drm/i915/guc: Print the GuC error capture output register list.

Print the GuC captured error state register list (string names
and values) when gpu_coredump_state printout is invoked via
the i915 debugfs for flushing the gpu error-state that was
captured prior.

Since GuC could have reported multiple engine register dumps
in a single notification event, parse the captured data
(appearing as a stream of structures) to identify each dump as
a different 'engine-capture-group-output'.

Finally, for each 'engine-capture-group-output' that is found,
verify if the engine register dump corresponds to the
engine_coredump content that was previously populated by the
i915_gpu_coredump function. That function would have copied
the context's vma's including the bacth buffer during the
G2H-context-reset notification that occurred earlier. Perform
this verification check by comparing guc_id, lrca and engine-
instance obtained from the 'engine-capture-group-output' vs a
copy of that same info taken during i915_gpu_coredump. If
they match, then print those vma's as well (such as the batch
buffers).

NOTE: the output format was verified using the gem_exec_capture
IGT test.

Signed-off-by: Alan Previn <alan.previn.teres.alexis@intel.com>
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220321164527.2500062-14-alan.previn.teres.alexis@intel.com

1 files changed, 8 insertions, 8 deletions

diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index c76d8df4c190..f41eb4d12b34 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -530,8 +530,8 @@ __find_vma(struct i915_vma_coredump *vma, const char *name)
 	return NULL;
 }
 
-static struct i915_vma_coredump *
-find_batch(const struct intel_engine_coredump *ee)
+struct i915_vma_coredump *
+intel_gpu_error_find_batch(const struct intel_engine_coredump *ee)
 {
 	return __find_vma(ee->vma, "batch");
 }
@@ -559,7 +559,7 @@ static void error_print_engine(struct drm_i915_error_state_buf *m,
 
 	error_print_instdone(m, ee);
 
-	batch = find_batch(ee);
+	batch = intel_gpu_error_find_batch(ee);
 	if (batch) {
 		u64 start = batch->gtt_offset;
 		u64 end = start + batch->gtt_size;
@@ -610,9 +610,9 @@ void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...)
 	va_end(args);
 }
 
-static void print_error_vma(struct drm_i915_error_state_buf *m,
-			    const struct intel_engine_cs *engine,
-			    const struct i915_vma_coredump *vma)
+void intel_gpu_error_print_vma(struct drm_i915_error_state_buf *m,
+			       const struct intel_engine_cs *engine,
+			       const struct i915_vma_coredump *vma)
 {
 	char out[ASCII85_BUFSZ];
 	struct page *page;
@@ -681,7 +681,7 @@ static void err_print_uc(struct drm_i915_error_state_buf *m,
 
 	intel_uc_fw_dump(&error_uc->guc_fw, &p);
 	intel_uc_fw_dump(&error_uc->huc_fw, &p);
-	print_error_vma(m, NULL, error_uc->guc_log);
+	intel_gpu_error_print_vma(m, NULL, error_uc->guc_log);
 }
 
 static void err_free_sgl(struct scatterlist *sgl)
@@ -801,7 +801,7 @@ static void err_print_gt_engines(struct drm_i915_error_state_buf *m,
 		error_print_context(m, "  Active context: ", &ee->context);
 
 		for (vma = ee->vma; vma; vma = vma->next)
-			print_error_vma(m, ee->engine, vma);
+			intel_gpu_error_print_vma(m, ee->engine, vma);
 	}
 
 }