Tejun Heo d6f3e7d564 sched_ext: Fix incorrect autogroup migration detection
scx_move_task() is called from sched_move_task() and tells the BPF scheduler
that cgroup migration is being committed. sched_move_task() is used by both
cgroup and autogroup migrations and scx_move_task() tried to filter out
autogroup migrations by testing the destination cgroup and PF_EXITING but
this is not enough. In fact, without explicitly tagging the thread which is
doing the cgroup migration, there is no good way to tell apart
scx_move_task() invocations for racing migration to the root cgroup and an
autogroup migration.

This led to scx_move_task() incorrectly ignoring a migration from non-root
cgroup to an autogroup of the root cgroup triggering the following warning:

  WARNING: CPU: 7 PID: 1 at kernel/sched/ext.c:3725 scx_cgroup_can_attach+0x196/0x340
  ...
  Call Trace:
  <TASK>
    cgroup_migrate_execute+0x5b1/0x700
    cgroup_attach_task+0x296/0x400
    __cgroup_procs_write+0x128/0x140
    cgroup_procs_write+0x17/0x30
    kernfs_fop_write_iter+0x141/0x1f0
    vfs_write+0x31d/0x4a0
    __x64_sys_write+0x72/0xf0
    do_syscall_64+0x82/0x160
    entry_SYSCALL_64_after_hwframe+0x76/0x7e

Fix it by adding an argument to sched_move_task() that indicates whether the
moving is for a cgroup or autogroup migration. After the change,
scx_move_task() is called only for cgroup migrations and renamed to
scx_cgroup_move_task().

Link: https://github.com/sched-ext/scx/issues/370
Fixes: 819513666966 ("sched_ext: Add cgroup support")
Cc: stable@vger.kernel.org # v6.12+
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
2025-01-27 08:31:50 -10:00

92 lines
3.5 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
/*
* BPF extensible scheduler class: Documentation/scheduler/sched-ext.rst
*
* Copyright (c) 2022 Meta Platforms, Inc. and affiliates.
* Copyright (c) 2022 Tejun Heo <tj@kernel.org>
* Copyright (c) 2022 David Vernet <dvernet@meta.com>
*/
#ifdef CONFIG_SCHED_CLASS_EXT
void scx_tick(struct rq *rq);
void init_scx_entity(struct sched_ext_entity *scx);
void scx_pre_fork(struct task_struct *p);
int scx_fork(struct task_struct *p);
void scx_post_fork(struct task_struct *p);
void scx_cancel_fork(struct task_struct *p);
bool scx_can_stop_tick(struct rq *rq);
void scx_rq_activate(struct rq *rq);
void scx_rq_deactivate(struct rq *rq);
int scx_check_setscheduler(struct task_struct *p, int policy);
bool task_should_scx(int policy);
void init_sched_ext_class(void);
static inline u32 scx_cpuperf_target(s32 cpu)
{
if (scx_enabled())
return cpu_rq(cpu)->scx.cpuperf_target;
else
return 0;
}
static inline bool task_on_scx(const struct task_struct *p)
{
return scx_enabled() && p->sched_class == &ext_sched_class;
}
#ifdef CONFIG_SCHED_CORE
bool scx_prio_less(const struct task_struct *a, const struct task_struct *b,
bool in_fi);
#endif
#else /* CONFIG_SCHED_CLASS_EXT */
static inline void scx_tick(struct rq *rq) {}
static inline void scx_pre_fork(struct task_struct *p) {}
static inline int scx_fork(struct task_struct *p) { return 0; }
static inline void scx_post_fork(struct task_struct *p) {}
static inline void scx_cancel_fork(struct task_struct *p) {}
static inline u32 scx_cpuperf_target(s32 cpu) { return 0; }
static inline bool scx_can_stop_tick(struct rq *rq) { return true; }
static inline void scx_rq_activate(struct rq *rq) {}
static inline void scx_rq_deactivate(struct rq *rq) {}
static inline int scx_check_setscheduler(struct task_struct *p, int policy) { return 0; }
static inline bool task_on_scx(const struct task_struct *p) { return false; }
static inline void init_sched_ext_class(void) {}
#endif /* CONFIG_SCHED_CLASS_EXT */
#if defined(CONFIG_SCHED_CLASS_EXT) && defined(CONFIG_SMP)
void __scx_update_idle(struct rq *rq, bool idle, bool do_notify);
static inline void scx_update_idle(struct rq *rq, bool idle, bool do_notify)
{
if (scx_enabled())
__scx_update_idle(rq, idle, do_notify);
}
#else
static inline void scx_update_idle(struct rq *rq, bool idle, bool do_notify) {}
#endif
#ifdef CONFIG_CGROUP_SCHED
#ifdef CONFIG_EXT_GROUP_SCHED
int scx_tg_online(struct task_group *tg);
void scx_tg_offline(struct task_group *tg);
int scx_cgroup_can_attach(struct cgroup_taskset *tset);
void scx_cgroup_move_task(struct task_struct *p);
void scx_cgroup_finish_attach(void);
void scx_cgroup_cancel_attach(struct cgroup_taskset *tset);
void scx_group_set_weight(struct task_group *tg, unsigned long cgrp_weight);
void scx_group_set_idle(struct task_group *tg, bool idle);
#else /* CONFIG_EXT_GROUP_SCHED */
static inline int scx_tg_online(struct task_group *tg) { return 0; }
static inline void scx_tg_offline(struct task_group *tg) {}
static inline int scx_cgroup_can_attach(struct cgroup_taskset *tset) { return 0; }
static inline void scx_cgroup_move_task(struct task_struct *p) {}
static inline void scx_cgroup_finish_attach(void) {}
static inline void scx_cgroup_cancel_attach(struct cgroup_taskset *tset) {}
static inline void scx_group_set_weight(struct task_group *tg, unsigned long cgrp_weight) {}
static inline void scx_group_set_idle(struct task_group *tg, bool idle) {}
#endif /* CONFIG_EXT_GROUP_SCHED */
#endif /* CONFIG_CGROUP_SCHED */