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/20211008122439.166063-7-markzhang@nvidia.com
Signed-off-by: Aharon Landau <aharonl@nvidia.com>
Signed-off-by: Neta Ostrovsky <netao@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Mark Zhang <markzhang@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

3 files changed, 59 insertions, 10 deletions

diff --git a/drivers/infiniband/core/counters.c b/drivers/infiniband/core/counters.c
index 331cd29f0d61..af59486fe418 100644
--- a/drivers/infiniband/core/counters.c
+++ b/drivers/infiniband/core/counters.c
@@ -106,6 +106,38 @@ static int __rdma_counter_bind_qp(struct rdma_counter *counter,
 	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)
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index f4814bb7f082..22a4adda7981 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -2676,6 +2676,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops)
 	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);
diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c
index 8d831d4fd2ad..1bf3aea4b71e 100644
--- a/drivers/infiniband/core/sysfs.c
+++ b/drivers/infiniband/core/sysfs.c
@@ -934,7 +934,8 @@ int ib_setup_device_attrs(struct ib_device *ibdev)
 {
 	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)) {
@@ -955,16 +956,23 @@ int ib_setup_device_attrs(struct ib_device *ibdev)
 	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;
@@ -972,7 +980,7 @@ int ib_setup_device_attrs(struct ib_device *ibdev)
 	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;
@@ -1027,7 +1035,8 @@ static int setup_hw_port_stats(struct ib_port *port,
 {
 	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))
@@ -1045,16 +1054,23 @@ static int setup_hw_port_stats(struct ib_port *port,
 	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;
@@ -1062,7 +1078,7 @@ static int setup_hw_port_stats(struct ib_port *port,
 	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;