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
--- /dev/null
+/*
+ * 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);
#include <linux/list.h>
#include <linux/spinlock.h>
+#include <linux/cgroup_rdma.h>
#include <rdma/ib_verbs.h>
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)
{
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;
}
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;
}
mutex_unlock(&device_mutex);
+ ib_device_unregister_rdmacg(device);
ib_device_unregister_sysfs(device);
ib_cache_cleanup_one(device);
struct ib_udata udata;
struct ib_ucontext *ucontext;
struct file *filp;
+ struct ib_rdmacg_object cg_obj;
int ret;
if (out_len < sizeof resp)
(unsigned long) cmd.response + sizeof resp,
in_len - sizeof cmd, out_len - sizeof resp);
+ ret = ib_rdmacg_try_charge(&cg_obj, ib_dev, RDMACG_RESOURCE_HCA_HANDLE);
+ if (ret)
+ goto err;
+
ucontext = ib_dev->alloc_ucontext(ib_dev, &udata);
if (IS_ERR(ucontext)) {
ret = PTR_ERR(ucontext);
- goto err;
+ goto err_alloc;
}
ucontext->device = ib_dev;
+ ucontext->cg_obj = cg_obj;
INIT_LIST_HEAD(&ucontext->pd_list);
INIT_LIST_HEAD(&ucontext->mr_list);
INIT_LIST_HEAD(&ucontext->mw_list);
put_pid(ucontext->tgid);
ib_dev->dealloc_ucontext(ucontext);
+err_alloc:
+ ib_rdmacg_uncharge(&cg_obj, ib_dev, RDMACG_RESOURCE_HCA_HANDLE);
+
err:
mutex_unlock(&file->mutex);
return ret;
return -ENOMEM;
init_uobj(uobj, 0, file->ucontext, &pd_lock_class);
+ ret = ib_rdmacg_try_charge(&uobj->cg_obj, ib_dev,
+ RDMACG_RESOURCE_HCA_OBJECT);
+ if (ret) {
+ kfree(uobj);
+ return ret;
+ }
+
down_write(&uobj->mutex);
pd = ib_dev->alloc_pd(ib_dev, file->ucontext, &udata);
ib_dealloc_pd(pd);
err:
+ ib_rdmacg_uncharge(&uobj->cg_obj, ib_dev, RDMACG_RESOURCE_HCA_OBJECT);
put_uobj_write(uobj);
return ret;
}
if (ret)
goto err_put;
+ ib_rdmacg_uncharge(&uobj->cg_obj, ib_dev, RDMACG_RESOURCE_HCA_OBJECT);
+
uobj->live = 0;
put_uobj_write(uobj);
goto err_put;
}
}
+ ret = ib_rdmacg_try_charge(&uobj->cg_obj, ib_dev,
+ RDMACG_RESOURCE_HCA_OBJECT);
+ if (ret)
+ goto err_charge;
mr = pd->device->reg_user_mr(pd, cmd.start, cmd.length, cmd.hca_va,
cmd.access_flags, &udata);
ib_dereg_mr(mr);
err_put:
+ ib_rdmacg_uncharge(&uobj->cg_obj, ib_dev, RDMACG_RESOURCE_HCA_OBJECT);
+
+err_charge:
put_pd_read(pd);
err_free:
if (ret)
return ret;
+ ib_rdmacg_uncharge(&uobj->cg_obj, ib_dev, RDMACG_RESOURCE_HCA_OBJECT);
+
idr_remove_uobj(&ib_uverbs_mr_idr, uobj);
mutex_lock(&file->mutex);
in_len - sizeof(cmd) - sizeof(struct ib_uverbs_cmd_hdr),
out_len - sizeof(resp));
+ ret = ib_rdmacg_try_charge(&uobj->cg_obj, ib_dev,
+ RDMACG_RESOURCE_HCA_OBJECT);
+ if (ret)
+ goto err_charge;
+
mw = pd->device->alloc_mw(pd, cmd.mw_type, &udata);
if (IS_ERR(mw)) {
ret = PTR_ERR(mw);
uverbs_dealloc_mw(mw);
err_put:
+ ib_rdmacg_uncharge(&uobj->cg_obj, ib_dev, RDMACG_RESOURCE_HCA_OBJECT);
+
+err_charge:
put_pd_read(pd);
err_free:
if (ret)
return ret;
+ ib_rdmacg_uncharge(&uobj->cg_obj, ib_dev, RDMACG_RESOURCE_HCA_OBJECT);
+
idr_remove_uobj(&ib_uverbs_mw_idr, uobj);
mutex_lock(&file->mutex);
if (cmd_sz > offsetof(typeof(*cmd), flags) + sizeof(cmd->flags))
attr.flags = cmd->flags;
+ ret = ib_rdmacg_try_charge(&obj->uobject.cg_obj, ib_dev,
+ RDMACG_RESOURCE_HCA_OBJECT);
+ if (ret)
+ goto err_charge;
+
cq = ib_dev->create_cq(ib_dev, &attr,
file->ucontext, uhw);
if (IS_ERR(cq)) {
ib_destroy_cq(cq);
err_file:
+ ib_rdmacg_uncharge(&obj->uobject.cg_obj, ib_dev,
+ RDMACG_RESOURCE_HCA_OBJECT);
+
+err_charge:
if (ev_file)
ib_uverbs_release_ucq(file, ev_file, obj);
if (ret)
return ret;
+ ib_rdmacg_uncharge(&uobj->cg_obj, ib_dev, RDMACG_RESOURCE_HCA_OBJECT);
+
idr_remove_uobj(&ib_uverbs_cq_idr, uobj);
mutex_lock(&file->mutex);
goto err_put;
}
+ ret = ib_rdmacg_try_charge(&obj->uevent.uobject.cg_obj, device,
+ RDMACG_RESOURCE_HCA_OBJECT);
+ if (ret)
+ goto err_put;
+
if (cmd->qp_type == IB_QPT_XRC_TGT)
qp = ib_create_qp(pd, &attr);
else
if (IS_ERR(qp)) {
ret = PTR_ERR(qp);
- goto err_put;
+ goto err_create;
}
if (cmd->qp_type != IB_QPT_XRC_TGT) {
err_destroy:
ib_destroy_qp(qp);
+err_create:
+ ib_rdmacg_uncharge(&obj->uevent.uobject.cg_obj, device,
+ RDMACG_RESOURCE_HCA_OBJECT);
+
err_put:
if (xrcd)
put_xrcd_read(xrcd_uobj);
if (ret)
return ret;
+ ib_rdmacg_uncharge(&uobj->cg_obj, ib_dev, RDMACG_RESOURCE_HCA_OBJECT);
+
if (obj->uxrcd)
atomic_dec(&obj->uxrcd->refcnt);
memset(&attr.dmac, 0, sizeof(attr.dmac));
memcpy(attr.grh.dgid.raw, cmd.attr.grh.dgid, 16);
+ ret = ib_rdmacg_try_charge(&uobj->cg_obj, ib_dev,
+ RDMACG_RESOURCE_HCA_OBJECT);
+ if (ret)
+ goto err_charge;
+
ah = pd->device->create_ah(pd, &attr, &udata);
if (IS_ERR(ah)) {
ret = PTR_ERR(ah);
- goto err_put;
+ goto err_create;
}
ah->device = pd->device;
err_destroy:
ib_destroy_ah(ah);
-err_put:
+err_create:
+ ib_rdmacg_uncharge(&uobj->cg_obj, ib_dev, RDMACG_RESOURCE_HCA_OBJECT);
+
+err_charge:
put_pd_read(pd);
err:
if (ret)
return ret;
+ ib_rdmacg_uncharge(&uobj->cg_obj, ib_dev, RDMACG_RESOURCE_HCA_OBJECT);
+
idr_remove_uobj(&ib_uverbs_ah_idr, uobj);
mutex_lock(&file->mutex);
err = -EINVAL;
goto err_free;
}
+
+ err = ib_rdmacg_try_charge(&uobj->cg_obj, ib_dev,
+ RDMACG_RESOURCE_HCA_OBJECT);
+ if (err)
+ goto err_free;
+
flow_id = ib_create_flow(qp, flow_attr, IB_FLOW_DOMAIN_USER);
if (IS_ERR(flow_id)) {
err = PTR_ERR(flow_id);
- goto err_free;
+ goto err_create;
}
flow_id->uobject = uobj;
uobj->object = flow_id;
idr_remove_uobj(&ib_uverbs_rule_idr, uobj);
destroy_flow:
ib_destroy_flow(flow_id);
+err_create:
+ ib_rdmacg_uncharge(&uobj->cg_obj, ib_dev, RDMACG_RESOURCE_HCA_OBJECT);
err_free:
kfree(flow_attr);
err_put:
flow_id = uobj->object;
ret = ib_destroy_flow(flow_id);
- if (!ret)
+ if (!ret) {
+ ib_rdmacg_uncharge(&uobj->cg_obj, ib_dev,
+ RDMACG_RESOURCE_HCA_OBJECT);
uobj->live = 0;
+ }
put_uobj_write(uobj);
obj->uevent.events_reported = 0;
INIT_LIST_HEAD(&obj->uevent.event_list);
+ ret = ib_rdmacg_try_charge(&obj->uevent.uobject.cg_obj, ib_dev,
+ RDMACG_RESOURCE_HCA_OBJECT);
+ if (ret)
+ goto err_put_cq;
+
srq = pd->device->create_srq(pd, &attr, udata);
if (IS_ERR(srq)) {
ret = PTR_ERR(srq);
ib_destroy_srq(srq);
err_put:
+ ib_rdmacg_uncharge(&obj->uevent.uobject.cg_obj, ib_dev,
+ RDMACG_RESOURCE_HCA_OBJECT);
put_pd_read(pd);
err_put_cq:
if (ret)
return ret;
+ ib_rdmacg_uncharge(&uobj->cg_obj, ib_dev, RDMACG_RESOURCE_HCA_OBJECT);
+
if (srq_type == IB_SRQT_XRC) {
us = container_of(obj, struct ib_usrq_object, uevent);
atomic_dec(&us->uxrcd->refcnt);
#include <rdma/ib.h>
#include "uverbs.h"
+#include "core_priv.h"
MODULE_AUTHOR("Roland Dreier");
MODULE_DESCRIPTION("InfiniBand userspace verbs access");
idr_remove_uobj(&ib_uverbs_ah_idr, uobj);
ib_destroy_ah(ah);
+ ib_rdmacg_uncharge(&uobj->cg_obj, context->device,
+ RDMACG_RESOURCE_HCA_OBJECT);
kfree(uobj);
}
idr_remove_uobj(&ib_uverbs_mw_idr, uobj);
uverbs_dealloc_mw(mw);
+ ib_rdmacg_uncharge(&uobj->cg_obj, context->device,
+ RDMACG_RESOURCE_HCA_OBJECT);
kfree(uobj);
}
idr_remove_uobj(&ib_uverbs_rule_idr, uobj);
ib_destroy_flow(flow_id);
+ ib_rdmacg_uncharge(&uobj->cg_obj, context->device,
+ RDMACG_RESOURCE_HCA_OBJECT);
kfree(uobj);
}
if (qp == qp->real_qp)
ib_uverbs_detach_umcast(qp, uqp);
ib_destroy_qp(qp);
+ ib_rdmacg_uncharge(&uobj->cg_obj, context->device,
+ RDMACG_RESOURCE_HCA_OBJECT);
ib_uverbs_release_uevent(file, &uqp->uevent);
kfree(uqp);
}
idr_remove_uobj(&ib_uverbs_srq_idr, uobj);
ib_destroy_srq(srq);
+ ib_rdmacg_uncharge(&uobj->cg_obj, context->device,
+ RDMACG_RESOURCE_HCA_OBJECT);
ib_uverbs_release_uevent(file, uevent);
kfree(uevent);
}
idr_remove_uobj(&ib_uverbs_cq_idr, uobj);
ib_destroy_cq(cq);
+ ib_rdmacg_uncharge(&uobj->cg_obj, context->device,
+ RDMACG_RESOURCE_HCA_OBJECT);
ib_uverbs_release_ucq(file, ev_file, ucq);
kfree(ucq);
}
idr_remove_uobj(&ib_uverbs_mr_idr, uobj);
ib_dereg_mr(mr);
+ ib_rdmacg_uncharge(&uobj->cg_obj, context->device,
+ RDMACG_RESOURCE_HCA_OBJECT);
kfree(uobj);
}
idr_remove_uobj(&ib_uverbs_pd_idr, uobj);
ib_dealloc_pd(pd);
+ ib_rdmacg_uncharge(&uobj->cg_obj, context->device,
+ RDMACG_RESOURCE_HCA_OBJECT);
kfree(uobj);
}
put_pid(context->tgid);
+ ib_rdmacg_uncharge(&context->cg_obj, context->device,
+ RDMACG_RESOURCE_HCA_HANDLE);
+
return context->device->dealloc_ucontext(context);
}
#include <linux/atomic.h>
#include <linux/mmu_notifier.h>
#include <linux/uaccess.h>
+#include <linux/cgroup_rdma.h>
extern struct workqueue_struct *ib_wq;
extern struct workqueue_struct *ib_comp_wq;
struct ib_umem;
+struct ib_rdmacg_object {
+#ifdef CONFIG_CGROUP_RDMA
+ struct rdma_cgroup *cg; /* owner rdma cgroup */
+#endif
+};
+
struct ib_ucontext {
struct ib_device *device;
struct list_head pd_list;
struct list_head no_private_counters;
int odp_mrs_count;
#endif
+
+ struct ib_rdmacg_object cg_obj;
};
struct ib_uobject {
struct ib_ucontext *context; /* associated user context */
void *object; /* containing object */
struct list_head list; /* link to context's list */
+ struct ib_rdmacg_object cg_obj; /* rdmacg object */
int id; /* index into kernel idr */
struct kref ref;
struct rw_semaphore mutex; /* protects .live */
struct attribute_group *hw_stats_ag;
struct rdma_hw_stats *hw_stats;
+#ifdef CONFIG_CGROUP_RDMA
+ struct rdmacg_device cg_device;
+#endif
+
/**
* The following mandatory functions are used only at device
* registration. Keep functions such as these at the end of this