[RESEND][PATCH v18 1/8] sched: Add CONFIG_SCHED_PROXY_EXEC & boot argument to enable/disable

[John Stultz <jstultz@google.com>]

Add a CONFIG_SCHED_PROXY_EXEC option, along with a boot argument
sched_proxy_exec= that can be used to disable the feature at boot
time if CONFIG_SCHED_PROXY_EXEC was enabled.

Also uses this option to allow the rq->donor to be different from
rq->curr.

Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: John Stultz <jstultz@google.com>
---
v7:
* Switch to CONFIG_SCHED_PROXY_EXEC/sched_proxy_exec= as
  suggested by Metin Kaya.
* Switch boot arg from =disable/enable to use kstrtobool(),
  which supports =yes|no|1|0|true|false|on|off, as also
  suggested by Metin Kaya, and print a message when a boot
  argument is used.
v8:
* Move CONFIG_SCHED_PROXY_EXEC under Scheduler Features as
  Suggested by Metin
* Minor rework reordering with split sched contexts patch
v12:
* Rework for selected -> donor renaming
v14:
* Depend on !PREEMPT_RT to avoid build issues for now
v15:
* Depend on EXPERT while patch series upstreaming is
  in progress.
v16:
* Allow "sched_proxy_exec" without "=true" to enable
  proxy-execution at boot time, in addition to the
  "sched_proxy_exec=true" or "sched_proxy_exec=false" options
  as suggested by Steven
* Drop the "default n" in Kconfig as suggested by Steven
* Add !SCHED_CLASS_EXT dependency until I can investigate if
  sched_ext can understand split contexts, as suggested by
  Peter
v17:
* Expanded the commit message a bit to clarify that the option
  allows the split contexts (rq->donor and rq->curr) to be
  different tasks, from feedback from Juri Lelli

Cc: Joel Fernandes <joelagnelf@nvidia.com>
Cc: Qais Yousef <qyousef@layalina.io>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Valentin Schneider <vschneid@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ben Segall <bsegall@google.com>
Cc: Zimuzo Ezeozue <zezeozue@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Will Deacon <will@kernel.org>
Cc: Waiman Long <longman@redhat.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: "Paul E. McKenney" <paulmck@kernel.org>
Cc: Metin Kaya <Metin.Kaya@arm.com>
Cc: Xuewen Yan <xuewen.yan94@gmail.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: Suleiman Souhlal <suleiman@google.com>
Cc: kuyo chang <kuyo.chang@mediatek.com>
Cc: hupu <hupu.gm@gmail.com>
Cc: kernel-team@android.com
---
 .../admin-guide/kernel-parameters.txt         |  5 ++++
 include/linux/sched.h                         | 13 +++++++++
 init/Kconfig                                  | 12 ++++++++
 kernel/sched/core.c                           | 29 +++++++++++++++++++
 kernel/sched/sched.h                          | 12 ++++++++
 5 files changed, 71 insertions(+)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index f1f2c0874da9d..5b89464ca570a 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -6387,6 +6387,11 @@
 	sa1100ir	[NET]
 			See drivers/net/irda/sa1100_ir.c.
 
+	sched_proxy_exec= [KNL]
+			Enables or disables "proxy execution" style
+			solution to mutex-based priority inversion.
+			Format: <bool>
+
 	sched_verbose	[KNL,EARLY] Enables verbose scheduler debug messages.
 
 	schedstats=	[KNL,X86] Enable or disable scheduled statistics.
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4f78a64beb52c..ba2a02ead8c7e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1664,6 +1664,19 @@ struct task_struct {
 	randomized_struct_fields_end
 } __attribute__ ((aligned (64)));
 
+#ifdef CONFIG_SCHED_PROXY_EXEC
+DECLARE_STATIC_KEY_TRUE(__sched_proxy_exec);
+static inline bool sched_proxy_exec(void)
+{
+	return static_branch_likely(&__sched_proxy_exec);
+}
+#else
+static inline bool sched_proxy_exec(void)
+{
+	return false;
+}
+#endif
+
 #define TASK_REPORT_IDLE	(TASK_REPORT + 1)
 #define TASK_REPORT_MAX		(TASK_REPORT_IDLE << 1)
 
diff --git a/init/Kconfig b/init/Kconfig
index af4c2f0854554..6844b25303913 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -875,6 +875,18 @@ config UCLAMP_BUCKETS_COUNT
 
 	  If in doubt, use the default value.
 
+config SCHED_PROXY_EXEC
+	bool "Proxy Execution"
+	# Avoid some build failures w/ PREEMPT_RT until it can be fixed
+	depends on !PREEMPT_RT
+	# Need to investigate how to inform sched_ext of split contexts
+	depends on !SCHED_CLASS_EXT
+	# Not particularly useful until we get to multi-rq proxying
+	depends on EXPERT
+	help
+	  This option enables proxy execution, a mechanism for mutex-owning
+	  tasks to inherit the scheduling context of higher priority waiters.
+
 endmenu
 
 #
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 8988d38d46a38..853157b27f384 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -119,6 +119,35 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(sched_compute_energy_tp);
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
+#ifdef CONFIG_SCHED_PROXY_EXEC
+DEFINE_STATIC_KEY_TRUE(__sched_proxy_exec);
+static int __init setup_proxy_exec(char *str)
+{
+	bool proxy_enable = true;
+
+	if (*str && kstrtobool(str + 1, &proxy_enable)) {
+		pr_warn("Unable to parse sched_proxy_exec=\n");
+		return 0;
+	}
+
+	if (proxy_enable) {
+		pr_info("sched_proxy_exec enabled via boot arg\n");
+		static_branch_enable(&__sched_proxy_exec);
+	} else {
+		pr_info("sched_proxy_exec disabled via boot arg\n");
+		static_branch_disable(&__sched_proxy_exec);
+	}
+	return 1;
+}
+#else
+static int __init setup_proxy_exec(char *str)
+{
+	pr_warn("CONFIG_SCHED_PROXY_EXEC=n, so it cannot be enabled or disabled at boot time\n");
+	return 0;
+}
+#endif
+__setup("sched_proxy_exec", setup_proxy_exec);
+
 /*
  * Debugging: various feature bits
  *
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 475bb5998295e..6b61e0c7f6e78 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1151,10 +1151,15 @@ struct rq {
 	 */
 	unsigned int		nr_uninterruptible;
 
+#ifdef CONFIG_SCHED_PROXY_EXEC
+	struct task_struct __rcu	*donor;  /* Scheduling context */
+	struct task_struct __rcu	*curr;   /* Execution context */
+#else
 	union {
 		struct task_struct __rcu *donor; /* Scheduler context */
 		struct task_struct __rcu *curr;  /* Execution context */
 	};
+#endif
 	struct sched_dl_entity	*dl_server;
 	struct task_struct	*idle;
 	struct task_struct	*stop;
@@ -1349,10 +1354,17 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 #define cpu_curr(cpu)		(cpu_rq(cpu)->curr)
 #define raw_rq()		raw_cpu_ptr(&runqueues)
 
+#ifdef CONFIG_SCHED_PROXY_EXEC
+static inline void rq_set_donor(struct rq *rq, struct task_struct *t)
+{
+	rcu_assign_pointer(rq->donor, t);
+}
+#else
 static inline void rq_set_donor(struct rq *rq, struct task_struct *t)
 {
 	/* Do nothing */
 }
+#endif
 
 #ifdef CONFIG_SCHED_CORE
 static inline struct cpumask *sched_group_span(struct sched_group *sg);
-- 
2.50.0.727.gbf7dc18ff4-goog