drm/i915: Use ABI engine class in error state ecode

Instead of printing out the internal engine mask, which can change between
kernel versions making it difficult to map to actual engines, present a
bitmask of hanging engines ABI classes. For example:

  [drm] GPU HANG: ecode 9:8:24dffffd, in gem_exec_schedu [1334]

Engine ABI class is useful to quickly categorize render vs media etc hangs
in bug reports. Considering virtual engine even more so than the current
scheme.

v2:
 * Do not re-order fields. (Chris)

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20201105113842.1395391-1-tvrtko.ursulin@linux.intel.com

diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 994738d..f38e6ab 100644 (file)
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1659,17 +1659,16 @@ static u32 generate_ecode(const struct intel_engine_coredump *ee)
 static const char *error_msg(struct i915_gpu_coredump *error)
 {
        struct intel_engine_coredump *first = NULL;
+       unsigned int hung_classes = 0;
        struct intel_gt_coredump *gt;
-       intel_engine_mask_t engines;
        int len;
 
-       engines = 0;
        for (gt = error->gt; gt; gt = gt->next) {
                struct intel_engine_coredump *cs;
 
                for (cs = gt->engine; cs; cs = cs->next) {
                        if (cs->hung) {
-                               engines |= cs->engine->mask;
+                               hung_classes |= BIT(cs->engine->uabi_class);
                                if (!first)
                                        first = cs;
                        }
@@ -1678,7 +1677,7 @@ static const char *error_msg(struct i915_gpu_coredump *error)
 
        len = scnprintf(error->error_msg, sizeof(error->error_msg),
                        "GPU HANG: ecode %d:%x:%08x",
-                       INTEL_GEN(error->i915), engines,
+                       INTEL_GEN(error->i915), hung_classes,
                        generate_ecode(first));
        if (first && first->context.pid) {
                /* Just show the first executing process, more is confusing */