cregit-Linux how code gets into the kernel

Release 4.7 kernel/cgroup.c

Directory: kernel
/*
 *  Generic process-grouping system.
 *
 *  Based originally on the cpuset system, extracted by Paul Menage
 *  Copyright (C) 2006 Google, Inc
 *
 *  Notifications support
 *  Copyright (C) 2009 Nokia Corporation
 *  Author: Kirill A. Shutemov
 *
 *  Copyright notices from the original cpuset code:
 *  --------------------------------------------------
 *  Copyright (C) 2003 BULL SA.
 *  Copyright (C) 2004-2006 Silicon Graphics, Inc.
 *
 *  Portions derived from Patrick Mochel's sysfs code.
 *  sysfs is Copyright (c) 2001-3 Patrick Mochel
 *
 *  2003-10-10 Written by Simon Derr.
 *  2003-10-22 Updates by Stephen Hemminger.
 *  2004 May-July Rework by Paul Jackson.
 *  ---------------------------------------------------
 *
 *  This file is subject to the terms and conditions of the GNU General Public
 *  License.  See the file COPYING in the main directory of the Linux
 *  distribution for more details.
 */


#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/cgroup.h>
#include <linux/cred.h>
#include <linux/ctype.h>
#include <linux/errno.h>
#include <linux/init_task.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/magic.h>
#include <linux/mm.h>
#include <linux/mutex.h>
#include <linux/mount.h>
#include <linux/pagemap.h>
#include <linux/proc_fs.h>
#include <linux/rcupdate.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/percpu-rwsem.h>
#include <linux/string.h>
#include <linux/sort.h>
#include <linux/kmod.h>
#include <linux/delayacct.h>
#include <linux/cgroupstats.h>
#include <linux/hashtable.h>
#include <linux/pid_namespace.h>
#include <linux/idr.h>
#include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
#include <linux/kthread.h>
#include <linux/delay.h>
#include <linux/atomic.h>
#include <linux/cpuset.h>
#include <linux/proc_ns.h>
#include <linux/nsproxy.h>
#include <linux/proc_ns.h>
#include <net/sock.h>

/*
 * pidlists linger the following amount before being destroyed.  The goal
 * is avoiding frequent destruction in the middle of consecutive read calls
 * Expiring in the middle is a performance problem not a correctness one.
 * 1 sec should be enough.
 */

#define CGROUP_PIDLIST_DESTROY_DELAY	HZ


#define CGROUP_FILE_NAME_MAX		(MAX_CGROUP_TYPE_NAMELEN +      \
                                         MAX_CFTYPE_NAME + 2)

/*
 * cgroup_mutex is the master lock.  Any modification to cgroup or its
 * hierarchy must be performed while holding it.
 *
 * css_set_lock protects task->cgroups pointer, the list of css_set
 * objects, and the chain of tasks off each css_set.
 *
 * These locks are exported if CONFIG_PROVE_RCU so that accessors in
 * cgroup.h can use them for lockdep annotations.
 */
#ifdef CONFIG_PROVE_RCU

DEFINE_MUTEX(cgroup_mutex);

DEFINE_SPINLOCK(css_set_lock);

EXPORT_SYMBOL_GPL(cgroup_mutex);

EXPORT_SYMBOL_GPL(css_set_lock);
#else
static DEFINE_MUTEX(cgroup_mutex);
static DEFINE_SPINLOCK(css_set_lock);
#endif

/*
 * Protects cgroup_idr and css_idr so that IDs can be released without
 * grabbing cgroup_mutex.
 */
static DEFINE_SPINLOCK(cgroup_idr_lock);

/*
 * Protects cgroup_file->kn for !self csses.  It synchronizes notifications
 * against file removal/re-creation across css hiding.
 */
static DEFINE_SPINLOCK(cgroup_file_kn_lock);

/*
 * Protects cgroup_subsys->release_agent_path.  Modifying it also requires
 * cgroup_mutex.  Reading requires either cgroup_mutex or this spinlock.
 */
static DEFINE_SPINLOCK(release_agent_path_lock);


struct percpu_rw_semaphore cgroup_threadgroup_rwsem;


#define cgroup_assert_mutex_or_rcu_locked()				\
	RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&                       \
                           !lockdep_is_held(&cgroup_mutex),             \
                           "cgroup_mutex or RCU read lock required");

/*
 * cgroup destruction makes heavy use of work items and there can be a lot
 * of concurrent destructions.  Use a separate workqueue so that cgroup
 * destruction work items don't end up filling up max_active of system_wq
 * which may lead to deadlock.
 */

static struct workqueue_struct *cgroup_destroy_wq;

/*
 * pidlist destructions need to be flushed on cgroup destruction.  Use a
 * separate workqueue as flush domain.
 */

static struct workqueue_struct *cgroup_pidlist_destroy_wq;

/* generate an array of cgroup subsystem pointers */

#define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys,

static struct cgroup_subsys *cgroup_subsys[] = {
#include <linux/cgroup_subsys.h>
};

#undef SUBSYS

/* array of cgroup subsystem names */

#define SUBSYS(_x) [_x ## _cgrp_id] = #_x,

static const char *cgroup_subsys_name[] = {
#include <linux/cgroup_subsys.h>
};

#undef SUBSYS

/* array of static_keys for cgroup_subsys_enabled() and cgroup_subsys_on_dfl() */

#define SUBSYS(_x)								\
	DEFINE_STATIC_KEY_TRUE(_x ## _cgrp_subsys_enabled_key);                 \
        DEFINE_STATIC_KEY_TRUE(_x ## _cgrp_subsys_on_dfl_key);                  \
        EXPORT_SYMBOL_GPL(_x ## _cgrp_subsys_enabled_key);                      \
        EXPORT_SYMBOL_GPL(_x ## _cgrp_subsys_on_dfl_key);
#include <linux/cgroup_subsys.h>

#undef SUBSYS


#define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys_enabled_key,

static struct static_key_true *cgroup_subsys_enabled_key[] = {
#include <linux/cgroup_subsys.h>
};

#undef SUBSYS


#define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys_on_dfl_key,

static struct static_key_true *cgroup_subsys_on_dfl_key[] = {
#include <linux/cgroup_subsys.h>
};

#undef SUBSYS

/*
 * The default hierarchy, reserved for the subsystems that are otherwise
 * unattached - it never has more than a single cgroup, and all tasks are
 * part of that cgroup.
 */

struct cgroup_root cgrp_dfl_root;

EXPORT_SYMBOL_GPL(cgrp_dfl_root);

/*
 * The default hierarchy always exists but is hidden until mounted for the
 * first time.  This is for backward compatibility.
 */

static bool cgrp_dfl_visible;

/* Controllers blocked by the commandline in v1 */

static u16 cgroup_no_v1_mask;

/* some controllers are not supported in the default hierarchy */

static u16 cgrp_dfl_inhibit_ss_mask;

/* some controllers are implicitly enabled on the default hierarchy */

static unsigned long cgrp_dfl_implicit_ss_mask;

/* The list of hierarchy roots */

static LIST_HEAD(cgroup_roots);

static int cgroup_root_count;

/* hierarchy ID allocation and mapping, protected by cgroup_mutex */
static DEFINE_IDR(cgroup_hierarchy_idr);

/*
 * Assign a monotonically increasing serial number to csses.  It guarantees
 * cgroups with bigger numbers are newer than those with smaller numbers.
 * Also, as csses are always appended to the parent's ->children list, it
 * guarantees that sibling csses are always sorted in the ascending serial
 * number order on the list.  Protected by cgroup_mutex.
 */

static u64 css_serial_nr_next = 1;

/*
 * These bitmask flags indicate whether tasks in the fork and exit paths have
 * fork/exit handlers to call. This avoids us having to do extra work in the
 * fork/exit path to check which subsystems have fork/exit callbacks.
 */

static u16 have_fork_callback __read_mostly;

static u16 have_exit_callback __read_mostly;

static u16 have_free_callback __read_mostly;

/* cgroup namespace for init task */

struct cgroup_namespace init_cgroup_ns = {
	.count		= { .counter = 2, },
	.user_ns	= &init_user_ns,
	.ns.ops		= &cgroupns_operations,
	.ns.inum	= PROC_CGROUP_INIT_INO,
	.root_cset	= &init_css_set,
};

/* Ditto for the can_fork callback. */

static u16 have_canfork_callback __read_mostly;


static struct file_system_type cgroup2_fs_type;

static struct cftype cgroup_dfl_base_files[];

static struct cftype cgroup_legacy_base_files[];

static int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask);
static void cgroup_lock_and_drain_offline(struct cgroup *cgrp);
static int cgroup_apply_control(struct cgroup *cgrp);
static void cgroup_finalize_control(struct cgroup *cgrp, int ret);
static void css_task_iter_advance(struct css_task_iter *it);
static int cgroup_destroy_locked(struct cgroup *cgrp);
static struct cgroup_subsys_state *css_create(struct cgroup *cgrp,
					      struct cgroup_subsys *ss);
static void css_release(struct percpu_ref *ref);
static void kill_css(struct cgroup_subsys_state *css);
static int cgroup_addrm_files(struct cgroup_subsys_state *css,
			      struct cgroup *cgrp, struct cftype cfts[],
			      bool is_add);

/**
 * cgroup_ssid_enabled - cgroup subsys enabled test by subsys ID
 * @ssid: subsys ID of interest
 *
 * cgroup_subsys_enabled() can only be used with literal subsys names which
 * is fine for individual subsystems but unsuitable for cgroup core.  This
 * is slower static_key_enabled() based test indexed by @ssid.
 */

static bool cgroup_ssid_enabled(int ssid) { if (CGROUP_SUBSYS_COUNT == 0) return false; return static_key_enabled(cgroup_subsys_enabled_key[ssid]); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo1866.67%150.00%
arnd bergmannarnd bergmann933.33%150.00%
Total27100.00%2100.00%


static bool cgroup_ssid_no_v1(int ssid) { return cgroup_no_v1_mask & (1 << ssid); }

Contributors

PersonTokensPropCommitsCommitProp
johannes weinerjohannes weiner18100.00%1100.00%
Total18100.00%1100.00%

/** * 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 bool cgroup_on_dfl(const struct cgroup *cgrp) { return cgrp->root == &cgrp_dfl_root; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo20100.00%1100.00%
Total20100.00%1100.00%

/* IDR wrappers which synchronize using cgroup_idr_lock */
static int cgroup_idr_alloc(struct idr *idr, void *ptr, int start, int end, gfp_t gfp_mask) { int ret; idr_preload(gfp_mask); spin_lock_bh(&cgroup_idr_lock); ret = idr_alloc(idr, ptr, start, end, gfp_mask & ~__GFP_DIRECT_RECLAIM); spin_unlock_bh(&cgroup_idr_lock); idr_preload_end(); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo6595.59%250.00%
vladimir davydovvladimir davydov22.94%125.00%
mel gormanmel gorman11.47%125.00%
Total68100.00%4100.00%


static void *cgroup_idr_replace(struct idr *idr, void *ptr, int id) { void *ret; spin_lock_bh(&cgroup_idr_lock); ret = idr_replace(idr, ptr, id); spin_unlock_bh(&cgroup_idr_lock); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo49100.00%2100.00%
Total49100.00%2100.00%


static void cgroup_idr_remove(struct idr *idr, int id) { spin_lock_bh(&cgroup_idr_lock); idr_remove(idr, id); spin_unlock_bh(&cgroup_idr_lock); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo33100.00%2100.00%
Total33100.00%2100.00%


static struct cgroup *cgroup_parent(struct cgroup *cgrp) { struct cgroup_subsys_state *parent_css = cgrp->self.parent; if (parent_css) return container_of(parent_css, struct cgroup, self); return NULL; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo42100.00%1100.00%
Total42100.00%1100.00%

/* subsystems visibly enabled on a cgroup */
static u16 cgroup_control(struct cgroup *cgrp) { struct cgroup *parent = cgroup_parent(cgrp); u16 root_ss_mask = cgrp->root->subsys_mask; if (parent) return parent->subtree_control; if (cgroup_on_dfl(cgrp)) root_ss_mask &= ~(cgrp_dfl_inhibit_ss_mask | cgrp_dfl_implicit_ss_mask); return root_ss_mask; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo58100.00%2100.00%
Total58100.00%2100.00%

/* subsystems enabled on a cgroup */
static u16 cgroup_ss_mask(struct cgroup *cgrp) { struct cgroup *parent = cgroup_parent(cgrp); if (parent) return parent->subtree_ss_mask; return cgrp->root->subsys_mask; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo37100.00%1100.00%
Total37100.00%1100.00%

/** * cgroup_css - obtain a cgroup's css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest (%NULL returns @cgrp->self) * * Return @cgrp's css (cgroup_subsys_state) associated with @ss. This * function must be called either under cgroup_mutex or rcu_read_lock() and * the caller is responsible for pinning the returned css if it wants to * keep accessing it outside the said locks. This function may return * %NULL if @cgrp doesn't have @subsys_id enabled. */
static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp, struct cgroup_subsys *ss) { if (ss) return rcu_dereference_check(cgrp->subsys[ss->id], lockdep_is_held(&cgroup_mutex)); else return &cgrp->self; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo48100.00%5100.00%
Total48100.00%5100.00%

/** * cgroup_e_css - obtain a cgroup's effective css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest (%NULL returns @cgrp->self) * * 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. */
static struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp, struct cgroup_subsys *ss) { lockdep_assert_held(&cgroup_mutex); if (!ss) return &cgrp->self; /* * This function is used while updating css associations and thus * can't test the csses directly. Test ss_mask. */ while (!(cgroup_ss_mask(cgrp) & (1 << ss->id))) { cgrp = cgroup_parent(cgrp); if (!cgrp) return NULL; } return cgroup_css(cgrp, ss); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo6784.81%571.43%
paul menagepaul menage1215.19%228.57%
Total79100.00%7100.00%

/** * cgroup_get_e_css - get a cgroup's effective css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest * * Find and get the effective css of @cgrp for @ss. The effective css is * defined as the matching css of the nearest ancestor including self which * has @ss enabled. If @ss is not mounted on the hierarchy @cgrp is on, * the root css is returned, so this function always returns a valid css. * The returned css must be put using css_put(). */
struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgrp, struct cgroup_subsys *ss) { struct cgroup_subsys_state *css; rcu_read_lock(); do { css = cgroup_css(cgrp, ss); if (css && css_tryget_online(css)) goto out_unlock; cgrp = cgroup_parent(cgrp); } while (cgrp); css = init_css_set.subsys[ss->id]; css_get(css); out_unlock: rcu_read_unlock(); return css; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo85100.00%1100.00%
Total85100.00%1100.00%

/* convenient tests for these bits */
static inline bool cgroup_is_dead(const struct cgroup *cgrp) { return !(cgrp->self.flags & CSS_ONLINE); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo1144.00%457.14%
paul menagepaul menage1144.00%228.57%
li zefanli zefan312.00%114.29%
Total25100.00%7100.00%


static void cgroup_get(struct cgroup *cgrp) { WARN_ON_ONCE(cgroup_is_dead(cgrp)); css_get(&cgrp->self); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo27100.00%1100.00%
Total27100.00%1100.00%


static bool cgroup_tryget(struct cgroup *cgrp) { return css_tryget(&cgrp->self); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo20100.00%1100.00%
Total20100.00%1100.00%


struct cgroup_subsys_state *of_css(struct kernfs_open_file *of) { struct cgroup *cgrp = of->kn->parent->priv; struct cftype *cft = of_cft(of); /* * This is open and unprotected implementation of cgroup_css(). * seq_css() is only called from a kernfs file operation which has * an active reference on the file. Because all the subsystem * files are drained before a css is disassociated with a cgroup, * the matching css from the cgroup's subsys table is guaranteed to * be and stay valid until the enclosing operation is complete. */ if (cft->ss) return rcu_dereference_raw(cgrp->subsys[cft->ss->id]); else return &cgrp->self; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo5382.81%480.00%
li zefanli zefan1117.19%120.00%
Total64100.00%5100.00%

EXPORT_SYMBOL_GPL(of_css);
static int notify_on_release(const struct cgroup *cgrp) { return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags); }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage2295.65%266.67%
adrian bunkadrian bunk14.35%133.33%
Total23100.00%3100.00%

/** * for_each_css - iterate all css's of a cgroup * @css: the iteration cursor * @ssid: the index of the subsystem, CGROUP_SUBSYS_COUNT after reaching the end * @cgrp: the target cgroup to iterate css's of * * Should be called under cgroup_[tree_]mutex. */ #define for_each_css(css, ssid, cgrp) \ for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \ if (!((css) = rcu_dereference_check( \ (cgrp)->subsys[(ssid)], \ lockdep_is_held(&cgroup_mutex)))) { } \ else /** * for_each_e_css - iterate all effective css's of a cgroup * @css: the iteration cursor * @ssid: the index of the subsystem, CGROUP_SUBSYS_COUNT after reaching the end * @cgrp: the target cgroup to iterate css's of * * Should be called under cgroup_[tree_]mutex. */ #define for_each_e_css(css, ssid, cgrp) \ for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \ if (!((css) = cgroup_e_css(cgrp, cgroup_subsys[(ssid)]))) \ ; \ else /** * for_each_subsys - iterate all enabled cgroup subsystems * @ss: the iteration cursor * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end */ #define for_each_subsys(ss, ssid) \ for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT && \ (((ss) = cgroup_subsys[ssid]) || true); (ssid)++) /** * do_each_subsys_mask - filter for_each_subsys with a bitmask * @ss: the iteration cursor * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end * @ss_mask: the bitmask * * The block will only run for cases where the ssid-th bit (1 << ssid) of * @ss_mask is set. */ #define do_each_subsys_mask(ss, ssid, ss_mask) do { \ unsigned long __ss_mask = (ss_mask); \ if (!CGROUP_SUBSYS_COUNT) { /* to avoid spurious gcc warning */ \ (ssid) = 0; \ break; \ } \ for_each_set_bit(ssid, &__ss_mask, CGROUP_SUBSYS_COUNT) { \ (ss) = cgroup_subsys[ssid]; \ { #define while_each_subsys_mask() \ } \ } \ } while (false) /* iterate across the hierarchies */ #define for_each_root(root) \ list_for_each_entry((root), &cgroup_roots, root_list) /* iterate over child cgrps, lock should be held throughout iteration */ #define cgroup_for_each_live_child(child, cgrp) \ list_for_each_entry((child), &(cgrp)->self.children, self.sibling) \ if (({ lockdep_assert_held(&cgroup_mutex); \ cgroup_is_dead(child); })) \ ; \ else /* walk live descendants in preorder */ #define cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) \ css_for_each_descendant_pre((d_css), cgroup_css((cgrp), NULL)) \ if (({ lockdep_assert_held(&cgroup_mutex); \ (dsct) = (d_css)->cgroup; \ cgroup_is_dead(dsct); })) \ ; \ else /* walk live descendants in postorder */ #define cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) \ css_for_each_descendant_post((d_css), cgroup_css((cgrp), NULL)) \ if (({ lockdep_assert_held(&cgroup_mutex); \ (dsct) = (d_css)->cgroup; \ cgroup_is_dead(dsct); })) \ ; \ else static void cgroup_release_agent(struct work_struct *work); static void check_for_release(struct cgroup *cgrp); /* * A cgroup can be associated with multiple css_sets as different tasks may * belong to different cgroups on different hierarchies. In the other * direction, a css_set is naturally associated with multiple cgroups. * This M:N relationship is represented by the following link structure * which exists for each association and allows traversing the associations * from both sides. */ struct cgrp_cset_link { /* the cgroup and css_set this link associates */ struct cgroup *cgrp; struct css_set *cset; /* list of cgrp_cset_links anchored at cgrp->cset_links */ struct list_head cset_link; /* list of cgrp_cset_links anchored at css_set->cgrp_links */ struct list_head cgrp_link; }; /* * The default css_set - used by init and its children prior to any * hierarchies being mounted. It contains a pointer to the root state * for each subsystem. Also used to anchor the list of css_sets. Not * reference-counted, to improve performance when child cgroups * haven't been created. */ struct css_set init_css_set = { .refcount = ATOMIC_INIT(1), .cgrp_links = LIST_HEAD_INIT(init_css_set.cgrp_links), .tasks = LIST_HEAD_INIT(init_css_set.tasks), .mg_tasks = LIST_HEAD_INIT(init_css_set.mg_tasks), .mg_preload_node = LIST_HEAD_INIT(init_css_set.mg_preload_node), .mg_node = LIST_HEAD_INIT(init_css_set.mg_node), .task_iters = LIST_HEAD_INIT(init_css_set.task_iters), }; static int css_set_count = 1; /* 1 for init_css_set */ /** * css_set_populated - does a css_set contain any tasks? * @cset: target css_set */
static bool css_set_populated(struct css_set *cset) { lockdep_assert_held(&css_set_lock); return !list_empty(&cset->tasks) || !list_empty(&cset->mg_tasks); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo36100.00%2100.00%
Total36100.00%2100.00%

/** * cgroup_update_populated - updated populated count of a cgroup * @cgrp: the target cgroup * @populated: inc or dec populated count * * One of the css_sets associated with @cgrp is either getting its first * task or losing the last. Update @cgrp->populated_cnt accordingly. The * count is propagated towards root so that a given cgroup's populated_cnt * is zero iff the cgroup and all its descendants don't contain any tasks. * * @cgrp's interface file "cgroup.populated" is zero if * @cgrp->populated_cnt is zero and 1 otherwise. When @cgrp->populated_cnt * changes from or to zero, userland is notified that the content of the * interface file has changed. This can be used to detect when @cgrp and * its descendants become populated or empty. */
static void cgroup_update_populated(struct cgroup *cgrp, bool populated) { lockdep_assert_held(&css_set_lock); do { bool trigger; if (populated) trigger = !cgrp->populated_cnt++; else trigger = !--cgrp->populated_cnt; if (!trigger) break; check_for_release(cgrp); cgroup_file_notify(&cgrp->events_file); cgrp = cgroup_parent(cgrp); } while (cgrp); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo7191.03%685.71%
li zefanli zefan78.97%114.29%
Total78100.00%7100.00%

/** * css_set_update_populated - update populated state of a css_set * @cset: target css_set * @populated: whether @cset is populated or depopulated * * @cset is either getting the first task or losing the last. Update the * ->populated_cnt of all associated cgroups accordingly. */
static void css_set_update_populated(struct css_set *cset, bool populated) { struct cgrp_cset_link *link; lockdep_assert_held(&css_set_lock); list_for_each_entry(link, &cset->cgrp_links, cgrp_link) cgroup_update_populated(link->cgrp, populated); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo42100.00%2100.00%
Total42100.00%2100.00%

/** * css_set_move_task - move a task from one css_set to another * @task: task being moved * @from_cset: css_set @task currently belongs to (may be NULL) * @to_cset: new css_set @task is being moved to (may be NULL) * @use_mg_tasks: move to @to_cset->mg_tasks instead of ->tasks * * Move @task from @from_cset to @to_cset. If @task didn't belong to any * css_set, @from_cset can be NULL. If @task is being disassociated * instead of moved, @to_cset can be NULL. * * This function automatically handles populated_cnt updates and * css_task_iter adjustments but the caller is responsible for managing * @from_cset and @to_cset's reference counts. */
static void css_set_move_task(struct task_struct *task, struct css_set *from_cset, struct css_set *to_cset, bool use_mg_tasks) { lockdep_assert_held(&css_set_lock); if (to_cset && !css_set_populated(to_cset)) css_set_update_populated(to_cset, true); if (from_cset) { struct css_task_iter *it, *pos; WARN_ON_ONCE(list_empty(&task->cg_list)); /* * @task is leaving, advance task iterators which are * pointing to it so that they can resume at the next * position. Advancing an iterator might remove it from * the list, use safe walk. See css_task_iter_advance*() * for details. */ list_for_each_entry_safe(it, pos, &from_cset->task_iters, iters_node) if (it->task_pos == &task->cg_list) css_task_iter_advance(it); list_del_init(&task->cg_list); if (!css_set_populated(from_cset)) css_set_update_populated(from_cset, false); } else { WARN_ON_ONCE(!list_empty(&task->cg_list)); } if (to_cset) { /* * 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(task->flags & PF_EXITING); rcu_assign_pointer(task->cgroups, to_cset); list_add_tail(&task->cg_list, use_mg_tasks ? &to_cset->mg_tasks : &to_cset->tasks); } }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo182100.00%4100.00%
Total182100.00%4100.00%

/* * hash table for cgroup groups. This improves the performance to find * an existing css_set. This hash doesn't (currently) take into * account cgroups in empty hierarchies. */ #define CSS_SET_HASH_BITS 7 static DEFINE_HASHTABLE(css_set_table, CSS_SET_HASH_BITS);
static unsigned long css_set_hash(struct cgroup_subsys_state *css[]) { unsigned long key = 0UL; struct cgroup_subsys *ss; int i; for_each_subsys(ss, i) key += (unsigned long)css[i]; key = (key >> 16) ^ key; return key; }

Contributors

PersonTokensPropCommitsCommitProp
li zefanli zefan4477.19%266.67%
tejun heotejun heo1322.81%133.33%
Total57100.00%3100.00%


static void put_css_set_locked(struct css_set *cset) { struct cgrp_cset_link *link, *tmp_link; struct cgroup_subsys *ss; int ssid; lockdep_assert_held(&css_set_lock); if (!atomic_dec_and_test(&cset->refcount)) return; /* This css_set is dead. unlink it and release cgroup and css refs */ for_each_subsys(ss, ssid) { list_del(&cset->e_cset_node[ssid]); css_put(cset->subsys[ssid]); } hash_del(&cset->hlist); css_set_count--; list_for_each_entry_safe(link, tmp_link, &cset->cgrp_links, cgrp_link) { list_del(&link->cset_link); list_del(&link->cgrp_link); if (cgroup_parent(link->cgrp)) cgroup_put(link->cgrp); kfree(link); } kfree_rcu(cset, rcu_head); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo6948.59%738.89%
paul menagepaul menage4733.10%633.33%
lai jiangshanlai jiangshan1913.38%211.11%
kosaki motohirokosaki motohiro53.52%15.56%
li zefanli zefan10.70%15.56%
ben blumben blum10.70%15.56%
Total142100.00%18100.00%


static void put_css_set(struct css_set *cset) { unsigned long flags; /* * Ensure that the refcount doesn't hit zero while any readers * can see it. Similar to atomic_dec_and_lock(), but for an * rwlock */ if (atomic_add_unless(&cset->refcount, -1, 1)) return; spin_lock_irqsave(&css_set_lock, flags); put_css_set_locked(cset); spin_unlock_irqrestore(&css_set_lock, flags); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo2445.28%350.00%
paul menagepaul menage1833.96%116.67%
daniel bristot de oliveiradaniel bristot de oliveira1018.87%116.67%
lai jiangshanlai jiangshan11.89%116.67%
Total53100.00%6100.00%

/* * refcounted get/put for css_set objects */
static inline void get_css_set(struct css_set *cset) { atomic_inc(&cset->refcount); }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage1365.00%250.00%
tejun heotejun heo735.00%250.00%
Total20100.00%4100.00%

/** * compare_css_sets - helper function for find_existing_css_set(). * @cset: candidate css_set being tested * @old_cset: existing css_set for a task * @new_cgrp: cgroup that's being entered by the task * @template: desired set of css pointers in css_set (pre-calculated) * * Returns true if "cset" matches "old_cset" except for the hierarchy * which "new_cgrp" belongs to, for which it should match "new_cgrp". */
static bool compare_css_sets(struct css_set *cset, struct css_set *old_cset, struct cgroup *new_cgrp, struct cgroup_subsys_state *template[]) { struct list_head *l1, *l2; /* * On the default hierarchy, there can be csets which are * associated with the same set of cgroups but different csses. * Let's first ensure that csses match. */ if (memcmp(template, cset->subsys, sizeof(cset->subsys))) return false; /* * Compare cgroup pointers in order to distinguish between * different cgroups in hierarchies. As different cgroups may * share the same effective css, this comparison is always * necessary. */ l1 = &cset->cgrp_links; l2 = &old_cset->cgrp_links; while (1) { struct cgrp_cset_link *link1, *link2; struct cgroup *cgrp1, *cgrp2; l1 = l1->next; l2 = l2->next; /* See if we reached the end - both lists are equal length. */ if (l1 == &cset->cgrp_links) { BUG_ON(l2 != &old_cset->cgrp_links); break; } else { BUG_ON(l2 == &old_cset->cgrp_links); } /* Locate the cgroups associated with these links. */ link1 = list_entry(l1, struct cgrp_cset_link, cgrp_link); link2 = list_entry(l2, struct cgrp_cset_link, cgrp_link); cgrp1 = link1->cgrp; cgrp2 = link2->cgrp; /* Hierarchies should be linked in the same order. */ BUG_ON(cgrp1->root != cgrp2->root); /* * If this hierarchy is the hierarchy of the cgroup * that's changing, then we need to check that this * css_set points to the new cgroup; if it's any other * hierarchy, then this css_set should point to the * same cgroup as the old css_set. */ if (cgrp1->root == new_cgrp->root) { if (cgrp1 != new_cgrp) return false; } else { if (cgrp1 != cgrp2) return false; } } return true; }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage19183.77%125.00%
tejun heotejun heo3716.23%375.00%
Total228100.00%4100.00%

/** * find_existing_css_set - init css array and find the matching css_set * @old_cset: the css_set that we're using before the cgroup transition * @cgrp: the cgroup that we're moving into * @template: out param for the new set of csses, should be clear on entry */
static struct css_set *find_existing_css_set(struct css_set *old_cset, struct cgroup *cgrp, struct cgroup_subsys_state *template[]) { struct cgroup_root *root = cgrp->root; struct cgroup_subsys *ss; struct css_set *cset; unsigned long key; int i; /* * Build the set of subsystem state objects that we want to see in the * new css_set. while subsystems can change globally, the entries here * won't change, so no need for locking. */ for_each_subsys(ss, i) { if (root->subsys_mask & (1UL << i)) { /* * @ss is in this hierarchy, so we want the * effective css from @cgrp. */ template[i] = cgroup_e_css(cgrp, ss); } else { /* * @ss is not in this hierarchy, so we don't want * to change the css. */ template[i] = old_cset->subsys[i]; } } key = css_set_hash(template); hash_for_each_possible(css_set_table, cset, hlist, key) { if (!compare_css_sets(cset, old_cset, cgrp, template)) continue; /* This css_set matches what we need */ return cset; } /* No existing cgroup group matched */ return NULL; }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage9263.89%529.41%
tejun heotejun heo2920.14%741.18%
li zefanli zefan2114.58%317.65%
ben blumben blum10.69%15.88%
aristeu sergio rozanski filhoaristeu sergio rozanski filho10.69%15.88%
Total144100.00%17100.00%


static void free_cgrp_cset_links(struct list_head *links_to_free) { struct cgrp_cset_link *link, *tmp_link; list_for_each_entry_safe(link, tmp_link, links_to_free, cset_link) { list_del(&link->cset_link); kfree(link); } }

Contributors

PersonTokensPropCommitsCommitProp
li zefanli zefan3579.55%150.00%
tejun heotejun heo920.45%150.00%
Total44100.00%2100.00%

/** * allocate_cgrp_cset_links - allocate cgrp_cset_links * @count: the number of links to allocate * @tmp_links: list_head the allocated links are put on * * Allocate @count cgrp_cset_link structures and chain them on @tmp_links * through ->cset_link. Returns 0 on success or -errno. */
static int allocate_cgrp_cset_links(int count, struct list_head *tmp_links) { struct cgrp_cset_link *link; int i; INIT_LIST_HEAD(tmp_links); for (i = 0; i < count; i++) { link = kzalloc(sizeof(*link), GFP_KERNEL); if (!link) { free_cgrp_cset_links(tmp_links); return -ENOMEM; } list_add(&link->cset_link, tmp_links); } return 0; }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage7589.29%250.00%
tejun heotejun heo910.71%250.00%
Total84100.00%4100.00%

/** * link_css_set - a helper function to link a css_set to a cgroup * @tmp_links: cgrp_cset_link objects allocated by allocate_cgrp_cset_links() * @cset: the css_set to be linked * @cgrp: the destination cgroup */
static void link_css_set(struct list_head *tmp_links, struct css_set *cset, struct cgroup *cgrp) { struct cgrp_cset_link *link; BUG_ON(list_empty(tmp_links)); if (cgroup_on_dfl(cgrp)) cset->dfl_cgrp = cgrp; link = list_first_entry(tmp_links, struct cgrp_cset_link, cset_link); link->cset = cset; link->cgrp = cgrp; /* * Always add links to the tail of the lists so that the lists are * in choronological order. */ list_move_tail(&link->cset_link, &cgrp->cset_links); list_add_tail(&link->cgrp_link, &cset->cgrp_links); if (cgroup_parent(cgrp)) cgroup_get(cgrp); }

Contributors

PersonTokensPropCommitsCommitProp
li zefanli zefan6256.36%114.29%
tejun heotejun heo4137.27%571.43%
paul menagepaul menage76.36%114.29%
Total110100.00%7100.00%

/** * find_css_set - return a new css_set with one cgroup updated * @old_cset: the baseline css_set * @cgrp: the cgroup to be updated * * Return a new css_set that's equivalent to @old_cset, but with @cgrp * substituted into the appropriate hierarchy. */
static struct css_set *find_css_set(struct css_set *old_cset, struct cgroup *cgrp) { struct cgroup_subsys_state *template[CGROUP_SUBSYS_COUNT] = { }; struct css_set *cset; struct list_head tmp_links; struct cgrp_cset_link *link; struct cgroup_subsys *ss; unsigned long key; int ssid; lockdep_assert_held(&cgroup_mutex); /* First see if we already have a cgroup group that matches * the desired set */ spin_lock_irq(&css_set_lock); cset = find_existing_css_set(old_cset, cgrp, template); if (cset) get_css_set(cset); spin_unlock_irq(&css_set_lock); if (cset) return cset; cset = kzalloc(sizeof(*cset), GFP_KERNEL); if (!cset) return NULL; /* Allocate all the cgrp_cset_link objects that we'll need */ if (allocate_cgrp_cset_links(cgroup_root_count, &tmp_links) < 0) { kfree(cset); return NULL; } atomic_set(&cset->refcount, 1); INIT_LIST_HEAD(&cset->cgrp_links); INIT_LIST_HEAD(&cset->tasks); INIT_LIST_HEAD(&cset->mg_tasks); INIT_LIST_HEAD(&cset->mg_preload_node); INIT_LIST_HEAD(&cset->mg_node); INIT_LIST_HEAD(&cset->task_iters); INIT_HLIST_NODE(&cset->hlist); /* Copy the set of subsystem state objects generated in * find_existing_css_set() */ memcpy(cset->subsys, template, sizeof(cset->subsys)); spin_lock_irq(&css_set_lock); /* Add reference counts and links from the new css_set. */ list_for_each_entry(link, &old_cset->cgrp_links, cgrp_link) { struct cgroup *c = link->cgrp; if (c->root == cgrp->root) c = cgrp; link_css_set(&tmp_links, cset, c); } BUG_ON(!list_empty(&tmp_links)); css_set_count++; /* Add @cset to the hash table */ key = css_set_hash(cset->subsys); hash_add(css_set_table, &cset->hlist, key); for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cset->subsys[ssid]; list_add_tail(&cset->e_cset_node[ssid], &css->cgroup->e_csets[ssid]); css_get(css); } spin_unlock_irq(&css_set_lock); return cset; }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage19051.77%419.05%
tejun heotejun heo13737.33%1257.14%
li zefanli zefan328.72%314.29%
daniel bristot de oliveiradaniel bristot de oliveira41.09%14.76%
lai jiangshanlai jiangshan41.09%14.76%
Total367100.00%21100.00%


static struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root) { struct cgroup *root_cgrp = kf_root->kn->priv; return root_cgrp->root; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo1862.07%266.67%
paul menagepaul menage1137.93%133.33%
Total29100.00%3100.00%


static int cgroup_init_root_id(struct cgroup_root *root) { int id; lockdep_assert_held(&cgroup_mutex); id = idr_alloc_cyclic(&cgroup_hierarchy_idr, root, 0, 0, GFP_KERNEL); if (id < 0) return id; root->hierarchy_id = id; return 0; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo4175.93%375.00%
paul menagepaul menage1324.07%125.00%
Total54100.00%4100.00%


static void cgroup_exit_root_id(struct cgroup_root *root) { lockdep_assert_held(&cgroup_mutex); if (root->hierarchy_id) { idr_remove(&cgroup_hierarchy_idr, root->hierarchy_id); root->hierarchy_id = 0; } }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo3175.61%375.00%
paul menagepaul menage1024.39%125.00%
Total41100.00%4100.00%


static void cgroup_free_root(struct cgroup_root *root) { if (root) { /* hierarchy ID should already have been released */ WARN_ON_ONCE(root->hierarchy_id); idr_destroy(&root->cgroup_idr); kfree(root); } }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo2052.63%250.00%
paul menagepaul menage1744.74%125.00%
chen hanxiaochen hanxiao12.63%125.00%
Total38100.00%4100.00%


static void cgroup_destroy_root(struct cgroup_root *root) { struct cgroup *cgrp = &root->cgrp; struct cgrp_cset_link *link, *tmp_link; cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); BUG_ON(atomic_read(&root->nr_cgrps)); BUG_ON(!list_empty(&cgrp->self.children)); /* Rebind all subsystems back to the default hierarchy */ WARN_ON(rebind_subsystems(&cgrp_dfl_root, root->subsys_mask)); /* * Release all the links from cset_links to this hierarchy's * root cgroup */ spin_lock_irq(&css_set_lock); list_for_each_entry_safe(link, tmp_link, &cgrp->cset_links, cset_link) { list_del(&link->cset_link); list_del(&link->cgrp_link); kfree(link); } spin_unlock_irq(&css_set_lock); if (!list_empty(&root->root_list)) { list_del(&root->root_list); cgroup_root_count--; } cgroup_exit_root_id(root); mutex_unlock(&cgroup_mutex); kernfs_destroy_root(root->kf_root); cgroup_free_root(root); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo13479.29%1071.43%
paul menagepaul menage3319.53%321.43%
daniel bristot de oliveiradaniel bristot de oliveira21.18%17.14%
Total169100.00%14100.00%

/* * look up cgroup associated with current task's cgroup namespace on the * specified hierarchy */
static struct cgroup * current_cgns_cgroup_from_root(struct cgroup_root *root) { struct cgroup *res = NULL; struct css_set *cset; lockdep_assert_held(&css_set_lock); rcu_read_lock(); cset = current->nsproxy->cgroup_ns->root_cset; if (cset == &init_css_set) { res = &root->cgrp; } else { struct cgrp_cset_link *link; list_for_each_entry(link, &cset->cgrp_links, cgrp_link) { struct cgroup *c = link->cgrp; if (c->root == root) { res = c; break; } } } rcu_read_unlock(); BUG_ON(!res); return res; }

Contributors

PersonTokensPropCommitsCommitProp
serge hallynserge hallyn114100.00%1100.00%
Total114100.00%1100.00%

/* look up cgroup associated with given css_set on the specified hierarchy */
static struct cgroup *cset_cgroup_from_root(struct css_set *cset, struct cgroup_root *root) { struct cgroup *res = NULL; lockdep_assert_held(&cgroup_mutex); lockdep_assert_held(&css_set_lock); if (cset == &init_css_set) { res = &root->cgrp; } else { struct cgrp_cset_link *link; list_for_each_entry(link, &cset->cgrp_links, cgrp_link) { struct cgroup *c = link->cgrp; if (c->root == root) { res = c; break; } } } BUG_ON(!res); return res; }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage4947.12%321.43%
tejun heotejun heo3028.85%857.14%
li zefanli zefan2524.04%321.43%
Total104100.00%14100.00%

/* * Return the cgroup for "task" from the given hierarchy. Must be * called with cgroup_mutex and css_set_lock held. */
static struct cgroup *task_cgroup_from_root(struct task_struct *task, struct cgroup_root *root) { /* * No need to lock the task - since we hold cgroup_mutex the * task can't change groups, so the only thing that can happen * is that it exits and its css is set back to init_css_set. */ return cset_cgroup_from_root(task_css_set(task), root); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo2170.00%480.00%
li zefanli zefan930.00%120.00%
Total30100.00%5100.00%

/* * A task must hold cgroup_mutex to modify cgroups. * * Any task can increment and decrement the count field without lock. * So in general, code holding cgroup_mutex can't rely on the count * field not changing. However, if the count goes to zero, then only * cgroup_attach_task() can increment it again. Because a count of zero * means that no tasks are currently attached, therefore there is no * way a task attached to that cgroup can fork (the other way to * increment the count). So code holding cgroup_mutex can safely * assume that if the count is zero, it will stay zero. Similarly, if * a task holds cgroup_mutex on a cgroup with zero count, it * knows that the cgroup won't be removed, as cgroup_rmdir() * needs that mutex. * * A cgroup can only be deleted if both its 'count' of using tasks * is zero, and its list of 'children' cgroups is empty. Since all * tasks in the system use _some_ cgroup, and since there is always at * least one task in the system (init, pid == 1), therefore, root cgroup * always has either children cgroups and/or using tasks. So we don't * need a special hack to ensure that root cgroup cannot be deleted. * * P.S. One more locking exception. RCU is used to guard the * update of a tasks cgroup pointer by cgroup_attach_task() */ static struct kernfs_syscall_ops cgroup_kf_syscall_ops; static const struct file_operations proc_cgroupstats_operations;
static char *cgroup_file_name(struct cgroup *cgrp, const struct cftype *cft, char *buf) { struct cgroup_subsys *ss = cft->ss; if (cft->ss && !(cft->flags & CFTYPE_NO_PREFIX) && !(cgrp->root->flags & CGRP_ROOT_NOPREFIX)) snprintf(buf, CGROUP_FILE_NAME_MAX, "%s.%s", cgroup_on_dfl(cgrp) ? ss->name : ss->legacy_name, cft->name); else strncpy(buf, cft->name, CGROUP_FILE_NAME_MAX); return buf; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo7778.57%240.00%
li zefanli zefan2121.43%360.00%
Total98100.00%5100.00%

/** * cgroup_file_mode - deduce file mode of a control file * @cft: the control file in question * * S_IRUGO for read, S_IWUSR for write. */
static umode_t cgroup_file_mode(const struct cftype *cft) { umode_t mode = 0; if (cft->read_u64 || cft->read_s64 || cft->seq_show) mode |= S_IRUGO; if (cft->write_u64 || cft->write_s64 || cft->write) { if (cft->flags & CFTYPE_WORLD_WRITABLE) mode |= S_IWUGO; else mode |= S_IWUSR; } return mode; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo6794.37%480.00%
paul menagepaul menage45.63%120.00%
Total71100.00%5100.00%

/** * cgroup_calc_subtree_ss_mask - calculate subtree_ss_mask * @subtree_control: the new subtree_control mask to consider * @this_ss_mask: available subsystems * * On the default hierarchy, a subsystem may request other subsystems to be * enabled together through its ->depends_on mask. In such cases, more * subsystems than specified in "cgroup.subtree_control" may be enabled. * * This function calculates which subsystems need to be enabled if * @subtree_control is to be applied while restricted to @this_ss_mask. */
static u16 cgroup_calc_subtree_ss_mask(u16 subtree_control, u16 this_ss_mask) { u16 cur_ss_mask = subtree_control; struct cgroup_subsys *ss; int ssid; lockdep_assert_held(&cgroup_mutex); cur_ss_mask |= cgrp_dfl_implicit_ss_mask; while (true) { u16 new_ss_mask = cur_ss_mask; do_each_subsys_mask(ss, ssid, cur_ss_mask) { new_ss_mask |= ss->depends_on; } while_each_subsys_mask(); /* * Mask out subsystems which aren't available. This can * happen only if some depended-upon subsystems were bound * to non-default hierarchies. */ new_ss_mask &= this_ss_mask; if (new_ss_mask == cur_ss_mask) break; cur_ss_mask = new_ss_mask; } return cur_ss_mask; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo8398.81%888.89%
aleksa saraialeksa sarai11.19%111.11%
Total84100.00%9100.00%

/** * cgroup_kn_unlock - unlocking helper for cgroup kernfs methods * @kn: the kernfs_node being serviced * * This helper undoes cgroup_kn_lock_live() and should be invoked before * the method finishes if locking succeeded. Note that once this function * returns the cgroup returned by cgroup_kn_lock_live() may become * inaccessible any time. If the caller intends to continue to access the * cgroup, it should pin it before invoking this function. */
static void cgroup_kn_unlock(struct kernfs_node *kn) { struct cgroup *cgrp; if (kernfs_type(kn) == KERNFS_DIR) cgrp = kn->priv; else cgrp = kn->parent->priv; mutex_unlock(&cgroup_mutex); kernfs_unbreak_active_protection(kn); cgroup_put(cgrp); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo3257.14%562.50%
paul menagepaul menage1832.14%112.50%
li zefanli zefan47.14%112.50%
nick pigginnick piggin23.57%112.50%
Total56100.00%8100.00%

/** * cgroup_kn_lock_live - locking helper for cgroup kernfs methods * @kn: the kernfs_node being serviced * @drain_offline: perform offline draining on the cgroup * * This helper is to be used by a cgroup kernfs method currently servicing * @kn. It breaks the active protection, performs cgroup locking and * verifies that the associated cgroup is alive. Returns the cgroup if * alive; otherwise, %NULL. A successful return should be undone by a * matching cgroup_kn_unlock() invocation. If @drain_offline is %true, the * cgroup is drained of offlining csses before return. * * Any cgroup kernfs method implementation which requires locking the * associated cgroup should use this helper. It avoids nesting cgroup * locking under kernfs active protection and allows all kernfs operations * including self-removal. */
static struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn, bool drain_offline) { struct cgroup *cgrp; if (kernfs_type(kn) == KERNFS_DIR) cgrp = kn->priv; else cgrp = kn->parent->priv; /* * We're gonna grab cgroup_mutex which nests outside kernfs * active_ref. cgroup liveliness check alone provides enough * protection against removal. Ensure @cgrp stays accessible and * break the active_ref protection. */ if (!cgroup_tryget(cgrp)) return NULL; kernfs_break_active_protection(kn); if (drain_offline) cgroup_lock_and_drain_offline(cgrp); else mutex_lock(&cgroup_mutex); if (!cgroup_is_dead(cgrp)) return cgrp; cgroup_kn_unlock(kn); return NULL; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo6162.89%650.00%
li zefanli zefan2727.84%433.33%
paul menagepaul menage66.19%18.33%
nick pigginnick piggin33.09%18.33%
Total97100.00%12100.00%


static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft) { char name[CGROUP_FILE_NAME_MAX]; lockdep_assert_held(&cgroup_mutex); if (cft->file_offset) { struct cgroup_subsys_state *css = cgroup_css(cgrp, cft->ss); struct cgroup_file *cfile = (void *)css + cft->file_offset; spin_lock_irq(&cgroup_file_kn_lock); cfile->kn = NULL; spin_unlock_irq(&cgroup_file_kn_lock); } kernfs_remove_by_name(cgrp->kn, cgroup_file_name(cgrp, cft, name)); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo9090.00%571.43%
nick pigginnick piggin66.00%114.29%
paul menagepaul menage44.00%114.29%
Total100100.00%7100.00%

/** * css_clear_dir - remove subsys files in a cgroup directory * @css: taget css */
static void css_clear_dir(struct cgroup_subsys_state *css) { struct cgroup *cgrp = css->cgroup; struct cftype *cfts; if (!(css->flags & CSS_VISIBLE)) return; css->flags &= ~CSS_VISIBLE; list_for_each_entry(cfts, &css->ss->cfts, node) cgroup_addrm_files(css, cgrp, cfts, false); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo4368.25%571.43%
aristeu sergio rozanski filhoaristeu sergio rozanski filho1726.98%114.29%
gao fenggao feng34.76%114.29%
Total63100.00%7100.00%

/** * css_populate_dir - create subsys files in a cgroup directory * @css: target css * * On failure, no file is added. */
static int css_populate_dir(struct cgroup_subsys_state *css) { struct cgroup *cgrp = css->cgroup; struct cftype *cfts, *failed_cfts; int ret; if ((css->flags & CSS_VISIBLE) || !cgrp->kn) return 0; if (!css->ss) { if (cgroup_on_dfl(cgrp)) cfts = cgroup_dfl_base_files; else cfts = cgroup_legacy_base_files; return cgroup_addrm_files(&cgrp->self, cgrp, cfts, true); } list_for_each_entry(cfts, &css->ss->cfts, node) { ret = cgroup_addrm_files(css, cgrp, cfts, true); if (ret < 0) { failed_cfts = cfts; goto err; } } css->flags |= CSS_VISIBLE; return 0; err: list_for_each_entry(cfts, &css->ss->cfts, node) { if (cfts == failed_cfts) break; cgroup_addrm_files(css, cgrp, cfts, false); } return ret; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo169100.00%4100.00%
Total169100.00%4100.00%


static int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) { struct cgroup *dcgrp = &dst_root->cgrp; struct cgroup_subsys *ss; int ssid, i, ret; lockdep_assert_held(&cgroup_mutex); do_each_subsys_mask(ss, ssid, ss_mask) { /* * If @ss has non-root csses attached to it, can't move. * If @ss is an implicit controller, it is exempt from this * rule and can be stolen. */ if (css_next_child(NULL, cgroup_css(&ss->root->cgrp, ss)) && !ss->implicit_on_dfl) return -EBUSY; /* can't move between two non-dummy roots either */ if (ss->root != &cgrp_dfl_root && dst_root != &cgrp_dfl_root) return -EBUSY; } while_each_subsys_mask(); do_each_subsys_mask(ss, ssid, ss_mask) { struct cgroup_root *src_root = ss->root; struct cgroup *scgrp = &src_root->cgrp; struct cgroup_subsys_state *css = cgroup_css(scgrp, ss); struct css_set *cset; WARN_ON(!css || cgroup_css(dcgrp, ss)); /* disable from the source */ src_root->subsys_mask &= ~(1 << ssid); WARN_ON(cgroup_apply_control(scgrp)); cgroup_finalize_control(scgrp, 0); /* rebind */ RCU_INIT_POINTER(scgrp->subsys[ssid], NULL); rcu_assign_pointer(dcgrp->subsys[ssid], css); ss->root = dst_root; css->cgroup = dcgrp; spin_lock_irq(&css_set_lock); hash_for_each(css_set_table, i, cset, hlist) list_move_tail(&cset->e_cset_node[ss->id], &dcgrp->e_csets[ss->id]); spin_unlock_irq(&css_set_lock); /* default hierarchy doesn't enable controllers by default */ dst_root->subsys_mask |= 1 << ssid; if (dst_root == &cgrp_dfl_root) { static_branch_enable(cgroup_subsys_on_dfl_key[ssid]); } else { dcgrp->subtree_control |= 1 << ssid; static_branch_disable(cgroup_subsys_on_dfl_key[ssid]); } ret = cgroup_apply_control(dcgrp); if (ret) pr_warn("partial failure to rebind %s controller (err=%d)\n", ss->name, ret); if (ss->bind) ss->bind(css); } while_each_subsys_mask(); kernfs_activate(dcgrp->kn); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo28478.02%2477.42%
paul menagepaul menage6317.31%13.23%
nick pigginnick piggin82.20%13.23%
ben blumben blum30.82%26.45%
daniel bristot de oliveiradaniel bristot de oliveira20.55%13.23%
lai jiangshanlai jiangshan20.55%13.23%
aleksa saraialeksa sarai20.55%13.23%
Total364100.00%31100.00%


static int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node, struct kernfs_root *kf_root) { int len = 0; char *buf = NULL; struct cgroup_root *kf_cgroot = cgroup_root_from_kf(kf_root); struct cgroup *ns_cgroup; buf = kmalloc(PATH_MAX, GFP_KERNEL); if (!buf) return -ENOMEM; spin_lock_irq(&css_set_lock); ns_cgroup = current_cgns_cgroup_from_root(kf_cgroot); len = kernfs_path_from_node(kf_node, ns_cgroup->kn, buf, PATH_MAX); spin_unlock_irq(&css_set_lock); if (len >= PATH_MAX) len = -ERANGE; else if (len > 0) { seq_escape(sf, buf, " \t\n\\"); len = 0; } kfree(buf); return len; }

Contributors

PersonTokensPropCommitsCommitProp
serge hallynserge hallyn13898.57%150.00%
daniel bristot de oliveiradaniel bristot de oliveira21.43%150.00%
Total140100.00%2100.00%


static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root) { struct cgroup_root *root = cgroup_root_from_kf(kf_root); struct cgroup_subsys *ss; int ssid; if (root != &cgrp_dfl_root) for_each_subsys(ss, ssid) if (root->subsys_mask & (1 << ssid)) seq_show_option(seq, ss->legacy_name, NULL); if (root->flags & CGRP_ROOT_NOPREFIX) seq_puts(seq, ",noprefix"); if (root->flags & CGRP_ROOT_XATTR) seq_puts(seq, ",xattr"); spin_lock(&release_agent_path_lock); if (strlen(root->release_agent_path)) seq_show_option(seq, "release_agent", root->release_agent_path); spin_unlock(&release_agent_path_lock); if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags)) seq_puts(seq, ",clone_children"); if (strlen(root->name)) seq_show_option(seq, "name", root->name); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage8648.86%426.67%
tejun heotejun heo5430.68%746.67%
daniel lezcanodaniel lezcano158.52%16.67%
aristeu sergio rozanski filhoaristeu sergio rozanski filho137.39%16.67%
kees cookkees cook84.55%213.33%
Total176100.00%15100.00%

struct cgroup_sb_opts { u16 subsys_mask; unsigned int flags; char *release_agent; bool cpuset_clone_children; char *name; /* User explicitly requested empty subsystem */ bool none; };
static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) { char *token, *o = data; bool all_ss = false, one_ss = false; u16 mask = U16_MAX; struct cgroup_subsys *ss; int nr_opts = 0; int i; #ifdef CONFIG_CPUSETS mask = ~((u16)1 << cpuset_cgrp_id); #endif memset(opts, 0, sizeof(*opts)); while ((token = strsep(&o, ",")) != NULL) { nr_opts++; if (!*token) return -EINVAL; if (!strcmp(token, "none")) { /* Explicitly have no subsystems */ opts->none = true; continue; } if (!strcmp(token, "all")) { /* Mutually exclusive option 'all' + subsystem name */ if (one_ss) return -EINVAL; all_ss = true; continue; } if (!strcmp(token, "noprefix")) { opts->flags |= CGRP_ROOT_NOPREFIX; continue; } if (!strcmp(token, "clone_children")) { opts->cpuset_clone_children = true; continue; } if (!strcmp(token, "xattr")) { opts->flags |= CGRP_ROOT_XATTR; continue; } if (!strncmp(token, "release_agent=", 14)) { /* Specifying two release agents is forbidden */ if (opts->release_agent) return -EINVAL; opts->release_agent = kstrndup(token + 14, PATH_MAX - 1, GFP_KERNEL); if (!opts->release_agent) return -ENOMEM; continue; } if (!strncmp(token, "name=", 5)) { const char *name = token + 5; /* Can't specify an empty name */ if (!strlen(name)) return -EINVAL; /* Must match [\w.-]+ */ for (i = 0; i < strlen(name); i++) { char c = name[i]; if (isalnum(c)) continue; if ((c == '.') || (c == '-') || (c == '_')) continue; return -EINVAL; } /* Specifying two names is forbidden */ if (opts->name) return -EINVAL; opts->name = kstrndup(name, MAX_CGROUP_ROOT_NAMELEN - 1, GFP_KERNEL); if (!opts->name) return -ENOMEM; continue; } for_each_subsys(ss, i) { if (strcmp(token, ss->legacy_name)) continue; if (!cgroup_ssid_enabled(i)) continue; if (cgroup_ssid_no_v1(i)) continue; /* Mutually exclusive option 'all' + subsystem name */ if (all_ss) return -EINVAL; opts->subsys_mask |= (1 << i); one_ss = true; break; } if (i == CGROUP_SUBSYS_COUNT) return -ENOENT; } /* * If the 'all' option was specified select all the subsystems, * otherwise if 'none', 'name=' and a subsystem name options were * not specified, let's default to 'all' */ if (all_ss || (!one_ss && !opts->none && !opts->name)) for_each_subsys(ss, i) if (cgroup_ssid_enabled(i) && !cgroup_ssid_no_v1(i)) opts->subsys_mask |= (1 << i); /* * We either have to specify by name or by subsystems. (So all * empty hierarchies must have a name). */ if (!opts->subsys_mask && !opts->name) return -EINVAL; /* * Option noprefix was introduced just for backward compatibility * with the old cpuset, so we allow noprefix only if mounting just * the cpuset subsystem. */ if ((opts->flags & CGRP_ROOT_NOPREFIX) && (opts->subsys_mask & mask)) return -EINVAL; /* Can't specify "none" and some subsystems */ if (opts->subsys_mask && opts->none) return -EINVAL; return 0; }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage33657.83%519.23%
tejun heotejun heo9015.49%1246.15%
daniel lezcanodaniel lezcano7512.91%27.69%
li zefanli zefan386.54%27.69%
aristeu sergio rozanski filhoaristeu sergio rozanski filho213.61%27.69%
johannes weinerjohannes weiner142.41%13.85%
dan carpenterdan carpenter40.69%13.85%
ben blumben blum30.52%13.85%
Total581100.00%26100.00%


static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data) { int ret = 0; struct cgroup_root *root = cgroup_root_from_kf(kf_root); struct cgroup_sb_opts opts; u16 added_mask, removed_mask; if (root == &cgrp_dfl_root) { pr_err("remount is not allowed\n"); return -EINVAL; } cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); /* See what subsystems are wanted */ ret = parse_cgroupfs_options(data, &opts); if (ret) goto out_unlock; if (opts.subsys_mask != root->subsys_mask || opts.release_agent) pr_warn("option changes via remount are deprecated (pid=%d comm=%s)\n", task_tgid_nr(current), current->comm); added_mask = opts.subsys_mask & ~root->subsys_mask; removed_mask = root->subsys_mask & ~opts.subsys_mask; /* Don't allow flags or name to change at remount */ if ((opts.flags ^ root->flags) || (opts.name && strcmp(opts.name, root->name))) { pr_err("option or name mismatch, new: 0x%x \"%s\", old: 0x%x \"%s\"\n", opts.flags, opts.name ?: "", root->flags, root->name); ret = -EINVAL; goto out_unlock; } /* remounting is not allowed for populated hierarchies */ if (!list_empty(&root->cgrp.self.children)) { ret = -EBUSY; goto out_unlock; } ret = rebind_subsystems(root, added_mask); if (ret) goto out_unlock; WARN_ON(rebind_subsystems(&cgrp_dfl_root, removed_mask)); if (opts.release_agent) { spin_lock(&release_agent_path_lock); strcpy(root->release_agent_path, opts.release_agent); spin_unlock(&release_agent_path_lock); } out_unlock: kfree(opts.release_agent); kfree(opts.name); mutex_unlock(&cgroup_mutex); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage14045.16%312.00%
tejun heotejun heo13242.58%1560.00%
aristeu sergio rozanski filhoaristeu sergio rozanski filho278.71%28.00%
ben blumben blum41.29%14.00%
li zefanli zefan30.97%14.00%
gao fenggao feng20.65%14.00%
jianyu zhanjianyu zhan10.32%14.00%
joe perchesjoe perches10.32%14.00%
Total310100.00%25100.00%

/* * To reduce the fork() overhead for systems that are not actually using * their cgroups capability, we don't maintain the lists running through * each css_set to its tasks until we see the list actually used - in other * words after the first mount. */ static bool use_task_css_set_links __read_mostly;
static void cgroup_enable_task_cg_lists(void) { struct task_struct *p, *g; spin_lock_irq(&css_set_lock); if (use_task_css_set_links) goto out_unlock; use_task_css_set_links = true; /* * We need tasklist_lock because RCU is not safe against * while_each_thread(). Besides, a forking task that has passed * cgroup_post_fork() without seeing use_task_css_set_links = 1 * is not guaranteed to have its child immediately visible in the * tasklist if we walk through it with RCU. */ read_lock(&tasklist_lock); do_each_thread(g, p) { WARN_ON_ONCE(!list_empty(&p->cg_list) || task_css_set(p) != &init_css_set); /* * We should check if the process is exiting, otherwise * it will race with cgroup_exit() in that the list * entry won't be deleted though the process has exited. * Do it while holding siglock so that we don't end up * racing against cgroup_exit(). * * Interrupts were already disabled while acquiring * the css_set_lock, so we do not need to disable it * again when acquiring the sighand->siglock here. */ spin_lock(&p->sighand->siglock); if (!(p->flags & PF_EXITING)) { struct css_set *cset = task_css_set(p); if (!css_set_populated(cset)) css_set_update_populated(cset, true); list_add_tail(&p->cg_list, &cset->tasks); get_css_set(cset); } spin_unlock(&p->sighand->siglock); } while_each_thread(g, p); read_unlock(&tasklist_lock); out_unlock: spin_unlock_irq(&css_set_lock); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo14285.54%777.78%
paul menagepaul menage1911.45%111.11%
daniel bristot de oliveiradaniel bristot de oliveira53.01%111.11%
Total166100.00%9100.00%


static void init_cgroup_housekeeping(struct cgroup *cgrp) { struct cgroup_subsys *ss; int ssid; INIT_LIST_HEAD(&cgrp->self.sibling); INIT_LIST_HEAD(&cgrp->self.children); INIT_LIST_HEAD(&cgrp->cset_links); INIT_LIST_HEAD(&cgrp->pidlists); mutex_init(&cgrp->pidlist_mutex); cgrp->self.cgroup = cgrp; cgrp->self.flags |= CSS_ONLINE; for_each_subsys(ss, ssid) INIT_LIST_HEAD(&cgrp->e_csets[ssid]); init_waitqueue_head(&cgrp->offline_waitq); INIT_WORK(&cgrp->release_agent_work, cgroup_release_agent); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo6355.26%969.23%
paul menagepaul menage3429.82%17.69%
li zefanli zefan108.77%17.69%
ben blumben blum76.14%215.38%
Total114100.00%13100.00%


static void init_cgroup_root(struct cgroup_root *root, struct cgroup_sb_opts *opts) { struct cgroup *cgrp = &root->cgrp; INIT_LIST_HEAD(&root->root_list); atomic_set(&root->nr_cgrps, 1); cgrp->root = root; init_cgroup_housekeeping(cgrp); idr_init(&root->cgroup_idr); root->flags = opts->flags; if (opts->release_agent) strcpy(root->release_agent_path, opts->release_agent); if (opts->name) strcpy(root->name, opts->name); if (opts->cpuset_clone_children) set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags); }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage7661.79%327.27%
tejun heotejun heo1915.45%545.45%
li zefanli zefan1310.57%19.09%
daniel lezcanodaniel lezcano97.32%19.09%
li zhongli zhong64.88%19.09%
Total123100.00%11100.00%


static int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask) { LIST_HEAD(tmp_links); struct cgroup *root_cgrp = &root->cgrp; struct css_set *cset; int i, ret; lockdep_assert_held(&cgroup_mutex); ret = cgroup_idr_alloc(&root->cgroup_idr, root_cgrp, 1, 2, GFP_KERNEL); if (ret < 0) goto out; root_cgrp->id = ret; root_cgrp->ancestor_ids[0] = ret; ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release, 0, GFP_KERNEL); if (ret) goto out; /* * We're accessing css_set_count without locking css_set_lock here, * but that's OK - it can only be increased by someone holding * cgroup_lock, and that's us. Later rebinding may disable * controllers on the default hierarchy and thus create new csets, * which can't be more than the existing ones. Allocate 2x. */ ret = allocate_cgrp_cset_links(2 * css_set_count, &tmp_links); if (ret) goto cancel_ref; ret = cgroup_init_root_id(root); if (ret) goto cancel_ref; root->kf_root = kernfs_create_root(&cgroup_kf_syscall_ops, KERNFS_ROOT_CREATE_DEACTIVATED, root_cgrp); if (IS_ERR(root->kf_root)) { ret = PTR_ERR(root->kf_root); goto exit_root_id; } root_cgrp->kn = root->kf_root->kn; ret = css_populate_dir(&root_cgrp->self); if (ret) goto destroy_root; ret = rebind_subsystems(root, ss_mask); if (ret) goto destroy_root; /* * There must be no failure case after here, since rebinding takes * care of subsystems' refcounts, which are explicitly dropped in * the failure exit path. */ list_add(&root->root_list, &cgroup_roots); cgroup_root_count++; /* * Link the root cgroup in this hierarchy into all the css_set * objects. */ spin_lock_irq(&css_set_lock); hash_for_each(css_set_table, i, cset, hlist) { link_css_set(&tmp_links, cset, root_cgrp); if (css_set_populated(cset)) cgroup_update_populated(root_cgrp, true); } spin_unlock_irq(&css_set_lock); BUG_ON(!list_empty(&root_cgrp->self.children)); BUG_ON(atomic_read(&root->nr_cgrps) != 1); kernfs_activate(root_cgrp->kn); ret = 0; goto out; destroy_root: kernfs_destroy_root(root->kf_root); root->kf_root = NULL; exit_root_id: cgroup_exit_root_id(root); cancel_ref: percpu_ref_exit(&root_cgrp->self.refcnt); out: free_cgrp_cset_links(&tmp_links); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo26871.28%2367.65%
paul menagepaul menage9324.73%514.71%
daniel lezcanodaniel lezcano71.86%12.94%
ben blumben blum30.80%12.94%
al viroal viro20.53%25.88%
daniel bristot de oliveiradaniel bristot de oliveira20.53%12.94%
vladimir davydovvladimir davydov10.27%12.94%
Total376100.00%34100.00%


static struct dentry *cgroup_mount(struct file_system_type *fs_type, int flags, const char *unused_dev_name, void *data) { bool is_v2 = fs_type == &cgroup2_fs_type; struct super_block *pinned_sb = NULL; struct cgroup_namespace *ns = current->nsproxy->cgroup_ns; struct cgroup_subsys *ss; struct cgroup_root *root; struct cgroup_sb_opts opts; struct dentry *dentry; int ret; int i; bool new_sb; get_cgroup_ns(ns); /* Check if the caller has permission to mount. */ if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN)) { put_cgroup_ns(ns); return ERR_PTR(-EPERM); } /* * The first time anyone tries to mount a cgroup, enable the list * linking each css_set to its tasks and fix up all existing tasks. */ if (!use_task_css_set_links) cgroup_enable_task_cg_lists(); if (is_v2) { if (data) { pr_err("cgroup2: unknown option \"%s\"\n", (char *)data); put_cgroup_ns(ns); return ERR_PTR(-EINVAL); } cgrp_dfl_visible = true; root = &cgrp_dfl_root; cgroup_get(&root->cgrp); goto out_mount; } cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); /* First find the desired set of subsystems */ ret = parse_cgroupfs_options(data, &opts); if (ret) goto out_unlock; /* * Destruction of cgroup root is asynchronous, so subsystems may * still be dying after the previous unmount. Let's drain the * dying subsystems. We just need to ensure that the ones * unmounted previously finish dying and don't care about new ones * starting. Testing ref liveliness is good enough. */ for_each_subsys(ss, i) { if (!(opts.subsys_mask & (1 << i)) || ss->root == &cgrp_dfl_root) continue; if (!percpu_ref_tryget_live(&ss->root->cgrp.self.refcnt)) { mutex_unlock(&cgroup_mutex); msleep(10); ret = restart_syscall(); goto out_free; } cgroup_put(&ss->root->cgrp); } for_each_root(root) { bool name_match = false; if (root == &cgrp_dfl_root) continue; /* * If we asked for a name then it must match. Also, if * name matches but sybsys_mask doesn't, we should fail. * Remember whether name matched. */ if (opts.name) { if (strcmp(opts.name, root->name)) continue; name_match = true; } /* * If we asked for subsystems (or explicitly for no * subsystems) then they must match. */ if ((opts.subsys_mask || opts.none) && (opts.subsys_mask != root->subsys_mask)) { if (!name_match) continue; ret = -EBUSY; goto out_unlock; } if (root->flags ^ opts.flags) pr_warn("new mount options do not match the existing superblock, will be ignored\n"); /* * We want to reuse @root whose lifetime is governed by its * ->cgrp. Let's check whether @root is alive and keep it * that way. As cgroup_kill_sb() can happen anytime, we * want to block it by pinning the sb so that @root doesn't * get killed before mount is complete. * * With the sb pinned, tryget_live can reliably indicate * whether @root can be reused. If it's being killed, * drain it. We can use wait_queue for the wait but this * path is super cold. Let's just sleep a bit and retry. */ pinned_sb = kernfs_pin_sb(root->kf_root, NULL); if (IS_ERR(pinned_sb) || !percpu_ref_tryget_live(&root->cgrp.self.refcnt)) { mutex_unlock(&cgroup_mutex); if (!IS_ERR_OR_NULL(pinned_sb)) deactivate_super(pinned_sb); msleep(10); ret = restart_syscall(); goto out_free; } ret = 0; goto out_unlock; } /* * No such thing, create a new one. name= matching without subsys * specification is allowed for already existing hierarchies but we * can't create new one without subsys specification. */ if (!opts.subsys_mask && !opts.none) { ret = -EINVAL; goto out_unlock; } /* * We know this subsystem has not yet been bound. Users in a non-init * user namespace may only mount hierarchies with no bound subsystems, * i.e. 'none,name=user1' */ if (!opts.none && !capable(CAP_SYS_ADMIN)) { ret = -EPERM; goto out_unlock; } root = kzalloc(sizeof(*root), GFP_KERNEL); if (!root) { ret = -ENOMEM; goto out_unlock; } init_cgroup_root(root, &opts); ret = cgroup_setup_root(root, opts.subsys_mask); if (ret) cgroup_free_root(root); out_unlock: mutex_unlock(&cgroup_mutex); out_free: kfree(opts.release_agent); kfree(opts.name); if (ret) { put_cgroup_ns(ns); return ERR_PTR(ret); } out_mount: dentry = kernfs_mount(fs_type, flags, root->kf_root, is_v2 ? CGROUP2_SUPER_MAGIC : CGROUP_SUPER_MAGIC, &new_sb); /* * In non-init cgroup namespace, instead of root cgroup's * dentry, we return the dentry corresponding to the * cgroupns->root_cgrp. */ if (!IS_ERR(dentry) && ns != &init_cgroup_ns) { struct dentry *nsdentry; struct cgroup *cgrp; mutex_lock(&cgroup_mutex); spin_lock_irq(&css_set_lock); cgrp = cset_cgroup_from_root(ns->root_cset, root); spin_unlock_irq(&css_set_lock); mutex_unlock(&cgroup_mutex); nsdentry = kernfs_node_dentry(cgrp->kn, dentry->d_sb); dput(dentry); dentry = nsdentry; } if (IS_ERR(dentry) || !new_sb) cgroup_put(&root->cgrp); /* * If @pinned_sb, we're reusing an existing root and holding an * extra ref on its sb. Mount is complete. Put the extra ref. */ if (pinned_sb) { WARN_ON(new_sb); deactivate_super(pinned_sb); } put_cgroup_ns(ns); return dentry; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo27937.30%1748.57%
serge hallynserge hallyn16522.06%12.86%
li zefanli zefan15520.72%514.29%
paul menagepaul menage13117.51%411.43%
ben blumben blum81.07%12.86%
jianyu zhanjianyu zhan30.40%25.71%
al viroal viro30.40%25.71%
daniel bristot de oliveiradaniel bristot de oliveira20.27%12.86%
david howellsdavid howells10.13%12.86%
joe perchesjoe perches10.13%12.86%
Total748100.00%35100.00%


static void cgroup_kill_sb(struct super_block *sb) { struct kernfs_root *kf_root = kernfs_root_from_sb(sb); struct cgroup_root *root = cgroup_root_from_kf(kf_root); /* * If @root doesn't have any mounts or children, start killing it. * This prevents new mounts by disabling percpu_ref_tryget_live(). * cgroup_mount() may wait for @root's release. * * And don't kill the default root. */ if (!list_empty(&root->cgrp.self.children) || root == &cgrp_dfl_root) cgroup_put(&root->cgrp); else percpu_ref_kill(&root->cgrp.self.refcnt); kernfs_kill_sb(sb); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo6076.92%770.00%
paul menagepaul menage810.26%110.00%
li zefanli zefan67.69%110.00%
johannes weinerjohannes weiner45.13%110.00%
Total78100.00%10100.00%

static struct file_system_type cgroup_fs_type = { .name = "cgroup", .mount = cgroup_mount, .kill_sb = cgroup_kill_sb, .fs_flags = FS_USERNS_MOUNT, }; static struct file_system_type cgroup2_fs_type = { .name = "cgroup2", .mount = cgroup_mount, .kill_sb = cgroup_kill_sb, .fs_flags = FS_USERNS_MOUNT, };
static char *cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen, struct cgroup_namespace *ns) { struct cgroup *root = cset_cgroup_from_root(ns->root_cset, cgrp->root); int ret; ret = kernfs_path_from_node(cgrp->kn, root->kn, buf, buflen); if (ret < 0 || ret >= buflen) return NULL; return buf; }

Contributors

PersonTokensPropCommitsCommitProp
aditya kaliaditya kali5268.42%133.33%
tejun heotejun heo2127.63%133.33%
paul menagepaul menage33.95%133.33%
Total76100.00%3100.00%


char *cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen, struct cgroup_namespace *ns) { char *ret; mutex_lock(&cgroup_mutex); spin_lock_irq(&css_set_lock); ret = cgroup_path_ns_locked(cgrp, buf, buflen, ns); spin_unlock_irq(&css_set_lock); mutex_unlock(&cgroup_mutex); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
aditya kaliaditya kali6597.01%150.00%
daniel bristot de oliveiradaniel bristot de oliveira22.99%150.00%
Total67100.00%2100.00%

EXPORT_SYMBOL_GPL(cgroup_path_ns); /** * task_cgroup_path - cgroup path of a task in the first cgroup hierarchy * @task: target task * @buf: the buffer to write the path into * @buflen: the length of the buffer * * Determine @task's cgroup on the first (the one with the lowest non-zero * hierarchy_id) cgroup hierarchy and copy its path into @buf. This * function grabs cgroup_mutex and shouldn't be used inside locks used by * cgroup controller callbacks. * * Return value is the same as kernfs_path(). */
char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen) { struct cgroup_root *root; struct cgroup *cgrp; int hierarchy_id = 1; char *path = NULL; mutex_lock(&cgroup_mutex); spin_lock_irq(&css_set_lock); root = idr_get_next(&cgroup_hierarchy_idr, &hierarchy_id); if (root) { cgrp = task_cgroup_from_root(task, root); path = cgroup_path_ns_locked(cgrp, buf, buflen, &init_cgroup_ns); } else { /* if no hierarchy exists, everyone is in "/" */ if (strlcpy(buf, "/", buflen) < buflen) path = buf; } spin_unlock_irq(&css_set_lock); mutex_unlock(&cgroup_mutex); return path; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo9070.87%654.55%
paul menagepaul menage3023.62%218.18%
aditya kaliaditya kali43.15%19.09%
daniel bristot de oliveiradaniel bristot de oliveira21.57%19.09%
xiaotian fengxiaotian feng10.79%19.09%
Total127100.00%11100.00%

EXPORT_SYMBOL_GPL(task_cgroup_path); /* used to track tasks and other necessary states during migration */ struct cgroup_taskset { /* the src and dst cset list running through cset->mg_node */ struct list_head src_csets; struct list_head dst_csets; /* the subsys currently being processed */ int ssid; /* * Fields for cgroup_taskset_*() iteration. * * Before migration is committed, the target migration tasks are on * ->mg_tasks of the csets on ->src_csets. After, on ->mg_tasks of * the csets on ->dst_csets. ->csets point to either ->src_csets * or ->dst_csets depending on whether migration is committed. * * ->cur_csets and ->cur_task point to the current task position * during iteration. */ struct list_head *csets; struct css_set *cur_cset; struct task_struct *cur_task; }; #define CGROUP_TASKSET_INIT(tset) (struct cgroup_taskset){ \ .src_csets = LIST_HEAD_INIT(tset.src_csets), \ .dst_csets = LIST_HEAD_INIT(tset.dst_csets), \ .csets = &tset.src_csets, \ } /** * cgroup_taskset_add - try to add a migration target task to a taskset * @task: target task * @tset: target taskset * * Add @task, which is a migration target, to @tset. This function becomes * noop if @task doesn't need to be migrated. @task's css_set should have * been added as a migration source and @task->cg_list will be moved from * the css_set's tasks list to mg_tasks one. */
static void cgroup_taskset_add(struct task_struct *task, struct cgroup_taskset *tset) { struct css_set *cset; lockdep_assert_held(&css_set_lock); /* @task either already exited or can't exit until the end */ if (task->flags & PF_EXITING) return; /* leave @task alone if post_fork() hasn't linked it yet */ if (list_empty(&task->cg_list)) return; cset = task_css_set(task); if (!cset->mg_src_cgrp) return; list_move_tail(&task->cg_list, &cset->mg_tasks); if (list_empty(&cset->mg_node)) list_add_tail(&cset->mg_node, &tset->src_csets); if (list_empty(&cset->mg_dst_cset->mg_node)) list_move_tail(&cset->mg_dst_cset->mg_node, &tset->dst_csets); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo127100.00%2100.00%
Total127100.00%2100.00%

/** * cgroup_taskset_first - reset taskset and return the first task * @tset: taskset of interest * @dst_cssp: output variable for the destination css * * @tset iteration is initialized and the first task is returned. */
struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp) { tset->cur_cset = list_first_entry(tset->csets, struct css_set, mg_node); tset->cur_task = NULL; return cgroup_taskset_next(tset, dst_cssp); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo4083.33%562.50%
paul menagepaul menage48.33%112.50%
al viroal viro36.25%112.50%
jeff liujeff liu12.08%112.50%
Total48100.00%8100.00%

/** * cgroup_taskset_next - iterate to the next task in taskset * @tset: taskset of interest * @dst_cssp: output variable for the destination css * * Return the next task in @tset. Iteration must have been initialized * with cgroup_taskset_first(). */
struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp) { struct css_set *cset = tset->cur_cset; struct task_struct *task = tset->cur_task; while (&cset->mg_node != tset->csets) { if (!task) task = list_first_entry(&cset->mg_tasks, struct task_struct, cg_list); else task = list_next_entry(task, cg_list); if (&task->cg_list != &cset->mg_tasks) { tset->cur_cset = cset; tset->cur_task = task; /* * This function may be called both before and * after cgroup_taskset_migrate(). The two cases * can be distinguished by looking at whether @cset * has its ->mg_dst_cset set. */ if (cset->mg_dst_cset) *dst_cssp = cset->mg_dst_cset->subsys[tset->ssid]; else *dst_cssp = cset->subsys[tset->ssid]; return task; } cset = list_next_entry(cset, mg_node); task = NULL; } return NULL; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo13082.28%880.00%
paul menagepaul menage2717.09%110.00%
kosaki motohirokosaki motohiro10.63%110.00%
Total158100.00%10100.00%

/** * cgroup_taskset_migrate - migrate a taskset * @tset: taget taskset * @root: cgroup root the migration is taking place on * * Migrate tasks in @tset as setup by migration preparation functions. * This function fails iff one of the ->can_attach callbacks fails and * guarantees that either all or none of the tasks in @tset are migrated. * @tset is consumed regardless of success. */
static int cgroup_taskset_migrate(struct cgroup_taskset *tset, struct cgroup_root *root) { struct cgroup_subsys *ss; struct task_struct *task, *tmp_task; struct css_set *cset, *tmp_cset; int ssid, failed_ssid, ret; /* methods shouldn't be called if no task is actually migrating */ if (list_empty(&tset->src_csets)) return 0; /* check that we can legitimately attach to the cgroup */ do_each_subsys_mask(ss, ssid, root->subsys_mask) { if (ss->can_attach) { tset->ssid = ssid; ret = ss->can_attach(tset); if (ret) { failed_ssid = ssid; goto out_cancel_attach; } } } while_each_subsys_mask(); /* * Now that we're guaranteed success, proceed to move all tasks to * the new cgroup. There are no failure cases after here, so this * is the commit point. */ spin_lock_irq(&css_set_lock); list_for_each_entry(cset, &tset->src_csets, mg_node) { list_for_each_entry_safe(task, tmp_task, &cset->mg_tasks, cg_list) { struct css_set *from_cset = task_css_set(task); struct css_set *to_cset = cset->mg_dst_cset; get_css_set(to_cset); css_set_move_task(task, from_cset, to_cset, true); put_css_set_locked(from_cset); } } spin_unlock_irq(&css_set_lock); /* * Migration is committed, all target tasks are now on dst_csets. * Nothing is sensitive to fork() after this point. Notify * controllers that migration is complete. */ tset->csets = &tset->dst_csets; do_each_subsys_mask(ss, ssid, root->subsys_mask) { if (ss->attach) { tset->ssid = ssid; ss->attach(tset); } } while_each_subsys_mask(); ret = 0; goto out_release_tset; out_cancel_attach: do_each_subsys_mask(ss, ssid, root->subsys_mask) { if (ssid == failed_ssid) break; if (ss->cancel_attach) { tset->ssid = ssid; ss->cancel_attach(tset); } } while_each_subsys_mask(); out_release_tset: spin_lock_irq(&css_set_lock); list_splice_init(&tset->dst_csets, &tset->src_csets); list_for_each_entry_safe(cset, tmp_cset, &tset->src_csets, mg_node) { list_splice_tail_init(&cset->mg_tasks, &cset->tasks); list_del_init(&cset->mg_node); } spin_unlock_irq(&css_set_lock); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo30589.71%861.54%
paul menagepaul menage216.18%215.38%
li zefanli zefan72.06%17.69%
daniel bristot de oliveiradaniel bristot de oliveira41.18%17.69%
ben blumben blum30.88%17.69%
Total340100.00%13100.00%

/** * cgroup_may_migrate_to - verify whether a cgroup can be migration destination * @dst_cgrp: destination cgroup to test * * On the default hierarchy, except for the root, subtree_control must be * zero for migration destination cgroups with tasks so that child cgroups * don't compete against tasks. */
static bool cgroup_may_migrate_to(struct cgroup *dst_cgrp) { return !cgroup_on_dfl(dst_cgrp) || !cgroup_parent(dst_cgrp) || !dst_cgrp->subtree_control; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo29100.00%1100.00%
Total29100.00%1100.00%

/** * cgroup_migrate_finish - cleanup after attach * @preloaded_csets: list of preloaded css_sets * * Undo cgroup_migrate_add_src() and cgroup_migrate_prepare_dst(). See * those functions for details. */
static void cgroup_migrate_finish(struct list_head *preloaded_csets) { struct css_set *cset, *tmp_cset; lockdep_assert_held(&cgroup_mutex); spin_lock_irq(&css_set_lock); list_for_each_entry_safe(cset, tmp_cset, preloaded_csets, mg_preload_node) { cset->mg_src_cgrp = NULL; cset->mg_dst_cgrp = NULL; cset->mg_dst_cset = NULL; list_del_init(&cset->mg_preload_node); put_css_set_locked(cset); } spin_unlock_irq(&css_set_lock); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo7796.25%880.00%
daniel bristot de oliveiradaniel bristot de oliveira22.50%110.00%
kirill a. shutemovkirill a. shutemov11.25%110.00%
Total80100.00%10100.00%

/** * cgroup_migrate_add_src - add a migration source css_set * @src_cset: the source css_set to add * @dst_cgrp: the destination cgroup * @preloaded_csets: list of preloaded css_sets * * Tasks belonging to @src_cset are about to be migrated to @dst_cgrp. Pin * @src_cset and add it to @preloaded_csets, which should later be cleaned * up by cgroup_migrate_finish(). * * 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, struct list_head *preloaded_csets) { struct cgroup *src_cgrp; lockdep_assert_held(&cgroup_mutex); lockdep_assert_held(&css_set_lock); /* * If ->dead, @src_set is associated with one or more dead cgroups * and doesn't contain any migratable tasks. Ignore it early so * that the rest of migration path doesn't get confused by it. */ if (src_cset->dead) return; src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root); if (!list_empty(&src_cset->mg_preload_node)) return; WARN_ON(src_cset->mg_src_cgrp); WARN_ON(src_cset->mg_dst_cgrp); WARN_ON(!list_empty(&src_cset->mg_tasks)); WARN_ON(!list_empty(&src_cset->mg_node)); src_cset->mg_src_cgrp = src_cgrp; src_cset->mg_dst_cgrp = dst_cgrp; get_css_set(src_cset); list_add(&src_cset->mg_preload_node, preloaded_csets); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo134100.00%4100.00%
Total134100.00%4100.00%

/** * cgroup_migrate_prepare_dst - prepare destination css_sets for migration * @preloaded_csets: list of preloaded source css_sets * * Tasks are about to be moved and all the source css_sets have been * preloaded to @preloaded_csets. This function looks up and pins all * destination css_sets, links each to its source, and append them to * @preloaded_csets. * * This function must be called after cgroup_migrate_add_src() has been * called on each migration source css_set. After migration is performed * using cgroup_migrate(), cgroup_migrate_finish() must be called on * @preloaded_csets. */
static int cgroup_migrate_prepare_dst(struct list_head *preloaded_csets) { LIST_HEAD(csets); struct css_set *src_cset, *tmp_cset; lockdep_assert_held(&cgroup_mutex); /* look up the dst cset for each src cset and link it to src */ list_for_each_entry_safe(src_cset, tmp_cset, preloaded_csets, mg_preload_node) { struct css_set *dst_cset; dst_cset = find_css_set(src_cset, src_cset->mg_dst_cgrp); if (!dst_cset) goto err; WARN_ON_ONCE(src_cset->mg_dst_cset || dst_cset->mg_dst_cset); /* * If src cset equals dst, it's noop. Drop the src. * cgroup_migrate() will skip the cset too. Note that we * can't handle src == dst as some nodes are used by both. */ if (src_cset == dst_cset) { src_cset->mg_src_cgrp = NULL; src_cset->mg_dst_cgrp = NULL; list_del_init(&src_cset->mg_preload_node); put_css_set(src_cset); put_css_set(dst_cset); continue; } src_cset->mg_dst_cset = dst_cset; if (list_empty(&dst_cset->mg_preload_node)) list_add(&dst_cset->mg_preload_node, &csets); else put_css_set(dst_cset); } list_splice_tail(&csets, preloaded_csets); return 0; err: cgroup_migrate_finish(&csets); return -ENOMEM; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo174100.00%6100.00%
Total174100.00%6100.00%

/** * cgroup_migrate - migrate a process or task to a cgroup * @leader: the leader of the process or the task to migrate * @threadgroup: whether @leader points to the whole process or a single task * @root: cgroup root migration is taking place on * * Migrate a process or task denoted by @leader. If migrating a 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(). * * As long as a controller's ->can_attach() doesn't fail, this function is * guaranteed to succeed. This means that, excluding ->can_attach() * failure, when migrating multiple targets, the success or failure can be * decided for all targets by invoking group_migrate_prepare_dst() before * actually starting migrating. */
static int cgroup_migrate(struct task_struct *leader, bool threadgroup, struct cgroup_root *root) { struct cgroup_taskset tset = CGROUP_TASKSET_INIT(tset); struct task_struct *task; /* * Prevent freeing of tasks while we take a snapshot. Tasks that are * already PF_EXITING could be freed from underneath us unless we * take an rcu_read_lock. */ spin_lock_irq(&css_set_lock); rcu_read_lock(); task = leader; do { cgroup_taskset_add(task, &tset); if (!threadgroup) break; } while_each_thread(leader, task);

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo3957.35%1055.56%
ben blumben blum1116.18%15.56%
li zefanli zefan913.24%15.56%
mandeep singh bainesmandeep singh baines57.35%211.11%
paul menagepaul menage34.41%316.67%
daniel bristot de oliveiradaniel bristot de oliveira11.47%15.56%
Total68100.00%18100.00%

rcu_read_unlock(); spin_unlock_irq(&css_set_lock); return cgroup_taskset_migrate(&tset, root); } /** * cgroup_attach_task - attach a task or a whole threadgroup to a cgroup * @dst_cgrp: the cgroup to attach to * @leader: the task or the leader of the threadgroup to be attached * @threadgroup: attach the whole threadgroup? * * Call holding cgroup_mutex and cgroup_threadgroup_rwsem. */
static int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader, bool threadgroup) { LIST_HEAD(preloaded_csets); struct task_struct *task; int ret; if (!cgroup_may_migrate_to(dst_cgrp)) return -EBUSY; /* look up all src csets */ spin_lock_irq(&css_set_lock); rcu_read_lock(); task = leader; do { cgroup_migrate_add_src(task_css_set(task), dst_cgrp, &preloaded_csets); if (!threadgroup) break; } while_each_thread(leader, task);

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo4857.14%555.56%
ben blumben blum3035.71%222.22%
li zefanli zefan55.95%111.11%
daniel bristot de oliveiradaniel bristot de oliveira11.19%111.11%
Total84100.00%9100.00%

rcu_read_unlock(); spin_unlock_irq(&css_set_lock); /* prepare dst csets and commit */ ret = cgroup_migrate_prepare_dst(&preloaded_csets); if (!ret) ret = cgroup_migrate(leader, threadgroup, dst_cgrp->root); cgroup_migrate_finish(&preloaded_csets); 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; spin_lock_irq(&css_set_lock); cgrp = task_cgroup_from_root(task, &cgrp_dfl_root); spin_unlock_irq(&css_set_lock); while (!cgroup_is_descendant(dst_cgrp, cgrp)) cgrp = cgroup_parent(cgrp); ret = -ENOMEM; inode = kernfs_get_inode(sb, cgrp->procs_file.kn); if (inode) { ret = inode_permission(inode, MAY_WRITE); iput(inode); } } put_cred(tcred); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo20899.05%480.00%
daniel bristot de oliveiradaniel bristot de oliveira20.95%120.00%
Total210100.00%5100.00%

/* * 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 * cgroup_mutex and threadgroup. */
static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off, bool threadgroup) { struct task_struct *tsk; struct cgroup_subsys *ss; struct cgroup *cgrp; pid_t pid; int ssid, ret; if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0) return -EINVAL; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENODEV; percpu_down_write(&cgroup_threadgroup_rwsem); rcu_read_lock(); if (pid) { tsk = find_task_by_vpid(pid); if (!tsk) { ret = -ESRCH; goto out_unlock_rcu; } } else { tsk = current; } if (threadgroup) tsk = tsk->group_leader; /* * Workqueue threads may acquire PF_NO_SETAFFINITY and become * trapped in a cpuset, or RT worker may be born in a cgroup * with no rt_runtime allocated. Just say no. */ if (tsk == kthreadd_task || (tsk->flags & PF_NO_SETAFFINITY)) { ret = -EINVAL; goto out_unlock_rcu; } get_task_struct(tsk); rcu_read_unlock(); ret = cgroup_procs_write_permission(tsk, cgrp, of); if (!ret) ret = cgroup_attach_task(cgrp, tsk, threadgroup); put_task_struct(tsk); goto out_unlock_threadgroup; out_unlock_rcu: rcu_read_unlock(); out_unlock_threadgroup: percpu_up_write(&cgroup_threadgroup_rwsem); for_each_subsys(ss, ssid) if (ss->post_attach) ss->post_attach(); cgroup_kn_unlock(of->kn); return ret ?: nbytes; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo19576.47%1361.90%
ben blumben blum3212.55%14.76%
paul menagepaul menage207.84%419.05%
mandeep singh bainesmandeep singh baines41.57%14.76%
pavel emelianovpavel emelianov20.78%14.76%
daisuke nishimuradaisuke nishimura20.78%14.76%
Total255100.00%21100.00%

/** * cgroup_attach_task_all - attach task 'tsk' to all cgroups of task 'from' * @from: attach to all cgroups of a given task * @tsk: the task to be attached */
int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) { struct cgroup_root *root; int retval = 0; mutex_lock(&cgroup_mutex); for_each_root(root) { struct cgroup *from_cgrp; if (root == &cgrp_dfl_root) continue; spin_lock_irq(&css_set_lock); from_cgrp = task_cgroup_from_root(from, root); spin_unlock_irq(&css_set_lock); retval = cgroup_attach_task(from_cgrp, tsk, false); if (retval) break; } mutex_unlock(&cgroup_mutex); return retval; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo9295.83%675.00%
li zefanli zefan22.08%112.50%
daniel bristot de oliveiradaniel bristot de oliveira22.08%112.50%
Total96100.00%8100.00%

EXPORT_SYMBOL_GPL(cgroup_attach_task_all);
static ssize_t cgroup_tasks_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return __cgroup_procs_write(of, buf, nbytes, off, false); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo1748.57%133.33%
paul menagepaul menage1337.14%133.33%
ben blumben blum514.29%133.33%
Total35100.00%3100.00%


static ssize_t cgroup_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return __cgroup_procs_write(of, buf, nbytes, off, true); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo1645.71%125.00%
ben blumben blum1234.29%125.00%
paul menagepaul menage617.14%125.00%
mandeep singh bainesmandeep singh baines12.86%125.00%
Total35100.00%4100.00%


static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup *cgrp; BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX); cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENODEV; spin_lock(&release_agent_path_lock); strlcpy(cgrp->root->release_agent_path, strstrip(buf), sizeof(cgrp->root->release_agent_path)); spin_unlock(&release_agent_path_lock); cgroup_kn_unlock(of->kn); return nbytes; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo6360.00%866.67%
paul menagepaul menage4240.00%433.33%
Total105100.00%12100.00%


static int cgroup_release_agent_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; spin_lock(&release_agent_path_lock); seq_puts(seq, cgrp->root->release_agent_path); spin_unlock(&release_agent_path_lock); seq_putc(seq, '\n'); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage3456.67%125.00%
tejun heotejun heo2643.33%375.00%
Total60100.00%4100.00%


static int cgroup_sane_behavior_show(struct seq_file *seq, void *v) { seq_puts(seq, "0\n"); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage1664.00%125.00%
tejun heotejun heo936.00%375.00%
Total25100.00%4100.00%


static void cgroup_print_ss_mask(struct seq_file *seq, u16 ss_mask) { struct cgroup_subsys *ss; bool printed = false; int ssid; do_each_subsys_mask(ss, ssid, ss_mask) { if (printed) seq_putc(seq, ' '); seq_printf(seq, "%s", ss->name); printed = true; } while_each_subsys_mask(); if (printed) seq_putc(seq, '\n'); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo4153.25%444.44%
paul menagepaul menage3444.16%333.33%
aleksa saraialeksa sarai11.30%111.11%
kosaki motohirokosaki motohiro11.30%111.11%
Total77100.00%9100.00%

/* show controllers which are enabled from the parent */
static int cgroup_controllers_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; cgroup_print_ss_mask(seq, cgroup_control(cgrp)); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo40100.00%3100.00%
Total40100.00%3100.00%

/* show controllers which are enabled for a given cgroup's children */
static int cgroup_subtree_control_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; cgroup_print_ss_mask(seq, cgrp->subtree_control); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo39100.00%2100.00%
Total39100.00%2100.00%

/** * cgroup_update_dfl_csses - update css assoc of a subtree in default hierarchy * @cgrp: root of the subtree to update csses for * * @cgrp's control masks have changed and its subtree's css associations * need to be updated accordingly. This function looks up all css_sets * which are attached to the subtree, creates the matching updated css_sets * and migrates the tasks to the new ones. */
static int cgroup_update_dfl_csses(struct cgroup *cgrp) { LIST_HEAD(preloaded_csets); struct cgroup_taskset tset = CGROUP_TASKSET_INIT(tset); struct cgroup_subsys_state *d_css; struct cgroup *dsct; struct css_set *src_cset; int ret; lockdep_assert_held(&cgroup_mutex); percpu_down_write(&cgroup_threadgroup_rwsem); /* look up all csses currently attached to @cgrp's subtree */ spin_lock_irq(&css_set_lock); cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { struct cgrp_cset_link *link; list_for_each_entry(link, &dsct->cset_links, cset_link) cgroup_migrate_add_src(link->cset, dsct, &preloaded_csets); } spin_unlock_irq(&css_set_lock); /* NULL dst indicates self on default hierarchy */ ret = cgroup_migrate_prepare_dst(&preloaded_csets); if (ret) goto out_finish; spin_lock_irq(&css_set_lock); list_for_each_entry(src_cset, &preloaded_csets, mg_preload_node) { struct task_struct *task, *ntask; /* src_csets precede dst_csets, break on the first dst_cset */ if (!src_cset->mg_src_cgrp) break; /* all tasks in src_csets need to be migrated */ list_for_each_entry_safe(task, ntask, &src_cset->tasks, cg_list) cgroup_taskset_add(task, &tset); } spin_unlock_irq(&css_set_lock); ret = cgroup_taskset_migrate(&tset, cgrp->root); out_finish: cgroup_migrate_finish(&preloaded_csets); percpu_up_write(&cgroup_threadgroup_rwsem); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo20298.06%888.89%
daniel bristot de oliveiradaniel bristot de oliveira41.94%111.11%
Total206100.00%9100.00%

/** * cgroup_lock_and_drain_offline - lock cgroup_mutex and drain offlined csses * @cgrp: root of the target subtree * * Because css offlining is asynchronous, userland may try to re-enable a * controller while the previous css is still around. This function grabs * cgroup_mutex and drains the previous css instances of @cgrp's subtree. */
static void cgroup_lock_and_drain_offline(struct cgroup *cgrp) __acquires(&cgroup_mutex

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo12100.00%2100.00%
Total12100.00%2100.00%

) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; struct cgroup_subsys *ss; int ssid; restart: mutex_lock(&cgroup_mutex); cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) { for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cgroup_css(dsct, ss); DEFINE_WAIT(wait); if (!css || !percpu_ref_is_dying(&css->refcnt)) continue; cgroup_get(dsct); prepare_to_wait(&dsct->offline_waitq, &wait, TASK_UNINTERRUPTIBLE); mutex_unlock(&cgroup_mutex); schedule(); finish_wait(&dsct->offline_waitq, &wait); cgroup_put(dsct); goto restart; } } } /** * cgroup_save_control - save control masks of a subtree * @cgrp: root of the target subtree * * Save ->subtree_control and ->subtree_ss_mask to the respective old_ * prefixed fields for @cgrp's subtree including @cgrp itself. */
static void cgroup_save_control(struct cgroup *cgrp) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { dsct->old_subtree_control = dsct->subtree_control; dsct->old_subtree_ss_mask = dsct->subtree_ss_mask; } }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo47100.00%1100.00%
Total47100.00%1100.00%

/** * cgroup_propagate_control - refresh control masks of a subtree * @cgrp: root of the target subtree * * For @cgrp and its subtree, ensure ->subtree_ss_mask matches * ->subtree_control and propagate controller availability through the * subtree so that descendants don't have unavailable controllers enabled. */
static void cgroup_propagate_control(struct cgroup *cgrp) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { dsct->subtree_control &= cgroup_control(dsct); dsct->subtree_ss_mask = cgroup_calc_subtree_ss_mask(dsct->subtree_control, cgroup_ss_mask(dsct)); } }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo56100.00%2100.00%
Total56100.00%2100.00%

/** * cgroup_restore_control - restore control masks of a subtree * @cgrp: root of the target subtree * * Restore ->subtree_control and ->subtree_ss_mask from the respective old_ * prefixed fields for @cgrp's subtree including @cgrp itself. */
static void cgroup_restore_control(struct cgroup *cgrp) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) { dsct->subtree_control = dsct->old_subtree_control; dsct->subtree_ss_mask = dsct->old_subtree_ss_mask; } }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo47100.00%1100.00%
Total47100.00%1100.00%


static bool css_visible(struct cgroup_subsys_state *css) { struct cgroup_subsys *ss = css->ss; struct cgroup *cgrp = css->cgroup; if (cgroup_control(cgrp) & (1 << ss->id)) return true; if (!(cgroup_ss_mask(cgrp) & (1 << ss->id))) return false; return cgroup_on_dfl(cgrp) && ss->implicit_on_dfl; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo78100.00%1100.00%
Total78100.00%1100.00%

/** * cgroup_apply_control_enable - enable or show csses according to control * @cgrp: root of the target subtree * * Walk @cgrp's subtree and create new csses or make the existing ones * visible. A css is created invisible if it's being implicitly enabled * through dependency. An invisible css is made visible when the userland * explicitly enables it. * * Returns 0 on success, -errno on failure. On failure, csses which have * been processed already aren't cleaned up. The caller is responsible for * cleaning up with cgroup_apply_control_disble(). */
static int cgroup_apply_control_enable(struct cgroup *cgrp) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; struct cgroup_subsys *ss; int ssid, ret; cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cgroup_css(dsct, ss); WARN_ON_ONCE(css && percpu_ref_is_dying(&css->refcnt)); if (!(cgroup_ss_mask(dsct) & (1 << ss->id))) continue; if (!css) { css = css_create(dsct, ss); if (IS_ERR(css)) return PTR_ERR(css); } if (css_visible(css)) { ret = css_populate_dir(css); if (ret) return ret; } } } return 0; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo148100.00%4100.00%
Total148100.00%4100.00%

/** * cgroup_apply_control_disable - kill or hide csses according to control * @cgrp: root of the target subtree * * Walk @cgrp's subtree and kill and hide csses so that they match * cgroup_ss_mask() and cgroup_visible_mask(). * * A css is hidden when the userland requests it to be disabled while other * subsystems are still depending on it. The css must not actively control * resources and be in the vanilla state if it's made visible again later. * Controllers which may be depended upon should provide ->css_reset() for * this purpose. */
static void cgroup_apply_control_disable(struct cgroup *cgrp) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; struct cgroup_subsys *ss; int ssid; cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) { for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cgroup_css(dsct, ss); WARN_ON_ONCE(css && percpu_ref_is_dying(&css->refcnt)); if (!css) continue; if (css->parent && !(cgroup_ss_mask(dsct) & (1 << ss->id))) { kill_css(css); } else if (!css_visible(css)) { css_clear_dir(css); if (ss->css_reset) ss->css_reset(css); } } } }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo136100.00%5100.00%
Total136100.00%5100.00%

/** * cgroup_apply_control - apply control mask updates to the subtree * @cgrp: root of the target subtree * * subsystems can be enabled and disabled in a subtree using the following * steps. * * 1. Call cgroup_save_control() to stash the current state. * 2. Update ->subtree_control masks in the subtree as desired. * 3. Call cgroup_apply_control() to apply the changes. * 4. Optionally perform other related operations. * 5. Call cgroup_finalize_control() to finish up. * * This function implements step 3 and propagates the mask changes * throughout @cgrp's subtree, updates csses accordingly and perform * process migrations. */
static int cgroup_apply_control(struct cgroup *cgrp) { int ret; cgroup_propagate_control(cgrp); ret = cgroup_apply_control_enable(cgrp); if (ret) return ret; /* * At this point, cgroup_e_css() results reflect the new csses * making the following cgroup_update_dfl_csses() properly update * css associations of all tasks in the subtree. */ ret = cgroup_update_dfl_csses(cgrp); if (ret) return ret; return 0; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo51100.00%1100.00%
Total51100.00%1100.00%

/** * cgroup_finalize_control - finalize control mask update * @cgrp: root of the target subtree * @ret: the result of the update * * Finalize control mask update. See cgroup_apply_control() for more info. */
static void cgroup_finalize_control(struct cgroup *cgrp, int ret) { if (ret) { cgroup_restore_control(cgrp); cgroup_propagate_control(cgrp); } cgroup_apply_control_disable(cgrp); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo35100.00%1100.00%
Total35100.00%1100.00%

/* change the enabled child controllers for a cgroup in the default hierarchy */
static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { u16 enable = 0, disable = 0; struct cgroup *cgrp, *child; struct cgroup_subsys *ss; char *tok; int ssid, ret; /* * Parse input - space separated list of subsystem names prefixed * with either + or -. */ buf = strstrip(buf); while ((tok = strsep(&buf, " "))) { if (tok[0] == '\0') continue; do_each_subsys_mask(ss, ssid, ~cgrp_dfl_inhibit_ss_mask) { if (!cgroup_ssid_enabled(ssid) || strcmp(tok + 1, ss->name)) continue; if (*tok == '+') { enable |= 1 << ssid; disable &= ~(1 << ssid); } else if (*tok == '-') { disable |= 1 << ssid; enable &= ~(1 << ssid); } else { return -EINVAL; } break; } while_each_subsys_mask(); if (ssid == CGROUP_SUBSYS_COUNT) return -EINVAL; } cgrp = cgroup_kn_lock_live(of->kn, true); if (!cgrp) return -ENODEV; for_each_subsys(ss, ssid) { if (enable & (1 << ssid)) { if (cgrp->subtree_control & (1 << ssid)) { enable &= ~(1 << ssid); continue; } if (!(cgroup_control(cgrp) & (1 << ssid))) { ret = -ENOENT; goto out_unlock; } } else if (disable & (1 << ssid)) { if (!(cgrp->subtree_control & (1 << ssid))) { disable &= ~(1 << ssid); continue; } /* a child has it enabled? */ cgroup_for_each_live_child(child, cgrp) { if (child->subtree_control & (1 << ssid)) { ret = -EBUSY; goto out_unlock; } } } } if (!enable && !disable) { ret = 0; goto out_unlock; } /* * Except for the root, subtree_control must be zero for a cgroup * with tasks so that child cgroups don't compete against tasks. */ if (enable && cgroup_parent(cgrp) && !list_empty(&cgrp->cset_links)) { ret = -EBUSY; goto out_unlock; } /* save and update control masks and prepare csses */ cgroup_save_control(cgrp); cgrp->subtree_control |= enable; cgrp->subtree_control &= ~disable; ret = cgroup_apply_control(cgrp); cgroup_finalize_control(cgrp, ret); kernfs_activate(cgrp->kn); ret = 0; out_unlock: cgroup_kn_unlock(of->kn); return ret ?: nbytes; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo45199.78%2195.45%
aleksa saraialeksa sarai10.22%14.55%
Total452100.00%22100.00%


static int cgroup_events_show(struct seq_file *seq, void *v) { seq_printf(seq, "populated %d\n", cgroup_is_populated(seq_css(seq)->cgroup)); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo2880.00%480.00%
paul menagepaul menage720.00%120.00%
Total35100.00%5100.00%


static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup *cgrp = of->kn->parent->priv; struct cftype *cft = of->kn->priv; struct cgroup_subsys_state *css; int ret; if (cft->write) return cft->write(of, buf, nbytes, off); /* * kernfs guarantees that a file isn't deleted with operations in * flight, which means that the matching css is and stays alive and * doesn't need to be pinned. The RCU locking is not necessary * either. It's just for the convenience of using cgroup_css(). */ rcu_read_lock(); css = cgroup_css(cgrp, cft->ss); rcu_read_unlock(); if (cft->write_u64) { unsigned long long v; ret = kstrtoull(buf, 0, &v); if (!ret) ret = cft->write_u64(css, cft, v); } else if (cft->write_s64) { long long v; ret = kstrtoll(buf, 0, &v); if (!ret) ret = cft->write_s64(css, cft, v); } else { ret = -EINVAL; } return ret ?: nbytes; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo10253.40%545.45%
paul menagepaul menage8343.46%327.27%
pavel emelianovpavel emelianov42.09%19.09%
li zefanli zefan10.52%19.09%
kosaki motohirokosaki motohiro10.52%19.09%
Total191100.00%11100.00%


static void *cgroup_seqfile_start(struct seq_file *seq, loff_t *ppos) { return seq_cft(seq)->seq_start(seq, ppos); }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage1862.07%133.33%
tejun heotejun heo1137.93%266.67%
Total29100.00%3100.00%


static void *cgroup_seqfile_next(struct seq_file *seq, void *v, loff_t *ppos) { return seq_cft(seq)->seq_next(seq, v, ppos); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo2674.29%125.00%
pavel emelianovpavel emelianov617.14%125.00%
paul menagepaul menage38.57%250.00%
Total35100.00%4100.00%


static void cgroup_seqfile_stop(struct seq_file *seq, void *v) { seq_cft(seq)->seq_stop(seq, v); }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage1451.85%150.00%
tejun heotejun heo1348.15%150.00%
Total27100.00%2100.00%


static int cgroup_seqfile_show(struct seq_file *m, void *arg) { struct cftype *cft = seq_cft(m); struct cgroup_subsys_state *css = seq_css(m); if (cft->seq_show) return cft->seq_show(m, arg); if (cft->read_u64) seq_printf(m, "%llu\n", cft->read_u64(css, cft)); else if (cft->read_s64) seq_printf(m, "%lld\n", cft->read_s64(css, cft)); else return -EINVAL; return 0; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo5451.92%550.00%
paul menagepaul menage4543.27%440.00%
serge hallynserge hallyn54.81%110.00%
Total104100.00%10100.00%

static struct kernfs_ops cgroup_kf_single_ops = { .atomic_write_len = PAGE_SIZE, .write = cgroup_file_write, .seq_show = cgroup_seqfile_show, }; static struct kernfs_ops cgroup_kf_ops = { .atomic_write_len = PAGE_SIZE, .write = cgroup_file_write, .seq_start = cgroup_seqfile_start, .seq_next = cgroup_seqfile_next, .seq_stop = cgroup_seqfile_stop, .seq_show = cgroup_seqfile_show, }; /* * cgroup_rename - Only allow simple rename of directories in place. */
static int cgroup_rename(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name_str) { struct cgroup *cgrp = kn->priv; int ret; if (kernfs_type(kn) != KERNFS_DIR) return -ENOTDIR; if (kn->parent != new_parent) return -EIO; /* * This isn't a proper migration and its usefulness is very * limited. Disallow on the default hierarchy. */ if (cgroup_on_dfl(cgrp)) return -EPERM; /* * We're gonna grab cgroup_mutex which nests outside kernfs * active_ref. kernfs_rename() doesn't require active_ref * protection. Break them before grabbing cgroup_mutex. */ kernfs_break_active_protection(new_parent); kernfs_break_active_protection(kn); mutex_lock(&cgroup_mutex); ret = kernfs_rename(kn, new_parent, new_name_str); mutex_unlock(&cgroup_mutex); kernfs_unbreak_active_protection(kn); kernfs_unbreak_active_protection(new_parent); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo7160.68%1062.50%
paul menagepaul menage4437.61%531.25%
aristeu sergio rozanski filhoaristeu sergio rozanski filho21.71%16.25%
Total117100.00%16100.00%

/* set uid and gid of cgroup dirs and files to that of the creator */
static int cgroup_kn_set_ugid(struct kernfs_node *kn) { struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID, .ia_uid = current_fsuid(), .ia_gid = current_fsgid(), }; if (uid_eq(iattr.ia_uid, GLOBAL_ROOT_UID) && gid_eq(iattr.ia_gid, GLOBAL_ROOT_GID)) return 0; return kernfs_setattr(kn, &iattr); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo68100.00%1100.00%
Total68100.00%1100.00%


static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp, struct cftype *cft) { char name[CGROUP_FILE_NAME_MAX]; struct kernfs_node *kn; struct lock_class_key *key = NULL; int ret; #ifdef CONFIG_DEBUG_LOCK_ALLOC key = &cft->lockdep_key; #endif kn = __kernfs_create_file(cgrp->kn, cgroup_file_name(cgrp, cft, name), cgroup_file_mode(cft), 0, cft->kf_ops, cft, NULL, key); if (IS_ERR(kn)) return PTR_ERR(kn); ret = cgroup_kn_set_ugid(kn); if (ret) { kernfs_remove(kn); return ret; } if (cft->file_offset) { struct cgroup_file *cfile = (void *)css + cft->file_offset; spin_lock_irq(&cgroup_file_kn_lock); cfile->kn = kn; spin_unlock_irq(&cgroup_file_kn_lock); } return 0; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo12776.05%1161.11%
paul menagepaul menage2313.77%422.22%
li zefanli zefan116.59%211.11%
serge hallynserge hallyn63.59%15.56%
Total167100.00%18100.00%

/** * cgroup_addrm_files - add or remove files to a cgroup directory * @css: the target css * @cgrp: the target cgroup (usually css->cgroup) * @cfts: array of cftypes to be added * @is_add: whether to add or remove * * Depending on @is_add, add or remove files defined by @cfts on @cgrp. * For removals, this function never fails. */
static int cgroup_addrm_files(struct cgroup_subsys_state *css, struct cgroup *cgrp, struct cftype cfts[], bool is_add) { struct cftype *cft, *cft_end = NULL; int ret = 0; lockdep_assert_held(&cgroup_mutex); restart: for (cft = cfts; cft != cft_end && cft->name[0] != '\0'; cft++) { /* does cft->flags tell us to skip this file on @cgrp? */ if ((cft->flags & __CFTYPE_ONLY_ON_DFL) && !cgroup_on_dfl(cgrp)) continue; if ((cft->flags & __CFTYPE_NOT_ON_DFL) && cgroup_on_dfl(cgrp)) continue; if ((cft->flags & CFTYPE_NOT_ON_ROOT) && !cgroup_parent(cgrp)) continue; if ((cft->flags & CFTYPE_ONLY_ON_ROOT) && cgroup_parent(cgrp)) continue; if (is_add) { ret = cgroup_add_file(css, cgrp, cft); if (ret) { pr_warn("%s: failed to add %s, err=%d\n", __func__, cft->name, ret); cft_end = cft; is_add = false; goto restart; } } else { cgroup_rm_file(cgrp, cft); } } return ret; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo9447.47%1562.50%
paul menagepaul menage5527.78%416.67%
li zefanli zefan2512.63%312.50%
gao fenggao feng2110.61%14.17%
joe perchesjoe perches31.52%14.17%
Total198100.00%24100.00%


static int cgroup_apply_cftypes(struct cftype *cfts, bool is_add) { LIST_HEAD(pending); struct cgroup_subsys *ss = cfts[0].ss; struct cgroup *root = &ss->root->cgrp; struct cgroup_subsys_state *css; int ret = 0; lockdep_assert_held(&cgroup_mutex); /* add/rm files for all cgroups created before */ css_for_each_descendant_pre(css, cgroup_css(root, ss)) { struct cgroup *cgrp = css->cgroup; if (!(css->flags & CSS_VISIBLE)) continue; ret = cgroup_addrm_files(css, cgrp, cfts, is_add); if (ret) break; } if (is_add && !ret) kernfs_activate(root->kn); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo8870.97%1878.26%
aristeu sergio rozanski filhoaristeu sergio rozanski filho1713.71%14.35%
li zefanli zefan129.68%313.04%
paul menagepaul menage75.65%14.35%
Total124100.00%23100.00%


static void cgroup_exit_cftypes(struct cftype *cfts) { struct cftype *cft; for (cft = cfts; cft->name[0] != '\0'; cft++) { /* free copy for custom atomic_write_len, see init_cftypes() */ if (cft->max_write_len && cft->max_write_len != PAGE_SIZE) kfree(cft->kf_ops); cft->kf_ops = NULL; cft->ss = NULL; /* revert flags set by cgroup core while adding @cfts */ cft->flags &= ~(__CFTYPE_ONLY_ON_DFL | __CFTYPE_NOT_ON_DFL); } }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo6783.75%480.00%
aristeu sergio rozanski filhoaristeu sergio rozanski filho1316.25%120.00%
Total80100.00%5100.00%


static int cgroup_init_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { struct cftype *cft; for (cft = cfts; cft->name[0] != '\0'; cft++) { struct kernfs_ops *kf_ops; WARN_ON(cft->ss || cft->kf_ops); if (cft->seq_start) kf_ops = &cgroup_kf_ops; else kf_ops = &cgroup_kf_single_ops; /* * Ugh... if @cft wants a custom max_write_len, we need to * make a copy of kf_ops to set its atomic_write_len. */ if (cft->max_write_len && cft->max_write_len != PAGE_SIZE) { kf_ops = kmemdup(kf_ops, sizeof(*kf_ops), GFP_KERNEL); if (!kf_ops) { cgroup_exit_cftypes(cfts); return -ENOMEM; } kf_ops->atomic_write_len = cft->max_write_len; } cft->kf_ops = kf_ops; cft->ss = ss; } return 0; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo10170.63%350.00%
paul menagepaul menage3020.98%116.67%
aristeu sergio rozanski filhoaristeu sergio rozanski filho117.69%116.67%
nick pigginnick piggin10.70%116.67%
Total143100.00%6100.00%


static int cgroup_rm_cftypes_locked(struct cftype *cfts) { lockdep_assert_held(&cgroup_mutex); if (!cfts || !cfts[0].ss) return -ENOENT; list_del(&cfts->node); cgroup_apply_cftypes(cfts, false); cgroup_exit_cftypes(cfts); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo4985.96%685.71%
paul menagepaul menage814.04%114.29%
Total57100.00%7100.00%

/** * cgroup_rm_cftypes - remove an array of cftypes from a subsystem * @cfts: zero-length name terminated array of cftypes * * Unregister @cfts. Files described by @cfts are removed from all * existing cgroups and all future cgroups won't have them either. This * function can be called anytime whether @cfts' subsys is attached or not. * * Returns 0 on successful unregistration, -ENOENT if @cfts is not * registered. */
int cgroup_rm_cftypes(struct cftype *cfts) { int ret; mutex_lock(&cgroup_mutex); ret = cgroup_rm_cftypes_locked(cfts); mutex_unlock(&cgroup_mutex); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo2365.71%250.00%
paul menagepaul menage1131.43%125.00%
aristeu sergio rozanski filhoaristeu sergio rozanski filho12.86%125.00%
Total35100.00%4100.00%

/** * cgroup_add_cftypes - add an array of cftypes to a subsystem * @ss: target cgroup subsystem * @cfts: zero-length name terminated array of cftypes * * Register @cfts to @ss. Files described by @cfts are created for all * existing cgroups to which @ss is attached and all future cgroups will * have them too. This function can be called anytime whether @ss is * attached or not. * * Returns 0 on successful registration, -errno on failure. Note that this * function currently returns 0 as long as @cfts registration is successful * even if some file creation attempts on existing cgroups fail. */
static int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { int ret; if (!cgroup_ssid_enabled(ss->id)) return 0; if (!cfts || cfts[0].name[0] == '\0') return 0; ret = cgroup_init_cftypes(ss, cfts); if (ret) return ret; mutex_lock(&cgroup_mutex); list_add_tail(&cfts->node, &ss->cfts); ret = cgroup_apply_cftypes(cfts, true); if (ret) cgroup_rm_cftypes_locked(cfts); mutex_unlock(&cgroup_mutex); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo6758.77%1178.57%
li zefanli zefan4741.23%321.43%
Total114100.00%14100.00%

/** * cgroup_add_dfl_cftypes - add an array of cftypes for default hierarchy * @ss: target cgroup subsystem * @cfts: zero-length name terminated array of cftypes * * Similar to cgroup_add_cftypes() but the added files are only used for * the default hierarchy. */
int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { struct cftype *cft; for (cft = cfts; cft && cft->name[0] != '\0'; cft++) cft->flags |= __CFTYPE_ONLY_ON_DFL; return cgroup_add_cftypes(ss, cfts); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo54100.00%2100.00%
Total54100.00%2100.00%

/** * cgroup_add_legacy_cftypes - add an array of cftypes for legacy hierarchies * @ss: target cgroup subsystem * @cfts: zero-length name terminated array of cftypes * * Similar to cgroup_add_cftypes() but the added files are only used for * the legacy hierarchies. */
int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { struct cftype *cft; for (cft = cfts; cft && cft->name[0] != '\0'; cft++) cft->flags |= __CFTYPE_NOT_ON_DFL; return cgroup_add_cftypes(ss, cfts); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo54100.00%3100.00%
Total54100.00%3100.00%

/** * cgroup_file_notify - generate a file modified event for a cgroup_file * @cfile: target cgroup_file * * @cfile must have been obtained by setting cftype->file_offset. */
void cgroup_file_notify(struct cgroup_file *cfile) { unsigned long flags; spin_lock_irqsave(&cgroup_file_kn_lock, flags); if (cfile->kn) kernfs_notify(cfile->kn); spin_unlock_irqrestore(&cgroup_file_kn_lock, flags); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo43100.00%1100.00%
Total43100.00%1100.00%

/** * cgroup_task_count - count the number of tasks in a cgroup. * @cgrp: the cgroup in question * * Return the number of tasks in the cgroup. */
static int cgroup_task_count(const struct cgroup *cgrp) { int count = 0; struct cgrp_cset_link *link; spin_lock_irq(&css_set_lock); list_for_each_entry(link, &cgrp->cset_links, cset_link) count += atomic_read(&link->cset->refcount); spin_unlock_irq(&css_set_lock); return count; }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage4070.18%333.33%
tejun heotejun heo1221.05%444.44%
kosaki motohirokosaki motohiro35.26%111.11%
daniel bristot de oliveiradaniel bristot de oliveira23.51%111.11%
Total57100.00%9100.00%

/** * css_next_child - find the next child of a given css * @pos: the current position (%NULL to initiate traversal) * @parent: css whose children to walk * * This function returns the next child of @parent and should be called * under either cgroup_mutex or RCU read lock. The only requirement is * that @parent and @pos are accessible. The next sibling is guaranteed to * be returned regardless of their states. * * 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. */
struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *parent) { struct cgroup_subsys_state *next; cgroup_assert_mutex_or_rcu_locked(); /* * @pos could already have been unlinked from the sibling list. * Once a cgroup is removed, its ->sibling.next is no longer * updated when its next sibling changes. CSS_RELEASED is set when * @pos is taken off list, at which time its next pointer is valid, * and, as releases are serialized, the one pointed to by the next * pointer is guaranteed to not have started release yet. This * implies that if we observe !CSS_RELEASED on @pos in this RCU * critical section, the one pointed to by its next pointer is * guaranteed to not have finished its RCU grace period even if we * have dropped rcu_read_lock() inbetween iterations. * * If @pos has CSS_RELEASED set, its next pointer can't be * dereferenced; however, as each css is given a monotonically * increasing unique serial number and always appended to the * sibling list, the next one can be found by walking the parent's * children until the first css with higher serial number than * @pos's. While this path can be slower, it happens iff iteration * races against release and the race window is very small. */ if (!pos) { next = list_entry_rcu(parent->children.next, struct cgroup_subsys_state, sibling); } else if (likely(!(pos->flags & CSS_RELEASED))) { next = list_entry_rcu(pos->sibling.next, struct cgroup_subsys_state, sibling); } else { list_for_each_entry_rcu(next, &parent->children, sibling) if (next->serial_nr > pos->serial_nr) break; } /* * @next, if not pointing to the head, can be dereferenced and is * the next sibling. */ if (&next->sibling != &parent->children) return next; return NULL; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo9879.67%866.67%
paul menagepaul menage1411.38%216.67%
li zefanli zefan118.94%216.67%
Total123100.00%12100.00%

/** * css_next_descendant_pre - find the next descendant for pre-order walk * @pos: the current position (%NULL to initiate traversal) * @root: css whose descendants to walk * * To be used by css_for_each_descendant_pre(). Find the next descendant * to visit for pre-order traversal of @root's descendants. @root is * included in the iteration and the first node to be visited. * * While this function requires cgroup_mutex or RCU read locking, it * doesn't require the whole traversal to be contained in a single critical * section. This function will return the correct next descendant as long * as both @pos and @root are accessible and @pos is a descendant of @root. * * 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. */
struct cgroup_subsys_state * css_next_descendant_pre(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *root) { struct cgroup_subsys_state *next; cgroup_assert_mutex_or_rcu_locked(); /* if first iteration, visit @root */ if (!pos) return root; /* visit the first child if exists */ next = css_next_child(NULL, pos); if (next) return next; /* no child, visit my or the closest ancestor's next sibling */ while (pos != root) { next = css_next_child(pos, pos->parent); if (next) return next; pos = pos->parent; } return NULL; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo6170.11%1173.33%
paul menagepaul menage1921.84%213.33%
gao fenggao feng55.75%16.67%
li zefanli zefan22.30%16.67%
Total87100.00%15100.00%

/** * css_rightmost_descendant - return the rightmost descendant of a css * @pos: css of interest * * Return the rightmost descendant of @pos. If there's no descendant, @pos * is returned. This can be used during pre-order traversal to skip * subtree of @pos. * * While this function requires cgroup_mutex or RCU read locking, it * doesn't require the whole traversal to be contained in a single critical * section. This function will return the correct rightmost descendant as * long as @pos is accessible. */
struct cgroup_subsys_state * css_rightmost_descendant(struct cgroup_subsys_state *pos) { struct cgroup_subsys_state *last, *tmp; cgroup_assert_mutex_or_rcu_locked(); do { last = pos; /* ->prev isn't RCU safe, walk ->next till the end */ pos = NULL; css_for_each_child(tmp, last) pos = tmp; } while (pos); return last; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo53100.00%5100.00%
Total53100.00%5100.00%


static struct cgroup_subsys_state * css_leftmost_descendant(struct cgroup_subsys_state *pos) { struct cgroup_subsys_state *last; do { last = pos; pos = css_next_child(NULL, pos); } while (pos); return last; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo42100.00%5100.00%
Total42100.00%5100.00%

/** * css_next_descendant_post - find the next descendant for post-order walk * @pos: the current position (%NULL to initiate traversal) * @root: css whose descendants to walk * * To be used by css_for_each_descendant_post(). Find the next descendant * to visit for post-order traversal of @root's descendants. @root is * included in the iteration and the last node to be visited. * * While this function requires cgroup_mutex or RCU read locking, it * doesn't require the whole traversal to be contained in a single critical * section. This function will return the correct next descendant as long * as both @pos and @cgroup are accessible and @pos is a descendant of * @cgroup. * * 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. */
struct cgroup_subsys_state * css_next_descendant_post(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *root) { struct cgroup_subsys_state *next; cgroup_assert_mutex_or_rcu_locked(); /* if first iteration, visit leftmost descendant which may be @root */ if (!pos) return css_leftmost_descendant(root); /* if we visited @root, we're done */ if (pos == root) return NULL; /* if there's an unvisited sibling, visit its leftmost descendant */ next = css_next_child(pos, pos->parent); if (next) return css_leftmost_descendant(next); /* no sibling left, visit parent */ return pos->parent; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo6586.67%981.82%
li zefanli zefan1013.33%218.18%
Total75100.00%11100.00%

/** * css_has_online_children - does a css have online children * @css: the target css * * Returns %true if @css has any online children; otherwise, %false. This * function can be called from any context but the caller is responsible * for synchronizing against on/offlining as necessary. */
bool css_has_online_children(struct cgroup_subsys_state *css) { struct cgroup_subsys_state *child; bool ret = false; rcu_read_lock(); css_for_each_child(child, css) { if (child->flags & CSS_ONLINE) { ret = true; break; } } rcu_read_unlock(); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo5198.08%583.33%
li zefanli zefan11.92%116.67%
Total52100.00%6100.00%

/** * css_task_iter_advance_css_set - advance a task itererator to the next css_set * @it: the iterator to advance * * Advance @it to the next css_set to walk. */
static void css_task_iter_advance_css_set(struct css_task_iter *it) { struct list_head *l = it->cset_pos; struct cgrp_cset_link *link; struct css_set *cset; lockdep_assert_held(&css_set_lock); /* Advance to the next non-empty css_set */ do { l = l->next; if (l == it->cset_head) { it->cset_pos = NULL; it->task_pos = NULL; return; } if (it->ss) { cset = container_of(l, struct css_set, e_cset_node[it->ss->id]); } else { link = list_entry(l, struct cgrp_cset_link, cset_link); cset = link->cset; } } while (!css_set_populated(cset)); it->cset_pos = l; if (!list_empty(&cset->tasks)) it->task_pos = cset->tasks.next; else it->task_pos = cset->mg_tasks.next; it->tasks_head = &cset->tasks; it->mg_tasks_head = &cset->mg_tasks; /* * We don't keep css_sets locked across iteration steps and thus * need to take steps to ensure that iteration can be resumed after * the lock is re-acquired. Iteration is performed at two levels - * css_sets and tasks in them. * * Once created, a css_set never leaves its cgroup lists, so a * pinned css_set is guaranteed to stay put and we can resume * iteration afterwards. * * Tasks may leave @cset across iteration steps. This is resolved * by registering each iterator with the css_set currently being * walked and making css_set_move_task() advance iterators whose * next task is leaving. */ if (it->cur_cset) { list_del(&it->iters_node); put_css_set_locked(it->cur_cset); } get_css_set(cset); it->cur_cset = cset; list_add(&it->iters_node, &cset->task_iters); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo21493.04%1477.78%
cliff wickmancliff wickman62.61%15.56%
li zefanli zefan52.17%15.56%
paul menagepaul menage52.17%211.11%
Total230100.00%18100.00%


static void css_task_iter_advance(struct css_task_iter *it) { struct list_head *l = it->task_pos; lockdep_assert_held(&css_set_lock); WARN_ON_ONCE(!l); /* * Advance iterator to find next entry. cset->tasks is consumed * first and then ->mg_tasks. After ->mg_tasks, we move onto the * next cset. */ l = l->next; if (l == it->tasks_head) l = it->mg_tasks_head->next; if (l == it->mg_tasks_head) css_task_iter_advance_css_set(it); else it->task_pos = l; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo75100.00%3100.00%
Total75100.00%3100.00%

/** * css_task_iter_start - initiate task iteration * @css: the css to walk tasks of * @it: the task iterator to use * * Initiate iteration through the tasks of @css. The caller can call * css_task_iter_next() to walk through the tasks until the function * returns NULL. On completion of iteration, css_task_iter_end() must be * called. */
void css_task_iter_start(struct cgroup_subsys_state *css, struct css_task_iter *it) { /* no one should try to iterate before mounting cgroups */ WARN_ON_ONCE(!use_task_css_set_links); memset(it, 0, sizeof(*it)); spin_lock_irq(&css_set_lock); it->ss = css->ss; if (it->ss) it->cset_pos = &css->cgroup->e_csets[css->ss->id]; else it->cset_pos = &css->cgroup->cset_links; it->cset_head = it->cset_pos; css_task_iter_advance_css_set(it); spin_unlock_irq(&css_set_lock); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo7975.96%1168.75%
paul menagepaul menage109.62%212.50%
cliff wickmancliff wickman109.62%16.25%
li zefanli zefan32.88%16.25%
daniel bristot de oliveiradaniel bristot de oliveira21.92%16.25%
Total104100.00%16100.00%

/** * css_task_iter_next - return the next task for the iterator * @it: the task iterator being iterated * * The "next" function for task iteration. @it should have been * initialized via css_task_iter_start(). Returns NULL when the iteration * reaches the end. */
struct task_struct *css_task_iter_next(struct css_task_iter *it) { if (it->cur_task) { put_task_struct(it->cur_task); it->cur_task = NULL; } spin_lock_irq(&css_set_lock); if (it->task_pos) { it->cur_task = list_entry(it->task_pos, struct task_struct, cg_list); get_task_struct(it->cur_task); css_task_iter_advance(it); } spin_unlock_irq(&css_set_lock); return it->cur_task; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo7587.21%770.00%
paul menagepaul menage910.47%220.00%
daniel bristot de oliveiradaniel bristot de oliveira22.33%110.00%
Total86100.00%10100.00%

/** * css_task_iter_end - finish task iteration * @it: the task iterator to finish * * Finish task iteration started by css_task_iter_start(). */
void css_task_iter_end(struct css_task_iter *it) { if (it->cur_cset) { spin_lock_irq(&css_set_lock); list_del(&it->iters_node); put_css_set_locked(it->cur_cset); spin_unlock_irq(&css_set_lock); } if (it->cur_task) put_task_struct(it->cur_task); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo5391.38%466.67%
paul menagepaul menage35.17%116.67%
daniel bristot de oliveiradaniel bristot de oliveira23.45%116.67%
Total58100.00%6100.00%

/** * cgroup_trasnsfer_tasks - move tasks from one cgroup to another * @to: cgroup to which the tasks will be moved * @from: cgroup in which the tasks currently reside * * Locking rules between cgroup_post_fork() and the migration path * guarantee that, if a task is forking while being migrated, the new child * is guaranteed to be either visible in the source cgroup after the * parent's migration is complete or put into the target cgroup. No task * can slip out of migration through forking. */
int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from) { LIST_HEAD(preloaded_csets); struct cgrp_cset_link *link; struct css_task_iter it; struct task_struct *task; int ret; if (!cgroup_may_migrate_to(to)) return -EBUSY; mutex_lock(&cgroup_mutex); /* all tasks in @from are being moved, all csets are source */ spin_lock_irq(&css_set_lock); list_for_each_entry(link, &from->cset_links, cset_link) cgroup_migrate_add_src(link->cset, to, &preloaded_csets); spin_unlock_irq(&css_set_lock); ret = cgroup_migrate_prepare_dst(&preloaded_csets); if (ret) goto out_err; /* * Migrate tasks one-by-one until @from is empty. This fails iff * ->can_attach() fails. */ do { css_task_iter_start(&from->self, &it); task = css_task_iter_next(&it); if (task) get_task_struct(task); css_task_iter_end(&it); if (task) { ret = cgroup_migrate(task, false, to->root); put_task_struct(task); } } while (task && !ret); out_err: cgroup_migrate_finish(&preloaded_csets); mutex_unlock(&cgroup_mutex); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo12666.32%1161.11%
paul menagepaul menage4925.79%211.11%
frederic weisbeckerfrederic weisbecker84.21%15.56%
kosaki motohirokosaki motohiro31.58%15.56%
daniel bristot de oliveiradaniel bristot de oliveira21.05%15.56%
rami rosenrami rosen10.53%15.56%
cliff wickmancliff wickman10.53%15.56%
Total190100.00%18100.00%

/* * Stuff for reading the 'tasks'/'procs' files. * * Reading this file can return large amounts of data if a cgroup has * *lots* of attached tasks. So it may need several calls to read(), * but we cannot guarantee that the information we produce is correct * unless we produce it entirely atomically. * */ /* which pidlist file are we talking about? */ enum cgroup_filetype { CGROUP_FILE_PROCS, CGROUP_FILE_TASKS, }; /* * A pidlist is a list of pids that virtually represents the contents of one * of the cgroup files ("procs" or "tasks"). We keep a list of such pidlists, * a pair (one each for procs, tasks) for each pid namespace that's relevant * to the cgroup. */ struct cgroup_pidlist { /* * used to find which pidlist is wanted. doesn't change as long as * this particular list stays in the list. */ struct { enum cgroup_filetype type; struct pid_namespace *ns; } key; /* array of xids */ pid_t *list; /* how many elements the above list has */ int length; /* each of these stored in a list by its cgroup */ struct list_head links; /* pointer to the cgroup we belong to, for list removal purposes */ struct cgroup *owner; /* for delayed destruction */ struct delayed_work destroy_dwork; }; /* * The following two functions "fix" the issue where there are more pids * than kmalloc will give memory for; in such cases, we use vmalloc/vfree. * TODO: replace with a kernel-wide solution to this problem */ #define PIDLIST_TOO_LARGE(c) ((c) * sizeof(pid_t) > (PAGE_SIZE * 2))
static void *pidlist_allocate(int count) { if (PIDLIST_TOO_LARGE(count)) return vmalloc(count * sizeof(pid_t)); else return kmalloc(count * sizeof(pid_t), GFP_KERNEL); }

Contributors

PersonTokensPropCommitsCommitProp
ben blumben blum3071.43%133.33%
tejun heotejun heo1228.57%266.67%
Total42100.00%3100.00%


static void pidlist_free(void *p) { kvfree(p); }

Contributors

PersonTokensPropCommitsCommitProp
ben blumben blum1066.67%125.00%
tejun heotejun heo426.67%250.00%
bandan dasbandan das16.67%125.00%
Total15100.00%4100.00%

/* * Used to destroy all pidlists lingering waiting for destroy timer. None * should be left afterwards. */
static void cgroup_pidlist_destroy_all(struct cgroup *cgrp) { struct cgroup_pidlist *l, *tmp_l; mutex_lock(&cgrp->pidlist_mutex); list_for_each_entry_safe(l, tmp_l, &cgrp->pidlists, links) mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, 0); mutex_unlock(&cgrp->pidlist_mutex); flush_workqueue(cgroup_pidlist_destroy_wq); BUG_ON(!list_empty(&cgrp->pidlists)); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo6993.24%466.67%
ben blumben blum45.41%116.67%
paul menagepaul menage11.35%116.67%
Total74100.00%6100.00%


static void cgroup_pidlist_destroy_work_fn(struct work_struct *work) { struct delayed_work *dwork = to_delayed_work(work); struct cgroup_pidlist *l = container_of(dwork, struct cgroup_pidlist, destroy_dwork); struct cgroup_pidlist *tofree = NULL; mutex_lock(&l->owner->pidlist_mutex); /* * Destroy iff we didn't get queued again. The state won't change * as destroy_dwork can only be queued while locked. */ if (!delayed_work_pending(dwork)) { list_del(&l->links); pidlist_free(l->list); put_pid_ns(l->key.ns); tofree = l; } mutex_unlock(&l->owner->pidlist_mutex); kfree(tofree); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo6661.68%457.14%
ben blumben blum3936.45%228.57%
eric w. biedermaneric w. biederman21.87%114.29%
Total107100.00%7100.00%

/* * pidlist_uniq - given a kmalloc()ed list, strip out all duplicate entries * Returns the number of unique elements. */
static int pidlist_uniq(pid_t *list, int length) { int src, dest = 1; /* * we presume the 0th element is unique, so i starts at 1. trivial * edge cases first; no work needs to be done for either */ if (length == 0 || length == 1) return length; /* src and dest walk down the list; dest counts unique elements */ for (src = 1; src < length; src++) { /* find next unique element */ while (list[src] == list[src-1]) { src++; if (src == length) goto after; } /* dest always points to where the next unique element goes */ list[dest] = list[src]; dest++; } after: return dest; }

Contributors

PersonTokensPropCommitsCommitProp
ben blumben blum7374.49%222.22%
tejun heotejun heo2121.43%333.33%
paul menagepaul menage22.04%222.22%
li zefanli zefan11.02%111.11%
gowrishankar mgowrishankar m11.02%111.11%
Total98100.00%9100.00%

/* * The two pid files - task and cgroup.procs - guaranteed that the result * is sorted, which forced this whole pidlist fiasco. As pid order is * different per namespace, each namespace needs differently sorted list, * making it impossible to use, for example, single rbtree of member tasks * sorted by task pointer. As pidlists can be fairly large, allocating one * per open file is dangerous, so cgroup had to implement shared pool of * pidlists keyed by cgroup and namespace. * * All this extra complexity was caused by the original implementation * committing to an entirely unnecessary property. In the long term, we * want to do away with it. Explicitly scramble sort order if on the * default hierarchy so that no such expectation exists in the new * interface. * * Scrambling is done by swapping every two consecutive bits, which is * non-identity one-to-one mapping which disturbs sort order sufficiently. */
static pid_t pid_fry(pid_t pid) { unsigned a = pid & 0x55555555; unsigned b = pid & 0xAAAAAAAA; return (a << 1) | (b >> 1); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo2775.00%233.33%
paul menagepaul menage411.11%233.33%
cliff wickmancliff wickman38.33%116.67%
ben blumben blum25.56%116.67%
Total36100.00%6100.00%


static pid_t cgroup_pid_fry(struct cgroup *cgrp, pid_t pid) { if (cgroup_on_dfl(cgrp)) return pid_fry(pid); else return pid; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo2477.42%342.86%
paul menagepaul menage722.58%457.14%
Total31100.00%7100.00%


static int cmppid(const void *a, const void *b) { return *(pid_t *)a - *(pid_t *)b; }

Contributors

PersonTokensPropCommitsCommitProp
ben blumben blum2477.42%120.00%
cliff wickmancliff wickman412.90%120.00%
paul menagepaul menage26.45%240.00%
kirill a. shutemovkirill a. shutemov13.23%120.00%
Total31100.00%5100.00%


static int fried_cmppid(const void *a, const void *b) { return pid_fry(*(pid_t *)a) - pid_fry(*(pid_t *)b); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo2259.46%116.67%
paul menagepaul menage924.32%350.00%
ben blumben blum410.81%116.67%
lai jiangshanlai jiangshan25.41%116.67%
Total37100.00%6100.00%


static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp, enum cgroup_filetype type) { struct cgroup_pidlist *l; /* don't need task_nsproxy() if we're looking at ourself */ struct pid_namespace *ns = task_active_pid_ns(current); lockdep_assert_held(&cgrp->pidlist_mutex); list_for_each_entry(l, &cgrp->pidlists, links) if (l->key.type == type && l->key.ns == ns) return l; return NULL; }

Contributors

PersonTokensPropCommitsCommitProp
ben blumben blum4054.79%116.67%
cliff wickmancliff wickman2230.14%116.67%
paul menagepaul menage68.22%233.33%
tejun heotejun heo34.11%116.67%
eric w. biedermaneric w. biederman22.74%116.67%
Total73100.00%6100.00%

/* * find the appropriate pidlist for our purpose (given procs vs tasks) * returns with the lock on that pidlist already held, and takes care * of the use count, or returns NULL with no locks held if we're out of * memory. */
static struct cgroup_pidlist *cgroup_pidlist_find_create(struct cgroup *cgrp, enum cgroup_filetype type) { struct cgroup_pidlist *l; lockdep_assert_held(&cgrp->pidlist_mutex); l = cgroup_pidlist_find(cgrp, type); if (l) return l; /* entry not found; create a new one */ l = kzalloc(sizeof(struct cgroup_pidlist), GFP_KERNEL); if (!l) return l; INIT_DELAYED_WORK(&l->destroy_dwork, cgroup_pidlist_destroy_work_fn); l->key.type = type; /* don't need task_nsproxy() if we're looking at ourself */ l->key.ns = get_pid_ns(task_active_pid_ns(current)); l->owner = cgrp; list_add(&l->links, &cgrp->pidlists); return l; }

Contributors

PersonTokensPropCommitsCommitProp
ben blumben blum4839.02%112.50%
tejun heotejun heo3528.46%450.00%
paul menagepaul menage2318.70%112.50%
cliff wickmancliff wickman1512.20%112.50%
li zefanli zefan21.63%112.50%
Total123100.00%8100.00%

/* * Load a cgroup's pidarray with either procs' tgids or tasks' pids */
static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, struct cgroup_pidlist **lp) { pid_t *array; int length; int pid, n = 0; /* used for populating the array */ struct css_task_iter it; struct task_struct *tsk; struct cgroup_pidlist *l; lockdep_assert_held(&cgrp->pidlist_mutex); /* * If cgroup gets more users after we read count, we won't have * enough space - tough. This race is indistinguishable to the * caller from the case that the additional cgroup users didn't * show up until sometime later on. */ length = cgroup_task_count(cgrp); array = pidlist_allocate(length); if (!array) return -ENOMEM; /* now, populate the array */ css_task_iter_start(&cgrp->self, &it); while ((tsk = css_task_iter_next(&it))) { if (unlikely(n == length)) break; /* get tgid or pid for procs or tasks file respectively */ if (type == CGROUP_FILE_PROCS) pid = task_tgid_vnr(tsk); else pid = task_pid_vnr(tsk); if (pid > 0) /* make sure to only use valid results */ array[n++] = pid; } css_task_iter_end(&it); length = n; /* now sort & (if procs) strip out duplicates */ if (cgroup_on_dfl(cgrp)) sort(array, length, sizeof(pid_t), fried_cmppid, NULL); else sort(array, length, sizeof(pid_t), cmppid, NULL); if (type == CGROUP_FILE_PROCS) length = pidlist_uniq(array, length); l = cgroup_pidlist_find_create(cgrp, type); if (!l) { pidlist_free(array); return -ENOMEM; } /* store array, freeing old if necessary */ pidlist_free(l->list); l->list = array; l->length = length; *lp = l; return 0; }

Contributors

PersonTokensPropCommitsCommitProp
cliff wickmancliff wickman9835.77%15.26%
ben blumben blum9735.40%315.79%
tejun heotejun heo3312.04%736.84%
paul menagepaul menage196.93%315.79%
li zefanli zefan134.74%210.53%
gowrishankar mgowrishankar m82.92%15.26%
kirill a. shutemovkirill a. shutemov62.19%210.53%
Total274100.00%19100.00%

/** * cgroupstats_build - build and fill cgroupstats * @stats: cgroupstats to fill information into * @dentry: A dentry entry belonging to the cgroup for which stats have * been requested. * * Build and fill cgroupstats so that taskstats can export it to user * space. */
int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) { struct kernfs_node *kn = kernfs_node_from_dentry(dentry); struct cgroup *cgrp; struct css_task_iter it; struct task_struct *tsk; /* it should be kernfs_node belonging to cgroupfs and is a directory */ if (dentry->d_sb->s_type != &cgroup_fs_type || !kn || kernfs_type(kn) != KERNFS_DIR) return -EINVAL; mutex_lock(&cgroup_mutex); /* * We aren't being called from kernfs and there's no guarantee on * @kn->priv's validity. For this and css_tryget_online_from_dir(), * @kn->priv is RCU safe. Let's do the RCU dancing. */ rcu_read_lock(); cgrp = rcu_dereference(kn->priv); if (!cgrp || cgroup_is_dead(cgrp)) { rcu_read_unlock(); mutex_unlock(&cgroup_mutex); return -ENOENT; } rcu_read_unlock(); css_task_iter_start(&cgrp->self, &it); while ((tsk = css_task_iter_next(&it))) { switch (tsk->state) { case TASK_RUNNING: stats->nr_running++; break; case TASK_INTERRUPTIBLE: stats->nr_sleeping++; break; case TASK_UNINTERRUPTIBLE: stats->nr_uninterruptible++; break; case TASK_STOPPED: stats->nr_stopped++; break; default: if (delayacct_is_task_waiting_on_io(tsk)) stats->nr_io_wait++; break; } } css_task_iter_end(&it); mutex_unlock(&cgroup_mutex); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
balbir singhbalbir singh7937.62%16.25%
tejun heotejun heo7033.33%743.75%
ben blumben blum2310.95%212.50%
kirill a. shutemovkirill a. shutemov209.52%16.25%
li zefanli zefan157.14%318.75%
cliff wickmancliff wickman20.95%16.25%
paul menagepaul menage10.48%16.25%
Total210100.00%16100.00%

/* * seq_file methods for the tasks/procs files. The seq_file position is the * next pid to display; the seq_file iterator is a pointer to the pid * in the cgroup->l->list array. */
static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos) { /* * Initially we receive a position value that corresponds to * one more than the last pid shown (or 0 on the first call or * after a seek to the start). Use a binary-search to find the * next pid to display, if any */ struct kernfs_open_file *of = s->private; struct cgroup *cgrp = seq_css(s)->cgroup; struct cgroup_pidlist *l; enum cgroup_filetype type = seq_cft(s)->private; int index = 0, pid = *pos; int *iter, ret; mutex_lock(&cgrp->pidlist_mutex); /* * !NULL @of->priv indicates that this isn't the first start() * after open. If the matching pidlist is around, we can use that. * Look for it. Note that @of->priv can't be used directly. It * could already have been destroyed. */ if (of->priv) of->priv = cgroup_pidlist_find(cgrp, type); /* * Either this is the first start() after open or the matching * pidlist has been destroyed inbetween. Create a new one. */ if (!of->priv) { ret = pidlist_array_load(cgrp, type, (struct cgroup_pidlist **)&of->priv); if (ret) return ERR_PTR(ret); } l = of->priv; if (pid) { int end = l->length; while (index < end) { int mid = (index + end) / 2; if (cgroup_pid_fry(cgrp, l->list[mid]) == pid) { index = mid; break; } else if (cgroup_pid_fry(cgrp, l->list[mid]) <= pid) index = mid + 1; else end = mid; } } /* If we're off the end of the array, we're done */ if (index >= l->length) return NULL; /* Update the abstract position to be the actual pid that we found */ iter = l->list + index; *pos = cgroup_pid_fry(cgrp, *iter); return iter; }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage8532.69%420.00%
tejun heotejun heo7830.00%945.00%
ben blumben blum5922.69%210.00%
kirill a. shutemovkirill a. shutemov3312.69%15.00%
li zefanli zefan20.77%210.00%
eric w. biedermaneric w. biederman20.77%15.00%
gowrishankar mgowrishankar m10.38%15.00%
Total260100.00%20100.00%


static void cgroup_pidlist_stop(struct seq_file *s, void *v) { struct kernfs_open_file *of = s->private; struct cgroup_pidlist *l = of->priv; if (l) mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, CGROUP_PIDLIST_DESTROY_DELAY); mutex_unlock(&seq_css(s)->cgroup->pidlist_mutex); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo3353.23%850.00%
paul menagepaul menage1930.65%425.00%
ben blumben blum46.45%16.25%
kirill a. shutemovkirill a. shutemov34.84%16.25%
li zefanli zefan23.23%16.25%
balbir singhbalbir singh11.61%16.25%
Total62100.00%16100.00%


static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos) { struct kernfs_open_file *of = s->private; struct cgroup_pidlist *l = of->priv; pid_t *p = v; pid_t *end = l->list + l->length; /* * Advance to the next pid in the array. If this goes off the * end, we're done */ p++; if (p >= end) { return NULL; } else { *pos = cgroup_pid_fry(seq_css(s)->cgroup, *p); return p; } }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage4851.61%110.00%
tejun heotejun heo2324.73%770.00%
ben blumben blum1819.35%110.00%
li zefanli zefan44.30%110.00%
Total93100.00%10100.00%


static int cgroup_pidlist_show(struct seq_file *s, void *v) { seq_printf(s, "%d\n", *(int *)v); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
ben blumben blum1237.50%125.00%
paul menagepaul menage1134.38%125.00%
tejun heotejun heo618.75%125.00%
joe perchesjoe perches39.38%125.00%
Total32100.00%4100.00%


static u64 cgroup_read_notify_on_release(struct cgroup_subsys_state *css, struct cftype *cft) { return notify_on_release(css->cgroup); }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage1354.17%120.00%
ben blumben blum520.83%120.00%
tejun heotejun heo520.83%240.00%
kirill a. shutemovkirill a. shutemov14.17%120.00%
Total24100.00%5100.00%


static int cgroup_write_notify_on_release(struct cgroup_subsys_state *css, struct cftype *cft, u64 val) { if (val) set_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags); else clear_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage3670.59%120.00%
tejun heotejun heo917.65%240.00%
ben blumben blum47.84%120.00%
kirill a. shutemovkirill a. shutemov23.92%120.00%
Total51100.00%5100.00%


static u64 cgroup_clone_children_read(struct cgroup_subsys_state *css, struct cftype *cft) { return test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo1137.93%240.00%
daniel lezcanodaniel lezcano931.03%120.00%
li zefanli zefan620.69%120.00%
ben blumben blum310.34%120.00%
Total29100.00%5100.00%


static int cgroup_clone_children_write(struct cgroup_subsys_state *css, struct cftype *cft, u64 val) { if (val) set_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); else clear_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
daniel lezcanodaniel lezcano2549.02%112.50%
tejun heotejun heo1019.61%225.00%
paul menagepaul menage713.73%337.50%
ben blumben blum59.80%112.50%
li zefanli zefan47.84%112.50%
Total51100.00%8100.00%

/* cgroup core interface files for the default hierarchy */ static struct cftype cgroup_dfl_base_files[] = { { .name = "cgroup.procs", .file_offset = offsetof(struct cgroup, procs_file), .seq_start = cgroup_pidlist_start, .seq_next = cgroup_pidlist_next, .seq_stop = cgroup_pidlist_stop, .seq_show = cgroup_pidlist_show, .private = CGROUP_FILE_PROCS, .write = cgroup_procs_write, }, { .name = "cgroup.controllers", .seq_show = cgroup_controllers_show, }, { .name = "cgroup.subtree_control", .seq_show = cgroup_subtree_control_show, .write = cgroup_subtree_control_write, }, { .name = "cgroup.events", .flags = CFTYPE_NOT_ON_ROOT, .file_offset = offsetof(struct cgroup, events_file), .seq_show = cgroup_events_show, }, { } /* terminate */ }; /* cgroup core interface files for the legacy hierarchies */ static struct cftype cgroup_legacy_base_files[] = { { .name = "cgroup.procs", .seq_start = cgroup_pidlist_start, .seq_next = cgroup_pidlist_next, .seq_stop = cgroup_pidlist_stop, .seq_show = cgroup_pidlist_show, .private = CGROUP_FILE_PROCS, .write = cgroup_procs_write, }, { .name = "cgroup.clone_children", .read_u64 = cgroup_clone_children_read, .write_u64 = cgroup_clone_children_write, }, { .name = "cgroup.sane_behavior", .flags = CFTYPE_ONLY_ON_ROOT, .seq_show = cgroup_sane_behavior_show, }, { .name = "tasks", .seq_start = cgroup_pidlist_start, .seq_next = cgroup_pidlist_next, .seq_stop = cgroup_pidlist_stop, .seq_show = cgroup_pidlist_show, .private = CGROUP_FILE_TASKS, .write = cgroup_tasks_write, }, { .name = "notify_on_release", .read_u64 = cgroup_read_notify_on_release, .write_u64 = cgroup_write_notify_on_release, }, { .name = "release_agent", .flags = CFTYPE_ONLY_ON_ROOT, .seq_show = cgroup_release_agent_show, .write = cgroup_release_agent_write, .max_write_len = PATH_MAX - 1, }, { } /* terminate */ }; /* * css destruction is four-stage process. * * 1. Destruction starts. Killing of the percpu_ref is initiated. * Implemented in kill_css(). * * 2. When the percpu_ref is confirmed to be visible as killed on all CPUs * and thus css_tryget_online() is guaranteed to fail, the css can be * offlined by invoking offline_css(). After offlining, the base ref is * put. Implemented in css_killed_work_fn(). * * 3. When the percpu_ref reaches zero, the only possible remaining * accessors are inside RCU read sections. css_release() schedules the * RCU callback. * * 4. After the grace period, the css can be freed. Implemented in * css_free_work_fn(). * * It is actually hairier because both step 2 and 4 require process context * and thus involve punting to css->destroy_work adding two additional * steps to the already complex sequence. */
static void css_free_work_fn(struct work_struct *work) { struct cgroup_subsys_state *css = container_of(work, struct cgroup_subsys_state, destroy_work); struct cgroup_subsys *ss = css->ss; struct cgroup *cgrp = css->cgroup; percpu_ref_exit(&css->refcnt); if (ss) { /* css free path */ struct cgroup_subsys_state *parent = css->parent; int id = css->id; ss->css_free(css); cgroup_idr_remove(&ss->css_idr, id); cgroup_put(cgrp); if (parent) css_put(parent); } else { /* cgroup free path */ atomic_dec(&cgrp->root->nr_cgrps); cgroup_pidlist_destroy_all(cgrp); cancel_work_sync(&cgrp->release_agent_work); if (cgroup_parent(cgrp)) { /* * We get a ref to the parent, and put the ref when * this cgroup is being freed, so it's guaranteed * that the parent won't be destroyed before its * children. */ cgroup_put(cgroup_parent(cgrp)); kernfs_put(cgrp->kn); kfree(cgrp); } else { /* * This is root cgroup's refcnt reaching zero, * which indicates that the root should be * released. */ cgroup_destroy_root(cgrp->root); } } }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo12672.41%1071.43%
vladimir davydovvladimir davydov2614.94%17.14%
paul menagepaul menage137.47%17.14%
li zefanli zefan95.17%214.29%
Total174100.00%14100.00%


static void css_free_rcu_fn(struct rcu_head *rcu_head) { struct cgroup_subsys_state *css = container_of(rcu_head, struct cgroup_subsys_state, rcu_head); INIT_WORK(&css->destroy_work, css_free_work_fn); queue_work(cgroup_destroy_wq, &css->destroy_work); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo4393.48%981.82%
li zefanli zefan24.35%19.09%
paul menagepaul menage12.17%19.09%
Total46100.00%11100.00%


static void css_release_work_fn(struct work_struct *work) { struct cgroup_subsys_state *css = container_of(work, struct cgroup_subsys_state, destroy_work); struct cgroup_subsys *ss = css->ss; struct cgroup *cgrp = css->cgroup; mutex_lock(&cgroup_mutex); css->flags |= CSS_RELEASED; list_del_rcu(&css->sibling); if (ss) { /* css release path */ cgroup_idr_replace(&ss->css_idr, NULL, css->id); if (ss->css_released) ss->css_released(css); } else { /* cgroup release path */ cgroup_idr_remove(&cgrp->root->cgroup_idr, cgrp->id); cgrp->id = -1; /* * There are two control paths which try to determine * cgroup from dentry without going through kernfs - * cgroupstats_build() and css_tryget_online_from_dir(). * Those are supported by RCU protecting clearing of * cgrp->kn->priv backpointer. */ if (cgrp->kn) RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv, NULL); } mutex_unlock(&cgroup_mutex); call_rcu(&css->rcu_head, css_free_rcu_fn); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo12877.11%1578.95%
li zefanli zefan2213.25%210.53%
paul menagepaul menage137.83%15.26%
vladimir davydovvladimir davydov31.81%15.26%
Total166100.00%19100.00%


static void css_release(struct percpu_ref *ref) { struct cgroup_subsys_state *css = container_of(ref, struct cgroup_subsys_state, refcnt); INIT_WORK(&css->destroy_work, css_release_work_fn); queue_work(cgroup_destroy_wq, &css->destroy_work); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo4393.48%571.43%
linus torvaldslinus torvalds24.35%114.29%
paul menagepaul menage12.17%114.29%
Total46100.00%7100.00%


static void init_and_link_css(struct cgroup_subsys_state *css, struct cgroup_subsys *ss, struct cgroup *cgrp) { lockdep_assert_held(&cgroup_mutex); cgroup_get(cgrp); memset(css, 0, sizeof(*css)); css->cgroup = cgrp; css->ss = ss; css->id = -1; INIT_LIST_HEAD(&css->sibling); INIT_LIST_HEAD(&css->children); css->serial_nr = css_serial_nr_next++; atomic_set(&css->online_cnt, 0); if (cgroup_parent(cgrp)) { css->parent = cgroup_css(cgroup_parent(cgrp), ss); css_get(css->parent); } BUG_ON(cgroup_css(cgrp, ss)); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo12087.59%1487.50%
paul menagepaul menage1712.41%212.50%
Total137100.00%16100.00%

/* invoke ->css_online() on a new CSS and mark it online if successful */
static int online_css(struct cgroup_subsys_state *css) { struct cgroup_subsys *ss = css->ss; int ret = 0; lockdep_assert_held(&cgroup_mutex); if (ss->css_online) ret = ss->css_online(css); if (!ret) { css->flags |= CSS_ONLINE; rcu_assign_pointer(css->cgroup->subsys[ss->id], css); atomic_inc(&css->online_cnt); if (css->parent) atomic_inc(&css->parent->online_cnt); } return ret; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo9492.16%1285.71%
li zefanli zefan87.84%214.29%
Total102100.00%14100.00%

/* if the CSS is online, invoke ->css_offline() on it and mark it offline */
static void offline_css(struct cgroup_subsys_state *css) { struct cgroup_subsys *ss = css->ss; lockdep_assert_held(&cgroup_mutex); if (!(css->flags & CSS_ONLINE)) return; if (ss->css_reset) ss->css_reset(css); if (ss->css_offline) ss->css_offline(css); css->flags &= ~CSS_ONLINE; RCU_INIT_POINTER(css->cgroup->subsys[ss->id], NULL); wake_up_all(&css->cgroup->offline_waitq); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo4647.42%1266.67%
paul menagepaul menage2727.84%211.11%
vladimir davydovvladimir davydov1313.40%15.56%
li zefanli zefan1111.34%316.67%
Total97100.00%18100.00%

/** * css_create - create a cgroup_subsys_state * @cgrp: the cgroup new css will be associated with * @ss: the subsys of new css * * Create a new css associated with @cgrp - @ss pair. On success, the new * css is online and installed in @cgrp. This function doesn't create the * interface files. Returns 0 on success, -errno on failure. */
static struct cgroup_subsys_state *css_create(struct cgroup *cgrp, struct cgroup_subsys *ss) { struct cgroup *parent = cgroup_parent(cgrp); struct cgroup_subsys_state *parent_css = cgroup_css(parent, ss); struct cgroup_subsys_state *css; int err; lockdep_assert_held(&cgroup_mutex); css = ss->css_alloc(parent_css); if (IS_ERR(css)) return css; init_and_link_css(css, ss, cgrp); err = percpu_ref_init(&css->refcnt, css_release, 0, GFP_KERNEL); if (err) goto err_free_css; err = cgroup_idr_alloc(&ss->css_idr, NULL, 2, 0, GFP_KERNEL); if (err < 0) goto err_free_css; css->id = err; /* @css is ready to be brought online now, make it visible */ list_add_tail_rcu(&css->sibling, &parent_css->children); cgroup_idr_replace(&ss->css_idr, css, css->id); err = online_css(css); if (err) goto err_list_del; if (ss->broken_hierarchy && !ss->warned_broken_hierarchy && cgroup_parent(parent)) { pr_warn("%s (%d) created nested cgroup for controller \"%s\" which has incomplete hierarchy support. Nested cgroups may change behavior in the future.\n", current->comm, current->pid, ss->name); if (!strcmp(ss->name, "memory")) pr_warn("\"memory\" requires setting use_hierarchy to 1 on the root\n"); ss->warned_broken_hierarchy = true; } return css; err_list_del: list_del_rcu(&css->sibling); err_free_css: call_rcu(&css->rcu_head, css_free_rcu_fn); return ERR_PTR(err); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo22483.27%2468.57%
paul menagepaul menage248.92%25.71%
li zefanli zefan103.72%38.57%
linus torvaldslinus torvalds31.12%12.86%
joe perchesjoe perches20.74%12.86%
daniel lezcanodaniel lezcano20.74%12.86%
jianyu zhanjianyu zhan20.74%12.86%
wenwei taowenwei tao10.37%12.86%
vladimir davydovvladimir davydov10.37%12.86%
Total269100.00%35100.00%


static struct cgroup *cgroup_create(struct cgroup *parent) { struct cgroup_root *root = parent->root; struct cgroup *cgrp, *tcgrp; int level = parent->level + 1; int ret; /* allocate the cgroup and its ID, 0 is reserved for the root */ cgrp = kzalloc(sizeof(*cgrp) + sizeof(cgrp->ancestor_ids[0]) * (level + 1), GFP_KERNEL); if (!cgrp) return ERR_PTR(-ENOMEM); ret = percpu_ref_init(&cgrp->self.refcnt, css_release, 0, GFP_KERNEL); if (ret) goto out_free_cgrp; /* * Temporarily set the pointer to NULL, so idr_find() won't return * a half-baked cgroup. */ cgrp->id = cgroup_idr_alloc(&root->cgroup_idr, NULL, 2, 0, GFP_KERNEL); if (cgrp->id < 0) { ret = -ENOMEM; goto out_cancel_ref; } init_cgroup_housekeeping(cgrp); cgrp->self.parent = &parent->self; cgrp->root = root; cgrp->level = level; for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) cgrp->ancestor_ids[tcgrp->level] = tcgrp->id; if (notify_on_release(parent)) set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags); if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &parent->flags)) set_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags); cgrp->self.serial_nr = css_serial_nr_next++; /* allocation complete, commit to creation */ list_add_tail_rcu(&cgrp->self.sibling, &cgroup_parent(cgrp)->self.children); atomic_inc(&root->nr_cgrps); cgroup_get(parent); /* * @cgrp is now fully operational. If something fails after this * point, it'll be released via the normal destruction path. */ cgroup_idr_replace(&root->cgroup_idr, cgrp, cgrp->id); /* * On the default hierarchy, a child doesn't automatically inherit * subtree_control from the parent. Each is configured manually. */ if (!cgroup_on_dfl(cgrp)) cgrp->subtree_control = cgroup_control(cgrp); cgroup_propagate_control(cgrp); /* @cgrp doesn't have dir yet so the following will only create csses */ ret = cgroup_apply_control_enable(cgrp); if (ret) goto out_destroy; return cgrp; out_cancel_ref: percpu_ref_exit(&cgrp->self.refcnt); out_free_cgrp: kfree(cgrp); return ERR_PTR(ret); out_destroy: cgroup_destroy_locked(cgrp); return ERR_PTR(ret); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo30279.47%3876.00%
paul menagepaul menage4712.37%48.00%
li zefanli zefan246.32%48.00%
daniel lezcanodaniel lezcano41.05%12.00%
kamezawa hiroyukikamezawa hiroyuki20.53%24.00%
vladimir davydovvladimir davydov10.26%12.00%
Total380100.00%50100.00%


static int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode) { struct cgroup *parent, *cgrp; struct kernfs_node *kn; int ret; /* do not accept '\n' to prevent making /proc/<pid>/cgroup unparsable */ if (strchr(name, '\n')) return -EINVAL; parent = cgroup_kn_lock_live(parent_kn, false); if (!parent) return -ENODEV; cgrp = cgroup_create(parent); if (IS_ERR(cgrp)) { ret = PTR_ERR(cgrp); goto out_unlock; } /* create the directory */ kn = kernfs_create_dir(parent->kn, name, mode, cgrp); if (IS_ERR(kn)) { ret = PTR_ERR(kn); goto out_destroy; } cgrp->kn = kn; /* * This extra ref will be put in cgroup_free_fn() and guarantees * that @cgrp->kn is always accessible. */ kernfs_get(kn); ret = cgroup_kn_set_ugid(kn); if (ret) goto out_destroy; ret = css_populate_dir(&cgrp->self); if (ret) goto out_destroy; ret = cgroup_apply_control_enable(cgrp); if (ret) goto out_destroy; /* let's create and online css's */ kernfs_activate(kn); ret = 0; goto out_unlock; out_destroy: cgroup_destroy_locked(cgrp); out_unlock: cgroup_kn_unlock(parent_kn); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo20595.35%1372.22%
kamezawa hiroyukikamezawa hiroyuki52.33%15.56%
li zefanli zefan31.40%211.11%
paul menagepaul menage20.93%211.11%
Total215100.00%18100.00%

/* * This is called when the refcnt of a css is confirmed to be killed. * css_tryget_online() is now guaranteed to fail. Tell the subsystem to * initate destruction and put the css ref from kill_css(). */
static void css_killed_work_fn(struct work_struct *work) { struct cgroup_subsys_state *css = container_of(work, struct cgroup_subsys_state, destroy_work); mutex_lock(&cgroup_mutex); do { offline_css(css); css_put(css); /* @css can't go away while we're holding cgroup_mutex */ css = css->parent; } while (css && atomic_dec_and_test(&css->online_cnt)); mutex_unlock(&cgroup_mutex); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo71100.00%8100.00%
Total71100.00%8100.00%

/* css kill confirmation processing requires process context, bounce */
static void css_killed_ref_fn(struct percpu_ref *ref) { struct cgroup_subsys_state *css = container_of(ref, struct cgroup_subsys_state, refcnt); if (atomic_dec_and_test(&css->online_cnt)) { INIT_WORK(&css->destroy_work, css_killed_work_fn); queue_work(cgroup_destroy_wq, &css->destroy_work); } }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo58100.00%7100.00%
Total58100.00%7100.00%

/** * kill_css - destroy a css * @css: css to destroy * * This function initiates destruction of @css by removing cgroup interface * files and putting its base reference. ->css_offline() will be invoked * asynchronously once css_tryget_online() is guaranteed to fail and when * the reference count reaches zero, @css will be released. */
static void kill_css(struct cgroup_subsys_state *css) { lockdep_assert_held(&cgroup_mutex); /* * This must happen before css is disassociated with its cgroup. * See seq_css() for details. */ css_clear_dir(css); /* * Killing would put the base ref, but we need to keep it alive * until after ->css_offline(). */ css_get(css); /* * cgroup core guarantees that, by the time ->css_offline() is * invoked, no new css reference will be given out via * css_tryget_online(). We can't simply call percpu_ref_kill() and * proceed to offlining css's because percpu_ref_kill() doesn't * guarantee that the ref is seen as killed on all CPUs on return. * * Use percpu_ref_kill_and_confirm() to get notifications as each * css is confirmed to be seen as killed on all CPUs. */ percpu_ref_kill_and_confirm(&css->refcnt, css_killed_ref_fn); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo2972.50%981.82%
paul menagepaul menage820.00%19.09%
ben blumben blum37.50%19.09%
Total40100.00%11100.00%

/** * cgroup_destroy_locked - the first stage of cgroup destruction * @cgrp: cgroup to be destroyed * * css's make use of percpu refcnts whose killing latency shouldn't be * exposed to userland and are RCU protected. Also, cgroup core needs to * guarantee that css_tryget_online() won't succeed by the time * ->css_offline() is invoked. To satisfy all the requirements, * destruction is implemented in the following two steps. * * s1. Verify @cgrp can be destroyed and mark it dying. Remove all * userland visible parts and start killing the percpu refcnts of * css's. Set up so that the next stage will be kicked off once all * the percpu refcnts are confirmed to be killed. * * s2. Invoke ->css_offline(), mark the cgroup dead and proceed with the * rest of destruction. Once all cgroup references are gone, the * cgroup is RCU-freed. * * This function implements s1. After this step, @cgrp is gone as far as * the userland is concerned and a new cgroup with the same name may be * created. As cgroup doesn't care about the names internally, this * doesn't cause any problem. */
static int cgroup_destroy_locked(struct cgroup *cgrp) __releases(&cgroup_mutex

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo650.00%125.00%
paul menagepaul menage433.33%250.00%
ben blumben blum216.67%125.00%
Total12100.00%4100.00%

) __acquires(&cgroup_mutex) { struct cgroup_subsys_state *css; struct cgrp_cset_link *link; int ssid; lockdep_assert_held(&cgroup_mutex); /* * Only migration can raise populated from zero and we're already * holding cgroup_mutex. */ if (cgroup_is_populated(cgrp)) return -EBUSY; /* * Make sure there's no live children. We can't test emptiness of * ->self.children as dead children linger on it while being * drained; otherwise, "rmdir parent/child parent" may fail. */ if (css_has_online_children(&cgrp->self)) return -EBUSY; /* * Mark @cgrp and the associated csets dead. The former prevents * further task migration and child creation by disabling * cgroup_lock_live_group(). The latter makes the csets ignored by * the migration path. */ cgrp->self.flags &= ~CSS_ONLINE; spin_lock_irq(&css_set_lock); list_for_each_entry(link, &cgrp->cset_links, cset_link) link->cset->dead = true; spin_unlock_irq(&css_set_lock); /* initiate massacre of all css's */ for_each_css(css, ssid, cgrp) kill_css(css); /* * Remove @cgrp directory along with the base files. @cgrp has an * extra ref on its kn. */ kernfs_remove(cgrp->kn); check_for_release(cgroup_parent(cgrp)); /* put the base reference */ percpu_ref_kill(&cgrp->self.refcnt); return 0; };
static int cgroup_rmdir(struct kernfs_node *kn) { struct cgroup *cgrp; int ret = 0; cgrp = cgroup_kn_lock_live(kn, false); if (!cgrp) return 0; ret = cgroup_destroy_locked(cgrp); cgroup_kn_unlock(kn); return ret; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo4686.79%777.78%
ben blumben blum713.21%222.22%
Total53100.00%9100.00%

static struct kernfs_syscall_ops cgroup_kf_syscall_ops = { .remount_fs = cgroup_remount, .show_options = cgroup_show_options, .mkdir = cgroup_mkdir, .rmdir = cgroup_rmdir, .rename = cgroup_rename, .show_path = cgroup_show_path, };
static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early) { struct cgroup_subsys_state *css; pr_debug("Initializing cgroup subsys %s\n", ss->name); mutex_lock(&cgroup_mutex); idr_init(&ss->css_idr); INIT_LIST_HEAD(&ss->cfts); /* Create the root cgroup state for this subsystem */ ss->root = &cgrp_dfl_root; css = ss->css_alloc(cgroup_css(&cgrp_dfl_root.cgrp, ss)); /* We don't handle early failures gracefully */ BUG_ON(IS_ERR(css)); init_and_link_css(css, ss, &cgrp_dfl_root.cgrp); /* * Root csses are never destroyed and we can't initialize * percpu_ref during early init. Disable refcnting. */ css->flags |= CSS_NO_REF; if (early) { /* allocation can't be done safely during early init */ css->id = 1; } else { css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2, GFP_KERNEL); BUG_ON(css->id < 0); } /* Update the init_css_set to contain a subsys * pointer to this state - since the subsystem is * newly registered, all tasks and hence the * init_css_set is in the subsystem's root cgroup. */ init_css_set.subsys[ss->id] = css; have_fork_callback |= (bool)ss->fork << ss->id; have_exit_callback |= (bool)ss->exit << ss->id; have_free_callback |= (bool)ss->free << ss->id; have_canfork_callback |= (bool)ss->can_fork << ss->id; /* At system boot, before all subsystems have been * registered, no tasks have been forked, so we don't * need to invoke fork callbacks here. */ BUG_ON(!list_empty(&init_task.tasks)); BUG_ON(online_css(css)); mutex_unlock(&cgroup_mutex); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo10945.42%1866.67%
ben blumben blum5221.67%27.41%
aleksa saraialeksa sarai3112.92%27.41%
paul menagepaul menage2711.25%27.41%
li zefanli zefan114.58%27.41%
vladimir davydovvladimir davydov104.17%13.70%
Total240100.00%27100.00%

/** * cgroup_init_early - cgroup initialization at system boot * * Initialize cgroups at system boot, and initialize any * subsystems that request early init. */
int __init cgroup_init_early(void) { static struct cgroup_sb_opts __initdata opts; struct cgroup_subsys *ss; int i; init_cgroup_root(&cgrp_dfl_root, &opts); cgrp_dfl_root.cgrp.self.flags |= CSS_NO_REF; RCU_INIT_POINTER(init_task.cgroups, &init_css_set); for_each_subsys(ss, i) { WARN(!ss->css_alloc || !ss->css_free || ss->name || ss->id, "invalid cgroup_subsys %d:%s css_alloc=%p css_free=%p id:name=%d:%s\n", i, cgroup_subsys_name[i], ss->css_alloc, ss->css_free, ss->id, ss->name); WARN(strlen(cgroup_subsys_name[i]) > MAX_CGROUP_TYPE_NAMELEN, "cgroup_subsys_name %s too long\n", cgroup_subsys_name[i]); ss->id = i; ss->name = cgroup_subsys_name[i]; if (!ss->legacy_name) ss->legacy_name = cgroup_subsys_name[i]; if (ss->early_init) cgroup_init_subsys(ss, true); } return 0; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo10259.30%1178.57%
ben blumben blum6537.79%17.14%
paul menagepaul menage42.33%17.14%
xiubo lixiubo li10.58%17.14%
Total172100.00%14100.00%

static u16 cgroup_disable_mask __initdata; /** * cgroup_init - cgroup initialization * * Register cgroup filesystem and /proc file, and initialize * any subsystems that didn't request early init. */
int __init cgroup_init(void) { struct cgroup_subsys *ss; int ssid; BUILD_BUG_ON(CGROUP_SUBSYS_COUNT > 16); BUG_ON(percpu_init_rwsem(&cgroup_threadgroup_rwsem)); BUG_ON(cgroup_init_cftypes(NULL, cgroup_dfl_base_files)); BUG_ON(cgroup_init_cftypes(NULL, cgroup_legacy_base_files)); get_user_ns(init_cgroup_ns.user_ns); mutex_lock(&cgroup_mutex); /* * Add init_css_set to the hash table so that dfl_root can link to * it during init. */ hash_add(css_set_table, &init_css_set.hlist, css_set_hash(init_css_set.subsys)); BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0)); mutex_unlock(&cgroup_mutex); for_each_subsys(ss, ssid) { if (ss->early_init) { struct cgroup_subsys_state *css = init_css_set.subsys[ss->id]; css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2, GFP_KERNEL); BUG_ON(css->id < 0); } else { cgroup_init_subsys(ss, false); } list_add_tail(&init_css_set.e_cset_node[ssid], &cgrp_dfl_root.cgrp.e_csets[ssid]); /* * Setting dfl_root subsys_mask needs to consider the * disabled flag and cftype registration needs kmalloc, * both of which aren't available during early_init. */ if (cgroup_disable_mask & (1 << ssid)) { static_branch_disable(cgroup_subsys_enabled_key[ssid]); printk(KERN_INFO "Disabling %s control group subsystem\n", ss->name); continue; } if (cgroup_ssid_no_v1(ssid)) printk(KERN_INFO "Disabling %s control group subsystem in v1 mounts\n", ss->name); cgrp_dfl_root.subsys_mask |= 1 << ss->id; if (ss->implicit_on_dfl) cgrp_dfl_implicit_ss_mask |= 1 << ss->id; else if (!ss->dfl_cftypes) cgrp_dfl_inhibit_ss_mask |= 1 << ss->id; if (ss->dfl_cftypes == ss->legacy_cftypes) { WARN_ON(cgroup_add_cftypes(ss, ss->dfl_cftypes)); } else { WARN_ON(cgroup_add_dfl_cftypes(ss, ss->dfl_cftypes)); WARN_ON(cgroup_add_legacy_cftypes(ss, ss->legacy_cftypes)); } if (ss->bind) ss->bind(init_css_set.subsys[ssid]); } /* init_css_set.subsys[] has been updated, re-hash */ hash_del(&init_css_set.hlist); hash_add(css_set_table, &init_css_set.hlist, css_set_hash(init_css_set.subsys)); WARN_ON(sysfs_create_mount_point(fs_kobj, "cgroup")); WARN_ON(register_filesystem(&cgroup_fs_type)); WARN_ON(register_filesystem(&cgroup2_fs_type)); WARN_ON(!proc_create("cgroups", 0, NULL, &proc_cgroupstats_operations)); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo30572.45%2464.86%
paul menagepaul menage358.31%38.11%
li zefanli zefan307.13%513.51%
vladimir davydovvladimir davydov184.28%12.70%
johannes weinerjohannes weiner174.04%12.70%
aditya kaliaditya kali71.66%12.70%
greg kroah-hartmangreg kroah-hartman61.43%12.70%
eric w. biedermaneric w. biederman30.71%12.70%
Total421100.00%37100.00%


static int __init cgroup_wq_init(void) { /* * There isn't much point in executing destruction path in * parallel. Good chunk is serialized with cgroup_mutex anyway. * Use 1 for @max_active. * * We would prefer to do this in cgroup_init() above, but that * is called before init_workqueues(): so leave this until after. */ cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1); BUG_ON(!cgroup_destroy_wq); /* * Used to destroy pidlists and separate to serve as flush domain. * Cap @max_active to 1 too. */ cgroup_pidlist_destroy_wq = alloc_workqueue("cgroup_pidlist_destroy", 0, 1); BUG_ON(!cgroup_pidlist_destroy_wq); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo48100.00%3100.00%
Total48100.00%3100.00%

core_initcall(cgroup_wq_init); /* * proc_cgroup_show() * - Print task's cgroup paths into seq_file, one line for each hierarchy * - Used for /proc/<pid>/cgroup. */
int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk) { char *buf, *path; int retval; struct cgroup_root *root; retval = -ENOMEM; buf = kmalloc(PATH_MAX, GFP_KERNEL); if (!buf) goto out; mutex_lock(&cgroup_mutex); spin_lock_irq(&css_set_lock); for_each_root(root) { struct cgroup_subsys *ss; struct cgroup *cgrp; int ssid, count = 0; if (root == &cgrp_dfl_root && !cgrp_dfl_visible) continue; seq_printf(m, "%d:", root->hierarchy_id); if (root != &cgrp_dfl_root) for_each_subsys(ss, ssid) if (root->subsys_mask & (1 << ssid)) seq_printf(m, "%s%s", count++ ? "," : "", ss->legacy_name); if (strlen(root->name)) seq_printf(m, "%sname=%s", count ? "," : "", root->name); seq_putc(m, ':'); cgrp = task_cgroup_from_root(tsk, root); /* * On traditional hierarchies, all zombie tasks show up as * belonging to the root cgroup. On the default hierarchy, * while a zombie doesn't show up in "cgroup.procs" and * thus can't be migrated, its /proc/PID/cgroup keeps * reporting the cgroup it belonged to before exiting. If * the cgroup is removed before the zombie is reaped, * " (deleted)" is appended to the cgroup path. */ if (cgroup_on_dfl(cgrp) || !(tsk->flags & PF_EXITING)) { path = cgroup_path_ns_locked(cgrp, buf, PATH_MAX, current->nsproxy->cgroup_ns); if (!path) { retval = -ENAMETOOLONG; goto out_unlock; } } else { path = "/"; } seq_puts(m, path); if (cgroup_on_dfl(cgrp) && cgroup_is_dead(cgrp)) seq_puts(m, " (deleted)\n"); else seq_putc(m, '\n'); } retval = 0; out_unlock: spin_unlock_irq(&css_set_lock); mutex_unlock(&cgroup_mutex); kfree(buf); out: return retval; }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage19459.88%630.00%
tejun heotejun heo11033.95%1155.00%
li zefanli zefan113.40%15.00%
aditya kaliaditya kali72.16%15.00%
daniel bristot de oliveiradaniel bristot de oliveira20.62%15.00%
Total324100.00%20100.00%

/* Display information about each subsystem and each hierarchy */
static int proc_cgroupstats_show(struct seq_file *m, void *v) { struct cgroup_subsys *ss; int i; seq_puts(m, "#subsys_name\thierarchy\tnum_cgroups\tenabled\n"); /* * ideally we don't want subsystems moving around while we do this. * cgroup_mutex is also necessary to guarantee an atomic snapshot of * subsys/hierarchy state. */ mutex_lock(&cgroup_mutex); for_each_subsys(ss, i) seq_printf(m, "%s\t%d\t%d\t%d\n", ss->legacy_name, ss->root->hierarchy_id, atomic_read(&ss->root->nr_cgrps), cgroup_ssid_enabled(i)); mutex_unlock(&cgroup_mutex); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage6273.81%444.44%
tejun heotejun heo2125.00%444.44%
ben blumben blum11.19%111.11%
Total84100.00%9100.00%


static int cgroupstats_open(struct inode *inode, struct file *file) { return single_open(file, proc_cgroupstats_show, NULL); }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage2596.15%150.00%
al viroal viro13.85%150.00%
Total26100.00%2100.00%

static const struct file_operations proc_cgroupstats_operations = { .open = cgroupstats_open, .read = seq_read, .llseek = seq_lseek, .release = single_release, }; /** * cgroup_fork - initialize cgroup related fields during copy_process() * @child: pointer to task_struct of forking parent process. * * A task is associated with the init_css_set until cgroup_post_fork() * attaches it to the parent's css_set. Empty cg_list indicates that * @child isn't holding reference to its css_set. */
void cgroup_fork(struct task_struct *child) { RCU_INIT_POINTER(child->cgroups, &init_css_set); INIT_LIST_HEAD(&child->cg_list); }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage2175.00%240.00%
tejun heotejun heo725.00%360.00%
Total28100.00%5100.00%

/** * cgroup_can_fork - called on a new task before the process is exposed * @child: the task in question. * * This calls the subsystem can_fork() callbacks. If the can_fork() callback * returns an error, the fork aborts with that error code. This allows for * a cgroup subsystem to conditionally allow or deny new forks. */
int cgroup_can_fork(struct task_struct *child) { struct cgroup_subsys *ss; int i, j, ret; do_each_subsys_mask(ss, i, have_canfork_callback) { ret = ss->can_fork(child); if (ret) goto out_revert; } while_each_subsys_mask(); return 0; out_revert: for_each_subsys(ss, j) { if (j >= i) break; if (ss->cancel_fork) ss->cancel_fork(child); } return ret; }

Contributors

PersonTokensPropCommitsCommitProp
aleksa saraialeksa sarai8294.25%150.00%
tejun heotejun heo55.75%150.00%
Total87100.00%2100.00%

/** * cgroup_cancel_fork - called if a fork failed after cgroup_can_fork() * @child: the task in question * * This calls the cancel_fork() callbacks if a fork failed *after* * cgroup_can_fork() succeded. */
void cgroup_cancel_fork(struct task_struct *child) { struct cgroup_subsys *ss; int i; for_each_subsys(ss, i) if (ss->cancel_fork) ss->cancel_fork(child); }

Contributors

PersonTokensPropCommitsCommitProp
aleksa saraialeksa sarai37100.00%1100.00%
Total37100.00%1100.00%

/** * cgroup_post_fork - called on a new task after adding it to the task list * @child: the task in question * * Adds the task to the list running through its css_set if necessary and * call the subsystem fork() callbacks. Has to be after the task is * visible on the task list in case we race with the first call to * cgroup_task_iter_start() - to guarantee that the new task ends up on its * list. */
void cgroup_post_fork(struct task_struct *child) { struct cgroup_subsys *ss; int i; /* * This may race against cgroup_enable_task_cg_lists(). As that * function sets use_task_css_set_links before grabbing * tasklist_lock and we just went through tasklist_lock to add * @child, it's guaranteed that either we see the set * use_task_css_set_links or cgroup_enable_task_cg_lists() sees * @child during its iteration. * * If we won the race, @child is associated with %current's * css_set. Grabbing css_set_lock guarantees both that the * association is stable, and, on completion of the parent's * migration, @child is visible in the source of migration or * already in the destination cgroup. This guarantee is necessary * when implementing operations which need to migrate all tasks of * a cgroup to another. * * Note that if we lose to cgroup_enable_task_cg_lists(), @child * will remain in init_css_set. This is safe because all tasks are * in the init_css_set before cg_links is enabled and there's no * operation which transfers all tasks out of init_css_set. */ if (use_task_css_set_links) { struct css_set *cset; spin_lock_irq(&css_set_lock); cset = task_css_set(current); if (list_empty(&child->cg_list)) { get_css_set(cset); css_set_move_task(child, NULL, cset, false); } spin_unlock_irq(&css_set_lock); } /* * Call ss->fork(). This must happen after @child is linked on * css_set; otherwise, @child might change state between ->fork() * and addition to css_set. */ do_each_subsys_mask(ss, i, have_fork_callback) { ss->fork(child); } while_each_subsys_mask(); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo7980.61%872.73%
paul menagepaul menage1616.33%19.09%
daniel bristot de oliveiradaniel bristot de oliveira22.04%19.09%
aleksa saraialeksa sarai11.02%19.09%
Total98100.00%11100.00%

/** * cgroup_exit - detach cgroup from exiting task * @tsk: pointer to task_struct of exiting process * * Description: Detach cgroup from @tsk and release it. * * Note that cgroups marked notify_on_release force every task in * them to take the global cgroup_mutex mutex when exiting. * This could impact scaling on very large systems. Be reluctant to * use notify_on_release cgroups where very high task exit scaling * is required on large systems. * * We set the exiting tasks cgroup to the root cgroup (top_cgroup). We * call cgroup_exit() while the task is still competent to handle * notify_on_release(), then leave the task attached to the root cgroup in * each hierarchy for the remainder of its exit. No need to bother with * init_css_set refcnting. init_css_set never goes away and we can't race * with migration path - PF_EXITING is visible to migration path. */
void cgroup_exit(struct task_struct *tsk) { struct cgroup_subsys *ss; struct css_set *cset; int i; /* * Unlink from @tsk from its css_set. As migration path can't race * with us, we can check css_set and cg_list without synchronization. */ cset = task_css_set(tsk); if (!list_empty(&tsk->cg_list)) { spin_lock_irq(&css_set_lock); css_set_move_task(tsk, cset, NULL, false); spin_unlock_irq(&css_set_lock); } else { get_css_set(cset); } /* see cgroup_post_fork() for details */ do_each_subsys_mask(ss, i, have_exit_callback) { ss->exit(tsk); } while_each_subsys_mask(); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo4546.88%964.29%
paul menagepaul menage3940.62%214.29%
peter zijlstrapeter zijlstra99.38%17.14%
daniel bristot de oliveiradaniel bristot de oliveira22.08%17.14%
aleksa saraialeksa sarai11.04%17.14%
Total96100.00%14100.00%


void cgroup_free(struct task_struct *task) { struct css_set *cset = task_css_set(task); struct cgroup_subsys *ss; int ssid; do_each_subsys_mask(ss, ssid, have_free_callback) { ss->free(task); } while_each_subsys_mask(); put_css_set(cset); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo4992.45%571.43%
paul menagepaul menage47.55%228.57%
Total53100.00%7100.00%


static void check_for_release(struct cgroup *cgrp) { if (notify_on_release(cgrp) && !cgroup_is_populated(cgrp) && !css_has_online_children(&cgrp->self) && !cgroup_is_dead(cgrp)) schedule_work(&cgrp->release_agent_work); }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage3880.85%225.00%
tejun heotejun heo510.64%450.00%
li zefanli zefan48.51%225.00%
Total47100.00%8100.00%

/* * Notify userspace when a cgroup is released, by running the * configured release agent with the name of the cgroup (path * relative to the root of cgroup file system) as the argument. * * Most likely, this user command will try to rmdir this cgroup. * * This races with the possibility that some other task will be * attached to this cgroup before it is removed, or that some other * user task will 'mkdir' a child cgroup of this cgroup. That's ok. * The presumed 'rmdir' will fail quietly if this cgroup is no longer * unused, and this cgroup will be reprieved from its death sentence, * to continue to serve a useful existence. Next time it's released, * we will get notified again, if it still has 'notify_on_release' set. * * The final arg to call_usermodehelper() is UMH_WAIT_EXEC, which * means only wait until the task is successfully execve()'d. The * separate release agent task is forked by call_usermodehelper(), * then control in this thread returns here, without waiting for the * release agent task. We don't bother to wait because the caller of * this routine has no use for the exit status of the release agent * task, so no sense holding our caller up for that. */
static void cgroup_release_agent(struct work_struct *work) { struct cgroup *cgrp = container_of(work, struct cgroup, release_agent_work); char *pathbuf = NULL, *agentbuf = NULL, *path; char *argv[3], *envp[3]; mutex_lock(&cgroup_mutex); pathbuf = kmalloc(PATH_MAX, GFP_KERNEL); agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL); if (!pathbuf || !agentbuf) goto out; spin_lock_irq(&css_set_lock); path = cgroup_path_ns_locked(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns); spin_unlock_irq(&css_set_lock); if (!path) goto out; argv[0] = agentbuf; argv[1] = path; argv[2] = NULL; /* minimal command environment */ envp[0] = "HOME=/"; envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin"; envp[2] = NULL; mutex_unlock(&cgroup_mutex); call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC); goto out_free; out: mutex_unlock(&cgroup_mutex); out_free: kfree(agentbuf); kfree(pathbuf); }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage12860.38%337.50%
li zefanli zefan5525.94%225.00%
aditya kaliaditya kali146.60%112.50%
tejun heotejun heo136.13%112.50%
daniel bristot de oliveiradaniel bristot de oliveira20.94%112.50%
Total212100.00%8100.00%


static int __init cgroup_disable(char *str) { struct cgroup_subsys *ss; char *token; int i; while ((token = strsep(&str, ",")) != NULL) { if (!*token) continue; for_each_subsys(ss, i) { if (strcmp(token, ss->name) && strcmp(token, ss->legacy_name)) continue; cgroup_disable_mask |= 1 << i; } } return 1; }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage5766.28%116.67%
tejun heotejun heo2933.72%583.33%
Total86100.00%6100.00%

__setup("cgroup_disable=", cgroup_disable);
static int __init cgroup_no_v1(char *str) { struct cgroup_subsys *ss; char *token; int i; while ((token = strsep(&str, ",")) != NULL) { if (!*token) continue; if (!strcmp(token, "all")) { cgroup_no_v1_mask = U16_MAX; break; } for_each_subsys(ss, i) { if (strcmp(token, ss->name) && strcmp(token, ss->legacy_name)) continue; cgroup_no_v1_mask |= 1 << i; } } return 1; }

Contributors

PersonTokensPropCommitsCommitProp
johannes weinerjohannes weiner10299.03%150.00%
tejun heotejun heo10.97%150.00%
Total103100.00%2100.00%

__setup("cgroup_no_v1=", cgroup_no_v1); /** * css_tryget_online_from_dir - get corresponding css from a cgroup dentry * @dentry: directory dentry of interest * @ss: subsystem of interest * * If @dentry is a directory for a cgroup which has @ss enabled on it, try * to get the corresponding css and return it. If such css doesn't exist * or can't be pinned, an ERR_PTR value is returned. */
struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, struct cgroup_subsys *ss) { struct kernfs_node *kn = kernfs_node_from_dentry(dentry); struct file_system_type *s_type = dentry->d_sb->s_type; struct cgroup_subsys_state *css = NULL; struct cgroup *cgrp; /* is @dentry a cgroup dir? */ if ((s_type != &cgroup_fs_type && s_type != &cgroup2_fs_type) || !kn || kernfs_type(kn) != KERNFS_DIR) return ERR_PTR(-EBADF); rcu_read_lock(); /* * This path doesn't originate from kernfs and @kn could already * have been or be removed at any point. @kn->priv is RCU * protected for this access. See css_release_work_fn() for details. */ cgrp = rcu_dereference(kn->priv); if (cgrp) css = cgroup_css(cgrp, ss); if (!css || !css_tryget_online(css)) css = ERR_PTR(-ENOENT); rcu_read_unlock(); return css; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo9168.42%675.00%
stephane eranianstephane eranian4130.83%112.50%
li zefanli zefan10.75%112.50%
Total133100.00%8100.00%

/** * css_from_id - lookup css by id * @id: the cgroup id * @ss: cgroup subsys to be looked into * * Returns the css if there's valid one with @id, otherwise returns NULL. * Should be called under rcu_read_lock(). */
struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss) { WARN_ON_ONCE(!rcu_read_lock_held()); return id > 0 ? idr_find(&ss->css_idr, id) : NULL; }

Contributors

PersonTokensPropCommitsCommitProp
li zefanli zefan2256.41%120.00%
tejun heotejun heo717.95%240.00%
vladimir davydovvladimir davydov615.38%120.00%
stephane eranianstephane eranian410.26%120.00%
Total39100.00%5100.00%

/** * cgroup_get_from_path - lookup and get a cgroup from its default hierarchy path * @path: path on the default hierarchy * * Find the cgroup at @path on the default hierarchy, increment its * reference count and return it. Returns pointer to the found cgroup on * success, ERR_PTR(-ENOENT) if @path doens't exist and ERR_PTR(-ENOTDIR) * if @path points to a non-directory. */
struct cgroup *cgroup_get_from_path(const char *path) { struct kernfs_node *kn; struct cgroup *cgrp; mutex_lock(&cgroup_mutex); kn = kernfs_walk_and_get(cgrp_dfl_root.cgrp.kn, path); if (kn) { if (kernfs_type(kn) == KERNFS_DIR) { cgrp = kn->priv; cgroup_get(cgrp); } else { cgrp = ERR_PTR(-ENOTDIR); } kernfs_put(kn); } else { cgrp = ERR_PTR(-ENOENT); } mutex_unlock(&cgroup_mutex); return cgrp; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo105100.00%1100.00%
Total105100.00%1100.00%

EXPORT_SYMBOL_GPL(cgroup_get_from_path); /* * sock->sk_cgrp_data handling. For more info, see sock_cgroup_data * definition in cgroup-defs.h. */ #ifdef CONFIG_SOCK_CGROUP_DATA #if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID) DEFINE_SPINLOCK(cgroup_sk_update_lock); static bool cgroup_sk_alloc_disabled __read_mostly;
void cgroup_sk_alloc_disable(void) { if (cgroup_sk_alloc_disabled) return; pr_info("cgroup: disabling cgroup2 socket matching due to net_prio or net_cls activation\n"); cgroup_sk_alloc_disabled = true; }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo21100.00%1100.00%
Total21100.00%1100.00%

#else #define cgroup_sk_alloc_disabled false #endif
void cgroup_sk_alloc(struct sock_cgroup_data *skcd) { if (cgroup_sk_alloc_disabled) return; rcu_read_lock(); while (true) { struct css_set *cset; cset = task_css_set(current); if (likely(cgroup_tryget(cset->dfl_cgrp))) { skcd->val = (unsigned long)cset->dfl_cgrp; break; } cpu_relax(); } rcu_read_unlock(); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo69100.00%1100.00%
Total69100.00%1100.00%


void cgroup_sk_free(struct sock_cgroup_data *skcd) { cgroup_put(sock_cgroup_ptr(skcd)); }

Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo18100.00%1100.00%
Total18100.00%1100.00%

#endif /* CONFIG_SOCK_CGROUP_DATA */ /* cgroup namespaces */
static struct cgroup_namespace *alloc_cgroup_ns(void) { struct cgroup_namespace *new_ns; int ret; new_ns = kzalloc(sizeof(struct cgroup_namespace), GFP_KERNEL); if (!new_ns) return ERR_PTR(-ENOMEM); ret = ns_alloc_inum(&new_ns->ns); if (ret) { kfree(new_ns); return ERR_PTR(ret); } atomic_set(&new_ns->count, 1); new_ns->ns.ops = &cgroupns_operations; return new_ns; }

Contributors

PersonTokensPropCommitsCommitProp
aditya kaliaditya kali92100.00%1100.00%
Total92100.00%1100.00%


void free_cgroup_ns(struct cgroup_namespace *ns) { put_css_set(ns->root_cset); put_user_ns(ns->user_ns); ns_free_inum(&ns->ns); kfree(ns); }

Contributors

PersonTokensPropCommitsCommitProp
aditya kaliaditya kali37100.00%1100.00%
Total37100.00%1100.00%

EXPORT_SYMBOL(free_cgroup_ns);
struct cgroup_namespace *copy_cgroup_ns(unsigned long flags, struct user_namespace *user_ns, struct cgroup_namespace *old_ns) { struct cgroup_namespace *new_ns; struct css_set *cset; BUG_ON(!old_ns); if (!(flags & CLONE_NEWCGROUP)) { get_cgroup_ns(old_ns); return old_ns; } /* Allow only sysadmin to create cgroup namespace. */ if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); mutex_lock(&cgroup_mutex); spin_lock_irq(&css_set_lock); cset = task_css_set(current); get_css_set(cset); spin_unlock_irq(&css_set_lock); mutex_unlock(&cgroup_mutex); new_ns = alloc_cgroup_ns(); if (IS_ERR(new_ns)) { put_css_set(cset); return new_ns; } new_ns->user_ns = get_user_ns(user_ns); new_ns->root_cset = cset; return new_ns; }

Contributors

PersonTokensPropCommitsCommitProp
aditya kaliaditya kali12885.33%125.00%
tejun heotejun heo2013.33%250.00%
daniel bristot de oliveiradaniel bristot de oliveira21.33%125.00%
Total150100.00%4100.00%


static inline struct cgroup_namespace *to_cg_ns(struct ns_common *ns) { return container_of(ns, struct cgroup_namespace, ns); }

Contributors

PersonTokensPropCommitsCommitProp
aditya kaliaditya kali25100.00%1100.00%
Total25100.00%1100.00%


static int cgroupns_install(struct nsproxy *nsproxy, struct ns_common *ns) { struct cgroup_namespace *cgroup_ns = to_cg_ns(ns); if (!ns_capable(current_user_ns(), CAP_SYS_ADMIN) || !ns_capable(cgroup_ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; /* Don't need to do anything if we are attaching to our own cgroupns. */ if (cgroup_ns == nsproxy->cgroup_ns) return 0; get_cgroup_ns(cgroup_ns); put_cgroup_ns(nsproxy->cgroup_ns); nsproxy->cgroup_ns = cgroup_ns; return 0; }

Contributors

PersonTokensPropCommitsCommitProp
aditya kaliaditya kali84100.00%2100.00%
Total84100.00%2100.00%


static struct ns_common *cgroupns_get(struct task_struct *task) { struct cgroup_namespace *ns = NULL; struct nsproxy *nsproxy; task_lock(task); nsproxy = task->nsproxy; if (nsproxy) { ns = nsproxy->cgroup_ns; get_cgroup_ns(ns); } task_unlock(task); return ns ? &ns->ns : NULL; }

Contributors

PersonTokensPropCommitsCommitProp
aditya kaliaditya kali68100.00%1100.00%
Total68100.00%1100.00%


static void cgroupns_put(struct ns_common *ns) { put_cgroup_ns(to_cg_ns(ns)); }

Contributors

PersonTokensPropCommitsCommitProp
aditya kaliaditya kali19100.00%1100.00%
Total19100.00%1100.00%

const struct proc_ns_operations cgroupns_operations = { .name = "cgroup", .type = CLONE_NEWCGROUP, .get = cgroupns_get, .put = cgroupns_put, .install = cgroupns_install, };
static __init int cgroup_namespaces_init(void) { return 0; }

Contributors

PersonTokensPropCommitsCommitProp
aditya kaliaditya kali12100.00%1100.00%
Total12100.00%1100.00%

subsys_initcall(cgroup_namespaces_init); #ifdef CONFIG_CGROUP_DEBUG
static struct cgroup_subsys_state * debug_css_alloc(struct cgroup_subsys_state *parent_css) { struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL); if (!css) return ERR_PTR(-ENOMEM); return css; }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage4193.18%133.33%
tejun heotejun heo36.82%266.67%
Total44100.00%3100.00%


static void debug_css_free(struct cgroup_subsys_state *css) { kfree(css); }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage1275.00%133.33%
tejun heotejun heo425.00%266.67%
Total16100.00%3100.00%


static u64 debug_taskcount_read(struct cgroup_subsys_state *css, struct cftype *cft) { return cgroup_task_count(css->cgroup); }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage1979.17%150.00%
tejun heotejun heo520.83%150.00%
Total24100.00%2100.00%


static u64 current_css_set_read(struct cgroup_subsys_state *css, struct cftype *cft) { return (u64)(unsigned long)current->cgroups; }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage2692.86%150.00%
tejun heotejun heo27.14%150.00%
Total28100.00%2100.00%


static u64 current_css_set_refcount_read(struct cgroup_subsys_state *css, struct cftype *cft) { u64 count; rcu_read_lock(); count = atomic_read(&task_css_set(current)->refcount); rcu_read_unlock(); return count; }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage3687.80%133.33%
tejun heotejun heo512.20%266.67%
Total41100.00%3100.00%


static int current_css_set_cg_links_read(struct seq_file *seq, void *v) { struct cgrp_cset_link *link; struct css_set *cset; char *name_buf; name_buf = kmalloc(NAME_MAX + 1, GFP_KERNEL); if (!name_buf) return -ENOMEM; spin_lock_irq(&css_set_lock); rcu_read_lock(); cset = rcu_dereference(current->cgroups); list_for_each_entry(link, &cset->cgrp_links, cgrp_link) { struct cgroup *c = link->cgrp; cgroup_name(c, name_buf, NAME_MAX + 1); seq_printf(seq, "Root %d group %s\n", c->root->hierarchy_id, name_buf); } rcu_read_unlock(); spin_unlock_irq(&css_set_lock); kfree(name_buf); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage7961.24%220.00%
tejun heotejun heo4837.21%770.00%
daniel bristot de oliveiradaniel bristot de oliveira21.55%110.00%
Total129100.00%10100.00%

#define MAX_TASKS_SHOWN_PER_CSS 25
static int cgroup_css_links_read(struct seq_file *seq, void *v) { struct cgroup_subsys_state *css = seq_css(seq); struct cgrp_cset_link *link; spin_lock_irq(&css_set_lock); list_for_each_entry(link, &css->cgroup->cset_links, cset_link) { struct css_set *cset = link->cset; struct task_struct *task; int count = 0; seq_printf(seq, "css_set %p\n", cset); list_for_each_entry(task, &cset->tasks, cg_list) { if (count++ > MAX_TASKS_SHOWN_PER_CSS) goto overflow; seq_printf(seq, " task %d\n", task_pid_vnr(task)); } list_for_each_entry(task, &cset->mg_tasks, cg_list) { if (count++ > MAX_TASKS_SHOWN_PER_CSS) goto overflow; seq_printf(seq, " task %d\n", task_pid_vnr(task)); } continue; overflow: seq_puts(seq, " ...\n"); } spin_unlock_irq(&css_set_lock); return 0; }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage9560.51%112.50%
tejun heotejun heo6038.22%675.00%
daniel bristot de oliveiradaniel bristot de oliveira21.27%112.50%
Total157100.00%8100.00%


static u64 releasable_read(struct cgroup_subsys_state *css, struct cftype *cft) { return (!cgroup_is_populated(css->cgroup) && !css_has_online_children(&css->cgroup->self)); }

Contributors

PersonTokensPropCommitsCommitProp
paul menagepaul menage2052.63%125.00%
li zefanli zefan1231.58%125.00%
tejun heotejun heo615.79%250.00%
Total38100.00%4100.00%

static struct cftype debug_files[] = { { .name = "taskcount", .read_u64 = debug_taskcount_read, }, { .name = "current_css_set", .read_u64 = current_css_set_read, }, { .name = "current_css_set_refcount", .read_u64 = current_css_set_refcount_read, }, { .name = "current_css_set_cg_links", .seq_show = current_css_set_cg_links_read, }, { .name = "cgroup_css_links", .seq_show = cgroup_css_links_read, }, { .name = "releasable", .read_u64 = releasable_read, }, { } /* terminate */ }; struct cgroup_subsys debug_cgrp_subsys = { .css_alloc = debug_css_alloc, .css_free = debug_css_free, .legacy_cftypes = debug_files, }; #endif /* CONFIG_CGROUP_DEBUG */

Overall Contributors

PersonTokensPropCommitsCommitProp
tejun heotejun heo1373960.52%34564.73%
paul menagepaul menage443619.54%264.88%
li zefanli zefan10464.61%6111.44%
ben blumben blum8323.66%101.88%
aditya kaliaditya kali7153.15%20.38%
serge hallynserge hallyn4441.96%40.75%
aleksa saraialeksa sarai1790.79%30.56%
johannes weinerjohannes weiner1660.73%20.38%
cliff wickmancliff wickman1610.71%10.19%
daniel lezcanodaniel lezcano1590.70%20.38%
aristeu sergio rozanski filhoaristeu sergio rozanski filho1290.57%30.56%
kirill a. shutemovkirill a. shutemov1060.47%40.75%
balbir singhbalbir singh860.38%10.19%
vladimir davydovvladimir davydov810.36%61.13%
daniel bristot de oliveiradaniel bristot de oliveira770.34%10.19%
gao fenggao feng490.22%30.56%
stephane eranianstephane eranian450.20%10.19%
lai jiangshanlai jiangshan280.12%40.75%
nick pigginnick piggin200.09%20.38%
joe perchesjoe perches170.07%20.38%
mandeep singh bainesmandeep singh baines160.07%40.75%
kosaki motohirokosaki motohiro140.06%20.38%
gowrishankar mgowrishankar m120.05%10.19%
pavel emelianovpavel emelianov120.05%10.19%
kamezawa hiroyukikamezawa hiroyuki100.04%20.38%
al viroal viro90.04%50.94%
arnd bergmannarnd bergmann90.04%10.19%
eric w. biedermaneric w. biederman90.04%20.38%
peter zijlstrapeter zijlstra90.04%10.19%
jianyu zhanjianyu zhan90.04%20.38%
greg kroah-hartmangreg kroah-hartman80.04%10.19%
frederic weisbeckerfrederic weisbecker80.04%10.19%
kees cookkees cook80.04%20.38%
eric pariseric paris60.03%10.19%
li zhongli zhong60.03%10.19%
linus torvaldslinus torvalds50.02%20.38%
daniel wagnerdaniel wagner50.02%20.38%
dan carpenterdan carpenter40.02%10.19%
hugh dickinshugh dickins40.02%10.19%
wei yongjunwei yongjun40.02%10.19%
daisuke nishimuradaisuke nishimura30.01%20.38%
mike galbraithmike galbraith30.01%10.19%
chen hanxiaochen hanxiao20.01%10.19%
alexey dobriyanalexey dobriyan20.01%10.19%
bandan dasbandan das10.00%10.19%
xiubo lixiubo li10.00%10.19%
mel gormanmel gorman10.00%10.19%
rami rosenrami rosen10.00%10.19%
arun sharmaarun sharma10.00%10.19%
adrian bunkadrian bunk10.00%10.19%
jeff liujeff liu10.00%10.19%
paul e. mckenneypaul e. mckenney10.00%10.19%
wenwei taowenwei tao10.00%10.19%
david howellsdavid howells10.00%10.19%
xiaotian fengxiaotian feng10.00%10.19%
Total22703100.00%533100.00%
Directory: kernel
Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.
{% endraw %}