[Intel-gfx] [RFCv2 12/12] drm/i915: Extended error state with TDR count, watchdog count and engine reset count

[Tomas Elf]

These new TDR-specific metrics have previously been added to
i915_hangcheck_info() in debugfs. During design review Chris Wilson asked for
these metrics to be added to the error state as well.

Signed-off-by: Tomas Elf <tomas.elf at intel.com>
Cc: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala at linux.intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h       | 3 +++
 drivers/gpu/drm/i915/i915_gpu_error.c | 6 ++++++
 2 files changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 2cf8b38..862e995 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -447,6 +447,9 @@ struct drm_i915_error_state {
 		int hangcheck_score;
 		enum intel_ring_hangcheck_action hangcheck_action;
 		int num_requests;
+		int hangcheck_tdr_count;
+		int hangcheck_watchdog_count;
+		int hangcheck_reset_count;
 
 		/* our own tracking of ring head and tail */
 		u32 cpu_ring_head;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index cee1825..f4d89df 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -303,6 +303,9 @@ static void i915_ring_error_state(struct drm_i915_error_state_buf *m,
 	err_printf(m, "  hangcheck: %s [%d]\n",
 		   hangcheck_action_to_str(ring->hangcheck_action),
 		   ring->hangcheck_score);
+	err_printf(m, "  TDR count: %d\n", ring->hangcheck_tdr_count);
+	err_printf(m, "  Watchdog count: %d\n", ring->hangcheck_watchdog_count);
+	err_printf(m, "  Engine reset count: %d\n", ring->hangcheck_reset_count);
 }
 
 void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...)
@@ -920,6 +923,9 @@ static void i915_record_ring_state(struct drm_device *dev,
 
 	ering->hangcheck_score = ring->hangcheck.score;
 	ering->hangcheck_action = ring->hangcheck.action;
+	ering->hangcheck_tdr_count = ring->hangcheck.tdr_count;
+	ering->hangcheck_watchdog_count = ring->hangcheck.watchdog_count;
+	ering->hangcheck_reset_count = ring->hangcheck.reset_count;
 
 	if (USES_PPGTT(dev)) {
 		int i;
-- 
1.9.1