Merge tag 'verbs_flow_counters' of git://git.kernel.org/pub/scm/linux/kernel/git/leon/linux-rdma.git into for-next

Pull verbs counters series from Leon Romanovsky:

====================
Verbs flow counters support

This series comes to allow user space applications to monitor real time
traffic activity and events of the verbs objects it manages, e.g.: ibv_qp,
ibv_wq, ibv_flow.

The API enables generic counters creation and define mapping to
association with a verbs object, the current mlx5 driver is using this API
for flow counters.

With this API, an application can monitor the entire life cycle of object
activity, defined here as a static counters attachment.  This API also
allows dynamic counters monitoring of measurement points for a partial
period in the verbs object life cycle.

In addition it presents the implementation of the generic counters
interface.

This will be achieved by extending flow creation by adding a new flow
count specification type which allows the user to associate a previously
created flow counters using the generic verbs counters interface to the
created flow, once associated the user could read statistics by using the
read function of the generic counters interface.

The API includes:
1. create and destroyed API of a new counters objects
2. read the counters values from HW

Note:
Attaching API to allow application to define the measurement points per
objects is a user space only API and this data is passed to kernel when
the counted object (e.g. flow) is created with the counters object.
===================

* tag 'verbs_flow_counters':
  IB/mlx5: Add counters read support
  IB/mlx5: Add flow counters read support
  IB/mlx5: Add flow counters binding support
  IB/mlx5: Add counters create and destroy support
  IB/uverbs: Add support for flow counters
  IB/core: Add support for flow counters
  IB/core: Support passing uhw for create_flow
  IB/uverbs: Add read counters support
  IB/core: Introduce counters read verb
  IB/uverbs: Add create/destroy counters support
  IB/core: Introduce counters object and its create/destroy
  IB/uverbs: Add an ib_uobject getter to ioctl() infrastructure
  net/mlx5: Export flow counter related API
  net/mlx5: Use flow counter pointer as input to the query function

1 files changed, 293 insertions, 12 deletions

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 0541581c5d84b..3544150f34699 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -2443,7 +2443,7 @@ static int check_mpls_supp_fields(u32 field_support, const __be32 *set_mask)
 #define LAST_TUNNEL_FIELD tunnel_id
 #define LAST_FLOW_TAG_FIELD tag_id
 #define LAST_DROP_FIELD size
-#define LAST_DROP_FIELD size
+#define LAST_COUNTERS_FIELD counters
 
 /* Field is the last supported field */
 #define FIELDS_NOT_SUPPORTED(filter, field)\
@@ -2807,6 +2807,18 @@ static int parse_flow_attr(struct mlx5_core_dev *mdev, u32 *match_c,
 		if (ret)
 			return ret;
 		break;
+	case IB_FLOW_SPEC_ACTION_COUNT:
+		if (FIELDS_NOT_SUPPORTED(ib_spec->flow_count,
+					 LAST_COUNTERS_FIELD))
+			return -EOPNOTSUPP;
+
+		/* for now support only one counters spec per flow */
+		if (action->action & MLX5_FLOW_CONTEXT_ACTION_COUNT)
+			return -EINVAL;
+
+		action->counters = ib_spec->flow_count.counters;
+		action->action |= MLX5_FLOW_CONTEXT_ACTION_COUNT;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -2954,6 +2966,17 @@ static void put_flow_table(struct mlx5_ib_dev *dev,
 	}
 }
 
+static void counters_clear_description(struct ib_counters *counters)
+{
+	struct mlx5_ib_mcounters *mcounters = to_mcounters(counters);
+
+	mutex_lock(&mcounters->mcntrs_mutex);
+	kfree(mcounters->counters_data);
+	mcounters->counters_data = NULL;
+	mcounters->cntrs_max_index = 0;
+	mutex_unlock(&mcounters->mcntrs_mutex);
+}
+
 static int mlx5_ib_destroy_flow(struct ib_flow *flow_id)
 {
 	struct mlx5_ib_dev *dev = to_mdev(flow_id->qp->device);
@@ -2973,8 +2996,11 @@ static int mlx5_ib_destroy_flow(struct ib_flow *flow_id)
 
 	mlx5_del_flow_rules(handler->rule);
 	put_flow_table(dev, handler->prio, true);
-	mutex_unlock(&dev->flow_db->lock);
+	if (handler->ibcounters &&
+	    atomic_read(&handler->ibcounters->usecnt) == 1)
+		counters_clear_description(handler->ibcounters);
 
+	mutex_unlock(&dev->flow_db->lock);
 	kfree(handler);
 
 	return 0;
@@ -3094,22 +3120,143 @@ static void set_underlay_qp(struct mlx5_ib_dev *dev,
 	}
 }
 
+static int read_flow_counters(struct ib_device *ibdev,
+			      struct mlx5_read_counters_attr *read_attr)
+{
+	struct mlx5_fc *fc = read_attr->hw_cntrs_hndl;
+	struct mlx5_ib_dev *dev = to_mdev(ibdev);
+
+	return mlx5_fc_query(dev->mdev, fc,
+			     &read_attr->out[IB_COUNTER_PACKETS],
+			     &read_attr->out[IB_COUNTER_BYTES]);
+}
+
+/* flow counters currently expose two counters packets and bytes */
+#define FLOW_COUNTERS_NUM 2
+static int counters_set_description(struct ib_counters *counters,
+				    enum mlx5_ib_counters_type counters_type,
+				    struct mlx5_ib_flow_counters_desc *desc_data,
+				    u32 ncounters)
+{
+	struct mlx5_ib_mcounters *mcounters = to_mcounters(counters);
+	u32 cntrs_max_index = 0;
+	int i;
+
+	if (counters_type != MLX5_IB_COUNTERS_FLOW)
+		return -EINVAL;
+
+	/* init the fields for the object */
+	mcounters->type = counters_type;
+	mcounters->read_counters = read_flow_counters;
+	mcounters->counters_num = FLOW_COUNTERS_NUM;
+	mcounters->ncounters = ncounters;
+	/* each counter entry have both description and index pair */
+	for (i = 0; i < ncounters; i++) {
+		if (desc_data[i].description > IB_COUNTER_BYTES)
+			return -EINVAL;
+
+		if (cntrs_max_index <= desc_data[i].index)
+			cntrs_max_index = desc_data[i].index + 1;
+	}
+
+	mutex_lock(&mcounters->mcntrs_mutex);
+	mcounters->counters_data = desc_data;
+	mcounters->cntrs_max_index = cntrs_max_index;
+	mutex_unlock(&mcounters->mcntrs_mutex);
+
+	return 0;
+}
+
+#define MAX_COUNTERS_NUM (USHRT_MAX / (sizeof(u32) * 2))
+static int flow_counters_set_data(struct ib_counters *ibcounters,
+				  struct mlx5_ib_create_flow *ucmd)
+{
+	struct mlx5_ib_mcounters *mcounters = to_mcounters(ibcounters);
+	struct mlx5_ib_flow_counters_data *cntrs_data = NULL;
+	struct mlx5_ib_flow_counters_desc *desc_data = NULL;
+	bool hw_hndl = false;
+	int ret = 0;
+
+	if (ucmd && ucmd->ncounters_data != 0) {
+		cntrs_data = ucmd->data;
+		if (cntrs_data->ncounters > MAX_COUNTERS_NUM)
+			return -EINVAL;
+
+		desc_data = kcalloc(cntrs_data->ncounters,
+				    sizeof(*desc_data),
+				    GFP_KERNEL);
+		if (!desc_data)
+			return  -ENOMEM;
+
+		if (copy_from_user(desc_data,
+				   u64_to_user_ptr(cntrs_data->counters_data),
+				   sizeof(*desc_data) * cntrs_data->ncounters)) {
+			ret = -EFAULT;
+			goto free;
+		}
+	}
+
+	if (!mcounters->hw_cntrs_hndl) {
+		mcounters->hw_cntrs_hndl = mlx5_fc_create(
+			to_mdev(ibcounters->device)->mdev, false);
+		if (!mcounters->hw_cntrs_hndl) {
+			ret = -ENOMEM;
+			goto free;
+		}
+		hw_hndl = true;
+	}
+
+	if (desc_data) {
+		/* counters already bound to at least one flow */
+		if (mcounters->cntrs_max_index) {
+			ret = -EINVAL;
+			goto free_hndl;
+		}
+
+		ret = counters_set_description(ibcounters,
+					       MLX5_IB_COUNTERS_FLOW,
+					       desc_data,
+					       cntrs_data->ncounters);
+		if (ret)
+			goto free_hndl;
+
+	} else if (!mcounters->cntrs_max_index) {
+		/* counters not bound yet, must have udata passed */
+		ret = -EINVAL;
+		goto free_hndl;
+	}
+
+	return 0;
+
+free_hndl:
+	if (hw_hndl) {
+		mlx5_fc_destroy(to_mdev(ibcounters->device)->mdev,
+				mcounters->hw_cntrs_hndl);
+		mcounters->hw_cntrs_hndl = NULL;
+	}
+free:
+	kfree(desc_data);
+	return ret;
+}
+
 static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev,
 						      struct mlx5_ib_flow_prio *ft_prio,
 						      const struct ib_flow_attr *flow_attr,
 						      struct mlx5_flow_destination *dst,
-						      u32 underlay_qpn)
+						      u32 underlay_qpn,
+						      struct mlx5_ib_create_flow *ucmd)
 {
 	struct mlx5_flow_table	*ft = ft_prio->flow_table;
 	struct mlx5_ib_flow_handler *handler;
 	struct mlx5_flow_act flow_act = {.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG};
 	struct mlx5_flow_spec *spec;
-	struct mlx5_flow_destination *rule_dst = dst;
+	struct mlx5_flow_destination dest_arr[2] = {};
+	struct mlx5_flow_destination *rule_dst = dest_arr;
 	const void *ib_flow = (const void *)flow_attr + sizeof(*flow_attr);
 	unsigned int spec_index;
 	u32 prev_type = 0;
 	int err = 0;
-	int dest_num = 1;
+	int dest_num = 0;
 	bool is_egress = flow_attr->flags & IB_FLOW_ATTR_FLAGS_EGRESS;
 
 	if (!is_valid_attr(dev->mdev, flow_attr))
@@ -3123,6 +3270,10 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev,
 	}
 
 	INIT_LIST_HEAD(&handler->list);
+	if (dst) {
+		memcpy(&dest_arr[0], dst, sizeof(*dst));
+		dest_num++;
+	}
 
 	for (spec_index = 0; spec_index < flow_attr->num_of_specs; spec_index++) {
 		err = parse_flow_attr(dev->mdev, spec->match_criteria,
@@ -3159,15 +3310,30 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev,
 		goto free;
 	}
 
+	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
+		err = flow_counters_set_data(flow_act.counters, ucmd);
+		if (err)
+			goto free;
+
+		handler->ibcounters = flow_act.counters;
+		dest_arr[dest_num].type =
+			MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+		dest_arr[dest_num].counter =
+			to_mcounters(flow_act.counters)->hw_cntrs_hndl;
+		dest_num++;
+	}
+
 	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DROP) {
-		rule_dst = NULL;
-		dest_num = 0;
+		if (!(flow_act.action & MLX5_FLOW_CONTEXT_ACTION_COUNT)) {
+			rule_dst = NULL;
+			dest_num = 0;
+		}
 	} else {
 		if (is_egress)
 			flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_ALLOW;
 		else
 			flow_act.action |=
-				dst ? MLX5_FLOW_CONTEXT_ACTION_FWD_DEST :
+				dest_num ?  MLX5_FLOW_CONTEXT_ACTION_FWD_DEST :
 					MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO;
 	}
 
@@ -3193,8 +3359,12 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev,
 
 	ft_prio->flow_table = ft;
 free:
-	if (err)
+	if (err && handler) {
+		if (handler->ibcounters &&
+		    atomic_read(&handler->ibcounters->usecnt) == 1)
+			counters_clear_description(handler->ibcounters);
 		kfree(handler);
+	}
 	kvfree(spec);
 	return err ? ERR_PTR(err) : handler;
 }
@@ -3204,7 +3374,7 @@ static struct mlx5_ib_flow_handler *create_flow_rule(struct mlx5_ib_dev *dev,
 						     const struct ib_flow_attr *flow_attr,
 						     struct mlx5_flow_destination *dst)
 {
-	return _create_flow_rule(dev, ft_prio, flow_attr, dst, 0);
+	return _create_flow_rule(dev, ft_prio, flow_attr, dst, 0, NULL);
 }
 
 static struct mlx5_ib_flow_handler *create_dont_trap_rule(struct mlx5_ib_dev *dev,
@@ -3334,7 +3504,8 @@ err:
 
 static struct ib_flow *mlx5_ib_create_flow(struct ib_qp *qp,
 					   struct ib_flow_attr *flow_attr,
-					   int domain)
+					   int domain,
+					   struct ib_udata *udata)
 {
 	struct mlx5_ib_dev *dev = to_mdev(qp->device);
 	struct mlx5_ib_qp *mqp = to_mqp(qp);
@@ -3343,9 +3514,44 @@ static struct ib_flow *mlx5_ib_create_flow(struct ib_qp *qp,
 	struct mlx5_ib_flow_prio *ft_prio_tx = NULL;
 	struct mlx5_ib_flow_prio *ft_prio;
 	bool is_egress = flow_attr->flags & IB_FLOW_ATTR_FLAGS_EGRESS;
+	struct mlx5_ib_create_flow *ucmd = NULL, ucmd_hdr;
+	size_t min_ucmd_sz, required_ucmd_sz;
 	int err;
 	int underlay_qpn;
 
+	if (udata && udata->inlen) {
+		min_ucmd_sz = offsetof(typeof(ucmd_hdr), reserved) +
+				sizeof(ucmd_hdr.reserved);
+		if (udata->inlen < min_ucmd_sz)
+			return ERR_PTR(-EOPNOTSUPP);
+
+		err = ib_copy_from_udata(&ucmd_hdr, udata, min_ucmd_sz);
+		if (err)
+			return ERR_PTR(err);
+
+		/* currently supports only one counters data */
+		if (ucmd_hdr.ncounters_data > 1)
+			return ERR_PTR(-EINVAL);
+
+		required_ucmd_sz = min_ucmd_sz +
+			sizeof(struct mlx5_ib_flow_counters_data) *
+			ucmd_hdr.ncounters_data;
+		if (udata->inlen > required_ucmd_sz &&
+		    !ib_is_udata_cleared(udata, required_ucmd_sz,
+					 udata->inlen - required_ucmd_sz))
+			return ERR_PTR(-EOPNOTSUPP);
+
+		ucmd = kzalloc(required_ucmd_sz, GFP_KERNEL);
+		if (!ucmd)
+			return ERR_PTR(-ENOMEM);
+
+		err = ib_copy_from_udata(ucmd, udata, required_ucmd_sz);
+		if (err) {
+			kfree(ucmd);
+			return ERR_PTR(err);
+		}
+	}
+
 	if (flow_attr->priority > MLX5_IB_FLOW_LAST_PRIO)
 		return ERR_PTR(-ENOMEM);
 
@@ -3399,7 +3605,7 @@ static struct ib_flow *mlx5_ib_create_flow(struct ib_qp *qp,
 			underlay_qpn = (mqp->flags & MLX5_IB_QP_UNDERLAY) ?
 					mqp->underlay_qpn : 0;
 			handler = _create_flow_rule(dev, ft_prio, flow_attr,
-						    dst, underlay_qpn);
+						    dst, underlay_qpn, ucmd);
 		}
 	} else if (flow_attr->type == IB_FLOW_ATTR_ALL_DEFAULT ||
 		   flow_attr->type == IB_FLOW_ATTR_MC_DEFAULT) {
@@ -3420,6 +3626,7 @@ static struct ib_flow *mlx5_ib_create_flow(struct ib_qp *qp,
 
 	mutex_unlock(&dev->flow_db->lock);
 	kfree(dst);
+	kfree(ucmd);
 
 	return &handler->ibflow;
 
@@ -3430,6 +3637,7 @@ destroy_ft:
 unlock:
 	mutex_unlock(&dev->flow_db->lock);
 	kfree(dst);
+	kfree(ucmd);
 	kfree(handler);
 	return ERR_PTR(err);
 }
@@ -5090,6 +5298,76 @@ static void depopulate_specs_root(struct mlx5_ib_dev *dev)
 	uverbs_free_spec_tree(dev->ib_dev.specs_root);
 }
 
+static int mlx5_ib_read_counters(struct ib_counters *counters,
+				 struct ib_counters_read_attr *read_attr,
+				 struct uverbs_attr_bundle *attrs)
+{
+	struct mlx5_ib_mcounters *mcounters = to_mcounters(counters);
+	struct mlx5_read_counters_attr mread_attr = {};
+	struct mlx5_ib_flow_counters_desc *desc;
+	int ret, i;
+
+	mutex_lock(&mcounters->mcntrs_mutex);
+	if (mcounters->cntrs_max_index > read_attr->ncounters) {
+		ret = -EINVAL;
+		goto err_bound;
+	}
+
+	mread_attr.out = kcalloc(mcounters->counters_num, sizeof(u64),
+				 GFP_KERNEL);
+	if (!mread_attr.out) {
+		ret = -ENOMEM;
+		goto err_bound;
+	}
+
+	mread_attr.hw_cntrs_hndl = mcounters->hw_cntrs_hndl;
+	mread_attr.flags = read_attr->flags;
+	ret = mcounters->read_counters(counters->device, &mread_attr);
+	if (ret)
+		goto err_read;
+
+	/* do the pass over the counters data array to assign according to the
+	 * descriptions and indexing pairs
+	 */
+	desc = mcounters->counters_data;
+	for (i = 0; i < mcounters->ncounters; i++)
+		read_attr->counters_buff[desc[i].index] += mread_attr.out[desc[i].description];
+
+err_read:
+	kfree(mread_attr.out);
+err_bound:
+	mutex_unlock(&mcounters->mcntrs_mutex);
+	return ret;
+}
+
+static int mlx5_ib_destroy_counters(struct ib_counters *counters)
+{
+	struct mlx5_ib_mcounters *mcounters = to_mcounters(counters);
+
+	counters_clear_description(counters);
+	if (mcounters->hw_cntrs_hndl)
+		mlx5_fc_destroy(to_mdev(counters->device)->mdev,
+				mcounters->hw_cntrs_hndl);
+
+	kfree(mcounters);
+
+	return 0;
+}
+
+static struct ib_counters *mlx5_ib_create_counters(struct ib_device *device,
+						   struct uverbs_attr_bundle *attrs)
+{
+	struct mlx5_ib_mcounters *mcounters;
+
+	mcounters = kzalloc(sizeof(*mcounters), GFP_KERNEL);
+	if (!mcounters)
+		return ERR_PTR(-ENOMEM);
+
+	mutex_init(&mcounters->mcntrs_mutex);
+
+	return &mcounters->ibcntrs;
+}
+
 void mlx5_ib_stage_init_cleanup(struct mlx5_ib_dev *dev)
 {
 	mlx5_ib_cleanup_multiport_master(dev);
@@ -5333,6 +5611,9 @@ int mlx5_ib_stage_caps_init(struct mlx5_ib_dev *dev)
 	dev->ib_dev.destroy_flow_action = mlx5_ib_destroy_flow_action;
 	dev->ib_dev.modify_flow_action_esp = mlx5_ib_modify_flow_action_esp;
 	dev->ib_dev.driver_id = RDMA_DRIVER_MLX5;
+	dev->ib_dev.create_counters = mlx5_ib_create_counters;
+	dev->ib_dev.destroy_counters = mlx5_ib_destroy_counters;
+	dev->ib_dev.read_counters = mlx5_ib_read_counters;
 
 	err = init_node_data(dev);
 	if (err)