On Tue, Jul 20, 2021 at 01:29:26PM -0700, John Harrison wrote:
On 7/16/2021 13:17, Matthew Brost wrote:
GuC will issue a reset on detecting an engine hang and will notify the driver via a G2H message. The driver will service the notification by resetting the guilty context to a simple state or banning it completely.
v2: (John Harrison)
- Move msg[0] lookup after length check
Cc: Matthew Brost matthew.brost@intel.com Cc: John Harrison John.C.Harrison@Intel.com Signed-off-by: Matthew Brost matthew.brost@intel.com
drivers/gpu/drm/i915/gt/uc/intel_guc.h | 2 ++ drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c | 3 ++ .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 36 +++++++++++++++++++ drivers/gpu/drm/i915/i915_trace.h | 10 ++++++ 4 files changed, 51 insertions(+)
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h index b3cfc52fe0bc..f23a3a618550 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h @@ -262,6 +262,8 @@ int intel_guc_deregister_done_process_msg(struct intel_guc *guc, const u32 *msg, u32 len); int intel_guc_sched_done_process_msg(struct intel_guc *guc, const u32 *msg, u32 len); +int intel_guc_context_reset_process_msg(struct intel_guc *guc,
const u32 *msg, u32 len);diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c index 503a78517610..c4f9b44b9f86 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c @@ -981,6 +981,9 @@ static int ct_process_request(struct intel_guc_ct *ct, struct ct_incoming_msg *r case INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_DONE: ret = intel_guc_sched_done_process_msg(guc, payload, len); break;
- case INTEL_GUC_ACTION_CONTEXT_RESET_NOTIFICATION:
ret = intel_guc_context_reset_process_msg(guc, payload, len);break;diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index fdb17279095c..feaf1ca61eaa 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -2196,6 +2196,42 @@ int intel_guc_sched_done_process_msg(struct intel_guc *guc, return 0; } +static void guc_context_replay(struct intel_context *ce) +{
- struct i915_sched_engine *sched_engine = ce->engine->sched_engine;
- __guc_reset_context(ce, true);
- tasklet_hi_schedule(&sched_engine->tasklet);
+}
+static void guc_handle_context_reset(struct intel_guc *guc,
struct intel_context *ce)+{
- trace_intel_context_reset(ce);
- guc_context_replay(ce);
+}
+int intel_guc_context_reset_process_msg(struct intel_guc *guc,
const u32 *msg, u32 len)+{
- struct intel_context *ce;
- int desc_idx;
- if (unlikely(len != 1)) {
drm_dbg(&guc_to_gt(guc)->i915->drm, "Invalid length %u", len);I think we decided that these should be drm_err rather than drm_dbg?
Yes, we did. Already fixed this message and all subsequent in my branch.
Matt
With that updated: Reviewed-by: John Harrison John.C.Harrison@Intel.com
return -EPROTO;- }
- desc_idx = msg[0];
- ce = g2h_context_lookup(guc, desc_idx);
- if (unlikely(!ce))
return -EPROTO;- guc_handle_context_reset(guc, ce);
- return 0;
+}
- void intel_guc_submission_print_info(struct intel_guc *guc, struct drm_printer *p) {
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h index 97c2e83984ed..c095c4d39456 100644 --- a/drivers/gpu/drm/i915/i915_trace.h +++ b/drivers/gpu/drm/i915/i915_trace.h @@ -929,6 +929,11 @@ DECLARE_EVENT_CLASS(intel_context, __entry->guc_sched_state_no_lock) ); +DEFINE_EVENT(intel_context, intel_context_reset,
TP_PROTO(struct intel_context *ce),TP_ARGS(ce)+);
- DEFINE_EVENT(intel_context, intel_context_register, TP_PROTO(struct intel_context *ce), TP_ARGS(ce)
@@ -1026,6 +1031,11 @@ trace_i915_request_out(struct i915_request *rq) { } +static inline void +trace_intel_context_reset(struct intel_context *ce) +{ +}
- static inline void trace_intel_context_register(struct intel_context *ce) {