diff options
Diffstat (limited to 'common/recipes-kernel/linux/linux-yocto-4.14.71/1070-Revert-Revert-drm-amdgpu-Program-ring-for-vce-instan.patch')
-rw-r--r-- | common/recipes-kernel/linux/linux-yocto-4.14.71/1070-Revert-Revert-drm-amdgpu-Program-ring-for-vce-instan.patch | 161 |
1 files changed, 161 insertions, 0 deletions
diff --git a/common/recipes-kernel/linux/linux-yocto-4.14.71/1070-Revert-Revert-drm-amdgpu-Program-ring-for-vce-instan.patch b/common/recipes-kernel/linux/linux-yocto-4.14.71/1070-Revert-Revert-drm-amdgpu-Program-ring-for-vce-instan.patch new file mode 100644 index 00000000..f4c12dfc --- /dev/null +++ b/common/recipes-kernel/linux/linux-yocto-4.14.71/1070-Revert-Revert-drm-amdgpu-Program-ring-for-vce-instan.patch @@ -0,0 +1,161 @@ +From 13413ecc53f6937a2e945f4f81f786663de3770e Mon Sep 17 00:00:00 2001 +From: Rex Zhu <Rex.Zhu@amd.com> +Date: Thu, 19 Oct 2017 14:54:16 +0800 +Subject: [PATCH 1070/4131] Revert "Revert "drm/amdgpu: Program ring for vce + instance 1 at its register space"" + +This reverts commit b65f7dba6f8642e644080549095f3ed6fc53ac12. +--- + drivers/gpu/drm/amd/amdgpu/vce_v3_0.c | 95 +++++++++++++++++++++++++---------- + 1 file changed, 68 insertions(+), 27 deletions(-) + +diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c +index 9ef8145..242dfb1 100644 +--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c ++++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c +@@ -77,13 +77,26 @@ static int vce_v3_0_set_clockgating_state(void *handle, + static uint64_t vce_v3_0_ring_get_rptr(struct amdgpu_ring *ring) + { + struct amdgpu_device *adev = ring->adev; ++ u32 v; ++ ++ mutex_lock(&adev->grbm_idx_mutex); ++ if (adev->vce.harvest_config == 0 || ++ adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE1) ++ WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(0)); ++ else if (adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE0) ++ WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(1)); + + if (ring == &adev->vce.ring[0]) +- return RREG32(mmVCE_RB_RPTR); ++ v = RREG32(mmVCE_RB_RPTR); + else if (ring == &adev->vce.ring[1]) +- return RREG32(mmVCE_RB_RPTR2); ++ v = RREG32(mmVCE_RB_RPTR2); + else +- return RREG32(mmVCE_RB_RPTR3); ++ v = RREG32(mmVCE_RB_RPTR3); ++ ++ WREG32(mmGRBM_GFX_INDEX, mmGRBM_GFX_INDEX_DEFAULT); ++ mutex_unlock(&adev->grbm_idx_mutex); ++ ++ return v; + } + + /** +@@ -96,13 +109,26 @@ static uint64_t vce_v3_0_ring_get_rptr(struct amdgpu_ring *ring) + static uint64_t vce_v3_0_ring_get_wptr(struct amdgpu_ring *ring) + { + struct amdgpu_device *adev = ring->adev; ++ u32 v; ++ ++ mutex_lock(&adev->grbm_idx_mutex); ++ if (adev->vce.harvest_config == 0 || ++ adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE1) ++ WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(0)); ++ else if (adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE0) ++ WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(1)); + + if (ring == &adev->vce.ring[0]) +- return RREG32(mmVCE_RB_WPTR); ++ v = RREG32(mmVCE_RB_WPTR); + else if (ring == &adev->vce.ring[1]) +- return RREG32(mmVCE_RB_WPTR2); ++ v = RREG32(mmVCE_RB_WPTR2); + else +- return RREG32(mmVCE_RB_WPTR3); ++ v = RREG32(mmVCE_RB_WPTR3); ++ ++ WREG32(mmGRBM_GFX_INDEX, mmGRBM_GFX_INDEX_DEFAULT); ++ mutex_unlock(&adev->grbm_idx_mutex); ++ ++ return v; + } + + /** +@@ -116,12 +142,22 @@ static void vce_v3_0_ring_set_wptr(struct amdgpu_ring *ring) + { + struct amdgpu_device *adev = ring->adev; + ++ mutex_lock(&adev->grbm_idx_mutex); ++ if (adev->vce.harvest_config == 0 || ++ adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE1) ++ WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(0)); ++ else if (adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE0) ++ WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(1)); ++ + if (ring == &adev->vce.ring[0]) + WREG32(mmVCE_RB_WPTR, lower_32_bits(ring->wptr)); + else if (ring == &adev->vce.ring[1]) + WREG32(mmVCE_RB_WPTR2, lower_32_bits(ring->wptr)); + else + WREG32(mmVCE_RB_WPTR3, lower_32_bits(ring->wptr)); ++ ++ WREG32(mmGRBM_GFX_INDEX, mmGRBM_GFX_INDEX_DEFAULT); ++ mutex_unlock(&adev->grbm_idx_mutex); + } + + static void vce_v3_0_override_vce_clock_gating(struct amdgpu_device *adev, bool override) +@@ -231,33 +267,38 @@ static int vce_v3_0_start(struct amdgpu_device *adev) + struct amdgpu_ring *ring; + int idx, r; + +- ring = &adev->vce.ring[0]; +- WREG32(mmVCE_RB_RPTR, lower_32_bits(ring->wptr)); +- WREG32(mmVCE_RB_WPTR, lower_32_bits(ring->wptr)); +- WREG32(mmVCE_RB_BASE_LO, ring->gpu_addr); +- WREG32(mmVCE_RB_BASE_HI, upper_32_bits(ring->gpu_addr)); +- WREG32(mmVCE_RB_SIZE, ring->ring_size / 4); +- +- ring = &adev->vce.ring[1]; +- WREG32(mmVCE_RB_RPTR2, lower_32_bits(ring->wptr)); +- WREG32(mmVCE_RB_WPTR2, lower_32_bits(ring->wptr)); +- WREG32(mmVCE_RB_BASE_LO2, ring->gpu_addr); +- WREG32(mmVCE_RB_BASE_HI2, upper_32_bits(ring->gpu_addr)); +- WREG32(mmVCE_RB_SIZE2, ring->ring_size / 4); +- +- ring = &adev->vce.ring[2]; +- WREG32(mmVCE_RB_RPTR3, lower_32_bits(ring->wptr)); +- WREG32(mmVCE_RB_WPTR3, lower_32_bits(ring->wptr)); +- WREG32(mmVCE_RB_BASE_LO3, ring->gpu_addr); +- WREG32(mmVCE_RB_BASE_HI3, upper_32_bits(ring->gpu_addr)); +- WREG32(mmVCE_RB_SIZE3, ring->ring_size / 4); +- + mutex_lock(&adev->grbm_idx_mutex); + for (idx = 0; idx < 2; ++idx) { + if (adev->vce.harvest_config & (1 << idx)) + continue; + + WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(idx)); ++ ++ /* Program instance 0 reg space for two instances or instance 0 case ++ program instance 1 reg space for only instance 1 available case */ ++ if (idx != 1 || adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE0) { ++ ring = &adev->vce.ring[0]; ++ WREG32(mmVCE_RB_RPTR, lower_32_bits(ring->wptr)); ++ WREG32(mmVCE_RB_WPTR, lower_32_bits(ring->wptr)); ++ WREG32(mmVCE_RB_BASE_LO, ring->gpu_addr); ++ WREG32(mmVCE_RB_BASE_HI, upper_32_bits(ring->gpu_addr)); ++ WREG32(mmVCE_RB_SIZE, ring->ring_size / 4); ++ ++ ring = &adev->vce.ring[1]; ++ WREG32(mmVCE_RB_RPTR2, lower_32_bits(ring->wptr)); ++ WREG32(mmVCE_RB_WPTR2, lower_32_bits(ring->wptr)); ++ WREG32(mmVCE_RB_BASE_LO2, ring->gpu_addr); ++ WREG32(mmVCE_RB_BASE_HI2, upper_32_bits(ring->gpu_addr)); ++ WREG32(mmVCE_RB_SIZE2, ring->ring_size / 4); ++ ++ ring = &adev->vce.ring[2]; ++ WREG32(mmVCE_RB_RPTR3, lower_32_bits(ring->wptr)); ++ WREG32(mmVCE_RB_WPTR3, lower_32_bits(ring->wptr)); ++ WREG32(mmVCE_RB_BASE_LO3, ring->gpu_addr); ++ WREG32(mmVCE_RB_BASE_HI3, upper_32_bits(ring->gpu_addr)); ++ WREG32(mmVCE_RB_SIZE3, ring->ring_size / 4); ++ } ++ + vce_v3_0_mc_resume(adev, idx); + WREG32_FIELD(VCE_STATUS, JOB_BUSY, 1); + +-- +2.7.4 + |