Merge branch 'phys_port'

Jiri Pirko says:

====================
This patchset is based on patch by Narendra_K@Dell.com
Once device which can change phys port id during its lifetime adopts this,
NETDEV_CHANGEPHYSPORTID event will be added and driver will call
call_netdevice_notifiers(NETDEV_NETDEV_CHANGEPHYSPORTID, dev) to propagate
the change to userspace.

v1->v2: as suggested by Ben, handle -EOPNOTSUPP in rtnl code (wrapped up ndo call)
v2->v3: adjusted patch 1 commit message
v3->v4: used "%phN" for sysfs printf as suggested by DaveM
        added igb/igbvf implementation as requested by Or Gerlitz
v4->v5: used prandom_u32 to generate id in igb_probe
        removed duplicate code in ibgvf_probe
        pushed dev_err string into one line in igbvf_refresh_ppid
v5->v6: use uuid_le_gen for generating 16-byte phys port id for igb/igbvf
	as suggested by BenH

1) Why do we need this, and why do existing facilities fail to provide
   a way to accomplish this?

Currenty there's very hard to tell if two netdevs are using the same physical
port. For sr-iov this can be get by sysfs. For other mechanisms, like NPAR
there's very hard to do it (one must learn it from NIC BIOS). But even for
sr-iov there's no way to say if two netdevs are using the same phys port when
these are passed through to virtual guests.

This patchset provides the generic way of letting this information know to
userspace. This info can be used by apps like NetworkManager, teamd, Wicked,
ovs daemon, etc, to do smarter bonding decisions.

2) Why is the physical port ID defined as a 32 byte opaque cookie?
   What formats and layouts need to be accomodated, and which
   influenced the design of the ID?

For user to distinguish if two netdevs are using the same port, he only needs
to compare their phys port ids. Nothing else is needed. This id has no
structure for security reasons. VF should not know anything about PF.

3) Are IDs globally unique?  Why or why not?  If IDs should be
   globally unique, but only in certain cases, what exactly are those
   cases.

Most of the time only uniqueness needed is in scope of single machine.
There might be case when the id should be unique between couple of machines
in virtualization environment. Given that for example for igb/igbvf 16B uuid
is used, there is no problem for this case as well. But each driver can
implement this differently focusing the hw capabilities and needs.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 85 insertions, 1 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 3ca60b070ef0..875f869dc38a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -728,6 +728,16 @@ struct netdev_fcoe_hbainfo {
 };
 #endif
 
+#define MAX_PHYS_PORT_ID_LEN 32
+
+/* This structure holds a unique identifier to identify the
+ * physical port used by a netdevice.
+ */
+struct netdev_phys_port_id {
+	unsigned char id[MAX_PHYS_PORT_ID_LEN];
+	unsigned char id_len;
+};
+
 /*
  * This structure defines the management hooks for network devices.
  * The following hooks can be defined; unless noted otherwise, they are
@@ -932,6 +942,12 @@ struct netdev_fcoe_hbainfo {
  *	that determine carrier state from physical hardware properties (eg
  *	network cables) or protocol-dependent mechanisms (eg
  *	USB_CDC_NOTIFY_NETWORK_CONNECTION) should NOT implement this function.
+ *
+ * int (*ndo_get_phys_port_id)(struct net_device *dev,
+ *			       struct netdev_phys_port_id *ppid);
+ *	Called to get ID of physical port of this device. If driver does
+ *	not implement this, it is assumed that the hw is not able to have
+ *	multiple net devices on single physical port.
  */
 struct net_device_ops {
 	int			(*ndo_init)(struct net_device *dev);
@@ -1060,6 +1076,8 @@ struct net_device_ops {
 						      struct nlmsghdr *nlh);
 	int			(*ndo_change_carrier)(struct net_device *dev,
 						      bool new_carrier);
+	int			(*ndo_get_phys_port_id)(struct net_device *dev,
+							struct netdev_phys_port_id *ppid);
 };
 
 /*
@@ -2315,6 +2333,8 @@ extern int		dev_set_mac_address(struct net_device *,
 					    struct sockaddr *);
 extern int		dev_change_carrier(struct net_device *,
 					   bool new_carrier);
+extern int		dev_get_phys_port_id(struct net_device *dev,
+					     struct netdev_phys_port_id *ppid);
 extern int		dev_hard_start_xmit(struct sk_buff *skb,
 					    struct net_device *dev,
 					    struct netdev_queue *txq);
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 03f6170ab337..04c0e7a5d484 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -143,6 +143,7 @@ enum {
 	IFLA_NUM_TX_QUEUES,
 	IFLA_NUM_RX_QUEUES,
 	IFLA_CARRIER,
+	IFLA_PHYS_PORT_ID,
 	__IFLA_MAX
 };
 
diff --git a/net/core/dev.c b/net/core/dev.c
index dfd9f5d56ae0..58eb802584b9 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4989,6 +4989,24 @@ int dev_change_carrier(struct net_device *dev, bool new_carrier)
 EXPORT_SYMBOL(dev_change_carrier);
 
 /**
+ *	dev_get_phys_port_id - Get device physical port ID
+ *	@dev: device
+ *	@ppid: port ID
+ *
+ *	Get device physical port ID
+ */
+int dev_get_phys_port_id(struct net_device *dev,
+			 struct netdev_phys_port_id *ppid)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+
+	if (!ops->ndo_get_phys_port_id)
+		return -EOPNOTSUPP;
+	return ops->ndo_get_phys_port_id(dev, ppid);
+}
+EXPORT_SYMBOL(dev_get_phys_port_id);
+
+/**
  *	dev_new_index	-	allocate an ifindex
  *	@net: the applicable net namespace
  *
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 981fed397d1d..8826b0d1e0cc 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -334,6 +334,27 @@ static ssize_t store_group(struct device *dev, struct device_attribute *attr,
 	return netdev_store(dev, attr, buf, len, change_group);
 }
 
+static ssize_t show_phys_port_id(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	struct net_device *netdev = to_net_dev(dev);
+	ssize_t ret = -EINVAL;
+
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	if (dev_isalive(netdev)) {
+		struct netdev_phys_port_id ppid;
+
+		ret = dev_get_phys_port_id(netdev, &ppid);
+		if (!ret)
+			ret = sprintf(buf, "%*phN\n", ppid.id_len, ppid.id);
+	}
+	rtnl_unlock();
+
+	return ret;
+}
+
 static struct device_attribute net_class_attributes[] = {
 	__ATTR(addr_assign_type, S_IRUGO, show_addr_assign_type, NULL),
 	__ATTR(addr_len, S_IRUGO, show_addr_len, NULL),
@@ -355,6 +376,7 @@ static struct device_attribute net_class_attributes[] = {
 	__ATTR(tx_queue_len, S_IRUGO | S_IWUSR, show_tx_queue_len,
 	       store_tx_queue_len),
 	__ATTR(netdev_group, S_IRUGO | S_IWUSR, show_group, store_group),
+	__ATTR(phys_port_id, S_IRUGO, show_phys_port_id, NULL),
 	{}
 };
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 3de740834d1f..0b2972c59b97 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -767,7 +767,8 @@ 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(MAX_PHYS_PORT_ID_LEN); /* IFLA_PHYS_PORT_ID */
 }
 
 static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev)
@@ -846,6 +847,24 @@ static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev)
 	return 0;
 }
 
+static int rtnl_phys_port_id_fill(struct sk_buff *skb, struct net_device *dev)
+{
+	int err;
+	struct netdev_phys_port_id ppid;
+
+	err = dev_get_phys_port_id(dev, &ppid);
+	if (err) {
+		if (err == -EOPNOTSUPP)
+			return 0;
+		return err;
+	}
+
+	if (nla_put(skb, IFLA_PHYS_PORT_ID, ppid.id_len, ppid.id))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
 static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			    int type, u32 pid, u32 seq, u32 change,
 			    unsigned int flags, u32 ext_filter_mask)
@@ -913,6 +932,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			goto nla_put_failure;
 	}
 
+	if (rtnl_phys_port_id_fill(skb, dev))
+		goto nla_put_failure;
+
 	attr = nla_reserve(skb, IFLA_STATS,
 			sizeof(struct rtnl_link_stats));
 	if (attr == NULL)
@@ -1113,6 +1135,7 @@ 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_PHYS_PORT_ID]	= { .type = NLA_BINARY, .len = MAX_PHYS_PORT_ID_LEN },
 };
 EXPORT_SYMBOL(ifla_policy);