IB/core: added support to use rdma cgroup controller

Added support APIs for IB core to register/unregister every IB/RDMA
device with rdma cgroup for tracking rdma resources.
IB core registers with rdma cgroup controller.
Added support APIs for uverbs layer to make use of rdma controller.
Added uverbs layer to perform resource charge/uncharge functionality.
Added support during query_device uverb operation to ensure it
returns resource limits by honoring rdma cgroup configured limits.

Signed-off-by: Parav Pandit <pandit.parav@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

drivers/infiniband/core/Makefile

@@ -13,6 +13,7 @@ ib_core-y :=			packer.o ud_header.o verbs.o cq.o rw.o sysfs.o \
 				multicast.o mad.o smi.o agent.o mad_rmpp.o
 ib_core-$(CONFIG_INFINIBAND_USER_MEM) += umem.o
 ib_core-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += umem_odp.o umem_rbtree.o
+ib_core-$(CONFIG_CGROUP_RDMA) += cgroup.o
 
 ib_cm-y :=			cm.o
 

drivers/infiniband/core/cgroup.c

@@ -0,0 +1,62 @@
+/*
+ * Copyright (C) 2016 Parav Pandit <pandit.parav@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#include "core_priv.h"
+
+/**
+ * ib_device_register_rdmacg - register with rdma cgroup.
+ * @device: device to register to participate in resource
+ *          accounting by rdma cgroup.
+ *
+ * Register with the rdma cgroup. Should be called before
+ * exposing rdma device to user space applications to avoid
+ * resource accounting leak.
+ * Returns 0 on success or otherwise failure code.
+ */
+int ib_device_register_rdmacg(struct ib_device *device)
+{
+	device->cg_device.name = device->name;
+	return rdmacg_register_device(&device->cg_device);
+}
+
+/**
+ * ib_device_unregister_rdmacg - unregister with rdma cgroup.
+ * @device: device to unregister.
+ *
+ * Unregister with the rdma cgroup. Should be called after
+ * all the resources are deallocated, and after a stage when any
+ * other resource allocation by user application cannot be done
+ * for this device to avoid any leak in accounting.
+ */
+void ib_device_unregister_rdmacg(struct ib_device *device)
+{
+	rdmacg_unregister_device(&device->cg_device);
+}
+
+int ib_rdmacg_try_charge(struct ib_rdmacg_object *cg_obj,
+			 struct ib_device *device,
+			 enum rdmacg_resource_type resource_index)
+{
+	return rdmacg_try_charge(&cg_obj->cg, &device->cg_device,
+				 resource_index);
+}
+EXPORT_SYMBOL(ib_rdmacg_try_charge);
+
+void ib_rdmacg_uncharge(struct ib_rdmacg_object *cg_obj,
+			struct ib_device *device,
+			enum rdmacg_resource_type resource_index)
+{
+	rdmacg_uncharge(cg_obj->cg, &device->cg_device,
+			resource_index);
+}
+EXPORT_SYMBOL(ib_rdmacg_uncharge);

drivers/infiniband/core/core_priv.h

@@ -35,6 +35,7 @@
 
 #include <linux/list.h>
 #include <linux/spinlock.h>
+#include <linux/cgroup_rdma.h>
 
 #include <rdma/ib_verbs.h>
 
@@ -121,6 +122,35 @@ int ib_cache_setup_one(struct ib_device *device);
 void ib_cache_cleanup_one(struct ib_device *device);
 void ib_cache_release_one(struct ib_device *device);
 
+#ifdef CONFIG_CGROUP_RDMA
+int ib_device_register_rdmacg(struct ib_device *device);
+void ib_device_unregister_rdmacg(struct ib_device *device);
+
+int ib_rdmacg_try_charge(struct ib_rdmacg_object *cg_obj,
+			 struct ib_device *device,
+			 enum rdmacg_resource_type resource_index);
+
+void ib_rdmacg_uncharge(struct ib_rdmacg_object *cg_obj,
+			struct ib_device *device,
+			enum rdmacg_resource_type resource_index);
+#else
+static inline int ib_device_register_rdmacg(struct ib_device *device)
+{ return 0; }
+
+static inline void ib_device_unregister_rdmacg(struct ib_device *device)
+{ }
+
+static inline int ib_rdmacg_try_charge(struct ib_rdmacg_object *cg_obj,
+				       struct ib_device *device,
+				       enum rdmacg_resource_type resource_index)
+{ return 0; }
+
+static inline void ib_rdmacg_uncharge(struct ib_rdmacg_object *cg_obj,
+				      struct ib_device *device,
+				      enum rdmacg_resource_type resource_index)
+{ }
+#endif
+
 static inline bool rdma_is_upper_dev_rcu(struct net_device *dev,
 					 struct net_device *upper)
 {

drivers/infiniband/core/device.c

@@ -360,10 +360,18 @@ int ib_register_device(struct ib_device *device,
 		goto out;
 	}
 
+	ret = ib_device_register_rdmacg(device);
+	if (ret) {
+		pr_warn("Couldn't register device with rdma cgroup\n");
+		ib_cache_cleanup_one(device);
+		goto out;
+	}
+
 	memset(&device->attrs, 0, sizeof(device->attrs));
 	ret = device->query_device(device, &device->attrs, &uhw);
 	if (ret) {
 		pr_warn("Couldn't query the device attributes\n");
+		ib_device_unregister_rdmacg(device);
 		ib_cache_cleanup_one(device);
 		goto out;
 	}
@@ -372,6 +380,7 @@ int ib_register_device(struct ib_device *device,
 	if (ret) {
 		pr_warn("Couldn't register device %s with driver model\n",
 			device->name);
+		ib_device_unregister_rdmacg(device);
 		ib_cache_cleanup_one(device);
 		goto out;
 	}
@@ -421,6 +430,7 @@ void ib_unregister_device(struct ib_device *device)
 
 	mutex_unlock(&device_mutex);
 
+	ib_device_unregister_rdmacg(device);
 	ib_device_unregister_sysfs(device);
 	ib_cache_cleanup_one(device);