Skip to contentSkip to conversation

verification: Updates for v6.17

PATCH New Steven Rostedt 1 participant 12 messages Jul 28, 2025

Subsystems (4)
lore
Share & tools
lore
#0 lore raw

cover verification: Updates for v6.17

git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace.git
rv/for-next

Head SHA1: 614384533dfe99293a7ff1bce3d4389adadbb759

Gabriele Monaco (9):
rv: Add da_handle_start_run_event_ to per-task monitors
rv: Remove trailing whitespace from tracepoint string
rv: Use strings in da monitors tracepoints
rv: Adjust monitor dependencies
rv: Retry when da monitor detects race conditions
sched: Adapt sched tracepoints for RV task model
rv: Replace tss and sncid monitors with more complete sts
rv: Add nrp and sssw per-task monitors
rv: Add opid per-cpu monitor

Nam Cao (2):
rv: Fix wrong type cast in monitors_show()
rv: Fix wrong type cast in reactors_show() and monitor_reactor_show()

----

 Documentation/trace/rv/monitor_sched.rst           | 307 ++++++++++++++++++---
 include/linux/rv.h                                 |   3 +-
 include/linux/sched.h                              |   7 +-
 include/rv/da_monitor.h                            | 131 +++++----
 include/trace/events/sched.h                       |  12 +-
 kernel/sched/core.c                                |  13 +-
 kernel/trace/rv/Kconfig                            |  11 +-
 kernel/trace/rv/Makefile                           |   6 +-
 kernel/trace/rv/monitors/{tss => nrp}/Kconfig      |  12 +-
 kernel/trace/rv/monitors/nrp/nrp.c                 | 138 +++++++++
 kernel/trace/rv/monitors/nrp/nrp.h                 |  75 +++++
 kernel/trace/rv/monitors/nrp/nrp_trace.h           |  15 +
 kernel/trace/rv/monitors/opid/Kconfig              |  19 ++
 kernel/trace/rv/monitors/opid/opid.c               | 168 +++++++++++
 kernel/trace/rv/monitors/opid/opid.h               | 104 +++++++
 .../{sncid/sncid_trace.h => opid/opid_trace.h}     |   8 +-
 kernel/trace/rv/monitors/sched/Kconfig             |   1 +
 kernel/trace/rv/monitors/sco/sco.c                 |   4 +-
 kernel/trace/rv/monitors/scpd/Kconfig              |   2 +-
 kernel/trace/rv/monitors/scpd/scpd.c               |   4 +-
 kernel/trace/rv/monitors/sncid/sncid.c             |  95 -------
 kernel/trace/rv/monitors/sncid/sncid.h             |  49 ----
 kernel/trace/rv/monitors/snep/Kconfig              |   2 +-
 kernel/trace/rv/monitors/snep/snep.c               |   4 +-
 kernel/trace/rv/monitors/{sncid => sssw}/Kconfig   |  10 +-
 kernel/trace/rv/monitors/sssw/sssw.c               | 116 ++++++++
 kernel/trace/rv/monitors/sssw/sssw.h               | 105 +++++++
 kernel/trace/rv/monitors/sssw/sssw_trace.h         |  15 +
 kernel/trace/rv/monitors/sts/Kconfig               |  19 ++
 kernel/trace/rv/monitors/sts/sts.c                 | 156 +++++++++++
 kernel/trace/rv/monitors/sts/sts.h                 | 117 ++++++++
 .../monitors/{tss/tss_trace.h => sts/sts_trace.h}  |   8 +-
 kernel/trace/rv/monitors/tss/tss.c                 |  90 ------
 kernel/trace/rv/monitors/tss/tss.h                 |  47 ----
 kernel/trace/rv/monitors/wip/Kconfig               |   2 +-
 kernel/trace/rv/rv.c                               |   2 +-
 kernel/trace/rv/rv_reactors.c                      |   4 +-
 kernel/trace/rv/rv_trace.h                         | 114 +++++---
 tools/verification/models/sched/nrp.dot            |  29 ++
 tools/verification/models/sched/opid.dot           |  35 +++
 tools/verification/models/sched/sncid.dot          |  18 --
 tools/verification/models/sched/sssw.dot           |  30 ++
 tools/verification/models/sched/sts.dot            |  38 +++
 tools/verification/models/sched/tss.dot            |  18 --
 44 files changed, 1668 insertions(+), 495 deletions(-)
 rename kernel/trace/rv/monitors/{tss => nrp}/Kconfig (51%)
 create mode 100644 kernel/trace/rv/monitors/nrp/nrp.c
 create mode 100644 kernel/trace/rv/monitors/nrp/nrp.h
 create mode 100644 kernel/trace/rv/monitors/nrp/nrp_trace.h
 create mode 100644 kernel/trace/rv/monitors/opid/Kconfig
 create mode 100644 kernel/trace/rv/monitors/opid/opid.c
 create mode 100644 kernel/trace/rv/monitors/opid/opid.h
 rename kernel/trace/rv/monitors/{sncid/sncid_trace.h => opid/opid_trace.h} (66%)
 delete mode 100644 kernel/trace/rv/monitors/sncid/sncid.c
 delete mode 100644 kernel/trace/rv/monitors/sncid/sncid.h
 rename kernel/trace/rv/monitors/{sncid => sssw}/Kconfig (58%)
 create mode 100644 kernel/trace/rv/monitors/sssw/sssw.c
 create mode 100644 kernel/trace/rv/monitors/sssw/sssw.h
 create mode 100644 kernel/trace/rv/monitors/sssw/sssw_trace.h
 create mode 100644 kernel/trace/rv/monitors/sts/Kconfig
 create mode 100644 kernel/trace/rv/monitors/sts/sts.c
 create mode 100644 kernel/trace/rv/monitors/sts/sts.h
 rename kernel/trace/rv/monitors/{tss/tss_trace.h => sts/sts_trace.h} (67%)
 delete mode 100644 kernel/trace/rv/monitors/tss/tss.c
 delete mode 100644 kernel/trace/rv/monitors/tss/tss.h
 create mode 100644 tools/verification/models/sched/nrp.dot
 create mode 100644 tools/verification/models/sched/opid.dot
 delete mode 100644 tools/verification/models/sched/sncid.dot
 create mode 100644 tools/verification/models/sched/sssw.dot
 create mode 100644 tools/verification/models/sched/sts.dot
 delete mode 100644 tools/verification/models/sched/tss.dot
#1 lore raw

PATCH 1/11 Fix wrong type cast in monitors_show()

From: Nam Cao <[email protected]>

Argument 'p' of monitors_show() is not a pointer to struct rv_monitor, it is actually a pointer to the list_head inside struct rv_monitor. Therefore it is wrong to cast 'p' to struct rv_monitor *.

This wrong type cast has been there since the beginning. But it still worked because the list_head was the first field in struct rv_monitor_def. This is no longer true since commit 24cbfe18d55a ("rv: Merge struct rv_monitor_def into struct rv_monitor") moved the list_head, and this wrong type cast became a functional problem.

Properly use container_of() instead.

---
 kernel/trace/rv/rv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
kernel/trace/rv/rv.c +1 -1
index 6c8498743b98..bd7d56dbf6c2 100644
@@ -458,7 +458,7 @@ static int create_monitor_dir(struct rv_monitor *mon, struct rv_monitor *parent)
  */
 static int monitors_show(struct seq_file *m, void *p)
 {
-	struct rv_monitor *mon = p;
+	struct rv_monitor *mon = container_of(p, struct rv_monitor, list);
 
 	if (mon->parent)
 		seq_printf(m, "%s:%s\n", mon->parent->name, mon->name);
Signature · 1 line
2.47.2
#2 lore raw

PATCH 2/11 Fix wrong type cast in reactors_show() and monitor_reactor_show()

In reply to Steven Rostedt

From: Nam Cao <[email protected]>

Argument 'p' of reactors_show() and monitor_reactor_show() is not a pointer to struct rv_reactor, it is actually a pointer to the list_head inside struct rv_reactor. Therefore it's wrong to cast 'p' to struct rv_reactor *.

This wrong type cast has been there since the beginning. But it still worked because the list_head was the first field in struct rv_reactor_def. This is no longer true since commit 3d3c376118b5 ("rv: Merge struct rv_reactor_def into struct rv_reactor") moved the list_head, and this wrong type cast became a functional problem.

Properly use container_of() instead.

Cc Masami Hiramatsu <[email protected]>
Cc Mathieu Desnoyers <[email protected]>
Cc Gabriele Monaco <[email protected]>
Fixes 3d3c376118b5 ("rv: Merge struct rv_reactor_def into struct rv_reactor")
---
 kernel/trace/rv/rv_reactors.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
kernel/trace/rv/rv_reactors.c +2 -2
index 106f2c4740f2..d32859fec238 100644
@@ -86,7 +86,7 @@ static struct rv_reactor *get_reactor_rdef_by_name(char *name)
  */
 static int reactors_show(struct seq_file *m, void *p)
 {
-	struct rv_reactor *reactor = p;
+	struct rv_reactor *reactor = container_of(p, struct rv_reactor, list);
 
 	seq_printf(m, "%s\n", reactor->name);
 	return 0;
@@ -139,7 +139,7 @@ static const struct file_operations available_reactors_ops = {
 static int monitor_reactor_show(struct seq_file *m, void *p)
 {
 	struct rv_monitor *mon = m->private;
-	struct rv_reactor *reactor = p;
+	struct rv_reactor *reactor = container_of(p, struct rv_reactor, list);
 
 	if (mon->reactor == reactor)
 		seq_printf(m, "[%s]\n", reactor->name);
Signature · 1 line
2.47.2
#3 lore raw

PATCH 3/11 Add da_handle_start_run_event_ to per-task monitors

In reply to Steven Rostedt

From: Gabriele Monaco <[email protected]>

The RV da_monitor API allows to start monitors in two ways:
da_handle_start_event_NAME and da_handle_start_run_event_NAME. The former is used when the event is followed by the initial state of the module, so we ignore the event but we know the monitor is in the initial state and can start monitoring, the latter can be used if the event can only occur in the initial state, so we do handle the event as if the monitor was in the initial state.
This latter API is defined for implicit monitors but not per-task ones.

Define da_handle_start_run_event_NAME macro also for per-task monitors.

---
 include/rv/da_monitor.h | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)
include/rv/da_monitor.h +24 -0
index 15f9ed4e4bb6..ed3c34fe18d6 100644
@@ -487,6 +487,30 @@ da_handle_start_event_##name(struct task_struct *tsk, enum events_##name event)
 	__da_handle_event_##name(da_mon, tsk, event);						\
 												\
 	return 1;										\
+}												\
+												\
+/*												\
+ * da_handle_start_run_event_##name - start monitoring and handle event				\
+ *												\
+ * This function is used to notify the monitor that the system is in the			\
+ * initial state, so the monitor can start monitoring and handling event.			\
+ */												\
+static inline bool										\
+da_handle_start_run_event_##name(struct task_struct *tsk, enum events_##name event)		\
+{												\
+	struct da_monitor *da_mon;								\
+												\
+	if (!da_monitor_enabled_##name())							\
+		return 0;									\
+												\
+	da_mon = da_get_monitor_##name(tsk);							\
+												\
+	if (unlikely(!da_monitoring_##name(da_mon)))						\
+		da_monitor_start_##name(da_mon);						\
+												\
+	__da_handle_event_##name(da_mon, tsk, event);						\
+												\
+	return 1;										\
 }
 
 /*
Signature · 1 line
2.47.2
#4 lore raw

PATCH 4/11 Remove trailing whitespace from tracepoint string

In reply to Steven Rostedt

From: Gabriele Monaco <[email protected]>

RV event tracepoints print a line with the format:

    "event_xyz: S0 x event -> S1 "
    "event_xyz: S1 x event -> S0 (final)"

While printing an event leading to a non-final state, the line has a trailing white space (visible above before the closing ").

Adapt the format string not to print the trailing whitespace if we are not printing "(final)".

---
 kernel/trace/rv/rv_trace.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)
kernel/trace/rv/rv_trace.h +4 -4
index b6f310498466..17ba07329b67 100644
@@ -29,11 +29,11 @@ DECLARE_EVENT_CLASS(event_da_monitor,
 		__entry->final_state		= final_state;
 	),
 
-	TP_printk("%s x %s -> %s %s",
+	TP_printk("%s x %s -> %s%s",
 		__entry->state,
 		__entry->event,
 		__entry->next_state,
-		__entry->final_state ? "(final)" : "")
+		__entry->final_state ? " (final)" : "")
 );
 
 DECLARE_EVENT_CLASS(error_da_monitor,
@@ -90,12 +90,12 @@ DECLARE_EVENT_CLASS(event_da_monitor_id,
 		__entry->final_state		= final_state;
 	),
 
-	TP_printk("%d: %s x %s -> %s %s",
+	TP_printk("%d: %s x %s -> %s%s",
 		__entry->id,
 		__entry->state,
 		__entry->event,
 		__entry->next_state,
-		__entry->final_state ? "(final)" : "")
+		__entry->final_state ? " (final)" : "")
 );
 
 DECLARE_EVENT_CLASS(error_da_monitor_id,
Signature · 1 line
2.47.2
#5 lore raw

PATCH 5/11 Use strings in da monitors tracepoints

In reply to Steven Rostedt

From: Gabriele Monaco <[email protected]>

Using DA monitors tracepoints with KASAN enabled triggers the following warning:

 BUG: KASAN: global-out-of-bounds in do_trace_event_raw_event_event_da_monitor+0xd6/0x1a0
 Read of size 32 at addr ffffffffaada8980 by task ...
 Call Trace:
  <TASK>
 [...]
  do_trace_event_raw_event_event_da_monitor+0xd6/0x1a0
  ? __pfx_do_trace_event_raw_event_event_da_monitor+0x10/0x10
  ? trace_event_sncid+0x83/0x200
  trace_event_sncid+0x163/0x200
 [...]
 The buggy address belongs to the variable:
  automaton_snep+0x4e0/0x5e0

This is caused by the tracepoints reading 32 bytes __array instead of __string from the automata definition. Such strings are literals and reading 32 bytes ends up in out of bound memory accesses (e.g. the next automaton's data in this case).
The error is harmless as, while printing the string, we stop at the null terminator, but it should still be fixed.

Use the __string facilities while defining the tracepoints to avoid reading out of bound memory.

Cc Masami Hiramatsu <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Tomas Glozar <[email protected]>
Cc Juri Lelli <[email protected]>
Cc Clark Williams <[email protected]>
Cc John Kacur <[email protected]>
Fixes 792575348ff7 ("rv/include: Add deterministic automata monitor definition via C macros")
---
 kernel/trace/rv/rv_trace.h | 76 +++++++++++++++++++-------------------
 1 file changed, 38 insertions(+), 38 deletions(-)
kernel/trace/rv/rv_trace.h +38 -38
index 17ba07329b67..d38e0d3abdfd 100644
@@ -16,23 +16,23 @@ DECLARE_EVENT_CLASS(event_da_monitor,
 	TP_ARGS(state, event, next_state, final_state),
 
 	TP_STRUCT__entry(
-		__array(	char,	state,		MAX_DA_NAME_LEN	)
-		__array(	char,	event,		MAX_DA_NAME_LEN	)
-		__array(	char,	next_state,	MAX_DA_NAME_LEN	)
-		__field(	bool,	final_state			)
+		__string(	state,		state		)
+		__string(	event,		event		)
+		__string(	next_state,	next_state	)
+		__field(	bool,		final_state	)
 	),
 
 	TP_fast_assign(
-		memcpy(__entry->state,		state,		MAX_DA_NAME_LEN);
-		memcpy(__entry->event,		event,		MAX_DA_NAME_LEN);
-		memcpy(__entry->next_state,	next_state,	MAX_DA_NAME_LEN);
-		__entry->final_state		= final_state;
+		__assign_str(state);
+		__assign_str(event);
+		__assign_str(next_state);
+		__entry->final_state = final_state;
 	),
 
 	TP_printk("%s x %s -> %s%s",
-		__entry->state,
-		__entry->event,
-		__entry->next_state,
+		__get_str(state),
+		__get_str(event),
+		__get_str(next_state),
 		__entry->final_state ? " (final)" : "")
 );
 
@@ -43,18 +43,18 @@ DECLARE_EVENT_CLASS(error_da_monitor,
 	TP_ARGS(state, event),
 
 	TP_STRUCT__entry(
-		__array(	char,	state,		MAX_DA_NAME_LEN	)
-		__array(	char,	event,		MAX_DA_NAME_LEN	)
+		__string(	state,	state	)
+		__string(	event,	event	)
 	),
 
 	TP_fast_assign(
-		memcpy(__entry->state,		state,		MAX_DA_NAME_LEN);
-		memcpy(__entry->event,		event,		MAX_DA_NAME_LEN);
+		__assign_str(state);
+		__assign_str(event);
 	),
 
 	TP_printk("event %s not expected in the state %s",
-		__entry->event,
-		__entry->state)
+		__get_str(event),
+		__get_str(state))
 );
 
 #include <monitors/wip/wip_trace.h>
@@ -75,26 +75,26 @@ DECLARE_EVENT_CLASS(event_da_monitor_id,
 	TP_ARGS(id, state, event, next_state, final_state),
 
 	TP_STRUCT__entry(
-		__field(	int,	id				)
-		__array(	char,	state,		MAX_DA_NAME_LEN	)
-		__array(	char,	event,		MAX_DA_NAME_LEN	)
-		__array(	char,	next_state,	MAX_DA_NAME_LEN	)
-		__field(	bool,	final_state			)
+		__field(	int,		id		)
+		__string(	state,		state		)
+		__string(	event,		event		)
+		__string(	next_state,	next_state	)
+		__field(	bool,		final_state	)
 	),
 
 	TP_fast_assign(
-		memcpy(__entry->state,		state,		MAX_DA_NAME_LEN);
-		memcpy(__entry->event,		event,		MAX_DA_NAME_LEN);
-		memcpy(__entry->next_state,	next_state,	MAX_DA_NAME_LEN);
-		__entry->id			= id;
-		__entry->final_state		= final_state;
+		__assign_str(state);
+		__assign_str(event);
+		__assign_str(next_state);
+		__entry->id		= id;
+		__entry->final_state	= final_state;
 	),
 
 	TP_printk("%d: %s x %s -> %s%s",
 		__entry->id,
-		__entry->state,
-		__entry->event,
-		__entry->next_state,
+		__get_str(state),
+		__get_str(event),
+		__get_str(next_state),
 		__entry->final_state ? " (final)" : "")
 );
 
@@ -105,21 +105,21 @@ DECLARE_EVENT_CLASS(error_da_monitor_id,
 	TP_ARGS(id, state, event),
 
 	TP_STRUCT__entry(
-		__field(	int,	id				)
-		__array(	char,	state,		MAX_DA_NAME_LEN	)
-		__array(	char,	event,		MAX_DA_NAME_LEN	)
+		__field(	int,	id	)
+		__string(	state,	state	)
+		__string(	event,	event	)
 	),
 
 	TP_fast_assign(
-		memcpy(__entry->state,		state,		MAX_DA_NAME_LEN);
-		memcpy(__entry->event,		event,		MAX_DA_NAME_LEN);
-		__entry->id			= id;
+		__assign_str(state);
+		__assign_str(event);
+		__entry->id	= id;
 	),
 
 	TP_printk("%d: event %s not expected in the state %s",
 		__entry->id,
-		__entry->event,
-		__entry->state)
+		__get_str(event),
+		__get_str(state))
 );
 
 #include <monitors/wwnr/wwnr_trace.h>
Signature · 1 line
2.47.2
#6 lore raw

PATCH 6/11 Adjust monitor dependencies

In reply to Steven Rostedt

From: Gabriele Monaco <[email protected]>

RV monitors relying on the preemptirqs tracepoints are set as dependent on PREEMPT_TRACER and IRQSOFF_TRACER. In fact, those configurations do enable the tracepoints but are not the minimal configurations enabling them, which are TRACE_PREEMPT_TOGGLE and TRACE_IRQFLAGS (not selectable manually).

Set TRACE_PREEMPT_TOGGLE and TRACE_IRQFLAGS as dependencies for monitors.

Cc Masami Hiramatsu <[email protected]>
Cc Ingo Molnar <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Tomas Glozar <[email protected]>
Cc Juri Lelli <[email protected]>
Cc Clark Williams <[email protected]>
Cc John Kacur <[email protected]>
Fixes fbe6c09b7eb4 ("rv: Add scpd, snep and sncid per-cpu monitors")
---
 kernel/trace/rv/monitors/scpd/Kconfig  | 2 +-
 kernel/trace/rv/monitors/sncid/Kconfig | 2 +-
 kernel/trace/rv/monitors/snep/Kconfig  | 2 +-
 kernel/trace/rv/monitors/wip/Kconfig   | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)
kernel/trace/rv/monitors/scpd/Kconfig +1 -1
index b9114fbf680f..682d0416188b 100644
@@ -2,7 +2,7 @@
 #
 config RV_MON_SCPD
 	depends on RV
-	depends on PREEMPT_TRACER
+	depends on TRACE_PREEMPT_TOGGLE
 	depends on RV_MON_SCHED
 	default y
 	select DA_MON_EVENTS_IMPLICIT
kernel/trace/rv/monitors/sncid/Kconfig +1 -1
index 76bcfef4fd10..3a5639feaaaf 100644
@@ -2,7 +2,7 @@
 #
 config RV_MON_SNCID
 	depends on RV
-	depends on IRQSOFF_TRACER
+	depends on TRACE_IRQFLAGS
 	depends on RV_MON_SCHED
 	default y
 	select DA_MON_EVENTS_IMPLICIT
kernel/trace/rv/monitors/snep/Kconfig +1 -1
index 77527f971232..7dd54f434ff7 100644
@@ -2,7 +2,7 @@
 #
 config RV_MON_SNEP
 	depends on RV
-	depends on PREEMPT_TRACER
+	depends on TRACE_PREEMPT_TOGGLE
 	depends on RV_MON_SCHED
 	default y
 	select DA_MON_EVENTS_IMPLICIT
kernel/trace/rv/monitors/wip/Kconfig +1 -1
index e464b9294865..87a26195792b 100644
@@ -2,7 +2,7 @@
 #
 config RV_MON_WIP
 	depends on RV
-	depends on PREEMPT_TRACER
+	depends on TRACE_PREEMPT_TOGGLE
 	select DA_MON_EVENTS_IMPLICIT
 	bool "wip monitor"
 	help
Signature · 1 line
2.47.2
#7 lore raw

PATCH 7/11 Retry when da monitor detects race conditions

In reply to Steven Rostedt

From: Gabriele Monaco <[email protected]>

DA monitor can be accessed from multiple cores simultaneously, this is likely, for instance when dealing with per-task monitors reacting on events that do not always occur on the CPU where the task is running. This can cause race conditions where two events change the next state and we see inconsistent values. E.g.:

[62] event_srs: 27: sleepable x sched_wakeup -> running (final)
[63] event_srs: 27: sleepable x sched_set_state_sleepable -> sleepable
[63] error_srs: 27: event sched_switch_suspend not expected in the state running

In this case the monitor fails because the event on CPU 62 wins against the one on CPU 63, although the correct state should have been sleepable, since the task get suspended.

Detect if the current state was modified by using try_cmpxchg while storing the next value. If it was, try again reading the current state. After a maximum number of failed retries, react by calling a special tracepoint, print on the console and reset the monitor.

Remove the functions da_monitor_curr_state() and da_monitor_set_state() as they only hide the underlying implementation in this case.

Monitors where this type of condition can occur must be able to account for racing events in any possible order, as we cannot know the winner.

---
 include/linux/rv.h         |   3 +-
 include/rv/da_monitor.h    | 107 +++++++++++++++++++------------------
 kernel/trace/rv/Kconfig    |   5 ++
 kernel/trace/rv/rv_trace.h |  24 +++++++++
 4 files changed, 85 insertions(+), 54 deletions(-)
include/linux/rv.h +2 -1
index 80731242fe60..14410a42faef 100644
@@ -10,7 +10,8 @@
 #include <linux/types.h>
 #include <linux/list.h>
 
-#define MAX_DA_NAME_LEN	32
+#define MAX_DA_NAME_LEN			32
+#define MAX_DA_RETRY_RACING_EVENTS	3
 
 #ifdef CONFIG_RV
 #include <linux/bitops.h>
include/rv/da_monitor.h +54 -53

140 lines not on this page · raw message

kernel/trace/rv/Kconfig +5 -0
index 26017378f79b..34164eb4ec91 100644
@@ -3,12 +3,17 @@
 config RV_MON_EVENTS
 	bool
 
+config RV_MON_MAINTENANCE_EVENTS
+	bool
+
 config DA_MON_EVENTS_IMPLICIT
 	select RV_MON_EVENTS
+	select RV_MON_MAINTENANCE_EVENTS
 	bool
 
 config DA_MON_EVENTS_ID
 	select RV_MON_EVENTS
+	select RV_MON_MAINTENANCE_EVENTS
 	bool
 
 config LTL_MON_EVENTS_ID
kernel/trace/rv/rv_trace.h +24 -0
index d38e0d3abdfd..3af46cd185b3 100644
@@ -176,6 +176,30 @@ DECLARE_EVENT_CLASS(error_ltl_monitor_id,
 #include <monitors/sleep/sleep_trace.h>
 // Add new monitors based on CONFIG_LTL_MON_EVENTS_ID here
 #endif /* CONFIG_LTL_MON_EVENTS_ID */
+
+#ifdef CONFIG_RV_MON_MAINTENANCE_EVENTS
+/* Tracepoint useful for monitors development, currenly only used in DA */
+TRACE_EVENT(rv_retries_error,
+
+	TP_PROTO(char *name, char *event),
+
+	TP_ARGS(name, event),
+
+	TP_STRUCT__entry(
+		__string(	name,	name	)
+		__string(	event,	event	)
+	),
+
+	TP_fast_assign(
+		__assign_str(name);
+		__assign_str(event);
+	),
+
+	TP_printk(__stringify(MAX_DA_RETRY_RACING_EVENTS)
+		" retries reached for event %s, resetting monitor %s",
+		__get_str(event), __get_str(name))
+);
+#endif /* CONFIG_RV_MON_MAINTENANCE_EVENTS */
 #endif /* _TRACE_RV_H */
 
 /* This part must be outside protection */
Signature · 1 line
2.47.2
#8 lore raw

PATCH 8/11 sched: Adapt sched tracepoints for RV task model

In reply to Steven Rostedt

From: Gabriele Monaco <[email protected]>

Add the following tracepoint:
* sched_set_need_resched(tsk, cpu, tif)
Called when a task is set the need resched [lazy] flag

Remove the unused ip parameter from sched_entry and sched_exit and alter sched_entry to have a value of preempt consistent with the one used in sched_switch.

Also adapt all monitors using sched_{entry,exit} to avoid breaking build.

These tracepoints are useful to describe the Linux task model and are adapted from the patches by Daniel Bristot de Oliveira
(https://bristot.me/linux-task-model/).

---
 include/linux/sched.h                  |  7 ++++++-
 include/trace/events/sched.h           | 12 ++++++++----
 kernel/sched/core.c                    | 13 ++++++++++---
 kernel/trace/rv/monitors/sco/sco.c     |  4 ++--
 kernel/trace/rv/monitors/scpd/scpd.c   |  4 ++--
 kernel/trace/rv/monitors/sncid/sncid.c |  4 ++--
 kernel/trace/rv/monitors/snep/snep.c   |  4 ++--
 kernel/trace/rv/monitors/tss/tss.c     |  4 ++--
 8 files changed, 34 insertions(+), 18 deletions(-)
include/linux/sched.h +6 -1
index fabd7fe1a07a..91d1fdbc2f56 100644
@@ -339,9 +339,11 @@ extern void io_schedule_finish(int token);
 extern long io_schedule_timeout(long timeout);
 extern void io_schedule(void);
 
-/* wrapper function to trace from this header file */
+/* wrapper functions to trace from this header file */
 DECLARE_TRACEPOINT(sched_set_state_tp);
 extern void __trace_set_current_state(int state_value);
+DECLARE_TRACEPOINT(sched_set_need_resched_tp);
+extern void __trace_set_need_resched(struct task_struct *curr, int tif);
 
 /**
  * struct prev_cputime - snapshot of system and user cputime
@@ -2063,6 +2065,9 @@ static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag)
 
 static inline void set_tsk_need_resched(struct task_struct *tsk)
 {
+	if (tracepoint_enabled(sched_set_need_resched_tp) &&
+	    !test_tsk_thread_flag(tsk, TIF_NEED_RESCHED))
+		__trace_set_need_resched(tsk, TIF_NEED_RESCHED);
 	set_tsk_thread_flag(tsk,TIF_NEED_RESCHED);
 }
 
include/trace/events/sched.h +8 -4
index 4e6b2910cec3..c08893bde255 100644
@@ -882,18 +882,22 @@ DECLARE_TRACE(sched_compute_energy,
 	TP_ARGS(p, dst_cpu, energy, max_util, busy_time));
 
 DECLARE_TRACE(sched_entry,
-	TP_PROTO(bool preempt, unsigned long ip),
-	TP_ARGS(preempt, ip));
+	TP_PROTO(bool preempt),
+	TP_ARGS(preempt));
 
 DECLARE_TRACE(sched_exit,
-	TP_PROTO(bool is_switch, unsigned long ip),
-	TP_ARGS(is_switch, ip));
+	TP_PROTO(bool is_switch),
+	TP_ARGS(is_switch));
 
 DECLARE_TRACE_CONDITION(sched_set_state,
 	TP_PROTO(struct task_struct *tsk, int state),
 	TP_ARGS(tsk, state),
 	TP_CONDITION(!!(tsk->__state) != !!state));
 
+DECLARE_TRACE(sched_set_need_resched,
+	TP_PROTO(struct task_struct *tsk, int cpu, int tif),
+	TP_ARGS(tsk, cpu, tif));
+
 #endif /* _TRACE_SCHED_H */
 
 /* This part must be outside protection */
kernel/sched/core.c +10 -3
index ec68fc686bd7..b485e0639616 100644
@@ -1110,6 +1110,7 @@ static void __resched_curr(struct rq *rq, int tif)
 
 	cpu = cpu_of(rq);
 
+	trace_sched_set_need_resched_tp(curr, cpu, tif);
 	if (cpu == smp_processor_id()) {
 		set_ti_thread_flag(cti, tif);
 		if (tif == TIF_NEED_RESCHED)
@@ -1125,6 +1126,11 @@ static void __resched_curr(struct rq *rq, int tif)
 	}
 }
 
+void __trace_set_need_resched(struct task_struct *curr, int tif)
+{
+	trace_sched_set_need_resched_tp(curr, smp_processor_id(), tif);
+}
+
 void resched_curr(struct rq *rq)
 {
 	__resched_curr(rq, TIF_NEED_RESCHED);
@@ -5329,7 +5335,7 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev)
 	 * switched the context for the first time. It is returning from
 	 * schedule for the first time in this path.
 	 */
-	trace_sched_exit_tp(true, CALLER_ADDR0);
+	trace_sched_exit_tp(true);
 	preempt_enable();
 
 	if (current->set_child_tid)
@@ -6678,7 +6684,8 @@ static void __sched notrace __schedule(int sched_mode)
 	struct rq *rq;
 	int cpu;
 
-	trace_sched_entry_tp(preempt, CALLER_ADDR0);
+	/* Trace preemptions consistently with task switches */
+	trace_sched_entry_tp(sched_mode == SM_PREEMPT);
 
 	cpu = smp_processor_id();
 	rq = cpu_rq(cpu);
@@ -6793,7 +6800,7 @@ static void __sched notrace __schedule(int sched_mode)
 		__balance_callbacks(rq);
 		raw_spin_rq_unlock_irq(rq);
 	}
-	trace_sched_exit_tp(is_switch, CALLER_ADDR0);
+	trace_sched_exit_tp(is_switch);
 }
 
 void __noreturn do_task_dead(void)
kernel/trace/rv/monitors/sco/sco.c +2 -2
index 66f4639d46ac..04c36405e2e3 100644
@@ -24,12 +24,12 @@ static void handle_sched_set_state(void *data, struct task_struct *tsk, int stat
 	da_handle_start_event_sco(sched_set_state_sco);
 }
 
-static void handle_schedule_entry(void *data, bool preempt, unsigned long ip)
+static void handle_schedule_entry(void *data, bool preempt)
 {
 	da_handle_event_sco(schedule_entry_sco);
 }
 
-static void handle_schedule_exit(void *data, bool is_switch, unsigned long ip)
+static void handle_schedule_exit(void *data, bool is_switch)
 {
 	da_handle_start_event_sco(schedule_exit_sco);
 }
kernel/trace/rv/monitors/scpd/scpd.c +2 -2
index 299703cd72b0..1e351ba52fee 100644
@@ -30,12 +30,12 @@ static void handle_preempt_enable(void *data, unsigned long ip, unsigned long pa
 	da_handle_start_event_scpd(preempt_enable_scpd);
 }
 
-static void handle_schedule_entry(void *data, bool preempt, unsigned long ip)
+static void handle_schedule_entry(void *data, bool preempt)
 {
 	da_handle_event_scpd(schedule_entry_scpd);
 }
 
-static void handle_schedule_exit(void *data, bool is_switch, unsigned long ip)
+static void handle_schedule_exit(void *data, bool is_switch)
 {
 	da_handle_event_scpd(schedule_exit_scpd);
 }
kernel/trace/rv/monitors/sncid/sncid.c +2 -2
index 3e1ee715a0fb..c8491f426365 100644
@@ -30,12 +30,12 @@ static void handle_irq_enable(void *data, unsigned long ip, unsigned long parent
 	da_handle_start_event_sncid(irq_enable_sncid);
 }
 
-static void handle_schedule_entry(void *data, bool preempt, unsigned long ip)
+static void handle_schedule_entry(void *data, bool preempt)
 {
 	da_handle_start_event_sncid(schedule_entry_sncid);
 }
 
-static void handle_schedule_exit(void *data, bool is_switch, unsigned long ip)
+static void handle_schedule_exit(void *data, bool is_switch)
 {
 	da_handle_start_event_sncid(schedule_exit_sncid);
 }
kernel/trace/rv/monitors/snep/snep.c +2 -2
index 2adc3108d60c..558950f524a5 100644
@@ -30,12 +30,12 @@ static void handle_preempt_enable(void *data, unsigned long ip, unsigned long pa
 	da_handle_start_event_snep(preempt_enable_snep);
 }
 
-static void handle_schedule_entry(void *data, bool preempt, unsigned long ip)
+static void handle_schedule_entry(void *data, bool preempt)
 {
 	da_handle_event_snep(schedule_entry_snep);
 }
 
-static void handle_schedule_exit(void *data, bool is_switch, unsigned long ip)
+static void handle_schedule_exit(void *data, bool is_switch)
 {
 	da_handle_start_event_snep(schedule_exit_snep);
 }
kernel/trace/rv/monitors/tss/tss.c +2 -2
index 0452fcd9edcf..95ebd15131f5 100644
@@ -27,12 +27,12 @@ static void handle_sched_switch(void *data, bool preempt,
 	da_handle_event_tss(sched_switch_tss);
 }
 
-static void handle_schedule_entry(void *data, bool preempt, unsigned long ip)
+static void handle_schedule_entry(void *data, bool preempt)
 {
 	da_handle_event_tss(schedule_entry_tss);
 }
 
-static void handle_schedule_exit(void *data, bool is_switch, unsigned long ip)
+static void handle_schedule_exit(void *data, bool is_switch)
 {
 	da_handle_start_event_tss(schedule_exit_tss);
 }
Signature · 1 line
2.47.2
#9 lore raw

PATCH 9/11 Replace tss and sncid monitors with more complete sts

In reply to Steven Rostedt

From: Gabriele Monaco <[email protected]>

The tss monitor currently guarantees task switches can happen only while scheduling, whereas the sncid monitor enforces scheduling occurs with interrupt disabled.

Replace the monitors with a more comprehensive specification which implies both but also ensures that:
* each scheduler call disable interrupts to switch
* each task switch happens with interrupts disabled

Cc Ingo Molnar <[email protected]>
Cc Jonathan Corbet <[email protected]>
Cc Masami Hiramatsu <[email protected]>
Cc Nam Cao <[email protected]>
Cc Tomas Glozar <[email protected]>
Cc Juri Lelli <[email protected]>
Cc Clark Williams <[email protected]>
Cc John Kacur <[email protected]>
Cc Peter Zijlstra <[email protected]>
---
 Documentation/trace/rv/monitor_sched.rst      |  87 +++++-----
 kernel/trace/rv/Kconfig                       |   3 +-
 kernel/trace/rv/Makefile                      |   3 +-
 kernel/trace/rv/monitors/sncid/Kconfig        |  15 --
 kernel/trace/rv/monitors/sncid/sncid.c        |  95 -----------
 kernel/trace/rv/monitors/sncid/sncid.h        |  49 ------
 kernel/trace/rv/monitors/sncid/sncid_trace.h  |  15 --
 kernel/trace/rv/monitors/sts/Kconfig          |  19 +++
 kernel/trace/rv/monitors/sts/sts.c            | 156 ++++++++++++++++++
 kernel/trace/rv/monitors/sts/sts.h            | 117 +++++++++++++
 .../{tss/tss_trace.h => sts/sts_trace.h}      |   8 +-
 kernel/trace/rv/monitors/tss/Kconfig          |  14 --
 kernel/trace/rv/monitors/tss/tss.c            |  90 ----------
 kernel/trace/rv/monitors/tss/tss.h            |  47 ------
 kernel/trace/rv/rv_trace.h                    |   3 +-
 tools/verification/models/sched/sncid.dot     |  18 --
 tools/verification/models/sched/sts.dot       |  38 +++++
 tools/verification/models/sched/tss.dot       |  18 --
 18 files changed, 385 insertions(+), 410 deletions(-)
 delete mode 100644 kernel/trace/rv/monitors/sncid/Kconfig
 delete mode 100644 kernel/trace/rv/monitors/sncid/sncid.c
 delete mode 100644 kernel/trace/rv/monitors/sncid/sncid.h
 delete mode 100644 kernel/trace/rv/monitors/sncid/sncid_trace.h
 create mode 100644 kernel/trace/rv/monitors/sts/Kconfig
 create mode 100644 kernel/trace/rv/monitors/sts/sts.c
 create mode 100644 kernel/trace/rv/monitors/sts/sts.h
 rename kernel/trace/rv/monitors/{tss/tss_trace.h => sts/sts_trace.h} (67%)
 delete mode 100644 kernel/trace/rv/monitors/tss/Kconfig
 delete mode 100644 kernel/trace/rv/monitors/tss/tss.c
 delete mode 100644 kernel/trace/rv/monitors/tss/tss.h
 delete mode 100644 tools/verification/models/sched/sncid.dot
 create mode 100644 tools/verification/models/sched/sts.dot
 delete mode 100644 tools/verification/models/sched/tss.dot
Documentation/trace/rv/monitor_sched.rst +48 -39
index 24b2c62a3bc2..6c4c00216c07 100644
@@ -40,26 +40,6 @@ defined in by Daniel Bristot in [1].
 
 Currently we included the following:
 
-Monitor tss
-~~~~~~~~~~~
-
-The task switch while scheduling (tss) monitor ensures a task switch happens
-only in scheduling context, that is inside a call to `__schedule`::
-
-                     |
-                     |
-                     v
-                   +-----------------+
-                   |     thread      | <+
-                   +-----------------+  |
-                     |                  |
-                     | schedule_entry   | schedule_exit
-                     v                  |
-    sched_switch                        |
-  +---------------                      |
-  |                       sched         |
-  +-------------->                     -+
-
 Monitor sco
 ~~~~~~~~~~~
 
@@ -144,26 +124,55 @@ does not enable preemption::
                                                   |
                           scheduling_contex      -+
 
-Monitor sncid
-~~~~~~~~~~~~~
-
-The schedule not called with interrupt disabled (sncid) monitor ensures
-schedule is not called with interrupt disabled::
+Monitor sts
+~~~~~~~~~~~
 
-                       |
-                       |
-                       v
-    schedule_entry   +--------------+
-    schedule_exit    |              |
-  +----------------- |  can_sched   |
-  |                  |              |
-  +----------------> |              | <+
-                     +--------------+  |
-                       |               |
-                       | irq_disable   | irq_enable
-                       v               |
-                                       |
-                        cant_sched    -+
+The schedule implies task switch (sts) monitor ensures a task switch happens
+only in scheduling context and up to once, as well as scheduling occurs with
+interrupts enabled but no task switch can happen before interrupts are
+disabled. When the next task picked for execution is the same as the previously
+running one, no real task switch occurs but interrupts are disabled nonetheless::
+
+    irq_entry                      |
+     +----+                        |
+     v    |                        v
+ +------------+ irq_enable    #===================#   irq_disable
+ |            | ------------> H                   H   irq_entry
+ | cant_sched | <------------ H                   H   irq_enable
+ |            | irq_disable   H     can_sched     H --------------+
+ +------------+               H                   H               |
+                              H                   H               |
+            +---------------> H                   H <-------------+
+            |                 #===================#
+            |                   |
+      schedule_exit             | schedule_entry
+            |                   v
+            |   +-------------------+     irq_enable
+            |   |    scheduling     | <---------------+
+            |   +-------------------+                 |
+            |     |                                   |
+            |     | irq_disable                    +--------+  irq_entry
+            |     v                                |        | --------+
+            |   +-------------------+  irq_entry   | in_irq |         |
+            |   |                   | -----------> |        | <-------+
+            |   | disable_to_switch |              +--------+
+            |   |                   | --+
+            |   +-------------------+   |
+            |     |                     |
+            |     | sched_switch        |
+            |     v                     |
+            |   +-------------------+   |
+            |   |     switching     |   | irq_enable
+            |   +-------------------+   |
+            |     |                     |
+            |     | irq_enable          |
+            |     v                     |
+            |   +-------------------+   |
+            +-- |  enable_to_exit   | <-+
+                +-------------------+
+                  ^               | irq_disable
+                  |               | irq_entry
+                  +---------------+ irq_enable
 
 References
 ----------
kernel/trace/rv/Kconfig +1 -2
index 34164eb4ec91..b688b24081c8 100644
@@ -50,12 +50,11 @@ source "kernel/trace/rv/monitors/wip/Kconfig"
 source "kernel/trace/rv/monitors/wwnr/Kconfig"
 
 source "kernel/trace/rv/monitors/sched/Kconfig"
-source "kernel/trace/rv/monitors/tss/Kconfig"
 source "kernel/trace/rv/monitors/sco/Kconfig"
 source "kernel/trace/rv/monitors/snroc/Kconfig"
 source "kernel/trace/rv/monitors/scpd/Kconfig"
 source "kernel/trace/rv/monitors/snep/Kconfig"
-source "kernel/trace/rv/monitors/sncid/Kconfig"
+source "kernel/trace/rv/monitors/sts/Kconfig"
 # Add new sched monitors here
 
 source "kernel/trace/rv/monitors/rtapp/Kconfig"
kernel/trace/rv/Makefile +1 -2
index 13ec2944c665..1939d3d7621c 100644
@@ -6,15 +6,14 @@ obj-$(CONFIG_RV) += rv.o
 obj-$(CONFIG_RV_MON_WIP) += monitors/wip/wip.o
 obj-$(CONFIG_RV_MON_WWNR) += monitors/wwnr/wwnr.o
 obj-$(CONFIG_RV_MON_SCHED) += monitors/sched/sched.o
-obj-$(CONFIG_RV_MON_TSS) += monitors/tss/tss.o
 obj-$(CONFIG_RV_MON_SCO) += monitors/sco/sco.o
 obj-$(CONFIG_RV_MON_SNROC) += monitors/snroc/snroc.o
 obj-$(CONFIG_RV_MON_SCPD) += monitors/scpd/scpd.o
 obj-$(CONFIG_RV_MON_SNEP) += monitors/snep/snep.o
-obj-$(CONFIG_RV_MON_SNCID) += monitors/sncid/sncid.o
 obj-$(CONFIG_RV_MON_RTAPP) += monitors/rtapp/rtapp.o
 obj-$(CONFIG_RV_MON_PAGEFAULT) += monitors/pagefault/pagefault.o
 obj-$(CONFIG_RV_MON_SLEEP) += monitors/sleep/sleep.o
+obj-$(CONFIG_RV_MON_STS) += monitors/sts/sts.o
 # Add new monitors here
 obj-$(CONFIG_RV_REACTORS) += rv_reactors.o
 obj-$(CONFIG_RV_REACT_PRINTK) += reactor_printk.o
kernel/trace/rv/monitors/sncid/Kconfig deleted +0 -15
deleted file mode 100644
index 3a5639feaaaf..000000000000
@@ -1,15 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-#
-config RV_MON_SNCID
-	depends on RV
-	depends on TRACE_IRQFLAGS
-	depends on RV_MON_SCHED
-	default y
-	select DA_MON_EVENTS_IMPLICIT
-	bool "sncid monitor"
-	help
-	  Monitor to ensure schedule is not called with interrupt disabled.
-	  This monitor is part of the sched monitors collection.
-
-	  For further information, see:
-	    Documentation/trace/rv/monitor_sched.rst
kernel/trace/rv/monitors/sncid/sncid.c deleted +0 -95

95 lines not on this page · raw message

kernel/trace/rv/monitors/sncid/sncid.h deleted +0 -49

49 lines not on this page · raw message

kernel/trace/rv/monitors/sncid/sncid_trace.h deleted +0 -15
deleted file mode 100644
index 3ce42a57671d..000000000000
@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-
-/*
- * Snippet to be included in rv_trace.h
- */
-
-#ifdef CONFIG_RV_MON_SNCID
-DEFINE_EVENT(event_da_monitor, event_sncid,
-	     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_sncid,
-	     TP_PROTO(char *state, char *event),
-	     TP_ARGS(state, event));
-#endif /* CONFIG_RV_MON_SNCID */
kernel/trace/rv/monitors/sts/Kconfig new file +19 -0
new file mode 100644
index 000000000000..7d1ff0f6fc91
@@ -0,0 +1,19 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+config RV_MON_STS
+	depends on RV
+	depends on TRACE_IRQFLAGS
+	depends on RV_MON_SCHED
+	default y
+	select DA_MON_EVENTS_IMPLICIT
+	bool "sts monitor"
+	help
+	  Monitor to ensure relationships between scheduler and task switches
+	   * the scheduler is called and returns with interrupts disabled
+	   * each call to the scheduler has up to one switch
+	   * switches only happen inside the scheduler
+	   * each call to the scheduler disables interrupts to switch
+	  This monitor is part of the sched monitors collection.
+
+	  For further information, see:
+	    Documentation/trace/rv/monitor_sched.rst
kernel/trace/rv/monitors/sts/sts.c new file +156 -0

156 lines not on this page · raw message

kernel/trace/rv/monitors/sts/sts.h new file +117 -0

117 lines not on this page · raw message

kernel/trace/rv/monitors/sts/sts_trace.h renamed from kernel/trace/rv/monitors/tss/tss_trace.h +4 -4
similarity index 67%
rename from kernel/trace/rv/monitors/tss/tss_trace.h
rename to kernel/trace/rv/monitors/sts/sts_trace.h
index 4619dbb50cc0..d78beb58d5b3 100644
@@ -4,12 +4,12 @@
  * Snippet to be included in rv_trace.h
  */
 
-#ifdef CONFIG_RV_MON_TSS
-DEFINE_EVENT(event_da_monitor, event_tss,
+#ifdef CONFIG_RV_MON_STS
+DEFINE_EVENT(event_da_monitor, event_sts,
 	     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_tss,
+DEFINE_EVENT(error_da_monitor, error_sts,
 	     TP_PROTO(char *state, char *event),
 	     TP_ARGS(state, event));
-#endif /* CONFIG_RV_MON_TSS */
+#endif /* CONFIG_RV_MON_STS */
kernel/trace/rv/monitors/tss/Kconfig deleted +0 -14
deleted file mode 100644
index 479f86f52e60..000000000000
@@ -1,14 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-#
-config RV_MON_TSS
-	depends on RV
-	depends on RV_MON_SCHED
-	default y
-	select DA_MON_EVENTS_IMPLICIT
-	bool "tss monitor"
-	help
-	  Monitor to ensure sched_switch happens only in scheduling context.
-	  This monitor is part of the sched monitors collection.
-
-	  For further information, see:
-	    Documentation/trace/rv/monitor_sched.rst
kernel/trace/rv/monitors/tss/tss.c deleted +0 -90

90 lines not on this page · raw message

kernel/trace/rv/monitors/tss/tss.h deleted +0 -47

47 lines not on this page · raw message

kernel/trace/rv/rv_trace.h +1 -2
index 3af46cd185b3..97b2f7e07f27 100644
@@ -58,11 +58,10 @@ DECLARE_EVENT_CLASS(error_da_monitor,
 );
 
 #include <monitors/wip/wip_trace.h>
-#include <monitors/tss/tss_trace.h>
 #include <monitors/sco/sco_trace.h>
 #include <monitors/scpd/scpd_trace.h>
 #include <monitors/snep/snep_trace.h>
-#include <monitors/sncid/sncid_trace.h>
+#include <monitors/sts/sts_trace.h>
 // Add new monitors based on CONFIG_DA_MON_EVENTS_IMPLICIT here
 
 #endif /* CONFIG_DA_MON_EVENTS_IMPLICIT */
tools/verification/models/sched/sncid.dot deleted +0 -18
deleted file mode 100644
index 072851721b50..000000000000
@@ -1,18 +0,0 @@
-digraph state_automaton {
-	center = true;
-	size = "7,11";
-	{node [shape = plaintext, style=invis, label=""] "__init_can_sched"};
-	{node [shape = ellipse] "can_sched"};
-	{node [shape = plaintext] "can_sched"};
-	{node [shape = plaintext] "cant_sched"};
-	"__init_can_sched" -> "can_sched";
-	"can_sched" [label = "can_sched", color = green3];
-	"can_sched" -> "can_sched" [ label = "schedule_entry\nschedule_exit" ];
-	"can_sched" -> "cant_sched" [ label = "irq_disable" ];
-	"cant_sched" [label = "cant_sched"];
-	"cant_sched" -> "can_sched" [ label = "irq_enable" ];
-	{ rank = min ;
-		"__init_can_sched";
-		"can_sched";
-	}
-}
tools/verification/models/sched/sts.dot new file +38 -0
new file mode 100644
index 000000000000..8f5f38be04d5
@@ -0,0 +1,38 @@
+digraph state_automaton {
+	center = true;
+	size = "7,11";
+	{node [shape = plaintext, style=invis, label=""] "__init_can_sched"};
+	{node [shape = doublecircle] "can_sched"};
+	{node [shape = circle] "can_sched"};
+	{node [shape = circle] "cant_sched"};
+	{node [shape = circle] "disable_to_switch"};
+	{node [shape = circle] "enable_to_exit"};
+	{node [shape = circle] "in_irq"};
+	{node [shape = circle] "scheduling"};
+	{node [shape = circle] "switching"};
+	"__init_can_sched" -> "can_sched";
+	"can_sched" [label = "can_sched", color = green3];
+	"can_sched" -> "cant_sched" [ label = "irq_disable" ];
+	"can_sched" -> "scheduling" [ label = "schedule_entry" ];
+	"cant_sched" [label = "cant_sched"];
+	"cant_sched" -> "can_sched" [ label = "irq_enable" ];
+	"cant_sched" -> "cant_sched" [ label = "irq_entry" ];
+	"disable_to_switch" [label = "disable_to_switch"];
+	"disable_to_switch" -> "enable_to_exit" [ label = "irq_enable" ];
+	"disable_to_switch" -> "in_irq" [ label = "irq_entry" ];
+	"disable_to_switch" -> "switching" [ label = "sched_switch" ];
+	"enable_to_exit" [label = "enable_to_exit"];
+	"enable_to_exit" -> "can_sched" [ label = "schedule_exit" ];
+	"enable_to_exit" -> "enable_to_exit" [ label = "irq_disable\nirq_entry\nirq_enable" ];
+	"in_irq" [label = "in_irq"];
+	"in_irq" -> "in_irq" [ label = "irq_entry" ];
+	"in_irq" -> "scheduling" [ label = "irq_enable" ];
+	"scheduling" [label = "scheduling"];
+	"scheduling" -> "disable_to_switch" [ label = "irq_disable" ];
+	"switching" [label = "switching"];
+	"switching" -> "enable_to_exit" [ label = "irq_enable" ];
+	{ rank = min ;
+		"__init_can_sched";
+		"can_sched";
+	}
+}
tools/verification/models/sched/tss.dot deleted +0 -18
deleted file mode 100644
index 7dfa1d9121bb..000000000000
@@ -1,18 +0,0 @@
-digraph state_automaton {
-	center = true;
-	size = "7,11";
-	{node [shape = plaintext] "sched"};
-	{node [shape = plaintext, style=invis, label=""] "__init_thread"};
-	{node [shape = ellipse] "thread"};
-	{node [shape = plaintext] "thread"};
-	"__init_thread" -> "thread";
-	"sched" [label = "sched"];
-	"sched" -> "sched" [ label = "sched_switch" ];
-	"sched" -> "thread" [ label = "schedule_exit" ];
-	"thread" [label = "thread", color = green3];
-	"thread" -> "sched" [ label = "schedule_entry" ];
-	{ rank = min ;
-		"__init_thread";
-		"thread";
-	}
-}
Signature · 1 line
2.47.2
#10 lore raw

PATCH 10/11 Add nrp and sssw per-task monitors

In reply to Steven Rostedt

From: Gabriele Monaco <[email protected]>

Add 2 per-task monitors as part of the sched model:

* nrp: need-resched preempts
Monitor to ensure preemption requires need resched.
* sssw: set state sleep and wakeup
Monitor to ensure sched_set_state to sleepable leads to sleeping and sleeping tasks require wakeup.

---
 Documentation/trace/rv/monitor_sched.rst   | 167 +++++++++++++++++++++
 kernel/trace/rv/Kconfig                    |   2 +
 kernel/trace/rv/Makefile                   |   2 +
 kernel/trace/rv/monitors/nrp/Kconfig       |  16 ++
 kernel/trace/rv/monitors/nrp/nrp.c         | 138 +++++++++++++++++
 kernel/trace/rv/monitors/nrp/nrp.h         |  75 +++++++++
 kernel/trace/rv/monitors/nrp/nrp_trace.h   |  15 ++
 kernel/trace/rv/monitors/sched/Kconfig     |   1 +
 kernel/trace/rv/monitors/sssw/Kconfig      |  15 ++
 kernel/trace/rv/monitors/sssw/sssw.c       | 116 ++++++++++++++
 kernel/trace/rv/monitors/sssw/sssw.h       | 105 +++++++++++++
 kernel/trace/rv/monitors/sssw/sssw_trace.h |  15 ++
 kernel/trace/rv/rv_trace.h                 |   2 +
 tools/verification/models/sched/nrp.dot    |  29 ++++
 tools/verification/models/sched/sssw.dot   |  30 ++++
 15 files changed, 728 insertions(+)
 create mode 100644 kernel/trace/rv/monitors/nrp/Kconfig
 create mode 100644 kernel/trace/rv/monitors/nrp/nrp.c
 create mode 100644 kernel/trace/rv/monitors/nrp/nrp.h
 create mode 100644 kernel/trace/rv/monitors/nrp/nrp_trace.h
 create mode 100644 kernel/trace/rv/monitors/sssw/Kconfig
 create mode 100644 kernel/trace/rv/monitors/sssw/sssw.c
 create mode 100644 kernel/trace/rv/monitors/sssw/sssw.h
 create mode 100644 kernel/trace/rv/monitors/sssw/sssw_trace.h
 create mode 100644 tools/verification/models/sched/nrp.dot
 create mode 100644 tools/verification/models/sched/sssw.dot
Documentation/trace/rv/monitor_sched.rst +167 -0
index 6c4c00216c07..11ef963cb578 100644
@@ -174,6 +174,173 @@ running one, no real task switch occurs but interrupts are disabled nonetheless:
                   |               | irq_entry
                   +---------------+ irq_enable
 
+Monitor nrp
+-----------
+
+The need resched preempts (nrp) monitor ensures preemption requires
+``need_resched``. Only kernel preemption is considered, since preemption
+while returning to userspace, for this monitor, is indistinguishable from
+``sched_switch_yield`` (described in the sssw monitor).
+A kernel preemption is whenever ``__schedule`` is called with the preemption
+flag set to true (e.g. from preempt_enable or exiting from interrupts). This
+type of preemption occurs after the need for ``rescheduling`` has been set.
+This is not valid for the *lazy* variant of the flag, which causes only
+userspace preemption.
+A ``schedule_entry_preempt`` may involve a task switch or not, in the latter
+case, a task goes through the scheduler from a preemption context but it is
+picked as the next task to run. Since the scheduler runs, this clears the need
+to reschedule. The ``any_thread_running`` state does not imply the monitored
+task is not running as this monitor does not track the outcome of scheduling.
+
+In theory, a preemption can only occur after the ``need_resched`` flag is set. In
+practice, however, it is possible to see a preemption where the flag is not
+set. This can happen in one specific condition::
+
+  need_resched
+                   preempt_schedule()
+                                           preempt_schedule_irq()
+                                                   __schedule()
+  !need_resched
+                           __schedule()
+
+In the situation above, standard preemption starts (e.g. from preempt_enable
+when the flag is set), an interrupt occurs before scheduling and, on its exit
+path, it schedules, which clears the ``need_resched`` flag.
+When the preempted task runs again, the standard preemption started earlier
+resumes, although the flag is no longer set. The monitor considers this a
+``nested_preemption``, this allows another preemption without re-setting the
+flag. This condition relaxes the monitor constraints and may catch false
+negatives (i.e. no real ``nested_preemptions``) but makes the monitor more
+robust and able to validate other scenarios.
+For simplicity, the monitor starts in ``preempt_irq``, although no interrupt
+occurred, as the situation above is hard to pinpoint::
+
+    schedule_entry
+    irq_entry                 #===========================================#
+  +-------------------------- H                                           H
+  |                           H                                           H
+  +-------------------------> H             any_thread_running            H
+                              H                                           H
+  +-------------------------> H                                           H
+  |                           #===========================================#
+  | schedule_entry              |                       ^
+  | schedule_entry_preempt      | sched_need_resched    | schedule_entry
+  |                             |                      schedule_entry_preempt
+  |                             v                       |
+  |                           +----------------------+  |
+  |                      +--- |                      |  |
+  |   sched_need_resched |    |     rescheduling     | -+
+  |                      +--> |                      |
+  |                           +----------------------+
+  |                             | irq_entry
+  |                             v
+  |                           +----------------------+
+  |                           |                      | ---+
+  |                      ---> |                      |    | sched_need_resched
+  |                           |      preempt_irq     |    | irq_entry
+  |                           |                      | <--+
+  |                           |                      | <--+
+  |                           +----------------------+    |
+  |                             | schedule_entry          | sched_need_resched
+  |                             | schedule_entry_preempt  |
+  |                             v                         |
+  |                           +-----------------------+   |
+  +-------------------------- |    nested_preempt     | --+
+                              +-----------------------+
+                                ^ irq_entry         |
+                                +-------------------+
+
+Due to how the ``need_resched`` flag on the preemption count works on arm64,
+this monitor is unstable on that architecture, as it often records preemption
+when the flag is not set, even in presence of the workaround above.
+For the time being, the monitor is disabled by default on arm64.
+
+Monitor sssw
+------------
+
+The set state sleep and wakeup (sssw) monitor ensures ``set_state`` to
+sleepable leads to sleeping and sleeping tasks require wakeup. It includes the
+following types of switch:
+
+* ``switch_suspend``:
+  a task puts itself to sleep, this can happen only after explicitly setting
+  the task to ``sleepable``. After a task is suspended, it needs to be woken up
+  (``waking`` state) before being switched in again.
+  Setting the task's state to ``sleepable`` can be reverted before switching if it
+  is woken up or set to ``runnable``.
+* ``switch_blocking``:
+  a special case of a ``switch_suspend`` where the task is waiting on a
+  sleeping RT lock (``PREEMPT_RT`` only), it is common to see wakeup and set
+  state events racing with each other and this leads the model to perceive this
+  type of switch when the task is not set to sleepable. This is a limitation of
+  the model in SMP system and workarounds may slow down the system.
+* ``switch_preempt``:
+  a task switch as a result of kernel preemption (``schedule_entry_preempt`` in
+  the nrp model).
+* ``switch_yield``:
+  a task explicitly calls the scheduler or is preempted while returning to
+  userspace. It can happen after a ``yield`` system call, from the idle task or
+  if the ``need_resched`` flag is set. By definition, a task cannot yield while
+  ``sleepable`` as that would be a suspension. A special case of a yield occurs
+  when a task in ``TASK_INTERRUPTIBLE`` calls the scheduler while a signal is
+  pending. The task doesn't go through the usual blocking/waking and is set
+  back to runnable, the resulting switch (if there) looks like a yield to the
+  ``signal_wakeup`` state and is followed by the signal delivery. From this
+  state, the monitor expects a signal even if it sees a wakeup event, although
+  not necessary, to rule out false negatives.
+
+This monitor doesn't include a running state, ``sleepable`` and ``runnable``
+are only referring to the task's desired state, which could be scheduled out
+(e.g. due to preemption). However, it does include the event
+``sched_switch_in`` to represent when a task is allowed to become running. This
+can be triggered also by preemption, but cannot occur after the task got to
+``sleeping`` before a ``wakeup`` occurs::
+
+   +--------------------------------------------------------------------------+
+   |                                                                          |
+   |                                                                          |
+   | switch_suspend           |                                               |
+   | switch_blocking          |                                               |
+   v                          v                                               |
+ +----------+              #==========================#   set_state_runnable  |
+ |          |              H                          H   wakeup              |
+ |          |              H                          H   switch_in           |
+ |          |              H                          H   switch_yield        |
+ | sleeping |              H                          H   switch_preempt      |
+ |          |              H                          H   signal_deliver      |
+ |          |  switch_     H                          H ------+               |
+ |          |  _blocking   H         runnable         H       |               |
+ |          | <----------- H                          H <-----+               |
+ +----------+              H                          H                       |
+   |   wakeup              H                          H                       |
+   +---------------------> H                          H                       |
+                           H                          H                       |
+               +---------> H                          H                       |
+               |           #==========================#                       |
+               |             |                ^                               |
+               |             |                | set_state_runnable            |
+               |             |                | wakeup                        |
+               |    set_state_sleepable       |      +------------------------+
+               |             v                |      |
+               |           +--------------------------+  set_state_sleepable
+               |           |                          |  switch_in
+               |           |                          |  switch_preempt
+   signal_deliver          |        sleepable         |  signal_deliver
+               |           |                          | ------+
+               |           |                          |       |
+               |           |                          | <-----+
+               |           +--------------------------+
+               |             |                ^
+               |        switch_yield          | set_state_sleepable
+               |             v                |
+               |           +---------------+  |
+               +---------- | signal_wakeup | -+
+                           +---------------+
+                             ^           | switch_in
+                             |           | switch_preempt
+                             |           | switch_yield
+                             +-----------+ wakeup
+
 References
 ----------
 
kernel/trace/rv/Kconfig +2 -0
index b688b24081c8..59d0db898d4a 100644
@@ -55,6 +55,8 @@ source "kernel/trace/rv/monitors/snroc/Kconfig"
 source "kernel/trace/rv/monitors/scpd/Kconfig"
 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"
 # Add new sched monitors here
 
 source "kernel/trace/rv/monitors/rtapp/Kconfig"
kernel/trace/rv/Makefile +2 -0
index 1939d3d7621c..2afac88539d3 100644
@@ -14,6 +14,8 @@ obj-$(CONFIG_RV_MON_RTAPP) += monitors/rtapp/rtapp.o
 obj-$(CONFIG_RV_MON_PAGEFAULT) += monitors/pagefault/pagefault.o
 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
 # Add new monitors here
 obj-$(CONFIG_RV_REACTORS) += rv_reactors.o
 obj-$(CONFIG_RV_REACT_PRINTK) += reactor_printk.o
kernel/trace/rv/monitors/nrp/Kconfig new file +16 -0
new file mode 100644
index 000000000000..f5ec08f65535
@@ -0,0 +1,16 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+config RV_MON_NRP
+	depends on RV
+	depends on RV_MON_SCHED
+	default y if !ARM64
+	select DA_MON_EVENTS_ID
+	bool "nrp monitor"
+	help
+	  Monitor to ensure preemption requires need resched.
+	  This monitor is part of the sched monitors collection.
+
+	  This monitor is unstable on arm64, say N unless you are testing it.
+
+	  For further information, see:
+	    Documentation/trace/rv/monitor_sched.rst
kernel/trace/rv/monitors/nrp/nrp.c new file +138 -0

138 lines not on this page · raw message

kernel/trace/rv/monitors/nrp/nrp.h new file +75 -0

75 lines not on this page · raw message

kernel/trace/rv/monitors/nrp/nrp_trace.h new file +15 -0
new file mode 100644
index 000000000000..2e13497de3b6
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Snippet to be included in rv_trace.h
+ */
+
+#ifdef CONFIG_RV_MON_NRP
+DEFINE_EVENT(event_da_monitor_id, event_nrp,
+	     TP_PROTO(int id, char *state, char *event, char *next_state, bool final_state),
+	     TP_ARGS(id, state, event, next_state, final_state));
+
+DEFINE_EVENT(error_da_monitor_id, error_nrp,
+	     TP_PROTO(int id, char *state, char *event),
+	     TP_ARGS(id, state, event));
+#endif /* CONFIG_RV_MON_NRP */
kernel/trace/rv/monitors/sched/Kconfig +1 -0
index ae3eb410abd7..aa16456da864 100644
@@ -2,6 +2,7 @@
 #
 config RV_MON_SCHED
 	depends on RV
+	depends on RV_PER_TASK_MONITORS >= 3
 	bool "sched monitor"
 	help
 	  Collection of monitors to check the scheduler behaves according to specifications.
kernel/trace/rv/monitors/sssw/Kconfig new file +15 -0
new file mode 100644
index 000000000000..23b7eeb38bbf
@@ -0,0 +1,15 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+config RV_MON_SSSW
+	depends on RV
+	depends on RV_MON_SCHED
+	default y
+	select DA_MON_EVENTS_ID
+	bool "sssw monitor"
+	help
+	  Monitor to ensure sched_set_state to sleepable leads to sleeping and
+	  sleeping tasks require wakeup.
+	  This monitor is part of the sched monitors collection.
+
+	  For further information, see:
+	    Documentation/trace/rv/monitor_sched.rst
kernel/trace/rv/monitors/sssw/sssw.c new file +116 -0

116 lines not on this page · raw message

kernel/trace/rv/monitors/sssw/sssw.h new file +105 -0

105 lines not on this page · raw message

kernel/trace/rv/monitors/sssw/sssw_trace.h new file +15 -0
new file mode 100644
index 000000000000..6c03cfc6960b
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Snippet to be included in rv_trace.h
+ */
+
+#ifdef CONFIG_RV_MON_SSSW
+DEFINE_EVENT(event_da_monitor_id, event_sssw,
+	     TP_PROTO(int id, char *state, char *event, char *next_state, bool final_state),
+	     TP_ARGS(id, state, event, next_state, final_state));
+
+DEFINE_EVENT(error_da_monitor_id, error_sssw,
+	     TP_PROTO(int id, char *state, char *event),
+	     TP_ARGS(id, state, event));
+#endif /* CONFIG_RV_MON_SSSW */
kernel/trace/rv/rv_trace.h +2 -0
index 97b2f7e07f27..e4e78d23b7b0 100644
@@ -123,6 +123,8 @@ DECLARE_EVENT_CLASS(error_da_monitor_id,
 
 #include <monitors/wwnr/wwnr_trace.h>
 #include <monitors/snroc/snroc_trace.h>
+#include <monitors/nrp/nrp_trace.h>
+#include <monitors/sssw/sssw_trace.h>
 // Add new monitors based on CONFIG_DA_MON_EVENTS_ID here
 
 #endif /* CONFIG_DA_MON_EVENTS_ID */
tools/verification/models/sched/nrp.dot new file +29 -0
new file mode 100644
index 000000000000..77bb64669416
@@ -0,0 +1,29 @@
+digraph state_automaton {
+	center = true;
+	size = "7,11";
+	{node [shape = doublecircle] "any_thread_running"};
+	{node [shape = circle] "any_thread_running"};
+	{node [shape = circle] "nested_preempt"};
+	{node [shape = plaintext, style=invis, label=""] "__init_preempt_irq"};
+	{node [shape = circle] "preempt_irq"};
+	{node [shape = circle] "rescheduling"};
+	"__init_preempt_irq" -> "preempt_irq";
+	"any_thread_running" [label = "any_thread_running", color = green3];
+	"any_thread_running" -> "any_thread_running" [ label = "schedule_entry\nirq_entry" ];
+	"any_thread_running" -> "rescheduling" [ label = "sched_need_resched" ];
+	"nested_preempt" [label = "nested_preempt"];
+	"nested_preempt" -> "any_thread_running" [ label = "schedule_entry_preempt\nschedule_entry" ];
+	"nested_preempt" -> "nested_preempt" [ label = "irq_entry" ];
+	"nested_preempt" -> "preempt_irq" [ label = "sched_need_resched" ];
+	"preempt_irq" [label = "preempt_irq"];
+	"preempt_irq" -> "nested_preempt" [ label = "schedule_entry_preempt\nschedule_entry" ];
+	"preempt_irq" -> "preempt_irq" [ label = "irq_entry\nsched_need_resched" ];
+	"rescheduling" [label = "rescheduling"];
+	"rescheduling" -> "any_thread_running" [ label = "schedule_entry_preempt\nschedule_entry" ];
+	"rescheduling" -> "preempt_irq" [ label = "irq_entry" ];
+	"rescheduling" -> "rescheduling" [ label = "sched_need_resched" ];
+	{ rank = min ;
+		"__init_preempt_irq";
+		"preempt_irq";
+	}
+}
tools/verification/models/sched/sssw.dot new file +30 -0
new file mode 100644
index 000000000000..4994c3e876be
@@ -0,0 +1,30 @@
+digraph state_automaton {
+	center = true;
+	size = "7,11";
+	{node [shape = plaintext, style=invis, label=""] "__init_runnable"};
+	{node [shape = doublecircle] "runnable"};
+	{node [shape = circle] "runnable"};
+	{node [shape = circle] "signal_wakeup"};
+	{node [shape = circle] "sleepable"};
+	{node [shape = circle] "sleeping"};
+	"__init_runnable" -> "runnable";
+	"runnable" [label = "runnable", color = green3];
+	"runnable" -> "runnable" [ label = "sched_set_state_runnable\nsched_wakeup\nsched_switch_in\nsched_switch_yield\nsched_switch_preempt\nsignal_deliver" ];
+	"runnable" -> "sleepable" [ label = "sched_set_state_sleepable" ];
+	"runnable" -> "sleeping" [ label = "sched_switch_blocking" ];
+	"signal_wakeup" [label = "signal_wakeup"];
+	"signal_wakeup" -> "runnable" [ label = "signal_deliver" ];
+	"signal_wakeup" -> "signal_wakeup" [ label = "sched_switch_in\nsched_switch_preempt\nsched_switch_yield\nsched_wakeup" ];
+	"signal_wakeup" -> "sleepable" [ label = "sched_set_state_sleepable" ];
+	"sleepable" [label = "sleepable"];
+	"sleepable" -> "runnable" [ label = "sched_set_state_runnable\nsched_wakeup" ];
+	"sleepable" -> "signal_wakeup" [ label = "sched_switch_yield" ];
+	"sleepable" -> "sleepable" [ label = "sched_set_state_sleepable\nsched_switch_in\nsched_switch_preempt\nsignal_deliver" ];
+	"sleepable" -> "sleeping" [ label = "sched_switch_suspend\nsched_switch_blocking" ];
+	"sleeping" [label = "sleeping"];
+	"sleeping" -> "runnable" [ label = "sched_wakeup" ];
+	{ rank = min ;
+		"__init_runnable";
+		"runnable";
+	}
+}
Signature · 1 line
2.47.2
#11 lore raw

PATCH 11/11 Add opid per-cpu monitor

In reply to Steven Rostedt

From: Gabriele Monaco <[email protected]>

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.

---
 Documentation/trace/rv/monitor_sched.rst   |  55 +++++++
 kernel/trace/rv/Kconfig                    |   1 +
 kernel/trace/rv/Makefile                   |   1 +
 kernel/trace/rv/monitors/opid/Kconfig      |  19 +++
 kernel/trace/rv/monitors/opid/opid.c       | 168 +++++++++++++++++++++
 kernel/trace/rv/monitors/opid/opid.h       | 104 +++++++++++++
 kernel/trace/rv/monitors/opid/opid_trace.h |  15 ++
 kernel/trace/rv/rv_trace.h                 |   1 +
 tools/verification/models/sched/opid.dot   |  35 +++++
 9 files changed, 399 insertions(+)
 create mode 100644 kernel/trace/rv/monitors/opid/Kconfig
 create mode 100644 kernel/trace/rv/monitors/opid/opid.c
 create mode 100644 kernel/trace/rv/monitors/opid/opid.h
 create mode 100644 kernel/trace/rv/monitors/opid/opid_trace.h
 create mode 100644 tools/verification/models/sched/opid.dot
Documentation/trace/rv/monitor_sched.rst +55 -0
index 11ef963cb578..3f8381ad9ec7 100644
@@ -341,6 +341,61 @@ can be triggered also by preemption, but cannot occur after the task got to
                              |           | switch_yield
                              +-----------+ wakeup
 
+Monitor opid
+------------
+
+The operations with preemption and irq disabled (opid) monitor ensures
+operations like ``wakeup`` and ``need_resched`` occur with interrupts and
+preemption disabled or during interrupt context, in such case preemption may
+not be disabled explicitly.
+``need_resched`` can be set by some RCU internals functions, in which case it
+doesn't match a task wakeup and might occur with only interrupts disabled::
+
+                 |                     sched_need_resched
+                 |                     sched_waking
+                 |                     irq_entry
+                 |                   +--------------------+
+                 v                   v                    |
+               +------------------------------------------------------+
+  +----------- |                     disabled                         | <+
+  |            +------------------------------------------------------+  |
+  |              |                 ^                                     |
+  |              |          preempt_disable      sched_need_resched      |
+  |       preempt_enable           |           +--------------------+    |
+  |              v                 |           v                    |    |
+  |            +------------------------------------------------------+  |
+  |            |                   irq_disabled                       |  |
+  |            +------------------------------------------------------+  |
+  |                              |             |        ^                |
+  |     irq_entry            irq_entry         |        |                |
+  |     sched_need_resched       v             |   irq_disable           |
+  |     sched_waking +--------------+          |        |                |
+  |           +----- |              |     irq_enable    |                |
+  |           |      |    in_irq    |          |        |                |
+  |           +----> |              |          |        |                |
+  |                  +--------------+          |        |          irq_disable
+  |                     |                      |        |                |
+  | irq_enable          | irq_enable           |        |                |
+  |                     v                      v        |                |
+  |            #======================================================#  |
+  |            H                     enabled                          H  |
+  |            #======================================================#  |
+  |              |                   ^         ^ preempt_enable     |    |
+  |       preempt_disable     preempt_enable   +--------------------+    |
+  |              v                   |                                   |
+  |            +------------------+  |                                   |
+  +----------> | preempt_disabled | -+                                   |
+               +------------------+                                      |
+                 |                                                       |
+                 +-------------------------------------------------------+
+
+This monitor is designed to work on ``PREEMPT_RT`` kernels, the special case of
+events occurring in interrupt context is a shortcut to identify valid scenarios
+where the preemption tracepoints might not be visible, during interrupts
+preemption is always disabled. On non- ``PREEMPT_RT`` kernels, the interrupts
+might invoke a softirq to set ``need_resched`` and wake up a task. This is
+another special case that is currently not supported by the monitor.
+
 References
 ----------
 
kernel/trace/rv/Kconfig +1 -0
index 59d0db898d4a..5b4be87ba59d 100644
@@ -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"
kernel/trace/rv/Makefile +1 -0
index 2afac88539d3..750e4ad6fa0f 100644
@@ -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
kernel/trace/rv/monitors/opid/Kconfig new file +19 -0
new file mode 100644
index 000000000000..561d32da572b
@@ -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
kernel/trace/rv/monitors/opid/opid.c new file +168 -0

168 lines not on this page · raw message

kernel/trace/rv/monitors/opid/opid.h new file +104 -0

104 lines not on this page · raw message

kernel/trace/rv/monitors/opid/opid_trace.h new file +15 -0
new file mode 100644
index 000000000000..3df6ff955c30
@@ -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 */
kernel/trace/rv/rv_trace.h +1 -0
index e4e78d23b7b0..4a6faddac614 100644
@@ -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 */
tools/verification/models/sched/opid.dot new file +35 -0
new file mode 100644
index 000000000000..840052f6952b
@@ -0,0 +1,35 @@
+digraph state_automaton {
+	center = true;
+	size = "7,11";
+	{node [shape = plaintext, style=invis, label=""] "__init_disabled"};
+	{node [shape = circle] "disabled"};
+	{node [shape = doublecircle] "enabled"};
+	{node [shape = circle] "enabled"};
+	{node [shape = circle] "in_irq"};
+	{node [shape = circle] "irq_disabled"};
+	{node [shape = circle] "preempt_disabled"};
+	"__init_disabled" -> "disabled";
+	"disabled" [label = "disabled"];
+	"disabled" -> "disabled" [ label = "sched_need_resched\nsched_waking\nirq_entry" ];
+	"disabled" -> "irq_disabled" [ label = "preempt_enable" ];
+	"disabled" -> "preempt_disabled" [ label = "irq_enable" ];
+	"enabled" [label = "enabled", color = green3];
+	"enabled" -> "enabled" [ label = "preempt_enable" ];
+	"enabled" -> "irq_disabled" [ label = "irq_disable" ];
+	"enabled" -> "preempt_disabled" [ label = "preempt_disable" ];
+	"in_irq" [label = "in_irq"];
+	"in_irq" -> "enabled" [ label = "irq_enable" ];
+	"in_irq" -> "in_irq" [ label = "sched_need_resched\nsched_waking\nirq_entry" ];
+	"irq_disabled" [label = "irq_disabled"];
+	"irq_disabled" -> "disabled" [ label = "preempt_disable" ];
+	"irq_disabled" -> "enabled" [ label = "irq_enable" ];
+	"irq_disabled" -> "in_irq" [ label = "irq_entry" ];
+	"irq_disabled" -> "irq_disabled" [ label = "sched_need_resched" ];
+	"preempt_disabled" [label = "preempt_disabled"];
+	"preempt_disabled" -> "disabled" [ label = "irq_disable" ];
+	"preempt_disabled" -> "enabled" [ label = "preempt_enable" ];
+	{ rank = min ;
+		"__init_disabled";
+		"disabled";
+	}
+}
Signature · 1 line
2.47.2