[PATCH 09/10] sched/core: Disable proxy-exec context switch under sched_ext by default

[Andrea Righi]

Proxy execution switches a donor's execution context to the mutex owner,
so the owner can make progress while the donor remains on the runqueue.

This logic might be incompatible with some sched_ext schedulers: the BPF
scheduler picks tasks through its own dispatch interface, and a
proxy-exec switch may end up running a task the BPF scheduler never
dispatched. This mismatch can break BPF context: sched_ext callbacks
fire against a task that isn't the one the BPF scheduler tracks as
running, so any kfunc they invoke operates on an inconsistent view of
the current task.

Therefore, when sched_ext is enabled, disable proxy-exec context
donation by default:

  - Force try_to_block_task() to actually block a mutex-blocked prev
    instead of keeping it on the rq as a donor.

  - Skip find_proxy_task() in the pick path. Clear any leftover
    PROXY_WAKING marker set by the mutex handoff, since
    find_proxy_task() is no longer there to do it; otherwise the task
    trips the blocked_on mismatch WARN in __set_task_blocked_on() when
    it resumes the mutex_lock() retry loop.

However, some schedulers may not consider proxy execution as a real
"task switch" and more like a "function call": the donor effectively
executes the lock owner's critical section, so the switch does not
represent a true change in scheduling ownership.

To handle both semantics, add a boot-time knob to enable proxy execution
under sched_ext when explicitly desired:

  sched_proxy_exec_scx=0|1

The default is 0, keeping proxy-exec disabled for the reasons described
above. Setting it to 1 allows donor->owner context switch even with
sched_ext enabled.

Signed-off-by: Andrea Righi <arighi@xxxxxxxxxx>
---
 .../admin-guide/kernel-parameters.txt         |  6 +++
 kernel/sched/core.c                           | 47 ++++++++++++++++++-
 2 files changed, 52 insertions(+), 1 deletion(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 4510b4b3c4165..f73c12e9645de 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -6821,6 +6821,12 @@ Kernel parameters
 			solution to mutex-based priority inversion.
 			Format: <bool>
 
+	sched_proxy_exec_scx= [KNL]
+			Enables or disables proxy execution when sched_ext is
+			enabled. The default is disabled, meaning proxy-exec
+			context donation is suppressed while sched_ext is active.
+			Format: <bool>
+
 	sched_verbose	[KNL,EARLY] Enables verbose scheduler debug messages.
 
 	schedstats=	[KNL,X86] Enable or disable scheduled statistics.
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 1c161dd9d7440..0f714c6613771 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -151,14 +151,52 @@ static int __init setup_proxy_exec(char *str)
 	}
 	return 1;
 }
+
+DEFINE_STATIC_KEY_FALSE(__sched_proxy_exec_scx);
+static __always_inline bool sched_proxy_exec_scx(void)
+{
+	return static_branch_unlikely(&__sched_proxy_exec_scx);
+}
+
+static int __init setup_proxy_exec_scx(char *str)
+{
+	bool proxy_scx_enable = false;
+
+	if (*str && kstrtobool(str + 1, &proxy_scx_enable)) {
+		pr_warn("Unable to parse sched_proxy_exec_scx=\n");
+		return 0;
+	}
+
+	if (proxy_scx_enable) {
+		pr_info("sched_proxy_exec_scx enabled via boot arg\n");
+		static_branch_enable(&__sched_proxy_exec_scx);
+	} else {
+		pr_info("sched_proxy_exec_scx disabled via boot arg\n");
+		static_branch_disable(&__sched_proxy_exec_scx);
+	}
+
+	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;
 }
+
+static __always_inline bool sched_proxy_exec_scx(void)
+{
+	return false;
+}
+
+static int __init setup_proxy_exec_scx(char *str)
+{
+	pr_warn("CONFIG_SCHED_PROXY_EXEC=n, so sched_proxy_exec_scx= is ignored\n");
+	return 0;
+}
 #endif
 __setup("sched_proxy_exec", setup_proxy_exec);
+__setup("sched_proxy_exec_scx", setup_proxy_exec_scx);
 
 /*
  * Debugging: various feature bits
@@ -7111,7 +7149,8 @@ static void __sched notrace __schedule(int sched_mode)
 		 * task_is_blocked() will always be false).
 		 */
 		try_to_block_task(rq, prev, &prev_state,
-				  !task_is_blocked(prev));
+				  !task_is_blocked(prev) ||
+				  (scx_enabled() && !sched_proxy_exec_scx()));
 		switch_count = &prev->nvcsw;
 	}
 
@@ -7123,6 +7162,12 @@ static void __sched notrace __schedule(int sched_mode)
 		struct task_struct *prev_donor = rq->donor;
 
 		rq_set_donor(rq, next);
+		if (scx_enabled() && !sched_proxy_exec_scx()) {
+			if (unlikely(next->blocked_on))
+				clear_task_blocked_on(next, PROXY_WAKING);
+			goto picked;
+		}
+
 		if (unlikely(next->blocked_on)) {
 			next = find_proxy_task(rq, next, &rf);
 			if (!next) {
-- 
2.54.0