extern void cgroup_init_smp(void);
extern void cgroup_lock(void);
extern void cgroup_unlock(void);
+extern void cgroup_fork(struct task_struct *p);
+extern void cgroup_fork_callbacks(struct task_struct *p);
+extern void cgroup_exit(struct task_struct *p, int run_callbacks);
/* Per-subsystem/per-cgroup state maintained by the system. */
struct cgroup_subsys_state {
static inline int cgroup_init_early(void) { return 0; }
static inline int cgroup_init(void) { return 0; }
static inline void cgroup_init_smp(void) {}
+static inline void cgroup_fork(struct task_struct *p) {}
+static inline void cgroup_fork_callbacks(struct task_struct *p) {}
+static inline void cgroup_exit(struct task_struct *p, int callbacks) {}
static inline void cgroup_lock(void) {}
static inline void cgroup_unlock(void) {}
#define for_each_root(_root) \
list_for_each_entry(_root, &roots, root_list)
+/* Each task_struct has an embedded css_set, so the get/put
+ * operation simply takes a reference count on all the cgroups
+ * referenced by subsystems in this css_set. This can end up
+ * multiple-counting some cgroups, but that's OK - the ref-count is
+ * just a busy/not-busy indicator; ensuring that we only count each
+ * cgroup once would require taking a global lock to ensure that no
+ * subsystems moved between hierarchies while we were doing so.
+ *
+ * Possible TODO: decide at boot time based on the number of
+ * registered subsystems and the number of CPUs or NUMA nodes whether
+ * it's better for performance to ref-count every subsystem, or to
+ * take a global lock and only add one ref count to each hierarchy.
+ */
+static void get_css_set(struct css_set *cg)
+{
+ int i;
+ for (i = 0; i < CGROUP_SUBSYS_COUNT; i++)
+ atomic_inc(&cg->subsys[i]->cgroup->count);
+}
+
+static void put_css_set(struct css_set *cg)
+{
+ int i;
+ for (i = 0; i < CGROUP_SUBSYS_COUNT; i++)
+ atomic_dec(&cg->subsys[i]->cgroup->count);
+}
+
/*
* There is one global cgroup mutex. We also require taking
* task_lock() when dereferencing a task's cgroup subsys pointers.
out:
return err;
}
+
+/**
+ * cgroup_fork - attach newly forked task to its parents cgroup.
+ * @tsk: pointer to task_struct of forking parent process.
+ *
+ * Description: A task inherits its parent's cgroup at fork().
+ *
+ * A pointer to the shared css_set was automatically copied in
+ * fork.c by dup_task_struct(). However, we ignore that copy, since
+ * it was not made under the protection of RCU or cgroup_mutex, so
+ * might no longer be a valid cgroup pointer. attach_task() might
+ * have already changed current->cgroup, allowing the previously
+ * referenced cgroup to be removed and freed.
+ *
+ * At the point that cgroup_fork() is called, 'current' is the parent
+ * task, and the passed argument 'child' points to the child task.
+ */
+void cgroup_fork(struct task_struct *child)
+{
+ rcu_read_lock();
+ child->cgroups = rcu_dereference(current->cgroups);
+ get_css_set(&child->cgroups);
+ rcu_read_unlock();
+}
+
+/**
+ * cgroup_fork_callbacks - called on a new task very soon before
+ * adding it to the tasklist. No need to take any locks since no-one
+ * can be operating on this task
+ */
+void cgroup_fork_callbacks(struct task_struct *child)
+{
+ if (need_forkexit_callback) {
+ int i;
+ for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+ struct cgroup_subsys *ss = subsys[i];
+ if (ss->fork)
+ ss->fork(ss, child);
+ }
+ }
+}
+
+/**
+ * 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.
+ *
+ * the_top_cgroup_hack:
+ *
+ * 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.
+ *
+ * To do this properly, we would increment the reference count on
+ * top_cgroup, and near the very end of the kernel/exit.c do_exit()
+ * code we would add a second cgroup function call, to drop that
+ * reference. This would just create an unnecessary hot spot on
+ * the top_cgroup reference count, to no avail.
+ *
+ * Normally, holding a reference to a cgroup without bumping its
+ * count is unsafe. The cgroup could go away, or someone could
+ * attach us to a different cgroup, decrementing the count on
+ * the first cgroup that we never incremented. But in this case,
+ * top_cgroup isn't going away, and either task has PF_EXITING set,
+ * which wards off any attach_task() attempts, or task is a failed
+ * fork, never visible to attach_task.
+ *
+ */
+void cgroup_exit(struct task_struct *tsk, int run_callbacks)
+{
+ int i;
+
+ if (run_callbacks && need_forkexit_callback) {
+ for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+ struct cgroup_subsys *ss = subsys[i];
+ if (ss->exit)
+ ss->exit(ss, tsk);
+ }
+ }
+ /* Reassign the task to the init_css_set. */
+ task_lock(tsk);
+ put_css_set(&tsk->cgroups);
+ tsk->cgroups = init_task.cgroups;
+ task_unlock(tsk);
+}
#include <linux/capability.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
+#include <linux/cgroup.h>
#include <linux/security.h>
#include <linux/swap.h>
#include <linux/syscalls.h>
{
int retval;
struct task_struct *p = NULL;
+ int cgroup_callbacks_done = 0;
if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
return ERR_PTR(-EINVAL);
p->io_context = NULL;
p->audit_context = NULL;
cpuset_fork(p);
+ cgroup_fork(p);
#ifdef CONFIG_NUMA
p->mempolicy = mpol_copy(p->mempolicy);
if (IS_ERR(p->mempolicy)) {
retval = PTR_ERR(p->mempolicy);
p->mempolicy = NULL;
- goto bad_fork_cleanup_cpuset;
+ goto bad_fork_cleanup_cgroup;
}
mpol_fix_fork_child_flag(p);
#endif
/* Perform scheduler related setup. Assign this task to a CPU. */
sched_fork(p, clone_flags);
+ /* Now that the task is set up, run cgroup callbacks if
+ * necessary. We need to run them before the task is visible
+ * on the tasklist. */
+ cgroup_fork_callbacks(p);
+ cgroup_callbacks_done = 1;
+
/* Need tasklist lock for parent etc handling! */
write_lock_irq(&tasklist_lock);
bad_fork_cleanup_policy:
#ifdef CONFIG_NUMA
mpol_free(p->mempolicy);
-bad_fork_cleanup_cpuset:
+bad_fork_cleanup_cgroup:
#endif
cpuset_exit(p);
+ cgroup_exit(p, cgroup_callbacks_done);
bad_fork_cleanup_delays_binfmt:
delayacct_tsk_free(p);
if (p->binfmt)
projects / GitHub / LineageOS / android_kernel_motorola_exynos9610.git / commitdiff