drm/xe: Save off position in ring in which a job was programmed

VF post-migration recovery needs to modify the ring with updated GGTT
addresses for pending jobs. Save off position in ring in which a job was
programmed to facilitate.

v4:
 - s/VF resume/VF post-migration recovery (Tomasz)

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Tomasz Lis <tomasz.lis@intel.com>
Link: https://lore.kernel.org/r/20251008214532.3442967-3-matthew.brost@intel.com

2 files changed, 24 insertions, 4 deletions

diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c
index d71837773d6c..ac0c6dcffe15 100644
--- a/drivers/gpu/drm/xe/xe_ring_ops.c
+++ b/drivers/gpu/drm/xe/xe_ring_ops.c
@@ -245,12 +245,14 @@ static int emit_copy_timestamp(struct xe_lrc *lrc, u32 *dw, int i)
 
 /* for engines that don't require any special HW handling (no EUs, no aux inval, etc) */
 static void __emit_job_gen12_simple(struct xe_sched_job *job, struct xe_lrc *lrc,
-				    u64 batch_addr, u32 seqno)
+				    u64 batch_addr, u32 *head, u32 seqno)
 {
 	u32 dw[MAX_JOB_SIZE_DW], i = 0;
 	u32 ppgtt_flag = get_ppgtt_flag(job);
 	struct xe_gt *gt = job->q->gt;
 
+	*head = lrc->ring.tail;
+
 	i = emit_copy_timestamp(lrc, dw, i);
 
 	if (job->ring_ops_flush_tlb) {
@@ -296,7 +298,7 @@ static bool has_aux_ccs(struct xe_device *xe)
 }
 
 static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc,
-				   u64 batch_addr, u32 seqno)
+				   u64 batch_addr, u32 *head, u32 seqno)
 {
 	u32 dw[MAX_JOB_SIZE_DW], i = 0;
 	u32 ppgtt_flag = get_ppgtt_flag(job);
@@ -304,6 +306,8 @@ static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc,
 	struct xe_device *xe = gt_to_xe(gt);
 	bool decode = job->q->class == XE_ENGINE_CLASS_VIDEO_DECODE;
 
+	*head = lrc->ring.tail;
+
 	i = emit_copy_timestamp(lrc, dw, i);
 
 	dw[i++] = preparser_disable(true);
@@ -346,7 +350,8 @@ static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc,
 
 static void __emit_job_gen12_render_compute(struct xe_sched_job *job,
 					    struct xe_lrc *lrc,
-					    u64 batch_addr, u32 seqno)
+					    u64 batch_addr, u32 *head,
+					    u32 seqno)
 {
 	u32 dw[MAX_JOB_SIZE_DW], i = 0;
 	u32 ppgtt_flag = get_ppgtt_flag(job);
@@ -355,6 +360,8 @@ static void __emit_job_gen12_render_compute(struct xe_sched_job *job,
 	bool lacks_render = !(gt->info.engine_mask & XE_HW_ENGINE_RCS_MASK);
 	u32 mask_flags = 0;
 
+	*head = lrc->ring.tail;
+
 	i = emit_copy_timestamp(lrc, dw, i);
 
 	dw[i++] = preparser_disable(true);
@@ -396,11 +403,14 @@ static void __emit_job_gen12_render_compute(struct xe_sched_job *job,
 }
 
 static void emit_migration_job_gen12(struct xe_sched_job *job,
-				     struct xe_lrc *lrc, u32 seqno)
+				     struct xe_lrc *lrc, u32 *head,
+				     u32 seqno)
 {
 	u32 saddr = xe_lrc_start_seqno_ggtt_addr(lrc);
 	u32 dw[MAX_JOB_SIZE_DW], i = 0;
 
+	*head = lrc->ring.tail;
+
 	i = emit_copy_timestamp(lrc, dw, i);
 
 	i = emit_store_imm_ggtt(saddr, seqno, dw, i);
@@ -434,6 +444,7 @@ static void emit_job_gen12_gsc(struct xe_sched_job *job)
 
 	__emit_job_gen12_simple(job, job->q->lrc[0],
 				job->ptrs[0].batch_addr,
+				&job->ptrs[0].head,
 				xe_sched_job_lrc_seqno(job));
 }
 
@@ -443,6 +454,7 @@ static void emit_job_gen12_copy(struct xe_sched_job *job)
 
 	if (xe_sched_job_is_migration(job->q)) {
 		emit_migration_job_gen12(job, job->q->lrc[0],
+					 &job->ptrs[0].head,
 					 xe_sched_job_lrc_seqno(job));
 		return;
 	}
@@ -450,6 +462,7 @@ static void emit_job_gen12_copy(struct xe_sched_job *job)
 	for (i = 0; i < job->q->width; ++i)
 		__emit_job_gen12_simple(job, job->q->lrc[i],
 					job->ptrs[i].batch_addr,
+					&job->ptrs[i].head,
 					xe_sched_job_lrc_seqno(job));
 }
 
@@ -461,6 +474,7 @@ static void emit_job_gen12_video(struct xe_sched_job *job)
 	for (i = 0; i < job->q->width; ++i)
 		__emit_job_gen12_video(job, job->q->lrc[i],
 				       job->ptrs[i].batch_addr,
+				       &job->ptrs[i].head,
 				       xe_sched_job_lrc_seqno(job));
 }
 
@@ -471,6 +485,7 @@ static void emit_job_gen12_render_compute(struct xe_sched_job *job)
 	for (i = 0; i < job->q->width; ++i)
 		__emit_job_gen12_render_compute(job, job->q->lrc[i],
 						job->ptrs[i].batch_addr,
+						&job->ptrs[i].head,
 						xe_sched_job_lrc_seqno(job));
 }
 
diff --git a/drivers/gpu/drm/xe/xe_sched_job_types.h b/drivers/gpu/drm/xe/xe_sched_job_types.h
index dbf260dded8d..7ce58765a34a 100644
--- a/drivers/gpu/drm/xe/xe_sched_job_types.h
+++ b/drivers/gpu/drm/xe/xe_sched_job_types.h
@@ -24,6 +24,11 @@ struct xe_job_ptrs {
 	struct dma_fence_chain *chain_fence;
 	/** @batch_addr: Batch buffer address. */
 	u64 batch_addr;
+	/**
+	 * @head: The tail pointer of the LRC (so head pointer of job) when the
+	 * job was submitted
+	 */
+	u32 head;
 };
 
 /**