+++ /dev/null
-From b858895d47341993c9549ba7563f61c811af77f1 Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Thu, 20 Jan 2022 16:25:19 +0000
-Subject: sched/tracing: Don't re-read p->state when emitting sched_switch
- event
-
-From: Valentin Schneider <valentin.schneider@arm.com>
-
-[ Upstream commit fa2c3254d7cfff5f7a916ab928a562d1165f17bb ]
-
-As of commit
-
- c6e7bd7afaeb ("sched/core: Optimize ttwu() spinning on p->on_cpu")
-
-the following sequence becomes possible:
-
- p->__state = TASK_INTERRUPTIBLE;
- __schedule()
- deactivate_task(p);
- ttwu()
- READ !p->on_rq
- p->__state=TASK_WAKING
- trace_sched_switch()
- __trace_sched_switch_state()
- task_state_index()
- return 0;
-
-TASK_WAKING isn't in TASK_REPORT, so the task appears as TASK_RUNNING in
-the trace event.
-
-Prevent this by pushing the value read from __schedule() down the trace
-event.
-
-Reported-by: Abhijeet Dharmapurikar <adharmap@quicinc.com>
-Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
-Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
-Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
-Link: https://lore.kernel.org/r/20220120162520.570782-2-valentin.schneider@arm.com
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- include/linux/sched.h | 11 ++++++++---
- include/trace/events/sched.h | 11 +++++++----
- kernel/sched/core.c | 4 ++--
- kernel/trace/fgraph.c | 4 +++-
- kernel/trace/ftrace.c | 4 +++-
- kernel/trace/trace_events.c | 8 ++++++--
- kernel/trace/trace_osnoise.c | 4 +++-
- kernel/trace/trace_sched_switch.c | 1 +
- kernel/trace/trace_sched_wakeup.c | 1 +
- 9 files changed, 34 insertions(+), 14 deletions(-)
-
-diff --git a/include/linux/sched.h b/include/linux/sched.h
-index 76e869550646..8fcf76fed984 100644
---- a/include/linux/sched.h
-+++ b/include/linux/sched.h
-@@ -1616,10 +1616,10 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk)
- #define TASK_REPORT_IDLE (TASK_REPORT + 1)
- #define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1)
-
--static inline unsigned int task_state_index(struct task_struct *tsk)
-+static inline unsigned int __task_state_index(unsigned int tsk_state,
-+ unsigned int tsk_exit_state)
- {
-- unsigned int tsk_state = READ_ONCE(tsk->__state);
-- unsigned int state = (tsk_state | tsk->exit_state) & TASK_REPORT;
-+ unsigned int state = (tsk_state | tsk_exit_state) & TASK_REPORT;
-
- BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX);
-
-@@ -1629,6 +1629,11 @@ static inline unsigned int task_state_index(struct task_struct *tsk)
- return fls(state);
- }
-
-+static inline unsigned int task_state_index(struct task_struct *tsk)
-+{
-+ return __task_state_index(READ_ONCE(tsk->__state), tsk->exit_state);
-+}
-+
- static inline char task_index_to_char(unsigned int state)
- {
- static const char state_char[] = "RSDTtXZPI";
-diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
-index 94640482cfe7..65e786756321 100644
---- a/include/trace/events/sched.h
-+++ b/include/trace/events/sched.h
-@@ -187,7 +187,9 @@ DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new,
- TP_ARGS(p));
-
- #ifdef CREATE_TRACE_POINTS
--static inline long __trace_sched_switch_state(bool preempt, struct task_struct *p)
-+static inline long __trace_sched_switch_state(bool preempt,
-+ unsigned int prev_state,
-+ struct task_struct *p)
- {
- unsigned int state;
-
-@@ -208,7 +210,7 @@ static inline long __trace_sched_switch_state(bool preempt, struct task_struct *
- * it for left shift operation to get the correct task->state
- * mapping.
- */
-- state = task_state_index(p);
-+ state = __task_state_index(prev_state, p->exit_state);
-
- return state ? (1 << (state - 1)) : state;
- }
-@@ -220,10 +222,11 @@ static inline long __trace_sched_switch_state(bool preempt, struct task_struct *
- TRACE_EVENT(sched_switch,
-
- TP_PROTO(bool preempt,
-+ unsigned int prev_state,
- struct task_struct *prev,
- struct task_struct *next),
-
-- TP_ARGS(preempt, prev, next),
-+ TP_ARGS(preempt, prev_state, prev, next),
-
- TP_STRUCT__entry(
- __array( char, prev_comm, TASK_COMM_LEN )
-@@ -239,7 +242,7 @@ TRACE_EVENT(sched_switch,
- memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN);
- __entry->prev_pid = prev->pid;
- __entry->prev_prio = prev->prio;
-- __entry->prev_state = __trace_sched_switch_state(preempt, prev);
-+ __entry->prev_state = __trace_sched_switch_state(preempt, prev_state, prev);
- memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
- __entry->next_pid = next->pid;
- __entry->next_prio = next->prio;
-diff --git a/kernel/sched/core.c b/kernel/sched/core.c
-index c51bd3692316..2fd338bcbdcc 100644
---- a/kernel/sched/core.c
-+++ b/kernel/sched/core.c
-@@ -4787,7 +4787,7 @@ static struct rq *finish_task_switch(struct task_struct *prev)
- {
- struct rq *rq = this_rq();
- struct mm_struct *mm = rq->prev_mm;
-- long prev_state;
-+ unsigned int prev_state;
-
- /*
- * The previous task will have left us with a preempt_count of 2
-@@ -6295,7 +6295,7 @@ static void __sched notrace __schedule(unsigned int sched_mode)
- migrate_disable_switch(rq, prev);
- psi_sched_switch(prev, next, !task_on_rq_queued(prev));
-
-- trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next);
-+ trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev_state, prev, next);
-
- /* Also unlocks the rq: */
- rq = context_switch(rq, prev, next, &rf);
-diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
-index b8a0d1d564fb..bb383ac91198 100644
---- a/kernel/trace/fgraph.c
-+++ b/kernel/trace/fgraph.c
-@@ -413,7 +413,9 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
-
- static void
- ftrace_graph_probe_sched_switch(void *ignore, bool preempt,
-- struct task_struct *prev, struct task_struct *next)
-+ unsigned int prev_state,
-+ struct task_struct *prev,
-+ struct task_struct *next)
- {
- unsigned long long timestamp;
- int index;
-diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
-index c672040142e9..136520a5b7c0 100644
---- a/kernel/trace/ftrace.c
-+++ b/kernel/trace/ftrace.c
-@@ -7093,7 +7093,9 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops)
-
- static void
- ftrace_filter_pid_sched_switch_probe(void *data, bool preempt,
-- struct task_struct *prev, struct task_struct *next)
-+ unsigned int prev_state,
-+ struct task_struct *prev,
-+ struct task_struct *next)
- {
- struct trace_array *tr = data;
- struct trace_pid_list *pid_list;
-diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
-index 44d031ffe511..dd17171829d6 100644
---- a/kernel/trace/trace_events.c
-+++ b/kernel/trace/trace_events.c
-@@ -759,7 +759,9 @@ void trace_event_follow_fork(struct trace_array *tr, bool enable)
-
- static void
- event_filter_pid_sched_switch_probe_pre(void *data, bool preempt,
-- struct task_struct *prev, struct task_struct *next)
-+ unsigned int prev_state,
-+ struct task_struct *prev,
-+ struct task_struct *next)
- {
- struct trace_array *tr = data;
- struct trace_pid_list *no_pid_list;
-@@ -783,7 +785,9 @@ event_filter_pid_sched_switch_probe_pre(void *data, bool preempt,
-
- static void
- event_filter_pid_sched_switch_probe_post(void *data, bool preempt,
-- struct task_struct *prev, struct task_struct *next)
-+ unsigned int prev_state,
-+ struct task_struct *prev,
-+ struct task_struct *next)
- {
- struct trace_array *tr = data;
- struct trace_pid_list *no_pid_list;
-diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
-index 93de784ee681..c3bd968e6147 100644
---- a/kernel/trace/trace_osnoise.c
-+++ b/kernel/trace/trace_osnoise.c
-@@ -1000,7 +1000,9 @@ thread_exit(struct osnoise_variables *osn_var, struct task_struct *t)
- * used to record the beginning and to report the end of a thread noise window.
- */
- static void
--trace_sched_switch_callback(void *data, bool preempt, struct task_struct *p,
-+trace_sched_switch_callback(void *data, bool preempt,
-+ unsigned int prev_state,
-+ struct task_struct *p,
- struct task_struct *n)
- {
- struct osnoise_variables *osn_var = this_cpu_osn_var();
-diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
-index e304196d7c28..993b0ed10d8c 100644
---- a/kernel/trace/trace_sched_switch.c
-+++ b/kernel/trace/trace_sched_switch.c
-@@ -22,6 +22,7 @@ static DEFINE_MUTEX(sched_register_mutex);
-
- static void
- probe_sched_switch(void *ignore, bool preempt,
-+ unsigned int prev_state,
- struct task_struct *prev, struct task_struct *next)
- {
- int flags;
-diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
-index 2402de520eca..46429f9a96fa 100644
---- a/kernel/trace/trace_sched_wakeup.c
-+++ b/kernel/trace/trace_sched_wakeup.c
-@@ -426,6 +426,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
-
- static void notrace
- probe_wakeup_sched_switch(void *ignore, bool preempt,
-+ unsigned int prev_state,
- struct task_struct *prev, struct task_struct *next)
- {
- struct trace_array_cpu *data;
---
-2.34.1
-
locking-lockdep-iterate-lock_classes-directly-when-r.patch
ext4-correct-cluster-len-and-clusters-changed-accoun.patch
ext4-fix-ext4_mb_mark_bb-with-flex_bg-with-fast_comm.patch
-sched-tracing-don-t-re-read-p-state-when-emitting-sc.patch
sched-tracing-report-task_rtlock_wait-tasks-as-task_.patch
ext4-don-t-bug-if-someone-dirty-pages-without-asking.patch
f2fs-fix-to-do-sanity-check-on-curseg-alloc_type.patch
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
- kernel/trace/trace_events.c | 28 ++++++++++++++++++++++++++++
+ kernel/trace/trace_events.c | 28 ++++++++++++++++++++++++++++
1 file changed, 28 insertions(+)
-diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
-index dd17171829d6..b35a66a8e7ce 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
-@@ -2637,6 +2637,33 @@ static void update_event_printk(struct trace_event_call *call,
+@@ -2633,6 +2633,33 @@ static void update_event_printk(struct t
}
}
void trace_event_eval_update(struct trace_eval_map **map, int len)
{
struct trace_event_call *call, *p;
-@@ -2672,6 +2699,7 @@ void trace_event_eval_update(struct trace_eval_map **map, int len)
+@@ -2668,6 +2695,7 @@ void trace_event_eval_update(struct trac
first = false;
}
update_event_printk(call, map[i]);
}
}
}
---
-2.34.1
-
#define GFP_TRACE (GFP_KERNEL | __GFP_ZERO)
static struct kmem_cache *field_cachep;
-@@ -2637,14 +2645,40 @@ static void update_event_printk(struct t
+@@ -2633,14 +2641,40 @@ static void update_event_printk(struct t
}
}
head = trace_get_fields(call);
list_for_each_entry(field, head, link) {
ptr = strchr(field->type, '[');
-@@ -2658,9 +2692,26 @@ static void update_event_fields(struct t
+@@ -2654,9 +2688,26 @@ static void update_event_fields(struct t
if (strncmp(map->eval_string, ptr, len) != 0)
continue;
}
}
-@@ -2883,6 +2934,7 @@ static void trace_module_add_events(stru
+@@ -2879,6 +2930,7 @@ static void trace_module_add_events(stru
static void trace_module_remove_events(struct module *mod)
{
struct trace_event_call *call, *p;
down_write(&trace_event_sem);
list_for_each_entry_safe(call, p, &ftrace_events, list) {
-@@ -2891,6 +2943,14 @@ static void trace_module_remove_events(s
+@@ -2887,6 +2939,14 @@ static void trace_module_remove_events(s
if (call->module == mod)
__trace_remove_event_call(call);
}
+++ /dev/null
-From a1dc99beee5717d3ef92d4c21ddf8a6240e9ea6c Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Thu, 20 Jan 2022 16:25:19 +0000
-Subject: sched/tracing: Don't re-read p->state when emitting sched_switch
- event
-
-From: Valentin Schneider <valentin.schneider@arm.com>
-
-[ Upstream commit fa2c3254d7cfff5f7a916ab928a562d1165f17bb ]
-
-As of commit
-
- c6e7bd7afaeb ("sched/core: Optimize ttwu() spinning on p->on_cpu")
-
-the following sequence becomes possible:
-
- p->__state = TASK_INTERRUPTIBLE;
- __schedule()
- deactivate_task(p);
- ttwu()
- READ !p->on_rq
- p->__state=TASK_WAKING
- trace_sched_switch()
- __trace_sched_switch_state()
- task_state_index()
- return 0;
-
-TASK_WAKING isn't in TASK_REPORT, so the task appears as TASK_RUNNING in
-the trace event.
-
-Prevent this by pushing the value read from __schedule() down the trace
-event.
-
-Reported-by: Abhijeet Dharmapurikar <adharmap@quicinc.com>
-Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
-Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
-Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
-Link: https://lore.kernel.org/r/20220120162520.570782-2-valentin.schneider@arm.com
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- include/linux/sched.h | 11 ++++++++---
- include/trace/events/sched.h | 11 +++++++----
- kernel/sched/core.c | 4 ++--
- kernel/trace/fgraph.c | 4 +++-
- kernel/trace/ftrace.c | 4 +++-
- kernel/trace/trace_events.c | 8 ++++++--
- kernel/trace/trace_osnoise.c | 4 +++-
- kernel/trace/trace_sched_switch.c | 1 +
- kernel/trace/trace_sched_wakeup.c | 1 +
- 9 files changed, 34 insertions(+), 14 deletions(-)
-
-diff --git a/include/linux/sched.h b/include/linux/sched.h
-index ee5ed8821963..084de9b70a77 100644
---- a/include/linux/sched.h
-+++ b/include/linux/sched.h
-@@ -1612,10 +1612,10 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk)
- #define TASK_REPORT_IDLE (TASK_REPORT + 1)
- #define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1)
-
--static inline unsigned int task_state_index(struct task_struct *tsk)
-+static inline unsigned int __task_state_index(unsigned int tsk_state,
-+ unsigned int tsk_exit_state)
- {
-- unsigned int tsk_state = READ_ONCE(tsk->__state);
-- unsigned int state = (tsk_state | tsk->exit_state) & TASK_REPORT;
-+ unsigned int state = (tsk_state | tsk_exit_state) & TASK_REPORT;
-
- BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX);
-
-@@ -1625,6 +1625,11 @@ static inline unsigned int task_state_index(struct task_struct *tsk)
- return fls(state);
- }
-
-+static inline unsigned int task_state_index(struct task_struct *tsk)
-+{
-+ return __task_state_index(READ_ONCE(tsk->__state), tsk->exit_state);
-+}
-+
- static inline char task_index_to_char(unsigned int state)
- {
- static const char state_char[] = "RSDTtXZPI";
-diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
-index 94640482cfe7..65e786756321 100644
---- a/include/trace/events/sched.h
-+++ b/include/trace/events/sched.h
-@@ -187,7 +187,9 @@ DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new,
- TP_ARGS(p));
-
- #ifdef CREATE_TRACE_POINTS
--static inline long __trace_sched_switch_state(bool preempt, struct task_struct *p)
-+static inline long __trace_sched_switch_state(bool preempt,
-+ unsigned int prev_state,
-+ struct task_struct *p)
- {
- unsigned int state;
-
-@@ -208,7 +210,7 @@ static inline long __trace_sched_switch_state(bool preempt, struct task_struct *
- * it for left shift operation to get the correct task->state
- * mapping.
- */
-- state = task_state_index(p);
-+ state = __task_state_index(prev_state, p->exit_state);
-
- return state ? (1 << (state - 1)) : state;
- }
-@@ -220,10 +222,11 @@ static inline long __trace_sched_switch_state(bool preempt, struct task_struct *
- TRACE_EVENT(sched_switch,
-
- TP_PROTO(bool preempt,
-+ unsigned int prev_state,
- struct task_struct *prev,
- struct task_struct *next),
-
-- TP_ARGS(preempt, prev, next),
-+ TP_ARGS(preempt, prev_state, prev, next),
-
- TP_STRUCT__entry(
- __array( char, prev_comm, TASK_COMM_LEN )
-@@ -239,7 +242,7 @@ TRACE_EVENT(sched_switch,
- memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN);
- __entry->prev_pid = prev->pid;
- __entry->prev_prio = prev->prio;
-- __entry->prev_state = __trace_sched_switch_state(preempt, prev);
-+ __entry->prev_state = __trace_sched_switch_state(preempt, prev_state, prev);
- memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
- __entry->next_pid = next->pid;
- __entry->next_prio = next->prio;
-diff --git a/kernel/sched/core.c b/kernel/sched/core.c
-index 0e4b8214af31..527ee363db3f 100644
---- a/kernel/sched/core.c
-+++ b/kernel/sched/core.c
-@@ -4821,7 +4821,7 @@ static struct rq *finish_task_switch(struct task_struct *prev)
- {
- struct rq *rq = this_rq();
- struct mm_struct *mm = rq->prev_mm;
-- long prev_state;
-+ unsigned int prev_state;
-
- /*
- * The previous task will have left us with a preempt_count of 2
-@@ -6257,7 +6257,7 @@ static void __sched notrace __schedule(unsigned int sched_mode)
- migrate_disable_switch(rq, prev);
- psi_sched_switch(prev, next, !task_on_rq_queued(prev));
-
-- trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next);
-+ trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev_state, prev, next);
-
- /* Also unlocks the rq: */
- rq = context_switch(rq, prev, next, &rf);
-diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
-index 22061d38fc00..19028e072cdb 100644
---- a/kernel/trace/fgraph.c
-+++ b/kernel/trace/fgraph.c
-@@ -415,7 +415,9 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
-
- static void
- ftrace_graph_probe_sched_switch(void *ignore, bool preempt,
-- struct task_struct *prev, struct task_struct *next)
-+ unsigned int prev_state,
-+ struct task_struct *prev,
-+ struct task_struct *next)
- {
- unsigned long long timestamp;
- int index;
-diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
-index be5f6b32a012..bbfa4606cba6 100644
---- a/kernel/trace/ftrace.c
-+++ b/kernel/trace/ftrace.c
-@@ -7317,7 +7317,9 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops)
-
- static void
- ftrace_filter_pid_sched_switch_probe(void *data, bool preempt,
-- struct task_struct *prev, struct task_struct *next)
-+ unsigned int prev_state,
-+ struct task_struct *prev,
-+ struct task_struct *next)
- {
- struct trace_array *tr = data;
- struct trace_pid_list *pid_list;
-diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
-index 92be9cb1d7d4..c097d89ca946 100644
---- a/kernel/trace/trace_events.c
-+++ b/kernel/trace/trace_events.c
-@@ -759,7 +759,9 @@ void trace_event_follow_fork(struct trace_array *tr, bool enable)
-
- static void
- event_filter_pid_sched_switch_probe_pre(void *data, bool preempt,
-- struct task_struct *prev, struct task_struct *next)
-+ unsigned int prev_state,
-+ struct task_struct *prev,
-+ struct task_struct *next)
- {
- struct trace_array *tr = data;
- struct trace_pid_list *no_pid_list;
-@@ -783,7 +785,9 @@ event_filter_pid_sched_switch_probe_pre(void *data, bool preempt,
-
- static void
- event_filter_pid_sched_switch_probe_post(void *data, bool preempt,
-- struct task_struct *prev, struct task_struct *next)
-+ unsigned int prev_state,
-+ struct task_struct *prev,
-+ struct task_struct *next)
- {
- struct trace_array *tr = data;
- struct trace_pid_list *no_pid_list;
-diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
-index b6da7bd2383d..b3b8060e8bdd 100644
---- a/kernel/trace/trace_osnoise.c
-+++ b/kernel/trace/trace_osnoise.c
-@@ -1168,7 +1168,9 @@ thread_exit(struct osnoise_variables *osn_var, struct task_struct *t)
- * used to record the beginning and to report the end of a thread noise window.
- */
- static void
--trace_sched_switch_callback(void *data, bool preempt, struct task_struct *p,
-+trace_sched_switch_callback(void *data, bool preempt,
-+ unsigned int prev_state,
-+ struct task_struct *p,
- struct task_struct *n)
- {
- struct osnoise_variables *osn_var = this_cpu_osn_var();
-diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
-index e304196d7c28..993b0ed10d8c 100644
---- a/kernel/trace/trace_sched_switch.c
-+++ b/kernel/trace/trace_sched_switch.c
-@@ -22,6 +22,7 @@ static DEFINE_MUTEX(sched_register_mutex);
-
- static void
- probe_sched_switch(void *ignore, bool preempt,
-+ unsigned int prev_state,
- struct task_struct *prev, struct task_struct *next)
- {
- int flags;
-diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
-index 2402de520eca..46429f9a96fa 100644
---- a/kernel/trace/trace_sched_wakeup.c
-+++ b/kernel/trace/trace_sched_wakeup.c
-@@ -426,6 +426,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
-
- static void notrace
- probe_wakeup_sched_switch(void *ignore, bool preempt,
-+ unsigned int prev_state,
- struct task_struct *prev, struct task_struct *next)
- {
- struct trace_array_cpu *data;
---
-2.34.1
-
locking-lockdep-iterate-lock_classes-directly-when-r.patch
ext4-correct-cluster-len-and-clusters-changed-accoun.patch
ext4-fix-ext4_mb_mark_bb-with-flex_bg-with-fast_comm.patch
-sched-tracing-don-t-re-read-p-state-when-emitting-sc.patch
sched-tracing-report-task_rtlock_wait-tasks-as-task_.patch
ext4-don-t-bug-if-someone-dirty-pages-without-asking.patch
f2fs-fix-to-do-sanity-check-on-curseg-alloc_type.patch
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
- kernel/trace/trace_events.c | 28 ++++++++++++++++++++++++++++
+ kernel/trace/trace_events.c | 28 ++++++++++++++++++++++++++++
1 file changed, 28 insertions(+)
-diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
-index c097d89ca946..f809d795a9a8 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
-@@ -2637,6 +2637,33 @@ static void update_event_printk(struct trace_event_call *call,
+@@ -2633,6 +2633,33 @@ static void update_event_printk(struct t
}
}
void trace_event_eval_update(struct trace_eval_map **map, int len)
{
struct trace_event_call *call, *p;
-@@ -2672,6 +2699,7 @@ void trace_event_eval_update(struct trace_eval_map **map, int len)
+@@ -2668,6 +2695,7 @@ void trace_event_eval_update(struct trac
first = false;
}
update_event_printk(call, map[i]);
}
}
}
---
-2.34.1
-
#define GFP_TRACE (GFP_KERNEL | __GFP_ZERO)
static struct kmem_cache *field_cachep;
-@@ -2637,14 +2645,40 @@ static void update_event_printk(struct t
+@@ -2633,14 +2641,40 @@ static void update_event_printk(struct t
}
}
head = trace_get_fields(call);
list_for_each_entry(field, head, link) {
ptr = strchr(field->type, '[');
-@@ -2658,9 +2692,26 @@ static void update_event_fields(struct t
+@@ -2654,9 +2688,26 @@ static void update_event_fields(struct t
if (strncmp(map->eval_string, ptr, len) != 0)
continue;
}
}
-@@ -2885,6 +2936,7 @@ static void trace_module_add_events(stru
+@@ -2881,6 +2932,7 @@ static void trace_module_add_events(stru
static void trace_module_remove_events(struct module *mod)
{
struct trace_event_call *call, *p;
down_write(&trace_event_sem);
list_for_each_entry_safe(call, p, &ftrace_events, list) {
-@@ -2893,6 +2945,14 @@ static void trace_module_remove_events(s
+@@ -2889,6 +2941,14 @@ static void trace_module_remove_events(s
if (call->module == mod)
__trace_remove_event_call(call);
}
+++ /dev/null
-From 535270b11943d367c3b2e10459733dba2b92d4b7 Mon Sep 17 00:00:00 2001
-From: Sasha Levin <sashal@kernel.org>
-Date: Thu, 20 Jan 2022 16:25:19 +0000
-Subject: sched/tracing: Don't re-read p->state when emitting sched_switch
- event
-
-From: Valentin Schneider <valentin.schneider@arm.com>
-
-[ Upstream commit fa2c3254d7cfff5f7a916ab928a562d1165f17bb ]
-
-As of commit
-
- c6e7bd7afaeb ("sched/core: Optimize ttwu() spinning on p->on_cpu")
-
-the following sequence becomes possible:
-
- p->__state = TASK_INTERRUPTIBLE;
- __schedule()
- deactivate_task(p);
- ttwu()
- READ !p->on_rq
- p->__state=TASK_WAKING
- trace_sched_switch()
- __trace_sched_switch_state()
- task_state_index()
- return 0;
-
-TASK_WAKING isn't in TASK_REPORT, so the task appears as TASK_RUNNING in
-the trace event.
-
-Prevent this by pushing the value read from __schedule() down the trace
-event.
-
-Reported-by: Abhijeet Dharmapurikar <adharmap@quicinc.com>
-Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
-Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
-Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
-Link: https://lore.kernel.org/r/20220120162520.570782-2-valentin.schneider@arm.com
-Signed-off-by: Sasha Levin <sashal@kernel.org>
----
- include/linux/sched.h | 11 ++++++++---
- include/trace/events/sched.h | 11 +++++++----
- kernel/sched/core.c | 4 ++--
- kernel/trace/fgraph.c | 4 +++-
- kernel/trace/ftrace.c | 4 +++-
- kernel/trace/trace_events.c | 8 ++++++--
- kernel/trace/trace_osnoise.c | 4 +++-
- kernel/trace/trace_sched_switch.c | 1 +
- kernel/trace/trace_sched_wakeup.c | 1 +
- 9 files changed, 34 insertions(+), 14 deletions(-)
-
-diff --git a/include/linux/sched.h b/include/linux/sched.h
-index 75ba8aa60248..a76a178f8eb6 100644
---- a/include/linux/sched.h
-+++ b/include/linux/sched.h
-@@ -1620,10 +1620,10 @@ static inline pid_t task_pgrp_nr(struct task_struct *tsk)
- #define TASK_REPORT_IDLE (TASK_REPORT + 1)
- #define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1)
-
--static inline unsigned int task_state_index(struct task_struct *tsk)
-+static inline unsigned int __task_state_index(unsigned int tsk_state,
-+ unsigned int tsk_exit_state)
- {
-- unsigned int tsk_state = READ_ONCE(tsk->__state);
-- unsigned int state = (tsk_state | tsk->exit_state) & TASK_REPORT;
-+ unsigned int state = (tsk_state | tsk_exit_state) & TASK_REPORT;
-
- BUILD_BUG_ON_NOT_POWER_OF_2(TASK_REPORT_MAX);
-
-@@ -1633,6 +1633,11 @@ static inline unsigned int task_state_index(struct task_struct *tsk)
- return fls(state);
- }
-
-+static inline unsigned int task_state_index(struct task_struct *tsk)
-+{
-+ return __task_state_index(READ_ONCE(tsk->__state), tsk->exit_state);
-+}
-+
- static inline char task_index_to_char(unsigned int state)
- {
- static const char state_char[] = "RSDTtXZPI";
-diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
-index 94640482cfe7..65e786756321 100644
---- a/include/trace/events/sched.h
-+++ b/include/trace/events/sched.h
-@@ -187,7 +187,9 @@ DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new,
- TP_ARGS(p));
-
- #ifdef CREATE_TRACE_POINTS
--static inline long __trace_sched_switch_state(bool preempt, struct task_struct *p)
-+static inline long __trace_sched_switch_state(bool preempt,
-+ unsigned int prev_state,
-+ struct task_struct *p)
- {
- unsigned int state;
-
-@@ -208,7 +210,7 @@ static inline long __trace_sched_switch_state(bool preempt, struct task_struct *
- * it for left shift operation to get the correct task->state
- * mapping.
- */
-- state = task_state_index(p);
-+ state = __task_state_index(prev_state, p->exit_state);
-
- return state ? (1 << (state - 1)) : state;
- }
-@@ -220,10 +222,11 @@ static inline long __trace_sched_switch_state(bool preempt, struct task_struct *
- TRACE_EVENT(sched_switch,
-
- TP_PROTO(bool preempt,
-+ unsigned int prev_state,
- struct task_struct *prev,
- struct task_struct *next),
-
-- TP_ARGS(preempt, prev, next),
-+ TP_ARGS(preempt, prev_state, prev, next),
-
- TP_STRUCT__entry(
- __array( char, prev_comm, TASK_COMM_LEN )
-@@ -239,7 +242,7 @@ TRACE_EVENT(sched_switch,
- memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN);
- __entry->prev_pid = prev->pid;
- __entry->prev_prio = prev->prio;
-- __entry->prev_state = __trace_sched_switch_state(preempt, prev);
-+ __entry->prev_state = __trace_sched_switch_state(preempt, prev_state, prev);
- memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
- __entry->next_pid = next->pid;
- __entry->next_prio = next->prio;
-diff --git a/kernel/sched/core.c b/kernel/sched/core.c
-index 1620ae8535dc..98f81293bea8 100644
---- a/kernel/sched/core.c
-+++ b/kernel/sched/core.c
-@@ -4835,7 +4835,7 @@ static struct rq *finish_task_switch(struct task_struct *prev)
- {
- struct rq *rq = this_rq();
- struct mm_struct *mm = rq->prev_mm;
-- long prev_state;
-+ unsigned int prev_state;
-
- /*
- * The previous task will have left us with a preempt_count of 2
-@@ -6299,7 +6299,7 @@ static void __sched notrace __schedule(unsigned int sched_mode)
- migrate_disable_switch(rq, prev);
- psi_sched_switch(prev, next, !task_on_rq_queued(prev));
-
-- trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next);
-+ trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev_state, prev, next);
-
- /* Also unlocks the rq: */
- rq = context_switch(rq, prev, next, &rf);
-diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
-index 22061d38fc00..19028e072cdb 100644
---- a/kernel/trace/fgraph.c
-+++ b/kernel/trace/fgraph.c
-@@ -415,7 +415,9 @@ static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
-
- static void
- ftrace_graph_probe_sched_switch(void *ignore, bool preempt,
-- struct task_struct *prev, struct task_struct *next)
-+ unsigned int prev_state,
-+ struct task_struct *prev,
-+ struct task_struct *next)
- {
- unsigned long long timestamp;
- int index;
-diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
-index 6105b7036482..8b568f57cc24 100644
---- a/kernel/trace/ftrace.c
-+++ b/kernel/trace/ftrace.c
-@@ -7346,7 +7346,9 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops)
-
- static void
- ftrace_filter_pid_sched_switch_probe(void *data, bool preempt,
-- struct task_struct *prev, struct task_struct *next)
-+ unsigned int prev_state,
-+ struct task_struct *prev,
-+ struct task_struct *next)
- {
- struct trace_array *tr = data;
- struct trace_pid_list *pid_list;
-diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
-index 3147614c1812..2a19ea747ff4 100644
---- a/kernel/trace/trace_events.c
-+++ b/kernel/trace/trace_events.c
-@@ -759,7 +759,9 @@ void trace_event_follow_fork(struct trace_array *tr, bool enable)
-
- static void
- event_filter_pid_sched_switch_probe_pre(void *data, bool preempt,
-- struct task_struct *prev, struct task_struct *next)
-+ unsigned int prev_state,
-+ struct task_struct *prev,
-+ struct task_struct *next)
- {
- struct trace_array *tr = data;
- struct trace_pid_list *no_pid_list;
-@@ -783,7 +785,9 @@ event_filter_pid_sched_switch_probe_pre(void *data, bool preempt,
-
- static void
- event_filter_pid_sched_switch_probe_post(void *data, bool preempt,
-- struct task_struct *prev, struct task_struct *next)
-+ unsigned int prev_state,
-+ struct task_struct *prev,
-+ struct task_struct *next)
- {
- struct trace_array *tr = data;
- struct trace_pid_list *no_pid_list;
-diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
-index 5e3c62a08fc0..e9ae1f33a7f0 100644
---- a/kernel/trace/trace_osnoise.c
-+++ b/kernel/trace/trace_osnoise.c
-@@ -1167,7 +1167,9 @@ thread_exit(struct osnoise_variables *osn_var, struct task_struct *t)
- * used to record the beginning and to report the end of a thread noise window.
- */
- static void
--trace_sched_switch_callback(void *data, bool preempt, struct task_struct *p,
-+trace_sched_switch_callback(void *data, bool preempt,
-+ unsigned int prev_state,
-+ struct task_struct *p,
- struct task_struct *n)
- {
- struct osnoise_variables *osn_var = this_cpu_osn_var();
-diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
-index e304196d7c28..993b0ed10d8c 100644
---- a/kernel/trace/trace_sched_switch.c
-+++ b/kernel/trace/trace_sched_switch.c
-@@ -22,6 +22,7 @@ static DEFINE_MUTEX(sched_register_mutex);
-
- static void
- probe_sched_switch(void *ignore, bool preempt,
-+ unsigned int prev_state,
- struct task_struct *prev, struct task_struct *next)
- {
- int flags;
-diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
-index 2402de520eca..46429f9a96fa 100644
---- a/kernel/trace/trace_sched_wakeup.c
-+++ b/kernel/trace/trace_sched_wakeup.c
-@@ -426,6 +426,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
-
- static void notrace
- probe_wakeup_sched_switch(void *ignore, bool preempt,
-+ unsigned int prev_state,
- struct task_struct *prev, struct task_struct *next)
- {
- struct trace_array_cpu *data;
---
-2.34.1
-
locking-lockdep-iterate-lock_classes-directly-when-r.patch
ext4-correct-cluster-len-and-clusters-changed-accoun.patch
ext4-fix-ext4_mb_mark_bb-with-flex_bg-with-fast_comm.patch
-sched-tracing-don-t-re-read-p-state-when-emitting-sc.patch
sched-tracing-report-task_rtlock_wait-tasks-as-task_.patch
ext4-don-t-bug-if-someone-dirty-pages-without-asking.patch
f2fs-fix-to-do-sanity-check-on-curseg-alloc_type.patch
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
- kernel/trace/trace_events.c | 28 ++++++++++++++++++++++++++++
+ kernel/trace/trace_events.c | 28 ++++++++++++++++++++++++++++
1 file changed, 28 insertions(+)
-diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
-index 2a19ea747ff4..f382ac9597f2 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
-@@ -2637,6 +2637,33 @@ static void update_event_printk(struct trace_event_call *call,
+@@ -2633,6 +2633,33 @@ static void update_event_printk(struct t
}
}
void trace_event_eval_update(struct trace_eval_map **map, int len)
{
struct trace_event_call *call, *p;
-@@ -2672,6 +2699,7 @@ void trace_event_eval_update(struct trace_eval_map **map, int len)
+@@ -2668,6 +2695,7 @@ void trace_event_eval_update(struct trac
first = false;
}
update_event_printk(call, map[i]);
}
}
}
---
-2.34.1
-
#define GFP_TRACE (GFP_KERNEL | __GFP_ZERO)
static struct kmem_cache *field_cachep;
-@@ -2637,14 +2645,40 @@ static void update_event_printk(struct t
+@@ -2633,14 +2641,40 @@ static void update_event_printk(struct t
}
}
head = trace_get_fields(call);
list_for_each_entry(field, head, link) {
ptr = strchr(field->type, '[');
-@@ -2658,9 +2692,26 @@ static void update_event_fields(struct t
+@@ -2654,9 +2688,26 @@ static void update_event_fields(struct t
if (strncmp(map->eval_string, ptr, len) != 0)
continue;
}
}
-@@ -2885,6 +2936,7 @@ static void trace_module_add_events(stru
+@@ -2881,6 +2932,7 @@ static void trace_module_add_events(stru
static void trace_module_remove_events(struct module *mod)
{
struct trace_event_call *call, *p;
down_write(&trace_event_sem);
list_for_each_entry_safe(call, p, &ftrace_events, list) {
-@@ -2893,6 +2945,14 @@ static void trace_module_remove_events(s
+@@ -2889,6 +2941,14 @@ static void trace_module_remove_events(s
if (call->module == mod)
__trace_remove_event_call(call);
}
projects / thirdparty / kernel / stable-queue.git / commitdiff
