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,
andrea.righi@canonical.com, joel@joelfernandes.org
Cc: linux-kernel@vger.kernel.org, bpf@vger.kernel.org,
kernel-team@meta.com, Tejun Heo <tj@kernel.org>
Subject: [PATCH 09/39] sched: Add @reason to sched_class->rq_{on|off}line()
Date: Wed, 1 May 2024 05:09:44 -1000 [thread overview]
Message-ID: <20240501151312.635565-10-tj@kernel.org> (raw)
In-Reply-To: <20240501151312.635565-1-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 e48af9fbbd71..90b505fbb488 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -9593,7 +9593,7 @@ 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;
@@ -9603,12 +9603,12 @@ 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;
@@ -9616,7 +9616,7 @@ void set_rq_offline(struct rq *rq)
update_rq_clock(rq);
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);
@@ -9712,7 +9712,7 @@ 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);
@@ -9756,7 +9756,7 @@ int sched_cpu_deactivate(unsigned int cpu)
rq_lock_irqsave(rq, &rf);
if (rq->rd) {
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 a04a436af8cc..010d1dc5f918 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2607,7 +2607,7 @@ 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);
@@ -2618,7 +2618,7 @@ 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 5d7cffee1a4e..8032256d3972 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -12446,14 +12446,14 @@ 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 3261b067b67e..8620474d117d 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2426,7 +2426,7 @@ 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);
@@ -2437,7 +2437,7 @@ 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 0b6a34ba2457..bcc8056acadb 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2271,6 +2271,11 @@ 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;
@@ -2309,8 +2314,8 @@ 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
@@ -2853,8 +2858,8 @@ 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 99ea5986038c..12501543c56d 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -497,7 +497,7 @@ 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);
@@ -515,7 +515,7 @@ 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);
rq_unlock_irqrestore(rq, &rf);
--
2.44.0
next prev parent reply other threads:[~2024-05-01 15:13 UTC|newest]
Thread overview: 141+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-05-01 15:09 [PATCHSET v6] sched: Implement BPF extensible scheduler class Tejun Heo
2024-05-01 15:09 ` [PATCH 01/39] cgroup: Implement cgroup_show_cftypes() Tejun Heo
2024-05-01 15:09 ` [PATCH 02/39] sched: Restructure sched_class order sanity checks in sched_init() Tejun Heo
2024-05-01 15:09 ` [PATCH 03/39] sched: Allow sched_cgroup_fork() to fail and introduce sched_cancel_fork() Tejun Heo
2024-05-01 15:09 ` [PATCH 04/39] sched: Add sched_class->reweight_task() Tejun Heo
2024-06-24 10:23 ` Peter Zijlstra
2024-06-24 10:31 ` Peter Zijlstra
2024-06-24 23:59 ` Tejun Heo
2024-06-25 7:29 ` Peter Zijlstra
2024-06-25 23:57 ` Tejun Heo
2024-06-26 1:29 ` [PATCH sched/urgent] sched/fair: set_load_weight() must also call reweight_task() for SCHED_IDLE tasks Tejun Heo
2024-06-26 2:19 ` [PATCH sched_ext/for-6.11] sched_ext: Account for idle policy when setting p->scx.weight in scx_ops_enable_task() Tejun Heo
2024-07-08 19:29 ` [PATCH v2 " Tejun Heo
2024-05-01 15:09 ` [PATCH 05/39] sched: Add sched_class->switching_to() and expose check_class_changing/changed() Tejun Heo
2024-06-24 11:06 ` Peter Zijlstra
2024-06-24 22:18 ` Tejun Heo
2024-06-25 8:16 ` Peter Zijlstra
2024-05-01 15:09 ` [PATCH 06/39] sched: Factor out cgroup weight conversion functions Tejun Heo
2024-05-01 15:09 ` [PATCH 07/39] sched: Expose css_tg() and __setscheduler_prio() Tejun Heo
2024-06-24 11:19 ` Peter Zijlstra
2024-06-24 18:56 ` Tejun Heo
2024-05-01 15:09 ` [PATCH 08/39] sched: Enumerate CPU cgroup file types Tejun Heo
2024-05-01 15:09 ` Tejun Heo [this message]
2024-06-24 11:32 ` [PATCH 09/39] sched: Add @reason to sched_class->rq_{on|off}line() Peter Zijlstra
2024-06-24 21:18 ` Tejun Heo
2024-06-25 8:29 ` Peter Zijlstra
2024-06-25 23:41 ` Tejun Heo
2024-06-26 8:23 ` Peter Zijlstra
2024-06-26 18:01 ` Tejun Heo
2024-06-27 1:27 ` [PATCH sched_ext/for-6.11] sched_ext: Disallow loading BPF scheduler if isolcpus= domain isolation is in effect Tejun Heo
2024-07-08 19:30 ` Tejun Heo
2024-05-01 15:09 ` [PATCH 10/39] sched: Factor out update_other_load_avgs() from __update_blocked_others() Tejun Heo
2024-06-24 12:35 ` Peter Zijlstra
2024-06-24 16:15 ` Vincent Guittot
2024-06-24 19:24 ` Tejun Heo
2024-06-25 9:13 ` Vincent Guittot
2024-06-26 20:49 ` Tejun Heo
2024-05-01 15:09 ` [PATCH 11/39] cpufreq_schedutil: Refactor sugov_cpu_is_busy() Tejun Heo
2024-05-01 15:09 ` [PATCH 12/39] sched: Add normal_policy() Tejun Heo
2024-05-01 15:09 ` [PATCH 13/39] sched_ext: Add boilerplate for extensible scheduler class Tejun Heo
2024-05-01 15:09 ` [PATCH 14/39] sched_ext: Implement BPF " Tejun Heo
2024-05-01 15:09 ` [PATCH 15/39] sched_ext: Add scx_simple and scx_example_qmap example schedulers Tejun Heo
2024-05-01 15:09 ` [PATCH 16/39] sched_ext: Add sysrq-S which disables the BPF scheduler Tejun Heo
2024-05-01 15:09 ` [PATCH 17/39] sched_ext: Implement runnable task stall watchdog Tejun Heo
2024-05-01 15:09 ` [PATCH 18/39] sched_ext: Allow BPF schedulers to disallow specific tasks from joining SCHED_EXT Tejun Heo
2024-06-24 12:40 ` Peter Zijlstra
2024-06-24 19:06 ` Tejun Heo
2024-05-01 15:09 ` [PATCH 19/39] sched_ext: Print sched_ext info when dumping stack Tejun Heo
2024-06-24 12:46 ` Peter Zijlstra
2024-06-24 14:25 ` Linus Torvalds
2024-06-24 18:34 ` Tejun Heo
2024-05-01 15:09 ` [PATCH 20/39] sched_ext: Print debug dump after an error exit Tejun Heo
2024-05-01 15:09 ` [PATCH 21/39] tools/sched_ext: Add scx_show_state.py Tejun Heo
2024-05-01 15:09 ` [PATCH 22/39] sched_ext: Implement scx_bpf_kick_cpu() and task preemption support Tejun Heo
2024-05-01 15:09 ` [PATCH 23/39] sched_ext: Add a central scheduler which makes all scheduling decisions on one CPU Tejun Heo
2024-05-01 15:09 ` [PATCH 24/39] sched_ext: Make watchdog handle ops.dispatch() looping stall Tejun Heo
2024-05-01 15:10 ` [PATCH 25/39] sched_ext: Add task state tracking operations Tejun Heo
2024-05-01 15:10 ` [PATCH 26/39] sched_ext: Implement tickless support Tejun Heo
2024-05-01 15:10 ` [PATCH 27/39] sched_ext: Track tasks that are subjects of the in-flight SCX operation Tejun Heo
2024-05-01 15:10 ` [PATCH 28/39] sched_ext: Add cgroup support Tejun Heo
2024-05-01 15:10 ` [PATCH 29/39] sched_ext: Add a cgroup scheduler which uses flattened hierarchy Tejun Heo
2024-05-01 15:10 ` [PATCH 30/39] sched_ext: Implement SCX_KICK_WAIT Tejun Heo
2024-05-01 15:10 ` [PATCH 31/39] sched_ext: Implement sched_ext_ops.cpu_acquire/release() Tejun Heo
2024-05-01 15:10 ` [PATCH 32/39] sched_ext: Implement sched_ext_ops.cpu_online/offline() Tejun Heo
2024-05-01 15:10 ` [PATCH 33/39] sched_ext: Bypass BPF scheduler while PM events are in progress Tejun Heo
2024-05-01 15:10 ` [PATCH 34/39] sched_ext: Implement core-sched support Tejun Heo
2024-05-01 15:10 ` [PATCH 35/39] sched_ext: Add vtime-ordered priority queue to dispatch_q's Tejun Heo
2024-05-01 15:10 ` [PATCH 36/39] sched_ext: Implement DSQ iterator Tejun Heo
2024-05-01 15:10 ` [PATCH 37/39] sched_ext: Add cpuperf support Tejun Heo
2024-05-01 15:10 ` [PATCH 38/39] sched_ext: Documentation: scheduler: Document extensible scheduler class Tejun Heo
2024-05-02 2:24 ` Bagas Sanjaya
2024-05-01 15:10 ` [PATCH 39/39] sched_ext: Add selftests Tejun Heo
2024-05-02 8:48 ` [PATCHSET v6] sched: Implement BPF extensible scheduler class Peter Zijlstra
2024-05-02 19:20 ` Tejun Heo
2024-05-03 8:52 ` Peter Zijlstra
2024-05-05 23:31 ` Tejun Heo
2024-05-13 8:03 ` Peter Zijlstra
2024-05-13 18:26 ` Steven Rostedt
2024-05-14 0:07 ` Qais Yousef
2024-05-14 21:34 ` David Vernet
2024-05-27 21:25 ` Qais Yousef
2024-05-28 23:46 ` Tejun Heo
2024-05-29 22:09 ` Qais Yousef
2024-05-17 9:58 ` Peter Zijlstra
2024-05-27 20:29 ` Qais Yousef
2024-05-14 20:22 ` Chris Mason
2024-05-14 22:06 ` Josh Don
2024-05-15 20:41 ` Tejun Heo
2024-05-21 0:19 ` Tejun Heo
2024-05-30 16:49 ` Tejun Heo
2024-05-06 18:47 ` Rik van Riel
2024-05-07 19:33 ` Tejun Heo
2024-05-07 19:47 ` Rik van Riel
2024-05-09 7:38 ` Changwoo Min
2024-05-10 18:24 ` Peter Jung
2024-05-13 20:36 ` Andrea Righi
2024-06-11 21:34 ` Linus Torvalds
2024-06-13 23:38 ` Tejun Heo
2024-06-19 20:56 ` Thomas Gleixner
2024-06-19 22:10 ` Linus Torvalds
2024-06-19 22:27 ` Thomas Gleixner
2024-06-19 22:55 ` Linus Torvalds
2024-06-20 2:35 ` Thomas Gleixner
2024-06-20 5:07 ` Linus Torvalds
2024-06-20 17:11 ` Linus Torvalds
2024-06-20 17:41 ` Tejun Heo
2024-06-20 22:15 ` [PATCH sched_ext/for-6.11] sched, sched_ext: Replace scx_next_task_picked() with sched_class->switch_class() Tejun Heo
2024-06-20 22:42 ` Linus Torvalds
2024-06-21 19:46 ` Tejun Heo
2024-06-24 9:04 ` Peter Zijlstra
2024-06-24 18:41 ` Tejun Heo
2024-06-24 9:02 ` Peter Zijlstra
2024-06-21 19:52 ` Tejun Heo
2024-06-24 8:59 ` Peter Zijlstra
2024-06-24 21:01 ` Tejun Heo
2024-06-25 7:49 ` Peter Zijlstra
2024-06-25 23:30 ` Tejun Heo
2024-06-26 8:28 ` Peter Zijlstra
2024-06-26 17:56 ` Tejun Heo
2024-06-20 18:47 ` [PATCHSET v6] sched: Implement BPF extensible scheduler class Thomas Gleixner
2024-06-20 19:20 ` Linus Torvalds
2024-06-21 9:35 ` Thomas Gleixner
2024-06-21 16:34 ` Linus Torvalds
2024-06-23 2:00 ` Tejun Heo
2024-06-23 10:31 ` Thomas Gleixner
2024-06-23 10:33 ` Thomas Gleixner
2024-06-24 14:23 ` Jason Gunthorpe
2024-06-20 19:58 ` Tejun Heo
2024-06-24 9:34 ` Peter Zijlstra
2024-06-24 20:17 ` Tejun Heo
2024-06-24 20:51 ` [PATCH sched_ext/for-6.11] sched, sched_ext: Simplify dl_prio() case handling in sched_fork() Tejun Heo
2024-07-08 18:56 ` Tejun Heo
2024-06-20 19:35 ` [PATCHSET v6] sched: Implement BPF extensible scheduler class Tejun Heo
2024-06-21 10:46 ` Thomas Gleixner
2024-06-21 21:14 ` Chris Mason
2024-06-23 8:14 ` Thomas Gleixner
2024-06-24 16:42 ` Chris Mason
2024-06-24 18:11 ` Tejun Heo
2024-06-24 22:01 ` Peter Oskolkov
2024-06-24 22:17 ` David Vernet
2024-06-24 21:54 ` Peter Oskolkov
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=20240501151312.635565-10-tj@kernel.org \
--to=tj@kernel.org \
--cc=andrea.righi@canonical.com \
--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=joel@joelfernandes.org \
--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 NNTP newsgroup(s).