From 2d088762631b212eb0809e112642843844ef64eb Mon Sep 17 00:00:00 2001 From: Nam Cao Date: Wed, 9 Jul 2025 21:21:12 +0200 Subject: rv: Add #undef TRACE_INCLUDE_FILE Without "#undef TRACE_INCLUDE_FILE", there could be a build error due to TRACE_INCLUDE_FILE being redefined. Therefore add it. Also fix a typo while at it. Cc: John Ogness Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://lore.kernel.org/f805e074581e927bb176c742c981fa7675b6ebe5.1752088709.git.namcao@linutronix.de Reviewed-by: Gabriele Monaco Signed-off-by: Nam Cao Signed-off-by: Steven Rostedt (Google) --- kernel/trace/rv/rv_trace.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/rv/rv_trace.h b/kernel/trace/rv/rv_trace.h index 422b75f58891..99c3801616d4 100644 --- a/kernel/trace/rv/rv_trace.h +++ b/kernel/trace/rv/rv_trace.h @@ -129,8 +129,9 @@ DECLARE_EVENT_CLASS(error_da_monitor_id, #endif /* CONFIG_DA_MON_EVENTS_ID */ #endif /* _TRACE_RV_H */ -/* This part ust be outside protection */ +/* This part must be outside protection */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE rv_trace #include -- cgit v1.2.3 From ff4e233d8ab70fe6ae460ecc8c0e5b24dd0fedb0 Mon Sep 17 00:00:00 2001 From: Nam Cao Date: Wed, 9 Jul 2025 21:21:15 +0200 Subject: rv: Let the reactors take care of buffers Each RV monitor has one static buffer to send to the reactors. If multiple errors are detected simultaneously, the one buffer could be overwritten. Instead, leave it to the reactors to handle buffering. Reviewed-by: Gabriele Monaco Signed-off-by: Nam Cao Signed-off-by: Steven Rostedt (Google) --- include/linux/rv.h | 9 ++++++-- include/rv/da_monitor.h | 45 +++++++++------------------------------- kernel/trace/rv/reactor_panic.c | 8 +++++-- kernel/trace/rv/reactor_printk.c | 8 +++++-- kernel/trace/rv/rv_reactors.c | 2 +- 5 files changed, 30 insertions(+), 42 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/rv.h b/include/linux/rv.h index 3452b5e4b29e..9428e62eb8e9 100644 --- a/include/linux/rv.h +++ b/include/linux/rv.h @@ -38,7 +38,7 @@ union rv_task_monitor { struct rv_reactor { const char *name; const char *description; - void (*react)(char *msg); + __printf(1, 2) void (*react)(const char *msg, ...); }; #endif @@ -50,7 +50,7 @@ struct rv_monitor { void (*disable)(void); void (*reset)(void); #ifdef CONFIG_RV_REACTORS - void (*react)(char *msg); + __printf(1, 2) void (*react)(const char *msg, ...); #endif }; @@ -64,6 +64,11 @@ void rv_put_task_monitor_slot(int slot); bool rv_reacting_on(void); int rv_unregister_reactor(struct rv_reactor *reactor); int rv_register_reactor(struct rv_reactor *reactor); +#else +static inline bool rv_reacting_on(void) +{ + return false; +} #endif /* CONFIG_RV_REACTORS */ #endif /* CONFIG_RV */ diff --git a/include/rv/da_monitor.h b/include/rv/da_monitor.h index 510c88bfabd4..15f9ed4e4bb6 100644 --- a/include/rv/da_monitor.h +++ b/include/rv/da_monitor.h @@ -19,45 +19,22 @@ #ifdef CONFIG_RV_REACTORS #define DECLARE_RV_REACTING_HELPERS(name, type) \ -static char REACT_MSG_##name[1024]; \ - \ -static inline char *format_react_msg_##name(type curr_state, type event) \ -{ \ - snprintf(REACT_MSG_##name, 1024, \ - "rv: monitor %s does not allow event %s on state %s\n", \ - #name, \ - model_get_event_name_##name(event), \ - model_get_state_name_##name(curr_state)); \ - return REACT_MSG_##name; \ -} \ - \ -static void cond_react_##name(char *msg) \ +static void cond_react_##name(type curr_state, type event) \ { \ - if (rv_##name.react) \ - rv_##name.react(msg); \ -} \ - \ -static bool rv_reacting_on_##name(void) \ -{ \ - return rv_reacting_on(); \ + if (!rv_reacting_on() || !rv_##name.react) \ + return; \ + rv_##name.react("rv: monitor %s does not allow event %s on state %s\n", \ + #name, \ + model_get_event_name_##name(event), \ + model_get_state_name_##name(curr_state)); \ } #else /* CONFIG_RV_REACTOR */ #define DECLARE_RV_REACTING_HELPERS(name, type) \ -static inline char *format_react_msg_##name(type curr_state, type event) \ -{ \ - return NULL; \ -} \ - \ -static void cond_react_##name(char *msg) \ +static void cond_react_##name(type curr_state, type event) \ { \ return; \ -} \ - \ -static bool rv_reacting_on_##name(void) \ -{ \ - return 0; \ } #endif @@ -170,8 +147,7 @@ da_event_##name(struct da_monitor *da_mon, enum events_##name event) \ return true; \ } \ \ - if (rv_reacting_on_##name()) \ - cond_react_##name(format_react_msg_##name(curr_state, event)); \ + cond_react_##name(curr_state, event); \ \ trace_error_##name(model_get_state_name_##name(curr_state), \ model_get_event_name_##name(event)); \ @@ -202,8 +178,7 @@ static inline bool da_event_##name(struct da_monitor *da_mon, struct task_struct return true; \ } \ \ - if (rv_reacting_on_##name()) \ - cond_react_##name(format_react_msg_##name(curr_state, event)); \ + cond_react_##name(curr_state, event); \ \ trace_error_##name(tsk->pid, \ model_get_state_name_##name(curr_state), \ diff --git a/kernel/trace/rv/reactor_panic.c b/kernel/trace/rv/reactor_panic.c index 0186ff4cbd0b..74c6bcc2c749 100644 --- a/kernel/trace/rv/reactor_panic.c +++ b/kernel/trace/rv/reactor_panic.c @@ -13,9 +13,13 @@ #include #include -static void rv_panic_reaction(char *msg) +__printf(1, 2) static void rv_panic_reaction(const char *msg, ...) { - panic(msg); + va_list args; + + va_start(args, msg); + vpanic(msg, args); + va_end(args); } static struct rv_reactor rv_panic = { diff --git a/kernel/trace/rv/reactor_printk.c b/kernel/trace/rv/reactor_printk.c index 178759dbf89f..2dae2916c05f 100644 --- a/kernel/trace/rv/reactor_printk.c +++ b/kernel/trace/rv/reactor_printk.c @@ -12,9 +12,13 @@ #include #include -static void rv_printk_reaction(char *msg) +__printf(1, 2) static void rv_printk_reaction(const char *msg, ...) { - printk_deferred(msg); + va_list args; + + va_start(args, msg); + vprintk_deferred(msg, args); + va_end(args); } static struct rv_reactor rv_printk = { diff --git a/kernel/trace/rv/rv_reactors.c b/kernel/trace/rv/rv_reactors.c index 9501ca886d83..740603670dd1 100644 --- a/kernel/trace/rv/rv_reactors.c +++ b/kernel/trace/rv/rv_reactors.c @@ -490,7 +490,7 @@ void reactor_cleanup_monitor(struct rv_monitor_def *mdef) /* * Nop reactor register */ -static void rv_nop_reaction(char *msg) +__printf(1, 2) static void rv_nop_reaction(const char *msg, ...) { } -- cgit v1.2.3 From c94d27c01b1ff2e26ca347524b3527534e285a39 Mon Sep 17 00:00:00 2001 From: Nam Cao Date: Wed, 9 Jul 2025 21:21:16 +0200 Subject: rv: rename CONFIG_DA_MON_EVENTS to CONFIG_RV_MON_EVENTS CONFIG_DA_MON_EVENTS is not specific to deterministic automaton. It could be used for other monitor types. Therefore rename it to CONFIG_RV_MON_EVENTS. This prepares for the introduction of linear temporal logic monitor. Cc: John Ogness Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://lore.kernel.org/507210517123d887c1d208aa2fd45ec69765d3f0.1752088709.git.namcao@linutronix.de Reviewed-by: Gabriele Monaco Signed-off-by: Nam Cao Signed-off-by: Steven Rostedt (Google) --- kernel/trace/rv/Kconfig | 6 +++--- kernel/trace/rv/rv.c | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/rv/Kconfig b/kernel/trace/rv/Kconfig index b39f36013ef2..6cdffc04b73c 100644 --- a/kernel/trace/rv/Kconfig +++ b/kernel/trace/rv/Kconfig @@ -1,14 +1,14 @@ # SPDX-License-Identifier: GPL-2.0-only # -config DA_MON_EVENTS +config RV_MON_EVENTS bool config DA_MON_EVENTS_IMPLICIT - select DA_MON_EVENTS + select RV_MON_EVENTS bool config DA_MON_EVENTS_ID - select DA_MON_EVENTS + select RV_MON_EVENTS bool menuconfig RV diff --git a/kernel/trace/rv/rv.c b/kernel/trace/rv/rv.c index e4077500a91d..e25d65fe432a 100644 --- a/kernel/trace/rv/rv.c +++ b/kernel/trace/rv/rv.c @@ -143,7 +143,7 @@ #include #include -#ifdef CONFIG_DA_MON_EVENTS +#ifdef CONFIG_RV_MON_EVENTS #define CREATE_TRACE_POINTS #include #endif -- cgit v1.2.3 From a9769a5b987838f03f3dd57b097794cd4c691098 Mon Sep 17 00:00:00 2001 From: Nam Cao Date: Wed, 9 Jul 2025 21:21:17 +0200 Subject: rv: Add support for LTL monitors While attempting to implement DA monitors for some complex specifications, deterministic automaton is found to be inappropriate as the specification language. The automaton is complicated, hard to understand, and error-prone. For these cases, linear temporal logic is more suitable as the specification language. Add support for linear temporal logic runtime verification monitor. Cc: John Ogness Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Gabriele Monaco Link: https://lore.kernel.org/d366c1fed60ed4e8f6451f3c15a99755f2740b5f.1752088709.git.namcao@linutronix.de Signed-off-by: Nam Cao Signed-off-by: Steven Rostedt (Google) --- include/linux/rv.h | 63 +++++++++++++++- include/rv/ltl_monitor.h | 184 +++++++++++++++++++++++++++++++++++++++++++++ kernel/fork.c | 5 +- kernel/trace/rv/Kconfig | 7 ++ kernel/trace/rv/rv_trace.h | 47 ++++++++++++ 5 files changed, 298 insertions(+), 8 deletions(-) create mode 100644 include/rv/ltl_monitor.h (limited to 'kernel/trace') diff --git a/include/linux/rv.h b/include/linux/rv.h index 9428e62eb8e9..1d5579f9b75a 100644 --- a/include/linux/rv.h +++ b/include/linux/rv.h @@ -10,6 +10,10 @@ #define MAX_DA_NAME_LEN 32 #ifdef CONFIG_RV +#include +#include +#include + /* * Deterministic automaton per-object variables. */ @@ -18,6 +22,59 @@ struct da_monitor { unsigned int curr_state; }; +#ifdef CONFIG_RV_LTL_MONITOR + +/* + * In the future, if the number of atomic propositions or the size of Buchi + * automaton is larger, we can switch to dynamic allocation. For now, the code + * is simpler this way. + */ +#define RV_MAX_LTL_ATOM 32 +#define RV_MAX_BA_STATES 32 + +/** + * struct ltl_monitor - A linear temporal logic runtime verification monitor + * @states: States in the Buchi automaton. As Buchi automaton is a + * non-deterministic state machine, the monitor can be in multiple + * states simultaneously. This is a bitmask of all possible states. + * If this is zero, that means either: + * - The monitor has not started yet (e.g. because not all + * atomic propositions are known). + * - There is no possible state to be in. In other words, a + * violation of the LTL property is detected. + * @atoms: The values of atomic propositions. + * @unknown_atoms: Atomic propositions which are still unknown. + */ +struct ltl_monitor { + DECLARE_BITMAP(states, RV_MAX_BA_STATES); + DECLARE_BITMAP(atoms, RV_MAX_LTL_ATOM); + DECLARE_BITMAP(unknown_atoms, RV_MAX_LTL_ATOM); +}; + +static inline bool rv_ltl_valid_state(struct ltl_monitor *mon) +{ + for (int i = 0; i < ARRAY_SIZE(mon->states); ++i) { + if (mon->states[i]) + return true; + } + return false; +} + +static inline bool rv_ltl_all_atoms_known(struct ltl_monitor *mon) +{ + for (int i = 0; i < ARRAY_SIZE(mon->unknown_atoms); ++i) { + if (mon->unknown_atoms[i]) + return false; + } + return true; +} + +#else + +struct ltl_monitor {}; + +#endif /* CONFIG_RV_LTL_MONITOR */ + /* * Per-task RV monitors count. Nowadays fixed in RV_PER_TASK_MONITORS. * If we find justification for more monitors, we can think about @@ -27,11 +84,9 @@ struct da_monitor { #define RV_PER_TASK_MONITORS 1 #define RV_PER_TASK_MONITOR_INIT (RV_PER_TASK_MONITORS) -/* - * Futher monitor types are expected, so make this a union. - */ union rv_task_monitor { - struct da_monitor da_mon; + struct da_monitor da_mon; + struct ltl_monitor ltl_mon; }; #ifdef CONFIG_RV_REACTORS diff --git a/include/rv/ltl_monitor.h b/include/rv/ltl_monitor.h new file mode 100644 index 000000000000..9a583125b566 --- /dev/null +++ b/include/rv/ltl_monitor.h @@ -0,0 +1,184 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/** + * This file must be combined with the $(MODEL_NAME).h file generated by + * tools/verification/rvgen. + */ + +#include +#include +#include +#include +#include +#include +#include + +#ifndef MONITOR_NAME +#error "Please include $(MODEL_NAME).h generated by rvgen" +#endif + +#ifdef CONFIG_RV_REACTORS +#define RV_MONITOR_NAME CONCATENATE(rv_, MONITOR_NAME) +static struct rv_monitor RV_MONITOR_NAME; + +static void rv_cond_react(struct task_struct *task) +{ + if (!rv_reacting_on() || !RV_MONITOR_NAME.react) + return; + RV_MONITOR_NAME.react("rv: "__stringify(MONITOR_NAME)": %s[%d]: violation detected\n", + task->comm, task->pid); +} +#else +static void rv_cond_react(struct task_struct *task) +{ +} +#endif + +static int ltl_monitor_slot = RV_PER_TASK_MONITOR_INIT; + +static void ltl_atoms_fetch(struct task_struct *task, struct ltl_monitor *mon); +static void ltl_atoms_init(struct task_struct *task, struct ltl_monitor *mon, bool task_creation); + +static struct ltl_monitor *ltl_get_monitor(struct task_struct *task) +{ + return &task->rv[ltl_monitor_slot].ltl_mon; +} + +static void ltl_task_init(struct task_struct *task, bool task_creation) +{ + struct ltl_monitor *mon = ltl_get_monitor(task); + + memset(&mon->states, 0, sizeof(mon->states)); + + for (int i = 0; i < LTL_NUM_ATOM; ++i) + __set_bit(i, mon->unknown_atoms); + + ltl_atoms_init(task, mon, task_creation); + ltl_atoms_fetch(task, mon); +} + +static void handle_task_newtask(void *data, struct task_struct *task, unsigned long flags) +{ + ltl_task_init(task, true); +} + +static int ltl_monitor_init(void) +{ + struct task_struct *g, *p; + int ret, cpu; + + ret = rv_get_task_monitor_slot(); + if (ret < 0) + return ret; + + ltl_monitor_slot = ret; + + rv_attach_trace_probe(name, task_newtask, handle_task_newtask); + + read_lock(&tasklist_lock); + + for_each_process_thread(g, p) + ltl_task_init(p, false); + + for_each_present_cpu(cpu) + ltl_task_init(idle_task(cpu), false); + + read_unlock(&tasklist_lock); + + return 0; +} + +static void ltl_monitor_destroy(void) +{ + rv_detach_trace_probe(name, task_newtask, handle_task_newtask); + + rv_put_task_monitor_slot(ltl_monitor_slot); + ltl_monitor_slot = RV_PER_TASK_MONITOR_INIT; +} + +static void ltl_illegal_state(struct task_struct *task, struct ltl_monitor *mon) +{ + CONCATENATE(trace_error_, MONITOR_NAME)(task); + rv_cond_react(task); +} + +static void ltl_attempt_start(struct task_struct *task, struct ltl_monitor *mon) +{ + if (rv_ltl_all_atoms_known(mon)) + ltl_start(task, mon); +} + +static inline void ltl_atom_set(struct ltl_monitor *mon, enum ltl_atom atom, bool value) +{ + __clear_bit(atom, mon->unknown_atoms); + if (value) + __set_bit(atom, mon->atoms); + else + __clear_bit(atom, mon->atoms); +} + +static void +ltl_trace_event(struct task_struct *task, struct ltl_monitor *mon, unsigned long *next_state) +{ + const char *format_str = "%s"; + DECLARE_SEQ_BUF(atoms, 64); + char states[32], next[32]; + int i; + + if (!CONCATENATE(CONCATENATE(trace_event_, MONITOR_NAME), _enabled)()) + return; + + snprintf(states, sizeof(states), "%*pbl", RV_MAX_BA_STATES, mon->states); + snprintf(next, sizeof(next), "%*pbl", RV_MAX_BA_STATES, next_state); + + for (i = 0; i < LTL_NUM_ATOM; ++i) { + if (test_bit(i, mon->atoms)) { + seq_buf_printf(&atoms, format_str, ltl_atom_str(i)); + format_str = ",%s"; + } + } + + CONCATENATE(trace_event_, MONITOR_NAME)(task, states, atoms.buffer, next); +} + +static void ltl_validate(struct task_struct *task, struct ltl_monitor *mon) +{ + DECLARE_BITMAP(next_states, RV_MAX_BA_STATES) = {0}; + + if (!rv_ltl_valid_state(mon)) + return; + + for (unsigned int i = 0; i < RV_NUM_BA_STATES; ++i) { + if (test_bit(i, mon->states)) + ltl_possible_next_states(mon, i, next_states); + } + + ltl_trace_event(task, mon, next_states); + + memcpy(mon->states, next_states, sizeof(next_states)); + + if (!rv_ltl_valid_state(mon)) + ltl_illegal_state(task, mon); +} + +static void ltl_atom_update(struct task_struct *task, enum ltl_atom atom, bool value) +{ + struct ltl_monitor *mon = ltl_get_monitor(task); + + ltl_atom_set(mon, atom, value); + ltl_atoms_fetch(task, mon); + + if (!rv_ltl_valid_state(mon)) + ltl_attempt_start(task, mon); + + ltl_validate(task, mon); +} + +static void __maybe_unused ltl_atom_pulse(struct task_struct *task, enum ltl_atom atom, bool value) +{ + struct ltl_monitor *mon = ltl_get_monitor(task); + + ltl_atom_update(task, atom, value); + + ltl_atom_set(mon, atom, !value); + ltl_validate(task, mon); +} diff --git a/kernel/fork.c b/kernel/fork.c index 1ee8eb11f38b..1f06559d17bf 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1886,10 +1886,7 @@ static void copy_oom_score_adj(u64 clone_flags, struct task_struct *tsk) #ifdef CONFIG_RV static void rv_task_fork(struct task_struct *p) { - int i; - - for (i = 0; i < RV_PER_TASK_MONITORS; i++) - p->rv[i].da_mon.monitoring = false; + memset(&p->rv, 0, sizeof(p->rv)); } #else #define rv_task_fork(p) do {} while (0) diff --git a/kernel/trace/rv/Kconfig b/kernel/trace/rv/Kconfig index 6cdffc04b73c..6e157f964991 100644 --- a/kernel/trace/rv/Kconfig +++ b/kernel/trace/rv/Kconfig @@ -11,6 +11,13 @@ config DA_MON_EVENTS_ID select RV_MON_EVENTS bool +config LTL_MON_EVENTS_ID + select RV_MON_EVENTS + bool + +config RV_LTL_MONITOR + bool + menuconfig RV bool "Runtime Verification" depends on TRACING diff --git a/kernel/trace/rv/rv_trace.h b/kernel/trace/rv/rv_trace.h index 99c3801616d4..fd3111ad1d51 100644 --- a/kernel/trace/rv/rv_trace.h +++ b/kernel/trace/rv/rv_trace.h @@ -127,6 +127,53 @@ DECLARE_EVENT_CLASS(error_da_monitor_id, // Add new monitors based on CONFIG_DA_MON_EVENTS_ID here #endif /* CONFIG_DA_MON_EVENTS_ID */ +#ifdef CONFIG_LTL_MON_EVENTS_ID +DECLARE_EVENT_CLASS(event_ltl_monitor_id, + + TP_PROTO(struct task_struct *task, char *states, char *atoms, char *next), + + TP_ARGS(task, states, atoms, next), + + TP_STRUCT__entry( + __string(comm, task->comm) + __field(pid_t, pid) + __string(states, states) + __string(atoms, atoms) + __string(next, next) + ), + + TP_fast_assign( + __assign_str(comm); + __entry->pid = task->pid; + __assign_str(states); + __assign_str(atoms); + __assign_str(next); + ), + + TP_printk("%s[%d]: (%s) x (%s) -> (%s)", __get_str(comm), __entry->pid, + __get_str(states), __get_str(atoms), __get_str(next)) +); + +DECLARE_EVENT_CLASS(error_ltl_monitor_id, + + TP_PROTO(struct task_struct *task), + + TP_ARGS(task), + + TP_STRUCT__entry( + __string(comm, task->comm) + __field(pid_t, pid) + ), + + TP_fast_assign( + __assign_str(comm); + __entry->pid = task->pid; + ), + + TP_printk("%s[%d]: violation detected", __get_str(comm), __entry->pid) +); +// Add new monitors based on CONFIG_LTL_MON_EVENTS_ID here +#endif /* CONFIG_LTL_MON_EVENTS_ID */ #endif /* _TRACE_RV_H */ /* This part must be outside protection */ -- cgit v1.2.3 From 886fc86e9419a2bf61713ba566eb6edd8e6aa989 Mon Sep 17 00:00:00 2001 From: Nam Cao Date: Wed, 9 Jul 2025 21:21:18 +0200 Subject: rv: Add rtapp container monitor Add the container "rtapp" which is the monitor collection for detecting problems with real-time applications. The monitors will be added in the follow-up commits. Cc: John Ogness Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://lore.kernel.org/fb18b87631d386271de00959d8d4826f23fcd1cd.1752088709.git.namcao@linutronix.de Reviewed-by: Gabriele Monaco Signed-off-by: Nam Cao Signed-off-by: Steven Rostedt (Google) --- kernel/trace/rv/Kconfig | 1 + kernel/trace/rv/Makefile | 1 + kernel/trace/rv/monitors/rtapp/Kconfig | 10 ++++++++++ kernel/trace/rv/monitors/rtapp/rtapp.c | 33 +++++++++++++++++++++++++++++++++ kernel/trace/rv/monitors/rtapp/rtapp.h | 3 +++ 5 files changed, 48 insertions(+) create mode 100644 kernel/trace/rv/monitors/rtapp/Kconfig create mode 100644 kernel/trace/rv/monitors/rtapp/rtapp.c create mode 100644 kernel/trace/rv/monitors/rtapp/rtapp.h (limited to 'kernel/trace') diff --git a/kernel/trace/rv/Kconfig b/kernel/trace/rv/Kconfig index 6e157f964991..5c407d291661 100644 --- a/kernel/trace/rv/Kconfig +++ b/kernel/trace/rv/Kconfig @@ -41,6 +41,7 @@ source "kernel/trace/rv/monitors/snroc/Kconfig" source "kernel/trace/rv/monitors/scpd/Kconfig" source "kernel/trace/rv/monitors/snep/Kconfig" source "kernel/trace/rv/monitors/sncid/Kconfig" +source "kernel/trace/rv/monitors/rtapp/Kconfig" # Add new monitors here config RV_REACTORS diff --git a/kernel/trace/rv/Makefile b/kernel/trace/rv/Makefile index f9b2cd0483c3..9b28c2419995 100644 --- a/kernel/trace/rv/Makefile +++ b/kernel/trace/rv/Makefile @@ -12,6 +12,7 @@ obj-$(CONFIG_RV_MON_SNROC) += monitors/snroc/snroc.o obj-$(CONFIG_RV_MON_SCPD) += monitors/scpd/scpd.o obj-$(CONFIG_RV_MON_SNEP) += monitors/snep/snep.o obj-$(CONFIG_RV_MON_SNCID) += monitors/sncid/sncid.o +obj-$(CONFIG_RV_MON_RTAPP) += monitors/rtapp/rtapp.o # 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/rtapp/Kconfig b/kernel/trace/rv/monitors/rtapp/Kconfig new file mode 100644 index 000000000000..b7415c3570bb --- /dev/null +++ b/kernel/trace/rv/monitors/rtapp/Kconfig @@ -0,0 +1,10 @@ +config RV_MON_RTAPP + depends on RV + bool "rtapp monitor" + help + Collection of monitors to check for common problems with real-time + application that may cause unexpected latency. + + If you are developing a real-time system and not entirely sure whether + the applications are designed correctly for real-time, you want to say + Y here. diff --git a/kernel/trace/rv/monitors/rtapp/rtapp.c b/kernel/trace/rv/monitors/rtapp/rtapp.c new file mode 100644 index 000000000000..fd75fc927d65 --- /dev/null +++ b/kernel/trace/rv/monitors/rtapp/rtapp.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include + +#define MODULE_NAME "rtapp" + +#include "rtapp.h" + +struct rv_monitor rv_rtapp; + +struct rv_monitor rv_rtapp = { + .name = "rtapp", + .description = "Collection of monitors for detecting problems with real-time applications", +}; + +static int __init register_rtapp(void) +{ + return rv_register_monitor(&rv_rtapp, NULL); +} + +static void __exit unregister_rtapp(void) +{ + rv_unregister_monitor(&rv_rtapp); +} + +module_init(register_rtapp); +module_exit(unregister_rtapp); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Nam Cao "); +MODULE_DESCRIPTION("Collection of monitors for detecting problems with real-time applications"); diff --git a/kernel/trace/rv/monitors/rtapp/rtapp.h b/kernel/trace/rv/monitors/rtapp/rtapp.h new file mode 100644 index 000000000000..4c200d67c7f6 --- /dev/null +++ b/kernel/trace/rv/monitors/rtapp/rtapp.h @@ -0,0 +1,3 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +extern struct rv_monitor rv_rtapp; -- cgit v1.2.3 From 9162620eb604d7461da5b02ec379bb50c3c3b604 Mon Sep 17 00:00:00 2001 From: Nam Cao Date: Wed, 9 Jul 2025 21:21:20 +0200 Subject: rv: Add rtapp_pagefault monitor Userspace real-time applications may have design flaws that they raise page faults in real-time threads, and thus have unexpected latencies. Add an linear temporal logic monitor to detect this scenario. Cc: John Ogness Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://lore.kernel.org/78fea8a2de6d058241d3c6502c1a92910772b0ed.1752088709.git.namcao@linutronix.de Reviewed-by: Gabriele Monaco Signed-off-by: Nam Cao Signed-off-by: Steven Rostedt (Google) --- kernel/trace/rv/Kconfig | 1 + kernel/trace/rv/Makefile | 1 + kernel/trace/rv/monitors/pagefault/Kconfig | 20 +++++ kernel/trace/rv/monitors/pagefault/pagefault.c | 88 ++++++++++++++++++++++ kernel/trace/rv/monitors/pagefault/pagefault.h | 64 ++++++++++++++++ .../trace/rv/monitors/pagefault/pagefault_trace.h | 14 ++++ kernel/trace/rv/rv_trace.h | 1 + tools/verification/models/rtapp/pagefault.ltl | 1 + 8 files changed, 190 insertions(+) create mode 100644 kernel/trace/rv/monitors/pagefault/Kconfig create mode 100644 kernel/trace/rv/monitors/pagefault/pagefault.c create mode 100644 kernel/trace/rv/monitors/pagefault/pagefault.h create mode 100644 kernel/trace/rv/monitors/pagefault/pagefault_trace.h create mode 100644 tools/verification/models/rtapp/pagefault.ltl (limited to 'kernel/trace') diff --git a/kernel/trace/rv/Kconfig b/kernel/trace/rv/Kconfig index 5c407d291661..6f86d8501e87 100644 --- a/kernel/trace/rv/Kconfig +++ b/kernel/trace/rv/Kconfig @@ -42,6 +42,7 @@ source "kernel/trace/rv/monitors/scpd/Kconfig" source "kernel/trace/rv/monitors/snep/Kconfig" source "kernel/trace/rv/monitors/sncid/Kconfig" source "kernel/trace/rv/monitors/rtapp/Kconfig" +source "kernel/trace/rv/monitors/pagefault/Kconfig" # Add new monitors here config RV_REACTORS diff --git a/kernel/trace/rv/Makefile b/kernel/trace/rv/Makefile index 9b28c2419995..353ecf939d0e 100644 --- a/kernel/trace/rv/Makefile +++ b/kernel/trace/rv/Makefile @@ -13,6 +13,7 @@ obj-$(CONFIG_RV_MON_SCPD) += monitors/scpd/scpd.o obj-$(CONFIG_RV_MON_SNEP) += monitors/snep/snep.o obj-$(CONFIG_RV_MON_SNCID) += monitors/sncid/sncid.o obj-$(CONFIG_RV_MON_RTAPP) += monitors/rtapp/rtapp.o +obj-$(CONFIG_RV_MON_PAGEFAULT) += monitors/pagefault/pagefault.o # Add new monitors here obj-$(CONFIG_RV_REACTORS) += rv_reactors.o obj-$(CONFIG_RV_REACT_PRINTK) += reactor_printk.o diff --git a/kernel/trace/rv/monitors/pagefault/Kconfig b/kernel/trace/rv/monitors/pagefault/Kconfig new file mode 100644 index 000000000000..5e16625f1653 --- /dev/null +++ b/kernel/trace/rv/monitors/pagefault/Kconfig @@ -0,0 +1,20 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +config RV_MON_PAGEFAULT + depends on RV + select RV_LTL_MONITOR + depends on RV_MON_RTAPP + depends on X86 || RISCV + default y + select LTL_MON_EVENTS_ID + bool "pagefault monitor" + help + Monitor that real-time tasks do not raise page faults, causing + undesirable latency. + + If you are developing a real-time system and not entirely sure whether + the applications are designed correctly for real-time, you want to say + Y here. + + This monitor does not affect execution speed while it is not running, + therefore it is safe to enable this in production kernel. diff --git a/kernel/trace/rv/monitors/pagefault/pagefault.c b/kernel/trace/rv/monitors/pagefault/pagefault.c new file mode 100644 index 000000000000..9fe6123b2200 --- /dev/null +++ b/kernel/trace/rv/monitors/pagefault/pagefault.c @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define MODULE_NAME "pagefault" + +#include +#include +#include + +#include "pagefault.h" +#include + +static void ltl_atoms_fetch(struct task_struct *task, struct ltl_monitor *mon) +{ + /* + * This includes "actual" real-time tasks and also PI-boosted + * tasks. A task being PI-boosted means it is blocking an "actual" + * real-task, therefore it should also obey the monitor's rule, + * otherwise the "actual" real-task may be delayed. + */ + ltl_atom_set(mon, LTL_RT, rt_or_dl_task(task)); +} + +static void ltl_atoms_init(struct task_struct *task, struct ltl_monitor *mon, bool task_creation) +{ + if (task_creation) + ltl_atom_set(mon, LTL_PAGEFAULT, false); +} + +static void handle_page_fault(void *data, unsigned long address, struct pt_regs *regs, + unsigned long error_code) +{ + ltl_atom_pulse(current, LTL_PAGEFAULT, true); +} + +static int enable_pagefault(void) +{ + int retval; + + retval = ltl_monitor_init(); + if (retval) + return retval; + + rv_attach_trace_probe("rtapp_pagefault", page_fault_kernel, handle_page_fault); + rv_attach_trace_probe("rtapp_pagefault", page_fault_user, handle_page_fault); + + return 0; +} + +static void disable_pagefault(void) +{ + rv_detach_trace_probe("rtapp_pagefault", page_fault_kernel, handle_page_fault); + rv_detach_trace_probe("rtapp_pagefault", page_fault_user, handle_page_fault); + + ltl_monitor_destroy(); +} + +static struct rv_monitor rv_pagefault = { + .name = "pagefault", + .description = "Monitor that RT tasks do not raise page faults", + .enable = enable_pagefault, + .disable = disable_pagefault, +}; + +static int __init register_pagefault(void) +{ + return rv_register_monitor(&rv_pagefault, &rv_rtapp); +} + +static void __exit unregister_pagefault(void) +{ + rv_unregister_monitor(&rv_pagefault); +} + +module_init(register_pagefault); +module_exit(unregister_pagefault); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Nam Cao "); +MODULE_DESCRIPTION("pagefault: Monitor that RT tasks do not raise page faults"); diff --git a/kernel/trace/rv/monitors/pagefault/pagefault.h b/kernel/trace/rv/monitors/pagefault/pagefault.h new file mode 100644 index 000000000000..c580ec194009 --- /dev/null +++ b/kernel/trace/rv/monitors/pagefault/pagefault.h @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * C implementation of Buchi automaton, automatically generated by + * tools/verification/rvgen from the linear temporal logic specification. + * For further information, see kernel documentation: + * Documentation/trace/rv/linear_temporal_logic.rst + */ + +#include + +#define MONITOR_NAME pagefault + +enum ltl_atom { + LTL_PAGEFAULT, + LTL_RT, + LTL_NUM_ATOM +}; +static_assert(LTL_NUM_ATOM <= RV_MAX_LTL_ATOM); + +static const char *ltl_atom_str(enum ltl_atom atom) +{ + static const char *const names[] = { + "pa", + "rt", + }; + + return names[atom]; +} + +enum ltl_buchi_state { + S0, + RV_NUM_BA_STATES +}; +static_assert(RV_NUM_BA_STATES <= RV_MAX_BA_STATES); + +static void ltl_start(struct task_struct *task, struct ltl_monitor *mon) +{ + bool pagefault = test_bit(LTL_PAGEFAULT, mon->atoms); + bool val3 = !pagefault; + bool rt = test_bit(LTL_RT, mon->atoms); + bool val1 = !rt; + bool val4 = val1 || val3; + + if (val4) + __set_bit(S0, mon->states); +} + +static void +ltl_possible_next_states(struct ltl_monitor *mon, unsigned int state, unsigned long *next) +{ + bool pagefault = test_bit(LTL_PAGEFAULT, mon->atoms); + bool val3 = !pagefault; + bool rt = test_bit(LTL_RT, mon->atoms); + bool val1 = !rt; + bool val4 = val1 || val3; + + switch (state) { + case S0: + if (val4) + __set_bit(S0, next); + break; + } +} diff --git a/kernel/trace/rv/monitors/pagefault/pagefault_trace.h b/kernel/trace/rv/monitors/pagefault/pagefault_trace.h new file mode 100644 index 000000000000..fe1f82597b1a --- /dev/null +++ b/kernel/trace/rv/monitors/pagefault/pagefault_trace.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Snippet to be included in rv_trace.h + */ + +#ifdef CONFIG_RV_MON_PAGEFAULT +DEFINE_EVENT(event_ltl_monitor_id, event_pagefault, + TP_PROTO(struct task_struct *task, char *states, char *atoms, char *next), + TP_ARGS(task, states, atoms, next)); +DEFINE_EVENT(error_ltl_monitor_id, error_pagefault, + TP_PROTO(struct task_struct *task), + TP_ARGS(task)); +#endif /* CONFIG_RV_MON_PAGEFAULT */ diff --git a/kernel/trace/rv/rv_trace.h b/kernel/trace/rv/rv_trace.h index fd3111ad1d51..98eee8ec96e4 100644 --- a/kernel/trace/rv/rv_trace.h +++ b/kernel/trace/rv/rv_trace.h @@ -172,6 +172,7 @@ DECLARE_EVENT_CLASS(error_ltl_monitor_id, TP_printk("%s[%d]: violation detected", __get_str(comm), __entry->pid) ); +#include // Add new monitors based on CONFIG_LTL_MON_EVENTS_ID here #endif /* CONFIG_LTL_MON_EVENTS_ID */ #endif /* _TRACE_RV_H */ diff --git a/tools/verification/models/rtapp/pagefault.ltl b/tools/verification/models/rtapp/pagefault.ltl new file mode 100644 index 000000000000..d7ce62102733 --- /dev/null +++ b/tools/verification/models/rtapp/pagefault.ltl @@ -0,0 +1 @@ +RULE = always (RT imply not PAGEFAULT) -- cgit v1.2.3 From f74f8bb246cf22f27752977da62079cb615f55b2 Mon Sep 17 00:00:00 2001 From: Nam Cao Date: Wed, 9 Jul 2025 21:21:21 +0200 Subject: rv: Add rtapp_sleep monitor Add a monitor for checking that real-time tasks do not go to sleep in a manner that may cause undesirable latency. Also change RV depends on TRACING to RV select TRACING to avoid the following recursive dependency: error: recursive dependency detected! symbol TRACING is selected by PREEMPTIRQ_TRACEPOINTS symbol PREEMPTIRQ_TRACEPOINTS depends on TRACE_IRQFLAGS symbol TRACE_IRQFLAGS is selected by RV_MON_SLEEP symbol RV_MON_SLEEP depends on RV symbol RV depends on TRACING Cc: John Ogness Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://lore.kernel.org/75bc5bcc741d153aa279c95faf778dff35c5c8ad.1752088709.git.namcao@linutronix.de Reviewed-by: Gabriele Monaco Signed-off-by: Nam Cao Signed-off-by: Steven Rostedt (Google) --- kernel/trace/rv/Kconfig | 3 +- kernel/trace/rv/Makefile | 1 + kernel/trace/rv/monitors/sleep/Kconfig | 22 +++ kernel/trace/rv/monitors/sleep/sleep.c | 237 ++++++++++++++++++++++++ kernel/trace/rv/monitors/sleep/sleep.h | 257 +++++++++++++++++++++++++++ kernel/trace/rv/monitors/sleep/sleep_trace.h | 14 ++ kernel/trace/rv/rv_trace.h | 1 + tools/verification/models/rtapp/sleep.ltl | 22 +++ 8 files changed, 556 insertions(+), 1 deletion(-) create mode 100644 kernel/trace/rv/monitors/sleep/Kconfig create mode 100644 kernel/trace/rv/monitors/sleep/sleep.c create mode 100644 kernel/trace/rv/monitors/sleep/sleep.h create mode 100644 kernel/trace/rv/monitors/sleep/sleep_trace.h create mode 100644 tools/verification/models/rtapp/sleep.ltl (limited to 'kernel/trace') diff --git a/kernel/trace/rv/Kconfig b/kernel/trace/rv/Kconfig index 6f86d8501e87..942d57575e67 100644 --- a/kernel/trace/rv/Kconfig +++ b/kernel/trace/rv/Kconfig @@ -20,7 +20,7 @@ config RV_LTL_MONITOR menuconfig RV bool "Runtime Verification" - depends on TRACING + select TRACING help Enable the kernel runtime verification infrastructure. RV is a lightweight (yet rigorous) method that complements classical @@ -43,6 +43,7 @@ source "kernel/trace/rv/monitors/snep/Kconfig" source "kernel/trace/rv/monitors/sncid/Kconfig" source "kernel/trace/rv/monitors/rtapp/Kconfig" source "kernel/trace/rv/monitors/pagefault/Kconfig" +source "kernel/trace/rv/monitors/sleep/Kconfig" # Add new monitors here config RV_REACTORS diff --git a/kernel/trace/rv/Makefile b/kernel/trace/rv/Makefile index 353ecf939d0e..13ec2944c665 100644 --- a/kernel/trace/rv/Makefile +++ b/kernel/trace/rv/Makefile @@ -14,6 +14,7 @@ obj-$(CONFIG_RV_MON_SNEP) += monitors/snep/snep.o obj-$(CONFIG_RV_MON_SNCID) += monitors/sncid/sncid.o obj-$(CONFIG_RV_MON_RTAPP) += monitors/rtapp/rtapp.o obj-$(CONFIG_RV_MON_PAGEFAULT) += monitors/pagefault/pagefault.o +obj-$(CONFIG_RV_MON_SLEEP) += monitors/sleep/sleep.o # 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/sleep/Kconfig b/kernel/trace/rv/monitors/sleep/Kconfig new file mode 100644 index 000000000000..6b7a122e7b47 --- /dev/null +++ b/kernel/trace/rv/monitors/sleep/Kconfig @@ -0,0 +1,22 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +config RV_MON_SLEEP + depends on RV + select RV_LTL_MONITOR + depends on HAVE_SYSCALL_TRACEPOINTS + depends on RV_MON_RTAPP + select TRACE_IRQFLAGS + default y + select LTL_MON_EVENTS_ID + bool "sleep monitor" + help + Monitor that real-time tasks do not sleep in a manner that may + cause undesirable latency. + + If you are developing a real-time system and not entirely sure whether + the applications are designed correctly for real-time, you want to say + Y here. + + Enabling this monitor may have performance impact (due to select + TRACE_IRQFLAGS). Therefore, you probably should say N for + production kernel. diff --git a/kernel/trace/rv/monitors/sleep/sleep.c b/kernel/trace/rv/monitors/sleep/sleep.c new file mode 100644 index 000000000000..eea447b06907 --- /dev/null +++ b/kernel/trace/rv/monitors/sleep/sleep.c @@ -0,0 +1,237 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define MODULE_NAME "sleep" + +#include +#include +#include +#include +#include +#include + +#include "sleep.h" +#include + +static void ltl_atoms_fetch(struct task_struct *task, struct ltl_monitor *mon) +{ + /* + * This includes "actual" real-time tasks and also PI-boosted + * tasks. A task being PI-boosted means it is blocking an "actual" + * real-task, therefore it should also obey the monitor's rule, + * otherwise the "actual" real-task may be delayed. + */ + ltl_atom_set(mon, LTL_RT, rt_or_dl_task(task)); +} + +static void ltl_atoms_init(struct task_struct *task, struct ltl_monitor *mon, bool task_creation) +{ + ltl_atom_set(mon, LTL_SLEEP, false); + ltl_atom_set(mon, LTL_WAKE, false); + ltl_atom_set(mon, LTL_ABORT_SLEEP, false); + ltl_atom_set(mon, LTL_WOKEN_BY_HARDIRQ, false); + ltl_atom_set(mon, LTL_WOKEN_BY_NMI, false); + ltl_atom_set(mon, LTL_WOKEN_BY_EQUAL_OR_HIGHER_PRIO, false); + + if (task_creation) { + ltl_atom_set(mon, LTL_KTHREAD_SHOULD_STOP, false); + ltl_atom_set(mon, LTL_NANOSLEEP_CLOCK_MONOTONIC, false); + ltl_atom_set(mon, LTL_NANOSLEEP_CLOCK_TAI, false); + ltl_atom_set(mon, LTL_NANOSLEEP_TIMER_ABSTIME, false); + ltl_atom_set(mon, LTL_CLOCK_NANOSLEEP, false); + ltl_atom_set(mon, LTL_FUTEX_WAIT, false); + ltl_atom_set(mon, LTL_FUTEX_LOCK_PI, false); + ltl_atom_set(mon, LTL_BLOCK_ON_RT_MUTEX, false); + } + + if (task->flags & PF_KTHREAD) { + ltl_atom_set(mon, LTL_KERNEL_THREAD, true); + + /* kernel tasks do not do syscall */ + ltl_atom_set(mon, LTL_FUTEX_WAIT, false); + ltl_atom_set(mon, LTL_FUTEX_LOCK_PI, false); + ltl_atom_set(mon, LTL_NANOSLEEP_CLOCK_MONOTONIC, false); + ltl_atom_set(mon, LTL_NANOSLEEP_CLOCK_TAI, false); + ltl_atom_set(mon, LTL_NANOSLEEP_TIMER_ABSTIME, false); + ltl_atom_set(mon, LTL_CLOCK_NANOSLEEP, false); + + if (strstarts(task->comm, "migration/")) + ltl_atom_set(mon, LTL_TASK_IS_MIGRATION, true); + else + ltl_atom_set(mon, LTL_TASK_IS_MIGRATION, false); + + if (strstarts(task->comm, "rcu")) + ltl_atom_set(mon, LTL_TASK_IS_RCU, true); + else + ltl_atom_set(mon, LTL_TASK_IS_RCU, false); + } else { + ltl_atom_set(mon, LTL_KTHREAD_SHOULD_STOP, false); + ltl_atom_set(mon, LTL_KERNEL_THREAD, false); + ltl_atom_set(mon, LTL_TASK_IS_RCU, false); + ltl_atom_set(mon, LTL_TASK_IS_MIGRATION, false); + } + +} + +static void handle_sched_set_state(void *data, struct task_struct *task, int state) +{ + if (state & TASK_INTERRUPTIBLE) + ltl_atom_pulse(task, LTL_SLEEP, true); + else if (state == TASK_RUNNING) + ltl_atom_pulse(task, LTL_ABORT_SLEEP, true); +} + +static void handle_sched_wakeup(void *data, struct task_struct *task) +{ + ltl_atom_pulse(task, LTL_WAKE, true); +} + +static void handle_sched_waking(void *data, struct task_struct *task) +{ + if (this_cpu_read(hardirq_context)) { + ltl_atom_pulse(task, LTL_WOKEN_BY_HARDIRQ, true); + } else if (in_task()) { + if (current->prio <= task->prio) + ltl_atom_pulse(task, LTL_WOKEN_BY_EQUAL_OR_HIGHER_PRIO, true); + } else if (in_nmi()) { + ltl_atom_pulse(task, LTL_WOKEN_BY_NMI, true); + } +} + +static void handle_contention_begin(void *data, void *lock, unsigned int flags) +{ + if (flags & LCB_F_RT) + ltl_atom_update(current, LTL_BLOCK_ON_RT_MUTEX, true); +} + +static void handle_contention_end(void *data, void *lock, int ret) +{ + ltl_atom_update(current, LTL_BLOCK_ON_RT_MUTEX, false); +} + +static void handle_sys_enter(void *data, struct pt_regs *regs, long id) +{ + struct ltl_monitor *mon; + unsigned long args[6]; + int op, cmd; + + mon = ltl_get_monitor(current); + + switch (id) { + case __NR_clock_nanosleep: +#ifdef __NR_clock_nanosleep_time64 + case __NR_clock_nanosleep_time64: +#endif + syscall_get_arguments(current, regs, args); + ltl_atom_set(mon, LTL_NANOSLEEP_CLOCK_MONOTONIC, args[0] == CLOCK_MONOTONIC); + ltl_atom_set(mon, LTL_NANOSLEEP_CLOCK_TAI, args[0] == CLOCK_TAI); + ltl_atom_set(mon, LTL_NANOSLEEP_TIMER_ABSTIME, args[1] == TIMER_ABSTIME); + ltl_atom_update(current, LTL_CLOCK_NANOSLEEP, true); + break; + + case __NR_futex: +#ifdef __NR_futex_time64 + case __NR_futex_time64: +#endif + syscall_get_arguments(current, regs, args); + op = args[1]; + cmd = op & FUTEX_CMD_MASK; + + switch (cmd) { + case FUTEX_LOCK_PI: + case FUTEX_LOCK_PI2: + ltl_atom_update(current, LTL_FUTEX_LOCK_PI, true); + break; + case FUTEX_WAIT: + case FUTEX_WAIT_BITSET: + case FUTEX_WAIT_REQUEUE_PI: + ltl_atom_update(current, LTL_FUTEX_WAIT, true); + break; + } + break; + } +} + +static void handle_sys_exit(void *data, struct pt_regs *regs, long ret) +{ + struct ltl_monitor *mon = ltl_get_monitor(current); + + ltl_atom_set(mon, LTL_FUTEX_LOCK_PI, false); + ltl_atom_set(mon, LTL_FUTEX_WAIT, false); + ltl_atom_set(mon, LTL_NANOSLEEP_CLOCK_MONOTONIC, false); + ltl_atom_set(mon, LTL_NANOSLEEP_CLOCK_TAI, false); + ltl_atom_set(mon, LTL_NANOSLEEP_TIMER_ABSTIME, false); + ltl_atom_update(current, LTL_CLOCK_NANOSLEEP, false); +} + +static void handle_kthread_stop(void *data, struct task_struct *task) +{ + /* FIXME: this could race with other tracepoint handlers */ + ltl_atom_update(task, LTL_KTHREAD_SHOULD_STOP, true); +} + +static int enable_sleep(void) +{ + int retval; + + retval = ltl_monitor_init(); + if (retval) + return retval; + + rv_attach_trace_probe("rtapp_sleep", sched_waking, handle_sched_waking); + rv_attach_trace_probe("rtapp_sleep", sched_wakeup, handle_sched_wakeup); + rv_attach_trace_probe("rtapp_sleep", sched_set_state_tp, handle_sched_set_state); + rv_attach_trace_probe("rtapp_sleep", contention_begin, handle_contention_begin); + rv_attach_trace_probe("rtapp_sleep", contention_end, handle_contention_end); + rv_attach_trace_probe("rtapp_sleep", sched_kthread_stop, handle_kthread_stop); + rv_attach_trace_probe("rtapp_sleep", sys_enter, handle_sys_enter); + rv_attach_trace_probe("rtapp_sleep", sys_exit, handle_sys_exit); + return 0; +} + +static void disable_sleep(void) +{ + rv_detach_trace_probe("rtapp_sleep", sched_waking, handle_sched_waking); + rv_detach_trace_probe("rtapp_sleep", sched_wakeup, handle_sched_wakeup); + rv_detach_trace_probe("rtapp_sleep", sched_set_state_tp, handle_sched_set_state); + rv_detach_trace_probe("rtapp_sleep", contention_begin, handle_contention_begin); + rv_detach_trace_probe("rtapp_sleep", contention_end, handle_contention_end); + rv_detach_trace_probe("rtapp_sleep", sched_kthread_stop, handle_kthread_stop); + rv_detach_trace_probe("rtapp_sleep", sys_enter, handle_sys_enter); + rv_detach_trace_probe("rtapp_sleep", sys_exit, handle_sys_exit); + + ltl_monitor_destroy(); +} + +static struct rv_monitor rv_sleep = { + .name = "sleep", + .description = "Monitor that RT tasks do not undesirably sleep", + .enable = enable_sleep, + .disable = disable_sleep, +}; + +static int __init register_sleep(void) +{ + return rv_register_monitor(&rv_sleep, &rv_rtapp); +} + +static void __exit unregister_sleep(void) +{ + rv_unregister_monitor(&rv_sleep); +} + +module_init(register_sleep); +module_exit(unregister_sleep); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Nam Cao "); +MODULE_DESCRIPTION("sleep: Monitor that RT tasks do not undesirably sleep"); diff --git a/kernel/trace/rv/monitors/sleep/sleep.h b/kernel/trace/rv/monitors/sleep/sleep.h new file mode 100644 index 000000000000..2ab46fd218d2 --- /dev/null +++ b/kernel/trace/rv/monitors/sleep/sleep.h @@ -0,0 +1,257 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * C implementation of Buchi automaton, automatically generated by + * tools/verification/rvgen from the linear temporal logic specification. + * For further information, see kernel documentation: + * Documentation/trace/rv/linear_temporal_logic.rst + */ + +#include + +#define MONITOR_NAME sleep + +enum ltl_atom { + LTL_ABORT_SLEEP, + LTL_BLOCK_ON_RT_MUTEX, + LTL_CLOCK_NANOSLEEP, + LTL_FUTEX_LOCK_PI, + LTL_FUTEX_WAIT, + LTL_KERNEL_THREAD, + LTL_KTHREAD_SHOULD_STOP, + LTL_NANOSLEEP_CLOCK_MONOTONIC, + LTL_NANOSLEEP_CLOCK_TAI, + LTL_NANOSLEEP_TIMER_ABSTIME, + LTL_RT, + LTL_SLEEP, + LTL_TASK_IS_MIGRATION, + LTL_TASK_IS_RCU, + LTL_WAKE, + LTL_WOKEN_BY_EQUAL_OR_HIGHER_PRIO, + LTL_WOKEN_BY_HARDIRQ, + LTL_WOKEN_BY_NMI, + LTL_NUM_ATOM +}; +static_assert(LTL_NUM_ATOM <= RV_MAX_LTL_ATOM); + +static const char *ltl_atom_str(enum ltl_atom atom) +{ + static const char *const names[] = { + "ab_sl", + "bl_on_rt_mu", + "cl_na", + "fu_lo_pi", + "fu_wa", + "ker_th", + "kth_sh_st", + "na_cl_mo", + "na_cl_ta", + "na_ti_ab", + "rt", + "sl", + "ta_mi", + "ta_rc", + "wak", + "wo_eq_hi_pr", + "wo_ha", + "wo_nm", + }; + + return names[atom]; +} + +enum ltl_buchi_state { + S0, + S1, + S2, + S3, + S4, + S5, + S6, + S7, + RV_NUM_BA_STATES +}; +static_assert(RV_NUM_BA_STATES <= RV_MAX_BA_STATES); + +static void ltl_start(struct task_struct *task, struct ltl_monitor *mon) +{ + bool task_is_migration = test_bit(LTL_TASK_IS_MIGRATION, mon->atoms); + bool task_is_rcu = test_bit(LTL_TASK_IS_RCU, mon->atoms); + bool val40 = task_is_rcu || task_is_migration; + bool futex_lock_pi = test_bit(LTL_FUTEX_LOCK_PI, mon->atoms); + bool val41 = futex_lock_pi || val40; + bool block_on_rt_mutex = test_bit(LTL_BLOCK_ON_RT_MUTEX, mon->atoms); + bool val5 = block_on_rt_mutex || val41; + bool kthread_should_stop = test_bit(LTL_KTHREAD_SHOULD_STOP, mon->atoms); + bool abort_sleep = test_bit(LTL_ABORT_SLEEP, mon->atoms); + bool val32 = abort_sleep || kthread_should_stop; + bool woken_by_nmi = test_bit(LTL_WOKEN_BY_NMI, mon->atoms); + bool val33 = woken_by_nmi || val32; + bool woken_by_hardirq = test_bit(LTL_WOKEN_BY_HARDIRQ, mon->atoms); + bool val34 = woken_by_hardirq || val33; + bool woken_by_equal_or_higher_prio = test_bit(LTL_WOKEN_BY_EQUAL_OR_HIGHER_PRIO, + mon->atoms); + bool val14 = woken_by_equal_or_higher_prio || val34; + bool wake = test_bit(LTL_WAKE, mon->atoms); + bool val13 = !wake; + bool kernel_thread = test_bit(LTL_KERNEL_THREAD, mon->atoms); + bool nanosleep_clock_tai = test_bit(LTL_NANOSLEEP_CLOCK_TAI, mon->atoms); + bool nanosleep_clock_monotonic = test_bit(LTL_NANOSLEEP_CLOCK_MONOTONIC, mon->atoms); + bool val24 = nanosleep_clock_monotonic || nanosleep_clock_tai; + bool nanosleep_timer_abstime = test_bit(LTL_NANOSLEEP_TIMER_ABSTIME, mon->atoms); + bool val25 = nanosleep_timer_abstime && val24; + bool clock_nanosleep = test_bit(LTL_CLOCK_NANOSLEEP, mon->atoms); + bool val18 = clock_nanosleep && val25; + bool futex_wait = test_bit(LTL_FUTEX_WAIT, mon->atoms); + bool val9 = futex_wait || val18; + bool val11 = val9 || kernel_thread; + bool sleep = test_bit(LTL_SLEEP, mon->atoms); + bool val2 = !sleep; + bool rt = test_bit(LTL_RT, mon->atoms); + bool val1 = !rt; + bool val3 = val1 || val2; + + if (val3) + __set_bit(S0, mon->states); + if (val11 && val13) + __set_bit(S1, mon->states); + if (val11 && val14) + __set_bit(S4, mon->states); + if (val5) + __set_bit(S5, mon->states); +} + +static void +ltl_possible_next_states(struct ltl_monitor *mon, unsigned int state, unsigned long *next) +{ + bool task_is_migration = test_bit(LTL_TASK_IS_MIGRATION, mon->atoms); + bool task_is_rcu = test_bit(LTL_TASK_IS_RCU, mon->atoms); + bool val40 = task_is_rcu || task_is_migration; + bool futex_lock_pi = test_bit(LTL_FUTEX_LOCK_PI, mon->atoms); + bool val41 = futex_lock_pi || val40; + bool block_on_rt_mutex = test_bit(LTL_BLOCK_ON_RT_MUTEX, mon->atoms); + bool val5 = block_on_rt_mutex || val41; + bool kthread_should_stop = test_bit(LTL_KTHREAD_SHOULD_STOP, mon->atoms); + bool abort_sleep = test_bit(LTL_ABORT_SLEEP, mon->atoms); + bool val32 = abort_sleep || kthread_should_stop; + bool woken_by_nmi = test_bit(LTL_WOKEN_BY_NMI, mon->atoms); + bool val33 = woken_by_nmi || val32; + bool woken_by_hardirq = test_bit(LTL_WOKEN_BY_HARDIRQ, mon->atoms); + bool val34 = woken_by_hardirq || val33; + bool woken_by_equal_or_higher_prio = test_bit(LTL_WOKEN_BY_EQUAL_OR_HIGHER_PRIO, + mon->atoms); + bool val14 = woken_by_equal_or_higher_prio || val34; + bool wake = test_bit(LTL_WAKE, mon->atoms); + bool val13 = !wake; + bool kernel_thread = test_bit(LTL_KERNEL_THREAD, mon->atoms); + bool nanosleep_clock_tai = test_bit(LTL_NANOSLEEP_CLOCK_TAI, mon->atoms); + bool nanosleep_clock_monotonic = test_bit(LTL_NANOSLEEP_CLOCK_MONOTONIC, mon->atoms); + bool val24 = nanosleep_clock_monotonic || nanosleep_clock_tai; + bool nanosleep_timer_abstime = test_bit(LTL_NANOSLEEP_TIMER_ABSTIME, mon->atoms); + bool val25 = nanosleep_timer_abstime && val24; + bool clock_nanosleep = test_bit(LTL_CLOCK_NANOSLEEP, mon->atoms); + bool val18 = clock_nanosleep && val25; + bool futex_wait = test_bit(LTL_FUTEX_WAIT, mon->atoms); + bool val9 = futex_wait || val18; + bool val11 = val9 || kernel_thread; + bool sleep = test_bit(LTL_SLEEP, mon->atoms); + bool val2 = !sleep; + bool rt = test_bit(LTL_RT, mon->atoms); + bool val1 = !rt; + bool val3 = val1 || val2; + + switch (state) { + case S0: + if (val3) + __set_bit(S0, next); + if (val11 && val13) + __set_bit(S1, next); + if (val11 && val14) + __set_bit(S4, next); + if (val5) + __set_bit(S5, next); + break; + case S1: + if (val11 && val13) + __set_bit(S1, next); + if (val13 && val3) + __set_bit(S2, next); + if (val14 && val3) + __set_bit(S3, next); + if (val11 && val14) + __set_bit(S4, next); + if (val13 && val5) + __set_bit(S6, next); + if (val14 && val5) + __set_bit(S7, next); + break; + case S2: + if (val11 && val13) + __set_bit(S1, next); + if (val13 && val3) + __set_bit(S2, next); + if (val14 && val3) + __set_bit(S3, next); + if (val11 && val14) + __set_bit(S4, next); + if (val13 && val5) + __set_bit(S6, next); + if (val14 && val5) + __set_bit(S7, next); + break; + case S3: + if (val3) + __set_bit(S0, next); + if (val11 && val13) + __set_bit(S1, next); + if (val11 && val14) + __set_bit(S4, next); + if (val5) + __set_bit(S5, next); + break; + case S4: + if (val3) + __set_bit(S0, next); + if (val11 && val13) + __set_bit(S1, next); + if (val11 && val14) + __set_bit(S4, next); + if (val5) + __set_bit(S5, next); + break; + case S5: + if (val3) + __set_bit(S0, next); + if (val11 && val13) + __set_bit(S1, next); + if (val11 && val14) + __set_bit(S4, next); + if (val5) + __set_bit(S5, next); + break; + case S6: + if (val11 && val13) + __set_bit(S1, next); + if (val13 && val3) + __set_bit(S2, next); + if (val14 && val3) + __set_bit(S3, next); + if (val11 && val14) + __set_bit(S4, next); + if (val13 && val5) + __set_bit(S6, next); + if (val14 && val5) + __set_bit(S7, next); + break; + case S7: + if (val3) + __set_bit(S0, next); + if (val11 && val13) + __set_bit(S1, next); + if (val11 && val14) + __set_bit(S4, next); + if (val5) + __set_bit(S5, next); + break; + } +} diff --git a/kernel/trace/rv/monitors/sleep/sleep_trace.h b/kernel/trace/rv/monitors/sleep/sleep_trace.h new file mode 100644 index 000000000000..22eaf31da987 --- /dev/null +++ b/kernel/trace/rv/monitors/sleep/sleep_trace.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Snippet to be included in rv_trace.h + */ + +#ifdef CONFIG_RV_MON_SLEEP +DEFINE_EVENT(event_ltl_monitor_id, event_sleep, + TP_PROTO(struct task_struct *task, char *states, char *atoms, char *next), + TP_ARGS(task, states, atoms, next)); +DEFINE_EVENT(error_ltl_monitor_id, error_sleep, + TP_PROTO(struct task_struct *task), + TP_ARGS(task)); +#endif /* CONFIG_RV_MON_SLEEP */ diff --git a/kernel/trace/rv/rv_trace.h b/kernel/trace/rv/rv_trace.h index 98eee8ec96e4..b6f310498466 100644 --- a/kernel/trace/rv/rv_trace.h +++ b/kernel/trace/rv/rv_trace.h @@ -173,6 +173,7 @@ DECLARE_EVENT_CLASS(error_ltl_monitor_id, TP_printk("%s[%d]: violation detected", __get_str(comm), __entry->pid) ); #include +#include // Add new monitors based on CONFIG_LTL_MON_EVENTS_ID here #endif /* CONFIG_LTL_MON_EVENTS_ID */ #endif /* _TRACE_RV_H */ diff --git a/tools/verification/models/rtapp/sleep.ltl b/tools/verification/models/rtapp/sleep.ltl new file mode 100644 index 000000000000..6379bbeb6212 --- /dev/null +++ b/tools/verification/models/rtapp/sleep.ltl @@ -0,0 +1,22 @@ +RULE = always ((RT and SLEEP) imply (RT_FRIENDLY_SLEEP or ALLOWLIST)) + +RT_FRIENDLY_SLEEP = (RT_VALID_SLEEP_REASON or KERNEL_THREAD) + and ((not WAKE) until RT_FRIENDLY_WAKE) + +RT_VALID_SLEEP_REASON = FUTEX_WAIT + or RT_FRIENDLY_NANOSLEEP + +RT_FRIENDLY_NANOSLEEP = CLOCK_NANOSLEEP + and NANOSLEEP_TIMER_ABSTIME + and (NANOSLEEP_CLOCK_MONOTONIC or NANOSLEEP_CLOCK_TAI) + +RT_FRIENDLY_WAKE = WOKEN_BY_EQUAL_OR_HIGHER_PRIO + or WOKEN_BY_HARDIRQ + or WOKEN_BY_NMI + or ABORT_SLEEP + or KTHREAD_SHOULD_STOP + +ALLOWLIST = BLOCK_ON_RT_MUTEX + or FUTEX_LOCK_PI + or TASK_IS_RCU + or TASK_IS_MIGRATION -- cgit v1.2.3 From fac5493251a680cb74343895d0e76843624a90d8 Mon Sep 17 00:00:00 2001 From: Nam Cao Date: Wed, 9 Jul 2025 21:21:23 +0200 Subject: rv: Allow to configure the number of per-task monitor Now that there are 2 monitors for real-time applications, users may want to enable both of them simultaneously. Make the number of per-task monitor configurable. Default it to 2 for now. Cc: John Ogness Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://lore.kernel.org/93e83313fc4ba7f6e66f4abe80ca5f5494d658d0.1752088709.git.namcao@linutronix.de Reviewed-by: Gabriele Monaco Signed-off-by: Nam Cao Signed-off-by: Steven Rostedt (Google) --- include/linux/rv.h | 9 +-------- include/linux/sched.h | 8 +++----- kernel/trace/rv/Kconfig | 9 +++++++++ kernel/trace/rv/monitors/rtapp/Kconfig | 1 + kernel/trace/rv/rv.c | 8 ++++---- 5 files changed, 18 insertions(+), 17 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/rv.h b/include/linux/rv.h index 1d5579f9b75a..97baf58d88b2 100644 --- a/include/linux/rv.h +++ b/include/linux/rv.h @@ -75,14 +75,7 @@ struct ltl_monitor {}; #endif /* CONFIG_RV_LTL_MONITOR */ -/* - * Per-task RV monitors count. Nowadays fixed in RV_PER_TASK_MONITORS. - * If we find justification for more monitors, we can think about - * adding more or developing a dynamic method. So far, none of - * these are justified. - */ -#define RV_PER_TASK_MONITORS 1 -#define RV_PER_TASK_MONITOR_INIT (RV_PER_TASK_MONITORS) +#define RV_PER_TASK_MONITOR_INIT (CONFIG_RV_PER_TASK_MONITORS) union rv_task_monitor { struct da_monitor da_mon; diff --git a/include/linux/sched.h b/include/linux/sched.h index 4f78a64beb52..fabd7fe1a07a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1642,12 +1642,10 @@ struct task_struct { #ifdef CONFIG_RV /* - * Per-task RV monitor. Nowadays fixed in RV_PER_TASK_MONITORS. - * If we find justification for more monitors, we can think - * about adding more or developing a dynamic method. So far, - * none of these are justified. + * Per-task RV monitor, fixed in CONFIG_RV_PER_TASK_MONITORS. + * If memory becomes a concern, we can think about a dynamic method. */ - union rv_task_monitor rv[RV_PER_TASK_MONITORS]; + union rv_task_monitor rv[CONFIG_RV_PER_TASK_MONITORS]; #endif #ifdef CONFIG_USER_EVENTS diff --git a/kernel/trace/rv/Kconfig b/kernel/trace/rv/Kconfig index 942d57575e67..c11bf7e61ebf 100644 --- a/kernel/trace/rv/Kconfig +++ b/kernel/trace/rv/Kconfig @@ -32,6 +32,15 @@ menuconfig RV For further information, see: Documentation/trace/rv/runtime-verification.rst +config RV_PER_TASK_MONITORS + int "Maximum number of per-task monitor" + depends on RV + range 1 8 + default 2 + help + This option configures the maximum number of per-task RV monitors that can run + simultaneously. + source "kernel/trace/rv/monitors/wip/Kconfig" source "kernel/trace/rv/monitors/wwnr/Kconfig" source "kernel/trace/rv/monitors/sched/Kconfig" diff --git a/kernel/trace/rv/monitors/rtapp/Kconfig b/kernel/trace/rv/monitors/rtapp/Kconfig index b7415c3570bb..1ce9370a9ba8 100644 --- a/kernel/trace/rv/monitors/rtapp/Kconfig +++ b/kernel/trace/rv/monitors/rtapp/Kconfig @@ -1,5 +1,6 @@ config RV_MON_RTAPP depends on RV + depends on RV_PER_TASK_MONITORS >= 2 bool "rtapp monitor" help Collection of monitors to check for common problems with real-time diff --git a/kernel/trace/rv/rv.c b/kernel/trace/rv/rv.c index e25d65fe432a..108429d16ec1 100644 --- a/kernel/trace/rv/rv.c +++ b/kernel/trace/rv/rv.c @@ -165,7 +165,7 @@ struct dentry *get_monitors_root(void) LIST_HEAD(rv_monitors_list); static int task_monitor_count; -static bool task_monitor_slots[RV_PER_TASK_MONITORS]; +static bool task_monitor_slots[CONFIG_RV_PER_TASK_MONITORS]; int rv_get_task_monitor_slot(void) { @@ -173,12 +173,12 @@ int rv_get_task_monitor_slot(void) lockdep_assert_held(&rv_interface_lock); - if (task_monitor_count == RV_PER_TASK_MONITORS) + if (task_monitor_count == CONFIG_RV_PER_TASK_MONITORS) return -EBUSY; task_monitor_count++; - for (i = 0; i < RV_PER_TASK_MONITORS; i++) { + for (i = 0; i < CONFIG_RV_PER_TASK_MONITORS; i++) { if (task_monitor_slots[i] == false) { task_monitor_slots[i] = true; return i; @@ -194,7 +194,7 @@ void rv_put_task_monitor_slot(int slot) { lockdep_assert_held(&rv_interface_lock); - if (slot < 0 || slot >= RV_PER_TASK_MONITORS) { + if (slot < 0 || slot >= CONFIG_RV_PER_TASK_MONITORS) { WARN_ONCE(1, "RV releasing an invalid slot!: %d\n", slot); return; } -- cgit v1.2.3 From 9efcf590827cd88cbb68b0f93b20c5f5add905f4 Mon Sep 17 00:00:00 2001 From: Gabriele Monaco Date: Wed, 23 Jul 2025 18:12:38 +0200 Subject: tools/dot2c: Fix generated files going over 100 column limit The dot2c.py script generates all states in a single line. This breaks the 100 column limit when the state machines are non-trivial. Change dot2c.py to generate the states in separate lines in case the generated line is going to be too long. Also adapt existing monitors with line length over the limit. Cc: Masami Hiramatsu Cc: Tomas Glozar Cc: Juri Lelli Cc: Clark Williams Cc: John Kacur Link: https://lore.kernel.org/20250723161240.194860-4-gmonaco@redhat.com Suggested-by: Nam Cao Signed-off-by: Gabriele Monaco Signed-off-by: Steven Rostedt (Google) --- kernel/trace/rv/monitors/snep/snep.h | 14 ++++++++++++-- tools/verification/rvgen/rvgen/dot2c.py | 20 +++++++++++--------- 2 files changed, 23 insertions(+), 11 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/rv/monitors/snep/snep.h b/kernel/trace/rv/monitors/snep/snep.h index 6d16b9ad931e..4cd9abb77b7b 100644 --- a/kernel/trace/rv/monitors/snep/snep.h +++ b/kernel/trace/rv/monitors/snep/snep.h @@ -41,8 +41,18 @@ static const struct automaton_snep automaton_snep = { "schedule_exit" }, .function = { - { non_scheduling_context_snep, non_scheduling_context_snep, scheduling_contex_snep, INVALID_STATE }, - { INVALID_STATE, INVALID_STATE, INVALID_STATE, non_scheduling_context_snep }, + { + non_scheduling_context_snep, + non_scheduling_context_snep, + scheduling_contex_snep, + INVALID_STATE + }, + { + INVALID_STATE, + INVALID_STATE, + INVALID_STATE, + non_scheduling_context_snep + }, }, .initial_state = non_scheduling_context_snep, .final_states = { 1, 0 }, diff --git a/tools/verification/rvgen/rvgen/dot2c.py b/tools/verification/rvgen/rvgen/dot2c.py index 6009caf568d9..b9b6f14cc536 100644 --- a/tools/verification/rvgen/rvgen/dot2c.py +++ b/tools/verification/rvgen/rvgen/dot2c.py @@ -152,28 +152,30 @@ class Dot2c(Automata): max_state_name = max(self.states, key = len).__len__() return max(max_state_name, self.invalid_state_str.__len__()) - def __get_state_string_length(self): - maxlen = self.__get_max_strlen_of_states() + self.enum_suffix.__len__() - return "%" + str(maxlen) + "s" - def get_aut_init_function(self): nr_states = self.states.__len__() nr_events = self.events.__len__() buff = [] - strformat = self.__get_state_string_length() - + maxlen = self.__get_max_strlen_of_states() + len(self.enum_suffix) + tab_braces = 2 * 8 + 2 + 1 # "\t\t{ " ... "}" + comma_space = 2 # ", " count last comma here + linetoolong = tab_braces + (maxlen + comma_space) * nr_events > self.line_length for x in range(nr_states): - line = "\t\t{ " + line = "\t\t{\n" if linetoolong else "\t\t{ " for y in range(nr_events): next_state = self.function[x][y] if next_state != self.invalid_state_str: next_state = self.function[x][y] + self.enum_suffix + if linetoolong: + line += "\t\t\t%s" % next_state + else: + line += "%*s" % (maxlen, next_state) if y != nr_events-1: - line = line + strformat % next_state + ", " + line += ",\n" if linetoolong else ", " else: - line = line + strformat % next_state + " }," + line += "\n\t\t}," if linetoolong else " }," buff.append(line) return self.__buff_to_string(buff) -- cgit v1.2.3 From 560473f2e2d77e153cb12ce1ef53c2abb6a5f0ca Mon Sep 17 00:00:00 2001 From: Gabriele Monaco Date: Wed, 23 Jul 2025 18:12:39 +0200 Subject: verification/rvgen: Organise Kconfig entries for nested monitors The current behaviour of rvgen when running with the -a option is to append the necessary lines at the end of the configuration for Kconfig, Makefile and tracepoints. This is not always the desired behaviour in case of nested monitors: while tracepoints are not affected by nesting and the Makefile's only requirement is that the parent monitor is built before its children, in the Kconfig it is better to have children defined right after their parent, otherwise the result has wrong indentation: [*] foo_parent monitor [*] foo_child1 monitor [*] foo_child2 monitor [*] bar_parent monitor [*] bar_child1 monitor [*] bar_child2 monitor [*] foo_child3 monitor [*] foo_child4 monitor Adapt rvgen to look for a different marker for nested monitors in the Kconfig file and append the line right after the last sibling, instead of the last monitor. Also add the marker when creating a new parent monitor. Cc: Masami Hiramatsu Cc: Tomas Glozar Cc: Juri Lelli Cc: Clark Williams Cc: John Kacur Link: https://lore.kernel.org/20250723161240.194860-5-gmonaco@redhat.com Reviewed-by: Nam Cao Signed-off-by: Gabriele Monaco Signed-off-by: Steven Rostedt (Google) --- kernel/trace/rv/Kconfig | 5 +++++ tools/verification/rvgen/rvgen/container.py | 10 ++++++++++ tools/verification/rvgen/rvgen/generator.py | 16 +++++++++++----- 3 files changed, 26 insertions(+), 5 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/rv/Kconfig b/kernel/trace/rv/Kconfig index c11bf7e61ebf..26017378f79b 100644 --- a/kernel/trace/rv/Kconfig +++ b/kernel/trace/rv/Kconfig @@ -43,6 +43,7 @@ config RV_PER_TASK_MONITORS source "kernel/trace/rv/monitors/wip/Kconfig" source "kernel/trace/rv/monitors/wwnr/Kconfig" + source "kernel/trace/rv/monitors/sched/Kconfig" source "kernel/trace/rv/monitors/tss/Kconfig" source "kernel/trace/rv/monitors/sco/Kconfig" @@ -50,9 +51,13 @@ source "kernel/trace/rv/monitors/snroc/Kconfig" source "kernel/trace/rv/monitors/scpd/Kconfig" source "kernel/trace/rv/monitors/snep/Kconfig" source "kernel/trace/rv/monitors/sncid/Kconfig" +# Add new sched monitors here + source "kernel/trace/rv/monitors/rtapp/Kconfig" source "kernel/trace/rv/monitors/pagefault/Kconfig" source "kernel/trace/rv/monitors/sleep/Kconfig" +# Add new rtapp monitors here + # Add new monitors here config RV_REACTORS diff --git a/tools/verification/rvgen/rvgen/container.py b/tools/verification/rvgen/rvgen/container.py index 47d8ab2ad3ec..51f188530b4d 100644 --- a/tools/verification/rvgen/rvgen/container.py +++ b/tools/verification/rvgen/rvgen/container.py @@ -20,3 +20,13 @@ class Container(generator.RVGenerator): main_h = self.main_h main_h = main_h.replace("%%MODEL_NAME%%", self.name) return main_h + + def fill_kconfig_tooltip(self): + """Override to produce a marker for this container in the Kconfig""" + container_marker = self._kconfig_marker(self.name) + "\n" + result = super().fill_kconfig_tooltip() + if self.auto_patch: + self._patch_file("Kconfig", + self._kconfig_marker(), container_marker) + return result + return result + container_marker diff --git a/tools/verification/rvgen/rvgen/generator.py b/tools/verification/rvgen/rvgen/generator.py index 19d0078a3803..3441385c1177 100644 --- a/tools/verification/rvgen/rvgen/generator.py +++ b/tools/verification/rvgen/rvgen/generator.py @@ -137,7 +137,8 @@ class RVGenerator: kconfig = kconfig.replace("%%MONITOR_DEPS%%", monitor_deps) return kconfig - def __patch_file(self, file, marker, line): + def _patch_file(self, file, marker, line): + assert self.auto_patch file_to_patch = os.path.join(self.rv_dir, file) content = self._read_file(file_to_patch) content = content.replace(marker, line + "\n" + marker) @@ -146,7 +147,7 @@ class RVGenerator: def fill_tracepoint_tooltip(self): monitor_class_type = self.fill_monitor_class_type() if self.auto_patch: - self.__patch_file("rv_trace.h", + self._patch_file("rv_trace.h", "// Add new monitors based on CONFIG_%s here" % monitor_class_type, "#include " % (self.name, self.name)) return " - Patching %s/rv_trace.h, double check the result" % self.rv_dir @@ -156,10 +157,15 @@ Add this line where other tracepoints are included and %s is defined: #include """ % (self.rv_dir, monitor_class_type, self.name, self.name) + def _kconfig_marker(self, container=None) -> str: + return "# Add new %smonitors here" % (container + " " + if container else "") + def fill_kconfig_tooltip(self): if self.auto_patch: - self.__patch_file("Kconfig", - "# Add new monitors here", + # monitors with a container should stay together in the Kconfig + self._patch_file("Kconfig", + self._kconfig_marker(self.parent), "source \"kernel/trace/rv/monitors/%s/Kconfig\"" % (self.name)) return " - Patching %s/Kconfig, double check the result" % self.rv_dir @@ -172,7 +178,7 @@ source \"kernel/trace/rv/monitors/%s/Kconfig\" name = self.name name_up = name.upper() if self.auto_patch: - self.__patch_file("Makefile", + self._patch_file("Makefile", "# Add new monitors here", "obj-$(CONFIG_RV_MON_%s) += monitors/%s/%s.o" % (name_up, name, name)) return " - Patching %s/Makefile, double check the result" % self.rv_dir -- cgit v1.2.3 From 58d5f0d437a8e036a65eeddfb7df2b5d6107f1ef Mon Sep 17 00:00:00 2001 From: Gabriele Monaco Date: Wed, 23 Jul 2025 18:12:40 +0200 Subject: rv: Return init error when registering monitors Monitors generated with dot2k have their registration function (the one called during monitor initialisation) return always 0, even if the registration failed on RV side. This can hide potential errors. Return the value returned by the RV register function. Cc: Masami Hiramatsu Cc: Tomas Glozar Cc: Juri Lelli Cc: Clark Williams Cc: John Kacur Link: https://lore.kernel.org/20250723161240.194860-6-gmonaco@redhat.com Reviewed-by: Nam Cao Signed-off-by: Gabriele Monaco Signed-off-by: Steven Rostedt (Google) --- kernel/trace/rv/monitors/sched/sched.c | 3 +-- kernel/trace/rv/monitors/sco/sco.c | 3 +-- kernel/trace/rv/monitors/scpd/scpd.c | 3 +-- kernel/trace/rv/monitors/sncid/sncid.c | 3 +-- kernel/trace/rv/monitors/snep/snep.c | 3 +-- kernel/trace/rv/monitors/snroc/snroc.c | 3 +-- kernel/trace/rv/monitors/tss/tss.c | 3 +-- kernel/trace/rv/monitors/wip/wip.c | 3 +-- kernel/trace/rv/monitors/wwnr/wwnr.c | 3 +-- tools/verification/rvgen/rvgen/templates/container/main.c | 3 +-- tools/verification/rvgen/rvgen/templates/dot2k/main.c | 3 +-- 11 files changed, 11 insertions(+), 22 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/rv/monitors/sched/sched.c b/kernel/trace/rv/monitors/sched/sched.c index 905e03c3c934..d04db4b543f9 100644 --- a/kernel/trace/rv/monitors/sched/sched.c +++ b/kernel/trace/rv/monitors/sched/sched.c @@ -21,8 +21,7 @@ struct rv_monitor rv_sched = { static int __init register_sched(void) { - rv_register_monitor(&rv_sched, NULL); - return 0; + return rv_register_monitor(&rv_sched, NULL); } static void __exit unregister_sched(void) diff --git a/kernel/trace/rv/monitors/sco/sco.c b/kernel/trace/rv/monitors/sco/sco.c index 4cff59220bfc..66f4639d46ac 100644 --- a/kernel/trace/rv/monitors/sco/sco.c +++ b/kernel/trace/rv/monitors/sco/sco.c @@ -71,8 +71,7 @@ static struct rv_monitor rv_sco = { static int __init register_sco(void) { - rv_register_monitor(&rv_sco, &rv_sched); - return 0; + return rv_register_monitor(&rv_sco, &rv_sched); } static void __exit unregister_sco(void) diff --git a/kernel/trace/rv/monitors/scpd/scpd.c b/kernel/trace/rv/monitors/scpd/scpd.c index cbdd6a5f8d7f..299703cd72b0 100644 --- a/kernel/trace/rv/monitors/scpd/scpd.c +++ b/kernel/trace/rv/monitors/scpd/scpd.c @@ -79,8 +79,7 @@ static struct rv_monitor rv_scpd = { static int __init register_scpd(void) { - rv_register_monitor(&rv_scpd, &rv_sched); - return 0; + return rv_register_monitor(&rv_scpd, &rv_sched); } static void __exit unregister_scpd(void) diff --git a/kernel/trace/rv/monitors/sncid/sncid.c b/kernel/trace/rv/monitors/sncid/sncid.c index f5037cd6214c..3e1ee715a0fb 100644 --- a/kernel/trace/rv/monitors/sncid/sncid.c +++ b/kernel/trace/rv/monitors/sncid/sncid.c @@ -79,8 +79,7 @@ static struct rv_monitor rv_sncid = { static int __init register_sncid(void) { - rv_register_monitor(&rv_sncid, &rv_sched); - return 0; + return rv_register_monitor(&rv_sncid, &rv_sched); } static void __exit unregister_sncid(void) diff --git a/kernel/trace/rv/monitors/snep/snep.c b/kernel/trace/rv/monitors/snep/snep.c index 0076ba6d7ea4..2adc3108d60c 100644 --- a/kernel/trace/rv/monitors/snep/snep.c +++ b/kernel/trace/rv/monitors/snep/snep.c @@ -79,8 +79,7 @@ static struct rv_monitor rv_snep = { static int __init register_snep(void) { - rv_register_monitor(&rv_snep, &rv_sched); - return 0; + return rv_register_monitor(&rv_snep, &rv_sched); } static void __exit unregister_snep(void) diff --git a/kernel/trace/rv/monitors/snroc/snroc.c b/kernel/trace/rv/monitors/snroc/snroc.c index bb1f60d55296..540e686e699f 100644 --- a/kernel/trace/rv/monitors/snroc/snroc.c +++ b/kernel/trace/rv/monitors/snroc/snroc.c @@ -68,8 +68,7 @@ static struct rv_monitor rv_snroc = { static int __init register_snroc(void) { - rv_register_monitor(&rv_snroc, &rv_sched); - return 0; + return rv_register_monitor(&rv_snroc, &rv_sched); } static void __exit unregister_snroc(void) diff --git a/kernel/trace/rv/monitors/tss/tss.c b/kernel/trace/rv/monitors/tss/tss.c index 542787e6524f..0452fcd9edcf 100644 --- a/kernel/trace/rv/monitors/tss/tss.c +++ b/kernel/trace/rv/monitors/tss/tss.c @@ -74,8 +74,7 @@ static struct rv_monitor rv_tss = { static int __init register_tss(void) { - rv_register_monitor(&rv_tss, &rv_sched); - return 0; + return rv_register_monitor(&rv_tss, &rv_sched); } static void __exit unregister_tss(void) diff --git a/kernel/trace/rv/monitors/wip/wip.c b/kernel/trace/rv/monitors/wip/wip.c index ed758fec8608..4b4e99615a11 100644 --- a/kernel/trace/rv/monitors/wip/wip.c +++ b/kernel/trace/rv/monitors/wip/wip.c @@ -71,8 +71,7 @@ static struct rv_monitor rv_wip = { static int __init register_wip(void) { - rv_register_monitor(&rv_wip, NULL); - return 0; + return rv_register_monitor(&rv_wip, NULL); } static void __exit unregister_wip(void) diff --git a/kernel/trace/rv/monitors/wwnr/wwnr.c b/kernel/trace/rv/monitors/wwnr/wwnr.c index 172f31c4b0f3..4145bea2729e 100644 --- a/kernel/trace/rv/monitors/wwnr/wwnr.c +++ b/kernel/trace/rv/monitors/wwnr/wwnr.c @@ -70,8 +70,7 @@ static struct rv_monitor rv_wwnr = { static int __init register_wwnr(void) { - rv_register_monitor(&rv_wwnr, NULL); - return 0; + return rv_register_monitor(&rv_wwnr, NULL); } static void __exit unregister_wwnr(void) diff --git a/tools/verification/rvgen/rvgen/templates/container/main.c b/tools/verification/rvgen/rvgen/templates/container/main.c index 89fc17cf8958..7d9b2f95c7e9 100644 --- a/tools/verification/rvgen/rvgen/templates/container/main.c +++ b/tools/verification/rvgen/rvgen/templates/container/main.c @@ -21,8 +21,7 @@ struct rv_monitor rv_%%MODEL_NAME%% = { static int __init register_%%MODEL_NAME%%(void) { - rv_register_monitor(&rv_%%MODEL_NAME%%, NULL); - return 0; + return rv_register_monitor(&rv_%%MODEL_NAME%%, NULL); } static void __exit unregister_%%MODEL_NAME%%(void) diff --git a/tools/verification/rvgen/rvgen/templates/dot2k/main.c b/tools/verification/rvgen/rvgen/templates/dot2k/main.c index 83044a20c89a..e0fd1134bd85 100644 --- a/tools/verification/rvgen/rvgen/templates/dot2k/main.c +++ b/tools/verification/rvgen/rvgen/templates/dot2k/main.c @@ -74,8 +74,7 @@ static struct rv_monitor rv_%%MODEL_NAME%% = { static int __init register_%%MODEL_NAME%%(void) { - rv_register_monitor(&rv_%%MODEL_NAME%%, %%PARENT%%); - return 0; + return rv_register_monitor(&rv_%%MODEL_NAME%%, %%PARENT%%); } static void __exit unregister_%%MODEL_NAME%%(void) -- cgit v1.2.3 From b0c08dd5348dfd8098bdb815bb04e7c59dfaea79 Mon Sep 17 00:00:00 2001 From: Nam Cao Date: Thu, 24 Jul 2025 19:33:26 +0200 Subject: rv: Remove unused field in struct rv_monitor_def rv_monitor_def::task_monitor is not used. Delete it. Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://lore.kernel.org/502d94f2696435690a2b1fdbe80a9e56c96fcabf.1753378331.git.namcao@linutronix.de Reviewed-by: Gabriele Monaco Signed-off-by: Nam Cao Signed-off-by: Steven Rostedt (Google) --- kernel/trace/rv/rv.h | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/rv/rv.h b/kernel/trace/rv/rv.h index 98fca0a1adbc..873364094402 100644 --- a/kernel/trace/rv/rv.h +++ b/kernel/trace/rv/rv.h @@ -41,7 +41,6 @@ struct rv_monitor_def { struct rv_reactor_def *rdef; bool reacting; #endif - bool task_monitor; }; struct dentry *get_monitors_root(void); -- cgit v1.2.3 From 24cbfe18d55a6866bc2e27fda74306f4a1b5cb01 Mon Sep 17 00:00:00 2001 From: Nam Cao Date: Thu, 24 Jul 2025 19:33:27 +0200 Subject: rv: Merge struct rv_monitor_def into struct rv_monitor Each struct rv_monitor has a unique struct rv_monitor_def associated with it. struct rv_monitor is statically allocated, while struct rv_monitor_def is dynamically allocated. This makes the code more complicated than it should be: - Lookup is required to get the associated rv_monitor_def from rv_monitor - Dynamic memory allocation is required for rv_monitor_def. This is harder to get right compared to static memory. For instance, there is an existing mistake: rv_unregister_monitor() does not free the memory allocated by rv_register_monitor(). This is fortunately not a real memory leak problem, as rv_unregister_monitor() is never called. Simplify and merge rv_monitor_def into rv_monitor. Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://lore.kernel.org/194449c00f87945c207aab4c96920c75796a4f53.1753378331.git.namcao@linutronix.de Reviewed-by: Gabriele Monaco Signed-off-by: Nam Cao Signed-off-by: Steven Rostedt (Google) --- include/linux/rv.h | 8 ++ kernel/trace/rv/rv.c | 211 +++++++++++++++++++----------------------- kernel/trace/rv/rv.h | 27 ++---- kernel/trace/rv/rv_reactors.c | 62 ++++++------- 4 files changed, 140 insertions(+), 168 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/rv.h b/include/linux/rv.h index 97baf58d88b2..dba53aecdfab 100644 --- a/include/linux/rv.h +++ b/include/linux/rv.h @@ -7,6 +7,9 @@ #ifndef _LINUX_RV_H #define _LINUX_RV_H +#include +#include + #define MAX_DA_NAME_LEN 32 #ifdef CONFIG_RV @@ -98,8 +101,13 @@ struct rv_monitor { void (*disable)(void); void (*reset)(void); #ifdef CONFIG_RV_REACTORS + struct rv_reactor_def *rdef; __printf(1, 2) void (*react)(const char *msg, ...); + bool reacting; #endif + struct list_head list; + struct rv_monitor *parent; + struct dentry *root_d; }; bool rv_monitoring_on(void); diff --git a/kernel/trace/rv/rv.c b/kernel/trace/rv/rv.c index 108429d16ec1..6c0be2fdc52d 100644 --- a/kernel/trace/rv/rv.c +++ b/kernel/trace/rv/rv.c @@ -210,9 +210,9 @@ void rv_put_task_monitor_slot(int slot) * Monitors with a parent are nested, * Monitors without a parent could be standalone or containers. */ -bool rv_is_nested_monitor(struct rv_monitor_def *mdef) +bool rv_is_nested_monitor(struct rv_monitor *mon) { - return mdef->parent != NULL; + return mon->parent != NULL; } /* @@ -223,16 +223,16 @@ bool rv_is_nested_monitor(struct rv_monitor_def *mdef) * for enable()/disable(). Use this condition to find empty containers. * Keep both conditions in case we have some non-compliant containers. */ -bool rv_is_container_monitor(struct rv_monitor_def *mdef) +bool rv_is_container_monitor(struct rv_monitor *mon) { - struct rv_monitor_def *next; + struct rv_monitor *next; - if (list_is_last(&mdef->list, &rv_monitors_list)) + if (list_is_last(&mon->list, &rv_monitors_list)) return false; - next = list_next_entry(mdef, list); + next = list_next_entry(mon, list); - return next->parent == mdef->monitor || !mdef->monitor->enable; + return next->parent == mon || !mon->enable; } /* @@ -241,10 +241,10 @@ bool rv_is_container_monitor(struct rv_monitor_def *mdef) static ssize_t monitor_enable_read_data(struct file *filp, char __user *user_buf, size_t count, loff_t *ppos) { - struct rv_monitor_def *mdef = filp->private_data; + struct rv_monitor *mon = filp->private_data; const char *buff; - buff = mdef->monitor->enabled ? "1\n" : "0\n"; + buff = mon->enabled ? "1\n" : "0\n"; return simple_read_from_buffer(user_buf, count, ppos, buff, strlen(buff)+1); } @@ -252,14 +252,14 @@ static ssize_t monitor_enable_read_data(struct file *filp, char __user *user_buf /* * __rv_disable_monitor - disabled an enabled monitor */ -static int __rv_disable_monitor(struct rv_monitor_def *mdef, bool sync) +static int __rv_disable_monitor(struct rv_monitor *mon, bool sync) { lockdep_assert_held(&rv_interface_lock); - if (mdef->monitor->enabled) { - mdef->monitor->enabled = 0; - if (mdef->monitor->disable) - mdef->monitor->disable(); + if (mon->enabled) { + mon->enabled = 0; + if (mon->disable) + mon->disable(); /* * Wait for the execution of all events to finish. @@ -273,90 +273,90 @@ static int __rv_disable_monitor(struct rv_monitor_def *mdef, bool sync) return 0; } -static void rv_disable_single(struct rv_monitor_def *mdef) +static void rv_disable_single(struct rv_monitor *mon) { - __rv_disable_monitor(mdef, true); + __rv_disable_monitor(mon, true); } -static int rv_enable_single(struct rv_monitor_def *mdef) +static int rv_enable_single(struct rv_monitor *mon) { int retval; lockdep_assert_held(&rv_interface_lock); - if (mdef->monitor->enabled) + if (mon->enabled) return 0; - retval = mdef->monitor->enable(); + retval = mon->enable(); if (!retval) - mdef->monitor->enabled = 1; + mon->enabled = 1; return retval; } -static void rv_disable_container(struct rv_monitor_def *mdef) +static void rv_disable_container(struct rv_monitor *mon) { - struct rv_monitor_def *p = mdef; + struct rv_monitor *p = mon; int enabled = 0; list_for_each_entry_continue(p, &rv_monitors_list, list) { - if (p->parent != mdef->monitor) + if (p->parent != mon) break; enabled += __rv_disable_monitor(p, false); } if (enabled) tracepoint_synchronize_unregister(); - mdef->monitor->enabled = 0; + mon->enabled = 0; } -static int rv_enable_container(struct rv_monitor_def *mdef) +static int rv_enable_container(struct rv_monitor *mon) { - struct rv_monitor_def *p = mdef; + struct rv_monitor *p = mon; int retval = 0; list_for_each_entry_continue(p, &rv_monitors_list, list) { - if (retval || p->parent != mdef->monitor) + if (retval || p->parent != mon) break; retval = rv_enable_single(p); } if (retval) - rv_disable_container(mdef); + rv_disable_container(mon); else - mdef->monitor->enabled = 1; + mon->enabled = 1; return retval; } /** * rv_disable_monitor - disable a given runtime monitor - * @mdef: Pointer to the monitor definition structure. + * @mon: Pointer to the monitor definition structure. * * Returns 0 on success. */ -int rv_disable_monitor(struct rv_monitor_def *mdef) +int rv_disable_monitor(struct rv_monitor *mon) { - if (rv_is_container_monitor(mdef)) - rv_disable_container(mdef); + if (rv_is_container_monitor(mon)) + rv_disable_container(mon); else - rv_disable_single(mdef); + rv_disable_single(mon); return 0; } /** * rv_enable_monitor - enable a given runtime monitor - * @mdef: Pointer to the monitor definition structure. + * @mon: Pointer to the monitor definition structure. * * Returns 0 on success, error otherwise. */ -int rv_enable_monitor(struct rv_monitor_def *mdef) +int rv_enable_monitor(struct rv_monitor *mon) { int retval; - if (rv_is_container_monitor(mdef)) - retval = rv_enable_container(mdef); + if (rv_is_container_monitor(mon)) + retval = rv_enable_container(mon); else - retval = rv_enable_single(mdef); + retval = rv_enable_single(mon); return retval; } @@ -367,7 +367,7 @@ int rv_enable_monitor(struct rv_monitor_def *mdef) static ssize_t monitor_enable_write_data(struct file *filp, const char __user *user_buf, size_t count, loff_t *ppos) { - struct rv_monitor_def *mdef = filp->private_data; + struct rv_monitor *mon = filp->private_data; int retval; bool val; @@ -378,9 +378,9 @@ static ssize_t monitor_enable_write_data(struct file *filp, const char __user *u mutex_lock(&rv_interface_lock); if (val) - retval = rv_enable_monitor(mdef); + retval = rv_enable_monitor(mon); else - retval = rv_disable_monitor(mdef); + retval = rv_disable_monitor(mon); mutex_unlock(&rv_interface_lock); @@ -399,12 +399,12 @@ static const struct file_operations interface_enable_fops = { static ssize_t monitor_desc_read_data(struct file *filp, char __user *user_buf, size_t count, loff_t *ppos) { - struct rv_monitor_def *mdef = filp->private_data; + struct rv_monitor *mon = filp->private_data; char buff[256]; memset(buff, 0, sizeof(buff)); - snprintf(buff, sizeof(buff), "%s\n", mdef->monitor->description); + snprintf(buff, sizeof(buff), "%s\n", mon->description); return simple_read_from_buffer(user_buf, count, ppos, buff, strlen(buff) + 1); } @@ -419,37 +419,37 @@ static const struct file_operations interface_desc_fops = { * the monitor dir, where the specific options of the monitor * are exposed. */ -static int create_monitor_dir(struct rv_monitor_def *mdef, struct rv_monitor_def *parent) +static int create_monitor_dir(struct rv_monitor *mon, struct rv_monitor *parent) { struct dentry *root = parent ? parent->root_d : get_monitors_root(); - const char *name = mdef->monitor->name; + const char *name = mon->name; struct dentry *tmp; int retval; - mdef->root_d = rv_create_dir(name, root); - if (!mdef->root_d) + mon->root_d = rv_create_dir(name, root); + if (!mon->root_d) return -ENOMEM; - tmp = rv_create_file("enable", RV_MODE_WRITE, mdef->root_d, mdef, &interface_enable_fops); + tmp = rv_create_file("enable", RV_MODE_WRITE, mon->root_d, mon, &interface_enable_fops); if (!tmp) { retval = -ENOMEM; goto out_remove_root; } - tmp = rv_create_file("desc", RV_MODE_READ, mdef->root_d, mdef, &interface_desc_fops); + tmp = rv_create_file("desc", RV_MODE_READ, mon->root_d, mon, &interface_desc_fops); if (!tmp) { retval = -ENOMEM; goto out_remove_root; } - retval = reactor_populate_monitor(mdef); + retval = reactor_populate_monitor(mon); if (retval) goto out_remove_root; return 0; out_remove_root: - rv_remove(mdef->root_d); + rv_remove(mon->root_d); return retval; } @@ -458,13 +458,12 @@ out_remove_root: */ static int monitors_show(struct seq_file *m, void *p) { - struct rv_monitor_def *mon_def = p; + struct rv_monitor *mon = p; - if (mon_def->parent) - seq_printf(m, "%s:%s\n", mon_def->parent->name, - mon_def->monitor->name); + if (mon->parent) + seq_printf(m, "%s:%s\n", mon->parent->name, mon->name); else - seq_printf(m, "%s\n", mon_def->monitor->name); + seq_printf(m, "%s\n", mon->name); return 0; } @@ -496,13 +495,13 @@ static void *available_monitors_next(struct seq_file *m, void *p, loff_t *pos) */ static void *enabled_monitors_next(struct seq_file *m, void *p, loff_t *pos) { - struct rv_monitor_def *m_def = p; + struct rv_monitor *mon = p; (*pos)++; - list_for_each_entry_continue(m_def, &rv_monitors_list, list) { - if (m_def->monitor->enabled) - return m_def; + list_for_each_entry_continue(mon, &rv_monitors_list, list) { + if (mon->enabled) + return mon; } return NULL; @@ -510,7 +509,7 @@ static void *enabled_monitors_next(struct seq_file *m, void *p, loff_t *pos) static void *enabled_monitors_start(struct seq_file *m, loff_t *pos) { - struct rv_monitor_def *m_def; + struct rv_monitor *mon; loff_t l; mutex_lock(&rv_interface_lock); @@ -518,15 +517,15 @@ static void *enabled_monitors_start(struct seq_file *m, loff_t *pos) if (list_empty(&rv_monitors_list)) return NULL; - m_def = list_entry(&rv_monitors_list, struct rv_monitor_def, list); + mon = list_entry(&rv_monitors_list, struct rv_monitor, list); for (l = 0; l <= *pos; ) { - m_def = enabled_monitors_next(m, m_def, &l); - if (!m_def) + mon = enabled_monitors_next(m, mon, &l); + if (!mon) break; } - return m_def; + return mon; } /* @@ -566,13 +565,13 @@ static const struct file_operations available_monitors_ops = { */ static void disable_all_monitors(void) { - struct rv_monitor_def *mdef; + struct rv_monitor *mon; int enabled = 0; mutex_lock(&rv_interface_lock); - list_for_each_entry(mdef, &rv_monitors_list, list) - enabled += __rv_disable_monitor(mdef, false); + list_for_each_entry(mon, &rv_monitors_list, list) + enabled += __rv_disable_monitor(mon, false); if (enabled) { /* @@ -598,7 +597,7 @@ static ssize_t enabled_monitors_write(struct file *filp, const char __user *user size_t count, loff_t *ppos) { char buff[MAX_RV_MONITOR_NAME_SIZE + 2]; - struct rv_monitor_def *mdef; + struct rv_monitor *mon; int retval = -EINVAL; bool enable = true; char *ptr, *tmp; @@ -633,17 +632,17 @@ static ssize_t enabled_monitors_write(struct file *filp, const char __user *user if (tmp) ptr = tmp+1; - list_for_each_entry(mdef, &rv_monitors_list, list) { - if (strcmp(ptr, mdef->monitor->name) != 0) + list_for_each_entry(mon, &rv_monitors_list, list) { + if (strcmp(ptr, mon->name) != 0) continue; /* * Monitor found! */ if (enable) - retval = rv_enable_monitor(mdef); + retval = rv_enable_monitor(mon); else - retval = rv_disable_monitor(mdef); + retval = rv_disable_monitor(mon); if (!retval) retval = count; @@ -702,11 +701,11 @@ static void turn_monitoring_off(void) static void reset_all_monitors(void) { - struct rv_monitor_def *mdef; + struct rv_monitor *mon; - list_for_each_entry(mdef, &rv_monitors_list, list) { - if (mdef->monitor->enabled && mdef->monitor->reset) - mdef->monitor->reset(); + list_for_each_entry(mon, &rv_monitors_list, list) { + if (mon->enabled && mon->reset) + mon->reset(); } } @@ -768,10 +767,10 @@ static const struct file_operations monitoring_on_fops = { .read = monitoring_on_read_data, }; -static void destroy_monitor_dir(struct rv_monitor_def *mdef) +static void destroy_monitor_dir(struct rv_monitor *mon) { - reactor_cleanup_monitor(mdef); - rv_remove(mdef->root_d); + reactor_cleanup_monitor(mon); + rv_remove(mon->root_d); } /** @@ -783,7 +782,7 @@ static void destroy_monitor_dir(struct rv_monitor_def *mdef) */ int rv_register_monitor(struct rv_monitor *monitor, struct rv_monitor *parent) { - struct rv_monitor_def *r, *p = NULL; + struct rv_monitor *r; int retval = 0; if (strlen(monitor->name) >= MAX_RV_MONITOR_NAME_SIZE) { @@ -795,49 +794,31 @@ int rv_register_monitor(struct rv_monitor *monitor, struct rv_monitor *parent) mutex_lock(&rv_interface_lock); list_for_each_entry(r, &rv_monitors_list, list) { - if (strcmp(monitor->name, r->monitor->name) == 0) { + if (strcmp(monitor->name, r->name) == 0) { pr_info("Monitor %s is already registered\n", monitor->name); retval = -EEXIST; goto out_unlock; } } - if (parent) { - list_for_each_entry(r, &rv_monitors_list, list) { - if (strcmp(parent->name, r->monitor->name) == 0) { - p = r; - break; - } - } - } - - if (p && rv_is_nested_monitor(p)) { + if (parent && rv_is_nested_monitor(parent)) { pr_info("Parent monitor %s is already nested, cannot nest further\n", parent->name); retval = -EINVAL; goto out_unlock; } - r = kzalloc(sizeof(struct rv_monitor_def), GFP_KERNEL); - if (!r) { - retval = -ENOMEM; - goto out_unlock; - } - - r->monitor = monitor; - r->parent = parent; + monitor->parent = parent; - retval = create_monitor_dir(r, p); - if (retval) { - kfree(r); - goto out_unlock; - } + retval = create_monitor_dir(monitor, parent); + if (retval) + return retval; /* keep children close to the parent for easier visualisation */ - if (p) - list_add(&r->list, &p->list); + if (parent) + list_add(&monitor->list, &parent->list); else - list_add_tail(&r->list, &rv_monitors_list); + list_add_tail(&monitor->list, &rv_monitors_list); out_unlock: mutex_unlock(&rv_interface_lock); @@ -852,17 +833,11 @@ out_unlock: */ int rv_unregister_monitor(struct rv_monitor *monitor) { - struct rv_monitor_def *ptr, *next; - mutex_lock(&rv_interface_lock); - list_for_each_entry_safe(ptr, next, &rv_monitors_list, list) { - if (strcmp(monitor->name, ptr->monitor->name) == 0) { - rv_disable_monitor(ptr); - list_del(&ptr->list); - destroy_monitor_dir(ptr); - } - } + rv_disable_monitor(monitor); + list_del(&monitor->list); + destroy_monitor_dir(monitor); mutex_unlock(&rv_interface_lock); return 0; diff --git a/kernel/trace/rv/rv.h b/kernel/trace/rv/rv.h index 873364094402..f039ec1c9156 100644 --- a/kernel/trace/rv/rv.h +++ b/kernel/trace/rv/rv.h @@ -32,34 +32,23 @@ struct rv_reactor_def { }; #endif -struct rv_monitor_def { - struct list_head list; - struct rv_monitor *monitor; - struct rv_monitor *parent; - struct dentry *root_d; -#ifdef CONFIG_RV_REACTORS - struct rv_reactor_def *rdef; - bool reacting; -#endif -}; - struct dentry *get_monitors_root(void); -int rv_disable_monitor(struct rv_monitor_def *mdef); -int rv_enable_monitor(struct rv_monitor_def *mdef); -bool rv_is_container_monitor(struct rv_monitor_def *mdef); -bool rv_is_nested_monitor(struct rv_monitor_def *mdef); +int rv_disable_monitor(struct rv_monitor *mon); +int rv_enable_monitor(struct rv_monitor *mon); +bool rv_is_container_monitor(struct rv_monitor *mon); +bool rv_is_nested_monitor(struct rv_monitor *mon); #ifdef CONFIG_RV_REACTORS -int reactor_populate_monitor(struct rv_monitor_def *mdef); -void reactor_cleanup_monitor(struct rv_monitor_def *mdef); +int reactor_populate_monitor(struct rv_monitor *mon); +void reactor_cleanup_monitor(struct rv_monitor *mon); int init_rv_reactors(struct dentry *root_dir); #else -static inline int reactor_populate_monitor(struct rv_monitor_def *mdef) +static inline int reactor_populate_monitor(struct rv_monitor *mon) { return 0; } -static inline void reactor_cleanup_monitor(struct rv_monitor_def *mdef) +static inline void reactor_cleanup_monitor(struct rv_monitor *mon) { return; } diff --git a/kernel/trace/rv/rv_reactors.c b/kernel/trace/rv/rv_reactors.c index 740603670dd1..7cc620a1be1a 100644 --- a/kernel/trace/rv/rv_reactors.c +++ b/kernel/trace/rv/rv_reactors.c @@ -138,10 +138,10 @@ static const struct file_operations available_reactors_ops = { */ static int monitor_reactor_show(struct seq_file *m, void *p) { - struct rv_monitor_def *mdef = m->private; + struct rv_monitor *mon = m->private; struct rv_reactor_def *rdef = p; - if (mdef->rdef == rdef) + if (mon->rdef == rdef) seq_printf(m, "[%s]\n", rdef->reactor->name); else seq_printf(m, "%s\n", rdef->reactor->name); @@ -158,41 +158,41 @@ static const struct seq_operations monitor_reactors_seq_ops = { .show = monitor_reactor_show }; -static void monitor_swap_reactors_single(struct rv_monitor_def *mdef, +static void monitor_swap_reactors_single(struct rv_monitor *mon, struct rv_reactor_def *rdef, bool reacting, bool nested) { bool monitor_enabled; /* nothing to do */ - if (mdef->rdef == rdef) + if (mon->rdef == rdef) return; - monitor_enabled = mdef->monitor->enabled; + monitor_enabled = mon->enabled; if (monitor_enabled) - rv_disable_monitor(mdef); + rv_disable_monitor(mon); /* swap reactor's usage */ - mdef->rdef->counter--; + mon->rdef->counter--; rdef->counter++; - mdef->rdef = rdef; - mdef->reacting = reacting; - mdef->monitor->react = rdef->reactor->react; + mon->rdef = rdef; + mon->reacting = reacting; + mon->react = rdef->reactor->react; /* enable only once if iterating through a container */ if (monitor_enabled && !nested) - rv_enable_monitor(mdef); + rv_enable_monitor(mon); } -static void monitor_swap_reactors(struct rv_monitor_def *mdef, +static void monitor_swap_reactors(struct rv_monitor *mon, struct rv_reactor_def *rdef, bool reacting) { - struct rv_monitor_def *p = mdef; + struct rv_monitor *p = mon; - if (rv_is_container_monitor(mdef)) + if (rv_is_container_monitor(mon)) list_for_each_entry_continue(p, &rv_monitors_list, list) { - if (p->parent != mdef->monitor) + if (p->parent != mon) break; monitor_swap_reactors_single(p, rdef, reacting, true); } @@ -202,7 +202,7 @@ static void monitor_swap_reactors(struct rv_monitor_def *mdef, * All nested monitors are enabled also if they were off, we may refine * this logic in the future. */ - monitor_swap_reactors_single(mdef, rdef, reacting, false); + monitor_swap_reactors_single(mon, rdef, reacting, false); } static ssize_t @@ -210,7 +210,7 @@ monitor_reactors_write(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { char buff[MAX_RV_REACTOR_NAME_SIZE + 2]; - struct rv_monitor_def *mdef; + struct rv_monitor *mon; struct rv_reactor_def *rdef; struct seq_file *seq_f; int retval = -EINVAL; @@ -237,7 +237,7 @@ monitor_reactors_write(struct file *file, const char __user *user_buf, * See monitor_reactors_open() */ seq_f = file->private_data; - mdef = seq_f->private; + mon = seq_f->private; mutex_lock(&rv_interface_lock); @@ -252,7 +252,7 @@ monitor_reactors_write(struct file *file, const char __user *user_buf, else enable = true; - monitor_swap_reactors(mdef, rdef, enable); + monitor_swap_reactors(mon, rdef, enable); retval = count; break; @@ -268,7 +268,7 @@ monitor_reactors_write(struct file *file, const char __user *user_buf, */ static int monitor_reactors_open(struct inode *inode, struct file *file) { - struct rv_monitor_def *mdef = inode->i_private; + struct rv_monitor *mon = inode->i_private; struct seq_file *seq_f; int ret; @@ -284,7 +284,7 @@ static int monitor_reactors_open(struct inode *inode, struct file *file) /* * Copy the create file "private" data to the seq_file private data. */ - seq_f->private = mdef; + seq_f->private = mon; return 0; }; @@ -454,37 +454,37 @@ static const struct file_operations reacting_on_fops = { /** * reactor_populate_monitor - creates per monitor reactors file - * @mdef: monitor's definition. + * @mon: The monitor. * * Returns 0 if successful, error otherwise. */ -int reactor_populate_monitor(struct rv_monitor_def *mdef) +int reactor_populate_monitor(struct rv_monitor *mon) { struct dentry *tmp; - tmp = rv_create_file("reactors", RV_MODE_WRITE, mdef->root_d, mdef, &monitor_reactors_ops); + tmp = rv_create_file("reactors", RV_MODE_WRITE, mon->root_d, mon, &monitor_reactors_ops); if (!tmp) return -ENOMEM; /* * Configure as the rv_nop reactor. */ - mdef->rdef = get_reactor_rdef_by_name("nop"); - mdef->rdef->counter++; - mdef->reacting = false; + mon->rdef = get_reactor_rdef_by_name("nop"); + mon->rdef->counter++; + mon->reacting = false; return 0; } /** * reactor_cleanup_monitor - cleanup a monitor reference - * @mdef: monitor's definition. + * @mon: the monitor. */ -void reactor_cleanup_monitor(struct rv_monitor_def *mdef) +void reactor_cleanup_monitor(struct rv_monitor *mon) { lockdep_assert_held(&rv_interface_lock); - mdef->rdef->counter--; - WARN_ON_ONCE(mdef->rdef->counter < 0); + mon->rdef->counter--; + WARN_ON_ONCE(mon->rdef->counter < 0); } /* -- cgit v1.2.3 From 3d3c376118b5f7ed7723c2b4fd7a0a1c1893d63e Mon Sep 17 00:00:00 2001 From: Nam Cao Date: Thu, 24 Jul 2025 19:33:28 +0200 Subject: rv: Merge struct rv_reactor_def into struct rv_reactor Each struct rv_reactor has a unique struct rv_reactor_def associated with it. struct rv_reactor is statically allocated, while struct rv_reactor_def is dynamically allocated. This makes the code more complicated than it should be: - Lookup is required to get the associated rv_reactor_def from rv_reactor - Dynamic memory allocation is required for rv_reactor_def. This is harder to get right compared to static memory. For instance, there is an existing mistake: rv_unregister_reactor() does not free the memory allocated by rv_register_reactor(). This is fortunately not a real memory leak problem as rv_unregister_reactor() is never called. Simplify and merge rv_reactor_def into rv_reactor. Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://lore.kernel.org/71cb91c86cd40df5b8c492b788787f2a73c3eaa3.1753378331.git.namcao@linutronix.de Reviewed-by: Gabriele Monaco Signed-off-by: Nam Cao Signed-off-by: Steven Rostedt (Google) --- include/linux/rv.h | 5 ++- kernel/trace/rv/rv.h | 9 ----- kernel/trace/rv/rv_reactors.c | 92 ++++++++++++++++++------------------------- 3 files changed, 43 insertions(+), 63 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/rv.h b/include/linux/rv.h index dba53aecdfab..c22c9b8c1567 100644 --- a/include/linux/rv.h +++ b/include/linux/rv.h @@ -90,6 +90,9 @@ struct rv_reactor { const char *name; const char *description; __printf(1, 2) void (*react)(const char *msg, ...); + struct list_head list; + /* protected by the monitor interface lock */ + int counter; }; #endif @@ -101,7 +104,7 @@ struct rv_monitor { void (*disable)(void); void (*reset)(void); #ifdef CONFIG_RV_REACTORS - struct rv_reactor_def *rdef; + struct rv_reactor *reactor; __printf(1, 2) void (*react)(const char *msg, ...); bool reacting; #endif diff --git a/kernel/trace/rv/rv.h b/kernel/trace/rv/rv.h index f039ec1c9156..8c38f9dd41bc 100644 --- a/kernel/trace/rv/rv.h +++ b/kernel/trace/rv/rv.h @@ -23,15 +23,6 @@ struct rv_interface { extern struct mutex rv_interface_lock; extern struct list_head rv_monitors_list; -#ifdef CONFIG_RV_REACTORS -struct rv_reactor_def { - struct list_head list; - struct rv_reactor *reactor; - /* protected by the monitor interface lock */ - int counter; -}; -#endif - struct dentry *get_monitors_root(void); int rv_disable_monitor(struct rv_monitor *mon); int rv_enable_monitor(struct rv_monitor *mon); diff --git a/kernel/trace/rv/rv_reactors.c b/kernel/trace/rv/rv_reactors.c index 7cc620a1be1a..2c7909e6d0e7 100644 --- a/kernel/trace/rv/rv_reactors.c +++ b/kernel/trace/rv/rv_reactors.c @@ -70,12 +70,12 @@ */ static LIST_HEAD(rv_reactors_list); -static struct rv_reactor_def *get_reactor_rdef_by_name(char *name) +static struct rv_reactor *get_reactor_rdef_by_name(char *name) { - struct rv_reactor_def *r; + struct rv_reactor *r; list_for_each_entry(r, &rv_reactors_list, list) { - if (strcmp(name, r->reactor->name) == 0) + if (strcmp(name, r->name) == 0) return r; } return NULL; @@ -86,9 +86,9 @@ static struct rv_reactor_def *get_reactor_rdef_by_name(char *name) */ static int reactors_show(struct seq_file *m, void *p) { - struct rv_reactor_def *rea_def = p; + struct rv_reactor *reactor = p; - seq_printf(m, "%s\n", rea_def->reactor->name); + seq_printf(m, "%s\n", reactor->name); return 0; } @@ -139,12 +139,12 @@ static const struct file_operations available_reactors_ops = { static int monitor_reactor_show(struct seq_file *m, void *p) { struct rv_monitor *mon = m->private; - struct rv_reactor_def *rdef = p; + struct rv_reactor *reactor = p; - if (mon->rdef == rdef) - seq_printf(m, "[%s]\n", rdef->reactor->name); + if (mon->reactor == reactor) + seq_printf(m, "[%s]\n", reactor->name); else - seq_printf(m, "%s\n", rdef->reactor->name); + seq_printf(m, "%s\n", reactor->name); return 0; } @@ -159,13 +159,13 @@ static const struct seq_operations monitor_reactors_seq_ops = { }; static void monitor_swap_reactors_single(struct rv_monitor *mon, - struct rv_reactor_def *rdef, + struct rv_reactor *reactor, bool reacting, bool nested) { bool monitor_enabled; /* nothing to do */ - if (mon->rdef == rdef) + if (mon->reactor == reactor) return; monitor_enabled = mon->enabled; @@ -173,12 +173,12 @@ static void monitor_swap_reactors_single(struct rv_monitor *mon, rv_disable_monitor(mon); /* swap reactor's usage */ - mon->rdef->counter--; - rdef->counter++; + mon->reactor->counter--; + reactor->counter++; - mon->rdef = rdef; + mon->reactor = reactor; mon->reacting = reacting; - mon->react = rdef->reactor->react; + mon->react = reactor->react; /* enable only once if iterating through a container */ if (monitor_enabled && !nested) @@ -186,7 +186,7 @@ static void monitor_swap_reactors_single(struct rv_monitor *mon, } static void monitor_swap_reactors(struct rv_monitor *mon, - struct rv_reactor_def *rdef, bool reacting) + struct rv_reactor *reactor, bool reacting) { struct rv_monitor *p = mon; @@ -194,7 +194,7 @@ static void monitor_swap_reactors(struct rv_monitor *mon, list_for_each_entry_continue(p, &rv_monitors_list, list) { if (p->parent != mon) break; - monitor_swap_reactors_single(p, rdef, reacting, true); + monitor_swap_reactors_single(p, reactor, reacting, true); } /* * This call enables and disables the monitor if they were active. @@ -202,7 +202,7 @@ static void monitor_swap_reactors(struct rv_monitor *mon, * All nested monitors are enabled also if they were off, we may refine * this logic in the future. */ - monitor_swap_reactors_single(mon, rdef, reacting, false); + monitor_swap_reactors_single(mon, reactor, reacting, false); } static ssize_t @@ -211,7 +211,7 @@ monitor_reactors_write(struct file *file, const char __user *user_buf, { char buff[MAX_RV_REACTOR_NAME_SIZE + 2]; struct rv_monitor *mon; - struct rv_reactor_def *rdef; + struct rv_reactor *reactor; struct seq_file *seq_f; int retval = -EINVAL; bool enable; @@ -243,16 +243,16 @@ monitor_reactors_write(struct file *file, const char __user *user_buf, retval = -EINVAL; - list_for_each_entry(rdef, &rv_reactors_list, list) { - if (strcmp(ptr, rdef->reactor->name) != 0) + list_for_each_entry(reactor, &rv_reactors_list, list) { + if (strcmp(ptr, reactor->name) != 0) continue; - if (rdef == get_reactor_rdef_by_name("nop")) + if (strcmp(reactor->name, "nop")) enable = false; else enable = true; - monitor_swap_reactors(mon, rdef, enable); + monitor_swap_reactors(mon, reactor, enable); retval = count; break; @@ -299,23 +299,16 @@ static const struct file_operations monitor_reactors_ops = { static int __rv_register_reactor(struct rv_reactor *reactor) { - struct rv_reactor_def *r; + struct rv_reactor *r; list_for_each_entry(r, &rv_reactors_list, list) { - if (strcmp(reactor->name, r->reactor->name) == 0) { + if (strcmp(reactor->name, r->name) == 0) { pr_info("Reactor %s is already registered\n", reactor->name); return -EINVAL; } } - r = kzalloc(sizeof(struct rv_reactor_def), GFP_KERNEL); - if (!r) - return -ENOMEM; - - r->reactor = reactor; - r->counter = 0; - - list_add_tail(&r->list, &rv_reactors_list); + list_add_tail(&reactor->list, &rv_reactors_list); return 0; } @@ -350,26 +343,19 @@ int rv_register_reactor(struct rv_reactor *reactor) */ int rv_unregister_reactor(struct rv_reactor *reactor) { - struct rv_reactor_def *ptr, *next; int ret = 0; mutex_lock(&rv_interface_lock); - list_for_each_entry_safe(ptr, next, &rv_reactors_list, list) { - if (strcmp(reactor->name, ptr->reactor->name) == 0) { - - if (!ptr->counter) { - list_del(&ptr->list); - } else { - printk(KERN_WARNING - "rv: the rv_reactor %s is in use by %d monitor(s)\n", - ptr->reactor->name, ptr->counter); - printk(KERN_WARNING "rv: the rv_reactor %s cannot be removed\n", - ptr->reactor->name); - ret = -EBUSY; - break; - } - } + if (!reactor->counter) { + list_del(&reactor->list); + } else { + printk(KERN_WARNING + "rv: the rv_reactor %s is in use by %d monitor(s)\n", + reactor->name, reactor->counter); + printk(KERN_WARNING "rv: the rv_reactor %s cannot be removed\n", + reactor->name); + ret = -EBUSY; } mutex_unlock(&rv_interface_lock); @@ -469,8 +455,8 @@ int reactor_populate_monitor(struct rv_monitor *mon) /* * Configure as the rv_nop reactor. */ - mon->rdef = get_reactor_rdef_by_name("nop"); - mon->rdef->counter++; + mon->reactor = get_reactor_rdef_by_name("nop"); + mon->reactor->counter++; mon->reacting = false; return 0; @@ -483,8 +469,8 @@ int reactor_populate_monitor(struct rv_monitor *mon) void reactor_cleanup_monitor(struct rv_monitor *mon) { lockdep_assert_held(&rv_interface_lock); - mon->rdef->counter--; - WARN_ON_ONCE(mon->rdef->counter < 0); + mon->reactor->counter--; + WARN_ON_ONCE(mon->reactor->counter < 0); } /* -- cgit v1.2.3 From 3d3800b4f7f4b1472a0ec2cffd535c05603f8f60 Mon Sep 17 00:00:00 2001 From: Nam Cao Date: Thu, 24 Jul 2025 19:33:29 +0200 Subject: rv: Remove rv_reactor's reference counter rv_reactor has a reference counter to ensure it is not removed while monitors are still using it. However, this is futile, as __exit functions are not expected to fail and will proceed normally despite rv_unregister_reactor() returning an error. At the moment, reactors do not support being built as modules, therefore they are never removed and the reference counters are not necessary. If we support building RV reactors as modules in the future, kernel module's centralized facilities such as try_module_get(), module_put() or MODULE_SOFTDEP should be used instead of this custom implementation. Remove this reference counter. Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://lore.kernel.org/bb946398436a5e17fb0f5b842ef3313c02291852.1753378331.git.namcao@linutronix.de Reviewed-by: Gabriele Monaco Signed-off-by: Nam Cao Signed-off-by: Steven Rostedt (Google) --- include/linux/rv.h | 2 -- kernel/trace/rv/rv.c | 1 - kernel/trace/rv/rv.h | 6 ------ kernel/trace/rv/rv_reactors.c | 33 ++------------------------------- 4 files changed, 2 insertions(+), 40 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/rv.h b/include/linux/rv.h index c22c9b8c1567..2f867d6f72ba 100644 --- a/include/linux/rv.h +++ b/include/linux/rv.h @@ -91,8 +91,6 @@ struct rv_reactor { const char *description; __printf(1, 2) void (*react)(const char *msg, ...); struct list_head list; - /* protected by the monitor interface lock */ - int counter; }; #endif diff --git a/kernel/trace/rv/rv.c b/kernel/trace/rv/rv.c index 6c0be2fdc52d..6c8498743b98 100644 --- a/kernel/trace/rv/rv.c +++ b/kernel/trace/rv/rv.c @@ -769,7 +769,6 @@ static const struct file_operations monitoring_on_fops = { static void destroy_monitor_dir(struct rv_monitor *mon) { - reactor_cleanup_monitor(mon); rv_remove(mon->root_d); } diff --git a/kernel/trace/rv/rv.h b/kernel/trace/rv/rv.h index 8c38f9dd41bc..1485a70c1bf4 100644 --- a/kernel/trace/rv/rv.h +++ b/kernel/trace/rv/rv.h @@ -31,7 +31,6 @@ bool rv_is_nested_monitor(struct rv_monitor *mon); #ifdef CONFIG_RV_REACTORS int reactor_populate_monitor(struct rv_monitor *mon); -void reactor_cleanup_monitor(struct rv_monitor *mon); int init_rv_reactors(struct dentry *root_dir); #else static inline int reactor_populate_monitor(struct rv_monitor *mon) @@ -39,11 +38,6 @@ static inline int reactor_populate_monitor(struct rv_monitor *mon) return 0; } -static inline void reactor_cleanup_monitor(struct rv_monitor *mon) -{ - return; -} - static inline int init_rv_reactors(struct dentry *root_dir) { return 0; diff --git a/kernel/trace/rv/rv_reactors.c b/kernel/trace/rv/rv_reactors.c index 2c7909e6d0e7..a8e849e6cd85 100644 --- a/kernel/trace/rv/rv_reactors.c +++ b/kernel/trace/rv/rv_reactors.c @@ -172,10 +172,6 @@ static void monitor_swap_reactors_single(struct rv_monitor *mon, if (monitor_enabled) rv_disable_monitor(mon); - /* swap reactor's usage */ - mon->reactor->counter--; - reactor->counter++; - mon->reactor = reactor; mon->reacting = reacting; mon->react = reactor->react; @@ -343,23 +339,10 @@ int rv_register_reactor(struct rv_reactor *reactor) */ int rv_unregister_reactor(struct rv_reactor *reactor) { - int ret = 0; - mutex_lock(&rv_interface_lock); - - if (!reactor->counter) { - list_del(&reactor->list); - } else { - printk(KERN_WARNING - "rv: the rv_reactor %s is in use by %d monitor(s)\n", - reactor->name, reactor->counter); - printk(KERN_WARNING "rv: the rv_reactor %s cannot be removed\n", - reactor->name); - ret = -EBUSY; - } - + list_del(&reactor->list); mutex_unlock(&rv_interface_lock); - return ret; + return 0; } /* @@ -456,23 +439,11 @@ int reactor_populate_monitor(struct rv_monitor *mon) * Configure as the rv_nop reactor. */ mon->reactor = get_reactor_rdef_by_name("nop"); - mon->reactor->counter++; mon->reacting = false; return 0; } -/** - * reactor_cleanup_monitor - cleanup a monitor reference - * @mon: the monitor. - */ -void reactor_cleanup_monitor(struct rv_monitor *mon) -{ - lockdep_assert_held(&rv_interface_lock); - mon->reactor->counter--; - WARN_ON_ONCE(mon->reactor->counter < 0); -} - /* * Nop reactor register */ -- cgit v1.2.3 From b8a7fba39cd49eab343bfe561d85bb5dc57541af Mon Sep 17 00:00:00 2001 From: Nam Cao Date: Thu, 24 Jul 2025 19:33:30 +0200 Subject: rv: Remove struct rv_monitor::reacting The field 'reacting' in struct rv_monitor is set but never used. Delete it. Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://lore.kernel.org/a6c16f845d2f1a09c4d0934ab83f3cb14478a71d.1753378331.git.namcao@linutronix.de Reviewed-by: Gabriele Monaco Signed-off-by: Nam Cao Signed-off-by: Steven Rostedt (Google) --- include/linux/rv.h | 1 - kernel/trace/rv/rv_reactors.c | 19 +++++-------------- 2 files changed, 5 insertions(+), 15 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/rv.h b/include/linux/rv.h index 2f867d6f72ba..80731242fe60 100644 --- a/include/linux/rv.h +++ b/include/linux/rv.h @@ -104,7 +104,6 @@ struct rv_monitor { #ifdef CONFIG_RV_REACTORS struct rv_reactor *reactor; __printf(1, 2) void (*react)(const char *msg, ...); - bool reacting; #endif struct list_head list; struct rv_monitor *parent; diff --git a/kernel/trace/rv/rv_reactors.c b/kernel/trace/rv/rv_reactors.c index a8e849e6cd85..106f2c4740f2 100644 --- a/kernel/trace/rv/rv_reactors.c +++ b/kernel/trace/rv/rv_reactors.c @@ -160,7 +160,7 @@ static const struct seq_operations monitor_reactors_seq_ops = { static void monitor_swap_reactors_single(struct rv_monitor *mon, struct rv_reactor *reactor, - bool reacting, bool nested) + bool nested) { bool monitor_enabled; @@ -173,7 +173,6 @@ static void monitor_swap_reactors_single(struct rv_monitor *mon, rv_disable_monitor(mon); mon->reactor = reactor; - mon->reacting = reacting; mon->react = reactor->react; /* enable only once if iterating through a container */ @@ -181,8 +180,7 @@ static void monitor_swap_reactors_single(struct rv_monitor *mon, rv_enable_monitor(mon); } -static void monitor_swap_reactors(struct rv_monitor *mon, - struct rv_reactor *reactor, bool reacting) +static void monitor_swap_reactors(struct rv_monitor *mon, struct rv_reactor *reactor) { struct rv_monitor *p = mon; @@ -190,7 +188,7 @@ static void monitor_swap_reactors(struct rv_monitor *mon, list_for_each_entry_continue(p, &rv_monitors_list, list) { if (p->parent != mon) break; - monitor_swap_reactors_single(p, reactor, reacting, true); + monitor_swap_reactors_single(p, reactor, true); } /* * This call enables and disables the monitor if they were active. @@ -198,7 +196,7 @@ static void monitor_swap_reactors(struct rv_monitor *mon, * All nested monitors are enabled also if they were off, we may refine * this logic in the future. */ - monitor_swap_reactors_single(mon, reactor, reacting, false); + monitor_swap_reactors_single(mon, reactor, false); } static ssize_t @@ -210,7 +208,6 @@ monitor_reactors_write(struct file *file, const char __user *user_buf, struct rv_reactor *reactor; struct seq_file *seq_f; int retval = -EINVAL; - bool enable; char *ptr; int len; @@ -243,12 +240,7 @@ monitor_reactors_write(struct file *file, const char __user *user_buf, if (strcmp(ptr, reactor->name) != 0) continue; - if (strcmp(reactor->name, "nop")) - enable = false; - else - enable = true; - - monitor_swap_reactors(mon, reactor, enable); + monitor_swap_reactors(mon, reactor); retval = count; break; @@ -439,7 +431,6 @@ int reactor_populate_monitor(struct rv_monitor *mon) * Configure as the rv_nop reactor. */ mon->reactor = get_reactor_rdef_by_name("nop"); - mon->reacting = false; return 0; } -- cgit v1.2.3 From e82aea50fe0600da176b2e50a6213f6057b719f9 Mon Sep 17 00:00:00 2001 From: Nam Cao Date: Sun, 27 Jul 2025 19:31:12 +0200 Subject: rv: Fix wrong type cast in monitors_show() Argument 'p' of monitors_show() is not a pointer to struct rv_monitor, it is actually a pointer to the list_head inside struct rv_monitor. Therefore it is wrong to cast 'p' to struct rv_monitor *. This wrong type cast has been there since the beginning. But it still worked because the list_head was the first field in struct rv_monitor_def. This is no longer true since commit 24cbfe18d55a ("rv: Merge struct rv_monitor_def into struct rv_monitor") moved the list_head, and this wrong type cast became a functional problem. Properly use container_of() instead. Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://lore.kernel.org/35e49e97696007919ceacf73796487a2e15a3d02.1753625621.git.namcao@linutronix.de Fixes: 24cbfe18d55a ("rv: Merge struct rv_monitor_def into struct rv_monitor") Signed-off-by: Nam Cao Reviewed-by: Gabriele Monaco Signed-off-by: Steven Rostedt (Google) --- kernel/trace/rv/rv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/trace') diff --git a/kernel/trace/rv/rv.c b/kernel/trace/rv/rv.c index 6c8498743b98..bd7d56dbf6c2 100644 --- a/kernel/trace/rv/rv.c +++ b/kernel/trace/rv/rv.c @@ -458,7 +458,7 @@ out_remove_root: */ static int monitors_show(struct seq_file *m, void *p) { - struct rv_monitor *mon = p; + struct rv_monitor *mon = container_of(p, struct rv_monitor, list); if (mon->parent) seq_printf(m, "%s:%s\n", mon->parent->name, mon->name); -- cgit v1.2.3 From 3cfb9c1a7db091f9030826b897d07ddce1591e7f Mon Sep 17 00:00:00 2001 From: Nam Cao Date: Sun, 27 Jul 2025 19:31:13 +0200 Subject: rv: Fix wrong type cast in reactors_show() and monitor_reactor_show() Argument 'p' of reactors_show() and monitor_reactor_show() is not a pointer to struct rv_reactor, it is actually a pointer to the list_head inside struct rv_reactor. Therefore it's wrong to cast 'p' to struct rv_reactor *. This wrong type cast has been there since the beginning. But it still worked because the list_head was the first field in struct rv_reactor_def. This is no longer true since commit 3d3c376118b5 ("rv: Merge struct rv_reactor_def into struct rv_reactor") moved the list_head, and this wrong type cast became a functional problem. Properly use container_of() instead. Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Cc: Gabriele Monaco Link: https://lore.kernel.org/b4febbd6844311209e4c8768b65d508b81bd8c9b.1753625621.git.namcao@linutronix.de Fixes: 3d3c376118b5 ("rv: Merge struct rv_reactor_def into struct rv_reactor") Signed-off-by: Nam Cao Signed-off-by: Steven Rostedt (Google) --- kernel/trace/rv/rv_reactors.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/rv/rv_reactors.c b/kernel/trace/rv/rv_reactors.c index 106f2c4740f2..d32859fec238 100644 --- a/kernel/trace/rv/rv_reactors.c +++ b/kernel/trace/rv/rv_reactors.c @@ -86,7 +86,7 @@ static struct rv_reactor *get_reactor_rdef_by_name(char *name) */ static int reactors_show(struct seq_file *m, void *p) { - struct rv_reactor *reactor = p; + struct rv_reactor *reactor = container_of(p, struct rv_reactor, list); seq_printf(m, "%s\n", reactor->name); return 0; @@ -139,7 +139,7 @@ static const struct file_operations available_reactors_ops = { static int monitor_reactor_show(struct seq_file *m, void *p) { struct rv_monitor *mon = m->private; - struct rv_reactor *reactor = p; + struct rv_reactor *reactor = container_of(p, struct rv_reactor, list); if (mon->reactor == reactor) seq_printf(m, "[%s]\n", reactor->name); -- cgit v1.2.3 From 7b70ac4cad2b20eaf415276bbaa0d9df9abb428c Mon Sep 17 00:00:00 2001 From: Gabriele Monaco Date: Mon, 28 Jul 2025 15:50:14 +0200 Subject: rv: Remove trailing whitespace from tracepoint string RV event tracepoints print a line with the format: "event_xyz: S0 x event -> S1 " "event_xyz: S1 x event -> S0 (final)" While printing an event leading to a non-final state, the line has a trailing white space (visible above before the closing "). Adapt the format string not to print the trailing whitespace if we are not printing "(final)". Cc: Masami Hiramatsu Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Tomas Glozar Cc: Juri Lelli Cc: Clark Williams Cc: John Kacur Link: https://lore.kernel.org/20250728135022.255578-3-gmonaco@redhat.com Reviewed-by: Nam Cao Signed-off-by: Gabriele Monaco Signed-off-by: Steven Rostedt (Google) --- kernel/trace/rv/rv_trace.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/rv/rv_trace.h b/kernel/trace/rv/rv_trace.h index b6f310498466..17ba07329b67 100644 --- a/kernel/trace/rv/rv_trace.h +++ b/kernel/trace/rv/rv_trace.h @@ -29,11 +29,11 @@ DECLARE_EVENT_CLASS(event_da_monitor, __entry->final_state = final_state; ), - TP_printk("%s x %s -> %s %s", + TP_printk("%s x %s -> %s%s", __entry->state, __entry->event, __entry->next_state, - __entry->final_state ? "(final)" : "") + __entry->final_state ? " (final)" : "") ); DECLARE_EVENT_CLASS(error_da_monitor, @@ -90,12 +90,12 @@ DECLARE_EVENT_CLASS(event_da_monitor_id, __entry->final_state = final_state; ), - TP_printk("%d: %s x %s -> %s %s", + TP_printk("%d: %s x %s -> %s%s", __entry->id, __entry->state, __entry->event, __entry->next_state, - __entry->final_state ? "(final)" : "") + __entry->final_state ? " (final)" : "") ); DECLARE_EVENT_CLASS(error_da_monitor_id, -- cgit v1.2.3 From 7f904ff6e58d398c4336f3c19c42b338324451f7 Mon Sep 17 00:00:00 2001 From: Gabriele Monaco Date: Mon, 28 Jul 2025 15:50:15 +0200 Subject: rv: Use strings in da monitors tracepoints Using DA monitors tracepoints with KASAN enabled triggers the following warning: BUG: KASAN: global-out-of-bounds in do_trace_event_raw_event_event_da_monitor+0xd6/0x1a0 Read of size 32 at addr ffffffffaada8980 by task ... Call Trace: [...] do_trace_event_raw_event_event_da_monitor+0xd6/0x1a0 ? __pfx_do_trace_event_raw_event_event_da_monitor+0x10/0x10 ? trace_event_sncid+0x83/0x200 trace_event_sncid+0x163/0x200 [...] The buggy address belongs to the variable: automaton_snep+0x4e0/0x5e0 This is caused by the tracepoints reading 32 bytes __array instead of __string from the automata definition. Such strings are literals and reading 32 bytes ends up in out of bound memory accesses (e.g. the next automaton's data in this case). The error is harmless as, while printing the string, we stop at the null terminator, but it should still be fixed. Use the __string facilities while defining the tracepoints to avoid reading out of bound memory. Cc: Masami Hiramatsu Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Tomas Glozar Cc: Juri Lelli Cc: Clark Williams Cc: John Kacur Link: https://lore.kernel.org/20250728135022.255578-4-gmonaco@redhat.com Fixes: 792575348ff7 ("rv/include: Add deterministic automata monitor definition via C macros") Reviewed-by: Nam Cao Signed-off-by: Gabriele Monaco Signed-off-by: Steven Rostedt (Google) --- kernel/trace/rv/rv_trace.h | 76 +++++++++++++++++++++++----------------------- 1 file changed, 38 insertions(+), 38 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/rv/rv_trace.h b/kernel/trace/rv/rv_trace.h index 17ba07329b67..d38e0d3abdfd 100644 --- a/kernel/trace/rv/rv_trace.h +++ b/kernel/trace/rv/rv_trace.h @@ -16,23 +16,23 @@ DECLARE_EVENT_CLASS(event_da_monitor, TP_ARGS(state, event, next_state, final_state), TP_STRUCT__entry( - __array( char, state, MAX_DA_NAME_LEN ) - __array( char, event, MAX_DA_NAME_LEN ) - __array( char, next_state, MAX_DA_NAME_LEN ) - __field( bool, final_state ) + __string( state, state ) + __string( event, event ) + __string( next_state, next_state ) + __field( bool, final_state ) ), TP_fast_assign( - memcpy(__entry->state, state, MAX_DA_NAME_LEN); - memcpy(__entry->event, event, MAX_DA_NAME_LEN); - memcpy(__entry->next_state, next_state, MAX_DA_NAME_LEN); - __entry->final_state = final_state; + __assign_str(state); + __assign_str(event); + __assign_str(next_state); + __entry->final_state = final_state; ), TP_printk("%s x %s -> %s%s", - __entry->state, - __entry->event, - __entry->next_state, + __get_str(state), + __get_str(event), + __get_str(next_state), __entry->final_state ? " (final)" : "") ); @@ -43,18 +43,18 @@ DECLARE_EVENT_CLASS(error_da_monitor, TP_ARGS(state, event), TP_STRUCT__entry( - __array( char, state, MAX_DA_NAME_LEN ) - __array( char, event, MAX_DA_NAME_LEN ) + __string( state, state ) + __string( event, event ) ), TP_fast_assign( - memcpy(__entry->state, state, MAX_DA_NAME_LEN); - memcpy(__entry->event, event, MAX_DA_NAME_LEN); + __assign_str(state); + __assign_str(event); ), TP_printk("event %s not expected in the state %s", - __entry->event, - __entry->state) + __get_str(event), + __get_str(state)) ); #include @@ -75,26 +75,26 @@ DECLARE_EVENT_CLASS(event_da_monitor_id, TP_ARGS(id, state, event, next_state, final_state), TP_STRUCT__entry( - __field( int, id ) - __array( char, state, MAX_DA_NAME_LEN ) - __array( char, event, MAX_DA_NAME_LEN ) - __array( char, next_state, MAX_DA_NAME_LEN ) - __field( bool, final_state ) + __field( int, id ) + __string( state, state ) + __string( event, event ) + __string( next_state, next_state ) + __field( bool, final_state ) ), TP_fast_assign( - memcpy(__entry->state, state, MAX_DA_NAME_LEN); - memcpy(__entry->event, event, MAX_DA_NAME_LEN); - memcpy(__entry->next_state, next_state, MAX_DA_NAME_LEN); - __entry->id = id; - __entry->final_state = final_state; + __assign_str(state); + __assign_str(event); + __assign_str(next_state); + __entry->id = id; + __entry->final_state = final_state; ), TP_printk("%d: %s x %s -> %s%s", __entry->id, - __entry->state, - __entry->event, - __entry->next_state, + __get_str(state), + __get_str(event), + __get_str(next_state), __entry->final_state ? " (final)" : "") ); @@ -105,21 +105,21 @@ DECLARE_EVENT_CLASS(error_da_monitor_id, TP_ARGS(id, state, event), TP_STRUCT__entry( - __field( int, id ) - __array( char, state, MAX_DA_NAME_LEN ) - __array( char, event, MAX_DA_NAME_LEN ) + __field( int, id ) + __string( state, state ) + __string( event, event ) ), TP_fast_assign( - memcpy(__entry->state, state, MAX_DA_NAME_LEN); - memcpy(__entry->event, event, MAX_DA_NAME_LEN); - __entry->id = id; + __assign_str(state); + __assign_str(event); + __entry->id = id; ), TP_printk("%d: event %s not expected in the state %s", __entry->id, - __entry->event, - __entry->state) + __get_str(event), + __get_str(state)) ); #include -- cgit v1.2.3 From 79de661707a4a2dc695fd3e00529a14b4f5ec50d Mon Sep 17 00:00:00 2001 From: Gabriele Monaco Date: Mon, 28 Jul 2025 15:50:16 +0200 Subject: rv: Adjust monitor dependencies RV monitors relying on the preemptirqs tracepoints are set as dependent on PREEMPT_TRACER and IRQSOFF_TRACER. In fact, those configurations do enable the tracepoints but are not the minimal configurations enabling them, which are TRACE_PREEMPT_TOGGLE and TRACE_IRQFLAGS (not selectable manually). Set TRACE_PREEMPT_TOGGLE and TRACE_IRQFLAGS as dependencies for monitors. Cc: Masami Hiramatsu Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Tomas Glozar Cc: Juri Lelli Cc: Clark Williams Cc: John Kacur Link: https://lore.kernel.org/20250728135022.255578-5-gmonaco@redhat.com Fixes: fbe6c09b7eb4 ("rv: Add scpd, snep and sncid per-cpu monitors") Acked-by: Nam Cao Signed-off-by: Gabriele Monaco Signed-off-by: Steven Rostedt (Google) --- kernel/trace/rv/monitors/scpd/Kconfig | 2 +- kernel/trace/rv/monitors/sncid/Kconfig | 2 +- kernel/trace/rv/monitors/snep/Kconfig | 2 +- kernel/trace/rv/monitors/wip/Kconfig | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/rv/monitors/scpd/Kconfig b/kernel/trace/rv/monitors/scpd/Kconfig index b9114fbf680f..682d0416188b 100644 --- a/kernel/trace/rv/monitors/scpd/Kconfig +++ b/kernel/trace/rv/monitors/scpd/Kconfig @@ -2,7 +2,7 @@ # config RV_MON_SCPD depends on RV - depends on PREEMPT_TRACER + depends on TRACE_PREEMPT_TOGGLE depends on RV_MON_SCHED default y select DA_MON_EVENTS_IMPLICIT diff --git a/kernel/trace/rv/monitors/sncid/Kconfig b/kernel/trace/rv/monitors/sncid/Kconfig index 76bcfef4fd10..3a5639feaaaf 100644 --- a/kernel/trace/rv/monitors/sncid/Kconfig +++ b/kernel/trace/rv/monitors/sncid/Kconfig @@ -2,7 +2,7 @@ # config RV_MON_SNCID depends on RV - depends on IRQSOFF_TRACER + depends on TRACE_IRQFLAGS depends on RV_MON_SCHED default y select DA_MON_EVENTS_IMPLICIT diff --git a/kernel/trace/rv/monitors/snep/Kconfig b/kernel/trace/rv/monitors/snep/Kconfig index 77527f971232..7dd54f434ff7 100644 --- a/kernel/trace/rv/monitors/snep/Kconfig +++ b/kernel/trace/rv/monitors/snep/Kconfig @@ -2,7 +2,7 @@ # config RV_MON_SNEP depends on RV - depends on PREEMPT_TRACER + depends on TRACE_PREEMPT_TOGGLE depends on RV_MON_SCHED default y select DA_MON_EVENTS_IMPLICIT diff --git a/kernel/trace/rv/monitors/wip/Kconfig b/kernel/trace/rv/monitors/wip/Kconfig index e464b9294865..87a26195792b 100644 --- a/kernel/trace/rv/monitors/wip/Kconfig +++ b/kernel/trace/rv/monitors/wip/Kconfig @@ -2,7 +2,7 @@ # config RV_MON_WIP depends on RV - depends on PREEMPT_TRACER + depends on TRACE_PREEMPT_TOGGLE select DA_MON_EVENTS_IMPLICIT bool "wip monitor" help -- cgit v1.2.3 From 9d475d80c93735f0f336b34a8e2c22beea6145ab Mon Sep 17 00:00:00 2001 From: Gabriele Monaco Date: Mon, 28 Jul 2025 15:50:17 +0200 Subject: rv: Retry when da monitor detects race conditions DA monitor can be accessed from multiple cores simultaneously, this is likely, for instance when dealing with per-task monitors reacting on events that do not always occur on the CPU where the task is running. This can cause race conditions where two events change the next state and we see inconsistent values. E.g.: [62] event_srs: 27: sleepable x sched_wakeup -> running (final) [63] event_srs: 27: sleepable x sched_set_state_sleepable -> sleepable [63] error_srs: 27: event sched_switch_suspend not expected in the state running In this case the monitor fails because the event on CPU 62 wins against the one on CPU 63, although the correct state should have been sleepable, since the task get suspended. Detect if the current state was modified by using try_cmpxchg while storing the next value. If it was, try again reading the current state. After a maximum number of failed retries, react by calling a special tracepoint, print on the console and reset the monitor. Remove the functions da_monitor_curr_state() and da_monitor_set_state() as they only hide the underlying implementation in this case. Monitors where this type of condition can occur must be able to account for racing events in any possible order, as we cannot know the winner. Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Tomas Glozar Cc: Juri Lelli Cc: Clark Williams Cc: John Kacur Cc: Peter Zijlstra Link: https://lore.kernel.org/20250728135022.255578-6-gmonaco@redhat.com Signed-off-by: Gabriele Monaco Reviewed-by: Nam Cao Signed-off-by: Steven Rostedt (Google) --- include/linux/rv.h | 3 +- include/rv/da_monitor.h | 107 +++++++++++++++++++++++---------------------- kernel/trace/rv/Kconfig | 5 +++ kernel/trace/rv/rv_trace.h | 24 ++++++++++ 4 files changed, 85 insertions(+), 54 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/rv.h b/include/linux/rv.h index 80731242fe60..14410a42faef 100644 --- a/include/linux/rv.h +++ b/include/linux/rv.h @@ -10,7 +10,8 @@ #include #include -#define MAX_DA_NAME_LEN 32 +#define MAX_DA_NAME_LEN 32 +#define MAX_DA_RETRY_RACING_EVENTS 3 #ifdef CONFIG_RV #include diff --git a/include/rv/da_monitor.h b/include/rv/da_monitor.h index ed3c34fe18d6..17fa4f6e5ea6 100644 --- a/include/rv/da_monitor.h +++ b/include/rv/da_monitor.h @@ -54,23 +54,6 @@ static inline void da_monitor_reset_##name(struct da_monitor *da_mon) \ da_mon->curr_state = model_get_initial_state_##name(); \ } \ \ -/* \ - * da_monitor_curr_state_##name - return the current state \ - */ \ -static inline type da_monitor_curr_state_##name(struct da_monitor *da_mon) \ -{ \ - return da_mon->curr_state; \ -} \ - \ -/* \ - * da_monitor_set_state_##name - set the new current state \ - */ \ -static inline void \ -da_monitor_set_state_##name(struct da_monitor *da_mon, enum states_##name state) \ -{ \ - da_mon->curr_state = state; \ -} \ - \ /* \ * da_monitor_start_##name - start monitoring \ * \ @@ -127,63 +110,81 @@ static inline bool da_monitor_handling_event_##name(struct da_monitor *da_mon) * 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. */ #define DECLARE_DA_MON_MODEL_HANDLER_IMPLICIT(name, type) \ \ static inline bool \ da_event_##name(struct da_monitor *da_mon, enum events_##name event) \ { \ - type curr_state = da_monitor_curr_state_##name(da_mon); \ - type next_state = model_get_next_state_##name(curr_state, event); \ - \ - if (next_state != INVALID_STATE) { \ - da_monitor_set_state_##name(da_mon, next_state); \ - \ - trace_event_##name(model_get_state_name_##name(curr_state), \ - model_get_event_name_##name(event), \ - model_get_state_name_##name(next_state), \ - model_is_final_state_##name(next_state)); \ - \ - return true; \ + enum states_##name 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_##name(curr_state, event); \ + if (next_state == INVALID_STATE) { \ + cond_react_##name(curr_state, event); \ + trace_error_##name(model_get_state_name_##name(curr_state), \ + model_get_event_name_##name(event)); \ + return false; \ + } \ + if (likely(try_cmpxchg(&da_mon->curr_state, &curr_state, next_state))) { \ + trace_event_##name(model_get_state_name_##name(curr_state), \ + model_get_event_name_##name(event), \ + model_get_state_name_##name(next_state), \ + model_is_final_state_##name(next_state)); \ + return true; \ + } \ } \ \ - cond_react_##name(curr_state, event); \ - \ - trace_error_##name(model_get_state_name_##name(curr_state), \ - model_get_event_name_##name(event)); \ - \ + trace_rv_retries_error(#name, model_get_event_name_##name(event)); \ + pr_warn("rv: " __stringify(MAX_DA_RETRY_RACING_EVENTS) \ + " retries reached for event %s, resetting monitor %s", \ + model_get_event_name_##name(event), #name); \ return false; \ } \ /* * 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. */ #define DECLARE_DA_MON_MODEL_HANDLER_PER_TASK(name, type) \ \ static inline bool da_event_##name(struct da_monitor *da_mon, struct task_struct *tsk, \ enum events_##name event) \ { \ - type curr_state = da_monitor_curr_state_##name(da_mon); \ - type next_state = model_get_next_state_##name(curr_state, event); \ - \ - if (next_state != INVALID_STATE) { \ - da_monitor_set_state_##name(da_mon, next_state); \ - \ - trace_event_##name(tsk->pid, \ - model_get_state_name_##name(curr_state), \ - model_get_event_name_##name(event), \ - model_get_state_name_##name(next_state), \ - model_is_final_state_##name(next_state)); \ - \ - return true; \ + enum states_##name 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_##name(curr_state, event); \ + if (next_state == INVALID_STATE) { \ + cond_react_##name(curr_state, event); \ + trace_error_##name(tsk->pid, \ + model_get_state_name_##name(curr_state), \ + model_get_event_name_##name(event)); \ + return false; \ + } \ + if (likely(try_cmpxchg(&da_mon->curr_state, &curr_state, next_state))) { \ + trace_event_##name(tsk->pid, \ + model_get_state_name_##name(curr_state), \ + model_get_event_name_##name(event), \ + model_get_state_name_##name(next_state), \ + model_is_final_state_##name(next_state)); \ + return true; \ + } \ } \ \ - cond_react_##name(curr_state, event); \ - \ - trace_error_##name(tsk->pid, \ - model_get_state_name_##name(curr_state), \ - model_get_event_name_##name(event)); \ - \ + trace_rv_retries_error(#name, model_get_event_name_##name(event)); \ + pr_warn("rv: " __stringify(MAX_DA_RETRY_RACING_EVENTS) \ + " retries reached for event %s, resetting monitor %s", \ + model_get_event_name_##name(event), #name); \ return false; \ } diff --git a/kernel/trace/rv/Kconfig b/kernel/trace/rv/Kconfig index 26017378f79b..34164eb4ec91 100644 --- a/kernel/trace/rv/Kconfig +++ b/kernel/trace/rv/Kconfig @@ -3,12 +3,17 @@ config RV_MON_EVENTS bool +config RV_MON_MAINTENANCE_EVENTS + bool + config DA_MON_EVENTS_IMPLICIT select RV_MON_EVENTS + select RV_MON_MAINTENANCE_EVENTS bool config DA_MON_EVENTS_ID select RV_MON_EVENTS + select RV_MON_MAINTENANCE_EVENTS bool config LTL_MON_EVENTS_ID diff --git a/kernel/trace/rv/rv_trace.h b/kernel/trace/rv/rv_trace.h index d38e0d3abdfd..3af46cd185b3 100644 --- a/kernel/trace/rv/rv_trace.h +++ b/kernel/trace/rv/rv_trace.h @@ -176,6 +176,30 @@ DECLARE_EVENT_CLASS(error_ltl_monitor_id, #include // Add new monitors based on CONFIG_LTL_MON_EVENTS_ID here #endif /* CONFIG_LTL_MON_EVENTS_ID */ + +#ifdef CONFIG_RV_MON_MAINTENANCE_EVENTS +/* Tracepoint useful for monitors development, currenly only used in DA */ +TRACE_EVENT(rv_retries_error, + + TP_PROTO(char *name, char *event), + + TP_ARGS(name, event), + + TP_STRUCT__entry( + __string( name, name ) + __string( event, event ) + ), + + TP_fast_assign( + __assign_str(name); + __assign_str(event); + ), + + TP_printk(__stringify(MAX_DA_RETRY_RACING_EVENTS) + " retries reached for event %s, resetting monitor %s", + __get_str(event), __get_str(name)) +); +#endif /* CONFIG_RV_MON_MAINTENANCE_EVENTS */ #endif /* _TRACE_RV_H */ /* This part must be outside protection */ -- cgit v1.2.3 From adcc3bfa8806761ac21aa271f78454113ec6936e Mon Sep 17 00:00:00 2001 From: Gabriele Monaco Date: Mon, 28 Jul 2025 15:50:18 +0200 Subject: sched: Adapt sched tracepoints for RV task model Add the following tracepoint: * sched_set_need_resched(tsk, cpu, tif) Called when a task is set the need resched [lazy] flag Remove the unused ip parameter from sched_entry and sched_exit and alter sched_entry to have a value of preempt consistent with the one used in sched_switch. Also adapt all monitors using sched_{entry,exit} to avoid breaking build. These tracepoints are useful to describe the Linux task model and are adapted from the patches by Daniel Bristot de Oliveira (https://bristot.me/linux-task-model/). Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Masami Hiramatsu Cc: Nam Cao Cc: Tomas Glozar Cc: Juri Lelli Cc: Clark Williams Cc: John Kacur Link: https://lore.kernel.org/20250728135022.255578-7-gmonaco@redhat.com Signed-off-by: Gabriele Monaco Signed-off-by: Steven Rostedt (Google) --- include/linux/sched.h | 7 ++++++- include/trace/events/sched.h | 12 ++++++++---- kernel/sched/core.c | 13 ++++++++++--- kernel/trace/rv/monitors/sco/sco.c | 4 ++-- kernel/trace/rv/monitors/scpd/scpd.c | 4 ++-- kernel/trace/rv/monitors/sncid/sncid.c | 4 ++-- kernel/trace/rv/monitors/snep/snep.c | 4 ++-- kernel/trace/rv/monitors/tss/tss.c | 4 ++-- 8 files changed, 34 insertions(+), 18 deletions(-) (limited to 'kernel/trace') diff --git a/include/linux/sched.h b/include/linux/sched.h index fabd7fe1a07a..91d1fdbc2f56 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -339,9 +339,11 @@ extern void io_schedule_finish(int token); extern long io_schedule_timeout(long timeout); extern void io_schedule(void); -/* wrapper function to trace from this header file */ +/* wrapper functions to trace from this header file */ DECLARE_TRACEPOINT(sched_set_state_tp); extern void __trace_set_current_state(int state_value); +DECLARE_TRACEPOINT(sched_set_need_resched_tp); +extern void __trace_set_need_resched(struct task_struct *curr, int tif); /** * struct prev_cputime - snapshot of system and user cputime @@ -2063,6 +2065,9 @@ static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag) static inline void set_tsk_need_resched(struct task_struct *tsk) { + if (tracepoint_enabled(sched_set_need_resched_tp) && + !test_tsk_thread_flag(tsk, TIF_NEED_RESCHED)) + __trace_set_need_resched(tsk, TIF_NEED_RESCHED); set_tsk_thread_flag(tsk,TIF_NEED_RESCHED); } diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index 4e6b2910cec3..c08893bde255 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -882,18 +882,22 @@ DECLARE_TRACE(sched_compute_energy, TP_ARGS(p, dst_cpu, energy, max_util, busy_time)); DECLARE_TRACE(sched_entry, - TP_PROTO(bool preempt, unsigned long ip), - TP_ARGS(preempt, ip)); + TP_PROTO(bool preempt), + TP_ARGS(preempt)); DECLARE_TRACE(sched_exit, - TP_PROTO(bool is_switch, unsigned long ip), - TP_ARGS(is_switch, ip)); + TP_PROTO(bool is_switch), + TP_ARGS(is_switch)); DECLARE_TRACE_CONDITION(sched_set_state, TP_PROTO(struct task_struct *tsk, int state), TP_ARGS(tsk, state), TP_CONDITION(!!(tsk->__state) != !!state)); +DECLARE_TRACE(sched_set_need_resched, + TP_PROTO(struct task_struct *tsk, int cpu, int tif), + TP_ARGS(tsk, cpu, tif)); + #endif /* _TRACE_SCHED_H */ /* This part must be outside protection */ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index ec68fc686bd7..b485e0639616 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1110,6 +1110,7 @@ static void __resched_curr(struct rq *rq, int tif) cpu = cpu_of(rq); + trace_sched_set_need_resched_tp(curr, cpu, tif); if (cpu == smp_processor_id()) { set_ti_thread_flag(cti, tif); if (tif == TIF_NEED_RESCHED) @@ -1125,6 +1126,11 @@ static void __resched_curr(struct rq *rq, int tif) } } +void __trace_set_need_resched(struct task_struct *curr, int tif) +{ + trace_sched_set_need_resched_tp(curr, smp_processor_id(), tif); +} + void resched_curr(struct rq *rq) { __resched_curr(rq, TIF_NEED_RESCHED); @@ -5329,7 +5335,7 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev) * switched the context for the first time. It is returning from * schedule for the first time in this path. */ - trace_sched_exit_tp(true, CALLER_ADDR0); + trace_sched_exit_tp(true); preempt_enable(); if (current->set_child_tid) @@ -6678,7 +6684,8 @@ static void __sched notrace __schedule(int sched_mode) struct rq *rq; int cpu; - trace_sched_entry_tp(preempt, CALLER_ADDR0); + /* Trace preemptions consistently with task switches */ + trace_sched_entry_tp(sched_mode == SM_PREEMPT); cpu = smp_processor_id(); rq = cpu_rq(cpu); @@ -6793,7 +6800,7 @@ picked: __balance_callbacks(rq); raw_spin_rq_unlock_irq(rq); } - trace_sched_exit_tp(is_switch, CALLER_ADDR0); + trace_sched_exit_tp(is_switch); } void __noreturn do_task_dead(void) diff --git a/kernel/trace/rv/monitors/sco/sco.c b/kernel/trace/rv/monitors/sco/sco.c index 66f4639d46ac..04c36405e2e3 100644 --- a/kernel/trace/rv/monitors/sco/sco.c +++ b/kernel/trace/rv/monitors/sco/sco.c @@ -24,12 +24,12 @@ static void handle_sched_set_state(void *data, struct task_struct *tsk, int stat da_handle_start_event_sco(sched_set_state_sco); } -static void handle_schedule_entry(void *data, bool preempt, unsigned long ip) +static void handle_schedule_entry(void *data, bool preempt) { da_handle_event_sco(schedule_entry_sco); } -static void handle_schedule_exit(void *data, bool is_switch, unsigned long ip) +static void handle_schedule_exit(void *data, bool is_switch) { da_handle_start_event_sco(schedule_exit_sco); } diff --git a/kernel/trace/rv/monitors/scpd/scpd.c b/kernel/trace/rv/monitors/scpd/scpd.c index 299703cd72b0..1e351ba52fee 100644 --- a/kernel/trace/rv/monitors/scpd/scpd.c +++ b/kernel/trace/rv/monitors/scpd/scpd.c @@ -30,12 +30,12 @@ static void handle_preempt_enable(void *data, unsigned long ip, unsigned long pa da_handle_start_event_scpd(preempt_enable_scpd); } -static void handle_schedule_entry(void *data, bool preempt, unsigned long ip) +static void handle_schedule_entry(void *data, bool preempt) { da_handle_event_scpd(schedule_entry_scpd); } -static void handle_schedule_exit(void *data, bool is_switch, unsigned long ip) +static void handle_schedule_exit(void *data, bool is_switch) { da_handle_event_scpd(schedule_exit_scpd); } diff --git a/kernel/trace/rv/monitors/sncid/sncid.c b/kernel/trace/rv/monitors/sncid/sncid.c index 3e1ee715a0fb..c8491f426365 100644 --- a/kernel/trace/rv/monitors/sncid/sncid.c +++ b/kernel/trace/rv/monitors/sncid/sncid.c @@ -30,12 +30,12 @@ static void handle_irq_enable(void *data, unsigned long ip, unsigned long parent da_handle_start_event_sncid(irq_enable_sncid); } -static void handle_schedule_entry(void *data, bool preempt, unsigned long ip) +static void handle_schedule_entry(void *data, bool preempt) { da_handle_start_event_sncid(schedule_entry_sncid); } -static void handle_schedule_exit(void *data, bool is_switch, unsigned long ip) +static void handle_schedule_exit(void *data, bool is_switch) { da_handle_start_event_sncid(schedule_exit_sncid); } diff --git a/kernel/trace/rv/monitors/snep/snep.c b/kernel/trace/rv/monitors/snep/snep.c index 2adc3108d60c..558950f524a5 100644 --- a/kernel/trace/rv/monitors/snep/snep.c +++ b/kernel/trace/rv/monitors/snep/snep.c @@ -30,12 +30,12 @@ static void handle_preempt_enable(void *data, unsigned long ip, unsigned long pa da_handle_start_event_snep(preempt_enable_snep); } -static void handle_schedule_entry(void *data, bool preempt, unsigned long ip) +static void handle_schedule_entry(void *data, bool preempt) { da_handle_event_snep(schedule_entry_snep); } -static void handle_schedule_exit(void *data, bool is_switch, unsigned long ip) +static void handle_schedule_exit(void *data, bool is_switch) { da_handle_start_event_snep(schedule_exit_snep); } diff --git a/kernel/trace/rv/monitors/tss/tss.c b/kernel/trace/rv/monitors/tss/tss.c index 0452fcd9edcf..95ebd15131f5 100644 --- a/kernel/trace/rv/monitors/tss/tss.c +++ b/kernel/trace/rv/monitors/tss/tss.c @@ -27,12 +27,12 @@ static void handle_sched_switch(void *data, bool preempt, da_handle_event_tss(sched_switch_tss); } -static void handle_schedule_entry(void *data, bool preempt, unsigned long ip) +static void handle_schedule_entry(void *data, bool preempt) { da_handle_event_tss(schedule_entry_tss); } -static void handle_schedule_exit(void *data, bool is_switch, unsigned long ip) +static void handle_schedule_exit(void *data, bool is_switch) { da_handle_start_event_tss(schedule_exit_tss); } -- cgit v1.2.3 From d0096c2f9cfcb4ce385698491604610fcc1a53b3 Mon Sep 17 00:00:00 2001 From: Gabriele Monaco Date: Mon, 28 Jul 2025 15:50:19 +0200 Subject: rv: Replace tss and sncid monitors with more complete sts The tss monitor currently guarantees task switches can happen only while scheduling, whereas the sncid monitor enforces scheduling occurs with interrupt disabled. Replace the monitors with a more comprehensive specification which implies both but also ensures that: * each scheduler call disable interrupts to switch * each task switch happens with interrupts disabled Cc: Ingo Molnar Cc: Jonathan Corbet Cc: Masami Hiramatsu Cc: Nam Cao Cc: Tomas Glozar Cc: Juri Lelli Cc: Clark Williams Cc: John Kacur Cc: Peter Zijlstra Link: https://lore.kernel.org/20250728135022.255578-8-gmonaco@redhat.com Signed-off-by: Gabriele Monaco Signed-off-by: Steven Rostedt (Google) --- Documentation/trace/rv/monitor_sched.rst | 87 ++++++++------- kernel/trace/rv/Kconfig | 3 +- kernel/trace/rv/Makefile | 3 +- kernel/trace/rv/monitors/sncid/Kconfig | 15 --- kernel/trace/rv/monitors/sncid/sncid.c | 95 ---------------- kernel/trace/rv/monitors/sncid/sncid.h | 49 --------- kernel/trace/rv/monitors/sncid/sncid_trace.h | 15 --- kernel/trace/rv/monitors/sts/Kconfig | 19 ++++ kernel/trace/rv/monitors/sts/sts.c | 156 +++++++++++++++++++++++++++ kernel/trace/rv/monitors/sts/sts.h | 117 ++++++++++++++++++++ kernel/trace/rv/monitors/sts/sts_trace.h | 15 +++ kernel/trace/rv/monitors/tss/Kconfig | 14 --- kernel/trace/rv/monitors/tss/tss.c | 90 ---------------- kernel/trace/rv/monitors/tss/tss.h | 47 -------- kernel/trace/rv/monitors/tss/tss_trace.h | 15 --- kernel/trace/rv/rv_trace.h | 3 +- tools/verification/models/sched/sncid.dot | 18 ---- tools/verification/models/sched/sts.dot | 38 +++++++ tools/verification/models/sched/tss.dot | 18 ---- 19 files changed, 396 insertions(+), 421 deletions(-) delete mode 100644 kernel/trace/rv/monitors/sncid/Kconfig delete mode 100644 kernel/trace/rv/monitors/sncid/sncid.c delete mode 100644 kernel/trace/rv/monitors/sncid/sncid.h delete mode 100644 kernel/trace/rv/monitors/sncid/sncid_trace.h create mode 100644 kernel/trace/rv/monitors/sts/Kconfig create mode 100644 kernel/trace/rv/monitors/sts/sts.c create mode 100644 kernel/trace/rv/monitors/sts/sts.h create mode 100644 kernel/trace/rv/monitors/sts/sts_trace.h delete mode 100644 kernel/trace/rv/monitors/tss/Kconfig delete mode 100644 kernel/trace/rv/monitors/tss/tss.c delete mode 100644 kernel/trace/rv/monitors/tss/tss.h delete mode 100644 kernel/trace/rv/monitors/tss/tss_trace.h delete mode 100644 tools/verification/models/sched/sncid.dot create mode 100644 tools/verification/models/sched/sts.dot delete mode 100644 tools/verification/models/sched/tss.dot (limited to 'kernel/trace') diff --git a/Documentation/trace/rv/monitor_sched.rst b/Documentation/trace/rv/monitor_sched.rst index 24b2c62a3bc2..6c4c00216c07 100644 --- a/Documentation/trace/rv/monitor_sched.rst +++ b/Documentation/trace/rv/monitor_sched.rst @@ -40,26 +40,6 @@ defined in by Daniel Bristot in [1]. Currently we included the following: -Monitor tss -~~~~~~~~~~~ - -The task switch while scheduling (tss) monitor ensures a task switch happens -only in scheduling context, that is inside a call to `__schedule`:: - - | - | - v - +-----------------+ - | thread | <+ - +-----------------+ | - | | - | schedule_entry | schedule_exit - v | - sched_switch | - +--------------- | - | sched | - +--------------> -+ - Monitor sco ~~~~~~~~~~~ @@ -144,26 +124,55 @@ does not enable preemption:: | scheduling_contex -+ -Monitor sncid -~~~~~~~~~~~~~ - -The schedule not called with interrupt disabled (sncid) monitor ensures -schedule is not called with interrupt disabled:: +Monitor sts +~~~~~~~~~~~ - | - | - v - schedule_entry +--------------+ - schedule_exit | | - +----------------- | can_sched | - | | | - +----------------> | | <+ - +--------------+ | - | | - | irq_disable | irq_enable - v | - | - cant_sched -+ +The schedule implies task switch (sts) monitor ensures a task switch happens +only in scheduling context and up to once, as well as scheduling occurs with +interrupts enabled but no task switch can happen before interrupts are +disabled. When the next task picked for execution is the same as the previously +running one, no real task switch occurs but interrupts are disabled nonetheless:: + + irq_entry | + +----+ | + v | v + +------------+ irq_enable #===================# irq_disable + | | ------------> H H irq_entry + | cant_sched | <------------ H H irq_enable + | | irq_disable H can_sched H --------------+ + +------------+ H H | + H H | + +---------------> H H <-------------+ + | #===================# + | | + schedule_exit | schedule_entry + | v + | +-------------------+ irq_enable + | | scheduling | <---------------+ + | +-------------------+ | + | | | + | | irq_disable +--------+ irq_entry + | v | | --------+ + | +-------------------+ irq_entry | in_irq | | + | | | -----------> | | <-------+ + | | disable_to_switch | +--------+ + | | | --+ + | +-------------------+ | + | | | + | | sched_switch | + | v | + | +-------------------+ | + | | switching | | irq_enable + | +-------------------+ | + | | | + | | irq_enable | + | v | + | +-------------------+ | + +-- | enable_to_exit | <-+ + +-------------------+ + ^ | irq_disable + | | irq_entry + +---------------+ irq_enable References ---------- diff --git a/kernel/trace/rv/Kconfig b/kernel/trace/rv/Kconfig index 34164eb4ec91..b688b24081c8 100644 --- a/kernel/trace/rv/Kconfig +++ b/kernel/trace/rv/Kconfig @@ -50,12 +50,11 @@ source "kernel/trace/rv/monitors/wip/Kconfig" source "kernel/trace/rv/monitors/wwnr/Kconfig" source "kernel/trace/rv/monitors/sched/Kconfig" -source "kernel/trace/rv/monitors/tss/Kconfig" source "kernel/trace/rv/monitors/sco/Kconfig" source "kernel/trace/rv/monitors/snroc/Kconfig" source "kernel/trace/rv/monitors/scpd/Kconfig" source "kernel/trace/rv/monitors/snep/Kconfig" -source "kernel/trace/rv/monitors/sncid/Kconfig" +source "kernel/trace/rv/monitors/sts/Kconfig" # Add new sched monitors here source "kernel/trace/rv/monitors/rtapp/Kconfig" diff --git a/kernel/trace/rv/Makefile b/kernel/trace/rv/Makefile index 13ec2944c665..1939d3d7621c 100644 --- a/kernel/trace/rv/Makefile +++ b/kernel/trace/rv/Makefile @@ -6,15 +6,14 @@ obj-$(CONFIG_RV) += rv.o obj-$(CONFIG_RV_MON_WIP) += monitors/wip/wip.o obj-$(CONFIG_RV_MON_WWNR) += monitors/wwnr/wwnr.o obj-$(CONFIG_RV_MON_SCHED) += monitors/sched/sched.o -obj-$(CONFIG_RV_MON_TSS) += monitors/tss/tss.o obj-$(CONFIG_RV_MON_SCO) += monitors/sco/sco.o obj-$(CONFIG_RV_MON_SNROC) += monitors/snroc/snroc.o obj-$(CONFIG_RV_MON_SCPD) += monitors/scpd/scpd.o obj-$(CONFIG_RV_MON_SNEP) += monitors/snep/snep.o -obj-$(CONFIG_RV_MON_SNCID) += monitors/sncid/sncid.o obj-$(CONFIG_RV_MON_RTAPP) += monitors/rtapp/rtapp.o obj-$(CONFIG_RV_MON_PAGEFAULT) += monitors/pagefault/pagefault.o obj-$(CONFIG_RV_MON_SLEEP) += monitors/sleep/sleep.o +obj-$(CONFIG_RV_MON_STS) += monitors/sts/sts.o # Add new monitors here obj-$(CONFIG_RV_REACTORS) += rv_reactors.o obj-$(CONFIG_RV_REACT_PRINTK) += reactor_printk.o diff --git a/kernel/trace/rv/monitors/sncid/Kconfig b/kernel/trace/rv/monitors/sncid/Kconfig deleted file mode 100644 index 3a5639feaaaf..000000000000 --- a/kernel/trace/rv/monitors/sncid/Kconfig +++ /dev/null @@ -1,15 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -# -config RV_MON_SNCID - depends on RV - depends on TRACE_IRQFLAGS - depends on RV_MON_SCHED - default y - select DA_MON_EVENTS_IMPLICIT - bool "sncid monitor" - help - Monitor to ensure schedule is not called with interrupt disabled. - This monitor is part of the sched monitors collection. - - For further information, see: - Documentation/trace/rv/monitor_sched.rst diff --git a/kernel/trace/rv/monitors/sncid/sncid.c b/kernel/trace/rv/monitors/sncid/sncid.c deleted file mode 100644 index c8491f426365..000000000000 --- a/kernel/trace/rv/monitors/sncid/sncid.c +++ /dev/null @@ -1,95 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include -#include -#include -#include -#include -#include -#include -#include - -#define MODULE_NAME "sncid" - -#include -#include -#include -#include - -#include "sncid.h" - -static struct rv_monitor rv_sncid; -DECLARE_DA_MON_PER_CPU(sncid, unsigned char); - -static void handle_irq_disable(void *data, unsigned long ip, unsigned long parent_ip) -{ - da_handle_event_sncid(irq_disable_sncid); -} - -static void handle_irq_enable(void *data, unsigned long ip, unsigned long parent_ip) -{ - da_handle_start_event_sncid(irq_enable_sncid); -} - -static void handle_schedule_entry(void *data, bool preempt) -{ - da_handle_start_event_sncid(schedule_entry_sncid); -} - -static void handle_schedule_exit(void *data, bool is_switch) -{ - da_handle_start_event_sncid(schedule_exit_sncid); -} - -static int enable_sncid(void) -{ - int retval; - - retval = da_monitor_init_sncid(); - if (retval) - return retval; - - rv_attach_trace_probe("sncid", irq_disable, handle_irq_disable); - rv_attach_trace_probe("sncid", irq_enable, handle_irq_enable); - rv_attach_trace_probe("sncid", sched_entry_tp, handle_schedule_entry); - rv_attach_trace_probe("sncid", sched_exit_tp, handle_schedule_exit); - - return 0; -} - -static void disable_sncid(void) -{ - rv_sncid.enabled = 0; - - rv_detach_trace_probe("sncid", irq_disable, handle_irq_disable); - rv_detach_trace_probe("sncid", irq_enable, handle_irq_enable); - rv_detach_trace_probe("sncid", sched_entry_tp, handle_schedule_entry); - rv_detach_trace_probe("sncid", sched_exit_tp, handle_schedule_exit); - - da_monitor_destroy_sncid(); -} - -static struct rv_monitor rv_sncid = { - .name = "sncid", - .description = "schedule not called with interrupt disabled.", - .enable = enable_sncid, - .disable = disable_sncid, - .reset = da_monitor_reset_all_sncid, - .enabled = 0, -}; - -static int __init register_sncid(void) -{ - return rv_register_monitor(&rv_sncid, &rv_sched); -} - -static void __exit unregister_sncid(void) -{ - rv_unregister_monitor(&rv_sncid); -} - -module_init(register_sncid); -module_exit(unregister_sncid); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Gabriele Monaco "); -MODULE_DESCRIPTION("sncid: schedule not called with interrupt disabled."); diff --git a/kernel/trace/rv/monitors/sncid/sncid.h b/kernel/trace/rv/monitors/sncid/sncid.h deleted file mode 100644 index 21304725142b..000000000000 --- a/kernel/trace/rv/monitors/sncid/sncid.h +++ /dev/null @@ -1,49 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Automatically generated C representation of sncid automaton - * For further information about this format, see kernel documentation: - * Documentation/trace/rv/deterministic_automata.rst - */ - -enum states_sncid { - can_sched_sncid = 0, - cant_sched_sncid, - state_max_sncid -}; - -#define INVALID_STATE state_max_sncid - -enum events_sncid { - irq_disable_sncid = 0, - irq_enable_sncid, - schedule_entry_sncid, - schedule_exit_sncid, - event_max_sncid -}; - -struct automaton_sncid { - char *state_names[state_max_sncid]; - char *event_names[event_max_sncid]; - unsigned char function[state_max_sncid][event_max_sncid]; - unsigned char initial_state; - bool final_states[state_max_sncid]; -}; - -static const struct automaton_sncid automaton_sncid = { - .state_names = { - "can_sched", - "cant_sched" - }, - .event_names = { - "irq_disable", - "irq_enable", - "schedule_entry", - "schedule_exit" - }, - .function = { - { cant_sched_sncid, INVALID_STATE, can_sched_sncid, can_sched_sncid }, - { INVALID_STATE, can_sched_sncid, INVALID_STATE, INVALID_STATE }, - }, - .initial_state = can_sched_sncid, - .final_states = { 1, 0 }, -}; diff --git a/kernel/trace/rv/monitors/sncid/sncid_trace.h b/kernel/trace/rv/monitors/sncid/sncid_trace.h deleted file mode 100644 index 3ce42a57671d..000000000000 --- a/kernel/trace/rv/monitors/sncid/sncid_trace.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -/* - * Snippet to be included in rv_trace.h - */ - -#ifdef CONFIG_RV_MON_SNCID -DEFINE_EVENT(event_da_monitor, event_sncid, - TP_PROTO(char *state, char *event, char *next_state, bool final_state), - TP_ARGS(state, event, next_state, final_state)); - -DEFINE_EVENT(error_da_monitor, error_sncid, - TP_PROTO(char *state, char *event), - TP_ARGS(state, event)); -#endif /* CONFIG_RV_MON_SNCID */ diff --git a/kernel/trace/rv/monitors/sts/Kconfig b/kernel/trace/rv/monitors/sts/Kconfig new file mode 100644 index 000000000000..7d1ff0f6fc91 --- /dev/null +++ b/kernel/trace/rv/monitors/sts/Kconfig @@ -0,0 +1,19 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +config RV_MON_STS + depends on RV + depends on TRACE_IRQFLAGS + depends on RV_MON_SCHED + default y + select DA_MON_EVENTS_IMPLICIT + bool "sts monitor" + help + Monitor to ensure relationships between scheduler and task switches + * the scheduler is called and returns with interrupts disabled + * each call to the scheduler has up to one switch + * switches only happen inside the scheduler + * each call to the scheduler disables interrupts to switch + This monitor is part of the sched monitors collection. + + For further information, see: + Documentation/trace/rv/monitor_sched.rst diff --git a/kernel/trace/rv/monitors/sts/sts.c b/kernel/trace/rv/monitors/sts/sts.c new file mode 100644 index 000000000000..c4a9cd67c1d2 --- /dev/null +++ b/kernel/trace/rv/monitors/sts/sts.c @@ -0,0 +1,156 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include +#include + +#define MODULE_NAME "sts" + +#include +#include +#include +#include +#include + +#include "sts.h" + +static struct rv_monitor rv_sts; +DECLARE_DA_MON_PER_CPU(sts, unsigned char); + +#ifdef CONFIG_X86_LOCAL_APIC +#include + +static void handle_vector_irq_entry(void *data, int vector) +{ + da_handle_event_sts(irq_entry_sts); +} + +static void attach_vector_irq(void) +{ + rv_attach_trace_probe("sts", local_timer_entry, handle_vector_irq_entry); + if (IS_ENABLED(CONFIG_IRQ_WORK)) + rv_attach_trace_probe("sts", irq_work_entry, handle_vector_irq_entry); + if (IS_ENABLED(CONFIG_SMP)) { + rv_attach_trace_probe("sts", reschedule_entry, handle_vector_irq_entry); + rv_attach_trace_probe("sts", call_function_entry, handle_vector_irq_entry); + rv_attach_trace_probe("sts", call_function_single_entry, handle_vector_irq_entry); + } +} + +static void detach_vector_irq(void) +{ + rv_detach_trace_probe("sts", local_timer_entry, handle_vector_irq_entry); + if (IS_ENABLED(CONFIG_IRQ_WORK)) + rv_detach_trace_probe("sts", irq_work_entry, handle_vector_irq_entry); + if (IS_ENABLED(CONFIG_SMP)) { + rv_detach_trace_probe("sts", reschedule_entry, handle_vector_irq_entry); + rv_detach_trace_probe("sts", call_function_entry, handle_vector_irq_entry); + rv_detach_trace_probe("sts", call_function_single_entry, handle_vector_irq_entry); + } +} + +#else +/* We assume irq_entry tracepoints are sufficient on other architectures */ +static void attach_vector_irq(void) { } +static void detach_vector_irq(void) { } +#endif + +static void handle_irq_disable(void *data, unsigned long ip, unsigned long parent_ip) +{ + da_handle_event_sts(irq_disable_sts); +} + +static void handle_irq_enable(void *data, unsigned long ip, unsigned long parent_ip) +{ + da_handle_event_sts(irq_enable_sts); +} + +static void handle_irq_entry(void *data, int irq, struct irqaction *action) +{ + da_handle_event_sts(irq_entry_sts); +} + +static void handle_sched_switch(void *data, bool preempt, + struct task_struct *prev, + struct task_struct *next, + unsigned int prev_state) +{ + da_handle_event_sts(sched_switch_sts); +} + +static void handle_schedule_entry(void *data, bool preempt) +{ + da_handle_event_sts(schedule_entry_sts); +} + +static void handle_schedule_exit(void *data, bool is_switch) +{ + da_handle_start_event_sts(schedule_exit_sts); +} + +static int enable_sts(void) +{ + int retval; + + retval = da_monitor_init_sts(); + if (retval) + return retval; + + rv_attach_trace_probe("sts", irq_disable, handle_irq_disable); + rv_attach_trace_probe("sts", irq_enable, handle_irq_enable); + rv_attach_trace_probe("sts", irq_handler_entry, handle_irq_entry); + rv_attach_trace_probe("sts", sched_switch, handle_sched_switch); + rv_attach_trace_probe("sts", sched_entry_tp, handle_schedule_entry); + rv_attach_trace_probe("sts", sched_exit_tp, handle_schedule_exit); + attach_vector_irq(); + + return 0; +} + +static void disable_sts(void) +{ + rv_sts.enabled = 0; + + rv_detach_trace_probe("sts", irq_disable, handle_irq_disable); + rv_detach_trace_probe("sts", irq_enable, handle_irq_enable); + rv_detach_trace_probe("sts", irq_handler_entry, handle_irq_entry); + rv_detach_trace_probe("sts", sched_switch, handle_sched_switch); + rv_detach_trace_probe("sts", sched_entry_tp, handle_schedule_entry); + rv_detach_trace_probe("sts", sched_exit_tp, handle_schedule_exit); + detach_vector_irq(); + + da_monitor_destroy_sts(); +} + +/* + * This is the monitor register section. + */ +static struct rv_monitor rv_sts = { + .name = "sts", + .description = "schedule implies task switch.", + .enable = enable_sts, + .disable = disable_sts, + .reset = da_monitor_reset_all_sts, + .enabled = 0, +}; + +static int __init register_sts(void) +{ + return rv_register_monitor(&rv_sts, &rv_sched); +} + +static void __exit unregister_sts(void) +{ + rv_unregister_monitor(&rv_sts); +} + +module_init(register_sts); +module_exit(unregister_sts); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Gabriele Monaco "); +MODULE_DESCRIPTION("sts: schedule implies task switch."); diff --git a/kernel/trace/rv/monitors/sts/sts.h b/kernel/trace/rv/monitors/sts/sts.h new file mode 100644 index 000000000000..3368b6599a00 --- /dev/null +++ b/kernel/trace/rv/monitors/sts/sts.h @@ -0,0 +1,117 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Automatically generated C representation of sts automaton + * For further information about this format, see kernel documentation: + * Documentation/trace/rv/deterministic_automata.rst + */ + +enum states_sts { + can_sched_sts = 0, + cant_sched_sts, + disable_to_switch_sts, + enable_to_exit_sts, + in_irq_sts, + scheduling_sts, + switching_sts, + state_max_sts +}; + +#define INVALID_STATE state_max_sts + +enum events_sts { + irq_disable_sts = 0, + irq_enable_sts, + irq_entry_sts, + sched_switch_sts, + schedule_entry_sts, + schedule_exit_sts, + event_max_sts +}; + +struct automaton_sts { + char *state_names[state_max_sts]; + char *event_names[event_max_sts]; + unsigned char function[state_max_sts][event_max_sts]; + unsigned char initial_state; + bool final_states[state_max_sts]; +}; + +static const struct automaton_sts automaton_sts = { + .state_names = { + "can_sched", + "cant_sched", + "disable_to_switch", + "enable_to_exit", + "in_irq", + "scheduling", + "switching" + }, + .event_names = { + "irq_disable", + "irq_enable", + "irq_entry", + "sched_switch", + "schedule_entry", + "schedule_exit" + }, + .function = { + { + cant_sched_sts, + INVALID_STATE, + INVALID_STATE, + INVALID_STATE, + scheduling_sts, + INVALID_STATE + }, + { + INVALID_STATE, + can_sched_sts, + cant_sched_sts, + INVALID_STATE, + INVALID_STATE, + INVALID_STATE + }, + { + INVALID_STATE, + enable_to_exit_sts, + in_irq_sts, + switching_sts, + INVALID_STATE, + INVALID_STATE + }, + { + enable_to_exit_sts, + enable_to_exit_sts, + enable_to_exit_sts, + INVALID_STATE, + INVALID_STATE, + can_sched_sts + }, + { + INVALID_STATE, + scheduling_sts, + in_irq_sts, + INVALID_STATE, + INVALID_STATE, + INVALID_STATE + }, + { + disable_to_switch_sts, + INVALID_STATE, + INVALID_STATE, + INVALID_STATE, + INVALID_STATE, + INVALID_STATE + }, + { + INVALID_STATE, + enable_to_exit_sts, + INVALID_STATE, + INVALID_STATE, + INVALID_STATE, + INVALID_STATE + }, + }, + .initial_state = can_sched_sts, + .final_states = { 1, 0, 0, 0, 0, 0, 0 }, +}; diff --git a/kernel/trace/rv/monitors/sts/sts_trace.h b/kernel/trace/rv/monitors/sts/sts_trace.h new file mode 100644 index 000000000000..d78beb58d5b3 --- /dev/null +++ b/kernel/trace/rv/monitors/sts/sts_trace.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Snippet to be included in rv_trace.h + */ + +#ifdef CONFIG_RV_MON_STS +DEFINE_EVENT(event_da_monitor, event_sts, + TP_PROTO(char *state, char *event, char *next_state, bool final_state), + TP_ARGS(state, event, next_state, final_state)); + +DEFINE_EVENT(error_da_monitor, error_sts, + TP_PROTO(char *state, char *event), + TP_ARGS(state, event)); +#endif /* CONFIG_RV_MON_STS */ diff --git a/kernel/trace/rv/monitors/tss/Kconfig b/kernel/trace/rv/monitors/tss/Kconfig deleted file mode 100644 index 479f86f52e60..000000000000 --- a/kernel/trace/rv/monitors/tss/Kconfig +++ /dev/null @@ -1,14 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -# -config RV_MON_TSS - depends on RV - depends on RV_MON_SCHED - default y - select DA_MON_EVENTS_IMPLICIT - bool "tss monitor" - help - Monitor to ensure sched_switch happens only in scheduling context. - This monitor is part of the sched monitors collection. - - For further information, see: - Documentation/trace/rv/monitor_sched.rst diff --git a/kernel/trace/rv/monitors/tss/tss.c b/kernel/trace/rv/monitors/tss/tss.c deleted file mode 100644 index 95ebd15131f5..000000000000 --- a/kernel/trace/rv/monitors/tss/tss.c +++ /dev/null @@ -1,90 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include -#include -#include -#include -#include -#include -#include -#include - -#define MODULE_NAME "tss" - -#include -#include -#include - -#include "tss.h" - -static struct rv_monitor rv_tss; -DECLARE_DA_MON_PER_CPU(tss, unsigned char); - -static void handle_sched_switch(void *data, bool preempt, - struct task_struct *prev, - struct task_struct *next, - unsigned int prev_state) -{ - da_handle_event_tss(sched_switch_tss); -} - -static void handle_schedule_entry(void *data, bool preempt) -{ - da_handle_event_tss(schedule_entry_tss); -} - -static void handle_schedule_exit(void *data, bool is_switch) -{ - da_handle_start_event_tss(schedule_exit_tss); -} - -static int enable_tss(void) -{ - int retval; - - retval = da_monitor_init_tss(); - if (retval) - return retval; - - rv_attach_trace_probe("tss", sched_switch, handle_sched_switch); - rv_attach_trace_probe("tss", sched_entry_tp, handle_schedule_entry); - rv_attach_trace_probe("tss", sched_exit_tp, handle_schedule_exit); - - return 0; -} - -static void disable_tss(void) -{ - rv_tss.enabled = 0; - - rv_detach_trace_probe("tss", sched_switch, handle_sched_switch); - rv_detach_trace_probe("tss", sched_entry_tp, handle_schedule_entry); - rv_detach_trace_probe("tss", sched_exit_tp, handle_schedule_exit); - - da_monitor_destroy_tss(); -} - -static struct rv_monitor rv_tss = { - .name = "tss", - .description = "task switch while scheduling.", - .enable = enable_tss, - .disable = disable_tss, - .reset = da_monitor_reset_all_tss, - .enabled = 0, -}; - -static int __init register_tss(void) -{ - return rv_register_monitor(&rv_tss, &rv_sched); -} - -static void __exit unregister_tss(void) -{ - rv_unregister_monitor(&rv_tss); -} - -module_init(register_tss); -module_exit(unregister_tss); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Gabriele Monaco "); -MODULE_DESCRIPTION("tss: task switch while scheduling."); diff --git a/kernel/trace/rv/monitors/tss/tss.h b/kernel/trace/rv/monitors/tss/tss.h deleted file mode 100644 index f0a36fda1b87..000000000000 --- a/kernel/trace/rv/monitors/tss/tss.h +++ /dev/null @@ -1,47 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Automatically generated C representation of tss automaton - * For further information about this format, see kernel documentation: - * Documentation/trace/rv/deterministic_automata.rst - */ - -enum states_tss { - thread_tss = 0, - sched_tss, - state_max_tss -}; - -#define INVALID_STATE state_max_tss - -enum events_tss { - sched_switch_tss = 0, - schedule_entry_tss, - schedule_exit_tss, - event_max_tss -}; - -struct automaton_tss { - char *state_names[state_max_tss]; - char *event_names[event_max_tss]; - unsigned char function[state_max_tss][event_max_tss]; - unsigned char initial_state; - bool final_states[state_max_tss]; -}; - -static const struct automaton_tss automaton_tss = { - .state_names = { - "thread", - "sched" - }, - .event_names = { - "sched_switch", - "schedule_entry", - "schedule_exit" - }, - .function = { - { INVALID_STATE, sched_tss, INVALID_STATE }, - { sched_tss, INVALID_STATE, thread_tss }, - }, - .initial_state = thread_tss, - .final_states = { 1, 0 }, -}; diff --git a/kernel/trace/rv/monitors/tss/tss_trace.h b/kernel/trace/rv/monitors/tss/tss_trace.h deleted file mode 100644 index 4619dbb50cc0..000000000000 --- a/kernel/trace/rv/monitors/tss/tss_trace.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ - -/* - * Snippet to be included in rv_trace.h - */ - -#ifdef CONFIG_RV_MON_TSS -DEFINE_EVENT(event_da_monitor, event_tss, - TP_PROTO(char *state, char *event, char *next_state, bool final_state), - TP_ARGS(state, event, next_state, final_state)); - -DEFINE_EVENT(error_da_monitor, error_tss, - TP_PROTO(char *state, char *event), - TP_ARGS(state, event)); -#endif /* CONFIG_RV_MON_TSS */ diff --git a/kernel/trace/rv/rv_trace.h b/kernel/trace/rv/rv_trace.h index 3af46cd185b3..97b2f7e07f27 100644 --- a/kernel/trace/rv/rv_trace.h +++ b/kernel/trace/rv/rv_trace.h @@ -58,11 +58,10 @@ DECLARE_EVENT_CLASS(error_da_monitor, ); #include -#include #include #include #include -#include +#include // Add new monitors based on CONFIG_DA_MON_EVENTS_IMPLICIT here #endif /* CONFIG_DA_MON_EVENTS_IMPLICIT */ diff --git a/tools/verification/models/sched/sncid.dot b/tools/verification/models/sched/sncid.dot deleted file mode 100644 index 072851721b50..000000000000 --- a/tools/verification/models/sched/sncid.dot +++ /dev/null @@ -1,18 +0,0 @@ -digraph state_automaton { - center = true; - size = "7,11"; - {node [shape = plaintext, style=invis, label=""] "__init_can_sched"}; - {node [shape = ellipse] "can_sched"}; - {node [shape = plaintext] "can_sched"}; - {node [shape = plaintext] "cant_sched"}; - "__init_can_sched" -> "can_sched"; - "can_sched" [label = "can_sched", color = green3]; - "can_sched" -> "can_sched" [ label = "schedule_entry\nschedule_exit" ]; - "can_sched" -> "cant_sched" [ label = "irq_disable" ]; - "cant_sched" [label = "cant_sched"]; - "cant_sched" -> "can_sched" [ label = "irq_enable" ]; - { rank = min ; - "__init_can_sched"; - "can_sched"; - } -} diff --git a/tools/verification/models/sched/sts.dot b/tools/verification/models/sched/sts.dot new file mode 100644 index 000000000000..8f5f38be04d5 --- /dev/null +++ b/tools/verification/models/sched/sts.dot @@ -0,0 +1,38 @@ +digraph state_automaton { + center = true; + size = "7,11"; + {node [shape = plaintext, style=invis, label=""] "__init_can_sched"}; + {node [shape = doublecircle] "can_sched"}; + {node [shape = circle] "can_sched"}; + {node [shape = circle] "cant_sched"}; + {node [shape = circle] "disable_to_switch"}; + {node [shape = circle] "enable_to_exit"}; + {node [shape = circle] "in_irq"}; + {node [shape = circle] "scheduling"}; + {node [shape = circle] "switching"}; + "__init_can_sched" -> "can_sched"; + "can_sched" [label = "can_sched", color = green3]; + "can_sched" -> "cant_sched" [ label = "irq_disable" ]; + "can_sched" -> "scheduling" [ label = "schedule_entry" ]; + "cant_sched" [label = "cant_sched"]; + "cant_sched" -> "can_sched" [ label = "irq_enable" ]; + "cant_sched" -> "cant_sched" [ label = "irq_entry" ]; + "disable_to_switch" [label = "disable_to_switch"]; + "disable_to_switch" -> "enable_to_exit" [ label = "irq_enable" ]; + "disable_to_switch" -> "in_irq" [ label = "irq_entry" ]; + "disable_to_switch" -> "switching" [ label = "sched_switch" ]; + "enable_to_exit" [label = "enable_to_exit"]; + "enable_to_exit" -> "can_sched" [ label = "schedule_exit" ]; + "enable_to_exit" -> "enable_to_exit" [ label = "irq_disable\nirq_entry\nirq_enable" ]; + "in_irq" [label = "in_irq"]; + "in_irq" -> "in_irq" [ label = "irq_entry" ]; + "in_irq" -> "scheduling" [ label = "irq_enable" ]; + "scheduling" [label = "scheduling"]; + "scheduling" -> "disable_to_switch" [ label = "irq_disable" ]; + "switching" [label = "switching"]; + "switching" -> "enable_to_exit" [ label = "irq_enable" ]; + { rank = min ; + "__init_can_sched"; + "can_sched"; + } +} diff --git a/tools/verification/models/sched/tss.dot b/tools/verification/models/sched/tss.dot deleted file mode 100644 index 7dfa1d9121bb..000000000000 --- a/tools/verification/models/sched/tss.dot +++ /dev/null @@ -1,18 +0,0 @@ -digraph state_automaton { - center = true; - size = "7,11"; - {node [shape = plaintext] "sched"}; - {node [shape = plaintext, style=invis, label=""] "__init_thread"}; - {node [shape = ellipse] "thread"}; - {node [shape = plaintext] "thread"}; - "__init_thread" -> "thread"; - "sched" [label = "sched"]; - "sched" -> "sched" [ label = "sched_switch" ]; - "sched" -> "thread" [ label = "schedule_exit" ]; - "thread" [label = "thread", color = green3]; - "thread" -> "sched" [ label = "schedule_entry" ]; - { rank = min ; - "__init_thread"; - "thread"; - } -} -- cgit v1.2.3 From e8440a88e56bb3aa24c384eec6de8bef1184bed2 Mon Sep 17 00:00:00 2001 From: Gabriele Monaco Date: Mon, 28 Jul 2025 15:50:20 +0200 Subject: rv: Add nrp and sssw per-task monitors Add 2 per-task monitors as part of the sched model: * nrp: need-resched preempts Monitor to ensure preemption requires need resched. * sssw: set state sleep and wakeup Monitor to ensure sched_set_state to sleepable leads to sleeping and sleeping tasks require wakeup. Cc: Ingo Molnar Cc: Jonathan Corbet Cc: Masami Hiramatsu Cc: Tomas Glozar Cc: Juri Lelli Cc: Clark Williams Cc: John Kacur Cc: Peter Zijlstra Link: https://lore.kernel.org/20250728135022.255578-9-gmonaco@redhat.com Signed-off-by: Gabriele Monaco Acked-by: Nam Cao Tested-by: Nam Cao Signed-off-by: Steven Rostedt (Google) --- Documentation/trace/rv/monitor_sched.rst | 167 +++++++++++++++++++++++++++++ kernel/trace/rv/Kconfig | 2 + kernel/trace/rv/Makefile | 2 + kernel/trace/rv/monitors/nrp/Kconfig | 16 +++ kernel/trace/rv/monitors/nrp/nrp.c | 138 ++++++++++++++++++++++++ kernel/trace/rv/monitors/nrp/nrp.h | 75 +++++++++++++ kernel/trace/rv/monitors/nrp/nrp_trace.h | 15 +++ kernel/trace/rv/monitors/sched/Kconfig | 1 + kernel/trace/rv/monitors/sssw/Kconfig | 15 +++ kernel/trace/rv/monitors/sssw/sssw.c | 116 ++++++++++++++++++++ kernel/trace/rv/monitors/sssw/sssw.h | 105 ++++++++++++++++++ kernel/trace/rv/monitors/sssw/sssw_trace.h | 15 +++ kernel/trace/rv/rv_trace.h | 2 + tools/verification/models/sched/nrp.dot | 29 +++++ tools/verification/models/sched/sssw.dot | 30 ++++++ 15 files changed, 728 insertions(+) create mode 100644 kernel/trace/rv/monitors/nrp/Kconfig create mode 100644 kernel/trace/rv/monitors/nrp/nrp.c create mode 100644 kernel/trace/rv/monitors/nrp/nrp.h create mode 100644 kernel/trace/rv/monitors/nrp/nrp_trace.h create mode 100644 kernel/trace/rv/monitors/sssw/Kconfig create mode 100644 kernel/trace/rv/monitors/sssw/sssw.c create mode 100644 kernel/trace/rv/monitors/sssw/sssw.h create mode 100644 kernel/trace/rv/monitors/sssw/sssw_trace.h create mode 100644 tools/verification/models/sched/nrp.dot create mode 100644 tools/verification/models/sched/sssw.dot (limited to 'kernel/trace') diff --git a/Documentation/trace/rv/monitor_sched.rst b/Documentation/trace/rv/monitor_sched.rst index 6c4c00216c07..11ef963cb578 100644 --- a/Documentation/trace/rv/monitor_sched.rst +++ b/Documentation/trace/rv/monitor_sched.rst @@ -174,6 +174,173 @@ running one, no real task switch occurs but interrupts are disabled nonetheless: | | irq_entry +---------------+ irq_enable +Monitor nrp +----------- + +The need resched preempts (nrp) monitor ensures preemption requires +``need_resched``. Only kernel preemption is considered, since preemption +while returning to userspace, for this monitor, is indistinguishable from +``sched_switch_yield`` (described in the sssw monitor). +A kernel preemption is whenever ``__schedule`` is called with the preemption +flag set to true (e.g. from preempt_enable or exiting from interrupts). This +type of preemption occurs after the need for ``rescheduling`` has been set. +This is not valid for the *lazy* variant of the flag, which causes only +userspace preemption. +A ``schedule_entry_preempt`` may involve a task switch or not, in the latter +case, a task goes through the scheduler from a preemption context but it is +picked as the next task to run. Since the scheduler runs, this clears the need +to reschedule. The ``any_thread_running`` state does not imply the monitored +task is not running as this monitor does not track the outcome of scheduling. + +In theory, a preemption can only occur after the ``need_resched`` flag is set. In +practice, however, it is possible to see a preemption where the flag is not +set. This can happen in one specific condition:: + + need_resched + preempt_schedule() + preempt_schedule_irq() + __schedule() + !need_resched + __schedule() + +In the situation above, standard preemption starts (e.g. from preempt_enable +when the flag is set), an interrupt occurs before scheduling and, on its exit +path, it schedules, which clears the ``need_resched`` flag. +When the preempted task runs again, the standard preemption started earlier +resumes, although the flag is no longer set. The monitor considers this a +``nested_preemption``, this allows another preemption without re-setting the +flag. This condition relaxes the monitor constraints and may catch false +negatives (i.e. no real ``nested_preemptions``) but makes the monitor more +robust and able to validate other scenarios. +For simplicity, the monitor starts in ``preempt_irq``, although no interrupt +occurred, as the situation above is hard to pinpoint:: + + schedule_entry + irq_entry #===========================================# + +-------------------------- H H + | H H + +-------------------------> H any_thread_running H + H H + +-------------------------> H H + | #===========================================# + | schedule_entry | ^ + | schedule_entry_preempt | sched_need_resched | schedule_entry + | | schedule_entry_preempt + | v | + | +----------------------+ | + | +--- | | | + | sched_need_resched | | rescheduling | -+ + | +--> | | + | +----------------------+ + | | irq_entry + | v + | +----------------------+ + | | | ---+ + | ---> | | | sched_need_resched + | | preempt_irq | | irq_entry + | | | <--+ + | | | <--+ + | +----------------------+ | + | | schedule_entry | sched_need_resched + | | schedule_entry_preempt | + | v | + | +-----------------------+ | + +-------------------------- | nested_preempt | --+ + +-----------------------+ + ^ irq_entry | + +-------------------+ + +Due to how the ``need_resched`` flag on the preemption count works on arm64, +this monitor is unstable on that architecture, as it often records preemption +when the flag is not set, even in presence of the workaround above. +For the time being, the monitor is disabled by default on arm64. + +Monitor sssw +------------ + +The set state sleep and wakeup (sssw) monitor ensures ``set_state`` to +sleepable leads to sleeping and sleeping tasks require wakeup. It includes the +following types of switch: + +* ``switch_suspend``: + a task puts itself to sleep, this can happen only after explicitly setting + the task to ``sleepable``. After a task is suspended, it needs to be woken up + (``waking`` state) before being switched in again. + Setting the task's state to ``sleepable`` can be reverted before switching if it + is woken up or set to ``runnable``. +* ``switch_blocking``: + a special case of a ``switch_suspend`` where the task is waiting on a + sleeping RT lock (``PREEMPT_RT`` only), it is common to see wakeup and set + state events racing with each other and this leads the model to perceive this + type of switch when the task is not set to sleepable. This is a limitation of + the model in SMP system and workarounds may slow down the system. +* ``switch_preempt``: + a task switch as a result of kernel preemption (``schedule_entry_preempt`` in + the nrp model). +* ``switch_yield``: + a task explicitly calls the scheduler or is preempted while returning to + userspace. It can happen after a ``yield`` system call, from the idle task or + if the ``need_resched`` flag is set. By definition, a task cannot yield while + ``sleepable`` as that would be a suspension. A special case of a yield occurs + when a task in ``TASK_INTERRUPTIBLE`` calls the scheduler while a signal is + pending. The task doesn't go through the usual blocking/waking and is set + back to runnable, the resulting switch (if there) looks like a yield to the + ``signal_wakeup`` state and is followed by the signal delivery. From this + state, the monitor expects a signal even if it sees a wakeup event, although + not necessary, to rule out false negatives. + +This monitor doesn't include a running state, ``sleepable`` and ``runnable`` +are only referring to the task's desired state, which could be scheduled out +(e.g. due to preemption). However, it does include the event +``sched_switch_in`` to represent when a task is allowed to become running. This +can be triggered also by preemption, but cannot occur after the task got to +``sleeping`` before a ``wakeup`` occurs:: + + +--------------------------------------------------------------------------+ + | | + | | + | switch_suspend | | + | switch_blocking | | + v v | + +----------+ #==========================# set_state_runnable | + | | H H wakeup | + | | H H switch_in | + | | H H switch_yield | + | sleeping | H H switch_preempt | + | | H H signal_deliver | + | | switch_ H H ------+ | + | | _blocking H runnable H | | + | | <----------- H H <-----+ | + +----------+ H H | + | wakeup H H | + +---------------------> H H | + H H | + +---------> H H | + | #==========================# | + | | ^ | + | | | set_state_runnable | + | | | wakeup | + | set_state_sleepable | +------------------------+ + | v | | + | +--------------------------+ set_state_sleepable + | | | switch_in + | | | switch_preempt + signal_deliver | sleepable | signal_deliver + | | | ------+ + | | | | + | | | <-----+ + | +--------------------------+ + | | ^ + | switch_yield | set_state_sleepable + | v | + | +---------------+ | + +---------- | signal_wakeup | -+ + +---------------+ + ^ | switch_in + | | switch_preempt + | | switch_yield + +-----------+ wakeup + References ---------- diff --git a/kernel/trace/rv/Kconfig b/kernel/trace/rv/Kconfig index b688b24081c8..59d0db898d4a 100644 --- a/kernel/trace/rv/Kconfig +++ b/kernel/trace/rv/Kconfig @@ -55,6 +55,8 @@ source "kernel/trace/rv/monitors/snroc/Kconfig" source "kernel/trace/rv/monitors/scpd/Kconfig" source "kernel/trace/rv/monitors/snep/Kconfig" source "kernel/trace/rv/monitors/sts/Kconfig" +source "kernel/trace/rv/monitors/nrp/Kconfig" +source "kernel/trace/rv/monitors/sssw/Kconfig" # Add new sched monitors here source "kernel/trace/rv/monitors/rtapp/Kconfig" diff --git a/kernel/trace/rv/Makefile b/kernel/trace/rv/Makefile index 1939d3d7621c..2afac88539d3 100644 --- a/kernel/trace/rv/Makefile +++ b/kernel/trace/rv/Makefile @@ -14,6 +14,8 @@ obj-$(CONFIG_RV_MON_RTAPP) += monitors/rtapp/rtapp.o obj-$(CONFIG_RV_MON_PAGEFAULT) += monitors/pagefault/pagefault.o obj-$(CONFIG_RV_MON_SLEEP) += monitors/sleep/sleep.o obj-$(CONFIG_RV_MON_STS) += monitors/sts/sts.o +obj-$(CONFIG_RV_MON_NRP) += monitors/nrp/nrp.o +obj-$(CONFIG_RV_MON_SSSW) += monitors/sssw/sssw.o # Add new monitors here obj-$(CONFIG_RV_REACTORS) += rv_reactors.o obj-$(CONFIG_RV_REACT_PRINTK) += reactor_printk.o diff --git a/kernel/trace/rv/monitors/nrp/Kconfig b/kernel/trace/rv/monitors/nrp/Kconfig new file mode 100644 index 000000000000..f5ec08f65535 --- /dev/null +++ b/kernel/trace/rv/monitors/nrp/Kconfig @@ -0,0 +1,16 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +config RV_MON_NRP + depends on RV + depends on RV_MON_SCHED + default y if !ARM64 + select DA_MON_EVENTS_ID + bool "nrp monitor" + help + Monitor to ensure preemption requires need resched. + This monitor is part of the sched monitors collection. + + This monitor is unstable on arm64, say N unless you are testing it. + + For further information, see: + Documentation/trace/rv/monitor_sched.rst diff --git a/kernel/trace/rv/monitors/nrp/nrp.c b/kernel/trace/rv/monitors/nrp/nrp.c new file mode 100644 index 000000000000..5a83b7171432 --- /dev/null +++ b/kernel/trace/rv/monitors/nrp/nrp.c @@ -0,0 +1,138 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include +#include + +#define MODULE_NAME "nrp" + +#include +#include +#include +#include + +#include "nrp.h" + +static struct rv_monitor rv_nrp; +DECLARE_DA_MON_PER_TASK(nrp, unsigned char); + +#ifdef CONFIG_X86_LOCAL_APIC +#include + +static void handle_vector_irq_entry(void *data, int vector) +{ + da_handle_event_nrp(current, irq_entry_nrp); +} + +static void attach_vector_irq(void) +{ + rv_attach_trace_probe("nrp", local_timer_entry, handle_vector_irq_entry); + if (IS_ENABLED(CONFIG_IRQ_WORK)) + rv_attach_trace_probe("nrp", irq_work_entry, handle_vector_irq_entry); + if (IS_ENABLED(CONFIG_SMP)) { + rv_attach_trace_probe("nrp", reschedule_entry, handle_vector_irq_entry); + rv_attach_trace_probe("nrp", call_function_entry, handle_vector_irq_entry); + rv_attach_trace_probe("nrp", call_function_single_entry, handle_vector_irq_entry); + } +} + +static void detach_vector_irq(void) +{ + rv_detach_trace_probe("nrp", local_timer_entry, handle_vector_irq_entry); + if (IS_ENABLED(CONFIG_IRQ_WORK)) + rv_detach_trace_probe("nrp", irq_work_entry, handle_vector_irq_entry); + if (IS_ENABLED(CONFIG_SMP)) { + rv_detach_trace_probe("nrp", reschedule_entry, handle_vector_irq_entry); + rv_detach_trace_probe("nrp", call_function_entry, handle_vector_irq_entry); + rv_detach_trace_probe("nrp", call_function_single_entry, handle_vector_irq_entry); + } +} + +#else +/* We assume irq_entry tracepoints are sufficient on other architectures */ +static void attach_vector_irq(void) { } +static void detach_vector_irq(void) { } +#endif + +static void handle_irq_entry(void *data, int irq, struct irqaction *action) +{ + da_handle_event_nrp(current, irq_entry_nrp); +} + +static void handle_sched_need_resched(void *data, struct task_struct *tsk, + int cpu, int tif) +{ + /* + * Although need_resched leads to both the rescheduling and preempt_irq + * states, it is safer to start the monitor always in preempt_irq, + * which may not mirror the system state but makes the monitor simpler, + */ + if (tif == TIF_NEED_RESCHED) + da_handle_start_event_nrp(tsk, sched_need_resched_nrp); +} + +static void handle_schedule_entry(void *data, bool preempt) +{ + if (preempt) + da_handle_event_nrp(current, schedule_entry_preempt_nrp); + else + da_handle_event_nrp(current, schedule_entry_nrp); +} + +static int enable_nrp(void) +{ + int retval; + + retval = da_monitor_init_nrp(); + if (retval) + return retval; + + rv_attach_trace_probe("nrp", irq_handler_entry, handle_irq_entry); + rv_attach_trace_probe("nrp", sched_set_need_resched_tp, handle_sched_need_resched); + rv_attach_trace_probe("nrp", sched_entry_tp, handle_schedule_entry); + attach_vector_irq(); + + return 0; +} + +static void disable_nrp(void) +{ + rv_nrp.enabled = 0; + + rv_detach_trace_probe("nrp", irq_handler_entry, handle_irq_entry); + rv_detach_trace_probe("nrp", sched_set_need_resched_tp, handle_sched_need_resched); + rv_detach_trace_probe("nrp", sched_entry_tp, handle_schedule_entry); + detach_vector_irq(); + + da_monitor_destroy_nrp(); +} + +static struct rv_monitor rv_nrp = { + .name = "nrp", + .description = "need resched preempts.", + .enable = enable_nrp, + .disable = disable_nrp, + .reset = da_monitor_reset_all_nrp, + .enabled = 0, +}; + +static int __init register_nrp(void) +{ + return rv_register_monitor(&rv_nrp, &rv_sched); +} + +static void __exit unregister_nrp(void) +{ + rv_unregister_monitor(&rv_nrp); +} + +module_init(register_nrp); +module_exit(unregister_nrp); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Gabriele Monaco "); +MODULE_DESCRIPTION("nrp: need resched preempts."); diff --git a/kernel/trace/rv/monitors/nrp/nrp.h b/kernel/trace/rv/monitors/nrp/nrp.h new file mode 100644 index 000000000000..c9f12207cbf6 --- /dev/null +++ b/kernel/trace/rv/monitors/nrp/nrp.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Automatically generated C representation of nrp automaton + * For further information about this format, see kernel documentation: + * Documentation/trace/rv/deterministic_automata.rst + */ + +enum states_nrp { + preempt_irq_nrp = 0, + any_thread_running_nrp, + nested_preempt_nrp, + rescheduling_nrp, + state_max_nrp +}; + +#define INVALID_STATE state_max_nrp + +enum events_nrp { + irq_entry_nrp = 0, + sched_need_resched_nrp, + schedule_entry_nrp, + schedule_entry_preempt_nrp, + event_max_nrp +}; + +struct automaton_nrp { + char *state_names[state_max_nrp]; + char *event_names[event_max_nrp]; + unsigned char function[state_max_nrp][event_max_nrp]; + unsigned char initial_state; + bool final_states[state_max_nrp]; +}; + +static const struct automaton_nrp automaton_nrp = { + .state_names = { + "preempt_irq", + "any_thread_running", + "nested_preempt", + "rescheduling" + }, + .event_names = { + "irq_entry", + "sched_need_resched", + "schedule_entry", + "schedule_entry_preempt" + }, + .function = { + { + preempt_irq_nrp, + preempt_irq_nrp, + nested_preempt_nrp, + nested_preempt_nrp + }, + { + any_thread_running_nrp, + rescheduling_nrp, + any_thread_running_nrp, + INVALID_STATE + }, + { + nested_preempt_nrp, + preempt_irq_nrp, + any_thread_running_nrp, + any_thread_running_nrp + }, + { + preempt_irq_nrp, + rescheduling_nrp, + any_thread_running_nrp, + any_thread_running_nrp + }, + }, + .initial_state = preempt_irq_nrp, + .final_states = { 0, 1, 0, 0 }, +}; diff --git a/kernel/trace/rv/monitors/nrp/nrp_trace.h b/kernel/trace/rv/monitors/nrp/nrp_trace.h new file mode 100644 index 000000000000..2e13497de3b6 --- /dev/null +++ b/kernel/trace/rv/monitors/nrp/nrp_trace.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Snippet to be included in rv_trace.h + */ + +#ifdef CONFIG_RV_MON_NRP +DEFINE_EVENT(event_da_monitor_id, event_nrp, + TP_PROTO(int id, char *state, char *event, char *next_state, bool final_state), + TP_ARGS(id, state, event, next_state, final_state)); + +DEFINE_EVENT(error_da_monitor_id, error_nrp, + TP_PROTO(int id, char *state, char *event), + TP_ARGS(id, state, event)); +#endif /* CONFIG_RV_MON_NRP */ diff --git a/kernel/trace/rv/monitors/sched/Kconfig b/kernel/trace/rv/monitors/sched/Kconfig index ae3eb410abd7..aa16456da864 100644 --- a/kernel/trace/rv/monitors/sched/Kconfig +++ b/kernel/trace/rv/monitors/sched/Kconfig @@ -2,6 +2,7 @@ # config RV_MON_SCHED depends on RV + depends on RV_PER_TASK_MONITORS >= 3 bool "sched monitor" help Collection of monitors to check the scheduler behaves according to specifications. diff --git a/kernel/trace/rv/monitors/sssw/Kconfig b/kernel/trace/rv/monitors/sssw/Kconfig new file mode 100644 index 000000000000..23b7eeb38bbf --- /dev/null +++ b/kernel/trace/rv/monitors/sssw/Kconfig @@ -0,0 +1,15 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +config RV_MON_SSSW + depends on RV + depends on RV_MON_SCHED + default y + select DA_MON_EVENTS_ID + bool "sssw monitor" + help + Monitor to ensure sched_set_state to sleepable leads to sleeping and + sleeping tasks require wakeup. + This monitor is part of the sched monitors collection. + + For further information, see: + Documentation/trace/rv/monitor_sched.rst diff --git a/kernel/trace/rv/monitors/sssw/sssw.c b/kernel/trace/rv/monitors/sssw/sssw.c new file mode 100644 index 000000000000..84b8d890d9d4 --- /dev/null +++ b/kernel/trace/rv/monitors/sssw/sssw.c @@ -0,0 +1,116 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include +#include + +#define MODULE_NAME "sssw" + +#include +#include +#include +#include + +#include "sssw.h" + +static struct rv_monitor rv_sssw; +DECLARE_DA_MON_PER_TASK(sssw, unsigned char); + +static void handle_sched_set_state(void *data, struct task_struct *tsk, int state) +{ + if (state == TASK_RUNNING) + da_handle_start_event_sssw(tsk, sched_set_state_runnable_sssw); + else + da_handle_event_sssw(tsk, sched_set_state_sleepable_sssw); +} + +static void handle_sched_switch(void *data, bool preempt, + struct task_struct *prev, + struct task_struct *next, + unsigned int prev_state) +{ + if (preempt) + da_handle_event_sssw(prev, sched_switch_preempt_sssw); + else if (prev_state == TASK_RUNNING) + da_handle_event_sssw(prev, sched_switch_yield_sssw); + else if (prev_state == TASK_RTLOCK_WAIT) + /* special case of sleeping task with racy conditions */ + da_handle_event_sssw(prev, sched_switch_blocking_sssw); + else + da_handle_event_sssw(prev, sched_switch_suspend_sssw); + da_handle_event_sssw(next, sched_switch_in_sssw); +} + +static void handle_sched_wakeup(void *data, struct task_struct *p) +{ + /* + * Wakeup can also lead to signal_wakeup although the system is + * actually runnable. The monitor can safely start with this event. + */ + da_handle_start_event_sssw(p, sched_wakeup_sssw); +} + +static void handle_signal_deliver(void *data, int sig, + struct kernel_siginfo *info, + struct k_sigaction *ka) +{ + da_handle_event_sssw(current, signal_deliver_sssw); +} + +static int enable_sssw(void) +{ + int retval; + + retval = da_monitor_init_sssw(); + if (retval) + return retval; + + rv_attach_trace_probe("sssw", sched_set_state_tp, handle_sched_set_state); + rv_attach_trace_probe("sssw", sched_switch, handle_sched_switch); + rv_attach_trace_probe("sssw", sched_wakeup, handle_sched_wakeup); + rv_attach_trace_probe("sssw", signal_deliver, handle_signal_deliver); + + return 0; +} + +static void disable_sssw(void) +{ + rv_sssw.enabled = 0; + + rv_detach_trace_probe("sssw", sched_set_state_tp, handle_sched_set_state); + rv_detach_trace_probe("sssw", sched_switch, handle_sched_switch); + rv_detach_trace_probe("sssw", sched_wakeup, handle_sched_wakeup); + rv_detach_trace_probe("sssw", signal_deliver, handle_signal_deliver); + + da_monitor_destroy_sssw(); +} + +static struct rv_monitor rv_sssw = { + .name = "sssw", + .description = "set state sleep and wakeup.", + .enable = enable_sssw, + .disable = disable_sssw, + .reset = da_monitor_reset_all_sssw, + .enabled = 0, +}; + +static int __init register_sssw(void) +{ + return rv_register_monitor(&rv_sssw, &rv_sched); +} + +static void __exit unregister_sssw(void) +{ + rv_unregister_monitor(&rv_sssw); +} + +module_init(register_sssw); +module_exit(unregister_sssw); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Gabriele Monaco "); +MODULE_DESCRIPTION("sssw: set state sleep and wakeup."); diff --git a/kernel/trace/rv/monitors/sssw/sssw.h b/kernel/trace/rv/monitors/sssw/sssw.h new file mode 100644 index 000000000000..243d54050c94 --- /dev/null +++ b/kernel/trace/rv/monitors/sssw/sssw.h @@ -0,0 +1,105 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Automatically generated C representation of sssw automaton + * For further information about this format, see kernel documentation: + * Documentation/trace/rv/deterministic_automata.rst + */ + +enum states_sssw { + runnable_sssw = 0, + signal_wakeup_sssw, + sleepable_sssw, + sleeping_sssw, + state_max_sssw +}; + +#define INVALID_STATE state_max_sssw + +enum events_sssw { + sched_set_state_runnable_sssw = 0, + sched_set_state_sleepable_sssw, + sched_switch_blocking_sssw, + sched_switch_in_sssw, + sched_switch_preempt_sssw, + sched_switch_suspend_sssw, + sched_switch_yield_sssw, + sched_wakeup_sssw, + signal_deliver_sssw, + event_max_sssw +}; + +struct automaton_sssw { + char *state_names[state_max_sssw]; + char *event_names[event_max_sssw]; + unsigned char function[state_max_sssw][event_max_sssw]; + unsigned char initial_state; + bool final_states[state_max_sssw]; +}; + +static const struct automaton_sssw automaton_sssw = { + .state_names = { + "runnable", + "signal_wakeup", + "sleepable", + "sleeping" + }, + .event_names = { + "sched_set_state_runnable", + "sched_set_state_sleepable", + "sched_switch_blocking", + "sched_switch_in", + "sched_switch_preempt", + "sched_switch_suspend", + "sched_switch_yield", + "sched_wakeup", + "signal_deliver" + }, + .function = { + { + runnable_sssw, + sleepable_sssw, + sleeping_sssw, + runnable_sssw, + runnable_sssw, + INVALID_STATE, + runnable_sssw, + runnable_sssw, + runnable_sssw + }, + { + INVALID_STATE, + sleepable_sssw, + INVALID_STATE, + signal_wakeup_sssw, + signal_wakeup_sssw, + INVALID_STATE, + signal_wakeup_sssw, + signal_wakeup_sssw, + runnable_sssw + }, + { + runnable_sssw, + sleepable_sssw, + sleeping_sssw, + sleepable_sssw, + sleepable_sssw, + sleeping_sssw, + signal_wakeup_sssw, + runnable_sssw, + sleepable_sssw + }, + { + INVALID_STATE, + INVALID_STATE, + INVALID_STATE, + INVALID_STATE, + INVALID_STATE, + INVALID_STATE, + INVALID_STATE, + runnable_sssw, + INVALID_STATE + }, + }, + .initial_state = runnable_sssw, + .final_states = { 1, 0, 0, 0 }, +}; diff --git a/kernel/trace/rv/monitors/sssw/sssw_trace.h b/kernel/trace/rv/monitors/sssw/sssw_trace.h new file mode 100644 index 000000000000..6c03cfc6960b --- /dev/null +++ b/kernel/trace/rv/monitors/sssw/sssw_trace.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Snippet to be included in rv_trace.h + */ + +#ifdef CONFIG_RV_MON_SSSW +DEFINE_EVENT(event_da_monitor_id, event_sssw, + TP_PROTO(int id, char *state, char *event, char *next_state, bool final_state), + TP_ARGS(id, state, event, next_state, final_state)); + +DEFINE_EVENT(error_da_monitor_id, error_sssw, + TP_PROTO(int id, char *state, char *event), + TP_ARGS(id, state, event)); +#endif /* CONFIG_RV_MON_SSSW */ diff --git a/kernel/trace/rv/rv_trace.h b/kernel/trace/rv/rv_trace.h index 97b2f7e07f27..e4e78d23b7b0 100644 --- a/kernel/trace/rv/rv_trace.h +++ b/kernel/trace/rv/rv_trace.h @@ -123,6 +123,8 @@ DECLARE_EVENT_CLASS(error_da_monitor_id, #include #include +#include +#include // Add new monitors based on CONFIG_DA_MON_EVENTS_ID here #endif /* CONFIG_DA_MON_EVENTS_ID */ diff --git a/tools/verification/models/sched/nrp.dot b/tools/verification/models/sched/nrp.dot new file mode 100644 index 000000000000..77bb64669416 --- /dev/null +++ b/tools/verification/models/sched/nrp.dot @@ -0,0 +1,29 @@ +digraph state_automaton { + center = true; + size = "7,11"; + {node [shape = doublecircle] "any_thread_running"}; + {node [shape = circle] "any_thread_running"}; + {node [shape = circle] "nested_preempt"}; + {node [shape = plaintext, style=invis, label=""] "__init_preempt_irq"}; + {node [shape = circle] "preempt_irq"}; + {node [shape = circle] "rescheduling"}; + "__init_preempt_irq" -> "preempt_irq"; + "any_thread_running" [label = "any_thread_running", color = green3]; + "any_thread_running" -> "any_thread_running" [ label = "schedule_entry\nirq_entry" ]; + "any_thread_running" -> "rescheduling" [ label = "sched_need_resched" ]; + "nested_preempt" [label = "nested_preempt"]; + "nested_preempt" -> "any_thread_running" [ label = "schedule_entry_preempt\nschedule_entry" ]; + "nested_preempt" -> "nested_preempt" [ label = "irq_entry" ]; + "nested_preempt" -> "preempt_irq" [ label = "sched_need_resched" ]; + "preempt_irq" [label = "preempt_irq"]; + "preempt_irq" -> "nested_preempt" [ label = "schedule_entry_preempt\nschedule_entry" ]; + "preempt_irq" -> "preempt_irq" [ label = "irq_entry\nsched_need_resched" ]; + "rescheduling" [label = "rescheduling"]; + "rescheduling" -> "any_thread_running" [ label = "schedule_entry_preempt\nschedule_entry" ]; + "rescheduling" -> "preempt_irq" [ label = "irq_entry" ]; + "rescheduling" -> "rescheduling" [ label = "sched_need_resched" ]; + { rank = min ; + "__init_preempt_irq"; + "preempt_irq"; + } +} diff --git a/tools/verification/models/sched/sssw.dot b/tools/verification/models/sched/sssw.dot new file mode 100644 index 000000000000..4994c3e876be --- /dev/null +++ b/tools/verification/models/sched/sssw.dot @@ -0,0 +1,30 @@ +digraph state_automaton { + center = true; + size = "7,11"; + {node [shape = plaintext, style=invis, label=""] "__init_runnable"}; + {node [shape = doublecircle] "runnable"}; + {node [shape = circle] "runnable"}; + {node [shape = circle] "signal_wakeup"}; + {node [shape = circle] "sleepable"}; + {node [shape = circle] "sleeping"}; + "__init_runnable" -> "runnable"; + "runnable" [label = "runnable", color = green3]; + "runnable" -> "runnable" [ label = "sched_set_state_runnable\nsched_wakeup\nsched_switch_in\nsched_switch_yield\nsched_switch_preempt\nsignal_deliver" ]; + "runnable" -> "sleepable" [ label = "sched_set_state_sleepable" ]; + "runnable" -> "sleeping" [ label = "sched_switch_blocking" ]; + "signal_wakeup" [label = "signal_wakeup"]; + "signal_wakeup" -> "runnable" [ label = "signal_deliver" ]; + "signal_wakeup" -> "signal_wakeup" [ label = "sched_switch_in\nsched_switch_preempt\nsched_switch_yield\nsched_wakeup" ]; + "signal_wakeup" -> "sleepable" [ label = "sched_set_state_sleepable" ]; + "sleepable" [label = "sleepable"]; + "sleepable" -> "runnable" [ label = "sched_set_state_runnable\nsched_wakeup" ]; + "sleepable" -> "signal_wakeup" [ label = "sched_switch_yield" ]; + "sleepable" -> "sleepable" [ label = "sched_set_state_sleepable\nsched_switch_in\nsched_switch_preempt\nsignal_deliver" ]; + "sleepable" -> "sleeping" [ label = "sched_switch_suspend\nsched_switch_blocking" ]; + "sleeping" [label = "sleeping"]; + "sleeping" -> "runnable" [ label = "sched_wakeup" ]; + { rank = min ; + "__init_runnable"; + "runnable"; + } +} -- cgit v1.2.3 From 614384533dfe99293a7ff1bce3d4389adadbb759 Mon Sep 17 00:00:00 2001 From: Gabriele Monaco Date: Mon, 28 Jul 2025 15:50:21 +0200 Subject: rv: Add opid per-cpu monitor Add a per-cpu monitor as part of the sched model: * opid: operations with preemption and irq disabled Monitor to ensure wakeup and need_resched occur with irq and preemption disabled or in irq handlers. Cc: Jonathan Corbet Cc: Masami Hiramatsu Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Tomas Glozar Cc: Juri Lelli Cc: Clark Williams Cc: John Kacur Link: https://lore.kernel.org/20250728135022.255578-10-gmonaco@redhat.com Signed-off-by: Gabriele Monaco Acked-by: Nam Cao Tested-by: Nam Cao Signed-off-by: Steven Rostedt (Google) --- Documentation/trace/rv/monitor_sched.rst | 55 ++++++++++ kernel/trace/rv/Kconfig | 1 + kernel/trace/rv/Makefile | 1 + kernel/trace/rv/monitors/opid/Kconfig | 19 ++++ kernel/trace/rv/monitors/opid/opid.c | 168 +++++++++++++++++++++++++++++ kernel/trace/rv/monitors/opid/opid.h | 104 ++++++++++++++++++ kernel/trace/rv/monitors/opid/opid_trace.h | 15 +++ kernel/trace/rv/rv_trace.h | 1 + tools/verification/models/sched/opid.dot | 35 ++++++ 9 files changed, 399 insertions(+) create mode 100644 kernel/trace/rv/monitors/opid/Kconfig create mode 100644 kernel/trace/rv/monitors/opid/opid.c create mode 100644 kernel/trace/rv/monitors/opid/opid.h create mode 100644 kernel/trace/rv/monitors/opid/opid_trace.h create mode 100644 tools/verification/models/sched/opid.dot (limited to 'kernel/trace') diff --git a/Documentation/trace/rv/monitor_sched.rst b/Documentation/trace/rv/monitor_sched.rst index 11ef963cb578..3f8381ad9ec7 100644 --- a/Documentation/trace/rv/monitor_sched.rst +++ b/Documentation/trace/rv/monitor_sched.rst @@ -341,6 +341,61 @@ can be triggered also by preemption, but cannot occur after the task got to | | switch_yield +-----------+ wakeup +Monitor opid +------------ + +The operations with preemption and irq disabled (opid) monitor ensures +operations like ``wakeup`` and ``need_resched`` occur with interrupts and +preemption disabled or during interrupt context, in such case preemption may +not be disabled explicitly. +``need_resched`` can be set by some RCU internals functions, in which case it +doesn't match a task wakeup and might occur with only interrupts disabled:: + + | sched_need_resched + | sched_waking + | irq_entry + | +--------------------+ + v v | + +------------------------------------------------------+ + +----------- | disabled | <+ + | +------------------------------------------------------+ | + | | ^ | + | | preempt_disable sched_need_resched | + | preempt_enable | +--------------------+ | + | v | v | | + | +------------------------------------------------------+ | + | | irq_disabled | | + | +------------------------------------------------------+ | + | | | ^ | + | irq_entry irq_entry | | | + | sched_need_resched v | irq_disable | + | sched_waking +--------------+ | | | + | +----- | | irq_enable | | + | | | in_irq | | | | + | +----> | | | | | + | +--------------+ | | irq_disable + | | | | | + | irq_enable | irq_enable | | | + | v v | | + | #======================================================# | + | H enabled H | + | #======================================================# | + | | ^ ^ preempt_enable | | + | preempt_disable preempt_enable +--------------------+ | + | v | | + | +------------------+ | | + +----------> | preempt_disabled | -+ | + +------------------+ | + | | + +-------------------------------------------------------+ + +This monitor is designed to work on ``PREEMPT_RT`` kernels, the special case of +events occurring in interrupt context is a shortcut to identify valid scenarios +where the preemption tracepoints might not be visible, during interrupts +preemption is always disabled. On non- ``PREEMPT_RT`` kernels, the interrupts +might invoke a softirq to set ``need_resched`` and wake up a task. This is +another special case that is currently not supported by the monitor. + References ---------- diff --git a/kernel/trace/rv/Kconfig b/kernel/trace/rv/Kconfig index 59d0db898d4a..5b4be87ba59d 100644 --- a/kernel/trace/rv/Kconfig +++ b/kernel/trace/rv/Kconfig @@ -57,6 +57,7 @@ source "kernel/trace/rv/monitors/snep/Kconfig" source "kernel/trace/rv/monitors/sts/Kconfig" source "kernel/trace/rv/monitors/nrp/Kconfig" source "kernel/trace/rv/monitors/sssw/Kconfig" +source "kernel/trace/rv/monitors/opid/Kconfig" # Add new sched monitors here source "kernel/trace/rv/monitors/rtapp/Kconfig" diff --git a/kernel/trace/rv/Makefile b/kernel/trace/rv/Makefile index 2afac88539d3..750e4ad6fa0f 100644 --- a/kernel/trace/rv/Makefile +++ b/kernel/trace/rv/Makefile @@ -16,6 +16,7 @@ obj-$(CONFIG_RV_MON_SLEEP) += monitors/sleep/sleep.o obj-$(CONFIG_RV_MON_STS) += monitors/sts/sts.o obj-$(CONFIG_RV_MON_NRP) += monitors/nrp/nrp.o obj-$(CONFIG_RV_MON_SSSW) += monitors/sssw/sssw.o +obj-$(CONFIG_RV_MON_OPID) += monitors/opid/opid.o # Add new monitors here obj-$(CONFIG_RV_REACTORS) += rv_reactors.o obj-$(CONFIG_RV_REACT_PRINTK) += reactor_printk.o diff --git a/kernel/trace/rv/monitors/opid/Kconfig b/kernel/trace/rv/monitors/opid/Kconfig new file mode 100644 index 000000000000..561d32da572b --- /dev/null +++ b/kernel/trace/rv/monitors/opid/Kconfig @@ -0,0 +1,19 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +config RV_MON_OPID + depends on RV + depends on TRACE_IRQFLAGS + depends on TRACE_PREEMPT_TOGGLE + depends on RV_MON_SCHED + default y if PREEMPT_RT + select DA_MON_EVENTS_IMPLICIT + bool "opid monitor" + help + Monitor to ensure operations like wakeup and need resched occur with + interrupts and preemption disabled or during IRQs, where preemption + may not be disabled explicitly. + + This monitor is unstable on !PREEMPT_RT, say N unless you are testing it. + + For further information, see: + Documentation/trace/rv/monitor_sched.rst diff --git a/kernel/trace/rv/monitors/opid/opid.c b/kernel/trace/rv/monitors/opid/opid.c new file mode 100644 index 000000000000..50d64e7fb8c4 --- /dev/null +++ b/kernel/trace/rv/monitors/opid/opid.c @@ -0,0 +1,168 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include +#include + +#define MODULE_NAME "opid" + +#include +#include +#include +#include +#include + +#include "opid.h" + +static struct rv_monitor rv_opid; +DECLARE_DA_MON_PER_CPU(opid, unsigned char); + +#ifdef CONFIG_X86_LOCAL_APIC +#include + +static void handle_vector_irq_entry(void *data, int vector) +{ + da_handle_event_opid(irq_entry_opid); +} + +static void attach_vector_irq(void) +{ + rv_attach_trace_probe("opid", local_timer_entry, handle_vector_irq_entry); + if (IS_ENABLED(CONFIG_IRQ_WORK)) + rv_attach_trace_probe("opid", irq_work_entry, handle_vector_irq_entry); + if (IS_ENABLED(CONFIG_SMP)) { + rv_attach_trace_probe("opid", reschedule_entry, handle_vector_irq_entry); + rv_attach_trace_probe("opid", call_function_entry, handle_vector_irq_entry); + rv_attach_trace_probe("opid", call_function_single_entry, handle_vector_irq_entry); + } +} + +static void detach_vector_irq(void) +{ + rv_detach_trace_probe("opid", local_timer_entry, handle_vector_irq_entry); + if (IS_ENABLED(CONFIG_IRQ_WORK)) + rv_detach_trace_probe("opid", irq_work_entry, handle_vector_irq_entry); + if (IS_ENABLED(CONFIG_SMP)) { + rv_detach_trace_probe("opid", reschedule_entry, handle_vector_irq_entry); + rv_detach_trace_probe("opid", call_function_entry, handle_vector_irq_entry); + rv_detach_trace_probe("opid", call_function_single_entry, handle_vector_irq_entry); + } +} + +#else +/* We assume irq_entry tracepoints are sufficient on other architectures */ +static void attach_vector_irq(void) { } +static void detach_vector_irq(void) { } +#endif + +static void handle_irq_disable(void *data, unsigned long ip, unsigned long parent_ip) +{ + da_handle_event_opid(irq_disable_opid); +} + +static void handle_irq_enable(void *data, unsigned long ip, unsigned long parent_ip) +{ + da_handle_event_opid(irq_enable_opid); +} + +static void handle_irq_entry(void *data, int irq, struct irqaction *action) +{ + da_handle_event_opid(irq_entry_opid); +} + +static void handle_preempt_disable(void *data, unsigned long ip, unsigned long parent_ip) +{ + da_handle_event_opid(preempt_disable_opid); +} + +static void handle_preempt_enable(void *data, unsigned long ip, unsigned long parent_ip) +{ + da_handle_event_opid(preempt_enable_opid); +} + +static void handle_sched_need_resched(void *data, struct task_struct *tsk, int cpu, int tif) +{ + /* The monitor's intitial state is not in_irq */ + if (this_cpu_read(hardirq_context)) + da_handle_event_opid(sched_need_resched_opid); + else + da_handle_start_event_opid(sched_need_resched_opid); +} + +static void handle_sched_waking(void *data, struct task_struct *p) +{ + /* The monitor's intitial state is not in_irq */ + if (this_cpu_read(hardirq_context)) + da_handle_event_opid(sched_waking_opid); + else + da_handle_start_event_opid(sched_waking_opid); +} + +static int enable_opid(void) +{ + int retval; + + retval = da_monitor_init_opid(); + if (retval) + return retval; + + rv_attach_trace_probe("opid", irq_disable, handle_irq_disable); + rv_attach_trace_probe("opid", irq_enable, handle_irq_enable); + rv_attach_trace_probe("opid", irq_handler_entry, handle_irq_entry); + rv_attach_trace_probe("opid", preempt_disable, handle_preempt_disable); + rv_attach_trace_probe("opid", preempt_enable, handle_preempt_enable); + rv_attach_trace_probe("opid", sched_set_need_resched_tp, handle_sched_need_resched); + rv_attach_trace_probe("opid", sched_waking, handle_sched_waking); + attach_vector_irq(); + + return 0; +} + +static void disable_opid(void) +{ + rv_opid.enabled = 0; + + rv_detach_trace_probe("opid", irq_disable, handle_irq_disable); + rv_detach_trace_probe("opid", irq_enable, handle_irq_enable); + rv_detach_trace_probe("opid", irq_handler_entry, handle_irq_entry); + rv_detach_trace_probe("opid", preempt_disable, handle_preempt_disable); + rv_detach_trace_probe("opid", preempt_enable, handle_preempt_enable); + rv_detach_trace_probe("opid", sched_set_need_resched_tp, handle_sched_need_resched); + rv_detach_trace_probe("opid", sched_waking, handle_sched_waking); + detach_vector_irq(); + + da_monitor_destroy_opid(); +} + +/* + * This is the monitor register section. + */ +static struct rv_monitor rv_opid = { + .name = "opid", + .description = "operations with preemption and irq disabled.", + .enable = enable_opid, + .disable = disable_opid, + .reset = da_monitor_reset_all_opid, + .enabled = 0, +}; + +static int __init register_opid(void) +{ + return rv_register_monitor(&rv_opid, &rv_sched); +} + +static void __exit unregister_opid(void) +{ + rv_unregister_monitor(&rv_opid); +} + +module_init(register_opid); +module_exit(unregister_opid); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Gabriele Monaco "); +MODULE_DESCRIPTION("opid: operations with preemption and irq disabled."); diff --git a/kernel/trace/rv/monitors/opid/opid.h b/kernel/trace/rv/monitors/opid/opid.h new file mode 100644 index 000000000000..b4b8c2ff7f64 --- /dev/null +++ b/kernel/trace/rv/monitors/opid/opid.h @@ -0,0 +1,104 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Automatically generated C representation of opid automaton + * For further information about this format, see kernel documentation: + * Documentation/trace/rv/deterministic_automata.rst + */ + +enum states_opid { + disabled_opid = 0, + enabled_opid, + in_irq_opid, + irq_disabled_opid, + preempt_disabled_opid, + state_max_opid +}; + +#define INVALID_STATE state_max_opid + +enum events_opid { + irq_disable_opid = 0, + irq_enable_opid, + irq_entry_opid, + preempt_disable_opid, + preempt_enable_opid, + sched_need_resched_opid, + sched_waking_opid, + event_max_opid +}; + +struct automaton_opid { + char *state_names[state_max_opid]; + char *event_names[event_max_opid]; + unsigned char function[state_max_opid][event_max_opid]; + unsigned char initial_state; + bool final_states[state_max_opid]; +}; + +static const struct automaton_opid automaton_opid = { + .state_names = { + "disabled", + "enabled", + "in_irq", + "irq_disabled", + "preempt_disabled" + }, + .event_names = { + "irq_disable", + "irq_enable", + "irq_entry", + "preempt_disable", + "preempt_enable", + "sched_need_resched", + "sched_waking" + }, + .function = { + { + INVALID_STATE, + preempt_disabled_opid, + disabled_opid, + INVALID_STATE, + irq_disabled_opid, + disabled_opid, + disabled_opid + }, + { + irq_disabled_opid, + INVALID_STATE, + INVALID_STATE, + preempt_disabled_opid, + enabled_opid, + INVALID_STATE, + INVALID_STATE + }, + { + INVALID_STATE, + enabled_opid, + in_irq_opid, + INVALID_STATE, + INVALID_STATE, + in_irq_opid, + in_irq_opid + }, + { + INVALID_STATE, + enabled_opid, + in_irq_opid, + disabled_opid, + INVALID_STATE, + irq_disabled_opid, + INVALID_STATE + }, + { + disabled_opid, + INVALID_STATE, + INVALID_STATE, + INVALID_STATE, + enabled_opid, + INVALID_STATE, + INVALID_STATE + }, + }, + .initial_state = disabled_opid, + .final_states = { 0, 1, 0, 0, 0 }, +}; diff --git a/kernel/trace/rv/monitors/opid/opid_trace.h b/kernel/trace/rv/monitors/opid/opid_trace.h new file mode 100644 index 000000000000..3df6ff955c30 --- /dev/null +++ b/kernel/trace/rv/monitors/opid/opid_trace.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Snippet to be included in rv_trace.h + */ + +#ifdef CONFIG_RV_MON_OPID +DEFINE_EVENT(event_da_monitor, event_opid, + TP_PROTO(char *state, char *event, char *next_state, bool final_state), + TP_ARGS(state, event, next_state, final_state)); + +DEFINE_EVENT(error_da_monitor, error_opid, + TP_PROTO(char *state, char *event), + TP_ARGS(state, event)); +#endif /* CONFIG_RV_MON_OPID */ diff --git a/kernel/trace/rv/rv_trace.h b/kernel/trace/rv/rv_trace.h index e4e78d23b7b0..4a6faddac614 100644 --- a/kernel/trace/rv/rv_trace.h +++ b/kernel/trace/rv/rv_trace.h @@ -62,6 +62,7 @@ DECLARE_EVENT_CLASS(error_da_monitor, #include #include #include +#include // Add new monitors based on CONFIG_DA_MON_EVENTS_IMPLICIT here #endif /* CONFIG_DA_MON_EVENTS_IMPLICIT */ diff --git a/tools/verification/models/sched/opid.dot b/tools/verification/models/sched/opid.dot new file mode 100644 index 000000000000..840052f6952b --- /dev/null +++ b/tools/verification/models/sched/opid.dot @@ -0,0 +1,35 @@ +digraph state_automaton { + center = true; + size = "7,11"; + {node [shape = plaintext, style=invis, label=""] "__init_disabled"}; + {node [shape = circle] "disabled"}; + {node [shape = doublecircle] "enabled"}; + {node [shape = circle] "enabled"}; + {node [shape = circle] "in_irq"}; + {node [shape = circle] "irq_disabled"}; + {node [shape = circle] "preempt_disabled"}; + "__init_disabled" -> "disabled"; + "disabled" [label = "disabled"]; + "disabled" -> "disabled" [ label = "sched_need_resched\nsched_waking\nirq_entry" ]; + "disabled" -> "irq_disabled" [ label = "preempt_enable" ]; + "disabled" -> "preempt_disabled" [ label = "irq_enable" ]; + "enabled" [label = "enabled", color = green3]; + "enabled" -> "enabled" [ label = "preempt_enable" ]; + "enabled" -> "irq_disabled" [ label = "irq_disable" ]; + "enabled" -> "preempt_disabled" [ label = "preempt_disable" ]; + "in_irq" [label = "in_irq"]; + "in_irq" -> "enabled" [ label = "irq_enable" ]; + "in_irq" -> "in_irq" [ label = "sched_need_resched\nsched_waking\nirq_entry" ]; + "irq_disabled" [label = "irq_disabled"]; + "irq_disabled" -> "disabled" [ label = "preempt_disable" ]; + "irq_disabled" -> "enabled" [ label = "irq_enable" ]; + "irq_disabled" -> "in_irq" [ label = "irq_entry" ]; + "irq_disabled" -> "irq_disabled" [ label = "sched_need_resched" ]; + "preempt_disabled" [label = "preempt_disabled"]; + "preempt_disabled" -> "disabled" [ label = "irq_disable" ]; + "preempt_disabled" -> "enabled" [ label = "preempt_enable" ]; + { rank = min ; + "__init_disabled"; + "disabled"; + } +} -- cgit v1.2.3