parent_dev);
+ if (rc < 0)
+ goto out_parent;
+
+ dev_net_set(parent_dev, &init_net);
+
+ rc = parent_create_sysfs_entry(netdev_priv(parent_dev));
+ if (rc < 0)
+ goto out_unreg;
+
+ parent = netdev_priv(parent_dev);
+ memcpy(parent->gid.raw, gid.raw, GID_LEN);
+ strncpy(parent->ipoib_main_interface, ibd->name, IFNAMSIZ);
+ parent_dev->dev_id = ibd->dev_id;
+
+ return parent;
+
+out_unreg:
+ unregister_netdevice(parent_dev);
+out_parent:
+ parent_deinit(parent_dev);
+out_netdev:
+ free_netdev(parent_dev);
+out_rtnl:
+ return ERR_PTR(rc);
+}
+
+
+static void parent_free(struct parent *parent)
+{
+ struct net_device *parent_dev = parent->dev;
+
+ parent_work_cancel_all(parent);
+
+ parent_release_all(parent_dev);
+
+ unregister_netdevice(parent_dev);
+}
+
+static void parent_free_all(void)
+{
+ struct parent *parent, *nxt;
+
+ list_for_each_entry_safe(parent, nxt, &parent_dev_list, parent_list)
+ parent_free(parent);
+}
+
+/* netdev events handlers */
+static inline int is_ipoib_pif_intf(struct net_device *dev)
+{
+ if (ARPHRD_INFINIBAND == dev->type && dev->priv_flags & IFF_EIPOIB_PIF)
+ return 1;
+ return 0;
+}
+
+static int parent_event_changename(struct parent *parent)
+{
+ parent_destroy_sysfs_entry(parent);
+
+ parent_create_sysfs_entry(parent);
+
+ return NOTIFY_DONE;
+}
+
+static int parent_master_netdev_event(unsigned long event,
+ struct net_device *parent_dev)
+{
+ struct parent *event_parent = netdev_priv(parent_dev);
+
+ switch (event) {
+ case NETDEV_CHANGENAME:
+ pr_info("%s: got NETDEV_CHANGENAME event", parent_dev->name);
+ return parent_event_changename(event_parent);
+ default:
+ break;
+ }
+
+ return NOTIFY_DONE;
+}
+
+static int parent_slave_netdev_event(unsigned long event,
+ struct net_device *slave_dev)
+{
+ struct net_device *parent_dev = slave_dev->master;
+ struct parent *parent = netdev_priv(parent_dev);
+
+ if (!parent_dev) {
+ pr_err("slave:%s has no parent.\n", slave_dev->name);
+ return NOTIFY_DONE;
+ }
+
+ switch (event) {
+ case NETDEV_UNREGISTER:
+ parent_release_slave(parent_dev, slave_dev);
+ break;
+ case NETDEV_CHANGE:
+ case NETDEV_UP:
+ case NETDEV_DOWN:
+ parent_set_carrier(parent);
+ break;
+ case NETDEV_CHANGEMTU:
+ parent_set_mtu(parent);
+ break;
+ case NETDEV_CHANGENAME:
+ break;
+ case NETDEV_FEAT_CHANGE:
+ parent_compute_features(parent);
+ break;
+ default:
+ break;
+ }
+
+ return NOTIFY_DONE;
+}
+
+static int eipoib_netdev_event(struct notifier_block *this,
+ unsigned long event, void *ptr)
+{
+ struct net_device *event_dev = (struct net_device *)ptr;
+
+ if (dev_net(event_dev) != &init_net)
+ return NOTIFY_DONE;
+
+ if (is_parent(event_dev))
+ return parent_master_netdev_event(event, event_dev);
+
+ if (is_slave(event_dev))
+ return parent_slave_netdev_event(event, event_dev);
+ /*
+ * general network device triggers event, check if it is new
+ * ib interface that we want to enslave.
+ */
+ return eipoib_device_event(this, event, ptr);
+}
+
+static struct notifier_block parent_netdev_notifier = {
+ .notifier_call = eipoib_netdev_event,
+};
+
+static int eipoib_device_event(struct notifier_block *unused,
+ unsigned long event, void *ptr)
+{
+ struct net_device *dev = ptr;
+ struct parent *parent;
+
+ if (!is_ipoib_pif_intf(dev))
+ return NOTIFY_DONE;
+
+ switch (event) {
+ case NETDEV_REGISTER:
+ parent = parent_create(dev);
+ if (IS_ERR(parent)) {
+ pr_warn("failed to create parent for %s\n",
+ dev->name);
+ break;
+ }
+ break;
+ case NETDEV_UNREGISTER:
+ parent = get_parent_by_pif_name(dev->name);
+ if (parent)
+ parent_free(parent);
+ break;
+ default:
+ break;
+ }
+
+ return NOTIFY_DONE;
+}
+
+static int __init mod_init(void)
+{
+ int rc;
+
+ pr_info(DRV_NAME": %s", version);
+
+ rc = register_pernet_subsys(&eipoib_net_ops);
+ if (rc)
+ goto out;
+
+ rc = register_netdevice_notifier(&parent_netdev_notifier);
+ if (rc) {
+ pr_err("%s failed to register_netdevice_notifier, rc: 0x%x\n",
+ __func__, rc);
+ goto unreg_subsys;
+ }
+
+ goto out;
+
+unreg_subsys:
+ unregister_pernet_subsys(&eipoib_net_ops);
+out:
+ return rc;
+
+}
+
+static void __exit mod_exit(void)
+{
+ unregister_netdevice_notifier(&parent_netdev_notifier);
+
+ unregister_pernet_subsys(&eipoib_net_ops);
+
+ rtnl_lock();
+ parent_free_all();
+ rtnl_unlock();
+}
+
+module_init(mod_init);
+module_exit(mod_exit);
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_VERSION(DRV_VERSION);
+MODULE_DESCRIPTION(DRV_DESCRIPTION ", v" DRV_VERSION);
+MODULE_AUTHOR("Ali Ayoub && Erez Shitrit");
--
1.7.1
^ permalink raw reply related
* Re: assert_cfg80211_lock warning with Linux v3.5-8833-g2d53492
From: Johannes Berg @ 2012-08-01 17:14 UTC (permalink / raw)
To: Seth Forshee
Cc: Arend van Spriel, John W. Linville, Josh Boyer, Brett Rudley,
Roland Vossen, linux-wireless, netdev
In-Reply-To: <20120801161959.GC22963@thinkpad-t410>
On Wed, 2012-08-01 at 11:19 -0500, Seth Forshee wrote:
> On Wed, Aug 01, 2012 at 05:53:58PM +0200, Johannes Berg wrote:
> > On Wed, 2012-08-01 at 17:51 +0200, Arend van Spriel wrote:
> > > On 08/01/2012 05:38 PM, Arend van Spriel wrote:
> > > >> brcmsmac needs to hold cfg80211_mutex before calling freq_reg_info...
> > > >> >
> > > >> > It looks like those calls were added in mid-June.
> > > >> >
> > > > I think mid-june sounds about right. We never observed the warning when
> > > > changes to use regulatory infrastructure were tested/reviewed. Should
> > > > this precondition be mentioned in cfg80211.h?
> > > >
> > > > Gr. AvS
> > >
> > > Diving in further it seems brcmsmac can not grab the cfg80211_mutex. So
> > > another solution is needed.
> >
> > Yeah I was going to say -- how can it possibly access that? It seems
> > that in some patch the API got broken, it should be taking the lock or
> > whatever ... I'll leave it to Luis to sort out though :-P
>
> In other drivers freq_reg_info only seems to get used by the regulatory
> notifiers, which get called with the lock held. brcmsmac is wanting to
> know whether or not OFDM is allowed when setting the channel though, and
> I didn't find that information anywhere outside the regulatory
> information. If there's another way then calling freq_reg_info() could
> be avoided. Or maybe we could add an OFDM flag to the channel
> information?
Seems reasonable to add the flags (or some of them) to the channel
flags, yeah.
johannes
^ permalink raw reply
* [PATCH V2 10/12] net/eipoib: Add sysfs support
From: Or Gerlitz @ 2012-08-01 17:09 UTC (permalink / raw)
To: davem; +Cc: roland, netdev, ali, sean.hefty, Erez Shitrit, Or Gerlitz
In-Reply-To: <1343840975-3252-1-git-send-email-ogerlitz@mellanox.com>
From: Erez Shitrit <erezsh@mellanox.co.il>
The management interface for the driver was using sysfs.
While most of this usage (all the "set" operations) was ported to use
rtnetlink, still some sysfs "show" entries were left in this posting,
till its clear if/how they can be implemented otherwise.
Here are few sysfs commands that are used in order to get
information from the driver,
1. get parent's slaves:
$ cat /sys/class/net/ethZ/eth/slaves
where ethZ is the driver interface
2. see the list of ipoib interfaces enslaved under eipoib interface,
$ cat /sys/class/net/ethX/eth/vifs
for example:
$ cat /sys/class/net/eth4/eth/vifs
SLAVE=ib0.1 MAC=9a:c2:1f:d7:3b:63 VLAN=N/A
SLAVE=ib0.2 MAC=52:54:00:60:55:88 VLAN=N/A
SLAVE=ib0.3 MAC=52:54:00:60:55:89 VLAN=N/A
Signed-off-by: Erez Shitrit <erezsh@mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
---
drivers/net/eipoib/eth_ipoib_sysfs.c | 435 ++++++++++++++++++++++++++++++++++
1 files changed, 435 insertions(+), 0 deletions(-)
create mode 100644 drivers/net/eipoib/eth_ipoib_sysfs.c
diff --git a/drivers/net/eipoib/eth_ipoib_sysfs.c b/drivers/net/eipoib/eth_ipoib_sysfs.c
new file mode 100644
index 0000000..8217e32
--- /dev/null
+++ b/drivers/net/eipoib/eth_ipoib_sysfs.c
@@ -0,0 +1,435 @@
+/*
+ * Copyright (c) 2012 Mellanox Technologies. All rights reserved
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * openfabric.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/sched.h>
+#include <linux/fs.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/netdevice.h>
+#include <linux/inetdevice.h>
+#include <linux/in.h>
+#include <linux/sysfs.h>
+#include <linux/ctype.h>
+#include <linux/inet.h>
+#include <linux/rtnetlink.h>
+#include <linux/etherdevice.h>
+#include <net/net_namespace.h>
+
+#include "eth_ipoib.h"
+
+#define to_dev(obj) container_of(obj, struct device, kobj)
+#define to_parent(cd) ((struct parent *)(netdev_priv(to_net_dev(cd))))
+#define MOD_NA_STRING "N/A"
+
+#define _sprintf(p, buf, format, arg...) \
+((PAGE_SIZE - (int)(p - buf)) <= 0 ? 0 : \
+ scnprintf(p, PAGE_SIZE - (int)(p - buf), format, ## arg))\
+
+#define _end_of_line(_p, _buf) \
+do { if (_p - _buf) /* eat the leftover space */ \
+ buf[_p - _buf - 1] = '\n'; \
+} while (0)
+
+/* helper functions */
+static int get_emac(u8 *mac, char *s)
+{
+ if (sscanf(s, "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx",
+ mac + 0, mac + 1, mac + 2, mac + 3, mac + 4,
+ mac + 5) != 6)
+ return -1;
+
+ return 0;
+}
+
+static int get_imac(u8 *mac, char *s)
+{
+ if (sscanf(s, "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx:%hhx:%hhx:"
+ "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx:%hhx:%hhx:"
+ "%hhx:%hhx:%hhx:%hhx",
+ mac + 0, mac + 1, mac + 2, mac + 3, mac + 4,
+ mac + 5, mac + 6, mac + 7, mac + 8, mac + 9,
+ mac + 10, mac + 11, mac + 12, mac + 13,
+ mac + 14, mac + 15, mac + 16, mac + 17,
+ mac + 18, mac + 19) != 20)
+ return -1;
+
+ return 0;
+}
+
+/* show/store functions per module (CLASS_ATTR) */
+static ssize_t show_parents(struct class *cls, struct class_attribute *attr,
+ char *buf)
+{
+ char *p = buf;
+ struct parent *parent;
+
+ rtnl_lock(); /* because of parent_dev_list */
+
+ list_for_each_entry(parent, &parent_dev_list, parent_list) {
+ p += _sprintf(p, buf, "%s over IB port: %s\n",
+ parent->dev->name,
+ parent->ipoib_main_interface);
+ }
+ _end_of_line(p, buf);
+
+ rtnl_unlock();
+ return (ssize_t)(p - buf);
+}
+
+/* show/store functions per parent (DEVICE_ATTR) */
+static ssize_t parent_show_neighs(struct device *d,
+ struct device_attribute *attr, char *buf)
+{
+ struct slave *slave;
+ struct neigh *neigh;
+ struct parent *parent = to_parent(d);
+ char *p = buf;
+
+ read_lock_bh(&parent->lock);
+ parent_for_each_slave(parent, slave) {
+ list_for_each_entry(neigh, &slave->neigh_list, list) {
+ p += _sprintf(p, buf, "SLAVE=%-10s EMAC=%pM IMAC=%pM:%pM:%pM:%.2x:%.2x\n",
+ slave->dev->name,
+ neigh->emac,
+ neigh->imac, neigh->imac + 6, neigh->imac + 12,
+ neigh->imac[18], neigh->imac[19]);
+ }
+ }
+
+ read_unlock_bh(&parent->lock);
+
+ _end_of_line(p, buf);
+
+ return (ssize_t)(p - buf);
+}
+
+struct neigh *parent_get_neigh_cmd(char op,
+ char *ifname, u8 *remac, u8 *rimac)
+{
+ struct neigh *neigh_cmd;
+
+ neigh_cmd = kzalloc(sizeof *neigh_cmd, GFP_ATOMIC);
+ if (!neigh_cmd) {
+ pr_err("%s cannot allocate neigh struct\n", ifname);
+ goto out;
+ }
+
+ /*
+ * populate emac field so it can be used easily
+ * in neigh_cmd_find_by_mac()
+ */
+ memcpy(neigh_cmd->emac, remac, ETH_ALEN);
+ memcpy(neigh_cmd->imac, rimac, INFINIBAND_ALEN);
+
+ /* prepare the command as a string */
+ sprintf(neigh_cmd->cmd, "%c%s %pM %pM:%pM:%pM:%.2x:%.2x",
+ op, ifname, remac, rimac, rimac + 6, rimac + 12, rimac[18], rimac[19]);
+out:
+ return neigh_cmd;
+}
+
+/* write_lock_bh(&parent->lock) must be held */
+ssize_t __parent_store_neighs(struct device *d,
+ struct device_attribute *attr,
+ const char *buffer, size_t count)
+{
+ char command[IFNAMSIZ + 1] = { 0, };
+ char emac_str[ETH_ALEN * 3] = { 0, };
+ u8 emac[ETH_ALEN];
+ char imac_str[INFINIBAND_ALEN * 3] = { 0, };
+ u8 imac[INFINIBAND_ALEN];
+ char *ifname;
+ int found = 0, ret = count;
+ struct slave *slave = NULL, *slave_tmp;
+ struct neigh *neigh;
+ struct parent *parent = to_parent(d);
+
+ sscanf(buffer, "%s %s %s", command, emac_str, imac_str);
+
+ /* check ifname */
+ ifname = command + 1;
+ if ((strlen(command) <= 1) || !dev_valid_name(ifname) ||
+ (command[0] != '+' && command[0] != '-'))
+ goto err_no_cmd;
+
+ /* check if ifname exist */
+ parent_for_each_slave(parent, slave_tmp) {
+ if (!strcmp(slave_tmp->dev->name, ifname)) {
+ found = 1;
+ slave = slave_tmp;
+ }
+ }
+
+ if (!found) {
+ pr_err("%s could not find slave\n", ifname);
+ ret = -EINVAL;
+ goto out;
+ }
+
+ if (get_emac(emac, emac_str)) {
+ pr_err("%s bad emac %s\n", ifname, emac_str);
+ ret = -EINVAL;
+ goto out;
+ }
+
+ if (get_imac(imac, imac_str)) {
+ pr_err("%s bad imac %s\n", ifname, imac_str);
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /* process command */
+ if (command[0] == '+') {
+ found = 0;
+ list_for_each_entry(neigh, &slave->neigh_list, list) {
+ if (!memcmp(neigh->emac, emac, ETH_ALEN))
+ found = 1;
+ }
+
+ if (found) {
+ pr_err("%s: cannot update neigh, slave already has "
+ "this neigh mac %pM\n",
+ slave->dev->name, emac);
+ ret = -EINVAL;
+ goto out;
+ }
+
+ neigh = kzalloc(sizeof *neigh, GFP_ATOMIC);
+ if (!neigh) {
+ pr_err("%s cannot allocate neigh struct\n",
+ slave->dev->name);
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ /* ready to go */
+ pr_info("%s: slave %s neigh mac is set to %pM\n",
+ ifname, parent->dev->name, emac);
+ memcpy(neigh->emac, emac, ETH_ALEN);
+ memcpy(neigh->imac, imac, INFINIBAND_ALEN);
+
+ list_add_tail(&neigh->list, &slave->neigh_list);
+
+ goto out;
+ }
+
+ if (command[0] == '-') {
+ found = 0;
+ list_for_each_entry(neigh, &slave->neigh_list, list) {
+ if (!memcmp(neigh->emac, emac, ETH_ALEN))
+ found = 1;
+ }
+
+ if (!found) {
+ pr_err("%s cannot delete neigh mac %pM\n",
+ ifname, emac);
+ ret = -EINVAL;
+ goto out;
+ }
+
+ list_del(&neigh->list);
+ kfree(neigh);
+
+ goto out;
+ }
+
+err_no_cmd:
+ pr_err("%s USAGE: (-|+)ifname emac imac\n", DRV_NAME);
+ ret = -EPERM;
+
+out:
+ return ret;
+}
+
+static DEVICE_ATTR(neighs, S_IRUGO, parent_show_neighs,
+ NULL);
+
+static ssize_t parent_show_vifs(struct device *d,
+ struct device_attribute *attr, char *buf)
+{
+ struct slave *slave;
+ struct parent *parent = to_parent(d);
+ char *p = buf;
+
+ read_lock_bh(&parent->lock);
+ parent_for_each_slave(parent, slave) {
+ if (is_zero_ether_addr(slave->emac)) {
+ p += _sprintf(p, buf, "SLAVE=%-10s MAC=%-17s "
+ "VLAN=%s\n", slave->dev->name,
+ MOD_NA_STRING, MOD_NA_STRING);
+ } else if (slave->vlan == VLAN_N_VID) {
+ p += _sprintf(p, buf, "SLAVE=%-10s MAC=%pM VLAN=%s\n",
+ slave->dev->name,
+ slave->emac,
+ MOD_NA_STRING);
+ } else {
+ p += _sprintf(p, buf, "SLAVE=%-10s MAC=%pM VLAN=%d\n",
+ slave->dev->name,
+ slave->emac,
+ slave->vlan);
+ }
+ }
+ read_unlock_bh(&parent->lock);
+
+ _end_of_line(p, buf);
+
+ return (ssize_t)(p - buf);
+}
+
+static DEVICE_ATTR(vifs, S_IRUGO, parent_show_vifs,
+ NULL);
+
+static ssize_t parent_show_slaves(struct device *d,
+ struct device_attribute *attr, char *buf)
+{
+ struct slave *slave;
+ struct parent *parent = to_parent(d);
+ char *p = buf;
+
+ read_lock_bh(&parent->lock);
+ parent_for_each_slave(parent, slave)
+ p += _sprintf(p, buf, "%s\n", slave->dev->name);
+ read_unlock_bh(&parent->lock);
+
+ _end_of_line(p, buf);
+
+ return (ssize_t)(p - buf);
+}
+
+static DEVICE_ATTR(slaves, S_IRUGO, parent_show_slaves,
+ NULL);
+
+/* sysfs create/destroy functions */
+static struct attribute *per_parent_attrs[] = {
+ &dev_attr_slaves.attr, /* DEVICE_ATTR(slaves..) */
+ &dev_attr_vifs.attr,
+ &dev_attr_neighs.attr,
+ NULL,
+};
+
+/* name spcase support */
+static const void *eipoib_namespace(struct class *cls,
+ const struct class_attribute *attr)
+{
+ const struct eipoib_net *eipoib_n =
+ container_of(attr,
+ struct eipoib_net, class_attr_eipoib_interfaces);
+ return eipoib_n->net;
+}
+
+static struct attribute_group parent_group = {
+ /* per parent sysfs files under: /sys/class/net/<IF>/eth/.. */
+ .name = "eth",
+ .attrs = per_parent_attrs
+};
+
+int create_slave_symlinks(struct net_device *master,
+ struct net_device *slave)
+{
+ char linkname[IFNAMSIZ+7];
+ int ret = 0;
+
+ ret = sysfs_create_link(&(slave->dev.kobj), &(master->dev.kobj),
+ "eth_parent");
+ if (ret)
+ return ret;
+
+ sprintf(linkname, "slave_%s", slave->name);
+ ret = sysfs_create_link(&(master->dev.kobj), &(slave->dev.kobj),
+ linkname);
+ return ret;
+
+}
+
+void destroy_slave_symlinks(struct net_device *master,
+ struct net_device *slave)
+{
+ char linkname[IFNAMSIZ+7];
+
+ sysfs_remove_link(&(slave->dev.kobj), "eth_parent");
+ sprintf(linkname, "slave_%s", slave->name);
+ sysfs_remove_link(&(master->dev.kobj), linkname);
+}
+
+static struct class_attribute class_attr_eth_ipoib_interfaces = {
+ .attr = {
+ .name = "eth_ipoib_interfaces",
+ .mode = S_IWUSR | S_IRUGO,
+ },
+ .show = show_parents,
+ .namespace = eipoib_namespace,
+};
+
+/* per module sysfs file under: /sys/class/net/eth_ipoib_interfaces */
+int mod_create_sysfs(struct eipoib_net *eipoib_n)
+{
+ int rc;
+ /* defined in CLASS_ATTR(eth_ipoib_interfaces..) */
+ eipoib_n->class_attr_eipoib_interfaces =
+ class_attr_eth_ipoib_interfaces;
+
+ sysfs_attr_init(&eipoib_n->class_attr_eipoib_interfaces.attr);
+
+ rc = netdev_class_create_file(&eipoib_n->class_attr_eipoib_interfaces);
+ if (rc)
+ pr_err("%s failed to create sysfs (rc %d)\n",
+ eipoib_n->class_attr_eipoib_interfaces.attr.name, rc);
+
+ return rc;
+}
+
+void mod_destroy_sysfs(struct eipoib_net *eipoib_n)
+{
+ netdev_class_remove_file(&eipoib_n->class_attr_eipoib_interfaces);
+}
+
+int parent_create_sysfs_entry(struct parent *parent)
+{
+ struct net_device *dev = parent->dev;
+ int rc;
+
+ rc = sysfs_create_group(&(dev->dev.kobj), &parent_group);
+ if (rc)
+ pr_info("failed to create sysfs group\n");
+
+ return rc;
+}
+
+void parent_destroy_sysfs_entry(struct parent *parent)
+{
+ struct net_device *dev = parent->dev;
+
+ sysfs_remove_group(&(dev->dev.kobj), &parent_group);
+}
--
1.7.1
^ permalink raw reply related
* Re: assert_cfg80211_lock warning with Linux v3.5-8833-g2d53492
From: Arend van Spriel @ 2012-08-01 17:24 UTC (permalink / raw)
To: Johannes Berg
Cc: John W. Linville, Josh Boyer, Brett Rudley, Roland Vossen,
linux-wireless-u79uwXL29TY76Z2rM5mHXA,
netdev-u79uwXL29TY76Z2rM5mHXA, Seth Forshee, Luis R. Rodriguez
In-Reply-To: <1343836438.4638.5.camel-8upI4CBIZJIJvtFkdXX2HixXY32XiHfO@public.gmane.org>
+ Luis
On 08/01/2012 05:53 PM, Johannes Berg wrote:
> On Wed, 2012-08-01 at 17:51 +0200, Arend van Spriel wrote:
>> On 08/01/2012 05:38 PM, Arend van Spriel wrote:
>>>> brcmsmac needs to hold cfg80211_mutex before calling freq_reg_info...
>>>>>
>>>>> It looks like those calls were added in mid-June.
>>>>>
>>> I think mid-june sounds about right. We never observed the warning when
>>> changes to use regulatory infrastructure were tested/reviewed. Should
>>> this precondition be mentioned in cfg80211.h?
>>>
>>> Gr. AvS
>>
>> Diving in further it seems brcmsmac can not grab the cfg80211_mutex. So
>> another solution is needed.
>
> Yeah I was going to say -- how can it possibly access that? It seems
> that in some patch the API got broken, it should be taking the lock or
> whatever ... I'll leave it to Luis to sort out though :-P
>
> johannes
>
The assert was added by following commit:
commit ac46d48e00349c63650b3cc6f9460fcc183da6a6
Author: Luis R. Rodriguez <lrodriguez-DlyHzToyqoxBDgjK7y7TUQ@public.gmane.org>
Date: Fri May 1 18:44:50 2009 -0400
cfg80211: fix race condition with wiphy_apply_custom_regulatory()
We forgot to lock using the cfg80211_mutex in
wiphy_apply_custom_regulatory(). Without the lock
there is possible race between processing a reply from CRDA
and a driver calling wiphy_apply_custom_regulatory(). During
the processing of the reply from CRDA we free last_request and
wiphy_apply_custom_regulatory() eventually accesses an
element from last_request in the through freq_reg_info_regd().
This is very difficult to reproduce (I haven't), it takes us
3 hours and you need to be banging hard, but the race is obvious
by looking at the code.
This should only affect those who use this caller, which currently
is ath5k, ath9k, and ar9170.
EIP: 0060:[<f8ebec50>] EFLAGS: 00210282 CPU: 1
EIP is at freq_reg_info_regd+0x24/0x121 [cfg80211]
It seems the API was as it currently is when adding regulatory framework
changes in brcmsmac so we should have seen this assert flying by. The
problem is that freq_reg_info() is exposed in cfg80211.h, but as it is
now it can only be used under the cfg80211_mutex lock, ie. in regulatory
notify callback (as Seth indicated).
Gr. AvS
--
To unsubscribe from this list: send the line "unsubscribe linux-wireless" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: assert_cfg80211_lock warning with Linux v3.5-8833-g2d53492
From: Seth Forshee @ 2012-08-01 17:56 UTC (permalink / raw)
To: Johannes Berg, John W. Linville
Cc: Arend van Spriel, Josh Boyer, Brett Rudley, Roland Vossen,
linux-wireless, netdev
In-Reply-To: <1343841285.4638.10.camel@jlt3.sipsolutions.net>
On Wed, Aug 01, 2012 at 07:14:45PM +0200, Johannes Berg wrote:
> On Wed, 2012-08-01 at 11:19 -0500, Seth Forshee wrote:
> > On Wed, Aug 01, 2012 at 05:53:58PM +0200, Johannes Berg wrote:
> > > On Wed, 2012-08-01 at 17:51 +0200, Arend van Spriel wrote:
> > > > On 08/01/2012 05:38 PM, Arend van Spriel wrote:
> > > > >> brcmsmac needs to hold cfg80211_mutex before calling freq_reg_info...
> > > > >> >
> > > > >> > It looks like those calls were added in mid-June.
> > > > >> >
> > > > > I think mid-june sounds about right. We never observed the warning when
> > > > > changes to use regulatory infrastructure were tested/reviewed. Should
> > > > > this precondition be mentioned in cfg80211.h?
> > > > >
> > > > > Gr. AvS
> > > >
> > > > Diving in further it seems brcmsmac can not grab the cfg80211_mutex. So
> > > > another solution is needed.
> > >
> > > Yeah I was going to say -- how can it possibly access that? It seems
> > > that in some patch the API got broken, it should be taking the lock or
> > > whatever ... I'll leave it to Luis to sort out though :-P
> >
> > In other drivers freq_reg_info only seems to get used by the regulatory
> > notifiers, which get called with the lock held. brcmsmac is wanting to
> > know whether or not OFDM is allowed when setting the channel though, and
> > I didn't find that information anywhere outside the regulatory
> > information. If there's another way then calling freq_reg_info() could
> > be avoided. Or maybe we could add an OFDM flag to the channel
> > information?
>
> Seems reasonable to add the flags (or some of them) to the channel
> flags, yeah.
Great, I'll work something up.
Seth
^ permalink raw reply
* Re: binding UDP port 0 with SO_REUSEADDR
From: Eric Dumazet @ 2012-08-01 19:02 UTC (permalink / raw)
To: Tobias S. Josefowitz; +Cc: netdev
In-Reply-To: <CAEZM=bNdyZoTiGYwNM_3v+ro7dEn0q9aTo4040tBDqDSH3HOXg@mail.gmail.com>
On Wed, 2012-08-01 at 13:36 +0200, Tobias S. Josefowitz wrote:
> Hey all,
>
> I recently noticed that binding UDP port 0 with SO_REUSEADDR yields
> unexpected results for me - the kernel occasionally gives out UDP
> ports used by other processes, if they were bound with SO_REUSEADDR,
> too.
>
> I did some digging, it seems that
> f24d43c07e208372aa3d3bff419afbf43ba87698 introduced this behaviour.
> I'm not at all sure if this could/should be called a bug, but I need
> to say, it was severly unexpected at my side, and that probably goes
> for others, too.
>
> Just bringing this to your attention, I have no suggestions on it whatsoever.
And why are you using SO_REUSEADDR on UDP unicast sockets ?
I mean, this is exactly saying " By using this REUSEADDR, I am allowing
this port being used by another process, even from another user"
^ permalink raw reply
* [PATCH] firmware: Remove obsolete Chelsio cxgb3 firmware
From: Tim Gardner @ 2012-08-01 19:17 UTC (permalink / raw)
To: linux-kernel
Cc: Tim Gardner, Paul Gortmaker, Ben Hutchings, James Bottomley,
Dan Williams, Divy Le Ray, netdev
The current firmware version used by the device driver
is 7.12.0
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Ben Hutchings <ben@decadent.org.uk>
Cc: James Bottomley <JBottomley@Parallels.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Divy Le Ray <divy@chelsio.com>
Cc: netdev@vger.kernel.org
Signed-off-by: Tim Gardner <tim.gardner@canonical.com>
---
firmware/Makefile | 1 -
firmware/cxgb3/t3fw-7.10.0.bin.ihex | 1935 -----------------------------------
2 files changed, 1936 deletions(-)
delete mode 100644 firmware/cxgb3/t3fw-7.10.0.bin.ihex
diff --git a/firmware/Makefile b/firmware/Makefile
index 344713b..76628e3 100644
--- a/firmware/Makefile
+++ b/firmware/Makefile
@@ -43,7 +43,6 @@ fw-shipped-$(CONFIG_CASSINI) += sun/cassini.bin
fw-shipped-$(CONFIG_COMPUTONE) += intelliport2.bin
fw-shipped-$(CONFIG_CHELSIO_T3) += cxgb3/t3b_psram-1.1.0.bin \
cxgb3/t3c_psram-1.1.0.bin \
- cxgb3/t3fw-7.10.0.bin \
cxgb3/ael2005_opt_edc.bin \
cxgb3/ael2005_twx_edc.bin \
cxgb3/ael2020_twx_edc.bin
diff --git a/firmware/cxgb3/t3fw-7.10.0.bin.ihex b/firmware/cxgb3/t3fw-7.10.0.bin.ihex
deleted file mode 100644
index 96399d8..0000000
--
1.7.9.5
^ permalink raw reply related
* Re: assert_cfg80211_lock warning with Linux v3.5-8833-g2d53492
From: Arend van Spriel @ 2012-08-01 19:28 UTC (permalink / raw)
To: Johannes Berg
Cc: John W. Linville, Josh Boyer, Brett Rudley, Roland Vossen,
linux-wireless-u79uwXL29TY76Z2rM5mHXA,
netdev-u79uwXL29TY76Z2rM5mHXA, Seth Forshee, Luis R. Rodriguez
In-Reply-To: <50196660.8090001-dY08KVG/lbpWk0Htik3J/w@public.gmane.org>
On 08/01/2012 07:24 PM, Arend van Spriel wrote:
> It seems the API was as it currently is when adding regulatory framework
> changes in brcmsmac so we should have seen this assert flying by. The
> problem is that freq_reg_info() is exposed in cfg80211.h, but as it is
> now it can only be used under the cfg80211_mutex lock, ie. in regulatory
> notify callback (as Seth indicated).
>
> Gr. AvS
Ah, I see you need to run a LOCKDEP-enabled kernel to get this warning.
Gr. AvS
--
To unsubscribe from this list: send the line "unsubscribe linux-wireless" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: v3.5: NETDEV WATCHDOG: eth0 (r8169): transmit queue 0 timed out
From: Francois Romieu @ 2012-08-01 19:24 UTC (permalink / raw)
To: George Spelvin; +Cc: netdev
In-Reply-To: <20120730190236.30339.qmail@science.horizon.com>
George Spelvin <linux@horizon.com> :
[...]
> There are a few local patches, but only two are anywhere close to the
> network interface, and they are test patches designed to fix this.
> Should I get rid of them?
It's up to you but I suggest that you keep them until there is something
better.
As long as the device recovers, you may try and lower the watchdog timeout
as well as increase the Tx ring size a bit (x2 or x4) to minimize the
annoyances.
--
Ueimor
^ permalink raw reply
* Re: binding UDP port 0 with SO_REUSEADDR
From: Tobias S. Josefowitz @ 2012-08-01 19:38 UTC (permalink / raw)
To: Eric Dumazet; +Cc: netdev
In-Reply-To: <1343847776.21269.797.camel@edumazet-glaptop>
On Wed, Aug 1, 2012 at 9:02 PM, Eric Dumazet <eric.dumazet@gmail.com> wrote:
> And why are you using SO_REUSEADDR on UDP unicast sockets ?
Simple. This happens in a "scripting" language. The wrapper code
assumes that it is better to set SO_REUSEADDR than not (which might be
argued, but backwards-compat can be nice) and at the time the code was
written the author must have assumed that even if the 'user' aka
programmer wants to bind to port 0, SO_REUSEADDR doesn't hurt, because
port 0 implicitly meant "please, a free one".
> I mean, this is exactly saying " By using this REUSEADDR, I am allowing
> this port being used by another process, even from another user"
I know. Still, while binding port 0 means "give me any port", I'm
quite sure most people would assume they get a free one. And maybe,
for whatever reasons, you want to share your random port later and
need SO_REUSEADDR because of that. A usecase where someone wants a
randomly chosen free or used port does not come to my mind, though.
Of course, I'm not relying on the kernel to revert back, I adapted the
wrapper code I mentioned above. I still felt like mentioning that it
was kind of unexpected, that's all.
Best,
Tobi
^ permalink raw reply
* Unable to get link beat with Niagara 2264 (Intel 82571EB) and e1000e driver on 3.4.4 (long)
From: Bradley Chapman @ 2012-08-01 22:20 UTC (permalink / raw)
To: netdev
All,
(please CC me as I am not subscribed to netdev)
I recently acquired an Interface Masters Niagara 2264 quad-port GigE
network card, based on the Intel 82571EB network controller (see
http://www.interfacemasters.com/products/2264.html for details). Prior
to using it in a new system I'm planning to build I decided to try it
out on my desktop system, which uses as Asus M4A89TD/PRO USB3
motherboard with the AMD 890FX chipset and a BIOS dated 03/08/2011,
running Debian 6.0.2.1.
I added the e1000e driver to my Linux 3.4.4 kernel config as a loadable
module and inserted it, and got the following:
e1000e: Intel(R) PRO/1000 Network Driver - 1.9.5-k
e1000e: Copyright(c) 1999 - 2012 Intel Corporation.
e1000e 0000:06:00.0: Disabling ASPM L1
e1000e 0000:06:00.0: (unregistered net_device): Interrupt Throttling
Rate (ints/sec) set to dynamic conservative mode
e1000e 0000:06:00.0: irq 91 for MSI/MSI-X
e1000e 0000:06:00.0: eth1: (PCI Express:2.5GT/s:Width x4) 00:0c:bd:01:cd:8c
e1000e 0000:06:00.0: eth1: Intel(R) PRO/1000 Network Connection
e1000e 0000:06:00.0: eth1: MAC: 0, PHY: 4, PBA No: C98149-002
e1000e 0000:06:00.1: Disabling ASPM L1
e1000e 0000:06:00.1: (unregistered net_device): Interrupt Throttling
Rate (ints/sec) set to dynamic conservative mode
e1000e 0000:06:00.1: irq 92 for MSI/MSI-X
udev[1123]: renamed network interface eth1 to eth2
e1000e 0000:06:00.1: eth1: (PCI Express:2.5GT/s:Width x4) 00:0c:bd:01:cd:8d
e1000e 0000:06:00.1: eth1: Intel(R) PRO/1000 Network Connection
e1000e 0000:06:00.1: eth1: MAC: 0, PHY: 4, PBA No: C98149-002
e1000e 0000:05:00.0: Disabling ASPM L1
e1000e 0000:05:00.0: (unregistered net_device): Interrupt Throttling
Rate (ints/sec) set to dynamic conservative mode
e1000e 0000:05:00.0: irq 93 for MSI/MSI-X
udev[8376]: renamed network interface eth1 to eth3
e1000e 0000:05:00.0: eth1: (PCI Express:2.5GT/s:Width x4) 00:0c:bd:01:cd:8a
e1000e 0000:05:00.0: eth1: Intel(R) PRO/1000 Network Connection
e1000e 0000:05:00.0: eth1: MAC: 0, PHY: 4, PBA No: C98149-002
e1000e 0000:05:00.1: Disabling ASPM L1
e1000e 0000:05:00.1: (unregistered net_device): Interrupt Throttling
Rate (ints/sec) set to dynamic conservative mode
e1000e 0000:05:00.1: irq 94 for MSI/MSI-X
udev[8400]: renamed network interface eth1 to eth4
e1000e 0000:05:00.1: eth1: (PCI Express:2.5GT/s:Width x4) 00:0c:bd:01:cd:8b
e1000e 0000:05:00.1: eth1: Intel(R) PRO/1000 Network Connection
e1000e 0000:05:00.1: eth1: MAC: 0, PHY: 4, PBA No: C98149-002
udev[8429]: renamed network interface eth1 to eth5
After doing so, though, I was unable to get a link beat on any of the
four RJ45 ports. I tried the Intel-supplied e1000e driver on the same
kernel and got the following:
e1000e: Intel(R) PRO/1000 Network Driver - 2.0.0.1-NAPI
e1000e: Copyright(c) 1999 - 2012 Intel Corporation.
e1000e 0000:06:00.0: Disabling ASPM L1
e1000e 0000:06:00.0: irq 91 for MSI/MSI-X
e1000e 0000:06:00.0: eth1: (PCI Express:2.5GT/s:Width x4) 00:0c:bd:01:cd:8c
e1000e 0000:06:00.0: eth1: Intel(R) PRO/1000 Network Connection
e1000e 0000:06:00.0: eth1: MAC: 1, PHY: 4, PBA No: C98149-002
e1000e 0000:06:00.1: Disabling ASPM L1
e1000e 0000:06:00.1: irq 92 for MSI/MSI-X
udev[8455]: renamed network interface eth1 to eth2
e1000e 0000:06:00.1: eth1: (PCI Express:2.5GT/s:Width x4) 00:0c:bd:01:cd:8d
e1000e 0000:06:00.1: eth1: Intel(R) PRO/1000 Network Connection
e1000e 0000:06:00.1: eth1: MAC: 1, PHY: 4, PBA No: C98149-002
e1000e 0000:05:00.0: Disabling ASPM L1
e1000e 0000:05:00.0: irq 93 for MSI/MSI-X
udev[8455]: renamed network interface eth1 to eth3
e1000e 0000:05:00.0: eth1: (PCI Express:2.5GT/s:Width x4) 00:0c:bd:01:cd:8a
e1000e 0000:05:00.0: eth1: Intel(R) PRO/1000 Network Connection
e1000e 0000:05:00.0: eth1: MAC: 1, PHY: 4, PBA No: C98149-002
e1000e 0000:05:00.1: Disabling ASPM L1
e1000e 0000:05:00.1: irq 94 for MSI/MSI-X
udev[8455]: renamed network interface eth1 to eth4
e1000e 0000:05:00.1: eth1: (PCI Express:2.5GT/s:Width x4) 00:0c:bd:01:cd:8b
e1000e 0000:05:00.1: eth1: Intel(R) PRO/1000 Network Connection
e1000e 0000:05:00.1: eth1: MAC: 1, PHY: 4, PBA No: C98149-002
udev[8455]: renamed network interface eth1 to eth5
ethtool -i and ethtool -d report the following for the Intel-supplied
driver for one of the four interfaces exported to userspace:
ethtool -i
----------
driver: e1000e
version: 2.0.0.1-NAPI
firmware-version: 5.0-2
bus-info: 0000:06:00.0
ethtool -d
----------
MAC Registers
-------------
0x00000: CTRL (Device control register) 0x40480241
Endian mode (buffers): little
Link reset: normal
Set link up: 1
Invert Loss-Of-Signal: no
Receive flow control: disabled
Transmit flow control: disabled
VLAN mode: enabled
Auto speed detect: disabled
Speed select: 1000Mb/s
Force speed: no
Force duplex: no
0x00008: STATUS (Device status register) 0x00080380
Duplex: half
Link up: no link config
TBI mode: disabled
Link speed: 1000Mb/s
Bus type: PCI Express
Port number: 0
0x00100: RCTL (Receive control register) 0x0400801A
Receiver: enabled
Store bad packets: disabled
Unicast promiscuous: enabled
Multicast promiscuous: enabled
Long packet: disabled
Descriptor minimum threshold size: 1/2
Broadcast accept mode: accept
VLAN filter: disabled
Canonical form indicator: disabled
Discard pause frames: filtered
Pass MAC control frames: don't pass
Receive buffer size: 2048
0x02808: RDLEN (Receive desc length) 0x00001000
0x02810: RDH (Receive desc head) 0x00000000
0x02818: RDT (Receive desc tail) 0x000000F0
0x02820: RDTR (Receive delay timer) 0x00000020
0x00400: TCTL (Transmit ctrl register) 0x3003F008
Transmitter: disabled
Pad short packets: enabled
Software XOFF Transmission: disabled
Re-transmit on late collision: disabled
0x03808: TDLEN (Transmit desc length) 0x00001000
0x03810: TDH (Transmit desc head) 0x00000000
0x03818: TDT (Transmit desc tail) 0x00000000
0x03820: TIDV (Transmit delay timer) 0x00000008
PHY type: unknown
mii-diag -a reports the following:
SIOCGMIIREG on eth2 failed: Input/output error
Basic registers of MII PHY #1: 1140 7909 02a8 0380 0de1 0000 0004 ffff.
Basic mode control register 0x1140: Auto-negotiation enabled.
Basic mode status register 0x7909 ... 7909.
Link status: not established.
End of basic transceiver information.
lspci reports the following:
02:00.0 PCI bridge: PLX Technology, Inc. PEX 8517 16-lane, 5-port PCI
Express Switch (rev ac)
03:00.0 PCI bridge: PLX Technology, Inc. PEX 8517 16-lane, 5-port PCI
Express Switch (rev ac)
03:01.0 PCI bridge: PLX Technology, Inc. PEX 8517 16-lane, 5-port PCI
Express Switch (rev ac)
03:02.0 PCI bridge: PLX Technology, Inc. PEX 8517 16-lane, 5-port PCI
Express Switch (rev ac)
05:00.0 Ethernet controller: Intel Corporation 82571EB Gigabit Ethernet
Controller (rev 06)
05:00.1 Ethernet controller: Intel Corporation 82571EB Gigabit Ethernet
Controller (rev 06)
06:00.0 Ethernet controller: Intel Corporation 82571EB Gigabit Ethernet
Controller (rev 06)
06:00.1 Ethernet controller: Intel Corporation 82571EB Gigabit Ethernet
Controller (rev 06)
I tried rebooting since switching to the new driver and it hasn't made a
difference. I did a bunch of digging in Google and couldn't find
anything that conclusively suggested a problem - I found lots of stuff
about BIOS bugs when dealing with ASPM, old regressions fixed in
previous kernels, and so on, but nothing that specifically identified my
problem.
Does anyone have any suggestions? I can try Linux 3.5 very easily and if
necessary I can also learn how to fetch a git tree and bisect it. I also
sent an e-mail to the manufacturer asking for assistance with this
device but I haven't received a response yet.
Thanks,
Brad
^ permalink raw reply
* [ANNOUNCE] iproute2 3.5.0
From: Stephen Hemminger @ 2012-08-01 23:05 UTC (permalink / raw)
To: netdev; +Cc: linux-kernel
Following the trend of releasing before going on vacation, here is the
iproute2 release to go with last weeks 3.5.0 kernel release. The changes
were mainly adding support for the new queuing disciplines (codel etc)
and cleaning up the manual pages.
Source:
http://www.kernel.org/pub/linux/utils/net/iproute2/iproute2-3.5.0.tar.gz
Repository:
git://git.kernel.org/pub/scm/linux/kernel/git/shemminger/iproute2.git
Andreas Henriksson (1):
iproute2: man page and /bin/ip disagree on del vs delete
Ben Hutchings (1):
ss: Report MSS from internal TCP information
Bjarni Ingi Gislason (2):
tc(8): Negative indent and missing "-" after an escape
tc-drr(8): tab unquoted in a argument to a macro
Chris Elston (1):
iproute2: allow IPv6 addresses for l2tp local and remote parameters
Eric Dumazet (3):
tc_codel: Controlled Delay AQM
fq_codel: Fair Queue Codel AQM
ip: speedup ip link
Hiroaki SHIMODA (2):
tc: u32: Fix icmp_code off.
tc: u32: Fix firstfrag filter.
Jan Ceuleers (2):
tc-codel: Fix typos in manpage
Add reference to tc-codel(8) to the SEE ALSO section
Li Wei (6):
tc: man: Fix incorrect parameter format in prio.
tc: prio: Perform more strict check on priomap.
tc: filter: validate filter priority in userspace.
tc: man: add 'delete' command.
tc: man: change man page and comment to confirm to code's behavior.
tc-bfifo: man: Add parameter value range.
Stephen Hemminger (7):
Update headers to 3.5 merge window
Remove derived man pages
Refactor ipaddr_list_or_flush
Remove reference to multipath algorithms in usage
man8: build cleanup
Add bridge command
v3.5.0
Vijay Subramanian (6):
Update tc-netem manpage to add ecn capability
tc-netem: Add support for ECN packet marking
tc-codel: Add manpage
tc-codel: Update usage text
tc-fq_codel: Add manpage
tc: Update manpage
^ permalink raw reply
* Re: v3.5: NETDEV WATCHDOG: eth0 (r8169): transmit queue 0 timed out
From: George Spelvin @ 2012-08-01 23:29 UTC (permalink / raw)
To: romieu; +Cc: linux, netdev
In-Reply-To: <20120801192455.GA29755@electric-eye.fr.zoreil.com>
Thank you for the response!
> It's up to you but I suggest that you keep them until there is something
> better.
I was going to; I just wondered if they interfered with debugging or
something.
> As long as the device recovers, you may try and lower the watchdog timeout
> as well as increase the Tx ring size a bit (x2 or x4) to minimize the
> annoyances.
Out of curiosity, how does increasing the Tx ring size help?
But okay. Just to make sure I'm doing it right (I'm pretty sure,
but scream if I'm making a mistake), I'm making the following edits to
drivers/net/ethernet/realtek/r8169.c
#define NUM_TX_DESC 64 /* Number of Tx descriptor registers */
I'll double that to 128.
Now, since I am actually running at gigabit speed into a pretty capable
network that I don't expect to ever block me, I should be able to send
one 1500-byte frame in 12.3 microseconds (with all overhead, one 1500-byte
frame is 1538 bytes or 12304 bits), so 128 frames in 1.6 ms.
There is the issue of TSO, so one descriptor might send more than one
frame, but I think it's likely to break at 4K pages, the worst case is
128 * 4096 / 1500 = 350 frames in that Tx ring, which will take 4.3 ms.
Either way, I can drop the Tx timeout a *lot*.
#define TL8169_TX_TIMEOUT (6*HZ)
I want to drop that to HZ/100 or less. Since I'm currently running with
CONFIG_HZ_100, and I'm not sure about the rounding (do I gain or lose
one tick due to ambiguity?) I'll bump HZ to 300 and change that to HZ/100.
That should give me a minimum of 2 ticks = 6.666 ms, which is still more
than it should take to transmit a full
To make this short timeout actually work, I have to remove the "round
to nearest second" round_timer() calls in net/sched/sch_generic.c (there
are two that apply to dev->watchdog_timer), since I do want a sub-second
timeout granularity.
^ permalink raw reply
* Re: [PATCH iproute2] ss: report SK_MEMINFO_BACKLOG
From: Stephen Hemminger @ 2012-08-02 0:06 UTC (permalink / raw)
To: Vijay Subramanian; +Cc: Eric Dumazet, netdev
In-Reply-To: <CAGK4HS-fUp2ZiW9F_ZogOXQo5_2ptcBHT9Y2j25ZaoXrYKnbAQ@mail.gmail.com>
On Thu, 26 Jul 2012 17:29:26 -0700
Vijay Subramanian <subramanian.vijay@gmail.com> wrote:
> On 26 July 2012 02:20, Eric Dumazet <eric.dumazet@gmail.com> wrote:
> > From: Eric Dumazet <edumazet@google.com>
> >
> > linux-3.6-rc1 supports SK_MEMINFO_BACKLOG with commit d594e987c6f54
> > (sock_diag: add SK_MEMINFO_BACKLOG)
> >
> > ss command can display it if provided by the kernel.
> >
> > Signed-off-by: Eric Dumazet <edumazet@google.com>
> > Cc: Vijay Subramanian <subramanian.vijay@gmail.com>
>
>
> Thanks Eric. I see now how you fixed this.
>
> Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com>
>
> Vijay
Applied (after 3.5.0 release).
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox