sched_ext: Maintain an online cid mask in the scheduler arenagrafted

Schedulers on the default cid mapping treat [0, nr_online_cids) as the
online set and restart on hotplug. Schedulers that install their own mapping
with scx_bpf_cid_override() have no way to learn which cids are online: the
count no longer identifies members and the CPU-form cpumask is unusable from
cid programs. This is an obvious hole in the cid API.

Add scx_bpf_online_cmask(), a kernel-maintained cmask in the scheduler's
arena, allocated alongside the per-CPU scratch masks and populated after the
cid mapping is finalized and before ops.init(), for child schedulers too.
The pointer stays valid through ops.exit() with no reference to take. It is
the arena offset as a void pointer, the same form struct_ops arena arguments
arrive in. The verifier types the void return as a scalar for the program's
arena cast.

The mask follows the SCX hotplug notifications: seeded from cpu_active_mask
and updated before ops.cid_online/offline() runs, so it lags cpu_online_mask
only inside a hotplug transition. Updates walk the scheduler list under the
lock that also serializes unlinking. Reads are live, not atomic snapshots.
Root initialization excludes hotplug.

v2: Reworded the getter kerneldoc (Andrea Righi).

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Andrea Righi <arighi@nvidia.com>

1 files changed, 97 insertions, 0 deletions

diff --git a/drivers/net/netdevsim/tc.c b/drivers/net/netdevsim/tc.c
new file mode 100644
index 000000000..a415e02a6
--- /dev/null
+++ b/drivers/net/netdevsim/tc.c
@@ -0,0 +1,97 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/netdevice.h>
+#include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
+
+#include "netdevsim.h"
+
+static int
+nsim_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv)
+{
+	struct flow_cls_common_offload *common = type_data;
+	int err = 0;
+
+	switch (type) {
+	case TC_SETUP_CLSBPF:
+		err = nsim_bpf_setup_tc_block_cb(type, type_data, cb_priv);
+		break;
+	case TC_SETUP_CLSFLOWER:
+		break;
+	default:
+		NSIM_EA(common->extack, "offload type not supported");
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+	return err;
+}
+
+static void nsim_taprio_stats(struct tc_taprio_qopt_stats *stats)
+{
+	stats->window_drops = 0;
+	stats->tx_overruns = 0;
+}
+
+static int nsim_setup_tc_taprio(struct net_device *dev,
+				struct tc_taprio_qopt_offload *offload)
+{
+	int err = 0;
+
+	switch (offload->cmd) {
+	case TAPRIO_CMD_REPLACE:
+	case TAPRIO_CMD_DESTROY:
+		break;
+	case TAPRIO_CMD_STATS:
+		nsim_taprio_stats(&offload->stats);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+	}
+
+	return err;
+}
+
+static int nsim_setup_tc_ets(struct net_device *dev,
+			     struct tc_ets_qopt_offload *offload)
+{
+	int err = 0;
+
+	switch (offload->command) {
+	case TC_ETS_REPLACE:
+	case TC_ETS_DESTROY:
+		break;
+	case TC_ETS_STATS:
+		_bstats_update(offload->stats.bstats, 0, 0);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+	}
+
+	return err;
+}
+
+static LIST_HEAD(nsim_block_cb_list);
+
+int
+nsim_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	switch (type) {
+	case TC_SETUP_QDISC_TAPRIO:
+		return nsim_setup_tc_taprio(dev, type_data);
+	case TC_SETUP_QDISC_ETS:
+		return nsim_setup_tc_ets(dev, type_data);
+	case TC_SETUP_BLOCK:
+		return flow_block_cb_setup_simple(type_data,
+						  &nsim_block_cb_list,
+						  nsim_setup_tc_block_cb,
+						  ns, ns, true);
+	case TC_SETUP_FT:
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+ALLOW_ERROR_INJECTION(nsim_setup_tc, ERRNO);