diff options
44 files changed, 346 insertions, 156 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 9f1a5bd39ae8..5b39d1399630 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -131,6 +131,11 @@ psp_cmd_submit_buf(struct psp_context *psp, msleep(1); } + if (ucode) { + ucode->tmr_mc_addr_lo = psp->cmd_buf_mem->resp.fw_addr_lo; + ucode->tmr_mc_addr_hi = psp->cmd_buf_mem->resp.fw_addr_hi; + } + return ret; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h index 08e38579af24..bdc472b6e641 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h @@ -194,6 +194,7 @@ enum AMDGPU_UCODE_ID { AMDGPU_UCODE_ID_SMC, AMDGPU_UCODE_ID_UVD, AMDGPU_UCODE_ID_VCE, + AMDGPU_UCODE_ID_VCN, AMDGPU_UCODE_ID_MAXIMUM, }; @@ -226,6 +227,9 @@ struct amdgpu_firmware_info { void *kaddr; /* ucode_size_bytes */ uint32_t ucode_size; + /* starting tmr mc address */ + uint32_t tmr_mc_addr_lo; + uint32_t tmr_mc_addr_hi; }; void amdgpu_ucode_print_mc_hdr(const struct common_firmware_header *hdr); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index 632fa5980ff4..e5a6db6beab7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -122,8 +122,6 @@ static void amdgpu_uvd_idle_work_handler(struct work_struct *work); int amdgpu_uvd_sw_init(struct amdgpu_device *adev) { - struct amdgpu_ring *ring; - struct drm_sched_rq *rq; unsigned long bo_size; const char *fw_name; const struct common_firmware_header *hdr; @@ -266,13 +264,6 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev) } } - ring = &adev->uvd.inst[0].ring; - rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL]; - r = drm_sched_entity_init(&adev->uvd.entity, &rq, 1, NULL); - if (r) { - DRM_ERROR("Failed setting up UVD kernel entity.\n"); - return r; - } for (i = 0; i < adev->uvd.max_handles; ++i) { atomic_set(&adev->uvd.handles[i], 0); adev->uvd.filp[i] = NULL; @@ -311,7 +302,7 @@ int amdgpu_uvd_sw_fini(struct amdgpu_device *adev) for (j = 0; j < adev->uvd.num_uvd_inst; ++j) { if (adev->uvd.harvest_config & (1 << j)) continue; - kfree(adev->uvd.inst[j].saved_bo); + kvfree(adev->uvd.inst[j].saved_bo); amdgpu_bo_free_kernel(&adev->uvd.inst[j].vcpu_bo, &adev->uvd.inst[j].gpu_addr, @@ -327,6 +318,29 @@ int amdgpu_uvd_sw_fini(struct amdgpu_device *adev) return 0; } +/** + * amdgpu_uvd_entity_init - init entity + * + * @adev: amdgpu_device pointer + * + */ +int amdgpu_uvd_entity_init(struct amdgpu_device *adev) +{ + struct amdgpu_ring *ring; + struct drm_sched_rq *rq; + int r; + + ring = &adev->uvd.inst[0].ring; + rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL]; + r = drm_sched_entity_init(&adev->uvd.entity, &rq, 1, NULL); + if (r) { + DRM_ERROR("Failed setting up UVD kernel entity.\n"); + return r; + } + + return 0; +} + int amdgpu_uvd_suspend(struct amdgpu_device *adev) { unsigned size; @@ -354,7 +368,7 @@ int amdgpu_uvd_suspend(struct amdgpu_device *adev) size = amdgpu_bo_size(adev->uvd.inst[j].vcpu_bo); ptr = adev->uvd.inst[j].cpu_addr; - adev->uvd.inst[j].saved_bo = kmalloc(size, GFP_KERNEL); + adev->uvd.inst[j].saved_bo = kvmalloc(size, GFP_KERNEL); if (!adev->uvd.inst[j].saved_bo) return -ENOMEM; @@ -380,7 +394,7 @@ int amdgpu_uvd_resume(struct amdgpu_device *adev) if (adev->uvd.inst[i].saved_bo != NULL) { memcpy_toio(ptr, adev->uvd.inst[i].saved_bo, size); - kfree(adev->uvd.inst[i].saved_bo); + kvfree(adev->uvd.inst[i].saved_bo); adev->uvd.inst[i].saved_bo = NULL; } else { const struct common_firmware_header *hdr; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h index 33c5f806f925..a3ab1a41060f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h @@ -69,6 +69,7 @@ struct amdgpu_uvd { int amdgpu_uvd_sw_init(struct amdgpu_device *adev); int amdgpu_uvd_sw_fini(struct amdgpu_device *adev); +int amdgpu_uvd_entity_init(struct amdgpu_device *adev); int amdgpu_uvd_suspend(struct amdgpu_device *adev); int amdgpu_uvd_resume(struct amdgpu_device *adev); int amdgpu_uvd_get_create_msg(struct amdgpu_ring *ring, uint32_t handle, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c index b6ab4f5350c8..0cc5190f4f36 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c @@ -90,8 +90,6 @@ static void amdgpu_vce_idle_work_handler(struct work_struct *work); */ int amdgpu_vce_sw_init(struct amdgpu_device *adev, unsigned long size) { - struct amdgpu_ring *ring; - struct drm_sched_rq *rq; const char *fw_name; const struct common_firmware_header *hdr; unsigned ucode_version, version_major, version_minor, binary_id; @@ -188,14 +186,6 @@ int amdgpu_vce_sw_init(struct amdgpu_device *adev, unsigned long size) return r; } - ring = &adev->vce.ring[0]; - rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL]; - r = drm_sched_entity_init(&adev->vce.entity, &rq, 1, NULL); - if (r != 0) { - DRM_ERROR("Failed setting up VCE run queue.\n"); - return r; - } - for (i = 0; i < AMDGPU_MAX_VCE_HANDLES; ++i) { atomic_set(&adev->vce.handles[i], 0); adev->vce.filp[i] = NULL; @@ -236,6 +226,29 @@ int amdgpu_vce_sw_fini(struct amdgpu_device *adev) } /** + * amdgpu_vce_entity_init - init entity + * + * @adev: amdgpu_device pointer + * + */ +int amdgpu_vce_entity_init(struct amdgpu_device *adev) +{ + struct amdgpu_ring *ring; + struct drm_sched_rq *rq; + int r; + + ring = &adev->vce.ring[0]; + rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL]; + r = drm_sched_entity_init(&adev->vce.entity, &rq, 1, NULL); + if (r != 0) { + DRM_ERROR("Failed setting up VCE run queue.\n"); + return r; + } + + return 0; +} + +/** * amdgpu_vce_suspend - unpin VCE fw memory * * @adev: amdgpu_device pointer diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h index 71781267ee4c..a1f209eed4c4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h @@ -55,6 +55,7 @@ struct amdgpu_vce { int amdgpu_vce_sw_init(struct amdgpu_device *adev, unsigned long size); int amdgpu_vce_sw_fini(struct amdgpu_device *adev); +int amdgpu_vce_entity_init(struct amdgpu_device *adev); int amdgpu_vce_suspend(struct amdgpu_device *adev); int amdgpu_vce_resume(struct amdgpu_device *adev); int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index 798648a19710..fd654a4406db 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -111,9 +111,10 @@ 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); @@ -129,7 +130,7 @@ int amdgpu_vcn_sw_fini(struct amdgpu_device *adev) { int i; - kfree(adev->vcn.saved_bo); + kvfree(adev->vcn.saved_bo); amdgpu_bo_free_kernel(&adev->vcn.vcpu_bo, &adev->vcn.gpu_addr, @@ -160,7 +161,7 @@ int amdgpu_vcn_suspend(struct amdgpu_device *adev) size = amdgpu_bo_size(adev->vcn.vcpu_bo); ptr = adev->vcn.cpu_addr; - adev->vcn.saved_bo = kmalloc(size, GFP_KERNEL); + adev->vcn.saved_bo = kvmalloc(size, GFP_KERNEL); if (!adev->vcn.saved_bo) return -ENOMEM; @@ -182,18 +183,20 @@ int amdgpu_vcn_resume(struct amdgpu_device *adev) if (adev->vcn.saved_bo != NULL) { memcpy_toio(ptr, adev->vcn.saved_bo, size); - kfree(adev->vcn.saved_bo); + kvfree(adev->vcn.saved_bo); adev->vcn.saved_bo = NULL; } else { const struct common_firmware_header *hdr; 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/psp_v10_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c index 0ff136d02d9b..02be34e72ed9 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c @@ -88,6 +88,9 @@ psp_v10_0_get_fw_type(struct amdgpu_firmware_info *ucode, enum psp_gfx_fw_type * case AMDGPU_UCODE_ID_VCE: *type = GFX_FW_TYPE_VCE; break; + case AMDGPU_UCODE_ID_VCN: + *type = GFX_FW_TYPE_VCN; + break; case AMDGPU_UCODE_ID_MAXIMUM: default: return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c index 6fed3d7797a8..8a926d1df939 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c @@ -123,6 +123,10 @@ static int uvd_v4_2_sw_init(void *handle) ring = &adev->uvd.inst->ring; sprintf(ring->name, "uvd"); r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.inst->irq, 0); + if (r) + return r; + + r = amdgpu_uvd_entity_init(adev); return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c index aeaa1ca46a99..50248059412e 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c @@ -120,6 +120,10 @@ static int uvd_v5_0_sw_init(void *handle) ring = &adev->uvd.inst->ring; sprintf(ring->name, "uvd"); r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.inst->irq, 0); + if (r) + return r; + + r = amdgpu_uvd_entity_init(adev); return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c index 598dbeaba636..6ae82cc2e55e 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c @@ -440,6 +440,8 @@ static int uvd_v6_0_sw_init(void *handle) } } + r = amdgpu_uvd_entity_init(adev); + return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c index 5fab3560a71d..9b7f8469bc5c 100644 --- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c @@ -410,6 +410,7 @@ static int uvd_v7_0_early_init(void *handle) static int uvd_v7_0_sw_init(void *handle) { struct amdgpu_ring *ring; + int i, j, r; struct amdgpu_device *adev = (struct amdgpu_device *)handle; @@ -478,6 +479,10 @@ static int uvd_v7_0_sw_init(void *handle) } } + r = amdgpu_uvd_entity_init(adev); + if (r) + return r; + r = amdgpu_virt_alloc_mm_table(adev); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c index d48e877b682e..7eaa54ba016b 100644 --- a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c @@ -439,6 +439,8 @@ static int vce_v2_0_sw_init(void *handle) return r; } + r = amdgpu_vce_entity_init(adev); + return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c index cc6ce6cc03f4..c8390f9adfd6 100644 --- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c @@ -448,6 +448,8 @@ static int vce_v3_0_sw_init(void *handle) return r; } + r = amdgpu_vce_entity_init(adev); + return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c index 65f8860169e9..2e4d1b5f6243 100644 --- a/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c @@ -419,6 +419,7 @@ static int vce_v4_0_sw_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; struct amdgpu_ring *ring; + unsigned size; int r, i; @@ -438,7 +439,7 @@ static int vce_v4_0_sw_init(void *handle) const struct common_firmware_header *hdr; unsigned size = amdgpu_bo_size(adev->vce.vcpu_bo); - adev->vce.saved_bo = kmalloc(size, GFP_KERNEL); + adev->vce.saved_bo = kvmalloc(size, GFP_KERNEL); if (!adev->vce.saved_bo) return -ENOMEM; @@ -474,6 +475,11 @@ static int vce_v4_0_sw_init(void *handle) return r; } + + r = amdgpu_vce_entity_init(adev); + if (r) + return r; + r = amdgpu_virt_alloc_mm_table(adev); if (r) return r; @@ -490,7 +496,7 @@ static int vce_v4_0_sw_fini(void *handle) amdgpu_virt_free_mm_table(adev); if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { - kfree(adev->vce.saved_bo); + kvfree(adev->vce.saved_bo); adev->vce.saved_bo = NULL; } diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c index 2ce91a748c40..072371ef5975 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c @@ -100,6 +100,16 @@ 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; @@ -265,26 +275,38 @@ 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)); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c index 52f2c01349e3..9bfb040352e9 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c @@ -98,10 +98,16 @@ int amdgpu_dm_crtc_set_crc_source(struct drm_crtc *crtc, const char *src_name, */ void amdgpu_dm_crtc_handle_crc_irq(struct drm_crtc *crtc) { - struct dm_crtc_state *crtc_state = to_dm_crtc_state(crtc->state); - struct dc_stream_state *stream_state = crtc_state->stream; + struct dm_crtc_state *crtc_state; + struct dc_stream_state *stream_state; uint32_t crcs[3]; + if (crtc == NULL) + return; + + crtc_state = to_dm_crtc_state(crtc->state); + stream_state = crtc_state->stream; + /* Early return if CRC capture is not enabled. */ if (!crtc_state->crc_enabled) return; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index a38e7ad36a7e..326b3e99b7e4 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -1812,6 +1812,8 @@ static void enable_link_hdmi(struct pipe_ctx *pipe_ctx) bool is_vga_mode = (stream->timing.h_addressable == 640) && (stream->timing.v_addressable == 480); + if (stream->phy_pix_clk == 0) + stream->phy_pix_clk = stream->timing.pix_clk_khz; if (stream->phy_pix_clk > 340000) is_over_340mhz = true; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 4ca41d6e3bcf..1644f2a946b0 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -268,24 +268,30 @@ bool resource_construct( return true; } +static int find_matching_clock_source( + const struct resource_pool *pool, + struct clock_source *clock_source) +{ + + int i; + for (i = 0; i < pool->clk_src_count; i++) { + if (pool->clock_sources[i] == clock_source) + return i; + } + return -1; +} void resource_unreference_clock_source( struct resource_context *res_ctx, const struct resource_pool *pool, struct clock_source *clock_source) { - int i; - - for (i = 0; i < pool->clk_src_count; i++) { - if (pool->clock_sources[i] != clock_source) - continue; + int i = find_matching_clock_source(pool, clock_source); + if (i > -1) res_ctx->clock_source_ref_count[i]--; - break; - } - if (pool->dp_clock_source == clock_source) res_ctx->dp_clock_source_ref_count--; } @@ -295,19 +301,31 @@ void resource_reference_clock_source( const struct resource_pool *pool, struct clock_source *clock_source) { - int i; - for (i = 0; i < pool->clk_src_count; i++) { - if (pool->clock_sources[i] != clock_source) - continue; + int i = find_matching_clock_source(pool, clock_source); + if (i > -1) res_ctx->clock_source_ref_count[i]++; - break; - } if (pool->dp_clock_source == clock_source) res_ctx->dp_clock_source_ref_count++; } +int resource_get_clock_source_reference( + struct resource_context *res_ctx, + const struct resource_pool *pool, + struct clock_source *clock_source) +{ + int i = find_matching_clock_source(pool, clock_source); + + if (i > -1) + return res_ctx->clock_source_ref_count[i]; + + if (pool->dp_clock_source == clock_source) + return res_ctx->dp_clock_source_ref_count; + + return -1; +} + bool resource_are_streams_timing_synchronizable( struct dc_stream_state *stream1, struct dc_stream_state *stream2) @@ -372,11 +390,11 @@ static bool is_sharable_clk_src( return false; if (dc_is_hdmi_signal(pipe_with_clk_src->stream->signal) - && dc_is_dvi_signal(pipe->stream->signal)) + && dc_is_dual_link_signal(pipe->stream->signal)) return false; if (dc_is_hdmi_signal(pipe->stream->signal) - && dc_is_dvi_signal(pipe_with_clk_src->stream->signal)) + && dc_is_dual_link_signal(pipe_with_clk_src->stream->signal)) return false; if (!resource_are_streams_timing_synchronizable( diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c index 752b3d62e793..eff7d22d78fb 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c @@ -930,7 +930,7 @@ void dce110_link_encoder_enable_tmds_output( enum bp_result result; /* Enable the PHY */ - + cntl.connector_obj_id = enc110->base.connector; cntl.action = TRANSMITTER_CONTROL_ENABLE; cntl.engine_id = enc->preferred_engine; cntl.transmitter = enc110->base.transmitter; @@ -972,7 +972,7 @@ void dce110_link_encoder_enable_dp_output( * We need to set number of lanes manually. */ configure_encoder(enc110, link_settings); - + cntl.connector_obj_id = enc110->base.connector; cntl.action = TRANSMITTER_CONTROL_ENABLE; cntl.engine_id = enc->preferred_engine; cntl.transmitter = enc110->base.transmitter; diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c index 1d98e3678b04..5450d4d38e8a 100644 --- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c @@ -1908,7 +1908,9 @@ static void dce110_reset_hw_ctx_wrap( pipe_ctx_old->plane_res.mi->funcs->free_mem_input( pipe_ctx_old->plane_res.mi, dc->current_state->stream_count); - if (old_clk) + if (old_clk && 0 == resource_get_clock_source_reference(&context->res_ctx, + dc->res_pool, + old_clk)) old_clk->funcs->cs_power_down(old_clk); dc->hwss.disable_plane(dc, pipe_ctx_old); diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_timing_generator.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_timing_generator.c index 2ea490f8482e..04b866f0fa1f 100644 --- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_timing_generator.c +++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_timing_generator.c @@ -772,7 +772,7 @@ void dce120_tg_set_blank(struct timing_generator *tg, CRTC_REG_SET( CRTC0_CRTC_DOUBLE_BUFFER_CONTROL, - CRTC_BLANK_DATA_DOUBLE_BUFFER_EN, 0); + CRTC_BLANK_DATA_DOUBLE_BUFFER_EN, 1); if (enable_blanking) CRTC_REG_SET(CRTC0_CRTC_BLANK_CONTROL, CRTC_BLANK_DATA_EN, 1); diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h index e92facbd038f..5b321008b0b5 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/resource.h +++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h @@ -103,6 +103,11 @@ void resource_reference_clock_source( const struct resource_pool *pool, struct clock_source *clock_source); +int resource_get_clock_source_reference( + struct resource_context *res_ctx, + const struct resource_pool *pool, + struct clock_source *clock_source); + bool resource_are_streams_timing_synchronizable( struct dc_stream_state *stream1, struct dc_stream_state *stream2); diff --git a/drivers/gpu/drm/i915/gvt/aperture_gm.c b/drivers/gpu/drm/i915/gvt/aperture_gm.c index 380eeb2a0e83..fe754022e356 100644 --- a/drivers/gpu/drm/i915/gvt/aperture_gm.c +++ b/drivers/gpu/drm/i915/gvt/aperture_gm.c @@ -131,7 +131,7 @@ void intel_vgpu_write_fence(struct intel_vgpu *vgpu, assert_rpm_wakelock_held(dev_priv); - if (WARN_ON(fence > vgpu_fence_sz(vgpu))) + if (WARN_ON(fence >= vgpu_fence_sz(vgpu))) return; reg = vgpu->fence.regs[fence]; diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c index 45e89b1e0481..a614db310ea2 100644 --- a/drivers/gpu/drm/i915/gvt/cmd_parser.c +++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c @@ -874,7 +874,7 @@ static int cmd_reg_handler(struct parser_exec_state *s, if (!intel_gvt_mmio_is_cmd_access(gvt, offset)) { gvt_vgpu_err("%s access to non-render register (%x)\n", cmd, offset); - return 0; + return -EBADRQC; } if (is_shadowed_mmio(offset)) { diff --git a/drivers/gpu/drm/i915/gvt/gvt.c b/drivers/gpu/drm/i915/gvt/gvt.c index 712f9d14e720..46c8b720e336 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.c +++ b/drivers/gpu/drm/i915/gvt/gvt.c @@ -176,6 +176,7 @@ static const struct intel_gvt_ops intel_gvt_ops = { .emulate_mmio_write = intel_vgpu_emulate_mmio_write, .vgpu_create = intel_gvt_create_vgpu, .vgpu_destroy = intel_gvt_destroy_vgpu, + .vgpu_release = intel_gvt_release_vgpu, .vgpu_reset = intel_gvt_reset_vgpu, .vgpu_activate = intel_gvt_activate_vgpu, .vgpu_deactivate = intel_gvt_deactivate_vgpu, @@ -315,6 +316,11 @@ void intel_gvt_clean_device(struct drm_i915_private *dev_priv) if (WARN_ON(!gvt)) return; + intel_gvt_destroy_idle_vgpu(gvt->idle_vgpu); + intel_gvt_hypervisor_host_exit(&dev_priv->drm.pdev->dev, gvt); + intel_gvt_cleanup_vgpu_type_groups(gvt); + intel_gvt_clean_vgpu_types(gvt); + intel_gvt_debugfs_clean(gvt); clean_service_thread(gvt); intel_gvt_clean_cmd_parser(gvt); @@ -322,17 +328,10 @@ void intel_gvt_clean_device(struct drm_i915_private *dev_priv) intel_gvt_clean_workload_scheduler(gvt); intel_gvt_clean_gtt(gvt); intel_gvt_clean_irq(gvt); - intel_gvt_clean_mmio_info(gvt); intel_gvt_free_firmware(gvt); - - intel_gvt_hypervisor_host_exit(&dev_priv->drm.pdev->dev, gvt); - intel_gvt_cleanup_vgpu_type_groups(gvt); - intel_gvt_clean_vgpu_types(gvt); - + intel_gvt_clean_mmio_info(gvt); idr_destroy(&gvt->vgpu_idr); - intel_gvt_destroy_idle_vgpu(gvt->idle_vgpu); - kfree(dev_priv->gvt); dev_priv->gvt = NULL; } diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h index 9a9671522774..31f6cdbe5c42 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.h +++ b/drivers/gpu/drm/i915/gvt/gvt.h @@ -486,6 +486,7 @@ void intel_gvt_destroy_idle_vgpu(struct intel_vgpu *vgpu); struct intel_vgpu *intel_gvt_create_vgpu(struct intel_gvt *gvt, struct intel_vgpu_type *type); void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu); +void intel_gvt_release_vgpu(struct intel_vgpu *vgpu); void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr, unsigned int engine_mask); void intel_gvt_reset_vgpu(struct intel_vgpu *vgpu); @@ -563,7 +564,8 @@ struct intel_gvt_ops { unsigned int); struct intel_vgpu *(*vgpu_create)(struct intel_gvt *, struct intel_vgpu_type *); - void (*vgpu_destroy)(struct intel_vgpu *); + void (*vgpu_destroy)(struct intel_vgpu *vgpu); + void (*vgpu_release)(struct intel_vgpu *vgpu); void (*vgpu_reset)(struct intel_vgpu *); void (*vgpu_activate)(struct intel_vgpu *); void (*vgpu_deactivate)(struct intel_vgpu *); diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index 4d2f53ae9f0f..a45f46d8537f 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -43,6 +43,8 @@ #include <linux/mdev.h> #include <linux/debugfs.h> +#include <linux/nospec.h> + #include "i915_drv.h" #include "gvt.h" @@ -187,14 +189,14 @@ static int gvt_dma_map_page(struct intel_vgpu *vgpu, unsigned long gfn, /* Setup DMA mapping. */ *dma_addr = dma_map_page(dev, page, 0, size, PCI_DMA_BIDIRECTIONAL); - ret = dma_mapping_error(dev, *dma_addr); - if (ret) { + if (dma_mapping_error(dev, *dma_addr)) { gvt_vgpu_err("DMA mapping failed for pfn 0x%lx, ret %d\n", page_to_pfn(page), ret); gvt_unpin_guest_page(vgpu, gfn, size); + return -ENOMEM; } - return ret; + return 0; } static void gvt_dma_unmap_page(struct intel_vgpu *vgpu, unsigned long gfn, @@ -666,7 +668,7 @@ static void __intel_vgpu_release(struct intel_vgpu *vgpu) if (atomic_cmpxchg(&vgpu->vdev.released, 0, 1)) return; - intel_gvt_ops->vgpu_deactivate(vgpu); + intel_gvt_ops->vgpu_release(vgpu); ret = vfio_unregister_notifier(mdev_dev(vgpu->vdev.mdev), VFIO_IOMMU_NOTIFY, &vgpu->vdev.iommu_notifier); @@ -1139,7 +1141,8 @@ static long intel_vgpu_ioctl(struct mdev_device *mdev, unsigned int cmd, } else if (cmd == VFIO_DEVICE_GET_REGION_INFO) { struct vfio_region_info info; struct vfio_info_cap caps = { .buf = NULL, .size = 0 }; - int i, ret; + unsigned int i; + int ret; struct vfio_region_info_cap_sparse_mmap *sparse = NULL; size_t size; int nr_areas = 1; @@ -1224,6 +1227,10 @@ static long intel_vgpu_ioctl(struct mdev_device *mdev, unsigned int cmd, if (info.index >= VFIO_PCI_NUM_REGIONS + vgpu->vdev.num_regions) return -EINVAL; + info.index = + array_index_nospec(info.index, + VFIO_PCI_NUM_REGIONS + + vgpu->vdev.num_regions); i = info.index - VFIO_PCI_NUM_REGIONS; @@ -1250,11 +1257,13 @@ static long intel_vgpu_ioctl(struct mdev_device *mdev, unsigned int cmd, &sparse->header, sizeof(*sparse) + (sparse->nr_areas * sizeof(*sparse->areas))); - kfree(sparse); - if (ret) + if (ret) { + kfree(sparse); return ret; + } break; default: + kfree(sparse); return -EINVAL; } } @@ -1270,6 +1279,7 @@ static long intel_vgpu_ioctl(struct mdev_device *mdev, unsigned int cmd, sizeof(info), caps.buf, caps.size)) { kfree(caps.buf); + kfree(sparse); return -EFAULT; } info.cap_offset = sizeof(info); @@ -1278,6 +1288,7 @@ static long intel_vgpu_ioctl(struct mdev_device *mdev, unsigned int cmd, kfree(caps.buf); } + kfree(sparse); return copy_to_user((void __user *)arg, &info, minsz) ? -EFAULT : 0; } else if (cmd == VFIO_DEVICE_GET_IRQ_INFO) { @@ -1615,7 +1626,6 @@ static int kvmgt_guest_init(struct mdev_device *mdev) kvmgt_protect_table_init(info); gvt_cache_init(vgpu); - mutex_init(&vgpu->dmabuf_lock); init_completion(&vgpu->vblank_done); info->track_node.track_write = kvmgt_page_track_write; diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index b0e566956b8d..43aa058e29fc 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -784,7 +784,8 @@ static void update_guest_context(struct intel_vgpu_workload *workload) kunmap(page); } -static void clean_workloads(struct intel_vgpu *vgpu, unsigned long engine_mask) +void intel_vgpu_clean_workloads(struct intel_vgpu *vgpu, + unsigned long engine_mask) { struct intel_vgpu_submission *s = &vgpu->submission; struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; @@ -879,7 +880,7 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id) * cleaned up during the resetting process later, so doing * the workload clean up here doesn't have any impact. **/ - clean_workloads(vgpu, ENGINE_MASK(ring_id)); + intel_vgpu_clean_workloads(vgpu, ENGINE_MASK(ring_id)); } workload->complete(workload); @@ -1081,7 +1082,7 @@ void intel_vgpu_reset_submission(struct intel_vgpu *vgpu, if (!s->active) return; - clean_workloads(vgpu, engine_mask); + intel_vgpu_clean_workloads(vgpu, engine_mask); s->ops->reset(vgpu, engine_mask); } diff --git a/drivers/gpu/drm/i915/gvt/scheduler.h b/drivers/gpu/drm/i915/gvt/scheduler.h index 21eddab4a9cd..ca5529d0e48e 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.h +++ b/drivers/gpu/drm/i915/gvt/scheduler.h @@ -158,4 +158,7 @@ intel_vgpu_create_workload(struct intel_vgpu *vgpu, int ring_id, void intel_vgpu_destroy_workload(struct intel_vgpu_workload *workload); +void intel_vgpu_clean_workloads(struct intel_vgpu *vgpu, + unsigned long engine_mask); + #endif diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index f6fa916517c3..a4e8e3cf74fd 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -222,7 +222,7 @@ void intel_gvt_activate_vgpu(struct intel_vgpu *vgpu) * @vgpu: virtual GPU * * This function is called when user wants to deactivate a virtual GPU. - * All virtual GPU runtime information will be destroyed. + * The virtual GPU will be stopped. * */ void intel_gvt_deactivate_vgpu(struct intel_vgpu *vgpu) @@ -238,12 +238,30 @@ void intel_gvt_deactivate_vgpu(struct intel_vgpu *vgpu) } intel_vgpu_stop_schedule(vgpu); - intel_vgpu_dmabuf_cleanup(vgpu); mutex_unlock(&vgpu->vgpu_lock); } /** + * intel_gvt_release_vgpu - release a virtual GPU + * @vgpu: virtual GPU + * + * This function is called when user wants to release a virtual GPU. + * The virtual GPU will be stopped and all runtime information will be + * destroyed. + * + */ +void intel_gvt_release_vgpu(struct intel_vgpu *vgpu) +{ + intel_gvt_deactivate_vgpu(vgpu); + + mutex_lock(&vgpu->vgpu_lock); + intel_vgpu_clean_workloads(vgpu, ALL_ENGINES); + intel_vgpu_dmabuf_cleanup(vgpu); + mutex_unlock(&vgpu->vgpu_lock); +} + +/** * intel_gvt_destroy_vgpu - destroy a virtual GPU * @vgpu: virtual GPU * @@ -361,6 +379,7 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt, vgpu->gvt = gvt; vgpu->sched_ctl.weight = param->weight; mutex_init(&vgpu->vgpu_lock); + mutex_init(&vgpu->dmabuf_lock); INIT_LIST_HEAD(&vgpu->dmabuf_obj_list_head); INIT_RADIX_TREE(&vgpu->page_track_tree, GFP_KERNEL); idr_init(&vgpu->object_idr); diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 91e7483228e1..08ec7446282e 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -9201,6 +9201,7 @@ enum skl_power_gate { #define TRANS_MSA_10_BPC (2 << 5) #define TRANS_MSA_12_BPC (3 << 5) #define TRANS_MSA_16_BPC (4 << 5) +#define TRANS_MSA_CEA_RANGE (1 << 3) /* LCPLL Control */ #define LCPLL_CTL _MMIO(0x130040) diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index 39d66f8493fa..8761513f3532 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -1685,6 +1685,10 @@ void intel_ddi_set_pipe_settings(const struct intel_crtc_state *crtc_state) WARN_ON(transcoder_is_dsi(cpu_transcoder)); temp = TRANS_MSA_SYNC_CLK; + + if (crtc_state->limited_color_range) + temp |= TRANS_MSA_CEA_RANGE; + switch (crtc_state->pipe_bpp) { case 18: temp |= TRANS_MSA_6_BPC; diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 33faad3197fe..6a8f27d0a742 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -387,8 +387,18 @@ static void intel_ring_setup_status_page(struct intel_engine_cs *engine) mmio = RING_HWS_PGA(engine->mmio_base); } - if (INTEL_GEN(dev_priv) >= 6) - I915_WRITE(RING_HWSTAM(engine->mmio_base), 0xffffffff); + if (INTEL_GEN(dev_priv) >= 6) { + u32 mask = ~0u; + + /* + * Keep the render interrupt unmasked as this papers over + * lost interrupts following a reset. + */ + if (engine->id == RCS) + mask &= ~BIT(0); + + I915_WRITE(RING_HWSTAM(engine->mmio_base), mask); + } I915_WRITE(mmio, engine->status_page.ggtt_offset); POSTING_READ(mmio); diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index b892ca8396e8..50b39aa4ffb8 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -359,8 +359,8 @@ intel_uncore_fw_release_timer(struct hrtimer *timer) } /* Note callers must have acquired the PUNIT->PMIC bus, before calling this. */ -static void intel_uncore_forcewake_reset(struct drm_i915_private *dev_priv, - bool restore) +static unsigned int +intel_uncore_forcewake_reset(struct drm_i915_private *dev_priv) { unsigned long irqflags; struct intel_uncore_forcewake_domain *domain; @@ -412,20 +412,11 @@ static void intel_uncore_forcewake_reset(struct drm_i915_private *dev_priv, dev_priv->uncore.funcs.force_wake_put(dev_priv, fw); fw_domains_reset(dev_priv, dev_priv->uncore.fw_domains); - - if (restore) { /* If reset with a user forcewake, try to restore */ - if (fw) - dev_priv->uncore.funcs.force_wake_get(dev_priv, fw); - - if (IS_GEN6(dev_priv) || IS_GEN7(dev_priv)) - dev_priv->uncore.fifo_count = - fifo_free_entries(dev_priv); - } - - if (!restore) - assert_forcewakes_inactive(dev_priv); + assert_forcewakes_inactive(dev_priv); spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); + + return fw; /* track the lost user forcewake domains */ } static u64 gen9_edram_size(struct drm_i915_private *dev_priv) @@ -534,7 +525,7 @@ check_for_unclaimed_mmio(struct drm_i915_private *dev_priv) } static void __intel_uncore_early_sanitize(struct drm_i915_private *dev_priv, - bool restore_forcewake) + unsigned int restore_forcewake) { /* clear out unclaimed reg detection bit */ if (check_for_unclaimed_mmio(dev_priv)) @@ -549,7 +540,17 @@ static void __intel_uncore_early_sanitize(struct drm_i915_private *dev_priv, } iosf_mbi_punit_acquire(); - intel_uncore_forcewake_reset(dev_priv, restore_forcewake); + intel_uncore_forcewake_reset(dev_priv); + if (restore_forcewake) { + spin_lock_irq(&dev_priv->uncore.lock); + dev_priv->uncore.funcs.force_wake_get(dev_priv, + restore_forcewake); + + if (IS_GEN6(dev_priv) || IS_GEN7(dev_priv)) + dev_priv->uncore.fifo_count = + fifo_free_entries(dev_priv); + spin_unlock_irq(&dev_priv->uncore.lock); + } iosf_mbi_punit_release(); } @@ -558,13 +559,18 @@ void intel_uncore_suspend(struct drm_i915_private *dev_priv) iosf_mbi_punit_acquire(); iosf_mbi_unregister_pmic_bus_access_notifier_unlocked( &dev_priv->uncore.pmic_bus_access_nb); - intel_uncore_forcewake_reset(dev_priv, false); + dev_priv->uncore.fw_domains_saved = + intel_uncore_forcewake_reset(dev_priv); iosf_mbi_punit_release(); } void intel_uncore_resume_early(struct drm_i915_private *dev_priv) { - __intel_uncore_early_sanitize(dev_priv, true); + unsigned int restore_forcewake; + + restore_forcewake = fetch_and_zero(&dev_priv->uncore.fw_domains_saved); + __intel_uncore_early_sanitize(dev_priv, restore_forcewake); + iosf_mbi_register_pmic_bus_access_notifier( &dev_priv->uncore.pmic_bus_access_nb); i915_check_and_clear_faults(dev_priv); @@ -1545,7 +1551,7 @@ void intel_uncore_init(struct drm_i915_private *dev_priv) intel_uncore_edram_detect(dev_priv); intel_uncore_fw_domains_init(dev_priv); - __intel_uncore_early_sanitize(dev_priv, false); + __intel_uncore_early_sanitize(dev_priv, 0); dev_priv->uncore.unclaimed_mmio_check = 1; dev_priv->uncore.pmic_bus_access_nb.notifier_call = @@ -1632,7 +1638,7 @@ void intel_uncore_fini(struct drm_i915_private *dev_priv) iosf_mbi_punit_acquire(); iosf_mbi_unregister_pmic_bus_access_notifier_unlocked( &dev_priv->uncore.pmic_bus_access_nb); - intel_uncore_forcewake_reset(dev_priv, false); + intel_uncore_forcewake_reset(dev_priv); iosf_mbi_punit_release(); } diff --git a/drivers/gpu/drm/i915/intel_uncore.h b/drivers/gpu/drm/i915/intel_uncore.h index 2fbe93178fb2..e5e157d288de 100644 --- a/drivers/gpu/drm/i915/intel_uncore.h +++ b/drivers/gpu/drm/i915/intel_uncore.h @@ -104,6 +104,7 @@ struct intel_uncore { enum forcewake_domains fw_domains; enum forcewake_domains fw_domains_active; + enum forcewake_domains fw_domains_saved; /* user domains saved for S3 */ u32 fw_set; u32 fw_clear; diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_object.c b/drivers/gpu/drm/i915/selftests/i915_gem_object.c index c69cbd5aed52..ba4f322d56b8 100644 --- a/drivers/gpu/drm/i915/selftests/i915_gem_object.c +++ b/drivers/gpu/drm/i915/selftests/i915_gem_object.c @@ -499,6 +499,19 @@ static bool assert_mmap_offset(struct drm_i915_private *i915, return err == expected; } +static void disable_retire_worker(struct drm_i915_private *i915) +{ + mutex_lock(&i915->drm.struct_mutex); + if (!i915->gt.active_requests++) { + intel_runtime_pm_get(i915); + i915_gem_unpark(i915); + intel_runtime_pm_put(i915); + } + mutex_unlock(&i915->drm.struct_mutex); + cancel_delayed_work_sync(&i915->gt.retire_work); + cancel_delayed_work_sync(&i915->gt.idle_work); +} + static int igt_mmap_offset_exhaustion(void *arg) { struct drm_i915_private *i915 = arg; @@ -509,12 +522,7 @@ static int igt_mmap_offset_exhaustion(void *arg) int loop, err; /* Disable background reaper */ - mutex_lock(&i915->drm.struct_mutex); - if (!i915->gt.active_requests++) - i915_gem_unpark(i915); - mutex_unlock(&i915->drm.struct_mutex); - cancel_delayed_work_sync(&i915->gt.retire_work); - cancel_delayed_work_sync(&i915->gt.idle_work); + disable_retire_worker(i915); GEM_BUG_ON(!i915->gt.awake); /* Trim the device mmap space to only a page */ diff --git a/drivers/gpu/drm/i915/selftests/intel_uncore.c b/drivers/gpu/drm/i915/selftests/intel_uncore.c index 47bc5b2ddb56..81d9d31042a9 100644 --- a/drivers/gpu/drm/i915/selftests/intel_uncore.c +++ b/drivers/gpu/drm/i915/selftests/intel_uncore.c @@ -160,7 +160,7 @@ static int intel_uncore_check_forcewake_domains(struct drm_i915_private *dev_pri i915_reg_t reg = { offset }; iosf_mbi_punit_acquire(); - intel_uncore_forcewake_reset(dev_priv, false); + intel_uncore_forcewake_reset(dev_priv); iosf_mbi_punit_release(); check_for_unclaimed_mmio(dev_priv); diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index bd84f71d27d8..ab1d9308c311 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -11,6 +11,7 @@ * */ +#include <linux/kernel.h> #include <linux/types.h> #include <linux/cpumask.h> #include <linux/qcom_scm.h> @@ -20,6 +21,7 @@ #include <linux/pm_opp.h> #include <linux/nvmem-consumer.h> #include <linux/iopoll.h> +#include <linux/slab.h> #include "msm_gem.h" #include "msm_mmu.h" #include "a5xx_gpu.h" @@ -92,12 +94,13 @@ static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname) ret = qcom_mdt_load(dev, fw, fwname, GPU_PAS_ID, mem_region, mem_phys, mem_size, NULL); } else { - char newname[strlen("qcom/") + strlen(fwname) + 1]; + char *newname; - sprintf(newname, "qcom/%s", fwname); + newname = kasprintf(GFP_KERNEL, "qcom/%s", fwname); ret = qcom_mdt_load(dev, fw, newname, GPU_PAS_ID, mem_region, mem_phys, mem_size, NULL); + kfree(newname); } if (ret) goto out; diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index 38ac50b73829..65c0ae7d8ad1 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -18,7 +18,9 @@ */ #include <linux/ascii85.h> +#include <linux/kernel.h> #include <linux/pm_opp.h> +#include <linux/slab.h> #include "adreno_gpu.h" #include "msm_gem.h" #include "msm_mmu.h" @@ -71,10 +73,12 @@ adreno_request_fw(struct adreno_gpu *adreno_gpu, const char *fwname) { struct drm_device *drm = adreno_gpu->base.dev; const struct firmware *fw = NULL; - char newname[strlen("qcom/") + strlen(fwname) + 1]; + char *newname; int ret; - sprintf(newname, "qcom/%s", fwname); + newname = kasprintf(GFP_KERNEL, "qcom/%s", fwname); + if (!newname) + return ERR_PTR(-ENOMEM); /* * Try first to load from qcom/$fwfile using a direct load (to avoid @@ -88,11 +92,12 @@ adreno_request_fw(struct adreno_gpu *adreno_gpu, const char *fwname) dev_info(drm->dev, "loaded %s from new location\n", newname); adreno_gpu->fwloc = FW_LOCATION_NEW; - return fw; + goto out; } else if (adreno_gpu->fwloc != FW_LOCATION_UNKNOWN) { dev_err(drm->dev, "failed to load %s: %d\n", newname, ret); - return ERR_PTR(ret); + fw = ERR_PTR(ret); + goto out; } } @@ -107,11 +112,12 @@ adreno_request_fw(struct adreno_gpu *adreno_gpu, const char *fwname) dev_info(drm->dev, "loaded %s from legacy location\n", newname); adreno_gpu->fwloc = FW_LOCATION_LEGACY; - return fw; + goto out; } else if (adreno_gpu->fwloc != FW_LOCATION_UNKNOWN) { dev_err(drm->dev, "failed to load %s: %d\n", fwname, ret); - return ERR_PTR(ret); + fw = ERR_PTR(ret); + goto out; } } @@ -127,16 +133,20 @@ adreno_request_fw(struct adreno_gpu *adreno_gpu, const char *fwname) dev_info(drm->dev, "loaded %s with helper\n", newname); adreno_gpu->fwloc = FW_LOCATION_HELPER; - return fw; + goto out; } else if (adreno_gpu->fwloc != FW_LOCATION_UNKNOWN) { dev_err(drm->dev, "failed to load %s: %d\n", newname, ret); - return ERR_PTR(ret); + fw = ERR_PTR(ret); + goto out; } } dev_err(drm->dev, "failed to load %s\n", fwname); - return ERR_PTR(-ENOENT); + fw = ERR_PTR(-ENOENT); +out: + kfree(newname); + return fw; } static int adreno_load_fw(struct adreno_gpu *adreno_gpu) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index 0bd3eda93e22..1b4de3486ef9 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -421,7 +421,7 @@ int dpu_encoder_helper_unregister_irq(struct dpu_encoder_phys *phys_enc, ret = dpu_core_irq_disable(phys_enc->dpu_kms, &irq->irq_idx, 1); if (ret) { - DRM_ERROR("diable failed id=%u, intr=%d, hw=%d, irq=%d ret=%d", + DRM_ERROR("disable failed id=%u, intr=%d, hw=%d, irq=%d ret=%d", DRMID(phys_enc->parent), intr_idx, irq->hw_idx, irq->irq_idx, ret); } @@ -2444,6 +2444,8 @@ int dpu_encoder_wait_for_event(struct drm_encoder *drm_enc, for (i = 0; i < dpu_enc->num_phys_encs; i++) { struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i]; + if (!phys) + continue; switch (event) { case MSM_ENC_COMMIT_DONE: @@ -2461,7 +2463,7 @@ int dpu_encoder_wait_for_event(struct drm_encoder *drm_enc, return -EINVAL; }; - if (phys && fn_wait) { + if (fn_wait) { DPU_ATRACE_BEGIN("wait_for_completion_event"); ret = fn_wait(phys); DPU_ATRACE_END("wait_for_completion_event"); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.c index a68f1249388c..a75eebca2f37 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.c @@ -121,7 +121,7 @@ void dpu_power_resource_deinit(struct platform_device *pdev, mutex_lock(&phandle->phandle_lock); list_for_each_entry_safe(curr_client, next_client, &phandle->power_client_clist, list) { - pr_err("cliend:%s-%d still registered with refcount:%d\n", + pr_err("client:%s-%d still registered with refcount:%d\n", curr_client->name, curr_client->id, curr_client->refcount); curr_client->active = false; diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h index 0cba86ed3f54..b611484866d6 100644 --- a/drivers/gpu/drm/msm/msm_drv.h +++ b/drivers/gpu/drm/msm/msm_drv.h @@ -263,7 +263,7 @@ void msm_gem_shrinker_cleanup(struct drm_device *dev); int msm_gem_mmap_obj(struct drm_gem_object *obj, struct vm_area_struct *vma); int msm_gem_mmap(struct file *filp, struct vm_area_struct *vma); -int msm_gem_fault(struct vm_fault *vmf); +vm_fault_t msm_gem_fault(struct vm_fault *vmf); uint64_t msm_gem_mmap_offset(struct drm_gem_object *obj); int msm_gem_get_iova(struct drm_gem_object *obj, struct msm_gem_address_space *aspace, uint64_t *iova); diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index f583bb4222f9..f59ca27a4a35 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -219,7 +219,7 @@ int msm_gem_mmap(struct file *filp, struct vm_area_struct *vma) return msm_gem_mmap_obj(vma->vm_private_data, vma); } -int msm_gem_fault(struct vm_fault *vmf) +vm_fault_t msm_gem_fault(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct drm_gem_object *obj = vma->vm_private_data; @@ -227,15 +227,18 @@ int msm_gem_fault(struct vm_fault *vmf) struct page **pages; unsigned long pfn; pgoff_t pgoff; - int ret; + int err; + vm_fault_t ret; /* * vm_ops.open/drm_gem_mmap_obj and close get and put * a reference on obj. So, we dont need to hold one here. */ - ret = mutex_lock_interruptible(&msm_obj->lock); - if (ret) + err = mutex_lock_interruptible(&msm_obj->lock); + if (err) { + ret = VM_FAULT_NOPAGE; goto out; + } if (WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED)) { mutex_unlock(&msm_obj->lock); @@ -245,7 +248,7 @@ int msm_gem_fault(struct vm_fault *vmf) /* make sure we have pages attached now */ pages = get_pages(obj); if (IS_ERR(pages)) { - ret = PTR_ERR(pages); + ret = vmf_error(PTR_ERR(pages)); goto out_unlock; } @@ -257,27 +260,11 @@ int msm_gem_fault(struct vm_fault *vmf) VERB("Inserting %p pfn %lx, pa %lx", (void *)vmf->address, pfn, pfn << PAGE_SHIFT); - ret = vm_insert_mixed(vma, vmf->address, __pfn_to_pfn_t(pfn, PFN_DEV)); - + ret = vmf_insert_mixed(vma, vmf->address, __pfn_to_pfn_t(pfn, PFN_DEV)); out_unlock: mutex_unlock(&msm_obj->lock); out: - switch (ret) { - case -EAGAIN: - case 0: - case -ERESTARTSYS: - case -EINTR: - case -EBUSY: - /* - * EBUSY is ok: this just means that another thread - * already did the job. - */ - return VM_FAULT_NOPAGE; - case -ENOMEM: - return VM_FAULT_OOM; - default: - return VM_FAULT_SIGBUS; - } + return ret; } /** get mmap offset */ |
