linux-stable/kernel/cgroup/cgroup-internal.h

223 lines
6.8 KiB
C
Raw Normal View History

#ifndef __CGROUP_INTERNAL_H
#define __CGROUP_INTERNAL_H
#include <linux/cgroup.h>
#include <linux/kernfs.h>
#include <linux/workqueue.h>
#include <linux/list.h>
#include <linux/refcount.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;
cgroup: don't call migration methods if there are no tasks to migrate Subsystem migration methods shouldn't be called for empty migrations. cgroup_migrate_execute() implements this guarantee by bailing early if there are no source css_sets. This used to be correct before a79a908fd2b0 ("cgroup: introduce cgroup namespaces"), but no longer since the commit because css_sets can stay pinned without tasks in them. This caused cgroup_migrate_execute() call into cpuset migration methods with an empty cgroup_taskset. cpuset migration methods correctly assume that cgroup_taskset_first() never returns NULL; however, due to the bug, it can, leading to the following oops. Unable to handle kernel paging request for data at address 0x00000960 Faulting instruction address: 0xc0000000001d6868 Oops: Kernel access of bad area, sig: 11 [#1] ... CPU: 14 PID: 16947 Comm: kworker/14:0 Tainted: G W 4.12.0-rc4-next-20170609 #2 Workqueue: events cpuset_hotplug_workfn task: c00000000ca60580 task.stack: c00000000c728000 NIP: c0000000001d6868 LR: c0000000001d6858 CTR: c0000000001d6810 REGS: c00000000c72b720 TRAP: 0300 Tainted: GW (4.12.0-rc4-next-20170609) MSR: 8000000000009033 <SF,EE,ME,IR,DR,RI,LE> CR: 44722422 XER: 20000000 CFAR: c000000000008710 DAR: 0000000000000960 DSISR: 40000000 SOFTE: 1 GPR00: c0000000001d6858 c00000000c72b9a0 c000000001536e00 0000000000000000 GPR04: c00000000c72b9c0 0000000000000000 c00000000c72bad0 c000000766367678 GPR08: c000000766366d10 c00000000c72b958 c000000001736e00 0000000000000000 GPR12: c0000000001d6810 c00000000e749300 c000000000123ef8 c000000775af4180 GPR16: 0000000000000000 0000000000000000 c00000075480e9c0 c00000075480e9e0 GPR20: c00000075480e8c0 0000000000000001 0000000000000000 c00000000c72ba20 GPR24: c00000000c72baa0 c00000000c72bac0 c000000001407248 c00000000c72ba20 GPR28: c00000000141fc80 c00000000c72bac0 c00000000c6bc790 0000000000000000 NIP [c0000000001d6868] cpuset_can_attach+0x58/0x1b0 LR [c0000000001d6858] cpuset_can_attach+0x48/0x1b0 Call Trace: [c00000000c72b9a0] [c0000000001d6858] cpuset_can_attach+0x48/0x1b0 (unreliable) [c00000000c72ba00] [c0000000001cbe80] cgroup_migrate_execute+0xb0/0x450 [c00000000c72ba80] [c0000000001d3754] cgroup_transfer_tasks+0x1c4/0x360 [c00000000c72bba0] [c0000000001d923c] cpuset_hotplug_workfn+0x86c/0xa20 [c00000000c72bca0] [c00000000011aa44] process_one_work+0x1e4/0x580 [c00000000c72bd30] [c00000000011ae78] worker_thread+0x98/0x5c0 [c00000000c72bdc0] [c000000000124058] kthread+0x168/0x1b0 [c00000000c72be30] [c00000000000b2e8] ret_from_kernel_thread+0x5c/0x74 Instruction dump: f821ffa1 7c7d1b78 60000000 60000000 38810020 7fa3eb78 3f42ffed 4bff4c25 60000000 3b5a0448 3d420020 eb610020 <e9230960> 7f43d378 e9290000 f92af200 ---[ end trace dcaaf98fb36d9e64 ]--- This patch fixes the bug by adding an explicit nr_tasks counter to cgroup_taskset and skipping calling the migration methods if the counter is zero. While at it, remove the now spurious check on no source css_sets. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-and-tested-by: Abdul Haleem <abdhalee@linux.vnet.ibm.com> Cc: Roman Gushchin <guro@fb.com> Cc: stable@vger.kernel.org # v4.6+ Fixes: a79a908fd2b0 ("cgroup: introduce cgroup namespaces") Link: http://lkml.kernel.org/r/1497266622.15415.39.camel@abdul.in.ibm.com
2017-07-08 11:17:02 +00:00
/* the number of tasks in the set */
int nr_tasks;
/* 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 (refcount_dec_not_one(&cset->refcount))
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)
{
refcount_inc(&cset->refcount);
}
bool cgroup_ssid_enabled(int ssid);
bool cgroup_on_dfl(const struct cgroup *cgrp);
bool cgroup_is_thread_root(struct cgroup *cgrp);
bool cgroup_is_threaded(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 ref_flags);
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);
cgroup: implement cgroup v2 thread support This patch implements cgroup v2 thread support. The goal of the thread mode is supporting hierarchical accounting and control at thread granularity while staying inside the resource domain model which allows coordination across different resource controllers and handling of anonymous resource consumptions. A cgroup is always created as a domain and can be made threaded by writing to the "cgroup.type" file. When a cgroup becomes threaded, it becomes a member of a threaded subtree which is anchored at the closest ancestor which isn't threaded. The threads of the processes which are in a threaded subtree can be placed anywhere without being restricted by process granularity or no-internal-process constraint. Note that the threads aren't allowed to escape to a different threaded subtree. To be used inside a threaded subtree, a controller should explicitly support threaded mode and be able to handle internal competition in the way which is appropriate for the resource. The root of a threaded subtree, the nearest ancestor which isn't threaded, is called the threaded domain and serves as the resource domain for the whole subtree. This is the last cgroup where domain controllers are operational and where all the domain-level resource consumptions in the subtree are accounted. This allows threaded controllers to operate at thread granularity when requested while staying inside the scope of system-level resource distribution. As the root cgroup is exempt from the no-internal-process constraint, it can serve as both a threaded domain and a parent to normal cgroups, so, unlike non-root cgroups, the root cgroup can have both domain and threaded children. Internally, in a threaded subtree, each css_set has its ->dom_cset pointing to a matching css_set which belongs to the threaded domain. This ensures that thread root level cgroup_subsys_state for all threaded controllers are readily accessible for domain-level operations. This patch enables threaded mode for the pids and perf_events controllers. Neither has to worry about domain-level resource consumptions and it's enough to simply set the flag. For more details on the interface and behavior of the thread mode, please refer to the section 2-2-2 in Documentation/cgroup-v2.txt added by this patch. v5: - Dropped silly no-op ->dom_cgrp init from cgroup_create(). Spotted by Waiman. - Documentation updated as suggested by Waiman. - cgroup.type content slightly reformatted. - Mark the debug controller threaded. v4: - Updated to the general idea of marking specific cgroups domain/threaded as suggested by PeterZ. v3: - Dropped "join" and always make mixed children join the parent's threaded subtree. v2: - After discussions with Waiman, support for mixed thread mode is added. This should address the issue that Peter pointed out where any nesting should be avoided for thread subtrees while coexisting with other domain cgroups. - Enabling / disabling thread mode now piggy backs on the existing control mask update mechanism. - Bug fixes and cleanup. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Waiman Long <longman@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org>
2017-07-21 15:14:51 +00:00
int cgroup_migrate_vet_dst(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);
struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup)
__acquires(&cgroup_threadgroup_rwsem);
void cgroup_procs_write_finish(struct task_struct *task)
__releases(&cgroup_threadgroup_rwsem);
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);
int cgroup_task_count(const struct cgroup *cgrp);
/*
* 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 */