drm/amdgpu:add VCN booting with firmware loaded by PSP

commit 4d77c0f676e910fb1f1870738aa4bd168f253621 upstream.

Setup psp firmware loading for VCN, and make VCN block
booting from tmr mac address.

Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Likun Gao <Likun.Gao@amd.com>
Signed-off-by: Likun Gao <Likun.Gao@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 308a975..1612d8a 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -93,9 +93,10 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
                version_major, version_minor, family_id);
 
 
-       bo_size = AMDGPU_GPU_PAGE_ALIGN(le32_to_cpu(hdr->ucode_size_bytes) + 8)
-                 +  AMDGPU_VCN_STACK_SIZE + AMDGPU_VCN_HEAP_SIZE
+       bo_size = AMDGPU_VCN_STACK_SIZE + AMDGPU_VCN_HEAP_SIZE
                  +  AMDGPU_VCN_SESSION_SIZE * 40;
+       if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP)
+               bo_size += AMDGPU_GPU_PAGE_ALIGN(le32_to_cpu(hdr->ucode_size_bytes) + 8);
        r = amdgpu_bo_create_kernel(adev, bo_size, PAGE_SIZE,
                                    AMDGPU_GEM_DOMAIN_VRAM, &adev->vcn.vcpu_bo,
                                    &adev->vcn.gpu_addr, &adev->vcn.cpu_addr);
@@ -191,11 +192,13 @@ int amdgpu_vcn_resume(struct amdgpu_device *adev)
                unsigned offset;
 
                hdr = (const struct common_firmware_header *)adev->vcn.fw->data;
-               offset = le32_to_cpu(hdr->ucode_array_offset_bytes);
-               memcpy_toio(adev->vcn.cpu_addr, adev->vcn.fw->data + offset,
-                           le32_to_cpu(hdr->ucode_size_bytes));
-               size -= le32_to_cpu(hdr->ucode_size_bytes);
-               ptr += le32_to_cpu(hdr->ucode_size_bytes);
+               if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP) {
+                       offset = le32_to_cpu(hdr->ucode_array_offset_bytes);
+                       memcpy_toio(adev->vcn.cpu_addr, adev->vcn.fw->data + offset,
+                                   le32_to_cpu(hdr->ucode_size_bytes));
+                       size -= le32_to_cpu(hdr->ucode_size_bytes);
+                       ptr += le32_to_cpu(hdr->ucode_size_bytes);
+               }
                memset_io(ptr, 0, size);
        }
 

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index a098712..f7b8cac 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -91,6 +91,16 @@ static int vcn_v1_0_sw_init(void *handle)
        if (r)
                return r;
 
+       if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
+               const struct common_firmware_header *hdr;
+               hdr = (const struct common_firmware_header *)adev->vcn.fw->data;
+               adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].ucode_id = AMDGPU_UCODE_ID_VCN;
+               adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].fw = adev->vcn.fw;
+               adev->firmware.fw_size +=
+                       ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE);
+               DRM_INFO("PSP loading VCN firmware\n");
+       }
+
        r = amdgpu_vcn_resume(adev);
        if (r)
                return r;
@@ -248,26 +258,38 @@ static int vcn_v1_0_resume(void *handle)
 static void vcn_v1_0_mc_resume(struct amdgpu_device *adev)
 {
        uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->vcn.fw->size + 4);
-
-       WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
+       uint32_t offset;
+
+       if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
+               WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
+                            (adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].tmr_mc_addr_lo));
+               WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH,
+                            (adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].tmr_mc_addr_hi));
+               WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_OFFSET0, 0);
+               offset = 0;
+       } else {
+               WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
                        lower_32_bits(adev->vcn.gpu_addr));
-       WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH,
+               WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH,
                        upper_32_bits(adev->vcn.gpu_addr));
-       WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_OFFSET0,
-                               AMDGPU_UVD_FIRMWARE_OFFSET >> 3);
+               offset = size;
+               WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_OFFSET0,
+                            AMDGPU_UVD_FIRMWARE_OFFSET >> 3);
+       }
+
        WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_SIZE0, size);
 
        WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW,
-                       lower_32_bits(adev->vcn.gpu_addr + size));
+                    lower_32_bits(adev->vcn.gpu_addr + offset));
        WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_HIGH,
-                       upper_32_bits(adev->vcn.gpu_addr + size));
+                    upper_32_bits(adev->vcn.gpu_addr + offset));
        WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_OFFSET1, 0);
        WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_SIZE1, AMDGPU_VCN_HEAP_SIZE);
 
        WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_LOW,
-                       lower_32_bits(adev->vcn.gpu_addr + size + AMDGPU_VCN_HEAP_SIZE));
+                    lower_32_bits(adev->vcn.gpu_addr + offset + AMDGPU_VCN_HEAP_SIZE));
        WREG32_SOC15(UVD, 0, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_HIGH,
-                       upper_32_bits(adev->vcn.gpu_addr + size + AMDGPU_VCN_HEAP_SIZE));
+                    upper_32_bits(adev->vcn.gpu_addr + offset + AMDGPU_VCN_HEAP_SIZE));
        WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_OFFSET2, 0);
        WREG32_SOC15(UVD, 0, mmUVD_VCPU_CACHE_SIZE2,
                        AMDGPU_VCN_STACK_SIZE + (AMDGPU_VCN_SESSION_SIZE * 40));