From: Tejun Heo <tj@kernel.org>
To: void@manifault.com, arighi@nvidia.com, multics69@gmail.com
Cc: linux-kernel@vger.kernel.org, sched-ext@lists.linux.dev,
memxor@gmail.com, bpf@vger.kernel.org, Tejun Heo <tj@kernel.org>
Subject: [PATCH 11/46] sched_ext: Drop kf_cpu_valid()
Date: Fri, 19 Sep 2025 14:58:34 -1000 [thread overview]
Message-ID: <20250920005931.2753828-12-tj@kernel.org> (raw)
In-Reply-To: <20250920005931.2753828-1-tj@kernel.org>
The intention behind kf_cpu_valid() was that when called from kfuncs,
kf_cpu_valid() would be able to implicitly determine the scx_sched instance
being operated on and thus wouldn't need @sch passed in explicitly. This
turned out to be unnecessarily complicated to implement and not have
justifiable practical benefits. Replace kf_cpu_valid() usages with
ops_cpu_valid() which takes explicit @sch.
Callers which don't have $sch available in the context are updated to read
$scx_root under RCU read lock, verify that it's not NULL and pass it in.
scx_bpf_cpu_rq() is restructured to use guard(rcu)() instead of explicit
rcu_read_[un]lock().
Signed-off-by: Tejun Heo <tj@kernel.org>
---
kernel/sched/ext.c | 67 ++++++++++++++++++++++++-----------------
kernel/sched/ext_idle.c | 12 +++++---
2 files changed, 48 insertions(+), 31 deletions(-)
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 373146154829..56ca09f46d1e 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -736,23 +736,6 @@ static bool ops_cpu_valid(struct scx_sched *sch, s32 cpu, const char *where)
}
}
-/**
- * kf_cpu_valid - Verify a CPU number, to be used on kfunc input args
- * @cpu: cpu number which came from a BPF ops
- * @where: extra information reported on error
- *
- * The same as ops_cpu_valid() but @sch is implicit.
- */
-static bool kf_cpu_valid(u32 cpu, const char *where)
-{
- if (__cpu_valid(cpu)) {
- return true;
- } else {
- scx_kf_error("invalid CPU %d%s%s", cpu, where ? " " : "", where ?: "");
- return false;
- }
-}
-
/**
* ops_sanitize_err - Sanitize a -errno value
* @sch: scx_sched to error out on error
@@ -5815,7 +5798,7 @@ static void scx_kick_cpu(struct scx_sched *sch, s32 cpu, u64 flags)
struct rq *this_rq;
unsigned long irq_flags;
- if (!kf_cpu_valid(cpu, NULL))
+ if (!ops_cpu_valid(sch, cpu, NULL))
return;
local_irq_save(irq_flags);
@@ -6224,7 +6207,12 @@ __bpf_kfunc void scx_bpf_dump_bstr(char *fmt, unsigned long long *data,
*/
__bpf_kfunc u32 scx_bpf_cpuperf_cap(s32 cpu)
{
- if (kf_cpu_valid(cpu, NULL))
+ struct scx_sched *sch;
+
+ guard(rcu)();
+
+ sch = rcu_dereference(scx_root);
+ if (likely(sch) && ops_cpu_valid(sch, cpu, NULL))
return arch_scale_cpu_capacity(cpu);
else
return SCX_CPUPERF_ONE;
@@ -6246,7 +6234,12 @@ __bpf_kfunc u32 scx_bpf_cpuperf_cap(s32 cpu)
*/
__bpf_kfunc u32 scx_bpf_cpuperf_cur(s32 cpu)
{
- if (kf_cpu_valid(cpu, NULL))
+ struct scx_sched *sch;
+
+ guard(rcu)();
+
+ sch = rcu_dereference(scx_root);
+ if (likely(sch) && ops_cpu_valid(sch, cpu, NULL))
return arch_scale_freq_capacity(cpu);
else
return SCX_CPUPERF_ONE;
@@ -6268,12 +6261,20 @@ __bpf_kfunc u32 scx_bpf_cpuperf_cur(s32 cpu)
*/
__bpf_kfunc void scx_bpf_cpuperf_set(s32 cpu, u32 perf)
{
+ struct scx_sched *sch;
+
+ guard(rcu)();
+
+ sch = rcu_dereference(sch);
+ if (unlikely(!sch))
+ return;
+
if (unlikely(perf > SCX_CPUPERF_ONE)) {
scx_kf_error("Invalid cpuperf target %u for CPU %d", perf, cpu);
return;
}
- if (kf_cpu_valid(cpu, NULL)) {
+ if (ops_cpu_valid(sch, cpu, NULL)) {
struct rq *rq = cpu_rq(cpu), *locked_rq = scx_locked_rq();
struct rq_flags rf;
@@ -6379,18 +6380,21 @@ __bpf_kfunc struct rq *scx_bpf_cpu_rq(s32 cpu)
{
struct scx_sched *sch;
- if (!kf_cpu_valid(cpu, NULL))
- return NULL;
+ guard(rcu)();
- rcu_read_lock();
sch = rcu_dereference(scx_root);
- if (likely(sch) && !sch->warned_deprecated_rq) {
+ if (unlikely(!sch))
+ return NULL;
+
+ if (!ops_cpu_valid(sch, cpu, NULL))
+ return NULL;
+
+ if (!sch->warned_deprecated_rq) {
printk_deferred(KERN_WARNING "sched_ext: %s() is deprecated; "
"use scx_bpf_locked_rq() when holding rq lock "
"or scx_bpf_cpu_curr() to read remote curr safely.\n", __func__);
sch->warned_deprecated_rq = true;
}
- rcu_read_unlock();
return cpu_rq(cpu);
}
@@ -6425,8 +6429,17 @@ __bpf_kfunc struct rq *scx_bpf_locked_rq(void)
*/
__bpf_kfunc struct task_struct *scx_bpf_cpu_curr(s32 cpu)
{
- if (!kf_cpu_valid(cpu, NULL))
+ struct scx_sched *sch;
+
+ guard(rcu)();
+
+ sch = rcu_dereference(scx_root);
+ if (unlikely(!sch))
return NULL;
+
+ if (!ops_cpu_valid(sch, cpu, NULL))
+ return NULL;
+
return rcu_dereference(cpu_rq(cpu)->curr);
}
diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c
index 6e2504ae7357..a576ec10522e 100644
--- a/kernel/sched/ext_idle.c
+++ b/kernel/sched/ext_idle.c
@@ -864,7 +864,7 @@ static s32 select_cpu_from_kfunc(struct scx_sched *sch, struct task_struct *p,
struct rq_flags rf;
s32 cpu;
- if (!kf_cpu_valid(prev_cpu, NULL))
+ if (!ops_cpu_valid(sch, prev_cpu, NULL))
return -EINVAL;
if (!check_builtin_idle_enabled(sch))
@@ -923,9 +923,13 @@ static s32 select_cpu_from_kfunc(struct scx_sched *sch, struct task_struct *p,
*/
__bpf_kfunc int scx_bpf_cpu_node(s32 cpu)
{
- if (!kf_cpu_valid(cpu, NULL))
- return NUMA_NO_NODE;
+ struct scx_sched *sch;
+
+ guard(rcu)();
+ sch = rcu_dereference(scx_root);
+ if (unlikely(!sch) || !ops_cpu_valid(sch, cpu, NULL))
+ return NUMA_NO_NODE;
return cpu_to_node(cpu);
}
@@ -1154,7 +1158,7 @@ __bpf_kfunc bool scx_bpf_test_and_clear_cpu_idle(s32 cpu)
if (!check_builtin_idle_enabled(sch))
return false;
- if (!kf_cpu_valid(cpu, NULL))
+ if (!ops_cpu_valid(sch, cpu, NULL))
return false;
return scx_idle_test_and_clear_cpu(cpu);
--
2.51.0
next prev parent reply other threads:[~2025-09-20 0:59 UTC|newest]
Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-09-20 0:58 [PATCHSET RFC] sched_ext: Implement cgroup sub-scheduler support Tejun Heo
2025-09-20 0:58 ` [PATCH 01/46] sched_ext: Use rhashtable_lookup() instead of rhashtable_lookup_fast() Tejun Heo
2025-09-20 0:58 ` [PATCH 02/46] sched_ext: Improve SCX_KF_DISPATCH comment Tejun Heo
2025-09-20 0:58 ` [PATCH 03/46] sched_ext: Fix stray scx_root usage in task_can_run_on_remote_rq() Tejun Heo
2025-09-20 0:58 ` [PATCH 04/46] sched_ext: Use bitfields for boolean warning flags Tejun Heo
2025-09-20 0:58 ` [PATCH 05/46] sched_ext: Add SCX_EFLAG_INITIALIZED to indicate successful ops.init() Tejun Heo
2025-09-20 0:58 ` [PATCH 06/46] sched_ext: Make qmap dump operation non-destructive Tejun Heo
2025-09-20 0:58 ` [PATCH 07/46] tools/sched_ext: scx_qmap: Make debug output quieter by default Tejun Heo
2025-09-20 0:58 ` [PATCH 08/46] sched_ext: Separate out scx_kick_cpu() and add @sch to it Tejun Heo
2025-09-20 0:58 ` [PATCH 09/46] sched_ext: Add the @sch parameter to __bstr_format() Tejun Heo
2025-09-20 0:58 ` [PATCH 10/46] sched_ext: Add the @sch parameter to ext_idle helpers Tejun Heo
2025-09-20 0:58 ` Tejun Heo [this message]
2025-09-20 0:58 ` [PATCH 12/46] sched_ext: Add the @sch parameter to scx_dsq_insert_preamble/commit() Tejun Heo
2025-09-20 0:58 ` [PATCH 13/46] sched_ext: Drop scx_kf_exit() and scx_kf_error() Tejun Heo
2025-09-20 0:58 ` [PATCH 14/46] sched_ext: Misc updates around scx_sched instance pointer Tejun Heo
2025-09-20 0:58 ` [PATCH 15/46] sched_ext: Keep dying tasks on a separate list Tejun Heo
2025-09-20 0:58 ` [PATCH 16/46] sched_ext: Implement cgroup subtree iteration for scx_task_iter Tejun Heo
2025-09-20 0:58 ` [PATCH 17/46] sched_ext: Add @kargs to scx_fork() Tejun Heo
2025-09-20 0:58 ` [PATCH 18/46] sched/core: Swap the order between sched_post_fork() and cgroup_post_fork() Tejun Heo
2025-09-20 0:58 ` [PATCH 19/46] cgroup: Expose some cgroup helpers Tejun Heo
2025-09-20 0:58 ` [PATCH 20/46] sched_ext: Update p->scx.disallow warning in scx_init_task() Tejun Heo
2025-09-20 0:58 ` [PATCH 21/46] sched_ext: Minor reorganization of enable/disable path Tejun Heo
2025-09-20 0:58 ` [PATCH 22/46] sched_ext: Factor out scx_claim_exit() from scx_disable() Tejun Heo
2025-09-20 0:58 ` [PATCH 23/46] sched_ext: Introduce cgroup sub-sched support Tejun Heo
2025-09-20 0:58 ` [PATCH 24/46] HACK_NOT_FOR_UPSTREAM: BPF: Implement prog grouping hack Tejun Heo
2025-09-20 0:58 ` [PATCH 25/46] sched_ext: Introduce scx_task_sched[_rcu]() Tejun Heo
2025-09-20 0:58 ` [PATCH 26/46] sched_ext: Introduce scx_prog_sched() Tejun Heo
2025-09-20 0:58 ` [PATCH 27/46] sched_ext: Ignore insertions of not-owned tasks into DSQs Tejun Heo
2025-09-20 0:58 ` [PATCH 28/46] sched_ext: scx_dsq_move() should validate the task belongs to the right scheduler Tejun Heo
2025-09-20 0:58 ` [PATCH 29/46] sched_ext: Refactor task init/exit helpers Tejun Heo
2025-09-20 0:58 ` [PATCH 30/46] sched_ext: Make scx_prio_less() handle multiple schedulers Tejun Heo
2025-09-20 0:58 ` [PATCH 31/46] sched_ext: Move bypass_depth into scx_sched Tejun Heo
2025-09-20 0:58 ` [PATCH 32/46] sched_ext: Make bypass mode sub-sched aware Tejun Heo
2025-09-20 0:58 ` [PATCH 33/46] sched_ext: Factor out scx_dispatch_sched() Tejun Heo
2025-09-20 0:58 ` [PATCH 34/46] sched_ext: When calling ops.dispatch() @prev must be on the same scx_sched Tejun Heo
2025-09-20 0:58 ` [PATCH 35/46] sched_ext: Dispatch from all scx_sched instances Tejun Heo
2025-09-20 0:58 ` [PATCH 36/46] sched_ext: Move scx_dsp_ctx and scx_dsp_max_batch into scx_sched Tejun Heo
2025-09-20 0:59 ` [PATCH 37/46] sched_ext: Make watchdog sub-sched aware Tejun Heo
2025-09-20 0:59 ` [PATCH 38/46] sched_ext: Convert scx_dump_state() spinlock to raw spinlock Tejun Heo
2025-09-20 0:59 ` [PATCH 39/46] sched_ext: Support dumping multiple schedulers and add scheduler identification Tejun Heo
2025-09-20 0:59 ` [PATCH 40/46] sched_ext: Implement cgroup sub-sched enabling and disabling Tejun Heo
2025-09-20 0:59 ` [PATCH 41/46] HACK_NOT_FOR_UPSTREAM: sched_ext: Work around @aux__prog prototype mismatch Tejun Heo
2025-09-20 0:59 ` [PATCH 42/46] sched_ext: Wrap global DSQs in per-node structure Tejun Heo
2025-09-20 0:59 ` [PATCH 43/46] sched_ext: Add bypass DSQ for sub-schedulers Tejun Heo
2025-09-20 0:59 ` [PATCH 44/46] sched_ext: Factor out scx_link_sched() and scx_unlink_sched() Tejun Heo
2025-09-20 0:59 ` [PATCH 45/46] sched_ext: Add rhashtable lookup for sub-schedulers Tejun Heo
2025-09-20 0:59 ` [PATCH 46/46] sched_ext: Add basic building blocks for nested sub-scheduler dispatching 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=20250920005931.2753828-12-tj@kernel.org \
--to=tj@kernel.org \
--cc=arighi@nvidia.com \
--cc=bpf@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=memxor@gmail.com \
--cc=multics69@gmail.com \
--cc=sched-ext@lists.linux.dev \
--cc=void@manifault.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