diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-02-28 06:41:08 +0100 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-02-28 06:41:08 +0100 |
| commit | f7878dc3a9d3d900c86a66d9742f7e06681b06cd (patch) | |
| tree | caf8dc1b1b668309200159519f0dc5c25c515acd | |
| parent | Merge branch 'for-4.11' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/p... (diff) | |
| parent | kernfs: fix locking around kernfs_ops->release() callback (diff) | |
| download | linux-f7878dc3a9d3d900c86a66d9742f7e06681b06cd.tar.xz linux-f7878dc3a9d3d900c86a66d9742f7e06681b06cd.zip | |
Merge branch 'for-4.11' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup
Pull cgroup updates from Tejun Heo:
"Several noteworthy changes.
- Parav's rdma controller is finally merged. It is very straight
forward and can limit the abosolute numbers of common rdma
constructs used by different cgroups.
- kernel/cgroup.c got too chubby and disorganized. Created
kernel/cgroup/ subdirectory and moved all cgroup related files
under kernel/ there and reorganized the core code. This hurts for
backporting patches but was long overdue.
- cgroup v2 process listing reimplemented so that it no longer
depends on allocating a buffer large enough to cache the entire
result to sort and uniq the output. v2 has always mangled the sort
order to ensure that users don't depend on the sorted output, so
this shouldn't surprise anybody. This makes the pid listing
functions use the same iterators that are used internally, which
have to have the same iterating capabilities anyway.
- perf cgroup filtering now works automatically on cgroup v2. This
patch was posted a long time ago but somehow fell through the
cracks.
- misc fixes asnd documentation updates"
* 'for-4.11' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (27 commits)
kernfs: fix locking around kernfs_ops->release() callback
cgroup: drop the matching uid requirement on migration for cgroup v2
cgroup, perf_event: make perf_event controller work on cgroup2 hierarchy
cgroup: misc cleanups
cgroup: call subsys->*attach() only for subsystems which are actually affected by migration
cgroup: track migration context in cgroup_mgctx
cgroup: cosmetic update to cgroup_taskset_add()
rdmacg: Fixed uninitialized current resource usage
cgroup: Add missing cgroup-v2 PID controller documentation.
rdmacg: Added documentation for rdmacg
IB/core: added support to use rdma cgroup controller
rdmacg: Added rdma cgroup controller
cgroup: fix a comment typo
cgroup: fix RCU related sparse warnings
cgroup: move namespace code to kernel/cgroup/namespace.c
cgroup: rename functions for consistency
cgroup: move v1 mount functions to kernel/cgroup/cgroup-v1.c
cgroup: separate out cgroup1_kf_syscall_ops
cgroup: refactor mount path and clearly distinguish v1 and v2 paths
cgroup: move cgroup v1 specific code to kernel/cgroup/cgroup-v1.c
...
30 files changed, 3264 insertions, 1898 deletions
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 4cc07ce3b8dd..3b8449f8ac7e 100644 --- a/Documentation/cgroup-v2.txt +++ b/Documentation/cgroup-v2.txt @@ -47,6 +47,12 @@ CONTENTS 5-3. IO 5-3-1. IO Interface Files 5-3-2. Writeback + 5-4. PID + 5-4-1. PID Interface Files + 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 @@ -328,14 +334,12 @@ a process with a non-root euid to migrate a target process into a cgroup by writing its PID to the "cgroup.procs" file, the following conditions must be met. -- The writer's euid must match either uid or suid of the target process. - - The writer must have write access to the "cgroup.procs" file. - The writer must have write access to the "cgroup.procs" file of the common ancestor of the source and destination cgroups. -The above three constraints ensure that while a delegatee may migrate +The above two constraints ensure that while a delegatee may migrate processes around freely in the delegated sub-hierarchy it can't pull in from or push out to outside the sub-hierarchy. @@ -350,10 +354,10 @@ all processes under C0 and C1 belong to U0. Let's also say U0 wants to write the PID of a process which is currently in C10 into "C00/cgroup.procs". U0 has write access to the -file and uid match on the process; however, the common ancestor of the -source cgroup C10 and the destination cgroup C00 is above the points -of delegation and U0 would not have write access to its "cgroup.procs" -files and thus the write will be denied with -EACCES. +file; however, the common ancestor of the source cgroup C10 and the +destination cgroup C00 is above the points of delegation and U0 would +not have write access to its "cgroup.procs" files and thus the write +will be denied with -EACCES. 2-6. Guidelines @@ -1119,6 +1123,91 @@ writeback as follows. vm.dirty[_background]_ratio. +5-4. PID + +The process number controller is used to allow a cgroup to stop any +new tasks from being fork()'d or clone()'d after a specified limit is +reached. + +The number of tasks in a cgroup can be exhausted in ways which other +controllers cannot prevent, thus warranting its own controller. For +example, a fork bomb is likely to exhaust the number of tasks before +hitting memory restrictions. + +Note that PIDs used in this controller refer to TIDs, process IDs as +used by the kernel. + + +5-4-1. PID Interface Files + + pids.max + + A read-write single value file which exists on non-root cgroups. The + default is "max". + + Hard limit of number of processes. + + pids.current + + A read-only single value file which exists on all cgroups. + + The number of processes currently in the cgroup and its descendants. + +Organisational operations are not blocked by cgroup policies, so it is +possible to have pids.current > pids.max. This can be done by either +setting the limit to be smaller than pids.current, or attaching enough +processes to the cgroup such that pids.current is larger than +pids.max. However, it is not possible to violate a cgroup PID policy +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. RDMA + +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 +always be filtered by cgroup v2 path. The controller can still be +moved to a legacy hierarchy after v2 hierarchy is populated. + + 6. Namespace 6-1. Basics 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 <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); diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h index 912ab4cd6eae..cb7d372e4bdf 100644 --- a/drivers/infiniband/core/core_priv.h +++ b/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> @@ -124,6 +125,35 @@ 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 a63e8400ea3b..593d2ce6ec7c 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -369,10 +369,18 @@ 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; } @@ -381,6 +389,7 @@ 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; } @@ -430,6 +439,7 @@ 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 b4b395a054ac..7b7a76e1279a 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); @@ -1905,6 +1954,11 @@ 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 @@ -1912,7 +1966,7 @@ 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) { @@ -1993,6 +2047,10 @@ 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); @@ -2519,6 +2577,8 @@ 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); @@ -2970,11 +3030,16 @@ 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; @@ -3013,7 +3078,10 @@ 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: @@ -3047,6 +3115,8 @@ 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); @@ -3861,10 +3931,16 @@ 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; @@ -3897,6 +3973,8 @@ 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: @@ -3936,8 +4014,11 @@ 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); @@ -4005,6 +4086,11 @@ 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); @@ -4069,6 +4155,8 @@ 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: @@ -4255,6 +4343,8 @@ 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 e3fb4b1af1ad..35c788a32e26 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -51,6 +51,7 @@ #include <rdma/ib.h> #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/fs/kernfs/dir.c b/fs/kernfs/dir.c index 439b946c4808..db5900aaa55a 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -478,7 +478,7 @@ static void kernfs_drain(struct kernfs_node *kn) rwsem_release(&kn->dep_map, 1, _RET_IP_); } - kernfs_unmap_bin_file(kn); + kernfs_drain_open_files(kn); mutex_lock(&kernfs_mutex); } diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index 4f0535890b30..35043a8c4529 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -515,7 +515,7 @@ static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma) goto out_put; rc = 0; - of->mmapped = 1; + of->mmapped = true; of->vm_ops = vma->vm_ops; vma->vm_ops = &kernfs_vm_ops; out_put: @@ -707,7 +707,8 @@ static int kernfs_fop_open(struct inode *inode, struct file *file) if (error) goto err_free; - ((struct seq_file *)file->private_data)->private = of; + of->seq_file = file->private_data; + of->seq_file->private = of; /* seq_file clears PWRITE unconditionally, restore it if WRITE */ if (file->f_mode & FMODE_WRITE) @@ -716,13 +717,22 @@ static int kernfs_fop_open(struct inode *inode, struct file *file) /* make sure we have open node struct */ error = kernfs_get_open_node(kn, of); if (error) - goto err_close; + goto err_seq_release; + + if (ops->open) { + /* nobody has access to @of yet, skip @of->mutex */ + error = ops->open(of); + if (error) + goto err_put_node; + } /* open succeeded, put active references */ kernfs_put_active(kn); return 0; -err_close: +err_put_node: + kernfs_put_open_node(kn, of); +err_seq_release: seq_release(inode, file); err_free: kfree(of->prealloc_buf); @@ -732,11 +742,41 @@ err_out: return error; } +/* used from release/drain to ensure that ->release() is called exactly once */ +static void kernfs_release_file(struct kernfs_node *kn, + struct kernfs_open_file *of) +{ + /* + * @of is guaranteed to have no other file operations in flight and + * we just want to synchronize release and drain paths. + * @kernfs_open_file_mutex is enough. @of->mutex can't be used + * here because drain path may be called from places which can + * cause circular dependency. + */ + lockdep_assert_held(&kernfs_open_file_mutex); + + if (!of->released) { + /* + * A file is never detached without being released and we + * need to be able to release files which are deactivated + * and being drained. Don't use kernfs_ops(). + */ + kn->attr.ops->release(of); + of->released = true; + } +} + static int kernfs_fop_release(struct inode *inode, struct file *filp) { struct kernfs_node *kn = filp->f_path.dentry->d_fsdata; struct kernfs_open_file *of = kernfs_of(filp); + if (kn->flags & KERNFS_HAS_RELEASE) { + mutex_lock(&kernfs_open_file_mutex); + kernfs_release_file(kn, of); + mutex_unlock(&kernfs_open_file_mutex); + } + kernfs_put_open_node(kn, of); seq_release(inode, filp); kfree(of->prealloc_buf); @@ -745,12 +785,12 @@ static int kernfs_fop_release(struct inode *inode, struct file *filp) return 0; } -void kernfs_unmap_bin_file(struct kernfs_node *kn) +void kernfs_drain_open_files(struct kernfs_node *kn) { struct kernfs_open_node *on; struct kernfs_open_file *of; - if (!(kn->flags & KERNFS_HAS_MMAP)) + if (!(kn->flags & (KERNFS_HAS_MMAP | KERNFS_HAS_RELEASE))) return; spin_lock_irq(&kernfs_open_node_lock); @@ -762,10 +802,16 @@ void kernfs_unmap_bin_file(struct kernfs_node *kn) return; mutex_lock(&kernfs_open_file_mutex); + list_for_each_entry(of, &on->files, list) { struct inode *inode = file_inode(of->file); - unmap_mapping_range(inode->i_mapping, 0, 0, 1); + + if (kn->flags & KERNFS_HAS_MMAP) + unmap_mapping_range(inode->i_mapping, 0, 0, 1); + + kernfs_release_file(kn, of); } + mutex_unlock(&kernfs_open_file_mutex); kernfs_put_open_node(kn, NULL); @@ -964,6 +1010,8 @@ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent, kn->flags |= KERNFS_HAS_SEQ_SHOW; if (ops->mmap) kn->flags |= KERNFS_HAS_MMAP; + if (ops->release) + kn->flags |= KERNFS_HAS_RELEASE; rc = kernfs_add_one(kn); if (rc) { diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index bfd551bbf231..3100987cf8ba 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -104,7 +104,7 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent, */ extern const struct file_operations kernfs_file_fops; -void kernfs_unmap_bin_file(struct kernfs_node *kn); +void kernfs_drain_open_files(struct kernfs_node *kn); /* * symlink.c diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 861b4677fc5b..3c02404cfce9 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -148,14 +148,18 @@ struct cgroup_subsys_state { * set for a task. */ struct css_set { - /* Reference count */ - atomic_t refcount; - /* - * List running through all cgroup groups in the same hash - * slot. Protected by css_set_lock + * Set of subsystem states, one for each subsystem. This array is + * immutable after creation apart from the init_css_set during + * subsystem registration (at boot time). */ - struct hlist_node hlist; + struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; + + /* reference count */ + atomic_t refcount; + + /* the default cgroup associated with this css_set */ + struct cgroup *dfl_cgrp; /* * Lists running through all tasks using this cgroup group. @@ -167,21 +171,29 @@ struct css_set { struct list_head tasks; struct list_head mg_tasks; + /* all css_task_iters currently walking this cset */ + struct list_head task_iters; + /* - * List of cgrp_cset_links pointing at cgroups referenced from this - * css_set. Protected by css_set_lock. + * On the default hierarhcy, ->subsys[ssid] may point to a css + * attached to an ancestor instead of the cgroup this css_set is + * associated with. The following node is anchored at + * ->subsys[ssid]->cgroup->e_csets[ssid] and provides a way to + * iterate through all css's attached to a given cgroup. */ - struct list_head cgrp_links; + struct list_head e_cset_node[CGROUP_SUBSYS_COUNT]; - /* the default cgroup associated with this css_set */ - struct cgroup *dfl_cgrp; + /* + * List running through all cgroup groups in the same hash + * slot. Protected by css_set_lock + */ + struct hlist_node hlist; /* - * Set of subsystem states, one for each subsystem. This array is - * immutable after creation apart from the init_css_set during - * subsystem registration (at boot time). + * List of cgrp_cset_links pointing at cgroups referenced from this + * css_set. Protected by css_set_lock. */ - struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; + struct list_head cgrp_links; /* * List of csets participating in the on-going migration either as @@ -201,18 +213,6 @@ struct css_set { struct cgroup *mg_dst_cgrp; struct css_set *mg_dst_cset; - /* - * On the default hierarhcy, ->subsys[ssid] may point to a css - * attached to an ancestor instead of the cgroup this css_set is - * associated with. The following node is anchored at - * ->subsys[ssid]->cgroup->e_csets[ssid] and provides a way to - * iterate through all css's attached to a given cgroup. - */ - struct list_head e_cset_node[CGROUP_SUBSYS_COUNT]; - - /* all css_task_iters currently walking this cset */ - struct list_head task_iters; - /* dead and being drained, ignore for migration */ bool dead; @@ -388,6 +388,9 @@ struct cftype { struct list_head node; /* anchored at ss->cfts */ struct kernfs_ops *kf_ops; + int (*open)(struct kernfs_open_file *of); + void (*release)(struct kernfs_open_file *of); + /* * read_u64() is a shortcut for the common case of returning a * single integer. Use it in place of read() diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index c83c23f0577b..f6b43fbb141c 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -266,7 +266,7 @@ void css_task_iter_end(struct css_task_iter *it); * cgroup_taskset_for_each_leader - iterate group leaders in a cgroup_taskset * @leader: the loop cursor * @dst_css: the destination css - * @tset: takset to iterate + * @tset: taskset to iterate * * Iterate threadgroup leaders of @tset. For single-task migrations, @tset * may not contain any. 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 <pandit.parav@gmail.com> + * + * 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 <linux/cgroup.h> + +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/linux/kernfs.h b/include/linux/kernfs.h index 7056238fd9f5..a9b11b8d06f2 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -46,6 +46,7 @@ enum kernfs_node_flag { KERNFS_SUICIDAL = 0x0400, KERNFS_SUICIDED = 0x0800, KERNFS_EMPTY_DIR = 0x1000, + KERNFS_HAS_RELEASE = 0x2000, }; /* @flags for kernfs_create_root() */ @@ -175,6 +176,7 @@ struct kernfs_open_file { /* published fields */ struct kernfs_node *kn; struct file *file; + struct seq_file *seq_file; void *priv; /* private fields, do not use outside kernfs proper */ @@ -185,12 +187,20 @@ struct kernfs_open_file { char *prealloc_buf; size_t atomic_write_len; - bool mmapped; + bool mmapped:1; + bool released:1; const struct vm_operations_struct *vm_ops; }; struct kernfs_ops { /* + * Optional open/release methods. Both are called with + * @of->seq_file populated. + */ + int (*open)(struct kernfs_open_file *of); + void (*release)(struct kernfs_open_file *of); + + /* * Read is handled by either seq_file or raw_read(). * * If seq_show() is present, seq_file path is active. Other seq diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index d84849c5dc05..0f1813c13687 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -60,6 +60,7 @@ #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; @@ -1356,6 +1357,12 @@ 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; @@ -1388,6 +1395,8 @@ struct ib_ucontext { struct list_head no_private_counters; int odp_mrs_count; #endif + + struct ib_rdmacg_object cg_obj; }; struct ib_uobject { @@ -1395,6 +1404,7 @@ 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 */ @@ -2128,6 +2138,10 @@ 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 8c39615165b7..a92f27da4a27 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1078,6 +1078,16 @@ 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/Makefile b/kernel/Makefile index 12c679f769c6..b302b4731d16 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -64,10 +64,7 @@ obj-$(CONFIG_KEXEC) += kexec.o obj-$(CONFIG_KEXEC_FILE) += kexec_file.o obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o obj-$(CONFIG_COMPAT) += compat.o -obj-$(CONFIG_CGROUPS) += cgroup.o -obj-$(CONFIG_CGROUP_FREEZER) += cgroup_freezer.o -obj-$(CONFIG_CGROUP_PIDS) += cgroup_pids.o -obj-$(CONFIG_CPUSETS) += cpuset.o +obj-$(CONFIG_CGROUPS) += cgroup/ obj-$(CONFIG_UTS_NS) += utsname.o obj-$(CONFIG_USER_NS) += user_namespace.o obj-$(CONFIG_PID_NS) += pid_namespace.o diff --git a/kernel/cgroup/Makefile b/kernel/cgroup/Makefile new file mode 100644 index 000000000000..387348a40c64 --- /dev/null +++ b/kernel/cgroup/Makefile @@ -0,0 +1,6 @@ +obj-y := cgroup.o namespace.o cgroup-v1.o + +obj-$(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/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h new file mode 100644 index 000000000000..9203bfb05603 --- /dev/null +++ b/kernel/cgroup/cgroup-internal.h @@ -0,0 +1,214 @@ +#ifndef __CGROUP_INTERNAL_H +#define __CGROUP_INTERNAL_H + +#include <linux/cgroup.h> +#include <linux/kernfs.h> +#include <linux/workqueue.h> +#include <linux/list.h> + +/* + * A cgroup can be associated with multiple css_sets as different tasks may + * belong to different cgroups on different hierarchies. In the other + * direction, a css_set is naturally associated with multiple cgroups. + * This M:N relationship is represented by the following link structure + * which exists for each association and allows traversing the associations + * from both sides. + */ +struct cgrp_cset_link { + /* the cgroup and css_set this link associates */ + struct cgroup *cgrp; + struct css_set *cset; + + /* list of cgrp_cset_links anchored at cgrp->cset_links */ + struct list_head cset_link; + + /* list of cgrp_cset_links anchored at css_set->cgrp_links */ + struct list_head cgrp_link; +}; + +/* used to track tasks and csets during migration */ +struct cgroup_taskset { + /* the src and dst cset list running through cset->mg_node */ + struct list_head src_csets; + struct list_head dst_csets; + + /* the subsys currently being processed */ + int ssid; + + /* + * Fields for cgroup_taskset_*() iteration. + * + * Before migration is committed, the target migration tasks are on + * ->mg_tasks of the csets on ->src_csets. After, on ->mg_tasks of + * the csets on ->dst_csets. ->csets point to either ->src_csets + * or ->dst_csets depending on whether migration is committed. + * + * ->cur_csets and ->cur_task point to the current task position + * during iteration. + */ + struct list_head *csets; + struct css_set *cur_cset; + struct task_struct *cur_task; +}; + +/* migration context also tracks preloading */ +struct cgroup_mgctx { + /* + * Preloaded source and destination csets. Used to guarantee + * atomic success or failure on actual migration. + */ + struct list_head preloaded_src_csets; + struct list_head preloaded_dst_csets; + + /* tasks and csets to migrate */ + struct cgroup_taskset tset; + + /* subsystems affected by migration */ + u16 ss_mask; +}; + +#define CGROUP_TASKSET_INIT(tset) \ +{ \ + .src_csets = LIST_HEAD_INIT(tset.src_csets), \ + .dst_csets = LIST_HEAD_INIT(tset.dst_csets), \ + .csets = &tset.src_csets, \ +} + +#define CGROUP_MGCTX_INIT(name) \ +{ \ + LIST_HEAD_INIT(name.preloaded_src_csets), \ + LIST_HEAD_INIT(name.preloaded_dst_csets), \ + CGROUP_TASKSET_INIT(name.tset), \ +} + +#define DEFINE_CGROUP_MGCTX(name) \ + struct cgroup_mgctx name = CGROUP_MGCTX_INIT(name) + +struct cgroup_sb_opts { + u16 subsys_mask; + unsigned int flags; + char *release_agent; + bool cpuset_clone_children; + char *name; + /* User explicitly requested empty subsystem */ + bool none; +}; + +extern struct mutex cgroup_mutex; +extern spinlock_t css_set_lock; +extern struct cgroup_subsys *cgroup_subsys[]; +extern struct list_head cgroup_roots; +extern struct file_system_type cgroup_fs_type; + +/* iterate across the hierarchies */ +#define for_each_root(root) \ + list_for_each_entry((root), &cgroup_roots, root_list) + +/** + * for_each_subsys - iterate all enabled cgroup subsystems + * @ss: the iteration cursor + * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end + */ +#define for_each_subsys(ss, ssid) \ + for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT && \ + (((ss) = cgroup_subsys[ssid]) || true); (ssid)++) + +static inline bool cgroup_is_dead(const struct cgroup *cgrp) +{ + return !(cgrp->self.flags & CSS_ONLINE); +} + +static inline bool notify_on_release(const struct cgroup *cgrp) +{ + return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags); +} + +void put_css_set_locked(struct css_set *cset); + +static inline void put_css_set(struct css_set *cset) +{ + unsigned long flags; + + /* + * Ensure that the refcount doesn't hit zero while any readers + * can see it. Similar to atomic_dec_and_lock(), but for an + * rwlock + */ + if (atomic_add_unless(&cset->refcount, -1, 1)) + return; + + spin_lock_irqsave(&css_set_lock, flags); + put_css_set_locked(cset); + spin_unlock_irqrestore(&css_set_lock, flags); +} + +/* + * refcounted get/put for css_set objects + */ +static inline void get_css_set(struct css_set *cset) +{ + atomic_inc(&cset->refcount); +} + +bool cgroup_ssid_enabled(int ssid); +bool cgroup_on_dfl(const struct cgroup *cgrp); + +struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root); +struct cgroup *task_cgroup_from_root(struct task_struct *task, + struct cgroup_root *root); +struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn, bool drain_offline); +void cgroup_kn_unlock(struct kernfs_node *kn); +int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen, + struct cgroup_namespace *ns); + +void cgroup_free_root(struct cgroup_root *root); +void init_cgroup_root(struct cgroup_root *root, struct cgroup_sb_opts *opts); +int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask); +int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask); +struct dentry *cgroup_do_mount(struct file_system_type *fs_type, int flags, + struct cgroup_root *root, unsigned long magic, + struct cgroup_namespace *ns); + +bool cgroup_may_migrate_to(struct cgroup *dst_cgrp); +void cgroup_migrate_finish(struct cgroup_mgctx *mgctx); +void cgroup_migrate_add_src(struct css_set *src_cset, struct cgroup *dst_cgrp, + struct cgroup_mgctx *mgctx); +int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx); +int cgroup_migrate(struct task_struct *leader, bool threadgroup, + struct cgroup_mgctx *mgctx); + +int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader, + bool threadgroup); +ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off, bool threadgroup); +ssize_t cgroup_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes, + loff_t off); + +void cgroup_lock_and_drain_offline(struct cgroup *cgrp); + +int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode); +int cgroup_rmdir(struct kernfs_node *kn); +int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node, + struct kernfs_root *kf_root); + +/* + * namespace.c + */ +extern const struct proc_ns_operations cgroupns_operations; + +/* + * cgroup-v1.c + */ +extern struct cftype cgroup1_base_files[]; +extern const struct file_operations proc_cgroupstats_operations; +extern struct kernfs_syscall_ops cgroup1_kf_syscall_ops; + +bool cgroup1_ssid_disabled(int ssid); +void cgroup1_pidlist_destroy_all(struct cgroup *cgrp); +void cgroup1_release_agent(struct work_struct *work); +void cgroup1_check_for_release(struct cgroup *cgrp); +struct dentry *cgroup1_mount(struct file_system_type *fs_type, int flags, + void *data, unsigned long magic, + struct cgroup_namespace *ns); + +#endif /* __CGROUP_INTERNAL_H */ diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c new file mode 100644 index 000000000000..fc34bcf2329f --- /dev/null +++ b/kernel/cgroup/cgroup-v1.c @@ -0,0 +1,1395 @@ +#include "cgroup-internal.h" + +#include <linux/ctype.h> +#include <linux/kmod.h> +#include <linux/sort.h> +#include <linux/delay.h> +#include <linux/mm.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> +#include <linux/delayacct.h> +#include <linux/pid_namespace.h> +#include <linux/cgroupstats.h> + +#include <trace/events/cgroup.h> + +/* + * pidlists linger the following amount before being destroyed. The goal + * is avoiding frequent destruction in the middle of consecutive read calls + * Expiring in the middle is a performance problem not a correctness one. + * 1 sec should be enough. + */ +#define CGROUP_PIDLIST_DESTROY_DELAY HZ + +/* Controllers blocked by the commandline in v1 */ +static u16 cgroup_no_v1_mask; + +/* + * pidlist destructions need to be flushed on cgroup destruction. Use a + * separate workqueue as flush domain. + */ +static struct workqueue_struct *cgroup_pidlist_destroy_wq; + +/* + * Protects cgroup_subsys->release_agent_path. Modifying it also requires + * cgroup_mutex. Reading requires either cgroup_mutex or this spinlock. + */ +static DEFINE_SPINLOCK(release_agent_path_lock); + +bool cgroup1_ssid_disabled(int ssid) +{ + return cgroup_no_v1_mask & (1 << ssid); +} + +/** + * cgroup_attach_task_all - attach task 'tsk' to all cgroups of task 'from' + * @from: attach to all cgroups of a given task + * @tsk: the task to be attached + */ +int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) +{ + struct cgroup_root *root; + int retval = 0; + + mutex_lock(&cgroup_mutex); + percpu_down_write(&cgroup_threadgroup_rwsem); + for_each_root(root) { + struct cgroup *from_cgrp; + + if (root == &cgrp_dfl_root) + continue; + + spin_lock_irq(&css_set_lock); + from_cgrp = task_cgroup_from_root(from, root); + spin_unlock_irq(&css_set_lock); + + retval = cgroup_attach_task(from_cgrp, tsk, false); + if (retval) + break; + } + percpu_up_write(&cgroup_threadgroup_rwsem); + mutex_unlock(&cgroup_mutex); + + return retval; +} +EXPORT_SYMBOL_GPL(cgroup_attach_task_all); + +/** + * cgroup_trasnsfer_tasks - move tasks from one cgroup to another + * @to: cgroup to which the tasks will be moved + * @from: cgroup in which the tasks currently reside + * + * Locking rules between cgroup_post_fork() and the migration path + * guarantee that, if a task is forking while being migrated, the new child + * is guaranteed to be either visible in the source cgroup after the + * parent's migration is complete or put into the target cgroup. No task + * can slip out of migration through forking. + */ +int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from) +{ + DEFINE_CGROUP_MGCTX(mgctx); + struct cgrp_cset_link *link; + struct css_task_iter it; + struct task_struct *task; + int ret; + + if (cgroup_on_dfl(to)) + return -EINVAL; + + if (!cgroup_may_migrate_to(to)) + return -EBUSY; + + mutex_lock(&cgroup_mutex); + + percpu_down_write(&cgroup_threadgroup_rwsem); + + /* all tasks in @from are being moved, all csets are source */ + spin_lock_irq(&css_set_lock); + list_for_each_entry(link, &from->cset_links, cset_link) + cgroup_migrate_add_src(link->cset, to, &mgctx); + spin_unlock_irq(&css_set_lock); + + ret = cgroup_migrate_prepare_dst(&mgctx); + if (ret) + goto out_err; + + /* + * Migrate tasks one-by-one until @from is empty. This fails iff + * ->can_attach() fails. + */ + do { + css_task_iter_start(&from->self, &it); + task = css_task_iter_next(&it); + if (task) + get_task_struct(task); + css_task_iter_end(&it); + + if (task) { + ret = cgroup_migrate(task, false, &mgctx); + if (!ret) + trace_cgroup_transfer_tasks(to, task, false); + put_task_struct(task); + } + } while (task && !ret); +out_err: + cgroup_migrate_finish(&mgctx); + percpu_up_write(&cgroup_threadgroup_rwsem); + mutex_unlock(&cgroup_mutex); + return ret; +} + +/* + * Stuff for reading the 'tasks'/'procs' files. + * + * Reading this file can return large amounts of data if a cgroup has + * *lots* of attached tasks. So it may need several calls to read(), + * but we cannot guarantee that the information we produce is correct + * unless we produce it entirely atomically. + * + */ + +/* which pidlist file are we talking about? */ +enum cgroup_filetype { + CGROUP_FILE_PROCS, + CGROUP_FILE_TASKS, +}; + +/* + * A pidlist is a list of pids that virtually represents the contents of one + * of the cgroup files ("procs" or "tasks"). We keep a list of such pidlists, + * a pair (one each for procs, tasks) for each pid namespace that's relevant + * to the cgroup. + */ +struct cgroup_pidlist { + /* + * used to find which pidlist is wanted. doesn't change as long as + * this particular list stays in the list. + */ + struct { enum cgroup_filetype type; struct pid_namespace *ns; } key; + /* array of xids */ + pid_t *list; + /* how many elements the above list has */ + int length; + /* each of these stored in a list by its cgroup */ + struct list_head links; + /* pointer to the cgroup we belong to, for list removal purposes */ + struct cgroup *owner; + /* for delayed destruction */ + struct delayed_work destroy_dwork; +}; + +/* + * The following two functions "fix" the issue where there are more pids + * than kmalloc will give memory for; in such cases, we use vmalloc/vfree. + * TODO: replace with a kernel-wide solution to this problem + */ +#define PIDLIST_TOO_LARGE(c) ((c) * sizeof(pid_t) > (PAGE_SIZE * 2)) +static void *pidlist_allocate(int count) +{ + if (PIDLIST_TOO_LARGE(count)) + return vmalloc(count * sizeof(pid_t)); + else + return kmalloc(count * sizeof(pid_t), GFP_KERNEL); +} + +static void pidlist_free(void *p) +{ + kvfree(p); +} + +/* + * Used to destroy all pidlists lingering waiting for destroy timer. None + * should be left afterwards. + */ +void cgroup1_pidlist_destroy_all(struct cgroup *cgrp) +{ + struct cgroup_pidlist *l, *tmp_l; + + mutex_lock(&cgrp->pidlist_mutex); + list_for_each_entry_safe(l, tmp_l, &cgrp->pidlists, links) + mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, 0); + mutex_unlock(&cgrp->pidlist_mutex); + + flush_workqueue(cgroup_pidlist_destroy_wq); + BUG_ON(!list_empty(&cgrp->pidlists)); +} + +static void cgroup_pidlist_destroy_work_fn(struct work_struct *work) +{ + struct delayed_work *dwork = to_delayed_work(work); + struct cgroup_pidlist *l = container_of(dwork, struct cgroup_pidlist, + destroy_dwork); + struct cgroup_pidlist *tofree = NULL; + + mutex_lock(&l->owner->pidlist_mutex); + + /* + * Destroy iff we didn't get queued again. The state won't change + * as destroy_dwork can only be queued while locked. + */ + if (!delayed_work_pending(dwork)) { + list_del(&l->links); + pidlist_free(l->list); + put_pid_ns(l->key.ns); + tofree = l; + } + + mutex_unlock(&l->owner->pidlist_mutex); + kfree(tofree); +} + +/* + * pidlist_uniq - given a kmalloc()ed list, strip out all duplicate entries + * Returns the number of unique elements. + */ +static int pidlist_uniq(pid_t *list, int length) +{ + int src, dest = 1; + + /* + * we presume the 0th element is unique, so i starts at 1. trivial + * edge cases first; no work needs to be done for either + */ + if (length == 0 || length == 1) + return length; + /* src and dest walk down the list; dest counts unique elements */ + for (src = 1; src < length; src++) { + /* find next unique element */ + while (list[src] == list[src-1]) { + src++; + if (src == length) + goto after; + } + /* dest always points to where the next unique element goes */ + list[dest] = list[src]; + dest++; + } +after: + return dest; +} + +/* + * The two pid files - task and cgroup.procs - guaranteed that the result + * is sorted, which forced this whole pidlist fiasco. As pid order is + * different per namespace, each namespace needs differently sorted list, + * making it impossible to use, for example, single rbtree of member tasks + * sorted by task pointer. As pidlists can be fairly large, allocating one + * per open file is dangerous, so cgroup had to implement shared pool of + * pidlists keyed by cgroup and namespace. + */ +static int cmppid(const void *a, const void *b) +{ + return *(pid_t *)a - *(pid_t *)b; +} + +static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp, + enum cgroup_filetype type) +{ + struct cgroup_pidlist *l; + /* don't need task_nsproxy() if we're looking at ourself */ + struct pid_namespace *ns = task_active_pid_ns(current); + + lockdep_assert_held(&cgrp->pidlist_mutex); + + list_for_each_entry(l, &cgrp->pidlists, links) + if (l->key.type == type && l->key.ns == ns) + return l; + return NULL; +} + +/* + * find the appropriate pidlist for our purpose (given procs vs tasks) + * returns with the lock on that pidlist already held, and takes care + * of the use count, or returns NULL with no locks held if we're out of + * memory. + */ +static struct cgroup_pidlist *cgroup_pidlist_find_create(struct cgroup *cgrp, + enum cgroup_filetype type) +{ + struct cgroup_pidlist *l; + + lockdep_assert_held(&cgrp->pidlist_mutex); + + l = cgroup_pidlist_find(cgrp, type); + if (l) + return l; + + /* entry not found; create a new one */ + l = kzalloc(sizeof(struct cgroup_pidlist), GFP_KERNEL); + if (!l) + return l; + + INIT_DELAYED_WORK(&l->destroy_dwork, cgroup_pidlist_destroy_work_fn); + l->key.type = type; + /* don't need task_nsproxy() if we're looking at ourself */ + l->key.ns = get_pid_ns(task_active_pid_ns(current)); + l->owner = cgrp; + list_add(&l->links, &cgrp->pidlists); + return l; +} + +/** + * cgroup_task_count - count the number of tasks in a cgroup. + * @cgrp: the cgroup in question + * + * Return the number of tasks in the cgroup. The returned number can be + * higher than the actual number of tasks due to css_set references from + * namespace roots and temporary usages. + */ +static int cgroup_task_count(const struct cgroup *cgrp) +{ + int count = 0; + struct cgrp_cset_link *link; + + spin_lock_irq(&css_set_lock); + list_for_each_entry(link, &cgrp->cset_links, cset_link) + count += atomic_read(&link->cset->refcount); + spin_unlock_irq(&css_set_lock); + return count; +} + +/* + * Load a cgroup's pidarray with either procs' tgids or tasks' pids + */ +static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, + struct cgroup_pidlist **lp) +{ + pid_t *array; + int length; + int pid, n = 0; /* used for populating the array */ + struct css_task_iter it; + struct task_struct *tsk; + struct cgroup_pidlist *l; + + lockdep_assert_held(&cgrp->pidlist_mutex); + + /* + * If cgroup gets more users after we read count, we won't have + * enough space - tough. This race is indistinguishable to the + * caller from the case that the additional cgroup users didn't + * show up until sometime later on. + */ + length = cgroup_task_count(cgrp); + array = pidlist_allocate(length); + if (!array) + return -ENOMEM; + /* now, populate the array */ + css_task_iter_start(&cgrp->self, &it); + while ((tsk = css_task_iter_next(&it))) { + if (unlikely(n == length)) + break; + /* get tgid or pid for procs or tasks file respectively */ + if (type == CGROUP_FILE_PROCS) + pid = task_tgid_vnr(tsk); + else + pid = task_pid_vnr(tsk); + if (pid > 0) /* make sure to only use valid results */ + array[n++] = pid; + } + css_task_iter_end(&it); + length = n; + /* now sort & (if procs) strip out duplicates */ + sort(array, length, sizeof(pid_t), cmppid, NULL); + if (type == CGROUP_FILE_PROCS) + length = pidlist_uniq(array, length); + + l = cgroup_pidlist_find_create(cgrp, type); + if (!l) { + pidlist_free(array); + return -ENOMEM; + } + + /* store array, freeing old if necessary */ + pidlist_free(l->list); + l->list = array; + l->length = length; + *lp = l; + return 0; +} + +/* + * seq_file methods for the tasks/procs files. The seq_file position is the + * next pid to display; the seq_file iterator is a pointer to the pid + * in the cgroup->l->list array. + */ + +static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos) +{ + /* + * Initially we receive a position value that corresponds to + * one more than the last pid shown (or 0 on the first call or + * after a seek to the start). Use a binary-search to find the + * next pid to display, if any + */ + struct kernfs_open_file *of = s->private; + struct cgroup *cgrp = seq_css(s)->cgroup; + struct cgroup_pidlist *l; + enum cgroup_filetype type = seq_cft(s)->private; + int index = 0, pid = *pos; + int *iter, ret; + + mutex_lock(&cgrp->pidlist_mutex); + + /* + * !NULL @of->priv indicates that this isn't the first start() + * after open. If the matching pidlist is around, we can use that. + * Look for it. Note that @of->priv can't be used directly. It + * could already have been destroyed. + */ + if (of->priv) + of->priv = cgroup_pidlist_find(cgrp, type); + + /* + * Either this is the first start() after open or the matching + * pidlist has been destroyed inbetween. Create a new one. + */ + if (!of->priv) { + ret = pidlist_array_load(cgrp, type, + (struct cgroup_pidlist **)&of->priv); + if (ret) + return ERR_PTR(ret); + } + l = of->priv; + + if (pid) { + int end = l->length; + + while (index < end) { + int mid = (index + end) / 2; + if (l->list[mid] == pid) { + index = mid; + break; + } else if (l->list[mid] <= pid) + index = mid + 1; + else + end = mid; + } + } + /* If we're off the end of the array, we're done */ + if (index >= l->length) + return NULL; + /* Update the abstract position to be the actual pid that we found */ + iter = l->list + index; + *pos = *iter; + return iter; +} + +static void cgroup_pidlist_stop(struct seq_file *s, void *v) +{ + struct kernfs_open_file *of = s->private; + struct cgroup_pidlist *l = of->priv; + + if (l) + mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, + CGROUP_PIDLIST_DESTROY_DELAY); + mutex_unlock(&seq_css(s)->cgroup->pidlist_mutex); +} + +static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos) +{ + struct kernfs_open_file *of = s->private; + struct cgroup_pidlist *l = of->priv; + pid_t *p = v; + pid_t *end = l->list + l->length; + /* + * Advance to the next pid in the array. If this goes off the + * end, we're done + */ + p++; + if (p >= end) { + return NULL; + } else { + *pos = *p; + return p; + } +} + +static int cgroup_pidlist_show(struct seq_file *s, void *v) +{ + seq_printf(s, "%d\n", *(int *)v); + + return 0; +} + +static ssize_t cgroup_tasks_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + return __cgroup_procs_write(of, buf, nbytes, off, false); +} + +static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct cgroup *cgrp; + + BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX); + + cgrp = cgroup_kn_lock_live(of->kn, false); + if (!cgrp) + return -ENODEV; + spin_lock(&release_agent_path_lock); + strlcpy(cgrp->root->release_agent_path, strstrip(buf), + sizeof(cgrp->root->release_agent_path)); + spin_unlock(&release_agent_path_lock); + cgroup_kn_unlock(of->kn); + return nbytes; +} + +static int cgroup_release_agent_show(struct seq_file *seq, void *v) +{ + struct cgroup *cgrp = seq_css(seq)->cgroup; + + spin_lock(&release_agent_path_lock); + seq_puts(seq, cgrp->root->release_agent_path); + spin_unlock(&release_agent_path_lock); + seq_putc(seq, '\n'); + return 0; +} + +static int cgroup_sane_behavior_show(struct seq_file *seq, void *v) +{ + seq_puts(seq, "0\n"); + return 0; +} + +static u64 cgroup_read_notify_on_release(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return notify_on_release(css->cgroup); +} + +static int cgroup_write_notify_on_release(struct cgroup_subsys_state *css, + struct cftype *cft, u64 val) +{ + if (val) + set_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags); + else + clear_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags); + return 0; +} + +static u64 cgroup_clone_children_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); +} + +static int cgroup_clone_children_write(struct cgroup_subsys_state *css, + struct cftype *cft, u64 val) +{ + if (val) + set_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); + else + clear_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); + return 0; +} + +/* cgroup core interface files for the legacy hierarchies */ +struct cftype cgroup1_base_files[] = { + { + .name = "cgroup.procs", + .seq_start = cgroup_pidlist_start, + .seq_next = cgroup_pidlist_next, + .seq_stop = cgroup_pidlist_stop, + .seq_show = cgroup_pidlist_show, + .private = CGROUP_FILE_PROCS, + .write = cgroup_procs_write, + }, + { + .name = "cgroup.clone_children", + .read_u64 = cgroup_clone_children_read, + .write_u64 = cgroup_clone_children_write, + }, + { + .name = "cgroup.sane_behavior", + .flags = CFTYPE_ONLY_ON_ROOT, + .seq_show = cgroup_sane_behavior_show, + }, + { + .name = "tasks", + .seq_start = cgroup_pidlist_start, + .seq_next = cgroup_pidlist_next, + .seq_stop = cgroup_pidlist_stop, + .seq_show = cgroup_pidlist_show, + .private = CGROUP_FILE_TASKS, + .write = cgroup_tasks_write, + }, + { + .name = "notify_on_release", + .read_u64 = cgroup_read_notify_on_release, + .write_u64 = cgroup_write_notify_on_release, + }, + { + .name = "release_agent", + .flags = CFTYPE_ONLY_ON_ROOT, + .seq_show = cgroup_release_agent_show, + .write = cgroup_release_agent_write, + .max_write_len = PATH_MAX - 1, + }, + { } /* terminate */ +}; + +/* Display information about each subsystem and each hierarchy */ +static int proc_cgroupstats_show(struct seq_file *m, void *v) +{ + struct cgroup_subsys *ss; + int i; + + seq_puts(m, "#subsys_name\thierarchy\tnum_cgroups\tenabled\n"); + /* + * ideally we don't want subsystems moving around while we do this. + * cgroup_mutex is also necessary to guarantee an atomic snapshot of + * subsys/hierarchy state. + */ + mutex_lock(&cgroup_mutex); + + for_each_subsys(ss, i) + seq_printf(m, "%s\t%d\t%d\t%d\n", + ss->legacy_name, ss->root->hierarchy_id, + atomic_read(&ss->root->nr_cgrps), + cgroup_ssid_enabled(i)); + + mutex_unlock(&cgroup_mutex); + return 0; +} + +static int cgroupstats_open(struct inode *inode, struct file *file) +{ + return single_open(file, proc_cgroupstats_show, NULL); +} + +const struct file_operations proc_cgroupstats_operations = { + .open = cgroupstats_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +/** + * cgroupstats_build - build and fill cgroupstats + * @stats: cgroupstats to fill information into + * @dentry: A dentry entry belonging to the cgroup for which stats have + * been requested. + * + * Build and fill cgroupstats so that taskstats can export it to user + * space. + */ +int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) +{ + struct kernfs_node *kn = kernfs_node_from_dentry(dentry); + struct cgroup *cgrp; + struct css_task_iter it; + struct task_struct *tsk; + + /* it should be kernfs_node belonging to cgroupfs and is a directory */ + if (dentry->d_sb->s_type != &cgroup_fs_type || !kn || + kernfs_type(kn) != KERNFS_DIR) + return -EINVAL; + + mutex_lock(&cgroup_mutex); + + /* + * We aren't being called from kernfs and there's no guarantee on + * @kn->priv's validity. For this and css_tryget_online_from_dir(), + * @kn->priv is RCU safe. Let's do the RCU dancing. + */ + rcu_read_lock(); + cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); + if (!cgrp || cgroup_is_dead(cgrp)) { + rcu_read_unlock(); + mutex_unlock(&cgroup_mutex); + return -ENOENT; + } + rcu_read_unlock(); + + css_task_iter_start(&cgrp->self, &it); + while ((tsk = css_task_iter_next(&it))) { + switch (tsk->state) { + case TASK_RUNNING: + stats->nr_running++; + break; + case TASK_INTERRUPTIBLE: + stats->nr_sleeping++; + break; + case TASK_UNINTERRUPTIBLE: + stats->nr_uninterruptible++; + break; + case TASK_STOPPED: + stats->nr_stopped++; + break; + default: + if (delayacct_is_task_waiting_on_io(tsk)) + stats->nr_io_wait++; + break; + } + } + css_task_iter_end(&it); + + mutex_unlock(&cgroup_mutex); + return 0; +} + +void cgroup1_check_for_release(struct cgroup *cgrp) +{ + if (notify_on_release(cgrp) && !cgroup_is_populated(cgrp) && + !css_has_online_children(&cgrp->self) && !cgroup_is_dead(cgrp)) + schedule_work(&cgrp->release_agent_work); +} + +/* + * Notify userspace when a cgroup is released, by running the + * configured release agent with the name of the cgroup (path + * relative to the root of cgroup file system) as the argument. + * + * Most likely, this user command will try to rmdir this cgroup. + * + * This races with the possibility that some other task will be + * attached to this cgroup before it is removed, or that some other + * user task will 'mkdir' a child cgroup of this cgroup. That's ok. + * The presumed 'rmdir' will fail quietly if this cgroup is no longer + * unused, and this cgroup will be reprieved from its death sentence, + * to continue to serve a useful existence. Next time it's released, + * we will get notified again, if it still has 'notify_on_release' set. + * + * The final arg to call_usermodehelper() is UMH_WAIT_EXEC, which + * means only wait until the task is successfully execve()'d. The + * separate release agent task is forked by call_usermodehelper(), + * then control in this thread returns here, without waiting for the + * release agent task. We don't bother to wait because the caller of + * this routine has no use for the exit status of the release agent + * task, so no sense holding our caller up for that. + */ +void cgroup1_release_agent(struct work_struct *work) +{ + struct cgroup *cgrp = + container_of(work, struct cgroup, release_agent_work); + char *pathbuf = NULL, *agentbuf = NULL; + char *argv[3], *envp[3]; + int ret; + + mutex_lock(&cgroup_mutex); + + pathbuf = kmalloc(PATH_MAX, GFP_KERNEL); + agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL); + if (!pathbuf || !agentbuf) + goto out; + + spin_lock_irq(&css_set_lock); + ret = cgroup_path_ns_locked(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns); + spin_unlock_irq(&css_set_lock); + if (ret < 0 || ret >= PATH_MAX) + goto out; + + argv[0] = agentbuf; + argv[1] = pathbuf; + argv[2] = NULL; + + /* minimal command environment */ + envp[0] = "HOME=/"; + envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin"; + envp[2] = NULL; + + mutex_unlock(&cgroup_mutex); + call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC); + goto out_free; +out: + mutex_unlock(&cgroup_mutex); +out_free: + kfree(agentbuf); + kfree(pathbuf); +} + +/* + * cgroup_rename - Only allow simple rename of directories in place. + */ +static int cgroup1_rename(struct kernfs_node *kn, struct kernfs_node *new_parent, + const char *new_name_str) +{ + struct cgroup *cgrp = kn->priv; + int ret; + + if (kernfs_type(kn) != KERNFS_DIR) + return -ENOTDIR; + if (kn->parent != new_parent) + return -EIO; + + /* + * We're gonna grab cgroup_mutex which nests outside kernfs + * active_ref. kernfs_rename() doesn't require active_ref + * protection. Break them before grabbing cgroup_mutex. + */ + kernfs_break_active_protection(new_parent); + kernfs_break_active_protection(kn); + + mutex_lock(&cgroup_mutex); + + ret = kernfs_rename(kn, new_parent, new_name_str); + if (!ret) + trace_cgroup_rename(cgrp); + + mutex_unlock(&cgroup_mutex); + + kernfs_unbreak_active_protection(kn); + kernfs_unbreak_active_protection(new_parent); + return ret; +} + +static int cgroup1_show_options(struct seq_file *seq, struct kernfs_root *kf_root) +{ + struct cgroup_root *root = cgroup_root_from_kf(kf_root); + struct cgroup_subsys *ss; + int ssid; + + for_each_subsys(ss, ssid) + if (root->subsys_mask & (1 << ssid)) + seq_show_option(seq, ss->legacy_name, NULL); + if (root->flags & CGRP_ROOT_NOPREFIX) + seq_puts(seq, ",noprefix"); + if (root->flags & CGRP_ROOT_XATTR) + seq_puts(seq, ",xattr"); + + spin_lock(&release_agent_path_lock); + if (strlen(root->release_agent_path)) + seq_show_option(seq, "release_agent", + root->release_agent_path); + spin_unlock(&release_agent_path_lock); + + if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags)) + seq_puts(seq, ",clone_children"); + if (strlen(root->name)) + seq_show_option(seq, "name", root->name); + return 0; +} + +static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) +{ + char *token, *o = data; + bool all_ss = false, one_ss = false; + u16 mask = U16_MAX; + struct cgroup_subsys *ss; + int nr_opts = 0; + int i; + +#ifdef CONFIG_CPUSETS + mask = ~((u16)1 << cpuset_cgrp_id); +#endif + + memset(opts, 0, sizeof(*opts)); + + while ((token = strsep(&o, ",")) != NULL) { + nr_opts++; + + if (!*token) + return -EINVAL; + if (!strcmp(token, "none")) { + /* Explicitly have no subsystems */ + opts->none = true; + continue; + } + if (!strcmp(token, "all")) { + /* Mutually exclusive option 'all' + subsystem name */ + if (one_ss) + return -EINVAL; + all_ss = true; + continue; + } + if (!strcmp(token, "noprefix")) { + opts->flags |= CGRP_ROOT_NOPREFIX; + continue; + } + if (!strcmp(token, "clone_children")) { + opts->cpuset_clone_children = true; + continue; + } + if (!strcmp(token, "xattr")) { + opts->flags |= CGRP_ROOT_XATTR; + continue; + } + if (!strncmp(token, "release_agent=", 14)) { + /* Specifying two release agents is forbidden */ + if (opts->release_agent) + return -EINVAL; + opts->release_agent = + kstrndup(token + 14, PATH_MAX - 1, GFP_KERNEL); + if (!opts->release_agent) + return -ENOMEM; + continue; + } + if (!strncmp(token, "name=", 5)) { + const char *name = token + 5; + /* Can't specify an empty name */ + if (!strlen(name)) + return -EINVAL; + /* Must match [\w.-]+ */ + for (i = 0; i < strlen(name); i++) { + char c = name[i]; + if (isalnum(c)) + continue; + if ((c == '.') || (c == '-') || (c == '_')) + continue; + return -EINVAL; + } + /* Specifying two names is forbidden */ + if (opts->name) + return -EINVAL; + opts->name = kstrndup(name, + MAX_CGROUP_ROOT_NAMELEN - 1, + GFP_KERNEL); + if (!opts->name) + return -ENOMEM; + + continue; + } + + for_each_subsys(ss, i) { + if (strcmp(token, ss->legacy_name)) + continue; + if (!cgroup_ssid_enabled(i)) + continue; + if (cgroup1_ssid_disabled(i)) + continue; + + /* Mutually exclusive option 'all' + subsystem name */ + if (all_ss) + return -EINVAL; + opts->subsys_mask |= (1 << i); + one_ss = true; + + break; + } + if (i == CGROUP_SUBSYS_COUNT) + return -ENOENT; + } + + /* + * If the 'all' option was specified select all the subsystems, + * otherwise if 'none', 'name=' and a subsystem name options were + * not specified, let's default to 'all' + */ + if (all_ss || (!one_ss && !opts->none && !opts->name)) + for_each_subsys(ss, i) + if (cgroup_ssid_enabled(i) && !cgroup1_ssid_disabled(i)) + opts->subsys_mask |= (1 << i); + + /* + * We either have to specify by name or by subsystems. (So all + * empty hierarchies must have a name). + */ + if (!opts->subsys_mask && !opts->name) + return -EINVAL; + + /* + * Option noprefix was introduced just for backward compatibility + * with the old cpuset, so we allow noprefix only if mounting just + * the cpuset subsystem. + */ + if ((opts->flags & CGRP_ROOT_NOPREFIX) && (opts->subsys_mask & mask)) + return -EINVAL; + + /* Can't specify "none" and some subsystems */ + if (opts->subsys_mask && opts->none) + return -EINVAL; + + return 0; +} + +static int cgroup1_remount(struct kernfs_root *kf_root, int *flags, char *data) +{ + int ret = 0; + struct cgroup_root *root = cgroup_root_from_kf(kf_root); + struct cgroup_sb_opts opts; + u16 added_mask, removed_mask; + + cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); + + /* See what subsystems are wanted */ + ret = parse_cgroupfs_options(data, &opts); + if (ret) + goto out_unlock; + + if (opts.subsys_mask != root->subsys_mask || opts.release_agent) + pr_warn("option changes via remount are deprecated (pid=%d comm=%s)\n", + task_tgid_nr(current), current->comm); + + added_mask = opts.subsys_mask & ~root->subsys_mask; + removed_mask = root->subsys_mask & ~opts.subsys_mask; + + /* Don't allow flags or name to change at remount */ + if ((opts.flags ^ root->flags) || + (opts.name && strcmp(opts.name, root->name))) { + pr_err("option or name mismatch, new: 0x%x \"%s\", old: 0x%x \"%s\"\n", + opts.flags, opts.name ?: "", root->flags, root->name); + ret = -EINVAL; + goto out_unlock; + } + + /* remounting is not allowed for populated hierarchies */ + if (!list_empty(&root->cgrp.self.children)) { + ret = -EBUSY; + goto out_unlock; + } + + ret = rebind_subsystems(root, added_mask); + if (ret) + goto out_unlock; + + WARN_ON(rebind_subsystems(&cgrp_dfl_root, removed_mask)); + + if (opts.release_agent) { + spin_lock(&release_agent_path_lock); + strcpy(root->release_agent_path, opts.release_agent); + spin_unlock(&release_agent_path_lock); + } + + trace_cgroup_remount(root); + + out_unlock: + kfree(opts.release_agent); + kfree(opts.name); + mutex_unlock(&cgroup_mutex); + return ret; +} + +struct kernfs_syscall_ops cgroup1_kf_syscall_ops = { + .rename = cgroup1_rename, + .show_options = cgroup1_show_options, + .remount_fs = cgroup1_remount, + .mkdir = cgroup_mkdir, + .rmdir = cgroup_rmdir, + .show_path = cgroup_show_path, +}; + +struct dentry *cgroup1_mount(struct file_system_type *fs_type, int flags, + void *data, unsigned long magic, + struct cgroup_namespace *ns) +{ + struct super_block *pinned_sb = NULL; + struct cgroup_sb_opts opts; + struct cgroup_root *root; + struct cgroup_subsys *ss; + struct dentry *dentry; + int i, ret; + + cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); + + /* First find the desired set of subsystems */ + ret = parse_cgroupfs_options(data, &opts); + if (ret) + goto out_unlock; + + /* + * Destruction of cgroup root is asynchronous, so subsystems may + * still be dying after the previous unmount. Let's drain the + * dying subsystems. We just need to ensure that the ones + * unmounted previously finish dying and don't care about new ones + * starting. Testing ref liveliness is good enough. + */ + for_each_subsys(ss, i) { + if (!(opts.subsys_mask & (1 << i)) || + ss->root == &cgrp_dfl_root) + continue; + + if (!percpu_ref_tryget_live(&ss->root->cgrp.self.refcnt)) { + mutex_unlock(&cgroup_mutex); + msleep(10); + ret = restart_syscall(); + goto out_free; + } + cgroup_put(&ss->root->cgrp); + } + + for_each_root(root) { + bool name_match = false; + + if (root == &cgrp_dfl_root) + continue; + + /* + * If we asked for a name then it must match. Also, if + * name matches but sybsys_mask doesn't, we should fail. + * Remember whether name matched. + */ + if (opts.name) { + if (strcmp(opts.name, root->name)) + continue; + name_match = true; + } + + /* + * If we asked for subsystems (or explicitly for no + * subsystems) then they must match. + */ + if ((opts.subsys_mask || opts.none) && + (opts.subsys_mask != root->subsys_mask)) { + if (!name_match) + continue; + ret = -EBUSY; + goto out_unlock; + } + + if (root->flags ^ opts.flags) + pr_warn("new mount options do not match the existing superblock, will be ignored\n"); + + /* + * We want to reuse @root whose lifetime is governed by its + * ->cgrp. Let's check whether @root is alive and keep it + * that way. As cgroup_kill_sb() can happen anytime, we + * want to block it by pinning the sb so that @root doesn't + * get killed before mount is complete. + * + * With the sb pinned, tryget_live can reliably indicate + * whether @root can be reused. If it's being killed, + * drain it. We can use wait_queue for the wait but this + * path is super cold. Let's just sleep a bit and retry. + */ + pinned_sb = kernfs_pin_sb(root->kf_root, NULL); + if (IS_ERR(pinned_sb) || + !percpu_ref_tryget_live(&root->cgrp.self.refcnt)) { + mutex_unlock(&cgroup_mutex); + if (!IS_ERR_OR_NULL(pinned_sb)) + deactivate_super(pinned_sb); + msleep(10); + ret = restart_syscall(); + goto out_free; + } + + ret = 0; + goto out_unlock; + } + + /* + * No such thing, create a new one. name= matching without subsys + * specification is allowed for already existing hierarchies but we + * can't create new one without subsys specification. + */ + if (!opts.subsys_mask && !opts.none) { + ret = -EINVAL; + goto out_unlock; + } + + /* Hierarchies may only be created in the initial cgroup namespace. */ + if (ns != &init_cgroup_ns) { + ret = -EPERM; + goto out_unlock; + } + + root = kzalloc(sizeof(*root), GFP_KERNEL); + if (!root) { + ret = -ENOMEM; + goto out_unlock; + } + + init_cgroup_root(root, &opts); + + ret = cgroup_setup_root(root, opts.subsys_mask); + if (ret) + cgroup_free_root(root); + +out_unlock: + mutex_unlock(&cgroup_mutex); +out_free: + kfree(opts.release_agent); + kfree(opts.name); + + if (ret) + return ERR_PTR(ret); + + dentry = cgroup_do_mount(&cgroup_fs_type, flags, root, + CGROUP_SUPER_MAGIC, ns); + + /* + * If @pinned_sb, we're reusing an existing root and holding an + * extra ref on its sb. Mount is complete. Put the extra ref. + */ + if (pinned_sb) + deactivate_super(pinned_sb); + + return dentry; +} + +static int __init cgroup1_wq_init(void) +{ + /* + * Used to destroy pidlists and separate to serve as flush domain. + * Cap @max_active to 1 too. + */ + cgroup_pidlist_destroy_wq = alloc_workqueue("cgroup_pidlist_destroy", + 0, 1); + BUG_ON(!cgroup_pidlist_destroy_wq); + return 0; +} +core_initcall(cgroup1_wq_init); + +static int __init cgroup_no_v1(char *str) +{ + struct cgroup_subsys *ss; + char *token; + int i; + + while ((token = strsep(&str, ",")) != NULL) { + if (!*token) + continue; + + if (!strcmp(token, "all")) { + cgroup_no_v1_mask = U16_MAX; + break; + } + + for_each_subsys(ss, i) { + if (strcmp(token, ss->name) && + strcmp(token, ss->legacy_name)) + continue; + + cgroup_no_v1_mask |= 1 << i; + } + } + return 1; +} +__setup("cgroup_no_v1=", cgroup_no_v1); + + +#ifdef CONFIG_CGROUP_DEBUG +static struct cgroup_subsys_state * +debug_css_alloc(struct cgroup_subsys_state *parent_css) +{ + struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL); + + if (!css) + return ERR_PTR(-ENOMEM); + + return css; +} + +static void debug_css_free(struct cgroup_subsys_state *css) +{ + kfree(css); +} + +static u64 debug_taskcount_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return cgroup_task_count(css->cgroup); +} + +static u64 current_css_set_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return (u64)(unsigned long)current->cgroups; +} + +static u64 current_css_set_refcount_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + u64 count; + + rcu_read_lock(); + count = atomic_read(&task_css_set(current)->refcount); + rcu_read_unlock(); + return count; +} + +static int current_css_set_cg_links_read(struct seq_file *seq, void *v) +{ + struct cgrp_cset_link *link; + struct css_set *cset; + char *name_buf; + + name_buf = kmalloc(NAME_MAX + 1, GFP_KERNEL); + if (!name_buf) + return -ENOMEM; + + spin_lock_irq(&css_set_lock); + rcu_read_lock(); + cset = rcu_dereference(current->cgroups); + list_for_each_entry(link, &cset->cgrp_links, cgrp_link) { + struct cgroup *c = link->cgrp; + + cgroup_name(c, name_buf, NAME_MAX + 1); + seq_printf(seq, "Root %d group %s\n", + c->root->hierarchy_id, name_buf); + } + rcu_read_unlock(); + spin_unlock_irq(&css_set_lock); + kfree(name_buf); + return 0; +} + +#define MAX_TASKS_SHOWN_PER_CSS 25 +static int cgroup_css_links_read(struct seq_file *seq, void *v) +{ + struct cgroup_subsys_state *css = seq_css(seq); + struct cgrp_cset_link *link; + + spin_lock_irq(&css_set_lock); + list_for_each_entry(link, &css->cgroup->cset_links, cset_link) { + struct css_set *cset = link->cset; + struct task_struct *task; + int count = 0; + + seq_printf(seq, "css_set %p\n", cset); + + list_for_each_entry(task, &cset->tasks, cg_list) { + if (count++ > MAX_TASKS_SHOWN_PER_CSS) + goto overflow; + seq_printf(seq, " task %d\n", task_pid_vnr(task)); + } + + list_for_each_entry(task, &cset->mg_tasks, cg_list) { + if (count++ > MAX_TASKS_SHOWN_PER_CSS) + goto overflow; + seq_printf(seq, " task %d\n", task_pid_vnr(task)); + } + continue; + overflow: + seq_puts(seq, " ...\n"); + } + spin_unlock_irq(&css_set_lock); + return 0; +} + +static u64 releasable_read(struct cgroup_subsys_state *css, struct cftype *cft) +{ + return (!cgroup_is_populated(css->cgroup) && + !css_has_online_children(&css->cgroup->self)); +} + +static struct cftype debug_files[] = { + { + .name = "taskcount", + .read_u64 = debug_taskcount_read, + }, + + { + .name = "current_css_set", + .read_u64 = current_css_set_read, + }, + + { + .name = "current_css_set_refcount", + .read_u64 = current_css_set_refcount_read, + }, + + { + .name = "current_css_set_cg_links", + .seq_show = current_css_set_cg_links_read, + }, + + { + .name = "cgroup_css_links", + .seq_show = cgroup_css_links_read, + }, + + { + .name = "releasable", + .read_u64 = releasable_read, + }, + + { } /* terminate */ +}; + +struct cgroup_subsys debug_cgrp_subsys = { + .css_alloc = debug_css_alloc, + .css_free = debug_css_free, + .legacy_cftypes = debug_files, +}; +#endif /* CONFIG_CGROUP_DEBUG */ diff --git a/kernel/cgroup.c b/kernel/cgroup/cgroup.c index 53bbca7c4859..e8f87bf9840c 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -28,15 +28,13 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/cgroup.h> +#include "cgroup-internal.h" + #include <linux/cred.h> -#include <linux/ctype.h> #include <linux/errno.h> #include <linux/init_task.h> #include <linux/kernel.h> -#include <linux/list.h> #include <linux/magic.h> -#include <linux/mm.h> #include <linux/mutex.h> #include <linux/mount.h> #include <linux/pagemap.h> @@ -47,16 +45,9 @@ #include <linux/spinlock.h> #include <linux/percpu-rwsem.h> #include <linux/string.h> -#include <linux/sort.h> -#include <linux/kmod.h> -#include <linux/delayacct.h> -#include <linux/cgroupstats.h> #include <linux/hashtable.h> -#include <linux/pid_namespace.h> #include <linux/idr.h> -#include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */ #include <linux/kthread.h> -#include <linux/delay.h> #include <linux/atomic.h> #include <linux/cpuset.h> #include <linux/proc_ns.h> @@ -67,14 +58,6 @@ #define CREATE_TRACE_POINTS #include <trace/events/cgroup.h> -/* - * pidlists linger the following amount before being destroyed. The goal - * is avoiding frequent destruction in the middle of consecutive read calls - * Expiring in the middle is a performance problem not a correctness one. - * 1 sec should be enough. - */ -#define CGROUP_PIDLIST_DESTROY_DELAY HZ - #define CGROUP_FILE_NAME_MAX (MAX_CGROUP_TYPE_NAMELEN + \ MAX_CFTYPE_NAME + 2) @@ -88,14 +71,12 @@ * These locks are exported if CONFIG_PROVE_RCU so that accessors in * cgroup.h can use them for lockdep annotations. */ -#ifdef CONFIG_PROVE_RCU DEFINE_MUTEX(cgroup_mutex); DEFINE_SPINLOCK(css_set_lock); + +#ifdef CONFIG_PROVE_RCU EXPORT_SYMBOL_GPL(cgroup_mutex); EXPORT_SYMBOL_GPL(css_set_lock); -#else -static DEFINE_MUTEX(cgroup_mutex); -static DEFINE_SPINLOCK(css_set_lock); #endif /* @@ -110,12 +91,6 @@ static DEFINE_SPINLOCK(cgroup_idr_lock); */ static DEFINE_SPINLOCK(cgroup_file_kn_lock); -/* - * Protects cgroup_subsys->release_agent_path. Modifying it also requires - * cgroup_mutex. Reading requires either cgroup_mutex or this spinlock. - */ -static DEFINE_SPINLOCK(release_agent_path_lock); - struct percpu_rw_semaphore cgroup_threadgroup_rwsem; #define cgroup_assert_mutex_or_rcu_locked() \ @@ -131,15 +106,9 @@ struct percpu_rw_semaphore cgroup_threadgroup_rwsem; */ static struct workqueue_struct *cgroup_destroy_wq; -/* - * pidlist destructions need to be flushed on cgroup destruction. Use a - * separate workqueue as flush domain. - */ -static struct workqueue_struct *cgroup_pidlist_destroy_wq; - /* generate an array of cgroup subsystem pointers */ #define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys, -static struct cgroup_subsys *cgroup_subsys[] = { +struct cgroup_subsys *cgroup_subsys[] = { #include <linux/cgroup_subsys.h> }; #undef SUBSYS @@ -186,18 +155,14 @@ EXPORT_SYMBOL_GPL(cgrp_dfl_root); */ static bool cgrp_dfl_visible; -/* Controllers blocked by the commandline in v1 */ -static u16 cgroup_no_v1_mask; - /* some controllers are not supported in the default hierarchy */ static u16 cgrp_dfl_inhibit_ss_mask; /* some controllers are implicitly enabled on the default hierarchy */ -static unsigned long cgrp_dfl_implicit_ss_mask; +static u16 cgrp_dfl_implicit_ss_mask; /* The list of hierarchy roots */ - -static LIST_HEAD(cgroup_roots); +LIST_HEAD(cgroup_roots); static int cgroup_root_count; /* hierarchy ID allocation and mapping, protected by cgroup_mutex */ @@ -213,13 +178,13 @@ static DEFINE_IDR(cgroup_hierarchy_idr); static u64 css_serial_nr_next = 1; /* - * These bitmask flags indicate whether tasks in the fork and exit paths have - * fork/exit handlers to call. This avoids us having to do extra work in the - * fork/exit path to check which subsystems have fork/exit callbacks. + * These bitmasks identify subsystems with specific features to avoid + * having to do iterative checks repeatedly. */ static u16 have_fork_callback __read_mostly; static u16 have_exit_callback __read_mostly; static u16 have_free_callback __read_mostly; +static u16 have_canfork_callback __read_mostly; /* cgroup namespace for init task */ struct cgroup_namespace init_cgroup_ns = { @@ -230,15 +195,9 @@ struct cgroup_namespace init_cgroup_ns = { .root_cset = &init_css_set, }; -/* Ditto for the can_fork callback. */ -static u16 have_canfork_callback __read_mostly; - static struct file_system_type cgroup2_fs_type; -static struct cftype cgroup_dfl_base_files[]; -static struct cftype cgroup_legacy_base_files[]; +static struct cftype cgroup_base_files[]; -static int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask); -static void cgroup_lock_and_drain_offline(struct cgroup *cgrp); static int cgroup_apply_control(struct cgroup *cgrp); static void cgroup_finalize_control(struct cgroup *cgrp, int ret); static void css_task_iter_advance(struct css_task_iter *it); @@ -259,7 +218,7 @@ static int cgroup_addrm_files(struct cgroup_subsys_state *css, * is fine for individual subsystems but unsuitable for cgroup core. This * is slower static_key_enabled() based test indexed by @ssid. */ -static bool cgroup_ssid_enabled(int ssid) +bool cgroup_ssid_enabled(int ssid) { if (CGROUP_SUBSYS_COUNT == 0) return false; @@ -267,11 +226,6 @@ static bool cgroup_ssid_enabled(int ssid) return static_key_enabled(cgroup_subsys_enabled_key[ssid]); } -static bool cgroup_ssid_no_v1(int ssid) -{ - return cgroup_no_v1_mask & (1 << ssid); -} - /** * cgroup_on_dfl - test whether a cgroup is on the default hierarchy * @cgrp: the cgroup of interest @@ -325,7 +279,7 @@ static bool cgroup_ssid_no_v1(int ssid) * * - debug: disallowed on the default hierarchy. */ -static bool cgroup_on_dfl(const struct cgroup *cgrp) +bool cgroup_on_dfl(const struct cgroup *cgrp) { return cgrp->root == &cgrp_dfl_root; } @@ -481,12 +435,6 @@ out_unlock: return css; } -/* convenient tests for these bits */ -static inline bool cgroup_is_dead(const struct cgroup *cgrp) -{ - return !(cgrp->self.flags & CSS_ONLINE); -} - static void cgroup_get(struct cgroup *cgrp) { WARN_ON_ONCE(cgroup_is_dead(cgrp)); @@ -518,11 +466,6 @@ struct cgroup_subsys_state *of_css(struct kernfs_open_file *of) } EXPORT_SYMBOL_GPL(of_css); -static int notify_on_release(const struct cgroup *cgrp) -{ - return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags); -} - /** * for_each_css - iterate all css's of a cgroup * @css: the iteration cursor @@ -553,15 +496,6 @@ static int notify_on_release(const struct cgroup *cgrp) else /** - * for_each_subsys - iterate all enabled cgroup subsystems - * @ss: the iteration cursor - * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end - */ -#define for_each_subsys(ss, ssid) \ - for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT && \ - (((ss) = cgroup_subsys[ssid]) || true); (ssid)++) - -/** * do_each_subsys_mask - filter for_each_subsys with a bitmask * @ss: the iteration cursor * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end @@ -585,10 +519,6 @@ static int notify_on_release(const struct cgroup *cgrp) } \ } while (false) -/* iterate across the hierarchies */ -#define for_each_root(root) \ - list_for_each_entry((root), &cgroup_roots, root_list) - /* iterate over child cgrps, lock should be held throughout iteration */ #define cgroup_for_each_live_child(child, cgrp) \ list_for_each_entry((child), &(cgrp)->self.children, self.sibling) \ @@ -615,29 +545,6 @@ static int notify_on_release(const struct cgroup *cgrp) ; \ else -static void cgroup_release_agent(struct work_struct *work); -static void check_for_release(struct cgroup *cgrp); - -/* - * A cgroup can be associated with multiple css_sets as different tasks may - * belong to different cgroups on different hierarchies. In the other - * direction, a css_set is naturally associated with multiple cgroups. - * This M:N relationship is represented by the following link structure - * which exists for each association and allows traversing the associations - * from both sides. - */ -struct cgrp_cset_link { - /* the cgroup and css_set this link associates */ - struct cgroup *cgrp; - struct css_set *cset; - - /* list of cgrp_cset_links anchored at cgrp->cset_links */ - struct list_head cset_link; - - /* list of cgrp_cset_links anchored at css_set->cgrp_links */ - struct list_head cgrp_link; -}; - /* * The default css_set - used by init and its children prior to any * hierarchies being mounted. It contains a pointer to the root state @@ -647,12 +554,12 @@ struct cgrp_cset_link { */ struct css_set init_css_set = { .refcount = ATOMIC_INIT(1), - .cgrp_links = LIST_HEAD_INIT(init_css_set.cgrp_links), .tasks = LIST_HEAD_INIT(init_css_set.tasks), .mg_tasks = LIST_HEAD_INIT(init_css_set.mg_tasks), + .task_iters = LIST_HEAD_INIT(init_css_set.task_iters), + .cgrp_links = LIST_HEAD_INIT(init_css_set.cgrp_links), .mg_preload_node = LIST_HEAD_INIT(init_css_set.mg_preload_node), .mg_node = LIST_HEAD_INIT(init_css_set.mg_node), - .task_iters = LIST_HEAD_INIT(init_css_set.task_iters), }; static int css_set_count = 1; /* 1 for init_css_set */ @@ -699,7 +606,7 @@ static void cgroup_update_populated(struct cgroup *cgrp, bool populated) if (!trigger) break; - check_for_release(cgrp); + cgroup1_check_for_release(cgrp); cgroup_file_notify(&cgrp->events_file); cgrp = cgroup_parent(cgrp); @@ -808,7 +715,7 @@ static unsigned long css_set_hash(struct cgroup_subsys_state *css[]) return key; } -static void put_css_set_locked(struct css_set *cset) +void put_css_set_locked(struct css_set *cset) { struct cgrp_cset_link *link, *tmp_link; struct cgroup_subsys *ss; @@ -838,31 +745,6 @@ static void put_css_set_locked(struct css_set *cset) kfree_rcu(cset, rcu_head); } -static void put_css_set(struct css_set *cset) -{ - unsigned long flags; - - /* - * Ensure that the refcount doesn't hit zero while any readers - * can see it. Similar to atomic_dec_and_lock(), but for an - * rwlock - */ - if (atomic_add_unless(&cset->refcount, -1, 1)) - return; - - spin_lock_irqsave(&css_set_lock, flags); - put_css_set_locked(cset); - spin_unlock_irqrestore(&css_set_lock, flags); -} - -/* - * refcounted get/put for css_set objects - */ -static inline void get_css_set(struct css_set *cset) -{ - atomic_inc(&cset->refcount); -} - /** * compare_css_sets - helper function for find_existing_css_set(). * @cset: candidate css_set being tested @@ -1095,13 +977,13 @@ static struct css_set *find_css_set(struct css_set *old_cset, } atomic_set(&cset->refcount, 1); - INIT_LIST_HEAD(&cset->cgrp_links); INIT_LIST_HEAD(&cset->tasks); INIT_LIST_HEAD(&cset->mg_tasks); - INIT_LIST_HEAD(&cset->mg_preload_node); - INIT_LIST_HEAD(&cset->mg_node); INIT_LIST_HEAD(&cset->task_iters); INIT_HLIST_NODE(&cset->hlist); + INIT_LIST_HEAD(&cset->cgrp_links); + INIT_LIST_HEAD(&cset->mg_preload_node); + INIT_LIST_HEAD(&cset->mg_node); /* Copy the set of subsystem state objects generated in * find_existing_css_set() */ @@ -1138,7 +1020,7 @@ static struct css_set *find_css_set(struct css_set *old_cset, return cset; } -static struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root) +struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root) { struct cgroup *root_cgrp = kf_root->kn->priv; @@ -1166,7 +1048,7 @@ static void cgroup_exit_root_id(struct cgroup_root *root) idr_remove(&cgroup_hierarchy_idr, root->hierarchy_id); } -static void cgroup_free_root(struct cgroup_root *root) +void cgroup_free_root(struct cgroup_root *root) { if (root) { idr_destroy(&root->cgroup_idr); @@ -1283,8 +1165,8 @@ static struct cgroup *cset_cgroup_from_root(struct css_set *cset, * Return the cgroup for "task" from the given hierarchy. Must be * called with cgroup_mutex and css_set_lock held. */ -static struct cgroup *task_cgroup_from_root(struct task_struct *task, - struct cgroup_root *root) +struct cgroup *task_cgroup_from_root(struct task_struct *task, + struct cgroup_root *root) { /* * No need to lock the task - since we hold cgroup_mutex the @@ -1321,7 +1203,6 @@ static struct cgroup *task_cgroup_from_root(struct task_struct *task, */ static struct kernfs_syscall_ops cgroup_kf_syscall_ops; -static const struct file_operations proc_cgroupstats_operations; static char *cgroup_file_name(struct cgroup *cgrp, const struct cftype *cft, char *buf) @@ -1415,7 +1296,7 @@ static u16 cgroup_calc_subtree_ss_mask(u16 subtree_control, u16 this_ss_mask) * inaccessible any time. If the caller intends to continue to access the * cgroup, it should pin it before invoking this function. */ -static void cgroup_kn_unlock(struct kernfs_node *kn) +void cgroup_kn_unlock(struct kernfs_node *kn) { struct cgroup *cgrp; @@ -1447,8 +1328,7 @@ static void cgroup_kn_unlock(struct kernfs_node *kn) * locking under kernfs active protection and allows all kernfs operations * including self-removal. */ -static struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn, - bool drain_offline) +struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn, bool drain_offline) { struct cgroup *cgrp; @@ -1532,9 +1412,9 @@ static int css_populate_dir(struct cgroup_subsys_state *css) if (!css->ss) { if (cgroup_on_dfl(cgrp)) - cfts = cgroup_dfl_base_files; + cfts = cgroup_base_files; else - cfts = cgroup_legacy_base_files; + cfts = cgroup1_base_files; return cgroup_addrm_files(&cgrp->self, cgrp, cfts, true); } @@ -1559,7 +1439,7 @@ err: return ret; } -static int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) +int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) { struct cgroup *dcgrp = &dst_root->cgrp; struct cgroup_subsys *ss; @@ -1629,8 +1509,8 @@ static int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) return 0; } -static int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node, - struct kernfs_root *kf_root) +int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node, + struct kernfs_root *kf_root) { int len = 0; char *buf = NULL; @@ -1656,237 +1536,10 @@ static int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node, return len; } -static int cgroup_show_options(struct seq_file *seq, - struct kernfs_root *kf_root) -{ - struct cgroup_root *root = cgroup_root_from_kf(kf_root); - struct cgroup_subsys *ss; - int ssid; - - if (root != &cgrp_dfl_root) - for_each_subsys(ss, ssid) - if (root->subsys_mask & (1 << ssid)) - seq_show_option(seq, ss->legacy_name, NULL); - if (root->flags & CGRP_ROOT_NOPREFIX) - seq_puts(seq, ",noprefix"); - if (root->flags & CGRP_ROOT_XATTR) - seq_puts(seq, ",xattr"); - - spin_lock(&release_agent_path_lock); - if (strlen(root->release_agent_path)) - seq_show_option(seq, "release_agent", - root->release_agent_path); - spin_unlock(&release_agent_path_lock); - - if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags)) - seq_puts(seq, ",clone_children"); - if (strlen(root->name)) - seq_show_option(seq, "name", root->name); - return 0; -} - -struct cgroup_sb_opts { - u16 subsys_mask; - unsigned int flags; - char *release_agent; - bool cpuset_clone_children; - char *name; - /* User explicitly requested empty subsystem */ - bool none; -}; - -static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) -{ - char *token, *o = data; - bool all_ss = false, one_ss = false; - u16 mask = U16_MAX; - struct cgroup_subsys *ss; - int nr_opts = 0; - int i; - -#ifdef CONFIG_CPUSETS - mask = ~((u16)1 << cpuset_cgrp_id); -#endif - - memset(opts, 0, sizeof(*opts)); - - while ((token = strsep(&o, ",")) != NULL) { - nr_opts++; - - if (!*token) - return -EINVAL; - if (!strcmp(token, "none")) { - /* Explicitly have no subsystems */ - opts->none = true; - continue; - } - if (!strcmp(token, "all")) { - /* Mutually exclusive option 'all' + subsystem name */ - if (one_ss) - return -EINVAL; - all_ss = true; - continue; - } - if (!strcmp(token, "noprefix")) { - opts->flags |= CGRP_ROOT_NOPREFIX; - continue; - } - if (!strcmp(token, "clone_children")) { - opts->cpuset_clone_children = true; - continue; - } - if (!strcmp(token, "xattr")) { - opts->flags |= CGRP_ROOT_XATTR; - continue; - } - if (!strncmp(token, "release_agent=", 14)) { - /* Specifying two release agents is forbidden */ - if (opts->release_agent) - return -EINVAL; - opts->release_agent = - kstrndup(token + 14, PATH_MAX - 1, GFP_KERNEL); - if (!opts->release_agent) - return -ENOMEM; - continue; - } - if (!strncmp(token, "name=", 5)) { - const char *name = token + 5; - /* Can't specify an empty name */ - if (!strlen(name)) - return -EINVAL; - /* Must match [\w.-]+ */ - for (i = 0; i < strlen(name); i++) { - char c = name[i]; - if (isalnum(c)) - continue; - if ((c == '.') || (c == '-') || (c == '_')) - continue; - return -EINVAL; - } - /* Specifying two names is forbidden */ - if (opts->name) - return -EINVAL; - opts->name = kstrndup(name, - MAX_CGROUP_ROOT_NAMELEN - 1, - GFP_KERNEL); - if (!opts->name) - return -ENOMEM; - - continue; - } - - for_each_subsys(ss, i) { - if (strcmp(token, ss->legacy_name)) - continue; - if (!cgroup_ssid_enabled(i)) - continue; - if (cgroup_ssid_no_v1(i)) - continue; - - /* Mutually exclusive option 'all' + subsystem name */ - if (all_ss) - return -EINVAL; - opts->subsys_mask |= (1 << i); - one_ss = true; - - break; - } - if (i == CGROUP_SUBSYS_COUNT) - return -ENOENT; - } - - /* - * If the 'all' option was specified select all the subsystems, - * otherwise if 'none', 'name=' and a subsystem name options were - * not specified, let's default to 'all' - */ - if (all_ss || (!one_ss && !opts->none && !opts->name)) - for_each_subsys(ss, i) - if (cgroup_ssid_enabled(i) && !cgroup_ssid_no_v1(i)) - opts->subsys_mask |= (1 << i); - - /* - * We either have to specify by name or by subsystems. (So all - * empty hierarchies must have a name). - */ - if (!opts->subsys_mask && !opts->name) - return -EINVAL; - - /* - * Option noprefix was introduced just for backward compatibility - * with the old cpuset, so we allow noprefix only if mounting just - * the cpuset subsystem. - */ - if ((opts->flags & CGRP_ROOT_NOPREFIX) && (opts->subsys_mask & mask)) - return -EINVAL; - - /* Can't specify "none" and some subsystems */ - if (opts->subsys_mask && opts->none) - return -EINVAL; - - return 0; -} - static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data) { - int ret = 0; - struct cgroup_root *root = cgroup_root_from_kf(kf_root); - struct cgroup_sb_opts opts; - u16 added_mask, removed_mask; - - if (root == &cgrp_dfl_root) { - pr_err("remount is not allowed\n"); - return -EINVAL; - } - - cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); - - /* See what subsystems are wanted */ - ret = parse_cgroupfs_options(data, &opts); - if (ret) - goto out_unlock; - - if (opts.subsys_mask != root->subsys_mask || opts.release_agent) - pr_warn("option changes via remount are deprecated (pid=%d comm=%s)\n", - task_tgid_nr(current), current->comm); - - added_mask = opts.subsys_mask & ~root->subsys_mask; - removed_mask = root->subsys_mask & ~opts.subsys_mask; - - /* Don't allow flags or name to change at remount */ - if ((opts.flags ^ root->flags) || - (opts.name && strcmp(opts.name, root->name))) { - pr_err("option or name mismatch, new: 0x%x \"%s\", old: 0x%x \"%s\"\n", - opts.flags, opts.name ?: "", root->flags, root->name); - ret = -EINVAL; - goto out_unlock; - } - - /* remounting is not allowed for populated hierarchies */ - if (!list_empty(&root->cgrp.self.children)) { - ret = -EBUSY; - goto out_unlock; - } - - ret = rebind_subsystems(root, added_mask); - if (ret) - goto out_unlock; - - WARN_ON(rebind_subsystems(&cgrp_dfl_root, removed_mask)); - - if (opts.release_agent) { - spin_lock(&release_agent_path_lock); - strcpy(root->release_agent_path, opts.release_agent); - spin_unlock(&release_agent_path_lock); - } - - trace_cgroup_remount(root); - - out_unlock: - kfree(opts.release_agent); - kfree(opts.name); - mutex_unlock(&cgroup_mutex); - return ret; + pr_err("remount is not allowed\n"); + return -EINVAL; } /* @@ -1964,11 +1617,10 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp) INIT_LIST_HEAD(&cgrp->e_csets[ssid]); init_waitqueue_head(&cgrp->offline_waitq); - INIT_WORK(&cgrp->release_agent_work, cgroup_release_agent); + INIT_WORK(&cgrp->release_agent_work, cgroup1_release_agent); } -static void init_cgroup_root(struct cgroup_root *root, - struct cgroup_sb_opts *opts) +void init_cgroup_root(struct cgroup_root *root, struct cgroup_sb_opts *opts) { struct cgroup *cgrp = &root->cgrp; @@ -1987,10 +1639,11 @@ static void init_cgroup_root(struct cgroup_root *root, set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags); } -static int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask) +int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask) { LIST_HEAD(tmp_links); struct cgroup *root_cgrp = &root->cgrp; + struct kernfs_syscall_ops *kf_sops; struct css_set *cset; int i, ret; @@ -2022,7 +1675,10 @@ static int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask) if (ret) goto cancel_ref; - root->kf_root = kernfs_create_root(&cgroup_kf_syscall_ops, + kf_sops = root == &cgrp_dfl_root ? + &cgroup_kf_syscall_ops : &cgroup1_kf_syscall_ops; + + root->kf_root = kernfs_create_root(kf_sops, KERNFS_ROOT_CREATE_DEACTIVATED, root_cgrp); if (IS_ERR(root->kf_root)) { @@ -2080,182 +1736,18 @@ out: return ret; } -static struct dentry *cgroup_mount(struct file_system_type *fs_type, - int flags, const char *unused_dev_name, - void *data) +struct dentry *cgroup_do_mount(struct file_system_type *fs_type, int flags, + struct cgroup_root *root, unsigned long magic, + struct cgroup_namespace *ns) { - bool is_v2 = fs_type == &cgroup2_fs_type; - struct super_block *pinned_sb = NULL; - struct cgroup_namespace *ns = current->nsproxy->cgroup_ns; - struct cgroup_subsys *ss; - struct cgroup_root *root; - struct cgroup_sb_opts opts; struct dentry *dentry; - int ret; - int i; bool new_sb; - get_cgroup_ns(ns); - - /* Check if the caller has permission to mount. */ - if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN)) { - put_cgroup_ns(ns); - return ERR_PTR(-EPERM); - } - - /* - * The first time anyone tries to mount a cgroup, enable the list - * linking each css_set to its tasks and fix up all existing tasks. - */ - if (!use_task_css_set_links) - cgroup_enable_task_cg_lists(); - - if (is_v2) { - if (data) { - pr_err("cgroup2: unknown option \"%s\"\n", (char *)data); - put_cgroup_ns(ns); - return ERR_PTR(-EINVAL); - } - cgrp_dfl_visible = true; - root = &cgrp_dfl_root; - cgroup_get(&root->cgrp); - goto out_mount; - } - - cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); - - /* First find the desired set of subsystems */ - ret = parse_cgroupfs_options(data, &opts); - if (ret) - goto out_unlock; - - /* - * Destruction of cgroup root is asynchronous, so subsystems may - * still be dying after the previous unmount. Let's drain the - * dying subsystems. We just need to ensure that the ones - * unmounted previously finish dying and don't care about new ones - * starting. Testing ref liveliness is good enough. - */ - for_each_subsys(ss, i) { - if (!(opts.subsys_mask & (1 << i)) || - ss->root == &cgrp_dfl_root) - continue; - - if (!percpu_ref_tryget_live(&ss->root->cgrp.self.refcnt)) { - mutex_unlock(&cgroup_mutex); - msleep(10); - ret = restart_syscall(); - goto out_free; - } - cgroup_put(&ss->root->cgrp); - } - - for_each_root(root) { - bool name_match = false; - - if (root == &cgrp_dfl_root) - continue; - - /* - * If we asked for a name then it must match. Also, if - * name matches but sybsys_mask doesn't, we should fail. - * Remember whether name matched. - */ - if (opts.name) { - if (strcmp(opts.name, root->name)) - continue; - name_match = true; - } - - /* - * If we asked for subsystems (or explicitly for no - * subsystems) then they must match. - */ - if ((opts.subsys_mask || opts.none) && - (opts.subsys_mask != root->subsys_mask)) { - if (!name_match) - continue; - ret = -EBUSY; - goto out_unlock; - } - - if (root->flags ^ opts.flags) - pr_warn("new mount options do not match the existing superblock, will be ignored\n"); - - /* - * We want to reuse @root whose lifetime is governed by its - * ->cgrp. Let's check whether @root is alive and keep it - * that way. As cgroup_kill_sb() can happen anytime, we - * want to block it by pinning the sb so that @root doesn't - * get killed before mount is complete. - * - * With the sb pinned, tryget_live can reliably indicate - * whether @root can be reused. If it's being killed, - * drain it. We can use wait_queue for the wait but this - * path is super cold. Let's just sleep a bit and retry. - */ - pinned_sb = kernfs_pin_sb(root->kf_root, NULL); - if (IS_ERR(pinned_sb) || - !percpu_ref_tryget_live(&root->cgrp.self.refcnt)) { - mutex_unlock(&cgroup_mutex); - if (!IS_ERR_OR_NULL(pinned_sb)) - deactivate_super(pinned_sb); - msleep(10); - ret = restart_syscall(); - goto out_free; - } - - ret = 0; - goto out_unlock; - } + dentry = kernfs_mount(fs_type, flags, root->kf_root, magic, &new_sb); /* - * No such thing, create a new one. name= matching without subsys - * specification is allowed for already existing hierarchies but we - * can't create new one without subsys specification. - */ - if (!opts.subsys_mask && !opts.none) { - ret = -EINVAL; - goto out_unlock; - } - - /* Hierarchies may only be created in the initial cgroup namespace. */ - if (ns != &init_cgroup_ns) { - ret = -EPERM; - goto out_unlock; - } - - root = kzalloc(sizeof(*root), GFP_KERNEL); - if (!root) { - ret = -ENOMEM; - goto out_unlock; - } - - init_cgroup_root(root, &opts); - - ret = cgroup_setup_root(root, opts.subsys_mask); - if (ret) - cgroup_free_root(root); - -out_unlock: - mutex_unlock(&cgroup_mutex); -out_free: - kfree(opts.release_agent); - kfree(opts.name); - - if (ret) { - put_cgroup_ns(ns); - return ERR_PTR(ret); - } -out_mount: - dentry = kernfs_mount(fs_type, flags, root->kf_root, - is_v2 ? CGROUP2_SUPER_MAGIC : CGROUP_SUPER_MAGIC, - &new_sb); - - /* - * In non-init cgroup namespace, instead of root cgroup's - * dentry, we return the dentry corresponding to the - * cgroupns->root_cgrp. + * In non-init cgroup namespace, instead of root cgroup's dentry, + * we return the dentry corresponding to the cgroupns->root_cgrp. */ if (!IS_ERR(dentry) && ns != &init_cgroup_ns) { struct dentry *nsdentry; @@ -2277,13 +1769,45 @@ out_mount: if (IS_ERR(dentry) || !new_sb) cgroup_put(&root->cgrp); + return dentry; +} + +static struct dentry *cgroup_mount(struct file_system_type *fs_type, + int flags, const char *unused_dev_name, + void *data) +{ + struct cgroup_namespace *ns = current->nsproxy->cgroup_ns; + struct dentry *dentry; + + get_cgroup_ns(ns); + + /* Check if the caller has permission to mount. */ + if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN)) { + put_cgroup_ns(ns); + return ERR_PTR(-EPERM); + } + /* - * If @pinned_sb, we're reusing an existing root and holding an - * extra ref on its sb. Mount is complete. Put the extra ref. + * The first time anyone tries to mount a cgroup, enable the list + * linking each css_set to its tasks and fix up all existing tasks. */ - if (pinned_sb) { - WARN_ON(new_sb); - deactivate_super(pinned_sb); + if (!use_task_css_set_links) + cgroup_enable_task_cg_lists(); + + if (fs_type == &cgroup2_fs_type) { + if (data) { + pr_err("cgroup2: unknown option \"%s\"\n", (char *)data); + put_cgroup_ns(ns); + return ERR_PTR(-EINVAL); + } + cgrp_dfl_visible = true; + cgroup_get(&cgrp_dfl_root.cgrp); + + dentry = cgroup_do_mount(&cgroup2_fs_type, flags, &cgrp_dfl_root, + CGROUP2_SUPER_MAGIC, ns); + } else { + dentry = cgroup1_mount(&cgroup_fs_type, flags, data, + CGROUP_SUPER_MAGIC, ns); } put_cgroup_ns(ns); @@ -2311,7 +1835,7 @@ static void cgroup_kill_sb(struct super_block *sb) kernfs_kill_sb(sb); } -static struct file_system_type cgroup_fs_type = { +struct file_system_type cgroup_fs_type = { .name = "cgroup", .mount = cgroup_mount, .kill_sb = cgroup_kill_sb, @@ -2325,8 +1849,8 @@ static struct file_system_type cgroup2_fs_type = { .fs_flags = FS_USERNS_MOUNT, }; -static int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen, - struct cgroup_namespace *ns) +int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen, + struct cgroup_namespace *ns) { struct cgroup *root = cset_cgroup_from_root(ns->root_cset, cgrp->root); @@ -2389,49 +1913,18 @@ int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen) } EXPORT_SYMBOL_GPL(task_cgroup_path); -/* used to track tasks and other necessary states during migration */ -struct cgroup_taskset { - /* the src and dst cset list running through cset->mg_node */ - struct list_head src_csets; - struct list_head dst_csets; - - /* the subsys currently being processed */ - int ssid; - - /* - * Fields for cgroup_taskset_*() iteration. - * - * Before migration is committed, the target migration tasks are on - * ->mg_tasks of the csets on ->src_csets. After, on ->mg_tasks of - * the csets on ->dst_csets. ->csets point to either ->src_csets - * or ->dst_csets depending on whether migration is committed. - * - * ->cur_csets and ->cur_task point to the current task position - * during iteration. - */ - struct list_head *csets; - struct css_set *cur_cset; - struct task_struct *cur_task; -}; - -#define CGROUP_TASKSET_INIT(tset) (struct cgroup_taskset){ \ - .src_csets = LIST_HEAD_INIT(tset.src_csets), \ - .dst_csets = LIST_HEAD_INIT(tset.dst_csets), \ - .csets = &tset.src_csets, \ -} - /** - * cgroup_taskset_add - try to add a migration target task to a taskset + * cgroup_migrate_add_task - add a migration target task to a migration context * @task: target task - * @tset: target taskset + * @mgctx: target migration context * - * Add @task, which is a migration target, to @tset. This function becomes - * noop if @task doesn't need to be migrated. @task's css_set should have - * been added as a migration source and @task->cg_list will be moved from - * the css_set's tasks list to mg_tasks one. + * Add @task, which is a migration target, to @mgctx->tset. This function + * becomes noop if @task doesn't need to be migrated. @task's css_set + * should have been added as a migration source and @task->cg_list will be + * moved from the css_set's tasks list to mg_tasks one. */ -static void cgroup_taskset_add(struct task_struct *task, - struct cgroup_taskset *tset) +static void cgroup_migrate_add_task(struct task_struct *task, + struct cgroup_mgctx *mgctx) { struct css_set *cset; @@ -2451,10 +1944,11 @@ static void cgroup_taskset_add(struct task_struct *task, list_move_tail(&task->cg_list, &cset->mg_tasks); if (list_empty(&cset->mg_node)) - list_add_tail(&cset->mg_node, &tset->src_csets); + list_add_tail(&cset->mg_node, + &mgctx->tset.src_csets); if (list_empty(&cset->mg_dst_cset->mg_node)) - list_move_tail(&cset->mg_dst_cset->mg_node, - &tset->dst_csets); + list_add_tail(&cset->mg_dst_cset->mg_node, + &mgctx->tset.dst_csets); } /** @@ -2521,17 +2015,16 @@ struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, /** * cgroup_taskset_migrate - migrate a taskset - * @tset: taget taskset - * @root: cgroup root the migration is taking place on + * @mgctx: migration context * - * Migrate tasks in @tset as setup by migration preparation functions. + * Migrate tasks in @mgctx as setup by migration preparation functions. * This function fails iff one of the ->can_attach callbacks fails and - * guarantees that either all or none of the tasks in @tset are migrated. - * @tset is consumed regardless of success. + * guarantees that either all or none of the tasks in @mgctx are migrated. + * @mgctx is consumed regardless of success. */ -static int cgroup_taskset_migrate(struct cgroup_taskset *tset, - struct cgroup_root *root) +static int cgroup_migrate_execute(struct cgroup_mgctx *mgctx) { + struct cgroup_taskset *tset = &mgctx->tset; struct cgroup_subsys *ss; struct task_struct *task, *tmp_task; struct css_set *cset, *tmp_cset; @@ -2542,7 +2035,7 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset, return 0; /* check that we can legitimately attach to the cgroup */ - do_each_subsys_mask(ss, ssid, root->subsys_mask) { + do_each_subsys_mask(ss, ssid, mgctx->ss_mask) { if (ss->can_attach) { tset->ssid = ssid; ret = ss->can_attach(tset); @@ -2578,7 +2071,7 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset, */ tset->csets = &tset->dst_csets; - do_each_subsys_mask(ss, ssid, root->subsys_mask) { + do_each_subsys_mask(ss, ssid, mgctx->ss_mask) { if (ss->attach) { tset->ssid = ssid; ss->attach(tset); @@ -2589,7 +2082,7 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset, goto out_release_tset; out_cancel_attach: - do_each_subsys_mask(ss, ssid, root->subsys_mask) { + do_each_subsys_mask(ss, ssid, mgctx->ss_mask) { if (ssid == failed_ssid) break; if (ss->cancel_attach) { @@ -2616,7 +2109,7 @@ out_release_tset: * zero for migration destination cgroups with tasks so that child cgroups * don't compete against tasks. */ -static bool cgroup_may_migrate_to(struct cgroup *dst_cgrp) +bool cgroup_may_migrate_to(struct cgroup *dst_cgrp) { return !cgroup_on_dfl(dst_cgrp) || !cgroup_parent(dst_cgrp) || !dst_cgrp->subtree_control; @@ -2624,25 +2117,31 @@ static bool cgroup_may_migrate_to(struct cgroup *dst_cgrp) /** * cgroup_migrate_finish - cleanup after attach - * @preloaded_csets: list of preloaded css_sets + * @mgctx: migration context * * Undo cgroup_migrate_add_src() and cgroup_migrate_prepare_dst(). See * those functions for details. */ -static void cgroup_migrate_finish(struct list_head *preloaded_csets) +void cgroup_migrate_finish(struct cgroup_mgctx *mgctx) { + LIST_HEAD(preloaded); struct css_set *cset, *tmp_cset; lockdep_assert_held(&cgroup_mutex); spin_lock_irq(&css_set_lock); - list_for_each_entry_safe(cset, tmp_cset, preloaded_csets, mg_preload_node) { + + list_splice_tail_init(&mgctx->preloaded_src_csets, &preloaded); + list_splice_tail_init(&mgctx->preloaded_dst_csets, &preloaded); + + list_for_each_entry_safe(cset, tmp_cset, &preloaded, mg_preload_node) { cset->mg_src_cgrp = NULL; cset->mg_dst_cgrp = NULL; cset->mg_dst_cset = NULL; list_del_init(&cset->mg_preload_node); put_css_set_locked(cset); } + spin_unlock_irq(&css_set_lock); } @@ -2650,10 +2149,10 @@ static void cgroup_migrate_finish(struct list_head *preloaded_csets) * cgroup_migrate_add_src - add a migration source css_set * @src_cset: the source css_set to add * @dst_cgrp: the destination cgroup - * @preloaded_csets: list of preloaded css_sets + * @mgctx: migration context * * Tasks belonging to @src_cset are about to be migrated to @dst_cgrp. Pin - * @src_cset and add it to @preloaded_csets, which should later be cleaned + * @src_cset and add it to @mgctx->src_csets, which should later be cleaned * up by cgroup_migrate_finish(). * * This function may be called without holding cgroup_threadgroup_rwsem @@ -2662,9 +2161,9 @@ static void cgroup_migrate_finish(struct list_head *preloaded_csets) * into play and the preloaded css_sets are guaranteed to cover all * migrations. */ -static void cgroup_migrate_add_src(struct css_set *src_cset, - struct cgroup *dst_cgrp, - struct list_head *preloaded_csets) +void cgroup_migrate_add_src(struct css_set *src_cset, + struct cgroup *dst_cgrp, + struct cgroup_mgctx *mgctx) { struct cgroup *src_cgrp; @@ -2692,33 +2191,35 @@ static void cgroup_migrate_add_src(struct css_set *src_cset, src_cset->mg_src_cgrp = src_cgrp; src_cset->mg_dst_cgrp = dst_cgrp; get_css_set(src_cset); - list_add(&src_cset->mg_preload_node, preloaded_csets); + list_add_tail(&src_cset->mg_preload_node, &mgctx->preloaded_src_csets); } /** * cgroup_migrate_prepare_dst - prepare destination css_sets for migration - * @preloaded_csets: list of preloaded source css_sets + * @mgctx: migration context * * Tasks are about to be moved and all the source css_sets have been - * preloaded to @preloaded_csets. This function looks up and pins all - * destination css_sets, links each to its source, and append them to - * @preloaded_csets. + * preloaded to @mgctx->preloaded_src_csets. This function looks up and + * pins all destination css_sets, links each to its source, and append them + * to @mgctx->preloaded_dst_csets. * * This function must be called after cgroup_migrate_add_src() has been * called on each migration source css_set. After migration is performed * using cgroup_migrate(), cgroup_migrate_finish() must be called on - * @preloaded_csets. + * @mgctx. */ -static int cgroup_migrate_prepare_dst(struct list_head *preloaded_csets) +int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx) { - LIST_HEAD(csets); struct css_set *src_cset, *tmp_cset; lockdep_assert_held(&cgroup_mutex); /* look up the dst cset for each src cset and link it to src */ - list_for_each_entry_safe(src_cset, tmp_cset, preloaded_csets, mg_preload_node) { + list_for_each_entry_safe(src_cset, tmp_cset, &mgctx->preloaded_src_csets, + mg_preload_node) { struct css_set *dst_cset; + struct cgroup_subsys *ss; + int ssid; dst_cset = find_css_set(src_cset, src_cset->mg_dst_cgrp); if (!dst_cset) @@ -2743,15 +2244,19 @@ static int cgroup_migrate_prepare_dst(struct list_head *preloaded_csets) src_cset->mg_dst_cset = dst_cset; if (list_empty(&dst_cset->mg_preload_node)) - list_add(&dst_cset->mg_preload_node, &csets); + list_add_tail(&dst_cset->mg_preload_node, + &mgctx->preloaded_dst_csets); else put_css_set(dst_cset); + + for_each_subsys(ss, ssid) + if (src_cset->subsys[ssid] != dst_cset->subsys[ssid]) + mgctx->ss_mask |= 1 << ssid; } - list_splice_tail(&csets, preloaded_csets); return 0; err: - cgroup_migrate_finish(&csets); + cgroup_migrate_finish(mgctx); return -ENOMEM; } @@ -2759,7 +2264,7 @@ err: * cgroup_migrate - migrate a process or task to a cgroup * @leader: the leader of the process or the task to migrate * @threadgroup: whether @leader points to the whole process or a single task - * @root: cgroup root migration is taking place on + * @mgctx: migration context * * Migrate a process or task denoted by @leader. If migrating a process, * the caller must be holding cgroup_threadgroup_rwsem. The caller is also @@ -2773,10 +2278,9 @@ err: * decided for all targets by invoking group_migrate_prepare_dst() before * actually starting migrating. */ -static int cgroup_migrate(struct task_struct *leader, bool threadgroup, - struct cgroup_root *root) +int cgroup_migrate(struct task_struct *leader, bool threadgroup, + struct cgroup_mgctx *mgctx) { - struct cgroup_taskset tset = CGROUP_TASKSET_INIT(tset); struct task_struct *task; /* @@ -2788,14 +2292,14 @@ static int cgroup_migrate(struct task_struct *leader, bool threadgroup, rcu_read_lock(); task = leader; do { - cgroup_taskset_add(task, &tset); + cgroup_migrate_add_task(task, mgctx); if (!threadgroup) break; } while_each_thread(leader, task); rcu_read_unlock(); spin_unlock_irq(&css_set_lock); - return cgroup_taskset_migrate(&tset, root); + return cgroup_migrate_execute(mgctx); } /** @@ -2806,10 +2310,10 @@ static int cgroup_migrate(struct task_struct *leader, bool threadgroup, * * Call holding cgroup_mutex and cgroup_threadgroup_rwsem. */ -static int cgroup_attach_task(struct cgroup *dst_cgrp, - struct task_struct *leader, bool threadgroup) +int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader, + bool threadgroup) { - LIST_HEAD(preloaded_csets); + DEFINE_CGROUP_MGCTX(mgctx); struct task_struct *task; int ret; @@ -2821,8 +2325,7 @@ static int cgroup_attach_task(struct cgroup *dst_cgrp, rcu_read_lock(); task = leader; do { - cgroup_migrate_add_src(task_css_set(task), dst_cgrp, - &preloaded_csets); + cgroup_migrate_add_src(task_css_set(task), dst_cgrp, &mgctx); if (!threadgroup) break; } while_each_thread(leader, task); @@ -2830,11 +2333,11 @@ static int cgroup_attach_task(struct cgroup *dst_cgrp, spin_unlock_irq(&css_set_lock); /* prepare dst csets and commit */ - ret = cgroup_migrate_prepare_dst(&preloaded_csets); + ret = cgroup_migrate_prepare_dst(&mgctx); if (!ret) - ret = cgroup_migrate(leader, threadgroup, dst_cgrp->root); + ret = cgroup_migrate(leader, threadgroup, &mgctx); - cgroup_migrate_finish(&preloaded_csets); + cgroup_migrate_finish(&mgctx); if (!ret) trace_cgroup_attach_task(dst_cgrp, leader, threadgroup); @@ -2846,20 +2349,9 @@ static int cgroup_procs_write_permission(struct task_struct *task, struct cgroup *dst_cgrp, struct kernfs_open_file *of) { - const struct cred *cred = current_cred(); - const struct cred *tcred = get_task_cred(task); int ret = 0; - /* - * even if we're attaching all tasks in the thread group, we only - * need to check permissions on one of them. - */ - if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) && - !uid_eq(cred->euid, tcred->uid) && - !uid_eq(cred->euid, tcred->suid)) - ret = -EACCES; - - if (!ret && cgroup_on_dfl(dst_cgrp)) { + if (cgroup_on_dfl(dst_cgrp)) { struct super_block *sb = of->file->f_path.dentry->d_sb; struct cgroup *cgrp; struct inode *inode; @@ -2877,9 +2369,21 @@ static int cgroup_procs_write_permission(struct task_struct *task, ret = inode_permission(inode, MAY_WRITE); iput(inode); } + } else { + const struct cred *cred = current_cred(); + const struct cred *tcred = get_task_cred(task); + + /* + * even if we're attaching all tasks in the thread group, + * we only need to check permissions on one of them. + */ + if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) && + !uid_eq(cred->euid, tcred->uid) && + !uid_eq(cred->euid, tcred->suid)) + ret = -EACCES; + put_cred(tcred); } - put_cred(tcred); return ret; } @@ -2888,8 +2392,8 @@ static int cgroup_procs_write_permission(struct task_struct *task, * function to attach either it or all tasks in its threadgroup. Will lock * cgroup_mutex and threadgroup. */ -static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, - size_t nbytes, loff_t off, bool threadgroup) +ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off, bool threadgroup) { struct task_struct *tsk; struct cgroup_subsys *ss; @@ -2950,86 +2454,12 @@ out_unlock_threadgroup: return ret ?: nbytes; } -/** - * cgroup_attach_task_all - attach task 'tsk' to all cgroups of task 'from' - * @from: attach to all cgroups of a given task - * @tsk: the task to be attached - */ -int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) -{ - struct cgroup_root *root; - int retval = 0; - - mutex_lock(&cgroup_mutex); - percpu_down_write(&cgroup_threadgroup_rwsem); - for_each_root(root) { - struct cgroup *from_cgrp; - - if (root == &cgrp_dfl_root) - continue; - - spin_lock_irq(&css_set_lock); - from_cgrp = task_cgroup_from_root(from, root); - spin_unlock_irq(&css_set_lock); - - retval = cgroup_attach_task(from_cgrp, tsk, false); - if (retval) - break; - } - percpu_up_write(&cgroup_threadgroup_rwsem); - mutex_unlock(&cgroup_mutex); - - return retval; -} -EXPORT_SYMBOL_GPL(cgroup_attach_task_all); - -static ssize_t cgroup_tasks_write(struct kernfs_open_file *of, - char *buf, size_t nbytes, loff_t off) -{ - return __cgroup_procs_write(of, buf, nbytes, off, false); -} - -static ssize_t cgroup_procs_write(struct kernfs_open_file *of, - char *buf, size_t nbytes, loff_t off) +ssize_t cgroup_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes, + loff_t off) { return __cgroup_procs_write(of, buf, nbytes, off, true); } -static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of, - char *buf, size_t nbytes, loff_t off) -{ - struct cgroup *cgrp; - - BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX); - - cgrp = cgroup_kn_lock_live(of->kn, false); - if (!cgrp) - return -ENODEV; - spin_lock(&release_agent_path_lock); - strlcpy(cgrp->root->release_agent_path, strstrip(buf), - sizeof(cgrp->root->release_agent_path)); - spin_unlock(&release_agent_path_lock); - cgroup_kn_unlock(of->kn); - return nbytes; -} - -static int cgroup_release_agent_show(struct seq_file *seq, void *v) -{ - struct cgroup *cgrp = seq_css(seq)->cgroup; - - spin_lock(&release_agent_path_lock); - seq_puts(seq, cgrp->root->release_agent_path); - spin_unlock(&release_agent_path_lock); - seq_putc(seq, '\n'); - return 0; -} - -static int cgroup_sane_behavior_show(struct seq_file *seq, void *v) -{ - seq_puts(seq, "0\n"); - return 0; -} - static void cgroup_print_ss_mask(struct seq_file *seq, u16 ss_mask) { struct cgroup_subsys *ss; @@ -3075,8 +2505,7 @@ static int cgroup_subtree_control_show(struct seq_file *seq, void *v) */ static int cgroup_update_dfl_csses(struct cgroup *cgrp) { - LIST_HEAD(preloaded_csets); - struct cgroup_taskset tset = CGROUP_TASKSET_INIT(tset); + DEFINE_CGROUP_MGCTX(mgctx); struct cgroup_subsys_state *d_css; struct cgroup *dsct; struct css_set *src_cset; @@ -3092,33 +2521,28 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) struct cgrp_cset_link *link; list_for_each_entry(link, &dsct->cset_links, cset_link) - cgroup_migrate_add_src(link->cset, dsct, - &preloaded_csets); + cgroup_migrate_add_src(link->cset, dsct, &mgctx); } spin_unlock_irq(&css_set_lock); /* NULL dst indicates self on default hierarchy */ - ret = cgroup_migrate_prepare_dst(&preloaded_csets); + ret = cgroup_migrate_prepare_dst(&mgctx); if (ret) goto out_finish; spin_lock_irq(&css_set_lock); - list_for_each_entry(src_cset, &preloaded_csets, mg_preload_node) { + list_for_each_entry(src_cset, &mgctx.preloaded_src_csets, mg_preload_node) { struct task_struct *task, *ntask; - /* src_csets precede dst_csets, break on the first dst_cset */ - if (!src_cset->mg_src_cgrp) - break; - /* all tasks in src_csets need to be migrated */ list_for_each_entry_safe(task, ntask, &src_cset->tasks, cg_list) - cgroup_taskset_add(task, &tset); + cgroup_migrate_add_task(task, &mgctx); } spin_unlock_irq(&css_set_lock); - ret = cgroup_taskset_migrate(&tset, cgrp->root); + ret = cgroup_migrate_execute(&mgctx); out_finish: - cgroup_migrate_finish(&preloaded_csets); + cgroup_migrate_finish(&mgctx); percpu_up_write(&cgroup_threadgroup_rwsem); return ret; } @@ -3131,7 +2555,7 @@ out_finish: * controller while the previous css is still around. This function grabs * cgroup_mutex and drains the previous css instances of @cgrp's subtree. */ -static void cgroup_lock_and_drain_offline(struct cgroup *cgrp) +void cgroup_lock_and_drain_offline(struct cgroup *cgrp) __acquires(&cgroup_mutex) { struct cgroup *dsct; @@ -3503,6 +2927,23 @@ static int cgroup_events_show(struct seq_file *seq, void *v) return 0; } +static int cgroup_file_open(struct kernfs_open_file *of) +{ + struct cftype *cft = of->kn->priv; + + if (cft->open) + return cft->open(of); + return 0; +} + +static void cgroup_file_release(struct kernfs_open_file *of) +{ + struct cftype *cft = of->kn->priv; + + if (cft->release) + cft->release(of); +} + static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { @@ -3553,7 +2994,8 @@ static void *cgroup_seqfile_next(struct seq_file *seq, void *v, loff_t *ppos) static void cgroup_seqfile_stop(struct seq_file *seq, void *v) { - seq_cft(seq)->seq_stop(seq, v); + if (seq_cft(seq)->seq_stop) + seq_cft(seq)->seq_stop(seq, v); } static int cgroup_seqfile_show(struct seq_file *m, void *arg) @@ -3575,12 +3017,16 @@ static int cgroup_seqfile_show(struct seq_file *m, void *arg) static struct kernfs_ops cgroup_kf_single_ops = { .atomic_write_len = PAGE_SIZE, + .open = cgroup_file_open, + .release = cgroup_file_release, .write = cgroup_file_write, .seq_show = cgroup_seqfile_show, }; static struct kernfs_ops cgroup_kf_ops = { .atomic_write_len = PAGE_SIZE, + .open = cgroup_file_open, + .release = cgroup_file_release, .write = cgroup_file_write, .seq_start = cgroup_seqfile_start, .seq_next = cgroup_seqfile_next, @@ -3588,48 +3034,6 @@ static struct kernfs_ops cgroup_kf_ops = { .seq_show = cgroup_seqfile_show, }; -/* - * cgroup_rename - Only allow simple rename of directories in place. - */ -static int cgroup_rename(struct kernfs_node *kn, struct kernfs_node *new_parent, - const char *new_name_str) -{ - struct cgroup *cgrp = kn->priv; - int ret; - - if (kernfs_type(kn) != KERNFS_DIR) - return -ENOTDIR; - if (kn->parent != new_parent) - return -EIO; - - /* - * This isn't a proper migration and its usefulness is very - * limited. Disallow on the default hierarchy. - */ - if (cgroup_on_dfl(cgrp)) - return -EPERM; - - /* - * We're gonna grab cgroup_mutex which nests outside kernfs - * active_ref. kernfs_rename() doesn't require active_ref - * protection. Break them before grabbing cgroup_mutex. - */ - kernfs_break_active_protection(new_parent); - kernfs_break_active_protection(kn); - - mutex_lock(&cgroup_mutex); - - ret = kernfs_rename(kn, new_parent, new_name_str); - if (!ret) - trace_cgroup_rename(cgrp); - - mutex_unlock(&cgroup_mutex); - - kernfs_unbreak_active_protection(kn); - kernfs_unbreak_active_protection(new_parent); - return ret; -} - /* set uid and gid of cgroup dirs and files to that of the creator */ static int cgroup_kn_set_ugid(struct kernfs_node *kn) { @@ -3926,26 +3330,6 @@ void cgroup_file_notify(struct cgroup_file *cfile) } /** - * cgroup_task_count - count the number of tasks in a cgroup. - * @cgrp: the cgroup in question - * - * Return the number of tasks in the cgroup. The returned number can be - * higher than the actual number of tasks due to css_set references from - * namespace roots and temporary usages. - */ -static int cgroup_task_count(const struct cgroup *cgrp) -{ - int count = 0; - struct cgrp_cset_link *link; - - spin_lock_irq(&css_set_lock); - list_for_each_entry(link, &cgrp->cset_links, cset_link) - count += atomic_read(&link->cset->refcount); - spin_unlock_irq(&css_set_lock); - return count; -} - -/** * css_next_child - find the next child of a given css * @pos: the current position (%NULL to initiate traversal) * @parent: css whose children to walk @@ -4343,560 +3727,69 @@ void css_task_iter_end(struct css_task_iter *it) put_task_struct(it->cur_task); } -/** - * cgroup_trasnsfer_tasks - move tasks from one cgroup to another - * @to: cgroup to which the tasks will be moved - * @from: cgroup in which the tasks currently reside - * - * Locking rules between cgroup_post_fork() and the migration path - * guarantee that, if a task is forking while being migrated, the new child - * is guaranteed to be either visible in the source cgroup after the - * parent's migration is complete or put into the target cgroup. No task - * can slip out of migration through forking. - */ -int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from) -{ - LIST_HEAD(preloaded_csets); - struct cgrp_cset_link *link; - struct css_task_iter it; - struct task_struct *task; - int ret; - - if (!cgroup_may_migrate_to(to)) - return -EBUSY; - - mutex_lock(&cgroup_mutex); - - percpu_down_write(&cgroup_threadgroup_rwsem); - - /* all tasks in @from are being moved, all csets are source */ - spin_lock_irq(&css_set_lock); - list_for_each_entry(link, &from->cset_links, cset_link) - cgroup_migrate_add_src(link->cset, to, &preloaded_csets); - spin_unlock_irq(&css_set_lock); - - ret = cgroup_migrate_prepare_dst(&preloaded_csets); - if (ret) - goto out_err; - - /* - * Migrate tasks one-by-one until @from is empty. This fails iff - * ->can_attach() fails. - */ - do { - css_task_iter_start(&from->self, &it); - task = css_task_iter_next(&it); - if (task) - get_task_struct(task); - css_task_iter_end(&it); - - if (task) { - ret = cgroup_migrate(task, false, to->root); - if (!ret) - trace_cgroup_transfer_tasks(to, task, false); - put_task_struct(task); - } - } while (task && !ret); -out_err: - cgroup_migrate_finish(&preloaded_csets); - percpu_up_write(&cgroup_threadgroup_rwsem); - mutex_unlock(&cgroup_mutex); - return ret; -} - -/* - * Stuff for reading the 'tasks'/'procs' files. - * - * Reading this file can return large amounts of data if a cgroup has - * *lots* of attached tasks. So it may need several calls to read(), - * but we cannot guarantee that the information we produce is correct - * unless we produce it entirely atomically. - * - */ - -/* which pidlist file are we talking about? */ -enum cgroup_filetype { - CGROUP_FILE_PROCS, - CGROUP_FILE_TASKS, -}; - -/* - * A pidlist is a list of pids that virtually represents the contents of one - * of the cgroup files ("procs" or "tasks"). We keep a list of such pidlists, - * a pair (one each for procs, tasks) for each pid namespace that's relevant - * to the cgroup. - */ -struct cgroup_pidlist { - /* - * used to find which pidlist is wanted. doesn't change as long as - * this particular list stays in the list. - */ - struct { enum cgroup_filetype type; struct pid_namespace *ns; } key; - /* array of xids */ - pid_t *list; - /* how many elements the above list has */ - int length; - /* each of these stored in a list by its cgroup */ - struct list_head links; - /* pointer to the cgroup we belong to, for list removal purposes */ - struct cgroup *owner; - /* for delayed destruction */ - struct delayed_work destroy_dwork; -}; - -/* - * The following two functions "fix" the issue where there are more pids - * than kmalloc will give memory for; in such cases, we use vmalloc/vfree. - * TODO: replace with a kernel-wide solution to this problem - */ -#define PIDLIST_TOO_LARGE(c) ((c) * sizeof(pid_t) > (PAGE_SIZE * 2)) -static void *pidlist_allocate(int count) -{ - if (PIDLIST_TOO_LARGE(count)) - return vmalloc(count * sizeof(pid_t)); - else - return kmalloc(count * sizeof(pid_t), GFP_KERNEL); -} - -static void pidlist_free(void *p) -{ - kvfree(p); -} - -/* - * Used to destroy all pidlists lingering waiting for destroy timer. None - * should be left afterwards. - */ -static void cgroup_pidlist_destroy_all(struct cgroup *cgrp) -{ - struct cgroup_pidlist *l, *tmp_l; - - mutex_lock(&cgrp->pidlist_mutex); - list_for_each_entry_safe(l, tmp_l, &cgrp->pidlists, links) - mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, 0); - mutex_unlock(&cgrp->pidlist_mutex); - - flush_workqueue(cgroup_pidlist_destroy_wq); - BUG_ON(!list_empty(&cgrp->pidlists)); -} - -static void cgroup_pidlist_destroy_work_fn(struct work_struct *work) -{ - struct delayed_work *dwork = to_delayed_work(work); - struct cgroup_pidlist *l = container_of(dwork, struct cgroup_pidlist, - destroy_dwork); - struct cgroup_pidlist *tofree = NULL; - - mutex_lock(&l->owner->pidlist_mutex); - - /* - * Destroy iff we didn't get queued again. The state won't change - * as destroy_dwork can only be queued while locked. - */ - if (!delayed_work_pending(dwork)) { - list_del(&l->links); - pidlist_free(l->list); - put_pid_ns(l->key.ns); - tofree = l; - } - - mutex_unlock(&l->owner->pidlist_mutex); - kfree(tofree); -} - -/* - * pidlist_uniq - given a kmalloc()ed list, strip out all duplicate entries - * Returns the number of unique elements. - */ -static int pidlist_uniq(pid_t *list, int length) -{ - int src, dest = 1; - - /* - * we presume the 0th element is unique, so i starts at 1. trivial - * edge cases first; no work needs to be done for either - */ - if (length == 0 || length == 1) - return length; - /* src and dest walk down the list; dest counts unique elements */ - for (src = 1; src < length; src++) { - /* find next unique element */ - while (list[src] == list[src-1]) { - src++; - if (src == length) - goto after; - } - /* dest always points to where the next unique element goes */ - list[dest] = list[src]; - dest++; - } -after: - return dest; -} - -/* - * The two pid files - task and cgroup.procs - guaranteed that the result - * is sorted, which forced this whole pidlist fiasco. As pid order is - * different per namespace, each namespace needs differently sorted list, - * making it impossible to use, for example, single rbtree of member tasks - * sorted by task pointer. As pidlists can be fairly large, allocating one - * per open file is dangerous, so cgroup had to implement shared pool of - * pidlists keyed by cgroup and namespace. - * - * All this extra complexity was caused by the original implementation - * committing to an entirely unnecessary property. In the long term, we - * want to do away with it. Explicitly scramble sort order if on the - * default hierarchy so that no such expectation exists in the new - * interface. - * - * Scrambling is done by swapping every two consecutive bits, which is - * non-identity one-to-one mapping which disturbs sort order sufficiently. - */ -static pid_t pid_fry(pid_t pid) +static void cgroup_procs_release(struct kernfs_open_file *of) { - unsigned a = pid & 0x55555555; - unsigned b = pid & 0xAAAAAAAA; - - return (a << 1) | (b >> 1); -} - -static pid_t cgroup_pid_fry(struct cgroup *cgrp, pid_t pid) -{ - if (cgroup_on_dfl(cgrp)) - return pid_fry(pid); - else - return pid; -} - -static int cmppid(const void *a, const void *b) -{ - return *(pid_t *)a - *(pid_t *)b; -} - -static int fried_cmppid(const void *a, const void *b) -{ - return pid_fry(*(pid_t *)a) - pid_fry(*(pid_t *)b); -} - -static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp, - enum cgroup_filetype type) -{ - struct cgroup_pidlist *l; - /* don't need task_nsproxy() if we're looking at ourself */ - struct pid_namespace *ns = task_active_pid_ns(current); - - lockdep_assert_held(&cgrp->pidlist_mutex); - - list_for_each_entry(l, &cgrp->pidlists, links) - if (l->key.type == type && l->key.ns == ns) - return l; - return NULL; -} - -/* - * find the appropriate pidlist for our purpose (given procs vs tasks) - * returns with the lock on that pidlist already held, and takes care - * of the use count, or returns NULL with no locks held if we're out of - * memory. - */ -static struct cgroup_pidlist *cgroup_pidlist_find_create(struct cgroup *cgrp, - enum cgroup_filetype type) -{ - struct cgroup_pidlist *l; - - lockdep_assert_held(&cgrp->pidlist_mutex); - - l = cgroup_pidlist_find(cgrp, type); - if (l) - return l; - - /* entry not found; create a new one */ - l = kzalloc(sizeof(struct cgroup_pidlist), GFP_KERNEL); - if (!l) - return l; - - INIT_DELAYED_WORK(&l->destroy_dwork, cgroup_pidlist_destroy_work_fn); - l->key.type = type; - /* don't need task_nsproxy() if we're looking at ourself */ - l->key.ns = get_pid_ns(task_active_pid_ns(current)); - l->owner = cgrp; - list_add(&l->links, &cgrp->pidlists); - return l; -} - -/* - * Load a cgroup's pidarray with either procs' tgids or tasks' pids - */ -static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, - struct cgroup_pidlist **lp) -{ - pid_t *array; - int length; - int pid, n = 0; /* used for populating the array */ - struct css_task_iter it; - struct task_struct *tsk; - struct cgroup_pidlist *l; - - lockdep_assert_held(&cgrp->pidlist_mutex); - - /* - * If cgroup gets more users after we read count, we won't have - * enough space - tough. This race is indistinguishable to the - * caller from the case that the additional cgroup users didn't - * show up until sometime later on. - */ - length = cgroup_task_count(cgrp); - array = pidlist_allocate(length); - if (!array) - return -ENOMEM; - /* now, populate the array */ - css_task_iter_start(&cgrp->self, &it); - while ((tsk = css_task_iter_next(&it))) { - if (unlikely(n == length)) - break; - /* get tgid or pid for procs or tasks file respectively */ - if (type == CGROUP_FILE_PROCS) - pid = task_tgid_vnr(tsk); - else - pid = task_pid_vnr(tsk); - if (pid > 0) /* make sure to only use valid results */ - array[n++] = pid; - } - css_task_iter_end(&it); - length = n; - /* now sort & (if procs) strip out duplicates */ - if (cgroup_on_dfl(cgrp)) - sort(array, length, sizeof(pid_t), fried_cmppid, NULL); - else - sort(array, length, sizeof(pid_t), cmppid, NULL); - if (type == CGROUP_FILE_PROCS) - length = pidlist_uniq(array, length); - - l = cgroup_pidlist_find_create(cgrp, type); - if (!l) { - pidlist_free(array); - return -ENOMEM; + if (of->priv) { + css_task_iter_end(of->priv); + kfree(of->priv); } - - /* store array, freeing old if necessary */ - pidlist_free(l->list); - l->list = array; - l->length = length; - *lp = l; - return 0; } -/** - * cgroupstats_build - build and fill cgroupstats - * @stats: cgroupstats to fill information into - * @dentry: A dentry entry belonging to the cgroup for which stats have - * been requested. - * - * Build and fill cgroupstats so that taskstats can export it to user - * space. - */ -int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) +static void *cgroup_procs_next(struct seq_file *s, void *v, loff_t *pos) { - struct kernfs_node *kn = kernfs_node_from_dentry(dentry); - struct cgroup *cgrp; - struct css_task_iter it; - struct task_struct *tsk; - - /* it should be kernfs_node belonging to cgroupfs and is a directory */ - if (dentry->d_sb->s_type != &cgroup_fs_type || !kn || - kernfs_type(kn) != KERNFS_DIR) - return -EINVAL; - - mutex_lock(&cgroup_mutex); - - /* - * We aren't being called from kernfs and there's no guarantee on - * @kn->priv's validity. For this and css_tryget_online_from_dir(), - * @kn->priv is RCU safe. Let's do the RCU dancing. - */ - rcu_read_lock(); - cgrp = rcu_dereference(kn->priv); - if (!cgrp || cgroup_is_dead(cgrp)) { - rcu_read_unlock(); - mutex_unlock(&cgroup_mutex); - return -ENOENT; - } - rcu_read_unlock(); + struct kernfs_open_file *of = s->private; + struct css_task_iter *it = of->priv; + struct task_struct *task; - css_task_iter_start(&cgrp->self, &it); - while ((tsk = css_task_iter_next(&it))) { - switch (tsk->state) { - case TASK_RUNNING: - stats->nr_running++; - break; - case TASK_INTERRUPTIBLE: - stats->nr_sleeping++; - break; - case TASK_UNINTERRUPTIBLE: - stats->nr_uninterruptible++; - break; - case TASK_STOPPED: - stats->nr_stopped++; - break; - default: - if (delayacct_is_task_waiting_on_io(tsk)) - stats->nr_io_wait++; - break; - } - } - css_task_iter_end(&it); + do { + task = css_task_iter_next(it); + } while (task && !thread_group_leader(task)); - mutex_unlock(&cgroup_mutex); - return 0; + return task; } - -/* - * seq_file methods for the tasks/procs files. The seq_file position is the - * next pid to display; the seq_file iterator is a pointer to the pid - * in the cgroup->l->list array. - */ - -static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos) +static void *cgroup_procs_start(struct seq_file *s, loff_t *pos) { - /* - * Initially we receive a position value that corresponds to - * one more than the last pid shown (or 0 on the first call or - * after a seek to the start). Use a binary-search to find the - * next pid to display, if any - */ struct kernfs_open_file *of = s->private; struct cgroup *cgrp = seq_css(s)->cgroup; - struct cgroup_pidlist *l; - enum cgroup_filetype type = seq_cft(s)->private; - int index = 0, pid = *pos; - int *iter, ret; - - mutex_lock(&cgrp->pidlist_mutex); + struct css_task_iter *it = of->priv; /* - * !NULL @of->priv indicates that this isn't the first start() - * after open. If the matching pidlist is around, we can use that. - * Look for it. Note that @of->priv can't be used directly. It - * could already have been destroyed. + * When a seq_file is seeked, it's always traversed sequentially + * from position 0, so we can simply keep iterating on !0 *pos. */ - if (of->priv) - of->priv = cgroup_pidlist_find(cgrp, type); - - /* - * Either this is the first start() after open or the matching - * pidlist has been destroyed inbetween. Create a new one. - */ - if (!of->priv) { - ret = pidlist_array_load(cgrp, type, - (struct cgroup_pidlist **)&of->priv); - if (ret) - return ERR_PTR(ret); - } - l = of->priv; - - if (pid) { - int end = l->length; - - while (index < end) { - int mid = (index + end) / 2; - if (cgroup_pid_fry(cgrp, l->list[mid]) == pid) { - index = mid; - break; - } else if (cgroup_pid_fry(cgrp, l->list[mid]) <= pid) - index = mid + 1; - else - end = mid; - } - } - /* If we're off the end of the array, we're done */ - if (index >= l->length) - return NULL; - /* Update the abstract position to be the actual pid that we found */ - iter = l->list + index; - *pos = cgroup_pid_fry(cgrp, *iter); - return iter; -} - -static void cgroup_pidlist_stop(struct seq_file *s, void *v) -{ - struct kernfs_open_file *of = s->private; - struct cgroup_pidlist *l = of->priv; - - if (l) - mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, - CGROUP_PIDLIST_DESTROY_DELAY); - mutex_unlock(&seq_css(s)->cgroup->pidlist_mutex); -} + if (!it) { + if (WARN_ON_ONCE((*pos)++)) + return ERR_PTR(-EINVAL); -static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos) -{ - struct kernfs_open_file *of = s->private; - struct cgroup_pidlist *l = of->priv; - pid_t *p = v; - pid_t *end = l->list + l->length; - /* - * Advance to the next pid in the array. If this goes off the - * end, we're done - */ - p++; - if (p >= end) { - return NULL; - } else { - *pos = cgroup_pid_fry(seq_css(s)->cgroup, *p); - return p; + it = kzalloc(sizeof(*it), GFP_KERNEL); + if (!it) + return ERR_PTR(-ENOMEM); + of->priv = it; + css_task_iter_start(&cgrp->self, it); + } else if (!(*pos)++) { + css_task_iter_end(it); + css_task_iter_start(&cgrp->self, it); } -} - -static int cgroup_pidlist_show(struct seq_file *s, void *v) -{ - seq_printf(s, "%d\n", *(int *)v); - return 0; + return cgroup_procs_next(s, NULL, NULL); } -static u64 cgroup_read_notify_on_release(struct cgroup_subsys_state *css, - struct cftype *cft) +static int cgroup_procs_show(struct seq_file *s, void *v) { - return notify_on_release(css->cgroup); -} - -static int cgroup_write_notify_on_release(struct cgroup_subsys_state *css, - struct cftype *cft, u64 val) -{ - if (val) - set_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags); - else - clear_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags); - return 0; -} - -static u64 cgroup_clone_children_read(struct cgroup_subsys_state *css, - struct cftype *cft) -{ - return test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); -} - -static int cgroup_clone_children_write(struct cgroup_subsys_state *css, - struct cftype *cft, u64 val) -{ - if (val) - set_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); - else - clear_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); + seq_printf(s, "%d\n", task_tgid_vnr(v)); return 0; } /* cgroup core interface files for the default hierarchy */ -static struct cftype cgroup_dfl_base_files[] = { +static struct cftype cgroup_base_files[] = { { .name = "cgroup.procs", .file_offset = offsetof(struct cgroup, procs_file), - .seq_start = cgroup_pidlist_start, - .seq_next = cgroup_pidlist_next, - .seq_stop = cgroup_pidlist_stop, - .seq_show = cgroup_pidlist_show, - .private = CGROUP_FILE_PROCS, + .release = cgroup_procs_release, + .seq_start = cgroup_procs_start, + .seq_next = cgroup_procs_next, + .seq_show = cgroup_procs_show, .write = cgroup_procs_write, }, { @@ -4917,51 +3810,6 @@ static struct cftype cgroup_dfl_base_files[] = { { } /* terminate */ }; -/* cgroup core interface files for the legacy hierarchies */ -static struct cftype cgroup_legacy_base_files[] = { - { - .name = "cgroup.procs", - .seq_start = cgroup_pidlist_start, - .seq_next = cgroup_pidlist_next, - .seq_stop = cgroup_pidlist_stop, - .seq_show = cgroup_pidlist_show, - .private = CGROUP_FILE_PROCS, - .write = cgroup_procs_write, - }, - { - .name = "cgroup.clone_children", - .read_u64 = cgroup_clone_children_read, - .write_u64 = cgroup_clone_children_write, - }, - { - .name = "cgroup.sane_behavior", - .flags = CFTYPE_ONLY_ON_ROOT, - .seq_show = cgroup_sane_behavior_show, - }, - { - .name = "tasks", - .seq_start = cgroup_pidlist_start, - .seq_next = cgroup_pidlist_next, - .seq_stop = cgroup_pidlist_stop, - .seq_show = cgroup_pidlist_show, - .private = CGROUP_FILE_TASKS, - .write = cgroup_tasks_write, - }, - { - .name = "notify_on_release", - .read_u64 = cgroup_read_notify_on_release, - .write_u64 = cgroup_write_notify_on_release, - }, - { - .name = "release_agent", - .flags = CFTYPE_ONLY_ON_ROOT, - .seq_show = cgroup_release_agent_show, - .write = cgroup_release_agent_write, - .max_write_len = PATH_MAX - 1, - }, - { } /* terminate */ -}; - /* * css destruction is four-stage process. * @@ -5007,7 +3855,7 @@ static void css_free_work_fn(struct work_struct *work) } else { /* cgroup free path */ atomic_dec(&cgrp->root->nr_cgrps); - cgroup_pidlist_destroy_all(cgrp); + cgroup1_pidlist_destroy_all(cgrp); cancel_work_sync(&cgrp->release_agent_work); if (cgroup_parent(cgrp)) { @@ -5302,8 +4150,7 @@ out_free_cgrp: return ERR_PTR(ret); } -static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, - umode_t mode) +int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode) { struct cgroup *parent, *cgrp; struct kernfs_node *kn; @@ -5507,7 +4354,7 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) */ kernfs_remove(cgrp->kn); - check_for_release(cgroup_parent(cgrp)); + cgroup1_check_for_release(cgroup_parent(cgrp)); /* put the base reference */ percpu_ref_kill(&cgrp->self.refcnt); @@ -5515,7 +4362,7 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) return 0; }; -static int cgroup_rmdir(struct kernfs_node *kn) +int cgroup_rmdir(struct kernfs_node *kn) { struct cgroup *cgrp; int ret = 0; @@ -5535,10 +4382,8 @@ static int cgroup_rmdir(struct kernfs_node *kn) static struct kernfs_syscall_ops cgroup_kf_syscall_ops = { .remount_fs = cgroup_remount, - .show_options = cgroup_show_options, .mkdir = cgroup_mkdir, .rmdir = cgroup_rmdir, - .rename = cgroup_rename, .show_path = cgroup_show_path, }; @@ -5646,8 +4491,8 @@ int __init cgroup_init(void) BUILD_BUG_ON(CGROUP_SUBSYS_COUNT > 16); BUG_ON(percpu_init_rwsem(&cgroup_threadgroup_rwsem)); - BUG_ON(cgroup_init_cftypes(NULL, cgroup_dfl_base_files)); - BUG_ON(cgroup_init_cftypes(NULL, cgroup_legacy_base_files)); + BUG_ON(cgroup_init_cftypes(NULL, cgroup_base_files)); + BUG_ON(cgroup_init_cftypes(NULL, cgroup1_base_files)); /* * The latency of the synchronize_sched() is too high for cgroups, @@ -5697,7 +4542,7 @@ int __init cgroup_init(void) continue; } - if (cgroup_ssid_no_v1(ssid)) + if (cgroup1_ssid_disabled(ssid)) printk(KERN_INFO "Disabling %s control group subsystem in v1 mounts\n", ss->name); @@ -5744,15 +4589,6 @@ static int __init cgroup_wq_init(void) */ cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1); BUG_ON(!cgroup_destroy_wq); - - /* - * Used to destroy pidlists and separate to serve as flush domain. - * Cap @max_active to 1 too. - */ - cgroup_pidlist_destroy_wq = alloc_workqueue("cgroup_pidlist_destroy", - 0, 1); - BUG_ON(!cgroup_pidlist_destroy_wq); - return 0; } core_initcall(cgroup_wq_init); @@ -5835,42 +4671,6 @@ out: return retval; } -/* Display information about each subsystem and each hierarchy */ -static int proc_cgroupstats_show(struct seq_file *m, void *v) -{ - struct cgroup_subsys *ss; - int i; - - seq_puts(m, "#subsys_name\thierarchy\tnum_cgroups\tenabled\n"); - /* - * ideally we don't want subsystems moving around while we do this. - * cgroup_mutex is also necessary to guarantee an atomic snapshot of - * subsys/hierarchy state. - */ - mutex_lock(&cgroup_mutex); - - for_each_subsys(ss, i) - seq_printf(m, "%s\t%d\t%d\t%d\n", - ss->legacy_name, ss->root->hierarchy_id, - atomic_read(&ss->root->nr_cgrps), - cgroup_ssid_enabled(i)); - - mutex_unlock(&cgroup_mutex); - return 0; -} - -static int cgroupstats_open(struct inode *inode, struct file *file) -{ - return single_open(file, proc_cgroupstats_show, NULL); -} - -static const struct file_operations proc_cgroupstats_operations = { - .open = cgroupstats_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - /** * cgroup_fork - initialize cgroup related fields during copy_process() * @child: pointer to task_struct of forking parent process. @@ -6050,76 +4850,6 @@ void cgroup_free(struct task_struct *task) put_css_set(cset); } -static void check_for_release(struct cgroup *cgrp) -{ - if (notify_on_release(cgrp) && !cgroup_is_populated(cgrp) && - !css_has_online_children(&cgrp->self) && !cgroup_is_dead(cgrp)) - schedule_work(&cgrp->release_agent_work); -} - -/* - * Notify userspace when a cgroup is released, by running the - * configured release agent with the name of the cgroup (path - * relative to the root of cgroup file system) as the argument. - * - * Most likely, this user command will try to rmdir this cgroup. - * - * This races with the possibility that some other task will be - * attached to this cgroup before it is removed, or that some other - * user task will 'mkdir' a child cgroup of this cgroup. That's ok. - * The presumed 'rmdir' will fail quietly if this cgroup is no longer - * unused, and this cgroup will be reprieved from its death sentence, - * to continue to serve a useful existence. Next time it's released, - * we will get notified again, if it still has 'notify_on_release' set. - * - * The final arg to call_usermodehelper() is UMH_WAIT_EXEC, which - * means only wait until the task is successfully execve()'d. The - * separate release agent task is forked by call_usermodehelper(), - * then control in this thread returns here, without waiting for the - * release agent task. We don't bother to wait because the caller of - * this routine has no use for the exit status of the release agent - * task, so no sense holding our caller up for that. - */ -static void cgroup_release_agent(struct work_struct *work) -{ - struct cgroup *cgrp = - container_of(work, struct cgroup, release_agent_work); - char *pathbuf = NULL, *agentbuf = NULL; - char *argv[3], *envp[3]; - int ret; - - mutex_lock(&cgroup_mutex); - - pathbuf = kmalloc(PATH_MAX, GFP_KERNEL); - agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL); - if (!pathbuf || !agentbuf) - goto out; - - spin_lock_irq(&css_set_lock); - ret = cgroup_path_ns_locked(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns); - spin_unlock_irq(&css_set_lock); - if (ret < 0 || ret >= PATH_MAX) - goto out; - - argv[0] = agentbuf; - argv[1] = pathbuf; - argv[2] = NULL; - - /* minimal command environment */ - envp[0] = "HOME=/"; - envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin"; - envp[2] = NULL; - - mutex_unlock(&cgroup_mutex); - call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC); - goto out_free; -out: - mutex_unlock(&cgroup_mutex); -out_free: - kfree(agentbuf); - kfree(pathbuf); -} - static int __init cgroup_disable(char *str) { struct cgroup_subsys *ss; @@ -6141,33 +4871,6 @@ static int __init cgroup_disable(char *str) } __setup("cgroup_disable=", cgroup_disable); -static int __init cgroup_no_v1(char *str) -{ - struct cgroup_subsys *ss; - char *token; - int i; - - while ((token = strsep(&str, ",")) != NULL) { - if (!*token) - continue; - - if (!strcmp(token, "all")) { - cgroup_no_v1_mask = U16_MAX; - break; - } - - for_each_subsys(ss, i) { - if (strcmp(token, ss->name) && - strcmp(token, ss->legacy_name)) - continue; - - cgroup_no_v1_mask |= 1 << i; - } - } - return 1; -} -__setup("cgroup_no_v1=", cgroup_no_v1); - /** * css_tryget_online_from_dir - get corresponding css from a cgroup dentry * @dentry: directory dentry of interest @@ -6197,7 +4900,7 @@ struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, * have been or be removed at any point. @kn->priv is RCU * protected for this access. See css_release_work_fn() for details. */ - cgrp = rcu_dereference(kn->priv); + cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); if (cgrp) css = cgroup_css(cgrp, ss); @@ -6349,154 +5052,6 @@ void cgroup_sk_free(struct sock_cgroup_data *skcd) #endif /* CONFIG_SOCK_CGROUP_DATA */ -/* cgroup namespaces */ - -static struct ucounts *inc_cgroup_namespaces(struct user_namespace *ns) -{ - return inc_ucount(ns, current_euid(), UCOUNT_CGROUP_NAMESPACES); -} - -static void dec_cgroup_namespaces(struct ucounts *ucounts) -{ - dec_ucount(ucounts, UCOUNT_CGROUP_NAMESPACES); -} - -static struct cgroup_namespace *alloc_cgroup_ns(void) -{ - struct cgroup_namespace *new_ns; - int ret; - - new_ns = kzalloc(sizeof(struct cgroup_namespace), GFP_KERNEL); - if (!new_ns) - return ERR_PTR(-ENOMEM); - ret = ns_alloc_inum(&new_ns->ns); - if (ret) { - kfree(new_ns); - return ERR_PTR(ret); - } - atomic_set(&new_ns->count, 1); - new_ns->ns.ops = &cgroupns_operations; - return new_ns; -} - -void free_cgroup_ns(struct cgroup_namespace *ns) -{ - put_css_set(ns->root_cset); - dec_cgroup_namespaces(ns->ucounts); - put_user_ns(ns->user_ns); - ns_free_inum(&ns->ns); - kfree(ns); -} -EXPORT_SYMBOL(free_cgroup_ns); - -struct cgroup_namespace *copy_cgroup_ns(unsigned long flags, - struct user_namespace *user_ns, - struct cgroup_namespace *old_ns) -{ - struct cgroup_namespace *new_ns; - struct ucounts *ucounts; - struct css_set *cset; - - BUG_ON(!old_ns); - - if (!(flags & CLONE_NEWCGROUP)) { - get_cgroup_ns(old_ns); - return old_ns; - } - - /* Allow only sysadmin to create cgroup namespace. */ - if (!ns_capable(user_ns, CAP_SYS_ADMIN)) - return ERR_PTR(-EPERM); - - ucounts = inc_cgroup_namespaces(user_ns); - if (!ucounts) - return ERR_PTR(-ENOSPC); - - /* It is not safe to take cgroup_mutex here */ - spin_lock_irq(&css_set_lock); - cset = task_css_set(current); - get_css_set(cset); - spin_unlock_irq(&css_set_lock); - - new_ns = alloc_cgroup_ns(); - if (IS_ERR(new_ns)) { - put_css_set(cset); - dec_cgroup_namespaces(ucounts); - return new_ns; - } - - new_ns->user_ns = get_user_ns(user_ns); - new_ns->ucounts = ucounts; - new_ns->root_cset = cset; - - return new_ns; -} - -static inline struct cgroup_namespace *to_cg_ns(struct ns_common *ns) -{ - return container_of(ns, struct cgroup_namespace, ns); -} - -static int cgroupns_install(struct nsproxy *nsproxy, struct ns_common *ns) -{ - struct cgroup_namespace *cgroup_ns = to_cg_ns(ns); - - if (!ns_capable(current_user_ns(), CAP_SYS_ADMIN) || - !ns_capable(cgroup_ns->user_ns, CAP_SYS_ADMIN)) - return -EPERM; - - /* Don't need to do anything if we are attaching to our own cgroupns. */ - if (cgroup_ns == nsproxy->cgroup_ns) - return 0; - - get_cgroup_ns(cgroup_ns); - put_cgroup_ns(nsproxy->cgroup_ns); - nsproxy->cgroup_ns = cgroup_ns; - - return 0; -} - -static struct ns_common *cgroupns_get(struct task_struct *task) -{ - struct cgroup_namespace *ns = NULL; - struct nsproxy *nsproxy; - - task_lock(task); - nsproxy = task->nsproxy; - if (nsproxy) { - ns = nsproxy->cgroup_ns; - get_cgroup_ns(ns); - } - task_unlock(task); - - return ns ? &ns->ns : NULL; -} - -static void cgroupns_put(struct ns_common *ns) -{ - put_cgroup_ns(to_cg_ns(ns)); -} - -static struct user_namespace *cgroupns_owner(struct ns_common *ns) -{ - return to_cg_ns(ns)->user_ns; -} - -const struct proc_ns_operations cgroupns_operations = { - .name = "cgroup", - .type = CLONE_NEWCGROUP, - .get = cgroupns_get, - .put = cgroupns_put, - .install = cgroupns_install, - .owner = cgroupns_owner, -}; - -static __init int cgroup_namespaces_init(void) -{ - return 0; -} -subsys_initcall(cgroup_namespaces_init); - #ifdef CONFIG_CGROUP_BPF int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog, enum bpf_attach_type type, bool overridable) @@ -6510,149 +5065,3 @@ int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog, return ret; } #endif /* CONFIG_CGROUP_BPF */ - -#ifdef CONFIG_CGROUP_DEBUG -static struct cgroup_subsys_state * -debug_css_alloc(struct cgroup_subsys_state *parent_css) -{ - struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL); - - if (!css) - return ERR_PTR(-ENOMEM); - - return css; -} - -static void debug_css_free(struct cgroup_subsys_state *css) -{ - kfree(css); -} - -static u64 debug_taskcount_read(struct cgroup_subsys_state *css, - struct cftype *cft) -{ - return cgroup_task_count(css->cgroup); -} - -static u64 current_css_set_read(struct cgroup_subsys_state *css, - struct cftype *cft) -{ - return (u64)(unsigned long)current->cgroups; -} - -static u64 current_css_set_refcount_read(struct cgroup_subsys_state *css, - struct cftype *cft) -{ - u64 count; - - rcu_read_lock(); - count = atomic_read(&task_css_set(current)->refcount); - rcu_read_unlock(); - return count; -} - -static int current_css_set_cg_links_read(struct seq_file *seq, void *v) -{ - struct cgrp_cset_link *link; - struct css_set *cset; - char *name_buf; - - name_buf = kmalloc(NAME_MAX + 1, GFP_KERNEL); - if (!name_buf) - return -ENOMEM; - - spin_lock_irq(&css_set_lock); - rcu_read_lock(); - cset = rcu_dereference(current->cgroups); - list_for_each_entry(link, &cset->cgrp_links, cgrp_link) { - struct cgroup *c = link->cgrp; - - cgroup_name(c, name_buf, NAME_MAX + 1); - seq_printf(seq, "Root %d group %s\n", - c->root->hierarchy_id, name_buf); - } - rcu_read_unlock(); - spin_unlock_irq(&css_set_lock); - kfree(name_buf); - return 0; -} - -#define MAX_TASKS_SHOWN_PER_CSS 25 -static int cgroup_css_links_read(struct seq_file *seq, void *v) -{ - struct cgroup_subsys_state *css = seq_css(seq); - struct cgrp_cset_link *link; - - spin_lock_irq(&css_set_lock); - list_for_each_entry(link, &css->cgroup->cset_links, cset_link) { - struct css_set *cset = link->cset; - struct task_struct *task; - int count = 0; - - seq_printf(seq, "css_set %p\n", cset); - - list_for_each_entry(task, &cset->tasks, cg_list) { - if (count++ > MAX_TASKS_SHOWN_PER_CSS) - goto overflow; - seq_printf(seq, " task %d\n", task_pid_vnr(task)); - } - - list_for_each_entry(task, &cset->mg_tasks, cg_list) { - if (count++ > MAX_TASKS_SHOWN_PER_CSS) - goto overflow; - seq_printf(seq, " task %d\n", task_pid_vnr(task)); - } - continue; - overflow: - seq_puts(seq, " ...\n"); - } - spin_unlock_irq(&css_set_lock); - return 0; -} - -static u64 releasable_read(struct cgroup_subsys_state *css, struct cftype *cft) -{ - return (!cgroup_is_populated(css->cgroup) && - !css_has_online_children(&css->cgroup->self)); -} - -static struct cftype debug_files[] = { - { - .name = "taskcount", - .read_u64 = debug_taskcount_read, - }, - - { - .name = "current_css_set", - .read_u64 = current_css_set_read, - }, - - { - .name = "current_css_set_refcount", - .read_u64 = current_css_set_refcount_read, - }, - - { - .name = "current_css_set_cg_links", - .seq_show = current_css_set_cg_links_read, - }, - - { - .name = "cgroup_css_links", - .seq_show = cgroup_css_links_read, - }, - - { - .name = "releasable", - .read_u64 = releasable_read, - }, - - { } /* terminate */ -}; - -struct cgroup_subsys debug_cgrp_subsys = { - .css_alloc = debug_css_alloc, - .css_free = debug_css_free, - .legacy_cftypes = debug_files, -}; -#endif /* CONFIG_CGROUP_DEBUG */ diff --git a/kernel/cpuset.c b/kernel/cgroup/cpuset.c index b3088886cd37..b3088886cd37 100644 --- a/kernel/cpuset.c +++ b/kernel/cgroup/cpuset.c diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup/freezer.c index 1b72d56edce5..1b72d56edce5 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup/freezer.c diff --git a/kernel/cgroup/namespace.c b/kernel/cgroup/namespace.c new file mode 100644 index 000000000000..cff7ea62c38f --- /dev/null +++ b/kernel/cgroup/namespace.c @@ -0,0 +1,155 @@ +#include "cgroup-internal.h" + +#include <linux/sched.h> +#include <linux/slab.h> +#include <linux/nsproxy.h> +#include <linux/proc_ns.h> + + +/* cgroup namespaces */ + +static struct ucounts *inc_cgroup_namespaces(struct user_namespace *ns) +{ + return inc_ucount(ns, current_euid(), UCOUNT_CGROUP_NAMESPACES); +} + +static void dec_cgroup_namespaces(struct ucounts *ucounts) +{ + dec_ucount(ucounts, UCOUNT_CGROUP_NAMESPACES); +} + +static struct cgroup_namespace *alloc_cgroup_ns(void) +{ + struct cgroup_namespace *new_ns; + int ret; + + new_ns = kzalloc(sizeof(struct cgroup_namespace), GFP_KERNEL); + if (!new_ns) + return ERR_PTR(-ENOMEM); + ret = ns_alloc_inum(&new_ns->ns); + if (ret) { + kfree(new_ns); + return ERR_PTR(ret); + } + atomic_set(&new_ns->count, 1); + new_ns->ns.ops = &cgroupns_operations; + return new_ns; +} + +void free_cgroup_ns(struct cgroup_namespace *ns) +{ + put_css_set(ns->root_cset); + dec_cgroup_namespaces(ns->ucounts); + put_user_ns(ns->user_ns); + ns_free_inum(&ns->ns); + kfree(ns); +} +EXPORT_SYMBOL(free_cgroup_ns); + +struct cgroup_namespace *copy_cgroup_ns(unsigned long flags, + struct user_namespace *user_ns, + struct cgroup_namespace *old_ns) +{ + struct cgroup_namespace *new_ns; + struct ucounts *ucounts; + struct css_set *cset; + + BUG_ON(!old_ns); + + if (!(flags & CLONE_NEWCGROUP)) { + get_cgroup_ns(old_ns); + return old_ns; + } + + /* Allow only sysadmin to create cgroup namespace. */ + if (!ns_capable(user_ns, CAP_SYS_ADMIN)) + return ERR_PTR(-EPERM); + + ucounts = inc_cgroup_namespaces(user_ns); + if (!ucounts) + return ERR_PTR(-ENOSPC); + + /* It is not safe to take cgroup_mutex here */ + spin_lock_irq(&css_set_lock); + cset = task_css_set(current); + get_css_set(cset); + spin_unlock_irq(&css_set_lock); + + new_ns = alloc_cgroup_ns(); + if (IS_ERR(new_ns)) { + put_css_set(cset); + dec_cgroup_namespaces(ucounts); + return new_ns; + } + + new_ns->user_ns = get_user_ns(user_ns); + new_ns->ucounts = ucounts; + new_ns->root_cset = cset; + + return new_ns; +} + +static inline struct cgroup_namespace *to_cg_ns(struct ns_common *ns) +{ + return container_of(ns, struct cgroup_namespace, ns); +} + +static int cgroupns_install(struct nsproxy *nsproxy, struct ns_common *ns) +{ + struct cgroup_namespace *cgroup_ns = to_cg_ns(ns); + + if (!ns_capable(current_user_ns(), CAP_SYS_ADMIN) || + !ns_capable(cgroup_ns->user_ns, CAP_SYS_ADMIN)) + return -EPERM; + + /* Don't need to do anything if we are attaching to our own cgroupns. */ + if (cgroup_ns == nsproxy->cgroup_ns) + return 0; + + get_cgroup_ns(cgroup_ns); + put_cgroup_ns(nsproxy->cgroup_ns); + nsproxy->cgroup_ns = cgroup_ns; + + return 0; +} + +static struct ns_common *cgroupns_get(struct task_struct *task) +{ + struct cgroup_namespace *ns = NULL; + struct nsproxy *nsproxy; + + task_lock(task); + nsproxy = task->nsproxy; + if (nsproxy) { + ns = nsproxy->cgroup_ns; + get_cgroup_ns(ns); + } + task_unlock(task); + + return ns ? &ns->ns : NULL; +} + +static void cgroupns_put(struct ns_common *ns) +{ + put_cgroup_ns(to_cg_ns(ns)); +} + +static struct user_namespace *cgroupns_owner(struct ns_common *ns) +{ + return to_cg_ns(ns)->user_ns; +} + +const struct proc_ns_operations cgroupns_operations = { + .name = "cgroup", + .type = CLONE_NEWCGROUP, + .get = cgroupns_get, + .put = cgroupns_put, + .install = cgroupns_install, + .owner = cgroupns_owner, +}; + +static __init int cgroup_namespaces_init(void) +{ + return 0; +} +subsys_initcall(cgroup_namespaces_init); diff --git a/kernel/cgroup_pids.c b/kernel/cgroup/pids.c index 2bd673783f1a..2bd673783f1a 100644 --- a/kernel/cgroup_pids.c +++ b/kernel/cgroup/pids.c 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 <pandit.parav@gmail.com> + * + * 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 <linux/bitops.h> +#include <linux/slab.h> +#include <linux/seq_file.h> +#include <linux/cgroup.h> +#include <linux/parser.h> +#include <linux/cgroup_rdma.h> + +#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, +}; diff --git a/kernel/events/core.c b/kernel/events/core.c index b2eb3542e829..5b4e0b98f4eb 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -10959,5 +10959,11 @@ struct cgroup_subsys perf_event_cgrp_subsys = { .css_alloc = perf_cgroup_css_alloc, .css_free = perf_cgroup_css_free, .attach = perf_cgroup_attach, + /* + * Implicitly enable on dfl hierarchy so that perf events can + * always be filtered by cgroup2 path as long as perf_event + * controller is not mounted on a legacy hierarchy. + */ + .implicit_on_dfl = true, }; #endif /* CONFIG_CGROUP_PERF */ diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c index 8fdee24725a7..eafbf11442b2 100644 --- a/tools/perf/util/cgroup.c +++ b/tools/perf/util/cgroup.c @@ -12,8 +12,8 @@ cgroupfs_find_mountpoint(char *buf, size_t maxlen) { FILE *fp; char mountpoint[PATH_MAX + 1], tokens[PATH_MAX + 1], type[PATH_MAX + 1]; + char path_v1[PATH_MAX + 1], path_v2[PATH_MAX + 2], *path; char *token, *saved_ptr = NULL; - int found = 0; fp = fopen("/proc/mounts", "r"); if (!fp) @@ -24,31 +24,43 @@ cgroupfs_find_mountpoint(char *buf, size_t maxlen) * and inspect every cgroupfs mount point to find one that has * perf_event subsystem */ + path_v1[0] = '\0'; + path_v2[0] = '\0'; + while (fscanf(fp, "%*s %"STR(PATH_MAX)"s %"STR(PATH_MAX)"s %" STR(PATH_MAX)"s %*d %*d\n", mountpoint, type, tokens) == 3) { - if (!strcmp(type, "cgroup")) { + if (!path_v1[0] && !strcmp(type, "cgroup")) { token = strtok_r(tokens, ",", &saved_ptr); while (token != NULL) { if (!strcmp(token, "perf_event")) { - found = 1; + strcpy(path_v1, mountpoint); break; } token = strtok_r(NULL, ",", &saved_ptr); } } - if (found) + + if (!path_v2[0] && !strcmp(type, "cgroup2")) + strcpy(path_v2, mountpoint); + + if (path_v1[0] && path_v2[0]) break; } fclose(fp); - if (!found) + + if (path_v1[0]) + path = path_v1; + else if (path_v2[0]) + path = path_v2; + else return -1; - if (strlen(mountpoint) < maxlen) { - strcpy(buf, mountpoint); + if (strlen(path) < maxlen) { + strcpy(buf, path); return 0; } return -1; |