[PATCH v2 7/9] tracing/osnoise: Split out per-cpu variable resets

[Crystal Wood <crwood@redhat.com>]

Reset per-cpu state every time we stop a kthread or detach an fd, rather
than assume everything gets cleaned up properly, and avoiding the need
to explicitly zero individual fields.

Also, stop initializing tlat->thread lazily, add some debug checks to
detect an unclean state, and clear osnoise_data.tainted in
osn_var_reset().

Signed-off-by: Crystal Wood <crwood@redhat.com>
---
v2: New patch.  Without this, I was seeing sampling = 1 leaking from a
kthread context to an fd context, which confused the latter into
operating with tlat->thread set to the old kernel thread, causing the fd
thread to hang.
---
 kernel/trace/trace_osnoise.c | 104 +++++++++++++++++------------------
 1 file changed, 51 insertions(+), 53 deletions(-)

diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index eaecd56492e3..ccd717db9a51 100644
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -319,23 +319,19 @@ static inline struct timerlat_variables *cpu_tmr_var(int cpu)
 	return per_cpu_ptr(&per_cpu_timerlat_var, cpu);
 }
 
+static inline void tlat_reset_cpu(int cpu)
+{
+	struct timerlat_variables *tlat = cpu_tmr_var(cpu);
+
+	WARN_ON_ONCE(tlat->thread);
+	memset(&tlat->zero, 0, sizeof(tlat->zero));
+}
+
 /*
- * tlat_var_reset - Reset the values of the given timerlat_variables
+ * tlat_var_reset - Reset non-per-cpu state
  */
 static inline void tlat_var_reset(void)
 {
-	struct timerlat_variables *tlat_var;
-	int cpu;
-
-	/*
-	 * So far, all the values are initialized as 0, so
-	 * zeroing the structure is perfect.
-	 */
-	for_each_online_cpu(cpu) {
-		tlat_var = cpu_tmr_var(cpu);
-		WARN_ON_ONCE(tlat_var->thread);
-		memset(&tlat_var->zero, 0, sizeof(tlat_var->zero));
-	}
 	/*
 	 * Reset also align_next, to be filled by a new offset by the first timerlat
 	 * thread that wakes up, if TIMERLAT_ALIGN is set.
@@ -343,38 +339,12 @@ static inline void tlat_var_reset(void)
 	atomic64_set(&align_next, 0);
 }
 #else /* CONFIG_TIMERLAT_TRACER */
-#define tlat_var_reset()	do {} while (0)
-#endif /* CONFIG_TIMERLAT_TRACER */
-
-/*
- * osn_var_reset - Reset the values of the given osnoise_variables
- */
-static inline void osn_var_reset(void)
+static inline void tlat_reset_cpu(int cpu)
 {
-	struct osnoise_variables *osn_var;
-	int cpu;
-
-	/*
-	 * So far, all the values are initialized as 0, so
-	 * zeroing the structure is perfect.
-	 */
-	for_each_online_cpu(cpu) {
-		osn_var = cpu_osn_var(cpu);
-
-		WARN_ON(osn_var->kthread);
-		WARN_ON(osn_var->fdd);
-		memset(&osn_var->zero, 0, sizeof(osn_var->zero));
-	}
 }
 
-/*
- * osn_var_reset_all - Reset the value of all per-cpu osnoise_variables
- */
-static inline void osn_var_reset_all(void)
-{
-	osn_var_reset();
-	tlat_var_reset();
-}
+#define tlat_var_reset()	do {} while (0)
+#endif /* CONFIG_TIMERLAT_TRACER */
 
 /*
  * Tells NMIs to call back to the osnoise tracer to record timestamps.
@@ -409,6 +379,36 @@ static struct osnoise_data {
 #endif
 };
 
+static inline void osn_reset_cpu(int cpu)
+{
+	struct osnoise_variables *osn = cpu_osn_var(cpu);
+
+	WARN_ON(osn->kthread);
+	WARN_ON(osn->fdd);
+	memset(&osn->zero, 0, sizeof(osn->zero));
+	tlat_reset_cpu(cpu);
+}
+
+/*
+ * osn_var_reset - Reset non-per-cpu state, and check for stale data
+ */
+static inline void osn_var_reset(void)
+{
+	struct osnoise_variables *osn;
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		osn = cpu_osn_var(cpu);
+
+		WARN_ON(osn->kthread);
+		WARN_ON(osn->fdd);
+		WARN_ON(osn->sampling);
+	}
+
+	tlat_var_reset();
+	osnoise_data.tainted = false;
+}
+
 #ifdef CONFIG_TIMERLAT_TRACER
 static inline bool timerlat_enabled(void)
 {
@@ -2036,6 +2036,7 @@ static void stop_kthread(unsigned int cpu)
 		kthread_stop(osn_var->kthread);
 		put_task_struct(osn_var->kthread);
 		osn_var->kthread = NULL;
+		osn_reset_cpu(cpu);
 	}
 
 	mutex_unlock(&osn_var->lock);
@@ -2468,18 +2469,12 @@ static void timerlat_fd_detach(struct fd_data *fdd)
 	if (WARN_ON(fdd != osn->fdd))
 		return;
 
-	WARN_ON(osn->kthread);
 	WARN_ON(fdd->thread != tlat->thread);
 	tlat->detach = true;
 	wake_up_process(tlat->thread);
 
 	mutex_lock(&tlat->detach_lock);
 
-	memset(tlat, 0, sizeof(*tlat));
-
-	osn->sampling = 0;
-	osn->pid = 0;
-
 	WARN_ON_ONCE(hrtimer_active(&tlat->timer));
 	hrtimer_cancel(&tlat->timer);
 	put_task_struct(fdd->thread);
@@ -2489,6 +2484,8 @@ static void timerlat_fd_detach(struct fd_data *fdd)
 	osn->fdd = NULL;
 
 	mutex_unlock(&tlat->detach_lock);
+
+	osn_reset_cpu(fdd->cpu);
 }
 
 static int timerlat_fd_open(struct inode *inode, struct file *file)
@@ -2545,7 +2542,11 @@ static int timerlat_fd_open(struct inode *inode, struct file *file)
 	osn_var->fdd = fdd;
 
 	tlat = this_cpu_tmr_var();
-	tlat->count = 0;
+	WARN_ON(tlat->thread);
+	WARN_ON(tlat->count != 0);
+	WARN_ON(tlat->tracing_thread);
+	WARN_ON(osn_var->sampling);
+	tlat->thread = current;
 
 	hrtimer_setup(&tlat->timer, timerlat_irq, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD);
 	return 0;
@@ -2637,9 +2638,6 @@ timerlat_fd_read(struct file *file, char __user *ubuf, size_t count,
 			}
 		}
 	} else {
-		tlat->tracing_thread = false;
-		tlat->thread = current;
-
 		/* Annotate now to drift new period */
 		tlat->abs_period = hrtimer_cb_get_time(&tlat->timer);
 
@@ -3014,7 +3012,7 @@ static int osnoise_workload_start(void)
 	if (osnoise_has_registered_instances())
 		return 0;
 
-	osn_var_reset_all();
+	osn_var_reset();
 
 	retval = osnoise_hook_events();
 	if (retval)
-- 
2.54.0