[PATCH] drm/i915: Report if an unbannable context is involved in a GPU hang

* [PATCH] drm/i915: Report if an unbannable context is involved in a GPU hang
@ 2018-02-05  9:41 Chris Wilson
  2018-02-05 10:01 ` Mika Kuoppala
                   ` (2 more replies)
  0 siblings, 3 replies; 4+ messages in thread
From: Chris Wilson @ 2018-02-05  9:41 UTC (permalink / raw)
  To: intel-gfx; +Cc: Mika

Since unbannable contexts are special and supposed not to be causing GPU
hangs in the first place, make it clear when they are implicated in said
hang. In practice, most unbannable contexts are those created by igt
for the express purpose of throwing untold thousands of hangs at the GPU
and wish to keep doing so to finish the test. Normally they are cleaned
up, but it's when they or the other unbannable kernel contexts stay
stuck in an erroneous state that we need to worry and so need
highlighting.

Suggested-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com
---
 drivers/gpu/drm/i915/i915_drv.h       |  1 +
 drivers/gpu/drm/i915/i915_gpu_error.c | 21 +++++++++++++++------
 2 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 4e158aab36d6..d6b5ac2a563d 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -555,6 +555,7 @@ struct i915_gpu_state {
 			int ban_score;
 			int active;
 			int guilty;
+			bool bannable;
 		} context;
 
 		struct drm_i915_error_object {
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index a81351d9e3a6..67c902412193 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -396,6 +396,11 @@ static void error_print_instdone(struct drm_i915_error_state_buf *m,
 			   ee->instdone.row[slice][subslice]);
 }
 
+static const char *bannable(const struct drm_i915_error_context *ctx)
+{
+	return ctx->bannable ? "" : " (unbannable)";
+}
+
 static void error_print_request(struct drm_i915_error_state_buf *m,
 				const char *prefix,
 				const struct drm_i915_error_request *erq)
@@ -414,9 +419,10 @@ static void error_print_context(struct drm_i915_error_state_buf *m,
 				const char *header,
 				const struct drm_i915_error_context *ctx)
 {
-	err_printf(m, "%s%s[%d] user_handle %d hw_id %d, prio %d, ban score %d guilty %d active %d\n",
+	err_printf(m, "%s%s[%d] user_handle %d hw_id %d, prio %d, ban score %d%s guilty %d active %d\n",
 		   header, ctx->comm, ctx->pid, ctx->handle, ctx->hw_id,
-		   ctx->priority, ctx->ban_score, ctx->guilty, ctx->active);
+		   ctx->priority, ctx->ban_score, bannable(ctx),
+		   ctx->guilty, ctx->active);
 }
 
 static void error_print_engine(struct drm_i915_error_state_buf *m,
@@ -644,11 +650,12 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 	for (i = 0; i < ARRAY_SIZE(error->engine); i++) {
 		if (error->engine[i].hangcheck_stalled &&
 		    error->engine[i].context.pid) {
-			err_printf(m, "Active process (on ring %s): %s [%d], score %d\n",
+			err_printf(m, "Active process (on ring %s): %s [%d], score %d%s\n",
 				   engine_name(m->i915, i),
 				   error->engine[i].context.comm,
 				   error->engine[i].context.pid,
-				   error->engine[i].context.ban_score);
+				   error->engine[i].context.ban_score,
+				   bannable(&error->engine[i].context));
 		}
 	}
 	err_printf(m, "Reset count: %u\n", error->reset_count);
@@ -736,12 +743,13 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 		if (obj) {
 			err_puts(m, dev_priv->engine[i]->name);
 			if (ee->context.pid)
-				err_printf(m, " (submitted by %s [%d], ctx %d [%d], score %d)",
+				err_printf(m, " (submitted by %s [%d], ctx %d [%d], score %d%s)",
 					   ee->context.comm,
 					   ee->context.pid,
 					   ee->context.handle,
 					   ee->context.hw_id,
-					   ee->context.ban_score);
+					   ee->context.ban_score,
+					   bannable(&ee->context));
 			err_printf(m, " --- gtt_offset = 0x%08x %08x\n",
 				   upper_32_bits(obj->gtt_offset),
 				   lower_32_bits(obj->gtt_offset));
@@ -1383,6 +1391,7 @@ static void record_context(struct drm_i915_error_context *e,
 	e->hw_id = ctx->hw_id;
 	e->priority = ctx->priority;
 	e->ban_score = atomic_read(&ctx->ban_score);
+	e->bannable = i915_gem_context_is_bannable(ctx);
 	e->guilty = atomic_read(&ctx->guilty_count);
 	e->active = atomic_read(&ctx->active_count);
 }
-- 
2.15.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

^ permalink raw reply related	[flat|nested] 4+ messages in thread