rtnetlink: add support for protodown reason

netdev protodown is a mechanism that allows protocols to
hold an interface down. It was initially introduced in
the kernel to hold links down by a multihoming protocol.
There was also an attempt to introduce protodown
reason at the time but was rejected. protodown and protodown reason
is supported by almost every switching and routing platform.
It was ok for a while to live without a protodown reason.
But, its become more critical now given more than
one protocol may need to keep a link down on a system
at the same time. eg: vrrp peer node, port security,
multihoming protocol. Its common for Network operators and
protocol developers to look for such a reason on a networking
box (Its also known as errDisable by most networking operators)

This patch adds support for link protodown reason
attribute. There are two ways to maintain protodown
reasons.
(a) enumerate every possible reason code in kernel
    - A protocol developer has to make a request and
      have that appear in a certain kernel version
(b) provide the bits in the kernel, and allow user-space
(sysadmin or NOS distributions) to manage the bit-to-reasonname
map.
	- This makes extending reason codes easier (kind of like
      the iproute2 table to vrf-name map /etc/iproute2/rt_tables.d/)

This patch takes approach (b).

a few things about the patch:
- It treats the protodown reason bits as counter to indicate
active protodown users
- Since protodown attribute is already an exposed UAPI,
the reason is not enforced on a protodown set. Its a no-op
if not used.
the patch follows the below algorithm:
  - presence of reason bits set indicates protodown
    is in use
  - user can set protodown and protodown reason in a
    single or multiple setlink operations
  - setlink operation to clear protodown, will return -EBUSY
    if there are active protodown reason bits
  - reason is not included in link dumps if not used

example with patched iproute2:
$cat /etc/iproute2/protodown_reasons.d/r.conf
0 mlag
1 evpn
2 vrrp
3 psecurity

$ip link set dev vxlan0 protodown on protodown_reason vrrp on
$ip link set dev vxlan0 protodown_reason mlag on
$ip link show
14: vxlan0: <BROADCAST,MULTICAST> mtu 1500 qdisc noop state DOWN mode
DEFAULT group default qlen 1000
    link/ether f6:06:be:17:91:e7 brd ff:ff:ff:ff:ff:ff protodown on <mlag,vrrp>

$ip link set dev vxlan0 protodown_reason mlag off
$ip link set dev vxlan0 protodown off protodown_reason vrrp off

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 133 insertions, 5 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 38a6371d9bc5..f7ef0f5c5569 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8715,6 +8715,31 @@ int dev_change_proto_down_generic(struct net_device *dev, bool proto_down)
 }
 EXPORT_SYMBOL(dev_change_proto_down_generic);
 
+/**
+ *	dev_change_proto_down_reason - proto down reason
+ *
+ *	@dev: device
+ *	@mask: proto down mask
+ *	@value: proto down value
+ */
+void dev_change_proto_down_reason(struct net_device *dev, unsigned long mask,
+				  u32 value)
+{
+	int b;
+
+	if (!mask) {
+		dev->proto_down_reason = value;
+	} else {
+		for_each_set_bit(b, &mask, 32) {
+			if (value & (1 << b))
+				dev->proto_down_reason |= BIT(b);
+			else
+				dev->proto_down_reason &= ~BIT(b);
+		}
+	}
+}
+EXPORT_SYMBOL(dev_change_proto_down_reason);
+
 u32 __dev_xdp_query(struct net_device *dev, bpf_op_t bpf_op,
 		    enum bpf_netdev_command cmd)
 {
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 85a4b0101f76..a54c3e0f2ee1 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1000,6 +1000,16 @@ static size_t rtnl_prop_list_size(const struct net_device *dev)
 	return size;
 }
 
+static size_t rtnl_proto_down_size(const struct net_device *dev)
+{
+	size_t size = nla_total_size(1);
+
+	if (dev->proto_down_reason)
+		size += nla_total_size(0) + nla_total_size(4);
+
+	return size;
+}
+
 static noinline size_t if_nlmsg_size(const struct net_device *dev,
 				     u32 ext_filter_mask)
 {
@@ -1041,7 +1051,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + nla_total_size(4)  /* IFLA_EVENT */
 	       + nla_total_size(4)  /* IFLA_NEW_NETNSID */
 	       + nla_total_size(4)  /* IFLA_NEW_IFINDEX */
-	       + nla_total_size(1)  /* IFLA_PROTO_DOWN */
+	       + rtnl_proto_down_size(dev)  /* proto down */
 	       + nla_total_size(4)  /* IFLA_TARGET_NETNSID */
 	       + nla_total_size(4)  /* IFLA_CARRIER_UP_COUNT */
 	       + nla_total_size(4)  /* IFLA_CARRIER_DOWN_COUNT */
@@ -1658,6 +1668,35 @@ nest_cancel:
 	return ret;
 }
 
+static int rtnl_fill_proto_down(struct sk_buff *skb,
+				const struct net_device *dev)
+{
+	struct nlattr *pr;
+	u32 preason;
+
+	if (nla_put_u8(skb, IFLA_PROTO_DOWN, dev->proto_down))
+		goto nla_put_failure;
+
+	preason = dev->proto_down_reason;
+	if (!preason)
+		return 0;
+
+	pr = nla_nest_start(skb, IFLA_PROTO_DOWN_REASON);
+	if (!pr)
+		return -EMSGSIZE;
+
+	if (nla_put_u32(skb, IFLA_PROTO_DOWN_REASON_VALUE, preason)) {
+		nla_nest_cancel(skb, pr);
+		goto nla_put_failure;
+	}
+
+	nla_nest_end(skb, pr);
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
 static int rtnl_fill_ifinfo(struct sk_buff *skb,
 			    struct net_device *dev, struct net *src_net,
 			    int type, u32 pid, u32 seq, u32 change,
@@ -1708,13 +1747,15 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
 	    nla_put_u32(skb, IFLA_CARRIER_CHANGES,
 			atomic_read(&dev->carrier_up_count) +
 			atomic_read(&dev->carrier_down_count)) ||
-	    nla_put_u8(skb, IFLA_PROTO_DOWN, dev->proto_down) ||
 	    nla_put_u32(skb, IFLA_CARRIER_UP_COUNT,
 			atomic_read(&dev->carrier_up_count)) ||
 	    nla_put_u32(skb, IFLA_CARRIER_DOWN_COUNT,
 			atomic_read(&dev->carrier_down_count)))
 		goto nla_put_failure;
 
+	if (rtnl_fill_proto_down(skb, dev))
+		goto nla_put_failure;
+
 	if (event != IFLA_EVENT_NONE) {
 		if (nla_put_u32(skb, IFLA_EVENT, event))
 			goto nla_put_failure;
@@ -1834,6 +1875,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
 	[IFLA_ALT_IFNAME]	= { .type = NLA_STRING,
 				    .len = ALTIFNAMSIZ - 1 },
 	[IFLA_PERM_ADDRESS]	= { .type = NLA_REJECT },
+	[IFLA_PROTO_DOWN_REASON] = { .type = NLA_NESTED },
 };
 
 static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
@@ -2483,6 +2525,67 @@ static int do_set_master(struct net_device *dev, int ifindex,
 	return 0;
 }
 
+static const struct nla_policy ifla_proto_down_reason_policy[IFLA_PROTO_DOWN_REASON_VALUE + 1] = {
+	[IFLA_PROTO_DOWN_REASON_MASK]	= { .type = NLA_U32 },
+	[IFLA_PROTO_DOWN_REASON_VALUE]	= { .type = NLA_U32 },
+};
+
+static int do_set_proto_down(struct net_device *dev,
+			     struct nlattr *nl_proto_down,
+			     struct nlattr *nl_proto_down_reason,
+			     struct netlink_ext_ack *extack)
+{
+	struct nlattr *pdreason[IFLA_PROTO_DOWN_REASON_MAX + 1];
+	const struct net_device_ops *ops = dev->netdev_ops;
+	unsigned long mask = 0;
+	u32 value;
+	bool proto_down;
+	int err;
+
+	if (!ops->ndo_change_proto_down) {
+		NL_SET_ERR_MSG(extack,  "Protodown not supported by device");
+		return -EOPNOTSUPP;
+	}
+
+	if (nl_proto_down_reason) {
+		err = nla_parse_nested_deprecated(pdreason,
+						  IFLA_PROTO_DOWN_REASON_MAX,
+						  nl_proto_down_reason,
+						  ifla_proto_down_reason_policy,
+						  NULL);
+		if (err < 0)
+			return err;
+
+		if (!pdreason[IFLA_PROTO_DOWN_REASON_VALUE]) {
+			NL_SET_ERR_MSG(extack, "Invalid protodown reason value");
+			return -EINVAL;
+		}
+
+		value = nla_get_u32(pdreason[IFLA_PROTO_DOWN_REASON_VALUE]);
+
+		if (pdreason[IFLA_PROTO_DOWN_REASON_MASK])
+			mask = nla_get_u32(pdreason[IFLA_PROTO_DOWN_REASON_MASK]);
+
+		dev_change_proto_down_reason(dev, mask, value);
+	}
+
+	if (nl_proto_down) {
+		proto_down = nla_get_u8(nl_proto_down);
+
+		/* Dont turn off protodown if there are active reasons */
+		if (!proto_down && dev->proto_down_reason) {
+			NL_SET_ERR_MSG(extack, "Cannot clear protodown, active reasons");
+			return -EBUSY;
+		}
+		err = dev_change_proto_down(dev,
+					    proto_down);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 #define DO_SETLINK_MODIFIED	0x01
 /* notify flag means notify + modified. */
 #define DO_SETLINK_NOTIFY	0x03
@@ -2771,9 +2874,9 @@ static int do_setlink(const struct sk_buff *skb,
 	}
 	err = 0;
 
-	if (tb[IFLA_PROTO_DOWN]) {
-		err = dev_change_proto_down(dev,
-					    nla_get_u8(tb[IFLA_PROTO_DOWN]));
+	if (tb[IFLA_PROTO_DOWN] || tb[IFLA_PROTO_DOWN_REASON]) {
+		err = do_set_proto_down(dev, tb[IFLA_PROTO_DOWN],
+					tb[IFLA_PROTO_DOWN_REASON], extack);
 		if (err)
 			goto errout;
 		status |= DO_SETLINK_NOTIFY;