[PATCH 03/34] sched: Allow sched_cgroup_fork() to fail and introduce sched_cancel_fork()

From: Tejun Heo
Date: Mon Jul 10 2023 - 21:14:42 EST


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@xxxxxxxxxx>
Reviewed-by: David Vernet <dvernet@xxxxxxxx>
Acked-by: Josh Don <joshdon@xxxxxxxxxx>
Acked-by: Hao Luo <haoluo@xxxxxxxxxx>
Acked-by: Barret Rhoden <brho@xxxxxxxxxx>
---
include/linux/sched/task.h | 3 ++-
kernel/fork.c | 15 ++++++++++-----
kernel/sched/core.c | 8 +++++++-
3 files changed, 19 insertions(+), 7 deletions(-)

diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 537cbf9a2ade..5431b350ed96 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -62,7 +62,8 @@ 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);

diff --git a/kernel/fork.c b/kernel/fork.c
index ed4e01daccaa..0a9c8c03889f 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2480,7 +2480,7 @@ __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;
@@ -2615,7 +2615,9 @@ __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
@@ -2661,13 +2663,13 @@ __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. */
@@ -2743,10 +2745,11 @@ __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) {
@@ -2785,6 +2788,8 @@ __latent_entropy struct task_struct *copy_process(
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
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 173a42336d54..a869236d0735 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4749,7 +4749,7 @@ 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;

@@ -4776,6 +4776,12 @@ 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)
--
2.41.0