From 2f90b8657ec942d1880f720e0177ee71df7c8e3c Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Thu, 20 Nov 2008 20:52:10 -0800
Subject: ixgbe: this patch adds support for DCB to the kernel and ixgbe driver
This adds support for Data Center Bridging (DCB) features in the ixgbe
driver and adds an rtnetlink interface for configuring DCB to the
kernel. The DCB feature support included are Priority Grouping (PG) -
which allows bandwidth guarantees to be allocated to groups to traffic
based on the 802.1q priority, and Priority Based Flow Control (PFC) -
which introduces a new MAC control PAUSE frame which works at
granularity of the 802.1p priority instead of the link (IEEE 802.3x).
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/dcb/Kconfig | 12 +
net/dcb/Makefile | 1 +
net/dcb/dcbnl.c | 704 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 717 insertions(+)
create mode 100644 net/dcb/Kconfig
create mode 100644 net/dcb/Makefile
create mode 100644 net/dcb/dcbnl.c
(limited to 'net/dcb')
diff --git a/net/dcb/Kconfig b/net/dcb/Kconfig
new file mode 100644
index 000000000000..bdf38802d339
--- /dev/null
+++ b/net/dcb/Kconfig
@@ -0,0 +1,12 @@
+config DCB
+ tristate "Data Center Bridging support"
+
+config DCBNL
+ bool "Data Center Bridging netlink interface support"
+ depends on DCB
+ default n
+ ---help---
+ This option turns on the netlink interface
+ (dcbnl) for Data Center Bridging capable devices.
+
+ If unsure, say N.
diff --git a/net/dcb/Makefile b/net/dcb/Makefile
new file mode 100644
index 000000000000..9930f4cde818
--- /dev/null
+++ b/net/dcb/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_DCB) += dcbnl.o
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
new file mode 100644
index 000000000000..516e8be83d72
--- /dev/null
+++ b/net/dcb/dcbnl.c
@@ -0,0 +1,704 @@
+/*
+ * Copyright (c) 2008, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
+ * Place - Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * Author: Lucy Liu <lucy.liu@intel.com>
+ */
+
+#include <linux/netdevice.h>
+#include <linux/netlink.h>
+#include <net/netlink.h>
+#include <net/rtnetlink.h>
+#include <linux/dcbnl.h>
+#include <linux/rtnetlink.h>
+#include <net/sock.h>
+
+/**
+ * Data Center Bridging (DCB) is a collection of Ethernet enhancements
+ * intended to allow network traffic with differing requirements
+ * (highly reliable, no drops vs. best effort vs. low latency) to operate
+ * and co-exist on Ethernet. Current DCB features are:
+ *
+ * Enhanced Transmission Selection (aka Priority Grouping [PG]) - provides a
+ * framework for assigning bandwidth guarantees to traffic classes.
+ *
+ * Priority-based Flow Control (PFC) - provides a flow control mechanism which
+ * can work independently for each 802.1p priority.
+ *
+ * Congestion Notification - provides a mechanism for end-to-end congestion
+ * control for protocols which do not have built-in congestion management.
+ *
+ * More information about the emerging standards for these Ethernet features
+ * can be found at: http://www.ieee802.org/1/pages/dcbridges.html
+ *
+ * This file implements an rtnetlink interface to allow configuration of DCB
+ * features for capable devices.
+ */
+
+MODULE_AUTHOR("Lucy Liu, <lucy.liu@intel.com>");
+MODULE_DESCRIPTION("Data Center Bridging generic netlink interface");
+MODULE_LICENSE("GPL");
+
+/**************** DCB attribute policies *************************************/
+
+/* DCB netlink attributes policy */
+static struct nla_policy dcbnl_rtnl_policy[DCB_ATTR_MAX + 1] = {
+ [DCB_ATTR_IFNAME] = {.type = NLA_STRING, .len = IFNAMSIZ - 1},
+ [DCB_ATTR_STATE] = {.type = NLA_U8},
+ [DCB_ATTR_PFC_CFG] = {.type = NLA_NESTED},
+ [DCB_ATTR_PG_CFG] = {.type = NLA_NESTED},
+ [DCB_ATTR_SET_ALL] = {.type = NLA_U8},
+ [DCB_ATTR_PERM_HWADDR] = {.type = NLA_FLAG},
+};
+
+/* DCB priority flow control to User Priority nested attributes */
+static struct nla_policy dcbnl_pfc_up_nest[DCB_PFC_UP_ATTR_MAX + 1] = {
+ [DCB_PFC_UP_ATTR_0] = {.type = NLA_U8},
+ [DCB_PFC_UP_ATTR_1] = {.type = NLA_U8},
+ [DCB_PFC_UP_ATTR_2] = {.type = NLA_U8},
+ [DCB_PFC_UP_ATTR_3] = {.type = NLA_U8},
+ [DCB_PFC_UP_ATTR_4] = {.type = NLA_U8},
+ [DCB_PFC_UP_ATTR_5] = {.type = NLA_U8},
+ [DCB_PFC_UP_ATTR_6] = {.type = NLA_U8},
+ [DCB_PFC_UP_ATTR_7] = {.type = NLA_U8},
+ [DCB_PFC_UP_ATTR_ALL] = {.type = NLA_FLAG},
+};
+
+/* DCB priority grouping nested attributes */
+static struct nla_policy dcbnl_pg_nest[DCB_PG_ATTR_MAX + 1] = {
+ [DCB_PG_ATTR_TC_0] = {.type = NLA_NESTED},
+ [DCB_PG_ATTR_TC_1] = {.type = NLA_NESTED},
+ [DCB_PG_ATTR_TC_2] = {.type = NLA_NESTED},
+ [DCB_PG_ATTR_TC_3] = {.type = NLA_NESTED},
+ [DCB_PG_ATTR_TC_4] = {.type = NLA_NESTED},
+ [DCB_PG_ATTR_TC_5] = {.type = NLA_NESTED},
+ [DCB_PG_ATTR_TC_6] = {.type = NLA_NESTED},
+ [DCB_PG_ATTR_TC_7] = {.type = NLA_NESTED},
+ [DCB_PG_ATTR_TC_ALL] = {.type = NLA_NESTED},
+ [DCB_PG_ATTR_BW_ID_0] = {.type = NLA_U8},
+ [DCB_PG_ATTR_BW_ID_1] = {.type = NLA_U8},
+ [DCB_PG_ATTR_BW_ID_2] = {.type = NLA_U8},
+ [DCB_PG_ATTR_BW_ID_3] = {.type = NLA_U8},
+ [DCB_PG_ATTR_BW_ID_4] = {.type = NLA_U8},
+ [DCB_PG_ATTR_BW_ID_5] = {.type = NLA_U8},
+ [DCB_PG_ATTR_BW_ID_6] = {.type = NLA_U8},
+ [DCB_PG_ATTR_BW_ID_7] = {.type = NLA_U8},
+ [DCB_PG_ATTR_BW_ID_ALL] = {.type = NLA_FLAG},
+};
+
+/* DCB traffic class nested attributes. */
+static struct nla_policy dcbnl_tc_param_nest[DCB_TC_ATTR_PARAM_MAX + 1] = {
+ [DCB_TC_ATTR_PARAM_PGID] = {.type = NLA_U8},
+ [DCB_TC_ATTR_PARAM_UP_MAPPING] = {.type = NLA_U8},
+ [DCB_TC_ATTR_PARAM_STRICT_PRIO] = {.type = NLA_U8},
+ [DCB_TC_ATTR_PARAM_BW_PCT] = {.type = NLA_U8},
+ [DCB_TC_ATTR_PARAM_ALL] = {.type = NLA_FLAG},
+};
+
+
+/* standard netlink reply call */
+static int dcbnl_reply(u8 value, u8 event, u8 cmd, u8 attr, u32 pid,
+ u32 seq, u16 flags)
+{
+ struct sk_buff *dcbnl_skb;
+ struct dcbmsg *dcb;
+ struct nlmsghdr *nlh;
+ int ret = -EINVAL;
+
+ dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!dcbnl_skb)
+ return ret;
+
+ nlh = NLMSG_NEW(dcbnl_skb, pid, seq, event, sizeof(*dcb), flags);
+
+ dcb = NLMSG_DATA(nlh);
+ dcb->dcb_family = AF_UNSPEC;
+ dcb->cmd = cmd;
+ dcb->dcb_pad = 0;
+
+ ret = nla_put_u8(dcbnl_skb, attr, value);
+ if (ret)
+ goto err;
+
+ /* end the message, assign the nlmsg_len. */
+ nlmsg_end(dcbnl_skb, nlh);
+ ret = rtnl_unicast(dcbnl_skb, &init_net, pid);
+ if (ret)
+ goto err;
+
+ return 0;
+nlmsg_failure:
+err:
+ kfree(dcbnl_skb);
+ return ret;
+}
+
+static int dcbnl_getstate(struct net_device *netdev, struct nlattr **tb,
+ u32 pid, u32 seq, u16 flags)
+{
+ int ret = -EINVAL;
+
+ /* if (!tb[DCB_ATTR_STATE] || !netdev->dcbnl_ops->getstate) */
+ if (!netdev->dcbnl_ops->getstate)
+ return ret;
+
+ ret = dcbnl_reply(netdev->dcbnl_ops->getstate(netdev), RTM_GETDCB,
+ DCB_CMD_GSTATE, DCB_ATTR_STATE, pid, seq, flags);
+
+ return ret;
+}
+
+static int dcbnl_getpfccfg(struct net_device *netdev, struct nlattr **tb,
+ u32 pid, u32 seq, u16 flags)
+{
+ struct sk_buff *dcbnl_skb;
+ struct nlmsghdr *nlh;
+ struct dcbmsg *dcb;
+ struct nlattr *data[DCB_PFC_UP_ATTR_MAX + 1], *nest;
+ u8 value;
+ int ret = -EINVAL;
+ int i;
+ int getall = 0;
+
+ if (!tb[DCB_ATTR_PFC_CFG] || !netdev->dcbnl_ops->getpfccfg)
+ return ret;
+
+ ret = nla_parse_nested(data, DCB_PFC_UP_ATTR_MAX,
+ tb[DCB_ATTR_PFC_CFG],
+ dcbnl_pfc_up_nest);
+ if (ret)
+ goto err_out;
+
+ dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!dcbnl_skb)
+ goto err_out;
+
+ nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags);
+
+ dcb = NLMSG_DATA(nlh);
+ dcb->dcb_family = AF_UNSPEC;
+ dcb->cmd = DCB_CMD_PFC_GCFG;
+
+ nest = nla_nest_start(dcbnl_skb, DCB_ATTR_PFC_CFG);
+ if (!nest)
+ goto err;
+
+ if (data[DCB_PFC_UP_ATTR_ALL])
+ getall = 1;
+
+ for (i = DCB_PFC_UP_ATTR_0; i <= DCB_PFC_UP_ATTR_7; i++) {
+ if (!getall && !data[i])
+ continue;
+
+ netdev->dcbnl_ops->getpfccfg(netdev, i - DCB_PFC_UP_ATTR_0,
+ &value);
+ ret = nla_put_u8(dcbnl_skb, i, value);
+
+ if (ret) {
+ nla_nest_cancel(dcbnl_skb, nest);
+ goto err;
+ }
+ }
+ nla_nest_end(dcbnl_skb, nest);
+
+ nlmsg_end(dcbnl_skb, nlh);
+
+ ret = rtnl_unicast(dcbnl_skb, &init_net, pid);
+ if (ret)
+ goto err;
+
+ return 0;
+nlmsg_failure:
+err:
+ kfree(dcbnl_skb);
+err_out:
+ return -EINVAL;
+}
+
+static int dcbnl_getperm_hwaddr(struct net_device *netdev, struct nlattr **tb,
+ u32 pid, u32 seq, u16 flags)
+{
+ struct sk_buff *dcbnl_skb;
+ struct nlmsghdr *nlh;
+ struct dcbmsg *dcb;
+ u8 perm_addr[MAX_ADDR_LEN];
+ int ret = -EINVAL;
+
+ if (!netdev->dcbnl_ops->getpermhwaddr)
+ return ret;
+
+ dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!dcbnl_skb)
+ goto err_out;
+
+ nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags);
+
+ dcb = NLMSG_DATA(nlh);
+ dcb->dcb_family = AF_UNSPEC;
+ dcb->cmd = DCB_CMD_GPERM_HWADDR;
+
+ netdev->dcbnl_ops->getpermhwaddr(netdev, perm_addr);
+
+ ret = nla_put(dcbnl_skb, DCB_ATTR_PERM_HWADDR, sizeof(perm_addr),
+ perm_addr);
+
+ nlmsg_end(dcbnl_skb, nlh);
+
+ ret = rtnl_unicast(dcbnl_skb, &init_net, pid);
+ if (ret)
+ goto err;
+
+ return 0;
+
+nlmsg_failure:
+err:
+ kfree(dcbnl_skb);
+err_out:
+ return -EINVAL;
+}
+
+static int __dcbnl_pg_getcfg(struct net_device *netdev, struct nlattr **tb,
+ u32 pid, u32 seq, u16 flags, int dir)
+{
+ struct sk_buff *dcbnl_skb;
+ struct nlmsghdr *nlh;
+ struct dcbmsg *dcb;
+ struct nlattr *pg_nest, *param_nest, *data;
+ struct nlattr *pg_tb[DCB_PG_ATTR_MAX + 1];
+ struct nlattr *param_tb[DCB_TC_ATTR_PARAM_MAX + 1];
+ u8 prio, pgid, tc_pct, up_map;
+ int ret = -EINVAL;
+ int getall = 0;
+ int i;
+
+ if (!tb[DCB_ATTR_PG_CFG] ||
+ !netdev->dcbnl_ops->getpgtccfgtx ||
+ !netdev->dcbnl_ops->getpgtccfgrx ||
+ !netdev->dcbnl_ops->getpgbwgcfgtx ||
+ !netdev->dcbnl_ops->getpgbwgcfgrx)
+ return ret;
+
+ ret = nla_parse_nested(pg_tb, DCB_PG_ATTR_MAX,
+ tb[DCB_ATTR_PG_CFG], dcbnl_pg_nest);
+
+ if (ret)
+ goto err_out;
+
+ dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!dcbnl_skb)
+ goto err_out;
+
+ nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags);
+
+ dcb = NLMSG_DATA(nlh);
+ dcb->dcb_family = AF_UNSPEC;
+ dcb->cmd = (dir) ? DCB_CMD_PGRX_GCFG : DCB_CMD_PGTX_GCFG;
+
+ pg_nest = nla_nest_start(dcbnl_skb, DCB_ATTR_PG_CFG);
+ if (!pg_nest)
+ goto err;
+
+ if (pg_tb[DCB_PG_ATTR_TC_ALL])
+ getall = 1;
+
+ for (i = DCB_PG_ATTR_TC_0; i <= DCB_PG_ATTR_TC_7; i++) {
+ if (!getall && !pg_tb[i])
+ continue;
+
+ if (pg_tb[DCB_PG_ATTR_TC_ALL])
+ data = pg_tb[DCB_PG_ATTR_TC_ALL];
+ else
+ data = pg_tb[i];
+ ret = nla_parse_nested(param_tb, DCB_TC_ATTR_PARAM_MAX,
+ data, dcbnl_tc_param_nest);
+ if (ret)
+ goto err_pg;
+
+ param_nest = nla_nest_start(dcbnl_skb, i);
+ if (!param_nest)
+ goto err_pg;
+
+ pgid = DCB_ATTR_VALUE_UNDEFINED;
+ prio = DCB_ATTR_VALUE_UNDEFINED;
+ tc_pct = DCB_ATTR_VALUE_UNDEFINED;
+ up_map = DCB_ATTR_VALUE_UNDEFINED;
+
+ if (dir) {
+ /* Rx */
+ netdev->dcbnl_ops->getpgtccfgrx(netdev,
+ i - DCB_PG_ATTR_TC_0, &prio,
+ &pgid, &tc_pct, &up_map);
+ } else {
+ /* Tx */
+ netdev->dcbnl_ops->getpgtccfgtx(netdev,
+ i - DCB_PG_ATTR_TC_0, &prio,
+ &pgid, &tc_pct, &up_map);
+ }
+
+ if (param_tb[DCB_TC_ATTR_PARAM_PGID] ||
+ param_tb[DCB_TC_ATTR_PARAM_ALL]) {
+ ret = nla_put_u8(dcbnl_skb,
+ DCB_TC_ATTR_PARAM_PGID, pgid);
+ if (ret)
+ goto err_param;
+ }
+ if (param_tb[DCB_TC_ATTR_PARAM_UP_MAPPING] ||
+ param_tb[DCB_TC_ATTR_PARAM_ALL]) {
+ ret = nla_put_u8(dcbnl_skb,
+ DCB_TC_ATTR_PARAM_UP_MAPPING, up_map);
+ if (ret)
+ goto err_param;
+ }
+ if (param_tb[DCB_TC_ATTR_PARAM_STRICT_PRIO] ||
+ param_tb[DCB_TC_ATTR_PARAM_ALL]) {
+ ret = nla_put_u8(dcbnl_skb,
+ DCB_TC_ATTR_PARAM_STRICT_PRIO, prio);
+ if (ret)
+ goto err_param;
+ }
+ if (param_tb[DCB_TC_ATTR_PARAM_BW_PCT] ||
+ param_tb[DCB_TC_ATTR_PARAM_ALL]) {
+ ret = nla_put_u8(dcbnl_skb, DCB_TC_ATTR_PARAM_BW_PCT,
+ tc_pct);
+ if (ret)
+ goto err_param;
+ }
+ nla_nest_end(dcbnl_skb, param_nest);
+ }
+
+ if (pg_tb[DCB_PG_ATTR_BW_ID_ALL])
+ getall = 1;
+ else
+ getall = 0;
+
+ for (i = DCB_PG_ATTR_BW_ID_0; i <= DCB_PG_ATTR_BW_ID_7; i++) {
+ if (!getall && !pg_tb[i])
+ continue;
+
+ tc_pct = DCB_ATTR_VALUE_UNDEFINED;
+
+ if (dir) {
+ /* Rx */
+ netdev->dcbnl_ops->getpgbwgcfgrx(netdev,
+ i - DCB_PG_ATTR_BW_ID_0, &tc_pct);
+ } else {
+ /* Tx */
+ netdev->dcbnl_ops->getpgbwgcfgtx(netdev,
+ i - DCB_PG_ATTR_BW_ID_0, &tc_pct);
+ }
+ ret = nla_put_u8(dcbnl_skb, i, tc_pct);
+
+ if (ret)
+ goto err_pg;
+ }
+
+ nla_nest_end(dcbnl_skb, pg_nest);
+
+ nlmsg_end(dcbnl_skb, nlh);
+
+ ret = rtnl_unicast(dcbnl_skb, &init_net, pid);
+ if (ret)
+ goto err;
+
+ return 0;
+
+err_param:
+ nla_nest_cancel(dcbnl_skb, param_nest);
+err_pg:
+ nla_nest_cancel(dcbnl_skb, pg_nest);
+nlmsg_failure:
+err:
+ kfree(dcbnl_skb);
+err_out:
+ ret = -EINVAL;
+ return ret;
+}
+
+static int dcbnl_pgtx_getcfg(struct net_device *netdev, struct nlattr **tb,
+ u32 pid, u32 seq, u16 flags)
+{
+ return __dcbnl_pg_getcfg(netdev, tb, pid, seq, flags, 0);
+}
+
+static int dcbnl_pgrx_getcfg(struct net_device *netdev, struct nlattr **tb,
+ u32 pid, u32 seq, u16 flags)
+{
+ return __dcbnl_pg_getcfg(netdev, tb, pid, seq, flags, 1);
+}
+
+static int dcbnl_setstate(struct net_device *netdev, struct nlattr **tb,
+ u32 pid, u32 seq, u16 flags)
+{
+ int ret = -EINVAL;
+ u8 value;
+
+ if (!tb[DCB_ATTR_STATE] || !netdev->dcbnl_ops->setstate)
+ return ret;
+
+ value = nla_get_u8(tb[DCB_ATTR_STATE]);
+
+ netdev->dcbnl_ops->setstate(netdev, value);
+
+ ret = dcbnl_reply(0, RTM_SETDCB, DCB_CMD_SSTATE, DCB_ATTR_STATE,
+ pid, seq, flags);
+
+ return ret;
+}
+
+static int dcbnl_setpfccfg(struct net_device *netdev, struct nlattr **tb,
+ u32 pid, u32 seq, u16 flags)
+{
+ struct nlattr *data[DCB_PFC_UP_ATTR_MAX + 1];
+ int i;
+ int ret = -EINVAL;
+ u8 value;
+
+ if (!tb[DCB_ATTR_PFC_CFG] || !netdev->dcbnl_ops->setpfccfg)
+ return ret;
+
+ ret = nla_parse_nested(data, DCB_PFC_UP_ATTR_MAX,
+ tb[DCB_ATTR_PFC_CFG],
+ dcbnl_pfc_up_nest);
+ if (ret)
+ goto err;
+
+ for (i = DCB_PFC_UP_ATTR_0; i <= DCB_PFC_UP_ATTR_7; i++) {
+ if (data[i] == NULL)
+ continue;
+ value = nla_get_u8(data[i]);
+ netdev->dcbnl_ops->setpfccfg(netdev,
+ data[i]->nla_type - DCB_PFC_UP_ATTR_0, value);
+ }
+
+ ret = dcbnl_reply(0, RTM_SETDCB, DCB_CMD_PFC_SCFG, DCB_ATTR_PFC_CFG,
+ pid, seq, flags);
+err:
+ return ret;
+}
+
+static int dcbnl_setall(struct net_device *netdev, struct nlattr **tb,
+ u32 pid, u32 seq, u16 flags)
+{
+ int ret = -EINVAL;
+
+ if (!tb[DCB_ATTR_SET_ALL] || !netdev->dcbnl_ops->setall)
+ return ret;
+
+ ret = dcbnl_reply(netdev->dcbnl_ops->setall(netdev), RTM_SETDCB,
+ DCB_CMD_SET_ALL, DCB_ATTR_SET_ALL, pid, seq, flags);
+
+ return ret;
+}
+
+static int __dcbnl_pg_setcfg(struct net_device *netdev, struct nlattr **tb,
+ u32 pid, u32 seq, u16 flags, int dir)
+{
+ struct nlattr *pg_tb[DCB_PG_ATTR_MAX + 1];
+ struct nlattr *param_tb[DCB_TC_ATTR_PARAM_MAX + 1];
+ int ret = -EINVAL;
+ int i;
+ u8 pgid;
+ u8 up_map;
+ u8 prio;
+ u8 tc_pct;
+
+ if (!tb[DCB_ATTR_PG_CFG] ||
+ !netdev->dcbnl_ops->setpgtccfgtx ||
+ !netdev->dcbnl_ops->setpgtccfgrx ||
+ !netdev->dcbnl_ops->setpgbwgcfgtx ||
+ !netdev->dcbnl_ops->setpgbwgcfgrx)
+ return ret;
+
+ ret = nla_parse_nested(pg_tb, DCB_PG_ATTR_MAX,
+ tb[DCB_ATTR_PG_CFG], dcbnl_pg_nest);
+ if (ret)
+ goto err;
+
+ for (i = DCB_PG_ATTR_TC_0; i <= DCB_PG_ATTR_TC_7; i++) {
+ if (!pg_tb[i])
+ continue;
+
+ ret = nla_parse_nested(param_tb, DCB_TC_ATTR_PARAM_MAX,
+ pg_tb[i], dcbnl_tc_param_nest);
+ if (ret)
+ goto err;
+
+ pgid = DCB_ATTR_VALUE_UNDEFINED;
+ prio = DCB_ATTR_VALUE_UNDEFINED;
+ tc_pct = DCB_ATTR_VALUE_UNDEFINED;
+ up_map = DCB_ATTR_VALUE_UNDEFINED;
+
+ if (param_tb[DCB_TC_ATTR_PARAM_STRICT_PRIO])
+ prio =
+ nla_get_u8(param_tb[DCB_TC_ATTR_PARAM_STRICT_PRIO]);
+
+ if (param_tb[DCB_TC_ATTR_PARAM_PGID])
+ pgid = nla_get_u8(param_tb[DCB_TC_ATTR_PARAM_PGID]);
+
+ if (param_tb[DCB_TC_ATTR_PARAM_BW_PCT])
+ tc_pct = nla_get_u8(param_tb[DCB_TC_ATTR_PARAM_BW_PCT]);
+
+ if (param_tb[DCB_TC_ATTR_PARAM_UP_MAPPING])
+ up_map =
+ nla_get_u8(param_tb[DCB_TC_ATTR_PARAM_UP_MAPPING]);
+
+ /* dir: Tx = 0, Rx = 1 */
+ if (dir) {
+ /* Rx */
+ netdev->dcbnl_ops->setpgtccfgrx(netdev,
+ i - DCB_PG_ATTR_TC_0,
+ prio, pgid, tc_pct, up_map);
+ } else {
+ /* Tx */
+ netdev->dcbnl_ops->setpgtccfgtx(netdev,
+ i - DCB_PG_ATTR_TC_0,
+ prio, pgid, tc_pct, up_map);
+ }
+ }
+
+ for (i = DCB_PG_ATTR_BW_ID_0; i <= DCB_PG_ATTR_BW_ID_7; i++) {
+ if (!pg_tb[i])
+ continue;
+
+ tc_pct = nla_get_u8(pg_tb[i]);
+
+ /* dir: Tx = 0, Rx = 1 */
+ if (dir) {
+ /* Rx */
+ netdev->dcbnl_ops->setpgbwgcfgrx(netdev,
+ i - DCB_PG_ATTR_BW_ID_0, tc_pct);
+ } else {
+ /* Tx */
+ netdev->dcbnl_ops->setpgbwgcfgtx(netdev,
+ i - DCB_PG_ATTR_BW_ID_0, tc_pct);
+ }
+ }
+
+ ret = dcbnl_reply(0, RTM_SETDCB,
+ (dir ? DCB_CMD_PGRX_SCFG : DCB_CMD_PGTX_SCFG),
+ DCB_ATTR_PG_CFG, pid, seq, flags);
+
+err:
+ return ret;
+}
+
+static int dcbnl_pgtx_setcfg(struct net_device *netdev, struct nlattr **tb,
+ u32 pid, u32 seq, u16 flags)
+{
+ return __dcbnl_pg_setcfg(netdev, tb, pid, seq, flags, 0);
+}
+
+static int dcbnl_pgrx_setcfg(struct net_device *netdev, struct nlattr **tb,
+ u32 pid, u32 seq, u16 flags)
+{
+ return __dcbnl_pg_setcfg(netdev, tb, pid, seq, flags, 1);
+}
+
+static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+{
+ struct net *net = sock_net(skb->sk);
+ struct net_device *netdev;
+ struct dcbmsg *dcb = (struct dcbmsg *)NLMSG_DATA(nlh);
+ struct nlattr *tb[DCB_ATTR_MAX + 1];
+ u32 pid = skb ? NETLINK_CB(skb).pid : 0;
+ int ret = -EINVAL;
+
+ if (net != &init_net)
+ return -EINVAL;
+
+ ret = nlmsg_parse(nlh, sizeof(*dcb), tb, DCB_ATTR_MAX,
+ dcbnl_rtnl_policy);
+ if (ret < 0)
+ return ret;
+
+ if (!tb[DCB_ATTR_IFNAME])
+ return -EINVAL;
+
+ netdev = dev_get_by_name(&init_net, nla_data(tb[DCB_ATTR_IFNAME]));
+ if (!netdev)
+ return -EINVAL;
+
+ if (!netdev->dcbnl_ops)
+ goto errout;
+
+ switch (dcb->cmd) {
+ case DCB_CMD_GSTATE:
+ ret = dcbnl_getstate(netdev, tb, pid, nlh->nlmsg_seq,
+ nlh->nlmsg_flags);
+ goto out;
+ case DCB_CMD_PFC_GCFG:
+ ret = dcbnl_getpfccfg(netdev, tb, pid, nlh->nlmsg_seq,
+ nlh->nlmsg_flags);
+ goto out;
+ case DCB_CMD_GPERM_HWADDR:
+ ret = dcbnl_getperm_hwaddr(netdev, tb, pid, nlh->nlmsg_seq,
+ nlh->nlmsg_flags);
+ goto out;
+ case DCB_CMD_PGTX_GCFG:
+ ret = dcbnl_pgtx_getcfg(netdev, tb, pid, nlh->nlmsg_seq,
+ nlh->nlmsg_flags);
+ goto out;
+ case DCB_CMD_PGRX_GCFG:
+ ret = dcbnl_pgrx_getcfg(netdev, tb, pid, nlh->nlmsg_seq,
+ nlh->nlmsg_flags);
+ goto out;
+ case DCB_CMD_SSTATE:
+ ret = dcbnl_setstate(netdev, tb, pid, nlh->nlmsg_seq,
+ nlh->nlmsg_flags);
+ goto out;
+ case DCB_CMD_PFC_SCFG:
+ ret = dcbnl_setpfccfg(netdev, tb, pid, nlh->nlmsg_seq,
+ nlh->nlmsg_flags);
+ goto out;
+
+ case DCB_CMD_SET_ALL:
+ ret = dcbnl_setall(netdev, tb, pid, nlh->nlmsg_seq,
+ nlh->nlmsg_flags);
+ goto out;
+ case DCB_CMD_PGTX_SCFG:
+ ret = dcbnl_pgtx_setcfg(netdev, tb, pid, nlh->nlmsg_seq,
+ nlh->nlmsg_flags);
+ goto out;
+ case DCB_CMD_PGRX_SCFG:
+ ret = dcbnl_pgrx_setcfg(netdev, tb, pid, nlh->nlmsg_seq,
+ nlh->nlmsg_flags);
+ goto out;
+ default:
+ goto errout;
+ }
+errout:
+ ret = -EINVAL;
+out:
+ dev_put(netdev);
+ return ret;
+}
+
+static int __init dcbnl_init(void)
+{
+ rtnl_register(PF_UNSPEC, RTM_GETDCB, dcb_doit, NULL);
+ rtnl_register(PF_UNSPEC, RTM_SETDCB, dcb_doit, NULL);
+
+ return 0;
+}
+module_init(dcbnl_init);
+
+static void __exit dcbnl_exit(void)
+{
+ rtnl_unregister(PF_UNSPEC, RTM_GETDCB);
+ rtnl_unregister(PF_UNSPEC, RTM_SETDCB);
+}
+module_exit(dcbnl_exit);
+
+
--
cgit
From 46132188bf72e22ef097f16ed5c969ee8cea1e8b Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Thu, 20 Nov 2008 21:05:08 -0800
Subject: DCB: Add interface to query for the DCB capabilities of an device.
Adds to the netlink interface for Data Center Bridging (DCB), allowing
the DCB capabilities supported by a device to be queried.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/dcb/dcbnl.c | 82 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 82 insertions(+)
(limited to 'net/dcb')
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 516e8be83d72..de61d64d102d 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -61,6 +61,7 @@ static struct nla_policy dcbnl_rtnl_policy[DCB_ATTR_MAX + 1] = {
[DCB_ATTR_PG_CFG] = {.type = NLA_NESTED},
[DCB_ATTR_SET_ALL] = {.type = NLA_U8},
[DCB_ATTR_PERM_HWADDR] = {.type = NLA_FLAG},
+ [DCB_ATTR_CAP] = {.type = NLA_NESTED},
};
/* DCB priority flow control to User Priority nested attributes */
@@ -107,6 +108,17 @@ static struct nla_policy dcbnl_tc_param_nest[DCB_TC_ATTR_PARAM_MAX + 1] = {
[DCB_TC_ATTR_PARAM_ALL] = {.type = NLA_FLAG},
};
+/* DCB capabilities nested attributes. */
+static struct nla_policy dcbnl_cap_nest[DCB_CAP_ATTR_MAX + 1] = {
+ [DCB_CAP_ATTR_ALL] = {.type = NLA_FLAG},
+ [DCB_CAP_ATTR_PG] = {.type = NLA_U8},
+ [DCB_CAP_ATTR_PFC] = {.type = NLA_U8},
+ [DCB_CAP_ATTR_UP2TC] = {.type = NLA_U8},
+ [DCB_CAP_ATTR_PG_TCS] = {.type = NLA_U8},
+ [DCB_CAP_ATTR_PFC_TCS] = {.type = NLA_U8},
+ [DCB_CAP_ATTR_GSP] = {.type = NLA_U8},
+ [DCB_CAP_ATTR_BCN] = {.type = NLA_U8},
+};
/* standard netlink reply call */
static int dcbnl_reply(u8 value, u8 event, u8 cmd, u8 attr, u32 pid,
@@ -269,6 +281,72 @@ err_out:
return -EINVAL;
}
+static int dcbnl_getcap(struct net_device *netdev, struct nlattr **tb,
+ u32 pid, u32 seq, u16 flags)
+{
+ struct sk_buff *dcbnl_skb;
+ struct nlmsghdr *nlh;
+ struct dcbmsg *dcb;
+ struct nlattr *data[DCB_CAP_ATTR_MAX + 1], *nest;
+ u8 value;
+ int ret = -EINVAL;
+ int i;
+ int getall = 0;
+
+ if (!tb[DCB_ATTR_CAP] || !netdev->dcbnl_ops->getcap)
+ return ret;
+
+ ret = nla_parse_nested(data, DCB_CAP_ATTR_MAX, tb[DCB_ATTR_CAP],
+ dcbnl_cap_nest);
+ if (ret)
+ goto err_out;
+
+ dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!dcbnl_skb)
+ goto err_out;
+
+ nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags);
+
+ dcb = NLMSG_DATA(nlh);
+ dcb->dcb_family = AF_UNSPEC;
+ dcb->cmd = DCB_CMD_GCAP;
+
+ nest = nla_nest_start(dcbnl_skb, DCB_ATTR_CAP);
+ if (!nest)
+ goto err;
+
+ if (data[DCB_CAP_ATTR_ALL])
+ getall = 1;
+
+ for (i = DCB_CAP_ATTR_ALL+1; i <= DCB_CAP_ATTR_MAX; i++) {
+ if (!getall && !data[i])
+ continue;
+
+ if (!netdev->dcbnl_ops->getcap(netdev, i, &value)) {
+ ret = nla_put_u8(dcbnl_skb, i, value);
+
+ if (ret) {
+ nla_nest_cancel(dcbnl_skb, nest);
+ goto err;
+ }
+ }
+ }
+ nla_nest_end(dcbnl_skb, nest);
+
+ nlmsg_end(dcbnl_skb, nlh);
+
+ ret = rtnl_unicast(dcbnl_skb, &init_net, pid);
+ if (ret)
+ goto err;
+
+ return 0;
+nlmsg_failure:
+err:
+ kfree(dcbnl_skb);
+err_out:
+ return -EINVAL;
+}
+
static int __dcbnl_pg_getcfg(struct net_device *netdev, struct nlattr **tb,
u32 pid, u32 seq, u16 flags, int dir)
{
@@ -675,6 +753,10 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
ret = dcbnl_pgrx_setcfg(netdev, tb, pid, nlh->nlmsg_seq,
nlh->nlmsg_flags);
goto out;
+ case DCB_CMD_GCAP:
+ ret = dcbnl_getcap(netdev, tb, pid, nlh->nlmsg_seq,
+ nlh->nlmsg_flags);
+ goto out;
default:
goto errout;
}
--
cgit
From 33dbabc4a7f7bd72313c73a3c199f31f3900336f Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Thu, 20 Nov 2008 21:08:19 -0800
Subject: DCB: Add interface to query # of TCs supported by device
Adds interface for Data Center Bridging (DCB) to query (and set if
supported) the number of traffic classes currently supported by the
device for the two (DCB) features: priority groups (PG) and priority
flow control (PFC).
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/dcb/dcbnl.c | 132 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 132 insertions(+)
(limited to 'net/dcb')
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index de61d64d102d..5ff7e3c0c172 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -120,6 +120,13 @@ static struct nla_policy dcbnl_cap_nest[DCB_CAP_ATTR_MAX + 1] = {
[DCB_CAP_ATTR_BCN] = {.type = NLA_U8},
};
+/* DCB capabilities nested attributes. */
+static struct nla_policy dcbnl_numtcs_nest[DCB_NUMTCS_ATTR_MAX + 1] = {
+ [DCB_NUMTCS_ATTR_ALL] = {.type = NLA_FLAG},
+ [DCB_NUMTCS_ATTR_PG] = {.type = NLA_U8},
+ [DCB_NUMTCS_ATTR_PFC] = {.type = NLA_U8},
+};
+
/* standard netlink reply call */
static int dcbnl_reply(u8 value, u8 event, u8 cmd, u8 attr, u32 pid,
u32 seq, u16 flags)
@@ -347,6 +354,123 @@ err_out:
return -EINVAL;
}
+static int dcbnl_getnumtcs(struct net_device *netdev, struct nlattr **tb,
+ u32 pid, u32 seq, u16 flags)
+{
+ struct sk_buff *dcbnl_skb;
+ struct nlmsghdr *nlh;
+ struct dcbmsg *dcb;
+ struct nlattr *data[DCB_NUMTCS_ATTR_MAX + 1], *nest;
+ u8 value;
+ int ret = -EINVAL;
+ int i;
+ int getall = 0;
+
+ if (!tb[DCB_ATTR_NUMTCS] || !netdev->dcbnl_ops->getnumtcs)
+ return ret;
+
+ ret = nla_parse_nested(data, DCB_NUMTCS_ATTR_MAX, tb[DCB_ATTR_NUMTCS],
+ dcbnl_numtcs_nest);
+ if (ret) {
+ ret = -EINVAL;
+ goto err_out;
+ }
+
+ dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!dcbnl_skb) {
+ ret = -EINVAL;
+ goto err_out;
+ }
+
+ nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags);
+
+ dcb = NLMSG_DATA(nlh);
+ dcb->dcb_family = AF_UNSPEC;
+ dcb->cmd = DCB_CMD_GNUMTCS;
+
+ nest = nla_nest_start(dcbnl_skb, DCB_ATTR_NUMTCS);
+ if (!nest) {
+ ret = -EINVAL;
+ goto err;
+ }
+
+ if (data[DCB_NUMTCS_ATTR_ALL])
+ getall = 1;
+
+ for (i = DCB_NUMTCS_ATTR_ALL+1; i <= DCB_NUMTCS_ATTR_MAX; i++) {
+ if (!getall && !data[i])
+ continue;
+
+ ret = netdev->dcbnl_ops->getnumtcs(netdev, i, &value);
+ if (!ret) {
+ ret = nla_put_u8(dcbnl_skb, i, value);
+
+ if (ret) {
+ nla_nest_cancel(dcbnl_skb, nest);
+ ret = -EINVAL;
+ goto err;
+ }
+ } else {
+ goto err;
+ }
+ }
+ nla_nest_end(dcbnl_skb, nest);
+
+ nlmsg_end(dcbnl_skb, nlh);
+
+ ret = rtnl_unicast(dcbnl_skb, &init_net, pid);
+ if (ret) {
+ ret = -EINVAL;
+ goto err;
+ }
+
+ return 0;
+nlmsg_failure:
+err:
+ kfree(dcbnl_skb);
+err_out:
+ return ret;
+}
+
+static int dcbnl_setnumtcs(struct net_device *netdev, struct nlattr **tb,
+ u32 pid, u32 seq, u16 flags)
+{
+ struct nlattr *data[DCB_NUMTCS_ATTR_MAX + 1];
+ int ret = -EINVAL;
+ u8 value;
+ int i;
+
+ if (!tb[DCB_ATTR_NUMTCS] || !netdev->dcbnl_ops->setstate)
+ return ret;
+
+ ret = nla_parse_nested(data, DCB_NUMTCS_ATTR_MAX, tb[DCB_ATTR_NUMTCS],
+ dcbnl_numtcs_nest);
+
+ if (ret) {
+ ret = -EINVAL;
+ goto err;
+ }
+
+ for (i = DCB_NUMTCS_ATTR_ALL+1; i <= DCB_NUMTCS_ATTR_MAX; i++) {
+ if (data[i] == NULL)
+ continue;
+
+ value = nla_get_u8(data[i]);
+
+ ret = netdev->dcbnl_ops->setnumtcs(netdev, i, value);
+
+ if (ret)
+ goto operr;
+ }
+
+operr:
+ ret = dcbnl_reply(!!ret, RTM_SETDCB, DCB_CMD_SNUMTCS,
+ DCB_ATTR_NUMTCS, pid, seq, flags);
+
+err:
+ return ret;
+}
+
static int __dcbnl_pg_getcfg(struct net_device *netdev, struct nlattr **tb,
u32 pid, u32 seq, u16 flags, int dir)
{
@@ -757,6 +881,14 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
ret = dcbnl_getcap(netdev, tb, pid, nlh->nlmsg_seq,
nlh->nlmsg_flags);
goto out;
+ case DCB_CMD_GNUMTCS:
+ ret = dcbnl_getnumtcs(netdev, tb, pid, nlh->nlmsg_seq,
+ nlh->nlmsg_flags);
+ goto out;
+ case DCB_CMD_SNUMTCS:
+ ret = dcbnl_setnumtcs(netdev, tb, pid, nlh->nlmsg_seq,
+ nlh->nlmsg_flags);
+ goto out;
default:
goto errout;
}
--
cgit
From 0eb3aa9bab20217fb42244ccdcb5bf8a002f504c Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Thu, 20 Nov 2008 21:09:23 -0800
Subject: DCB: Add interface to query the state of PFC feature.
Adds a netlink interface for Data Center Bridging (DCB) to get and set
the enable state of the Priority Flow Control (PFC) feature.
Primarily, this is a way to turn off PFC in the driver while DCB
remains enabled.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/dcb/dcbnl.c | 43 +++++++++++++++++++++++++++++++++++++++++++
1 file changed, 43 insertions(+)
(limited to 'net/dcb')
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 5ff7e3c0c172..758419c6f59b 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -62,6 +62,7 @@ static struct nla_policy dcbnl_rtnl_policy[DCB_ATTR_MAX + 1] = {
[DCB_ATTR_SET_ALL] = {.type = NLA_U8},
[DCB_ATTR_PERM_HWADDR] = {.type = NLA_FLAG},
[DCB_ATTR_CAP] = {.type = NLA_NESTED},
+ [DCB_ATTR_PFC_STATE] = {.type = NLA_U8},
};
/* DCB priority flow control to User Priority nested attributes */
@@ -471,6 +472,40 @@ err:
return ret;
}
+static int dcbnl_getpfcstate(struct net_device *netdev, struct nlattr **tb,
+ u32 pid, u32 seq, u16 flags)
+{
+ int ret = -EINVAL;
+
+ if (!netdev->dcbnl_ops->getpfcstate)
+ return ret;
+
+ ret = dcbnl_reply(netdev->dcbnl_ops->getpfcstate(netdev), RTM_GETDCB,
+ DCB_CMD_PFC_GSTATE, DCB_ATTR_PFC_STATE,
+ pid, seq, flags);
+
+ return ret;
+}
+
+static int dcbnl_setpfcstate(struct net_device *netdev, struct nlattr **tb,
+ u32 pid, u32 seq, u16 flags)
+{
+ int ret = -EINVAL;
+ u8 value;
+
+ if (!tb[DCB_ATTR_PFC_STATE] || !netdev->dcbnl_ops->setpfcstate)
+ return ret;
+
+ value = nla_get_u8(tb[DCB_ATTR_PFC_STATE]);
+
+ netdev->dcbnl_ops->setpfcstate(netdev, value);
+
+ ret = dcbnl_reply(0, RTM_SETDCB, DCB_CMD_PFC_SSTATE, DCB_ATTR_PFC_STATE,
+ pid, seq, flags);
+
+ return ret;
+}
+
static int __dcbnl_pg_getcfg(struct net_device *netdev, struct nlattr **tb,
u32 pid, u32 seq, u16 flags, int dir)
{
@@ -889,6 +924,14 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
ret = dcbnl_setnumtcs(netdev, tb, pid, nlh->nlmsg_seq,
nlh->nlmsg_flags);
goto out;
+ case DCB_CMD_PFC_GSTATE:
+ ret = dcbnl_getpfcstate(netdev, tb, pid, nlh->nlmsg_seq,
+ nlh->nlmsg_flags);
+ goto out;
+ case DCB_CMD_PFC_SSTATE:
+ ret = dcbnl_setpfcstate(netdev, tb, pid, nlh->nlmsg_seq,
+ nlh->nlmsg_flags);
+ goto out;
default:
goto errout;
}
--
cgit
From 859ee3c43812051e21816c6d6d4cc04fb7ce9b2e Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Thu, 20 Nov 2008 21:10:23 -0800
Subject: DCB: Add support for DCB BCN
Adds an interface to configure the Backward Congestion Notification
(BCN) feature. In a BCN capabale network, congestion notifications
from congested points out in the network can cause the end station
limit the rate of a given traffic flow.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/dcb/dcbnl.c | 174 +++++++++++++++++++++++++++++++++++++++++++++++++++++---
1 file changed, 167 insertions(+), 7 deletions(-)
(limited to 'net/dcb')
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 758419c6f59b..b2bda3f610df 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -55,14 +55,15 @@ MODULE_LICENSE("GPL");
/* DCB netlink attributes policy */
static struct nla_policy dcbnl_rtnl_policy[DCB_ATTR_MAX + 1] = {
- [DCB_ATTR_IFNAME] = {.type = NLA_STRING, .len = IFNAMSIZ - 1},
- [DCB_ATTR_STATE] = {.type = NLA_U8},
- [DCB_ATTR_PFC_CFG] = {.type = NLA_NESTED},
- [DCB_ATTR_PG_CFG] = {.type = NLA_NESTED},
- [DCB_ATTR_SET_ALL] = {.type = NLA_U8},
+ [DCB_ATTR_IFNAME] = {.type = NLA_NUL_STRING, .len = IFNAMSIZ - 1},
+ [DCB_ATTR_STATE] = {.type = NLA_U8},
+ [DCB_ATTR_PFC_CFG] = {.type = NLA_NESTED},
+ [DCB_ATTR_PG_CFG] = {.type = NLA_NESTED},
+ [DCB_ATTR_SET_ALL] = {.type = NLA_U8},
[DCB_ATTR_PERM_HWADDR] = {.type = NLA_FLAG},
- [DCB_ATTR_CAP] = {.type = NLA_NESTED},
- [DCB_ATTR_PFC_STATE] = {.type = NLA_U8},
+ [DCB_ATTR_CAP] = {.type = NLA_NESTED},
+ [DCB_ATTR_PFC_STATE] = {.type = NLA_U8},
+ [DCB_ATTR_BCN] = {.type = NLA_NESTED},
};
/* DCB priority flow control to User Priority nested attributes */
@@ -128,6 +129,33 @@ static struct nla_policy dcbnl_numtcs_nest[DCB_NUMTCS_ATTR_MAX + 1] = {
[DCB_NUMTCS_ATTR_PFC] = {.type = NLA_U8},
};
+/* DCB BCN nested attributes. */
+static struct nla_policy dcbnl_bcn_nest[DCB_BCN_ATTR_MAX + 1] = {
+ [DCB_BCN_ATTR_RP_0] = {.type = NLA_U8},
+ [DCB_BCN_ATTR_RP_1] = {.type = NLA_U8},
+ [DCB_BCN_ATTR_RP_2] = {.type = NLA_U8},
+ [DCB_BCN_ATTR_RP_3] = {.type = NLA_U8},
+ [DCB_BCN_ATTR_RP_4] = {.type = NLA_U8},
+ [DCB_BCN_ATTR_RP_5] = {.type = NLA_U8},
+ [DCB_BCN_ATTR_RP_6] = {.type = NLA_U8},
+ [DCB_BCN_ATTR_RP_7] = {.type = NLA_U8},
+ [DCB_BCN_ATTR_RP_ALL] = {.type = NLA_FLAG},
+ [DCB_BCN_ATTR_ALPHA] = {.type = NLA_U32},
+ [DCB_BCN_ATTR_BETA] = {.type = NLA_U32},
+ [DCB_BCN_ATTR_GD] = {.type = NLA_U32},
+ [DCB_BCN_ATTR_GI] = {.type = NLA_U32},
+ [DCB_BCN_ATTR_TMAX] = {.type = NLA_U32},
+ [DCB_BCN_ATTR_TD] = {.type = NLA_U32},
+ [DCB_BCN_ATTR_RMIN] = {.type = NLA_U32},
+ [DCB_BCN_ATTR_W] = {.type = NLA_U32},
+ [DCB_BCN_ATTR_RD] = {.type = NLA_U32},
+ [DCB_BCN_ATTR_RU] = {.type = NLA_U32},
+ [DCB_BCN_ATTR_WRTT] = {.type = NLA_U32},
+ [DCB_BCN_ATTR_RI] = {.type = NLA_U32},
+ [DCB_BCN_ATTR_C] = {.type = NLA_U32},
+ [DCB_BCN_ATTR_ALL] = {.type = NLA_FLAG},
+};
+
/* standard netlink reply call */
static int dcbnl_reply(u8 value, u8 event, u8 cmd, u8 attr, u32 pid,
u32 seq, u16 flags)
@@ -843,6 +871,130 @@ static int dcbnl_pgrx_setcfg(struct net_device *netdev, struct nlattr **tb,
return __dcbnl_pg_setcfg(netdev, tb, pid, seq, flags, 1);
}
+static int dcbnl_bcn_getcfg(struct net_device *netdev, struct nlattr **tb,
+ u32 pid, u32 seq, u16 flags)
+{
+ struct sk_buff *dcbnl_skb;
+ struct nlmsghdr *nlh;
+ struct dcbmsg *dcb;
+ struct nlattr *bcn_nest;
+ struct nlattr *bcn_tb[DCB_BCN_ATTR_MAX + 1];
+ u8 value_byte;
+ u32 value_integer;
+ int ret = -EINVAL;
+ bool getall = false;
+ int i;
+
+ if (!tb[DCB_ATTR_BCN] || !netdev->dcbnl_ops->getbcnrp ||
+ !netdev->dcbnl_ops->getbcncfg)
+ return ret;
+
+ ret = nla_parse_nested(bcn_tb, DCB_BCN_ATTR_MAX,
+ tb[DCB_ATTR_BCN], dcbnl_bcn_nest);
+
+ if (ret)
+ goto err_out;
+
+ dcbnl_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!dcbnl_skb)
+ goto err_out;
+
+ nlh = NLMSG_NEW(dcbnl_skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags);
+
+ dcb = NLMSG_DATA(nlh);
+ dcb->dcb_family = AF_UNSPEC;
+ dcb->cmd = DCB_CMD_BCN_GCFG;
+
+ bcn_nest = nla_nest_start(dcbnl_skb, DCB_ATTR_BCN);
+ if (!bcn_nest)
+ goto err;
+
+ if (bcn_tb[DCB_BCN_ATTR_ALL])
+ getall = true;
+
+ for (i = DCB_BCN_ATTR_RP_0; i <= DCB_BCN_ATTR_RP_7; i++) {
+ if (!getall && !bcn_tb[i])
+ continue;
+
+ netdev->dcbnl_ops->getbcnrp(netdev, i - DCB_BCN_ATTR_RP_0,
+ &value_byte);
+ ret = nla_put_u8(dcbnl_skb, i, value_byte);
+ if (ret)
+ goto err_bcn;
+ }
+
+ for (i = DCB_BCN_ATTR_ALPHA; i <= DCB_BCN_ATTR_RI; i++) {
+ if (!getall && !bcn_tb[i])
+ continue;
+
+ netdev->dcbnl_ops->getbcncfg(netdev, i,
+ &value_integer);
+ ret = nla_put_u32(dcbnl_skb, i, value_integer);
+ if (ret)
+ goto err_bcn;
+ }
+
+ nla_nest_end(dcbnl_skb, bcn_nest);
+
+ nlmsg_end(dcbnl_skb, nlh);
+
+ ret = rtnl_unicast(dcbnl_skb, &init_net, pid);
+ if (ret)
+ goto err;
+
+ return 0;
+
+err_bcn:
+ nla_nest_cancel(dcbnl_skb, bcn_nest);
+nlmsg_failure:
+err:
+ kfree(dcbnl_skb);
+err_out:
+ ret = -EINVAL;
+ return ret;
+}
+
+static int dcbnl_bcn_setcfg(struct net_device *netdev, struct nlattr **tb,
+ u32 pid, u32 seq, u16 flags)
+{
+ struct nlattr *data[DCB_BCN_ATTR_MAX + 1];
+ int i;
+ int ret = -EINVAL;
+ u8 value_byte;
+ u32 value_int;
+
+ if (!tb[DCB_ATTR_BCN] || !netdev->dcbnl_ops->setbcncfg
+ || !netdev->dcbnl_ops->setbcnrp)
+ return ret;
+
+ ret = nla_parse_nested(data, DCB_BCN_ATTR_MAX,
+ tb[DCB_ATTR_BCN],
+ dcbnl_pfc_up_nest);
+ if (ret)
+ goto err;
+
+ for (i = DCB_BCN_ATTR_RP_0; i <= DCB_BCN_ATTR_RP_7; i++) {
+ if (data[i] == NULL)
+ continue;
+ value_byte = nla_get_u8(data[i]);
+ netdev->dcbnl_ops->setbcnrp(netdev,
+ data[i]->nla_type - DCB_BCN_ATTR_RP_0, value_byte);
+ }
+
+ for (i = DCB_BCN_ATTR_ALPHA; i <= DCB_BCN_ATTR_RI; i++) {
+ if (data[i] == NULL)
+ continue;
+ value_int = nla_get_u32(data[i]);
+ netdev->dcbnl_ops->setbcncfg(netdev,
+ i, value_int);
+ }
+
+ ret = dcbnl_reply(0, RTM_SETDCB, DCB_CMD_BCN_SCFG, DCB_ATTR_BCN,
+ pid, seq, flags);
+err:
+ return ret;
+}
+
static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
{
struct net *net = sock_net(skb->sk);
@@ -891,6 +1043,10 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
ret = dcbnl_pgrx_getcfg(netdev, tb, pid, nlh->nlmsg_seq,
nlh->nlmsg_flags);
goto out;
+ case DCB_CMD_BCN_GCFG:
+ ret = dcbnl_bcn_getcfg(netdev, tb, pid, nlh->nlmsg_seq,
+ nlh->nlmsg_flags);
+ goto out;
case DCB_CMD_SSTATE:
ret = dcbnl_setstate(netdev, tb, pid, nlh->nlmsg_seq,
nlh->nlmsg_flags);
@@ -932,6 +1088,10 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
ret = dcbnl_setpfcstate(netdev, tb, pid, nlh->nlmsg_seq,
nlh->nlmsg_flags);
goto out;
+ case DCB_CMD_BCN_SCFG:
+ ret = dcbnl_bcn_setcfg(netdev, tb, pid, nlh->nlmsg_seq,
+ nlh->nlmsg_flags);
+ goto out;
default:
goto errout;
}
--
cgit
From 7a6b6f515f77d1c62a2f383b6dce18cb0af0cf4f Mon Sep 17 00:00:00 2001
From: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Date: Tue, 25 Nov 2008 01:02:08 -0800
Subject: DCB: fix kconfig option
Since the netlink option for DCB is necessary to actually be useful,
simplified the Kconfig option. In addition, added useful help text for the
Kconfig option.
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/dcb/Kconfig | 24 +++++++++++++++++-------
net/dcb/dcbnl.c | 2 +-
2 files changed, 18 insertions(+), 8 deletions(-)
(limited to 'net/dcb')
diff --git a/net/dcb/Kconfig b/net/dcb/Kconfig
index bdf38802d339..4066d59c8de5 100644
--- a/net/dcb/Kconfig
+++ b/net/dcb/Kconfig
@@ -1,12 +1,22 @@
config DCB
- tristate "Data Center Bridging support"
-
-config DCBNL
- bool "Data Center Bridging netlink interface support"
- depends on DCB
+ bool "Data Center Bridging support"
default n
---help---
- This option turns on the netlink interface
- (dcbnl) for Data Center Bridging capable devices.
+ This enables support for configuring Data Center Bridging (DCB)
+ features on DCB capable Ethernet adapters via rtnetlink. Say 'Y'
+ if you have a DCB capable Ethernet adapter which supports this
+ interface and you are connected to a DCB capable switch.
+
+ DCB is a collection of Ethernet enhancements which allow DCB capable
+ NICs and switches to support network traffic with differing
+ requirements (highly reliable, no drops vs. best effort vs. low
+ latency) to co-exist on Ethernet.
+
+ DCB features include:
+ Enhanced Transmission Selection (aka Priority Grouping) - provides a
+ framework for assigning bandwidth guarantees to traffic classes.
+ Priority-based Flow Control (PFC) - a MAC control pause frame which
+ works at the granularity of the 802.1p priority instead of the
+ link (802.3x).
If unsure, say N.
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index b2bda3f610df..79a351d323af 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -48,7 +48,7 @@
*/
MODULE_AUTHOR("Lucy Liu, <lucy.liu@intel.com>");
-MODULE_DESCRIPTION("Data Center Bridging generic netlink interface");
+MODULE_DESCRIPTION("Data Center Bridging netlink interface");
MODULE_LICENSE("GPL");
/**************** DCB attribute policies *************************************/
--
cgit
From 8b124a8e14c04378466ddfe63e41fc5035f957eb Mon Sep 17 00:00:00 2001
From: Don Skidmore <donald.c.skidmore@intel.com>
Date: Mon, 15 Dec 2008 01:06:23 -0800
Subject: net: fix dcbnl_setnumtcs operation check
dcbml_setnumtcs wasn't checking for the presence of the setnumtcs
function. Instead, it was checking for setstate which was a bug.
Signed-off-by: Don Skidmore <donald.c.skidmore@intel.com>
Signed-off-by: Eric W Multanen <eric.w.multanen@intel.com>
Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/dcb/dcbnl.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'net/dcb')
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 79a351d323af..a1254061629f 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -469,7 +469,7 @@ static int dcbnl_setnumtcs(struct net_device *netdev, struct nlattr **tb,
u8 value;
int i;
- if (!tb[DCB_ATTR_NUMTCS] || !netdev->dcbnl_ops->setstate)
+ if (!tb[DCB_ATTR_NUMTCS] || !netdev->dcbnl_ops->setnumtcs)
return ret;
ret = nla_parse_nested(data, DCB_NUMTCS_ATTR_MAX, tb[DCB_ATTR_NUMTCS],
--
cgit
From 1486a61ebcd2711532f8163d30babc40e11e7b40 Mon Sep 17 00:00:00 2001
From: Don Skidmore <donald.c.skidmore@intel.com>
Date: Sun, 21 Dec 2008 20:09:50 -0800
Subject: net: fix DCB setstate to return success/failure
Data Center Bridging (DCB) had no way to know if setstate had failed in the
driver. This patch enables dcb netlink code to handle the status for the DCB
setstate interface. Likewise it allows the driver to return a failed status
if MSI-X isn't enabled.
Signed-off-by: Don Skidmore <donald.c.skidmore@intel.com>
Signed-off-by: Eric W Multanen <eric.w.multanen@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/dcb/dcbnl.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
(limited to 'net/dcb')
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index a1254061629f..fc88fc4d4f63 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -714,9 +714,8 @@ static int dcbnl_setstate(struct net_device *netdev, struct nlattr **tb,
value = nla_get_u8(tb[DCB_ATTR_STATE]);
- netdev->dcbnl_ops->setstate(netdev, value);
-
- ret = dcbnl_reply(0, RTM_SETDCB, DCB_CMD_SSTATE, DCB_ATTR_STATE,
+ ret = dcbnl_reply(netdev->dcbnl_ops->setstate(netdev, value),
+ RTM_SETDCB, DCB_CMD_SSTATE, DCB_ATTR_STATE,
pid, seq, flags);
return ret;
--
cgit
From f4314e815e87b4ab1c9b1115dd5853cd20ca999c Mon Sep 17 00:00:00 2001
From: Don Skidmore <donald.c.skidmore@intel.com>
Date: Sun, 21 Dec 2008 20:10:29 -0800
Subject: net: add DCNA attribute to the BCN interface for DCB
Adds the Backward Congestion Notification Address (BCNA) attribute to the
Backward Congestion Notification (BCN) interface for Data Center Bridging
(DCB), which was missing. Receive the BCNA attribute in the ixgbe driver.
The BCNA attribute is for a switch to inform the endstation about the physical
port identification in order to support BCN on aggregated links.
Signed-off-by: Don Skidmore <donald.c.skidmore@intel.com>
Signed-off-by: Eric W Multanen <eric.w.multanen@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
net/dcb/dcbnl.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
(limited to 'net/dcb')
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index fc88fc4d4f63..5dbfe5fdc0d6 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -140,6 +140,8 @@ static struct nla_policy dcbnl_bcn_nest[DCB_BCN_ATTR_MAX + 1] = {
[DCB_BCN_ATTR_RP_6] = {.type = NLA_U8},
[DCB_BCN_ATTR_RP_7] = {.type = NLA_U8},
[DCB_BCN_ATTR_RP_ALL] = {.type = NLA_FLAG},
+ [DCB_BCN_ATTR_BCNA_0] = {.type = NLA_U32},
+ [DCB_BCN_ATTR_BCNA_1] = {.type = NLA_U32},
[DCB_BCN_ATTR_ALPHA] = {.type = NLA_U32},
[DCB_BCN_ATTR_BETA] = {.type = NLA_U32},
[DCB_BCN_ATTR_GD] = {.type = NLA_U32},
@@ -922,7 +924,7 @@ static int dcbnl_bcn_getcfg(struct net_device *netdev, struct nlattr **tb,
goto err_bcn;
}
- for (i = DCB_BCN_ATTR_ALPHA; i <= DCB_BCN_ATTR_RI; i++) {
+ for (i = DCB_BCN_ATTR_BCNA_0; i <= DCB_BCN_ATTR_RI; i++) {
if (!getall && !bcn_tb[i])
continue;
@@ -980,7 +982,7 @@ static int dcbnl_bcn_setcfg(struct net_device *netdev, struct nlattr **tb,
data[i]->nla_type - DCB_BCN_ATTR_RP_0, value_byte);
}
- for (i = DCB_BCN_ATTR_ALPHA; i <= DCB_BCN_ATTR_RI; i++) {
+ for (i = DCB_BCN_ATTR_BCNA_0; i <= DCB_BCN_ATTR_RI; i++) {
if (data[i] == NULL)
continue;
value_int = nla_get_u32(data[i]);
--
cgit