ethtool: add tunnel info interface

Add an interface to report offloaded UDP ports via ethtool netlink.

Now that core takes care of tracking which UDP tunnel ports the NICs
are aware of we can quite easily export this information out to
user space.

The responsibility of writing the netlink dumps is split between
ethtool code and udp_tunnel_nic.c - since udp_tunnel module may
not always be loaded, yet we should always report the capabilities
of the NIC.

$ ethtool --show-tunnels eth0
Tunnel information for eth0:
  UDP port table 0:
    Size: 4
    Types: vxlan
    No entries
  UDP port table 1:
    Size: 4
    Types: geneve, vxlan-gpe
    Entries (1):
        port 1230, vxlan-gpe

v4:
 - back to v2, build fix is now directly in udp_tunnel.h
v3:
 - don't compile ETHTOOL_MSG_TUNNEL_INFO_GET in if CONFIG_INET
   not set.
v2:
 - fix string set count,
 - reorder enums in the uAPI,
 - fix type of ETHTOOL_A_TUNNEL_UDP_TABLE_TYPES to bitset
   in docs and comments.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 292 insertions, 1 deletions

diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile
index 0c2b94f20499..7a849ff22dad 100644
--- a/net/ethtool/Makefile
+++ b/net/ethtool/Makefile
@@ -6,4 +6,5 @@ obj-$(CONFIG_ETHTOOL_NETLINK)	+= ethtool_nl.o
 
 ethtool_nl-y	:= netlink.o bitset.o strset.o linkinfo.o linkmodes.o \
 		   linkstate.o debug.o wol.o features.o privflags.o rings.o \
-		   channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o
+		   channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o \
+		   tunnels.o
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index c54166713797..ed19573fccd7 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 
+#include <linux/ethtool_netlink.h>
 #include <linux/net_tstamp.h>
 #include <linux/phy.h>
 #include <linux/rtnetlink.h>
@@ -272,6 +273,14 @@ const char ts_rx_filter_names[][ETH_GSTRING_LEN] = {
 };
 static_assert(ARRAY_SIZE(ts_rx_filter_names) == __HWTSTAMP_FILTER_CNT);
 
+const char udp_tunnel_type_names[][ETH_GSTRING_LEN] = {
+	[ETHTOOL_UDP_TUNNEL_TYPE_VXLAN]		= "vxlan",
+	[ETHTOOL_UDP_TUNNEL_TYPE_GENEVE]	= "geneve",
+	[ETHTOOL_UDP_TUNNEL_TYPE_VXLAN_GPE]	= "vxlan-gpe",
+};
+static_assert(ARRAY_SIZE(udp_tunnel_type_names) ==
+	      __ETHTOOL_UDP_TUNNEL_TYPE_CNT);
+
 /* return false if legacy contained non-0 deprecated fields
  * maxtxpkt/maxrxpkt. rest of ksettings always updated
  */
diff --git a/net/ethtool/common.h b/net/ethtool/common.h
index b83bef38368c..3d9251c95a8b 100644
--- a/net/ethtool/common.h
+++ b/net/ethtool/common.h
@@ -28,6 +28,7 @@ extern const char wol_mode_names[][ETH_GSTRING_LEN];
 extern const char sof_timestamping_names[][ETH_GSTRING_LEN];
 extern const char ts_tx_type_names[][ETH_GSTRING_LEN];
 extern const char ts_rx_filter_names[][ETH_GSTRING_LEN];
+extern const char udp_tunnel_type_names[][ETH_GSTRING_LEN];
 
 int __ethtool_get_link(struct net_device *dev);
 
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index 88fd07f47040..fb9d096faaa4 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -181,6 +181,12 @@ err:
 	return NULL;
 }
 
+void *ethnl_dump_put(struct sk_buff *skb, struct netlink_callback *cb, u8 cmd)
+{
+	return genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+			   &ethtool_genl_family, 0, cmd);
+}
+
 void *ethnl_bcastmsg_put(struct sk_buff *skb, u8 cmd)
 {
 	return genlmsg_put(skb, 0, ++ethnl_bcast_seq, &ethtool_genl_family, 0,
@@ -849,6 +855,12 @@ static const struct genl_ops ethtool_genl_ops[] = {
 		.flags	= GENL_UNS_ADMIN_PERM,
 		.doit	= ethnl_act_cable_test_tdr,
 	},
+	{
+		.cmd	= ETHTOOL_MSG_TUNNEL_INFO_GET,
+		.doit	= ethnl_tunnel_info_doit,
+		.start	= ethnl_tunnel_info_start,
+		.dumpit	= ethnl_tunnel_info_dumpit,
+	},
 };
 
 static const struct genl_multicast_group ethtool_nl_mcgrps[] = {
diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h
index 9a96b6e90dc2..e2085005caac 100644
--- a/net/ethtool/netlink.h
+++ b/net/ethtool/netlink.h
@@ -19,6 +19,7 @@ int ethnl_fill_reply_header(struct sk_buff *skb, struct net_device *dev,
 struct sk_buff *ethnl_reply_init(size_t payload, struct net_device *dev, u8 cmd,
 				 u16 hdr_attrtype, struct genl_info *info,
 				 void **ehdrp);
+void *ethnl_dump_put(struct sk_buff *skb, struct netlink_callback *cb, u8 cmd);
 void *ethnl_bcastmsg_put(struct sk_buff *skb, u8 cmd);
 int ethnl_multicast(struct sk_buff *skb, struct net_device *dev);
 
@@ -361,5 +362,8 @@ int ethnl_set_pause(struct sk_buff *skb, struct genl_info *info);
 int ethnl_set_eee(struct sk_buff *skb, struct genl_info *info);
 int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info);
 int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info);
+int ethnl_tunnel_info_doit(struct sk_buff *skb, struct genl_info *info);
+int ethnl_tunnel_info_start(struct netlink_callback *cb);
+int ethnl_tunnel_info_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
 
 #endif /* _NET_ETHTOOL_NETLINK_H */
diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c
index 773634b6b048..82707b662fe4 100644
--- a/net/ethtool/strset.c
+++ b/net/ethtool/strset.c
@@ -75,6 +75,11 @@ static const struct strset_info info_template[] = {
 		.count		= __HWTSTAMP_FILTER_CNT,
 		.strings	= ts_rx_filter_names,
 	},
+	[ETH_SS_UDP_TUNNEL_TYPES] = {
+		.per_dev	= false,
+		.count		= __ETHTOOL_UDP_TUNNEL_TYPE_CNT,
+		.strings	= udp_tunnel_type_names,
+	},
 };
 
 struct strset_req_info {
diff --git a/net/ethtool/tunnels.c b/net/ethtool/tunnels.c
new file mode 100644
index 000000000000..6b89255f1231
--- /dev/null
+++ b/net/ethtool/tunnels.c
@@ -0,0 +1,259 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/ethtool_netlink.h>
+#include <net/udp_tunnel.h>
+
+#include "bitset.h"
+#include "common.h"
+#include "netlink.h"
+
+static const struct nla_policy
+ethtool_tunnel_info_policy[ETHTOOL_A_TUNNEL_INFO_MAX + 1] = {
+	[ETHTOOL_A_TUNNEL_INFO_UNSPEC]		= { .type = NLA_REJECT },
+	[ETHTOOL_A_TUNNEL_INFO_HEADER]		= { .type = NLA_NESTED },
+};
+
+static_assert(ETHTOOL_UDP_TUNNEL_TYPE_VXLAN == ilog2(UDP_TUNNEL_TYPE_VXLAN));
+static_assert(ETHTOOL_UDP_TUNNEL_TYPE_GENEVE == ilog2(UDP_TUNNEL_TYPE_GENEVE));
+static_assert(ETHTOOL_UDP_TUNNEL_TYPE_VXLAN_GPE ==
+	      ilog2(UDP_TUNNEL_TYPE_VXLAN_GPE));
+
+static ssize_t
+ethnl_tunnel_info_reply_size(const struct ethnl_req_info *req_base,
+			     struct netlink_ext_ack *extack)
+{
+	bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS;
+	const struct udp_tunnel_nic_info *info;
+	unsigned int i;
+	size_t size;
+	int ret;
+
+	info = req_base->dev->udp_tunnel_nic_info;
+	if (!info) {
+		NL_SET_ERR_MSG(extack,
+			       "device does not report tunnel offload info");
+		return -EOPNOTSUPP;
+	}
+
+	size =	nla_total_size(0); /* _INFO_UDP_PORTS */
+
+	for (i = 0; i < UDP_TUNNEL_NIC_MAX_TABLES; i++) {
+		if (!info->tables[i].n_entries)
+			return size;
+
+		size += nla_total_size(0); /* _UDP_TABLE */
+		size +=	nla_total_size(sizeof(u32)); /* _UDP_TABLE_SIZE */
+		ret = ethnl_bitset32_size(&info->tables[i].tunnel_types, NULL,
+					  __ETHTOOL_UDP_TUNNEL_TYPE_CNT,
+					  udp_tunnel_type_names, compact);
+		if (ret < 0)
+			return ret;
+		size += ret;
+
+		size += udp_tunnel_nic_dump_size(req_base->dev, i);
+	}
+
+	return size;
+}
+
+static int
+ethnl_tunnel_info_fill_reply(const struct ethnl_req_info *req_base,
+			     struct sk_buff *skb)
+{
+	bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS;
+	const struct udp_tunnel_nic_info *info;
+	struct nlattr *ports, *table;
+	unsigned int i;
+
+	info = req_base->dev->udp_tunnel_nic_info;
+	if (!info)
+		return -EOPNOTSUPP;
+
+	ports = nla_nest_start(skb, ETHTOOL_A_TUNNEL_INFO_UDP_PORTS);
+	if (!ports)
+		return -EMSGSIZE;
+
+	for (i = 0; i < UDP_TUNNEL_NIC_MAX_TABLES; i++) {
+		if (!info->tables[i].n_entries)
+			break;
+
+		table = nla_nest_start(skb, ETHTOOL_A_TUNNEL_UDP_TABLE);
+		if (!table)
+			goto err_cancel_ports;
+
+		if (nla_put_u32(skb, ETHTOOL_A_TUNNEL_UDP_TABLE_SIZE,
+				info->tables[i].n_entries))
+			goto err_cancel_table;
+
+		if (ethnl_put_bitset32(skb, ETHTOOL_A_TUNNEL_UDP_TABLE_TYPES,
+				       &info->tables[i].tunnel_types, NULL,
+				       __ETHTOOL_UDP_TUNNEL_TYPE_CNT,
+				       udp_tunnel_type_names, compact))
+			goto err_cancel_table;
+
+		if (udp_tunnel_nic_dump_write(req_base->dev, i, skb))
+			goto err_cancel_table;
+
+		nla_nest_end(skb, table);
+	}
+
+	nla_nest_end(skb, ports);
+
+	return 0;
+
+err_cancel_table:
+	nla_nest_cancel(skb, table);
+err_cancel_ports:
+	nla_nest_cancel(skb, ports);
+	return -EMSGSIZE;
+}
+
+static int
+ethnl_tunnel_info_req_parse(struct ethnl_req_info *req_info,
+			    const struct nlmsghdr *nlhdr, struct net *net,
+			    struct netlink_ext_ack *extack, bool require_dev)
+{
+	struct nlattr *tb[ETHTOOL_A_TUNNEL_INFO_MAX + 1];
+	int ret;
+
+	ret = nlmsg_parse(nlhdr, GENL_HDRLEN, tb, ETHTOOL_A_TUNNEL_INFO_MAX,
+			  ethtool_tunnel_info_policy, extack);
+	if (ret < 0)
+		return ret;
+
+	return ethnl_parse_header_dev_get(req_info,
+					  tb[ETHTOOL_A_TUNNEL_INFO_HEADER],
+					  net, extack, require_dev);
+}
+
+int ethnl_tunnel_info_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct ethnl_req_info req_info = {};
+	struct sk_buff *rskb;
+	void *reply_payload;
+	int reply_len;
+	int ret;
+
+	ret = ethnl_tunnel_info_req_parse(&req_info, info->nlhdr,
+					  genl_info_net(info), info->extack,
+					  true);
+	if (ret < 0)
+		return ret;
+
+	rtnl_lock();
+	ret = ethnl_tunnel_info_reply_size(&req_info, info->extack);
+	if (ret < 0)
+		goto err_unlock_rtnl;
+	reply_len = ret + ethnl_reply_header_size();
+
+	rskb = ethnl_reply_init(reply_len, req_info.dev,
+				ETHTOOL_MSG_TUNNEL_INFO_GET,
+				ETHTOOL_A_TUNNEL_INFO_HEADER,
+				info, &reply_payload);
+	if (!rskb) {
+		ret = -ENOMEM;
+		goto err_unlock_rtnl;
+	}
+
+	ret = ethnl_tunnel_info_fill_reply(&req_info, rskb);
+	if (ret)
+		goto err_free_msg;
+	rtnl_unlock();
+	dev_put(req_info.dev);
+	genlmsg_end(rskb, reply_payload);
+
+	return genlmsg_reply(rskb, info);
+
+err_free_msg:
+	nlmsg_free(rskb);
+err_unlock_rtnl:
+	rtnl_unlock();
+	dev_put(req_info.dev);
+	return ret;
+}
+
+struct ethnl_tunnel_info_dump_ctx {
+	struct ethnl_req_info	req_info;
+	int			pos_hash;
+	int			pos_idx;
+};
+
+int ethnl_tunnel_info_start(struct netlink_callback *cb)
+{
+	struct ethnl_tunnel_info_dump_ctx *ctx = (void *)cb->ctx;
+	int ret;
+
+	BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx));
+
+	memset(ctx, 0, sizeof(*ctx));
+
+	ret = ethnl_tunnel_info_req_parse(&ctx->req_info, cb->nlh,
+					  sock_net(cb->skb->sk), cb->extack,
+					  false);
+	if (ctx->req_info.dev) {
+		dev_put(ctx->req_info.dev);
+		ctx->req_info.dev = NULL;
+	}
+
+	return ret;
+}
+
+int ethnl_tunnel_info_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct ethnl_tunnel_info_dump_ctx *ctx = (void *)cb->ctx;
+	struct net *net = sock_net(skb->sk);
+	int s_idx = ctx->pos_idx;
+	int h, idx = 0;
+	int ret = 0;
+	void *ehdr;
+
+	rtnl_lock();
+	cb->seq = net->dev_base_seq;
+	for (h = ctx->pos_hash; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
+		struct hlist_head *head;
+		struct net_device *dev;
+
+		head = &net->dev_index_head[h];
+		idx = 0;
+		hlist_for_each_entry(dev, head, index_hlist) {
+			if (idx < s_idx)
+				goto cont;
+
+			ehdr = ethnl_dump_put(skb, cb,
+					      ETHTOOL_MSG_TUNNEL_INFO_GET);
+			if (!ehdr) {
+				ret = -EMSGSIZE;
+				goto out;
+			}
+
+			ret = ethnl_fill_reply_header(skb, dev, ETHTOOL_A_TUNNEL_INFO_HEADER);
+			if (ret < 0) {
+				genlmsg_cancel(skb, ehdr);
+				goto out;
+			}
+
+			ctx->req_info.dev = dev;
+			ret = ethnl_tunnel_info_fill_reply(&ctx->req_info, skb);
+			ctx->req_info.dev = NULL;
+			if (ret < 0) {
+				genlmsg_cancel(skb, ehdr);
+				if (ret == -EOPNOTSUPP)
+					goto cont;
+				goto out;
+			}
+			genlmsg_end(skb, ehdr);
+cont:
+			idx++;
+		}
+	}
+out:
+	rtnl_unlock();
+
+	ctx->pos_hash = h;
+	ctx->pos_idx = idx;
+	nl_dump_check_consistent(cb, nlmsg_hdr(skb));
+
+	if (ret == -EMSGSIZE && skb->len)
+		return skb->len;
+	return ret;
+}