rv/rtapp: Add wakeup monitor

Add a wakeup monitor to detect a lower-priority task waking up a
higher-priority task.

The rtapp/sleep monitor already detects this. However, that monitor
triggers an error in the context of the wakee task and user only gets
the stacktrace of that task. It is also extremely useful to get the
stacktrace of the waker task, which this monitor offers. In other
words, this monitor complements the rtapp/sleep monitor.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Reviewed-by: Gabriele Monaco <gmonaco@redhat.com>
Link: https://lore.kernel.org/r/ba5658fa13e49ada466b84a2c211f233037180b5.1781852967.git.namcao@linutronix.de
Signed-off-by: Gabriele Monaco <gmonaco@redhat.com>

Documentation/trace/rv/monitor_rtapp.rst

@@ -124,3 +124,23 @@ to handle some special cases:
     real-time-safe because preemption is disabled for the duration.
   - `FUTEX_LOCK_PI` is included in the allowlist for the same reason as
     `BLOCK_ON_RT_MUTEX`.
+
+Monitor wakeup
+++++++++++++++
+
+The `wakeup` monitor reports real-time threads being woken by lower-priority threads,
+which is a hint of priority inversion. Its specification is::
+
+  RULE = always (((RT and USER_THREAD) imply
+                (not (WOKEN_BY_LOWER_PRIO or WOKEN_BY_SOFTIRQ)) or ALLOWLIST))
+
+  ALLOWLIST = BLOCK_ON_RT_MUTEX
+           or FUTEX_LOCK_PI
+
+The `sleep` monitor already reports this type of problem. The difference is the
+context in which the problem is reported. While the `sleep` monitor reports the problem
+in the context of the wakee, this `wakeup` monitor reports the problem in the context of
+the waker. This monitor complement the `sleep` monitor, giving user better
+understanding of the issue. For instance, to debug a lower-priority task waking a
+higher-priority task scenario, user can enable both `wakeup` monitor and `sleep`
+monitor to get the stack traces of both tasks.

kernel/trace/rv/Kconfig

@@ -76,6 +76,7 @@ source "kernel/trace/rv/monitors/opid/Kconfig"
 source "kernel/trace/rv/monitors/rtapp/Kconfig"
 source "kernel/trace/rv/monitors/pagefault/Kconfig"
 source "kernel/trace/rv/monitors/sleep/Kconfig"
+source "kernel/trace/rv/monitors/wakeup/Kconfig"
 # Add new rtapp monitors here
 
 source "kernel/trace/rv/monitors/stall/Kconfig"

kernel/trace/rv/Makefile

@@ -20,6 +20,7 @@ obj-$(CONFIG_RV_MON_OPID) += monitors/opid/opid.o
 obj-$(CONFIG_RV_MON_STALL) += monitors/stall/stall.o
 obj-$(CONFIG_RV_MON_DEADLINE) += monitors/deadline/deadline.o
 obj-$(CONFIG_RV_MON_NOMISS) += monitors/nomiss/nomiss.o
+obj-$(CONFIG_RV_MON_WAKEUP) += monitors/wakeup/wakeup.o
 # Add new monitors here
 obj-$(CONFIG_RV_REACTORS) += rv_reactors.o
 obj-$(CONFIG_RV_REACT_PRINTK) += reactor_printk.o

kernel/trace/rv/monitors/rtapp/Kconfig

@@ -1,6 +1,6 @@
 config RV_MON_RTAPP
 	depends on RV
-	depends on RV_PER_TASK_MONITORS >= 2
+	depends on RV_PER_TASK_MONITORS >= 3
 	bool "rtapp monitor"
 	help
 	  Collection of monitors to check for common problems with real-time

kernel/trace/rv/monitors/wakeup/Kconfig

@@ -0,0 +1,16 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+config RV_MON_WAKEUP
+	depends on RV
+	depends on RV_MON_RTAPP
+	depends on HAVE_SYSCALL_TRACEPOINTS
+	default y
+	select LTL_MON_EVENTS_ID
+	bool "wakeup monitor"
+	help
+	  This monitor detects a lower-priority task waking up a
+	  higher-priority task. The RV_MON_SLEEP monitor already
+	  detects this case, but this monitor detects in the context
+	  of the waker task instead. This and RV_MON_SLEEP can be
+	  enabled together to get the stacktrace of both the waker
+	  task and the wakee task.

kernel/trace/rv/monitors/wakeup/wakeup.c

@@ -0,0 +1,153 @@
+// 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>
+
+#define MODULE_NAME "wakeup"
+
+#include <trace/events/syscalls.h>
+#include <trace/events/sched.h>
+#include <trace/events/lock.h>
+#include <uapi/linux/futex.h>
+
+#include <rv_trace.h>
+#include <monitors/rtapp/rtapp.h>
+
+
+#ifndef __NR_futex
+#define __NR_futex (-__COUNTER__)
+#endif
+#ifndef __NR_futex_time64
+#define __NR_futex_time64 (-__COUNTER__)
+#endif
+
+#include "wakeup.h"
+#include <rv/ltl_monitor.h>
+
+static void ltl_atoms_fetch(struct task_struct *task, struct ltl_monitor *mon)
+{
+	/*
+	 * This includes "actual" real-time tasks and also PI-boosted
+	 * tasks. A task being PI-boosted means it is blocking an "actual"
+	 * real-task, therefore it should also obey the monitor's rule,
+	 * otherwise the "actual" real-task may be delayed.
+	 */
+	ltl_atom_set(mon, LTL_RT, rt_or_dl_task(task));
+}
+
+static void ltl_atoms_init(struct task_struct *task, struct ltl_monitor *mon, bool task_creation)
+{
+	ltl_atom_set(mon, LTL_WOKEN_BY_LOWER_PRIO, false);
+	ltl_atom_set(mon, LTL_WOKEN_BY_SOFTIRQ, false);
+
+	if (task_creation) {
+		ltl_atom_set(mon, LTL_BLOCK_ON_RT_MUTEX, false);
+		ltl_atom_set(mon, LTL_FUTEX_LOCK_PI, false);
+	}
+
+	ltl_atom_set(mon, LTL_USER_THREAD, !(task->flags & PF_KTHREAD));
+}
+
+static void handle_sched_waking(void *data, struct task_struct *task)
+{
+	if (in_task()) {
+		if (current->prio > task->prio)
+			ltl_atom_pulse(task, LTL_WOKEN_BY_LOWER_PRIO, true);
+	} else if (in_serving_softirq()) {
+		ltl_atom_pulse(task, LTL_WOKEN_BY_SOFTIRQ, true);
+	}
+}
+
+static void handle_contention_begin(void *data, void *lock, unsigned int flags)
+{
+	if (flags & LCB_F_RT)
+		ltl_atom_update(current, LTL_BLOCK_ON_RT_MUTEX, true);
+}
+
+static void handle_contention_end(void *data, void *lock, int ret)
+{
+	ltl_atom_update(current, LTL_BLOCK_ON_RT_MUTEX, false);
+}
+
+static void handle_sys_enter(void *data, struct pt_regs *regs, long id)
+{
+	unsigned long args[6];
+	int op, cmd;
+
+	switch (id) {
+	case __NR_futex:
+	case __NR_futex_time64:
+		syscall_get_arguments(current, regs, args);
+		op = args[1];
+		cmd = op & FUTEX_CMD_MASK;
+
+		switch (cmd) {
+		case FUTEX_LOCK_PI:
+		case FUTEX_LOCK_PI2:
+			ltl_atom_update(current, LTL_FUTEX_LOCK_PI, true);
+			break;
+		}
+		break;
+	}
+}
+
+static void handle_sys_exit(void *data, struct pt_regs *regs, long ret)
+{
+	ltl_atom_update(current, LTL_FUTEX_LOCK_PI, false);
+}
+
+static int enable_wakeup(void)
+{
+	int retval;
+
+	retval = ltl_monitor_init();
+	if (retval)
+		return retval;
+
+	rv_attach_trace_probe("rtapp_wakeup", sched_waking, handle_sched_waking);
+	rv_attach_trace_probe("rtapp_wakeup", contention_begin, handle_contention_begin);
+	rv_attach_trace_probe("rtapp_wakeup", contention_end, handle_contention_end);
+	rv_attach_trace_probe("rtapp_wakeup", sys_enter, handle_sys_enter);
+	rv_attach_trace_probe("rtapp_wakeup", sys_exit, handle_sys_exit);
+
+	return 0;
+}
+
+static void disable_wakeup(void)
+{
+	rv_detach_trace_probe("rtapp_wakeup", sched_waking, handle_sched_waking);
+	rv_detach_trace_probe("rtapp_wakeup", contention_begin, handle_contention_begin);
+	rv_detach_trace_probe("rtapp_wakeup", contention_end, handle_contention_end);
+	rv_detach_trace_probe("rtapp_wakeup", sys_enter, handle_sys_enter);
+	rv_detach_trace_probe("rtapp_wakeup", sys_exit, handle_sys_exit);
+
+	ltl_monitor_destroy();
+}
+
+static struct rv_monitor rv_wakeup = {
+	.name = "wakeup",
+	.description = "Monitor that real-time tasks are not woken by lower-priority tasks",
+	.enable = enable_wakeup,
+	.disable = disable_wakeup,
+};
+
+static int __init register_wakeup(void)
+{
+	return rv_register_monitor(&rv_wakeup, &rv_rtapp);
+}
+
+static void __exit unregister_wakeup(void)
+{
+	rv_unregister_monitor(&rv_wakeup);
+}
+
+module_init(register_wakeup);
+module_exit(unregister_wakeup);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Nam Cao <namcao@linutronix.de>");
+MODULE_DESCRIPTION("Monitor that real-time tasks are not woken by lower-priority tasks");

kernel/trace/rv/monitors/wakeup/wakeup.h

@@ -0,0 +1,92 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * C implementation of Buchi automaton, automatically generated by
+ * tools/verification/rvgen from the linear temporal logic specification.
+ * For further information, see kernel documentation:
+ *   Documentation/trace/rv/linear_temporal_logic.rst
+ */
+
+#include <linux/rv.h>
+
+#define MONITOR_NAME wakeup
+
+enum ltl_atom {
+	LTL_BLOCK_ON_RT_MUTEX,
+	LTL_FUTEX_LOCK_PI,
+	LTL_RT,
+	LTL_USER_THREAD,
+	LTL_WOKEN_BY_LOWER_PRIO,
+	LTL_WOKEN_BY_SOFTIRQ,
+	LTL_NUM_ATOM
+};
+static_assert(LTL_NUM_ATOM <= RV_MAX_LTL_ATOM);
+
+static const char *ltl_atom_str(enum ltl_atom atom)
+{
+	static const char *const names[] = {
+		"bl_on_rt_mu",
+		"fu_lo_pi",
+		"rt",
+		"us_th",
+		"wo_lo_pr",
+		"wo_so",
+	};
+
+	return names[atom];
+}
+
+enum ltl_buchi_state {
+	S0,
+	RV_NUM_BA_STATES
+};
+static_assert(RV_NUM_BA_STATES <= RV_MAX_BA_STATES);
+
+static void ltl_start(struct task_struct *task, struct ltl_monitor *mon)
+{
+	bool woken_by_softirq = test_bit(LTL_WOKEN_BY_SOFTIRQ, mon->atoms);
+	bool woken_by_lower_prio = test_bit(LTL_WOKEN_BY_LOWER_PRIO, mon->atoms);
+	bool user_thread = test_bit(LTL_USER_THREAD, mon->atoms);
+	bool rt = test_bit(LTL_RT, mon->atoms);
+	bool futex_lock_pi = test_bit(LTL_FUTEX_LOCK_PI, mon->atoms);
+	bool block_on_rt_mutex = test_bit(LTL_BLOCK_ON_RT_MUTEX, mon->atoms);
+	bool val9 = block_on_rt_mutex || futex_lock_pi;
+	bool val6 = !woken_by_softirq;
+	bool val5 = !woken_by_lower_prio;
+	bool val8 = val5 && val6;
+	bool val10 = val8 || val9;
+	bool val3 = !user_thread;
+	bool val2 = !rt;
+	bool val4 = val2 || val3;
+	bool val11 = val4 || val10;
+
+	if (val11)
+		__set_bit(S0, mon->states);
+}
+
+static void
+ltl_possible_next_states(struct ltl_monitor *mon, unsigned int state, unsigned long *next)
+{
+	bool woken_by_softirq = test_bit(LTL_WOKEN_BY_SOFTIRQ, mon->atoms);
+	bool woken_by_lower_prio = test_bit(LTL_WOKEN_BY_LOWER_PRIO, mon->atoms);
+	bool user_thread = test_bit(LTL_USER_THREAD, mon->atoms);
+	bool rt = test_bit(LTL_RT, mon->atoms);
+	bool futex_lock_pi = test_bit(LTL_FUTEX_LOCK_PI, mon->atoms);
+	bool block_on_rt_mutex = test_bit(LTL_BLOCK_ON_RT_MUTEX, mon->atoms);
+	bool val9 = block_on_rt_mutex || futex_lock_pi;
+	bool val6 = !woken_by_softirq;
+	bool val5 = !woken_by_lower_prio;
+	bool val8 = val5 && val6;
+	bool val10 = val8 || val9;
+	bool val3 = !user_thread;
+	bool val2 = !rt;
+	bool val4 = val2 || val3;
+	bool val11 = val4 || val10;
+
+	switch (state) {
+	case S0:
+		if (val11)
+			__set_bit(S0, next);
+		break;
+	}
+}

kernel/trace/rv/monitors/wakeup/wakeup_trace.h

@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Snippet to be included in rv_trace.h
+ */
+
+#ifdef CONFIG_RV_MON_WAKEUP
+DEFINE_EVENT(event_ltl_monitor_id, event_wakeup,
+	     TP_PROTO(struct task_struct *task, char *states, char *atoms, char *next),
+	     TP_ARGS(task, states, atoms, next));
+DEFINE_EVENT(error_ltl_monitor_id, error_wakeup,
+	     TP_PROTO(struct task_struct *task),
+	     TP_ARGS(task));
+#endif /* CONFIG_RV_MON_WAKEUP */

kernel/trace/rv/rv_trace.h

@@ -241,6 +241,7 @@ DECLARE_EVENT_CLASS(error_ltl_monitor_id,
 );
 #include <monitors/pagefault/pagefault_trace.h>
 #include <monitors/sleep/sleep_trace.h>
+#include <monitors/wakeup/wakeup_trace.h>
 // Add new monitors based on CONFIG_LTL_MON_EVENTS_ID here
 #endif /* CONFIG_LTL_MON_EVENTS_ID */
 

tools/verification/models/rtapp/wakeup.ltl

@@ -0,0 +1,5 @@
+RULE = always (((RT and USER_THREAD) imply
+		(not (WOKEN_BY_LOWER_PRIO or WOKEN_BY_SOFTIRQ)) or ALLOWLIST))
+
+ALLOWLIST = BLOCK_ON_RT_MUTEX
+         or FUTEX_LOCK_PI