[CI 04/13] drm/xe/xelp: Support auxccs invalidation on blitter

[Tvrtko Ursulin <tvrtko.ursulin@igalia.com>]

Auxccs platforms need to be able to invalidate auxccs on the blitter
engine.

Add the relevant mmio register and enable this by refactoring the ring
emission a bit to consolidate all non-render engines.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
---
 drivers/gpu/drm/xe/regs/xe_gt_regs.h |   1 +
 drivers/gpu/drm/xe/xe_ring_ops.c     | 118 ++++++++++-----------------
 2 files changed, 46 insertions(+), 73 deletions(-)

diff --git a/drivers/gpu/drm/xe/regs/xe_gt_regs.h b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
index 3545e0be06da..f3bc2abf678c 100644
--- a/drivers/gpu/drm/xe/regs/xe_gt_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
@@ -94,6 +94,7 @@
 #define CCS_AUX_INV				XE_REG(0x4208)
 
 #define VD0_AUX_INV				XE_REG(0x4218)
+#define BCS_AUX_INV				XE_REG(0x4248)
 #define VE0_AUX_INV				XE_REG(0x4238)
 
 #define VE1_AUX_INV				XE_REG(0x42b8)
diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c
index f384c9968859..87e467972070 100644
--- a/drivers/gpu/drm/xe/xe_ring_ops.c
+++ b/drivers/gpu/drm/xe/xe_ring_ops.c
@@ -248,46 +248,6 @@ static int emit_copy_timestamp(struct xe_lrc *lrc, u32 *dw, int i)
 	return 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 *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) {
-		dw[i++] = preparser_disable(true);
-		i = emit_flush_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc),
-					seqno, MI_INVALIDATE_TLB, dw, i);
-		dw[i++] = preparser_disable(false);
-	} else {
-		i = emit_store_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc),
-					seqno, dw, i);
-	}
-
-	i = emit_bb_start(batch_addr, ppgtt_flag, dw, i);
-
-	if (job->user_fence.used) {
-		i = emit_flush_dw(dw, i);
-		i = emit_store_imm_ppgtt_posted(job->user_fence.addr,
-						job->user_fence.value,
-						dw, i);
-	}
-
-	i = emit_flush_imm_ggtt(xe_lrc_seqno_ggtt_addr(lrc), seqno, 0, dw, i);
-
-	i = emit_user_interrupt(dw, i);
-
-	xe_gt_assert(gt, i <= MAX_JOB_SIZE_DW);
-
-	xe_lrc_write_ring(lrc, dw, i * sizeof(*dw));
-}
-
 static bool has_aux_ccs(struct xe_device *xe)
 {
 	/*
@@ -302,40 +262,52 @@ static bool has_aux_ccs(struct xe_device *xe)
 	return !xe->info.has_flat_ccs;
 }
 
-static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc,
-				   u64 batch_addr, u32 *head, u32 seqno)
+static void __emit_job_gen12_xcs(struct xe_sched_job *job, struct xe_lrc *lrc,
+				 u64 batch_addr, u32 *head, u32 seqno)
 {
-	u32 dw[MAX_JOB_SIZE_DW], i = 0;
-	u32 ppgtt_flag = get_ppgtt_flag(job);
+	const unsigned int class = job->q->class;
 	struct xe_gt *gt = job->q->gt;
-	struct xe_device *xe = gt_to_xe(gt);
-	bool decode = job->q->class == XE_ENGINE_CLASS_VIDEO_DECODE;
+	const bool aux_ccs = has_aux_ccs(gt_to_xe(gt)) &&
+			     (class == XE_ENGINE_CLASS_COPY ||
+			      class == XE_ENGINE_CLASS_VIDEO_DECODE ||
+			      class == XE_ENGINE_CLASS_VIDEO_ENHANCE);
+	const bool invalidate_tlb = aux_ccs || job->ring_ops_flush_tlb;
+	u32 dw[MAX_JOB_SIZE_DW], i = 0;
 
 	*head = lrc->ring.tail;
 
 	i = emit_copy_timestamp(lrc, dw, i);
 
-	dw[i++] = preparser_disable(true);
-
-	/* hsdes: 1809175790 */
-	if (has_aux_ccs(xe)) {
-		if (decode)
-			i = emit_aux_table_inv(gt, VD0_AUX_INV, dw, i);
-		else
-			i = emit_aux_table_inv(gt, VE0_AUX_INV, dw, i);
-	}
-
-	if (job->ring_ops_flush_tlb)
+	if (invalidate_tlb) {
+		dw[i++] = preparser_disable(true);
 		i = emit_flush_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc),
-					seqno, MI_INVALIDATE_TLB, dw, i);
+					seqno,
+					MI_INVALIDATE_TLB,
+					dw, i);
+		/* hsdes: 1809175790 */
+		if (aux_ccs) {
+			struct xe_reg reg;
 
-	dw[i++] = preparser_disable(false);
+			switch (job->q->class) {
+			case XE_ENGINE_CLASS_COPY:
+				reg = BCS_AUX_INV;
+				break;
+			case XE_ENGINE_CLASS_VIDEO_DECODE:
+				reg = VD0_AUX_INV;
+				break;
+			default:
+				reg = VE0_AUX_INV;
+			};
 
-	if (!job->ring_ops_flush_tlb)
+			i = emit_aux_table_inv(gt, reg, dw, i);
+		}
+		dw[i++] = preparser_disable(false);
+	} else {
 		i = emit_store_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc),
 					seqno, dw, i);
+	}
 
-	i = emit_bb_start(batch_addr, ppgtt_flag, dw, i);
+	i = emit_bb_start(batch_addr, get_ppgtt_flag(job), dw, i);
 
 	if (job->user_fence.used) {
 		i = emit_flush_dw(dw, i);
@@ -455,10 +427,10 @@ static void emit_job_gen12_gsc(struct xe_sched_job *job)
 
 	xe_gt_assert(gt, job->q->width <= 1); /* no parallel submission for GSCCS */
 
-	__emit_job_gen12_simple(job, job->q->lrc[0],
-				job->ptrs[0].batch_addr,
-				&job->ptrs[0].head,
-				xe_sched_job_lrc_seqno(job));
+	__emit_job_gen12_xcs(job, job->q->lrc[0],
+			     job->ptrs[0].batch_addr,
+			     &job->ptrs[0].head,
+			     xe_sched_job_lrc_seqno(job));
 }
 
 static void emit_job_gen12_copy(struct xe_sched_job *job)
@@ -473,10 +445,10 @@ 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));
+		__emit_job_gen12_xcs(job, job->q->lrc[i],
+				     job->ptrs[i].batch_addr,
+				     &job->ptrs[0].head,
+				     xe_sched_job_lrc_seqno(job));
 }
 
 static void emit_job_gen12_video(struct xe_sched_job *job)
@@ -485,10 +457,10 @@ static void emit_job_gen12_video(struct xe_sched_job *job)
 
 	/* FIXME: Not doing parallel handshake for now */
 	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));
+		__emit_job_gen12_xcs(job, job->q->lrc[i],
+				     job->ptrs[i].batch_addr,
+				     &job->ptrs[0].head,
+				     xe_sched_job_lrc_seqno(job));
 }
 
 static void emit_job_gen12_render_compute(struct xe_sched_job *job)
-- 
2.48.0