net: Add napi_struct parameter irq_suspend_timeout

Add a per-NAPI IRQ suspension parameter, which can be get/set with
netdev-genl.

This patch doesn't change any behavior but prepares the code for other
changes in the following commits which use irq_suspend_timeout as a
timeout for IRQ suspension.

Signed-off-by: Martin Karsten <mkarsten@uwaterloo.ca>
Co-developed-by: Joe Damato <jdamato@fastly.com>
Signed-off-by: Joe Damato <jdamato@fastly.com>
Tested-by: Joe Damato <jdamato@fastly.com>
Tested-by: Martin Karsten <mkarsten@uwaterloo.ca>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
Link: https://patch.msgid.link/20241109050245.191288-2-jdamato@fastly.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Documentation/netlink/specs/netdev.yaml

@@ -263,6 +263,11 @@ attribute-sets:
              the end of a NAPI cycle. This may add receive latency in exchange
              for reducing the number of frames processed by the network stack.
         type: uint
+      -
+        name: irq-suspend-timeout
+        doc: The timeout, in nanoseconds, of how long to suspend irq
+             processing, if event polling finds events
+        type: uint
   -
     name: queue
     attributes:
@@ -653,6 +658,7 @@ operations:
             - pid
             - defer-hard-irqs
             - gro-flush-timeout
+            - irq-suspend-timeout
       dump:
         request:
           attributes:
@@ -704,6 +710,7 @@ operations:
             - id
             - defer-hard-irqs
             - gro-flush-timeout
+            - irq-suspend-timeout
 
 kernel-family:
   headers: [ "linux/list.h"]

include/linux/netdevice.h

@@ -348,6 +348,7 @@ struct gro_list {
  */
 struct napi_config {
 	u64 gro_flush_timeout;
+	u64 irq_suspend_timeout;
 	u32 defer_hard_irqs;
 	unsigned int napi_id;
 };
@@ -384,6 +385,7 @@ struct napi_struct {
 	struct hrtimer		timer;
 	struct task_struct	*thread;
 	unsigned long		gro_flush_timeout;
+	unsigned long		irq_suspend_timeout;
 	u32			defer_hard_irqs;
 	/* control-path-only fields follow */
 	struct list_head	dev_list;

include/uapi/linux/netdev.h

@@ -124,6 +124,7 @@ enum {
 	NETDEV_A_NAPI_PID,
 	NETDEV_A_NAPI_DEFER_HARD_IRQS,
 	NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT,
+	NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT,
 
 	__NETDEV_A_NAPI_MAX,
 	NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1)

net/core/dev.c

@@ -6666,6 +6666,7 @@ static void napi_restore_config(struct napi_struct *n)
 {
 	n->defer_hard_irqs = n->config->defer_hard_irqs;
 	n->gro_flush_timeout = n->config->gro_flush_timeout;
+	n->irq_suspend_timeout = n->config->irq_suspend_timeout;
 	/* a NAPI ID might be stored in the config, if so use it. if not, use
 	 * napi_hash_add to generate one for us. It will be saved to the config
 	 * in napi_disable.
@@ -6680,6 +6681,7 @@ static void napi_save_config(struct napi_struct *n)
 {
 	n->config->defer_hard_irqs = n->defer_hard_irqs;
 	n->config->gro_flush_timeout = n->gro_flush_timeout;
+	n->config->irq_suspend_timeout = n->irq_suspend_timeout;
 	n->config->napi_id = n->napi_id;
 	napi_hash_del(n);
 }

net/core/dev.h

@@ -236,6 +236,31 @@ static inline void netdev_set_gro_flush_timeout(struct net_device *netdev,
 		netdev->napi_config[i].gro_flush_timeout = timeout;
 }
 
+/**
+ * napi_get_irq_suspend_timeout - get the irq_suspend_timeout
+ * @n: napi struct to get the irq_suspend_timeout from
+ *
+ * Return: the per-NAPI value of the irq_suspend_timeout field.
+ */
+static inline unsigned long
+napi_get_irq_suspend_timeout(const struct napi_struct *n)
+{
+	return READ_ONCE(n->irq_suspend_timeout);
+}
+
+/**
+ * napi_set_irq_suspend_timeout - set the irq_suspend_timeout for a napi
+ * @n: napi struct to set the irq_suspend_timeout
+ * @timeout: timeout value to set
+ *
+ * napi_set_irq_suspend_timeout sets the per-NAPI irq_suspend_timeout
+ */
+static inline void napi_set_irq_suspend_timeout(struct napi_struct *n,
+						unsigned long timeout)
+{
+	WRITE_ONCE(n->irq_suspend_timeout, timeout);
+}
+
 int rps_cpumask_housekeeping(struct cpumask *mask);
 
 #if defined(CONFIG_DEBUG_NET) && defined(CONFIG_BPF_SYSCALL)

net/core/netdev-genl-gen.c

@@ -92,10 +92,11 @@ 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_GRO_FLUSH_TIMEOUT + 1] = {
+static const struct nla_policy netdev_napi_set_nl_policy[NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT + 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, },
 };
 
 /* Ops table for netdev */
@@ -186,7 +187,7 @@ 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_GRO_FLUSH_TIMEOUT,
+		.maxattr	= NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT,
 		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
 	},
 };

net/core/netdev-genl.c

@@ -161,6 +161,7 @@ static int
 netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi,
 			const struct genl_info *info)
 {
+	unsigned long irq_suspend_timeout;
 	unsigned long gro_flush_timeout;
 	u32 napi_defer_hard_irqs;
 	void *hdr;
@@ -196,6 +197,11 @@ netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi,
 			napi_defer_hard_irqs))
 		goto nla_put_failure;
 
+	irq_suspend_timeout = napi_get_irq_suspend_timeout(napi);
+	if (nla_put_uint(rsp, NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT,
+			 irq_suspend_timeout))
+		goto nla_put_failure;
+
 	gro_flush_timeout = napi_get_gro_flush_timeout(napi);
 	if (nla_put_uint(rsp, NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT,
 			 gro_flush_timeout))
@@ -306,6 +312,7 @@ int netdev_nl_napi_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 static int
 netdev_nl_napi_set_config(struct napi_struct *napi, struct genl_info *info)
 {
+	u64 irq_suspend_timeout = 0;
 	u64 gro_flush_timeout = 0;
 	u32 defer = 0;
 
@@ -314,6 +321,11 @@ netdev_nl_napi_set_config(struct napi_struct *napi, struct genl_info *info)
 		napi_set_defer_hard_irqs(napi, defer);
 	}
 
+	if (info->attrs[NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT]) {
+		irq_suspend_timeout = nla_get_uint(info->attrs[NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT]);
+		napi_set_irq_suspend_timeout(napi, irq_suspend_timeout);
+	}
+
 	if (info->attrs[NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT]) {
 		gro_flush_timeout = nla_get_uint(info->attrs[NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT]);
 		napi_set_gro_flush_timeout(napi, gro_flush_timeout);

tools/include/uapi/linux/netdev.h

@@ -124,6 +124,7 @@ enum {
 	NETDEV_A_NAPI_PID,
 	NETDEV_A_NAPI_DEFER_HARD_IRQS,
 	NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT,
+	NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT,
 
 	__NETDEV_A_NAPI_MAX,
 	NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1)