kevin/linux
1
Fork 0
Code

sched: Allow sched_cgroup_fork() to fail and introduce sched_cancel_fork()

Browse Source 
A new BPF extensible sched_class will need more control over the forking
process. It wants to be able to fail from sched_cgroup_fork() after the new
task's sched_task_group is initialized so that the loaded BPF program can
prepare the task with its cgroup association is established and reject fork
if e.g. allocation fails.

Allow sched_cgroup_fork() to fail by making it return int instead of void
and adding sched_cancel_fork() to undo sched_fork() in the error path.

sched_cgroup_fork() doesn't fail yet and this patch shouldn't cause any
behavior changes.

v2: Patch description updated to detail the expected use.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: David Vernet <dvernet@meta.com>
Acked-by: Josh Don <joshdon@google.com>
Acked-by: Hao Luo <haoluo@google.com>
Acked-by: Barret Rhoden <brho@google.com>
This commit is contained in:
Tejun Heo 2024-06-18 10:09:16 -10:00
parent df268382ad
commit 304b3f2bc0
3 changed files with 19 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
include/linux/sched/task.h
View File

@ -63,7 +63,8 @@ extern asmlinkage void schedule_tail(struct task_struct *prev);
extern void init_idle(struct task_struct *idle, int cpu);
extern int sched_fork(unsigned long clone_flags, struct task_struct *p);
extern void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs);
extern int sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs);
extern void sched_cancel_fork(struct task_struct *p);
extern void sched_post_fork(struct task_struct *p);
extern void sched_dead(struct task_struct *p);

15
kernel/fork.c
View File

@ -2363,7 +2363,7 @@ __latent_entropy struct task_struct *copy_process(
retval = perf_event_init_task(p, clone_flags);
if (retval)
goto bad_fork_cleanup_policy;
goto bad_fork_sched_cancel_fork;
retval = audit_alloc(p);
if (retval)
goto bad_fork_cleanup_perf;
@ -2496,7 +2496,9 @@ __latent_entropy struct task_struct *copy_process(
* cgroup specific, it unconditionally needs to place the task on a
* runqueue.
*/
sched_cgroup_fork(p, args);
retval = sched_cgroup_fork(p, args);
if (retval)
goto bad_fork_cancel_cgroup;
/*
* From this point on we must avoid any synchronous user-space
@ -2542,13 +2544,13 @@ __latent_entropy struct task_struct *copy_process(
/* Don't start children in a dying pid namespace */
if (unlikely(!(ns_of_pid(pid)->pid_allocated & PIDNS_ADDING))) {
retval = -ENOMEM;
goto bad_fork_cancel_cgroup;
goto bad_fork_core_free;
}
/* Let kill terminate clone/fork in the middle */
if (fatal_signal_pending(current)) {
retval = -EINTR;
goto bad_fork_cancel_cgroup;
goto bad_fork_core_free;
}
/* No more failure paths after this point. */
@ -2622,10 +2624,11 @@ __latent_entropy struct task_struct *copy_process(
return p;
bad_fork_cancel_cgroup:
bad_fork_core_free:
sched_core_free(p);
spin_unlock(&current->sighand->siglock);
write_unlock_irq(&tasklist_lock);
bad_fork_cancel_cgroup:
cgroup_cancel_fork(p, args);
bad_fork_put_pidfd:
if (clone_flags & CLONE_PIDFD) {
@ -2664,6 +2667,8 @@ bad_fork_cleanup_audit:
audit_free(p);
bad_fork_cleanup_perf:
perf_event_free_task(p);
bad_fork_sched_cancel_fork:
sched_cancel_fork(p);
bad_fork_cleanup_policy:
lockdep_free_task(p);
#ifdef CONFIG_NUMA

8
kernel/sched/core.c
View File

@ -4609,7 +4609,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
return 0;
}
void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs)
int sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs)
{
unsigned long flags;
@ -4636,6 +4636,12 @@ void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs)
if (p->sched_class->task_fork)
p->sched_class->task_fork(p);
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
return 0;
}
void sched_cancel_fork(struct task_struct *p)
{
}
void sched_post_fork(struct task_struct *p)