root_task_group.shares = ROOT_TASK_GROUP_LOAD;
init_cfs_bandwidth(&root_task_group.cfs_bandwidth, NULL);
#endif /* CONFIG_FAIR_GROUP_SCHED */
+#ifdef CONFIG_EXT_GROUP_SCHED
+ root_task_group.scx_weight = CGROUP_WEIGHT_DFL;
+#endif /* CONFIG_EXT_GROUP_SCHED */
#ifdef CONFIG_RT_GROUP_SCHED
root_task_group.rt_se = (struct sched_rt_entity **)ptr;
ptr += nr_cpu_ids * sizeof(void **);
if (!alloc_rt_sched_group(tg, parent))
goto err;
+ scx_group_set_weight(tg, CGROUP_WEIGHT_DFL);
alloc_uclamp_sched_group(tg, parent);
return tg;
put_prev_task(rq, tsk);
sched_change_group(tsk, group);
+ scx_move_task(tsk);
if (queued)
enqueue_task(rq, tsk, queue_flags);
{
struct task_group *tg = css_tg(css);
struct task_group *parent = css_tg(css->parent);
+ int ret;
+
+ ret = scx_tg_online(tg);
+ if (ret)
+ return ret;
if (parent)
sched_online_group(tg, parent);
return 0;
}
+static void cpu_cgroup_css_offline(struct cgroup_subsys_state *css)
+{
+ struct task_group *tg = css_tg(css);
+
+ scx_tg_offline(tg);
+}
+
static void cpu_cgroup_css_released(struct cgroup_subsys_state *css)
{
struct task_group *tg = css_tg(css);
sched_unregister_group(tg);
}
-#ifdef CONFIG_RT_GROUP_SCHED
static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
{
+#ifdef CONFIG_RT_GROUP_SCHED
struct task_struct *task;
struct cgroup_subsys_state *css;
if (!sched_rt_can_attach(css_tg(css), task))
return -EINVAL;
}
- return 0;
-}
#endif
+ return scx_cgroup_can_attach(tset);
+}
static void cpu_cgroup_attach(struct cgroup_taskset *tset)
{
cgroup_taskset_for_each(task, css, tset)
sched_move_task(task);
+
+ scx_cgroup_finish_attach();
+}
+
+static void cpu_cgroup_cancel_attach(struct cgroup_taskset *tset)
+{
+ scx_cgroup_cancel_attach(tset);
}
#ifdef CONFIG_UCLAMP_TASK_GROUP
#ifdef CONFIG_GROUP_SCHED_WEIGHT
static unsigned long tg_weight(struct task_group *tg)
{
+#ifdef CONFIG_FAIR_GROUP_SCHED
return scale_load_down(tg->shares);
+#else
+ return sched_weight_from_cgroup(tg->scx_weight);
+#endif
}
static int cpu_shares_write_u64(struct cgroup_subsys_state *css,
struct cftype *cftype, u64 shareval)
{
+ int ret;
+
if (shareval > scale_load_down(ULONG_MAX))
shareval = MAX_SHARES;
- return sched_group_set_shares(css_tg(css), scale_load(shareval));
+ ret = sched_group_set_shares(css_tg(css), scale_load(shareval));
+ if (!ret)
+ scx_group_set_weight(css_tg(css),
+ sched_weight_to_cgroup(shareval));
+ return ret;
}
static u64 cpu_shares_read_u64(struct cgroup_subsys_state *css,
static int cpu_idle_write_s64(struct cgroup_subsys_state *css,
struct cftype *cft, s64 idle)
{
- return sched_group_set_idle(css_tg(css), idle);
+ int ret;
+
+ ret = sched_group_set_idle(css_tg(css), idle);
+ if (!ret)
+ scx_group_set_idle(css_tg(css), idle);
+ return ret;
}
#endif
struct cftype *cft, u64 cgrp_weight)
{
unsigned long weight;
+ int ret;
if (cgrp_weight < CGROUP_WEIGHT_MIN || cgrp_weight > CGROUP_WEIGHT_MAX)
return -ERANGE;
weight = sched_weight_from_cgroup(cgrp_weight);
- return sched_group_set_shares(css_tg(css), scale_load(weight));
+ ret = sched_group_set_shares(css_tg(css), scale_load(weight));
+ if (!ret)
+ scx_group_set_weight(css_tg(css), cgrp_weight);
+ return ret;
}
static s64 cpu_weight_nice_read_s64(struct cgroup_subsys_state *css,
struct cftype *cft, s64 nice)
{
unsigned long weight;
- int idx;
+ int idx, ret;
if (nice < MIN_NICE || nice > MAX_NICE)
return -ERANGE;
idx = array_index_nospec(idx, 40);
weight = sched_prio_to_weight[idx];
- return sched_group_set_shares(css_tg(css), scale_load(weight));
+ ret = sched_group_set_shares(css_tg(css), scale_load(weight));
+ if (!ret)
+ scx_group_set_weight(css_tg(css),
+ sched_weight_to_cgroup(weight));
+ return ret;
}
#endif /* CONFIG_GROUP_SCHED_WEIGHT */
struct cgroup_subsys cpu_cgrp_subsys = {
.css_alloc = cpu_cgroup_css_alloc,
.css_online = cpu_cgroup_css_online,
+ .css_offline = cpu_cgroup_css_offline,
.css_released = cpu_cgroup_css_released,
.css_free = cpu_cgroup_css_free,
.css_extra_stat_show = cpu_extra_stat_show,
.css_local_stat_show = cpu_local_stat_show,
-#ifdef CONFIG_RT_GROUP_SCHED
.can_attach = cpu_cgroup_can_attach,
-#endif
.attach = cpu_cgroup_attach,
+ .cancel_attach = cpu_cgroup_cancel_attach,
.legacy_cftypes = cpu_legacy_files,
.dfl_cftypes = cpu_files,
.early_init = true,
*/
SCX_OPS_SWITCH_PARTIAL = 1LLU << 3,
+ /*
+ * CPU cgroup support flags
+ */
+ SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16, /* cpu.weight */
+
SCX_OPS_ALL_FLAGS = SCX_OPS_KEEP_BUILTIN_IDLE |
SCX_OPS_ENQ_LAST |
SCX_OPS_ENQ_EXITING |
- SCX_OPS_SWITCH_PARTIAL,
+ SCX_OPS_SWITCH_PARTIAL |
+ SCX_OPS_HAS_CGROUP_WEIGHT,
};
/* argument container for ops.init_task() */
* to the scheduler transition path.
*/
bool fork;
+#ifdef CONFIG_EXT_GROUP_SCHED
+ /* the cgroup the task is joining */
+ struct cgroup *cgroup;
+#endif
};
/* argument container for ops.exit_task() */
bool cancelled;
};
+/* argument container for ops->cgroup_init() */
+struct scx_cgroup_init_args {
+ /* the weight of the cgroup [1..10000] */
+ u32 weight;
+};
+
enum scx_cpu_preempt_reason {
/* next task is being scheduled by &sched_class_rt */
SCX_CPU_PREEMPT_RT,
*/
void (*dump_task)(struct scx_dump_ctx *ctx, struct task_struct *p);
+#ifdef CONFIG_EXT_GROUP_SCHED
+ /**
+ * cgroup_init - Initialize a cgroup
+ * @cgrp: cgroup being initialized
+ * @args: init arguments, see the struct definition
+ *
+ * Either the BPF scheduler is being loaded or @cgrp created, initialize
+ * @cgrp for sched_ext. This operation may block.
+ *
+ * Return 0 for success, -errno for failure. An error return while
+ * loading will abort loading of the BPF scheduler. During cgroup
+ * creation, it will abort the specific cgroup creation.
+ */
+ s32 (*cgroup_init)(struct cgroup *cgrp,
+ struct scx_cgroup_init_args *args);
+
+ /**
+ * cgroup_exit - Exit a cgroup
+ * @cgrp: cgroup being exited
+ *
+ * Either the BPF scheduler is being unloaded or @cgrp destroyed, exit
+ * @cgrp for sched_ext. This operation my block.
+ */
+ void (*cgroup_exit)(struct cgroup *cgrp);
+
+ /**
+ * cgroup_prep_move - Prepare a task to be moved to a different cgroup
+ * @p: task being moved
+ * @from: cgroup @p is being moved from
+ * @to: cgroup @p is being moved to
+ *
+ * Prepare @p for move from cgroup @from to @to. This operation may
+ * block and can be used for allocations.
+ *
+ * Return 0 for success, -errno for failure. An error return aborts the
+ * migration.
+ */
+ s32 (*cgroup_prep_move)(struct task_struct *p,
+ struct cgroup *from, struct cgroup *to);
+
+ /**
+ * cgroup_move - Commit cgroup move
+ * @p: task being moved
+ * @from: cgroup @p is being moved from
+ * @to: cgroup @p is being moved to
+ *
+ * Commit the move. @p is dequeued during this operation.
+ */
+ void (*cgroup_move)(struct task_struct *p,
+ struct cgroup *from, struct cgroup *to);
+
+ /**
+ * cgroup_cancel_move - Cancel cgroup move
+ * @p: task whose cgroup move is being canceled
+ * @from: cgroup @p was being moved from
+ * @to: cgroup @p was being moved to
+ *
+ * @p was cgroup_prep_move()'d but failed before reaching cgroup_move().
+ * Undo the preparation.
+ */
+ void (*cgroup_cancel_move)(struct task_struct *p,
+ struct cgroup *from, struct cgroup *to);
+
+ /**
+ * cgroup_set_weight - A cgroup's weight is being changed
+ * @cgrp: cgroup whose weight is being updated
+ * @weight: new weight [1..10000]
+ *
+ * Update @tg's weight to @weight.
+ */
+ void (*cgroup_set_weight)(struct cgroup *cgrp, u32 weight);
+#endif /* CONFIG_CGROUPS */
+
/*
* All online ops must come before ops.cpu_online().
*/
SCX_KICK_WAIT = 1LLU << 2,
};
+enum scx_tg_flags {
+ SCX_TG_ONLINE = 1U << 0,
+ SCX_TG_INITED = 1U << 1,
+};
+
enum scx_ops_enable_state {
SCX_OPS_PREPPING,
SCX_OPS_ENABLING,
resched_curr(rq);
}
+#ifdef CONFIG_EXT_GROUP_SCHED
+static struct cgroup *tg_cgrp(struct task_group *tg)
+{
+ /*
+ * If CGROUP_SCHED is disabled, @tg is NULL. If @tg is an autogroup,
+ * @tg->css.cgroup is NULL. In both cases, @tg can be treated as the
+ * root cgroup.
+ */
+ if (tg && tg->css.cgroup)
+ return tg->css.cgroup;
+ else
+ return &cgrp_dfl_root.cgrp;
+}
+
+#define SCX_INIT_TASK_ARGS_CGROUP(tg) .cgroup = tg_cgrp(tg),
+
+#else /* CONFIG_EXT_GROUP_SCHED */
+
+#define SCX_INIT_TASK_ARGS_CGROUP(tg)
+
+#endif /* CONFIG_EXT_GROUP_SCHED */
+
static enum scx_task_state scx_get_task_state(const struct task_struct *p)
{
return (p->scx.flags & SCX_TASK_STATE_MASK) >> SCX_TASK_STATE_SHIFT;
if (SCX_HAS_OP(init_task)) {
struct scx_init_task_args args = {
+ SCX_INIT_TASK_ARGS_CGROUP(tg)
.fork = fork,
};
scx_set_task_state(p, SCX_TASK_ENABLED);
if (SCX_HAS_OP(set_weight))
- SCX_CALL_OP(SCX_KF_REST, set_weight, p, p->scx.weight);
+ SCX_CALL_OP_TASK(SCX_KF_REST, set_weight, p, p->scx.weight);
}
static void scx_ops_disable_task(struct task_struct *p)
}
#endif
+#ifdef CONFIG_EXT_GROUP_SCHED
+
+DEFINE_STATIC_PERCPU_RWSEM(scx_cgroup_rwsem);
+static bool cgroup_warned_missing_weight;
+static bool cgroup_warned_missing_idle;
+
+static void scx_cgroup_warn_missing_weight(struct task_group *tg)
+{
+ if (scx_ops_enable_state() == SCX_OPS_DISABLED ||
+ cgroup_warned_missing_weight)
+ return;
+
+ if ((scx_ops.flags & SCX_OPS_HAS_CGROUP_WEIGHT) || !tg->css.parent)
+ return;
+
+ pr_warn("sched_ext: \"%s\" does not implement cgroup cpu.weight\n",
+ scx_ops.name);
+ cgroup_warned_missing_weight = true;
+}
+
+static void scx_cgroup_warn_missing_idle(struct task_group *tg)
+{
+ if (scx_ops_enable_state() == SCX_OPS_DISABLED ||
+ cgroup_warned_missing_idle)
+ return;
+
+ if (!tg->idle)
+ return;
+
+ pr_warn("sched_ext: \"%s\" does not implement cgroup cpu.idle\n",
+ scx_ops.name);
+ cgroup_warned_missing_idle = true;
+}
+
+int scx_tg_online(struct task_group *tg)
+{
+ int ret = 0;
+
+ WARN_ON_ONCE(tg->scx_flags & (SCX_TG_ONLINE | SCX_TG_INITED));
+
+ percpu_down_read(&scx_cgroup_rwsem);
+
+ scx_cgroup_warn_missing_weight(tg);
+
+ if (SCX_HAS_OP(cgroup_init)) {
+ struct scx_cgroup_init_args args = { .weight = tg->scx_weight };
+
+ ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init,
+ tg->css.cgroup, &args);
+ if (!ret)
+ tg->scx_flags |= SCX_TG_ONLINE | SCX_TG_INITED;
+ else
+ ret = ops_sanitize_err("cgroup_init", ret);
+ } else {
+ tg->scx_flags |= SCX_TG_ONLINE;
+ }
+
+ percpu_up_read(&scx_cgroup_rwsem);
+ return ret;
+}
+
+void scx_tg_offline(struct task_group *tg)
+{
+ WARN_ON_ONCE(!(tg->scx_flags & SCX_TG_ONLINE));
+
+ percpu_down_read(&scx_cgroup_rwsem);
+
+ if (SCX_HAS_OP(cgroup_exit) && (tg->scx_flags & SCX_TG_INITED))
+ SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, tg->css.cgroup);
+ tg->scx_flags &= ~(SCX_TG_ONLINE | SCX_TG_INITED);
+
+ percpu_up_read(&scx_cgroup_rwsem);
+}
+
+int scx_cgroup_can_attach(struct cgroup_taskset *tset)
+{
+ struct cgroup_subsys_state *css;
+ struct task_struct *p;
+ int ret;
+
+ /* released in scx_finish/cancel_attach() */
+ percpu_down_read(&scx_cgroup_rwsem);
+
+ if (!scx_enabled())
+ return 0;
+
+ cgroup_taskset_for_each(p, css, tset) {
+ struct cgroup *from = tg_cgrp(task_group(p));
+ struct cgroup *to = tg_cgrp(css_tg(css));
+
+ WARN_ON_ONCE(p->scx.cgrp_moving_from);
+
+ /*
+ * sched_move_task() omits identity migrations. Let's match the
+ * behavior so that ops.cgroup_prep_move() and ops.cgroup_move()
+ * always match one-to-one.
+ */
+ if (from == to)
+ continue;
+
+ if (SCX_HAS_OP(cgroup_prep_move)) {
+ ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_prep_move,
+ p, from, css->cgroup);
+ if (ret)
+ goto err;
+ }
+
+ p->scx.cgrp_moving_from = from;
+ }
+
+ return 0;
+
+err:
+ cgroup_taskset_for_each(p, css, tset) {
+ if (SCX_HAS_OP(cgroup_cancel_move) && p->scx.cgrp_moving_from)
+ SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, p,
+ p->scx.cgrp_moving_from, css->cgroup);
+ p->scx.cgrp_moving_from = NULL;
+ }
+
+ percpu_up_read(&scx_cgroup_rwsem);
+ return ops_sanitize_err("cgroup_prep_move", ret);
+}
+
+void scx_move_task(struct task_struct *p)
+{
+ if (!scx_enabled())
+ return;
+
+ /*
+ * We're called from sched_move_task() which handles both cgroup and
+ * autogroup moves. Ignore the latter.
+ *
+ * Also ignore exiting tasks, because in the exit path tasks transition
+ * from the autogroup to the root group, so task_group_is_autogroup()
+ * alone isn't able to catch exiting autogroup tasks. This is safe for
+ * cgroup_move(), because cgroup migrations never happen for PF_EXITING
+ * tasks.
+ */
+ if (task_group_is_autogroup(task_group(p)) || (p->flags & PF_EXITING))
+ return;
+
+ /*
+ * @p must have ops.cgroup_prep_move() called on it and thus
+ * cgrp_moving_from set.
+ */
+ if (SCX_HAS_OP(cgroup_move) && !WARN_ON_ONCE(!p->scx.cgrp_moving_from))
+ SCX_CALL_OP_TASK(SCX_KF_UNLOCKED, cgroup_move, p,
+ p->scx.cgrp_moving_from, tg_cgrp(task_group(p)));
+ p->scx.cgrp_moving_from = NULL;
+}
+
+void scx_cgroup_finish_attach(void)
+{
+ percpu_up_read(&scx_cgroup_rwsem);
+}
+
+void scx_cgroup_cancel_attach(struct cgroup_taskset *tset)
+{
+ struct cgroup_subsys_state *css;
+ struct task_struct *p;
+
+ if (!scx_enabled())
+ goto out_unlock;
+
+ cgroup_taskset_for_each(p, css, tset) {
+ if (SCX_HAS_OP(cgroup_cancel_move) && p->scx.cgrp_moving_from)
+ SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, p,
+ p->scx.cgrp_moving_from, css->cgroup);
+ p->scx.cgrp_moving_from = NULL;
+ }
+out_unlock:
+ percpu_up_read(&scx_cgroup_rwsem);
+}
+
+void scx_group_set_weight(struct task_group *tg, unsigned long weight)
+{
+ percpu_down_read(&scx_cgroup_rwsem);
+
+ if (tg->scx_weight != weight) {
+ if (SCX_HAS_OP(cgroup_set_weight))
+ SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_set_weight,
+ tg_cgrp(tg), weight);
+ tg->scx_weight = weight;
+ }
+
+ percpu_up_read(&scx_cgroup_rwsem);
+}
+
+void scx_group_set_idle(struct task_group *tg, bool idle)
+{
+ percpu_down_read(&scx_cgroup_rwsem);
+ scx_cgroup_warn_missing_idle(tg);
+ percpu_up_read(&scx_cgroup_rwsem);
+}
+
+static void scx_cgroup_lock(void)
+{
+ percpu_down_write(&scx_cgroup_rwsem);
+}
+
+static void scx_cgroup_unlock(void)
+{
+ percpu_up_write(&scx_cgroup_rwsem);
+}
+
+#else /* CONFIG_EXT_GROUP_SCHED */
+
+static inline void scx_cgroup_lock(void) {}
+static inline void scx_cgroup_unlock(void) {}
+
+#endif /* CONFIG_EXT_GROUP_SCHED */
+
/*
* Omitted operations:
*
rcu_read_unlock();
}
+#ifdef CONFIG_EXT_GROUP_SCHED
+static void scx_cgroup_exit(void)
+{
+ struct cgroup_subsys_state *css;
+
+ percpu_rwsem_assert_held(&scx_cgroup_rwsem);
+
+ /*
+ * scx_tg_on/offline() are excluded through scx_cgroup_rwsem. If we walk
+ * cgroups and exit all the inited ones, all online cgroups are exited.
+ */
+ rcu_read_lock();
+ css_for_each_descendant_post(css, &root_task_group.css) {
+ struct task_group *tg = css_tg(css);
+
+ if (!(tg->scx_flags & SCX_TG_INITED))
+ continue;
+ tg->scx_flags &= ~SCX_TG_INITED;
+
+ if (!scx_ops.cgroup_exit)
+ continue;
+
+ if (WARN_ON_ONCE(!css_tryget(css)))
+ continue;
+ rcu_read_unlock();
+
+ SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, css->cgroup);
+
+ rcu_read_lock();
+ css_put(css);
+ }
+ rcu_read_unlock();
+}
+
+static int scx_cgroup_init(void)
+{
+ struct cgroup_subsys_state *css;
+ int ret;
+
+ percpu_rwsem_assert_held(&scx_cgroup_rwsem);
+
+ cgroup_warned_missing_weight = false;
+ cgroup_warned_missing_idle = false;
+
+ /*
+ * scx_tg_on/offline() are excluded thorugh scx_cgroup_rwsem. If we walk
+ * cgroups and init, all online cgroups are initialized.
+ */
+ rcu_read_lock();
+ css_for_each_descendant_pre(css, &root_task_group.css) {
+ struct task_group *tg = css_tg(css);
+ struct scx_cgroup_init_args args = { .weight = tg->scx_weight };
+
+ scx_cgroup_warn_missing_weight(tg);
+ scx_cgroup_warn_missing_idle(tg);
+
+ if ((tg->scx_flags &
+ (SCX_TG_ONLINE | SCX_TG_INITED)) != SCX_TG_ONLINE)
+ continue;
+
+ if (!scx_ops.cgroup_init) {
+ tg->scx_flags |= SCX_TG_INITED;
+ continue;
+ }
+
+ if (WARN_ON_ONCE(!css_tryget(css)))
+ continue;
+ rcu_read_unlock();
+
+ ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init,
+ css->cgroup, &args);
+ if (ret) {
+ css_put(css);
+ return ret;
+ }
+ tg->scx_flags |= SCX_TG_INITED;
+
+ rcu_read_lock();
+ css_put(css);
+ }
+ rcu_read_unlock();
+
+ return 0;
+}
+
+#else
+static void scx_cgroup_exit(void) {}
+static int scx_cgroup_init(void) { return 0; }
+#endif
+
/********************************************************************************
* Sysfs interface and ops enable/disable.
WRITE_ONCE(scx_switching_all, false);
/*
- * Avoid racing against fork. See scx_ops_enable() for explanation on
- * the locking order.
+ * Avoid racing against fork and cgroup changes. See scx_ops_enable()
+ * for explanation on the locking order.
*/
percpu_down_write(&scx_fork_rwsem);
cpus_read_lock();
+ scx_cgroup_lock();
spin_lock_irq(&scx_tasks_lock);
scx_task_iter_init(&sti);
static_branch_disable_cpuslocked(&scx_builtin_idle_enabled);
synchronize_rcu();
+ scx_cgroup_exit();
+
+ scx_cgroup_unlock();
cpus_read_unlock();
percpu_up_write(&scx_fork_rwsem);
scx_watchdog_timeout / 2);
/*
- * Lock out forks before opening the floodgate so that they don't wander
- * into the operations prematurely.
+ * Lock out forks, cgroup on/offlining and moves before opening the
+ * floodgate so that they don't wander into the operations prematurely.
+ *
+ * We don't need to keep the CPUs stable but static_branch_*() requires
+ * cpus_read_lock() and scx_cgroup_rwsem must nest inside
+ * cpu_hotplug_lock because of the following dependency chain:
+ *
+ * cpu_hotplug_lock --> cgroup_threadgroup_rwsem --> scx_cgroup_rwsem
*
- * We don't need to keep the CPUs stable but grab cpus_read_lock() to
- * ease future locking changes for cgroup suport.
+ * So, we need to do cpus_read_lock() before scx_cgroup_lock() and use
+ * static_branch_*_cpuslocked().
*
* Note that cpu_hotplug_lock must nest inside scx_fork_rwsem due to the
* following dependency chain:
*/
percpu_down_write(&scx_fork_rwsem);
cpus_read_lock();
+ scx_cgroup_lock();
check_hotplug_seq(ops);
static_branch_disable_cpuslocked(&scx_builtin_idle_enabled);
}
+ /*
+ * All cgroups should be initialized before letting in tasks. cgroup
+ * on/offlining and task migrations are already locked out.
+ */
+ ret = scx_cgroup_init();
+ if (ret)
+ goto err_disable_unlock_all;
+
static_branch_enable_cpuslocked(&__scx_ops_enabled);
/*
spin_unlock_irq(&scx_tasks_lock);
preempt_enable();
+ scx_cgroup_unlock();
cpus_read_unlock();
percpu_up_write(&scx_fork_rwsem);
return ret;
err_disable_unlock_all:
+ scx_cgroup_unlock();
percpu_up_write(&scx_fork_rwsem);
err_disable_unlock_cpus:
cpus_read_unlock();
switch (moff) {
case offsetof(struct sched_ext_ops, init_task):
+#ifdef CONFIG_EXT_GROUP_SCHED
+ case offsetof(struct sched_ext_ops, cgroup_init):
+ case offsetof(struct sched_ext_ops, cgroup_exit):
+ case offsetof(struct sched_ext_ops, cgroup_prep_move):
+#endif
case offsetof(struct sched_ext_ops, cpu_online):
case offsetof(struct sched_ext_ops, cpu_offline):
case offsetof(struct sched_ext_ops, init):
static void exit_task_stub(struct task_struct *p, struct scx_exit_task_args *args) {}
static void enable_stub(struct task_struct *p) {}
static void disable_stub(struct task_struct *p) {}
+#ifdef CONFIG_EXT_GROUP_SCHED
+static s32 cgroup_init_stub(struct cgroup *cgrp, struct scx_cgroup_init_args *args) { return -EINVAL; }
+static void cgroup_exit_stub(struct cgroup *cgrp) {}
+static s32 cgroup_prep_move_stub(struct task_struct *p, struct cgroup *from, struct cgroup *to) { return -EINVAL; }
+static void cgroup_move_stub(struct task_struct *p, struct cgroup *from, struct cgroup *to) {}
+static void cgroup_cancel_move_stub(struct task_struct *p, struct cgroup *from, struct cgroup *to) {}
+static void cgroup_set_weight_stub(struct cgroup *cgrp, u32 weight) {}
+#endif
static void cpu_online_stub(s32 cpu) {}
static void cpu_offline_stub(s32 cpu) {}
static s32 init_stub(void) { return -EINVAL; }
.exit_task = exit_task_stub,
.enable = enable_stub,
.disable = disable_stub,
+#ifdef CONFIG_EXT_GROUP_SCHED
+ .cgroup_init = cgroup_init_stub,
+ .cgroup_exit = cgroup_exit_stub,
+ .cgroup_prep_move = cgroup_prep_move_stub,
+ .cgroup_move = cgroup_move_stub,
+ .cgroup_cancel_move = cgroup_cancel_move_stub,
+ .cgroup_set_weight = cgroup_set_weight_stub,
+#endif
.cpu_online = cpu_online_stub,
.cpu_offline = cpu_offline_stub,
.init = init_stub,
* definitions so that BPF scheduler implementations can use them
* through the generated vmlinux.h.
*/
- WRITE_ONCE(v, SCX_ENQ_WAKEUP | SCX_DEQ_SLEEP | SCX_KICK_PREEMPT);
+ WRITE_ONCE(v, SCX_ENQ_WAKEUP | SCX_DEQ_SLEEP | SCX_KICK_PREEMPT |
+ SCX_TG_ONLINE);
BUG_ON(rhashtable_init(&dsq_hash, &dsq_hash_params));
init_dsq(&scx_dsq_global, SCX_DSQ_GLOBAL);
return cpu_rq(cpu);
}
+/**
+ * scx_bpf_task_cgroup - Return the sched cgroup of a task
+ * @p: task of interest
+ *
+ * @p->sched_task_group->css.cgroup represents the cgroup @p is associated with
+ * from the scheduler's POV. SCX operations should use this function to
+ * determine @p's current cgroup as, unlike following @p->cgroups,
+ * @p->sched_task_group is protected by @p's rq lock and thus atomic w.r.t. all
+ * rq-locked operations. Can be called on the parameter tasks of rq-locked
+ * operations. The restriction guarantees that @p's rq is locked by the caller.
+ */
+#ifdef CONFIG_CGROUP_SCHED
+__bpf_kfunc struct cgroup *scx_bpf_task_cgroup(struct task_struct *p)
+{
+ struct task_group *tg = p->sched_task_group;
+ struct cgroup *cgrp = &cgrp_dfl_root.cgrp;
+
+ if (!scx_kf_allowed_on_arg_tasks(__SCX_KF_RQ_LOCKED, p))
+ goto out;
+
+ /*
+ * A task_group may either be a cgroup or an autogroup. In the latter
+ * case, @tg->css.cgroup is %NULL. A task_group can't become the other
+ * kind once created.
+ */
+ if (tg && tg->css.cgroup)
+ cgrp = tg->css.cgroup;
+ else
+ cgrp = &cgrp_dfl_root.cgrp;
+out:
+ cgroup_get(cgrp);
+ return cgrp;
+}
+#endif
+
__bpf_kfunc_end_defs();
BTF_KFUNCS_START(scx_kfunc_ids_any)
BTF_ID_FLAGS(func, scx_bpf_task_running, KF_RCU)
BTF_ID_FLAGS(func, scx_bpf_task_cpu, KF_RCU)
BTF_ID_FLAGS(func, scx_bpf_cpu_rq)
+#ifdef CONFIG_CGROUP_SCHED
+BTF_ID_FLAGS(func, scx_bpf_task_cgroup, KF_RCU | KF_ACQUIRE)
+#endif
BTF_KFUNCS_END(scx_kfunc_ids_any)
static const struct btf_kfunc_id_set scx_kfunc_set_any = {
projects / nvme.git / commitdiff