diff options
Diffstat (limited to 'drivers/gpu')
79 files changed, 728 insertions, 568 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 9776e0b488cf..011e4fbe27f1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -4483,7 +4483,11 @@ static int amdgpu_device_recover_vram(struct amdgpu_device *adev) dev_info(adev->dev, "recover vram bo from shadow start\n"); mutex_lock(&adev->shadow_list_lock); list_for_each_entry(vmbo, &adev->shadow_list, shadow_list) { - shadow = &vmbo->bo; + /* If vm is compute context or adev is APU, shadow will be NULL */ + if (!vmbo->shadow) + continue; + shadow = vmbo->shadow; + /* No need to recover an evicted BO */ if (shadow->tbo.resource->mem_type != TTM_PL_TT || shadow->tbo.resource->start == AMDGPU_BO_INVALID_OFFSET || diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c index 0c546245793b..82e27bd4f038 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c @@ -21,6 +21,8 @@ * */ +#include <linux/firmware.h> + #include "amdgpu_mes.h" #include "amdgpu.h" #include "soc15_common.h" @@ -1423,3 +1425,60 @@ error_pasid: kfree(vm); return 0; } + +int amdgpu_mes_init_microcode(struct amdgpu_device *adev, int pipe) +{ + const struct mes_firmware_header_v1_0 *mes_hdr; + struct amdgpu_firmware_info *info; + char ucode_prefix[30]; + char fw_name[40]; + int r; + + amdgpu_ucode_ip_version_decode(adev, GC_HWIP, ucode_prefix, sizeof(ucode_prefix)); + snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mes%s.bin", + ucode_prefix, + pipe == AMDGPU_MES_SCHED_PIPE ? "" : "1"); + r = amdgpu_ucode_request(adev, &adev->mes.fw[pipe], fw_name); + if (r) + goto out; + + mes_hdr = (const struct mes_firmware_header_v1_0 *) + adev->mes.fw[pipe]->data; + adev->mes.uc_start_addr[pipe] = + le32_to_cpu(mes_hdr->mes_uc_start_addr_lo) | + ((uint64_t)(le32_to_cpu(mes_hdr->mes_uc_start_addr_hi)) << 32); + adev->mes.data_start_addr[pipe] = + le32_to_cpu(mes_hdr->mes_data_start_addr_lo) | + ((uint64_t)(le32_to_cpu(mes_hdr->mes_data_start_addr_hi)) << 32); + + if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { + int ucode, ucode_data; + + if (pipe == AMDGPU_MES_SCHED_PIPE) { + ucode = AMDGPU_UCODE_ID_CP_MES; + ucode_data = AMDGPU_UCODE_ID_CP_MES_DATA; + } else { + ucode = AMDGPU_UCODE_ID_CP_MES1; + ucode_data = AMDGPU_UCODE_ID_CP_MES1_DATA; + } + + info = &adev->firmware.ucode[ucode]; + info->ucode_id = ucode; + info->fw = adev->mes.fw[pipe]; + adev->firmware.fw_size += + ALIGN(le32_to_cpu(mes_hdr->mes_ucode_size_bytes), + PAGE_SIZE); + + info = &adev->firmware.ucode[ucode_data]; + info->ucode_id = ucode_data; + info->fw = adev->mes.fw[pipe]; + adev->firmware.fw_size += + ALIGN(le32_to_cpu(mes_hdr->mes_ucode_data_size_bytes), + PAGE_SIZE); + } + + return 0; +out: + amdgpu_ucode_release(&adev->mes.fw[pipe]); + return r; +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h index ad980f4b66e1..547ec35691fa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h @@ -91,14 +91,12 @@ struct amdgpu_mes { struct amdgpu_bo *ucode_fw_obj[AMDGPU_MAX_MES_PIPES]; uint64_t ucode_fw_gpu_addr[AMDGPU_MAX_MES_PIPES]; uint32_t *ucode_fw_ptr[AMDGPU_MAX_MES_PIPES]; - uint32_t ucode_fw_version[AMDGPU_MAX_MES_PIPES]; uint64_t uc_start_addr[AMDGPU_MAX_MES_PIPES]; /* mes ucode data */ struct amdgpu_bo *data_fw_obj[AMDGPU_MAX_MES_PIPES]; uint64_t data_fw_gpu_addr[AMDGPU_MAX_MES_PIPES]; uint32_t *data_fw_ptr[AMDGPU_MAX_MES_PIPES]; - uint32_t data_fw_version[AMDGPU_MAX_MES_PIPES]; uint64_t data_start_addr[AMDGPU_MAX_MES_PIPES]; /* eop gpu obj */ @@ -308,6 +306,7 @@ struct amdgpu_mes_funcs { int amdgpu_mes_ctx_get_offs(struct amdgpu_ring *ring, unsigned int id_offs); +int amdgpu_mes_init_microcode(struct amdgpu_device *adev, int pipe); int amdgpu_mes_init(struct amdgpu_device *adev); void amdgpu_mes_fini(struct amdgpu_device *adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c index e9b45089a28a..863b2a34b2d6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sched.c @@ -38,6 +38,7 @@ static int amdgpu_sched_process_priority_override(struct amdgpu_device *adev, { struct fd f = fdget(fd); struct amdgpu_fpriv *fpriv; + struct amdgpu_ctx_mgr *mgr; struct amdgpu_ctx *ctx; uint32_t id; int r; @@ -51,8 +52,11 @@ static int amdgpu_sched_process_priority_override(struct amdgpu_device *adev, return r; } - idr_for_each_entry(&fpriv->ctx_mgr.ctx_handles, ctx, id) + mgr = &fpriv->ctx_mgr; + mutex_lock(&mgr->lock); + idr_for_each_entry(&mgr->ctx_handles, ctx, id) amdgpu_ctx_priority_override(ctx, priority); + mutex_unlock(&mgr->lock); fdput(f); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c index 5cb62e6249c2..6e7058a2d1c8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c @@ -1091,3 +1091,39 @@ void amdgpu_ucode_ip_version_decode(struct amdgpu_device *adev, int block_type, snprintf(ucode_prefix, len, "%s_%d_%d_%d", ip_name, maj, min, rev); } + +/* + * amdgpu_ucode_request - Fetch and validate amdgpu microcode + * + * @adev: amdgpu device + * @fw: pointer to load firmware to + * @fw_name: firmware to load + * + * This is a helper that will use request_firmware and amdgpu_ucode_validate + * to load and run basic validation on firmware. If the load fails, remap + * the error code to -ENODEV, so that early_init functions will fail to load. + */ +int amdgpu_ucode_request(struct amdgpu_device *adev, const struct firmware **fw, + const char *fw_name) +{ + int err = request_firmware(fw, fw_name, adev->dev); + + if (err) + return -ENODEV; + err = amdgpu_ucode_validate(*fw); + if (err) + dev_dbg(adev->dev, "\"%s\" failed to validate\n", fw_name); + + return err; +} + +/* + * amdgpu_ucode_release - Release firmware microcode + * + * @fw: pointer to firmware to release + */ +void amdgpu_ucode_release(const struct firmware **fw) +{ + release_firmware(*fw); + *fw = NULL; +} diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h index 1c36235b4539..4c20eb410960 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h @@ -543,6 +543,9 @@ void amdgpu_ucode_print_sdma_hdr(const struct common_firmware_header *hdr); void amdgpu_ucode_print_psp_hdr(const struct common_firmware_header *hdr); void amdgpu_ucode_print_gpu_info_hdr(const struct common_firmware_header *hdr); int amdgpu_ucode_validate(const struct firmware *fw); +int amdgpu_ucode_request(struct amdgpu_device *adev, const struct firmware **fw, + const char *fw_name); +void amdgpu_ucode_release(const struct firmware **fw); bool amdgpu_ucode_hdr_version(union amdgpu_firmware_header *hdr, uint16_t hdr_major, uint16_t hdr_minor); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 0320be4a5fc6..1f3fdf6cb903 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -3797,7 +3797,8 @@ static int gfx_v9_0_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; - amdgpu_irq_put(adev, &adev->gfx.cp_ecc_error_irq, 0); + if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__GFX)) + amdgpu_irq_put(adev, &adev->gfx.cp_ecc_error_irq, 0); amdgpu_irq_put(adev, &adev->gfx.priv_reg_irq, 0); amdgpu_irq_put(adev, &adev->gfx.priv_inst_irq, 0); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index f513e2c2e964..d96ee48e1706 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -1142,7 +1142,6 @@ static int gmc_v10_0_hw_fini(void *handle) return 0; } - amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0); amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c index 96e0bb5bee78..2d11e8e7e123 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c @@ -931,7 +931,6 @@ static int gmc_v11_0_hw_fini(void *handle) return 0; } - amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0); amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0); gmc_v11_0_gart_disable(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 67ca16a8027c..0d9e9d9dd4a1 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1898,7 +1898,6 @@ static int gmc_v9_0_hw_fini(void *handle) if (adev->mmhub.funcs->update_power_gating) adev->mmhub.funcs->update_power_gating(adev, false); - amdgpu_irq_put(adev, &adev->gmc.ecc_irq, 0); amdgpu_irq_put(adev, &adev->gmc.vm_fault, 0); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c index a1b751d9ac06..323d68b2124f 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c @@ -54,6 +54,7 @@ static int jpeg_v3_0_early_init(void *handle) switch (adev->ip_versions[UVD_HWIP][0]) { case IP_VERSION(3, 1, 1): + case IP_VERSION(3, 1, 2): break; default: harvest = RREG32_SOC15(JPEG, 0, mmCC_UVD_HARVESTING); diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c b/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c index 067d10073a56..09105029445a 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v10_1.c @@ -375,93 +375,6 @@ static const struct amdgpu_mes_funcs mes_v10_1_funcs = { .resume_gang = mes_v10_1_resume_gang, }; -static int mes_v10_1_init_microcode(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) -{ - const char *chip_name; - char fw_name[30]; - int err; - const struct mes_firmware_header_v1_0 *mes_hdr; - struct amdgpu_firmware_info *info; - - switch (adev->ip_versions[GC_HWIP][0]) { - case IP_VERSION(10, 1, 10): - chip_name = "navi10"; - break; - case IP_VERSION(10, 3, 0): - chip_name = "sienna_cichlid"; - break; - default: - BUG(); - } - - if (pipe == AMDGPU_MES_SCHED_PIPE) - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mes.bin", - chip_name); - else - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mes1.bin", - chip_name); - - err = request_firmware(&adev->mes.fw[pipe], fw_name, adev->dev); - if (err) - return err; - - err = amdgpu_ucode_validate(adev->mes.fw[pipe]); - if (err) { - release_firmware(adev->mes.fw[pipe]); - adev->mes.fw[pipe] = NULL; - return err; - } - - mes_hdr = (const struct mes_firmware_header_v1_0 *) - adev->mes.fw[pipe]->data; - adev->mes.ucode_fw_version[pipe] = - le32_to_cpu(mes_hdr->mes_ucode_version); - adev->mes.ucode_fw_version[pipe] = - le32_to_cpu(mes_hdr->mes_ucode_data_version); - adev->mes.uc_start_addr[pipe] = - le32_to_cpu(mes_hdr->mes_uc_start_addr_lo) | - ((uint64_t)(le32_to_cpu(mes_hdr->mes_uc_start_addr_hi)) << 32); - adev->mes.data_start_addr[pipe] = - le32_to_cpu(mes_hdr->mes_data_start_addr_lo) | - ((uint64_t)(le32_to_cpu(mes_hdr->mes_data_start_addr_hi)) << 32); - - if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { - int ucode, ucode_data; - - if (pipe == AMDGPU_MES_SCHED_PIPE) { - ucode = AMDGPU_UCODE_ID_CP_MES; - ucode_data = AMDGPU_UCODE_ID_CP_MES_DATA; - } else { - ucode = AMDGPU_UCODE_ID_CP_MES1; - ucode_data = AMDGPU_UCODE_ID_CP_MES1_DATA; - } - - info = &adev->firmware.ucode[ucode]; - info->ucode_id = ucode; - info->fw = adev->mes.fw[pipe]; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(mes_hdr->mes_ucode_size_bytes), - PAGE_SIZE); - - info = &adev->firmware.ucode[ucode_data]; - info->ucode_id = ucode_data; - info->fw = adev->mes.fw[pipe]; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(mes_hdr->mes_ucode_data_size_bytes), - PAGE_SIZE); - } - - return 0; -} - -static void mes_v10_1_free_microcode(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) -{ - release_firmware(adev->mes.fw[pipe]); - adev->mes.fw[pipe] = NULL; -} - static int mes_v10_1_allocate_ucode_buffer(struct amdgpu_device *adev, enum admgpu_mes_pipe pipe) { @@ -1019,10 +932,6 @@ static int mes_v10_1_sw_init(void *handle) if (!adev->enable_mes_kiq && pipe == AMDGPU_MES_KIQ_PIPE) continue; - r = mes_v10_1_init_microcode(adev, pipe); - if (r) - return r; - r = mes_v10_1_allocate_eop_buf(adev, pipe); if (r) return r; @@ -1059,8 +968,7 @@ static int mes_v10_1_sw_fini(void *handle) amdgpu_bo_free_kernel(&adev->mes.eop_gpu_obj[pipe], &adev->mes.eop_gpu_addr[pipe], NULL); - - mes_v10_1_free_microcode(adev, pipe); + amdgpu_ucode_release(&adev->mes.fw[pipe]); } amdgpu_bo_free_kernel(&adev->gfx.kiq.ring.mqd_obj, @@ -1229,6 +1137,22 @@ static int mes_v10_1_resume(void *handle) return amdgpu_mes_resume(adev); } +static int mes_v10_0_early_init(void *handle) +{ + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + int pipe, r; + + for (pipe = 0; pipe < AMDGPU_MAX_MES_PIPES; pipe++) { + if (!adev->enable_mes_kiq && pipe == AMDGPU_MES_KIQ_PIPE) + continue; + r = amdgpu_mes_init_microcode(adev, pipe); + if (r) + return r; + } + + return 0; +} + static int mes_v10_0_late_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; @@ -1241,6 +1165,7 @@ static int mes_v10_0_late_init(void *handle) static const struct amd_ip_funcs mes_v10_1_ip_funcs = { .name = "mes_v10_1", + .early_init = mes_v10_0_early_init, .late_init = mes_v10_0_late_init, .sw_init = mes_v10_1_sw_init, .sw_fini = mes_v10_1_sw_fini, diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c index 6f0e389be5f6..e3168149ca8f 100644 --- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c @@ -453,84 +453,6 @@ static const struct amdgpu_mes_funcs mes_v11_0_funcs = { .misc_op = mes_v11_0_misc_op, }; -static int mes_v11_0_init_microcode(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) -{ - char fw_name[30]; - char ucode_prefix[30]; - int err; - const struct mes_firmware_header_v1_0 *mes_hdr; - struct amdgpu_firmware_info *info; - - amdgpu_ucode_ip_version_decode(adev, GC_HWIP, ucode_prefix, sizeof(ucode_prefix)); - - if (pipe == AMDGPU_MES_SCHED_PIPE) - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mes.bin", - ucode_prefix); - else - snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mes1.bin", - ucode_prefix); - - err = request_firmware(&adev->mes.fw[pipe], fw_name, adev->dev); - if (err) - return err; - - err = amdgpu_ucode_validate(adev->mes.fw[pipe]); - if (err) { - release_firmware(adev->mes.fw[pipe]); - adev->mes.fw[pipe] = NULL; - return err; - } - - mes_hdr = (const struct mes_firmware_header_v1_0 *) - adev->mes.fw[pipe]->data; - adev->mes.ucode_fw_version[pipe] = - le32_to_cpu(mes_hdr->mes_ucode_version); - adev->mes.ucode_fw_version[pipe] = - le32_to_cpu(mes_hdr->mes_ucode_data_version); - adev->mes.uc_start_addr[pipe] = - le32_to_cpu(mes_hdr->mes_uc_start_addr_lo) | - ((uint64_t)(le32_to_cpu(mes_hdr->mes_uc_start_addr_hi)) << 32); - adev->mes.data_start_addr[pipe] = - le32_to_cpu(mes_hdr->mes_data_start_addr_lo) | - ((uint64_t)(le32_to_cpu(mes_hdr->mes_data_start_addr_hi)) << 32); - - if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) { - int ucode, ucode_data; - - if (pipe == AMDGPU_MES_SCHED_PIPE) { - ucode = AMDGPU_UCODE_ID_CP_MES; - ucode_data = AMDGPU_UCODE_ID_CP_MES_DATA; - } else { - ucode = AMDGPU_UCODE_ID_CP_MES1; - ucode_data = AMDGPU_UCODE_ID_CP_MES1_DATA; - } - - info = &adev->firmware.ucode[ucode]; - info->ucode_id = ucode; - info->fw = adev->mes.fw[pipe]; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(mes_hdr->mes_ucode_size_bytes), - PAGE_SIZE); - - info = &adev->firmware.ucode[ucode_data]; - info->ucode_id = ucode_data; - info->fw = adev->mes.fw[pipe]; - adev->firmware.fw_size += - ALIGN(le32_to_cpu(mes_hdr->mes_ucode_data_size_bytes), - PAGE_SIZE); - } - - return 0; -} - -static void mes_v11_0_free_microcode(struct amdgpu_device *adev, - enum admgpu_mes_pipe pipe) -{ - release_firmware(adev->mes.fw[pipe]); - adev->mes.fw[pipe] = NULL; -} - static int mes_v11_0_allocate_ucode_buffer(struct amdgpu_device *adev, enum admgpu_mes_pipe pipe) { @@ -1098,10 +1020,6 @@ static int mes_v11_0_sw_init(void *handle) if (!adev->enable_mes_kiq && pipe == AMDGPU_MES_KIQ_PIPE) continue; - r = mes_v11_0_init_microcode(adev, pipe); - if (r) - return r; - r = mes_v11_0_allocate_eop_buf(adev, pipe); if (r) return r; @@ -1138,8 +1056,7 @@ static int mes_v11_0_sw_fini(void *handle) amdgpu_bo_free_kernel(&adev->mes.eop_gpu_obj[pipe], &adev->mes.eop_gpu_addr[pipe], NULL); - - mes_v11_0_free_microcode(adev, pipe); + amdgpu_ucode_release(&adev->mes.fw[pipe]); } amdgpu_bo_free_kernel(&adev->gfx.kiq.ring.mqd_obj, @@ -1334,6 +1251,22 @@ static int mes_v11_0_resume(void *handle) return amdgpu_mes_resume(adev); } +static int mes_v11_0_early_init(void *handle) +{ + struct amdgpu_device *adev = (struct amdgpu_device *)handle; + int pipe, r; + + for (pipe = 0; pipe < AMDGPU_MAX_MES_PIPES; pipe++) { + if (!adev->enable_mes_kiq && pipe == AMDGPU_MES_KIQ_PIPE) + continue; + r = amdgpu_mes_init_microcode(adev, pipe); + if (r) + return r; + } + + return 0; +} + static int mes_v11_0_late_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; @@ -1348,6 +1281,7 @@ static int mes_v11_0_late_init(void *handle) static const struct amd_ip_funcs mes_v11_0_ip_funcs = { .name = "mes_v11_0", + .early_init = mes_v11_0_early_init, .late_init = mes_v11_0_late_init, .sw_init = mes_v11_0_sw_init, .sw_fini = mes_v11_0_sw_fini, diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index 4d780e4430e7..77d5a6f30409 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -1941,9 +1941,11 @@ static int sdma_v4_0_hw_fini(void *handle) return 0; } - for (i = 0; i < adev->sdma.num_instances; i++) { - amdgpu_irq_put(adev, &adev->sdma.ecc_irq, - AMDGPU_SDMA_IRQ_INSTANCE0 + i); + if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__SDMA)) { + for (i = 0; i < adev->sdma.num_instances; i++) { + amdgpu_irq_put(adev, &adev->sdma.ecc_irq, + AMDGPU_SDMA_IRQ_INSTANCE0 + i); + } } sdma_v4_0_ctx_switch_enable(adev, false); diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c index 9c52af500525..d150a90daa40 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc21.c +++ b/drivers/gpu/drm/amd/amdgpu/soc21.c @@ -715,7 +715,7 @@ static int soc21_common_early_init(void *handle) AMD_PG_SUPPORT_VCN_DPG | AMD_PG_SUPPORT_GFX_PG | AMD_PG_SUPPORT_JPEG; - adev->external_rev_id = adev->rev_id + 0x1; + adev->external_rev_id = adev->rev_id + 0x80; break; default: diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 99b99f0b42c0..b46732cefe37 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -39,6 +39,7 @@ #include "dc/dc_edid_parser.h" #include "dc/dc_stat.h" #include "amdgpu_dm_trace.h" +#include "dc/inc/dc_link_ddc.h" #include "vid.h" #include "amdgpu.h" @@ -2254,6 +2255,14 @@ static void s3_handle_mst(struct drm_device *dev, bool suspend) if (suspend) { drm_dp_mst_topology_mgr_suspend(mgr); } else { + /* if extended timeout is supported in hardware, + * default to LTTPR timeout (3.2ms) first as a W/A for DP link layer + * CTS 4.2.1.1 regression introduced by CTS specs requirement update. + */ + dc_link_aux_try_to_configure_timeout(aconnector->dc_link->ddc, LINK_AUX_DEFAULT_LTTPR_TIMEOUT_PERIOD); + if (!dp_is_lttpr_present(aconnector->dc_link)) + dc_link_aux_try_to_configure_timeout(aconnector->dc_link->ddc, LINK_AUX_DEFAULT_TIMEOUT_PERIOD); + ret = drm_dp_mst_topology_mgr_resume(mgr, true); if (ret < 0) { dm_helpers_dp_mst_stop_top_mgr(aconnector->dc_link->ctx, @@ -7584,6 +7593,13 @@ static void amdgpu_dm_commit_cursors(struct drm_atomic_state *state) handle_cursor_update(plane, old_plane_state); } +static inline uint32_t get_mem_type(struct drm_framebuffer *fb) +{ + struct amdgpu_bo *abo = gem_to_amdgpu_bo(fb->obj[0]); + + return abo->tbo.resource ? abo->tbo.resource->mem_type : 0; +} + static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, struct dc_state *dc_state, struct drm_device *dev, @@ -7657,6 +7673,8 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, continue; dc_plane = dm_new_plane_state->dc_state; + if (!dc_plane) + continue; bundle->surface_updates[planes_count].surface = dc_plane; if (new_pcrtc_state->color_mgmt_changed) { @@ -7701,11 +7719,13 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, /* * Only allow immediate flips for fast updates that don't - * change FB pitch, DCC state, rotation or mirroing. + * change memory domain, FB pitch, DCC state, rotation or + * mirroring. */ bundle->flip_addrs[planes_count].flip_immediate = crtc->state->async_flip && - acrtc_state->update_type == UPDATE_TYPE_FAST; + acrtc_state->update_type == UPDATE_TYPE_FAST && + get_mem_type(old_plane_state->fb) == get_mem_type(fb); timestamp_ns = ktime_get_ns(); bundle->flip_addrs[planes_count].flip_timestamp_in_us = div_u64(timestamp_ns, 1000); @@ -9199,8 +9219,9 @@ static int dm_update_plane_state(struct dc *dc, return -EINVAL; } + if (dm_old_plane_state->dc_state) + dc_plane_state_release(dm_old_plane_state->dc_state); - dc_plane_state_release(dm_old_plane_state->dc_state); dm_new_plane_state->dc_state = NULL; *lock_and_validation_needed = true; @@ -9737,6 +9758,7 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, ret = compute_mst_dsc_configs_for_state(state, dm_state->context, vars); if (ret) { DRM_DEBUG_DRIVER("compute_mst_dsc_configs_for_state() failed\n"); + ret = -EINVAL; goto fail; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index df74bc88e460..e2f9141d6d93 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -1368,6 +1368,7 @@ int pre_validate_dsc(struct drm_atomic_state *state, ret = pre_compute_mst_dsc_configs_for_state(state, local_dc_state, vars); if (ret != 0) { DRM_INFO_ONCE("pre_compute_mst_dsc_configs_for_state() failed\n"); + ret = -EINVAL; goto clean_exit; } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c index 090b2c02aee1..0827c7df2855 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c @@ -333,8 +333,8 @@ void dcn31_smu_set_zstate_support(struct clk_mgr_internal *clk_mgr, enum dcn_zst (support == DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY)) support = DCN_ZSTATE_SUPPORT_DISALLOW; - - if (support == DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY) + if (support == DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY || + support == DCN_ZSTATE_SUPPORT_ALLOW_Z8_Z10_ONLY) param = 1; else param = 0; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_smu.c index aa264c600408..0765334f0825 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_smu.c @@ -349,8 +349,6 @@ void dcn314_smu_set_zstate_support(struct clk_mgr_internal *clk_mgr, enum dcn_zs if (!clk_mgr->smu_present) return; - // Arg[15:0] = 8/9/0 for Z8/Z9/disallow -> existing bits - // Arg[16] = Disallow Z9 -> new bit switch (support) { case DCN_ZSTATE_SUPPORT_ALLOW: @@ -369,6 +367,16 @@ void dcn314_smu_set_zstate_support(struct clk_mgr_internal *clk_mgr, enum dcn_zs param = (1 << 10); break; + case DCN_ZSTATE_SUPPORT_ALLOW_Z8_Z10_ONLY: + msg_id = VBIOSSMC_MSG_AllowZstatesEntry; + param = (1 << 10) | (1 << 8); + break; + + case DCN_ZSTATE_SUPPORT_ALLOW_Z8_ONLY: + msg_id = VBIOSSMC_MSG_AllowZstatesEntry; + param = (1 << 8); + break; + default: //DCN_ZSTATE_SUPPORT_UNKNOWN msg_id = VBIOSSMC_MSG_AllowZstatesEntry; param = 0; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c index 9eb9fe5b8d2c..1d84a04acb3f 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c @@ -756,6 +756,8 @@ void dcn32_clk_mgr_construct( struct pp_smu_funcs *pp_smu, struct dccg *dccg) { + struct clk_log_info log_info = {0}; + clk_mgr->base.ctx = ctx; clk_mgr->base.funcs = &dcn32_funcs; if (ASICREV_IS_GC_11_0_2(clk_mgr->base.ctx->asic_id.hw_internal_rev)) { @@ -789,6 +791,7 @@ void dcn32_clk_mgr_construct( clk_mgr->base.clks.ref_dtbclk_khz = 268750; } + /* integer part is now VCO frequency in kHz */ clk_mgr->base.dentist_vco_freq_khz = dcn32_get_vco_frequency_from_reg(clk_mgr); @@ -796,6 +799,8 @@ void dcn32_clk_mgr_construct( if (clk_mgr->base.dentist_vco_freq_khz == 0) clk_mgr->base.dentist_vco_freq_khz = 4300000; /* Updated as per HW docs */ + dcn32_dump_clk_registers(&clk_mgr->base.boot_snapshot, &clk_mgr->base, &log_info); + if (ctx->dc->debug.disable_dtb_ref_clk_switch && clk_mgr->base.clks.ref_dtbclk_khz != clk_mgr->base.boot_snapshot.dtbclk) { clk_mgr->base.clks.ref_dtbclk_khz = clk_mgr->base.boot_snapshot.dtbclk; 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 bf7fcd268cb4..6299130663a3 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -3381,7 +3381,7 @@ bool dc_link_setup_psr(struct dc_link *link, case FAMILY_YELLOW_CARP: case AMDGPU_FAMILY_GC_10_3_6: case AMDGPU_FAMILY_GC_11_0_1: - if (dc->debug.disable_z10) + if (dc->debug.disable_z10 || dc->debug.psr_skip_crtc_disable) psr_context->psr_level.bits.SKIP_CRTC_DISABLE = true; break; default: 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 fd8db482e56f..f0d05829288b 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -1707,6 +1707,9 @@ bool dc_remove_plane_from_context( struct dc_stream_status *stream_status = NULL; struct resource_pool *pool = dc->res_pool; + if (!plane_state) + return true; + for (i = 0; i < context->stream_count; i++) if (context->streams[i] == stream) { stream_status = &context->stream_status[i]; diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index 0598465fd1a1..3f277009075f 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -491,6 +491,8 @@ enum dcn_pwr_state { enum dcn_zstate_support_state { DCN_ZSTATE_SUPPORT_UNKNOWN, DCN_ZSTATE_SUPPORT_ALLOW, + DCN_ZSTATE_SUPPORT_ALLOW_Z8_ONLY, + DCN_ZSTATE_SUPPORT_ALLOW_Z8_Z10_ONLY, DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY, DCN_ZSTATE_SUPPORT_DISALLOW, }; @@ -764,7 +766,6 @@ struct dc_debug_options { bool disable_mem_low_power; bool pstate_enabled; bool disable_dmcu; - bool disable_psr; bool force_abm_enable; bool disable_stereo_support; bool vsr_support; @@ -780,6 +781,7 @@ struct dc_debug_options { unsigned int force_odm_combine; //bit vector based on otg inst unsigned int seamless_boot_odm_combine; unsigned int force_odm_combine_4to1; //bit vector based on otg inst + int minimum_z8_residency_time; bool disable_z9_mpc; unsigned int force_fclk_khz; bool enable_tri_buf; @@ -828,6 +830,7 @@ struct dc_debug_options { int crb_alloc_policy_min_disp_count; bool disable_z10; bool enable_z9_disable_interface; + bool psr_skip_crtc_disable; union dpia_debug_options dpia_debug; bool disable_fixed_vs_aux_timeout_wa; bool force_disable_subvp; diff --git a/drivers/gpu/drm/amd/display/dc/dc_link.h b/drivers/gpu/drm/amd/display/dc/dc_link.h index caf0c7af2d0b..17f080f8af6c 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_link.h +++ b/drivers/gpu/drm/amd/display/dc/dc_link.h @@ -117,7 +117,7 @@ struct psr_settings { * Add a struct dc_panel_config under dc_link */ struct dc_panel_config { - // extra panel power sequence parameters + /* extra panel power sequence parameters */ struct pps { unsigned int extra_t3_ms; unsigned int extra_t7_ms; @@ -127,13 +127,21 @@ struct dc_panel_config { unsigned int extra_t12_ms; unsigned int extra_post_OUI_ms; } pps; - // ABM + /* PSR */ + struct psr { + bool disable_psr; + bool disallow_psrsu; + bool rc_disable; + bool rc_allow_static_screen; + bool rc_allow_fullscreen_VPB; + } psr; + /* ABM */ struct varib { unsigned int varibright_feature_enable; unsigned int def_varibright_level; unsigned int abm_config_setting; } varib; - // edp DSC + /* edp DSC */ struct dsc { bool disable_dsc_edp; unsigned int force_dsc_edp_policy; diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index 55d63d860ef1..0dcd9fea122d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -726,11 +726,15 @@ void dcn10_hubp_pg_control( } } -static void power_on_plane( +static void power_on_plane_resources( struct dce_hwseq *hws, int plane_id) { DC_LOGGER_INIT(hws->ctx->logger); + + if (hws->funcs.dpp_root_clock_control) + hws->funcs.dpp_root_clock_control(hws, plane_id, true); + if (REG(DC_IP_REQUEST_CNTL)) { REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1); @@ -1237,11 +1241,15 @@ void dcn10_plane_atomic_power_down(struct dc *dc, hws->funcs.hubp_pg_control(hws, hubp->inst, false); dpp->funcs->dpp_reset(dpp); + REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 0); DC_LOG_DEBUG( "Power gated front end %d\n", hubp->inst); } + + if (hws->funcs.dpp_root_clock_control) + hws->funcs.dpp_root_clock_control(hws, dpp->inst, false); } /* disable HW used by plane. @@ -2450,7 +2458,7 @@ static void dcn10_enable_plane( undo_DEGVIDCN10_253_wa(dc); - power_on_plane(dc->hwseq, + power_on_plane_resources(dc->hwseq, pipe_ctx->plane_res.hubp->inst); /* enable DCFCLK current DCHUB */ @@ -3369,7 +3377,9 @@ static bool dcn10_can_pipe_disable_cursor(struct pipe_ctx *pipe_ctx) for (test_pipe = pipe_ctx->top_pipe; test_pipe; test_pipe = test_pipe->top_pipe) { // Skip invisible layer and pipe-split plane on same layer - if (!test_pipe->plane_state->visible || test_pipe->plane_state->layer_index == cur_layer) + if (!test_pipe->plane_state || + !test_pipe->plane_state->visible || + test_pipe->plane_state->layer_index == cur_layer) continue; r2 = test_pipe->plane_res.scl_data.recout; diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index f348bc15a925..2d49e99a152c 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1087,11 +1087,15 @@ void dcn20_blank_pixel_data( } -static void dcn20_power_on_plane( +static void dcn20_power_on_plane_resources( struct dce_hwseq *hws, struct pipe_ctx *pipe_ctx) { DC_LOGGER_INIT(hws->ctx->logger); + + if (hws->funcs.dpp_root_clock_control) + hws->funcs.dpp_root_clock_control(hws, pipe_ctx->plane_res.dpp->inst, true); + if (REG(DC_IP_REQUEST_CNTL)) { REG_SET(DC_IP_REQUEST_CNTL, 0, IP_REQUEST_EN, 1); @@ -1115,7 +1119,7 @@ static void dcn20_enable_plane(struct dc *dc, struct pipe_ctx *pipe_ctx, //if (dc->debug.sanity_checks) { // dcn10_verify_allow_pstate_change_high(dc); //} - dcn20_power_on_plane(dc->hwseq, pipe_ctx); + dcn20_power_on_plane_resources(dc->hwseq, pipe_ctx); /* enable DCFCLK current DCHUB */ pipe_ctx->plane_res.hubp->funcs->hubp_clk_cntl(pipe_ctx->plane_res.hubp, true); diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c index 887081472c0d..ce6c70e25703 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c @@ -671,12 +671,15 @@ static const struct dc_debug_options debug_defaults_diags = { .disable_pplib_wm_range = true, .disable_stutter = true, .disable_48mhz_pwrdwn = true, - .disable_psr = true, .enable_tri_buf = true, .use_max_lb = true }; static const struct dc_panel_config panel_config_defaults = { + .psr = { + .disable_psr = false, + .disallow_psrsu = false, + }, .ilr = { .optimize_edp_link_rate = true, }, diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c index e958f838c804..5a8d1a051314 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c @@ -723,7 +723,6 @@ static const struct dc_debug_options debug_defaults_drv = { .underflow_assert_delay_us = 0xFFFFFFFF, .dwb_fi_phase = -1, // -1 = disable, .dmub_command_table = true, - .disable_psr = false, .use_max_lb = true, .exit_idle_opt_for_cursor_updates = true }; @@ -742,11 +741,17 @@ static const struct dc_debug_options debug_defaults_diags = { .scl_reset_length10 = true, .dwb_fi_phase = -1, // -1 = disable .dmub_command_table = true, - .disable_psr = true, .enable_tri_buf = true, .use_max_lb = true }; +static const struct dc_panel_config panel_config_defaults = { + .psr = { + .disable_psr = false, + .disallow_psrsu = false, + }, +}; + static void dcn30_dpp_destroy(struct dpp **dpp) { kfree(TO_DCN20_DPP(*dpp)); @@ -2214,6 +2219,11 @@ void dcn30_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params } } +static void dcn30_get_panel_config_defaults(struct dc_panel_config *panel_config) +{ + *panel_config = panel_config_defaults; +} + static const struct resource_funcs dcn30_res_pool_funcs = { .destroy = dcn30_destroy_resource_pool, .link_enc_create = dcn30_link_encoder_create, @@ -2233,6 +2243,7 @@ static const struct resource_funcs dcn30_res_pool_funcs = { .release_post_bldn_3dlut = dcn30_release_post_bldn_3dlut, .update_bw_bounding_box = dcn30_update_bw_bounding_box, .patch_unknown_plane_state = dcn20_patch_unknown_plane_state, + .get_panel_config_defaults = dcn30_get_panel_config_defaults, }; #define CTX ctx diff --git a/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c b/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c index b925b6ddde5a..d3945876aced 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c @@ -112,10 +112,16 @@ static const struct dc_debug_options debug_defaults_diags = { .dwb_fi_phase = -1, // -1 = disable .dmub_command_table = true, .enable_tri_buf = true, - .disable_psr = true, .use_max_lb = true }; +static const struct dc_panel_config panel_config_defaults = { + .psr = { + .disable_psr = false, + .disallow_psrsu = false, + }, +}; + enum dcn302_clk_src_array_id { DCN302_CLK_SRC_PLL0, DCN302_CLK_SRC_PLL1, @@ -1132,6 +1138,11 @@ void dcn302_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param DC_FP_END(); } +static void dcn302_get_panel_config_defaults(struct dc_panel_config *panel_config) +{ + *panel_config = panel_config_defaults; +} + static struct resource_funcs dcn302_res_pool_funcs = { .destroy = dcn302_destroy_resource_pool, .link_enc_create = dcn302_link_encoder_create, @@ -1151,6 +1162,7 @@ static struct resource_funcs dcn302_res_pool_funcs = { .release_post_bldn_3dlut = dcn30_release_post_bldn_3dlut, .update_bw_bounding_box = dcn302_update_bw_bounding_box, .patch_unknown_plane_state = dcn20_patch_unknown_plane_state, + .get_panel_config_defaults = dcn302_get_panel_config_defaults, }; static struct dc_cap_funcs cap_funcs = { diff --git a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c index 527d5c902878..7e7f18bef098 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c @@ -96,7 +96,13 @@ static const struct dc_debug_options debug_defaults_diags = { .dwb_fi_phase = -1, // -1 = disable .dmub_command_table = true, .enable_tri_buf = true, - .disable_psr = true, +}; + +static const struct dc_panel_config panel_config_defaults = { + .psr = { + .disable_psr = false, + .disallow_psrsu = false, + }, }; enum dcn303_clk_src_array_id { @@ -1055,6 +1061,10 @@ static void dcn303_destroy_resource_pool(struct resource_pool **pool) *pool = NULL; } +static void dcn303_get_panel_config_defaults(struct dc_panel_config *panel_config) +{ + *panel_config = panel_config_defaults; +} void dcn303_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params) { @@ -1082,6 +1092,7 @@ static struct resource_funcs dcn303_res_pool_funcs = { .release_post_bldn_3dlut = dcn30_release_post_bldn_3dlut, .update_bw_bounding_box = dcn303_update_bw_bounding_box, .patch_unknown_plane_state = dcn20_patch_unknown_plane_state, + .get_panel_config_defaults = dcn303_get_panel_config_defaults, }; static struct dc_cap_funcs cap_funcs = { diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.c index 7f34418e6308..7d2b982506fd 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dccg.c @@ -66,17 +66,8 @@ void dccg31_update_dpp_dto(struct dccg *dccg, int dpp_inst, int req_dppclk) REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_ENABLE[dpp_inst], 1); } else { - //DTO must be enabled to generate a 0Hz clock output - if (dccg->ctx->dc->debug.root_clock_optimization.bits.dpp) { - REG_UPDATE(DPPCLK_DTO_CTRL, - DPPCLK_DTO_ENABLE[dpp_inst], 1); - REG_SET_2(DPPCLK_DTO_PARAM[dpp_inst], 0, - DPPCLK0_DTO_PHASE, 0, - DPPCLK0_DTO_MODULO, 1); - } else { - REG_UPDATE(DPPCLK_DTO_CTRL, - DPPCLK_DTO_ENABLE[dpp_inst], 0); - } + REG_UPDATE(DPPCLK_DTO_CTRL, + DPPCLK_DTO_ENABLE[dpp_inst], 0); } dccg->pipe_dppclk_khz[dpp_inst] = req_dppclk; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c index d825f11b4fea..d3f76512841b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c @@ -911,6 +911,10 @@ static const struct dc_debug_options debug_defaults_diags = { }; static const struct dc_panel_config panel_config_defaults = { + .psr = { + .disable_psr = false, + .disallow_psrsu = false, + }, .ilr = { .optimize_edp_link_rate = true, }, diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c index 389a8938ee45..85ea3334355c 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_dccg.c @@ -289,8 +289,31 @@ static void dccg314_set_valid_pixel_rate( dccg314_set_dtbclk_dto(dccg, &dto_params); } +static void dccg314_dpp_root_clock_control( + struct dccg *dccg, + unsigned int dpp_inst, + bool clock_on) +{ + struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg); + + if (clock_on) { + /* turn off the DTO and leave phase/modulo at max */ + REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_ENABLE[dpp_inst], 0); + REG_SET_2(DPPCLK_DTO_PARAM[dpp_inst], 0, + DPPCLK0_DTO_PHASE, 0xFF, + DPPCLK0_DTO_MODULO, 0xFF); + } else { + /* turn on the DTO to generate a 0hz clock */ + REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_ENABLE[dpp_inst], 1); + REG_SET_2(DPPCLK_DTO_PARAM[dpp_inst], 0, + DPPCLK0_DTO_PHASE, 0, + DPPCLK0_DTO_MODULO, 1); + } +} + static const struct dccg_funcs dccg314_funcs = { .update_dpp_dto = dccg31_update_dpp_dto, + .dpp_root_clock_control = dccg314_dpp_root_clock_control, .get_dccg_ref_freq = dccg31_get_dccg_ref_freq, .dccg_init = dccg31_init, .set_dpstreamclk = dccg314_set_dpstreamclk, diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c index 8e824dc81ded..414d7358a075 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.c @@ -392,6 +392,16 @@ void dcn314_set_pixels_per_cycle(struct pipe_ctx *pipe_ctx) pix_per_cycle); } +void dcn314_dpp_root_clock_control(struct dce_hwseq *hws, unsigned int dpp_inst, bool clock_on) +{ + if (!hws->ctx->dc->debug.root_clock_optimization.bits.dpp) + return; + + if (hws->ctx->dc->res_pool->dccg->funcs->dpp_root_clock_control) + hws->ctx->dc->res_pool->dccg->funcs->dpp_root_clock_control( + hws->ctx->dc->res_pool->dccg, dpp_inst, clock_on); +} + void dcn314_hubp_pg_control(struct dce_hwseq *hws, unsigned int hubp_inst, bool power_on) { struct dc_context *ctx = hws->ctx; diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h index c419d3dbdfee..c786d5e6a428 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_hwseq.h @@ -43,4 +43,6 @@ void dcn314_set_pixels_per_cycle(struct pipe_ctx *pipe_ctx); void dcn314_hubp_pg_control(struct dce_hwseq *hws, unsigned int hubp_inst, bool power_on); +void dcn314_dpp_root_clock_control(struct dce_hwseq *hws, unsigned int dpp_inst, bool clock_on); + #endif /* __DC_HWSS_DCN314_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c index 343f4d9dd5e3..5267e901a35c 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_init.c @@ -137,6 +137,7 @@ static const struct hwseq_private_funcs dcn314_private_funcs = { .plane_atomic_disable = dcn20_plane_atomic_disable, .plane_atomic_power_down = dcn10_plane_atomic_power_down, .enable_power_gating_plane = dcn314_enable_power_gating_plane, + .dpp_root_clock_control = dcn314_dpp_root_clock_control, .hubp_pg_control = dcn314_hubp_pg_control, .program_all_writeback_pipes_in_tree = dcn30_program_all_writeback_pipes_in_tree, .update_odm = dcn314_update_odm, diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c index ffaa4e5b3fca..b7782433ce6b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c @@ -884,6 +884,8 @@ static const struct dc_plane_cap plane_cap = { static const struct dc_debug_options debug_defaults_drv = { .disable_z10 = false, .enable_z9_disable_interface = true, + .minimum_z8_residency_time = 2000, + .psr_skip_crtc_disable = true, .disable_dmcu = true, .force_abm_enable = false, .timing_trace = false, @@ -940,6 +942,10 @@ static const struct dc_debug_options debug_defaults_diags = { }; static const struct dc_panel_config panel_config_defaults = { + .psr = { + .disable_psr = false, + .disallow_psrsu = false, + }, .ilr = { .optimize_edp_link_rate = true, }, diff --git a/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c b/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c index 58746c437554..31cbc5762eab 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn315/dcn315_resource.c @@ -907,6 +907,10 @@ static const struct dc_debug_options debug_defaults_diags = { }; static const struct dc_panel_config panel_config_defaults = { + .psr = { + .disable_psr = false, + .disallow_psrsu = false, + }, .ilr = { .optimize_edp_link_rate = true, }, diff --git a/drivers/gpu/drm/amd/display/dc/dcn316/dcn316_resource.c b/drivers/gpu/drm/amd/display/dc/dcn316/dcn316_resource.c index 6b40a11ac83a..af3eddc0cf32 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn316/dcn316_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn316/dcn316_resource.c @@ -906,6 +906,10 @@ static const struct dc_debug_options debug_defaults_diags = { }; static const struct dc_panel_config panel_config_defaults = { + .psr = { + .disable_psr = false, + .disallow_psrsu = false, + }, .ilr = { .optimize_edp_link_rate = true, }, diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c index 1a85509c12f2..e9188bce62e0 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_hwseq.c @@ -984,6 +984,7 @@ void dcn32_init_hw(struct dc *dc) if (dc->ctx->dmub_srv) { dc_dmub_srv_query_caps_cmd(dc->ctx->dmub_srv->dmub); dc->caps.dmub_caps.psr = dc->ctx->dmub_srv->dmub->feature_caps.psr; + dc->caps.dmub_caps.mclk_sw = dc->ctx->dmub_srv->dmub->feature_caps.fw_assisted_mclk_switch; } /* Enable support for ODM and windowed MPO if policy flag is set */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c index a942e2812183..814620e6638f 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource.c @@ -1984,7 +1984,7 @@ int dcn32_populate_dml_pipes_from_context( // In general cases we want to keep the dram clock change requirement // (prefer configs that support MCLK switch). Only override to false // for SubVP - if (subvp_in_use) + if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching || subvp_in_use) context->bw_ctx.dml.soc.dram_clock_change_requirement_final = false; else context->bw_ctx.dml.soc.dram_clock_change_requirement_final = true; @@ -2037,6 +2037,14 @@ static struct resource_funcs dcn32_res_pool_funcs = { .remove_phantom_pipes = dcn32_remove_phantom_pipes, }; +static uint32_t read_pipe_fuses(struct dc_context *ctx) +{ + uint32_t value = REG_READ(CC_DC_PIPE_DIS); + /* DCN32 support max 4 pipes */ + value = value & 0xf; + return value; +} + static bool dcn32_resource_construct( uint8_t num_virtual_links, @@ -2079,7 +2087,7 @@ static bool dcn32_resource_construct( pool->base.res_cap = &res_cap_dcn32; /* max number of pipes for ASIC before checking for pipe fuses */ num_pipes = pool->base.res_cap->num_timing_generator; - pipe_fuses = REG_READ(CC_DC_PIPE_DIS); + pipe_fuses = read_pipe_fuses(ctx); for (i = 0; i < pool->base.res_cap->num_timing_generator; i++) if (pipe_fuses & 1 << i) diff --git a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c index d320e21680da..213ff3672bd5 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn321/dcn321_resource.c @@ -1621,6 +1621,14 @@ static struct resource_funcs dcn321_res_pool_funcs = { .remove_phantom_pipes = dcn32_remove_phantom_pipes, }; +static uint32_t read_pipe_fuses(struct dc_context *ctx) +{ + uint32_t value = REG_READ(CC_DC_PIPE_DIS); + /* DCN321 support max 4 pipes */ + value = value & 0xf; + return value; +} + static bool dcn321_resource_construct( uint8_t num_virtual_links, @@ -1663,7 +1671,7 @@ static bool dcn321_resource_construct( pool->base.res_cap = &res_cap_dcn321; /* max number of pipes for ASIC before checking for pipe fuses */ num_pipes = pool->base.res_cap->num_timing_generator; - pipe_fuses = REG_READ(CC_DC_PIPE_DIS); + pipe_fuses = read_pipe_fuses(ctx); for (i = 0; i < pool->base.res_cap->num_timing_generator; i++) if (pipe_fuses & 1 << i) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c index 45db40c41882..186538e3e3c0 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c @@ -963,6 +963,8 @@ static enum dcn_zstate_support_state decide_zstate_support(struct dc *dc, struc * 2. single eDP, on link 0, 1 plane and stutter period > 5ms * Z10 only cases: * 1. single eDP, on link 0, 1 plane and stutter period >= 5ms + * Z8 cases: + * 1. stutter period sufficient * Zstate not allowed cases: * 1. Everything else */ @@ -971,6 +973,9 @@ static enum dcn_zstate_support_state decide_zstate_support(struct dc *dc, struc else if (context->stream_count == 1 && context->streams[0]->signal == SIGNAL_TYPE_EDP) { struct dc_link *link = context->streams[0]->sink->link; struct dc_stream_status *stream_status = &context->stream_status[0]; + int minmum_z8_residency = dc->debug.minimum_z8_residency_time > 0 ? dc->debug.minimum_z8_residency_time : 1000; + bool allow_z8 = context->bw_ctx.dml.vba.StutterPeriod > (double)minmum_z8_residency; + bool is_pwrseq0 = link->link_index == 0; if (dc_extended_blank_supported(dc)) { for (i = 0; i < dc->res_pool->pipe_count; i++) { @@ -983,18 +988,20 @@ static enum dcn_zstate_support_state decide_zstate_support(struct dc *dc, struc } } } - /* zstate only supported on PWRSEQ0 and when there's <2 planes*/ - if (link->link_index != 0 || stream_status->plane_count > 1) + + /* Don't support multi-plane configurations */ + if (stream_status->plane_count > 1) return DCN_ZSTATE_SUPPORT_DISALLOW; - if (context->bw_ctx.dml.vba.StutterPeriod > 5000.0 || optimized_min_dst_y_next_start_us > 5000) + if (is_pwrseq0 && (context->bw_ctx.dml.vba.StutterPeriod > 5000.0 || optimized_min_dst_y_next_start_us > 5000)) return DCN_ZSTATE_SUPPORT_ALLOW; - else if (link->psr_settings.psr_version == DC_PSR_VERSION_1 && !dc->debug.disable_psr) - return DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY; + else if (is_pwrseq0 && link->psr_settings.psr_version == DC_PSR_VERSION_1 && !link->panel_config.psr.disable_psr) + return allow_z8 ? DCN_ZSTATE_SUPPORT_ALLOW_Z8_Z10_ONLY : DCN_ZSTATE_SUPPORT_ALLOW_Z10_ONLY; else - return DCN_ZSTATE_SUPPORT_DISALLOW; - } else + return allow_z8 ? DCN_ZSTATE_SUPPORT_ALLOW_Z8_ONLY : DCN_ZSTATE_SUPPORT_DISALLOW; + } else { return DCN_ZSTATE_SUPPORT_DISALLOW; + } } void dcn20_calculate_dlg_params( diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.c index 990dbd736e2c..fdfb19337ea6 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn30/dcn30_fpu.c @@ -368,7 +368,9 @@ void dcn30_fpu_update_soc_for_wm_a(struct dc *dc, struct dc_state *context) dc_assert_fp_enabled(); if (dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].valid) { - context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.pstate_latency_us; + if (!context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching || + context->bw_ctx.dml.soc.dram_clock_change_latency_us == 0) + context->bw_ctx.dml.soc.dram_clock_change_latency_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.pstate_latency_us; context->bw_ctx.dml.soc.sr_enter_plus_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.sr_enter_plus_exit_time_us; context->bw_ctx.dml.soc.sr_exit_time_us = dc->clk_mgr->bw_params->wm_table.nv_entries[WM_A].dml_input.sr_exit_time_us; } @@ -520,9 +522,21 @@ void dcn30_fpu_calculate_wm_and_dlg( pipe_idx++; } - DC_FP_START(); + // WA: restrict FPO to use first non-strobe mode (NV24 BW issue) + if (context->bw_ctx.bw.dcn.clk.fw_based_mclk_switching && + dc->dml.soc.num_chans <= 4 && + context->bw_ctx.dml.vba.DRAMSpeed <= 1700 && + context->bw_ctx.dml.vba.DRAMSpeed >= 1500) { + + for (i = 0; i < dc->dml.soc.num_states; i++) { + if (dc->dml.soc.clock_limits[i].dram_speed_mts > 1700) { + context->bw_ctx.dml.vba.DRAMSpeed = dc->dml.soc.clock_limits[i].dram_speed_mts; + break; + } + } + } + dcn20_calculate_dlg_params(dc, context, pipes, pipe_cnt, vlevel); - DC_FP_END(); if (!pstate_en) /* Restore full p-state latency */ diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c index 34b6c763a455..4f91e6475423 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn314/dcn314_fpu.c @@ -148,8 +148,8 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_14_soc = { .num_states = 5, .sr_exit_time_us = 16.5, .sr_enter_plus_exit_time_us = 18.5, - .sr_exit_z8_time_us = 442.0, - .sr_enter_plus_exit_z8_time_us = 560.0, + .sr_exit_z8_time_us = 268.0, + .sr_enter_plus_exit_z8_time_us = 393.0, .writeback_latency_us = 12.0, .dram_channel_width_bytes = 4, .round_trip_ping_latency_dcfclk_cycles = 106, diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c index e22b4b3880af..d2b184fdd7e0 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c @@ -1200,9 +1200,7 @@ static void dcn32_full_validate_bw_helper(struct dc *dc, } } else { // Most populate phantom DLG params before programming hardware / timing for phantom pipe - DC_FP_START(); dcn32_helper_populate_phantom_dlg_params(dc, context, pipes, *pipe_cnt); - DC_FP_END(); /* Call validate_apply_pipe_split flags after calling DML getters for * phantom dlg params, or some of the VBA params indicating pipe split @@ -1503,11 +1501,8 @@ bool dcn32_internal_validate_bw(struct dc *dc, dml_log_pipe_params(&context->bw_ctx.dml, pipes, pipe_cnt); - if (!fast_validate) { - DC_FP_START(); + if (!fast_validate) dcn32_full_validate_bw_helper(dc, context, pipes, &vlevel, split, merge, &pipe_cnt); - DC_FP_END(); - } if (fast_validate || (dc->debug.dml_disallow_alternate_prefetch_modes && @@ -2172,9 +2167,7 @@ static int build_synthetic_soc_states(struct clk_bw_params *bw_params, entry.fabricclk_mhz = 0; entry.dram_speed_mts = 0; - DC_FP_START(); insert_entry_into_table_sorted(table, num_entries, &entry); - DC_FP_END(); } // Insert the max DCFCLK @@ -2182,9 +2175,7 @@ static int build_synthetic_soc_states(struct clk_bw_params *bw_params, entry.fabricclk_mhz = 0; entry.dram_speed_mts = 0; - DC_FP_START(); insert_entry_into_table_sorted(table, num_entries, &entry); - DC_FP_END(); // Insert the UCLK DPMS for (i = 0; i < num_uclk_dpms; i++) { @@ -2192,9 +2183,7 @@ static int build_synthetic_soc_states(struct clk_bw_params *bw_params, entry.fabricclk_mhz = 0; entry.dram_speed_mts = bw_params->clk_table.entries[i].memclk_mhz * 16; - DC_FP_START(); insert_entry_into_table_sorted(table, num_entries, &entry); - DC_FP_END(); } // If FCLK is coarse grained, insert individual DPMs. @@ -2204,9 +2193,7 @@ static int build_synthetic_soc_states(struct clk_bw_params *bw_params, entry.fabricclk_mhz = bw_params->clk_table.entries[i].fclk_mhz; entry.dram_speed_mts = 0; - DC_FP_START(); insert_entry_into_table_sorted(table, num_entries, &entry); - DC_FP_END(); } } // If FCLK fine grained, only insert max @@ -2215,9 +2202,7 @@ static int build_synthetic_soc_states(struct clk_bw_params *bw_params, entry.fabricclk_mhz = max_fclk_mhz; entry.dram_speed_mts = 0; - DC_FP_START(); insert_entry_into_table_sorted(table, num_entries, &entry); - DC_FP_END(); } // At this point, the table contains all "points of interest" based on diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c index 820042f6aaca..e02e9d4b04a9 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c @@ -807,7 +807,8 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman v->SwathHeightY[k], v->SwathHeightC[k], TWait, - v->DRAMSpeedPerState[mode_lib->vba.VoltageLevel] <= MEM_STROBE_FREQ_MHZ ? + (v->DRAMSpeedPerState[mode_lib->vba.VoltageLevel] <= MEM_STROBE_FREQ_MHZ || + v->DCFCLKPerState[mode_lib->vba.VoltageLevel] <= MIN_DCFCLK_FREQ_MHZ) ? mode_lib->vba.ip.min_prefetch_in_strobe_us : 0, /* Output */ &v->DSTXAfterScaler[k], @@ -3288,7 +3289,7 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l v->swath_width_chroma_ub_this_state[k], v->SwathHeightYThisState[k], v->SwathHeightCThisState[k], v->TWait, - v->DRAMSpeedPerState[i] <= MEM_STROBE_FREQ_MHZ ? + (v->DRAMSpeedPerState[i] <= MEM_STROBE_FREQ_MHZ || v->DCFCLKState[i][j] <= MIN_DCFCLK_FREQ_MHZ) ? mode_lib->vba.ip.min_prefetch_in_strobe_us : 0, /* Output */ diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.h b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.h index c8b28c83ddf4..e92eee2c664d 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.h +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.h @@ -52,6 +52,7 @@ #define BPP_BLENDED_PIPE 0xffffffff #define MEM_STROBE_FREQ_MHZ 1600 +#define MIN_DCFCLK_FREQ_MHZ 200 #define MEM_STROBE_MAX_DELIVERY_TIME_US 60.0 struct display_mode_lib; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c index b80cef70fa60..383a409a3f54 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c @@ -106,16 +106,16 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_21_soc = { .clock_limits = { { .state = 0, - .dcfclk_mhz = 1564.0, - .fabricclk_mhz = 400.0, - .dispclk_mhz = 2150.0, - .dppclk_mhz = 2150.0, + .dcfclk_mhz = 1434.0, + .fabricclk_mhz = 2250.0, + .dispclk_mhz = 1720.0, + .dppclk_mhz = 1720.0, .phyclk_mhz = 810.0, .phyclk_d18_mhz = 667.0, - .phyclk_d32_mhz = 625.0, + .phyclk_d32_mhz = 313.0, .socclk_mhz = 1200.0, - .dscclk_mhz = 716.667, - .dram_speed_mts = 1600.0, + .dscclk_mhz = 573.333, + .dram_speed_mts = 16000.0, .dtbclk_mhz = 1564.0, }, }, @@ -125,14 +125,14 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_21_soc = { .sr_exit_z8_time_us = 285.0, .sr_enter_plus_exit_z8_time_us = 320, .writeback_latency_us = 12.0, - .round_trip_ping_latency_dcfclk_cycles = 263, + .round_trip_ping_latency_dcfclk_cycles = 207, .urgent_latency_pixel_data_only_us = 4, .urgent_latency_pixel_mixed_with_vm_data_us = 4, .urgent_latency_vm_data_only_us = 4, - .fclk_change_latency_us = 20, - .usr_retraining_latency_us = 2, - .smn_latency_us = 2, - .mall_allocated_for_dcn_mbytes = 64, + .fclk_change_latency_us = 7, + .usr_retraining_latency_us = 0, + .smn_latency_us = 0, + .mall_allocated_for_dcn_mbytes = 32, .urgent_out_of_order_return_per_channel_pixel_only_bytes = 4096, .urgent_out_of_order_return_per_channel_pixel_and_vm_bytes = 4096, .urgent_out_of_order_return_per_channel_vm_only_bytes = 4096, diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h index ce006762f257..ad6acd1b34e1 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h @@ -148,18 +148,21 @@ struct dccg_funcs { struct dccg *dccg, int inst); -void (*set_pixel_rate_div)( - struct dccg *dccg, - uint32_t otg_inst, - enum pixel_rate_div k1, - enum pixel_rate_div k2); - -void (*set_valid_pixel_rate)( - struct dccg *dccg, - int ref_dtbclk_khz, - int otg_inst, - int pixclk_khz); + void (*set_pixel_rate_div)(struct dccg *dccg, + uint32_t otg_inst, + enum pixel_rate_div k1, + enum pixel_rate_div k2); + void (*set_valid_pixel_rate)( + struct dccg *dccg, + int ref_dtbclk_khz, + int otg_inst, + int pixclk_khz); + + void (*dpp_root_clock_control)( + struct dccg *dccg, + unsigned int dpp_inst, + bool clock_on); }; #endif //__DAL_DCCG_H__ diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h index a4d61bb724b6..39bd53b79020 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h @@ -115,6 +115,10 @@ struct hwseq_private_funcs { void (*plane_atomic_disable)(struct dc *dc, struct pipe_ctx *pipe_ctx); void (*enable_power_gating_plane)(struct dce_hwseq *hws, bool enable); + void (*dpp_root_clock_control)( + struct dce_hwseq *hws, + unsigned int dpp_inst, + bool clock_on); void (*dpp_pg_control)(struct dce_hwseq *hws, unsigned int dpp_inst, bool power_on); diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn32.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn32.c index a76da0131add..9c20516be066 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn32.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn32.c @@ -130,12 +130,13 @@ void dmub_dcn32_reset(struct dmub_srv *dmub) REG_WRITE(DMCUB_INBOX1_WPTR, 0); REG_WRITE(DMCUB_OUTBOX1_RPTR, 0); REG_WRITE(DMCUB_OUTBOX1_WPTR, 0); + REG_WRITE(DMCUB_OUTBOX0_RPTR, 0); + REG_WRITE(DMCUB_OUTBOX0_WPTR, 0); REG_WRITE(DMCUB_SCRATCH0, 0); } void dmub_dcn32_reset_release(struct dmub_srv *dmub) { - REG_WRITE(DMCUB_GPINT_DATAIN1, 0); REG_UPDATE(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET, 0); REG_WRITE(DMCUB_SCRATCH15, dmub->psp_version & 0x001100FF); REG_UPDATE_2(DMCUB_CNTL, DMCUB_ENABLE, 1, DMCUB_TRACEPORT_EN, 1); diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c index 1b300c569faf..69b51612c39a 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c @@ -36,6 +36,8 @@ #define amdgpu_dpm_enable_bapm(adev, e) \ ((adev)->powerplay.pp_funcs->enable_bapm((adev)->powerplay.pp_handle, (e))) +#define amdgpu_dpm_is_legacy_dpm(adev) ((adev)->powerplay.pp_handle == (adev)) + int amdgpu_dpm_get_sclk(struct amdgpu_device *adev, bool low) { const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; @@ -1414,15 +1416,24 @@ int amdgpu_dpm_get_smu_prv_buf_details(struct amdgpu_device *adev, int amdgpu_dpm_is_overdrive_supported(struct amdgpu_device *adev) { - struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle; - struct smu_context *smu = adev->powerplay.pp_handle; + if (is_support_sw_smu(adev)) { + struct smu_context *smu = adev->powerplay.pp_handle; - if ((is_support_sw_smu(adev) && smu->od_enabled) || - (is_support_sw_smu(adev) && smu->is_apu) || - (!is_support_sw_smu(adev) && hwmgr->od_enabled)) - return true; + return (smu->od_enabled || smu->is_apu); + } else { + struct pp_hwmgr *hwmgr; - return false; + /* + * dpm on some legacy asics don't carry od_enabled member + * as its pp_handle is casted directly from adev. + */ + if (amdgpu_dpm_is_legacy_dpm(adev)) + return false; + + hwmgr = (struct pp_hwmgr *)adev->powerplay.pp_handle; + + return hwmgr->od_enabled; + } } int amdgpu_dpm_set_pp_table(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/bridge/lontium-lt8912b.c b/drivers/gpu/drm/bridge/lontium-lt8912b.c index 1b74a913f1b8..5e419934d2a3 100644 --- a/drivers/gpu/drm/bridge/lontium-lt8912b.c +++ b/drivers/gpu/drm/bridge/lontium-lt8912b.c @@ -504,7 +504,6 @@ static int lt8912_attach_dsi(struct lt8912 *lt) dsi->format = MIPI_DSI_FMT_RGB888; dsi->mode_flags = MIPI_DSI_MODE_VIDEO | - MIPI_DSI_MODE_VIDEO_BURST | MIPI_DSI_MODE_LPM | MIPI_DSI_MODE_NO_EOT_PACKET; diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c index dd64b93c78e5..8219310025de 100644 --- a/drivers/gpu/drm/i915/display/icl_dsi.c +++ b/drivers/gpu/drm/i915/display/icl_dsi.c @@ -1210,7 +1210,7 @@ static void gen11_dsi_powerup_panel(struct intel_encoder *encoder) /* panel power on related mipi dsi vbt sequences */ intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_POWER_ON); - intel_dsi_msleep(intel_dsi, intel_dsi->panel_on_delay); + msleep(intel_dsi->panel_on_delay); intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DEASSERT_RESET); intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_INIT_OTP); intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DISPLAY_ON); diff --git a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c index 2cbc1292ab38..f102c13cb959 100644 --- a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c +++ b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c @@ -762,17 +762,6 @@ void intel_dsi_vbt_exec_sequence(struct intel_dsi *intel_dsi, gpiod_set_value_cansleep(intel_dsi->gpio_backlight, 0); } -void intel_dsi_msleep(struct intel_dsi *intel_dsi, int msec) -{ - struct intel_connector *connector = intel_dsi->attached_connector; - - /* For v3 VBTs in vid-mode the delays are part of the VBT sequences */ - if (is_vid_mode(intel_dsi) && connector->panel.vbt.dsi.seq_version >= 3) - return; - - msleep(msec); -} - void intel_dsi_log_params(struct intel_dsi *intel_dsi) { struct drm_i915_private *i915 = to_i915(intel_dsi->base.base.dev); diff --git a/drivers/gpu/drm/i915/display/intel_dsi_vbt.h b/drivers/gpu/drm/i915/display/intel_dsi_vbt.h index dc642c1fe7ef..468d873fab1a 100644 --- a/drivers/gpu/drm/i915/display/intel_dsi_vbt.h +++ b/drivers/gpu/drm/i915/display/intel_dsi_vbt.h @@ -16,7 +16,6 @@ void intel_dsi_vbt_gpio_init(struct intel_dsi *intel_dsi, bool panel_is_on); void intel_dsi_vbt_gpio_cleanup(struct intel_dsi *intel_dsi); void intel_dsi_vbt_exec_sequence(struct intel_dsi *intel_dsi, enum mipi_seq seq_id); -void intel_dsi_msleep(struct intel_dsi *intel_dsi, int msec); void intel_dsi_log_params(struct intel_dsi *intel_dsi); #endif /* __INTEL_DSI_VBT_H__ */ diff --git a/drivers/gpu/drm/i915/display/skl_scaler.c b/drivers/gpu/drm/i915/display/skl_scaler.c index 4092679be21e..90f42f63128e 100644 --- a/drivers/gpu/drm/i915/display/skl_scaler.c +++ b/drivers/gpu/drm/i915/display/skl_scaler.c @@ -85,6 +85,10 @@ static u16 skl_scaler_calc_phase(int sub, int scale, bool chroma_cosited) #define ICL_MAX_SRC_H 4096 #define ICL_MAX_DST_W 5120 #define ICL_MAX_DST_H 4096 +#define MTL_MAX_SRC_W 4096 +#define MTL_MAX_SRC_H 8192 +#define MTL_MAX_DST_W 8192 +#define MTL_MAX_DST_H 8192 #define SKL_MIN_YUV_420_SRC_W 16 #define SKL_MIN_YUV_420_SRC_H 16 @@ -101,6 +105,10 @@ skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach, struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); const struct drm_display_mode *adjusted_mode = &crtc_state->hw.adjusted_mode; + int pipe_src_w = drm_rect_width(&crtc_state->pipe_src); + int pipe_src_h = drm_rect_height(&crtc_state->pipe_src); + int min_src_w, min_src_h, min_dst_w, min_dst_h; + int max_src_w, max_src_h, max_dst_w, max_dst_h; /* * Src coordinates are already rotated by 270 degrees for @@ -155,15 +163,33 @@ skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach, return -EINVAL; } + min_src_w = SKL_MIN_SRC_W; + min_src_h = SKL_MIN_SRC_H; + min_dst_w = SKL_MIN_DST_W; + min_dst_h = SKL_MIN_DST_H; + + if (DISPLAY_VER(dev_priv) < 11) { + max_src_w = SKL_MAX_SRC_W; + max_src_h = SKL_MAX_SRC_H; + max_dst_w = SKL_MAX_DST_W; + max_dst_h = SKL_MAX_DST_H; + } else if (DISPLAY_VER(dev_priv) < 14) { + max_src_w = ICL_MAX_SRC_W; + max_src_h = ICL_MAX_SRC_H; + max_dst_w = ICL_MAX_DST_W; + max_dst_h = ICL_MAX_DST_H; + } else { + max_src_w = MTL_MAX_SRC_W; + max_src_h = MTL_MAX_SRC_H; + max_dst_w = MTL_MAX_DST_W; + max_dst_h = MTL_MAX_DST_H; + } + /* range checks */ - if (src_w < SKL_MIN_SRC_W || src_h < SKL_MIN_SRC_H || - dst_w < SKL_MIN_DST_W || dst_h < SKL_MIN_DST_H || - (DISPLAY_VER(dev_priv) >= 11 && - (src_w > ICL_MAX_SRC_W || src_h > ICL_MAX_SRC_H || - dst_w > ICL_MAX_DST_W || dst_h > ICL_MAX_DST_H)) || - (DISPLAY_VER(dev_priv) < 11 && - (src_w > SKL_MAX_SRC_W || src_h > SKL_MAX_SRC_H || - dst_w > SKL_MAX_DST_W || dst_h > SKL_MAX_DST_H))) { + if (src_w < min_src_w || src_h < min_src_h || + dst_w < min_dst_w || dst_h < min_dst_h || + src_w > max_src_w || src_h > max_src_h || + dst_w > max_dst_w || dst_h > max_dst_h) { drm_dbg_kms(&dev_priv->drm, "scaler_user index %u.%u: src %ux%u dst %ux%u " "size is out of scaler range\n", @@ -172,6 +198,21 @@ skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach, return -EINVAL; } + /* + * The pipe scaler does not use all the bits of PIPESRC, at least + * on the earlier platforms. So even when we're scaling a plane + * the *pipe* source size must not be too large. For simplicity + * we assume the limits match the scaler source size limits. Might + * not be 100% accurate on all platforms, but good enough for now. + */ + if (pipe_src_w > max_src_w || pipe_src_h > max_src_h) { + drm_dbg_kms(&dev_priv->drm, + "scaler_user index %u.%u: pipe src size %ux%u " + "is out of scaler range\n", + crtc->pipe, scaler_user, pipe_src_w, pipe_src_h); + return -EINVAL; + } + /* mark this plane as a scaler user in crtc_state */ scaler_state->scaler_users |= (1 << scaler_user); drm_dbg_kms(&dev_priv->drm, "scaler_user index %u.%u: " diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c index 90e3e41095b3..00c80f29ad99 100644 --- a/drivers/gpu/drm/i915/display/vlv_dsi.c +++ b/drivers/gpu/drm/i915/display/vlv_dsi.c @@ -782,7 +782,6 @@ static void intel_dsi_pre_enable(struct intel_atomic_state *state, { struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder); struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc); - struct intel_connector *connector = to_intel_connector(conn_state->connector); struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); enum pipe pipe = crtc->pipe; enum port port; @@ -830,21 +829,10 @@ static void intel_dsi_pre_enable(struct intel_atomic_state *state, if (!IS_GEMINILAKE(dev_priv)) intel_dsi_prepare(encoder, pipe_config); + /* Give the panel time to power-on and then deassert its reset */ intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_POWER_ON); - - /* - * Give the panel time to power-on and then deassert its reset. - * Depending on the VBT MIPI sequences version the deassert-seq - * may contain the necessary delay, intel_dsi_msleep() will skip - * the delay in that case. If there is no deassert-seq, then an - * unconditional msleep is used to give the panel time to power-on. - */ - if (connector->panel.vbt.dsi.sequence[MIPI_SEQ_DEASSERT_RESET]) { - intel_dsi_msleep(intel_dsi, intel_dsi->panel_on_delay); - intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DEASSERT_RESET); - } else { - msleep(intel_dsi->panel_on_delay); - } + msleep(intel_dsi->panel_on_delay); + intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DEASSERT_RESET); if (IS_GEMINILAKE(dev_priv)) { glk_cold_boot = glk_dsi_enable_io(encoder); @@ -878,7 +866,7 @@ static void intel_dsi_pre_enable(struct intel_atomic_state *state, msleep(20); /* XXX */ for_each_dsi_port(port, intel_dsi->ports) dpi_send_cmd(intel_dsi, TURN_ON, false, port); - intel_dsi_msleep(intel_dsi, 100); + msleep(100); intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DISPLAY_ON); @@ -1006,7 +994,7 @@ static void intel_dsi_post_disable(struct intel_atomic_state *state, /* Assert reset */ intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_ASSERT_RESET); - intel_dsi_msleep(intel_dsi, intel_dsi->panel_off_delay); + msleep(intel_dsi->panel_off_delay); intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_POWER_OFF); intel_dsi->panel_power_off_time = ktime_get_boottime(); diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index fe4f279aaeb3..a2efc0b9d50c 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -1133,6 +1133,8 @@ static const struct intel_gt_definition xelpmp_extra_gt[] = { static const struct intel_device_info mtl_info = { XE_HP_FEATURES, XE_LPDP_FEATURES, + .__runtime.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | + BIT(TRANSCODER_C) | BIT(TRANSCODER_D), /* * Real graphics IP version will be obtained from hardware GMD_ID * register. Value provided here is just for sanity checking. diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 2372bfa04aa8..25015996f627 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -7840,8 +7840,8 @@ enum skl_power_gate { #define _PLANE_CSC_RY_GY_1(pipe) _PIPE(pipe, _PLANE_CSC_RY_GY_1_A, \ _PLANE_CSC_RY_GY_1_B) -#define _PLANE_CSC_RY_GY_2(pipe) _PIPE(pipe, _PLANE_INPUT_CSC_RY_GY_2_A, \ - _PLANE_INPUT_CSC_RY_GY_2_B) +#define _PLANE_CSC_RY_GY_2(pipe) _PIPE(pipe, _PLANE_CSC_RY_GY_2_A, \ + _PLANE_CSC_RY_GY_2_B) #define PLANE_CSC_COEFF(pipe, plane, index) _MMIO_PLANE(plane, \ _PLANE_CSC_RY_GY_1(pipe) + (index) * 4, \ _PLANE_CSC_RY_GY_2(pipe) + (index) * 4) diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c index 7cb8d9849c07..a10feb8a4194 100644 --- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c @@ -606,8 +606,7 @@ static int a4xx_pm_suspend(struct msm_gpu *gpu) { static int a4xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value) { - *value = gpu_read64(gpu, REG_A4XX_RBBM_PERFCTR_CP_0_LO, - REG_A4XX_RBBM_PERFCTR_CP_0_HI); + *value = gpu_read64(gpu, REG_A4XX_RBBM_PERFCTR_CP_0_LO); return 0; } diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index 02ff306f96f4..24feae285ccd 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -605,11 +605,9 @@ static int a5xx_ucode_init(struct msm_gpu *gpu) a5xx_ucode_check_version(a5xx_gpu, a5xx_gpu->pfp_bo); } - gpu_write64(gpu, REG_A5XX_CP_ME_INSTR_BASE_LO, - REG_A5XX_CP_ME_INSTR_BASE_HI, a5xx_gpu->pm4_iova); + gpu_write64(gpu, REG_A5XX_CP_ME_INSTR_BASE_LO, a5xx_gpu->pm4_iova); - gpu_write64(gpu, REG_A5XX_CP_PFP_INSTR_BASE_LO, - REG_A5XX_CP_PFP_INSTR_BASE_HI, a5xx_gpu->pfp_iova); + gpu_write64(gpu, REG_A5XX_CP_PFP_INSTR_BASE_LO, a5xx_gpu->pfp_iova); return 0; } @@ -868,8 +866,7 @@ static int a5xx_hw_init(struct msm_gpu *gpu) * memory rendering at this point in time and we don't want to block off * part of the virtual memory space. */ - gpu_write64(gpu, REG_A5XX_RBBM_SECVID_TSB_TRUSTED_BASE_LO, - REG_A5XX_RBBM_SECVID_TSB_TRUSTED_BASE_HI, 0x00000000); + gpu_write64(gpu, REG_A5XX_RBBM_SECVID_TSB_TRUSTED_BASE_LO, 0x00000000); gpu_write(gpu, REG_A5XX_RBBM_SECVID_TSB_TRUSTED_SIZE, 0x00000000); /* Put the GPU into 64 bit by default */ @@ -908,8 +905,7 @@ static int a5xx_hw_init(struct msm_gpu *gpu) return ret; /* Set the ringbuffer address */ - gpu_write64(gpu, REG_A5XX_CP_RB_BASE, REG_A5XX_CP_RB_BASE_HI, - gpu->rb[0]->iova); + gpu_write64(gpu, REG_A5XX_CP_RB_BASE, gpu->rb[0]->iova); /* * If the microcode supports the WHERE_AM_I opcode then we can use that @@ -936,7 +932,7 @@ static int a5xx_hw_init(struct msm_gpu *gpu) } gpu_write64(gpu, REG_A5XX_CP_RB_RPTR_ADDR, - REG_A5XX_CP_RB_RPTR_ADDR_HI, shadowptr(a5xx_gpu, gpu->rb[0])); + shadowptr(a5xx_gpu, gpu->rb[0])); } else if (gpu->nr_rings > 1) { /* Disable preemption if WHERE_AM_I isn't available */ a5xx_preempt_fini(gpu); @@ -1239,9 +1235,9 @@ static void a5xx_fault_detect_irq(struct msm_gpu *gpu) gpu_read(gpu, REG_A5XX_RBBM_STATUS), gpu_read(gpu, REG_A5XX_CP_RB_RPTR), gpu_read(gpu, REG_A5XX_CP_RB_WPTR), - gpu_read64(gpu, REG_A5XX_CP_IB1_BASE, REG_A5XX_CP_IB1_BASE_HI), + gpu_read64(gpu, REG_A5XX_CP_IB1_BASE), gpu_read(gpu, REG_A5XX_CP_IB1_BUFSZ), - gpu_read64(gpu, REG_A5XX_CP_IB2_BASE, REG_A5XX_CP_IB2_BASE_HI), + gpu_read64(gpu, REG_A5XX_CP_IB2_BASE), gpu_read(gpu, REG_A5XX_CP_IB2_BUFSZ)); /* Turn off the hangcheck timer to keep it from bothering us */ @@ -1427,8 +1423,7 @@ static int a5xx_pm_suspend(struct msm_gpu *gpu) static int a5xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value) { - *value = gpu_read64(gpu, REG_A5XX_RBBM_ALWAYSON_COUNTER_LO, - REG_A5XX_RBBM_ALWAYSON_COUNTER_HI); + *value = gpu_read64(gpu, REG_A5XX_RBBM_ALWAYSON_COUNTER_LO); return 0; } @@ -1465,8 +1460,7 @@ static int a5xx_crashdumper_run(struct msm_gpu *gpu, if (IS_ERR_OR_NULL(dumper->ptr)) return -EINVAL; - gpu_write64(gpu, REG_A5XX_CP_CRASH_SCRIPT_BASE_LO, - REG_A5XX_CP_CRASH_SCRIPT_BASE_HI, dumper->iova); + gpu_write64(gpu, REG_A5XX_CP_CRASH_SCRIPT_BASE_LO, dumper->iova); gpu_write(gpu, REG_A5XX_CP_CRASH_DUMP_CNTL, 1); @@ -1666,8 +1660,7 @@ static u64 a5xx_gpu_busy(struct msm_gpu *gpu, unsigned long *out_sample_rate) { u64 busy_cycles; - busy_cycles = gpu_read64(gpu, REG_A5XX_RBBM_PERFCTR_RBBM_0_LO, - REG_A5XX_RBBM_PERFCTR_RBBM_0_HI); + busy_cycles = gpu_read64(gpu, REG_A5XX_RBBM_PERFCTR_RBBM_0_LO); *out_sample_rate = clk_get_rate(gpu->core_clk); return busy_cycles; diff --git a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c index e0eef47dae63..f58dd564d122 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c @@ -137,7 +137,6 @@ void a5xx_preempt_trigger(struct msm_gpu *gpu) /* Set the address of the incoming preemption record */ gpu_write64(gpu, REG_A5XX_CP_CONTEXT_SWITCH_RESTORE_ADDR_LO, - REG_A5XX_CP_CONTEXT_SWITCH_RESTORE_ADDR_HI, a5xx_gpu->preempt_iova[ring->id]); a5xx_gpu->next_ring = ring; @@ -212,8 +211,7 @@ void a5xx_preempt_hw_init(struct msm_gpu *gpu) } /* Write a 0 to signal that we aren't switching pagetables */ - gpu_write64(gpu, REG_A5XX_CP_CONTEXT_SWITCH_SMMU_INFO_LO, - REG_A5XX_CP_CONTEXT_SWITCH_SMMU_INFO_HI, 0); + gpu_write64(gpu, REG_A5XX_CP_CONTEXT_SWITCH_SMMU_INFO_LO, 0); /* Reset the preemption state */ set_preempt_state(a5xx_gpu, PREEMPT_NONE); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index 9d7fc44c1e2a..95e73eddc5e9 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -247,8 +247,7 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) OUT_RING(ring, submit->seqno); trace_msm_gpu_submit_flush(submit, - gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO, - REG_A6XX_CP_ALWAYS_ON_COUNTER_HI)); + gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO)); a6xx_flush(gpu, ring); } @@ -947,8 +946,7 @@ static int a6xx_ucode_init(struct msm_gpu *gpu) } } - gpu_write64(gpu, REG_A6XX_CP_SQE_INSTR_BASE, - REG_A6XX_CP_SQE_INSTR_BASE+1, a6xx_gpu->sqe_iova); + gpu_write64(gpu, REG_A6XX_CP_SQE_INSTR_BASE, a6xx_gpu->sqe_iova); return 0; } @@ -999,8 +997,7 @@ static int hw_init(struct msm_gpu *gpu) * memory rendering at this point in time and we don't want to block off * part of the virtual memory space. */ - gpu_write64(gpu, REG_A6XX_RBBM_SECVID_TSB_TRUSTED_BASE_LO, - REG_A6XX_RBBM_SECVID_TSB_TRUSTED_BASE_HI, 0x00000000); + gpu_write64(gpu, REG_A6XX_RBBM_SECVID_TSB_TRUSTED_BASE_LO, 0x00000000); gpu_write(gpu, REG_A6XX_RBBM_SECVID_TSB_TRUSTED_SIZE, 0x00000000); /* Turn on 64 bit addressing for all blocks */ @@ -1049,11 +1046,9 @@ static int hw_init(struct msm_gpu *gpu) if (!adreno_is_a650_family(adreno_gpu)) { /* Set the GMEM VA range [0x100000:0x100000 + gpu->gmem - 1] */ - gpu_write64(gpu, REG_A6XX_UCHE_GMEM_RANGE_MIN_LO, - REG_A6XX_UCHE_GMEM_RANGE_MIN_HI, 0x00100000); + gpu_write64(gpu, REG_A6XX_UCHE_GMEM_RANGE_MIN_LO, 0x00100000); gpu_write64(gpu, REG_A6XX_UCHE_GMEM_RANGE_MAX_LO, - REG_A6XX_UCHE_GMEM_RANGE_MAX_HI, 0x00100000 + adreno_gpu->gmem - 1); } @@ -1145,8 +1140,7 @@ static int hw_init(struct msm_gpu *gpu) goto out; /* Set the ringbuffer address */ - gpu_write64(gpu, REG_A6XX_CP_RB_BASE, REG_A6XX_CP_RB_BASE_HI, - gpu->rb[0]->iova); + gpu_write64(gpu, REG_A6XX_CP_RB_BASE, gpu->rb[0]->iova); /* Targets that support extended APRIV can use the RPTR shadow from * hardware but all the other ones need to disable the feature. Targets @@ -1178,7 +1172,6 @@ static int hw_init(struct msm_gpu *gpu) } gpu_write64(gpu, REG_A6XX_CP_RB_RPTR_ADDR_LO, - REG_A6XX_CP_RB_RPTR_ADDR_HI, shadowptr(a6xx_gpu, gpu->rb[0])); } @@ -1506,9 +1499,9 @@ static void a6xx_fault_detect_irq(struct msm_gpu *gpu) gpu_read(gpu, REG_A6XX_RBBM_STATUS), gpu_read(gpu, REG_A6XX_CP_RB_RPTR), gpu_read(gpu, REG_A6XX_CP_RB_WPTR), - gpu_read64(gpu, REG_A6XX_CP_IB1_BASE, REG_A6XX_CP_IB1_BASE_HI), + gpu_read64(gpu, REG_A6XX_CP_IB1_BASE), gpu_read(gpu, REG_A6XX_CP_IB1_REM_SIZE), - gpu_read64(gpu, REG_A6XX_CP_IB2_BASE, REG_A6XX_CP_IB2_BASE_HI), + gpu_read64(gpu, REG_A6XX_CP_IB2_BASE), gpu_read(gpu, REG_A6XX_CP_IB2_REM_SIZE)); /* Turn off the hangcheck timer to keep it from bothering us */ @@ -1719,8 +1712,7 @@ static int a6xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value) /* Force the GPU power on so we can read this register */ a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET); - *value = gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO, - REG_A6XX_CP_ALWAYS_ON_COUNTER_HI); + *value = gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO); a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET); @@ -1858,6 +1850,39 @@ static uint32_t a6xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) return ring->memptrs->rptr = gpu_read(gpu, REG_A6XX_CP_RB_RPTR); } +static bool a6xx_progress(struct msm_gpu *gpu, struct msm_ringbuffer *ring) +{ + struct msm_cp_state cp_state = { + .ib1_base = gpu_read64(gpu, REG_A6XX_CP_IB1_BASE), + .ib2_base = gpu_read64(gpu, REG_A6XX_CP_IB2_BASE), + .ib1_rem = gpu_read(gpu, REG_A6XX_CP_IB1_REM_SIZE), + .ib2_rem = gpu_read(gpu, REG_A6XX_CP_IB2_REM_SIZE), + }; + bool progress; + + /* + * Adjust the remaining data to account for what has already been + * fetched from memory, but not yet consumed by the SQE. + * + * This is not *technically* correct, the amount buffered could + * exceed the IB size due to hw prefetching ahead, but: + * + * (1) We aren't trying to find the exact position, just whether + * progress has been made + * (2) The CP_REG_TO_MEM at the end of a submit should be enough + * to prevent prefetching into an unrelated submit. (And + * either way, at some point the ROQ will be full.) + */ + cp_state.ib1_rem += gpu_read(gpu, REG_A6XX_CP_CSQ_IB1_STAT) >> 16; + cp_state.ib2_rem += gpu_read(gpu, REG_A6XX_CP_CSQ_IB2_STAT) >> 16; + + progress = !!memcmp(&cp_state, &ring->last_cp_state, sizeof(cp_state)); + + ring->last_cp_state = cp_state; + + return progress; +} + static u32 a618_get_speed_bin(u32 fuse) { if (fuse == 0) @@ -1974,6 +1999,7 @@ static const struct adreno_gpu_funcs funcs = { .create_address_space = a6xx_create_address_space, .create_private_address_space = a6xx_create_private_address_space, .get_rptr = a6xx_get_rptr, + .progress = a6xx_progress, }, .get_timestamp = a6xx_get_timestamp, }; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c index a5c3d1ed255a..a023d5f962dc 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c @@ -147,8 +147,7 @@ static int a6xx_crashdumper_run(struct msm_gpu *gpu, /* Make sure all pending memory writes are posted */ wmb(); - gpu_write64(gpu, REG_A6XX_CP_CRASH_SCRIPT_BASE_LO, - REG_A6XX_CP_CRASH_SCRIPT_BASE_HI, dumper->iova); + gpu_write64(gpu, REG_A6XX_CP_CRASH_SCRIPT_BASE_LO, dumper->iova); gpu_write(gpu, REG_A6XX_CP_CRASH_DUMP_CNTL, 1); diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c index cd009d56d35d..ed1e0c650bb1 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_device.c +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c @@ -440,20 +440,21 @@ struct msm_gpu *adreno_load_gpu(struct drm_device *dev) ret = pm_runtime_get_sync(&pdev->dev); if (ret < 0) { - pm_runtime_put_sync(&pdev->dev); + pm_runtime_put_noidle(&pdev->dev); DRM_DEV_ERROR(dev->dev, "Couldn't power up the GPU: %d\n", ret); - return NULL; + goto err_disable_rpm; } mutex_lock(&gpu->lock); ret = msm_gpu_hw_init(gpu); mutex_unlock(&gpu->lock); - pm_runtime_put_autosuspend(&pdev->dev); if (ret) { DRM_DEV_ERROR(dev->dev, "gpu hw init failed: %d\n", ret); - return NULL; + goto err_put_rpm; } + pm_runtime_put_autosuspend(&pdev->dev); + #ifdef CONFIG_DEBUG_FS if (gpu->funcs->debugfs_init) { gpu->funcs->debugfs_init(gpu, dev->primary); @@ -462,6 +463,13 @@ struct msm_gpu *adreno_load_gpu(struct drm_device *dev) #endif return gpu; + +err_put_rpm: + pm_runtime_put_sync_suspend(&pdev->dev); +err_disable_rpm: + pm_runtime_disable(&pdev->dev); + + return NULL; } static int find_chipid(struct device *dev, struct adreno_rev *rev) diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index 5a0ff112634b..ac3d1d492a48 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -50,6 +50,8 @@ #define MSM_VERSION_MINOR 9 #define MSM_VERSION_PATCHLEVEL 0 +static void msm_deinit_vram(struct drm_device *ddev); + static const struct drm_mode_config_funcs mode_config_funcs = { .fb_create = msm_framebuffer_create, .output_poll_changed = drm_fb_helper_output_poll_changed, @@ -241,7 +243,8 @@ static int msm_drm_uninit(struct device *dev) msm_fbdev_free(ddev); #endif - msm_disp_snapshot_destroy(ddev); + if (kms) + msm_disp_snapshot_destroy(ddev); drm_mode_config_cleanup(ddev); @@ -249,19 +252,16 @@ static int msm_drm_uninit(struct device *dev) drm_bridge_remove(priv->bridges[i]); priv->num_bridges = 0; - pm_runtime_get_sync(dev); - msm_irq_uninstall(ddev); - pm_runtime_put_sync(dev); + if (kms) { + pm_runtime_get_sync(dev); + msm_irq_uninstall(ddev); + pm_runtime_put_sync(dev); + } if (kms && kms->funcs) kms->funcs->destroy(kms); - if (priv->vram.paddr) { - unsigned long attrs = DMA_ATTR_NO_KERNEL_MAPPING; - drm_mm_takedown(&priv->vram.mm); - dma_free_attrs(dev, priv->vram.size, NULL, - priv->vram.paddr, attrs); - } + msm_deinit_vram(ddev); component_unbind_all(dev, ddev); @@ -401,6 +401,19 @@ static int msm_init_vram(struct drm_device *dev) return ret; } +static void msm_deinit_vram(struct drm_device *ddev) +{ + struct msm_drm_private *priv = ddev->dev_private; + unsigned long attrs = DMA_ATTR_NO_KERNEL_MAPPING; + + if (!priv->vram.paddr) + return; + + drm_mm_takedown(&priv->vram.mm); + dma_free_attrs(ddev->dev, priv->vram.size, NULL, priv->vram.paddr, + attrs); +} + static int msm_drm_init(struct device *dev, const struct drm_driver *drv) { struct msm_drm_private *priv = dev_get_drvdata(dev); @@ -420,7 +433,10 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv) priv->dev = ddev; priv->wq = alloc_ordered_workqueue("msm", 0); - priv->hangcheck_period = DRM_MSM_HANGCHECK_DEFAULT_PERIOD; + if (!priv->wq) { + ret = -ENOMEM; + goto err_put_dev; + } INIT_LIST_HEAD(&priv->objects); mutex_init(&priv->obj_lock); @@ -443,12 +459,12 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv) ret = msm_init_vram(ddev); if (ret) - return ret; + goto err_cleanup_mode_config; /* Bind all our sub-components: */ ret = component_bind_all(dev, ddev); if (ret) - return ret; + goto err_deinit_vram; dma_set_max_seg_size(dev, UINT_MAX); @@ -543,6 +559,17 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv) err_msm_uninit: msm_drm_uninit(dev); + + return ret; + +err_deinit_vram: + msm_deinit_vram(ddev); +err_cleanup_mode_config: + drm_mode_config_cleanup(ddev); + destroy_workqueue(priv->wq); +err_put_dev: + drm_dev_put(ddev); + return ret; } diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h index b2ea262296a4..d4e0ef608950 100644 --- a/drivers/gpu/drm/msm/msm_drv.h +++ b/drivers/gpu/drm/msm/msm_drv.h @@ -224,7 +224,13 @@ struct msm_drm_private { struct drm_atomic_state *pm_state; - /* For hang detection, in ms */ + /** + * hangcheck_period: For hang detection, in ms + * + * Note that in practice, a submit/job will get at least two hangcheck + * periods, due to checking for progress being implemented as simply + * "have the CP position registers changed since last time?" + */ unsigned int hangcheck_period; /** diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index 4f495eecc34b..380249500325 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -494,6 +494,21 @@ static void hangcheck_timer_reset(struct msm_gpu *gpu) round_jiffies_up(jiffies + msecs_to_jiffies(priv->hangcheck_period))); } +static bool made_progress(struct msm_gpu *gpu, struct msm_ringbuffer *ring) +{ + if (ring->hangcheck_progress_retries >= DRM_MSM_HANGCHECK_PROGRESS_RETRIES) + return false; + + if (!gpu->funcs->progress) + return false; + + if (!gpu->funcs->progress(gpu, ring)) + return false; + + ring->hangcheck_progress_retries++; + return true; +} + static void hangcheck_handler(struct timer_list *t) { struct msm_gpu *gpu = from_timer(gpu, t, hangcheck_timer); @@ -504,9 +519,12 @@ static void hangcheck_handler(struct timer_list *t) if (fence != ring->hangcheck_fence) { /* some progress has been made.. ya! */ ring->hangcheck_fence = fence; - } else if (fence_before(fence, ring->fctx->last_fence)) { + ring->hangcheck_progress_retries = 0; + } else if (fence_before(fence, ring->fctx->last_fence) && + !made_progress(gpu, ring)) { /* no progress and not done.. hung! */ ring->hangcheck_fence = fence; + ring->hangcheck_progress_retries = 0; DRM_DEV_ERROR(dev->dev, "%s: hangcheck detected gpu lockup rb %d!\n", gpu->name, ring->id); DRM_DEV_ERROR(dev->dev, "%s: completed fence: %u\n", @@ -832,6 +850,7 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev, struct msm_gpu *gpu, const struct msm_gpu_funcs *funcs, const char *name, struct msm_gpu_config *config) { + struct msm_drm_private *priv = drm->dev_private; int i, ret, nr_rings = config->nr_rings; void *memptrs; uint64_t memptrs_iova; @@ -859,6 +878,16 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev, kthread_init_work(&gpu->recover_work, recover_worker); kthread_init_work(&gpu->fault_work, fault_worker); + priv->hangcheck_period = DRM_MSM_HANGCHECK_DEFAULT_PERIOD; + + /* + * If progress detection is supported, halve the hangcheck timer + * duration, as it takes two iterations of the hangcheck handler + * to detect a hang. + */ + if (funcs->progress) + priv->hangcheck_period /= 2; + timer_setup(&gpu->hangcheck_timer, hangcheck_handler, 0); spin_lock_init(&gpu->perf_lock); diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index a89bfdc3d7f9..732295e25683 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -78,6 +78,15 @@ struct msm_gpu_funcs { struct msm_gem_address_space *(*create_private_address_space) (struct msm_gpu *gpu); uint32_t (*get_rptr)(struct msm_gpu *gpu, struct msm_ringbuffer *ring); + + /** + * progress: Has the GPU made progress? + * + * Return true if GPU position in cmdstream has advanced (or changed) + * since the last call. To avoid false negatives, this should account + * for cmdstream that is buffered in this FIFO upstream of the CP fw. + */ + bool (*progress)(struct msm_gpu *gpu, struct msm_ringbuffer *ring); }; /* Additional state for iommu faults: */ @@ -237,6 +246,7 @@ struct msm_gpu { #define DRM_MSM_INACTIVE_PERIOD 66 /* in ms (roughly four frames) */ #define DRM_MSM_HANGCHECK_DEFAULT_PERIOD 500 /* in ms */ +#define DRM_MSM_HANGCHECK_PROGRESS_RETRIES 3 struct timer_list hangcheck_timer; /* Fault info for most recent iova fault: */ @@ -548,7 +558,7 @@ static inline void gpu_rmw(struct msm_gpu *gpu, u32 reg, u32 mask, u32 or) msm_rmw(gpu->mmio + (reg << 2), mask, or); } -static inline u64 gpu_read64(struct msm_gpu *gpu, u32 lo, u32 hi) +static inline u64 gpu_read64(struct msm_gpu *gpu, u32 reg) { u64 val; @@ -566,17 +576,17 @@ static inline u64 gpu_read64(struct msm_gpu *gpu, u32 lo, u32 hi) * when the lo is read, so make sure to read the lo first to trigger * that */ - val = (u64) msm_readl(gpu->mmio + (lo << 2)); - val |= ((u64) msm_readl(gpu->mmio + (hi << 2)) << 32); + val = (u64) msm_readl(gpu->mmio + (reg << 2)); + val |= ((u64) msm_readl(gpu->mmio + ((reg + 1) << 2)) << 32); return val; } -static inline void gpu_write64(struct msm_gpu *gpu, u32 lo, u32 hi, u64 val) +static inline void gpu_write64(struct msm_gpu *gpu, u32 reg, u64 val) { /* Why not a writeq here? Read the screed above */ - msm_writel(lower_32_bits(val), gpu->mmio + (lo << 2)); - msm_writel(upper_32_bits(val), gpu->mmio + (hi << 2)); + msm_writel(lower_32_bits(val), gpu->mmio + (reg << 2)); + msm_writel(upper_32_bits(val), gpu->mmio + ((reg + 1) << 2)); } int msm_gpu_pm_suspend(struct msm_gpu *gpu); diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.h b/drivers/gpu/drm/msm/msm_ringbuffer.h index 2a5045abe46e..698b333abccd 100644 --- a/drivers/gpu/drm/msm/msm_ringbuffer.h +++ b/drivers/gpu/drm/msm/msm_ringbuffer.h @@ -35,6 +35,11 @@ struct msm_rbmemptrs { volatile u64 ttbr0; }; +struct msm_cp_state { + uint64_t ib1_base, ib2_base; + uint32_t ib1_rem, ib2_rem; +}; + struct msm_ringbuffer { struct msm_gpu *gpu; int id; @@ -64,6 +69,29 @@ struct msm_ringbuffer { uint64_t memptrs_iova; struct msm_fence_context *fctx; + /** + * hangcheck_progress_retries: + * + * The number of extra hangcheck duration cycles that we have given + * due to it appearing that the GPU is making forward progress. + * + * For GPU generations which support progress detection (see. + * msm_gpu_funcs::progress()), if the GPU appears to be making progress + * (ie. the CP has advanced in the command stream, we'll allow up to + * DRM_MSM_HANGCHECK_PROGRESS_RETRIES expirations of the hangcheck timer + * before killing the job. But to detect progress we need two sample + * points, so the duration of the hangcheck timer is halved. In other + * words we'll let the submit run for up to: + * + * (DRM_MSM_HANGCHECK_DEFAULT_PERIOD / 2) * (DRM_MSM_HANGCHECK_PROGRESS_RETRIES + 1) + */ + int hangcheck_progress_retries; + + /** + * last_cp_state: The state of the CP at the last call to gpu->progress() + */ + struct msm_cp_state last_cp_state; + /* * preempt_lock protects preemption and serializes wptr updates against * preemption. Can be aquired from irq context. diff --git a/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c b/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c index b4729a94c34a..898b892f1143 100644 --- a/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c +++ b/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c @@ -471,7 +471,7 @@ static int otm8009a_probe(struct mipi_dsi_device *dsi) DRM_MODE_CONNECTOR_DSI); ctx->bl_dev = devm_backlight_device_register(dev, dev_name(dev), - dsi->host->dev, ctx, + dev, ctx, &otm8009a_backlight_ops, NULL); if (IS_ERR(ctx->bl_dev)) { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 0bc1ebc43002..1ec9c53a7bf4 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -1221,9 +1221,6 @@ int vmw_kms_write_svga(struct vmw_private *vmw_priv, bool vmw_kms_validate_mode_vram(struct vmw_private *dev_priv, uint32_t pitch, uint32_t height); -u32 vmw_get_vblank_counter(struct drm_crtc *crtc); -int vmw_enable_vblank(struct drm_crtc *crtc); -void vmw_disable_vblank(struct drm_crtc *crtc); int vmw_kms_present(struct vmw_private *dev_priv, struct drm_file *file_priv, struct vmw_framebuffer *vfb, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index 13721bcf047c..aab6389cb4aa 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -31,7 +31,6 @@ #include <drm/drm_fourcc.h> #include <drm/drm_rect.h> #include <drm/drm_sysfs.h> -#include <drm/drm_vblank.h> #include "vmwgfx_kms.h" @@ -832,15 +831,6 @@ void vmw_du_crtc_atomic_begin(struct drm_crtc *crtc, void vmw_du_crtc_atomic_flush(struct drm_crtc *crtc, struct drm_atomic_state *state) { - struct drm_pending_vblank_event *event = crtc->state->event; - - if (event) { - crtc->state->event = NULL; - - spin_lock_irq(&crtc->dev->event_lock); - drm_crtc_send_vblank_event(crtc, event); - spin_unlock_irq(&crtc->dev->event_lock); - } } @@ -1274,70 +1264,10 @@ static void vmw_framebuffer_bo_destroy(struct drm_framebuffer *framebuffer) kfree(vfbd); } -static int vmw_framebuffer_bo_dirty(struct drm_framebuffer *framebuffer, - struct drm_file *file_priv, - unsigned int flags, unsigned int color, - struct drm_clip_rect *clips, - unsigned int num_clips) -{ - struct vmw_private *dev_priv = vmw_priv(framebuffer->dev); - struct vmw_framebuffer_bo *vfbd = - vmw_framebuffer_to_vfbd(framebuffer); - struct drm_clip_rect norect; - int ret, increment = 1; - - drm_modeset_lock_all(&dev_priv->drm); - - if (!num_clips) { - num_clips = 1; - clips = &norect; - norect.x1 = norect.y1 = 0; - norect.x2 = framebuffer->width; - norect.y2 = framebuffer->height; - } else if (flags & DRM_MODE_FB_DIRTY_ANNOTATE_COPY) { - num_clips /= 2; - increment = 2; - } - - switch (dev_priv->active_display_unit) { - case vmw_du_legacy: - ret = vmw_kms_ldu_do_bo_dirty(dev_priv, &vfbd->base, 0, 0, - clips, num_clips, increment); - break; - default: - ret = -EINVAL; - WARN_ONCE(true, "Dirty called with invalid display system.\n"); - break; - } - - vmw_cmd_flush(dev_priv, false); - - drm_modeset_unlock_all(&dev_priv->drm); - - return ret; -} - -static int vmw_framebuffer_bo_dirty_ext(struct drm_framebuffer *framebuffer, - struct drm_file *file_priv, - unsigned int flags, unsigned int color, - struct drm_clip_rect *clips, - unsigned int num_clips) -{ - struct vmw_private *dev_priv = vmw_priv(framebuffer->dev); - - if (dev_priv->active_display_unit == vmw_du_legacy && - vmw_cmd_supported(dev_priv)) - return vmw_framebuffer_bo_dirty(framebuffer, file_priv, flags, - color, clips, num_clips); - - return drm_atomic_helper_dirtyfb(framebuffer, file_priv, flags, color, - clips, num_clips); -} - static const struct drm_framebuffer_funcs vmw_framebuffer_bo_funcs = { .create_handle = vmw_framebuffer_bo_create_handle, .destroy = vmw_framebuffer_bo_destroy, - .dirty = vmw_framebuffer_bo_dirty_ext, + .dirty = drm_atomic_helper_dirtyfb, }; /* @@ -2158,30 +2088,6 @@ bool vmw_kms_validate_mode_vram(struct vmw_private *dev_priv, dev_priv->max_primary_mem : dev_priv->vram_size); } - -/* - * Function called by DRM code called with vbl_lock held. - */ -u32 vmw_get_vblank_counter(struct drm_crtc *crtc) -{ - return 0; -} - -/* - * Function called by DRM code called with vbl_lock held. - */ -int vmw_enable_vblank(struct drm_crtc *crtc) -{ - return -EINVAL; -} - -/* - * Function called by DRM code called with vbl_lock held. - */ -void vmw_disable_vblank(struct drm_crtc *crtc) -{ -} - /** * vmw_du_update_layout - Update the display unit with topology from resolution * plugin and generate DRM uevent diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h index 85f86faa3243..b02d2793659f 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h @@ -517,11 +517,6 @@ void vmw_du_connector_destroy_state(struct drm_connector *connector, */ int vmw_kms_ldu_init_display(struct vmw_private *dev_priv); int vmw_kms_ldu_close_display(struct vmw_private *dev_priv); -int vmw_kms_ldu_do_bo_dirty(struct vmw_private *dev_priv, - struct vmw_framebuffer *framebuffer, - unsigned int flags, unsigned int color, - struct drm_clip_rect *clips, - unsigned int num_clips, int increment); int vmw_kms_update_proxy(struct vmw_resource *res, const struct drm_clip_rect *clips, unsigned num_clips, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c index b8761f16dd78..ac72c20715f3 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c @@ -28,7 +28,6 @@ #include <drm/drm_atomic.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_fourcc.h> -#include <drm/drm_vblank.h> #include "vmwgfx_kms.h" @@ -235,9 +234,7 @@ static const struct drm_crtc_funcs vmw_legacy_crtc_funcs = { .atomic_duplicate_state = vmw_du_crtc_duplicate_state, .atomic_destroy_state = vmw_du_crtc_destroy_state, .set_config = drm_atomic_helper_set_config, - .get_vblank_counter = vmw_get_vblank_counter, - .enable_vblank = vmw_enable_vblank, - .disable_vblank = vmw_disable_vblank, + .page_flip = drm_atomic_helper_page_flip, }; @@ -277,6 +274,12 @@ static const struct drm_connector_helper_funcs vmw_ldu_connector_helper_funcs = { }; +static int vmw_kms_ldu_do_bo_dirty(struct vmw_private *dev_priv, + struct vmw_framebuffer *framebuffer, + unsigned int flags, unsigned int color, + struct drm_mode_rect *clips, + unsigned int num_clips); + /* * Legacy Display Plane Functions */ @@ -295,7 +298,6 @@ vmw_ldu_primary_plane_atomic_update(struct drm_plane *plane, struct drm_framebuffer *fb; struct drm_crtc *crtc = new_state->crtc ?: old_state->crtc; - ldu = vmw_crtc_to_ldu(crtc); dev_priv = vmw_priv(plane->dev); fb = new_state->fb; @@ -308,8 +310,31 @@ vmw_ldu_primary_plane_atomic_update(struct drm_plane *plane, vmw_ldu_del_active(dev_priv, ldu); vmw_ldu_commit_list(dev_priv); -} + if (vfb && vmw_cmd_supported(dev_priv)) { + struct drm_mode_rect fb_rect = { + .x1 = 0, + .y1 = 0, + .x2 = vfb->base.width, + .y2 = vfb->base.height + }; + struct drm_mode_rect *damage_rects = drm_plane_get_damage_clips(new_state); + u32 rect_count = drm_plane_get_damage_clips_count(new_state); + int ret; + + if (!damage_rects) { + damage_rects = &fb_rect; + rect_count = 1; + } + + ret = vmw_kms_ldu_do_bo_dirty(dev_priv, vfb, 0, 0, damage_rects, rect_count); + + drm_WARN_ONCE(plane->dev, ret, + "vmw_kms_ldu_do_bo_dirty failed with: ret=%d\n", ret); + + vmw_cmd_flush(dev_priv, false); + } +} static const struct drm_plane_funcs vmw_ldu_plane_funcs = { .update_plane = drm_atomic_helper_update_plane, @@ -507,10 +532,6 @@ int vmw_kms_ldu_init_display(struct vmw_private *dev_priv) dev_priv->ldu_priv->last_num_active = 0; dev_priv->ldu_priv->fb = NULL; - ret = drm_vblank_init(dev, num_display_units); - if (ret != 0) - goto err_free; - vmw_kms_create_implicit_placement_property(dev_priv); for (i = 0; i < num_display_units; ++i) { @@ -544,11 +565,11 @@ int vmw_kms_ldu_close_display(struct vmw_private *dev_priv) } -int vmw_kms_ldu_do_bo_dirty(struct vmw_private *dev_priv, - struct vmw_framebuffer *framebuffer, - unsigned int flags, unsigned int color, - struct drm_clip_rect *clips, - unsigned int num_clips, int increment) +static int vmw_kms_ldu_do_bo_dirty(struct vmw_private *dev_priv, + struct vmw_framebuffer *framebuffer, + unsigned int flags, unsigned int color, + struct drm_mode_rect *clips, + unsigned int num_clips) { size_t fifo_size; int i; @@ -564,7 +585,7 @@ int vmw_kms_ldu_do_bo_dirty(struct vmw_private *dev_priv, return -ENOMEM; memset(cmd, 0, fifo_size); - for (i = 0; i < num_clips; i++, clips += increment) { + for (i = 0; i < num_clips; i++, clips++) { cmd[i].header = SVGA_CMD_UPDATE; cmd[i].body.x = clips->x1; cmd[i].body.y = clips->y1; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c index 9c79873f62f0..e1f36a09c59c 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c @@ -29,7 +29,6 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_damage_helper.h> #include <drm/drm_fourcc.h> -#include <drm/drm_vblank.h> #include "vmwgfx_kms.h" @@ -320,9 +319,6 @@ static const struct drm_crtc_funcs vmw_screen_object_crtc_funcs = { .atomic_destroy_state = vmw_du_crtc_destroy_state, .set_config = drm_atomic_helper_set_config, .page_flip = drm_atomic_helper_page_flip, - .get_vblank_counter = vmw_get_vblank_counter, - .enable_vblank = vmw_enable_vblank, - .disable_vblank = vmw_disable_vblank, }; /* @@ -730,7 +726,6 @@ vmw_sou_primary_plane_atomic_update(struct drm_plane *plane, struct drm_plane_state *old_state = drm_atomic_get_old_plane_state(state, plane); struct drm_plane_state *new_state = drm_atomic_get_new_plane_state(state, plane); struct drm_crtc *crtc = new_state->crtc; - struct drm_pending_vblank_event *event = NULL; struct vmw_fence_obj *fence = NULL; int ret; @@ -754,24 +749,6 @@ vmw_sou_primary_plane_atomic_update(struct drm_plane *plane, return; } - /* For error case vblank event is send from vmw_du_crtc_atomic_flush */ - event = crtc->state->event; - if (event && fence) { - struct drm_file *file_priv = event->base.file_priv; - - ret = vmw_event_fence_action_queue(file_priv, - fence, - &event->base, - &event->event.vbl.tv_sec, - &event->event.vbl.tv_usec, - true); - - if (unlikely(ret != 0)) - DRM_ERROR("Failed to queue event on fence.\n"); - else - crtc->state->event = NULL; - } - if (fence) vmw_fence_obj_unreference(&fence); } @@ -947,7 +924,7 @@ err_free: int vmw_kms_sou_init_display(struct vmw_private *dev_priv) { struct drm_device *dev = &dev_priv->drm; - int i, ret; + int i; /* Screen objects won't work if GMR's aren't available */ if (!dev_priv->has_gmr) @@ -957,12 +934,6 @@ int vmw_kms_sou_init_display(struct vmw_private *dev_priv) return -ENOSYS; } - ret = -ENOMEM; - - ret = drm_vblank_init(dev, VMWGFX_NUM_DISPLAY_UNITS); - if (unlikely(ret != 0)) - return ret; - for (i = 0; i < VMWGFX_NUM_DISPLAY_UNITS; ++i) vmw_sou_init(dev_priv, i); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c index 8650c3aea8f0..0090abe89254 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c @@ -29,7 +29,6 @@ #include <drm/drm_atomic_helper.h> #include <drm/drm_damage_helper.h> #include <drm/drm_fourcc.h> -#include <drm/drm_vblank.h> #include "vmwgfx_kms.h" #include "vmw_surface_cache.h" @@ -925,9 +924,6 @@ static const struct drm_crtc_funcs vmw_stdu_crtc_funcs = { .atomic_destroy_state = vmw_du_crtc_destroy_state, .set_config = drm_atomic_helper_set_config, .page_flip = drm_atomic_helper_page_flip, - .get_vblank_counter = vmw_get_vblank_counter, - .enable_vblank = vmw_enable_vblank, - .disable_vblank = vmw_disable_vblank, }; @@ -1591,7 +1587,6 @@ vmw_stdu_primary_plane_atomic_update(struct drm_plane *plane, struct vmw_plane_state *vps = vmw_plane_state_to_vps(new_state); struct drm_crtc *crtc = new_state->crtc; struct vmw_screen_target_display_unit *stdu; - struct drm_pending_vblank_event *event; struct vmw_fence_obj *fence = NULL; struct vmw_private *dev_priv; int ret; @@ -1640,23 +1635,6 @@ vmw_stdu_primary_plane_atomic_update(struct drm_plane *plane, return; } - /* In case of error, vblank event is send in vmw_du_crtc_atomic_flush */ - event = crtc->state->event; - if (event && fence) { - struct drm_file *file_priv = event->base.file_priv; - - ret = vmw_event_fence_action_queue(file_priv, - fence, - &event->base, - &event->event.vbl.tv_sec, - &event->event.vbl.tv_usec, - true); - if (ret) - DRM_ERROR("Failed to queue event on fence.\n"); - else - crtc->state->event = NULL; - } - if (fence) vmw_fence_obj_unreference(&fence); } @@ -1883,10 +1861,6 @@ int vmw_kms_stdu_init_display(struct vmw_private *dev_priv) if (!(dev_priv->capabilities & SVGA_CAP_GBOBJECTS)) return -ENOSYS; - ret = drm_vblank_init(dev, VMWGFX_NUM_DISPLAY_UNITS); - if (unlikely(ret != 0)) - return ret; - dev_priv->active_display_unit = vmw_du_screen_target; for (i = 0; i < VMWGFX_NUM_DISPLAY_UNITS; ++i) { |