net: add sysfs attribute to control napi threaded mode

This patch adds a new sysfs attribute to the network device class.
Said attribute provides a per-device control to enable/disable the
threaded mode for all the napi instances of the given network device,
without the need for a device up/down.
User sets it to 1 or 0 to enable or disable threaded mode.
Note: when switching between threaded and the current softirq based mode
for a napi instance, it will not immediately take effect if the napi is
currently being polled. The mode switch will happen for the next time
napi_schedule() is called.

Co-developed-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Co-developed-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Co-developed-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Wei Wang <weiwan@google.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 86 insertions, 2 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 1e35f4f44f3b..7647278e46f0 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4291,8 +4291,9 @@ static inline void ____napi_schedule(struct softnet_data *sd,
 
 	if (test_bit(NAPI_STATE_THREADED, &napi->state)) {
 		/* Paired with smp_mb__before_atomic() in
-		 * napi_enable(). Use READ_ONCE() to guarantee
-		 * a complete read on napi->thread. Only call
+		 * napi_enable()/dev_set_threaded().
+		 * Use READ_ONCE() to guarantee a complete
+		 * read on napi->thread. Only call
 		 * wake_up_process() when it's not NULL.
 		 */
 		thread = READ_ONCE(napi->thread);
@@ -6738,6 +6739,49 @@ static void init_gro_hash(struct napi_struct *napi)
 	napi->gro_bitmask = 0;
 }
 
+int dev_set_threaded(struct net_device *dev, bool threaded)
+{
+	struct napi_struct *napi;
+	int err = 0;
+
+	if (dev->threaded == threaded)
+		return 0;
+
+	if (threaded) {
+		list_for_each_entry(napi, &dev->napi_list, dev_list) {
+			if (!napi->thread) {
+				err = napi_kthread_create(napi);
+				if (err) {
+					threaded = false;
+					break;
+				}
+			}
+		}
+	}
+
+	dev->threaded = threaded;
+
+	/* Make sure kthread is created before THREADED bit
+	 * is set.
+	 */
+	smp_mb__before_atomic();
+
+	/* Setting/unsetting threaded mode on a napi might not immediately
+	 * take effect, if the current napi instance is actively being
+	 * polled. In this case, the switch between threaded mode and
+	 * softirq mode will happen in the next round of napi_schedule().
+	 * This should not cause hiccups/stalls to the live traffic.
+	 */
+	list_for_each_entry(napi, &dev->napi_list, dev_list) {
+		if (threaded)
+			set_bit(NAPI_STATE_THREADED, &napi->state);
+		else
+			clear_bit(NAPI_STATE_THREADED, &napi->state);
+	}
+
+	return err;
+}
+
 void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
 		    int (*poll)(struct napi_struct *, int), int weight)
 {
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 91afb0b6de69..307628fdf380 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -538,6 +538,45 @@ static ssize_t phys_switch_id_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(phys_switch_id);
 
+static ssize_t threaded_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	struct net_device *netdev = to_net_dev(dev);
+	ssize_t ret = -EINVAL;
+
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	if (dev_isalive(netdev))
+		ret = sprintf(buf, fmt_dec, netdev->threaded);
+
+	rtnl_unlock();
+	return ret;
+}
+
+static int modify_napi_threaded(struct net_device *dev, unsigned long val)
+{
+	int ret;
+
+	if (list_empty(&dev->napi_list))
+		return -EOPNOTSUPP;
+
+	if (val != 0 && val != 1)
+		return -EOPNOTSUPP;
+
+	ret = dev_set_threaded(dev, val);
+
+	return ret;
+}
+
+static ssize_t threaded_store(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t len)
+{
+	return netdev_store(dev, attr, buf, len, modify_napi_threaded);
+}
+static DEVICE_ATTR_RW(threaded);
+
 static struct attribute *net_class_attrs[] __ro_after_init = {
 	&dev_attr_netdev_group.attr,
 	&dev_attr_type.attr,
@@ -570,6 +609,7 @@ static struct attribute *net_class_attrs[] __ro_after_init = {
 	&dev_attr_proto_down.attr,
 	&dev_attr_carrier_up_count.attr,
 	&dev_attr_carrier_down_count.attr,
+	&dev_attr_threaded.attr,
 	NULL,
 };
 ATTRIBUTE_GROUPS(net_class);