net: bridge: add stp_mode attribute for STP mode selection

The bridge-stp usermode helper is currently restricted to the initial
network namespace, preventing userspace STP daemons (e.g. mstpd) from
operating on bridges in other network namespaces. Since commit
ff62198553 ("bridge: Only call /sbin/bridge-stp for the initial
network namespace"), bridges in non-init namespaces silently fall
back to kernel STP with no way to use userspace STP.

Add a new bridge attribute IFLA_BR_STP_MODE that allows explicit
per-bridge control over STP mode selection:

  BR_STP_MODE_AUTO (default) - Existing behavior: invoke the
    /sbin/bridge-stp helper in init_net only; fall back to kernel STP
    if it fails or in non-init namespaces.

  BR_STP_MODE_USER - Directly enable userspace STP (BR_USER_STP)
    without invoking the helper. Works in any network namespace.
    Userspace is responsible for ensuring an STP daemon manages the
    bridge.

  BR_STP_MODE_KERNEL - Directly enable kernel STP (BR_KERNEL_STP)
    without invoking the helper.

The mode can only be changed while STP is disabled, or set to the
same value (-EBUSY otherwise). IFLA_BR_STP_MODE is processed before
IFLA_BR_STP_STATE in br_changelink(), so both can be set atomically
in a single netlink message. The mode can also be changed in the
same message that disables STP.

The stp_mode struct field is u8 since all possible values fit, while
NLA_U32 is used for the netlink attribute since it occupies the same
space in the netlink message as NLA_U8.

A new stp_helper_active boolean tracks whether the /sbin/bridge-stp
helper was invoked during br_stp_start(), so that br_stp_stop() only
calls the helper for stop when it was called for start. This avoids
calling the helper asymmetrically when stp_mode changes between
start and stop.

Suggested-by: Ido Schimmel <idosch@nvidia.com>
Assisted-by: Claude:claude-opus-4-6
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Acked-by: Nikolay Aleksandrov <nikolay@nvidia.com>
Signed-off-by: Andy Roulin <aroulin@nvidia.com>
Link: https://patch.msgid.link/20260405205224.3163000-2-aroulin@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Documentation/netlink/specs/rt-link.yaml

@@ -840,6 +840,14 @@ definitions:
     entries:
       - p2p
       - mp
+  -
+    name: br-stp-mode
+    type: enum
+    enum-name: br-stp-mode
+    entries:
+      - auto
+      - user
+      - kernel
 
 attribute-sets:
   -
@@ -1550,6 +1558,10 @@ attribute-sets:
       -
         name: fdb-max-learned
         type: u32
+      -
+        name: stp-mode
+        type: u32
+        enum: br-stp-mode
   -
     name: linkinfo-brport-attrs
     name-prefix: ifla-brport-

include/uapi/linux/if_link.h

@@ -744,6 +744,11 @@ enum in6_addr_gen_mode {
  * @IFLA_BR_FDB_MAX_LEARNED
  *   Set the number of max dynamically learned FDB entries for the current
  *   bridge.
+ *
+ * @IFLA_BR_STP_MODE
+ *   Set the STP mode for the bridge, which controls how the bridge
+ *   selects between userspace and kernel STP. The valid values are
+ *   documented below in the ``BR_STP_MODE_*`` constants.
  */
 enum {
 	IFLA_BR_UNSPEC,
@@ -796,11 +801,45 @@ enum {
 	IFLA_BR_MCAST_QUERIER_STATE,
 	IFLA_BR_FDB_N_LEARNED,
 	IFLA_BR_FDB_MAX_LEARNED,
+	IFLA_BR_STP_MODE,
 	__IFLA_BR_MAX,
 };
 
 #define IFLA_BR_MAX	(__IFLA_BR_MAX - 1)
 
+/**
+ * DOC: Bridge STP mode values
+ *
+ * @BR_STP_MODE_AUTO
+ *   Default. The kernel invokes the ``/sbin/bridge-stp`` helper to hand
+ *   the bridge to a userspace STP daemon (e.g. mstpd). Only attempted in
+ *   the initial network namespace; in other namespaces this falls back to
+ *   kernel STP.
+ *
+ * @BR_STP_MODE_USER
+ *   Directly enable userspace STP (``BR_USER_STP``) without invoking the
+ *   ``/sbin/bridge-stp`` helper. Works in any network namespace.
+ *   Userspace is responsible for ensuring an STP daemon manages the
+ *   bridge.
+ *
+ * @BR_STP_MODE_KERNEL
+ *   Directly enable kernel STP (``BR_KERNEL_STP``) without invoking the
+ *   helper.
+ *
+ * The mode controls how the bridge selects between userspace and kernel
+ * STP when STP is enabled via ``IFLA_BR_STP_STATE``. It can only be
+ * changed while STP is disabled (``IFLA_BR_STP_STATE`` == 0), returns
+ * ``-EBUSY`` otherwise. The default value is ``BR_STP_MODE_AUTO``.
+ */
+enum br_stp_mode {
+	BR_STP_MODE_AUTO,
+	BR_STP_MODE_USER,
+	BR_STP_MODE_KERNEL,
+	__BR_STP_MODE_MAX
+};
+
+#define BR_STP_MODE_MAX (__BR_STP_MODE_MAX - 1)
+
 struct ifla_bridge_id {
 	__u8	prio[2];
 	__u8	addr[6]; /* ETH_ALEN */

net/bridge/br_device.c

@@ -518,6 +518,7 @@ void br_dev_setup(struct net_device *dev)
 	ether_addr_copy(br->group_addr, eth_stp_addr);
 
 	br->stp_enabled = BR_NO_STP;
+	br->stp_mode = BR_STP_MODE_AUTO;
 	br->group_fwd_mask = BR_GROUPFWD_DEFAULT;
 	br->group_fwd_mask_required = BR_GROUPFWD_DEFAULT;
 

net/bridge/br_netlink.c

@@ -1270,6 +1270,9 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = {
 		NLA_POLICY_EXACT_LEN(sizeof(struct br_boolopt_multi)),
 	[IFLA_BR_FDB_N_LEARNED] = { .type = NLA_REJECT },
 	[IFLA_BR_FDB_MAX_LEARNED] = { .type = NLA_U32 },
+	[IFLA_BR_STP_MODE] = NLA_POLICY_RANGE(NLA_U32,
+					      BR_STP_MODE_AUTO,
+					      BR_STP_MODE_MAX),
 };
 
 static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
@@ -1306,6 +1309,23 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
 			return err;
 	}
 
+	if (data[IFLA_BR_STP_MODE]) {
+		u32 mode = nla_get_u32(data[IFLA_BR_STP_MODE]);
+
+		if (mode != br->stp_mode) {
+			bool stp_off = br->stp_enabled == BR_NO_STP ||
+				       (data[IFLA_BR_STP_STATE] &&
+					!nla_get_u32(data[IFLA_BR_STP_STATE]));
+
+			if (!stp_off) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "Can't change STP mode while STP is enabled");
+				return -EBUSY;
+			}
+		}
+		br->stp_mode = mode;
+	}
+
 	if (data[IFLA_BR_STP_STATE]) {
 		u32 stp_enabled = nla_get_u32(data[IFLA_BR_STP_STATE]);
 
@@ -1634,6 +1654,7 @@ static size_t br_get_size(const struct net_device *brdev)
 	       nla_total_size(sizeof(u8)) +     /* IFLA_BR_NF_CALL_ARPTABLES */
 #endif
 	       nla_total_size(sizeof(struct br_boolopt_multi)) + /* IFLA_BR_MULTI_BOOLOPT */
+	       nla_total_size(sizeof(u32)) +    /* IFLA_BR_STP_MODE */
 	       0;
 }
 
@@ -1686,7 +1707,8 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev)
 	    nla_put(skb, IFLA_BR_MULTI_BOOLOPT, sizeof(bm), &bm) ||
 	    nla_put_u32(skb, IFLA_BR_FDB_N_LEARNED,
 			atomic_read(&br->fdb_n_learned)) ||
-	    nla_put_u32(skb, IFLA_BR_FDB_MAX_LEARNED, br->fdb_max_learned))
+	    nla_put_u32(skb, IFLA_BR_FDB_MAX_LEARNED, br->fdb_max_learned) ||
+	    nla_put_u32(skb, IFLA_BR_STP_MODE, br->stp_mode))
 		return -EMSGSIZE;
 
 #ifdef CONFIG_BRIDGE_VLAN_FILTERING

net/bridge/br_private.h

@@ -523,6 +523,8 @@ struct net_bridge {
 	unsigned char			topology_change;
 	unsigned char			topology_change_detected;
 	u16				root_port;
+	u8				stp_mode;
+	bool				stp_helper_active;
 	unsigned long			max_age;
 	unsigned long			hello_time;
 	unsigned long			forward_delay;

net/bridge/br_stp_if.c

@@ -149,7 +149,9 @@ static void br_stp_start(struct net_bridge *br)
 {
 	int err = -ENOENT;
 
-	if (net_eq(dev_net(br->dev), &init_net))
+	/* AUTO mode: try bridge-stp helper in init_net only */
+	if (br->stp_mode == BR_STP_MODE_AUTO &&
+	    net_eq(dev_net(br->dev), &init_net))
 		err = br_stp_call_user(br, "start");
 
 	if (err && err != -ENOENT)
@@ -162,8 +164,9 @@ static void br_stp_start(struct net_bridge *br)
 	else if (br->bridge_forward_delay > BR_MAX_FORWARD_DELAY)
 		__br_set_forward_delay(br, BR_MAX_FORWARD_DELAY);
 
-	if (!err) {
+	if (br->stp_mode == BR_STP_MODE_USER || !err) {
 		br->stp_enabled = BR_USER_STP;
+		br->stp_helper_active = !err;
 		br_debug(br, "userspace STP started\n");
 	} else {
 		br->stp_enabled = BR_KERNEL_STP;
@@ -180,12 +183,14 @@ static void br_stp_start(struct net_bridge *br)
 
 static void br_stp_stop(struct net_bridge *br)
 {
-	int err;
-
 	if (br->stp_enabled == BR_USER_STP) {
-		err = br_stp_call_user(br, "stop");
-		if (err)
-			br_err(br, "failed to stop userspace STP (%d)\n", err);
+		if (br->stp_helper_active) {
+			int err = br_stp_call_user(br, "stop");
+
+			if (err)
+				br_err(br, "failed to stop userspace STP (%d)\n", err);
+			br->stp_helper_active = false;
+		}
 
 		/* To start timers on any ports left in blocking */
 		spin_lock_bh(&br->lock);