From: Haohui Mai <ricetons@xxxxxxxxx>
[ Upstream commit 7dba6e838e741caadcf27ef717b6dcb561e77f89 ]
This patch fixes the issue where the driver miscomputes the 64-bit
values of the wptr of the SDMA doorbell when initializing the
hardware. SDMA engines v4 and later on have full 64-bit registers for
wptr thus they should be set properly.
Older generation hardwares like CIK / SI have only 16 / 20 / 24bits
for the WPTR, where the calls of lower_32_bits() will be removed in a
following patch.
Reviewed-by: Christian König <christian.koenig@xxxxxxx>
Signed-off-by: Haohui Mai <ricetons@xxxxxxxxx>
Signed-off-by: Alex Deucher <alexander.deucher@xxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 4 ++--
drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c | 8 ++++----
drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c | 8 ++++----
3 files changed, 10 insertions(+), 10 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index f0638db57111..66b6b175ae90 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -772,8 +772,8 @@ static void sdma_v4_0_ring_set_wptr(struct amdgpu_ring *ring)
DRM_DEBUG("Using doorbell -- "
"wptr_offs == 0x%08x "
- "lower_32_bits(ring->wptr) << 2 == 0x%08x "
- "upper_32_bits(ring->wptr) << 2 == 0x%08x\n",
+ "lower_32_bits(ring->wptr << 2) == 0x%08x "
+ "upper_32_bits(ring->wptr << 2) == 0x%08x\n",
ring->wptr_offs,
lower_32_bits(ring->wptr << 2),
upper_32_bits(ring->wptr << 2));
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
index 81e033549dda..6982735e88ba 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
@@ -400,8 +400,8 @@ static void sdma_v5_0_ring_set_wptr(struct amdgpu_ring *ring)
if (ring->use_doorbell) {
DRM_DEBUG("Using doorbell -- "
"wptr_offs == 0x%08x "
- "lower_32_bits(ring->wptr) << 2 == 0x%08x "
- "upper_32_bits(ring->wptr) << 2 == 0x%08x\n",
+ "lower_32_bits(ring->wptr << 2) == 0x%08x "
+ "upper_32_bits(ring->wptr << 2) == 0x%08x\n",
ring->wptr_offs,
lower_32_bits(ring->wptr << 2),
upper_32_bits(ring->wptr << 2));
@@ -780,9 +780,9 @@ static int sdma_v5_0_gfx_resume(struct amdgpu_device *adev)
if (!amdgpu_sriov_vf(adev)) { /* only bare-metal use register write for wptr */
WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR),
- lower_32_bits(ring->wptr) << 2);
+ lower_32_bits(ring->wptr << 2));
WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_HI),
- upper_32_bits(ring->wptr) << 2);
+ upper_32_bits(ring->wptr << 2));
}
doorbell = RREG32_SOC15_IP(GC, sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_DOORBELL));
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
index d3d6d5b045b8..ce3a3d1bdaa8 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
@@ -287,8 +287,8 @@ static void sdma_v5_2_ring_set_wptr(struct amdgpu_ring *ring)
if (ring->use_doorbell) {
DRM_DEBUG("Using doorbell -- "
"wptr_offs == 0x%08x "
- "lower_32_bits(ring->wptr) << 2 == 0x%08x "
- "upper_32_bits(ring->wptr) << 2 == 0x%08x\n",
+ "lower_32_bits(ring->wptr << 2) == 0x%08x "
+ "upper_32_bits(ring->wptr << 2) == 0x%08x\n",
ring->wptr_offs,
lower_32_bits(ring->wptr << 2),
upper_32_bits(ring->wptr << 2));
@@ -664,8 +664,8 @@ static int sdma_v5_2_gfx_resume(struct amdgpu_device *adev)
WREG32_SOC15_IP(GC, sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_GFX_MINOR_PTR_UPDATE), 1);
if (!amdgpu_sriov_vf(adev)) { /* only bare-metal use register write for wptr */
- WREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR), lower_32_bits(ring->wptr) << 2);
- WREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_HI), upper_32_bits(ring->wptr) << 2);
+ WREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR), lower_32_bits(ring->wptr << 2));
+ WREG32(sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_GFX_RB_WPTR_HI), upper_32_bits(ring->wptr << 2));
}
doorbell = RREG32_SOC15_IP(GC, sdma_v5_2_get_reg_offset(adev, i, mmSDMA0_GFX_DOORBELL));
--
2.35.1
