rv: Add opid per-cpu monitor

Add a per-cpu monitor as part of the sched model:
* opid: operations with preemption and irq disabled
    Monitor to ensure wakeup and need_resched occur with irq and
    preemption disabled or in irq handlers.

Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tomas Glozar <tglozar@redhat.com>
Cc: Juri Lelli <jlelli@redhat.com>
Cc: Clark Williams <williams@redhat.com>
Cc: John Kacur <jkacur@redhat.com>
Link: https://lore.kernel.org/20250728135022.255578-10-gmonaco@redhat.com
Signed-off-by: Gabriele Monaco <gmonaco@redhat.com>
Acked-by: Nam Cao <namcao@linutronix.de>
Tested-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

7 files changed, 309 insertions, 0 deletions

diff --git a/kernel/trace/rv/Kconfig b/kernel/trace/rv/Kconfig
index 59d0db898d4a..5b4be87ba59d 100644
--- a/kernel/trace/rv/Kconfig
+++ b/kernel/trace/rv/Kconfig
@@ -57,6 +57,7 @@ source "kernel/trace/rv/monitors/snep/Kconfig"
 source "kernel/trace/rv/monitors/sts/Kconfig"
 source "kernel/trace/rv/monitors/nrp/Kconfig"
 source "kernel/trace/rv/monitors/sssw/Kconfig"
+source "kernel/trace/rv/monitors/opid/Kconfig"
 # Add new sched monitors here
 
 source "kernel/trace/rv/monitors/rtapp/Kconfig"
diff --git a/kernel/trace/rv/Makefile b/kernel/trace/rv/Makefile
index 2afac88539d3..750e4ad6fa0f 100644
--- a/kernel/trace/rv/Makefile
+++ b/kernel/trace/rv/Makefile
@@ -16,6 +16,7 @@ obj-$(CONFIG_RV_MON_SLEEP) += monitors/sleep/sleep.o
 obj-$(CONFIG_RV_MON_STS) += monitors/sts/sts.o
 obj-$(CONFIG_RV_MON_NRP) += monitors/nrp/nrp.o
 obj-$(CONFIG_RV_MON_SSSW) += monitors/sssw/sssw.o
+obj-$(CONFIG_RV_MON_OPID) += monitors/opid/opid.o
 # Add new monitors here
 obj-$(CONFIG_RV_REACTORS) += rv_reactors.o
 obj-$(CONFIG_RV_REACT_PRINTK) += reactor_printk.o
diff --git a/kernel/trace/rv/monitors/opid/Kconfig b/kernel/trace/rv/monitors/opid/Kconfig
new file mode 100644
index 000000000000..561d32da572b
--- /dev/null
+++ b/kernel/trace/rv/monitors/opid/Kconfig
@@ -0,0 +1,19 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+config RV_MON_OPID
+	depends on RV
+	depends on TRACE_IRQFLAGS
+	depends on TRACE_PREEMPT_TOGGLE
+	depends on RV_MON_SCHED
+	default y if PREEMPT_RT
+	select DA_MON_EVENTS_IMPLICIT
+	bool "opid monitor"
+	help
+	  Monitor to ensure operations like wakeup and need resched occur with
+	  interrupts and preemption disabled or during IRQs, where preemption
+	  may not be disabled explicitly.
+
+	  This monitor is unstable on !PREEMPT_RT, say N unless you are testing it.
+
+	  For further information, see:
+	    Documentation/trace/rv/monitor_sched.rst
diff --git a/kernel/trace/rv/monitors/opid/opid.c b/kernel/trace/rv/monitors/opid/opid.c
new file mode 100644
index 000000000000..50d64e7fb8c4
--- /dev/null
+++ b/kernel/trace/rv/monitors/opid/opid.c
@@ -0,0 +1,168 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/ftrace.h>
+#include <linux/tracepoint.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/rv.h>
+#include <rv/instrumentation.h>
+#include <rv/da_monitor.h>
+
+#define MODULE_NAME "opid"
+
+#include <trace/events/sched.h>
+#include <trace/events/irq.h>
+#include <trace/events/preemptirq.h>
+#include <rv_trace.h>
+#include <monitors/sched/sched.h>
+
+#include "opid.h"
+
+static struct rv_monitor rv_opid;
+DECLARE_DA_MON_PER_CPU(opid, unsigned char);
+
+#ifdef CONFIG_X86_LOCAL_APIC
+#include <asm/trace/irq_vectors.h>
+
+static void handle_vector_irq_entry(void *data, int vector)
+{
+	da_handle_event_opid(irq_entry_opid);
+}
+
+static void attach_vector_irq(void)
+{
+	rv_attach_trace_probe("opid", local_timer_entry, handle_vector_irq_entry);
+	if (IS_ENABLED(CONFIG_IRQ_WORK))
+		rv_attach_trace_probe("opid", irq_work_entry, handle_vector_irq_entry);
+	if (IS_ENABLED(CONFIG_SMP)) {
+		rv_attach_trace_probe("opid", reschedule_entry, handle_vector_irq_entry);
+		rv_attach_trace_probe("opid", call_function_entry, handle_vector_irq_entry);
+		rv_attach_trace_probe("opid", call_function_single_entry, handle_vector_irq_entry);
+	}
+}
+
+static void detach_vector_irq(void)
+{
+	rv_detach_trace_probe("opid", local_timer_entry, handle_vector_irq_entry);
+	if (IS_ENABLED(CONFIG_IRQ_WORK))
+		rv_detach_trace_probe("opid", irq_work_entry, handle_vector_irq_entry);
+	if (IS_ENABLED(CONFIG_SMP)) {
+		rv_detach_trace_probe("opid", reschedule_entry, handle_vector_irq_entry);
+		rv_detach_trace_probe("opid", call_function_entry, handle_vector_irq_entry);
+		rv_detach_trace_probe("opid", call_function_single_entry, handle_vector_irq_entry);
+	}
+}
+
+#else
+/* We assume irq_entry tracepoints are sufficient on other architectures */
+static void attach_vector_irq(void) { }
+static void detach_vector_irq(void) { }
+#endif
+
+static void handle_irq_disable(void *data, unsigned long ip, unsigned long parent_ip)
+{
+	da_handle_event_opid(irq_disable_opid);
+}
+
+static void handle_irq_enable(void *data, unsigned long ip, unsigned long parent_ip)
+{
+	da_handle_event_opid(irq_enable_opid);
+}
+
+static void handle_irq_entry(void *data, int irq, struct irqaction *action)
+{
+	da_handle_event_opid(irq_entry_opid);
+}
+
+static void handle_preempt_disable(void *data, unsigned long ip, unsigned long parent_ip)
+{
+	da_handle_event_opid(preempt_disable_opid);
+}
+
+static void handle_preempt_enable(void *data, unsigned long ip, unsigned long parent_ip)
+{
+	da_handle_event_opid(preempt_enable_opid);
+}
+
+static void handle_sched_need_resched(void *data, struct task_struct *tsk, int cpu, int tif)
+{
+	/* The monitor's intitial state is not in_irq */
+	if (this_cpu_read(hardirq_context))
+		da_handle_event_opid(sched_need_resched_opid);
+	else
+		da_handle_start_event_opid(sched_need_resched_opid);
+}
+
+static void handle_sched_waking(void *data, struct task_struct *p)
+{
+	/* The monitor's intitial state is not in_irq */
+	if (this_cpu_read(hardirq_context))
+		da_handle_event_opid(sched_waking_opid);
+	else
+		da_handle_start_event_opid(sched_waking_opid);
+}
+
+static int enable_opid(void)
+{
+	int retval;
+
+	retval = da_monitor_init_opid();
+	if (retval)
+		return retval;
+
+	rv_attach_trace_probe("opid", irq_disable, handle_irq_disable);
+	rv_attach_trace_probe("opid", irq_enable, handle_irq_enable);
+	rv_attach_trace_probe("opid", irq_handler_entry, handle_irq_entry);
+	rv_attach_trace_probe("opid", preempt_disable, handle_preempt_disable);
+	rv_attach_trace_probe("opid", preempt_enable, handle_preempt_enable);
+	rv_attach_trace_probe("opid", sched_set_need_resched_tp, handle_sched_need_resched);
+	rv_attach_trace_probe("opid", sched_waking, handle_sched_waking);
+	attach_vector_irq();
+
+	return 0;
+}
+
+static void disable_opid(void)
+{
+	rv_opid.enabled = 0;
+
+	rv_detach_trace_probe("opid", irq_disable, handle_irq_disable);
+	rv_detach_trace_probe("opid", irq_enable, handle_irq_enable);
+	rv_detach_trace_probe("opid", irq_handler_entry, handle_irq_entry);
+	rv_detach_trace_probe("opid", preempt_disable, handle_preempt_disable);
+	rv_detach_trace_probe("opid", preempt_enable, handle_preempt_enable);
+	rv_detach_trace_probe("opid", sched_set_need_resched_tp, handle_sched_need_resched);
+	rv_detach_trace_probe("opid", sched_waking, handle_sched_waking);
+	detach_vector_irq();
+
+	da_monitor_destroy_opid();
+}
+
+/*
+ * This is the monitor register section.
+ */
+static struct rv_monitor rv_opid = {
+	.name = "opid",
+	.description = "operations with preemption and irq disabled.",
+	.enable = enable_opid,
+	.disable = disable_opid,
+	.reset = da_monitor_reset_all_opid,
+	.enabled = 0,
+};
+
+static int __init register_opid(void)
+{
+	return rv_register_monitor(&rv_opid, &rv_sched);
+}
+
+static void __exit unregister_opid(void)
+{
+	rv_unregister_monitor(&rv_opid);
+}
+
+module_init(register_opid);
+module_exit(unregister_opid);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Gabriele Monaco <gmonaco@redhat.com>");
+MODULE_DESCRIPTION("opid: operations with preemption and irq disabled.");
diff --git a/kernel/trace/rv/monitors/opid/opid.h b/kernel/trace/rv/monitors/opid/opid.h
new file mode 100644
index 000000000000..b4b8c2ff7f64
--- /dev/null
+++ b/kernel/trace/rv/monitors/opid/opid.h
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Automatically generated C representation of opid automaton
+ * For further information about this format, see kernel documentation:
+ *   Documentation/trace/rv/deterministic_automata.rst
+ */
+
+enum states_opid {
+	disabled_opid = 0,
+	enabled_opid,
+	in_irq_opid,
+	irq_disabled_opid,
+	preempt_disabled_opid,
+	state_max_opid
+};
+
+#define INVALID_STATE state_max_opid
+
+enum events_opid {
+	irq_disable_opid = 0,
+	irq_enable_opid,
+	irq_entry_opid,
+	preempt_disable_opid,
+	preempt_enable_opid,
+	sched_need_resched_opid,
+	sched_waking_opid,
+	event_max_opid
+};
+
+struct automaton_opid {
+	char *state_names[state_max_opid];
+	char *event_names[event_max_opid];
+	unsigned char function[state_max_opid][event_max_opid];
+	unsigned char initial_state;
+	bool final_states[state_max_opid];
+};
+
+static const struct automaton_opid automaton_opid = {
+	.state_names = {
+		"disabled",
+		"enabled",
+		"in_irq",
+		"irq_disabled",
+		"preempt_disabled"
+	},
+	.event_names = {
+		"irq_disable",
+		"irq_enable",
+		"irq_entry",
+		"preempt_disable",
+		"preempt_enable",
+		"sched_need_resched",
+		"sched_waking"
+	},
+	.function = {
+		{
+			INVALID_STATE,
+			preempt_disabled_opid,
+			disabled_opid,
+			INVALID_STATE,
+			irq_disabled_opid,
+			disabled_opid,
+			disabled_opid
+		},
+		{
+			irq_disabled_opid,
+			INVALID_STATE,
+			INVALID_STATE,
+			preempt_disabled_opid,
+			enabled_opid,
+			INVALID_STATE,
+			INVALID_STATE
+		},
+		{
+			INVALID_STATE,
+			enabled_opid,
+			in_irq_opid,
+			INVALID_STATE,
+			INVALID_STATE,
+			in_irq_opid,
+			in_irq_opid
+		},
+		{
+			INVALID_STATE,
+			enabled_opid,
+			in_irq_opid,
+			disabled_opid,
+			INVALID_STATE,
+			irq_disabled_opid,
+			INVALID_STATE
+		},
+		{
+			disabled_opid,
+			INVALID_STATE,
+			INVALID_STATE,
+			INVALID_STATE,
+			enabled_opid,
+			INVALID_STATE,
+			INVALID_STATE
+		},
+	},
+	.initial_state = disabled_opid,
+	.final_states = { 0, 1, 0, 0, 0 },
+};
diff --git a/kernel/trace/rv/monitors/opid/opid_trace.h b/kernel/trace/rv/monitors/opid/opid_trace.h
new file mode 100644
index 000000000000..3df6ff955c30
--- /dev/null
+++ b/kernel/trace/rv/monitors/opid/opid_trace.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Snippet to be included in rv_trace.h
+ */
+
+#ifdef CONFIG_RV_MON_OPID
+DEFINE_EVENT(event_da_monitor, event_opid,
+	     TP_PROTO(char *state, char *event, char *next_state, bool final_state),
+	     TP_ARGS(state, event, next_state, final_state));
+
+DEFINE_EVENT(error_da_monitor, error_opid,
+	     TP_PROTO(char *state, char *event),
+	     TP_ARGS(state, event));
+#endif /* CONFIG_RV_MON_OPID */
diff --git a/kernel/trace/rv/rv_trace.h b/kernel/trace/rv/rv_trace.h
index e4e78d23b7b0..4a6faddac614 100644
--- a/kernel/trace/rv/rv_trace.h
+++ b/kernel/trace/rv/rv_trace.h
@@ -62,6 +62,7 @@ DECLARE_EVENT_CLASS(error_da_monitor,
 #include <monitors/scpd/scpd_trace.h>
 #include <monitors/snep/snep_trace.h>
 #include <monitors/sts/sts_trace.h>
+#include <monitors/opid/opid_trace.h>
 // Add new monitors based on CONFIG_DA_MON_EVENTS_IMPLICIT here
 
 #endif /* CONFIG_DA_MON_EVENTS_IMPLICIT */