[PATCH v2 0/7] Devcoredump Improvements

[PATCH v2 0/7] Devcoredump Improvements

[Matthew Brost]

Mainly enabling devcoredump for LR queues. Missing is engine capture
from Zhanjun worked on to find one manually or from the GuC. Can be done
in a follow up.

Matt

Matthew Brost (7):
  drm/xe: Add xe_ring_lrc_is_idle() helper
  drm/xe: Remove redundant rebind from preempt rebind worker
  drm/xe: Add ring address to LRC snapshot
  drm/xe: Add ring start to LRC snapshot
  drm/xe: Improve schedule disable response failure
  drm/xe: Add exec queue param to devcoredump
  drm/xe: Change xe_engine_snapshot_capture_for_job to be for queue

 drivers/gpu/drm/xe/xe_devcoredump.c       | 16 ++++++-------
 drivers/gpu/drm/xe/xe_devcoredump.h       |  6 +++--
 drivers/gpu/drm/xe/xe_devcoredump_types.h |  2 --
 drivers/gpu/drm/xe/xe_guc_capture.c       | 29 ++++++++++-------------
 drivers/gpu/drm/xe/xe_guc_capture.h       |  6 ++---
 drivers/gpu/drm/xe/xe_guc_submit.c        | 13 ++++++----
 drivers/gpu/drm/xe/xe_hw_engine.c         |  8 +++----
 drivers/gpu/drm/xe/xe_hw_engine.h         |  4 ++--
 drivers/gpu/drm/xe/xe_lrc.c               | 26 ++++++++++++++++++++
 drivers/gpu/drm/xe/xe_lrc.h               |  4 ++++
 drivers/gpu/drm/xe/xe_vm.c                |  4 ----
 11 files changed, 71 insertions(+), 47 deletions(-)

-- 
2.34.1

[PATCH v2 1/7] drm/xe: Add xe_ring_lrc_is_idle() helper

[Matthew Brost]

Add helper to compare ring head and tail to determine if LRC is idle.

v2:
 - Fix kernel doc (CI, Zhanjun)

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
---
 drivers/gpu/drm/xe/xe_guc_submit.c |  2 +-
 drivers/gpu/drm/xe/xe_lrc.c        | 13 +++++++++++++
 drivers/gpu/drm/xe/xe_lrc.h        |  2 ++
 3 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index c70b75a3eb85..663ad4d97b34 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1696,7 +1696,7 @@ static void guc_exec_queue_stop(struct xe_guc *guc, struct xe_exec_queue *q)
 				ban = true;
 			}
 		} else if (xe_exec_queue_is_lr(q) &&
-			   (xe_lrc_ring_head(q->lrc[0]) != xe_lrc_ring_tail(q->lrc[0]))) {
+			   !xe_lrc_ring_is_idle(q->lrc[0])) {
 			ban = true;
 		}
 
diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index 4b65da77c6e0..e0d80e8201eb 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -1763,3 +1763,16 @@ u32 xe_lrc_update_timestamp(struct xe_lrc *lrc, u32 *old_ts)
 
 	return lrc->ctx_timestamp;
 }
+
+/**
+ * xe_lrc_ring_is_idle() - LRC is idle
+ * @lrc: Pointer to the lrc.
+ *
+ * Compare LRC ring head and tail to determine if idle.
+ *
+ * Return: True is ring is idle, False otherwise
+ */
+bool xe_lrc_ring_is_idle(struct xe_lrc *lrc)
+{
+	return xe_lrc_ring_head(lrc) == xe_lrc_ring_tail(lrc);
+}
diff --git a/drivers/gpu/drm/xe/xe_lrc.h b/drivers/gpu/drm/xe/xe_lrc.h
index 40d8f6906d3e..9d64cedc4d14 100644
--- a/drivers/gpu/drm/xe/xe_lrc.h
+++ b/drivers/gpu/drm/xe/xe_lrc.h
@@ -78,6 +78,8 @@ u32 xe_lrc_ring_head(struct xe_lrc *lrc);
 u32 xe_lrc_ring_space(struct xe_lrc *lrc);
 void xe_lrc_write_ring(struct xe_lrc *lrc, const void *data, size_t size);
 
+bool xe_lrc_ring_is_idle(struct xe_lrc *lrc);
+
 u32 xe_lrc_indirect_ring_ggtt_addr(struct xe_lrc *lrc);
 u32 xe_lrc_ggtt_addr(struct xe_lrc *lrc);
 u32 *xe_lrc_regs(struct xe_lrc *lrc);
-- 
2.34.1

[PATCH v2 2/7] drm/xe: Remove redundant rebind from preempt rebind worker

[Matthew Brost]

We issue a rebind in xe_preempt_work_begin so no need to call
xe_vm_rebind again in the preempt rebind worker.

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
---
 drivers/gpu/drm/xe/xe_vm.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 624133fae5f5..756c72cd6048 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -525,10 +525,6 @@ static void preempt_rebind_work_func(struct work_struct *w)
 	if (err)
 		goto out_unlock;
 
-	err = xe_vm_rebind(vm, true);
-	if (err)
-		goto out_unlock;
-
 	/* Wait on rebinds and munmap style VM unbinds */
 	wait = dma_resv_wait_timeout(xe_vm_resv(vm),
 				     DMA_RESV_USAGE_KERNEL,
-- 
2.34.1

[PATCH v2 3/7] drm/xe: Add ring address to LRC snapshot

[Matthew Brost]

The ring is currently in LRC BO but this may change going forward.
Include the ring address in the snapshot protecting again any future
changes.

v2:
 - s/ring_desc/ring_addr (Jonathan)

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
---
 drivers/gpu/drm/xe/xe_lrc.c | 3 +++
 drivers/gpu/drm/xe/xe_lrc.h | 1 +
 2 files changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index e0d80e8201eb..cc77e5132157 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -1636,6 +1636,7 @@ struct xe_lrc_snapshot *xe_lrc_snapshot_capture(struct xe_lrc *lrc)
 		xe_vm_get(lrc->bo->vm);
 
 	snapshot->context_desc = xe_lrc_ggtt_addr(lrc);
+	snapshot->ring_addr = __xe_lrc_ring_ggtt_addr(lrc);
 	snapshot->indirect_context_desc = xe_lrc_indirect_ring_ggtt_addr(lrc);
 	snapshot->head = xe_lrc_ring_head(lrc);
 	snapshot->tail.internal = lrc->ring.tail;
@@ -1693,6 +1694,8 @@ void xe_lrc_snapshot_print(struct xe_lrc_snapshot *snapshot, struct drm_printer
 		return;
 
 	drm_printf(p, "\tHW Context Desc: 0x%08x\n", snapshot->context_desc);
+	drm_printf(p, "\tHW Ring address: 0x%08x\n",
+		   snapshot->ring_addr);
 	drm_printf(p, "\tHW Indirect Ring State: 0x%08x\n",
 		   snapshot->indirect_context_desc);
 	drm_printf(p, "\tLRC Head: (memory) %u\n", snapshot->head);
diff --git a/drivers/gpu/drm/xe/xe_lrc.h b/drivers/gpu/drm/xe/xe_lrc.h
index 9d64cedc4d14..37ca321ed492 100644
--- a/drivers/gpu/drm/xe/xe_lrc.h
+++ b/drivers/gpu/drm/xe/xe_lrc.h
@@ -25,6 +25,7 @@ struct xe_lrc_snapshot {
 	unsigned long lrc_size, lrc_offset;
 
 	u32 context_desc;
+	u32 ring_addr;
 	u32 indirect_context_desc;
 	u32 head;
 	struct {
-- 
2.34.1

[PATCH v2 4/7] drm/xe: Add ring start to LRC snapshot

[Matthew Brost]

Add LRC ring start register to LRC snapshot to verify no LRC register
corruption upon hang. This could be possible if the indirect ring state
was mapped to user space or via an internal KMD memory corruption.

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
---
 drivers/gpu/drm/xe/xe_lrc.c | 10 ++++++++++
 drivers/gpu/drm/xe/xe_lrc.h |  1 +
 2 files changed, 11 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index cc77e5132157..22e58c6e2a35 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -1061,6 +1061,14 @@ u32 xe_lrc_ring_tail(struct xe_lrc *lrc)
 		return xe_lrc_read_ctx_reg(lrc, CTX_RING_TAIL) & TAIL_ADDR;
 }
 
+static u32 xe_lrc_ring_start(struct xe_lrc *lrc)
+{
+	if (xe_lrc_has_indirect_ring_state(lrc))
+		return xe_lrc_read_indirect_ctx_reg(lrc, INDIRECT_CTX_RING_START);
+	else
+		return xe_lrc_read_ctx_reg(lrc, CTX_RING_START);
+}
+
 void xe_lrc_set_ring_head(struct xe_lrc *lrc, u32 head)
 {
 	if (xe_lrc_has_indirect_ring_state(lrc))
@@ -1641,6 +1649,7 @@ struct xe_lrc_snapshot *xe_lrc_snapshot_capture(struct xe_lrc *lrc)
 	snapshot->head = xe_lrc_ring_head(lrc);
 	snapshot->tail.internal = lrc->ring.tail;
 	snapshot->tail.memory = xe_lrc_ring_tail(lrc);
+	snapshot->start = xe_lrc_ring_start(lrc);
 	snapshot->start_seqno = xe_lrc_start_seqno(lrc);
 	snapshot->seqno = xe_lrc_seqno(lrc);
 	snapshot->lrc_bo = xe_bo_get(lrc->bo);
@@ -1701,6 +1710,7 @@ void xe_lrc_snapshot_print(struct xe_lrc_snapshot *snapshot, struct drm_printer
 	drm_printf(p, "\tLRC Head: (memory) %u\n", snapshot->head);
 	drm_printf(p, "\tLRC Tail: (internal) %u, (memory) %u\n",
 		   snapshot->tail.internal, snapshot->tail.memory);
+	drm_printf(p, "\tRing start: (memory) 0x%08x\n", snapshot->start);
 	drm_printf(p, "\tStart seqno: (memory) %d\n", snapshot->start_seqno);
 	drm_printf(p, "\tSeqno: (memory) %d\n", snapshot->seqno);
 	drm_printf(p, "\tTimestamp: 0x%08x\n", snapshot->ctx_timestamp);
diff --git a/drivers/gpu/drm/xe/xe_lrc.h b/drivers/gpu/drm/xe/xe_lrc.h
index 37ca321ed492..b459dcab8787 100644
--- a/drivers/gpu/drm/xe/xe_lrc.h
+++ b/drivers/gpu/drm/xe/xe_lrc.h
@@ -28,6 +28,7 @@ struct xe_lrc_snapshot {
 	u32 ring_addr;
 	u32 indirect_context_desc;
 	u32 head;
+	u32 start;
 	struct {
 		u32 internal;
 		u32 memory;
-- 
2.34.1

[PATCH v2 5/7] drm/xe: Improve schedule disable response failure

[Matthew Brost]

Print Guc ID and take devcoredump on schedule disable response failure.
GuC ID is useful information and a schedule disable response failure is
possible the LRC state is corrupted so a devcoredump is helpful to debug.

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
---
 drivers/gpu/drm/xe/xe_guc_submit.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 663ad4d97b34..3d61c650c0d2 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1124,7 +1124,10 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job)
 		if (!ret || xe_guc_read_stopped(guc)) {
 trigger_reset:
 			if (!ret)
-				xe_gt_warn(guc_to_gt(guc), "Schedule disable failed to respond");
+				xe_gt_warn(guc_to_gt(guc),
+					   "Schedule disable failed to respond, guc_id=%d",
+					   q->guc->id);
+			xe_devcoredump(q, job);
 			set_exec_queue_extra_ref(q);
 			xe_exec_queue_get(q);	/* GT reset owns this */
 			set_exec_queue_banned(q);
-- 
2.34.1

[PATCH v2 6/7] drm/xe: Add exec queue param to devcoredump

[Matthew Brost]

During capture time, the target job may be unavailable (e.g., if it's in
LR mode). However, the associated exec queue will be available
regardless, so add an exec queue param for such cases.

v2:
 - Reword commit message (Jonathan)

Cc: Zhanjun Dong <zhanjun.dong@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
---
 drivers/gpu/drm/xe/xe_devcoredump.c | 15 +++++++++------
 drivers/gpu/drm/xe/xe_devcoredump.h |  6 ++++--
 drivers/gpu/drm/xe/xe_guc_submit.c  |  2 +-
 3 files changed, 14 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_devcoredump.c b/drivers/gpu/drm/xe/xe_devcoredump.c
index d3570d3d573c..c32cbb46ef8c 100644
--- a/drivers/gpu/drm/xe/xe_devcoredump.c
+++ b/drivers/gpu/drm/xe/xe_devcoredump.c
@@ -238,10 +238,10 @@ static void xe_devcoredump_free(void *data)
 }
 
 static void devcoredump_snapshot(struct xe_devcoredump *coredump,
+				 struct xe_exec_queue *q,
 				 struct xe_sched_job *job)
 {
 	struct xe_devcoredump_snapshot *ss = &coredump->snapshot;
-	struct xe_exec_queue *q = job->q;
 	struct xe_guc *guc = exec_queue_to_guc(q);
 	u32 adj_logical_mask = q->logical_mask;
 	u32 width_mask = (0x1 << q->width) - 1;
@@ -278,10 +278,12 @@ static void devcoredump_snapshot(struct xe_devcoredump *coredump,
 	ss->guc.log = xe_guc_log_snapshot_capture(&guc->log, true);
 	ss->guc.ct = xe_guc_ct_snapshot_capture(&guc->ct);
 	ss->ge = xe_guc_exec_queue_snapshot_capture(q);
-	ss->job = xe_sched_job_snapshot_capture(job);
+	if (job)
+		ss->job = xe_sched_job_snapshot_capture(job);
 	ss->vm = xe_vm_snapshot_capture(q->vm);
 
-	xe_engine_snapshot_capture_for_job(job);
+	if (job)
+		xe_engine_snapshot_capture_for_job(job);
 
 	queue_work(system_unbound_wq, &ss->work);
 
@@ -291,15 +293,16 @@ static void devcoredump_snapshot(struct xe_devcoredump *coredump,
 
 /**
  * xe_devcoredump - Take the required snapshots and initialize coredump device.
+ * @q: The faulty xe_exec_queue, where the issue was detected.
  * @job: The faulty xe_sched_job, where the issue was detected.
  *
  * This function should be called at the crash time within the serialized
  * gt_reset. It is skipped if we still have the core dump device available
  * with the information of the 'first' snapshot.
  */
-void xe_devcoredump(struct xe_sched_job *job)
+void xe_devcoredump(struct xe_exec_queue *q, struct xe_sched_job *job)
 {
-	struct xe_device *xe = gt_to_xe(job->q->gt);
+	struct xe_device *xe = gt_to_xe(q->gt);
 	struct xe_devcoredump *coredump = &xe->devcoredump;
 
 	if (coredump->captured) {
@@ -308,7 +311,7 @@ void xe_devcoredump(struct xe_sched_job *job)
 	}
 
 	coredump->captured = true;
-	devcoredump_snapshot(coredump, job);
+	devcoredump_snapshot(coredump, q, job);
 
 	drm_info(&xe->drm, "Xe device coredump has been created\n");
 	drm_info(&xe->drm, "Check your /sys/class/drm/card%d/device/devcoredump/data\n",
diff --git a/drivers/gpu/drm/xe/xe_devcoredump.h b/drivers/gpu/drm/xe/xe_devcoredump.h
index a4eebc285fc8..c04a534e3384 100644
--- a/drivers/gpu/drm/xe/xe_devcoredump.h
+++ b/drivers/gpu/drm/xe/xe_devcoredump.h
@@ -10,13 +10,15 @@
 
 struct drm_printer;
 struct xe_device;
+struct xe_exec_queue;
 struct xe_sched_job;
 
 #ifdef CONFIG_DEV_COREDUMP
-void xe_devcoredump(struct xe_sched_job *job);
+void xe_devcoredump(struct xe_exec_queue *q, struct xe_sched_job *job);
 int xe_devcoredump_init(struct xe_device *xe);
 #else
-static inline void xe_devcoredump(struct xe_sched_job *job)
+static inline void xe_devcoredump(struct xe_exec_queue *q,
+				  struct xe_sched_job *job)
 {
 }
 
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 3d61c650c0d2..46fd4621bfca 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1157,7 +1157,7 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job)
 	trace_xe_sched_job_timedout(job);
 
 	if (!exec_queue_killed(q))
-		xe_devcoredump(job);
+		xe_devcoredump(q, job);
 
 	/*
 	 * Kernel jobs should never fail, nor should VM jobs if they do
-- 
2.34.1

[PATCH v2 7/7] drm/xe: Change xe_engine_snapshot_capture_for_job to be for queue

[Matthew Brost]

During capture time, the target job may be unavailable (e.g., if it's in
LR mode). However, the associated exec queue will be available
regardless, change xe_engine_snapshot_capture_for_job to take a queue
argument ann rename to xe_engine_snapshot_capture_for_queue.

v2:
 - Reword commit message (Jonathan)
 - Remove redundant queueu check (Zhanjun)
 - Remove devcoredump job member (Zhanjun)

Cc: Zhanjun Dong <zhanjun.dong@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
---
 drivers/gpu/drm/xe/xe_devcoredump.c       |  5 +---
 drivers/gpu/drm/xe/xe_devcoredump_types.h |  2 --
 drivers/gpu/drm/xe/xe_guc_capture.c       | 29 ++++++++++-------------
 drivers/gpu/drm/xe/xe_guc_capture.h       |  6 ++---
 drivers/gpu/drm/xe/xe_guc_submit.c        |  4 ++--
 drivers/gpu/drm/xe/xe_hw_engine.c         |  8 +++----
 drivers/gpu/drm/xe/xe_hw_engine.h         |  4 ++--
 7 files changed, 24 insertions(+), 34 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_devcoredump.c b/drivers/gpu/drm/xe/xe_devcoredump.c
index c32cbb46ef8c..0e5edf14a241 100644
--- a/drivers/gpu/drm/xe/xe_devcoredump.c
+++ b/drivers/gpu/drm/xe/xe_devcoredump.c
@@ -232,7 +232,6 @@ static void xe_devcoredump_free(void *data)
 	/* To prevent stale data on next snapshot, clear everything */
 	memset(&coredump->snapshot, 0, sizeof(coredump->snapshot));
 	coredump->captured = false;
-	coredump->job = NULL;
 	drm_info(&coredump_to_xe(coredump)->drm,
 		 "Xe device coredump has been deleted.\n");
 }
@@ -259,7 +258,6 @@ static void devcoredump_snapshot(struct xe_devcoredump *coredump,
 	strscpy(ss->process_name, process_name);
 
 	ss->gt = q->gt;
-	coredump->job = job;
 	INIT_WORK(&ss->work, xe_devcoredump_deferred_snap_work);
 
 	cookie = dma_fence_begin_signalling();
@@ -282,8 +280,7 @@ static void devcoredump_snapshot(struct xe_devcoredump *coredump,
 		ss->job = xe_sched_job_snapshot_capture(job);
 	ss->vm = xe_vm_snapshot_capture(q->vm);
 
-	if (job)
-		xe_engine_snapshot_capture_for_job(job);
+	xe_engine_snapshot_capture_for_queue(q);
 
 	queue_work(system_unbound_wq, &ss->work);
 
diff --git a/drivers/gpu/drm/xe/xe_devcoredump_types.h b/drivers/gpu/drm/xe/xe_devcoredump_types.h
index 3703ddea1252..be4d59ea9ac8 100644
--- a/drivers/gpu/drm/xe/xe_devcoredump_types.h
+++ b/drivers/gpu/drm/xe/xe_devcoredump_types.h
@@ -80,8 +80,6 @@ struct xe_devcoredump {
 	bool captured;
 	/** @snapshot: Snapshot is captured at time of the first crash */
 	struct xe_devcoredump_snapshot snapshot;
-	/** @job: Point to the faulting job */
-	struct xe_sched_job *job;
 };
 
 #endif
diff --git a/drivers/gpu/drm/xe/xe_guc_capture.c b/drivers/gpu/drm/xe/xe_guc_capture.c
index cc72446a5de1..cd6d80b5b51d 100644
--- a/drivers/gpu/drm/xe/xe_guc_capture.c
+++ b/drivers/gpu/drm/xe/xe_guc_capture.c
@@ -1793,29 +1793,24 @@ void xe_engine_snapshot_print(struct xe_hw_engine_snapshot *snapshot, struct drm
 }
 
 /**
- * xe_guc_capture_get_matching_and_lock - Matching GuC capture for the job.
- * @job: The job object.
+ * xe_guc_capture_get_matching_and_lock - Matching GuC capture for the queue.
+ * @q: The exec queue object
  *
- * Search within the capture outlist for the job, could be used for check if
- * GuC capture is ready for the job.
+ * Search within the capture outlist for the queue, could be used for check if
+ * GuC capture is ready for the queue.
  * If found, the locked boolean of the node will be flagged.
  *
  * Returns: found guc-capture node ptr else NULL
  */
 struct __guc_capture_parsed_output *
-xe_guc_capture_get_matching_and_lock(struct xe_sched_job *job)
+xe_guc_capture_get_matching_and_lock(struct xe_exec_queue *q)
 {
 	struct xe_hw_engine *hwe;
 	enum xe_hw_engine_id id;
-	struct xe_exec_queue *q;
 	struct xe_device *xe;
 	u16 guc_class = GUC_LAST_ENGINE_CLASS + 1;
 	struct xe_devcoredump_snapshot *ss;
 
-	if (!job)
-		return NULL;
-
-	q = job->q;
 	if (!q || !q->gt)
 		return NULL;
 
@@ -1827,7 +1822,7 @@ xe_guc_capture_get_matching_and_lock(struct xe_sched_job *job)
 	if (ss->matched_node && ss->matched_node->source == XE_ENGINE_CAPTURE_SOURCE_GUC)
 		return ss->matched_node;
 
-	/* Find hwe for the job */
+	/* Find hwe for the queue */
 	for_each_hw_engine(hwe, q->gt, id) {
 		if (hwe != q->hwe)
 			continue;
@@ -1859,17 +1854,16 @@ xe_guc_capture_get_matching_and_lock(struct xe_sched_job *job)
 }
 
 /**
- * xe_engine_snapshot_capture_for_job - Take snapshot of associated engine
- * @job: The job object
+ * xe_engine_snapshot_capture_for_queue - Take snapshot of associated engine
+ * @q: The exec queue object
  *
  * Take snapshot of associated HW Engine
  *
  * Returns: None.
  */
 void
-xe_engine_snapshot_capture_for_job(struct xe_sched_job *job)
+xe_engine_snapshot_capture_for_queue(struct xe_exec_queue *q)
 {
-	struct xe_exec_queue *q = job->q;
 	struct xe_device *xe = gt_to_xe(q->gt);
 	struct xe_devcoredump *coredump = &xe->devcoredump;
 	struct xe_hw_engine *hwe;
@@ -1887,11 +1881,12 @@ xe_engine_snapshot_capture_for_job(struct xe_sched_job *job)
 		}
 
 		if (!coredump->snapshot.hwe[id]) {
-			coredump->snapshot.hwe[id] = xe_hw_engine_snapshot_capture(hwe, job);
+			coredump->snapshot.hwe[id] =
+				xe_hw_engine_snapshot_capture(hwe, q);
 		} else {
 			struct __guc_capture_parsed_output *new;
 
-			new = xe_guc_capture_get_matching_and_lock(job);
+			new = xe_guc_capture_get_matching_and_lock(q);
 			if (new) {
 				struct xe_guc *guc =  &q->gt->uc.guc;
 
diff --git a/drivers/gpu/drm/xe/xe_guc_capture.h b/drivers/gpu/drm/xe/xe_guc_capture.h
index 97a795d13dd1..20a078dc4b85 100644
--- a/drivers/gpu/drm/xe/xe_guc_capture.h
+++ b/drivers/gpu/drm/xe/xe_guc_capture.h
@@ -11,10 +11,10 @@
 #include "xe_guc.h"
 #include "xe_guc_fwif.h"
 
+struct xe_exec_queue;
 struct xe_guc;
 struct xe_hw_engine;
 struct xe_hw_engine_snapshot;
-struct xe_sched_job;
 
 static inline enum guc_capture_list_class_type xe_guc_class_to_capture_class(u16 class)
 {
@@ -50,10 +50,10 @@ size_t xe_guc_capture_ads_input_worst_size(struct xe_guc *guc);
 const struct __guc_mmio_reg_descr_group *
 xe_guc_capture_get_reg_desc_list(struct xe_gt *gt, u32 owner, u32 type,
 				 enum guc_capture_list_class_type capture_class, bool is_ext);
-struct __guc_capture_parsed_output *xe_guc_capture_get_matching_and_lock(struct xe_sched_job *job);
+struct __guc_capture_parsed_output *xe_guc_capture_get_matching_and_lock(struct xe_exec_queue *q);
 void xe_engine_manual_capture(struct xe_hw_engine *hwe, struct xe_hw_engine_snapshot *snapshot);
 void xe_engine_snapshot_print(struct xe_hw_engine_snapshot *snapshot, struct drm_printer *p);
-void xe_engine_snapshot_capture_for_job(struct xe_sched_job *job);
+void xe_engine_snapshot_capture_for_queue(struct xe_exec_queue *q);
 void xe_guc_capture_steered_list_init(struct xe_guc *guc);
 void xe_guc_capture_put_matched_nodes(struct xe_guc *guc);
 int xe_guc_capture_init(struct xe_guc *guc);
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 46fd4621bfca..985a21a72da4 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1061,13 +1061,13 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job)
 	 * do manual capture first and decide later if we need to use it
 	 */
 	if (!exec_queue_killed(q) && !xe->devcoredump.captured &&
-	    !xe_guc_capture_get_matching_and_lock(job)) {
+	    !xe_guc_capture_get_matching_and_lock(q)) {
 		/* take force wake before engine register manual capture */
 		fw_ref = xe_force_wake_get(gt_to_fw(q->gt), XE_FORCEWAKE_ALL);
 		if (!xe_force_wake_ref_has_domain(fw_ref, XE_FORCEWAKE_ALL))
 			xe_gt_info(q->gt, "failed to get forcewake for coredump capture\n");
 
-		xe_engine_snapshot_capture_for_job(job);
+		xe_engine_snapshot_capture_for_queue(q);
 
 		xe_force_wake_put(gt_to_fw(q->gt), fw_ref);
 	}
diff --git a/drivers/gpu/drm/xe/xe_hw_engine.c b/drivers/gpu/drm/xe/xe_hw_engine.c
index 1557acee3523..0cfa2b9282be 100644
--- a/drivers/gpu/drm/xe/xe_hw_engine.c
+++ b/drivers/gpu/drm/xe/xe_hw_engine.c
@@ -829,7 +829,7 @@ void xe_hw_engine_handle_irq(struct xe_hw_engine *hwe, u16 intr_vec)
 /**
  * xe_hw_engine_snapshot_capture - Take a quick snapshot of the HW Engine.
  * @hwe: Xe HW Engine.
- * @job: The job object.
+ * @q: The exec queue object.
  *
  * This can be printed out in a later stage like during dev_coredump
  * analysis.
@@ -838,7 +838,7 @@ void xe_hw_engine_handle_irq(struct xe_hw_engine *hwe, u16 intr_vec)
  * caller, using `xe_hw_engine_snapshot_free`.
  */
 struct xe_hw_engine_snapshot *
-xe_hw_engine_snapshot_capture(struct xe_hw_engine *hwe, struct xe_sched_job *job)
+xe_hw_engine_snapshot_capture(struct xe_hw_engine *hwe, struct xe_exec_queue *q)
 {
 	struct xe_hw_engine_snapshot *snapshot;
 	struct __guc_capture_parsed_output *node;
@@ -864,9 +864,9 @@ xe_hw_engine_snapshot_capture(struct xe_hw_engine *hwe, struct xe_sched_job *job
 	if (IS_SRIOV_VF(gt_to_xe(hwe->gt)))
 		return snapshot;
 
-	if (job) {
+	if (q) {
 		/* If got guc capture, set source to GuC */
-		node = xe_guc_capture_get_matching_and_lock(job);
+		node = xe_guc_capture_get_matching_and_lock(q);
 		if (node) {
 			struct xe_device *xe = gt_to_xe(hwe->gt);
 			struct xe_devcoredump *coredump = &xe->devcoredump;
diff --git a/drivers/gpu/drm/xe/xe_hw_engine.h b/drivers/gpu/drm/xe/xe_hw_engine.h
index da0a6922a26f..6b5f9fa2a594 100644
--- a/drivers/gpu/drm/xe/xe_hw_engine.h
+++ b/drivers/gpu/drm/xe/xe_hw_engine.h
@@ -11,7 +11,7 @@
 struct drm_printer;
 struct drm_xe_engine_class_instance;
 struct xe_device;
-struct xe_sched_job;
+struct xe_exec_queue;
 
 #ifdef CONFIG_DRM_XE_JOB_TIMEOUT_MIN
 #define XE_HW_ENGINE_JOB_TIMEOUT_MIN CONFIG_DRM_XE_JOB_TIMEOUT_MIN
@@ -56,7 +56,7 @@ void xe_hw_engine_enable_ring(struct xe_hw_engine *hwe);
 u32 xe_hw_engine_mask_per_class(struct xe_gt *gt,
 				enum xe_engine_class engine_class);
 struct xe_hw_engine_snapshot *
-xe_hw_engine_snapshot_capture(struct xe_hw_engine *hwe, struct xe_sched_job *job);
+xe_hw_engine_snapshot_capture(struct xe_hw_engine *hwe, struct xe_exec_queue *q);
 void xe_hw_engine_snapshot_free(struct xe_hw_engine_snapshot *snapshot);
 void xe_hw_engine_print(struct xe_hw_engine *hwe, struct drm_printer *p);
 void xe_hw_engine_setup_default_lrc_state(struct xe_hw_engine *hwe);
-- 
2.34.1