[PATCH 6.0 200/862] drm/amdgpu: Enable F32_WPTR_POLL_ENABLE in mqd

[Greg Kroah-Hartman]

From: Ruili Ji <ruiliji2@xxxxxxx>

commit 21a550de5faf9f54013334c9a6a7643b8fd80b36 upstream.

This patch is to fix the SDMA user queue doorbell missing issue on
SDMA 6.0. F32_WPTR_POLL_ENABLE has to be set if doorbell mode is
used. Otherwise ringing SDMA user queue doorbell can't wake up
system from gfxoff.

Signed-off-by: Ruili Ji <ruiliji2@xxxxxxx>
Reviewed-by: Yifan Zhang <yifan1.zhang@xxxxxxx>
Signed-off-by: Alex Deucher <alexander.deucher@xxxxxxx>
Cc: stable@xxxxxxxxxxxxxxx # 6.0.x
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
 drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c           |    3 ++-
 drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c |    3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

--- a/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v6_0.c
@@ -910,7 +910,8 @@ static int sdma_v6_0_mqd_init(struct amd
 	m->sdmax_rlcx_rb_cntl =
 		order_base_2(prop->queue_size / 4) << SDMA0_QUEUE0_RB_CNTL__RB_SIZE__SHIFT |
 		1 << SDMA0_QUEUE0_RB_CNTL__RPTR_WRITEBACK_ENABLE__SHIFT |
-		4 << SDMA0_QUEUE0_RB_CNTL__RPTR_WRITEBACK_TIMER__SHIFT;
+		4 << SDMA0_QUEUE0_RB_CNTL__RPTR_WRITEBACK_TIMER__SHIFT |
+		1 << SDMA0_QUEUE0_RB_CNTL__F32_WPTR_POLL_ENABLE__SHIFT;
 
 	m->sdmax_rlcx_rb_base = lower_32_bits(prop->hqd_base_gpu_addr >> 8);
 	m->sdmax_rlcx_rb_base_hi = upper_32_bits(prop->hqd_base_gpu_addr >> 8);
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
@@ -375,7 +375,8 @@ static void update_mqd_sdma(struct mqd_m
 		<< SDMA0_QUEUE0_RB_CNTL__RB_SIZE__SHIFT |
 		q->vmid << SDMA0_QUEUE0_RB_CNTL__RB_VMID__SHIFT |
 		1 << SDMA0_QUEUE0_RB_CNTL__RPTR_WRITEBACK_ENABLE__SHIFT |
-		6 << SDMA0_QUEUE0_RB_CNTL__RPTR_WRITEBACK_TIMER__SHIFT;
+		6 << SDMA0_QUEUE0_RB_CNTL__RPTR_WRITEBACK_TIMER__SHIFT |
+		1 << SDMA0_QUEUE0_RB_CNTL__F32_WPTR_POLL_ENABLE__SHIFT;
 
 	m->sdmax_rlcx_rb_base = lower_32_bits(q->queue_address >> 8);
 	m->sdmax_rlcx_rb_base_hi = upper_32_bits(q->queue_address >> 8);