diff --git a/Documentation/cgroup-v1/rdma.txt b/Documentation/cgroup-v1/rdma.txt new file mode 100644 index 000000000000..af618171e0eb --- /dev/null +++ b/Documentation/cgroup-v1/rdma.txt @@ -0,0 +1,109 @@ + RDMA Controller + ---------------- + +Contents +-------- + +1. Overview + 1-1. What is RDMA controller? + 1-2. Why RDMA controller needed? + 1-3. How is RDMA controller implemented? +2. Usage Examples + +1. Overview + +1-1. What is RDMA controller? +----------------------------- + +RDMA controller allows user to limit RDMA/IB specific resources that a given +set of processes can use. These processes are grouped using RDMA controller. + +RDMA controller defines two resources which can be limited for processes of a +cgroup. + +1-2. Why RDMA controller needed? +-------------------------------- + +Currently user space applications can easily take away all the rdma verb +specific resources such as AH, CQ, QP, MR etc. Due to which other applications +in other cgroup or kernel space ULPs may not even get chance to allocate any +rdma resources. This can leads to service unavailability. + +Therefore RDMA controller is needed through which resource consumption +of processes can be limited. Through this controller different rdma +resources can be accounted. + +1-3. How is RDMA controller implemented? +---------------------------------------- + +RDMA cgroup allows limit configuration of resources. Rdma cgroup maintains +resource accounting per cgroup, per device using resource pool structure. +Each such resource pool is limited up to 64 resources in given resource pool +by rdma cgroup, which can be extended later if required. + +This resource pool object is linked to the cgroup css. Typically there +are 0 to 4 resource pool instances per cgroup, per device in most use cases. +But nothing limits to have it more. At present hundreds of RDMA devices per +single cgroup may not be handled optimally, however there is no +known use case or requirement for such configuration either. + +Since RDMA resources can be allocated from any process and can be freed by any +of the child processes which shares the address space, rdma resources are +always owned by the creator cgroup css. This allows process migration from one +to other cgroup without major complexity of transferring resource ownership; +because such ownership is not really present due to shared nature of +rdma resources. Linking resources around css also ensures that cgroups can be +deleted after processes migrated. This allow progress migration as well with +active resources, even though that is not a primary use case. + +Whenever RDMA resource charging occurs, owner rdma cgroup is returned to +the caller. Same rdma cgroup should be passed while uncharging the resource. +This also allows process migrated with active RDMA resource to charge +to new owner cgroup for new resource. It also allows to uncharge resource of +a process from previously charged cgroup which is migrated to new cgroup, +even though that is not a primary use case. + +Resource pool object is created in following situations. +(a) User sets the limit and no previous resource pool exist for the device +of interest for the cgroup. +(b) No resource limits were configured, but IB/RDMA stack tries to +charge the resource. So that it correctly uncharge them when applications are +running without limits and later on when limits are enforced during uncharging, +otherwise usage count will drop to negative. + +Resource pool is destroyed if all the resource limits are set to max and +it is the last resource getting deallocated. + +User should set all the limit to max value if it intents to remove/unconfigure +the resource pool for a particular device. + +IB stack honors limits enforced by the rdma controller. When application +query about maximum resource limits of IB device, it returns minimum of +what is configured by user for a given cgroup and what is supported by +IB device. + +Following resources can be accounted by rdma controller. + hca_handle Maximum number of HCA Handles + hca_object Maximum number of HCA Objects + +2. Usage Examples +----------------- + +(a) Configure resource limit: +echo mlx4_0 hca_handle=2 hca_object=2000 > /sys/fs/cgroup/rdma/1/rdma.max +echo ocrdma1 hca_handle=3 > /sys/fs/cgroup/rdma/2/rdma.max + +(b) Query resource limit: +cat /sys/fs/cgroup/rdma/2/rdma.max +#Output: +mlx4_0 hca_handle=2 hca_object=2000 +ocrdma1 hca_handle=3 hca_object=max + +(c) Query current usage: +cat /sys/fs/cgroup/rdma/2/rdma.current +#Output: +mlx4_0 hca_handle=1 hca_object=20 +ocrdma1 hca_handle=1 hca_object=23 + +(d) Delete resource limit: +echo echo mlx4_0 hca_handle=max hca_object=max > /sys/fs/cgroup/rdma/1/rdma.max diff --git a/Documentation/cgroup-v2.txt b/Documentation/cgroup-v2.txt index 1d101423ca92..3b8449f8ac7e 100644 --- a/Documentation/cgroup-v2.txt +++ b/Documentation/cgroup-v2.txt @@ -49,8 +49,10 @@ CONTENTS 5-3-2. Writeback 5-4. PID 5-4-1. PID Interface Files - 5-5. Misc - 5-5-1. perf_event + 5-5. RDMA + 5-5-1. RDMA Interface Files + 5-6. Misc + 5-6-1. perf_event 6. Namespace 6-1. Basics 6-2. The Root and Views @@ -1160,9 +1162,45 @@ through fork() or clone(). These will return -EAGAIN if the creation of a new process would cause a cgroup policy to be violated. -5-5. Misc +5-5. RDMA -5-5-1. perf_event +The "rdma" controller regulates the distribution and accounting of +of RDMA resources. + +5-5-1. RDMA Interface Files + + rdma.max + A readwrite nested-keyed file that exists for all the cgroups + except root that describes current configured resource limit + for a RDMA/IB device. + + Lines are keyed by device name and are not ordered. + Each line contains space separated resource name and its configured + limit that can be distributed. + + The following nested keys are defined. + + hca_handle Maximum number of HCA Handles + hca_object Maximum number of HCA Objects + + An example for mlx4 and ocrdma device follows. + + mlx4_0 hca_handle=2 hca_object=2000 + ocrdma1 hca_handle=3 hca_object=max + + rdma.current + A read-only file that describes current resource usage. + It exists for all the cgroup except root. + + An example for mlx4 and ocrdma device follows. + + mlx4_0 hca_handle=1 hca_object=20 + ocrdma1 hca_handle=1 hca_object=23 + + +5-6. Misc + +5-6-1. perf_event perf_event controller, if not mounted on a legacy hierarchy, is automatically enabled on the v2 hierarchy so that perf events can diff --git a/drivers/infiniband/core/Makefile b/drivers/infiniband/core/Makefile index edaae9f9853c..e426ac877d19 100644 --- a/drivers/infiniband/core/Makefile +++ b/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 diff --git a/drivers/infiniband/core/cgroup.c b/drivers/infiniband/core/cgroup.c new file mode 100644 index 000000000000..126ac5f99db7 --- /dev/null +++ b/drivers/infiniband/core/cgroup.c @@ -0,0 +1,62 @@ +/* + * Copyright (C) 2016 Parav Pandit + * + * 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); diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h index d29372624f3a..389f6192bddc 100644 --- a/drivers/infiniband/core/core_priv.h +++ b/drivers/infiniband/core/core_priv.h @@ -35,6 +35,7 @@ #include #include +#include #include @@ -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) { diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 571974cd3919..70065386acbc 100644 --- a/drivers/infiniband/core/device.c +++ b/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); 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); diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index b3f95d453fba..cdbd26d6574b 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -51,6 +51,7 @@ #include #include "uverbs.h" +#include "core_priv.h" MODULE_AUTHOR("Roland Dreier"); MODULE_DESCRIPTION("InfiniBand userspace verbs access"); @@ -237,6 +238,8 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file, 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); } @@ -246,6 +249,8 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file, 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); } @@ -254,6 +259,8 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file, 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); } @@ -266,6 +273,8 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file, 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); } @@ -298,6 +307,8 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file, 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); } @@ -310,6 +321,8 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file, 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); } @@ -319,6 +332,8 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file, 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); } @@ -339,11 +354,16 @@ static int ib_uverbs_cleanup_ucontext(struct ib_uverbs_file *file, 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); } diff --git a/include/linux/cgroup_rdma.h b/include/linux/cgroup_rdma.h new file mode 100644 index 000000000000..e94290b29e99 --- /dev/null +++ b/include/linux/cgroup_rdma.h @@ -0,0 +1,53 @@ +/* + * Copyright (C) 2016 Parav Pandit + * + * This file is subject to the terms and conditions of version 2 of the GNU + * General Public License. See the file COPYING in the main directory of the + * Linux distribution for more details. + */ + +#ifndef _CGROUP_RDMA_H +#define _CGROUP_RDMA_H + +#include + +enum rdmacg_resource_type { + RDMACG_RESOURCE_HCA_HANDLE, + RDMACG_RESOURCE_HCA_OBJECT, + RDMACG_RESOURCE_MAX, +}; + +#ifdef CONFIG_CGROUP_RDMA + +struct rdma_cgroup { + struct cgroup_subsys_state css; + + /* + * head to keep track of all resource pools + * that belongs to this cgroup. + */ + struct list_head rpools; +}; + +struct rdmacg_device { + struct list_head dev_node; + struct list_head rpools; + char *name; +}; + +/* + * APIs for RDMA/IB stack to publish when a device wants to + * participate in resource accounting + */ +int rdmacg_register_device(struct rdmacg_device *device); +void rdmacg_unregister_device(struct rdmacg_device *device); + +/* APIs for RDMA/IB stack to charge/uncharge pool specific resources */ +int rdmacg_try_charge(struct rdma_cgroup **rdmacg, + struct rdmacg_device *device, + enum rdmacg_resource_type index); +void rdmacg_uncharge(struct rdma_cgroup *cg, + struct rdmacg_device *device, + enum rdmacg_resource_type index); +#endif /* CONFIG_CGROUP_RDMA */ +#endif /* _CGROUP_RDMA_H */ diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h index 0df0336acee9..d0e597c44585 100644 --- a/include/linux/cgroup_subsys.h +++ b/include/linux/cgroup_subsys.h @@ -56,6 +56,10 @@ SUBSYS(hugetlb) SUBSYS(pids) #endif +#if IS_ENABLED(CONFIG_CGROUP_RDMA) +SUBSYS(rdma) +#endif + /* * The following subsystems are not supported on the default hierarchy. */ diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 958a24d8fae7..63896a477896 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -60,6 +60,7 @@ #include #include #include +#include extern struct workqueue_struct *ib_wq; extern struct workqueue_struct *ib_comp_wq; @@ -1331,6 +1332,12 @@ struct ib_fmr_attr { 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; @@ -1363,6 +1370,8 @@ struct ib_ucontext { struct list_head no_private_counters; int odp_mrs_count; #endif + + struct ib_rdmacg_object cg_obj; }; struct ib_uobject { @@ -1370,6 +1379,7 @@ 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 */ @@ -2118,6 +2128,10 @@ struct ib_device { 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 diff --git a/init/Kconfig b/init/Kconfig index 223b734abccd..ef80d46a32b6 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1090,6 +1090,16 @@ config CGROUP_PIDS since the PIDs limit only affects a process's ability to fork, not to attach to a cgroup. +config CGROUP_RDMA + bool "RDMA controller" + help + Provides enforcement of RDMA resources defined by IB stack. + It is fairly easy for consumers to exhaust RDMA resources, which + can result into resource unavailability to other consumers. + RDMA controller is designed to stop this from happening. + Attaching processes with active RDMA resources to the cgroup + hierarchy is allowed even if can cross the hierarchy's limit. + config CGROUP_FREEZER bool "Freezer controller" help diff --git a/kernel/cgroup/Makefile b/kernel/cgroup/Makefile index 6d42a3211164..387348a40c64 100644 --- a/kernel/cgroup/Makefile +++ b/kernel/cgroup/Makefile @@ -2,4 +2,5 @@ obj-y := cgroup.o namespace.o cgroup-v1.o obj-$(CONFIG_CGROUP_FREEZER) += freezer.o obj-$(CONFIG_CGROUP_PIDS) += pids.o +obj-$(CONFIG_CGROUP_RDMA) += rdma.o obj-$(CONFIG_CPUSETS) += cpuset.o diff --git a/kernel/cgroup/rdma.c b/kernel/cgroup/rdma.c new file mode 100644 index 000000000000..defad3c5e7dc --- /dev/null +++ b/kernel/cgroup/rdma.c @@ -0,0 +1,619 @@ +/* + * RDMA resource limiting controller for cgroups. + * + * Used to allow a cgroup hierarchy to stop processes from consuming + * additional RDMA resources after a certain limit is reached. + * + * Copyright (C) 2016 Parav Pandit + * + * This file is subject to the terms and conditions of version 2 of the GNU + * General Public License. See the file COPYING in the main directory of the + * Linux distribution for more details. + */ + +#include +#include +#include +#include +#include +#include + +#define RDMACG_MAX_STR "max" + +/* + * Protects list of resource pools maintained on per cgroup basis + * and rdma device list. + */ +static DEFINE_MUTEX(rdmacg_mutex); +static LIST_HEAD(rdmacg_devices); + +enum rdmacg_file_type { + RDMACG_RESOURCE_TYPE_MAX, + RDMACG_RESOURCE_TYPE_STAT, +}; + +/* + * resource table definition as to be seen by the user. + * Need to add entries to it when more resources are + * added/defined at IB verb/core layer. + */ +static char const *rdmacg_resource_names[] = { + [RDMACG_RESOURCE_HCA_HANDLE] = "hca_handle", + [RDMACG_RESOURCE_HCA_OBJECT] = "hca_object", +}; + +/* resource tracker for each resource of rdma cgroup */ +struct rdmacg_resource { + int max; + int usage; +}; + +/* + * resource pool object which represents per cgroup, per device + * resources. There are multiple instances of this object per cgroup, + * therefore it cannot be embedded within rdma_cgroup structure. It + * is maintained as list. + */ +struct rdmacg_resource_pool { + struct rdmacg_device *device; + struct rdmacg_resource resources[RDMACG_RESOURCE_MAX]; + + struct list_head cg_node; + struct list_head dev_node; + + /* count active user tasks of this pool */ + u64 usage_sum; + /* total number counts which are set to max */ + int num_max_cnt; +}; + +static struct rdma_cgroup *css_rdmacg(struct cgroup_subsys_state *css) +{ + return container_of(css, struct rdma_cgroup, css); +} + +static struct rdma_cgroup *parent_rdmacg(struct rdma_cgroup *cg) +{ + return css_rdmacg(cg->css.parent); +} + +static inline struct rdma_cgroup *get_current_rdmacg(void) +{ + return css_rdmacg(task_get_css(current, rdma_cgrp_id)); +} + +static void set_resource_limit(struct rdmacg_resource_pool *rpool, + int index, int new_max) +{ + if (new_max == S32_MAX) { + if (rpool->resources[index].max != S32_MAX) + rpool->num_max_cnt++; + } else { + if (rpool->resources[index].max == S32_MAX) + rpool->num_max_cnt--; + } + rpool->resources[index].max = new_max; +} + +static void set_all_resource_max_limit(struct rdmacg_resource_pool *rpool) +{ + int i; + + for (i = 0; i < RDMACG_RESOURCE_MAX; i++) + set_resource_limit(rpool, i, S32_MAX); +} + +static void free_cg_rpool_locked(struct rdmacg_resource_pool *rpool) +{ + lockdep_assert_held(&rdmacg_mutex); + + list_del(&rpool->cg_node); + list_del(&rpool->dev_node); + kfree(rpool); +} + +static struct rdmacg_resource_pool * +find_cg_rpool_locked(struct rdma_cgroup *cg, + struct rdmacg_device *device) + +{ + struct rdmacg_resource_pool *pool; + + lockdep_assert_held(&rdmacg_mutex); + + list_for_each_entry(pool, &cg->rpools, cg_node) + if (pool->device == device) + return pool; + + return NULL; +} + +static struct rdmacg_resource_pool * +get_cg_rpool_locked(struct rdma_cgroup *cg, struct rdmacg_device *device) +{ + struct rdmacg_resource_pool *rpool; + + rpool = find_cg_rpool_locked(cg, device); + if (rpool) + return rpool; + + rpool = kzalloc(sizeof(*rpool), GFP_KERNEL); + if (!rpool) + return ERR_PTR(-ENOMEM); + + rpool->device = device; + set_all_resource_max_limit(rpool); + + INIT_LIST_HEAD(&rpool->cg_node); + INIT_LIST_HEAD(&rpool->dev_node); + list_add_tail(&rpool->cg_node, &cg->rpools); + list_add_tail(&rpool->dev_node, &device->rpools); + return rpool; +} + +/** + * uncharge_cg_locked - uncharge resource for rdma cgroup + * @cg: pointer to cg to uncharge and all parents in hierarchy + * @device: pointer to rdmacg device + * @index: index of the resource to uncharge in cg (resource pool) + * + * It also frees the resource pool which was created as part of + * charging operation when there are no resources attached to + * resource pool. + */ +static void +uncharge_cg_locked(struct rdma_cgroup *cg, + struct rdmacg_device *device, + enum rdmacg_resource_type index) +{ + struct rdmacg_resource_pool *rpool; + + rpool = find_cg_rpool_locked(cg, device); + + /* + * rpool cannot be null at this stage. Let kernel operate in case + * if there a bug in IB stack or rdma controller, instead of crashing + * the system. + */ + if (unlikely(!rpool)) { + pr_warn("Invalid device %p or rdma cgroup %p\n", cg, device); + return; + } + + rpool->resources[index].usage--; + + /* + * A negative count (or overflow) is invalid, + * it indicates a bug in the rdma controller. + */ + WARN_ON_ONCE(rpool->resources[index].usage < 0); + rpool->usage_sum--; + if (rpool->usage_sum == 0 && + rpool->num_max_cnt == RDMACG_RESOURCE_MAX) { + /* + * No user of the rpool and all entries are set to max, so + * safe to delete this rpool. + */ + free_cg_rpool_locked(rpool); + } +} + +/** + * rdmacg_uncharge_hierarchy - hierarchically uncharge rdma resource count + * @device: pointer to rdmacg device + * @stop_cg: while traversing hirerchy, when meet with stop_cg cgroup + * stop uncharging + * @index: index of the resource to uncharge in cg in given resource pool + */ +static void rdmacg_uncharge_hierarchy(struct rdma_cgroup *cg, + struct rdmacg_device *device, + struct rdma_cgroup *stop_cg, + enum rdmacg_resource_type index) +{ + struct rdma_cgroup *p; + + mutex_lock(&rdmacg_mutex); + + for (p = cg; p != stop_cg; p = parent_rdmacg(p)) + uncharge_cg_locked(p, device, index); + + mutex_unlock(&rdmacg_mutex); + + css_put(&cg->css); +} + +/** + * rdmacg_uncharge - hierarchically uncharge rdma resource count + * @device: pointer to rdmacg device + * @index: index of the resource to uncharge in cgroup in given resource pool + */ +void rdmacg_uncharge(struct rdma_cgroup *cg, + struct rdmacg_device *device, + enum rdmacg_resource_type index) +{ + if (index >= RDMACG_RESOURCE_MAX) + return; + + rdmacg_uncharge_hierarchy(cg, device, NULL, index); +} +EXPORT_SYMBOL(rdmacg_uncharge); + +/** + * rdmacg_try_charge - hierarchically try to charge the rdma resource + * @rdmacg: pointer to rdma cgroup which will own this resource + * @device: pointer to rdmacg device + * @index: index of the resource to charge in cgroup (resource pool) + * + * This function follows charging resource in hierarchical way. + * It will fail if the charge would cause the new value to exceed the + * hierarchical limit. + * Returns 0 if the charge succeded, otherwise -EAGAIN, -ENOMEM or -EINVAL. + * Returns pointer to rdmacg for this resource when charging is successful. + * + * Charger needs to account resources on two criteria. + * (a) per cgroup & (b) per device resource usage. + * Per cgroup resource usage ensures that tasks of cgroup doesn't cross + * the configured limits. Per device provides granular configuration + * in multi device usage. It allocates resource pool in the hierarchy + * for each parent it come across for first resource. Later on resource + * pool will be available. Therefore it will be much faster thereon + * to charge/uncharge. + */ +int rdmacg_try_charge(struct rdma_cgroup **rdmacg, + struct rdmacg_device *device, + enum rdmacg_resource_type index) +{ + struct rdma_cgroup *cg, *p; + struct rdmacg_resource_pool *rpool; + s64 new; + int ret = 0; + + if (index >= RDMACG_RESOURCE_MAX) + return -EINVAL; + + /* + * hold on to css, as cgroup can be removed but resource + * accounting happens on css. + */ + cg = get_current_rdmacg(); + + mutex_lock(&rdmacg_mutex); + for (p = cg; p; p = parent_rdmacg(p)) { + rpool = get_cg_rpool_locked(p, device); + if (IS_ERR(rpool)) { + ret = PTR_ERR(rpool); + goto err; + } else { + new = rpool->resources[index].usage + 1; + if (new > rpool->resources[index].max) { + ret = -EAGAIN; + goto err; + } else { + rpool->resources[index].usage = new; + rpool->usage_sum++; + } + } + } + mutex_unlock(&rdmacg_mutex); + + *rdmacg = cg; + return 0; + +err: + mutex_unlock(&rdmacg_mutex); + rdmacg_uncharge_hierarchy(cg, device, p, index); + return ret; +} +EXPORT_SYMBOL(rdmacg_try_charge); + +/** + * rdmacg_register_device - register rdmacg device to rdma controller. + * @device: pointer to rdmacg device whose resources need to be accounted. + * + * If IB stack wish a device to participate in rdma cgroup resource + * tracking, it must invoke this API to register with rdma cgroup before + * any user space application can start using the RDMA resources. + * Returns 0 on success or EINVAL when table length given is beyond + * supported size. + */ +int rdmacg_register_device(struct rdmacg_device *device) +{ + INIT_LIST_HEAD(&device->dev_node); + INIT_LIST_HEAD(&device->rpools); + + mutex_lock(&rdmacg_mutex); + list_add_tail(&device->dev_node, &rdmacg_devices); + mutex_unlock(&rdmacg_mutex); + return 0; +} +EXPORT_SYMBOL(rdmacg_register_device); + +/** + * rdmacg_unregister_device - unregister rdmacg device from rdma controller. + * @device: pointer to rdmacg device which was previously registered with rdma + * controller using rdmacg_register_device(). + * + * IB stack must invoke this after all the resources of the IB device + * are destroyed and after ensuring that no more resources will be created + * when this API is invoked. + */ +void rdmacg_unregister_device(struct rdmacg_device *device) +{ + struct rdmacg_resource_pool *rpool, *tmp; + + /* + * Synchronize with any active resource settings, + * usage query happening via configfs. + */ + mutex_lock(&rdmacg_mutex); + list_del_init(&device->dev_node); + + /* + * Now that this device is off the cgroup list, its safe to free + * all the rpool resources. + */ + list_for_each_entry_safe(rpool, tmp, &device->rpools, dev_node) + free_cg_rpool_locked(rpool); + + mutex_unlock(&rdmacg_mutex); +} +EXPORT_SYMBOL(rdmacg_unregister_device); + +static int parse_resource(char *c, int *intval) +{ + substring_t argstr; + const char **table = &rdmacg_resource_names[0]; + char *name, *value = c; + size_t len; + int ret, i = 0; + + name = strsep(&value, "="); + if (!name || !value) + return -EINVAL; + + len = strlen(value); + + for (i = 0; i < RDMACG_RESOURCE_MAX; i++) { + if (strcmp(table[i], name)) + continue; + + argstr.from = value; + argstr.to = value + len; + + ret = match_int(&argstr, intval); + if (ret >= 0) { + if (*intval < 0) + break; + return i; + } + if (strncmp(value, RDMACG_MAX_STR, len) == 0) { + *intval = S32_MAX; + return i; + } + break; + } + return -EINVAL; +} + +static int rdmacg_parse_limits(char *options, + int *new_limits, unsigned long *enables) +{ + char *c; + int err = -EINVAL; + + /* parse resource options */ + while ((c = strsep(&options, " ")) != NULL) { + int index, intval; + + index = parse_resource(c, &intval); + if (index < 0) + goto err; + + new_limits[index] = intval; + *enables |= BIT(index); + } + return 0; + +err: + return err; +} + +static struct rdmacg_device *rdmacg_get_device_locked(const char *name) +{ + struct rdmacg_device *device; + + lockdep_assert_held(&rdmacg_mutex); + + list_for_each_entry(device, &rdmacg_devices, dev_node) + if (!strcmp(name, device->name)) + return device; + + return NULL; +} + +static ssize_t rdmacg_resource_set_max(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct rdma_cgroup *cg = css_rdmacg(of_css(of)); + const char *dev_name; + struct rdmacg_resource_pool *rpool; + struct rdmacg_device *device; + char *options = strstrip(buf); + int *new_limits; + unsigned long enables = 0; + int i = 0, ret = 0; + + /* extract the device name first */ + dev_name = strsep(&options, " "); + if (!dev_name) { + ret = -EINVAL; + goto err; + } + + new_limits = kcalloc(RDMACG_RESOURCE_MAX, sizeof(int), GFP_KERNEL); + if (!new_limits) { + ret = -ENOMEM; + goto err; + } + + ret = rdmacg_parse_limits(options, new_limits, &enables); + if (ret) + goto parse_err; + + /* acquire lock to synchronize with hot plug devices */ + mutex_lock(&rdmacg_mutex); + + device = rdmacg_get_device_locked(dev_name); + if (!device) { + ret = -ENODEV; + goto dev_err; + } + + rpool = get_cg_rpool_locked(cg, device); + if (IS_ERR(rpool)) { + ret = PTR_ERR(rpool); + goto dev_err; + } + + /* now set the new limits of the rpool */ + for_each_set_bit(i, &enables, RDMACG_RESOURCE_MAX) + set_resource_limit(rpool, i, new_limits[i]); + + if (rpool->usage_sum == 0 && + rpool->num_max_cnt == RDMACG_RESOURCE_MAX) { + /* + * No user of the rpool and all entries are set to max, so + * safe to delete this rpool. + */ + free_cg_rpool_locked(rpool); + } + +dev_err: + mutex_unlock(&rdmacg_mutex); + +parse_err: + kfree(new_limits); + +err: + return ret ?: nbytes; +} + +static void print_rpool_values(struct seq_file *sf, + struct rdmacg_resource_pool *rpool) +{ + enum rdmacg_file_type sf_type; + int i; + u32 value; + + sf_type = seq_cft(sf)->private; + + for (i = 0; i < RDMACG_RESOURCE_MAX; i++) { + seq_puts(sf, rdmacg_resource_names[i]); + seq_putc(sf, '='); + if (sf_type == RDMACG_RESOURCE_TYPE_MAX) { + if (rpool) + value = rpool->resources[i].max; + else + value = S32_MAX; + } else { + if (rpool) + value = rpool->resources[i].usage; + else + value = 0; + } + + if (value == S32_MAX) + seq_puts(sf, RDMACG_MAX_STR); + else + seq_printf(sf, "%d", value); + seq_putc(sf, ' '); + } +} + +static int rdmacg_resource_read(struct seq_file *sf, void *v) +{ + struct rdmacg_device *device; + struct rdmacg_resource_pool *rpool; + struct rdma_cgroup *cg = css_rdmacg(seq_css(sf)); + + mutex_lock(&rdmacg_mutex); + + list_for_each_entry(device, &rdmacg_devices, dev_node) { + seq_printf(sf, "%s ", device->name); + + rpool = find_cg_rpool_locked(cg, device); + print_rpool_values(sf, rpool); + + seq_putc(sf, '\n'); + } + + mutex_unlock(&rdmacg_mutex); + return 0; +} + +static struct cftype rdmacg_files[] = { + { + .name = "max", + .write = rdmacg_resource_set_max, + .seq_show = rdmacg_resource_read, + .private = RDMACG_RESOURCE_TYPE_MAX, + .flags = CFTYPE_NOT_ON_ROOT, + }, + { + .name = "current", + .seq_show = rdmacg_resource_read, + .private = RDMACG_RESOURCE_TYPE_STAT, + .flags = CFTYPE_NOT_ON_ROOT, + }, + { } /* terminate */ +}; + +static struct cgroup_subsys_state * +rdmacg_css_alloc(struct cgroup_subsys_state *parent) +{ + struct rdma_cgroup *cg; + + cg = kzalloc(sizeof(*cg), GFP_KERNEL); + if (!cg) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&cg->rpools); + return &cg->css; +} + +static void rdmacg_css_free(struct cgroup_subsys_state *css) +{ + struct rdma_cgroup *cg = css_rdmacg(css); + + kfree(cg); +} + +/** + * rdmacg_css_offline - cgroup css_offline callback + * @css: css of interest + * + * This function is called when @css is about to go away and responsible + * for shooting down all rdmacg associated with @css. As part of that it + * marks all the resource pool entries to max value, so that when resources are + * uncharged, associated resource pool can be freed as well. + */ +static void rdmacg_css_offline(struct cgroup_subsys_state *css) +{ + struct rdma_cgroup *cg = css_rdmacg(css); + struct rdmacg_resource_pool *rpool; + + mutex_lock(&rdmacg_mutex); + + list_for_each_entry(rpool, &cg->rpools, cg_node) + set_all_resource_max_limit(rpool); + + mutex_unlock(&rdmacg_mutex); +} + +struct cgroup_subsys rdma_cgrp_subsys = { + .css_alloc = rdmacg_css_alloc, + .css_free = rdmacg_css_free, + .css_offline = rdmacg_css_offline, + .legacy_cftypes = rdmacg_files, + .dfl_cftypes = rdmacg_files, +};