net: Extend NAPI threaded polling to allow kthread based busy polling

Add a new state NAPI_STATE_THREADED_BUSY_POLL to the NAPI state enum to
enable and disable threaded busy polling.

When threaded busy polling is enabled for a NAPI, enable
NAPI_STATE_THREADED also.

When the threaded NAPI is scheduled, set NAPI_STATE_IN_BUSY_POLL to
signal napi_complete_done not to rearm interrupts.

Whenever NAPI_STATE_THREADED_BUSY_POLL is unset, the
NAPI_STATE_IN_BUSY_POLL will be unset, napi_complete_done unsets the
NAPI_STATE_SCHED_THREADED bit also, which in turn will make the kthread
go to sleep.

Signed-off-by: Samiullah Khawaja <skhawaja@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Acked-by: Martin Karsten <mkarsten@uwaterloo.ca>
Tested-by: Martin Karsten <mkarsten@uwaterloo.ca>
Link: https://patch.msgid.link/20251028203007.575686-2-skhawaja@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Documentation/netlink/specs/netdev.yaml

@@ -88,7 +88,7 @@ definitions:
   -
     name: napi-threaded
     type: enum
-    entries: [disabled, enabled]
+    entries: [disabled, enabled, busy-poll]
 
 attribute-sets:
   -
@@ -291,7 +291,8 @@ attribute-sets:
         name: threaded
         doc: Whether the NAPI is configured to operate in threaded polling
              mode. If this is set to enabled then the NAPI context operates
-             in threaded polling mode.
+             in threaded polling mode. If this is set to busy-poll, then the
+             threaded polling mode also busy polls.
         type: u32
         enum: napi-threaded
   -

Documentation/networking/napi.rst

@@ -263,7 +263,9 @@ are not well known).
 Busy polling is enabled by either setting ``SO_BUSY_POLL`` on
 selected sockets or using the global ``net.core.busy_poll`` and
 ``net.core.busy_read`` sysctls. An io_uring API for NAPI busy polling
-also exists.
+also exists. Threaded polling of NAPI also has a mode to busy poll for
+packets (:ref:`threaded busy polling<threaded_busy_poll>`) using the NAPI
+processing kthread.
 
 epoll-based busy polling
 ------------------------
@@ -426,6 +428,52 @@ Therefore, setting ``gro_flush_timeout`` and ``napi_defer_hard_irqs`` is
 the recommended usage, because otherwise setting ``irq-suspend-timeout``
 might not have any discernible effect.
 
+.. _threaded_busy_poll:
+
+Threaded NAPI busy polling
+--------------------------
+
+Threaded NAPI busy polling extends threaded NAPI and adds support to do
+continuous busy polling of the NAPI. This can be useful for forwarding or
+AF_XDP applications.
+
+Threaded NAPI busy polling can be enabled on per NIC queue basis using Netlink.
+
+For example, using the following script:
+
+.. code-block:: bash
+
+  $ ynl --family netdev --do napi-set \
+            --json='{"id": 66, "threaded": "busy-poll"}'
+
+The kernel will create a kthread that busy polls on this NAPI.
+
+The user may elect to set the CPU affinity of this kthread to an unused CPU
+core to improve how often the NAPI is polled at the expense of wasted CPU
+cycles. Note that this will keep the CPU core busy with 100% usage.
+
+Once threaded busy polling is enabled for a NAPI, PID of the kthread can be
+retrieved using Netlink so the affinity of the kthread can be set up.
+
+For example, the following script can be used to fetch the PID:
+
+.. code-block:: bash
+
+  $ ynl --family netdev --do napi-get --json='{"id": 66}'
+
+This will output something like following, the pid `258` is the PID of the
+kthread that is polling this NAPI.
+
+.. code-block:: bash
+
+  $ {'defer-hard-irqs': 0,
+     'gro-flush-timeout': 0,
+     'id': 66,
+     'ifindex': 2,
+     'irq-suspend-timeout': 0,
+     'pid': 258,
+     'threaded': 'busy-poll'}
+
 .. _threaded:
 
 Threaded NAPI

include/linux/netdevice.h

@@ -423,11 +423,12 @@ enum {
 	NAPI_STATE_NPSVC,		/* Netpoll - don't dequeue from poll_list */
 	NAPI_STATE_LISTED,		/* NAPI added to system lists */
 	NAPI_STATE_NO_BUSY_POLL,	/* Do not add in napi_hash, no busy polling */
-	NAPI_STATE_IN_BUSY_POLL,	/* sk_busy_loop() owns this NAPI */
+	NAPI_STATE_IN_BUSY_POLL,	/* Do not rearm NAPI interrupt */
 	NAPI_STATE_PREFER_BUSY_POLL,	/* prefer busy-polling over softirq processing*/
 	NAPI_STATE_THREADED,		/* The poll is performed inside its own thread*/
 	NAPI_STATE_SCHED_THREADED,	/* Napi is currently scheduled in threaded mode */
 	NAPI_STATE_HAS_NOTIFIER,	/* Napi has an IRQ notifier */
+	NAPI_STATE_THREADED_BUSY_POLL,	/* The threaded NAPI poller will busy poll */
 };
 
 enum {
@@ -442,6 +443,7 @@ enum {
 	NAPIF_STATE_THREADED		= BIT(NAPI_STATE_THREADED),
 	NAPIF_STATE_SCHED_THREADED	= BIT(NAPI_STATE_SCHED_THREADED),
 	NAPIF_STATE_HAS_NOTIFIER	= BIT(NAPI_STATE_HAS_NOTIFIER),
+	NAPIF_STATE_THREADED_BUSY_POLL	= BIT(NAPI_STATE_THREADED_BUSY_POLL),
 };
 
 enum gro_result {

include/uapi/linux/netdev.h

@@ -80,6 +80,7 @@ enum netdev_qstats_scope {
 enum netdev_napi_threaded {
 	NETDEV_NAPI_THREADED_DISABLED,
 	NETDEV_NAPI_THREADED_ENABLED,
+	NETDEV_NAPI_THREADED_BUSY_POLL,
 };
 
 enum {

net/core/dev.c

@@ -7089,7 +7089,8 @@ static void napi_stop_kthread(struct napi_struct *napi)
 		 */
 		if ((val & NAPIF_STATE_SCHED_THREADED) ||
 		    !(val & NAPIF_STATE_SCHED)) {
-			new = val & (~NAPIF_STATE_THREADED);
+			new = val & (~(NAPIF_STATE_THREADED |
+				       NAPIF_STATE_THREADED_BUSY_POLL));
 		} else {
 			msleep(20);
 			continue;
@@ -7113,6 +7114,16 @@ static void napi_stop_kthread(struct napi_struct *napi)
 	napi->thread = NULL;
 }
 
+static void napi_set_threaded_state(struct napi_struct *napi,
+				    enum netdev_napi_threaded threaded_mode)
+{
+	bool threaded = threaded_mode != NETDEV_NAPI_THREADED_DISABLED;
+	bool busy_poll = threaded_mode == NETDEV_NAPI_THREADED_BUSY_POLL;
+
+	assign_bit(NAPI_STATE_THREADED, &napi->state, threaded);
+	assign_bit(NAPI_STATE_THREADED_BUSY_POLL, &napi->state, busy_poll);
+}
+
 int napi_set_threaded(struct napi_struct *napi,
 		      enum netdev_napi_threaded threaded)
 {
@@ -7139,7 +7150,7 @@ int napi_set_threaded(struct napi_struct *napi,
 	} else {
 		/* Make sure kthread is created before THREADED bit is set. */
 		smp_mb__before_atomic();
-		assign_bit(NAPI_STATE_THREADED, &napi->state, threaded);
+		napi_set_threaded_state(napi, threaded);
 	}
 
 	return 0;
@@ -7531,7 +7542,9 @@ void napi_disable_locked(struct napi_struct *n)
 		}
 
 		new = val | NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC;
-		new &= ~(NAPIF_STATE_THREADED | NAPIF_STATE_PREFER_BUSY_POLL);
+		new &= ~(NAPIF_STATE_THREADED |
+			 NAPIF_STATE_THREADED_BUSY_POLL |
+			 NAPIF_STATE_PREFER_BUSY_POLL);
 	} while (!try_cmpxchg(&n->state, &val, new));
 
 	hrtimer_cancel(&n->timer);
@@ -7743,7 +7756,7 @@ static int napi_thread_wait(struct napi_struct *napi)
 	return -1;
 }
 
-static void napi_threaded_poll_loop(struct napi_struct *napi)
+static void napi_threaded_poll_loop(struct napi_struct *napi, bool busy_poll)
 {
 	struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
 	struct softnet_data *sd;
@@ -7772,22 +7785,47 @@ static void napi_threaded_poll_loop(struct napi_struct *napi)
 		}
 		skb_defer_free_flush();
 		bpf_net_ctx_clear(bpf_net_ctx);
+
+		/* When busy poll is enabled, the old packets are not flushed in
+		 * napi_complete_done. So flush them here.
+		 */
+		if (busy_poll)
+			gro_flush_normal(&napi->gro, HZ >= 1000);
 		local_bh_enable();
 
+		/* Call cond_resched here to avoid watchdog warnings. */
+		if (repoll || busy_poll) {
+			rcu_softirq_qs_periodic(last_qs);
+			cond_resched();
+		}
+
 		if (!repoll)
 			break;
-
-		rcu_softirq_qs_periodic(last_qs);
-		cond_resched();
 	}
 }
 
 static int napi_threaded_poll(void *data)
 {
 	struct napi_struct *napi = data;
+	bool want_busy_poll;
+	bool in_busy_poll;
+	unsigned long val;
 
-	while (!napi_thread_wait(napi))
+	while (!napi_thread_wait(napi)) {
-		napi_threaded_poll_loop(napi);
+		val = READ_ONCE(napi->state);
+
+		want_busy_poll = val & NAPIF_STATE_THREADED_BUSY_POLL;
+		in_busy_poll = val & NAPIF_STATE_IN_BUSY_POLL;
+
+		if (unlikely(val & NAPIF_STATE_DISABLE))
+			want_busy_poll = false;
+
+		if (want_busy_poll != in_busy_poll)
+			assign_bit(NAPI_STATE_IN_BUSY_POLL, &napi->state,
+				   want_busy_poll);
+
+		napi_threaded_poll_loop(napi, want_busy_poll);
+	}
 
 	return 0;
 }
@@ -13097,7 +13135,7 @@ static void run_backlog_napi(unsigned int cpu)
 {
 	struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu);
 
-	napi_threaded_poll_loop(&sd->backlog);
+	napi_threaded_poll_loop(&sd->backlog, false);
 }
 
 static void backlog_napi_setup(unsigned int cpu)

net/core/dev.h

@@ -317,6 +317,9 @@ static inline void napi_set_irq_suspend_timeout(struct napi_struct *n,
 
 static inline enum netdev_napi_threaded napi_get_threaded(struct napi_struct *n)
 {
+	if (test_bit(NAPI_STATE_THREADED_BUSY_POLL, &n->state))
+		return NETDEV_NAPI_THREADED_BUSY_POLL;
+
 	if (test_bit(NAPI_STATE_THREADED, &n->state))
 		return NETDEV_NAPI_THREADED_ENABLED;
 

net/core/netdev-genl-gen.c

@@ -97,7 +97,7 @@ static const struct nla_policy netdev_napi_set_nl_policy[NETDEV_A_NAPI_THREADED
 	[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_U32, 1),
+	[NETDEV_A_NAPI_THREADED] = NLA_POLICY_MAX(NLA_U32, 2),
 };
 
 /* NETDEV_CMD_BIND_TX - do */

tools/include/uapi/linux/netdev.h

@@ -80,6 +80,7 @@ enum netdev_qstats_scope {
 enum netdev_napi_threaded {
 	NETDEV_NAPI_THREADED_DISABLED,
 	NETDEV_NAPI_THREADED_ENABLED,
+	NETDEV_NAPI_THREADED_BUSY_POLL,
 };
 
 enum {