|
[Public]
As long as there is no hw programming sequence requirement to do it as two separate writes this looks fine to me.
Acked-by: Alex Deucher <alexander.deucher@xxxxxxx>
From: Liang, Prike <Prike.Liang@xxxxxxx>
Sent: Friday, November 15, 2024 3:39 AM To: amd-gfx@xxxxxxxxxxxxxxxxxxxxx <amd-gfx@xxxxxxxxxxxxxxxxxxxxx> Cc: Deucher, Alexander <Alexander.Deucher@xxxxxxx>; Liang, Prike <Prike.Liang@xxxxxxx> Subject: [PATCH] drm/amdgpu: reduce the mmio writes in kiq setting There's no need to perform the two MMIO writes in the KIQ
Setting registers programmed period, and reducing the MMIO writes will save the driver loading time. Signed-off-by: Prike Liang <Prike.Liang@xxxxxxx> --- drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 8 ++------ drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 4 +--- drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c | 4 +--- drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 4 +--- drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 4 +--- drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c | 4 +--- drivers/gpu/drm/amd/amdgpu/mes_v11_0.c | 4 +--- drivers/gpu/drm/amd/amdgpu/mes_v12_0.c | 4 +--- 8 files changed, 9 insertions(+), 27 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 9da95b25e158..ffd3c45b4ccd 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -6593,17 +6593,13 @@ static void gfx_v10_0_kiq_setting(struct amdgpu_ring *ring) tmp = RREG32_SOC15(GC, 0, mmRLC_CP_SCHEDULERS_Sienna_Cichlid); tmp &= 0xffffff00; tmp |= (ring->me << 5) | (ring->pipe << 3) | (ring->queue); - WREG32_SOC15(GC, 0, mmRLC_CP_SCHEDULERS_Sienna_Cichlid, tmp); - tmp |= 0x80; - WREG32_SOC15(GC, 0, mmRLC_CP_SCHEDULERS_Sienna_Cichlid, tmp); + WREG32_SOC15(GC, 0, mmRLC_CP_SCHEDULERS_Sienna_Cichlid, tmp | 0x80); break; default: tmp = RREG32_SOC15(GC, 0, mmRLC_CP_SCHEDULERS); tmp &= 0xffffff00; tmp |= (ring->me << 5) | (ring->pipe << 3) | (ring->queue); - WREG32_SOC15(GC, 0, mmRLC_CP_SCHEDULERS, tmp); - tmp |= 0x80; - WREG32_SOC15(GC, 0, mmRLC_CP_SCHEDULERS, tmp); + WREG32_SOC15(GC, 0, mmRLC_CP_SCHEDULERS, tmp | 0x80); break; } } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index 5aff8f72de9c..a2aedcabae65 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -3890,9 +3890,7 @@ static void gfx_v11_0_kiq_setting(struct amdgpu_ring *ring) tmp = RREG32_SOC15(GC, 0, regRLC_CP_SCHEDULERS); tmp &= 0xffffff00; tmp |= (ring->me << 5) | (ring->pipe << 3) | (ring->queue); - WREG32_SOC15(GC, 0, regRLC_CP_SCHEDULERS, tmp); - tmp |= 0x80; - WREG32_SOC15(GC, 0, regRLC_CP_SCHEDULERS, tmp); + WREG32_SOC15(GC, 0, regRLC_CP_SCHEDULERS, tmp | 0x80); } static void gfx_v11_0_cp_set_doorbell_range(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c index 9fec28d8a5fc..c61d383c45c4 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c @@ -2826,9 +2826,7 @@ static void gfx_v12_0_kiq_setting(struct amdgpu_ring *ring) tmp = RREG32_SOC15(GC, 0, regRLC_CP_SCHEDULERS); tmp &= 0xffffff00; tmp |= (ring->me << 5) | (ring->pipe << 3) | (ring->queue); - WREG32_SOC15(GC, 0, regRLC_CP_SCHEDULERS, tmp); - tmp |= 0x80; - WREG32_SOC15(GC, 0, regRLC_CP_SCHEDULERS, tmp); + WREG32_SOC15(GC, 0, regRLC_CP_SCHEDULERS, tmp | 0x80); } static void gfx_v12_0_cp_set_doorbell_range(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 480c41ee947e..d465c3ea6e6c 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -4304,9 +4304,7 @@ static void gfx_v8_0_kiq_setting(struct amdgpu_ring *ring) tmp = RREG32(mmRLC_CP_SCHEDULERS); tmp &= 0xffffff00; tmp |= (ring->me << 5) | (ring->pipe << 3) | (ring->queue); - WREG32(mmRLC_CP_SCHEDULERS, tmp); - tmp |= 0x80; - WREG32(mmRLC_CP_SCHEDULERS, tmp); + WREG32(mmRLC_CP_SCHEDULERS, tmp | 0x80); } static int gfx_v8_0_kiq_kcq_enable(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index e9248a855ba7..a6cb30558f2f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -3482,9 +3482,7 @@ static void gfx_v9_0_kiq_setting(struct amdgpu_ring *ring) tmp = RREG32_SOC15(GC, 0, mmRLC_CP_SCHEDULERS); tmp &= 0xffffff00; tmp |= (ring->me << 5) | (ring->pipe << 3) | (ring->queue); - WREG32_SOC15_RLC(GC, 0, mmRLC_CP_SCHEDULERS, tmp); - tmp |= 0x80; - WREG32_SOC15_RLC(GC, 0, mmRLC_CP_SCHEDULERS, tmp); + WREG32_SOC15_RLC(GC, 0, mmRLC_CP_SCHEDULERS, tmp | 0x80); } static void gfx_v9_0_mqd_set_priority(struct amdgpu_ring *ring, struct v9_mqd *mqd) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c index 016290f00592..ae3c8645633b 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_3.c @@ -1771,9 +1771,7 @@ static void gfx_v9_4_3_xcc_kiq_setting(struct amdgpu_ring *ring, int xcc_id) tmp = RREG32_SOC15(GC, GET_INST(GC, xcc_id), regRLC_CP_SCHEDULERS); tmp &= 0xffffff00; tmp |= (ring->me << 5) | (ring->pipe << 3) | (ring->queue); - WREG32_SOC15_RLC(GC, GET_INST(GC, xcc_id), regRLC_CP_SCHEDULERS, tmp); - tmp |= 0x80; - WREG32_SOC15_RLC(GC, GET_INST(GC, xcc_id), regRLC_CP_SCHEDULERS, tmp); + WREG32_SOC15_RLC(GC, GET_INST(GC, xcc_id), regRLC_CP_SCHEDULERS, tmp | 0x80); } static void gfx_v9_4_3_mqd_set_priority(struct amdgpu_ring *ring, struct v9_mqd *mqd) diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c index 8ca137313961..3b818441c7ba 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -1491,9 +1491,7 @@ static void mes_v11_0_kiq_setting(struct amdgpu_ring *ring) tmp = RREG32_SOC15(GC, 0, regRLC_CP_SCHEDULERS); tmp &= 0xffffff00; tmp |= (ring->me << 5) | (ring->pipe << 3) | (ring->queue); - WREG32_SOC15(GC, 0, regRLC_CP_SCHEDULERS, tmp); - tmp |= 0x80; - WREG32_SOC15(GC, 0, regRLC_CP_SCHEDULERS, tmp); + WREG32_SOC15(GC, 0, regRLC_CP_SCHEDULERS, tmp | 0x80); } static void mes_v11_0_kiq_clear(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c index 9d0e342a2f81..44b0d0f76944 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c @@ -1453,9 +1453,7 @@ static void mes_v12_0_kiq_setting(struct amdgpu_ring *ring) tmp = RREG32_SOC15(GC, 0, regRLC_CP_SCHEDULERS); tmp &= 0xffffff00; tmp |= (ring->me << 5) | (ring->pipe << 3) | (ring->queue); - WREG32_SOC15(GC, 0, regRLC_CP_SCHEDULERS, tmp); - tmp |= 0x80; - WREG32_SOC15(GC, 0, regRLC_CP_SCHEDULERS, tmp); + WREG32_SOC15(GC, 0, regRLC_CP_SCHEDULERS, tmp | 0x80); } static int mes_v12_0_kiq_hw_init(struct amdgpu_device *adev) -- 2.34.1 |
