From: Peter Zijlstra <peterz@infradead.org>
To: tglx@linutronix.de, mingo@kernel.org
Cc: linux-kernel@vger.kernel.org, bigeasy@linutronix.de,
qais.yousef@arm.com, swood@redhat.com, peterz@infradead.org,
valentin.schneider@arm.com, juri.lelli@redhat.com,
vincent.guittot@linaro.org, dietmar.eggemann@arm.com,
rostedt@goodmis.org, bsegall@google.com, mgorman@suse.de,
bristot@redhat.com, vincent.donnefort@arm.com, tj@kernel.org,
ouwen210@hotmail.com
Subject: [PATCH v3 01/19] stop_machine: Add function and caller debug info
Date: Thu, 15 Oct 2020 13:05:33 +0200 [thread overview]
Message-ID: <20201015110923.362565979@infradead.org> (raw)
In-Reply-To: 20201015110532.738127234@infradead.org
Crashes in stop-machine are hard to connect to the calling code, add a
little something to help with that.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
include/linux/stop_machine.h | 5 +++++
kernel/stop_machine.c | 23 ++++++++++++++++++++---
lib/dump_stack.c | 2 ++
3 files changed, 27 insertions(+), 3 deletions(-)
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -24,6 +24,7 @@ typedef int (*cpu_stop_fn_t)(void *arg);
struct cpu_stop_work {
struct list_head list; /* cpu_stopper->works */
cpu_stop_fn_t fn;
+ unsigned long caller;
void *arg;
struct cpu_stop_done *done;
};
@@ -36,6 +37,8 @@ void stop_machine_park(int cpu);
void stop_machine_unpark(int cpu);
void stop_machine_yield(const struct cpumask *cpumask);
+extern void print_stop_info(const char *log_lvl, struct task_struct *task);
+
#else /* CONFIG_SMP */
#include <linux/workqueue.h>
@@ -80,6 +83,8 @@ static inline bool stop_one_cpu_nowait(u
return false;
}
+static inline void print_stop_info(const char *log_lvl, struct task_struct *task) { }
+
#endif /* CONFIG_SMP */
/*
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -42,11 +42,23 @@ struct cpu_stopper {
struct list_head works; /* list of pending works */
struct cpu_stop_work stop_work; /* for stop_cpus */
+ unsigned long caller;
+ cpu_stop_fn_t fn;
};
static DEFINE_PER_CPU(struct cpu_stopper, cpu_stopper);
static bool stop_machine_initialized = false;
+void print_stop_info(const char *log_lvl, struct task_struct *task)
+{
+ struct cpu_stopper *stopper = this_cpu_ptr(&cpu_stopper);
+
+ if (task != stopper->thread)
+ return;
+
+ printk("%sStopper: %pS <- %pS\n", log_lvl, stopper->fn, (void *)stopper->caller);
+}
+
/* static data for stop_cpus */
static DEFINE_MUTEX(stop_cpus_mutex);
static bool stop_cpus_in_progress;
@@ -123,7 +135,7 @@ static bool cpu_stop_queue_work(unsigned
int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg)
{
struct cpu_stop_done done;
- struct cpu_stop_work work = { .fn = fn, .arg = arg, .done = &done };
+ struct cpu_stop_work work = { .fn = fn, .arg = arg, .done = &done, .caller = _RET_IP_ };
cpu_stop_init_done(&done, 1);
if (!cpu_stop_queue_work(cpu, &work))
@@ -331,7 +343,8 @@ int stop_two_cpus(unsigned int cpu1, uns
work1 = work2 = (struct cpu_stop_work){
.fn = multi_cpu_stop,
.arg = &msdata,
- .done = &done
+ .done = &done,
+ .caller = _RET_IP_,
};
cpu_stop_init_done(&done, 2);
@@ -367,7 +380,7 @@ int stop_two_cpus(unsigned int cpu1, uns
bool stop_one_cpu_nowait(unsigned int cpu, cpu_stop_fn_t fn, void *arg,
struct cpu_stop_work *work_buf)
{
- *work_buf = (struct cpu_stop_work){ .fn = fn, .arg = arg, };
+ *work_buf = (struct cpu_stop_work){ .fn = fn, .arg = arg, .caller = _RET_IP_, };
return cpu_stop_queue_work(cpu, work_buf);
}
@@ -487,6 +500,8 @@ static void cpu_stopper_thread(unsigned
int ret;
/* cpu stop callbacks must not sleep, make in_atomic() == T */
+ stopper->caller = work->caller;
+ stopper->fn = fn;
preempt_count_inc();
ret = fn(arg);
if (done) {
@@ -495,6 +510,8 @@ static void cpu_stopper_thread(unsigned
cpu_stop_signal_done(done);
}
preempt_count_dec();
+ stopper->fn = NULL;
+ stopper->caller = 0;
WARN_ONCE(preempt_count(),
"cpu_stop: %ps(%p) leaked preempt count\n", fn, arg);
goto repeat;
--- a/lib/dump_stack.c
+++ b/lib/dump_stack.c
@@ -12,6 +12,7 @@
#include <linux/atomic.h>
#include <linux/kexec.h>
#include <linux/utsname.h>
+#include <linux/stop_machine.h>
static char dump_stack_arch_desc_str[128];
@@ -57,6 +58,7 @@ void dump_stack_print_info(const char *l
log_lvl, dump_stack_arch_desc_str);
print_worker_info(log_lvl, current);
+ print_stop_info(log_lvl, current);
}
/**
next prev parent reply other threads:[~2020-10-15 11:10 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-10-15 11:05 [PATCH v3 00/19] sched: Migrate disable support Peter Zijlstra
2020-10-15 11:05 ` Peter Zijlstra [this message]
2020-10-15 11:05 ` [PATCH v3 02/19] sched: Fix balance_callback() Peter Zijlstra
2020-10-15 11:05 ` [PATCH v3 03/19] sched/hotplug: Ensure only per-cpu kthreads run during hotplug Peter Zijlstra
2020-10-15 11:05 ` [PATCH v3 04/19] sched/core: Wait for tasks being pushed away on hotplug Peter Zijlstra
2020-10-15 11:05 ` [PATCH v3 05/19] workqueue: Manually break affinity " Peter Zijlstra
2020-10-15 11:05 ` [PATCH v3 06/19] sched/hotplug: Consolidate task migration on CPU unplug Peter Zijlstra
2020-10-15 11:05 ` [PATCH v3 07/19] sched: Fix hotplug vs CPU bandwidth control Peter Zijlstra
2020-10-15 11:05 ` [PATCH v3 08/19] sched: Massage set_cpus_allowed() Peter Zijlstra
2020-10-15 11:05 ` [PATCH v3 09/19] sched: Add migrate_disable() Peter Zijlstra
2020-10-15 11:05 ` [PATCH v3 10/19] sched: Fix migrate_disable() vs set_cpus_allowed_ptr() Peter Zijlstra
2020-10-15 13:54 ` Valentin Schneider
2020-10-15 14:19 ` Peter Zijlstra
2020-10-16 12:48 ` Valentin Schneider
[not found] ` <BN8PR12MB29784D239007D0D6CA3F4F2A9A010@BN8PR12MB2978.namprd12.prod.outlook.com>
2020-10-18 15:51 ` Valentin Schneider
[not found] ` <BN8PR12MB2978F76887133CCA2102B7589A1E0@BN8PR12MB2978.namprd12.prod.outlook.com>
2020-10-19 17:36 ` Valentin Schneider
[not found] ` <BN8PR12MB2978D36FF4A81C344DCF37FD9A1F0@BN8PR12MB2978.namprd12.prod.outlook.com>
2020-10-20 7:56 ` Peter Zijlstra
2020-10-15 11:05 ` [PATCH v3 11/19] sched/core: Make migrate disable and CPU hotplug cooperative Peter Zijlstra
[not found] ` <BN8PR12MB2978A3BB8062DF4CEEB184109A030@BN8PR12MB2978.namprd12.prod.outlook.com>
2020-10-16 9:35 ` Peter Zijlstra
2020-10-15 11:05 ` [PATCH v3 12/19] sched,rt: Use cpumask_any*_distribute() Peter Zijlstra
2020-10-15 11:05 ` [PATCH v3 13/19] sched,rt: Use the full cpumask for balancing Peter Zijlstra
2020-10-15 11:05 ` [PATCH v3 14/19] sched, lockdep: Annotate ->pi_lock recursion Peter Zijlstra
2020-10-15 11:05 ` [PATCH v3 15/19] sched: Fix migrate_disable() vs rt/dl balancing Peter Zijlstra
2020-10-15 11:05 ` [PATCH v3 16/19] sched/proc: Print accurate cpumask vs migrate_disable() Peter Zijlstra
2020-10-15 11:05 ` [PATCH v3 17/19] sched: Add migrate_disable() tracepoints Peter Zijlstra
2020-10-15 11:05 ` [PATCH v3 18/19] sched: Deny self-issued __set_cpus_allowed_ptr() when migrate_disable() Peter Zijlstra
2020-10-15 11:05 ` [PATCH v3 19/19] sched: Comment affine_move_task() Peter Zijlstra
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20201015110923.362565979@infradead.org \
--to=peterz@infradead.org \
--cc=bigeasy@linutronix.de \
--cc=bristot@redhat.com \
--cc=bsegall@google.com \
--cc=dietmar.eggemann@arm.com \
--cc=juri.lelli@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mgorman@suse.de \
--cc=mingo@kernel.org \
--cc=ouwen210@hotmail.com \
--cc=qais.yousef@arm.com \
--cc=rostedt@goodmis.org \
--cc=swood@redhat.com \
--cc=tglx@linutronix.de \
--cc=tj@kernel.org \
--cc=valentin.schneider@arm.com \
--cc=vincent.donnefort@arm.com \
--cc=vincent.guittot@linaro.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).