[PATCH 1/2] drm/amdgpu: fix transform feedback GDS hang on gfx10 (v2)

[Marek Olšák]

From: Marek Olšák <marek.olsak at amd.com>

v2: update emit_ib_size
(though it's still wrong because it was wrong before)

Signed-off-by: Marek Olšák <marek.olsak at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gds.h |  3 ++-
 drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c  | 14 +++++++++++---
 2 files changed, 13 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gds.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gds.h
index dad2186f4ed5..df8a23554831 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gds.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gds.h
@@ -24,21 +24,22 @@
 #ifndef __AMDGPU_GDS_H__
 #define __AMDGPU_GDS_H__
 
 struct amdgpu_ring;
 struct amdgpu_bo;
 
 struct amdgpu_gds {
 	uint32_t gds_size;
 	uint32_t gws_size;
 	uint32_t oa_size;
-	uint32_t			gds_compute_max_wave_id;
+	uint32_t gds_compute_max_wave_id;
+	uint32_t vgt_gs_max_wave_id;
 };
 
 struct amdgpu_gds_reg_offset {
 	uint32_t	mem_base;
 	uint32_t	mem_size;
 	uint32_t	gws;
 	uint32_t	oa;
 };
 
 #endif /* __AMDGPU_GDS_H__ */
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 16b2bcc590e7..6baaa65a1daa 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -4211,20 +4211,29 @@ static void gfx_v10_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 }
 
 static void gfx_v10_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 				       struct amdgpu_job *job,
 				       struct amdgpu_ib *ib,
 				       uint32_t flags)
 {
 	unsigned vmid = AMDGPU_JOB_GET_VMID(job);
 	u32 header, control = 0;
 
+	/* Prevent a hw deadlock due to a wave ID mismatch between ME and GDS.
+	 * This resets the wave ID counters. (needed by transform feedback)
+	 * TODO: This might only be needed on a VMID switch when we change
+	 *       the GDS OA mapping, not sure.
+	 */
+	amdgpu_ring_write(ring, PACKET3(PACKET3_SET_CONFIG_REG, 1));
+	amdgpu_ring_write(ring, mmVGT_GS_MAX_WAVE_ID);
+	amdgpu_ring_write(ring, ring->adev->gds.vgt_gs_max_wave_id);
+
 	if (ib->flags & AMDGPU_IB_FLAG_CE)
 		header = PACKET3(PACKET3_INDIRECT_BUFFER_CNST, 2);
 	else
 		header = PACKET3(PACKET3_INDIRECT_BUFFER, 2);
 
 	control |= ib->length_dw | (vmid << 24);
 
 	if (amdgpu_mcbp && (ib->flags & AMDGPU_IB_FLAG_PREEMPT)) {
 		control |= INDIRECT_BUFFER_PRE_ENB(1);
 
@@ -4944,21 +4953,21 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_gfx = {
 		     */
 		5 + /* COND_EXEC */
 		7 + /* HDP_flush */
 		4 + /* VGT_flush */
 		14 + /*	CE_META */
 		31 + /*	DE_META */
 		3 + /* CNTX_CTRL */
 		5 + /* HDP_INVL */
 		8 + 8 + /* FENCE x2 */
 		2, /* SWITCH_BUFFER */
-	.emit_ib_size =	4, /* gfx_v10_0_ring_emit_ib_gfx */
+	.emit_ib_size =	7, /* gfx_v10_0_ring_emit_ib_gfx */
 	.emit_ib = gfx_v10_0_ring_emit_ib_gfx,
 	.emit_fence = gfx_v10_0_ring_emit_fence,
 	.emit_pipeline_sync = gfx_v10_0_ring_emit_pipeline_sync,
 	.emit_vm_flush = gfx_v10_0_ring_emit_vm_flush,
 	.emit_gds_switch = gfx_v10_0_ring_emit_gds_switch,
 	.emit_hdp_flush = gfx_v10_0_ring_emit_hdp_flush,
 	.test_ring = gfx_v10_0_ring_test_ring,
 	.test_ib = gfx_v10_0_ring_test_ib,
 	.insert_nop = amdgpu_ring_insert_nop,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
@@ -5092,24 +5101,23 @@ static void gfx_v10_0_set_rlc_funcs(struct amdgpu_device *adev)
 	default:
 		break;
 	}
 }
 
 static void gfx_v10_0_set_gds_init(struct amdgpu_device *adev)
 {
 	/* init asic gds info */
 	switch (adev->asic_type) {
 	case CHIP_NAVI10:
-		adev->gds.gds_size = 0x10000;
-		break;
 	default:
 		adev->gds.gds_size = 0x10000;
+		adev->gds.vgt_gs_max_wave_id = 0x3ff;
 		break;
 	}
 
 	adev->gds.gws_size = 64;
 	adev->gds.oa_size = 16;
 }
 
 static void gfx_v10_0_set_user_wgp_inactive_bitmap_per_sh(struct amdgpu_device *adev,
 							  u32 bitmap)
 {
-- 
2.17.1