From: Aharon Landau <aharonl@nvidia.com>
Date: Fri, 8 Oct 2021 15:24:32 +0300
Subject: RDMA/counter: Add optional counter support
Patch-mainline: v5.16-rc1
Git-commit: 5e2ddd1e598273d77f653c70df96fc417a2d0a85
References: jsc#SLE-19249

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>
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
 drivers/infiniband/core/counters.c |   32 ++++++++++++++++++++++++++++++++
 drivers/infiniband/core/device.c   |    1 +
 drivers/infiniband/core/sysfs.c    |   36 ++++++++++++++++++++++++++----------
 include/rdma/ib_verbs.h            |   13 +++++++++++++
 include/rdma/rdma_counter.h        |    2 ++
 5 files changed, 74 insertions(+), 10 deletions(-)

--- a/drivers/infiniband/core/counters.c
+++ b/drivers/infiniband/core/counters.c
@@ -106,6 +106,38 @@ static int __rdma_counter_bind_qp(struct
 	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)
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -2676,6 +2676,7 @@ void ib_set_device_ops(struct ib_device
 	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);
--- a/drivers/infiniband/core/sysfs.c
+++ b/drivers/infiniband/core/sysfs.c
@@ -934,7 +934,8 @@ int ib_setup_device_attrs(struct ib_devi
 {
 	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_devi
 	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_devi
 	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
 {
 	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
 	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
 	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;
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -545,12 +545,18 @@ enum ib_port_speed {
 	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;
 };
 
 /**
@@ -2563,6 +2569,13 @@ struct ib_device_ops {
 			    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.
 	 */
 	int (*fill_res_mr_entry)(struct sk_buff *msg, struct ib_mr *ibmr);
--- a/include/rdma/rdma_counter.h
+++ b/include/rdma/rdma_counter.h
@@ -63,4 +63,6 @@ int rdma_counter_get_mode(struct ib_devi
 			  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_ */