From: Tejun Heo <tj@kernel.org>
To: torvalds@linux-foundation.org, mingo@redhat.com,
peterz@infradead.org, juri.lelli@redhat.com,
vincent.guittot@linaro.org, dietmar.eggemann@arm.com,
rostedt@goodmis.org, bsegall@google.com, mgorman@suse.de,
bristot@redhat.com, vschneid@redhat.com, ast@kernel.org,
daniel@iogearbox.net, andrii@kernel.org, martin.lau@kernel.org,
joshdon@google.com, brho@google.com, pjt@google.com,
derkling@google.com, haoluo@google.com, dvernet@meta.com,
dschatzberg@meta.com, dskarlat@cs.cmu.edu, riel@surriel.com,
changwoo@igalia.com, himadrics@inria.fr, memxor@gmail.com
Cc: linux-kernel@vger.kernel.org, bpf@vger.kernel.org,
kernel-team@meta.com, Tejun Heo <tj@kernel.org>
Subject: [PATCH 03/36] sched: Allow sched_cgroup_fork() to fail and introduce sched_cancel_fork()
Date: Fri, 10 Nov 2023 16:47:29 -1000 [thread overview]
Message-ID: <20231111024835.2164816-4-tj@kernel.org> (raw)
In-Reply-To: <20231111024835.2164816-1-tj@kernel.org>
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>
---
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 a23af225c898..03d35e3eda3c 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -61,7 +61,8 @@ 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 204bc1c33533..38c5d142c691 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2472,7 +2472,7 @@ __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;
@@ -2604,7 +2604,9 @@ __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
@@ -2650,13 +2652,13 @@ __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. */
@@ -2732,10 +2734,11 @@ __latent_entropy struct task_struct *copy_process(
return p;
-bad_fork_cancel_cgroup:
+bad_fork_core_free:
sched_core_free(p);
spin_unlock(¤t->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) {
@@ -2774,6 +2777,8 @@ __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 5c0ef271a31a..b5fb4b894477 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4784,7 +4784,7 @@ 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;
@@ -4811,6 +4811,12 @@ 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)
--
2.42.0
next prev parent reply other threads:[~2023-11-11 2:49 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-11-11 2:47 [PATCHSET v5] sched: Implement BPF extensible scheduler class Tejun Heo
2023-11-11 2:47 ` [PATCH 01/36] cgroup: Implement cgroup_show_cftypes() Tejun Heo
2023-11-11 2:47 ` [PATCH 02/36] sched: Restructure sched_class order sanity checks in sched_init() Tejun Heo
2023-11-11 2:47 ` Tejun Heo [this message]
2023-11-11 2:47 ` [PATCH 04/36] sched: Add sched_class->reweight_task() Tejun Heo
2023-11-11 2:47 ` [PATCH 05/36] sched: Add sched_class->switching_to() and expose check_class_changing/changed() Tejun Heo
2023-11-11 2:47 ` [PATCH 06/36] sched: Factor out cgroup weight conversion functions Tejun Heo
2023-11-11 2:47 ` [PATCH 07/36] sched: Expose css_tg() and __setscheduler_prio() Tejun Heo
2023-11-11 2:47 ` [PATCH 08/36] sched: Enumerate CPU cgroup file types Tejun Heo
2023-11-11 2:47 ` [PATCH 09/36] sched: Add @reason to sched_class->rq_{on|off}line() Tejun Heo
2023-11-11 2:47 ` [PATCH 10/36] sched: Add normal_policy() Tejun Heo
2023-11-11 2:47 ` [PATCH 11/36] sched_ext: Add boilerplate for extensible scheduler class Tejun Heo
2023-11-11 2:47 ` [PATCH 12/36] sched_ext: Implement BPF " Tejun Heo
2023-11-13 13:34 ` Changwoo Min
2023-11-14 19:07 ` Tejun Heo
2023-11-13 20:04 ` Andrea Righi
2023-11-14 19:07 ` Tejun Heo
2023-11-23 8:07 ` Andrea Righi
2023-11-25 19:59 ` Tejun Heo
2023-11-26 9:05 ` Andrea Righi
2023-12-07 2:04 ` [PATCH] scx: set p->scx.ops_state using atomic_long_set_release Changwoo Min
2023-12-08 0:16 ` Tejun Heo
2024-03-23 2:37 ` [PATCH 12/36] sched_ext: Implement BPF extensible scheduler class Joel Fernandes
2024-03-23 22:12 ` Tejun Heo
2024-04-25 21:28 ` Joel Fernandes
2024-04-26 16:57 ` Barret Rhoden
2024-04-26 21:58 ` Tejun Heo
2023-11-11 2:47 ` [PATCH 13/36] sched_ext: Add scx_simple and scx_example_qmap example schedulers Tejun Heo
2023-11-12 4:17 ` kernel test robot
2023-11-12 18:06 ` Tejun Heo
2023-11-11 2:47 ` [PATCH 14/36] sched_ext: Add sysrq-S which disables the BPF scheduler Tejun Heo
2023-11-11 2:47 ` [PATCH 15/36] sched_ext: Implement runnable task stall watchdog Tejun Heo
2023-11-11 2:47 ` [PATCH 16/36] sched_ext: Allow BPF schedulers to disallow specific tasks from joining SCHED_EXT Tejun Heo
2023-11-11 2:47 ` [PATCH 17/36] sched_ext: Allow BPF schedulers to switch all eligible tasks into sched_ext Tejun Heo
2023-11-11 2:47 ` [PATCH 18/36] sched_ext: Print sched_ext info when dumping stack Tejun Heo
2023-11-14 19:23 ` [PATCH v2 " Tejun Heo
2023-11-11 2:47 ` [PATCH 19/36] sched_ext: Implement scx_bpf_kick_cpu() and task preemption support Tejun Heo
2023-11-11 2:47 ` [PATCH 20/36] sched_ext: Add a central scheduler which makes all scheduling decisions on one CPU Tejun Heo
2023-11-11 2:47 ` [PATCH 21/36] sched_ext: Make watchdog handle ops.dispatch() looping stall Tejun Heo
2023-11-11 2:47 ` [PATCH 22/36] sched_ext: Add task state tracking operations Tejun Heo
2023-11-11 2:47 ` [PATCH 23/36] sched_ext: Implement tickless support Tejun Heo
2023-11-11 2:47 ` [PATCH 24/36] sched_ext: Track tasks that are subjects of the in-flight SCX operation Tejun Heo
2023-11-11 2:47 ` [PATCH 25/36] sched_ext: Add cgroup support Tejun Heo
2023-11-11 2:47 ` [PATCH 26/36] sched_ext: Add a cgroup-based core-scheduling scheduler Tejun Heo
2023-11-11 2:47 ` [PATCH 27/36] sched_ext: Add a cgroup scheduler which uses flattened hierarchy Tejun Heo
2023-11-11 2:47 ` [PATCH 28/36] sched_ext: Implement SCX_KICK_WAIT Tejun Heo
2023-11-11 2:47 ` [PATCH 29/36] sched_ext: Implement sched_ext_ops.cpu_acquire/release() Tejun Heo
2023-11-11 2:47 ` [PATCH 30/36] sched_ext: Implement sched_ext_ops.cpu_online/offline() Tejun Heo
2023-11-11 2:47 ` [PATCH 31/36] sched_ext: Implement core-sched support Tejun Heo
2023-11-11 2:47 ` [PATCH 32/36] sched_ext: Add vtime-ordered priority queue to dispatch_q's Tejun Heo
2023-11-11 2:47 ` [PATCH 33/36] sched_ext: Documentation: scheduler: Document extensible scheduler class Tejun Heo
2023-11-11 2:48 ` [PATCH 34/36] sched_ext: Add a basic, userland vruntime scheduler Tejun Heo
2023-11-11 2:48 ` [PATCH 35/36] sched_ext: Add scx_rusty, a rust userspace hybrid scheduler Tejun Heo
2023-11-11 2:48 ` [PATCH 36/36] sched_ext: Add scx_layered, a highly configurable multi-layer scheduler Tejun Heo
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20231111024835.2164816-4-tj@kernel.org \
--to=tj@kernel.org \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=brho@google.com \
--cc=bristot@redhat.com \
--cc=bsegall@google.com \
--cc=changwoo@igalia.com \
--cc=daniel@iogearbox.net \
--cc=derkling@google.com \
--cc=dietmar.eggemann@arm.com \
--cc=dschatzberg@meta.com \
--cc=dskarlat@cs.cmu.edu \
--cc=dvernet@meta.com \
--cc=haoluo@google.com \
--cc=himadrics@inria.fr \
--cc=joshdon@google.com \
--cc=juri.lelli@redhat.com \
--cc=kernel-team@meta.com \
--cc=linux-kernel@vger.kernel.org \
--cc=martin.lau@kernel.org \
--cc=memxor@gmail.com \
--cc=mgorman@suse.de \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=pjt@google.com \
--cc=riel@surriel.com \
--cc=rostedt@goodmis.org \
--cc=torvalds@linux-foundation.org \
--cc=vincent.guittot@linaro.org \
--cc=vschneid@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).