drm/i915: Show if we consider the engine is idle in the GPU error state

Useful for verifying our bookkeeper when we encounter is knowing whether
we think the engine is idle at the time of the GPU hang.

References: https://bugs.freedesktop.org/show_bug.cgi?id=104305
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171219131419.13117-1-chris@chris-wilson.co.uk

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index eb4f6d7d87551d7a2d3781ce4ecbbc5e9743a3f1..ca2a61966a231fc40ffb8d26c0c00ea7991b9cb0 100644 (file)
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -948,6 +948,7 @@ struct i915_gpu_state {
        struct drm_i915_error_engine {
                int engine_id;
                /* Software tracked state */
+               bool idle;
                bool waiting;
                int num_waiters;
                unsigned long hangcheck_timestamp;

diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 84831e94eec87bd80550b4b0428570d5e12e8445..944059322daae9df32dd957331baabef8183a914 100644 (file)
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -416,6 +416,7 @@ static void error_print_engine(struct drm_i915_error_state_buf *m,
        int n;
 
        err_printf(m, "%s command stream:\n", engine_str(ee->engine_id));
+       err_printf(m, "  IDLE?: %s\n", yesno(ee->idle));
        err_printf(m, "  START: 0x%08x\n", ee->start);
        err_printf(m, "  HEAD:  0x%08x [0x%08x]\n", ee->head, ee->rq_head);
        err_printf(m, "  TAIL:  0x%08x [0x%08x, 0x%08x]\n",
@@ -1239,6 +1240,7 @@ static void error_record_engine_registers(struct i915_gpu_state *error,
                ee->hws = I915_READ(mmio);
        }
 
+       ee->idle = intel_engine_is_idle(engine);
        ee->hangcheck_timestamp = engine->hangcheck.action_timestamp;
        ee->hangcheck_action = engine->hangcheck.action;
        ee->hangcheck_stalled = engine->hangcheck.stalled;