sched: Add CONFIG_SCHED_PROXY_EXEC & boot argument to enable/disable

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.

Signed-off-by: John Stultz <jstultz@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Link: https://lkml.kernel.org/r/20250712033407.2383110-2-jstultz@google.com

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.

include/linux/sched.h

@@ -1656,6 +1656,19 @@ 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)
 

init/Kconfig

@@ -878,6 +878,18 @@ 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
 
 #

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
  *

kernel/sched/sched.h

@@ -1142,10 +1142,15 @@ struct rq {
 	 */
 	unsigned long 		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;
@@ -1326,10 +1331,17 @@ 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);