[PATCH 0/6] Fix a couple of wedge corner-case memory leaks

[PATCH 0/6] Fix a couple of wedge corner-case memory leaks

[Stuart Summers]

Most of the patches in this series are just adding
some debug hints to help track these down. I split
these up in case we want to pick and choose which ones
to include in the tree. I found them useful.

The main interesting patch is the last one in the
series which fixes some corner cases when the
driver becomes wedged in the middle of either communication
with the DRM scheduler or in the event the GuC becomes
unresponsive. In both of these cases there is a chance
we could leak memory around the exec queue members
like the LRC and the LRC BO. This patch fixes those
scenarios.

This series depends on [1].

v2: Address feedback from Matt:
    - Let the DRM scheduler handle pausing/unpausing
    - Still do the wait after scheduling disable/deregister
      as with the previous patch, but skip the intermediate
      software-based schedule disable using the "banned"
      flag and instead just jump straight to the deregister
      handling which will fully reset the queue state.
      Note that for this case I am seeing a hardware failure
      after submitting to GuC but before receiving the
      response from GuC. So even if we wedge in this case
      (monitoring the hardware state change), the queue
      itself is not wedged because of the active GuC
      submission (CT is not stalled at that point).
v3: Add back in the xe pause checks and instead just kickstart
    message handling in the guc_submi_fini() routine before
    doing the async wait there.
v4: Handle the CT communication loss during wedge asynchronously
    Also combine those last two patches into one to handle
    wedge cleanup generally.
v5: Add a new patch with a little documentation on the GuC
    submission handling stages.
    Move the scheduler kickstart and destruction call on the
    dangling queues into the wedged_fini() callback. These
    only get called now for queues which are in an error
    state - wedge was called, but these weren't fully
    cleaned up as seen by the lack of exec_queue reference
    at the time of wedging.
    Also fix the migration ordering teardown reference mistake
    pointed by Matt in the previous series rev.
v6: Implement and test against [1] with the changes Matt suggested.

[1]: https://patchwork.freedesktop.org/series/155315/

Stuart Summers (6):
  drm/xe: Add additional trace points for LRCs
  drm/xe: Add a trace point for VM close
  drm/xe: Add the BO pointer info to the BO trace
  drm/xe: Add new exec queue trace points
  drm/xe: Correct migration VM teardown order
  drm/xe: Clean up GuC software state after a wedge

 drivers/gpu/drm/xe/xe_exec_queue.c |  4 +++
 drivers/gpu/drm/xe/xe_guc_submit.c | 17 +++++++++---
 drivers/gpu/drm/xe/xe_lrc.c        |  4 +++
 drivers/gpu/drm/xe/xe_lrc.h        |  3 +++
 drivers/gpu/drm/xe/xe_migrate.c    |  7 ++---
 drivers/gpu/drm/xe/xe_trace.h      | 22 ++++++++++++++--
 drivers/gpu/drm/xe/xe_trace_bo.h   | 12 +++++++--
 drivers/gpu/drm/xe/xe_trace_lrc.h  | 42 +++++++++++++++++++++++++++++-
 drivers/gpu/drm/xe/xe_vm.c         |  2 ++
 9 files changed, 101 insertions(+), 12 deletions(-)

-- 
2.34.1

[PATCH 1/6] drm/xe: Add additional trace points for LRCs

[Stuart Summers]

Add trace points to indicate when an LRC has been
created and destroyed or get and put.

Signed-off-by: Stuart Summers <stuart.summers@intel.com>
---
 drivers/gpu/drm/xe/xe_lrc.c       |  4 +++
 drivers/gpu/drm/xe/xe_lrc.h       |  3 +++
 drivers/gpu/drm/xe/xe_trace_lrc.h | 42 ++++++++++++++++++++++++++++++-
 3 files changed, 48 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index b5083c99dd50..42d1c861fe18 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -1575,6 +1575,8 @@ struct xe_lrc *xe_lrc_create(struct xe_hw_engine *hwe, struct xe_vm *vm,
 		return ERR_PTR(err);
 	}
 
+	trace_xe_lrc_create(lrc);
+
 	return lrc;
 }
 
@@ -1589,6 +1591,8 @@ void xe_lrc_destroy(struct kref *ref)
 {
 	struct xe_lrc *lrc = container_of(ref, struct xe_lrc, refcount);
 
+	trace_xe_lrc_destroy(lrc);
+
 	xe_lrc_finish(lrc);
 	kfree(lrc);
 }
diff --git a/drivers/gpu/drm/xe/xe_lrc.h b/drivers/gpu/drm/xe/xe_lrc.h
index 2fb628da5c43..fd67810f9812 100644
--- a/drivers/gpu/drm/xe/xe_lrc.h
+++ b/drivers/gpu/drm/xe/xe_lrc.h
@@ -8,6 +8,7 @@
 #include <linux/types.h>
 
 #include "xe_lrc_types.h"
+#include "xe_trace_lrc.h"
 
 struct drm_printer;
 struct xe_bb;
@@ -61,6 +62,7 @@ void xe_lrc_destroy(struct kref *ref);
 static inline struct xe_lrc *xe_lrc_get(struct xe_lrc *lrc)
 {
 	kref_get(&lrc->refcount);
+	trace_xe_lrc_get(lrc);
 	return lrc;
 }
 
@@ -73,6 +75,7 @@ static inline struct xe_lrc *xe_lrc_get(struct xe_lrc *lrc)
  */
 static inline void xe_lrc_put(struct xe_lrc *lrc)
 {
+	trace_xe_lrc_put(lrc);
 	kref_put(&lrc->refcount, xe_lrc_destroy);
 }
 
diff --git a/drivers/gpu/drm/xe/xe_trace_lrc.h b/drivers/gpu/drm/xe/xe_trace_lrc.h
index d525cbee1e34..e8daa5d323e7 100644
--- a/drivers/gpu/drm/xe/xe_trace_lrc.h
+++ b/drivers/gpu/drm/xe/xe_trace_lrc.h
@@ -13,7 +13,6 @@
 #include <linux/types.h>
 
 #include "xe_gt_types.h"
-#include "xe_lrc.h"
 #include "xe_lrc_types.h"
 
 #define __dev_name_lrc(lrc)	dev_name(gt_to_xe((lrc)->fence_ctx.gt)->drm.dev)
@@ -42,6 +41,47 @@ TRACE_EVENT(xe_lrc_update_timestamp,
 		      __get_str(device_id))
 );
 
+DECLARE_EVENT_CLASS(xe_lrc,
+	    TP_PROTO(struct xe_lrc *lrc),
+	    TP_ARGS(lrc),
+
+	    TP_STRUCT__entry(
+		     __field(struct xe_lrc *, lrc)
+		     __string(name, lrc->fence_ctx.name)
+		     __string(device_id, __dev_name_lrc(lrc))
+	    ),
+
+	    TP_fast_assign(
+		   __entry->lrc	= lrc;
+		   __assign_str(name);
+		   __assign_str(device_id);
+		   ),
+
+	    TP_printk("lrc=:%p lrc->name=%s device_id:%s",
+		      __entry->lrc, __get_str(name),
+		      __get_str(device_id))
+);
+
+DEFINE_EVENT(xe_lrc, xe_lrc_create,
+	     TP_PROTO(struct xe_lrc *lrc),
+	     TP_ARGS(lrc)
+);
+
+DEFINE_EVENT(xe_lrc, xe_lrc_destroy,
+	     TP_PROTO(struct xe_lrc *lrc),
+	     TP_ARGS(lrc)
+);
+
+DEFINE_EVENT(xe_lrc, xe_lrc_get,
+	     TP_PROTO(struct xe_lrc *lrc),
+	     TP_ARGS(lrc)
+);
+
+DEFINE_EVENT(xe_lrc, xe_lrc_put,
+	     TP_PROTO(struct xe_lrc *lrc),
+	     TP_ARGS(lrc)
+);
+
 #endif
 
 /* This part must be outside protection */
-- 
2.34.1

Re: [PATCH 1/6] drm/xe: Add additional trace points for LRCs

[Matt Atwood]

On Mon, Oct 27, 2025 at 06:04:07PM +0000, Stuart Summers wrote:
> Add trace points to indicate when an LRC has been
> created and destroyed or get and put.
> 
> Signed-off-by: Stuart Summers <stuart.summers@intel.com>
> ---
>  drivers/gpu/drm/xe/xe_lrc.c       |  4 +++
>  drivers/gpu/drm/xe/xe_lrc.h       |  3 +++
>  drivers/gpu/drm/xe/xe_trace_lrc.h | 42 ++++++++++++++++++++++++++++++-
>  3 files changed, 48 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
> index b5083c99dd50..42d1c861fe18 100644
> --- a/drivers/gpu/drm/xe/xe_lrc.c
> +++ b/drivers/gpu/drm/xe/xe_lrc.c
> @@ -1575,6 +1575,8 @@ struct xe_lrc *xe_lrc_create(struct xe_hw_engine *hwe, struct xe_vm *vm,
>  		return ERR_PTR(err);
>  	}
>  
> +	trace_xe_lrc_create(lrc);
> +
>  	return lrc;
>  }
>  
> @@ -1589,6 +1591,8 @@ void xe_lrc_destroy(struct kref *ref)
>  {
>  	struct xe_lrc *lrc = container_of(ref, struct xe_lrc, refcount);
>  
> +	trace_xe_lrc_destroy(lrc);
> +
>  	xe_lrc_finish(lrc);
>  	kfree(lrc);
>  }
> diff --git a/drivers/gpu/drm/xe/xe_lrc.h b/drivers/gpu/drm/xe/xe_lrc.h
> index 2fb628da5c43..fd67810f9812 100644
> --- a/drivers/gpu/drm/xe/xe_lrc.h
> +++ b/drivers/gpu/drm/xe/xe_lrc.h
> @@ -8,6 +8,7 @@
>  #include <linux/types.h>
>  
>  #include "xe_lrc_types.h"
> +#include "xe_trace_lrc.h"
>  
>  struct drm_printer;
>  struct xe_bb;
> @@ -61,6 +62,7 @@ void xe_lrc_destroy(struct kref *ref);
>  static inline struct xe_lrc *xe_lrc_get(struct xe_lrc *lrc)
>  {
>  	kref_get(&lrc->refcount);
> +	trace_xe_lrc_get(lrc);
>  	return lrc;
>  }
>  
> @@ -73,6 +75,7 @@ static inline struct xe_lrc *xe_lrc_get(struct xe_lrc *lrc)
>   */
>  static inline void xe_lrc_put(struct xe_lrc *lrc)
>  {
> +	trace_xe_lrc_put(lrc);
>  	kref_put(&lrc->refcount, xe_lrc_destroy);
>  }
>  
> diff --git a/drivers/gpu/drm/xe/xe_trace_lrc.h b/drivers/gpu/drm/xe/xe_trace_lrc.h
> index d525cbee1e34..e8daa5d323e7 100644
> --- a/drivers/gpu/drm/xe/xe_trace_lrc.h
> +++ b/drivers/gpu/drm/xe/xe_trace_lrc.h
> @@ -13,7 +13,6 @@
>  #include <linux/types.h>
>  
>  #include "xe_gt_types.h"
> -#include "xe_lrc.h"
>  #include "xe_lrc_types.h"
>  
>  #define __dev_name_lrc(lrc)	dev_name(gt_to_xe((lrc)->fence_ctx.gt)->drm.dev)
> @@ -42,6 +41,47 @@ TRACE_EVENT(xe_lrc_update_timestamp,
>  		      __get_str(device_id))
>  );
>  
> +DECLARE_EVENT_CLASS(xe_lrc,
> +	    TP_PROTO(struct xe_lrc *lrc),
> +	    TP_ARGS(lrc),
> +
> +	    TP_STRUCT__entry(
This looks wrong style wise, but is done in every instance we do
anything like this. Maybe Matt Brost can chime in on why the style is
this way, and if a change is suggested it can be done in a follow up
patch.

Reviewed-by: Matt Atwood <matthew.s.atwood@intel.com>
> +		     __field(struct xe_lrc *, lrc)
> +		     __string(name, lrc->fence_ctx.name)
> +		     __string(device_id, __dev_name_lrc(lrc))
> +	    ),
> +
> +	    TP_fast_assign(
> +		   __entry->lrc	= lrc;
> +		   __assign_str(name);
> +		   __assign_str(device_id);
> +		   ),
> +
> +	    TP_printk("lrc=:%p lrc->name=%s device_id:%s",
> +		      __entry->lrc, __get_str(name),
> +		      __get_str(device_id))
> +);
> +
> +DEFINE_EVENT(xe_lrc, xe_lrc_create,
> +	     TP_PROTO(struct xe_lrc *lrc),
> +	     TP_ARGS(lrc)
> +);
> +
> +DEFINE_EVENT(xe_lrc, xe_lrc_destroy,
> +	     TP_PROTO(struct xe_lrc *lrc),
> +	     TP_ARGS(lrc)
> +);
> +
> +DEFINE_EVENT(xe_lrc, xe_lrc_get,
> +	     TP_PROTO(struct xe_lrc *lrc),
> +	     TP_ARGS(lrc)
> +);
> +
> +DEFINE_EVENT(xe_lrc, xe_lrc_put,
> +	     TP_PROTO(struct xe_lrc *lrc),
> +	     TP_ARGS(lrc)
> +);
> +
>  #endif
>  
>  /* This part must be outside protection */
> -- 
> 2.34.1
> 

Re: [PATCH 1/6] drm/xe: Add additional trace points for LRCs

[Summers, Stuart]

On Tue, 2025-10-28 at 12:46 -0700, Matt Atwood wrote:
> On Mon, Oct 27, 2025 at 06:04:07PM +0000, Stuart Summers wrote:
> > Add trace points to indicate when an LRC has been
> > created and destroyed or get and put.
> > 
> > Signed-off-by: Stuart Summers <stuart.summers@intel.com>
> > ---
> >  drivers/gpu/drm/xe/xe_lrc.c       |  4 +++
> >  drivers/gpu/drm/xe/xe_lrc.h       |  3 +++
> >  drivers/gpu/drm/xe/xe_trace_lrc.h | 42
> > ++++++++++++++++++++++++++++++-
> >  3 files changed, 48 insertions(+), 1 deletion(-)
> > 
> > diff --git a/drivers/gpu/drm/xe/xe_lrc.c
> > b/drivers/gpu/drm/xe/xe_lrc.c
> > index b5083c99dd50..42d1c861fe18 100644
> > --- a/drivers/gpu/drm/xe/xe_lrc.c
> > +++ b/drivers/gpu/drm/xe/xe_lrc.c
> > @@ -1575,6 +1575,8 @@ struct xe_lrc *xe_lrc_create(struct
> > xe_hw_engine *hwe, struct xe_vm *vm,
> >                 return ERR_PTR(err);
> >         }
> >  
> > +       trace_xe_lrc_create(lrc);
> > +
> >         return lrc;
> >  }
> >  
> > @@ -1589,6 +1591,8 @@ void xe_lrc_destroy(struct kref *ref)
> >  {
> >         struct xe_lrc *lrc = container_of(ref, struct xe_lrc,
> > refcount);
> >  
> > +       trace_xe_lrc_destroy(lrc);
> > +
> >         xe_lrc_finish(lrc);
> >         kfree(lrc);
> >  }
> > diff --git a/drivers/gpu/drm/xe/xe_lrc.h
> > b/drivers/gpu/drm/xe/xe_lrc.h
> > index 2fb628da5c43..fd67810f9812 100644
> > --- a/drivers/gpu/drm/xe/xe_lrc.h
> > +++ b/drivers/gpu/drm/xe/xe_lrc.h
> > @@ -8,6 +8,7 @@
> >  #include <linux/types.h>
> >  
> >  #include "xe_lrc_types.h"
> > +#include "xe_trace_lrc.h"
> >  
> >  struct drm_printer;
> >  struct xe_bb;
> > @@ -61,6 +62,7 @@ void xe_lrc_destroy(struct kref *ref);
> >  static inline struct xe_lrc *xe_lrc_get(struct xe_lrc *lrc)
> >  {
> >         kref_get(&lrc->refcount);
> > +       trace_xe_lrc_get(lrc);
> >         return lrc;
> >  }
> >  
> > @@ -73,6 +75,7 @@ static inline struct xe_lrc *xe_lrc_get(struct
> > xe_lrc *lrc)
> >   */
> >  static inline void xe_lrc_put(struct xe_lrc *lrc)
> >  {
> > +       trace_xe_lrc_put(lrc);
> >         kref_put(&lrc->refcount, xe_lrc_destroy);
> >  }
> >  
> > diff --git a/drivers/gpu/drm/xe/xe_trace_lrc.h
> > b/drivers/gpu/drm/xe/xe_trace_lrc.h
> > index d525cbee1e34..e8daa5d323e7 100644
> > --- a/drivers/gpu/drm/xe/xe_trace_lrc.h
> > +++ b/drivers/gpu/drm/xe/xe_trace_lrc.h
> > @@ -13,7 +13,6 @@
> >  #include <linux/types.h>
> >  
> >  #include "xe_gt_types.h"
> > -#include "xe_lrc.h"
> >  #include "xe_lrc_types.h"
> >  
> >  #define __dev_name_lrc(lrc)    dev_name(gt_to_xe((lrc)-
> > >fence_ctx.gt)->drm.dev)
> > @@ -42,6 +41,47 @@ TRACE_EVENT(xe_lrc_update_timestamp,
> >                       __get_str(device_id))
> >  );
> >  
> > +DECLARE_EVENT_CLASS(xe_lrc,
> > +           TP_PROTO(struct xe_lrc *lrc),
> > +           TP_ARGS(lrc),
> > +
> > +           TP_STRUCT__entry(
> This looks wrong style wise, but is done in every instance we do
> anything like this. Maybe Matt Brost can chime in on why the style is
> this way, and if a change is suggested it can be done in a follow up
> patch.

Yeah I had taken this from one of the existing tracefs entries. I agree
it doesn't look right. I'd like to pull that out separately though if
possible.

> 
> Reviewed-by: Matt Atwood <matthew.s.atwood@intel.com>

Thanks for the review!

-Stuart

> > +                    __field(struct xe_lrc *, lrc)
> > +                    __string(name, lrc->fence_ctx.name)
> > +                    __string(device_id, __dev_name_lrc(lrc))
> > +           ),
> > +
> > +           TP_fast_assign(
> > +                  __entry->lrc = lrc;
> > +                  __assign_str(name);
> > +                  __assign_str(device_id);
> > +                  ),
> > +
> > +           TP_printk("lrc=:%p lrc->name=%s device_id:%s",
> > +                     __entry->lrc, __get_str(name),
> > +                     __get_str(device_id))
> > +);
> > +
> > +DEFINE_EVENT(xe_lrc, xe_lrc_create,
> > +            TP_PROTO(struct xe_lrc *lrc),
> > +            TP_ARGS(lrc)
> > +);
> > +
> > +DEFINE_EVENT(xe_lrc, xe_lrc_destroy,
> > +            TP_PROTO(struct xe_lrc *lrc),
> > +            TP_ARGS(lrc)
> > +);
> > +
> > +DEFINE_EVENT(xe_lrc, xe_lrc_get,
> > +            TP_PROTO(struct xe_lrc *lrc),
> > +            TP_ARGS(lrc)
> > +);
> > +
> > +DEFINE_EVENT(xe_lrc, xe_lrc_put,
> > +            TP_PROTO(struct xe_lrc *lrc),
> > +            TP_ARGS(lrc)
> > +);
> > +
> >  #endif
> >  
> >  /* This part must be outside protection */
> > -- 
> > 2.34.1
> > 

[PATCH 2/6] drm/xe: Add a trace point for VM close

[Stuart Summers]

All better tracking of error cases when calling through
xe_vm_close_and_put().

Signed-off-by: Stuart Summers <stuart.summers@intel.com>
---
 drivers/gpu/drm/xe/xe_trace_bo.h | 6 ++++++
 drivers/gpu/drm/xe/xe_vm.c       | 2 ++
 2 files changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_trace_bo.h b/drivers/gpu/drm/xe/xe_trace_bo.h
index 86323cf3be2c..238311cfb816 100644
--- a/drivers/gpu/drm/xe/xe_trace_bo.h
+++ b/drivers/gpu/drm/xe/xe_trace_bo.h
@@ -14,6 +14,7 @@
 
 #include "xe_bo.h"
 #include "xe_bo_types.h"
+#include "xe_exec_queue_types.h"
 #include "xe_vm.h"
 
 #define __dev_name_bo(bo)	dev_name(xe_bo_device(bo)->drm.dev)
@@ -223,6 +224,11 @@ DEFINE_EVENT(xe_vm, xe_vm_free,
 	     TP_ARGS(vm)
 );
 
+DEFINE_EVENT(xe_vm, xe_vm_close,
+	     TP_PROTO(struct xe_vm *vm),
+	     TP_ARGS(vm)
+);
+
 DEFINE_EVENT(xe_vm, xe_vm_cpu_bind,
 	     TP_PROTO(struct xe_vm *vm),
 	     TP_ARGS(vm)
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 00f3520dec38..e383982bad8a 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -1672,6 +1672,8 @@ static void xe_vm_close(struct xe_vm *vm)
 	bool bound;
 	int idx;
 
+	trace_xe_vm_close(vm);
+
 	bound = drm_dev_enter(&xe->drm, &idx);
 
 	down_write(&vm->lock);
-- 
2.34.1

Re: [PATCH 2/6] drm/xe: Add a trace point for VM close

[Matt Atwood]

On Mon, Oct 27, 2025 at 06:04:08PM +0000, Stuart Summers wrote:
> All better tracking of error cases when calling through
s/all/add
> xe_vm_close_and_put().
> 
> Signed-off-by: Stuart Summers <stuart.summers@intel.com>
> ---
>  drivers/gpu/drm/xe/xe_trace_bo.h | 6 ++++++
>  drivers/gpu/drm/xe/xe_vm.c       | 2 ++
>  2 files changed, 8 insertions(+)
> 
> diff --git a/drivers/gpu/drm/xe/xe_trace_bo.h b/drivers/gpu/drm/xe/xe_trace_bo.h
> index 86323cf3be2c..238311cfb816 100644
> --- a/drivers/gpu/drm/xe/xe_trace_bo.h
> +++ b/drivers/gpu/drm/xe/xe_trace_bo.h
> @@ -14,6 +14,7 @@
>  
>  #include "xe_bo.h"
>  #include "xe_bo_types.h"
> +#include "xe_exec_queue_types.h"
This doesnt appear to be required for this patch and should be included
in the patch titled "Add new exec queue trace points".

With its removal.

Reviewed-by: Matt Atwood <matthew.s.atwood@intel.com>
>  #include "xe_vm.h"
>  
>  #define __dev_name_bo(bo)	dev_name(xe_bo_device(bo)->drm.dev)
> @@ -223,6 +224,11 @@ DEFINE_EVENT(xe_vm, xe_vm_free,
>  	     TP_ARGS(vm)
>  );
>  
> +DEFINE_EVENT(xe_vm, xe_vm_close,
> +	     TP_PROTO(struct xe_vm *vm),
> +	     TP_ARGS(vm)
> +);
> +
>  DEFINE_EVENT(xe_vm, xe_vm_cpu_bind,
>  	     TP_PROTO(struct xe_vm *vm),
>  	     TP_ARGS(vm)
> diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
> index 00f3520dec38..e383982bad8a 100644
> --- a/drivers/gpu/drm/xe/xe_vm.c
> +++ b/drivers/gpu/drm/xe/xe_vm.c
> @@ -1672,6 +1672,8 @@ static void xe_vm_close(struct xe_vm *vm)
>  	bool bound;
>  	int idx;
>  
> +	trace_xe_vm_close(vm);
> +
>  	bound = drm_dev_enter(&xe->drm, &idx);
>  
>  	down_write(&vm->lock);
> -- 
> 2.34.1
> 

Re: [PATCH 2/6] drm/xe: Add a trace point for VM close

[Summers, Stuart]

On Tue, 2025-10-28 at 13:03 -0700, Matt Atwood wrote:
> On Mon, Oct 27, 2025 at 06:04:08PM +0000, Stuart Summers wrote:
> > All better tracking of error cases when calling through
> s/all/add

Ok

> > xe_vm_close_and_put().
> > 
> > Signed-off-by: Stuart Summers <stuart.summers@intel.com>
> > ---
> >  drivers/gpu/drm/xe/xe_trace_bo.h | 6 ++++++
> >  drivers/gpu/drm/xe/xe_vm.c       | 2 ++
> >  2 files changed, 8 insertions(+)
> > 
> > diff --git a/drivers/gpu/drm/xe/xe_trace_bo.h
> > b/drivers/gpu/drm/xe/xe_trace_bo.h
> > index 86323cf3be2c..238311cfb816 100644
> > --- a/drivers/gpu/drm/xe/xe_trace_bo.h
> > +++ b/drivers/gpu/drm/xe/xe_trace_bo.h
> > @@ -14,6 +14,7 @@
> >  
> >  #include "xe_bo.h"
> >  #include "xe_bo_types.h"
> > +#include "xe_exec_queue_types.h"
> This doesnt appear to be required for this patch and should be
> included
> in the patch titled "Add new exec queue trace points".

Hm.. yeah this must have been held over from some debug I was doing.
Sorry about that! I'll make sure to clean these things up in the next
post.

Thanks,
Stuart

> 
> With its removal.
> 
> Reviewed-by: Matt Atwood <matthew.s.atwood@intel.com>
> >  #include "xe_vm.h"
> >  
> >  #define __dev_name_bo(bo)      dev_name(xe_bo_device(bo)->drm.dev)
> > @@ -223,6 +224,11 @@ DEFINE_EVENT(xe_vm, xe_vm_free,
> >              TP_ARGS(vm)
> >  );
> >  
> > +DEFINE_EVENT(xe_vm, xe_vm_close,
> > +            TP_PROTO(struct xe_vm *vm),
> > +            TP_ARGS(vm)
> > +);
> > +
> >  DEFINE_EVENT(xe_vm, xe_vm_cpu_bind,
> >              TP_PROTO(struct xe_vm *vm),
> >              TP_ARGS(vm)
> > diff --git a/drivers/gpu/drm/xe/xe_vm.c
> > b/drivers/gpu/drm/xe/xe_vm.c
> > index 00f3520dec38..e383982bad8a 100644
> > --- a/drivers/gpu/drm/xe/xe_vm.c
> > +++ b/drivers/gpu/drm/xe/xe_vm.c
> > @@ -1672,6 +1672,8 @@ static void xe_vm_close(struct xe_vm *vm)
> >         bool bound;
> >         int idx;
> >  
> > +       trace_xe_vm_close(vm);
> > +
> >         bound = drm_dev_enter(&xe->drm, &idx);
> >  
> >         down_write(&vm->lock);
> > -- 
> > 2.34.1
> > 

[PATCH 3/6] drm/xe: Add the BO pointer info to the BO trace

[Stuart Summers]

Just a little extra detail to make BOs easier to track
through the trace event log.

Signed-off-by: Stuart Summers <stuart.summers@intel.com>
---
 drivers/gpu/drm/xe/xe_trace_bo.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_trace_bo.h b/drivers/gpu/drm/xe/xe_trace_bo.h
index 238311cfb816..0d795733e0f0 100644
--- a/drivers/gpu/drm/xe/xe_trace_bo.h
+++ b/drivers/gpu/drm/xe/xe_trace_bo.h
@@ -27,6 +27,7 @@ DECLARE_EVENT_CLASS(xe_bo,
 
 		    TP_STRUCT__entry(
 			     __string(dev, __dev_name_bo(bo))
+			     __field(struct xe_bo *, bo)
 			     __field(size_t, size)
 			     __field(u32, flags)
 			     __field(struct xe_vm *, vm)
@@ -34,13 +35,14 @@ DECLARE_EVENT_CLASS(xe_bo,
 
 		    TP_fast_assign(
 			   __assign_str(dev);
+			   __entry->bo = bo;
 			   __entry->size = xe_bo_size(bo);
 			   __entry->flags = bo->flags;
 			   __entry->vm = bo->vm;
 			   ),
 
-		    TP_printk("dev=%s, size=%zu, flags=0x%02x, vm=%p",
-			      __get_str(dev), __entry->size,
+		    TP_printk("dev=%s, %p, size=%zu, flags=0x%02x, vm=%p",
+			      __get_str(dev), __entry->bo, __entry->size,
 			      __entry->flags, __entry->vm)
 );
 
-- 
2.34.1

Re: [PATCH 3/6] drm/xe: Add the BO pointer info to the BO trace

[Matt Atwood]

On Mon, Oct 27, 2025 at 06:04:09PM +0000, Stuart Summers wrote:
> Just a little extra detail to make BOs easier to track
> through the trace event log.
> 
Reviewed-by: Matt Atwood <matthew.s.atwood@intel.com>
> Signed-off-by: Stuart Summers <stuart.summers@intel.com>
> ---
>  drivers/gpu/drm/xe/xe_trace_bo.h | 6 ++++--
>  1 file changed, 4 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_trace_bo.h b/drivers/gpu/drm/xe/xe_trace_bo.h
> index 238311cfb816..0d795733e0f0 100644
> --- a/drivers/gpu/drm/xe/xe_trace_bo.h
> +++ b/drivers/gpu/drm/xe/xe_trace_bo.h
> @@ -27,6 +27,7 @@ DECLARE_EVENT_CLASS(xe_bo,
>  
>  		    TP_STRUCT__entry(
>  			     __string(dev, __dev_name_bo(bo))
> +			     __field(struct xe_bo *, bo)
>  			     __field(size_t, size)
>  			     __field(u32, flags)
>  			     __field(struct xe_vm *, vm)
> @@ -34,13 +35,14 @@ DECLARE_EVENT_CLASS(xe_bo,
>  
>  		    TP_fast_assign(
>  			   __assign_str(dev);
> +			   __entry->bo = bo;
>  			   __entry->size = xe_bo_size(bo);
>  			   __entry->flags = bo->flags;
>  			   __entry->vm = bo->vm;
>  			   ),
>  
> -		    TP_printk("dev=%s, size=%zu, flags=0x%02x, vm=%p",
> -			      __get_str(dev), __entry->size,
> +		    TP_printk("dev=%s, %p, size=%zu, flags=0x%02x, vm=%p",
> +			      __get_str(dev), __entry->bo, __entry->size,
>  			      __entry->flags, __entry->vm)
>  );
>  
> -- 
> 2.34.1
> 

[PATCH 4/6] drm/xe: Add new exec queue trace points

[Stuart Summers]

Add an exec queue and guc exec queue trace point
to separate out which part of the stack is executing.

This is helpful because several of the guc specific
paths rely on responses from guc which is interesting
to view separately in the event the guc stops responding
in the middle of an operation that would expect a
response from guc otherwise.

Also add in the exec queue pointer information to
the trace events for easier tracking. Contexts (guc_ids)
can get re-used, so this just makes grepping a little
easier in this type of debug.

Signed-off-by: Stuart Summers <stuart.summers@intel.com>
---
 drivers/gpu/drm/xe/xe_exec_queue.c |  4 ++++
 drivers/gpu/drm/xe/xe_guc_submit.c | 11 +++++++----
 drivers/gpu/drm/xe/xe_trace.h      | 22 ++++++++++++++++++++--
 3 files changed, 31 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 90cbc95f8e2e..a2ef381cf6d9 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -377,6 +377,8 @@ void xe_exec_queue_destroy(struct kref *ref)
 	struct xe_exec_queue *q = container_of(ref, struct xe_exec_queue, refcount);
 	struct xe_exec_queue *eq, *next;
 
+	trace_xe_exec_queue_destroy(q);
+
 	if (xe_exec_queue_uses_pxp(q))
 		xe_pxp_exec_queue_remove(gt_to_xe(q->gt)->pxp, q);
 
@@ -953,6 +955,8 @@ void xe_exec_queue_kill(struct xe_exec_queue *q)
 {
 	struct xe_exec_queue *eq = q, *next;
 
+	trace_xe_exec_queue_kill(q);
+
 	list_for_each_entry_safe(eq, next, &eq->multi_gt_list,
 				 multi_gt_link) {
 		q->ops->kill(eq);
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index d4ffdb71ef3d..3f672355b3bb 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1004,9 +1004,12 @@ void xe_guc_submit_wedge(struct xe_guc *guc)
 	}
 
 	mutex_lock(&guc->submission_state.lock);
-	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q)
-		if (xe_exec_queue_get_unless_zero(q))
+	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) {
+		if (xe_exec_queue_get_unless_zero(q)) {
 			set_exec_queue_wedged(q);
+			trace_xe_exec_queue_wedge(q);
+		}
+	}
 	mutex_unlock(&guc->submission_state.lock);
 }
 
@@ -1456,7 +1459,7 @@ static void __guc_exec_queue_destroy_async(struct work_struct *w)
 	struct xe_guc *guc = exec_queue_to_guc(q);
 
 	xe_pm_runtime_get(guc_to_xe(guc));
-	trace_xe_exec_queue_destroy(q);
+	trace_xe_guc_exec_queue_destroy(q);
 
 	if (xe_exec_queue_is_lr(q))
 		cancel_work_sync(&ge->lr_tdr);
@@ -1727,7 +1730,7 @@ static int guc_exec_queue_init(struct xe_exec_queue *q)
 
 static void guc_exec_queue_kill(struct xe_exec_queue *q)
 {
-	trace_xe_exec_queue_kill(q);
+	trace_xe_guc_exec_queue_kill(q);
 	set_exec_queue_killed(q);
 	__suspend_fence_signal(q);
 	xe_guc_exec_queue_trigger_cleanup(q);
diff --git a/drivers/gpu/drm/xe/xe_trace.h b/drivers/gpu/drm/xe/xe_trace.h
index 314f42fcbcbd..a5dd0c48d894 100644
--- a/drivers/gpu/drm/xe/xe_trace.h
+++ b/drivers/gpu/drm/xe/xe_trace.h
@@ -71,6 +71,7 @@ DECLARE_EVENT_CLASS(xe_exec_queue,
 
 		    TP_STRUCT__entry(
 			     __string(dev, __dev_name_eq(q))
+			     __field(struct xe_exec_queue *, q)
 			     __field(enum xe_engine_class, class)
 			     __field(u32, logical_mask)
 			     __field(u8, gt_id)
@@ -82,6 +83,7 @@ DECLARE_EVENT_CLASS(xe_exec_queue,
 
 		    TP_fast_assign(
 			   __assign_str(dev);
+			   __entry->q = q;
 			   __entry->class = q->class;
 			   __entry->logical_mask = q->logical_mask;
 			   __entry->gt_id = q->gt->info.id;
@@ -91,8 +93,9 @@ DECLARE_EVENT_CLASS(xe_exec_queue,
 			   __entry->flags = q->flags;
 			   ),
 
-		    TP_printk("dev=%s, %d:0x%x, gt=%d, width=%d, guc_id=%d, guc_state=0x%x, flags=0x%x",
-			      __get_str(dev), __entry->class, __entry->logical_mask,
+		    TP_printk("dev=%s, %p, %d:0x%x, gt=%d, width=%d, guc_id=%d, guc_state=0x%x, flags=0x%x",
+			      __get_str(dev), __entry->q,
+			      __entry->class, __entry->logical_mask,
 			      __entry->gt_id, __entry->width, __entry->guc_id,
 			      __entry->guc_state, __entry->flags)
 );
@@ -147,11 +150,21 @@ DEFINE_EVENT(xe_exec_queue, xe_exec_queue_close,
 	     TP_ARGS(q)
 );
 
+DEFINE_EVENT(xe_exec_queue, xe_exec_queue_wedge,
+	     TP_PROTO(struct xe_exec_queue *q),
+	     TP_ARGS(q)
+);
+
 DEFINE_EVENT(xe_exec_queue, xe_exec_queue_kill,
 	     TP_PROTO(struct xe_exec_queue *q),
 	     TP_ARGS(q)
 );
 
+DEFINE_EVENT(xe_exec_queue, xe_guc_exec_queue_kill,
+	     TP_PROTO(struct xe_exec_queue *q),
+	     TP_ARGS(q)
+);
+
 DEFINE_EVENT(xe_exec_queue, xe_exec_queue_cleanup_entity,
 	     TP_PROTO(struct xe_exec_queue *q),
 	     TP_ARGS(q)
@@ -162,6 +175,11 @@ DEFINE_EVENT(xe_exec_queue, xe_exec_queue_destroy,
 	     TP_ARGS(q)
 );
 
+DEFINE_EVENT(xe_exec_queue, xe_guc_exec_queue_destroy,
+	     TP_PROTO(struct xe_exec_queue *q),
+	     TP_ARGS(q)
+);
+
 DEFINE_EVENT(xe_exec_queue, xe_exec_queue_reset,
 	     TP_PROTO(struct xe_exec_queue *q),
 	     TP_ARGS(q)
-- 
2.34.1

Re: [PATCH 4/6] drm/xe: Add new exec queue trace points

[Matt Atwood]

On Mon, Oct 27, 2025 at 06:04:10PM +0000, Stuart Summers wrote:
> Add an exec queue and guc exec queue trace point
> to separate out which part of the stack is executing.
> 
> This is helpful because several of the guc specific
> paths rely on responses from guc which is interesting
> to view separately in the event the guc stops responding
> in the middle of an operation that would expect a
> response from guc otherwise.
> 
> Also add in the exec queue pointer information to
> the trace events for easier tracking. Contexts (guc_ids)
> can get re-used, so this just makes grepping a little
> easier in this type of debug.
> 
Reviewed-by: Matt Atwood <matthew.s.atwood@intel.com>
> Signed-off-by: Stuart Summers <stuart.summers@intel.com>
> ---
>  drivers/gpu/drm/xe/xe_exec_queue.c |  4 ++++
>  drivers/gpu/drm/xe/xe_guc_submit.c | 11 +++++++----
>  drivers/gpu/drm/xe/xe_trace.h      | 22 ++++++++++++++++++++--
>  3 files changed, 31 insertions(+), 6 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
> index 90cbc95f8e2e..a2ef381cf6d9 100644
> --- a/drivers/gpu/drm/xe/xe_exec_queue.c
> +++ b/drivers/gpu/drm/xe/xe_exec_queue.c
> @@ -377,6 +377,8 @@ void xe_exec_queue_destroy(struct kref *ref)
>  	struct xe_exec_queue *q = container_of(ref, struct xe_exec_queue, refcount);
>  	struct xe_exec_queue *eq, *next;
>  
> +	trace_xe_exec_queue_destroy(q);
> +
>  	if (xe_exec_queue_uses_pxp(q))
>  		xe_pxp_exec_queue_remove(gt_to_xe(q->gt)->pxp, q);
>  
> @@ -953,6 +955,8 @@ void xe_exec_queue_kill(struct xe_exec_queue *q)
>  {
>  	struct xe_exec_queue *eq = q, *next;
>  
> +	trace_xe_exec_queue_kill(q);
> +
>  	list_for_each_entry_safe(eq, next, &eq->multi_gt_list,
>  				 multi_gt_link) {
>  		q->ops->kill(eq);
> diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
> index d4ffdb71ef3d..3f672355b3bb 100644
> --- a/drivers/gpu/drm/xe/xe_guc_submit.c
> +++ b/drivers/gpu/drm/xe/xe_guc_submit.c
> @@ -1004,9 +1004,12 @@ void xe_guc_submit_wedge(struct xe_guc *guc)
>  	}
>  
>  	mutex_lock(&guc->submission_state.lock);
> -	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q)
> -		if (xe_exec_queue_get_unless_zero(q))
> +	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) {
> +		if (xe_exec_queue_get_unless_zero(q)) {
>  			set_exec_queue_wedged(q);
> +			trace_xe_exec_queue_wedge(q);
> +		}
> +	}
>  	mutex_unlock(&guc->submission_state.lock);
>  }
>  
> @@ -1456,7 +1459,7 @@ static void __guc_exec_queue_destroy_async(struct work_struct *w)
>  	struct xe_guc *guc = exec_queue_to_guc(q);
>  
>  	xe_pm_runtime_get(guc_to_xe(guc));
> -	trace_xe_exec_queue_destroy(q);
> +	trace_xe_guc_exec_queue_destroy(q);
>  
>  	if (xe_exec_queue_is_lr(q))
>  		cancel_work_sync(&ge->lr_tdr);
> @@ -1727,7 +1730,7 @@ static int guc_exec_queue_init(struct xe_exec_queue *q)
>  
>  static void guc_exec_queue_kill(struct xe_exec_queue *q)
>  {
> -	trace_xe_exec_queue_kill(q);
> +	trace_xe_guc_exec_queue_kill(q);
>  	set_exec_queue_killed(q);
>  	__suspend_fence_signal(q);
>  	xe_guc_exec_queue_trigger_cleanup(q);
> diff --git a/drivers/gpu/drm/xe/xe_trace.h b/drivers/gpu/drm/xe/xe_trace.h
> index 314f42fcbcbd..a5dd0c48d894 100644
> --- a/drivers/gpu/drm/xe/xe_trace.h
> +++ b/drivers/gpu/drm/xe/xe_trace.h
> @@ -71,6 +71,7 @@ DECLARE_EVENT_CLASS(xe_exec_queue,
>  
>  		    TP_STRUCT__entry(
>  			     __string(dev, __dev_name_eq(q))
> +			     __field(struct xe_exec_queue *, q)
>  			     __field(enum xe_engine_class, class)
>  			     __field(u32, logical_mask)
>  			     __field(u8, gt_id)
> @@ -82,6 +83,7 @@ DECLARE_EVENT_CLASS(xe_exec_queue,
>  
>  		    TP_fast_assign(
>  			   __assign_str(dev);
> +			   __entry->q = q;
>  			   __entry->class = q->class;
>  			   __entry->logical_mask = q->logical_mask;
>  			   __entry->gt_id = q->gt->info.id;
> @@ -91,8 +93,9 @@ DECLARE_EVENT_CLASS(xe_exec_queue,
>  			   __entry->flags = q->flags;
>  			   ),
>  
> -		    TP_printk("dev=%s, %d:0x%x, gt=%d, width=%d, guc_id=%d, guc_state=0x%x, flags=0x%x",
> -			      __get_str(dev), __entry->class, __entry->logical_mask,
> +		    TP_printk("dev=%s, %p, %d:0x%x, gt=%d, width=%d, guc_id=%d, guc_state=0x%x, flags=0x%x",
> +			      __get_str(dev), __entry->q,
> +			      __entry->class, __entry->logical_mask,
>  			      __entry->gt_id, __entry->width, __entry->guc_id,
>  			      __entry->guc_state, __entry->flags)
>  );
> @@ -147,11 +150,21 @@ DEFINE_EVENT(xe_exec_queue, xe_exec_queue_close,
>  	     TP_ARGS(q)
>  );
>  
> +DEFINE_EVENT(xe_exec_queue, xe_exec_queue_wedge,
> +	     TP_PROTO(struct xe_exec_queue *q),
> +	     TP_ARGS(q)
> +);
> +
>  DEFINE_EVENT(xe_exec_queue, xe_exec_queue_kill,
>  	     TP_PROTO(struct xe_exec_queue *q),
>  	     TP_ARGS(q)
>  );
>  
> +DEFINE_EVENT(xe_exec_queue, xe_guc_exec_queue_kill,
> +	     TP_PROTO(struct xe_exec_queue *q),
> +	     TP_ARGS(q)
> +);
> +
>  DEFINE_EVENT(xe_exec_queue, xe_exec_queue_cleanup_entity,
>  	     TP_PROTO(struct xe_exec_queue *q),
>  	     TP_ARGS(q)
> @@ -162,6 +175,11 @@ DEFINE_EVENT(xe_exec_queue, xe_exec_queue_destroy,
>  	     TP_ARGS(q)
>  );
>  
> +DEFINE_EVENT(xe_exec_queue, xe_guc_exec_queue_destroy,
> +	     TP_PROTO(struct xe_exec_queue *q),
> +	     TP_ARGS(q)
> +);
> +
>  DEFINE_EVENT(xe_exec_queue, xe_exec_queue_reset,
>  	     TP_PROTO(struct xe_exec_queue *q),
>  	     TP_ARGS(q)
> -- 
> 2.34.1
> 

[PATCH 5/6] drm/xe: Correct migration VM teardown order

[Stuart Summers]

Adjust the sequence of the migration teardown to match what
is happening in the init() function.

v2: Take a reference to the migrate queue before put (Matt)

Signed-off-by: Stuart Summers <stuart.summers@intel.com>
---
 drivers/gpu/drm/xe/xe_migrate.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 56a5804726e9..9d60bc2b57e4 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -98,17 +98,18 @@ struct xe_migrate {
 static void xe_migrate_fini(void *arg)
 {
 	struct xe_migrate *m = arg;
+	struct xe_vm *vm = m->q->vm;
 
-	xe_vm_lock(m->q->vm, false);
+	xe_vm_lock(vm, false);
 	xe_bo_unpin(m->pt_bo);
-	xe_vm_unlock(m->q->vm);
+	xe_vm_unlock(vm);
 
 	dma_fence_put(m->fence);
 	xe_bo_put(m->pt_bo);
 	drm_suballoc_manager_fini(&m->vm_update_sa);
 	mutex_destroy(&m->job_mutex);
-	xe_vm_close_and_put(m->q->vm);
 	xe_exec_queue_put(m->q);
+	xe_vm_close_and_put(vm);
 }
 
 static u64 xe_migrate_vm_addr(u64 slot, u32 level)
-- 
2.34.1

Re: [PATCH 5/6] drm/xe: Correct migration VM teardown order

[Matthew Brost]

On Mon, Oct 27, 2025 at 06:04:11PM +0000, Stuart Summers wrote:
> Adjust the sequence of the migration teardown to match what
> is happening in the init() function.
> 
> v2: Take a reference to the migrate queue before put (Matt)
> 
> Signed-off-by: Stuart Summers <stuart.summers@intel.com>

Reviewed-by: Matthew Brost <matthew.brost@intel.com>

> ---
>  drivers/gpu/drm/xe/xe_migrate.c | 7 ++++---
>  1 file changed, 4 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
> index 56a5804726e9..9d60bc2b57e4 100644
> --- a/drivers/gpu/drm/xe/xe_migrate.c
> +++ b/drivers/gpu/drm/xe/xe_migrate.c
> @@ -98,17 +98,18 @@ struct xe_migrate {
>  static void xe_migrate_fini(void *arg)
>  {
>  	struct xe_migrate *m = arg;
> +	struct xe_vm *vm = m->q->vm;
>  
> -	xe_vm_lock(m->q->vm, false);
> +	xe_vm_lock(vm, false);
>  	xe_bo_unpin(m->pt_bo);
> -	xe_vm_unlock(m->q->vm);
> +	xe_vm_unlock(vm);
>  
>  	dma_fence_put(m->fence);
>  	xe_bo_put(m->pt_bo);
>  	drm_suballoc_manager_fini(&m->vm_update_sa);
>  	mutex_destroy(&m->job_mutex);
> -	xe_vm_close_and_put(m->q->vm);
>  	xe_exec_queue_put(m->q);
> +	xe_vm_close_and_put(vm);
>  }
>  
>  static u64 xe_migrate_vm_addr(u64 slot, u32 level)
> -- 
> 2.34.1
> 

[PATCH 6/6] drm/xe: Clean up GuC software state after a wedge

[Stuart Summers]

When the driver is wedged during a hardware failure, there
is a chance the queue kill coming from those events can
race with either the scheduler teardown or the queue
deregistration with GuC. Basically the following two
scenarios can occur (from event trace):

Scheduler start missing:
  xe_exec_queue_create
  xe_exec_queue_kill
  xe_guc_exec_queue_kill
  xe_exec_queue_destroy

GuC CT response missing:
  xe_exec_queue_create
  xe_exec_queue_register
  xe_exec_queue_scheduling_enable
  xe_exec_queue_scheduling_done
  xe_exec_queue_kill
  xe_guc_exec_queue_kill
  xe_exec_queue_close
  xe_exec_queue_destroy
  xe_exec_queue_cleanup_entity
  xe_exec_queue_scheduling_disable

The above traces depend also on inclusion of [1].

In the first scenario, the queue is created, but killed
prior to completing the message cleanup. In the second,
we go through a full registration before killing. The
CT communication happens in that last call to
xe_exec_queue_scheduling_disable.

We expect to then get a call to xe_guc_exec_queue_destroy
in both cases if the aforementioned scheduler/GuC CT communication
had happened, which we are missing here, hence missing any
LRC/BO cleanup in the exec queues in question.

Once the scheduler rework in [2] is available, simply ensure
all queues are either marked as wedged or cleaned up
explicitly by destroying any remaining registered queues.

Without this change, if we inject wedges in the above scenarios
we can expect the following when the DRM memory tracking is
enabled (see CONFIG_DRM_DEBUG_MM):
[  129.600285] [drm:drm_mm_takedown] *ERROR* node [00647000 + 00008000]: inserted at
                drm_mm_insert_node_in_range+0x2ec/0x4b0
                __xe_ggtt_insert_bo_at+0x10f/0x360 [xe]
                __xe_bo_create_locked+0x184/0x520 [xe]
                xe_bo_create_pin_map_at_aligned+0x3b/0x180 [xe]
                xe_bo_create_pin_map+0x13/0x20 [xe]
                xe_lrc_create+0x139/0x18e0 [xe]
                xe_exec_queue_create+0x22f/0x3e0 [xe]
                xe_exec_queue_create_ioctl+0x4e9/0xbf0 [xe]
                drm_ioctl_kernel+0x9f/0xf0
                drm_ioctl+0x20f/0x440
                xe_drm_ioctl+0x121/0x150 [xe]
                __x64_sys_ioctl+0x8c/0xe0
                do_syscall_64+0x4c/0x1d0
                entry_SYSCALL_64_after_hwframe+0x76/0x7e
[  129.601966] [drm:drm_mm_takedown] *ERROR* node [0064f000 + 00008000]: inserted at
                drm_mm_insert_node_in_range+0x2ec/0x4b0
                __xe_ggtt_insert_bo_at+0x10f/0x360 [xe]
                __xe_bo_create_locked+0x184/0x520 [xe]
                xe_bo_create_pin_map_at_aligned+0x3b/0x180 [xe]
                xe_bo_create_pin_map+0x13/0x20 [xe]
                xe_lrc_create+0x139/0x18e0 [xe]
                xe_exec_queue_create+0x22f/0x3e0 [xe]
                xe_exec_queue_create_bind+0x7f/0xd0 [xe]
                xe_vm_create+0x4aa/0x8b0 [xe]
                xe_vm_create_ioctl+0x17b/0x420 [xe]
                drm_ioctl_kernel+0x9f/0xf0
                drm_ioctl+0x20f/0x440
                xe_drm_ioctl+0x121/0x150 [xe]
                __x64_sys_ioctl+0x8c/0xe0
                do_syscall_64+0x4c/0x1d0
                entry_SYSCALL_64_after_hwframe+0x76/0x7e

v2: Pulled in [2] as suggested by Matt and used his recommendation
    of destroying registered queues at the time of wedging.

Signed-off-by: Stuart Summers <stuart.summers@intel.com>

[1] https://patchwork.freedesktop.org/patch/680852/?series=155352&rev=4
[2] https://patchwork.freedesktop.org/series/155315/
---
 drivers/gpu/drm/xe/xe_guc_submit.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 3f672355b3bb..dc26aa4b5f47 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -296,6 +296,8 @@ static void guc_submit_wedged_fini(void *arg)
 
 	mutex_lock(&guc->submission_state.lock);
 	xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) {
+		xe_gt_assert(guc_to_gt(guc),
+			     !drm_sched_is_stopped(&q->guc->sched.base));
 		if (exec_queue_wedged(q)) {
 			mutex_unlock(&guc->submission_state.lock);
 			xe_exec_queue_put(q);
@@ -972,6 +974,8 @@ static void xe_guc_exec_queue_trigger_cleanup(struct xe_exec_queue *q)
 		xe_sched_tdr_queue_imm(&q->guc->sched);
 }
 
+static void __guc_exec_queue_destroy(struct xe_guc *guc, struct xe_exec_queue *q);
+
 /**
  * xe_guc_submit_wedge() - Wedge GuC submission
  * @guc: the GuC object
@@ -1008,6 +1012,8 @@ void xe_guc_submit_wedge(struct xe_guc *guc)
 		if (xe_exec_queue_get_unless_zero(q)) {
 			set_exec_queue_wedged(q);
 			trace_xe_exec_queue_wedge(q);
+		} else if (exec_queue_registered(q)) {
+			__guc_exec_queue_destroy(guc, q);
 		}
 	}
 	mutex_unlock(&guc->submission_state.lock);
-- 
2.34.1

✗ CI.checkpatch: warning for Fix a couple of wedge corner-case memory leaks (rev6)

[Patchwork]

== Series Details ==

Series: Fix a couple of wedge corner-case memory leaks (rev6)
URL   : https://patchwork.freedesktop.org/series/155352/
State : warning

== Summary ==

+ KERNEL=/kernel
+ git clone https://gitlab.freedesktop.org/drm/maintainer-tools mt
Cloning into 'mt'...
warning: redirecting to https://gitlab.freedesktop.org/drm/maintainer-tools.git/
+ git -C mt rev-list -n1 origin/master
f867e605613af1770f90c4b0afd4a8f06424d1f0
+ cd /kernel
+ git config --global --add safe.directory /kernel
+ git log -n1
commit c0b9b8ebd244f28b48397d561698ee61161b2d59
Author: Stuart Summers <stuart.summers@intel.com>
Date:   Mon Oct 27 18:04:12 2025 +0000

    drm/xe: Clean up GuC software state after a wedge
    
    When the driver is wedged during a hardware failure, there
    is a chance the queue kill coming from those events can
    race with either the scheduler teardown or the queue
    deregistration with GuC. Basically the following two
    scenarios can occur (from event trace):
    
    Scheduler start missing:
      xe_exec_queue_create
      xe_exec_queue_kill
      xe_guc_exec_queue_kill
      xe_exec_queue_destroy
    
    GuC CT response missing:
      xe_exec_queue_create
      xe_exec_queue_register
      xe_exec_queue_scheduling_enable
      xe_exec_queue_scheduling_done
      xe_exec_queue_kill
      xe_guc_exec_queue_kill
      xe_exec_queue_close
      xe_exec_queue_destroy
      xe_exec_queue_cleanup_entity
      xe_exec_queue_scheduling_disable
    
    The above traces depend also on inclusion of [1].
    
    In the first scenario, the queue is created, but killed
    prior to completing the message cleanup. In the second,
    we go through a full registration before killing. The
    CT communication happens in that last call to
    xe_exec_queue_scheduling_disable.
    
    We expect to then get a call to xe_guc_exec_queue_destroy
    in both cases if the aforementioned scheduler/GuC CT communication
    had happened, which we are missing here, hence missing any
    LRC/BO cleanup in the exec queues in question.
    
    Once the scheduler rework in [2] is available, simply ensure
    all queues are either marked as wedged or cleaned up
    explicitly by destroying any remaining registered queues.
    
    Without this change, if we inject wedges in the above scenarios
    we can expect the following when the DRM memory tracking is
    enabled (see CONFIG_DRM_DEBUG_MM):
    [  129.600285] [drm:drm_mm_takedown] *ERROR* node [00647000 + 00008000]: inserted at
                    drm_mm_insert_node_in_range+0x2ec/0x4b0
                    __xe_ggtt_insert_bo_at+0x10f/0x360 [xe]
                    __xe_bo_create_locked+0x184/0x520 [xe]
                    xe_bo_create_pin_map_at_aligned+0x3b/0x180 [xe]
                    xe_bo_create_pin_map+0x13/0x20 [xe]
                    xe_lrc_create+0x139/0x18e0 [xe]
                    xe_exec_queue_create+0x22f/0x3e0 [xe]
                    xe_exec_queue_create_ioctl+0x4e9/0xbf0 [xe]
                    drm_ioctl_kernel+0x9f/0xf0
                    drm_ioctl+0x20f/0x440
                    xe_drm_ioctl+0x121/0x150 [xe]
                    __x64_sys_ioctl+0x8c/0xe0
                    do_syscall_64+0x4c/0x1d0
                    entry_SYSCALL_64_after_hwframe+0x76/0x7e
    [  129.601966] [drm:drm_mm_takedown] *ERROR* node [0064f000 + 00008000]: inserted at
                    drm_mm_insert_node_in_range+0x2ec/0x4b0
                    __xe_ggtt_insert_bo_at+0x10f/0x360 [xe]
                    __xe_bo_create_locked+0x184/0x520 [xe]
                    xe_bo_create_pin_map_at_aligned+0x3b/0x180 [xe]
                    xe_bo_create_pin_map+0x13/0x20 [xe]
                    xe_lrc_create+0x139/0x18e0 [xe]
                    xe_exec_queue_create+0x22f/0x3e0 [xe]
                    xe_exec_queue_create_bind+0x7f/0xd0 [xe]
                    xe_vm_create+0x4aa/0x8b0 [xe]
                    xe_vm_create_ioctl+0x17b/0x420 [xe]
                    drm_ioctl_kernel+0x9f/0xf0
                    drm_ioctl+0x20f/0x440
                    xe_drm_ioctl+0x121/0x150 [xe]
                    __x64_sys_ioctl+0x8c/0xe0
                    do_syscall_64+0x4c/0x1d0
                    entry_SYSCALL_64_after_hwframe+0x76/0x7e
    
    v2: Pulled in [2] as suggested by Matt and used his recommendation
        of destroying registered queues at the time of wedging.
    
    Signed-off-by: Stuart Summers <stuart.summers@intel.com>
    
    [1] https://patchwork.freedesktop.org/patch/680852/?series=155352&rev=4
    [2] https://patchwork.freedesktop.org/series/155315/
+ /mt/dim checkpatch a8f3783a2ccf78b04e48cf235f03629b80ffa3e0 drm-intel
70d334d19aff drm/xe: Add additional trace points for LRCs
-:78: CHECK:PARENTHESIS_ALIGNMENT: Alignment should match open parenthesis
#78: FILE: drivers/gpu/drm/xe/xe_trace_lrc.h:45:
+DECLARE_EVENT_CLASS(xe_lrc,
+	    TP_PROTO(struct xe_lrc *lrc),

-:81: CHECK:OPEN_ENDED_LINE: Lines should not end with a '('
#81: FILE: drivers/gpu/drm/xe/xe_trace_lrc.h:48:
+	    TP_STRUCT__entry(

-:87: CHECK:OPEN_ENDED_LINE: Lines should not end with a '('
#87: FILE: drivers/gpu/drm/xe/xe_trace_lrc.h:54:
+	    TP_fast_assign(

total: 0 errors, 0 warnings, 3 checks, 91 lines checked
a71482bd2861 drm/xe: Add a trace point for VM close
53265f817012 drm/xe: Add the BO pointer info to the BO trace
1c2eb0f97314 drm/xe: Add new exec queue trace points
b98f6625fd40 drm/xe: Correct migration VM teardown order
c0b9b8ebd244 drm/xe: Clean up GuC software state after a wedge

✗ CI.KUnit: failure for Fix a couple of wedge corner-case memory leaks (rev6)

[Patchwork]

== Series Details ==

Series: Fix a couple of wedge corner-case memory leaks (rev6)
URL   : https://patchwork.freedesktop.org/series/155352/
State : failure

== Summary ==

+ trap cleanup EXIT
+ /kernel/tools/testing/kunit/kunit.py run --kunitconfig /kernel/drivers/gpu/drm/xe/.kunitconfig
ERROR:root:In file included from ../include/linux/bitfield.h:10,
                 from ../drivers/gpu/drm/xe/xe_guc_submit.c:8:
../drivers/gpu/drm/xe/xe_guc_submit.c: In function ‘guc_submit_wedged_fini’:
../drivers/gpu/drm/xe/xe_guc_submit.c:300:31: error: implicit declaration of function ‘drm_sched_is_stopped’; did you mean ‘drm_sched_stop’? [-Werror=implicit-function-declaration]
  300 |                              !drm_sched_is_stopped(&q->guc->sched.base));
      |                               ^~~~~~~~~~~~~~~~~~~~
../include/linux/build_bug.h:30:63: note: in definition of macro ‘BUILD_BUG_ON_INVALID’
   30 | #define BUILD_BUG_ON_INVALID(e) ((void)(sizeof((__force long)(e))))
      |                                                               ^
../drivers/gpu/drm/xe/xe_assert.h:112:9: note: in expansion of macro ‘__xe_assert_msg’
  112 |         __xe_assert_msg(__xe, condition,                                                        \
      |         ^~~~~~~~~~~~~~~
../drivers/gpu/drm/xe/xe_assert.h:148:9: note: in expansion of macro ‘xe_assert_msg’
  148 |         xe_assert_msg(tile_to_xe(__tile), condition, "tile: %u VRAM %s\n" msg,                  \
      |         ^~~~~~~~~~~~~
../drivers/gpu/drm/xe/xe_assert.h:172:9: note: in expansion of macro ‘xe_tile_assert_msg’
  172 |         xe_tile_assert_msg(gt_to_tile(__gt), condition, "GT: %u type %d\n" msg,                 \
      |         ^~~~~~~~~~~~~~~~~~
../drivers/gpu/drm/xe/xe_assert.h:169:37: note: in expansion of macro ‘xe_gt_assert_msg’
  169 | #define xe_gt_assert(gt, condition) xe_gt_assert_msg((gt), condition, "")
      |                                     ^~~~~~~~~~~~~~~~
../drivers/gpu/drm/xe/xe_guc_submit.c:299:17: note: in expansion of macro ‘xe_gt_assert’
  299 |                 xe_gt_assert(guc_to_gt(guc),
      |                 ^~~~~~~~~~~~
cc1: some warnings being treated as errors
make[7]: *** [../scripts/Makefile.build:287: drivers/gpu/drm/xe/xe_guc_submit.o] Error 1
make[7]: *** Waiting for unfinished jobs....
make[6]: *** [../scripts/Makefile.build:556: drivers/gpu/drm/xe] Error 2
make[5]: *** [../scripts/Makefile.build:556: drivers/gpu/drm] Error 2
make[4]: *** [../scripts/Makefile.build:556: drivers/gpu] Error 2
make[3]: *** [../scripts/Makefile.build:556: drivers] Error 2
make[2]: *** [/kernel/Makefile:2010: .] Error 2
make[1]: *** [/kernel/Makefile:248: __sub-make] Error 2
make: *** [Makefile:248: __sub-make] Error 2

[18:16:47] Configuring KUnit Kernel ...
Generating .config ...
Populating config with:
$ make ARCH=um O=.kunit olddefconfig
[18:16:51] Building KUnit Kernel ...
Populating config with:
$ make ARCH=um O=.kunit olddefconfig
Building with:
$ make all compile_commands.json scripts_gdb ARCH=um O=.kunit --jobs=48
+ cleanup
++ stat -c %u:%g /kernel
+ chown -R 1003:1003 /kernel

Re: CI.KUnit: failure for Fix a couple of wedge corner-case memory leaks (rev6)

[Summers, Stuart]

On Mon, 2025-10-27 at 18:17 +0000, Patchwork wrote:
> == Series Details ==
> 
> Series: Fix a couple of wedge corner-case memory leaks (rev6)
> URL   : https://patchwork.freedesktop.org/series/155352/
> State : failure
> 
> == Summary ==
> 
> + trap cleanup EXIT
> + /kernel/tools/testing/kunit/kunit.py run --kunitconfig
> /kernel/drivers/gpu/drm/xe/.kunitconfig
> ERROR:root:In file included from ../include/linux/bitfield.h:10,
>                  from ../drivers/gpu/drm/xe/xe_guc_submit.c:8:
> ../drivers/gpu/drm/xe/xe_guc_submit.c: In function
> ‘guc_submit_wedged_fini’:
> ../drivers/gpu/drm/xe/xe_guc_submit.c:300:31: error: implicit
> declaration of function ‘drm_sched_is_stopped’; did you mean
> ‘drm_sched_stop’? [-Werror=implicit-function-declaration]

Hm.. I didn't see this when testing locally. I'll double check here.

-Stuart

>   300 |                              !drm_sched_is_stopped(&q->guc-
> >sched.base));
>       |                               ^~~~~~~~~~~~~~~~~~~~
> ../include/linux/build_bug.h:30:63: note: in definition of macro
> ‘BUILD_BUG_ON_INVALID’
>    30 | #define BUILD_BUG_ON_INVALID(e) ((void)(sizeof((__force
> long)(e))))
>       |                                                              
> ^
> ../drivers/gpu/drm/xe/xe_assert.h:112:9: note: in expansion of macro
> ‘__xe_assert_msg’
>   112 |         __xe_assert_msg(__xe,
> condition,                                                        \
>       |         ^~~~~~~~~~~~~~~
> ../drivers/gpu/drm/xe/xe_assert.h:148:9: note: in expansion of macro
> ‘xe_assert_msg’
>   148 |         xe_assert_msg(tile_to_xe(__tile), condition, "tile:
> %u VRAM %s\n" msg,                  \
>       |         ^~~~~~~~~~~~~
> ../drivers/gpu/drm/xe/xe_assert.h:172:9: note: in expansion of macro
> ‘xe_tile_assert_msg’
>   172 |         xe_tile_assert_msg(gt_to_tile(__gt), condition, "GT:
> %u type %d\n" msg,                 \
>       |         ^~~~~~~~~~~~~~~~~~
> ../drivers/gpu/drm/xe/xe_assert.h:169:37: note: in expansion of macro
> ‘xe_gt_assert_msg’
>   169 | #define xe_gt_assert(gt, condition) xe_gt_assert_msg((gt),
> condition, "")
>       |                                     ^~~~~~~~~~~~~~~~
> ../drivers/gpu/drm/xe/xe_guc_submit.c:299:17: note: in expansion of
> macro ‘xe_gt_assert’
>   299 |                 xe_gt_assert(guc_to_gt(guc),
>       |                 ^~~~~~~~~~~~
> cc1: some warnings being treated as errors
> make[7]: *** [../scripts/Makefile.build:287:
> drivers/gpu/drm/xe/xe_guc_submit.o] Error 1
> make[7]: *** Waiting for unfinished jobs....
> make[6]: *** [../scripts/Makefile.build:556: drivers/gpu/drm/xe]
> Error 2
> make[5]: *** [../scripts/Makefile.build:556: drivers/gpu/drm] Error 2
> make[4]: *** [../scripts/Makefile.build:556: drivers/gpu] Error 2
> make[3]: *** [../scripts/Makefile.build:556: drivers] Error 2
> make[2]: *** [/kernel/Makefile:2010: .] Error 2
> make[1]: *** [/kernel/Makefile:248: __sub-make] Error 2
> make: *** [Makefile:248: __sub-make] Error 2
> 
> [18:16:47] Configuring KUnit Kernel ...
> Generating .config ...
> Populating config with:
> $ make ARCH=um O=.kunit olddefconfig
> [18:16:51] Building KUnit Kernel ...
> Populating config with:
> $ make ARCH=um O=.kunit olddefconfig
> Building with:
> $ make all compile_commands.json scripts_gdb ARCH=um O=.kunit --
> jobs=48
> + cleanup
> ++ stat -c %u:%g /kernel
> + chown -R 1003:1003 /kernel
> 
> 

Re: CI.KUnit: failure for Fix a couple of wedge corner-case memory leaks (rev6)

[Summers, Stuart]

On Mon, 2025-10-27 at 18:18 +0000, Summers, Stuart wrote:
> On Mon, 2025-10-27 at 18:17 +0000, Patchwork wrote:
> > == Series Details ==
> > 
> > Series: Fix a couple of wedge corner-case memory leaks (rev6)
> > URL   : https://patchwork.freedesktop.org/series/155352/
> > State : failure
> > 
> > == Summary ==
> > 
> > + trap cleanup EXIT
> > + /kernel/tools/testing/kunit/kunit.py run --kunitconfig
> > /kernel/drivers/gpu/drm/xe/.kunitconfig
> > ERROR:root:In file included from ../include/linux/bitfield.h:10,
> >                  from ../drivers/gpu/drm/xe/xe_guc_submit.c:8:
> > ../drivers/gpu/drm/xe/xe_guc_submit.c: In function
> > ‘guc_submit_wedged_fini’:
> > ../drivers/gpu/drm/xe/xe_guc_submit.c:300:31: error: implicit
> > declaration of function ‘drm_sched_is_stopped’; did you mean
> > ‘drm_sched_stop’? [-Werror=implicit-function-declaration]
> 
> Hm.. I didn't see this when testing locally. I'll double check here.

Ah right, this comes with
https://patchwork.freedesktop.org/patch/681606/?series=155315&rev=3
which isn't available yet. I'm working on reviewing that series as
well. I still think it's worth getting feedback on this series in
parallel, but let me know if there are any concerns there.

Thanks,
Stuart

> 
> -Stuart
> 
> >   300 |                              !drm_sched_is_stopped(&q->guc-
> > > sched.base));
> >       |                               ^~~~~~~~~~~~~~~~~~~~
> > ../include/linux/build_bug.h:30:63: note: in definition of macro
> > ‘BUILD_BUG_ON_INVALID’
> >    30 | #define BUILD_BUG_ON_INVALID(e) ((void)(sizeof((__force
> > long)(e))))
> >      
> > |                                                              
> > ^
> > ../drivers/gpu/drm/xe/xe_assert.h:112:9: note: in expansion of
> > macro
> > ‘__xe_assert_msg’
> >   112 |         __xe_assert_msg(__xe,
> > condition,                                                        \
> >       |         ^~~~~~~~~~~~~~~
> > ../drivers/gpu/drm/xe/xe_assert.h:148:9: note: in expansion of
> > macro
> > ‘xe_assert_msg’
> >   148 |         xe_assert_msg(tile_to_xe(__tile), condition, "tile:
> > %u VRAM %s\n" msg,                  \
> >       |         ^~~~~~~~~~~~~
> > ../drivers/gpu/drm/xe/xe_assert.h:172:9: note: in expansion of
> > macro
> > ‘xe_tile_assert_msg’
> >   172 |         xe_tile_assert_msg(gt_to_tile(__gt), condition,
> > "GT:
> > %u type %d\n" msg,                 \
> >       |         ^~~~~~~~~~~~~~~~~~
> > ../drivers/gpu/drm/xe/xe_assert.h:169:37: note: in expansion of
> > macro
> > ‘xe_gt_assert_msg’
> >   169 | #define xe_gt_assert(gt, condition) xe_gt_assert_msg((gt),
> > condition, "")
> >       |                                     ^~~~~~~~~~~~~~~~
> > ../drivers/gpu/drm/xe/xe_guc_submit.c:299:17: note: in expansion of
> > macro ‘xe_gt_assert’
> >   299 |                 xe_gt_assert(guc_to_gt(guc),
> >       |                 ^~~~~~~~~~~~
> > cc1: some warnings being treated as errors
> > make[7]: *** [../scripts/Makefile.build:287:
> > drivers/gpu/drm/xe/xe_guc_submit.o] Error 1
> > make[7]: *** Waiting for unfinished jobs....
> > make[6]: *** [../scripts/Makefile.build:556: drivers/gpu/drm/xe]
> > Error 2
> > make[5]: *** [../scripts/Makefile.build:556: drivers/gpu/drm] Error
> > 2
> > make[4]: *** [../scripts/Makefile.build:556: drivers/gpu] Error 2
> > make[3]: *** [../scripts/Makefile.build:556: drivers] Error 2
> > make[2]: *** [/kernel/Makefile:2010: .] Error 2
> > make[1]: *** [/kernel/Makefile:248: __sub-make] Error 2
> > make: *** [Makefile:248: __sub-make] Error 2
> > 
> > [18:16:47] Configuring KUnit Kernel ...
> > Generating .config ...
> > Populating config with:
> > $ make ARCH=um O=.kunit olddefconfig
> > [18:16:51] Building KUnit Kernel ...
> > Populating config with:
> > $ make ARCH=um O=.kunit olddefconfig
> > Building with:
> > $ make all compile_commands.json scripts_gdb ARCH=um O=.kunit --
> > jobs=48
> > + cleanup
> > ++ stat -c %u:%g /kernel
> > + chown -R 1003:1003 /kernel
> > 
> > 
> 

[PATCH 0/6] Fix a couple of wedge corner-case memory leaks

[Stuart Summers]

Most of the patches in this series are just adding
some debug hints to help track these down. I split
these up in case we want to pick and choose which ones
to include in the tree. I found them useful.

The main two interesting patches are the last two in the
series which are fixing some corner cases when the
driver becomes wedged in the middle of either communication
with the DRM scheduler or in the event the GuC becomes
unresponsive. In both of these cases there is a chance
we could leak memory around the exec queue members
like the LRC and the LRC BO. These patches fix those
scenarios.

v2: Address feedback from Matt:
    - Let the DRM scheduler handle pausing/unpausing
    - Still do the wait after scheduling disable/deregister
      as with the previous patch, but skip the intermediate
      software-based schedule disable using the "banned"
      flag and instead just jump straight to the deregister
      handling which will fully reset the queue state.
      Note that for this case I am seeing a hardware failure
      after submitting to GuC but before receiving the
      response from GuC. So even if we wedge in this case
      (monitoring the hardware state change), the queue
      itself is not wedged because of the active GuC
      submission (CT is not stalled at that point).
v3: Add back in the xe pause checks and instead just kickstart
    message handling in the guc_submi_fini() routine before
    doing the async wait there.
v4: Handle the CT communication loss during wedge asynchronously
    Also combine those last two patches into one to handle
    wedge cleanup generally.

Stuart Summers (6):
  drm/xe: Add additional trace points for LRCs
  drm/xe: Add a trace point for VM close
  drm/xe: Add the BO pointer info to the BO trace
  drm/xe: Add new exec queue trace points
  drm/xe: Correct migration VM teardown order
  drm/xe: Clean up GuC software state after a wedge

 drivers/gpu/drm/xe/xe_exec_queue.c |  4 +++
 drivers/gpu/drm/xe/xe_guc_submit.c | 26 +++++++++++++++---
 drivers/gpu/drm/xe/xe_lrc.c        |  4 +++
 drivers/gpu/drm/xe/xe_lrc.h        |  3 +++
 drivers/gpu/drm/xe/xe_migrate.c    |  2 +-
 drivers/gpu/drm/xe/xe_trace.h      | 22 ++++++++++++++--
 drivers/gpu/drm/xe/xe_trace_bo.h   | 12 +++++++--
 drivers/gpu/drm/xe/xe_trace_lrc.h  | 42 +++++++++++++++++++++++++++++-
 drivers/gpu/drm/xe/xe_vm.c         |  2 ++
 9 files changed, 107 insertions(+), 10 deletions(-)

-- 
2.34.1

[PATCH 1/6] drm/xe: Add additional trace points for LRCs

[Stuart Summers]

Add trace points to indicate when an LRC has been
created and destroyed or get and put.

Signed-off-by: Stuart Summers <stuart.summers@intel.com>
---
 drivers/gpu/drm/xe/xe_lrc.c       |  4 +++
 drivers/gpu/drm/xe/xe_lrc.h       |  3 +++
 drivers/gpu/drm/xe/xe_trace_lrc.h | 42 ++++++++++++++++++++++++++++++-
 3 files changed, 48 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index b5083c99dd50..42d1c861fe18 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -1575,6 +1575,8 @@ struct xe_lrc *xe_lrc_create(struct xe_hw_engine *hwe, struct xe_vm *vm,
 		return ERR_PTR(err);
 	}
 
+	trace_xe_lrc_create(lrc);
+
 	return lrc;
 }
 
@@ -1589,6 +1591,8 @@ void xe_lrc_destroy(struct kref *ref)
 {
 	struct xe_lrc *lrc = container_of(ref, struct xe_lrc, refcount);
 
+	trace_xe_lrc_destroy(lrc);
+
 	xe_lrc_finish(lrc);
 	kfree(lrc);
 }
diff --git a/drivers/gpu/drm/xe/xe_lrc.h b/drivers/gpu/drm/xe/xe_lrc.h
index 2fb628da5c43..fd67810f9812 100644
--- a/drivers/gpu/drm/xe/xe_lrc.h
+++ b/drivers/gpu/drm/xe/xe_lrc.h
@@ -8,6 +8,7 @@
 #include <linux/types.h>
 
 #include "xe_lrc_types.h"
+#include "xe_trace_lrc.h"
 
 struct drm_printer;
 struct xe_bb;
@@ -61,6 +62,7 @@ void xe_lrc_destroy(struct kref *ref);
 static inline struct xe_lrc *xe_lrc_get(struct xe_lrc *lrc)
 {
 	kref_get(&lrc->refcount);
+	trace_xe_lrc_get(lrc);
 	return lrc;
 }
 
@@ -73,6 +75,7 @@ static inline struct xe_lrc *xe_lrc_get(struct xe_lrc *lrc)
  */
 static inline void xe_lrc_put(struct xe_lrc *lrc)
 {
+	trace_xe_lrc_put(lrc);
 	kref_put(&lrc->refcount, xe_lrc_destroy);
 }
 
diff --git a/drivers/gpu/drm/xe/xe_trace_lrc.h b/drivers/gpu/drm/xe/xe_trace_lrc.h
index d525cbee1e34..e8daa5d323e7 100644
--- a/drivers/gpu/drm/xe/xe_trace_lrc.h
+++ b/drivers/gpu/drm/xe/xe_trace_lrc.h
@@ -13,7 +13,6 @@
 #include <linux/types.h>
 
 #include "xe_gt_types.h"
-#include "xe_lrc.h"
 #include "xe_lrc_types.h"
 
 #define __dev_name_lrc(lrc)	dev_name(gt_to_xe((lrc)->fence_ctx.gt)->drm.dev)
@@ -42,6 +41,47 @@ TRACE_EVENT(xe_lrc_update_timestamp,
 		      __get_str(device_id))
 );
 
+DECLARE_EVENT_CLASS(xe_lrc,
+	    TP_PROTO(struct xe_lrc *lrc),
+	    TP_ARGS(lrc),
+
+	    TP_STRUCT__entry(
+		     __field(struct xe_lrc *, lrc)
+		     __string(name, lrc->fence_ctx.name)
+		     __string(device_id, __dev_name_lrc(lrc))
+	    ),
+
+	    TP_fast_assign(
+		   __entry->lrc	= lrc;
+		   __assign_str(name);
+		   __assign_str(device_id);
+		   ),
+
+	    TP_printk("lrc=:%p lrc->name=%s device_id:%s",
+		      __entry->lrc, __get_str(name),
+		      __get_str(device_id))
+);
+
+DEFINE_EVENT(xe_lrc, xe_lrc_create,
+	     TP_PROTO(struct xe_lrc *lrc),
+	     TP_ARGS(lrc)
+);
+
+DEFINE_EVENT(xe_lrc, xe_lrc_destroy,
+	     TP_PROTO(struct xe_lrc *lrc),
+	     TP_ARGS(lrc)
+);
+
+DEFINE_EVENT(xe_lrc, xe_lrc_get,
+	     TP_PROTO(struct xe_lrc *lrc),
+	     TP_ARGS(lrc)
+);
+
+DEFINE_EVENT(xe_lrc, xe_lrc_put,
+	     TP_PROTO(struct xe_lrc *lrc),
+	     TP_ARGS(lrc)
+);
+
 #endif
 
 /* This part must be outside protection */
-- 
2.34.1