diff options
| -rw-r--r-- | Documentation/cgroups/unified-hierarchy.txt | 102 | ||||
| -rw-r--r-- | MAINTAINERS | 1 | ||||
| -rw-r--r-- | fs/kernfs/kernfs-internal.h | 1 | ||||
| -rw-r--r-- | include/linux/cgroup-defs.h | 501 | ||||
| -rw-r--r-- | include/linux/cgroup.h | 1007 | ||||
| -rw-r--r-- | include/linux/init_task.h | 8 | ||||
| -rw-r--r-- | include/linux/kernfs.h | 5 | ||||
| -rw-r--r-- | include/linux/sched.h | 65 | ||||
| -rw-r--r-- | init/Kconfig | 1 | ||||
| -rw-r--r-- | kernel/cgroup.c | 273 | ||||
| -rw-r--r-- | kernel/fork.c | 4 |
11 files changed, 1028 insertions, 940 deletions
diff --git a/Documentation/cgroups/unified-hierarchy.txt b/Documentation/cgroups/unified-hierarchy.txt index eb102fb..86847a7 100644 --- a/Documentation/cgroups/unified-hierarchy.txt +++ b/Documentation/cgroups/unified-hierarchy.txt @@ -17,15 +17,18 @@ CONTENTS 3. Structural Constraints 3-1. Top-down 3-2. No internal tasks -4. Other Changes - 4-1. [Un]populated Notification - 4-2. Other Core Changes - 4-3. Per-Controller Changes - 4-3-1. blkio - 4-3-2. cpuset - 4-3-3. memory -5. Planned Changes - 5-1. CAP for resource control +4. Delegation + 4-1. Model of delegation + 4-2. Common ancestor rule +5. Other Changes + 5-1. [Un]populated Notification + 5-2. Other Core Changes + 5-3. Per-Controller Changes + 5-3-1. blkio + 5-3-2. cpuset + 5-3-3. memory +6. Planned Changes + 6-1. CAP for resource control 1. Background @@ -245,9 +248,72 @@ cgroup must create children and transfer all its tasks to the children before enabling controllers in its "cgroup.subtree_control" file. -4. Other Changes +4. Delegation -4-1. [Un]populated Notification +4-1. Model of delegation + +A cgroup can be delegated to a less privileged user by granting write +access of the directory and its "cgroup.procs" file to the user. Note +that the resource control knobs in a given directory concern the +resources of the parent and thus must not be delegated along with the +directory. + +Once delegated, the user can build sub-hierarchy under the directory, +organize processes as it sees fit and further distribute the resources +it got from the parent. The limits and other settings of all resource +controllers are hierarchical and regardless of what happens in the +delegated sub-hierarchy, nothing can escape the resource restrictions +imposed by the parent. + +Currently, cgroup doesn't impose any restrictions on the number of +cgroups in or nesting depth of a delegated sub-hierarchy; however, +this may in the future be limited explicitly. + + +4-2. Common ancestor rule + +On the unified hierarchy, to write to a "cgroup.procs" file, in +addition to the usual write permission to the file and uid match, the +writer must also have write access to the "cgroup.procs" file of the +common ancestor of the source and destination cgroups. This prevents +delegatees from smuggling processes across disjoint sub-hierarchies. + +Let's say cgroups C0 and C1 have been delegated to user U0 who created +C00, C01 under C0 and C10 under C1 as follows. + + ~~~~~~~~~~~~~ - C0 - C00 + ~ cgroup ~ \ C01 + ~ hierarchy ~ + ~~~~~~~~~~~~~ - C1 - C10 + +C0 and C1 are separate entities in terms of resource distribution +regardless of their relative positions in the hierarchy. The +resources the processes under C0 are entitled to are controlled by +C0's ancestors and may be completely different from C1. It's clear +that the intention of delegating C0 to U0 is allowing U0 to organize +the processes under C0 and further control the distribution of C0's +resources. + +On traditional hierarchies, if a task has write access to "tasks" or +"cgroup.procs" file of a cgroup and its uid agrees with the target, it +can move the target to the cgroup. In the above example, U0 will not +only be able to move processes in each sub-hierarchy but also across +the two sub-hierarchies, effectively allowing it to violate the +organizational and resource restrictions implied by the hierarchical +structure above C0 and C1. + +On the unified hierarchy, let's say U0 wants to write the pid of a +process which has a matching uid and is currently in C10 into +"C00/cgroup.procs". U0 obviously has write access to the file and +migration permission 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" and thus be denied with -EACCES. + + +5. Other Changes + +5-1. [Un]populated Notification cgroup users often need a way to determine when a cgroup's subhierarchy becomes empty so that it can be cleaned up. cgroup @@ -289,7 +355,7 @@ supported and the interface files "release_agent" and "notify_on_release" do not exist. -4-2. Other Core Changes +5-2. Other Core Changes - None of the mount options is allowed. @@ -306,14 +372,14 @@ supported and the interface files "release_agent" and - The "cgroup.clone_children" file is removed. -4-3. Per-Controller Changes +5-3. Per-Controller Changes -4-3-1. blkio +5-3-1. blkio - blk-throttle becomes properly hierarchical. -4-3-2. cpuset +5-3-2. cpuset - Tasks are kept in empty cpusets after hotplug and take on the masks of the nearest non-empty ancestor, instead of being moved to it. @@ -322,7 +388,7 @@ supported and the interface files "release_agent" and masks of the nearest non-empty ancestor. -4-3-3. memory +5-3-3. memory - use_hierarchy is on by default and the cgroup file for the flag is not created. @@ -407,9 +473,9 @@ supported and the interface files "release_agent" and memory.low, memory.high, and memory.max will use the string "max" to indicate and set the highest possible value. -5. Planned Changes +6. Planned Changes -5-1. CAP for resource control +6-1. CAP for resource control Unified hierarchy will require one of the capabilities(7), which is yet to be decided, for all resource control related knobs. Process diff --git a/MAINTAINERS b/MAINTAINERS index 68457d8..c54a674 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2816,6 +2816,7 @@ F: drivers/connector/ CONTROL GROUP (CGROUP) M: Tejun Heo <tj@kernel.org> M: Li Zefan <lizefan@huawei.com> +M: Johannes Weiner <hannes@cmpxchg.org> L: cgroups@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup.git S: Maintained diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h index af9fa74..6762bfb 100644 --- a/fs/kernfs/kernfs-internal.h +++ b/fs/kernfs/kernfs-internal.h @@ -76,7 +76,6 @@ extern struct kmem_cache *kernfs_node_cache; /* * inode.c */ -struct inode *kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn); void kernfs_evict_inode(struct inode *inode); int kernfs_iop_permission(struct inode *inode, int mask); int kernfs_iop_setattr(struct dentry *dentry, struct iattr *iattr); diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h new file mode 100644 index 0000000..93755a6 --- /dev/null +++ b/include/linux/cgroup-defs.h @@ -0,0 +1,501 @@ +/* + * linux/cgroup-defs.h - basic definitions for cgroup + * + * This file provides basic type and interface. Include this file directly + * only if necessary to avoid cyclic dependencies. + */ +#ifndef _LINUX_CGROUP_DEFS_H +#define _LINUX_CGROUP_DEFS_H + +#include <linux/limits.h> +#include <linux/list.h> +#include <linux/idr.h> +#include <linux/wait.h> +#include <linux/mutex.h> +#include <linux/rcupdate.h> +#include <linux/percpu-refcount.h> +#include <linux/percpu-rwsem.h> +#include <linux/workqueue.h> + +#ifdef CONFIG_CGROUPS + +struct cgroup; +struct cgroup_root; +struct cgroup_subsys; +struct cgroup_taskset; +struct kernfs_node; +struct kernfs_ops; +struct kernfs_open_file; +struct seq_file; + +#define MAX_CGROUP_TYPE_NAMELEN 32 +#define MAX_CGROUP_ROOT_NAMELEN 64 +#define MAX_CFTYPE_NAME 64 + +/* define the enumeration of all cgroup subsystems */ +#define SUBSYS(_x) _x ## _cgrp_id, +enum cgroup_subsys_id { +#include <linux/cgroup_subsys.h> + CGROUP_SUBSYS_COUNT, +}; +#undef SUBSYS + +/* bits in struct cgroup_subsys_state flags field */ +enum { + CSS_NO_REF = (1 << 0), /* no reference counting for this css */ + CSS_ONLINE = (1 << 1), /* between ->css_online() and ->css_offline() */ + CSS_RELEASED = (1 << 2), /* refcnt reached zero, released */ +}; + +/* bits in struct cgroup flags field */ +enum { + /* Control Group requires release notifications to userspace */ + CGRP_NOTIFY_ON_RELEASE, + /* + * Clone the parent's configuration when creating a new child + * cpuset cgroup. For historical reasons, this option can be + * specified at mount time and thus is implemented here. + */ + CGRP_CPUSET_CLONE_CHILDREN, +}; + +/* cgroup_root->flags */ +enum { + CGRP_ROOT_SANE_BEHAVIOR = (1 << 0), /* __DEVEL__sane_behavior specified */ + CGRP_ROOT_NOPREFIX = (1 << 1), /* mounted subsystems have no named prefix */ + CGRP_ROOT_XATTR = (1 << 2), /* supports extended attributes */ +}; + +/* cftype->flags */ +enum { + CFTYPE_ONLY_ON_ROOT = (1 << 0), /* only create on root cgrp */ + CFTYPE_NOT_ON_ROOT = (1 << 1), /* don't create on root cgrp */ + CFTYPE_NO_PREFIX = (1 << 3), /* (DON'T USE FOR NEW FILES) no subsys prefix */ + + /* internal flags, do not use outside cgroup core proper */ + __CFTYPE_ONLY_ON_DFL = (1 << 16), /* only on default hierarchy */ + __CFTYPE_NOT_ON_DFL = (1 << 17), /* not on default hierarchy */ +}; + +/* + * Per-subsystem/per-cgroup state maintained by the system. This is the + * fundamental structural building block that controllers deal with. + * + * Fields marked with "PI:" are public and immutable and may be accessed + * directly without synchronization. + */ +struct cgroup_subsys_state { + /* PI: the cgroup that this css is attached to */ + struct cgroup *cgroup; + + /* PI: the cgroup subsystem that this css is attached to */ + struct cgroup_subsys *ss; + + /* reference count - access via css_[try]get() and css_put() */ + struct percpu_ref refcnt; + + /* PI: the parent css */ + struct cgroup_subsys_state *parent; + + /* siblings list anchored at the parent's ->children */ + struct list_head sibling; + struct list_head children; + + /* + * PI: Subsys-unique ID. 0 is unused and root is always 1. The + * matching css can be looked up using css_from_id(). + */ + int id; + + unsigned int flags; + + /* + * Monotonically increasing unique serial number which defines a + * uniform order among all csses. It's guaranteed that all + * ->children lists are in the ascending order of ->serial_nr and + * used to allow interrupting and resuming iterations. + */ + u64 serial_nr; + + /* percpu_ref killing and RCU release */ + struct rcu_head rcu_head; + struct work_struct destroy_work; +}; + +/* + * A css_set is a structure holding pointers to a set of + * cgroup_subsys_state objects. This saves space in the task struct + * object and speeds up fork()/exit(), since a single inc/dec and a + * list_add()/del() can bump the reference count on the entire cgroup + * 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 + */ + struct hlist_node hlist; + + /* + * Lists running through all tasks using this cgroup group. + * mg_tasks lists tasks which belong to this cset but are in the + * process of being migrated out or in. Protected by + * css_set_rwsem, but, during migration, once tasks are moved to + * mg_tasks, it can be read safely while holding cgroup_mutex. + */ + struct list_head tasks; + struct list_head mg_tasks; + + /* + * List of cgrp_cset_links pointing at cgroups referenced from this + * css_set. Protected by css_set_lock. + */ + struct list_head cgrp_links; + + /* the default cgroup associated with this css_set */ + struct cgroup *dfl_cgrp; + + /* + * 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 cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; + + /* + * List of csets participating in the on-going migration either as + * source or destination. Protected by cgroup_mutex. + */ + struct list_head mg_preload_node; + struct list_head mg_node; + + /* + * If this cset is acting as the source of migration the following + * two fields are set. mg_src_cgrp is the source cgroup of the + * on-going migration and mg_dst_cset is the destination cset the + * target tasks on this cset should be migrated to. Protected by + * cgroup_mutex. + */ + struct cgroup *mg_src_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]; + + /* For RCU-protected deletion */ + struct rcu_head rcu_head; +}; + +struct cgroup { + /* self css with NULL ->ss, points back to this cgroup */ + struct cgroup_subsys_state self; + + unsigned long flags; /* "unsigned long" so bitops work */ + + /* + * idr allocated in-hierarchy ID. + * + * ID 0 is not used, the ID of the root cgroup is always 1, and a + * new cgroup will be assigned with a smallest available ID. + * + * Allocating/Removing ID must be protected by cgroup_mutex. + */ + int id; + + /* + * If this cgroup contains any tasks, it contributes one to + * populated_cnt. All children with non-zero popuplated_cnt of + * their own contribute one. The count is zero iff there's no task + * in this cgroup or its subtree. + */ + int populated_cnt; + + struct kernfs_node *kn; /* cgroup kernfs entry */ + struct kernfs_node *procs_kn; /* kn for "cgroup.procs" */ + struct kernfs_node *populated_kn; /* kn for "cgroup.subtree_populated" */ + + /* + * The bitmask of subsystems enabled on the child cgroups. + * ->subtree_control is the one configured through + * "cgroup.subtree_control" while ->child_subsys_mask is the + * effective one which may have more subsystems enabled. + * Controller knobs are made available iff it's enabled in + * ->subtree_control. + */ + unsigned int subtree_control; + unsigned int child_subsys_mask; + + /* Private pointers for each registered subsystem */ + struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT]; + + struct cgroup_root *root; + + /* + * List of cgrp_cset_links pointing at css_sets with tasks in this + * cgroup. Protected by css_set_lock. + */ + struct list_head cset_links; + + /* + * On the default hierarchy, a css_set for a cgroup with some + * susbsys disabled will point to css's which are associated with + * the closest ancestor which has the subsys enabled. The + * following lists all css_sets which point to this cgroup's css + * for the given subsystem. + */ + struct list_head e_csets[CGROUP_SUBSYS_COUNT]; + + /* + * list of pidlists, up to two for each namespace (one for procs, one + * for tasks); created on demand. + */ + struct list_head pidlists; + struct mutex pidlist_mutex; + + /* used to wait for offlining of csses */ + wait_queue_head_t offline_waitq; + + /* used to schedule release agent */ + struct work_struct release_agent_work; +}; + +/* + * A cgroup_root represents the root of a cgroup hierarchy, and may be + * associated with a kernfs_root to form an active hierarchy. This is + * internal to cgroup core. Don't access directly from controllers. + */ +struct cgroup_root { + struct kernfs_root *kf_root; + + /* The bitmask of subsystems attached to this hierarchy */ + unsigned int subsys_mask; + + /* Unique id for this hierarchy. */ + int hierarchy_id; + + /* The root cgroup. Root is destroyed on its release. */ + struct cgroup cgrp; + + /* Number of cgroups in the hierarchy, used only for /proc/cgroups */ + atomic_t nr_cgrps; + + /* A list running through the active hierarchies */ + struct list_head root_list; + + /* Hierarchy-specific flags */ + unsigned int flags; + + /* IDs for cgroups in this hierarchy */ + struct idr cgroup_idr; + + /* The path to use for release notifications. */ + char release_agent_path[PATH_MAX]; + + /* The name for this hierarchy - may be empty */ + char name[MAX_CGROUP_ROOT_NAMELEN]; +}; + +/* + * struct cftype: handler definitions for cgroup control files + * + * When reading/writing to a file: + * - the cgroup to use is file->f_path.dentry->d_parent->d_fsdata + * - the 'cftype' of the file is file->f_path.dentry->d_fsdata + */ +struct cftype { + /* + * By convention, the name should begin with the name of the + * subsystem, followed by a period. Zero length string indicates + * end of cftype array. + */ + char name[MAX_CFTYPE_NAME]; + int private; + /* + * If not 0, file mode is set to this value, otherwise it will + * be figured out automatically + */ + umode_t mode; + + /* + * The maximum length of string, excluding trailing nul, that can + * be passed to write. If < PAGE_SIZE-1, PAGE_SIZE-1 is assumed. + */ + size_t max_write_len; + + /* CFTYPE_* flags */ + unsigned int flags; + + /* + * Fields used for internal bookkeeping. Initialized automatically + * during registration. + */ + struct cgroup_subsys *ss; /* NULL for cgroup core files */ + struct list_head node; /* anchored at ss->cfts */ + struct kernfs_ops *kf_ops; + + /* + * read_u64() is a shortcut for the common case of returning a + * single integer. Use it in place of read() + */ + u64 (*read_u64)(struct cgroup_subsys_state *css, struct cftype *cft); + /* + * read_s64() is a signed version of read_u64() + */ + s64 (*read_s64)(struct cgroup_subsys_state *css, struct cftype *cft); + + /* generic seq_file read interface */ + int (*seq_show)(struct seq_file *sf, void *v); + + /* optional ops, implement all or none */ + void *(*seq_start)(struct seq_file *sf, loff_t *ppos); + void *(*seq_next)(struct seq_file *sf, void *v, loff_t *ppos); + void (*seq_stop)(struct seq_file *sf, void *v); + + /* + * write_u64() is a shortcut for the common case of accepting + * a single integer (as parsed by simple_strtoull) from + * userspace. Use in place of write(); return 0 or error. + */ + int (*write_u64)(struct cgroup_subsys_state *css, struct cftype *cft, + u64 val); + /* + * write_s64() is a signed version of write_u64() + */ + int (*write_s64)(struct cgroup_subsys_state *css, struct cftype *cft, + s64 val); + + /* + * write() is the generic write callback which maps directly to + * kernfs write operation and overrides all other operations. + * Maximum write size is determined by ->max_write_len. Use + * of_css/cft() to access the associated css and cft. + */ + ssize_t (*write)(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off); + +#ifdef CONFIG_DEBUG_LOCK_ALLOC + struct lock_class_key lockdep_key; +#endif +}; + +/* + * Control Group subsystem type. + * See Documentation/cgroups/cgroups.txt for details + */ +struct cgroup_subsys { + struct cgroup_subsys_state *(*css_alloc)(struct cgroup_subsys_state *parent_css); + int (*css_online)(struct cgroup_subsys_state *css); + void (*css_offline)(struct cgroup_subsys_state *css); + void (*css_released)(struct cgroup_subsys_state *css); + void (*css_free)(struct cgroup_subsys_state *css); + void (*css_reset)(struct cgroup_subsys_state *css); + void (*css_e_css_changed)(struct cgroup_subsys_state *css); + + int (*can_attach)(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset); + void (*cancel_attach)(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset); + void (*attach)(struct cgroup_subsys_state *css, + struct cgroup_taskset *tset); + void (*fork)(struct task_struct *task); + void (*exit)(struct cgroup_subsys_state *css, + struct cgroup_subsys_state *old_css, + struct task_struct *task); + void (*bind)(struct cgroup_subsys_state *root_css); + + int disabled; + int early_init; + + /* + * If %false, this subsystem is properly hierarchical - + * configuration, resource accounting and restriction on a parent + * cgroup cover those of its children. If %true, hierarchy support + * is broken in some ways - some subsystems ignore hierarchy + * completely while others are only implemented half-way. + * + * It's now disallowed to create nested cgroups if the subsystem is + * broken and cgroup core will emit a warning message on such + * cases. Eventually, all subsystems will be made properly + * hierarchical and this will go away. + */ + bool broken_hierarchy; + bool warned_broken_hierarchy; + + /* the following two fields are initialized automtically during boot */ + int id; + const char *name; + + /* link to parent, protected by cgroup_lock() */ + struct cgroup_root *root; + + /* idr for css->id */ + struct idr css_idr; + + /* + * List of cftypes. Each entry is the first entry of an array + * terminated by zero length name. + */ + struct list_head cfts; + + /* + * Base cftypes which are automatically registered. The two can + * point to the same array. + */ + struct cftype *dfl_cftypes; /* for the default hierarchy */ + struct cftype *legacy_cftypes; /* for the legacy hierarchies */ + + /* + * A subsystem may depend on other subsystems. When such subsystem + * is enabled on a cgroup, the depended-upon subsystems are enabled + * together if available. Subsystems enabled due to dependency are + * not visible to userland until explicitly enabled. The following + * specifies the mask of subsystems that this one depends on. + */ + unsigned int depends_on; +}; + +extern struct percpu_rw_semaphore cgroup_threadgroup_rwsem; + +/** + * cgroup_threadgroup_change_begin - threadgroup exclusion for cgroups + * @tsk: target task + * + * Called from threadgroup_change_begin() and allows cgroup operations to + * synchronize against threadgroup changes using a percpu_rw_semaphore. + */ +static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk) +{ + percpu_down_read(&cgroup_threadgroup_rwsem); +} + +/** + * cgroup_threadgroup_change_end - threadgroup exclusion for cgroups + * @tsk: target task + * + * Called from threadgroup_change_end(). Counterpart of + * cgroup_threadcgroup_change_begin(). + */ +static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) +{ + percpu_up_read(&cgroup_threadgroup_rwsem); +} + +#else /* CONFIG_CGROUPS */ + +#define CGROUP_SUBSYS_COUNT 0 + +static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk) {} +static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) {} + +#endif /* CONFIG_CGROUPS */ + +#endif /* _LINUX_CGROUP_DEFS_H */ diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index e7da0aa..a593e29 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -11,94 +11,200 @@ #include <linux/sched.h> #include <linux/cpumask.h> #include <linux/nodemask.h> -#include <linux/rcupdate.h> #include <linux/rculist.h> #include <linux/cgroupstats.h> #include <linux/rwsem.h> -#include <linux/idr.h> -#include <linux/workqueue.h> #include <linux/fs.h> -#include <linux/percpu-refcount.h> #include <linux/seq_file.h> #include <linux/kernfs.h> -#include <linux/wait.h> + +#include <linux/cgroup-defs.h> #ifdef CONFIG_CGROUPS -struct cgroup_root; -struct cgroup_subsys; -struct cgroup; +/* a css_task_iter should be treated as an opaque object */ +struct css_task_iter { + struct cgroup_subsys *ss; -extern int cgroup_init_early(void); -extern int cgroup_init(void); -extern void cgroup_fork(struct task_struct *p); -extern void cgroup_post_fork(struct task_struct *p); -extern void cgroup_exit(struct task_struct *p); -extern int cgroupstats_build(struct cgroupstats *stats, - struct dentry *dentry); + struct list_head *cset_pos; + struct list_head *cset_head; + + struct list_head *task_pos; + struct list_head *tasks_head; + struct list_head *mg_tasks_head; +}; -extern int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, - struct pid *pid, struct task_struct *tsk); +extern struct cgroup_root cgrp_dfl_root; +extern struct css_set init_css_set; -/* define the enumeration of all cgroup subsystems */ -#define SUBSYS(_x) _x ## _cgrp_id, -enum cgroup_subsys_id { +#define SUBSYS(_x) extern struct cgroup_subsys _x ## _cgrp_subsys; #include <linux/cgroup_subsys.h> - CGROUP_SUBSYS_COUNT, -}; #undef SUBSYS +bool css_has_online_children(struct cgroup_subsys_state *css); +struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss); +struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup, + struct cgroup_subsys *ss); +struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, + struct cgroup_subsys *ss); + +bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor); +int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); +int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); + +int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); +int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); +int cgroup_rm_cftypes(struct cftype *cfts); + +char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen); +int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry); +int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *tsk); + +void cgroup_fork(struct task_struct *p); +void cgroup_post_fork(struct task_struct *p); +void cgroup_exit(struct task_struct *p); + +int cgroup_init_early(void); +int cgroup_init(void); + /* - * Per-subsystem/per-cgroup state maintained by the system. This is the - * fundamental structural building block that controllers deal with. + * Iteration helpers and macros. + */ + +struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, + struct cgroup_subsys_state *parent); +struct cgroup_subsys_state *css_next_descendant_pre(struct cgroup_subsys_state *pos, + struct cgroup_subsys_state *css); +struct cgroup_subsys_state *css_rightmost_descendant(struct cgroup_subsys_state *pos); +struct cgroup_subsys_state *css_next_descendant_post(struct cgroup_subsys_state *pos, + struct cgroup_subsys_state *css); + +struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset); +struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset); + +void css_task_iter_start(struct cgroup_subsys_state *css, + struct css_task_iter *it); +struct task_struct *css_task_iter_next(struct css_task_iter *it); +void css_task_iter_end(struct css_task_iter *it); + +/** + * css_for_each_child - iterate through children of a css + * @pos: the css * to use as the loop cursor + * @parent: css whose children to walk * - * Fields marked with "PI:" are public and immutable and may be accessed - * directly without synchronization. + * Walk @parent's children. Must be called under rcu_read_lock(). + * + * If a subsystem synchronizes ->css_online() and the start of iteration, a + * css which finished ->css_online() is guaranteed to be visible in the + * future iterations and will stay visible until the last reference is put. + * A css which hasn't finished ->css_online() or already finished + * ->css_offline() may show up during traversal. It's each subsystem's + * responsibility to synchronize against on/offlining. + * + * It is allowed to temporarily drop RCU read lock during iteration. The + * caller is responsible for ensuring that @pos remains accessible until + * the start of the next iteration by, for example, bumping the css refcnt. */ -struct cgroup_subsys_state { - /* PI: the cgroup that this css is attached to */ - struct cgroup *cgroup; - - /* PI: the cgroup subsystem that this css is attached to */ - struct cgroup_subsys *ss; - - /* reference count - access via css_[try]get() and css_put() */ - struct percpu_ref refcnt; - - /* PI: the parent css */ - struct cgroup_subsys_state *parent; - - /* siblings list anchored at the parent's ->children */ - struct list_head sibling; - struct list_head children; - - /* - * PI: Subsys-unique ID. 0 is unused and root is always 1. The - * matching css can be looked up using css_from_id(). - */ - int id; - - unsigned int flags; - - /* - * Monotonically increasing unique serial number which defines a - * uniform order among all csses. It's guaranteed that all - * ->children lists are in the ascending order of ->serial_nr and - * used to allow interrupting and resuming iterations. - */ - u64 serial_nr; - - /* percpu_ref killing and RCU release */ - struct rcu_head rcu_head; - struct work_struct destroy_work; -}; +#define css_for_each_child(pos, parent) \ + for ((pos) = css_next_child(NULL, (parent)); (pos); \ + (pos) = css_next_child((pos), (parent))) -/* bits in struct cgroup_subsys_state flags field */ -enum { - CSS_NO_REF = (1 << 0), /* no reference counting for this css */ - CSS_ONLINE = (1 << 1), /* between ->css_online() and ->css_offline() */ - CSS_RELEASED = (1 << 2), /* refcnt reached zero, released */ -}; +/** + * css_for_each_descendant_pre - pre-order walk of a css's descendants + * @pos: the css * to use as the loop cursor + * @root: css whose descendants to walk + * + * Walk @root's descendants. @root is included in the iteration and the + * first node to be visited. Must be called under rcu_read_lock(). + * + * If a subsystem synchronizes ->css_online() and the start of iteration, a + * css which finished ->css_online() is guaranteed to be visible in the + * future iterations and will stay visible until the last reference is put. + * A css which hasn't finished ->css_online() or already finished + * ->css_offline() may show up during traversal. It's each subsystem's + * responsibility to synchronize against on/offlining. + * + * For example, the following guarantees that a descendant can't escape + * state updates of its ancestors. + * + * my_online(@css) + * { + * Lock @css's parent and @css; + * Inherit state from the parent; + * Unlock both. + * } + * + * my_update_state(@css) + * { + * css_for_each_descendant_pre(@pos, @css) { + * Lock @pos; + * if (@pos == @css) + * Update @css's state; + * else + * Verify @pos is alive and inherit state from its parent; + * Unlock @pos; + * } + * } + * + * As long as the inheriting step, including checking the parent state, is + * enclosed inside @pos locking, double-locking the parent isn't necessary + * while inheriting. The state update to the parent is guaranteed to be + * visible by walking order and, as long as inheriting operations to the + * same @pos are atomic to each other, multiple updates racing each other + * still result in the correct state. It's guaranateed that at least one + * inheritance happens for any css after the latest update to its parent. + * + * If checking parent's state requires locking the parent, each inheriting + * iteration should lock and unlock both @pos->parent and @pos. + * + * Alternatively, a subsystem may choose to use a single global lock to + * synchronize ->css_online() and ->css_offline() against tree-walking + * operations. + * + * It is allowed to temporarily drop RCU read lock during iteration. The + * caller is responsible for ensuring that @pos remains accessible until + * the start of the next iteration by, for example, bumping the css refcnt. + */ +#define css_for_each_descendant_pre(pos, css) \ + for ((pos) = css_next_descendant_pre(NULL, (css)); (pos); \ + (pos) = css_next_descendant_pre((pos), (css))) + +/** + * css_for_each_descendant_post - post-order walk of a css's descendants + * @pos: the css * to use as the loop cursor + * @css: css whose descendants to walk + * + * Similar to css_for_each_descendant_pre() but performs post-order + * traversal instead. @root is included in the iteration and the last + * node to be visited. + * + * If a subsystem synchronizes ->css_online() and the start of iteration, a + * css which finished ->css_online() is guaranteed to be visible in the + * future iterations and will stay visible until the last reference is put. + * A css which hasn't finished ->css_online() or already finished + * ->css_offline() may show up during traversal. It's each subsystem's + * responsibility to synchronize against on/offlining. + * + * Note that the walk visibility guarantee example described in pre-order + * walk doesn't apply the same to post-order walks. + */ +#define css_for_each_descendant_post(pos, css) \ + for ((pos) = css_next_descendant_post(NULL, (css)); (pos); \ + (pos) = css_next_descendant_post((pos), (css))) + +/** + * cgroup_taskset_for_each - iterate cgroup_taskset + * @task: the loop cursor + * @tset: taskset to iterate + */ +#define cgroup_taskset_for_each(task, tset) \ + for ((task) = cgroup_taskset_first((tset)); (task); \ + (task) = cgroup_taskset_next((tset))) + +/* + * Inline functions. + */ /** * css_get - obtain a reference on the specified css @@ -185,532 +291,6 @@ static inline void css_put_many(struct cgroup_subsys_state *css, unsigned int n) percpu_ref_put_many(&css->refcnt, n); } -/* bits in struct cgroup flags field */ -enum { - /* Control Group requires release notifications to userspace */ - CGRP_NOTIFY_ON_RELEASE, - /* - * Clone the parent's configuration when creating a new child - * cpuset cgroup. For historical reasons, this option can be - * specified at mount time and thus is implemented here. - */ - CGRP_CPUSET_CLONE_CHILDREN, -}; - -struct cgroup { - /* self css with NULL ->ss, points back to this cgroup */ - struct cgroup_subsys_state self; - - unsigned long flags; /* "unsigned long" so bitops work */ - - /* - * idr allocated in-hierarchy ID. - * - * ID 0 is not used, the ID of the root cgroup is always 1, and a - * new cgroup will be assigned with a smallest available ID. - * - * Allocating/Removing ID must be protected by cgroup_mutex. - */ - int id; - - /* - * If this cgroup contains any tasks, it contributes one to - * populated_cnt. All children with non-zero popuplated_cnt of - * their own contribute one. The count is zero iff there's no task - * in this cgroup or its subtree. - */ - int populated_cnt; - - struct kernfs_node *kn; /* cgroup kernfs entry */ - struct kernfs_node *populated_kn; /* kn for "cgroup.subtree_populated" */ - - /* - * The bitmask of subsystems enabled on the child cgroups. - * ->subtree_control is the one configured through - * "cgroup.subtree_control" while ->child_subsys_mask is the - * effective one which may have more subsystems enabled. - * Controller knobs are made available iff it's enabled in - * ->subtree_control. - */ - unsigned int subtree_control; - unsigned int child_subsys_mask; - - /* Private pointers for each registered subsystem */ - struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT]; - - struct cgroup_root *root; - - /* - * List of cgrp_cset_links pointing at css_sets with tasks in this - * cgroup. Protected by css_set_lock. - */ - struct list_head cset_links; - - /* - * On the default hierarchy, a css_set for a cgroup with some - * susbsys disabled will point to css's which are associated with - * the closest ancestor which has the subsys enabled. The - * following lists all css_sets which point to this cgroup's css - * for the given subsystem. - */ - struct list_head e_csets[CGROUP_SUBSYS_COUNT]; - - /* - * list of pidlists, up to two for each namespace (one for procs, one - * for tasks); created on demand. - */ - struct list_head pidlists; - struct mutex pidlist_mutex; - - /* used to wait for offlining of csses */ - wait_queue_head_t offline_waitq; - - /* used to schedule release agent */ - struct work_struct release_agent_work; -}; - -#define MAX_CGROUP_ROOT_NAMELEN 64 - -/* cgroup_root->flags */ -enum { - CGRP_ROOT_SANE_BEHAVIOR = (1 << 0), /* __DEVEL__sane_behavior specified */ - CGRP_ROOT_NOPREFIX = (1 << 1), /* mounted subsystems have no named prefix */ - CGRP_ROOT_XATTR = (1 << 2), /* supports extended attributes */ -}; - -/* - * A cgroup_root represents the root of a cgroup hierarchy, and may be - * associated with a kernfs_root to form an active hierarchy. This is - * internal to cgroup core. Don't access directly from controllers. - */ -struct cgroup_root { - struct kernfs_root *kf_root; - - /* The bitmask of subsystems attached to this hierarchy */ - unsigned int subsys_mask; - - /* Unique id for this hierarchy. */ - int hierarchy_id; - - /* The root cgroup. Root is destroyed on its release. */ - struct cgroup cgrp; - - /* Number of cgroups in the hierarchy, used only for /proc/cgroups */ - atomic_t nr_cgrps; - - /* A list running through the active hierarchies */ - struct list_head root_list; - - /* Hierarchy-specific flags */ - unsigned int flags; - - /* IDs for cgroups in this hierarchy */ - struct idr cgroup_idr; - - /* The path to use for release notifications. */ - char release_agent_path[PATH_MAX]; - - /* The name for this hierarchy - may be empty */ - char name[MAX_CGROUP_ROOT_NAMELEN]; -}; - -/* - * A css_set is a structure holding pointers to a set of - * cgroup_subsys_state objects. This saves space in the task struct - * object and speeds up fork()/exit(), since a single inc/dec and a - * list_add()/del() can bump the reference count on the entire cgroup - * 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 - */ - struct hlist_node hlist; - - /* - * Lists running through all tasks using this cgroup group. - * mg_tasks lists tasks which belong to this cset but are in the - * process of being migrated out or in. Protected by - * css_set_rwsem, but, during migration, once tasks are moved to - * mg_tasks, it can be read safely while holding cgroup_mutex. - */ - struct list_head tasks; - struct list_head mg_tasks; - - /* - * List of cgrp_cset_links pointing at cgroups referenced from this - * css_set. Protected by css_set_lock. - */ - struct list_head cgrp_links; - - /* the default cgroup associated with this css_set */ - struct cgroup *dfl_cgrp; - - /* - * 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 cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; - - /* - * List of csets participating in the on-going migration either as - * source or destination. Protected by cgroup_mutex. - */ - struct list_head mg_preload_node; - struct list_head mg_node; - - /* - * If this cset is acting as the source of migration the following - * two fields are set. mg_src_cgrp is the source cgroup of the - * on-going migration and mg_dst_cset is the destination cset the - * target tasks on this cset should be migrated to. Protected by - * cgroup_mutex. - */ - struct cgroup *mg_src_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]; - - /* For RCU-protected deletion */ - struct rcu_head rcu_head; -}; - -/* - * struct cftype: handler definitions for cgroup control files - * - * When reading/writing to a file: - * - the cgroup to use is file->f_path.dentry->d_parent->d_fsdata - * - the 'cftype' of the file is file->f_path.dentry->d_fsdata - */ - -/* cftype->flags */ -enum { - CFTYPE_ONLY_ON_ROOT = (1 << 0), /* only create on root cgrp */ - CFTYPE_NOT_ON_ROOT = (1 << 1), /* don't create on root cgrp */ - CFTYPE_NO_PREFIX = (1 << 3), /* (DON'T USE FOR NEW FILES) no subsys prefix */ - - /* internal flags, do not use outside cgroup core proper */ - __CFTYPE_ONLY_ON_DFL = (1 << 16), /* only on default hierarchy */ - __CFTYPE_NOT_ON_DFL = (1 << 17), /* not on default hierarchy */ -}; - -#define MAX_CFTYPE_NAME 64 - -struct cftype { - /* - * By convention, the name should begin with the name of the - * subsystem, followed by a period. Zero length string indicates - * end of cftype array. - */ - char name[MAX_CFTYPE_NAME]; - int private; - /* - * If not 0, file mode is set to this value, otherwise it will - * be figured out automatically - */ - umode_t mode; - - /* - * The maximum length of string, excluding trailing nul, that can - * be passed to write. If < PAGE_SIZE-1, PAGE_SIZE-1 is assumed. - */ - size_t max_write_len; - - /* CFTYPE_* flags */ - unsigned int flags; - - /* - * Fields used for internal bookkeeping. Initialized automatically - * during registration. - */ - struct cgroup_subsys *ss; /* NULL for cgroup core files */ - struct list_head node; /* anchored at ss->cfts */ - struct kernfs_ops *kf_ops; - - /* - * read_u64() is a shortcut for the common case of returning a - * single integer. Use it in place of read() - */ - u64 (*read_u64)(struct cgroup_subsys_state *css, struct cftype *cft); - /* - * read_s64() is a signed version of read_u64() - */ - s64 (*read_s64)(struct cgroup_subsys_state *css, struct cftype *cft); - - /* generic seq_file read interface */ - int (*seq_show)(struct seq_file *sf, void *v); - - /* optional ops, implement all or none */ - void *(*seq_start)(struct seq_file *sf, loff_t *ppos); - void *(*seq_next)(struct seq_file *sf, void *v, loff_t *ppos); - void (*seq_stop)(struct seq_file *sf, void *v); - - /* - * write_u64() is a shortcut for the common case of accepting - * a single integer (as parsed by simple_strtoull) from - * userspace. Use in place of write(); return 0 or error. - */ - int (*write_u64)(struct cgroup_subsys_state *css, struct cftype *cft, - u64 val); - /* - * write_s64() is a signed version of write_u64() - */ - int (*write_s64)(struct cgroup_subsys_state *css, struct cftype *cft, - s64 val); - - /* - * write() is the generic write callback which maps directly to - * kernfs write operation and overrides all other operations. - * Maximum write size is determined by ->max_write_len. Use - * of_css/cft() to access the associated css and cft. - */ - ssize_t (*write)(struct kernfs_open_file *of, - char *buf, size_t nbytes, loff_t off); - -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lock_class_key lockdep_key; -#endif -}; - -extern struct cgroup_root cgrp_dfl_root; -extern struct css_set init_css_set; - -/** - * cgroup_on_dfl - test whether a cgroup is on the default hierarchy - * @cgrp: the cgroup of interest - * - * The default hierarchy is the v2 interface of cgroup and this function - * can be used to test whether a cgroup is on the default hierarchy for - * cases where a subsystem should behave differnetly depending on the - * interface version. - * - * The set of behaviors which change on the default hierarchy are still - * being determined and the mount option is prefixed with __DEVEL__. - * - * List of changed behaviors: - * - * - Mount options "noprefix", "xattr", "clone_children", "release_agent" - * and "name" are disallowed. - * - * - When mounting an existing superblock, mount options should match. - * - * - Remount is disallowed. - * - * - rename(2) is disallowed. - * - * - "tasks" is removed. Everything should be at process granularity. Use - * "cgroup.procs" instead. - * - * - "cgroup.procs" is not sorted. pids will be unique unless they got - * recycled inbetween reads. - * - * - "release_agent" and "notify_on_release" are removed. Replacement - * notification mechanism will be implemented. - * - * - "cgroup.clone_children" is removed. - * - * - "cgroup.subtree_populated" is available. Its value is 0 if the cgroup - * and its descendants contain no task; otherwise, 1. The file also - * generates kernfs notification which can be monitored through poll and - * [di]notify when the value of the file changes. - * - * - cpuset: tasks will be kept in empty cpusets when hotplug happens and - * take masks of ancestors with non-empty cpus/mems, instead of being - * moved to an ancestor. - * - * - cpuset: a task can be moved into an empty cpuset, and again it takes - * masks of ancestors. - * - * - memcg: use_hierarchy is on by default and the cgroup file for the flag - * is not created. - * - * - blkcg: blk-throttle becomes properly hierarchical. - * - * - debug: disallowed on the default hierarchy. - */ -static inline bool cgroup_on_dfl(const struct cgroup *cgrp) -{ - return cgrp->root == &cgrp_dfl_root; -} - -/* no synchronization, the result can only be used as a hint */ -static inline bool cgroup_has_tasks(struct cgroup *cgrp) -{ - return !list_empty(&cgrp->cset_links); -} - -/* returns ino associated with a cgroup */ -static inline ino_t cgroup_ino(struct cgroup *cgrp) -{ - return cgrp->kn->ino; -} - -/* cft/css accessors for cftype->write() operation */ -static inline struct cftype *of_cft(struct kernfs_open_file *of) -{ - return of->kn->priv; -} - -struct cgroup_subsys_state *of_css(struct kernfs_open_file *of); - -/* cft/css accessors for cftype->seq_*() operations */ -static inline struct cftype *seq_cft(struct seq_file *seq) -{ - return of_cft(seq->private); -} - -static inline struct cgroup_subsys_state *seq_css(struct seq_file *seq) -{ - return of_css(seq->private); -} - -/* - * Name / path handling functions. All are thin wrappers around the kernfs - * counterparts and can be called under any context. - */ - -static inline int cgroup_name(struct cgroup *cgrp, char *buf, size_t buflen) -{ - return kernfs_name(cgrp->kn, buf, buflen); -} - -static inline char * __must_check cgroup_path(struct cgroup *cgrp, char *buf, - size_t buflen) -{ - return kernfs_path(cgrp->kn, buf, buflen); -} - -static inline void pr_cont_cgroup_name(struct cgroup *cgrp) -{ - pr_cont_kernfs_name(cgrp->kn); -} - -static inline void pr_cont_cgroup_path(struct cgroup *cgrp) -{ - pr_cont_kernfs_path(cgrp->kn); -} - -char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen); - -int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); -int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); -int cgroup_rm_cftypes(struct cftype *cfts); - -bool cgroup_is_descendant(struct cgroup *cgrp, struct cgroup *ancestor); - -/* - * Control Group taskset, used to pass around set of tasks to cgroup_subsys - * methods. - */ -struct cgroup_taskset; -struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset); -struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset); - -/** - * cgroup_taskset_for_each - iterate cgroup_taskset - * @task: the loop cursor - * @tset: taskset to iterate - */ -#define cgroup_taskset_for_each(task, tset) \ - for ((task) = cgroup_taskset_first((tset)); (task); \ - (task) = cgroup_taskset_next((tset))) - -/* - * Control Group subsystem type. - * See Documentation/cgroups/cgroups.txt for details - */ - -struct cgroup_subsys { - struct cgroup_subsys_state *(*css_alloc)(struct cgroup_subsys_state *parent_css); - int (*css_online)(struct cgroup_subsys_state *css); - void (*css_offline)(struct cgroup_subsys_state *css); - void (*css_released)(struct cgroup_subsys_state *css); - void (*css_free)(struct cgroup_subsys_state *css); - void (*css_reset)(struct cgroup_subsys_state *css); - void (*css_e_css_changed)(struct cgroup_subsys_state *css); - - int (*can_attach)(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset); - void (*cancel_attach)(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset); - void (*attach)(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset); - void (*fork)(struct task_struct *task); - void (*exit)(struct cgroup_subsys_state *css, - struct cgroup_subsys_state *old_css, - struct task_struct *task); - void (*bind)(struct cgroup_subsys_state *root_css); - - int disabled; - int early_init; - - /* - * If %false, this subsystem is properly hierarchical - - * configuration, resource accounting and restriction on a parent - * cgroup cover those of its children. If %true, hierarchy support - * is broken in some ways - some subsystems ignore hierarchy - * completely while others are only implemented half-way. - * - * It's now disallowed to create nested cgroups if the subsystem is - * broken and cgroup core will emit a warning message on such - * cases. Eventually, all subsystems will be made properly - * hierarchical and this will go away. - */ - bool broken_hierarchy; - bool warned_broken_hierarchy; - - /* the following two fields are initialized automtically during boot */ - int id; -#define MAX_CGROUP_TYPE_NAMELEN 32 - const char *name; - - /* link to parent, protected by cgroup_lock() */ - struct cgroup_root *root; - - /* idr for css->id */ - struct idr css_idr; - - /* - * List of cftypes. Each entry is the first entry of an array - * terminated by zero length name. - */ - struct list_head cfts; - - /* - * Base cftypes which are automatically registered. The two can - * point to the same array. - */ - struct cftype *dfl_cftypes; /* for the default hierarchy */ - struct cftype *legacy_cftypes; /* for the legacy hierarchies */ - - /* - * A subsystem may depend on other subsystems. When such subsystem - * is enabled on a cgroup, the depended-upon subsystems are enabled - * together if available. Subsystems enabled due to dependency are - * not visible to userland until explicitly enabled. The following - * specifies the mask of subsystems that this one depends on. - */ - unsigned int depends_on; -}; - -#define SUBSYS(_x) extern struct cgroup_subsys _x ## _cgrp_subsys; -#include <linux/cgroup_subsys.h> -#undef SUBSYS - /** * task_css_set_check - obtain a task's css_set with extra access conditions * @task: the task to obtain css_set for @@ -818,178 +398,137 @@ static inline struct cgroup *task_cgroup(struct task_struct *task, return task_css(task, subsys_id)->cgroup; } -struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, - struct cgroup_subsys_state *parent); - -struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss); - /** - * css_for_each_child - iterate through children of a css - * @pos: the css * to use as the loop cursor - * @parent: css whose children to walk + * cgroup_on_dfl - test whether a cgroup is on the default hierarchy + * @cgrp: the cgroup of interest * - * Walk @parent's children. Must be called under rcu_read_lock(). + * The default hierarchy is the v2 interface of cgroup and this function + * can be used to test whether a cgroup is on the default hierarchy for + * cases where a subsystem should behave differnetly depending on the + * interface version. * - * If a subsystem synchronizes ->css_online() and the start of iteration, a - * css which finished ->css_online() is guaranteed to be visible in the - * future iterations and will stay visible until the last reference is put. - * A css which hasn't finished ->css_online() or already finished - * ->css_offline() may show up during traversal. It's each subsystem's - * responsibility to synchronize against on/offlining. + * The set of behaviors which change on the default hierarchy are still + * being determined and the mount option is prefixed with __DEVEL__. * - * It is allowed to temporarily drop RCU read lock during iteration. The - * caller is responsible for ensuring that @pos remains accessible until - * the start of the next iteration by, for example, bumping the css refcnt. - */ -#define css_for_each_child(pos, parent) \ - for ((pos) = css_next_child(NULL, (parent)); (pos); \ - (pos) = css_next_child((pos), (parent))) - -struct cgroup_subsys_state * -css_next_descendant_pre(struct cgroup_subsys_state *pos, - struct cgroup_subsys_state *css); - -struct cgroup_subsys_state * -css_rightmost_descendant(struct cgroup_subsys_state *pos); - -/** - * css_for_each_descendant_pre - pre-order walk of a css's descendants - * @pos: the css * to use as the loop cursor - * @root: css whose descendants to walk + * List of changed behaviors: * - * Walk @root's descendants. @root is included in the iteration and the - * first node to be visited. Must be called under rcu_read_lock(). + * - Mount options "noprefix", "xattr", "clone_children", "release_agent" + * and "name" are disallowed. * - * If a subsystem synchronizes ->css_online() and the start of iteration, a - * css which finished ->css_online() is guaranteed to be visible in the - * future iterations and will stay visible until the last reference is put. - * A css which hasn't finished ->css_online() or already finished - * ->css_offline() may show up during traversal. It's each subsystem's - * responsibility to synchronize against on/offlining. + * - When mounting an existing superblock, mount options should match. * - * For example, the following guarantees that a descendant can't escape - * state updates of its ancestors. + * - Remount is disallowed. * - * my_online(@css) - * { - * Lock @css's parent and @css; - * Inherit state from the parent; - * Unlock both. - * } + * - rename(2) is disallowed. * - * my_update_state(@css) - * { - * css_for_each_descendant_pre(@pos, @css) { - * Lock @pos; - * if (@pos == @css) - * Update @css's state; - * else - * Verify @pos is alive and inherit state from its parent; - * Unlock @pos; - * } - * } + * - "tasks" is removed. Everything should be at process granularity. Use + * "cgroup.procs" instead. * - * As long as the inheriting step, including checking the parent state, is - * enclosed inside @pos locking, double-locking the parent isn't necessary - * while inheriting. The state update to the parent is guaranteed to be - * visible by walking order and, as long as inheriting operations to the - * same @pos are atomic to each other, multiple updates racing each other - * still result in the correct state. It's guaranateed that at least one - * inheritance happens for any css after the latest update to its parent. + * - "cgroup.procs" is not sorted. pids will be unique unless they got + * recycled inbetween reads. * - * If checking parent's state requires locking the parent, each inheriting - * iteration should lock and unlock both @pos->parent and @pos. + * - "release_agent" and "notify_on_release" are removed. Replacement + * notification mechanism will be implemented. * - * Alternatively, a subsystem may choose to use a single global lock to - * synchronize ->css_online() and ->css_offline() against tree-walking - * operations. + * - "cgroup.clone_children" is removed. * - * It is allowed to temporarily drop RCU read lock during iteration. The - * caller is responsible for ensuring that @pos remains accessible until - * the start of the next iteration by, for example, bumping the css refcnt. - */ -#define css_for_each_descendant_pre(pos, css) \ - for ((pos) = css_next_descendant_pre(NULL, (css)); (pos); \ - (pos) = css_next_descendant_pre((pos), (css))) - -struct cgroup_subsys_state * -css_next_descendant_post(struct cgroup_subsys_state *pos, - struct cgroup_subsys_state *css); - -/** - * css_for_each_descendant_post - post-order walk of a css's descendants - * @pos: the css * to use as the loop cursor - * @css: css whose descendants to walk + * - "cgroup.subtree_populated" is available. Its value is 0 if the cgroup + * and its descendants contain no task; otherwise, 1. The file also + * generates kernfs notification which can be monitored through poll and + * [di]notify when the value of the file changes. * - * Similar to css_for_each_descendant_pre() but performs post-order - * traversal instead. @root is included in the iteration and the last - * node to be visited. + * - cpuset: tasks will be kept in empty cpusets when hotplug happens and + * take masks of ancestors with non-empty cpus/mems, instead of being + * moved to an ancestor. * - * If a subsystem synchronizes ->css_online() and the start of iteration, a - * css which finished ->css_online() is guaranteed to be visible in the - * future iterations and will stay visible until the last reference is put. - * A css which hasn't finished ->css_online() or already finished - * ->css_offline() may show up during traversal. It's each subsystem's - * responsibility to synchronize against on/offlining. + * - cpuset: a task can be moved into an empty cpuset, and again it takes + * masks of ancestors. * - * Note that the walk visibility guarantee example described in pre-order - * walk doesn't apply the same to post-order walks. + * - memcg: use_hierarchy is on by default and the cgroup file for the flag + * is not created. + * + * - blkcg: blk-throttle becomes properly hierarchical. + * + * - debug: disallowed on the default hierarchy. */ -#define css_for_each_descendant_post(pos, css) \ - for ((pos) = css_next_descendant_post(NULL, (css)); (pos); \ - (pos) = css_next_descendant_post((pos), (css))) +static inline bool cgroup_on_dfl(const struct cgroup *cgrp) +{ + return cgrp->root == &cgrp_dfl_root; +} -bool css_has_online_children(struct cgroup_subsys_state *css); +/* no synchronization, the result can only be used as a hint */ +static inline bool cgroup_has_tasks(struct cgroup *cgrp) +{ + return !list_empty(&cgrp->cset_links); +} -/* A css_task_iter should be treated as an opaque object */ -struct css_task_iter { - struct cgroup_subsys *ss; +/* returns ino associated with a cgroup */ +static inline ino_t cgroup_ino(struct cgroup *cgrp) +{ + return cgrp->kn->ino; +} - struct list_head *cset_pos; - struct list_head *cset_head; +/* cft/css accessors for cftype->write() operation */ +static inline struct cftype *of_cft(struct kernfs_open_file *of) +{ + return of->kn->priv; +} - struct list_head *task_pos; - struct list_head *tasks_head; - struct list_head *mg_tasks_head; -}; +struct cgroup_subsys_state *of_css(struct kernfs_open_file *of); -void css_task_iter_start(struct cgroup_subsys_state *css, - struct css_task_iter *it); -struct task_struct *css_task_iter_next(struct css_task_iter *it); -void css_task_iter_end(struct css_task_iter *it); +/* cft/css accessors for cftype->seq_*() operations */ +static inline struct cftype *seq_cft(struct seq_file *seq) +{ + return of_cft(seq->private); +} -int cgroup_attach_task_all(struct task_struct *from, struct task_struct *); -int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); +static inline struct cgroup_subsys_state *seq_css(struct seq_file *seq) +{ + return of_css(seq->private); +} -struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup, - struct cgroup_subsys *ss); -struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, - struct cgroup_subsys *ss); +/* + * Name / path handling functions. All are thin wrappers around the kernfs + * counterparts and can be called under any context. + */ -#else /* !CONFIG_CGROUPS */ +static inline int cgroup_name(struct cgroup *cgrp, char *buf, size_t buflen) +{ + return kernfs_name(cgrp->kn, buf, buflen); +} -struct cgroup_subsys_state; +static inline char * __must_check cgroup_path(struct cgroup *cgrp, char *buf, + size_t buflen) +{ + return kernfs_path(cgrp->kn, buf, buflen); +} -static inline int cgroup_init_early(void) { return 0; } -static inline int cgroup_init(void) { return 0; } -static inline void cgroup_fork(struct task_struct *p) {} -static inline void cgroup_post_fork(struct task_struct *p) {} -static inline void cgroup_exit(struct task_struct *p) {} +static inline void pr_cont_cgroup_name(struct cgroup *cgrp) +{ + pr_cont_kernfs_name(cgrp->kn); +} -static inline int cgroupstats_build(struct cgroupstats *stats, - struct dentry *dentry) +static inline void pr_cont_cgroup_path(struct cgroup *cgrp) { - return -EINVAL; + pr_cont_kernfs_path(cgrp->kn); } -static inline void css_put(struct cgroup_subsys_state *css) {} +#else /* !CONFIG_CGROUPS */ -/* No cgroups - nothing to do */ +struct cgroup_subsys_state; + +static inline void css_put(struct cgroup_subsys_state *css) {} static inline int cgroup_attach_task_all(struct task_struct *from, - struct task_struct *t) -{ - return 0; -} + struct task_struct *t) { return 0; } +static inline int cgroupstats_build(struct cgroupstats *stats, + struct dentry *dentry) { return -EINVAL; } + +static inline void cgroup_fork(struct task_struct *p) {} +static inline void cgroup_post_fork(struct task_struct *p) {} +static inline void cgroup_exit(struct task_struct *p) {} + +static inline int cgroup_init_early(void) { return 0; } +static inline int cgroup_init(void) { return 0; } #endif /* !CONFIG_CGROUPS */ diff --git a/include/linux/init_task.h b/include/linux/init_task.h index bb9b075..e8493fe 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -25,13 +25,6 @@ extern struct files_struct init_files; extern struct fs_struct init_fs; -#ifdef CONFIG_CGROUPS -#define INIT_GROUP_RWSEM(sig) \ - .group_rwsem = __RWSEM_INITIALIZER(sig.group_rwsem), -#else -#define INIT_GROUP_RWSEM(sig) -#endif - #ifdef CONFIG_CPUSETS #define INIT_CPUSET_SEQ(tsk) \ .mems_allowed_seq = SEQCNT_ZERO(tsk.mems_allowed_seq), @@ -55,7 +48,6 @@ extern struct fs_struct init_fs; }, \ .cred_guard_mutex = \ __MUTEX_INITIALIZER(sig.cred_guard_mutex), \ - INIT_GROUP_RWSEM(sig) \ } extern struct nsproxy init_nsproxy; diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h index 71ecdab..e6b2f7d 100644 --- a/include/linux/kernfs.h +++ b/include/linux/kernfs.h @@ -277,6 +277,7 @@ void kernfs_put(struct kernfs_node *kn); struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry); struct kernfs_root *kernfs_root_from_sb(struct super_block *sb); +struct inode *kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn); struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags, void *priv); @@ -352,6 +353,10 @@ static inline struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry) static inline struct kernfs_root *kernfs_root_from_sb(struct super_block *sb) { return NULL; } +static inline struct inode * +kernfs_get_inode(struct super_block *sb, struct kernfs_node *kn) +{ return NULL; } + static inline struct kernfs_root * kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags, void *priv) diff --git a/include/linux/sched.h b/include/linux/sched.h index 93ed0b6..a09ece3 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -58,6 +58,7 @@ struct sched_param { #include <linux/uidgid.h> #include <linux/gfp.h> #include <linux/magic.h> +#include <linux/cgroup-defs.h> #include <asm/processor.h> @@ -755,18 +756,6 @@ struct signal_struct { unsigned audit_tty_log_passwd; struct tty_audit_buf *tty_audit_buf; #endif -#ifdef CONFIG_CGROUPS - /* - * group_rwsem prevents new tasks from entering the threadgroup and - * member tasks from exiting,a more specifically, setting of - * PF_EXITING. fork and exit paths are protected with this rwsem - * using threadgroup_change_begin/end(). Users which require - * threadgroup to remain stable should use threadgroup_[un]lock() - * which also takes care of exec path. Currently, cgroup is the - * only user. - */ - struct rw_semaphore group_rwsem; -#endif oom_flags_t oom_flags; short oom_score_adj; /* OOM kill score adjustment */ @@ -2725,53 +2714,33 @@ static inline void unlock_task_sighand(struct task_struct *tsk, spin_unlock_irqrestore(&tsk->sighand->siglock, *flags); } -#ifdef CONFIG_CGROUPS -static inline void threadgroup_change_begin(struct task_struct *tsk) -{ - down_read(&tsk->signal->group_rwsem); -} -static inline void threadgroup_change_end(struct task_struct *tsk) -{ - up_read(&tsk->signal->group_rwsem); -} - /** - * threadgroup_lock - lock threadgroup - * @tsk: member task of the threadgroup to lock - * - * Lock the threadgroup @tsk belongs to. No new task is allowed to enter - * and member tasks aren't allowed to exit (as indicated by PF_EXITING) or - * change ->group_leader/pid. This is useful for cases where the threadgroup - * needs to stay stable across blockable operations. - * - * fork and exit paths explicitly call threadgroup_change_{begin|end}() for - * synchronization. While held, no new task will be added to threadgroup - * and no existing live task will have its PF_EXITING set. + * threadgroup_change_begin - mark the beginning of changes to a threadgroup + * @tsk: task causing the changes * - * de_thread() does threadgroup_change_{begin|end}() when a non-leader - * sub-thread becomes a new leader. + * All operations which modify a threadgroup - a new thread joining the + * group, death of a member thread (the assertion of PF_EXITING) and + * exec(2) dethreading the process and replacing the leader - are wrapped + * by threadgroup_change_{begin|end}(). This is to provide a place which + * subsystems needing threadgroup stability can hook into for + * synchronization. */ -static inline void threadgroup_lock(struct task_struct *tsk) +static inline void threadgroup_change_begin(struct task_struct *tsk) { - down_write(&tsk->signal->group_rwsem); + might_sleep(); + cgroup_threadgroup_change_begin(tsk); } /** - * threadgroup_unlock - unlock threadgroup - * @tsk: member task of the threadgroup to unlock + * threadgroup_change_end - mark the end of changes to a threadgroup + * @tsk: task causing the changes * - * Reverse threadgroup_lock(). + * See threadgroup_change_begin(). */ -static inline void threadgroup_unlock(struct task_struct *tsk) +static inline void threadgroup_change_end(struct task_struct *tsk) { - up_write(&tsk->signal->group_rwsem); + cgroup_threadgroup_change_end(tsk); } -#else -static inline void threadgroup_change_begin(struct task_struct *tsk) {} -static inline void threadgroup_change_end(struct task_struct *tsk) {} -static inline void threadgroup_lock(struct task_struct *tsk) {} -static inline void threadgroup_unlock(struct task_struct *tsk) {} -#endif #ifndef __HAVE_THREAD_FUNCTIONS diff --git a/init/Kconfig b/init/Kconfig index f0c2e68..7d1ffd2 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -924,6 +924,7 @@ config NUMA_BALANCING_DEFAULT_ENABLED menuconfig CGROUPS bool "Control Group support" select KERNFS + select PERCPU_RWSEM help This option adds support for grouping sets of processes together, for use with process control subsystems such as Cpusets, CFS, memory diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 469dd54..9ef9fc8 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -46,6 +46,7 @@ #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/rwsem.h> +#include <linux/percpu-rwsem.h> #include <linux/string.h> #include <linux/sort.h> #include <linux/kmod.h> @@ -103,6 +104,8 @@ static DEFINE_SPINLOCK(cgroup_idr_lock); */ static DEFINE_SPINLOCK(release_agent_path_lock); +struct percpu_rw_semaphore cgroup_threadgroup_rwsem; + #define cgroup_assert_mutex_or_rcu_locked() \ rcu_lockdep_assert(rcu_read_lock_held() || \ lockdep_is_held(&cgroup_mutex), \ @@ -156,7 +159,7 @@ static bool cgrp_dfl_root_visible; static bool cgroup_legacy_files_on_dfl; /* some controllers are not supported in the default hierarchy */ -static unsigned int cgrp_dfl_root_inhibit_ss_mask; +static unsigned long cgrp_dfl_root_inhibit_ss_mask; /* The list of hierarchy roots */ @@ -175,18 +178,19 @@ static DEFINE_IDR(cgroup_hierarchy_idr); */ static u64 css_serial_nr_next = 1; -/* This flag indicates whether tasks in the fork and exit paths should - * check for fork/exit handlers to call. This avoids us having to do - * extra work in the fork/exit path if none of the subsystems need to - * be called. +/* + * 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. */ -static int need_forkexit_callback __read_mostly; +static unsigned long have_fork_callback __read_mostly; +static unsigned long have_exit_callback __read_mostly; static struct cftype cgroup_dfl_base_files[]; static struct cftype cgroup_legacy_base_files[]; static int rebind_subsystems(struct cgroup_root *dst_root, - unsigned int ss_mask); + unsigned long ss_mask); static int cgroup_destroy_locked(struct cgroup *cgrp); static int create_css(struct cgroup *cgrp, struct cgroup_subsys *ss, bool visible); @@ -261,7 +265,7 @@ static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp, * @cgrp: the cgroup of interest * @ss: the subsystem of interest (%NULL returns @cgrp->self) * - * Similar to cgroup_css() but returns the effctive css, which is defined + * Similar to cgroup_css() but returns the effective css, which is defined * as the matching css of the nearest ancestor including self which has @ss * enabled. If @ss is associated with the hierarchy @cgrp is on, this * function is guaranteed to return non-NULL css. @@ -409,6 +413,24 @@ static int notify_on_release(const struct cgroup *cgrp) for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT && \ (((ss) = cgroup_subsys[ssid]) || true); (ssid)++) +/** + * for_each_subsys_which - filter for_each_subsys with a bitmask + * @ss: the iteration cursor + * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end + * @ss_maskp: a pointer to the bitmask + * + * The block will only run for cases where the ssid-th bit (1 << ssid) of + * mask is set to 1. + */ +#define for_each_subsys_which(ss, ssid, ss_maskp) \ + if (!CGROUP_SUBSYS_COUNT) /* to avoid spurious gcc warning */ \ + (ssid) = 0; \ + else \ + for_each_set_bit(ssid, ss_maskp, CGROUP_SUBSYS_COUNT) \ + if (((ss) = cgroup_subsys[ssid]) && false) \ + break; \ + else + /* iterate across the hierarchies */ #define for_each_root(root) \ list_for_each_entry((root), &cgroup_roots, root_list) @@ -882,7 +904,7 @@ static void cgroup_exit_root_id(struct cgroup_root *root) static void cgroup_free_root(struct cgroup_root *root) { if (root) { - /* hierarhcy ID shoulid already have been released */ + /* hierarchy ID should already have been released */ WARN_ON_ONCE(root->hierarchy_id); idr_destroy(&root->cgroup_idr); @@ -998,7 +1020,7 @@ static struct cgroup *task_cgroup_from_root(struct task_struct *task, * update of a tasks cgroup pointer by cgroup_attach_task() */ -static int cgroup_populate_dir(struct cgroup *cgrp, unsigned int subsys_mask); +static int cgroup_populate_dir(struct cgroup *cgrp, unsigned long subsys_mask); static struct kernfs_syscall_ops cgroup_kf_syscall_ops; static const struct file_operations proc_cgroupstats_operations; @@ -1068,11 +1090,11 @@ static void cgroup_put(struct cgroup *cgrp) * @subtree_control is to be applied to @cgrp. The returned mask is always * a superset of @subtree_control and follows the usual hierarchy rules. */ -static unsigned int cgroup_calc_child_subsys_mask(struct cgroup *cgrp, - unsigned int subtree_control) +static unsigned long cgroup_calc_child_subsys_mask(struct cgroup *cgrp, + unsigned long subtree_control) { struct cgroup *parent = cgroup_parent(cgrp); - unsigned int cur_ss_mask = subtree_control; + unsigned long cur_ss_mask = subtree_control; struct cgroup_subsys *ss; int ssid; @@ -1082,11 +1104,10 @@ static unsigned int cgroup_calc_child_subsys_mask(struct cgroup *cgrp, return cur_ss_mask; while (true) { - unsigned int new_ss_mask = cur_ss_mask; + unsigned long new_ss_mask = cur_ss_mask; - for_each_subsys(ss, ssid) - if (cur_ss_mask & (1 << ssid)) - new_ss_mask |= ss->depends_on; + for_each_subsys_which(ss, ssid, &cur_ss_mask) + new_ss_mask |= ss->depends_on; /* * Mask out subsystems which aren't available. This can @@ -1200,7 +1221,7 @@ static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft) * @cgrp: target cgroup * @subsys_mask: mask of the subsystem ids whose files should be removed */ -static void cgroup_clear_dir(struct cgroup *cgrp, unsigned int subsys_mask) +static void cgroup_clear_dir(struct cgroup *cgrp, unsigned long subsys_mask) { struct cgroup_subsys *ss; int i; @@ -1215,18 +1236,16 @@ static void cgroup_clear_dir(struct cgroup *cgrp, unsigned int subsys_mask) } } -static int rebind_subsystems(struct cgroup_root *dst_root, unsigned int ss_mask) +static int rebind_subsystems(struct cgroup_root *dst_root, + unsigned long ss_mask) { struct cgroup_subsys *ss; - unsigned int tmp_ss_mask; + unsigned long tmp_ss_mask; int ssid, i, ret; lockdep_assert_held(&cgroup_mutex); - for_each_subsys(ss, ssid) { - if (!(ss_mask & (1 << ssid))) - continue; - + for_each_subsys_which(ss, ssid, &ss_mask) { /* if @ss has non-root csses attached to it, can't move */ if (css_next_child(NULL, cgroup_css(&ss->root->cgrp, ss))) return -EBUSY; @@ -1253,7 +1272,7 @@ static int rebind_subsystems(struct cgroup_root *dst_root, unsigned int ss_mask) * Just warn about it and continue. */ if (cgrp_dfl_root_visible) { - pr_warn("failed to create files (%d) while rebinding 0x%x to default root\n", + pr_warn("failed to create files (%d) while rebinding 0x%lx to default root\n", ret, ss_mask); pr_warn("you may retry by moving them to a different hierarchy and unbinding\n"); } @@ -1263,18 +1282,14 @@ static int rebind_subsystems(struct cgroup_root *dst_root, unsigned int ss_mask) * Nothing can fail from this point on. Remove files for the * removed subsystems and rebind each subsystem. */ - for_each_subsys(ss, ssid) - if (ss_mask & (1 << ssid)) - cgroup_clear_dir(&ss->root->cgrp, 1 << ssid); + for_each_subsys_which(ss, ssid, &ss_mask) + cgroup_clear_dir(&ss->root->cgrp, 1 << ssid); - for_each_subsys(ss, ssid) { + for_each_subsys_which(ss, ssid, &ss_mask) { struct cgroup_root *src_root; struct cgroup_subsys_state *css; struct css_set *cset; - if (!(ss_mask & (1 << ssid))) - continue; - src_root = ss->root; css = cgroup_css(&src_root->cgrp, ss); @@ -1338,7 +1353,7 @@ static int cgroup_show_options(struct seq_file *seq, } struct cgroup_sb_opts { - unsigned int subsys_mask; + unsigned long subsys_mask; unsigned int flags; char *release_agent; bool cpuset_clone_children; @@ -1351,7 +1366,7 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) { char *token, *o = data; bool all_ss = false, one_ss = false; - unsigned int mask = -1U; + unsigned long mask = -1UL; struct cgroup_subsys *ss; int nr_opts = 0; int i; @@ -1495,7 +1510,7 @@ 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; - unsigned int added_mask, removed_mask; + unsigned long added_mask, removed_mask; if (root == &cgrp_dfl_root) { pr_err("remount is not allowed\n"); @@ -1641,7 +1656,7 @@ 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, unsigned int ss_mask) +static int cgroup_setup_root(struct cgroup_root *root, unsigned long ss_mask) { LIST_HEAD(tmp_links); struct cgroup *root_cgrp = &root->cgrp; @@ -2052,9 +2067,9 @@ static void cgroup_task_migrate(struct cgroup *old_cgrp, lockdep_assert_held(&css_set_rwsem); /* - * We are synchronized through threadgroup_lock() against PF_EXITING - * setting such that we can't race against cgroup_exit() changing the - * css_set to init_css_set and dropping the old one. + * We are synchronized through cgroup_threadgroup_rwsem against + * PF_EXITING setting such that we can't race against cgroup_exit() + * changing the css_set to init_css_set and dropping the old one. */ WARN_ON_ONCE(tsk->flags & PF_EXITING); old_cset = task_css_set(tsk); @@ -2111,10 +2126,11 @@ static void cgroup_migrate_finish(struct list_head *preloaded_csets) * @src_cset and add it to @preloaded_csets, which should later be cleaned * up by cgroup_migrate_finish(). * - * This function may be called without holding threadgroup_lock even if the - * target is a process. Threads may be created and destroyed but as long - * as cgroup_mutex is not dropped, no new css_set can be put into play and - * the preloaded css_sets are guaranteed to cover all migrations. + * This function may be called without holding cgroup_threadgroup_rwsem + * even if the target is a process. Threads may be created and destroyed + * but as long as cgroup_mutex is not dropped, no new css_set can be put + * 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, @@ -2217,7 +2233,7 @@ err: * @threadgroup: whether @leader points to the whole process or a single task * * Migrate a process or task denoted by @leader to @cgrp. If migrating a - * process, the caller must be holding threadgroup_lock of @leader. The + * process, the caller must be holding cgroup_threadgroup_rwsem. The * caller is also responsible for invoking cgroup_migrate_add_src() and * cgroup_migrate_prepare_dst() on the targets before invoking this * function and following up with cgroup_migrate_finish(). @@ -2345,7 +2361,7 @@ out_release_tset: * @leader: the task or the leader of the threadgroup to be attached * @threadgroup: attach the whole threadgroup? * - * Call holding cgroup_mutex and threadgroup_lock of @leader. + * Call holding cgroup_mutex and cgroup_threadgroup_rwsem. */ static int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader, bool threadgroup) @@ -2376,6 +2392,47 @@ static int cgroup_attach_task(struct cgroup *dst_cgrp, return ret; } +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)) { + struct super_block *sb = of->file->f_path.dentry->d_sb; + struct cgroup *cgrp; + struct inode *inode; + + down_read(&css_set_rwsem); + cgrp = task_cgroup_from_root(task, &cgrp_dfl_root); + up_read(&css_set_rwsem); + + while (!cgroup_is_descendant(dst_cgrp, cgrp)) + cgrp = cgroup_parent(cgrp); + + ret = -ENOMEM; + inode = kernfs_get_inode(sb, cgrp->procs_kn); + if (inode) { + ret = inode_permission(inode, MAY_WRITE); + iput(inode); + } + } + + put_cred(tcred); + return ret; +} + /* * Find the task_struct of the task to attach by vpid and pass it along to the * function to attach either it or all tasks in its threadgroup. Will lock @@ -2385,7 +2442,6 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off, bool threadgroup) { struct task_struct *tsk; - const struct cred *cred = current_cred(), *tcred; struct cgroup *cgrp; pid_t pid; int ret; @@ -2397,29 +2453,17 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, if (!cgrp) return -ENODEV; -retry_find_task: + percpu_down_write(&cgroup_threadgroup_rwsem); rcu_read_lock(); if (pid) { tsk = find_task_by_vpid(pid); if (!tsk) { - rcu_read_unlock(); ret = -ESRCH; - goto out_unlock_cgroup; + goto out_unlock_rcu; } - /* - * even if we're attaching all tasks in the thread group, we - * only need to check permissions on one of them. - */ - tcred = __task_cred(tsk); - if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) && - !uid_eq(cred->euid, tcred->uid) && - !uid_eq(cred->euid, tcred->suid)) { - rcu_read_unlock(); - ret = -EACCES; - goto out_unlock_cgroup; - } - } else + } else { tsk = current; + } if (threadgroup) tsk = tsk->group_leader; @@ -2431,35 +2475,23 @@ retry_find_task: */ if (tsk == kthreadd_task || (tsk->flags & PF_NO_SETAFFINITY)) { ret = -EINVAL; - rcu_read_unlock(); - goto out_unlock_cgroup; + goto out_unlock_rcu; } get_task_struct(tsk); rcu_read_unlock(); - threadgroup_lock(tsk); - if (threadgroup) { - if (!thread_group_leader(tsk)) { - /* - * a race with de_thread from another thread's exec() - * may strip us of our leadership, if this happens, - * there is no choice but to throw this task away and - * try again; this is - * "double-double-toil-and-trouble-check locking". - */ - threadgroup_unlock(tsk); - put_task_struct(tsk); - goto retry_find_task; - } - } - - ret = cgroup_attach_task(cgrp, tsk, threadgroup); - - threadgroup_unlock(tsk); + ret = cgroup_procs_write_permission(tsk, cgrp, of); + if (!ret) + ret = cgroup_attach_task(cgrp, tsk, threadgroup); put_task_struct(tsk); -out_unlock_cgroup: + goto out_unlock_threadgroup; + +out_unlock_rcu: + rcu_read_unlock(); +out_unlock_threadgroup: + percpu_up_write(&cgroup_threadgroup_rwsem); cgroup_kn_unlock(of->kn); return ret ?: nbytes; } @@ -2542,19 +2574,17 @@ static int cgroup_sane_behavior_show(struct seq_file *seq, void *v) return 0; } -static void cgroup_print_ss_mask(struct seq_file *seq, unsigned int ss_mask) +static void cgroup_print_ss_mask(struct seq_file *seq, unsigned long ss_mask) { struct cgroup_subsys *ss; bool printed = false; int ssid; - for_each_subsys(ss, ssid) { - if (ss_mask & (1 << ssid)) { - if (printed) - seq_putc(seq, ' '); - seq_printf(seq, "%s", ss->name); - printed = true; - } + for_each_subsys_which(ss, ssid, &ss_mask) { + if (printed) + seq_putc(seq, ' '); + seq_printf(seq, "%s", ss->name); + printed = true; } if (printed) seq_putc(seq, '\n'); @@ -2606,6 +2636,8 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) lockdep_assert_held(&cgroup_mutex); + percpu_down_write(&cgroup_threadgroup_rwsem); + /* look up all csses currently attached to @cgrp's subtree */ down_read(&css_set_rwsem); css_for_each_descendant_pre(css, cgroup_css(cgrp, NULL)) { @@ -2661,17 +2693,8 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) goto out_finish; last_task = task; - threadgroup_lock(task); - /* raced against de_thread() from another thread? */ - if (!thread_group_leader(task)) { - threadgroup_unlock(task); - put_task_struct(task); - continue; - } - ret = cgroup_migrate(src_cset->dfl_cgrp, task, true); - threadgroup_unlock(task); put_task_struct(task); if (WARN(ret, "cgroup: failed to update controllers for the default hierarchy (%d), further operations may crash or hang\n", ret)) @@ -2681,6 +2704,7 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) out_finish: cgroup_migrate_finish(&preloaded_csets); + percpu_up_write(&cgroup_threadgroup_rwsem); return ret; } @@ -2689,8 +2713,8 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { - unsigned int enable = 0, disable = 0; - unsigned int css_enable, css_disable, old_sc, new_sc, old_ss, new_ss; + unsigned long enable = 0, disable = 0; + unsigned long css_enable, css_disable, old_sc, new_sc, old_ss, new_ss; struct cgroup *cgrp, *child; struct cgroup_subsys *ss; char *tok; @@ -2702,11 +2726,12 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, */ buf = strstrip(buf); while ((tok = strsep(&buf, " "))) { + unsigned long tmp_ss_mask = ~cgrp_dfl_root_inhibit_ss_mask; + if (tok[0] == '\0') continue; - for_each_subsys(ss, ssid) { - if (ss->disabled || strcmp(tok + 1, ss->name) || - ((1 << ss->id) & cgrp_dfl_root_inhibit_ss_mask)) + for_each_subsys_which(ss, ssid, &tmp_ss_mask) { + if (ss->disabled || strcmp(tok + 1, ss->name)) continue; if (*tok == '+') { @@ -2793,10 +2818,7 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, * still around. In such cases, wait till it's gone using * offline_waitq. */ - for_each_subsys(ss, ssid) { - if (!(css_enable & (1 << ssid))) - continue; - + for_each_subsys_which(ss, ssid, &css_enable) { cgroup_for_each_live_child(child, cgrp) { DEFINE_WAIT(wait); @@ -3087,7 +3109,9 @@ static int cgroup_add_file(struct cgroup *cgrp, struct cftype *cft) return ret; } - if (cft->seq_show == cgroup_populated_show) + if (cft->write == cgroup_procs_write) + cgrp->procs_kn = kn; + else if (cft->seq_show == cgroup_populated_show) cgrp->populated_kn = kn; return 0; } @@ -4322,7 +4346,7 @@ static struct cftype cgroup_legacy_base_files[] = { * * On failure, no file is added. */ -static int cgroup_populate_dir(struct cgroup *cgrp, unsigned int subsys_mask) +static int cgroup_populate_dir(struct cgroup *cgrp, unsigned long subsys_mask) { struct cgroup_subsys *ss; int i, ret = 0; @@ -4931,7 +4955,8 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early) * init_css_set is in the subsystem's root cgroup. */ init_css_set.subsys[ss->id] = css; - need_forkexit_callback |= ss->fork || ss->exit; + have_fork_callback |= (bool)ss->fork << ss->id; + have_exit_callback |= (bool)ss->exit << ss->id; /* At system boot, before all subsystems have been * registered, no tasks have been forked, so we don't @@ -4989,6 +5014,7 @@ int __init cgroup_init(void) unsigned long key; int ssid, err; + 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)); @@ -5241,11 +5267,8 @@ void cgroup_post_fork(struct task_struct *child) * css_set; otherwise, @child might change state between ->fork() * and addition to css_set. */ - if (need_forkexit_callback) { - for_each_subsys(ss, i) - if (ss->fork) - ss->fork(child); - } + for_each_subsys_which(ss, i, &have_fork_callback) + ss->fork(child); } /** @@ -5289,16 +5312,12 @@ void cgroup_exit(struct task_struct *tsk) cset = task_css_set(tsk); RCU_INIT_POINTER(tsk->cgroups, &init_css_set); - if (need_forkexit_callback) { - /* see cgroup_post_fork() for details */ - for_each_subsys(ss, i) { - if (ss->exit) { - struct cgroup_subsys_state *old_css = cset->subsys[i]; - struct cgroup_subsys_state *css = task_css(tsk, i); + /* see cgroup_post_fork() for details */ + for_each_subsys_which(ss, i, &have_exit_callback) { + struct cgroup_subsys_state *old_css = cset->subsys[i]; + struct cgroup_subsys_state *css = task_css(tsk, i); - ss->exit(css, old_css, tsk); - } - } + ss->exit(css, old_css, tsk); } if (put_cset) diff --git a/kernel/fork.c b/kernel/fork.c index 4c95cb3..1bfefc6 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1141,10 +1141,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) tty_audit_fork(sig); sched_autogroup_fork(sig); -#ifdef CONFIG_CGROUPS - init_rwsem(&sig->group_rwsem); -#endif - sig->oom_score_adj = current->signal->oom_score_adj; sig->oom_score_adj_min = current->signal->oom_score_adj_min; |
