* [PATCH v3 09/13] sched: Add deadline tracepoints
From: Gabriele Monaco @ 2025-12-05 13:16 UTC (permalink / raw)
To: linux-kernel, Steven Rostedt, Nam Cao, Masami Hiramatsu,
Ingo Molnar, Peter Zijlstra, linux-trace-kernel
Cc: Gabriele Monaco, Tomas Glozar, Juri Lelli, Clark Williams,
John Kacur
In-Reply-To: <20251205131621.135513-1-gmonaco@redhat.com>
Add the following tracepoints:
* sched_dl_throttle(dl_se, cpu):
Called when a deadline entity is throttled
* sched_dl_replenish(dl_se, cpu):
Called when a deadline entity's runtime is replenished
* sched_dl_server_start(dl_se, cpu):
Called when a deadline server is started
* sched_dl_server_stop(dl_se, cpu):
Called when a deadline server is stopped
Those tracepoints can be useful to validate the deadline scheduler with
RV and are not exported to tracefs.
Signed-off-by: Gabriele Monaco <gmonaco@redhat.com>
---
Notes:
V3:
* Rename dl argument to dl_se in tracepoints
include/trace/events/sched.h | 16 ++++++++++++++++
kernel/sched/core.c | 4 ++++
kernel/sched/deadline.c | 7 +++++++
3 files changed, 27 insertions(+)
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 7b2645b50e78..366b2e8ec40c 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -896,6 +896,22 @@ DECLARE_TRACE(sched_set_need_resched,
TP_PROTO(struct task_struct *tsk, int cpu, int tif),
TP_ARGS(tsk, cpu, tif));
+DECLARE_TRACE(sched_dl_throttle,
+ TP_PROTO(struct sched_dl_entity *dl_se, int cpu),
+ TP_ARGS(dl_se, cpu));
+
+DECLARE_TRACE(sched_dl_replenish,
+ TP_PROTO(struct sched_dl_entity *dl_se, int cpu),
+ TP_ARGS(dl_se, cpu));
+
+DECLARE_TRACE(sched_dl_server_start,
+ TP_PROTO(struct sched_dl_entity *dl_se, int cpu),
+ TP_ARGS(dl_se, cpu));
+
+DECLARE_TRACE(sched_dl_server_stop,
+ TP_PROTO(struct sched_dl_entity *dl_se, int cpu),
+ TP_ARGS(dl_se, cpu));
+
#endif /* _TRACE_SCHED_H */
/* This part must be outside protection */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5516778c19eb..3aed0ed6f2e9 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -122,6 +122,10 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(sched_compute_energy_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_entry_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_exit_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_set_need_resched_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(sched_dl_throttle_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(sched_dl_replenish_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(sched_dl_server_start_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(sched_dl_server_stop_tp);
DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
DEFINE_PER_CPU(struct rnd_state, sched_rnd_state);
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 319439fe1870..2192e9f42e02 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -733,6 +733,7 @@ static inline void replenish_dl_new_period(struct sched_dl_entity *dl_se,
dl_se->dl_throttled = 1;
dl_se->dl_defer_armed = 1;
}
+ trace_sched_dl_replenish_tp(dl_se, cpu_of(rq));
}
/*
@@ -850,6 +851,8 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se)
if (dl_se->dl_throttled)
dl_se->dl_throttled = 0;
+ trace_sched_dl_replenish_tp(dl_se, cpu_of(rq));
+
/*
* If this is the replenishment of a deferred reservation,
* clear the flag and return.
@@ -1341,6 +1344,7 @@ static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se)
dl_time_before(rq_clock(rq), dl_next_period(dl_se))) {
if (unlikely(is_dl_boosted(dl_se) || !start_dl_timer(dl_se)))
return;
+ trace_sched_dl_throttle_tp(dl_se, cpu_of(rq));
dl_se->dl_throttled = 1;
if (dl_se->runtime > 0)
dl_se->runtime = 0;
@@ -1504,6 +1508,7 @@ static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64
throttle:
if (dl_runtime_exceeded(dl_se) || dl_se->dl_yielded) {
+ trace_sched_dl_throttle_tp(dl_se, cpu_of(rq));
dl_se->dl_throttled = 1;
/* If requested, inform the user about runtime overruns. */
@@ -1795,6 +1800,7 @@ void dl_server_start(struct sched_dl_entity *dl_se)
if (WARN_ON_ONCE(!cpu_online(cpu_of(rq))))
return;
+ trace_sched_dl_server_start_tp(dl_se, cpu_of(rq));
dl_se->dl_server_active = 1;
enqueue_dl_entity(dl_se, ENQUEUE_WAKEUP);
if (!dl_task(dl_se->rq->curr) || dl_entity_preempt(dl_se, &rq->curr->dl))
@@ -1806,6 +1812,7 @@ void dl_server_stop(struct sched_dl_entity *dl_se)
if (!dl_server(dl_se) || !dl_server_active(dl_se))
return;
+ trace_sched_dl_server_stop_tp(dl_se, cpu_of(dl_se->rq));
dequeue_dl_entity(dl_se, DEQUEUE_SLEEP);
hrtimer_try_to_cancel(&dl_se->dl_timer);
dl_se->dl_defer_armed = 0;
--
2.52.0
^ permalink raw reply related
* [PATCH v3 08/13] sched: Export hidden tracepoints to modules
From: Gabriele Monaco @ 2025-12-05 13:16 UTC (permalink / raw)
To: linux-kernel, Steven Rostedt, Nam Cao, Ingo Molnar,
Peter Zijlstra
Cc: Gabriele Monaco, Tomas Glozar, Juri Lelli, Clark Williams,
John Kacur, linux-trace-kernel
In-Reply-To: <20251205131621.135513-1-gmonaco@redhat.com>
The tracepoints sched_entry, sched_exit and sched_set_need_resched
are not exported to tracefs as trace events, this allows only kernel
code to access them. Helper modules like [1] can be used to still have
the tracepoints available to ftrace for debugging purposes, but they do
rely on the tracepoints being exported.
Export the 3 not exported tracepoints.
Note that sched_set_state is already exported as the macro is called
from modules.
[1] - https://github.com/qais-yousef/sched_tp.git
Signed-off-by: Gabriele Monaco <gmonaco@redhat.com>
---
kernel/sched/core.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 41ba0be16911..5516778c19eb 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -119,6 +119,9 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_cfs_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_se_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp);
EXPORT_TRACEPOINT_SYMBOL_GPL(sched_compute_energy_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(sched_entry_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(sched_exit_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(sched_set_need_resched_tp);
DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
DEFINE_PER_CPU(struct rnd_state, sched_rnd_state);
--
2.52.0
^ permalink raw reply related
* [PATCH v3 07/13] rv: Convert the opid monitor to a hybrid automaton
From: Gabriele Monaco @ 2025-12-05 13:16 UTC (permalink / raw)
To: linux-kernel, Steven Rostedt, Nam Cao, Gabriele Monaco,
Jonathan Corbet, Masami Hiramatsu, linux-trace-kernel, linux-doc
Cc: Tomas Glozar, Juri Lelli, Clark Williams, John Kacur
In-Reply-To: <20251205131621.135513-1-gmonaco@redhat.com>
The opid monitor validates that wakeup and need_resched events only
occur with interrupts and preemption disabled by following the
preemptirq tracepoints.
As reported in [1], those tracepoints might be inaccurate in some
situations (e.g. NMIs).
Since the monitor doesn't validate other ordering properties, remove the
dependency on preemptirq tracepoints and convert the monitor to a hybrid
automaton to validate the constraint during event handling.
This makes the monitor more robust by also removing the workaround for
interrupts missing the preemption tracepoints, which was working on
PREEMPT_RT only and allows the monitor to be built on kernels without
the preemptirqs tracepoints.
[1] - https://lore.kernel.org/lkml/20250625120823.60600-1-gmonaco@redhat.com
Signed-off-by: Gabriele Monaco <gmonaco@redhat.com>
---
Documentation/trace/rv/monitor_sched.rst | 62 +++---------
kernel/trace/rv/monitors/opid/Kconfig | 11 +-
kernel/trace/rv/monitors/opid/opid.c | 111 +++++++--------------
kernel/trace/rv/monitors/opid/opid.h | 86 ++++------------
kernel/trace/rv/monitors/opid/opid_trace.h | 4 +
kernel/trace/rv/rv_trace.h | 2 +-
tools/verification/models/sched/opid.dot | 36 ++-----
7 files changed, 82 insertions(+), 230 deletions(-)
diff --git a/Documentation/trace/rv/monitor_sched.rst b/Documentation/trace/rv/monitor_sched.rst
index 3f8381ad9ec7..0b96d6e147c6 100644
--- a/Documentation/trace/rv/monitor_sched.rst
+++ b/Documentation/trace/rv/monitor_sched.rst
@@ -346,55 +346,21 @@ 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.
+preemption disabled.
``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.
+doesn't match a task wakeup and might occur with only interrupts disabled.
+The interrupt and preemption status are validated by the hybrid automaton
+constraints when processing the events::
+
+ |
+ |
+ v
+ #=========# sched_need_resched;irq_off == 1
+ H H sched_waking;irq_off == 1 && preempt_off == 1
+ H any H ------------------------------------------------+
+ H H |
+ H H <-----------------------------------------------+
+ #=========#
References
----------
diff --git a/kernel/trace/rv/monitors/opid/Kconfig b/kernel/trace/rv/monitors/opid/Kconfig
index 561d32da572b..6d02e239b684 100644
--- a/kernel/trace/rv/monitors/opid/Kconfig
+++ b/kernel/trace/rv/monitors/opid/Kconfig
@@ -2,18 +2,13 @@
#
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
+ default y
+ select HA_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.
+ interrupts and preemption disabled.
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
index 25a40e90fa40..160a518ce1cb 100644
--- a/kernel/trace/rv/monitors/opid/opid.c
+++ b/kernel/trace/rv/monitors/opid/opid.c
@@ -10,94 +10,63 @@
#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>
#define RV_MON_TYPE RV_MON_PER_CPU
#include "opid.h"
-#include <rv/da_monitor.h>
+#include <rv/ha_monitor.h>
-#ifdef CONFIG_X86_LOCAL_APIC
-#include <asm/trace/irq_vectors.h>
-
-static void handle_vector_irq_entry(void *data, int vector)
+static u64 ha_get_env(struct ha_monitor *ha_mon, enum envs_opid env, u64 time_ns)
{
- da_handle_event(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);
+ if (env == irq_off_opid)
+ return irqs_disabled();
+ else if (env == preempt_off_opid) {
+ /*
+ * If CONFIG_PREEMPTION is enabled, then the tracepoint itself disables
+ * preemption (adding one to the preempt_count). Since we are
+ * interested in the preempt_count at the time the tracepoint was
+ * hit, we consider 1 as still enabled.
+ */
+ if (IS_ENABLED(CONFIG_PREEMPTION))
+ return (preempt_count() & PREEMPT_MASK) > 1;
+ return true;
}
+ return ENV_INVALID_VALUE;
}
-static void detach_vector_irq(void)
+static inline bool ha_verify_guards(struct ha_monitor *ha_mon,
+ enum states curr_state, enum events event,
+ enum states next_state, u64 time_ns)
{
- 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);
- }
+ bool res = true;
+
+ if (curr_state == any_opid && event == sched_need_resched_opid)
+ res = ha_get_env(ha_mon, irq_off_opid, time_ns) == 1ull;
+ else if (curr_state == any_opid && event == sched_waking_opid)
+ res = ha_get_env(ha_mon, irq_off_opid, time_ns) == 1ull &&
+ ha_get_env(ha_mon, preempt_off_opid, time_ns) == 1ull;
+ return res;
}
-#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)
+static bool ha_verify_constraint(struct ha_monitor *ha_mon,
+ enum states curr_state, enum events event,
+ enum states next_state, u64 time_ns)
{
- da_handle_event(irq_disable_opid);
-}
+ if (!ha_verify_guards(ha_mon, curr_state, event, next_state, time_ns))
+ return false;
-static void handle_irq_enable(void *data, unsigned long ip, unsigned long parent_ip)
-{
- da_handle_event(irq_enable_opid);
-}
-
-static void handle_irq_entry(void *data, int irq, struct irqaction *action)
-{
- da_handle_event(irq_entry_opid);
-}
-
-static void handle_preempt_disable(void *data, unsigned long ip, unsigned long parent_ip)
-{
- da_handle_event(preempt_disable_opid);
-}
-
-static void handle_preempt_enable(void *data, unsigned long ip, unsigned long parent_ip)
-{
- da_handle_event(preempt_enable_opid);
+ return true;
}
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(sched_need_resched_opid);
- else
- da_handle_start_event(sched_need_resched_opid);
+ da_handle_start_event(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(sched_waking_opid);
- else
- da_handle_start_event(sched_waking_opid);
+ da_handle_start_event(sched_waking_opid);
}
static int enable_opid(void)
@@ -108,14 +77,8 @@ static int enable_opid(void)
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;
}
@@ -124,14 +87,8 @@ static void disable_opid(void)
{
rv_this.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();
}
diff --git a/kernel/trace/rv/monitors/opid/opid.h b/kernel/trace/rv/monitors/opid/opid.h
index 092992514970..fb0aa4c28aa6 100644
--- a/kernel/trace/rv/monitors/opid/opid.h
+++ b/kernel/trace/rv/monitors/opid/opid.h
@@ -8,30 +8,31 @@
#define MONITOR_NAME opid
enum states_opid {
- disabled_opid,
- enabled_opid,
- in_irq_opid,
- irq_disabled_opid,
- preempt_disabled_opid,
+ any_opid,
state_max_opid,
};
#define INVALID_STATE state_max_opid
enum events_opid {
- irq_disable_opid,
- irq_enable_opid,
- irq_entry_opid,
- preempt_disable_opid,
- preempt_enable_opid,
sched_need_resched_opid,
sched_waking_opid,
event_max_opid,
};
+enum envs_opid {
+ irq_off_opid,
+ preempt_off_opid,
+ env_max_opid,
+ env_max_stored_opid = irq_off_opid,
+};
+
+_Static_assert(env_max_stored_opid <= MAX_HA_ENV_LEN, "Not enough slots");
+
struct automaton_opid {
char *state_names[state_max_opid];
char *event_names[event_max_opid];
+ char *env_names[env_max_opid];
unsigned char function[state_max_opid][event_max_opid];
unsigned char initial_state;
bool final_states[state_max_opid];
@@ -39,68 +40,19 @@ struct automaton_opid {
static const struct automaton_opid automaton_opid = {
.state_names = {
- "disabled",
- "enabled",
- "in_irq",
- "irq_disabled",
- "preempt_disabled",
+ "any",
},
.event_names = {
- "irq_disable",
- "irq_enable",
- "irq_entry",
- "preempt_disable",
- "preempt_enable",
"sched_need_resched",
"sched_waking",
},
+ .env_names = {
+ "irq_off",
+ "preempt_off",
+ },
.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,
- },
+ { any_opid, any_opid },
},
- .initial_state = disabled_opid,
- .final_states = { 0, 1, 0, 0, 0 },
+ .initial_state = any_opid,
+ .final_states = { 1 },
};
diff --git a/kernel/trace/rv/monitors/opid/opid_trace.h b/kernel/trace/rv/monitors/opid/opid_trace.h
index 3df6ff955c30..b04005b64208 100644
--- a/kernel/trace/rv/monitors/opid/opid_trace.h
+++ b/kernel/trace/rv/monitors/opid/opid_trace.h
@@ -12,4 +12,8 @@ DEFINE_EVENT(event_da_monitor, event_opid,
DEFINE_EVENT(error_da_monitor, error_opid,
TP_PROTO(char *state, char *event),
TP_ARGS(state, event));
+
+DEFINE_EVENT(error_env_da_monitor, error_env_opid,
+ TP_PROTO(char *state, char *event, char *env),
+ TP_ARGS(state, event, env));
#endif /* CONFIG_RV_MON_OPID */
diff --git a/kernel/trace/rv/rv_trace.h b/kernel/trace/rv/rv_trace.h
index 1661f8fe4a88..9e8072d863a2 100644
--- a/kernel/trace/rv/rv_trace.h
+++ b/kernel/trace/rv/rv_trace.h
@@ -62,7 +62,6 @@ 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
#ifdef CONFIG_HA_MON_EVENTS_IMPLICIT
@@ -91,6 +90,7 @@ DECLARE_EVENT_CLASS(error_env_da_monitor,
__get_str(env))
);
+#include <monitors/opid/opid_trace.h>
// Add new monitors based on CONFIG_HA_MON_EVENTS_IMPLICIT here
#endif
diff --git a/tools/verification/models/sched/opid.dot b/tools/verification/models/sched/opid.dot
index 840052f6952b..511051fce430 100644
--- a/tools/verification/models/sched/opid.dot
+++ b/tools/verification/models/sched/opid.dot
@@ -1,35 +1,13 @@
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" ];
+ {node [shape = plaintext, style=invis, label=""] "__init_any"};
+ {node [shape = doublecircle] "any"};
+ "__init_any" -> "any";
+ "any" [label = "any", color = green3];
+ "any" -> "any" [ label = "sched_need_resched;irq_off == 1\nsched_waking;irq_off == 1 && preempt_off == 1" ];
{ rank = min ;
- "__init_disabled";
- "disabled";
+ "__init_any";
+ "any";
}
}
--
2.52.0
^ permalink raw reply related
* [PATCH v3 06/13] rv: Add sample hybrid monitors stall
From: Gabriele Monaco @ 2025-12-05 13:16 UTC (permalink / raw)
To: linux-kernel, Steven Rostedt, Nam Cao, Jonathan Corbet,
Gabriele Monaco, Masami Hiramatsu, linux-doc, linux-trace-kernel
Cc: Tomas Glozar, Juri Lelli, Clark Williams, John Kacur
In-Reply-To: <20251205131621.135513-1-gmonaco@redhat.com>
Add a sample monitor to showcase hybrid/timed automata.
The stall monitor identifies tasks stalled for longer than a threshold
and reacts when that happens.
Signed-off-by: Gabriele Monaco <gmonaco@redhat.com>
---
Notes:
V3:
* Extend stall model to handle preemption
Documentation/tools/rv/index.rst | 1 +
Documentation/tools/rv/rv-mon-stall.rst | 44 ++++++
Documentation/trace/rv/index.rst | 1 +
Documentation/trace/rv/monitor_stall.rst | 43 ++++++
kernel/trace/rv/Kconfig | 1 +
kernel/trace/rv/Makefile | 1 +
kernel/trace/rv/monitors/stall/Kconfig | 13 ++
kernel/trace/rv/monitors/stall/stall.c | 150 +++++++++++++++++++
kernel/trace/rv/monitors/stall/stall.h | 81 ++++++++++
kernel/trace/rv/monitors/stall/stall_trace.h | 19 +++
kernel/trace/rv/rv_trace.h | 1 +
tools/verification/models/stall.dot | 22 +++
12 files changed, 377 insertions(+)
create mode 100644 Documentation/tools/rv/rv-mon-stall.rst
create mode 100644 Documentation/trace/rv/monitor_stall.rst
create mode 100644 kernel/trace/rv/monitors/stall/Kconfig
create mode 100644 kernel/trace/rv/monitors/stall/stall.c
create mode 100644 kernel/trace/rv/monitors/stall/stall.h
create mode 100644 kernel/trace/rv/monitors/stall/stall_trace.h
create mode 100644 tools/verification/models/stall.dot
diff --git a/Documentation/tools/rv/index.rst b/Documentation/tools/rv/index.rst
index 64ba2efe2e85..4d66e0a78e1e 100644
--- a/Documentation/tools/rv/index.rst
+++ b/Documentation/tools/rv/index.rst
@@ -16,6 +16,7 @@ Runtime verification (rv) tool
rv-mon-wip
rv-mon-wwnr
rv-mon-sched
+ rv-mon-stall
.. only:: subproject and html
diff --git a/Documentation/tools/rv/rv-mon-stall.rst b/Documentation/tools/rv/rv-mon-stall.rst
new file mode 100644
index 000000000000..c79d7c2e4dd4
--- /dev/null
+++ b/Documentation/tools/rv/rv-mon-stall.rst
@@ -0,0 +1,44 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+============
+rv-mon-stall
+============
+--------------------
+Stalled task monitor
+--------------------
+
+:Manual section: 1
+
+SYNOPSIS
+========
+
+**rv mon stall** [*OPTIONS*]
+
+DESCRIPTION
+===========
+
+The stalled task (**stall**) monitor is a sample per-task timed monitor that
+checks if tasks are scheduled within a defined threshold after they are ready.
+
+See kernel documentation for further information about this monitor:
+<https://docs.kernel.org/trace/rv/monitor_stall.html>
+
+OPTIONS
+=======
+
+.. include:: common_ikm.rst
+
+SEE ALSO
+========
+
+**rv**\(1), **rv-mon**\(1)
+
+Linux kernel *RV* documentation:
+<https://www.kernel.org/doc/html/latest/trace/rv/index.html>
+
+AUTHOR
+======
+
+Written by Gabriele Monaco <gmonaco@redhat.com>
+
+.. include:: common_appendix.rst
diff --git a/Documentation/trace/rv/index.rst b/Documentation/trace/rv/index.rst
index ad298784bda2..bf9962f49959 100644
--- a/Documentation/trace/rv/index.rst
+++ b/Documentation/trace/rv/index.rst
@@ -16,3 +16,4 @@ Runtime Verification
monitor_wwnr.rst
monitor_sched.rst
monitor_rtapp.rst
+ monitor_stall.rst
diff --git a/Documentation/trace/rv/monitor_stall.rst b/Documentation/trace/rv/monitor_stall.rst
new file mode 100644
index 000000000000..d29e820b2433
--- /dev/null
+++ b/Documentation/trace/rv/monitor_stall.rst
@@ -0,0 +1,43 @@
+Monitor stall
+=============
+
+- Name: stall - stalled task monitor
+- Type: per-task hybrid automaton
+- Author: Gabriele Monaco <gmonaco@redhat.com>
+
+Description
+-----------
+
+The stalled task (stall) monitor is a sample per-task timed monitor that checks
+if tasks are scheduled within a defined threshold after they are ready::
+
+ |
+ |
+ v
+ #==========================#
+ +-----------------> H dequeued H
+ | #==========================#
+ | |
+ sched_switch_wait | sched_wakeup;reset(clk)
+ | v
+ | +--------------------------+ <+
+ | | enqueued | | sched_wakeup
+ | | clk < threshold_jiffies | -+
+ | +--------------------------+
+ | | ^
+ | sched_switch_in sched_switch_preempt;reset(clk)
+ | v |
+ | +--------------------------+
+ +------------------ | running |
+ +--------------------------+
+ ^ sched_switch_in |
+ | sched_wakeup |
+ +----------------------+
+
+The threshold can be configured as a parameter by either booting with the
+``stall.threshold_jiffies=<new value>`` argument or writing a new value to
+``/sys/module/stall/parameters/threshold_jiffies``.
+
+Specification
+-------------
+Graphviz Dot file in tools/verification/models/stall.dot
diff --git a/kernel/trace/rv/Kconfig b/kernel/trace/rv/Kconfig
index 4ad392dfc57f..720fbe4935f8 100644
--- a/kernel/trace/rv/Kconfig
+++ b/kernel/trace/rv/Kconfig
@@ -78,6 +78,7 @@ source "kernel/trace/rv/monitors/pagefault/Kconfig"
source "kernel/trace/rv/monitors/sleep/Kconfig"
# Add new rtapp monitors here
+source "kernel/trace/rv/monitors/stall/Kconfig"
# Add new monitors here
config RV_REACTORS
diff --git a/kernel/trace/rv/Makefile b/kernel/trace/rv/Makefile
index 750e4ad6fa0f..51c95e2d2da6 100644
--- a/kernel/trace/rv/Makefile
+++ b/kernel/trace/rv/Makefile
@@ -17,6 +17,7 @@ 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
+obj-$(CONFIG_RV_MON_STALL) += monitors/stall/stall.o
# Add new monitors here
obj-$(CONFIG_RV_REACTORS) += rv_reactors.o
obj-$(CONFIG_RV_REACT_PRINTK) += reactor_printk.o
diff --git a/kernel/trace/rv/monitors/stall/Kconfig b/kernel/trace/rv/monitors/stall/Kconfig
new file mode 100644
index 000000000000..6f846b642544
--- /dev/null
+++ b/kernel/trace/rv/monitors/stall/Kconfig
@@ -0,0 +1,13 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+config RV_MON_STALL
+ depends on RV
+ select HA_MON_EVENTS_ID
+ bool "stall monitor"
+ help
+ Enable the stall sample monitor that illustrates the usage of hybrid
+ automata monitors. It can be used to identify tasks stalled for
+ longer than a threshold.
+
+ For further information, see:
+ Documentation/trace/rv/monitor_stall.rst
diff --git a/kernel/trace/rv/monitors/stall/stall.c b/kernel/trace/rv/monitors/stall/stall.c
new file mode 100644
index 000000000000..9ccfda6b0e73
--- /dev/null
+++ b/kernel/trace/rv/monitors/stall/stall.c
@@ -0,0 +1,150 @@
+// 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 "stall"
+
+#include <trace/events/sched.h>
+#include <rv_trace.h>
+
+#define RV_MON_TYPE RV_MON_PER_TASK
+#define HA_TIMER_TYPE HA_TIMER_WHEEL
+#include "stall.h"
+#include <rv/ha_monitor.h>
+
+static u64 threshold_jiffies = 1000;
+module_param(threshold_jiffies, ullong, 0644);
+
+static u64 ha_get_env(struct ha_monitor *ha_mon, enum envs_stall env, u64 time_ns)
+{
+ if (env == clk_stall)
+ return ha_get_clk_jiffy(ha_mon, env);
+ return ENV_INVALID_VALUE;
+}
+
+static void ha_reset_env(struct ha_monitor *ha_mon, enum envs_stall env, u64 time_ns)
+{
+ if (env == clk_stall)
+ ha_reset_clk_jiffy(ha_mon, env);
+}
+
+static inline bool ha_verify_invariants(struct ha_monitor *ha_mon,
+ enum states curr_state, enum events event,
+ enum states next_state, u64 time_ns)
+{
+ if (curr_state == enqueued_stall)
+ return ha_check_invariant_jiffy(ha_mon, clk_stall, time_ns);
+ return true;
+}
+
+static inline bool ha_verify_guards(struct ha_monitor *ha_mon,
+ enum states curr_state, enum events event,
+ enum states next_state, u64 time_ns)
+{
+ bool res = true;
+
+ if (curr_state == dequeued_stall && event == sched_wakeup_stall)
+ ha_reset_env(ha_mon, clk_stall, time_ns);
+ else if (curr_state == running_stall && event == sched_switch_preempt_stall)
+ ha_reset_env(ha_mon, clk_stall, time_ns);
+ return res;
+}
+
+static inline void ha_setup_invariants(struct ha_monitor *ha_mon,
+ enum states curr_state, enum events event,
+ enum states next_state, u64 time_ns)
+{
+ if (next_state == curr_state)
+ return;
+ if (next_state == enqueued_stall)
+ ha_start_timer_jiffy(ha_mon, clk_stall, threshold_jiffies, time_ns);
+ else if (curr_state == enqueued_stall)
+ ha_cancel_timer(ha_mon);
+}
+
+static bool ha_verify_constraint(struct ha_monitor *ha_mon,
+ enum states curr_state, enum events event,
+ enum states next_state, u64 time_ns)
+{
+ if (!ha_verify_invariants(ha_mon, curr_state, event, next_state, time_ns))
+ return false;
+
+ if (!ha_verify_guards(ha_mon, curr_state, event, next_state, time_ns))
+ return false;
+
+ ha_setup_invariants(ha_mon, curr_state, event, next_state, time_ns);
+
+ return true;
+}
+
+static void handle_sched_switch(void *data, bool preempt,
+ struct task_struct *prev,
+ struct task_struct *next,
+ unsigned int prev_state)
+{
+ if (!preempt && prev_state != TASK_RUNNING)
+ da_handle_start_event(prev, sched_switch_wait_stall);
+ else
+ da_handle_event(prev, sched_switch_preempt_stall);
+ da_handle_event(next, sched_switch_in_stall);
+}
+
+static void handle_sched_wakeup(void *data, struct task_struct *p)
+{
+ da_handle_event(p, sched_wakeup_stall);
+}
+
+static int enable_stall(void)
+{
+ int retval;
+
+ retval = da_monitor_init();
+ if (retval)
+ return retval;
+
+ rv_attach_trace_probe("stall", sched_switch, handle_sched_switch);
+ rv_attach_trace_probe("stall", sched_wakeup, handle_sched_wakeup);
+
+ return 0;
+}
+
+static void disable_stall(void)
+{
+ rv_this.enabled = 0;
+
+ rv_detach_trace_probe("stall", sched_switch, handle_sched_switch);
+ rv_detach_trace_probe("stall", sched_wakeup, handle_sched_wakeup);
+
+ da_monitor_destroy();
+}
+
+static struct rv_monitor rv_this = {
+ .name = "stall",
+ .description = "identify tasks stalled for longer than a threshold.",
+ .enable = enable_stall,
+ .disable = disable_stall,
+ .reset = da_monitor_reset_all,
+ .enabled = 0,
+};
+
+static int __init register_stall(void)
+{
+ return rv_register_monitor(&rv_this, NULL);
+}
+
+static void __exit unregister_stall(void)
+{
+ rv_unregister_monitor(&rv_this);
+}
+
+module_init(register_stall);
+module_exit(unregister_stall);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Gabriele Monaco <gmonaco@redhat.com>");
+MODULE_DESCRIPTION("stall: identify tasks stalled for longer than a threshold.");
diff --git a/kernel/trace/rv/monitors/stall/stall.h b/kernel/trace/rv/monitors/stall/stall.h
new file mode 100644
index 000000000000..638520cb1082
--- /dev/null
+++ b/kernel/trace/rv/monitors/stall/stall.h
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Automatically generated C representation of stall automaton
+ * For further information about this format, see kernel documentation:
+ * Documentation/trace/rv/deterministic_automata.rst
+ */
+
+#define MONITOR_NAME stall
+
+enum states_stall {
+ dequeued_stall,
+ enqueued_stall,
+ running_stall,
+ state_max_stall,
+};
+
+#define INVALID_STATE state_max_stall
+
+enum events_stall {
+ sched_switch_in_stall,
+ sched_switch_preempt_stall,
+ sched_switch_wait_stall,
+ sched_wakeup_stall,
+ event_max_stall,
+};
+
+enum envs_stall {
+ clk_stall,
+ env_max_stall,
+ env_max_stored_stall = env_max_stall,
+};
+
+_Static_assert(env_max_stored_stall <= MAX_HA_ENV_LEN, "Not enough slots");
+
+struct automaton_stall {
+ char *state_names[state_max_stall];
+ char *event_names[event_max_stall];
+ char *env_names[env_max_stall];
+ unsigned char function[state_max_stall][event_max_stall];
+ unsigned char initial_state;
+ bool final_states[state_max_stall];
+};
+
+static const struct automaton_stall automaton_stall = {
+ .state_names = {
+ "dequeued",
+ "enqueued",
+ "running",
+ },
+ .event_names = {
+ "sched_switch_in",
+ "sched_switch_preempt",
+ "sched_switch_wait",
+ "sched_wakeup",
+ },
+ .env_names = {
+ "clk",
+ },
+ .function = {
+ {
+ INVALID_STATE,
+ INVALID_STATE,
+ INVALID_STATE,
+ enqueued_stall,
+ },
+ {
+ running_stall,
+ INVALID_STATE,
+ INVALID_STATE,
+ enqueued_stall,
+ },
+ {
+ running_stall,
+ enqueued_stall,
+ dequeued_stall,
+ running_stall,
+ },
+ },
+ .initial_state = dequeued_stall,
+ .final_states = { 1, 0, 0 },
+};
diff --git a/kernel/trace/rv/monitors/stall/stall_trace.h b/kernel/trace/rv/monitors/stall/stall_trace.h
new file mode 100644
index 000000000000..6a7cc1b1d040
--- /dev/null
+++ b/kernel/trace/rv/monitors/stall/stall_trace.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Snippet to be included in rv_trace.h
+ */
+
+#ifdef CONFIG_RV_MON_STALL
+DEFINE_EVENT(event_da_monitor_id, event_stall,
+ 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_stall,
+ TP_PROTO(int id, char *state, char *event),
+ TP_ARGS(id, state, event));
+
+DEFINE_EVENT(error_env_da_monitor_id, error_env_stall,
+ TP_PROTO(int id, char *state, char *event, char *env),
+ TP_ARGS(id, state, event, env));
+#endif /* CONFIG_RV_MON_STALL */
diff --git a/kernel/trace/rv/rv_trace.h b/kernel/trace/rv/rv_trace.h
index 7c598967bc0e..1661f8fe4a88 100644
--- a/kernel/trace/rv/rv_trace.h
+++ b/kernel/trace/rv/rv_trace.h
@@ -187,6 +187,7 @@ DECLARE_EVENT_CLASS(error_env_da_monitor_id,
__get_str(env))
);
+#include <monitors/stall/stall_trace.h>
// Add new monitors based on CONFIG_HA_MON_EVENTS_ID here
#endif
diff --git a/tools/verification/models/stall.dot b/tools/verification/models/stall.dot
new file mode 100644
index 000000000000..50077d1dff74
--- /dev/null
+++ b/tools/verification/models/stall.dot
@@ -0,0 +1,22 @@
+digraph state_automaton {
+ center = true;
+ size = "7,11";
+ {node [shape = circle] "enqueued"};
+ {node [shape = plaintext, style=invis, label=""] "__init_dequeued"};
+ {node [shape = doublecircle] "dequeued"};
+ {node [shape = circle] "running"};
+ "__init_dequeued" -> "dequeued";
+ "enqueued" [label = "enqueued\nclk < threshold_jiffies"];
+ "running" [label = "running"];
+ "dequeued" [label = "dequeued", color = green3];
+ "running" -> "running" [ label = "sched_switch_in\nsched_wakeup" ];
+ "enqueued" -> "enqueued" [ label = "sched_wakeup" ];
+ "enqueued" -> "running" [ label = "sched_switch_in" ];
+ "running" -> "dequeued" [ label = "sched_switch_wait" ];
+ "dequeued" -> "enqueued" [ label = "sched_wakeup;reset(clk)" ];
+ "running" -> "enqueued" [ label = "sched_switch_preempt;reset(clk)" ];
+ { rank = min ;
+ "__init_dequeued";
+ "dequeued";
+ }
+}
--
2.52.0
^ permalink raw reply related
* [PATCH v3 05/13] Documentation/rv: Add documentation about hybrid automata
From: Gabriele Monaco @ 2025-12-05 13:16 UTC (permalink / raw)
To: linux-kernel, Steven Rostedt, Nam Cao, Gabriele Monaco,
Jonathan Corbet, linux-trace-kernel, linux-doc
Cc: Tomas Glozar, Juri Lelli, Clark Williams, John Kacur
In-Reply-To: <20251205131621.135513-1-gmonaco@redhat.com>
Describe theory and implementation of hybrid automata in the dedicated
page hybrid_automata.rst
Include a section on how to integrate a hybrid automaton in
monitor_synthesis.rst
Also remove a hanging $ in deterministic_automata.rst
Signed-off-by: Gabriele Monaco <gmonaco@redhat.com>
---
Notes:
V3:
* Improve documentation clarity after review
.../trace/rv/deterministic_automata.rst | 2 +-
Documentation/trace/rv/hybrid_automata.rst | 341 ++++++++++++++++++
Documentation/trace/rv/index.rst | 1 +
Documentation/trace/rv/monitor_synthesis.rst | 117 +++++-
4 files changed, 458 insertions(+), 3 deletions(-)
create mode 100644 Documentation/trace/rv/hybrid_automata.rst
diff --git a/Documentation/trace/rv/deterministic_automata.rst b/Documentation/trace/rv/deterministic_automata.rst
index d0638f95a455..7a1c2b20ec72 100644
--- a/Documentation/trace/rv/deterministic_automata.rst
+++ b/Documentation/trace/rv/deterministic_automata.rst
@@ -11,7 +11,7 @@ where:
- *E* is the finite set of events;
- x\ :subscript:`0` is the initial state;
- X\ :subscript:`m` (subset of *X*) is the set of marked (or final) states.
-- *f* : *X* x *E* -> *X* $ is the transition function. It defines the state
+- *f* : *X* x *E* -> *X* is the transition function. It defines the state
transition in the occurrence of an event from *E* in the state *X*. In the
special case of deterministic automata, the occurrence of the event in *E*
in a state in *X* has a deterministic next state from *X*.
diff --git a/Documentation/trace/rv/hybrid_automata.rst b/Documentation/trace/rv/hybrid_automata.rst
new file mode 100644
index 000000000000..39c037a71b89
--- /dev/null
+++ b/Documentation/trace/rv/hybrid_automata.rst
@@ -0,0 +1,341 @@
+Hybrid Automata
+===============
+
+Hybrid automata are an extension of deterministic automata, there are several
+definitions of hybrid automata in the literature. The adaptation implemented
+here is formally denoted by G and defined as a 7-tuple:
+
+ *G* = { *X*, *E*, *V*, *f*, x\ :subscript:`0`, X\ :subscript:`m`, *i* }
+
+- *X* is the set of states;
+- *E* is the finite set of events;
+- *V* is the finite set of environment variables;
+- x\ :subscript:`0` is the initial state;
+- X\ :subscript:`m` (subset of *X*) is the set of marked (or final) states.
+- *f* : *X* x *E* x *C(V)* -> *X* is the transition function.
+ It defines the state transition in the occurrence of an event from *E* in the
+ state *X*. Unlike deterministic automata, the transition function also
+ includes guards from the set of all possible constraints (defined as *C(V)*).
+ Guards can be true or false with the valuation of *V* when the event occurs,
+ and the transition is possible only when constraints are true. Similarly to
+ deterministic automata, the occurrence of the event in *E* in a state in *X*
+ has a deterministic next state from *X*, if the guard is true.
+- *i* : *X* -> *C'(V)* is the invariant assignment function, this is a
+ constraint assigned to each state in *X*, every state in *X* must be left
+ before the invariant turns to false. We can omit the representation of
+ invariants whose value is true regardless of the valuation of *V*.
+
+The set of all possible constraints *C(V)* is defined according to the
+following grammar:
+
+ g = v < c | v > c | v <= c | v >= c | v == c | v != c | g && g | true
+
+With v a variable in *V* and c a numerical value.
+
+We define the special case of hybrid automata whose variables grow with uniform
+rates as timed automata. In this case, the variables are called clocks.
+As the name implies, timed automata can be used to describe real time.
+Additionally, clocks support another type of guard which always evaluates to true:
+
+ reset(v)
+
+The reset constraint is used to set the value of a clock to 0.
+
+The set of invariant constraints *C'(V)* is a subset of *C(V)* including only
+constraint of the form:
+
+ g = v < c | true
+
+This simplifies the implementation as a clock expiration is a necessary and
+sufficient condition for the violation of invariants while still allowing more
+complex constraints to be specified as guards.
+
+It is important to note that any hybrid automaton is a valid deterministic
+automaton with additional guards and invariants. Those can only further
+constrain what transitions are valid but it is not possible to define
+transition functions starting from the same state in *X* and the same event in
+*E* but ending up in different states in *X* based on the valuation of *V*.
+
+Examples
+--------
+
+Wip as hybrid automaton
+~~~~~~~~~~~~~~~~~~~~~~~
+
+The 'wip' (wakeup in preemptive) example introduced as a deterministic automaton
+can also be described as:
+
+- *X* = { ``any_thread_running`` }
+- *E* = { ``sched_waking`` }
+- *V* = { ``preemptive`` }
+- x\ :subscript:`0` = ``any_thread_running``
+- X\ :subscript:`m` = {``any_thread_running``}
+- *f* =
+ - *f*\ (``any_thread_running``, ``sched_waking``, ``preemptive==0``) = ``any_thread_running``
+- *i* =
+ - *i*\ (``any_thread_running``) = ``true``
+
+Which can be represented graphically as::
+
+ |
+ |
+ v
+ #====================# sched_waking;preemptive==0
+ H H ------------------------------+
+ H any_thread_running H |
+ H H <-----------------------------+
+ #====================#
+
+In this example, by using the preemptive state of the system as an environment
+variable, we can assert this constraint on ``sched_waking`` without requiring
+preemption events (as we would in a deterministic automaton), which can be
+useful in case those events are not available or not reliable on the system.
+
+Since all the invariants in *i* are true, we can omit them from the representation.
+
+Stall model with guards (iteration 1)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+As a sample timed automaton we can define 'stall' as:
+
+- *X* = { ``dequeued``, ``enqueued``, ``running``}
+- *E* = { ``enqueue``, ``dequeue``, ``switch_in``}
+- *V* = { ``clk`` }
+- x\ :subscript:`0` = ``dequeue``
+- X\ :subscript:`m` = {``dequeue``}
+- *f* =
+ - *f*\ (``enqueued``, ``switch_in``, ``clk < threshold``) = ``running``
+ - *f*\ (``running``, ``dequeue``) = ``dequeued``
+ - *f*\ (``dequeued``, ``enqueue``, ``reset(clk)``) = ``enqueued``
+- *i* = *omitted as all true*
+
+Graphically represented as::
+
+ |
+ |
+ v
+ #============================#
+ H dequeued H <+
+ #============================# |
+ | |
+ | enqueue; reset(clk) |
+ v |
+ +----------------------------+ |
+ | enqueued | | dequeue
+ +----------------------------+ |
+ | |
+ | switch_in; clk < threshold |
+ v |
+ +----------------------------+ |
+ | running | -+
+ +----------------------------+
+
+This model imposes that the time between when a task is enqueued (it becomes
+runnable) and when the task gets to run must be lower than a certain threshold.
+A failure in this model means that the task is starving.
+One problem in using guards on the edges in this case is that the model will
+not report a failure until the ``switch_in`` event occurs. This means that,
+according to the model, it is valid for the task never to run.
+
+Stall model with invariants (iteration 2)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The first iteration isn't exactly what was intended, we can change the model as:
+
+- *X* = { ``dequeued``, ``enqueued``, ``running``}
+- *E* = { ``enqueue``, ``dequeue``, ``switch_in``}
+- *V* = { ``clk`` }
+- x\ :subscript:`0` = ``dequeue``
+- X\ :subscript:`m` = {``dequeue``}
+- *f* =
+ - *f*\ (``enqueued``, ``switch_in``) = ``running``
+ - *f*\ (``running``, ``dequeue``) = ``dequeued``
+ - *f*\ (``dequeued``, ``enqueue``, ``reset(clk)``) = ``enqueued``
+- *i* =
+ - *i*\ (``enqueued``) = ``clk < threshold``
+
+Graphically::
+
+ |
+ |
+ v
+ #=========================#
+ H dequeued H <+
+ #=========================# |
+ | |
+ | enqueue; reset(clk) |
+ v |
+ +-------------------------+ |
+ | enqueued | |
+ | clk < threshold | | dequeue
+ +-------------------------+ |
+ | |
+ | switch_in |
+ v |
+ +-------------------------+ |
+ | running | -+
+ +-------------------------+
+
+In this case, we moved the guard as an invariant to the ``enqueued`` state,
+this means we not only forbid the occurrence of ``switch_in`` when ``clk`` is
+past the threshold but also mark as invalid in case we are *still* in
+``enqueued`` after the threshold. This model is effectively in an invalid state
+as soon as a task is starving, rather than when the starving task finally runs.
+
+Hybrid Automaton in C
+---------------------
+
+The definition of hybrid automata in C is heavily based on the deterministic
+automata one. Specifically, we add the set of environment variables and the
+constraints (both guards on transitions and invariants on states) as follows.
+This is a combination of both iterations of the stall example::
+
+ /* enum representation of X (set of states) to be used as index */
+ enum states {
+ dequeued,
+ enqueued,
+ running,
+ state_max,
+ };
+
+ #define INVALID_STATE state_max
+
+ /* enum representation of E (set of events) to be used as index */
+ enum events {
+ dequeue,
+ enqueue,
+ switch_in,
+ event_max,
+ };
+
+ /* enum representation of V (set of environment variables) to be used as index */
+ enum envs {
+ clk,
+ env_max,
+ env_max_stored = env_max,
+ };
+
+ struct automaton {
+ char *state_names[state_max]; // X: the set of states
+ char *event_names[event_max]; // E: the finite set of events
+ char *env_names[env_max]; // V: the finite set of env vars
+ unsigned char function[state_max][event_max]; // f: transition function
+ unsigned char initial_state; // x_0: the initial state
+ bool final_states[state_max]; // X_m: the set of marked states
+ };
+
+ struct automaton aut = {
+ .state_names = {
+ "dequeued",
+ "enqueued",
+ "running",
+ },
+ .event_names = {
+ "dequeue",
+ "enqueue",
+ "switch_in",
+ },
+ .env_names = {
+ "clk",
+ },
+ .function = {
+ { INVALID_STATE, enqueued, INVALID_STATE },
+ { INVALID_STATE, INVALID_STATE, running },
+ { dequeued, INVALID_STATE, INVALID_STATE },
+ },
+ .initial_state = dequeued,
+ .final_states = { 1, 0, 0 },
+ };
+
+ static bool verify_constraint(enum states curr_state, enum events event,
+ enum states next_state)
+ {
+ bool res = true;
+
+ /* Validate guards as part of f */
+ if (curr_state == enqueued && event == sched_switch_in)
+ res = get_env(clk) < threshold;
+ else if (curr_state == dequeued && event == sched_wakeup)
+ reset_env(clk);
+
+ /* Validate invariants in i */
+ if (next_state == curr_state || !res)
+ return res;
+ if (next_state == enqueued)
+ ha_start_timer_jiffy(ha_mon, clk, threshold_jiffies);
+ else if (curr_state == enqueued)
+ res = !ha_cancel_timer(ha_mon);
+ return res;
+ }
+
+The function ``verify_constraint``, here reported as simplified, checks guards,
+performs resets and starts timers to validate invariants according to
+specification.
+Due to the complex nature of environment variables, the user needs to provide
+functions to get and reset environment variables that are not common clocks
+(e.g. clocks with ns or jiffy granularity).
+Since invariants are only defined as clock expirations (e.g. *clk <
+threshold*), reaching the expiration of a timer armed when entering the state
+is in fact a failure in the model and triggers a reaction. Leaving the state
+stops the timer.
+
+It is important to note that timers implemented with hrtimers introduce
+overhead, if the monitor has several instances (e.g. all tasks) this can become
+an issue. The impact can be decreased using the timer wheel (``HA_TIMER_TYPE``
+set to ``HA_TIMER_WHEEL``), this lowers the responsiveness of the timer without
+damaging the accuracy of the model, since the invariant condition is checked
+before disabling the timer in case the callback is late.
+Alternatively, if the monitor is guaranteed to *eventually* leave the state and
+the incurred delay to wait for the next event is acceptable, guards can be used
+in place of invariants, as seen in the stall example.
+
+Graphviz .dot format
+--------------------
+
+Also the Graphviz representation of hybrid automata is an extension of the
+deterministic automata one. Specifically, guards can be provided in the event
+name separated by ``;``::
+
+ "state_start" -> "state_dest" [ label = "sched_waking;preemptible==0;reset(clk)" ];
+
+Invariant can be specified in the state label (not the node name!) separated by ``\n``::
+
+ "enqueued" [label = "enqueued\nclk < threshold_jiffies"];
+
+Constraints can be specified as valid C comparisons and allow spaces, the first
+element of the comparison must be the clock while the second is a numerical or
+parametrised value. Guards allow comparisons to be combined with boolean
+operations (``&&`` and ``||``), resets must be separated from other constraints.
+
+This is the full example of the last version of the 'stall' model in DOT::
+
+ digraph state_automaton {
+ {node [shape = circle] "enqueued"};
+ {node [shape = plaintext, style=invis, label=""] "__init_dequeued"};
+ {node [shape = doublecircle] "dequeued"};
+ {node [shape = circle] "running"};
+ "__init_dequeued" -> "dequeued";
+ "enqueued" [label = "enqueued\nclk < threshold_jiffies"];
+ "running" [label = "running"];
+ "dequeued" [label = "dequeued"];
+ "enqueued" -> "running" [ label = "switch_in" ];
+ "running" -> "dequeued" [ label = "dequeue" ];
+ "dequeued" -> "enqueued" [ label = "enqueue;reset(clk)" ];
+ { rank = min ;
+ "__init_dequeued";
+ "dequeued";
+ }
+ }
+
+References
+----------
+
+One book covering model checking and timed automata is::
+
+ Christel Baier and Joost-Pieter Katoen: Principles of Model Checking,
+ The MIT Press, 2008.
+
+Hybrid automata are described in detail in::
+
+ Thomas Henzinger: The theory of hybrid automata,
+ Proceedings 11th Annual IEEE Symposium on Logic in Computer Science, 1996.
diff --git a/Documentation/trace/rv/index.rst b/Documentation/trace/rv/index.rst
index a2812ac5cfeb..ad298784bda2 100644
--- a/Documentation/trace/rv/index.rst
+++ b/Documentation/trace/rv/index.rst
@@ -9,6 +9,7 @@ Runtime Verification
runtime-verification.rst
deterministic_automata.rst
linear_temporal_logic.rst
+ hybrid_automata.rst
monitor_synthesis.rst
da_monitor_instrumentation.rst
monitor_wip.rst
diff --git a/Documentation/trace/rv/monitor_synthesis.rst b/Documentation/trace/rv/monitor_synthesis.rst
index cc5f97977a29..2c1b5a0ae154 100644
--- a/Documentation/trace/rv/monitor_synthesis.rst
+++ b/Documentation/trace/rv/monitor_synthesis.rst
@@ -18,8 +18,8 @@ functions that glue the monitor to the system reference model, and the
trace output as a reaction to event parsing and exceptions, as depicted
below::
- Linux +----- RV Monitor ----------------------------------+ Formal
- Realm | | Realm
+ Linux +---- RV Monitor ----------------------------------+ Formal
+ Realm | | Realm
+-------------------+ +----------------+ +-----------------+
| Linux kernel | | Monitor | | Reference |
| Tracing | -> | Instance(s) | <- | Model |
@@ -45,6 +45,7 @@ creating monitors. The header files are:
* rv/da_monitor.h for deterministic automaton monitor.
* rv/ltl_monitor.h for linear temporal logic monitor.
+ * rv/ha_monitor.h for hybrid automaton monitor.
rvgen
-----
@@ -252,6 +253,118 @@ the task, the monitor may need some time to start validating tasks which have
been running before the monitor is enabled. Therefore, it is recommended to
start the tasks of interest after enabling the monitor.
+rv/ha_monitor.h
++++++++++++++++
+
+The implementation of hybrid automaton monitors derives directly from the
+deterministic automaton one. Despite using a different header
+(``ha_monitor.h``) the functions to handle events are the same (e.g.
+``da_handle_event``).
+
+Additionally, the `rvgen` tool populates skeletons for the
+``ha_verify_constraint``, ``ha_get_env`` and ``ha_reset_env`` based on the
+monitor specification in the monitor source file.
+
+``ha_verify_constraint`` is typically ready as it is generated by `rvgen`:
+
+* standard constraints on edges are turned into the form::
+
+ res = ha_get_env(ha_mon, ENV) < VALUE;
+
+* reset constraints are turned into the form::
+
+ ha_reset_env(ha_mon, ENV);
+
+* constraints on the state are implemented using timers
+
+ - armed before entering the state
+
+ - cancelled while entering any other state
+
+ - untouched if the state does not change as a result of the event
+
+ - checked if the timer expired but the callback did not run
+
+ - available implementation are `HA_TIMER_HRTIMER` and `HA_TIMER_WHEEL`
+
+ - hrtimers are more precise but may have higher overhead
+
+ - select by defining `HA_TIMER_TYPE` before including the header::
+
+ #define HA_TIMER_TYPE HA_TIMER_HRTIMER
+
+Constraint values can be specified in different forms:
+
+* literal value (with optional unit). E.g.::
+
+ preemptive == 0
+ clk < 100ns
+ threshold <= 10j
+
+* constant value (uppercase string). E.g.::
+
+ clk < MAX_NS
+
+* parameter (lowercase string). E.g.::
+
+ clk <= threshold_jiffies
+
+* macro (uppercase string with parentheses). E.g.::
+
+ clk < MAX_NS()
+
+* function (lowercase string with parentheses). E.g.::
+
+ clk <= threshold_jiffies()
+
+In all cases, `rvgen` will try to understand the type of the environment
+variable from the name or unit. For instance, constants or parameters
+terminating with ``_NS`` or ``_jiffies`` are intended as clocks with ns and jiffy
+granularity, respectively. Literals with measure unit `j` are jiffies and if a
+time unit is specified (`ns` to `s`), `rvgen` will convert the value to `ns`.
+
+Constants need to be defined by the user (but unlike the name, they don't
+necessarily need to be defined as constants). Parameters get converted to
+module parameters and the user needs to provide a default value.
+Also function and macros are defined by the user, by default they get as an
+argument the ``ha_monitor``, a common usage would be to get the required value
+from the target, e.g. the task in per-task monitors, using the helper
+``ha_get_target(ha_mon)``.
+
+If `rvgen` determines that the variable is a clock, it provides the getter and
+resetter based on the unit. Otherwise, the user needs to provide an appropriate
+definition.
+Typically non-clock environment variables are not reset. In such case only the
+getter skeleton will be present in the file generated by `rvgen`.
+For instance, the getter for preemptive can be filled as::
+
+ static u64 ha_get_env(struct ha_monitor *ha_mon, enum envs env)
+ {
+ if (env == preemptible)
+ return preempt_count() == 0;
+ return ENV_INVALID_VALUE;
+ }
+
+The function is supplied the ``ha_mon`` parameter in case some storage is
+required (as it is for clocks), but environment variables without reset do not
+require a storage and can ignore that argument.
+The number of environment variables requiring a storage is limited by
+``MAX_HA_ENV_LEN``, however such limitation doesn't stand for other variables.
+
+Finally, constraints on states are only valid for clocks and only if the
+constraint is of the form `clk < N`. This is because such constraints are
+implemented with the expiration of a timer.
+Typically the clock variables are reset just before arming the timer, but this
+doesn't have to be the case and the available functions take care of it.
+It is a responsibility of per-task monitors to make sure no timer is left
+running when the task exits.
+
+By default the generator implements timers with hrtimers (setting
+``HA_TIMER_TYPE`` to ``HA_TIMER_HRTIMER``), this gives better responsiveness
+but higher overhead. The timer wheel (``HA_TIMER_WHEEL``) is a good alternative
+for monitors with several instances (e.g. per-task) that achieves lower
+overhead with increased latency, yet without compromising precision.
+
Final remarks
-------------
--
2.52.0
^ permalink raw reply related
* [PATCH v3 04/13] verification/rvgen: Add support for Hybrid Automata
From: Gabriele Monaco @ 2025-12-05 13:16 UTC (permalink / raw)
To: linux-kernel, Steven Rostedt, Nam Cao, Gabriele Monaco,
linux-trace-kernel
Cc: Tomas Glozar, Juri Lelli, Clark Williams, John Kacur
In-Reply-To: <20251205131621.135513-1-gmonaco@redhat.com>
Add the possibility to parse dot files as hybrid automata and generate
the necessary code from rvgen.
Hybrid automata are very similar to deterministic ones and most
functionality is shared, the dot files include also constraints together
with event names (separated by ;) and state names (separated by \n).
The tool can now generate the appropriate code to validate constraints
at runtime according to the dot specification.
Signed-off-by: Gabriele Monaco <gmonaco@redhat.com>
---
tools/verification/rvgen/__main__.py | 8 +-
tools/verification/rvgen/rvgen/automata.py | 141 +++++-
tools/verification/rvgen/rvgen/dot2c.py | 49 ++
tools/verification/rvgen/rvgen/dot2k.py | 473 +++++++++++++++++-
tools/verification/rvgen/rvgen/generator.py | 2 +
.../rvgen/rvgen/templates/dot2k/main.c | 2 +-
.../rvgen/templates/dot2k/trace_hybrid.h | 16 +
7 files changed, 677 insertions(+), 14 deletions(-)
create mode 100644 tools/verification/rvgen/rvgen/templates/dot2k/trace_hybrid.h
diff --git a/tools/verification/rvgen/__main__.py b/tools/verification/rvgen/__main__.py
index fa6fc1f4de2f..b8e07e463293 100644
--- a/tools/verification/rvgen/__main__.py
+++ b/tools/verification/rvgen/__main__.py
@@ -9,7 +9,7 @@
# Documentation/trace/rv/da_monitor_synthesis.rst
if __name__ == '__main__':
- from rvgen.dot2k import dot2k
+ from rvgen.dot2k import da2k, ha2k
from rvgen.generator import Monitor
from rvgen.container import Container
from rvgen.ltl2k import ltl2k
@@ -29,7 +29,7 @@ if __name__ == '__main__':
monitor_parser.add_argument("-p", "--parent", dest="parent",
required=False, help="Create a monitor nested to parent")
monitor_parser.add_argument('-c', "--class", dest="monitor_class",
- help="Monitor class, either \"da\" or \"ltl\"")
+ help="Monitor class, either \"da\", \"ha\" or \"ltl\"")
monitor_parser.add_argument('-s', "--spec", dest="spec", help="Monitor specification file")
monitor_parser.add_argument('-t', "--monitor_type", dest="monitor_type",
help=f"Available options: {', '.join(Monitor.monitor_types.keys())}")
@@ -43,7 +43,9 @@ if __name__ == '__main__':
if params.subcmd == "monitor":
print("Opening and parsing the specification file %s" % params.spec)
if params.monitor_class == "da":
- monitor = dot2k(params.spec, params.monitor_type, vars(params))
+ monitor = da2k(params.spec, params.monitor_type, vars(params))
+ elif params.monitor_class == "ha":
+ monitor = ha2k(params.spec, params.monitor_type, vars(params))
elif params.monitor_class == "ltl":
monitor = ltl2k(params.spec, params.monitor_type, vars(params))
else:
diff --git a/tools/verification/rvgen/rvgen/automata.py b/tools/verification/rvgen/rvgen/automata.py
index 977ba859c34e..252c9960ee1c 100644
--- a/tools/verification/rvgen/rvgen/automata.py
+++ b/tools/verification/rvgen/rvgen/automata.py
@@ -9,24 +9,63 @@
# Documentation/trace/rv/deterministic_automata.rst
import ntpath
+import re
+from typing import Iterator
+
+class _ConstraintKey:
+ """Base class for constraint keys."""
+
+class _StateConstraintKey(_ConstraintKey, int):
+ """Key for a state constraint. Under the hood just state_id."""
+ def __new__(cls, state_id: int):
+ return super().__new__(cls, state_id)
+
+class _EventConstraintKey(_ConstraintKey, tuple):
+ """Key for an event constraint. Under the hood just tuple(state_id,event_id)."""
+ def __new__(cls, state_id: int, event_id: int):
+ return super().__new__(cls, (state_id, event_id))
class Automata:
"""Automata class: Reads a dot file and part it as an automata.
+ It supports both deterministic and hybrid automata.
+
Attributes:
dot_file: A dot file with an state_automaton definition.
"""
invalid_state_str = "INVALID_STATE"
+ # val can be numerical, uppercase (constant or macro), lowercase (parameter or function)
+ # only numerical values should have units
+ constraint_rule = re.compile(r"""
+ ^
+ (?P<env>[a-zA-Z_][a-zA-Z0-9_]+) # C-like identifier for the env var
+ (?P<op>[!<=>]{1,2}) # operator
+ (?P<val>
+ [0-9]+ | # numerical value
+ [A-Z_]+\(\) | # macro
+ [A-Z_]+ | # constant
+ [a-z_]+\(\) | # function
+ [a-z_]+ # parameter
+ )
+ (?P<unit>[a-z]{1,2})? # optional unit for numerical values
+ """, re.VERBOSE)
+ constraint_reset = re.compile(r"^reset\((?P<env>[a-zA-Z_][a-zA-Z0-9_]+)\)")
def __init__(self, file_path, model_name=None):
self.__dot_path = file_path
self.name = model_name or self.__get_model_name()
self.__dot_lines = self.__open_dot()
self.states, self.initial_state, self.final_states = self.__get_state_variables()
- self.events = self.__get_event_variables()
- self.function = self.__create_matrix()
+ self.env_types = {}
+ self.env_stored = set()
+ self.constraint_vars = set()
+ self.self_loop_reset_events = set()
+ self.events, self.envs = self.__get_event_variables()
+ self.function, self.constraints = self.__create_matrix()
self.events_start, self.events_start_run = self.__store_init_events()
+ self.env_stored = sorted(self.env_stored)
+ self.constraint_vars = sorted(self.constraint_vars)
def __get_model_name(self) -> str:
basename = ntpath.basename(self.__dot_path)
@@ -116,11 +155,12 @@ class Automata:
return states, initial_state, final_states
- def __get_event_variables(self) -> list[str]:
+ def __get_event_variables(self) -> tuple[list[str], list[str]]:
# here we are at the begin of transitions, take a note, we will return later.
cursor = self.__get_cursor_begin_events()
events = []
+ envs = []
while self.__dot_lines[cursor].lstrip()[0] == '"':
# transitions have the format:
# "all_fired" -> "both_fired" [ label = "disable_irq" ];
@@ -134,12 +174,74 @@ class Automata:
# so split them.
for i in event.split("\\n"):
- events.append(i)
+ # if the event contains a constraint (hybrid automata),
+ # it will be separated by a ";":
+ # "sched_switch;x<1000;reset(x)"
+ ev, *constr = i.split(";")
+ if constr:
+ if len(constr) > 2:
+ raise ValueError("Only 1 constraint and 1 reset are supported")
+ envs += self.__extract_env_var(constr)
+ events.append(ev)
+ else:
+ # state labels have the format:
+ # "enable_fired" [label = "enable_fired\ncondition"];
+ # ----- label is here -----^^^^^
+ # label and node name must be the same, condition is optional
+ state = self.__dot_lines[cursor].split("label")[1].split('"')[1]
+ _, *constr = state.split("\\n")
+ if constr:
+ if len(constr) > 1:
+ raise ValueError("Only 1 constraint is supported in the state")
+ envs += self.__extract_env_var([constr[0].replace(" ", "")])
cursor += 1
- return sorted(set(events))
-
- def __create_matrix(self) -> list[list[str]]:
+ return sorted(set(events)), sorted(set(envs))
+
+ def _split_constraint_expr(self, constr: list[str]) -> Iterator[tuple[str,
+ str | None]]:
+ """
+ Get a list of strings of the type constr1 && constr2 and returns a list of
+ constraints and separators: [[constr1,"&&"],[constr2,None]]
+ """
+ exprs = []
+ seps = []
+ for c in constr:
+ while "&&" in c or "||" in c:
+ a = c.find("&&")
+ o = c.find("||")
+ pos = a if o < 0 or 0 < a < o else o
+ exprs.append(c[:pos].replace(" ", ""))
+ seps.append(c[pos:pos+2].replace(" ", ""))
+ c = c[pos+2:].replace(" ", "")
+ exprs.append(c)
+ seps.append(None)
+ return zip(exprs, seps)
+
+ def __extract_env_var(self, constraint: list[str]) -> list[str]:
+ env = []
+ for c, _ in self._split_constraint_expr(constraint):
+ rule = self.constraint_rule.search(c)
+ reset = self.constraint_reset.search(c)
+ if rule:
+ env.append(rule["env"])
+ if rule.groupdict().get("unit"):
+ self.env_types[rule["env"]] = rule["unit"]
+ if rule["val"][0].isalpha():
+ self.constraint_vars.add(rule["val"])
+ # try to infer unit from constants or parameters
+ val_for_unit = rule["val"].lower().replace("()", "")
+ if val_for_unit.endswith("_ns"):
+ self.env_types[rule["env"]] = "ns"
+ if val_for_unit.endswith("_jiffies"):
+ self.env_types[rule["env"]] = "j"
+ if reset:
+ env.append(reset["env"])
+ # environment variables that are reset need a storage
+ self.env_stored.add(reset["env"])
+ return env
+
+ def __create_matrix(self) -> tuple[list[list[str]], dict[_ConstraintKey, list[str]]]:
# transform the array into a dictionary
events = self.events
states = self.states
@@ -157,6 +259,7 @@ class Automata:
# declare the matrix....
matrix = [[ self.invalid_state_str for x in range(nr_event)] for y in range(nr_state)]
+ constraints: dict[_ConstraintKey, list[str]] = {}
# and we are back! Let's fill the matrix
cursor = self.__get_cursor_begin_events()
@@ -168,10 +271,22 @@ class Automata:
dest_state = line[2].replace('"','').replace(',','_')
possible_events = "".join(line[line.index("label")+2:-1]).replace('"','')
for event in possible_events.split("\\n"):
+ event, *constr = event.split(";")
+ if constr:
+ key = _EventConstraintKey(states_dict[origin_state], events_dict[event])
+ constraints[key] = constr
+ # those events reset also on self loops
+ if origin_state == dest_state and "reset" in "".join(constr):
+ self.self_loop_reset_events.add(event)
matrix[states_dict[origin_state]][events_dict[event]] = dest_state
+ else:
+ state = self.__dot_lines[cursor].split("label")[1].split('"')[1]
+ state, *constr = state.replace(" ", "").split("\\n")
+ if constr:
+ constraints[_StateConstraintKey(states_dict[state])] = constr
cursor += 1
- return matrix
+ return matrix, constraints
def __store_init_events(self) -> tuple[list[bool], list[bool]]:
events_start = [False] * len(self.events)
@@ -203,3 +318,13 @@ class Automata:
if any(self.events_start):
return False
return self.events_start_run[self.events.index(event)]
+
+ def is_hybrid_automata(self) -> bool:
+ return bool(self.envs)
+
+ def is_event_constraint(self, key: _ConstraintKey) -> bool:
+ """
+ Given the key in self.constraints return true if it is an event
+ constraint, false if it is a state constraint
+ """
+ return isinstance(key, _EventConstraintKey)
diff --git a/tools/verification/rvgen/rvgen/dot2c.py b/tools/verification/rvgen/rvgen/dot2c.py
index 06a26bf15a7e..7f2efcfe3e52 100644
--- a/tools/verification/rvgen/rvgen/dot2c.py
+++ b/tools/verification/rvgen/rvgen/dot2c.py
@@ -19,6 +19,7 @@ class Dot2c(Automata):
enum_suffix = ""
enum_states_def = "states"
enum_events_def = "events"
+ enum_envs_def = "envs"
struct_automaton_def = "automaton"
var_automaton_def = "aut"
@@ -61,6 +62,39 @@ class Dot2c(Automata):
return buff
+ def __get_non_stored_envs(self) -> list[str]:
+ return [ e for e in self.envs if e not in self.env_stored ]
+
+ def __get_enum_envs_content(self) -> list[str]:
+ buff = []
+ # We first place env variables that have a u64 storage.
+ # Those are limited by MAX_HA_ENV_LEN, other variables
+ # are read only and don't require a storage.
+ unstored = self.__get_non_stored_envs()
+ for env in list(self.env_stored) + unstored:
+ buff.append("\t%s%s," % (env, self.enum_suffix))
+
+ buff.append("\tenv_max%s," % self.enum_suffix)
+ buff.append("\tenv_max_stored%s = %s%s," %
+ (self.enum_suffix,
+ unstored[0] if len(unstored) else "env_max",
+ self.enum_suffix))
+
+ return buff
+
+ def format_envs_enum(self) -> list[str]:
+ buff = []
+ if self.is_hybrid_automata():
+ buff.append("enum %s {" % self.enum_envs_def)
+ buff += self.__get_enum_envs_content()
+ buff.append("};\n")
+ buff.append('_Static_assert(env_max_stored%s <= MAX_HA_ENV_LEN, "Not enough slots");' %
+ (self.enum_suffix))
+ if {"ns", "us", "ms", "s"}.intersection(self.env_types.values()):
+ buff.append("#define HA_CLK_NS")
+ buff.append("")
+ return buff
+
def get_minimun_type(self) -> str:
min_type = "unsigned char"
@@ -81,6 +115,8 @@ class Dot2c(Automata):
buff.append("struct %s {" % self.struct_automaton_def)
buff.append("\tchar *state_names[state_max%s];" % (self.enum_suffix))
buff.append("\tchar *event_names[event_max%s];" % (self.enum_suffix))
+ if self.is_hybrid_automata():
+ buff.append("\tchar *env_names[env_max%s];" % (self.enum_suffix))
buff.append("\t%s function[state_max%s][event_max%s];" % (min_type, self.enum_suffix, self.enum_suffix))
buff.append("\t%s initial_state;" % min_type)
buff.append("\tbool final_states[state_max%s];" % (self.enum_suffix))
@@ -113,6 +149,17 @@ class Dot2c(Automata):
return buff
+ def format_aut_init_envs_string(self) -> list[str]:
+ buff = []
+ if self.is_hybrid_automata():
+ buff.append("\t.env_names = {")
+ # maintain consistent order with the enum
+ ordered_envs = list(self.env_stored) + self.__get_non_stored_envs()
+ buff.append(self.__get_string_vector_per_line_content(ordered_envs))
+ buff.append("\t},")
+
+ return buff
+
def __get_max_strlen_of_states(self) -> int:
max_state_name = max(self.states, key = len).__len__()
return max(max_state_name, self.invalid_state_str.__len__())
@@ -205,10 +252,12 @@ class Dot2c(Automata):
buff += self.format_states_enum()
buff += self.format_invalid_state()
buff += self.format_events_enum()
+ buff += self.format_envs_enum()
buff += self.format_automaton_definition()
buff += self.format_aut_init_header()
buff += self.format_aut_init_states_string()
buff += self.format_aut_init_events_string()
+ buff += self.format_aut_init_envs_string()
buff += self.format_aut_init_function()
buff += self.format_aut_init_initial_state()
buff += self.format_aut_init_final_states()
diff --git a/tools/verification/rvgen/rvgen/dot2k.py b/tools/verification/rvgen/rvgen/dot2k.py
index 6128fe238430..e72369ec1ad7 100644
--- a/tools/verification/rvgen/rvgen/dot2k.py
+++ b/tools/verification/rvgen/rvgen/dot2k.py
@@ -8,8 +8,10 @@
# For further information, see:
# Documentation/trace/rv/da_monitor_synthesis.rst
+from collections import deque
from .dot2c import Dot2c
from .generator import Monitor
+from .automata import _EventConstraintKey, _StateConstraintKey
class dot2k(Monitor, Dot2c):
@@ -20,12 +22,16 @@ class dot2k(Monitor, Dot2c):
Monitor.__init__(self, extra_params)
Dot2c.__init__(self, file_path, extra_params.get("model_name"))
self.enum_suffix = "_%s" % self.name
+ self.monitor_class = extra_params["monitor_class"]
def fill_monitor_type(self) -> str:
- return self.monitor_type.upper()
+ buff = [ self.monitor_type.upper() ]
+ buff += self._fill_timer_type()
+ return "\n".join(buff)
def fill_tracepoint_handlers_skel(self) -> str:
buff = []
+ buff += self._fill_hybrid_definitions()
for event in self.events:
buff.append("static void handle_%s(void *data, /* XXX: fill header */)" % event)
buff.append("{")
@@ -77,6 +83,7 @@ class dot2k(Monitor, Dot2c):
#
self.enum_states_def = "states_%s" % self.name
self.enum_events_def = "events_%s" % self.name
+ self.enum_envs_def = "envs_%s" % self.name
self.struct_automaton_def = "automaton_%s" % self.name
self.var_automaton_def = "automaton_%s" % self.name
@@ -107,8 +114,14 @@ class dot2k(Monitor, Dot2c):
("char *", "state"),
("char *", "event"),
]
+ tp_args_error_env = tp_args_error + [("char *", "env")]
+ tp_args_dict = {
+ "event": tp_args_event,
+ "error": tp_args_error,
+ "error_env": tp_args_error_env
+ }
tp_args_id = ("int ", "id")
- tp_args = tp_args_event if tp_type == "event" else tp_args_error
+ tp_args = tp_args_dict[tp_type]
if self.monitor_type == "per_task":
tp_args.insert(0, tp_args_id)
tp_proto_c = ", ".join([a+b for a,b in tp_args])
@@ -117,6 +130,14 @@ class dot2k(Monitor, Dot2c):
buff.append(" TP_ARGS(%s)" % tp_args_c)
return '\n'.join(buff)
+ def _fill_hybrid_definitions(self) -> list:
+ """Stub, not valid for deterministic automata"""
+ return []
+
+ def _fill_timer_type(self) -> list:
+ """Stub, not valid for deterministic automata"""
+ return []
+
def fill_main_c(self) -> str:
main_c = super().fill_main_c()
@@ -127,5 +148,453 @@ class dot2k(Monitor, Dot2c):
main_c = main_c.replace("%%MIN_TYPE%%", min_type)
main_c = main_c.replace("%%NR_EVENTS%%", str(nr_events))
main_c = main_c.replace("%%MONITOR_TYPE%%", monitor_type)
+ main_c = main_c.replace("%%MONITOR_CLASS%%", self.monitor_class)
return main_c
+
+class da2k(dot2k):
+ """Deterministic automata only"""
+ def __init__(self, *args, **kwargs):
+ super().__init__(*args, **kwargs)
+ if self.is_hybrid_automata():
+ raise ValueError("Detected hybrid automata, use the 'ha' class")
+
+class ha2k(dot2k):
+ """Hybrid automata only"""
+ def __init__(self, *args, **kwargs):
+ super().__init__(*args, **kwargs)
+ if not self.is_hybrid_automata():
+ raise ValueError("Detected deterministic automata, use the 'da' class")
+ self.trace_h = self._read_template_file("trace_hybrid.h")
+ self.__parse_constraints()
+
+ def fill_monitor_class_type(self) -> str:
+ if self.monitor_type == "per_task":
+ return "HA_MON_EVENTS_ID"
+ return "HA_MON_EVENTS_IMPLICIT"
+
+ def fill_monitor_class(self) -> str:
+ """
+ Used for tracepoint classes, since they are shared we keep da
+ instead of ha (also for the ha specific tracepoints).
+ The tracepoint class is not visible to the tools.
+ """
+ return super().fill_monitor_class()
+
+ def __adjust_value(self, value: str | int, unit: str | None) -> str:
+ """Adjust the value in ns"""
+ try:
+ value = int(value)
+ except ValueError:
+ # it's a constant, a parameter or a function
+ if value.endswith("()"):
+ return value.replace("()", "(ha_mon)")
+ return value
+ match unit:
+ case "us":
+ value *= 10**3
+ case "ms":
+ value *= 10**6
+ case "s":
+ value *= 10**9
+ return str(value) + "ull"
+
+ def __parse_single_constraint(self, rule: dict, value: str) -> str:
+ return "ha_get_env(ha_mon, %s%s, time_ns) %s %s" % (
+ rule["env"], self.enum_suffix, rule["op"], value)
+
+ def __get_constraint_env(self, constr: str) -> str:
+ """Extract the second argument from an ha_ function"""
+ env = constr.split("(")[1].split()[1].rstrip(")").rstrip(",")
+ assert env.rstrip(f"_{self.name}") in self.envs
+ return env
+
+ def __start_to_invariant_check(self, constr:str) -> str:
+ # by default assume the timer has ns expiration
+ env = self.__get_constraint_env(constr)
+ clock_type = "ns"
+ if self.env_types.get(env.rstrip(f"_{self.name}")) == "j":
+ clock_type = "jiffy"
+
+ return "return ha_check_invariant_%s(ha_mon, %s, time_ns)" % (clock_type, env)
+
+ def __start_to_conv(self, constr: str) -> str:
+ """
+ Undo the storage conversion done by ha_start_timer_
+ """
+ return "ha_inv_to_guard" + constr[constr.find("("):]
+
+ def __parse_timer_constraint(self, rule: dict, value: str) -> str:
+ # by default assume the timer has ns expiration
+ clock_type = "ns"
+ if self.env_types.get(rule["env"]) == "j":
+ clock_type = "jiffy"
+
+ return "ha_start_timer_%s(ha_mon, %s%s, %s, time_ns)" % (clock_type, rule["env"],
+ self.enum_suffix, value)
+
+ def __format_guard_rules(self, rules: list[str]) -> list[str]:
+ """
+ Merge guard constraints as a single C return statement.
+ If the rules include a stored env, also check its validity.
+ Break lines in a best effort way that tries to keep readability.
+ """
+ if not rules:
+ return []
+
+ invalid_checks = [f"ha_monitor_env_invalid(ha_mon, {env}{self.enum_suffix}) ||"
+ for env in self.env_stored if any(env in rule for rule in rules)]
+ if invalid_checks and len(rules) > 1:
+ rules[0] = "(" + rules[0]
+ rules[-1] = rules[-1] + ")"
+ rules = invalid_checks + rules
+
+ separator = "\n\t\t " if sum(len(r) for r in rules) > 80 else " "
+ return ["res = " + separator.join(rules)]
+
+ def __validate_constraint(self, key: tuple[int, int] | int, constr: str,
+ rule, reset) -> None:
+ # event constrains are tuples and allow both rules and reset
+ # state constraints are only used for expirations (e.g. clk<N)
+ if self.is_event_constraint(key):
+ if not rule and not reset:
+ raise ValueError("Unrecognised event constraint (%s/%s: %s)"
+ % (self.states[key[0]], self.events[key[1]], constr))
+ if rule and (rule["env"] in self.env_types and
+ rule["env"] not in self.env_stored):
+ raise ValueError("Clocks in hybrid automata always require a storage (%s)"
+ % rule["env"])
+ else:
+ if not rule:
+ raise ValueError("Unrecognised state constraint (%s: %s)"
+ % (self.states[key], constr))
+ if rule["env"] not in self.env_stored:
+ raise ValueError("State constraints always require a storage (%s)"
+ % rule["env"])
+ if rule["op"] not in ["<", "<="]:
+ raise ValueError("State constraints must be clock expirations like clk<N (%s)"
+ % rule.string)
+
+ def __parse_constraints(self) -> None:
+ self.guards: dict[_EventConstraintKey, str] = {}
+ self.invariants: dict[_StateConstraintKey, str] = {}
+ for key, constraint in self.constraints.items():
+ rules = []
+ resets = []
+ for c, sep in self._split_constraint_expr(constraint):
+ rule = self.constraint_rule.search(c)
+ reset = self.constraint_reset.search(c)
+ self.__validate_constraint(key, c, rule, reset)
+ if rule:
+ value = rule["val"]
+ value_len = len(rule["val"])
+ unit = None
+ if rule.groupdict().get("unit"):
+ value_len += len(rule["unit"])
+ unit = rule["unit"]
+ c = c[:-(value_len)]
+ value = self.__adjust_value(value, unit)
+ if self.is_event_constraint(key):
+ c = self.__parse_single_constraint(rule, value)
+ if sep:
+ c += f" {sep}"
+ else:
+ c = self.__parse_timer_constraint(rule, value)
+ rules.append(c)
+ if reset:
+ c = "ha_reset_env(ha_mon, %s%s, time_ns)" % (reset["env"],
+ self.enum_suffix)
+ resets.append(c)
+ if self.is_event_constraint(key):
+ res = self.__format_guard_rules(rules) + resets
+ self.guards[key] = ";".join(res)
+ else:
+ self.invariants[key] = rules[0]
+
+ def __fill_verify_invariants_func(self) -> list[str]:
+ buff = []
+ if not self.invariants:
+ return []
+
+ buff.append(
+"""static inline bool ha_verify_invariants(struct ha_monitor *ha_mon,
+\t\t\t\t\tenum %s curr_state, enum %s event,
+\t\t\t\t\tenum %s next_state, u64 time_ns)
+{""" % (self.enum_states_def, self.enum_events_def, self.enum_states_def))
+
+ _else = ""
+ for state, constr in self.invariants.items():
+ check_str = self.__start_to_invariant_check(constr)
+ buff.append("\t%sif (curr_state == %s%s)" %
+ (_else, self.states[state], self.enum_suffix))
+ buff.append("\t\t%s;" % check_str)
+ _else = "else "
+
+ buff.append("\treturn true;\n}\n")
+ return buff
+
+ def __fill_convert_inv_guard_func(self) -> list[str]:
+ buff = []
+ if not self.invariants:
+ return []
+
+ conflict_guards, conflict_invs = self.__find_inv_conflicts()
+ if not conflict_guards and not conflict_invs:
+ return []
+
+ buff.append(
+"""static inline void ha_convert_inv_guard(struct ha_monitor *ha_mon,
+\t\t\t\t\tenum %s curr_state, enum %s event,
+\t\t\t\t\tenum %s next_state, u64 time_ns)
+{""" % (self.enum_states_def, self.enum_events_def, self.enum_states_def))
+ buff.append("\tif (curr_state == next_state)\n\t\treturn;")
+
+ _else = ""
+ for state, constr in self.invariants.items():
+ # a state with invariant can reach us without reset
+ # multiple conflicts must have the same invariant, otherwise we cannot
+ # know how to reset the value
+ conf_i = [start for start, end in conflict_invs if end == state]
+ # we can reach a guard without reset
+ conf_g = [e for s, e in conflict_guards if s == state]
+ if not conf_i and not conf_g:
+ continue
+ buff.append("\t%sif (curr_state == %s%s)" %
+ (_else, self.states[state], self.enum_suffix))
+ buff.append("\t\t%s;" % self.__start_to_conv(constr))
+ _else = "else "
+
+ buff.append("}\n")
+ return buff
+
+ def __fill_verify_guards_func(self) -> list[str]:
+ buff = []
+ if not self.guards:
+ return []
+
+ buff.append(
+"""static inline bool ha_verify_guards(struct ha_monitor *ha_mon,
+\t\t\t\t enum %s curr_state, enum %s event,
+\t\t\t\t enum %s next_state, u64 time_ns)
+{
+\tbool res = true;
+""" % (self.enum_states_def, self.enum_events_def, self.enum_states_def))
+
+ _else = ""
+ for edge, constr in self.guards.items():
+ buff.append("\t%sif (curr_state == %s%s && event == %s%s)" %
+ (_else, self.states[edge[0]], self.enum_suffix,
+ self.events[edge[1]], self.enum_suffix))
+ if constr.count(";") > 0:
+ buff[-1] += " {"
+ buff += [ "\t\t%s;" % c for c in constr.split(";") ]
+ if constr.count(";") > 0:
+ _else = "} else "
+ else:
+ _else = "else "
+ if _else[0] == "}":
+ buff.append("\t}")
+ buff.append("\treturn res;\n}\n")
+ return buff
+
+ def __find_inv_conflicts(self) -> tuple[set[tuple[int, _EventConstraintKey]],
+ set[tuple[int, _StateConstraintKey]]]:
+ """
+ Run a breadth first search from all states with an invariant.
+ Find any conflicting constraints reachable from there, this can be
+ another state with an invariant or an edge with a non-reset guard.
+ Stop when we find a reset.
+
+ Return the set of conflicting guards and invariants as tuples of
+ conflicting state and constraint key.
+ """
+ conflict_guards : set[tuple[int, _EventConstraintKey]] = set()
+ conflict_invs : set[tuple[int, _StateConstraintKey]] = set()
+ for start_idx in self.invariants:
+ queue = deque([(start_idx, 0)]) # (state_idx, distance)
+ env = self.__get_constraint_env(self.invariants[start_idx])
+
+ while queue:
+ curr_idx, distance = queue.popleft()
+
+ # Check state condition
+ if curr_idx != start_idx and curr_idx in self.invariants:
+ conflict_invs.add((start_idx, _StateConstraintKey(curr_idx)))
+ continue
+
+ # Check if we should stop
+ if distance > len(self.states):
+ break
+ if curr_idx != start_idx and distance > 1:
+ continue
+
+ for event_idx, next_state_name in enumerate(self.function[curr_idx]):
+ if next_state_name == self.invalid_state_str:
+ continue
+ curr_guard = self.guards.get((curr_idx, event_idx), "")
+ if "reset" in curr_guard and env in curr_guard:
+ continue
+
+ if env in curr_guard:
+ conflict_guards.add((start_idx,
+ _EventConstraintKey(curr_idx, event_idx)))
+ continue
+
+ next_idx = self.states.index(next_state_name)
+ queue.append((next_idx, distance + 1))
+
+ return conflict_guards, conflict_invs
+
+ def __fill_setup_invariants_func(self) -> list[str]:
+ buff = []
+ if not self.invariants:
+ return []
+
+ buff.append(
+"""static inline void ha_setup_invariants(struct ha_monitor *ha_mon,
+\t\t\t\t enum %s curr_state, enum %s event,
+\t\t\t\t enum %s next_state, u64 time_ns)
+{""" % (self.enum_states_def, self.enum_events_def, self.enum_states_def))
+
+ conditions = ["next_state == curr_state"]
+ conditions += ["event != %s%s" % (e, self.enum_suffix)
+ for e in self.self_loop_reset_events]
+ condition_str = " && ".join(conditions)
+ buff.append(f"\tif ({condition_str})\n\t\treturn;")
+
+ _else = ""
+ for state, constr in self.invariants.items():
+ buff.append("\t%sif (next_state == %s%s)" %
+ (_else, self.states[state], self.enum_suffix))
+ buff.append("\t\t%s;" % constr)
+ _else = "else "
+
+ for state in self.invariants:
+ buff.append("\telse if (curr_state == %s%s)" %
+ (self.states[state], self.enum_suffix))
+ buff.append("\t\tha_cancel_timer(ha_mon);")
+
+ buff.append("}\n")
+ return buff
+
+ def __fill_constr_func(self) -> list[str]:
+ buff = []
+ if not self.constraints:
+ return []
+
+ buff.append(
+"""/*
+ * These functions are used to validate state transitions.
+ *
+ * They are generated by parsing the model, there is usually no need to change them.
+ * If the monitor requires a timer, there are functions responsible to arm it when
+ * the next state has a constraint, cancel it in any other case and to check
+ * that it didn't expire before the callback run. Transitions to the same state
+ * without a reset never affect timers.
+ * Due to the different representations between invariants and guards, there is
+ * a function to convert it in case invariants or guards are reachable from
+ * another invariant without reset. Those are not present if not required in
+ * the model. This is all automatic but is worth checking because it may show
+ * errors in the model (e.g. missing resets).
+ */""")
+
+ buff += self.__fill_verify_invariants_func()
+ inv_conflicts = self.__fill_convert_inv_guard_func()
+ buff += inv_conflicts
+ buff += self.__fill_verify_guards_func()
+ buff += self.__fill_setup_invariants_func()
+
+ buff.append(
+"""static bool ha_verify_constraint(struct ha_monitor *ha_mon,
+\t\t\t\t enum %s curr_state, enum %s event,
+\t\t\t\t enum %s next_state, u64 time_ns)
+{""" % (self.enum_states_def, self.enum_events_def, self.enum_states_def))
+
+ if self.invariants:
+ buff.append("\tif (!ha_verify_invariants(ha_mon, curr_state, event, next_state, time_ns))\n\t\treturn false;\n")
+ if inv_conflicts:
+ buff.append("\tha_convert_inv_guard(ha_mon, curr_state, event, next_state, time_ns);\n")
+
+ if self.guards:
+ buff.append("\tif (!ha_verify_guards(ha_mon, curr_state, event, next_state, time_ns))\n\t\treturn false;\n")
+
+ if self.invariants:
+ buff.append("\tha_setup_invariants(ha_mon, curr_state, event, next_state, time_ns);\n")
+
+ buff.append("\treturn true;\n}\n")
+ return buff
+
+ def __fill_env_getter(self, env: str) -> str:
+ if env in self.env_types:
+ match self.env_types[env]:
+ case "ns" | "us" | "ms" | "s":
+ return "ha_get_clk_ns(ha_mon, env, time_ns);"
+ case "j":
+ return "ha_get_clk_jiffy(ha_mon, env);"
+ return "/* XXX: how do I read %s? */" % env
+
+ def __fill_env_resetter(self, env: str) -> str:
+ if env in self.env_types:
+ match self.env_types[env]:
+ case "ns" | "us" | "ms" | "s":
+ return "ha_reset_clk_ns(ha_mon, env, time_ns);"
+ case "j":
+ return "ha_reset_clk_jiffy(ha_mon, env);"
+ return "/* XXX: how do I reset %s? */" % env
+
+ def __fill_hybrid_get_reset_functions(self) -> list[str]:
+ buff = []
+ if self.is_hybrid_automata():
+ for var in self.constraint_vars:
+ if var.endswith("()"):
+ func_name = var.replace("()", "")
+ if func_name.isupper():
+ buff.append("#define %s(ha_mon) /* XXX: what is %s(ha_mon)? */\n" % (func_name, func_name))
+ else:
+ buff.append("static inline u64 %s(struct ha_monitor *ha_mon)\n{" % func_name)
+ buff.append("\treturn /* XXX: what is %s(ha_mon)? */;" % func_name)
+ buff.append("}\n")
+ elif var.isupper():
+ buff.append("#define %s /* XXX: what is %s? */\n" % (var, var))
+ else:
+ buff.append("static u64 %s = /* XXX: default value */;" % var)
+ buff.append("module_param(%s, ullong, 0644);\n" % var)
+ buff.append("""/*
+ * These functions define how to read and reset the environment variable.
+ *
+ * Common environment variables like ns-based and jiffy-based clocks have
+ * pre-define getters and resetters you can use. The parser can infer the type
+ * of the environment variable if you supply a measure unit in the constraint.
+ * If you define your own functions, make sure to add appropriate memory
+ * barriers if required.
+ * Some environment variables don't require a storage as they read a system
+ * state (e.g. preemption count). Those variables are never reset, so we don't
+ * define a reset function on monitors only relying on this type of variables.
+ */""")
+ buff.append("static u64 ha_get_env(struct ha_monitor *ha_mon, enum envs%s env, u64 time_ns)\n{" % self.enum_suffix)
+ _else = ""
+ for env in self.envs:
+ buff.append("\t%sif (env == %s%s)\n\t\treturn %s" %
+ (_else, env, self.enum_suffix, self.__fill_env_getter(env)))
+ _else = "else "
+ buff.append("\treturn ENV_INVALID_VALUE;\n}\n")
+ if len(self.env_stored):
+ buff.append("static void ha_reset_env(struct ha_monitor *ha_mon, enum envs%s env, u64 time_ns)\n{" % self.enum_suffix)
+ _else = ""
+ for env in self.env_stored:
+ buff.append("\t%sif (env == %s%s)\n\t\t%s" %
+ (_else, env, self.enum_suffix, self.__fill_env_resetter(env)))
+ _else = "else "
+ buff.append("}\n")
+ return buff
+
+ def _fill_hybrid_definitions(self) -> list[str]:
+ return self.__fill_hybrid_get_reset_functions() + self.__fill_constr_func()
+
+ def _fill_timer_type(self) -> list:
+ if self.invariants:
+ return [
+ "/* XXX: If the monitor has several instances, consider HA_TIMER_WHEEL */",
+ "#define HA_TIMER_TYPE HA_TIMER_HRTIMER"
+ ]
+ return []
diff --git a/tools/verification/rvgen/rvgen/generator.py b/tools/verification/rvgen/rvgen/generator.py
index 3441385c1177..b80af3fd6701 100644
--- a/tools/verification/rvgen/rvgen/generator.py
+++ b/tools/verification/rvgen/rvgen/generator.py
@@ -255,12 +255,14 @@ class Monitor(RVGenerator):
monitor_class_type = self.fill_monitor_class_type()
tracepoint_args_skel_event = self.fill_tracepoint_args_skel("event")
tracepoint_args_skel_error = self.fill_tracepoint_args_skel("error")
+ tracepoint_args_skel_error_env = self.fill_tracepoint_args_skel("error_env")
trace_h = trace_h.replace("%%MODEL_NAME%%", self.name)
trace_h = trace_h.replace("%%MODEL_NAME_UP%%", self.name.upper())
trace_h = trace_h.replace("%%MONITOR_CLASS%%", monitor_class)
trace_h = trace_h.replace("%%MONITOR_CLASS_TYPE%%", monitor_class_type)
trace_h = trace_h.replace("%%TRACEPOINT_ARGS_SKEL_EVENT%%", tracepoint_args_skel_event)
trace_h = trace_h.replace("%%TRACEPOINT_ARGS_SKEL_ERROR%%", tracepoint_args_skel_error)
+ trace_h = trace_h.replace("%%TRACEPOINT_ARGS_SKEL_ERROR_ENV%%", tracepoint_args_skel_error_env)
return trace_h
def print_files(self):
diff --git a/tools/verification/rvgen/rvgen/templates/dot2k/main.c b/tools/verification/rvgen/rvgen/templates/dot2k/main.c
index a14e4f0883db..bf0999f6657a 100644
--- a/tools/verification/rvgen/rvgen/templates/dot2k/main.c
+++ b/tools/verification/rvgen/rvgen/templates/dot2k/main.c
@@ -21,7 +21,7 @@
*/
#define RV_MON_TYPE RV_MON_%%MONITOR_TYPE%%
#include "%%MODEL_NAME%%.h"
-#include <rv/da_monitor.h>
+#include <rv/%%MONITOR_CLASS%%_monitor.h>
/*
* This is the instrumentation part of the monitor.
diff --git a/tools/verification/rvgen/rvgen/templates/dot2k/trace_hybrid.h b/tools/verification/rvgen/rvgen/templates/dot2k/trace_hybrid.h
new file mode 100644
index 000000000000..c8290e9ba2f4
--- /dev/null
+++ b/tools/verification/rvgen/rvgen/templates/dot2k/trace_hybrid.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Snippet to be included in rv_trace.h
+ */
+
+#ifdef CONFIG_RV_MON_%%MODEL_NAME_UP%%
+DEFINE_EVENT(event_%%MONITOR_CLASS%%, event_%%MODEL_NAME%%,
+%%TRACEPOINT_ARGS_SKEL_EVENT%%);
+
+DEFINE_EVENT(error_%%MONITOR_CLASS%%, error_%%MODEL_NAME%%,
+%%TRACEPOINT_ARGS_SKEL_ERROR%%);
+
+DEFINE_EVENT(error_env_%%MONITOR_CLASS%%, error_env_%%MODEL_NAME%%,
+%%TRACEPOINT_ARGS_SKEL_ERROR_ENV%%);
+#endif /* CONFIG_RV_MON_%%MODEL_NAME_UP%% */
--
2.52.0
^ permalink raw reply related
* [PATCH v3 03/13] verification/rvgen: Allow spaces in and events strings
From: Gabriele Monaco @ 2025-12-05 13:16 UTC (permalink / raw)
To: linux-kernel, Steven Rostedt, Nam Cao, Gabriele Monaco,
linux-trace-kernel
Cc: Tomas Glozar, Juri Lelli, Clark Williams, John Kacur
In-Reply-To: <20251205131621.135513-1-gmonaco@redhat.com>
Currently the automata parser assumes event strings don't have any
space, this stands true for event names, but can be a wrong assumption
if we want to store other information in the event strings (e.g.
constraints for hybrid automata).
Adapt the parser logic to allow spaces in the event strings.
Reviewed-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Gabriele Monaco <gmonaco@redhat.com>
---
tools/verification/rvgen/rvgen/automata.py | 9 ++++-----
1 file changed, 4 insertions(+), 5 deletions(-)
diff --git a/tools/verification/rvgen/rvgen/automata.py b/tools/verification/rvgen/rvgen/automata.py
index 3f06aef8d4fd..977ba859c34e 100644
--- a/tools/verification/rvgen/rvgen/automata.py
+++ b/tools/verification/rvgen/rvgen/automata.py
@@ -127,14 +127,13 @@ class Automata:
# ------------ event is here ------------^^^^^
if self.__dot_lines[cursor].split()[1] == "->":
line = self.__dot_lines[cursor].split()
- event = line[-2].replace('"','')
+ event = "".join(line[line.index("label")+2:-1]).replace('"','')
# when a transition has more than one lables, they are like this
# "local_irq_enable\nhw_local_irq_enable_n"
# so split them.
- event = event.replace("\\n", " ")
- for i in event.split():
+ for i in event.split("\\n"):
events.append(i)
cursor += 1
@@ -167,8 +166,8 @@ class Automata:
line = self.__dot_lines[cursor].split()
origin_state = line[0].replace('"','').replace(',','_')
dest_state = line[2].replace('"','').replace(',','_')
- possible_events = line[-2].replace('"','').replace("\\n", " ")
- for event in possible_events.split():
+ possible_events = "".join(line[line.index("label")+2:-1]).replace('"','')
+ for event in possible_events.split("\\n"):
matrix[states_dict[origin_state]][events_dict[event]] = dest_state
cursor += 1
--
2.52.0
^ permalink raw reply related
* [PATCH v3 02/13] rv: Add Hybrid Automata monitor type
From: Gabriele Monaco @ 2025-12-05 13:16 UTC (permalink / raw)
To: linux-kernel, Steven Rostedt, Nam Cao, Gabriele Monaco,
Masami Hiramatsu, linux-trace-kernel
Cc: Tomas Glozar, Juri Lelli, Clark Williams, John Kacur
In-Reply-To: <20251205131621.135513-1-gmonaco@redhat.com>
Deterministic automata define which events are allowed in every state,
but cannot define more sophisticated constraint taking into account the
system's environment (e.g. time or other states not producing events).
Add the Hybrid Automata monitor type as an extension of Deterministic
automata where each state transition is validating a constraint on a
finite number of environment variables.
Hybrid automata can be used to implement timed automata, where the
environment variables are clocks.
Also implement the necessary functionality to handle clock constraints
(ns or jiffy granularity) on state and events.
Signed-off-by: Gabriele Monaco <gmonaco@redhat.com>
---
Notes:
V3:
* Improve functions naming for HA helpers
include/linux/rv.h | 38 +++
include/rv/da_monitor.h | 83 ++++++-
include/rv/ha_monitor.h | 476 +++++++++++++++++++++++++++++++++++++
kernel/trace/rv/Kconfig | 13 +
kernel/trace/rv/rv_trace.h | 63 +++++
5 files changed, 664 insertions(+), 9 deletions(-)
create mode 100644 include/rv/ha_monitor.h
diff --git a/include/linux/rv.h b/include/linux/rv.h
index 58774eb3aecf..0aef9e3c785c 100644
--- a/include/linux/rv.h
+++ b/include/linux/rv.h
@@ -81,11 +81,49 @@ struct ltl_monitor {};
#endif /* CONFIG_RV_LTL_MONITOR */
+#ifdef CONFIG_RV_HA_MONITOR
+/*
+ * In the future, hybrid automata may rely on multiple
+ * environment variables, e.g. different clocks started at
+ * different times or running at different speed.
+ * For now we support only 1 variable.
+ */
+#define MAX_HA_ENV_LEN 1
+
+/*
+ * Monitors can pick the preferred timer implementation:
+ * No timer: if monitors don't have state invariants.
+ * Timer wheel: lightweight invariants check but far less precise.
+ * Hrtimer: accurate invariants check with higher overhead.
+ */
+#define HA_TIMER_NONE 0
+#define HA_TIMER_WHEEL 1
+#define HA_TIMER_HRTIMER 2
+
+/*
+ * Hybrid automaton per-object variables.
+ */
+struct ha_monitor {
+ struct da_monitor da_mon;
+ u64 env_store[MAX_HA_ENV_LEN];
+ union {
+ struct hrtimer hrtimer;
+ struct timer_list timer;
+ };
+};
+
+#else
+
+struct ha_monitor { };
+
+#endif /* CONFIG_RV_HA_MONITOR */
+
#define RV_PER_TASK_MONITOR_INIT (CONFIG_RV_PER_TASK_MONITORS)
union rv_task_monitor {
struct da_monitor da_mon;
struct ltl_monitor ltl_mon;
+ struct ha_monitor ha_mon;
};
#ifdef CONFIG_RV_REACTORS
diff --git a/include/rv/da_monitor.h b/include/rv/da_monitor.h
index 6b564fad8c4d..4d0f9fb60e3c 100644
--- a/include/rv/da_monitor.h
+++ b/include/rv/da_monitor.h
@@ -3,9 +3,9 @@
* Copyright (C) 2019-2022 Red Hat, Inc. Daniel Bristot de Oliveira <bristot@kernel.org>
*
* Deterministic automata (DA) monitor functions, to be used together
- * with automata models in C generated by the dot2k tool.
+ * with automata models in C generated by the rvgen tool.
*
- * The dot2k tool is available at tools/verification/dot2k/
+ * The rvgen tool is available at tools/verification/rvgen/
*
* For further information, see:
* Documentation/trace/rv/da_monitor_synthesis.rst
@@ -22,6 +22,33 @@
static struct rv_monitor rv_this;
+/*
+ * Hook to allow the implementation of hybrid automata: define it with a
+ * function that takes curr_state, event and next_state and returns true if the
+ * environment constraints (e.g. timing) are satisfied, false otherwise.
+ */
+#ifndef da_monitor_event_hook
+#define da_monitor_event_hook(...) true
+#endif
+
+/*
+ * Hook to allow the implementation of hybrid automata: define it with a
+ * function that takes the da_monitor and performs further initialisation
+ * (e.g. reset set up timers).
+ */
+#ifndef da_monitor_init_hook
+#define da_monitor_init_hook(da_mon)
+#endif
+
+/*
+ * Hook to allow the implementation of hybrid automata: define it with a
+ * function that takes the da_monitor and performs further reset (e.g. reset
+ * all clocks).
+ */
+#ifndef da_monitor_reset_hook
+#define da_monitor_reset_hook(da_mon)
+#endif
+
/*
* Type for the target id, default to int but can be overridden.
*/
@@ -43,6 +70,7 @@ static void react(enum states curr_state, enum events event)
*/
static inline void da_monitor_reset(struct da_monitor *da_mon)
{
+ da_monitor_reset_hook(da_mon);
da_mon->monitoring = 0;
da_mon->curr_state = model_get_initial_state();
}
@@ -57,6 +85,7 @@ static inline void da_monitor_start(struct da_monitor *da_mon)
{
da_mon->curr_state = model_get_initial_state();
da_mon->monitoring = 1;
+ da_monitor_init_hook(da_mon);
}
/*
@@ -106,14 +135,14 @@ static inline bool da_monitor_handling_event(struct da_monitor *da_mon)
/*
* global monitor (a single variable)
*/
-static struct da_monitor da_mon_this;
+static union rv_task_monitor da_mon_this;
/*
* da_get_monitor - return the global monitor address
*/
static struct da_monitor *da_get_monitor(void)
{
- return &da_mon_this;
+ return &(da_mon_this.da_mon);
}
/*
@@ -136,7 +165,10 @@ static inline int da_monitor_init(void)
/*
* da_monitor_destroy - destroy the monitor
*/
-static inline void da_monitor_destroy(void) { }
+static inline void da_monitor_destroy(void)
+{
+ da_monitor_reset_all();
+}
#elif RV_MON_TYPE == RV_MON_PER_CPU
/*
@@ -146,14 +178,14 @@ static inline void da_monitor_destroy(void) { }
/*
* per-cpu monitor variables
*/
-static DEFINE_PER_CPU(struct da_monitor, da_mon_this);
+static DEFINE_PER_CPU(union rv_task_monitor, da_mon_this);
/*
* da_get_monitor - return current CPU monitor address
*/
static struct da_monitor *da_get_monitor(void)
{
- return this_cpu_ptr(&da_mon_this);
+ return &this_cpu_ptr(&da_mon_this)->da_mon;
}
/*
@@ -165,7 +197,7 @@ static void da_monitor_reset_all(void)
int cpu;
for_each_cpu(cpu, cpu_online_mask) {
- da_mon = per_cpu_ptr(&da_mon_this, cpu);
+ da_mon = &per_cpu_ptr(&da_mon_this, cpu)->da_mon;
da_monitor_reset(da_mon);
}
}
@@ -182,7 +214,10 @@ static inline int da_monitor_init(void)
/*
* da_monitor_destroy - destroy the monitor
*/
-static inline void da_monitor_destroy(void) { }
+static inline void da_monitor_destroy(void)
+{
+ da_monitor_reset_all();
+}
#elif RV_MON_TYPE == RV_MON_PER_TASK
/*
@@ -203,6 +238,24 @@ static inline struct da_monitor *da_get_monitor(struct task_struct *tsk)
return &tsk->rv[task_mon_slot].da_mon;
}
+/*
+ * da_get_task - return the task associated to the monitor
+ */
+static inline struct task_struct *da_get_task(struct da_monitor *da_mon)
+{
+ return container_of(da_mon, struct task_struct, rv[task_mon_slot].da_mon);
+}
+
+/*
+ * da_get_id - return the id associated to the monitor
+ *
+ * For per-task monitors, the id is the task's PID.
+ */
+static inline da_id_type da_get_id(struct da_monitor *da_mon)
+{
+ return da_get_task(da_mon)->pid;
+}
+
static void da_monitor_reset_all(void)
{
struct task_struct *g, *p;
@@ -247,6 +300,8 @@ static inline void da_monitor_destroy(void)
}
rv_put_task_monitor_slot(task_mon_slot);
task_mon_slot = RV_PER_TASK_MONITOR_INIT;
+
+ da_monitor_reset_all();
}
#endif /* RV_MON_TYPE */
@@ -273,6 +328,14 @@ static inline void da_trace_error(struct da_monitor *da_mon,
CONCATENATE(trace_error_, MONITOR_NAME)(curr_state, event);
}
+/*
+ * da_get_id - unused for implicit monitors
+ */
+static inline da_id_type da_get_id(struct da_monitor *da_mon)
+{
+ return 0;
+}
+
#elif RV_MON_TYPE == RV_MON_PER_TASK
/*
* Trace events for per_task monitors, report the PID of the task.
@@ -317,6 +380,8 @@ static inline bool da_event(struct da_monitor *da_mon, enum events event, da_id_
return false;
}
if (likely(try_cmpxchg(&da_mon->curr_state, &curr_state, next_state))) {
+ if (!da_monitor_event_hook(da_mon, curr_state, event, next_state, id))
+ return false;
da_trace_event(da_mon, model_get_state_name(curr_state),
model_get_event_name(event),
model_get_state_name(next_state),
diff --git a/include/rv/ha_monitor.h b/include/rv/ha_monitor.h
new file mode 100644
index 000000000000..c8a434cb46ac
--- /dev/null
+++ b/include/rv/ha_monitor.h
@@ -0,0 +1,476 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2025-2028 Red Hat, Inc. Gabriele Monaco <gmonaco@redhat.com>
+ *
+ * Hybrid automata (HA) monitor functions, to be used together
+ * with automata models in C generated by the rvgen tool.
+ *
+ * This type of monitors extends the Deterministic automata (DA) class by
+ * adding a set of environment variables (e.g. clocks) that can be used to
+ * constraint the valid transitions.
+ *
+ * The rvgen tool is available at tools/verification/rvgen/
+ *
+ * For further information, see:
+ * Documentation/trace/rv/ha_monitor_synthesis.rst
+ */
+
+#ifndef _RV_HA_MONITOR_H
+#define _RV_HA_MONITOR_H
+
+#include <rv/automata.h>
+
+#ifndef da_id_type
+#define da_id_type int
+#endif
+
+static inline void ha_monitor_init_env(struct da_monitor *da_mon);
+static inline void ha_monitor_reset_env(struct da_monitor *da_mon);
+static inline void ha_setup_timer(struct ha_monitor *ha_mon);
+static inline bool ha_cancel_timer(struct ha_monitor *ha_mon);
+static bool ha_monitor_handle_constraint(struct da_monitor *da_mon,
+ enum states curr_state,
+ enum events event,
+ enum states next_state,
+ da_id_type id);
+#define da_monitor_event_hook ha_monitor_handle_constraint
+#define da_monitor_init_hook ha_monitor_init_env
+#define da_monitor_reset_hook ha_monitor_reset_env
+
+#include <rv/da_monitor.h>
+#include <linux/seq_buf.h>
+
+/* This simplifies things since da_mon and ha_mon coexist in the same union */
+_Static_assert(offsetof(struct ha_monitor, da_mon) == 0,
+ "da_mon must be the first element in an ha_mon!");
+#define to_ha_monitor(da) container_of(da, struct ha_monitor, da_mon)
+
+#define ENV_MAX CONCATENATE(env_max_, MONITOR_NAME)
+#define ENV_MAX_STORED CONCATENATE(env_max_stored_, MONITOR_NAME)
+#define envs CONCATENATE(envs_, MONITOR_NAME)
+
+/* Environment storage before being reset */
+#define ENV_INVALID_VALUE U64_MAX
+/* Error with no event occurs only on timeouts */
+#define EVENT_NONE EVENT_MAX
+#define EVENT_NONE_LBL "none"
+#define ENV_BUFFER_SIZE 64
+
+#ifdef CONFIG_RV_REACTORS
+
+/*
+ * ha_react - trigger the reaction after a failed environment constraint
+ *
+ * The transition from curr_state with event is otherwise valid, but the
+ * environment constraint is false. This function can be called also with no
+ * event from a timer (state constraints only).
+ */
+static void ha_react(enum states curr_state, enum events event, char *env)
+{
+ rv_react(&rv_this,
+ "rv: monitor %s does not allow event %s on state %s with env %s\n",
+ __stringify(MONITOR_NAME),
+ event == EVENT_NONE ? EVENT_NONE_LBL : model_get_event_name(event),
+ model_get_state_name(curr_state), env);
+}
+
+#else /* CONFIG_RV_REACTOR */
+
+static void ha_react(enum states curr_state, enum events event, char *env) { }
+#endif
+
+/*
+ * model_get_state_name - return the (string) name of the given state
+ */
+static char *model_get_env_name(enum envs env)
+{
+ if ((env < 0) || (env >= ENV_MAX))
+ return "INVALID";
+
+ return RV_AUTOMATON_NAME.env_names[env];
+}
+
+/*
+ * Monitors requiring a timer implementation need to request it explicitly.
+ */
+#ifndef HA_TIMER_TYPE
+#define HA_TIMER_TYPE HA_TIMER_NONE
+#endif
+
+#if HA_TIMER_TYPE == HA_TIMER_WHEEL
+static void ha_monitor_timer_callback(struct timer_list *timer);
+#elif HA_TIMER_TYPE == HA_TIMER_HRTIMER
+static enum hrtimer_restart ha_monitor_timer_callback(struct hrtimer *hrtimer);
+#endif
+
+/*
+ * ktime_get_ns is expensive, since we usually don't require precise accounting
+ * of changes within the same event, cache the current time at the beginning of
+ * the constraint handler and use the cache for subsequent calls.
+ * Monitors without ns clocks automatically skip this.
+ */
+#ifdef HA_CLK_NS
+#define ha_get_ns() ktime_get_ns()
+#else
+#define ha_get_ns() 0
+#endif /* HA_CLK_NS */
+
+/* Should be supplied by the monitor */
+static u64 ha_get_env(struct ha_monitor *ha_mon, enum envs env, u64 time_ns);
+static bool ha_verify_constraint(struct ha_monitor *ha_mon,
+ enum states curr_state,
+ enum events event,
+ enum states next_state,
+ u64 time_ns);
+
+/*
+ * ha_monitor_reset_all_stored - reset all environment variables in the monitor
+ */
+static inline void ha_monitor_reset_all_stored(struct ha_monitor *ha_mon)
+{
+ for (int i = 0; i < ENV_MAX_STORED; i++)
+ WRITE_ONCE(ha_mon->env_store[i], ENV_INVALID_VALUE);
+}
+
+/*
+ * ha_monitor_init_env - setup timer and reset all environment
+ *
+ * Called from a hook in the DA start functions, it supplies the da_mon
+ * corresponding to the current ha_mon.
+ * Not all hybrid automata require the timer, still set it for simplicity.
+ */
+static inline void ha_monitor_init_env(struct da_monitor *da_mon)
+{
+ struct ha_monitor *ha_mon = to_ha_monitor(da_mon);
+
+ ha_monitor_reset_all_stored(ha_mon);
+ ha_setup_timer(ha_mon);
+}
+
+/*
+ * ha_monitor_reset_env - stop timer and reset all environment
+ *
+ * Called from a hook in the DA reset functions, it supplies the da_mon
+ * corresponding to the current ha_mon.
+ * Not all hybrid automata require the timer, still clear it for simplicity.
+ */
+static inline void ha_monitor_reset_env(struct da_monitor *da_mon)
+{
+ struct ha_monitor *ha_mon = to_ha_monitor(da_mon);
+
+ ha_monitor_reset_all_stored(ha_mon);
+ /* Initialisation resets the monitor before initialising the timer */
+ if (likely(da_monitoring(da_mon)))
+ ha_cancel_timer(ha_mon);
+}
+
+/*
+ * ha_monitor_env_invalid - return true if env has not been initialised
+ */
+static inline bool ha_monitor_env_invalid(struct ha_monitor *ha_mon, enum envs env)
+{
+ return READ_ONCE(ha_mon->env_store[env]) == ENV_INVALID_VALUE;
+}
+
+static inline void ha_get_env_string(struct seq_buf *s,
+ struct ha_monitor *ha_mon, u64 time_ns)
+{
+ const char *format_str = "%s=%llu";
+
+ for (int i = 0; i < ENV_MAX; i++) {
+ seq_buf_printf(s, format_str, model_get_env_name(i),
+ ha_get_env(ha_mon, i, time_ns));
+ format_str = ",%s=%llu";
+ }
+}
+
+#if RV_MON_TYPE == RV_MON_GLOBAL || RV_MON_TYPE == RV_MON_PER_CPU
+static inline void ha_trace_error_env(struct ha_monitor *ha_mon,
+ char *curr_state, char *event, char *env,
+ da_id_type id)
+{
+ CONCATENATE(trace_error_env_, MONITOR_NAME)(curr_state, event, env);
+}
+#elif RV_MON_TYPE == RV_MON_PER_TASK
+static inline void ha_trace_error_env(struct ha_monitor *ha_mon,
+ char *curr_state, char *event, char *env,
+ da_id_type id)
+{
+ CONCATENATE(trace_error_env_, MONITOR_NAME)(id, curr_state, event, env);
+}
+#endif /* RV_MON_TYPE */
+
+/*
+ * ha_get_monitor - return the current monitor
+ */
+#define ha_get_monitor(...) to_ha_monitor(da_get_monitor(__VA_ARGS__))
+
+/*
+ * ha_monitor_handle_constraint - handle the constraint on the current transition
+ *
+ * If the monitor implementation defines a constraint in the transition from
+ * curr_state to event, react and trace appropriately as well as return false.
+ * This function is called from the hook in the DA event handle function and
+ * triggers a failure in the monitor.
+ */
+static bool ha_monitor_handle_constraint(struct da_monitor *da_mon,
+ enum states curr_state,
+ enum events event,
+ enum states next_state,
+ da_id_type id)
+{
+ struct ha_monitor *ha_mon = to_ha_monitor(da_mon);
+ u64 time_ns = ha_get_ns();
+ DECLARE_SEQ_BUF(env_string, ENV_BUFFER_SIZE);
+
+ if (ha_verify_constraint(ha_mon, curr_state, event, next_state, time_ns))
+ return true;
+
+ ha_get_env_string(&env_string, ha_mon, time_ns);
+ ha_react(curr_state, event, env_string.buffer);
+ ha_trace_error_env(ha_mon,
+ model_get_state_name(curr_state),
+ model_get_event_name(event),
+ env_string.buffer, id);
+ return false;
+}
+
+static inline void __ha_monitor_timer_callback(struct ha_monitor *ha_mon)
+{
+ enum states curr_state = READ_ONCE(ha_mon->da_mon.curr_state);
+ DECLARE_SEQ_BUF(env_string, ENV_BUFFER_SIZE);
+ u64 time_ns = ha_get_ns();
+
+ ha_get_env_string(&env_string, ha_mon, time_ns);
+ ha_react(curr_state, EVENT_NONE, env_string.buffer);
+ ha_trace_error_env(ha_mon, model_get_state_name(curr_state),
+ EVENT_NONE_LBL, env_string.buffer,
+ da_get_id(&ha_mon->da_mon));
+
+ da_monitor_reset(&ha_mon->da_mon);
+}
+
+/*
+ * The clock variables have 2 different representations in the env_store:
+ * - The guard representation is the timestamp of the last reset
+ * - The invariant representation is the timestamp when the invariant expires
+ * As the representations are incompatible, care must be taken when switching
+ * between them: the invariant representation can only be used when starting a
+ * timer when the previous representation was guard (e.g. no other invariant
+ * started since the last reset operation).
+ * Likewise, switching from invariant to guard representation without a reset
+ * can be done only by subtracting the exact value used to start the invariant.
+ *
+ * Reading the environment variable (ha_get_clk) also reflects this difference
+ * any reads in states that have an invariant return the (possibly negative)
+ * time since expiration, other reads return the time since last reset.
+ */
+
+/*
+ * Helper functions for env variables describing clocks with ns granularity
+ */
+static inline u64 ha_get_clk_ns(struct ha_monitor *ha_mon, enum envs env, u64 time_ns)
+{
+ return time_ns - READ_ONCE(ha_mon->env_store[env]);
+}
+static inline void ha_reset_clk_ns(struct ha_monitor *ha_mon, enum envs env, u64 time_ns)
+{
+ WRITE_ONCE(ha_mon->env_store[env], time_ns);
+}
+static inline void ha_set_invariant_ns(struct ha_monitor *ha_mon, enum envs env,
+ u64 value, u64 time_ns)
+{
+ WRITE_ONCE(ha_mon->env_store[env], time_ns + value);
+}
+static inline bool ha_check_invariant_ns(struct ha_monitor *ha_mon,
+ enum envs env, u64 time_ns)
+{
+ return READ_ONCE(ha_mon->env_store[env]) >= time_ns;
+}
+/*
+ * ha_invariant_passed_ns - prepare the invariant and return the time since reset
+ */
+static inline u64 ha_invariant_passed_ns(struct ha_monitor *ha_mon, enum envs env,
+ u64 expire, u64 time_ns)
+{
+ u64 passed = 0;
+
+ if (env < 0 || env >= ENV_MAX_STORED)
+ return 0;
+ if (ha_monitor_env_invalid(ha_mon, env))
+ return 0;
+ passed = ha_get_env(ha_mon, env, time_ns);
+ ha_set_invariant_ns(ha_mon, env, expire - passed, time_ns);
+ return passed;
+}
+
+/*
+ * Helper functions for env variables describing clocks with jiffy granularity
+ */
+static inline u64 ha_get_clk_jiffy(struct ha_monitor *ha_mon, enum envs env)
+{
+ return get_jiffies_64() - READ_ONCE(ha_mon->env_store[env]);
+}
+static inline void ha_reset_clk_jiffy(struct ha_monitor *ha_mon, enum envs env)
+{
+ WRITE_ONCE(ha_mon->env_store[env], get_jiffies_64());
+}
+static inline void ha_set_invariant_jiffy(struct ha_monitor *ha_mon,
+ enum envs env, u64 value)
+{
+ WRITE_ONCE(ha_mon->env_store[env], get_jiffies_64() + value);
+}
+static inline bool ha_check_invariant_jiffy(struct ha_monitor *ha_mon,
+ enum envs env, u64 time_ns)
+{
+ return time_after64(READ_ONCE(ha_mon->env_store[env]), get_jiffies_64());
+
+}
+/*
+ * ha_invariant_passed_jiffy - prepare the invariant and return the time since reset
+ */
+static inline u64 ha_invariant_passed_jiffy(struct ha_monitor *ha_mon, enum envs env,
+ u64 expire, u64 time_ns)
+{
+ u64 passed = 0;
+
+ if (env < 0 || env >= ENV_MAX_STORED)
+ return 0;
+ if (ha_monitor_env_invalid(ha_mon, env))
+ return 0;
+ passed = ha_get_env(ha_mon, env, time_ns);
+ ha_set_invariant_jiffy(ha_mon, env, expire - passed);
+ return passed;
+}
+
+/*
+ * Retrieve the last reset time (guard representation) from the invariant
+ * representation (expiration).
+ * It the caller's responsibility to make sure the storage was actually in the
+ * invariant representation (e.g. the current state has an invariant).
+ * The provided value must be the same used when starting the invariant.
+ *
+ * This function's access to the storage is NOT atomic, due to the rarity when
+ * this is used. If a monitor allows writes concurrent to this, likely
+ * other things are broken and need rethinking the model or additional locking.
+ */
+static inline void ha_inv_to_guard(struct ha_monitor *ha_mon, enum envs env,
+ u64 value, u64 time_ns)
+{
+ WRITE_ONCE(ha_mon->env_store[env], READ_ONCE(ha_mon->env_store[env]) - value);
+}
+
+#if HA_TIMER_TYPE == HA_TIMER_WHEEL
+/*
+ * Helper functions to handle the monitor timer.
+ * Not all monitors require a timer, in such case the timer will be set up but
+ * never armed.
+ * Timers start since the last reset of the supplied env or from now if env is
+ * not an environment variable. If env was not initialised no timer starts.
+ * Timers can expire on any CPU unless the monitor is per-cpu,
+ * where we assume every event occurs on the local CPU.
+ */
+static void ha_monitor_timer_callback(struct timer_list *timer)
+{
+ struct ha_monitor *ha_mon = container_of(timer, struct ha_monitor, timer);
+
+ __ha_monitor_timer_callback(ha_mon);
+}
+static inline void ha_setup_timer(struct ha_monitor *ha_mon)
+{
+ int mode = 0;
+
+ if (RV_MON_TYPE == RV_MON_PER_CPU)
+ mode |= TIMER_PINNED;
+ timer_setup(&ha_mon->timer, ha_monitor_timer_callback, mode);
+}
+static inline void ha_start_timer_jiffy(struct ha_monitor *ha_mon, enum envs env,
+ u64 expire, u64 time_ns)
+{
+ u64 passed = ha_invariant_passed_jiffy(ha_mon, env, expire, time_ns);
+
+ mod_timer(&ha_mon->timer, get_jiffies_64() + expire - passed);
+}
+static inline void ha_start_timer_ns(struct ha_monitor *ha_mon, enum envs env,
+ u64 expire, u64 time_ns)
+{
+ u64 passed = ha_invariant_passed_ns(ha_mon, env, expire, time_ns);
+
+ ha_start_timer_jiffy(ha_mon, ENV_MAX_STORED,
+ nsecs_to_jiffies(expire - passed) + 1, time_ns);
+}
+/*
+ * ha_cancel_timer - Cancel the timer
+ *
+ * Returns:
+ * * 1 when the timer was active
+ * * 0 when the timer was not active or running a callback
+ */
+static inline bool ha_cancel_timer(struct ha_monitor *ha_mon)
+{
+ return timer_delete(&ha_mon->timer);
+}
+#elif HA_TIMER_TYPE == HA_TIMER_HRTIMER
+/*
+ * Helper functions to handle the monitor timer.
+ * Not all monitors require a timer, in such case the timer will be set up but
+ * never armed.
+ * Timers start since the last reset of the supplied env or from now if env is
+ * not an environment variable. If env was not initialised no timer starts.
+ * Timers can expire on any CPU unless the monitor is per-cpu,
+ * where we assume every event occurs on the local CPU.
+ */
+static enum hrtimer_restart ha_monitor_timer_callback(struct hrtimer *hrtimer)
+{
+ struct ha_monitor *ha_mon = container_of(hrtimer, struct ha_monitor, hrtimer);
+
+ __ha_monitor_timer_callback(ha_mon);
+ return HRTIMER_NORESTART;
+}
+static inline void ha_setup_timer(struct ha_monitor *ha_mon)
+{
+ hrtimer_setup(&ha_mon->hrtimer, ha_monitor_timer_callback,
+ CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
+}
+static inline void ha_start_timer_ns(struct ha_monitor *ha_mon, enum envs env,
+ u64 expire, u64 time_ns)
+{
+ int mode = HRTIMER_MODE_REL_HARD;
+ u64 passed = ha_invariant_passed_ns(ha_mon, env, expire, time_ns);
+
+ if (RV_MON_TYPE == RV_MON_PER_CPU)
+ mode |= HRTIMER_MODE_PINNED;
+ hrtimer_start(&ha_mon->hrtimer, ns_to_ktime(expire - passed), mode);
+}
+static inline void ha_start_timer_jiffy(struct ha_monitor *ha_mon, enum envs env,
+ u64 expire, u64 time_ns)
+{
+ u64 passed = ha_invariant_passed_jiffy(ha_mon, env, expire, time_ns);
+
+ ha_start_timer_ns(ha_mon, ENV_MAX_STORED,
+ jiffies_to_nsecs(expire - passed), time_ns);
+}
+/*
+ * ha_cancel_timer - Cancel the timer
+ *
+ * Returns:
+ * * 1 when the timer was active
+ * * 0 when the timer was not active or running a callback
+ */
+static inline bool ha_cancel_timer(struct ha_monitor *ha_mon)
+{
+ return hrtimer_try_to_cancel(&ha_mon->hrtimer) == 1;
+}
+#else //HA_TIMER_NONE
+/*
+ * Start function is intentionally not defined, monitors using timers must
+ * set HA_TIMER_TYPE to either HA_TIMER_WHEEL or HA_TIMER_HRTIMER.
+ */
+static inline void ha_setup_timer(struct ha_monitor *ha_mon) { }
+static inline bool ha_cancel_timer(struct ha_monitor *ha_mon)
+{
+ return false;
+}
+#endif
+
+#endif
diff --git a/kernel/trace/rv/Kconfig b/kernel/trace/rv/Kconfig
index 5b4be87ba59d..4ad392dfc57f 100644
--- a/kernel/trace/rv/Kconfig
+++ b/kernel/trace/rv/Kconfig
@@ -23,6 +23,19 @@ config LTL_MON_EVENTS_ID
config RV_LTL_MONITOR
bool
+config RV_HA_MONITOR
+ bool
+
+config HA_MON_EVENTS_IMPLICIT
+ select DA_MON_EVENTS_IMPLICIT
+ select RV_HA_MONITOR
+ bool
+
+config HA_MON_EVENTS_ID
+ select DA_MON_EVENTS_ID
+ select RV_HA_MONITOR
+ bool
+
menuconfig RV
bool "Runtime Verification"
select TRACING
diff --git a/kernel/trace/rv/rv_trace.h b/kernel/trace/rv/rv_trace.h
index 4a6faddac614..7c598967bc0e 100644
--- a/kernel/trace/rv/rv_trace.h
+++ b/kernel/trace/rv/rv_trace.h
@@ -65,6 +65,36 @@ DECLARE_EVENT_CLASS(error_da_monitor,
#include <monitors/opid/opid_trace.h>
// Add new monitors based on CONFIG_DA_MON_EVENTS_IMPLICIT here
+#ifdef CONFIG_HA_MON_EVENTS_IMPLICIT
+/* For simplicity this class is marked as DA although relevant only for HA */
+DECLARE_EVENT_CLASS(error_env_da_monitor,
+
+ TP_PROTO(char *state, char *event, char *env),
+
+ TP_ARGS(state, event, env),
+
+ TP_STRUCT__entry(
+ __string( state, state )
+ __string( event, event )
+ __string( env, env )
+ ),
+
+ TP_fast_assign(
+ __assign_str(state);
+ __assign_str(event);
+ __assign_str(env);
+ ),
+
+ TP_printk("event %s not expected in the state %s with env %s",
+ __get_str(event),
+ __get_str(state),
+ __get_str(env))
+);
+
+// Add new monitors based on CONFIG_HA_MON_EVENTS_IMPLICIT here
+
+#endif
+
#endif /* CONFIG_DA_MON_EVENTS_IMPLICIT */
#ifdef CONFIG_DA_MON_EVENTS_ID
@@ -128,6 +158,39 @@ DECLARE_EVENT_CLASS(error_da_monitor_id,
#include <monitors/sssw/sssw_trace.h>
// Add new monitors based on CONFIG_DA_MON_EVENTS_ID here
+#ifdef CONFIG_HA_MON_EVENTS_ID
+/* For simplicity this class is marked as DA although relevant only for HA */
+DECLARE_EVENT_CLASS(error_env_da_monitor_id,
+
+ TP_PROTO(int id, char *state, char *event, char *env),
+
+ TP_ARGS(id, state, event, env),
+
+ TP_STRUCT__entry(
+ __field( int, id )
+ __string( state, state )
+ __string( event, event )
+ __string( env, env )
+ ),
+
+ TP_fast_assign(
+ __assign_str(state);
+ __assign_str(event);
+ __assign_str(env);
+ __entry->id = id;
+ ),
+
+ TP_printk("%d: event %s not expected in the state %s with env %s",
+ __entry->id,
+ __get_str(event),
+ __get_str(state),
+ __get_str(env))
+);
+
+// Add new monitors based on CONFIG_HA_MON_EVENTS_ID here
+
+#endif
+
#endif /* CONFIG_DA_MON_EVENTS_ID */
#ifdef CONFIG_LTL_MON_EVENTS_ID
DECLARE_EVENT_CLASS(event_ltl_monitor_id,
--
2.52.0
^ permalink raw reply related
* [PATCH v3 01/13] rv: Unify DA event handling functions across monitor types
From: Gabriele Monaco @ 2025-12-05 13:16 UTC (permalink / raw)
To: linux-kernel, Steven Rostedt, Nam Cao, Gabriele Monaco,
linux-trace-kernel
Cc: Tomas Glozar, Juri Lelli, Clark Williams, John Kacur
In-Reply-To: <20251205131621.135513-1-gmonaco@redhat.com>
The DA event handling functions are mostly duplicated because the
per-task monitors need to propagate the task to use the pid in the trace
events. This is a maintenance burden for a little advantage.
The task can be obtained with some pointer arithmetic from the da_mon,
hence only the function tracing events really need to differ.
Unify all code handling the events, create da_trace_event() and
da_trace_error() that only call the tracepoint function.
Propagate the monitor id through the calls, the do_trace_ functions use
the id (pid) in case of per-task monitors but ignore it for implicit
monitors.
Signed-off-by: Gabriele Monaco <gmonaco@redhat.com>
---
Notes:
V3:
* Rearrange start/handle helpers to share more code
include/rv/da_monitor.h | 303 +++++++++++++++++-----------------------
1 file changed, 132 insertions(+), 171 deletions(-)
diff --git a/include/rv/da_monitor.h b/include/rv/da_monitor.h
index 7b28ef9f73bd..6b564fad8c4d 100644
--- a/include/rv/da_monitor.h
+++ b/include/rv/da_monitor.h
@@ -22,6 +22,13 @@
static struct rv_monitor rv_this;
+/*
+ * Type for the target id, default to int but can be overridden.
+ */
+#ifndef da_id_type
+#define da_id_type int
+#endif
+
static void react(enum states curr_state, enum events event)
{
rv_react(&rv_this,
@@ -91,90 +98,6 @@ static inline bool da_monitor_handling_event(struct da_monitor *da_mon)
return 1;
}
-#if RV_MON_TYPE == RV_MON_GLOBAL || RV_MON_TYPE == RV_MON_PER_CPU
-/*
- * Event handler for implicit monitors. Implicit monitor is the one which the
- * handler does not need to specify which da_monitor to manipulate. Examples
- * of implicit monitor are the per_cpu or the global ones.
- *
- * Retry in case there is a race between getting and setting the next state,
- * warn and reset the monitor if it runs out of retries. The monitor should be
- * able to handle various orders.
- */
-
-static inline bool da_event(struct da_monitor *da_mon, enum events event)
-{
- enum states curr_state, next_state;
-
- curr_state = READ_ONCE(da_mon->curr_state);
- for (int i = 0; i < MAX_DA_RETRY_RACING_EVENTS; i++) {
- next_state = model_get_next_state(curr_state, event);
- if (next_state == INVALID_STATE) {
- react(curr_state, event);
- CONCATENATE(trace_error_, MONITOR_NAME)(
- model_get_state_name(curr_state),
- model_get_event_name(event));
- return false;
- }
- if (likely(try_cmpxchg(&da_mon->curr_state, &curr_state, next_state))) {
- CONCATENATE(trace_event_, MONITOR_NAME)(
- model_get_state_name(curr_state),
- model_get_event_name(event),
- model_get_state_name(next_state),
- model_is_final_state(next_state));
- return true;
- }
- }
-
- trace_rv_retries_error(__stringify(MONITOR_NAME), model_get_event_name(event));
- pr_warn("rv: " __stringify(MAX_DA_RETRY_RACING_EVENTS)
- " retries reached for event %s, resetting monitor %s",
- model_get_event_name(event), __stringify(MONITOR_NAME));
- return false;
-}
-
-#elif RV_MON_TYPE == RV_MON_PER_TASK
-/*
- * Event handler for per_task monitors.
- *
- * Retry in case there is a race between getting and setting the next state,
- * warn and reset the monitor if it runs out of retries. The monitor should be
- * able to handle various orders.
- */
-
-static inline bool da_event(struct da_monitor *da_mon, struct task_struct *tsk,
- enum events event)
-{
- enum states curr_state, next_state;
-
- curr_state = READ_ONCE(da_mon->curr_state);
- for (int i = 0; i < MAX_DA_RETRY_RACING_EVENTS; i++) {
- next_state = model_get_next_state(curr_state, event);
- if (next_state == INVALID_STATE) {
- react(curr_state, event);
- CONCATENATE(trace_error_, MONITOR_NAME)(tsk->pid,
- model_get_state_name(curr_state),
- model_get_event_name(event));
- return false;
- }
- if (likely(try_cmpxchg(&da_mon->curr_state, &curr_state, next_state))) {
- CONCATENATE(trace_event_, MONITOR_NAME)(tsk->pid,
- model_get_state_name(curr_state),
- model_get_event_name(event),
- model_get_state_name(next_state),
- model_is_final_state(next_state));
- return true;
- }
- }
-
- trace_rv_retries_error(__stringify(MONITOR_NAME), model_get_event_name(event));
- pr_warn("rv: " __stringify(MAX_DA_RETRY_RACING_EVENTS)
- " retries reached for event %s, resetting monitor %s",
- model_get_event_name(event), __stringify(MONITOR_NAME));
- return false;
-}
-#endif /* RV_MON_TYPE */
-
#if RV_MON_TYPE == RV_MON_GLOBAL
/*
* Functions to define, init and get a global monitor.
@@ -329,115 +252,179 @@ static inline void da_monitor_destroy(void)
#if RV_MON_TYPE == RV_MON_GLOBAL || RV_MON_TYPE == RV_MON_PER_CPU
/*
- * Handle event for implicit monitor: da_get_monitor() will figure out
- * the monitor.
+ * Trace events for implicit monitors. Implicit monitor is the one which the
+ * handler does not need to specify which da_monitor to manipulate. Examples
+ * of implicit monitor are the per_cpu or the global ones.
*/
-static inline void __da_handle_event(struct da_monitor *da_mon,
- enum events event)
+static inline void da_trace_event(struct da_monitor *da_mon,
+ char *curr_state, char *event,
+ char *next_state, bool is_final,
+ da_id_type id)
{
- bool retval;
+ CONCATENATE(trace_event_, MONITOR_NAME)(curr_state, event, next_state,
+ is_final);
+}
- retval = da_event(da_mon, event);
- if (!retval)
- da_monitor_reset(da_mon);
+static inline void da_trace_error(struct da_monitor *da_mon,
+ char *curr_state, char *event,
+ da_id_type id)
+{
+ CONCATENATE(trace_error_, MONITOR_NAME)(curr_state, event);
}
+#elif RV_MON_TYPE == RV_MON_PER_TASK
/*
- * da_handle_event - handle an event
+ * Trace events for per_task monitors, report the PID of the task.
*/
-static inline void da_handle_event(enum events event)
-{
- struct da_monitor *da_mon = da_get_monitor();
- bool retval;
- retval = da_monitor_handling_event(da_mon);
- if (!retval)
- return;
+static inline void da_trace_event(struct da_monitor *da_mon,
+ char *curr_state, char *event,
+ char *next_state, bool is_final,
+ da_id_type id)
+{
+ CONCATENATE(trace_event_, MONITOR_NAME)(id, curr_state, event,
+ next_state, is_final);
+}
- __da_handle_event(da_mon, event);
+static inline void da_trace_error(struct da_monitor *da_mon,
+ char *curr_state, char *event,
+ da_id_type id)
+{
+ CONCATENATE(trace_error_, MONITOR_NAME)(id, curr_state, event);
}
+#endif /* RV_MON_TYPE */
/*
- * da_handle_start_event - start monitoring or handle event
- *
- * This function is used to notify the monitor that the system is returning
- * to the initial state, so the monitor can start monitoring in the next event.
- * Thus:
+ * da_event - handle an event for the da_mon
*
- * If the monitor already started, handle the event.
- * If the monitor did not start yet, start the monitor but skip the event.
+ * This function is valid for both implicit and id monitors.
+ * Retry in case there is a race between getting and setting the next state,
+ * warn and reset the monitor if it runs out of retries. The monitor should be
+ * able to handle various orders.
*/
-static inline bool da_handle_start_event(enum events event)
+static inline bool da_event(struct da_monitor *da_mon, enum events event, da_id_type id)
{
- struct da_monitor *da_mon;
+ enum states curr_state, next_state;
- if (!da_monitor_enabled())
- return 0;
+ curr_state = READ_ONCE(da_mon->curr_state);
+ for (int i = 0; i < MAX_DA_RETRY_RACING_EVENTS; i++) {
+ next_state = model_get_next_state(curr_state, event);
+ if (next_state == INVALID_STATE) {
+ react(curr_state, event);
+ da_trace_error(da_mon, model_get_state_name(curr_state),
+ model_get_event_name(event), id);
+ return false;
+ }
+ if (likely(try_cmpxchg(&da_mon->curr_state, &curr_state, next_state))) {
+ da_trace_event(da_mon, model_get_state_name(curr_state),
+ model_get_event_name(event),
+ model_get_state_name(next_state),
+ model_is_final_state(next_state), id);
+ return true;
+ }
+ }
+
+ trace_rv_retries_error(__stringify(MONITOR_NAME), model_get_event_name(event));
+ pr_warn("rv: " __stringify(MAX_DA_RETRY_RACING_EVENTS)
+ " retries reached for event %s, resetting monitor %s",
+ model_get_event_name(event), __stringify(MONITOR_NAME));
+ return false;
+}
- da_mon = da_get_monitor();
+static inline void __da_handle_event_common(struct da_monitor *da_mon,
+ enum events event, da_id_type id)
+{
+ if (!da_event(da_mon, event, id))
+ da_monitor_reset(da_mon);
+}
+static inline void __da_handle_event(struct da_monitor *da_mon,
+ enum events event, da_id_type id)
+{
+ if (da_monitor_handling_event(da_mon))
+ __da_handle_event_common(da_mon, event, id);
+}
+
+static inline bool __da_handle_start_event(struct da_monitor *da_mon,
+ enum events event, da_id_type id)
+{
+ if (!da_monitor_enabled())
+ return 0;
if (unlikely(!da_monitoring(da_mon))) {
da_monitor_start(da_mon);
return 0;
}
- __da_handle_event(da_mon, event);
+ __da_handle_event_common(da_mon, event, id);
return 1;
}
-/*
- * da_handle_start_run_event - 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(enum events event)
+static inline bool __da_handle_start_run_event(struct da_monitor *da_mon,
+ enum events event, da_id_type id)
{
- struct da_monitor *da_mon;
-
if (!da_monitor_enabled())
return 0;
-
- da_mon = da_get_monitor();
-
if (unlikely(!da_monitoring(da_mon)))
da_monitor_start(da_mon);
- __da_handle_event(da_mon, event);
+ __da_handle_event_common(da_mon, event, id);
return 1;
}
-#elif RV_MON_TYPE == RV_MON_PER_TASK
+#if RV_MON_TYPE == RV_MON_GLOBAL || RV_MON_TYPE == RV_MON_PER_CPU
/*
- * Handle event for per task.
+ * Handle event for implicit monitor: da_get_monitor() will figure out
+ * the monitor.
*/
-static inline void __da_handle_event(struct da_monitor *da_mon,
- struct task_struct *tsk, enum events event)
+/*
+ * da_handle_event - handle an event
+ */
+static inline void da_handle_event(enum events event)
{
- bool retval;
+ __da_handle_event(da_get_monitor(), event, 0);
+}
- retval = da_event(da_mon, tsk, event);
- if (!retval)
- da_monitor_reset(da_mon);
+/*
+ * da_handle_start_event - start monitoring or handle event
+ *
+ * This function is used to notify the monitor that the system is returning
+ * to the initial state, so the monitor can start monitoring in the next event.
+ * Thus:
+ *
+ * If the monitor already started, handle the event.
+ * If the monitor did not start yet, start the monitor but skip the event.
+ */
+static inline bool da_handle_start_event(enum events event)
+{
+ return __da_handle_start_event(da_get_monitor(), event, 0);
}
/*
- * da_handle_event - handle an event
+ * da_handle_start_run_event - 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 void da_handle_event(struct task_struct *tsk, enum events event)
+static inline bool da_handle_start_run_event(enum events event)
{
- struct da_monitor *da_mon = da_get_monitor(tsk);
- bool retval;
+ return __da_handle_start_run_event(da_get_monitor(), event, 0);
+}
- retval = da_monitor_handling_event(da_mon);
- if (!retval)
- return;
+#elif RV_MON_TYPE == RV_MON_PER_TASK
+/*
+ * Handle event for per task.
+ */
- __da_handle_event(da_mon, tsk, event);
+/*
+ * da_handle_event - handle an event
+ */
+static inline void da_handle_event(struct task_struct *tsk, enum events event)
+{
+ __da_handle_event(da_get_monitor(tsk), event, tsk->pid);
}
/*
@@ -453,21 +440,7 @@ static inline void da_handle_event(struct task_struct *tsk, enum events event)
static inline bool da_handle_start_event(struct task_struct *tsk,
enum events event)
{
- struct da_monitor *da_mon;
-
- if (!da_monitor_enabled())
- return 0;
-
- da_mon = da_get_monitor(tsk);
-
- if (unlikely(!da_monitoring(da_mon))) {
- da_monitor_start(da_mon);
- return 0;
- }
-
- __da_handle_event(da_mon, tsk, event);
-
- return 1;
+ return __da_handle_start_event(da_get_monitor(tsk), event, tsk->pid);
}
/*
@@ -479,19 +452,7 @@ static inline bool da_handle_start_event(struct task_struct *tsk,
static inline bool da_handle_start_run_event(struct task_struct *tsk,
enum events event)
{
- struct da_monitor *da_mon;
-
- if (!da_monitor_enabled())
- return 0;
-
- da_mon = da_get_monitor(tsk);
-
- if (unlikely(!da_monitoring(da_mon)))
- da_monitor_start(da_mon);
-
- __da_handle_event(da_mon, tsk, event);
-
- return 1;
+ return __da_handle_start_run_event(da_get_monitor(tsk), event, tsk->pid);
}
#endif /* RV_MON_TYPE */
--
2.52.0
^ permalink raw reply related
* [PATCH v3 00/13] rv: Add Hybrid Automata monitor type, per-object and deadline monitors
From: Gabriele Monaco @ 2025-12-05 13:16 UTC (permalink / raw)
To: linux-kernel, Steven Rostedt, Nam Cao
Cc: Gabriele Monaco, Tomas Glozar, Juri Lelli, Clark Williams,
John Kacur, linux-trace-kernel
This series contains several related changes, the main areas are:
* hybrid automata
Hybrid automata are an extension of deterministic automata where each
state transition is validating a constraint on a finite number of
environment variables.
Hybrid automata can be used to implement timed automata, where the
environment variables are clocks.
* per-object monitors
Define the generic per-object monitor allow RV monitors on any kind
of object where the user can specify how to get an id (e.g. pid for
tasks) and the data type for the monitor_target (e.g. struct
task_struct * for tasks).
The monitor storage (e.g. the rv monitor, pointer to the target, etc.)
is stored in a hash table indexed by id.
* deadline monitors collection
Add the throttle and nomiss monitors to validate timing aspects of
the deadline scheduler, as they work for tasks and servers, their
inclusion requires also per-object monitors (for dl entities).
Also add the boost and laxity monitors specific to servers.
This series is based on the previously sent [1] that includes
preliminary patches present in V2 [2] and already reviewed. As such this
series is simplified and includes only relevant new changes.
The entire series can also be found on:
git.kernel.org/pub/scm/linux/kernel/git/gmonaco/linux.git rv_hybrid_automata
Changes since V2 [2]:
* Adapt models to new dl server behaviour
* Rearrange start/handle helpers to share more code
* Improve documentation clarity after review
* Extend stall model to handle preemption
* Improve functions naming for HA helpers
* Use kmalloc_nolock for per-obj storage allocation
* Add boost and laxity monitors for deadline servers
* Add _is_id_monitor() in dot2k to handle per-obj together with per-task
* Rename dl argument to dl_se in tracepoints
* Use __COUNTER__ in dl monitor syscall helpers
* Fix conflicts after rebase (cond_react -> rv_react)
* General cleanup
Changes since V1 [3]:
* Cleanup unused trace events definitions
* Improve hybrid automata description about use of timers
* Unify event handler internals across DA monitor types
* Implement timer wheel alternative for invariants
* Extend models to consider timing of task switches (in before deadline,
out after throttle)
* Refactor tracepoints and per-object monitors to allow server events
from remote CPUs
* Changed clock representation in case of invariants (time to expire vs
time since reset) and allow conversion without reset
* Extend dot2k to understand the graph relations and suggest where
invariant conversions are needed
* General cleanup of rvgen scripts
[1] - https://lore.kernel.org/lkml/20251126104241.291258-1-gmonaco@redhat.com
[2] - https://lore.kernel.org/lkml/20250919140954.104920-1-gmonaco@redhat.com
[3] - https://lore.kernel.org/lkml/20250814150809.140739-1-gmonaco@redhat.com
To: Steven Rostedt <rostedt@goodmis.org>
To: Nam Cao <namcao@linutronix.de>
Cc: Tomas Glozar <tglozar@redhat.com>
Cc: Juri Lelli <jlelli@redhat.com>
Cc: Clark Williams <williams@redhat.com>
Cc: John Kacur <jkacur@redhat.com>
Cc: linux-trace-kernel@vger.kernel.org
Gabriele Monaco (13):
rv: Unify DA event handling functions across monitor types
rv: Add Hybrid Automata monitor type
verification/rvgen: Allow spaces in and events strings
verification/rvgen: Add support for Hybrid Automata
Documentation/rv: Add documentation about hybrid automata
rv: Add sample hybrid monitors stall
rv: Convert the opid monitor to a hybrid automaton
sched: Export hidden tracepoints to modules
sched: Add deadline tracepoints
rv: Add support for per-object monitors in DA/HA
verification/rvgen: Add support for per-obj monitors
rv: Add deadline monitors
rv: Add dl_server specific monitors
Documentation/tools/rv/index.rst | 1 +
Documentation/tools/rv/rv-mon-stall.rst | 44 ++
.../trace/rv/deterministic_automata.rst | 2 +-
Documentation/trace/rv/hybrid_automata.rst | 341 +++++++++
Documentation/trace/rv/index.rst | 3 +
Documentation/trace/rv/monitor_deadline.rst | 266 +++++++
Documentation/trace/rv/monitor_sched.rst | 62 +-
Documentation/trace/rv/monitor_stall.rst | 43 ++
Documentation/trace/rv/monitor_synthesis.rst | 117 +++-
include/linux/rv.h | 39 ++
include/rv/da_monitor.h | 654 +++++++++++++-----
include/rv/ha_monitor.h | 479 +++++++++++++
include/trace/events/sched.h | 16 +
kernel/sched/core.c | 7 +
kernel/sched/deadline.c | 7 +
kernel/trace/rv/Kconfig | 21 +
kernel/trace/rv/Makefile | 6 +
kernel/trace/rv/monitors/boost/Kconfig | 15 +
kernel/trace/rv/monitors/boost/boost.c | 279 ++++++++
kernel/trace/rv/monitors/boost/boost.h | 159 +++++
kernel/trace/rv/monitors/boost/boost_trace.h | 19 +
kernel/trace/rv/monitors/deadline/Kconfig | 10 +
kernel/trace/rv/monitors/deadline/deadline.c | 35 +
kernel/trace/rv/monitors/deadline/deadline.h | 203 ++++++
kernel/trace/rv/monitors/laxity/Kconfig | 14 +
kernel/trace/rv/monitors/laxity/laxity.c | 226 ++++++
kernel/trace/rv/monitors/laxity/laxity.h | 126 ++++
.../trace/rv/monitors/laxity/laxity_trace.h | 19 +
kernel/trace/rv/monitors/nomiss/Kconfig | 15 +
kernel/trace/rv/monitors/nomiss/nomiss.c | 289 ++++++++
kernel/trace/rv/monitors/nomiss/nomiss.h | 137 ++++
.../trace/rv/monitors/nomiss/nomiss_trace.h | 19 +
kernel/trace/rv/monitors/opid/Kconfig | 11 +-
kernel/trace/rv/monitors/opid/opid.c | 111 +--
kernel/trace/rv/monitors/opid/opid.h | 86 +--
kernel/trace/rv/monitors/opid/opid_trace.h | 4 +
kernel/trace/rv/monitors/stall/Kconfig | 13 +
kernel/trace/rv/monitors/stall/stall.c | 150 ++++
kernel/trace/rv/monitors/stall/stall.h | 81 +++
kernel/trace/rv/monitors/stall/stall_trace.h | 19 +
kernel/trace/rv/monitors/throttle/Kconfig | 15 +
kernel/trace/rv/monitors/throttle/throttle.c | 248 +++++++
kernel/trace/rv/monitors/throttle/throttle.h | 116 ++++
.../rv/monitors/throttle/throttle_trace.h | 19 +
kernel/trace/rv/rv_trace.h | 70 +-
tools/verification/models/deadline/boost.dot | 51 ++
tools/verification/models/deadline/laxity.dot | 34 +
tools/verification/models/deadline/nomiss.dot | 43 ++
.../verification/models/deadline/throttle.dot | 44 ++
tools/verification/models/sched/opid.dot | 36 +-
tools/verification/models/stall.dot | 22 +
tools/verification/rvgen/__main__.py | 8 +-
tools/verification/rvgen/rvgen/automata.py | 150 +++-
tools/verification/rvgen/rvgen/dot2c.py | 49 ++
tools/verification/rvgen/rvgen/dot2k.py | 488 ++++++++++++-
tools/verification/rvgen/rvgen/generator.py | 4 +-
.../rvgen/rvgen/templates/dot2k/main.c | 2 +-
.../rvgen/templates/dot2k/trace_hybrid.h | 16 +
58 files changed, 5138 insertions(+), 425 deletions(-)
create mode 100644 Documentation/tools/rv/rv-mon-stall.rst
create mode 100644 Documentation/trace/rv/hybrid_automata.rst
create mode 100644 Documentation/trace/rv/monitor_deadline.rst
create mode 100644 Documentation/trace/rv/monitor_stall.rst
create mode 100644 include/rv/ha_monitor.h
create mode 100644 kernel/trace/rv/monitors/boost/Kconfig
create mode 100644 kernel/trace/rv/monitors/boost/boost.c
create mode 100644 kernel/trace/rv/monitors/boost/boost.h
create mode 100644 kernel/trace/rv/monitors/boost/boost_trace.h
create mode 100644 kernel/trace/rv/monitors/deadline/Kconfig
create mode 100644 kernel/trace/rv/monitors/deadline/deadline.c
create mode 100644 kernel/trace/rv/monitors/deadline/deadline.h
create mode 100644 kernel/trace/rv/monitors/laxity/Kconfig
create mode 100644 kernel/trace/rv/monitors/laxity/laxity.c
create mode 100644 kernel/trace/rv/monitors/laxity/laxity.h
create mode 100644 kernel/trace/rv/monitors/laxity/laxity_trace.h
create mode 100644 kernel/trace/rv/monitors/nomiss/Kconfig
create mode 100644 kernel/trace/rv/monitors/nomiss/nomiss.c
create mode 100644 kernel/trace/rv/monitors/nomiss/nomiss.h
create mode 100644 kernel/trace/rv/monitors/nomiss/nomiss_trace.h
create mode 100644 kernel/trace/rv/monitors/stall/Kconfig
create mode 100644 kernel/trace/rv/monitors/stall/stall.c
create mode 100644 kernel/trace/rv/monitors/stall/stall.h
create mode 100644 kernel/trace/rv/monitors/stall/stall_trace.h
create mode 100644 kernel/trace/rv/monitors/throttle/Kconfig
create mode 100644 kernel/trace/rv/monitors/throttle/throttle.c
create mode 100644 kernel/trace/rv/monitors/throttle/throttle.h
create mode 100644 kernel/trace/rv/monitors/throttle/throttle_trace.h
create mode 100644 tools/verification/models/deadline/boost.dot
create mode 100644 tools/verification/models/deadline/laxity.dot
create mode 100644 tools/verification/models/deadline/nomiss.dot
create mode 100644 tools/verification/models/deadline/throttle.dot
create mode 100644 tools/verification/models/stall.dot
create mode 100644 tools/verification/rvgen/rvgen/templates/dot2k/trace_hybrid.h
base-commit: ce91eea7c90fe4ec76c071f6d3cc14e1ce049b30
--
2.52.0
^ permalink raw reply
* Re: [PATCH v2 3/4] kernel.h: move VERIFY_OCTAL_PERMISSIONS() to sysfs.h
From: Petr Pavlu @ 2025-12-05 12:58 UTC (permalink / raw)
To: Yury Norov (NVIDIA)
Cc: Steven Rostedt, Masami Hiramatsu, Mathieu Desnoyers,
Andy Shevchenko, Christophe Leroy, Randy Dunlap, Ingo Molnar,
Jani Nikula, Joonas Lahtinen, David Laight, Andi Shyti,
Rodrigo Vivi, Tvrtko Ursulin, Daniel Gomez, Greg Kroah-Hartman,
Rafael J. Wysocki, Danilo Krummrich, Andrew Morton, linux-kernel,
intel-gfx, dri-devel, linux-modules, linux-trace-kernel
In-Reply-To: <20251203162329.280182-4-yury.norov@gmail.com>
On 12/3/25 5:23 PM, Yury Norov (NVIDIA) wrote:
> The macro is related to sysfs, but is defined in kernel.h. Move it to
> the proper header, and unload the generic kernel.h.
>
> Now that the macro is removed from kernel.h, linux/moduleparam.h is
> decoupled, and kernel.h inclusion can be removed.
>
> Acked-by: Randy Dunlap <rdunlap@infradead.org>
> Tested-by: Randy Dunlap <rdunlap@infradead.org>
> Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
> Signed-off-by: Yury Norov (NVIDIA) <yury.norov@gmail.com>
Reviewed-by: Petr Pavlu <petr.pavlu@suse.com>
--
Thanks,
Petr
^ permalink raw reply
* Re: [PATCH v2 2/4] moduleparam: include required headers explicitly
From: Petr Pavlu @ 2025-12-05 12:51 UTC (permalink / raw)
To: Yury Norov (NVIDIA)
Cc: Steven Rostedt, Masami Hiramatsu, Mathieu Desnoyers,
Andy Shevchenko, Christophe Leroy, Randy Dunlap, Ingo Molnar,
Jani Nikula, Joonas Lahtinen, David Laight, Andi Shyti,
Rodrigo Vivi, Tvrtko Ursulin, Daniel Gomez, Greg Kroah-Hartman,
Rafael J. Wysocki, Danilo Krummrich, Andrew Morton, linux-kernel,
intel-gfx, dri-devel, linux-modules, linux-trace-kernel
In-Reply-To: <20251203162329.280182-3-yury.norov@gmail.com>
On 12/3/25 5:23 PM, Yury Norov (NVIDIA) wrote:
> The following patch drops moduleparam.h dependency on kernel.h. In
> preparation to it, list all the required headers explicitly.
>
> Suggested-by: Petr Pavlu <petr.pavlu@suse.com>
> CC: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
> Signed-off-by: Yury Norov (NVIDIA) <yury.norov@gmail.com>
Reviewed-by: Petr Pavlu <petr.pavlu@suse.com>
--
Thanks,
Petr
^ permalink raw reply
* [PATCH] kprobes: Call check_ftrace_location() on CONFIG_KPROBES_ON_FTRACE
From: qingwei.hu @ 2025-12-05 9:29 UTC (permalink / raw)
To: naveen, davem, mhiramat; +Cc: linux-kernel, linux-trace-kernel, Qingwei Hu
From: Qingwei Hu <qingwei.hu@bytedance.com>
There is a possible configuration dependency:
KPROBES_ON_FTRACE [=n]
^----- KPROBES [=y]
|--- HAVE_KPROBES_ON_FTRACE [=n]
|--- DYNAMIC_FTRACE_WITH_REGS [=n]
^----- FTRACE [=y]
|--- DYNAMIC_FTRACE [=y]
|--- HAVE_DYNAMIC_FTRACE_WITH_REGS [=n]
With DYNAMIC_FTRACE=y, ftrace_location() is meaningful and may
return the same address as the probe target.
However, when KPROBES_ON_FTRACE=n, the current implementation
returns -EINVAL after calling check_ftrace_location(), causing
the validation to fail.
Adjust the logic so that ftrace-based checks are performed only
when CONFIG_KPROBES_ON_FTRACE is enabled, ensuring correct
kprobe behavior even when KPROBES_ON_FTRACE=n.
Signed-off-by: Qingwei Hu <qingwei.hu@bytedance.com>
---
kernel/kprobes.c | 20 +++++++-------------
1 file changed, 7 insertions(+), 13 deletions(-)
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index ab8f9fc1f0d1..f4aa4ba1ca9c 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1512,19 +1512,15 @@ static inline int warn_kprobe_rereg(struct kprobe *p)
return 0;
}
-static int check_ftrace_location(struct kprobe *p)
+#ifdef CONFIG_KPROBES_ON_FTRACE
+static void check_ftrace_location(struct kprobe *p)
{
unsigned long addr = (unsigned long)p->addr;
- if (ftrace_location(addr) == addr) {
-#ifdef CONFIG_KPROBES_ON_FTRACE
+ if (ftrace_location(addr) == addr)
p->flags |= KPROBE_FLAG_FTRACE;
-#else
- return -EINVAL;
-#endif
- }
- return 0;
}
+#endif
static bool is_cfi_preamble_symbol(unsigned long addr)
{
@@ -1540,11 +1536,9 @@ static bool is_cfi_preamble_symbol(unsigned long addr)
static int check_kprobe_address_safe(struct kprobe *p,
struct module **probed_mod)
{
- int ret;
-
- ret = check_ftrace_location(p);
- if (ret)
- return ret;
+#ifdef CONFIG_KPROBES_ON_FTRACE
+ check_ftrace_location(p);
+#endif
guard(jump_label_lock)();
--
2.39.5
^ permalink raw reply related
* Re: [PATCH bpf v4 2/2] selftests/bpf: add regression test for bpf_d_path()
From: Song Liu @ 2025-12-04 23:47 UTC (permalink / raw)
To: Shuran Liu
Cc: mattbobrowski, bpf, ast, daniel, andrii, martin.lau, eddyz87,
yonghong.song, john.fastabend, kpsingh, sdf, haoluo, jolsa,
rostedt, mhiramat, mathieu.desnoyers, linux-kernel,
linux-trace-kernel, dxu, linux-kselftest, shuah
In-Reply-To: <20251204123853.1235-1-electronlsr@gmail.com>
On Thu, Dec 4, 2025 at 4:39 AM Shuran Liu <electronlsr@gmail.com> wrote:
>
> Hi,
>
> I looked into the CI failure and it’s caused by the test assuming
> /tmp is on tmpfs, which is not true in the CI environment, so
> fallocate() fails there. Since /dev/shm is mounted as tmpfs on that
> setup, would it be acceptable to change the test to use a file under
> /dev/shm instead of /tmp?
You can use mkstemp. There are a few examples in prog_tests.
Thanks,
Song
^ permalink raw reply
* Re: [PATCH bpf v3 2/2] selftests/bpf: fix and consolidate d_path LSM regression test
From: Song Liu @ 2025-12-04 21:41 UTC (permalink / raw)
To: Shuran Liu
Cc: andrii, ast, bpf, daniel, dxu, eddyz87, ftyg, gplhust955, haoluo,
haoran.ni.cs, john.fastabend, jolsa, kpsingh, linux-kernel,
linux-kselftest, linux-trace-kernel, martin.lau,
mathieu.desnoyers, mattbobrowski, mhiramat, rostedt, sdf, shuah,
yonghong.song
In-Reply-To: <20251204043424.7512-1-electronlsr@gmail.com>
On Wed, Dec 3, 2025 at 8:34 PM Shuran Liu <electronlsr@gmail.com> wrote:
>
> Hi Song,
>
> Thanks for the review.
>
> > I don't get why we add this selftest here. It doesn't appear to be related to
> > patch 1/2.
>
> The regression that patch 1/2 fixes was originally hit by an LSM program
> calling bpf_d_path() from the bprm_check_security hook. The new subtest is a
> minimal reproducer for that scenario: without patch 1/2 the string comparison
> never matches due to verifier's faulty optimization, and with patch 1/2 it
> behaves correctly.
I somehow didn't reproduce this in my local tests. Thanks for the explanation.
Song
^ permalink raw reply
* [PATCH] tracing: Fix fixed array of synthetic event
From: Steven Rostedt @ 2025-12-04 20:19 UTC (permalink / raw)
To: LKML, Linux Trace Kernel
Cc: Masami Hiramatsu, Mathieu Desnoyers, Douglas Raillard
From: Steven Rostedt <rostedt@goodmis.org>
The commit 4d38328eb442d ("tracing: Fix synth event printk format for str
fields") replaced "%.*s" with "%s" but missed removing the number size of
the dynamic and static strings. The commit e1a453a57bc7 ("tracing: Do not
add length to print format in synthetic events") fixed the dynamic part
but did not fix the static part. That is, with the commands:
# echo 's:wake_lat char[] wakee; u64 delta;' >> /sys/kernel/tracing/dynamic_events
# echo 'hist:keys=pid:ts=common_timestamp.usecs if !(common_flags & 0x18)' > /sys/kernel/tracing/events/sched/sched_waking/trigger
# echo 'hist:keys=next_pid:delta=common_timestamp.usecs-$ts:onmatch(sched.sched_waking).trace(wake_lat,next_comm,$delta)' > /sys/kernel/tracing/events/sched/sched_switch/trigger
That caused the output of:
<idle>-0 [001] d..5. 193.428167: wake_lat: wakee=(efault)sshd-sessiondelta=155
sshd-session-879 [001] d..5. 193.811080: wake_lat: wakee=(efault)kworker/u34:5delta=58
<idle>-0 [002] d..5. 193.811198: wake_lat: wakee=(efault)bashdelta=91
The commit e1a453a57bc7 fixed the part where the synthetic event had
"char[] wakee". But if one were to replace that with a static size string:
# echo 's:wake_lat char[16] wakee; u64 delta;' >> /sys/kernel/tracing/dynamic_events
Where "wakee" is defined as "char[16]" and not "char[]" making it a static
size, the code triggered the "(efaul)" again.
Remove the added STR_VAR_LEN_MAX size as the string is still going to be
nul terminated.
Cc: stable@vger.kernel.org
Fixes: e1a453a57bc7 ("tracing: Do not add length to print format in synthetic events")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
kernel/trace/trace_events_synth.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index 2f19bbe73d27..4554c458b78c 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -375,7 +375,6 @@ static enum print_line_t print_synth_event(struct trace_iterator *iter,
n_u64++;
} else {
trace_seq_printf(s, print_fmt, se->fields[i]->name,
- STR_VAR_LEN_MAX,
(char *)&entry->fields[n_u64].as_u64,
i == se->n_fields - 1 ? "" : " ");
n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
--
2.51.0
^ permalink raw reply related
* Re: [PATCH v3 1/2] cpufreq: Replace trace_cpu_frequency with trace_policy_frequency
From: Steven Rostedt @ 2025-12-04 18:47 UTC (permalink / raw)
To: srinivas pandruvada
Cc: Rafael J. Wysocki, Christian Loehle, Samuel Wu, Huang Rui,
Gautham R. Shenoy, Mario Limonciello, Perry Yuan, Jonathan Corbet,
Viresh Kumar, Masami Hiramatsu, Mathieu Desnoyers, Len Brown,
Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko,
Martin KaFai Lau, Eduard Zingerman, Song Liu, Yonghong Song,
John Fastabend, KP Singh, Stanislav Fomichev, Hao Luo, Jiri Olsa,
Peter Zijlstra, Ingo Molnar, Arnaldo Carvalho de Melo,
Namhyung Kim, Mark Rutland, Alexander Shishkin, Ian Rogers,
Adrian Hunter, James Clark, kernel-team, linux-pm, linux-doc,
linux-kernel, linux-trace-kernel, bpf, linux-perf-users
In-Reply-To: <2b31224a6cf361a5d2859c84aa1bcdf52916423e.camel@linux.intel.com>
On Thu, 04 Dec 2025 09:21:13 -0800
srinivas pandruvada <srinivas.pandruvada@linux.intel.com> wrote:
> We have tools using tracing. We may need to check those tools.
>
> https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git/tree/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py?h=next-20251204
I only see this using pstate_sample event.
> https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git/tree/tools/power/x86/amd_pstate_tracer/amd_pstate_trace.py?h=next-20251204
I only see this using amd_cpu event.
-- Steve
^ permalink raw reply
* Re: [PATCH v3 1/2] cpufreq: Replace trace_cpu_frequency with trace_policy_frequency
From: Steven Rostedt @ 2025-12-04 18:46 UTC (permalink / raw)
To: Rafael J. Wysocki
Cc: Christian Loehle, Samuel Wu, Huang Rui, Gautham R. Shenoy,
Mario Limonciello, Perry Yuan, Jonathan Corbet, Viresh Kumar,
Masami Hiramatsu, Mathieu Desnoyers, Srinivas Pandruvada,
Len Brown, Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko,
Martin KaFai Lau, Eduard Zingerman, Song Liu, Yonghong Song,
John Fastabend, KP Singh, Stanislav Fomichev, Hao Luo, Jiri Olsa,
Peter Zijlstra, Ingo Molnar, Arnaldo Carvalho de Melo,
Namhyung Kim, Mark Rutland, Alexander Shishkin, Ian Rogers,
Adrian Hunter, James Clark, kernel-team, linux-pm, linux-doc,
linux-kernel, linux-trace-kernel, bpf, linux-perf-users
In-Reply-To: <CAJZ5v0irO1zmh=un+8vDQ8h2k-sHFTpCPCwr=iVRPcozHMRKHA@mail.gmail.com>
On Thu, 4 Dec 2025 18:24:57 +0100
"Rafael J. Wysocki" <rafael@kernel.org> wrote:
> > I'm not exactly sure what you mean here. There is an "onchange" trigger you
> > can use to trigger a synthetic event whenever a change happens. But I think
> > the data here wants to know which CPU had its policy change. Hence the CPU
> > mask.
>
> IIUC he wants to trace frequency changes per policy, not per CPU
> (because there are cases in which multiple CPUs belong to one policy
> and arguably the frequency doesn't need to be traced for all of them),
> but tooling should know which CPUs belong to the same policy, so it
> should be straightforward to use that knowledge when processing the
> traces.
In case you only care about frequency changes, you could do this:
# echo 'freq_change u32 state;' > /sys/kernel/tracing/synthetic_events
# echo 'hist:keys=common_type:s=state:onchange($s).trace(freq_change,$s)' > /sys/kernel/tracing/events/power/cpu_frequency/trigger
# echo 1 > /sys/kernel/tracing/events/synthetic/freq_change/enable
# cat /sys/kernel/tracing/trace
# tracer: nop
#
# entries-in-buffer/entries-written: 2833/2833 #P:56
#
# _-----=> irqs-off/BH-disabled
# / _----=> need-resched
# | / _---=> hardirq/softirq
# || / _--=> preempt-depth
# ||| / _-=> migrate-disable
# |||| / delay
# TASK-PID CPU# ||||| TIMESTAMP FUNCTION
# | | | ||||| | |
sed-596089 [034] d..5. 2687140.288806: freq_change: state=2000000
bash-596090 [020] d.s4. 2687140.290407: freq_change: state=1900000
<idle>-0 [028] d.s7. 2687140.290425: freq_change: state=3000000
bash-596090 [020] d..5. 2687140.291152: freq_change: state=1900000
<idle>-0 [000] dNs5. 2687140.326526: freq_change: state=1200000
CPU 3/KVM-10724 [019] d.s5. 2687140.358418: freq_change: state=2100000
CPU 6/KVM-10727 [021] d.h5. 2687140.394403: freq_change: state=1300000
CPU 6/KVM-10727 [021] d.h5. 2687140.398403: freq_change: state=1400000
CPU 6/KVM-10727 [021] d.h5. 2687140.402402: freq_change: state=1500000
CPU 6/KVM-10727 [021] d.h5. 2687140.406400: freq_change: state=1600000
CPU 6/KVM-10727 [021] d.h5. 2687140.410404: freq_change: state=1700000
[..]
Which BTW, I'll be giving a talk about synthetic events at OSS in Tokyo ;-)
(cheap plug!)
https://ossjapan2025.sched.com/event/29FoB/synthetic-events-and-tracing-latency-within-the-kernel-steven-rostedt-google?iframe=yes&w=100%&sidebar=yes&bg=no
-- Steve
^ permalink raw reply
* Re: [PATCH v3 1/2] cpufreq: Replace trace_cpu_frequency with trace_policy_frequency
From: Rafael J. Wysocki @ 2025-12-04 17:24 UTC (permalink / raw)
To: Steven Rostedt
Cc: Rafael J. Wysocki, Christian Loehle, Samuel Wu, Huang Rui,
Gautham R. Shenoy, Mario Limonciello, Perry Yuan, Jonathan Corbet,
Viresh Kumar, Masami Hiramatsu, Mathieu Desnoyers,
Srinivas Pandruvada, Len Brown, Alexei Starovoitov,
Daniel Borkmann, Andrii Nakryiko, Martin KaFai Lau,
Eduard Zingerman, Song Liu, Yonghong Song, John Fastabend,
KP Singh, Stanislav Fomichev, Hao Luo, Jiri Olsa, Peter Zijlstra,
Ingo Molnar, Arnaldo Carvalho de Melo, Namhyung Kim, Mark Rutland,
Alexander Shishkin, Ian Rogers, Adrian Hunter, James Clark,
kernel-team, linux-pm, linux-doc, linux-kernel,
linux-trace-kernel, bpf, linux-perf-users
In-Reply-To: <20251204114844.54953b01@gandalf.local.home>
On Thu, Dec 4, 2025 at 5:48 PM Steven Rostedt <rostedt@goodmis.org> wrote:
>
> On Thu, 4 Dec 2025 15:57:41 +0100
> "Rafael J. Wysocki" <rafael@kernel.org> wrote:
>
> > > perf timechart seem to do per-CPU reporting though?
> > > So this is broken by not emitting an event per-CPU? At least with a simple s/cpu_frequency/policy_frequency/
> > > like here.
> > > Similar for the bpf samples technically...
> >
> > This kind of boils down to whether or not tracepoints can be regarded
> > as ABI and to what extent.
>
> They are an ABI and they are not an ABI. It really boils down to "if you
> break the ABI but no user space notices, did you really break the ABI?" the
> answer is "no". But if user space notices, then yes you did. But it is
> possible to still fix user space (I did this with powertop).
My concern is that the patch effectively removes one trace point
(cpu_frequency) and adds another one with a different format
(policy_frequency), updates one utility in the kernel tree and expects
everyone else to somehow know that they should switch over.
I know about at least several people who have their own scripts using
this tracepoint though.
> >
> > In this particular case, I'm not sure I agree with the stated motivation.
> >
> > First of all, on systems with one CPU per cpufreq policy (the vast
> > majority of x86, including AMD, and the ARM systems using the CPPC
> > driver AFAICS), the "issue" at hand is actually a non-issue and
> > changing the name of the tracepoint alone would confuse things in user
> > space IIUC. Those need to work the way they do today.
>
> If the way the tracepoint changes, it's best to change the name too.
> Tooling can check to see which name is available to determine how to
> process the traces.
If it is updated to do so, yes, but in the meantime?
> >
> > On systems with multiple CPUs per cpufreq policy there is some extra
> > overhead related to the cpu_frequency tracepoint, but the if someone
> > is only interested in the "policy" frequency, they can filter out all
> > CPUs belonging to the same policy except for one from the traces,
> > don't they?
>
> I'm not exactly sure what you mean here. There is an "onchange" trigger you
> can use to trigger a synthetic event whenever a change happens. But I think
> the data here wants to know which CPU had its policy change. Hence the CPU
> mask.
IIUC he wants to trace frequency changes per policy, not per CPU
(because there are cases in which multiple CPUs belong to one policy
and arguably the frequency doesn't need to be traced for all of them),
but tooling should know which CPUs belong to the same policy, so it
should be straightforward to use that knowledge when processing the
traces.
^ permalink raw reply
* Re: [PATCH v3 1/2] cpufreq: Replace trace_cpu_frequency with trace_policy_frequency
From: srinivas pandruvada @ 2025-12-04 17:21 UTC (permalink / raw)
To: Rafael J. Wysocki, Christian Loehle
Cc: Samuel Wu, Huang Rui, Gautham R. Shenoy, Mario Limonciello,
Perry Yuan, Jonathan Corbet, Viresh Kumar, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Len Brown,
Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko,
Martin KaFai Lau, Eduard Zingerman, Song Liu, Yonghong Song,
John Fastabend, KP Singh, Stanislav Fomichev, Hao Luo, Jiri Olsa,
Peter Zijlstra, Ingo Molnar, Arnaldo Carvalho de Melo,
Namhyung Kim, Mark Rutland, Alexander Shishkin, Ian Rogers,
Adrian Hunter, James Clark, kernel-team, linux-pm, linux-doc,
linux-kernel, linux-trace-kernel, bpf, linux-perf-users
In-Reply-To: <CAJZ5v0hAmgjozeX0egBs_ii_zzKXGPsPBUWwmGD+23KD++Rzqw@mail.gmail.com>
On Thu, 2025-12-04 at 15:57 +0100, Rafael J. Wysocki wrote:
> On Thu, Dec 4, 2025 at 1:49 PM Christian Loehle
> <christian.loehle@arm.com> wrote:
> >
> > On 12/1/25 20:24, Samuel Wu wrote:
> > > The existing cpu_frequency trace_event can be verbose, emitting a
> > > nearly
> > > identical trace event for every CPU in the policy even when their
> > > frequencies are identical.
> > >
> > > This patch replaces the cpu_frequency trace event with
> > > policy_frequency
> > > trace event, a more efficient alternative. From the kernel's
> > > perspective, emitting a trace event once per policy instead of
> > > once per
> > > cpu saves some memory and is less overhead. From the post-
> > > processing
> > > perspective, analysis of the trace log is simplified without any
> > > loss of
> > > information.
> > >
> > > Signed-off-by: Samuel Wu <wusamuel@google.com>
> > > ---
> > > drivers/cpufreq/cpufreq.c | 14 ++------------
> > > drivers/cpufreq/intel_pstate.c | 6 ++++--
> > > include/trace/events/power.h | 24 +++++++++++++++++++++---
> > > kernel/trace/power-traces.c | 2 +-
> > > samples/bpf/cpustat_kern.c | 8 ++++----
> > > samples/bpf/cpustat_user.c | 6 +++---
> > > tools/perf/builtin-timechart.c | 12 ++++++------
> > > 7 files changed, 41 insertions(+), 31 deletions(-)
> > >
> > > diff --git a/drivers/cpufreq/cpufreq.c
> > > b/drivers/cpufreq/cpufreq.c
> > > index 4472bb1ec83c..dd3f08f3b958 100644
> > > --- a/drivers/cpufreq/cpufreq.c
> > > +++ b/drivers/cpufreq/cpufreq.c
> > > @@ -309,8 +309,6 @@ static void cpufreq_notify_transition(struct
> > > cpufreq_policy *policy,
> > > struct cpufreq_freqs *freqs,
> > > unsigned int state)
> > > {
> > > - int cpu;
> > > -
> > > BUG_ON(irqs_disabled());
> > >
> > > if (cpufreq_disabled())
> > > @@ -344,10 +342,7 @@ static void cpufreq_notify_transition(struct
> > > cpufreq_policy *policy,
> > > adjust_jiffies(CPUFREQ_POSTCHANGE, freqs);
> > > pr_debug("FREQ: %u - CPUs: %*pbl\n", freqs->new,
> > > cpumask_pr_args(policy->cpus));
> > > -
> > > - for_each_cpu(cpu, policy->cpus)
> > > - trace_cpu_frequency(freqs->new, cpu);
> > > -
> > > + trace_policy_frequency(freqs->new, policy->cpu,
> > > policy->cpus);
> > >
> > > srcu_notifier_call_chain(&cpufreq_transition_notifier_list,
> > > CPUFREQ_POSTCHANGE,
> > > freqs);
> > >
> > > @@ -2201,7 +2196,6 @@ unsigned int
> > > cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
> > > unsigned int target_freq)
> > > {
> > > unsigned int freq;
> > > - int cpu;
> > >
> > > target_freq = clamp_val(target_freq, policy->min, policy-
> > > >max);
> > > freq = cpufreq_driver->fast_switch(policy, target_freq);
> > > @@ -2213,11 +2207,7 @@ unsigned int
> > > cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
> > > arch_set_freq_scale(policy->related_cpus, freq,
> > > arch_scale_freq_ref(policy->cpu));
> > > cpufreq_stats_record_transition(policy, freq);
> > > -
> > > - if (trace_cpu_frequency_enabled()) {
> > > - for_each_cpu(cpu, policy->cpus)
> > > - trace_cpu_frequency(freq, cpu);
> > > - }
> > > + trace_policy_frequency(freq, policy->cpu, policy->cpus);
> > >
> > > return freq;
> > > }
> > > diff --git a/drivers/cpufreq/intel_pstate.c
> > > b/drivers/cpufreq/intel_pstate.c
> > > index ec4abe374573..9724b5d19d83 100644
> > > --- a/drivers/cpufreq/intel_pstate.c
> > > +++ b/drivers/cpufreq/intel_pstate.c
> > > @@ -2297,7 +2297,8 @@ static int hwp_get_cpu_scaling(int cpu)
> > >
> > > static void intel_pstate_set_pstate(struct cpudata *cpu, int
> > > pstate)
> > > {
> > > - trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu-
> > > >cpu);
> > > + trace_policy_frequency(pstate * cpu->pstate.scaling, cpu-
> > > >cpu,
> > > + cpumask_of(cpu->cpu));
> > > cpu->pstate.current_pstate = pstate;
> > > /*
> > > * Generally, there is no guarantee that this code will
> > > always run on
> > > @@ -2587,7 +2588,8 @@ static void
> > > intel_pstate_adjust_pstate(struct cpudata *cpu)
> > >
> > > target_pstate = get_target_pstate(cpu);
> > > target_pstate = intel_pstate_prepare_request(cpu,
> > > target_pstate);
> > > - trace_cpu_frequency(target_pstate * cpu->pstate.scaling,
> > > cpu->cpu);
> > > + trace_policy_frequency(target_pstate * cpu->pstate.scaling,
> > > cpu->cpu,
> > > + cpumask_of(cpu->cpu));
> > > intel_pstate_update_pstate(cpu, target_pstate);
> > >
> > > sample = &cpu->sample;
> > > diff --git a/include/trace/events/power.h
> > > b/include/trace/events/power.h
> > > index 370f8df2fdb4..317098ffdd5f 100644
> > > --- a/include/trace/events/power.h
> > > +++ b/include/trace/events/power.h
> > > @@ -182,11 +182,29 @@ TRACE_EVENT(pstate_sample,
> > > { PM_EVENT_RECOVER, "recover" }, \
> > > { PM_EVENT_POWEROFF, "poweroff" })
> > >
> > > -DEFINE_EVENT(cpu, cpu_frequency,
> > > +TRACE_EVENT(policy_frequency,
> > >
> > > - TP_PROTO(unsigned int frequency, unsigned int cpu_id),
> > > + TP_PROTO(unsigned int frequency, unsigned int cpu_id,
> > > + const struct cpumask *policy_cpus),
> > >
> > > - TP_ARGS(frequency, cpu_id)
> > > + TP_ARGS(frequency, cpu_id, policy_cpus),
> > > +
> > > + TP_STRUCT__entry(
> > > + __field(u32, state)
> > > + __field(u32, cpu_id)
> > > + __cpumask(cpumask)
> > > + ),
> > > +
> > > + TP_fast_assign(
> > > + __entry->state = frequency;
> > > + __entry->cpu_id = cpu_id;
> > > + __assign_cpumask(cpumask, policy_cpus);
> > > + ),
> > > +
> > > + TP_printk("state=%lu cpu_id=%lu policy_cpus=%*pb",
> > > + (unsigned long)__entry->state,
> > > + (unsigned long)__entry->cpu_id,
> > > + cpumask_pr_args((struct cpumask
> > > *)__get_dynamic_array(cpumask)))
> > > );
> > >
> > > TRACE_EVENT(cpu_frequency_limits,
> > > diff --git a/kernel/trace/power-traces.c b/kernel/trace/power-
> > > traces.c
> > > index f2fe33573e54..a537e68a6878 100644
> > > --- a/kernel/trace/power-traces.c
> > > +++ b/kernel/trace/power-traces.c
> > > @@ -16,5 +16,5 @@
> > >
> > > EXPORT_TRACEPOINT_SYMBOL_GPL(suspend_resume);
> > > EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_idle);
> > > -EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_frequency);
> > > +EXPORT_TRACEPOINT_SYMBOL_GPL(policy_frequency);
> > >
> > > diff --git a/samples/bpf/cpustat_kern.c
> > > b/samples/bpf/cpustat_kern.c
> > > index 7ec7143e2757..f485de0f89b2 100644
> > > --- a/samples/bpf/cpustat_kern.c
> > > +++ b/samples/bpf/cpustat_kern.c
> > > @@ -75,9 +75,9 @@ struct {
> > > } pstate_duration SEC(".maps");
> > >
> > > /*
> > > - * The trace events for cpu_idle and cpu_frequency are taken
> > > from:
> > > + * The trace events for cpu_idle and policy_frequency are taken
> > > from:
> > > * /sys/kernel/tracing/events/power/cpu_idle/format
> > > - * /sys/kernel/tracing/events/power/cpu_frequency/format
> > > + * /sys/kernel/tracing/events/power/policy_frequency/format
> > > *
> > > * These two events have same format, so define one common
> > > structure.
> > > */
> > > @@ -162,7 +162,7 @@ int bpf_prog1(struct cpu_args *ctx)
> > > */
> > > if (ctx->state != (u32)-1) {
> > >
> > > - /* record pstate after have first cpu_frequency
> > > event */
> > > + /* record pstate after have first policy_frequency
> > > event */
> > > if (!*pts)
> > > return 0;
> > >
> > > @@ -208,7 +208,7 @@ int bpf_prog1(struct cpu_args *ctx)
> > > return 0;
> > > }
> > >
> > > -SEC("tracepoint/power/cpu_frequency")
> > > +SEC("tracepoint/power/policy_frequency")
> > > int bpf_prog2(struct cpu_args *ctx)
> > > {
> > > u64 *pts, *cstate, *pstate, cur_ts, delta;
> > > diff --git a/samples/bpf/cpustat_user.c
> > > b/samples/bpf/cpustat_user.c
> > > index 356f756cba0d..f7e81f702358 100644
> > > --- a/samples/bpf/cpustat_user.c
> > > +++ b/samples/bpf/cpustat_user.c
> > > @@ -143,12 +143,12 @@ static int
> > > cpu_stat_inject_cpu_idle_event(void)
> > >
> > > /*
> > > * It's possible to have no any frequency change for long time
> > > and cannot
> > > - * get ftrace event 'trace_cpu_frequency' for long period, this
> > > introduces
> > > + * get ftrace event 'trace_policy_frequency' for long period,
> > > this introduces
> > > * big deviation for pstate statistics.
> > > *
> > > * To solve this issue, below code forces to set
> > > 'scaling_max_freq' to 208MHz
> > > - * for triggering ftrace event 'trace_cpu_frequency' and then
> > > recovery back to
> > > - * the maximum frequency value 1.2GHz.
> > > + * for triggering ftrace event 'trace_policy_frequency' and then
> > > recovery back
> > > + * to the maximum frequency value 1.2GHz.
> > > */
> > > static int cpu_stat_inject_cpu_frequency_event(void)
> > > {
> > > diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-
> > > timechart.c
> > > index 22050c640dfa..3ef1a2fd0493 100644
> > > --- a/tools/perf/builtin-timechart.c
> > > +++ b/tools/perf/builtin-timechart.c
> > > @@ -612,10 +612,10 @@ process_sample_cpu_idle(struct timechart
> > > *tchart __maybe_unused,
> > > }
> > >
> > > static int
> > > -process_sample_cpu_frequency(struct timechart *tchart,
> > > - struct evsel *evsel,
> > > - struct perf_sample *sample,
> > > - const char *backtrace __maybe_unused)
> > > +process_sample_policy_frequency(struct timechart *tchart,
> > > + struct evsel *evsel,
> > > + struct perf_sample *sample,
> > > + const char *backtrace
> > > __maybe_unused)
> > > {
> > > u32 state = evsel__intval(evsel, sample, "state");
> > > u32 cpu_id = evsel__intval(evsel, sample, "cpu_id");
> > > @@ -1541,7 +1541,7 @@ static int __cmd_timechart(struct timechart
> > > *tchart, const char *output_name)
> > > {
> > > const struct evsel_str_handler power_tracepoints[] = {
> > > { "power:cpu_idle",
> > > process_sample_cpu_idle },
> > > - { "power:cpu_frequency",
> > > process_sample_cpu_frequency },
> > > + { "power:policy_frequency",
> > > process_sample_policy_frequency },
> > > { "sched:sched_wakeup",
> > > process_sample_sched_wakeup },
> > > { "sched:sched_switch",
> > > process_sample_sched_switch },
> > > #ifdef SUPPORT_OLD_POWER_EVENTS
> > > @@ -1804,7 +1804,7 @@ static int timechart__record(struct
> > > timechart *tchart, int argc, const char **ar
> > > unsigned int backtrace_args_no =
> > > ARRAY_SIZE(backtrace_args);
> > >
> > > const char * const power_args[] = {
> > > - "-e", "power:cpu_frequency",
> > > + "-e", "power:policy_frequency",
> > > "-e", "power:cpu_idle",
> > > };
> > > unsigned int power_args_nr = ARRAY_SIZE(power_args);
> >
> > perf timechart seem to do per-CPU reporting though?
> > So this is broken by not emitting an event per-CPU? At least with a
> > simple s/cpu_frequency/policy_frequency/
> > like here.
> > Similar for the bpf samples technically...
>
> This kind of boils down to whether or not tracepoints can be regarded
> as ABI and to what extent.
>
We have tools using tracing. We may need to check those tools.
https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git/tree/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py?h=next-20251204
https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git/tree/tools/power/x86/amd_pstate_tracer/amd_pstate_trace.py?h=next-20251204
Thanks,
Srinivas
> In this particular case, I'm not sure I agree with the stated
> motivation.
>
> First of all, on systems with one CPU per cpufreq policy (the vast
> majority of x86, including AMD, and the ARM systems using the CPPC
> driver AFAICS), the "issue" at hand is actually a non-issue and
> changing the name of the tracepoint alone would confuse things in
> user
> space IIUC. Those need to work the way they do today.
>
> On systems with multiple CPUs per cpufreq policy there is some extra
> overhead related to the cpu_frequency tracepoint, but the if someone
> is only interested in the "policy" frequency, they can filter out all
> CPUs belonging to the same policy except for one from the traces,
> don't they?
^ permalink raw reply
* Re: [PATCH v3 1/2] cpufreq: Replace trace_cpu_frequency with trace_policy_frequency
From: Steven Rostedt @ 2025-12-04 16:48 UTC (permalink / raw)
To: Rafael J. Wysocki
Cc: Christian Loehle, Samuel Wu, Huang Rui, Gautham R. Shenoy,
Mario Limonciello, Perry Yuan, Jonathan Corbet, Viresh Kumar,
Masami Hiramatsu, Mathieu Desnoyers, Srinivas Pandruvada,
Len Brown, Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko,
Martin KaFai Lau, Eduard Zingerman, Song Liu, Yonghong Song,
John Fastabend, KP Singh, Stanislav Fomichev, Hao Luo, Jiri Olsa,
Peter Zijlstra, Ingo Molnar, Arnaldo Carvalho de Melo,
Namhyung Kim, Mark Rutland, Alexander Shishkin, Ian Rogers,
Adrian Hunter, James Clark, kernel-team, linux-pm, linux-doc,
linux-kernel, linux-trace-kernel, bpf, linux-perf-users
In-Reply-To: <CAJZ5v0hAmgjozeX0egBs_ii_zzKXGPsPBUWwmGD+23KD++Rzqw@mail.gmail.com>
On Thu, 4 Dec 2025 15:57:41 +0100
"Rafael J. Wysocki" <rafael@kernel.org> wrote:
> > perf timechart seem to do per-CPU reporting though?
> > So this is broken by not emitting an event per-CPU? At least with a simple s/cpu_frequency/policy_frequency/
> > like here.
> > Similar for the bpf samples technically...
>
> This kind of boils down to whether or not tracepoints can be regarded
> as ABI and to what extent.
They are an ABI and they are not an ABI. It really boils down to "if you
break the ABI but no user space notices, did you really break the ABI?" the
answer is "no". But if user space notices, then yes you did. But it is
possible to still fix user space (I did this with powertop).
>
> In this particular case, I'm not sure I agree with the stated motivation.
>
> First of all, on systems with one CPU per cpufreq policy (the vast
> majority of x86, including AMD, and the ARM systems using the CPPC
> driver AFAICS), the "issue" at hand is actually a non-issue and
> changing the name of the tracepoint alone would confuse things in user
> space IIUC. Those need to work the way they do today.
If the way the tracepoint changes, it's best to change the name too.
Tooling can check to see which name is available to determine how to
process the traces.
>
> On systems with multiple CPUs per cpufreq policy there is some extra
> overhead related to the cpu_frequency tracepoint, but the if someone
> is only interested in the "policy" frequency, they can filter out all
> CPUs belonging to the same policy except for one from the traces,
> don't they?
I'm not exactly sure what you mean here. There is an "onchange" trigger you
can use to trigger a synthetic event whenever a change happens. But I think
the data here wants to know which CPU had its policy change. Hence the CPU
mask.
-- Steve
^ permalink raw reply
* Re: [PATCH v3] Documentation/rv: Fix dead link to monitor_synthesis.rst
From: Steven Rostedt @ 2025-12-04 15:14 UTC (permalink / raw)
To: Gabriele Monaco
Cc: Soham Metha, linux-kernel-mentees, shuah, skhan, namcao,
mathieu.desnoyers, mhiramat, bagasdotme, linux-kernel,
Jonathan Corbet, linux-trace-kernel, linux-doc
In-Reply-To: <a34546391cc59f9f880ec271292ac201292bac61.camel@redhat.com>
On Thu, 04 Dec 2025 07:36:57 +0100
Gabriele Monaco <gmonaco@redhat.com> wrote:
> Anyway looks good to me.
>
> Acked-by: Gabriele Monaco <gmonaco@redhat.com>
Jon,
Care to take this through your tree? Gabriele is the maintainer of this
code.
-- Steve
^ permalink raw reply
* Re: [PATCH v3 1/2] cpufreq: Replace trace_cpu_frequency with trace_policy_frequency
From: Rafael J. Wysocki @ 2025-12-04 14:57 UTC (permalink / raw)
To: Christian Loehle
Cc: Samuel Wu, Huang Rui, Gautham R. Shenoy, Mario Limonciello,
Perry Yuan, Jonathan Corbet, Rafael J. Wysocki, Viresh Kumar,
Steven Rostedt, Masami Hiramatsu, Mathieu Desnoyers,
Srinivas Pandruvada, Len Brown, Alexei Starovoitov,
Daniel Borkmann, Andrii Nakryiko, Martin KaFai Lau,
Eduard Zingerman, Song Liu, Yonghong Song, John Fastabend,
KP Singh, Stanislav Fomichev, Hao Luo, Jiri Olsa, Peter Zijlstra,
Ingo Molnar, Arnaldo Carvalho de Melo, Namhyung Kim, Mark Rutland,
Alexander Shishkin, Ian Rogers, Adrian Hunter, James Clark,
kernel-team, linux-pm, linux-doc, linux-kernel,
linux-trace-kernel, bpf, linux-perf-users
In-Reply-To: <f28577c1-ca95-43ca-b179-32e2cd46d054@arm.com>
On Thu, Dec 4, 2025 at 1:49 PM Christian Loehle
<christian.loehle@arm.com> wrote:
>
> On 12/1/25 20:24, Samuel Wu wrote:
> > The existing cpu_frequency trace_event can be verbose, emitting a nearly
> > identical trace event for every CPU in the policy even when their
> > frequencies are identical.
> >
> > This patch replaces the cpu_frequency trace event with policy_frequency
> > trace event, a more efficient alternative. From the kernel's
> > perspective, emitting a trace event once per policy instead of once per
> > cpu saves some memory and is less overhead. From the post-processing
> > perspective, analysis of the trace log is simplified without any loss of
> > information.
> >
> > Signed-off-by: Samuel Wu <wusamuel@google.com>
> > ---
> > drivers/cpufreq/cpufreq.c | 14 ++------------
> > drivers/cpufreq/intel_pstate.c | 6 ++++--
> > include/trace/events/power.h | 24 +++++++++++++++++++++---
> > kernel/trace/power-traces.c | 2 +-
> > samples/bpf/cpustat_kern.c | 8 ++++----
> > samples/bpf/cpustat_user.c | 6 +++---
> > tools/perf/builtin-timechart.c | 12 ++++++------
> > 7 files changed, 41 insertions(+), 31 deletions(-)
> >
> > diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
> > index 4472bb1ec83c..dd3f08f3b958 100644
> > --- a/drivers/cpufreq/cpufreq.c
> > +++ b/drivers/cpufreq/cpufreq.c
> > @@ -309,8 +309,6 @@ static void cpufreq_notify_transition(struct cpufreq_policy *policy,
> > struct cpufreq_freqs *freqs,
> > unsigned int state)
> > {
> > - int cpu;
> > -
> > BUG_ON(irqs_disabled());
> >
> > if (cpufreq_disabled())
> > @@ -344,10 +342,7 @@ static void cpufreq_notify_transition(struct cpufreq_policy *policy,
> > adjust_jiffies(CPUFREQ_POSTCHANGE, freqs);
> > pr_debug("FREQ: %u - CPUs: %*pbl\n", freqs->new,
> > cpumask_pr_args(policy->cpus));
> > -
> > - for_each_cpu(cpu, policy->cpus)
> > - trace_cpu_frequency(freqs->new, cpu);
> > -
> > + trace_policy_frequency(freqs->new, policy->cpu, policy->cpus);
> > srcu_notifier_call_chain(&cpufreq_transition_notifier_list,
> > CPUFREQ_POSTCHANGE, freqs);
> >
> > @@ -2201,7 +2196,6 @@ unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
> > unsigned int target_freq)
> > {
> > unsigned int freq;
> > - int cpu;
> >
> > target_freq = clamp_val(target_freq, policy->min, policy->max);
> > freq = cpufreq_driver->fast_switch(policy, target_freq);
> > @@ -2213,11 +2207,7 @@ unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
> > arch_set_freq_scale(policy->related_cpus, freq,
> > arch_scale_freq_ref(policy->cpu));
> > cpufreq_stats_record_transition(policy, freq);
> > -
> > - if (trace_cpu_frequency_enabled()) {
> > - for_each_cpu(cpu, policy->cpus)
> > - trace_cpu_frequency(freq, cpu);
> > - }
> > + trace_policy_frequency(freq, policy->cpu, policy->cpus);
> >
> > return freq;
> > }
> > diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
> > index ec4abe374573..9724b5d19d83 100644
> > --- a/drivers/cpufreq/intel_pstate.c
> > +++ b/drivers/cpufreq/intel_pstate.c
> > @@ -2297,7 +2297,8 @@ static int hwp_get_cpu_scaling(int cpu)
> >
> > static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
> > {
> > - trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
> > + trace_policy_frequency(pstate * cpu->pstate.scaling, cpu->cpu,
> > + cpumask_of(cpu->cpu));
> > cpu->pstate.current_pstate = pstate;
> > /*
> > * Generally, there is no guarantee that this code will always run on
> > @@ -2587,7 +2588,8 @@ static void intel_pstate_adjust_pstate(struct cpudata *cpu)
> >
> > target_pstate = get_target_pstate(cpu);
> > target_pstate = intel_pstate_prepare_request(cpu, target_pstate);
> > - trace_cpu_frequency(target_pstate * cpu->pstate.scaling, cpu->cpu);
> > + trace_policy_frequency(target_pstate * cpu->pstate.scaling, cpu->cpu,
> > + cpumask_of(cpu->cpu));
> > intel_pstate_update_pstate(cpu, target_pstate);
> >
> > sample = &cpu->sample;
> > diff --git a/include/trace/events/power.h b/include/trace/events/power.h
> > index 370f8df2fdb4..317098ffdd5f 100644
> > --- a/include/trace/events/power.h
> > +++ b/include/trace/events/power.h
> > @@ -182,11 +182,29 @@ TRACE_EVENT(pstate_sample,
> > { PM_EVENT_RECOVER, "recover" }, \
> > { PM_EVENT_POWEROFF, "poweroff" })
> >
> > -DEFINE_EVENT(cpu, cpu_frequency,
> > +TRACE_EVENT(policy_frequency,
> >
> > - TP_PROTO(unsigned int frequency, unsigned int cpu_id),
> > + TP_PROTO(unsigned int frequency, unsigned int cpu_id,
> > + const struct cpumask *policy_cpus),
> >
> > - TP_ARGS(frequency, cpu_id)
> > + TP_ARGS(frequency, cpu_id, policy_cpus),
> > +
> > + TP_STRUCT__entry(
> > + __field(u32, state)
> > + __field(u32, cpu_id)
> > + __cpumask(cpumask)
> > + ),
> > +
> > + TP_fast_assign(
> > + __entry->state = frequency;
> > + __entry->cpu_id = cpu_id;
> > + __assign_cpumask(cpumask, policy_cpus);
> > + ),
> > +
> > + TP_printk("state=%lu cpu_id=%lu policy_cpus=%*pb",
> > + (unsigned long)__entry->state,
> > + (unsigned long)__entry->cpu_id,
> > + cpumask_pr_args((struct cpumask *)__get_dynamic_array(cpumask)))
> > );
> >
> > TRACE_EVENT(cpu_frequency_limits,
> > diff --git a/kernel/trace/power-traces.c b/kernel/trace/power-traces.c
> > index f2fe33573e54..a537e68a6878 100644
> > --- a/kernel/trace/power-traces.c
> > +++ b/kernel/trace/power-traces.c
> > @@ -16,5 +16,5 @@
> >
> > EXPORT_TRACEPOINT_SYMBOL_GPL(suspend_resume);
> > EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_idle);
> > -EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_frequency);
> > +EXPORT_TRACEPOINT_SYMBOL_GPL(policy_frequency);
> >
> > diff --git a/samples/bpf/cpustat_kern.c b/samples/bpf/cpustat_kern.c
> > index 7ec7143e2757..f485de0f89b2 100644
> > --- a/samples/bpf/cpustat_kern.c
> > +++ b/samples/bpf/cpustat_kern.c
> > @@ -75,9 +75,9 @@ struct {
> > } pstate_duration SEC(".maps");
> >
> > /*
> > - * The trace events for cpu_idle and cpu_frequency are taken from:
> > + * The trace events for cpu_idle and policy_frequency are taken from:
> > * /sys/kernel/tracing/events/power/cpu_idle/format
> > - * /sys/kernel/tracing/events/power/cpu_frequency/format
> > + * /sys/kernel/tracing/events/power/policy_frequency/format
> > *
> > * These two events have same format, so define one common structure.
> > */
> > @@ -162,7 +162,7 @@ int bpf_prog1(struct cpu_args *ctx)
> > */
> > if (ctx->state != (u32)-1) {
> >
> > - /* record pstate after have first cpu_frequency event */
> > + /* record pstate after have first policy_frequency event */
> > if (!*pts)
> > return 0;
> >
> > @@ -208,7 +208,7 @@ int bpf_prog1(struct cpu_args *ctx)
> > return 0;
> > }
> >
> > -SEC("tracepoint/power/cpu_frequency")
> > +SEC("tracepoint/power/policy_frequency")
> > int bpf_prog2(struct cpu_args *ctx)
> > {
> > u64 *pts, *cstate, *pstate, cur_ts, delta;
> > diff --git a/samples/bpf/cpustat_user.c b/samples/bpf/cpustat_user.c
> > index 356f756cba0d..f7e81f702358 100644
> > --- a/samples/bpf/cpustat_user.c
> > +++ b/samples/bpf/cpustat_user.c
> > @@ -143,12 +143,12 @@ static int cpu_stat_inject_cpu_idle_event(void)
> >
> > /*
> > * It's possible to have no any frequency change for long time and cannot
> > - * get ftrace event 'trace_cpu_frequency' for long period, this introduces
> > + * get ftrace event 'trace_policy_frequency' for long period, this introduces
> > * big deviation for pstate statistics.
> > *
> > * To solve this issue, below code forces to set 'scaling_max_freq' to 208MHz
> > - * for triggering ftrace event 'trace_cpu_frequency' and then recovery back to
> > - * the maximum frequency value 1.2GHz.
> > + * for triggering ftrace event 'trace_policy_frequency' and then recovery back
> > + * to the maximum frequency value 1.2GHz.
> > */
> > static int cpu_stat_inject_cpu_frequency_event(void)
> > {
> > diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
> > index 22050c640dfa..3ef1a2fd0493 100644
> > --- a/tools/perf/builtin-timechart.c
> > +++ b/tools/perf/builtin-timechart.c
> > @@ -612,10 +612,10 @@ process_sample_cpu_idle(struct timechart *tchart __maybe_unused,
> > }
> >
> > static int
> > -process_sample_cpu_frequency(struct timechart *tchart,
> > - struct evsel *evsel,
> > - struct perf_sample *sample,
> > - const char *backtrace __maybe_unused)
> > +process_sample_policy_frequency(struct timechart *tchart,
> > + struct evsel *evsel,
> > + struct perf_sample *sample,
> > + const char *backtrace __maybe_unused)
> > {
> > u32 state = evsel__intval(evsel, sample, "state");
> > u32 cpu_id = evsel__intval(evsel, sample, "cpu_id");
> > @@ -1541,7 +1541,7 @@ static int __cmd_timechart(struct timechart *tchart, const char *output_name)
> > {
> > const struct evsel_str_handler power_tracepoints[] = {
> > { "power:cpu_idle", process_sample_cpu_idle },
> > - { "power:cpu_frequency", process_sample_cpu_frequency },
> > + { "power:policy_frequency", process_sample_policy_frequency },
> > { "sched:sched_wakeup", process_sample_sched_wakeup },
> > { "sched:sched_switch", process_sample_sched_switch },
> > #ifdef SUPPORT_OLD_POWER_EVENTS
> > @@ -1804,7 +1804,7 @@ static int timechart__record(struct timechart *tchart, int argc, const char **ar
> > unsigned int backtrace_args_no = ARRAY_SIZE(backtrace_args);
> >
> > const char * const power_args[] = {
> > - "-e", "power:cpu_frequency",
> > + "-e", "power:policy_frequency",
> > "-e", "power:cpu_idle",
> > };
> > unsigned int power_args_nr = ARRAY_SIZE(power_args);
>
> perf timechart seem to do per-CPU reporting though?
> So this is broken by not emitting an event per-CPU? At least with a simple s/cpu_frequency/policy_frequency/
> like here.
> Similar for the bpf samples technically...
This kind of boils down to whether or not tracepoints can be regarded
as ABI and to what extent.
In this particular case, I'm not sure I agree with the stated motivation.
First of all, on systems with one CPU per cpufreq policy (the vast
majority of x86, including AMD, and the ARM systems using the CPPC
driver AFAICS), the "issue" at hand is actually a non-issue and
changing the name of the tracepoint alone would confuse things in user
space IIUC. Those need to work the way they do today.
On systems with multiple CPUs per cpufreq policy there is some extra
overhead related to the cpu_frequency tracepoint, but the if someone
is only interested in the "policy" frequency, they can filter out all
CPUs belonging to the same policy except for one from the traces,
don't they?
^ permalink raw reply
* Re: [PATCH 1/2] rust: sync: add Arc::DATA_OFFSET
From: Daniel Almeida @ 2025-12-04 13:32 UTC (permalink / raw)
To: Alice Ryhl
Cc: Greg Kroah-Hartman, Carlos Llamas, Steven Rostedt,
Masami Hiramatsu, Mathieu Desnoyers, Miguel Ojeda, Boqun Feng,
Gary Guo, Björn Roy Baron, Benno Lossin, Andreas Hindborg,
Trevor Gross, Danilo Krummrich, Arve Hjønnevåg,
Todd Kjos, Martijn Coenen, Joel Fernandes, Christian Brauner,
Suren Baghdasaryan, rust-for-linux, linux-trace-kernel,
linux-kernel
In-Reply-To: <20251203-binder-trace1-v1-1-22d3ffddb44e@google.com>
> On 3 Dec 2025, at 08:48, Alice Ryhl <aliceryhl@google.com> wrote:
>
> This constant will be used to expose some offset constants from the Rust
> Binder driver to tracepoints which are implemented in C. The constant is
> usually equal to sizeof(refcount_t), but may be larger if T has a large
> alignment.
>
> Signed-off-by: Alice Ryhl <aliceryhl@google.com>
> ---
> rust/kernel/sync/arc.rs | 3 +++
> 1 file changed, 3 insertions(+)
>
> diff --git a/rust/kernel/sync/arc.rs b/rust/kernel/sync/arc.rs
> index 289f77abf415a2a52e039a2c0291413eda01217c..921e19333b895f0d971591c4753047d0248a3029 100644
> --- a/rust/kernel/sync/arc.rs
> +++ b/rust/kernel/sync/arc.rs
> @@ -240,6 +240,9 @@ pub fn new(contents: T, flags: Flags) -> Result<Self, AllocError> {
> // `Arc` object.
> Ok(unsafe { Self::from_inner(inner) })
> }
> +
> + /// The offset that the value is stored at.
> + pub const DATA_OFFSET: usize = core::mem::offset_of!(ArcInner<T>, data);
> }
>
> impl<T: ?Sized> Arc<T> {
>
> --
> 2.52.0.158.g65b55ccf14-goog
>
>
Reviewed-by: Daniel Almeida <daniel.almeida@collabora.com>
^ permalink raw reply
* Re: [PATCH v3 1/2] cpufreq: Replace trace_cpu_frequency with trace_policy_frequency
From: Christian Loehle @ 2025-12-04 12:48 UTC (permalink / raw)
To: Samuel Wu, Huang Rui, Gautham R. Shenoy, Mario Limonciello,
Perry Yuan, Jonathan Corbet, Rafael J. Wysocki, Viresh Kumar,
Steven Rostedt, Masami Hiramatsu, Mathieu Desnoyers,
Srinivas Pandruvada, Len Brown, Alexei Starovoitov,
Daniel Borkmann, Andrii Nakryiko, Martin KaFai Lau,
Eduard Zingerman, Song Liu, Yonghong Song, John Fastabend,
KP Singh, Stanislav Fomichev, Hao Luo, Jiri Olsa, Peter Zijlstra,
Ingo Molnar, Arnaldo Carvalho de Melo, Namhyung Kim, Mark Rutland,
Alexander Shishkin, Ian Rogers, Adrian Hunter, James Clark
Cc: kernel-team, linux-pm, linux-doc, linux-kernel,
linux-trace-kernel, bpf, linux-perf-users
In-Reply-To: <20251201202437.3750901-2-wusamuel@google.com>
On 12/1/25 20:24, Samuel Wu wrote:
> The existing cpu_frequency trace_event can be verbose, emitting a nearly
> identical trace event for every CPU in the policy even when their
> frequencies are identical.
>
> This patch replaces the cpu_frequency trace event with policy_frequency
> trace event, a more efficient alternative. From the kernel's
> perspective, emitting a trace event once per policy instead of once per
> cpu saves some memory and is less overhead. From the post-processing
> perspective, analysis of the trace log is simplified without any loss of
> information.
>
> Signed-off-by: Samuel Wu <wusamuel@google.com>
> ---
> drivers/cpufreq/cpufreq.c | 14 ++------------
> drivers/cpufreq/intel_pstate.c | 6 ++++--
> include/trace/events/power.h | 24 +++++++++++++++++++++---
> kernel/trace/power-traces.c | 2 +-
> samples/bpf/cpustat_kern.c | 8 ++++----
> samples/bpf/cpustat_user.c | 6 +++---
> tools/perf/builtin-timechart.c | 12 ++++++------
> 7 files changed, 41 insertions(+), 31 deletions(-)
>
> diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
> index 4472bb1ec83c..dd3f08f3b958 100644
> --- a/drivers/cpufreq/cpufreq.c
> +++ b/drivers/cpufreq/cpufreq.c
> @@ -309,8 +309,6 @@ static void cpufreq_notify_transition(struct cpufreq_policy *policy,
> struct cpufreq_freqs *freqs,
> unsigned int state)
> {
> - int cpu;
> -
> BUG_ON(irqs_disabled());
>
> if (cpufreq_disabled())
> @@ -344,10 +342,7 @@ static void cpufreq_notify_transition(struct cpufreq_policy *policy,
> adjust_jiffies(CPUFREQ_POSTCHANGE, freqs);
> pr_debug("FREQ: %u - CPUs: %*pbl\n", freqs->new,
> cpumask_pr_args(policy->cpus));
> -
> - for_each_cpu(cpu, policy->cpus)
> - trace_cpu_frequency(freqs->new, cpu);
> -
> + trace_policy_frequency(freqs->new, policy->cpu, policy->cpus);
> srcu_notifier_call_chain(&cpufreq_transition_notifier_list,
> CPUFREQ_POSTCHANGE, freqs);
>
> @@ -2201,7 +2196,6 @@ unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
> unsigned int target_freq)
> {
> unsigned int freq;
> - int cpu;
>
> target_freq = clamp_val(target_freq, policy->min, policy->max);
> freq = cpufreq_driver->fast_switch(policy, target_freq);
> @@ -2213,11 +2207,7 @@ unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
> arch_set_freq_scale(policy->related_cpus, freq,
> arch_scale_freq_ref(policy->cpu));
> cpufreq_stats_record_transition(policy, freq);
> -
> - if (trace_cpu_frequency_enabled()) {
> - for_each_cpu(cpu, policy->cpus)
> - trace_cpu_frequency(freq, cpu);
> - }
> + trace_policy_frequency(freq, policy->cpu, policy->cpus);
>
> return freq;
> }
> diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
> index ec4abe374573..9724b5d19d83 100644
> --- a/drivers/cpufreq/intel_pstate.c
> +++ b/drivers/cpufreq/intel_pstate.c
> @@ -2297,7 +2297,8 @@ static int hwp_get_cpu_scaling(int cpu)
>
> static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
> {
> - trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
> + trace_policy_frequency(pstate * cpu->pstate.scaling, cpu->cpu,
> + cpumask_of(cpu->cpu));
> cpu->pstate.current_pstate = pstate;
> /*
> * Generally, there is no guarantee that this code will always run on
> @@ -2587,7 +2588,8 @@ static void intel_pstate_adjust_pstate(struct cpudata *cpu)
>
> target_pstate = get_target_pstate(cpu);
> target_pstate = intel_pstate_prepare_request(cpu, target_pstate);
> - trace_cpu_frequency(target_pstate * cpu->pstate.scaling, cpu->cpu);
> + trace_policy_frequency(target_pstate * cpu->pstate.scaling, cpu->cpu,
> + cpumask_of(cpu->cpu));
> intel_pstate_update_pstate(cpu, target_pstate);
>
> sample = &cpu->sample;
> diff --git a/include/trace/events/power.h b/include/trace/events/power.h
> index 370f8df2fdb4..317098ffdd5f 100644
> --- a/include/trace/events/power.h
> +++ b/include/trace/events/power.h
> @@ -182,11 +182,29 @@ TRACE_EVENT(pstate_sample,
> { PM_EVENT_RECOVER, "recover" }, \
> { PM_EVENT_POWEROFF, "poweroff" })
>
> -DEFINE_EVENT(cpu, cpu_frequency,
> +TRACE_EVENT(policy_frequency,
>
> - TP_PROTO(unsigned int frequency, unsigned int cpu_id),
> + TP_PROTO(unsigned int frequency, unsigned int cpu_id,
> + const struct cpumask *policy_cpus),
>
> - TP_ARGS(frequency, cpu_id)
> + TP_ARGS(frequency, cpu_id, policy_cpus),
> +
> + TP_STRUCT__entry(
> + __field(u32, state)
> + __field(u32, cpu_id)
> + __cpumask(cpumask)
> + ),
> +
> + TP_fast_assign(
> + __entry->state = frequency;
> + __entry->cpu_id = cpu_id;
> + __assign_cpumask(cpumask, policy_cpus);
> + ),
> +
> + TP_printk("state=%lu cpu_id=%lu policy_cpus=%*pb",
> + (unsigned long)__entry->state,
> + (unsigned long)__entry->cpu_id,
> + cpumask_pr_args((struct cpumask *)__get_dynamic_array(cpumask)))
> );
>
> TRACE_EVENT(cpu_frequency_limits,
> diff --git a/kernel/trace/power-traces.c b/kernel/trace/power-traces.c
> index f2fe33573e54..a537e68a6878 100644
> --- a/kernel/trace/power-traces.c
> +++ b/kernel/trace/power-traces.c
> @@ -16,5 +16,5 @@
>
> EXPORT_TRACEPOINT_SYMBOL_GPL(suspend_resume);
> EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_idle);
> -EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_frequency);
> +EXPORT_TRACEPOINT_SYMBOL_GPL(policy_frequency);
>
> diff --git a/samples/bpf/cpustat_kern.c b/samples/bpf/cpustat_kern.c
> index 7ec7143e2757..f485de0f89b2 100644
> --- a/samples/bpf/cpustat_kern.c
> +++ b/samples/bpf/cpustat_kern.c
> @@ -75,9 +75,9 @@ struct {
> } pstate_duration SEC(".maps");
>
> /*
> - * The trace events for cpu_idle and cpu_frequency are taken from:
> + * The trace events for cpu_idle and policy_frequency are taken from:
> * /sys/kernel/tracing/events/power/cpu_idle/format
> - * /sys/kernel/tracing/events/power/cpu_frequency/format
> + * /sys/kernel/tracing/events/power/policy_frequency/format
> *
> * These two events have same format, so define one common structure.
> */
> @@ -162,7 +162,7 @@ int bpf_prog1(struct cpu_args *ctx)
> */
> if (ctx->state != (u32)-1) {
>
> - /* record pstate after have first cpu_frequency event */
> + /* record pstate after have first policy_frequency event */
> if (!*pts)
> return 0;
>
> @@ -208,7 +208,7 @@ int bpf_prog1(struct cpu_args *ctx)
> return 0;
> }
>
> -SEC("tracepoint/power/cpu_frequency")
> +SEC("tracepoint/power/policy_frequency")
> int bpf_prog2(struct cpu_args *ctx)
> {
> u64 *pts, *cstate, *pstate, cur_ts, delta;
> diff --git a/samples/bpf/cpustat_user.c b/samples/bpf/cpustat_user.c
> index 356f756cba0d..f7e81f702358 100644
> --- a/samples/bpf/cpustat_user.c
> +++ b/samples/bpf/cpustat_user.c
> @@ -143,12 +143,12 @@ static int cpu_stat_inject_cpu_idle_event(void)
>
> /*
> * It's possible to have no any frequency change for long time and cannot
> - * get ftrace event 'trace_cpu_frequency' for long period, this introduces
> + * get ftrace event 'trace_policy_frequency' for long period, this introduces
> * big deviation for pstate statistics.
> *
> * To solve this issue, below code forces to set 'scaling_max_freq' to 208MHz
> - * for triggering ftrace event 'trace_cpu_frequency' and then recovery back to
> - * the maximum frequency value 1.2GHz.
> + * for triggering ftrace event 'trace_policy_frequency' and then recovery back
> + * to the maximum frequency value 1.2GHz.
> */
> static int cpu_stat_inject_cpu_frequency_event(void)
> {
> diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
> index 22050c640dfa..3ef1a2fd0493 100644
> --- a/tools/perf/builtin-timechart.c
> +++ b/tools/perf/builtin-timechart.c
> @@ -612,10 +612,10 @@ process_sample_cpu_idle(struct timechart *tchart __maybe_unused,
> }
>
> static int
> -process_sample_cpu_frequency(struct timechart *tchart,
> - struct evsel *evsel,
> - struct perf_sample *sample,
> - const char *backtrace __maybe_unused)
> +process_sample_policy_frequency(struct timechart *tchart,
> + struct evsel *evsel,
> + struct perf_sample *sample,
> + const char *backtrace __maybe_unused)
> {
> u32 state = evsel__intval(evsel, sample, "state");
> u32 cpu_id = evsel__intval(evsel, sample, "cpu_id");
> @@ -1541,7 +1541,7 @@ static int __cmd_timechart(struct timechart *tchart, const char *output_name)
> {
> const struct evsel_str_handler power_tracepoints[] = {
> { "power:cpu_idle", process_sample_cpu_idle },
> - { "power:cpu_frequency", process_sample_cpu_frequency },
> + { "power:policy_frequency", process_sample_policy_frequency },
> { "sched:sched_wakeup", process_sample_sched_wakeup },
> { "sched:sched_switch", process_sample_sched_switch },
> #ifdef SUPPORT_OLD_POWER_EVENTS
> @@ -1804,7 +1804,7 @@ static int timechart__record(struct timechart *tchart, int argc, const char **ar
> unsigned int backtrace_args_no = ARRAY_SIZE(backtrace_args);
>
> const char * const power_args[] = {
> - "-e", "power:cpu_frequency",
> + "-e", "power:policy_frequency",
> "-e", "power:cpu_idle",
> };
> unsigned int power_args_nr = ARRAY_SIZE(power_args);
perf timechart seem to do per-CPU reporting though?
So this is broken by not emitting an event per-CPU? At least with a simple s/cpu_frequency/policy_frequency/
like here.
Similar for the bpf samples technically...
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox