drm/i915: Print error state times relative to capture

Commit Message

Mika Kuoppala April 27, 2018, 3:12 p.m. UTC

Using plain jiffies in error state output makes the output
time differences relative to the current system time. This
is wrong as it makes output time differences dependent
of when the error state is printed rather than when it is
captured.

Store capture jiffies into error state and use it
when outputting the state to fix time differences output.

v2: use engine timestamp as epoch, output formatting (Chris)

Cc: Chris Wilson <[e-mail]>
Signed-off-by: Mika Kuoppala <[e-mail]>
---
 drivers/gpu/drm/i915/i915_gpu_error.c | 48 +++++++++++++++++++++++++++++------
 drivers/gpu/drm/i915/i915_gpu_error.h |  2 ++
 2 files changed, 42 insertions(+), 8 deletions(-)

Comments

Chris Wilson April 27, 2018, 3:32 p.m. UTC | #1

Quoting Mika Kuoppala (2018-04-27 16:12:48)
> @@ -427,8 +428,10 @@ static void error_print_context(struct drm_i915_error_state_buf *m,
>  }
>  
>  static void error_print_engine(struct drm_i915_error_state_buf *m,
> -                              const struct drm_i915_error_engine *ee)
> +                              const struct i915_gpu_state *error,
> +                              const int engine_n)

Make it pass in the error_engine again, and
Reviewed-by: Chris Wilson <[e-mail]>
-Chris

Mika Kuoppala May 2, 2018, 8:34 a.m. UTC | #2

Chris Wilson <[e-mail]> writes:

> Quoting Mika Kuoppala (2018-04-27 16:12:48)
>> @@ -427,8 +428,10 @@ static void error_print_context(struct drm_i915_error_state_buf *m,
>>  }
>>  
>>  static void error_print_engine(struct drm_i915_error_state_buf *m,
>> -                              const struct drm_i915_error_engine *ee)
>> +                              const struct i915_gpu_state *error,
>> +                              const int engine_n)
>
> Make it pass in the error_engine again, and

Done.

> Reviewed-by: Chris Wilson <[e-mail]>

Thanks for review. Pushed.
-Mika

Patch

diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 671ffa37614e..fca550954be0 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -403,16 +403,17 @@  static const char *bannable(const struct drm_i915_error_context *ctx)
 }
 
 static void error_print_request(struct drm_i915_error_state_buf *m,
+				const struct i915_gpu_state *error,
 				const char *prefix,
 				const struct drm_i915_error_request *erq)
 {
 	if (!erq->seqno)
 		return;
 
-	err_printf(m, "%s pid %d, ban score %d, seqno %8x:%08x, prio %d, emitted %dms ago, head %08x, tail %08x\n",
+	err_printf(m, "%s pid %d, ban score %d, seqno %8x:%08x, prio %d, emitted %dms, head %08x, tail %08x\n",
 		   prefix, erq->pid, erq->ban_score,
 		   erq->context, erq->seqno, erq->sched_attr.priority,
-		   jiffies_to_msecs(jiffies - erq->jiffies),
+		   jiffies_to_msecs(erq->jiffies - error->epoch),
 		   erq->head, erq->tail);
 }
 
@@ -427,8 +428,10 @@  static void error_print_context(struct drm_i915_error_state_buf *m,
 }
 
 static void error_print_engine(struct drm_i915_error_state_buf *m,
-			       const struct drm_i915_error_engine *ee)
+			       const struct i915_gpu_state *error,
+			       const int engine_n)
 {
+	const struct drm_i915_error_engine *ee = &error->engine[engine_n];
 	int n;
 
 	err_printf(m, "%s command stream:\n",
@@ -497,14 +500,18 @@  static void error_print_engine(struct drm_i915_error_state_buf *m,
 	err_printf(m, "  hangcheck stall: %s\n", yesno(ee->hangcheck_stalled));
 	err_printf(m, "  hangcheck action: %s\n",
 		   hangcheck_action_to_str(ee->hangcheck_action));
-	err_printf(m, "  hangcheck action timestamp: %lu, %u ms ago\n",
+
+	err_printf(m, "  hangcheck action timestamp: %dms (%lu%s)\n",
+		   jiffies_to_msecs(ee->hangcheck_timestamp -
+				    error->epoch),
 		   ee->hangcheck_timestamp,
-		   jiffies_to_msecs(jiffies - ee->hangcheck_timestamp));
+		   ee->hangcheck_timestamp == error->epoch ? "; epoch" : "");
+
 	err_printf(m, "  engine reset count: %u\n", ee->reset_count);
 
 	for (n = 0; n < ee->num_ports; n++) {
 		err_printf(m, "  ELSP[%d]:", n);
-		error_print_request(m, " ", &ee->execlist[n]);
+		error_print_request(m, error, " ", &ee->execlist[n]);
 	}
 
 	error_print_context(m, "  Active context: ", &ee->context);
@@ -650,6 +657,11 @@  int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 	ts = ktime_to_timespec64(error->uptime);
 	err_printf(m, "Uptime: %lld s %ld us\n",
 		   (s64)ts.tv_sec, ts.tv_nsec / NSEC_PER_USEC);
+	err_printf(m, "Epoch: %lu jiffies (%u HZ)\n", error->epoch, HZ);
+	err_printf(m, "Capture: %lu jiffies; %d ms ago, %d ms after epoch\n",
+		   error->capture,
+		   jiffies_to_msecs(jiffies - error->capture),
+		   jiffies_to_msecs(error->capture - error->epoch));
 
 	for (i = 0; i < ARRAY_SIZE(error->engine); i++) {
 		if (error->engine[i].hangcheck_stalled &&
@@ -710,7 +722,7 @@  int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 
 	for (i = 0; i < ARRAY_SIZE(error->engine); i++) {
 		if (error->engine[i].engine_id != -1)
-			error_print_engine(m, &error->engine[i]);
+			error_print_engine(m, error, i);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(error->active_vm); i++) {
@@ -769,7 +781,8 @@  int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 				   dev_priv->engine[i]->name,
 				   ee->num_requests);
 			for (j = 0; j < ee->num_requests; j++)
-				error_print_request(m, " ", &ee->requests[j]);
+				error_print_request(m, error, " ",
+						    &ee->requests[j]);
 		}
 
 		if (IS_ERR(ee->waiters)) {
@@ -1735,6 +1748,22 @@  static void capture_params(struct i915_gpu_state *error)
 #undef DUP
 }
 
+static unsigned long capture_find_epoch(const struct i915_gpu_state *error)
+{
+	unsigned long epoch = error->capture;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(error->engine); i++) {
+		const struct drm_i915_error_engine *ee = &error->engine[i];
+
+		if (ee->hangcheck_stalled &&
+		    time_before(ee->hangcheck_timestamp, epoch))
+			epoch = ee->hangcheck_timestamp;
+	}
+
+	return epoch;
+}
+
 static int capture(void *data)
 {
 	struct i915_gpu_state *error = data;
@@ -1743,6 +1772,7 @@  static int capture(void *data)
 	error->boottime = ktime_get_boottime();
 	error->uptime = ktime_sub(ktime_get(),
 				  error->i915->gt.last_init_time);
+	error->capture = jiffies;
 
 	capture_params(error);
 	capture_gen_state(error);
@@ -1756,6 +1786,8 @@  static int capture(void *data)
 	error->overlay = intel_overlay_capture_error_state(error->i915);
 	error->display = intel_display_capture_error_state(error->i915);
 
+	error->epoch = capture_find_epoch(error);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h
index 5d6fdcbc092c..0accd2ed72d9 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.h
+++ b/drivers/gpu/drm/i915/i915_gpu_error.h
@@ -31,6 +31,8 @@  struct i915_gpu_state {
 	ktime_t time;
 	ktime_t boottime;
 	ktime_t uptime;
+	unsigned long capture;
+	unsigned long epoch;
 
 	struct drm_i915_private *i915;