RDMA/counter: Add optional counter support

An optional counter is a driver-specific counter that may be dynamically
enabled/disabled. This enhancement allows drivers to expose counters
which are, for example, mutually exclusive and cannot be enabled at the
same time, counters that might degrades performance, optional debug
counters, etc.

Optional counters are marked with IB_STAT_FLAG_OPTIONAL flag. They are not
exported in sysfs, and must be at the end of all stats, otherwise the
attr->show() in sysfs would get wrong indexes for hwcounters that are
behind optional counters.

Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Aharon Landau <[e-mail]>
Signed-off-by: Neta Ostrovsky <[e-mail]>
Signed-off-by: Leon Romanovsky <[e-mail]>
Signed-off-by: Mark Zhang <[e-mail]>
Signed-off-by: Jason Gunthorpe <[e-mail]>

drivers/infiniband/core/counters.c

···
 	return ret;
 }
 
+int rdma_counter_modify(struct ib_device *dev, u32 port,
+			unsigned int index, bool enable)
+{
+	struct rdma_hw_stats *stats;
+	int ret = 0;
+
+	if (!dev->ops.modify_hw_stat)
+		return -EOPNOTSUPP;
+
+	stats = ib_get_hw_stats_port(dev, port);
+	if (!stats || index >= stats->num_counters ||
+	    !(stats->descs[index].flags & IB_STAT_FLAG_OPTIONAL))
+		return -EINVAL;
+
+	mutex_lock(&stats->lock);
+
+	if (enable != test_bit(index, stats->is_disabled))
+		goto out;
+
+	ret = dev->ops.modify_hw_stat(dev, port, index, enable);
+	if (ret)
+		goto out;
+
+	if (enable)
+		clear_bit(index, stats->is_disabled);
+	else
+		set_bit(index, stats->is_disabled);
+out:
+	mutex_unlock(&stats->lock);
+	return ret;
+}
+
 static struct rdma_counter *alloc_and_bind(struct ib_device *dev, u32 port,
 					   struct ib_qp *qp,
 					   enum rdma_nl_counter_mode mode)

drivers/infiniband/core/device.c

···
 	SET_DEVICE_OP(dev_ops, modify_cq);
 	SET_DEVICE_OP(dev_ops, modify_device);
 	SET_DEVICE_OP(dev_ops, modify_flow_action_esp);
+	SET_DEVICE_OP(dev_ops, modify_hw_stat);
 	SET_DEVICE_OP(dev_ops, modify_port);
 	SET_DEVICE_OP(dev_ops, modify_qp);
 	SET_DEVICE_OP(dev_ops, modify_srq);

drivers/infiniband/core/sysfs.c

···
 {
 	struct hw_stats_device_attribute *attr;
 	struct hw_stats_device_data *data;
-	int i, ret;
+	bool opstat_skipped = false;
+	int i, ret, pos = 0;
 
 	data = alloc_hw_stats_device(ibdev);
 	if (IS_ERR(data)) {
···
 	data->stats->timestamp = jiffies;
 
 	for (i = 0; i < data->stats->num_counters; i++) {
-		attr = &data->attrs[i];
+		if (data->stats->descs[i].flags & IB_STAT_FLAG_OPTIONAL) {
+			opstat_skipped = true;
+			continue;
+		}
+
+		WARN_ON(opstat_skipped);
+		attr = &data->attrs[pos];
 		sysfs_attr_init(&attr->attr.attr);
 		attr->attr.attr.name = data->stats->descs[i].name;
 		attr->attr.attr.mode = 0444;
 		attr->attr.show = hw_stat_device_show;
 		attr->show = show_hw_stats;
-		data->group.attrs[i] = &attr->attr.attr;
+		data->group.attrs[pos] = &attr->attr.attr;
+		pos++;
 	}
 
-	attr = &data->attrs[i];
+	attr = &data->attrs[pos];
 	sysfs_attr_init(&attr->attr.attr);
 	attr->attr.attr.name = "lifespan";
 	attr->attr.attr.mode = 0644;
···
 	attr->show = show_stats_lifespan;
 	attr->attr.store = hw_stat_device_store;
 	attr->store = set_stats_lifespan;
-	data->group.attrs[i] = &attr->attr.attr;
+	data->group.attrs[pos] = &attr->attr.attr;
 	for (i = 0; i != ARRAY_SIZE(ibdev->groups); i++)
 		if (!ibdev->groups[i]) {
 			ibdev->groups[i] = &data->group;
···
 {
 	struct hw_stats_port_attribute *attr;
 	struct hw_stats_port_data *data;
-	int i, ret;
+	bool opstat_skipped = false;
+	int i, ret, pos = 0;
 
 	data = alloc_hw_stats_port(port, group);
 	if (IS_ERR(data))
···
 	data->stats->timestamp = jiffies;
 
 	for (i = 0; i < data->stats->num_counters; i++) {
-		attr = &data->attrs[i];
+		if (data->stats->descs[i].flags & IB_STAT_FLAG_OPTIONAL) {
+			opstat_skipped = true;
+			continue;
+		}
+
+		WARN_ON(opstat_skipped);
+		attr = &data->attrs[pos];
 		sysfs_attr_init(&attr->attr.attr);
 		attr->attr.attr.name = data->stats->descs[i].name;
 		attr->attr.attr.mode = 0444;
 		attr->attr.show = hw_stat_port_show;
 		attr->show = show_hw_stats;
-		group->attrs[i] = &attr->attr.attr;
+		group->attrs[pos] = &attr->attr.attr;
+		pos++;
 	}
 
-	attr = &data->attrs[i];
+	attr = &data->attrs[pos];
 	sysfs_attr_init(&attr->attr.attr);
 	attr->attr.attr.name = "lifespan";
 	attr->attr.attr.mode = 0644;
···
 	attr->show = show_stats_lifespan;
 	attr->attr.store = hw_stat_port_store;
 	attr->store = set_stats_lifespan;
-	group->attrs[i] = &attr->attr.attr;
+	group->attrs[pos] = &attr->attr.attr;
 
 	port->hw_stats_data = data;
 	return 0;

include/rdma/ib_verbs.h

···
 	IB_SPEED_NDR	= 128,
 };
 
+enum ib_stat_flag {
+	IB_STAT_FLAG_OPTIONAL = 1 << 0,
+};
+
 /**
  * struct rdma_stat_desc
  * @name - The name of the counter
+ * @flags - Flags of the counter; For example, IB_STAT_FLAG_OPTIONAL
  */
 struct rdma_stat_desc {
 	const char *name;
+	unsigned int flags;
 };
 
 /**
···
 	int (*get_hw_stats)(struct ib_device *device,
 			    struct rdma_hw_stats *stats, u32 port, int index);
 
+	/**
+	 * modify_hw_stat - Modify the counter configuration
+	 * @enable: true/false when enable/disable a counter
+	 * Return codes - 0 on success or error code otherwise.
+	 */
+	int (*modify_hw_stat)(struct ib_device *device, u32 port,
+			      unsigned int counter_index, bool enable);
 	/**
 	 * Allows rdma drivers to add their own restrack attributes.
 	 */

include/rdma/rdma_counter.h

···
 			  enum rdma_nl_counter_mode *mode,
 			  enum rdma_nl_counter_mask *mask);
 
+int rdma_counter_modify(struct ib_device *dev, u32 port,
+			unsigned int index, bool enable);
 #endif /* _RDMA_COUNTER_H_ */