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
Cc: linux-kernel@vger.kernel.org, bpf@vger.kernel.org,
kernel-team@meta.com, Tejun Heo <tj@kernel.org>
Subject: [PATCH 10/32] sched: Add @reason to sched_class->rq_{on|off}line()
Date: Fri, 17 Mar 2023 11:33:11 -1000 [thread overview]
Message-ID: <20230317213333.2174969-11-tj@kernel.org> (raw)
In-Reply-To: <20230317213333.2174969-1-tj@kernel.org>
->rq_{on|off}line are called either during CPU hotplug or cpuset partition
updates. A planned BPF extensible sched_class wants to tell the BPF
scheduler progs about CPU hotplug events in a way that's synchronized with
rq state changes.
As the BPF scheduler progs aren't necessarily affected by cpuset partition
updates, we need a way to distinguish the two types of events. Let's add an
argument to tell them apart.
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>
---
kernel/sched/core.c | 12 ++++++------
kernel/sched/deadline.c | 4 ++--
kernel/sched/fair.c | 4 ++--
kernel/sched/rt.c | 4 ++--
kernel/sched/sched.h | 13 +++++++++----
kernel/sched/topology.c | 4 ++--
6 files changed, 23 insertions(+), 18 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 59136fafa94c..aa63371aa84c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -9428,7 +9428,7 @@ static inline void balance_hotplug_wait(void)
#endif /* CONFIG_HOTPLUG_CPU */
-void set_rq_online(struct rq *rq)
+void set_rq_online(struct rq *rq, enum rq_onoff_reason reason)
{
if (!rq->online) {
const struct sched_class *class;
@@ -9438,19 +9438,19 @@ void set_rq_online(struct rq *rq)
for_each_class(class) {
if (class->rq_online)
- class->rq_online(rq);
+ class->rq_online(rq, reason);
}
}
}
-void set_rq_offline(struct rq *rq)
+void set_rq_offline(struct rq *rq, enum rq_onoff_reason reason)
{
if (rq->online) {
const struct sched_class *class;
for_each_class(class) {
if (class->rq_offline)
- class->rq_offline(rq);
+ class->rq_offline(rq, reason);
}
cpumask_clear_cpu(rq->cpu, rq->rd->online);
@@ -9546,7 +9546,7 @@ int sched_cpu_activate(unsigned int cpu)
rq_lock_irqsave(rq, &rf);
if (rq->rd) {
BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
- set_rq_online(rq);
+ set_rq_online(rq, RQ_ONOFF_HOTPLUG);
}
rq_unlock_irqrestore(rq, &rf);
@@ -9591,7 +9591,7 @@ int sched_cpu_deactivate(unsigned int cpu)
if (rq->rd) {
update_rq_clock(rq);
BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
- set_rq_offline(rq);
+ set_rq_offline(rq, RQ_ONOFF_HOTPLUG);
}
rq_unlock_irqrestore(rq, &rf);
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 71b24371a6f7..a7bb573c4c82 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2518,7 +2518,7 @@ static void set_cpus_allowed_dl(struct task_struct *p,
}
/* Assumes rq->lock is held */
-static void rq_online_dl(struct rq *rq)
+static void rq_online_dl(struct rq *rq, enum rq_onoff_reason reason)
{
if (rq->dl.overloaded)
dl_set_overload(rq);
@@ -2529,7 +2529,7 @@ static void rq_online_dl(struct rq *rq)
}
/* Assumes rq->lock is held */
-static void rq_offline_dl(struct rq *rq)
+static void rq_offline_dl(struct rq *rq, enum rq_onoff_reason reason)
{
if (rq->dl.overloaded)
dl_clear_overload(rq);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 681ab0dd0bc1..28204472a3f1 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -11805,14 +11805,14 @@ void trigger_load_balance(struct rq *rq)
nohz_balancer_kick(rq);
}
-static void rq_online_fair(struct rq *rq)
+static void rq_online_fair(struct rq *rq, enum rq_onoff_reason reason)
{
update_sysctl();
update_runtime_enabled(rq);
}
-static void rq_offline_fair(struct rq *rq)
+static void rq_offline_fair(struct rq *rq, enum rq_onoff_reason reason)
{
update_sysctl();
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 0a11f44adee5..2b4c769438a1 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2473,7 +2473,7 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p)
}
/* Assumes rq->lock is held */
-static void rq_online_rt(struct rq *rq)
+static void rq_online_rt(struct rq *rq, enum rq_onoff_reason reason)
{
if (rq->rt.overloaded)
rt_set_overload(rq);
@@ -2484,7 +2484,7 @@ static void rq_online_rt(struct rq *rq)
}
/* Assumes rq->lock is held */
-static void rq_offline_rt(struct rq *rq)
+static void rq_offline_rt(struct rq *rq, enum rq_onoff_reason reason)
{
if (rq->rt.overloaded)
rt_clear_overload(rq);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 67f7f1149630..958613dd8290 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2183,6 +2183,11 @@ extern const u32 sched_prio_to_wmult[40];
#define RETRY_TASK ((void *)-1UL)
+enum rq_onoff_reason {
+ RQ_ONOFF_HOTPLUG, /* CPU is going on/offline */
+ RQ_ONOFF_TOPOLOGY, /* sched domain topology update */
+};
+
struct affinity_context {
const struct cpumask *new_mask;
struct cpumask *user_mask;
@@ -2219,8 +2224,8 @@ struct sched_class {
void (*set_cpus_allowed)(struct task_struct *p, struct affinity_context *ctx);
- void (*rq_online)(struct rq *rq);
- void (*rq_offline)(struct rq *rq);
+ void (*rq_online)(struct rq *rq, enum rq_onoff_reason reason);
+ void (*rq_offline)(struct rq *rq, enum rq_onoff_reason reason);
struct rq *(*find_lock_rq)(struct task_struct *p, struct rq *rq);
#endif
@@ -2787,8 +2792,8 @@ static inline void double_rq_unlock(struct rq *rq1, struct rq *rq2)
raw_spin_rq_unlock(rq1);
}
-extern void set_rq_online (struct rq *rq);
-extern void set_rq_offline(struct rq *rq);
+extern void set_rq_online (struct rq *rq, enum rq_onoff_reason reason);
+extern void set_rq_offline(struct rq *rq, enum rq_onoff_reason reason);
extern bool sched_smp_initialized;
#else /* CONFIG_SMP */
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 051aaf65c749..155c4e7e0f08 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -495,7 +495,7 @@ void rq_attach_root(struct rq *rq, struct root_domain *rd)
old_rd = rq->rd;
if (cpumask_test_cpu(rq->cpu, old_rd->online))
- set_rq_offline(rq);
+ set_rq_offline(rq, RQ_ONOFF_TOPOLOGY);
cpumask_clear_cpu(rq->cpu, old_rd->span);
@@ -513,7 +513,7 @@ void rq_attach_root(struct rq *rq, struct root_domain *rd)
cpumask_set_cpu(rq->cpu, rd->span);
if (cpumask_test_cpu(rq->cpu, cpu_active_mask))
- set_rq_online(rq);
+ set_rq_online(rq, RQ_ONOFF_TOPOLOGY);
raw_spin_rq_unlock_irqrestore(rq, flags);
--
2.39.2
next prev parent reply other threads:[~2023-03-17 21:36 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-03-17 21:33 [PATCHSET v3] sched: Implement BPF extensible scheduler class Tejun Heo
2023-03-17 21:33 ` [PATCH 01/32] cgroup: Implement cgroup_show_cftypes() Tejun Heo
2023-03-17 21:33 ` [PATCH 02/32] sched: Encapsulate task attribute change sequence into a helper macro Tejun Heo
2023-03-17 21:33 ` [PATCH 03/32] sched: Restructure sched_class order sanity checks in sched_init() Tejun Heo
2023-03-17 21:33 ` [PATCH 04/32] sched: Allow sched_cgroup_fork() to fail and introduce sched_cancel_fork() Tejun Heo
2023-03-17 21:33 ` [PATCH 05/32] sched: Add sched_class->reweight_task() Tejun Heo
2023-03-17 21:33 ` [PATCH 06/32] sched: Add sched_class->switching_to() and expose check_class_changing/changed() Tejun Heo
2023-03-17 21:33 ` [PATCH 07/32] sched: Factor out cgroup weight conversion functions Tejun Heo
2023-03-17 21:33 ` [PATCH 08/32] sched: Expose css_tg(), __setscheduler_prio() and SCHED_CHANGE_BLOCK() Tejun Heo
2023-03-17 21:33 ` [PATCH 09/32] sched: Enumerate CPU cgroup file types Tejun Heo
2023-03-17 21:33 ` Tejun Heo [this message]
2023-03-17 21:33 ` [PATCH 11/32] sched: Add normal_policy() Tejun Heo
2023-03-17 21:33 ` [PATCH 12/32] sched_ext: Add boilerplate for extensible scheduler class Tejun Heo
2023-03-17 21:33 ` [PATCH 13/32] sched_ext: Implement BPF " Tejun Heo
2023-03-17 21:33 ` [PATCH 14/32] sched_ext: Add scx_example_simple and scx_example_qmap example schedulers Tejun Heo
2023-03-17 21:33 ` [PATCH 15/32] sched_ext: Add sysrq-S which disables the BPF scheduler Tejun Heo
2023-03-17 21:33 ` [PATCH 16/32] sched_ext: Implement runnable task stall watchdog Tejun Heo
2023-03-17 21:33 ` [PATCH 17/32] sched_ext: Allow BPF schedulers to disallow specific tasks from joining SCHED_EXT Tejun Heo
2023-03-17 21:33 ` [PATCH 18/32] sched_ext: Allow BPF schedulers to switch all eligible tasks into sched_ext Tejun Heo
2023-03-17 21:33 ` [PATCH 19/32] sched_ext: Implement scx_bpf_kick_cpu() and task preemption support Tejun Heo
2023-03-17 21:33 ` [PATCH 20/32] sched_ext: Make watchdog handle ops.dispatch() looping stall Tejun Heo
2023-03-17 21:33 ` [PATCH 21/32] sched_ext: Add task state tracking operations Tejun Heo
2023-03-17 21:33 ` [PATCH 22/32] sched_ext: Implement tickless support Tejun Heo
2023-03-17 21:33 ` [PATCH 23/32] sched_ext: Track tasks that are subjects of the in-flight SCX operation Tejun Heo
2023-03-17 21:33 ` [PATCH 24/32] sched_ext: Add cgroup support Tejun Heo
2023-04-20 20:02 ` Andrea Righi
2023-04-21 14:32 ` Tejun Heo
2023-03-17 21:33 ` [PATCH 25/32] sched_ext: Implement SCX_KICK_WAIT Tejun Heo
2023-03-17 21:33 ` [PATCH 26/32] sched_ext: Implement sched_ext_ops.cpu_acquire/release() Tejun Heo
2023-03-17 21:33 ` [PATCH 27/32] sched_ext: Implement sched_ext_ops.cpu_online/offline() Tejun Heo
2023-03-17 21:33 ` [PATCH 28/32] sched_ext: Implement core-sched support Tejun Heo
2023-04-20 19:56 ` Andrea Righi
2023-04-21 14:31 ` Tejun Heo
2023-03-17 21:33 ` [PATCH 29/32] sched_ext: Add vtime-ordered priority queue to dispatch_q's Tejun Heo
2023-03-17 21:33 ` [PATCH 30/32] sched_ext: Documentation: scheduler: Document extensible scheduler class Tejun Heo
2023-03-18 2:05 ` Bagas Sanjaya
2023-03-17 21:33 ` [PATCH 31/32] sched_ext: Add a basic, userland vruntime scheduler Tejun Heo
2023-03-17 21:33 ` [PATCH 32/32] sched_ext: Add a rust userspace hybrid example 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=20230317213333.2174969-11-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=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=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=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