[PATCH 01/23] drm/i915: Capture dmc firmware information before reset

[Michel Thierry]

The firmware may change between the hang and cat /sys/class/drm/card0/error

v2: if version is 0, the fw was not loaded.

Cc: Chris Wilson <chris at chris-wilson.co.uk>
Reviewed-by: Michal Wajdeczko <michal.wajdeczko at intel.com>
Reviewed-by: Chris Wilson <chris at chris-wilson.co.uk>
Signed-off-by: Michel Thierry <michel.thierry at intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h       |  3 +++
 drivers/gpu/drm/i915/i915_gpu_error.c | 21 +++++++++++++++------
 2 files changed, 18 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index c9b0949f6c1a..cc76416ea3da 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -959,6 +959,9 @@ struct i915_gpu_state {
 	u32 gab_ctl;
 	u32 gfx_mode;
 
+	/* Firmware load state */
+	u32 dmc_version;
+
 	u32 nfence;
 	u64 fence[I915_MAX_NUM_FENCES];
 	struct intel_overlay_error_state *overlay;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 8effc59f5cb5..42f729687229 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -623,13 +623,10 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 	err_printf(m, "IOMMU enabled?: %d\n", error->iommu);
 
 	if (HAS_CSR(dev_priv)) {
-		struct intel_csr *csr = &dev_priv->csr;
-
-		err_printf(m, "DMC loaded: %s\n",
-			   yesno(csr->dmc_payload != NULL));
+		err_printf(m, "DMC loaded: %s\n", yesno(error->dmc_version));
 		err_printf(m, "DMC fw version: %d.%d\n",
-			   CSR_VERSION_MAJOR(csr->version),
-			   CSR_VERSION_MINOR(csr->version));
+			   CSR_VERSION_MAJOR(error->dmc_version),
+			   CSR_VERSION_MINOR(error->dmc_version));
 	}
 
 	err_printf(m, "GT awake: %s\n", yesno(error->awake));
@@ -1588,6 +1585,17 @@ static void i915_capture_reg_state(struct drm_i915_private *dev_priv,
 	error->pgtbl_er = I915_READ(PGTBL_ER);
 }
 
+/* Capture all firmware related information. */
+static void i915_capture_fw_state(struct drm_i915_private *dev_priv,
+				  struct i915_gpu_state *error)
+{
+	if (HAS_CSR(dev_priv)) {
+		struct intel_csr *csr = &dev_priv->csr;
+
+		error->dmc_version = csr->version;
+	}
+}
+
 static void i915_error_capture_msg(struct drm_i915_private *dev_priv,
 				   struct i915_gpu_state *error,
 				   u32 engine_mask,
@@ -1657,6 +1665,7 @@ static int capture(void *data)
 
 	i915_capture_gen_state(error->i915, error);
 	i915_capture_reg_state(error->i915, error);
+	i915_capture_fw_state(error->i915, error);
 	i915_gem_record_fences(error->i915, error);
 	i915_gem_record_rings(error->i915, error);
 	i915_capture_active_buffers(error->i915, error);
-- 
2.11.0