| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20211129123601.2101873-2-valentin.schneider@arm.com>
Date: Mon, 29 Nov 2021 12:36:00 +0000
From: Valentin Schneider <valentin.schneider@....com>
To: linux-kernel@...r.kernel.org
Cc: Abhijeet Dharmapurikar <adharmap@...cinc.com>,
Uwe Kleine-König
<u.kleine-koenig@...gutronix.de>,
Dietmar Eggemann <dietmar.eggemann@....com>,
Steven Rostedt <rostedt@...dmis.org>,
Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...nel.org>,
Vincent Guittot <vincent.guittot@...aro.org>,
Thomas Gleixner <tglx@...utronix.de>,
Sebastian Andrzej Siewior <bigeasy@...utronix.de>,
Juri Lelli <juri.lelli@...hat.com>,
Daniel Bristot de Oliveira <bristot@...hat.com>,
Kees Cook <keescook@...omium.org>,
Andrew Morton <akpm@...ux-foundation.org>
Subject: [RFC PATCH 1/2] sched/tracing: Don't re-read p->state when emitting sched_switch event
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@...cinc.com>
Signed-off-by: Valentin Schneider <valentin.schneider@....com>
---
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_sched_switch.c | 1 +
7 files changed, 30 insertions(+), 13 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index d2e261adb8ea..d00837d12b9d 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 beaa8be6241e..91e6c33650ca 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4822,7 +4822,7 @@ 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
@@ -6287,7 +6287,7 @@ 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 30bc880c3849..e296ddeec99f 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -7311,7 +7311,9 @@ 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 4021b9a79f93..6ddc6cc0d5d5 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_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;
--
2.25.1
Powered by blists - more mailing lists