net: napi: Add napi_config

Add a persistent NAPI config area for NAPI configuration to the core.
Drivers opt-in to setting the persistent config for a NAPI by passing an
index when calling netif_napi_add_config.

napi_config is allocated in alloc_netdev_mqs, freed in free_netdev
(after the NAPIs are deleted).

Drivers which call netif_napi_add_config will have persistent per-NAPI
settings: NAPI IDs, gro_flush_timeout, and defer_hard_irq settings.

Per-NAPI settings are saved in napi_disable and restored in napi_enable.

Co-developed-by: Martin Karsten <mkarsten@uwaterloo.ca>
Signed-off-by: Martin Karsten <mkarsten@uwaterloo.ca>
Signed-off-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20241011184527.16393-6-jdamato@fastly.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 73 insertions, 7 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index e21ace3551d5..c682173a7642 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6505,6 +6505,23 @@ EXPORT_SYMBOL(napi_busy_loop);
 
 #endif /* CONFIG_NET_RX_BUSY_POLL */
 
+static void __napi_hash_add_with_id(struct napi_struct *napi,
+				    unsigned int napi_id)
+{
+	napi->napi_id = napi_id;
+	hlist_add_head_rcu(&napi->napi_hash_node,
+			   &napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]);
+}
+
+static void napi_hash_add_with_id(struct napi_struct *napi,
+				  unsigned int napi_id)
+{
+	spin_lock(&napi_hash_lock);
+	WARN_ON_ONCE(napi_by_id(napi_id));
+	__napi_hash_add_with_id(napi, napi_id);
+	spin_unlock(&napi_hash_lock);
+}
+
 static void napi_hash_add(struct napi_struct *napi)
 {
 	if (test_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state))
@@ -6517,10 +6534,8 @@ static void napi_hash_add(struct napi_struct *napi)
 		if (unlikely(++napi_gen_id < MIN_NAPI_ID))
 			napi_gen_id = MIN_NAPI_ID;
 	} while (napi_by_id(napi_gen_id));
-	napi->napi_id = napi_gen_id;
 
-	hlist_add_head_rcu(&napi->napi_hash_node,
-			   &napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]);
+	__napi_hash_add_with_id(napi, napi_gen_id);
 
 	spin_unlock(&napi_hash_lock);
 }
@@ -6643,6 +6658,28 @@ void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index,
 }
 EXPORT_SYMBOL(netif_queue_set_napi);
 
+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;
+	/* 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.
+	 */
+	if (n->config->napi_id)
+		napi_hash_add_with_id(n, n->config->napi_id);
+	else
+		napi_hash_add(n);
+}
+
+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->napi_id = n->napi_id;
+	napi_hash_del(n);
+}
+
 void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi,
 			   int (*poll)(struct napi_struct *, int), int weight)
 {
@@ -6653,8 +6690,6 @@ void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi,
 	INIT_HLIST_NODE(&napi->napi_hash_node);
 	hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
 	napi->timer.function = napi_watchdog;
-	napi_set_defer_hard_irqs(napi, READ_ONCE(dev->napi_defer_hard_irqs));
-	napi_set_gro_flush_timeout(napi, READ_ONCE(dev->gro_flush_timeout));
 	init_gro_hash(napi);
 	napi->skb = NULL;
 	INIT_LIST_HEAD(&napi->rx_list);
@@ -6672,7 +6707,13 @@ void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi,
 	set_bit(NAPI_STATE_SCHED, &napi->state);
 	set_bit(NAPI_STATE_NPSVC, &napi->state);
 	list_add_rcu(&napi->dev_list, &dev->napi_list);
-	napi_hash_add(napi);
+
+	/* default settings from sysfs are applied to all NAPIs. any per-NAPI
+	 * configuration will be loaded in napi_enable
+	 */
+	napi_set_defer_hard_irqs(napi, READ_ONCE(dev->napi_defer_hard_irqs));
+	napi_set_gro_flush_timeout(napi, READ_ONCE(dev->gro_flush_timeout));
+
 	napi_get_frags_check(napi);
 	/* Create kthread for this napi if dev->threaded is set.
 	 * Clear dev->threaded if kthread creation failed so that
@@ -6704,6 +6745,11 @@ void napi_disable(struct napi_struct *n)
 
 	hrtimer_cancel(&n->timer);
 
+	if (n->config)
+		napi_save_config(n);
+	else
+		napi_hash_del(n);
+
 	clear_bit(NAPI_STATE_DISABLE, &n->state);
 }
 EXPORT_SYMBOL(napi_disable);
@@ -6719,6 +6765,11 @@ void napi_enable(struct napi_struct *n)
 {
 	unsigned long new, val = READ_ONCE(n->state);
 
+	if (n->config)
+		napi_restore_config(n);
+	else
+		napi_hash_add(n);
+
 	do {
 		BUG_ON(!test_bit(NAPI_STATE_SCHED, &val));
 
@@ -6748,7 +6799,11 @@ void __netif_napi_del(struct napi_struct *napi)
 	if (!test_and_clear_bit(NAPI_STATE_LISTED, &napi->state))
 		return;
 
-	napi_hash_del(napi);
+	if (napi->config) {
+		napi->index = -1;
+		napi->config = NULL;
+	}
+
 	list_del_rcu(&napi->dev_list);
 	napi_free_frags(napi);
 
@@ -11085,6 +11140,8 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 		unsigned int txqs, unsigned int rxqs)
 {
 	struct net_device *dev;
+	size_t napi_config_sz;
+	unsigned int maxqs;
 
 	BUG_ON(strlen(name) >= sizeof(dev->name));
 
@@ -11098,6 +11155,8 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 		return NULL;
 	}
 
+	maxqs = max(txqs, rxqs);
+
 	dev = kvzalloc(struct_size(dev, priv, sizeof_priv),
 		       GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL);
 	if (!dev)
@@ -11174,6 +11233,11 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 	if (!dev->ethtool)
 		goto free_all;
 
+	napi_config_sz = array_size(maxqs, sizeof(*dev->napi_config));
+	dev->napi_config = kvzalloc(napi_config_sz, GFP_KERNEL_ACCOUNT);
+	if (!dev->napi_config)
+		goto free_all;
+
 	strscpy(dev->name, name);
 	dev->name_assign_type = name_assign_type;
 	dev->group = INIT_NETDEV_GROUP;
@@ -11237,6 +11301,8 @@ void free_netdev(struct net_device *dev)
 	list_for_each_entry_safe(p, n, &dev->napi_list, dev_list)
 		netif_napi_del(p);
 
+	kvfree(dev->napi_config);
+
 	ref_tracker_dir_exit(&dev->refcnt_tracker);
 #ifdef CONFIG_PCPU_DEV_REFCNT
 	free_percpu(dev->pcpu_refcnt);