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

11 files changed, 587 insertions, 41 deletions

diff --git a/drivers/infiniband/core/Makefile b/drivers/infiniband/core/Makefile
index 8d42373..6166770 100644
--- a/drivers/infiniband/core/Makefile
+++ b/drivers/infiniband/core/Makefile
@@ -37,4 +37,4 @@ ib_uverbs-y :=			uverbs_main.o uverbs_cmd.o uverbs_marshall.o \
 				rdma_core.o uverbs_std_types.o uverbs_ioctl.o \
 				uverbs_ioctl_merge.o uverbs_std_types_cq.o \
 				uverbs_std_types_flow_action.o uverbs_std_types_dm.o \
-				uverbs_std_types_mr.o
+				uverbs_std_types_mr.o uverbs_std_types_counters.o
diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h
index cfb5161..c0d40fc 100644
--- a/drivers/infiniband/core/uverbs.h
+++ b/drivers/infiniband/core/uverbs.h
@@ -263,6 +263,7 @@ struct ib_uverbs_flow_spec {
 		struct ib_uverbs_flow_spec_action_tag	flow_tag;
 		struct ib_uverbs_flow_spec_action_drop	drop;
 		struct ib_uverbs_flow_spec_action_handle action;
+		struct ib_uverbs_flow_spec_action_count flow_count;
 	};
 };
 
@@ -287,6 +288,7 @@ extern const struct uverbs_object_def UVERBS_OBJECT(UVERBS_OBJECT_RWQ_IND_TBL);
 extern const struct uverbs_object_def UVERBS_OBJECT(UVERBS_OBJECT_XRCD);
 extern const struct uverbs_object_def UVERBS_OBJECT(UVERBS_OBJECT_FLOW_ACTION);
 extern const struct uverbs_object_def UVERBS_OBJECT(UVERBS_OBJECT_DM);
+extern const struct uverbs_object_def UVERBS_OBJECT(UVERBS_OBJECT_COUNTERS);
 
 #define IB_UVERBS_DECLARE_CMD(name)					\
 	ssize_t ib_uverbs_##name(struct ib_uverbs_file *file,		\
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index e74262e..3179a95 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -2748,43 +2748,82 @@ out_put:
 struct ib_uflow_resources {
 	size_t			max;
 	size_t			num;
-	struct ib_flow_action	*collection[0];
+	size_t			collection_num;
+	size_t			counters_num;
+	struct ib_counters	**counters;
+	struct ib_flow_action	**collection;
 };
 
 static struct ib_uflow_resources *flow_resources_alloc(size_t num_specs)
 {
 	struct ib_uflow_resources *resources;
 
-	resources =
-		kmalloc(sizeof(*resources) +
-			num_specs * sizeof(*resources->collection), GFP_KERNEL);
+	resources = kzalloc(sizeof(*resources), GFP_KERNEL);
 
 	if (!resources)
-		return NULL;
+		goto err_res;
+
+	resources->counters =
+		kcalloc(num_specs, sizeof(*resources->counters), GFP_KERNEL);
+
+	if (!resources->counters)
+		goto err_cnt;
+
+	resources->collection =
+		kcalloc(num_specs, sizeof(*resources->collection), GFP_KERNEL);
+
+	if (!resources->collection)
+		goto err_collection;
 
-	resources->num = 0;
 	resources->max = num_specs;
 
 	return resources;
+
+err_collection:
+	kfree(resources->counters);
+err_cnt:
+	kfree(resources);
+err_res:
+	return NULL;
 }
 
 void ib_uverbs_flow_resources_free(struct ib_uflow_resources *uflow_res)
 {
 	unsigned int i;
 
-	for (i = 0; i < uflow_res->num; i++)
+	for (i = 0; i < uflow_res->collection_num; i++)
 		atomic_dec(&uflow_res->collection[i]->usecnt);
 
+	for (i = 0; i < uflow_res->counters_num; i++)
+		atomic_dec(&uflow_res->counters[i]->usecnt);
+
+	kfree(uflow_res->collection);
+	kfree(uflow_res->counters);
 	kfree(uflow_res);
 }
 
 static void flow_resources_add(struct ib_uflow_resources *uflow_res,
-			       struct ib_flow_action *action)
+			       enum ib_flow_spec_type type,
+			       void *ibobj)
 {
 	WARN_ON(uflow_res->num >= uflow_res->max);
 
-	atomic_inc(&action->usecnt);
-	uflow_res->collection[uflow_res->num++] = action;
+	switch (type) {
+	case IB_FLOW_SPEC_ACTION_HANDLE:
+		atomic_inc(&((struct ib_flow_action *)ibobj)->usecnt);
+		uflow_res->collection[uflow_res->collection_num++] =
+			(struct ib_flow_action *)ibobj;
+		break;
+	case IB_FLOW_SPEC_ACTION_COUNT:
+		atomic_inc(&((struct ib_counters *)ibobj)->usecnt);
+		uflow_res->counters[uflow_res->counters_num++] =
+			(struct ib_counters *)ibobj;
+		break;
+	default:
+		WARN_ON(1);
+	}
+
+	uflow_res->num++;
 }
 
 static int kern_spec_to_ib_spec_action(struct ib_ucontext *ucontext,
@@ -2821,9 +2860,29 @@ static int kern_spec_to_ib_spec_action(struct ib_ucontext *ucontext,
 			return -EINVAL;
 		ib_spec->action.size =
 			sizeof(struct ib_flow_spec_action_handle);
-		flow_resources_add(uflow_res, ib_spec->action.act);
+		flow_resources_add(uflow_res,
+				   IB_FLOW_SPEC_ACTION_HANDLE,
+				   ib_spec->action.act);
 		uobj_put_obj_read(ib_spec->action.act);
 		break;
+	case IB_FLOW_SPEC_ACTION_COUNT:
+		if (kern_spec->flow_count.size !=
+			sizeof(struct ib_uverbs_flow_spec_action_count))
+			return -EINVAL;
+		ib_spec->flow_count.counters =
+			uobj_get_obj_read(counters,
+					  UVERBS_OBJECT_COUNTERS,
+					  kern_spec->flow_count.handle,
+					  ucontext);
+		if (!ib_spec->flow_count.counters)
+			return -EINVAL;
+		ib_spec->flow_count.size =
+				sizeof(struct ib_flow_spec_action_count);
+		flow_resources_add(uflow_res,
+				   IB_FLOW_SPEC_ACTION_COUNT,
+				   ib_spec->flow_count.counters);
+		uobj_put_obj_read(ib_spec->flow_count.counters);
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -3542,11 +3601,16 @@ int ib_uverbs_ex_create_flow(struct ib_uverbs_file *file,
 		err = -EINVAL;
 		goto err_free;
 	}
-	flow_id = ib_create_flow(qp, flow_attr, IB_FLOW_DOMAIN_USER);
+
+	flow_id = qp->device->create_flow(qp, flow_attr,
+					  IB_FLOW_DOMAIN_USER, uhw);
+
 	if (IS_ERR(flow_id)) {
 		err = PTR_ERR(flow_id);
 		goto err_free;
 	}
+	atomic_inc(&qp->usecnt);
+	flow_id->qp = qp;
 	flow_id->uobject = uobj;
 	uobj->object = flow_id;
 	uflow = container_of(uobj, typeof(*uflow), uobject);
diff --git a/drivers/infiniband/core/uverbs_std_types.c b/drivers/infiniband/core/uverbs_std_types.c
index 569f48bd..b570acb 100644
--- a/drivers/infiniband/core/uverbs_std_types.c
+++ b/drivers/infiniband/core/uverbs_std_types.c
@@ -302,7 +302,8 @@ static DECLARE_UVERBS_OBJECT_TREE(uverbs_default_objects,
 				  &UVERBS_OBJECT(UVERBS_OBJECT_RWQ_IND_TBL),
 				  &UVERBS_OBJECT(UVERBS_OBJECT_XRCD),
 				  &UVERBS_OBJECT(UVERBS_OBJECT_FLOW_ACTION),
-				  &UVERBS_OBJECT(UVERBS_OBJECT_DM));
+				  &UVERBS_OBJECT(UVERBS_OBJECT_DM),
+				  &UVERBS_OBJECT(UVERBS_OBJECT_COUNTERS));
 
 const struct uverbs_object_tree_def *uverbs_default_get_objects(void)
 {
diff --git a/drivers/infiniband/core/uverbs_std_types_counters.c b/drivers/infiniband/core/uverbs_std_types_counters.c
new file mode 100644
index 0000000..03b182a
--- /dev/null
+++ b/drivers/infiniband/core/uverbs_std_types_counters.c
@@ -0,0 +1,157 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * Copyright (c) 2018, Mellanox Technologies inc.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include "uverbs.h"
+#include <rdma/uverbs_std_types.h>
+
+static int uverbs_free_counters(struct ib_uobject *uobject,
+				enum rdma_remove_reason why)
+{
+	struct ib_counters *counters = uobject->object;
+
+	if (why == RDMA_REMOVE_DESTROY &&
+	    atomic_read(&counters->usecnt))
+		return -EBUSY;
+
+	return counters->device->destroy_counters(counters);
+}
+
+static int UVERBS_HANDLER(UVERBS_METHOD_COUNTERS_CREATE)(struct ib_device *ib_dev,
+							 struct ib_uverbs_file *file,
+							 struct uverbs_attr_bundle *attrs)
+{
+	struct ib_counters *counters;
+	struct ib_uobject *uobj;
+	int ret;
+
+	/*
+	 * This check should be removed once the infrastructure
+	 * have the ability to remove methods from parse tree once
+	 * such condition is met.
+	 */
+	if (!ib_dev->create_counters)
+		return -EOPNOTSUPP;
+
+	uobj = uverbs_attr_get_uobject(attrs, UVERBS_ATTR_CREATE_COUNTERS_HANDLE);
+	counters = ib_dev->create_counters(ib_dev, attrs);
+	if (IS_ERR(counters)) {
+		ret = PTR_ERR(counters);
+		goto err_create_counters;
+	}
+
+	counters->device = ib_dev;
+	counters->uobject = uobj;
+	uobj->object = counters;
+	atomic_set(&counters->usecnt, 0);
+
+	return 0;
+
+err_create_counters:
+	return ret;
+}
+
+static int UVERBS_HANDLER(UVERBS_METHOD_COUNTERS_READ)(struct ib_device *ib_dev,
+						       struct ib_uverbs_file *file,
+						       struct uverbs_attr_bundle *attrs)
+{
+	struct ib_counters_read_attr read_attr = {};
+	const struct uverbs_attr *uattr;
+	struct ib_counters *counters =
+		uverbs_attr_get_obj(attrs, UVERBS_ATTR_READ_COUNTERS_HANDLE);
+	int ret;
+
+	if (!ib_dev->read_counters)
+		return -EOPNOTSUPP;
+
+	if (!atomic_read(&counters->usecnt))
+		return -EINVAL;
+
+	ret = uverbs_copy_from(&read_attr.flags, attrs,
+			       UVERBS_ATTR_READ_COUNTERS_FLAGS);
+	if (ret)
+		return ret;
+
+	uattr = uverbs_attr_get(attrs, UVERBS_ATTR_READ_COUNTERS_BUFF);
+	read_attr.ncounters = uattr->ptr_attr.len / sizeof(u64);
+	read_attr.counters_buff = kcalloc(read_attr.ncounters,
+					  sizeof(u64), GFP_KERNEL);
+	if (!read_attr.counters_buff)
+		return -ENOMEM;
+
+	ret = ib_dev->read_counters(counters,
+				    &read_attr,
+				    attrs);
+	if (ret)
+		goto err_read;
+
+	ret = uverbs_copy_to(attrs, UVERBS_ATTR_READ_COUNTERS_BUFF,
+			     read_attr.counters_buff,
+			     read_attr.ncounters * sizeof(u64));
+
+err_read:
+	kfree(read_attr.counters_buff);
+	return ret;
+}
+
+static DECLARE_UVERBS_NAMED_METHOD(UVERBS_METHOD_COUNTERS_CREATE,
+	&UVERBS_ATTR_IDR(UVERBS_ATTR_CREATE_COUNTERS_HANDLE,
+			 UVERBS_OBJECT_COUNTERS,
+			 UVERBS_ACCESS_NEW,
+			 UA_FLAGS(UVERBS_ATTR_SPEC_F_MANDATORY)));
+
+static DECLARE_UVERBS_NAMED_METHOD_WITH_HANDLER(UVERBS_METHOD_COUNTERS_DESTROY,
+	uverbs_destroy_def_handler,
+	&UVERBS_ATTR_IDR(UVERBS_ATTR_DESTROY_COUNTERS_HANDLE,
+			 UVERBS_OBJECT_COUNTERS,
+			 UVERBS_ACCESS_DESTROY,
+			 UA_FLAGS(UVERBS_ATTR_SPEC_F_MANDATORY)));
+
+#define MAX_COUNTERS_BUFF_SIZE USHRT_MAX
+static DECLARE_UVERBS_NAMED_METHOD(UVERBS_METHOD_COUNTERS_READ,
+	&UVERBS_ATTR_IDR(UVERBS_ATTR_READ_COUNTERS_HANDLE,
+			 UVERBS_OBJECT_COUNTERS,
+			 UVERBS_ACCESS_READ,
+			 UA_FLAGS(UVERBS_ATTR_SPEC_F_MANDATORY)),
+	&UVERBS_ATTR_PTR_OUT(UVERBS_ATTR_READ_COUNTERS_BUFF,
+			     UVERBS_ATTR_SIZE(0, MAX_COUNTERS_BUFF_SIZE),
+			     UA_FLAGS(UVERBS_ATTR_SPEC_F_MANDATORY)),
+	&UVERBS_ATTR_PTR_IN(UVERBS_ATTR_READ_COUNTERS_FLAGS,
+			    UVERBS_ATTR_TYPE(__u32),
+			    UA_FLAGS(UVERBS_ATTR_SPEC_F_MANDATORY)));
+
+DECLARE_UVERBS_NAMED_OBJECT(UVERBS_OBJECT_COUNTERS,
+			    &UVERBS_TYPE_ALLOC_IDR(0, uverbs_free_counters),
+			    &UVERBS_METHOD(UVERBS_METHOD_COUNTERS_CREATE),
+			    &UVERBS_METHOD(UVERBS_METHOD_COUNTERS_DESTROY),
+			    &UVERBS_METHOD(UVERBS_METHOD_COUNTERS_READ));
+
diff --git a/drivers/infiniband/core/uverbs_std_types_cq.c b/drivers/infiniband/core/uverbs_std_types_cq.c
index b0dbae9..3d293d0 100644
--- a/drivers/infiniband/core/uverbs_std_types_cq.c
+++ b/drivers/infiniband/core/uverbs_std_types_cq.c
@@ -65,7 +65,6 @@ static int UVERBS_HANDLER(UVERBS_METHOD_CQ_CREATE)(struct ib_device *ib_dev,
 	struct ib_cq_init_attr attr = {};
 	struct ib_cq                   *cq;
 	struct ib_uverbs_completion_event_file    *ev_file = NULL;
-	const struct uverbs_attr *ev_file_attr;
 	struct ib_uobject *ev_file_uobj;
 
 	if (!(ib_dev->uverbs_cmd_mask & 1ULL << IB_USER_VERBS_CMD_CREATE_CQ))
@@ -87,10 +86,8 @@ static int UVERBS_HANDLER(UVERBS_METHOD_CQ_CREATE)(struct ib_device *ib_dev,
 						UVERBS_ATTR_CREATE_CQ_FLAGS)))
 		return -EFAULT;
 
-	ev_file_attr = uverbs_attr_get(attrs, UVERBS_ATTR_CREATE_CQ_COMP_CHANNEL);
-	if (!IS_ERR(ev_file_attr)) {
-		ev_file_uobj = ev_file_attr->obj_attr.uobject;
-
+	ev_file_uobj = uverbs_attr_get_uobject(attrs, UVERBS_ATTR_CREATE_CQ_COMP_CHANNEL);
+	if (!IS_ERR(ev_file_uobj)) {
 		ev_file = container_of(ev_file_uobj,
 				       struct ib_uverbs_completion_event_file,
 				       uobj_file.uobj);
@@ -102,8 +99,8 @@ static int UVERBS_HANDLER(UVERBS_METHOD_CQ_CREATE)(struct ib_device *ib_dev,
 		goto err_event_file;
 	}
 
-	obj = container_of(uverbs_attr_get(attrs,
-					   UVERBS_ATTR_CREATE_CQ_HANDLE)->obj_attr.uobject,
+	obj = container_of(uverbs_attr_get_uobject(attrs,
+						   UVERBS_ATTR_CREATE_CQ_HANDLE),
 			   typeof(*obj), uobject);
 	obj->uverbs_file	   = ucontext->ufile;
 	obj->comp_events_reported  = 0;
@@ -170,13 +167,17 @@ static int UVERBS_HANDLER(UVERBS_METHOD_CQ_DESTROY)(struct ib_device *ib_dev,
 						    struct ib_uverbs_file *file,
 						    struct uverbs_attr_bundle *attrs)
 {
-	struct ib_uverbs_destroy_cq_resp resp;
 	struct ib_uobject *uobj =
-		uverbs_attr_get(attrs, UVERBS_ATTR_DESTROY_CQ_HANDLE)->obj_attr.uobject;
-	struct ib_ucq_object *obj = container_of(uobj, struct ib_ucq_object,
-						 uobject);
+		uverbs_attr_get_uobject(attrs, UVERBS_ATTR_DESTROY_CQ_HANDLE);
+	struct ib_uverbs_destroy_cq_resp resp;
+	struct ib_ucq_object *obj;
 	int ret;
 
+	if (IS_ERR(uobj))
+		return PTR_ERR(uobj);
+
+	obj = container_of(uobj, struct ib_ucq_object, uobject);
+
 	if (!(ib_dev->uverbs_cmd_mask & 1ULL << IB_USER_VERBS_CMD_DESTROY_CQ))
 		return -EOPNOTSUPP;
 
diff --git a/drivers/infiniband/core/uverbs_std_types_flow_action.c b/drivers/infiniband/core/uverbs_std_types_flow_action.c
index b4f016d..a7be51c 100644
--- a/drivers/infiniband/core/uverbs_std_types_flow_action.c
+++ b/drivers/infiniband/core/uverbs_std_types_flow_action.c
@@ -320,7 +320,7 @@ static int UVERBS_HANDLER(UVERBS_METHOD_FLOW_ACTION_ESP_CREATE)(struct ib_device
 		return ret;
 
 	/* No need to check as this attribute is marked as MANDATORY */
-	uobj = uverbs_attr_get(attrs, UVERBS_ATTR_FLOW_ACTION_ESP_HANDLE)->obj_attr.uobject;
+	uobj = uverbs_attr_get_uobject(attrs, UVERBS_ATTR_FLOW_ACTION_ESP_HANDLE);
 	action = ib_dev->create_flow_action_esp(ib_dev, &esp_attr.hdr, attrs);
 	if (IS_ERR(action))
 		return PTR_ERR(action);
@@ -350,7 +350,7 @@ static int UVERBS_HANDLER(UVERBS_METHOD_FLOW_ACTION_ESP_MODIFY)(struct ib_device
 	if (ret)
 		return ret;
 
-	uobj = uverbs_attr_get(attrs, UVERBS_ATTR_FLOW_ACTION_ESP_HANDLE)->obj_attr.uobject;
+	uobj = uverbs_attr_get_uobject(attrs, UVERBS_ATTR_FLOW_ACTION_ESP_HANDLE);
 	action = uobj->object;
 
 	if (action->type != IB_FLOW_ACTION_ESP)
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index 6ddfb1f..0b56828 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1983,7 +1983,7 @@ struct ib_flow *ib_create_flow(struct ib_qp *qp,
 	if (!qp->device->create_flow)
 		return ERR_PTR(-EOPNOTSUPP);
 
-	flow_id = qp->device->create_flow(qp, flow_attr, domain);
+	flow_id = qp->device->create_flow(qp, flow_attr, domain, NULL);
 	if (!IS_ERR(flow_id)) {
 		atomic_inc(&qp->usecnt);
 		flow_id->qp = qp;
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 722c825..f839bf3 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -1808,7 +1808,7 @@ static int mlx4_ib_add_dont_trap_rule(struct mlx4_dev *dev,
 
 static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp,
 				    struct ib_flow_attr *flow_attr,
-				    int domain)
+				    int domain, struct ib_udata *udata)
 {
 	int err = 0, i = 0, j = 0;
 	struct mlx4_ib_flow *mflow;
@@ -1826,6 +1826,10 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp,
 	    (flow_attr->type != IB_FLOW_ATTR_NORMAL))
 		return ERR_PTR(-EOPNOTSUPP);
 
+	if (udata &&
+	    udata->inlen && !ib_is_udata_cleared(udata, 0, udata->inlen))
+		return ERR_PTR(-EOPNOTSUPP);
+
 	memset(type, 0, sizeof(type));
 
 	mflow = kzalloc(sizeof(*mflow), GFP_KERNEL);
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 0541581..3544150 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)
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 49a1aa0..d89c8fe 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -175,6 +175,7 @@ struct mlx5_ib_flow_handler {
 	struct ib_flow			ibflow;
 	struct mlx5_ib_flow_prio	*prio;
 	struct mlx5_flow_handle		*rule;
+	struct ib_counters		*ibcounters;
 };
 
 struct mlx5_ib_flow_db {
@@ -813,6 +814,41 @@ struct mlx5_memic {
 	DECLARE_BITMAP(memic_alloc_pages, MLX5_MAX_MEMIC_PAGES);
 };
 
+struct mlx5_read_counters_attr {
+	struct mlx5_fc *hw_cntrs_hndl;
+	u64 *out;
+	u32 flags;
+};
+
+enum mlx5_ib_counters_type {
+	MLX5_IB_COUNTERS_FLOW,
+};
+
+struct mlx5_ib_mcounters {
+	struct ib_counters ibcntrs;
+	enum mlx5_ib_counters_type type;
+	/* number of counters supported for this counters type */
+	u32 counters_num;
+	struct mlx5_fc *hw_cntrs_hndl;
+	/* read function for this counters type */
+	int (*read_counters)(struct ib_device *ibdev,
+			     struct mlx5_read_counters_attr *read_attr);
+	/* max index set as part of create_flow */
+	u32 cntrs_max_index;
+	/* number of counters data entries (<description,index> pair) */
+	u32 ncounters;
+	/* counters data array for descriptions and indexes */
+	struct mlx5_ib_flow_counters_desc *counters_data;
+	/* protects access to mcounters internal data */
+	struct mutex mcntrs_mutex;
+};
+
+static inline struct mlx5_ib_mcounters *
+to_mcounters(struct ib_counters *ibcntrs)
+{
+	return container_of(ibcntrs, struct mlx5_ib_mcounters, ibcntrs);
+}
+
 struct mlx5_ib_dev {
 	struct ib_device		ib_dev;
 	struct mlx5_core_dev		*mdev;