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>

1 files changed, 96 insertions, 6 deletions

diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 700782203483..33bc88a38574 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -316,6 +316,7 @@ ssize_t ib_uverbs_get_context(struct ib_uverbs_file *file,
 	struct ib_udata                   udata;
 	struct ib_ucontext		 *ucontext;
 	struct file			 *filp;
+	struct ib_rdmacg_object		 cg_obj;
 	int ret;
 
 	if (out_len < sizeof resp)
@@ -335,13 +336,18 @@ ssize_t ib_uverbs_get_context(struct ib_uverbs_file *file,
 		   (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);
@@ -407,6 +413,9 @@ err_free:
 	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;
@@ -561,6 +570,13 @@ ssize_t ib_uverbs_alloc_pd(struct ib_uverbs_file *file,
 		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);
@@ -605,6 +621,7 @@ err_idr:
 	ib_dealloc_pd(pd);
 
 err:
+	ib_rdmacg_uncharge(&uobj->cg_obj, ib_dev, RDMACG_RESOURCE_HCA_OBJECT);
 	put_uobj_write(uobj);
 	return ret;
 }
@@ -637,6 +654,8 @@ ssize_t ib_uverbs_dealloc_pd(struct ib_uverbs_file *file,
 	if (ret)
 		goto err_put;
 
+	ib_rdmacg_uncharge(&uobj->cg_obj, ib_dev, RDMACG_RESOURCE_HCA_OBJECT);
+
 	uobj->live = 0;
 	put_uobj_write(uobj);
 
@@ -1006,6 +1025,10 @@ ssize_t ib_uverbs_reg_mr(struct ib_uverbs_file *file,
 			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);
@@ -1054,6 +1077,9 @@ err_unreg:
 	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:
@@ -1178,6 +1204,8 @@ ssize_t ib_uverbs_dereg_mr(struct ib_uverbs_file *file,
 	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);
@@ -1226,6 +1254,11 @@ ssize_t ib_uverbs_alloc_mw(struct ib_uverbs_file *file,
 		   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);
@@ -1271,6 +1304,9 @@ err_unalloc:
 	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:
@@ -1306,6 +1342,8 @@ ssize_t ib_uverbs_dealloc_mw(struct ib_uverbs_file *file,
 	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);
@@ -1405,6 +1443,11 @@ static struct ib_ucq_object *create_cq(struct ib_uverbs_file *file,
 	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)) {
@@ -1452,6 +1495,10 @@ err_free:
 	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);
 
@@ -1732,6 +1779,8 @@ ssize_t ib_uverbs_destroy_cq(struct ib_uverbs_file *file,
 	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);
@@ -1904,6 +1953,11 @@ static int create_qp(struct ib_uverbs_file *file,
 			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
@@ -1911,7 +1965,7 @@ static int create_qp(struct ib_uverbs_file *file,
 
 	if (IS_ERR(qp)) {
 		ret = PTR_ERR(qp);
-		goto err_put;
+		goto err_create;
 	}
 
 	if (cmd->qp_type != IB_QPT_XRC_TGT) {
@@ -1992,6 +2046,10 @@ err_cb:
 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);
@@ -2518,6 +2576,8 @@ ssize_t ib_uverbs_destroy_qp(struct ib_uverbs_file *file,
 	if (ret)
 		return ret;
 
+	ib_rdmacg_uncharge(&uobj->cg_obj, ib_dev, RDMACG_RESOURCE_HCA_OBJECT);
+
 	if (obj->uxrcd)
 		atomic_dec(&obj->uxrcd->refcnt);
 
@@ -2969,11 +3029,16 @@ ssize_t ib_uverbs_create_ah(struct ib_uverbs_file *file,
 	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;
@@ -3012,7 +3077,10 @@ err_copy:
 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:
@@ -3046,6 +3114,8 @@ ssize_t ib_uverbs_destroy_ah(struct ib_uverbs_file *file,
 	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);
@@ -3822,10 +3892,16 @@ int ib_uverbs_ex_create_flow(struct ib_uverbs_file *file,
 		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;
@@ -3858,6 +3934,8 @@ err_copy:
 	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:
@@ -3897,8 +3975,11 @@ int ib_uverbs_ex_destroy_flow(struct ib_uverbs_file *file,
 	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);
 
@@ -3966,6 +4047,11 @@ static int __uverbs_create_xsrq(struct ib_uverbs_file *file,
 	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);
@@ -4030,6 +4116,8 @@ err_destroy:
 	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:
@@ -4216,6 +4304,8 @@ ssize_t ib_uverbs_destroy_srq(struct ib_uverbs_file *file,
 	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);