[PATCH] rt_spin_lock: To list the correct owner of rt_spin_lock

From: Mintu Patel
Date: Mon Jun 13 2022 - 14:42:04 EST


rt_spin_lock is actually mutex on RT Kernel so it goes for contention
for lock. Currently owners of rt_spin_lock are decided before actual
acquiring of lock. This patch would depict the correct owner of
rt_spin_lock. The patch would help in solving crashes and deadlock
due to race condition of lock

acquiring rt_spin_lock acquired the lock released the lock
<--------> <------->
contention period Held period

Thread1 Thread2

__try_to_take_rt_mutex+0x95c+0x74 enqueue_task_dl+0x8cc/0x8dc
rt_spin_lock_slowlock_locked+0xac+2 rt_mutex_setprio+0x28c/0x574
rt_spin_lock_slowlock+0x5c/0x90 task_blocks_rt_mutex+0x240/0x310
rt_spin_lock+0x58/0x5c rt_spin_lock_slowlock_locked+0xac/0x2
driverA_acquire_lock+0x28/0x56 rt_spin_lock_slowlock+0x5c/0x90
rt_spin_lock+0x58/0x5c
driverB_acquire_lock+0x48/0x6c

As per above call traces sample, Thread1 acquired the rt_spin_lock and
went to critical section on the other hand Thread2 kept trying to acquire
the same rt_spin_lock held by Thread1 ie contention period is too high.
Finally Thread2 entered to dl queue due to high held time of the lock by
Thread1. The below patch would help us to know the correct owner of
rt_spin_lock and point us the driver's critical section. Respective driver
need to be debugged for longer held period of lock.

ex: cat /sys/kernel/debug/tracing/trace

kworker/u13:0-150 [003] .....11 202.761025: rt_spinlock_acquire:
Process: kworker/u13:0 is acquiring lock: &kbdev->hwaccess_lock
kworker/u13:0-150 [003] .....11 202.761039: rt_spinlock_acquired:
Process: kworker/u13:0 has acquired lock: &kbdev->hwaccess_lock
kworker/u13:0-150 [003] .....11 202.761042: rt_spinlock_released:
Process: kworker/u13:0 has released lock: &kbdev->hwaccess_lock

Signed-off-by: Mintu Patel <mintupatel89@xxxxxxxxx>
Signed-off-by: Chinmoy Ghosh <chinmoyghosh2001@xxxxxxxxx>
Signed-off-by: Vishal Badole <badolevishal1116@xxxxxxxxx>
Signed-off-by: Vimal Kumar <vimal.kumar32@xxxxxxxxx>
---
include/trace/events/lock.h | 60 +++++++++++++++++++++++++++++++++++++
kernel/locking/rtmutex.c | 10 +++++++
2 files changed, 70 insertions(+)

diff --git a/include/trace/events/lock.h b/include/trace/events/lock.h
index d7512129a324..8bb21b31c9a9 100644
--- a/include/trace/events/lock.h
+++ b/include/trace/events/lock.h
@@ -36,6 +36,66 @@ TRACE_EVENT(lock_acquire,
__get_str(name))
);

+TRACE_EVENT(rt_spinlock_acquire,
+
+ TP_PROTO(struct lockdep_map *lock, struct task_struct *pname),
+
+ TP_ARGS(lock, pname),
+
+ TP_STRUCT__entry(
+ __string(name, lock->name)
+ __string(process_name, pname->comm)
+ ),
+
+ TP_fast_assign(
+ __assign_str(name, lock->name);
+ __assign_str(process_name, pname->comm);
+ ),
+
+ TP_printk("Process: %s is acquiring lock: %s", __get_str(process_name),
+ __get_str(name))
+);
+
+TRACE_EVENT(rt_spinlock_acquired,
+
+ TP_PROTO(struct lockdep_map *lock, struct task_struct *pname),
+
+ TP_ARGS(lock, pname),
+
+ TP_STRUCT__entry(
+ __string(name, lock->name)
+ __string(process_name, pname->comm)
+ ),
+
+ TP_fast_assign(
+ __assign_str(name, lock->name);
+ __assign_str(process_name, pname->comm);
+ ),
+
+ TP_printk("Process: %s has acquired lock: %s", __get_str(process_name),
+ __get_str(name))
+);
+
+TRACE_EVENT(rt_spinlock_released,
+
+ TP_PROTO(struct lockdep_map *lock, struct task_struct *pname),
+
+ TP_ARGS(lock, pname),
+
+ TP_STRUCT__entry(
+ __string(name, lock->name)
+ __string(process_name, pname->comm)
+ ),
+
+ TP_fast_assign(
+ __assign_str(name, lock->name);
+ __assign_str(process_name, pname->comm);
+ ),
+
+ TP_printk("Process: %s has released lock: %s", __get_str(process_name),
+ __get_str(name))
+);
+
DECLARE_EVENT_CLASS(lock,

TP_PROTO(struct lockdep_map *lock, unsigned long ip),
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 08e233b7dc21..fb10c4e44f09 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -25,6 +25,7 @@
#include <linux/timer.h>
#include <linux/ww_mutex.h>
#include <linux/blkdev.h>
+#include <trace/events/lock.h>

#include "rtmutex_common.h"

@@ -1144,7 +1145,13 @@ void __lockfunc rt_spin_lock(spinlock_t *lock)
sleeping_lock_inc();
migrate_disable();
spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
+#ifdef CONFIG_RT_SPIN_LOCK_TRACING
+ trace_rt_spinlock_acquire(&lock->dep_map, current);
+#endif
rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock);
+#ifdef CONFIG_RT_SPIN_LOCK_TRACING
+ trace_rt_spinlock_acquired(&lock->dep_map, current);
+#endif
}
EXPORT_SYMBOL(rt_spin_lock);

@@ -1168,6 +1175,9 @@ void __lockfunc rt_spin_unlock(spinlock_t *lock)
{
/* NOTE: we always pass in '1' for nested, for simplicity */
spin_release(&lock->dep_map, 1, _RET_IP_);
+#ifdef CONFIG_RT_SPIN_LOCK_TRACING
+ trace_rt_spinlock_released(&lock->dep_map, current);
+#endif
rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock);
migrate_enable();
sleeping_lock_dec();
--
2.25.1