[PATCH 1/2] if_link: Add VF multicast promiscuous mode control

[Hiroshi Shimamoto]

From: Hiroshi Shimamoto <h-shimamoto@xxxxxxxxxxxxx>

Add netlink directives and ndo entry to control VF multicast promiscuous mode.

Intel ixgbe and ixgbevf driver can handle only 30 multicast MAC addresses
per VF. It means that we cannot assign over 30 IPv6 addresses to a single
VF interface on VM. We want thousands IPv6 addresses in VM.

There is capability of multicast promiscuous mode in Intel 82599 chip.
It enables all multicast packets are delivered to the target VF.

This patch prepares to control that VF multicast promiscuous functionality.

Signed-off-by: Hiroshi Shimamoto <h-shimamoto@xxxxxxxxxxxxx>
Reviewed-by: Hayato Momma <h-momma@xxxxxxxxxxxxx>
CC: Choi, Sy Jong <sy.jong.choi@xxxxxxxxx>
---
 include/linux/if_link.h      |  1 +
 include/linux/netdevice.h    |  3 +++
 include/uapi/linux/if_link.h |  6 ++++++
 net/core/rtnetlink.c         | 18 ++++++++++++++++--
 4 files changed, 26 insertions(+), 2 deletions(-)

diff --git a/include/linux/if_link.h b/include/linux/if_link.h
index 119130e..bc29ddf 100644
--- a/include/linux/if_link.h
+++ b/include/linux/if_link.h
@@ -14,5 +14,6 @@ struct ifla_vf_info {
 	__u32 linkstate;
 	__u32 min_tx_rate;
 	__u32 max_tx_rate;
+	__u32 mc_promisc;
 };
 #endif /* _LINUX_IF_LINK_H */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 52fd8e8..12e88a7 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -868,6 +868,7 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
  * int (*ndo_set_vf_rate)(struct net_device *dev, int vf, int min_tx_rate,
  *			  int max_tx_rate);
  * int (*ndo_set_vf_spoofchk)(struct net_device *dev, int vf, bool setting);
+ * int (*ndo_set_vf_mc_promisc)(struct net_device *dev, int vf, bool setting);
  * int (*ndo_get_vf_config)(struct net_device *dev,
  *			    int vf, struct ifla_vf_info *ivf);
  * int (*ndo_set_vf_link_state)(struct net_device *dev, int vf, int link_state);
@@ -1084,6 +1085,8 @@ struct net_device_ops {
 						   int max_tx_rate);
 	int			(*ndo_set_vf_spoofchk)(struct net_device *dev,
 						       int vf, bool setting);
+	int			(*ndo_set_vf_mc_promisc)(struct net_device *dev,
+							 int vf, bool setting);
 	int			(*ndo_get_vf_config)(struct net_device *dev,
 						     int vf,
 						     struct ifla_vf_info *ivf);
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index f7d0d2d..32b4b9e 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -454,6 +454,7 @@ enum {
 	IFLA_VF_SPOOFCHK,	/* Spoof Checking on/off switch */
 	IFLA_VF_LINK_STATE,	/* link state enable/disable/auto switch */
 	IFLA_VF_RATE,		/* Min and Max TX Bandwidth Allocation */
+	IFLA_VF_MC_PROMISC,	/* Multicast Promiscuous on/off switch */
 	__IFLA_VF_MAX,
 };
 
@@ -498,6 +499,11 @@ struct ifla_vf_link_state {
 	__u32 link_state;
 };
 
+struct ifla_vf_mc_promisc {
+	__u32 vf;
+	__u32 setting;
+};
+
 /* VF ports management section
  *
  *	Nested layout of set/get msg is:
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 9cf6fe9..5992245 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -807,7 +807,8 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev,
 			 nla_total_size(sizeof(struct ifla_vf_vlan)) +
 			 nla_total_size(sizeof(struct ifla_vf_spoofchk)) +
 			 nla_total_size(sizeof(struct ifla_vf_rate)) +
-			 nla_total_size(sizeof(struct ifla_vf_link_state)));
+			 nla_total_size(sizeof(struct ifla_vf_link_state)) +
+			 nla_total_size(sizeof(struct ifla_vf_mc_promisc)));
 		return size;
 	} else
 		return 0;
@@ -1099,6 +1100,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			struct ifla_vf_tx_rate vf_tx_rate;
 			struct ifla_vf_spoofchk vf_spoofchk;
 			struct ifla_vf_link_state vf_linkstate;
+			struct ifla_vf_mc_promisc vf_mc_promisc;
 
 			/*
 			 * Not all SR-IOV capable drivers support the
@@ -1107,6 +1109,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			 * report anything.
 			 */
 			ivi.spoofchk = -1;
+			ivi.mc_promisc = -1;
 			memset(ivi.mac, 0, sizeof(ivi.mac));
 			/* The default value for VF link state is "auto"
 			 * IFLA_VF_LINK_STATE_AUTO which equals zero
@@ -1119,7 +1122,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 				vf_rate.vf =
 				vf_tx_rate.vf =
 				vf_spoofchk.vf =
-				vf_linkstate.vf = ivi.vf;
+				vf_linkstate.vf =
+				vf_mc_promisc.vf = ivi.vf;
 
 			memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac));
 			vf_vlan.vlan = ivi.vlan;
@@ -1128,6 +1132,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			vf_rate.min_tx_rate = ivi.min_tx_rate;
 			vf_rate.max_tx_rate = ivi.max_tx_rate;
 			vf_spoofchk.setting = ivi.spoofchk;
+			vf_mc_promisc.setting = ivi.mc_promisc;
 			vf_linkstate.link_state = ivi.linkstate;
 			vf = nla_nest_start(skb, IFLA_VF_INFO);
 			if (!vf) {
@@ -1461,6 +1466,15 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr *attr)
 								 ivl->link_state);
 			break;
 		}
+		case IFLA_VF_MC_PROMISC: {
+			struct ifla_vf_mc_promisc *ivm;
+			ivm = nla_data(vf);
+			err = -EOPNOTSUPP;
+			if (ops->ndo_set_vf_mc_promisc)
+				err = ops->ndo_set_vf_mc_promisc(dev, ivm->vf,
+								 ivm->setting);
+			break;
+		}
 		default:
 			err = -EINVAL;
 			break;
-- 
1.9.0

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/