Re: [Intel-gfx] [PATCH 35/47] drm/i915/guc: Handle context reset notification

2021-07-14 Thread Matthew Brost 
On Mon, Jul 12, 2021 at 03:58:12PM -0700, John Harrison wrote:
> On 6/24/2021 00:05, 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.
> > 
> > Cc: Matthew Brost 
> > Cc: John Harrison 
> > Signed-off-by: Matthew Brost 
> > ---
> >   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 | 35 +++
> >   drivers/gpu/drm/i915/i915_trace.h | 10 ++
> >   4 files changed, 50 insertions(+)
> > 
> > diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h 
> > b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
> > index 85ef6767f13b..e94b0ef733da 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);
> >   void intel_guc_submission_reset_prepare(struct intel_guc *guc);
> >   void intel_guc_submission_reset(struct intel_guc *guc, bool stalled);
> > 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 4ed074df88e5..a2020373b8e8 100644
> > --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
> > +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
> > @@ -945,6 +945,9 @@ 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;
> > default:
> > ret = -EOPNOTSUPP;
> > 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 16b61fe71b07..9845c5bd9832 100644
> > --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> > +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
> > @@ -2192,6 +2192,41 @@ 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(_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 = msg[0];
> Should do this dereference after checking the length? Or is it guaranteed
> that the length cannot be zero?
> 

I think for safety, it should be moved.

Matt

> John.
> 
> > +
> > +   if (unlikely(len != 1)) {
> > +   drm_dbg(_to_gt(guc)->i915->drm, "Invalid length %u", len);
> > +   return -EPROTO;
> > +   }
> > +
> > +   ce = g2h_context_lookup(guc, desc_idx);
> > +   if (unlikely(!ce))
> > +   return -EPROTO;
> > +
> > +   guc_handle_context_reset(guc, ce);
> > +
> > +   return 0;
> > +}
> > +
> >   void intel_guc_log_submission_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)
> >   {
>

Re: [Intel-gfx] [PATCH 35/47] drm/i915/guc: Handle context reset notification

2021-07-12 Thread John Harrison 

On 6/24/2021 00:05, 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.

Cc: Matthew Brost 
Cc: John Harrison 
Signed-off-by: Matthew Brost 
---
  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 | 35 +++
  drivers/gpu/drm/i915/i915_trace.h | 10 ++
  4 files changed, 50 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h 
b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
index 85ef6767f13b..e94b0ef733da 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);
  
  void intel_guc_submission_reset_prepare(struct intel_guc *guc);

  void intel_guc_submission_reset(struct intel_guc *guc, bool stalled);
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 4ed074df88e5..a2020373b8e8 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
@@ -945,6 +945,9 @@ 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;
default:
ret = -EOPNOTSUPP;
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 16b61fe71b07..9845c5bd9832 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -2192,6 +2192,41 @@ 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(_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 = msg[0];
Should do this dereference after checking the length? Or is it 
guaranteed that the length cannot be zero?


John.


+
+   if (unlikely(len != 1)) {
+   drm_dbg(_to_gt(guc)->i915->drm, "Invalid length %u", len);
+   return -EPROTO;
+   }
+
+   ce = g2h_context_lookup(guc, desc_idx);
+   if (unlikely(!ce))
+   return -EPROTO;
+
+   guc_handle_context_reset(guc, ce);
+
+   return 0;
+}
+
  void intel_guc_log_submission_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)
  {


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

[Intel-gfx] [PATCH 35/47] drm/i915/guc: Handle context reset notification

2021-06-24 Thread Matthew Brost 
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.

Cc: Matthew Brost 
Cc: John Harrison 
Signed-off-by: Matthew Brost 
---
 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 | 35 +++
 drivers/gpu/drm/i915/i915_trace.h | 10 ++
 4 files changed, 50 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h 
b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
index 85ef6767f13b..e94b0ef733da 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);
 
 void intel_guc_submission_reset_prepare(struct intel_guc *guc);
 void intel_guc_submission_reset(struct intel_guc *guc, bool stalled);
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 4ed074df88e5..a2020373b8e8 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
@@ -945,6 +945,9 @@ 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;
default:
ret = -EOPNOTSUPP;
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 16b61fe71b07..9845c5bd9832 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -2192,6 +2192,41 @@ 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(_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 = msg[0];
+
+   if (unlikely(len != 1)) {
+   drm_dbg(_to_gt(guc)->i915->drm, "Invalid length %u", len);
+   return -EPROTO;
+   }
+
+   ce = g2h_context_lookup(guc, desc_idx);
+   if (unlikely(!ce))
+   return -EPROTO;
+
+   guc_handle_context_reset(guc, ce);
+
+   return 0;
+}
+
 void intel_guc_log_submission_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)
 {
-- 
2.28.0

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