Add support to set NAPI threaded for individual NAPI

A net device has a threaded sysctl that can be used to enable threaded
NAPI polling on all of the NAPI contexts under that device. Allow
enabling threaded NAPI polling at individual NAPI level using netlink.

Extend the netlink operation `napi-set` and allow setting the threaded
attribute of a NAPI. This will enable the threaded polling on a NAPI
context.

Add a test in `nl_netdev.py` that verifies various cases of threaded
NAPI being set at NAPI and at device level.

Tested
 ./tools/testing/selftests/net/nl_netdev.py
 TAP version 13
 1..7
 ok 1 nl_netdev.empty_check
 ok 2 nl_netdev.lo_check
 ok 3 nl_netdev.page_pool_check
 ok 4 nl_netdev.napi_list_check
 ok 5 nl_netdev.dev_set_threaded
 ok 6 nl_netdev.napi_set_threaded
 ok 7 nl_netdev.nsim_rxq_reset_down
 # Totals: pass:7 fail:0 xfail:0 xpass:0 skip:0 error:0

Signed-off-by: Samiullah Khawaja <skhawaja@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250710211203.3979655-1-skhawaja@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

4 files changed, 51 insertions, 5 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 19ddc3e6990a..621a639aeba1 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6961,6 +6961,31 @@ static void napi_stop_kthread(struct napi_struct *napi)
 	napi->thread = NULL;
 }
 
+int napi_set_threaded(struct napi_struct *napi, bool threaded)
+{
+	if (threaded) {
+		if (!napi->thread) {
+			int err = napi_kthread_create(napi);
+
+			if (err)
+				return err;
+		}
+	}
+
+	if (napi->config)
+		napi->config->threaded = threaded;
+
+	if (!threaded && napi->thread) {
+		napi_stop_kthread(napi);
+	} else {
+		/* Make sure kthread is created before THREADED bit is set. */
+		smp_mb__before_atomic();
+		assign_bit(NAPI_STATE_THREADED, &napi->state, threaded);
+	}
+
+	return 0;
+}
+
 int dev_set_threaded(struct net_device *dev, bool threaded)
 {
 	struct napi_struct *napi;
@@ -6968,9 +6993,6 @@ int dev_set_threaded(struct net_device *dev, bool threaded)
 
 	netdev_assert_locked_or_invisible(dev);
 
-	if (dev->threaded == threaded)
-		return 0;
-
 	if (threaded) {
 		list_for_each_entry(napi, &dev->napi_list, dev_list) {
 			if (!napi->thread) {
@@ -7221,6 +7243,8 @@ static void napi_restore_config(struct napi_struct *n)
 		napi_hash_add(n);
 		n->config->napi_id = n->napi_id;
 	}
+
+	WARN_ON_ONCE(napi_set_threaded(n, n->config->threaded));
 }
 
 static void napi_save_config(struct napi_struct *n)
diff --git a/net/core/dev.h b/net/core/dev.h
index e93f36b7ddf3..a603387fb566 100644
--- a/net/core/dev.h
+++ b/net/core/dev.h
@@ -315,6 +315,13 @@ static inline void napi_set_irq_suspend_timeout(struct napi_struct *n,
 	WRITE_ONCE(n->irq_suspend_timeout, timeout);
 }
 
+static inline bool napi_get_threaded(struct napi_struct *n)
+{
+	return test_bit(NAPI_STATE_THREADED, &n->state);
+}
+
+int napi_set_threaded(struct napi_struct *n, bool threaded);
+
 int rps_cpumask_housekeeping(struct cpumask *mask);
 
 #if defined(CONFIG_DEBUG_NET) && defined(CONFIG_BPF_SYSCALL)
diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c
index 4fc44587f493..0994bd68a7e6 100644
--- a/net/core/netdev-genl-gen.c
+++ b/net/core/netdev-genl-gen.c
@@ -92,11 +92,12 @@ static const struct nla_policy netdev_bind_rx_nl_policy[NETDEV_A_DMABUF_FD + 1]
 };
 
 /* NETDEV_CMD_NAPI_SET - do */
-static const struct nla_policy netdev_napi_set_nl_policy[NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT + 1] = {
+static const struct nla_policy netdev_napi_set_nl_policy[NETDEV_A_NAPI_THREADED + 1] = {
 	[NETDEV_A_NAPI_ID] = { .type = NLA_U32, },
 	[NETDEV_A_NAPI_DEFER_HARD_IRQS] = NLA_POLICY_FULL_RANGE(NLA_U32, &netdev_a_napi_defer_hard_irqs_range),
 	[NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT] = { .type = NLA_UINT, },
 	[NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT] = { .type = NLA_UINT, },
+	[NETDEV_A_NAPI_THREADED] = NLA_POLICY_MAX(NLA_UINT, 1),
 };
 
 /* NETDEV_CMD_BIND_TX - do */
@@ -193,7 +194,7 @@ static const struct genl_split_ops netdev_nl_ops[] = {
 		.cmd		= NETDEV_CMD_NAPI_SET,
 		.doit		= netdev_nl_napi_set_doit,
 		.policy		= netdev_napi_set_nl_policy,
-		.maxattr	= NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT,
+		.maxattr	= NETDEV_A_NAPI_THREADED,
 		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
 	},
 	{
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 2afa7b2141aa..5875df372415 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -184,6 +184,10 @@ netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi,
 	if (napi->irq >= 0 && nla_put_u32(rsp, NETDEV_A_NAPI_IRQ, napi->irq))
 		goto nla_put_failure;
 
+	if (nla_put_uint(rsp, NETDEV_A_NAPI_THREADED,
+			 napi_get_threaded(napi)))
+		goto nla_put_failure;
+
 	if (napi->thread) {
 		pid = task_pid_nr(napi->thread);
 		if (nla_put_u32(rsp, NETDEV_A_NAPI_PID, pid))
@@ -322,8 +326,18 @@ netdev_nl_napi_set_config(struct napi_struct *napi, struct genl_info *info)
 {
 	u64 irq_suspend_timeout = 0;
 	u64 gro_flush_timeout = 0;
+	u8 threaded = 0;
 	u32 defer = 0;
 
+	if (info->attrs[NETDEV_A_NAPI_THREADED]) {
+		int ret;
+
+		threaded = nla_get_uint(info->attrs[NETDEV_A_NAPI_THREADED]);
+		ret = napi_set_threaded(napi, !!threaded);
+		if (ret)
+			return ret;
+	}
+
 	if (info->attrs[NETDEV_A_NAPI_DEFER_HARD_IRQS]) {
 		defer = nla_get_u32(info->attrs[NETDEV_A_NAPI_DEFER_HARD_IRQS]);
 		napi_set_defer_hard_irqs(napi, defer);