[PATCH net-next 3/5] net: napi: Make gro_flush_timeout per-NAPI

[Joe Damato]

Allow per-NAPI gro_flush_timeout setting.

The existing sysfs parameter is respected; writes to sysfs will write to
all NAPI structs for the device and the net_device gro_flush_timeout
field.  Reads from sysfs will read from the net_device field.

The ability to set gro_flush_timeout on specific NAPI instances will be
added in a later commit, via netdev-genl.

Signed-off-by: Joe Damato <jdamato@xxxxxxxxxx>
Reviewed-by: Martin Karsten <mkarsten@xxxxxxxxxxxx>
Tested-by: Martin Karsten <mkarsten@xxxxxxxxxxxx>
---
 include/linux/netdevice.h | 26 ++++++++++++++++++++++++++
 net/core/dev.c            | 32 ++++++++++++++++++++++++++++----
 net/core/net-sysfs.c      |  2 +-
 3 files changed, 55 insertions(+), 5 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7d53380da4c0..d00024d9f857 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -372,6 +372,7 @@ struct napi_struct {
 	int			rx_count; /* length of rx_list */
 	unsigned int		napi_id;
 	int			defer_hard_irqs;
+	unsigned long		gro_flush_timeout;
 	struct hrtimer		timer;
 	struct task_struct	*thread;
 	/* control-path-only fields follow */
@@ -557,6 +558,31 @@ void napi_set_defer_hard_irqs(struct napi_struct *n, int defer);
  */
 void netdev_set_defer_hard_irqs(struct net_device *netdev, int defer);
 
+/**
+ * napi_get_gro_flush_timeout - get the gro_flush_timeout
+ * @n: napi struct to get the gro_flush_timeout from
+ *
+ * Returns the per-NAPI value of the gro_flush_timeout field.
+ */
+unsigned long napi_get_gro_flush_timeout(const struct napi_struct *n);
+
+/**
+ * napi_set_gro_flush_timeout - set the gro_flush_timeout for a napi
+ * @n: napi struct to set the gro_flush_timeout
+ * @timeout: timeout value to set
+ *
+ * napi_set_gro_flush_timeout sets the per-NAPI gro_flush_timeout
+ */
+void napi_set_gro_flush_timeout(struct napi_struct *n, unsigned long timeout);
+
+/**
+ * netdev_set_gro_flush_timeout - set gro_flush_timeout for all NAPIs of a netdev
+ * @netdev: the net_device for which all NAPIs will have their gro_flush_timeout set
+ * @timeout: the timeout value to set
+ */
+void netdev_set_gro_flush_timeout(struct net_device *netdev,
+				  unsigned long timeout);
+
 /**
  * napi_complete_done - NAPI processing complete
  * @n: NAPI context
diff --git a/net/core/dev.c b/net/core/dev.c
index f7baff0da057..3f7cb1085efa 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6234,6 +6234,29 @@ void netdev_set_defer_hard_irqs(struct net_device *netdev, int defer)
 }
 EXPORT_SYMBOL_GPL(netdev_set_defer_hard_irqs);
 
+unsigned long napi_get_gro_flush_timeout(const struct napi_struct *n)
+{
+	return READ_ONCE(n->gro_flush_timeout);
+}
+EXPORT_SYMBOL_GPL(napi_get_gro_flush_timeout);
+
+void napi_set_gro_flush_timeout(struct napi_struct *n, unsigned long timeout)
+{
+	WRITE_ONCE(n->gro_flush_timeout, timeout);
+}
+EXPORT_SYMBOL_GPL(napi_set_gro_flush_timeout);
+
+void netdev_set_gro_flush_timeout(struct net_device *netdev,
+				  unsigned long timeout)
+{
+	struct napi_struct *napi;
+
+	WRITE_ONCE(netdev->gro_flush_timeout, timeout);
+	list_for_each_entry(napi, &netdev->napi_list, dev_list)
+		napi_set_gro_flush_timeout(napi, timeout);
+}
+EXPORT_SYMBOL_GPL(netdev_set_gro_flush_timeout);
+
 bool napi_complete_done(struct napi_struct *n, int work_done)
 {
 	unsigned long flags, val, new, timeout = 0;
@@ -6251,12 +6274,12 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 
 	if (work_done) {
 		if (n->gro_bitmask)
-			timeout = READ_ONCE(n->dev->gro_flush_timeout);
+			timeout = napi_get_gro_flush_timeout(n);
 		n->defer_hard_irqs_count = napi_get_defer_hard_irqs(n);
 	}
 	if (n->defer_hard_irqs_count > 0) {
 		n->defer_hard_irqs_count--;
-		timeout = READ_ONCE(n->dev->gro_flush_timeout);
+		timeout = napi_get_gro_flush_timeout(n);
 		if (timeout)
 			ret = false;
 	}
@@ -6391,7 +6414,7 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock,
 
 	if (flags & NAPI_F_PREFER_BUSY_POLL) {
 		napi->defer_hard_irqs_count = napi_get_defer_hard_irqs(napi);
-		timeout = READ_ONCE(napi->dev->gro_flush_timeout);
+		timeout = napi_get_gro_flush_timeout(napi);
 		if (napi->defer_hard_irqs_count && timeout) {
 			hrtimer_start(&napi->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED);
 			skip_schedule = true;
@@ -6673,6 +6696,7 @@ void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi,
 	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);
@@ -11054,7 +11078,7 @@ void netdev_sw_irq_coalesce_default_on(struct net_device *dev)
 	WARN_ON(dev->reg_state == NETREG_REGISTERED);
 
 	if (!IS_ENABLED(CONFIG_PREEMPT_RT)) {
-		dev->gro_flush_timeout = 20000;
+		netdev_set_gro_flush_timeout(dev, 20000);
 		netdev_set_defer_hard_irqs(dev, 1);
 	}
 }
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 8272f0144d81..ff545a422b1f 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -408,7 +408,7 @@ NETDEVICE_SHOW_RW(tx_queue_len, fmt_dec);
 
 static int change_gro_flush_timeout(struct net_device *dev, unsigned long val)
 {
-	WRITE_ONCE(dev->gro_flush_timeout, val);
+	netdev_set_gro_flush_timeout(dev, val);
 	return 0;
 }
 
-- 
2.25.1