Merge branch 'net-introduce-rps_default_mask'

Paolo Abeni says:

====================
net: introduce rps_default_mask

Real-time setups try hard to ensure proper isolation between time
critical applications and e.g. network processing performed by the
network stack in softirq and RPS is used to move the softirq
activity away from the isolated core.

If the network configuration is dynamic, with netns and devices
routinely created at run-time, enforcing the correct RPS setting
on each newly created device allowing to transient bad configuration
became complex.

Additionally, when multi-queue devices are involved, configuring rps
in user-space on each queue easily becomes very expensive, e.g.
some setups use veths with per cpu queues.

These series try to address the above, introducing a new
sysctl knob: rps_default_mask. The new sysctl entry allows
configuring a netns-wide RPS mask, to be enforced since receive
queue creation time without any fourther per device configuration
required.

Additionally, a simple self-test is introduced to check the
rps_default_mask behavior.
====================

Link: https://lore.kernel.org/r/cover.1675789134.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 49 insertions, 30 deletions

diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index ca55dd747d6c..4b361ac6a252 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -831,42 +831,18 @@ static ssize_t show_rps_map(struct netdev_rx_queue *queue, char *buf)
 	return len < PAGE_SIZE ? len : -EINVAL;
 }
 
-static ssize_t store_rps_map(struct netdev_rx_queue *queue,
-			     const char *buf, size_t len)
+static int netdev_rx_queue_set_rps_mask(struct netdev_rx_queue *queue,
+					cpumask_var_t mask)
 {
-	struct rps_map *old_map, *map;
-	cpumask_var_t mask;
-	int err, cpu, i;
 	static DEFINE_MUTEX(rps_map_mutex);
-
-	if (!capable(CAP_NET_ADMIN))
-		return -EPERM;
-
-	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
-		return -ENOMEM;
-
-	err = bitmap_parse(buf, len, cpumask_bits(mask), nr_cpumask_bits);
-	if (err) {
-		free_cpumask_var(mask);
-		return err;
-	}
-
-	if (!cpumask_empty(mask)) {
-		cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_DOMAIN));
-		cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_WQ));
-		if (cpumask_empty(mask)) {
-			free_cpumask_var(mask);
-			return -EINVAL;
-		}
-	}
+	struct rps_map *old_map, *map;
+	int cpu, i;
 
 	map = kzalloc(max_t(unsigned int,
 			    RPS_MAP_SIZE(cpumask_weight(mask)), L1_CACHE_BYTES),
 		      GFP_KERNEL);
-	if (!map) {
-		free_cpumask_var(mask);
+	if (!map)
 		return -ENOMEM;
-	}
 
 	i = 0;
 	for_each_cpu_and(cpu, mask, cpu_online_mask)
@@ -893,9 +869,45 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue,
 
 	if (old_map)
 		kfree_rcu(old_map, rcu);
+	return 0;
+}
 
+int rps_cpumask_housekeeping(struct cpumask *mask)
+{
+	if (!cpumask_empty(mask)) {
+		cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_DOMAIN));
+		cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_WQ));
+		if (cpumask_empty(mask))
+			return -EINVAL;
+	}
+	return 0;
+}
+
+static ssize_t store_rps_map(struct netdev_rx_queue *queue,
+			     const char *buf, size_t len)
+{
+	cpumask_var_t mask;
+	int err;
+
+	if (!capable(CAP_NET_ADMIN))
+		return -EPERM;
+
+	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	err = bitmap_parse(buf, len, cpumask_bits(mask), nr_cpumask_bits);
+	if (err)
+		goto out;
+
+	err = rps_cpumask_housekeeping(mask);
+	if (err)
+		goto out;
+
+	err = netdev_rx_queue_set_rps_mask(queue, mask);
+
+out:
 	free_cpumask_var(mask);
-	return len;
+	return err ? : len;
 }
 
 static ssize_t show_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue,
@@ -1071,6 +1083,13 @@ static int rx_queue_add_kobject(struct net_device *dev, int index)
 			goto err;
 	}
 
+#if IS_ENABLED(CONFIG_RPS) && IS_ENABLED(CONFIG_SYSCTL)
+	if (!cpumask_empty(&rps_default_mask)) {
+		error = netdev_rx_queue_set_rps_mask(queue, &rps_default_mask);
+		if (error)
+			goto err;
+	}
+#endif
 	kobject_uevent(kobj, KOBJ_ADD);
 
 	return error;