diff options
Diffstat (limited to 'drivers/gpu/drm/msm')
151 files changed, 8326 insertions, 5736 deletions
diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig index 7ec833b6d829..7f127e2ae442 100644 --- a/drivers/gpu/drm/msm/Kconfig +++ b/drivers/gpu/drm/msm/Kconfig @@ -104,6 +104,7 @@ config DRM_MSM_DPU config DRM_MSM_DP bool "Enable DisplayPort support in MSM DRM driver" depends on DRM_MSM + select DRM_DISPLAY_HDMI_AUDIO_HELPER select RATIONAL default y help @@ -170,6 +171,8 @@ config DRM_MSM_HDMI bool "Enable HDMI support in MSM DRM driver" depends on DRM_MSM default y + select DRM_DISPLAY_HDMI_HELPER + select DRM_DISPLAY_HDMI_STATE_HELPER help Compile in support for the HDMI output MSM DRM driver. It can be a primary or a secondary display on device. Note that this is used diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile index f274d9430cc3..44c66a293415 100644 --- a/drivers/gpu/drm/msm/Makefile +++ b/drivers/gpu/drm/msm/Makefile @@ -48,7 +48,6 @@ msm-display-$(CONFIG_DRM_MSM_MDP4) += \ disp/mdp4/mdp4_dsi_encoder.o \ disp/mdp4/mdp4_dtv_encoder.o \ disp/mdp4/mdp4_lcdc_encoder.o \ - disp/mdp4/mdp4_lvds_connector.o \ disp/mdp4/mdp4_lvds_pll.o \ disp/mdp4/mdp4_irq.o \ disp/mdp4/mdp4_kms.o \ @@ -78,6 +77,7 @@ msm-display-$(CONFIG_DRM_MSM_DPU) += \ disp/dpu1/dpu_hw_catalog.o \ disp/dpu1/dpu_hw_cdm.o \ disp/dpu1/dpu_hw_ctl.o \ + disp/dpu1/dpu_hw_cwb.o \ disp/dpu1/dpu_hw_dsc.o \ disp/dpu1/dpu_hw_dsc_1_2.o \ disp/dpu1/dpu_hw_interrupts.o \ @@ -195,6 +195,11 @@ ADRENO_HEADERS = \ generated/a4xx.xml.h \ generated/a5xx.xml.h \ generated/a6xx.xml.h \ + generated/a6xx_descriptors.xml.h \ + generated/a6xx_enums.xml.h \ + generated/a6xx_perfcntrs.xml.h \ + generated/a7xx_enums.xml.h \ + generated/a7xx_perfcntrs.xml.h \ generated/a6xx_gmu.xml.h \ generated/adreno_common.xml.h \ generated/adreno_pm4.xml.h \ diff --git a/drivers/gpu/drm/msm/adreno/a2xx_catalog.c b/drivers/gpu/drm/msm/adreno/a2xx_catalog.c index 9ddb7b31fd98..5ddd015f930d 100644 --- a/drivers/gpu/drm/msm/adreno/a2xx_catalog.c +++ b/drivers/gpu/drm/msm/adreno/a2xx_catalog.c @@ -45,8 +45,3 @@ static const struct adreno_info a2xx_gpus[] = { } }; DECLARE_ADRENO_GPULIST(a2xx); - -MODULE_FIRMWARE("qcom/leia_pfp_470.fw"); -MODULE_FIRMWARE("qcom/leia_pm4_470.fw"); -MODULE_FIRMWARE("qcom/yamato_pfp.fw"); -MODULE_FIRMWARE("qcom/yamato_pm4.fw"); diff --git a/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c b/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c index 39641551eeb6..4280f71e472a 100644 --- a/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c +++ b/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c @@ -71,10 +71,6 @@ static int a2xx_gpummu_unmap(struct msm_mmu *mmu, uint64_t iova, size_t len) return 0; } -static void a2xx_gpummu_resume_translation(struct msm_mmu *mmu) -{ -} - static void a2xx_gpummu_destroy(struct msm_mmu *mmu) { struct a2xx_gpummu *gpummu = to_a2xx_gpummu(mmu); @@ -90,7 +86,6 @@ static const struct msm_mmu_funcs funcs = { .map = a2xx_gpummu_map, .unmap = a2xx_gpummu_unmap, .destroy = a2xx_gpummu_destroy, - .resume_translation = a2xx_gpummu_resume_translation, }; struct msm_mmu *a2xx_gpummu_new(struct device *dev, struct msm_gpu *gpu) diff --git a/drivers/gpu/drm/msm/adreno/a3xx_catalog.c b/drivers/gpu/drm/msm/adreno/a3xx_catalog.c index 2eb6c3e93748..1498e6532f62 100644 --- a/drivers/gpu/drm/msm/adreno/a3xx_catalog.c +++ b/drivers/gpu/drm/msm/adreno/a3xx_catalog.c @@ -85,8 +85,3 @@ static const struct adreno_info a3xx_gpus[] = { } }; DECLARE_ADRENO_GPULIST(a3xx); - -MODULE_FIRMWARE("qcom/a300_pm4.fw"); -MODULE_FIRMWARE("qcom/a300_pfp.fw"); -MODULE_FIRMWARE("qcom/a330_pm4.fw"); -MODULE_FIRMWARE("qcom/a330_pfp.fw"); diff --git a/drivers/gpu/drm/msm/adreno/a4xx_catalog.c b/drivers/gpu/drm/msm/adreno/a4xx_catalog.c index 93519f807f87..09f9f228b75e 100644 --- a/drivers/gpu/drm/msm/adreno/a4xx_catalog.c +++ b/drivers/gpu/drm/msm/adreno/a4xx_catalog.c @@ -45,6 +45,3 @@ static const struct adreno_info a4xx_gpus[] = { } }; DECLARE_ADRENO_GPULIST(a4xx); - -MODULE_FIRMWARE("qcom/a420_pm4.fw"); -MODULE_FIRMWARE("qcom/a420_pfp.fw"); diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c index 50c490b492f0..f1b18a6663f7 100644 --- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c @@ -251,8 +251,8 @@ static int a4xx_hw_init(struct msm_gpu *gpu) gpu_write(gpu, REG_A4XX_UCHE_CACHE_WAYS_VFD, 0x07); /* Disable L2 bypass to avoid UCHE out of bounds errors */ - gpu_write(gpu, REG_A4XX_UCHE_TRAP_BASE_LO, 0xffff0000); - gpu_write(gpu, REG_A4XX_UCHE_TRAP_BASE_HI, 0xffff0000); + gpu_write(gpu, REG_A4XX_UCHE_TRAP_BASE_LO, lower_32_bits(adreno_gpu->uche_trap_base)); + gpu_write(gpu, REG_A4XX_UCHE_TRAP_BASE_HI, upper_32_bits(adreno_gpu->uche_trap_base)); gpu_write(gpu, REG_A4XX_CP_DEBUG, (1 << 25) | (adreno_is_a420(adreno_gpu) ? (1 << 29) : 0)); @@ -693,6 +693,8 @@ struct msm_gpu *a4xx_gpu_init(struct drm_device *dev) if (ret) goto fail; + adreno_gpu->uche_trap_base = 0xffff0000ffff0000ull; + if (!gpu->aspace) { /* TODO we think it is possible to configure the GPU to * restrict access to VRAM carveout. But the required diff --git a/drivers/gpu/drm/msm/adreno/a5xx_catalog.c b/drivers/gpu/drm/msm/adreno/a5xx_catalog.c index 633f31539162..b48a636d8237 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_catalog.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_catalog.c @@ -150,12 +150,3 @@ static const struct adreno_info a5xx_gpus[] = { } }; DECLARE_ADRENO_GPULIST(a5xx); - -MODULE_FIRMWARE("qcom/a530_pm4.fw"); -MODULE_FIRMWARE("qcom/a530_pfp.fw"); -MODULE_FIRMWARE("qcom/a530v3_gpmu.fw2"); -MODULE_FIRMWARE("qcom/a530_zap.mdt"); -MODULE_FIRMWARE("qcom/a530_zap.b00"); -MODULE_FIRMWARE("qcom/a530_zap.b01"); -MODULE_FIRMWARE("qcom/a530_zap.b02"); -MODULE_FIRMWARE("qcom/a540_gpmu.fw2"); diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index ee89db72e36e..60aef0796236 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -131,6 +131,8 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) struct msm_ringbuffer *ring = submit->ring; unsigned int i, ibs = 0; + adreno_check_and_reenable_stall(adreno_gpu); + if (IS_ENABLED(CONFIG_DRM_MSM_GPU_SUDO) && submit->in_rb) { ring->cur_ctx_seqno = 0; a5xx_submit_in_rb(gpu, submit); @@ -750,10 +752,10 @@ static int a5xx_hw_init(struct msm_gpu *gpu) gpu_write(gpu, REG_A5XX_UCHE_CACHE_WAYS, 0x02); /* Disable L2 bypass in the UCHE */ - gpu_write(gpu, REG_A5XX_UCHE_TRAP_BASE_LO, 0xFFFF0000); - gpu_write(gpu, REG_A5XX_UCHE_TRAP_BASE_HI, 0x0001FFFF); - gpu_write(gpu, REG_A5XX_UCHE_WRITE_THRU_BASE_LO, 0xFFFF0000); - gpu_write(gpu, REG_A5XX_UCHE_WRITE_THRU_BASE_HI, 0x0001FFFF); + gpu_write(gpu, REG_A5XX_UCHE_TRAP_BASE_LO, lower_32_bits(adreno_gpu->uche_trap_base)); + gpu_write(gpu, REG_A5XX_UCHE_TRAP_BASE_HI, upper_32_bits(adreno_gpu->uche_trap_base)); + gpu_write(gpu, REG_A5XX_UCHE_WRITE_THRU_BASE_LO, lower_32_bits(adreno_gpu->uche_trap_base)); + gpu_write(gpu, REG_A5XX_UCHE_WRITE_THRU_BASE_HI, upper_32_bits(adreno_gpu->uche_trap_base)); /* Set the GMEM VA range (0 to gpu->gmem) */ gpu_write(gpu, REG_A5XX_UCHE_GMEM_RANGE_MIN_LO, 0x00100000); @@ -1253,7 +1255,7 @@ static void a5xx_fault_detect_irq(struct msm_gpu *gpu) gpu_read(gpu, REG_A5XX_CP_IB2_BUFSZ)); /* Turn off the hangcheck timer to keep it from bothering us */ - del_timer(&gpu->hangcheck_timer); + timer_delete(&gpu->hangcheck_timer); kthread_queue_work(gpu->worker, &gpu->recover_work); } @@ -1760,11 +1762,6 @@ struct msm_gpu *a5xx_gpu_init(struct drm_device *dev) unsigned int nr_rings; int ret; - if (!pdev) { - DRM_DEV_ERROR(dev->dev, "No A5XX device is defined\n"); - return ERR_PTR(-ENXIO); - } - a5xx_gpu = kzalloc(sizeof(*a5xx_gpu), GFP_KERNEL); if (!a5xx_gpu) return ERR_PTR(-ENOMEM); @@ -1805,5 +1802,7 @@ struct msm_gpu *a5xx_gpu_init(struct drm_device *dev) adreno_gpu->ubwc_config.macrotile_mode = 0; adreno_gpu->ubwc_config.ubwc_swizzle = 0x7; + adreno_gpu->uche_trap_base = 0x0001ffffffff0000ull; + return gpu; } diff --git a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c index 0469fea55010..b5f9d40687d5 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c @@ -79,7 +79,8 @@ static struct msm_ringbuffer *get_next_ring(struct msm_gpu *gpu) static void a5xx_preempt_timer(struct timer_list *t) { - struct a5xx_gpu *a5xx_gpu = from_timer(a5xx_gpu, t, preempt_timer); + struct a5xx_gpu *a5xx_gpu = timer_container_of(a5xx_gpu, t, + preempt_timer); struct msm_gpu *gpu = &a5xx_gpu->base.base; struct drm_device *dev = gpu->dev; @@ -182,7 +183,7 @@ void a5xx_preempt_irq(struct msm_gpu *gpu) return; /* Delete the preemption watchdog timer */ - del_timer(&a5xx_gpu->preempt_timer); + timer_delete(&a5xx_gpu->preempt_timer); /* * The hardware should be setting CP_CONTEXT_SWITCH_CNTL to zero before diff --git a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c index 0c560e84ad5a..a45819e04aab 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c @@ -681,6 +681,7 @@ static const struct adreno_info a6xx_gpus[] = { [ADRENO_FW_SQE] = "a630_sqe.fw", }, .gmem = (SZ_128K + SZ_4K), + .quirks = ADRENO_QUIRK_4GB_VA, .inactive_period = DRM_MSM_INACTIVE_PERIOD, .init = a6xx_gpu_init, .zapfw = "a610_zap.mdt", @@ -713,6 +714,7 @@ static const struct adreno_info a6xx_gpus[] = { [ADRENO_FW_GMU] = "a630_gmu.bin", }, .gmem = SZ_512K, + .quirks = ADRENO_QUIRK_4GB_VA, .inactive_period = DRM_MSM_INACTIVE_PERIOD, .init = a6xx_gpu_init, .zapfw = "a615_zap.mdt", @@ -743,7 +745,8 @@ static const struct adreno_info a6xx_gpus[] = { }, .gmem = SZ_512K, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT, + .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | + ADRENO_QUIRK_4GB_VA, .init = a6xx_gpu_init, .zapfw = "a615_zap.mbn", .a6xx = &(const struct a6xx_info) { @@ -769,7 +772,8 @@ static const struct adreno_info a6xx_gpus[] = { }, .gmem = SZ_512K, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT, + .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | + ADRENO_QUIRK_4GB_VA, .init = a6xx_gpu_init, .a6xx = &(const struct a6xx_info) { .protect = &a630_protect, @@ -791,6 +795,7 @@ static const struct adreno_info a6xx_gpus[] = { [ADRENO_FW_GMU] = "a619_gmu.bin", }, .gmem = SZ_512K, + .quirks = ADRENO_QUIRK_4GB_VA, .inactive_period = DRM_MSM_INACTIVE_PERIOD, .init = a6xx_gpu_init, .zapfw = "a615_zap.mdt", @@ -815,6 +820,7 @@ static const struct adreno_info a6xx_gpus[] = { [ADRENO_FW_GMU] = "a619_gmu.bin", }, .gmem = SZ_512K, + .quirks = ADRENO_QUIRK_4GB_VA, .inactive_period = DRM_MSM_INACTIVE_PERIOD, .init = a6xx_gpu_init, .zapfw = "a615_zap.mdt", @@ -838,8 +844,9 @@ static const struct adreno_info a6xx_gpus[] = { [ADRENO_FW_GMU] = "a619_gmu.bin", }, .gmem = SZ_512K, + .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | + ADRENO_QUIRK_4GB_VA, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT, .init = a6xx_gpu_init, .zapfw = "a615_zap.mdt", .a6xx = &(const struct a6xx_info) { @@ -874,12 +881,39 @@ static const struct adreno_info a6xx_gpus[] = { .gmu_cgc_mode = 0x00020200, .prim_fifo_threshold = 0x00010000, }, - .address_space_size = SZ_16G, .speedbins = ADRENO_SPEEDBINS( { 0, 0 }, { 137, 1 }, ), }, { + .chip_ids = ADRENO_CHIP_IDS(0x06020300), + .family = ADRENO_6XX_GEN3, + .fw = { + [ADRENO_FW_SQE] = "a650_sqe.fw", + [ADRENO_FW_GMU] = "a623_gmu.bin", + }, + .gmem = SZ_512K, + .inactive_period = DRM_MSM_INACTIVE_PERIOD, + .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | + ADRENO_QUIRK_HAS_HW_APRIV, + .init = a6xx_gpu_init, + .a6xx = &(const struct a6xx_info) { + .hwcg = a690_hwcg, + .protect = &a650_protect, + .gmu_cgc_mode = 0x00020200, + .prim_fifo_threshold = 0x00010000, + .bcms = (const struct a6xx_bcm[]) { + { .name = "SH0", .buswidth = 16 }, + { .name = "MC0", .buswidth = 4 }, + { + .name = "ACV", + .fixed = true, + .perfmode = BIT(3), + }, + { /* sentinel */ }, + }, + }, + }, { .chip_ids = ADRENO_CHIP_IDS( 0x06030001, 0x06030002 @@ -891,8 +925,9 @@ static const struct adreno_info a6xx_gpus[] = { [ADRENO_FW_GMU] = "a630_gmu.bin", }, .gmem = SZ_1M, + .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | + ADRENO_QUIRK_4GB_VA, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT, .init = a6xx_gpu_init, .zapfw = "a630_zap.mdt", .a6xx = &(const struct a6xx_info) { @@ -910,8 +945,9 @@ static const struct adreno_info a6xx_gpus[] = { [ADRENO_FW_GMU] = "a640_gmu.bin", }, .gmem = SZ_1M, + .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | + ADRENO_QUIRK_4GB_VA, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT, .init = a6xx_gpu_init, .zapfw = "a640_zap.mdt", .a6xx = &(const struct a6xx_info) { @@ -944,7 +980,6 @@ static const struct adreno_info a6xx_gpus[] = { .gmu_cgc_mode = 0x00020202, .prim_fifo_threshold = 0x00300200, }, - .address_space_size = SZ_16G, .speedbins = ADRENO_SPEEDBINS( { 0, 0 }, { 1, 1 }, @@ -971,7 +1006,6 @@ static const struct adreno_info a6xx_gpus[] = { .gmu_cgc_mode = 0x00020000, .prim_fifo_threshold = 0x00300200, }, - .address_space_size = SZ_16G, }, { .chip_ids = ADRENO_CHIP_IDS(0x06060300), .family = ADRENO_6XX_GEN4, @@ -990,7 +1024,6 @@ static const struct adreno_info a6xx_gpus[] = { .gmu_cgc_mode = 0x00020200, .prim_fifo_threshold = 0x00300200, }, - .address_space_size = SZ_16G, }, { .chip_ids = ADRENO_CHIP_IDS(0x06030500), .family = ADRENO_6XX_GEN4, @@ -1010,7 +1043,6 @@ static const struct adreno_info a6xx_gpus[] = { .gmu_cgc_mode = 0x00020202, .prim_fifo_threshold = 0x00200200, }, - .address_space_size = SZ_16G, .speedbins = ADRENO_SPEEDBINS( { 0, 0 }, { 117, 0 }, @@ -1027,8 +1059,9 @@ static const struct adreno_info a6xx_gpus[] = { [ADRENO_FW_GMU] = "a640_gmu.bin", }, .gmem = SZ_2M, + .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | + ADRENO_QUIRK_4GB_VA, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT, .init = a6xx_gpu_init, .zapfw = "a640_zap.mdt", .a6xx = &(const struct a6xx_info) { @@ -1056,22 +1089,10 @@ static const struct adreno_info a6xx_gpus[] = { .gmu_cgc_mode = 0x00020200, .prim_fifo_threshold = 0x00800200, }, - .address_space_size = SZ_16G, } }; DECLARE_ADRENO_GPULIST(a6xx); -MODULE_FIRMWARE("qcom/a615_zap.mbn"); -MODULE_FIRMWARE("qcom/a619_gmu.bin"); -MODULE_FIRMWARE("qcom/a630_sqe.fw"); -MODULE_FIRMWARE("qcom/a630_gmu.bin"); -MODULE_FIRMWARE("qcom/a630_zap.mbn"); -MODULE_FIRMWARE("qcom/a640_gmu.bin"); -MODULE_FIRMWARE("qcom/a650_gmu.bin"); -MODULE_FIRMWARE("qcom/a650_sqe.fw"); -MODULE_FIRMWARE("qcom/a660_gmu.bin"); -MODULE_FIRMWARE("qcom/a660_sqe.fw"); - static const struct adreno_reglist a702_hwcg[] = { { REG_A6XX_RBBM_CLOCK_CNTL_SP0, 0x22222222 }, { REG_A6XX_RBBM_CLOCK_CNTL2_SP0, 0x02222220 }, @@ -1314,7 +1335,7 @@ static const uint32_t a7xx_pwrup_reglist_regs[] = { REG_A6XX_RB_NC_MODE_CNTL, REG_A6XX_RB_CMP_DBG_ECO_CNTL, REG_A7XX_GRAS_NC_MODE_CNTL, - REG_A6XX_RB_CONTEXT_SWITCH_GMEM_SAVE_RESTORE, + REG_A6XX_RB_CONTEXT_SWITCH_GMEM_SAVE_RESTORE_ENABLE, REG_A6XX_UCHE_GBIF_GX_CONFIG, REG_A6XX_UCHE_CLIENT_PF, REG_A6XX_TPL1_DBG_ECO_CNTL1, @@ -1366,7 +1387,6 @@ static const struct adreno_info a7xx_gpus[] = { .pwrup_reglist = &a7xx_pwrup_reglist, .gmu_cgc_mode = 0x00020000, }, - .address_space_size = SZ_16G, .preempt_record_size = 2860 * SZ_1K, }, { .chip_ids = ADRENO_CHIP_IDS(0x43050a01), /* "C510v2" */ @@ -1388,8 +1408,18 @@ static const struct adreno_info a7xx_gpus[] = { .pwrup_reglist = &a7xx_pwrup_reglist, .gmu_chipid = 0x7020100, .gmu_cgc_mode = 0x00020202, + .bcms = (const struct a6xx_bcm[]) { + { .name = "SH0", .buswidth = 16 }, + { .name = "MC0", .buswidth = 4 }, + { + .name = "ACV", + .fixed = true, + .perfmode = BIT(3), + .perfmode_bw = 16500000, + }, + { /* sentinel */ }, + }, }, - .address_space_size = SZ_16G, .preempt_record_size = 4192 * SZ_1K, }, { .chip_ids = ADRENO_CHIP_IDS(0x43050c01), /* "C512v2" */ @@ -1411,7 +1441,6 @@ static const struct adreno_info a7xx_gpus[] = { .gmu_chipid = 0x7050001, .gmu_cgc_mode = 0x00020202, }, - .address_space_size = SZ_256G, .preempt_record_size = 4192 * SZ_1K, }, { .chip_ids = ADRENO_CHIP_IDS(0x43051401), /* "C520v2" */ @@ -1432,8 +1461,18 @@ static const struct adreno_info a7xx_gpus[] = { .pwrup_reglist = &a7xx_pwrup_reglist, .gmu_chipid = 0x7090100, .gmu_cgc_mode = 0x00020202, + .bcms = (const struct a6xx_bcm[]) { + { .name = "SH0", .buswidth = 16 }, + { .name = "MC0", .buswidth = 4 }, + { + .name = "ACV", + .fixed = true, + .perfmode = BIT(2), + .perfmode_bw = 10687500, + }, + { /* sentinel */ }, + }, }, - .address_space_size = SZ_16G, .preempt_record_size = 3572 * SZ_1K, } }; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index e386b059187a..38c0f8ef85c3 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -9,6 +9,7 @@ #include <linux/pm_domain.h> #include <linux/pm_opp.h> #include <soc/qcom/cmd-db.h> +#include <soc/qcom/tcs.h> #include <drm/drm_gem.h> #include "a6xx_gpu.h" @@ -27,7 +28,7 @@ static void a6xx_gmu_fault(struct a6xx_gmu *gmu) gmu->hung = true; /* Turn off the hangcheck timer while we are resetting */ - del_timer(&gpu->hangcheck_timer); + timer_delete(&gpu->hangcheck_timer); /* Queue the GPU handler because we need to treat this as a recovery */ kthread_queue_work(gpu->worker, &gpu->recover_work); @@ -109,9 +110,11 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp, bool suspended) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + const struct a6xx_info *info = adreno_gpu->info->a6xx; struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); struct a6xx_gmu *gmu = &a6xx_gpu->gmu; u32 perf_index; + u32 bw_index = 0; unsigned long gpu_freq; int ret = 0; @@ -124,6 +127,37 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp, if (gpu_freq == gmu->gpu_freqs[perf_index]) break; + /* If enabled, find the corresponding DDR bandwidth index */ + if (info->bcms && gmu->nr_gpu_bws > 1) { + unsigned int bw = dev_pm_opp_get_bw(opp, true, 0); + + for (bw_index = 0; bw_index < gmu->nr_gpu_bws - 1; bw_index++) { + if (bw == gmu->gpu_bw_table[bw_index]) + break; + } + + /* Vote AB as a fraction of the max bandwidth, starting from A750 */ + if (bw && adreno_is_a750_family(adreno_gpu)) { + u64 tmp; + + /* For now, vote for 25% of the bandwidth */ + tmp = bw * 25; + do_div(tmp, 100); + + /* + * The AB vote consists of a 16 bit wide quantized level + * against the maximum supported bandwidth. + * Quantization can be calculated as below: + * vote = (bandwidth * 2^16) / max bandwidth + */ + tmp *= MAX_AB_VOTE; + do_div(tmp, gmu->gpu_bw_table[gmu->nr_gpu_bws - 1]); + + bw_index |= AB_VOTE(clamp(tmp, 1, MAX_AB_VOTE)); + bw_index |= AB_VOTE_ENABLE; + } + } + gmu->current_perf_index = perf_index; gmu->freq = gmu->gpu_freqs[perf_index]; @@ -139,8 +173,10 @@ void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp, return; if (!gmu->legacy) { - a6xx_hfi_set_freq(gmu, perf_index); - dev_pm_opp_set_opp(&gpu->pdev->dev, opp); + a6xx_hfi_set_freq(gmu, perf_index, bw_index); + /* With Bandwidth voting, we now vote for all resources, so skip OPP set */ + if (!bw_index) + dev_pm_opp_set_opp(&gpu->pdev->dev, opp); return; } @@ -729,6 +765,7 @@ static int a6xx_gmu_fw_load(struct a6xx_gmu *gmu) const struct firmware *fw_image = adreno_gpu->fw[ADRENO_FW_GMU]; const struct block_header *blk; u32 reg_offset; + u32 ver; u32 itcm_base = 0x00000000; u32 dtcm_base = 0x00040000; @@ -775,6 +812,12 @@ static int a6xx_gmu_fw_load(struct a6xx_gmu *gmu) } } + ver = gmu_read(gmu, REG_A6XX_GMU_CORE_FW_VERSION); + DRM_INFO_ONCE("Loaded GMU firmware v%u.%u.%u\n", + FIELD_GET(A6XX_GMU_CORE_FW_VERSION_MAJOR__MASK, ver), + FIELD_GET(A6XX_GMU_CORE_FW_VERSION_MINOR__MASK, ver), + FIELD_GET(A6XX_GMU_CORE_FW_VERSION_STEP__MASK, ver)); + return 0; } @@ -1021,14 +1064,6 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu) gmu->hung = false; - /* Notify AOSS about the ACD state (unimplemented for now => disable it) */ - if (!IS_ERR(gmu->qmp)) { - ret = qmp_send(gmu->qmp, "{class: gpu, res: acd, val: %d}", - 0 /* Hardcode ACD to be disabled for now */); - if (ret) - dev_err(gmu->dev, "failed to send GPU ACD state\n"); - } - /* Turn on the resources */ pm_runtime_get_sync(gmu->dev); @@ -1126,49 +1161,50 @@ static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu) struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; u32 val; + int ret; /* - * The GMU may still be in slumber unless the GPU started so check and - * skip putting it back into slumber if so + * GMU firmware's internal power state gets messed up if we send "prepare_slumber" hfi when + * oob_gpu handshake wasn't done after the last wake up. So do a dummy handshake here when + * required */ - val = gmu_read(gmu, REG_A6XX_GPU_GMU_CX_GMU_RPMH_POWER_STATE); + if (adreno_gpu->base.needs_hw_init) { + if (a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET)) + goto force_off; + + a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET); + } - if (val != 0xf) { - int ret = a6xx_gmu_wait_for_idle(gmu); + ret = a6xx_gmu_wait_for_idle(gmu); - /* If the GMU isn't responding assume it is hung */ - if (ret) { - a6xx_gmu_force_off(gmu); - return; - } + /* If the GMU isn't responding assume it is hung */ + if (ret) + goto force_off; - a6xx_bus_clear_pending_transactions(adreno_gpu, a6xx_gpu->hung); + a6xx_bus_clear_pending_transactions(adreno_gpu, a6xx_gpu->hung); - /* tell the GMU we want to slumber */ - ret = a6xx_gmu_notify_slumber(gmu); - if (ret) { - a6xx_gmu_force_off(gmu); - return; - } + /* tell the GMU we want to slumber */ + ret = a6xx_gmu_notify_slumber(gmu); + if (ret) + goto force_off; - ret = gmu_poll_timeout(gmu, - REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS, val, - !(val & A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS_GPUBUSYIGNAHB), - 100, 10000); + ret = gmu_poll_timeout(gmu, + REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS, val, + !(val & A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS_GPUBUSYIGNAHB), + 100, 10000); - /* - * Let the user know we failed to slumber but don't worry too - * much because we are powering down anyway - */ + /* + * Let the user know we failed to slumber but don't worry too + * much because we are powering down anyway + */ - if (ret) - DRM_DEV_ERROR(gmu->dev, - "Unable to slumber GMU: status = 0%x/0%x\n", - gmu_read(gmu, - REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS), - gmu_read(gmu, - REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS2)); - } + if (ret) + DRM_DEV_ERROR(gmu->dev, + "Unable to slumber GMU: status = 0%x/0%x\n", + gmu_read(gmu, + REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS), + gmu_read(gmu, + REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS2)); /* Turn off HFI */ a6xx_hfi_stop(gmu); @@ -1178,6 +1214,11 @@ static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu) /* Tell RPMh to power off the GPU */ a6xx_rpmh_stop(gmu); + + return; + +force_off: + a6xx_gmu_force_off(gmu); } @@ -1265,7 +1306,7 @@ static int a6xx_gmu_memory_alloc(struct a6xx_gmu *gmu, struct a6xx_gmu_bo *bo, bo->virt = msm_gem_get_vaddr(bo->obj); bo->size = size; - msm_gem_object_set_name(bo->obj, name); + msm_gem_object_set_name(bo->obj, "%s", name); return 0; } @@ -1287,6 +1328,104 @@ static int a6xx_gmu_memory_probe(struct a6xx_gmu *gmu) return 0; } +/** + * struct bcm_db - Auxiliary data pertaining to each Bus Clock Manager (BCM) + * @unit: divisor used to convert bytes/sec bw value to an RPMh msg + * @width: multiplier used to convert bytes/sec bw value to an RPMh msg + * @vcd: virtual clock domain that this bcm belongs to + * @reserved: reserved field + */ +struct bcm_db { + __le32 unit; + __le16 width; + u8 vcd; + u8 reserved; +}; + +static int a6xx_gmu_rpmh_bw_votes_init(struct adreno_gpu *adreno_gpu, + const struct a6xx_info *info, + struct a6xx_gmu *gmu) +{ + const struct bcm_db *bcm_data[GMU_MAX_BCMS] = { 0 }; + unsigned int bcm_index, bw_index, bcm_count = 0; + + /* Retrieve BCM data from cmd-db */ + for (bcm_index = 0; bcm_index < GMU_MAX_BCMS; bcm_index++) { + const struct a6xx_bcm *bcm = &info->bcms[bcm_index]; + size_t count; + + /* Stop at NULL terminated bcm entry */ + if (!bcm->name) + break; + + bcm_data[bcm_index] = cmd_db_read_aux_data(bcm->name, &count); + if (IS_ERR(bcm_data[bcm_index])) + return PTR_ERR(bcm_data[bcm_index]); + + if (!count) { + dev_err(gmu->dev, "invalid BCM '%s' aux data size\n", + bcm->name); + return -EINVAL; + } + + bcm_count++; + } + + /* Generate BCM votes values for each bandwidth & BCM */ + for (bw_index = 0; bw_index < gmu->nr_gpu_bws; bw_index++) { + u32 *data = gmu->gpu_ib_votes[bw_index]; + u32 bw = gmu->gpu_bw_table[bw_index]; + + /* Calculations loosely copied from bcm_aggregate() & tcs_cmd_gen() */ + for (bcm_index = 0; bcm_index < bcm_count; bcm_index++) { + const struct a6xx_bcm *bcm = &info->bcms[bcm_index]; + bool commit = false; + u64 peak; + u32 vote; + + if (bcm_index == bcm_count - 1 || + (bcm_data[bcm_index + 1] && + bcm_data[bcm_index]->vcd != bcm_data[bcm_index + 1]->vcd)) + commit = true; + + if (!bw) { + data[bcm_index] = BCM_TCS_CMD(commit, false, 0, 0); + continue; + } + + if (bcm->fixed) { + u32 perfmode = 0; + + /* GMU on A6xx votes perfmode on all valid bandwidth */ + if (!adreno_is_a7xx(adreno_gpu) || + (bcm->perfmode_bw && bw >= bcm->perfmode_bw)) + perfmode = bcm->perfmode; + + data[bcm_index] = BCM_TCS_CMD(commit, true, 0, perfmode); + continue; + } + + /* Multiply the bandwidth by the width of the connection */ + peak = (u64)bw * le16_to_cpu(bcm_data[bcm_index]->width); + do_div(peak, bcm->buswidth); + + /* Input bandwidth value is in KBps, scale the value to BCM unit */ + peak *= 1000; + do_div(peak, le32_to_cpu(bcm_data[bcm_index]->unit)); + + vote = clamp(peak, 1, BCM_TCS_CMD_VOTE_MASK); + + /* GMUs on A7xx votes on both x & y */ + if (adreno_is_a7xx(adreno_gpu)) + data[bcm_index] = BCM_TCS_CMD(commit, true, vote, vote); + else + data[bcm_index] = BCM_TCS_CMD(commit, true, 0, vote); + } + } + + return 0; +} + /* Return the 'arc-level' for the given frequency */ static unsigned int a6xx_gmu_get_arc_level(struct device *dev, unsigned long freq) @@ -1390,12 +1529,15 @@ static int a6xx_gmu_rpmh_arc_votes_init(struct device *dev, u32 *votes, * The GMU votes with the RPMh for itself and on behalf of the GPU but we need * to construct the list of votes on the CPU and send it over. Query the RPMh * voltage levels and build the votes + * The GMU can also vote for DDR interconnects, use the OPP bandwidth entries + * and BCM parameters to build the votes. */ static int a6xx_gmu_rpmh_votes_init(struct a6xx_gmu *gmu) { struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; + const struct a6xx_info *info = adreno_gpu->info->a6xx; struct msm_gpu *gpu = &adreno_gpu->base; int ret; @@ -1407,6 +1549,10 @@ static int a6xx_gmu_rpmh_votes_init(struct a6xx_gmu *gmu) ret |= a6xx_gmu_rpmh_arc_votes_init(gmu->dev, gmu->cx_arc_votes, gmu->gmu_freqs, gmu->nr_gmu_freqs, "cx.lvl"); + /* Build the interconnect votes */ + if (info->bcms && gmu->nr_gpu_bws > 1) + ret |= a6xx_gmu_rpmh_bw_votes_init(adreno_gpu, info, gmu); + return ret; } @@ -1442,10 +1588,43 @@ static int a6xx_gmu_build_freq_table(struct device *dev, unsigned long *freqs, return index; } +static int a6xx_gmu_build_bw_table(struct device *dev, unsigned long *bandwidths, + u32 size) +{ + int count = dev_pm_opp_get_opp_count(dev); + struct dev_pm_opp *opp; + int i, index = 0; + unsigned int bandwidth = 1; + + /* + * The OPP table doesn't contain the "off" bandwidth level so we need to + * add 1 to the table size to account for it + */ + + if (WARN(count + 1 > size, + "The GMU bandwidth table is being truncated\n")) + count = size - 1; + + /* Set the "off" bandwidth */ + bandwidths[index++] = 0; + + for (i = 0; i < count; i++) { + opp = dev_pm_opp_find_bw_ceil(dev, &bandwidth, 0); + if (IS_ERR(opp)) + break; + + dev_pm_opp_put(opp); + bandwidths[index++] = bandwidth++; + } + + return index; +} + static int a6xx_gmu_pwrlevels_probe(struct a6xx_gmu *gmu) { struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; + const struct a6xx_info *info = adreno_gpu->info->a6xx; struct msm_gpu *gpu = &adreno_gpu->base; int ret = 0; @@ -1472,10 +1651,87 @@ static int a6xx_gmu_pwrlevels_probe(struct a6xx_gmu *gmu) gmu->current_perf_index = gmu->nr_gpu_freqs - 1; + /* + * The GMU also handles GPU Interconnect Votes so build a list + * of DDR bandwidths from the GPU OPP table + */ + if (info->bcms) + gmu->nr_gpu_bws = a6xx_gmu_build_bw_table(&gpu->pdev->dev, + gmu->gpu_bw_table, ARRAY_SIZE(gmu->gpu_bw_table)); + /* Build the list of RPMh votes that we'll send to the GMU */ return a6xx_gmu_rpmh_votes_init(gmu); } +static int a6xx_gmu_acd_probe(struct a6xx_gmu *gmu) +{ + struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); + struct a6xx_hfi_acd_table *cmd = &gmu->acd_table; + struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; + struct msm_gpu *gpu = &adreno_gpu->base; + int ret, i, cmd_idx = 0; + extern bool disable_acd; + + /* Skip ACD probe if requested via module param */ + if (disable_acd) { + DRM_DEV_ERROR(gmu->dev, "Skipping GPU ACD probe\n"); + return 0; + } + + cmd->version = 1; + cmd->stride = 1; + cmd->enable_by_level = 0; + + /* Skip freq = 0 and parse acd-level for rest of the OPPs */ + for (i = 1; i < gmu->nr_gpu_freqs; i++) { + struct dev_pm_opp *opp; + struct device_node *np; + unsigned long freq; + u32 val; + + freq = gmu->gpu_freqs[i]; + opp = dev_pm_opp_find_freq_exact(&gpu->pdev->dev, freq, true); + np = dev_pm_opp_get_of_node(opp); + + ret = of_property_read_u32(np, "qcom,opp-acd-level", &val); + of_node_put(np); + dev_pm_opp_put(opp); + if (ret == -EINVAL) + continue; + else if (ret) { + DRM_DEV_ERROR(gmu->dev, "Unable to read acd level for freq %lu\n", freq); + return ret; + } + + cmd->enable_by_level |= BIT(i); + cmd->data[cmd_idx++] = val; + } + + cmd->num_levels = cmd_idx; + + /* It is a problem if qmp node is unavailable when ACD is required */ + if (cmd->enable_by_level && IS_ERR_OR_NULL(gmu->qmp)) { + DRM_DEV_ERROR(gmu->dev, "Unable to send ACD state to AOSS\n"); + return -EINVAL; + } + + /* Otherwise, nothing to do if qmp is unavailable */ + if (IS_ERR_OR_NULL(gmu->qmp)) + return 0; + + /* + * Notify AOSS about the ACD state. AOSS is supposed to assume that ACD is disabled on + * system reset. So it is harmless if we couldn't notify 'OFF' state + */ + ret = qmp_send(gmu->qmp, "{class: gpu, res: acd, val: %d}", !!cmd->enable_by_level); + if (ret && cmd->enable_by_level) { + DRM_DEV_ERROR(gmu->dev, "Failed to send ACD state to AOSS\n"); + return ret; + } + + return 0; +} + static int a6xx_gmu_clocks_probe(struct a6xx_gmu *gmu) { int ret = devm_clk_bulk_get_all(gmu->dev, &gmu->clocks); @@ -1794,10 +2050,11 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node) goto detach_cxpd; } + /* Other errors are handled during GPU ACD probe */ gmu->qmp = qmp_get(gmu->dev); - if (IS_ERR(gmu->qmp) && adreno_is_a7xx(adreno_gpu)) { - ret = PTR_ERR(gmu->qmp); - goto remove_device_link; + if (PTR_ERR_OR_ZERO(gmu->qmp) == -EPROBE_DEFER) { + ret = -EPROBE_DEFER; + goto detach_gxpd; } init_completion(&gmu->pd_gate); @@ -1813,6 +2070,10 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node) /* Get the power levels for the GMU and GPU */ a6xx_gmu_pwrlevels_probe(gmu); + ret = a6xx_gmu_acd_probe(gmu); + if (ret) + goto detach_gxpd; + /* Set up the HFI queues */ a6xx_hfi_init(gmu); @@ -1823,7 +2084,13 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node) return 0; -remove_device_link: +detach_gxpd: + if (!IS_ERR_OR_NULL(gmu->gxpd)) + dev_pm_domain_detach(gmu->gxpd, false); + + if (!IS_ERR_OR_NULL(gmu->qmp)) + qmp_put(gmu->qmp); + device_link_del(link); detach_cxpd: diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h index b4a79f88ccf4..b2d4489b4024 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h @@ -19,6 +19,18 @@ struct a6xx_gmu_bo { u64 iova; }; +#define GMU_MAX_GX_FREQS 16 +#define GMU_MAX_CX_FREQS 4 +#define GMU_MAX_BCMS 3 + +struct a6xx_bcm { + char *name; + unsigned int buswidth; + bool fixed; + unsigned int perfmode; + unsigned int perfmode_bw; +}; + /* * These define the different GMU wake up options - these define how both the * CPU and the GMU bring up the hardware @@ -79,12 +91,17 @@ struct a6xx_gmu { int current_perf_index; int nr_gpu_freqs; - unsigned long gpu_freqs[16]; - u32 gx_arc_votes[16]; + unsigned long gpu_freqs[GMU_MAX_GX_FREQS]; + u32 gx_arc_votes[GMU_MAX_GX_FREQS]; + struct a6xx_hfi_acd_table acd_table; + + int nr_gpu_bws; + unsigned long gpu_bw_table[GMU_MAX_GX_FREQS]; + u32 gpu_ib_votes[GMU_MAX_GX_FREQS][GMU_MAX_BCMS]; int nr_gmu_freqs; - unsigned long gmu_freqs[4]; - u32 cx_arc_votes[4]; + unsigned long gmu_freqs[GMU_MAX_CX_FREQS]; + u32 cx_arc_votes[GMU_MAX_CX_FREQS]; unsigned long freq; @@ -193,7 +210,7 @@ void a6xx_hfi_init(struct a6xx_gmu *gmu); int a6xx_hfi_start(struct a6xx_gmu *gmu, int boot_state); void a6xx_hfi_stop(struct a6xx_gmu *gmu); int a6xx_hfi_send_prep_slumber(struct a6xx_gmu *gmu); -int a6xx_hfi_set_freq(struct a6xx_gmu *gmu, int index); +int a6xx_hfi_set_freq(struct a6xx_gmu *gmu, u32 perf_index, u32 bw_index); bool a6xx_gmu_gx_is_on(struct a6xx_gmu *gmu); bool a6xx_gmu_sptprac_is_on(struct a6xx_gmu *gmu); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index 019610341df1..491fde0083a2 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -130,6 +130,20 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu, OUT_RING(ring, lower_32_bits(rbmemptr(ring, fence))); OUT_RING(ring, upper_32_bits(rbmemptr(ring, fence))); OUT_RING(ring, submit->seqno - 1); + + OUT_PKT7(ring, CP_THREAD_CONTROL, 1); + OUT_RING(ring, CP_SET_THREAD_BOTH); + + /* Reset state used to synchronize BR and BV */ + OUT_PKT7(ring, CP_RESET_CONTEXT_STATE, 1); + OUT_RING(ring, + CP_RESET_CONTEXT_STATE_0_CLEAR_ON_CHIP_TS | + CP_RESET_CONTEXT_STATE_0_CLEAR_RESOURCE_TABLE | + CP_RESET_CONTEXT_STATE_0_CLEAR_BV_BR_COUNTER | + CP_RESET_CONTEXT_STATE_0_RESET_GLOBAL_LOCAL_TS); + + OUT_PKT7(ring, CP_THREAD_CONTROL, 1); + OUT_RING(ring, CP_SET_THREAD_BR); } if (!sysprof) { @@ -212,6 +226,8 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) struct msm_ringbuffer *ring = submit->ring; unsigned int i, ibs = 0; + adreno_check_and_reenable_stall(adreno_gpu); + a6xx_set_pagetable(a6xx_gpu, ring, submit); get_stats_counter(ring, REG_A6XX_RBBM_PERFCTR_CP(0), @@ -242,10 +258,10 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) break; fallthrough; case MSM_SUBMIT_CMD_BUF: - OUT_PKT7(ring, CP_INDIRECT_BUFFER_PFE, 3); + OUT_PKT7(ring, CP_INDIRECT_BUFFER, 3); OUT_RING(ring, lower_32_bits(submit->cmd[i].iova)); OUT_RING(ring, upper_32_bits(submit->cmd[i].iova)); - OUT_RING(ring, submit->cmd[i].size); + OUT_RING(ring, A5XX_CP_INDIRECT_BUFFER_2_IB_SIZE(submit->cmd[i].size)); ibs++; break; } @@ -335,6 +351,8 @@ static void a7xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) struct msm_ringbuffer *ring = submit->ring; unsigned int i, ibs = 0; + adreno_check_and_reenable_stall(adreno_gpu); + /* * Toggle concurrent binning for pagetable switch and set the thread to * BR since only it can execute the pagetable switch packets. @@ -377,10 +395,10 @@ static void a7xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) break; fallthrough; case MSM_SUBMIT_CMD_BUF: - OUT_PKT7(ring, CP_INDIRECT_BUFFER_PFE, 3); + OUT_PKT7(ring, CP_INDIRECT_BUFFER, 3); OUT_RING(ring, lower_32_bits(submit->cmd[i].iova)); OUT_RING(ring, upper_32_bits(submit->cmd[i].iova)); - OUT_RING(ring, submit->cmd[i].size); + OUT_RING(ring, A5XX_CP_INDIRECT_BUFFER_2_IB_SIZE(submit->cmd[i].size)); ibs++; break; } @@ -616,6 +634,14 @@ static void a6xx_calc_ubwc_config(struct adreno_gpu *gpu) gpu->ubwc_config.uavflagprd_inv = 2; } + if (adreno_is_a623(gpu)) { + gpu->ubwc_config.highest_bank_bit = 16; + gpu->ubwc_config.amsbc = 1; + gpu->ubwc_config.rgb565_predicator = 1; + gpu->ubwc_config.uavflagprd_inv = 2; + gpu->ubwc_config.macrotile_mode = 1; + } + if (adreno_is_a640_family(gpu)) gpu->ubwc_config.amsbc = 1; @@ -647,7 +673,6 @@ static void a6xx_calc_ubwc_config(struct adreno_gpu *gpu) if (adreno_is_7c3(gpu)) { gpu->ubwc_config.highest_bank_bit = 14; gpu->ubwc_config.amsbc = 1; - gpu->ubwc_config.rgb565_predicator = 1; gpu->ubwc_config.uavflagprd_inv = 2; gpu->ubwc_config.macrotile_mode = 1; } @@ -1123,12 +1148,12 @@ static int hw_init(struct msm_gpu *gpu) /* Disable L2 bypass in the UCHE */ if (adreno_is_a7xx(adreno_gpu)) { - gpu_write64(gpu, REG_A6XX_UCHE_TRAP_BASE, 0x0001fffffffff000llu); - gpu_write64(gpu, REG_A6XX_UCHE_WRITE_THRU_BASE, 0x0001fffffffff000llu); + gpu_write64(gpu, REG_A6XX_UCHE_TRAP_BASE, adreno_gpu->uche_trap_base); + gpu_write64(gpu, REG_A6XX_UCHE_WRITE_THRU_BASE, adreno_gpu->uche_trap_base); } else { - gpu_write64(gpu, REG_A6XX_UCHE_WRITE_RANGE_MAX, 0x0001ffffffffffc0llu); - gpu_write64(gpu, REG_A6XX_UCHE_TRAP_BASE, 0x0001fffffffff000llu); - gpu_write64(gpu, REG_A6XX_UCHE_WRITE_THRU_BASE, 0x0001fffffffff000llu); + gpu_write64(gpu, REG_A6XX_UCHE_WRITE_RANGE_MAX, adreno_gpu->uche_trap_base + 0xfc0); + gpu_write64(gpu, REG_A6XX_UCHE_TRAP_BASE, adreno_gpu->uche_trap_base); + gpu_write64(gpu, REG_A6XX_UCHE_WRITE_THRU_BASE, adreno_gpu->uche_trap_base); } if (!(adreno_is_a650_family(adreno_gpu) || @@ -1698,7 +1723,7 @@ static void a6xx_fault_detect_irq(struct msm_gpu *gpu) gpu_read(gpu, REG_A6XX_CP_IB2_REM_SIZE)); /* Turn off the hangcheck timer to keep it from bothering us */ - del_timer(&gpu->hangcheck_timer); + timer_delete(&gpu->hangcheck_timer); kthread_queue_work(gpu->worker, &gpu->recover_work); } @@ -1718,7 +1743,7 @@ static void a7xx_sw_fuse_violation_irq(struct msm_gpu *gpu) */ if (status & (A7XX_CX_MISC_SW_FUSE_VALUE_RAYTRACING | A7XX_CX_MISC_SW_FUSE_VALUE_LPAC)) { - del_timer(&gpu->hangcheck_timer); + timer_delete(&gpu->hangcheck_timer); kthread_queue_work(gpu->worker, &gpu->recover_work); } @@ -2260,7 +2285,7 @@ a6xx_create_private_address_space(struct msm_gpu *gpu) return ERR_CAST(mmu); return msm_gem_address_space_create(mmu, - "gpu", 0x100000000ULL, + "gpu", ADRENO_VM_START, adreno_private_address_space_size(gpu)); } @@ -2533,6 +2558,8 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev) } } + adreno_gpu->uche_trap_base = 0x1fffffffff000ull; + if (gpu->aspace) msm_mmu_set_fault_handler(gpu->aspace->mmu, gpu, a6xx_fault_handler); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h index 4aceffb6aae8..6e71f617fc3d 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h @@ -6,6 +6,10 @@ #include "adreno_gpu.h" +#include "a6xx_enums.xml.h" +#include "a7xx_enums.xml.h" +#include "a6xx_perfcntrs.xml.h" +#include "a7xx_perfcntrs.xml.h" #include "a6xx.xml.h" #include "a6xx_gmu.h" @@ -44,6 +48,7 @@ struct a6xx_info { u32 gmu_chipid; u32 gmu_cgc_mode; u32 prim_fifo_threshold; + const struct a6xx_bcm *bcms; }; struct a6xx_gpu { diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c index 0fcae53c0b14..a85d3df7a5fa 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c @@ -158,7 +158,7 @@ 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, dumper->iova); + gpu_write64(gpu, REG_A6XX_CP_CRASH_DUMP_SCRIPT_BASE, dumper->iova); gpu_write(gpu, REG_A6XX_CP_CRASH_DUMP_CNTL, 1); @@ -1214,12 +1214,12 @@ static void a6xx_get_gmu_registers(struct msm_gpu *gpu, struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); a6xx_state->gmu_registers = state_kcalloc(a6xx_state, - 3, sizeof(*a6xx_state->gmu_registers)); + 4, sizeof(*a6xx_state->gmu_registers)); if (!a6xx_state->gmu_registers) return; - a6xx_state->nr_gmu_registers = 3; + a6xx_state->nr_gmu_registers = 4; /* Get the CX GMU registers from AHB */ _a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gmu_reglist[0], @@ -1227,6 +1227,13 @@ static void a6xx_get_gmu_registers(struct msm_gpu *gpu, _a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gmu_reglist[1], &a6xx_state->gmu_registers[1], true); + if (adreno_is_a621(adreno_gpu) || adreno_is_a623(adreno_gpu)) + _a6xx_get_gmu_registers(gpu, a6xx_state, &a621_gpucc_reg, + &a6xx_state->gmu_registers[2], false); + else + _a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gpucc_reg, + &a6xx_state->gmu_registers[2], false); + if (!a6xx_gmu_gx_is_on(&a6xx_gpu->gmu)) return; @@ -1234,7 +1241,7 @@ static void a6xx_get_gmu_registers(struct msm_gpu *gpu, gpu_write(gpu, REG_A6XX_GMU_AO_AHB_FENCE_CTRL, 0); _a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gmu_reglist[2], - &a6xx_state->gmu_registers[2], false); + &a6xx_state->gmu_registers[3], false); } static struct msm_gpu_state_bo *a6xx_snapshot_gmu_bo( @@ -1507,6 +1514,8 @@ static void a6xx_get_indexed_registers(struct msm_gpu *gpu, /* Restore the size in the hardware */ gpu_write(gpu, REG_A6XX_CP_MEM_POOL_SIZE, mempool_size); + + a6xx_state->nr_indexed_regs = count; } static void a7xx_get_indexed_registers(struct msm_gpu *gpu, diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h index dd4c28a8d923..95d93ac6812a 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h @@ -212,7 +212,7 @@ static const struct a6xx_shader_block { SHADER(A6XX_SP_LB_5_DATA, 0x200), SHADER(A6XX_SP_CB_BINDLESS_DATA, 0x800), SHADER(A6XX_SP_CB_LEGACY_DATA, 0x280), - SHADER(A6XX_SP_UAV_DATA, 0x80), + SHADER(A6XX_SP_GFX_UAV_BASE_DATA, 0x80), SHADER(A6XX_SP_INST_TAG, 0x80), SHADER(A6XX_SP_CB_BINDLESS_TAG, 0x80), SHADER(A6XX_SP_TMO_UMO_TAG, 0x80), @@ -363,6 +363,9 @@ static const u32 a6xx_gmu_cx_registers[] = { 0x51e0, 0x51e2, 0x51f0, 0x51f0, 0x5200, 0x5201, /* GMU AO */ 0x9300, 0x9316, 0x9400, 0x9400, +}; + +static const u32 a6xx_gmu_gpucc_registers[] = { /* GPU CC */ 0x9800, 0x9812, 0x9840, 0x9852, 0x9c00, 0x9c04, 0x9c07, 0x9c0b, 0x9c15, 0x9c1c, 0x9c1e, 0x9c2d, 0x9c3c, 0x9c3d, 0x9c3f, 0x9c40, @@ -373,6 +376,17 @@ static const u32 a6xx_gmu_cx_registers[] = { 0xbc00, 0xbc16, 0xbc20, 0xbc27, }; +static const u32 a621_gmu_gpucc_registers[] = { + /* GPU CC */ + 0x9800, 0x980e, 0x9c00, 0x9c0e, 0xb000, 0xb004, 0xb400, 0xb404, + 0xb800, 0xb804, 0xbc00, 0xbc05, 0xbc14, 0xbc1d, 0xbc2a, 0xbc30, + 0xbc32, 0xbc32, 0xbc41, 0xbc55, 0xbc66, 0xbc68, 0xbc78, 0xbc7a, + 0xbc89, 0xbc8a, 0xbc9c, 0xbc9e, 0xbca0, 0xbca3, 0xbcb3, 0xbcb5, + 0xbcc5, 0xbcc7, 0xbcd6, 0xbcd8, 0xbce8, 0xbce9, 0xbcf9, 0xbcfc, + 0xbd0b, 0xbd0c, 0xbd1c, 0xbd1e, 0xbd40, 0xbd70, 0xbe00, 0xbe16, + 0xbe20, 0xbe2d, +}; + static const u32 a6xx_gmu_cx_rscc_registers[] = { /* GPU RSCC */ 0x008c, 0x008c, 0x0101, 0x0102, 0x0340, 0x0342, 0x0344, 0x0347, @@ -386,6 +400,9 @@ static const struct a6xx_registers a6xx_gmu_reglist[] = { REGS(a6xx_gmu_gx_registers, 0, 0), }; +static const struct a6xx_registers a6xx_gpucc_reg = REGS(a6xx_gmu_gpucc_registers, 0, 0); +static const struct a6xx_registers a621_gpucc_reg = REGS(a621_gmu_gpucc_registers, 0, 0); + static u32 a6xx_get_cp_roq_size(struct msm_gpu *gpu); static u32 a7xx_get_cp_roq_size(struct msm_gpu *gpu); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c index cb8844ed46b2..8e69b1e84657 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c @@ -6,6 +6,7 @@ #include <linux/list.h> #include <soc/qcom/cmd-db.h> +#include <soc/qcom/tcs.h> #include "a6xx_gmu.h" #include "a6xx_gmu.xml.h" @@ -99,16 +100,14 @@ static int a6xx_hfi_queue_write(struct a6xx_gmu *gmu, return 0; } -static int a6xx_hfi_wait_for_ack(struct a6xx_gmu *gmu, u32 id, u32 seqnum, - u32 *payload, u32 payload_size) +static int a6xx_hfi_wait_for_msg_interrupt(struct a6xx_gmu *gmu, u32 id, u32 seqnum) { - struct a6xx_hfi_queue *queue = &gmu->queues[HFI_RESPONSE_QUEUE]; - u32 val; int ret; + u32 val; /* Wait for a response */ ret = gmu_poll_timeout(gmu, REG_A6XX_GMU_GMU2HOST_INTR_INFO, val, - val & A6XX_GMU_GMU2HOST_INTR_INFO_MSGQ, 100, 5000); + val & A6XX_GMU_GMU2HOST_INTR_INFO_MSGQ, 100, 1000000); if (ret) { DRM_DEV_ERROR(gmu->dev, @@ -121,6 +120,19 @@ static int a6xx_hfi_wait_for_ack(struct a6xx_gmu *gmu, u32 id, u32 seqnum, gmu_write(gmu, REG_A6XX_GMU_GMU2HOST_INTR_CLR, A6XX_GMU_GMU2HOST_INTR_INFO_MSGQ); + return 0; +} + +static int a6xx_hfi_wait_for_ack(struct a6xx_gmu *gmu, u32 id, u32 seqnum, + u32 *payload, u32 payload_size) +{ + struct a6xx_hfi_queue *queue = &gmu->queues[HFI_RESPONSE_QUEUE]; + int ret; + + ret = a6xx_hfi_wait_for_msg_interrupt(gmu, id, seqnum); + if (ret) + return ret; + for (;;) { struct a6xx_hfi_msg_response resp; @@ -128,12 +140,18 @@ static int a6xx_hfi_wait_for_ack(struct a6xx_gmu *gmu, u32 id, u32 seqnum, ret = a6xx_hfi_queue_read(gmu, queue, (u32 *) &resp, sizeof(resp) >> 2); - /* If the queue is empty our response never made it */ + /* If the queue is empty, there may have been previous missed + * responses that preceded the response to our packet. Wait + * further before we give up. + */ if (!ret) { - DRM_DEV_ERROR(gmu->dev, - "The HFI response queue is unexpectedly empty\n"); - - return -ENOENT; + ret = a6xx_hfi_wait_for_msg_interrupt(gmu, id, seqnum); + if (ret) { + DRM_DEV_ERROR(gmu->dev, + "The HFI response queue is unexpectedly empty\n"); + return ret; + } + continue; } if (HFI_HEADER_ID(resp.header) == HFI_F2H_MSG_ERROR) { @@ -259,6 +277,48 @@ static int a6xx_hfi_send_perf_table(struct a6xx_gmu *gmu) NULL, 0); } +static void a6xx_generate_bw_table(const struct a6xx_info *info, struct a6xx_gmu *gmu, + struct a6xx_hfi_msg_bw_table *msg) +{ + unsigned int i, j; + + for (i = 0; i < GMU_MAX_BCMS; i++) { + if (!info->bcms[i].name) + break; + msg->ddr_cmds_addrs[i] = cmd_db_read_addr(info->bcms[i].name); + } + msg->ddr_cmds_num = i; + + for (i = 0; i < gmu->nr_gpu_bws; ++i) + for (j = 0; j < msg->ddr_cmds_num; j++) + msg->ddr_cmds_data[i][j] = gmu->gpu_ib_votes[i][j]; + msg->bw_level_num = gmu->nr_gpu_bws; + + /* Compute the wait bitmask with each BCM having the commit bit */ + msg->ddr_wait_bitmask = 0; + for (j = 0; j < msg->ddr_cmds_num; j++) + if (msg->ddr_cmds_data[0][j] & BCM_TCS_CMD_COMMIT_MASK) + msg->ddr_wait_bitmask |= BIT(j); + + /* + * These are the CX (CNOC) votes - these are used by the GMU + * The 'CN0' BCM is used on all targets, and votes are basically + * 'off' and 'on' states with first bit to enable the path. + */ + + msg->cnoc_cmds_addrs[0] = cmd_db_read_addr("CN0"); + msg->cnoc_cmds_num = 1; + + msg->cnoc_cmds_data[0][0] = BCM_TCS_CMD(true, false, 0, 0); + msg->cnoc_cmds_data[1][0] = BCM_TCS_CMD(true, true, 0, BIT(0)); + + /* Compute the wait bitmask with each BCM having the commit bit */ + msg->cnoc_wait_bitmask = 0; + for (j = 0; j < msg->cnoc_cmds_num; j++) + if (msg->cnoc_cmds_data[0][j] & BCM_TCS_CMD_COMMIT_MASK) + msg->cnoc_wait_bitmask |= BIT(j); +} + static void a618_build_bw_table(struct a6xx_hfi_msg_bw_table *msg) { /* Send a single "off" entry since the 618 GMU doesn't do bus scaling */ @@ -664,6 +724,7 @@ static int a6xx_hfi_send_bw_table(struct a6xx_gmu *gmu) struct a6xx_hfi_msg_bw_table *msg; struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; + const struct a6xx_info *info = adreno_gpu->info->a6xx; if (gmu->bw_table) goto send; @@ -672,7 +733,9 @@ static int a6xx_hfi_send_bw_table(struct a6xx_gmu *gmu) if (!msg) return -ENOMEM; - if (adreno_is_a618(adreno_gpu)) + if (info->bcms && gmu->nr_gpu_bws > 1) + a6xx_generate_bw_table(info, gmu, msg); + else if (adreno_is_a618(adreno_gpu)) a618_build_bw_table(msg); else if (adreno_is_a619(adreno_gpu)) a619_build_bw_table(msg); @@ -702,6 +765,38 @@ send: NULL, 0); } +#define HFI_FEATURE_ACD 12 + +static int a6xx_hfi_enable_acd(struct a6xx_gmu *gmu) +{ + struct a6xx_hfi_acd_table *acd_table = &gmu->acd_table; + struct a6xx_hfi_msg_feature_ctrl msg = { + .feature = HFI_FEATURE_ACD, + .enable = 1, + .data = 0, + }; + int ret; + + if (!acd_table->enable_by_level) + return 0; + + /* Enable ACD feature at GMU */ + ret = a6xx_hfi_send_msg(gmu, HFI_H2F_FEATURE_CTRL, &msg, sizeof(msg), NULL, 0); + if (ret) { + DRM_DEV_ERROR(gmu->dev, "Unable to enable ACD (%d)\n", ret); + return ret; + } + + /* Send ACD table to GMU */ + ret = a6xx_hfi_send_msg(gmu, HFI_H2F_MSG_ACD, acd_table, sizeof(*acd_table), NULL, 0); + if (ret) { + DRM_DEV_ERROR(gmu->dev, "Unable to ACD table (%d)\n", ret); + return ret; + } + + return 0; +} + static int a6xx_hfi_send_test(struct a6xx_gmu *gmu) { struct a6xx_hfi_msg_test msg = { 0 }; @@ -726,13 +821,13 @@ static int a6xx_hfi_send_core_fw_start(struct a6xx_gmu *gmu) sizeof(msg), NULL, 0); } -int a6xx_hfi_set_freq(struct a6xx_gmu *gmu, int index) +int a6xx_hfi_set_freq(struct a6xx_gmu *gmu, u32 freq_index, u32 bw_index) { struct a6xx_hfi_gx_bw_perf_vote_cmd msg = { 0 }; msg.ack_type = 1; /* blocking */ - msg.freq = index; - msg.bw = 0; /* TODO: bus scaling */ + msg.freq = freq_index; + msg.bw = bw_index; return a6xx_hfi_send_msg(gmu, HFI_H2F_MSG_GX_BW_PERF_VOTE, &msg, sizeof(msg), NULL, 0); @@ -799,6 +894,10 @@ int a6xx_hfi_start(struct a6xx_gmu *gmu, int boot_state) if (ret) return ret; + ret = a6xx_hfi_enable_acd(gmu); + if (ret) + return ret; + ret = a6xx_hfi_send_core_fw_start(gmu); if (ret) return ret; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.h b/drivers/gpu/drm/msm/adreno/a6xx_hfi.h index 528110169398..653ef720e2da 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.h @@ -151,12 +151,33 @@ struct a6xx_hfi_msg_test { u32 header; }; +#define HFI_H2F_MSG_ACD 7 +#define MAX_ACD_STRIDE 2 + +struct a6xx_hfi_acd_table { + u32 header; + u32 version; + u32 enable_by_level; + u32 stride; + u32 num_levels; + u32 data[16 * MAX_ACD_STRIDE]; +}; + #define HFI_H2F_MSG_START 10 struct a6xx_hfi_msg_start { u32 header; }; +#define HFI_H2F_FEATURE_CTRL 11 + +struct a6xx_hfi_msg_feature_ctrl { + u32 header; + u32 feature; + u32 enable; + u32 data; +}; + #define HFI_H2F_MSG_CORE_FW_START 14 struct a6xx_hfi_msg_core_fw_start { @@ -173,6 +194,11 @@ struct a6xx_hfi_gx_bw_perf_vote_cmd { u32 bw; }; +#define AB_VOTE_MASK GENMASK(31, 16) +#define MAX_AB_VOTE (FIELD_MAX(AB_VOTE_MASK) - 1) +#define AB_VOTE(vote) FIELD_PREP(AB_VOTE_MASK, (vote)) +#define AB_VOTE_ENABLE BIT(8) + #define HFI_H2F_MSG_PREPARE_SLUMBER 33 struct a6xx_hfi_prep_slumber_cmd { diff --git a/drivers/gpu/drm/msm/adreno/a6xx_preempt.c b/drivers/gpu/drm/msm/adreno/a6xx_preempt.c index 2fd4e39f618f..e6084e6999eb 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_preempt.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_preempt.c @@ -87,7 +87,8 @@ static struct msm_ringbuffer *get_next_ring(struct msm_gpu *gpu) static void a6xx_preempt_timer(struct timer_list *t) { - struct a6xx_gpu *a6xx_gpu = from_timer(a6xx_gpu, t, preempt_timer); + struct a6xx_gpu *a6xx_gpu = timer_container_of(a6xx_gpu, t, + preempt_timer); struct msm_gpu *gpu = &a6xx_gpu->base.base; struct drm_device *dev = gpu->dev; @@ -146,7 +147,7 @@ void a6xx_preempt_irq(struct msm_gpu *gpu) return; /* Delete the preemption watchdog timer */ - del_timer(&a6xx_gpu->preempt_timer); + timer_delete(&a6xx_gpu->preempt_timer); /* * The hardware should be setting the stop bit of CP_CONTEXT_SWITCH_CNTL @@ -209,7 +210,7 @@ void a6xx_preempt_hw_init(struct msm_gpu *gpu) gpu_write64(gpu, REG_A6XX_CP_CONTEXT_SWITCH_SMMU_INFO, 0); /* Enable the GMEM save/restore feature for preemption */ - gpu_write(gpu, REG_A6XX_RB_CONTEXT_SWITCH_GMEM_SAVE_RESTORE, 0x1); + gpu_write(gpu, REG_A6XX_RB_CONTEXT_SWITCH_GMEM_SAVE_RESTORE_ENABLE, 0x1); /* Reset the preemption state */ set_preempt_state(a6xx_gpu, PREEMPT_NONE); diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c index 236b25c094cd..16e7ac444efd 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_device.c +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c @@ -24,6 +24,10 @@ int enable_preemption = -1; MODULE_PARM_DESC(enable_preemption, "Enable preemption (A7xx only) (1=on , 0=disable, -1=auto (default))"); module_param(enable_preemption, int, 0600); +bool disable_acd; +MODULE_PARM_DESC(disable_acd, "Forcefully disable GPU ACD"); +module_param_unsafe(disable_acd, bool, 0400); + extern const struct adreno_gpulist a2xx_gpulist; extern const struct adreno_gpulist a3xx_gpulist; extern const struct adreno_gpulist a4xx_gpulist; @@ -133,9 +137,8 @@ err_disable_rpm: return NULL; } -static int find_chipid(struct device *dev, uint32_t *chipid) +static int find_chipid(struct device_node *node, uint32_t *chipid) { - struct device_node *node = dev->of_node; const char *compat; int ret; @@ -169,15 +172,36 @@ static int find_chipid(struct device *dev, uint32_t *chipid) /* and if that fails, fall back to legacy "qcom,chipid" property: */ ret = of_property_read_u32(node, "qcom,chipid", chipid); if (ret) { - DRM_DEV_ERROR(dev, "could not parse qcom,chipid: %d\n", ret); + DRM_ERROR("%pOF: could not parse qcom,chipid: %d\n", + node, ret); return ret; } - dev_warn(dev, "Using legacy qcom,chipid binding!\n"); + pr_warn("%pOF: Using legacy qcom,chipid binding!\n", node); return 0; } +bool adreno_has_gpu(struct device_node *node) +{ + const struct adreno_info *info; + uint32_t chip_id; + int ret; + + ret = find_chipid(node, &chip_id); + if (ret) + return false; + + info = adreno_info(chip_id); + if (!info) { + pr_warn("%pOF: Unknown GPU revision: %"ADRENO_CHIPID_FMT"\n", + node, ADRENO_CHIPID_ARGS(chip_id)); + return false; + } + + return true; +} + static int adreno_bind(struct device *dev, struct device *master, void *data) { static struct adreno_platform_config config = {}; @@ -187,19 +211,18 @@ static int adreno_bind(struct device *dev, struct device *master, void *data) struct msm_gpu *gpu; int ret; - ret = find_chipid(dev, &config.chip_id); - if (ret) + ret = find_chipid(dev->of_node, &config.chip_id); + /* We shouldn't have gotten this far if we can't parse the chip_id */ + if (WARN_ON(ret)) return ret; dev->platform_data = &config; priv->gpu_pdev = to_platform_device(dev); info = adreno_info(config.chip_id); - if (!info) { - dev_warn(drm->dev, "Unknown GPU revision: %"ADRENO_CHIPID_FMT"\n", - ADRENO_CHIPID_ARGS(config.chip_id)); + /* We shouldn't have gotten this far if we don't recognize the GPU: */ + if (WARN_ON(!info)) return -ENXIO; - } config.info = info; diff --git a/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h b/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h index 9a327d543f27..e02cabb39f19 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h @@ -1311,8 +1311,8 @@ static struct a6xx_indexed_registers gen7_9_0_cp_indexed_reg_list[] = { REG_A7XX_CP_BV_SQE_UCODE_DBG_DATA, 0x08000}, { "CP_BV_SQE_STAT_ADDR", REG_A7XX_CP_BV_SQE_STAT_ADDR, REG_A7XX_CP_BV_SQE_STAT_DATA, 0x00040}, - { "CP_RESOURCE_TBL", REG_A7XX_CP_RESOURCE_TBL_DBG_ADDR, - REG_A7XX_CP_RESOURCE_TBL_DBG_DATA, 0x04100}, + { "CP_RESOURCE_TBL", REG_A7XX_CP_RESOURCE_TABLE_DBG_ADDR, + REG_A7XX_CP_RESOURCE_TABLE_DBG_DATA, 0x04100}, { "CP_LPAC_DRAW_STATE_ADDR", REG_A7XX_CP_LPAC_DRAW_STATE_ADDR, REG_A7XX_CP_LPAC_DRAW_STATE_DATA, 0x00200}, { "CP_LPAC_ROQ", REG_A7XX_CP_LPAC_ROQ_DBG_ADDR, diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index 75f5367e73ca..86bff915c3e7 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -236,34 +236,77 @@ adreno_iommu_create_address_space(struct msm_gpu *gpu, u64 adreno_private_address_space_size(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(&gpu->pdev->dev); + const struct io_pgtable_cfg *ttbr1_cfg; if (address_space_size) return address_space_size; - if (adreno_gpu->info->address_space_size) - return adreno_gpu->info->address_space_size; + if (adreno_gpu->info->quirks & ADRENO_QUIRK_4GB_VA) + return SZ_4G; - return SZ_4G; + if (!adreno_smmu || !adreno_smmu->get_ttbr1_cfg) + return SZ_4G; + + ttbr1_cfg = adreno_smmu->get_ttbr1_cfg(adreno_smmu->cookie); + + /* + * Userspace VM is actually using TTBR0, but both are the same size, + * with b48 (sign bit) selecting which TTBRn to use. So if IAS is + * 48, the total (kernel+user) address space size is effectively + * 49 bits. But what userspace is control of is the lower 48. + */ + return BIT(ttbr1_cfg->ias) - ADRENO_VM_START; +} + +void adreno_check_and_reenable_stall(struct adreno_gpu *adreno_gpu) +{ + struct msm_gpu *gpu = &adreno_gpu->base; + struct msm_drm_private *priv = gpu->dev->dev_private; + unsigned long flags; + + /* + * Wait until the cooldown period has passed and we would actually + * collect a crashdump to re-enable stall-on-fault. + */ + spin_lock_irqsave(&priv->fault_stall_lock, flags); + if (!priv->stall_enabled && + ktime_after(ktime_get(), priv->stall_reenable_time) && + !READ_ONCE(gpu->crashstate)) { + priv->stall_enabled = true; + + gpu->aspace->mmu->funcs->set_stall(gpu->aspace->mmu, true); + } + spin_unlock_irqrestore(&priv->fault_stall_lock, flags); } #define ARM_SMMU_FSR_TF BIT(1) #define ARM_SMMU_FSR_PF BIT(3) #define ARM_SMMU_FSR_EF BIT(4) +#define ARM_SMMU_FSR_SS BIT(30) int adreno_fault_handler(struct msm_gpu *gpu, unsigned long iova, int flags, struct adreno_smmu_fault_info *info, const char *block, u32 scratch[4]) { + struct msm_drm_private *priv = gpu->dev->dev_private; const char *type = "UNKNOWN"; - bool do_devcoredump = info && !READ_ONCE(gpu->crashstate); + bool do_devcoredump = info && (info->fsr & ARM_SMMU_FSR_SS) && + !READ_ONCE(gpu->crashstate); + unsigned long irq_flags; /* - * If we aren't going to be resuming later from fault_worker, then do - * it now. + * In case there is a subsequent storm of pagefaults, disable + * stall-on-fault for at least half a second. */ - if (!do_devcoredump) { - gpu->aspace->mmu->funcs->resume_translation(gpu->aspace->mmu); + spin_lock_irqsave(&priv->fault_stall_lock, irq_flags); + if (priv->stall_enabled) { + priv->stall_enabled = false; + + gpu->aspace->mmu->funcs->set_stall(gpu->aspace->mmu, false); } + priv->stall_reenable_time = ktime_add_ms(ktime_get(), 500); + spin_unlock_irqrestore(&priv->fault_stall_lock, irq_flags); /* * Print a default message if we couldn't get the data from the @@ -291,16 +334,18 @@ int adreno_fault_handler(struct msm_gpu *gpu, unsigned long iova, int flags, scratch[0], scratch[1], scratch[2], scratch[3]); if (do_devcoredump) { + struct msm_gpu_fault_info fault_info = {}; + /* Turn off the hangcheck timer to keep it from bothering us */ - del_timer(&gpu->hangcheck_timer); + timer_delete(&gpu->hangcheck_timer); - gpu->fault_info.ttbr0 = info->ttbr0; - gpu->fault_info.iova = iova; - gpu->fault_info.flags = flags; - gpu->fault_info.type = type; - gpu->fault_info.block = block; + fault_info.ttbr0 = info->ttbr0; + fault_info.iova = iova; + fault_info.flags = flags; + fault_info.type = type; + fault_info.block = block; - kthread_queue_work(gpu->worker, &gpu->fault_work); + msm_gpu_fault_crashstate_capture(gpu, &fault_info); } return 0; @@ -310,10 +355,11 @@ int adreno_get_param(struct msm_gpu *gpu, struct msm_file_private *ctx, uint32_t param, uint64_t *value, uint32_t *len) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct drm_device *drm = gpu->dev; /* No pointer params yet */ if (*len != 0) - return -EINVAL; + return UERR(EINVAL, drm, "invalid len"); switch (param) { case MSM_PARAM_GPU_ID: @@ -365,12 +411,12 @@ int adreno_get_param(struct msm_gpu *gpu, struct msm_file_private *ctx, return 0; case MSM_PARAM_VA_START: if (ctx->aspace == gpu->aspace) - return -EINVAL; + return UERR(EINVAL, drm, "requires per-process pgtables"); *value = ctx->aspace->va_start; return 0; case MSM_PARAM_VA_SIZE: if (ctx->aspace == gpu->aspace) - return -EINVAL; + return UERR(EINVAL, drm, "requires per-process pgtables"); *value = ctx->aspace->va_size; return 0; case MSM_PARAM_HIGHEST_BANK_BIT: @@ -385,15 +431,19 @@ int adreno_get_param(struct msm_gpu *gpu, struct msm_file_private *ctx, case MSM_PARAM_MACROTILE_MODE: *value = adreno_gpu->ubwc_config.macrotile_mode; return 0; + case MSM_PARAM_UCHE_TRAP_BASE: + *value = adreno_gpu->uche_trap_base; + return 0; default: - DBG("%s: invalid param: %u", gpu->name, param); - return -EINVAL; + return UERR(EINVAL, drm, "%s: invalid param: %u", gpu->name, param); } } int adreno_set_param(struct msm_gpu *gpu, struct msm_file_private *ctx, uint32_t param, uint64_t value, uint32_t len) { + struct drm_device *drm = gpu->dev; + switch (param) { case MSM_PARAM_COMM: case MSM_PARAM_CMDLINE: @@ -401,11 +451,11 @@ int adreno_set_param(struct msm_gpu *gpu, struct msm_file_private *ctx, * that should be a reasonable upper bound */ if (len > PAGE_SIZE) - return -EINVAL; + return UERR(EINVAL, drm, "invalid len"); break; default: if (len != 0) - return -EINVAL; + return UERR(EINVAL, drm, "invalid len"); } switch (param) { @@ -434,11 +484,10 @@ int adreno_set_param(struct msm_gpu *gpu, struct msm_file_private *ctx, } case MSM_PARAM_SYSPROF: if (!capable(CAP_SYS_ADMIN)) - return -EPERM; + return UERR(EPERM, drm, "invalid permissions"); return msm_file_private_set_sysprof(ctx, gpu, value); default: - DBG("%s: invalid param: %u", gpu->name, param); - return -EINVAL; + return UERR(EINVAL, drm, "%s: invalid param: %u", gpu->name, param); } } @@ -879,6 +928,16 @@ void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state, drm_printf(p, " - dir=%s\n", info->flags & IOMMU_FAULT_WRITE ? "WRITE" : "READ"); drm_printf(p, " - type=%s\n", info->type); drm_printf(p, " - source=%s\n", info->block); + + /* Information extracted from what we think are the current + * pgtables. Hopefully the TTBR0 matches what we've extracted + * from the SMMU registers in smmu_info! + */ + drm_puts(p, "pgtable-fault-info:\n"); + drm_printf(p, " - ttbr0: %.16llx\n", (u64)info->pgtbl_ttbr0); + drm_printf(p, " - asid: %d\n", info->asid); + drm_printf(p, " - ptes: %.16llx %.16llx %.16llx %.16llx\n", + info->ptes[0], info->ptes[1], info->ptes[2], info->ptes[3]); } drm_printf(p, "rbbm-status: 0x%08x\n", state->rbbm_status); diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h index e71f420f8b3a..bc063594a359 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h @@ -57,6 +57,7 @@ enum adreno_family { #define ADRENO_QUIRK_HAS_HW_APRIV BIT(3) #define ADRENO_QUIRK_HAS_CACHED_COHERENT BIT(4) #define ADRENO_QUIRK_PREEMPTION BIT(5) +#define ADRENO_QUIRK_4GB_VA BIT(6) /* Helper for formating the chip_id in the way that userspace tools like * crashdec expect. @@ -104,7 +105,6 @@ struct adreno_info { union { const struct a6xx_info *a6xx; }; - u64 address_space_size; /** * @speedbins: Optional table of fuse to speedbin mappings * @@ -253,6 +253,8 @@ struct adreno_gpu { bool gmu_is_wrapper; bool has_ray_tracing; + + u64 uche_trap_base; }; #define to_adreno_gpu(x) container_of(x, struct adreno_gpu, base) @@ -440,6 +442,11 @@ static inline int adreno_is_a621(const struct adreno_gpu *gpu) return gpu->info->chip_ids[0] == 0x06020100; } +static inline int adreno_is_a623(const struct adreno_gpu *gpu) +{ + return gpu->info->chip_ids[0] == 0x06020300; +} + static inline int adreno_is_a630(const struct adreno_gpu *gpu) { return adreno_is_revn(gpu, 630); @@ -559,6 +566,11 @@ static inline int adreno_is_a740_family(struct adreno_gpu *gpu) gpu->info->family == ADRENO_7XX_GEN3; } +static inline int adreno_is_a750_family(struct adreno_gpu *gpu) +{ + return gpu->info->family == ADRENO_7XX_GEN3; +} + static inline int adreno_is_a7xx(struct adreno_gpu *gpu) { /* Update with non-fake (i.e. non-A702) Gen 7 GPUs */ @@ -566,6 +578,8 @@ static inline int adreno_is_a7xx(struct adreno_gpu *gpu) adreno_is_a740_family(gpu); } +/* Put vm_start above 32b to catch issues with not setting xyz_BASE_HI */ +#define ADRENO_VM_START 0x100000000ULL u64 adreno_private_address_space_size(struct msm_gpu *gpu); int adreno_get_param(struct msm_gpu *gpu, struct msm_file_private *ctx, uint32_t param, uint64_t *value, uint32_t *len); @@ -622,6 +636,8 @@ int adreno_fault_handler(struct msm_gpu *gpu, unsigned long iova, int flags, struct adreno_smmu_fault_info *info, const char *block, u32 scratch[4]); +void adreno_check_and_reenable_stall(struct adreno_gpu *gpu); + int adreno_read_speedbin(struct device *dev, u32 *speedbin); /* diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_10_0_sm8650.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_10_0_sm8650.h index e187e7b1cef1..ffc4d4257ae5 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_10_0_sm8650.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_10_0_sm8650.h @@ -27,17 +27,16 @@ static const struct dpu_mdp_cfg sm8650_mdp = { }, }; -/* FIXME: get rid of DPU_CTL_SPLIT_DISPLAY in favour of proper ACTIVE_CTL support */ static const struct dpu_ctl_cfg sm8650_ctl[] = { { .name = "ctl_0", .id = CTL_0, .base = 0x15000, .len = 0x1000, - .features = CTL_SM8550_MASK | BIT(DPU_CTL_SPLIT_DISPLAY), + .features = CTL_SM8550_MASK, .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 9), }, { .name = "ctl_1", .id = CTL_1, .base = 0x16000, .len = 0x1000, - .features = CTL_SM8550_MASK | BIT(DPU_CTL_SPLIT_DISPLAY), + .features = CTL_SM8550_MASK, .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 10), }, { .name = "ctl_2", .id = CTL_2, @@ -254,25 +253,25 @@ static const struct dpu_pingpong_cfg sm8650_pp[] = { .merge_3d = MERGE_3D_2, .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), }, { - .name = "pingpong_6", .id = PINGPONG_6, + .name = "pingpong_cwb_0", .id = PINGPONG_CWB_0, .base = 0x66000, .len = 0, .features = BIT(DPU_PINGPONG_DITHER), .sblk = &sc7280_pp_sblk, .merge_3d = MERGE_3D_3, }, { - .name = "pingpong_7", .id = PINGPONG_7, + .name = "pingpong_cwb_1", .id = PINGPONG_CWB_1, .base = 0x66400, .len = 0, .features = BIT(DPU_PINGPONG_DITHER), .sblk = &sc7280_pp_sblk, .merge_3d = MERGE_3D_3, }, { - .name = "pingpong_8", .id = PINGPONG_8, + .name = "pingpong_cwb_2", .id = PINGPONG_CWB_2, .base = 0x7e000, .len = 0, .features = BIT(DPU_PINGPONG_DITHER), .sblk = &sc7280_pp_sblk, .merge_3d = MERGE_3D_4, }, { - .name = "pingpong_9", .id = PINGPONG_9, + .name = "pingpong_cwb_3", .id = PINGPONG_CWB_3, .base = 0x7e400, .len = 0, .features = BIT(DPU_PINGPONG_DITHER), .sblk = &sc7280_pp_sblk, @@ -343,8 +342,8 @@ static const struct dpu_wb_cfg sm8650_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .xin_id = 6, .vbif_idx = VBIF_RT, .maxlinewidth = 4096, @@ -352,6 +351,25 @@ static const struct dpu_wb_cfg sm8650_wb[] = { }, }; +static const struct dpu_cwb_cfg sm8650_cwb[] = { + { + .name = "cwb_0", .id = CWB_0, + .base = 0x66200, .len = 0x8, + }, + { + .name = "cwb_1", .id = CWB_1, + .base = 0x66600, .len = 0x8, + }, + { + .name = "cwb_2", .id = CWB_2, + .base = 0x7E200, .len = 0x8, + }, + { + .name = "cwb_3", .id = CWB_3, + .base = 0x7E600, .len = 0x8, + }, +}; + static const struct dpu_intf_cfg sm8650_intf[] = { { .name = "intf_0", .id = INTF_0, @@ -433,6 +451,7 @@ const struct dpu_mdss_cfg dpu_sm8650_cfg = { .mdss_ver = &sm8650_mdss_ver, .caps = &sm8650_dpu_caps, .mdp = &sm8650_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sm8650_ctl), .ctl = sm8650_ctl, .sspp_count = ARRAY_SIZE(sm8650_sspp), @@ -449,6 +468,8 @@ const struct dpu_mdss_cfg dpu_sm8650_cfg = { .merge_3d = sm8650_merge_3d, .wb_count = ARRAY_SIZE(sm8650_wb), .wb = sm8650_wb, + .cwb_count = ARRAY_SIZE(sm8650_cwb), + .cwb = sm8650_cwb, .intf_count = ARRAY_SIZE(sm8650_intf), .intf = sm8650_intf, .vbif_count = ARRAY_SIZE(sm8650_vbif), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_14_msm8937.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_14_msm8937.h index ab3dfb0b374e..39027a21c6fe 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_14_msm8937.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_14_msm8937.h @@ -100,14 +100,12 @@ static const struct dpu_pingpong_cfg msm8937_pp[] = { { .name = "pingpong_0", .id = PINGPONG_0, .base = 0x70000, .len = 0xd4, - .features = PINGPONG_MSM8996_MASK, .sblk = &msm8996_pp_sblk, .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), .intr_rdptr = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12), }, { .name = "pingpong_1", .id = PINGPONG_1, .base = 0x70800, .len = 0xd4, - .features = PINGPONG_MSM8996_MASK, .sblk = &msm8996_pp_sblk, .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), .intr_rdptr = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13), @@ -132,7 +130,6 @@ static const struct dpu_intf_cfg msm8937_intf[] = { .prog_fetch_lines_worst_case = 14, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 26), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 27), - .intr_tear_rd_ptr = -1, }, { .name = "intf_2", .id = INTF_2, .base = 0x6b000, .len = 0x268, @@ -141,7 +138,6 @@ static const struct dpu_intf_cfg msm8937_intf[] = { .prog_fetch_lines_worst_case = 14, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 28), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 29), - .intr_tear_rd_ptr = -1, }, }; @@ -190,6 +186,7 @@ const struct dpu_mdss_cfg dpu_msm8937_cfg = { .mdss_ver = &msm8937_mdss_ver, .caps = &msm8937_dpu_caps, .mdp = msm8937_mdp, + .cdm = &dpu_cdm_1_x_4_x, .ctl_count = ARRAY_SIZE(msm8937_ctl), .ctl = msm8937_ctl, .sspp_count = ARRAY_SIZE(msm8937_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_15_msm8917.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_15_msm8917.h index 6bdaecca6761..8d1b43ea1663 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_15_msm8917.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_15_msm8917.h @@ -93,7 +93,6 @@ static const struct dpu_pingpong_cfg msm8917_pp[] = { { .name = "pingpong_0", .id = PINGPONG_0, .base = 0x70000, .len = 0xd4, - .features = PINGPONG_MSM8996_MASK, .sblk = &msm8996_pp_sblk, .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), .intr_rdptr = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12), @@ -118,7 +117,6 @@ static const struct dpu_intf_cfg msm8917_intf[] = { .prog_fetch_lines_worst_case = 14, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 26), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 27), - .intr_tear_rd_ptr = -1, }, }; @@ -167,6 +165,7 @@ const struct dpu_mdss_cfg dpu_msm8917_cfg = { .mdss_ver = &msm8917_mdss_ver, .caps = &msm8917_dpu_caps, .mdp = msm8917_mdp, + .cdm = &dpu_cdm_1_x_4_x, .ctl_count = ARRAY_SIZE(msm8917_ctl), .ctl = msm8917_ctl, .sspp_count = ARRAY_SIZE(msm8917_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_16_msm8953.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_16_msm8953.h index 14f36ea6ad0e..16c12499b24b 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_16_msm8953.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_16_msm8953.h @@ -100,14 +100,12 @@ static const struct dpu_pingpong_cfg msm8953_pp[] = { { .name = "pingpong_0", .id = PINGPONG_0, .base = 0x70000, .len = 0xd4, - .features = PINGPONG_MSM8996_MASK, .sblk = &msm8996_pp_sblk, .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), .intr_rdptr = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12), }, { .name = "pingpong_1", .id = PINGPONG_1, .base = 0x70800, .len = 0xd4, - .features = PINGPONG_MSM8996_MASK, .sblk = &msm8996_pp_sblk, .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), .intr_rdptr = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13), @@ -131,7 +129,6 @@ static const struct dpu_intf_cfg msm8953_intf[] = { .prog_fetch_lines_worst_case = 14, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25), - .intr_tear_rd_ptr = -1, }, { .name = "intf_1", .id = INTF_1, .base = 0x6a800, .len = 0x268, @@ -140,7 +137,6 @@ static const struct dpu_intf_cfg msm8953_intf[] = { .prog_fetch_lines_worst_case = 14, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 26), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 27), - .intr_tear_rd_ptr = -1, }, { .name = "intf_2", .id = INTF_2, .base = 0x6b000, .len = 0x268, @@ -149,7 +145,6 @@ static const struct dpu_intf_cfg msm8953_intf[] = { .prog_fetch_lines_worst_case = 14, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 28), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 29), - .intr_tear_rd_ptr = -1, }, }; @@ -198,6 +193,7 @@ const struct dpu_mdss_cfg dpu_msm8953_cfg = { .mdss_ver = &msm8953_mdss_ver, .caps = &msm8953_dpu_caps, .mdp = msm8953_mdp, + .cdm = &dpu_cdm_1_x_4_x, .ctl_count = ARRAY_SIZE(msm8953_ctl), .ctl = msm8953_ctl, .sspp_count = ARRAY_SIZE(msm8953_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_7_msm8996.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_7_msm8996.h index 491f6f5827d1..91f514d28ac6 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_7_msm8996.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_1_7_msm8996.h @@ -181,15 +181,15 @@ static const struct dpu_pingpong_cfg msm8996_pp[] = { { .name = "pingpong_0", .id = PINGPONG_0, .base = 0x70000, .len = 0xd4, - .features = PINGPONG_MSM8996_TE2_MASK, - .sblk = &msm8996_pp_sblk_te, + .features = PINGPONG_MSM8996_MASK, + .sblk = &msm8996_pp_sblk, .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), .intr_rdptr = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12), }, { .name = "pingpong_1", .id = PINGPONG_1, .base = 0x70800, .len = 0xd4, - .features = PINGPONG_MSM8996_TE2_MASK, - .sblk = &msm8996_pp_sblk_te, + .features = PINGPONG_MSM8996_MASK, + .sblk = &msm8996_pp_sblk, .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), .intr_rdptr = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13), }, { @@ -241,7 +241,6 @@ static const struct dpu_intf_cfg msm8996_intf[] = { .prog_fetch_lines_worst_case = 25, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25), - .intr_tear_rd_ptr = -1, }, { .name = "intf_1", .id = INTF_1, .base = 0x6a800, .len = 0x268, @@ -250,7 +249,6 @@ static const struct dpu_intf_cfg msm8996_intf[] = { .prog_fetch_lines_worst_case = 25, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 26), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 27), - .intr_tear_rd_ptr = -1, }, { .name = "intf_2", .id = INTF_2, .base = 0x6b000, .len = 0x268, @@ -259,7 +257,6 @@ static const struct dpu_intf_cfg msm8996_intf[] = { .prog_fetch_lines_worst_case = 25, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 28), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 29), - .intr_tear_rd_ptr = -1, }, { .name = "intf_3", .id = INTF_3, .base = 0x6b800, .len = 0x268, @@ -267,7 +264,6 @@ static const struct dpu_intf_cfg msm8996_intf[] = { .prog_fetch_lines_worst_case = 25, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 30), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 31), - .intr_tear_rd_ptr = -1, }, }; @@ -316,6 +312,7 @@ const struct dpu_mdss_cfg dpu_msm8996_cfg = { .mdss_ver = &msm8996_mdss_ver, .caps = &msm8996_dpu_caps, .mdp = msm8996_mdp, + .cdm = &dpu_cdm_1_x_4_x, .ctl_count = ARRAY_SIZE(msm8996_ctl), .ctl = msm8996_ctl, .sspp_count = ARRAY_SIZE(msm8996_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h index 64c94e919a69..413cd59dc0c4 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_0_msm8998.h @@ -170,15 +170,15 @@ static const struct dpu_pingpong_cfg msm8998_pp[] = { { .name = "pingpong_0", .id = PINGPONG_0, .base = 0x70000, .len = 0xd4, - .features = PINGPONG_SDM845_TE2_MASK, - .sblk = &sdm845_pp_sblk_te, + .features = PINGPONG_SDM845_MASK, + .sblk = &sdm845_pp_sblk, .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), .intr_rdptr = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12), }, { .name = "pingpong_1", .id = PINGPONG_1, .base = 0x70800, .len = 0xd4, - .features = PINGPONG_SDM845_TE2_MASK, - .sblk = &sdm845_pp_sblk_te, + .features = PINGPONG_SDM845_MASK, + .sblk = &sdm845_pp_sblk, .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), .intr_rdptr = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13), }, { @@ -302,6 +302,7 @@ const struct dpu_mdss_cfg dpu_msm8998_cfg = { .mdss_ver = &msm8998_mdss_ver, .caps = &msm8998_dpu_caps, .mdp = &msm8998_mdp, + .cdm = &dpu_cdm_1_x_4_x, .ctl_count = ARRAY_SIZE(msm8998_ctl), .ctl = msm8998_ctl, .sspp_count = ARRAY_SIZE(msm8998_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_2_sdm660.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_2_sdm660.h index 424815e7fb7d..b2eb7ca699e3 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_2_sdm660.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_2_sdm660.h @@ -141,15 +141,15 @@ static const struct dpu_pingpong_cfg sdm660_pp[] = { { .name = "pingpong_0", .id = PINGPONG_0, .base = 0x70000, .len = 0xd4, - .features = PINGPONG_SDM845_TE2_MASK, - .sblk = &sdm845_pp_sblk_te, + .features = PINGPONG_SDM845_MASK, + .sblk = &sdm845_pp_sblk, .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), .intr_rdptr = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12), }, { .name = "pingpong_1", .id = PINGPONG_1, .base = 0x70800, .len = 0xd4, - .features = PINGPONG_SDM845_TE2_MASK, - .sblk = &sdm845_pp_sblk_te, + .features = PINGPONG_SDM845_MASK, + .sblk = &sdm845_pp_sblk, .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), .intr_rdptr = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13), }, { @@ -202,7 +202,6 @@ static const struct dpu_intf_cfg sdm660_intf[] = { .prog_fetch_lines_worst_case = 21, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25), - .intr_tear_rd_ptr = -1, }, { .name = "intf_1", .id = INTF_1, .base = 0x6a800, .len = 0x280, @@ -211,7 +210,6 @@ static const struct dpu_intf_cfg sdm660_intf[] = { .prog_fetch_lines_worst_case = 21, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 26), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 27), - .intr_tear_rd_ptr = -1, }, { .name = "intf_2", .id = INTF_2, .base = 0x6b000, .len = 0x280, @@ -220,7 +218,6 @@ static const struct dpu_intf_cfg sdm660_intf[] = { .prog_fetch_lines_worst_case = 21, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 28), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 29), - .intr_tear_rd_ptr = -1, }, }; @@ -269,6 +266,7 @@ const struct dpu_mdss_cfg dpu_sdm660_cfg = { .mdss_ver = &sdm660_mdss_ver, .caps = &sdm660_dpu_caps, .mdp = &sdm660_mdp, + .cdm = &dpu_cdm_1_x_4_x, .ctl_count = ARRAY_SIZE(sdm660_ctl), .ctl = sdm660_ctl, .sspp_count = ARRAY_SIZE(sdm660_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_3_sdm630.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_3_sdm630.h index df01227fc364..85e121ad84a0 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_3_sdm630.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_3_3_sdm630.h @@ -115,14 +115,14 @@ static const struct dpu_pingpong_cfg sdm630_pp[] = { { .name = "pingpong_0", .id = PINGPONG_0, .base = 0x70000, .len = 0xd4, - .features = PINGPONG_SDM845_TE2_MASK, - .sblk = &sdm845_pp_sblk_te, + .features = BIT(DPU_PINGPONG_DITHER), + .sblk = &sdm845_pp_sblk, .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), .intr_rdptr = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12), }, { .name = "pingpong_2", .id = PINGPONG_2, .base = 0x71000, .len = 0xd4, - .features = PINGPONG_SDM845_MASK, + .features = BIT(DPU_PINGPONG_DITHER), .sblk = &sdm845_pp_sblk, .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), .intr_rdptr = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 14), @@ -147,7 +147,6 @@ static const struct dpu_intf_cfg sdm630_intf[] = { .prog_fetch_lines_worst_case = 21, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25), - .intr_tear_rd_ptr = -1, }, { .name = "intf_1", .id = INTF_1, .base = 0x6a800, .len = 0x280, @@ -156,7 +155,6 @@ static const struct dpu_intf_cfg sdm630_intf[] = { .prog_fetch_lines_worst_case = 21, .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 26), .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 27), - .intr_tear_rd_ptr = -1, }, }; @@ -205,6 +203,7 @@ const struct dpu_mdss_cfg dpu_sdm630_cfg = { .mdss_ver = &sdm630_mdss_ver, .caps = &sdm630_dpu_caps, .mdp = &sdm630_mdp, + .cdm = &dpu_cdm_1_x_4_x, .ctl_count = ARRAY_SIZE(sdm630_ctl), .ctl = sdm630_ctl, .sspp_count = ARRAY_SIZE(sdm630_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_0_sdm845.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_0_sdm845.h index 72bd4f7e9e50..49363d7d5b93 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_0_sdm845.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_0_sdm845.h @@ -194,15 +194,15 @@ static const struct dpu_pingpong_cfg sdm845_pp[] = { { .name = "pingpong_0", .id = PINGPONG_0, .base = 0x70000, .len = 0xd4, - .features = PINGPONG_SDM845_TE2_MASK, - .sblk = &sdm845_pp_sblk_te, + .features = PINGPONG_SDM845_MASK, + .sblk = &sdm845_pp_sblk, .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), .intr_rdptr = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12), }, { .name = "pingpong_1", .id = PINGPONG_1, .base = 0x70800, .len = 0xd4, - .features = PINGPONG_SDM845_TE2_MASK, - .sblk = &sdm845_pp_sblk_te, + .features = PINGPONG_SDM845_MASK, + .sblk = &sdm845_pp_sblk, .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), .intr_rdptr = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13), }, { @@ -319,6 +319,7 @@ const struct dpu_mdss_cfg dpu_sdm845_cfg = { .mdss_ver = &sdm845_mdss_ver, .caps = &sdm845_dpu_caps, .mdp = &sdm845_mdp, + .cdm = &dpu_cdm_1_x_4_x, .ctl_count = ARRAY_SIZE(sdm845_ctl), .ctl = sdm845_ctl, .sspp_count = ARRAY_SIZE(sdm845_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_1_sdm670.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_1_sdm670.h index daef07924886..c2fde980fb52 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_1_sdm670.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_4_1_sdm670.h @@ -132,6 +132,7 @@ const struct dpu_mdss_cfg dpu_sdm670_cfg = { .mdss_ver = &sdm670_mdss_ver, .caps = &sdm845_dpu_caps, .mdp = &sdm670_mdp, + .cdm = &dpu_cdm_1_x_4_x, .ctl_count = ARRAY_SIZE(sdm845_ctl), .ctl = sdm845_ctl, .sspp_count = ARRAY_SIZE(sdm670_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h index 36cc9dbc00b5..08d38e1d420c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h @@ -37,17 +37,16 @@ static const struct dpu_mdp_cfg sm8150_mdp = { }, }; -/* FIXME: get rid of DPU_CTL_SPLIT_DISPLAY in favour of proper ACTIVE_CTL support */ static const struct dpu_ctl_cfg sm8150_ctl[] = { { .name = "ctl_0", .id = CTL_0, .base = 0x1000, .len = 0x1e0, - .features = BIT(DPU_CTL_ACTIVE_CFG) | BIT(DPU_CTL_SPLIT_DISPLAY), + .features = BIT(DPU_CTL_ACTIVE_CFG), .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 9), }, { .name = "ctl_1", .id = CTL_1, .base = 0x1200, .len = 0x1e0, - .features = BIT(DPU_CTL_ACTIVE_CFG) | BIT(DPU_CTL_SPLIT_DISPLAY), + .features = BIT(DPU_CTL_ACTIVE_CFG), .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 10), }, { .name = "ctl_2", .id = CTL_2, @@ -76,7 +75,7 @@ static const struct dpu_sspp_cfg sm8150_sspp[] = { { .name = "sspp_0", .id = SSPP_VIG0, .base = 0x4000, .len = 0x1f0, - .features = VIG_SDM845_MASK, + .features = VIG_SDM845_MASK_SDMA, .sblk = &dpu_vig_sblk_qseed3_1_4, .xin_id = 0, .type = SSPP_TYPE_VIG, @@ -84,7 +83,7 @@ static const struct dpu_sspp_cfg sm8150_sspp[] = { }, { .name = "sspp_1", .id = SSPP_VIG1, .base = 0x6000, .len = 0x1f0, - .features = VIG_SDM845_MASK, + .features = VIG_SDM845_MASK_SDMA, .sblk = &dpu_vig_sblk_qseed3_1_4, .xin_id = 4, .type = SSPP_TYPE_VIG, @@ -92,7 +91,7 @@ static const struct dpu_sspp_cfg sm8150_sspp[] = { }, { .name = "sspp_2", .id = SSPP_VIG2, .base = 0x8000, .len = 0x1f0, - .features = VIG_SDM845_MASK, + .features = VIG_SDM845_MASK_SDMA, .sblk = &dpu_vig_sblk_qseed3_1_4, .xin_id = 8, .type = SSPP_TYPE_VIG, @@ -100,7 +99,7 @@ static const struct dpu_sspp_cfg sm8150_sspp[] = { }, { .name = "sspp_3", .id = SSPP_VIG3, .base = 0xa000, .len = 0x1f0, - .features = VIG_SDM845_MASK, + .features = VIG_SDM845_MASK_SDMA, .sblk = &dpu_vig_sblk_qseed3_1_4, .xin_id = 12, .type = SSPP_TYPE_VIG, @@ -108,7 +107,7 @@ static const struct dpu_sspp_cfg sm8150_sspp[] = { }, { .name = "sspp_8", .id = SSPP_DMA0, .base = 0x24000, .len = 0x1f0, - .features = DMA_SDM845_MASK, + .features = DMA_SDM845_MASK_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 1, .type = SSPP_TYPE_DMA, @@ -116,7 +115,7 @@ static const struct dpu_sspp_cfg sm8150_sspp[] = { }, { .name = "sspp_9", .id = SSPP_DMA1, .base = 0x26000, .len = 0x1f0, - .features = DMA_SDM845_MASK, + .features = DMA_SDM845_MASK_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 5, .type = SSPP_TYPE_DMA, @@ -124,7 +123,7 @@ static const struct dpu_sspp_cfg sm8150_sspp[] = { }, { .name = "sspp_10", .id = SSPP_DMA2, .base = 0x28000, .len = 0x1f0, - .features = DMA_CURSOR_SDM845_MASK, + .features = DMA_CURSOR_SDM845_MASK_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 9, .type = SSPP_TYPE_DMA, @@ -132,7 +131,7 @@ static const struct dpu_sspp_cfg sm8150_sspp[] = { }, { .name = "sspp_11", .id = SSPP_DMA3, .base = 0x2a000, .len = 0x1f0, - .features = DMA_CURSOR_SDM845_MASK, + .features = DMA_CURSOR_SDM845_MASK_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 13, .type = SSPP_TYPE_DMA, @@ -298,8 +297,8 @@ static const struct dpu_wb_cfg sm8150_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .clk_ctrl = DPU_CLK_CTRL_WB2, .xin_id = 6, .vbif_idx = VBIF_RT, @@ -388,6 +387,7 @@ const struct dpu_mdss_cfg dpu_sm8150_cfg = { .mdss_ver = &sm8150_mdss_ver, .caps = &sm8150_dpu_caps, .mdp = &sm8150_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sm8150_ctl), .ctl = sm8150_ctl, .sspp_count = ARRAY_SIZE(sm8150_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h index e8eacdb47967..6c04f41f9bac 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h @@ -41,12 +41,12 @@ static const struct dpu_ctl_cfg sc8180x_ctl[] = { { .name = "ctl_0", .id = CTL_0, .base = 0x1000, .len = 0x1e0, - .features = BIT(DPU_CTL_ACTIVE_CFG) | BIT(DPU_CTL_SPLIT_DISPLAY), + .features = BIT(DPU_CTL_ACTIVE_CFG), .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 9), }, { .name = "ctl_1", .id = CTL_1, .base = 0x1200, .len = 0x1e0, - .features = BIT(DPU_CTL_ACTIVE_CFG) | BIT(DPU_CTL_SPLIT_DISPLAY), + .features = BIT(DPU_CTL_ACTIVE_CFG), .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 10), }, { .name = "ctl_2", .id = CTL_2, @@ -75,7 +75,7 @@ static const struct dpu_sspp_cfg sc8180x_sspp[] = { { .name = "sspp_0", .id = SSPP_VIG0, .base = 0x4000, .len = 0x1f0, - .features = VIG_SDM845_MASK, + .features = VIG_SDM845_MASK_SDMA, .sblk = &dpu_vig_sblk_qseed3_1_4, .xin_id = 0, .type = SSPP_TYPE_VIG, @@ -83,7 +83,7 @@ static const struct dpu_sspp_cfg sc8180x_sspp[] = { }, { .name = "sspp_1", .id = SSPP_VIG1, .base = 0x6000, .len = 0x1f0, - .features = VIG_SDM845_MASK, + .features = VIG_SDM845_MASK_SDMA, .sblk = &dpu_vig_sblk_qseed3_1_4, .xin_id = 4, .type = SSPP_TYPE_VIG, @@ -91,7 +91,7 @@ static const struct dpu_sspp_cfg sc8180x_sspp[] = { }, { .name = "sspp_2", .id = SSPP_VIG2, .base = 0x8000, .len = 0x1f0, - .features = VIG_SDM845_MASK, + .features = VIG_SDM845_MASK_SDMA, .sblk = &dpu_vig_sblk_qseed3_1_4, .xin_id = 8, .type = SSPP_TYPE_VIG, @@ -99,7 +99,7 @@ static const struct dpu_sspp_cfg sc8180x_sspp[] = { }, { .name = "sspp_3", .id = SSPP_VIG3, .base = 0xa000, .len = 0x1f0, - .features = VIG_SDM845_MASK, + .features = VIG_SDM845_MASK_SDMA, .sblk = &dpu_vig_sblk_qseed3_1_4, .xin_id = 12, .type = SSPP_TYPE_VIG, @@ -107,7 +107,7 @@ static const struct dpu_sspp_cfg sc8180x_sspp[] = { }, { .name = "sspp_8", .id = SSPP_DMA0, .base = 0x24000, .len = 0x1f0, - .features = DMA_SDM845_MASK, + .features = DMA_SDM845_MASK_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 1, .type = SSPP_TYPE_DMA, @@ -115,7 +115,7 @@ static const struct dpu_sspp_cfg sc8180x_sspp[] = { }, { .name = "sspp_9", .id = SSPP_DMA1, .base = 0x26000, .len = 0x1f0, - .features = DMA_SDM845_MASK, + .features = DMA_SDM845_MASK_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 5, .type = SSPP_TYPE_DMA, @@ -123,7 +123,7 @@ static const struct dpu_sspp_cfg sc8180x_sspp[] = { }, { .name = "sspp_10", .id = SSPP_DMA2, .base = 0x28000, .len = 0x1f0, - .features = DMA_CURSOR_SDM845_MASK, + .features = DMA_CURSOR_SDM845_MASK_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 9, .type = SSPP_TYPE_DMA, @@ -131,7 +131,7 @@ static const struct dpu_sspp_cfg sc8180x_sspp[] = { }, { .name = "sspp_11", .id = SSPP_DMA3, .base = 0x2a000, .len = 0x1f0, - .features = DMA_CURSOR_SDM845_MASK, + .features = DMA_CURSOR_SDM845_MASK_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 13, .type = SSPP_TYPE_DMA, @@ -305,8 +305,8 @@ static const struct dpu_wb_cfg sc8180x_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .clk_ctrl = DPU_CLK_CTRL_WB2, .xin_id = 6, .vbif_idx = VBIF_RT, @@ -383,6 +383,7 @@ static const struct dpu_perf_cfg sc8180x_perf_data = { .min_core_ib = 2400000, .min_llcc_ib = 800000, .min_dram_ib = 800000, + .min_prefill_lines = 24, .danger_lut_tbl = {0xf, 0xffff, 0x0}, .safe_lut_tbl = {0xfff0, 0xf000, 0xffff}, .qos_lut_tbl = { @@ -414,6 +415,7 @@ const struct dpu_mdss_cfg dpu_sc8180x_cfg = { .mdss_ver = &sc8180x_mdss_ver, .caps = &sc8180x_dpu_caps, .mdp = &sc8180x_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sc8180x_ctl), .ctl = sc8180x_ctl, .sspp_count = ARRAY_SIZE(sc8180x_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_2_sm7150.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_2_sm7150.h index 2fe674d1e059..71ba48b05656 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_2_sm7150.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_2_sm7150.h @@ -38,12 +38,12 @@ static const struct dpu_ctl_cfg sm7150_ctl[] = { { .name = "ctl_0", .id = CTL_0, .base = 0x1000, .len = 0x1e0, - .features = BIT(DPU_CTL_ACTIVE_CFG) | BIT(DPU_CTL_SPLIT_DISPLAY), + .features = BIT(DPU_CTL_ACTIVE_CFG), .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 9), }, { .name = "ctl_1", .id = CTL_1, .base = 0x1200, .len = 0x1e0, - .features = BIT(DPU_CTL_ACTIVE_CFG) | BIT(DPU_CTL_SPLIT_DISPLAY), + .features = BIT(DPU_CTL_ACTIVE_CFG), .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 10), }, { .name = "ctl_2", .id = CTL_2, @@ -72,7 +72,7 @@ static const struct dpu_sspp_cfg sm7150_sspp[] = { { .name = "sspp_0", .id = SSPP_VIG0, .base = 0x4000, .len = 0x1f0, - .features = VIG_SDM845_MASK, + .features = VIG_SDM845_MASK_NO_SDMA, .sblk = &dpu_vig_sblk_qseed3_2_4, .xin_id = 0, .type = SSPP_TYPE_VIG, @@ -80,7 +80,7 @@ static const struct dpu_sspp_cfg sm7150_sspp[] = { }, { .name = "sspp_1", .id = SSPP_VIG1, .base = 0x6000, .len = 0x1f0, - .features = VIG_SDM845_MASK, + .features = VIG_SDM845_MASK_NO_SDMA, .sblk = &dpu_vig_sblk_qseed3_2_4, .xin_id = 4, .type = SSPP_TYPE_VIG, @@ -88,7 +88,7 @@ static const struct dpu_sspp_cfg sm7150_sspp[] = { }, { .name = "sspp_2", .id = SSPP_DMA0, .base = 0x24000, .len = 0x1f0, - .features = DMA_SDM845_MASK, + .features = DMA_SDM845_MASK_NO_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 1, .type = SSPP_TYPE_DMA, @@ -96,7 +96,7 @@ static const struct dpu_sspp_cfg sm7150_sspp[] = { }, { .name = "sspp_9", .id = SSPP_DMA1, .base = 0x26000, .len = 0x1f0, - .features = DMA_SDM845_MASK, + .features = DMA_SDM845_MASK_NO_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 5, .type = SSPP_TYPE_DMA, @@ -104,7 +104,7 @@ static const struct dpu_sspp_cfg sm7150_sspp[] = { }, { .name = "sspp_10", .id = SSPP_DMA2, .base = 0x28000, .len = 0x1f0, - .features = DMA_CURSOR_SDM845_MASK, + .features = DMA_CURSOR_SDM845_MASK_NO_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 9, .type = SSPP_TYPE_DMA, @@ -261,8 +261,8 @@ static const struct dpu_wb_cfg sm7150_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .clk_ctrl = DPU_CLK_CTRL_WB2, .xin_id = 6, .vbif_idx = VBIF_RT, @@ -309,6 +309,7 @@ const struct dpu_mdss_cfg dpu_sm7150_cfg = { .mdss_ver = &sm7150_mdss_ver, .caps = &sm7150_dpu_caps, .mdp = &sm7150_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sm7150_ctl), .ctl = sm7150_ctl, .sspp_count = ARRAY_SIZE(sm7150_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_3_sm6150.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_3_sm6150.h new file mode 100644 index 000000000000..da11830d4407 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_3_sm6150.h @@ -0,0 +1,271 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#ifndef _DPU_5_3_SM6150_H +#define _DPU_5_3_SM6150_H + +static const struct dpu_caps sm6150_dpu_caps = { + .max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH, + .max_mixer_blendstages = 0x9, + .has_dim_layer = true, + .has_idle_pc = true, + .max_linewidth = 2160, + .pixel_ram_size = DEFAULT_PIXEL_RAM_SIZE, + .max_hdeci_exp = MAX_HORZ_DECIMATION, + .max_vdeci_exp = MAX_VERT_DECIMATION, +}; + +static const struct dpu_mdp_cfg sm6150_mdp = { + .name = "top_0", + .base = 0x0, .len = 0x45c, + .features = 0, + .clk_ctrls = { + [DPU_CLK_CTRL_VIG0] = { .reg_off = 0x2ac, .bit_off = 0 }, + [DPU_CLK_CTRL_DMA0] = { .reg_off = 0x2ac, .bit_off = 8 }, + [DPU_CLK_CTRL_DMA1] = { .reg_off = 0x2b4, .bit_off = 8 }, + [DPU_CLK_CTRL_DMA2] = { .reg_off = 0x2bc, .bit_off = 8 }, + [DPU_CLK_CTRL_DMA3] = { .reg_off = 0x2c4, .bit_off = 8 }, + [DPU_CLK_CTRL_WB2] = { .reg_off = 0x2bc, .bit_off = 16 }, + }, +}; + +static const struct dpu_ctl_cfg sm6150_ctl[] = { + { + .name = "ctl_0", .id = CTL_0, + .base = 0x1000, .len = 0x1e0, + .features = BIT(DPU_CTL_ACTIVE_CFG), + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 9), + }, { + .name = "ctl_1", .id = CTL_1, + .base = 0x1200, .len = 0x1e0, + .features = BIT(DPU_CTL_ACTIVE_CFG), + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 10), + }, { + .name = "ctl_2", .id = CTL_2, + .base = 0x1400, .len = 0x1e0, + .features = BIT(DPU_CTL_ACTIVE_CFG), + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 11), + }, { + .name = "ctl_3", .id = CTL_3, + .base = 0x1600, .len = 0x1e0, + .features = BIT(DPU_CTL_ACTIVE_CFG), + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 12), + }, { + .name = "ctl_4", .id = CTL_4, + .base = 0x1800, .len = 0x1e0, + .features = BIT(DPU_CTL_ACTIVE_CFG), + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 13), + }, { + .name = "ctl_5", .id = CTL_5, + .base = 0x1a00, .len = 0x1e0, + .features = BIT(DPU_CTL_ACTIVE_CFG), + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 23), + }, +}; + +static const struct dpu_sspp_cfg sm6150_sspp[] = { + { + .name = "sspp_0", .id = SSPP_VIG0, + .base = 0x4000, .len = 0x1f0, + .features = VIG_SDM845_MASK_SDMA, + .sblk = &dpu_vig_sblk_qseed3_2_4, + .xin_id = 0, + .type = SSPP_TYPE_VIG, + .clk_ctrl = DPU_CLK_CTRL_VIG0, + }, { + .name = "sspp_8", .id = SSPP_DMA0, + .base = 0x24000, .len = 0x1f0, + .features = DMA_SDM845_MASK_SDMA, + .sblk = &dpu_dma_sblk, + .xin_id = 1, + .type = SSPP_TYPE_DMA, + .clk_ctrl = DPU_CLK_CTRL_DMA0, + }, { + .name = "sspp_9", .id = SSPP_DMA1, + .base = 0x26000, .len = 0x1f0, + .features = DMA_SDM845_MASK_SDMA, + .sblk = &dpu_dma_sblk, + .xin_id = 5, + .type = SSPP_TYPE_DMA, + .clk_ctrl = DPU_CLK_CTRL_DMA1, + }, { + .name = "sspp_10", .id = SSPP_DMA2, + .base = 0x28000, .len = 0x1f0, + .features = DMA_CURSOR_SDM845_MASK_SDMA, + .sblk = &dpu_dma_sblk, + .xin_id = 9, + .type = SSPP_TYPE_DMA, + .clk_ctrl = DPU_CLK_CTRL_DMA2, + }, { + .name = "sspp_11", .id = SSPP_DMA3, + .base = 0x2a000, .len = 0x1f0, + .features = DMA_CURSOR_SDM845_MASK_SDMA, + .sblk = &dpu_dma_sblk, + .xin_id = 13, + .type = SSPP_TYPE_DMA, + .clk_ctrl = DPU_CLK_CTRL_DMA3, + }, +}; + +static const struct dpu_lm_cfg sm6150_lm[] = { + { + .name = "lm_0", .id = LM_0, + .base = 0x44000, .len = 0x320, + .features = MIXER_QCM2290_MASK, + .sblk = &sdm845_lm_sblk, + .pingpong = PINGPONG_0, + .dspp = DSPP_0, + }, { + .name = "lm_1", .id = LM_1, + .base = 0x45000, .len = 0x320, + .features = MIXER_QCM2290_MASK, + .sblk = &sdm845_lm_sblk, + .pingpong = PINGPONG_1, + }, { + .name = "lm_2", .id = LM_2, + .base = 0x46000, .len = 0x320, + .features = MIXER_QCM2290_MASK, + .sblk = &sdm845_lm_sblk, + .pingpong = PINGPONG_2, + }, +}; + +static const struct dpu_dspp_cfg sm6150_dspp[] = { + { + .name = "dspp_0", .id = DSPP_0, + .base = 0x54000, .len = 0x1800, + .features = DSPP_SC7180_MASK, + .sblk = &sdm845_dspp_sblk, + }, +}; + +static const struct dpu_pingpong_cfg sm6150_pp[] = { + { + .name = "pingpong_0", .id = PINGPONG_0, + .base = 0x70000, .len = 0xd4, + .features = PINGPONG_SM8150_MASK, + .sblk = &sdm845_pp_sblk, + .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), + }, { + .name = "pingpong_1", .id = PINGPONG_1, + .base = 0x70800, .len = 0xd4, + .features = PINGPONG_SM8150_MASK, + .sblk = &sdm845_pp_sblk, + .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), + }, { + .name = "pingpong_2", .id = PINGPONG_2, + .base = 0x71000, .len = 0xd4, + .features = PINGPONG_SM8150_MASK, + .sblk = &sdm845_pp_sblk, + .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), + }, +}; + +static const struct dpu_wb_cfg sm6150_wb[] = { + { + .name = "wb_2", .id = WB_2, + .base = 0x65000, .len = 0x2c8, + .features = WB_SM8250_MASK, + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), + .clk_ctrl = DPU_CLK_CTRL_WB2, + .xin_id = 6, + .vbif_idx = VBIF_RT, + .maxlinewidth = 2160, + .intr_wb_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 4), + }, +}; + +static const struct dpu_intf_cfg sm6150_intf[] = { + { + .name = "intf_0", .id = INTF_0, + .base = 0x6a000, .len = 0x280, + .features = INTF_SC7180_MASK, + .type = INTF_DP, + .controller_id = MSM_DP_CONTROLLER_0, + .prog_fetch_lines_worst_case = 24, + .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24), + .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25), + }, { + .name = "intf_1", .id = INTF_1, + .base = 0x6a800, .len = 0x2c0, + .features = INTF_SC7180_MASK, + .type = INTF_DSI, + .controller_id = MSM_DSI_CONTROLLER_0, + .prog_fetch_lines_worst_case = 24, + .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 26), + .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 27), + .intr_tear_rd_ptr = DPU_IRQ_IDX(MDP_INTF1_TEAR_INTR, 2), + }, { + .name = "intf_3", .id = INTF_3, + .base = 0x6b800, .len = 0x280, + .features = INTF_SC7180_MASK, + .type = INTF_DP, + .controller_id = MSM_DP_CONTROLLER_1, + .prog_fetch_lines_worst_case = 24, + .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 30), + .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 31), + }, +}; + +static const struct dpu_perf_cfg sm6150_perf_data = { + .max_bw_low = 4800000, + .max_bw_high = 4800000, + .min_core_ib = 2400000, + .min_llcc_ib = 0, + .min_dram_ib = 800000, + .min_prefill_lines = 24, + .danger_lut_tbl = {0xf, 0xffff, 0x0}, + .safe_lut_tbl = {0xfff8, 0xf000, 0xffff}, + .qos_lut_tbl = { + {.nentry = ARRAY_SIZE(sm8150_qos_linear), + .entries = sm8150_qos_linear + }, + {.nentry = ARRAY_SIZE(sc7180_qos_macrotile), + .entries = sc7180_qos_macrotile + }, + {.nentry = ARRAY_SIZE(sc7180_qos_nrt), + .entries = sc7180_qos_nrt + }, + /* TODO: macrotile-qseed is different from macrotile */ + }, + .cdp_cfg = { + {.rd_enable = 1, .wr_enable = 1}, + {.rd_enable = 1, .wr_enable = 0} + }, + .clk_inefficiency_factor = 105, + .bw_inefficiency_factor = 120, +}; + +static const struct dpu_mdss_version sm6150_mdss_ver = { + .core_major_ver = 5, + .core_minor_ver = 3, +}; + +const struct dpu_mdss_cfg dpu_sm6150_cfg = { + .mdss_ver = &sm6150_mdss_ver, + .caps = &sm6150_dpu_caps, + .mdp = &sm6150_mdp, + .cdm = &dpu_cdm_5_x, + .ctl_count = ARRAY_SIZE(sm6150_ctl), + .ctl = sm6150_ctl, + .sspp_count = ARRAY_SIZE(sm6150_sspp), + .sspp = sm6150_sspp, + .mixer_count = ARRAY_SIZE(sm6150_lm), + .mixer = sm6150_lm, + .dspp_count = ARRAY_SIZE(sm6150_dspp), + .dspp = sm6150_dspp, + .pingpong_count = ARRAY_SIZE(sm6150_pp), + .pingpong = sm6150_pp, + .wb_count = ARRAY_SIZE(sm6150_wb), + .wb = sm6150_wb, + .intf_count = ARRAY_SIZE(sm6150_intf), + .intf = sm6150_intf, + .vbif_count = ARRAY_SIZE(sdm845_vbif), + .vbif = sdm845_vbif, + .perf = &sm6150_perf_data, +}; + +#endif diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h index 76f60a2df7a8..fcfb3774f7a1 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h @@ -69,7 +69,7 @@ static const struct dpu_sspp_cfg sm6125_sspp[] = { { .name = "sspp_0", .id = SSPP_VIG0, .base = 0x4000, .len = 0x1f0, - .features = VIG_SDM845_MASK, + .features = VIG_SDM845_MASK_NO_SDMA, .sblk = &dpu_vig_sblk_qseed3_2_4, .xin_id = 0, .type = SSPP_TYPE_VIG, @@ -77,7 +77,7 @@ static const struct dpu_sspp_cfg sm6125_sspp[] = { }, { .name = "sspp_8", .id = SSPP_DMA0, .base = 0x24000, .len = 0x1f0, - .features = DMA_SDM845_MASK, + .features = DMA_SDM845_MASK_NO_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 1, .type = SSPP_TYPE_DMA, @@ -85,7 +85,7 @@ static const struct dpu_sspp_cfg sm6125_sspp[] = { }, { .name = "sspp_9", .id = SSPP_DMA1, .base = 0x26000, .len = 0x1f0, - .features = DMA_SDM845_MASK, + .features = DMA_SDM845_MASK_NO_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 5, .type = SSPP_TYPE_DMA, @@ -145,8 +145,8 @@ static const struct dpu_wb_cfg sm6125_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .clk_ctrl = DPU_CLK_CTRL_WB2, .xin_id = 6, .vbif_idx = VBIF_RT, @@ -216,6 +216,7 @@ const struct dpu_mdss_cfg dpu_sm6125_cfg = { .mdss_ver = &sm6125_mdss_ver, .caps = &sm6125_dpu_caps, .mdp = &sm6125_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sm6125_ctl), .ctl = sm6125_ctl, .sspp_count = ARRAY_SIZE(sm6125_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h index e8916ae826a6..a86fdb33ebdd 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_0_sm8250.h @@ -35,17 +35,16 @@ static const struct dpu_mdp_cfg sm8250_mdp = { }, }; -/* FIXME: get rid of DPU_CTL_SPLIT_DISPLAY in favour of proper ACTIVE_CTL support */ static const struct dpu_ctl_cfg sm8250_ctl[] = { { .name = "ctl_0", .id = CTL_0, .base = 0x1000, .len = 0x1e0, - .features = BIT(DPU_CTL_ACTIVE_CFG) | BIT(DPU_CTL_SPLIT_DISPLAY), + .features = BIT(DPU_CTL_ACTIVE_CFG), .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 9), }, { .name = "ctl_1", .id = CTL_1, .base = 0x1200, .len = 0x1e0, - .features = BIT(DPU_CTL_ACTIVE_CFG) | BIT(DPU_CTL_SPLIT_DISPLAY), + .features = BIT(DPU_CTL_ACTIVE_CFG), .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 10), }, { .name = "ctl_2", .id = CTL_2, @@ -386,7 +385,7 @@ const struct dpu_mdss_cfg dpu_sm8250_cfg = { .mdss_ver = &sm8250_mdss_ver, .caps = &sm8250_dpu_caps, .mdp = &sm8250_mdp, - .cdm = &sc7280_cdm, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sm8250_ctl), .ctl = sm8250_ctl, .sspp_count = ARRAY_SIZE(sm8250_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h index 7382ebb6e5b2..842fcc5887fe 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_2_sc7180.h @@ -51,7 +51,7 @@ static const struct dpu_sspp_cfg sc7180_sspp[] = { { .name = "sspp_0", .id = SSPP_VIG0, .base = 0x4000, .len = 0x1f8, - .features = VIG_SDM845_MASK, + .features = VIG_SDM845_MASK_NO_SDMA, .sblk = &dpu_vig_sblk_qseed3_3_0, .xin_id = 0, .type = SSPP_TYPE_VIG, @@ -59,7 +59,7 @@ static const struct dpu_sspp_cfg sc7180_sspp[] = { }, { .name = "sspp_8", .id = SSPP_DMA0, .base = 0x24000, .len = 0x1f8, - .features = DMA_SDM845_MASK, + .features = DMA_SDM845_MASK_NO_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 1, .type = SSPP_TYPE_DMA, @@ -67,7 +67,7 @@ static const struct dpu_sspp_cfg sc7180_sspp[] = { }, { .name = "sspp_9", .id = SSPP_DMA1, .base = 0x26000, .len = 0x1f8, - .features = DMA_CURSOR_SDM845_MASK, + .features = DMA_CURSOR_SDM845_MASK_NO_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 5, .type = SSPP_TYPE_DMA, @@ -75,7 +75,7 @@ static const struct dpu_sspp_cfg sc7180_sspp[] = { }, { .name = "sspp_10", .id = SSPP_DMA2, .base = 0x28000, .len = 0x1f8, - .features = DMA_CURSOR_SDM845_MASK, + .features = DMA_CURSOR_SDM845_MASK_NO_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 9, .type = SSPP_TYPE_DMA, @@ -157,8 +157,8 @@ static const struct dpu_wb_cfg sc7180_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .clk_ctrl = DPU_CLK_CTRL_WB2, .xin_id = 6, .vbif_idx = VBIF_RT, @@ -204,6 +204,7 @@ const struct dpu_mdss_cfg dpu_sc7180_cfg = { .mdss_ver = &sc7180_mdss_ver, .caps = &sc7180_dpu_caps, .mdp = &sc7180_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sc7180_ctl), .ctl = sc7180_ctl, .sspp_count = ARRAY_SIZE(sc7180_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_3_sm6115.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_3_sm6115.h index 43f64a005f5a..c5fd89dd7c89 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_3_sm6115.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_3_sm6115.h @@ -38,7 +38,7 @@ static const struct dpu_sspp_cfg sm6115_sspp[] = { { .name = "sspp_0", .id = SSPP_VIG0, .base = 0x4000, .len = 0x1f8, - .features = VIG_SDM845_MASK, + .features = VIG_SDM845_MASK_NO_SDMA, .sblk = &dpu_vig_sblk_qseed3_3_0, .xin_id = 0, .type = SSPP_TYPE_VIG, @@ -46,7 +46,7 @@ static const struct dpu_sspp_cfg sm6115_sspp[] = { }, { .name = "sspp_8", .id = SSPP_DMA0, .base = 0x24000, .len = 0x1f8, - .features = DMA_SDM845_MASK, + .features = DMA_SDM845_MASK_NO_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 1, .type = SSPP_TYPE_DMA, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_4_sm6350.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_4_sm6350.h index 0502cee2f116..a234bb289d24 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_4_sm6350.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_4_sm6350.h @@ -59,7 +59,7 @@ static const struct dpu_sspp_cfg sm6350_sspp[] = { { .name = "sspp_0", .id = SSPP_VIG0, .base = 0x4000, .len = 0x1f8, - .features = VIG_SDM845_MASK, + .features = VIG_SDM845_MASK_NO_SDMA, .sblk = &dpu_vig_sblk_qseed3_3_0, .xin_id = 0, .type = SSPP_TYPE_VIG, @@ -67,7 +67,7 @@ static const struct dpu_sspp_cfg sm6350_sspp[] = { }, { .name = "sspp_8", .id = SSPP_DMA0, .base = 0x24000, .len = 0x1f8, - .features = DMA_SDM845_MASK, + .features = DMA_SDM845_MASK_NO_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 1, .type = SSPP_TYPE_DMA, @@ -75,7 +75,7 @@ static const struct dpu_sspp_cfg sm6350_sspp[] = { }, { .name = "sspp_9", .id = SSPP_DMA1, .base = 0x26000, .len = 0x1f8, - .features = DMA_CURSOR_SDM845_MASK, + .features = DMA_CURSOR_SDM845_MASK_NO_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 5, .type = SSPP_TYPE_DMA, @@ -83,7 +83,7 @@ static const struct dpu_sspp_cfg sm6350_sspp[] = { }, { .name = "sspp_10", .id = SSPP_DMA2, .base = 0x28000, .len = 0x1f8, - .features = DMA_CURSOR_SDM845_MASK, + .features = DMA_CURSOR_SDM845_MASK_NO_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 9, .type = SSPP_TYPE_DMA, @@ -151,8 +151,8 @@ static const struct dpu_wb_cfg sm6350_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .clk_ctrl = DPU_CLK_CTRL_WB2, .xin_id = 6, .vbif_idx = VBIF_RT, @@ -222,6 +222,7 @@ const struct dpu_mdss_cfg dpu_sm6350_cfg = { .mdss_ver = &sm6350_mdss_ver, .caps = &sm6350_dpu_caps, .mdp = &sm6350_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sm6350_ctl), .ctl = sm6350_ctl, .sspp_count = ARRAY_SIZE(sm6350_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_5_qcm2290.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_5_qcm2290.h index 3cbb2fe8aba2..53f3be28f6f6 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_5_qcm2290.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_5_qcm2290.h @@ -46,7 +46,7 @@ static const struct dpu_sspp_cfg qcm2290_sspp[] = { }, { .name = "sspp_8", .id = SSPP_DMA0, .base = 0x24000, .len = 0x1f8, - .features = DMA_SDM845_MASK, + .features = DMA_SDM845_MASK_NO_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 1, .type = SSPP_TYPE_DMA, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_9_sm6375.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_9_sm6375.h index a06c8634d2d7..3a3bc8e429be 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_9_sm6375.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_6_9_sm6375.h @@ -39,7 +39,7 @@ static const struct dpu_sspp_cfg sm6375_sspp[] = { { .name = "sspp_0", .id = SSPP_VIG0, .base = 0x4000, .len = 0x1f8, - .features = VIG_SDM845_MASK, + .features = VIG_SDM845_MASK_NO_SDMA, .sblk = &dpu_vig_sblk_qseed3_3_0, .xin_id = 0, .type = SSPP_TYPE_VIG, @@ -47,7 +47,7 @@ static const struct dpu_sspp_cfg sm6375_sspp[] = { }, { .name = "sspp_8", .id = SSPP_DMA0, .base = 0x24000, .len = 0x1f8, - .features = DMA_SDM845_MASK, + .features = DMA_SDM845_MASK_NO_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 1, .type = SSPP_TYPE_DMA, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h index f7c08e89c882..90e86063a372 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_0_sm8350.h @@ -35,17 +35,16 @@ static const struct dpu_mdp_cfg sm8350_mdp = { }, }; -/* FIXME: get rid of DPU_CTL_SPLIT_DISPLAY in favour of proper ACTIVE_CTL support */ static const struct dpu_ctl_cfg sm8350_ctl[] = { { .name = "ctl_0", .id = CTL_0, .base = 0x15000, .len = 0x1e8, - .features = BIT(DPU_CTL_SPLIT_DISPLAY) | CTL_SC7280_MASK, + .features = CTL_SC7280_MASK, .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 9), }, { .name = "ctl_1", .id = CTL_1, .base = 0x16000, .len = 0x1e8, - .features = BIT(DPU_CTL_SPLIT_DISPLAY) | CTL_SC7280_MASK, + .features = CTL_SC7280_MASK, .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 10), }, { .name = "ctl_2", .id = CTL_2, @@ -305,8 +304,8 @@ static const struct dpu_wb_cfg sm8350_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .clk_ctrl = DPU_CLK_CTRL_WB2, .xin_id = 6, .vbif_idx = VBIF_RT, @@ -396,6 +395,7 @@ const struct dpu_mdss_cfg dpu_sm8350_cfg = { .mdss_ver = &sm8350_mdss_ver, .caps = &sm8350_dpu_caps, .mdp = &sm8350_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sm8350_ctl), .ctl = sm8350_ctl, .sspp_count = ARRAY_SIZE(sm8350_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h index 2f153e0b5c6a..e9625c48c567 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_7_2_sc7280.h @@ -248,7 +248,7 @@ const struct dpu_mdss_cfg dpu_sc7280_cfg = { .mdss_ver = &sc7280_mdss_ver, .caps = &sc7280_dpu_caps, .mdp = &sc7280_mdp, - .cdm = &sc7280_cdm, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sc7280_ctl), .ctl = sc7280_ctl, .sspp_count = ARRAY_SIZE(sc7280_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h index 0d143e390eca..139f11321fea 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_0_sc8280xp.h @@ -35,17 +35,16 @@ static const struct dpu_mdp_cfg sc8280xp_mdp = { }, }; -/* FIXME: get rid of DPU_CTL_SPLIT_DISPLAY in favour of proper ACTIVE_CTL support */ static const struct dpu_ctl_cfg sc8280xp_ctl[] = { { .name = "ctl_0", .id = CTL_0, .base = 0x15000, .len = 0x204, - .features = BIT(DPU_CTL_SPLIT_DISPLAY) | CTL_SC7280_MASK, + .features = CTL_SC7280_MASK, .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 9), }, { .name = "ctl_1", .id = CTL_1, .base = 0x16000, .len = 0x204, - .features = BIT(DPU_CTL_SPLIT_DISPLAY) | CTL_SC7280_MASK, + .features = CTL_SC7280_MASK, .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 10), }, { .name = "ctl_2", .id = CTL_2, @@ -74,7 +73,7 @@ static const struct dpu_sspp_cfg sc8280xp_sspp[] = { { .name = "sspp_0", .id = SSPP_VIG0, .base = 0x4000, .len = 0x2ac, - .features = VIG_SDM845_MASK, + .features = VIG_SDM845_MASK_SDMA, .sblk = &dpu_vig_sblk_qseed3_3_0, .xin_id = 0, .type = SSPP_TYPE_VIG, @@ -82,7 +81,7 @@ static const struct dpu_sspp_cfg sc8280xp_sspp[] = { }, { .name = "sspp_1", .id = SSPP_VIG1, .base = 0x6000, .len = 0x2ac, - .features = VIG_SDM845_MASK, + .features = VIG_SDM845_MASK_SDMA, .sblk = &dpu_vig_sblk_qseed3_3_0, .xin_id = 4, .type = SSPP_TYPE_VIG, @@ -90,7 +89,7 @@ static const struct dpu_sspp_cfg sc8280xp_sspp[] = { }, { .name = "sspp_2", .id = SSPP_VIG2, .base = 0x8000, .len = 0x2ac, - .features = VIG_SDM845_MASK, + .features = VIG_SDM845_MASK_SDMA, .sblk = &dpu_vig_sblk_qseed3_3_0, .xin_id = 8, .type = SSPP_TYPE_VIG, @@ -98,7 +97,7 @@ static const struct dpu_sspp_cfg sc8280xp_sspp[] = { }, { .name = "sspp_3", .id = SSPP_VIG3, .base = 0xa000, .len = 0x2ac, - .features = VIG_SDM845_MASK, + .features = VIG_SDM845_MASK_SDMA, .sblk = &dpu_vig_sblk_qseed3_3_0, .xin_id = 12, .type = SSPP_TYPE_VIG, @@ -106,7 +105,7 @@ static const struct dpu_sspp_cfg sc8280xp_sspp[] = { }, { .name = "sspp_8", .id = SSPP_DMA0, .base = 0x24000, .len = 0x2ac, - .features = DMA_SDM845_MASK, + .features = DMA_SDM845_MASK_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 1, .type = SSPP_TYPE_DMA, @@ -114,7 +113,7 @@ static const struct dpu_sspp_cfg sc8280xp_sspp[] = { }, { .name = "sspp_9", .id = SSPP_DMA1, .base = 0x26000, .len = 0x2ac, - .features = DMA_SDM845_MASK, + .features = DMA_SDM845_MASK_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 5, .type = SSPP_TYPE_DMA, @@ -122,7 +121,7 @@ static const struct dpu_sspp_cfg sc8280xp_sspp[] = { }, { .name = "sspp_10", .id = SSPP_DMA2, .base = 0x28000, .len = 0x2ac, - .features = DMA_CURSOR_SDM845_MASK, + .features = DMA_CURSOR_SDM845_MASK_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 9, .type = SSPP_TYPE_DMA, @@ -130,7 +129,7 @@ static const struct dpu_sspp_cfg sc8280xp_sspp[] = { }, { .name = "sspp_11", .id = SSPP_DMA3, .base = 0x2a000, .len = 0x2ac, - .features = DMA_CURSOR_SDM845_MASK, + .features = DMA_CURSOR_SDM845_MASK_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 13, .type = SSPP_TYPE_DMA, @@ -435,6 +434,7 @@ const struct dpu_mdss_cfg dpu_sc8280xp_cfg = { .mdss_ver = &sc8280xp_mdss_ver, .caps = &sc8280xp_dpu_caps, .mdp = &sc8280xp_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sc8280xp_ctl), .ctl = sc8280xp_ctl, .sspp_count = ARRAY_SIZE(sc8280xp_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h index a1779c5597ae..461294143a90 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_1_sm8450.h @@ -36,17 +36,16 @@ static const struct dpu_mdp_cfg sm8450_mdp = { }, }; -/* FIXME: get rid of DPU_CTL_SPLIT_DISPLAY in favour of proper ACTIVE_CTL support */ static const struct dpu_ctl_cfg sm8450_ctl[] = { { .name = "ctl_0", .id = CTL_0, .base = 0x15000, .len = 0x204, - .features = BIT(DPU_CTL_SPLIT_DISPLAY) | CTL_SC7280_MASK, + .features = CTL_SC7280_MASK, .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 9), }, { .name = "ctl_1", .id = CTL_1, .base = 0x16000, .len = 0x204, - .features = BIT(DPU_CTL_SPLIT_DISPLAY) | CTL_SC7280_MASK, + .features = CTL_SC7280_MASK, .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 10), }, { .name = "ctl_2", .id = CTL_2, @@ -257,13 +256,13 @@ static const struct dpu_pingpong_cfg sm8450_pp[] = { .merge_3d = MERGE_3D_2, .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), }, { - .name = "pingpong_6", .id = PINGPONG_6, + .name = "pingpong_cwb_0", .id = PINGPONG_CWB_0, .base = 0x65800, .len = 0, .features = BIT(DPU_PINGPONG_DITHER), .sblk = &sc7280_pp_sblk, .merge_3d = MERGE_3D_3, }, { - .name = "pingpong_7", .id = PINGPONG_7, + .name = "pingpong_cwb_1", .id = PINGPONG_CWB_1, .base = 0x65c00, .len = 0, .features = BIT(DPU_PINGPONG_DITHER), .sblk = &sc7280_pp_sblk, @@ -321,8 +320,8 @@ static const struct dpu_wb_cfg sm8450_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .clk_ctrl = DPU_CLK_CTRL_WB2, .xin_id = 6, .vbif_idx = VBIF_RT, @@ -412,6 +411,7 @@ const struct dpu_mdss_cfg dpu_sm8450_cfg = { .mdss_ver = &sm8450_mdss_ver, .caps = &sm8450_dpu_caps, .mdp = &sm8450_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sm8450_ctl), .ctl = sm8450_ctl, .sspp_count = ARRAY_SIZE(sm8450_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h index 907b4d7ceb47..c248b3b55c41 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_8_4_sa8775p.h @@ -35,17 +35,16 @@ static const struct dpu_mdp_cfg sa8775p_mdp = { }, }; -/* FIXME: get rid of DPU_CTL_SPLIT_DISPLAY in favour of proper ACTIVE_CTL support */ static const struct dpu_ctl_cfg sa8775p_ctl[] = { { .name = "ctl_0", .id = CTL_0, .base = 0x15000, .len = 0x204, - .features = BIT(DPU_CTL_SPLIT_DISPLAY) | CTL_SC7280_MASK, + .features = CTL_SC7280_MASK, .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 9), }, { .name = "ctl_1", .id = CTL_1, .base = 0x16000, .len = 0x204, - .features = BIT(DPU_CTL_SPLIT_DISPLAY) | CTL_SC7280_MASK, + .features = CTL_SC7280_MASK, .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 10), }, { .name = "ctl_2", .id = CTL_2, @@ -256,13 +255,13 @@ static const struct dpu_pingpong_cfg sa8775p_pp[] = { .merge_3d = MERGE_3D_2, .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), }, { - .name = "pingpong_6", .id = PINGPONG_6, + .name = "pingpong_6", .id = PINGPONG_CWB_0, .base = 0x65800, .len = 0, .features = BIT(DPU_PINGPONG_DITHER), .sblk = &sc7280_pp_sblk, .merge_3d = MERGE_3D_3, }, { - .name = "pingpong_7", .id = PINGPONG_7, + .name = "pingpong_7", .id = PINGPONG_CWB_1, .base = 0x65c00, .len = 0, .features = BIT(DPU_PINGPONG_DITHER), .sblk = &sc7280_pp_sblk, @@ -458,7 +457,7 @@ const struct dpu_mdss_cfg dpu_sa8775p_cfg = { .mdss_ver = &sa8775p_mdss_ver, .caps = &sa8775p_dpu_caps, .mdp = &sa8775p_mdp, - .cdm = &sc7280_cdm, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sa8775p_ctl), .ctl = sa8775p_ctl, .sspp_count = ARRAY_SIZE(sa8775p_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h index a1dbbf5c652f..59c7fdf28e89 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_0_sm8550.h @@ -27,17 +27,16 @@ static const struct dpu_mdp_cfg sm8550_mdp = { }, }; -/* FIXME: get rid of DPU_CTL_SPLIT_DISPLAY in favour of proper ACTIVE_CTL support */ static const struct dpu_ctl_cfg sm8550_ctl[] = { { .name = "ctl_0", .id = CTL_0, .base = 0x15000, .len = 0x290, - .features = CTL_SM8550_MASK | BIT(DPU_CTL_SPLIT_DISPLAY), + .features = CTL_SM8550_MASK, .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 9), }, { .name = "ctl_1", .id = CTL_1, .base = 0x16000, .len = 0x290, - .features = CTL_SM8550_MASK | BIT(DPU_CTL_SPLIT_DISPLAY), + .features = CTL_SM8550_MASK, .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 10), }, { .name = "ctl_2", .id = CTL_2, @@ -66,70 +65,70 @@ static const struct dpu_sspp_cfg sm8550_sspp[] = { { .name = "sspp_0", .id = SSPP_VIG0, .base = 0x4000, .len = 0x344, - .features = VIG_SDM845_MASK, + .features = VIG_SDM845_MASK_SDMA, .sblk = &dpu_vig_sblk_qseed3_3_2, .xin_id = 0, .type = SSPP_TYPE_VIG, }, { .name = "sspp_1", .id = SSPP_VIG1, .base = 0x6000, .len = 0x344, - .features = VIG_SDM845_MASK, + .features = VIG_SDM845_MASK_SDMA, .sblk = &dpu_vig_sblk_qseed3_3_2, .xin_id = 4, .type = SSPP_TYPE_VIG, }, { .name = "sspp_2", .id = SSPP_VIG2, .base = 0x8000, .len = 0x344, - .features = VIG_SDM845_MASK, + .features = VIG_SDM845_MASK_SDMA, .sblk = &dpu_vig_sblk_qseed3_3_2, .xin_id = 8, .type = SSPP_TYPE_VIG, }, { .name = "sspp_3", .id = SSPP_VIG3, .base = 0xa000, .len = 0x344, - .features = VIG_SDM845_MASK, + .features = VIG_SDM845_MASK_SDMA, .sblk = &dpu_vig_sblk_qseed3_3_2, .xin_id = 12, .type = SSPP_TYPE_VIG, }, { .name = "sspp_8", .id = SSPP_DMA0, .base = 0x24000, .len = 0x344, - .features = DMA_SDM845_MASK, + .features = DMA_SDM845_MASK_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 1, .type = SSPP_TYPE_DMA, }, { .name = "sspp_9", .id = SSPP_DMA1, .base = 0x26000, .len = 0x344, - .features = DMA_SDM845_MASK, + .features = DMA_SDM845_MASK_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 5, .type = SSPP_TYPE_DMA, }, { .name = "sspp_10", .id = SSPP_DMA2, .base = 0x28000, .len = 0x344, - .features = DMA_SDM845_MASK, + .features = DMA_SDM845_MASK_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 9, .type = SSPP_TYPE_DMA, }, { .name = "sspp_11", .id = SSPP_DMA3, .base = 0x2a000, .len = 0x344, - .features = DMA_SDM845_MASK, + .features = DMA_SDM845_MASK_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 13, .type = SSPP_TYPE_DMA, }, { .name = "sspp_12", .id = SSPP_DMA4, .base = 0x2c000, .len = 0x344, - .features = DMA_CURSOR_SDM845_MASK, + .features = DMA_CURSOR_SDM845_MASK_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 14, .type = SSPP_TYPE_DMA, }, { .name = "sspp_13", .id = SSPP_DMA5, .base = 0x2e000, .len = 0x344, - .features = DMA_CURSOR_SDM845_MASK, + .features = DMA_CURSOR_SDM845_MASK_SDMA, .sblk = &dpu_dma_sblk, .xin_id = 15, .type = SSPP_TYPE_DMA, @@ -253,13 +252,13 @@ static const struct dpu_pingpong_cfg sm8550_pp[] = { .merge_3d = MERGE_3D_2, .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), }, { - .name = "pingpong_6", .id = PINGPONG_6, + .name = "pingpong_cwb_0", .id = PINGPONG_CWB_0, .base = 0x66000, .len = 0, .features = BIT(DPU_PINGPONG_DITHER), .sblk = &sc7280_pp_sblk, .merge_3d = MERGE_3D_3, }, { - .name = "pingpong_7", .id = PINGPONG_7, + .name = "pingpong_cwb_1", .id = PINGPONG_CWB_1, .base = 0x66400, .len = 0, .features = BIT(DPU_PINGPONG_DITHER), .sblk = &sc7280_pp_sblk, @@ -317,8 +316,8 @@ static const struct dpu_wb_cfg sm8550_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .xin_id = 6, .vbif_idx = VBIF_RT, .maxlinewidth = 4096, @@ -407,6 +406,7 @@ const struct dpu_mdss_cfg dpu_sm8550_cfg = { .mdss_ver = &sm8550_mdss_ver, .caps = &sm8550_dpu_caps, .mdp = &sm8550_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(sm8550_ctl), .ctl = sm8550_ctl, .sspp_count = ARRAY_SIZE(sm8550_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_1_sar2130p.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_1_sar2130p.h new file mode 100644 index 000000000000..5667d055fbd1 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_1_sar2130p.h @@ -0,0 +1,433 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2022. Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2015-2018, 2020 The Linux Foundation. All rights reserved. + */ + +#ifndef _DPU_9_1_SAR2130P_H +#define _DPU_9_1_SAR2130P_H + +static const struct dpu_caps sar2130p_dpu_caps = { + .max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH, + .max_mixer_blendstages = 0xb, + .has_src_split = true, + .has_dim_layer = true, + .has_idle_pc = true, + .has_3d_merge = true, + .max_linewidth = 5120, + .pixel_ram_size = DEFAULT_PIXEL_RAM_SIZE, +}; + +static const struct dpu_mdp_cfg sar2130p_mdp = { + .name = "top_0", + .base = 0, .len = 0x494, + .features = BIT(DPU_MDP_PERIPH_0_REMOVED), + .clk_ctrls = { + [DPU_CLK_CTRL_REG_DMA] = { .reg_off = 0x2bc, .bit_off = 20 }, + }, +}; + +static const struct dpu_ctl_cfg sar2130p_ctl[] = { + { + .name = "ctl_0", .id = CTL_0, + .base = 0x15000, .len = 0x290, + .features = CTL_SM8550_MASK, + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 9), + }, { + .name = "ctl_1", .id = CTL_1, + .base = 0x16000, .len = 0x290, + .features = CTL_SM8550_MASK, + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 10), + }, { + .name = "ctl_2", .id = CTL_2, + .base = 0x17000, .len = 0x290, + .features = CTL_SM8550_MASK, + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 11), + }, { + .name = "ctl_3", .id = CTL_3, + .base = 0x18000, .len = 0x290, + .features = CTL_SM8550_MASK, + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 12), + }, { + .name = "ctl_4", .id = CTL_4, + .base = 0x19000, .len = 0x290, + .features = CTL_SM8550_MASK, + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 13), + }, { + .name = "ctl_5", .id = CTL_5, + .base = 0x1a000, .len = 0x290, + .features = CTL_SM8550_MASK, + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 23), + }, +}; + +static const struct dpu_sspp_cfg sar2130p_sspp[] = { + { + .name = "sspp_0", .id = SSPP_VIG0, + .base = 0x4000, .len = 0x344, + .features = VIG_SDM845_MASK_SDMA, + .sblk = &dpu_vig_sblk_qseed3_3_2, + .xin_id = 0, + .type = SSPP_TYPE_VIG, + }, { + .name = "sspp_1", .id = SSPP_VIG1, + .base = 0x6000, .len = 0x344, + .features = VIG_SDM845_MASK_SDMA, + .sblk = &dpu_vig_sblk_qseed3_3_2, + .xin_id = 4, + .type = SSPP_TYPE_VIG, + }, { + .name = "sspp_2", .id = SSPP_VIG2, + .base = 0x8000, .len = 0x344, + .features = VIG_SDM845_MASK_SDMA, + .sblk = &dpu_vig_sblk_qseed3_3_2, + .xin_id = 8, + .type = SSPP_TYPE_VIG, + }, { + .name = "sspp_3", .id = SSPP_VIG3, + .base = 0xa000, .len = 0x344, + .features = VIG_SDM845_MASK_SDMA, + .sblk = &dpu_vig_sblk_qseed3_3_2, + .xin_id = 12, + .type = SSPP_TYPE_VIG, + }, { + .name = "sspp_8", .id = SSPP_DMA0, + .base = 0x24000, .len = 0x344, + .features = DMA_SDM845_MASK_SDMA, + .sblk = &dpu_dma_sblk, + .xin_id = 1, + .type = SSPP_TYPE_DMA, + }, { + .name = "sspp_9", .id = SSPP_DMA1, + .base = 0x26000, .len = 0x344, + .features = DMA_SDM845_MASK_SDMA, + .sblk = &dpu_dma_sblk, + .xin_id = 5, + .type = SSPP_TYPE_DMA, + }, { + .name = "sspp_10", .id = SSPP_DMA2, + .base = 0x28000, .len = 0x344, + .features = DMA_SDM845_MASK_SDMA, + .sblk = &dpu_dma_sblk, + .xin_id = 9, + .type = SSPP_TYPE_DMA, + }, { + .name = "sspp_11", .id = SSPP_DMA3, + .base = 0x2a000, .len = 0x344, + .features = DMA_SDM845_MASK_SDMA, + .sblk = &dpu_dma_sblk, + .xin_id = 13, + .type = SSPP_TYPE_DMA, + }, { + .name = "sspp_12", .id = SSPP_DMA4, + .base = 0x2c000, .len = 0x344, + .features = DMA_CURSOR_SDM845_MASK_SDMA, + .sblk = &dpu_dma_sblk, + .xin_id = 14, + .type = SSPP_TYPE_DMA, + }, { + .name = "sspp_13", .id = SSPP_DMA5, + .base = 0x2e000, .len = 0x344, + .features = DMA_CURSOR_SDM845_MASK_SDMA, + .sblk = &dpu_dma_sblk, + .xin_id = 15, + .type = SSPP_TYPE_DMA, + }, +}; + +static const struct dpu_lm_cfg sar2130p_lm[] = { + { + .name = "lm_0", .id = LM_0, + .base = 0x44000, .len = 0x320, + .features = MIXER_SDM845_MASK, + .sblk = &sdm845_lm_sblk, + .lm_pair = LM_1, + .pingpong = PINGPONG_0, + .dspp = DSPP_0, + }, { + .name = "lm_1", .id = LM_1, + .base = 0x45000, .len = 0x320, + .features = MIXER_SDM845_MASK, + .sblk = &sdm845_lm_sblk, + .lm_pair = LM_0, + .pingpong = PINGPONG_1, + .dspp = DSPP_1, + }, { + .name = "lm_2", .id = LM_2, + .base = 0x46000, .len = 0x320, + .features = MIXER_SDM845_MASK, + .sblk = &sdm845_lm_sblk, + .lm_pair = LM_3, + .pingpong = PINGPONG_2, + .dspp = DSPP_2, + }, { + .name = "lm_3", .id = LM_3, + .base = 0x47000, .len = 0x320, + .features = MIXER_SDM845_MASK, + .sblk = &sdm845_lm_sblk, + .lm_pair = LM_2, + .pingpong = PINGPONG_3, + .dspp = DSPP_3, + }, { + .name = "lm_4", .id = LM_4, + .base = 0x48000, .len = 0x320, + .features = MIXER_SDM845_MASK, + .sblk = &sdm845_lm_sblk, + .lm_pair = LM_5, + .pingpong = PINGPONG_4, + }, { + .name = "lm_5", .id = LM_5, + .base = 0x49000, .len = 0x320, + .features = MIXER_SDM845_MASK, + .sblk = &sdm845_lm_sblk, + .lm_pair = LM_4, + .pingpong = PINGPONG_5, + }, +}; + +static const struct dpu_dspp_cfg sar2130p_dspp[] = { + { + .name = "dspp_0", .id = DSPP_0, + .base = 0x54000, .len = 0x1800, + .features = DSPP_SC7180_MASK, + .sblk = &sdm845_dspp_sblk, + }, { + .name = "dspp_1", .id = DSPP_1, + .base = 0x56000, .len = 0x1800, + .features = DSPP_SC7180_MASK, + .sblk = &sdm845_dspp_sblk, + }, { + .name = "dspp_2", .id = DSPP_2, + .base = 0x58000, .len = 0x1800, + .features = DSPP_SC7180_MASK, + .sblk = &sdm845_dspp_sblk, + }, { + .name = "dspp_3", .id = DSPP_3, + .base = 0x5a000, .len = 0x1800, + .features = DSPP_SC7180_MASK, + .sblk = &sdm845_dspp_sblk, + }, +}; +static const struct dpu_pingpong_cfg sar2130p_pp[] = { + { + .name = "pingpong_0", .id = PINGPONG_0, + .base = 0x69000, .len = 0, + .features = BIT(DPU_PINGPONG_DITHER), + .sblk = &sc7280_pp_sblk, + .merge_3d = MERGE_3D_0, + .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 8), + }, { + .name = "pingpong_1", .id = PINGPONG_1, + .base = 0x6a000, .len = 0, + .features = BIT(DPU_PINGPONG_DITHER), + .sblk = &sc7280_pp_sblk, + .merge_3d = MERGE_3D_0, + .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 9), + }, { + .name = "pingpong_2", .id = PINGPONG_2, + .base = 0x6b000, .len = 0, + .features = BIT(DPU_PINGPONG_DITHER), + .sblk = &sc7280_pp_sblk, + .merge_3d = MERGE_3D_1, + .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 10), + }, { + .name = "pingpong_3", .id = PINGPONG_3, + .base = 0x6c000, .len = 0, + .features = BIT(DPU_PINGPONG_DITHER), + .sblk = &sc7280_pp_sblk, + .merge_3d = MERGE_3D_1, + .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 11), + }, { + .name = "pingpong_4", .id = PINGPONG_4, + .base = 0x6d000, .len = 0, + .features = BIT(DPU_PINGPONG_DITHER), + .sblk = &sc7280_pp_sblk, + .merge_3d = MERGE_3D_2, + .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 30), + }, { + .name = "pingpong_5", .id = PINGPONG_5, + .base = 0x6e000, .len = 0, + .features = BIT(DPU_PINGPONG_DITHER), + .sblk = &sc7280_pp_sblk, + .merge_3d = MERGE_3D_2, + .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), + }, { + .name = "pingpong_cwb_0", .id = PINGPONG_CWB_0, + .base = 0x66000, .len = 0, + .features = BIT(DPU_PINGPONG_DITHER), + .sblk = &sc7280_pp_sblk, + .merge_3d = MERGE_3D_3, + }, { + .name = "pingpong_cwb_1", .id = PINGPONG_CWB_1, + .base = 0x66400, .len = 0, + .features = BIT(DPU_PINGPONG_DITHER), + .sblk = &sc7280_pp_sblk, + .merge_3d = MERGE_3D_3, + }, +}; + +static const struct dpu_merge_3d_cfg sar2130p_merge_3d[] = { + { + .name = "merge_3d_0", .id = MERGE_3D_0, + .base = 0x4e000, .len = 0x8, + }, { + .name = "merge_3d_1", .id = MERGE_3D_1, + .base = 0x4f000, .len = 0x8, + }, { + .name = "merge_3d_2", .id = MERGE_3D_2, + .base = 0x50000, .len = 0x8, + }, { + .name = "merge_3d_3", .id = MERGE_3D_3, + .base = 0x66700, .len = 0x8, + }, +}; + +/* + * NOTE: Each display compression engine (DCE) contains dual hard + * slice DSC encoders so both share same base address but with + * its own different sub block address. + */ +static const struct dpu_dsc_cfg sar2130p_dsc[] = { + { + .name = "dce_0_0", .id = DSC_0, + .base = 0x80000, .len = 0x4, + .features = BIT(DPU_DSC_HW_REV_1_2), + .sblk = &dsc_sblk_0, + }, { + .name = "dce_0_1", .id = DSC_1, + .base = 0x80000, .len = 0x4, + .features = BIT(DPU_DSC_HW_REV_1_2), + .sblk = &dsc_sblk_1, + }, { + .name = "dce_1_0", .id = DSC_2, + .base = 0x81000, .len = 0x4, + .features = BIT(DPU_DSC_HW_REV_1_2) | BIT(DPU_DSC_NATIVE_42x_EN), + .sblk = &dsc_sblk_0, + }, { + .name = "dce_1_1", .id = DSC_3, + .base = 0x81000, .len = 0x4, + .features = BIT(DPU_DSC_HW_REV_1_2) | BIT(DPU_DSC_NATIVE_42x_EN), + .sblk = &dsc_sblk_1, + }, +}; + +static const struct dpu_wb_cfg sar2130p_wb[] = { + { + .name = "wb_2", .id = WB_2, + .base = 0x65000, .len = 0x2c8, + .features = WB_SM8250_MASK, + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), + .xin_id = 6, + .vbif_idx = VBIF_RT, + .maxlinewidth = 4096, + .intr_wb_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 4), + }, +}; + +static const struct dpu_intf_cfg sar2130p_intf[] = { + { + .name = "intf_0", .id = INTF_0, + .base = 0x34000, .len = 0x280, + .features = INTF_SC7280_MASK, + .type = INTF_DP, + .controller_id = MSM_DP_CONTROLLER_0, + .prog_fetch_lines_worst_case = 24, + .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 24), + .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 25), + }, { + .name = "intf_1", .id = INTF_1, + .base = 0x35000, .len = 0x300, + .features = INTF_SC7280_MASK, + .type = INTF_DSI, + .controller_id = MSM_DSI_CONTROLLER_0, + .prog_fetch_lines_worst_case = 24, + .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 26), + .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 27), + .intr_tear_rd_ptr = DPU_IRQ_IDX(MDP_INTF1_TEAR_INTR, 2), + }, { + .name = "intf_2", .id = INTF_2, + .base = 0x36000, .len = 0x300, + .features = INTF_SC7280_MASK, + .type = INTF_DSI, + .controller_id = MSM_DSI_CONTROLLER_1, + .prog_fetch_lines_worst_case = 24, + .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 28), + .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 29), + .intr_tear_rd_ptr = DPU_IRQ_IDX(MDP_INTF2_TEAR_INTR, 2), + }, { + .name = "intf_3", .id = INTF_3, + .base = 0x37000, .len = 0x280, + .features = INTF_SC7280_MASK, + .type = INTF_DP, + .controller_id = MSM_DP_CONTROLLER_1, + .prog_fetch_lines_worst_case = 24, + .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 30), + .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 31), + }, +}; + +static const struct dpu_perf_cfg sar2130p_perf_data = { + .max_bw_low = 13600000, + .max_bw_high = 18200000, + .min_core_ib = 2500000, + .min_llcc_ib = 0, + .min_dram_ib = 800000, + .min_prefill_lines = 35, + /* FIXME: lut tables */ + .danger_lut_tbl = {0x3ffff, 0x3ffff, 0x0}, + .safe_lut_tbl = {0xfe00, 0xfe00, 0xffff}, + .qos_lut_tbl = { + {.nentry = ARRAY_SIZE(sc7180_qos_linear), + .entries = sc7180_qos_linear + }, + {.nentry = ARRAY_SIZE(sc7180_qos_macrotile), + .entries = sc7180_qos_macrotile + }, + {.nentry = ARRAY_SIZE(sc7180_qos_nrt), + .entries = sc7180_qos_nrt + }, + /* TODO: macrotile-qseed is different from macrotile */ + }, + .cdp_cfg = { + {.rd_enable = 0, .wr_enable = 0}, + {.rd_enable = 0, .wr_enable = 0} + }, + .clk_inefficiency_factor = 105, + .bw_inefficiency_factor = 120, +}; + +static const struct dpu_mdss_version sar2130p_mdss_ver = { + .core_major_ver = 9, + .core_minor_ver = 1, +}; + +const struct dpu_mdss_cfg dpu_sar2130p_cfg = { + .mdss_ver = &sar2130p_mdss_ver, + .caps = &sar2130p_dpu_caps, + .mdp = &sar2130p_mdp, + .cdm = &dpu_cdm_5_x, + .ctl_count = ARRAY_SIZE(sar2130p_ctl), + .ctl = sar2130p_ctl, + .sspp_count = ARRAY_SIZE(sar2130p_sspp), + .sspp = sar2130p_sspp, + .mixer_count = ARRAY_SIZE(sar2130p_lm), + .mixer = sar2130p_lm, + .dspp_count = ARRAY_SIZE(sar2130p_dspp), + .dspp = sar2130p_dspp, + .pingpong_count = ARRAY_SIZE(sar2130p_pp), + .pingpong = sar2130p_pp, + .dsc_count = ARRAY_SIZE(sar2130p_dsc), + .dsc = sar2130p_dsc, + .merge_3d_count = ARRAY_SIZE(sar2130p_merge_3d), + .merge_3d = sar2130p_merge_3d, + .wb_count = ARRAY_SIZE(sar2130p_wb), + .wb = sar2130p_wb, + .intf_count = ARRAY_SIZE(sar2130p_intf), + .intf = sar2130p_intf, + .vbif_count = ARRAY_SIZE(sm8550_vbif), + .vbif = sm8550_vbif, + .perf = &sar2130p_perf_data, +}; + +#endif diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h index 4f110be6b750..52cc10aec1f9 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_9_2_x1e80100.h @@ -26,17 +26,16 @@ static const struct dpu_mdp_cfg x1e80100_mdp = { }, }; -/* FIXME: get rid of DPU_CTL_SPLIT_DISPLAY in favour of proper ACTIVE_CTL support */ static const struct dpu_ctl_cfg x1e80100_ctl[] = { { .name = "ctl_0", .id = CTL_0, .base = 0x15000, .len = 0x290, - .features = CTL_SM8550_MASK | BIT(DPU_CTL_SPLIT_DISPLAY), + .features = CTL_SM8550_MASK, .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 9), }, { .name = "ctl_1", .id = CTL_1, .base = 0x16000, .len = 0x290, - .features = CTL_SM8550_MASK | BIT(DPU_CTL_SPLIT_DISPLAY), + .features = CTL_SM8550_MASK, .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 10), }, { .name = "ctl_2", .id = CTL_2, @@ -253,13 +252,13 @@ static const struct dpu_pingpong_cfg x1e80100_pp[] = { .merge_3d = MERGE_3D_2, .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), }, { - .name = "pingpong_6", .id = PINGPONG_6, + .name = "pingpong_cwb_0", .id = PINGPONG_CWB_0, .base = 0x66000, .len = 0, .features = BIT(DPU_PINGPONG_DITHER), .sblk = &sc7280_pp_sblk, .merge_3d = MERGE_3D_3, }, { - .name = "pingpong_7", .id = PINGPONG_7, + .name = "pingpong_cwb_1", .id = PINGPONG_CWB_1, .base = 0x66400, .len = 0, .features = BIT(DPU_PINGPONG_DITHER), .sblk = &sc7280_pp_sblk, @@ -317,8 +316,8 @@ static const struct dpu_wb_cfg x1e80100_wb[] = { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, .features = WB_SM8250_MASK, - .format_list = wb2_formats_rgb, - .num_formats = ARRAY_SIZE(wb2_formats_rgb), + .format_list = wb2_formats_rgb_yuv, + .num_formats = ARRAY_SIZE(wb2_formats_rgb_yuv), .xin_id = 6, .vbif_idx = VBIF_RT, .maxlinewidth = 4096, @@ -453,6 +452,7 @@ const struct dpu_mdss_cfg dpu_x1e80100_cfg = { .mdss_ver = &x1e80100_mdss_ver, .caps = &x1e80100_dpu_caps, .mdp = &x1e80100_mdp, + .cdm = &dpu_cdm_5_x, .ctl_count = ARRAY_SIZE(x1e80100_ctl), .ctl = x1e80100_ctl, .sspp_count = ARRAY_SIZE(x1e80100_sspp), diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c index 6f0a37f954fe..0fb5789c60d0 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c @@ -118,26 +118,38 @@ static void _dpu_core_perf_calc_crtc(const struct dpu_core_perf *core_perf, return; } - memset(perf, 0, sizeof(struct dpu_core_perf_params)); - - if (core_perf->perf_tune.mode == DPU_PERF_MODE_MINIMUM) { - perf->bw_ctl = 0; - perf->max_per_pipe_ib = 0; - perf->core_clk_rate = 0; - } else if (core_perf->perf_tune.mode == DPU_PERF_MODE_FIXED) { - perf->bw_ctl = core_perf->fix_core_ab_vote; - perf->max_per_pipe_ib = core_perf->fix_core_ib_vote; - perf->core_clk_rate = core_perf->fix_core_clk_rate; - } else { - perf->bw_ctl = _dpu_core_perf_calc_bw(perf_cfg, crtc); - perf->max_per_pipe_ib = perf_cfg->min_dram_ib; - perf->core_clk_rate = _dpu_core_perf_calc_clk(perf_cfg, crtc, state); - } - + perf->bw_ctl = _dpu_core_perf_calc_bw(perf_cfg, crtc); + perf->max_per_pipe_ib = perf_cfg->min_dram_ib; + perf->core_clk_rate = _dpu_core_perf_calc_clk(perf_cfg, crtc, state); DRM_DEBUG_ATOMIC( - "crtc=%d clk_rate=%llu core_ib=%llu core_ab=%llu\n", + "crtc=%d clk_rate=%llu core_ib=%u core_ab=%u\n", crtc->base.id, perf->core_clk_rate, - perf->max_per_pipe_ib, perf->bw_ctl); + perf->max_per_pipe_ib, + (u32)DIV_ROUND_UP_ULL(perf->bw_ctl, 1000)); +} + +static void dpu_core_perf_aggregate(struct drm_device *ddev, + enum dpu_crtc_client_type curr_client_type, + struct dpu_core_perf_params *perf) +{ + struct dpu_crtc_state *dpu_cstate; + struct drm_crtc *tmp_crtc; + + drm_for_each_crtc(tmp_crtc, ddev) { + if (tmp_crtc->enabled && + curr_client_type == dpu_crtc_get_client_type(tmp_crtc)) { + dpu_cstate = to_dpu_crtc_state(tmp_crtc->state); + + perf->max_per_pipe_ib = max(perf->max_per_pipe_ib, + dpu_cstate->new_perf.max_per_pipe_ib); + + perf->bw_ctl += dpu_cstate->new_perf.bw_ctl; + + DRM_DEBUG_ATOMIC("crtc=%d bw=%llu\n", + tmp_crtc->base.id, + dpu_cstate->new_perf.bw_ctl); + } + } } /** @@ -150,11 +162,9 @@ int dpu_core_perf_crtc_check(struct drm_crtc *crtc, struct drm_crtc_state *state) { u32 bw, threshold; - u64 bw_sum_of_intfs = 0; - enum dpu_crtc_client_type curr_client_type; struct dpu_crtc_state *dpu_cstate; - struct drm_crtc *tmp_crtc; struct dpu_kms *kms; + struct dpu_core_perf_params perf = { 0 }; if (!crtc || !state) { DPU_ERROR("invalid crtc\n"); @@ -172,80 +182,56 @@ int dpu_core_perf_crtc_check(struct drm_crtc *crtc, /* obtain new values */ _dpu_core_perf_calc_crtc(&kms->perf, crtc, state, &dpu_cstate->new_perf); - bw_sum_of_intfs = dpu_cstate->new_perf.bw_ctl; - curr_client_type = dpu_crtc_get_client_type(crtc); - - drm_for_each_crtc(tmp_crtc, crtc->dev) { - if (tmp_crtc->enabled && - dpu_crtc_get_client_type(tmp_crtc) == curr_client_type && - tmp_crtc != crtc) { - struct dpu_crtc_state *tmp_cstate = - to_dpu_crtc_state(tmp_crtc->state); - - DRM_DEBUG_ATOMIC("crtc:%d bw:%llu ctrl:%d\n", - tmp_crtc->base.id, tmp_cstate->new_perf.bw_ctl, - tmp_cstate->bw_control); + dpu_core_perf_aggregate(crtc->dev, dpu_crtc_get_client_type(crtc), &perf); - bw_sum_of_intfs += tmp_cstate->new_perf.bw_ctl; - } - - /* convert bandwidth to kb */ - bw = DIV_ROUND_UP_ULL(bw_sum_of_intfs, 1000); - DRM_DEBUG_ATOMIC("calculated bandwidth=%uk\n", bw); + /* convert bandwidth to kb */ + bw = DIV_ROUND_UP_ULL(perf.bw_ctl, 1000); + DRM_DEBUG_ATOMIC("calculated bandwidth=%uk\n", bw); - threshold = kms->perf.perf_cfg->max_bw_high; + threshold = kms->perf.perf_cfg->max_bw_high; - DRM_DEBUG_ATOMIC("final threshold bw limit = %d\n", threshold); + DRM_DEBUG_ATOMIC("final threshold bw limit = %d\n", threshold); - if (!threshold) { - DPU_ERROR("no bandwidth limits specified\n"); - return -E2BIG; - } else if (bw > threshold) { - DPU_ERROR("exceeds bandwidth: %ukb > %ukb\n", bw, - threshold); - return -E2BIG; - } + if (!threshold) { + DPU_ERROR("no bandwidth limits specified\n"); + return -E2BIG; + } else if (bw > threshold) { + DPU_ERROR("exceeds bandwidth: %ukb > %ukb\n", bw, + threshold); + return -E2BIG; } return 0; } static int _dpu_core_perf_crtc_update_bus(struct dpu_kms *kms, - struct drm_crtc *crtc) + struct drm_crtc *crtc) { struct dpu_core_perf_params perf = { 0 }; - enum dpu_crtc_client_type curr_client_type - = dpu_crtc_get_client_type(crtc); - struct drm_crtc *tmp_crtc; - struct dpu_crtc_state *dpu_cstate; int i, ret = 0; - u64 avg_bw; + u32 avg_bw; + u32 peak_bw; if (!kms->num_paths) return 0; - drm_for_each_crtc(tmp_crtc, crtc->dev) { - if (tmp_crtc->enabled && - curr_client_type == - dpu_crtc_get_client_type(tmp_crtc)) { - dpu_cstate = to_dpu_crtc_state(tmp_crtc->state); - - perf.max_per_pipe_ib = max(perf.max_per_pipe_ib, - dpu_cstate->new_perf.max_per_pipe_ib); - - perf.bw_ctl += dpu_cstate->new_perf.bw_ctl; + if (kms->perf.perf_tune.mode == DPU_PERF_MODE_MINIMUM) { + avg_bw = 0; + peak_bw = 0; + } else if (kms->perf.perf_tune.mode == DPU_PERF_MODE_FIXED) { + avg_bw = kms->perf.fix_core_ab_vote; + peak_bw = kms->perf.fix_core_ib_vote; + } else { + dpu_core_perf_aggregate(crtc->dev, dpu_crtc_get_client_type(crtc), &perf); - DRM_DEBUG_ATOMIC("crtc=%d bw=%llu paths:%d\n", - tmp_crtc->base.id, - dpu_cstate->new_perf.bw_ctl, kms->num_paths); - } + avg_bw = div_u64(perf.bw_ctl, 1000); /*Bps_to_icc*/ + peak_bw = perf.max_per_pipe_ib; } - avg_bw = perf.bw_ctl; - do_div(avg_bw, (kms->num_paths * 1000)); /*Bps_to_icc*/ + avg_bw /= kms->num_paths; for (i = 0; i < kms->num_paths; i++) - icc_set_bw(kms->path[i], avg_bw, perf.max_per_pipe_ib); + icc_set_bw(kms->path[i], avg_bw, peak_bw); return ret; } @@ -476,9 +462,9 @@ int dpu_core_perf_debugfs_init(struct dpu_kms *dpu_kms, struct dentry *parent) &perf->core_clk_rate); debugfs_create_u32("enable_bw_release", 0600, entry, (u32 *)&perf->enable_bw_release); - debugfs_create_u32("threshold_low", 0400, entry, + debugfs_create_u32("low_core_ab", 0400, entry, (u32 *)&perf->perf_cfg->max_bw_low); - debugfs_create_u32("threshold_high", 0400, entry, + debugfs_create_u32("max_core_ab", 0400, entry, (u32 *)&perf->perf_cfg->max_bw_high); debugfs_create_u32("min_core_ib", 0400, entry, (u32 *)&perf->perf_cfg->min_core_ib); @@ -490,9 +476,9 @@ int dpu_core_perf_debugfs_init(struct dpu_kms *dpu_kms, struct dentry *parent) (u32 *)perf, &dpu_core_perf_mode_fops); debugfs_create_u64("fix_core_clk_rate", 0600, entry, &perf->fix_core_clk_rate); - debugfs_create_u64("fix_core_ib_vote", 0600, entry, + debugfs_create_u32("fix_core_ib_vote", 0600, entry, &perf->fix_core_ib_vote); - debugfs_create_u64("fix_core_ab_vote", 0600, entry, + debugfs_create_u32("fix_core_ab_vote", 0600, entry, &perf->fix_core_ab_vote); return 0; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h index 451bf8021114..d2f21d34e501 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h @@ -19,7 +19,7 @@ * @core_clk_rate: core clock rate request */ struct dpu_core_perf_params { - u64 max_per_pipe_ib; + u32 max_per_pipe_ib; u64 bw_ctl; u64 core_clk_rate; }; @@ -40,8 +40,8 @@ struct dpu_core_perf_tune { * @perf_tune: debug control for performance tuning * @enable_bw_release: debug control for bandwidth release * @fix_core_clk_rate: fixed core clock request in Hz used in mode 2 - * @fix_core_ib_vote: fixed core ib vote in bps used in mode 2 - * @fix_core_ab_vote: fixed core ab vote in bps used in mode 2 + * @fix_core_ib_vote: fixed core ib vote in KBps used in mode 2 + * @fix_core_ab_vote: fixed core ab vote in KBps used in mode 2 */ struct dpu_core_perf { const struct dpu_perf_cfg *perf_cfg; @@ -50,8 +50,8 @@ struct dpu_core_perf { struct dpu_core_perf_tune perf_tune; u32 enable_bw_release; u64 fix_core_clk_rate; - u64 fix_core_ib_vote; - u64 fix_core_ab_vote; + u32 fix_core_ib_vote; + u32 fix_core_ab_vote; }; int dpu_core_perf_crtc_check(struct drm_crtc *crtc, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c index ad3462476a14..a4b0fe0d9899 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c @@ -445,9 +445,9 @@ static void _dpu_crtc_blend_setup_mixer(struct drm_crtc *crtc, uint32_t lm_idx; bool bg_alpha_enable = false; - DECLARE_BITMAP(fetch_active, SSPP_MAX); + DECLARE_BITMAP(active_fetch, SSPP_MAX); - memset(fetch_active, 0, sizeof(fetch_active)); + memset(active_fetch, 0, sizeof(active_fetch)); drm_atomic_crtc_for_each_plane(plane, crtc) { state = plane->state; if (!state) @@ -464,7 +464,7 @@ static void _dpu_crtc_blend_setup_mixer(struct drm_crtc *crtc, if (pstate->stage == DPU_STAGE_BASE && format->alpha_enable) bg_alpha_enable = true; - set_bit(pstate->pipe.sspp->idx, fetch_active); + set_bit(pstate->pipe.sspp->idx, active_fetch); _dpu_crtc_blend_setup_pipe(crtc, plane, mixer, cstate->num_mixers, pstate->stage, @@ -472,7 +472,7 @@ static void _dpu_crtc_blend_setup_mixer(struct drm_crtc *crtc, &pstate->pipe, 0, stage_cfg); if (pstate->r_pipe.sspp) { - set_bit(pstate->r_pipe.sspp->idx, fetch_active); + set_bit(pstate->r_pipe.sspp->idx, active_fetch); _dpu_crtc_blend_setup_pipe(crtc, plane, mixer, cstate->num_mixers, pstate->stage, @@ -492,8 +492,8 @@ static void _dpu_crtc_blend_setup_mixer(struct drm_crtc *crtc, } } - if (ctl->ops.set_active_pipes) - ctl->ops.set_active_pipes(ctl, fetch_active); + if (ctl->ops.set_active_fetch_pipes) + ctl->ops.set_active_fetch_pipes(ctl, active_fetch); _dpu_crtc_program_lm_output_roi(crtc); } @@ -519,6 +519,8 @@ static void _dpu_crtc_blend_setup(struct drm_crtc *crtc) if (mixer[i].lm_ctl->ops.clear_all_blendstages) mixer[i].lm_ctl->ops.clear_all_blendstages( mixer[i].lm_ctl); + if (mixer[i].lm_ctl->ops.set_active_fetch_pipes) + mixer[i].lm_ctl->ops.set_active_fetch_pipes(mixer[i].lm_ctl, NULL); } /* initialize stage cfg */ @@ -953,6 +955,45 @@ static int _dpu_crtc_wait_for_frame_done(struct drm_crtc *crtc) return rc; } +static int dpu_crtc_kickoff_clone_mode(struct drm_crtc *crtc) +{ + struct drm_encoder *encoder; + struct drm_encoder *rt_encoder = NULL, *wb_encoder = NULL; + struct dpu_kms *dpu_kms = _dpu_crtc_get_kms(crtc); + + /* Find encoder for real time display */ + drm_for_each_encoder_mask(encoder, crtc->dev, + crtc->state->encoder_mask) { + if (encoder->encoder_type == DRM_MODE_ENCODER_VIRTUAL) + wb_encoder = encoder; + else + rt_encoder = encoder; + } + + if (!rt_encoder || !wb_encoder) { + DRM_DEBUG_ATOMIC("real time or wb encoder not found\n"); + return -EINVAL; + } + + dpu_encoder_prepare_for_kickoff(wb_encoder); + dpu_encoder_prepare_for_kickoff(rt_encoder); + + dpu_vbif_clear_errors(dpu_kms); + + /* + * Kickoff real time encoder last as it's the encoder that + * will do the flush + */ + dpu_encoder_kickoff(wb_encoder); + dpu_encoder_kickoff(rt_encoder); + + /* Don't start frame done timers until the kickoffs have finished */ + dpu_encoder_start_frame_done_timer(wb_encoder); + dpu_encoder_start_frame_done_timer(rt_encoder); + + return 0; +} + /** * dpu_crtc_commit_kickoff - trigger kickoff of the commit for this crtc * @crtc: Pointer to drm crtc object @@ -981,13 +1022,27 @@ void dpu_crtc_commit_kickoff(struct drm_crtc *crtc) goto end; } } - /* - * Encoder will flush/start now, unless it has a tx pending. If so, it - * may delay and flush at an irq event (e.g. ppdone) - */ - drm_for_each_encoder_mask(encoder, crtc->dev, - crtc->state->encoder_mask) - dpu_encoder_prepare_for_kickoff(encoder); + + if (drm_crtc_in_clone_mode(crtc->state)) { + if (dpu_crtc_kickoff_clone_mode(crtc)) + goto end; + } else { + /* + * Encoder will flush/start now, unless it has a tx pending. + * If so, it may delay and flush at an irq event (e.g. ppdone) + */ + drm_for_each_encoder_mask(encoder, crtc->dev, + crtc->state->encoder_mask) + dpu_encoder_prepare_for_kickoff(encoder); + + dpu_vbif_clear_errors(dpu_kms); + + drm_for_each_encoder_mask(encoder, crtc->dev, + crtc->state->encoder_mask) { + dpu_encoder_kickoff(encoder); + dpu_encoder_start_frame_done_timer(encoder); + } + } if (atomic_inc_return(&dpu_crtc->frame_pending) == 1) { /* acquire bandwidth and other resources */ @@ -997,11 +1052,6 @@ void dpu_crtc_commit_kickoff(struct drm_crtc *crtc) dpu_crtc->play_count++; - dpu_vbif_clear_errors(dpu_kms); - - drm_for_each_encoder_mask(encoder, crtc->dev, crtc->state->encoder_mask) - dpu_encoder_kickoff(encoder); - reinit_completion(&dpu_crtc->frame_done_comp); end: @@ -1189,6 +1239,192 @@ static bool dpu_crtc_needs_dirtyfb(struct drm_crtc_state *cstate) return false; } +static int dpu_crtc_reassign_planes(struct drm_crtc *crtc, struct drm_crtc_state *crtc_state) +{ + int total_planes = crtc->dev->mode_config.num_total_plane; + struct drm_atomic_state *state = crtc_state->state; + struct dpu_global_state *global_state; + struct drm_plane_state **states; + struct drm_plane *plane; + int ret; + + global_state = dpu_kms_get_global_state(crtc_state->state); + if (IS_ERR(global_state)) + return PTR_ERR(global_state); + + dpu_rm_release_all_sspp(global_state, crtc); + + if (!crtc_state->enable) + return 0; + + states = kcalloc(total_planes, sizeof(*states), GFP_KERNEL); + if (!states) + return -ENOMEM; + + drm_atomic_crtc_state_for_each_plane(plane, crtc_state) { + struct drm_plane_state *plane_state = + drm_atomic_get_plane_state(state, plane); + + if (IS_ERR(plane_state)) { + ret = PTR_ERR(plane_state); + goto done; + } + + states[plane_state->normalized_zpos] = plane_state; + } + + ret = dpu_assign_plane_resources(global_state, state, crtc, states, total_planes); + +done: + kfree(states); + return ret; +} + +#define MAX_CHANNELS_PER_CRTC 2 +#define MAX_HDISPLAY_SPLIT 1080 + +static struct msm_display_topology dpu_crtc_get_topology( + struct drm_crtc *crtc, + struct dpu_kms *dpu_kms, + struct drm_crtc_state *crtc_state) +{ + struct drm_display_mode *mode = &crtc_state->adjusted_mode; + struct msm_display_topology topology = {0}; + struct drm_encoder *drm_enc; + + drm_for_each_encoder_mask(drm_enc, crtc->dev, crtc_state->encoder_mask) + dpu_encoder_update_topology(drm_enc, &topology, crtc_state->state, + &crtc_state->adjusted_mode); + + topology.cwb_enabled = drm_crtc_in_clone_mode(crtc_state); + + /* + * Datapath topology selection + * + * Dual display + * 2 LM, 2 INTF ( Split display using 2 interfaces) + * + * Single display + * 1 LM, 1 INTF + * 2 LM, 1 INTF (stream merge to support high resolution interfaces) + * + * If DSC is enabled, use 2 LMs for 2:2:1 topology + * + * Add dspps to the reservation requirements if ctm is requested + * + * Only hardcode num_lm to 2 for cases where num_intf == 2 and CWB is not + * enabled. This is because in cases where CWB is enabled, num_intf will + * count both the WB and real-time phys encoders. + * + * For non-DSC CWB usecases, have the num_lm be decided by the + * (mode->hdisplay > MAX_HDISPLAY_SPLIT) check. + */ + + if (topology.num_intf == 2 && !topology.cwb_enabled) + topology.num_lm = 2; + else if (topology.num_dsc == 2) + topology.num_lm = 2; + else if (dpu_kms->catalog->caps->has_3d_merge) + topology.num_lm = (mode->hdisplay > MAX_HDISPLAY_SPLIT) ? 2 : 1; + else + topology.num_lm = 1; + + if (crtc_state->ctm) + topology.num_dspp = topology.num_lm; + + return topology; +} + +static int dpu_crtc_assign_resources(struct drm_crtc *crtc, + struct drm_crtc_state *crtc_state) +{ + struct dpu_hw_blk *hw_ctl[MAX_CHANNELS_PER_CRTC]; + struct dpu_hw_blk *hw_lm[MAX_CHANNELS_PER_CRTC]; + struct dpu_hw_blk *hw_dspp[MAX_CHANNELS_PER_CRTC]; + int i, num_lm, num_ctl, num_dspp; + struct dpu_kms *dpu_kms = _dpu_crtc_get_kms(crtc); + struct dpu_global_state *global_state; + struct dpu_crtc_state *cstate; + struct msm_display_topology topology; + int ret; + + /* + * Release and Allocate resources on every modeset + */ + global_state = dpu_kms_get_global_state(crtc_state->state); + if (IS_ERR(global_state)) + return PTR_ERR(global_state); + + dpu_rm_release(global_state, crtc); + + if (!crtc_state->enable) + return 0; + + topology = dpu_crtc_get_topology(crtc, dpu_kms, crtc_state); + ret = dpu_rm_reserve(&dpu_kms->rm, global_state, + crtc_state->crtc, &topology); + if (ret) + return ret; + + cstate = to_dpu_crtc_state(crtc_state); + + num_ctl = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, + crtc_state->crtc, + DPU_HW_BLK_CTL, hw_ctl, + ARRAY_SIZE(hw_ctl)); + num_lm = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, + crtc_state->crtc, + DPU_HW_BLK_LM, hw_lm, + ARRAY_SIZE(hw_lm)); + num_dspp = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, + crtc_state->crtc, + DPU_HW_BLK_DSPP, hw_dspp, + ARRAY_SIZE(hw_dspp)); + + for (i = 0; i < num_lm; i++) { + int ctl_idx = (i < num_ctl) ? i : (num_ctl-1); + + cstate->mixers[i].hw_lm = to_dpu_hw_mixer(hw_lm[i]); + cstate->mixers[i].lm_ctl = to_dpu_hw_ctl(hw_ctl[ctl_idx]); + if (i < num_dspp) + cstate->mixers[i].hw_dspp = to_dpu_hw_dspp(hw_dspp[i]); + } + + cstate->num_mixers = num_lm; + + return 0; +} + +/** + * dpu_crtc_check_mode_changed: check if full modeset is required + * @old_crtc_state: Previous CRTC state + * @new_crtc_state: Corresponding CRTC state to be checked + * + * Check if the changes in the object properties demand full mode set. + */ +int dpu_crtc_check_mode_changed(struct drm_crtc_state *old_crtc_state, + struct drm_crtc_state *new_crtc_state) +{ + struct drm_encoder *drm_enc; + struct drm_crtc *crtc = new_crtc_state->crtc; + bool clone_mode_enabled = drm_crtc_in_clone_mode(old_crtc_state); + bool clone_mode_requested = drm_crtc_in_clone_mode(new_crtc_state); + + DRM_DEBUG_ATOMIC("%d\n", crtc->base.id); + + /* there might be cases where encoder needs a modeset too */ + drm_for_each_encoder_mask(drm_enc, crtc->dev, new_crtc_state->encoder_mask) { + if (dpu_encoder_needs_modeset(drm_enc, new_crtc_state->state)) + new_crtc_state->mode_changed = true; + } + + if ((clone_mode_requested && !clone_mode_enabled) || + (!clone_mode_requested && clone_mode_enabled)) + new_crtc_state->mode_changed = true; + + return 0; +} + static int dpu_crtc_atomic_check(struct drm_crtc *crtc, struct drm_atomic_state *state) { @@ -1204,6 +1440,20 @@ static int dpu_crtc_atomic_check(struct drm_crtc *crtc, bool needs_dirtyfb = dpu_crtc_needs_dirtyfb(crtc_state); + /* don't reallocate resources if only ACTIVE has beeen changed */ + if (crtc_state->mode_changed || crtc_state->connectors_changed) { + rc = dpu_crtc_assign_resources(crtc, crtc_state); + if (rc < 0) + return rc; + } + + if (dpu_use_virtual_planes && + (crtc_state->planes_changed || crtc_state->zpos_changed)) { + rc = dpu_crtc_reassign_planes(crtc, crtc_state); + if (rc < 0) + return rc; + } + if (!crtc_state->enable || !drm_atomic_crtc_effectively_active(crtc_state)) { DRM_DEBUG_ATOMIC("crtc%d -> enable %d, active %d, skip atomic_check\n", crtc->base.id, crtc_state->enable, @@ -1214,10 +1464,6 @@ static int dpu_crtc_atomic_check(struct drm_crtc *crtc, DRM_DEBUG_ATOMIC("%s: check\n", dpu_crtc->name); - /* force a full mode set if active state changed */ - if (crtc_state->active_changed) - crtc_state->mode_changed = true; - if (cstate->num_mixers) { rc = _dpu_crtc_check_and_setup_lm_bounds(crtc, crtc_state); if (rc) @@ -1436,8 +1682,9 @@ static int dpu_crtc_debugfs_state_show(struct seq_file *s, void *v) seq_printf(s, "intf_mode: %d\n", dpu_crtc_get_intf_mode(crtc)); seq_printf(s, "core_clk_rate: %llu\n", dpu_crtc->cur_perf.core_clk_rate); - seq_printf(s, "bw_ctl: %llu\n", dpu_crtc->cur_perf.bw_ctl); - seq_printf(s, "max_per_pipe_ib: %llu\n", + seq_printf(s, "bw_ctl: %uk\n", + (u32)DIV_ROUND_UP_ULL(dpu_crtc->cur_perf.bw_ctl, 1000)); + seq_printf(s, "max_per_pipe_ib: %u\n", dpu_crtc->cur_perf.max_per_pipe_ib); return 0; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h index 0b148f3ce0d7..94392b9b9245 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h @@ -239,6 +239,9 @@ static inline int dpu_crtc_frame_pending(struct drm_crtc *crtc) return crtc ? atomic_read(&to_dpu_crtc(crtc)->frame_pending) : -EINVAL; } +int dpu_crtc_check_mode_changed(struct drm_crtc_state *old_crtc_state, + struct drm_crtc_state *new_crtc_state); + int dpu_crtc_vblank(struct drm_crtc *crtc, bool en); void dpu_crtc_vblank_callback(struct drm_crtc *crtc); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index 67f5fc6fdae1..c0ed110a7d30 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -2,7 +2,7 @@ /* * Copyright (C) 2013 Red Hat * Copyright (c) 2014-2018, 2020-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved. * * Author: Rob Clark <robdclark@gmail.com> */ @@ -24,6 +24,7 @@ #include "dpu_hw_catalog.h" #include "dpu_hw_intf.h" #include "dpu_hw_ctl.h" +#include "dpu_hw_cwb.h" #include "dpu_hw_dspp.h" #include "dpu_hw_dsc.h" #include "dpu_hw_merge3d.h" @@ -58,8 +59,6 @@ #define IDLE_SHORT_TIMEOUT 1 -#define MAX_HDISPLAY_SPLIT 1080 - /* timeout in frames waiting for frame done */ #define DPU_ENCODER_FRAME_DONE_TIMEOUT_FRAMES 5 @@ -135,8 +134,12 @@ enum dpu_enc_rc_states { * @cur_slave: As above but for the slave encoder. * @hw_pp: Handle to the pingpong blocks used for the display. No. * pingpong blocks can be different than num_phys_encs. + * @hw_cwb: Handle to the CWB muxes used for concurrent writeback + * display. Number of CWB muxes can be different than + * num_phys_encs. * @hw_dsc: Handle to the DSC blocks used for the display. * @dsc_mask: Bitmask of used DSC blocks. + * @cwb_mask: Bitmask of used CWB muxes * @intfs_swapped: Whether or not the phys_enc interfaces have been swapped * for partial update right-only cases, such as pingpong * split where virtual pingpong does not generate IRQs @@ -179,9 +182,11 @@ struct dpu_encoder_virt { struct dpu_encoder_phys *cur_master; struct dpu_encoder_phys *cur_slave; struct dpu_hw_pingpong *hw_pp[MAX_CHANNELS_PER_ENC]; + struct dpu_hw_cwb *hw_cwb[MAX_CHANNELS_PER_ENC]; struct dpu_hw_dsc *hw_dsc[MAX_CHANNELS_PER_ENC]; unsigned int dsc_mask; + unsigned int cwb_mask; bool intfs_swapped; @@ -622,9 +627,9 @@ bool dpu_encoder_use_dsc_merge(struct drm_encoder *drm_enc) if (dpu_enc->phys_encs[i]) intf_count++; - /* See dpu_encoder_get_topology, we only support 2:2:1 topology */ - if (dpu_enc->dsc) - num_dsc = 2; + for (i = 0; i < MAX_CHANNELS_PER_ENC; i++) + if (dpu_enc->hw_dsc[i]) + num_dsc++; return (num_dsc > 0) && (num_dsc > intf_count); } @@ -647,130 +652,51 @@ struct drm_dsc_config *dpu_encoder_get_dsc_config(struct drm_encoder *drm_enc) return NULL; } -static struct msm_display_topology dpu_encoder_get_topology( - struct dpu_encoder_virt *dpu_enc, - struct dpu_kms *dpu_kms, - struct drm_display_mode *mode, - struct drm_crtc_state *crtc_state, - struct drm_dsc_config *dsc) +void dpu_encoder_update_topology(struct drm_encoder *drm_enc, + struct msm_display_topology *topology, + struct drm_atomic_state *state, + const struct drm_display_mode *adj_mode) { - struct msm_display_topology topology = {0}; - int i, intf_count = 0; + struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc); + struct msm_drm_private *priv = dpu_enc->base.dev->dev_private; + struct msm_display_info *disp_info = &dpu_enc->disp_info; + struct dpu_kms *dpu_kms = to_dpu_kms(priv->kms); + struct drm_connector *connector; + struct drm_connector_state *conn_state; + struct drm_framebuffer *fb; + struct drm_dsc_config *dsc; + + int i; for (i = 0; i < MAX_PHYS_ENCODERS_PER_VIRTUAL; i++) if (dpu_enc->phys_encs[i]) - intf_count++; - - /* Datapath topology selection - * - * Dual display - * 2 LM, 2 INTF ( Split display using 2 interfaces) - * - * Single display - * 1 LM, 1 INTF - * 2 LM, 1 INTF (stream merge to support high resolution interfaces) - * - * Add dspps to the reservation requirements if ctm is requested - */ - if (intf_count == 2) - topology.num_lm = 2; - else if (!dpu_kms->catalog->caps->has_3d_merge) - topology.num_lm = 1; - else - topology.num_lm = (mode->hdisplay > MAX_HDISPLAY_SPLIT) ? 2 : 1; - - if (crtc_state->ctm) - topology.num_dspp = topology.num_lm; + topology->num_intf++; - topology.num_intf = intf_count; + dsc = dpu_encoder_get_dsc_config(drm_enc); + /* We only support 2 DSC mode (with 2 LM and 1 INTF) */ if (dsc) { /* - * In case of Display Stream Compression (DSC), we would use - * 2 DSC encoders, 2 layer mixers and 1 interface - * this is power optimal and can drive up to (including) 4k - * screens + * Use 2 DSC encoders, 2 layer mixers and 1 or 2 interfaces + * when Display Stream Compression (DSC) is enabled, + * and when enough DSC blocks are available. + * This is power-optimal and can drive up to (including) 4k + * screens. */ - topology.num_dsc = 2; - topology.num_lm = 2; - topology.num_intf = 1; - } - - return topology; -} - -static void dpu_encoder_assign_crtc_resources(struct dpu_kms *dpu_kms, - struct drm_encoder *drm_enc, - struct dpu_global_state *global_state, - struct drm_crtc_state *crtc_state) -{ - struct dpu_crtc_state *cstate; - struct dpu_hw_blk *hw_ctl[MAX_CHANNELS_PER_ENC]; - struct dpu_hw_blk *hw_lm[MAX_CHANNELS_PER_ENC]; - struct dpu_hw_blk *hw_dspp[MAX_CHANNELS_PER_ENC]; - int num_lm, num_ctl, num_dspp, i; - - cstate = to_dpu_crtc_state(crtc_state); - - memset(cstate->mixers, 0, sizeof(cstate->mixers)); - - num_ctl = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, - drm_enc->base.id, DPU_HW_BLK_CTL, hw_ctl, ARRAY_SIZE(hw_ctl)); - num_lm = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, - drm_enc->base.id, DPU_HW_BLK_LM, hw_lm, ARRAY_SIZE(hw_lm)); - num_dspp = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, - drm_enc->base.id, DPU_HW_BLK_DSPP, hw_dspp, - ARRAY_SIZE(hw_dspp)); - - for (i = 0; i < num_lm; i++) { - int ctl_idx = (i < num_ctl) ? i : (num_ctl-1); - - cstate->mixers[i].hw_lm = to_dpu_hw_mixer(hw_lm[i]); - cstate->mixers[i].lm_ctl = to_dpu_hw_ctl(hw_ctl[ctl_idx]); - cstate->mixers[i].hw_dspp = i < num_dspp ? to_dpu_hw_dspp(hw_dspp[i]) : NULL; - } - - cstate->num_mixers = num_lm; -} - -static int dpu_encoder_virt_atomic_check( - struct drm_encoder *drm_enc, - struct drm_crtc_state *crtc_state, - struct drm_connector_state *conn_state) -{ - struct dpu_encoder_virt *dpu_enc; - struct msm_drm_private *priv; - struct dpu_kms *dpu_kms; - struct drm_display_mode *adj_mode; - struct msm_display_topology topology; - struct msm_display_info *disp_info; - struct dpu_global_state *global_state; - struct drm_framebuffer *fb; - struct drm_dsc_config *dsc; - int ret = 0; - - if (!drm_enc || !crtc_state || !conn_state) { - DPU_ERROR("invalid arg(s), drm_enc %d, crtc/conn state %d/%d\n", - drm_enc != NULL, crtc_state != NULL, conn_state != NULL); - return -EINVAL; + WARN(topology->num_intf > 2, + "DSC topology cannot support more than 2 interfaces\n"); + if (topology->num_intf >= 2 || dpu_kms->catalog->dsc_count >= 2) + topology->num_dsc = 2; + else + topology->num_dsc = 1; } - dpu_enc = to_dpu_encoder_virt(drm_enc); - DPU_DEBUG_ENC(dpu_enc, "\n"); - - priv = drm_enc->dev->dev_private; - disp_info = &dpu_enc->disp_info; - dpu_kms = to_dpu_kms(priv->kms); - adj_mode = &crtc_state->adjusted_mode; - global_state = dpu_kms_get_global_state(crtc_state->state); - if (IS_ERR(global_state)) - return PTR_ERR(global_state); - - trace_dpu_enc_atomic_check(DRMID(drm_enc)); - - dsc = dpu_encoder_get_dsc_config(drm_enc); - - topology = dpu_encoder_get_topology(dpu_enc, dpu_kms, adj_mode, crtc_state, dsc); + connector = drm_atomic_get_new_connector_for_encoder(state, drm_enc); + if (!connector) + return; + conn_state = drm_atomic_get_new_connector_state(state, connector); + if (!conn_state) + return; /* * Use CDM only for writeback or DP at the moment as other interfaces cannot handle it. @@ -781,34 +707,45 @@ static int dpu_encoder_virt_atomic_check( fb = conn_state->writeback_job->fb; if (fb && MSM_FORMAT_IS_YUV(msm_framebuffer_format(fb))) - topology.needs_cdm = true; + topology->num_cdm++; } else if (disp_info->intf_type == INTF_DP) { if (msm_dp_is_yuv_420_enabled(priv->dp[disp_info->h_tile_instance[0]], adj_mode)) - topology.needs_cdm = true; + topology->num_cdm++; } +} - if (topology.needs_cdm && !dpu_enc->cur_master->hw_cdm) - crtc_state->mode_changed = true; - else if (!topology.needs_cdm && dpu_enc->cur_master->hw_cdm) - crtc_state->mode_changed = true; - /* - * Release and Allocate resources on every modeset - * Dont allocate when active is false. - */ - if (drm_atomic_crtc_needs_modeset(crtc_state)) { - dpu_rm_release(global_state, drm_enc); +bool dpu_encoder_needs_modeset(struct drm_encoder *drm_enc, struct drm_atomic_state *state) +{ + struct drm_connector *connector; + struct drm_connector_state *conn_state; + struct drm_framebuffer *fb; + struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc); - if (!crtc_state->active_changed || crtc_state->enable) - ret = dpu_rm_reserve(&dpu_kms->rm, global_state, - drm_enc, crtc_state, topology); - if (!ret) - dpu_encoder_assign_crtc_resources(dpu_kms, drm_enc, - global_state, crtc_state); - } + if (!drm_enc || !state) + return false; - trace_dpu_enc_atomic_check_flags(DRMID(drm_enc), adj_mode->flags); + connector = drm_atomic_get_new_connector_for_encoder(state, drm_enc); + if (!connector) + return false; - return ret; + conn_state = drm_atomic_get_new_connector_state(state, connector); + + /** + * These checks are duplicated from dpu_encoder_update_topology() since + * CRTC and encoder don't hold topology information + */ + if (dpu_enc->disp_info.intf_type == INTF_WB && conn_state->writeback_job) { + fb = conn_state->writeback_job->fb; + if (fb && MSM_FORMAT_IS_YUV(msm_framebuffer_format(fb))) { + if (!dpu_enc->cur_master->hw_cdm) + return true; + } else { + if (dpu_enc->cur_master->hw_cdm) + return true; + } + } + + return false; } static void _dpu_encoder_update_vsync_source(struct dpu_encoder_virt *dpu_enc, @@ -1219,8 +1156,12 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc, struct dpu_hw_blk *hw_pp[MAX_CHANNELS_PER_ENC]; struct dpu_hw_blk *hw_ctl[MAX_CHANNELS_PER_ENC]; struct dpu_hw_blk *hw_dsc[MAX_CHANNELS_PER_ENC]; + struct dpu_hw_blk *hw_cwb[MAX_CHANNELS_PER_ENC]; int num_ctl, num_pp, num_dsc; + int num_cwb = 0; + bool is_cwb_encoder; unsigned int dsc_mask = 0; + unsigned int cwb_mask = 0; int i; if (!drm_enc) { @@ -1233,6 +1174,8 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc, priv = drm_enc->dev->dev_private; dpu_kms = to_dpu_kms(priv->kms); + is_cwb_encoder = drm_crtc_in_clone_mode(crtc_state) && + dpu_enc->disp_info.intf_type == INTF_WB; global_state = dpu_kms_get_existing_global_state(dpu_kms); if (IS_ERR_OR_NULL(global_state)) { @@ -1243,18 +1186,38 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc, trace_dpu_enc_mode_set(DRMID(drm_enc)); /* Query resource that have been reserved in atomic check step. */ - num_pp = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, - drm_enc->base.id, DPU_HW_BLK_PINGPONG, hw_pp, - ARRAY_SIZE(hw_pp)); + if (is_cwb_encoder) { + num_pp = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, + drm_enc->crtc, + DPU_HW_BLK_DCWB_PINGPONG, + hw_pp, ARRAY_SIZE(hw_pp)); + num_cwb = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, + drm_enc->crtc, + DPU_HW_BLK_CWB, + hw_cwb, ARRAY_SIZE(hw_cwb)); + } else { + num_pp = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, + drm_enc->crtc, + DPU_HW_BLK_PINGPONG, hw_pp, + ARRAY_SIZE(hw_pp)); + } + + for (i = 0; i < num_cwb; i++) { + dpu_enc->hw_cwb[i] = to_dpu_hw_cwb(hw_cwb[i]); + cwb_mask |= BIT(dpu_enc->hw_cwb[i]->idx - CWB_0); + } + + dpu_enc->cwb_mask = cwb_mask; + num_ctl = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, - drm_enc->base.id, DPU_HW_BLK_CTL, hw_ctl, ARRAY_SIZE(hw_ctl)); + drm_enc->crtc, DPU_HW_BLK_CTL, hw_ctl, ARRAY_SIZE(hw_ctl)); for (i = 0; i < MAX_CHANNELS_PER_ENC; i++) dpu_enc->hw_pp[i] = i < num_pp ? to_dpu_hw_pingpong(hw_pp[i]) : NULL; num_dsc = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, - drm_enc->base.id, DPU_HW_BLK_DSC, + drm_enc->crtc, DPU_HW_BLK_DSC, hw_dsc, ARRAY_SIZE(hw_dsc)); for (i = 0; i < num_dsc; i++) { dpu_enc->hw_dsc[i] = to_dpu_hw_dsc(hw_dsc[i]); @@ -1268,7 +1231,7 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc, struct dpu_hw_blk *hw_cdm = NULL; dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, - drm_enc->base.id, DPU_HW_BLK_CDM, + drm_enc->crtc, DPU_HW_BLK_CDM, &hw_cdm, 1); dpu_enc->cur_master->hw_cdm = hw_cdm ? to_dpu_hw_cdm(hw_cdm) : NULL; } @@ -1283,7 +1246,11 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc, return; } - phys->hw_ctl = i < num_ctl ? to_dpu_hw_ctl(hw_ctl[i]) : NULL; + /* Use first (and only) CTL if active CTLs are supported */ + if (num_ctl == 1) + phys->hw_ctl = to_dpu_hw_ctl(hw_ctl[0]); + else + phys->hw_ctl = i < num_ctl ? to_dpu_hw_ctl(hw_ctl[i]) : NULL; if (!phys->hw_ctl) { DPU_ERROR_ENC(dpu_enc, "no ctl block assigned at idx: %d\n", i); @@ -1447,7 +1414,7 @@ static void dpu_encoder_virt_atomic_disable(struct drm_encoder *drm_enc, /* after phys waits for frame-done, should be no more frames pending */ if (atomic_xchg(&dpu_enc->frame_done_timeout_ms, 0)) { DPU_ERROR("enc%d timeout pending\n", drm_enc->base.id); - del_timer_sync(&dpu_enc->frame_done_timer); + timer_delete_sync(&dpu_enc->frame_done_timer); } dpu_encoder_resource_control(drm_enc, DPU_ENC_RC_EVENT_STOP); @@ -1619,7 +1586,7 @@ void dpu_encoder_frame_done_callback( if (!dpu_enc->frame_busy_mask[0]) { atomic_set(&dpu_enc->frame_done_timeout_ms, 0); - del_timer(&dpu_enc->frame_done_timer); + timer_delete(&dpu_enc->frame_done_timer); dpu_encoder_resource_control(drm_enc, DPU_ENC_RC_EVENT_FRAME_DONE); @@ -1654,6 +1621,7 @@ static void dpu_encoder_off_work(struct work_struct *work) static void _dpu_encoder_trigger_flush(struct drm_encoder *drm_enc, struct dpu_encoder_phys *phys, uint32_t extra_flush_bits) { + struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc); struct dpu_hw_ctl *ctl; int pending_kickoff_cnt; u32 ret = UINT_MAX; @@ -1671,6 +1639,15 @@ static void _dpu_encoder_trigger_flush(struct drm_encoder *drm_enc, pending_kickoff_cnt = dpu_encoder_phys_inc_pending(phys); + /* Return early if encoder is writeback and in clone mode */ + if (drm_enc->encoder_type == DRM_MODE_ENCODER_VIRTUAL && + dpu_enc->cwb_mask) { + DPU_DEBUG("encoder %d skip flush for concurrent writeback encoder\n", + DRMID(drm_enc)); + return; + } + + if (extra_flush_bits && ctl->ops.update_pending_flush) ctl->ops.update_pending_flush(ctl, extra_flush_bits); @@ -1693,6 +1670,8 @@ static void _dpu_encoder_trigger_flush(struct drm_encoder *drm_enc, */ static void _dpu_encoder_trigger_start(struct dpu_encoder_phys *phys) { + struct dpu_encoder_virt *dpu_enc; + if (!phys) { DPU_ERROR("invalid argument(s)\n"); return; @@ -1703,6 +1682,14 @@ static void _dpu_encoder_trigger_start(struct dpu_encoder_phys *phys) return; } + dpu_enc = to_dpu_encoder_virt(phys->parent); + + if (phys->parent->encoder_type == DRM_MODE_ENCODER_VIRTUAL && + dpu_enc->cwb_mask) { + DPU_DEBUG("encoder %d CWB enabled, skipping\n", DRMID(phys->parent)); + return; + } + if (phys->ops.trigger_start && phys->enable_state != DPU_ENC_DISABLED) phys->ops.trigger_start(phys); } @@ -2020,7 +2007,6 @@ static void dpu_encoder_dsc_pipe_cfg(struct dpu_hw_ctl *ctl, static void dpu_encoder_prep_dsc(struct dpu_encoder_virt *dpu_enc, struct drm_dsc_config *dsc) { - /* coding only for 2LM, 2enc, 1 dsc config */ struct dpu_encoder_phys *enc_master = dpu_enc->cur_master; struct dpu_hw_ctl *ctl = enc_master->hw_ctl; struct dpu_hw_dsc *hw_dsc[MAX_CHANNELS_PER_ENC]; @@ -2030,22 +2016,24 @@ static void dpu_encoder_prep_dsc(struct dpu_encoder_virt *dpu_enc, int dsc_common_mode; int pic_width; u32 initial_lines; + int num_dsc = 0; int i; for (i = 0; i < MAX_CHANNELS_PER_ENC; i++) { hw_pp[i] = dpu_enc->hw_pp[i]; hw_dsc[i] = dpu_enc->hw_dsc[i]; - if (!hw_pp[i] || !hw_dsc[i]) { - DPU_ERROR_ENC(dpu_enc, "invalid params for DSC\n"); - return; - } + if (!hw_pp[i] || !hw_dsc[i]) + break; + + num_dsc++; } - dsc_common_mode = 0; pic_width = dsc->pic_width; - dsc_common_mode = DSC_MODE_SPLIT_PANEL; + dsc_common_mode = 0; + if (num_dsc > 1) + dsc_common_mode |= DSC_MODE_SPLIT_PANEL; if (dpu_encoder_use_dsc_merge(enc_master->parent)) dsc_common_mode |= DSC_MODE_MULTIPLEX; if (enc_master->intf_mode == INTF_MODE_VIDEO) @@ -2054,14 +2042,10 @@ static void dpu_encoder_prep_dsc(struct dpu_encoder_virt *dpu_enc, this_frame_slices = pic_width / dsc->slice_width; intf_ip_w = this_frame_slices * dsc->slice_width; - /* - * dsc merge case: when using 2 encoders for the same stream, - * no. of slices need to be same on both the encoders. - */ - enc_ip_w = intf_ip_w / 2; + enc_ip_w = intf_ip_w / num_dsc; initial_lines = dpu_encoder_dsc_initial_line_calc(dsc, enc_ip_w); - for (i = 0; i < MAX_CHANNELS_PER_ENC; i++) + for (i = 0; i < num_dsc; i++) dpu_encoder_dsc_pipe_cfg(ctl, hw_dsc[i], hw_pp[i], dsc, dsc_common_mode, initial_lines); } @@ -2135,6 +2119,25 @@ bool dpu_encoder_is_valid_for_commit(struct drm_encoder *drm_enc) } /** + * dpu_encoder_start_frame_done_timer - Start the encoder frame done timer + * @drm_enc: Pointer to drm encoder structure + */ +void dpu_encoder_start_frame_done_timer(struct drm_encoder *drm_enc) +{ + struct dpu_encoder_virt *dpu_enc; + unsigned long timeout_ms; + + dpu_enc = to_dpu_encoder_virt(drm_enc); + timeout_ms = DPU_ENCODER_FRAME_DONE_TIMEOUT_FRAMES * 1000 / + drm_mode_vrefresh(&drm_enc->crtc->state->adjusted_mode); + + atomic_set(&dpu_enc->frame_done_timeout_ms, timeout_ms); + mod_timer(&dpu_enc->frame_done_timer, + jiffies + msecs_to_jiffies(timeout_ms)); + +} + +/** * dpu_encoder_kickoff - trigger a double buffer flip of the ctl path * (i.e. ctl flush and start) immediately. * @drm_enc: encoder pointer @@ -2143,7 +2146,6 @@ void dpu_encoder_kickoff(struct drm_encoder *drm_enc) { struct dpu_encoder_virt *dpu_enc; struct dpu_encoder_phys *phys; - unsigned long timeout_ms; unsigned int i; DPU_ATRACE_BEGIN("encoder_kickoff"); @@ -2151,13 +2153,6 @@ void dpu_encoder_kickoff(struct drm_encoder *drm_enc) trace_dpu_enc_kickoff(DRMID(drm_enc)); - timeout_ms = DPU_ENCODER_FRAME_DONE_TIMEOUT_FRAMES * 1000 / - drm_mode_vrefresh(&drm_enc->crtc->state->adjusted_mode); - - atomic_set(&dpu_enc->frame_done_timeout_ms, timeout_ms); - mod_timer(&dpu_enc->frame_done_timer, - jiffies + msecs_to_jiffies(timeout_ms)); - /* All phys encs are ready to go, trigger the kickoff */ _dpu_encoder_kickoff_phys(dpu_enc); @@ -2183,22 +2178,25 @@ static void dpu_encoder_helper_reset_mixers(struct dpu_encoder_phys *phys_enc) memset(&mixer, 0, sizeof(mixer)); /* reset all mixers for this encoder */ - if (phys_enc->hw_ctl->ops.clear_all_blendstages) - phys_enc->hw_ctl->ops.clear_all_blendstages(phys_enc->hw_ctl); + if (ctl->ops.clear_all_blendstages) + ctl->ops.clear_all_blendstages(ctl); global_state = dpu_kms_get_existing_global_state(phys_enc->dpu_kms); num_lm = dpu_rm_get_assigned_resources(&phys_enc->dpu_kms->rm, global_state, - phys_enc->parent->base.id, DPU_HW_BLK_LM, hw_lm, ARRAY_SIZE(hw_lm)); + phys_enc->parent->crtc, DPU_HW_BLK_LM, hw_lm, ARRAY_SIZE(hw_lm)); for (i = 0; i < num_lm; i++) { hw_mixer[i] = to_dpu_hw_mixer(hw_lm[i]); - if (phys_enc->hw_ctl->ops.update_pending_flush_mixer) - phys_enc->hw_ctl->ops.update_pending_flush_mixer(ctl, hw_mixer[i]->idx); + if (ctl->ops.update_pending_flush_mixer) + ctl->ops.update_pending_flush_mixer(ctl, hw_mixer[i]->idx); /* clear all blendstages */ - if (phys_enc->hw_ctl->ops.setup_blendstage) - phys_enc->hw_ctl->ops.setup_blendstage(ctl, hw_mixer[i]->idx, NULL); + if (ctl->ops.setup_blendstage) + ctl->ops.setup_blendstage(ctl, hw_mixer[i]->idx, NULL); + + if (ctl->ops.set_active_fetch_pipes) + ctl->ops.set_active_fetch_pipes(ctl, NULL); } } @@ -2250,7 +2248,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc) dpu_enc = to_dpu_encoder_virt(phys_enc->parent); - phys_enc->hw_ctl->ops.reset(ctl); + ctl->ops.reset(ctl); dpu_encoder_helper_reset_mixers(phys_enc); @@ -2265,8 +2263,8 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc) phys_enc->hw_wb->ops.bind_pingpong_blk(phys_enc->hw_wb, PINGPONG_NONE); /* mark WB flush as pending */ - if (phys_enc->hw_ctl->ops.update_pending_flush_wb) - phys_enc->hw_ctl->ops.update_pending_flush_wb(ctl, phys_enc->hw_wb->idx); + if (ctl->ops.update_pending_flush_wb) + ctl->ops.update_pending_flush_wb(ctl, phys_enc->hw_wb->idx); } else { for (i = 0; i < dpu_enc->num_phys_encs; i++) { if (dpu_enc->phys_encs[i] && phys_enc->hw_intf->ops.bind_pingpong_blk) @@ -2275,8 +2273,8 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc) PINGPONG_NONE); /* mark INTF flush as pending */ - if (phys_enc->hw_ctl->ops.update_pending_flush_intf) - phys_enc->hw_ctl->ops.update_pending_flush_intf(phys_enc->hw_ctl, + if (ctl->ops.update_pending_flush_intf) + ctl->ops.update_pending_flush_intf(ctl, dpu_enc->phys_encs[i]->hw_intf->idx); } } @@ -2284,12 +2282,15 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc) if (phys_enc->hw_pp && phys_enc->hw_pp->ops.setup_dither) phys_enc->hw_pp->ops.setup_dither(phys_enc->hw_pp, NULL); + if (dpu_enc->cwb_mask) + dpu_encoder_helper_phys_setup_cwb(phys_enc, false); + /* reset the merge 3D HW block */ if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d) { phys_enc->hw_pp->merge_3d->ops.setup_3d_mode(phys_enc->hw_pp->merge_3d, BLEND_3D_NONE); - if (phys_enc->hw_ctl->ops.update_pending_flush_merge_3d) - phys_enc->hw_ctl->ops.update_pending_flush_merge_3d(ctl, + if (ctl->ops.update_pending_flush_merge_3d) + ctl->ops.update_pending_flush_merge_3d(ctl, phys_enc->hw_pp->merge_3d->idx); } @@ -2297,9 +2298,9 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc) if (phys_enc->hw_cdm->ops.bind_pingpong_blk && phys_enc->hw_pp) phys_enc->hw_cdm->ops.bind_pingpong_blk(phys_enc->hw_cdm, PINGPONG_NONE); - if (phys_enc->hw_ctl->ops.update_pending_flush_cdm) - phys_enc->hw_ctl->ops.update_pending_flush_cdm(phys_enc->hw_ctl, - phys_enc->hw_cdm->idx); + if (ctl->ops.update_pending_flush_cdm) + ctl->ops.update_pending_flush_cdm(ctl, + phys_enc->hw_cdm->idx); } if (dpu_enc->dsc) { @@ -2310,6 +2311,7 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc) intf_cfg.stream_sel = 0; /* Don't care value for video mode */ intf_cfg.mode_3d = dpu_encoder_helper_get_3d_blend_mode(phys_enc); intf_cfg.dsc = dpu_encoder_helper_get_dsc(phys_enc); + intf_cfg.cwb = dpu_enc->cwb_mask; if (phys_enc->hw_intf) intf_cfg.intf = phys_enc->hw_intf->idx; @@ -2327,6 +2329,68 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc) ctl->ops.clear_pending_flush(ctl); } +void dpu_encoder_helper_phys_setup_cwb(struct dpu_encoder_phys *phys_enc, + bool enable) +{ + struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(phys_enc->parent); + struct dpu_hw_cwb *hw_cwb; + struct dpu_hw_ctl *hw_ctl; + struct dpu_hw_cwb_setup_cfg cwb_cfg; + + struct dpu_kms *dpu_kms; + struct dpu_global_state *global_state; + struct dpu_hw_blk *rt_pp_list[MAX_CHANNELS_PER_ENC]; + int num_pp; + + if (!phys_enc->hw_wb) + return; + + hw_ctl = phys_enc->hw_ctl; + + if (!phys_enc->hw_ctl) { + DPU_DEBUG("[wb:%d] no ctl assigned\n", + phys_enc->hw_wb->idx - WB_0); + return; + } + + dpu_kms = phys_enc->dpu_kms; + global_state = dpu_kms_get_existing_global_state(dpu_kms); + num_pp = dpu_rm_get_assigned_resources(&dpu_kms->rm, global_state, + phys_enc->parent->crtc, + DPU_HW_BLK_PINGPONG, rt_pp_list, + ARRAY_SIZE(rt_pp_list)); + + if (num_pp == 0 || num_pp > MAX_CHANNELS_PER_ENC) { + DPU_DEBUG_ENC(dpu_enc, "invalid num_pp %d\n", num_pp); + return; + } + + /* + * The CWB mux supports using LM or DSPP as tap points. For now, + * always use LM tap point + */ + cwb_cfg.input = INPUT_MODE_LM_OUT; + + for (int i = 0; i < MAX_CHANNELS_PER_ENC; i++) { + hw_cwb = dpu_enc->hw_cwb[i]; + if (!hw_cwb) + continue; + + if (enable) { + struct dpu_hw_pingpong *hw_pp = + to_dpu_hw_pingpong(rt_pp_list[i]); + cwb_cfg.pp_idx = hw_pp->idx; + } else { + cwb_cfg.pp_idx = PINGPONG_NONE; + } + + hw_cwb->ops.config_cwb(hw_cwb, &cwb_cfg); + + if (hw_ctl->ops.update_pending_flush_cwb) + hw_ctl->ops.update_pending_flush_cwb(hw_ctl, hw_cwb->idx); + } +} + /** * dpu_encoder_helper_phys_setup_cdm - setup chroma down sampling block * @phys_enc: Pointer to physical encoder @@ -2513,6 +2577,38 @@ static int dpu_encoder_virt_add_phys_encs( return 0; } +/** + * dpu_encoder_get_clones - Calculate the possible_clones for DPU encoder + * @drm_enc: DRM encoder pointer + * Returns: possible_clones mask + */ +uint32_t dpu_encoder_get_clones(struct drm_encoder *drm_enc) +{ + struct drm_encoder *curr; + int type = drm_enc->encoder_type; + uint32_t clone_mask = drm_encoder_mask(drm_enc); + + /* + * Set writeback as possible clones of real-time DSI encoders and vice + * versa + * + * Writeback encoders can't be clones of each other and DSI + * encoders can't be clones of each other. + * + * TODO: Add DP encoders as valid possible clones for writeback encoders + * (and vice versa) once concurrent writeback has been validated for DP + */ + drm_for_each_encoder(curr, drm_enc->dev) { + if ((type == DRM_MODE_ENCODER_VIRTUAL && + curr->encoder_type == DRM_MODE_ENCODER_DSI) || + (type == DRM_MODE_ENCODER_DSI && + curr->encoder_type == DRM_MODE_ENCODER_VIRTUAL)) + clone_mask |= drm_encoder_mask(curr); + } + + return clone_mask; +} + static int dpu_encoder_setup_display(struct dpu_encoder_virt *dpu_enc, struct dpu_kms *dpu_kms, struct msm_display_info *disp_info) @@ -2597,8 +2693,8 @@ static int dpu_encoder_setup_display(struct dpu_encoder_virt *dpu_enc, static void dpu_encoder_frame_done_timeout(struct timer_list *t) { - struct dpu_encoder_virt *dpu_enc = from_timer(dpu_enc, t, - frame_done_timer); + struct dpu_encoder_virt *dpu_enc = timer_container_of(dpu_enc, t, + frame_done_timer); struct drm_encoder *drm_enc = &dpu_enc->base; u32 event; @@ -2630,7 +2726,6 @@ static const struct drm_encoder_helper_funcs dpu_encoder_helper_funcs = { .atomic_mode_set = dpu_encoder_virt_atomic_mode_set, .atomic_disable = dpu_encoder_virt_atomic_disable, .atomic_enable = dpu_encoder_virt_atomic_enable, - .atomic_check = dpu_encoder_virt_atomic_check, }; static const struct drm_encoder_funcs dpu_encoder_funcs = { @@ -2789,6 +2884,18 @@ enum dpu_intf_mode dpu_encoder_get_intf_mode(struct drm_encoder *encoder) } /** + * dpu_encoder_helper_get_cwb_mask - get CWB blocks mask for the DPU encoder + * @phys_enc: Pointer to physical encoder structure + */ +unsigned int dpu_encoder_helper_get_cwb_mask(struct dpu_encoder_phys *phys_enc) +{ + struct drm_encoder *encoder = phys_enc->parent; + struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(encoder); + + return dpu_enc->cwb_mask; +} + +/** * dpu_encoder_helper_get_dsc - get DSC blocks mask for the DPU encoder * This helper function is used by physical encoder to get DSC blocks mask * used for this encoder. diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h index 92b5ee390788..ca1ca2e51d7e 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved. * Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. * Copyright (C) 2013 Red Hat * Author: Rob Clark <robdclark@gmail.com> @@ -60,6 +60,8 @@ enum dpu_intf_mode dpu_encoder_get_intf_mode(struct drm_encoder *encoder); void dpu_encoder_virt_runtime_resume(struct drm_encoder *encoder); +uint32_t dpu_encoder_get_clones(struct drm_encoder *drm_enc); + struct drm_encoder *dpu_encoder_init(struct drm_device *dev, int drm_enc_mode, struct msm_display_info *disp_info); @@ -80,6 +82,13 @@ int dpu_encoder_get_crc(const struct drm_encoder *drm_enc, u32 *crcs, int pos); bool dpu_encoder_use_dsc_merge(struct drm_encoder *drm_enc); +void dpu_encoder_update_topology(struct drm_encoder *drm_enc, + struct msm_display_topology *topology, + struct drm_atomic_state *state, + const struct drm_display_mode *adj_mode); + +bool dpu_encoder_needs_modeset(struct drm_encoder *drm_enc, struct drm_atomic_state *state); + void dpu_encoder_prepare_wb_job(struct drm_encoder *drm_enc, struct drm_writeback_job *job); @@ -88,4 +97,5 @@ void dpu_encoder_cleanup_wb_job(struct drm_encoder *drm_enc, bool dpu_encoder_is_valid_for_commit(struct drm_encoder *drm_enc); +void dpu_encoder_start_frame_done_timer(struct drm_encoder *drm_enc); #endif /* __DPU_ENCODER_H__ */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h index 63f09857025c..61b22d949454 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved. * Copyright (c) 2015-2018 The Linux Foundation. All rights reserved. */ @@ -309,6 +309,8 @@ static inline enum dpu_3d_blend_mode dpu_encoder_helper_get_3d_blend_mode( return BLEND_3D_NONE; } +unsigned int dpu_encoder_helper_get_cwb_mask(struct dpu_encoder_phys *phys_enc); + unsigned int dpu_encoder_helper_get_dsc(struct dpu_encoder_phys *phys_enc); struct drm_dsc_config *dpu_encoder_get_dsc_config(struct drm_encoder *drm_enc); @@ -331,6 +333,9 @@ int dpu_encoder_helper_wait_for_irq(struct dpu_encoder_phys *phys_enc, void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc); +void dpu_encoder_helper_phys_setup_cwb(struct dpu_encoder_phys *phys_enc, + bool enable); + void dpu_encoder_helper_phys_setup_cdm(struct dpu_encoder_phys *phys_enc, const struct msm_format *dpu_fmt, u32 output_type); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c index e9bbccc44dad..a0ba55ab3c89 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c @@ -5,6 +5,7 @@ #define pr_fmt(fmt) "[drm:%s:%d] " fmt, __func__, __LINE__ #include <linux/delay.h> +#include <linux/string_choices.h> #include "dpu_encoder_phys.h" #include "dpu_hw_interrupts.h" #include "dpu_hw_pingpong.h" @@ -59,6 +60,8 @@ static void _dpu_encoder_phys_cmd_update_intf_cfg( return; intf_cfg.intf = phys_enc->hw_intf->idx; + if (phys_enc->split_role == ENC_ROLE_MASTER) + intf_cfg.intf_master = phys_enc->hw_intf->idx; intf_cfg.intf_mode_sel = DPU_CTL_MODE_SEL_CMD; intf_cfg.stream_sel = cmd_enc->stream_sel; intf_cfg.mode_3d = dpu_encoder_helper_get_3d_blend_mode(phys_enc); @@ -261,7 +264,7 @@ static int dpu_encoder_phys_cmd_control_vblank_irq( DRM_DEBUG_KMS("id:%u pp:%d enable=%s/%d\n", DRMID(phys_enc->parent), phys_enc->hw_pp->idx - PINGPONG_0, - enable ? "true" : "false", refcount); + str_true_false(enable), refcount); if (enable) { if (phys_enc->vblank_refcount == 0) @@ -285,7 +288,7 @@ end: DRM_ERROR("vblank irq err id:%u pp:%d ret:%d, enable %s/%d\n", DRMID(phys_enc->parent), phys_enc->hw_pp->idx - PINGPONG_0, ret, - enable ? "true" : "false", refcount); + str_true_false(enable), refcount); } return ret; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c index abd6600046cb..1c468ca5d692 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c @@ -94,17 +94,21 @@ static void drm_mode_to_intf_timing_params( timing->vsync_polarity = 0; } - /* for DP/EDP, Shift timings to align it to bottom right */ - if (phys_enc->hw_intf->cap->type == INTF_DP) { + timing->wide_bus_en = dpu_encoder_is_widebus_enabled(phys_enc->parent); + timing->compression_en = dpu_encoder_is_dsc_enabled(phys_enc->parent); + + /* + * For DP/EDP, Shift timings to align it to bottom right. + * wide_bus_en is set for everything excluding SDM845 & + * porch changes cause DisplayPort failure and HDMI tearing. + */ + if (phys_enc->hw_intf->cap->type == INTF_DP && timing->wide_bus_en) { timing->h_back_porch += timing->h_front_porch; timing->h_front_porch = 0; timing->v_back_porch += timing->v_front_porch; timing->v_front_porch = 0; } - timing->wide_bus_en = dpu_encoder_is_widebus_enabled(phys_enc->parent); - timing->compression_en = dpu_encoder_is_dsc_enabled(phys_enc->parent); - /* * for DP, divide the horizonal parameters by 2 when * widebus is enabled @@ -298,6 +302,8 @@ static void dpu_encoder_phys_vid_setup_timing_engine( if (phys_enc->hw_cdm) intf_cfg.cdm = phys_enc->hw_cdm->idx; intf_cfg.intf = phys_enc->hw_intf->idx; + if (phys_enc->split_role == ENC_ROLE_MASTER) + intf_cfg.intf_master = phys_enc->hw_intf->idx; intf_cfg.intf_mode_sel = DPU_CTL_MODE_SEL_VID; intf_cfg.stream_sel = 0; /* Don't care value for video mode */ intf_cfg.mode_3d = dpu_encoder_helper_get_3d_blend_mode(phys_enc); @@ -372,7 +378,8 @@ static void dpu_encoder_phys_vid_underrun_irq(void *arg) static bool dpu_encoder_phys_vid_needs_single_flush( struct dpu_encoder_phys *phys_enc) { - return phys_enc->split_role != ENC_ROLE_SOLO; + return !(phys_enc->hw_ctl->caps->features & BIT(DPU_CTL_ACTIVE_CFG)) && + phys_enc->split_role != ENC_ROLE_SOLO; } static void dpu_encoder_phys_vid_atomic_mode_set( diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c index 4c006ec74575..849fea580a4c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved. */ #define pr_fmt(fmt) "[drm:%s:%d] " fmt, __func__, __LINE__ @@ -68,7 +68,7 @@ static void dpu_encoder_phys_wb_set_ot_limit( ot_params.num = hw_wb->idx - WB_0; ot_params.width = phys_enc->cached_mode.hdisplay; ot_params.height = phys_enc->cached_mode.vdisplay; - ot_params.is_wfd = true; + ot_params.is_wfd = !dpu_encoder_helper_get_cwb_mask(phys_enc); ot_params.frame_rate = drm_mode_vrefresh(&phys_enc->cached_mode); ot_params.vbif_idx = hw_wb->caps->vbif_idx; ot_params.rd = false; @@ -111,7 +111,7 @@ static void dpu_encoder_phys_wb_set_qos_remap( qos_params.vbif_idx = hw_wb->caps->vbif_idx; qos_params.xin_id = hw_wb->caps->xin_id; qos_params.num = hw_wb->idx - WB_0; - qos_params.is_rt = false; + qos_params.is_rt = dpu_encoder_helper_get_cwb_mask(phys_enc); DPU_DEBUG("[qos_remap] wb:%d vbif:%d xin:%d is_rt:%d\n", qos_params.num, @@ -174,6 +174,7 @@ static void dpu_encoder_phys_wb_setup_fb(struct dpu_encoder_phys *phys_enc, struct dpu_encoder_phys_wb *wb_enc = to_dpu_encoder_phys_wb(phys_enc); struct dpu_hw_wb *hw_wb; struct dpu_hw_wb_cfg *wb_cfg; + u32 cdp_usage; if (!phys_enc || !phys_enc->dpu_kms || !phys_enc->dpu_kms->catalog) { DPU_ERROR("invalid encoder\n"); @@ -182,6 +183,10 @@ static void dpu_encoder_phys_wb_setup_fb(struct dpu_encoder_phys *phys_enc, hw_wb = phys_enc->hw_wb; wb_cfg = &wb_enc->wb_cfg; + if (dpu_encoder_helper_get_cwb_mask(phys_enc)) + cdp_usage = DPU_PERF_CDP_USAGE_RT; + else + cdp_usage = DPU_PERF_CDP_USAGE_NRT; wb_cfg->intf_mode = phys_enc->intf_mode; wb_cfg->roi.x1 = 0; @@ -199,7 +204,7 @@ static void dpu_encoder_phys_wb_setup_fb(struct dpu_encoder_phys *phys_enc, const struct dpu_perf_cfg *perf = phys_enc->dpu_kms->catalog->perf; hw_wb->ops.setup_cdp(hw_wb, format, - perf->cdp_cfg[DPU_PERF_CDP_USAGE_NRT].wr_enable); + perf->cdp_cfg[cdp_usage].wr_enable); } if (hw_wb->ops.setup_outaddress) @@ -236,6 +241,7 @@ static void dpu_encoder_phys_wb_setup_ctl(struct dpu_encoder_phys *phys_enc) intf_cfg.intf = DPU_NONE; intf_cfg.wb = hw_wb->idx; + intf_cfg.cwb = dpu_encoder_helper_get_cwb_mask(phys_enc); if (mode_3d && hw_pp && hw_pp->merge_3d) intf_cfg.merge_3d = hw_pp->merge_3d->idx; @@ -340,6 +346,8 @@ static void dpu_encoder_phys_wb_setup( dpu_encoder_helper_phys_setup_cdm(phys_enc, format, CDM_CDWN_OUTPUT_WB); + dpu_encoder_helper_phys_setup_cwb(phys_enc, true); + dpu_encoder_phys_wb_setup_ctl(phys_enc); } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c index 2cbf41f33cc0..c878fe196aeb 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c @@ -34,11 +34,11 @@ #define VIG_MSM8998_MASK \ (VIG_MASK | BIT(DPU_SSPP_SCALER_QSEED3_COMPATIBLE)) -#define VIG_SDM845_MASK \ +#define VIG_SDM845_MASK_NO_SDMA \ (VIG_MASK | BIT(DPU_SSPP_QOS_8LVL) | BIT(DPU_SSPP_SCALER_QSEED3_COMPATIBLE)) #define VIG_SDM845_MASK_SDMA \ - (VIG_SDM845_MASK | BIT(DPU_SSPP_SMART_DMA_V2)) + (VIG_SDM845_MASK_NO_SDMA | BIT(DPU_SSPP_SMART_DMA_V2)) #define VIG_QCM2290_MASK (VIG_BASE_MASK | BIT(DPU_SSPP_QOS_8LVL)) @@ -54,24 +54,24 @@ BIT(DPU_SSPP_CDP) | BIT(DPU_SSPP_EXCL_RECT)) #define VIG_SC7280_MASK \ - (VIG_SDM845_MASK | BIT(DPU_SSPP_INLINE_ROTATION)) + (VIG_SDM845_MASK_NO_SDMA | BIT(DPU_SSPP_INLINE_ROTATION)) #define VIG_SC7280_MASK_SDMA \ (VIG_SC7280_MASK | BIT(DPU_SSPP_SMART_DMA_V2)) -#define DMA_SDM845_MASK \ +#define DMA_SDM845_MASK_NO_SDMA \ (BIT(DPU_SSPP_QOS) | BIT(DPU_SSPP_QOS_8LVL) |\ BIT(DPU_SSPP_TS_PREFILL) | BIT(DPU_SSPP_TS_PREFILL_REC1) |\ BIT(DPU_SSPP_CDP) | BIT(DPU_SSPP_EXCL_RECT)) -#define DMA_CURSOR_SDM845_MASK \ - (DMA_SDM845_MASK | BIT(DPU_SSPP_CURSOR)) +#define DMA_CURSOR_SDM845_MASK_NO_SDMA \ + (DMA_SDM845_MASK_NO_SDMA | BIT(DPU_SSPP_CURSOR)) #define DMA_SDM845_MASK_SDMA \ - (DMA_SDM845_MASK | BIT(DPU_SSPP_SMART_DMA_V2)) + (DMA_SDM845_MASK_NO_SDMA | BIT(DPU_SSPP_SMART_DMA_V2)) #define DMA_CURSOR_SDM845_MASK_SDMA \ - (DMA_CURSOR_SDM845_MASK | BIT(DPU_SSPP_SMART_DMA_V2)) + (DMA_CURSOR_SDM845_MASK_NO_SDMA | BIT(DPU_SSPP_SMART_DMA_V2)) #define DMA_CURSOR_MSM8996_MASK \ (DMA_MSM8996_MASK | BIT(DPU_SSPP_CURSOR)) @@ -98,15 +98,9 @@ #define PINGPONG_MSM8996_MASK \ (BIT(DPU_PINGPONG_DSC)) -#define PINGPONG_MSM8996_TE2_MASK \ - (PINGPONG_MSM8996_MASK | BIT(DPU_PINGPONG_TE2)) - #define PINGPONG_SDM845_MASK \ (BIT(DPU_PINGPONG_DITHER) | BIT(DPU_PINGPONG_DSC)) -#define PINGPONG_SDM845_TE2_MASK \ - (PINGPONG_SDM845_MASK | BIT(DPU_PINGPONG_TE2)) - #define PINGPONG_SM8150_MASK \ (BIT(DPU_PINGPONG_DITHER) | BIT(DPU_PINGPONG_DSC)) @@ -232,37 +226,6 @@ static const u32 rotation_v2_formats[] = { /* TODO add formats after validation */ }; -static const u32 wb2_formats_rgb[] = { - DRM_FORMAT_RGB565, - DRM_FORMAT_BGR565, - DRM_FORMAT_RGB888, - DRM_FORMAT_ARGB8888, - DRM_FORMAT_RGBA8888, - DRM_FORMAT_ABGR8888, - DRM_FORMAT_XRGB8888, - DRM_FORMAT_RGBX8888, - DRM_FORMAT_XBGR8888, - DRM_FORMAT_ARGB1555, - DRM_FORMAT_RGBA5551, - DRM_FORMAT_XRGB1555, - DRM_FORMAT_RGBX5551, - DRM_FORMAT_ARGB4444, - DRM_FORMAT_RGBA4444, - DRM_FORMAT_RGBX4444, - DRM_FORMAT_XRGB4444, - DRM_FORMAT_BGR888, - DRM_FORMAT_BGRA8888, - DRM_FORMAT_BGRX8888, - DRM_FORMAT_ABGR1555, - DRM_FORMAT_BGRA5551, - DRM_FORMAT_XBGR1555, - DRM_FORMAT_BGRX5551, - DRM_FORMAT_ABGR4444, - DRM_FORMAT_BGRA4444, - DRM_FORMAT_BGRX4444, - DRM_FORMAT_XBGR4444, -}; - static const u32 wb2_formats_rgb_yuv[] = { DRM_FORMAT_RGB565, DRM_FORMAT_BGR565, @@ -407,8 +370,6 @@ static const struct dpu_sspp_sub_blks dpu_dma_sblk = _DMA_SBLK(); * MIXER sub blocks config *************************************************************/ -/* MSM8998 */ - static const struct dpu_lm_sub_blks msm8998_lm_sblk = { .maxwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH, .maxblendstages = 7, /* excluding base layer */ @@ -418,8 +379,6 @@ static const struct dpu_lm_sub_blks msm8998_lm_sblk = { }, }; -/* SDM845 */ - static const struct dpu_lm_sub_blks sdm845_lm_sblk = { .maxwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH, .maxblendstages = 11, /* excluding base layer */ @@ -429,8 +388,6 @@ static const struct dpu_lm_sub_blks sdm845_lm_sblk = { }, }; -/* SC7180 */ - static const struct dpu_lm_sub_blks sc7180_lm_sblk = { .maxwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH, .maxblendstages = 7, /* excluding base layer */ @@ -439,8 +396,6 @@ static const struct dpu_lm_sub_blks sc7180_lm_sblk = { }, }; -/* QCM2290 */ - static const struct dpu_lm_sub_blks qcm2290_lm_sblk = { .maxwidth = DEFAULT_DPU_LINE_WIDTH, .maxblendstages = 4, /* excluding base layer */ @@ -465,22 +420,11 @@ static const struct dpu_dspp_sub_blks sdm845_dspp_sblk = { /************************************************************* * PINGPONG sub blocks config *************************************************************/ -static const struct dpu_pingpong_sub_blks msm8996_pp_sblk_te = { - .te2 = {.name = "te2", .base = 0x2000, .len = 0x0, - .version = 0x1}, -}; static const struct dpu_pingpong_sub_blks msm8996_pp_sblk = { /* No dither block */ }; -static const struct dpu_pingpong_sub_blks sdm845_pp_sblk_te = { - .te2 = {.name = "te2", .base = 0x2000, .len = 0x0, - .version = 0x1}, - .dither = {.name = "dither", .base = 0x30e0, - .len = 0x20, .version = 0x10000}, -}; - static const struct dpu_pingpong_sub_blks sdm845_pp_sblk = { .dither = {.name = "dither", .base = 0x30e0, .len = 0x20, .version = 0x10000}, @@ -507,7 +451,14 @@ static const struct dpu_dsc_sub_blks dsc_sblk_1 = { /************************************************************* * CDM block config *************************************************************/ -static const struct dpu_cdm_cfg sc7280_cdm = { +static const struct dpu_cdm_cfg dpu_cdm_1_x_4_x = { + .name = "cdm_0", + .id = CDM_0, + .len = 0x224, + .base = 0x79200, +}; + +static const struct dpu_cdm_cfg dpu_cdm_5_x = { .name = "cdm_0", .id = CDM_0, .len = 0x228, @@ -765,6 +716,7 @@ static const struct dpu_qos_lut_entry sc7180_qos_nrt[] = { #include "catalog/dpu_5_0_sm8150.h" #include "catalog/dpu_5_1_sc8180x.h" #include "catalog/dpu_5_2_sm7150.h" +#include "catalog/dpu_5_3_sm6150.h" #include "catalog/dpu_5_4_sm6125.h" #include "catalog/dpu_6_0_sm8250.h" @@ -782,7 +734,7 @@ static const struct dpu_qos_lut_entry sc7180_qos_nrt[] = { #include "catalog/dpu_8_4_sa8775p.h" #include "catalog/dpu_9_0_sm8550.h" - +#include "catalog/dpu_9_1_sar2130p.h" #include "catalog/dpu_9_2_x1e80100.h" #include "catalog/dpu_10_0_sm8650.h" diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h index c701d18c3522..01dd6e65f777 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h @@ -115,7 +115,6 @@ enum { /** * PINGPONG sub-blocks - * @DPU_PINGPONG_TE2 Additional tear check block for split pipes * @DPU_PINGPONG_SPLIT PP block supports split fifo * @DPU_PINGPONG_SLAVE PP block is a suitable slave for split fifo * @DPU_PINGPONG_DITHER Dither blocks @@ -123,8 +122,7 @@ enum { * @DPU_PINGPONG_MAX */ enum { - DPU_PINGPONG_TE2 = 0x1, - DPU_PINGPONG_SPLIT, + DPU_PINGPONG_SPLIT = 0x1, DPU_PINGPONG_SLAVE, DPU_PINGPONG_DITHER, DPU_PINGPONG_DSC, @@ -404,8 +402,6 @@ struct dpu_dspp_sub_blks { }; struct dpu_pingpong_sub_blks { - struct dpu_pp_blk te; - struct dpu_pp_blk te2; struct dpu_pp_blk dither; }; @@ -613,6 +609,16 @@ struct dpu_wb_cfg { enum dpu_clk_ctrl_type clk_ctrl; }; +/* + * struct dpu_cwb_cfg : MDP CWB mux instance info + * @id: enum identifying this block + * @base: register base offset to mdss + * @features bit mask identifying sub-blocks/features + */ +struct dpu_cwb_cfg { + DPU_HW_BLK_INFO; +}; + /** * struct dpu_vbif_dynamic_ot_cfg - dynamic OT setting * @pps pixel per seconds @@ -815,6 +821,9 @@ struct dpu_mdss_cfg { u32 dspp_count; const struct dpu_dspp_cfg *dspp; + u32 cwb_count; + const struct dpu_cwb_cfg *cwb; + /* Add additional block data structures here */ const struct dpu_perf_cfg *perf; @@ -828,6 +837,7 @@ extern const struct dpu_mdss_cfg dpu_msm8937_cfg; extern const struct dpu_mdss_cfg dpu_msm8953_cfg; extern const struct dpu_mdss_cfg dpu_msm8996_cfg; extern const struct dpu_mdss_cfg dpu_msm8998_cfg; +extern const struct dpu_mdss_cfg dpu_sar2130p_cfg; extern const struct dpu_mdss_cfg dpu_sdm630_cfg; extern const struct dpu_mdss_cfg dpu_sdm660_cfg; extern const struct dpu_mdss_cfg dpu_sdm845_cfg; @@ -839,6 +849,7 @@ extern const struct dpu_mdss_cfg dpu_sm8250_cfg; extern const struct dpu_mdss_cfg dpu_sc7180_cfg; extern const struct dpu_mdss_cfg dpu_sm6115_cfg; extern const struct dpu_mdss_cfg dpu_sm6125_cfg; +extern const struct dpu_mdss_cfg dpu_sm6150_cfg; extern const struct dpu_mdss_cfg dpu_sm6350_cfg; extern const struct dpu_mdss_cfg dpu_qcm2290_cfg; extern const struct dpu_mdss_cfg dpu_sm6375_cfg; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c index ae1534c49ae0..3f88c3641d4a 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c @@ -214,7 +214,9 @@ static void dpu_hw_cdm_bind_pingpong_blk(struct dpu_hw_cdm *ctx, const enum dpu_ mux_cfg = DPU_REG_READ(c, CDM_MUX); mux_cfg &= ~0xf; - if (pp) + if (pp >= PINGPONG_CWB_0) + mux_cfg |= 0xd; + else if (pp) mux_cfg |= (pp - PINGPONG_0) & 0x7; else mux_cfg |= 0xf; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c index 4893f10d6a58..573e42b06ad0 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved. */ #include <linux/delay.h> @@ -31,12 +31,14 @@ #define CTL_MERGE_3D_ACTIVE 0x0E4 #define CTL_DSC_ACTIVE 0x0E8 #define CTL_WB_ACTIVE 0x0EC +#define CTL_CWB_ACTIVE 0x0F0 #define CTL_INTF_ACTIVE 0x0F4 #define CTL_CDM_ACTIVE 0x0F8 #define CTL_FETCH_PIPE_ACTIVE 0x0FC #define CTL_MERGE_3D_FLUSH 0x100 #define CTL_DSC_FLUSH 0x104 #define CTL_WB_FLUSH 0x108 +#define CTL_CWB_FLUSH 0x10C #define CTL_INTF_FLUSH 0x110 #define CTL_CDM_FLUSH 0x114 #define CTL_PERIPH_FLUSH 0x128 @@ -53,6 +55,7 @@ #define PERIPH_IDX 30 #define INTF_IDX 31 #define WB_IDX 16 +#define CWB_IDX 28 #define DSPP_IDX 29 /* From DPU hw rev 7.x.x */ #define CTL_INVALID_BIT 0xffff #define CTL_DEFAULT_GROUP_ID 0xf @@ -110,6 +113,7 @@ static inline void dpu_hw_ctl_clear_pending_flush(struct dpu_hw_ctl *ctx) ctx->pending_flush_mask = 0x0; ctx->pending_intf_flush_mask = 0; ctx->pending_wb_flush_mask = 0; + ctx->pending_cwb_flush_mask = 0; ctx->pending_merge_3d_flush_mask = 0; ctx->pending_dsc_flush_mask = 0; ctx->pending_cdm_flush_mask = 0; @@ -144,6 +148,9 @@ static inline void dpu_hw_ctl_trigger_flush_v1(struct dpu_hw_ctl *ctx) if (ctx->pending_flush_mask & BIT(WB_IDX)) DPU_REG_WRITE(&ctx->hw, CTL_WB_FLUSH, ctx->pending_wb_flush_mask); + if (ctx->pending_flush_mask & BIT(CWB_IDX)) + DPU_REG_WRITE(&ctx->hw, CTL_CWB_FLUSH, + ctx->pending_cwb_flush_mask); if (ctx->pending_flush_mask & BIT(DSPP_IDX)) for (dspp = DSPP_0; dspp < DSPP_MAX; dspp++) { @@ -254,6 +261,12 @@ static void dpu_hw_ctl_update_pending_flush_mixer(struct dpu_hw_ctl *ctx, case LM_5: ctx->pending_flush_mask |= BIT(20); break; + case LM_6: + ctx->pending_flush_mask |= BIT(21); + break; + case LM_7: + ctx->pending_flush_mask |= BIT(27); + break; default: break; } @@ -310,6 +323,13 @@ static void dpu_hw_ctl_update_pending_flush_wb_v1(struct dpu_hw_ctl *ctx, ctx->pending_flush_mask |= BIT(WB_IDX); } +static void dpu_hw_ctl_update_pending_flush_cwb_v1(struct dpu_hw_ctl *ctx, + enum dpu_cwb cwb) +{ + ctx->pending_cwb_flush_mask |= BIT(cwb - CWB_0); + ctx->pending_flush_mask |= BIT(CWB_IDX); +} + static void dpu_hw_ctl_update_pending_flush_intf_v1(struct dpu_hw_ctl *ctx, enum dpu_intf intf) { @@ -547,7 +567,9 @@ static void dpu_hw_ctl_intf_cfg_v1(struct dpu_hw_ctl *ctx, u32 intf_active = 0; u32 dsc_active = 0; u32 wb_active = 0; + u32 cwb_active = 0; u32 mode_sel = 0; + u32 merge_3d_active = 0; /* CTL_TOP[31:28] carries group_id to collate CTL paths * per VM. Explicitly disable it until VM support is @@ -561,7 +583,9 @@ static void dpu_hw_ctl_intf_cfg_v1(struct dpu_hw_ctl *ctx, intf_active = DPU_REG_READ(c, CTL_INTF_ACTIVE); wb_active = DPU_REG_READ(c, CTL_WB_ACTIVE); + cwb_active = DPU_REG_READ(c, CTL_CWB_ACTIVE); dsc_active = DPU_REG_READ(c, CTL_DSC_ACTIVE); + merge_3d_active = DPU_REG_READ(c, CTL_MERGE_3D_ACTIVE); if (cfg->intf) intf_active |= BIT(cfg->intf - INTF_0); @@ -569,17 +593,24 @@ static void dpu_hw_ctl_intf_cfg_v1(struct dpu_hw_ctl *ctx, if (cfg->wb) wb_active |= BIT(cfg->wb - WB_0); + if (cfg->cwb) + cwb_active |= cfg->cwb; + if (cfg->dsc) dsc_active |= cfg->dsc; + if (cfg->merge_3d) + merge_3d_active |= BIT(cfg->merge_3d - MERGE_3D_0); + DPU_REG_WRITE(c, CTL_TOP, mode_sel); DPU_REG_WRITE(c, CTL_INTF_ACTIVE, intf_active); DPU_REG_WRITE(c, CTL_WB_ACTIVE, wb_active); + DPU_REG_WRITE(c, CTL_CWB_ACTIVE, cwb_active); DPU_REG_WRITE(c, CTL_DSC_ACTIVE, dsc_active); + DPU_REG_WRITE(c, CTL_MERGE_3D_ACTIVE, merge_3d_active); - if (cfg->merge_3d) - DPU_REG_WRITE(c, CTL_MERGE_3D_ACTIVE, - BIT(cfg->merge_3d - MERGE_3D_0)); + if (cfg->intf_master) + DPU_REG_WRITE(c, CTL_INTF_MASTER, BIT(cfg->intf_master - INTF_0)); if (cfg->cdm) DPU_REG_WRITE(c, CTL_CDM_ACTIVE, cfg->cdm); @@ -623,7 +654,9 @@ static void dpu_hw_ctl_reset_intf_cfg_v1(struct dpu_hw_ctl *ctx, { struct dpu_hw_blk_reg_map *c = &ctx->hw; u32 intf_active = 0; + u32 intf_master = 0; u32 wb_active = 0; + u32 cwb_active = 0; u32 merge3d_active = 0; u32 dsc_active; u32 cdm_active; @@ -645,10 +678,27 @@ static void dpu_hw_ctl_reset_intf_cfg_v1(struct dpu_hw_ctl *ctx, dpu_hw_ctl_clear_all_blendstages(ctx); + if (ctx->ops.set_active_fetch_pipes) + ctx->ops.set_active_fetch_pipes(ctx, NULL); + if (cfg->intf) { intf_active = DPU_REG_READ(c, CTL_INTF_ACTIVE); intf_active &= ~BIT(cfg->intf - INTF_0); DPU_REG_WRITE(c, CTL_INTF_ACTIVE, intf_active); + + intf_master = DPU_REG_READ(c, CTL_INTF_MASTER); + + /* Unset this intf as master, if it is the current master */ + if (intf_master == BIT(cfg->intf - INTF_0)) { + DPU_DEBUG_DRIVER("Unsetting INTF_%d master\n", cfg->intf - INTF_0); + DPU_REG_WRITE(c, CTL_INTF_MASTER, 0); + } + } + + if (cfg->cwb) { + cwb_active = DPU_REG_READ(c, CTL_CWB_ACTIVE); + cwb_active &= ~cfg->cwb; + DPU_REG_WRITE(c, CTL_CWB_ACTIVE, cwb_active); } if (cfg->wb) { @@ -670,8 +720,8 @@ static void dpu_hw_ctl_reset_intf_cfg_v1(struct dpu_hw_ctl *ctx, } } -static void dpu_hw_ctl_set_fetch_pipe_active(struct dpu_hw_ctl *ctx, - unsigned long *fetch_active) +static void dpu_hw_ctl_set_active_fetch_pipes(struct dpu_hw_ctl *ctx, + unsigned long *fetch_active) { int i; u32 val = 0; @@ -703,6 +753,7 @@ static void _setup_ctl_ops(struct dpu_hw_ctl_ops *ops, ops->update_pending_flush_merge_3d = dpu_hw_ctl_update_pending_flush_merge_3d_v1; ops->update_pending_flush_wb = dpu_hw_ctl_update_pending_flush_wb_v1; + ops->update_pending_flush_cwb = dpu_hw_ctl_update_pending_flush_cwb_v1; ops->update_pending_flush_dsc = dpu_hw_ctl_update_pending_flush_dsc_v1; ops->update_pending_flush_cdm = dpu_hw_ctl_update_pending_flush_cdm_v1; @@ -733,7 +784,7 @@ static void _setup_ctl_ops(struct dpu_hw_ctl_ops *ops, ops->update_pending_flush_dspp = dpu_hw_ctl_update_pending_flush_dspp; if (cap & BIT(DPU_CTL_FETCH_ACTIVE)) - ops->set_active_pipes = dpu_hw_ctl_set_fetch_pipe_active; + ops->set_active_fetch_pipes = dpu_hw_ctl_set_active_fetch_pipes; }; /** diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h index 85c6c835cc87..feb09590bc8f 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved. */ #ifndef _DPU_HW_CTL_H @@ -36,21 +36,25 @@ struct dpu_hw_stage_cfg { /** * struct dpu_hw_intf_cfg :Describes how the DPU writes data to output interface * @intf : Interface id + * @intf_master: Master interface id in the dual pipe topology * @mode_3d: 3d mux configuration * @merge_3d: 3d merge block used * @intf_mode_sel: Interface mode, cmd / vid * @cdm: CDM block used * @stream_sel: Stream selection for multi-stream interfaces * @dsc: DSC BIT masks used + * @cwb: CWB BIT masks used */ struct dpu_hw_intf_cfg { enum dpu_intf intf; + enum dpu_intf intf_master; enum dpu_wb wb; enum dpu_3d_blend_mode mode_3d; enum dpu_merge_3d merge_3d; enum dpu_ctl_mode_sel intf_mode_sel; enum dpu_cdm cdm; int stream_sel; + unsigned int cwb; unsigned int dsc; }; @@ -115,6 +119,15 @@ struct dpu_hw_ctl_ops { enum dpu_wb blk); /** + * OR in the given flushbits to the cached pending_(cwb_)flush_mask + * No effect on hardware + * @ctx : ctl path ctx pointer + * @blk : concurrent writeback block index + */ + void (*update_pending_flush_cwb)(struct dpu_hw_ctl *ctx, + enum dpu_cwb blk); + + /** * OR in the given flushbits to the cached pending_(intf_)flush_mask * No effect on hardware * @ctx : ctl path ctx pointer @@ -243,7 +256,7 @@ struct dpu_hw_ctl_ops { void (*setup_blendstage)(struct dpu_hw_ctl *ctx, enum dpu_lm lm, struct dpu_hw_stage_cfg *cfg); - void (*set_active_pipes)(struct dpu_hw_ctl *ctx, + void (*set_active_fetch_pipes)(struct dpu_hw_ctl *ctx, unsigned long *fetch_active); }; @@ -258,6 +271,7 @@ struct dpu_hw_ctl_ops { * @pending_flush_mask: storage for pending ctl_flush managed via ops * @pending_intf_flush_mask: pending INTF flush * @pending_wb_flush_mask: pending WB flush + * @pending_cwb_flush_mask: pending CWB flush * @pending_dsc_flush_mask: pending DSC flush * @pending_cdm_flush_mask: pending CDM flush * @ops: operation list @@ -274,6 +288,7 @@ struct dpu_hw_ctl { u32 pending_flush_mask; u32 pending_intf_flush_mask; u32 pending_wb_flush_mask; + u32 pending_cwb_flush_mask; u32 pending_periph_flush_mask; u32 pending_merge_3d_flush_mask; u32 pending_dspp_flush_mask[DSPP_MAX - DSPP_0]; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cwb.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cwb.c new file mode 100644 index 000000000000..ae785f4ff0d4 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cwb.c @@ -0,0 +1,75 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved + */ + +#include <drm/drm_managed.h> +#include "dpu_hw_cwb.h" + +#include <linux/bitfield.h> + +#define CWB_MUX 0x000 +#define CWB_MODE 0x004 + +/* CWB mux block bit definitions */ +#define CWB_MUX_MASK GENMASK(3, 0) +#define CWB_MODE_MASK GENMASK(2, 0) + +static void dpu_hw_cwb_config(struct dpu_hw_cwb *ctx, + struct dpu_hw_cwb_setup_cfg *cwb_cfg) +{ + struct dpu_hw_blk_reg_map *c = &ctx->hw; + int cwb_mux_cfg = 0xF; + enum dpu_pingpong pp; + enum cwb_mode_input input; + + if (!cwb_cfg) + return; + + input = cwb_cfg->input; + pp = cwb_cfg->pp_idx; + + if (input >= INPUT_MODE_MAX) + return; + + /* + * The CWB_MUX register takes the pingpong index for the real-time + * display + */ + if ((pp != PINGPONG_NONE) && (pp < PINGPONG_MAX)) + cwb_mux_cfg = FIELD_PREP(CWB_MUX_MASK, pp - PINGPONG_0); + + input = FIELD_PREP(CWB_MODE_MASK, input); + + DPU_REG_WRITE(c, CWB_MUX, cwb_mux_cfg); + DPU_REG_WRITE(c, CWB_MODE, input); +} + +/** + * dpu_hw_cwb_init() - Initializes the writeback hw driver object with cwb. + * @dev: Corresponding device for devres management + * @cfg: wb_path catalog entry for which driver object is required + * @addr: mapped register io address of MDP + * Return: Error code or allocated dpu_hw_wb context + */ +struct dpu_hw_cwb *dpu_hw_cwb_init(struct drm_device *dev, + const struct dpu_cwb_cfg *cfg, + void __iomem *addr) +{ + struct dpu_hw_cwb *c; + + if (!addr) + return ERR_PTR(-EINVAL); + + c = drmm_kzalloc(dev, sizeof(*c), GFP_KERNEL); + if (!c) + return ERR_PTR(-ENOMEM); + + c->hw.blk_addr = addr + cfg->base; + c->hw.log_mask = DPU_DBG_MASK_CWB; + + c->idx = cfg->id; + c->ops.config_cwb = dpu_hw_cwb_config; + + return c; +} diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cwb.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cwb.h new file mode 100644 index 000000000000..96b6edf6b2bb --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cwb.h @@ -0,0 +1,70 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved + */ + +#ifndef _DPU_HW_CWB_H +#define _DPU_HW_CWB_H + +#include "dpu_hw_util.h" + +struct dpu_hw_cwb; + +enum cwb_mode_input { + INPUT_MODE_LM_OUT, + INPUT_MODE_DSPP_OUT, + INPUT_MODE_MAX +}; + +/** + * struct dpu_hw_cwb_setup_cfg : Describes configuration for CWB mux + * @pp_idx: Index of the real-time pinpong that the CWB mux will + * feed the CWB mux + * @input: Input tap point + */ +struct dpu_hw_cwb_setup_cfg { + enum dpu_pingpong pp_idx; + enum cwb_mode_input input; +}; + +/** + * + * struct dpu_hw_cwb_ops : Interface to the cwb hw driver functions + * @config_cwb: configure CWB mux + */ +struct dpu_hw_cwb_ops { + void (*config_cwb)(struct dpu_hw_cwb *ctx, + struct dpu_hw_cwb_setup_cfg *cwb_cfg); +}; + +/** + * struct dpu_hw_cwb : CWB mux driver object + * @base: Hardware block base structure + * @hw: Block hardware details + * @idx: CWB index + * @ops: handle to operations possible for this CWB + */ +struct dpu_hw_cwb { + struct dpu_hw_blk base; + struct dpu_hw_blk_reg_map hw; + + enum dpu_cwb idx; + + struct dpu_hw_cwb_ops ops; +}; + +/** + * dpu_hw_cwb - convert base object dpu_hw_base to container + * @hw: Pointer to base hardware block + * return: Pointer to hardware block container + */ +static inline struct dpu_hw_cwb *to_dpu_hw_cwb(struct dpu_hw_blk *hw) +{ + return container_of(hw, struct dpu_hw_cwb, base); +} + +struct dpu_hw_cwb *dpu_hw_cwb_init(struct drm_device *dev, + const struct dpu_cwb_cfg *cfg, + void __iomem *addr); + +#endif /*_DPU_HW_CWB_H */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h index f8806a4d317b..175639c8bfbb 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h @@ -1,5 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-only */ -/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. +/* + * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. */ #ifndef _DPU_HW_MDSS_H @@ -75,12 +77,14 @@ enum dpu_hw_blk_type { DPU_HW_BLK_LM, DPU_HW_BLK_CTL, DPU_HW_BLK_PINGPONG, + DPU_HW_BLK_DCWB_PINGPONG, DPU_HW_BLK_INTF, DPU_HW_BLK_WB, DPU_HW_BLK_DSPP, DPU_HW_BLK_MERGE_3D, DPU_HW_BLK_DSC, DPU_HW_BLK_CDM, + DPU_HW_BLK_CWB, DPU_HW_BLK_MAX, }; @@ -121,6 +125,7 @@ enum dpu_lm { LM_4, LM_5, LM_6, + LM_7, LM_MAX }; @@ -165,6 +170,8 @@ enum dpu_dsc { DSC_3, DSC_4, DSC_5, + DSC_6, + DSC_7, DSC_MAX }; @@ -183,8 +190,10 @@ enum dpu_pingpong { PINGPONG_5, PINGPONG_6, PINGPONG_7, - PINGPONG_8, - PINGPONG_9, + PINGPONG_CWB_0, + PINGPONG_CWB_1, + PINGPONG_CWB_2, + PINGPONG_CWB_3, PINGPONG_S0, PINGPONG_MAX }; @@ -195,6 +204,7 @@ enum dpu_merge_3d { MERGE_3D_2, MERGE_3D_3, MERGE_3D_4, + MERGE_3D_5, MERGE_3D_MAX }; @@ -350,6 +360,7 @@ struct dpu_mdss_color { #define DPU_DBG_MASK_DSPP (1 << 10) #define DPU_DBG_MASK_DSC (1 << 11) #define DPU_DBG_MASK_CDM (1 << 12) +#define DPU_DBG_MASK_CWB (1 << 13) /** * struct dpu_hw_tear_check - Struct contains parameters to configure diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c index fb9f90957762..4853e516c487 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_wb.c @@ -173,7 +173,9 @@ static void dpu_hw_wb_bind_pingpong_blk( mux_cfg = DPU_REG_READ(c, WB_MUX); mux_cfg &= ~0xf; - if (pp) + if (pp >= PINGPONG_CWB_0) + mux_cfg |= (pp < PINGPONG_CWB_2) ? 0xd : 0xb; + else if (pp) mux_cfg |= (pp - PINGPONG_0) & 0x7; else mux_cfg |= 0xf; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c index 8b251f87a052..1fd82b6747e9 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c @@ -2,7 +2,7 @@ /* * Copyright (C) 2013 Red Hat * Copyright (c) 2014-2018, The Linux Foundation. All rights reserved. - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved. * * Author: Rob Clark <robdclark@gmail.com> */ @@ -51,6 +51,9 @@ #define DPU_DEBUGFS_DIR "msm_dpu" #define DPU_DEBUGFS_HWMASKNAME "hw_log_mask" +bool dpu_use_virtual_planes; +module_param(dpu_use_virtual_planes, bool, 0); + static int dpu_kms_hw_init(struct msm_kms *kms); static void _dpu_kms_mmu_destroy(struct dpu_kms *dpu_kms); @@ -443,6 +446,19 @@ static void dpu_kms_disable_commit(struct msm_kms *kms) pm_runtime_put_sync(&dpu_kms->pdev->dev); } +static int dpu_kms_check_mode_changed(struct msm_kms *kms, struct drm_atomic_state *state) +{ + struct drm_crtc_state *new_crtc_state; + struct drm_crtc_state *old_crtc_state; + struct drm_crtc *crtc; + int i; + + for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) + dpu_crtc_check_mode_changed(old_crtc_state, new_crtc_state); + + return 0; +} + static void dpu_kms_flush_commit(struct msm_kms *kms, unsigned crtc_mask) { struct dpu_kms *dpu_kms = to_dpu_kms(kms); @@ -808,8 +824,11 @@ static int _dpu_kms_drm_obj_init(struct dpu_kms *dpu_kms) return ret; num_encoders = 0; - drm_for_each_encoder(encoder, dev) + drm_for_each_encoder(encoder, dev) { num_encoders++; + if (catalog->cwb_count > 0) + encoder->possible_clones = dpu_encoder_get_clones(encoder); + } max_crtc_count = min(catalog->mixer_count, num_encoders); @@ -829,8 +848,11 @@ static int _dpu_kms_drm_obj_init(struct dpu_kms *dpu_kms) type, catalog->sspp[i].features, catalog->sspp[i].features & BIT(DPU_SSPP_CURSOR)); - plane = dpu_plane_init(dev, catalog->sspp[i].id, type, - (1UL << max_crtc_count) - 1); + if (dpu_use_virtual_planes) + plane = dpu_plane_init_virtual(dev, type, (1UL << max_crtc_count) - 1); + else + plane = dpu_plane_init(dev, catalog->sspp[i].id, type, + (1UL << max_crtc_count) - 1); if (IS_ERR(plane)) { DPU_ERROR("dpu_plane_init failed\n"); ret = PTR_ERR(plane); @@ -932,12 +954,14 @@ static void dpu_kms_mdp_snapshot(struct msm_disp_state *disp_state, struct msm_k /* dump CTL sub-blocks HW regs info */ for (i = 0; i < cat->ctl_count; i++) msm_disp_snapshot_add_block(disp_state, cat->ctl[i].len, - dpu_kms->mmio + cat->ctl[i].base, cat->ctl[i].name); + dpu_kms->mmio + cat->ctl[i].base, "%s", + cat->ctl[i].name); /* dump DSPP sub-blocks HW regs info */ for (i = 0; i < cat->dspp_count; i++) { base = dpu_kms->mmio + cat->dspp[i].base; - msm_disp_snapshot_add_block(disp_state, cat->dspp[i].len, base, cat->dspp[i].name); + msm_disp_snapshot_add_block(disp_state, cat->dspp[i].len, base, + "%s", cat->dspp[i].name); if (cat->dspp[i].sblk && cat->dspp[i].sblk->pcc.len > 0) msm_disp_snapshot_add_block(disp_state, cat->dspp[i].sblk->pcc.len, @@ -949,13 +973,14 @@ static void dpu_kms_mdp_snapshot(struct msm_disp_state *disp_state, struct msm_k /* dump INTF sub-blocks HW regs info */ for (i = 0; i < cat->intf_count; i++) msm_disp_snapshot_add_block(disp_state, cat->intf[i].len, - dpu_kms->mmio + cat->intf[i].base, cat->intf[i].name); + dpu_kms->mmio + cat->intf[i].base, "%s", + cat->intf[i].name); /* dump PP sub-blocks HW regs info */ for (i = 0; i < cat->pingpong_count; i++) { base = dpu_kms->mmio + cat->pingpong[i].base; msm_disp_snapshot_add_block(disp_state, cat->pingpong[i].len, base, - cat->pingpong[i].name); + "%s", cat->pingpong[i].name); /* TE2 sub-block has length of 0, so will not print it */ @@ -969,7 +994,8 @@ static void dpu_kms_mdp_snapshot(struct msm_disp_state *disp_state, struct msm_k /* dump SSPP sub-blocks HW regs info */ for (i = 0; i < cat->sspp_count; i++) { base = dpu_kms->mmio + cat->sspp[i].base; - msm_disp_snapshot_add_block(disp_state, cat->sspp[i].len, base, cat->sspp[i].name); + msm_disp_snapshot_add_block(disp_state, cat->sspp[i].len, base, + "%s", cat->sspp[i].name); if (cat->sspp[i].sblk && cat->sspp[i].sblk->scaler_blk.len > 0) msm_disp_snapshot_add_block(disp_state, cat->sspp[i].sblk->scaler_blk.len, @@ -987,12 +1013,14 @@ static void dpu_kms_mdp_snapshot(struct msm_disp_state *disp_state, struct msm_k /* dump LM sub-blocks HW regs info */ for (i = 0; i < cat->mixer_count; i++) msm_disp_snapshot_add_block(disp_state, cat->mixer[i].len, - dpu_kms->mmio + cat->mixer[i].base, cat->mixer[i].name); + dpu_kms->mmio + cat->mixer[i].base, + "%s", cat->mixer[i].name); /* dump WB sub-blocks HW regs info */ for (i = 0; i < cat->wb_count; i++) msm_disp_snapshot_add_block(disp_state, cat->wb[i].len, - dpu_kms->mmio + cat->wb[i].base, cat->wb[i].name); + dpu_kms->mmio + cat->wb[i].base, "%s", + cat->wb[i].name); if (cat->mdp[0].features & BIT(DPU_MDP_PERIPH_0_REMOVED)) { msm_disp_snapshot_add_block(disp_state, MDP_PERIPH_TOP0, @@ -1004,10 +1032,16 @@ static void dpu_kms_mdp_snapshot(struct msm_disp_state *disp_state, struct msm_k dpu_kms->mmio + cat->mdp[0].base, "top"); } + /* dump CWB sub-blocks HW regs info */ + for (i = 0; i < cat->cwb_count; i++) + msm_disp_snapshot_add_block(disp_state, cat->cwb[i].len, + dpu_kms->mmio + cat->cwb[i].base, cat->cwb[i].name); + /* dump DSC sub-blocks HW regs info */ for (i = 0; i < cat->dsc_count; i++) { base = dpu_kms->mmio + cat->dsc[i].base; - msm_disp_snapshot_add_block(disp_state, cat->dsc[i].len, base, cat->dsc[i].name); + msm_disp_snapshot_add_block(disp_state, cat->dsc[i].len, base, + "%s", cat->dsc[i].name); if (cat->dsc[i].features & BIT(DPU_DSC_HW_REV_1_2)) { struct dpu_dsc_blk enc = cat->dsc[i].sblk->enc; @@ -1022,7 +1056,16 @@ static void dpu_kms_mdp_snapshot(struct msm_disp_state *disp_state, struct msm_k if (cat->cdm) msm_disp_snapshot_add_block(disp_state, cat->cdm->len, - dpu_kms->mmio + cat->cdm->base, cat->cdm->name); + dpu_kms->mmio + cat->cdm->base, + "%s", cat->cdm->name); + + for (i = 0; i < dpu_kms->catalog->vbif_count; i++) { + const struct dpu_vbif_cfg *vbif = &dpu_kms->catalog->vbif[i]; + + msm_disp_snapshot_add_block(disp_state, vbif->len, + dpu_kms->vbif[vbif->id] + vbif->base, + "%s", vbif->name); + } pm_runtime_put_sync(&dpu_kms->pdev->dev); } @@ -1035,6 +1078,7 @@ static const struct msm_kms_funcs kms_funcs = { .irq = dpu_core_irq, .enable_commit = dpu_kms_enable_commit, .disable_commit = dpu_kms_disable_commit, + .check_mode_changed = dpu_kms_check_mode_changed, .flush_commit = dpu_kms_flush_commit, .wait_flush = dpu_kms_wait_flush, .complete_commit = dpu_kms_complete_commit, @@ -1468,6 +1512,7 @@ static const struct of_device_id dpu_dt_match[] = { { .compatible = "qcom,msm8998-dpu", .data = &dpu_msm8998_cfg, }, { .compatible = "qcom,qcm2290-dpu", .data = &dpu_qcm2290_cfg, }, { .compatible = "qcom,sa8775p-dpu", .data = &dpu_sa8775p_cfg, }, + { .compatible = "qcom,sar2130p-dpu", .data = &dpu_sar2130p_cfg, }, { .compatible = "qcom,sdm630-mdp5", .data = &dpu_sdm630_cfg, }, { .compatible = "qcom,sdm660-mdp5", .data = &dpu_sdm660_cfg, }, { .compatible = "qcom,sdm670-dpu", .data = &dpu_sdm670_cfg, }, @@ -1478,6 +1523,7 @@ static const struct of_device_id dpu_dt_match[] = { { .compatible = "qcom,sc8280xp-dpu", .data = &dpu_sc8280xp_cfg, }, { .compatible = "qcom,sm6115-dpu", .data = &dpu_sm6115_cfg, }, { .compatible = "qcom,sm6125-dpu", .data = &dpu_sm6125_cfg, }, + { .compatible = "qcom,sm6150-dpu", .data = &dpu_sm6150_cfg, }, { .compatible = "qcom,sm6350-dpu", .data = &dpu_sm6350_cfg, }, { .compatible = "qcom,sm6375-dpu", .data = &dpu_sm6375_cfg, }, { .compatible = "qcom,sm7150-dpu", .data = &dpu_sm7150_cfg, }, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h index 88d64d43ea1a..a57ec2ec1060 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h @@ -54,6 +54,8 @@ #define ktime_compare_safe(A, B) \ ktime_compare(ktime_sub((A), (B)), ktime_set(0, 0)) +extern bool dpu_use_virtual_planes; + struct dpu_kms { struct msm_kms base; struct drm_device *dev; @@ -122,12 +124,15 @@ struct dpu_global_state { struct dpu_rm *rm; - uint32_t pingpong_to_enc_id[PINGPONG_MAX - PINGPONG_0]; - uint32_t mixer_to_enc_id[LM_MAX - LM_0]; - uint32_t ctl_to_enc_id[CTL_MAX - CTL_0]; - uint32_t dspp_to_enc_id[DSPP_MAX - DSPP_0]; - uint32_t dsc_to_enc_id[DSC_MAX - DSC_0]; - uint32_t cdm_to_enc_id; + uint32_t pingpong_to_crtc_id[PINGPONG_MAX - PINGPONG_0]; + uint32_t mixer_to_crtc_id[LM_MAX - LM_0]; + uint32_t ctl_to_crtc_id[CTL_MAX - CTL_0]; + uint32_t dspp_to_crtc_id[DSPP_MAX - DSPP_0]; + uint32_t dsc_to_crtc_id[DSC_MAX - DSC_0]; + uint32_t cdm_to_crtc_id; + + uint32_t sspp_to_crtc_id[SSPP_MAX - SSPP_NONE]; + uint32_t cwb_to_crtc_id[CWB_MAX - CWB_0]; }; struct dpu_global_state diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c index 703e58901d53..421138bc3cb7 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c @@ -20,7 +20,6 @@ #include "msm_drv.h" #include "msm_mdss.h" #include "dpu_kms.h" -#include "dpu_formats.h" #include "dpu_hw_sspp.h" #include "dpu_hw_util.h" #include "dpu_trace.h" @@ -730,12 +729,40 @@ static int dpu_plane_check_inline_rotation(struct dpu_plane *pdpu, static int dpu_plane_atomic_check_pipe(struct dpu_plane *pdpu, struct dpu_sw_pipe *pipe, struct dpu_sw_pipe_cfg *pipe_cfg, - const struct msm_format *fmt, - const struct drm_display_mode *mode) + const struct drm_display_mode *mode, + struct drm_plane_state *new_plane_state) { uint32_t min_src_size; struct dpu_kms *kms = _dpu_plane_get_kms(&pdpu->base); int ret; + const struct msm_format *fmt; + uint32_t supported_rotations; + const struct dpu_sspp_cfg *pipe_hw_caps; + const struct dpu_sspp_sub_blks *sblk; + + pipe_hw_caps = pipe->sspp->cap; + sblk = pipe->sspp->cap->sblk; + + /* + * We already have verified scaling against platform limitations. + * Now check if the SSPP supports scaling at all. + */ + if (!sblk->scaler_blk.len && + ((drm_rect_width(&new_plane_state->src) >> 16 != + drm_rect_width(&new_plane_state->dst)) || + (drm_rect_height(&new_plane_state->src) >> 16 != + drm_rect_height(&new_plane_state->dst)))) + return -ERANGE; + + fmt = msm_framebuffer_format(new_plane_state->fb); + + supported_rotations = DRM_MODE_REFLECT_MASK | DRM_MODE_ROTATE_0; + + if (pipe_hw_caps->features & BIT(DPU_SSPP_INLINE_ROTATION)) + supported_rotations |= DRM_MODE_ROTATE_90; + + pipe_cfg->rotation = drm_rotation_simplify(new_plane_state->rotation, + supported_rotations); min_src_size = MSM_FORMAT_IS_YUV(fmt) ? 2 : 1; @@ -878,7 +905,7 @@ static int dpu_plane_atomic_check_nosspp(struct drm_plane *plane, drm_rect_rotate_inv(&pipe_cfg->src_rect, new_plane_state->fb->width, new_plane_state->fb->height, new_plane_state->rotation); - if (r_pipe_cfg->src_rect.x1 != 0) + if (drm_rect_width(&r_pipe_cfg->src_rect) != 0) drm_rect_rotate_inv(&r_pipe_cfg->src_rect, new_plane_state->fb->width, new_plane_state->fb->height, new_plane_state->rotation); @@ -888,6 +915,48 @@ static int dpu_plane_atomic_check_nosspp(struct drm_plane *plane, return 0; } +static int dpu_plane_is_multirect_capable(struct dpu_hw_sspp *sspp, + struct dpu_sw_pipe_cfg *pipe_cfg, + const struct msm_format *fmt) +{ + if (drm_rect_width(&pipe_cfg->src_rect) != drm_rect_width(&pipe_cfg->dst_rect) || + drm_rect_height(&pipe_cfg->src_rect) != drm_rect_height(&pipe_cfg->dst_rect)) + return false; + + if (pipe_cfg->rotation & DRM_MODE_ROTATE_90) + return false; + + if (MSM_FORMAT_IS_YUV(fmt)) + return false; + + if (!test_bit(DPU_SSPP_SMART_DMA_V1, &sspp->cap->features) && + !test_bit(DPU_SSPP_SMART_DMA_V2, &sspp->cap->features)) + return false; + + return true; +} + +static int dpu_plane_is_parallel_capable(struct dpu_sw_pipe_cfg *pipe_cfg, + const struct msm_format *fmt, + uint32_t max_linewidth) +{ + if (MSM_FORMAT_IS_UBWC(fmt) && + drm_rect_width(&pipe_cfg->src_rect) > max_linewidth / 2) + return false; + + return true; +} + +static int dpu_plane_is_multirect_parallel_capable(struct dpu_hw_sspp *sspp, + struct dpu_sw_pipe_cfg *pipe_cfg, + const struct msm_format *fmt, + uint32_t max_linewidth) +{ + return dpu_plane_is_multirect_capable(sspp, pipe_cfg, fmt) && + dpu_plane_is_parallel_capable(pipe_cfg, fmt, max_linewidth); +} + + static int dpu_plane_atomic_check_sspp(struct drm_plane *plane, struct drm_atomic_state *state, const struct drm_crtc_state *crtc_state) @@ -898,90 +967,118 @@ static int dpu_plane_atomic_check_sspp(struct drm_plane *plane, struct dpu_plane_state *pstate = to_dpu_plane_state(new_plane_state); struct dpu_sw_pipe *pipe = &pstate->pipe; struct dpu_sw_pipe *r_pipe = &pstate->r_pipe; - const struct msm_format *fmt; struct dpu_sw_pipe_cfg *pipe_cfg = &pstate->pipe_cfg; struct dpu_sw_pipe_cfg *r_pipe_cfg = &pstate->r_pipe_cfg; - uint32_t max_linewidth; - uint32_t supported_rotations; - const struct dpu_sspp_cfg *pipe_hw_caps; - const struct dpu_sspp_sub_blks *sblk; int ret = 0; - pipe_hw_caps = pipe->sspp->cap; - sblk = pipe->sspp->cap->sblk; - - /* - * We already have verified scaling against platform limitations. - * Now check if the SSPP supports scaling at all. - */ - if (!sblk->scaler_blk.len && - ((drm_rect_width(&new_plane_state->src) >> 16 != - drm_rect_width(&new_plane_state->dst)) || - (drm_rect_height(&new_plane_state->src) >> 16 != - drm_rect_height(&new_plane_state->dst)))) - return -ERANGE; - - fmt = msm_framebuffer_format(new_plane_state->fb); + ret = dpu_plane_atomic_check_pipe(pdpu, pipe, pipe_cfg, + &crtc_state->adjusted_mode, + new_plane_state); + if (ret) + return ret; - max_linewidth = pdpu->catalog->caps->max_linewidth; + if (drm_rect_width(&r_pipe_cfg->src_rect) != 0) { + ret = dpu_plane_atomic_check_pipe(pdpu, r_pipe, r_pipe_cfg, + &crtc_state->adjusted_mode, + new_plane_state); + if (ret) + return ret; + } - supported_rotations = DRM_MODE_REFLECT_MASK | DRM_MODE_ROTATE_0; + return 0; +} - if (pipe_hw_caps->features & BIT(DPU_SSPP_INLINE_ROTATION)) - supported_rotations |= DRM_MODE_ROTATE_90; +static bool dpu_plane_try_multirect_parallel(struct dpu_sw_pipe *pipe, struct dpu_sw_pipe_cfg *pipe_cfg, + struct dpu_sw_pipe *r_pipe, struct dpu_sw_pipe_cfg *r_pipe_cfg, + struct dpu_hw_sspp *sspp, const struct msm_format *fmt, + uint32_t max_linewidth) +{ + r_pipe->sspp = NULL; - pipe_cfg->rotation = drm_rotation_simplify(new_plane_state->rotation, - supported_rotations); - r_pipe_cfg->rotation = pipe_cfg->rotation; + pipe->multirect_index = DPU_SSPP_RECT_SOLO; + pipe->multirect_mode = DPU_SSPP_MULTIRECT_NONE; - ret = dpu_plane_atomic_check_pipe(pdpu, pipe, pipe_cfg, fmt, - &crtc_state->adjusted_mode); - if (ret) - return ret; + r_pipe->multirect_index = DPU_SSPP_RECT_SOLO; + r_pipe->multirect_mode = DPU_SSPP_MULTIRECT_NONE; if (drm_rect_width(&r_pipe_cfg->src_rect) != 0) { - /* - * In parallel multirect case only the half of the usual width - * is supported for tiled formats. If we are here, we know that - * full width is more than max_linewidth, thus each rect is - * wider than allowed. - */ - if (MSM_FORMAT_IS_UBWC(fmt) && - drm_rect_width(&pipe_cfg->src_rect) > max_linewidth) { - DPU_DEBUG_PLANE(pdpu, "invalid src " DRM_RECT_FMT " line:%u, tiled format\n", - DRM_RECT_ARG(&pipe_cfg->src_rect), max_linewidth); - return -E2BIG; - } + if (!dpu_plane_is_multirect_parallel_capable(pipe->sspp, pipe_cfg, fmt, max_linewidth) || + !dpu_plane_is_multirect_parallel_capable(pipe->sspp, r_pipe_cfg, fmt, max_linewidth)) + return false; - if (drm_rect_width(&pipe_cfg->src_rect) != drm_rect_width(&pipe_cfg->dst_rect) || - drm_rect_height(&pipe_cfg->src_rect) != drm_rect_height(&pipe_cfg->dst_rect) || - (!test_bit(DPU_SSPP_SMART_DMA_V1, &pipe->sspp->cap->features) && - !test_bit(DPU_SSPP_SMART_DMA_V2, &pipe->sspp->cap->features)) || - pipe_cfg->rotation & DRM_MODE_ROTATE_90 || - MSM_FORMAT_IS_YUV(fmt)) { - DPU_DEBUG_PLANE(pdpu, "invalid src " DRM_RECT_FMT " line:%u, can't use split source\n", - DRM_RECT_ARG(&pipe_cfg->src_rect), max_linewidth); - return -E2BIG; - } + r_pipe->sspp = pipe->sspp; - /* - * Use multirect for wide plane. We do not support dynamic - * assignment of SSPPs, so we know the configuration. - */ pipe->multirect_index = DPU_SSPP_RECT_0; pipe->multirect_mode = DPU_SSPP_MULTIRECT_PARALLEL; - r_pipe->sspp = pipe->sspp; r_pipe->multirect_index = DPU_SSPP_RECT_1; r_pipe->multirect_mode = DPU_SSPP_MULTIRECT_PARALLEL; + } - ret = dpu_plane_atomic_check_pipe(pdpu, r_pipe, r_pipe_cfg, fmt, - &crtc_state->adjusted_mode); - if (ret) - return ret; + return true; +} + +static int dpu_plane_try_multirect_shared(struct dpu_plane_state *pstate, + struct dpu_plane_state *prev_adjacent_pstate, + const struct msm_format *fmt, + uint32_t max_linewidth) +{ + struct dpu_sw_pipe *pipe = &pstate->pipe; + struct dpu_sw_pipe *r_pipe = &pstate->r_pipe; + struct dpu_sw_pipe_cfg *pipe_cfg = &pstate->pipe_cfg; + struct dpu_sw_pipe *prev_pipe = &prev_adjacent_pstate->pipe; + struct dpu_sw_pipe_cfg *prev_pipe_cfg = &prev_adjacent_pstate->pipe_cfg; + const struct msm_format *prev_fmt = msm_framebuffer_format(prev_adjacent_pstate->base.fb); + u16 max_tile_height = 1; + + if (prev_adjacent_pstate->r_pipe.sspp != NULL || + prev_pipe->multirect_mode != DPU_SSPP_MULTIRECT_NONE) + return false; + + if (!dpu_plane_is_multirect_capable(pipe->sspp, pipe_cfg, fmt) || + !dpu_plane_is_multirect_capable(prev_pipe->sspp, prev_pipe_cfg, prev_fmt)) + return false; + + if (MSM_FORMAT_IS_UBWC(fmt)) + max_tile_height = max(max_tile_height, fmt->tile_height); + + if (MSM_FORMAT_IS_UBWC(prev_fmt)) + max_tile_height = max(max_tile_height, prev_fmt->tile_height); + + r_pipe->multirect_index = DPU_SSPP_RECT_SOLO; + r_pipe->multirect_mode = DPU_SSPP_MULTIRECT_NONE; + + r_pipe->sspp = NULL; + + if (dpu_plane_is_parallel_capable(pipe_cfg, fmt, max_linewidth) && + dpu_plane_is_parallel_capable(prev_pipe_cfg, prev_fmt, max_linewidth) && + (pipe_cfg->dst_rect.x1 >= prev_pipe_cfg->dst_rect.x2 || + prev_pipe_cfg->dst_rect.x1 >= pipe_cfg->dst_rect.x2)) { + pipe->sspp = prev_pipe->sspp; + + pipe->multirect_index = DPU_SSPP_RECT_1; + pipe->multirect_mode = DPU_SSPP_MULTIRECT_PARALLEL; + + prev_pipe->multirect_index = DPU_SSPP_RECT_0; + prev_pipe->multirect_mode = DPU_SSPP_MULTIRECT_PARALLEL; + + return true; } - return 0; + if (pipe_cfg->dst_rect.y1 >= prev_pipe_cfg->dst_rect.y2 + 2 * max_tile_height || + prev_pipe_cfg->dst_rect.y1 >= pipe_cfg->dst_rect.y2 + 2 * max_tile_height) { + pipe->sspp = prev_pipe->sspp; + + pipe->multirect_index = DPU_SSPP_RECT_1; + pipe->multirect_mode = DPU_SSPP_MULTIRECT_TIME_MX; + + prev_pipe->multirect_index = DPU_SSPP_RECT_0; + prev_pipe->multirect_mode = DPU_SSPP_MULTIRECT_TIME_MX; + + return true; + } + + return false; } static int dpu_plane_atomic_check(struct drm_plane *plane, @@ -995,14 +1092,19 @@ static int dpu_plane_atomic_check(struct drm_plane *plane, struct dpu_kms *dpu_kms = _dpu_plane_get_kms(plane); struct dpu_sw_pipe *pipe = &pstate->pipe; struct dpu_sw_pipe *r_pipe = &pstate->r_pipe; + struct dpu_sw_pipe_cfg *pipe_cfg = &pstate->pipe_cfg; + struct dpu_sw_pipe_cfg *r_pipe_cfg = &pstate->r_pipe_cfg; const struct drm_crtc_state *crtc_state = NULL; + uint32_t max_linewidth = dpu_kms->catalog->caps->max_linewidth; if (new_plane_state->crtc) crtc_state = drm_atomic_get_new_crtc_state(state, new_plane_state->crtc); pipe->sspp = dpu_rm_get_sspp(&dpu_kms->rm, pdpu->pipe); - r_pipe->sspp = NULL; + + if (!pipe->sspp) + return -EINVAL; ret = dpu_plane_atomic_check_nosspp(plane, new_plane_state, crtc_state); if (ret) @@ -1011,14 +1113,182 @@ static int dpu_plane_atomic_check(struct drm_plane *plane, if (!new_plane_state->visible) return 0; - pipe->multirect_index = DPU_SSPP_RECT_SOLO; - pipe->multirect_mode = DPU_SSPP_MULTIRECT_NONE; - r_pipe->multirect_index = DPU_SSPP_RECT_SOLO; - r_pipe->multirect_mode = DPU_SSPP_MULTIRECT_NONE; + if (!dpu_plane_try_multirect_parallel(pipe, pipe_cfg, r_pipe, r_pipe_cfg, + pipe->sspp, + msm_framebuffer_format(new_plane_state->fb), + max_linewidth)) { + DPU_DEBUG_PLANE(pdpu, "invalid " DRM_RECT_FMT " /" DRM_RECT_FMT + " max_line:%u, can't use split source\n", + DRM_RECT_ARG(&pipe_cfg->src_rect), + DRM_RECT_ARG(&r_pipe_cfg->src_rect), + max_linewidth); + return -E2BIG; + } return dpu_plane_atomic_check_sspp(plane, state, crtc_state); } +static int dpu_plane_virtual_atomic_check(struct drm_plane *plane, + struct drm_atomic_state *state) +{ + struct drm_plane_state *plane_state = + drm_atomic_get_plane_state(state, plane); + struct drm_plane_state *old_plane_state = + drm_atomic_get_old_plane_state(state, plane); + struct dpu_plane_state *pstate = to_dpu_plane_state(plane_state); + struct drm_crtc_state *crtc_state; + int ret; + + if (IS_ERR(plane_state)) + return PTR_ERR(plane_state); + + if (plane_state->crtc) + crtc_state = drm_atomic_get_new_crtc_state(state, + plane_state->crtc); + + ret = dpu_plane_atomic_check_nosspp(plane, plane_state, crtc_state); + if (ret) + return ret; + + if (!plane_state->visible) { + /* + * resources are freed by dpu_crtc_assign_plane_resources(), + * but clean them here. + */ + pstate->pipe.sspp = NULL; + pstate->r_pipe.sspp = NULL; + + return 0; + } + + /* + * Force resource reallocation if the format of FB or src/dst have + * changed. We might need to allocate different SSPP or SSPPs for this + * plane than the one used previously. + */ + if (!old_plane_state || !old_plane_state->fb || + old_plane_state->src_w != plane_state->src_w || + old_plane_state->src_h != plane_state->src_h || + old_plane_state->src_w != plane_state->src_w || + old_plane_state->crtc_h != plane_state->crtc_h || + msm_framebuffer_format(old_plane_state->fb) != + msm_framebuffer_format(plane_state->fb)) + crtc_state->planes_changed = true; + + return 0; +} + +static int dpu_plane_virtual_assign_resources(struct drm_crtc *crtc, + struct dpu_global_state *global_state, + struct drm_atomic_state *state, + struct drm_plane_state *plane_state, + struct drm_plane_state *prev_adjacent_plane_state) +{ + const struct drm_crtc_state *crtc_state = NULL; + struct drm_plane *plane = plane_state->plane; + struct dpu_kms *dpu_kms = _dpu_plane_get_kms(plane); + struct dpu_rm_sspp_requirements reqs; + struct dpu_plane_state *pstate, *prev_adjacent_pstate; + struct dpu_sw_pipe *pipe; + struct dpu_sw_pipe *r_pipe; + struct dpu_sw_pipe_cfg *pipe_cfg; + struct dpu_sw_pipe_cfg *r_pipe_cfg; + const struct msm_format *fmt; + + if (plane_state->crtc) + crtc_state = drm_atomic_get_new_crtc_state(state, + plane_state->crtc); + + pstate = to_dpu_plane_state(plane_state); + prev_adjacent_pstate = prev_adjacent_plane_state ? + to_dpu_plane_state(prev_adjacent_plane_state) : NULL; + pipe = &pstate->pipe; + r_pipe = &pstate->r_pipe; + pipe_cfg = &pstate->pipe_cfg; + r_pipe_cfg = &pstate->r_pipe_cfg; + + pipe->sspp = NULL; + r_pipe->sspp = NULL; + + if (!plane_state->fb) + return -EINVAL; + + fmt = msm_framebuffer_format(plane_state->fb); + reqs.yuv = MSM_FORMAT_IS_YUV(fmt); + reqs.scale = (plane_state->src_w >> 16 != plane_state->crtc_w) || + (plane_state->src_h >> 16 != plane_state->crtc_h); + + reqs.rot90 = drm_rotation_90_or_270(plane_state->rotation); + + if (drm_rect_width(&r_pipe_cfg->src_rect) == 0) { + if (!prev_adjacent_pstate || + !dpu_plane_try_multirect_shared(pstate, prev_adjacent_pstate, fmt, + dpu_kms->catalog->caps->max_linewidth)) { + pipe->sspp = dpu_rm_reserve_sspp(&dpu_kms->rm, global_state, crtc, &reqs); + if (!pipe->sspp) + return -ENODEV; + + r_pipe->sspp = NULL; + + pipe->multirect_index = DPU_SSPP_RECT_SOLO; + pipe->multirect_mode = DPU_SSPP_MULTIRECT_NONE; + + r_pipe->multirect_index = DPU_SSPP_RECT_SOLO; + r_pipe->multirect_mode = DPU_SSPP_MULTIRECT_NONE; + } + } else { + pipe->sspp = dpu_rm_reserve_sspp(&dpu_kms->rm, global_state, crtc, &reqs); + if (!pipe->sspp) + return -ENODEV; + + if (!dpu_plane_try_multirect_parallel(pipe, pipe_cfg, r_pipe, r_pipe_cfg, + pipe->sspp, + msm_framebuffer_format(plane_state->fb), + dpu_kms->catalog->caps->max_linewidth)) { + /* multirect is not possible, use two SSPP blocks */ + r_pipe->sspp = dpu_rm_reserve_sspp(&dpu_kms->rm, global_state, crtc, &reqs); + if (!r_pipe->sspp) + return -ENODEV; + + pipe->multirect_index = DPU_SSPP_RECT_SOLO; + pipe->multirect_mode = DPU_SSPP_MULTIRECT_NONE; + + r_pipe->multirect_index = DPU_SSPP_RECT_SOLO; + r_pipe->multirect_mode = DPU_SSPP_MULTIRECT_NONE; + } + } + + return dpu_plane_atomic_check_sspp(plane, state, crtc_state); +} + +int dpu_assign_plane_resources(struct dpu_global_state *global_state, + struct drm_atomic_state *state, + struct drm_crtc *crtc, + struct drm_plane_state **states, + unsigned int num_planes) +{ + unsigned int i; + struct drm_plane_state *prev_adjacent_plane_state = NULL; + + for (i = 0; i < num_planes; i++) { + struct drm_plane_state *plane_state = states[i]; + + if (!plane_state || + !plane_state->visible) + continue; + + int ret = dpu_plane_virtual_assign_resources(crtc, global_state, + state, plane_state, + prev_adjacent_plane_state); + if (ret) + break; + + prev_adjacent_plane_state = plane_state; + } + + return 0; +} + static void dpu_plane_flush_csc(struct dpu_plane *pdpu, struct dpu_sw_pipe *pipe) { const struct msm_format *format = @@ -1436,39 +1706,29 @@ static const struct drm_plane_helper_funcs dpu_plane_helper_funcs = { .atomic_update = dpu_plane_atomic_update, }; -/** - * dpu_plane_init - create new dpu plane for the given pipe - * @dev: Pointer to DRM device - * @pipe: dpu hardware pipe identifier - * @type: Plane type - PRIMARY/OVERLAY/CURSOR - * @possible_crtcs: bitmask of crtc that can be attached to the given pipe - * - * Initialize the plane. - */ -struct drm_plane *dpu_plane_init(struct drm_device *dev, - uint32_t pipe, enum drm_plane_type type, - unsigned long possible_crtcs) +static const struct drm_plane_helper_funcs dpu_plane_virtual_helper_funcs = { + .prepare_fb = dpu_plane_prepare_fb, + .cleanup_fb = dpu_plane_cleanup_fb, + .atomic_check = dpu_plane_virtual_atomic_check, + .atomic_update = dpu_plane_atomic_update, +}; + +/* initialize plane */ +static struct drm_plane *dpu_plane_init_common(struct drm_device *dev, + enum drm_plane_type type, + unsigned long possible_crtcs, + bool inline_rotation, + const uint32_t *format_list, + uint32_t num_formats, + enum dpu_sspp pipe) { struct drm_plane *plane = NULL; - const uint32_t *format_list; struct dpu_plane *pdpu; struct msm_drm_private *priv = dev->dev_private; struct dpu_kms *kms = to_dpu_kms(priv->kms); - struct dpu_hw_sspp *pipe_hw; - uint32_t num_formats; uint32_t supported_rotations; int ret; - /* initialize underlying h/w driver */ - pipe_hw = dpu_rm_get_sspp(&kms->rm, pipe); - if (!pipe_hw || !pipe_hw->cap || !pipe_hw->cap->sblk) { - DPU_ERROR("[%u]SSPP is invalid\n", pipe); - return ERR_PTR(-EINVAL); - } - - format_list = pipe_hw->cap->sblk->format_list; - num_formats = pipe_hw->cap->sblk->num_formats; - pdpu = drmm_universal_plane_alloc(dev, struct dpu_plane, base, 0xff, &dpu_plane_funcs, format_list, num_formats, @@ -1494,7 +1754,7 @@ struct drm_plane *dpu_plane_init(struct drm_device *dev, supported_rotations = DRM_MODE_REFLECT_MASK | DRM_MODE_ROTATE_0 | DRM_MODE_ROTATE_180; - if (pipe_hw->cap->features & BIT(DPU_SSPP_INLINE_ROTATION)) + if (inline_rotation) supported_rotations |= DRM_MODE_ROTATE_MASK; drm_plane_create_rotation_property(plane, @@ -1502,10 +1762,98 @@ struct drm_plane *dpu_plane_init(struct drm_device *dev, drm_plane_enable_fb_damage_clips(plane); - /* success! finalize initialization */ + DPU_DEBUG("%s created for pipe:%u id:%u\n", plane->name, + pipe, plane->base.id); + return plane; +} + +/** + * dpu_plane_init - create new dpu plane for the given pipe + * @dev: Pointer to DRM device + * @pipe: dpu hardware pipe identifier + * @type: Plane type - PRIMARY/OVERLAY/CURSOR + * @possible_crtcs: bitmask of crtc that can be attached to the given pipe + * + * Initialize the plane. + */ +struct drm_plane *dpu_plane_init(struct drm_device *dev, + uint32_t pipe, enum drm_plane_type type, + unsigned long possible_crtcs) +{ + struct drm_plane *plane = NULL; + struct msm_drm_private *priv = dev->dev_private; + struct dpu_kms *kms = to_dpu_kms(priv->kms); + struct dpu_hw_sspp *pipe_hw; + + /* initialize underlying h/w driver */ + pipe_hw = dpu_rm_get_sspp(&kms->rm, pipe); + if (!pipe_hw || !pipe_hw->cap || !pipe_hw->cap->sblk) { + DPU_ERROR("[%u]SSPP is invalid\n", pipe); + return ERR_PTR(-EINVAL); + } + + + plane = dpu_plane_init_common(dev, type, possible_crtcs, + pipe_hw->cap->features & BIT(DPU_SSPP_INLINE_ROTATION), + pipe_hw->cap->sblk->format_list, + pipe_hw->cap->sblk->num_formats, + pipe); + if (IS_ERR(plane)) + return plane; + drm_plane_helper_add(plane, &dpu_plane_helper_funcs); DPU_DEBUG("%s created for pipe:%u id:%u\n", plane->name, pipe, plane->base.id); + + return plane; +} + +/** + * dpu_plane_init_virtual - create new virtualized DPU plane + * @dev: Pointer to DRM device + * @type: Plane type - PRIMARY/OVERLAY/CURSOR + * @possible_crtcs: bitmask of crtc that can be attached to the given pipe + * + * Initialize the virtual plane with no backing SSPP / pipe. + */ +struct drm_plane *dpu_plane_init_virtual(struct drm_device *dev, + enum drm_plane_type type, + unsigned long possible_crtcs) +{ + struct drm_plane *plane = NULL; + struct msm_drm_private *priv = dev->dev_private; + struct dpu_kms *kms = to_dpu_kms(priv->kms); + bool has_inline_rotation = false; + const u32 *format_list = NULL; + u32 num_formats = 0; + int i; + + /* Determine the largest configuration that we can implement */ + for (i = 0; i < kms->catalog->sspp_count; i++) { + const struct dpu_sspp_cfg *cfg = &kms->catalog->sspp[i]; + + if (test_bit(DPU_SSPP_INLINE_ROTATION, &cfg->features)) + has_inline_rotation = true; + + if (!format_list || + cfg->sblk->csc_blk.len) { + format_list = cfg->sblk->format_list; + num_formats = cfg->sblk->num_formats; + } + } + + plane = dpu_plane_init_common(dev, type, possible_crtcs, + has_inline_rotation, + format_list, + num_formats, + SSPP_NONE); + if (IS_ERR(plane)) + return plane; + + drm_plane_helper_add(plane, &dpu_plane_virtual_helper_funcs); + + DPU_DEBUG("%s created virtual id:%u\n", plane->name, plane->base.id); + return plane; } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h index 97090ca7842b..acd5725175cd 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h @@ -62,10 +62,23 @@ struct drm_plane *dpu_plane_init(struct drm_device *dev, uint32_t pipe, enum drm_plane_type type, unsigned long possible_crtcs); +struct drm_plane *dpu_plane_init_virtual(struct drm_device *dev, + enum drm_plane_type type, + unsigned long possible_crtcs); + +int dpu_plane_color_fill(struct drm_plane *plane, + uint32_t color, uint32_t alpha); + #ifdef CONFIG_DEBUG_FS void dpu_plane_danger_signal_ctrl(struct drm_plane *plane, bool enable); #else static inline void dpu_plane_danger_signal_ctrl(struct drm_plane *plane, bool enable) {} #endif +int dpu_assign_plane_resources(struct dpu_global_state *global_state, + struct drm_atomic_state *state, + struct drm_crtc *crtc, + struct drm_plane_state **states, + unsigned int num_planes); + #endif /* _DPU_PLANE_H_ */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c index c247af03dc8e..2e296f79cba1 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved. - * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) 2023-2024 Qualcomm Innovation Center, Inc. All rights reserved. */ #define pr_fmt(fmt) "[drm:%s] " fmt, __func__ @@ -9,6 +9,7 @@ #include "dpu_hw_lm.h" #include "dpu_hw_ctl.h" #include "dpu_hw_cdm.h" +#include "dpu_hw_cwb.h" #include "dpu_hw_pingpong.h" #include "dpu_hw_sspp.h" #include "dpu_hw_intf.h" @@ -21,20 +22,12 @@ static inline bool reserved_by_other(uint32_t *res_map, int idx, - uint32_t enc_id) + uint32_t crtc_id) { - return res_map[idx] && res_map[idx] != enc_id; + return res_map[idx] && res_map[idx] != crtc_id; } /** - * struct dpu_rm_requirements - Reservation requirements parameter bundle - * @topology: selected topology for the display - */ -struct dpu_rm_requirements { - struct msm_display_topology topology; -}; - -/** * dpu_rm_init - Read hardware catalog and create reservation tracking objects * for all HW blocks. * @dev: Corresponding device for devres management @@ -60,6 +53,8 @@ int dpu_rm_init(struct drm_device *dev, /* Clear, setup lists */ memset(rm, 0, sizeof(*rm)); + rm->has_legacy_ctls = (cat->mdss_ver->core_major_ver < 5); + /* Interrogate HW catalog and create tracking items for hw blocks */ for (i = 0; i < cat->mixer_count; i++) { struct dpu_hw_mixer *hw; @@ -130,6 +125,19 @@ int dpu_rm_init(struct drm_device *dev, rm->hw_wb[wb->id - WB_0] = hw; } + for (i = 0; i < cat->cwb_count; i++) { + struct dpu_hw_cwb *hw; + const struct dpu_cwb_cfg *cwb = &cat->cwb[i]; + + hw = dpu_hw_cwb_init(dev, cwb, mmio); + if (IS_ERR(hw)) { + rc = PTR_ERR(hw); + DPU_ERROR("failed cwb object creation: err %d\n", rc); + goto fail; + } + rm->cwb_blks[cwb->id - CWB_0] = &hw->base; + } + for (i = 0; i < cat->ctl_count; i++) { struct dpu_hw_ctl *hw; const struct dpu_ctl_cfg *ctl = &cat->ctl[i]; @@ -227,13 +235,66 @@ static int _dpu_rm_get_lm_peer(struct dpu_rm *rm, int primary_idx) return -EINVAL; } +static int _dpu_rm_reserve_cwb_mux_and_pingpongs(struct dpu_rm *rm, + struct dpu_global_state *global_state, + uint32_t crtc_id, + struct msm_display_topology *topology) +{ + int num_cwb_mux = topology->num_lm, cwb_mux_count = 0; + int cwb_pp_start_idx = PINGPONG_CWB_0 - PINGPONG_0; + int cwb_pp_idx[MAX_BLOCKS]; + int cwb_mux_idx[MAX_BLOCKS]; + + /* + * Reserve additional dedicated CWB PINGPONG blocks and muxes for each + * mixer + * + * TODO: add support reserving resources for platforms with no + * PINGPONG_CWB + */ + for (int i = 0; i < ARRAY_SIZE(rm->mixer_blks) && + cwb_mux_count < num_cwb_mux; i++) { + for (int j = 0; j < ARRAY_SIZE(rm->cwb_blks); j++) { + /* + * Odd LMs must be assigned to odd CWB muxes and even + * LMs with even CWB muxes. + * + * Since the RM HW block array index is based on the HW + * block ids, we can also use the array index to enforce + * the odd/even rule. See dpu_rm_init() for more + * information + */ + if (reserved_by_other(global_state->cwb_to_crtc_id, j, crtc_id) || + i % 2 != j % 2) + continue; + + cwb_mux_idx[cwb_mux_count] = j; + cwb_pp_idx[cwb_mux_count] = j + cwb_pp_start_idx; + cwb_mux_count++; + break; + } + } + + if (cwb_mux_count != num_cwb_mux) { + DPU_ERROR("Unable to reserve all CWB PINGPONGs\n"); + return -ENAVAIL; + } + + for (int i = 0; i < cwb_mux_count; i++) { + global_state->pingpong_to_crtc_id[cwb_pp_idx[i]] = crtc_id; + global_state->cwb_to_crtc_id[cwb_mux_idx[i]] = crtc_id; + } + + return 0; +} + /** * _dpu_rm_check_lm_and_get_connected_blks - check if proposed layer mixer meets * proposed use case requirements, incl. hardwired dependent blocks like * pingpong * @rm: dpu resource manager handle * @global_state: resources shared across multiple kms objects - * @enc_id: encoder id requesting for allocation + * @crtc_id: crtc id requesting for allocation * @lm_idx: index of proposed layer mixer in rm->mixer_blks[], function checks * if lm, and all other hardwired blocks connected to the lm (pp) is * available and appropriate @@ -241,20 +302,19 @@ static int _dpu_rm_get_lm_peer(struct dpu_rm *rm, int primary_idx) * mixer in rm->pingpong_blks[]. * @dspp_idx: output parameter, index of dspp block attached to the layer * mixer in rm->dspp_blks[]. - * @reqs: input parameter, rm requirements for HW blocks needed in the - * datapath. + * @topology: selected topology for the display * Return: true if lm matches all requirements, false otherwise */ static bool _dpu_rm_check_lm_and_get_connected_blks(struct dpu_rm *rm, struct dpu_global_state *global_state, - uint32_t enc_id, int lm_idx, int *pp_idx, int *dspp_idx, - struct dpu_rm_requirements *reqs) + uint32_t crtc_id, int lm_idx, int *pp_idx, int *dspp_idx, + struct msm_display_topology *topology) { const struct dpu_lm_cfg *lm_cfg; int idx; /* Already reserved? */ - if (reserved_by_other(global_state->mixer_to_enc_id, lm_idx, enc_id)) { + if (reserved_by_other(global_state->mixer_to_crtc_id, lm_idx, crtc_id)) { DPU_DEBUG("lm %d already reserved\n", lm_idx + LM_0); return false; } @@ -266,14 +326,14 @@ static bool _dpu_rm_check_lm_and_get_connected_blks(struct dpu_rm *rm, return false; } - if (reserved_by_other(global_state->pingpong_to_enc_id, idx, enc_id)) { + if (reserved_by_other(global_state->pingpong_to_crtc_id, idx, crtc_id)) { DPU_DEBUG("lm %d pp %d already reserved\n", lm_cfg->id, lm_cfg->pingpong); return false; } *pp_idx = idx; - if (!reqs->topology.num_dspp) + if (!topology->num_dspp) return true; idx = lm_cfg->dspp - DSPP_0; @@ -282,7 +342,7 @@ static bool _dpu_rm_check_lm_and_get_connected_blks(struct dpu_rm *rm, return false; } - if (reserved_by_other(global_state->dspp_to_enc_id, idx, enc_id)) { + if (reserved_by_other(global_state->dspp_to_crtc_id, idx, crtc_id)) { DPU_DEBUG("lm %d dspp %d already reserved\n", lm_cfg->id, lm_cfg->dspp); return false; @@ -294,8 +354,8 @@ static bool _dpu_rm_check_lm_and_get_connected_blks(struct dpu_rm *rm, static int _dpu_rm_reserve_lms(struct dpu_rm *rm, struct dpu_global_state *global_state, - uint32_t enc_id, - struct dpu_rm_requirements *reqs) + uint32_t crtc_id, + struct msm_display_topology *topology) { int lm_idx[MAX_BLOCKS]; @@ -303,14 +363,14 @@ static int _dpu_rm_reserve_lms(struct dpu_rm *rm, int dspp_idx[MAX_BLOCKS] = {0}; int i, lm_count = 0; - if (!reqs->topology.num_lm) { - DPU_ERROR("invalid number of lm: %d\n", reqs->topology.num_lm); + if (!topology->num_lm) { + DPU_ERROR("invalid number of lm: %d\n", topology->num_lm); return -EINVAL; } /* Find a primary mixer */ for (i = 0; i < ARRAY_SIZE(rm->mixer_blks) && - lm_count < reqs->topology.num_lm; i++) { + lm_count < topology->num_lm; i++) { if (!rm->mixer_blks[i]) continue; @@ -318,15 +378,15 @@ static int _dpu_rm_reserve_lms(struct dpu_rm *rm, lm_idx[lm_count] = i; if (!_dpu_rm_check_lm_and_get_connected_blks(rm, global_state, - enc_id, i, &pp_idx[lm_count], - &dspp_idx[lm_count], reqs)) { + crtc_id, i, &pp_idx[lm_count], + &dspp_idx[lm_count], topology)) { continue; } ++lm_count; /* Valid primary mixer found, find matching peers */ - if (lm_count < reqs->topology.num_lm) { + if (lm_count < topology->num_lm) { int j = _dpu_rm_get_lm_peer(rm, i); /* ignore the peer if there is an error or if the peer was already processed */ @@ -337,9 +397,9 @@ static int _dpu_rm_reserve_lms(struct dpu_rm *rm, continue; if (!_dpu_rm_check_lm_and_get_connected_blks(rm, - global_state, enc_id, j, + global_state, crtc_id, j, &pp_idx[lm_count], &dspp_idx[lm_count], - reqs)) { + topology)) { continue; } @@ -348,18 +408,18 @@ static int _dpu_rm_reserve_lms(struct dpu_rm *rm, } } - if (lm_count != reqs->topology.num_lm) { + if (lm_count != topology->num_lm) { DPU_DEBUG("unable to find appropriate mixers\n"); return -ENAVAIL; } for (i = 0; i < lm_count; i++) { - global_state->mixer_to_enc_id[lm_idx[i]] = enc_id; - global_state->pingpong_to_enc_id[pp_idx[i]] = enc_id; - global_state->dspp_to_enc_id[dspp_idx[i]] = - reqs->topology.num_dspp ? enc_id : 0; + global_state->mixer_to_crtc_id[lm_idx[i]] = crtc_id; + global_state->pingpong_to_crtc_id[pp_idx[i]] = crtc_id; + global_state->dspp_to_crtc_id[dspp_idx[i]] = + topology->num_dspp ? crtc_id : 0; - trace_dpu_rm_reserve_lms(lm_idx[i] + LM_0, enc_id, + trace_dpu_rm_reserve_lms(lm_idx[i] + LM_0, crtc_id, pp_idx[i] + PINGPONG_0); } @@ -369,17 +429,26 @@ static int _dpu_rm_reserve_lms(struct dpu_rm *rm, static int _dpu_rm_reserve_ctls( struct dpu_rm *rm, struct dpu_global_state *global_state, - uint32_t enc_id, + uint32_t crtc_id, const struct msm_display_topology *top) { int ctl_idx[MAX_BLOCKS]; int i = 0, j, num_ctls; bool needs_split_display; - /* each hw_intf needs its own hw_ctrl to program its control path */ - num_ctls = top->num_intf; - - needs_split_display = _dpu_rm_needs_split_display(top); + if (rm->has_legacy_ctls) { + /* + * TODO: check if there is a need for special handling if + * DPU < 5.0 get CWB support. + */ + num_ctls = top->num_intf; + + needs_split_display = _dpu_rm_needs_split_display(top); + } else { + /* use single CTL */ + num_ctls = 1; + needs_split_display = false; + } for (j = 0; j < ARRAY_SIZE(rm->ctl_blks); j++) { const struct dpu_hw_ctl *ctl; @@ -388,7 +457,7 @@ static int _dpu_rm_reserve_ctls( if (!rm->ctl_blks[j]) continue; - if (reserved_by_other(global_state->ctl_to_enc_id, j, enc_id)) + if (reserved_by_other(global_state->ctl_to_crtc_id, j, crtc_id)) continue; ctl = to_dpu_hw_ctl(rm->ctl_blks[j]); @@ -412,8 +481,8 @@ static int _dpu_rm_reserve_ctls( return -ENAVAIL; for (i = 0; i < ARRAY_SIZE(ctl_idx) && i < num_ctls; i++) { - global_state->ctl_to_enc_id[ctl_idx[i]] = enc_id; - trace_dpu_rm_reserve_ctls(i + CTL_0, enc_id); + global_state->ctl_to_crtc_id[ctl_idx[i]] = crtc_id; + trace_dpu_rm_reserve_ctls(i + CTL_0, crtc_id); } return 0; @@ -421,12 +490,12 @@ static int _dpu_rm_reserve_ctls( static int _dpu_rm_pingpong_next_index(struct dpu_global_state *global_state, int start, - uint32_t enc_id) + uint32_t crtc_id) { int i; for (i = start; i < (PINGPONG_MAX - PINGPONG_0); i++) { - if (global_state->pingpong_to_enc_id[i] == enc_id) + if (global_state->pingpong_to_crtc_id[i] == crtc_id) return i; } @@ -447,7 +516,7 @@ static int _dpu_rm_pingpong_dsc_check(int dsc_idx, int pp_idx) static int _dpu_rm_dsc_alloc(struct dpu_rm *rm, struct dpu_global_state *global_state, - uint32_t enc_id, + uint32_t crtc_id, const struct msm_display_topology *top) { int num_dsc = 0; @@ -460,10 +529,10 @@ static int _dpu_rm_dsc_alloc(struct dpu_rm *rm, if (!rm->dsc_blks[dsc_idx]) continue; - if (reserved_by_other(global_state->dsc_to_enc_id, dsc_idx, enc_id)) + if (reserved_by_other(global_state->dsc_to_crtc_id, dsc_idx, crtc_id)) continue; - pp_idx = _dpu_rm_pingpong_next_index(global_state, pp_idx, enc_id); + pp_idx = _dpu_rm_pingpong_next_index(global_state, pp_idx, crtc_id); if (pp_idx < 0) return -ENAVAIL; @@ -471,7 +540,7 @@ static int _dpu_rm_dsc_alloc(struct dpu_rm *rm, if (ret) return -ENAVAIL; - global_state->dsc_to_enc_id[dsc_idx] = enc_id; + global_state->dsc_to_crtc_id[dsc_idx] = crtc_id; num_dsc++; pp_idx++; } @@ -487,7 +556,7 @@ static int _dpu_rm_dsc_alloc(struct dpu_rm *rm, static int _dpu_rm_dsc_alloc_pair(struct dpu_rm *rm, struct dpu_global_state *global_state, - uint32_t enc_id, + uint32_t crtc_id, const struct msm_display_topology *top) { int num_dsc = 0; @@ -502,11 +571,11 @@ static int _dpu_rm_dsc_alloc_pair(struct dpu_rm *rm, continue; /* consective dsc index to be paired */ - if (reserved_by_other(global_state->dsc_to_enc_id, dsc_idx, enc_id) || - reserved_by_other(global_state->dsc_to_enc_id, dsc_idx + 1, enc_id)) + if (reserved_by_other(global_state->dsc_to_crtc_id, dsc_idx, crtc_id) || + reserved_by_other(global_state->dsc_to_crtc_id, dsc_idx + 1, crtc_id)) continue; - pp_idx = _dpu_rm_pingpong_next_index(global_state, pp_idx, enc_id); + pp_idx = _dpu_rm_pingpong_next_index(global_state, pp_idx, crtc_id); if (pp_idx < 0) return -ENAVAIL; @@ -516,7 +585,7 @@ static int _dpu_rm_dsc_alloc_pair(struct dpu_rm *rm, continue; } - pp_idx = _dpu_rm_pingpong_next_index(global_state, pp_idx + 1, enc_id); + pp_idx = _dpu_rm_pingpong_next_index(global_state, pp_idx + 1, crtc_id); if (pp_idx < 0) return -ENAVAIL; @@ -526,8 +595,8 @@ static int _dpu_rm_dsc_alloc_pair(struct dpu_rm *rm, continue; } - global_state->dsc_to_enc_id[dsc_idx] = enc_id; - global_state->dsc_to_enc_id[dsc_idx + 1] = enc_id; + global_state->dsc_to_crtc_id[dsc_idx] = crtc_id; + global_state->dsc_to_crtc_id[dsc_idx + 1] = crtc_id; num_dsc += 2; pp_idx++; /* start for next pair */ } @@ -543,11 +612,9 @@ static int _dpu_rm_dsc_alloc_pair(struct dpu_rm *rm, static int _dpu_rm_reserve_dsc(struct dpu_rm *rm, struct dpu_global_state *global_state, - struct drm_encoder *enc, + uint32_t crtc_id, const struct msm_display_topology *top) { - uint32_t enc_id = enc->base.id; - if (!top->num_dsc || !top->num_intf) return 0; @@ -563,16 +630,17 @@ static int _dpu_rm_reserve_dsc(struct dpu_rm *rm, /* num_dsc should be either 1, 2 or 4 */ if (top->num_dsc > top->num_intf) /* merge mode */ - return _dpu_rm_dsc_alloc_pair(rm, global_state, enc_id, top); + return _dpu_rm_dsc_alloc_pair(rm, global_state, crtc_id, top); else - return _dpu_rm_dsc_alloc(rm, global_state, enc_id, top); + return _dpu_rm_dsc_alloc(rm, global_state, crtc_id, top); return 0; } static int _dpu_rm_reserve_cdm(struct dpu_rm *rm, struct dpu_global_state *global_state, - struct drm_encoder *enc) + uint32_t crtc_id, + int num_cdm) { /* try allocating only one CDM block */ if (!rm->cdm_blk) { @@ -580,12 +648,17 @@ static int _dpu_rm_reserve_cdm(struct dpu_rm *rm, return -EIO; } - if (global_state->cdm_to_enc_id) { + if (num_cdm > 1) { + DPU_ERROR("More than 1 INTF requesting CDM\n"); + return -EINVAL; + } + + if (global_state->cdm_to_crtc_id) { DPU_ERROR("CDM_0 is already allocated\n"); return -EIO; } - global_state->cdm_to_enc_id = enc->base.id; + global_state->cdm_to_crtc_id = crtc_id; return 0; } @@ -593,30 +666,37 @@ static int _dpu_rm_reserve_cdm(struct dpu_rm *rm, static int _dpu_rm_make_reservation( struct dpu_rm *rm, struct dpu_global_state *global_state, - struct drm_encoder *enc, - struct dpu_rm_requirements *reqs) + uint32_t crtc_id, + struct msm_display_topology *topology) { int ret; - ret = _dpu_rm_reserve_lms(rm, global_state, enc->base.id, reqs); + ret = _dpu_rm_reserve_lms(rm, global_state, crtc_id, topology); if (ret) { DPU_ERROR("unable to find appropriate mixers\n"); return ret; } - ret = _dpu_rm_reserve_ctls(rm, global_state, enc->base.id, - &reqs->topology); + if (topology->cwb_enabled) { + ret = _dpu_rm_reserve_cwb_mux_and_pingpongs(rm, global_state, + crtc_id, topology); + if (ret) + return ret; + } + + ret = _dpu_rm_reserve_ctls(rm, global_state, crtc_id, + topology); if (ret) { DPU_ERROR("unable to find appropriate CTL\n"); return ret; } - ret = _dpu_rm_reserve_dsc(rm, global_state, enc, &reqs->topology); + ret = _dpu_rm_reserve_dsc(rm, global_state, crtc_id, topology); if (ret) return ret; - if (reqs->topology.needs_cdm) { - ret = _dpu_rm_reserve_cdm(rm, global_state, enc); + if (topology->num_cdm > 0) { + ret = _dpu_rm_reserve_cdm(rm, global_state, crtc_id, topology->num_cdm); if (ret) { DPU_ERROR("unable to find CDM blk\n"); return ret; @@ -626,27 +706,13 @@ static int _dpu_rm_make_reservation( return ret; } -static int _dpu_rm_populate_requirements( - struct drm_encoder *enc, - struct dpu_rm_requirements *reqs, - struct msm_display_topology req_topology) -{ - reqs->topology = req_topology; - - DRM_DEBUG_KMS("num_lm: %d num_dsc: %d num_intf: %d cdm: %d\n", - reqs->topology.num_lm, reqs->topology.num_dsc, - reqs->topology.num_intf, reqs->topology.needs_cdm); - - return 0; -} - static void _dpu_rm_clear_mapping(uint32_t *res_mapping, int cnt, - uint32_t enc_id) + uint32_t crtc_id) { int i; for (i = 0; i < cnt; i++) { - if (res_mapping[i] == enc_id) + if (res_mapping[i] == crtc_id) res_mapping[i] = 0; } } @@ -655,23 +721,27 @@ static void _dpu_rm_clear_mapping(uint32_t *res_mapping, int cnt, * dpu_rm_release - Given the encoder for the display chain, release any * HW blocks previously reserved for that use case. * @global_state: resources shared across multiple kms objects - * @enc: DRM Encoder handle + * @crtc: DRM CRTC handle * @return: 0 on Success otherwise -ERROR */ void dpu_rm_release(struct dpu_global_state *global_state, - struct drm_encoder *enc) + struct drm_crtc *crtc) { - _dpu_rm_clear_mapping(global_state->pingpong_to_enc_id, - ARRAY_SIZE(global_state->pingpong_to_enc_id), enc->base.id); - _dpu_rm_clear_mapping(global_state->mixer_to_enc_id, - ARRAY_SIZE(global_state->mixer_to_enc_id), enc->base.id); - _dpu_rm_clear_mapping(global_state->ctl_to_enc_id, - ARRAY_SIZE(global_state->ctl_to_enc_id), enc->base.id); - _dpu_rm_clear_mapping(global_state->dsc_to_enc_id, - ARRAY_SIZE(global_state->dsc_to_enc_id), enc->base.id); - _dpu_rm_clear_mapping(global_state->dspp_to_enc_id, - ARRAY_SIZE(global_state->dspp_to_enc_id), enc->base.id); - _dpu_rm_clear_mapping(&global_state->cdm_to_enc_id, 1, enc->base.id); + uint32_t crtc_id = crtc->base.id; + + _dpu_rm_clear_mapping(global_state->pingpong_to_crtc_id, + ARRAY_SIZE(global_state->pingpong_to_crtc_id), crtc_id); + _dpu_rm_clear_mapping(global_state->mixer_to_crtc_id, + ARRAY_SIZE(global_state->mixer_to_crtc_id), crtc_id); + _dpu_rm_clear_mapping(global_state->ctl_to_crtc_id, + ARRAY_SIZE(global_state->ctl_to_crtc_id), crtc_id); + _dpu_rm_clear_mapping(global_state->dsc_to_crtc_id, + ARRAY_SIZE(global_state->dsc_to_crtc_id), crtc_id); + _dpu_rm_clear_mapping(global_state->dspp_to_crtc_id, + ARRAY_SIZE(global_state->dspp_to_crtc_id), crtc_id); + _dpu_rm_clear_mapping(&global_state->cdm_to_crtc_id, 1, crtc_id); + _dpu_rm_clear_mapping(global_state->cwb_to_crtc_id, + ARRAY_SIZE(global_state->cwb_to_crtc_id), crtc_id); } /** @@ -683,46 +753,116 @@ void dpu_rm_release(struct dpu_global_state *global_state, * HW Reservations should be released via dpu_rm_release_hw. * @rm: DPU Resource Manager handle * @global_state: resources shared across multiple kms objects - * @enc: DRM Encoder handle - * @crtc_state: Proposed Atomic DRM CRTC State handle + * @crtc: DRM CRTC handle * @topology: Pointer to topology info for the display * @return: 0 on Success otherwise -ERROR */ int dpu_rm_reserve( struct dpu_rm *rm, struct dpu_global_state *global_state, - struct drm_encoder *enc, - struct drm_crtc_state *crtc_state, - struct msm_display_topology topology) + struct drm_crtc *crtc, + struct msm_display_topology *topology) { - struct dpu_rm_requirements reqs; int ret; - /* Check if this is just a page-flip */ - if (!drm_atomic_crtc_needs_modeset(crtc_state)) - return 0; - if (IS_ERR(global_state)) { DPU_ERROR("failed to global state\n"); return PTR_ERR(global_state); } - DRM_DEBUG_KMS("reserving hw for enc %d crtc %d\n", - enc->base.id, crtc_state->crtc->base.id); + DRM_DEBUG_KMS("reserving hw for crtc %d\n", crtc->base.id); - ret = _dpu_rm_populate_requirements(enc, &reqs, topology); - if (ret) { - DPU_ERROR("failed to populate hw requirements\n"); - return ret; - } + DRM_DEBUG_KMS("num_lm: %d num_dsc: %d num_intf: %d\n", + topology->num_lm, topology->num_dsc, + topology->num_intf); - ret = _dpu_rm_make_reservation(rm, global_state, enc, &reqs); + ret = _dpu_rm_make_reservation(rm, global_state, crtc->base.id, topology); if (ret) DPU_ERROR("failed to reserve hw resources: %d\n", ret); + return ret; +} +static struct dpu_hw_sspp *dpu_rm_try_sspp(struct dpu_rm *rm, + struct dpu_global_state *global_state, + struct drm_crtc *crtc, + struct dpu_rm_sspp_requirements *reqs, + unsigned int type) +{ + uint32_t crtc_id = crtc->base.id; + struct dpu_hw_sspp *hw_sspp; + int i; - return ret; + for (i = 0; i < ARRAY_SIZE(rm->hw_sspp); i++) { + if (!rm->hw_sspp[i]) + continue; + + if (global_state->sspp_to_crtc_id[i]) + continue; + + hw_sspp = rm->hw_sspp[i]; + + if (hw_sspp->cap->type != type) + continue; + + if (reqs->scale && !hw_sspp->cap->sblk->scaler_blk.len) + continue; + + // TODO: QSEED2 and RGB scalers are not yet supported + if (reqs->scale && !hw_sspp->ops.setup_scaler) + continue; + + if (reqs->yuv && !hw_sspp->cap->sblk->csc_blk.len) + continue; + + if (reqs->rot90 && !(hw_sspp->cap->features & DPU_SSPP_INLINE_ROTATION)) + continue; + + global_state->sspp_to_crtc_id[i] = crtc_id; + + return rm->hw_sspp[i]; + } + + return NULL; +} + +/** + * dpu_rm_reserve_sspp - Reserve the required SSPP for the provided CRTC + * @rm: DPU Resource Manager handle + * @global_state: private global state + * @crtc: DRM CRTC handle + * @reqs: SSPP required features + */ +struct dpu_hw_sspp *dpu_rm_reserve_sspp(struct dpu_rm *rm, + struct dpu_global_state *global_state, + struct drm_crtc *crtc, + struct dpu_rm_sspp_requirements *reqs) +{ + struct dpu_hw_sspp *hw_sspp = NULL; + + if (!reqs->scale && !reqs->yuv) + hw_sspp = dpu_rm_try_sspp(rm, global_state, crtc, reqs, SSPP_TYPE_DMA); + if (!hw_sspp && reqs->scale) + hw_sspp = dpu_rm_try_sspp(rm, global_state, crtc, reqs, SSPP_TYPE_RGB); + if (!hw_sspp) + hw_sspp = dpu_rm_try_sspp(rm, global_state, crtc, reqs, SSPP_TYPE_VIG); + + return hw_sspp; +} + +/** + * dpu_rm_release_all_sspp - Given the CRTC, release all SSPP + * blocks previously reserved for that use case. + * @global_state: resources shared across multiple kms objects + * @crtc: DRM CRTC handle + */ +void dpu_rm_release_all_sspp(struct dpu_global_state *global_state, + struct drm_crtc *crtc) +{ + uint32_t crtc_id = crtc->base.id; + + _dpu_rm_clear_mapping(global_state->sspp_to_crtc_id, + ARRAY_SIZE(global_state->sspp_to_crtc_id), crtc_id); } /** @@ -730,50 +870,57 @@ int dpu_rm_reserve( * assigned to this encoder * @rm: DPU Resource Manager handle * @global_state: resources shared across multiple kms objects - * @enc_id: encoder id requesting for allocation + * @crtc: DRM CRTC handle * @type: resource type to return data for * @blks: pointer to the array to be filled by HW resources * @blks_size: size of the @blks array */ int dpu_rm_get_assigned_resources(struct dpu_rm *rm, - struct dpu_global_state *global_state, uint32_t enc_id, + struct dpu_global_state *global_state, struct drm_crtc *crtc, enum dpu_hw_blk_type type, struct dpu_hw_blk **blks, int blks_size) { + uint32_t crtc_id = crtc->base.id; struct dpu_hw_blk **hw_blks; - uint32_t *hw_to_enc_id; + uint32_t *hw_to_crtc_id; int i, num_blks, max_blks; switch (type) { case DPU_HW_BLK_PINGPONG: + case DPU_HW_BLK_DCWB_PINGPONG: hw_blks = rm->pingpong_blks; - hw_to_enc_id = global_state->pingpong_to_enc_id; + hw_to_crtc_id = global_state->pingpong_to_crtc_id; max_blks = ARRAY_SIZE(rm->pingpong_blks); break; case DPU_HW_BLK_LM: hw_blks = rm->mixer_blks; - hw_to_enc_id = global_state->mixer_to_enc_id; + hw_to_crtc_id = global_state->mixer_to_crtc_id; max_blks = ARRAY_SIZE(rm->mixer_blks); break; case DPU_HW_BLK_CTL: hw_blks = rm->ctl_blks; - hw_to_enc_id = global_state->ctl_to_enc_id; + hw_to_crtc_id = global_state->ctl_to_crtc_id; max_blks = ARRAY_SIZE(rm->ctl_blks); break; case DPU_HW_BLK_DSPP: hw_blks = rm->dspp_blks; - hw_to_enc_id = global_state->dspp_to_enc_id; + hw_to_crtc_id = global_state->dspp_to_crtc_id; max_blks = ARRAY_SIZE(rm->dspp_blks); break; case DPU_HW_BLK_DSC: hw_blks = rm->dsc_blks; - hw_to_enc_id = global_state->dsc_to_enc_id; + hw_to_crtc_id = global_state->dsc_to_crtc_id; max_blks = ARRAY_SIZE(rm->dsc_blks); break; case DPU_HW_BLK_CDM: hw_blks = &rm->cdm_blk; - hw_to_enc_id = &global_state->cdm_to_enc_id; + hw_to_crtc_id = &global_state->cdm_to_crtc_id; max_blks = 1; break; + case DPU_HW_BLK_CWB: + hw_blks = rm->cwb_blks; + hw_to_crtc_id = global_state->cwb_to_crtc_id; + max_blks = ARRAY_SIZE(rm->cwb_blks); + break; default: DPU_ERROR("blk type %d not managed by rm\n", type); return 0; @@ -781,17 +928,31 @@ int dpu_rm_get_assigned_resources(struct dpu_rm *rm, num_blks = 0; for (i = 0; i < max_blks; i++) { - if (hw_to_enc_id[i] != enc_id) + if (hw_to_crtc_id[i] != crtc_id) continue; + if (type == DPU_HW_BLK_PINGPONG) { + struct dpu_hw_pingpong *pp = to_dpu_hw_pingpong(hw_blks[i]); + + if (pp->idx >= PINGPONG_CWB_0) + continue; + } + + if (type == DPU_HW_BLK_DCWB_PINGPONG) { + struct dpu_hw_pingpong *pp = to_dpu_hw_pingpong(hw_blks[i]); + + if (pp->idx < PINGPONG_CWB_0) + continue; + } + if (num_blks == blks_size) { - DPU_ERROR("More than %d resources assigned to enc %d\n", - blks_size, enc_id); + DPU_ERROR("More than %d resources assigned to crtc %d\n", + blks_size, crtc_id); break; } if (!hw_blks[i]) { - DPU_ERROR("Allocated resource %d unavailable to assign to enc %d\n", - type, enc_id); + DPU_ERROR("Allocated resource %d unavailable to assign to crtc %d\n", + type, crtc_id); break; } blks[num_blks++] = hw_blks[i]; @@ -826,37 +987,50 @@ void dpu_rm_print_state(struct drm_printer *p, drm_puts(p, "resource mapping:\n"); drm_puts(p, "\tpingpong="); - for (i = 0; i < ARRAY_SIZE(global_state->pingpong_to_enc_id); i++) + for (i = 0; i < ARRAY_SIZE(global_state->pingpong_to_crtc_id); i++) dpu_rm_print_state_helper(p, rm->pingpong_blks[i], - global_state->pingpong_to_enc_id[i]); + global_state->pingpong_to_crtc_id[i]); drm_puts(p, "\n"); drm_puts(p, "\tmixer="); - for (i = 0; i < ARRAY_SIZE(global_state->mixer_to_enc_id); i++) + for (i = 0; i < ARRAY_SIZE(global_state->mixer_to_crtc_id); i++) dpu_rm_print_state_helper(p, rm->mixer_blks[i], - global_state->mixer_to_enc_id[i]); + global_state->mixer_to_crtc_id[i]); drm_puts(p, "\n"); drm_puts(p, "\tctl="); - for (i = 0; i < ARRAY_SIZE(global_state->ctl_to_enc_id); i++) + for (i = 0; i < ARRAY_SIZE(global_state->ctl_to_crtc_id); i++) dpu_rm_print_state_helper(p, rm->ctl_blks[i], - global_state->ctl_to_enc_id[i]); + global_state->ctl_to_crtc_id[i]); drm_puts(p, "\n"); drm_puts(p, "\tdspp="); - for (i = 0; i < ARRAY_SIZE(global_state->dspp_to_enc_id); i++) + for (i = 0; i < ARRAY_SIZE(global_state->dspp_to_crtc_id); i++) dpu_rm_print_state_helper(p, rm->dspp_blks[i], - global_state->dspp_to_enc_id[i]); + global_state->dspp_to_crtc_id[i]); drm_puts(p, "\n"); drm_puts(p, "\tdsc="); - for (i = 0; i < ARRAY_SIZE(global_state->dsc_to_enc_id); i++) + for (i = 0; i < ARRAY_SIZE(global_state->dsc_to_crtc_id); i++) dpu_rm_print_state_helper(p, rm->dsc_blks[i], - global_state->dsc_to_enc_id[i]); + global_state->dsc_to_crtc_id[i]); drm_puts(p, "\n"); drm_puts(p, "\tcdm="); dpu_rm_print_state_helper(p, rm->cdm_blk, - global_state->cdm_to_enc_id); + global_state->cdm_to_crtc_id); + drm_puts(p, "\n"); + + drm_puts(p, "\tsspp="); + /* skip SSPP_NONE and start from the next index */ + for (i = SSPP_NONE + 1; i < ARRAY_SIZE(global_state->sspp_to_crtc_id); i++) + dpu_rm_print_state_helper(p, rm->hw_sspp[i] ? &rm->hw_sspp[i]->base : NULL, + global_state->sspp_to_crtc_id[i]); + drm_puts(p, "\n"); + + drm_puts(p, "\tcwb="); + for (i = 0; i < ARRAY_SIZE(global_state->cwb_to_crtc_id); i++) + dpu_rm_print_state_helper(p, rm->cwb_blks[i], + global_state->cwb_to_crtc_id[i]); drm_puts(p, "\n"); } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h index ea0e49cb7b0d..aa62966056d4 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h @@ -20,9 +20,11 @@ struct dpu_global_state; * @ctl_blks: array of ctl hardware resources * @hw_intf: array of intf hardware resources * @hw_wb: array of wb hardware resources + * @hw_cwb: array of cwb hardware resources * @dspp_blks: array of dspp hardware resources * @hw_sspp: array of sspp hardware resources * @cdm_blk: cdm hardware resource + * @has_legacy_ctls: DPU uses pre-ACTIVE CTL blocks. */ struct dpu_rm { struct dpu_hw_blk *pingpong_blks[PINGPONG_MAX - PINGPONG_0]; @@ -30,11 +32,19 @@ struct dpu_rm { struct dpu_hw_blk *ctl_blks[CTL_MAX - CTL_0]; struct dpu_hw_intf *hw_intf[INTF_MAX - INTF_0]; struct dpu_hw_wb *hw_wb[WB_MAX - WB_0]; + struct dpu_hw_blk *cwb_blks[CWB_MAX - CWB_0]; struct dpu_hw_blk *dspp_blks[DSPP_MAX - DSPP_0]; struct dpu_hw_blk *merge_3d_blks[MERGE_3D_MAX - MERGE_3D_0]; struct dpu_hw_blk *dsc_blks[DSC_MAX - DSC_0]; struct dpu_hw_sspp *hw_sspp[SSPP_MAX - SSPP_NONE]; struct dpu_hw_blk *cdm_blk; + bool has_legacy_ctls; +}; + +struct dpu_rm_sspp_requirements { + bool yuv; + bool scale; + bool rot90; }; /** @@ -43,14 +53,17 @@ struct dpu_rm { * @num_intf: number of interfaces the panel is mounted on * @num_dspp: number of dspp blocks used * @num_dsc: number of Display Stream Compression (DSC) blocks used - * @needs_cdm: indicates whether cdm block is needed for this display topology + * @num_cdm: indicates how many outputs are requesting cdm block for + * this display topology + * @cwb_enabled: indicates whether CWB is enabled for this display topology */ struct msm_display_topology { u32 num_lm; u32 num_intf; u32 num_dspp; u32 num_dsc; - bool needs_cdm; + int num_cdm; + bool cwb_enabled; }; int dpu_rm_init(struct drm_device *dev, @@ -61,15 +74,22 @@ int dpu_rm_init(struct drm_device *dev, int dpu_rm_reserve(struct dpu_rm *rm, struct dpu_global_state *global_state, - struct drm_encoder *drm_enc, - struct drm_crtc_state *crtc_state, - struct msm_display_topology topology); + struct drm_crtc *crtc, + struct msm_display_topology *topology); void dpu_rm_release(struct dpu_global_state *global_state, - struct drm_encoder *enc); + struct drm_crtc *crtc); + +struct dpu_hw_sspp *dpu_rm_reserve_sspp(struct dpu_rm *rm, + struct dpu_global_state *global_state, + struct drm_crtc *crtc, + struct dpu_rm_sspp_requirements *reqs); + +void dpu_rm_release_all_sspp(struct dpu_global_state *global_state, + struct drm_crtc *crtc); int dpu_rm_get_assigned_resources(struct dpu_rm *rm, - struct dpu_global_state *global_state, uint32_t enc_id, + struct dpu_global_state *global_state, struct drm_crtc *crtc, enum dpu_hw_blk_type type, struct dpu_hw_blk **blks, int blks_size); void dpu_rm_print_state(struct drm_printer *p, diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c index c469e66cfc11..7e942c1337b3 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c @@ -6,6 +6,8 @@ #include <linux/delay.h> +#include <drm/drm_bridge.h> +#include <drm/drm_bridge_connector.h> #include <drm/drm_vblank.h> #include "msm_drv.h" @@ -189,7 +191,7 @@ static int mdp4_modeset_init_intf(struct mdp4_kms *mdp4_kms, struct msm_drm_private *priv = dev->dev_private; struct drm_encoder *encoder; struct drm_connector *connector; - struct device_node *panel_node; + struct drm_bridge *next_bridge; int dsi_id; int ret; @@ -199,27 +201,43 @@ static int mdp4_modeset_init_intf(struct mdp4_kms *mdp4_kms, * bail out early if there is no panel node (no need to * initialize LCDC encoder and LVDS connector) */ - panel_node = of_graph_get_remote_node(dev->dev->of_node, 0, 0); - if (!panel_node) - return 0; + next_bridge = devm_drm_of_get_bridge(dev->dev, dev->dev->of_node, 0, 0); + if (IS_ERR(next_bridge)) { + ret = PTR_ERR(next_bridge); + if (ret == -ENODEV) + return 0; + return ret; + } - encoder = mdp4_lcdc_encoder_init(dev, panel_node); + encoder = mdp4_lcdc_encoder_init(dev); if (IS_ERR(encoder)) { DRM_DEV_ERROR(dev->dev, "failed to construct LCDC encoder\n"); - of_node_put(panel_node); return PTR_ERR(encoder); } /* LCDC can be hooked to DMA_P (TODO: Add DMA_S later?) */ encoder->possible_crtcs = 1 << DMA_P; - connector = mdp4_lvds_connector_init(dev, panel_node, encoder); + ret = drm_bridge_attach(encoder, next_bridge, NULL, DRM_BRIDGE_ATTACH_NO_CONNECTOR); + if (ret) { + DRM_DEV_ERROR(dev->dev, "failed to attach LVDS panel/bridge: %d\n", ret); + + return ret; + } + + connector = drm_bridge_connector_init(dev, encoder); if (IS_ERR(connector)) { DRM_DEV_ERROR(dev->dev, "failed to initialize LVDS connector\n"); - of_node_put(panel_node); return PTR_ERR(connector); } + ret = drm_connector_attach_encoder(connector, encoder); + if (ret) { + DRM_DEV_ERROR(dev->dev, "failed to attach LVDS connector: %d\n", ret); + + return ret; + } + break; case DRM_MODE_ENCODER_TMDS: encoder = mdp4_dtv_encoder_init(dev); diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.h b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.h index 94b1ba92785f..f9d988076337 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.h +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.h @@ -191,12 +191,7 @@ struct drm_crtc *mdp4_crtc_init(struct drm_device *dev, long mdp4_dtv_round_pixclk(struct drm_encoder *encoder, unsigned long rate); struct drm_encoder *mdp4_dtv_encoder_init(struct drm_device *dev); -long mdp4_lcdc_round_pixclk(struct drm_encoder *encoder, unsigned long rate); -struct drm_encoder *mdp4_lcdc_encoder_init(struct drm_device *dev, - struct device_node *panel_node); - -struct drm_connector *mdp4_lvds_connector_init(struct drm_device *dev, - struct device_node *panel_node, struct drm_encoder *encoder); +struct drm_encoder *mdp4_lcdc_encoder_init(struct drm_device *dev); #ifdef CONFIG_DRM_MSM_DSI struct drm_encoder *mdp4_dsi_encoder_init(struct drm_device *dev); @@ -207,13 +202,6 @@ static inline struct drm_encoder *mdp4_dsi_encoder_init(struct drm_device *dev) } #endif -#ifdef CONFIG_COMMON_CLK -struct clk *mpd4_lvds_pll_init(struct drm_device *dev); -#else -static inline struct clk *mpd4_lvds_pll_init(struct drm_device *dev) -{ - return ERR_PTR(-ENODEV); -} -#endif +struct clk *mpd4_get_lcdc_clock(struct drm_device *dev); #endif /* __MDP4_KMS_H__ */ diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c index 8bbc7fb881d5..06a307c1272d 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c @@ -14,7 +14,6 @@ struct mdp4_lcdc_encoder { struct drm_encoder base; - struct device_node *panel_node; struct drm_panel *panel; struct clk *lcdc_clk; unsigned long int pixclock; @@ -262,19 +261,12 @@ static void mdp4_lcdc_encoder_disable(struct drm_encoder *encoder) struct mdp4_lcdc_encoder *mdp4_lcdc_encoder = to_mdp4_lcdc_encoder(encoder); struct mdp4_kms *mdp4_kms = get_kms(encoder); - struct drm_panel *panel; if (WARN_ON(!mdp4_lcdc_encoder->enabled)) return; mdp4_write(mdp4_kms, REG_MDP4_LCDC_ENABLE, 0); - panel = of_drm_find_panel(mdp4_lcdc_encoder->panel_node); - if (!IS_ERR(panel)) { - drm_panel_disable(panel); - drm_panel_unprepare(panel); - } - /* * Wait for a vsync so we know the ENABLE=0 latched before * the (connector) source of the vsync's gets disabled, @@ -300,7 +292,6 @@ static void mdp4_lcdc_encoder_enable(struct drm_encoder *encoder) to_mdp4_lcdc_encoder(encoder); unsigned long pc = mdp4_lcdc_encoder->pixclock; struct mdp4_kms *mdp4_kms = get_kms(encoder); - struct drm_panel *panel; uint32_t config; int ret; @@ -335,12 +326,6 @@ static void mdp4_lcdc_encoder_enable(struct drm_encoder *encoder) if (ret) DRM_DEV_ERROR(dev->dev, "failed to enable lcdc_clk: %d\n", ret); - panel = of_drm_find_panel(mdp4_lcdc_encoder->panel_node); - if (!IS_ERR(panel)) { - drm_panel_prepare(panel); - drm_panel_enable(panel); - } - setup_phy(encoder); mdp4_write(mdp4_kms, REG_MDP4_LCDC_ENABLE, 1); @@ -348,22 +333,34 @@ static void mdp4_lcdc_encoder_enable(struct drm_encoder *encoder) mdp4_lcdc_encoder->enabled = true; } +static enum drm_mode_status +mdp4_lcdc_encoder_mode_valid(struct drm_encoder *encoder, + const struct drm_display_mode *mode) +{ + struct mdp4_lcdc_encoder *mdp4_lcdc_encoder = + to_mdp4_lcdc_encoder(encoder); + long actual, requested; + + requested = 1000 * mode->clock; + actual = clk_round_rate(mdp4_lcdc_encoder->lcdc_clk, requested); + + DBG("requested=%ld, actual=%ld", requested, actual); + + if (actual != requested) + return MODE_CLOCK_RANGE; + + return MODE_OK; +} + static const struct drm_encoder_helper_funcs mdp4_lcdc_encoder_helper_funcs = { .mode_set = mdp4_lcdc_encoder_mode_set, .disable = mdp4_lcdc_encoder_disable, .enable = mdp4_lcdc_encoder_enable, + .mode_valid = mdp4_lcdc_encoder_mode_valid, }; -long mdp4_lcdc_round_pixclk(struct drm_encoder *encoder, unsigned long rate) -{ - struct mdp4_lcdc_encoder *mdp4_lcdc_encoder = - to_mdp4_lcdc_encoder(encoder); - return clk_round_rate(mdp4_lcdc_encoder->lcdc_clk, rate); -} - /* initialize encoder */ -struct drm_encoder *mdp4_lcdc_encoder_init(struct drm_device *dev, - struct device_node *panel_node) +struct drm_encoder *mdp4_lcdc_encoder_init(struct drm_device *dev) { struct drm_encoder *encoder; struct mdp4_lcdc_encoder *mdp4_lcdc_encoder; @@ -374,14 +371,11 @@ struct drm_encoder *mdp4_lcdc_encoder_init(struct drm_device *dev, if (IS_ERR(mdp4_lcdc_encoder)) return ERR_CAST(mdp4_lcdc_encoder); - mdp4_lcdc_encoder->panel_node = panel_node; - encoder = &mdp4_lcdc_encoder->base; drm_encoder_helper_add(encoder, &mdp4_lcdc_encoder_helper_funcs); - /* TODO: do we need different pll in other cases? */ - mdp4_lcdc_encoder->lcdc_clk = mpd4_lvds_pll_init(dev); + mdp4_lcdc_encoder->lcdc_clk = mpd4_get_lcdc_clock(dev); if (IS_ERR(mdp4_lcdc_encoder->lcdc_clk)) { DRM_DEV_ERROR(dev->dev, "failed to get lvds_clk\n"); return ERR_CAST(mdp4_lcdc_encoder->lcdc_clk); diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c deleted file mode 100644 index 7444b75c4215..000000000000 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c +++ /dev/null @@ -1,121 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2014 Red Hat - * Author: Rob Clark <robdclark@gmail.com> - * Author: Vinay Simha <vinaysimha@inforcecomputing.com> - */ - -#include "mdp4_kms.h" - -struct mdp4_lvds_connector { - struct drm_connector base; - struct drm_encoder *encoder; - struct device_node *panel_node; - struct drm_panel *panel; -}; -#define to_mdp4_lvds_connector(x) container_of(x, struct mdp4_lvds_connector, base) - -static enum drm_connector_status mdp4_lvds_connector_detect( - struct drm_connector *connector, bool force) -{ - struct mdp4_lvds_connector *mdp4_lvds_connector = - to_mdp4_lvds_connector(connector); - - if (!mdp4_lvds_connector->panel) { - mdp4_lvds_connector->panel = - of_drm_find_panel(mdp4_lvds_connector->panel_node); - if (IS_ERR(mdp4_lvds_connector->panel)) - mdp4_lvds_connector->panel = NULL; - } - - return mdp4_lvds_connector->panel ? - connector_status_connected : - connector_status_disconnected; -} - -static void mdp4_lvds_connector_destroy(struct drm_connector *connector) -{ - struct mdp4_lvds_connector *mdp4_lvds_connector = - to_mdp4_lvds_connector(connector); - - drm_connector_cleanup(connector); - - kfree(mdp4_lvds_connector); -} - -static int mdp4_lvds_connector_get_modes(struct drm_connector *connector) -{ - struct mdp4_lvds_connector *mdp4_lvds_connector = - to_mdp4_lvds_connector(connector); - struct drm_panel *panel = mdp4_lvds_connector->panel; - int ret = 0; - - if (panel) - ret = drm_panel_get_modes(panel, connector); - - return ret; -} - -static enum drm_mode_status -mdp4_lvds_connector_mode_valid(struct drm_connector *connector, - struct drm_display_mode *mode) -{ - struct mdp4_lvds_connector *mdp4_lvds_connector = - to_mdp4_lvds_connector(connector); - struct drm_encoder *encoder = mdp4_lvds_connector->encoder; - long actual, requested; - - requested = 1000 * mode->clock; - actual = mdp4_lcdc_round_pixclk(encoder, requested); - - DBG("requested=%ld, actual=%ld", requested, actual); - - if (actual != requested) - return MODE_CLOCK_RANGE; - - return MODE_OK; -} - -static const struct drm_connector_funcs mdp4_lvds_connector_funcs = { - .detect = mdp4_lvds_connector_detect, - .fill_modes = drm_helper_probe_single_connector_modes, - .destroy = mdp4_lvds_connector_destroy, - .reset = drm_atomic_helper_connector_reset, - .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, - .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, -}; - -static const struct drm_connector_helper_funcs mdp4_lvds_connector_helper_funcs = { - .get_modes = mdp4_lvds_connector_get_modes, - .mode_valid = mdp4_lvds_connector_mode_valid, -}; - -/* initialize connector */ -struct drm_connector *mdp4_lvds_connector_init(struct drm_device *dev, - struct device_node *panel_node, struct drm_encoder *encoder) -{ - struct drm_connector *connector = NULL; - struct mdp4_lvds_connector *mdp4_lvds_connector; - - mdp4_lvds_connector = kzalloc(sizeof(*mdp4_lvds_connector), GFP_KERNEL); - if (!mdp4_lvds_connector) - return ERR_PTR(-ENOMEM); - - mdp4_lvds_connector->encoder = encoder; - mdp4_lvds_connector->panel_node = panel_node; - - connector = &mdp4_lvds_connector->base; - - drm_connector_init(dev, connector, &mdp4_lvds_connector_funcs, - DRM_MODE_CONNECTOR_LVDS); - drm_connector_helper_add(connector, &mdp4_lvds_connector_helper_funcs); - - connector->polled = 0; - - connector->interlace_allowed = 0; - connector->doublescan_allowed = 0; - - drm_connector_attach_encoder(connector, encoder); - - return connector; -} diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_pll.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_pll.c index ab8c0c187fb2..fa2c29470510 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_pll.c +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_pll.c @@ -122,40 +122,59 @@ static const struct clk_ops mpd4_lvds_pll_ops = { .set_rate = mpd4_lvds_pll_set_rate, }; -static const char *mpd4_lvds_pll_parents[] = { - "pxo", +static const struct clk_parent_data mpd4_lvds_pll_parents[] = { + { .fw_name = "pxo", .name = "pxo", }, }; static struct clk_init_data pll_init = { .name = "mpd4_lvds_pll", .ops = &mpd4_lvds_pll_ops, - .parent_names = mpd4_lvds_pll_parents, + .parent_data = mpd4_lvds_pll_parents, .num_parents = ARRAY_SIZE(mpd4_lvds_pll_parents), }; -struct clk *mpd4_lvds_pll_init(struct drm_device *dev) +static struct clk_hw *mpd4_lvds_pll_init(struct drm_device *dev) { struct mdp4_lvds_pll *lvds_pll; - struct clk *clk; int ret; lvds_pll = devm_kzalloc(dev->dev, sizeof(*lvds_pll), GFP_KERNEL); - if (!lvds_pll) { - ret = -ENOMEM; - goto fail; - } + if (!lvds_pll) + return ERR_PTR(-ENOMEM); lvds_pll->dev = dev; lvds_pll->pll_hw.init = &pll_init; - clk = devm_clk_register(dev->dev, &lvds_pll->pll_hw); - if (IS_ERR(clk)) { - ret = PTR_ERR(clk); - goto fail; + ret = devm_clk_hw_register(dev->dev, &lvds_pll->pll_hw); + if (ret) + return ERR_PTR(ret); + + ret = devm_of_clk_add_hw_provider(dev->dev, of_clk_hw_simple_get, &lvds_pll->pll_hw); + if (ret) + return ERR_PTR(ret); + + return &lvds_pll->pll_hw; +} + +struct clk *mpd4_get_lcdc_clock(struct drm_device *dev) +{ + struct clk_hw *hw; + struct clk *clk; + + + /* TODO: do we need different pll in other cases? */ + hw = mpd4_lvds_pll_init(dev); + if (IS_ERR(hw)) { + DRM_DEV_ERROR(dev->dev, "failed to register LVDS PLL\n"); + return ERR_CAST(hw); } - return clk; + clk = devm_clk_get(dev->dev, "lcdc_clk"); + if (clk == ERR_PTR(-ENOENT)) { + drm_warn(dev, "can't get LCDC clock, using PLL directly\n"); -fail: - return ERR_PTR(ret); + return devm_clk_hw_get_clk(dev->dev, hw, "lcdc_clk"); + } + + return clk; } diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_ctl.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_ctl.c index 666de99a46a5..fc183fe37f56 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_ctl.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_ctl.c @@ -3,6 +3,7 @@ * Copyright (c) 2014-2015 The Linux Foundation. All rights reserved. */ +#include <linux/string_choices.h> #include "mdp5_kms.h" #include "mdp5_ctl.h" @@ -233,7 +234,7 @@ int mdp5_ctl_set_encoder_state(struct mdp5_ctl *ctl, return -EINVAL; ctl->encoder_enabled = enabled; - DBG("intf_%d: %s", intf->num, enabled ? "on" : "off"); + DBG("intf_%d: %s", intf->num, str_on_off(enabled)); if (start_signal_needed(ctl, pipeline)) { send_start_signal(ctl); diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c index 62de248ed1b0..bb1601921938 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c @@ -368,7 +368,7 @@ static void mdp5_plane_atomic_update(struct drm_plane *plane, } static int mdp5_plane_atomic_async_check(struct drm_plane *plane, - struct drm_atomic_state *state) + struct drm_atomic_state *state, bool flip) { struct drm_plane_state *new_plane_state = drm_atomic_get_new_plane_state(state, plane); diff --git a/drivers/gpu/drm/msm/disp/msm_disp_snapshot.c b/drivers/gpu/drm/msm/disp/msm_disp_snapshot.c index e75b97127c0d..2be00b11e557 100644 --- a/drivers/gpu/drm/msm/disp/msm_disp_snapshot.c +++ b/drivers/gpu/drm/msm/disp/msm_disp_snapshot.c @@ -109,7 +109,7 @@ int msm_disp_snapshot_init(struct drm_device *drm_dev) mutex_init(&kms->dump_mutex); - kms->dump_worker = kthread_create_worker(0, "%s", "disp_snapshot"); + kms->dump_worker = kthread_run_worker(0, "%s", "disp_snapshot"); if (IS_ERR(kms->dump_worker)) DRM_ERROR("failed to create disp state task\n"); diff --git a/drivers/gpu/drm/msm/dp/dp_audio.c b/drivers/gpu/drm/msm/dp/dp_audio.c index c179ed0e9e2b..f8bfb908f9b4 100644 --- a/drivers/gpu/drm/msm/dp/dp_audio.c +++ b/drivers/gpu/drm/msm/dp/dp_audio.c @@ -13,12 +13,13 @@ #include "dp_catalog.h" #include "dp_audio.h" +#include "dp_drm.h" #include "dp_panel.h" +#include "dp_reg.h" #include "dp_display.h" #include "dp_utils.h" struct msm_dp_audio_private { - struct platform_device *audio_pdev; struct platform_device *pdev; struct drm_device *drm_dev; struct msm_dp_catalog *catalog; @@ -28,251 +29,64 @@ struct msm_dp_audio_private { struct msm_dp_audio msm_dp_audio; }; -static u32 msm_dp_audio_get_header(struct msm_dp_catalog *catalog, - enum msm_dp_catalog_audio_sdp_type sdp, - enum msm_dp_catalog_audio_header_type header) -{ - return msm_dp_catalog_audio_get_header(catalog, sdp, header); -} - -static void msm_dp_audio_set_header(struct msm_dp_catalog *catalog, - u32 data, - enum msm_dp_catalog_audio_sdp_type sdp, - enum msm_dp_catalog_audio_header_type header) -{ - msm_dp_catalog_audio_set_header(catalog, sdp, header, data); -} - static void msm_dp_audio_stream_sdp(struct msm_dp_audio_private *audio) { - struct msm_dp_catalog *catalog = audio->catalog; - u32 value, new_value; - u8 parity_byte; - - /* Config header and parity byte 1 */ - value = msm_dp_audio_get_header(catalog, - DP_AUDIO_SDP_STREAM, DP_AUDIO_SDP_HEADER_1); - - new_value = 0x02; - parity_byte = msm_dp_utils_calculate_parity(new_value); - value |= ((new_value << HEADER_BYTE_1_BIT) - | (parity_byte << PARITY_BYTE_1_BIT)); - drm_dbg_dp(audio->drm_dev, - "Header Byte 1: value = 0x%x, parity_byte = 0x%x\n", - value, parity_byte); - msm_dp_audio_set_header(catalog, value, - DP_AUDIO_SDP_STREAM, DP_AUDIO_SDP_HEADER_1); - - /* Config header and parity byte 2 */ - value = msm_dp_audio_get_header(catalog, - DP_AUDIO_SDP_STREAM, DP_AUDIO_SDP_HEADER_2); - new_value = value; - parity_byte = msm_dp_utils_calculate_parity(new_value); - value |= ((new_value << HEADER_BYTE_2_BIT) - | (parity_byte << PARITY_BYTE_2_BIT)); - drm_dbg_dp(audio->drm_dev, - "Header Byte 2: value = 0x%x, parity_byte = 0x%x\n", - value, parity_byte); - - msm_dp_audio_set_header(catalog, value, - DP_AUDIO_SDP_STREAM, DP_AUDIO_SDP_HEADER_2); - - /* Config header and parity byte 3 */ - value = msm_dp_audio_get_header(catalog, - DP_AUDIO_SDP_STREAM, DP_AUDIO_SDP_HEADER_3); - - new_value = audio->channels - 1; - parity_byte = msm_dp_utils_calculate_parity(new_value); - value |= ((new_value << HEADER_BYTE_3_BIT) - | (parity_byte << PARITY_BYTE_3_BIT)); - drm_dbg_dp(audio->drm_dev, - "Header Byte 3: value = 0x%x, parity_byte = 0x%x\n", - value, parity_byte); - - msm_dp_audio_set_header(catalog, value, - DP_AUDIO_SDP_STREAM, DP_AUDIO_SDP_HEADER_3); + struct dp_sdp_header sdp_hdr = { + .HB0 = 0x00, + .HB1 = 0x02, + .HB2 = 0x00, + .HB3 = audio->channels - 1, + }; + + msm_dp_catalog_write_audio_stream(audio->catalog, &sdp_hdr); } static void msm_dp_audio_timestamp_sdp(struct msm_dp_audio_private *audio) { - struct msm_dp_catalog *catalog = audio->catalog; - u32 value, new_value; - u8 parity_byte; - - /* Config header and parity byte 1 */ - value = msm_dp_audio_get_header(catalog, - DP_AUDIO_SDP_TIMESTAMP, DP_AUDIO_SDP_HEADER_1); - - new_value = 0x1; - parity_byte = msm_dp_utils_calculate_parity(new_value); - value |= ((new_value << HEADER_BYTE_1_BIT) - | (parity_byte << PARITY_BYTE_1_BIT)); - drm_dbg_dp(audio->drm_dev, - "Header Byte 1: value = 0x%x, parity_byte = 0x%x\n", - value, parity_byte); - msm_dp_audio_set_header(catalog, value, - DP_AUDIO_SDP_TIMESTAMP, DP_AUDIO_SDP_HEADER_1); - - /* Config header and parity byte 2 */ - value = msm_dp_audio_get_header(catalog, - DP_AUDIO_SDP_TIMESTAMP, DP_AUDIO_SDP_HEADER_2); - - new_value = 0x17; - parity_byte = msm_dp_utils_calculate_parity(new_value); - value |= ((new_value << HEADER_BYTE_2_BIT) - | (parity_byte << PARITY_BYTE_2_BIT)); - drm_dbg_dp(audio->drm_dev, - "Header Byte 2: value = 0x%x, parity_byte = 0x%x\n", - value, parity_byte); - msm_dp_audio_set_header(catalog, value, - DP_AUDIO_SDP_TIMESTAMP, DP_AUDIO_SDP_HEADER_2); - - /* Config header and parity byte 3 */ - value = msm_dp_audio_get_header(catalog, - DP_AUDIO_SDP_TIMESTAMP, DP_AUDIO_SDP_HEADER_3); - - new_value = (0x0 | (0x11 << 2)); - parity_byte = msm_dp_utils_calculate_parity(new_value); - value |= ((new_value << HEADER_BYTE_3_BIT) - | (parity_byte << PARITY_BYTE_3_BIT)); - drm_dbg_dp(audio->drm_dev, - "Header Byte 3: value = 0x%x, parity_byte = 0x%x\n", - value, parity_byte); - msm_dp_audio_set_header(catalog, value, - DP_AUDIO_SDP_TIMESTAMP, DP_AUDIO_SDP_HEADER_3); + struct dp_sdp_header sdp_hdr = { + .HB0 = 0x00, + .HB1 = 0x01, + .HB2 = 0x17, + .HB3 = 0x0 | (0x11 << 2), + }; + + msm_dp_catalog_write_audio_timestamp(audio->catalog, &sdp_hdr); } static void msm_dp_audio_infoframe_sdp(struct msm_dp_audio_private *audio) { - struct msm_dp_catalog *catalog = audio->catalog; - u32 value, new_value; - u8 parity_byte; - - /* Config header and parity byte 1 */ - value = msm_dp_audio_get_header(catalog, - DP_AUDIO_SDP_INFOFRAME, DP_AUDIO_SDP_HEADER_1); - - new_value = 0x84; - parity_byte = msm_dp_utils_calculate_parity(new_value); - value |= ((new_value << HEADER_BYTE_1_BIT) - | (parity_byte << PARITY_BYTE_1_BIT)); - drm_dbg_dp(audio->drm_dev, - "Header Byte 1: value = 0x%x, parity_byte = 0x%x\n", - value, parity_byte); - msm_dp_audio_set_header(catalog, value, - DP_AUDIO_SDP_INFOFRAME, DP_AUDIO_SDP_HEADER_1); - - /* Config header and parity byte 2 */ - value = msm_dp_audio_get_header(catalog, - DP_AUDIO_SDP_INFOFRAME, DP_AUDIO_SDP_HEADER_2); - - new_value = 0x1b; - parity_byte = msm_dp_utils_calculate_parity(new_value); - value |= ((new_value << HEADER_BYTE_2_BIT) - | (parity_byte << PARITY_BYTE_2_BIT)); - drm_dbg_dp(audio->drm_dev, - "Header Byte 2: value = 0x%x, parity_byte = 0x%x\n", - value, parity_byte); - msm_dp_audio_set_header(catalog, value, - DP_AUDIO_SDP_INFOFRAME, DP_AUDIO_SDP_HEADER_2); - - /* Config header and parity byte 3 */ - value = msm_dp_audio_get_header(catalog, - DP_AUDIO_SDP_INFOFRAME, DP_AUDIO_SDP_HEADER_3); - - new_value = (0x0 | (0x11 << 2)); - parity_byte = msm_dp_utils_calculate_parity(new_value); - value |= ((new_value << HEADER_BYTE_3_BIT) - | (parity_byte << PARITY_BYTE_3_BIT)); - drm_dbg_dp(audio->drm_dev, - "Header Byte 3: value = 0x%x, parity_byte = 0x%x\n", - new_value, parity_byte); - msm_dp_audio_set_header(catalog, value, - DP_AUDIO_SDP_INFOFRAME, DP_AUDIO_SDP_HEADER_3); + struct dp_sdp_header sdp_hdr = { + .HB0 = 0x00, + .HB1 = 0x84, + .HB2 = 0x1b, + .HB3 = 0x0 | (0x11 << 2), + }; + + msm_dp_catalog_write_audio_infoframe(audio->catalog, &sdp_hdr); } static void msm_dp_audio_copy_management_sdp(struct msm_dp_audio_private *audio) { - struct msm_dp_catalog *catalog = audio->catalog; - u32 value, new_value; - u8 parity_byte; - - /* Config header and parity byte 1 */ - value = msm_dp_audio_get_header(catalog, - DP_AUDIO_SDP_COPYMANAGEMENT, DP_AUDIO_SDP_HEADER_1); - - new_value = 0x05; - parity_byte = msm_dp_utils_calculate_parity(new_value); - value |= ((new_value << HEADER_BYTE_1_BIT) - | (parity_byte << PARITY_BYTE_1_BIT)); - drm_dbg_dp(audio->drm_dev, - "Header Byte 1: value = 0x%x, parity_byte = 0x%x\n", - value, parity_byte); - msm_dp_audio_set_header(catalog, value, - DP_AUDIO_SDP_COPYMANAGEMENT, DP_AUDIO_SDP_HEADER_1); - - /* Config header and parity byte 2 */ - value = msm_dp_audio_get_header(catalog, - DP_AUDIO_SDP_COPYMANAGEMENT, DP_AUDIO_SDP_HEADER_2); - - new_value = 0x0F; - parity_byte = msm_dp_utils_calculate_parity(new_value); - value |= ((new_value << HEADER_BYTE_2_BIT) - | (parity_byte << PARITY_BYTE_2_BIT)); - drm_dbg_dp(audio->drm_dev, - "Header Byte 2: value = 0x%x, parity_byte = 0x%x\n", - value, parity_byte); - msm_dp_audio_set_header(catalog, value, - DP_AUDIO_SDP_COPYMANAGEMENT, DP_AUDIO_SDP_HEADER_2); - - /* Config header and parity byte 3 */ - value = msm_dp_audio_get_header(catalog, - DP_AUDIO_SDP_COPYMANAGEMENT, DP_AUDIO_SDP_HEADER_3); - - new_value = 0x0; - parity_byte = msm_dp_utils_calculate_parity(new_value); - value |= ((new_value << HEADER_BYTE_3_BIT) - | (parity_byte << PARITY_BYTE_3_BIT)); - drm_dbg_dp(audio->drm_dev, - "Header Byte 3: value = 0x%x, parity_byte = 0x%x\n", - value, parity_byte); - msm_dp_audio_set_header(catalog, value, - DP_AUDIO_SDP_COPYMANAGEMENT, DP_AUDIO_SDP_HEADER_3); + struct dp_sdp_header sdp_hdr = { + .HB0 = 0x00, + .HB1 = 0x05, + .HB2 = 0x0f, + .HB3 = 0x00, + }; + + msm_dp_catalog_write_audio_copy_mgmt(audio->catalog, &sdp_hdr); } static void msm_dp_audio_isrc_sdp(struct msm_dp_audio_private *audio) { - struct msm_dp_catalog *catalog = audio->catalog; - u32 value, new_value; - u8 parity_byte; - - /* Config header and parity byte 1 */ - value = msm_dp_audio_get_header(catalog, - DP_AUDIO_SDP_ISRC, DP_AUDIO_SDP_HEADER_1); - - new_value = 0x06; - parity_byte = msm_dp_utils_calculate_parity(new_value); - value |= ((new_value << HEADER_BYTE_1_BIT) - | (parity_byte << PARITY_BYTE_1_BIT)); - drm_dbg_dp(audio->drm_dev, - "Header Byte 1: value = 0x%x, parity_byte = 0x%x\n", - value, parity_byte); - msm_dp_audio_set_header(catalog, value, - DP_AUDIO_SDP_ISRC, DP_AUDIO_SDP_HEADER_1); - - /* Config header and parity byte 2 */ - value = msm_dp_audio_get_header(catalog, - DP_AUDIO_SDP_ISRC, DP_AUDIO_SDP_HEADER_2); - - new_value = 0x0F; - parity_byte = msm_dp_utils_calculate_parity(new_value); - value |= ((new_value << HEADER_BYTE_2_BIT) - | (parity_byte << PARITY_BYTE_2_BIT)); - drm_dbg_dp(audio->drm_dev, - "Header Byte 2: value = 0x%x, parity_byte = 0x%x\n", - value, parity_byte); - msm_dp_audio_set_header(catalog, value, - DP_AUDIO_SDP_ISRC, DP_AUDIO_SDP_HEADER_2); + struct dp_sdp_header sdp_hdr = { + .HB0 = 0x00, + .HB1 = 0x06, + .HB2 = 0x0f, + .HB3 = 0x00, + }; + + msm_dp_catalog_write_audio_isrc(audio->catalog, &sdp_hdr); } static void msm_dp_audio_setup_sdp(struct msm_dp_audio_private *audio) @@ -346,24 +160,11 @@ static void msm_dp_audio_enable(struct msm_dp_audio_private *audio, bool enable) msm_dp_catalog_audio_enable(catalog, enable); } -static struct msm_dp_audio_private *msm_dp_audio_get_data(struct platform_device *pdev) +static struct msm_dp_audio_private *msm_dp_audio_get_data(struct msm_dp *msm_dp_display) { struct msm_dp_audio *msm_dp_audio; - struct msm_dp *msm_dp_display; - - if (!pdev) { - DRM_ERROR("invalid input\n"); - return ERR_PTR(-ENODEV); - } - - msm_dp_display = platform_get_drvdata(pdev); - if (!msm_dp_display) { - DRM_ERROR("invalid input\n"); - return ERR_PTR(-ENODEV); - } msm_dp_audio = msm_dp_display->msm_dp_audio; - if (!msm_dp_audio) { DRM_ERROR("invalid msm_dp_audio data\n"); return ERR_PTR(-EINVAL); @@ -372,68 +173,16 @@ static struct msm_dp_audio_private *msm_dp_audio_get_data(struct platform_device return container_of(msm_dp_audio, struct msm_dp_audio_private, msm_dp_audio); } -static int msm_dp_audio_hook_plugged_cb(struct device *dev, void *data, - hdmi_codec_plugged_cb fn, - struct device *codec_dev) -{ - - struct platform_device *pdev; - struct msm_dp *msm_dp_display; - - pdev = to_platform_device(dev); - if (!pdev) { - pr_err("invalid input\n"); - return -ENODEV; - } - - msm_dp_display = platform_get_drvdata(pdev); - if (!msm_dp_display) { - pr_err("invalid input\n"); - return -ENODEV; - } - - return msm_dp_display_set_plugged_cb(msm_dp_display, fn, codec_dev); -} - -static int msm_dp_audio_get_eld(struct device *dev, - void *data, uint8_t *buf, size_t len) -{ - struct platform_device *pdev; - struct msm_dp *msm_dp_display; - - pdev = to_platform_device(dev); - - if (!pdev) { - DRM_ERROR("invalid input\n"); - return -ENODEV; - } - - msm_dp_display = platform_get_drvdata(pdev); - if (!msm_dp_display) { - DRM_ERROR("invalid input\n"); - return -ENODEV; - } - - mutex_lock(&msm_dp_display->connector->eld_mutex); - memcpy(buf, msm_dp_display->connector->eld, - min(sizeof(msm_dp_display->connector->eld), len)); - mutex_unlock(&msm_dp_display->connector->eld_mutex); - - return 0; -} - -int msm_dp_audio_hw_params(struct device *dev, - void *data, - struct hdmi_codec_daifmt *daifmt, - struct hdmi_codec_params *params) +int msm_dp_audio_prepare(struct drm_connector *connector, + struct drm_bridge *bridge, + struct hdmi_codec_daifmt *daifmt, + struct hdmi_codec_params *params) { int rc = 0; struct msm_dp_audio_private *audio; - struct platform_device *pdev; struct msm_dp *msm_dp_display; - pdev = to_platform_device(dev); - msm_dp_display = platform_get_drvdata(pdev); + msm_dp_display = to_dp_bridge(bridge)->msm_dp_display; /* * there could be cases where sound card can be opened even @@ -448,7 +197,7 @@ int msm_dp_audio_hw_params(struct device *dev, goto end; } - audio = msm_dp_audio_get_data(pdev); + audio = msm_dp_audio_get_data(msm_dp_display); if (IS_ERR(audio)) { rc = PTR_ERR(audio); goto end; @@ -467,15 +216,14 @@ end: return rc; } -static void msm_dp_audio_shutdown(struct device *dev, void *data) +void msm_dp_audio_shutdown(struct drm_connector *connector, + struct drm_bridge *bridge) { struct msm_dp_audio_private *audio; - struct platform_device *pdev; struct msm_dp *msm_dp_display; - pdev = to_platform_device(dev); - msm_dp_display = platform_get_drvdata(pdev); - audio = msm_dp_audio_get_data(pdev); + msm_dp_display = to_dp_bridge(bridge)->msm_dp_display; + audio = msm_dp_audio_get_data(msm_dp_display); if (IS_ERR(audio)) { DRM_ERROR("failed to get audio data\n"); return; @@ -497,56 +245,14 @@ static void msm_dp_audio_shutdown(struct device *dev, void *data) msm_dp_display_signal_audio_complete(msm_dp_display); } -static const struct hdmi_codec_ops msm_dp_audio_codec_ops = { - .hw_params = msm_dp_audio_hw_params, - .audio_shutdown = msm_dp_audio_shutdown, - .get_eld = msm_dp_audio_get_eld, - .hook_plugged_cb = msm_dp_audio_hook_plugged_cb, -}; - -static struct hdmi_codec_pdata codec_data = { - .ops = &msm_dp_audio_codec_ops, - .max_i2s_channels = 8, - .i2s = 1, -}; - -void msm_dp_unregister_audio_driver(struct device *dev, struct msm_dp_audio *msm_dp_audio) -{ - struct msm_dp_audio_private *audio_priv; - - audio_priv = container_of(msm_dp_audio, struct msm_dp_audio_private, msm_dp_audio); - - if (audio_priv->audio_pdev) { - platform_device_unregister(audio_priv->audio_pdev); - audio_priv->audio_pdev = NULL; - } -} - -int msm_dp_register_audio_driver(struct device *dev, - struct msm_dp_audio *msm_dp_audio) -{ - struct msm_dp_audio_private *audio_priv; - - audio_priv = container_of(msm_dp_audio, - struct msm_dp_audio_private, msm_dp_audio); - - audio_priv->audio_pdev = platform_device_register_data(dev, - HDMI_CODEC_DRV_NAME, - PLATFORM_DEVID_AUTO, - &codec_data, - sizeof(codec_data)); - return PTR_ERR_OR_ZERO(audio_priv->audio_pdev); -} - struct msm_dp_audio *msm_dp_audio_get(struct platform_device *pdev, - struct msm_dp_panel *panel, struct msm_dp_catalog *catalog) { int rc = 0; struct msm_dp_audio_private *audio; struct msm_dp_audio *msm_dp_audio; - if (!pdev || !panel || !catalog) { + if (!pdev || !catalog) { DRM_ERROR("invalid input\n"); rc = -EINVAL; goto error; @@ -563,8 +269,6 @@ struct msm_dp_audio *msm_dp_audio_get(struct platform_device *pdev, msm_dp_audio = &audio->msm_dp_audio; - msm_dp_catalog_audio_init(catalog); - return msm_dp_audio; error: return ERR_PTR(rc); diff --git a/drivers/gpu/drm/msm/dp/dp_audio.h b/drivers/gpu/drm/msm/dp/dp_audio.h index 1c9efaaa40e5..58fc14693e48 100644 --- a/drivers/gpu/drm/msm/dp/dp_audio.h +++ b/drivers/gpu/drm/msm/dp/dp_audio.h @@ -8,7 +8,6 @@ #include <linux/platform_device.h> -#include "dp_panel.h" #include "dp_catalog.h" #include <sound/hdmi-codec.h> @@ -28,34 +27,15 @@ struct msm_dp_audio { * Creates and instance of dp audio. * * @pdev: caller's platform device instance. - * @panel: an instance of msm_dp_panel module. * @catalog: an instance of msm_dp_catalog module. * * Returns the error code in case of failure, otherwize * an instance of newly created msm_dp_module. */ struct msm_dp_audio *msm_dp_audio_get(struct platform_device *pdev, - struct msm_dp_panel *panel, struct msm_dp_catalog *catalog); /** - * msm_dp_register_audio_driver() - * - * Registers DP device with hdmi_codec interface. - * - * @dev: DP device instance. - * @msm_dp_audio: an instance of msm_dp_audio module. - * - * - * Returns the error code in case of failure, otherwise - * zero on success. - */ -int msm_dp_register_audio_driver(struct device *dev, - struct msm_dp_audio *msm_dp_audio); - -void msm_dp_unregister_audio_driver(struct device *dev, struct msm_dp_audio *msm_dp_audio); - -/** * msm_dp_audio_put() * * Cleans the msm_dp_audio instance. @@ -64,10 +44,12 @@ void msm_dp_unregister_audio_driver(struct device *dev, struct msm_dp_audio *msm */ void msm_dp_audio_put(struct msm_dp_audio *msm_dp_audio); -int msm_dp_audio_hw_params(struct device *dev, - void *data, - struct hdmi_codec_daifmt *daifmt, - struct hdmi_codec_params *params); +int msm_dp_audio_prepare(struct drm_connector *connector, + struct drm_bridge *bridge, + struct hdmi_codec_daifmt *daifmt, + struct hdmi_codec_params *params); +void msm_dp_audio_shutdown(struct drm_connector *connector, + struct drm_bridge *bridge); #endif /* _DP_AUDIO_H_ */ diff --git a/drivers/gpu/drm/msm/dp/dp_catalog.c b/drivers/gpu/drm/msm/dp/dp_catalog.c index 2a755a06ac49..7b7eadb2f83b 100644 --- a/drivers/gpu/drm/msm/dp/dp_catalog.c +++ b/drivers/gpu/drm/msm/dp/dp_catalog.c @@ -79,7 +79,6 @@ struct msm_dp_catalog_private { struct device *dev; struct drm_device *drm_dev; struct dss_io_data io; - u32 (*audio_map)[DP_AUDIO_SDP_HEADER_MAX]; struct msm_dp_catalog msm_dp_catalog; }; @@ -276,43 +275,6 @@ int msm_dp_catalog_aux_wait_for_hpd_connect_state(struct msm_dp_catalog *msm_dp_ min(wait_us, 2000), wait_us); } -static void dump_regs(void __iomem *base, int len) -{ - int i; - u32 x0, x4, x8, xc; - u32 addr_off = 0; - - len = DIV_ROUND_UP(len, 16); - for (i = 0; i < len; i++) { - x0 = readl_relaxed(base + addr_off); - x4 = readl_relaxed(base + addr_off + 0x04); - x8 = readl_relaxed(base + addr_off + 0x08); - xc = readl_relaxed(base + addr_off + 0x0c); - - pr_info("%08x: %08x %08x %08x %08x", addr_off, x0, x4, x8, xc); - addr_off += 16; - } -} - -void msm_dp_catalog_dump_regs(struct msm_dp_catalog *msm_dp_catalog) -{ - struct msm_dp_catalog_private *catalog = container_of(msm_dp_catalog, - struct msm_dp_catalog_private, msm_dp_catalog); - struct dss_io_data *io = &catalog->io; - - pr_info("AHB regs\n"); - dump_regs(io->ahb.base, io->ahb.len); - - pr_info("AUXCLK regs\n"); - dump_regs(io->aux.base, io->aux.len); - - pr_info("LCLK regs\n"); - dump_regs(io->link.base, io->link.len); - - pr_info("P0CLK regs\n"); - dump_regs(io->p0.base, io->p0.len); -} - u32 msm_dp_catalog_aux_get_irq(struct msm_dp_catalog *msm_dp_catalog) { struct msm_dp_catalog_private *catalog = container_of(msm_dp_catalog, @@ -1159,38 +1121,75 @@ struct msm_dp_catalog *msm_dp_catalog_get(struct device *dev) return &catalog->msm_dp_catalog; } -u32 msm_dp_catalog_audio_get_header(struct msm_dp_catalog *msm_dp_catalog, - enum msm_dp_catalog_audio_sdp_type sdp, - enum msm_dp_catalog_audio_header_type header) +void msm_dp_catalog_write_audio_stream(struct msm_dp_catalog *msm_dp_catalog, + struct dp_sdp_header *sdp_hdr) { - struct msm_dp_catalog_private *catalog; - u32 (*sdp_map)[DP_AUDIO_SDP_HEADER_MAX]; + struct msm_dp_catalog_private *catalog = container_of(msm_dp_catalog, + struct msm_dp_catalog_private, msm_dp_catalog); + u32 header[2]; - catalog = container_of(msm_dp_catalog, - struct msm_dp_catalog_private, msm_dp_catalog); + msm_dp_utils_pack_sdp_header(sdp_hdr, header); + + msm_dp_write_link(catalog, MMSS_DP_AUDIO_STREAM_0, header[0]); + msm_dp_write_link(catalog, MMSS_DP_AUDIO_STREAM_1, header[1]); +} + +void msm_dp_catalog_write_audio_timestamp(struct msm_dp_catalog *msm_dp_catalog, + struct dp_sdp_header *sdp_hdr) +{ + struct msm_dp_catalog_private *catalog = container_of(msm_dp_catalog, + struct msm_dp_catalog_private, msm_dp_catalog); + u32 header[2]; - sdp_map = catalog->audio_map; + msm_dp_utils_pack_sdp_header(sdp_hdr, header); - return msm_dp_read_link(catalog, sdp_map[sdp][header]); + msm_dp_write_link(catalog, MMSS_DP_AUDIO_TIMESTAMP_0, header[0]); + msm_dp_write_link(catalog, MMSS_DP_AUDIO_TIMESTAMP_1, header[1]); } -void msm_dp_catalog_audio_set_header(struct msm_dp_catalog *msm_dp_catalog, - enum msm_dp_catalog_audio_sdp_type sdp, - enum msm_dp_catalog_audio_header_type header, - u32 data) +void msm_dp_catalog_write_audio_infoframe(struct msm_dp_catalog *msm_dp_catalog, + struct dp_sdp_header *sdp_hdr) { - struct msm_dp_catalog_private *catalog; - u32 (*sdp_map)[DP_AUDIO_SDP_HEADER_MAX]; + struct msm_dp_catalog_private *catalog = container_of(msm_dp_catalog, + struct msm_dp_catalog_private, msm_dp_catalog); + u32 header[2]; - if (!msm_dp_catalog) - return; + msm_dp_utils_pack_sdp_header(sdp_hdr, header); - catalog = container_of(msm_dp_catalog, - struct msm_dp_catalog_private, msm_dp_catalog); + msm_dp_write_link(catalog, MMSS_DP_AUDIO_INFOFRAME_0, header[0]); + msm_dp_write_link(catalog, MMSS_DP_AUDIO_INFOFRAME_1, header[1]); +} + +void msm_dp_catalog_write_audio_copy_mgmt(struct msm_dp_catalog *msm_dp_catalog, + struct dp_sdp_header *sdp_hdr) +{ + struct msm_dp_catalog_private *catalog = container_of(msm_dp_catalog, + struct msm_dp_catalog_private, msm_dp_catalog); + u32 header[2]; - sdp_map = catalog->audio_map; + msm_dp_utils_pack_sdp_header(sdp_hdr, header); - msm_dp_write_link(catalog, sdp_map[sdp][header], data); + msm_dp_write_link(catalog, MMSS_DP_AUDIO_COPYMANAGEMENT_0, header[0]); + msm_dp_write_link(catalog, MMSS_DP_AUDIO_COPYMANAGEMENT_1, header[1]); +} + +void msm_dp_catalog_write_audio_isrc(struct msm_dp_catalog *msm_dp_catalog, + struct dp_sdp_header *sdp_hdr) +{ + struct msm_dp_catalog_private *catalog = container_of(msm_dp_catalog, + struct msm_dp_catalog_private, msm_dp_catalog); + struct dp_sdp_header tmp = *sdp_hdr; + u32 header[2]; + u32 reg; + + /* XXX: is it necessary to preserve this field? */ + reg = msm_dp_read_link(catalog, MMSS_DP_AUDIO_ISRC_1); + tmp.HB3 = FIELD_GET(HEADER_3_MASK, reg); + + msm_dp_utils_pack_sdp_header(&tmp, header); + + msm_dp_write_link(catalog, MMSS_DP_AUDIO_ISRC_0, header[0]); + msm_dp_write_link(catalog, MMSS_DP_AUDIO_ISRC_1, header[1]); } void msm_dp_catalog_audio_config_acr(struct msm_dp_catalog *msm_dp_catalog, u32 select) @@ -1276,47 +1275,6 @@ void msm_dp_catalog_audio_config_sdp(struct msm_dp_catalog *msm_dp_catalog) msm_dp_write_link(catalog, MMSS_DP_SDP_CFG2, sdp_cfg2); } -void msm_dp_catalog_audio_init(struct msm_dp_catalog *msm_dp_catalog) -{ - struct msm_dp_catalog_private *catalog; - - static u32 sdp_map[][DP_AUDIO_SDP_HEADER_MAX] = { - { - MMSS_DP_AUDIO_STREAM_0, - MMSS_DP_AUDIO_STREAM_1, - MMSS_DP_AUDIO_STREAM_1, - }, - { - MMSS_DP_AUDIO_TIMESTAMP_0, - MMSS_DP_AUDIO_TIMESTAMP_1, - MMSS_DP_AUDIO_TIMESTAMP_1, - }, - { - MMSS_DP_AUDIO_INFOFRAME_0, - MMSS_DP_AUDIO_INFOFRAME_1, - MMSS_DP_AUDIO_INFOFRAME_1, - }, - { - MMSS_DP_AUDIO_COPYMANAGEMENT_0, - MMSS_DP_AUDIO_COPYMANAGEMENT_1, - MMSS_DP_AUDIO_COPYMANAGEMENT_1, - }, - { - MMSS_DP_AUDIO_ISRC_0, - MMSS_DP_AUDIO_ISRC_1, - MMSS_DP_AUDIO_ISRC_1, - }, - }; - - if (!msm_dp_catalog) - return; - - catalog = container_of(msm_dp_catalog, - struct msm_dp_catalog_private, msm_dp_catalog); - - catalog->audio_map = sdp_map; -} - void msm_dp_catalog_audio_sfe_level(struct msm_dp_catalog *msm_dp_catalog, u32 safe_to_exit_level) { struct msm_dp_catalog_private *catalog; diff --git a/drivers/gpu/drm/msm/dp/dp_catalog.h b/drivers/gpu/drm/msm/dp/dp_catalog.h index e932b17eecbf..6678b0ac9a67 100644 --- a/drivers/gpu/drm/msm/dp/dp_catalog.h +++ b/drivers/gpu/drm/msm/dp/dp_catalog.h @@ -31,22 +31,6 @@ #define DP_HW_VERSION_1_0 0x10000000 #define DP_HW_VERSION_1_2 0x10020000 -enum msm_dp_catalog_audio_sdp_type { - DP_AUDIO_SDP_STREAM, - DP_AUDIO_SDP_TIMESTAMP, - DP_AUDIO_SDP_INFOFRAME, - DP_AUDIO_SDP_COPYMANAGEMENT, - DP_AUDIO_SDP_ISRC, - DP_AUDIO_SDP_MAX, -}; - -enum msm_dp_catalog_audio_header_type { - DP_AUDIO_SDP_HEADER_1, - DP_AUDIO_SDP_HEADER_2, - DP_AUDIO_SDP_HEADER_3, - DP_AUDIO_SDP_HEADER_MAX, -}; - struct msm_dp_catalog { bool wide_bus_en; }; @@ -104,7 +88,6 @@ int msm_dp_catalog_panel_timing_cfg(struct msm_dp_catalog *msm_dp_catalog, u32 t u32 sync_start, u32 width_blanking, u32 msm_dp_active); void msm_dp_catalog_panel_enable_vsc_sdp(struct msm_dp_catalog *msm_dp_catalog, struct dp_sdp *vsc_sdp); void msm_dp_catalog_panel_disable_vsc_sdp(struct msm_dp_catalog *msm_dp_catalog); -void msm_dp_catalog_dump_regs(struct msm_dp_catalog *msm_dp_catalog); void msm_dp_catalog_panel_tpg_enable(struct msm_dp_catalog *msm_dp_catalog, struct drm_display_mode *drm_mode); void msm_dp_catalog_panel_tpg_disable(struct msm_dp_catalog *msm_dp_catalog); @@ -112,17 +95,19 @@ void msm_dp_catalog_panel_tpg_disable(struct msm_dp_catalog *msm_dp_catalog); struct msm_dp_catalog *msm_dp_catalog_get(struct device *dev); /* DP Audio APIs */ -u32 msm_dp_catalog_audio_get_header(struct msm_dp_catalog *msm_dp_catalog, - enum msm_dp_catalog_audio_sdp_type sdp, - enum msm_dp_catalog_audio_header_type header); -void msm_dp_catalog_audio_set_header(struct msm_dp_catalog *msm_dp_catalog, - enum msm_dp_catalog_audio_sdp_type sdp, - enum msm_dp_catalog_audio_header_type header, - u32 data); +void msm_dp_catalog_write_audio_stream(struct msm_dp_catalog *msm_dp_catalog, + struct dp_sdp_header *sdp_hdr); +void msm_dp_catalog_write_audio_timestamp(struct msm_dp_catalog *msm_dp_catalog, + struct dp_sdp_header *sdp_hdr); +void msm_dp_catalog_write_audio_infoframe(struct msm_dp_catalog *msm_dp_catalog, + struct dp_sdp_header *sdp_hdr); +void msm_dp_catalog_write_audio_copy_mgmt(struct msm_dp_catalog *msm_dp_catalog, + struct dp_sdp_header *sdp_hdr); +void msm_dp_catalog_write_audio_isrc(struct msm_dp_catalog *msm_dp_catalog, + struct dp_sdp_header *sdp_hdr); void msm_dp_catalog_audio_config_acr(struct msm_dp_catalog *catalog, u32 select); void msm_dp_catalog_audio_enable(struct msm_dp_catalog *catalog, bool enable); void msm_dp_catalog_audio_config_sdp(struct msm_dp_catalog *catalog); -void msm_dp_catalog_audio_init(struct msm_dp_catalog *catalog); void msm_dp_catalog_audio_sfe_level(struct msm_dp_catalog *catalog, u32 safe_to_exit_level); #endif /* _DP_CATALOG_H_ */ diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c index 9c463ae2f8fa..a50bfafbb4ea 100644 --- a/drivers/gpu/drm/msm/dp/dp_ctrl.c +++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c @@ -11,6 +11,7 @@ #include <linux/phy/phy.h> #include <linux/phy/phy-dp.h> #include <linux/pm_opp.h> +#include <linux/string_choices.h> #include <drm/display/drm_dp_helper.h> #include <drm/drm_fixed.h> @@ -1033,10 +1034,12 @@ static int msm_dp_ctrl_set_vx_px(struct msm_dp_ctrl_private *ctrl, return 0; } -static int msm_dp_ctrl_update_vx_px(struct msm_dp_ctrl_private *ctrl) +static int msm_dp_ctrl_update_phy_vx_px(struct msm_dp_ctrl_private *ctrl, + enum drm_dp_phy dp_phy) { struct msm_dp_link *link = ctrl->link; - int ret = 0, lane, lane_cnt; + int lane, lane_cnt, reg; + int ret = 0; u8 buf[4]; u32 max_level_reached = 0; u32 voltage_swing_level = link->phy_params.v_level; @@ -1074,8 +1077,13 @@ static int msm_dp_ctrl_update_vx_px(struct msm_dp_ctrl_private *ctrl) drm_dbg_dp(ctrl->drm_dev, "sink: p|v=0x%x\n", voltage_swing_level | pre_emphasis_level); - ret = drm_dp_dpcd_write(ctrl->aux, DP_TRAINING_LANE0_SET, - buf, lane_cnt); + + if (dp_phy == DP_PHY_DPRX) + reg = DP_TRAINING_LANE0_SET; + else + reg = DP_TRAINING_LANE0_SET_PHY_REPEATER(dp_phy); + + ret = drm_dp_dpcd_write(ctrl->aux, reg, buf, lane_cnt); if (ret == lane_cnt) ret = 0; @@ -1083,9 +1091,10 @@ static int msm_dp_ctrl_update_vx_px(struct msm_dp_ctrl_private *ctrl) } static bool msm_dp_ctrl_train_pattern_set(struct msm_dp_ctrl_private *ctrl, - u8 pattern) + u8 pattern, enum drm_dp_phy dp_phy) { u8 buf; + int reg; int ret = 0; drm_dbg_dp(ctrl->drm_dev, "sink: pattern=%x\n", pattern); @@ -1095,31 +1104,26 @@ static bool msm_dp_ctrl_train_pattern_set(struct msm_dp_ctrl_private *ctrl, if (pattern && pattern != DP_TRAINING_PATTERN_4) buf |= DP_LINK_SCRAMBLING_DISABLE; - ret = drm_dp_dpcd_writeb(ctrl->aux, DP_TRAINING_PATTERN_SET, buf); - return ret == 1; -} - -static int msm_dp_ctrl_read_link_status(struct msm_dp_ctrl_private *ctrl, - u8 *link_status) -{ - int ret = 0, len; - - len = drm_dp_dpcd_read_link_status(ctrl->aux, link_status); - if (len != DP_LINK_STATUS_SIZE) { - DRM_ERROR("DP link status read failed, err: %d\n", len); - ret = -EINVAL; - } + if (dp_phy == DP_PHY_DPRX) + reg = DP_TRAINING_PATTERN_SET; + else + reg = DP_TRAINING_PATTERN_SET_PHY_REPEATER(dp_phy); - return ret; + ret = drm_dp_dpcd_writeb(ctrl->aux, reg, buf); + return ret == 1; } static int msm_dp_ctrl_link_train_1(struct msm_dp_ctrl_private *ctrl, - int *training_step) + int *training_step, enum drm_dp_phy dp_phy) { + int delay_us; int tries, old_v_level, ret = 0; u8 link_status[DP_LINK_STATUS_SIZE]; int const maximum_retries = 4; + delay_us = drm_dp_read_clock_recovery_delay(ctrl->aux, + ctrl->panel->dpcd, dp_phy, false); + msm_dp_catalog_ctrl_state_ctrl(ctrl->catalog, 0); *training_step = DP_TRAINING_1; @@ -1128,18 +1132,19 @@ static int msm_dp_ctrl_link_train_1(struct msm_dp_ctrl_private *ctrl, if (ret) return ret; msm_dp_ctrl_train_pattern_set(ctrl, DP_TRAINING_PATTERN_1 | - DP_LINK_SCRAMBLING_DISABLE); + DP_LINK_SCRAMBLING_DISABLE, dp_phy); - ret = msm_dp_ctrl_update_vx_px(ctrl); + msm_dp_link_reset_phy_params_vx_px(ctrl->link); + ret = msm_dp_ctrl_update_phy_vx_px(ctrl, dp_phy); if (ret) return ret; tries = 0; old_v_level = ctrl->link->phy_params.v_level; for (tries = 0; tries < maximum_retries; tries++) { - drm_dp_link_train_clock_recovery_delay(ctrl->aux, ctrl->panel->dpcd); + fsleep(delay_us); - ret = msm_dp_ctrl_read_link_status(ctrl, link_status); + ret = drm_dp_dpcd_read_phy_link_status(ctrl->aux, dp_phy, link_status); if (ret) return ret; @@ -1160,7 +1165,7 @@ static int msm_dp_ctrl_link_train_1(struct msm_dp_ctrl_private *ctrl, } msm_dp_link_adjust_levels(ctrl->link, link_status); - ret = msm_dp_ctrl_update_vx_px(ctrl); + ret = msm_dp_ctrl_update_phy_vx_px(ctrl, dp_phy); if (ret) return ret; } @@ -1212,21 +1217,31 @@ static int msm_dp_ctrl_link_lane_down_shift(struct msm_dp_ctrl_private *ctrl) return 0; } -static void msm_dp_ctrl_clear_training_pattern(struct msm_dp_ctrl_private *ctrl) +static void msm_dp_ctrl_clear_training_pattern(struct msm_dp_ctrl_private *ctrl, + enum drm_dp_phy dp_phy) { - msm_dp_ctrl_train_pattern_set(ctrl, DP_TRAINING_PATTERN_DISABLE); - drm_dp_link_train_channel_eq_delay(ctrl->aux, ctrl->panel->dpcd); + int delay_us; + + msm_dp_ctrl_train_pattern_set(ctrl, DP_TRAINING_PATTERN_DISABLE, dp_phy); + + delay_us = drm_dp_read_channel_eq_delay(ctrl->aux, + ctrl->panel->dpcd, dp_phy, false); + fsleep(delay_us); } static int msm_dp_ctrl_link_train_2(struct msm_dp_ctrl_private *ctrl, - int *training_step) + int *training_step, enum drm_dp_phy dp_phy) { + int delay_us; int tries = 0, ret = 0; u8 pattern; u32 state_ctrl_bit; int const maximum_retries = 5; u8 link_status[DP_LINK_STATUS_SIZE]; + delay_us = drm_dp_read_channel_eq_delay(ctrl->aux, + ctrl->panel->dpcd, dp_phy, false); + msm_dp_catalog_ctrl_state_ctrl(ctrl->catalog, 0); *training_step = DP_TRAINING_2; @@ -1246,12 +1261,12 @@ static int msm_dp_ctrl_link_train_2(struct msm_dp_ctrl_private *ctrl, if (ret) return ret; - msm_dp_ctrl_train_pattern_set(ctrl, pattern); + msm_dp_ctrl_train_pattern_set(ctrl, pattern, dp_phy); for (tries = 0; tries <= maximum_retries; tries++) { - drm_dp_link_train_channel_eq_delay(ctrl->aux, ctrl->panel->dpcd); + fsleep(delay_us); - ret = msm_dp_ctrl_read_link_status(ctrl, link_status); + ret = drm_dp_dpcd_read_phy_link_status(ctrl->aux, dp_phy, link_status); if (ret) return ret; @@ -1261,7 +1276,7 @@ static int msm_dp_ctrl_link_train_2(struct msm_dp_ctrl_private *ctrl, } msm_dp_link_adjust_levels(ctrl->link, link_status); - ret = msm_dp_ctrl_update_vx_px(ctrl); + ret = msm_dp_ctrl_update_phy_vx_px(ctrl, dp_phy); if (ret) return ret; @@ -1270,9 +1285,32 @@ static int msm_dp_ctrl_link_train_2(struct msm_dp_ctrl_private *ctrl, return -ETIMEDOUT; } +static int msm_dp_ctrl_link_train_1_2(struct msm_dp_ctrl_private *ctrl, + int *training_step, enum drm_dp_phy dp_phy) +{ + int ret; + + ret = msm_dp_ctrl_link_train_1(ctrl, training_step, dp_phy); + if (ret) { + DRM_ERROR("link training #1 on phy %d failed. ret=%d\n", dp_phy, ret); + return ret; + } + drm_dbg_dp(ctrl->drm_dev, "link training #1 on phy %d successful\n", dp_phy); + + ret = msm_dp_ctrl_link_train_2(ctrl, training_step, dp_phy); + if (ret) { + DRM_ERROR("link training #2 on phy %d failed. ret=%d\n", dp_phy, ret); + return ret; + } + drm_dbg_dp(ctrl->drm_dev, "link training #2 on phy %d successful\n", dp_phy); + + return 0; +} + static int msm_dp_ctrl_link_train(struct msm_dp_ctrl_private *ctrl, int *training_step) { + int i; int ret = 0; const u8 *dpcd = ctrl->panel->dpcd; u8 encoding[] = { 0, DP_SET_ANSI_8B10B }; @@ -1285,8 +1323,6 @@ static int msm_dp_ctrl_link_train(struct msm_dp_ctrl_private *ctrl, link_info.rate = ctrl->link->link_params.rate; link_info.capabilities = DP_LINK_CAP_ENHANCED_FRAMING; - msm_dp_link_reset_phy_params_vx_px(ctrl->link); - msm_dp_aux_link_configure(ctrl->aux, &link_info); if (drm_dp_max_downspread(dpcd)) @@ -1301,24 +1337,27 @@ static int msm_dp_ctrl_link_train(struct msm_dp_ctrl_private *ctrl, &assr, 1); } - ret = msm_dp_ctrl_link_train_1(ctrl, training_step); + for (i = ctrl->link->lttpr_count - 1; i >= 0; i--) { + enum drm_dp_phy dp_phy = DP_PHY_LTTPR(i); + + ret = msm_dp_ctrl_link_train_1_2(ctrl, training_step, dp_phy); + msm_dp_ctrl_clear_training_pattern(ctrl, dp_phy); + + if (ret) + break; + } + if (ret) { - DRM_ERROR("link training #1 failed. ret=%d\n", ret); + DRM_ERROR("link training of LTTPR(s) failed. ret=%d\n", ret); goto end; } - /* print success info as this is a result of user initiated action */ - drm_dbg_dp(ctrl->drm_dev, "link training #1 successful\n"); - - ret = msm_dp_ctrl_link_train_2(ctrl, training_step); + ret = msm_dp_ctrl_link_train_1_2(ctrl, training_step, DP_PHY_DPRX); if (ret) { - DRM_ERROR("link training #2 failed. ret=%d\n", ret); + DRM_ERROR("link training on sink failed. ret=%d\n", ret); goto end; } - /* print success info as this is a result of user initiated action */ - drm_dbg_dp(ctrl->drm_dev, "link training #2 successful\n"); - end: msm_dp_catalog_ctrl_state_ctrl(ctrl->catalog, 0); @@ -1366,9 +1405,9 @@ int msm_dp_ctrl_core_clk_enable(struct msm_dp_ctrl *msm_dp_ctrl) drm_dbg_dp(ctrl->drm_dev, "enable core clocks \n"); drm_dbg_dp(ctrl->drm_dev, "stream_clks:%s link_clks:%s core_clks:%s\n", - ctrl->stream_clks_on ? "on" : "off", - ctrl->link_clks_on ? "on" : "off", - ctrl->core_clks_on ? "on" : "off"); + str_on_off(ctrl->stream_clks_on), + str_on_off(ctrl->link_clks_on), + str_on_off(ctrl->core_clks_on)); return 0; } @@ -1385,9 +1424,9 @@ void msm_dp_ctrl_core_clk_disable(struct msm_dp_ctrl *msm_dp_ctrl) drm_dbg_dp(ctrl->drm_dev, "disable core clocks \n"); drm_dbg_dp(ctrl->drm_dev, "stream_clks:%s link_clks:%s core_clks:%s\n", - ctrl->stream_clks_on ? "on" : "off", - ctrl->link_clks_on ? "on" : "off", - ctrl->core_clks_on ? "on" : "off"); + str_on_off(ctrl->stream_clks_on), + str_on_off(ctrl->link_clks_on), + str_on_off(ctrl->core_clks_on)); } static int msm_dp_ctrl_link_clk_enable(struct msm_dp_ctrl *msm_dp_ctrl) @@ -1416,9 +1455,9 @@ static int msm_dp_ctrl_link_clk_enable(struct msm_dp_ctrl *msm_dp_ctrl) drm_dbg_dp(ctrl->drm_dev, "enable link clocks\n"); drm_dbg_dp(ctrl->drm_dev, "stream_clks:%s link_clks:%s core_clks:%s\n", - ctrl->stream_clks_on ? "on" : "off", - ctrl->link_clks_on ? "on" : "off", - ctrl->core_clks_on ? "on" : "off"); + str_on_off(ctrl->stream_clks_on), + str_on_off(ctrl->link_clks_on), + str_on_off(ctrl->core_clks_on)); return 0; } @@ -1435,9 +1474,9 @@ static void msm_dp_ctrl_link_clk_disable(struct msm_dp_ctrl *msm_dp_ctrl) drm_dbg_dp(ctrl->drm_dev, "disabled link clocks\n"); drm_dbg_dp(ctrl->drm_dev, "stream_clks:%s link_clks:%s core_clks:%s\n", - ctrl->stream_clks_on ? "on" : "off", - ctrl->link_clks_on ? "on" : "off", - ctrl->core_clks_on ? "on" : "off"); + str_on_off(ctrl->stream_clks_on), + str_on_off(ctrl->link_clks_on), + str_on_off(ctrl->core_clks_on)); } static int msm_dp_ctrl_enable_mainlink_clocks(struct msm_dp_ctrl_private *ctrl) @@ -1635,7 +1674,7 @@ static int msm_dp_ctrl_link_maintenance(struct msm_dp_ctrl_private *ctrl) if (ret) goto end; - msm_dp_ctrl_clear_training_pattern(ctrl); + msm_dp_ctrl_clear_training_pattern(ctrl, DP_PHY_DPRX); msm_dp_catalog_ctrl_state_ctrl(ctrl->catalog, DP_STATE_CTRL_SEND_VIDEO); @@ -1659,7 +1698,7 @@ static bool msm_dp_ctrl_send_phy_test_pattern(struct msm_dp_ctrl_private *ctrl) return false; } msm_dp_catalog_ctrl_send_phy_pattern(ctrl->catalog, pattern_requested); - msm_dp_ctrl_update_vx_px(ctrl); + msm_dp_ctrl_update_phy_vx_px(ctrl, DP_PHY_DPRX); msm_dp_link_send_test_response(ctrl->link); pattern_sent = msm_dp_catalog_ctrl_read_phy_pattern(ctrl->catalog); @@ -1804,7 +1843,7 @@ static bool msm_dp_ctrl_channel_eq_ok(struct msm_dp_ctrl_private *ctrl) u8 link_status[DP_LINK_STATUS_SIZE]; int num_lanes = ctrl->link->link_params.num_lanes; - msm_dp_ctrl_read_link_status(ctrl, link_status); + drm_dp_dpcd_read_link_status(ctrl->aux, link_status); return drm_dp_channel_eq_ok(link_status, num_lanes); } @@ -1862,7 +1901,7 @@ int msm_dp_ctrl_on_link(struct msm_dp_ctrl *msm_dp_ctrl) if (!msm_dp_catalog_link_is_connected(ctrl->catalog)) break; - msm_dp_ctrl_read_link_status(ctrl, link_status); + drm_dp_dpcd_read_link_status(ctrl->aux, link_status); rc = msm_dp_ctrl_link_rate_down_shift(ctrl); if (rc < 0) { /* already in RBR = 1.6G */ @@ -1887,7 +1926,7 @@ int msm_dp_ctrl_on_link(struct msm_dp_ctrl *msm_dp_ctrl) if (!msm_dp_catalog_link_is_connected(ctrl->catalog)) break; - msm_dp_ctrl_read_link_status(ctrl, link_status); + drm_dp_dpcd_read_link_status(ctrl->aux, link_status); if (!drm_dp_clock_recovery_ok(link_status, ctrl->link->link_params.num_lanes)) @@ -1901,7 +1940,7 @@ int msm_dp_ctrl_on_link(struct msm_dp_ctrl *msm_dp_ctrl) } /* stop link training before start re training */ - msm_dp_ctrl_clear_training_pattern(ctrl); + msm_dp_ctrl_clear_training_pattern(ctrl, DP_PHY_DPRX); } rc = msm_dp_ctrl_reinitialize_mainlink(ctrl); @@ -1925,7 +1964,7 @@ int msm_dp_ctrl_on_link(struct msm_dp_ctrl *msm_dp_ctrl) * link training failed * end txing train pattern here */ - msm_dp_ctrl_clear_training_pattern(ctrl); + msm_dp_ctrl_clear_training_pattern(ctrl, DP_PHY_DPRX); msm_dp_ctrl_deinitialize_mainlink(ctrl); rc = -ECONNRESET; @@ -1996,7 +2035,7 @@ int msm_dp_ctrl_on_stream(struct msm_dp_ctrl *msm_dp_ctrl, bool force_link_train msm_dp_ctrl_link_retrain(ctrl); /* stop txing train pattern to end link training */ - msm_dp_ctrl_clear_training_pattern(ctrl); + msm_dp_ctrl_clear_training_pattern(ctrl, DP_PHY_DPRX); /* * Set up transfer unit values and set controller state to send diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index 6d69598e85c5..a48e6db4f156 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -11,7 +11,9 @@ #include <linux/of_irq.h> #include <linux/phy/phy.h> #include <linux/delay.h> +#include <linux/string_choices.h> #include <drm/display/drm_dp_aux_bus.h> +#include <drm/display/drm_hdmi_audio_helper.h> #include <drm/drm_edid.h> #include "msm_drv.h" @@ -126,6 +128,11 @@ static const struct msm_dp_desc msm_dp_desc_sa8775p[] = { {} }; +static const struct msm_dp_desc msm_dp_desc_sdm845[] = { + { .io_start = 0x0ae90000, .id = MSM_DP_CONTROLLER_0 }, + {} +}; + static const struct msm_dp_desc msm_dp_desc_sc7180[] = { { .io_start = 0x0ae90000, .id = MSM_DP_CONTROLLER_0, .wide_bus_supported = true }, {} @@ -178,7 +185,7 @@ static const struct of_device_id msm_dp_dt_match[] = { { .compatible = "qcom,sc8180x-edp", .data = &msm_dp_desc_sc8180x }, { .compatible = "qcom,sc8280xp-dp", .data = &msm_dp_desc_sc8280xp }, { .compatible = "qcom,sc8280xp-edp", .data = &msm_dp_desc_sc8280xp }, - { .compatible = "qcom,sdm845-dp", .data = &msm_dp_desc_sc7180 }, + { .compatible = "qcom,sdm845-dp", .data = &msm_dp_desc_sdm845 }, { .compatible = "qcom,sm8350-dp", .data = &msm_dp_desc_sc7180 }, { .compatible = "qcom,sm8650-dp", .data = &msm_dp_desc_sm8650 }, { .compatible = "qcom,x1e80100-dp", .data = &msm_dp_desc_x1e80100 }, @@ -287,13 +294,6 @@ static int msm_dp_display_bind(struct device *dev, struct device *master, goto end; } - - rc = msm_dp_register_audio_driver(dev, dp->audio); - if (rc) { - DRM_ERROR("Audio registration Dp failed\n"); - goto end; - } - rc = msm_dp_hpd_event_thread_start(dp); if (rc) { DRM_ERROR("Event thread create failed\n"); @@ -315,7 +315,6 @@ static void msm_dp_display_unbind(struct device *dev, struct device *master, of_dp_aux_depopulate_bus(dp->aux); - msm_dp_unregister_audio_driver(dev, dp->audio); msm_dp_aux_unregister(dp->aux); dp->drm_dev = NULL; dp->aux->drm_dev = NULL; @@ -343,8 +342,7 @@ static int msm_dp_display_send_hpd_notification(struct msm_dp_display_private *d { if ((hpd && dp->msm_dp_display.link_ready) || (!hpd && !dp->msm_dp_display.link_ready)) { - drm_dbg_dp(dp->drm_dev, "HPD already %s\n", - (hpd ? "on" : "off")); + drm_dbg_dp(dp->drm_dev, "HPD already %s\n", str_on_off(hpd)); return 0; } @@ -367,11 +365,35 @@ static int msm_dp_display_send_hpd_notification(struct msm_dp_display_private *d return 0; } +static int msm_dp_display_lttpr_init(struct msm_dp_display_private *dp, u8 *dpcd) +{ + int rc, lttpr_count; + + if (drm_dp_read_lttpr_common_caps(dp->aux, dpcd, dp->link->lttpr_common_caps)) + return 0; + + lttpr_count = drm_dp_lttpr_count(dp->link->lttpr_common_caps); + rc = drm_dp_lttpr_init(dp->aux, lttpr_count); + if (rc) { + DRM_ERROR("failed to set LTTPRs transparency mode, rc=%d\n", rc); + return 0; + } + + return lttpr_count; +} + static int msm_dp_display_process_hpd_high(struct msm_dp_display_private *dp) { struct drm_connector *connector = dp->msm_dp_display.connector; const struct drm_display_info *info = &connector->display_info; int rc = 0; + u8 dpcd[DP_RECEIVER_CAP_SIZE]; + + rc = drm_dp_read_dpcd_caps(dp->aux, dpcd); + if (rc) + goto end; + + dp->link->lttpr_count = msm_dp_display_lttpr_init(dp, dpcd); rc = msm_dp_panel_read_sink_caps(dp->panel, connector); if (rc) @@ -611,9 +633,9 @@ static void msm_dp_display_handle_plugged_change(struct msm_dp *msm_dp_display, struct msm_dp_display_private, msm_dp_display); /* notify audio subsystem only if sink supports audio */ - if (msm_dp_display->plugged_cb && msm_dp_display->codec_dev && - dp->audio_supported) - msm_dp_display->plugged_cb(msm_dp_display->codec_dev, plugged); + if (dp->audio_supported) + drm_connector_hdmi_audio_plugged_notify(msm_dp_display->connector, + plugged); } static int msm_dp_hpd_unplug_handle(struct msm_dp_display_private *dp, u32 data) @@ -722,9 +744,6 @@ static int msm_dp_init_sub_modules(struct msm_dp_display_private *dp) { int rc = 0; struct device *dev = &dp->msm_dp_display.pdev->dev; - struct msm_dp_panel_in panel_in = { - .dev = dev, - }; struct phy *phy; phy = devm_phy_get(dev, "dp"); @@ -765,11 +784,7 @@ static int msm_dp_init_sub_modules(struct msm_dp_display_private *dp) goto error_link; } - panel_in.aux = dp->aux; - panel_in.catalog = dp->catalog; - panel_in.link = dp->link; - - dp->panel = msm_dp_panel_get(&panel_in); + dp->panel = msm_dp_panel_get(dev, dp->aux, dp->link, dp->catalog); if (IS_ERR(dp->panel)) { rc = PTR_ERR(dp->panel); DRM_ERROR("failed to initialize panel, rc = %d\n", rc); @@ -787,7 +802,7 @@ static int msm_dp_init_sub_modules(struct msm_dp_display_private *dp) goto error_ctrl; } - dp->audio = msm_dp_audio_get(dp->msm_dp_display.pdev, dp->panel, dp->catalog); + dp->audio = msm_dp_audio_get(dp->msm_dp_display.pdev, dp->catalog); if (IS_ERR(dp->audio)) { rc = PTR_ERR(dp->audio); pr_err("failed to initialize audio, rc = %d\n", rc); @@ -899,19 +914,6 @@ static int msm_dp_display_disable(struct msm_dp_display_private *dp) return 0; } -int msm_dp_display_set_plugged_cb(struct msm_dp *msm_dp_display, - hdmi_codec_plugged_cb fn, struct device *codec_dev) -{ - bool plugged; - - msm_dp_display->plugged_cb = fn; - msm_dp_display->codec_dev = codec_dev; - plugged = msm_dp_display->link_ready; - msm_dp_display_handle_plugged_change(msm_dp_display, plugged); - - return 0; -} - /** * msm_dp_bridge_mode_valid - callback to determine if specified mode is valid * @bridge: Pointer to drm bridge structure @@ -1499,13 +1501,13 @@ int msm_dp_modeset_init(struct msm_dp *msm_dp_display, struct drm_device *dev, } void msm_dp_bridge_atomic_enable(struct drm_bridge *drm_bridge, - struct drm_bridge_state *old_bridge_state) + struct drm_atomic_state *state) { struct msm_dp_bridge *msm_dp_bridge = to_dp_bridge(drm_bridge); struct msm_dp *dp = msm_dp_bridge->msm_dp_display; int rc = 0; struct msm_dp_display_private *msm_dp_display; - u32 state; + u32 hpd_state; bool force_link_train = false; msm_dp_display = container_of(dp, struct msm_dp_display_private, msm_dp_display); @@ -1524,8 +1526,8 @@ void msm_dp_bridge_atomic_enable(struct drm_bridge *drm_bridge, return; } - state = msm_dp_display->hpd_state; - if (state != ST_DISPLAY_OFF && state != ST_MAINLINK_READY) { + hpd_state = msm_dp_display->hpd_state; + if (hpd_state != ST_DISPLAY_OFF && hpd_state != ST_MAINLINK_READY) { mutex_unlock(&msm_dp_display->event_mutex); return; } @@ -1537,9 +1539,9 @@ void msm_dp_bridge_atomic_enable(struct drm_bridge *drm_bridge, return; } - state = msm_dp_display->hpd_state; + hpd_state = msm_dp_display->hpd_state; - if (state == ST_DISPLAY_OFF) { + if (hpd_state == ST_DISPLAY_OFF) { msm_dp_display_host_phy_init(msm_dp_display); force_link_train = true; } @@ -1560,7 +1562,7 @@ void msm_dp_bridge_atomic_enable(struct drm_bridge *drm_bridge, } void msm_dp_bridge_atomic_disable(struct drm_bridge *drm_bridge, - struct drm_bridge_state *old_bridge_state) + struct drm_atomic_state *state) { struct msm_dp_bridge *msm_dp_bridge = to_dp_bridge(drm_bridge); struct msm_dp *dp = msm_dp_bridge->msm_dp_display; @@ -1572,11 +1574,11 @@ void msm_dp_bridge_atomic_disable(struct drm_bridge *drm_bridge, } void msm_dp_bridge_atomic_post_disable(struct drm_bridge *drm_bridge, - struct drm_bridge_state *old_bridge_state) + struct drm_atomic_state *state) { struct msm_dp_bridge *msm_dp_bridge = to_dp_bridge(drm_bridge); struct msm_dp *dp = msm_dp_bridge->msm_dp_display; - u32 state; + u32 hpd_state; struct msm_dp_display_private *msm_dp_display; msm_dp_display = container_of(dp, struct msm_dp_display_private, msm_dp_display); @@ -1586,15 +1588,15 @@ void msm_dp_bridge_atomic_post_disable(struct drm_bridge *drm_bridge, mutex_lock(&msm_dp_display->event_mutex); - state = msm_dp_display->hpd_state; - if (state != ST_DISCONNECT_PENDING && state != ST_CONNECTED) + hpd_state = msm_dp_display->hpd_state; + if (hpd_state != ST_DISCONNECT_PENDING && hpd_state != ST_CONNECTED) drm_dbg_dp(dp->drm_dev, "type=%d wrong hpd_state=%d\n", - dp->connector_type, state); + dp->connector_type, hpd_state); msm_dp_display_disable(msm_dp_display); - state = msm_dp_display->hpd_state; - if (state == ST_DISCONNECT_PENDING) { + hpd_state = msm_dp_display->hpd_state; + if (hpd_state == ST_DISCONNECT_PENDING) { /* completed disconnection */ msm_dp_display->hpd_state = ST_DISCONNECTED; } else { diff --git a/drivers/gpu/drm/msm/dp/dp_display.h b/drivers/gpu/drm/msm/dp/dp_display.h index ecbc2d92f546..cc6e2cab36e9 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.h +++ b/drivers/gpu/drm/msm/dp/dp_display.h @@ -7,7 +7,6 @@ #define _DP_DISPLAY_H_ #include "dp_panel.h" -#include <sound/hdmi-codec.h> #include "disp/msm_disp_snapshot.h" #define DP_MAX_PIXEL_CLK_KHZ 675000 @@ -15,7 +14,6 @@ struct msm_dp { struct drm_device *drm_dev; struct platform_device *pdev; - struct device *codec_dev; struct drm_connector *connector; struct drm_bridge *next_bridge; bool link_ready; @@ -25,14 +23,10 @@ struct msm_dp { bool is_edp; bool internal_hpd; - hdmi_codec_plugged_cb plugged_cb; - struct msm_dp_audio *msm_dp_audio; bool psr_supported; }; -int msm_dp_display_set_plugged_cb(struct msm_dp *msm_dp_display, - hdmi_codec_plugged_cb fn, struct device *codec_dev); int msm_dp_display_get_modes(struct msm_dp *msm_dp_display); bool msm_dp_display_check_video_test(struct msm_dp *msm_dp_display); int msm_dp_display_get_test_bpp(struct msm_dp *msm_dp_display); diff --git a/drivers/gpu/drm/msm/dp/dp_drm.c b/drivers/gpu/drm/msm/dp/dp_drm.c index 16b7913d1eef..f222d7ccaa88 100644 --- a/drivers/gpu/drm/msm/dp/dp_drm.c +++ b/drivers/gpu/drm/msm/dp/dp_drm.c @@ -3,6 +3,7 @@ * Copyright (c) 2017-2020, The Linux Foundation. All rights reserved. */ +#include <linux/string_choices.h> #include <drm/drm_atomic_helper.h> #include <drm/drm_atomic.h> #include <drm/drm_bridge.h> @@ -11,6 +12,7 @@ #include "msm_drv.h" #include "msm_kms.h" +#include "dp_audio.h" #include "dp_drm.h" /** @@ -25,7 +27,7 @@ static enum drm_connector_status msm_dp_bridge_detect(struct drm_bridge *bridge) dp = to_dp_bridge(bridge)->msm_dp_display; drm_dbg_dp(dp->drm_dev, "link_ready = %s\n", - (dp->link_ready) ? "true" : "false"); + str_true_false(dp->link_ready)); return (dp->link_ready) ? connector_status_connected : connector_status_disconnected; @@ -41,7 +43,7 @@ static int msm_dp_bridge_atomic_check(struct drm_bridge *bridge, dp = to_dp_bridge(bridge)->msm_dp_display; drm_dbg_dp(dp->drm_dev, "link_ready = %s\n", - (dp->link_ready) ? "true" : "false"); + str_true_false(dp->link_ready)); /* * There is no protection in the DRM framework to check if the display @@ -113,6 +115,9 @@ static const struct drm_bridge_funcs msm_dp_bridge_ops = { .hpd_disable = msm_dp_bridge_hpd_disable, .hpd_notify = msm_dp_bridge_hpd_notify, .debugfs_init = msm_dp_bridge_debugfs_init, + + .dp_audio_prepare = msm_dp_audio_prepare, + .dp_audio_shutdown = msm_dp_audio_shutdown, }; static int msm_edp_bridge_atomic_check(struct drm_bridge *drm_bridge, @@ -137,9 +142,8 @@ static int msm_edp_bridge_atomic_check(struct drm_bridge *drm_bridge, } static void msm_edp_bridge_atomic_enable(struct drm_bridge *drm_bridge, - struct drm_bridge_state *old_bridge_state) + struct drm_atomic_state *state) { - struct drm_atomic_state *atomic_state = old_bridge_state->base.state; struct drm_crtc *crtc; struct drm_crtc_state *old_crtc_state; struct msm_dp_bridge *msm_dp_bridge = to_dp_bridge(drm_bridge); @@ -151,25 +155,24 @@ static void msm_edp_bridge_atomic_enable(struct drm_bridge *drm_bridge, * If the panel is in psr, just exit psr state and skip the full * bridge enable sequence. */ - crtc = drm_atomic_get_new_crtc_for_encoder(atomic_state, + crtc = drm_atomic_get_new_crtc_for_encoder(state, drm_bridge->encoder); if (!crtc) return; - old_crtc_state = drm_atomic_get_old_crtc_state(atomic_state, crtc); + old_crtc_state = drm_atomic_get_old_crtc_state(state, crtc); if (old_crtc_state && old_crtc_state->self_refresh_active) { msm_dp_display_set_psr(dp, false); return; } - msm_dp_bridge_atomic_enable(drm_bridge, old_bridge_state); + msm_dp_bridge_atomic_enable(drm_bridge, state); } static void msm_edp_bridge_atomic_disable(struct drm_bridge *drm_bridge, - struct drm_bridge_state *old_bridge_state) + struct drm_atomic_state *atomic_state) { - struct drm_atomic_state *atomic_state = old_bridge_state->base.state; struct drm_crtc *crtc; struct drm_crtc_state *new_crtc_state = NULL, *old_crtc_state = NULL; struct msm_dp_bridge *msm_dp_bridge = to_dp_bridge(drm_bridge); @@ -208,13 +211,12 @@ static void msm_edp_bridge_atomic_disable(struct drm_bridge *drm_bridge, } out: - msm_dp_bridge_atomic_disable(drm_bridge, old_bridge_state); + msm_dp_bridge_atomic_disable(drm_bridge, atomic_state); } static void msm_edp_bridge_atomic_post_disable(struct drm_bridge *drm_bridge, - struct drm_bridge_state *old_bridge_state) + struct drm_atomic_state *atomic_state) { - struct drm_atomic_state *atomic_state = old_bridge_state->base.state; struct drm_crtc *crtc; struct drm_crtc_state *new_crtc_state = NULL; @@ -233,7 +235,7 @@ static void msm_edp_bridge_atomic_post_disable(struct drm_bridge *drm_bridge, if (new_crtc_state->self_refresh_active) return; - msm_dp_bridge_atomic_post_disable(drm_bridge, old_bridge_state); + msm_dp_bridge_atomic_post_disable(drm_bridge, atomic_state); } /** @@ -298,14 +300,15 @@ int msm_dp_bridge_init(struct msm_dp *msm_dp_display, struct drm_device *dev, struct msm_dp_bridge *msm_dp_bridge; struct drm_bridge *bridge; - msm_dp_bridge = devm_kzalloc(dev->dev, sizeof(*msm_dp_bridge), GFP_KERNEL); - if (!msm_dp_bridge) - return -ENOMEM; + msm_dp_bridge = devm_drm_bridge_alloc(dev->dev, struct msm_dp_bridge, bridge, + msm_dp_display->is_edp ? &msm_edp_bridge_ops : + &msm_dp_bridge_ops); + if (IS_ERR(msm_dp_bridge)) + return PTR_ERR(msm_dp_bridge); msm_dp_bridge->msm_dp_display = msm_dp_display; bridge = &msm_dp_bridge->bridge; - bridge->funcs = msm_dp_display->is_edp ? &msm_edp_bridge_ops : &msm_dp_bridge_ops; bridge->type = msm_dp_display->connector_type; bridge->ycbcr_420_allowed = yuv_supported; @@ -322,9 +325,13 @@ int msm_dp_bridge_init(struct msm_dp *msm_dp_display, struct drm_device *dev, */ if (!msm_dp_display->is_edp) { bridge->ops = + DRM_BRIDGE_OP_DP_AUDIO | DRM_BRIDGE_OP_DETECT | DRM_BRIDGE_OP_HPD | DRM_BRIDGE_OP_MODES; + bridge->hdmi_audio_dev = &msm_dp_display->pdev->dev; + bridge->hdmi_audio_max_i2s_playback_channels = 8; + bridge->hdmi_audio_dai_port = -1; } rc = devm_drm_bridge_add(dev->dev, bridge); diff --git a/drivers/gpu/drm/msm/dp/dp_drm.h b/drivers/gpu/drm/msm/dp/dp_drm.h index 8eae2f74839f..d8c9b905f8bf 100644 --- a/drivers/gpu/drm/msm/dp/dp_drm.h +++ b/drivers/gpu/drm/msm/dp/dp_drm.h @@ -26,11 +26,11 @@ int msm_dp_bridge_init(struct msm_dp *msm_dp_display, struct drm_device *dev, bool yuv_supported); void msm_dp_bridge_atomic_enable(struct drm_bridge *drm_bridge, - struct drm_bridge_state *old_bridge_state); + struct drm_atomic_state *state); void msm_dp_bridge_atomic_disable(struct drm_bridge *drm_bridge, - struct drm_bridge_state *old_bridge_state); + struct drm_atomic_state *state); void msm_dp_bridge_atomic_post_disable(struct drm_bridge *drm_bridge, - struct drm_bridge_state *old_bridge_state); + struct drm_atomic_state *state); enum drm_mode_status msm_dp_bridge_mode_valid(struct drm_bridge *bridge, const struct drm_display_info *info, const struct drm_display_mode *mode); diff --git a/drivers/gpu/drm/msm/dp/dp_link.c b/drivers/gpu/drm/msm/dp/dp_link.c index 1a1fbb2d7d4f..92a9077959b3 100644 --- a/drivers/gpu/drm/msm/dp/dp_link.c +++ b/drivers/gpu/drm/msm/dp/dp_link.c @@ -714,21 +714,21 @@ end: static int msm_dp_link_parse_sink_status_field(struct msm_dp_link_private *link) { - int len; + int ret; link->prev_sink_count = link->msm_dp_link.sink_count; - len = drm_dp_read_sink_count(link->aux); - if (len < 0) { + ret = drm_dp_read_sink_count(link->aux); + if (ret < 0) { DRM_ERROR("DP parse sink count failed\n"); - return len; + return ret; } - link->msm_dp_link.sink_count = len; + link->msm_dp_link.sink_count = ret; - len = drm_dp_dpcd_read_link_status(link->aux, - link->link_status); - if (len < DP_LINK_STATUS_SIZE) { + ret = drm_dp_dpcd_read_link_status(link->aux, + link->link_status); + if (ret < 0) { DRM_ERROR("DP link status read failed\n"); - return len; + return ret; } return msm_dp_link_parse_request(link); diff --git a/drivers/gpu/drm/msm/dp/dp_link.h b/drivers/gpu/drm/msm/dp/dp_link.h index 8db5d5698a97..ba47c6d19fbf 100644 --- a/drivers/gpu/drm/msm/dp/dp_link.h +++ b/drivers/gpu/drm/msm/dp/dp_link.h @@ -7,6 +7,7 @@ #define _DP_LINK_H_ #include "dp_aux.h" +#include <drm/display/drm_dp_helper.h> #define DS_PORT_STATUS_CHANGED 0x200 #define DP_TEST_BIT_DEPTH_UNKNOWN 0xFFFFFFFF @@ -60,6 +61,9 @@ struct msm_dp_link_phy_params { }; struct msm_dp_link { + u8 lttpr_common_caps[DP_LTTPR_COMMON_CAP_SIZE]; + int lttpr_count; + u32 sink_request; u32 test_response; diff --git a/drivers/gpu/drm/msm/dp/dp_panel.c b/drivers/gpu/drm/msm/dp/dp_panel.c index 5d7eaa31bf31..4e8ab75c771b 100644 --- a/drivers/gpu/drm/msm/dp/dp_panel.c +++ b/drivers/gpu/drm/msm/dp/dp_panel.c @@ -47,7 +47,7 @@ static void msm_dp_panel_read_psr_cap(struct msm_dp_panel_private *panel) static int msm_dp_panel_read_dpcd(struct msm_dp_panel *msm_dp_panel) { - int rc; + int rc, max_lttpr_lanes, max_lttpr_rate; struct msm_dp_panel_private *panel; struct msm_dp_link_info *link_info; u8 *dpcd, major, minor; @@ -75,6 +75,16 @@ static int msm_dp_panel_read_dpcd(struct msm_dp_panel *msm_dp_panel) if (link_info->rate > msm_dp_panel->max_dp_link_rate) link_info->rate = msm_dp_panel->max_dp_link_rate; + /* Limit data lanes from LTTPR capabilities, if any */ + max_lttpr_lanes = drm_dp_lttpr_max_lane_count(panel->link->lttpr_common_caps); + if (max_lttpr_lanes && max_lttpr_lanes < link_info->num_lanes) + link_info->num_lanes = max_lttpr_lanes; + + /* Limit link rate from LTTPR capabilities, if any */ + max_lttpr_rate = drm_dp_lttpr_max_link_rate(panel->link->lttpr_common_caps); + if (max_lttpr_rate && max_lttpr_rate < link_info->rate) + link_info->rate = max_lttpr_rate; + drm_dbg_dp(panel->drm_dev, "version: %d.%d\n", major, minor); drm_dbg_dp(panel->drm_dev, "link_rate=%d\n", link_info->rate); drm_dbg_dp(panel->drm_dev, "lane_count=%d\n", link_info->num_lanes); @@ -317,17 +327,6 @@ static int msm_dp_panel_setup_vsc_sdp_yuv_420(struct msm_dp_panel *msm_dp_panel) return 0; } -void msm_dp_panel_dump_regs(struct msm_dp_panel *msm_dp_panel) -{ - struct msm_dp_catalog *catalog; - struct msm_dp_panel_private *panel; - - panel = container_of(msm_dp_panel, struct msm_dp_panel_private, msm_dp_panel); - catalog = panel->catalog; - - msm_dp_catalog_dump_regs(catalog); -} - int msm_dp_panel_timing_cfg(struct msm_dp_panel *msm_dp_panel) { u32 data, total_ver, total_hor; @@ -486,25 +485,26 @@ static int msm_dp_panel_parse_dt(struct msm_dp_panel *msm_dp_panel) return 0; } -struct msm_dp_panel *msm_dp_panel_get(struct msm_dp_panel_in *in) +struct msm_dp_panel *msm_dp_panel_get(struct device *dev, struct drm_dp_aux *aux, + struct msm_dp_link *link, struct msm_dp_catalog *catalog) { struct msm_dp_panel_private *panel; struct msm_dp_panel *msm_dp_panel; int ret; - if (!in->dev || !in->catalog || !in->aux || !in->link) { + if (!dev || !catalog || !aux || !link) { DRM_ERROR("invalid input\n"); return ERR_PTR(-EINVAL); } - panel = devm_kzalloc(in->dev, sizeof(*panel), GFP_KERNEL); + panel = devm_kzalloc(dev, sizeof(*panel), GFP_KERNEL); if (!panel) return ERR_PTR(-ENOMEM); - panel->dev = in->dev; - panel->aux = in->aux; - panel->catalog = in->catalog; - panel->link = in->link; + panel->dev = dev; + panel->aux = aux; + panel->catalog = catalog; + panel->link = link; msm_dp_panel = &panel->msm_dp_panel; msm_dp_panel->max_bw_code = DP_LINK_BW_8_1; diff --git a/drivers/gpu/drm/msm/dp/dp_panel.h b/drivers/gpu/drm/msm/dp/dp_panel.h index 0e944db3adf2..4906f4f09f24 100644 --- a/drivers/gpu/drm/msm/dp/dp_panel.h +++ b/drivers/gpu/drm/msm/dp/dp_panel.h @@ -21,13 +21,6 @@ struct msm_dp_display_mode { bool out_fmt_is_yuv_420; }; -struct msm_dp_panel_in { - struct device *dev; - struct drm_dp_aux *aux; - struct msm_dp_link *link; - struct msm_dp_catalog *catalog; -}; - struct msm_dp_panel_psr { u8 version; u8 capabilities; @@ -55,7 +48,6 @@ struct msm_dp_panel { int msm_dp_panel_init_panel_info(struct msm_dp_panel *msm_dp_panel); int msm_dp_panel_deinit(struct msm_dp_panel *msm_dp_panel); int msm_dp_panel_timing_cfg(struct msm_dp_panel *msm_dp_panel); -void msm_dp_panel_dump_regs(struct msm_dp_panel *msm_dp_panel); int msm_dp_panel_read_sink_caps(struct msm_dp_panel *msm_dp_panel, struct drm_connector *connector); u32 msm_dp_panel_get_mode_bpp(struct msm_dp_panel *msm_dp_panel, u32 mode_max_bpp, @@ -92,6 +84,7 @@ static inline bool is_lane_count_valid(u32 lane_count) lane_count == 4); } -struct msm_dp_panel *msm_dp_panel_get(struct msm_dp_panel_in *in); +struct msm_dp_panel *msm_dp_panel_get(struct device *dev, struct drm_dp_aux *aux, + struct msm_dp_link *link, struct msm_dp_catalog *catalog); void msm_dp_panel_put(struct msm_dp_panel *msm_dp_panel); #endif /* _DP_PANEL_H_ */ diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.c b/drivers/gpu/drm/msm/dsi/dsi_cfg.c index 10ba7d153d1c..7675558ae2e5 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_cfg.c +++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.c @@ -221,6 +221,22 @@ static const struct msm_dsi_config sc7280_dsi_cfg = { }, }; +static const struct regulator_bulk_data sa8775p_dsi_regulators[] = { + { .supply = "vdda", .init_load_uA = 8300 }, /* 1.2 V */ + { .supply = "refgen" }, +}; + +static const struct msm_dsi_config sa8775p_dsi_cfg = { + .io_offset = DSI_6G_REG_SHIFT, + .regulator_data = sa8775p_dsi_regulators, + .num_regulators = ARRAY_SIZE(sa8775p_dsi_regulators), + .bus_clk_names = dsi_v2_4_clk_names, + .num_bus_clks = ARRAY_SIZE(dsi_v2_4_clk_names), + .io_start = { + { 0xae94000, 0xae96000 }, + }, +}; + static const struct msm_dsi_host_cfg_ops msm_dsi_v2_host_ops = { .link_clk_set_rate = dsi_link_clk_set_rate_v2, .link_clk_enable = dsi_link_clk_enable_v2, @@ -286,12 +302,16 @@ static const struct msm_dsi_cfg_handler dsi_cfg_handlers[] = { &sdm845_dsi_cfg, &msm_dsi_6g_v2_host_ops}, {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_3_0, &sdm845_dsi_cfg, &msm_dsi_6g_v2_host_ops}, + {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_3_1, + &sdm845_dsi_cfg, &msm_dsi_6g_v2_host_ops}, {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_4_0, &sdm845_dsi_cfg, &msm_dsi_6g_v2_host_ops}, {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_4_1, &sdm845_dsi_cfg, &msm_dsi_6g_v2_host_ops}, {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_5_0, &sc7280_dsi_cfg, &msm_dsi_6g_v2_host_ops}, + {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_5_1, + &sa8775p_dsi_cfg, &msm_dsi_6g_v2_host_ops}, {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_6_0, &sdm845_dsi_cfg, &msm_dsi_6g_v2_host_ops}, {MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_7_0, diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.h b/drivers/gpu/drm/msm/dsi/dsi_cfg.h index 4c9b4b37681b..65b0705fac0e 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_cfg.h +++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.h @@ -23,9 +23,11 @@ #define MSM_DSI_6G_VER_MINOR_V2_2_0 0x20000000 #define MSM_DSI_6G_VER_MINOR_V2_2_1 0x20020001 #define MSM_DSI_6G_VER_MINOR_V2_3_0 0x20030000 +#define MSM_DSI_6G_VER_MINOR_V2_3_1 0x20030001 #define MSM_DSI_6G_VER_MINOR_V2_4_0 0x20040000 #define MSM_DSI_6G_VER_MINOR_V2_4_1 0x20040001 #define MSM_DSI_6G_VER_MINOR_V2_5_0 0x20050000 +#define MSM_DSI_6G_VER_MINOR_V2_5_1 0x20050001 #define MSM_DSI_6G_VER_MINOR_V2_6_0 0x20060000 #define MSM_DSI_6G_VER_MINOR_V2_7_0 0x20070000 #define MSM_DSI_6G_VER_MINOR_V2_8_0 0x20080000 diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index a98d24b7cb00..4d75529c0e85 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -179,18 +179,18 @@ struct msm_dsi_host { int irq; }; - static inline u32 dsi_read(struct msm_dsi_host *msm_host, u32 reg) { return readl(msm_host->ctrl_base + reg); } + static inline void dsi_write(struct msm_dsi_host *msm_host, u32 reg, u32 data) { writel(data, msm_host->ctrl_base + reg); } -static const struct msm_dsi_cfg_handler *dsi_get_config( - struct msm_dsi_host *msm_host) +static const struct msm_dsi_cfg_handler * +dsi_get_config(struct msm_dsi_host *msm_host) { const struct msm_dsi_cfg_handler *cfg_hnd = NULL; struct device *dev = &msm_host->pdev->dev; @@ -200,7 +200,8 @@ static const struct msm_dsi_cfg_handler *dsi_get_config( ahb_clk = msm_clk_get(msm_host->pdev, "iface"); if (IS_ERR(ahb_clk)) { - pr_err("%s: cannot get interface clock\n", __func__); + dev_err_probe(dev, PTR_ERR(ahb_clk), "%s: cannot get interface clock\n", + __func__); goto exit; } @@ -208,13 +209,13 @@ static const struct msm_dsi_cfg_handler *dsi_get_config( ret = clk_prepare_enable(ahb_clk); if (ret) { - pr_err("%s: unable to enable ahb_clk\n", __func__); + dev_err_probe(dev, ret, "%s: unable to enable ahb_clk\n", __func__); goto runtime_put; } ret = dsi_get_version(msm_host->ctrl_base, &major, &minor); if (ret) { - pr_err("%s: Invalid version\n", __func__); + dev_err_probe(dev, ret, "%s: Invalid version\n", __func__); goto disable_clks; } @@ -281,42 +282,31 @@ static int dsi_clk_init(struct msm_dsi_host *msm_host) msm_host->num_bus_clks = cfg->num_bus_clks; ret = devm_clk_bulk_get(&pdev->dev, msm_host->num_bus_clks, msm_host->bus_clks); - if (ret < 0) { - dev_err(&pdev->dev, "Unable to get clocks, ret = %d\n", ret); - goto exit; - } + if (ret < 0) + return dev_err_probe(&pdev->dev, ret, "Unable to get clocks\n"); /* get link and source clocks */ msm_host->byte_clk = msm_clk_get(pdev, "byte"); - if (IS_ERR(msm_host->byte_clk)) { - ret = PTR_ERR(msm_host->byte_clk); - pr_err("%s: can't find dsi_byte clock. ret=%d\n", - __func__, ret); - msm_host->byte_clk = NULL; - goto exit; - } + if (IS_ERR(msm_host->byte_clk)) + return dev_err_probe(&pdev->dev, PTR_ERR(msm_host->byte_clk), + "%s: can't find dsi_byte clock\n", + __func__); msm_host->pixel_clk = msm_clk_get(pdev, "pixel"); - if (IS_ERR(msm_host->pixel_clk)) { - ret = PTR_ERR(msm_host->pixel_clk); - pr_err("%s: can't find dsi_pixel clock. ret=%d\n", - __func__, ret); - msm_host->pixel_clk = NULL; - goto exit; - } + if (IS_ERR(msm_host->pixel_clk)) + return dev_err_probe(&pdev->dev, PTR_ERR(msm_host->pixel_clk), + "%s: can't find dsi_pixel clock\n", + __func__); msm_host->esc_clk = msm_clk_get(pdev, "core"); - if (IS_ERR(msm_host->esc_clk)) { - ret = PTR_ERR(msm_host->esc_clk); - pr_err("%s: can't find dsi_esc clock. ret=%d\n", - __func__, ret); - msm_host->esc_clk = NULL; - goto exit; - } + if (IS_ERR(msm_host->esc_clk)) + return dev_err_probe(&pdev->dev, PTR_ERR(msm_host->esc_clk), + "%s: can't find dsi_esc clock\n", + __func__); if (cfg_hnd->ops->clk_init_ver) ret = cfg_hnd->ops->clk_init_ver(msm_host); -exit: + return ret; } @@ -380,7 +370,6 @@ int dsi_link_clk_set_rate_6g(struct msm_dsi_host *msm_host) return 0; } - int dsi_link_clk_enable_6g(struct msm_dsi_host *msm_host) { int ret; @@ -598,7 +587,6 @@ static void dsi_calc_pclk(struct msm_dsi_host *msm_host, bool is_bonded_dsi) DBG("pclk=%lu, bclk=%lu", msm_host->pixel_clk_rate, msm_host->byte_clk_rate); - } int dsi_calc_clk_rate_6g(struct msm_dsi_host *msm_host, bool is_bonded_dsi) @@ -687,8 +675,8 @@ static inline enum dsi_traffic_mode dsi_get_traffic_mode(const u32 mode_flags) return NON_BURST_SYNCH_EVENT; } -static inline enum dsi_vid_dst_format dsi_get_vid_fmt( - const enum mipi_dsi_pixel_format mipi_fmt) +static inline enum dsi_vid_dst_format +dsi_get_vid_fmt(const enum mipi_dsi_pixel_format mipi_fmt) { switch (mipi_fmt) { case MIPI_DSI_FMT_RGB888: return VID_DST_FORMAT_RGB888; @@ -699,8 +687,8 @@ static inline enum dsi_vid_dst_format dsi_get_vid_fmt( } } -static inline enum dsi_cmd_dst_format dsi_get_cmd_fmt( - const enum mipi_dsi_pixel_format mipi_fmt) +static inline enum dsi_cmd_dst_format +dsi_get_cmd_fmt(const enum mipi_dsi_pixel_format mipi_fmt) { switch (mipi_fmt) { case MIPI_DSI_FMT_RGB888: return CMD_DST_FORMAT_RGB888; @@ -846,7 +834,7 @@ static void dsi_ctrl_enable(struct msm_dsi_host *msm_host, dsi_write(msm_host, REG_DSI_CPHY_MODE_CTRL, BIT(0)); } -static void dsi_update_dsc_timing(struct msm_dsi_host *msm_host, bool is_cmd_mode, u32 hdisplay) +static void dsi_update_dsc_timing(struct msm_dsi_host *msm_host, bool is_cmd_mode) { struct drm_dsc_config *dsc = msm_host->dsc; u32 reg, reg_ctrl, reg_ctrl2; @@ -858,7 +846,7 @@ static void dsi_update_dsc_timing(struct msm_dsi_host *msm_host, bool is_cmd_mod /* first calculate dsc parameters and then program * compress mode registers */ - slice_per_intf = msm_dsc_get_slices_per_intf(dsc, hdisplay); + slice_per_intf = dsc->slice_count; total_bytes_per_intf = dsc->slice_chunk_size * slice_per_intf; bytes_per_pkt = dsc->slice_chunk_size; /* * slice_per_pkt; */ @@ -991,7 +979,7 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_bonded_dsi) if (msm_host->mode_flags & MIPI_DSI_MODE_VIDEO) { if (msm_host->dsc) - dsi_update_dsc_timing(msm_host, false, mode->hdisplay); + dsi_update_dsc_timing(msm_host, false); dsi_write(msm_host, REG_DSI_ACTIVE_H, DSI_ACTIVE_H_START(ha_start) | @@ -1012,7 +1000,7 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_bonded_dsi) DSI_ACTIVE_VSYNC_VPOS_END(vs_end)); } else { /* command mode */ if (msm_host->dsc) - dsi_update_dsc_timing(msm_host, true, mode->hdisplay); + dsi_update_dsc_timing(msm_host, true); /* image data and 1 byte write_memory_start cmd */ if (!msm_host->dsc) @@ -1292,14 +1280,15 @@ static int dsi_cmd_dma_add(struct msm_dsi_host *msm_host, static int dsi_short_read1_resp(u8 *buf, const struct mipi_dsi_msg *msg) { u8 *data = msg->rx_buf; + if (data && (msg->rx_len >= 1)) { *data = buf[1]; /* strip out dcs type */ return 1; - } else { - pr_err("%s: read data does not match with rx_buf len %zu\n", - __func__, msg->rx_len); - return -EINVAL; } + + pr_err("%s: read data does not match with rx_buf len %zu\n", + __func__, msg->rx_len); + return -EINVAL; } /* @@ -1308,15 +1297,16 @@ static int dsi_short_read1_resp(u8 *buf, const struct mipi_dsi_msg *msg) static int dsi_short_read2_resp(u8 *buf, const struct mipi_dsi_msg *msg) { u8 *data = msg->rx_buf; + if (data && (msg->rx_len >= 2)) { data[0] = buf[1]; /* strip out dcs type */ data[1] = buf[2]; return 2; - } else { - pr_err("%s: read data does not match with rx_buf len %zu\n", - __func__, msg->rx_len); - return -EINVAL; } + + pr_err("%s: read data does not match with rx_buf len %zu\n", + __func__, msg->rx_len); + return -EINVAL; } static int dsi_long_read_resp(u8 *buf, const struct mipi_dsi_msg *msg) @@ -1376,8 +1366,9 @@ static int dsi_cmd_dma_tx(struct msm_dsi_host *msm_host, int len) ret = -ETIMEDOUT; else ret = len; - } else + } else { ret = len; + } return ret; } @@ -1445,11 +1436,12 @@ static int dsi_cmds2buf_tx(struct msm_dsi_host *msm_host, return len; } - /* for video mode, do not send cmds more than - * one pixel line, since it only transmit it - * during BLLP. - */ - /* TODO: if the command is sent in LP mode, the bit rate is only + /* + * for video mode, do not send cmds more than + * one pixel line, since it only transmit it + * during BLLP. + * + * TODO: if the command is sent in LP mode, the bit rate is only * half of esc clk rate. In this case, if the video is already * actively streaming, we need to check more carefully if the * command can be fit into one BLLP. @@ -1767,8 +1759,20 @@ static int dsi_populate_dsc_params(struct msm_dsi_host *msm_host, struct drm_dsc return -EINVAL; } - if (dsc->bits_per_component != 8) { - DRM_DEV_ERROR(&msm_host->pdev->dev, "DSI does not support bits_per_component != 8 yet\n"); + switch (dsc->bits_per_component) { + case 8: + case 10: + case 12: + /* + * Only 8, 10, and 12 bpc are supported for DSC 1.1 block. + * If additional bpc values need to be supported, update + * this quard with the appropriate DSC version verification. + */ + break; + default: + DRM_DEV_ERROR(&msm_host->pdev->dev, + "Unsupported bits_per_component value: %d\n", + dsc->bits_per_component); return -EOPNOTSUPP; } @@ -1779,7 +1783,7 @@ static int dsi_populate_dsc_params(struct msm_dsi_host *msm_host, struct drm_dsc drm_dsc_set_const_params(dsc); drm_dsc_set_rc_buf_thresh(dsc); - /* handle only bpp = bpc = 8, pre-SCR panels */ + /* DPU supports only pre-SCR panels */ ret = drm_dsc_setup_rc_params(dsc, DRM_DSC_1_1_PRE_SCR); if (ret) { DRM_DEV_ERROR(&msm_host->pdev->dev, "could not find DSC RC parameters\n"); @@ -1827,11 +1831,18 @@ static int dsi_host_parse_dt(struct msm_dsi_host *msm_host) __func__, ret); goto err; } - if (!ret) + if (!ret) { msm_dsi->te_source = devm_kstrdup(dev, te_source, GFP_KERNEL); + if (!msm_dsi->te_source) { + DRM_DEV_ERROR(dev, "%s: failed to allocate te_source\n", + __func__); + ret = -ENOMEM; + goto err; + } + } ret = 0; - if (of_property_read_bool(np, "syscon-sfpb")) { + if (of_property_present(np, "syscon-sfpb")) { msm_host->sfpb = syscon_regmap_lookup_by_phandle(np, "syscon-sfpb"); if (IS_ERR(msm_host->sfpb)) { @@ -1874,39 +1885,35 @@ int msm_dsi_host_init(struct msm_dsi *msm_dsi) int ret; msm_host = devm_kzalloc(&pdev->dev, sizeof(*msm_host), GFP_KERNEL); - if (!msm_host) { + if (!msm_host) return -ENOMEM; - } msm_host->pdev = pdev; msm_dsi->host = &msm_host->base; ret = dsi_host_parse_dt(msm_host); - if (ret) { - pr_err("%s: failed to parse dt\n", __func__); - return ret; - } + if (ret) + return dev_err_probe(&pdev->dev, ret, "%s: failed to parse dt\n", + __func__); msm_host->ctrl_base = msm_ioremap_size(pdev, "dsi_ctrl", &msm_host->ctrl_size); - if (IS_ERR(msm_host->ctrl_base)) { - pr_err("%s: unable to map Dsi ctrl base\n", __func__); - return PTR_ERR(msm_host->ctrl_base); - } + if (IS_ERR(msm_host->ctrl_base)) + return dev_err_probe(&pdev->dev, PTR_ERR(msm_host->ctrl_base), + "%s: unable to map Dsi ctrl base\n", __func__); pm_runtime_enable(&pdev->dev); msm_host->cfg_hnd = dsi_get_config(msm_host); - if (!msm_host->cfg_hnd) { - pr_err("%s: get config failed\n", __func__); - return -EINVAL; - } + if (!msm_host->cfg_hnd) + return dev_err_probe(&pdev->dev, -EINVAL, + "%s: get config failed\n", __func__); cfg = msm_host->cfg_hnd->cfg; msm_host->id = dsi_host_get_id(msm_host); - if (msm_host->id < 0) { - pr_err("%s: unable to identify DSI host index\n", __func__); - return msm_host->id; - } + if (msm_host->id < 0) + return dev_err_probe(&pdev->dev, msm_host->id, + "%s: unable to identify DSI host index\n", + __func__); /* fixup base address by io offset */ msm_host->ctrl_base += cfg->io_offset; @@ -1918,42 +1925,32 @@ int msm_dsi_host_init(struct msm_dsi *msm_dsi) return ret; ret = dsi_clk_init(msm_host); - if (ret) { - pr_err("%s: unable to initialize dsi clks\n", __func__); - return ret; - } + if (ret) + return dev_err_probe(&pdev->dev, ret, "%s: unable to initialize dsi clks\n", __func__); msm_host->rx_buf = devm_kzalloc(&pdev->dev, SZ_4K, GFP_KERNEL); - if (!msm_host->rx_buf) { - pr_err("%s: alloc rx temp buf failed\n", __func__); + if (!msm_host->rx_buf) return -ENOMEM; - } ret = devm_pm_opp_set_clkname(&pdev->dev, "byte"); if (ret) return ret; /* OPP table is optional */ ret = devm_pm_opp_of_add_table(&pdev->dev); - if (ret && ret != -ENODEV) { - dev_err(&pdev->dev, "invalid OPP table in device tree\n"); - return ret; - } + if (ret && ret != -ENODEV) + return dev_err_probe(&pdev->dev, ret, "invalid OPP table in device tree\n"); msm_host->irq = irq_of_parse_and_map(pdev->dev.of_node, 0); - if (!msm_host->irq) { - dev_err(&pdev->dev, "failed to get irq\n"); - return -EINVAL; - } + if (!msm_host->irq) + return dev_err_probe(&pdev->dev, -EINVAL, "failed to get irq\n"); /* do not autoenable, will be enabled later */ ret = devm_request_irq(&pdev->dev, msm_host->irq, dsi_host_irq, IRQF_TRIGGER_HIGH | IRQF_NO_AUTOEN, "dsi_isr", msm_host); - if (ret < 0) { - dev_err(&pdev->dev, "failed to request IRQ%u: %d\n", - msm_host->irq, ret); - return ret; - } + if (ret < 0) + return dev_err_probe(&pdev->dev, ret, "failed to request IRQ%u\n", + msm_host->irq); init_completion(&msm_host->dma_comp); init_completion(&msm_host->video_comp); diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c index a210b7c9e5ca..ca400924d4ee 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_manager.c +++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c @@ -74,17 +74,35 @@ static int dsi_mgr_setup_components(int id) int ret; if (!IS_BONDED_DSI()) { + /* + * Set the usecase before calling msm_dsi_host_register(), which would + * already program the PLL source mux based on a default usecase. + */ + msm_dsi_phy_set_usecase(msm_dsi->phy, MSM_DSI_PHY_STANDALONE); + msm_dsi_host_set_phy_mode(msm_dsi->host, msm_dsi->phy); + ret = msm_dsi_host_register(msm_dsi->host); if (ret) return ret; - - msm_dsi_phy_set_usecase(msm_dsi->phy, MSM_DSI_PHY_STANDALONE); - msm_dsi_host_set_phy_mode(msm_dsi->host, msm_dsi->phy); } else if (other_dsi) { struct msm_dsi *master_link_dsi = IS_MASTER_DSI_LINK(id) ? msm_dsi : other_dsi; struct msm_dsi *slave_link_dsi = IS_MASTER_DSI_LINK(id) ? other_dsi : msm_dsi; + + /* + * PLL0 is to drive both DSI link clocks in bonded DSI mode. + * + * Set the usecase before calling msm_dsi_host_register(), which would + * already program the PLL source mux based on a default usecase. + */ + msm_dsi_phy_set_usecase(clk_master_dsi->phy, + MSM_DSI_PHY_MASTER); + msm_dsi_phy_set_usecase(clk_slave_dsi->phy, + MSM_DSI_PHY_SLAVE); + msm_dsi_host_set_phy_mode(msm_dsi->host, msm_dsi->phy); + msm_dsi_host_set_phy_mode(other_dsi->host, other_dsi->phy); + /* Register slave host first, so that slave DSI device * has a chance to probe, and do not block the master * DSI device's probe. @@ -98,14 +116,6 @@ static int dsi_mgr_setup_components(int id) ret = msm_dsi_host_register(master_link_dsi->host); if (ret) return ret; - - /* PLL0 is to drive both 2 DSI link clocks in bonded DSI mode. */ - msm_dsi_phy_set_usecase(clk_master_dsi->phy, - MSM_DSI_PHY_MASTER); - msm_dsi_phy_set_usecase(clk_slave_dsi->phy, - MSM_DSI_PHY_SLAVE); - msm_dsi_host_set_phy_mode(msm_dsi->host, msm_dsi->phy); - msm_dsi_host_set_phy_mode(other_dsi->host, other_dsi->phy); } return 0; @@ -424,12 +434,13 @@ static enum drm_mode_status dsi_mgr_bridge_mode_valid(struct drm_bridge *bridge, } static int dsi_mgr_bridge_attach(struct drm_bridge *bridge, + struct drm_encoder *encoder, enum drm_bridge_attach_flags flags) { int id = dsi_mgr_bridge_get_id(bridge); struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id); - return drm_bridge_attach(bridge->encoder, msm_dsi->next_bridge, + return drm_bridge_attach(encoder, msm_dsi->next_bridge, bridge, flags); } @@ -451,15 +462,14 @@ int msm_dsi_manager_connector_init(struct msm_dsi *msm_dsi, struct drm_connector *connector; int ret; - dsi_bridge = devm_kzalloc(msm_dsi->dev->dev, - sizeof(*dsi_bridge), GFP_KERNEL); - if (!dsi_bridge) - return -ENOMEM; + dsi_bridge = devm_drm_bridge_alloc(msm_dsi->dev->dev, struct dsi_bridge, base, + &dsi_mgr_bridge_funcs); + if (IS_ERR(dsi_bridge)) + return PTR_ERR(dsi_bridge); dsi_bridge->id = msm_dsi->id; bridge = &dsi_bridge->base; - bridge->funcs = &dsi_mgr_bridge_funcs; ret = devm_drm_bridge_add(msm_dsi->dev->dev, bridge); if (ret) diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c index dd58bc0a49eb..5973d7325699 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c @@ -567,6 +567,8 @@ static const struct of_device_id dsi_phy_dt_match[] = { .data = &dsi_phy_14nm_8953_cfgs }, { .compatible = "qcom,sm6125-dsi-phy-14nm", .data = &dsi_phy_14nm_2290_cfgs }, + { .compatible = "qcom,sm6150-dsi-phy-14nm", + .data = &dsi_phy_14nm_6150_cfgs }, #endif #ifdef CONFIG_DRM_MSM_DSI_10NM_PHY { .compatible = "qcom,dsi-phy-10nm", @@ -579,6 +581,10 @@ static const struct of_device_id dsi_phy_dt_match[] = { .data = &dsi_phy_7nm_cfgs }, { .compatible = "qcom,dsi-phy-7nm-8150", .data = &dsi_phy_7nm_8150_cfgs }, + { .compatible = "qcom,sa8775p-dsi-phy-5nm", + .data = &dsi_phy_5nm_8775p_cfgs }, + { .compatible = "qcom,sar2130p-dsi-phy-5nm", + .data = &dsi_phy_5nm_sar2130p_cfgs }, { .compatible = "qcom,sc7280-dsi-phy-7nm", .data = &dsi_phy_7nm_7280_cfgs }, { .compatible = "qcom,sm6375-dsi-phy-7nm", diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h index 4953459edd63..7ea608f620fe 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h @@ -6,6 +6,7 @@ #ifndef __DSI_PHY_H__ #define __DSI_PHY_H__ +#include <dt-bindings/clock/qcom,dsi-phy-28nm.h> #include <linux/clk-provider.h> #include <linux/delay.h> #include <linux/regulator/consumer.h> @@ -46,6 +47,7 @@ extern const struct msm_dsi_phy_cfg dsi_phy_28nm_8937_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_28nm_8960_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_20nm_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_14nm_cfgs; +extern const struct msm_dsi_phy_cfg dsi_phy_14nm_6150_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_14nm_660_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_14nm_2290_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_14nm_8953_cfgs; @@ -57,6 +59,8 @@ extern const struct msm_dsi_phy_cfg dsi_phy_7nm_8150_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_7nm_7280_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_5nm_8350_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_5nm_8450_cfgs; +extern const struct msm_dsi_phy_cfg dsi_phy_5nm_8775p_cfgs; +extern const struct msm_dsi_phy_cfg dsi_phy_5nm_sar2130p_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_4nm_8550_cfgs; extern const struct msm_dsi_phy_cfg dsi_phy_4nm_8650_cfgs; @@ -83,9 +87,7 @@ struct msm_dsi_dphy_timing { u8 hs_halfbyte_en_ckln; }; -#define DSI_BYTE_PLL_CLK 0 -#define DSI_PIXEL_PLL_CLK 1 -#define NUM_PROVIDED_CLKS 2 +#define NUM_PROVIDED_CLKS (DSI_PIXEL_PLL_CLK + 1) #define DSI_LANE_MAX 5 diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c index 677c62571811..af2e30f3f842 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c @@ -3,6 +3,7 @@ * Copyright (c) 2018, The Linux Foundation */ +#include <dt-bindings/clock/qcom,dsi-phy-28nm.h> #include <linux/clk.h> #include <linux/clk-provider.h> #include <linux/iopoll.h> @@ -703,6 +704,13 @@ static int dsi_pll_10nm_init(struct msm_dsi_phy *phy) /* TODO: Remove this when we have proper display handover support */ msm_dsi_phy_pll_save_state(phy); + /* + * Store also proper vco_current_rate, because its value will be used in + * dsi_10nm_pll_restore_state(). + */ + if (!dsi_pll_10nm_vco_recalc_rate(&pll_10nm->clk_hw, VCO_REF_CLK_RATE)) + pll_10nm->vco_current_rate = pll_10nm->phy->cfg->min_pll_rate; + return 0; } diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c index 1723f0e4faa4..3a1c8ece6657 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c @@ -3,6 +3,7 @@ * Copyright (c) 2016, The Linux Foundation. All rights reserved. */ +#include <dt-bindings/clock/qcom,dsi-phy-28nm.h> #include <linux/clk.h> #include <linux/clk-provider.h> #include <linux/delay.h> @@ -1032,6 +1033,10 @@ static const struct regulator_bulk_data dsi_phy_14nm_73p4mA_regulators[] = { { .supply = "vcca", .init_load_uA = 73400 }, }; +static const struct regulator_bulk_data dsi_phy_14nm_36mA_regulators[] = { + { .supply = "vdda", .init_load_uA = 36000 }, +}; + const struct msm_dsi_phy_cfg dsi_phy_14nm_cfgs = { .has_phy_lane = true, .regulator_data = dsi_phy_14nm_17mA_regulators, @@ -1097,3 +1102,20 @@ const struct msm_dsi_phy_cfg dsi_phy_14nm_2290_cfgs = { .io_start = { 0x5e94400 }, .num_dsi_phy = 1, }; + +const struct msm_dsi_phy_cfg dsi_phy_14nm_6150_cfgs = { + .has_phy_lane = true, + .regulator_data = dsi_phy_14nm_36mA_regulators, + .num_regulators = ARRAY_SIZE(dsi_phy_14nm_36mA_regulators), + .ops = { + .enable = dsi_14nm_phy_enable, + .disable = dsi_14nm_phy_disable, + .pll_init = dsi_pll_14nm_init, + .save_pll_state = dsi_14nm_pll_save_state, + .restore_pll_state = dsi_14nm_pll_restore_state, + }, + .min_pll_rate = VCO_MIN_RATE, + .max_pll_rate = VCO_MAX_RATE, + .io_start = { 0xae94400 }, + .num_dsi_phy = 1, +}; diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c index 1383e3a4e050..90348a2af3e9 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c @@ -3,6 +3,7 @@ * Copyright (c) 2015, The Linux Foundation. All rights reserved. */ +#include <dt-bindings/clock/qcom,dsi-phy-28nm.h> #include <linux/clk.h> #include <linux/clk-provider.h> diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c index 5311ab7f3c70..f3643320ff2f 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c @@ -3,6 +3,7 @@ * Copyright (c) 2012-2015, The Linux Foundation. All rights reserved. */ +#include <dt-bindings/clock/qcom,dsi-phy-28nm.h> #include <linux/clk-provider.h> #include <linux/delay.h> diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c index 798168180c1a..c19890358b74 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c @@ -3,6 +3,8 @@ * Copyright (c) 2018, The Linux Foundation */ +#include <dt-bindings/clock/qcom,dsi-phy-28nm.h> +#include <linux/bitfield.h> #include <linux/clk.h> #include <linux/clk-provider.h> #include <linux/iopoll.h> @@ -305,7 +307,7 @@ static void dsi_pll_commit(struct dsi_pll_7nm *pll, struct dsi_pll_config *confi writel(pll->phy->cphy_mode ? 0x00 : 0x10, base + REG_DSI_7nm_PHY_PLL_CMODE_1); writel(config->pll_clock_inverters, - base + REG_DSI_7nm_PHY_PLL_CLOCK_INVERTERS); + base + REG_DSI_7nm_PHY_PLL_CLOCK_INVERTERS_1); } static int dsi_pll_7nm_vco_set_rate(struct clk_hw *hw, unsigned long rate, @@ -572,11 +574,11 @@ static void dsi_7nm_pll_save_state(struct msm_dsi_phy *phy) cached->pll_out_div &= 0x3; cmn_clk_cfg0 = readl(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG0); - cached->bit_clk_div = cmn_clk_cfg0 & 0xf; - cached->pix_clk_div = (cmn_clk_cfg0 & 0xf0) >> 4; + cached->bit_clk_div = FIELD_GET(DSI_7nm_PHY_CMN_CLK_CFG0_DIV_CTRL_3_0__MASK, cmn_clk_cfg0); + cached->pix_clk_div = FIELD_GET(DSI_7nm_PHY_CMN_CLK_CFG0_DIV_CTRL_7_4__MASK, cmn_clk_cfg0); cmn_clk_cfg1 = readl(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG1); - cached->pll_mux = cmn_clk_cfg1 & 0x3; + cached->pll_mux = FIELD_GET(DSI_7nm_PHY_CMN_CLK_CFG1_DSICLK_SEL__MASK, cmn_clk_cfg1); DBG("DSI PLL%d outdiv %x bit_clk_div %x pix_clk_div %x pll_mux %x", pll_7nm->phy->id, cached->pll_out_div, cached->bit_clk_div, @@ -598,7 +600,8 @@ static int dsi_7nm_pll_restore_state(struct msm_dsi_phy *phy) dsi_pll_cmn_clk_cfg0_write(pll_7nm, DSI_7nm_PHY_CMN_CLK_CFG0_DIV_CTRL_3_0(cached->bit_clk_div) | DSI_7nm_PHY_CMN_CLK_CFG0_DIV_CTRL_7_4(cached->pix_clk_div)); - dsi_pll_cmn_clk_cfg1_update(pll_7nm, 0x3, cached->pll_mux); + dsi_pll_cmn_clk_cfg1_update(pll_7nm, DSI_7nm_PHY_CMN_CLK_CFG1_DSICLK_SEL__MASK, + cached->pll_mux); ret = dsi_pll_7nm_vco_set_rate(phy->vco_hw, pll_7nm->vco_current_rate, @@ -736,11 +739,9 @@ static int pll_7nm_register(struct dsi_pll_7nm *pll_7nm, struct clk_hw **provide * don't register a pclk_mux clock and just use post_out_div instead */ if (pll_7nm->phy->cphy_mode) { - u32 data; - - data = readl(pll_7nm->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1); - writel(data | 3, pll_7nm->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1); - + dsi_pll_cmn_clk_cfg1_update(pll_7nm, + DSI_7nm_PHY_CMN_CLK_CFG1_DSICLK_SEL__MASK, + DSI_7nm_PHY_CMN_CLK_CFG1_DSICLK_SEL(3)); phy_pll_out_dsi_parent = pll_post_out_div; } else { snprintf(clk_name, sizeof(clk_name), "dsi%d_pclk_mux", pll_7nm->phy->id); @@ -1146,6 +1147,10 @@ static const struct regulator_bulk_data dsi_phy_7nm_37750uA_regulators[] = { { .supply = "vdds", .init_load_uA = 37550 }, }; +static const struct regulator_bulk_data dsi_phy_7nm_48000uA_regulators[] = { + { .supply = "vdds", .init_load_uA = 48000 }, +}; + static const struct regulator_bulk_data dsi_phy_7nm_98000uA_regulators[] = { { .supply = "vdds", .init_load_uA = 98000 }, }; @@ -1288,6 +1293,52 @@ const struct msm_dsi_phy_cfg dsi_phy_5nm_8450_cfgs = { .quirks = DSI_PHY_7NM_QUIRK_V4_3, }; +const struct msm_dsi_phy_cfg dsi_phy_5nm_8775p_cfgs = { + .has_phy_lane = true, + .regulator_data = dsi_phy_7nm_48000uA_regulators, + .num_regulators = ARRAY_SIZE(dsi_phy_7nm_48000uA_regulators), + .ops = { + .enable = dsi_7nm_phy_enable, + .disable = dsi_7nm_phy_disable, + .pll_init = dsi_pll_7nm_init, + .save_pll_state = dsi_7nm_pll_save_state, + .restore_pll_state = dsi_7nm_pll_restore_state, + .set_continuous_clock = dsi_7nm_set_continuous_clock, + }, + .min_pll_rate = 600000000UL, +#ifdef CONFIG_64BIT + .max_pll_rate = 5000000000UL, +#else + .max_pll_rate = ULONG_MAX, +#endif + .io_start = { 0xae94400, 0xae96400 }, + .num_dsi_phy = 2, + .quirks = DSI_PHY_7NM_QUIRK_V4_2, +}; + +const struct msm_dsi_phy_cfg dsi_phy_5nm_sar2130p_cfgs = { + .has_phy_lane = true, + .regulator_data = dsi_phy_7nm_97800uA_regulators, + .num_regulators = ARRAY_SIZE(dsi_phy_7nm_97800uA_regulators), + .ops = { + .enable = dsi_7nm_phy_enable, + .disable = dsi_7nm_phy_disable, + .pll_init = dsi_pll_7nm_init, + .save_pll_state = dsi_7nm_pll_save_state, + .restore_pll_state = dsi_7nm_pll_restore_state, + .set_continuous_clock = dsi_7nm_set_continuous_clock, + }, + .min_pll_rate = 600000000UL, +#ifdef CONFIG_64BIT + .max_pll_rate = 5000000000UL, +#else + .max_pll_rate = ULONG_MAX, +#endif + .io_start = { 0xae95000, 0xae97000 }, + .num_dsi_phy = 2, + .quirks = DSI_PHY_7NM_QUIRK_V5_2, +}; + const struct msm_dsi_phy_cfg dsi_phy_4nm_8550_cfgs = { .has_phy_lane = true, .regulator_data = dsi_phy_7nm_98400uA_regulators, diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.c b/drivers/gpu/drm/msm/hdmi/hdmi.c index 37b3809c6bdd..2fd388b892dc 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi.c @@ -8,12 +8,13 @@ #include <linux/gpio/consumer.h> #include <linux/of_irq.h> #include <linux/of_platform.h> +#include <linux/pinctrl/consumer.h> #include <linux/platform_device.h> #include <drm/drm_bridge_connector.h> #include <drm/drm_of.h> +#include <drm/display/drm_hdmi_state_helper.h> -#include <sound/hdmi-codec.h> #include "hdmi.h" void msm_hdmi_set_mode(struct hdmi *hdmi, bool power_on) @@ -24,7 +25,7 @@ void msm_hdmi_set_mode(struct hdmi *hdmi, bool power_on) spin_lock_irqsave(&hdmi->reg_lock, flags); if (power_on) { ctrl |= HDMI_CTRL_ENABLE; - if (!hdmi->hdmi_mode) { + if (!hdmi->connector->display_info.is_hdmi) { ctrl |= HDMI_CTRL_HDMI; hdmi_write(hdmi, REG_HDMI_CTRL, ctrl); ctrl &= ~HDMI_CTRL_HDMI; @@ -165,8 +166,6 @@ int msm_hdmi_modeset_init(struct hdmi *hdmi, hdmi->dev = dev; hdmi->encoder = encoder; - hdmi_audio_infoframe_init(&hdmi->audio.infoframe); - ret = msm_hdmi_bridge_init(hdmi); if (ret) { DRM_DEV_ERROR(dev->dev, "failed to create HDMI bridge: %d\n", ret); @@ -201,12 +200,6 @@ int msm_hdmi_modeset_init(struct hdmi *hdmi, goto fail; } - ret = msm_hdmi_hpd_enable(hdmi->bridge); - if (ret < 0) { - DRM_DEV_ERROR(&hdmi->pdev->dev, "failed to enable HPD: %d\n", ret); - goto fail; - } - return 0; fail: @@ -222,135 +215,26 @@ fail: * The hdmi device: */ -#define HDMI_CFG(item, entry) \ - .item ## _names = item ##_names_ ## entry, \ - .item ## _cnt = ARRAY_SIZE(item ## _names_ ## entry) - -static const char *hpd_reg_names_8960[] = {"core-vdda"}; -static const char *hpd_clk_names_8960[] = {"core", "master_iface", "slave_iface"}; +static const char * const pwr_reg_names_8960[] = {"core-vdda"}; +static const char * const pwr_clk_names_8960[] = {"core", "master_iface", "slave_iface"}; static const struct hdmi_platform_config hdmi_tx_8960_config = { - HDMI_CFG(hpd_reg, 8960), - HDMI_CFG(hpd_clk, 8960), + .pwr_reg_names = pwr_reg_names_8960, + .pwr_reg_cnt = ARRAY_SIZE(pwr_reg_names_8960), + .pwr_clk_names = pwr_clk_names_8960, + .pwr_clk_cnt = ARRAY_SIZE(pwr_clk_names_8960), }; -static const char *pwr_reg_names_8x74[] = {"core-vdda", "core-vcc"}; -static const char *pwr_clk_names_8x74[] = {"extp", "alt_iface"}; -static const char *hpd_clk_names_8x74[] = {"iface", "core", "mdp_core"}; -static unsigned long hpd_clk_freq_8x74[] = {0, 19200000, 0}; +static const char * const pwr_reg_names_8x74[] = {"core-vdda", "core-vcc"}; +static const char * const pwr_clk_names_8x74[] = {"iface", "core", "mdp_core", "alt_iface"}; static const struct hdmi_platform_config hdmi_tx_8974_config = { - HDMI_CFG(pwr_reg, 8x74), - HDMI_CFG(pwr_clk, 8x74), - HDMI_CFG(hpd_clk, 8x74), - .hpd_freq = hpd_clk_freq_8x74, + .pwr_reg_names = pwr_reg_names_8x74, + .pwr_reg_cnt = ARRAY_SIZE(pwr_reg_names_8x74), + .pwr_clk_names = pwr_clk_names_8x74, + .pwr_clk_cnt = ARRAY_SIZE(pwr_clk_names_8x74), }; -/* - * HDMI audio codec callbacks - */ -static int msm_hdmi_audio_hw_params(struct device *dev, void *data, - struct hdmi_codec_daifmt *daifmt, - struct hdmi_codec_params *params) -{ - struct hdmi *hdmi = dev_get_drvdata(dev); - unsigned int chan; - unsigned int channel_allocation = 0; - unsigned int rate; - unsigned int level_shift = 0; /* 0dB */ - bool down_mix = false; - - DRM_DEV_DEBUG(dev, "%u Hz, %d bit, %d channels\n", params->sample_rate, - params->sample_width, params->cea.channels); - - switch (params->cea.channels) { - case 2: - /* FR and FL speakers */ - channel_allocation = 0; - chan = MSM_HDMI_AUDIO_CHANNEL_2; - break; - case 4: - /* FC, LFE, FR and FL speakers */ - channel_allocation = 0x3; - chan = MSM_HDMI_AUDIO_CHANNEL_4; - break; - case 6: - /* RR, RL, FC, LFE, FR and FL speakers */ - channel_allocation = 0x0B; - chan = MSM_HDMI_AUDIO_CHANNEL_6; - break; - case 8: - /* FRC, FLC, RR, RL, FC, LFE, FR and FL speakers */ - channel_allocation = 0x1F; - chan = MSM_HDMI_AUDIO_CHANNEL_8; - break; - default: - return -EINVAL; - } - - switch (params->sample_rate) { - case 32000: - rate = HDMI_SAMPLE_RATE_32KHZ; - break; - case 44100: - rate = HDMI_SAMPLE_RATE_44_1KHZ; - break; - case 48000: - rate = HDMI_SAMPLE_RATE_48KHZ; - break; - case 88200: - rate = HDMI_SAMPLE_RATE_88_2KHZ; - break; - case 96000: - rate = HDMI_SAMPLE_RATE_96KHZ; - break; - case 176400: - rate = HDMI_SAMPLE_RATE_176_4KHZ; - break; - case 192000: - rate = HDMI_SAMPLE_RATE_192KHZ; - break; - default: - DRM_DEV_ERROR(dev, "rate[%d] not supported!\n", - params->sample_rate); - return -EINVAL; - } - - msm_hdmi_audio_set_sample_rate(hdmi, rate); - msm_hdmi_audio_info_setup(hdmi, 1, chan, channel_allocation, - level_shift, down_mix); - - return 0; -} - -static void msm_hdmi_audio_shutdown(struct device *dev, void *data) -{ - struct hdmi *hdmi = dev_get_drvdata(dev); - - msm_hdmi_audio_info_setup(hdmi, 0, 0, 0, 0, 0); -} - -static const struct hdmi_codec_ops msm_hdmi_audio_codec_ops = { - .hw_params = msm_hdmi_audio_hw_params, - .audio_shutdown = msm_hdmi_audio_shutdown, -}; - -static struct hdmi_codec_pdata codec_data = { - .ops = &msm_hdmi_audio_codec_ops, - .max_i2s_channels = 8, - .i2s = 1, -}; - -static int msm_hdmi_register_audio_driver(struct hdmi *hdmi, struct device *dev) -{ - hdmi->audio_pdev = platform_device_register_data(dev, - HDMI_CODEC_DRV_NAME, - PLATFORM_DEVID_AUTO, - &codec_data, - sizeof(codec_data)); - return PTR_ERR_OR_ZERO(hdmi->audio_pdev); -} - static int msm_hdmi_bind(struct device *dev, struct device *master, void *data) { struct msm_drm_private *priv = dev_get_drvdata(master); @@ -362,12 +246,6 @@ static int msm_hdmi_bind(struct device *dev, struct device *master, void *data) return err; priv->hdmi = hdmi; - err = msm_hdmi_register_audio_driver(hdmi, dev); - if (err) { - DRM_ERROR("Failed to attach an audio codec %d\n", err); - hdmi->audio_pdev = NULL; - } - return 0; } @@ -377,12 +255,6 @@ static void msm_hdmi_unbind(struct device *dev, struct device *master, struct msm_drm_private *priv = dev_get_drvdata(master); if (priv->hdmi) { - if (priv->hdmi->audio_pdev) - platform_device_unregister(priv->hdmi->audio_pdev); - - if (priv->hdmi->bridge) - msm_hdmi_hpd_disable(priv->hdmi); - msm_hdmi_destroy(priv->hdmi); priv->hdmi = NULL; } @@ -412,6 +284,7 @@ static int msm_hdmi_dev_probe(struct platform_device *pdev) hdmi->pdev = pdev; hdmi->config = config; spin_lock_init(&hdmi->reg_lock); + mutex_init(&hdmi->state_mutex); ret = drm_of_find_panel_or_bridge(pdev->dev.of_node, 1, 0, NULL, &hdmi->next_bridge); if (ret && ret != -ENODEV) @@ -438,20 +311,6 @@ static int msm_hdmi_dev_probe(struct platform_device *pdev) if (hdmi->irq < 0) return hdmi->irq; - hdmi->hpd_regs = devm_kcalloc(&pdev->dev, - config->hpd_reg_cnt, - sizeof(hdmi->hpd_regs[0]), - GFP_KERNEL); - if (!hdmi->hpd_regs) - return -ENOMEM; - - for (i = 0; i < config->hpd_reg_cnt; i++) - hdmi->hpd_regs[i].supply = config->hpd_reg_names[i]; - - ret = devm_regulator_bulk_get(&pdev->dev, config->hpd_reg_cnt, hdmi->hpd_regs); - if (ret) - return dev_err_probe(dev, ret, "failed to get hpd regulators\n"); - hdmi->pwr_regs = devm_kcalloc(&pdev->dev, config->pwr_reg_cnt, sizeof(hdmi->pwr_regs[0]), @@ -466,25 +325,6 @@ static int msm_hdmi_dev_probe(struct platform_device *pdev) if (ret) return dev_err_probe(dev, ret, "failed to get pwr regulators\n"); - hdmi->hpd_clks = devm_kcalloc(&pdev->dev, - config->hpd_clk_cnt, - sizeof(hdmi->hpd_clks[0]), - GFP_KERNEL); - if (!hdmi->hpd_clks) - return -ENOMEM; - - for (i = 0; i < config->hpd_clk_cnt; i++) { - struct clk *clk; - - clk = msm_clk_get(pdev, config->hpd_clk_names[i]); - if (IS_ERR(clk)) - return dev_err_probe(dev, PTR_ERR(clk), - "failed to get hpd clk: %s\n", - config->hpd_clk_names[i]); - - hdmi->hpd_clks[i] = clk; - } - hdmi->pwr_clks = devm_kcalloc(&pdev->dev, config->pwr_clk_cnt, sizeof(hdmi->pwr_clks[0]), @@ -492,17 +332,17 @@ static int msm_hdmi_dev_probe(struct platform_device *pdev) if (!hdmi->pwr_clks) return -ENOMEM; - for (i = 0; i < config->pwr_clk_cnt; i++) { - struct clk *clk; + for (i = 0; i < config->pwr_clk_cnt; i++) + hdmi->pwr_clks[i].id = config->pwr_clk_names[i]; - clk = msm_clk_get(pdev, config->pwr_clk_names[i]); - if (IS_ERR(clk)) - return dev_err_probe(dev, PTR_ERR(clk), - "failed to get pwr clk: %s\n", - config->pwr_clk_names[i]); + ret = devm_clk_bulk_get(&pdev->dev, config->pwr_clk_cnt, hdmi->pwr_clks); + if (ret) + return ret; - hdmi->pwr_clks[i] = clk; - } + hdmi->extp_clk = devm_clk_get_optional(&pdev->dev, "extp"); + if (IS_ERR(hdmi->extp_clk)) + return dev_err_probe(dev, PTR_ERR(hdmi->extp_clk), + "failed to get extp clock\n"); hdmi->hpd_gpiod = devm_gpiod_get_optional(&pdev->dev, "hpd", GPIOD_IN); /* This will catch e.g. -EPROBE_DEFER */ @@ -548,6 +388,48 @@ static void msm_hdmi_dev_remove(struct platform_device *pdev) msm_hdmi_put_phy(hdmi); } +static int msm_hdmi_runtime_suspend(struct device *dev) +{ + struct hdmi *hdmi = dev_get_drvdata(dev); + const struct hdmi_platform_config *config = hdmi->config; + + clk_bulk_disable_unprepare(config->pwr_clk_cnt, hdmi->pwr_clks); + + pinctrl_pm_select_sleep_state(dev); + + regulator_bulk_disable(config->pwr_reg_cnt, hdmi->pwr_regs); + + return 0; +} + +static int msm_hdmi_runtime_resume(struct device *dev) +{ + struct hdmi *hdmi = dev_get_drvdata(dev); + const struct hdmi_platform_config *config = hdmi->config; + int ret; + + ret = regulator_bulk_enable(config->pwr_reg_cnt, hdmi->pwr_regs); + if (ret) + return ret; + + ret = pinctrl_pm_select_default_state(dev); + if (ret) + goto fail; + + ret = clk_bulk_prepare_enable(config->pwr_clk_cnt, hdmi->pwr_clks); + if (ret) + goto fail; + + return 0; + +fail: + pinctrl_pm_select_sleep_state(dev); + + return ret; +} + +DEFINE_RUNTIME_DEV_PM_OPS(msm_hdmi_pm_ops, msm_hdmi_runtime_suspend, msm_hdmi_runtime_resume, NULL); + static const struct of_device_id msm_hdmi_dt_match[] = { { .compatible = "qcom,hdmi-tx-8998", .data = &hdmi_tx_8974_config }, { .compatible = "qcom,hdmi-tx-8996", .data = &hdmi_tx_8974_config }, @@ -565,6 +447,7 @@ static struct platform_driver msm_hdmi_driver = { .driver = { .name = "hdmi_msm", .of_match_table = msm_hdmi_dt_match, + .pm = &msm_hdmi_pm_ops, }, }; diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.h b/drivers/gpu/drm/msm/hdmi/hdmi.h index a62d2aedfbb7..d5e572d10d6a 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi.h +++ b/drivers/gpu/drm/msm/hdmi/hdmi.h @@ -24,8 +24,8 @@ struct hdmi_platform_config; struct hdmi_audio { bool enabled; - struct hdmi_audio_infoframe infoframe; int rate; + int channels; }; struct hdmi_hdcp_ctrl; @@ -33,7 +33,6 @@ struct hdmi_hdcp_ctrl; struct hdmi { struct drm_device *dev; struct platform_device *pdev; - struct platform_device *audio_pdev; const struct hdmi_platform_config *config; @@ -42,16 +41,17 @@ struct hdmi { /* video state: */ bool power_on; + bool hpd_enabled; + struct mutex state_mutex; /* protects two booleans */ unsigned long int pixclock; void __iomem *mmio; void __iomem *qfprom_mmio; phys_addr_t mmio_phy_addr; - struct regulator_bulk_data *hpd_regs; struct regulator_bulk_data *pwr_regs; - struct clk **hpd_clks; - struct clk **pwr_clks; + struct clk_bulk_data *pwr_clks; + struct clk *extp_clk; struct gpio_desc *hpd_gpiod; @@ -67,8 +67,6 @@ struct hdmi { /* the encoder we are hooked to (outside of hdmi block) */ struct drm_encoder *encoder; - bool hdmi_mode; /* are we in hdmi mode? */ - int irq; struct workqueue_struct *workq; @@ -86,21 +84,12 @@ struct hdmi { /* platform config data (ie. from DT, or pdata) */ struct hdmi_platform_config { - /* regulators that need to be on for hpd: */ - const char **hpd_reg_names; - int hpd_reg_cnt; - /* regulators that need to be on for screen pwr: */ - const char **pwr_reg_names; + const char * const *pwr_reg_names; int pwr_reg_cnt; - /* clks that need to be on for hpd: */ - const char **hpd_clk_names; - const long unsigned *hpd_freq; - int hpd_clk_cnt; - - /* clks that need to be on for screen pwr (ie pixel clk): */ - const char **pwr_clk_names; + /* clks that need to be on: */ + const char * const *pwr_clk_names; int pwr_clk_cnt; }; @@ -207,26 +196,16 @@ static inline int msm_hdmi_pll_8998_init(struct platform_device *pdev) /* * audio: */ -/* Supported HDMI Audio channels and rates */ -#define MSM_HDMI_AUDIO_CHANNEL_2 0 -#define MSM_HDMI_AUDIO_CHANNEL_4 1 -#define MSM_HDMI_AUDIO_CHANNEL_6 2 -#define MSM_HDMI_AUDIO_CHANNEL_8 3 - -#define HDMI_SAMPLE_RATE_32KHZ 0 -#define HDMI_SAMPLE_RATE_44_1KHZ 1 -#define HDMI_SAMPLE_RATE_48KHZ 2 -#define HDMI_SAMPLE_RATE_88_2KHZ 3 -#define HDMI_SAMPLE_RATE_96KHZ 4 -#define HDMI_SAMPLE_RATE_176_4KHZ 5 -#define HDMI_SAMPLE_RATE_192KHZ 6 +struct hdmi_codec_daifmt; +struct hdmi_codec_params; int msm_hdmi_audio_update(struct hdmi *hdmi); -int msm_hdmi_audio_info_setup(struct hdmi *hdmi, bool enabled, - uint32_t num_of_channels, uint32_t channel_allocation, - uint32_t level_shift, bool down_mix); -void msm_hdmi_audio_set_sample_rate(struct hdmi *hdmi, int rate); - +int msm_hdmi_bridge_audio_prepare(struct drm_connector *connector, + struct drm_bridge *bridge, + struct hdmi_codec_daifmt *daifmt, + struct hdmi_codec_params *params); +void msm_hdmi_bridge_audio_shutdown(struct drm_connector *connector, + struct drm_bridge *bridge); /* * hdmi bridge: @@ -237,8 +216,8 @@ int msm_hdmi_bridge_init(struct hdmi *hdmi); void msm_hdmi_hpd_irq(struct drm_bridge *bridge); enum drm_connector_status msm_hdmi_bridge_detect( struct drm_bridge *bridge); -int msm_hdmi_hpd_enable(struct drm_bridge *bridge); -void msm_hdmi_hpd_disable(struct hdmi *hdmi); +void msm_hdmi_hpd_enable(struct drm_bridge *bridge); +void msm_hdmi_hpd_disable(struct drm_bridge *bridge); /* * i2c adapter for ddc: diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_audio.c b/drivers/gpu/drm/msm/hdmi/hdmi_audio.c index 4c2058c4adc1..b9ec14ef2c20 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_audio.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_audio.c @@ -4,86 +4,28 @@ * Author: Rob Clark <robdclark@gmail.com> */ -#include <linux/hdmi.h> -#include "hdmi.h" +#include <drm/display/drm_hdmi_helper.h> +#include <drm/display/drm_hdmi_state_helper.h> -/* maps MSM_HDMI_AUDIO_CHANNEL_n consts used by audio driver to # of channels: */ -static int nchannels[] = { 2, 4, 6, 8 }; - -/* Supported HDMI Audio sample rates */ -#define MSM_HDMI_SAMPLE_RATE_32KHZ 0 -#define MSM_HDMI_SAMPLE_RATE_44_1KHZ 1 -#define MSM_HDMI_SAMPLE_RATE_48KHZ 2 -#define MSM_HDMI_SAMPLE_RATE_88_2KHZ 3 -#define MSM_HDMI_SAMPLE_RATE_96KHZ 4 -#define MSM_HDMI_SAMPLE_RATE_176_4KHZ 5 -#define MSM_HDMI_SAMPLE_RATE_192KHZ 6 -#define MSM_HDMI_SAMPLE_RATE_MAX 7 - - -struct hdmi_msm_audio_acr { - uint32_t n; /* N parameter for clock regeneration */ - uint32_t cts; /* CTS parameter for clock regeneration */ -}; - -struct hdmi_msm_audio_arcs { - unsigned long int pixclock; - struct hdmi_msm_audio_acr lut[MSM_HDMI_SAMPLE_RATE_MAX]; -}; - -#define HDMI_MSM_AUDIO_ARCS(pclk, ...) { (1000 * (pclk)), __VA_ARGS__ } - -/* Audio constants lookup table for hdmi_msm_audio_acr_setup */ -/* Valid Pixel-Clock rates: 25.2MHz, 27MHz, 27.03MHz, 74.25MHz, 148.5MHz */ -static const struct hdmi_msm_audio_arcs acr_lut[] = { - /* 25.200MHz */ - HDMI_MSM_AUDIO_ARCS(25200, { - {4096, 25200}, {6272, 28000}, {6144, 25200}, {12544, 28000}, - {12288, 25200}, {25088, 28000}, {24576, 25200} }), - /* 27.000MHz */ - HDMI_MSM_AUDIO_ARCS(27000, { - {4096, 27000}, {6272, 30000}, {6144, 27000}, {12544, 30000}, - {12288, 27000}, {25088, 30000}, {24576, 27000} }), - /* 27.027MHz */ - HDMI_MSM_AUDIO_ARCS(27030, { - {4096, 27027}, {6272, 30030}, {6144, 27027}, {12544, 30030}, - {12288, 27027}, {25088, 30030}, {24576, 27027} }), - /* 74.250MHz */ - HDMI_MSM_AUDIO_ARCS(74250, { - {4096, 74250}, {6272, 82500}, {6144, 74250}, {12544, 82500}, - {12288, 74250}, {25088, 82500}, {24576, 74250} }), - /* 148.500MHz */ - HDMI_MSM_AUDIO_ARCS(148500, { - {4096, 148500}, {6272, 165000}, {6144, 148500}, {12544, 165000}, - {12288, 148500}, {25088, 165000}, {24576, 148500} }), -}; - -static const struct hdmi_msm_audio_arcs *get_arcs(unsigned long int pixclock) -{ - int i; +#include <linux/hdmi.h> - for (i = 0; i < ARRAY_SIZE(acr_lut); i++) { - const struct hdmi_msm_audio_arcs *arcs = &acr_lut[i]; - if (arcs->pixclock == pixclock) - return arcs; - } +#include <sound/hdmi-codec.h> - return NULL; -} +#include "hdmi.h" int msm_hdmi_audio_update(struct hdmi *hdmi) { struct hdmi_audio *audio = &hdmi->audio; - struct hdmi_audio_infoframe *info = &audio->infoframe; - const struct hdmi_msm_audio_arcs *arcs = NULL; bool enabled = audio->enabled; uint32_t acr_pkt_ctrl, vbi_pkt_ctrl, aud_pkt_ctrl; - uint32_t infofrm_ctrl, audio_config; + uint32_t audio_config; + + if (!hdmi->connector->display_info.is_hdmi) + return -EINVAL; + + DBG("audio: enabled=%d, channels=%d, rate=%d", + audio->enabled, audio->channels, audio->rate); - DBG("audio: enabled=%d, channels=%d, channel_allocation=0x%x, " - "level_shift_value=%d, downmix_inhibit=%d, rate=%d", - audio->enabled, info->channels, info->channel_allocation, - info->level_shift_value, info->downmix_inhibit, audio->rate); DBG("video: power_on=%d, pixclock=%lu", hdmi->power_on, hdmi->pixclock); if (enabled && !(hdmi->power_on && hdmi->pixclock)) { @@ -91,20 +33,10 @@ int msm_hdmi_audio_update(struct hdmi *hdmi) enabled = false; } - if (enabled) { - arcs = get_arcs(hdmi->pixclock); - if (!arcs) { - DBG("disabling audio: unsupported pixclock: %lu", - hdmi->pixclock); - enabled = false; - } - } - /* Read first before writing */ acr_pkt_ctrl = hdmi_read(hdmi, REG_HDMI_ACR_PKT_CTRL); vbi_pkt_ctrl = hdmi_read(hdmi, REG_HDMI_VBI_PKT_CTRL); aud_pkt_ctrl = hdmi_read(hdmi, REG_HDMI_AUDIO_PKT_CTRL1); - infofrm_ctrl = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL0); audio_config = hdmi_read(hdmi, REG_HDMI_AUDIO_CFG); /* Clear N/CTS selection bits */ @@ -113,17 +45,13 @@ int msm_hdmi_audio_update(struct hdmi *hdmi) if (enabled) { uint32_t n, cts, multiplier; enum hdmi_acr_cts select; - uint8_t buf[14]; - n = arcs->lut[audio->rate].n; - cts = arcs->lut[audio->rate].cts; + drm_hdmi_acr_get_n_cts(hdmi->pixclock, audio->rate, &n, &cts); - if ((MSM_HDMI_SAMPLE_RATE_192KHZ == audio->rate) || - (MSM_HDMI_SAMPLE_RATE_176_4KHZ == audio->rate)) { + if (audio->rate == 192000 || audio->rate == 176400) { multiplier = 4; n >>= 2; /* divide N by 4 and use multiplier */ - } else if ((MSM_HDMI_SAMPLE_RATE_96KHZ == audio->rate) || - (MSM_HDMI_SAMPLE_RATE_88_2KHZ == audio->rate)) { + } else if (audio->rate == 96000 || audio->rate == 88200) { multiplier = 2; n >>= 1; /* divide N by 2 and use multiplier */ } else { @@ -136,13 +64,11 @@ int msm_hdmi_audio_update(struct hdmi *hdmi) acr_pkt_ctrl |= HDMI_ACR_PKT_CTRL_AUDIO_PRIORITY; acr_pkt_ctrl |= HDMI_ACR_PKT_CTRL_N_MULTIPLIER(multiplier); - if ((MSM_HDMI_SAMPLE_RATE_48KHZ == audio->rate) || - (MSM_HDMI_SAMPLE_RATE_96KHZ == audio->rate) || - (MSM_HDMI_SAMPLE_RATE_192KHZ == audio->rate)) + if (audio->rate == 48000 || audio->rate == 96000 || + audio->rate == 192000) select = ACR_48; - else if ((MSM_HDMI_SAMPLE_RATE_44_1KHZ == audio->rate) || - (MSM_HDMI_SAMPLE_RATE_88_2KHZ == audio->rate) || - (MSM_HDMI_SAMPLE_RATE_176_4KHZ == audio->rate)) + else if (audio->rate == 44100 || audio->rate == 88200 || + audio->rate == 176400) select = ACR_44; else /* default to 32k */ select = ACR_32; @@ -155,20 +81,12 @@ int msm_hdmi_audio_update(struct hdmi *hdmi) HDMI_ACR_1_N(n)); hdmi_write(hdmi, REG_HDMI_AUDIO_PKT_CTRL2, - COND(info->channels != 2, HDMI_AUDIO_PKT_CTRL2_LAYOUT) | + COND(audio->channels != 2, HDMI_AUDIO_PKT_CTRL2_LAYOUT) | HDMI_AUDIO_PKT_CTRL2_OVERRIDE); acr_pkt_ctrl |= HDMI_ACR_PKT_CTRL_CONT; acr_pkt_ctrl |= HDMI_ACR_PKT_CTRL_SEND; - /* configure infoframe: */ - hdmi_audio_infoframe_pack(info, buf, sizeof(buf)); - hdmi_write(hdmi, REG_HDMI_AUDIO_INFO0, - (buf[3] << 0) | (buf[4] << 8) | - (buf[5] << 16) | (buf[6] << 24)); - hdmi_write(hdmi, REG_HDMI_AUDIO_INFO1, - (buf[7] << 0) | (buf[8] << 8)); - hdmi_write(hdmi, REG_HDMI_GC, 0); vbi_pkt_ctrl |= HDMI_VBI_PKT_CTRL_GC_ENABLE; @@ -176,11 +94,6 @@ int msm_hdmi_audio_update(struct hdmi *hdmi) aud_pkt_ctrl |= HDMI_AUDIO_PKT_CTRL1_AUDIO_SAMPLE_SEND; - infofrm_ctrl |= HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SEND; - infofrm_ctrl |= HDMI_INFOFRAME_CTRL0_AUDIO_INFO_CONT; - infofrm_ctrl |= HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SOURCE; - infofrm_ctrl |= HDMI_INFOFRAME_CTRL0_AUDIO_INFO_UPDATE; - audio_config &= ~HDMI_AUDIO_CFG_FIFO_WATERMARK__MASK; audio_config |= HDMI_AUDIO_CFG_FIFO_WATERMARK(4); audio_config |= HDMI_AUDIO_CFG_ENGINE_ENABLE; @@ -190,17 +103,12 @@ int msm_hdmi_audio_update(struct hdmi *hdmi) vbi_pkt_ctrl &= ~HDMI_VBI_PKT_CTRL_GC_ENABLE; vbi_pkt_ctrl &= ~HDMI_VBI_PKT_CTRL_GC_EVERY_FRAME; aud_pkt_ctrl &= ~HDMI_AUDIO_PKT_CTRL1_AUDIO_SAMPLE_SEND; - infofrm_ctrl &= ~HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SEND; - infofrm_ctrl &= ~HDMI_INFOFRAME_CTRL0_AUDIO_INFO_CONT; - infofrm_ctrl &= ~HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SOURCE; - infofrm_ctrl &= ~HDMI_INFOFRAME_CTRL0_AUDIO_INFO_UPDATE; audio_config &= ~HDMI_AUDIO_CFG_ENGINE_ENABLE; } hdmi_write(hdmi, REG_HDMI_ACR_PKT_CTRL, acr_pkt_ctrl); hdmi_write(hdmi, REG_HDMI_VBI_PKT_CTRL, vbi_pkt_ctrl); hdmi_write(hdmi, REG_HDMI_AUDIO_PKT_CTRL1, aud_pkt_ctrl); - hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL0, infofrm_ctrl); hdmi_write(hdmi, REG_HDMI_AUD_INT, COND(enabled, HDMI_AUD_INT_AUD_FIFO_URUN_INT) | @@ -214,41 +122,58 @@ int msm_hdmi_audio_update(struct hdmi *hdmi) return 0; } -int msm_hdmi_audio_info_setup(struct hdmi *hdmi, bool enabled, - uint32_t num_of_channels, uint32_t channel_allocation, - uint32_t level_shift, bool down_mix) +int msm_hdmi_bridge_audio_prepare(struct drm_connector *connector, + struct drm_bridge *bridge, + struct hdmi_codec_daifmt *daifmt, + struct hdmi_codec_params *params) { - struct hdmi_audio *audio; - - if (!hdmi) - return -ENXIO; - - audio = &hdmi->audio; - - if (num_of_channels >= ARRAY_SIZE(nchannels)) + struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); + struct hdmi *hdmi = hdmi_bridge->hdmi; + int ret; + + drm_dbg_driver(bridge->dev, "%u Hz, %d bit, %d channels\n", + params->sample_rate, + params->sample_width, + params->cea.channels); + + switch (params->sample_rate) { + case 32000: + case 44100: + case 48000: + case 88200: + case 96000: + case 176400: + case 192000: + break; + default: + drm_err(bridge->dev, "rate[%d] not supported!\n", + params->sample_rate); return -EINVAL; + } - audio->enabled = enabled; - audio->infoframe.channels = nchannels[num_of_channels]; - audio->infoframe.channel_allocation = channel_allocation; - audio->infoframe.level_shift_value = level_shift; - audio->infoframe.downmix_inhibit = down_mix; + ret = drm_atomic_helper_connector_hdmi_update_audio_infoframe(connector, + ¶ms->cea); + if (ret) + return ret; + + hdmi->audio.rate = params->sample_rate; + hdmi->audio.channels = params->cea.channels; + hdmi->audio.enabled = true; return msm_hdmi_audio_update(hdmi); } -void msm_hdmi_audio_set_sample_rate(struct hdmi *hdmi, int rate) +void msm_hdmi_bridge_audio_shutdown(struct drm_connector *connector, + struct drm_bridge *bridge) { - struct hdmi_audio *audio; - - if (!hdmi) - return; + struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); + struct hdmi *hdmi = hdmi_bridge->hdmi; - audio = &hdmi->audio; + drm_atomic_helper_connector_hdmi_clear_audio_infoframe(connector); - if ((rate < 0) || (rate >= MSM_HDMI_SAMPLE_RATE_MAX)) - return; + hdmi->audio.rate = 0; + hdmi->audio.channels = 2; + hdmi->audio.enabled = false; - audio->rate = rate; msm_hdmi_audio_update(hdmi); } diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c b/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c index 4a5b5112227f..53a7ce8cc7bc 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_bridge.c @@ -7,6 +7,8 @@ #include <linux/delay.h> #include <drm/drm_bridge_connector.h> #include <drm/drm_edid.h> +#include <drm/display/drm_hdmi_helper.h> +#include <drm/display/drm_hdmi_state_helper.h> #include "msm_kms.h" #include "hdmi.h" @@ -16,75 +18,53 @@ static void msm_hdmi_power_on(struct drm_bridge *bridge) struct drm_device *dev = bridge->dev; struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); struct hdmi *hdmi = hdmi_bridge->hdmi; - const struct hdmi_platform_config *config = hdmi->config; - int i, ret; - - pm_runtime_get_sync(&hdmi->pdev->dev); + int ret; - ret = regulator_bulk_enable(config->pwr_reg_cnt, hdmi->pwr_regs); - if (ret) - DRM_DEV_ERROR(dev->dev, "failed to enable pwr regulator: %d\n", ret); + pm_runtime_resume_and_get(&hdmi->pdev->dev); - if (config->pwr_clk_cnt > 0) { + if (hdmi->extp_clk) { DBG("pixclock: %lu", hdmi->pixclock); - ret = clk_set_rate(hdmi->pwr_clks[0], hdmi->pixclock); - if (ret) { - DRM_DEV_ERROR(dev->dev, "failed to set pixel clk: %s (%d)\n", - config->pwr_clk_names[0], ret); - } - } + ret = clk_set_rate(hdmi->extp_clk, hdmi->pixclock); + if (ret) + DRM_DEV_ERROR(dev->dev, "failed to set extp clk rate: %d\n", ret); - for (i = 0; i < config->pwr_clk_cnt; i++) { - ret = clk_prepare_enable(hdmi->pwr_clks[i]); - if (ret) { - DRM_DEV_ERROR(dev->dev, "failed to enable pwr clk: %s (%d)\n", - config->pwr_clk_names[i], ret); - } + ret = clk_prepare_enable(hdmi->extp_clk); + if (ret) + DRM_DEV_ERROR(dev->dev, "failed to enable extp clk: %d\n", ret); } } static void power_off(struct drm_bridge *bridge) { - struct drm_device *dev = bridge->dev; struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); struct hdmi *hdmi = hdmi_bridge->hdmi; - const struct hdmi_platform_config *config = hdmi->config; - int i, ret; /* TODO do we need to wait for final vblank somewhere before * cutting the clocks? */ mdelay(16 + 4); - for (i = 0; i < config->pwr_clk_cnt; i++) - clk_disable_unprepare(hdmi->pwr_clks[i]); - - ret = regulator_bulk_disable(config->pwr_reg_cnt, hdmi->pwr_regs); - if (ret) - DRM_DEV_ERROR(dev->dev, "failed to disable pwr regulator: %d\n", ret); + if (hdmi->extp_clk) + clk_disable_unprepare(hdmi->extp_clk); pm_runtime_put(&hdmi->pdev->dev); } #define AVI_IFRAME_LINE_NUMBER 1 +#define SPD_IFRAME_LINE_NUMBER 1 +#define VENSPEC_IFRAME_LINE_NUMBER 3 -static void msm_hdmi_config_avi_infoframe(struct hdmi *hdmi) +static int msm_hdmi_config_avi_infoframe(struct hdmi *hdmi, + const u8 *buffer, size_t len) { - struct drm_crtc *crtc = hdmi->encoder->crtc; - const struct drm_display_mode *mode = &crtc->state->adjusted_mode; - union hdmi_infoframe frame; - u8 buffer[HDMI_INFOFRAME_SIZE(AVI)]; + u32 buf[4] = {}; u32 val; - int len; - - drm_hdmi_avi_infoframe_from_display_mode(&frame.avi, - hdmi->connector, mode); + int i; - len = hdmi_infoframe_pack(&frame, buffer, sizeof(buffer)); - if (len < 0) { + if (len != HDMI_INFOFRAME_SIZE(AVI) || len - 3 > sizeof(buf)) { DRM_DEV_ERROR(&hdmi->pdev->dev, "failed to configure avi infoframe\n"); - return; + return -EINVAL; } /* @@ -93,56 +73,247 @@ static void msm_hdmi_config_avi_infoframe(struct hdmi *hdmi) * written to the LSB byte of AVI_INFO0 and the version is written to * the third byte from the LSB of AVI_INFO3 */ - hdmi_write(hdmi, REG_HDMI_AVI_INFO(0), + memcpy(buf, &buffer[3], len - 3); + + buf[3] |= buffer[1] << 24; + + for (i = 0; i < ARRAY_SIZE(buf); i++) + hdmi_write(hdmi, REG_HDMI_AVI_INFO(i), buf[i]); + + val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL1); + val |= HDMI_INFOFRAME_CTRL0_AVI_SEND | + HDMI_INFOFRAME_CTRL0_AVI_CONT; + hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL0, val); + + val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL1); + val &= ~HDMI_INFOFRAME_CTRL1_AVI_INFO_LINE__MASK; + val |= HDMI_INFOFRAME_CTRL1_AVI_INFO_LINE(AVI_IFRAME_LINE_NUMBER); + hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL1, val); + + return 0; +} + +static int msm_hdmi_config_audio_infoframe(struct hdmi *hdmi, + const u8 *buffer, size_t len) +{ + u32 val; + + if (len != HDMI_INFOFRAME_SIZE(AUDIO)) { + DRM_DEV_ERROR(&hdmi->pdev->dev, + "failed to configure audio infoframe\n"); + return -EINVAL; + } + + hdmi_write(hdmi, REG_HDMI_AUDIO_INFO0, buffer[3] | buffer[4] << 8 | buffer[5] << 16 | buffer[6] << 24); - hdmi_write(hdmi, REG_HDMI_AVI_INFO(1), + hdmi_write(hdmi, REG_HDMI_AUDIO_INFO1, buffer[7] | buffer[8] << 8 | buffer[9] << 16 | buffer[10] << 24); - hdmi_write(hdmi, REG_HDMI_AVI_INFO(2), - buffer[11] | - buffer[12] << 8 | - buffer[13] << 16 | - buffer[14] << 24); + val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL1); + val |= HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SEND | + HDMI_INFOFRAME_CTRL0_AUDIO_INFO_CONT | + HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SOURCE | + HDMI_INFOFRAME_CTRL0_AUDIO_INFO_UPDATE; + hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL0, val); - hdmi_write(hdmi, REG_HDMI_AVI_INFO(3), - buffer[15] | - buffer[16] << 8 | - buffer[1] << 24); + return 0; +} - hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL0, - HDMI_INFOFRAME_CTRL0_AVI_SEND | - HDMI_INFOFRAME_CTRL0_AVI_CONT); +static int msm_hdmi_config_spd_infoframe(struct hdmi *hdmi, + const u8 *buffer, size_t len) +{ + u32 buf[7] = {}; + u32 val; + int i; - val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL1); - val &= ~HDMI_INFOFRAME_CTRL1_AVI_INFO_LINE__MASK; - val |= HDMI_INFOFRAME_CTRL1_AVI_INFO_LINE(AVI_IFRAME_LINE_NUMBER); - hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL1, val); + if (len != HDMI_INFOFRAME_SIZE(SPD) || len - 3 > sizeof(buf)) { + DRM_DEV_ERROR(&hdmi->pdev->dev, + "failed to configure SPD infoframe\n"); + return -EINVAL; + } + + /* checksum gets written together with the body of the frame */ + hdmi_write(hdmi, REG_HDMI_GENERIC1_HDR, + buffer[0] | + buffer[1] << 8 | + buffer[2] << 16); + + memcpy(buf, &buffer[3], len - 3); + + for (i = 0; i < ARRAY_SIZE(buf); i++) + hdmi_write(hdmi, REG_HDMI_GENERIC1(i), buf[i]); + + val = hdmi_read(hdmi, REG_HDMI_GEN_PKT_CTRL); + val |= HDMI_GEN_PKT_CTRL_GENERIC1_SEND | + HDMI_GEN_PKT_CTRL_GENERIC1_CONT | + HDMI_GEN_PKT_CTRL_GENERIC1_LINE(SPD_IFRAME_LINE_NUMBER); + hdmi_write(hdmi, REG_HDMI_GEN_PKT_CTRL, val); + + return 0; } -static void msm_hdmi_bridge_pre_enable(struct drm_bridge *bridge) +static int msm_hdmi_config_hdmi_infoframe(struct hdmi *hdmi, + const u8 *buffer, size_t len) +{ + u32 buf[7] = {}; + u32 val; + int i; + + if (len < HDMI_INFOFRAME_HEADER_SIZE + HDMI_VENDOR_INFOFRAME_SIZE || + len - 3 > sizeof(buf)) { + DRM_DEV_ERROR(&hdmi->pdev->dev, + "failed to configure HDMI infoframe\n"); + return -EINVAL; + } + + /* checksum gets written together with the body of the frame */ + hdmi_write(hdmi, REG_HDMI_GENERIC0_HDR, + buffer[0] | + buffer[1] << 8 | + buffer[2] << 16); + + memcpy(buf, &buffer[3], len - 3); + + for (i = 0; i < ARRAY_SIZE(buf); i++) + hdmi_write(hdmi, REG_HDMI_GENERIC0(i), buf[i]); + + val = hdmi_read(hdmi, REG_HDMI_GEN_PKT_CTRL); + val |= HDMI_GEN_PKT_CTRL_GENERIC0_SEND | + HDMI_GEN_PKT_CTRL_GENERIC0_CONT | + HDMI_GEN_PKT_CTRL_GENERIC0_UPDATE | + HDMI_GEN_PKT_CTRL_GENERIC0_LINE(VENSPEC_IFRAME_LINE_NUMBER); + hdmi_write(hdmi, REG_HDMI_GEN_PKT_CTRL, val); + + return 0; +} + +static int msm_hdmi_bridge_clear_infoframe(struct drm_bridge *bridge, + enum hdmi_infoframe_type type) +{ + struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); + struct hdmi *hdmi = hdmi_bridge->hdmi; + u32 val; + + switch (type) { + case HDMI_INFOFRAME_TYPE_AVI: + val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL0); + val &= ~(HDMI_INFOFRAME_CTRL0_AVI_SEND | + HDMI_INFOFRAME_CTRL0_AVI_CONT); + hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL0, val); + + val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL1); + val &= ~HDMI_INFOFRAME_CTRL1_AVI_INFO_LINE__MASK; + hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL1, val); + + break; + + case HDMI_INFOFRAME_TYPE_AUDIO: + val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL0); + val &= ~(HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SEND | + HDMI_INFOFRAME_CTRL0_AUDIO_INFO_CONT | + HDMI_INFOFRAME_CTRL0_AUDIO_INFO_SOURCE | + HDMI_INFOFRAME_CTRL0_AUDIO_INFO_UPDATE); + hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL0, val); + + val = hdmi_read(hdmi, REG_HDMI_INFOFRAME_CTRL1); + val &= ~HDMI_INFOFRAME_CTRL1_AUDIO_INFO_LINE__MASK; + hdmi_write(hdmi, REG_HDMI_INFOFRAME_CTRL1, val); + + break; + + case HDMI_INFOFRAME_TYPE_SPD: + val = hdmi_read(hdmi, REG_HDMI_GEN_PKT_CTRL); + val &= ~(HDMI_GEN_PKT_CTRL_GENERIC1_SEND | + HDMI_GEN_PKT_CTRL_GENERIC1_CONT | + HDMI_GEN_PKT_CTRL_GENERIC1_LINE__MASK); + hdmi_write(hdmi, REG_HDMI_GEN_PKT_CTRL, val); + + break; + + case HDMI_INFOFRAME_TYPE_VENDOR: + val = hdmi_read(hdmi, REG_HDMI_GEN_PKT_CTRL); + val &= ~(HDMI_GEN_PKT_CTRL_GENERIC0_SEND | + HDMI_GEN_PKT_CTRL_GENERIC0_CONT | + HDMI_GEN_PKT_CTRL_GENERIC0_UPDATE | + HDMI_GEN_PKT_CTRL_GENERIC0_LINE__MASK); + hdmi_write(hdmi, REG_HDMI_GEN_PKT_CTRL, val); + + break; + + default: + drm_dbg_driver(hdmi_bridge->base.dev, "Unsupported infoframe type %x\n", type); + } + + return 0; +} + +static int msm_hdmi_bridge_write_infoframe(struct drm_bridge *bridge, + enum hdmi_infoframe_type type, + const u8 *buffer, size_t len) +{ + struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); + struct hdmi *hdmi = hdmi_bridge->hdmi; + + msm_hdmi_bridge_clear_infoframe(bridge, type); + + switch (type) { + case HDMI_INFOFRAME_TYPE_AVI: + return msm_hdmi_config_avi_infoframe(hdmi, buffer, len); + case HDMI_INFOFRAME_TYPE_AUDIO: + return msm_hdmi_config_audio_infoframe(hdmi, buffer, len); + case HDMI_INFOFRAME_TYPE_SPD: + return msm_hdmi_config_spd_infoframe(hdmi, buffer, len); + case HDMI_INFOFRAME_TYPE_VENDOR: + return msm_hdmi_config_hdmi_infoframe(hdmi, buffer, len); + default: + drm_dbg_driver(hdmi_bridge->base.dev, "Unsupported infoframe type %x\n", type); + return 0; + } +} + +static void msm_hdmi_set_timings(struct hdmi *hdmi, + const struct drm_display_mode *mode); + +static void msm_hdmi_bridge_atomic_pre_enable(struct drm_bridge *bridge, + struct drm_atomic_state *state) { struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); struct hdmi *hdmi = hdmi_bridge->hdmi; struct hdmi_phy *phy = hdmi->phy; + struct drm_encoder *encoder = bridge->encoder; + struct drm_connector *connector; + struct drm_connector_state *conn_state; + struct drm_crtc_state *crtc_state; DBG("power up"); + connector = drm_atomic_get_new_connector_for_encoder(state, encoder); + conn_state = drm_atomic_get_new_connector_state(state, connector); + crtc_state = drm_atomic_get_new_crtc_state(state, conn_state->crtc); + + hdmi->pixclock = conn_state->hdmi.tmds_char_rate; + + msm_hdmi_set_timings(hdmi, &crtc_state->adjusted_mode); + + mutex_lock(&hdmi->state_mutex); if (!hdmi->power_on) { msm_hdmi_phy_resource_enable(phy); msm_hdmi_power_on(bridge); hdmi->power_on = true; - if (hdmi->hdmi_mode) { - msm_hdmi_config_avi_infoframe(hdmi); - msm_hdmi_audio_update(hdmi); - } } + mutex_unlock(&hdmi->state_mutex); + + if (connector->display_info.is_hdmi) + msm_hdmi_audio_update(hdmi); + + drm_atomic_helper_connector_hdmi_update_infoframes(connector, state); msm_hdmi_phy_powerup(phy, hdmi->pixclock); @@ -152,7 +323,8 @@ static void msm_hdmi_bridge_pre_enable(struct drm_bridge *bridge) msm_hdmi_hdcp_on(hdmi->hdcp_ctrl); } -static void msm_hdmi_bridge_post_disable(struct drm_bridge *bridge) +static void msm_hdmi_bridge_atomic_post_disable(struct drm_bridge *bridge, + struct drm_atomic_state *state) { struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); struct hdmi *hdmi = hdmi_bridge->hdmi; @@ -162,32 +334,29 @@ static void msm_hdmi_bridge_post_disable(struct drm_bridge *bridge) msm_hdmi_hdcp_off(hdmi->hdcp_ctrl); DBG("power down"); - msm_hdmi_set_mode(hdmi, false); + + /* Keep the HDMI enabled if the HPD is enabled */ + mutex_lock(&hdmi->state_mutex); + msm_hdmi_set_mode(hdmi, hdmi->hpd_enabled); msm_hdmi_phy_powerdown(phy); if (hdmi->power_on) { power_off(bridge); hdmi->power_on = false; - if (hdmi->hdmi_mode) + if (hdmi->connector->display_info.is_hdmi) msm_hdmi_audio_update(hdmi); msm_hdmi_phy_resource_disable(phy); } + mutex_unlock(&hdmi->state_mutex); } -static void msm_hdmi_bridge_mode_set(struct drm_bridge *bridge, - const struct drm_display_mode *mode, - const struct drm_display_mode *adjusted_mode) +static void msm_hdmi_set_timings(struct hdmi *hdmi, + const struct drm_display_mode *mode) { - struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); - struct hdmi *hdmi = hdmi_bridge->hdmi; int hstart, hend, vstart, vend; uint32_t frame_ctrl; - mode = adjusted_mode; - - hdmi->pixclock = mode->clock * 1000; - hstart = mode->htotal - mode->hsync_start; hend = mode->htotal - mode->hsync_start + mode->hdisplay; @@ -231,9 +400,6 @@ static void msm_hdmi_bridge_mode_set(struct drm_bridge *bridge, frame_ctrl |= HDMI_FRAME_CTRL_INTERLACED_EN; DBG("frame_ctrl=%08x", frame_ctrl); hdmi_write(hdmi, REG_HDMI_FRAME_CTRL, frame_ctrl); - - if (hdmi->hdmi_mode) - msm_hdmi_audio_update(hdmi); } static const struct drm_edid *msm_hdmi_bridge_edid_read(struct drm_bridge *bridge, @@ -251,32 +417,18 @@ static const struct drm_edid *msm_hdmi_bridge_edid_read(struct drm_bridge *bridg hdmi_write(hdmi, REG_HDMI_CTRL, hdmi_ctrl); - if (drm_edid) { - /* - * FIXME: This should use connector->display_info.is_hdmi from a - * path that has read the EDID and called - * drm_edid_connector_update(). - */ - const struct edid *edid = drm_edid_raw(drm_edid); - - hdmi->hdmi_mode = drm_detect_hdmi_monitor(edid); - } - return drm_edid; } -static enum drm_mode_status msm_hdmi_bridge_mode_valid(struct drm_bridge *bridge, - const struct drm_display_info *info, - const struct drm_display_mode *mode) +static enum drm_mode_status msm_hdmi_bridge_tmds_char_rate_valid(const struct drm_bridge *bridge, + const struct drm_display_mode *mode, + unsigned long long tmds_rate) { struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); struct hdmi *hdmi = hdmi_bridge->hdmi; - const struct hdmi_platform_config *config = hdmi->config; struct msm_drm_private *priv = bridge->dev->dev_private; struct msm_kms *kms = priv->kms; - long actual, requested; - - requested = 1000 * mode->clock; + long actual; /* for mdp5/apq8074, we manage our own pixel clk (as opposed to * mdp4/dtv stuff where pixel clk is assigned to mdp/encoder @@ -284,27 +436,36 @@ static enum drm_mode_status msm_hdmi_bridge_mode_valid(struct drm_bridge *bridge */ if (kms->funcs->round_pixclk) actual = kms->funcs->round_pixclk(kms, - requested, hdmi_bridge->hdmi->encoder); - else if (config->pwr_clk_cnt > 0) - actual = clk_round_rate(hdmi->pwr_clks[0], requested); + tmds_rate, + hdmi_bridge->hdmi->encoder); + else if (hdmi->extp_clk) + actual = clk_round_rate(hdmi->extp_clk, tmds_rate); else - actual = requested; + actual = tmds_rate; - DBG("requested=%ld, actual=%ld", requested, actual); + DBG("requested=%lld, actual=%ld", tmds_rate, actual); - if (actual != requested) + if (actual != tmds_rate) return MODE_CLOCK_RANGE; return 0; } static const struct drm_bridge_funcs msm_hdmi_bridge_funcs = { - .pre_enable = msm_hdmi_bridge_pre_enable, - .post_disable = msm_hdmi_bridge_post_disable, - .mode_set = msm_hdmi_bridge_mode_set, - .mode_valid = msm_hdmi_bridge_mode_valid, + .atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state, + .atomic_destroy_state = drm_atomic_helper_bridge_destroy_state, + .atomic_reset = drm_atomic_helper_bridge_reset, + .atomic_pre_enable = msm_hdmi_bridge_atomic_pre_enable, + .atomic_post_disable = msm_hdmi_bridge_atomic_post_disable, .edid_read = msm_hdmi_bridge_edid_read, .detect = msm_hdmi_bridge_detect, + .hpd_enable = msm_hdmi_hpd_enable, + .hpd_disable = msm_hdmi_hpd_disable, + .hdmi_tmds_char_rate_valid = msm_hdmi_bridge_tmds_char_rate_valid, + .hdmi_clear_infoframe = msm_hdmi_bridge_clear_infoframe, + .hdmi_write_infoframe = msm_hdmi_bridge_write_infoframe, + .hdmi_audio_prepare = msm_hdmi_bridge_audio_prepare, + .hdmi_audio_shutdown = msm_hdmi_bridge_audio_shutdown, }; static void @@ -324,21 +485,27 @@ int msm_hdmi_bridge_init(struct hdmi *hdmi) struct hdmi_bridge *hdmi_bridge; int ret; - hdmi_bridge = devm_kzalloc(hdmi->dev->dev, - sizeof(*hdmi_bridge), GFP_KERNEL); - if (!hdmi_bridge) - return -ENOMEM; + hdmi_bridge = devm_drm_bridge_alloc(hdmi->dev->dev, struct hdmi_bridge, base, + &msm_hdmi_bridge_funcs); + if (IS_ERR(hdmi_bridge)) + return PTR_ERR(hdmi_bridge); hdmi_bridge->hdmi = hdmi; INIT_WORK(&hdmi_bridge->hpd_work, msm_hdmi_hotplug_work); bridge = &hdmi_bridge->base; - bridge->funcs = &msm_hdmi_bridge_funcs; bridge->ddc = hdmi->i2c; bridge->type = DRM_MODE_CONNECTOR_HDMIA; + bridge->vendor = "Qualcomm"; + bridge->product = "Snapdragon"; bridge->ops = DRM_BRIDGE_OP_HPD | DRM_BRIDGE_OP_DETECT | + DRM_BRIDGE_OP_HDMI | + DRM_BRIDGE_OP_HDMI_AUDIO | DRM_BRIDGE_OP_EDID; + bridge->hdmi_audio_max_i2s_playback_channels = 8; + bridge->hdmi_audio_dev = &hdmi->pdev->dev; + bridge->hdmi_audio_dai_port = -1; ret = devm_drm_bridge_add(hdmi->dev->dev, bridge); if (ret) diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_hpd.c b/drivers/gpu/drm/msm/hdmi/hdmi_hpd.c index 9ce0ffa35417..407e6c449ee0 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_hpd.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_hpd.c @@ -60,68 +60,30 @@ static void msm_hdmi_phy_reset(struct hdmi *hdmi) } } -static void enable_hpd_clocks(struct hdmi *hdmi, bool enable) -{ - const struct hdmi_platform_config *config = hdmi->config; - struct device *dev = &hdmi->pdev->dev; - int i, ret; - - if (enable) { - for (i = 0; i < config->hpd_clk_cnt; i++) { - if (config->hpd_freq && config->hpd_freq[i]) { - ret = clk_set_rate(hdmi->hpd_clks[i], - config->hpd_freq[i]); - if (ret) - dev_warn(dev, - "failed to set clk %s (%d)\n", - config->hpd_clk_names[i], ret); - } - - ret = clk_prepare_enable(hdmi->hpd_clks[i]); - if (ret) { - DRM_DEV_ERROR(dev, - "failed to enable hpd clk: %s (%d)\n", - config->hpd_clk_names[i], ret); - } - } - } else { - for (i = config->hpd_clk_cnt - 1; i >= 0; i--) - clk_disable_unprepare(hdmi->hpd_clks[i]); - } -} - -int msm_hdmi_hpd_enable(struct drm_bridge *bridge) +void msm_hdmi_hpd_enable(struct drm_bridge *bridge) { struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); struct hdmi *hdmi = hdmi_bridge->hdmi; - const struct hdmi_platform_config *config = hdmi->config; struct device *dev = &hdmi->pdev->dev; uint32_t hpd_ctrl; int ret; unsigned long flags; - ret = regulator_bulk_enable(config->hpd_reg_cnt, hdmi->hpd_regs); - if (ret) { - DRM_DEV_ERROR(dev, "failed to enable hpd regulators: %d\n", ret); - goto fail; - } - - ret = pinctrl_pm_select_default_state(dev); - if (ret) { - DRM_DEV_ERROR(dev, "pinctrl state chg failed: %d\n", ret); - goto fail; - } - if (hdmi->hpd_gpiod) gpiod_set_value_cansleep(hdmi->hpd_gpiod, 1); - pm_runtime_get_sync(dev); - enable_hpd_clocks(hdmi, true); + ret = pm_runtime_resume_and_get(dev); + if (WARN_ON(ret)) + return; + mutex_lock(&hdmi->state_mutex); msm_hdmi_set_mode(hdmi, false); msm_hdmi_phy_reset(hdmi); msm_hdmi_set_mode(hdmi, true); + hdmi->hpd_enabled = true; + mutex_unlock(&hdmi->state_mutex); + hdmi_write(hdmi, REG_HDMI_USEC_REFTIMER, 0x0001001b); /* enable HPD events: */ @@ -140,34 +102,23 @@ int msm_hdmi_hpd_enable(struct drm_bridge *bridge) hdmi_write(hdmi, REG_HDMI_HPD_CTRL, HDMI_HPD_CTRL_ENABLE | hpd_ctrl); spin_unlock_irqrestore(&hdmi->reg_lock, flags); - - return 0; - -fail: - return ret; } -void msm_hdmi_hpd_disable(struct hdmi *hdmi) +void msm_hdmi_hpd_disable(struct drm_bridge *bridge) { - const struct hdmi_platform_config *config = hdmi->config; + struct hdmi_bridge *hdmi_bridge = to_hdmi_bridge(bridge); + struct hdmi *hdmi = hdmi_bridge->hdmi; struct device *dev = &hdmi->pdev->dev; - int ret; /* Disable HPD interrupt */ hdmi_write(hdmi, REG_HDMI_HPD_INT_CTRL, 0); - msm_hdmi_set_mode(hdmi, false); + mutex_lock(&hdmi->state_mutex); + hdmi->hpd_enabled = false; + msm_hdmi_set_mode(hdmi, hdmi->power_on); + mutex_unlock(&hdmi->state_mutex); - enable_hpd_clocks(hdmi, false); pm_runtime_put(dev); - - ret = pinctrl_pm_select_sleep_state(dev); - if (ret) - dev_warn(dev, "pinctrl state chg failed: %d\n", ret); - - ret = regulator_bulk_disable(config->hpd_reg_cnt, hdmi->hpd_regs); - if (ret) - dev_warn(dev, "failed to disable hpd regulator: %d\n", ret); } void msm_hdmi_hpd_irq(struct drm_bridge *bridge) @@ -202,14 +153,16 @@ void msm_hdmi_hpd_irq(struct drm_bridge *bridge) static enum drm_connector_status detect_reg(struct hdmi *hdmi) { - uint32_t hpd_int_status; + u32 hpd_int_status = 0; + int ret; - pm_runtime_get_sync(&hdmi->pdev->dev); - enable_hpd_clocks(hdmi, true); + ret = pm_runtime_resume_and_get(&hdmi->pdev->dev); + if (ret) + goto out; hpd_int_status = hdmi_read(hdmi, REG_HDMI_HPD_INT_STATUS); - enable_hpd_clocks(hdmi, false); +out: pm_runtime_put(&hdmi->pdev->dev); return (hpd_int_status & HDMI_HPD_INT_STATUS_CABLE_DETECTED) ? diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_i2c.c b/drivers/gpu/drm/msm/hdmi/hdmi_i2c.c index 7aa500d24240..ebefea4fb408 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_i2c.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_i2c.c @@ -107,11 +107,15 @@ static int msm_hdmi_i2c_xfer(struct i2c_adapter *i2c, if (num == 0) return num; + ret = pm_runtime_resume_and_get(&hdmi->pdev->dev); + if (ret) + return ret; + init_ddc(hdmi_i2c); ret = ddc_clear_irq(hdmi_i2c); if (ret) - return ret; + goto fail; for (i = 0; i < num; i++) { struct i2c_msg *p = &msgs[i]; @@ -169,7 +173,7 @@ static int msm_hdmi_i2c_xfer(struct i2c_adapter *i2c, hdmi_read(hdmi, REG_HDMI_DDC_SW_STATUS), hdmi_read(hdmi, REG_HDMI_DDC_HW_STATUS), hdmi_read(hdmi, REG_HDMI_DDC_INT_CTRL)); - return ret; + goto fail; } ddc_status = hdmi_read(hdmi, REG_HDMI_DDC_SW_STATUS); @@ -202,7 +206,13 @@ static int msm_hdmi_i2c_xfer(struct i2c_adapter *i2c, } } + pm_runtime_put(&hdmi->pdev->dev); + return i; + +fail: + pm_runtime_put(&hdmi->pdev->dev); + return ret; } static u32 msm_hdmi_i2c_func(struct i2c_adapter *adapter) diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_phy.c b/drivers/gpu/drm/msm/hdmi/hdmi_phy.c index 03120c54ced6..667573f1db7c 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_phy.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_phy.c @@ -58,7 +58,11 @@ int msm_hdmi_phy_resource_enable(struct hdmi_phy *phy) struct device *dev = &phy->pdev->dev; int i, ret = 0; - pm_runtime_get_sync(dev); + ret = pm_runtime_resume_and_get(dev); + if (ret) { + DRM_DEV_ERROR(dev, "runtime resume failed: %d\n", ret); + return ret; + } ret = regulator_bulk_enable(cfg->num_regs, phy->regs); if (ret) { diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c index 9c45d641b521..87a91148a731 100644 --- a/drivers/gpu/drm/msm/msm_atomic.c +++ b/drivers/gpu/drm/msm/msm_atomic.c @@ -115,7 +115,7 @@ int msm_atomic_init_pending_timer(struct msm_pending_timer *timer, timer->kms = kms; timer->crtc_idx = crtc_idx; - timer->worker = kthread_create_worker(0, "atomic-worker-%d", crtc_idx); + timer->worker = kthread_run_worker(0, "atomic-worker-%d", crtc_idx); if (IS_ERR(timer->worker)) { int ret = PTR_ERR(timer->worker); timer->worker = NULL; @@ -183,10 +183,16 @@ static unsigned get_crtc_mask(struct drm_atomic_state *state) int msm_atomic_check(struct drm_device *dev, struct drm_atomic_state *state) { + struct msm_drm_private *priv = dev->dev_private; + struct msm_kms *kms = priv->kms; struct drm_crtc_state *old_crtc_state, *new_crtc_state; struct drm_crtc *crtc; - int i; + int i, ret = 0; + /* + * FIXME: stop setting allow_modeset and move this check to the DPU + * driver. + */ for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { if ((old_crtc_state->ctm && !new_crtc_state->ctm) || @@ -196,6 +202,11 @@ int msm_atomic_check(struct drm_device *dev, struct drm_atomic_state *state) } } + if (kms && kms->funcs && kms->funcs->check_mode_changed) + ret = kms->funcs->check_mode_changed(kms, state); + if (ret) + return ret; + return drm_atomic_helper_check(dev, state); } @@ -221,6 +232,8 @@ void msm_atomic_commit_tail(struct drm_atomic_state *state) kms->funcs->wait_flush(kms, crtc_mask); trace_msm_atomic_wait_flush_finish(crtc_mask); + atomic_set(&kms->fault_snapshot_capture, 0); + /* * Now that there is no in-progress flush, prepare the * current update: diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c index 7ab607252d18..6af72162cda4 100644 --- a/drivers/gpu/drm/msm/msm_debugfs.c +++ b/drivers/gpu/drm/msm/msm_debugfs.c @@ -208,6 +208,35 @@ DEFINE_DEBUGFS_ATTRIBUTE(shrink_fops, shrink_get, shrink_set, "0x%08llx\n"); +/* + * Return the number of microseconds to wait until stall-on-fault is + * re-enabled. If 0 then it is already enabled or will be re-enabled on the + * next submit (unless there's a leftover devcoredump). This is useful for + * kernel tests that intentionally produce a fault and check the devcoredump to + * wait until the cooldown period is over. + */ + +static int +stall_reenable_time_get(void *data, u64 *val) +{ + struct msm_drm_private *priv = data; + unsigned long irq_flags; + + spin_lock_irqsave(&priv->fault_stall_lock, irq_flags); + + if (priv->stall_enabled) + *val = 0; + else + *val = max(ktime_us_delta(priv->stall_reenable_time, ktime_get()), 0); + + spin_unlock_irqrestore(&priv->fault_stall_lock, irq_flags); + + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(stall_reenable_time_fops, + stall_reenable_time_get, NULL, + "%lld\n"); static int msm_gem_show(struct seq_file *m, void *arg) { @@ -319,6 +348,9 @@ static void msm_debugfs_gpu_init(struct drm_minor *minor) debugfs_create_bool("disable_err_irq", 0600, minor->debugfs_root, &priv->disable_err_irq); + debugfs_create_file("stall_reenable_time_us", 0400, minor->debugfs_root, + priv, &stall_reenable_time_fops); + gpu_devfreq = debugfs_create_dir("devfreq", minor->debugfs_root); debugfs_create_bool("idle_clamp",0600, gpu_devfreq, diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index ffbcc97b5018..f0d016ce8e11 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -11,7 +11,7 @@ #include <linux/of_address.h> #include <linux/uaccess.h> -#include <drm/drm_client_setup.h> +#include <drm/clients/drm_client_setup.h> #include <drm/drm_drv.h> #include <drm/drm_file.h> #include <drm/drm_ioctl.h> @@ -245,6 +245,10 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv) drm_gem_lru_init(&priv->lru.willneed, &priv->lru.lock); drm_gem_lru_init(&priv->lru.dontneed, &priv->lru.lock); + /* Initialize stall-on-fault */ + spin_lock_init(&priv->fault_stall_lock); + priv->stall_enabled = true; + /* Teach lockdep about lock ordering wrt. shrinker: */ fs_reclaim_acquire(GFP_KERNEL); might_lock(&priv->lru.lock); @@ -538,7 +542,7 @@ static int msm_ioctl_gem_info_set_iova(struct drm_device *dev, /* Only supported if per-process address space is supported: */ if (priv->gpu->aspace == ctx->aspace) - return -EOPNOTSUPP; + return UERR(EOPNOTSUPP, dev, "requires per-process pgtables"); if (should_fail(&fail_gem_iova, obj->size)) return -ENOMEM; @@ -551,6 +555,7 @@ static int msm_ioctl_gem_info_set_metadata(struct drm_gem_object *obj, u32 metadata_size) { struct msm_gem_object *msm_obj = to_msm_bo(obj); + void *new_metadata; void *buf; int ret; @@ -568,8 +573,14 @@ static int msm_ioctl_gem_info_set_metadata(struct drm_gem_object *obj, if (ret) goto out; - msm_obj->metadata = + new_metadata = krealloc(msm_obj->metadata, metadata_size, GFP_KERNEL); + if (!new_metadata) { + ret = -ENOMEM; + goto out; + } + + msm_obj->metadata = new_metadata; msm_obj->metadata_size = metadata_size; memcpy(msm_obj->metadata, buf, metadata_size); @@ -671,7 +682,7 @@ static int msm_ioctl_gem_info(struct drm_device *dev, void *data, ret = msm_ioctl_gem_info_set_iova(dev, file, obj, args->value); break; case MSM_INFO_GET_FLAGS: - if (obj->import_attach) { + if (drm_gem_is_imported(obj)) { ret = -EINVAL; break; } @@ -894,6 +905,7 @@ static const struct drm_driver msm_driver = { DRIVER_RENDER | DRIVER_ATOMIC | DRIVER_MODESET | + DRIVER_SYNCOBJ_TIMELINE | DRIVER_SYNCOBJ, .open = msm_open, .postclose = msm_postclose, @@ -910,7 +922,6 @@ static const struct drm_driver msm_driver = { .fops = &fops, .name = "msm", .desc = "MSM Snapdragon DRM", - .date = "20130625", .major = MSM_VERSION_MAJOR, .minor = MSM_VERSION_MINOR, .patchlevel = MSM_VERSION_PATCHLEVEL, @@ -926,7 +937,7 @@ static const struct drm_driver msm_driver = { * is no external component that we need to add since LVDS is within MDP4 * itself. */ -static int add_components_mdp(struct device *master_dev, +static int add_mdp_components(struct device *master_dev, struct component_match **matchptr) { struct device_node *np = master_dev->of_node; @@ -1030,7 +1041,7 @@ static int add_gpu_components(struct device *dev, if (!np) return 0; - if (of_device_is_available(np)) + if (of_device_is_available(np) && adreno_has_gpu(np)) drm_of_component_match_add(dev, matchptr, component_compare_of, np); of_node_put(np); @@ -1071,7 +1082,7 @@ int msm_drv_probe(struct device *master_dev, /* Add mdp components if we have KMS. */ if (kms_init) { - ret = add_components_mdp(master_dev, &match); + ret = add_mdp_components(master_dev, &match); if (ret) return ret; } diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h index f15962cfb373..c8afb1ea6040 100644 --- a/drivers/gpu/drm/msm/msm_drv.h +++ b/drivers/gpu/drm/msm/msm_drv.h @@ -28,6 +28,7 @@ #include <drm/drm_atomic.h> #include <drm/drm_atomic_helper.h> +#include <drm/drm_print.h> #include <drm/drm_probe_helper.h> #include <drm/display/drm_dsc.h> #include <drm/msm_drm.h> @@ -221,6 +222,29 @@ struct msm_drm_private { * the sw hangcheck mechanism. */ bool disable_err_irq; + + /** + * @fault_stall_lock: + * + * Serialize changes to stall-on-fault state. + */ + spinlock_t fault_stall_lock; + + /** + * @fault_stall_reenable_time: + * + * If stall_enabled is false, when to reenable stall-on-fault. + * Protected by @fault_stall_lock. + */ + ktime_t stall_reenable_time; + + /** + * @stall_enabled: + * + * Whether stall-on-fault is currently enabled. Protected by + * @fault_stall_lock. + */ + bool stall_enabled; }; const struct msm_format *mdp_get_format(struct msm_kms *kms, uint32_t format, uint64_t modifier); @@ -506,6 +530,12 @@ void msm_hrtimer_work_init(struct msm_hrtimer_work *work, clockid_t clock_id, enum hrtimer_mode mode); +/* Helper for returning a UABI error with optional logging which can make + * it easier for userspace to understand what it is doing wrong. + */ +#define UERR(err, drm, fmt, ...) \ + ({ DRM_DEV_DEBUG_DRIVER((drm)->dev, fmt, ##__VA_ARGS__); -(err); }) + #define DBG(fmt, ...) DRM_DEBUG_DRIVER(fmt"\n", ##__VA_ARGS__) #define VERB(fmt, ...) if (0) DRM_DEBUG_DRIVER(fmt"\n", ##__VA_ARGS__) diff --git a/drivers/gpu/drm/msm/msm_dsc_helper.h b/drivers/gpu/drm/msm/msm_dsc_helper.h index b9049fe1e279..63f95523b2cb 100644 --- a/drivers/gpu/drm/msm/msm_dsc_helper.h +++ b/drivers/gpu/drm/msm/msm_dsc_helper.h @@ -13,17 +13,6 @@ #include <drm/display/drm_dsc_helper.h> /** - * msm_dsc_get_slices_per_intf() - calculate number of slices per interface - * @dsc: Pointer to drm dsc config struct - * @intf_width: interface width in pixels - * Returns: Integer representing the number of slices for the given interface - */ -static inline u32 msm_dsc_get_slices_per_intf(const struct drm_dsc_config *dsc, u32 intf_width) -{ - return DIV_ROUND_UP(intf_width, dsc->slice_width); -} - -/** * msm_dsc_get_bytes_per_line() - calculate bytes per line * @dsc: Pointer to drm dsc config struct * Returns: Integer value representing bytes per line. DSI and DP need diff --git a/drivers/gpu/drm/msm/msm_fence.c b/drivers/gpu/drm/msm/msm_fence.c index 1a5d4f1c8b42..d41e5a6bbee0 100644 --- a/drivers/gpu/drm/msm/msm_fence.c +++ b/drivers/gpu/drm/msm/msm_fence.c @@ -65,8 +65,7 @@ msm_fence_context_alloc(struct drm_device *dev, volatile uint32_t *fenceptr, fctx->completed_fence = fctx->last_fence; *fctx->fenceptr = fctx->last_fence; - hrtimer_init(&fctx->deadline_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); - fctx->deadline_timer.function = deadline_timer; + hrtimer_setup(&fctx->deadline_timer, deadline_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); kthread_init_work(&fctx->deadline_work, deadline_work); diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index ebc9ba66efb8..ebd8a3603359 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -735,7 +735,7 @@ static void *get_vaddr(struct drm_gem_object *obj, unsigned madv) msm_gem_assert_locked(obj); - if (obj->import_attach) + if (drm_gem_is_imported(obj)) return ERR_PTR(-ENODEV); pages = msm_gem_get_pages_locked(obj, madv); @@ -963,7 +963,8 @@ void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m, uint64_t off = drm_vma_node_start(&obj->vma_node); const char *madv; - msm_gem_lock(obj); + if (!msm_gem_trylock(obj)) + return; stats->all.count++; stats->all.size += obj->size; @@ -1074,7 +1075,7 @@ static void msm_gem_free_object(struct drm_gem_object *obj) put_iova_spaces(obj, true); - if (obj->import_attach) { + if (drm_gem_is_imported(obj)) { GEM_WARN_ON(msm_obj->vaddr); /* Don't drop the pages for imported dmabuf, as they are not diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h index 85f0257e83da..ea001b0a6b64 100644 --- a/drivers/gpu/drm/msm/msm_gem.h +++ b/drivers/gpu/drm/msm/msm_gem.h @@ -188,6 +188,12 @@ msm_gem_lock(struct drm_gem_object *obj) dma_resv_lock(obj->resv, NULL); } +static inline bool __must_check +msm_gem_trylock(struct drm_gem_object *obj) +{ + return dma_resv_trylock(obj->resv); +} + static inline int msm_gem_lock_interruptible(struct drm_gem_object *obj) { @@ -224,7 +230,7 @@ msm_gem_assert_locked(struct drm_gem_object *obj) /* imported/exported objects are not purgeable: */ static inline bool is_unpurgeable(struct msm_gem_object *msm_obj) { - return msm_obj->base.import_attach || msm_obj->pin_count; + return drm_gem_is_imported(&msm_obj->base) || msm_obj->pin_count; } static inline bool is_purgeable(struct msm_gem_object *msm_obj) diff --git a/drivers/gpu/drm/msm/msm_gem_prime.c b/drivers/gpu/drm/msm/msm_gem_prime.c index ee267490c935..2e37913d5a6a 100644 --- a/drivers/gpu/drm/msm/msm_gem_prime.c +++ b/drivers/gpu/drm/msm/msm_gem_prime.c @@ -50,7 +50,7 @@ int msm_gem_prime_pin(struct drm_gem_object *obj) struct page **pages; int ret = 0; - if (obj->import_attach) + if (drm_gem_is_imported(obj)) return 0; pages = msm_gem_pin_pages_locked(obj); @@ -62,7 +62,7 @@ int msm_gem_prime_pin(struct drm_gem_object *obj) void msm_gem_prime_unpin(struct drm_gem_object *obj) { - if (obj->import_attach) + if (drm_gem_is_imported(obj)) return; msm_gem_unpin_pages_locked(obj); diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index f775638d239a..d4f71bb54e84 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -20,8 +20,8 @@ /* For userspace errors, use DRM_UT_DRIVER.. so that userspace can enable * error msgs for debugging, but we don't spam dmesg by default */ -#define SUBMIT_ERROR(submit, fmt, ...) \ - DRM_DEV_DEBUG_DRIVER((submit)->dev->dev, fmt, ##__VA_ARGS__) +#define SUBMIT_ERROR(err, submit, fmt, ...) \ + UERR(err, (submit)->dev, fmt, ##__VA_ARGS__) /* * Cmdstream submission: @@ -85,6 +85,15 @@ void __msm_gem_submit_destroy(struct kref *kref) container_of(kref, struct msm_gem_submit, ref); unsigned i; + /* + * In error paths, we could unref the submit without calling + * drm_sched_entity_push_job(), so msm_job_free() will never + * get called. Since drm_sched_job_cleanup() will NULL out + * s_fence, we can use that to detect this case. + */ + if (submit->base.s_fence) + drm_sched_job_cleanup(&submit->base); + if (submit->fence_id) { spin_lock(&submit->queue->idr_lock); idr_remove(&submit->queue->fence_idr, submit->fence_id); @@ -142,8 +151,7 @@ static int submit_lookup_objects(struct msm_gem_submit *submit, if ((submit_bo.flags & ~MSM_SUBMIT_BO_FLAGS) || !(submit_bo.flags & MANDATORY_FLAGS)) { - SUBMIT_ERROR(submit, "invalid flags: %x\n", submit_bo.flags); - ret = -EINVAL; + ret = SUBMIT_ERROR(EINVAL, submit, "invalid flags: %x\n", submit_bo.flags); i = 0; goto out; } @@ -162,8 +170,7 @@ static int submit_lookup_objects(struct msm_gem_submit *submit, */ obj = idr_find(&file->object_idr, submit->bos[i].handle); if (!obj) { - SUBMIT_ERROR(submit, "invalid handle %u at index %u\n", submit->bos[i].handle, i); - ret = -EINVAL; + ret = SUBMIT_ERROR(EINVAL, submit, "invalid handle %u at index %u\n", submit->bos[i].handle, i); goto out_unlock; } @@ -206,14 +213,12 @@ static int submit_lookup_cmds(struct msm_gem_submit *submit, case MSM_SUBMIT_CMD_CTX_RESTORE_BUF: break; default: - SUBMIT_ERROR(submit, "invalid type: %08x\n", submit_cmd.type); - return -EINVAL; + return SUBMIT_ERROR(EINVAL, submit, "invalid type: %08x\n", submit_cmd.type); } if (submit_cmd.size % 4) { - SUBMIT_ERROR(submit, "non-aligned cmdstream buffer size: %u\n", - submit_cmd.size); - ret = -EINVAL; + ret = SUBMIT_ERROR(EINVAL, submit, "non-aligned cmdstream buffer size: %u\n", + submit_cmd.size); goto out; } @@ -371,9 +376,8 @@ static int submit_bo(struct msm_gem_submit *submit, uint32_t idx, struct drm_gem_object **obj, uint64_t *iova) { if (idx >= submit->nr_bos) { - SUBMIT_ERROR(submit, "invalid buffer index: %u (out of %u)\n", - idx, submit->nr_bos); - return -EINVAL; + return SUBMIT_ERROR(EINVAL, submit, "invalid buffer index: %u (out of %u)\n", + idx, submit->nr_bos); } if (obj) @@ -392,10 +396,8 @@ static int submit_reloc(struct msm_gem_submit *submit, struct drm_gem_object *ob uint32_t *ptr; int ret = 0; - if (offset % 4) { - SUBMIT_ERROR(submit, "non-aligned cmdstream buffer: %u\n", offset); - return -EINVAL; - } + if (offset % 4) + return SUBMIT_ERROR(EINVAL, submit, "non-aligned cmdstream buffer: %u\n", offset); /* For now, just map the entire thing. Eventually we probably * to do it page-by-page, w/ kmap() if not vmap()d.. @@ -414,9 +416,8 @@ static int submit_reloc(struct msm_gem_submit *submit, struct drm_gem_object *ob uint64_t iova; if (submit_reloc.submit_offset % 4) { - SUBMIT_ERROR(submit, "non-aligned reloc offset: %u\n", - submit_reloc.submit_offset); - ret = -EINVAL; + ret = SUBMIT_ERROR(EINVAL, submit, "non-aligned reloc offset: %u\n", + submit_reloc.submit_offset); goto out; } @@ -425,8 +426,7 @@ static int submit_reloc(struct msm_gem_submit *submit, struct drm_gem_object *ob if ((off >= (obj->size / 4)) || (off < last_offset)) { - SUBMIT_ERROR(submit, "invalid offset %u at reloc %u\n", off, i); - ret = -EINVAL; + ret = SUBMIT_ERROR(EINVAL, submit, "invalid offset %u at reloc %u\n", off, i); goto out; } @@ -513,12 +513,12 @@ static struct drm_syncobj **msm_parse_deps(struct msm_gem_submit *submit, if (syncobj_desc.point && !drm_core_check_feature(submit->dev, DRIVER_SYNCOBJ_TIMELINE)) { - ret = -EOPNOTSUPP; + ret = SUBMIT_ERROR(EOPNOTSUPP, submit, "syncobj timeline unsupported"); break; } if (syncobj_desc.flags & ~MSM_SUBMIT_SYNCOBJ_FLAGS) { - ret = -EINVAL; + ret = SUBMIT_ERROR(EINVAL, submit, "invalid syncobj flags: %x", syncobj_desc.flags); break; } @@ -531,7 +531,7 @@ static struct drm_syncobj **msm_parse_deps(struct msm_gem_submit *submit, syncobjs[i] = drm_syncobj_find(file, syncobj_desc.handle); if (!syncobjs[i]) { - ret = -EINVAL; + ret = SUBMIT_ERROR(EINVAL, submit, "invalid syncobj handle: %u", i); break; } } @@ -588,14 +588,14 @@ static struct msm_submit_post_dep *msm_parse_post_deps(struct drm_device *dev, post_deps[i].point = syncobj_desc.point; if (syncobj_desc.flags) { - ret = -EINVAL; + ret = UERR(EINVAL, dev, "invalid syncobj flags"); break; } if (syncobj_desc.point) { if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ_TIMELINE)) { - ret = -EOPNOTSUPP; + ret = UERR(EOPNOTSUPP, dev, "syncobj timeline unsupported"); break; } @@ -609,7 +609,7 @@ static struct msm_submit_post_dep *msm_parse_post_deps(struct drm_device *dev, post_deps[i].syncobj = drm_syncobj_find(file, syncobj_desc.handle); if (!post_deps[i].syncobj) { - ret = -EINVAL; + ret = UERR(EINVAL, dev, "invalid syncobj handle"); break; } } @@ -658,6 +658,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, struct msm_ringbuffer *ring; struct msm_submit_post_dep *post_deps = NULL; struct drm_syncobj **syncobjs_to_reset = NULL; + struct sync_file *sync_file = NULL; int out_fence_fd = -1; unsigned i; int ret; @@ -677,10 +678,10 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, * be more clever to dispatch to appropriate gpu module: */ if (MSM_PIPE_ID(args->flags) != MSM_PIPE_3D0) - return -EINVAL; + return UERR(EINVAL, dev, "invalid pipe"); if (MSM_PIPE_FLAGS(args->flags) & ~MSM_SUBMIT_FLAGS) - return -EINVAL; + return UERR(EINVAL, dev, "invalid flags"); if (args->flags & MSM_SUBMIT_SUDO) { if (!IS_ENABLED(CONFIG_DRM_MSM_GPU_SUDO) || @@ -724,7 +725,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, in_fence = sync_file_get_fence(args->fence_fd); if (!in_fence) { - ret = -EINVAL; + ret = UERR(EINVAL, dev, "invalid in-fence"); goto out_unlock; } @@ -788,8 +789,8 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, if (!submit->cmd[i].size || (size_add(submit->cmd[i].size, submit->cmd[i].offset) > obj->size / 4)) { - SUBMIT_ERROR(submit, "invalid cmdstream size: %u\n", submit->cmd[i].size * 4); - ret = -EINVAL; + ret = UERR(EINVAL, dev, "invalid cmdstream size: %u\n", + submit->cmd[i].size * 4); goto out; } @@ -799,8 +800,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, continue; if (!gpu->allow_relocs) { - SUBMIT_ERROR(submit, "relocs not allowed\n"); - ret = -EINVAL; + ret = UERR(EINVAL, dev, "relocs not allowed\n"); goto out; } @@ -826,7 +826,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, (!args->fence || idr_find(&queue->fence_idr, args->fence))) { spin_unlock(&queue->idr_lock); idr_preload_end(); - ret = -EINVAL; + ret = UERR(EINVAL, dev, "invalid in-fence-sn"); goto out; } @@ -868,7 +868,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, } if (ret == 0 && args->flags & MSM_SUBMIT_FENCE_FD_OUT) { - struct sync_file *sync_file = sync_file_create(submit->user_fence); + sync_file = sync_file_create(submit->user_fence); if (!sync_file) { ret = -ENOMEM; } else { @@ -902,8 +902,11 @@ out: out_unlock: mutex_unlock(&queue->lock); out_post_unlock: - if (ret && (out_fence_fd >= 0)) + if (ret && (out_fence_fd >= 0)) { put_unused_fd(out_fence_fd); + if (sync_file) + fput(sync_file->file); + } if (!IS_ERR_OR_NULL(submit)) { msm_gem_submit_put(submit); diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index 0d4a3744cfcb..3947f7ba1421 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -257,7 +257,8 @@ out: } static void msm_gpu_crashstate_capture(struct msm_gpu *gpu, - struct msm_gem_submit *submit, char *comm, char *cmd) + struct msm_gem_submit *submit, struct msm_gpu_fault_info *fault_info, + char *comm, char *cmd) { struct msm_gpu_state *state; @@ -276,11 +277,21 @@ static void msm_gpu_crashstate_capture(struct msm_gpu *gpu, /* Fill in the additional crash state information */ state->comm = kstrdup(comm, GFP_KERNEL); state->cmd = kstrdup(cmd, GFP_KERNEL); - state->fault_info = gpu->fault_info; + if (fault_info) + state->fault_info = *fault_info; if (submit) { int i; + if (state->fault_info.ttbr0) { + struct msm_gpu_fault_info *info = &state->fault_info; + struct msm_mmu *mmu = submit->aspace->mmu; + + msm_iommu_pagetable_params(mmu, &info->pgtbl_ttbr0, + &info->asid); + msm_iommu_pagetable_walk(mmu, info->iova, info->ptes); + } + state->bos = kcalloc(submit->nr_bos, sizeof(struct msm_gpu_state_bo), GFP_KERNEL); @@ -299,7 +310,8 @@ static void msm_gpu_crashstate_capture(struct msm_gpu *gpu, } #else static void msm_gpu_crashstate_capture(struct msm_gpu *gpu, - struct msm_gem_submit *submit, char *comm, char *cmd) + struct msm_gem_submit *submit, struct msm_gpu_fault_info *fault_info, + char *comm, char *cmd) { } #endif @@ -396,7 +408,7 @@ static void recover_worker(struct kthread_work *work) /* Record the crash state */ pm_runtime_get_sync(&gpu->pdev->dev); - msm_gpu_crashstate_capture(gpu, submit, comm, cmd); + msm_gpu_crashstate_capture(gpu, submit, NULL, comm, cmd); kfree(cmd); kfree(comm); @@ -450,9 +462,8 @@ out_unlock: msm_gpu_retire(gpu); } -static void fault_worker(struct kthread_work *work) +void msm_gpu_fault_crashstate_capture(struct msm_gpu *gpu, struct msm_gpu_fault_info *fault_info) { - struct msm_gpu *gpu = container_of(work, struct msm_gpu, fault_work); struct msm_gem_submit *submit; struct msm_ringbuffer *cur_ring = gpu->funcs->active_ring(gpu); char *comm = NULL, *cmd = NULL; @@ -475,16 +486,13 @@ static void fault_worker(struct kthread_work *work) /* Record the crash state */ pm_runtime_get_sync(&gpu->pdev->dev); - msm_gpu_crashstate_capture(gpu, submit, comm, cmd); + msm_gpu_crashstate_capture(gpu, submit, fault_info, comm, cmd); pm_runtime_put_sync(&gpu->pdev->dev); kfree(cmd); kfree(comm); resume_smmu: - memset(&gpu->fault_info, 0, sizeof(gpu->fault_info)); - gpu->aspace->mmu->funcs->resume_translation(gpu->aspace->mmu); - mutex_unlock(&gpu->lock); } @@ -512,7 +520,7 @@ static bool made_progress(struct msm_gpu *gpu, struct msm_ringbuffer *ring) static void hangcheck_handler(struct timer_list *t) { - struct msm_gpu *gpu = from_timer(gpu, t, hangcheck_timer); + struct msm_gpu *gpu = timer_container_of(gpu, t, hangcheck_timer); struct drm_device *dev = gpu->dev; struct msm_ringbuffer *ring = gpu->funcs->active_ring(gpu); uint32_t fence = ring->memptrs->fence; @@ -859,7 +867,7 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev, gpu->funcs = funcs; gpu->name = name; - gpu->worker = kthread_create_worker(0, "gpu-worker"); + gpu->worker = kthread_run_worker(0, "gpu-worker"); if (IS_ERR(gpu->worker)) { ret = PTR_ERR(gpu->worker); gpu->worker = NULL; @@ -873,7 +881,6 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev, init_waitqueue_head(&gpu->retire_event); kthread_init_work(&gpu->retire_work, retire_worker); kthread_init_work(&gpu->recover_work, recover_worker); - kthread_init_work(&gpu->fault_work, fault_worker); priv->hangcheck_period = DRM_MSM_HANGCHECK_DEFAULT_PERIOD; diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index 7cabc8480d7c..5bf7cd985b9c 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -101,6 +101,14 @@ struct msm_gpu_fault_info { int flags; const char *type; const char *block; + + /* Information about what we think/expect is the current SMMU state, + * for example expected_ttbr0 should match smmu_info.ttbr0 which + * was read back from SMMU registers. + */ + phys_addr_t pgtbl_ttbr0; + u64 ptes[4]; + int asid; }; /** @@ -245,12 +253,6 @@ struct msm_gpu { #define DRM_MSM_HANGCHECK_PROGRESS_RETRIES 3 struct timer_list hangcheck_timer; - /* Fault info for most recent iova fault: */ - struct msm_gpu_fault_info fault_info; - - /* work for handling GPU ioval faults: */ - struct kthread_work fault_work; - /* work for handling GPU recovery: */ struct kthread_work recover_work; @@ -660,6 +662,7 @@ msm_gpu_create_private_address_space(struct msm_gpu *gpu, struct task_struct *ta void msm_gpu_cleanup(struct msm_gpu *gpu); struct msm_gpu *adreno_load_gpu(struct drm_device *dev); +bool adreno_has_gpu(struct device_node *node); void __init adreno_register(void); void __exit adreno_unregister(void); @@ -697,6 +700,8 @@ static inline void msm_gpu_crashstate_put(struct msm_gpu *gpu) mutex_unlock(&gpu->lock); } +void msm_gpu_fault_crashstate_capture(struct msm_gpu *gpu, struct msm_gpu_fault_info *fault_info); + /* * Simple macro to semi-cleanly add the MAP_PRIV flag for targets that can * support expanded privileges diff --git a/drivers/gpu/drm/msm/msm_gpu_devfreq.c b/drivers/gpu/drm/msm/msm_gpu_devfreq.c index 6970b0f7f457..2e1d5c343272 100644 --- a/drivers/gpu/drm/msm/msm_gpu_devfreq.c +++ b/drivers/gpu/drm/msm/msm_gpu_devfreq.c @@ -156,6 +156,7 @@ void msm_devfreq_init(struct msm_gpu *gpu) priv->gpu_devfreq_config.downdifferential = 10; mutex_init(&df->lock); + df->suspended = true; ret = dev_pm_qos_add_request(&gpu->pdev->dev, &df->boost_freq, DEV_PM_QOS_MIN_FREQUENCY, 0); diff --git a/drivers/gpu/drm/msm/msm_io_utils.c b/drivers/gpu/drm/msm/msm_io_utils.c index afedd61c3e28..a6efe1eac271 100644 --- a/drivers/gpu/drm/msm/msm_io_utils.c +++ b/drivers/gpu/drm/msm/msm_io_utils.c @@ -135,8 +135,7 @@ void msm_hrtimer_work_init(struct msm_hrtimer_work *work, clockid_t clock_id, enum hrtimer_mode mode) { - hrtimer_init(&work->timer, clock_id, mode); - work->timer.function = msm_hrtimer_worktimer; + hrtimer_setup(&work->timer, msm_hrtimer_worktimer, clock_id, mode); work->worker = worker; kthread_init_work(&work->work, fn); } diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c index 2a94e82316f9..739ce2c283a4 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -195,6 +195,28 @@ struct iommu_domain_geometry *msm_iommu_get_geometry(struct msm_mmu *mmu) return &iommu->domain->geometry; } +int +msm_iommu_pagetable_walk(struct msm_mmu *mmu, unsigned long iova, uint64_t ptes[4]) +{ + struct msm_iommu_pagetable *pagetable; + struct arm_lpae_io_pgtable_walk_data wd = {}; + + if (mmu->type != MSM_MMU_IOMMU_PAGETABLE) + return -EINVAL; + + pagetable = to_pagetable(mmu); + + if (!pagetable->pgtbl_ops->pgtable_walk) + return -EINVAL; + + pagetable->pgtbl_ops->pgtable_walk(pagetable->pgtbl_ops, iova, &wd); + + for (int i = 0; i < ARRAY_SIZE(wd.ptes); i++) + ptes[i] = wd.ptes[i]; + + return 0; +} + static const struct msm_mmu_funcs pagetable_funcs = { .map = msm_iommu_pagetable_map, .unmap = msm_iommu_pagetable_unmap, @@ -243,7 +265,7 @@ static const struct iommu_flush_ops tlb_ops = { .tlb_add_page = msm_iommu_tlb_add_page, }; -static int msm_fault_handler(struct iommu_domain *domain, struct device *dev, +static int msm_gpu_fault_handler(struct iommu_domain *domain, struct device *dev, unsigned long iova, int flags, void *arg); struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent) @@ -319,11 +341,10 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent) return &pagetable->base; } -static int msm_fault_handler(struct iommu_domain *domain, struct device *dev, +static int msm_gpu_fault_handler(struct iommu_domain *domain, struct device *dev, unsigned long iova, int flags, void *arg) { struct msm_iommu *iommu = arg; - struct msm_mmu *mmu = &iommu->base; struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(iommu->base.dev); struct adreno_smmu_fault_info info, *ptr = NULL; @@ -337,18 +358,26 @@ static int msm_fault_handler(struct iommu_domain *domain, struct device *dev, pr_warn_ratelimited("*** fault: iova=%16lx, flags=%d\n", iova, flags); - if (mmu->funcs->resume_translation) - mmu->funcs->resume_translation(mmu); - return 0; } -static void msm_iommu_resume_translation(struct msm_mmu *mmu) +static int msm_disp_fault_handler(struct iommu_domain *domain, struct device *dev, + unsigned long iova, int flags, void *arg) +{ + struct msm_iommu *iommu = arg; + + if (iommu->base.handler) + return iommu->base.handler(iommu->base.arg, iova, flags, NULL); + + return -ENOSYS; +} + +static void msm_iommu_set_stall(struct msm_mmu *mmu, bool enable) { struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(mmu->dev); - if (adreno_smmu->resume_translation) - adreno_smmu->resume_translation(adreno_smmu->cookie, true); + if (adreno_smmu->set_stall) + adreno_smmu->set_stall(adreno_smmu->cookie, enable); } static void msm_iommu_detach(struct msm_mmu *mmu) @@ -398,7 +427,7 @@ static const struct msm_mmu_funcs funcs = { .map = msm_iommu_map, .unmap = msm_iommu_unmap, .destroy = msm_iommu_destroy, - .resume_translation = msm_iommu_resume_translation, + .set_stall = msm_iommu_set_stall, }; struct msm_mmu *msm_iommu_new(struct device *dev, unsigned long quirks) @@ -437,6 +466,21 @@ struct msm_mmu *msm_iommu_new(struct device *dev, unsigned long quirks) return &iommu->base; } +struct msm_mmu *msm_iommu_disp_new(struct device *dev, unsigned long quirks) +{ + struct msm_iommu *iommu; + struct msm_mmu *mmu; + + mmu = msm_iommu_new(dev, quirks); + if (IS_ERR_OR_NULL(mmu)) + return mmu; + + iommu = to_msm_iommu(mmu); + iommu_set_fault_handler(iommu->domain, msm_disp_fault_handler, iommu); + + return mmu; +} + struct msm_mmu *msm_iommu_gpu_new(struct device *dev, struct msm_gpu *gpu, unsigned long quirks) { struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(dev); @@ -448,7 +492,7 @@ struct msm_mmu *msm_iommu_gpu_new(struct device *dev, struct msm_gpu *gpu, unsig return mmu; iommu = to_msm_iommu(mmu); - iommu_set_fault_handler(iommu->domain, msm_fault_handler, iommu); + iommu_set_fault_handler(iommu->domain, msm_gpu_fault_handler, iommu); /* Enable stall on iommu fault: */ if (adreno_smmu->set_stall) diff --git a/drivers/gpu/drm/msm/msm_kms.c b/drivers/gpu/drm/msm/msm_kms.c index 4cfad12f4dc1..35d5397e73b4 100644 --- a/drivers/gpu/drm/msm/msm_kms.c +++ b/drivers/gpu/drm/msm/msm_kms.c @@ -164,12 +164,26 @@ void msm_crtc_disable_vblank(struct drm_crtc *crtc) vblank_ctrl_queue_work(priv, crtc, false); } +static int msm_kms_fault_handler(void *arg, unsigned long iova, int flags, void *data) +{ + struct msm_kms *kms = arg; + + if (atomic_read(&kms->fault_snapshot_capture) == 0) { + msm_disp_snapshot_state(kms->dev); + atomic_inc(&kms->fault_snapshot_capture); + } + + return -ENOSYS; +} + struct msm_gem_address_space *msm_kms_init_aspace(struct drm_device *dev) { struct msm_gem_address_space *aspace; struct msm_mmu *mmu; struct device *mdp_dev = dev->dev; struct device *mdss_dev = mdp_dev->parent; + struct msm_drm_private *priv = dev->dev_private; + struct msm_kms *kms = priv->kms; struct device *iommu_dev; /* @@ -181,7 +195,7 @@ struct msm_gem_address_space *msm_kms_init_aspace(struct drm_device *dev) else iommu_dev = mdss_dev; - mmu = msm_iommu_new(iommu_dev, 0); + mmu = msm_iommu_disp_new(iommu_dev, 0); if (IS_ERR(mmu)) return ERR_CAST(mmu); @@ -195,8 +209,11 @@ struct msm_gem_address_space *msm_kms_init_aspace(struct drm_device *dev) if (IS_ERR(aspace)) { dev_err(mdp_dev, "aspace create, error %pe\n", aspace); mmu->funcs->destroy(mmu); + return aspace; } + msm_mmu_set_fault_handler(aspace->mmu, kms, msm_kms_fault_handler); + return aspace; } @@ -268,7 +285,7 @@ int msm_drm_kms_init(struct device *dev, const struct drm_driver *drv) /* initialize event thread */ ev_thread = &priv->event_thread[drm_crtc_index(crtc)]; ev_thread->dev = ddev; - ev_thread->worker = kthread_create_worker(0, "crtc_event:%d", crtc->base.id); + ev_thread->worker = kthread_run_worker(0, "crtc_event:%d", crtc->base.id); if (IS_ERR(ev_thread->worker)) { ret = PTR_ERR(ev_thread->worker); DRM_DEV_ERROR(dev, "failed to create crtc_event kthread\n"); diff --git a/drivers/gpu/drm/msm/msm_kms.h b/drivers/gpu/drm/msm/msm_kms.h index e60162744c66..43b58d052ee6 100644 --- a/drivers/gpu/drm/msm/msm_kms.h +++ b/drivers/gpu/drm/msm/msm_kms.h @@ -60,6 +60,13 @@ struct msm_kms_funcs { void (*disable_commit)(struct msm_kms *kms); /** + * @check_mode_changed: + * + * Verify if the commit requires a full modeset on one of CRTCs. + */ + int (*check_mode_changed)(struct msm_kms *kms, struct drm_atomic_state *state); + + /** * Prepare for atomic commit. This is called after any previous * (async or otherwise) commit has completed. */ @@ -128,6 +135,9 @@ struct msm_kms { int irq; bool irq_requested; + /* rate limit the snapshot capture to once per attach */ + atomic_t fault_snapshot_capture; + /* mapper-id used to request GEM buffer mapped for scanout: */ struct msm_gem_address_space *aspace; diff --git a/drivers/gpu/drm/msm/msm_mdss.c b/drivers/gpu/drm/msm/msm_mdss.c index 76b6ae35a3cb..709979fcfab6 100644 --- a/drivers/gpu/drm/msm/msm_mdss.c +++ b/drivers/gpu/drm/msm/msm_mdss.c @@ -150,7 +150,7 @@ static int _msm_mdss_irq_domain_add(struct msm_mdss *msm_mdss) dev = msm_mdss->dev; - domain = irq_domain_add_linear(dev->of_node, 32, + domain = irq_domain_create_linear(of_fwnode_handle(dev->of_node), 32, &msm_mdss_irqdomain_ops, msm_mdss); if (!domain) { dev_err(dev, "failed to add irq_domain\n"); @@ -166,22 +166,32 @@ static int _msm_mdss_irq_domain_add(struct msm_mdss *msm_mdss) static void msm_mdss_setup_ubwc_dec_20(struct msm_mdss *msm_mdss) { const struct msm_mdss_data *data = msm_mdss->mdss_data; + u32 value = MDSS_UBWC_STATIC_UBWC_SWIZZLE(data->ubwc_swizzle) | + MDSS_UBWC_STATIC_HIGHEST_BANK_BIT(data->highest_bank_bit); - writel_relaxed(data->ubwc_static, msm_mdss->mmio + REG_MDSS_UBWC_STATIC); + if (data->ubwc_bank_spread) + value |= MDSS_UBWC_STATIC_UBWC_BANK_SPREAD; + + if (data->ubwc_enc_version == UBWC_1_0) + value |= MDSS_UBWC_STATIC_UBWC_MIN_ACC_LEN(1); + + writel_relaxed(value, msm_mdss->mmio + REG_MDSS_UBWC_STATIC); } static void msm_mdss_setup_ubwc_dec_30(struct msm_mdss *msm_mdss) { const struct msm_mdss_data *data = msm_mdss->mdss_data; - u32 value = (data->ubwc_swizzle & 0x1) | - (data->highest_bank_bit & 0x3) << 4 | - (data->macrotile_mode & 0x1) << 12; + u32 value = MDSS_UBWC_STATIC_UBWC_SWIZZLE(data->ubwc_swizzle & 0x1) | + MDSS_UBWC_STATIC_HIGHEST_BANK_BIT(data->highest_bank_bit); + + if (data->macrotile_mode) + value |= MDSS_UBWC_STATIC_MACROTILE_MODE; if (data->ubwc_enc_version == UBWC_3_0) - value |= BIT(10); + value |= MDSS_UBWC_STATIC_UBWC_AMSBC; if (data->ubwc_enc_version == UBWC_1_0) - value |= BIT(8); + value |= MDSS_UBWC_STATIC_UBWC_MIN_ACC_LEN(1); writel_relaxed(value, msm_mdss->mmio + REG_MDSS_UBWC_STATIC); } @@ -189,10 +199,14 @@ static void msm_mdss_setup_ubwc_dec_30(struct msm_mdss *msm_mdss) static void msm_mdss_setup_ubwc_dec_40(struct msm_mdss *msm_mdss) { const struct msm_mdss_data *data = msm_mdss->mdss_data; - u32 value = (data->ubwc_swizzle & 0x7) | - (data->ubwc_static & 0x1) << 3 | - (data->highest_bank_bit & 0x7) << 4 | - (data->macrotile_mode & 0x1) << 12; + u32 value = MDSS_UBWC_STATIC_UBWC_SWIZZLE(data->ubwc_swizzle) | + MDSS_UBWC_STATIC_HIGHEST_BANK_BIT(data->highest_bank_bit); + + if (data->ubwc_bank_spread) + value |= MDSS_UBWC_STATIC_UBWC_BANK_SPREAD; + + if (data->macrotile_mode) + value |= MDSS_UBWC_STATIC_MACROTILE_MODE; writel_relaxed(value, msm_mdss->mmio + REG_MDSS_UBWC_STATIC); @@ -572,7 +586,17 @@ static const struct msm_mdss_data sa8775p_data = { .ubwc_enc_version = UBWC_4_0, .ubwc_dec_version = UBWC_4_0, .ubwc_swizzle = 4, - .ubwc_static = 1, + .ubwc_bank_spread = true, + .highest_bank_bit = 0, + .macrotile_mode = true, + .reg_bus_bw = 74000, +}; + +static const struct msm_mdss_data sar2130p_data = { + .ubwc_enc_version = UBWC_3_0, /* 4.0.2 in hw */ + .ubwc_dec_version = UBWC_4_3, + .ubwc_swizzle = 6, + .ubwc_bank_spread = true, .highest_bank_bit = 0, .macrotile_mode = 1, .reg_bus_bw = 74000, @@ -581,7 +605,8 @@ static const struct msm_mdss_data sa8775p_data = { static const struct msm_mdss_data sc7180_data = { .ubwc_enc_version = UBWC_2_0, .ubwc_dec_version = UBWC_2_0, - .ubwc_static = 0x1e, + .ubwc_swizzle = 6, + .ubwc_bank_spread = true, .highest_bank_bit = 0x1, .reg_bus_bw = 76800, }; @@ -590,9 +615,9 @@ static const struct msm_mdss_data sc7280_data = { .ubwc_enc_version = UBWC_3_0, .ubwc_dec_version = UBWC_4_0, .ubwc_swizzle = 6, - .ubwc_static = 1, + .ubwc_bank_spread = true, .highest_bank_bit = 1, - .macrotile_mode = 1, + .macrotile_mode = true, .reg_bus_bw = 74000, }; @@ -600,7 +625,7 @@ static const struct msm_mdss_data sc8180x_data = { .ubwc_enc_version = UBWC_3_0, .ubwc_dec_version = UBWC_3_0, .highest_bank_bit = 3, - .macrotile_mode = 1, + .macrotile_mode = true, .reg_bus_bw = 76800, }; @@ -608,9 +633,9 @@ static const struct msm_mdss_data sc8280xp_data = { .ubwc_enc_version = UBWC_4_0, .ubwc_dec_version = UBWC_4_0, .ubwc_swizzle = 6, - .ubwc_static = 1, + .ubwc_bank_spread = true, .highest_bank_bit = 3, - .macrotile_mode = 1, + .macrotile_mode = true, .reg_bus_bw = 76800, }; @@ -632,7 +657,7 @@ static const struct msm_mdss_data sm6350_data = { .ubwc_enc_version = UBWC_2_0, .ubwc_dec_version = UBWC_2_0, .ubwc_swizzle = 6, - .ubwc_static = 0x1e, + .ubwc_bank_spread = true, .highest_bank_bit = 1, .reg_bus_bw = 76800, }; @@ -655,7 +680,7 @@ static const struct msm_mdss_data sm6115_data = { .ubwc_enc_version = UBWC_1_0, .ubwc_dec_version = UBWC_2_0, .ubwc_swizzle = 7, - .ubwc_static = 0x11f, + .ubwc_bank_spread = true, .highest_bank_bit = 0x1, .reg_bus_bw = 76800, }; @@ -667,14 +692,21 @@ static const struct msm_mdss_data sm6125_data = { .highest_bank_bit = 1, }; +static const struct msm_mdss_data sm6150_data = { + .ubwc_enc_version = UBWC_2_0, + .ubwc_dec_version = UBWC_2_0, + .highest_bank_bit = 1, + .reg_bus_bw = 76800, +}; + static const struct msm_mdss_data sm8250_data = { .ubwc_enc_version = UBWC_4_0, .ubwc_dec_version = UBWC_4_0, .ubwc_swizzle = 6, - .ubwc_static = 1, + .ubwc_bank_spread = true, /* TODO: highest_bank_bit = 2 for LP_DDR4 */ .highest_bank_bit = 3, - .macrotile_mode = 1, + .macrotile_mode = true, .reg_bus_bw = 76800, }; @@ -682,10 +714,10 @@ static const struct msm_mdss_data sm8350_data = { .ubwc_enc_version = UBWC_4_0, .ubwc_dec_version = UBWC_4_0, .ubwc_swizzle = 6, - .ubwc_static = 1, + .ubwc_bank_spread = true, /* TODO: highest_bank_bit = 2 for LP_DDR4 */ .highest_bank_bit = 3, - .macrotile_mode = 1, + .macrotile_mode = true, .reg_bus_bw = 74000, }; @@ -693,10 +725,10 @@ static const struct msm_mdss_data sm8550_data = { .ubwc_enc_version = UBWC_4_0, .ubwc_dec_version = UBWC_4_3, .ubwc_swizzle = 6, - .ubwc_static = 1, + .ubwc_bank_spread = true, /* TODO: highest_bank_bit = 2 for LP_DDR4 */ .highest_bank_bit = 3, - .macrotile_mode = 1, + .macrotile_mode = true, .reg_bus_bw = 57000, }; @@ -704,10 +736,10 @@ static const struct msm_mdss_data x1e80100_data = { .ubwc_enc_version = UBWC_4_0, .ubwc_dec_version = UBWC_4_3, .ubwc_swizzle = 6, - .ubwc_static = 1, + .ubwc_bank_spread = true, /* TODO: highest_bank_bit = 2 for LP_DDR4 */ .highest_bank_bit = 3, - .macrotile_mode = 1, + .macrotile_mode = true, /* TODO: Add reg_bus_bw with real value */ }; @@ -716,6 +748,7 @@ static const struct of_device_id mdss_dt_match[] = { { .compatible = "qcom,msm8998-mdss", .data = &msm8998_data }, { .compatible = "qcom,qcm2290-mdss", .data = &qcm2290_data }, { .compatible = "qcom,sa8775p-mdss", .data = &sa8775p_data }, + { .compatible = "qcom,sar2130p-mdss", .data = &sar2130p_data }, { .compatible = "qcom,sdm670-mdss", .data = &sdm670_data }, { .compatible = "qcom,sdm845-mdss", .data = &sdm845_data }, { .compatible = "qcom,sc7180-mdss", .data = &sc7180_data }, @@ -724,6 +757,7 @@ static const struct of_device_id mdss_dt_match[] = { { .compatible = "qcom,sc8280xp-mdss", .data = &sc8280xp_data }, { .compatible = "qcom,sm6115-mdss", .data = &sm6115_data }, { .compatible = "qcom,sm6125-mdss", .data = &sm6125_data }, + { .compatible = "qcom,sm6150-mdss", .data = &sm6150_data }, { .compatible = "qcom,sm6350-mdss", .data = &sm6350_data }, { .compatible = "qcom,sm6375-mdss", .data = &sm6350_data }, { .compatible = "qcom,sm7150-mdss", .data = &sm7150_data }, diff --git a/drivers/gpu/drm/msm/msm_mdss.h b/drivers/gpu/drm/msm/msm_mdss.h index 3afef4b1786d..14dc53704314 100644 --- a/drivers/gpu/drm/msm/msm_mdss.h +++ b/drivers/gpu/drm/msm/msm_mdss.h @@ -11,9 +11,9 @@ struct msm_mdss_data { /* can be read from register 0x58 */ u32 ubwc_dec_version; u32 ubwc_swizzle; - u32 ubwc_static; u32 highest_bank_bit; - u32 macrotile_mode; + bool ubwc_bank_spread; + bool macrotile_mode; u32 reg_bus_bw; }; diff --git a/drivers/gpu/drm/msm/msm_mmu.h b/drivers/gpu/drm/msm/msm_mmu.h index 88af4f490881..0c694907140d 100644 --- a/drivers/gpu/drm/msm/msm_mmu.h +++ b/drivers/gpu/drm/msm/msm_mmu.h @@ -15,7 +15,7 @@ struct msm_mmu_funcs { size_t len, int prot); int (*unmap)(struct msm_mmu *mmu, uint64_t iova, size_t len); void (*destroy)(struct msm_mmu *mmu); - void (*resume_translation)(struct msm_mmu *mmu); + void (*set_stall)(struct msm_mmu *mmu, bool enable); }; enum msm_mmu_type { @@ -42,6 +42,7 @@ static inline void msm_mmu_init(struct msm_mmu *mmu, struct device *dev, struct msm_mmu *msm_iommu_new(struct device *dev, unsigned long quirks); struct msm_mmu *msm_iommu_gpu_new(struct device *dev, struct msm_gpu *gpu, unsigned long quirks); +struct msm_mmu *msm_iommu_disp_new(struct device *dev, unsigned long quirks); static inline void msm_mmu_set_fault_handler(struct msm_mmu *mmu, void *arg, int (*handler)(void *arg, unsigned long iova, int flags, void *data)) @@ -53,7 +54,8 @@ static inline void msm_mmu_set_fault_handler(struct msm_mmu *mmu, void *arg, struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent); int msm_iommu_pagetable_params(struct msm_mmu *mmu, phys_addr_t *ttbr, - int *asid); + int *asid); +int msm_iommu_pagetable_walk(struct msm_mmu *mmu, unsigned long iova, uint64_t ptes[4]); struct iommu_domain_geometry *msm_iommu_get_geometry(struct msm_mmu *mmu); #endif /* __MSM_MMU_H__ */ diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c index c803556a8f64..89dce15eed3b 100644 --- a/drivers/gpu/drm/msm/msm_ringbuffer.c +++ b/drivers/gpu/drm/msm/msm_ringbuffer.c @@ -59,8 +59,14 @@ static const struct drm_sched_backend_ops msm_sched_ops = { struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id, void *memptrs, uint64_t memptrs_iova) { + struct drm_sched_init_args args = { + .ops = &msm_sched_ops, + .num_rqs = DRM_SCHED_PRIORITY_COUNT, + .credit_limit = num_hw_submissions, + .timeout = MAX_SCHEDULE_TIMEOUT, + .dev = gpu->dev->dev, + }; struct msm_ringbuffer *ring; - long sched_timeout; char name[32]; int ret; @@ -87,6 +93,7 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id, } msm_gem_object_set_name(ring->bo, "ring%d", id); + args.name = to_msm_bo(ring->bo)->name; ring->end = ring->start + (MSM_GPU_RINGBUFFER_SZ >> 2); ring->next = ring->start; @@ -95,13 +102,7 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id, ring->memptrs = memptrs; ring->memptrs_iova = memptrs_iova; - /* currently managing hangcheck ourselves: */ - sched_timeout = MAX_SCHEDULE_TIMEOUT; - - ret = drm_sched_init(&ring->sched, &msm_sched_ops, NULL, - DRM_SCHED_PRIORITY_COUNT, - num_hw_submissions, 0, sched_timeout, - NULL, NULL, to_msm_bo(ring->bo)->name, gpu->dev->dev); + ret = drm_sched_init(&ring->sched, &args); if (ret) { goto fail; } diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c index 2fc3eaf81f44..7fed1de63b5d 100644 --- a/drivers/gpu/drm/msm/msm_submitqueue.c +++ b/drivers/gpu/drm/msm/msm_submitqueue.c @@ -18,7 +18,7 @@ int msm_file_private_set_sysprof(struct msm_file_private *ctx, switch (sysprof) { default: - return -EINVAL; + return UERR(EINVAL, gpu->dev, "Invalid sysprof: %d", sysprof); case 2: pm_runtime_get_sync(&gpu->pdev->dev); fallthrough; diff --git a/drivers/gpu/drm/msm/registers/adreno/a6xx.xml b/drivers/gpu/drm/msm/registers/adreno/a6xx.xml index 2db425abf0f3..d860fd94feae 100644 --- a/drivers/gpu/drm/msm/registers/adreno/a6xx.xml +++ b/drivers/gpu/drm/msm/registers/adreno/a6xx.xml @@ -5,6 +5,11 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <import file="freedreno_copyright.xml"/> <import file="adreno/adreno_common.xml"/> <import file="adreno/adreno_pm4.xml"/> +<import file="adreno/a6xx_enums.xml"/> +<import file="adreno/a7xx_enums.xml"/> +<import file="adreno/a6xx_perfcntrs.xml"/> +<import file="adreno/a7xx_perfcntrs.xml"/> +<import file="adreno/a6xx_descriptors.xml"/> <!-- Each register that is actually being used by driver should have "usage" defined, @@ -20,2205 +25,6 @@ is either overwritten by renderpass/blit (ib2) or not used if not overwritten by a particular renderpass/blit. --> -<!-- these might be same as a5xx --> -<enum name="a6xx_tile_mode"> - <value name="TILE6_LINEAR" value="0"/> - <value name="TILE6_2" value="2"/> - <value name="TILE6_3" value="3"/> -</enum> - -<enum name="a6xx_format"> - <value value="0x02" name="FMT6_A8_UNORM"/> - <value value="0x03" name="FMT6_8_UNORM"/> - <value value="0x04" name="FMT6_8_SNORM"/> - <value value="0x05" name="FMT6_8_UINT"/> - <value value="0x06" name="FMT6_8_SINT"/> - - <value value="0x08" name="FMT6_4_4_4_4_UNORM"/> - <value value="0x0a" name="FMT6_5_5_5_1_UNORM"/> - <value value="0x0c" name="FMT6_1_5_5_5_UNORM"/> <!-- read only --> - <value value="0x0e" name="FMT6_5_6_5_UNORM"/> - - <value value="0x0f" name="FMT6_8_8_UNORM"/> - <value value="0x10" name="FMT6_8_8_SNORM"/> - <value value="0x11" name="FMT6_8_8_UINT"/> - <value value="0x12" name="FMT6_8_8_SINT"/> - <value value="0x13" name="FMT6_L8_A8_UNORM"/> - - <value value="0x15" name="FMT6_16_UNORM"/> - <value value="0x16" name="FMT6_16_SNORM"/> - <value value="0x17" name="FMT6_16_FLOAT"/> - <value value="0x18" name="FMT6_16_UINT"/> - <value value="0x19" name="FMT6_16_SINT"/> - - <value value="0x21" name="FMT6_8_8_8_UNORM"/> - <value value="0x22" name="FMT6_8_8_8_SNORM"/> - <value value="0x23" name="FMT6_8_8_8_UINT"/> - <value value="0x24" name="FMT6_8_8_8_SINT"/> - - <value value="0x30" name="FMT6_8_8_8_8_UNORM"/> - <value value="0x31" name="FMT6_8_8_8_X8_UNORM"/> <!-- samples 1 for alpha --> - <value value="0x32" name="FMT6_8_8_8_8_SNORM"/> - <value value="0x33" name="FMT6_8_8_8_8_UINT"/> - <value value="0x34" name="FMT6_8_8_8_8_SINT"/> - - <value value="0x35" name="FMT6_9_9_9_E5_FLOAT"/> - - <value value="0x36" name="FMT6_10_10_10_2_UNORM"/> - <value value="0x37" name="FMT6_10_10_10_2_UNORM_DEST"/> - <value value="0x39" name="FMT6_10_10_10_2_SNORM"/> - <value value="0x3a" name="FMT6_10_10_10_2_UINT"/> - <value value="0x3b" name="FMT6_10_10_10_2_SINT"/> - - <value value="0x42" name="FMT6_11_11_10_FLOAT"/> - - <value value="0x43" name="FMT6_16_16_UNORM"/> - <value value="0x44" name="FMT6_16_16_SNORM"/> - <value value="0x45" name="FMT6_16_16_FLOAT"/> - <value value="0x46" name="FMT6_16_16_UINT"/> - <value value="0x47" name="FMT6_16_16_SINT"/> - - <value value="0x48" name="FMT6_32_UNORM"/> - <value value="0x49" name="FMT6_32_SNORM"/> - <value value="0x4a" name="FMT6_32_FLOAT"/> - <value value="0x4b" name="FMT6_32_UINT"/> - <value value="0x4c" name="FMT6_32_SINT"/> - <value value="0x4d" name="FMT6_32_FIXED"/> - - <value value="0x58" name="FMT6_16_16_16_UNORM"/> - <value value="0x59" name="FMT6_16_16_16_SNORM"/> - <value value="0x5a" name="FMT6_16_16_16_FLOAT"/> - <value value="0x5b" name="FMT6_16_16_16_UINT"/> - <value value="0x5c" name="FMT6_16_16_16_SINT"/> - - <value value="0x60" name="FMT6_16_16_16_16_UNORM"/> - <value value="0x61" name="FMT6_16_16_16_16_SNORM"/> - <value value="0x62" name="FMT6_16_16_16_16_FLOAT"/> - <value value="0x63" name="FMT6_16_16_16_16_UINT"/> - <value value="0x64" name="FMT6_16_16_16_16_SINT"/> - - <value value="0x65" name="FMT6_32_32_UNORM"/> - <value value="0x66" name="FMT6_32_32_SNORM"/> - <value value="0x67" name="FMT6_32_32_FLOAT"/> - <value value="0x68" name="FMT6_32_32_UINT"/> - <value value="0x69" name="FMT6_32_32_SINT"/> - <value value="0x6a" name="FMT6_32_32_FIXED"/> - - <value value="0x70" name="FMT6_32_32_32_UNORM"/> - <value value="0x71" name="FMT6_32_32_32_SNORM"/> - <value value="0x72" name="FMT6_32_32_32_UINT"/> - <value value="0x73" name="FMT6_32_32_32_SINT"/> - <value value="0x74" name="FMT6_32_32_32_FLOAT"/> - <value value="0x75" name="FMT6_32_32_32_FIXED"/> - - <value value="0x80" name="FMT6_32_32_32_32_UNORM"/> - <value value="0x81" name="FMT6_32_32_32_32_SNORM"/> - <value value="0x82" name="FMT6_32_32_32_32_FLOAT"/> - <value value="0x83" name="FMT6_32_32_32_32_UINT"/> - <value value="0x84" name="FMT6_32_32_32_32_SINT"/> - <value value="0x85" name="FMT6_32_32_32_32_FIXED"/> - - <value value="0x8c" name="FMT6_G8R8B8R8_422_UNORM"/> <!-- UYVY --> - <value value="0x8d" name="FMT6_R8G8R8B8_422_UNORM"/> <!-- YUYV --> - <value value="0x8e" name="FMT6_R8_G8B8_2PLANE_420_UNORM"/> <!-- NV12 --> - <value value="0x8f" name="FMT6_NV21"/> - <value value="0x90" name="FMT6_R8_G8_B8_3PLANE_420_UNORM"/> <!-- YV12 --> - - <value value="0x91" name="FMT6_Z24_UNORM_S8_UINT_AS_R8G8B8A8"/> - - <!-- Note: tiling/UBWC for these may be different from equivalent formats - For example FMT6_NV12_Y is not compatible with FMT6_8_UNORM - --> - <value value="0x94" name="FMT6_NV12_Y"/> - <value value="0x95" name="FMT6_NV12_UV"/> - <value value="0x96" name="FMT6_NV12_VU"/> - <value value="0x97" name="FMT6_NV12_4R"/> - <value value="0x98" name="FMT6_NV12_4R_Y"/> - <value value="0x99" name="FMT6_NV12_4R_UV"/> - <value value="0x9a" name="FMT6_P010"/> - <value value="0x9b" name="FMT6_P010_Y"/> - <value value="0x9c" name="FMT6_P010_UV"/> - <value value="0x9d" name="FMT6_TP10"/> - <value value="0x9e" name="FMT6_TP10_Y"/> - <value value="0x9f" name="FMT6_TP10_UV"/> - - <value value="0xa0" name="FMT6_Z24_UNORM_S8_UINT"/> - - <value value="0xab" name="FMT6_ETC2_RG11_UNORM"/> - <value value="0xac" name="FMT6_ETC2_RG11_SNORM"/> - <value value="0xad" name="FMT6_ETC2_R11_UNORM"/> - <value value="0xae" name="FMT6_ETC2_R11_SNORM"/> - <value value="0xaf" name="FMT6_ETC1"/> - <value value="0xb0" name="FMT6_ETC2_RGB8"/> - <value value="0xb1" name="FMT6_ETC2_RGBA8"/> - <value value="0xb2" name="FMT6_ETC2_RGB8A1"/> - <value value="0xb3" name="FMT6_DXT1"/> - <value value="0xb4" name="FMT6_DXT3"/> - <value value="0xb5" name="FMT6_DXT5"/> - <value value="0xb7" name="FMT6_RGTC1_UNORM"/> - <value value="0xb8" name="FMT6_RGTC1_SNORM"/> - <value value="0xbb" name="FMT6_RGTC2_UNORM"/> - <value value="0xbc" name="FMT6_RGTC2_SNORM"/> - <value value="0xbe" name="FMT6_BPTC_UFLOAT"/> - <value value="0xbf" name="FMT6_BPTC_FLOAT"/> - <value value="0xc0" name="FMT6_BPTC"/> - <value value="0xc1" name="FMT6_ASTC_4x4"/> - <value value="0xc2" name="FMT6_ASTC_5x4"/> - <value value="0xc3" name="FMT6_ASTC_5x5"/> - <value value="0xc4" name="FMT6_ASTC_6x5"/> - <value value="0xc5" name="FMT6_ASTC_6x6"/> - <value value="0xc6" name="FMT6_ASTC_8x5"/> - <value value="0xc7" name="FMT6_ASTC_8x6"/> - <value value="0xc8" name="FMT6_ASTC_8x8"/> - <value value="0xc9" name="FMT6_ASTC_10x5"/> - <value value="0xca" name="FMT6_ASTC_10x6"/> - <value value="0xcb" name="FMT6_ASTC_10x8"/> - <value value="0xcc" name="FMT6_ASTC_10x10"/> - <value value="0xcd" name="FMT6_ASTC_12x10"/> - <value value="0xce" name="FMT6_ASTC_12x12"/> - - <!-- for sampling stencil (integer, 2nd channel), not available on a630 --> - <value value="0xea" name="FMT6_Z24_UINT_S8_UINT"/> - - <!-- Not a hw enum, used internally in driver --> - <value value="0xff" name="FMT6_NONE"/> - -</enum> - -<!-- probably same as a5xx --> -<enum name="a6xx_polygon_mode"> - <value name="POLYMODE6_POINTS" value="1"/> - <value name="POLYMODE6_LINES" value="2"/> - <value name="POLYMODE6_TRIANGLES" value="3"/> -</enum> - -<enum name="a6xx_depth_format"> - <value name="DEPTH6_NONE" value="0"/> - <value name="DEPTH6_16" value="1"/> - <value name="DEPTH6_24_8" value="2"/> - <value name="DEPTH6_32" value="4"/> -</enum> - -<bitset name="a6x_cp_protect" inline="yes"> - <bitfield name="BASE_ADDR" low="0" high="17"/> - <bitfield name="MASK_LEN" low="18" high="30"/> - <bitfield name="READ" pos="31" type="boolean"/> -</bitset> - -<enum name="a6xx_shader_id"> - <value value="0x9" name="A6XX_TP0_TMO_DATA"/> - <value value="0xa" name="A6XX_TP0_SMO_DATA"/> - <value value="0xb" name="A6XX_TP0_MIPMAP_BASE_DATA"/> - <value value="0x19" name="A6XX_TP1_TMO_DATA"/> - <value value="0x1a" name="A6XX_TP1_SMO_DATA"/> - <value value="0x1b" name="A6XX_TP1_MIPMAP_BASE_DATA"/> - <value value="0x29" name="A6XX_SP_INST_DATA"/> - <value value="0x2a" name="A6XX_SP_LB_0_DATA"/> - <value value="0x2b" name="A6XX_SP_LB_1_DATA"/> - <value value="0x2c" name="A6XX_SP_LB_2_DATA"/> - <value value="0x2d" name="A6XX_SP_LB_3_DATA"/> - <value value="0x2e" name="A6XX_SP_LB_4_DATA"/> - <value value="0x2f" name="A6XX_SP_LB_5_DATA"/> - <value value="0x30" name="A6XX_SP_CB_BINDLESS_DATA"/> - <value value="0x31" name="A6XX_SP_CB_LEGACY_DATA"/> - <value value="0x32" name="A6XX_SP_UAV_DATA"/> - <value value="0x33" name="A6XX_SP_INST_TAG"/> - <value value="0x34" name="A6XX_SP_CB_BINDLESS_TAG"/> - <value value="0x35" name="A6XX_SP_TMO_UMO_TAG"/> - <value value="0x36" name="A6XX_SP_SMO_TAG"/> - <value value="0x37" name="A6XX_SP_STATE_DATA"/> - <value value="0x49" name="A6XX_HLSQ_CHUNK_CVS_RAM"/> - <value value="0x4a" name="A6XX_HLSQ_CHUNK_CPS_RAM"/> - <value value="0x4b" name="A6XX_HLSQ_CHUNK_CVS_RAM_TAG"/> - <value value="0x4c" name="A6XX_HLSQ_CHUNK_CPS_RAM_TAG"/> - <value value="0x4d" name="A6XX_HLSQ_ICB_CVS_CB_BASE_TAG"/> - <value value="0x4e" name="A6XX_HLSQ_ICB_CPS_CB_BASE_TAG"/> - <value value="0x50" name="A6XX_HLSQ_CVS_MISC_RAM"/> - <value value="0x51" name="A6XX_HLSQ_CPS_MISC_RAM"/> - <value value="0x52" name="A6XX_HLSQ_INST_RAM"/> - <value value="0x53" name="A6XX_HLSQ_GFX_CVS_CONST_RAM"/> - <value value="0x54" name="A6XX_HLSQ_GFX_CPS_CONST_RAM"/> - <value value="0x55" name="A6XX_HLSQ_CVS_MISC_RAM_TAG"/> - <value value="0x56" name="A6XX_HLSQ_CPS_MISC_RAM_TAG"/> - <value value="0x57" name="A6XX_HLSQ_INST_RAM_TAG"/> - <value value="0x58" name="A6XX_HLSQ_GFX_CVS_CONST_RAM_TAG"/> - <value value="0x59" name="A6XX_HLSQ_GFX_CPS_CONST_RAM_TAG"/> - <value value="0x5a" name="A6XX_HLSQ_PWR_REST_RAM"/> - <value value="0x5b" name="A6XX_HLSQ_PWR_REST_TAG"/> - <value value="0x60" name="A6XX_HLSQ_DATAPATH_META"/> - <value value="0x61" name="A6XX_HLSQ_FRONTEND_META"/> - <value value="0x62" name="A6XX_HLSQ_INDIRECT_META"/> - <value value="0x63" name="A6XX_HLSQ_BACKEND_META"/> - <value value="0x70" name="A6XX_SP_LB_6_DATA"/> - <value value="0x71" name="A6XX_SP_LB_7_DATA"/> - <value value="0x73" name="A6XX_HLSQ_INST_RAM_1"/> -</enum> - -<enum name="a7xx_statetype_id"> - <value value="0" name="A7XX_TP0_NCTX_REG"/> - <value value="1" name="A7XX_TP0_CTX0_3D_CVS_REG"/> - <value value="2" name="A7XX_TP0_CTX0_3D_CPS_REG"/> - <value value="3" name="A7XX_TP0_CTX1_3D_CVS_REG"/> - <value value="4" name="A7XX_TP0_CTX1_3D_CPS_REG"/> - <value value="5" name="A7XX_TP0_CTX2_3D_CPS_REG"/> - <value value="6" name="A7XX_TP0_CTX3_3D_CPS_REG"/> - <value value="9" name="A7XX_TP0_TMO_DATA"/> - <value value="10" name="A7XX_TP0_SMO_DATA"/> - <value value="11" name="A7XX_TP0_MIPMAP_BASE_DATA"/> - <value value="32" name="A7XX_SP_NCTX_REG"/> - <value value="33" name="A7XX_SP_CTX0_3D_CVS_REG"/> - <value value="34" name="A7XX_SP_CTX0_3D_CPS_REG"/> - <value value="35" name="A7XX_SP_CTX1_3D_CVS_REG"/> - <value value="36" name="A7XX_SP_CTX1_3D_CPS_REG"/> - <value value="37" name="A7XX_SP_CTX2_3D_CPS_REG"/> - <value value="38" name="A7XX_SP_CTX3_3D_CPS_REG"/> - <value value="39" name="A7XX_SP_INST_DATA"/> - <value value="40" name="A7XX_SP_INST_DATA_1"/> - <value value="41" name="A7XX_SP_LB_0_DATA"/> - <value value="42" name="A7XX_SP_LB_1_DATA"/> - <value value="43" name="A7XX_SP_LB_2_DATA"/> - <value value="44" name="A7XX_SP_LB_3_DATA"/> - <value value="45" name="A7XX_SP_LB_4_DATA"/> - <value value="46" name="A7XX_SP_LB_5_DATA"/> - <value value="47" name="A7XX_SP_LB_6_DATA"/> - <value value="48" name="A7XX_SP_LB_7_DATA"/> - <value value="49" name="A7XX_SP_CB_RAM"/> - <value value="50" name="A7XX_SP_LB_13_DATA"/> - <value value="51" name="A7XX_SP_LB_14_DATA"/> - <value value="52" name="A7XX_SP_INST_TAG"/> - <value value="53" name="A7XX_SP_INST_DATA_2"/> - <value value="54" name="A7XX_SP_TMO_TAG"/> - <value value="55" name="A7XX_SP_SMO_TAG"/> - <value value="56" name="A7XX_SP_STATE_DATA"/> - <value value="57" name="A7XX_SP_HWAVE_RAM"/> - <value value="58" name="A7XX_SP_L0_INST_BUF"/> - <value value="59" name="A7XX_SP_LB_8_DATA"/> - <value value="60" name="A7XX_SP_LB_9_DATA"/> - <value value="61" name="A7XX_SP_LB_10_DATA"/> - <value value="62" name="A7XX_SP_LB_11_DATA"/> - <value value="63" name="A7XX_SP_LB_12_DATA"/> - <value value="64" name="A7XX_HLSQ_DATAPATH_DSTR_META"/> - <value value="67" name="A7XX_HLSQ_L2STC_TAG_RAM"/> - <value value="68" name="A7XX_HLSQ_L2STC_INFO_CMD"/> - <value value="69" name="A7XX_HLSQ_CVS_BE_CTXT_BUF_RAM_TAG"/> - <value value="70" name="A7XX_HLSQ_CPS_BE_CTXT_BUF_RAM_TAG"/> - <value value="71" name="A7XX_HLSQ_GFX_CVS_BE_CTXT_BUF_RAM"/> - <value value="72" name="A7XX_HLSQ_GFX_CPS_BE_CTXT_BUF_RAM"/> - <value value="73" name="A7XX_HLSQ_CHUNK_CVS_RAM"/> - <value value="74" name="A7XX_HLSQ_CHUNK_CPS_RAM"/> - <value value="75" name="A7XX_HLSQ_CHUNK_CVS_RAM_TAG"/> - <value value="76" name="A7XX_HLSQ_CHUNK_CPS_RAM_TAG"/> - <value value="77" name="A7XX_HLSQ_ICB_CVS_CB_BASE_TAG"/> - <value value="78" name="A7XX_HLSQ_ICB_CPS_CB_BASE_TAG"/> - <value value="79" name="A7XX_HLSQ_CVS_MISC_RAM"/> - <value value="80" name="A7XX_HLSQ_CPS_MISC_RAM"/> - <value value="81" name="A7XX_HLSQ_CPS_MISC_RAM_1"/> - <value value="82" name="A7XX_HLSQ_INST_RAM"/> - <value value="83" name="A7XX_HLSQ_GFX_CVS_CONST_RAM"/> - <value value="84" name="A7XX_HLSQ_GFX_CPS_CONST_RAM"/> - <value value="85" name="A7XX_HLSQ_CVS_MISC_RAM_TAG"/> - <value value="86" name="A7XX_HLSQ_CPS_MISC_RAM_TAG"/> - <value value="87" name="A7XX_HLSQ_INST_RAM_TAG"/> - <value value="88" name="A7XX_HLSQ_GFX_CVS_CONST_RAM_TAG"/> - <value value="89" name="A7XX_HLSQ_GFX_CPS_CONST_RAM_TAG"/> - <value value="90" name="A7XX_HLSQ_GFX_LOCAL_MISC_RAM"/> - <value value="91" name="A7XX_HLSQ_GFX_LOCAL_MISC_RAM_TAG"/> - <value value="92" name="A7XX_HLSQ_INST_RAM_1"/> - <value value="93" name="A7XX_HLSQ_STPROC_META"/> - <value value="94" name="A7XX_HLSQ_BV_BE_META"/> - <value value="95" name="A7XX_HLSQ_INST_RAM_2"/> - <value value="96" name="A7XX_HLSQ_DATAPATH_META"/> - <value value="97" name="A7XX_HLSQ_FRONTEND_META"/> - <value value="98" name="A7XX_HLSQ_INDIRECT_META"/> - <value value="99" name="A7XX_HLSQ_BACKEND_META"/> -</enum> - -<enum name="a6xx_debugbus_id"> - <value value="0x1" name="A6XX_DBGBUS_CP"/> - <value value="0x2" name="A6XX_DBGBUS_RBBM"/> - <value value="0x3" name="A6XX_DBGBUS_VBIF"/> - <value value="0x4" name="A6XX_DBGBUS_HLSQ"/> - <value value="0x5" name="A6XX_DBGBUS_UCHE"/> - <value value="0x6" name="A6XX_DBGBUS_DPM"/> - <value value="0x7" name="A6XX_DBGBUS_TESS"/> - <value value="0x8" name="A6XX_DBGBUS_PC"/> - <value value="0x9" name="A6XX_DBGBUS_VFDP"/> - <value value="0xa" name="A6XX_DBGBUS_VPC"/> - <value value="0xb" name="A6XX_DBGBUS_TSE"/> - <value value="0xc" name="A6XX_DBGBUS_RAS"/> - <value value="0xd" name="A6XX_DBGBUS_VSC"/> - <value value="0xe" name="A6XX_DBGBUS_COM"/> - <value value="0x10" name="A6XX_DBGBUS_LRZ"/> - <value value="0x11" name="A6XX_DBGBUS_A2D"/> - <value value="0x12" name="A6XX_DBGBUS_CCUFCHE"/> - <value value="0x13" name="A6XX_DBGBUS_GMU_CX"/> - <value value="0x14" name="A6XX_DBGBUS_RBP"/> - <value value="0x15" name="A6XX_DBGBUS_DCS"/> - <value value="0x16" name="A6XX_DBGBUS_DBGC"/> - <value value="0x17" name="A6XX_DBGBUS_CX"/> - <value value="0x18" name="A6XX_DBGBUS_GMU_GX"/> - <value value="0x19" name="A6XX_DBGBUS_TPFCHE"/> - <value value="0x1a" name="A6XX_DBGBUS_GBIF_GX"/> - <value value="0x1d" name="A6XX_DBGBUS_GPC"/> - <value value="0x1e" name="A6XX_DBGBUS_LARC"/> - <value value="0x1f" name="A6XX_DBGBUS_HLSQ_SPTP"/> - <value value="0x20" name="A6XX_DBGBUS_RB_0"/> - <value value="0x21" name="A6XX_DBGBUS_RB_1"/> - <value value="0x22" name="A6XX_DBGBUS_RB_2"/> - <value value="0x24" name="A6XX_DBGBUS_UCHE_WRAPPER"/> - <value value="0x28" name="A6XX_DBGBUS_CCU_0"/> - <value value="0x29" name="A6XX_DBGBUS_CCU_1"/> - <value value="0x2a" name="A6XX_DBGBUS_CCU_2"/> - <value value="0x38" name="A6XX_DBGBUS_VFD_0"/> - <value value="0x39" name="A6XX_DBGBUS_VFD_1"/> - <value value="0x3a" name="A6XX_DBGBUS_VFD_2"/> - <value value="0x3b" name="A6XX_DBGBUS_VFD_3"/> - <value value="0x3c" name="A6XX_DBGBUS_VFD_4"/> - <value value="0x3d" name="A6XX_DBGBUS_VFD_5"/> - <value value="0x40" name="A6XX_DBGBUS_SP_0"/> - <value value="0x41" name="A6XX_DBGBUS_SP_1"/> - <value value="0x42" name="A6XX_DBGBUS_SP_2"/> - <value value="0x48" name="A6XX_DBGBUS_TPL1_0"/> - <value value="0x49" name="A6XX_DBGBUS_TPL1_1"/> - <value value="0x4a" name="A6XX_DBGBUS_TPL1_2"/> - <value value="0x4b" name="A6XX_DBGBUS_TPL1_3"/> - <value value="0x4c" name="A6XX_DBGBUS_TPL1_4"/> - <value value="0x4d" name="A6XX_DBGBUS_TPL1_5"/> - <value value="0x58" name="A6XX_DBGBUS_SPTP_0"/> - <value value="0x59" name="A6XX_DBGBUS_SPTP_1"/> - <value value="0x5a" name="A6XX_DBGBUS_SPTP_2"/> - <value value="0x5b" name="A6XX_DBGBUS_SPTP_3"/> - <value value="0x5c" name="A6XX_DBGBUS_SPTP_4"/> - <value value="0x5d" name="A6XX_DBGBUS_SPTP_5"/> -</enum> - -<enum name="a7xx_state_location"> - <value value="0" name="A7XX_HLSQ_STATE"/> - <value value="1" name="A7XX_HLSQ_DP"/> - <value value="2" name="A7XX_SP_TOP"/> - <value value="3" name="A7XX_USPTP"/> - <value value="4" name="A7XX_HLSQ_DP_STR"/> -</enum> - -<enum name="a7xx_pipe"> - <value value="0" name="A7XX_PIPE_NONE"/> - <value value="1" name="A7XX_PIPE_BR"/> - <value value="2" name="A7XX_PIPE_BV"/> - <value value="3" name="A7XX_PIPE_LPAC"/> -</enum> - -<enum name="a7xx_cluster"> - <value value="0" name="A7XX_CLUSTER_NONE"/> - <value value="1" name="A7XX_CLUSTER_FE"/> - <value value="2" name="A7XX_CLUSTER_SP_VS"/> - <value value="3" name="A7XX_CLUSTER_PC_VS"/> - <value value="4" name="A7XX_CLUSTER_GRAS"/> - <value value="5" name="A7XX_CLUSTER_SP_PS"/> - <value value="6" name="A7XX_CLUSTER_VPC_PS"/> - <value value="7" name="A7XX_CLUSTER_PS"/> -</enum> - -<enum name="a7xx_debugbus_id"> - <value value="1" name="A7XX_DBGBUS_CP_0_0"/> - <value value="2" name="A7XX_DBGBUS_CP_0_1"/> - <value value="3" name="A7XX_DBGBUS_RBBM"/> - <value value="5" name="A7XX_DBGBUS_GBIF_GX"/> - <value value="6" name="A7XX_DBGBUS_GBIF_CX"/> - <value value="7" name="A7XX_DBGBUS_HLSQ"/> - <value value="9" name="A7XX_DBGBUS_UCHE_0"/> - <value value="10" name="A7XX_DBGBUS_UCHE_1"/> - <value value="13" name="A7XX_DBGBUS_TESS_BR"/> - <value value="14" name="A7XX_DBGBUS_TESS_BV"/> - <value value="17" name="A7XX_DBGBUS_PC_BR"/> - <value value="18" name="A7XX_DBGBUS_PC_BV"/> - <value value="21" name="A7XX_DBGBUS_VFDP_BR"/> - <value value="22" name="A7XX_DBGBUS_VFDP_BV"/> - <value value="25" name="A7XX_DBGBUS_VPC_BR"/> - <value value="26" name="A7XX_DBGBUS_VPC_BV"/> - <value value="29" name="A7XX_DBGBUS_TSE_BR"/> - <value value="30" name="A7XX_DBGBUS_TSE_BV"/> - <value value="33" name="A7XX_DBGBUS_RAS_BR"/> - <value value="34" name="A7XX_DBGBUS_RAS_BV"/> - <value value="37" name="A7XX_DBGBUS_VSC"/> - <value value="39" name="A7XX_DBGBUS_COM_0"/> - <value value="43" name="A7XX_DBGBUS_LRZ_BR"/> - <value value="44" name="A7XX_DBGBUS_LRZ_BV"/> - <value value="47" name="A7XX_DBGBUS_UFC_0"/> - <value value="48" name="A7XX_DBGBUS_UFC_1"/> - <value value="55" name="A7XX_DBGBUS_GMU_GX"/> - <value value="59" name="A7XX_DBGBUS_DBGC"/> - <value value="60" name="A7XX_DBGBUS_CX"/> - <value value="61" name="A7XX_DBGBUS_GMU_CX"/> - <value value="62" name="A7XX_DBGBUS_GPC_BR"/> - <value value="63" name="A7XX_DBGBUS_GPC_BV"/> - <value value="66" name="A7XX_DBGBUS_LARC"/> - <value value="68" name="A7XX_DBGBUS_HLSQ_SPTP"/> - <value value="70" name="A7XX_DBGBUS_RB_0"/> - <value value="71" name="A7XX_DBGBUS_RB_1"/> - <value value="72" name="A7XX_DBGBUS_RB_2"/> - <value value="73" name="A7XX_DBGBUS_RB_3"/> - <value value="74" name="A7XX_DBGBUS_RB_4"/> - <value value="75" name="A7XX_DBGBUS_RB_5"/> - <value value="102" name="A7XX_DBGBUS_UCHE_WRAPPER"/> - <value value="106" name="A7XX_DBGBUS_CCU_0"/> - <value value="107" name="A7XX_DBGBUS_CCU_1"/> - <value value="108" name="A7XX_DBGBUS_CCU_2"/> - <value value="109" name="A7XX_DBGBUS_CCU_3"/> - <value value="110" name="A7XX_DBGBUS_CCU_4"/> - <value value="111" name="A7XX_DBGBUS_CCU_5"/> - <value value="138" name="A7XX_DBGBUS_VFD_BR_0"/> - <value value="139" name="A7XX_DBGBUS_VFD_BR_1"/> - <value value="140" name="A7XX_DBGBUS_VFD_BR_2"/> - <value value="141" name="A7XX_DBGBUS_VFD_BR_3"/> - <value value="142" name="A7XX_DBGBUS_VFD_BR_4"/> - <value value="143" name="A7XX_DBGBUS_VFD_BR_5"/> - <value value="144" name="A7XX_DBGBUS_VFD_BR_6"/> - <value value="145" name="A7XX_DBGBUS_VFD_BR_7"/> - <value value="202" name="A7XX_DBGBUS_VFD_BV_0"/> - <value value="203" name="A7XX_DBGBUS_VFD_BV_1"/> - <value value="204" name="A7XX_DBGBUS_VFD_BV_2"/> - <value value="205" name="A7XX_DBGBUS_VFD_BV_3"/> - <value value="234" name="A7XX_DBGBUS_USP_0"/> - <value value="235" name="A7XX_DBGBUS_USP_1"/> - <value value="236" name="A7XX_DBGBUS_USP_2"/> - <value value="237" name="A7XX_DBGBUS_USP_3"/> - <value value="238" name="A7XX_DBGBUS_USP_4"/> - <value value="239" name="A7XX_DBGBUS_USP_5"/> - <value value="266" name="A7XX_DBGBUS_TP_0"/> - <value value="267" name="A7XX_DBGBUS_TP_1"/> - <value value="268" name="A7XX_DBGBUS_TP_2"/> - <value value="269" name="A7XX_DBGBUS_TP_3"/> - <value value="270" name="A7XX_DBGBUS_TP_4"/> - <value value="271" name="A7XX_DBGBUS_TP_5"/> - <value value="272" name="A7XX_DBGBUS_TP_6"/> - <value value="273" name="A7XX_DBGBUS_TP_7"/> - <value value="274" name="A7XX_DBGBUS_TP_8"/> - <value value="275" name="A7XX_DBGBUS_TP_9"/> - <value value="276" name="A7XX_DBGBUS_TP_10"/> - <value value="277" name="A7XX_DBGBUS_TP_11"/> - <value value="330" name="A7XX_DBGBUS_USPTP_0"/> - <value value="331" name="A7XX_DBGBUS_USPTP_1"/> - <value value="332" name="A7XX_DBGBUS_USPTP_2"/> - <value value="333" name="A7XX_DBGBUS_USPTP_3"/> - <value value="334" name="A7XX_DBGBUS_USPTP_4"/> - <value value="335" name="A7XX_DBGBUS_USPTP_5"/> - <value value="336" name="A7XX_DBGBUS_USPTP_6"/> - <value value="337" name="A7XX_DBGBUS_USPTP_7"/> - <value value="338" name="A7XX_DBGBUS_USPTP_8"/> - <value value="339" name="A7XX_DBGBUS_USPTP_9"/> - <value value="340" name="A7XX_DBGBUS_USPTP_10"/> - <value value="341" name="A7XX_DBGBUS_USPTP_11"/> - <value value="396" name="A7XX_DBGBUS_CCHE_0"/> - <value value="397" name="A7XX_DBGBUS_CCHE_1"/> - <value value="398" name="A7XX_DBGBUS_CCHE_2"/> - <value value="408" name="A7XX_DBGBUS_VPC_DSTR_0"/> - <value value="409" name="A7XX_DBGBUS_VPC_DSTR_1"/> - <value value="410" name="A7XX_DBGBUS_VPC_DSTR_2"/> - <value value="411" name="A7XX_DBGBUS_HLSQ_DP_STR_0"/> - <value value="412" name="A7XX_DBGBUS_HLSQ_DP_STR_1"/> - <value value="413" name="A7XX_DBGBUS_HLSQ_DP_STR_2"/> - <value value="414" name="A7XX_DBGBUS_HLSQ_DP_STR_3"/> - <value value="415" name="A7XX_DBGBUS_HLSQ_DP_STR_4"/> - <value value="416" name="A7XX_DBGBUS_HLSQ_DP_STR_5"/> - <value value="443" name="A7XX_DBGBUS_UFC_DSTR_0"/> - <value value="444" name="A7XX_DBGBUS_UFC_DSTR_1"/> - <value value="445" name="A7XX_DBGBUS_UFC_DSTR_2"/> - <value value="446" name="A7XX_DBGBUS_CGC_SUBCORE"/> - <value value="447" name="A7XX_DBGBUS_CGC_CORE"/> -</enum> - -<enum name="a6xx_cp_perfcounter_select"> - <value value="0" name="PERF_CP_ALWAYS_COUNT"/> - <value value="1" name="PERF_CP_BUSY_GFX_CORE_IDLE"/> - <value value="2" name="PERF_CP_BUSY_CYCLES"/> - <value value="3" name="PERF_CP_NUM_PREEMPTIONS"/> - <value value="4" name="PERF_CP_PREEMPTION_REACTION_DELAY"/> - <value value="5" name="PERF_CP_PREEMPTION_SWITCH_OUT_TIME"/> - <value value="6" name="PERF_CP_PREEMPTION_SWITCH_IN_TIME"/> - <value value="7" name="PERF_CP_DEAD_DRAWS_IN_BIN_RENDER"/> - <value value="8" name="PERF_CP_PREDICATED_DRAWS_KILLED"/> - <value value="9" name="PERF_CP_MODE_SWITCH"/> - <value value="10" name="PERF_CP_ZPASS_DONE"/> - <value value="11" name="PERF_CP_CONTEXT_DONE"/> - <value value="12" name="PERF_CP_CACHE_FLUSH"/> - <value value="13" name="PERF_CP_LONG_PREEMPTIONS"/> - <value value="14" name="PERF_CP_SQE_I_CACHE_STARVE"/> - <value value="15" name="PERF_CP_SQE_IDLE"/> - <value value="16" name="PERF_CP_SQE_PM4_STARVE_RB_IB"/> - <value value="17" name="PERF_CP_SQE_PM4_STARVE_SDS"/> - <value value="18" name="PERF_CP_SQE_MRB_STARVE"/> - <value value="19" name="PERF_CP_SQE_RRB_STARVE"/> - <value value="20" name="PERF_CP_SQE_VSD_STARVE"/> - <value value="21" name="PERF_CP_VSD_DECODE_STARVE"/> - <value value="22" name="PERF_CP_SQE_PIPE_OUT_STALL"/> - <value value="23" name="PERF_CP_SQE_SYNC_STALL"/> - <value value="24" name="PERF_CP_SQE_PM4_WFI_STALL"/> - <value value="25" name="PERF_CP_SQE_SYS_WFI_STALL"/> - <value value="26" name="PERF_CP_SQE_T4_EXEC"/> - <value value="27" name="PERF_CP_SQE_LOAD_STATE_EXEC"/> - <value value="28" name="PERF_CP_SQE_SAVE_SDS_STATE"/> - <value value="29" name="PERF_CP_SQE_DRAW_EXEC"/> - <value value="30" name="PERF_CP_SQE_CTXT_REG_BUNCH_EXEC"/> - <value value="31" name="PERF_CP_SQE_EXEC_PROFILED"/> - <value value="32" name="PERF_CP_MEMORY_POOL_EMPTY"/> - <value value="33" name="PERF_CP_MEMORY_POOL_SYNC_STALL"/> - <value value="34" name="PERF_CP_MEMORY_POOL_ABOVE_THRESH"/> - <value value="35" name="PERF_CP_AHB_WR_STALL_PRE_DRAWS"/> - <value value="36" name="PERF_CP_AHB_STALL_SQE_GMU"/> - <value value="37" name="PERF_CP_AHB_STALL_SQE_WR_OTHER"/> - <value value="38" name="PERF_CP_AHB_STALL_SQE_RD_OTHER"/> - <value value="39" name="PERF_CP_CLUSTER0_EMPTY"/> - <value value="40" name="PERF_CP_CLUSTER1_EMPTY"/> - <value value="41" name="PERF_CP_CLUSTER2_EMPTY"/> - <value value="42" name="PERF_CP_CLUSTER3_EMPTY"/> - <value value="43" name="PERF_CP_CLUSTER4_EMPTY"/> - <value value="44" name="PERF_CP_CLUSTER5_EMPTY"/> - <value value="45" name="PERF_CP_PM4_DATA"/> - <value value="46" name="PERF_CP_PM4_HEADERS"/> - <value value="47" name="PERF_CP_VBIF_READ_BEATS"/> - <value value="48" name="PERF_CP_VBIF_WRITE_BEATS"/> - <value value="49" name="PERF_CP_SQE_INSTR_COUNTER"/> -</enum> - -<enum name="a6xx_rbbm_perfcounter_select"> - <value value="0" name="PERF_RBBM_ALWAYS_COUNT"/> - <value value="1" name="PERF_RBBM_ALWAYS_ON"/> - <value value="2" name="PERF_RBBM_TSE_BUSY"/> - <value value="3" name="PERF_RBBM_RAS_BUSY"/> - <value value="4" name="PERF_RBBM_PC_DCALL_BUSY"/> - <value value="5" name="PERF_RBBM_PC_VSD_BUSY"/> - <value value="6" name="PERF_RBBM_STATUS_MASKED"/> - <value value="7" name="PERF_RBBM_COM_BUSY"/> - <value value="8" name="PERF_RBBM_DCOM_BUSY"/> - <value value="9" name="PERF_RBBM_VBIF_BUSY"/> - <value value="10" name="PERF_RBBM_VSC_BUSY"/> - <value value="11" name="PERF_RBBM_TESS_BUSY"/> - <value value="12" name="PERF_RBBM_UCHE_BUSY"/> - <value value="13" name="PERF_RBBM_HLSQ_BUSY"/> -</enum> - -<enum name="a6xx_pc_perfcounter_select"> - <value value="0" name="PERF_PC_BUSY_CYCLES"/> - <value value="1" name="PERF_PC_WORKING_CYCLES"/> - <value value="2" name="PERF_PC_STALL_CYCLES_VFD"/> - <value value="3" name="PERF_PC_STALL_CYCLES_TSE"/> - <value value="4" name="PERF_PC_STALL_CYCLES_VPC"/> - <value value="5" name="PERF_PC_STALL_CYCLES_UCHE"/> - <value value="6" name="PERF_PC_STALL_CYCLES_TESS"/> - <value value="7" name="PERF_PC_STALL_CYCLES_TSE_ONLY"/> - <value value="8" name="PERF_PC_STALL_CYCLES_VPC_ONLY"/> - <value value="9" name="PERF_PC_PASS1_TF_STALL_CYCLES"/> - <value value="10" name="PERF_PC_STARVE_CYCLES_FOR_INDEX"/> - <value value="11" name="PERF_PC_STARVE_CYCLES_FOR_TESS_FACTOR"/> - <value value="12" name="PERF_PC_STARVE_CYCLES_FOR_VIZ_STREAM"/> - <value value="13" name="PERF_PC_STARVE_CYCLES_FOR_POSITION"/> - <value value="14" name="PERF_PC_STARVE_CYCLES_DI"/> - <value value="15" name="PERF_PC_VIS_STREAMS_LOADED"/> - <value value="16" name="PERF_PC_INSTANCES"/> - <value value="17" name="PERF_PC_VPC_PRIMITIVES"/> - <value value="18" name="PERF_PC_DEAD_PRIM"/> - <value value="19" name="PERF_PC_LIVE_PRIM"/> - <value value="20" name="PERF_PC_VERTEX_HITS"/> - <value value="21" name="PERF_PC_IA_VERTICES"/> - <value value="22" name="PERF_PC_IA_PRIMITIVES"/> - <value value="23" name="PERF_PC_GS_PRIMITIVES"/> - <value value="24" name="PERF_PC_HS_INVOCATIONS"/> - <value value="25" name="PERF_PC_DS_INVOCATIONS"/> - <value value="26" name="PERF_PC_VS_INVOCATIONS"/> - <value value="27" name="PERF_PC_GS_INVOCATIONS"/> - <value value="28" name="PERF_PC_DS_PRIMITIVES"/> - <value value="29" name="PERF_PC_VPC_POS_DATA_TRANSACTION"/> - <value value="30" name="PERF_PC_3D_DRAWCALLS"/> - <value value="31" name="PERF_PC_2D_DRAWCALLS"/> - <value value="32" name="PERF_PC_NON_DRAWCALL_GLOBAL_EVENTS"/> - <value value="33" name="PERF_TESS_BUSY_CYCLES"/> - <value value="34" name="PERF_TESS_WORKING_CYCLES"/> - <value value="35" name="PERF_TESS_STALL_CYCLES_PC"/> - <value value="36" name="PERF_TESS_STARVE_CYCLES_PC"/> - <value value="37" name="PERF_PC_TSE_TRANSACTION"/> - <value value="38" name="PERF_PC_TSE_VERTEX"/> - <value value="39" name="PERF_PC_TESS_PC_UV_TRANS"/> - <value value="40" name="PERF_PC_TESS_PC_UV_PATCHES"/> - <value value="41" name="PERF_PC_TESS_FACTOR_TRANS"/> -</enum> - -<enum name="a6xx_vfd_perfcounter_select"> - <value value="0" name="PERF_VFD_BUSY_CYCLES"/> - <value value="1" name="PERF_VFD_STALL_CYCLES_UCHE"/> - <value value="2" name="PERF_VFD_STALL_CYCLES_VPC_ALLOC"/> - <value value="3" name="PERF_VFD_STALL_CYCLES_SP_INFO"/> - <value value="4" name="PERF_VFD_STALL_CYCLES_SP_ATTR"/> - <value value="5" name="PERF_VFD_STARVE_CYCLES_UCHE"/> - <value value="6" name="PERF_VFD_RBUFFER_FULL"/> - <value value="7" name="PERF_VFD_ATTR_INFO_FIFO_FULL"/> - <value value="8" name="PERF_VFD_DECODED_ATTRIBUTE_BYTES"/> - <value value="9" name="PERF_VFD_NUM_ATTRIBUTES"/> - <value value="10" name="PERF_VFD_UPPER_SHADER_FIBERS"/> - <value value="11" name="PERF_VFD_LOWER_SHADER_FIBERS"/> - <value value="12" name="PERF_VFD_MODE_0_FIBERS"/> - <value value="13" name="PERF_VFD_MODE_1_FIBERS"/> - <value value="14" name="PERF_VFD_MODE_2_FIBERS"/> - <value value="15" name="PERF_VFD_MODE_3_FIBERS"/> - <value value="16" name="PERF_VFD_MODE_4_FIBERS"/> - <value value="17" name="PERF_VFD_TOTAL_VERTICES"/> - <value value="18" name="PERF_VFDP_STALL_CYCLES_VFD"/> - <value value="19" name="PERF_VFDP_STALL_CYCLES_VFD_INDEX"/> - <value value="20" name="PERF_VFDP_STALL_CYCLES_VFD_PROG"/> - <value value="21" name="PERF_VFDP_STARVE_CYCLES_PC"/> - <value value="22" name="PERF_VFDP_VS_STAGE_WAVES"/> -</enum> - -<enum name="a6xx_hlsq_perfcounter_select"> - <value value="0" name="PERF_HLSQ_BUSY_CYCLES"/> - <value value="1" name="PERF_HLSQ_STALL_CYCLES_UCHE"/> - <value value="2" name="PERF_HLSQ_STALL_CYCLES_SP_STATE"/> - <value value="3" name="PERF_HLSQ_STALL_CYCLES_SP_FS_STAGE"/> - <value value="4" name="PERF_HLSQ_UCHE_LATENCY_CYCLES"/> - <value value="5" name="PERF_HLSQ_UCHE_LATENCY_COUNT"/> - <value value="6" name="PERF_HLSQ_FS_STAGE_1X_WAVES"/> - <value value="7" name="PERF_HLSQ_FS_STAGE_2X_WAVES"/> - <value value="8" name="PERF_HLSQ_QUADS"/> - <value value="9" name="PERF_HLSQ_CS_INVOCATIONS"/> - <value value="10" name="PERF_HLSQ_COMPUTE_DRAWCALLS"/> - <value value="11" name="PERF_HLSQ_FS_DATA_WAIT_PROGRAMMING"/> - <value value="12" name="PERF_HLSQ_DUAL_FS_PROG_ACTIVE"/> - <value value="13" name="PERF_HLSQ_DUAL_VS_PROG_ACTIVE"/> - <value value="14" name="PERF_HLSQ_FS_BATCH_COUNT_ZERO"/> - <value value="15" name="PERF_HLSQ_VS_BATCH_COUNT_ZERO"/> - <value value="16" name="PERF_HLSQ_WAVE_PENDING_NO_QUAD"/> - <value value="17" name="PERF_HLSQ_WAVE_PENDING_NO_PRIM_BASE"/> - <value value="18" name="PERF_HLSQ_STALL_CYCLES_VPC"/> - <value value="19" name="PERF_HLSQ_PIXELS"/> - <value value="20" name="PERF_HLSQ_DRAW_MODE_SWITCH_VSFS_SYNC"/> -</enum> - -<enum name="a6xx_vpc_perfcounter_select"> - <value value="0" name="PERF_VPC_BUSY_CYCLES"/> - <value value="1" name="PERF_VPC_WORKING_CYCLES"/> - <value value="2" name="PERF_VPC_STALL_CYCLES_UCHE"/> - <value value="3" name="PERF_VPC_STALL_CYCLES_VFD_WACK"/> - <value value="4" name="PERF_VPC_STALL_CYCLES_HLSQ_PRIM_ALLOC"/> - <value value="5" name="PERF_VPC_STALL_CYCLES_PC"/> - <value value="6" name="PERF_VPC_STALL_CYCLES_SP_LM"/> - <value value="7" name="PERF_VPC_STARVE_CYCLES_SP"/> - <value value="8" name="PERF_VPC_STARVE_CYCLES_LRZ"/> - <value value="9" name="PERF_VPC_PC_PRIMITIVES"/> - <value value="10" name="PERF_VPC_SP_COMPONENTS"/> - <value value="11" name="PERF_VPC_STALL_CYCLES_VPCRAM_POS"/> - <value value="12" name="PERF_VPC_LRZ_ASSIGN_PRIMITIVES"/> - <value value="13" name="PERF_VPC_RB_VISIBLE_PRIMITIVES"/> - <value value="14" name="PERF_VPC_LM_TRANSACTION"/> - <value value="15" name="PERF_VPC_STREAMOUT_TRANSACTION"/> - <value value="16" name="PERF_VPC_VS_BUSY_CYCLES"/> - <value value="17" name="PERF_VPC_PS_BUSY_CYCLES"/> - <value value="18" name="PERF_VPC_VS_WORKING_CYCLES"/> - <value value="19" name="PERF_VPC_PS_WORKING_CYCLES"/> - <value value="20" name="PERF_VPC_STARVE_CYCLES_RB"/> - <value value="21" name="PERF_VPC_NUM_VPCRAM_READ_POS"/> - <value value="22" name="PERF_VPC_WIT_FULL_CYCLES"/> - <value value="23" name="PERF_VPC_VPCRAM_FULL_CYCLES"/> - <value value="24" name="PERF_VPC_LM_FULL_WAIT_FOR_INTP_END"/> - <value value="25" name="PERF_VPC_NUM_VPCRAM_WRITE"/> - <value value="26" name="PERF_VPC_NUM_VPCRAM_READ_SO"/> - <value value="27" name="PERF_VPC_NUM_ATTR_REQ_LM"/> -</enum> - -<enum name="a6xx_tse_perfcounter_select"> - <value value="0" name="PERF_TSE_BUSY_CYCLES"/> - <value value="1" name="PERF_TSE_CLIPPING_CYCLES"/> - <value value="2" name="PERF_TSE_STALL_CYCLES_RAS"/> - <value value="3" name="PERF_TSE_STALL_CYCLES_LRZ_BARYPLANE"/> - <value value="4" name="PERF_TSE_STALL_CYCLES_LRZ_ZPLANE"/> - <value value="5" name="PERF_TSE_STARVE_CYCLES_PC"/> - <value value="6" name="PERF_TSE_INPUT_PRIM"/> - <value value="7" name="PERF_TSE_INPUT_NULL_PRIM"/> - <value value="8" name="PERF_TSE_TRIVAL_REJ_PRIM"/> - <value value="9" name="PERF_TSE_CLIPPED_PRIM"/> - <value value="10" name="PERF_TSE_ZERO_AREA_PRIM"/> - <value value="11" name="PERF_TSE_FACENESS_CULLED_PRIM"/> - <value value="12" name="PERF_TSE_ZERO_PIXEL_PRIM"/> - <value value="13" name="PERF_TSE_OUTPUT_NULL_PRIM"/> - <value value="14" name="PERF_TSE_OUTPUT_VISIBLE_PRIM"/> - <value value="15" name="PERF_TSE_CINVOCATION"/> - <value value="16" name="PERF_TSE_CPRIMITIVES"/> - <value value="17" name="PERF_TSE_2D_INPUT_PRIM"/> - <value value="18" name="PERF_TSE_2D_ALIVE_CYCLES"/> - <value value="19" name="PERF_TSE_CLIP_PLANES"/> -</enum> - -<enum name="a6xx_ras_perfcounter_select"> - <value value="0" name="PERF_RAS_BUSY_CYCLES"/> - <value value="1" name="PERF_RAS_SUPERTILE_ACTIVE_CYCLES"/> - <value value="2" name="PERF_RAS_STALL_CYCLES_LRZ"/> - <value value="3" name="PERF_RAS_STARVE_CYCLES_TSE"/> - <value value="4" name="PERF_RAS_SUPER_TILES"/> - <value value="5" name="PERF_RAS_8X4_TILES"/> - <value value="6" name="PERF_RAS_MASKGEN_ACTIVE"/> - <value value="7" name="PERF_RAS_FULLY_COVERED_SUPER_TILES"/> - <value value="8" name="PERF_RAS_FULLY_COVERED_8X4_TILES"/> - <value value="9" name="PERF_RAS_PRIM_KILLED_INVISILBE"/> - <value value="10" name="PERF_RAS_SUPERTILE_GEN_ACTIVE_CYCLES"/> - <value value="11" name="PERF_RAS_LRZ_INTF_WORKING_CYCLES"/> - <value value="12" name="PERF_RAS_BLOCKS"/> -</enum> - -<enum name="a6xx_uche_perfcounter_select"> - <value value="0" name="PERF_UCHE_BUSY_CYCLES"/> - <value value="1" name="PERF_UCHE_STALL_CYCLES_ARBITER"/> - <value value="2" name="PERF_UCHE_VBIF_LATENCY_CYCLES"/> - <value value="3" name="PERF_UCHE_VBIF_LATENCY_SAMPLES"/> - <value value="4" name="PERF_UCHE_VBIF_READ_BEATS_TP"/> - <value value="5" name="PERF_UCHE_VBIF_READ_BEATS_VFD"/> - <value value="6" name="PERF_UCHE_VBIF_READ_BEATS_HLSQ"/> - <value value="7" name="PERF_UCHE_VBIF_READ_BEATS_LRZ"/> - <value value="8" name="PERF_UCHE_VBIF_READ_BEATS_SP"/> - <value value="9" name="PERF_UCHE_READ_REQUESTS_TP"/> - <value value="10" name="PERF_UCHE_READ_REQUESTS_VFD"/> - <value value="11" name="PERF_UCHE_READ_REQUESTS_HLSQ"/> - <value value="12" name="PERF_UCHE_READ_REQUESTS_LRZ"/> - <value value="13" name="PERF_UCHE_READ_REQUESTS_SP"/> - <value value="14" name="PERF_UCHE_WRITE_REQUESTS_LRZ"/> - <value value="15" name="PERF_UCHE_WRITE_REQUESTS_SP"/> - <value value="16" name="PERF_UCHE_WRITE_REQUESTS_VPC"/> - <value value="17" name="PERF_UCHE_WRITE_REQUESTS_VSC"/> - <value value="18" name="PERF_UCHE_EVICTS"/> - <value value="19" name="PERF_UCHE_BANK_REQ0"/> - <value value="20" name="PERF_UCHE_BANK_REQ1"/> - <value value="21" name="PERF_UCHE_BANK_REQ2"/> - <value value="22" name="PERF_UCHE_BANK_REQ3"/> - <value value="23" name="PERF_UCHE_BANK_REQ4"/> - <value value="24" name="PERF_UCHE_BANK_REQ5"/> - <value value="25" name="PERF_UCHE_BANK_REQ6"/> - <value value="26" name="PERF_UCHE_BANK_REQ7"/> - <value value="27" name="PERF_UCHE_VBIF_READ_BEATS_CH0"/> - <value value="28" name="PERF_UCHE_VBIF_READ_BEATS_CH1"/> - <value value="29" name="PERF_UCHE_GMEM_READ_BEATS"/> - <value value="30" name="PERF_UCHE_TPH_REF_FULL"/> - <value value="31" name="PERF_UCHE_TPH_VICTIM_FULL"/> - <value value="32" name="PERF_UCHE_TPH_EXT_FULL"/> - <value value="33" name="PERF_UCHE_VBIF_STALL_WRITE_DATA"/> - <value value="34" name="PERF_UCHE_DCMP_LATENCY_SAMPLES"/> - <value value="35" name="PERF_UCHE_DCMP_LATENCY_CYCLES"/> - <value value="36" name="PERF_UCHE_VBIF_READ_BEATS_PC"/> - <value value="37" name="PERF_UCHE_READ_REQUESTS_PC"/> - <value value="38" name="PERF_UCHE_RAM_READ_REQ"/> - <value value="39" name="PERF_UCHE_RAM_WRITE_REQ"/> -</enum> - -<enum name="a6xx_tp_perfcounter_select"> - <value value="0" name="PERF_TP_BUSY_CYCLES"/> - <value value="1" name="PERF_TP_STALL_CYCLES_UCHE"/> - <value value="2" name="PERF_TP_LATENCY_CYCLES"/> - <value value="3" name="PERF_TP_LATENCY_TRANS"/> - <value value="4" name="PERF_TP_FLAG_CACHE_REQUEST_SAMPLES"/> - <value value="5" name="PERF_TP_FLAG_CACHE_REQUEST_LATENCY"/> - <value value="6" name="PERF_TP_L1_CACHELINE_REQUESTS"/> - <value value="7" name="PERF_TP_L1_CACHELINE_MISSES"/> - <value value="8" name="PERF_TP_SP_TP_TRANS"/> - <value value="9" name="PERF_TP_TP_SP_TRANS"/> - <value value="10" name="PERF_TP_OUTPUT_PIXELS"/> - <value value="11" name="PERF_TP_FILTER_WORKLOAD_16BIT"/> - <value value="12" name="PERF_TP_FILTER_WORKLOAD_32BIT"/> - <value value="13" name="PERF_TP_QUADS_RECEIVED"/> - <value value="14" name="PERF_TP_QUADS_OFFSET"/> - <value value="15" name="PERF_TP_QUADS_SHADOW"/> - <value value="16" name="PERF_TP_QUADS_ARRAY"/> - <value value="17" name="PERF_TP_QUADS_GRADIENT"/> - <value value="18" name="PERF_TP_QUADS_1D"/> - <value value="19" name="PERF_TP_QUADS_2D"/> - <value value="20" name="PERF_TP_QUADS_BUFFER"/> - <value value="21" name="PERF_TP_QUADS_3D"/> - <value value="22" name="PERF_TP_QUADS_CUBE"/> - <value value="23" name="PERF_TP_DIVERGENT_QUADS_RECEIVED"/> - <value value="24" name="PERF_TP_PRT_NON_RESIDENT_EVENTS"/> - <value value="25" name="PERF_TP_OUTPUT_PIXELS_POINT"/> - <value value="26" name="PERF_TP_OUTPUT_PIXELS_BILINEAR"/> - <value value="27" name="PERF_TP_OUTPUT_PIXELS_MIP"/> - <value value="28" name="PERF_TP_OUTPUT_PIXELS_ANISO"/> - <value value="29" name="PERF_TP_OUTPUT_PIXELS_ZERO_LOD"/> - <value value="30" name="PERF_TP_FLAG_CACHE_REQUESTS"/> - <value value="31" name="PERF_TP_FLAG_CACHE_MISSES"/> - <value value="32" name="PERF_TP_L1_5_L2_REQUESTS"/> - <value value="33" name="PERF_TP_2D_OUTPUT_PIXELS"/> - <value value="34" name="PERF_TP_2D_OUTPUT_PIXELS_POINT"/> - <value value="35" name="PERF_TP_2D_OUTPUT_PIXELS_BILINEAR"/> - <value value="36" name="PERF_TP_2D_FILTER_WORKLOAD_16BIT"/> - <value value="37" name="PERF_TP_2D_FILTER_WORKLOAD_32BIT"/> - <value value="38" name="PERF_TP_TPA2TPC_TRANS"/> - <value value="39" name="PERF_TP_L1_MISSES_ASTC_1TILE"/> - <value value="40" name="PERF_TP_L1_MISSES_ASTC_2TILE"/> - <value value="41" name="PERF_TP_L1_MISSES_ASTC_4TILE"/> - <value value="42" name="PERF_TP_L1_5_L2_COMPRESS_REQS"/> - <value value="43" name="PERF_TP_L1_5_L2_COMPRESS_MISS"/> - <value value="44" name="PERF_TP_L1_BANK_CONFLICT"/> - <value value="45" name="PERF_TP_L1_5_MISS_LATENCY_CYCLES"/> - <value value="46" name="PERF_TP_L1_5_MISS_LATENCY_TRANS"/> - <value value="47" name="PERF_TP_QUADS_CONSTANT_MULTIPLIED"/> - <value value="48" name="PERF_TP_FRONTEND_WORKING_CYCLES"/> - <value value="49" name="PERF_TP_L1_TAG_WORKING_CYCLES"/> - <value value="50" name="PERF_TP_L1_DATA_WRITE_WORKING_CYCLES"/> - <value value="51" name="PERF_TP_PRE_L1_DECOM_WORKING_CYCLES"/> - <value value="52" name="PERF_TP_BACKEND_WORKING_CYCLES"/> - <value value="53" name="PERF_TP_FLAG_CACHE_WORKING_CYCLES"/> - <value value="54" name="PERF_TP_L1_5_CACHE_WORKING_CYCLES"/> - <value value="55" name="PERF_TP_STARVE_CYCLES_SP"/> - <value value="56" name="PERF_TP_STARVE_CYCLES_UCHE"/> -</enum> - -<enum name="a6xx_sp_perfcounter_select"> - <value value="0" name="PERF_SP_BUSY_CYCLES"/> - <value value="1" name="PERF_SP_ALU_WORKING_CYCLES"/> - <value value="2" name="PERF_SP_EFU_WORKING_CYCLES"/> - <value value="3" name="PERF_SP_STALL_CYCLES_VPC"/> - <value value="4" name="PERF_SP_STALL_CYCLES_TP"/> - <value value="5" name="PERF_SP_STALL_CYCLES_UCHE"/> - <value value="6" name="PERF_SP_STALL_CYCLES_RB"/> - <value value="7" name="PERF_SP_NON_EXECUTION_CYCLES"/> - <value value="8" name="PERF_SP_WAVE_CONTEXTS"/> - <value value="9" name="PERF_SP_WAVE_CONTEXT_CYCLES"/> - <value value="10" name="PERF_SP_FS_STAGE_WAVE_CYCLES"/> - <value value="11" name="PERF_SP_FS_STAGE_WAVE_SAMPLES"/> - <value value="12" name="PERF_SP_VS_STAGE_WAVE_CYCLES"/> - <value value="13" name="PERF_SP_VS_STAGE_WAVE_SAMPLES"/> - <value value="14" name="PERF_SP_FS_STAGE_DURATION_CYCLES"/> - <value value="15" name="PERF_SP_VS_STAGE_DURATION_CYCLES"/> - <value value="16" name="PERF_SP_WAVE_CTRL_CYCLES"/> - <value value="17" name="PERF_SP_WAVE_LOAD_CYCLES"/> - <value value="18" name="PERF_SP_WAVE_EMIT_CYCLES"/> - <value value="19" name="PERF_SP_WAVE_NOP_CYCLES"/> - <value value="20" name="PERF_SP_WAVE_WAIT_CYCLES"/> - <value value="21" name="PERF_SP_WAVE_FETCH_CYCLES"/> - <value value="22" name="PERF_SP_WAVE_IDLE_CYCLES"/> - <value value="23" name="PERF_SP_WAVE_END_CYCLES"/> - <value value="24" name="PERF_SP_WAVE_LONG_SYNC_CYCLES"/> - <value value="25" name="PERF_SP_WAVE_SHORT_SYNC_CYCLES"/> - <value value="26" name="PERF_SP_WAVE_JOIN_CYCLES"/> - <value value="27" name="PERF_SP_LM_LOAD_INSTRUCTIONS"/> - <value value="28" name="PERF_SP_LM_STORE_INSTRUCTIONS"/> - <value value="29" name="PERF_SP_LM_ATOMICS"/> - <value value="30" name="PERF_SP_GM_LOAD_INSTRUCTIONS"/> - <value value="31" name="PERF_SP_GM_STORE_INSTRUCTIONS"/> - <value value="32" name="PERF_SP_GM_ATOMICS"/> - <value value="33" name="PERF_SP_VS_STAGE_TEX_INSTRUCTIONS"/> - <value value="34" name="PERF_SP_VS_STAGE_EFU_INSTRUCTIONS"/> - <value value="35" name="PERF_SP_VS_STAGE_FULL_ALU_INSTRUCTIONS"/> - <value value="36" name="PERF_SP_VS_STAGE_HALF_ALU_INSTRUCTIONS"/> - <value value="37" name="PERF_SP_FS_STAGE_TEX_INSTRUCTIONS"/> - <value value="38" name="PERF_SP_FS_STAGE_CFLOW_INSTRUCTIONS"/> - <value value="39" name="PERF_SP_FS_STAGE_EFU_INSTRUCTIONS"/> - <value value="40" name="PERF_SP_FS_STAGE_FULL_ALU_INSTRUCTIONS"/> - <value value="41" name="PERF_SP_FS_STAGE_HALF_ALU_INSTRUCTIONS"/> - <value value="42" name="PERF_SP_FS_STAGE_BARY_INSTRUCTIONS"/> - <value value="43" name="PERF_SP_VS_INSTRUCTIONS"/> - <value value="44" name="PERF_SP_FS_INSTRUCTIONS"/> - <value value="45" name="PERF_SP_ADDR_LOCK_COUNT"/> - <value value="46" name="PERF_SP_UCHE_READ_TRANS"/> - <value value="47" name="PERF_SP_UCHE_WRITE_TRANS"/> - <value value="48" name="PERF_SP_EXPORT_VPC_TRANS"/> - <value value="49" name="PERF_SP_EXPORT_RB_TRANS"/> - <value value="50" name="PERF_SP_PIXELS_KILLED"/> - <value value="51" name="PERF_SP_ICL1_REQUESTS"/> - <value value="52" name="PERF_SP_ICL1_MISSES"/> - <value value="53" name="PERF_SP_HS_INSTRUCTIONS"/> - <value value="54" name="PERF_SP_DS_INSTRUCTIONS"/> - <value value="55" name="PERF_SP_GS_INSTRUCTIONS"/> - <value value="56" name="PERF_SP_CS_INSTRUCTIONS"/> - <value value="57" name="PERF_SP_GPR_READ"/> - <value value="58" name="PERF_SP_GPR_WRITE"/> - <value value="59" name="PERF_SP_FS_STAGE_HALF_EFU_INSTRUCTIONS"/> - <value value="60" name="PERF_SP_VS_STAGE_HALF_EFU_INSTRUCTIONS"/> - <value value="61" name="PERF_SP_LM_BANK_CONFLICTS"/> - <value value="62" name="PERF_SP_TEX_CONTROL_WORKING_CYCLES"/> - <value value="63" name="PERF_SP_LOAD_CONTROL_WORKING_CYCLES"/> - <value value="64" name="PERF_SP_FLOW_CONTROL_WORKING_CYCLES"/> - <value value="65" name="PERF_SP_LM_WORKING_CYCLES"/> - <value value="66" name="PERF_SP_DISPATCHER_WORKING_CYCLES"/> - <value value="67" name="PERF_SP_SEQUENCER_WORKING_CYCLES"/> - <value value="68" name="PERF_SP_LOW_EFFICIENCY_STARVED_BY_TP"/> - <value value="69" name="PERF_SP_STARVE_CYCLES_HLSQ"/> - <value value="70" name="PERF_SP_NON_EXECUTION_LS_CYCLES"/> - <value value="71" name="PERF_SP_WORKING_EU"/> - <value value="72" name="PERF_SP_ANY_EU_WORKING"/> - <value value="73" name="PERF_SP_WORKING_EU_FS_STAGE"/> - <value value="74" name="PERF_SP_ANY_EU_WORKING_FS_STAGE"/> - <value value="75" name="PERF_SP_WORKING_EU_VS_STAGE"/> - <value value="76" name="PERF_SP_ANY_EU_WORKING_VS_STAGE"/> - <value value="77" name="PERF_SP_WORKING_EU_CS_STAGE"/> - <value value="78" name="PERF_SP_ANY_EU_WORKING_CS_STAGE"/> - <value value="79" name="PERF_SP_GPR_READ_PREFETCH"/> - <value value="80" name="PERF_SP_GPR_READ_CONFLICT"/> - <value value="81" name="PERF_SP_GPR_WRITE_CONFLICT"/> - <value value="82" name="PERF_SP_GM_LOAD_LATENCY_CYCLES"/> - <value value="83" name="PERF_SP_GM_LOAD_LATENCY_SAMPLES"/> - <value value="84" name="PERF_SP_EXECUTABLE_WAVES"/> -</enum> - -<enum name="a6xx_rb_perfcounter_select"> - <value value="0" name="PERF_RB_BUSY_CYCLES"/> - <value value="1" name="PERF_RB_STALL_CYCLES_HLSQ"/> - <value value="2" name="PERF_RB_STALL_CYCLES_FIFO0_FULL"/> - <value value="3" name="PERF_RB_STALL_CYCLES_FIFO1_FULL"/> - <value value="4" name="PERF_RB_STALL_CYCLES_FIFO2_FULL"/> - <value value="5" name="PERF_RB_STARVE_CYCLES_SP"/> - <value value="6" name="PERF_RB_STARVE_CYCLES_LRZ_TILE"/> - <value value="7" name="PERF_RB_STARVE_CYCLES_CCU"/> - <value value="8" name="PERF_RB_STARVE_CYCLES_Z_PLANE"/> - <value value="9" name="PERF_RB_STARVE_CYCLES_BARY_PLANE"/> - <value value="10" name="PERF_RB_Z_WORKLOAD"/> - <value value="11" name="PERF_RB_HLSQ_ACTIVE"/> - <value value="12" name="PERF_RB_Z_READ"/> - <value value="13" name="PERF_RB_Z_WRITE"/> - <value value="14" name="PERF_RB_C_READ"/> - <value value="15" name="PERF_RB_C_WRITE"/> - <value value="16" name="PERF_RB_TOTAL_PASS"/> - <value value="17" name="PERF_RB_Z_PASS"/> - <value value="18" name="PERF_RB_Z_FAIL"/> - <value value="19" name="PERF_RB_S_FAIL"/> - <value value="20" name="PERF_RB_BLENDED_FXP_COMPONENTS"/> - <value value="21" name="PERF_RB_BLENDED_FP16_COMPONENTS"/> - <value value="22" name="PERF_RB_PS_INVOCATIONS"/> - <value value="23" name="PERF_RB_2D_ALIVE_CYCLES"/> - <value value="24" name="PERF_RB_2D_STALL_CYCLES_A2D"/> - <value value="25" name="PERF_RB_2D_STARVE_CYCLES_SRC"/> - <value value="26" name="PERF_RB_2D_STARVE_CYCLES_SP"/> - <value value="27" name="PERF_RB_2D_STARVE_CYCLES_DST"/> - <value value="28" name="PERF_RB_2D_VALID_PIXELS"/> - <value value="29" name="PERF_RB_3D_PIXELS"/> - <value value="30" name="PERF_RB_BLENDER_WORKING_CYCLES"/> - <value value="31" name="PERF_RB_ZPROC_WORKING_CYCLES"/> - <value value="32" name="PERF_RB_CPROC_WORKING_CYCLES"/> - <value value="33" name="PERF_RB_SAMPLER_WORKING_CYCLES"/> - <value value="34" name="PERF_RB_STALL_CYCLES_CCU_COLOR_READ"/> - <value value="35" name="PERF_RB_STALL_CYCLES_CCU_COLOR_WRITE"/> - <value value="36" name="PERF_RB_STALL_CYCLES_CCU_DEPTH_READ"/> - <value value="37" name="PERF_RB_STALL_CYCLES_CCU_DEPTH_WRITE"/> - <value value="38" name="PERF_RB_STALL_CYCLES_VPC"/> - <value value="39" name="PERF_RB_2D_INPUT_TRANS"/> - <value value="40" name="PERF_RB_2D_OUTPUT_RB_DST_TRANS"/> - <value value="41" name="PERF_RB_2D_OUTPUT_RB_SRC_TRANS"/> - <value value="42" name="PERF_RB_BLENDED_FP32_COMPONENTS"/> - <value value="43" name="PERF_RB_COLOR_PIX_TILES"/> - <value value="44" name="PERF_RB_STALL_CYCLES_CCU"/> - <value value="45" name="PERF_RB_EARLY_Z_ARB3_GRANT"/> - <value value="46" name="PERF_RB_LATE_Z_ARB3_GRANT"/> - <value value="47" name="PERF_RB_EARLY_Z_SKIP_GRANT"/> -</enum> - -<enum name="a6xx_vsc_perfcounter_select"> - <value value="0" name="PERF_VSC_BUSY_CYCLES"/> - <value value="1" name="PERF_VSC_WORKING_CYCLES"/> - <value value="2" name="PERF_VSC_STALL_CYCLES_UCHE"/> - <value value="3" name="PERF_VSC_EOT_NUM"/> - <value value="4" name="PERF_VSC_INPUT_TILES"/> -</enum> - -<enum name="a6xx_ccu_perfcounter_select"> - <value value="0" name="PERF_CCU_BUSY_CYCLES"/> - <value value="1" name="PERF_CCU_STALL_CYCLES_RB_DEPTH_RETURN"/> - <value value="2" name="PERF_CCU_STALL_CYCLES_RB_COLOR_RETURN"/> - <value value="3" name="PERF_CCU_STARVE_CYCLES_FLAG_RETURN"/> - <value value="4" name="PERF_CCU_DEPTH_BLOCKS"/> - <value value="5" name="PERF_CCU_COLOR_BLOCKS"/> - <value value="6" name="PERF_CCU_DEPTH_BLOCK_HIT"/> - <value value="7" name="PERF_CCU_COLOR_BLOCK_HIT"/> - <value value="8" name="PERF_CCU_PARTIAL_BLOCK_READ"/> - <value value="9" name="PERF_CCU_GMEM_READ"/> - <value value="10" name="PERF_CCU_GMEM_WRITE"/> - <value value="11" name="PERF_CCU_DEPTH_READ_FLAG0_COUNT"/> - <value value="12" name="PERF_CCU_DEPTH_READ_FLAG1_COUNT"/> - <value value="13" name="PERF_CCU_DEPTH_READ_FLAG2_COUNT"/> - <value value="14" name="PERF_CCU_DEPTH_READ_FLAG3_COUNT"/> - <value value="15" name="PERF_CCU_DEPTH_READ_FLAG4_COUNT"/> - <value value="16" name="PERF_CCU_DEPTH_READ_FLAG5_COUNT"/> - <value value="17" name="PERF_CCU_DEPTH_READ_FLAG6_COUNT"/> - <value value="18" name="PERF_CCU_DEPTH_READ_FLAG8_COUNT"/> - <value value="19" name="PERF_CCU_COLOR_READ_FLAG0_COUNT"/> - <value value="20" name="PERF_CCU_COLOR_READ_FLAG1_COUNT"/> - <value value="21" name="PERF_CCU_COLOR_READ_FLAG2_COUNT"/> - <value value="22" name="PERF_CCU_COLOR_READ_FLAG3_COUNT"/> - <value value="23" name="PERF_CCU_COLOR_READ_FLAG4_COUNT"/> - <value value="24" name="PERF_CCU_COLOR_READ_FLAG5_COUNT"/> - <value value="25" name="PERF_CCU_COLOR_READ_FLAG6_COUNT"/> - <value value="26" name="PERF_CCU_COLOR_READ_FLAG8_COUNT"/> - <value value="27" name="PERF_CCU_2D_RD_REQ"/> - <value value="28" name="PERF_CCU_2D_WR_REQ"/> -</enum> - -<enum name="a6xx_lrz_perfcounter_select"> - <value value="0" name="PERF_LRZ_BUSY_CYCLES"/> - <value value="1" name="PERF_LRZ_STARVE_CYCLES_RAS"/> - <value value="2" name="PERF_LRZ_STALL_CYCLES_RB"/> - <value value="3" name="PERF_LRZ_STALL_CYCLES_VSC"/> - <value value="4" name="PERF_LRZ_STALL_CYCLES_VPC"/> - <value value="5" name="PERF_LRZ_STALL_CYCLES_FLAG_PREFETCH"/> - <value value="6" name="PERF_LRZ_STALL_CYCLES_UCHE"/> - <value value="7" name="PERF_LRZ_LRZ_READ"/> - <value value="8" name="PERF_LRZ_LRZ_WRITE"/> - <value value="9" name="PERF_LRZ_READ_LATENCY"/> - <value value="10" name="PERF_LRZ_MERGE_CACHE_UPDATING"/> - <value value="11" name="PERF_LRZ_PRIM_KILLED_BY_MASKGEN"/> - <value value="12" name="PERF_LRZ_PRIM_KILLED_BY_LRZ"/> - <value value="13" name="PERF_LRZ_VISIBLE_PRIM_AFTER_LRZ"/> - <value value="14" name="PERF_LRZ_FULL_8X8_TILES"/> - <value value="15" name="PERF_LRZ_PARTIAL_8X8_TILES"/> - <value value="16" name="PERF_LRZ_TILE_KILLED"/> - <value value="17" name="PERF_LRZ_TOTAL_PIXEL"/> - <value value="18" name="PERF_LRZ_VISIBLE_PIXEL_AFTER_LRZ"/> - <value value="19" name="PERF_LRZ_FULLY_COVERED_TILES"/> - <value value="20" name="PERF_LRZ_PARTIAL_COVERED_TILES"/> - <value value="21" name="PERF_LRZ_FEEDBACK_ACCEPT"/> - <value value="22" name="PERF_LRZ_FEEDBACK_DISCARD"/> - <value value="23" name="PERF_LRZ_FEEDBACK_STALL"/> - <value value="24" name="PERF_LRZ_STALL_CYCLES_RB_ZPLANE"/> - <value value="25" name="PERF_LRZ_STALL_CYCLES_RB_BPLANE"/> - <value value="26" name="PERF_LRZ_STALL_CYCLES_VC"/> - <value value="27" name="PERF_LRZ_RAS_MASK_TRANS"/> -</enum> - -<enum name="a6xx_cmp_perfcounter_select"> - <value value="0" name="PERF_CMPDECMP_STALL_CYCLES_ARB"/> - <value value="1" name="PERF_CMPDECMP_VBIF_LATENCY_CYCLES"/> - <value value="2" name="PERF_CMPDECMP_VBIF_LATENCY_SAMPLES"/> - <value value="3" name="PERF_CMPDECMP_VBIF_READ_DATA_CCU"/> - <value value="4" name="PERF_CMPDECMP_VBIF_WRITE_DATA_CCU"/> - <value value="5" name="PERF_CMPDECMP_VBIF_READ_REQUEST"/> - <value value="6" name="PERF_CMPDECMP_VBIF_WRITE_REQUEST"/> - <value value="7" name="PERF_CMPDECMP_VBIF_READ_DATA"/> - <value value="8" name="PERF_CMPDECMP_VBIF_WRITE_DATA"/> - <value value="9" name="PERF_CMPDECMP_FLAG_FETCH_CYCLES"/> - <value value="10" name="PERF_CMPDECMP_FLAG_FETCH_SAMPLES"/> - <value value="11" name="PERF_CMPDECMP_DEPTH_WRITE_FLAG1_COUNT"/> - <value value="12" name="PERF_CMPDECMP_DEPTH_WRITE_FLAG2_COUNT"/> - <value value="13" name="PERF_CMPDECMP_DEPTH_WRITE_FLAG3_COUNT"/> - <value value="14" name="PERF_CMPDECMP_DEPTH_WRITE_FLAG4_COUNT"/> - <value value="15" name="PERF_CMPDECMP_DEPTH_WRITE_FLAG5_COUNT"/> - <value value="16" name="PERF_CMPDECMP_DEPTH_WRITE_FLAG6_COUNT"/> - <value value="17" name="PERF_CMPDECMP_DEPTH_WRITE_FLAG8_COUNT"/> - <value value="18" name="PERF_CMPDECMP_COLOR_WRITE_FLAG1_COUNT"/> - <value value="19" name="PERF_CMPDECMP_COLOR_WRITE_FLAG2_COUNT"/> - <value value="20" name="PERF_CMPDECMP_COLOR_WRITE_FLAG3_COUNT"/> - <value value="21" name="PERF_CMPDECMP_COLOR_WRITE_FLAG4_COUNT"/> - <value value="22" name="PERF_CMPDECMP_COLOR_WRITE_FLAG5_COUNT"/> - <value value="23" name="PERF_CMPDECMP_COLOR_WRITE_FLAG6_COUNT"/> - <value value="24" name="PERF_CMPDECMP_COLOR_WRITE_FLAG8_COUNT"/> - <value value="25" name="PERF_CMPDECMP_2D_STALL_CYCLES_VBIF_REQ"/> - <value value="26" name="PERF_CMPDECMP_2D_STALL_CYCLES_VBIF_WR"/> - <value value="27" name="PERF_CMPDECMP_2D_STALL_CYCLES_VBIF_RETURN"/> - <value value="28" name="PERF_CMPDECMP_2D_RD_DATA"/> - <value value="29" name="PERF_CMPDECMP_2D_WR_DATA"/> - <value value="30" name="PERF_CMPDECMP_VBIF_READ_DATA_UCHE_CH0"/> - <value value="31" name="PERF_CMPDECMP_VBIF_READ_DATA_UCHE_CH1"/> - <value value="32" name="PERF_CMPDECMP_2D_OUTPUT_TRANS"/> - <value value="33" name="PERF_CMPDECMP_VBIF_WRITE_DATA_UCHE"/> - <value value="34" name="PERF_CMPDECMP_DEPTH_WRITE_FLAG0_COUNT"/> - <value value="35" name="PERF_CMPDECMP_COLOR_WRITE_FLAG0_COUNT"/> - <value value="36" name="PERF_CMPDECMP_COLOR_WRITE_FLAGALPHA_COUNT"/> - <value value="37" name="PERF_CMPDECMP_2D_BUSY_CYCLES"/> - <value value="38" name="PERF_CMPDECMP_2D_REORDER_STARVE_CYCLES"/> - <value value="39" name="PERF_CMPDECMP_2D_PIXELS"/> -</enum> - -<!-- -Used in a6xx_2d_blit_cntl.. the value mostly seems to correlate to the -component type/size, so I think it relates to internal format used for -blending? The one exception is that 16b unorm and 32b float use the -same value... maybe 16b unorm is uncommon enough that it was just easier -to upconvert to 32b float internally? - - 8b unorm: 10 (sometimes 0, is the high bit part of something else?) -16b unorm: 4 - -32b int: 7 -16b int: 6 - 8b int: 5 - -32b float: 4 -16b float: 3 - --> -<enum name="a6xx_2d_ifmt"> - <value value="0x10" name="R2D_UNORM8"/> - <value value="0x7" name="R2D_INT32"/> - <value value="0x6" name="R2D_INT16"/> - <value value="0x5" name="R2D_INT8"/> - <value value="0x4" name="R2D_FLOAT32"/> - <value value="0x3" name="R2D_FLOAT16"/> - <value value="0x1" name="R2D_UNORM8_SRGB"/> - <value value="0x0" name="R2D_RAW"/> -</enum> - -<enum name="a6xx_ztest_mode"> - <doc>Allow early z-test and early-lrz (if applicable)</doc> - <value value="0x0" name="A6XX_EARLY_Z"/> - <doc>Disable early z-test and early-lrz test (if applicable)</doc> - <value value="0x1" name="A6XX_LATE_Z"/> - <doc> - A special mode that allows early-lrz test but disables - early-z test. Which might sound a bit funny, since - lrz-test happens before z-test. But as long as a couple - conditions are maintained this allows using lrz-test in - cases where fragment shader has kill/discard: - - 1) Disable lrz-write in cases where it is uncertain during - binning pass that a fragment will pass. Ie. if frag - shader has-kill, writes-z, or alpha/stencil test is - enabled. (For correctness, lrz-write must be disabled - when blend is enabled.) This is analogous to how a - z-prepass works. - - 2) Disable lrz-write and test if a depth-test direction - reversal is detected. Due to condition (1), the contents - of the lrz buffer are a conservative estimation of the - depth buffer during the draw pass. Meaning that geometry - that we know for certain will not be visible will not pass - lrz-test. But geometry which may be (or contributes to - blend) will pass the lrz-test. - - This allows us to keep early-lrz-test in cases where the frag - shader does not write-z (ie. we know the z-value before FS) - and does not have side-effects (image/ssbo writes, etc), but - does have kill/discard. Which turns out to be a common - enough case that it is useful to keep early-lrz test against - the conservative lrz buffer to discard fragments that we - know will definitely not be visible. - </doc> - <value value="0x2" name="A6XX_EARLY_LRZ_LATE_Z"/> - <doc>Not a real hw value, used internally by mesa</doc> - <value value="0x3" name="A6XX_INVALID_ZTEST"/> -</enum> - -<enum name="a6xx_tess_spacing"> - <value value="0x0" name="TESS_EQUAL"/> - <value value="0x2" name="TESS_FRACTIONAL_ODD"/> - <value value="0x3" name="TESS_FRACTIONAL_EVEN"/> -</enum> -<enum name="a6xx_tess_output"> - <value value="0x0" name="TESS_POINTS"/> - <value value="0x1" name="TESS_LINES"/> - <value value="0x2" name="TESS_CW_TRIS"/> - <value value="0x3" name="TESS_CCW_TRIS"/> -</enum> - -<enum name="a7xx_cp_perfcounter_select"> - <value value="0" name="A7XX_PERF_CP_ALWAYS_COUNT"/> - <value value="1" name="A7XX_PERF_CP_BUSY_GFX_CORE_IDLE"/> - <value value="2" name="A7XX_PERF_CP_BUSY_CYCLES"/> - <value value="3" name="A7XX_PERF_CP_NUM_PREEMPTIONS"/> - <value value="4" name="A7XX_PERF_CP_PREEMPTION_REACTION_DELAY"/> - <value value="5" name="A7XX_PERF_CP_PREEMPTION_SWITCH_OUT_TIME"/> - <value value="6" name="A7XX_PERF_CP_PREEMPTION_SWITCH_IN_TIME"/> - <value value="7" name="A7XX_PERF_CP_DEAD_DRAWS_IN_BIN_RENDER"/> - <value value="8" name="A7XX_PERF_CP_PREDICATED_DRAWS_KILLED"/> - <value value="9" name="A7XX_PERF_CP_MODE_SWITCH"/> - <value value="10" name="A7XX_PERF_CP_ZPASS_DONE"/> - <value value="11" name="A7XX_PERF_CP_CONTEXT_DONE"/> - <value value="12" name="A7XX_PERF_CP_CACHE_FLUSH"/> - <value value="13" name="A7XX_PERF_CP_LONG_PREEMPTIONS"/> - <value value="14" name="A7XX_PERF_CP_SQE_I_CACHE_STARVE"/> - <value value="15" name="A7XX_PERF_CP_SQE_IDLE"/> - <value value="16" name="A7XX_PERF_CP_SQE_PM4_STARVE_RB_IB"/> - <value value="17" name="A7XX_PERF_CP_SQE_PM4_STARVE_SDS"/> - <value value="18" name="A7XX_PERF_CP_SQE_MRB_STARVE"/> - <value value="19" name="A7XX_PERF_CP_SQE_RRB_STARVE"/> - <value value="20" name="A7XX_PERF_CP_SQE_VSD_STARVE"/> - <value value="21" name="A7XX_PERF_CP_VSD_DECODE_STARVE"/> - <value value="22" name="A7XX_PERF_CP_SQE_PIPE_OUT_STALL"/> - <value value="23" name="A7XX_PERF_CP_SQE_SYNC_STALL"/> - <value value="24" name="A7XX_PERF_CP_SQE_PM4_WFI_STALL"/> - <value value="25" name="A7XX_PERF_CP_SQE_SYS_WFI_STALL"/> - <value value="26" name="A7XX_PERF_CP_SQE_T4_EXEC"/> - <value value="27" name="A7XX_PERF_CP_SQE_LOAD_STATE_EXEC"/> - <value value="28" name="A7XX_PERF_CP_SQE_SAVE_SDS_STATE"/> - <value value="29" name="A7XX_PERF_CP_SQE_DRAW_EXEC"/> - <value value="30" name="A7XX_PERF_CP_SQE_CTXT_REG_BUNCH_EXEC"/> - <value value="31" name="A7XX_PERF_CP_SQE_EXEC_PROFILED"/> - <value value="32" name="A7XX_PERF_CP_MEMORY_POOL_EMPTY"/> - <value value="33" name="A7XX_PERF_CP_MEMORY_POOL_SYNC_STALL"/> - <value value="34" name="A7XX_PERF_CP_MEMORY_POOL_ABOVE_THRESH"/> - <value value="35" name="A7XX_PERF_CP_AHB_WR_STALL_PRE_DRAWS"/> - <value value="36" name="A7XX_PERF_CP_AHB_STALL_SQE_GMU"/> - <value value="37" name="A7XX_PERF_CP_AHB_STALL_SQE_WR_OTHER"/> - <value value="38" name="A7XX_PERF_CP_AHB_STALL_SQE_RD_OTHER"/> - <value value="39" name="A7XX_PERF_CP_CLUSTER0_EMPTY"/> - <value value="40" name="A7XX_PERF_CP_CLUSTER1_EMPTY"/> - <value value="41" name="A7XX_PERF_CP_CLUSTER2_EMPTY"/> - <value value="42" name="A7XX_PERF_CP_CLUSTER3_EMPTY"/> - <value value="43" name="A7XX_PERF_CP_CLUSTER4_EMPTY"/> - <value value="44" name="A7XX_PERF_CP_CLUSTER5_EMPTY"/> - <value value="45" name="A7XX_PERF_CP_PM4_DATA"/> - <value value="46" name="A7XX_PERF_CP_PM4_HEADERS"/> - <value value="47" name="A7XX_PERF_CP_VBIF_READ_BEATS"/> - <value value="48" name="A7XX_PERF_CP_VBIF_WRITE_BEATS"/> - <value value="49" name="A7XX_PERF_CP_SQE_INSTR_COUNTER"/> - <value value="50" name="A7XX_PERF_CP_RESERVED_50"/> - <value value="51" name="A7XX_PERF_CP_RESERVED_51"/> - <value value="52" name="A7XX_PERF_CP_RESERVED_52"/> - <value value="53" name="A7XX_PERF_CP_RESERVED_53"/> - <value value="54" name="A7XX_PERF_CP_RESERVED_54"/> - <value value="55" name="A7XX_PERF_CP_RESERVED_55"/> - <value value="56" name="A7XX_PERF_CP_RESERVED_56"/> - <value value="57" name="A7XX_PERF_CP_RESERVED_57"/> - <value value="58" name="A7XX_PERF_CP_RESERVED_58"/> - <value value="59" name="A7XX_PERF_CP_RESERVED_59"/> - <value value="60" name="A7XX_PERF_CP_CLUSTER0_FULL"/> - <value value="61" name="A7XX_PERF_CP_CLUSTER1_FULL"/> - <value value="62" name="A7XX_PERF_CP_CLUSTER2_FULL"/> - <value value="63" name="A7XX_PERF_CP_CLUSTER3_FULL"/> - <value value="64" name="A7XX_PERF_CP_CLUSTER4_FULL"/> - <value value="65" name="A7XX_PERF_CP_CLUSTER5_FULL"/> - <value value="66" name="A7XX_PERF_CP_CLUSTER6_FULL"/> - <value value="67" name="A7XX_PERF_CP_CLUSTER6_EMPTY"/> - <value value="68" name="A7XX_PERF_CP_ICACHE_MISSES"/> - <value value="69" name="A7XX_PERF_CP_ICACHE_HITS"/> - <value value="70" name="A7XX_PERF_CP_ICACHE_STALL"/> - <value value="71" name="A7XX_PERF_CP_DCACHE_MISSES"/> - <value value="72" name="A7XX_PERF_CP_DCACHE_HITS"/> - <value value="73" name="A7XX_PERF_CP_DCACHE_STALLS"/> - <value value="74" name="A7XX_PERF_CP_AQE_SQE_STALL"/> - <value value="75" name="A7XX_PERF_CP_SQE_AQE_STARVE"/> - <value value="76" name="A7XX_PERF_CP_PREEMPT_LATENCY"/> - <value value="77" name="A7XX_PERF_CP_SQE_MD8_STALL_CYCLES"/> - <value value="78" name="A7XX_PERF_CP_SQE_MESH_EXEC_CYCLES"/> - <value value="79" name="A7XX_PERF_CP_AQE_NUM_AS_CHUNKS"/> - <value value="80" name="A7XX_PERF_CP_AQE_NUM_MS_CHUNKS"/> -</enum> - -<enum name="a7xx_rbbm_perfcounter_select"> - <value value="0" name="A7XX_PERF_RBBM_ALWAYS_COUNT"/> - <value value="1" name="A7XX_PERF_RBBM_ALWAYS_ON"/> - <value value="2" name="A7XX_PERF_RBBM_TSE_BUSY"/> - <value value="3" name="A7XX_PERF_RBBM_RAS_BUSY"/> - <value value="4" name="A7XX_PERF_RBBM_PC_DCALL_BUSY"/> - <value value="5" name="A7XX_PERF_RBBM_PC_VSD_BUSY"/> - <value value="6" name="A7XX_PERF_RBBM_STATUS_MASKED"/> - <value value="7" name="A7XX_PERF_RBBM_COM_BUSY"/> - <value value="8" name="A7XX_PERF_RBBM_DCOM_BUSY"/> - <value value="9" name="A7XX_PERF_RBBM_VBIF_BUSY"/> - <value value="10" name="A7XX_PERF_RBBM_VSC_BUSY"/> - <value value="11" name="A7XX_PERF_RBBM_TESS_BUSY"/> - <value value="12" name="A7XX_PERF_RBBM_UCHE_BUSY"/> - <value value="13" name="A7XX_PERF_RBBM_HLSQ_BUSY"/> -</enum> - -<enum name="a7xx_pc_perfcounter_select"> - <value value="0" name="A7XX_PERF_PC_BUSY_CYCLES"/> - <value value="1" name="A7XX_PERF_PC_WORKING_CYCLES"/> - <value value="2" name="A7XX_PERF_PC_STALL_CYCLES_VFD"/> - <value value="3" name="A7XX_PERF_PC_RESERVED"/> - <value value="4" name="A7XX_PERF_PC_STALL_CYCLES_VPC"/> - <value value="5" name="A7XX_PERF_PC_STALL_CYCLES_UCHE"/> - <value value="6" name="A7XX_PERF_PC_STALL_CYCLES_TESS"/> - <value value="7" name="A7XX_PERF_PC_STALL_CYCLES_VFD_ONLY"/> - <value value="8" name="A7XX_PERF_PC_STALL_CYCLES_VPC_ONLY"/> - <value value="9" name="A7XX_PERF_PC_PASS1_TF_STALL_CYCLES"/> - <value value="10" name="A7XX_PERF_PC_STARVE_CYCLES_FOR_INDEX"/> - <value value="11" name="A7XX_PERF_PC_STARVE_CYCLES_FOR_TESS_FACTOR"/> - <value value="12" name="A7XX_PERF_PC_STARVE_CYCLES_FOR_VIZ_STREAM"/> - <value value="13" name="A7XX_PERF_PC_STARVE_CYCLES_DI"/> - <value value="14" name="A7XX_PERF_PC_VIS_STREAMS_LOADED"/> - <value value="15" name="A7XX_PERF_PC_INSTANCES"/> - <value value="16" name="A7XX_PERF_PC_VPC_PRIMITIVES"/> - <value value="17" name="A7XX_PERF_PC_DEAD_PRIM"/> - <value value="18" name="A7XX_PERF_PC_LIVE_PRIM"/> - <value value="19" name="A7XX_PERF_PC_VERTEX_HITS"/> - <value value="20" name="A7XX_PERF_PC_IA_VERTICES"/> - <value value="21" name="A7XX_PERF_PC_IA_PRIMITIVES"/> - <value value="22" name="A7XX_PERF_PC_RESERVED_22"/> - <value value="23" name="A7XX_PERF_PC_HS_INVOCATIONS"/> - <value value="24" name="A7XX_PERF_PC_DS_INVOCATIONS"/> - <value value="25" name="A7XX_PERF_PC_VS_INVOCATIONS"/> - <value value="26" name="A7XX_PERF_PC_GS_INVOCATIONS"/> - <value value="27" name="A7XX_PERF_PC_DS_PRIMITIVES"/> - <value value="28" name="A7XX_PERF_PC_3D_DRAWCALLS"/> - <value value="29" name="A7XX_PERF_PC_2D_DRAWCALLS"/> - <value value="30" name="A7XX_PERF_PC_NON_DRAWCALL_GLOBAL_EVENTS"/> - <value value="31" name="A7XX_PERF_PC_TESS_BUSY_CYCLES"/> - <value value="32" name="A7XX_PERF_PC_TESS_WORKING_CYCLES"/> - <value value="33" name="A7XX_PERF_PC_TESS_STALL_CYCLES_PC"/> - <value value="34" name="A7XX_PERF_PC_TESS_STARVE_CYCLES_PC"/> - <value value="35" name="A7XX_PERF_PC_TESS_SINGLE_PRIM_CYCLES"/> - <value value="36" name="A7XX_PERF_PC_TESS_PC_UV_TRANS"/> - <value value="37" name="A7XX_PERF_PC_TESS_PC_UV_PATCHES"/> - <value value="38" name="A7XX_PERF_PC_TESS_FACTOR_TRANS"/> - <value value="39" name="A7XX_PERF_PC_TAG_CHECKED_VERTICES"/> - <value value="40" name="A7XX_PERF_PC_MESH_VS_WAVES"/> - <value value="41" name="A7XX_PERF_PC_MESH_DRAWS"/> - <value value="42" name="A7XX_PERF_PC_MESH_DEAD_DRAWS"/> - <value value="43" name="A7XX_PERF_PC_MESH_MVIS_EN_DRAWS"/> - <value value="44" name="A7XX_PERF_PC_MESH_DEAD_PRIM"/> - <value value="45" name="A7XX_PERF_PC_MESH_LIVE_PRIM"/> - <value value="46" name="A7XX_PERF_PC_MESH_PA_EN_PRIM"/> - <value value="47" name="A7XX_PERF_PC_STARVE_CYCLES_FOR_MVIS_STREAM"/> - <value value="48" name="A7XX_PERF_PC_STARVE_CYCLES_PREDRAW"/> - <value value="49" name="A7XX_PERF_PC_STALL_CYCLES_COMPUTE_GFX"/> - <value value="50" name="A7XX_PERF_PC_STALL_CYCLES_GFX_COMPUTE"/> - <value value="51" name="A7XX_PERF_PC_TESS_PC_MULTI_PATCH_TRANS"/> -</enum> - -<enum name="a7xx_vfd_perfcounter_select"> - <value value="0" name="A7XX_PERF_VFD_BUSY_CYCLES"/> - <value value="1" name="A7XX_PERF_VFD_STALL_CYCLES_UCHE"/> - <value value="2" name="A7XX_PERF_VFD_STALL_CYCLES_VPC_ALLOC"/> - <value value="3" name="A7XX_PERF_VFD_STALL_CYCLES_SP_INFO"/> - <value value="4" name="A7XX_PERF_VFD_STALL_CYCLES_SP_ATTR"/> - <value value="5" name="A7XX_PERF_VFD_STARVE_CYCLES_UCHE"/> - <value value="6" name="A7XX_PERF_VFD_RBUFFER_FULL"/> - <value value="7" name="A7XX_PERF_VFD_ATTR_INFO_FIFO_FULL"/> - <value value="8" name="A7XX_PERF_VFD_DECODED_ATTRIBUTE_BYTES"/> - <value value="9" name="A7XX_PERF_VFD_NUM_ATTRIBUTES"/> - <value value="10" name="A7XX_PERF_VFD_UPPER_SHADER_FIBERS"/> - <value value="11" name="A7XX_PERF_VFD_LOWER_SHADER_FIBERS"/> - <value value="12" name="A7XX_PERF_VFD_MODE_0_FIBERS"/> - <value value="13" name="A7XX_PERF_VFD_MODE_1_FIBERS"/> - <value value="14" name="A7XX_PERF_VFD_MODE_2_FIBERS"/> - <value value="15" name="A7XX_PERF_VFD_MODE_3_FIBERS"/> - <value value="16" name="A7XX_PERF_VFD_MODE_4_FIBERS"/> - <value value="17" name="A7XX_PERF_VFD_TOTAL_VERTICES"/> - <value value="18" name="A7XX_PERF_VFDP_STALL_CYCLES_VFD"/> - <value value="19" name="A7XX_PERF_VFDP_STALL_CYCLES_VFD_INDEX"/> - <value value="20" name="A7XX_PERF_VFDP_STALL_CYCLES_VFD_PROG"/> - <value value="21" name="A7XX_PERF_VFDP_STARVE_CYCLES_PC"/> - <value value="22" name="A7XX_PERF_VFDP_VS_STAGE_WAVES"/> - <value value="23" name="A7XX_PERF_VFD_STALL_CYCLES_PRG_END_FE"/> - <value value="24" name="A7XX_PERF_VFD_STALL_CYCLES_CBSYNC"/> -</enum> - -<enum name="a7xx_hlsq_perfcounter_select"> - <value value="0" name="A7XX_PERF_HLSQ_BUSY_CYCLES"/> - <value value="1" name="A7XX_PERF_HLSQ_STALL_CYCLES_UCHE"/> - <value value="2" name="A7XX_PERF_HLSQ_STALL_CYCLES_SP_STATE"/> - <value value="3" name="A7XX_PERF_HLSQ_STALL_CYCLES_SP_FS_STAGE"/> - <value value="4" name="A7XX_PERF_HLSQ_UCHE_LATENCY_CYCLES"/> - <value value="5" name="A7XX_PERF_HLSQ_UCHE_LATENCY_COUNT"/> - <value value="6" name="A7XX_PERF_HLSQ_RESERVED_6"/> - <value value="7" name="A7XX_PERF_HLSQ_RESERVED_7"/> - <value value="8" name="A7XX_PERF_HLSQ_RESERVED_8"/> - <value value="9" name="A7XX_PERF_HLSQ_RESERVED_9"/> - <value value="10" name="A7XX_PERF_HLSQ_COMPUTE_DRAWCALLS"/> - <value value="11" name="A7XX_PERF_HLSQ_FS_DATA_WAIT_PROGRAMMING"/> - <value value="12" name="A7XX_PERF_HLSQ_DUAL_FS_PROG_ACTIVE"/> - <value value="13" name="A7XX_PERF_HLSQ_DUAL_VS_PROG_ACTIVE"/> - <value value="14" name="A7XX_PERF_HLSQ_FS_BATCH_COUNT_ZERO"/> - <value value="15" name="A7XX_PERF_HLSQ_VS_BATCH_COUNT_ZERO"/> - <value value="16" name="A7XX_PERF_HLSQ_WAVE_PENDING_NO_QUAD"/> - <value value="17" name="A7XX_PERF_HLSQ_WAVE_PENDING_NO_PRIM_BASE"/> - <value value="18" name="A7XX_PERF_HLSQ_STALL_CYCLES_VPC"/> - <value value="19" name="A7XX_PERF_HLSQ_RESERVED_19"/> - <value value="20" name="A7XX_PERF_HLSQ_DRAW_MODE_SWITCH_VSFS_SYNC"/> - <value value="21" name="A7XX_PERF_HLSQ_VSBR_STALL_CYCLES"/> - <value value="22" name="A7XX_PERF_HLSQ_FS_STALL_CYCLES"/> - <value value="23" name="A7XX_PERF_HLSQ_LPAC_STALL_CYCLES"/> - <value value="24" name="A7XX_PERF_HLSQ_BV_STALL_CYCLES"/> - <value value="25" name="A7XX_PERF_HLSQ_VSBR_DEREF_CYCLES"/> - <value value="26" name="A7XX_PERF_HLSQ_FS_DEREF_CYCLES"/> - <value value="27" name="A7XX_PERF_HLSQ_LPAC_DEREF_CYCLES"/> - <value value="28" name="A7XX_PERF_HLSQ_BV_DEREF_CYCLES"/> - <value value="29" name="A7XX_PERF_HLSQ_VSBR_S2W_CYCLES"/> - <value value="30" name="A7XX_PERF_HLSQ_FS_S2W_CYCLES"/> - <value value="31" name="A7XX_PERF_HLSQ_LPAC_S2W_CYCLES"/> - <value value="32" name="A7XX_PERF_HLSQ_BV_S2W_CYCLES"/> - <value value="33" name="A7XX_PERF_HLSQ_VSBR_WAIT_FS_S2W"/> - <value value="34" name="A7XX_PERF_HLSQ_FS_WAIT_VS_S2W"/> - <value value="35" name="A7XX_PERF_HLSQ_LPAC_WAIT_VS_S2W"/> - <value value="36" name="A7XX_PERF_HLSQ_BV_WAIT_FS_S2W"/> - <value value="37" name="A7XX_PERF_HLSQ_VS_WAIT_CONST_RESOURCE"/> - <value value="38" name="A7XX_PERF_HLSQ_FS_WAIT_SAME_VS_S2W"/> - <value value="39" name="A7XX_PERF_HLSQ_FS_STARVING_SP"/> - <value value="40" name="A7XX_PERF_HLSQ_VS_DATA_WAIT_PROGRAMMING"/> - <value value="41" name="A7XX_PERF_HLSQ_BV_DATA_WAIT_PROGRAMMING"/> - <value value="42" name="A7XX_PERF_HLSQ_STPROC_WAVE_CONTEXTS_VS"/> - <value value="43" name="A7XX_PERF_HLSQ_STPROC_WAVE_CONTEXT_CYCLES_VS"/> - <value value="44" name="A7XX_PERF_HLSQ_STPROC_WAVE_CONTEXTS_FS"/> - <value value="45" name="A7XX_PERF_HLSQ_STPROC_WAVE_CONTEXT_CYCLES_FS"/> - <value value="46" name="A7XX_PERF_HLSQ_STPROC_WAVE_CONTEXTS_BV"/> - <value value="47" name="A7XX_PERF_HLSQ_STPROC_WAVE_CONTEXT_CYCLES_BV"/> - <value value="48" name="A7XX_PERF_HLSQ_STPROC_WAVE_CONTEXTS_LPAC"/> - <value value="49" name="A7XX_PERF_HLSQ_STPROC_WAVE_CONTEXT_CYCLES_LPAC"/> - <value value="50" name="A7XX_PERF_HLSQ_SPTROC_STCHE_WARMUP_INC_VS"/> - <value value="51" name="A7XX_PERF_HLSQ_SPTROC_STCHE_WARMUP_INC_FS"/> - <value value="52" name="A7XX_PERF_HLSQ_SPTROC_STCHE_WARMUP_INC_BV"/> - <value value="53" name="A7XX_PERF_HLSQ_SPTROC_STCHE_WARMUP_INC_LPAC"/> - <value value="54" name="A7XX_PERF_HLSQ_SPTROC_STCHE_MISS_INC_VS"/> - <value value="55" name="A7XX_PERF_HLSQ_SPTROC_STCHE_MISS_INC_FS"/> - <value value="56" name="A7XX_PERF_HLSQ_SPTROC_STCHE_MISS_INC_BV"/> - <value value="57" name="A7XX_PERF_HLSQ_SPTROC_STCHE_MISS_INC_LPAC"/> -</enum> - -<enum name="a7xx_vpc_perfcounter_select"> - <value value="0" name="A7XX_PERF_VPC_BUSY_CYCLES"/> - <value value="1" name="A7XX_PERF_VPC_WORKING_CYCLES"/> - <value value="2" name="A7XX_PERF_VPC_STALL_CYCLES_UCHE"/> - <value value="3" name="A7XX_PERF_VPC_STALL_CYCLES_VFD_WACK"/> - <value value="4" name="A7XX_PERF_VPC_STALL_CYCLES_HLSQ_PRIM_ALLOC"/> - <value value="5" name="A7XX_PERF_VPC_RESERVED_5"/> - <value value="6" name="A7XX_PERF_VPC_STALL_CYCLES_SP_LM"/> - <value value="7" name="A7XX_PERF_VPC_STARVE_CYCLES_SP"/> - <value value="8" name="A7XX_PERF_VPC_STARVE_CYCLES_LRZ"/> - <value value="9" name="A7XX_PERF_VPC_PC_PRIMITIVES"/> - <value value="10" name="A7XX_PERF_VPC_SP_COMPONENTS"/> - <value value="11" name="A7XX_PERF_VPC_STALL_CYCLES_VPCRAM_POS"/> - <value value="12" name="A7XX_PERF_VPC_LRZ_ASSIGN_PRIMITIVES"/> - <value value="13" name="A7XX_PERF_VPC_RB_VISIBLE_PRIMITIVES"/> - <value value="14" name="A7XX_PERF_VPC_LM_TRANSACTION"/> - <value value="15" name="A7XX_PERF_VPC_STREAMOUT_TRANSACTION"/> - <value value="16" name="A7XX_PERF_VPC_VS_BUSY_CYCLES"/> - <value value="17" name="A7XX_PERF_VPC_PS_BUSY_CYCLES"/> - <value value="18" name="A7XX_PERF_VPC_VS_WORKING_CYCLES"/> - <value value="19" name="A7XX_PERF_VPC_PS_WORKING_CYCLES"/> - <value value="20" name="A7XX_PERF_VPC_STARVE_CYCLES_RB"/> - <value value="21" name="A7XX_PERF_VPC_NUM_VPCRAM_READ_POS"/> - <value value="22" name="A7XX_PERF_VPC_WIT_FULL_CYCLES"/> - <value value="23" name="A7XX_PERF_VPC_VPCRAM_FULL_CYCLES"/> - <value value="24" name="A7XX_PERF_VPC_LM_FULL_WAIT_FOR_INTP_END"/> - <value value="25" name="A7XX_PERF_VPC_NUM_VPCRAM_WRITE"/> - <value value="26" name="A7XX_PERF_VPC_NUM_VPCRAM_READ_SO"/> - <value value="27" name="A7XX_PERF_VPC_NUM_ATTR_REQ_LM"/> - <value value="28" name="A7XX_PERF_VPC_STALL_CYCLE_TSE"/> - <value value="29" name="A7XX_PERF_VPC_TSE_PRIMITIVES"/> - <value value="30" name="A7XX_PERF_VPC_GS_PRIMITIVES"/> - <value value="31" name="A7XX_PERF_VPC_TSE_TRANSACTIONS"/> - <value value="32" name="A7XX_PERF_VPC_STALL_CYCLES_CCU"/> - <value value="33" name="A7XX_PERF_VPC_NUM_WM_HIT"/> - <value value="34" name="A7XX_PERF_VPC_STALL_DQ_WACK"/> - <value value="35" name="A7XX_PERF_VPC_STALL_CYCLES_CCHE"/> - <value value="36" name="A7XX_PERF_VPC_STARVE_CYCLES_CCHE"/> - <value value="37" name="A7XX_PERF_VPC_NUM_PA_REQ"/> - <value value="38" name="A7XX_PERF_VPC_NUM_LM_REQ_HIT"/> - <value value="39" name="A7XX_PERF_VPC_CCHE_REQBUF_FULL"/> - <value value="40" name="A7XX_PERF_VPC_STALL_CYCLES_LM_ACK"/> - <value value="41" name="A7XX_PERF_VPC_STALL_CYCLES_PRG_END_FE"/> - <value value="42" name="A7XX_PERF_VPC_STALL_CYCLES_PRG_END_PCVS"/> - <value value="43" name="A7XX_PERF_VPC_STALL_CYCLES_PRG_END_VPCPS"/> -</enum> - -<enum name="a7xx_tse_perfcounter_select"> - <value value="0" name="A7XX_PERF_TSE_BUSY_CYCLES"/> - <value value="1" name="A7XX_PERF_TSE_CLIPPING_CYCLES"/> - <value value="2" name="A7XX_PERF_TSE_STALL_CYCLES_RAS"/> - <value value="3" name="A7XX_PERF_TSE_STALL_CYCLES_LRZ_BARYPLANE"/> - <value value="4" name="A7XX_PERF_TSE_STALL_CYCLES_LRZ_ZPLANE"/> - <value value="5" name="A7XX_PERF_TSE_STARVE_CYCLES_PC"/> - <value value="6" name="A7XX_PERF_TSE_INPUT_PRIM"/> - <value value="7" name="A7XX_PERF_TSE_INPUT_NULL_PRIM"/> - <value value="8" name="A7XX_PERF_TSE_TRIVAL_REJ_PRIM"/> - <value value="9" name="A7XX_PERF_TSE_CLIPPED_PRIM"/> - <value value="10" name="A7XX_PERF_TSE_ZERO_AREA_PRIM"/> - <value value="11" name="A7XX_PERF_TSE_FACENESS_CULLED_PRIM"/> - <value value="12" name="A7XX_PERF_TSE_ZERO_PIXEL_PRIM"/> - <value value="13" name="A7XX_PERF_TSE_OUTPUT_NULL_PRIM"/> - <value value="14" name="A7XX_PERF_TSE_OUTPUT_VISIBLE_PRIM"/> - <value value="15" name="A7XX_PERF_TSE_CINVOCATION"/> - <value value="16" name="A7XX_PERF_TSE_CPRIMITIVES"/> - <value value="17" name="A7XX_PERF_TSE_2D_INPUT_PRIM"/> - <value value="18" name="A7XX_PERF_TSE_2D_ALIVE_CYCLES"/> - <value value="19" name="A7XX_PERF_TSE_CLIP_PLANES"/> -</enum> - -<enum name="a7xx_ras_perfcounter_select"> - <value value="0" name="A7XX_PERF_RAS_BUSY_CYCLES"/> - <value value="1" name="A7XX_PERF_RAS_SUPERTILE_ACTIVE_CYCLES"/> - <value value="2" name="A7XX_PERF_RAS_STALL_CYCLES_LRZ"/> - <value value="3" name="A7XX_PERF_RAS_STARVE_CYCLES_TSE"/> - <value value="4" name="A7XX_PERF_RAS_SUPER_TILES"/> - <value value="5" name="A7XX_PERF_RAS_8X4_TILES"/> - <value value="6" name="A7XX_PERF_RAS_MASKGEN_ACTIVE"/> - <value value="7" name="A7XX_PERF_RAS_FULLY_COVERED_SUPER_TILES"/> - <value value="8" name="A7XX_PERF_RAS_FULLY_COVERED_8X4_TILES"/> - <value value="9" name="A7XX_PERF_RAS_PRIM_KILLED_INVISILBE"/> - <value value="10" name="A7XX_PERF_RAS_SUPERTILE_GEN_ACTIVE_CYCLES"/> - <value value="11" name="A7XX_PERF_RAS_LRZ_INTF_WORKING_CYCLES"/> - <value value="12" name="A7XX_PERF_RAS_BLOCKS"/> - <value value="13" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_0_WORKING_CC_l2"/> - <value value="14" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_1_WORKING_CC_l2"/> - <value value="15" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_2_WORKING_CC_l2"/> - <value value="16" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_3_WORKING_CC_l2"/> - <value value="17" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_4_WORKING_CC_l2"/> - <value value="18" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_5_WORKING_CC_l2"/> - <value value="19" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_6_WORKING_CC_l2"/> - <value value="20" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_7_WORKING_CC_l2"/> - <value value="21" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_8_WORKING_CC_l2"/> - <value value="22" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_9_WORKING_CC_l2"/> - <value value="23" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_10_WORKING_CC_l2"/> - <value value="24" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_11_WORKING_CC_l2"/> - <value value="25" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_12_WORKING_CC_l2"/> - <value value="26" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_13_WORKING_CC_l2"/> - <value value="27" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_14_WORKING_CC_l2"/> - <value value="28" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_15_WORKING_CC_l2"/> - <value value="29" name="A7XX_PERF_RAS_FALSE_PARTIAL_STILE"/> - -</enum> - -<enum name="a7xx_uche_perfcounter_select"> - <value value="0" name="A7XX_PERF_UCHE_BUSY_CYCLES"/> - <value value="1" name="A7XX_PERF_UCHE_STALL_CYCLES_ARBITER"/> - <value value="2" name="A7XX_PERF_UCHE_VBIF_LATENCY_CYCLES"/> - <value value="3" name="A7XX_PERF_UCHE_VBIF_LATENCY_SAMPLES"/> - <value value="4" name="A7XX_PERF_UCHE_VBIF_READ_BEATS_TP"/> - <value value="5" name="A7XX_PERF_UCHE_VBIF_READ_BEATS_VFD"/> - <value value="6" name="A7XX_PERF_UCHE_VBIF_READ_BEATS_HLSQ"/> - <value value="7" name="A7XX_PERF_UCHE_VBIF_READ_BEATS_LRZ"/> - <value value="8" name="A7XX_PERF_UCHE_VBIF_READ_BEATS_SP"/> - <value value="9" name="A7XX_PERF_UCHE_READ_REQUESTS_TP"/> - <value value="10" name="A7XX_PERF_UCHE_READ_REQUESTS_VFD"/> - <value value="11" name="A7XX_PERF_UCHE_READ_REQUESTS_HLSQ"/> - <value value="12" name="A7XX_PERF_UCHE_READ_REQUESTS_LRZ"/> - <value value="13" name="A7XX_PERF_UCHE_READ_REQUESTS_SP"/> - <value value="14" name="A7XX_PERF_UCHE_WRITE_REQUESTS_LRZ"/> - <value value="15" name="A7XX_PERF_UCHE_WRITE_REQUESTS_SP"/> - <value value="16" name="A7XX_PERF_UCHE_WRITE_REQUESTS_VPC"/> - <value value="17" name="A7XX_PERF_UCHE_WRITE_REQUESTS_VSC"/> - <value value="18" name="A7XX_PERF_UCHE_EVICTS"/> - <value value="19" name="A7XX_PERF_UCHE_BANK_REQ0"/> - <value value="20" name="A7XX_PERF_UCHE_BANK_REQ1"/> - <value value="21" name="A7XX_PERF_UCHE_BANK_REQ2"/> - <value value="22" name="A7XX_PERF_UCHE_BANK_REQ3"/> - <value value="23" name="A7XX_PERF_UCHE_BANK_REQ4"/> - <value value="24" name="A7XX_PERF_UCHE_BANK_REQ5"/> - <value value="25" name="A7XX_PERF_UCHE_BANK_REQ6"/> - <value value="26" name="A7XX_PERF_UCHE_BANK_REQ7"/> - <value value="27" name="A7XX_PERF_UCHE_VBIF_READ_BEATS_CH0"/> - <value value="28" name="A7XX_PERF_UCHE_VBIF_READ_BEATS_CH1"/> - <value value="29" name="A7XX_PERF_UCHE_GMEM_READ_BEATS"/> - <value value="30" name="A7XX_PERF_UCHE_TPH_REF_FULL"/> - <value value="31" name="A7XX_PERF_UCHE_TPH_VICTIM_FULL"/> - <value value="32" name="A7XX_PERF_UCHE_TPH_EXT_FULL"/> - <value value="33" name="A7XX_PERF_UCHE_VBIF_STALL_WRITE_DATA"/> - <value value="34" name="A7XX_PERF_UCHE_DCMP_LATENCY_SAMPLES"/> - <value value="35" name="A7XX_PERF_UCHE_DCMP_LATENCY_CYCLES"/> - <value value="36" name="A7XX_PERF_UCHE_VBIF_READ_BEATS_PC"/> - <value value="37" name="A7XX_PERF_UCHE_READ_REQUESTS_PC"/> - <value value="38" name="A7XX_PERF_UCHE_RAM_READ_REQ"/> - <value value="39" name="A7XX_PERF_UCHE_RAM_WRITE_REQ"/> - <value value="40" name="A7XX_PERF_UCHE_STARVED_CYCLES_VBIF_DECMP"/> - <value value="41" name="A7XX_PERF_UCHE_STALL_CYCLES_DECMP"/> - <value value="42" name="A7XX_PERF_UCHE_ARBITER_STALL_CYCLES_VBIF"/> - <value value="43" name="A7XX_PERF_UCHE_READ_REQUESTS_TP_UBWC"/> - <value value="44" name="A7XX_PERF_UCHE_READ_REQUESTS_TP_NONUBWC"/> - <value value="45" name="A7XX_PERF_UCHE_READ_REQUESTS_TP_GMEM"/> - <value value="46" name="A7XX_PERF_UCHE_LONG_LINE_ALL_EVICTS_KAILUA"/> - <value value="47" name="A7XX_PERF_UCHE_LONG_LINE_PARTIAL_EVICTS_KAILUA"/> - <value value="48" name="A7XX_PERF_UCHE_TPH_CONFLICT_CL_CCHE"/> - <value value="49" name="A7XX_PERF_UCHE_TPH_CONFLICT_CL_OTHER_KAILUA"/> - <value value="50" name="A7XX_PERF_UCHE_DBANK_CONFLICT_CL_CCHE"/> - <value value="51" name="A7XX_PERF_UCHE_DBANK_CONFLICT_CL_OTHER_CLIENTS"/> - <value value="52" name="A7XX_PERF_UCHE_VBIF_WRITE_BEATS_CH0"/> - <value value="53" name="A7XX_PERF_UCHE_VBIF_WRITE_BEATS_CH1"/> - <value value="54" name="A7XX_PERF_UCHE_CCHE_TPH_QUEUE_FULL"/> - <value value="55" name="A7XX_PERF_UCHE_CCHE_DPH_QUEUE_FULL"/> - <value value="56" name="A7XX_PERF_UCHE_GMEM_WRITE_BEATS"/> - <value value="57" name="A7XX_PERF_UCHE_UBWC_READ_BEATS"/> - <value value="58" name="A7XX_PERF_UCHE_UBWC_WRITE_BEATS"/> -</enum> - -<enum name="a7xx_tp_perfcounter_select"> - <value value="0" name="A7XX_PERF_TP_BUSY_CYCLES"/> - <value value="1" name="A7XX_PERF_TP_STALL_CYCLES_UCHE"/> - <value value="2" name="A7XX_PERF_TP_LATENCY_CYCLES"/> - <value value="3" name="A7XX_PERF_TP_LATENCY_TRANS"/> - <value value="4" name="A7XX_PERF_TP_FLAG_FIFO_DELAY_SAMPLES"/> - <value value="5" name="A7XX_PERF_TP_FLAG_FIFO_DELAY_CYCLES"/> - <value value="6" name="A7XX_PERF_TP_L1_CACHELINE_REQUESTS"/> - <value value="7" name="A7XX_PERF_TP_L1_CACHELINE_MISSES"/> - <value value="8" name="A7XX_PERF_TP_SP_TP_TRANS"/> - <value value="9" name="A7XX_PERF_TP_TP_SP_TRANS"/> - <value value="10" name="A7XX_PERF_TP_OUTPUT_PIXELS"/> - <value value="11" name="A7XX_PERF_TP_FILTER_WORKLOAD_16BIT"/> - <value value="12" name="A7XX_PERF_TP_FILTER_WORKLOAD_32BIT"/> - <value value="13" name="A7XX_PERF_TP_QUADS_RECEIVED"/> - <value value="14" name="A7XX_PERF_TP_QUADS_OFFSET"/> - <value value="15" name="A7XX_PERF_TP_QUADS_SHADOW"/> - <value value="16" name="A7XX_PERF_TP_QUADS_ARRAY"/> - <value value="17" name="A7XX_PERF_TP_QUADS_GRADIENT"/> - <value value="18" name="A7XX_PERF_TP_QUADS_1D"/> - <value value="19" name="A7XX_PERF_TP_QUADS_2D"/> - <value value="20" name="A7XX_PERF_TP_QUADS_BUFFER"/> - <value value="21" name="A7XX_PERF_TP_QUADS_3D"/> - <value value="22" name="A7XX_PERF_TP_QUADS_CUBE"/> - <value value="23" name="A7XX_PERF_TP_DIVERGENT_QUADS_RECEIVED"/> - <value value="24" name="A7XX_PERF_TP_PRT_NON_RESIDENT_EVENTS"/> - <value value="25" name="A7XX_PERF_TP_OUTPUT_PIXELS_POINT"/> - <value value="26" name="A7XX_PERF_TP_OUTPUT_PIXELS_BILINEAR"/> - <value value="27" name="A7XX_PERF_TP_OUTPUT_PIXELS_MIP"/> - <value value="28" name="A7XX_PERF_TP_OUTPUT_PIXELS_ANISO"/> - <value value="29" name="A7XX_PERF_TP_OUTPUT_PIXELS_ZERO_LOD"/> - <value value="30" name="A7XX_PERF_TP_FLAG_CACHE_REQUESTS"/> - <value value="31" name="A7XX_PERF_TP_FLAG_CACHE_MISSES"/> - <value value="32" name="A7XX_PERF_TP_L1_5_L2_REQUESTS"/> - <value value="33" name="A7XX_PERF_TP_2D_OUTPUT_PIXELS"/> - <value value="34" name="A7XX_PERF_TP_2D_OUTPUT_PIXELS_POINT"/> - <value value="35" name="A7XX_PERF_TP_2D_OUTPUT_PIXELS_BILINEAR"/> - <value value="36" name="A7XX_PERF_TP_2D_FILTER_WORKLOAD_16BIT"/> - <value value="37" name="A7XX_PERF_TP_2D_FILTER_WORKLOAD_32BIT"/> - <value value="38" name="A7XX_PERF_TP_TPA2TPC_TRANS"/> - <value value="39" name="A7XX_PERF_TP_L1_MISSES_ASTC_1TILE"/> - <value value="40" name="A7XX_PERF_TP_L1_MISSES_ASTC_2TILE"/> - <value value="41" name="A7XX_PERF_TP_L1_MISSES_ASTC_4TILE"/> - <value value="42" name="A7XX_PERF_TP_L1_5_COMPRESS_REQS"/> - <value value="43" name="A7XX_PERF_TP_L1_5_L2_COMPRESS_MISS"/> - <value value="44" name="A7XX_PERF_TP_L1_BANK_CONFLICT"/> - <value value="45" name="A7XX_PERF_TP_L1_5_MISS_LATENCY_CYCLES"/> - <value value="46" name="A7XX_PERF_TP_L1_5_MISS_LATENCY_TRANS"/> - <value value="47" name="A7XX_PERF_TP_QUADS_CONSTANT_MULTIPLIED"/> - <value value="48" name="A7XX_PERF_TP_FRONTEND_WORKING_CYCLES"/> - <value value="49" name="A7XX_PERF_TP_L1_TAG_WORKING_CYCLES"/> - <value value="50" name="A7XX_PERF_TP_L1_DATA_WRITE_WORKING_CYCLES"/> - <value value="51" name="A7XX_PERF_TP_PRE_L1_DECOM_WORKING_CYCLES"/> - <value value="52" name="A7XX_PERF_TP_BACKEND_WORKING_CYCLES"/> - <value value="53" name="A7XX_PERF_TP_L1_5_CACHE_WORKING_CYCLES"/> - <value value="54" name="A7XX_PERF_TP_STARVE_CYCLES_SP"/> - <value value="55" name="A7XX_PERF_TP_STARVE_CYCLES_UCHE"/> - <value value="56" name="A7XX_PERF_TP_STALL_CYCLES_UFC"/> - <value value="57" name="A7XX_PERF_TP_FORMAT_DECOMP"/> - <value value="58" name="A7XX_PERF_TP_FILTER_POINT_FP16"/> - <value value="59" name="A7XX_PERF_TP_FILTER_POINT_FP32"/> - <value value="60" name="A7XX_PERF_TP_LATENCY_FIFO_FULL"/> - <value value="61" name="A7XX_PERF_TP_RESERVED_61"/> - <value value="62" name="A7XX_PERF_TP_RESERVED_62"/> - <value value="63" name="A7XX_PERF_TP_RESERVED_63"/> - <value value="64" name="A7XX_PERF_TP_RESERVED_64"/> - <value value="65" name="A7XX_PERF_TP_RESERVED_65"/> - <value value="66" name="A7XX_PERF_TP_RESERVED_66"/> - <value value="67" name="A7XX_PERF_TP_RESERVED_67"/> - <value value="68" name="A7XX_PERF_TP_RESERVED_68"/> - <value value="69" name="A7XX_PERF_TP_RESERVED_69"/> - <value value="70" name="A7XX_PERF_TP_RESERVED_70"/> - <value value="71" name="A7XX_PERF_TP_RESERVED_71"/> - <value value="72" name="A7XX_PERF_TP_RESERVED_72"/> - <value value="73" name="A7XX_PERF_TP_RESERVED_73"/> - <value value="74" name="A7XX_PERF_TP_RESERVED_74"/> - <value value="75" name="A7XX_PERF_TP_RESERVED_75"/> - <value value="76" name="A7XX_PERF_TP_RESERVED_76"/> - <value value="77" name="A7XX_PERF_TP_RESERVED_77"/> - <value value="78" name="A7XX_PERF_TP_RESERVED_78"/> - <value value="79" name="A7XX_PERF_TP_RESERVED_79"/> - <value value="80" name="A7XX_PERF_TP_RESERVED_80"/> - <value value="81" name="A7XX_PERF_TP_RESERVED_81"/> - <value value="82" name="A7XX_PERF_TP_RESERVED_82"/> - <value value="83" name="A7XX_PERF_TP_RESERVED_83"/> - <value value="84" name="A7XX_PERF_TP_RESERVED_84"/> - <value value="85" name="A7XX_PERF_TP_RESERVED_85"/> - <value value="86" name="A7XX_PERF_TP_RESERVED_86"/> - <value value="87" name="A7XX_PERF_TP_RESERVED_87"/> - <value value="88" name="A7XX_PERF_TP_RESERVED_88"/> - <value value="89" name="A7XX_PERF_TP_RESERVED_89"/> - <value value="90" name="A7XX_PERF_TP_RESERVED_90"/> - <value value="91" name="A7XX_PERF_TP_RESERVED_91"/> - <value value="92" name="A7XX_PERF_TP_RESERVED_92"/> - <value value="93" name="A7XX_PERF_TP_RESERVED_93"/> - <value value="94" name="A7XX_PERF_TP_RESERVED_94"/> - <value value="95" name="A7XX_PERF_TP_RESERVED_95"/> - <value value="96" name="A7XX_PERF_TP_RESERVED_96"/> - <value value="97" name="A7XX_PERF_TP_RESERVED_97"/> - <value value="98" name="A7XX_PERF_TP_RESERVED_98"/> - <value value="99" name="A7XX_PERF_TP_RESERVED_99"/> - <value value="100" name="A7XX_PERF_TP_RESERVED_100"/> - <value value="101" name="A7XX_PERF_TP_RESERVED_101"/> - <value value="102" name="A7XX_PERF_TP_RESERVED_102"/> - <value value="103" name="A7XX_PERF_TP_RESERVED_103"/> - <value value="104" name="A7XX_PERF_TP_RESERVED_104"/> - <value value="105" name="A7XX_PERF_TP_RESERVED_105"/> - <value value="106" name="A7XX_PERF_TP_RESERVED_106"/> - <value value="107" name="A7XX_PERF_TP_RESERVED_107"/> - <value value="108" name="A7XX_PERF_TP_RESERVED_108"/> - <value value="109" name="A7XX_PERF_TP_RESERVED_109"/> - <value value="110" name="A7XX_PERF_TP_RESERVED_110"/> - <value value="111" name="A7XX_PERF_TP_RESERVED_111"/> - <value value="112" name="A7XX_PERF_TP_RESERVED_112"/> - <value value="113" name="A7XX_PERF_TP_RESERVED_113"/> - <value value="114" name="A7XX_PERF_TP_RESERVED_114"/> - <value value="115" name="A7XX_PERF_TP_RESERVED_115"/> - <value value="116" name="A7XX_PERF_TP_RESERVED_116"/> - <value value="117" name="A7XX_PERF_TP_RESERVED_117"/> - <value value="118" name="A7XX_PERF_TP_RESERVED_118"/> - <value value="119" name="A7XX_PERF_TP_RESERVED_119"/> - <value value="120" name="A7XX_PERF_TP_RESERVED_120"/> - <value value="121" name="A7XX_PERF_TP_RESERVED_121"/> - <value value="122" name="A7XX_PERF_TP_RESERVED_122"/> - <value value="123" name="A7XX_PERF_TP_RESERVED_123"/> - <value value="124" name="A7XX_PERF_TP_RESERVED_124"/> - <value value="125" name="A7XX_PERF_TP_RESERVED_125"/> - <value value="126" name="A7XX_PERF_TP_RESERVED_126"/> - <value value="127" name="A7XX_PERF_TP_RESERVED_127"/> - <value value="128" name="A7XX_PERF_TP_FORMAT_DECOMP_BILINEAR"/> - <value value="129" name="A7XX_PERF_TP_PACKED_POINT_BOTH_VALID_FP16"/> - <value value="130" name="A7XX_PERF_TP_PACKED_POINT_SINGLE_VALID_FP16"/> - <value value="131" name="A7XX_PERF_TP_PACKED_POINT_BOTH_VALID_FP32"/> - <value value="132" name="A7XX_PERF_TP_PACKED_POINT_SINGLE_VALID_FP32"/> -</enum> - -<enum name="a7xx_sp_perfcounter_select"> - <value value="0" name="A7XX_PERF_SP_BUSY_CYCLES"/> - <value value="1" name="A7XX_PERF_SP_ALU_WORKING_CYCLES"/> - <value value="2" name="A7XX_PERF_SP_EFU_WORKING_CYCLES"/> - <value value="3" name="A7XX_PERF_SP_STALL_CYCLES_VPC"/> - <value value="4" name="A7XX_PERF_SP_STALL_CYCLES_TP"/> - <value value="5" name="A7XX_PERF_SP_STALL_CYCLES_UCHE"/> - <value value="6" name="A7XX_PERF_SP_STALL_CYCLES_RB"/> - <value value="7" name="A7XX_PERF_SP_NON_EXECUTION_CYCLES"/> - <value value="8" name="A7XX_PERF_SP_WAVE_CONTEXTS"/> - <value value="9" name="A7XX_PERF_SP_WAVE_CONTEXT_CYCLES"/> - <value value="10" name="A7XX_PERF_SP_STAGE_WAVE_CYCLES"/> - <value value="11" name="A7XX_PERF_SP_STAGE_WAVE_SAMPLES"/> - <value value="12" name="A7XX_PERF_SP_VS_STAGE_WAVE_CYCLES"/> - <value value="13" name="A7XX_PERF_SP_VS_STAGE_WAVE_SAMPLES"/> - <value value="14" name="A7XX_PERF_SP_FS_STAGE_DURATION_CYCLES"/> - <value value="15" name="A7XX_PERF_SP_VS_STAGE_DURATION_CYCLES"/> - <value value="16" name="A7XX_PERF_SP_WAVE_CTRL_CYCLES"/> - <value value="17" name="A7XX_PERF_SP_WAVE_LOAD_CYCLES"/> - <value value="18" name="A7XX_PERF_SP_WAVE_EMIT_CYCLES"/> - <value value="19" name="A7XX_PERF_SP_WAVE_NOP_CYCLES"/> - <value value="20" name="A7XX_PERF_SP_WAVE_WAIT_CYCLES"/> - <value value="21" name="A7XX_PERF_SP_WAVE_FETCH_CYCLES"/> - <value value="22" name="A7XX_PERF_SP_WAVE_IDLE_CYCLES"/> - <value value="23" name="A7XX_PERF_SP_WAVE_END_CYCLES"/> - <value value="24" name="A7XX_PERF_SP_WAVE_LONG_SYNC_CYCLES"/> - <value value="25" name="A7XX_PERF_SP_WAVE_SHORT_SYNC_CYCLES"/> - <value value="26" name="A7XX_PERF_SP_WAVE_JOIN_CYCLES"/> - <value value="27" name="A7XX_PERF_SP_LM_LOAD_INSTRUCTIONS"/> - <value value="28" name="A7XX_PERF_SP_LM_STORE_INSTRUCTIONS"/> - <value value="29" name="A7XX_PERF_SP_LM_ATOMICS"/> - <value value="30" name="A7XX_PERF_SP_GM_LOAD_INSTRUCTIONS"/> - <value value="31" name="A7XX_PERF_SP_GM_STORE_INSTRUCTIONS"/> - <value value="32" name="A7XX_PERF_SP_GM_ATOMICS"/> - <value value="33" name="A7XX_PERF_SP_VS_STAGE_TEX_INSTRUCTIONS"/> - <value value="34" name="A7XX_PERF_SP_VS_STAGE_EFU_INSTRUCTIONS"/> - <value value="35" name="A7XX_PERF_SP_VS_STAGE_FULL_ALU_INSTRUCTIONS"/> - <value value="36" name="A7XX_PERF_SP_VS_STAGE_HALF_ALU_INSTRUCTIONS"/> - <value value="37" name="A7XX_PERF_SP_FS_STAGE_TEX_INSTRUCTIONS"/> - <value value="38" name="A7XX_PERF_SP_FS_STAGE_CFLOW_INSTRUCTIONS"/> - <value value="39" name="A7XX_PERF_SP_FS_STAGE_EFU_INSTRUCTIONS"/> - <value value="40" name="A7XX_PERF_SP_FS_STAGE_FULL_ALU_INSTRUCTIONS"/> - <value value="41" name="A7XX_PERF_SP_FS_STAGE_HALF_ALU_INSTRUCTIONS"/> - <value value="42" name="A7XX_PERF_SP_FS_STAGE_BARY_INSTRUCTIONS"/> - <value value="43" name="A7XX_PERF_SP_VS_INSTRUCTIONS"/> - <value value="44" name="A7XX_PERF_SP_FS_INSTRUCTIONS"/> - <value value="45" name="A7XX_PERF_SP_ADDR_LOCK_COUNT"/> - <value value="46" name="A7XX_PERF_SP_UCHE_READ_TRANS"/> - <value value="47" name="A7XX_PERF_SP_UCHE_WRITE_TRANS"/> - <value value="48" name="A7XX_PERF_SP_EXPORT_VPC_TRANS"/> - <value value="49" name="A7XX_PERF_SP_EXPORT_RB_TRANS"/> - <value value="50" name="A7XX_PERF_SP_PIXELS_KILLED"/> - <value value="51" name="A7XX_PERF_SP_ICL1_REQUESTS"/> - <value value="52" name="A7XX_PERF_SP_ICL1_MISSES"/> - <value value="53" name="A7XX_PERF_SP_HS_INSTRUCTIONS"/> - <value value="54" name="A7XX_PERF_SP_DS_INSTRUCTIONS"/> - <value value="55" name="A7XX_PERF_SP_GS_INSTRUCTIONS"/> - <value value="56" name="A7XX_PERF_SP_CS_INSTRUCTIONS"/> - <value value="57" name="A7XX_PERF_SP_GPR_READ"/> - <value value="58" name="A7XX_PERF_SP_GPR_WRITE"/> - <value value="59" name="A7XX_PERF_SP_FS_STAGE_HALF_EFU_INSTRUCTIONS"/> - <value value="60" name="A7XX_PERF_SP_VS_STAGE_HALF_EFU_INSTRUCTIONS"/> - <value value="61" name="A7XX_PERF_SP_LM_BANK_CONFLICTS"/> - <value value="62" name="A7XX_PERF_SP_TEX_CONTROL_WORKING_CYCLES"/> - <value value="63" name="A7XX_PERF_SP_LOAD_CONTROL_WORKING_CYCLES"/> - <value value="64" name="A7XX_PERF_SP_FLOW_CONTROL_WORKING_CYCLES"/> - <value value="65" name="A7XX_PERF_SP_LM_WORKING_CYCLES"/> - <value value="66" name="A7XX_PERF_SP_DISPATCHER_WORKING_CYCLES"/> - <value value="67" name="A7XX_PERF_SP_SEQUENCER_WORKING_CYCLES"/> - <value value="68" name="A7XX_PERF_SP_LOW_EFFICIENCY_STARVED_BY_TP"/> - <value value="69" name="A7XX_PERF_SP_STARVE_CYCLES_HLSQ"/> - <value value="70" name="A7XX_PERF_SP_NON_EXECUTION_LS_CYCLES"/> - <value value="71" name="A7XX_PERF_SP_WORKING_EU"/> - <value value="72" name="A7XX_PERF_SP_ANY_EU_WORKING"/> - <value value="73" name="A7XX_PERF_SP_WORKING_EU_FS_STAGE"/> - <value value="74" name="A7XX_PERF_SP_ANY_EU_WORKING_FS_STAGE"/> - <value value="75" name="A7XX_PERF_SP_WORKING_EU_VS_STAGE"/> - <value value="76" name="A7XX_PERF_SP_ANY_EU_WORKING_VS_STAGE"/> - <value value="77" name="A7XX_PERF_SP_WORKING_EU_CS_STAGE"/> - <value value="78" name="A7XX_PERF_SP_ANY_EU_WORKING_CS_STAGE"/> - <value value="79" name="A7XX_PERF_SP_GPR_READ_PREFETCH"/> - <value value="80" name="A7XX_PERF_SP_GPR_READ_CONFLICT"/> - <value value="81" name="A7XX_PERF_SP_GPR_WRITE_CONFLICT"/> - <value value="82" name="A7XX_PERF_SP_GM_LOAD_LATENCY_CYCLES"/> - <value value="83" name="A7XX_PERF_SP_GM_LOAD_LATENCY_SAMPLES"/> - <value value="84" name="A7XX_PERF_SP_EXECUTABLE_WAVES"/> - <value value="85" name="A7XX_PERF_SP_ICL1_MISS_FETCH_CYCLES"/> - <value value="86" name="A7XX_PERF_SP_WORKING_EU_LPAC"/> - <value value="87" name="A7XX_PERF_SP_BYPASS_BUSY_CYCLES"/> - <value value="88" name="A7XX_PERF_SP_ANY_EU_WORKING_LPAC"/> - <value value="89" name="A7XX_PERF_SP_WAVE_ALU_CYCLES"/> - <value value="90" name="A7XX_PERF_SP_WAVE_EFU_CYCLES"/> - <value value="91" name="A7XX_PERF_SP_WAVE_INT_CYCLES"/> - <value value="92" name="A7XX_PERF_SP_WAVE_CSP_CYCLES"/> - <value value="93" name="A7XX_PERF_SP_EWAVE_CONTEXTS"/> - <value value="94" name="A7XX_PERF_SP_EWAVE_CONTEXT_CYCLES"/> - <value value="95" name="A7XX_PERF_SP_LPAC_BUSY_CYCLES"/> - <value value="96" name="A7XX_PERF_SP_LPAC_INSTRUCTIONS"/> - <value value="97" name="A7XX_PERF_SP_FS_STAGE_1X_WAVES"/> - <value value="98" name="A7XX_PERF_SP_FS_STAGE_2X_WAVES"/> - <value value="99" name="A7XX_PERF_SP_QUADS"/> - <value value="100" name="A7XX_PERF_SP_CS_INVOCATIONS"/> - <value value="101" name="A7XX_PERF_SP_PIXELS"/> - <value value="102" name="A7XX_PERF_SP_LPAC_DRAWCALLS"/> - <value value="103" name="A7XX_PERF_SP_PI_WORKING_CYCLES"/> - <value value="104" name="A7XX_PERF_SP_WAVE_INPUT_CYCLES"/> - <value value="105" name="A7XX_PERF_SP_WAVE_OUTPUT_CYCLES"/> - <value value="106" name="A7XX_PERF_SP_WAVE_HWAVE_WAIT_CYCLES"/> - <value value="107" name="A7XX_PERF_SP_WAVE_HWAVE_SYNC"/> - <value value="108" name="A7XX_PERF_SP_OUTPUT_3D_PIXELS"/> - <value value="109" name="A7XX_PERF_SP_FULL_ALU_MAD_INSTRUCTIONS"/> - <value value="110" name="A7XX_PERF_SP_HALF_ALU_MAD_INSTRUCTIONS"/> - <value value="111" name="A7XX_PERF_SP_FULL_ALU_MUL_INSTRUCTIONS"/> - <value value="112" name="A7XX_PERF_SP_HALF_ALU_MUL_INSTRUCTIONS"/> - <value value="113" name="A7XX_PERF_SP_FULL_ALU_ADD_INSTRUCTIONS"/> - <value value="114" name="A7XX_PERF_SP_HALF_ALU_ADD_INSTRUCTIONS"/> - <value value="115" name="A7XX_PERF_SP_BARY_FP32_INSTRUCTIONS"/> - <value value="116" name="A7XX_PERF_SP_ALU_GPR_READ_CYCLES"/> - <value value="117" name="A7XX_PERF_SP_ALU_DATA_FORWARDING_CYCLES"/> - <value value="118" name="A7XX_PERF_SP_LM_FULL_CYCLES"/> - <value value="119" name="A7XX_PERF_SP_TEXTURE_FETCH_LATENCY_CYCLES"/> - <value value="120" name="A7XX_PERF_SP_TEXTURE_FETCH_LATENCY_SAMPLES"/> - <value value="121" name="A7XX_PERF_SP_FS_STAGE_PI_TEX_INSTRUCTION"/> - <value value="122" name="A7XX_PERF_SP_RAY_QUERY_INSTRUCTIONS"/> - <value value="123" name="A7XX_PERF_SP_RBRT_KICKOFF_FIBERS"/> - <value value="124" name="A7XX_PERF_SP_RBRT_KICKOFF_DQUADS"/> - <value value="125" name="A7XX_PERF_SP_RTU_BUSY_CYCLES"/> - <value value="126" name="A7XX_PERF_SP_RTU_L0_HITS"/> - <value value="127" name="A7XX_PERF_SP_RTU_L0_MISSES"/> - <value value="128" name="A7XX_PERF_SP_RTU_L0_HIT_ON_MISS"/> - <value value="129" name="A7XX_PERF_SP_RTU_STALL_CYCLES_WAVE_QUEUE"/> - <value value="130" name="A7XX_PERF_SP_RTU_STALL_CYCLES_L0_HIT_QUEUE"/> - <value value="131" name="A7XX_PERF_SP_RTU_STALL_CYCLES_L0_MISS_QUEUE"/> - <value value="132" name="A7XX_PERF_SP_RTU_STALL_CYCLES_L0D_IDX_QUEUE"/> - <value value="133" name="A7XX_PERF_SP_RTU_STALL_CYCLES_L0DATA"/> - <value value="134" name="A7XX_PERF_SP_RTU_STALL_CYCLES_REPLACE_CNT"/> - <value value="135" name="A7XX_PERF_SP_RTU_STALL_CYCLES_MRG_CNT"/> - <value value="136" name="A7XX_PERF_SP_RTU_STALL_CYCLES_UCHE"/> - <value value="137" name="A7XX_PERF_SP_RTU_OPERAND_FETCH_STALL_CYCLES_L0"/> - <value value="138" name="A7XX_PERF_SP_RTU_OPERAND_FETCH_STALL_CYCLES_INS_FIFO"/> - <value value="139" name="A7XX_PERF_SP_RTU_BVH_FETCH_LATENCY_CYCLES"/> - <value value="140" name="A7XX_PERF_SP_RTU_BVH_FETCH_LATENCY_SAMPLES"/> - <value value="141" name="A7XX_PERF_SP_STCHE_MISS_INC_VS"/> - <value value="142" name="A7XX_PERF_SP_STCHE_MISS_INC_FS"/> - <value value="143" name="A7XX_PERF_SP_STCHE_MISS_INC_BV"/> - <value value="144" name="A7XX_PERF_SP_STCHE_MISS_INC_LPAC"/> - <value value="145" name="A7XX_PERF_SP_VGPR_ACTIVE_CONTEXTS"/> - <value value="146" name="A7XX_PERF_SP_PGPR_ALLOC_CONTEXTS"/> - <value value="147" name="A7XX_PERF_SP_VGPR_ALLOC_CONTEXTS"/> - <value value="148" name="A7XX_PERF_SP_RTU_RAY_BOX_INTERSECTIONS"/> - <value value="149" name="A7XX_PERF_SP_RTU_RAY_TRIANGLE_INTERSECTIONS"/> - <value value="150" name="A7XX_PERF_SP_SCH_STALL_CYCLES_RTU"/> -</enum> - -<enum name="a7xx_rb_perfcounter_select"> - <value value="0" name="A7XX_PERF_RB_BUSY_CYCLES"/> - <value value="1" name="A7XX_PERF_RB_STALL_CYCLES_HLSQ"/> - <value value="2" name="A7XX_PERF_RB_STALL_CYCLES_FIFO0_FULL"/> - <value value="3" name="A7XX_PERF_RB_STALL_CYCLES_FIFO1_FULL"/> - <value value="4" name="A7XX_PERF_RB_STALL_CYCLES_FIFO2_FULL"/> - <value value="5" name="A7XX_PERF_RB_STARVE_CYCLES_SP"/> - <value value="6" name="A7XX_PERF_RB_STARVE_CYCLES_LRZ_TILE"/> - <value value="7" name="A7XX_PERF_RB_STARVE_CYCLES_CCU"/> - <value value="8" name="A7XX_PERF_RB_STARVE_CYCLES_Z_PLANE"/> - <value value="9" name="A7XX_PERF_RB_STARVE_CYCLES_BARY_PLANE"/> - <value value="10" name="A7XX_PERF_RB_Z_WORKLOAD"/> - <value value="11" name="A7XX_PERF_RB_HLSQ_ACTIVE"/> - <value value="12" name="A7XX_PERF_RB_Z_READ"/> - <value value="13" name="A7XX_PERF_RB_Z_WRITE"/> - <value value="14" name="A7XX_PERF_RB_C_READ"/> - <value value="15" name="A7XX_PERF_RB_C_WRITE"/> - <value value="16" name="A7XX_PERF_RB_TOTAL_PASS"/> - <value value="17" name="A7XX_PERF_RB_Z_PASS"/> - <value value="18" name="A7XX_PERF_RB_Z_FAIL"/> - <value value="19" name="A7XX_PERF_RB_S_FAIL"/> - <value value="20" name="A7XX_PERF_RB_BLENDED_FXP_COMPONENTS"/> - <value value="21" name="A7XX_PERF_RB_BLENDED_FP16_COMPONENTS"/> - <value value="22" name="A7XX_PERF_RB_PS_INVOCATIONS"/> - <value value="23" name="A7XX_PERF_RB_2D_ALIVE_CYCLES"/> - <value value="24" name="A7XX_PERF_RB_2D_STALL_CYCLES_A2D"/> - <value value="25" name="A7XX_PERF_RB_2D_STARVE_CYCLES_SRC"/> - <value value="26" name="A7XX_PERF_RB_2D_STARVE_CYCLES_SP"/> - <value value="27" name="A7XX_PERF_RB_2D_STARVE_CYCLES_DST"/> - <value value="28" name="A7XX_PERF_RB_2D_VALID_PIXELS"/> - <value value="29" name="A7XX_PERF_RB_3D_PIXELS"/> - <value value="30" name="A7XX_PERF_RB_BLENDER_WORKING_CYCLES"/> - <value value="31" name="A7XX_PERF_RB_ZPROC_WORKING_CYCLES"/> - <value value="32" name="A7XX_PERF_RB_CPROC_WORKING_CYCLES"/> - <value value="33" name="A7XX_PERF_RB_SAMPLER_WORKING_CYCLES"/> - <value value="34" name="A7XX_PERF_RB_STALL_CYCLES_CCU_COLOR_READ"/> - <value value="35" name="A7XX_PERF_RB_STALL_CYCLES_CCU_COLOR_WRITE"/> - <value value="36" name="A7XX_PERF_RB_STALL_CYCLES_CCU_DEPTH_READ"/> - <value value="37" name="A7XX_PERF_RB_STALL_CYCLES_CCU_DEPTH_WRITE"/> - <value value="38" name="A7XX_PERF_RB_STALL_CYCLES_VPC"/> - <value value="39" name="A7XX_PERF_RB_2D_INPUT_TRANS"/> - <value value="40" name="A7XX_PERF_RB_2D_OUTPUT_RB_DST_TRANS"/> - <value value="41" name="A7XX_PERF_RB_2D_OUTPUT_RB_SRC_TRANS"/> - <value value="42" name="A7XX_PERF_RB_BLENDED_FP32_COMPONENTS"/> - <value value="43" name="A7XX_PERF_RB_COLOR_PIX_TILES"/> - <value value="44" name="A7XX_PERF_RB_STALL_CYCLES_CCU"/> - <value value="45" name="A7XX_PERF_RB_EARLY_Z_ARB3_GRANT"/> - <value value="46" name="A7XX_PERF_RB_LATE_Z_ARB3_GRANT"/> - <value value="47" name="A7XX_PERF_RB_EARLY_Z_SKIP_GRANT"/> - <value value="48" name="A7XX_PERF_RB_VRS_1x1_QUADS"/> - <value value="49" name="A7XX_PERF_RB_VRS_2x1_QUADS"/> - <value value="50" name="A7XX_PERF_RB_VRS_1x2_QUADS"/> - <value value="51" name="A7XX_PERF_RB_VRS_2x2_QUADS"/> - <value value="52" name="A7XX_PERF_RB_VRS_4x2_QUADS"/> - <value value="53" name="A7XX_PERF_RB_VRS_4x4_QUADS"/> -</enum> - -<enum name="a7xx_vsc_perfcounter_select"> - <value value="0" name="A7XX_PERF_VSC_BUSY_CYCLES"/> - <value value="1" name="A7XX_PERF_VSC_WORKING_CYCLES"/> - <value value="2" name="A7XX_PERF_VSC_STALL_CYCLES_UCHE"/> - <value value="3" name="A7XX_PERF_VSC_EOT_NUM"/> - <value value="4" name="A7XX_PERF_VSC_INPUT_TILES"/> -</enum> - -<enum name="a7xx_ccu_perfcounter_select"> - <value value="0" name="A7XX_PERF_CCU_BUSY_CYCLES"/> - <value value="1" name="A7XX_PERF_CCU_STALL_CYCLES_RB_DEPTH_RETURN"/> - <value value="2" name="A7XX_PERF_CCU_STALL_CYCLES_RB_COLOR_RETURN"/> - <value value="3" name="A7XX_PERF_CCU_DEPTH_BLOCKS"/> - <value value="4" name="A7XX_PERF_CCU_COLOR_BLOCKS"/> - <value value="5" name="A7XX_PERF_CCU_DEPTH_BLOCK_HIT"/> - <value value="6" name="A7XX_PERF_CCU_COLOR_BLOCK_HIT"/> - <value value="7" name="A7XX_PERF_CCU_PARTIAL_BLOCK_READ"/> - <value value="8" name="A7XX_PERF_CCU_GMEM_READ"/> - <value value="9" name="A7XX_PERF_CCU_GMEM_WRITE"/> - <value value="10" name="A7XX_PERF_CCU_2D_RD_REQ"/> - <value value="11" name="A7XX_PERF_CCU_2D_WR_REQ"/> - <value value="12" name="A7XX_PERF_CCU_UBWC_COLOR_BLOCKS_CONCURRENT"/> - <value value="13" name="A7XX_PERF_CCU_UBWC_DEPTH_BLOCKS_CONCURRENT"/> - <value value="14" name="A7XX_PERF_CCU_COLOR_RESOLVE_DROPPED"/> - <value value="15" name="A7XX_PERF_CCU_DEPTH_RESOLVE_DROPPED"/> - <value value="16" name="A7XX_PERF_CCU_COLOR_RENDER_CONCURRENT"/> - <value value="17" name="A7XX_PERF_CCU_DEPTH_RENDER_CONCURRENT"/> - <value value="18" name="A7XX_PERF_CCU_COLOR_RESOLVE_AFTER_RENDER"/> - <value value="19" name="A7XX_PERF_CCU_DEPTH_RESOLVE_AFTER_RENDER"/> - <value value="20" name="A7XX_PERF_CCU_GMEM_EXTRA_DEPTH_READ"/> - <value value="21" name="A7XX_PERF_CCU_GMEM_COLOR_READ_4AA"/> - <value value="22" name="A7XX_PERF_CCU_GMEM_COLOR_READ_4AA_FULL"/> -</enum> - -<enum name="a7xx_lrz_perfcounter_select"> - <value value="0" name="A7XX_PERF_LRZ_BUSY_CYCLES"/> - <value value="1" name="A7XX_PERF_LRZ_STARVE_CYCLES_RAS"/> - <value value="2" name="A7XX_PERF_LRZ_STALL_CYCLES_RB"/> - <value value="3" name="A7XX_PERF_LRZ_STALL_CYCLES_VSC"/> - <value value="4" name="A7XX_PERF_LRZ_STALL_CYCLES_VPC"/> - <value value="5" name="A7XX_PERF_LRZ_STALL_CYCLES_FLAG_PREFETCH"/> - <value value="6" name="A7XX_PERF_LRZ_STALL_CYCLES_UCHE"/> - <value value="7" name="A7XX_PERF_LRZ_LRZ_READ"/> - <value value="8" name="A7XX_PERF_LRZ_LRZ_WRITE"/> - <value value="9" name="A7XX_PERF_LRZ_READ_LATENCY"/> - <value value="10" name="A7XX_PERF_LRZ_MERGE_CACHE_UPDATING"/> - <value value="11" name="A7XX_PERF_LRZ_PRIM_KILLED_BY_MASKGEN"/> - <value value="12" name="A7XX_PERF_LRZ_PRIM_KILLED_BY_LRZ"/> - <value value="13" name="A7XX_PERF_LRZ_VISIBLE_PRIM_AFTER_LRZ"/> - <value value="14" name="A7XX_PERF_LRZ_FULL_8X8_TILES"/> - <value value="15" name="A7XX_PERF_LRZ_PARTIAL_8X8_TILES"/> - <value value="16" name="A7XX_PERF_LRZ_TILE_KILLED"/> - <value value="17" name="A7XX_PERF_LRZ_TOTAL_PIXEL"/> - <value value="18" name="A7XX_PERF_LRZ_VISIBLE_PIXEL_AFTER_LRZ"/> - <value value="19" name="A7XX_PERF_LRZ_FEEDBACK_ACCEPT"/> - <value value="20" name="A7XX_PERF_LRZ_FEEDBACK_DISCARD"/> - <value value="21" name="A7XX_PERF_LRZ_FEEDBACK_STALL"/> - <value value="22" name="A7XX_PERF_LRZ_STALL_CYCLES_RB_ZPLANE"/> - <value value="23" name="A7XX_PERF_LRZ_STALL_CYCLES_RB_BPLANE"/> - <value value="24" name="A7XX_PERF_LRZ_RAS_MASK_TRANS"/> - <value value="25" name="A7XX_PERF_LRZ_STALL_CYCLES_MVC"/> - <value value="26" name="A7XX_PERF_LRZ_TILE_KILLED_BY_IMAGE_VRS"/> - <value value="27" name="A7XX_PERF_LRZ_TILE_KILLED_BY_Z"/> -</enum> - -<enum name="a7xx_cmp_perfcounter_select"> - <value value="0" name="A7XX_PERF_CMPDECMP_STALL_CYCLES_ARB"/> - <value value="1" name="A7XX_PERF_CMPDECMP_VBIF_LATENCY_CYCLES"/> - <value value="2" name="A7XX_PERF_CMPDECMP_VBIF_LATENCY_SAMPLES"/> - <value value="3" name="A7XX_PERF_CMPDECMP_VBIF_READ_DATA_CCU"/> - <value value="4" name="A7XX_PERF_CMPDECMP_VBIF_WRITE_DATA_CCU"/> - <value value="5" name="A7XX_PERF_CMPDECMP_VBIF_READ_REQUEST"/> - <value value="6" name="A7XX_PERF_CMPDECMP_VBIF_WRITE_REQUEST"/> - <value value="7" name="A7XX_PERF_CMPDECMP_VBIF_READ_DATA"/> - <value value="8" name="A7XX_PERF_CMPDECMP_VBIF_WRITE_DATA"/> - <value value="9" name="A7XX_PERF_CMPDECMP_DEPTH_WRITE_FLAG1_COUNT"/> - <value value="10" name="A7XX_PERF_CMPDECMP_DEPTH_WRITE_FLAG2_COUNT"/> - <value value="11" name="A7XX_PERF_CMPDECMP_DEPTH_WRITE_FLAG3_COUNT"/> - <value value="12" name="A7XX_PERF_CMPDECMP_DEPTH_WRITE_FLAG4_COUNT"/> - <value value="13" name="A7XX_PERF_CMPDECMP_DEPTH_WRITE_FLAG5_COUNT"/> - <value value="14" name="A7XX_PERF_CMPDECMP_DEPTH_WRITE_FLAG6_COUNT"/> - <value value="15" name="A7XX_PERF_CMPDECMP_DEPTH_WRITE_FLAG8_COUNT"/> - <value value="16" name="A7XX_PERF_CMPDECMP_COLOR_WRITE_FLAG1_COUNT"/> - <value value="17" name="A7XX_PERF_CMPDECMP_COLOR_WRITE_FLAG2_COUNT"/> - <value value="18" name="A7XX_PERF_CMPDECMP_COLOR_WRITE_FLAG3_COUNT"/> - <value value="19" name="A7XX_PERF_CMPDECMP_COLOR_WRITE_FLAG4_COUNT"/> - <value value="20" name="A7XX_PERF_CMPDECMP_COLOR_WRITE_FLAG5_COUNT"/> - <value value="21" name="A7XX_PERF_CMPDECMP_COLOR_WRITE_FLAG6_COUNT"/> - <value value="22" name="A7XX_PERF_CMPDECMP_COLOR_WRITE_FLAG8_COUNT"/> - <value value="23" name="A7XX_PERF_CMPDECMP_VBIF_READ_DATA_UCHE_CH0"/> - <value value="24" name="A7XX_PERF_CMPDECMP_VBIF_READ_DATA_UCHE_CH1"/> - <value value="25" name="A7XX_PERF_CMPDECMP_VBIF_WRITE_DATA_UCHE"/> - <value value="26" name="A7XX_PERF_CMPDECMP_DEPTH_WRITE_FLAG0_COUNT"/> - <value value="27" name="A7XX_PERF_CMPDECMP_COLOR_WRITE_FLAG0_COUNT"/> - <value value="28" name="A7XX_PERF_CMPDECMP_COLOR_WRITE_FLAGALPHA_COUNT"/> - <value value="29" name="A7XX_PERF_CMPDECMP_RESOLVE_EVENTS"/> - <value value="30" name="A7XX_PERF_CMPDECMP_CONCURRENT_RESOLVE_EVENTS"/> - <value value="31" name="A7XX_PERF_CMPDECMP_DROPPED_CLEAR_EVENTS"/> - <value value="32" name="A7XX_PERF_CMPDECMP_ST_BLOCKS_CONCURRENT"/> - <value value="33" name="A7XX_PERF_CMPDECMP_LRZ_ST_BLOCKS_CONCURRENT"/> - <value value="34" name="A7XX_PERF_CMPDECMP_DEPTH_READ_FLAG0_COUNT"/> - <value value="35" name="A7XX_PERF_CMPDECMP_DEPTH_READ_FLAG1_COUNT"/> - <value value="36" name="A7XX_PERF_CMPDECMP_DEPTH_READ_FLAG2_COUNT"/> - <value value="37" name="A7XX_PERF_CMPDECMP_DEPTH_READ_FLAG3_COUNT"/> - <value value="38" name="A7XX_PERF_CMPDECMP_DEPTH_READ_FLAG4_COUNT"/> - <value value="39" name="A7XX_PERF_CMPDECMP_DEPTH_READ_FLAG5_COUNT"/> - <value value="40" name="A7XX_PERF_CMPDECMP_DEPTH_READ_FLAG6_COUNT"/> - <value value="41" name="A7XX_PERF_CMPDECMP_DEPTH_READ_FLAG8_COUNT"/> - <value value="42" name="A7XX_PERF_CMPDECMP_COLOR_READ_FLAG0_COUNT"/> - <value value="43" name="A7XX_PERF_CMPDECMP_COLOR_READ_FLAG1_COUNT"/> - <value value="44" name="A7XX_PERF_CMPDECMP_COLOR_READ_FLAG2_COUNT"/> - <value value="45" name="A7XX_PERF_CMPDECMP_COLOR_READ_FLAG3_COUNT"/> - <value value="46" name="A7XX_PERF_CMPDECMP_COLOR_READ_FLAG4_COUNT"/> - <value value="47" name="A7XX_PERF_CMPDECMP_COLOR_READ_FLAG5_COUNT"/> - <value value="48" name="A7XX_PERF_CMPDECMP_COLOR_READ_FLAG6_COUNT"/> - <value value="49" name="A7XX_PERF_CMPDECMP_COLOR_READ_FLAG8_COUNT"/> -</enum> - -<enum name="a7xx_gbif_perfcounter_select"> - <value value="0" name="A7XX_PERF_GBIF_RESERVED_0"/> - <value value="1" name="A7XX_PERF_GBIF_RESERVED_1"/> - <value value="2" name="A7XX_PERF_GBIF_RESERVED_2"/> - <value value="3" name="A7XX_PERF_GBIF_RESERVED_3"/> - <value value="4" name="A7XX_PERF_GBIF_RESERVED_4"/> - <value value="5" name="A7XX_PERF_GBIF_RESERVED_5"/> - <value value="6" name="A7XX_PERF_GBIF_RESERVED_6"/> - <value value="7" name="A7XX_PERF_GBIF_RESERVED_7"/> - <value value="8" name="A7XX_PERF_GBIF_RESERVED_8"/> - <value value="9" name="A7XX_PERF_GBIF_RESERVED_9"/> - <value value="10" name="A7XX_PERF_GBIF_AXI0_READ_REQUESTS_TOTAL"/> - <value value="11" name="A7XX_PERF_GBIF_AXI1_READ_REQUESTS_TOTAL"/> - <value value="12" name="A7XX_PERF_GBIF_RESERVED_12"/> - <value value="13" name="A7XX_PERF_GBIF_RESERVED_13"/> - <value value="14" name="A7XX_PERF_GBIF_RESERVED_14"/> - <value value="15" name="A7XX_PERF_GBIF_RESERVED_15"/> - <value value="16" name="A7XX_PERF_GBIF_RESERVED_16"/> - <value value="17" name="A7XX_PERF_GBIF_RESERVED_17"/> - <value value="18" name="A7XX_PERF_GBIF_RESERVED_18"/> - <value value="19" name="A7XX_PERF_GBIF_RESERVED_19"/> - <value value="20" name="A7XX_PERF_GBIF_RESERVED_20"/> - <value value="21" name="A7XX_PERF_GBIF_RESERVED_21"/> - <value value="22" name="A7XX_PERF_GBIF_AXI0_WRITE_REQUESTS_TOTAL"/> - <value value="23" name="A7XX_PERF_GBIF_AXI1_WRITE_REQUESTS_TOTAL"/> - <value value="24" name="A7XX_PERF_GBIF_RESERVED_24"/> - <value value="25" name="A7XX_PERF_GBIF_RESERVED_25"/> - <value value="26" name="A7XX_PERF_GBIF_RESERVED_26"/> - <value value="27" name="A7XX_PERF_GBIF_RESERVED_27"/> - <value value="28" name="A7XX_PERF_GBIF_RESERVED_28"/> - <value value="29" name="A7XX_PERF_GBIF_RESERVED_29"/> - <value value="30" name="A7XX_PERF_GBIF_RESERVED_30"/> - <value value="31" name="A7XX_PERF_GBIF_RESERVED_31"/> - <value value="32" name="A7XX_PERF_GBIF_RESERVED_32"/> - <value value="33" name="A7XX_PERF_GBIF_RESERVED_33"/> - <value value="34" name="A7XX_PERF_GBIF_AXI0_READ_DATA_BEATS_TOTAL"/> - <value value="35" name="A7XX_PERF_GBIF_AXI1_READ_DATA_BEATS_TOTAL"/> - <value value="36" name="A7XX_PERF_GBIF_RESERVED_36"/> - <value value="37" name="A7XX_PERF_GBIF_RESERVED_37"/> - <value value="38" name="A7XX_PERF_GBIF_RESERVED_38"/> - <value value="39" name="A7XX_PERF_GBIF_RESERVED_39"/> - <value value="40" name="A7XX_PERF_GBIF_RESERVED_40"/> - <value value="41" name="A7XX_PERF_GBIF_RESERVED_41"/> - <value value="42" name="A7XX_PERF_GBIF_RESERVED_42"/> - <value value="43" name="A7XX_PERF_GBIF_RESERVED_43"/> - <value value="44" name="A7XX_PERF_GBIF_RESERVED_44"/> - <value value="45" name="A7XX_PERF_GBIF_RESERVED_45"/> - <value value="46" name="A7XX_PERF_GBIF_AXI0_WRITE_DATA_BEATS_TOTAL"/> - <value value="47" name="A7XX_PERF_GBIF_AXI1_WRITE_DATA_BEATS_TOTAL"/> - <value value="48" name="A7XX_PERF_GBIF_RESERVED_48"/> - <value value="49" name="A7XX_PERF_GBIF_RESERVED_49"/> - <value value="50" name="A7XX_PERF_GBIF_RESERVED_50"/> - <value value="51" name="A7XX_PERF_GBIF_RESERVED_51"/> - <value value="52" name="A7XX_PERF_GBIF_RESERVED_52"/> - <value value="53" name="A7XX_PERF_GBIF_RESERVED_53"/> - <value value="54" name="A7XX_PERF_GBIF_RESERVED_54"/> - <value value="55" name="A7XX_PERF_GBIF_RESERVED_55"/> - <value value="56" name="A7XX_PERF_GBIF_RESERVED_56"/> - <value value="57" name="A7XX_PERF_GBIF_RESERVED_57"/> - <value value="58" name="A7XX_PERF_GBIF_RESERVED_58"/> - <value value="59" name="A7XX_PERF_GBIF_RESERVED_59"/> - <value value="60" name="A7XX_PERF_GBIF_RESERVED_60"/> - <value value="61" name="A7XX_PERF_GBIF_RESERVED_61"/> - <value value="62" name="A7XX_PERF_GBIF_RESERVED_62"/> - <value value="63" name="A7XX_PERF_GBIF_RESERVED_63"/> - <value value="64" name="A7XX_PERF_GBIF_RESERVED_64"/> - <value value="65" name="A7XX_PERF_GBIF_RESERVED_65"/> - <value value="66" name="A7XX_PERF_GBIF_RESERVED_66"/> - <value value="67" name="A7XX_PERF_GBIF_RESERVED_67"/> - <value value="68" name="A7XX_PERF_GBIF_CYCLES_CH0_HELD_OFF_RD_ALL"/> - <value value="69" name="A7XX_PERF_GBIF_CYCLES_CH1_HELD_OFF_RD_ALL"/> - <value value="70" name="A7XX_PERF_GBIF_CYCLES_CH0_HELD_OFF_WR_ALL"/> - <value value="71" name="A7XX_PERF_GBIF_CYCLES_CH1_HELD_OFF_WR_ALL"/> - <value value="72" name="A7XX_PERF_GBIF_AXI_CH0_REQUEST_HELD_OFF"/> - <value value="73" name="A7XX_PERF_GBIF_AXI_CH1_REQUEST_HELD_OFF"/> - <value value="74" name="A7XX_PERF_GBIF_AXI_REQUEST_HELD_OFF"/> - <value value="75" name="A7XX_PERF_GBIF_AXI_CH0_WRITE_DATA_HELD_OFF"/> - <value value="76" name="A7XX_PERF_GBIF_AXI_CH1_WRITE_DATA_HELD_OFF"/> - <value value="77" name="A7XX_PERF_GBIF_AXI_ALL_WRITE_DATA_HELD_OFF"/> - <value value="78" name="A7XX_PERF_GBIF_AXI_ALL_READ_BEATS"/> - <value value="79" name="A7XX_PERF_GBIF_AXI_ALL_WRITE_BEATS"/> - <value value="80" name="A7XX_PERF_GBIF_AXI_ALL_BEATS"/> -</enum> - -<enum name="a7xx_ufc_perfcounter_select"> - <value value="0" name="A7XX_PERF_UFC_BUSY_CYCLES"/> - <value value="1" name="A7XX_PERF_UFC_READ_DATA_VBIF"/> - <value value="2" name="A7XX_PERF_UFC_WRITE_DATA_VBIF"/> - <value value="3" name="A7XX_PERF_UFC_READ_REQUEST_VBIF"/> - <value value="4" name="A7XX_PERF_UFC_WRITE_REQUEST_VBIF"/> - <value value="5" name="A7XX_PERF_UFC_LRZ_FILTER_HIT"/> - <value value="6" name="A7XX_PERF_UFC_LRZ_FILTER_MISS"/> - <value value="7" name="A7XX_PERF_UFC_CRE_FILTER_HIT"/> - <value value="8" name="A7XX_PERF_UFC_CRE_FILTER_MISS"/> - <value value="9" name="A7XX_PERF_UFC_SP_FILTER_HIT"/> - <value value="10" name="A7XX_PERF_UFC_SP_FILTER_MISS"/> - <value value="11" name="A7XX_PERF_UFC_SP_REQUESTS"/> - <value value="12" name="A7XX_PERF_UFC_TP_FILTER_HIT"/> - <value value="13" name="A7XX_PERF_UFC_TP_FILTER_MISS"/> - <value value="14" name="A7XX_PERF_UFC_TP_REQUESTS"/> - <value value="15" name="A7XX_PERF_UFC_MAIN_HIT_LRZ_PREFETCH"/> - <value value="16" name="A7XX_PERF_UFC_MAIN_HIT_CRE_PREFETCH"/> - <value value="17" name="A7XX_PERF_UFC_MAIN_HIT_SP_PREFETCH"/> - <value value="18" name="A7XX_PERF_UFC_MAIN_HIT_TP_PREFETCH"/> - <value value="19" name="A7XX_PERF_UFC_MAIN_HIT_UBWC_READ"/> - <value value="20" name="A7XX_PERF_UFC_MAIN_HIT_UBWC_WRITE"/> - <value value="21" name="A7XX_PERF_UFC_MAIN_MISS_LRZ_PREFETCH"/> - <value value="22" name="A7XX_PERF_UFC_MAIN_MISS_CRE_PREFETCH"/> - <value value="23" name="A7XX_PERF_UFC_MAIN_MISS_SP_PREFETCH"/> - <value value="24" name="A7XX_PERF_UFC_MAIN_MISS_TP_PREFETCH"/> - <value value="25" name="A7XX_PERF_UFC_MAIN_MISS_UBWC_READ"/> - <value value="26" name="A7XX_PERF_UFC_MAIN_MISS_UBWC_WRITE"/> - <value value="27" name="A7XX_PERF_UFC_UBWC_READ_UFC_TRANS"/> - <value value="28" name="A7XX_PERF_UFC_UBWC_WRITE_UFC_TRANS"/> - <value value="29" name="A7XX_PERF_UFC_STALL_CYCLES_GBIF_CMD"/> - <value value="30" name="A7XX_PERF_UFC_STALL_CYCLES_GBIF_RDATA"/> - <value value="31" name="A7XX_PERF_UFC_STALL_CYCLES_GBIF_WDATA"/> - <value value="32" name="A7XX_PERF_UFC_STALL_CYCLES_UBWC_WR_FLAG"/> - <value value="33" name="A7XX_PERF_UFC_STALL_CYCLES_UBWC_FLAG_RTN"/> - <value value="34" name="A7XX_PERF_UFC_STALL_CYCLES_UBWC_EVENT"/> - <value value="35" name="A7XX_PERF_UFC_LRZ_PREFETCH_STALLED_CYCLES"/> - <value value="36" name="A7XX_PERF_UFC_CRE_PREFETCH_STALLED_CYCLES"/> - <value value="37" name="A7XX_PERF_UFC_SPTP_PREFETCH_STALLED_CYCLES"/> - <value value="38" name="A7XX_PERF_UFC_UBWC_RD_STALLED_CYCLES"/> - <value value="39" name="A7XX_PERF_UFC_UBWC_WR_STALLED_CYCLES"/> - <value value="40" name="A7XX_PERF_UFC_PREFETCH_STALLED_CYCLES"/> - <value value="41" name="A7XX_PERF_UFC_EVICTION_STALLED_CYCLES"/> - <value value="42" name="A7XX_PERF_UFC_LOCK_STALLED_CYCLES"/> - <value value="43" name="A7XX_PERF_UFC_MISS_LATENCY_CYCLES"/> - <value value="44" name="A7XX_PERF_UFC_MISS_LATENCY_SAMPLES"/> - <value value="45" name="A7XX_PERF_UFC_UBWC_REQ_STALLED_CYCLES"/> - <value value="46" name="A7XX_PERF_UFC_TP_HINT_TAG_MISS"/> - <value value="47" name="A7XX_PERF_UFC_TP_HINT_TAG_HIT_RDY"/> - <value value="48" name="A7XX_PERF_UFC_TP_HINT_TAG_HIT_NRDY"/> - <value value="49" name="A7XX_PERF_UFC_TP_HINT_IS_FCLEAR"/> - <value value="50" name="A7XX_PERF_UFC_TP_HINT_IS_ALPHA0"/> - <value value="51" name="A7XX_PERF_UFC_SP_L1_FILTER_HIT"/> - <value value="52" name="A7XX_PERF_UFC_SP_L1_FILTER_MISS"/> - <value value="53" name="A7XX_PERF_UFC_SP_L1_FILTER_REQUESTS"/> - <value value="54" name="A7XX_PERF_UFC_TP_L1_TAG_HIT_RDY"/> - <value value="55" name="A7XX_PERF_UFC_TP_L1_TAG_HIT_NRDY"/> - <value value="56" name="A7XX_PERF_UFC_TP_L1_TAG_MISS"/> - <value value="57" name="A7XX_PERF_UFC_TP_L1_FILTER_REQUESTS"/> -</enum> - <domain name="A6XX" width="32" prefix="variant" varset="chip"> <bitset name="A6XX_RBBM_INT_0_MASK" inline="no" varset="chip"> <bitfield name="RBBM_GPU_IDLE" pos="0" type="boolean"/> @@ -2371,7 +177,7 @@ to upconvert to 32b float internally? <reg32 offset="0x08ab" name="CP_CONTEXT_SWITCH_LEVEL_STATUS" variants="A7XX-"/> <array offset="0x08D0" name="CP_PERFCTR_CP_SEL" stride="1" length="14"/> <array offset="0x08e0" name="CP_BV_PERFCTR_CP_SEL" stride="1" length="7" variants="A7XX-"/> - <reg64 offset="0x0900" name="CP_CRASH_SCRIPT_BASE"/> + <reg64 offset="0x0900" name="CP_CRASH_DUMP_SCRIPT_BASE"/> <reg32 offset="0x0902" name="CP_CRASH_DUMP_CNTL"/> <reg32 offset="0x0903" name="CP_CRASH_DUMP_STATUS"/> <reg32 offset="0x0908" name="CP_SQE_STAT_ADDR"/> @@ -2400,22 +206,22 @@ to upconvert to 32b float internally? --> <reg64 offset="0x0934" name="CP_VSD_BASE"/> - <bitset name="a6xx_roq_stat" inline="yes"> + <bitset name="a6xx_roq_status" inline="yes"> <bitfield name="RPTR" low="0" high="9"/> <bitfield name="WPTR" low="16" high="25"/> </bitset> - <reg32 offset="0x0939" name="CP_ROQ_RB_STAT" type="a6xx_roq_stat"/> - <reg32 offset="0x093a" name="CP_ROQ_IB1_STAT" type="a6xx_roq_stat"/> - <reg32 offset="0x093b" name="CP_ROQ_IB2_STAT" type="a6xx_roq_stat"/> - <reg32 offset="0x093c" name="CP_ROQ_SDS_STAT" type="a6xx_roq_stat"/> - <reg32 offset="0x093d" name="CP_ROQ_MRB_STAT" type="a6xx_roq_stat"/> - <reg32 offset="0x093e" name="CP_ROQ_VSD_STAT" type="a6xx_roq_stat"/> - - <reg32 offset="0x0943" name="CP_IB1_DWORDS"/> - <reg32 offset="0x0944" name="CP_IB2_DWORDS"/> - <reg32 offset="0x0945" name="CP_SDS_DWORDS"/> - <reg32 offset="0x0946" name="CP_MRB_DWORDS"/> - <reg32 offset="0x0947" name="CP_VSD_DWORDS"/> + <reg32 offset="0x0939" name="CP_ROQ_RB_STATUS" type="a6xx_roq_status"/> + <reg32 offset="0x093a" name="CP_ROQ_IB1_STATUS" type="a6xx_roq_status"/> + <reg32 offset="0x093b" name="CP_ROQ_IB2_STATUS" type="a6xx_roq_status"/> + <reg32 offset="0x093c" name="CP_ROQ_SDS_STATUS" type="a6xx_roq_status"/> + <reg32 offset="0x093d" name="CP_ROQ_MRB_STATUS" type="a6xx_roq_status"/> + <reg32 offset="0x093e" name="CP_ROQ_VSD_STATUS" type="a6xx_roq_status"/> + + <reg32 offset="0x0943" name="CP_IB1_INIT_SIZE"/> + <reg32 offset="0x0944" name="CP_IB2_INIT_SIZE"/> + <reg32 offset="0x0945" name="CP_SDS_INIT_SIZE"/> + <reg32 offset="0x0946" name="CP_MRB_INIT_SIZE"/> + <reg32 offset="0x0947" name="CP_VSD_INIT_SIZE"/> <reg32 offset="0x0948" name="CP_ROQ_AVAIL_RB"> <doc>number of remaining dwords incl current dword being consumed?</doc> @@ -2451,6 +257,7 @@ to upconvert to 32b float internally? <reg32 offset="0x098D" name="CP_AHB_CNTL"/> <reg32 offset="0x0A00" name="CP_APERTURE_CNTL_HOST" variants="A6XX"/> <reg32 offset="0x0A00" name="CP_APERTURE_CNTL_HOST" type="a7xx_aperture_cntl" variants="A7XX-"/> + <reg32 offset="0x0A01" name="CP_APERTURE_CNTL_SQE" variants="A6XX"/> <reg32 offset="0x0A03" name="CP_APERTURE_CNTL_CD" variants="A6XX"/> <reg32 offset="0x0A03" name="CP_APERTURE_CNTL_CD" type="a7xx_aperture_cntl" variants="A7XX-"/> @@ -2468,8 +275,8 @@ to upconvert to 32b float internally? <reg32 offset="0x0a97" name="CP_BV_MEM_POOL_DBG_DATA" variants="A7XX-"/> <reg64 offset="0x0a98" name="CP_BV_RB_RPTR_ADDR" variants="A7XX-"/> - <reg32 offset="0x0a9a" name="CP_RESOURCE_TBL_DBG_ADDR" variants="A7XX-"/> - <reg32 offset="0x0a9b" name="CP_RESOURCE_TBL_DBG_DATA" variants="A7XX-"/> + <reg32 offset="0x0a9a" name="CP_RESOURCE_TABLE_DBG_ADDR" variants="A7XX-"/> + <reg32 offset="0x0a9b" name="CP_RESOURCE_TABLE_DBG_DATA" variants="A7XX-"/> <reg32 offset="0x0ad0" name="CP_BV_APRIV_CNTL" variants="A7XX-"/> <reg32 offset="0x0ada" name="CP_BV_CHICKEN_DBG" variants="A7XX-"/> @@ -2619,28 +426,17 @@ to upconvert to 32b float internally? vertices in, number of primnitives assembled etc. --> - <reg32 offset="0x0540" name="RBBM_PRIMCTR_0_LO"/> <!-- vs vertices in --> - <reg32 offset="0x0541" name="RBBM_PRIMCTR_0_HI"/> - <reg32 offset="0x0542" name="RBBM_PRIMCTR_1_LO"/> <!-- vs primitives out --> - <reg32 offset="0x0543" name="RBBM_PRIMCTR_1_HI"/> - <reg32 offset="0x0544" name="RBBM_PRIMCTR_2_LO"/> <!-- hs vertices in --> - <reg32 offset="0x0545" name="RBBM_PRIMCTR_2_HI"/> - <reg32 offset="0x0546" name="RBBM_PRIMCTR_3_LO"/> <!-- hs patches out --> - <reg32 offset="0x0547" name="RBBM_PRIMCTR_3_HI"/> - <reg32 offset="0x0548" name="RBBM_PRIMCTR_4_LO"/> <!-- dss vertices in --> - <reg32 offset="0x0549" name="RBBM_PRIMCTR_4_HI"/> - <reg32 offset="0x054a" name="RBBM_PRIMCTR_5_LO"/> <!-- ds primitives out --> - <reg32 offset="0x054b" name="RBBM_PRIMCTR_5_HI"/> - <reg32 offset="0x054c" name="RBBM_PRIMCTR_6_LO"/> <!-- gs primitives in --> - <reg32 offset="0x054d" name="RBBM_PRIMCTR_6_HI"/> - <reg32 offset="0x054e" name="RBBM_PRIMCTR_7_LO"/> <!-- gs primitives out --> - <reg32 offset="0x054f" name="RBBM_PRIMCTR_7_HI"/> - <reg32 offset="0x0550" name="RBBM_PRIMCTR_8_LO"/> <!-- gs primitives out --> - <reg32 offset="0x0551" name="RBBM_PRIMCTR_8_HI"/> - <reg32 offset="0x0552" name="RBBM_PRIMCTR_9_LO"/> <!-- raster primitives in --> - <reg32 offset="0x0553" name="RBBM_PRIMCTR_9_HI"/> - <reg32 offset="0x0554" name="RBBM_PRIMCTR_10_LO"/> - <reg32 offset="0x0555" name="RBBM_PRIMCTR_10_HI"/> + <reg64 offset="0x0540" name="RBBM_PIPESTAT_IAVERTICES"/> + <reg64 offset="0x0542" name="RBBM_PIPESTAT_IAPRIMITIVES"/> + <reg64 offset="0x0544" name="RBBM_PIPESTAT_VSINVOCATIONS"/> + <reg64 offset="0x0546" name="RBBM_PIPESTAT_HSINVOCATIONS"/> + <reg64 offset="0x0548" name="RBBM_PIPESTAT_DSINVOCATIONS"/> + <reg64 offset="0x054a" name="RBBM_PIPESTAT_GSINVOCATIONS"/> + <reg64 offset="0x054c" name="RBBM_PIPESTAT_GSPRIMITIVES"/> + <reg64 offset="0x054e" name="RBBM_PIPESTAT_CINVOCATIONS"/> + <reg64 offset="0x0550" name="RBBM_PIPESTAT_CPRIMITIVES"/> + <reg64 offset="0x0552" name="RBBM_PIPESTAT_PSINVOCATIONS"/> + <reg64 offset="0x0554" name="RBBM_PIPESTAT_CSINVOCATIONS"/> <reg32 offset="0xF400" name="RBBM_SECVID_TRUST_CNTL"/> <reg64 offset="0xF800" name="RBBM_SECVID_TSB_TRUSTED_BASE"/> @@ -2779,7 +575,7 @@ to upconvert to 32b float internally? <reg32 offset="0x0011f" name="RBBM_CGC_P2S_TRIG_CMD" variants="A7XX-"/> <reg32 offset="0x00120" name="RBBM_CLOCK_CNTL_TEX_FCHE"/> <reg32 offset="0x00121" name="RBBM_CLOCK_DELAY_TEX_FCHE"/> - <reg32 offset="0x00122" name="RBBM_CLOCK_HYST_TEX_FCHE"/> + <reg32 offset="0x00122" name="RBBM_CLOCK_HYST_TEX_FCHE" variants="A6XX"/> <reg32 offset="0x00122" name="RBBM_CGC_P2S_STATUS" variants="A7XX-"> <bitfield name="TXDONE" pos="0" type="boolean"/> </reg32> @@ -2840,7 +636,7 @@ to upconvert to 32b float internally? </reg32> <reg32 offset="0x062f" name="DBGC_CFG_DBGBUS_TRACE_BUF1"/> <reg32 offset="0x0630" name="DBGC_CFG_DBGBUS_TRACE_BUF2"/> - <array offset="0x0CD8" name="VSC_PERFCTR_VSC_SEL" stride="1" length="2"/> + <array offset="0x0CD8" name="VSC_PERFCTR_VSC_SEL" stride="1" length="2" variants="A6XX"/> <reg32 offset="0x0CD8" name="VSC_UNKNOWN_0CD8" variants="A7XX"> <doc> Set to true when binning, isn't changed afterwards @@ -2936,8 +732,8 @@ to upconvert to 32b float internally? <bitfield name="WIDTH" low="0" high="7" shr="5" type="uint"/> <bitfield name="HEIGHT" low="8" high="16" shr="4" type="uint"/> </reg32> - <reg64 offset="0x0c03" name="VSC_DRAW_STRM_SIZE_ADDRESS" type="waddress" usage="cmd"/> - <reg32 offset="0x0c06" name="VSC_BIN_COUNT" usage="rp_blit"> + <reg64 offset="0x0c03" name="VSC_SIZE_BASE" type="waddress" usage="cmd"/> + <reg32 offset="0x0c06" name="VSC_EXPANDED_BIN_CNTL" usage="rp_blit"> <bitfield name="NX" low="1" high="10" type="uint"/> <bitfield name="NY" low="11" high="20" type="uint"/> </reg32> @@ -2967,14 +763,14 @@ to upconvert to 32b float internally? LIMIT is set to PITCH - 64, to make room for a bit of overflow --> - <reg64 offset="0x0c30" name="VSC_PRIM_STRM_ADDRESS" type="waddress" usage="cmd"/> - <reg32 offset="0x0c32" name="VSC_PRIM_STRM_PITCH" usage="cmd"/> - <reg32 offset="0x0c33" name="VSC_PRIM_STRM_LIMIT" usage="cmd"/> - <reg64 offset="0x0c34" name="VSC_DRAW_STRM_ADDRESS" type="waddress" usage="cmd"/> - <reg32 offset="0x0c36" name="VSC_DRAW_STRM_PITCH" usage="cmd"/> - <reg32 offset="0x0c37" name="VSC_DRAW_STRM_LIMIT" usage="cmd"/> - - <array offset="0x0c38" name="VSC_STATE" stride="1" length="32" usage="rp_blit"> + <reg64 offset="0x0c30" name="VSC_PIPE_DATA_PRIM_BASE" type="waddress" usage="cmd"/> + <reg32 offset="0x0c32" name="VSC_PIPE_DATA_PRIM_STRIDE" usage="cmd"/> + <reg32 offset="0x0c33" name="VSC_PIPE_DATA_PRIM_LENGTH" usage="cmd"/> + <reg64 offset="0x0c34" name="VSC_PIPE_DATA_DRAW_BASE" type="waddress" usage="cmd"/> + <reg32 offset="0x0c36" name="VSC_PIPE_DATA_DRAW_STRIDE" usage="cmd"/> + <reg32 offset="0x0c37" name="VSC_PIPE_DATA_DRAW_LENGTH" usage="cmd"/> + + <array offset="0x0c38" name="VSC_CHANNEL_VISIBILITY" stride="1" length="32" usage="rp_blit"> <doc> Seems to be a bitmap of which tiles mapped to the VSC pipe contain geometry. @@ -2985,7 +781,7 @@ to upconvert to 32b float internally? <reg32 offset="0x0" name="REG"/> </array> - <array offset="0x0c58" name="VSC_PRIM_STRM_SIZE" stride="1" length="32" variants="A6XX" usage="rp_blit"> + <array offset="0x0c58" name="VSC_PIPE_DATA_PRIM_SIZE" stride="1" length="32" variants="A6XX" usage="rp_blit"> <doc> Has the size of data written to corresponding VSC_PRIM_STRM buffer. @@ -2993,10 +789,10 @@ to upconvert to 32b float internally? <reg32 offset="0x0" name="REG"/> </array> - <array offset="0x0c78" name="VSC_DRAW_STRM_SIZE" stride="1" length="32" variants="A6XX" usage="rp_blit"> + <array offset="0x0c78" name="VSC_PIPE_DATA_DRAW_SIZE" stride="1" length="32" variants="A6XX" usage="rp_blit"> <doc> Has the size of data written to corresponding VSC pipe, ie. - same thing that is written out to VSC_DRAW_STRM_SIZE_ADDRESS_LO/HI + same thing that is written out to VSC_SIZE_BASE </doc> <reg32 offset="0x0" name="REG"/> </array> @@ -3028,17 +824,17 @@ to upconvert to 32b float internally? <bitfield name="PERSP_DIVISION_DISABLE" pos="9" type="boolean"/> </reg32> - <bitset name="a6xx_gras_xs_cl_cntl" inline="yes"> + <bitset name="a6xx_gras_xs_clip_cull_distance" inline="yes"> <bitfield name="CLIP_MASK" low="0" high="7"/> <bitfield name="CULL_MASK" low="8" high="15"/> </bitset> - <reg32 offset="0x8001" name="GRAS_VS_CL_CNTL" type="a6xx_gras_xs_cl_cntl" usage="rp_blit"/> - <reg32 offset="0x8002" name="GRAS_DS_CL_CNTL" type="a6xx_gras_xs_cl_cntl" usage="rp_blit"/> - <reg32 offset="0x8003" name="GRAS_GS_CL_CNTL" type="a6xx_gras_xs_cl_cntl" usage="rp_blit"/> - <reg32 offset="0x8004" name="GRAS_MAX_LAYER_INDEX" low="0" high="10" type="uint" usage="rp_blit"/> + <reg32 offset="0x8001" name="GRAS_CL_VS_CLIP_CULL_DISTANCE" type="a6xx_gras_xs_clip_cull_distance" usage="rp_blit"/> + <reg32 offset="0x8002" name="GRAS_CL_DS_CLIP_CULL_DISTANCE" type="a6xx_gras_xs_clip_cull_distance" usage="rp_blit"/> + <reg32 offset="0x8003" name="GRAS_CL_GS_CLIP_CULL_DISTANCE" type="a6xx_gras_xs_clip_cull_distance" usage="rp_blit"/> + <reg32 offset="0x8004" name="GRAS_CL_ARRAY_SIZE" low="0" high="10" type="uint" usage="rp_blit"/> - <reg32 offset="0x8005" name="GRAS_CNTL" usage="rp_blit"> - <!-- see also RB_RENDER_CONTROL0 --> + <reg32 offset="0x8005" name="GRAS_CL_INTERP_CNTL" usage="rp_blit"> + <!-- see also RB_INTERP_CNTL --> <bitfield name="IJ_PERSP_PIXEL" pos="0" type="boolean"/> <bitfield name="IJ_PERSP_CENTROID" pos="1" type="boolean"/> <bitfield name="IJ_PERSP_SAMPLE" pos="2" type="boolean"/> @@ -3067,7 +863,7 @@ to upconvert to 32b float internally? <!-- <reg32 offset="0x80f0" name="GRAS_UNKNOWN_80F0" type="a6xx_reg_xy"/> --> <!-- 0x8006-0x800f invalid --> - <array offset="0x8010" name="GRAS_CL_VPORT" stride="6" length="16" usage="rp_blit"> + <array offset="0x8010" name="GRAS_CL_VIEWPORT" stride="6" length="16" usage="rp_blit"> <reg32 offset="0" name="XOFFSET" type="float"/> <reg32 offset="1" name="XSCALE" type="float"/> <reg32 offset="2" name="YOFFSET" type="float"/> @@ -3075,7 +871,7 @@ to upconvert to 32b float internally? <reg32 offset="4" name="ZOFFSET" type="float"/> <reg32 offset="5" name="ZSCALE" type="float"/> </array> - <array offset="0x8070" name="GRAS_CL_Z_CLAMP" stride="2" length="16" usage="rp_blit"> + <array offset="0x8070" name="GRAS_CL_VIEWPORT_ZCLAMP" stride="2" length="16" usage="rp_blit"> <reg32 offset="0" name="MIN" type="float"/> <reg32 offset="1" name="MAX" type="float"/> </array> @@ -3124,7 +920,12 @@ to upconvert to 32b float internally? <reg32 offset="0x8099" name="GRAS_SU_CONSERVATIVE_RAS_CNTL" usage="cmd"> <bitfield name="CONSERVATIVERASEN" pos="0" type="boolean"/> - <bitfield name="SHIFTAMOUNT" low="1" high="2"/> + <enum name="a6xx_shift_amount"> + <value value="0" name="NO_SHIFT"/> + <value value="1" name="HALF_PIXEL_SHIFT"/> + <value value="2" name="FULL_PIXEL_SHIFT"/> + </enum> + <bitfield name="SHIFTAMOUNT" low="1" high="2" type="a6xx_shift_amount"/> <bitfield name="INNERCONSERVATIVERASEN" pos="3" type="boolean"/> <bitfield name="UNK4" low="4" high="5"/> </reg32> @@ -3133,13 +934,13 @@ to upconvert to 32b float internally? <bitfield name="LINELENGTHEN" pos="1" type="boolean"/> </reg32> - <bitset name="a6xx_gras_layer_cntl" inline="yes"> + <bitset name="a6xx_gras_us_xs_siv_cntl" inline="yes"> <bitfield name="WRITES_LAYER" pos="0" type="boolean"/> <bitfield name="WRITES_VIEW" pos="1" type="boolean"/> </bitset> - <reg32 offset="0x809b" name="GRAS_VS_LAYER_CNTL" type="a6xx_gras_layer_cntl" usage="rp_blit"/> - <reg32 offset="0x809c" name="GRAS_GS_LAYER_CNTL" type="a6xx_gras_layer_cntl" usage="rp_blit"/> - <reg32 offset="0x809d" name="GRAS_DS_LAYER_CNTL" type="a6xx_gras_layer_cntl" usage="rp_blit"/> + <reg32 offset="0x809b" name="GRAS_SU_VS_SIV_CNTL" type="a6xx_gras_us_xs_siv_cntl" usage="rp_blit"/> + <reg32 offset="0x809c" name="GRAS_SU_GS_SIV_CNTL" type="a6xx_gras_us_xs_siv_cntl" usage="rp_blit"/> + <reg32 offset="0x809d" name="GRAS_SU_DS_SIV_CNTL" type="a6xx_gras_us_xs_siv_cntl" usage="rp_blit"/> <!-- 0x809e/0x809f invalid --> <enum name="a6xx_sequenced_thread_dist"> @@ -3213,13 +1014,13 @@ to upconvert to 32b float internally? <enum name="a6xx_lrz_feedback_mask"> <value value="0x0" name="LRZ_FEEDBACK_NONE"/> <value value="0x1" name="LRZ_FEEDBACK_EARLY_Z"/> - <value value="0x2" name="LRZ_FEEDBACK_EARLY_LRZ_LATE_Z"/> + <value value="0x2" name="LRZ_FEEDBACK_EARLY_Z_LATE_Z"/> <!-- We don't have a flag type and this flags combination is often used --> - <value value="0x3" name="LRZ_FEEDBACK_EARLY_Z_OR_EARLY_LRZ_LATE_Z"/> + <value value="0x3" name="LRZ_FEEDBACK_EARLY_Z_OR_EARLY_Z_LATE_Z"/> <value value="0x4" name="LRZ_FEEDBACK_LATE_Z"/> </enum> - <reg32 offset="0x80a1" name="GRAS_BIN_CONTROL" usage="rp_blit"> + <reg32 offset="0x80a1" name="GRAS_SC_BIN_CNTL" usage="rp_blit"> <bitfield name="BINW" low="0" high="5" shr="5" type="uint"/> <bitfield name="BINH" low="8" high="14" shr="4" type="uint"/> <bitfield name="RENDER_MODE" low="18" high="20" type="a6xx_render_mode"/> @@ -3235,22 +1036,22 @@ to upconvert to 32b float internally? <bitfield name="UNK27" pos="27"/> </reg32> - <reg32 offset="0x80a2" name="GRAS_RAS_MSAA_CNTL" usage="rp_blit"> + <reg32 offset="0x80a2" name="GRAS_SC_RAS_MSAA_CNTL" usage="rp_blit"> <bitfield name="SAMPLES" low="0" high="1" type="a3xx_msaa_samples"/> <bitfield name="UNK2" pos="2"/> <bitfield name="UNK3" pos="3"/> </reg32> - <reg32 offset="0x80a3" name="GRAS_DEST_MSAA_CNTL" usage="rp_blit"> + <reg32 offset="0x80a3" name="GRAS_SC_DEST_MSAA_CNTL" usage="rp_blit"> <bitfield name="SAMPLES" low="0" high="1" type="a3xx_msaa_samples"/> <bitfield name="MSAA_DISABLE" pos="2" type="boolean"/> </reg32> - <bitset name="a6xx_sample_config" inline="yes"> + <bitset name="a6xx_msaa_sample_pos_cntl" inline="yes"> <bitfield name="UNK0" pos="0"/> <bitfield name="LOCATION_ENABLE" pos="1" type="boolean"/> </bitset> - <bitset name="a6xx_sample_locations" inline="yes"> + <bitset name="a6xx_programmable_msaa_pos" inline="yes"> <bitfield name="SAMPLE_0_X" low="0" high="3" radix="4" type="fixed"/> <bitfield name="SAMPLE_0_Y" low="4" high="7" radix="4" type="fixed"/> <bitfield name="SAMPLE_1_X" low="8" high="11" radix="4" type="fixed"/> @@ -3261,9 +1062,9 @@ to upconvert to 32b float internally? <bitfield name="SAMPLE_3_Y" low="28" high="31" radix="4" type="fixed"/> </bitset> - <reg32 offset="0x80a4" name="GRAS_SAMPLE_CONFIG" type="a6xx_sample_config" usage="rp_blit"/> - <reg32 offset="0x80a5" name="GRAS_SAMPLE_LOCATION_0" type="a6xx_sample_locations" usage="rp_blit"/> - <reg32 offset="0x80a6" name="GRAS_SAMPLE_LOCATION_1" type="a6xx_sample_locations" usage="rp_blit"/> + <reg32 offset="0x80a4" name="GRAS_SC_MSAA_SAMPLE_POS_CNTL" type="a6xx_msaa_sample_pos_cntl" usage="rp_blit"/> + <reg32 offset="0x80a5" name="GRAS_SC_PROGRAMMABLE_MSAA_POS_0" type="a6xx_programmable_msaa_pos" usage="rp_blit"/> + <reg32 offset="0x80a6" name="GRAS_SC_PROGRAMMABLE_MSAA_POS_1" type="a6xx_programmable_msaa_pos" usage="rp_blit"/> <reg32 offset="0x80a7" name="GRAS_UNKNOWN_80A7" variants="A7XX-" usage="cmd"/> @@ -3286,13 +1087,36 @@ to upconvert to 32b float internally? <reg32 offset="0x80f0" name="GRAS_SC_WINDOW_SCISSOR_TL" type="a6xx_reg_xy" usage="rp_blit"/> <reg32 offset="0x80f1" name="GRAS_SC_WINDOW_SCISSOR_BR" type="a6xx_reg_xy" usage="rp_blit"/> - <!-- 0x80f4 - 0x80fa are used for VK_KHR_fragment_shading_rate --> - <reg64 offset="0x80f4" name="GRAS_UNKNOWN_80F4" variants="A7XX-" usage="cmd"/> - <reg64 offset="0x80f5" name="GRAS_UNKNOWN_80F5" variants="A7XX-" usage="cmd"/> - <reg64 offset="0x80f6" name="GRAS_UNKNOWN_80F6" variants="A7XX-" usage="cmd"/> - <reg64 offset="0x80f8" name="GRAS_UNKNOWN_80F8" variants="A7XX-" usage="cmd"/> - <reg64 offset="0x80f9" name="GRAS_UNKNOWN_80F9" variants="A7XX-" usage="cmd"/> - <reg64 offset="0x80fa" name="GRAS_UNKNOWN_80FA" variants="A7XX-" usage="cmd"/> + <enum name="a6xx_fsr_combiner"> + <value value="0" name="FSR_COMBINER_OP_KEEP"/> + <value value="1" name="FSR_COMBINER_OP_REPLACE"/> + <value value="2" name="FSR_COMBINER_OP_MIN"/> + <value value="3" name="FSR_COMBINER_OP_MAX"/> + <value value="4" name="FSR_COMBINER_OP_MUL"/> + </enum> + + <reg32 offset="0x80f4" name="GRAS_VRS_CONFIG" variants="A7XX-" usage="rp_blit"> + <bitfield name="PIPELINE_FSR_ENABLE" pos="0" type="boolean"/> + <bitfield name="FRAG_SIZE_X" low="1" high="2" type="uint"/> + <bitfield name="FRAG_SIZE_Y" low="3" high="4" type="uint"/> + <bitfield name="COMBINER_OP_1" low="5" high="7" type="a6xx_fsr_combiner"/> + <bitfield name="COMBINER_OP_2" low="8" high="10" type="a6xx_fsr_combiner"/> + <bitfield name="ATTACHMENT_FSR_ENABLE" pos="13" type="boolean"/> + <bitfield name="PRIMITIVE_FSR_ENABLE" pos="20" type="boolean"/> + </reg32> + <reg32 offset="0x80f5" name="GRAS_QUALITY_BUFFER_INFO" variants="A7XX-" usage="rp_blit"> + <bitfield name="LAYERED" pos="0" type="boolean"/> + <bitfield name="TILE_MODE" low="1" high="2" type="a6xx_tile_mode"/> + </reg32> + <reg32 offset="0x80f6" name="GRAS_QUALITY_BUFFER_DIMENSION" variants="A7XX-" usage="rp_blit"> + <bitfield name="WIDTH" low="0" high="15" type="uint"/> + <bitfield name="HEIGHT" low="16" high="31" type="uint"/> + </reg32> + <reg64 offset="0x80f8" name="GRAS_QUALITY_BUFFER_BASE" variants="A7XX-" type="waddress" usage="rp_blit"/> + <reg32 offset="0x80fa" name="GRAS_QUALITY_BUFFER_PITCH" variants="A7XX-" usage="rp_blit"> + <bitfield name="PITCH" shr="6" low="0" high="7" type="uint"/> + <bitfield name="ARRAY_PITCH" shr="6" low="10" high="28" type="uint"/> + </reg32> <enum name="a6xx_lrz_dir_status"> <value value="0x1" name="LRZ_DIR_LE"/> @@ -3313,7 +1137,7 @@ to upconvert to 32b float internally? </doc> <bitfield name="FC_ENABLE" pos="3" type="boolean" variants="A6XX"/> <!-- set when depth-test + depth-write enabled --> - <bitfield name="Z_TEST_ENABLE" pos="4" type="boolean"/> + <bitfield name="Z_WRITE_ENABLE" pos="4" type="boolean"/> <bitfield name="Z_BOUNDS_ENABLE" pos="5" type="boolean"/> <bitfield name="DIR" low="6" high="7" type="a6xx_lrz_dir_status"/> <doc> @@ -3339,14 +1163,13 @@ to upconvert to 32b float internally? <bitfield name="FRAGCOORDSAMPLEMODE" low="1" high="2" type="a6xx_fragcoord_sample_mode"/> </reg32> - <reg32 offset="0x8102" name="GRAS_LRZ_MRT_BUF_INFO_0" usage="rp_blit"> + <reg32 offset="0x8102" name="GRAS_LRZ_MRT_BUFFER_INFO_0" usage="rp_blit"> <bitfield name="COLOR_FORMAT" low="0" high="7" type="a6xx_format"/> </reg32> <reg64 offset="0x8103" name="GRAS_LRZ_BUFFER_BASE" align="256" type="waddress" usage="rp_blit"/> <reg32 offset="0x8105" name="GRAS_LRZ_BUFFER_PITCH" usage="rp_blit"> - <!-- TODO: fix the shr fields --> <bitfield name="PITCH" low="0" high="7" shr="5" type="uint"/> - <bitfield name="ARRAY_PITCH" low="10" high="28" shr="4" type="uint"/> + <bitfield name="ARRAY_PITCH" low="10" high="28" shr="8" type="uint"/> </reg32> <!-- @@ -3381,18 +1204,18 @@ to upconvert to 32b float internally? --> <reg64 offset="0x8106" name="GRAS_LRZ_FAST_CLEAR_BUFFER_BASE" align="64" type="waddress" usage="rp_blit"/> <!-- 0x8108 invalid --> - <reg32 offset="0x8109" name="GRAS_SAMPLE_CNTL" usage="rp_blit"> + <reg32 offset="0x8109" name="GRAS_LRZ_PS_SAMPLEFREQ_CNTL" usage="rp_blit"> <bitfield name="PER_SAMP_MODE" pos="0" type="boolean"/> </reg32> <!-- LRZ buffer represents a single array layer + mip level, and there is a single buffer per depth image. Thus to reuse LRZ between renderpasses it is necessary to track the depth view used in the past renderpass, which - GRAS_LRZ_DEPTH_VIEW is for. - GRAS_LRZ_CNTL checks if current value of GRAS_LRZ_DEPTH_VIEW is equal to + GRAS_LRZ_VIEW_INFO is for. + GRAS_LRZ_CNTL checks if current value of GRAS_LRZ_VIEW_INFO is equal to the value stored in the LRZ buffer, if not - LRZ is disabled. --> - <reg32 offset="0x810a" name="GRAS_LRZ_DEPTH_VIEW" usage="cmd"> + <reg32 offset="0x810a" name="GRAS_LRZ_VIEW_INFO" usage="cmd"> <bitfield name="BASE_LAYER" low="0" high="10" type="uint"/> <bitfield name="LAYER_COUNT" low="16" high="26" type="uint"/> <bitfield name="BASE_MIP_LEVEL" low="28" high="31" type="uint"/> @@ -3408,7 +1231,7 @@ to upconvert to 32b float internally? <reg32 offset="0x8110" name="GRAS_UNKNOWN_8110" low="0" high="1" usage="cmd"/> <!-- A bit tentative but it's a color and it is followed by LRZ_CLEAR --> - <reg32 offset="0x8111" name="GRAS_LRZ_CLEAR_DEPTH_F32" type="float" variants="A7XX-"/> + <reg32 offset="0x8111" name="GRAS_LRZ_DEPTH_CLEAR" type="float" variants="A7XX-"/> <reg32 offset="0x8113" name="GRAS_LRZ_DEPTH_BUFFER_INFO" variants="A7XX-" usage="rp_blit"> <bitfield name="DEPTH_FORMAT" low="0" high="2" type="a6xx_depth_format"/> @@ -3430,7 +1253,7 @@ to upconvert to 32b float internally? <value value="0x5" name="ROTATE_VFLIP"/> </enum> - <bitset name="a6xx_2d_blit_cntl" inline="yes"> + <bitset name="a6xx_a2d_bit_cntl" inline="yes"> <bitfield name="ROTATE" low="0" high="2" type="a6xx_rotation"/> <bitfield name="OVERWRITEEN" pos="3" type="boolean"/> <bitfield name="UNK4" low="4" high="6"/> @@ -3447,22 +1270,22 @@ to upconvert to 32b float internally? <bitfield name="UNK30" pos="30" type="boolean" variants="A7XX-"/> </bitset> - <reg32 offset="0x8400" name="GRAS_2D_BLIT_CNTL" type="a6xx_2d_blit_cntl" usage="rp_blit"/> + <reg32 offset="0x8400" name="GRAS_A2D_BLT_CNTL" type="a6xx_a2d_bit_cntl" usage="rp_blit"/> <!-- note: the low 8 bits for src coords are valid, probably fixed point it would be a bit weird though, since we subtract 1 from BR coords apparently signed, gallium driver uses negative coords and it works? --> - <reg32 offset="0x8401" name="GRAS_2D_SRC_TL_X" low="8" high="24" type="int" usage="rp_blit"/> - <reg32 offset="0x8402" name="GRAS_2D_SRC_BR_X" low="8" high="24" type="int" usage="rp_blit"/> - <reg32 offset="0x8403" name="GRAS_2D_SRC_TL_Y" low="8" high="24" type="int" usage="rp_blit"/> - <reg32 offset="0x8404" name="GRAS_2D_SRC_BR_Y" low="8" high="24" type="int" usage="rp_blit"/> - <reg32 offset="0x8405" name="GRAS_2D_DST_TL" type="a6xx_reg_xy" usage="rp_blit"/> - <reg32 offset="0x8406" name="GRAS_2D_DST_BR" type="a6xx_reg_xy" usage="rp_blit"/> + <reg32 offset="0x8401" name="GRAS_A2D_SRC_XMIN" low="8" high="24" type="int" usage="rp_blit"/> + <reg32 offset="0x8402" name="GRAS_A2D_SRC_XMAX" low="8" high="24" type="int" usage="rp_blit"/> + <reg32 offset="0x8403" name="GRAS_A2D_SRC_YMIN" low="8" high="24" type="int" usage="rp_blit"/> + <reg32 offset="0x8404" name="GRAS_A2D_SRC_YMAX" low="8" high="24" type="int" usage="rp_blit"/> + <reg32 offset="0x8405" name="GRAS_A2D_DEST_TL" type="a6xx_reg_xy" usage="rp_blit"/> + <reg32 offset="0x8406" name="GRAS_A2D_DEST_BR" type="a6xx_reg_xy" usage="rp_blit"/> <reg32 offset="0x8407" name="GRAS_2D_UNKNOWN_8407" low="0" high="31"/> <reg32 offset="0x8408" name="GRAS_2D_UNKNOWN_8408" low="0" high="31"/> <reg32 offset="0x8409" name="GRAS_2D_UNKNOWN_8409" low="0" high="31"/> - <reg32 offset="0x840a" name="GRAS_2D_RESOLVE_CNTL_1" type="a6xx_reg_xy" usage="rp_blit"/> - <reg32 offset="0x840b" name="GRAS_2D_RESOLVE_CNTL_2" type="a6xx_reg_xy" usage="rp_blit"/> + <reg32 offset="0x840a" name="GRAS_A2D_SCISSOR_TL" type="a6xx_reg_xy" usage="rp_blit"/> + <reg32 offset="0x840b" name="GRAS_A2D_SCISSOR_BR" type="a6xx_reg_xy" usage="rp_blit"/> <!-- 0x840c-0x85ff invalid --> <!-- always 0x880 ? (and 0 in a640/a650 traces?) --> @@ -3481,7 +1304,7 @@ to upconvert to 32b float internally? --> <!-- same as GRAS_BIN_CONTROL, but without bit 27: --> - <reg32 offset="0x8800" name="RB_BIN_CONTROL" variants="A6XX" usage="rp_blit"> + <reg32 offset="0x8800" name="RB_CNTL" variants="A6XX" usage="rp_blit"> <bitfield name="BINW" low="0" high="5" shr="5" type="uint"/> <bitfield name="BINH" low="8" high="14" shr="4" type="uint"/> <bitfield name="RENDER_MODE" low="18" high="20" type="a6xx_render_mode"/> @@ -3490,7 +1313,7 @@ to upconvert to 32b float internally? <bitfield name="LRZ_FEEDBACK_ZMODE_MASK" low="24" high="26" type="a6xx_lrz_feedback_mask"/> </reg32> - <reg32 offset="0x8800" name="RB_BIN_CONTROL" variants="A7XX-" usage="rp_blit"> + <reg32 offset="0x8800" name="RB_CNTL" variants="A7XX-" usage="rp_blit"> <bitfield name="BINW" low="0" high="5" shr="5" type="uint"/> <bitfield name="BINH" low="8" high="14" shr="4" type="uint"/> <bitfield name="RENDER_MODE" low="18" high="20" type="a6xx_render_mode"/> @@ -3501,8 +1324,7 @@ to upconvert to 32b float internally? <reg32 offset="0x8801" name="RB_RENDER_CNTL" variants="A6XX" usage="rp_blit"> <bitfield name="CCUSINGLECACHELINESIZE" low="3" high="5"/> <bitfield name="EARLYVIZOUTEN" pos="6" type="boolean"/> - <!-- set during binning pass: --> - <bitfield name="BINNING" pos="7" type="boolean"/> + <bitfield name="FS_DISABLE" pos="7" type="boolean"/> <bitfield name="UNK8" low="8" high="10"/> <bitfield name="RASTER_MODE" pos="8" type="a6xx_raster_mode"/> <bitfield name="RASTER_DIRECTION" low="9" high="10" type="a6xx_raster_direction"/> @@ -3515,15 +1337,14 @@ to upconvert to 32b float internally? </reg32> <reg32 offset="0x8801" name="RB_RENDER_CNTL" variants="A7XX-" usage="rp_blit"> <bitfield name="EARLYVIZOUTEN" pos="6" type="boolean"/> - <!-- set during binning pass: --> - <bitfield name="BINNING" pos="7" type="boolean"/> + <bitfield name="FS_DISABLE" pos="7" type="boolean"/> <bitfield name="RASTER_MODE" pos="8" type="a6xx_raster_mode"/> <bitfield name="RASTER_DIRECTION" low="9" high="10" type="a6xx_raster_direction"/> <bitfield name="CONSERVATIVERASEN" pos="11" type="boolean"/> <bitfield name="INNERCONSERVATIVERASEN" pos="12" type="boolean"/> </reg32> <reg32 offset="0x8116" name="GRAS_SU_RENDER_CNTL" variants="A7XX-" usage="rp_blit"> - <bitfield name="BINNING" pos="7" type="boolean"/> + <bitfield name="FS_DISABLE" pos="7" type="boolean"/> </reg32> <reg32 offset="0x8802" name="RB_RAS_MSAA_CNTL" usage="rp_blit"> @@ -3536,16 +1357,16 @@ to upconvert to 32b float internally? <bitfield name="MSAA_DISABLE" pos="2" type="boolean"/> </reg32> - <reg32 offset="0x8804" name="RB_SAMPLE_CONFIG" type="a6xx_sample_config" usage="rp_blit"/> - <reg32 offset="0x8805" name="RB_SAMPLE_LOCATION_0" type="a6xx_sample_locations" usage="rp_blit"/> - <reg32 offset="0x8806" name="RB_SAMPLE_LOCATION_1" type="a6xx_sample_locations" usage="rp_blit"/> + <reg32 offset="0x8804" name="RB_MSAA_SAMPLE_POS_CNTL" type="a6xx_msaa_sample_pos_cntl" usage="rp_blit"/> + <reg32 offset="0x8805" name="RB_PROGRAMMABLE_MSAA_POS_0" type="a6xx_programmable_msaa_pos" usage="rp_blit"/> + <reg32 offset="0x8806" name="RB_PROGRAMMABLE_MSAA_POS_1" type="a6xx_programmable_msaa_pos" usage="rp_blit"/> <!-- 0x8807-0x8808 invalid --> <!-- note: maybe not actually called RB_RENDER_CONTROLn (since RB_RENDER_CNTL name comes from kernel and is probably right) --> - <reg32 offset="0x8809" name="RB_RENDER_CONTROL0" usage="rp_blit"> - <!-- see also GRAS_CNTL --> + <reg32 offset="0x8809" name="RB_INTERP_CNTL" usage="rp_blit"> + <!-- see also GRAS_CL_INTERP_CNTL --> <bitfield name="IJ_PERSP_PIXEL" pos="0" type="boolean"/> <bitfield name="IJ_PERSP_CENTROID" pos="1" type="boolean"/> <bitfield name="IJ_PERSP_SAMPLE" pos="2" type="boolean"/> @@ -3555,7 +1376,7 @@ to upconvert to 32b float internally? <bitfield name="COORD_MASK" low="6" high="9" type="hex"/> <bitfield name="UNK10" pos="10" type="boolean"/> </reg32> - <reg32 offset="0x880a" name="RB_RENDER_CONTROL1" usage="rp_blit"> + <reg32 offset="0x880a" name="RB_PS_INPUT_CNTL" usage="rp_blit"> <!-- enable bits for various FS sysvalue regs: --> <bitfield name="SAMPLEMASK" pos="0" type="boolean"/> <bitfield name="POSTDEPTHCOVERAGE" pos="1" type="boolean"/> @@ -3567,16 +1388,16 @@ to upconvert to 32b float internally? <bitfield name="FOVEATION" pos="8" type="boolean"/> </reg32> - <reg32 offset="0x880b" name="RB_FS_OUTPUT_CNTL0" usage="rp_blit"> + <reg32 offset="0x880b" name="RB_PS_OUTPUT_CNTL" usage="rp_blit"> <bitfield name="DUAL_COLOR_IN_ENABLE" pos="0" type="boolean"/> <bitfield name="FRAG_WRITES_Z" pos="1" type="boolean"/> <bitfield name="FRAG_WRITES_SAMPMASK" pos="2" type="boolean"/> <bitfield name="FRAG_WRITES_STENCILREF" pos="3" type="boolean"/> </reg32> - <reg32 offset="0x880c" name="RB_FS_OUTPUT_CNTL1" usage="rp_blit"> + <reg32 offset="0x880c" name="RB_PS_MRT_CNTL" usage="rp_blit"> <bitfield name="MRT" low="0" high="3" type="uint"/> </reg32> - <reg32 offset="0x880d" name="RB_RENDER_COMPONENTS" usage="rp_blit"> + <reg32 offset="0x880d" name="RB_PS_OUTPUT_MASK" usage="rp_blit"> <bitfield name="RT0" low="0" high="3"/> <bitfield name="RT1" low="4" high="7"/> <bitfield name="RT2" low="8" high="11"/> @@ -3608,7 +1429,7 @@ to upconvert to 32b float internally? <bitfield name="SRGB_MRT7" pos="7" type="boolean"/> </reg32> - <reg32 offset="0x8810" name="RB_SAMPLE_CNTL" usage="rp_blit"> + <reg32 offset="0x8810" name="RB_PS_SAMPLEFREQ_CNTL" usage="rp_blit"> <bitfield name="PER_SAMP_MODE" pos="0" type="boolean"/> </reg32> <reg32 offset="0x8811" name="RB_UNKNOWN_8811" low="4" high="6" usage="cmd"/> @@ -3672,18 +1493,18 @@ to upconvert to 32b float internally? <reg32 offset="0x7" name="BASE_GMEM" low="12" high="31" shr="12"/> </array> - <reg32 offset="0x8860" name="RB_BLEND_RED_F32" type="float" usage="rp_blit"/> - <reg32 offset="0x8861" name="RB_BLEND_GREEN_F32" type="float" usage="rp_blit"/> - <reg32 offset="0x8862" name="RB_BLEND_BLUE_F32" type="float" usage="rp_blit"/> - <reg32 offset="0x8863" name="RB_BLEND_ALPHA_F32" type="float" usage="rp_blit"/> - <reg32 offset="0x8864" name="RB_ALPHA_CONTROL" usage="cmd"> + <reg32 offset="0x8860" name="RB_BLEND_CONSTANT_RED_FP32" type="float" usage="rp_blit"/> + <reg32 offset="0x8861" name="RB_BLEND_CONSTANT_GREEN_FP32" type="float" usage="rp_blit"/> + <reg32 offset="0x8862" name="RB_BLEND_CONSTANT_BLUE_FP32" type="float" usage="rp_blit"/> + <reg32 offset="0x8863" name="RB_BLEND_CONSTANT_ALPHA_FP32" type="float" usage="rp_blit"/> + <reg32 offset="0x8864" name="RB_ALPHA_TEST_CNTL" usage="cmd"> <bitfield name="ALPHA_REF" low="0" high="7" type="hex"/> <bitfield name="ALPHA_TEST" pos="8" type="boolean"/> <bitfield name="ALPHA_TEST_FUNC" low="9" high="11" type="adreno_compare_func"/> </reg32> <reg32 offset="0x8865" name="RB_BLEND_CNTL" usage="rp_blit"> <!-- per-mrt enable bit --> - <bitfield name="ENABLE_BLEND" low="0" high="7"/> + <bitfield name="BLEND_READS_DEST" low="0" high="7"/> <bitfield name="INDEPENDENT_BLEND" pos="8" type="boolean"/> <bitfield name="DUAL_COLOR_IN_ENABLE" pos="9" type="boolean"/> <bitfield name="ALPHA_TO_COVERAGE" pos="10" type="boolean"/> @@ -3726,12 +1547,12 @@ to upconvert to 32b float internally? <reg32 offset="0x8873" name="RB_DEPTH_BUFFER_PITCH" low="0" high="13" shr="6" type="uint" usage="rp_blit"/> <reg32 offset="0x8874" name="RB_DEPTH_BUFFER_ARRAY_PITCH" low="0" high="27" shr="6" type="uint" usage="rp_blit"/> <reg64 offset="0x8875" name="RB_DEPTH_BUFFER_BASE" type="waddress" align="64" usage="rp_blit"/> - <reg32 offset="0x8877" name="RB_DEPTH_BUFFER_BASE_GMEM" low="12" high="31" shr="12" usage="rp_blit"/> + <reg32 offset="0x8877" name="RB_DEPTH_GMEM_BASE" low="12" high="31" shr="12" usage="rp_blit"/> - <reg32 offset="0x8878" name="RB_Z_BOUNDS_MIN" type="float" usage="rp_blit"/> - <reg32 offset="0x8879" name="RB_Z_BOUNDS_MAX" type="float" usage="rp_blit"/> + <reg32 offset="0x8878" name="RB_DEPTH_BOUND_MIN" type="float" usage="rp_blit"/> + <reg32 offset="0x8879" name="RB_DEPTH_BOUND_MAX" type="float" usage="rp_blit"/> <!-- 0x887a-0x887f invalid --> - <reg32 offset="0x8880" name="RB_STENCIL_CONTROL" usage="rp_blit"> + <reg32 offset="0x8880" name="RB_STENCIL_CNTL" usage="rp_blit"> <bitfield name="STENCIL_ENABLE" pos="0" type="boolean"/> <bitfield name="STENCIL_ENABLE_BF" pos="1" type="boolean"/> <!-- @@ -3753,11 +1574,11 @@ to upconvert to 32b float internally? <reg32 offset="0x8115" name="GRAS_SU_STENCIL_CNTL" usage="rp_blit"> <bitfield name="STENCIL_ENABLE" pos="0" type="boolean"/> </reg32> - <reg32 offset="0x8881" name="RB_STENCIL_INFO" variants="A6XX" usage="rp_blit"> + <reg32 offset="0x8881" name="RB_STENCIL_BUFFER_INFO" variants="A6XX" usage="rp_blit"> <bitfield name="SEPARATE_STENCIL" pos="0" type="boolean"/> <bitfield name="UNK1" pos="1" type="boolean"/> </reg32> - <reg32 offset="0x8881" name="RB_STENCIL_INFO" variants="A7XX-" usage="rp_blit"> + <reg32 offset="0x8881" name="RB_STENCIL_BUFFER_INFO" variants="A7XX-" usage="rp_blit"> <bitfield name="SEPARATE_STENCIL" pos="0" type="boolean"/> <bitfield name="UNK1" pos="1" type="boolean"/> <bitfield name="TILEMODE" low="2" high="3" type="a6xx_tile_mode"/> @@ -3765,22 +1586,22 @@ to upconvert to 32b float internally? <reg32 offset="0x8882" name="RB_STENCIL_BUFFER_PITCH" low="0" high="11" shr="6" type="uint" usage="rp_blit"/> <reg32 offset="0x8883" name="RB_STENCIL_BUFFER_ARRAY_PITCH" low="0" high="23" shr="6" type="uint" usage="rp_blit"/> <reg64 offset="0x8884" name="RB_STENCIL_BUFFER_BASE" type="waddress" align="64" usage="rp_blit"/> - <reg32 offset="0x8886" name="RB_STENCIL_BUFFER_BASE_GMEM" low="12" high="31" shr="12" usage="rp_blit"/> - <reg32 offset="0x8887" name="RB_STENCILREF" usage="rp_blit"> + <reg32 offset="0x8886" name="RB_STENCIL_GMEM_BASE" low="12" high="31" shr="12" usage="rp_blit"/> + <reg32 offset="0x8887" name="RB_STENCIL_REF_CNTL" usage="rp_blit"> <bitfield name="REF" low="0" high="7"/> <bitfield name="BFREF" low="8" high="15"/> </reg32> - <reg32 offset="0x8888" name="RB_STENCILMASK" usage="rp_blit"> + <reg32 offset="0x8888" name="RB_STENCIL_MASK" usage="rp_blit"> <bitfield name="MASK" low="0" high="7"/> <bitfield name="BFMASK" low="8" high="15"/> </reg32> - <reg32 offset="0x8889" name="RB_STENCILWRMASK" usage="rp_blit"> + <reg32 offset="0x8889" name="RB_STENCIL_WRITE_MASK" usage="rp_blit"> <bitfield name="WRMASK" low="0" high="7"/> <bitfield name="BFWRMASK" low="8" high="15"/> </reg32> <!-- 0x888a-0x888f invalid --> <reg32 offset="0x8890" name="RB_WINDOW_OFFSET" type="a6xx_reg_xy" usage="rp_blit"/> - <reg32 offset="0x8891" name="RB_SAMPLE_COUNT_CONTROL" usage="cmd"> + <reg32 offset="0x8891" name="RB_SAMPLE_COUNTER_CNTL" usage="cmd"> <bitfield name="DISABLE" pos="0" type="boolean"/> <bitfield name="COPY" pos="1" type="boolean"/> </reg32> @@ -3791,27 +1612,27 @@ to upconvert to 32b float internally? <reg32 offset="0x8899" name="RB_UNKNOWN_8899" variants="A7XX-" usage="cmd"/> <!-- 0x8899-0x88bf invalid --> <!-- clamps depth value for depth test/write --> - <reg32 offset="0x88c0" name="RB_Z_CLAMP_MIN" type="float" usage="rp_blit"/> - <reg32 offset="0x88c1" name="RB_Z_CLAMP_MAX" type="float" usage="rp_blit"/> + <reg32 offset="0x88c0" name="RB_VIEWPORT_ZCLAMP_MIN" type="float" usage="rp_blit"/> + <reg32 offset="0x88c1" name="RB_VIEWPORT_ZCLAMP_MAX" type="float" usage="rp_blit"/> <!-- 0x88c2-0x88cf invalid--> - <reg32 offset="0x88d0" name="RB_UNKNOWN_88D0" usage="rp_blit"> + <reg32 offset="0x88d0" name="RB_RESOLVE_CNTL_0" usage="rp_blit"> <bitfield name="UNK0" low="0" high="12"/> <bitfield name="UNK16" low="16" high="26"/> </reg32> - <reg32 offset="0x88d1" name="RB_BLIT_SCISSOR_TL" type="a6xx_reg_xy" usage="rp_blit"/> - <reg32 offset="0x88d2" name="RB_BLIT_SCISSOR_BR" type="a6xx_reg_xy" usage="rp_blit"/> + <reg32 offset="0x88d1" name="RB_RESOLVE_CNTL_1" type="a6xx_reg_xy" usage="rp_blit"/> + <reg32 offset="0x88d2" name="RB_RESOLVE_CNTL_2" type="a6xx_reg_xy" usage="rp_blit"/> <!-- weird to duplicate other regs from same block?? --> - <reg32 offset="0x88d3" name="RB_BIN_CONTROL2" usage="rp_blit"> + <reg32 offset="0x88d3" name="RB_RESOLVE_CNTL_3" usage="rp_blit"> <bitfield name="BINW" low="0" high="5" shr="5" type="uint"/> <bitfield name="BINH" low="8" high="14" shr="4" type="uint"/> </reg32> - <reg32 offset="0x88d4" name="RB_WINDOW_OFFSET2" type="a6xx_reg_xy" usage="rp_blit"/> - <reg32 offset="0x88d5" name="RB_BLIT_GMEM_MSAA_CNTL" usage="rp_blit"> + <reg32 offset="0x88d4" name="RB_RESOLVE_WINDOW_OFFSET" type="a6xx_reg_xy" usage="rp_blit"/> + <reg32 offset="0x88d5" name="RB_RESOLVE_GMEM_BUFFER_INFO" usage="rp_blit"> <bitfield name="SAMPLES" low="3" high="4" type="a3xx_msaa_samples"/> </reg32> - <reg32 offset="0x88d6" name="RB_BLIT_BASE_GMEM" low="12" high="31" shr="12" usage="rp_blit"/> + <reg32 offset="0x88d6" name="RB_RESOLVE_GMEM_BUFFER_BASE" low="12" high="31" shr="12" usage="rp_blit"/> <!-- s/DST_FORMAT/DST_INFO/ probably: --> - <reg32 offset="0x88d7" name="RB_BLIT_DST_INFO" usage="rp_blit"> + <reg32 offset="0x88d7" name="RB_RESOLVE_SYSTEM_BUFFER_INFO" usage="rp_blit"> <bitfield name="TILE_MODE" low="0" high="1" type="a6xx_tile_mode"/> <bitfield name="FLAGS" pos="2" type="boolean"/> <bitfield name="SAMPLES" low="3" high="4" type="a3xx_msaa_samples"/> @@ -3820,25 +1641,31 @@ to upconvert to 32b float internally? <bitfield name="UNK15" pos="15" type="boolean"/> <bitfield name="MUTABLEEN" pos="16" type="boolean" variants="A7XX-"/> </reg32> - <reg64 offset="0x88d8" name="RB_BLIT_DST" type="waddress" align="64" usage="rp_blit"/> - <reg32 offset="0x88da" name="RB_BLIT_DST_PITCH" low="0" high="15" shr="6" type="uint" usage="rp_blit"/> + <reg64 offset="0x88d8" name="RB_RESOLVE_SYSTEM_BUFFER_BASE" type="waddress" align="64" usage="rp_blit"/> + <reg32 offset="0x88da" name="RB_RESOLVE_SYSTEM_BUFFER_PITCH" low="0" high="15" shr="6" type="uint" usage="rp_blit"/> <!-- array-pitch is size of layer --> - <reg32 offset="0x88db" name="RB_BLIT_DST_ARRAY_PITCH" low="0" high="28" shr="6" type="uint" usage="rp_blit"/> - <reg64 offset="0x88dc" name="RB_BLIT_FLAG_DST" type="waddress" align="64" usage="rp_blit"/> - <reg32 offset="0x88de" name="RB_BLIT_FLAG_DST_PITCH" usage="rp_blit"> + <reg32 offset="0x88db" name="RB_RESOLVE_SYSTEM_BUFFER_ARRAY_PITCH" low="0" high="28" shr="6" type="uint" usage="rp_blit"/> + <reg64 offset="0x88dc" name="RB_RESOLVE_SYSTEM_FLAG_BUFFER_BASE" type="waddress" align="64" usage="rp_blit"/> + <reg32 offset="0x88de" name="RB_RESOLVE_SYSTEM_FLAG_BUFFER_PITCH" usage="rp_blit"> <bitfield name="PITCH" low="0" high="10" shr="6" type="uint"/> <bitfield name="ARRAY_PITCH" low="11" high="27" shr="7" type="uint"/> </reg32> - <reg32 offset="0x88df" name="RB_BLIT_CLEAR_COLOR_DW0" usage="rp_blit"/> - <reg32 offset="0x88e0" name="RB_BLIT_CLEAR_COLOR_DW1" usage="rp_blit"/> - <reg32 offset="0x88e1" name="RB_BLIT_CLEAR_COLOR_DW2" usage="rp_blit"/> - <reg32 offset="0x88e2" name="RB_BLIT_CLEAR_COLOR_DW3" usage="rp_blit"/> + <reg32 offset="0x88df" name="RB_RESOLVE_CLEAR_COLOR_DW0" usage="rp_blit"/> + <reg32 offset="0x88e0" name="RB_RESOLVE_CLEAR_COLOR_DW1" usage="rp_blit"/> + <reg32 offset="0x88e1" name="RB_RESOLVE_CLEAR_COLOR_DW2" usage="rp_blit"/> + <reg32 offset="0x88e2" name="RB_RESOLVE_CLEAR_COLOR_DW3" usage="rp_blit"/> + + <enum name="a6xx_blit_event_type"> + <value value="0x0" name="BLIT_EVENT_STORE"/> + <value value="0x1" name="BLIT_EVENT_STORE_AND_CLEAR"/> + <value value="0x2" name="BLIT_EVENT_CLEAR"/> + <value value="0x3" name="BLIT_EVENT_LOAD"/> + </enum> <!-- seems somewhat similar to what we called RB_CLEAR_CNTL on a5xx: --> - <reg32 offset="0x88e3" name="RB_BLIT_INFO" usage="rp_blit"> - <bitfield name="UNK0" pos="0" type="boolean"/> <!-- s8 stencil restore/clear? But also color restore? --> - <bitfield name="GMEM" pos="1" type="boolean"/> <!-- set for restore and clear to gmem? --> + <reg32 offset="0x88e3" name="RB_RESOLVE_OPERATION" usage="rp_blit"> + <bitfield name="TYPE" low="0" high="1" type="a6xx_blit_event_type"/> <bitfield name="SAMPLE_0" pos="2" type="boolean"/> <!-- takes sample 0 instead of averaging --> <bitfield name="DEPTH" pos="3" type="boolean"/> <!-- z16/z32/z24s8/x24x8 clear or resolve? --> <doc> @@ -3853,16 +1680,20 @@ to upconvert to 32b float internally? <!-- set when this is the last resolve on a650+ --> <bitfield name="LAST" low="8" high="9"/> <!-- - a618 GLES: color render target number being resolved for RM6_RESOLVE, 0x8 for depth, 0x9 for separate stencil. - a618 VK: 0x8 for depth RM6_RESOLVE, 0x9 for separate stencil, 0 otherwise. - - We believe this is related to concurrent resolves + a618 GLES: color render target number being resolved for CCU_RESOLVE, 0x8 for depth, 0x9 for separate stencil. + a618 VK: 0x8 for depth CCU_RESOLVE, 0x9 for separate stencil, 0 otherwise. + a7xx VK: 0x8 for depth, 0x9 for separate stencil, 0x0 to 0x7 used for concurrent resolves of color render + targets inside a given resolve group. --> <bitfield name="BUFFER_ID" low="12" high="15"/> </reg32> - <reg32 offset="0x88e4" name="RB_UNKNOWN_88E4" variants="A7XX-" usage="rp_blit"> - <!-- Value conditioned based on predicate, changed before blits --> - <bitfield name="UNK0" pos="0" type="boolean"/> + + <enum name="a7xx_blit_clear_mode"> + <value value="0x0" name="CLEAR_MODE_SYSMEM"/> + <value value="0x1" name="CLEAR_MODE_GMEM"/> + </enum> + <reg32 offset="0x88e4" name="RB_CLEAR_TARGET" variants="A7XX-" usage="rp_blit"> + <bitfield name="CLEAR_MODE" pos="0" type="a7xx_blit_clear_mode"/> </reg32> <enum name="a6xx_ccu_cache_size"> @@ -3871,7 +1702,7 @@ to upconvert to 32b float internally? <value value="0x2" name="CCU_CACHE_SIZE_QUARTER"/> <value value="0x3" name="CCU_CACHE_SIZE_EIGHTH"/> </enum> - <reg32 offset="0x88e5" name="RB_CCU_CNTL2" variants="A7XX-" usage="cmd"> + <reg32 offset="0x88e5" name="RB_CCU_CACHE_CNTL" variants="A7XX-" usage="cmd"> <bitfield name="DEPTH_OFFSET_HI" pos="0" type="hex"/> <bitfield name="COLOR_OFFSET_HI" pos="2" type="hex"/> <bitfield name="DEPTH_CACHE_SIZE" low="10" high="11" type="a6xx_ccu_cache_size"/> @@ -3895,7 +1726,13 @@ to upconvert to 32b float internally? <bitfield name="PITCH" low="0" high="10" shr="6" type="uint"/> <bitfield name="ARRAY_PITCH" low="11" high="23" shr="7" type="uint"/> </reg32> - <reg32 offset="0x88f4" name="RB_UNKNOWN_88F4" low="0" high="2"/> + + <reg32 offset="0x88f4" name="RB_VRS_CONFIG" usage="rp_blit"> + <bitfield name="UNK2" pos="2" type="boolean"/> + <bitfield name="PIPELINE_FSR_ENABLE" pos="4" type="boolean"/> + <bitfield name="ATTACHMENT_FSR_ENABLE" pos="5" type="boolean"/> + <bitfield name="PRIMITIVE_FSR_ENABLE" pos="18" type="boolean"/> + </reg32> <!-- Connected to VK_EXT_fragment_density_map? --> <reg32 offset="0x88f5" name="RB_UNKNOWN_88F5" variants="A7XX-"/> <!-- 0x88f6-0x88ff invalid --> @@ -3906,7 +1743,7 @@ to upconvert to 32b float internally? <bitfield name="UNK8" low="8" high="10"/> <bitfield name="ARRAY_PITCH" low="11" high="27" shr="7" type="uint"/> </reg32> - <array offset="0x8903" name="RB_MRT_FLAG_BUFFER" stride="3" length="8" usage="rp_blit"> + <array offset="0x8903" name="RB_COLOR_FLAG_BUFFER" stride="3" length="8" usage="rp_blit"> <reg64 offset="0" name="ADDR" type="waddress" align="64"/> <reg32 offset="2" name="PITCH"> <bitfield name="PITCH" low="0" high="10" shr="6" type="uint"/> @@ -3915,10 +1752,10 @@ to upconvert to 32b float internally? </array> <!-- 0x891b-0x8926 invalid --> <doc> - RB_SAMPLE_COUNT_ADDR register is used up to (and including) a730. After that + RB_SAMPLE_COUNTER_BASE register is used up to (and including) a730. After that the address is specified through CP_EVENT_WRITE7::WRITE_SAMPLE_COUNT. </doc> - <reg64 offset="0x8927" name="RB_SAMPLE_COUNT_ADDR" type="waddress" align="16" usage="cmd"/> + <reg64 offset="0x8927" name="RB_SAMPLE_COUNTER_BASE" type="waddress" align="16" usage="cmd"/> <!-- 0x8929-0x89ff invalid --> <!-- TODO: there are some registers in the 0x8a00-0x8bff range --> @@ -3932,10 +1769,10 @@ to upconvert to 32b float internally? <reg32 offset="0x8a20" name="RB_UNKNOWN_8A20" variants="A6XX" usage="rp_blit"/> <reg32 offset="0x8a30" name="RB_UNKNOWN_8A30" variants="A6XX" usage="rp_blit"/> - <reg32 offset="0x8c00" name="RB_2D_BLIT_CNTL" type="a6xx_2d_blit_cntl" usage="rp_blit"/> - <reg32 offset="0x8c01" name="RB_2D_UNKNOWN_8C01" low="0" high="31" usage="rp_blit"/> + <reg32 offset="0x8c00" name="RB_A2D_BLT_CNTL" type="a6xx_a2d_bit_cntl" usage="rp_blit"/> + <reg32 offset="0x8c01" name="RB_A2D_PIXEL_CNTL" low="0" high="31" usage="rp_blit"/> - <bitset name="a6xx_2d_src_surf_info" inline="yes"> + <bitset name="a6xx_a2d_src_texture_info" inline="yes"> <bitfield name="COLOR_FORMAT" low="0" high="7" type="a6xx_format"/> <bitfield name="TILE_MODE" low="8" high="9" type="a6xx_tile_mode"/> <bitfield name="COLOR_SWAP" low="10" high="11" type="a3xx_color_swap"/> @@ -3954,7 +1791,7 @@ to upconvert to 32b float internally? <bitfield name="MUTABLEEN" pos="29" type="boolean" variants="A7XX-"/> </bitset> - <bitset name="a6xx_2d_dst_surf_info" inline="yes"> + <bitset name="a6xx_a2d_dest_buffer_info" inline="yes"> <bitfield name="COLOR_FORMAT" low="0" high="7" type="a6xx_format"/> <bitfield name="TILE_MODE" low="8" high="9" type="a6xx_tile_mode"/> <bitfield name="COLOR_SWAP" low="10" high="11" type="a3xx_color_swap"/> @@ -3965,26 +1802,26 @@ to upconvert to 32b float internally? </bitset> <!-- 0x8c02-0x8c16 invalid --> - <reg32 offset="0x8c17" name="RB_2D_DST_INFO" type="a6xx_2d_dst_surf_info" usage="rp_blit"/> - <reg64 offset="0x8c18" name="RB_2D_DST" type="waddress" align="64" usage="rp_blit"/> - <reg32 offset="0x8c1a" name="RB_2D_DST_PITCH" low="0" high="15" shr="6" type="uint" usage="rp_blit"/> + <reg32 offset="0x8c17" name="RB_A2D_DEST_BUFFER_INFO" type="a6xx_a2d_dest_buffer_info" usage="rp_blit"/> + <reg64 offset="0x8c18" name="RB_A2D_DEST_BUFFER_BASE" type="waddress" align="64" usage="rp_blit"/> + <reg32 offset="0x8c1a" name="RB_A2D_DEST_BUFFER_PITCH" low="0" high="15" shr="6" type="uint" usage="rp_blit"/> <!-- this is a guess but seems likely (for NV12/IYUV): --> - <reg64 offset="0x8c1b" name="RB_2D_DST_PLANE1" type="waddress" align="64" usage="rp_blit"/> - <reg32 offset="0x8c1d" name="RB_2D_DST_PLANE_PITCH" low="0" high="15" shr="6" type="uint" usage="rp_blit"/> - <reg64 offset="0x8c1e" name="RB_2D_DST_PLANE2" type="waddress" align="64" usage="rp_blit"/> + <reg64 offset="0x8c1b" name="RB_A2D_DEST_BUFFER_BASE_1" type="waddress" align="64" usage="rp_blit"/> + <reg32 offset="0x8c1d" name="RB_A2D_DEST_BUFFER_PITCH_1" low="0" high="15" shr="6" type="uint" usage="rp_blit"/> + <reg64 offset="0x8c1e" name="RB_A2D_DEST_BUFFER_BASE_2" type="waddress" align="64" usage="rp_blit"/> - <reg64 offset="0x8c20" name="RB_2D_DST_FLAGS" type="waddress" align="64" usage="rp_blit"/> - <reg32 offset="0x8c22" name="RB_2D_DST_FLAGS_PITCH" low="0" high="7" shr="6" type="uint" usage="rp_blit"/> + <reg64 offset="0x8c20" name="RB_A2D_DEST_FLAG_BUFFER_BASE" type="waddress" align="64" usage="rp_blit"/> + <reg32 offset="0x8c22" name="RB_A2D_DEST_FLAG_BUFFER_PITCH" low="0" high="7" shr="6" type="uint" usage="rp_blit"/> <!-- this is a guess but seems likely (for NV12 with UBWC): --> - <reg64 offset="0x8c23" name="RB_2D_DST_FLAGS_PLANE" type="waddress" align="64" usage="rp_blit"/> - <reg32 offset="0x8c25" name="RB_2D_DST_FLAGS_PLANE_PITCH" low="0" high="7" shr="6" type="uint" usage="rp_blit"/> + <reg64 offset="0x8c23" name="RB_A2D_DEST_FLAG_BUFFER_BASE_1" type="waddress" align="64" usage="rp_blit"/> + <reg32 offset="0x8c25" name="RB_A2D_DEST_FLAG_BUFFER_PITCH_1" low="0" high="7" shr="6" type="uint" usage="rp_blit"/> <!-- TODO: 0x8c26-0x8c33 are all full 32-bit registers --> <!-- unlike a5xx, these are per channel values rather than packed --> - <reg32 offset="0x8c2c" name="RB_2D_SRC_SOLID_C0" usage="rp_blit"/> - <reg32 offset="0x8c2d" name="RB_2D_SRC_SOLID_C1" usage="rp_blit"/> - <reg32 offset="0x8c2e" name="RB_2D_SRC_SOLID_C2" usage="rp_blit"/> - <reg32 offset="0x8c2f" name="RB_2D_SRC_SOLID_C3" usage="rp_blit"/> + <reg32 offset="0x8c2c" name="RB_A2D_CLEAR_COLOR_DW0" usage="rp_blit"/> + <reg32 offset="0x8c2d" name="RB_A2D_CLEAR_COLOR_DW1" usage="rp_blit"/> + <reg32 offset="0x8c2e" name="RB_A2D_CLEAR_COLOR_DW2" usage="rp_blit"/> + <reg32 offset="0x8c2f" name="RB_A2D_CLEAR_COLOR_DW3" usage="rp_blit"/> <reg32 offset="0x8c34" name="RB_UNKNOWN_8C34" variants="A7XX-" usage="cmd"/> @@ -3996,7 +1833,7 @@ to upconvert to 32b float internally? <reg32 offset="0x8e04" name="RB_DBG_ECO_CNTL" usage="cmd"/> <!-- TODO: valid mask 0xfffffeff --> <reg32 offset="0x8e05" name="RB_ADDR_MODE_CNTL" pos="0" type="a5xx_address_mode"/> <!-- 0x02080000 in GMEM, zero otherwise? --> - <reg32 offset="0x8e06" name="RB_UNKNOWN_8E06" variants="A7XX-" usage="cmd"/> + <reg32 offset="0x8e06" name="RB_CCU_DBG_ECO_CNTL" variants="A7XX-" usage="cmd"/> <reg32 offset="0x8e07" name="RB_CCU_CNTL" usage="cmd" variants="A6XX"> <bitfield name="GMEM_FAST_CLEAR_DISABLE" pos="0" type="boolean"/> @@ -4017,10 +1854,21 @@ to upconvert to 32b float internally? <bitfield name="COLOR_OFFSET" low="23" high="31" shr="12" type="hex"/> <!--TODO: valid mask 0xfffffc1f --> </reg32> + <enum name="a7xx_concurrent_resolve_mode"> + <value value="0x0" name="CONCURRENT_RESOLVE_MODE_DISABLED"/> + <value value="0x1" name="CONCURRENT_RESOLVE_MODE_1"/> + <value value="0x2" name="CONCURRENT_RESOLVE_MODE_2"/> + </enum> + <enum name="a7xx_concurrent_unresolve_mode"> + <value value="0x0" name="CONCURRENT_UNRESOLVE_MODE_DISABLED"/> + <value value="0x1" name="CONCURRENT_UNRESOLVE_MODE_PARTIAL"/> + <value value="0x3" name="CONCURRENT_UNRESOLVE_MODE_FULL"/> + </enum> <reg32 offset="0x8e07" name="RB_CCU_CNTL" usage="cmd" variants="A7XX-"> <bitfield name="GMEM_FAST_CLEAR_DISABLE" pos="0" type="boolean"/> - <bitfield name="CONCURRENT_RESOLVE" pos="2" type="boolean"/> - <!-- rest of the bits were moved to RB_CCU_CNTL2 --> + <bitfield name="CONCURRENT_RESOLVE_MODE" low="2" high="3" type="a7xx_concurrent_resolve_mode"/> + <bitfield name="CONCURRENT_UNRESOLVE_MODE" low="5" high="6" type="a7xx_concurrent_unresolve_mode"/> + <!-- rest of the bits were moved to RB_CCU_CACHE_CNTL --> </reg32> <reg32 offset="0x8e08" name="RB_NC_MODE_CNTL"> <bitfield name="MODE" pos="0" type="boolean"/> @@ -4046,9 +1894,9 @@ to upconvert to 32b float internally? <reg32 offset="0x8e3d" name="RB_RB_SUB_BLOCK_SEL_CNTL_CD"/> <!-- 0x8e3e-0x8e4f invalid --> <!-- GMEM save/restore for preemption: --> - <reg32 offset="0x8e50" name="RB_CONTEXT_SWITCH_GMEM_SAVE_RESTORE" pos="0" type="boolean"/> + <reg32 offset="0x8e50" name="RB_CONTEXT_SWITCH_GMEM_SAVE_RESTORE_ENABLE" pos="0" type="boolean"/> <!-- address for GMEM save/restore? --> - <reg32 offset="0x8e51" name="RB_UNKNOWN_8E51" type="waddress" align="1"/> + <reg32 offset="0x8e51" name="RB_CONTEXT_SWITCH_GMEM_SAVE_RESTORE_ADDR" type="waddress" align="1"/> <!-- 0x8e53-0x8e7f invalid --> <reg32 offset="0x8e79" name="RB_UNKNOWN_8E79" variants="A7XX-" usage="cmd"/> <!-- 0x8e80-0x8e83 are valid --> @@ -4069,38 +1917,38 @@ to upconvert to 32b float internally? <bitfield name="CLIP_DIST_03_LOC" low="8" high="15" type="uint"/> <bitfield name="CLIP_DIST_47_LOC" low="16" high="23" type="uint"/> </bitset> - <reg32 offset="0x9101" name="VPC_VS_CLIP_CNTL" type="a6xx_vpc_xs_clip_cntl" usage="rp_blit"/> - <reg32 offset="0x9102" name="VPC_GS_CLIP_CNTL" type="a6xx_vpc_xs_clip_cntl" usage="rp_blit"/> - <reg32 offset="0x9103" name="VPC_DS_CLIP_CNTL" type="a6xx_vpc_xs_clip_cntl" usage="rp_blit"/> + <reg32 offset="0x9101" name="VPC_VS_CLIP_CULL_CNTL" type="a6xx_vpc_xs_clip_cntl" usage="rp_blit"/> + <reg32 offset="0x9102" name="VPC_GS_CLIP_CULL_CNTL" type="a6xx_vpc_xs_clip_cntl" usage="rp_blit"/> + <reg32 offset="0x9103" name="VPC_DS_CLIP_CULL_CNTL" type="a6xx_vpc_xs_clip_cntl" usage="rp_blit"/> - <reg32 offset="0x9311" name="VPC_VS_CLIP_CNTL_V2" type="a6xx_vpc_xs_clip_cntl" usage="rp_blit"/> - <reg32 offset="0x9312" name="VPC_GS_CLIP_CNTL_V2" type="a6xx_vpc_xs_clip_cntl" usage="rp_blit"/> - <reg32 offset="0x9313" name="VPC_DS_CLIP_CNTL_V2" type="a6xx_vpc_xs_clip_cntl" usage="rp_blit"/> + <reg32 offset="0x9311" name="VPC_VS_CLIP_CULL_CNTL_V2" type="a6xx_vpc_xs_clip_cntl" usage="rp_blit"/> + <reg32 offset="0x9312" name="VPC_GS_CLIP_CULL_CNTL_V2" type="a6xx_vpc_xs_clip_cntl" usage="rp_blit"/> + <reg32 offset="0x9313" name="VPC_DS_CLIP_CULL_CNTL_V2" type="a6xx_vpc_xs_clip_cntl" usage="rp_blit"/> - <bitset name="a6xx_vpc_xs_layer_cntl" inline="yes"> + <bitset name="a6xx_vpc_xs_siv_cntl" inline="yes"> <bitfield name="LAYERLOC" low="0" high="7" type="uint"/> <bitfield name="VIEWLOC" low="8" high="15" type="uint"/> <bitfield name="SHADINGRATELOC" low="16" high="23" type="uint" variants="A7XX-"/> </bitset> - <reg32 offset="0x9104" name="VPC_VS_LAYER_CNTL" type="a6xx_vpc_xs_layer_cntl" usage="rp_blit"/> - <reg32 offset="0x9105" name="VPC_GS_LAYER_CNTL" type="a6xx_vpc_xs_layer_cntl" usage="rp_blit"/> - <reg32 offset="0x9106" name="VPC_DS_LAYER_CNTL" type="a6xx_vpc_xs_layer_cntl" usage="rp_blit"/> + <reg32 offset="0x9104" name="VPC_VS_SIV_CNTL" type="a6xx_vpc_xs_siv_cntl" usage="rp_blit"/> + <reg32 offset="0x9105" name="VPC_GS_SIV_CNTL" type="a6xx_vpc_xs_siv_cntl" usage="rp_blit"/> + <reg32 offset="0x9106" name="VPC_DS_SIV_CNTL" type="a6xx_vpc_xs_siv_cntl" usage="rp_blit"/> - <reg32 offset="0x9314" name="VPC_VS_LAYER_CNTL_V2" type="a6xx_vpc_xs_layer_cntl" usage="rp_blit"/> - <reg32 offset="0x9315" name="VPC_GS_LAYER_CNTL_V2" type="a6xx_vpc_xs_layer_cntl" usage="rp_blit"/> - <reg32 offset="0x9316" name="VPC_DS_LAYER_CNTL_V2" type="a6xx_vpc_xs_layer_cntl" usage="rp_blit"/> + <reg32 offset="0x9314" name="VPC_VS_SIV_CNTL_V2" type="a6xx_vpc_xs_siv_cntl" usage="rp_blit"/> + <reg32 offset="0x9315" name="VPC_GS_SIV_CNTL_V2" type="a6xx_vpc_xs_siv_cntl" usage="rp_blit"/> + <reg32 offset="0x9316" name="VPC_DS_SIV_CNTL_V2" type="a6xx_vpc_xs_siv_cntl" usage="rp_blit"/> <reg32 offset="0x9107" name="VPC_UNKNOWN_9107" variants="A6XX" usage="rp_blit"> - <!-- this mirrors PC_RASTER_CNTL::DISCARD, although it seems it's unused --> + <!-- this mirrors VPC_RAST_STREAM_CNTL::DISCARD, although it seems it's unused --> <bitfield name="RASTER_DISCARD" pos="0" type="boolean"/> <bitfield name="UNK2" pos="2" type="boolean"/> </reg32> - <reg32 offset="0x9108" name="VPC_POLYGON_MODE" usage="rp_blit"> + <reg32 offset="0x9108" name="VPC_RAST_CNTL" usage="rp_blit"> <bitfield name="MODE" low="0" high="1" type="a6xx_polygon_mode"/> </reg32> - <bitset name="a6xx_primitive_cntl_0" inline="yes"> + <bitset name="a6xx_pc_cntl" inline="yes"> <bitfield name="PRIMITIVE_RESTART" pos="0" type="boolean"/> <bitfield name="PROVOKING_VTX_LAST" pos="1" type="boolean"/> <bitfield name="D3D_VERTEX_ORDERING" pos="2" type="boolean"> @@ -4113,7 +1961,7 @@ to upconvert to 32b float internally? <bitfield name="UNK3" pos="3" type="boolean"/> </bitset> - <bitset name="a6xx_primitive_cntl_5" inline="yes"> + <bitset name="a6xx_gs_param_0" inline="yes"> <doc> geometry shader </doc> @@ -4125,7 +1973,7 @@ to upconvert to 32b float internally? <bitfield name="UNK18" pos="18"/> </bitset> - <bitset name="a6xx_multiview_cntl" inline="yes"> + <bitset name="a6xx_stereo_rendering_cntl" inline="yes"> <bitfield name="ENABLE" pos="0" type="boolean"/> <bitfield name="DISABLEMULTIPOS" pos="1" type="boolean"> <doc> @@ -4139,10 +1987,10 @@ to upconvert to 32b float internally? <bitfield name="VIEWS" low="2" high="6" type="uint"/> </bitset> - <reg32 offset="0x9109" name="VPC_PRIMITIVE_CNTL_0" type="a6xx_primitive_cntl_0" variants="A7XX-" usage="rp_blit"/> - <reg32 offset="0x910a" name="VPC_PRIMITIVE_CNTL_5" type="a6xx_primitive_cntl_5" variants="A7XX-" usage="rp_blit"/> - <reg32 offset="0x910b" name="VPC_MULTIVIEW_MASK" type="hex" low="0" high="15" variants="A7XX-" usage="rp_blit"/> - <reg32 offset="0x910c" name="VPC_MULTIVIEW_CNTL" type="a6xx_multiview_cntl" variants="A7XX-" usage="rp_blit"/> + <reg32 offset="0x9109" name="VPC_PC_CNTL" type="a6xx_pc_cntl" variants="A7XX-" usage="rp_blit"/> + <reg32 offset="0x910a" name="VPC_GS_PARAM_0" type="a6xx_gs_param_0" variants="A7XX-" usage="rp_blit"/> + <reg32 offset="0x910b" name="VPC_STEREO_RENDERING_VIEWMASK" type="hex" low="0" high="15" variants="A7XX-" usage="rp_blit"/> + <reg32 offset="0x910c" name="VPC_STEREO_RENDERING_CNTL" type="a6xx_stereo_rendering_cntl" variants="A7XX-" usage="rp_blit"/> <enum name="a6xx_varying_interp_mode"> <value value="0" name="INTERP_SMOOTH"/> @@ -4159,11 +2007,11 @@ to upconvert to 32b float internally? </enum> <!-- 0x9109-0x91ff invalid --> - <array offset="0x9200" name="VPC_VARYING_INTERP" stride="1" length="8" usage="rp_blit"> + <array offset="0x9200" name="VPC_VARYING_INTERP_MODE" stride="1" length="8" usage="rp_blit"> <doc>Packed array of a6xx_varying_interp_mode</doc> <reg32 offset="0x0" name="MODE"/> </array> - <array offset="0x9208" name="VPC_VARYING_PS_REPL" stride="1" length="8" usage="rp_blit"> + <array offset="0x9208" name="VPC_VARYING_REPLACE_MODE_0" stride="1" length="8" usage="rp_blit"> <doc>Packed array of a6xx_varying_ps_repl_mode</doc> <reg32 offset="0x0" name="MODE"/> </array> @@ -4172,12 +2020,12 @@ to upconvert to 32b float internally? <reg32 offset="0x9210" name="VPC_UNKNOWN_9210" low="0" high="31" variants="A6XX" usage="cmd"/> <reg32 offset="0x9211" name="VPC_UNKNOWN_9211" low="0" high="31" variants="A6XX" usage="cmd"/> - <array offset="0x9212" name="VPC_VAR" stride="1" length="4" usage="rp_blit"> + <array offset="0x9212" name="VPC_VARYING_LM_TRANSFER_CNTL_0" stride="1" length="4" usage="rp_blit"> <!-- one bit per varying component: --> <reg32 offset="0" name="DISABLE"/> </array> - <reg32 offset="0x9216" name="VPC_SO_CNTL" usage="rp_blit"> + <reg32 offset="0x9216" name="VPC_SO_MAPPING_WPTR" usage="rp_blit"> <!-- Choose which DWORD to write to. There is an array of (4 * 64) DWORD's, dumped in the devcoredump at @@ -4198,7 +2046,7 @@ to upconvert to 32b float internally? When EmitStreamVertex(N) happens, the HW goes to DWORD 64 * N and then "executes" the next 64 DWORD's. - This field is auto-incremented when VPC_SO_PROG is + This field is auto-incremented when VPC_SO_MAPPING_PORT is written to. --> <bitfield name="ADDR" low="0" high="7" type="hex"/> @@ -4206,7 +2054,7 @@ to upconvert to 32b float internally? <bitfield name="RESET" pos="16" type="boolean"/> </reg32> <!-- special register, write multiple times to load SO program (not readable) --> - <reg32 offset="0x9217" name="VPC_SO_PROG" usage="rp_blit"> + <reg32 offset="0x9217" name="VPC_SO_MAPPING_PORT" usage="rp_blit"> <bitfield name="A_BUF" low="0" high="1" type="uint"/> <bitfield name="A_OFF" low="2" high="10" shr="2" type="uint"/> <bitfield name="A_EN" pos="11" type="boolean"/> @@ -4215,7 +2063,7 @@ to upconvert to 32b float internally? <bitfield name="B_EN" pos="23" type="boolean"/> </reg32> - <reg64 offset="0x9218" name="VPC_SO_STREAM_COUNTS" type="waddress" align="32" usage="cmd"/> + <reg64 offset="0x9218" name="VPC_SO_QUERY_BASE" type="waddress" align="32" usage="cmd"/> <array offset="0x921a" name="VPC_SO" stride="7" length="4" usage="cmd"> <reg64 offset="0" name="BUFFER_BASE" type="waddress" align="32"/> @@ -4225,14 +2073,14 @@ to upconvert to 32b float internally? <reg64 offset="5" name="FLUSH_BASE" type="waddress" align="32"/> </array> - <reg32 offset="0x9236" name="VPC_POINT_COORD_INVERT" usage="cmd"> + <reg32 offset="0x9236" name="VPC_REPLACE_MODE_CNTL" usage="cmd"> <bitfield name="INVERT" pos="0" type="boolean"/> </reg32> <!-- 0x9237-0x92ff invalid --> <!-- always 0x0 ? --> <reg32 offset="0x9300" name="VPC_UNKNOWN_9300" low="0" high="2" usage="cmd"/> - <bitset name="a6xx_vpc_xs_pack" inline="yes"> + <bitset name="a6xx_vpc_xs_cntl" inline="yes"> <doc> num of varyings plus four for gl_Position (plus one if gl_PointSize) plus # of transform-feedback (streamout) varyings if using the @@ -4249,11 +2097,11 @@ to upconvert to 32b float internally? </doc> </bitfield> </bitset> - <reg32 offset="0x9301" name="VPC_VS_PACK" type="a6xx_vpc_xs_pack" usage="rp_blit"/> - <reg32 offset="0x9302" name="VPC_GS_PACK" type="a6xx_vpc_xs_pack" usage="rp_blit"/> - <reg32 offset="0x9303" name="VPC_DS_PACK" type="a6xx_vpc_xs_pack" usage="rp_blit"/> + <reg32 offset="0x9301" name="VPC_VS_CNTL" type="a6xx_vpc_xs_cntl" usage="rp_blit"/> + <reg32 offset="0x9302" name="VPC_GS_CNTL" type="a6xx_vpc_xs_cntl" usage="rp_blit"/> + <reg32 offset="0x9303" name="VPC_DS_CNTL" type="a6xx_vpc_xs_cntl" usage="rp_blit"/> - <reg32 offset="0x9304" name="VPC_CNTL_0" usage="rp_blit"> + <reg32 offset="0x9304" name="VPC_PS_CNTL" usage="rp_blit"> <bitfield name="NUMNONPOSVAR" low="0" high="7" type="uint"/> <!-- for fixed-function (i.e. no GS) gl_PrimitiveID in FS --> <bitfield name="PRIMIDLOC" low="8" high="15" type="uint"/> @@ -4272,7 +2120,7 @@ to upconvert to 32b float internally? </bitfield> </reg32> - <reg32 offset="0x9305" name="VPC_SO_STREAM_CNTL" usage="rp_blit"> + <reg32 offset="0x9305" name="VPC_SO_CNTL" usage="rp_blit"> <!-- It's offset by 1, and 0 means "disabled" --> @@ -4282,19 +2130,19 @@ to upconvert to 32b float internally? <bitfield name="BUF3_STREAM" low="9" high="11" type="uint"/> <bitfield name="STREAM_ENABLE" low="15" high="18" type="hex"/> </reg32> - <reg32 offset="0x9306" name="VPC_SO_DISABLE" usage="rp_blit"> + <reg32 offset="0x9306" name="VPC_SO_OVERRIDE" usage="rp_blit"> <bitfield name="DISABLE" pos="0" type="boolean"/> </reg32> - <reg32 offset="0x9307" name="VPC_POLYGON_MODE2" variants="A7XX-" usage="rp_blit"> + <reg32 offset="0x9307" name="VPC_PS_RAST_CNTL" variants="A6XX-" usage="rp_blit"> <!-- A702 + A7xx --> <bitfield name="MODE" low="0" high="1" type="a6xx_polygon_mode"/> </reg32> - <reg32 offset="0x9308" name="VPC_ATTR_BUF_SIZE_GMEM" variants="A7XX-" usage="rp_blit"> + <reg32 offset="0x9308" name="VPC_ATTR_BUF_GMEM_SIZE" variants="A7XX-" usage="rp_blit"> <bitfield name="SIZE_GMEM" low="0" high="31"/> </reg32> - <reg32 offset="0x9309" name="VPC_ATTR_BUF_BASE_GMEM" variants="A7XX-" usage="rp_blit"> + <reg32 offset="0x9309" name="VPC_ATTR_BUF_GMEM_BASE" variants="A7XX-" usage="rp_blit"> <bitfield name="BASE_GMEM" low="0" high="31"/> </reg32> - <reg32 offset="0x9b09" name="PC_ATTR_BUF_SIZE_GMEM" variants="A7XX-" usage="rp_blit"> + <reg32 offset="0x9b09" name="PC_ATTR_BUF_GMEM_SIZE" variants="A7XX-" usage="rp_blit"> <bitfield name="SIZE_GMEM" low="0" high="31"/> </reg32> @@ -4311,15 +2159,15 @@ to upconvert to 32b float internally? <!-- TODO: regs from 0x9624-0x963a --> <!-- 0x963b-0x97ff invalid --> - <reg32 offset="0x9800" name="PC_TESS_NUM_VERTEX" low="0" high="5" type="uint" usage="rp_blit"/> + <reg32 offset="0x9800" name="PC_HS_PARAM_0" low="0" high="5" type="uint" usage="rp_blit"/> <!-- always 0x0 ? --> - <reg32 offset="0x9801" name="PC_HS_INPUT_SIZE" usage="rp_blit"> + <reg32 offset="0x9801" name="PC_HS_PARAM_1" usage="rp_blit"> <bitfield name="SIZE" low="0" high="10" type="uint"/> <bitfield name="UNK13" pos="13"/> </reg32> - <reg32 offset="0x9802" name="PC_TESS_CNTL" usage="rp_blit"> + <reg32 offset="0x9802" name="PC_DS_PARAM" usage="rp_blit"> <bitfield name="SPACING" low="0" high="1" type="a6xx_tess_spacing"/> <bitfield name="OUTPUT" low="2" high="3" type="a6xx_tess_output"/> </reg32> @@ -4334,7 +2182,7 @@ to upconvert to 32b float internally? </reg32> <!-- New in a6xx gen3+ --> - <reg32 offset="0x9808" name="PC_SO_STREAM_CNTL" usage="rp_blit"> + <reg32 offset="0x9808" name="PC_DGEN_SO_CNTL" usage="rp_blit"> <bitfield name="STREAM_ENABLE" low="15" high="18" type="hex"/> </reg32> @@ -4344,15 +2192,15 @@ to upconvert to 32b float internally? <!-- 0x980b-0x983f invalid --> <!-- 0x9840 - 0x9842 are not readable --> - <reg32 offset="0x9840" name="PC_DRAW_CMD"> + <reg32 offset="0x9840" name="PC_DRAW_INITIATOR"> <bitfield name="STATE_ID" low="0" high="7"/> </reg32> - <reg32 offset="0x9841" name="PC_DISPATCH_CMD"> + <reg32 offset="0x9841" name="PC_KERNEL_INITIATOR"> <bitfield name="STATE_ID" low="0" high="7"/> </reg32> - <reg32 offset="0x9842" name="PC_EVENT_CMD"> + <reg32 offset="0x9842" name="PC_EVENT_INITIATOR"> <!-- I think only the low bit is actually used? --> <bitfield name="STATE_ID" low="16" high="23"/> <bitfield name="EVENT" low="0" high="6" type="vgt_event_type"/> @@ -4367,27 +2215,27 @@ to upconvert to 32b float internally? <!-- 0x9843-0x997f invalid --> - <reg32 offset="0x9981" name="PC_POLYGON_MODE" variants="A6XX" usage="rp_blit"> + <reg32 offset="0x9981" name="PC_DGEN_RAST_CNTL" variants="A6XX" usage="rp_blit"> <bitfield name="MODE" low="0" high="1" type="a6xx_polygon_mode"/> </reg32> - <reg32 offset="0x9809" name="PC_POLYGON_MODE" variants="A7XX-" usage="rp_blit"> + <reg32 offset="0x9809" name="PC_DGEN_RAST_CNTL" variants="A7XX-" usage="rp_blit"> <bitfield name="MODE" low="0" high="1" type="a6xx_polygon_mode"/> </reg32> - <reg32 offset="0x9980" name="PC_RASTER_CNTL" variants="A6XX" usage="rp_blit"> + <reg32 offset="0x9980" name="VPC_RAST_STREAM_CNTL" variants="A6XX" usage="rp_blit"> <!-- which stream to send to GRAS --> <bitfield name="STREAM" low="0" high="1" type="uint"/> <!-- discard primitives before rasterization --> <bitfield name="DISCARD" pos="2" type="boolean"/> </reg32> - <!-- VPC_RASTER_CNTL --> - <reg32 offset="0x9107" name="PC_RASTER_CNTL" variants="A7XX-" usage="rp_blit"> + <!-- VPC_RAST_STREAM_CNTL --> + <reg32 offset="0x9107" name="VPC_RAST_STREAM_CNTL" variants="A7XX-" usage="rp_blit"> <!-- which stream to send to GRAS --> <bitfield name="STREAM" low="0" high="1" type="uint"/> <!-- discard primitives before rasterization --> <bitfield name="DISCARD" pos="2" type="boolean"/> </reg32> - <reg32 offset="0x9317" name="PC_RASTER_CNTL_V2" variants="A7XX-" usage="rp_blit"> + <reg32 offset="0x9317" name="VPC_RAST_STREAM_CNTL_V2" variants="A7XX-" usage="rp_blit"> <!-- which stream to send to GRAS --> <bitfield name="STREAM" low="0" high="1" type="uint"/> <!-- discard primitives before rasterization --> @@ -4397,17 +2245,17 @@ to upconvert to 32b float internally? <!-- Both are a750+. Probably needed to correctly overlap execution of several draws. --> - <reg32 offset="0x9885" name="PC_TESS_PARAM_SIZE" variants="A7XX-" usage="cmd"/> + <reg32 offset="0x9885" name="PC_HS_BUFFER_SIZE" variants="A7XX-" usage="cmd"/> <!-- Blob adds a bit more space {0x10, 0x20, 0x30, 0x40} bytes, but the meaning of this additional space is not known. --> - <reg32 offset="0x9886" name="PC_TESS_FACTOR_SIZE" variants="A7XX-" usage="cmd"/> + <reg32 offset="0x9886" name="PC_TF_BUFFER_SIZE" variants="A7XX-" usage="cmd"/> <!-- 0x9982-0x9aff invalid --> - <reg32 offset="0x9b00" name="PC_PRIMITIVE_CNTL_0" type="a6xx_primitive_cntl_0" usage="rp_blit"/> + <reg32 offset="0x9b00" name="PC_CNTL" type="a6xx_pc_cntl" usage="rp_blit"/> - <bitset name="a6xx_xs_out_cntl" inline="yes"> + <bitset name="a6xx_pc_xs_cntl" inline="yes"> <doc> num of varyings plus four for gl_Position (plus one if gl_PointSize) plus # of transform-feedback (streamout) varyings if using the @@ -4417,19 +2265,19 @@ to upconvert to 32b float internally? <bitfield name="PSIZE" pos="8" type="boolean"/> <bitfield name="LAYER" pos="9" type="boolean"/> <bitfield name="VIEW" pos="10" type="boolean"/> - <!-- note: PC_VS_OUT_CNTL doesn't have the PRIMITIVE_ID bit --> + <!-- note: PC_VS_CNTL doesn't have the PRIMITIVE_ID bit --> <bitfield name="PRIMITIVE_ID" pos="11" type="boolean"/> <bitfield name="CLIP_MASK" low="16" high="23" type="uint"/> <bitfield name="SHADINGRATE" pos="24" type="boolean" variants="A7XX-"/> </bitset> - <reg32 offset="0x9b01" name="PC_VS_OUT_CNTL" type="a6xx_xs_out_cntl" usage="rp_blit"/> - <reg32 offset="0x9b02" name="PC_GS_OUT_CNTL" type="a6xx_xs_out_cntl" usage="rp_blit"/> + <reg32 offset="0x9b01" name="PC_VS_CNTL" type="a6xx_pc_xs_cntl" usage="rp_blit"/> + <reg32 offset="0x9b02" name="PC_GS_CNTL" type="a6xx_pc_xs_cntl" usage="rp_blit"/> <!-- since HS can't output anything, only PRIMITIVE_ID is valid --> - <reg32 offset="0x9b03" name="PC_HS_OUT_CNTL" type="a6xx_xs_out_cntl" usage="rp_blit"/> - <reg32 offset="0x9b04" name="PC_DS_OUT_CNTL" type="a6xx_xs_out_cntl" usage="rp_blit"/> + <reg32 offset="0x9b03" name="PC_HS_CNTL" type="a6xx_pc_xs_cntl" usage="rp_blit"/> + <reg32 offset="0x9b04" name="PC_DS_CNTL" type="a6xx_pc_xs_cntl" usage="rp_blit"/> - <reg32 offset="0x9b05" name="PC_PRIMITIVE_CNTL_5" type="a6xx_primitive_cntl_5" usage="rp_blit"/> + <reg32 offset="0x9b05" name="PC_GS_PARAM_0" type="a6xx_gs_param_0" usage="rp_blit"/> <reg32 offset="0x9b06" name="PC_PRIMITIVE_CNTL_6" variants="A6XX" usage="rp_blit"> <doc> @@ -4438,9 +2286,9 @@ to upconvert to 32b float internally? <bitfield name="STRIDE_IN_VPC" low="0" high="10" type="uint"/> </reg32> - <reg32 offset="0x9b07" name="PC_MULTIVIEW_CNTL" type="a6xx_multiview_cntl" usage="rp_blit"/> + <reg32 offset="0x9b07" name="PC_STEREO_RENDERING_CNTL" type="a6xx_stereo_rendering_cntl" usage="rp_blit"/> <!-- mask of enabled views, doesn't exist on A630 --> - <reg32 offset="0x9b08" name="PC_MULTIVIEW_MASK" type="hex" low="0" high="15" usage="rp_blit"/> + <reg32 offset="0x9b08" name="PC_STEREO_RENDERING_VIEWMASK" type="hex" low="0" high="15" usage="rp_blit"/> <!-- 0x9b09-0x9bff invalid --> <reg32 offset="0x9c00" name="PC_2D_EVENT_CMD"> <!-- special register (but note first 8 bits can be written/read) --> @@ -4451,31 +2299,31 @@ to upconvert to 32b float internally? <!-- TODO: 0x9e00-0xa000 range incomplete --> <reg32 offset="0x9e00" name="PC_DBG_ECO_CNTL"/> <reg32 offset="0x9e01" name="PC_ADDR_MODE_CNTL" type="a5xx_address_mode"/> - <reg64 offset="0x9e04" name="PC_DRAW_INDX_BASE"/> - <reg32 offset="0x9e06" name="PC_DRAW_FIRST_INDX" type="uint"/> - <reg32 offset="0x9e07" name="PC_DRAW_MAX_INDICES" type="uint"/> - <reg64 offset="0x9e08" name="PC_TESSFACTOR_ADDR" variants="A6XX" type="waddress" align="32" usage="cmd"/> - <reg64 offset="0x9810" name="PC_TESSFACTOR_ADDR" variants="A7XX-" type="waddress" align="32" usage="cmd"/> + <reg64 offset="0x9e04" name="PC_DMA_BASE"/> + <reg32 offset="0x9e06" name="PC_DMA_OFFSET" type="uint"/> + <reg32 offset="0x9e07" name="PC_DMA_SIZE" type="uint"/> + <reg64 offset="0x9e08" name="PC_TESS_BASE" variants="A6XX" type="waddress" align="32" usage="cmd"/> + <reg64 offset="0x9810" name="PC_TESS_BASE" variants="A7XX-" type="waddress" align="32" usage="cmd"/> - <reg32 offset="0x9e0b" name="PC_DRAW_INITIATOR" type="vgt_draw_initiator_a4xx"> + <reg32 offset="0x9e0b" name="PC_DRAWCALL_CNTL" type="vgt_draw_initiator_a4xx"> <doc> Possibly not really "initiating" the draw but the layout is similar to VGT_DRAW_INITIATOR on older gens </doc> </reg32> - <reg32 offset="0x9e0c" name="PC_DRAW_NUM_INSTANCES" type="uint"/> - <reg32 offset="0x9e0d" name="PC_DRAW_NUM_INDICES" type="uint"/> + <reg32 offset="0x9e0c" name="PC_DRAWCALL_INSTANCE_NUM" type="uint"/> + <reg32 offset="0x9e0d" name="PC_DRAWCALL_SIZE" type="uint"/> <!-- These match the contents of CP_SET_BIN_DATA (not written directly) --> - <reg32 offset="0x9e11" name="PC_VSTREAM_CONTROL"> + <reg32 offset="0x9e11" name="PC_VIS_STREAM_CNTL"> <bitfield name="UNK0" low="0" high="15"/> <bitfield name="VSC_SIZE" low="16" high="21" type="uint"/> <bitfield name="VSC_N" low="22" high="26" type="uint"/> </reg32> - <reg64 offset="0x9e12" name="PC_BIN_PRIM_STRM" type="waddress" align="32"/> - <reg64 offset="0x9e14" name="PC_BIN_DRAW_STRM" type="waddress" align="32"/> + <reg64 offset="0x9e12" name="PC_PVIS_STREAM_BIN_BASE" type="waddress" align="32"/> + <reg64 offset="0x9e14" name="PC_DVIS_STREAM_BIN_BASE" type="waddress" align="32"/> - <reg32 offset="0x9e1c" name="PC_VISIBILITY_OVERRIDE"> + <reg32 offset="0x9e1c" name="PC_DRAWCALL_CNTL_OVERRIDE"> <doc>Written by CP_SET_VISIBILITY_OVERRIDE handler</doc> <bitfield name="OVERRIDE" pos="0" type="boolean"/> </reg32> @@ -4488,18 +2336,18 @@ to upconvert to 32b float internally? <!-- always 0x0 --> <reg32 offset="0x9e72" name="PC_UNKNOWN_9E72" usage="cmd"/> - <reg32 offset="0xa000" name="VFD_CONTROL_0" usage="rp_blit"> + <reg32 offset="0xa000" name="VFD_CNTL_0" usage="rp_blit"> <bitfield name="FETCH_CNT" low="0" high="5" type="uint"/> <bitfield name="DECODE_CNT" low="8" high="13" type="uint"/> </reg32> - <reg32 offset="0xa001" name="VFD_CONTROL_1" usage="rp_blit"> + <reg32 offset="0xa001" name="VFD_CNTL_1" usage="rp_blit"> <bitfield name="REGID4VTX" low="0" high="7" type="a3xx_regid"/> <bitfield name="REGID4INST" low="8" high="15" type="a3xx_regid"/> <bitfield name="REGID4PRIMID" low="16" high="23" type="a3xx_regid"/> <!-- only used for VS in non-multi-position-output case --> <bitfield name="REGID4VIEWID" low="24" high="31" type="a3xx_regid"/> </reg32> - <reg32 offset="0xa002" name="VFD_CONTROL_2" usage="rp_blit"> + <reg32 offset="0xa002" name="VFD_CNTL_2" usage="rp_blit"> <bitfield name="REGID_HSRELPATCHID" low="0" high="7" type="a3xx_regid"> <doc> This is the ID of the current patch within the @@ -4512,32 +2360,32 @@ to upconvert to 32b float internally? </bitfield> <bitfield name="REGID_INVOCATIONID" low="8" high="15" type="a3xx_regid"/> </reg32> - <reg32 offset="0xa003" name="VFD_CONTROL_3" usage="rp_blit"> + <reg32 offset="0xa003" name="VFD_CNTL_3" usage="rp_blit"> <bitfield name="REGID_DSPRIMID" low="0" high="7" type="a3xx_regid"/> <bitfield name="REGID_DSRELPATCHID" low="8" high="15" type="a3xx_regid"/> <bitfield name="REGID_TESSX" low="16" high="23" type="a3xx_regid"/> <bitfield name="REGID_TESSY" low="24" high="31" type="a3xx_regid"/> </reg32> - <reg32 offset="0xa004" name="VFD_CONTROL_4" usage="rp_blit"> + <reg32 offset="0xa004" name="VFD_CNTL_4" usage="rp_blit"> <bitfield name="UNK0" low="0" high="7" type="a3xx_regid"/> </reg32> - <reg32 offset="0xa005" name="VFD_CONTROL_5" usage="rp_blit"> + <reg32 offset="0xa005" name="VFD_CNTL_5" usage="rp_blit"> <bitfield name="REGID_GSHEADER" low="0" high="7" type="a3xx_regid"/> <bitfield name="UNK8" low="8" high="15" type="a3xx_regid"/> </reg32> - <reg32 offset="0xa006" name="VFD_CONTROL_6" usage="rp_blit"> + <reg32 offset="0xa006" name="VFD_CNTL_6" usage="rp_blit"> <!-- True if gl_PrimitiveID is read via the FS --> <bitfield name="PRIMID4PSEN" pos="0" type="boolean"/> </reg32> - <reg32 offset="0xa007" name="VFD_MODE_CNTL" usage="cmd"> + <reg32 offset="0xa007" name="VFD_RENDER_MODE" usage="cmd"> <bitfield name="RENDER_MODE" low="0" high="2" type="a6xx_render_mode"/> </reg32> - <reg32 offset="0xa008" name="VFD_MULTIVIEW_CNTL" type="a6xx_multiview_cntl" usage="rp_blit"/> - <reg32 offset="0xa009" name="VFD_ADD_OFFSET" usage="cmd"> + <reg32 offset="0xa008" name="VFD_STEREO_RENDERING_CNTL" type="a6xx_stereo_rendering_cntl" usage="rp_blit"/> + <reg32 offset="0xa009" name="VFD_MODE_CNTL" usage="cmd"> <!-- add VFD_INDEX_OFFSET to REGID4VTX --> <bitfield name="VERTEX" pos="0" type="boolean"/> <!-- add VFD_INSTANCE_START_OFFSET to REGID4INST --> @@ -4546,14 +2394,14 @@ to upconvert to 32b float internally? <reg32 offset="0xa00e" name="VFD_INDEX_OFFSET" usage="rp_blit"/> <reg32 offset="0xa00f" name="VFD_INSTANCE_START_OFFSET" usage="rp_blit"/> - <array offset="0xa010" name="VFD_FETCH" stride="4" length="32" usage="rp_blit"> + <array offset="0xa010" name="VFD_VERTEX_BUFFER" stride="4" length="32" usage="rp_blit"> <reg64 offset="0x0" name="BASE" type="address" align="1"/> <reg32 offset="0x2" name="SIZE" type="uint"/> <reg32 offset="0x3" name="STRIDE" low="0" high="11" type="uint"/> </array> - <array offset="0xa090" name="VFD_DECODE" stride="2" length="32" usage="rp_blit"> + <array offset="0xa090" name="VFD_FETCH_INSTR" stride="2" length="32" usage="rp_blit"> <reg32 offset="0x0" name="INSTR"> - <!-- IDX and byte OFFSET into VFD_FETCH --> + <!-- IDX and byte OFFSET into VFD_VERTEX_BUFFER --> <bitfield name="IDX" low="0" high="4" type="uint"/> <bitfield name="OFFSET" low="5" high="16"/> <bitfield name="INSTANCED" pos="17" type="boolean"/> @@ -4573,7 +2421,7 @@ to upconvert to 32b float internally? <reg32 offset="0xa0f8" name="VFD_POWER_CNTL" low="0" high="2" usage="rp_blit"/> - <reg32 offset="0xa600" name="VFD_UNKNOWN_A600" variants="A7XX-" usage="cmd"/> + <reg32 offset="0xa600" name="VFD_DBG_ECO_CNTL" variants="A7XX-" usage="cmd"/> <reg32 offset="0xa601" name="VFD_ADDR_MODE_CNTL" type="a5xx_address_mode"/> <array offset="0xa610" name="VFD_PERFCTR_VFD_SEL" stride="1" length="8" variants="A6XX"/> @@ -4588,7 +2436,7 @@ to upconvert to 32b float internally? <value value="1" name="THREAD128"/> </enum> - <bitset name="a6xx_sp_xs_ctrl_reg0" inline="yes"> + <bitset name="a6xx_sp_xs_cntl_0" inline="yes"> <!-- if set to SINGLE, only use 1 concurrent wave on each SP --> <bitfield name="THREADMODE" pos="0" type="a3xx_threadmode"/> <!-- @@ -4620,7 +2468,7 @@ to upconvert to 32b float internally? --> <bitfield name="BINDLESS_TEX" pos="0" type="boolean"/> <bitfield name="BINDLESS_SAMP" pos="1" type="boolean"/> - <bitfield name="BINDLESS_IBO" pos="2" type="boolean"/> + <bitfield name="BINDLESS_UAV" pos="2" type="boolean"/> <bitfield name="BINDLESS_UBO" pos="3" type="boolean"/> <bitfield name="ENABLED" pos="8" type="boolean"/> @@ -4630,17 +2478,17 @@ to upconvert to 32b float internally? --> <bitfield name="NTEX" low="9" high="16" type="uint"/> <bitfield name="NSAMP" low="17" high="21" type="uint"/> - <bitfield name="NIBO" low="22" high="28" type="uint"/> + <bitfield name="NUAV" low="22" high="28" type="uint"/> </bitset> - <bitset name="a6xx_sp_xs_prim_cntl" inline="yes"> + <bitset name="a6xx_sp_xs_output_cntl" inline="yes"> <!-- # of VS outputs including pos/psize --> <bitfield name="OUT" low="0" high="5" type="uint"/> <!-- FLAGS_REGID only for GS --> <bitfield name="FLAGS_REGID" low="6" high="13" type="a3xx_regid"/> </bitset> - <reg32 offset="0xa800" name="SP_VS_CTRL_REG0" type="a6xx_sp_xs_ctrl_reg0" usage="rp_blit"> + <reg32 offset="0xa800" name="SP_VS_CNTL_0" type="a6xx_sp_xs_cntl_0" usage="rp_blit"> <!-- This field actually controls all geometry stages. TCS, TES, and GS must have the same mergedregs setting as VS. @@ -4665,10 +2513,10 @@ to upconvert to 32b float internally? </reg32> <!-- bitmask of true/false conditions for VS brac.N instructions, bit N corresponds to brac.N --> - <reg32 offset="0xa801" name="SP_VS_BRANCH_COND" type="hex"/> + <reg32 offset="0xa801" name="SP_VS_BOOLEAN_CF_MASK" type="hex"/> <!-- # of VS outputs including pos/psize --> - <reg32 offset="0xa802" name="SP_VS_PRIMITIVE_CNTL" type="a6xx_sp_xs_prim_cntl" usage="rp_blit"/> - <array offset="0xa803" name="SP_VS_OUT" stride="1" length="16" usage="rp_blit"> + <reg32 offset="0xa802" name="SP_VS_OUTPUT_CNTL" type="a6xx_sp_xs_output_cntl" usage="rp_blit"/> + <array offset="0xa803" name="SP_VS_OUTPUT" stride="1" length="16" usage="rp_blit"> <reg32 offset="0x0" name="REG"> <bitfield name="A_REGID" low="0" high="7" type="a3xx_regid"/> <bitfield name="A_COMPMASK" low="8" high="11" type="hex"/> @@ -4678,12 +2526,12 @@ to upconvert to 32b float internally? </array> <!-- Starting with a5xx, position/psize outputs from shader end up in the - SP_VS_OUT map, with highest OUTLOCn position. (Generally they are + SP_VS_OUTPUT map, with highest OUTLOCn position. (Generally they are the last entries too, except when gl_PointCoord is used, blob inserts an extra varying after, but with a lower OUTLOC position. If present, psize is last, preceded by position. --> - <array offset="0xa813" name="SP_VS_VPC_DST" stride="1" length="8" usage="rp_blit"> + <array offset="0xa813" name="SP_VS_VPC_DEST" stride="1" length="8" usage="rp_blit"> <reg32 offset="0x0" name="REG"> <bitfield name="OUTLOC0" low="0" high="7" type="uint"/> <bitfield name="OUTLOC1" low="8" high="15" type="uint"/> @@ -4752,7 +2600,7 @@ to upconvert to 32b float internally? </bitfield> </bitset> - <bitset name="a6xx_sp_xs_pvt_mem_hw_stack_offset" inline="yes"> + <bitset name="a6xx_sp_xs_pvt_mem_stack_offset" inline="yes"> <doc> This seems to be be the equivalent of HWSTACKOFFSET in a3xx. The ldp/stp offset formula above isn't affected by @@ -4763,18 +2611,18 @@ to upconvert to 32b float internally? <bitfield name="OFFSET" low="0" high="18" shr="11"/> </bitset> - <reg32 offset="0xa81b" name="SP_VS_OBJ_FIRST_EXEC_OFFSET" type="uint" usage="rp_blit"/> - <reg64 offset="0xa81c" name="SP_VS_OBJ_START" type="address" align="32" usage="rp_blit"/> + <reg32 offset="0xa81b" name="SP_VS_PROGRAM_COUNTER_OFFSET" type="uint" usage="rp_blit"/> + <reg64 offset="0xa81c" name="SP_VS_BASE" type="address" align="32" usage="rp_blit"/> <reg32 offset="0xa81e" name="SP_VS_PVT_MEM_PARAM" type="a6xx_sp_xs_pvt_mem_param" usage="rp_blit"/> - <reg64 offset="0xa81f" name="SP_VS_PVT_MEM_ADDR" type="waddress" align="32" usage="rp_blit"/> + <reg64 offset="0xa81f" name="SP_VS_PVT_MEM_BASE" type="waddress" align="32" usage="rp_blit"/> <reg32 offset="0xa821" name="SP_VS_PVT_MEM_SIZE" type="a6xx_sp_xs_pvt_mem_size" usage="rp_blit"/> - <reg32 offset="0xa822" name="SP_VS_TEX_COUNT" low="0" high="7" type="uint" usage="rp_blit"/> + <reg32 offset="0xa822" name="SP_VS_TSIZE" low="0" high="7" type="uint" usage="rp_blit"/> <reg32 offset="0xa823" name="SP_VS_CONFIG" type="a6xx_sp_xs_config" usage="rp_blit"/> - <reg32 offset="0xa824" name="SP_VS_INSTRLEN" low="0" high="27" type="uint" usage="rp_blit"/> - <reg32 offset="0xa825" name="SP_VS_PVT_MEM_HW_STACK_OFFSET" type="a6xx_sp_xs_pvt_mem_hw_stack_offset" usage="rp_blit"/> - <reg32 offset="0xa82d" name="SP_VS_VGPR_CONFIG" variants="A7XX-" usage="cmd"/> + <reg32 offset="0xa824" name="SP_VS_INSTR_SIZE" low="0" high="27" type="uint" usage="rp_blit"/> + <reg32 offset="0xa825" name="SP_VS_PVT_MEM_STACK_OFFSET" type="a6xx_sp_xs_pvt_mem_stack_offset" usage="rp_blit"/> + <reg32 offset="0xa82d" name="SP_VS_VGS_CNTL" variants="A7XX-" usage="cmd"/> - <reg32 offset="0xa830" name="SP_HS_CTRL_REG0" type="a6xx_sp_xs_ctrl_reg0" usage="rp_blit"> + <reg32 offset="0xa830" name="SP_HS_CNTL_0" type="a6xx_sp_xs_cntl_0" usage="rp_blit"> <!-- There is no mergedregs bit, that comes from the VS. --> <bitfield name="EARLYPREAMBLE" pos="20" type="boolean"/> </reg32> @@ -4782,32 +2630,32 @@ to upconvert to 32b float internally? Total size of local storage in dwords divided by the wave size. The maximum value is 64. With the wave size being always 64 for HS, the maximum size of local storage should be: - 64 (wavesize) * 64 (SP_HS_WAVE_INPUT_SIZE) * 4 = 16k + 64 (wavesize) * 64 (SP_HS_CNTL_1) * 4 = 16k --> - <reg32 offset="0xa831" name="SP_HS_WAVE_INPUT_SIZE" low="0" high="7" type="uint" usage="rp_blit"/> - <reg32 offset="0xa832" name="SP_HS_BRANCH_COND" type="hex" usage="rp_blit"/> + <reg32 offset="0xa831" name="SP_HS_CNTL_1" low="0" high="7" type="uint" usage="rp_blit"/> + <reg32 offset="0xa832" name="SP_HS_BOOLEAN_CF_MASK" type="hex" usage="rp_blit"/> <!-- TODO: exact same layout as 0xa81b-0xa825 --> - <reg32 offset="0xa833" name="SP_HS_OBJ_FIRST_EXEC_OFFSET" type="uint" usage="rp_blit"/> - <reg64 offset="0xa834" name="SP_HS_OBJ_START" type="address" align="32" usage="rp_blit"/> + <reg32 offset="0xa833" name="SP_HS_PROGRAM_COUNTER_OFFSET" type="uint" usage="rp_blit"/> + <reg64 offset="0xa834" name="SP_HS_BASE" type="address" align="32" usage="rp_blit"/> <reg32 offset="0xa836" name="SP_HS_PVT_MEM_PARAM" type="a6xx_sp_xs_pvt_mem_param" usage="rp_blit"/> - <reg64 offset="0xa837" name="SP_HS_PVT_MEM_ADDR" type="waddress" align="32" usage="rp_blit"/> + <reg64 offset="0xa837" name="SP_HS_PVT_MEM_BASE" type="waddress" align="32" usage="rp_blit"/> <reg32 offset="0xa839" name="SP_HS_PVT_MEM_SIZE" type="a6xx_sp_xs_pvt_mem_size" usage="rp_blit"/> - <reg32 offset="0xa83a" name="SP_HS_TEX_COUNT" low="0" high="7" type="uint" usage="rp_blit"/> + <reg32 offset="0xa83a" name="SP_HS_TSIZE" low="0" high="7" type="uint" usage="rp_blit"/> <reg32 offset="0xa83b" name="SP_HS_CONFIG" type="a6xx_sp_xs_config" usage="rp_blit"/> - <reg32 offset="0xa83c" name="SP_HS_INSTRLEN" low="0" high="27" type="uint" usage="rp_blit"/> - <reg32 offset="0xa83d" name="SP_HS_PVT_MEM_HW_STACK_OFFSET" type="a6xx_sp_xs_pvt_mem_hw_stack_offset" usage="rp_blit"/> - <reg32 offset="0xa82f" name="SP_HS_VGPR_CONFIG" variants="A7XX-" usage="cmd"/> + <reg32 offset="0xa83c" name="SP_HS_INSTR_SIZE" low="0" high="27" type="uint" usage="rp_blit"/> + <reg32 offset="0xa83d" name="SP_HS_PVT_MEM_STACK_OFFSET" type="a6xx_sp_xs_pvt_mem_stack_offset" usage="rp_blit"/> + <reg32 offset="0xa82f" name="SP_HS_VGS_CNTL" variants="A7XX-" usage="cmd"/> - <reg32 offset="0xa840" name="SP_DS_CTRL_REG0" type="a6xx_sp_xs_ctrl_reg0" usage="rp_blit"> + <reg32 offset="0xa840" name="SP_DS_CNTL_0" type="a6xx_sp_xs_cntl_0" usage="rp_blit"> <!-- There is no mergedregs bit, that comes from the VS. --> <bitfield name="EARLYPREAMBLE" pos="20" type="boolean"/> </reg32> - <reg32 offset="0xa841" name="SP_DS_BRANCH_COND" type="hex"/> + <reg32 offset="0xa841" name="SP_DS_BOOLEAN_CF_MASK" type="hex"/> <!-- TODO: exact same layout as 0xa802-0xa81a --> - <reg32 offset="0xa842" name="SP_DS_PRIMITIVE_CNTL" type="a6xx_sp_xs_prim_cntl" usage="rp_blit"/> - <array offset="0xa843" name="SP_DS_OUT" stride="1" length="16" usage="rp_blit"> + <reg32 offset="0xa842" name="SP_DS_OUTPUT_CNTL" type="a6xx_sp_xs_output_cntl" usage="rp_blit"/> + <array offset="0xa843" name="SP_DS_OUTPUT" stride="1" length="16" usage="rp_blit"> <reg32 offset="0x0" name="REG"> <bitfield name="A_REGID" low="0" high="7" type="a3xx_regid"/> <bitfield name="A_COMPMASK" low="8" high="11" type="hex"/> @@ -4815,7 +2663,7 @@ to upconvert to 32b float internally? <bitfield name="B_COMPMASK" low="24" high="27" type="hex"/> </reg32> </array> - <array offset="0xa853" name="SP_DS_VPC_DST" stride="1" length="8" usage="rp_blit"> + <array offset="0xa853" name="SP_DS_VPC_DEST" stride="1" length="8" usage="rp_blit"> <reg32 offset="0x0" name="REG"> <bitfield name="OUTLOC0" low="0" high="7" type="uint"/> <bitfield name="OUTLOC1" low="8" high="15" type="uint"/> @@ -4825,22 +2673,22 @@ to upconvert to 32b float internally? </array> <!-- TODO: exact same layout as 0xa81b-0xa825 --> - <reg32 offset="0xa85b" name="SP_DS_OBJ_FIRST_EXEC_OFFSET" type="uint" usage="rp_blit"/> - <reg64 offset="0xa85c" name="SP_DS_OBJ_START" type="address" align="32" usage="rp_blit"/> + <reg32 offset="0xa85b" name="SP_DS_PROGRAM_COUNTER_OFFSET" type="uint" usage="rp_blit"/> + <reg64 offset="0xa85c" name="SP_DS_BASE" type="address" align="32" usage="rp_blit"/> <reg32 offset="0xa85e" name="SP_DS_PVT_MEM_PARAM" type="a6xx_sp_xs_pvt_mem_param" usage="rp_blit"/> - <reg64 offset="0xa85f" name="SP_DS_PVT_MEM_ADDR" type="waddress" align="32" usage="rp_blit"/> + <reg64 offset="0xa85f" name="SP_DS_PVT_MEM_BASE" type="waddress" align="32" usage="rp_blit"/> <reg32 offset="0xa861" name="SP_DS_PVT_MEM_SIZE" type="a6xx_sp_xs_pvt_mem_size" usage="rp_blit"/> - <reg32 offset="0xa862" name="SP_DS_TEX_COUNT" low="0" high="7" type="uint" usage="rp_blit"/> + <reg32 offset="0xa862" name="SP_DS_TSIZE" low="0" high="7" type="uint" usage="rp_blit"/> <reg32 offset="0xa863" name="SP_DS_CONFIG" type="a6xx_sp_xs_config" usage="rp_blit"/> - <reg32 offset="0xa864" name="SP_DS_INSTRLEN" low="0" high="27" type="uint" usage="rp_blit"/> - <reg32 offset="0xa865" name="SP_DS_PVT_MEM_HW_STACK_OFFSET" type="a6xx_sp_xs_pvt_mem_hw_stack_offset" usage="rp_blit"/> - <reg32 offset="0xa868" name="SP_DS_VGPR_CONFIG" variants="A7XX-" usage="cmd"/> + <reg32 offset="0xa864" name="SP_DS_INSTR_SIZE" low="0" high="27" type="uint" usage="rp_blit"/> + <reg32 offset="0xa865" name="SP_DS_PVT_MEM_STACK_OFFSET" type="a6xx_sp_xs_pvt_mem_stack_offset" usage="rp_blit"/> + <reg32 offset="0xa868" name="SP_DS_VGS_CNTL" variants="A7XX-" usage="cmd"/> - <reg32 offset="0xa870" name="SP_GS_CTRL_REG0" type="a6xx_sp_xs_ctrl_reg0" usage="rp_blit"> + <reg32 offset="0xa870" name="SP_GS_CNTL_0" type="a6xx_sp_xs_cntl_0" usage="rp_blit"> <!-- There is no mergedregs bit, that comes from the VS. --> <bitfield name="EARLYPREAMBLE" pos="20" type="boolean"/> </reg32> - <reg32 offset="0xa871" name="SP_GS_PRIM_SIZE" low="0" high="7" type="uint" usage="rp_blit"> + <reg32 offset="0xa871" name="SP_GS_CNTL_1" low="0" high="7" type="uint" usage="rp_blit"> <doc> Normally the size of the output of the last stage in dwords. It should be programmed as follows: @@ -4854,11 +2702,11 @@ to upconvert to 32b float internally? doesn't matter in practice. </doc> </reg32> - <reg32 offset="0xa872" name="SP_GS_BRANCH_COND" type="hex" usage="rp_blit"/> + <reg32 offset="0xa872" name="SP_GS_BOOLEAN_CF_MASK" type="hex" usage="rp_blit"/> <!-- TODO: exact same layout as 0xa802-0xa81a --> - <reg32 offset="0xa873" name="SP_GS_PRIMITIVE_CNTL" type="a6xx_sp_xs_prim_cntl" usage="rp_blit"/> - <array offset="0xa874" name="SP_GS_OUT" stride="1" length="16" usage="rp_blit"> + <reg32 offset="0xa873" name="SP_GS_OUTPUT_CNTL" type="a6xx_sp_xs_output_cntl" usage="rp_blit"/> + <array offset="0xa874" name="SP_GS_OUTPUT" stride="1" length="16" usage="rp_blit"> <reg32 offset="0x0" name="REG"> <bitfield name="A_REGID" low="0" high="7" type="a3xx_regid"/> <bitfield name="A_COMPMASK" low="8" high="11" type="hex"/> @@ -4867,7 +2715,7 @@ to upconvert to 32b float internally? </reg32> </array> - <array offset="0xa884" name="SP_GS_VPC_DST" stride="1" length="8" usage="rp_blit"> + <array offset="0xa884" name="SP_GS_VPC_DEST" stride="1" length="8" usage="rp_blit"> <reg32 offset="0x0" name="REG"> <bitfield name="OUTLOC0" low="0" high="7" type="uint"/> <bitfield name="OUTLOC1" low="8" high="15" type="uint"/> @@ -4877,29 +2725,29 @@ to upconvert to 32b float internally? </array> <!-- TODO: exact same layout as 0xa81b-0xa825 --> - <reg32 offset="0xa88c" name="SP_GS_OBJ_FIRST_EXEC_OFFSET" type="uint" usage="rp_blit"/> - <reg64 offset="0xa88d" name="SP_GS_OBJ_START" type="address" align="32" usage="rp_blit"/> + <reg32 offset="0xa88c" name="SP_GS_PROGRAM_COUNTER_OFFSET" type="uint" usage="rp_blit"/> + <reg64 offset="0xa88d" name="SP_GS_BASE" type="address" align="32" usage="rp_blit"/> <reg32 offset="0xa88f" name="SP_GS_PVT_MEM_PARAM" type="a6xx_sp_xs_pvt_mem_param" usage="rp_blit"/> - <reg64 offset="0xa890" name="SP_GS_PVT_MEM_ADDR" type="waddress" align="32" usage="rp_blit"/> + <reg64 offset="0xa890" name="SP_GS_PVT_MEM_BASE" type="waddress" align="32" usage="rp_blit"/> <reg32 offset="0xa892" name="SP_GS_PVT_MEM_SIZE" type="a6xx_sp_xs_pvt_mem_size" usage="rp_blit"/> - <reg32 offset="0xa893" name="SP_GS_TEX_COUNT" low="0" high="7" type="uint" usage="rp_blit"/> + <reg32 offset="0xa893" name="SP_GS_TSIZE" low="0" high="7" type="uint" usage="rp_blit"/> <reg32 offset="0xa894" name="SP_GS_CONFIG" type="a6xx_sp_xs_config" usage="rp_blit"/> - <reg32 offset="0xa895" name="SP_GS_INSTRLEN" low="0" high="27" type="uint" usage="rp_blit"/> - <reg32 offset="0xa896" name="SP_GS_PVT_MEM_HW_STACK_OFFSET" type="a6xx_sp_xs_pvt_mem_hw_stack_offset" usage="rp_blit"/> - <reg32 offset="0xa899" name="SP_GS_VGPR_CONFIG" variants="A7XX-" usage="cmd"/> - - <reg64 offset="0xa8a0" name="SP_VS_TEX_SAMP" type="address" align="16" usage="cmd"/> - <reg64 offset="0xa8a2" name="SP_HS_TEX_SAMP" type="address" align="16" usage="cmd"/> - <reg64 offset="0xa8a4" name="SP_DS_TEX_SAMP" type="address" align="16" usage="cmd"/> - <reg64 offset="0xa8a6" name="SP_GS_TEX_SAMP" type="address" align="16" usage="cmd"/> - <reg64 offset="0xa8a8" name="SP_VS_TEX_CONST" type="address" align="64" usage="cmd"/> - <reg64 offset="0xa8aa" name="SP_HS_TEX_CONST" type="address" align="64" usage="cmd"/> - <reg64 offset="0xa8ac" name="SP_DS_TEX_CONST" type="address" align="64" usage="cmd"/> - <reg64 offset="0xa8ae" name="SP_GS_TEX_CONST" type="address" align="64" usage="cmd"/> + <reg32 offset="0xa895" name="SP_GS_INSTR_SIZE" low="0" high="27" type="uint" usage="rp_blit"/> + <reg32 offset="0xa896" name="SP_GS_PVT_MEM_STACK_OFFSET" type="a6xx_sp_xs_pvt_mem_stack_offset" usage="rp_blit"/> + <reg32 offset="0xa899" name="SP_GS_VGS_CNTL" variants="A7XX-" usage="cmd"/> + + <reg64 offset="0xa8a0" name="SP_VS_SAMPLER_BASE" type="address" align="16" usage="cmd"/> + <reg64 offset="0xa8a2" name="SP_HS_SAMPLER_BASE" type="address" align="16" usage="cmd"/> + <reg64 offset="0xa8a4" name="SP_DS_SAMPLER_BASE" type="address" align="16" usage="cmd"/> + <reg64 offset="0xa8a6" name="SP_GS_SAMPLER_BASE" type="address" align="16" usage="cmd"/> + <reg64 offset="0xa8a8" name="SP_VS_TEXMEMOBJ_BASE" type="address" align="64" usage="cmd"/> + <reg64 offset="0xa8aa" name="SP_HS_TEXMEMOBJ_BASE" type="address" align="64" usage="cmd"/> + <reg64 offset="0xa8ac" name="SP_DS_TEXMEMOBJ_BASE" type="address" align="64" usage="cmd"/> + <reg64 offset="0xa8ae" name="SP_GS_TEXMEMOBJ_BASE" type="address" align="64" usage="cmd"/> <!-- TODO: 4 unknown bool registers 0xa8c0-0xa8c3 --> - <reg32 offset="0xa980" name="SP_FS_CTRL_REG0" type="a6xx_sp_xs_ctrl_reg0" usage="rp_blit"> + <reg32 offset="0xa980" name="SP_PS_CNTL_0" type="a6xx_sp_xs_cntl_0" usage="rp_blit"> <bitfield name="THREADSIZE" pos="20" type="a6xx_threadsize"/> <bitfield name="UNK21" pos="21" type="boolean"/> <bitfield name="VARYING" pos="22" type="boolean"/> @@ -4909,8 +2757,7 @@ to upconvert to 32b float internally? fine derivatives and quad subgroup ops. </doc> </bitfield> - <!-- note: vk blob uses bit24 --> - <bitfield name="UNK24" pos="24" type="boolean"/> + <bitfield name="INOUTREGOVERLAP" pos="24" type="boolean"/> <bitfield name="UNK25" pos="25" type="boolean"/> <bitfield name="PIXLODENABLE" pos="26" type="boolean"> <doc> @@ -4923,12 +2770,12 @@ to upconvert to 32b float internally? <bitfield name="EARLYPREAMBLE" pos="28" type="boolean"/> <bitfield name="MERGEDREGS" pos="31" type="boolean"/> </reg32> - <reg32 offset="0xa981" name="SP_FS_BRANCH_COND" type="hex"/> - <reg32 offset="0xa982" name="SP_FS_OBJ_FIRST_EXEC_OFFSET" type="uint" usage="rp_blit"/> - <reg64 offset="0xa983" name="SP_FS_OBJ_START" type="address" align="32" usage="rp_blit"/> - <reg32 offset="0xa985" name="SP_FS_PVT_MEM_PARAM" type="a6xx_sp_xs_pvt_mem_param" usage="rp_blit"/> - <reg64 offset="0xa986" name="SP_FS_PVT_MEM_ADDR" type="waddress" align="32" usage="rp_blit"/> - <reg32 offset="0xa988" name="SP_FS_PVT_MEM_SIZE" type="a6xx_sp_xs_pvt_mem_size" usage="rp_blit"/> + <reg32 offset="0xa981" name="SP_PS_BOOLEAN_CF_MASK" type="hex"/> + <reg32 offset="0xa982" name="SP_PS_PROGRAM_COUNTER_OFFSET" type="uint" usage="rp_blit"/> + <reg64 offset="0xa983" name="SP_PS_BASE" type="address" align="32" usage="rp_blit"/> + <reg32 offset="0xa985" name="SP_PS_PVT_MEM_PARAM" type="a6xx_sp_xs_pvt_mem_param" usage="rp_blit"/> + <reg64 offset="0xa986" name="SP_PS_PVT_MEM_BASE" type="waddress" align="32" usage="rp_blit"/> + <reg32 offset="0xa988" name="SP_PS_PVT_MEM_SIZE" type="a6xx_sp_xs_pvt_mem_size" usage="rp_blit"/> <reg32 offset="0xa989" name="SP_BLEND_CNTL" usage="rp_blit"> <!-- per-mrt enable bit --> @@ -4948,7 +2795,7 @@ to upconvert to 32b float internally? <bitfield name="SRGB_MRT6" pos="6" type="boolean"/> <bitfield name="SRGB_MRT7" pos="7" type="boolean"/> </reg32> - <reg32 offset="0xa98b" name="SP_FS_RENDER_COMPONENTS" usage="rp_blit"> + <reg32 offset="0xa98b" name="SP_PS_OUTPUT_MASK" usage="rp_blit"> <bitfield name="RT0" low="0" high="3"/> <bitfield name="RT1" low="4" high="7"/> <bitfield name="RT2" low="8" high="11"/> @@ -4958,17 +2805,17 @@ to upconvert to 32b float internally? <bitfield name="RT6" low="24" high="27"/> <bitfield name="RT7" low="28" high="31"/> </reg32> - <reg32 offset="0xa98c" name="SP_FS_OUTPUT_CNTL0" usage="rp_blit"> + <reg32 offset="0xa98c" name="SP_PS_OUTPUT_CNTL" usage="rp_blit"> <bitfield name="DUAL_COLOR_IN_ENABLE" pos="0" type="boolean"/> <bitfield name="DEPTH_REGID" low="8" high="15" type="a3xx_regid"/> <bitfield name="SAMPMASK_REGID" low="16" high="23" type="a3xx_regid"/> <bitfield name="STENCILREF_REGID" low="24" high="31" type="a3xx_regid"/> </reg32> - <reg32 offset="0xa98d" name="SP_FS_OUTPUT_CNTL1" usage="rp_blit"> + <reg32 offset="0xa98d" name="SP_PS_MRT_CNTL" usage="rp_blit"> <bitfield name="MRT" low="0" high="3" type="uint"/> </reg32> - <array offset="0xa98e" name="SP_FS_OUTPUT" stride="1" length="8" usage="rp_blit"> + <array offset="0xa98e" name="SP_PS_OUTPUT" stride="1" length="8" usage="rp_blit"> <doc>per MRT</doc> <reg32 offset="0x0" name="REG"> <bitfield name="REGID" low="0" high="7" type="a3xx_regid"/> @@ -4976,7 +2823,7 @@ to upconvert to 32b float internally? </reg32> </array> - <array offset="0xa996" name="SP_FS_MRT" stride="1" length="8" usage="rp_blit"> + <array offset="0xa996" name="SP_PS_MRT" stride="1" length="8" usage="rp_blit"> <reg32 offset="0" name="REG"> <bitfield name="COLOR_FORMAT" low="0" high="7" type="a6xx_format"/> <bitfield name="COLOR_SINT" pos="8" type="boolean"/> @@ -4985,7 +2832,7 @@ to upconvert to 32b float internally? </reg32> </array> - <reg32 offset="0xa99e" name="SP_FS_PREFETCH_CNTL" usage="rp_blit"> + <reg32 offset="0xa99e" name="SP_PS_INITIAL_TEX_LOAD_CNTL" usage="rp_blit"> <bitfield name="COUNT" low="0" high="2" type="uint"/> <bitfield name="IJ_WRITE_DISABLE" pos="3" type="boolean"/> <doc> @@ -5002,7 +2849,7 @@ to upconvert to 32b float internally? <!-- Blob never uses it --> <bitfield name="CONSTSLOTID4COORD" low="16" high="24" type="uint" variants="A7XX-"/> </reg32> - <array offset="0xa99f" name="SP_FS_PREFETCH" stride="1" length="4" variants="A6XX" usage="rp_blit"> + <array offset="0xa99f" name="SP_PS_INITIAL_TEX_LOAD" stride="1" length="4" variants="A6XX" usage="rp_blit"> <reg32 offset="0" name="CMD" variants="A6XX"> <bitfield name="SRC" low="0" high="6" type="uint"/> <bitfield name="SAMP_ID" low="7" high="10" type="uint"/> @@ -5016,7 +2863,7 @@ to upconvert to 32b float internally? <bitfield name="CMD" low="29" high="31" type="a6xx_tex_prefetch_cmd"/> </reg32> </array> - <array offset="0xa99f" name="SP_FS_PREFETCH" stride="1" length="4" variants="A7XX-" usage="rp_blit"> + <array offset="0xa99f" name="SP_PS_INITIAL_TEX_LOAD" stride="1" length="4" variants="A7XX-" usage="rp_blit"> <reg32 offset="0" name="CMD" variants="A7XX-"> <bitfield name="SRC" low="0" high="6" type="uint"/> <bitfield name="SAMP_ID" low="7" high="9" type="uint"/> @@ -5028,22 +2875,23 @@ to upconvert to 32b float internally? <bitfield name="CMD" low="26" high="29" type="a6xx_tex_prefetch_cmd"/> </reg32> </array> - <array offset="0xa9a3" name="SP_FS_BINDLESS_PREFETCH" stride="1" length="4" usage="rp_blit"> + <array offset="0xa9a3" name="SP_PS_INITIAL_TEX_INDEX" stride="1" length="4" usage="rp_blit"> <reg32 offset="0" name="CMD"> <bitfield name="SAMP_ID" low="0" high="15" type="uint"/> <bitfield name="TEX_ID" low="16" high="31" type="uint"/> </reg32> </array> - <reg32 offset="0xa9a7" name="SP_FS_TEX_COUNT" low="0" high="7" type="uint" usage="rp_blit"/> + <reg32 offset="0xa9a7" name="SP_PS_TSIZE" low="0" high="7" type="uint" usage="rp_blit"/> <reg32 offset="0xa9a8" name="SP_UNKNOWN_A9A8" low="0" high="16" usage="cmd"/> <!-- always 0x0 ? --> - <reg32 offset="0xa9a9" name="SP_FS_PVT_MEM_HW_STACK_OFFSET" type="a6xx_sp_xs_pvt_mem_hw_stack_offset" usage="rp_blit"/> + <reg32 offset="0xa9a9" name="SP_PS_PVT_MEM_STACK_OFFSET" type="a6xx_sp_xs_pvt_mem_stack_offset" usage="rp_blit"/> + <reg32 offset="0xa9ab" name="SP_PS_UNKNOWN_A9AB" variants="A7XX-" usage="cmd"/> <!-- TODO: unknown bool register at 0xa9aa, likely same as 0xa8c0-0xa8c3 but for FS --> - <reg32 offset="0xa9b0" name="SP_CS_CTRL_REG0" type="a6xx_sp_xs_ctrl_reg0" usage="cmd"> + <reg32 offset="0xa9b0" name="SP_CS_CNTL_0" type="a6xx_sp_xs_cntl_0" usage="cmd"> <bitfield name="THREADSIZE" pos="20" type="a6xx_threadsize"/> <!-- seems to make SP use less concurrent threads when possible? --> <bitfield name="UNK21" pos="21" type="boolean"/> @@ -5053,8 +2901,15 @@ to upconvert to 32b float internally? <bitfield name="MERGEDREGS" pos="31" type="boolean"/> </reg32> + <enum name="a6xx_const_ram_mode"> + <value value="0x0" name="CONSTLEN_128"/> + <value value="0x1" name="CONSTLEN_192"/> + <value value="0x2" name="CONSTLEN_256"/> + <value value="0x3" name="CONSTLEN_512"/> <!-- a7xx only --> + </enum> + <!-- set for compute shaders --> - <reg32 offset="0xa9b1" name="SP_CS_UNKNOWN_A9B1" usage="cmd"> + <reg32 offset="0xa9b1" name="SP_CS_CNTL_1" usage="cmd"> <bitfield name="SHARED_SIZE" low="0" high="4" type="uint"> <doc> If 0 - all 32k of shared storage is enabled, otherwise @@ -5065,32 +2920,36 @@ to upconvert to 32b float internally? always return 0) </doc> </bitfield> - <bitfield name="UNK5" pos="5" type="boolean"/> - <!-- always 1 ? --> - <bitfield name="UNK6" pos="6" type="boolean"/> + <bitfield name="CONSTANTRAMMODE" low="5" high="6" type="a6xx_const_ram_mode"> + <doc> + This defines the split between consts and local + memory in the Local Buffer. The programmed value + must be at least the actual CONSTLEN. + </doc> + </bitfield> </reg32> - <reg32 offset="0xa9b2" name="SP_CS_BRANCH_COND" type="hex" usage="cmd"/> - <reg32 offset="0xa9b3" name="SP_CS_OBJ_FIRST_EXEC_OFFSET" type="uint" usage="cmd"/> - <reg64 offset="0xa9b4" name="SP_CS_OBJ_START" type="address" align="32" usage="cmd"/> + <reg32 offset="0xa9b2" name="SP_CS_BOOLEAN_CF_MASK" type="hex" usage="cmd"/> + <reg32 offset="0xa9b3" name="SP_CS_PROGRAM_COUNTER_OFFSET" type="uint" usage="cmd"/> + <reg64 offset="0xa9b4" name="SP_CS_BASE" type="address" align="32" usage="cmd"/> <reg32 offset="0xa9b6" name="SP_CS_PVT_MEM_PARAM" type="a6xx_sp_xs_pvt_mem_param" usage="cmd"/> - <reg64 offset="0xa9b7" name="SP_CS_PVT_MEM_ADDR" align="32" usage="cmd"/> + <reg64 offset="0xa9b7" name="SP_CS_PVT_MEM_BASE" align="32" usage="cmd"/> <reg32 offset="0xa9b9" name="SP_CS_PVT_MEM_SIZE" type="a6xx_sp_xs_pvt_mem_size" usage="cmd"/> - <reg32 offset="0xa9ba" name="SP_CS_TEX_COUNT" low="0" high="7" type="uint" usage="cmd"/> + <reg32 offset="0xa9ba" name="SP_CS_TSIZE" low="0" high="7" type="uint" usage="cmd"/> <reg32 offset="0xa9bb" name="SP_CS_CONFIG" type="a6xx_sp_xs_config" usage="cmd"/> - <reg32 offset="0xa9bc" name="SP_CS_INSTRLEN" low="0" high="27" type="uint" usage="cmd"/> - <reg32 offset="0xa9bd" name="SP_CS_PVT_MEM_HW_STACK_OFFSET" type="a6xx_sp_xs_pvt_mem_hw_stack_offset" usage="cmd"/> + <reg32 offset="0xa9bc" name="SP_CS_INSTR_SIZE" low="0" high="27" type="uint" usage="cmd"/> + <reg32 offset="0xa9bd" name="SP_CS_PVT_MEM_STACK_OFFSET" type="a6xx_sp_xs_pvt_mem_stack_offset" usage="cmd"/> <reg32 offset="0xa9be" name="SP_CS_UNKNOWN_A9BE" variants="A7XX-" usage="cmd"/> - <reg32 offset="0xa9c5" name="SP_CS_VGPR_CONFIG" variants="A7XX-" usage="cmd"/> + <reg32 offset="0xa9c5" name="SP_CS_VGS_CNTL" variants="A7XX-" usage="cmd"/> - <!-- new in a6xx gen4, matches HLSQ_CS_CNTL_0 --> - <reg32 offset="0xa9c2" name="SP_CS_CNTL_0" usage="cmd"> + <!-- new in a6xx gen4, matches SP_CS_CONST_CONFIG_0 --> + <reg32 offset="0xa9c2" name="SP_CS_WIE_CNTL_0" usage="cmd"> <bitfield name="WGIDCONSTID" low="0" high="7" type="a3xx_regid"/> <bitfield name="WGSIZECONSTID" low="8" high="15" type="a3xx_regid"/> <bitfield name="WGOFFSETCONSTID" low="16" high="23" type="a3xx_regid"/> <bitfield name="LOCALIDREGID" low="24" high="31" type="a3xx_regid"/> </reg32> - <!-- new in a6xx gen4, matches HLSQ_CS_CNTL_1 --> - <reg32 offset="0xa9c3" name="SP_CS_CNTL_1" variants="A6XX" usage="cmd"> + <!-- new in a6xx gen4, matches SP_CS_WGE_CNTL --> + <reg32 offset="0xa9c3" name="SP_CS_WIE_CNTL_1" variants="A6XX" usage="cmd"> <!-- gl_LocalInvocationIndex --> <bitfield name="LINEARLOCALIDREGID" low="0" high="7" type="a3xx_regid"/> <!-- a650 has 6 "SP cores" (but 3 "SP"). this makes it use only @@ -5102,7 +2961,18 @@ to upconvert to 32b float internally? <bitfield name="THREADSIZE_SCALAR" pos="10" type="boolean"/> </reg32> - <reg32 offset="0xa9c3" name="SP_CS_CNTL_1" variants="A7XX-" usage="cmd"> + <enum name="a7xx_workitem_rast_order"> + <value value="0x0" name="WORKITEMRASTORDER_LINEAR"/> + <doc> + This is a fixed tiling, with 4x4 invocation outer tiles + containing 2x2 invocation inner tiles. The intent is to + improve cache locality with textures and images accessed + using gl_LocalInvocationID. + </doc> + <value value="0x1" name="WORKITEMRASTORDER_TILED"/> + </enum> + + <reg32 offset="0xa9c3" name="SP_CS_WIE_CNTL_1" variants="A7XX-" usage="cmd"> <!-- gl_LocalInvocationIndex --> <bitfield name="LINEARLOCALIDREGID" low="0" high="7" type="a3xx_regid"/> <!-- Must match SP_CS_CTRL --> @@ -5110,18 +2980,16 @@ to upconvert to 32b float internally? <!-- 1 thread per wave (would hang if THREAD128 is also set) --> <bitfield name="THREADSIZE_SCALAR" pos="9" type="boolean"/> - <!-- Affects getone. If enabled, getone sometimes executed 1? less times - than there are subgroups. - --> - <bitfield name="UNK15" pos="15" type="boolean"/> + <doc>How invocations/fibers within a workgroup are tiled.</doc> + <bitfield name="WORKITEMRASTORDER" pos="15" type="a7xx_workitem_rast_order"/> </reg32> <!-- TODO: two 64kb aligned addresses at a9d0/a9d2 --> - <reg64 offset="0xa9e0" name="SP_FS_TEX_SAMP" type="address" align="16" usage="rp_blit"/> - <reg64 offset="0xa9e2" name="SP_CS_TEX_SAMP" type="address" align="16" usage="cmd"/> - <reg64 offset="0xa9e4" name="SP_FS_TEX_CONST" type="address" align="64" usage="rp_blit"/> - <reg64 offset="0xa9e6" name="SP_CS_TEX_CONST" type="address" align="64" usage="cmd"/> + <reg64 offset="0xa9e0" name="SP_PS_SAMPLER_BASE" type="address" align="16" usage="rp_blit"/> + <reg64 offset="0xa9e2" name="SP_CS_SAMPLER_BASE" type="address" align="16" usage="cmd"/> + <reg64 offset="0xa9e4" name="SP_PS_TEXMEMOBJ_BASE" type="address" align="64" usage="rp_blit"/> + <reg64 offset="0xa9e6" name="SP_CS_TEXMEMOBJ_BASE" type="address" align="64" usage="cmd"/> <enum name="a6xx_bindless_descriptor_size"> <doc> @@ -5146,18 +3014,19 @@ to upconvert to 32b float internally? </array> <!-- - IBO state for compute shader: + UAV state for compute shader: --> - <reg64 offset="0xa9f2" name="SP_CS_IBO" type="address" align="16"/> - <reg32 offset="0xaa00" name="SP_CS_IBO_COUNT" low="0" high="6" type="uint"/> + <reg64 offset="0xa9f2" name="SP_CS_UAV_BASE" type="address" align="16" variants="A6XX"/> + <reg64 offset="0xa9f8" name="SP_CS_UAV_BASE" type="address" align="16" variants="A7XX"/> + <reg32 offset="0xaa00" name="SP_CS_USIZE" low="0" high="6" type="uint"/> <!-- Correlated with avgs/uvgs usage in FS --> - <reg32 offset="0xaa01" name="SP_FS_VGPR_CONFIG" type="uint" variants="A7XX-" usage="cmd"/> + <reg32 offset="0xaa01" name="SP_PS_VGS_CNTL" type="uint" variants="A7XX-" usage="cmd"/> - <reg32 offset="0xaa02" name="SP_PS_ALIASED_COMPONENTS_CONTROL" variants="A7XX-" usage="cmd"> + <reg32 offset="0xaa02" name="SP_PS_OUTPUT_CONST_CNTL" variants="A7XX-" usage="cmd"> <bitfield name="ENABLED" pos="0" type="boolean"/> </reg32> - <reg32 offset="0xaa03" name="SP_PS_ALIASED_COMPONENTS" variants="A7XX-" usage="cmd"> + <reg32 offset="0xaa03" name="SP_PS_OUTPUT_CONST_MASK" variants="A7XX-" usage="cmd"> <doc> Specify for which components the output color should be read from alias, e.g. for: @@ -5167,7 +3036,7 @@ to upconvert to 32b float internally? alias.1.b32.0 r1.x, c4.x alias.1.b32.0 r0.x, c0.x - the SP_PS_ALIASED_COMPONENTS would be 0x00001111 + the SP_PS_OUTPUT_CONST_MASK would be 0x00001111 </doc> <bitfield name="RT0" low="0" high="3"/> @@ -5193,7 +3062,7 @@ to upconvert to 32b float internally? <value value="0x2" name="ISAMMODE_GL"/> </enum> - <reg32 offset="0xab00" name="SP_MODE_CONTROL" usage="rp_blit"> + <reg32 offset="0xab00" name="SP_MODE_CNTL" usage="rp_blit"> <!-- When set, half register loads from the constant file will load a 32-bit value (so hc0.y loads the same value as c0.y) @@ -5210,16 +3079,16 @@ to upconvert to 32b float internally? <reg32 offset="0xab01" name="SP_UNKNOWN_AB01" variants="A7XX-" usage="cmd"/> <reg32 offset="0xab02" name="SP_UNKNOWN_AB02" variants="A7XX-" usage="cmd"/> - <reg32 offset="0xab04" name="SP_FS_CONFIG" type="a6xx_sp_xs_config" usage="rp_blit"/> - <reg32 offset="0xab05" name="SP_FS_INSTRLEN" low="0" high="27" type="uint" usage="rp_blit"/> + <reg32 offset="0xab04" name="SP_PS_CONFIG" type="a6xx_sp_xs_config" usage="rp_blit"/> + <reg32 offset="0xab05" name="SP_PS_INSTR_SIZE" low="0" high="27" type="uint" usage="rp_blit"/> - <array offset="0xab10" name="SP_BINDLESS_BASE" stride="2" length="5" variants="A6XX" usage="rp_blit"> + <array offset="0xab10" name="SP_GFX_BINDLESS_BASE" stride="2" length="5" variants="A6XX" usage="rp_blit"> <reg64 offset="0" name="DESCRIPTOR" variants="A6XX"> <bitfield name="DESC_SIZE" low="0" high="1" type="a6xx_bindless_descriptor_size"/> <bitfield name="ADDR" low="2" high="63" shr="2" type="address"/> </reg64> </array> - <array offset="0xab0a" name="SP_BINDLESS_BASE" stride="2" length="8" variants="A7XX-" usage="rp_blit"> + <array offset="0xab0a" name="SP_GFX_BINDLESS_BASE" stride="2" length="8" variants="A7XX-" usage="rp_blit"> <reg64 offset="0" name="DESCRIPTOR" variants="A7XX-"> <bitfield name="DESC_SIZE" low="0" high="1" type="a6xx_bindless_descriptor_size"/> <bitfield name="ADDR" low="2" high="63" shr="2" type="address"/> @@ -5227,15 +3096,15 @@ to upconvert to 32b float internally? </array> <!-- - Combined IBO state for 3d pipe, used for Image and SSBO write/atomic - instructions VS/HS/DS/GS/FS. See SP_CS_IBO_* for compute shaders. + Combined UAV state for 3d pipe, used for Image and SSBO write/atomic + instructions VS/HS/DS/GS/FS. See SP_CS_UAV_BASE_* for compute shaders. --> - <reg64 offset="0xab1a" name="SP_IBO" type="address" align="16" usage="cmd"/> - <reg32 offset="0xab20" name="SP_IBO_COUNT" low="0" high="6" type="uint" usage="cmd"/> + <reg64 offset="0xab1a" name="SP_GFX_UAV_BASE" type="address" align="16" usage="cmd"/> + <reg32 offset="0xab20" name="SP_GFX_USIZE" low="0" high="6" type="uint" usage="cmd"/> <reg32 offset="0xab22" name="SP_UNKNOWN_AB22" variants="A7XX-" usage="cmd"/> - <bitset name="a6xx_sp_2d_dst_format" inline="yes"> + <bitset name="a6xx_sp_a2d_output_info" inline="yes"> <bitfield name="NORM" pos="0" type="boolean"/> <bitfield name="SINT" pos="1" type="boolean"/> <bitfield name="UINT" pos="2" type="boolean"/> @@ -5248,8 +3117,8 @@ to upconvert to 32b float internally? <bitfield name="MASK" low="12" high="15"/> </bitset> - <reg32 offset="0xacc0" name="SP_2D_DST_FORMAT" type="a6xx_sp_2d_dst_format" variants="A6XX" usage="rp_blit"/> - <reg32 offset="0xa9bf" name="SP_2D_DST_FORMAT" type="a6xx_sp_2d_dst_format" variants="A7XX-" usage="rp_blit"/> + <reg32 offset="0xacc0" name="SP_A2D_OUTPUT_INFO" type="a6xx_sp_a2d_output_info" variants="A6XX" usage="rp_blit"/> + <reg32 offset="0xa9bf" name="SP_A2D_OUTPUT_INFO" type="a6xx_sp_a2d_output_info" variants="A7XX-" usage="rp_blit"/> <reg32 offset="0xae00" name="SP_DBG_ECO_CNTL" usage="cmd"/> <reg32 offset="0xae01" name="SP_ADDR_MODE_CNTL" pos="0" type="a5xx_address_mode"/> @@ -5257,16 +3126,16 @@ to upconvert to 32b float internally? <!-- TODO: valid bits 0x3c3f, see kernel --> </reg32> <reg32 offset="0xae03" name="SP_CHICKEN_BITS" usage="cmd"/> - <reg32 offset="0xae04" name="SP_FLOAT_CNTL" usage="cmd"> + <reg32 offset="0xae04" name="SP_NC_MODE_CNTL_2" usage="cmd"> <bitfield name="F16_NO_INF" pos="3" type="boolean"/> </reg32> <reg32 offset="0xae06" name="SP_UNKNOWN_AE06" variants="A7XX-" usage="cmd"/> - <reg32 offset="0xae08" name="SP_UNKNOWN_AE08" variants="A7XX-" usage="cmd"/> - <reg32 offset="0xae09" name="SP_UNKNOWN_AE09" variants="A7XX-" usage="cmd"/> - <reg32 offset="0xae0a" name="SP_UNKNOWN_AE0A" variants="A7XX-" usage="cmd"/> + <reg32 offset="0xae08" name="SP_CHICKEN_BITS_1" variants="A7XX-" usage="cmd"/> + <reg32 offset="0xae09" name="SP_CHICKEN_BITS_2" variants="A7XX-" usage="cmd"/> + <reg32 offset="0xae0a" name="SP_CHICKEN_BITS_3" variants="A7XX-" usage="cmd"/> - <reg32 offset="0xae0f" name="SP_PERFCTR_ENABLE" usage="cmd"> + <reg32 offset="0xae0f" name="SP_PERFCTR_SHADER_MASK" usage="cmd"> <!-- some perfcntrs are affected by a per-stage enable bit (PERF_SP_ALU_WORKING_CYCLES for example) TODO: verify position of HS/DS/GS bits --> @@ -5281,7 +3150,7 @@ to upconvert to 32b float internally? <array offset="0xae60" name="SP_PERFCTR_HLSQ_SEL" stride="1" length="6" variants="A7XX-"/> <reg32 offset="0xae6a" name="SP_UNKNOWN_AE6A" variants="A7XX-" usage="cmd"/> <reg32 offset="0xae6b" name="SP_UNKNOWN_AE6B" variants="A7XX-" usage="cmd"/> - <reg32 offset="0xae6c" name="SP_UNKNOWN_AE6C" variants="A7XX-" usage="cmd"/> + <reg32 offset="0xae6c" name="SP_HLSQ_DBG_ECO_CNTL" variants="A7XX-" usage="cmd"/> <reg32 offset="0xae6d" name="SP_READ_SEL" variants="A7XX-"> <bitfield name="LOCATION" low="18" high="19" type="a7xx_state_location"/> <bitfield name="PIPE" low="16" high="17" type="a7xx_pipe"/> @@ -5301,33 +3170,44 @@ to upconvert to 32b float internally? "a6xx_sp_ps_tp_cluster" but this actually specifies the border color base for compute shaders. --> - <reg64 offset="0xb180" name="SP_PS_TP_BORDER_COLOR_BASE_ADDR" type="address" align="128" usage="cmd"/> + <reg64 offset="0xb180" name="TPL1_CS_BORDER_COLOR_BASE" type="address" align="128" usage="cmd"/> <reg32 offset="0xb182" name="SP_UNKNOWN_B182" low="0" high="2" usage="cmd"/> <reg32 offset="0xb183" name="SP_UNKNOWN_B183" low="0" high="23" usage="cmd"/> <reg32 offset="0xb190" name="SP_UNKNOWN_B190"/> <reg32 offset="0xb191" name="SP_UNKNOWN_B191"/> - <!-- could be all the stuff below here is actually TPL1?? --> - - <reg32 offset="0xb300" name="SP_TP_RAS_MSAA_CNTL" usage="rp_blit"> + <reg32 offset="0xb300" name="TPL1_RAS_MSAA_CNTL" usage="rp_blit"> <bitfield name="SAMPLES" low="0" high="1" type="a3xx_msaa_samples"/> <bitfield name="UNK2" low="2" high="3"/> </reg32> - <reg32 offset="0xb301" name="SP_TP_DEST_MSAA_CNTL" usage="rp_blit"> + <reg32 offset="0xb301" name="TPL1_DEST_MSAA_CNTL" usage="rp_blit"> <bitfield name="SAMPLES" low="0" high="1" type="a3xx_msaa_samples"/> <bitfield name="MSAA_DISABLE" pos="2" type="boolean"/> </reg32> <!-- looks to work in the same way as a5xx: --> - <reg64 offset="0xb302" name="SP_TP_BORDER_COLOR_BASE_ADDR" type="address" align="128" usage="cmd"/> - <reg32 offset="0xb304" name="SP_TP_SAMPLE_CONFIG" type="a6xx_sample_config" usage="rp_blit"/> - <reg32 offset="0xb305" name="SP_TP_SAMPLE_LOCATION_0" type="a6xx_sample_locations" usage="rp_blit"/> - <reg32 offset="0xb306" name="SP_TP_SAMPLE_LOCATION_1" type="a6xx_sample_locations" usage="rp_blit"/> - <reg32 offset="0xb307" name="SP_TP_WINDOW_OFFSET" type="a6xx_reg_xy" usage="rp_blit"/> - <reg32 offset="0xb309" name="SP_TP_MODE_CNTL" usage="cmd"> + <reg64 offset="0xb302" name="TPL1_GFX_BORDER_COLOR_BASE" type="address" align="128" usage="cmd"/> + <reg32 offset="0xb304" name="TPL1_MSAA_SAMPLE_POS_CNTL" type="a6xx_msaa_sample_pos_cntl" usage="rp_blit"/> + <reg32 offset="0xb305" name="TPL1_PROGRAMMABLE_MSAA_POS_0" type="a6xx_programmable_msaa_pos" usage="rp_blit"/> + <reg32 offset="0xb306" name="TPL1_PROGRAMMABLE_MSAA_POS_1" type="a6xx_programmable_msaa_pos" usage="rp_blit"/> + <reg32 offset="0xb307" name="TPL1_WINDOW_OFFSET" type="a6xx_reg_xy" usage="rp_blit"/> + + <enum name="a6xx_coord_round"> + <value value="0" name="COORD_TRUNCATE"/> + <value value="1" name="COORD_ROUND_NEAREST_EVEN"/> + </enum> + + <enum name="a6xx_nearest_mode"> + <value value="0" name="ROUND_CLAMP_TRUNCATE"/> + <value value="1" name="CLAMP_ROUND_TRUNCATE"/> + </enum> + + <reg32 offset="0xb309" name="TPL1_MODE_CNTL" usage="cmd"> <bitfield name="ISAMMODE" low="0" high="1" type="a6xx_isam_mode"/> - <bitfield name="UNK3" low="2" high="7"/> + <bitfield name="TEXCOORDROUNDMODE" pos="2" type="a6xx_coord_round"/> + <bitfield name="NEARESTMIPSNAP" pos="5" type="a6xx_nearest_mode"/> + <bitfield name="DESTDATATYPEOVERRIDE" pos="7" type="boolean"/> </reg32> <reg32 offset="0xb310" name="SP_UNKNOWN_B310" variants="A7XX-" usage="cmd"/> @@ -5336,42 +3216,45 @@ to upconvert to 32b float internally? badly named or the functionality moved in a6xx. But downstream kernel calls this "a6xx_sp_ps_tp_2d_cluster" --> - <reg32 offset="0xb4c0" name="SP_PS_2D_SRC_INFO" type="a6xx_2d_src_surf_info" variants="A6XX" usage="rp_blit"/> - <reg32 offset="0xb4c1" name="SP_PS_2D_SRC_SIZE" variants="A6XX" usage="rp_blit"> + <reg32 offset="0xb4c0" name="TPL1_A2D_SRC_TEXTURE_INFO" type="a6xx_a2d_src_texture_info" variants="A6XX" usage="rp_blit"/> + <reg32 offset="0xb4c1" name="TPL1_A2D_SRC_TEXTURE_SIZE" variants="A6XX" usage="rp_blit"> <bitfield name="WIDTH" low="0" high="14" type="uint"/> <bitfield name="HEIGHT" low="15" high="29" type="uint"/> </reg32> - <reg64 offset="0xb4c2" name="SP_PS_2D_SRC" type="address" align="16" variants="A6XX" usage="rp_blit"/> - <reg32 offset="0xb4c4" name="SP_PS_2D_SRC_PITCH" variants="A6XX" usage="rp_blit"> + <reg64 offset="0xb4c2" name="TPL1_A2D_SRC_TEXTURE_BASE" type="address" align="16" variants="A6XX" usage="rp_blit"/> + <reg32 offset="0xb4c4" name="TPL1_A2D_SRC_TEXTURE_PITCH" variants="A6XX" usage="rp_blit"> <bitfield name="UNK0" low="0" high="8"/> <bitfield name="PITCH" low="9" high="23" shr="6" type="uint"/> </reg32> - <reg32 offset="0xb2c0" name="SP_PS_2D_SRC_INFO" type="a6xx_2d_src_surf_info" variants="A7XX-" usage="rp_blit"/> - <reg32 offset="0xb2c1" name="SP_PS_2D_SRC_SIZE" variants="A7XX"> + <reg32 offset="0xb2c0" name="TPL1_A2D_SRC_TEXTURE_INFO" type="a6xx_a2d_src_texture_info" variants="A7XX-" usage="rp_blit"/> + <reg32 offset="0xb2c1" name="TPL1_A2D_SRC_TEXTURE_SIZE" variants="A7XX"> <bitfield name="WIDTH" low="0" high="14" type="uint"/> <bitfield name="HEIGHT" low="15" high="29" type="uint"/> </reg32> - <reg64 offset="0xb2c2" name="SP_PS_2D_SRC" type="address" align="16" variants="A7XX-" usage="rp_blit"/> - <reg32 offset="0xb2c4" name="SP_PS_2D_SRC_PITCH" variants="A7XX"> - <bitfield name="UNK0" low="0" high="8"/> - <bitfield name="PITCH" low="9" high="23" shr="6" type="uint"/> + <reg64 offset="0xb2c2" name="TPL1_A2D_SRC_TEXTURE_BASE" type="address" align="16" variants="A7XX-" usage="rp_blit"/> + <reg32 offset="0xb2c4" name="TPL1_A2D_SRC_TEXTURE_PITCH" variants="A7XX"> + <!-- + Bits from 3..9 must be zero unless 'TPL1_A2D_BLT_CNTL::TYPE' + is A6XX_TEX_IMG_BUFFER, which allows for lower alignment. + --> + <bitfield name="PITCH" low="3" high="23" type="uint"/> </reg32> <!-- planes for NV12, etc. (TODO: not tested) --> - <reg64 offset="0xb4c5" name="SP_PS_2D_SRC_PLANE1" type="address" align="16" variants="A6XX"/> - <reg32 offset="0xb4c7" name="SP_PS_2D_SRC_PLANE_PITCH" low="0" high="11" shr="6" type="uint" variants="A6XX"/> - <reg64 offset="0xb4c8" name="SP_PS_2D_SRC_PLANE2" type="address" align="16" variants="A6XX"/> + <reg64 offset="0xb4c5" name="TPL1_A2D_SRC_TEXTURE_BASE_1" type="address" align="16" variants="A6XX"/> + <reg32 offset="0xb4c7" name="TPL1_A2D_SRC_TEXTURE_PITCH_1" low="0" high="11" shr="6" type="uint" variants="A6XX"/> + <reg64 offset="0xb4c8" name="TPL1_A2D_SRC_TEXTURE_BASE_2" type="address" align="16" variants="A6XX"/> - <reg64 offset="0xb2c5" name="SP_PS_2D_SRC_PLANE1" type="address" align="16" variants="A7XX-"/> - <reg32 offset="0xb2c7" name="SP_PS_2D_SRC_PLANE_PITCH" low="0" high="11" shr="6" type="uint" variants="A7XX-"/> - <reg64 offset="0xb2c8" name="SP_PS_2D_SRC_PLANE2" type="address" align="16" variants="A7XX-"/> + <reg64 offset="0xb2c5" name="TPL1_A2D_SRC_TEXTURE_BASE_1" type="address" align="16" variants="A7XX-"/> + <reg32 offset="0xb2c7" name="TPL1_A2D_SRC_TEXTURE_PITCH_1" low="0" high="11" shr="6" type="uint" variants="A7XX-"/> + <reg64 offset="0xb2c8" name="TPL1_A2D_SRC_TEXTURE_BASE_2" type="address" align="16" variants="A7XX-"/> - <reg64 offset="0xb4ca" name="SP_PS_2D_SRC_FLAGS" type="address" align="16" variants="A6XX" usage="rp_blit"/> - <reg32 offset="0xb4cc" name="SP_PS_2D_SRC_FLAGS_PITCH" low="0" high="7" shr="6" type="uint" variants="A6XX" usage="rp_blit"/> + <reg64 offset="0xb4ca" name="TPL1_A2D_SRC_TEXTURE_FLAG_BASE" type="address" align="16" variants="A6XX" usage="rp_blit"/> + <reg32 offset="0xb4cc" name="TPL1_A2D_SRC_TEXTURE_FLAG_PITCH" low="0" high="7" shr="6" type="uint" variants="A6XX" usage="rp_blit"/> - <reg64 offset="0xb2ca" name="SP_PS_2D_SRC_FLAGS" type="address" align="16" variants="A7XX-" usage="rp_blit"/> - <reg32 offset="0xb2cc" name="SP_PS_2D_SRC_FLAGS_PITCH" low="0" high="7" shr="6" type="uint" variants="A7XX-" usage="rp_blit"/> + <reg64 offset="0xb2ca" name="TPL1_A2D_SRC_TEXTURE_FLAG_BASE" type="address" align="16" variants="A7XX-" usage="rp_blit"/> + <reg32 offset="0xb2cc" name="TPL1_A2D_SRC_TEXTURE_FLAG_PITCH" low="0" high="7" shr="6" type="uint" variants="A7XX-" usage="rp_blit"/> <reg32 offset="0xb4cd" name="SP_PS_UNKNOWN_B4CD" low="6" high="31" variants="A6XX"/> <reg32 offset="0xb4ce" name="SP_PS_UNKNOWN_B4CE" low="0" high="31" variants="A6XX"/> @@ -5383,8 +3266,12 @@ to upconvert to 32b float internally? <reg32 offset="0xb2ce" name="SP_PS_UNKNOWN_B4CE" low="0" high="31" variants="A7XX"/> <reg32 offset="0xb2cf" name="SP_PS_UNKNOWN_B4CF" low="0" high="30" variants="A7XX"/> <reg32 offset="0xb2d0" name="SP_PS_UNKNOWN_B4D0" low="0" high="29" variants="A7XX"/> - <reg32 offset="0xb2d1" name="SP_PS_2D_WINDOW_OFFSET" type="a6xx_reg_xy" variants="A7XX"/> - <reg32 offset="0xb2d2" name="SP_PS_UNKNOWN_B2D2" variants="A7XX-" usage="rp_blit"/> + <reg32 offset="0xb2d1" name="TPL1_A2D_WINDOW_OFFSET" type="a6xx_reg_xy" variants="A7XX"/> + <reg32 offset="0xb2d2" name="TPL1_A2D_BLT_CNTL" variants="A7XX-" usage="rp_blit"> + <bitfield name="RAW_COPY" pos="0" type="boolean"/> + <bitfield name="START_OFFSET_TEXELS" low="16" high="21"/> + <bitfield name="TYPE" low="29" high="31" type="a6xx_tex_type"/> + </reg32> <reg32 offset="0xab21" name="SP_WINDOW_OFFSET" type="a6xx_reg_xy" variants="A7XX-" usage="rp_blit"/> <!-- always 0x100000 or 0x1000000? --> @@ -5422,34 +3309,44 @@ to upconvert to 32b float internally? <!-- TODO: 4 more perfcntr sel at 0xb620 ? --> - <bitset name="a6xx_hlsq_xs_cntl" inline="yes"> + <bitset name="a6xx_xs_const_config" inline="yes"> <bitfield name="CONSTLEN" low="0" high="7" shr="2" type="uint"/> <bitfield name="ENABLED" pos="8" type="boolean"/> <bitfield name="READ_IMM_SHARED_CONSTS" pos="9" type="boolean" variants="A7XX-"/> </bitset> - <reg32 offset="0xb800" name="HLSQ_VS_CNTL" type="a6xx_hlsq_xs_cntl" variants="A6XX" usage="rp_blit"/> - <reg32 offset="0xb801" name="HLSQ_HS_CNTL" type="a6xx_hlsq_xs_cntl" variants="A6XX" usage="rp_blit"/> - <reg32 offset="0xb802" name="HLSQ_DS_CNTL" type="a6xx_hlsq_xs_cntl" variants="A6XX" usage="rp_blit"/> - <reg32 offset="0xb803" name="HLSQ_GS_CNTL" type="a6xx_hlsq_xs_cntl" variants="A6XX" usage="rp_blit"/> + <reg32 offset="0xb800" name="SP_VS_CONST_CONFIG" type="a6xx_xs_const_config" variants="A6XX" usage="rp_blit"/> + <reg32 offset="0xb801" name="SP_HS_CONST_CONFIG" type="a6xx_xs_const_config" variants="A6XX" usage="rp_blit"/> + <reg32 offset="0xb802" name="SP_DS_CONST_CONFIG" type="a6xx_xs_const_config" variants="A6XX" usage="rp_blit"/> + <reg32 offset="0xb803" name="SP_GS_CONST_CONFIG" type="a6xx_xs_const_config" variants="A6XX" usage="rp_blit"/> - <reg32 offset="0xa827" name="HLSQ_VS_CNTL" type="a6xx_hlsq_xs_cntl" variants="A7XX-" usage="rp_blit"/> - <reg32 offset="0xa83f" name="HLSQ_HS_CNTL" type="a6xx_hlsq_xs_cntl" variants="A7XX-" usage="rp_blit"/> - <reg32 offset="0xa867" name="HLSQ_DS_CNTL" type="a6xx_hlsq_xs_cntl" variants="A7XX-" usage="rp_blit"/> - <reg32 offset="0xa898" name="HLSQ_GS_CNTL" type="a6xx_hlsq_xs_cntl" variants="A7XX-" usage="rp_blit"/> + <reg32 offset="0xa827" name="SP_VS_CONST_CONFIG" type="a6xx_xs_const_config" variants="A7XX-" usage="rp_blit"/> + <reg32 offset="0xa83f" name="SP_HS_CONST_CONFIG" type="a6xx_xs_const_config" variants="A7XX-" usage="rp_blit"/> + <reg32 offset="0xa867" name="SP_DS_CONST_CONFIG" type="a6xx_xs_const_config" variants="A7XX-" usage="rp_blit"/> + <reg32 offset="0xa898" name="SP_GS_CONST_CONFIG" type="a6xx_xs_const_config" variants="A7XX-" usage="rp_blit"/> - <reg32 offset="0xa9aa" name="HLSQ_FS_UNKNOWN_A9AA" variants="A7XX-" usage="rp_blit"> - <!-- Tentatively named, appears to disable consts being loaded via CP_LOAD_STATE6_FRAG --> - <bitfield name="CONSTS_LOAD_DISABLE" pos="0" type="boolean"/> + <reg32 offset="0xa9aa" name="SP_RENDER_CNTL" variants="A7XX-" usage="rp_blit"> + <bitfield name="FS_DISABLE" pos="0" type="boolean"/> </reg32> - <!-- Always 0 --> - <reg32 offset="0xa9ac" name="HLSQ_UNKNOWN_A9AC" variants="A7XX-" usage="cmd"/> + <reg32 offset="0xa9ac" name="SP_DITHER_CNTL" variants="A7XX-" usage="cmd"> + <bitfield name="DITHER_MODE_MRT0" low="0" high="1" type="adreno_rb_dither_mode"/> + <bitfield name="DITHER_MODE_MRT1" low="2" high="3" type="adreno_rb_dither_mode"/> + <bitfield name="DITHER_MODE_MRT2" low="4" high="5" type="adreno_rb_dither_mode"/> + <bitfield name="DITHER_MODE_MRT3" low="6" high="7" type="adreno_rb_dither_mode"/> + <bitfield name="DITHER_MODE_MRT4" low="8" high="9" type="adreno_rb_dither_mode"/> + <bitfield name="DITHER_MODE_MRT5" low="10" high="11" type="adreno_rb_dither_mode"/> + <bitfield name="DITHER_MODE_MRT6" low="12" high="13" type="adreno_rb_dither_mode"/> + <bitfield name="DITHER_MODE_MRT7" low="14" high="15" type="adreno_rb_dither_mode"/> + </reg32> - <!-- Used in VK_KHR_fragment_shading_rate --> - <reg32 offset="0xa9ad" name="HLSQ_UNKNOWN_A9AD" variants="A7XX-" usage="cmd"/> + <reg32 offset="0xa9ad" name="SP_VRS_CONFIG" variants="A7XX-" usage="rp_blit"> + <bitfield name="PIPELINE_FSR_ENABLE" pos="0" type="boolean"/> + <bitfield name="ATTACHMENT_FSR_ENABLE" pos="1" type="boolean"/> + <bitfield name="PRIMITIVE_FSR_ENABLE" pos="3" type="boolean"/> + </reg32> - <reg32 offset="0xa9ae" name="HLSQ_UNKNOWN_A9AE" variants="A7XX-" usage="rp_blit"> + <reg32 offset="0xa9ae" name="SP_PS_CNTL_1" variants="A7XX-" usage="rp_blit"> <bitfield name="SYSVAL_REGS_COUNT" low="0" high="7" type="uint"/> <!-- UNK8 is set on a730/a740 --> <bitfield name="UNK8" pos="8" type="boolean"/> @@ -5462,94 +3359,94 @@ to upconvert to 32b float internally? <reg32 offset="0xb823" name="HLSQ_LOAD_STATE_GEOM_DATA"/> - <bitset name="a6xx_hlsq_fs_cntl_0" inline="yes"> + <bitset name="a6xx_sp_ps_wave_cntl" inline="yes"> <!-- must match SP_FS_CTRL --> <bitfield name="THREADSIZE" pos="0" type="a6xx_threadsize"/> <bitfield name="VARYINGS" pos="1" type="boolean"/> <bitfield name="UNK2" low="2" high="11"/> </bitset> - <bitset name="a6xx_hlsq_control_3_reg" inline="yes"> + <bitset name="a6xx_sp_reg_prog_id_1" inline="yes"> <!-- register loaded with position (bary.f) --> <bitfield name="IJ_PERSP_PIXEL" low="0" high="7" type="a3xx_regid"/> <bitfield name="IJ_LINEAR_PIXEL" low="8" high="15" type="a3xx_regid"/> <bitfield name="IJ_PERSP_CENTROID" low="16" high="23" type="a3xx_regid"/> <bitfield name="IJ_LINEAR_CENTROID" low="24" high="31" type="a3xx_regid"/> </bitset> - <bitset name="a6xx_hlsq_control_4_reg" inline="yes"> + <bitset name="a6xx_sp_reg_prog_id_2" inline="yes"> <bitfield name="IJ_PERSP_SAMPLE" low="0" high="7" type="a3xx_regid"/> <bitfield name="IJ_LINEAR_SAMPLE" low="8" high="15" type="a3xx_regid"/> <bitfield name="XYCOORDREGID" low="16" high="23" type="a3xx_regid"/> <bitfield name="ZWCOORDREGID" low="24" high="31" type="a3xx_regid"/> </bitset> - <bitset name="a6xx_hlsq_control_5_reg" inline="yes"> + <bitset name="a6xx_sp_reg_prog_id_3" inline="yes"> <bitfield name="LINELENGTHREGID" low="0" high="7" type="a3xx_regid"/> <bitfield name="FOVEATIONQUALITYREGID" low="8" high="15" type="a3xx_regid"/> </bitset> - <reg32 offset="0xb980" type="a6xx_hlsq_fs_cntl_0" name="HLSQ_FS_CNTL_0" variants="A6XX" usage="rp_blit"/> + <reg32 offset="0xb980" type="a6xx_sp_ps_wave_cntl" name="SP_PS_WAVE_CNTL" variants="A6XX" usage="rp_blit"/> <reg32 offset="0xb981" name="HLSQ_UNKNOWN_B981" pos="0" type="boolean" variants="A6XX"/> <!-- never used by blob --> - <reg32 offset="0xb982" name="HLSQ_CONTROL_1_REG" low="0" high="2" variants="A6XX" usage="rp_blit"> + <reg32 offset="0xb982" name="SP_LB_PARAM_LIMIT" low="0" high="2" variants="A6XX" usage="rp_blit"> <!-- Sets the maximum number of primitives allowed in one FS wave minus one, similarly to the A3xx field, except that it's not necessary to set it to anything but the maximum, since the hardware will simply emit smaller waves when it runs out of space. --> <bitfield name="PRIMALLOCTHRESHOLD" low="0" high="2" type="uint"/> </reg32> - <reg32 offset="0xb983" name="HLSQ_CONTROL_2_REG" variants="A6XX" usage="rp_blit"> + <reg32 offset="0xb983" name="SP_REG_PROG_ID_0" variants="A6XX" usage="rp_blit"> <bitfield name="FACEREGID" low="0" high="7" type="a3xx_regid"/> <!-- SAMPLEID is loaded into a half-precision register: --> <bitfield name="SAMPLEID" low="8" high="15" type="a3xx_regid"/> <bitfield name="SAMPLEMASK" low="16" high="23" type="a3xx_regid"/> <bitfield name="CENTERRHW" low="24" high="31" type="a3xx_regid"/> </reg32> - <reg32 offset="0xb984" type="a6xx_hlsq_control_3_reg" name="HLSQ_CONTROL_3_REG" variants="A6XX" usage="rp_blit"/> - <reg32 offset="0xb985" type="a6xx_hlsq_control_4_reg" name="HLSQ_CONTROL_4_REG" variants="A6XX" usage="rp_blit"/> - <reg32 offset="0xb986" type="a6xx_hlsq_control_5_reg" name="HLSQ_CONTROL_5_REG" variants="A6XX" usage="rp_blit"/> - <reg32 offset="0xb987" name="HLSQ_CS_CNTL" type="a6xx_hlsq_xs_cntl" variants="A6XX" usage="cmd"/> - <reg32 offset="0xa9c6" type="a6xx_hlsq_fs_cntl_0" name="HLSQ_FS_CNTL_0" variants="A7XX-" usage="rp_blit"/> - <reg32 offset="0xa9c7" name="HLSQ_CONTROL_1_REG" low="0" high="2" variants="A7XX-" usage="rp_blit"> + <reg32 offset="0xb984" type="a6xx_sp_reg_prog_id_1" name="SP_REG_PROG_ID_1" variants="A6XX" usage="rp_blit"/> + <reg32 offset="0xb985" type="a6xx_sp_reg_prog_id_2" name="SP_REG_PROG_ID_2" variants="A6XX" usage="rp_blit"/> + <reg32 offset="0xb986" type="a6xx_sp_reg_prog_id_3" name="SP_REG_PROG_ID_3" variants="A6XX" usage="rp_blit"/> + <reg32 offset="0xb987" name="SP_CS_CONST_CONFIG" type="a6xx_xs_const_config" variants="A6XX" usage="cmd"/> + <reg32 offset="0xa9c6" type="a6xx_sp_ps_wave_cntl" name="SP_PS_WAVE_CNTL" variants="A7XX-" usage="rp_blit"/> + <reg32 offset="0xa9c7" name="SP_LB_PARAM_LIMIT" low="0" high="2" variants="A7XX-" usage="rp_blit"> <bitfield name="PRIMALLOCTHRESHOLD" low="0" high="2" type="uint"/> </reg32> - <reg32 offset="0xa9c8" name="HLSQ_CONTROL_2_REG" variants="A7XX-" usage="rp_blit"> + <reg32 offset="0xa9c8" name="SP_REG_PROG_ID_0" variants="A7XX-" usage="rp_blit"> <bitfield name="FACEREGID" low="0" high="7" type="a3xx_regid"/> <!-- SAMPLEID is loaded into a half-precision register: --> <bitfield name="SAMPLEID" low="8" high="15" type="a3xx_regid"/> <bitfield name="SAMPLEMASK" low="16" high="23" type="a3xx_regid"/> <bitfield name="CENTERRHW" low="24" high="31" type="a3xx_regid"/> </reg32> - <reg32 offset="0xa9c9" type="a6xx_hlsq_control_3_reg" name="HLSQ_CONTROL_3_REG" variants="A7XX-" usage="rp_blit"/> - <reg32 offset="0xa9ca" type="a6xx_hlsq_control_4_reg" name="HLSQ_CONTROL_4_REG" variants="A7XX-" usage="rp_blit"/> - <reg32 offset="0xa9cb" type="a6xx_hlsq_control_5_reg" name="HLSQ_CONTROL_5_REG" variants="A7XX-" usage="rp_blit"/> - <reg32 offset="0xa9cd" name="HLSQ_CS_CNTL" type="a6xx_hlsq_xs_cntl" variants="A7XX-" usage="cmd"/> + <reg32 offset="0xa9c9" type="a6xx_sp_reg_prog_id_1" name="SP_REG_PROG_ID_1" variants="A7XX-" usage="rp_blit"/> + <reg32 offset="0xa9ca" type="a6xx_sp_reg_prog_id_2" name="SP_REG_PROG_ID_2" variants="A7XX-" usage="rp_blit"/> + <reg32 offset="0xa9cb" type="a6xx_sp_reg_prog_id_3" name="SP_REG_PROG_ID_3" variants="A7XX-" usage="rp_blit"/> + <reg32 offset="0xa9cd" name="SP_CS_CONST_CONFIG" type="a6xx_xs_const_config" variants="A7XX-" usage="cmd"/> <!-- TODO: what does KERNELDIM do exactly (blob sets it differently from turnip) --> - <reg32 offset="0xb990" name="HLSQ_CS_NDRANGE_0" variants="A6XX" usage="rp_blit"> + <reg32 offset="0xb990" name="SP_CS_NDRANGE_0" variants="A6XX" usage="rp_blit"> <bitfield name="KERNELDIM" low="0" high="1" type="uint"/> <!-- localsize is value minus one: --> <bitfield name="LOCALSIZEX" low="2" high="11" type="uint"/> <bitfield name="LOCALSIZEY" low="12" high="21" type="uint"/> <bitfield name="LOCALSIZEZ" low="22" high="31" type="uint"/> </reg32> - <reg32 offset="0xb991" name="HLSQ_CS_NDRANGE_1" variants="A6XX" usage="rp_blit"> + <reg32 offset="0xb991" name="SP_CS_NDRANGE_1" variants="A6XX" usage="rp_blit"> <bitfield name="GLOBALSIZE_X" low="0" high="31" type="uint"/> </reg32> - <reg32 offset="0xb992" name="HLSQ_CS_NDRANGE_2" variants="A6XX" usage="rp_blit"> + <reg32 offset="0xb992" name="SP_CS_NDRANGE_2" variants="A6XX" usage="rp_blit"> <bitfield name="GLOBALOFF_X" low="0" high="31" type="uint"/> </reg32> - <reg32 offset="0xb993" name="HLSQ_CS_NDRANGE_3" variants="A6XX" usage="rp_blit"> + <reg32 offset="0xb993" name="SP_CS_NDRANGE_3" variants="A6XX" usage="rp_blit"> <bitfield name="GLOBALSIZE_Y" low="0" high="31" type="uint"/> </reg32> - <reg32 offset="0xb994" name="HLSQ_CS_NDRANGE_4" variants="A6XX" usage="rp_blit"> + <reg32 offset="0xb994" name="SP_CS_NDRANGE_4" variants="A6XX" usage="rp_blit"> <bitfield name="GLOBALOFF_Y" low="0" high="31" type="uint"/> </reg32> - <reg32 offset="0xb995" name="HLSQ_CS_NDRANGE_5" variants="A6XX" usage="rp_blit"> + <reg32 offset="0xb995" name="SP_CS_NDRANGE_5" variants="A6XX" usage="rp_blit"> <bitfield name="GLOBALSIZE_Z" low="0" high="31" type="uint"/> </reg32> - <reg32 offset="0xb996" name="HLSQ_CS_NDRANGE_6" variants="A6XX" usage="rp_blit"> + <reg32 offset="0xb996" name="SP_CS_NDRANGE_6" variants="A6XX" usage="rp_blit"> <bitfield name="GLOBALOFF_Z" low="0" high="31" type="uint"/> </reg32> - <reg32 offset="0xb997" name="HLSQ_CS_CNTL_0" variants="A6XX" usage="rp_blit"> + <reg32 offset="0xb997" name="SP_CS_CONST_CONFIG_0" variants="A6XX" usage="rp_blit"> <!-- these are all vec3. first 3 need to be high regs - WGSIZECONSTID is the local size (from HLSQ_CS_NDRANGE_0) + WGSIZECONSTID is the local size (from SP_CS_NDRANGE_0) WGOFFSETCONSTID is WGIDCONSTID*WGSIZECONSTID --> <bitfield name="WGIDCONSTID" low="0" high="7" type="a3xx_regid"/> @@ -5557,7 +3454,7 @@ to upconvert to 32b float internally? <bitfield name="WGOFFSETCONSTID" low="16" high="23" type="a3xx_regid"/> <bitfield name="LOCALIDREGID" low="24" high="31" type="a3xx_regid"/> </reg32> - <reg32 offset="0xb998" name="HLSQ_CS_CNTL_1" variants="A6XX" usage="rp_blit"> + <reg32 offset="0xb998" name="SP_CS_WGE_CNTL" variants="A6XX" usage="rp_blit"> <!-- gl_LocalInvocationIndex --> <bitfield name="LINEARLOCALIDREGID" low="0" high="7" type="a3xx_regid"/> <!-- a650 has 6 "SP cores" (but 3 "SP"). this makes it use only @@ -5569,40 +3466,40 @@ to upconvert to 32b float internally? <bitfield name="THREADSIZE_SCALAR" pos="10" type="boolean"/> </reg32> <!--note: vulkan blob doesn't use these --> - <reg32 offset="0xb999" name="HLSQ_CS_KERNEL_GROUP_X" variants="A6XX" usage="rp_blit"/> - <reg32 offset="0xb99a" name="HLSQ_CS_KERNEL_GROUP_Y" variants="A6XX" usage="rp_blit"/> - <reg32 offset="0xb99b" name="HLSQ_CS_KERNEL_GROUP_Z" variants="A6XX" usage="rp_blit"/> + <reg32 offset="0xb999" name="SP_CS_KERNEL_GROUP_X" variants="A6XX" usage="rp_blit"/> + <reg32 offset="0xb99a" name="SP_CS_KERNEL_GROUP_Y" variants="A6XX" usage="rp_blit"/> + <reg32 offset="0xb99b" name="SP_CS_KERNEL_GROUP_Z" variants="A6XX" usage="rp_blit"/> <!-- TODO: what does KERNELDIM do exactly (blob sets it differently from turnip) --> - <reg32 offset="0xa9d4" name="HLSQ_CS_NDRANGE_0" variants="A7XX-" usage="rp_blit"> + <reg32 offset="0xa9d4" name="SP_CS_NDRANGE_0" variants="A7XX-" usage="rp_blit"> <bitfield name="KERNELDIM" low="0" high="1" type="uint"/> <!-- localsize is value minus one: --> <bitfield name="LOCALSIZEX" low="2" high="11" type="uint"/> <bitfield name="LOCALSIZEY" low="12" high="21" type="uint"/> <bitfield name="LOCALSIZEZ" low="22" high="31" type="uint"/> </reg32> - <reg32 offset="0xa9d5" name="HLSQ_CS_NDRANGE_1" variants="A7XX-" usage="rp_blit"> + <reg32 offset="0xa9d5" name="SP_CS_NDRANGE_1" variants="A7XX-" usage="rp_blit"> <bitfield name="GLOBALSIZE_X" low="0" high="31" type="uint"/> </reg32> - <reg32 offset="0xa9d6" name="HLSQ_CS_NDRANGE_2" variants="A7XX-" usage="rp_blit"> + <reg32 offset="0xa9d6" name="SP_CS_NDRANGE_2" variants="A7XX-" usage="rp_blit"> <bitfield name="GLOBALOFF_X" low="0" high="31" type="uint"/> </reg32> - <reg32 offset="0xa9d7" name="HLSQ_CS_NDRANGE_3" variants="A7XX-" usage="rp_blit"> + <reg32 offset="0xa9d7" name="SP_CS_NDRANGE_3" variants="A7XX-" usage="rp_blit"> <bitfield name="GLOBALSIZE_Y" low="0" high="31" type="uint"/> </reg32> - <reg32 offset="0xa9d8" name="HLSQ_CS_NDRANGE_4" variants="A7XX-" usage="rp_blit"> + <reg32 offset="0xa9d8" name="SP_CS_NDRANGE_4" variants="A7XX-" usage="rp_blit"> <bitfield name="GLOBALOFF_Y" low="0" high="31" type="uint"/> </reg32> - <reg32 offset="0xa9d9" name="HLSQ_CS_NDRANGE_5" variants="A7XX-" usage="rp_blit"> + <reg32 offset="0xa9d9" name="SP_CS_NDRANGE_5" variants="A7XX-" usage="rp_blit"> <bitfield name="GLOBALSIZE_Z" low="0" high="31" type="uint"/> </reg32> - <reg32 offset="0xa9da" name="HLSQ_CS_NDRANGE_6" variants="A7XX-" usage="rp_blit"> + <reg32 offset="0xa9da" name="SP_CS_NDRANGE_6" variants="A7XX-" usage="rp_blit"> <bitfield name="GLOBALOFF_Z" low="0" high="31" type="uint"/> </reg32> <!--note: vulkan blob doesn't use these --> - <reg32 offset="0xa9dc" name="HLSQ_CS_KERNEL_GROUP_X" variants="A7XX-" usage="rp_blit"/> - <reg32 offset="0xa9dd" name="HLSQ_CS_KERNEL_GROUP_Y" variants="A7XX-" usage="rp_blit"/> - <reg32 offset="0xa9de" name="HLSQ_CS_KERNEL_GROUP_Z" variants="A7XX-" usage="rp_blit"/> + <reg32 offset="0xa9dc" name="SP_CS_KERNEL_GROUP_X" variants="A7XX-" usage="rp_blit"/> + <reg32 offset="0xa9dd" name="SP_CS_KERNEL_GROUP_Y" variants="A7XX-" usage="rp_blit"/> + <reg32 offset="0xa9de" name="SP_CS_KERNEL_GROUP_Z" variants="A7XX-" usage="rp_blit"/> <enum name="a7xx_cs_yalign"> <value name="CS_YALIGN_1" value="8"/> @@ -5611,19 +3508,29 @@ to upconvert to 32b float internally? <value name="CS_YALIGN_8" value="1"/> </enum> - <reg32 offset="0xa9db" name="HLSQ_CS_CNTL_1" variants="A7XX-" usage="rp_blit"> + <reg32 offset="0xa9db" name="SP_CS_WGE_CNTL" variants="A7XX-" usage="rp_blit"> <!-- gl_LocalInvocationIndex --> <bitfield name="LINEARLOCALIDREGID" low="0" high="7" type="a3xx_regid"/> <!-- Must match SP_CS_CTRL --> <bitfield name="THREADSIZE" pos="9" type="a6xx_threadsize"/> - <bitfield name="UNK11" pos="11" type="boolean"/> - <bitfield name="UNK22" pos="22" type="boolean"/> - <bitfield name="UNK26" pos="26" type="boolean"/> - <bitfield name="YALIGN" low="27" high="30" type="a7xx_cs_yalign"/> + <doc> + When this bit is enabled, the dispatch order interleaves + the z coordinate instead of launching all workgroups + with z=0, then all with z=1 and so on. + </doc> + <bitfield name="WORKGROUPRASTORDERZFIRSTEN" pos="11" type="boolean"/> + <doc> + When both fields are non-0 then the dispatcher uses + these tile sizes to launch workgroups in a tiled manner + when the x and y workgroup counts are + both more than 1. + </doc> + <bitfield name="WGTILEWIDTH" low="20" high="25"/> + <bitfield name="WGTILEHEIGHT" low="26" high="31"/> </reg32> - <reg32 offset="0xa9df" name="HLSQ_CS_LOCAL_SIZE" variants="A7XX-" usage="cmd"> - <!-- localsize is value minus one: --> + <reg32 offset="0xa9df" name="SP_CS_NDRANGE_7" variants="A7XX-" usage="cmd"> + <!-- The size of the last workgroup. localsize is value minus one: --> <bitfield name="LOCALSIZEX" low="2" high="11" type="uint"/> <bitfield name="LOCALSIZEY" low="12" high="21" type="uint"/> <bitfield name="LOCALSIZEZ" low="22" high="31" type="uint"/> @@ -5641,29 +3548,27 @@ to upconvert to 32b float internally? </reg64> </array> - <!-- new in a6xx gen4, mirror of SP_CS_UNKNOWN_A9B1? --> - <reg32 offset="0xb9d0" name="HLSQ_CS_UNKNOWN_B9D0" variants="A6XX" usage="cmd"> + <!-- new in a6xx gen4, mirror of SP_CS_CNTL_1? --> + <reg32 offset="0xb9d0" name="HLSQ_CS_CTRL_REG1" variants="A6XX" usage="cmd"> <bitfield name="SHARED_SIZE" low="0" high="4" type="uint"/> - <bitfield name="UNK5" pos="5" type="boolean"/> - <!-- always 1 ? --> - <bitfield name="UNK6" pos="6" type="boolean"/> + <bitfield name="CONSTANTRAMMODE" low="5" high="6" type="a6xx_const_ram_mode"/> </reg32> - <reg32 offset="0xbb00" name="HLSQ_DRAW_CMD" variants="A6XX"> + <reg32 offset="0xbb00" name="SP_DRAW_INITIATOR" variants="A6XX"> <bitfield name="STATE_ID" low="0" high="7"/> </reg32> - <reg32 offset="0xbb01" name="HLSQ_DISPATCH_CMD" variants="A6XX"> + <reg32 offset="0xbb01" name="SP_KERNEL_INITIATOR" variants="A6XX"> <bitfield name="STATE_ID" low="0" high="7"/> </reg32> - <reg32 offset="0xbb02" name="HLSQ_EVENT_CMD" variants="A6XX"> + <reg32 offset="0xbb02" name="SP_EVENT_INITIATOR" variants="A6XX"> <!-- I think only the low bit is actually used? --> <bitfield name="STATE_ID" low="16" high="23"/> <bitfield name="EVENT" low="0" high="6" type="vgt_event_type"/> </reg32> - <reg32 offset="0xbb08" name="HLSQ_INVALIDATE_CMD" variants="A6XX" usage="cmd"> + <reg32 offset="0xbb08" name="SP_UPDATE_CNTL" variants="A6XX" usage="cmd"> <doc> This register clears pending loads queued up by CP_LOAD_STATE6. Each bit resets a particular kind(s) of @@ -5678,8 +3583,8 @@ to upconvert to 32b float internally? <bitfield name="FS_STATE" pos="4" type="boolean"/> <bitfield name="CS_STATE" pos="5" type="boolean"/> - <bitfield name="CS_IBO" pos="6" type="boolean"/> - <bitfield name="GFX_IBO" pos="7" type="boolean"/> + <bitfield name="CS_UAV" pos="6" type="boolean"/> + <bitfield name="GFX_UAV" pos="7" type="boolean"/> <!-- Note: these only do something when HLSQ_SHARED_CONSTS is set to 1 --> <bitfield name="CS_SHARED_CONST" pos="19" type="boolean"/> @@ -5690,20 +3595,20 @@ to upconvert to 32b float internally? <bitfield name="GFX_BINDLESS" low="14" high="18" type="hex"/> </reg32> - <reg32 offset="0xab1c" name="HLSQ_DRAW_CMD" variants="A7XX-"> + <reg32 offset="0xab1c" name="SP_DRAW_INITIATOR" variants="A7XX-"> <bitfield name="STATE_ID" low="0" high="7"/> </reg32> - <reg32 offset="0xab1d" name="HLSQ_DISPATCH_CMD" variants="A7XX-"> + <reg32 offset="0xab1d" name="SP_KERNEL_INITIATOR" variants="A7XX-"> <bitfield name="STATE_ID" low="0" high="7"/> </reg32> - <reg32 offset="0xab1e" name="HLSQ_EVENT_CMD" variants="A7XX-"> + <reg32 offset="0xab1e" name="SP_EVENT_INITIATOR" variants="A7XX-"> <bitfield name="STATE_ID" low="16" high="23"/> <bitfield name="EVENT" low="0" high="6" type="vgt_event_type"/> </reg32> - <reg32 offset="0xab1f" name="HLSQ_INVALIDATE_CMD" variants="A7XX-" usage="cmd"> + <reg32 offset="0xab1f" name="SP_UPDATE_CNTL" variants="A7XX-" usage="cmd"> <doc> This register clears pending loads queued up by CP_LOAD_STATE6. Each bit resets a particular kind(s) of @@ -5718,18 +3623,18 @@ to upconvert to 32b float internally? <bitfield name="FS_STATE" pos="4" type="boolean"/> <bitfield name="CS_STATE" pos="5" type="boolean"/> - <bitfield name="CS_IBO" pos="6" type="boolean"/> - <bitfield name="GFX_IBO" pos="7" type="boolean"/> + <bitfield name="CS_UAV" pos="6" type="boolean"/> + <bitfield name="GFX_UAV" pos="7" type="boolean"/> <!-- SS6_BINDLESS: one bit per bindless base --> <bitfield name="CS_BINDLESS" low="9" high="16" type="hex"/> <bitfield name="GFX_BINDLESS" low="17" high="24" type="hex"/> </reg32> - <reg32 offset="0xbb10" name="HLSQ_FS_CNTL" type="a6xx_hlsq_xs_cntl" variants="A6XX" usage="rp_blit"/> - <reg32 offset="0xab03" name="HLSQ_FS_CNTL" type="a6xx_hlsq_xs_cntl" variants="A7XX-" usage="rp_blit"/> + <reg32 offset="0xbb10" name="SP_PS_CONST_CONFIG" type="a6xx_xs_const_config" variants="A6XX" usage="rp_blit"/> + <reg32 offset="0xab03" name="SP_PS_CONST_CONFIG" type="a6xx_xs_const_config" variants="A7XX-" usage="rp_blit"/> - <array offset="0xab40" name="HLSQ_SHARED_CONSTS_IMM" stride="1" length="64" variants="A7XX-"/> + <array offset="0xab40" name="SP_SHARED_CONSTANT_GFX_0" stride="1" length="64" variants="A7XX-"/> <reg32 offset="0xbb11" name="HLSQ_SHARED_CONSTS" variants="A6XX" usage="cmd"> <doc> @@ -5738,7 +3643,7 @@ to upconvert to 32b float internally? const pool and 16 in the geometry const pool although only 8 are actually used (why?) and they are mapped to c504-c511 in each stage. Both VS and FS shared consts - are written using ST6_CONSTANTS/SB6_IBO, so that both + are written using ST6_CONSTANTS/SB6_UAV, so that both the geometry and FS shared consts can be written at once by using CP_LOAD_STATE6 rather than CP_LOAD_STATE6_FRAG/CP_LOAD_STATE6_GEOM. In addition @@ -5747,13 +3652,13 @@ to upconvert to 32b float internally? There is also a separate shared constant pool for CS, which is loaded through CP_LOAD_STATE6_FRAG with - ST6_UBO/ST6_IBO. However the only real difference for CS + ST6_UBO/ST6_UAV. However the only real difference for CS is the dword units. </doc> <bitfield name="ENABLE" pos="0" type="boolean"/> </reg32> - <!-- mirror of SP_BINDLESS_BASE --> + <!-- mirror of SP_GFX_BINDLESS_BASE --> <array offset="0xbb20" name="HLSQ_BINDLESS_BASE" stride="2" length="5" variants="A6XX" usage="cmd"> <reg64 offset="0" name="DESCRIPTOR"> <bitfield name="DESC_SIZE" low="0" high="1" type="a6xx_bindless_descriptor_size"/> @@ -5788,10 +3693,10 @@ to upconvert to 32b float internally? sequence. The sequence used internally for an event looks like: - write EVENT_CMD pipe register - write CP_EVENT_START - - write HLSQ_EVENT_CMD with event or HLSQ_DRAW_CMD - - write PC_EVENT_CMD with event or PC_DRAW_CMD - - write HLSQ_EVENT_CMD(CONTEXT_DONE) - - write PC_EVENT_CMD(CONTEXT_DONE) + - write SP_EVENT_INITIATOR with event or SP_DRAW_INITIATOR + - write PC_EVENT_INITIATOR with event or PC_DRAW_INITIATOR + - write SP_EVENT_INITIATOR(CONTEXT_DONE) + - write PC_EVENT_INITIATOR(CONTEXT_DONE) - write CP_EVENT_END Writing to CP_EVENT_END seems to actually trigger the context roll --> @@ -5809,193 +3714,6 @@ to upconvert to 32b float internally? </reg32> </domain> -<!-- Seems basically the same as a5xx, maybe move to common.xml.. --> -<domain name="A6XX_TEX_SAMP" width="32"> - <doc>Texture sampler dwords</doc> - <enum name="a6xx_tex_filter"> <!-- same as a4xx? --> - <value name="A6XX_TEX_NEAREST" value="0"/> - <value name="A6XX_TEX_LINEAR" value="1"/> - <value name="A6XX_TEX_ANISO" value="2"/> - <value name="A6XX_TEX_CUBIC" value="3"/> <!-- a650 only --> - </enum> - <enum name="a6xx_tex_clamp"> <!-- same as a4xx? --> - <value name="A6XX_TEX_REPEAT" value="0"/> - <value name="A6XX_TEX_CLAMP_TO_EDGE" value="1"/> - <value name="A6XX_TEX_MIRROR_REPEAT" value="2"/> - <value name="A6XX_TEX_CLAMP_TO_BORDER" value="3"/> - <value name="A6XX_TEX_MIRROR_CLAMP" value="4"/> - </enum> - <enum name="a6xx_tex_aniso"> <!-- same as a4xx? --> - <value name="A6XX_TEX_ANISO_1" value="0"/> - <value name="A6XX_TEX_ANISO_2" value="1"/> - <value name="A6XX_TEX_ANISO_4" value="2"/> - <value name="A6XX_TEX_ANISO_8" value="3"/> - <value name="A6XX_TEX_ANISO_16" value="4"/> - </enum> - <enum name="a6xx_reduction_mode"> - <value name="A6XX_REDUCTION_MODE_AVERAGE" value="0"/> - <value name="A6XX_REDUCTION_MODE_MIN" value="1"/> - <value name="A6XX_REDUCTION_MODE_MAX" value="2"/> - </enum> - - <reg32 offset="0" name="0"> - <bitfield name="MIPFILTER_LINEAR_NEAR" pos="0" type="boolean"/> - <bitfield name="XY_MAG" low="1" high="2" type="a6xx_tex_filter"/> - <bitfield name="XY_MIN" low="3" high="4" type="a6xx_tex_filter"/> - <bitfield name="WRAP_S" low="5" high="7" type="a6xx_tex_clamp"/> - <bitfield name="WRAP_T" low="8" high="10" type="a6xx_tex_clamp"/> - <bitfield name="WRAP_R" low="11" high="13" type="a6xx_tex_clamp"/> - <bitfield name="ANISO" low="14" high="16" type="a6xx_tex_aniso"/> - <bitfield name="LOD_BIAS" low="19" high="31" type="fixed" radix="8"/><!-- no idea how many bits for real --> - </reg32> - <reg32 offset="1" name="1"> - <bitfield name="CLAMPENABLE" pos="0" type="boolean"> - <doc> - clamp result to [0, 1] if the format is unorm or - [-1, 1] if the format is snorm, *after* - filtering. Has no effect for other formats. - </doc> - </bitfield> - <bitfield name="COMPARE_FUNC" low="1" high="3" type="adreno_compare_func"/> - <bitfield name="CUBEMAPSEAMLESSFILTOFF" pos="4" type="boolean"/> - <bitfield name="UNNORM_COORDS" pos="5" type="boolean"/> - <bitfield name="MIPFILTER_LINEAR_FAR" pos="6" type="boolean"/> - <bitfield name="MAX_LOD" low="8" high="19" type="ufixed" radix="8"/> - <bitfield name="MIN_LOD" low="20" high="31" type="ufixed" radix="8"/> - </reg32> - <reg32 offset="2" name="2"> - <bitfield name="REDUCTION_MODE" low="0" high="1" type="a6xx_reduction_mode"/> - <bitfield name="CHROMA_LINEAR" pos="5" type="boolean"/> - <bitfield name="BCOLOR" low="7" high="31"/> - </reg32> - <reg32 offset="3" name="3"/> -</domain> - -<domain name="A6XX_TEX_CONST" width="32" varset="chip"> - <doc>Texture constant dwords</doc> - <enum name="a6xx_tex_swiz"> <!-- same as a4xx? --> - <value name="A6XX_TEX_X" value="0"/> - <value name="A6XX_TEX_Y" value="1"/> - <value name="A6XX_TEX_Z" value="2"/> - <value name="A6XX_TEX_W" value="3"/> - <value name="A6XX_TEX_ZERO" value="4"/> - <value name="A6XX_TEX_ONE" value="5"/> - </enum> - <enum name="a6xx_tex_type"> <!-- same as a4xx? --> - <value name="A6XX_TEX_1D" value="0"/> - <value name="A6XX_TEX_2D" value="1"/> - <value name="A6XX_TEX_CUBE" value="2"/> - <value name="A6XX_TEX_3D" value="3"/> - <value name="A6XX_TEX_BUFFER" value="4"/> - </enum> - <reg32 offset="0" name="0"> - <bitfield name="TILE_MODE" low="0" high="1" type="a6xx_tile_mode"/> - <bitfield name="SRGB" pos="2" type="boolean"/> - <bitfield name="SWIZ_X" low="4" high="6" type="a6xx_tex_swiz"/> - <bitfield name="SWIZ_Y" low="7" high="9" type="a6xx_tex_swiz"/> - <bitfield name="SWIZ_Z" low="10" high="12" type="a6xx_tex_swiz"/> - <bitfield name="SWIZ_W" low="13" high="15" type="a6xx_tex_swiz"/> - <bitfield name="MIPLVLS" low="16" high="19" type="uint"/> - <!-- overlaps with MIPLVLS --> - <bitfield name="CHROMA_MIDPOINT_X" pos="16" type="boolean"/> - <bitfield name="CHROMA_MIDPOINT_Y" pos="18" type="boolean"/> - <bitfield name="SAMPLES" low="20" high="21" type="a3xx_msaa_samples"/> - <bitfield name="FMT" low="22" high="29" type="a6xx_format"/> - <!-- - Why is the swap needed in addition to SWIZ_*? The swap - is performed before border color replacement, while the - swizzle is applied after after it. - --> - <bitfield name="SWAP" low="30" high="31" type="a3xx_color_swap"/> - </reg32> - <reg32 offset="1" name="1"> - <bitfield name="WIDTH" low="0" high="14" type="uint"/> - <bitfield name="HEIGHT" low="15" high="29" type="uint"/> - <bitfield name="MUTABLEEN" pos="31" type="boolean" variants="A7XX-"/> - </reg32> - <reg32 offset="2" name="2"> - <!-- - These fields overlap PITCH, and are used instead of - PITCH/PITCHALIGN when TYPE is A6XX_TEX_BUFFER. - --> - <doc> probably for D3D structured UAVs, normally set to 1 </doc> - <bitfield name="STRUCTSIZETEXELS" low="4" high="15" type="uint"/> - <bitfield name="STARTOFFSETTEXELS" low="16" high="21" type="uint"/> - - <!-- minimum pitch (for mipmap levels): log2(pitchalign / 64) --> - <bitfield name="PITCHALIGN" low="0" high="3" type="uint"/> - <doc>Pitch in bytes (so actually stride)</doc> - <bitfield name="PITCH" low="7" high="28" type="uint"/> - <bitfield name="TYPE" low="29" high="31" type="a6xx_tex_type"/> - </reg32> - <reg32 offset="3" name="3"> - <!-- - ARRAY_PITCH is basically LAYERSZ for the first mipmap level, and - for 3d textures (laid out mipmap level first) MIN_LAYERSZ is the - layer size at the point that it stops being reduced moving to - higher (smaller) mipmap levels - --> - <bitfield name="ARRAY_PITCH" low="0" high="22" shr="12" type="uint"/> - <bitfield name="MIN_LAYERSZ" low="23" high="26" shr="12"/> - <!-- - by default levels with w < 16 are linear - TILE_ALL makes all levels have tiling - seems required when using UBWC, since all levels have UBWC (can possibly be disabled?) - --> - <bitfield name="TILE_ALL" pos="27" type="boolean"/> - <bitfield name="FLAG" pos="28" type="boolean"/> - </reg32> - <!-- for 2-3 plane format, BASE is flag buffer address (if enabled) - the address of the non-flag base buffer is determined automatically, - and must follow the flag buffer - --> - <reg32 offset="4" name="4"> - <bitfield name="BASE_LO" low="5" high="31" shr="5"/> - </reg32> - <reg32 offset="5" name="5"> - <bitfield name="BASE_HI" low="0" high="16"/> - <bitfield name="DEPTH" low="17" high="29" type="uint"/> - </reg32> - <reg32 offset="6" name="6"> - <!-- overlaps with PLANE_PITCH --> - <bitfield name="MIN_LOD_CLAMP" low="0" high="11" type="ufixed" radix="8"/> - <!-- pitch for plane 2 / plane 3 --> - <bitfield name="PLANE_PITCH" low="8" high="31" type="uint"/> - </reg32> - <!-- 7/8 is plane 2 address for planar formats --> - <reg32 offset="7" name="7"> - <bitfield name="FLAG_LO" low="5" high="31" shr="5"/> - </reg32> - <reg32 offset="8" name="8"> - <bitfield name="FLAG_HI" low="0" high="16"/> - </reg32> - <!-- 9/10 is plane 3 address for planar formats --> - <reg32 offset="9" name="9"> - <bitfield name="FLAG_BUFFER_ARRAY_PITCH" low="0" high="16" shr="4" type="uint"/> - </reg32> - <reg32 offset="10" name="10"> - <bitfield name="FLAG_BUFFER_PITCH" low="0" high="6" shr="6" type="uint"/> - <!-- log2 size of the first level, required for mipmapping --> - <bitfield name="FLAG_BUFFER_LOGW" low="8" high="11" type="uint"/> - <bitfield name="FLAG_BUFFER_LOGH" low="12" high="15" type="uint"/> - </reg32> - <reg32 offset="11" name="11"/> - <reg32 offset="12" name="12"/> - <reg32 offset="13" name="13"/> - <reg32 offset="14" name="14"/> - <reg32 offset="15" name="15"/> -</domain> - -<domain name="A6XX_UBO" width="32"> - <reg32 offset="0" name="0"> - <bitfield name="BASE_LO" low="0" high="31"/> - </reg32> - <reg32 offset="1" name="1"> - <bitfield name="BASE_HI" low="0" high="16"/> - <bitfield name="SIZE" low="17" high="31"/> <!-- size in vec4 (4xDWORD) units --> - </reg32> -</domain> - <domain name="A6XX_PDC" width="32"> <reg32 offset="0x1140" name="GPU_ENABLE_PDC"/> <reg32 offset="0x1148" name="GPU_SEQ_START_ADDR"/> diff --git a/drivers/gpu/drm/msm/registers/adreno/a6xx_descriptors.xml b/drivers/gpu/drm/msm/registers/adreno/a6xx_descriptors.xml new file mode 100644 index 000000000000..307d43dda8a2 --- /dev/null +++ b/drivers/gpu/drm/msm/registers/adreno/a6xx_descriptors.xml @@ -0,0 +1,198 @@ +<?xml version="1.0" encoding="UTF-8"?> +<database xmlns="http://nouveau.freedesktop.org/" +xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" +xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> +<import file="freedreno_copyright.xml"/> +<import file="adreno/adreno_common.xml"/> +<import file="adreno/adreno_pm4.xml"/> +<import file="adreno/a6xx_enums.xml"/> + +<domain name="A6XX_TEX_SAMP" width="32"> + <doc>Texture sampler dwords</doc> + <enum name="a6xx_tex_filter"> <!-- same as a4xx? --> + <value name="A6XX_TEX_NEAREST" value="0"/> + <value name="A6XX_TEX_LINEAR" value="1"/> + <value name="A6XX_TEX_ANISO" value="2"/> + <value name="A6XX_TEX_CUBIC" value="3"/> <!-- a650 only --> + </enum> + <enum name="a6xx_tex_clamp"> <!-- same as a4xx? --> + <value name="A6XX_TEX_REPEAT" value="0"/> + <value name="A6XX_TEX_CLAMP_TO_EDGE" value="1"/> + <value name="A6XX_TEX_MIRROR_REPEAT" value="2"/> + <value name="A6XX_TEX_CLAMP_TO_BORDER" value="3"/> + <value name="A6XX_TEX_MIRROR_CLAMP" value="4"/> + </enum> + <enum name="a6xx_tex_aniso"> <!-- same as a4xx? --> + <value name="A6XX_TEX_ANISO_1" value="0"/> + <value name="A6XX_TEX_ANISO_2" value="1"/> + <value name="A6XX_TEX_ANISO_4" value="2"/> + <value name="A6XX_TEX_ANISO_8" value="3"/> + <value name="A6XX_TEX_ANISO_16" value="4"/> + </enum> + <enum name="a6xx_reduction_mode"> + <value name="A6XX_REDUCTION_MODE_AVERAGE" value="0"/> + <value name="A6XX_REDUCTION_MODE_MIN" value="1"/> + <value name="A6XX_REDUCTION_MODE_MAX" value="2"/> + </enum> + <enum name="a6xx_fast_border_color"> + <!-- R B G A --> + <value name="A6XX_BORDER_COLOR_0_0_0_0" value="0"/> + <value name="A6XX_BORDER_COLOR_0_0_0_1" value="1"/> + <value name="A6XX_BORDER_COLOR_1_1_1_0" value="2"/> + <value name="A6XX_BORDER_COLOR_1_1_1_1" value="3"/> + </enum> + + <reg32 offset="0" name="0"> + <bitfield name="MIPFILTER_LINEAR_NEAR" pos="0" type="boolean"/> + <bitfield name="XY_MAG" low="1" high="2" type="a6xx_tex_filter"/> + <bitfield name="XY_MIN" low="3" high="4" type="a6xx_tex_filter"/> + <bitfield name="WRAP_S" low="5" high="7" type="a6xx_tex_clamp"/> + <bitfield name="WRAP_T" low="8" high="10" type="a6xx_tex_clamp"/> + <bitfield name="WRAP_R" low="11" high="13" type="a6xx_tex_clamp"/> + <bitfield name="ANISO" low="14" high="16" type="a6xx_tex_aniso"/> + <bitfield name="LOD_BIAS" low="19" high="31" type="fixed" radix="8"/><!-- no idea how many bits for real --> + </reg32> + <reg32 offset="1" name="1"> + <bitfield name="CLAMPENABLE" pos="0" type="boolean"> + <doc> + clamp result to [0, 1] if the format is unorm or + [-1, 1] if the format is snorm, *after* + filtering. Has no effect for other formats. + </doc> + </bitfield> + <bitfield name="COMPARE_FUNC" low="1" high="3" type="adreno_compare_func"/> + <bitfield name="CUBEMAPSEAMLESSFILTOFF" pos="4" type="boolean"/> + <bitfield name="UNNORM_COORDS" pos="5" type="boolean"/> + <bitfield name="MIPFILTER_LINEAR_FAR" pos="6" type="boolean"/> + <bitfield name="MAX_LOD" low="8" high="19" type="ufixed" radix="8"/> + <bitfield name="MIN_LOD" low="20" high="31" type="ufixed" radix="8"/> + </reg32> + <reg32 offset="2" name="2"> + <bitfield name="REDUCTION_MODE" low="0" high="1" type="a6xx_reduction_mode"/> + <bitfield name="FASTBORDERCOLOR" low="2" high="3" type="a6xx_fast_border_color"/> + <bitfield name="FASTBORDERCOLOREN" pos="4" type="boolean"/> + <bitfield name="CHROMA_LINEAR" pos="5" type="boolean"/> + <bitfield name="BCOLOR" low="7" high="31"/> + </reg32> + <reg32 offset="3" name="3"/> +</domain> + +<domain name="A6XX_TEX_CONST" width="32" varset="chip"> + <doc>Texture constant dwords</doc> + <enum name="a6xx_tex_swiz"> <!-- same as a4xx? --> + <value name="A6XX_TEX_X" value="0"/> + <value name="A6XX_TEX_Y" value="1"/> + <value name="A6XX_TEX_Z" value="2"/> + <value name="A6XX_TEX_W" value="3"/> + <value name="A6XX_TEX_ZERO" value="4"/> + <value name="A6XX_TEX_ONE" value="5"/> + </enum> + <reg32 offset="0" name="0"> + <bitfield name="TILE_MODE" low="0" high="1" type="a6xx_tile_mode"/> + <bitfield name="SRGB" pos="2" type="boolean"/> + <bitfield name="SWIZ_X" low="4" high="6" type="a6xx_tex_swiz"/> + <bitfield name="SWIZ_Y" low="7" high="9" type="a6xx_tex_swiz"/> + <bitfield name="SWIZ_Z" low="10" high="12" type="a6xx_tex_swiz"/> + <bitfield name="SWIZ_W" low="13" high="15" type="a6xx_tex_swiz"/> + <bitfield name="MIPLVLS" low="16" high="19" type="uint"/> + <!-- overlaps with MIPLVLS --> + <bitfield name="CHROMA_MIDPOINT_X" pos="16" type="boolean"/> + <bitfield name="CHROMA_MIDPOINT_Y" pos="18" type="boolean"/> + <bitfield name="SAMPLES" low="20" high="21" type="a3xx_msaa_samples"/> + <bitfield name="FMT" low="22" high="29" type="a6xx_format"/> + <!-- + Why is the swap needed in addition to SWIZ_*? The swap + is performed before border color replacement, while the + swizzle is applied after after it. + --> + <bitfield name="SWAP" low="30" high="31" type="a3xx_color_swap"/> + </reg32> + <reg32 offset="1" name="1"> + <bitfield name="WIDTH" low="0" high="14" type="uint"/> + <bitfield name="HEIGHT" low="15" high="29" type="uint"/> + <bitfield name="MUTABLEEN" pos="31" type="boolean" variants="A7XX-"/> + </reg32> + <reg32 offset="2" name="2"> + <!-- + These fields overlap PITCH, and are used instead of + PITCH/PITCHALIGN when TYPE is A6XX_TEX_BUFFER. + --> + <doc> probably for D3D structured UAVs, normally set to 1 </doc> + <bitfield name="STRUCTSIZETEXELS" low="4" high="15" type="uint"/> + <bitfield name="STARTOFFSETTEXELS" low="16" high="21" type="uint"/> + + <!-- minimum pitch (for mipmap levels): log2(pitchalign / 64) --> + <bitfield name="PITCHALIGN" low="0" high="3" type="uint"/> + <doc>Pitch in bytes (so actually stride)</doc> + <bitfield name="PITCH" low="7" high="28" type="uint"/> + <bitfield name="TYPE" low="29" high="31" type="a6xx_tex_type"/> + </reg32> + <reg32 offset="3" name="3"> + <!-- + ARRAY_PITCH is basically LAYERSZ for the first mipmap level, and + for 3d textures (laid out mipmap level first) MIN_LAYERSZ is the + layer size at the point that it stops being reduced moving to + higher (smaller) mipmap levels + --> + <bitfield name="ARRAY_PITCH" low="0" high="22" shr="12" type="uint"/> + <bitfield name="MIN_LAYERSZ" low="23" high="26" shr="12"/> + <!-- + by default levels with w < 16 are linear + TILE_ALL makes all levels have tiling + seems required when using UBWC, since all levels have UBWC (can possibly be disabled?) + --> + <bitfield name="TILE_ALL" pos="27" type="boolean"/> + <bitfield name="FLAG" pos="28" type="boolean"/> + </reg32> + <!-- for 2-3 plane format, BASE is flag buffer address (if enabled) + the address of the non-flag base buffer is determined automatically, + and must follow the flag buffer + --> + <reg32 offset="4" name="4"> + <bitfield name="BASE_LO" low="5" high="31" shr="5"/> + </reg32> + <reg32 offset="5" name="5"> + <bitfield name="BASE_HI" low="0" high="16"/> + <bitfield name="DEPTH" low="17" high="29" type="uint"/> + </reg32> + <reg32 offset="6" name="6"> + <!-- overlaps with PLANE_PITCH --> + <bitfield name="MIN_LOD_CLAMP" low="0" high="11" type="ufixed" radix="8"/> + <!-- pitch for plane 2 / plane 3 --> + <bitfield name="PLANE_PITCH" low="8" high="31" type="uint"/> + </reg32> + <!-- 7/8 is plane 2 address for planar formats --> + <reg32 offset="7" name="7"> + <bitfield name="FLAG_LO" low="5" high="31" shr="5"/> + </reg32> + <reg32 offset="8" name="8"> + <bitfield name="FLAG_HI" low="0" high="16"/> + </reg32> + <!-- 9/10 is plane 3 address for planar formats --> + <reg32 offset="9" name="9"> + <bitfield name="FLAG_BUFFER_ARRAY_PITCH" low="0" high="16" shr="4" type="uint"/> + </reg32> + <reg32 offset="10" name="10"> + <bitfield name="FLAG_BUFFER_PITCH" low="0" high="6" shr="6" type="uint"/> + <!-- log2 size of the first level, required for mipmapping --> + <bitfield name="FLAG_BUFFER_LOGW" low="8" high="11" type="uint"/> + <bitfield name="FLAG_BUFFER_LOGH" low="12" high="15" type="uint"/> + </reg32> + <reg32 offset="11" name="11"/> + <reg32 offset="12" name="12"/> + <reg32 offset="13" name="13"/> + <reg32 offset="14" name="14"/> + <reg32 offset="15" name="15"/> +</domain> + +<domain name="A6XX_UBO" width="32"> + <reg32 offset="0" name="0"> + <bitfield name="BASE_LO" low="0" high="31"/> + </reg32> + <reg32 offset="1" name="1"> + <bitfield name="BASE_HI" low="0" high="16"/> + <bitfield name="SIZE" low="17" high="31"/> <!-- size in vec4 (4xDWORD) units --> + </reg32> +</domain> + +</database> diff --git a/drivers/gpu/drm/msm/registers/adreno/a6xx_enums.xml b/drivers/gpu/drm/msm/registers/adreno/a6xx_enums.xml new file mode 100644 index 000000000000..665539b098c6 --- /dev/null +++ b/drivers/gpu/drm/msm/registers/adreno/a6xx_enums.xml @@ -0,0 +1,383 @@ +<?xml version="1.0" encoding="UTF-8"?> +<database xmlns="http://nouveau.freedesktop.org/" +xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" +xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> +<import file="freedreno_copyright.xml"/> +<import file="adreno/adreno_common.xml"/> +<import file="adreno/adreno_pm4.xml"/> + +<enum name="a6xx_tile_mode"> + <value name="TILE6_LINEAR" value="0"/> + <value name="TILE6_2" value="2"/> + <value name="TILE6_3" value="3"/> +</enum> + +<enum name="a6xx_format"> + <value value="0x02" name="FMT6_A8_UNORM"/> + <value value="0x03" name="FMT6_8_UNORM"/> + <value value="0x04" name="FMT6_8_SNORM"/> + <value value="0x05" name="FMT6_8_UINT"/> + <value value="0x06" name="FMT6_8_SINT"/> + + <value value="0x08" name="FMT6_4_4_4_4_UNORM"/> + <value value="0x0a" name="FMT6_5_5_5_1_UNORM"/> + <value value="0x0c" name="FMT6_1_5_5_5_UNORM"/> <!-- read only --> + <value value="0x0e" name="FMT6_5_6_5_UNORM"/> + + <value value="0x0f" name="FMT6_8_8_UNORM"/> + <value value="0x10" name="FMT6_8_8_SNORM"/> + <value value="0x11" name="FMT6_8_8_UINT"/> + <value value="0x12" name="FMT6_8_8_SINT"/> + <value value="0x13" name="FMT6_L8_A8_UNORM"/> + + <value value="0x15" name="FMT6_16_UNORM"/> + <value value="0x16" name="FMT6_16_SNORM"/> + <value value="0x17" name="FMT6_16_FLOAT"/> + <value value="0x18" name="FMT6_16_UINT"/> + <value value="0x19" name="FMT6_16_SINT"/> + + <value value="0x21" name="FMT6_8_8_8_UNORM"/> + <value value="0x22" name="FMT6_8_8_8_SNORM"/> + <value value="0x23" name="FMT6_8_8_8_UINT"/> + <value value="0x24" name="FMT6_8_8_8_SINT"/> + + <value value="0x30" name="FMT6_8_8_8_8_UNORM"/> + <value value="0x31" name="FMT6_8_8_8_X8_UNORM"/> <!-- samples 1 for alpha --> + <value value="0x32" name="FMT6_8_8_8_8_SNORM"/> + <value value="0x33" name="FMT6_8_8_8_8_UINT"/> + <value value="0x34" name="FMT6_8_8_8_8_SINT"/> + + <value value="0x35" name="FMT6_9_9_9_E5_FLOAT"/> + + <value value="0x36" name="FMT6_10_10_10_2_UNORM"/> + <value value="0x37" name="FMT6_10_10_10_2_UNORM_DEST"/> + <value value="0x39" name="FMT6_10_10_10_2_SNORM"/> + <value value="0x3a" name="FMT6_10_10_10_2_UINT"/> + <value value="0x3b" name="FMT6_10_10_10_2_SINT"/> + + <value value="0x42" name="FMT6_11_11_10_FLOAT"/> + + <value value="0x43" name="FMT6_16_16_UNORM"/> + <value value="0x44" name="FMT6_16_16_SNORM"/> + <value value="0x45" name="FMT6_16_16_FLOAT"/> + <value value="0x46" name="FMT6_16_16_UINT"/> + <value value="0x47" name="FMT6_16_16_SINT"/> + + <value value="0x48" name="FMT6_32_UNORM"/> + <value value="0x49" name="FMT6_32_SNORM"/> + <value value="0x4a" name="FMT6_32_FLOAT"/> + <value value="0x4b" name="FMT6_32_UINT"/> + <value value="0x4c" name="FMT6_32_SINT"/> + <value value="0x4d" name="FMT6_32_FIXED"/> + + <value value="0x58" name="FMT6_16_16_16_UNORM"/> + <value value="0x59" name="FMT6_16_16_16_SNORM"/> + <value value="0x5a" name="FMT6_16_16_16_FLOAT"/> + <value value="0x5b" name="FMT6_16_16_16_UINT"/> + <value value="0x5c" name="FMT6_16_16_16_SINT"/> + + <value value="0x60" name="FMT6_16_16_16_16_UNORM"/> + <value value="0x61" name="FMT6_16_16_16_16_SNORM"/> + <value value="0x62" name="FMT6_16_16_16_16_FLOAT"/> + <value value="0x63" name="FMT6_16_16_16_16_UINT"/> + <value value="0x64" name="FMT6_16_16_16_16_SINT"/> + + <value value="0x65" name="FMT6_32_32_UNORM"/> + <value value="0x66" name="FMT6_32_32_SNORM"/> + <value value="0x67" name="FMT6_32_32_FLOAT"/> + <value value="0x68" name="FMT6_32_32_UINT"/> + <value value="0x69" name="FMT6_32_32_SINT"/> + <value value="0x6a" name="FMT6_32_32_FIXED"/> + + <value value="0x70" name="FMT6_32_32_32_UNORM"/> + <value value="0x71" name="FMT6_32_32_32_SNORM"/> + <value value="0x72" name="FMT6_32_32_32_UINT"/> + <value value="0x73" name="FMT6_32_32_32_SINT"/> + <value value="0x74" name="FMT6_32_32_32_FLOAT"/> + <value value="0x75" name="FMT6_32_32_32_FIXED"/> + + <value value="0x80" name="FMT6_32_32_32_32_UNORM"/> + <value value="0x81" name="FMT6_32_32_32_32_SNORM"/> + <value value="0x82" name="FMT6_32_32_32_32_FLOAT"/> + <value value="0x83" name="FMT6_32_32_32_32_UINT"/> + <value value="0x84" name="FMT6_32_32_32_32_SINT"/> + <value value="0x85" name="FMT6_32_32_32_32_FIXED"/> + + <value value="0x8c" name="FMT6_G8R8B8R8_422_UNORM"/> <!-- UYVY --> + <value value="0x8d" name="FMT6_R8G8R8B8_422_UNORM"/> <!-- YUYV --> + <value value="0x8e" name="FMT6_R8_G8B8_2PLANE_420_UNORM"/> <!-- NV12 --> + <value value="0x8f" name="FMT6_NV21"/> + <value value="0x90" name="FMT6_R8_G8_B8_3PLANE_420_UNORM"/> <!-- YV12 --> + + <value value="0x91" name="FMT6_Z24_UNORM_S8_UINT_AS_R8G8B8A8"/> + + <!-- Note: tiling/UBWC for these may be different from equivalent formats + For example FMT6_NV12_Y is not compatible with FMT6_8_UNORM + --> + <value value="0x94" name="FMT6_NV12_Y"/> + <value value="0x95" name="FMT6_NV12_UV"/> + <value value="0x96" name="FMT6_NV12_VU"/> + <value value="0x97" name="FMT6_NV12_4R"/> + <value value="0x98" name="FMT6_NV12_4R_Y"/> + <value value="0x99" name="FMT6_NV12_4R_UV"/> + <value value="0x9a" name="FMT6_P010"/> + <value value="0x9b" name="FMT6_P010_Y"/> + <value value="0x9c" name="FMT6_P010_UV"/> + <value value="0x9d" name="FMT6_TP10"/> + <value value="0x9e" name="FMT6_TP10_Y"/> + <value value="0x9f" name="FMT6_TP10_UV"/> + + <value value="0xa0" name="FMT6_Z24_UNORM_S8_UINT"/> + + <value value="0xab" name="FMT6_ETC2_RG11_UNORM"/> + <value value="0xac" name="FMT6_ETC2_RG11_SNORM"/> + <value value="0xad" name="FMT6_ETC2_R11_UNORM"/> + <value value="0xae" name="FMT6_ETC2_R11_SNORM"/> + <value value="0xaf" name="FMT6_ETC1"/> + <value value="0xb0" name="FMT6_ETC2_RGB8"/> + <value value="0xb1" name="FMT6_ETC2_RGBA8"/> + <value value="0xb2" name="FMT6_ETC2_RGB8A1"/> + <value value="0xb3" name="FMT6_DXT1"/> + <value value="0xb4" name="FMT6_DXT3"/> + <value value="0xb5" name="FMT6_DXT5"/> + <value value="0xb6" name="FMT6_RGTC1_UNORM"/> + <value value="0xb7" name="FMT6_RGTC1_UNORM_FAST"/> + <value value="0xb8" name="FMT6_RGTC1_SNORM"/> + <value value="0xb9" name="FMT6_RGTC1_SNORM_FAST"/> + <value value="0xba" name="FMT6_RGTC2_UNORM"/> + <value value="0xbb" name="FMT6_RGTC2_UNORM_FAST"/> + <value value="0xbc" name="FMT6_RGTC2_SNORM"/> + <value value="0xbd" name="FMT6_RGTC2_SNORM_FAST"/> + <value value="0xbe" name="FMT6_BPTC_UFLOAT"/> + <value value="0xbf" name="FMT6_BPTC_FLOAT"/> + <value value="0xc0" name="FMT6_BPTC"/> + <value value="0xc1" name="FMT6_ASTC_4x4"/> + <value value="0xc2" name="FMT6_ASTC_5x4"/> + <value value="0xc3" name="FMT6_ASTC_5x5"/> + <value value="0xc4" name="FMT6_ASTC_6x5"/> + <value value="0xc5" name="FMT6_ASTC_6x6"/> + <value value="0xc6" name="FMT6_ASTC_8x5"/> + <value value="0xc7" name="FMT6_ASTC_8x6"/> + <value value="0xc8" name="FMT6_ASTC_8x8"/> + <value value="0xc9" name="FMT6_ASTC_10x5"/> + <value value="0xca" name="FMT6_ASTC_10x6"/> + <value value="0xcb" name="FMT6_ASTC_10x8"/> + <value value="0xcc" name="FMT6_ASTC_10x10"/> + <value value="0xcd" name="FMT6_ASTC_12x10"/> + <value value="0xce" name="FMT6_ASTC_12x12"/> + + <!-- for sampling stencil (integer, 2nd channel), not available on a630 --> + <value value="0xea" name="FMT6_Z24_UINT_S8_UINT"/> + + <!-- Not a hw enum, used internally in driver --> + <value value="0xff" name="FMT6_NONE"/> + +</enum> + +<!-- probably same as a5xx --> +<enum name="a6xx_polygon_mode"> + <value name="POLYMODE6_POINTS" value="1"/> + <value name="POLYMODE6_LINES" value="2"/> + <value name="POLYMODE6_TRIANGLES" value="3"/> +</enum> + +<enum name="a6xx_depth_format"> + <value name="DEPTH6_NONE" value="0"/> + <value name="DEPTH6_16" value="1"/> + <value name="DEPTH6_24_8" value="2"/> + <value name="DEPTH6_32" value="4"/> +</enum> + +<bitset name="a6x_cp_protect" inline="yes"> + <bitfield name="BASE_ADDR" low="0" high="17"/> + <bitfield name="MASK_LEN" low="18" high="30"/> + <bitfield name="READ" pos="31" type="boolean"/> +</bitset> + +<enum name="a6xx_shader_id"> + <value value="0x9" name="A6XX_TP0_TMO_DATA"/> + <value value="0xa" name="A6XX_TP0_SMO_DATA"/> + <value value="0xb" name="A6XX_TP0_MIPMAP_BASE_DATA"/> + <value value="0x19" name="A6XX_TP1_TMO_DATA"/> + <value value="0x1a" name="A6XX_TP1_SMO_DATA"/> + <value value="0x1b" name="A6XX_TP1_MIPMAP_BASE_DATA"/> + <value value="0x29" name="A6XX_SP_INST_DATA"/> + <value value="0x2a" name="A6XX_SP_LB_0_DATA"/> + <value value="0x2b" name="A6XX_SP_LB_1_DATA"/> + <value value="0x2c" name="A6XX_SP_LB_2_DATA"/> + <value value="0x2d" name="A6XX_SP_LB_3_DATA"/> + <value value="0x2e" name="A6XX_SP_LB_4_DATA"/> + <value value="0x2f" name="A6XX_SP_LB_5_DATA"/> + <value value="0x30" name="A6XX_SP_CB_BINDLESS_DATA"/> + <value value="0x31" name="A6XX_SP_CB_LEGACY_DATA"/> + <value value="0x32" name="A6XX_SP_GFX_UAV_BASE_DATA"/> + <value value="0x33" name="A6XX_SP_INST_TAG"/> + <value value="0x34" name="A6XX_SP_CB_BINDLESS_TAG"/> + <value value="0x35" name="A6XX_SP_TMO_UMO_TAG"/> + <value value="0x36" name="A6XX_SP_SMO_TAG"/> + <value value="0x37" name="A6XX_SP_STATE_DATA"/> + <value value="0x49" name="A6XX_HLSQ_CHUNK_CVS_RAM"/> + <value value="0x4a" name="A6XX_HLSQ_CHUNK_CPS_RAM"/> + <value value="0x4b" name="A6XX_HLSQ_CHUNK_CVS_RAM_TAG"/> + <value value="0x4c" name="A6XX_HLSQ_CHUNK_CPS_RAM_TAG"/> + <value value="0x4d" name="A6XX_HLSQ_ICB_CVS_CB_BASE_TAG"/> + <value value="0x4e" name="A6XX_HLSQ_ICB_CPS_CB_BASE_TAG"/> + <value value="0x50" name="A6XX_HLSQ_CVS_MISC_RAM"/> + <value value="0x51" name="A6XX_HLSQ_CPS_MISC_RAM"/> + <value value="0x52" name="A6XX_HLSQ_INST_RAM"/> + <value value="0x53" name="A6XX_HLSQ_GFX_CVS_CONST_RAM"/> + <value value="0x54" name="A6XX_HLSQ_GFX_CPS_CONST_RAM"/> + <value value="0x55" name="A6XX_HLSQ_CVS_MISC_RAM_TAG"/> + <value value="0x56" name="A6XX_HLSQ_CPS_MISC_RAM_TAG"/> + <value value="0x57" name="A6XX_HLSQ_INST_RAM_TAG"/> + <value value="0x58" name="A6XX_HLSQ_GFX_CVS_CONST_RAM_TAG"/> + <value value="0x59" name="A6XX_HLSQ_GFX_CPS_CONST_RAM_TAG"/> + <value value="0x5a" name="A6XX_HLSQ_PWR_REST_RAM"/> + <value value="0x5b" name="A6XX_HLSQ_PWR_REST_TAG"/> + <value value="0x60" name="A6XX_HLSQ_DATAPATH_META"/> + <value value="0x61" name="A6XX_HLSQ_FRONTEND_META"/> + <value value="0x62" name="A6XX_HLSQ_INDIRECT_META"/> + <value value="0x63" name="A6XX_HLSQ_BACKEND_META"/> + <value value="0x70" name="A6XX_SP_LB_6_DATA"/> + <value value="0x71" name="A6XX_SP_LB_7_DATA"/> + <value value="0x73" name="A6XX_HLSQ_INST_RAM_1"/> +</enum> + +<enum name="a6xx_debugbus_id"> + <value value="0x1" name="A6XX_DBGBUS_CP"/> + <value value="0x2" name="A6XX_DBGBUS_RBBM"/> + <value value="0x3" name="A6XX_DBGBUS_VBIF"/> + <value value="0x4" name="A6XX_DBGBUS_HLSQ"/> + <value value="0x5" name="A6XX_DBGBUS_UCHE"/> + <value value="0x6" name="A6XX_DBGBUS_DPM"/> + <value value="0x7" name="A6XX_DBGBUS_TESS"/> + <value value="0x8" name="A6XX_DBGBUS_PC"/> + <value value="0x9" name="A6XX_DBGBUS_VFDP"/> + <value value="0xa" name="A6XX_DBGBUS_VPC"/> + <value value="0xb" name="A6XX_DBGBUS_TSE"/> + <value value="0xc" name="A6XX_DBGBUS_RAS"/> + <value value="0xd" name="A6XX_DBGBUS_VSC"/> + <value value="0xe" name="A6XX_DBGBUS_COM"/> + <value value="0x10" name="A6XX_DBGBUS_LRZ"/> + <value value="0x11" name="A6XX_DBGBUS_A2D"/> + <value value="0x12" name="A6XX_DBGBUS_CCUFCHE"/> + <value value="0x13" name="A6XX_DBGBUS_GMU_CX"/> + <value value="0x14" name="A6XX_DBGBUS_RBP"/> + <value value="0x15" name="A6XX_DBGBUS_DCS"/> + <value value="0x16" name="A6XX_DBGBUS_DBGC"/> + <value value="0x17" name="A6XX_DBGBUS_CX"/> + <value value="0x18" name="A6XX_DBGBUS_GMU_GX"/> + <value value="0x19" name="A6XX_DBGBUS_TPFCHE"/> + <value value="0x1a" name="A6XX_DBGBUS_GBIF_GX"/> + <value value="0x1d" name="A6XX_DBGBUS_GPC"/> + <value value="0x1e" name="A6XX_DBGBUS_LARC"/> + <value value="0x1f" name="A6XX_DBGBUS_HLSQ_SPTP"/> + <value value="0x20" name="A6XX_DBGBUS_RB_0"/> + <value value="0x21" name="A6XX_DBGBUS_RB_1"/> + <value value="0x22" name="A6XX_DBGBUS_RB_2"/> + <value value="0x24" name="A6XX_DBGBUS_UCHE_WRAPPER"/> + <value value="0x28" name="A6XX_DBGBUS_CCU_0"/> + <value value="0x29" name="A6XX_DBGBUS_CCU_1"/> + <value value="0x2a" name="A6XX_DBGBUS_CCU_2"/> + <value value="0x38" name="A6XX_DBGBUS_VFD_0"/> + <value value="0x39" name="A6XX_DBGBUS_VFD_1"/> + <value value="0x3a" name="A6XX_DBGBUS_VFD_2"/> + <value value="0x3b" name="A6XX_DBGBUS_VFD_3"/> + <value value="0x3c" name="A6XX_DBGBUS_VFD_4"/> + <value value="0x3d" name="A6XX_DBGBUS_VFD_5"/> + <value value="0x40" name="A6XX_DBGBUS_SP_0"/> + <value value="0x41" name="A6XX_DBGBUS_SP_1"/> + <value value="0x42" name="A6XX_DBGBUS_SP_2"/> + <value value="0x48" name="A6XX_DBGBUS_TPL1_0"/> + <value value="0x49" name="A6XX_DBGBUS_TPL1_1"/> + <value value="0x4a" name="A6XX_DBGBUS_TPL1_2"/> + <value value="0x4b" name="A6XX_DBGBUS_TPL1_3"/> + <value value="0x4c" name="A6XX_DBGBUS_TPL1_4"/> + <value value="0x4d" name="A6XX_DBGBUS_TPL1_5"/> + <value value="0x58" name="A6XX_DBGBUS_SPTP_0"/> + <value value="0x59" name="A6XX_DBGBUS_SPTP_1"/> + <value value="0x5a" name="A6XX_DBGBUS_SPTP_2"/> + <value value="0x5b" name="A6XX_DBGBUS_SPTP_3"/> + <value value="0x5c" name="A6XX_DBGBUS_SPTP_4"/> + <value value="0x5d" name="A6XX_DBGBUS_SPTP_5"/> +</enum> + +<!-- +Used in a6xx_a2d_bit_cntl.. the value mostly seems to correlate to the +component type/size, so I think it relates to internal format used for +blending? The one exception is that 16b unorm and 32b float use the +same value... maybe 16b unorm is uncommon enough that it was just easier +to upconvert to 32b float internally? + + 8b unorm: 10 (sometimes 0, is the high bit part of something else?) +16b unorm: 4 + +32b int: 7 +16b int: 6 + 8b int: 5 + +32b float: 4 +16b float: 3 + --> +<enum name="a6xx_2d_ifmt"> + <value value="0x10" name="R2D_UNORM8"/> + <value value="0x7" name="R2D_INT32"/> + <value value="0x6" name="R2D_INT16"/> + <value value="0x5" name="R2D_INT8"/> + <value value="0x4" name="R2D_FLOAT32"/> + <value value="0x3" name="R2D_FLOAT16"/> + <value value="0x1" name="R2D_UNORM8_SRGB"/> + <value value="0x0" name="R2D_RAW"/> +</enum> + +<enum name="a6xx_tex_type"> + <value name="A6XX_TEX_1D" value="0"/> + <value name="A6XX_TEX_2D" value="1"/> + <value name="A6XX_TEX_CUBE" value="2"/> + <value name="A6XX_TEX_3D" value="3"/> + <value name="A6XX_TEX_BUFFER" value="4"/> + <doc> + A special buffer type for usage as the source for buffer + to image copies with lower alignment requirements than + A6XX_TEX_2D, available since A7XX. + </doc> + <value name="A6XX_TEX_IMG_BUFFER" value="5"/> +</enum> + +<enum name="a6xx_ztest_mode"> + <doc>Allow early z-test and early-lrz (if applicable)</doc> + <value value="0x0" name="A6XX_EARLY_Z"/> + <doc>Disable early z-test and early-lrz test (if applicable)</doc> + <value value="0x1" name="A6XX_LATE_Z"/> + <doc> + A special mode that allows early-lrz (if applicable) or early-z + tests, but also does late-z tests at which point it writes depth. + + This mode is used when fragment can be killed (via discard or + sample mask) after early-z tests and it writes depth. In such case + depth can be written only at late-z stage, but it's ok to use + early-z to discard fragments. + + However this mode is not compatible with: + - Lack of D/S attachment + - Stencil writes on stencil or depth test failures + - Per-sample shading + </doc> + <value value="0x2" name="A6XX_EARLY_Z_LATE_Z"/> + <doc>Not a real hw value, used internally by mesa</doc> + <value value="0x3" name="A6XX_INVALID_ZTEST"/> +</enum> + +<enum name="a6xx_tess_spacing"> + <value value="0x0" name="TESS_EQUAL"/> + <value value="0x2" name="TESS_FRACTIONAL_ODD"/> + <value value="0x3" name="TESS_FRACTIONAL_EVEN"/> +</enum> +<enum name="a6xx_tess_output"> + <value value="0x0" name="TESS_POINTS"/> + <value value="0x1" name="TESS_LINES"/> + <value value="0x2" name="TESS_CW_TRIS"/> + <value value="0x3" name="TESS_CCW_TRIS"/> +</enum> + +</database> diff --git a/drivers/gpu/drm/msm/registers/adreno/a6xx_gmu.xml b/drivers/gpu/drm/msm/registers/adreno/a6xx_gmu.xml index 6531749d30f4..3d2cc339b8f1 100644 --- a/drivers/gpu/drm/msm/registers/adreno/a6xx_gmu.xml +++ b/drivers/gpu/drm/msm/registers/adreno/a6xx_gmu.xml @@ -52,6 +52,11 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <reg32 offset="0x23fd" name="GMU_DCVS_PERF_SETTING"/> <reg32 offset="0x23fe" name="GMU_DCVS_BW_SETTING"/> <reg32 offset="0x23ff" name="GMU_DCVS_RETURN"/> + <reg32 offset="0x2bf8" name="GMU_CORE_FW_VERSION"> + <bitfield name="MAJOR" low="28" high="31"/> + <bitfield name="MINOR" low="16" high="27"/> + <bitfield name="STEP" low="0" high="15"/> + </reg32> <reg32 offset="0x4c00" name="GMU_ICACHE_CONFIG"/> <reg32 offset="0x4c01" name="GMU_DCACHE_CONFIG"/> <reg32 offset="0x4c0f" name="GMU_SYS_BUS_CONFIG"/> diff --git a/drivers/gpu/drm/msm/registers/adreno/a6xx_perfcntrs.xml b/drivers/gpu/drm/msm/registers/adreno/a6xx_perfcntrs.xml new file mode 100644 index 000000000000..c446a2eb1120 --- /dev/null +++ b/drivers/gpu/drm/msm/registers/adreno/a6xx_perfcntrs.xml @@ -0,0 +1,600 @@ +<?xml version="1.0" encoding="UTF-8"?> +<database xmlns="http://nouveau.freedesktop.org/" +xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" +xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> +<import file="freedreno_copyright.xml"/> +<import file="adreno/adreno_common.xml"/> +<import file="adreno/adreno_pm4.xml"/> + +<enum name="a6xx_cp_perfcounter_select"> + <value value="0" name="PERF_CP_ALWAYS_COUNT"/> + <value value="1" name="PERF_CP_BUSY_GFX_CORE_IDLE"/> + <value value="2" name="PERF_CP_BUSY_CYCLES"/> + <value value="3" name="PERF_CP_NUM_PREEMPTIONS"/> + <value value="4" name="PERF_CP_PREEMPTION_REACTION_DELAY"/> + <value value="5" name="PERF_CP_PREEMPTION_SWITCH_OUT_TIME"/> + <value value="6" name="PERF_CP_PREEMPTION_SWITCH_IN_TIME"/> + <value value="7" name="PERF_CP_DEAD_DRAWS_IN_BIN_RENDER"/> + <value value="8" name="PERF_CP_PREDICATED_DRAWS_KILLED"/> + <value value="9" name="PERF_CP_MODE_SWITCH"/> + <value value="10" name="PERF_CP_ZPASS_DONE"/> + <value value="11" name="PERF_CP_CONTEXT_DONE"/> + <value value="12" name="PERF_CP_CACHE_FLUSH"/> + <value value="13" name="PERF_CP_LONG_PREEMPTIONS"/> + <value value="14" name="PERF_CP_SQE_I_CACHE_STARVE"/> + <value value="15" name="PERF_CP_SQE_IDLE"/> + <value value="16" name="PERF_CP_SQE_PM4_STARVE_RB_IB"/> + <value value="17" name="PERF_CP_SQE_PM4_STARVE_SDS"/> + <value value="18" name="PERF_CP_SQE_MRB_STARVE"/> + <value value="19" name="PERF_CP_SQE_RRB_STARVE"/> + <value value="20" name="PERF_CP_SQE_VSD_STARVE"/> + <value value="21" name="PERF_CP_VSD_DECODE_STARVE"/> + <value value="22" name="PERF_CP_SQE_PIPE_OUT_STALL"/> + <value value="23" name="PERF_CP_SQE_SYNC_STALL"/> + <value value="24" name="PERF_CP_SQE_PM4_WFI_STALL"/> + <value value="25" name="PERF_CP_SQE_SYS_WFI_STALL"/> + <value value="26" name="PERF_CP_SQE_T4_EXEC"/> + <value value="27" name="PERF_CP_SQE_LOAD_STATE_EXEC"/> + <value value="28" name="PERF_CP_SQE_SAVE_SDS_STATE"/> + <value value="29" name="PERF_CP_SQE_DRAW_EXEC"/> + <value value="30" name="PERF_CP_SQE_CTXT_REG_BUNCH_EXEC"/> + <value value="31" name="PERF_CP_SQE_EXEC_PROFILED"/> + <value value="32" name="PERF_CP_MEMORY_POOL_EMPTY"/> + <value value="33" name="PERF_CP_MEMORY_POOL_SYNC_STALL"/> + <value value="34" name="PERF_CP_MEMORY_POOL_ABOVE_THRESH"/> + <value value="35" name="PERF_CP_AHB_WR_STALL_PRE_DRAWS"/> + <value value="36" name="PERF_CP_AHB_STALL_SQE_GMU"/> + <value value="37" name="PERF_CP_AHB_STALL_SQE_WR_OTHER"/> + <value value="38" name="PERF_CP_AHB_STALL_SQE_RD_OTHER"/> + <value value="39" name="PERF_CP_CLUSTER0_EMPTY"/> + <value value="40" name="PERF_CP_CLUSTER1_EMPTY"/> + <value value="41" name="PERF_CP_CLUSTER2_EMPTY"/> + <value value="42" name="PERF_CP_CLUSTER3_EMPTY"/> + <value value="43" name="PERF_CP_CLUSTER4_EMPTY"/> + <value value="44" name="PERF_CP_CLUSTER5_EMPTY"/> + <value value="45" name="PERF_CP_PM4_DATA"/> + <value value="46" name="PERF_CP_PM4_HEADERS"/> + <value value="47" name="PERF_CP_VBIF_READ_BEATS"/> + <value value="48" name="PERF_CP_VBIF_WRITE_BEATS"/> + <value value="49" name="PERF_CP_SQE_INSTR_COUNTER"/> +</enum> + +<enum name="a6xx_rbbm_perfcounter_select"> + <value value="0" name="PERF_RBBM_ALWAYS_COUNT"/> + <value value="1" name="PERF_RBBM_ALWAYS_ON"/> + <value value="2" name="PERF_RBBM_TSE_BUSY"/> + <value value="3" name="PERF_RBBM_RAS_BUSY"/> + <value value="4" name="PERF_RBBM_PC_DCALL_BUSY"/> + <value value="5" name="PERF_RBBM_PC_VSD_BUSY"/> + <value value="6" name="PERF_RBBM_STATUS_MASKED"/> + <value value="7" name="PERF_RBBM_COM_BUSY"/> + <value value="8" name="PERF_RBBM_DCOM_BUSY"/> + <value value="9" name="PERF_RBBM_VBIF_BUSY"/> + <value value="10" name="PERF_RBBM_VSC_BUSY"/> + <value value="11" name="PERF_RBBM_TESS_BUSY"/> + <value value="12" name="PERF_RBBM_UCHE_BUSY"/> + <value value="13" name="PERF_RBBM_HLSQ_BUSY"/> +</enum> + +<enum name="a6xx_pc_perfcounter_select"> + <value value="0" name="PERF_PC_BUSY_CYCLES"/> + <value value="1" name="PERF_PC_WORKING_CYCLES"/> + <value value="2" name="PERF_PC_STALL_CYCLES_VFD"/> + <value value="3" name="PERF_PC_STALL_CYCLES_TSE"/> + <value value="4" name="PERF_PC_STALL_CYCLES_VPC"/> + <value value="5" name="PERF_PC_STALL_CYCLES_UCHE"/> + <value value="6" name="PERF_PC_STALL_CYCLES_TESS"/> + <value value="7" name="PERF_PC_STALL_CYCLES_TSE_ONLY"/> + <value value="8" name="PERF_PC_STALL_CYCLES_VPC_ONLY"/> + <value value="9" name="PERF_PC_PASS1_TF_STALL_CYCLES"/> + <value value="10" name="PERF_PC_STARVE_CYCLES_FOR_INDEX"/> + <value value="11" name="PERF_PC_STARVE_CYCLES_FOR_TESS_FACTOR"/> + <value value="12" name="PERF_PC_STARVE_CYCLES_FOR_VIZ_STREAM"/> + <value value="13" name="PERF_PC_STARVE_CYCLES_FOR_POSITION"/> + <value value="14" name="PERF_PC_STARVE_CYCLES_DI"/> + <value value="15" name="PERF_PC_VIS_STREAMS_LOADED"/> + <value value="16" name="PERF_PC_INSTANCES"/> + <value value="17" name="PERF_PC_VPC_PRIMITIVES"/> + <value value="18" name="PERF_PC_DEAD_PRIM"/> + <value value="19" name="PERF_PC_LIVE_PRIM"/> + <value value="20" name="PERF_PC_VERTEX_HITS"/> + <value value="21" name="PERF_PC_IA_VERTICES"/> + <value value="22" name="PERF_PC_IA_PRIMITIVES"/> + <value value="23" name="PERF_PC_GS_PRIMITIVES"/> + <value value="24" name="PERF_PC_HS_INVOCATIONS"/> + <value value="25" name="PERF_PC_DS_INVOCATIONS"/> + <value value="26" name="PERF_PC_VS_INVOCATIONS"/> + <value value="27" name="PERF_PC_GS_INVOCATIONS"/> + <value value="28" name="PERF_PC_DS_PRIMITIVES"/> + <value value="29" name="PERF_PC_VPC_POS_DATA_TRANSACTION"/> + <value value="30" name="PERF_PC_3D_DRAWCALLS"/> + <value value="31" name="PERF_PC_2D_DRAWCALLS"/> + <value value="32" name="PERF_PC_NON_DRAWCALL_GLOBAL_EVENTS"/> + <value value="33" name="PERF_TESS_BUSY_CYCLES"/> + <value value="34" name="PERF_TESS_WORKING_CYCLES"/> + <value value="35" name="PERF_TESS_STALL_CYCLES_PC"/> + <value value="36" name="PERF_TESS_STARVE_CYCLES_PC"/> + <value value="37" name="PERF_PC_TSE_TRANSACTION"/> + <value value="38" name="PERF_PC_TSE_VERTEX"/> + <value value="39" name="PERF_PC_TESS_PC_UV_TRANS"/> + <value value="40" name="PERF_PC_TESS_PC_UV_PATCHES"/> + <value value="41" name="PERF_PC_TESS_FACTOR_TRANS"/> +</enum> + +<enum name="a6xx_vfd_perfcounter_select"> + <value value="0" name="PERF_VFD_BUSY_CYCLES"/> + <value value="1" name="PERF_VFD_STALL_CYCLES_UCHE"/> + <value value="2" name="PERF_VFD_STALL_CYCLES_VPC_ALLOC"/> + <value value="3" name="PERF_VFD_STALL_CYCLES_SP_INFO"/> + <value value="4" name="PERF_VFD_STALL_CYCLES_SP_ATTR"/> + <value value="5" name="PERF_VFD_STARVE_CYCLES_UCHE"/> + <value value="6" name="PERF_VFD_RBUFFER_FULL"/> + <value value="7" name="PERF_VFD_ATTR_INFO_FIFO_FULL"/> + <value value="8" name="PERF_VFD_DECODED_ATTRIBUTE_BYTES"/> + <value value="9" name="PERF_VFD_NUM_ATTRIBUTES"/> + <value value="10" name="PERF_VFD_UPPER_SHADER_FIBERS"/> + <value value="11" name="PERF_VFD_LOWER_SHADER_FIBERS"/> + <value value="12" name="PERF_VFD_MODE_0_FIBERS"/> + <value value="13" name="PERF_VFD_MODE_1_FIBERS"/> + <value value="14" name="PERF_VFD_MODE_2_FIBERS"/> + <value value="15" name="PERF_VFD_MODE_3_FIBERS"/> + <value value="16" name="PERF_VFD_MODE_4_FIBERS"/> + <value value="17" name="PERF_VFD_TOTAL_VERTICES"/> + <value value="18" name="PERF_VFDP_STALL_CYCLES_VFD"/> + <value value="19" name="PERF_VFDP_STALL_CYCLES_VFD_INDEX"/> + <value value="20" name="PERF_VFDP_STALL_CYCLES_VFD_PROG"/> + <value value="21" name="PERF_VFDP_STARVE_CYCLES_PC"/> + <value value="22" name="PERF_VFDP_VS_STAGE_WAVES"/> +</enum> + +<enum name="a6xx_hlsq_perfcounter_select"> + <value value="0" name="PERF_HLSQ_BUSY_CYCLES"/> + <value value="1" name="PERF_HLSQ_STALL_CYCLES_UCHE"/> + <value value="2" name="PERF_HLSQ_STALL_CYCLES_SP_STATE"/> + <value value="3" name="PERF_HLSQ_STALL_CYCLES_SP_FS_STAGE"/> + <value value="4" name="PERF_HLSQ_UCHE_LATENCY_CYCLES"/> + <value value="5" name="PERF_HLSQ_UCHE_LATENCY_COUNT"/> + <value value="6" name="PERF_HLSQ_FS_STAGE_1X_WAVES"/> + <value value="7" name="PERF_HLSQ_FS_STAGE_2X_WAVES"/> + <value value="8" name="PERF_HLSQ_QUADS"/> + <value value="9" name="PERF_HLSQ_CS_INVOCATIONS"/> + <value value="10" name="PERF_HLSQ_COMPUTE_DRAWCALLS"/> + <value value="11" name="PERF_HLSQ_FS_DATA_WAIT_PROGRAMMING"/> + <value value="12" name="PERF_HLSQ_DUAL_FS_PROG_ACTIVE"/> + <value value="13" name="PERF_HLSQ_DUAL_VS_PROG_ACTIVE"/> + <value value="14" name="PERF_HLSQ_FS_BATCH_COUNT_ZERO"/> + <value value="15" name="PERF_HLSQ_VS_BATCH_COUNT_ZERO"/> + <value value="16" name="PERF_HLSQ_WAVE_PENDING_NO_QUAD"/> + <value value="17" name="PERF_HLSQ_WAVE_PENDING_NO_PRIM_BASE"/> + <value value="18" name="PERF_HLSQ_STALL_CYCLES_VPC"/> + <value value="19" name="PERF_HLSQ_PIXELS"/> + <value value="20" name="PERF_HLSQ_DRAW_MODE_SWITCH_VSFS_SYNC"/> +</enum> + +<enum name="a6xx_vpc_perfcounter_select"> + <value value="0" name="PERF_VPC_BUSY_CYCLES"/> + <value value="1" name="PERF_VPC_WORKING_CYCLES"/> + <value value="2" name="PERF_VPC_STALL_CYCLES_UCHE"/> + <value value="3" name="PERF_VPC_STALL_CYCLES_VFD_WACK"/> + <value value="4" name="PERF_VPC_STALL_CYCLES_HLSQ_PRIM_ALLOC"/> + <value value="5" name="PERF_VPC_STALL_CYCLES_PC"/> + <value value="6" name="PERF_VPC_STALL_CYCLES_SP_LM"/> + <value value="7" name="PERF_VPC_STARVE_CYCLES_SP"/> + <value value="8" name="PERF_VPC_STARVE_CYCLES_LRZ"/> + <value value="9" name="PERF_VPC_PC_PRIMITIVES"/> + <value value="10" name="PERF_VPC_SP_COMPONENTS"/> + <value value="11" name="PERF_VPC_STALL_CYCLES_VPCRAM_POS"/> + <value value="12" name="PERF_VPC_LRZ_ASSIGN_PRIMITIVES"/> + <value value="13" name="PERF_VPC_RB_VISIBLE_PRIMITIVES"/> + <value value="14" name="PERF_VPC_LM_TRANSACTION"/> + <value value="15" name="PERF_VPC_STREAMOUT_TRANSACTION"/> + <value value="16" name="PERF_VPC_VS_BUSY_CYCLES"/> + <value value="17" name="PERF_VPC_PS_BUSY_CYCLES"/> + <value value="18" name="PERF_VPC_VS_WORKING_CYCLES"/> + <value value="19" name="PERF_VPC_PS_WORKING_CYCLES"/> + <value value="20" name="PERF_VPC_STARVE_CYCLES_RB"/> + <value value="21" name="PERF_VPC_NUM_VPCRAM_READ_POS"/> + <value value="22" name="PERF_VPC_WIT_FULL_CYCLES"/> + <value value="23" name="PERF_VPC_VPCRAM_FULL_CYCLES"/> + <value value="24" name="PERF_VPC_LM_FULL_WAIT_FOR_INTP_END"/> + <value value="25" name="PERF_VPC_NUM_VPCRAM_WRITE"/> + <value value="26" name="PERF_VPC_NUM_VPCRAM_READ_SO"/> + <value value="27" name="PERF_VPC_NUM_ATTR_REQ_LM"/> +</enum> + +<enum name="a6xx_tse_perfcounter_select"> + <value value="0" name="PERF_TSE_BUSY_CYCLES"/> + <value value="1" name="PERF_TSE_CLIPPING_CYCLES"/> + <value value="2" name="PERF_TSE_STALL_CYCLES_RAS"/> + <value value="3" name="PERF_TSE_STALL_CYCLES_LRZ_BARYPLANE"/> + <value value="4" name="PERF_TSE_STALL_CYCLES_LRZ_ZPLANE"/> + <value value="5" name="PERF_TSE_STARVE_CYCLES_PC"/> + <value value="6" name="PERF_TSE_INPUT_PRIM"/> + <value value="7" name="PERF_TSE_INPUT_NULL_PRIM"/> + <value value="8" name="PERF_TSE_TRIVAL_REJ_PRIM"/> + <value value="9" name="PERF_TSE_CLIPPED_PRIM"/> + <value value="10" name="PERF_TSE_ZERO_AREA_PRIM"/> + <value value="11" name="PERF_TSE_FACENESS_CULLED_PRIM"/> + <value value="12" name="PERF_TSE_ZERO_PIXEL_PRIM"/> + <value value="13" name="PERF_TSE_OUTPUT_NULL_PRIM"/> + <value value="14" name="PERF_TSE_OUTPUT_VISIBLE_PRIM"/> + <value value="15" name="PERF_TSE_CINVOCATION"/> + <value value="16" name="PERF_TSE_CPRIMITIVES"/> + <value value="17" name="PERF_TSE_2D_INPUT_PRIM"/> + <value value="18" name="PERF_TSE_2D_ALIVE_CYCLES"/> + <value value="19" name="PERF_TSE_CLIP_PLANES"/> +</enum> + +<enum name="a6xx_ras_perfcounter_select"> + <value value="0" name="PERF_RAS_BUSY_CYCLES"/> + <value value="1" name="PERF_RAS_SUPERTILE_ACTIVE_CYCLES"/> + <value value="2" name="PERF_RAS_STALL_CYCLES_LRZ"/> + <value value="3" name="PERF_RAS_STARVE_CYCLES_TSE"/> + <value value="4" name="PERF_RAS_SUPER_TILES"/> + <value value="5" name="PERF_RAS_8X4_TILES"/> + <value value="6" name="PERF_RAS_MASKGEN_ACTIVE"/> + <value value="7" name="PERF_RAS_FULLY_COVERED_SUPER_TILES"/> + <value value="8" name="PERF_RAS_FULLY_COVERED_8X4_TILES"/> + <value value="9" name="PERF_RAS_PRIM_KILLED_INVISILBE"/> + <value value="10" name="PERF_RAS_SUPERTILE_GEN_ACTIVE_CYCLES"/> + <value value="11" name="PERF_RAS_LRZ_INTF_WORKING_CYCLES"/> + <value value="12" name="PERF_RAS_BLOCKS"/> +</enum> + +<enum name="a6xx_uche_perfcounter_select"> + <value value="0" name="PERF_UCHE_BUSY_CYCLES"/> + <value value="1" name="PERF_UCHE_STALL_CYCLES_ARBITER"/> + <value value="2" name="PERF_UCHE_VBIF_LATENCY_CYCLES"/> + <value value="3" name="PERF_UCHE_VBIF_LATENCY_SAMPLES"/> + <value value="4" name="PERF_UCHE_VBIF_READ_BEATS_TP"/> + <value value="5" name="PERF_UCHE_VBIF_READ_BEATS_VFD"/> + <value value="6" name="PERF_UCHE_VBIF_READ_BEATS_HLSQ"/> + <value value="7" name="PERF_UCHE_VBIF_READ_BEATS_LRZ"/> + <value value="8" name="PERF_UCHE_VBIF_READ_BEATS_SP"/> + <value value="9" name="PERF_UCHE_READ_REQUESTS_TP"/> + <value value="10" name="PERF_UCHE_READ_REQUESTS_VFD"/> + <value value="11" name="PERF_UCHE_READ_REQUESTS_HLSQ"/> + <value value="12" name="PERF_UCHE_READ_REQUESTS_LRZ"/> + <value value="13" name="PERF_UCHE_READ_REQUESTS_SP"/> + <value value="14" name="PERF_UCHE_WRITE_REQUESTS_LRZ"/> + <value value="15" name="PERF_UCHE_WRITE_REQUESTS_SP"/> + <value value="16" name="PERF_UCHE_WRITE_REQUESTS_VPC"/> + <value value="17" name="PERF_UCHE_WRITE_REQUESTS_VSC"/> + <value value="18" name="PERF_UCHE_EVICTS"/> + <value value="19" name="PERF_UCHE_BANK_REQ0"/> + <value value="20" name="PERF_UCHE_BANK_REQ1"/> + <value value="21" name="PERF_UCHE_BANK_REQ2"/> + <value value="22" name="PERF_UCHE_BANK_REQ3"/> + <value value="23" name="PERF_UCHE_BANK_REQ4"/> + <value value="24" name="PERF_UCHE_BANK_REQ5"/> + <value value="25" name="PERF_UCHE_BANK_REQ6"/> + <value value="26" name="PERF_UCHE_BANK_REQ7"/> + <value value="27" name="PERF_UCHE_VBIF_READ_BEATS_CH0"/> + <value value="28" name="PERF_UCHE_VBIF_READ_BEATS_CH1"/> + <value value="29" name="PERF_UCHE_GMEM_READ_BEATS"/> + <value value="30" name="PERF_UCHE_TPH_REF_FULL"/> + <value value="31" name="PERF_UCHE_TPH_VICTIM_FULL"/> + <value value="32" name="PERF_UCHE_TPH_EXT_FULL"/> + <value value="33" name="PERF_UCHE_VBIF_STALL_WRITE_DATA"/> + <value value="34" name="PERF_UCHE_DCMP_LATENCY_SAMPLES"/> + <value value="35" name="PERF_UCHE_DCMP_LATENCY_CYCLES"/> + <value value="36" name="PERF_UCHE_VBIF_READ_BEATS_PC"/> + <value value="37" name="PERF_UCHE_READ_REQUESTS_PC"/> + <value value="38" name="PERF_UCHE_RAM_READ_REQ"/> + <value value="39" name="PERF_UCHE_RAM_WRITE_REQ"/> +</enum> + +<enum name="a6xx_tp_perfcounter_select"> + <value value="0" name="PERF_TP_BUSY_CYCLES"/> + <value value="1" name="PERF_TP_STALL_CYCLES_UCHE"/> + <value value="2" name="PERF_TP_LATENCY_CYCLES"/> + <value value="3" name="PERF_TP_LATENCY_TRANS"/> + <value value="4" name="PERF_TP_FLAG_CACHE_REQUEST_SAMPLES"/> + <value value="5" name="PERF_TP_FLAG_CACHE_REQUEST_LATENCY"/> + <value value="6" name="PERF_TP_L1_CACHELINE_REQUESTS"/> + <value value="7" name="PERF_TP_L1_CACHELINE_MISSES"/> + <value value="8" name="PERF_TP_SP_TP_TRANS"/> + <value value="9" name="PERF_TP_TP_SP_TRANS"/> + <value value="10" name="PERF_TP_OUTPUT_PIXELS"/> + <value value="11" name="PERF_TP_FILTER_WORKLOAD_16BIT"/> + <value value="12" name="PERF_TP_FILTER_WORKLOAD_32BIT"/> + <value value="13" name="PERF_TP_QUADS_RECEIVED"/> + <value value="14" name="PERF_TP_QUADS_OFFSET"/> + <value value="15" name="PERF_TP_QUADS_SHADOW"/> + <value value="16" name="PERF_TP_QUADS_ARRAY"/> + <value value="17" name="PERF_TP_QUADS_GRADIENT"/> + <value value="18" name="PERF_TP_QUADS_1D"/> + <value value="19" name="PERF_TP_QUADS_2D"/> + <value value="20" name="PERF_TP_QUADS_BUFFER"/> + <value value="21" name="PERF_TP_QUADS_3D"/> + <value value="22" name="PERF_TP_QUADS_CUBE"/> + <value value="23" name="PERF_TP_DIVERGENT_QUADS_RECEIVED"/> + <value value="24" name="PERF_TP_PRT_NON_RESIDENT_EVENTS"/> + <value value="25" name="PERF_TP_OUTPUT_PIXELS_POINT"/> + <value value="26" name="PERF_TP_OUTPUT_PIXELS_BILINEAR"/> + <value value="27" name="PERF_TP_OUTPUT_PIXELS_MIP"/> + <value value="28" name="PERF_TP_OUTPUT_PIXELS_ANISO"/> + <value value="29" name="PERF_TP_OUTPUT_PIXELS_ZERO_LOD"/> + <value value="30" name="PERF_TP_FLAG_CACHE_REQUESTS"/> + <value value="31" name="PERF_TP_FLAG_CACHE_MISSES"/> + <value value="32" name="PERF_TP_L1_5_L2_REQUESTS"/> + <value value="33" name="PERF_TP_2D_OUTPUT_PIXELS"/> + <value value="34" name="PERF_TP_2D_OUTPUT_PIXELS_POINT"/> + <value value="35" name="PERF_TP_2D_OUTPUT_PIXELS_BILINEAR"/> + <value value="36" name="PERF_TP_2D_FILTER_WORKLOAD_16BIT"/> + <value value="37" name="PERF_TP_2D_FILTER_WORKLOAD_32BIT"/> + <value value="38" name="PERF_TP_TPA2TPC_TRANS"/> + <value value="39" name="PERF_TP_L1_MISSES_ASTC_1TILE"/> + <value value="40" name="PERF_TP_L1_MISSES_ASTC_2TILE"/> + <value value="41" name="PERF_TP_L1_MISSES_ASTC_4TILE"/> + <value value="42" name="PERF_TP_L1_5_L2_COMPRESS_REQS"/> + <value value="43" name="PERF_TP_L1_5_L2_COMPRESS_MISS"/> + <value value="44" name="PERF_TP_L1_BANK_CONFLICT"/> + <value value="45" name="PERF_TP_L1_5_MISS_LATENCY_CYCLES"/> + <value value="46" name="PERF_TP_L1_5_MISS_LATENCY_TRANS"/> + <value value="47" name="PERF_TP_QUADS_CONSTANT_MULTIPLIED"/> + <value value="48" name="PERF_TP_FRONTEND_WORKING_CYCLES"/> + <value value="49" name="PERF_TP_L1_TAG_WORKING_CYCLES"/> + <value value="50" name="PERF_TP_L1_DATA_WRITE_WORKING_CYCLES"/> + <value value="51" name="PERF_TP_PRE_L1_DECOM_WORKING_CYCLES"/> + <value value="52" name="PERF_TP_BACKEND_WORKING_CYCLES"/> + <value value="53" name="PERF_TP_FLAG_CACHE_WORKING_CYCLES"/> + <value value="54" name="PERF_TP_L1_5_CACHE_WORKING_CYCLES"/> + <value value="55" name="PERF_TP_STARVE_CYCLES_SP"/> + <value value="56" name="PERF_TP_STARVE_CYCLES_UCHE"/> +</enum> + +<enum name="a6xx_sp_perfcounter_select"> + <value value="0" name="PERF_SP_BUSY_CYCLES"/> + <value value="1" name="PERF_SP_ALU_WORKING_CYCLES"/> + <value value="2" name="PERF_SP_EFU_WORKING_CYCLES"/> + <value value="3" name="PERF_SP_STALL_CYCLES_VPC"/> + <value value="4" name="PERF_SP_STALL_CYCLES_TP"/> + <value value="5" name="PERF_SP_STALL_CYCLES_UCHE"/> + <value value="6" name="PERF_SP_STALL_CYCLES_RB"/> + <value value="7" name="PERF_SP_NON_EXECUTION_CYCLES"/> + <value value="8" name="PERF_SP_WAVE_CONTEXTS"/> + <value value="9" name="PERF_SP_WAVE_CONTEXT_CYCLES"/> + <value value="10" name="PERF_SP_FS_STAGE_WAVE_CYCLES"/> + <value value="11" name="PERF_SP_FS_STAGE_WAVE_SAMPLES"/> + <value value="12" name="PERF_SP_VS_STAGE_WAVE_CYCLES"/> + <value value="13" name="PERF_SP_VS_STAGE_WAVE_SAMPLES"/> + <value value="14" name="PERF_SP_FS_STAGE_DURATION_CYCLES"/> + <value value="15" name="PERF_SP_VS_STAGE_DURATION_CYCLES"/> + <value value="16" name="PERF_SP_WAVE_CTRL_CYCLES"/> + <value value="17" name="PERF_SP_WAVE_LOAD_CYCLES"/> + <value value="18" name="PERF_SP_WAVE_EMIT_CYCLES"/> + <value value="19" name="PERF_SP_WAVE_NOP_CYCLES"/> + <value value="20" name="PERF_SP_WAVE_WAIT_CYCLES"/> + <value value="21" name="PERF_SP_WAVE_FETCH_CYCLES"/> + <value value="22" name="PERF_SP_WAVE_IDLE_CYCLES"/> + <value value="23" name="PERF_SP_WAVE_END_CYCLES"/> + <value value="24" name="PERF_SP_WAVE_LONG_SYNC_CYCLES"/> + <value value="25" name="PERF_SP_WAVE_SHORT_SYNC_CYCLES"/> + <value value="26" name="PERF_SP_WAVE_JOIN_CYCLES"/> + <value value="27" name="PERF_SP_LM_LOAD_INSTRUCTIONS"/> + <value value="28" name="PERF_SP_LM_STORE_INSTRUCTIONS"/> + <value value="29" name="PERF_SP_LM_ATOMICS"/> + <value value="30" name="PERF_SP_GM_LOAD_INSTRUCTIONS"/> + <value value="31" name="PERF_SP_GM_STORE_INSTRUCTIONS"/> + <value value="32" name="PERF_SP_GM_ATOMICS"/> + <value value="33" name="PERF_SP_VS_STAGE_TEX_INSTRUCTIONS"/> + <value value="34" name="PERF_SP_VS_STAGE_EFU_INSTRUCTIONS"/> + <value value="35" name="PERF_SP_VS_STAGE_FULL_ALU_INSTRUCTIONS"/> + <value value="36" name="PERF_SP_VS_STAGE_HALF_ALU_INSTRUCTIONS"/> + <value value="37" name="PERF_SP_FS_STAGE_TEX_INSTRUCTIONS"/> + <value value="38" name="PERF_SP_FS_STAGE_CFLOW_INSTRUCTIONS"/> + <value value="39" name="PERF_SP_FS_STAGE_EFU_INSTRUCTIONS"/> + <value value="40" name="PERF_SP_FS_STAGE_FULL_ALU_INSTRUCTIONS"/> + <value value="41" name="PERF_SP_FS_STAGE_HALF_ALU_INSTRUCTIONS"/> + <value value="42" name="PERF_SP_FS_STAGE_BARY_INSTRUCTIONS"/> + <value value="43" name="PERF_SP_VS_INSTRUCTIONS"/> + <value value="44" name="PERF_SP_FS_INSTRUCTIONS"/> + <value value="45" name="PERF_SP_ADDR_LOCK_COUNT"/> + <value value="46" name="PERF_SP_UCHE_READ_TRANS"/> + <value value="47" name="PERF_SP_UCHE_WRITE_TRANS"/> + <value value="48" name="PERF_SP_EXPORT_VPC_TRANS"/> + <value value="49" name="PERF_SP_EXPORT_RB_TRANS"/> + <value value="50" name="PERF_SP_PIXELS_KILLED"/> + <value value="51" name="PERF_SP_ICL1_REQUESTS"/> + <value value="52" name="PERF_SP_ICL1_MISSES"/> + <value value="53" name="PERF_SP_HS_INSTRUCTIONS"/> + <value value="54" name="PERF_SP_DS_INSTRUCTIONS"/> + <value value="55" name="PERF_SP_GS_INSTRUCTIONS"/> + <value value="56" name="PERF_SP_CS_INSTRUCTIONS"/> + <value value="57" name="PERF_SP_GPR_READ"/> + <value value="58" name="PERF_SP_GPR_WRITE"/> + <value value="59" name="PERF_SP_FS_STAGE_HALF_EFU_INSTRUCTIONS"/> + <value value="60" name="PERF_SP_VS_STAGE_HALF_EFU_INSTRUCTIONS"/> + <value value="61" name="PERF_SP_LM_BANK_CONFLICTS"/> + <value value="62" name="PERF_SP_TEX_CONTROL_WORKING_CYCLES"/> + <value value="63" name="PERF_SP_LOAD_CONTROL_WORKING_CYCLES"/> + <value value="64" name="PERF_SP_FLOW_CONTROL_WORKING_CYCLES"/> + <value value="65" name="PERF_SP_LM_WORKING_CYCLES"/> + <value value="66" name="PERF_SP_DISPATCHER_WORKING_CYCLES"/> + <value value="67" name="PERF_SP_SEQUENCER_WORKING_CYCLES"/> + <value value="68" name="PERF_SP_LOW_EFFICIENCY_STARVED_BY_TP"/> + <value value="69" name="PERF_SP_STARVE_CYCLES_HLSQ"/> + <value value="70" name="PERF_SP_NON_EXECUTION_LS_CYCLES"/> + <value value="71" name="PERF_SP_WORKING_EU"/> + <value value="72" name="PERF_SP_ANY_EU_WORKING"/> + <value value="73" name="PERF_SP_WORKING_EU_FS_STAGE"/> + <value value="74" name="PERF_SP_ANY_EU_WORKING_FS_STAGE"/> + <value value="75" name="PERF_SP_WORKING_EU_VS_STAGE"/> + <value value="76" name="PERF_SP_ANY_EU_WORKING_VS_STAGE"/> + <value value="77" name="PERF_SP_WORKING_EU_CS_STAGE"/> + <value value="78" name="PERF_SP_ANY_EU_WORKING_CS_STAGE"/> + <value value="79" name="PERF_SP_GPR_READ_PREFETCH"/> + <value value="80" name="PERF_SP_GPR_READ_CONFLICT"/> + <value value="81" name="PERF_SP_GPR_WRITE_CONFLICT"/> + <value value="82" name="PERF_SP_GM_LOAD_LATENCY_CYCLES"/> + <value value="83" name="PERF_SP_GM_LOAD_LATENCY_SAMPLES"/> + <value value="84" name="PERF_SP_EXECUTABLE_WAVES"/> +</enum> + +<enum name="a6xx_rb_perfcounter_select"> + <value value="0" name="PERF_RB_BUSY_CYCLES"/> + <value value="1" name="PERF_RB_STALL_CYCLES_HLSQ"/> + <value value="2" name="PERF_RB_STALL_CYCLES_FIFO0_FULL"/> + <value value="3" name="PERF_RB_STALL_CYCLES_FIFO1_FULL"/> + <value value="4" name="PERF_RB_STALL_CYCLES_FIFO2_FULL"/> + <value value="5" name="PERF_RB_STARVE_CYCLES_SP"/> + <value value="6" name="PERF_RB_STARVE_CYCLES_LRZ_TILE"/> + <value value="7" name="PERF_RB_STARVE_CYCLES_CCU"/> + <value value="8" name="PERF_RB_STARVE_CYCLES_Z_PLANE"/> + <value value="9" name="PERF_RB_STARVE_CYCLES_BARY_PLANE"/> + <value value="10" name="PERF_RB_Z_WORKLOAD"/> + <value value="11" name="PERF_RB_HLSQ_ACTIVE"/> + <value value="12" name="PERF_RB_Z_READ"/> + <value value="13" name="PERF_RB_Z_WRITE"/> + <value value="14" name="PERF_RB_C_READ"/> + <value value="15" name="PERF_RB_C_WRITE"/> + <value value="16" name="PERF_RB_TOTAL_PASS"/> + <value value="17" name="PERF_RB_Z_PASS"/> + <value value="18" name="PERF_RB_Z_FAIL"/> + <value value="19" name="PERF_RB_S_FAIL"/> + <value value="20" name="PERF_RB_BLENDED_FXP_COMPONENTS"/> + <value value="21" name="PERF_RB_BLENDED_FP16_COMPONENTS"/> + <value value="22" name="PERF_RB_PS_INVOCATIONS"/> + <value value="23" name="PERF_RB_2D_ALIVE_CYCLES"/> + <value value="24" name="PERF_RB_2D_STALL_CYCLES_A2D"/> + <value value="25" name="PERF_RB_2D_STARVE_CYCLES_SRC"/> + <value value="26" name="PERF_RB_2D_STARVE_CYCLES_SP"/> + <value value="27" name="PERF_RB_2D_STARVE_CYCLES_DST"/> + <value value="28" name="PERF_RB_2D_VALID_PIXELS"/> + <value value="29" name="PERF_RB_3D_PIXELS"/> + <value value="30" name="PERF_RB_BLENDER_WORKING_CYCLES"/> + <value value="31" name="PERF_RB_ZPROC_WORKING_CYCLES"/> + <value value="32" name="PERF_RB_CPROC_WORKING_CYCLES"/> + <value value="33" name="PERF_RB_SAMPLER_WORKING_CYCLES"/> + <value value="34" name="PERF_RB_STALL_CYCLES_CCU_COLOR_READ"/> + <value value="35" name="PERF_RB_STALL_CYCLES_CCU_COLOR_WRITE"/> + <value value="36" name="PERF_RB_STALL_CYCLES_CCU_DEPTH_READ"/> + <value value="37" name="PERF_RB_STALL_CYCLES_CCU_DEPTH_WRITE"/> + <value value="38" name="PERF_RB_STALL_CYCLES_VPC"/> + <value value="39" name="PERF_RB_2D_INPUT_TRANS"/> + <value value="40" name="PERF_RB_2D_OUTPUT_RB_DST_TRANS"/> + <value value="41" name="PERF_RB_2D_OUTPUT_RB_SRC_TRANS"/> + <value value="42" name="PERF_RB_BLENDED_FP32_COMPONENTS"/> + <value value="43" name="PERF_RB_COLOR_PIX_TILES"/> + <value value="44" name="PERF_RB_STALL_CYCLES_CCU"/> + <value value="45" name="PERF_RB_EARLY_Z_ARB3_GRANT"/> + <value value="46" name="PERF_RB_LATE_Z_ARB3_GRANT"/> + <value value="47" name="PERF_RB_EARLY_Z_SKIP_GRANT"/> +</enum> + +<enum name="a6xx_vsc_perfcounter_select"> + <value value="0" name="PERF_VSC_BUSY_CYCLES"/> + <value value="1" name="PERF_VSC_WORKING_CYCLES"/> + <value value="2" name="PERF_VSC_STALL_CYCLES_UCHE"/> + <value value="3" name="PERF_VSC_EOT_NUM"/> + <value value="4" name="PERF_VSC_INPUT_TILES"/> +</enum> + +<enum name="a6xx_ccu_perfcounter_select"> + <value value="0" name="PERF_CCU_BUSY_CYCLES"/> + <value value="1" name="PERF_CCU_STALL_CYCLES_RB_DEPTH_RETURN"/> + <value value="2" name="PERF_CCU_STALL_CYCLES_RB_COLOR_RETURN"/> + <value value="3" name="PERF_CCU_STARVE_CYCLES_FLAG_RETURN"/> + <value value="4" name="PERF_CCU_DEPTH_BLOCKS"/> + <value value="5" name="PERF_CCU_COLOR_BLOCKS"/> + <value value="6" name="PERF_CCU_DEPTH_BLOCK_HIT"/> + <value value="7" name="PERF_CCU_COLOR_BLOCK_HIT"/> + <value value="8" name="PERF_CCU_PARTIAL_BLOCK_READ"/> + <value value="9" name="PERF_CCU_GMEM_READ"/> + <value value="10" name="PERF_CCU_GMEM_WRITE"/> + <value value="11" name="PERF_CCU_DEPTH_READ_FLAG0_COUNT"/> + <value value="12" name="PERF_CCU_DEPTH_READ_FLAG1_COUNT"/> + <value value="13" name="PERF_CCU_DEPTH_READ_FLAG2_COUNT"/> + <value value="14" name="PERF_CCU_DEPTH_READ_FLAG3_COUNT"/> + <value value="15" name="PERF_CCU_DEPTH_READ_FLAG4_COUNT"/> + <value value="16" name="PERF_CCU_DEPTH_READ_FLAG5_COUNT"/> + <value value="17" name="PERF_CCU_DEPTH_READ_FLAG6_COUNT"/> + <value value="18" name="PERF_CCU_DEPTH_READ_FLAG8_COUNT"/> + <value value="19" name="PERF_CCU_COLOR_READ_FLAG0_COUNT"/> + <value value="20" name="PERF_CCU_COLOR_READ_FLAG1_COUNT"/> + <value value="21" name="PERF_CCU_COLOR_READ_FLAG2_COUNT"/> + <value value="22" name="PERF_CCU_COLOR_READ_FLAG3_COUNT"/> + <value value="23" name="PERF_CCU_COLOR_READ_FLAG4_COUNT"/> + <value value="24" name="PERF_CCU_COLOR_READ_FLAG5_COUNT"/> + <value value="25" name="PERF_CCU_COLOR_READ_FLAG6_COUNT"/> + <value value="26" name="PERF_CCU_COLOR_READ_FLAG8_COUNT"/> + <value value="27" name="PERF_CCU_2D_RD_REQ"/> + <value value="28" name="PERF_CCU_2D_WR_REQ"/> +</enum> + +<enum name="a6xx_lrz_perfcounter_select"> + <value value="0" name="PERF_LRZ_BUSY_CYCLES"/> + <value value="1" name="PERF_LRZ_STARVE_CYCLES_RAS"/> + <value value="2" name="PERF_LRZ_STALL_CYCLES_RB"/> + <value value="3" name="PERF_LRZ_STALL_CYCLES_VSC"/> + <value value="4" name="PERF_LRZ_STALL_CYCLES_VPC"/> + <value value="5" name="PERF_LRZ_STALL_CYCLES_FLAG_PREFETCH"/> + <value value="6" name="PERF_LRZ_STALL_CYCLES_UCHE"/> + <value value="7" name="PERF_LRZ_LRZ_READ"/> + <value value="8" name="PERF_LRZ_LRZ_WRITE"/> + <value value="9" name="PERF_LRZ_READ_LATENCY"/> + <value value="10" name="PERF_LRZ_MERGE_CACHE_UPDATING"/> + <value value="11" name="PERF_LRZ_PRIM_KILLED_BY_MASKGEN"/> + <value value="12" name="PERF_LRZ_PRIM_KILLED_BY_LRZ"/> + <value value="13" name="PERF_LRZ_VISIBLE_PRIM_AFTER_LRZ"/> + <value value="14" name="PERF_LRZ_FULL_8X8_TILES"/> + <value value="15" name="PERF_LRZ_PARTIAL_8X8_TILES"/> + <value value="16" name="PERF_LRZ_TILE_KILLED"/> + <value value="17" name="PERF_LRZ_TOTAL_PIXEL"/> + <value value="18" name="PERF_LRZ_VISIBLE_PIXEL_AFTER_LRZ"/> + <value value="19" name="PERF_LRZ_FULLY_COVERED_TILES"/> + <value value="20" name="PERF_LRZ_PARTIAL_COVERED_TILES"/> + <value value="21" name="PERF_LRZ_FEEDBACK_ACCEPT"/> + <value value="22" name="PERF_LRZ_FEEDBACK_DISCARD"/> + <value value="23" name="PERF_LRZ_FEEDBACK_STALL"/> + <value value="24" name="PERF_LRZ_STALL_CYCLES_RB_ZPLANE"/> + <value value="25" name="PERF_LRZ_STALL_CYCLES_RB_BPLANE"/> + <value value="26" name="PERF_LRZ_STALL_CYCLES_VC"/> + <value value="27" name="PERF_LRZ_RAS_MASK_TRANS"/> +</enum> + +<enum name="a6xx_cmp_perfcounter_select"> + <value value="0" name="PERF_CMPDECMP_STALL_CYCLES_ARB"/> + <value value="1" name="PERF_CMPDECMP_VBIF_LATENCY_CYCLES"/> + <value value="2" name="PERF_CMPDECMP_VBIF_LATENCY_SAMPLES"/> + <value value="3" name="PERF_CMPDECMP_VBIF_READ_DATA_CCU"/> + <value value="4" name="PERF_CMPDECMP_VBIF_WRITE_DATA_CCU"/> + <value value="5" name="PERF_CMPDECMP_VBIF_READ_REQUEST"/> + <value value="6" name="PERF_CMPDECMP_VBIF_WRITE_REQUEST"/> + <value value="7" name="PERF_CMPDECMP_VBIF_READ_DATA"/> + <value value="8" name="PERF_CMPDECMP_VBIF_WRITE_DATA"/> + <value value="9" name="PERF_CMPDECMP_FLAG_FETCH_CYCLES"/> + <value value="10" name="PERF_CMPDECMP_FLAG_FETCH_SAMPLES"/> + <value value="11" name="PERF_CMPDECMP_DEPTH_WRITE_FLAG1_COUNT"/> + <value value="12" name="PERF_CMPDECMP_DEPTH_WRITE_FLAG2_COUNT"/> + <value value="13" name="PERF_CMPDECMP_DEPTH_WRITE_FLAG3_COUNT"/> + <value value="14" name="PERF_CMPDECMP_DEPTH_WRITE_FLAG4_COUNT"/> + <value value="15" name="PERF_CMPDECMP_DEPTH_WRITE_FLAG5_COUNT"/> + <value value="16" name="PERF_CMPDECMP_DEPTH_WRITE_FLAG6_COUNT"/> + <value value="17" name="PERF_CMPDECMP_DEPTH_WRITE_FLAG8_COUNT"/> + <value value="18" name="PERF_CMPDECMP_COLOR_WRITE_FLAG1_COUNT"/> + <value value="19" name="PERF_CMPDECMP_COLOR_WRITE_FLAG2_COUNT"/> + <value value="20" name="PERF_CMPDECMP_COLOR_WRITE_FLAG3_COUNT"/> + <value value="21" name="PERF_CMPDECMP_COLOR_WRITE_FLAG4_COUNT"/> + <value value="22" name="PERF_CMPDECMP_COLOR_WRITE_FLAG5_COUNT"/> + <value value="23" name="PERF_CMPDECMP_COLOR_WRITE_FLAG6_COUNT"/> + <value value="24" name="PERF_CMPDECMP_COLOR_WRITE_FLAG8_COUNT"/> + <value value="25" name="PERF_CMPDECMP_2D_STALL_CYCLES_VBIF_REQ"/> + <value value="26" name="PERF_CMPDECMP_2D_STALL_CYCLES_VBIF_WR"/> + <value value="27" name="PERF_CMPDECMP_2D_STALL_CYCLES_VBIF_RETURN"/> + <value value="28" name="PERF_CMPDECMP_2D_RD_DATA"/> + <value value="29" name="PERF_CMPDECMP_2D_WR_DATA"/> + <value value="30" name="PERF_CMPDECMP_VBIF_READ_DATA_UCHE_CH0"/> + <value value="31" name="PERF_CMPDECMP_VBIF_READ_DATA_UCHE_CH1"/> + <value value="32" name="PERF_CMPDECMP_2D_OUTPUT_TRANS"/> + <value value="33" name="PERF_CMPDECMP_VBIF_WRITE_DATA_UCHE"/> + <value value="34" name="PERF_CMPDECMP_DEPTH_WRITE_FLAG0_COUNT"/> + <value value="35" name="PERF_CMPDECMP_COLOR_WRITE_FLAG0_COUNT"/> + <value value="36" name="PERF_CMPDECMP_COLOR_WRITE_FLAGALPHA_COUNT"/> + <value value="37" name="PERF_CMPDECMP_2D_BUSY_CYCLES"/> + <value value="38" name="PERF_CMPDECMP_2D_REORDER_STARVE_CYCLES"/> + <value value="39" name="PERF_CMPDECMP_2D_PIXELS"/> +</enum> + +</database> diff --git a/drivers/gpu/drm/msm/registers/adreno/a7xx_enums.xml b/drivers/gpu/drm/msm/registers/adreno/a7xx_enums.xml new file mode 100644 index 000000000000..661b0dd0f675 --- /dev/null +++ b/drivers/gpu/drm/msm/registers/adreno/a7xx_enums.xml @@ -0,0 +1,223 @@ +<?xml version="1.0" encoding="UTF-8"?> +<database xmlns="http://nouveau.freedesktop.org/" +xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" +xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> +<import file="freedreno_copyright.xml"/> +<import file="adreno/adreno_common.xml"/> +<import file="adreno/adreno_pm4.xml"/> + +<enum name="a7xx_statetype_id"> + <value value="0" name="A7XX_TP0_NCTX_REG"/> + <value value="1" name="A7XX_TP0_CTX0_3D_CVS_REG"/> + <value value="2" name="A7XX_TP0_CTX0_3D_CPS_REG"/> + <value value="3" name="A7XX_TP0_CTX1_3D_CVS_REG"/> + <value value="4" name="A7XX_TP0_CTX1_3D_CPS_REG"/> + <value value="5" name="A7XX_TP0_CTX2_3D_CPS_REG"/> + <value value="6" name="A7XX_TP0_CTX3_3D_CPS_REG"/> + <value value="9" name="A7XX_TP0_TMO_DATA"/> + <value value="10" name="A7XX_TP0_SMO_DATA"/> + <value value="11" name="A7XX_TP0_MIPMAP_BASE_DATA"/> + <value value="32" name="A7XX_SP_NCTX_REG"/> + <value value="33" name="A7XX_SP_CTX0_3D_CVS_REG"/> + <value value="34" name="A7XX_SP_CTX0_3D_CPS_REG"/> + <value value="35" name="A7XX_SP_CTX1_3D_CVS_REG"/> + <value value="36" name="A7XX_SP_CTX1_3D_CPS_REG"/> + <value value="37" name="A7XX_SP_CTX2_3D_CPS_REG"/> + <value value="38" name="A7XX_SP_CTX3_3D_CPS_REG"/> + <value value="39" name="A7XX_SP_INST_DATA"/> + <value value="40" name="A7XX_SP_INST_DATA_1"/> + <value value="41" name="A7XX_SP_LB_0_DATA"/> + <value value="42" name="A7XX_SP_LB_1_DATA"/> + <value value="43" name="A7XX_SP_LB_2_DATA"/> + <value value="44" name="A7XX_SP_LB_3_DATA"/> + <value value="45" name="A7XX_SP_LB_4_DATA"/> + <value value="46" name="A7XX_SP_LB_5_DATA"/> + <value value="47" name="A7XX_SP_LB_6_DATA"/> + <value value="48" name="A7XX_SP_LB_7_DATA"/> + <value value="49" name="A7XX_SP_CB_RAM"/> + <value value="50" name="A7XX_SP_LB_13_DATA"/> + <value value="51" name="A7XX_SP_LB_14_DATA"/> + <value value="52" name="A7XX_SP_INST_TAG"/> + <value value="53" name="A7XX_SP_INST_DATA_2"/> + <value value="54" name="A7XX_SP_TMO_TAG"/> + <value value="55" name="A7XX_SP_SMO_TAG"/> + <value value="56" name="A7XX_SP_STATE_DATA"/> + <value value="57" name="A7XX_SP_HWAVE_RAM"/> + <value value="58" name="A7XX_SP_L0_INST_BUF"/> + <value value="59" name="A7XX_SP_LB_8_DATA"/> + <value value="60" name="A7XX_SP_LB_9_DATA"/> + <value value="61" name="A7XX_SP_LB_10_DATA"/> + <value value="62" name="A7XX_SP_LB_11_DATA"/> + <value value="63" name="A7XX_SP_LB_12_DATA"/> + <value value="64" name="A7XX_HLSQ_DATAPATH_DSTR_META"/> + <value value="67" name="A7XX_HLSQ_L2STC_TAG_RAM"/> + <value value="68" name="A7XX_HLSQ_L2STC_INFO_CMD"/> + <value value="69" name="A7XX_HLSQ_CVS_BE_CTXT_BUF_RAM_TAG"/> + <value value="70" name="A7XX_HLSQ_CPS_BE_CTXT_BUF_RAM_TAG"/> + <value value="71" name="A7XX_HLSQ_GFX_CVS_BE_CTXT_BUF_RAM"/> + <value value="72" name="A7XX_HLSQ_GFX_CPS_BE_CTXT_BUF_RAM"/> + <value value="73" name="A7XX_HLSQ_CHUNK_CVS_RAM"/> + <value value="74" name="A7XX_HLSQ_CHUNK_CPS_RAM"/> + <value value="75" name="A7XX_HLSQ_CHUNK_CVS_RAM_TAG"/> + <value value="76" name="A7XX_HLSQ_CHUNK_CPS_RAM_TAG"/> + <value value="77" name="A7XX_HLSQ_ICB_CVS_CB_BASE_TAG"/> + <value value="78" name="A7XX_HLSQ_ICB_CPS_CB_BASE_TAG"/> + <value value="79" name="A7XX_HLSQ_CVS_MISC_RAM"/> + <value value="80" name="A7XX_HLSQ_CPS_MISC_RAM"/> + <value value="81" name="A7XX_HLSQ_CPS_MISC_RAM_1"/> + <value value="82" name="A7XX_HLSQ_INST_RAM"/> + <value value="83" name="A7XX_HLSQ_GFX_CVS_CONST_RAM"/> + <value value="84" name="A7XX_HLSQ_GFX_CPS_CONST_RAM"/> + <value value="85" name="A7XX_HLSQ_CVS_MISC_RAM_TAG"/> + <value value="86" name="A7XX_HLSQ_CPS_MISC_RAM_TAG"/> + <value value="87" name="A7XX_HLSQ_INST_RAM_TAG"/> + <value value="88" name="A7XX_HLSQ_GFX_CVS_CONST_RAM_TAG"/> + <value value="89" name="A7XX_HLSQ_GFX_CPS_CONST_RAM_TAG"/> + <value value="90" name="A7XX_HLSQ_GFX_LOCAL_MISC_RAM"/> + <value value="91" name="A7XX_HLSQ_GFX_LOCAL_MISC_RAM_TAG"/> + <value value="92" name="A7XX_HLSQ_INST_RAM_1"/> + <value value="93" name="A7XX_HLSQ_STPROC_META"/> + <value value="94" name="A7XX_HLSQ_BV_BE_META"/> + <value value="95" name="A7XX_HLSQ_INST_RAM_2"/> + <value value="96" name="A7XX_HLSQ_DATAPATH_META"/> + <value value="97" name="A7XX_HLSQ_FRONTEND_META"/> + <value value="98" name="A7XX_HLSQ_INDIRECT_META"/> + <value value="99" name="A7XX_HLSQ_BACKEND_META"/> +</enum> + +<enum name="a7xx_state_location"> + <value value="0" name="A7XX_HLSQ_STATE"/> + <value value="1" name="A7XX_HLSQ_DP"/> + <value value="2" name="A7XX_SP_TOP"/> + <value value="3" name="A7XX_USPTP"/> + <value value="4" name="A7XX_HLSQ_DP_STR"/> +</enum> + +<enum name="a7xx_pipe"> + <value value="0" name="A7XX_PIPE_NONE"/> + <value value="1" name="A7XX_PIPE_BR"/> + <value value="2" name="A7XX_PIPE_BV"/> + <value value="3" name="A7XX_PIPE_LPAC"/> +</enum> + +<enum name="a7xx_cluster"> + <value value="0" name="A7XX_CLUSTER_NONE"/> + <value value="1" name="A7XX_CLUSTER_FE"/> + <value value="2" name="A7XX_CLUSTER_SP_VS"/> + <value value="3" name="A7XX_CLUSTER_PC_VS"/> + <value value="4" name="A7XX_CLUSTER_GRAS"/> + <value value="5" name="A7XX_CLUSTER_SP_PS"/> + <value value="6" name="A7XX_CLUSTER_VPC_PS"/> + <value value="7" name="A7XX_CLUSTER_PS"/> +</enum> + +<enum name="a7xx_debugbus_id"> + <value value="1" name="A7XX_DBGBUS_CP_0_0"/> + <value value="2" name="A7XX_DBGBUS_CP_0_1"/> + <value value="3" name="A7XX_DBGBUS_RBBM"/> + <value value="5" name="A7XX_DBGBUS_GBIF_GX"/> + <value value="6" name="A7XX_DBGBUS_GBIF_CX"/> + <value value="7" name="A7XX_DBGBUS_HLSQ"/> + <value value="9" name="A7XX_DBGBUS_UCHE_0"/> + <value value="10" name="A7XX_DBGBUS_UCHE_1"/> + <value value="13" name="A7XX_DBGBUS_TESS_BR"/> + <value value="14" name="A7XX_DBGBUS_TESS_BV"/> + <value value="17" name="A7XX_DBGBUS_PC_BR"/> + <value value="18" name="A7XX_DBGBUS_PC_BV"/> + <value value="21" name="A7XX_DBGBUS_VFDP_BR"/> + <value value="22" name="A7XX_DBGBUS_VFDP_BV"/> + <value value="25" name="A7XX_DBGBUS_VPC_BR"/> + <value value="26" name="A7XX_DBGBUS_VPC_BV"/> + <value value="29" name="A7XX_DBGBUS_TSE_BR"/> + <value value="30" name="A7XX_DBGBUS_TSE_BV"/> + <value value="33" name="A7XX_DBGBUS_RAS_BR"/> + <value value="34" name="A7XX_DBGBUS_RAS_BV"/> + <value value="37" name="A7XX_DBGBUS_VSC"/> + <value value="39" name="A7XX_DBGBUS_COM_0"/> + <value value="43" name="A7XX_DBGBUS_LRZ_BR"/> + <value value="44" name="A7XX_DBGBUS_LRZ_BV"/> + <value value="47" name="A7XX_DBGBUS_UFC_0"/> + <value value="48" name="A7XX_DBGBUS_UFC_1"/> + <value value="55" name="A7XX_DBGBUS_GMU_GX"/> + <value value="59" name="A7XX_DBGBUS_DBGC"/> + <value value="60" name="A7XX_DBGBUS_CX"/> + <value value="61" name="A7XX_DBGBUS_GMU_CX"/> + <value value="62" name="A7XX_DBGBUS_GPC_BR"/> + <value value="63" name="A7XX_DBGBUS_GPC_BV"/> + <value value="66" name="A7XX_DBGBUS_LARC"/> + <value value="68" name="A7XX_DBGBUS_HLSQ_SPTP"/> + <value value="70" name="A7XX_DBGBUS_RB_0"/> + <value value="71" name="A7XX_DBGBUS_RB_1"/> + <value value="72" name="A7XX_DBGBUS_RB_2"/> + <value value="73" name="A7XX_DBGBUS_RB_3"/> + <value value="74" name="A7XX_DBGBUS_RB_4"/> + <value value="75" name="A7XX_DBGBUS_RB_5"/> + <value value="102" name="A7XX_DBGBUS_UCHE_WRAPPER"/> + <value value="106" name="A7XX_DBGBUS_CCU_0"/> + <value value="107" name="A7XX_DBGBUS_CCU_1"/> + <value value="108" name="A7XX_DBGBUS_CCU_2"/> + <value value="109" name="A7XX_DBGBUS_CCU_3"/> + <value value="110" name="A7XX_DBGBUS_CCU_4"/> + <value value="111" name="A7XX_DBGBUS_CCU_5"/> + <value value="138" name="A7XX_DBGBUS_VFD_BR_0"/> + <value value="139" name="A7XX_DBGBUS_VFD_BR_1"/> + <value value="140" name="A7XX_DBGBUS_VFD_BR_2"/> + <value value="141" name="A7XX_DBGBUS_VFD_BR_3"/> + <value value="142" name="A7XX_DBGBUS_VFD_BR_4"/> + <value value="143" name="A7XX_DBGBUS_VFD_BR_5"/> + <value value="144" name="A7XX_DBGBUS_VFD_BR_6"/> + <value value="145" name="A7XX_DBGBUS_VFD_BR_7"/> + <value value="202" name="A7XX_DBGBUS_VFD_BV_0"/> + <value value="203" name="A7XX_DBGBUS_VFD_BV_1"/> + <value value="204" name="A7XX_DBGBUS_VFD_BV_2"/> + <value value="205" name="A7XX_DBGBUS_VFD_BV_3"/> + <value value="234" name="A7XX_DBGBUS_USP_0"/> + <value value="235" name="A7XX_DBGBUS_USP_1"/> + <value value="236" name="A7XX_DBGBUS_USP_2"/> + <value value="237" name="A7XX_DBGBUS_USP_3"/> + <value value="238" name="A7XX_DBGBUS_USP_4"/> + <value value="239" name="A7XX_DBGBUS_USP_5"/> + <value value="266" name="A7XX_DBGBUS_TP_0"/> + <value value="267" name="A7XX_DBGBUS_TP_1"/> + <value value="268" name="A7XX_DBGBUS_TP_2"/> + <value value="269" name="A7XX_DBGBUS_TP_3"/> + <value value="270" name="A7XX_DBGBUS_TP_4"/> + <value value="271" name="A7XX_DBGBUS_TP_5"/> + <value value="272" name="A7XX_DBGBUS_TP_6"/> + <value value="273" name="A7XX_DBGBUS_TP_7"/> + <value value="274" name="A7XX_DBGBUS_TP_8"/> + <value value="275" name="A7XX_DBGBUS_TP_9"/> + <value value="276" name="A7XX_DBGBUS_TP_10"/> + <value value="277" name="A7XX_DBGBUS_TP_11"/> + <value value="330" name="A7XX_DBGBUS_USPTP_0"/> + <value value="331" name="A7XX_DBGBUS_USPTP_1"/> + <value value="332" name="A7XX_DBGBUS_USPTP_2"/> + <value value="333" name="A7XX_DBGBUS_USPTP_3"/> + <value value="334" name="A7XX_DBGBUS_USPTP_4"/> + <value value="335" name="A7XX_DBGBUS_USPTP_5"/> + <value value="336" name="A7XX_DBGBUS_USPTP_6"/> + <value value="337" name="A7XX_DBGBUS_USPTP_7"/> + <value value="338" name="A7XX_DBGBUS_USPTP_8"/> + <value value="339" name="A7XX_DBGBUS_USPTP_9"/> + <value value="340" name="A7XX_DBGBUS_USPTP_10"/> + <value value="341" name="A7XX_DBGBUS_USPTP_11"/> + <value value="396" name="A7XX_DBGBUS_CCHE_0"/> + <value value="397" name="A7XX_DBGBUS_CCHE_1"/> + <value value="398" name="A7XX_DBGBUS_CCHE_2"/> + <value value="408" name="A7XX_DBGBUS_VPC_DSTR_0"/> + <value value="409" name="A7XX_DBGBUS_VPC_DSTR_1"/> + <value value="410" name="A7XX_DBGBUS_VPC_DSTR_2"/> + <value value="411" name="A7XX_DBGBUS_HLSQ_DP_STR_0"/> + <value value="412" name="A7XX_DBGBUS_HLSQ_DP_STR_1"/> + <value value="413" name="A7XX_DBGBUS_HLSQ_DP_STR_2"/> + <value value="414" name="A7XX_DBGBUS_HLSQ_DP_STR_3"/> + <value value="415" name="A7XX_DBGBUS_HLSQ_DP_STR_4"/> + <value value="416" name="A7XX_DBGBUS_HLSQ_DP_STR_5"/> + <value value="443" name="A7XX_DBGBUS_UFC_DSTR_0"/> + <value value="444" name="A7XX_DBGBUS_UFC_DSTR_1"/> + <value value="445" name="A7XX_DBGBUS_UFC_DSTR_2"/> + <value value="446" name="A7XX_DBGBUS_CGC_SUBCORE"/> + <value value="447" name="A7XX_DBGBUS_CGC_CORE"/> +</enum> + +</database> diff --git a/drivers/gpu/drm/msm/registers/adreno/a7xx_perfcntrs.xml b/drivers/gpu/drm/msm/registers/adreno/a7xx_perfcntrs.xml new file mode 100644 index 000000000000..9bf78b0a854b --- /dev/null +++ b/drivers/gpu/drm/msm/registers/adreno/a7xx_perfcntrs.xml @@ -0,0 +1,1030 @@ +<?xml version="1.0" encoding="UTF-8"?> +<database xmlns="http://nouveau.freedesktop.org/" +xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" +xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> +<import file="freedreno_copyright.xml"/> +<import file="adreno/adreno_common.xml"/> +<import file="adreno/adreno_pm4.xml"/> + +<enum name="a7xx_cp_perfcounter_select"> + <value value="0" name="A7XX_PERF_CP_ALWAYS_COUNT"/> + <value value="1" name="A7XX_PERF_CP_BUSY_GFX_CORE_IDLE"/> + <value value="2" name="A7XX_PERF_CP_BUSY_CYCLES"/> + <value value="3" name="A7XX_PERF_CP_NUM_PREEMPTIONS"/> + <value value="4" name="A7XX_PERF_CP_PREEMPTION_REACTION_DELAY"/> + <value value="5" name="A7XX_PERF_CP_PREEMPTION_SWITCH_OUT_TIME"/> + <value value="6" name="A7XX_PERF_CP_PREEMPTION_SWITCH_IN_TIME"/> + <value value="7" name="A7XX_PERF_CP_DEAD_DRAWS_IN_BIN_RENDER"/> + <value value="8" name="A7XX_PERF_CP_PREDICATED_DRAWS_KILLED"/> + <value value="9" name="A7XX_PERF_CP_MODE_SWITCH"/> + <value value="10" name="A7XX_PERF_CP_ZPASS_DONE"/> + <value value="11" name="A7XX_PERF_CP_CONTEXT_DONE"/> + <value value="12" name="A7XX_PERF_CP_CACHE_FLUSH"/> + <value value="13" name="A7XX_PERF_CP_LONG_PREEMPTIONS"/> + <value value="14" name="A7XX_PERF_CP_SQE_I_CACHE_STARVE"/> + <value value="15" name="A7XX_PERF_CP_SQE_IDLE"/> + <value value="16" name="A7XX_PERF_CP_SQE_PM4_STARVE_RB_IB"/> + <value value="17" name="A7XX_PERF_CP_SQE_PM4_STARVE_SDS"/> + <value value="18" name="A7XX_PERF_CP_SQE_MRB_STARVE"/> + <value value="19" name="A7XX_PERF_CP_SQE_RRB_STARVE"/> + <value value="20" name="A7XX_PERF_CP_SQE_VSD_STARVE"/> + <value value="21" name="A7XX_PERF_CP_VSD_DECODE_STARVE"/> + <value value="22" name="A7XX_PERF_CP_SQE_PIPE_OUT_STALL"/> + <value value="23" name="A7XX_PERF_CP_SQE_SYNC_STALL"/> + <value value="24" name="A7XX_PERF_CP_SQE_PM4_WFI_STALL"/> + <value value="25" name="A7XX_PERF_CP_SQE_SYS_WFI_STALL"/> + <value value="26" name="A7XX_PERF_CP_SQE_T4_EXEC"/> + <value value="27" name="A7XX_PERF_CP_SQE_LOAD_STATE_EXEC"/> + <value value="28" name="A7XX_PERF_CP_SQE_SAVE_SDS_STATE"/> + <value value="29" name="A7XX_PERF_CP_SQE_DRAW_EXEC"/> + <value value="30" name="A7XX_PERF_CP_SQE_CTXT_REG_BUNCH_EXEC"/> + <value value="31" name="A7XX_PERF_CP_SQE_EXEC_PROFILED"/> + <value value="32" name="A7XX_PERF_CP_MEMORY_POOL_EMPTY"/> + <value value="33" name="A7XX_PERF_CP_MEMORY_POOL_SYNC_STALL"/> + <value value="34" name="A7XX_PERF_CP_MEMORY_POOL_ABOVE_THRESH"/> + <value value="35" name="A7XX_PERF_CP_AHB_WR_STALL_PRE_DRAWS"/> + <value value="36" name="A7XX_PERF_CP_AHB_STALL_SQE_GMU"/> + <value value="37" name="A7XX_PERF_CP_AHB_STALL_SQE_WR_OTHER"/> + <value value="38" name="A7XX_PERF_CP_AHB_STALL_SQE_RD_OTHER"/> + <value value="39" name="A7XX_PERF_CP_CLUSTER0_EMPTY"/> + <value value="40" name="A7XX_PERF_CP_CLUSTER1_EMPTY"/> + <value value="41" name="A7XX_PERF_CP_CLUSTER2_EMPTY"/> + <value value="42" name="A7XX_PERF_CP_CLUSTER3_EMPTY"/> + <value value="43" name="A7XX_PERF_CP_CLUSTER4_EMPTY"/> + <value value="44" name="A7XX_PERF_CP_CLUSTER5_EMPTY"/> + <value value="45" name="A7XX_PERF_CP_PM4_DATA"/> + <value value="46" name="A7XX_PERF_CP_PM4_HEADERS"/> + <value value="47" name="A7XX_PERF_CP_VBIF_READ_BEATS"/> + <value value="48" name="A7XX_PERF_CP_VBIF_WRITE_BEATS"/> + <value value="49" name="A7XX_PERF_CP_SQE_INSTR_COUNTER"/> + <value value="50" name="A7XX_PERF_CP_RESERVED_50"/> + <value value="51" name="A7XX_PERF_CP_RESERVED_51"/> + <value value="52" name="A7XX_PERF_CP_RESERVED_52"/> + <value value="53" name="A7XX_PERF_CP_RESERVED_53"/> + <value value="54" name="A7XX_PERF_CP_RESERVED_54"/> + <value value="55" name="A7XX_PERF_CP_RESERVED_55"/> + <value value="56" name="A7XX_PERF_CP_RESERVED_56"/> + <value value="57" name="A7XX_PERF_CP_RESERVED_57"/> + <value value="58" name="A7XX_PERF_CP_RESERVED_58"/> + <value value="59" name="A7XX_PERF_CP_RESERVED_59"/> + <value value="60" name="A7XX_PERF_CP_CLUSTER0_FULL"/> + <value value="61" name="A7XX_PERF_CP_CLUSTER1_FULL"/> + <value value="62" name="A7XX_PERF_CP_CLUSTER2_FULL"/> + <value value="63" name="A7XX_PERF_CP_CLUSTER3_FULL"/> + <value value="64" name="A7XX_PERF_CP_CLUSTER4_FULL"/> + <value value="65" name="A7XX_PERF_CP_CLUSTER5_FULL"/> + <value value="66" name="A7XX_PERF_CP_CLUSTER6_FULL"/> + <value value="67" name="A7XX_PERF_CP_CLUSTER6_EMPTY"/> + <value value="68" name="A7XX_PERF_CP_ICACHE_MISSES"/> + <value value="69" name="A7XX_PERF_CP_ICACHE_HITS"/> + <value value="70" name="A7XX_PERF_CP_ICACHE_STALL"/> + <value value="71" name="A7XX_PERF_CP_DCACHE_MISSES"/> + <value value="72" name="A7XX_PERF_CP_DCACHE_HITS"/> + <value value="73" name="A7XX_PERF_CP_DCACHE_STALLS"/> + <value value="74" name="A7XX_PERF_CP_AQE_SQE_STALL"/> + <value value="75" name="A7XX_PERF_CP_SQE_AQE_STARVE"/> + <value value="76" name="A7XX_PERF_CP_PREEMPT_LATENCY"/> + <value value="77" name="A7XX_PERF_CP_SQE_MD8_STALL_CYCLES"/> + <value value="78" name="A7XX_PERF_CP_SQE_MESH_EXEC_CYCLES"/> + <value value="79" name="A7XX_PERF_CP_AQE_NUM_AS_CHUNKS"/> + <value value="80" name="A7XX_PERF_CP_AQE_NUM_MS_CHUNKS"/> +</enum> + +<enum name="a7xx_rbbm_perfcounter_select"> + <value value="0" name="A7XX_PERF_RBBM_ALWAYS_COUNT"/> + <value value="1" name="A7XX_PERF_RBBM_ALWAYS_ON"/> + <value value="2" name="A7XX_PERF_RBBM_TSE_BUSY"/> + <value value="3" name="A7XX_PERF_RBBM_RAS_BUSY"/> + <value value="4" name="A7XX_PERF_RBBM_PC_DCALL_BUSY"/> + <value value="5" name="A7XX_PERF_RBBM_PC_VSD_BUSY"/> + <value value="6" name="A7XX_PERF_RBBM_STATUS_MASKED"/> + <value value="7" name="A7XX_PERF_RBBM_COM_BUSY"/> + <value value="8" name="A7XX_PERF_RBBM_DCOM_BUSY"/> + <value value="9" name="A7XX_PERF_RBBM_VBIF_BUSY"/> + <value value="10" name="A7XX_PERF_RBBM_VSC_BUSY"/> + <value value="11" name="A7XX_PERF_RBBM_TESS_BUSY"/> + <value value="12" name="A7XX_PERF_RBBM_UCHE_BUSY"/> + <value value="13" name="A7XX_PERF_RBBM_HLSQ_BUSY"/> +</enum> + +<enum name="a7xx_pc_perfcounter_select"> + <value value="0" name="A7XX_PERF_PC_BUSY_CYCLES"/> + <value value="1" name="A7XX_PERF_PC_WORKING_CYCLES"/> + <value value="2" name="A7XX_PERF_PC_STALL_CYCLES_VFD"/> + <value value="3" name="A7XX_PERF_PC_RESERVED"/> + <value value="4" name="A7XX_PERF_PC_STALL_CYCLES_VPC"/> + <value value="5" name="A7XX_PERF_PC_STALL_CYCLES_UCHE"/> + <value value="6" name="A7XX_PERF_PC_STALL_CYCLES_TESS"/> + <value value="7" name="A7XX_PERF_PC_STALL_CYCLES_VFD_ONLY"/> + <value value="8" name="A7XX_PERF_PC_STALL_CYCLES_VPC_ONLY"/> + <value value="9" name="A7XX_PERF_PC_PASS1_TF_STALL_CYCLES"/> + <value value="10" name="A7XX_PERF_PC_STARVE_CYCLES_FOR_INDEX"/> + <value value="11" name="A7XX_PERF_PC_STARVE_CYCLES_FOR_TESS_FACTOR"/> + <value value="12" name="A7XX_PERF_PC_STARVE_CYCLES_FOR_VIZ_STREAM"/> + <value value="13" name="A7XX_PERF_PC_STARVE_CYCLES_DI"/> + <value value="14" name="A7XX_PERF_PC_VIS_STREAMS_LOADED"/> + <value value="15" name="A7XX_PERF_PC_INSTANCES"/> + <value value="16" name="A7XX_PERF_PC_VPC_PRIMITIVES"/> + <value value="17" name="A7XX_PERF_PC_DEAD_PRIM"/> + <value value="18" name="A7XX_PERF_PC_LIVE_PRIM"/> + <value value="19" name="A7XX_PERF_PC_VERTEX_HITS"/> + <value value="20" name="A7XX_PERF_PC_IA_VERTICES"/> + <value value="21" name="A7XX_PERF_PC_IA_PRIMITIVES"/> + <value value="22" name="A7XX_PERF_PC_RESERVED_22"/> + <value value="23" name="A7XX_PERF_PC_HS_INVOCATIONS"/> + <value value="24" name="A7XX_PERF_PC_DS_INVOCATIONS"/> + <value value="25" name="A7XX_PERF_PC_VS_INVOCATIONS"/> + <value value="26" name="A7XX_PERF_PC_GS_INVOCATIONS"/> + <value value="27" name="A7XX_PERF_PC_DS_PRIMITIVES"/> + <value value="28" name="A7XX_PERF_PC_3D_DRAWCALLS"/> + <value value="29" name="A7XX_PERF_PC_2D_DRAWCALLS"/> + <value value="30" name="A7XX_PERF_PC_NON_DRAWCALL_GLOBAL_EVENTS"/> + <value value="31" name="A7XX_PERF_PC_TESS_BUSY_CYCLES"/> + <value value="32" name="A7XX_PERF_PC_TESS_WORKING_CYCLES"/> + <value value="33" name="A7XX_PERF_PC_TESS_STALL_CYCLES_PC"/> + <value value="34" name="A7XX_PERF_PC_TESS_STARVE_CYCLES_PC"/> + <value value="35" name="A7XX_PERF_PC_TESS_SINGLE_PRIM_CYCLES"/> + <value value="36" name="A7XX_PERF_PC_TESS_PC_UV_TRANS"/> + <value value="37" name="A7XX_PERF_PC_TESS_PC_UV_PATCHES"/> + <value value="38" name="A7XX_PERF_PC_TESS_FACTOR_TRANS"/> + <value value="39" name="A7XX_PERF_PC_TAG_CHECKED_VERTICES"/> + <value value="40" name="A7XX_PERF_PC_MESH_VS_WAVES"/> + <value value="41" name="A7XX_PERF_PC_MESH_DRAWS"/> + <value value="42" name="A7XX_PERF_PC_MESH_DEAD_DRAWS"/> + <value value="43" name="A7XX_PERF_PC_MESH_MVIS_EN_DRAWS"/> + <value value="44" name="A7XX_PERF_PC_MESH_DEAD_PRIM"/> + <value value="45" name="A7XX_PERF_PC_MESH_LIVE_PRIM"/> + <value value="46" name="A7XX_PERF_PC_MESH_PA_EN_PRIM"/> + <value value="47" name="A7XX_PERF_PC_STARVE_CYCLES_FOR_MVIS_STREAM"/> + <value value="48" name="A7XX_PERF_PC_STARVE_CYCLES_PREDRAW"/> + <value value="49" name="A7XX_PERF_PC_STALL_CYCLES_COMPUTE_GFX"/> + <value value="50" name="A7XX_PERF_PC_STALL_CYCLES_GFX_COMPUTE"/> + <value value="51" name="A7XX_PERF_PC_TESS_PC_MULTI_PATCH_TRANS"/> +</enum> + +<enum name="a7xx_vfd_perfcounter_select"> + <value value="0" name="A7XX_PERF_VFD_BUSY_CYCLES"/> + <value value="1" name="A7XX_PERF_VFD_STALL_CYCLES_UCHE"/> + <value value="2" name="A7XX_PERF_VFD_STALL_CYCLES_VPC_ALLOC"/> + <value value="3" name="A7XX_PERF_VFD_STALL_CYCLES_SP_INFO"/> + <value value="4" name="A7XX_PERF_VFD_STALL_CYCLES_SP_ATTR"/> + <value value="5" name="A7XX_PERF_VFD_STARVE_CYCLES_UCHE"/> + <value value="6" name="A7XX_PERF_VFD_RBUFFER_FULL"/> + <value value="7" name="A7XX_PERF_VFD_ATTR_INFO_FIFO_FULL"/> + <value value="8" name="A7XX_PERF_VFD_DECODED_ATTRIBUTE_BYTES"/> + <value value="9" name="A7XX_PERF_VFD_NUM_ATTRIBUTES"/> + <value value="10" name="A7XX_PERF_VFD_UPPER_SHADER_FIBERS"/> + <value value="11" name="A7XX_PERF_VFD_LOWER_SHADER_FIBERS"/> + <value value="12" name="A7XX_PERF_VFD_MODE_0_FIBERS"/> + <value value="13" name="A7XX_PERF_VFD_MODE_1_FIBERS"/> + <value value="14" name="A7XX_PERF_VFD_MODE_2_FIBERS"/> + <value value="15" name="A7XX_PERF_VFD_MODE_3_FIBERS"/> + <value value="16" name="A7XX_PERF_VFD_MODE_4_FIBERS"/> + <value value="17" name="A7XX_PERF_VFD_TOTAL_VERTICES"/> + <value value="18" name="A7XX_PERF_VFDP_STALL_CYCLES_VFD"/> + <value value="19" name="A7XX_PERF_VFDP_STALL_CYCLES_VFD_INDEX"/> + <value value="20" name="A7XX_PERF_VFDP_STALL_CYCLES_VFD_PROG"/> + <value value="21" name="A7XX_PERF_VFDP_STARVE_CYCLES_PC"/> + <value value="22" name="A7XX_PERF_VFDP_VS_STAGE_WAVES"/> + <value value="23" name="A7XX_PERF_VFD_STALL_CYCLES_PRG_END_FE"/> + <value value="24" name="A7XX_PERF_VFD_STALL_CYCLES_CBSYNC"/> +</enum> + +<enum name="a7xx_hlsq_perfcounter_select"> + <value value="0" name="A7XX_PERF_HLSQ_BUSY_CYCLES"/> + <value value="1" name="A7XX_PERF_HLSQ_STALL_CYCLES_UCHE"/> + <value value="2" name="A7XX_PERF_HLSQ_STALL_CYCLES_SP_STATE"/> + <value value="3" name="A7XX_PERF_HLSQ_STALL_CYCLES_SP_FS_STAGE"/> + <value value="4" name="A7XX_PERF_HLSQ_UCHE_LATENCY_CYCLES"/> + <value value="5" name="A7XX_PERF_HLSQ_UCHE_LATENCY_COUNT"/> + <value value="6" name="A7XX_PERF_HLSQ_RESERVED_6"/> + <value value="7" name="A7XX_PERF_HLSQ_RESERVED_7"/> + <value value="8" name="A7XX_PERF_HLSQ_RESERVED_8"/> + <value value="9" name="A7XX_PERF_HLSQ_RESERVED_9"/> + <value value="10" name="A7XX_PERF_HLSQ_COMPUTE_DRAWCALLS"/> + <value value="11" name="A7XX_PERF_HLSQ_FS_DATA_WAIT_PROGRAMMING"/> + <value value="12" name="A7XX_PERF_HLSQ_DUAL_FS_PROG_ACTIVE"/> + <value value="13" name="A7XX_PERF_HLSQ_DUAL_VS_PROG_ACTIVE"/> + <value value="14" name="A7XX_PERF_HLSQ_FS_BATCH_COUNT_ZERO"/> + <value value="15" name="A7XX_PERF_HLSQ_VS_BATCH_COUNT_ZERO"/> + <value value="16" name="A7XX_PERF_HLSQ_WAVE_PENDING_NO_QUAD"/> + <value value="17" name="A7XX_PERF_HLSQ_WAVE_PENDING_NO_PRIM_BASE"/> + <value value="18" name="A7XX_PERF_HLSQ_STALL_CYCLES_VPC"/> + <value value="19" name="A7XX_PERF_HLSQ_RESERVED_19"/> + <value value="20" name="A7XX_PERF_HLSQ_DRAW_MODE_SWITCH_VSFS_SYNC"/> + <value value="21" name="A7XX_PERF_HLSQ_VSBR_STALL_CYCLES"/> + <value value="22" name="A7XX_PERF_HLSQ_FS_STALL_CYCLES"/> + <value value="23" name="A7XX_PERF_HLSQ_LPAC_STALL_CYCLES"/> + <value value="24" name="A7XX_PERF_HLSQ_BV_STALL_CYCLES"/> + <value value="25" name="A7XX_PERF_HLSQ_VSBR_DEREF_CYCLES"/> + <value value="26" name="A7XX_PERF_HLSQ_FS_DEREF_CYCLES"/> + <value value="27" name="A7XX_PERF_HLSQ_LPAC_DEREF_CYCLES"/> + <value value="28" name="A7XX_PERF_HLSQ_BV_DEREF_CYCLES"/> + <value value="29" name="A7XX_PERF_HLSQ_VSBR_S2W_CYCLES"/> + <value value="30" name="A7XX_PERF_HLSQ_FS_S2W_CYCLES"/> + <value value="31" name="A7XX_PERF_HLSQ_LPAC_S2W_CYCLES"/> + <value value="32" name="A7XX_PERF_HLSQ_BV_S2W_CYCLES"/> + <value value="33" name="A7XX_PERF_HLSQ_VSBR_WAIT_FS_S2W"/> + <value value="34" name="A7XX_PERF_HLSQ_FS_WAIT_VS_S2W"/> + <value value="35" name="A7XX_PERF_HLSQ_LPAC_WAIT_VS_S2W"/> + <value value="36" name="A7XX_PERF_HLSQ_BV_WAIT_FS_S2W"/> + <value value="37" name="A7XX_PERF_HLSQ_VS_WAIT_CONST_RESOURCE"/> + <value value="38" name="A7XX_PERF_HLSQ_FS_WAIT_SAME_VS_S2W"/> + <value value="39" name="A7XX_PERF_HLSQ_FS_STARVING_SP"/> + <value value="40" name="A7XX_PERF_HLSQ_VS_DATA_WAIT_PROGRAMMING"/> + <value value="41" name="A7XX_PERF_HLSQ_BV_DATA_WAIT_PROGRAMMING"/> + <value value="42" name="A7XX_PERF_HLSQ_STPROC_WAVE_CONTEXTS_VS"/> + <value value="43" name="A7XX_PERF_HLSQ_STPROC_WAVE_CONTEXT_CYCLES_VS"/> + <value value="44" name="A7XX_PERF_HLSQ_STPROC_WAVE_CONTEXTS_FS"/> + <value value="45" name="A7XX_PERF_HLSQ_STPROC_WAVE_CONTEXT_CYCLES_FS"/> + <value value="46" name="A7XX_PERF_HLSQ_STPROC_WAVE_CONTEXTS_BV"/> + <value value="47" name="A7XX_PERF_HLSQ_STPROC_WAVE_CONTEXT_CYCLES_BV"/> + <value value="48" name="A7XX_PERF_HLSQ_STPROC_WAVE_CONTEXTS_LPAC"/> + <value value="49" name="A7XX_PERF_HLSQ_STPROC_WAVE_CONTEXT_CYCLES_LPAC"/> + <value value="50" name="A7XX_PERF_HLSQ_SPTROC_STCHE_WARMUP_INC_VS"/> + <value value="51" name="A7XX_PERF_HLSQ_SPTROC_STCHE_WARMUP_INC_FS"/> + <value value="52" name="A7XX_PERF_HLSQ_SPTROC_STCHE_WARMUP_INC_BV"/> + <value value="53" name="A7XX_PERF_HLSQ_SPTROC_STCHE_WARMUP_INC_LPAC"/> + <value value="54" name="A7XX_PERF_HLSQ_SPTROC_STCHE_MISS_INC_VS"/> + <value value="55" name="A7XX_PERF_HLSQ_SPTROC_STCHE_MISS_INC_FS"/> + <value value="56" name="A7XX_PERF_HLSQ_SPTROC_STCHE_MISS_INC_BV"/> + <value value="57" name="A7XX_PERF_HLSQ_SPTROC_STCHE_MISS_INC_LPAC"/> +</enum> + +<enum name="a7xx_vpc_perfcounter_select"> + <value value="0" name="A7XX_PERF_VPC_BUSY_CYCLES"/> + <value value="1" name="A7XX_PERF_VPC_WORKING_CYCLES"/> + <value value="2" name="A7XX_PERF_VPC_STALL_CYCLES_UCHE"/> + <value value="3" name="A7XX_PERF_VPC_STALL_CYCLES_VFD_WACK"/> + <value value="4" name="A7XX_PERF_VPC_STALL_CYCLES_HLSQ_PRIM_ALLOC"/> + <value value="5" name="A7XX_PERF_VPC_RESERVED_5"/> + <value value="6" name="A7XX_PERF_VPC_STALL_CYCLES_SP_LM"/> + <value value="7" name="A7XX_PERF_VPC_STARVE_CYCLES_SP"/> + <value value="8" name="A7XX_PERF_VPC_STARVE_CYCLES_LRZ"/> + <value value="9" name="A7XX_PERF_VPC_PC_PRIMITIVES"/> + <value value="10" name="A7XX_PERF_VPC_SP_COMPONENTS"/> + <value value="11" name="A7XX_PERF_VPC_STALL_CYCLES_VPCRAM_POS"/> + <value value="12" name="A7XX_PERF_VPC_LRZ_ASSIGN_PRIMITIVES"/> + <value value="13" name="A7XX_PERF_VPC_RB_VISIBLE_PRIMITIVES"/> + <value value="14" name="A7XX_PERF_VPC_LM_TRANSACTION"/> + <value value="15" name="A7XX_PERF_VPC_STREAMOUT_TRANSACTION"/> + <value value="16" name="A7XX_PERF_VPC_VS_BUSY_CYCLES"/> + <value value="17" name="A7XX_PERF_VPC_PS_BUSY_CYCLES"/> + <value value="18" name="A7XX_PERF_VPC_VS_WORKING_CYCLES"/> + <value value="19" name="A7XX_PERF_VPC_PS_WORKING_CYCLES"/> + <value value="20" name="A7XX_PERF_VPC_STARVE_CYCLES_RB"/> + <value value="21" name="A7XX_PERF_VPC_NUM_VPCRAM_READ_POS"/> + <value value="22" name="A7XX_PERF_VPC_WIT_FULL_CYCLES"/> + <value value="23" name="A7XX_PERF_VPC_VPCRAM_FULL_CYCLES"/> + <value value="24" name="A7XX_PERF_VPC_LM_FULL_WAIT_FOR_INTP_END"/> + <value value="25" name="A7XX_PERF_VPC_NUM_VPCRAM_WRITE"/> + <value value="26" name="A7XX_PERF_VPC_NUM_VPCRAM_READ_SO"/> + <value value="27" name="A7XX_PERF_VPC_NUM_ATTR_REQ_LM"/> + <value value="28" name="A7XX_PERF_VPC_STALL_CYCLE_TSE"/> + <value value="29" name="A7XX_PERF_VPC_TSE_PRIMITIVES"/> + <value value="30" name="A7XX_PERF_VPC_GS_PRIMITIVES"/> + <value value="31" name="A7XX_PERF_VPC_TSE_TRANSACTIONS"/> + <value value="32" name="A7XX_PERF_VPC_STALL_CYCLES_CCU"/> + <value value="33" name="A7XX_PERF_VPC_NUM_WM_HIT"/> + <value value="34" name="A7XX_PERF_VPC_STALL_DQ_WACK"/> + <value value="35" name="A7XX_PERF_VPC_STALL_CYCLES_CCHE"/> + <value value="36" name="A7XX_PERF_VPC_STARVE_CYCLES_CCHE"/> + <value value="37" name="A7XX_PERF_VPC_NUM_PA_REQ"/> + <value value="38" name="A7XX_PERF_VPC_NUM_LM_REQ_HIT"/> + <value value="39" name="A7XX_PERF_VPC_CCHE_REQBUF_FULL"/> + <value value="40" name="A7XX_PERF_VPC_STALL_CYCLES_LM_ACK"/> + <value value="41" name="A7XX_PERF_VPC_STALL_CYCLES_PRG_END_FE"/> + <value value="42" name="A7XX_PERF_VPC_STALL_CYCLES_PRG_END_PCVS"/> + <value value="43" name="A7XX_PERF_VPC_STALL_CYCLES_PRG_END_VPCPS"/> +</enum> + +<enum name="a7xx_tse_perfcounter_select"> + <value value="0" name="A7XX_PERF_TSE_BUSY_CYCLES"/> + <value value="1" name="A7XX_PERF_TSE_CLIPPING_CYCLES"/> + <value value="2" name="A7XX_PERF_TSE_STALL_CYCLES_RAS"/> + <value value="3" name="A7XX_PERF_TSE_STALL_CYCLES_LRZ_BARYPLANE"/> + <value value="4" name="A7XX_PERF_TSE_STALL_CYCLES_LRZ_ZPLANE"/> + <value value="5" name="A7XX_PERF_TSE_STARVE_CYCLES_PC"/> + <value value="6" name="A7XX_PERF_TSE_INPUT_PRIM"/> + <value value="7" name="A7XX_PERF_TSE_INPUT_NULL_PRIM"/> + <value value="8" name="A7XX_PERF_TSE_TRIVAL_REJ_PRIM"/> + <value value="9" name="A7XX_PERF_TSE_CLIPPED_PRIM"/> + <value value="10" name="A7XX_PERF_TSE_ZERO_AREA_PRIM"/> + <value value="11" name="A7XX_PERF_TSE_FACENESS_CULLED_PRIM"/> + <value value="12" name="A7XX_PERF_TSE_ZERO_PIXEL_PRIM"/> + <value value="13" name="A7XX_PERF_TSE_OUTPUT_NULL_PRIM"/> + <value value="14" name="A7XX_PERF_TSE_OUTPUT_VISIBLE_PRIM"/> + <value value="15" name="A7XX_PERF_TSE_CINVOCATION"/> + <value value="16" name="A7XX_PERF_TSE_CPRIMITIVES"/> + <value value="17" name="A7XX_PERF_TSE_2D_INPUT_PRIM"/> + <value value="18" name="A7XX_PERF_TSE_2D_ALIVE_CYCLES"/> + <value value="19" name="A7XX_PERF_TSE_CLIP_PLANES"/> +</enum> + +<enum name="a7xx_ras_perfcounter_select"> + <value value="0" name="A7XX_PERF_RAS_BUSY_CYCLES"/> + <value value="1" name="A7XX_PERF_RAS_SUPERTILE_ACTIVE_CYCLES"/> + <value value="2" name="A7XX_PERF_RAS_STALL_CYCLES_LRZ"/> + <value value="3" name="A7XX_PERF_RAS_STARVE_CYCLES_TSE"/> + <value value="4" name="A7XX_PERF_RAS_SUPER_TILES"/> + <value value="5" name="A7XX_PERF_RAS_8X4_TILES"/> + <value value="6" name="A7XX_PERF_RAS_MASKGEN_ACTIVE"/> + <value value="7" name="A7XX_PERF_RAS_FULLY_COVERED_SUPER_TILES"/> + <value value="8" name="A7XX_PERF_RAS_FULLY_COVERED_8X4_TILES"/> + <value value="9" name="A7XX_PERF_RAS_PRIM_KILLED_INVISILBE"/> + <value value="10" name="A7XX_PERF_RAS_SUPERTILE_GEN_ACTIVE_CYCLES"/> + <value value="11" name="A7XX_PERF_RAS_LRZ_INTF_WORKING_CYCLES"/> + <value value="12" name="A7XX_PERF_RAS_BLOCKS"/> + <value value="13" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_0_WORKING_CC_l2"/> + <value value="14" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_1_WORKING_CC_l2"/> + <value value="15" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_2_WORKING_CC_l2"/> + <value value="16" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_3_WORKING_CC_l2"/> + <value value="17" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_4_WORKING_CC_l2"/> + <value value="18" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_5_WORKING_CC_l2"/> + <value value="19" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_6_WORKING_CC_l2"/> + <value value="20" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_7_WORKING_CC_l2"/> + <value value="21" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_8_WORKING_CC_l2"/> + <value value="22" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_9_WORKING_CC_l2"/> + <value value="23" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_10_WORKING_CC_l2"/> + <value value="24" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_11_WORKING_CC_l2"/> + <value value="25" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_12_WORKING_CC_l2"/> + <value value="26" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_13_WORKING_CC_l2"/> + <value value="27" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_14_WORKING_CC_l2"/> + <value value="28" name="A7XX_PERF_RAS_SAMPLE_MASK_GEN_LANE_15_WORKING_CC_l2"/> + <value value="29" name="A7XX_PERF_RAS_FALSE_PARTIAL_STILE"/> + +</enum> + +<enum name="a7xx_uche_perfcounter_select"> + <value value="0" name="A7XX_PERF_UCHE_BUSY_CYCLES"/> + <value value="1" name="A7XX_PERF_UCHE_STALL_CYCLES_ARBITER"/> + <value value="2" name="A7XX_PERF_UCHE_VBIF_LATENCY_CYCLES"/> + <value value="3" name="A7XX_PERF_UCHE_VBIF_LATENCY_SAMPLES"/> + <value value="4" name="A7XX_PERF_UCHE_VBIF_READ_BEATS_TP"/> + <value value="5" name="A7XX_PERF_UCHE_VBIF_READ_BEATS_VFD"/> + <value value="6" name="A7XX_PERF_UCHE_VBIF_READ_BEATS_HLSQ"/> + <value value="7" name="A7XX_PERF_UCHE_VBIF_READ_BEATS_LRZ"/> + <value value="8" name="A7XX_PERF_UCHE_VBIF_READ_BEATS_SP"/> + <value value="9" name="A7XX_PERF_UCHE_READ_REQUESTS_TP"/> + <value value="10" name="A7XX_PERF_UCHE_READ_REQUESTS_VFD"/> + <value value="11" name="A7XX_PERF_UCHE_READ_REQUESTS_HLSQ"/> + <value value="12" name="A7XX_PERF_UCHE_READ_REQUESTS_LRZ"/> + <value value="13" name="A7XX_PERF_UCHE_READ_REQUESTS_SP"/> + <value value="14" name="A7XX_PERF_UCHE_WRITE_REQUESTS_LRZ"/> + <value value="15" name="A7XX_PERF_UCHE_WRITE_REQUESTS_SP"/> + <value value="16" name="A7XX_PERF_UCHE_WRITE_REQUESTS_VPC"/> + <value value="17" name="A7XX_PERF_UCHE_WRITE_REQUESTS_VSC"/> + <value value="18" name="A7XX_PERF_UCHE_EVICTS"/> + <value value="19" name="A7XX_PERF_UCHE_BANK_REQ0"/> + <value value="20" name="A7XX_PERF_UCHE_BANK_REQ1"/> + <value value="21" name="A7XX_PERF_UCHE_BANK_REQ2"/> + <value value="22" name="A7XX_PERF_UCHE_BANK_REQ3"/> + <value value="23" name="A7XX_PERF_UCHE_BANK_REQ4"/> + <value value="24" name="A7XX_PERF_UCHE_BANK_REQ5"/> + <value value="25" name="A7XX_PERF_UCHE_BANK_REQ6"/> + <value value="26" name="A7XX_PERF_UCHE_BANK_REQ7"/> + <value value="27" name="A7XX_PERF_UCHE_VBIF_READ_BEATS_CH0"/> + <value value="28" name="A7XX_PERF_UCHE_VBIF_READ_BEATS_CH1"/> + <value value="29" name="A7XX_PERF_UCHE_GMEM_READ_BEATS"/> + <value value="30" name="A7XX_PERF_UCHE_TPH_REF_FULL"/> + <value value="31" name="A7XX_PERF_UCHE_TPH_VICTIM_FULL"/> + <value value="32" name="A7XX_PERF_UCHE_TPH_EXT_FULL"/> + <value value="33" name="A7XX_PERF_UCHE_VBIF_STALL_WRITE_DATA"/> + <value value="34" name="A7XX_PERF_UCHE_DCMP_LATENCY_SAMPLES"/> + <value value="35" name="A7XX_PERF_UCHE_DCMP_LATENCY_CYCLES"/> + <value value="36" name="A7XX_PERF_UCHE_VBIF_READ_BEATS_PC"/> + <value value="37" name="A7XX_PERF_UCHE_READ_REQUESTS_PC"/> + <value value="38" name="A7XX_PERF_UCHE_RAM_READ_REQ"/> + <value value="39" name="A7XX_PERF_UCHE_RAM_WRITE_REQ"/> + <value value="40" name="A7XX_PERF_UCHE_STARVED_CYCLES_VBIF_DECMP"/> + <value value="41" name="A7XX_PERF_UCHE_STALL_CYCLES_DECMP"/> + <value value="42" name="A7XX_PERF_UCHE_ARBITER_STALL_CYCLES_VBIF"/> + <value value="43" name="A7XX_PERF_UCHE_READ_REQUESTS_TP_UBWC"/> + <value value="44" name="A7XX_PERF_UCHE_READ_REQUESTS_TP_NONUBWC"/> + <value value="45" name="A7XX_PERF_UCHE_READ_REQUESTS_TP_GMEM"/> + <value value="46" name="A7XX_PERF_UCHE_LONG_LINE_ALL_EVICTS_KAILUA"/> + <value value="47" name="A7XX_PERF_UCHE_LONG_LINE_PARTIAL_EVICTS_KAILUA"/> + <value value="48" name="A7XX_PERF_UCHE_TPH_CONFLICT_CL_CCHE"/> + <value value="49" name="A7XX_PERF_UCHE_TPH_CONFLICT_CL_OTHER_KAILUA"/> + <value value="50" name="A7XX_PERF_UCHE_DBANK_CONFLICT_CL_CCHE"/> + <value value="51" name="A7XX_PERF_UCHE_DBANK_CONFLICT_CL_OTHER_CLIENTS"/> + <value value="52" name="A7XX_PERF_UCHE_VBIF_WRITE_BEATS_CH0"/> + <value value="53" name="A7XX_PERF_UCHE_VBIF_WRITE_BEATS_CH1"/> + <value value="54" name="A7XX_PERF_UCHE_CCHE_TPH_QUEUE_FULL"/> + <value value="55" name="A7XX_PERF_UCHE_CCHE_DPH_QUEUE_FULL"/> + <value value="56" name="A7XX_PERF_UCHE_GMEM_WRITE_BEATS"/> + <value value="57" name="A7XX_PERF_UCHE_UBWC_READ_BEATS"/> + <value value="58" name="A7XX_PERF_UCHE_UBWC_WRITE_BEATS"/> +</enum> + +<enum name="a7xx_tp_perfcounter_select"> + <value value="0" name="A7XX_PERF_TP_BUSY_CYCLES"/> + <value value="1" name="A7XX_PERF_TP_STALL_CYCLES_UCHE"/> + <value value="2" name="A7XX_PERF_TP_LATENCY_CYCLES"/> + <value value="3" name="A7XX_PERF_TP_LATENCY_TRANS"/> + <value value="4" name="A7XX_PERF_TP_FLAG_FIFO_DELAY_SAMPLES"/> + <value value="5" name="A7XX_PERF_TP_FLAG_FIFO_DELAY_CYCLES"/> + <value value="6" name="A7XX_PERF_TP_L1_CACHELINE_REQUESTS"/> + <value value="7" name="A7XX_PERF_TP_L1_CACHELINE_MISSES"/> + <value value="8" name="A7XX_PERF_TP_SP_TP_TRANS"/> + <value value="9" name="A7XX_PERF_TP_TP_SP_TRANS"/> + <value value="10" name="A7XX_PERF_TP_OUTPUT_PIXELS"/> + <value value="11" name="A7XX_PERF_TP_FILTER_WORKLOAD_16BIT"/> + <value value="12" name="A7XX_PERF_TP_FILTER_WORKLOAD_32BIT"/> + <value value="13" name="A7XX_PERF_TP_QUADS_RECEIVED"/> + <value value="14" name="A7XX_PERF_TP_QUADS_OFFSET"/> + <value value="15" name="A7XX_PERF_TP_QUADS_SHADOW"/> + <value value="16" name="A7XX_PERF_TP_QUADS_ARRAY"/> + <value value="17" name="A7XX_PERF_TP_QUADS_GRADIENT"/> + <value value="18" name="A7XX_PERF_TP_QUADS_1D"/> + <value value="19" name="A7XX_PERF_TP_QUADS_2D"/> + <value value="20" name="A7XX_PERF_TP_QUADS_BUFFER"/> + <value value="21" name="A7XX_PERF_TP_QUADS_3D"/> + <value value="22" name="A7XX_PERF_TP_QUADS_CUBE"/> + <value value="23" name="A7XX_PERF_TP_DIVERGENT_QUADS_RECEIVED"/> + <value value="24" name="A7XX_PERF_TP_PRT_NON_RESIDENT_EVENTS"/> + <value value="25" name="A7XX_PERF_TP_OUTPUT_PIXELS_POINT"/> + <value value="26" name="A7XX_PERF_TP_OUTPUT_PIXELS_BILINEAR"/> + <value value="27" name="A7XX_PERF_TP_OUTPUT_PIXELS_MIP"/> + <value value="28" name="A7XX_PERF_TP_OUTPUT_PIXELS_ANISO"/> + <value value="29" name="A7XX_PERF_TP_OUTPUT_PIXELS_ZERO_LOD"/> + <value value="30" name="A7XX_PERF_TP_FLAG_CACHE_REQUESTS"/> + <value value="31" name="A7XX_PERF_TP_FLAG_CACHE_MISSES"/> + <value value="32" name="A7XX_PERF_TP_L1_5_L2_REQUESTS"/> + <value value="33" name="A7XX_PERF_TP_2D_OUTPUT_PIXELS"/> + <value value="34" name="A7XX_PERF_TP_2D_OUTPUT_PIXELS_POINT"/> + <value value="35" name="A7XX_PERF_TP_2D_OUTPUT_PIXELS_BILINEAR"/> + <value value="36" name="A7XX_PERF_TP_2D_FILTER_WORKLOAD_16BIT"/> + <value value="37" name="A7XX_PERF_TP_2D_FILTER_WORKLOAD_32BIT"/> + <value value="38" name="A7XX_PERF_TP_TPA2TPC_TRANS"/> + <value value="39" name="A7XX_PERF_TP_L1_MISSES_ASTC_1TILE"/> + <value value="40" name="A7XX_PERF_TP_L1_MISSES_ASTC_2TILE"/> + <value value="41" name="A7XX_PERF_TP_L1_MISSES_ASTC_4TILE"/> + <value value="42" name="A7XX_PERF_TP_L1_5_COMPRESS_REQS"/> + <value value="43" name="A7XX_PERF_TP_L1_5_L2_COMPRESS_MISS"/> + <value value="44" name="A7XX_PERF_TP_L1_BANK_CONFLICT"/> + <value value="45" name="A7XX_PERF_TP_L1_5_MISS_LATENCY_CYCLES"/> + <value value="46" name="A7XX_PERF_TP_L1_5_MISS_LATENCY_TRANS"/> + <value value="47" name="A7XX_PERF_TP_QUADS_CONSTANT_MULTIPLIED"/> + <value value="48" name="A7XX_PERF_TP_FRONTEND_WORKING_CYCLES"/> + <value value="49" name="A7XX_PERF_TP_L1_TAG_WORKING_CYCLES"/> + <value value="50" name="A7XX_PERF_TP_L1_DATA_WRITE_WORKING_CYCLES"/> + <value value="51" name="A7XX_PERF_TP_PRE_L1_DECOM_WORKING_CYCLES"/> + <value value="52" name="A7XX_PERF_TP_BACKEND_WORKING_CYCLES"/> + <value value="53" name="A7XX_PERF_TP_L1_5_CACHE_WORKING_CYCLES"/> + <value value="54" name="A7XX_PERF_TP_STARVE_CYCLES_SP"/> + <value value="55" name="A7XX_PERF_TP_STARVE_CYCLES_UCHE"/> + <value value="56" name="A7XX_PERF_TP_STALL_CYCLES_UFC"/> + <value value="57" name="A7XX_PERF_TP_FORMAT_DECOMP"/> + <value value="58" name="A7XX_PERF_TP_FILTER_POINT_FP16"/> + <value value="59" name="A7XX_PERF_TP_FILTER_POINT_FP32"/> + <value value="60" name="A7XX_PERF_TP_LATENCY_FIFO_FULL"/> + <value value="61" name="A7XX_PERF_TP_RESERVED_61"/> + <value value="62" name="A7XX_PERF_TP_RESERVED_62"/> + <value value="63" name="A7XX_PERF_TP_RESERVED_63"/> + <value value="64" name="A7XX_PERF_TP_RESERVED_64"/> + <value value="65" name="A7XX_PERF_TP_RESERVED_65"/> + <value value="66" name="A7XX_PERF_TP_RESERVED_66"/> + <value value="67" name="A7XX_PERF_TP_RESERVED_67"/> + <value value="68" name="A7XX_PERF_TP_RESERVED_68"/> + <value value="69" name="A7XX_PERF_TP_RESERVED_69"/> + <value value="70" name="A7XX_PERF_TP_RESERVED_70"/> + <value value="71" name="A7XX_PERF_TP_RESERVED_71"/> + <value value="72" name="A7XX_PERF_TP_RESERVED_72"/> + <value value="73" name="A7XX_PERF_TP_RESERVED_73"/> + <value value="74" name="A7XX_PERF_TP_RESERVED_74"/> + <value value="75" name="A7XX_PERF_TP_RESERVED_75"/> + <value value="76" name="A7XX_PERF_TP_RESERVED_76"/> + <value value="77" name="A7XX_PERF_TP_RESERVED_77"/> + <value value="78" name="A7XX_PERF_TP_RESERVED_78"/> + <value value="79" name="A7XX_PERF_TP_RESERVED_79"/> + <value value="80" name="A7XX_PERF_TP_RESERVED_80"/> + <value value="81" name="A7XX_PERF_TP_RESERVED_81"/> + <value value="82" name="A7XX_PERF_TP_RESERVED_82"/> + <value value="83" name="A7XX_PERF_TP_RESERVED_83"/> + <value value="84" name="A7XX_PERF_TP_RESERVED_84"/> + <value value="85" name="A7XX_PERF_TP_RESERVED_85"/> + <value value="86" name="A7XX_PERF_TP_RESERVED_86"/> + <value value="87" name="A7XX_PERF_TP_RESERVED_87"/> + <value value="88" name="A7XX_PERF_TP_RESERVED_88"/> + <value value="89" name="A7XX_PERF_TP_RESERVED_89"/> + <value value="90" name="A7XX_PERF_TP_RESERVED_90"/> + <value value="91" name="A7XX_PERF_TP_RESERVED_91"/> + <value value="92" name="A7XX_PERF_TP_RESERVED_92"/> + <value value="93" name="A7XX_PERF_TP_RESERVED_93"/> + <value value="94" name="A7XX_PERF_TP_RESERVED_94"/> + <value value="95" name="A7XX_PERF_TP_RESERVED_95"/> + <value value="96" name="A7XX_PERF_TP_RESERVED_96"/> + <value value="97" name="A7XX_PERF_TP_RESERVED_97"/> + <value value="98" name="A7XX_PERF_TP_RESERVED_98"/> + <value value="99" name="A7XX_PERF_TP_RESERVED_99"/> + <value value="100" name="A7XX_PERF_TP_RESERVED_100"/> + <value value="101" name="A7XX_PERF_TP_RESERVED_101"/> + <value value="102" name="A7XX_PERF_TP_RESERVED_102"/> + <value value="103" name="A7XX_PERF_TP_RESERVED_103"/> + <value value="104" name="A7XX_PERF_TP_RESERVED_104"/> + <value value="105" name="A7XX_PERF_TP_RESERVED_105"/> + <value value="106" name="A7XX_PERF_TP_RESERVED_106"/> + <value value="107" name="A7XX_PERF_TP_RESERVED_107"/> + <value value="108" name="A7XX_PERF_TP_RESERVED_108"/> + <value value="109" name="A7XX_PERF_TP_RESERVED_109"/> + <value value="110" name="A7XX_PERF_TP_RESERVED_110"/> + <value value="111" name="A7XX_PERF_TP_RESERVED_111"/> + <value value="112" name="A7XX_PERF_TP_RESERVED_112"/> + <value value="113" name="A7XX_PERF_TP_RESERVED_113"/> + <value value="114" name="A7XX_PERF_TP_RESERVED_114"/> + <value value="115" name="A7XX_PERF_TP_RESERVED_115"/> + <value value="116" name="A7XX_PERF_TP_RESERVED_116"/> + <value value="117" name="A7XX_PERF_TP_RESERVED_117"/> + <value value="118" name="A7XX_PERF_TP_RESERVED_118"/> + <value value="119" name="A7XX_PERF_TP_RESERVED_119"/> + <value value="120" name="A7XX_PERF_TP_RESERVED_120"/> + <value value="121" name="A7XX_PERF_TP_RESERVED_121"/> + <value value="122" name="A7XX_PERF_TP_RESERVED_122"/> + <value value="123" name="A7XX_PERF_TP_RESERVED_123"/> + <value value="124" name="A7XX_PERF_TP_RESERVED_124"/> + <value value="125" name="A7XX_PERF_TP_RESERVED_125"/> + <value value="126" name="A7XX_PERF_TP_RESERVED_126"/> + <value value="127" name="A7XX_PERF_TP_RESERVED_127"/> + <value value="128" name="A7XX_PERF_TP_FORMAT_DECOMP_BILINEAR"/> + <value value="129" name="A7XX_PERF_TP_PACKED_POINT_BOTH_VALID_FP16"/> + <value value="130" name="A7XX_PERF_TP_PACKED_POINT_SINGLE_VALID_FP16"/> + <value value="131" name="A7XX_PERF_TP_PACKED_POINT_BOTH_VALID_FP32"/> + <value value="132" name="A7XX_PERF_TP_PACKED_POINT_SINGLE_VALID_FP32"/> +</enum> + +<enum name="a7xx_sp_perfcounter_select"> + <value value="0" name="A7XX_PERF_SP_BUSY_CYCLES"/> + <value value="1" name="A7XX_PERF_SP_ALU_WORKING_CYCLES"/> + <value value="2" name="A7XX_PERF_SP_EFU_WORKING_CYCLES"/> + <value value="3" name="A7XX_PERF_SP_STALL_CYCLES_VPC"/> + <value value="4" name="A7XX_PERF_SP_STALL_CYCLES_TP"/> + <value value="5" name="A7XX_PERF_SP_STALL_CYCLES_UCHE"/> + <value value="6" name="A7XX_PERF_SP_STALL_CYCLES_RB"/> + <value value="7" name="A7XX_PERF_SP_NON_EXECUTION_CYCLES"/> + <value value="8" name="A7XX_PERF_SP_WAVE_CONTEXTS"/> + <value value="9" name="A7XX_PERF_SP_WAVE_CONTEXT_CYCLES"/> + <value value="10" name="A7XX_PERF_SP_STAGE_WAVE_CYCLES"/> + <value value="11" name="A7XX_PERF_SP_STAGE_WAVE_SAMPLES"/> + <value value="12" name="A7XX_PERF_SP_VS_STAGE_WAVE_CYCLES"/> + <value value="13" name="A7XX_PERF_SP_VS_STAGE_WAVE_SAMPLES"/> + <value value="14" name="A7XX_PERF_SP_FS_STAGE_DURATION_CYCLES"/> + <value value="15" name="A7XX_PERF_SP_VS_STAGE_DURATION_CYCLES"/> + <value value="16" name="A7XX_PERF_SP_WAVE_CTRL_CYCLES"/> + <value value="17" name="A7XX_PERF_SP_WAVE_LOAD_CYCLES"/> + <value value="18" name="A7XX_PERF_SP_WAVE_EMIT_CYCLES"/> + <value value="19" name="A7XX_PERF_SP_WAVE_NOP_CYCLES"/> + <value value="20" name="A7XX_PERF_SP_WAVE_WAIT_CYCLES"/> + <value value="21" name="A7XX_PERF_SP_WAVE_FETCH_CYCLES"/> + <value value="22" name="A7XX_PERF_SP_WAVE_IDLE_CYCLES"/> + <value value="23" name="A7XX_PERF_SP_WAVE_END_CYCLES"/> + <value value="24" name="A7XX_PERF_SP_WAVE_LONG_SYNC_CYCLES"/> + <value value="25" name="A7XX_PERF_SP_WAVE_SHORT_SYNC_CYCLES"/> + <value value="26" name="A7XX_PERF_SP_WAVE_JOIN_CYCLES"/> + <value value="27" name="A7XX_PERF_SP_LM_LOAD_INSTRUCTIONS"/> + <value value="28" name="A7XX_PERF_SP_LM_STORE_INSTRUCTIONS"/> + <value value="29" name="A7XX_PERF_SP_LM_ATOMICS"/> + <value value="30" name="A7XX_PERF_SP_GM_LOAD_INSTRUCTIONS"/> + <value value="31" name="A7XX_PERF_SP_GM_STORE_INSTRUCTIONS"/> + <value value="32" name="A7XX_PERF_SP_GM_ATOMICS"/> + <value value="33" name="A7XX_PERF_SP_VS_STAGE_TEX_INSTRUCTIONS"/> + <value value="34" name="A7XX_PERF_SP_VS_STAGE_EFU_INSTRUCTIONS"/> + <value value="35" name="A7XX_PERF_SP_VS_STAGE_FULL_ALU_INSTRUCTIONS"/> + <value value="36" name="A7XX_PERF_SP_VS_STAGE_HALF_ALU_INSTRUCTIONS"/> + <value value="37" name="A7XX_PERF_SP_FS_STAGE_TEX_INSTRUCTIONS"/> + <value value="38" name="A7XX_PERF_SP_FS_STAGE_CFLOW_INSTRUCTIONS"/> + <value value="39" name="A7XX_PERF_SP_FS_STAGE_EFU_INSTRUCTIONS"/> + <value value="40" name="A7XX_PERF_SP_FS_STAGE_FULL_ALU_INSTRUCTIONS"/> + <value value="41" name="A7XX_PERF_SP_FS_STAGE_HALF_ALU_INSTRUCTIONS"/> + <value value="42" name="A7XX_PERF_SP_FS_STAGE_BARY_INSTRUCTIONS"/> + <value value="43" name="A7XX_PERF_SP_VS_INSTRUCTIONS"/> + <value value="44" name="A7XX_PERF_SP_FS_INSTRUCTIONS"/> + <value value="45" name="A7XX_PERF_SP_ADDR_LOCK_COUNT"/> + <value value="46" name="A7XX_PERF_SP_UCHE_READ_TRANS"/> + <value value="47" name="A7XX_PERF_SP_UCHE_WRITE_TRANS"/> + <value value="48" name="A7XX_PERF_SP_EXPORT_VPC_TRANS"/> + <value value="49" name="A7XX_PERF_SP_EXPORT_RB_TRANS"/> + <value value="50" name="A7XX_PERF_SP_PIXELS_KILLED"/> + <value value="51" name="A7XX_PERF_SP_ICL1_REQUESTS"/> + <value value="52" name="A7XX_PERF_SP_ICL1_MISSES"/> + <value value="53" name="A7XX_PERF_SP_HS_INSTRUCTIONS"/> + <value value="54" name="A7XX_PERF_SP_DS_INSTRUCTIONS"/> + <value value="55" name="A7XX_PERF_SP_GS_INSTRUCTIONS"/> + <value value="56" name="A7XX_PERF_SP_CS_INSTRUCTIONS"/> + <value value="57" name="A7XX_PERF_SP_GPR_READ"/> + <value value="58" name="A7XX_PERF_SP_GPR_WRITE"/> + <value value="59" name="A7XX_PERF_SP_FS_STAGE_HALF_EFU_INSTRUCTIONS"/> + <value value="60" name="A7XX_PERF_SP_VS_STAGE_HALF_EFU_INSTRUCTIONS"/> + <value value="61" name="A7XX_PERF_SP_LM_BANK_CONFLICTS"/> + <value value="62" name="A7XX_PERF_SP_TEX_CONTROL_WORKING_CYCLES"/> + <value value="63" name="A7XX_PERF_SP_LOAD_CONTROL_WORKING_CYCLES"/> + <value value="64" name="A7XX_PERF_SP_FLOW_CONTROL_WORKING_CYCLES"/> + <value value="65" name="A7XX_PERF_SP_LM_WORKING_CYCLES"/> + <value value="66" name="A7XX_PERF_SP_DISPATCHER_WORKING_CYCLES"/> + <value value="67" name="A7XX_PERF_SP_SEQUENCER_WORKING_CYCLES"/> + <value value="68" name="A7XX_PERF_SP_LOW_EFFICIENCY_STARVED_BY_TP"/> + <value value="69" name="A7XX_PERF_SP_STARVE_CYCLES_HLSQ"/> + <value value="70" name="A7XX_PERF_SP_NON_EXECUTION_LS_CYCLES"/> + <value value="71" name="A7XX_PERF_SP_WORKING_EU"/> + <value value="72" name="A7XX_PERF_SP_ANY_EU_WORKING"/> + <value value="73" name="A7XX_PERF_SP_WORKING_EU_FS_STAGE"/> + <value value="74" name="A7XX_PERF_SP_ANY_EU_WORKING_FS_STAGE"/> + <value value="75" name="A7XX_PERF_SP_WORKING_EU_VS_STAGE"/> + <value value="76" name="A7XX_PERF_SP_ANY_EU_WORKING_VS_STAGE"/> + <value value="77" name="A7XX_PERF_SP_WORKING_EU_CS_STAGE"/> + <value value="78" name="A7XX_PERF_SP_ANY_EU_WORKING_CS_STAGE"/> + <value value="79" name="A7XX_PERF_SP_GPR_READ_PREFETCH"/> + <value value="80" name="A7XX_PERF_SP_GPR_READ_CONFLICT"/> + <value value="81" name="A7XX_PERF_SP_GPR_WRITE_CONFLICT"/> + <value value="82" name="A7XX_PERF_SP_GM_LOAD_LATENCY_CYCLES"/> + <value value="83" name="A7XX_PERF_SP_GM_LOAD_LATENCY_SAMPLES"/> + <value value="84" name="A7XX_PERF_SP_EXECUTABLE_WAVES"/> + <value value="85" name="A7XX_PERF_SP_ICL1_MISS_FETCH_CYCLES"/> + <value value="86" name="A7XX_PERF_SP_WORKING_EU_LPAC"/> + <value value="87" name="A7XX_PERF_SP_BYPASS_BUSY_CYCLES"/> + <value value="88" name="A7XX_PERF_SP_ANY_EU_WORKING_LPAC"/> + <value value="89" name="A7XX_PERF_SP_WAVE_ALU_CYCLES"/> + <value value="90" name="A7XX_PERF_SP_WAVE_EFU_CYCLES"/> + <value value="91" name="A7XX_PERF_SP_WAVE_INT_CYCLES"/> + <value value="92" name="A7XX_PERF_SP_WAVE_CSP_CYCLES"/> + <value value="93" name="A7XX_PERF_SP_EWAVE_CONTEXTS"/> + <value value="94" name="A7XX_PERF_SP_EWAVE_CONTEXT_CYCLES"/> + <value value="95" name="A7XX_PERF_SP_LPAC_BUSY_CYCLES"/> + <value value="96" name="A7XX_PERF_SP_LPAC_INSTRUCTIONS"/> + <value value="97" name="A7XX_PERF_SP_FS_STAGE_1X_WAVES"/> + <value value="98" name="A7XX_PERF_SP_FS_STAGE_2X_WAVES"/> + <value value="99" name="A7XX_PERF_SP_QUADS"/> + <value value="100" name="A7XX_PERF_SP_CS_INVOCATIONS"/> + <value value="101" name="A7XX_PERF_SP_PIXELS"/> + <value value="102" name="A7XX_PERF_SP_LPAC_DRAWCALLS"/> + <value value="103" name="A7XX_PERF_SP_PI_WORKING_CYCLES"/> + <value value="104" name="A7XX_PERF_SP_WAVE_INPUT_CYCLES"/> + <value value="105" name="A7XX_PERF_SP_WAVE_OUTPUT_CYCLES"/> + <value value="106" name="A7XX_PERF_SP_WAVE_HWAVE_WAIT_CYCLES"/> + <value value="107" name="A7XX_PERF_SP_WAVE_HWAVE_SYNC"/> + <value value="108" name="A7XX_PERF_SP_OUTPUT_3D_PIXELS"/> + <value value="109" name="A7XX_PERF_SP_FULL_ALU_MAD_INSTRUCTIONS"/> + <value value="110" name="A7XX_PERF_SP_HALF_ALU_MAD_INSTRUCTIONS"/> + <value value="111" name="A7XX_PERF_SP_FULL_ALU_MUL_INSTRUCTIONS"/> + <value value="112" name="A7XX_PERF_SP_HALF_ALU_MUL_INSTRUCTIONS"/> + <value value="113" name="A7XX_PERF_SP_FULL_ALU_ADD_INSTRUCTIONS"/> + <value value="114" name="A7XX_PERF_SP_HALF_ALU_ADD_INSTRUCTIONS"/> + <value value="115" name="A7XX_PERF_SP_BARY_FP32_INSTRUCTIONS"/> + <value value="116" name="A7XX_PERF_SP_ALU_GPR_READ_CYCLES"/> + <value value="117" name="A7XX_PERF_SP_ALU_DATA_FORWARDING_CYCLES"/> + <value value="118" name="A7XX_PERF_SP_LM_FULL_CYCLES"/> + <value value="119" name="A7XX_PERF_SP_TEXTURE_FETCH_LATENCY_CYCLES"/> + <value value="120" name="A7XX_PERF_SP_TEXTURE_FETCH_LATENCY_SAMPLES"/> + <value value="121" name="A7XX_PERF_SP_FS_STAGE_PI_TEX_INSTRUCTION"/> + <value value="122" name="A7XX_PERF_SP_RAY_QUERY_INSTRUCTIONS"/> + <value value="123" name="A7XX_PERF_SP_RBRT_KICKOFF_FIBERS"/> + <value value="124" name="A7XX_PERF_SP_RBRT_KICKOFF_DQUADS"/> + <value value="125" name="A7XX_PERF_SP_RTU_BUSY_CYCLES"/> + <value value="126" name="A7XX_PERF_SP_RTU_L0_HITS"/> + <value value="127" name="A7XX_PERF_SP_RTU_L0_MISSES"/> + <value value="128" name="A7XX_PERF_SP_RTU_L0_HIT_ON_MISS"/> + <value value="129" name="A7XX_PERF_SP_RTU_STALL_CYCLES_WAVE_QUEUE"/> + <value value="130" name="A7XX_PERF_SP_RTU_STALL_CYCLES_L0_HIT_QUEUE"/> + <value value="131" name="A7XX_PERF_SP_RTU_STALL_CYCLES_L0_MISS_QUEUE"/> + <value value="132" name="A7XX_PERF_SP_RTU_STALL_CYCLES_L0D_IDX_QUEUE"/> + <value value="133" name="A7XX_PERF_SP_RTU_STALL_CYCLES_L0DATA"/> + <value value="134" name="A7XX_PERF_SP_RTU_STALL_CYCLES_REPLACE_CNT"/> + <value value="135" name="A7XX_PERF_SP_RTU_STALL_CYCLES_MRG_CNT"/> + <value value="136" name="A7XX_PERF_SP_RTU_STALL_CYCLES_UCHE"/> + <value value="137" name="A7XX_PERF_SP_RTU_OPERAND_FETCH_STALL_CYCLES_L0"/> + <value value="138" name="A7XX_PERF_SP_RTU_OPERAND_FETCH_STALL_CYCLES_INS_FIFO"/> + <value value="139" name="A7XX_PERF_SP_RTU_BVH_FETCH_LATENCY_CYCLES"/> + <value value="140" name="A7XX_PERF_SP_RTU_BVH_FETCH_LATENCY_SAMPLES"/> + <value value="141" name="A7XX_PERF_SP_STCHE_MISS_INC_VS"/> + <value value="142" name="A7XX_PERF_SP_STCHE_MISS_INC_FS"/> + <value value="143" name="A7XX_PERF_SP_STCHE_MISS_INC_BV"/> + <value value="144" name="A7XX_PERF_SP_STCHE_MISS_INC_LPAC"/> + <value value="145" name="A7XX_PERF_SP_VGPR_ACTIVE_CONTEXTS"/> + <value value="146" name="A7XX_PERF_SP_PGPR_ALLOC_CONTEXTS"/> + <value value="147" name="A7XX_PERF_SP_VGPR_ALLOC_CONTEXTS"/> + <value value="148" name="A7XX_PERF_SP_RTU_RAY_BOX_INTERSECTIONS"/> + <value value="149" name="A7XX_PERF_SP_RTU_RAY_TRIANGLE_INTERSECTIONS"/> + <value value="150" name="A7XX_PERF_SP_SCH_STALL_CYCLES_RTU"/> +</enum> + +<enum name="a7xx_rb_perfcounter_select"> + <value value="0" name="A7XX_PERF_RB_BUSY_CYCLES"/> + <value value="1" name="A7XX_PERF_RB_STALL_CYCLES_HLSQ"/> + <value value="2" name="A7XX_PERF_RB_STALL_CYCLES_FIFO0_FULL"/> + <value value="3" name="A7XX_PERF_RB_STALL_CYCLES_FIFO1_FULL"/> + <value value="4" name="A7XX_PERF_RB_STALL_CYCLES_FIFO2_FULL"/> + <value value="5" name="A7XX_PERF_RB_STARVE_CYCLES_SP"/> + <value value="6" name="A7XX_PERF_RB_STARVE_CYCLES_LRZ_TILE"/> + <value value="7" name="A7XX_PERF_RB_STARVE_CYCLES_CCU"/> + <value value="8" name="A7XX_PERF_RB_STARVE_CYCLES_Z_PLANE"/> + <value value="9" name="A7XX_PERF_RB_STARVE_CYCLES_BARY_PLANE"/> + <value value="10" name="A7XX_PERF_RB_Z_WORKLOAD"/> + <value value="11" name="A7XX_PERF_RB_HLSQ_ACTIVE"/> + <value value="12" name="A7XX_PERF_RB_Z_READ"/> + <value value="13" name="A7XX_PERF_RB_Z_WRITE"/> + <value value="14" name="A7XX_PERF_RB_C_READ"/> + <value value="15" name="A7XX_PERF_RB_C_WRITE"/> + <value value="16" name="A7XX_PERF_RB_TOTAL_PASS"/> + <value value="17" name="A7XX_PERF_RB_Z_PASS"/> + <value value="18" name="A7XX_PERF_RB_Z_FAIL"/> + <value value="19" name="A7XX_PERF_RB_S_FAIL"/> + <value value="20" name="A7XX_PERF_RB_BLENDED_FXP_COMPONENTS"/> + <value value="21" name="A7XX_PERF_RB_BLENDED_FP16_COMPONENTS"/> + <value value="22" name="A7XX_PERF_RB_PS_INVOCATIONS"/> + <value value="23" name="A7XX_PERF_RB_2D_ALIVE_CYCLES"/> + <value value="24" name="A7XX_PERF_RB_2D_STALL_CYCLES_A2D"/> + <value value="25" name="A7XX_PERF_RB_2D_STARVE_CYCLES_SRC"/> + <value value="26" name="A7XX_PERF_RB_2D_STARVE_CYCLES_SP"/> + <value value="27" name="A7XX_PERF_RB_2D_STARVE_CYCLES_DST"/> + <value value="28" name="A7XX_PERF_RB_2D_VALID_PIXELS"/> + <value value="29" name="A7XX_PERF_RB_3D_PIXELS"/> + <value value="30" name="A7XX_PERF_RB_BLENDER_WORKING_CYCLES"/> + <value value="31" name="A7XX_PERF_RB_ZPROC_WORKING_CYCLES"/> + <value value="32" name="A7XX_PERF_RB_CPROC_WORKING_CYCLES"/> + <value value="33" name="A7XX_PERF_RB_SAMPLER_WORKING_CYCLES"/> + <value value="34" name="A7XX_PERF_RB_STALL_CYCLES_CCU_COLOR_READ"/> + <value value="35" name="A7XX_PERF_RB_STALL_CYCLES_CCU_COLOR_WRITE"/> + <value value="36" name="A7XX_PERF_RB_STALL_CYCLES_CCU_DEPTH_READ"/> + <value value="37" name="A7XX_PERF_RB_STALL_CYCLES_CCU_DEPTH_WRITE"/> + <value value="38" name="A7XX_PERF_RB_STALL_CYCLES_VPC"/> + <value value="39" name="A7XX_PERF_RB_2D_INPUT_TRANS"/> + <value value="40" name="A7XX_PERF_RB_2D_OUTPUT_RB_DST_TRANS"/> + <value value="41" name="A7XX_PERF_RB_2D_OUTPUT_RB_SRC_TRANS"/> + <value value="42" name="A7XX_PERF_RB_BLENDED_FP32_COMPONENTS"/> + <value value="43" name="A7XX_PERF_RB_COLOR_PIX_TILES"/> + <value value="44" name="A7XX_PERF_RB_STALL_CYCLES_CCU"/> + <value value="45" name="A7XX_PERF_RB_EARLY_Z_ARB3_GRANT"/> + <value value="46" name="A7XX_PERF_RB_LATE_Z_ARB3_GRANT"/> + <value value="47" name="A7XX_PERF_RB_EARLY_Z_SKIP_GRANT"/> + <value value="48" name="A7XX_PERF_RB_VRS_1x1_QUADS"/> + <value value="49" name="A7XX_PERF_RB_VRS_2x1_QUADS"/> + <value value="50" name="A7XX_PERF_RB_VRS_1x2_QUADS"/> + <value value="51" name="A7XX_PERF_RB_VRS_2x2_QUADS"/> + <value value="52" name="A7XX_PERF_RB_VRS_4x2_QUADS"/> + <value value="53" name="A7XX_PERF_RB_VRS_4x4_QUADS"/> +</enum> + +<enum name="a7xx_vsc_perfcounter_select"> + <value value="0" name="A7XX_PERF_VSC_BUSY_CYCLES"/> + <value value="1" name="A7XX_PERF_VSC_WORKING_CYCLES"/> + <value value="2" name="A7XX_PERF_VSC_STALL_CYCLES_UCHE"/> + <value value="3" name="A7XX_PERF_VSC_EOT_NUM"/> + <value value="4" name="A7XX_PERF_VSC_INPUT_TILES"/> +</enum> + +<enum name="a7xx_ccu_perfcounter_select"> + <value value="0" name="A7XX_PERF_CCU_BUSY_CYCLES"/> + <value value="1" name="A7XX_PERF_CCU_STALL_CYCLES_RB_DEPTH_RETURN"/> + <value value="2" name="A7XX_PERF_CCU_STALL_CYCLES_RB_COLOR_RETURN"/> + <value value="3" name="A7XX_PERF_CCU_DEPTH_BLOCKS"/> + <value value="4" name="A7XX_PERF_CCU_COLOR_BLOCKS"/> + <value value="5" name="A7XX_PERF_CCU_DEPTH_BLOCK_HIT"/> + <value value="6" name="A7XX_PERF_CCU_COLOR_BLOCK_HIT"/> + <value value="7" name="A7XX_PERF_CCU_PARTIAL_BLOCK_READ"/> + <value value="8" name="A7XX_PERF_CCU_GMEM_READ"/> + <value value="9" name="A7XX_PERF_CCU_GMEM_WRITE"/> + <value value="10" name="A7XX_PERF_CCU_2D_RD_REQ"/> + <value value="11" name="A7XX_PERF_CCU_2D_WR_REQ"/> + <value value="12" name="A7XX_PERF_CCU_UBWC_COLOR_BLOCKS_CONCURRENT"/> + <value value="13" name="A7XX_PERF_CCU_UBWC_DEPTH_BLOCKS_CONCURRENT"/> + <value value="14" name="A7XX_PERF_CCU_COLOR_RESOLVE_DROPPED"/> + <value value="15" name="A7XX_PERF_CCU_DEPTH_RESOLVE_DROPPED"/> + <value value="16" name="A7XX_PERF_CCU_COLOR_RENDER_CONCURRENT"/> + <value value="17" name="A7XX_PERF_CCU_DEPTH_RENDER_CONCURRENT"/> + <value value="18" name="A7XX_PERF_CCU_COLOR_RESOLVE_AFTER_RENDER"/> + <value value="19" name="A7XX_PERF_CCU_DEPTH_RESOLVE_AFTER_RENDER"/> + <value value="20" name="A7XX_PERF_CCU_GMEM_EXTRA_DEPTH_READ"/> + <value value="21" name="A7XX_PERF_CCU_GMEM_COLOR_READ_4AA"/> + <value value="22" name="A7XX_PERF_CCU_GMEM_COLOR_READ_4AA_FULL"/> +</enum> + +<enum name="a7xx_lrz_perfcounter_select"> + <value value="0" name="A7XX_PERF_LRZ_BUSY_CYCLES"/> + <value value="1" name="A7XX_PERF_LRZ_STARVE_CYCLES_RAS"/> + <value value="2" name="A7XX_PERF_LRZ_STALL_CYCLES_RB"/> + <value value="3" name="A7XX_PERF_LRZ_STALL_CYCLES_VSC"/> + <value value="4" name="A7XX_PERF_LRZ_STALL_CYCLES_VPC"/> + <value value="5" name="A7XX_PERF_LRZ_STALL_CYCLES_FLAG_PREFETCH"/> + <value value="6" name="A7XX_PERF_LRZ_STALL_CYCLES_UCHE"/> + <value value="7" name="A7XX_PERF_LRZ_LRZ_READ"/> + <value value="8" name="A7XX_PERF_LRZ_LRZ_WRITE"/> + <value value="9" name="A7XX_PERF_LRZ_READ_LATENCY"/> + <value value="10" name="A7XX_PERF_LRZ_MERGE_CACHE_UPDATING"/> + <value value="11" name="A7XX_PERF_LRZ_PRIM_KILLED_BY_MASKGEN"/> + <value value="12" name="A7XX_PERF_LRZ_PRIM_KILLED_BY_LRZ"/> + <value value="13" name="A7XX_PERF_LRZ_VISIBLE_PRIM_AFTER_LRZ"/> + <value value="14" name="A7XX_PERF_LRZ_FULL_8X8_TILES"/> + <value value="15" name="A7XX_PERF_LRZ_PARTIAL_8X8_TILES"/> + <value value="16" name="A7XX_PERF_LRZ_TILE_KILLED"/> + <value value="17" name="A7XX_PERF_LRZ_TOTAL_PIXEL"/> + <value value="18" name="A7XX_PERF_LRZ_VISIBLE_PIXEL_AFTER_LRZ"/> + <value value="19" name="A7XX_PERF_LRZ_FEEDBACK_ACCEPT"/> + <value value="20" name="A7XX_PERF_LRZ_FEEDBACK_DISCARD"/> + <value value="21" name="A7XX_PERF_LRZ_FEEDBACK_STALL"/> + <value value="22" name="A7XX_PERF_LRZ_STALL_CYCLES_RB_ZPLANE"/> + <value value="23" name="A7XX_PERF_LRZ_STALL_CYCLES_RB_BPLANE"/> + <value value="24" name="A7XX_PERF_LRZ_RAS_MASK_TRANS"/> + <value value="25" name="A7XX_PERF_LRZ_STALL_CYCLES_MVC"/> + <value value="26" name="A7XX_PERF_LRZ_TILE_KILLED_BY_IMAGE_VRS"/> + <value value="27" name="A7XX_PERF_LRZ_TILE_KILLED_BY_Z"/> +</enum> + +<enum name="a7xx_cmp_perfcounter_select"> + <value value="0" name="A7XX_PERF_CMPDECMP_STALL_CYCLES_ARB"/> + <value value="1" name="A7XX_PERF_CMPDECMP_VBIF_LATENCY_CYCLES"/> + <value value="2" name="A7XX_PERF_CMPDECMP_VBIF_LATENCY_SAMPLES"/> + <value value="3" name="A7XX_PERF_CMPDECMP_VBIF_READ_DATA_CCU"/> + <value value="4" name="A7XX_PERF_CMPDECMP_VBIF_WRITE_DATA_CCU"/> + <value value="5" name="A7XX_PERF_CMPDECMP_VBIF_READ_REQUEST"/> + <value value="6" name="A7XX_PERF_CMPDECMP_VBIF_WRITE_REQUEST"/> + <value value="7" name="A7XX_PERF_CMPDECMP_VBIF_READ_DATA"/> + <value value="8" name="A7XX_PERF_CMPDECMP_VBIF_WRITE_DATA"/> + <value value="9" name="A7XX_PERF_CMPDECMP_DEPTH_WRITE_FLAG1_COUNT"/> + <value value="10" name="A7XX_PERF_CMPDECMP_DEPTH_WRITE_FLAG2_COUNT"/> + <value value="11" name="A7XX_PERF_CMPDECMP_DEPTH_WRITE_FLAG3_COUNT"/> + <value value="12" name="A7XX_PERF_CMPDECMP_DEPTH_WRITE_FLAG4_COUNT"/> + <value value="13" name="A7XX_PERF_CMPDECMP_DEPTH_WRITE_FLAG5_COUNT"/> + <value value="14" name="A7XX_PERF_CMPDECMP_DEPTH_WRITE_FLAG6_COUNT"/> + <value value="15" name="A7XX_PERF_CMPDECMP_DEPTH_WRITE_FLAG8_COUNT"/> + <value value="16" name="A7XX_PERF_CMPDECMP_COLOR_WRITE_FLAG1_COUNT"/> + <value value="17" name="A7XX_PERF_CMPDECMP_COLOR_WRITE_FLAG2_COUNT"/> + <value value="18" name="A7XX_PERF_CMPDECMP_COLOR_WRITE_FLAG3_COUNT"/> + <value value="19" name="A7XX_PERF_CMPDECMP_COLOR_WRITE_FLAG4_COUNT"/> + <value value="20" name="A7XX_PERF_CMPDECMP_COLOR_WRITE_FLAG5_COUNT"/> + <value value="21" name="A7XX_PERF_CMPDECMP_COLOR_WRITE_FLAG6_COUNT"/> + <value value="22" name="A7XX_PERF_CMPDECMP_COLOR_WRITE_FLAG8_COUNT"/> + <value value="23" name="A7XX_PERF_CMPDECMP_VBIF_READ_DATA_UCHE_CH0"/> + <value value="24" name="A7XX_PERF_CMPDECMP_VBIF_READ_DATA_UCHE_CH1"/> + <value value="25" name="A7XX_PERF_CMPDECMP_VBIF_WRITE_DATA_UCHE"/> + <value value="26" name="A7XX_PERF_CMPDECMP_DEPTH_WRITE_FLAG0_COUNT"/> + <value value="27" name="A7XX_PERF_CMPDECMP_COLOR_WRITE_FLAG0_COUNT"/> + <value value="28" name="A7XX_PERF_CMPDECMP_COLOR_WRITE_FLAGALPHA_COUNT"/> + <value value="29" name="A7XX_PERF_CMPDECMP_RESOLVE_EVENTS"/> + <value value="30" name="A7XX_PERF_CMPDECMP_CONCURRENT_RESOLVE_EVENTS"/> + <value value="31" name="A7XX_PERF_CMPDECMP_DROPPED_CLEAR_EVENTS"/> + <value value="32" name="A7XX_PERF_CMPDECMP_ST_BLOCKS_CONCURRENT"/> + <value value="33" name="A7XX_PERF_CMPDECMP_LRZ_ST_BLOCKS_CONCURRENT"/> + <value value="34" name="A7XX_PERF_CMPDECMP_DEPTH_READ_FLAG0_COUNT"/> + <value value="35" name="A7XX_PERF_CMPDECMP_DEPTH_READ_FLAG1_COUNT"/> + <value value="36" name="A7XX_PERF_CMPDECMP_DEPTH_READ_FLAG2_COUNT"/> + <value value="37" name="A7XX_PERF_CMPDECMP_DEPTH_READ_FLAG3_COUNT"/> + <value value="38" name="A7XX_PERF_CMPDECMP_DEPTH_READ_FLAG4_COUNT"/> + <value value="39" name="A7XX_PERF_CMPDECMP_DEPTH_READ_FLAG5_COUNT"/> + <value value="40" name="A7XX_PERF_CMPDECMP_DEPTH_READ_FLAG6_COUNT"/> + <value value="41" name="A7XX_PERF_CMPDECMP_DEPTH_READ_FLAG8_COUNT"/> + <value value="42" name="A7XX_PERF_CMPDECMP_COLOR_READ_FLAG0_COUNT"/> + <value value="43" name="A7XX_PERF_CMPDECMP_COLOR_READ_FLAG1_COUNT"/> + <value value="44" name="A7XX_PERF_CMPDECMP_COLOR_READ_FLAG2_COUNT"/> + <value value="45" name="A7XX_PERF_CMPDECMP_COLOR_READ_FLAG3_COUNT"/> + <value value="46" name="A7XX_PERF_CMPDECMP_COLOR_READ_FLAG4_COUNT"/> + <value value="47" name="A7XX_PERF_CMPDECMP_COLOR_READ_FLAG5_COUNT"/> + <value value="48" name="A7XX_PERF_CMPDECMP_COLOR_READ_FLAG6_COUNT"/> + <value value="49" name="A7XX_PERF_CMPDECMP_COLOR_READ_FLAG8_COUNT"/> +</enum> + +<enum name="a7xx_gbif_perfcounter_select"> + <value value="0" name="A7XX_PERF_GBIF_RESERVED_0"/> + <value value="1" name="A7XX_PERF_GBIF_RESERVED_1"/> + <value value="2" name="A7XX_PERF_GBIF_RESERVED_2"/> + <value value="3" name="A7XX_PERF_GBIF_RESERVED_3"/> + <value value="4" name="A7XX_PERF_GBIF_RESERVED_4"/> + <value value="5" name="A7XX_PERF_GBIF_RESERVED_5"/> + <value value="6" name="A7XX_PERF_GBIF_RESERVED_6"/> + <value value="7" name="A7XX_PERF_GBIF_RESERVED_7"/> + <value value="8" name="A7XX_PERF_GBIF_RESERVED_8"/> + <value value="9" name="A7XX_PERF_GBIF_RESERVED_9"/> + <value value="10" name="A7XX_PERF_GBIF_AXI0_READ_REQUESTS_TOTAL"/> + <value value="11" name="A7XX_PERF_GBIF_AXI1_READ_REQUESTS_TOTAL"/> + <value value="12" name="A7XX_PERF_GBIF_RESERVED_12"/> + <value value="13" name="A7XX_PERF_GBIF_RESERVED_13"/> + <value value="14" name="A7XX_PERF_GBIF_RESERVED_14"/> + <value value="15" name="A7XX_PERF_GBIF_RESERVED_15"/> + <value value="16" name="A7XX_PERF_GBIF_RESERVED_16"/> + <value value="17" name="A7XX_PERF_GBIF_RESERVED_17"/> + <value value="18" name="A7XX_PERF_GBIF_RESERVED_18"/> + <value value="19" name="A7XX_PERF_GBIF_RESERVED_19"/> + <value value="20" name="A7XX_PERF_GBIF_RESERVED_20"/> + <value value="21" name="A7XX_PERF_GBIF_RESERVED_21"/> + <value value="22" name="A7XX_PERF_GBIF_AXI0_WRITE_REQUESTS_TOTAL"/> + <value value="23" name="A7XX_PERF_GBIF_AXI1_WRITE_REQUESTS_TOTAL"/> + <value value="24" name="A7XX_PERF_GBIF_RESERVED_24"/> + <value value="25" name="A7XX_PERF_GBIF_RESERVED_25"/> + <value value="26" name="A7XX_PERF_GBIF_RESERVED_26"/> + <value value="27" name="A7XX_PERF_GBIF_RESERVED_27"/> + <value value="28" name="A7XX_PERF_GBIF_RESERVED_28"/> + <value value="29" name="A7XX_PERF_GBIF_RESERVED_29"/> + <value value="30" name="A7XX_PERF_GBIF_RESERVED_30"/> + <value value="31" name="A7XX_PERF_GBIF_RESERVED_31"/> + <value value="32" name="A7XX_PERF_GBIF_RESERVED_32"/> + <value value="33" name="A7XX_PERF_GBIF_RESERVED_33"/> + <value value="34" name="A7XX_PERF_GBIF_AXI0_READ_DATA_BEATS_TOTAL"/> + <value value="35" name="A7XX_PERF_GBIF_AXI1_READ_DATA_BEATS_TOTAL"/> + <value value="36" name="A7XX_PERF_GBIF_RESERVED_36"/> + <value value="37" name="A7XX_PERF_GBIF_RESERVED_37"/> + <value value="38" name="A7XX_PERF_GBIF_RESERVED_38"/> + <value value="39" name="A7XX_PERF_GBIF_RESERVED_39"/> + <value value="40" name="A7XX_PERF_GBIF_RESERVED_40"/> + <value value="41" name="A7XX_PERF_GBIF_RESERVED_41"/> + <value value="42" name="A7XX_PERF_GBIF_RESERVED_42"/> + <value value="43" name="A7XX_PERF_GBIF_RESERVED_43"/> + <value value="44" name="A7XX_PERF_GBIF_RESERVED_44"/> + <value value="45" name="A7XX_PERF_GBIF_RESERVED_45"/> + <value value="46" name="A7XX_PERF_GBIF_AXI0_WRITE_DATA_BEATS_TOTAL"/> + <value value="47" name="A7XX_PERF_GBIF_AXI1_WRITE_DATA_BEATS_TOTAL"/> + <value value="48" name="A7XX_PERF_GBIF_RESERVED_48"/> + <value value="49" name="A7XX_PERF_GBIF_RESERVED_49"/> + <value value="50" name="A7XX_PERF_GBIF_RESERVED_50"/> + <value value="51" name="A7XX_PERF_GBIF_RESERVED_51"/> + <value value="52" name="A7XX_PERF_GBIF_RESERVED_52"/> + <value value="53" name="A7XX_PERF_GBIF_RESERVED_53"/> + <value value="54" name="A7XX_PERF_GBIF_RESERVED_54"/> + <value value="55" name="A7XX_PERF_GBIF_RESERVED_55"/> + <value value="56" name="A7XX_PERF_GBIF_RESERVED_56"/> + <value value="57" name="A7XX_PERF_GBIF_RESERVED_57"/> + <value value="58" name="A7XX_PERF_GBIF_RESERVED_58"/> + <value value="59" name="A7XX_PERF_GBIF_RESERVED_59"/> + <value value="60" name="A7XX_PERF_GBIF_RESERVED_60"/> + <value value="61" name="A7XX_PERF_GBIF_RESERVED_61"/> + <value value="62" name="A7XX_PERF_GBIF_RESERVED_62"/> + <value value="63" name="A7XX_PERF_GBIF_RESERVED_63"/> + <value value="64" name="A7XX_PERF_GBIF_RESERVED_64"/> + <value value="65" name="A7XX_PERF_GBIF_RESERVED_65"/> + <value value="66" name="A7XX_PERF_GBIF_RESERVED_66"/> + <value value="67" name="A7XX_PERF_GBIF_RESERVED_67"/> + <value value="68" name="A7XX_PERF_GBIF_CYCLES_CH0_HELD_OFF_RD_ALL"/> + <value value="69" name="A7XX_PERF_GBIF_CYCLES_CH1_HELD_OFF_RD_ALL"/> + <value value="70" name="A7XX_PERF_GBIF_CYCLES_CH0_HELD_OFF_WR_ALL"/> + <value value="71" name="A7XX_PERF_GBIF_CYCLES_CH1_HELD_OFF_WR_ALL"/> + <value value="72" name="A7XX_PERF_GBIF_AXI_CH0_REQUEST_HELD_OFF"/> + <value value="73" name="A7XX_PERF_GBIF_AXI_CH1_REQUEST_HELD_OFF"/> + <value value="74" name="A7XX_PERF_GBIF_AXI_REQUEST_HELD_OFF"/> + <value value="75" name="A7XX_PERF_GBIF_AXI_CH0_WRITE_DATA_HELD_OFF"/> + <value value="76" name="A7XX_PERF_GBIF_AXI_CH1_WRITE_DATA_HELD_OFF"/> + <value value="77" name="A7XX_PERF_GBIF_AXI_ALL_WRITE_DATA_HELD_OFF"/> + <value value="78" name="A7XX_PERF_GBIF_AXI_ALL_READ_BEATS"/> + <value value="79" name="A7XX_PERF_GBIF_AXI_ALL_WRITE_BEATS"/> + <value value="80" name="A7XX_PERF_GBIF_AXI_ALL_BEATS"/> +</enum> + +<enum name="a7xx_ufc_perfcounter_select"> + <value value="0" name="A7XX_PERF_UFC_BUSY_CYCLES"/> + <value value="1" name="A7XX_PERF_UFC_READ_DATA_VBIF"/> + <value value="2" name="A7XX_PERF_UFC_WRITE_DATA_VBIF"/> + <value value="3" name="A7XX_PERF_UFC_READ_REQUEST_VBIF"/> + <value value="4" name="A7XX_PERF_UFC_WRITE_REQUEST_VBIF"/> + <value value="5" name="A7XX_PERF_UFC_LRZ_FILTER_HIT"/> + <value value="6" name="A7XX_PERF_UFC_LRZ_FILTER_MISS"/> + <value value="7" name="A7XX_PERF_UFC_CRE_FILTER_HIT"/> + <value value="8" name="A7XX_PERF_UFC_CRE_FILTER_MISS"/> + <value value="9" name="A7XX_PERF_UFC_SP_FILTER_HIT"/> + <value value="10" name="A7XX_PERF_UFC_SP_FILTER_MISS"/> + <value value="11" name="A7XX_PERF_UFC_SP_REQUESTS"/> + <value value="12" name="A7XX_PERF_UFC_TP_FILTER_HIT"/> + <value value="13" name="A7XX_PERF_UFC_TP_FILTER_MISS"/> + <value value="14" name="A7XX_PERF_UFC_TP_REQUESTS"/> + <value value="15" name="A7XX_PERF_UFC_MAIN_HIT_LRZ_PREFETCH"/> + <value value="16" name="A7XX_PERF_UFC_MAIN_HIT_CRE_PREFETCH"/> + <value value="17" name="A7XX_PERF_UFC_MAIN_HIT_SP_PREFETCH"/> + <value value="18" name="A7XX_PERF_UFC_MAIN_HIT_TP_PREFETCH"/> + <value value="19" name="A7XX_PERF_UFC_MAIN_HIT_UBWC_READ"/> + <value value="20" name="A7XX_PERF_UFC_MAIN_HIT_UBWC_WRITE"/> + <value value="21" name="A7XX_PERF_UFC_MAIN_MISS_LRZ_PREFETCH"/> + <value value="22" name="A7XX_PERF_UFC_MAIN_MISS_CRE_PREFETCH"/> + <value value="23" name="A7XX_PERF_UFC_MAIN_MISS_SP_PREFETCH"/> + <value value="24" name="A7XX_PERF_UFC_MAIN_MISS_TP_PREFETCH"/> + <value value="25" name="A7XX_PERF_UFC_MAIN_MISS_UBWC_READ"/> + <value value="26" name="A7XX_PERF_UFC_MAIN_MISS_UBWC_WRITE"/> + <value value="27" name="A7XX_PERF_UFC_UBWC_READ_UFC_TRANS"/> + <value value="28" name="A7XX_PERF_UFC_UBWC_WRITE_UFC_TRANS"/> + <value value="29" name="A7XX_PERF_UFC_STALL_CYCLES_GBIF_CMD"/> + <value value="30" name="A7XX_PERF_UFC_STALL_CYCLES_GBIF_RDATA"/> + <value value="31" name="A7XX_PERF_UFC_STALL_CYCLES_GBIF_WDATA"/> + <value value="32" name="A7XX_PERF_UFC_STALL_CYCLES_UBWC_WR_FLAG"/> + <value value="33" name="A7XX_PERF_UFC_STALL_CYCLES_UBWC_FLAG_RTN"/> + <value value="34" name="A7XX_PERF_UFC_STALL_CYCLES_UBWC_EVENT"/> + <value value="35" name="A7XX_PERF_UFC_LRZ_PREFETCH_STALLED_CYCLES"/> + <value value="36" name="A7XX_PERF_UFC_CRE_PREFETCH_STALLED_CYCLES"/> + <value value="37" name="A7XX_PERF_UFC_SPTP_PREFETCH_STALLED_CYCLES"/> + <value value="38" name="A7XX_PERF_UFC_UBWC_RD_STALLED_CYCLES"/> + <value value="39" name="A7XX_PERF_UFC_UBWC_WR_STALLED_CYCLES"/> + <value value="40" name="A7XX_PERF_UFC_PREFETCH_STALLED_CYCLES"/> + <value value="41" name="A7XX_PERF_UFC_EVICTION_STALLED_CYCLES"/> + <value value="42" name="A7XX_PERF_UFC_LOCK_STALLED_CYCLES"/> + <value value="43" name="A7XX_PERF_UFC_MISS_LATENCY_CYCLES"/> + <value value="44" name="A7XX_PERF_UFC_MISS_LATENCY_SAMPLES"/> + <value value="45" name="A7XX_PERF_UFC_UBWC_REQ_STALLED_CYCLES"/> + <value value="46" name="A7XX_PERF_UFC_TP_HINT_TAG_MISS"/> + <value value="47" name="A7XX_PERF_UFC_TP_HINT_TAG_HIT_RDY"/> + <value value="48" name="A7XX_PERF_UFC_TP_HINT_TAG_HIT_NRDY"/> + <value value="49" name="A7XX_PERF_UFC_TP_HINT_IS_FCLEAR"/> + <value value="50" name="A7XX_PERF_UFC_TP_HINT_IS_ALPHA0"/> + <value value="51" name="A7XX_PERF_UFC_SP_L1_FILTER_HIT"/> + <value value="52" name="A7XX_PERF_UFC_SP_L1_FILTER_MISS"/> + <value value="53" name="A7XX_PERF_UFC_SP_L1_FILTER_REQUESTS"/> + <value value="54" name="A7XX_PERF_UFC_TP_L1_TAG_HIT_RDY"/> + <value value="55" name="A7XX_PERF_UFC_TP_L1_TAG_HIT_NRDY"/> + <value value="56" name="A7XX_PERF_UFC_TP_L1_TAG_MISS"/> + <value value="57" name="A7XX_PERF_UFC_TP_L1_FILTER_REQUESTS"/> +</enum> + +</database> diff --git a/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml b/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml index 55a35182858c..7abc08635495 100644 --- a/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml +++ b/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml @@ -21,9 +21,9 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <value name="HLSQ_FLUSH" value="7" variants="A3XX-A4XX"/> <value name="VIZQUERY_END" value="8" variants="A2XX"/> <value name="SC_WAIT_WC" value="9" variants="A2XX"/> - <value name="WRITE_PRIMITIVE_COUNTS" value="9" variants="A6XX"/> - <value name="START_PRIMITIVE_CTRS" value="11" variants="A6XX"/> - <value name="STOP_PRIMITIVE_CTRS" value="12" variants="A6XX"/> + <value name="WRITE_PRIMITIVE_COUNTS" value="9" variants="A6XX-"/> + <value name="START_PRIMITIVE_CTRS" value="11" variants="A6XX-"/> + <value name="STOP_PRIMITIVE_CTRS" value="12" variants="A6XX-"/> <!-- Not sure that these 4 events don't have the same meaning as on A5XX+ --> <value name="RST_PIX_CNT" value="13" variants="A2XX-A4XX"/> <value name="RST_VTX_CNT" value="14" variants="A2XX-A4XX"/> @@ -31,8 +31,8 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <value name="STAT_EVENT" value="16" variants="A2XX-A4XX"/> <value name="CACHE_FLUSH_AND_INV_TS_EVENT" value="20" variants="A2XX-A4XX"/> <doc> - If A6XX_RB_SAMPLE_COUNT_CONTROL.copy is true, writes OQ Z passed - sample counts to RB_SAMPLE_COUNT_ADDR. This writes to main + If A6XX_RB_SAMPLE_COUNTER_CNTL.copy is true, writes OQ Z passed + sample counts to RB_SAMPLE_COUNTER_BASE. This writes to main memory, skipping UCHE. </doc> <value name="ZPASS_DONE" value="21"/> @@ -98,6 +98,13 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <value name="BLIT" value="30" variants="A5XX-"/> <doc> + Flip between the primary and secondary LRZ buffers. This is used + for concurrent binning, so that BV can write to one buffer while + BR reads from the other. + </doc> + <value name="LRZ_FLIP_BUFFER" value="36" variants="A7XX"/> + + <doc> Clears based on GRAS_LRZ_CNTL configuration, could clear fast-clear buffer or LRZ direction. LRZ direction is stored at lrz_fc_offset + 0x200, has 1 byte which @@ -114,6 +121,7 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <value name="BLIT_OP_FILL_2D" value="39" variants="A5XX-"/> <value name="BLIT_OP_COPY_2D" value="40" variants="A5XX-A6XX"/> <value name="UNK_40" value="40" variants="A7XX"/> + <value name="LRZ_Q_CACHE_INVALIDATE" value="41" variants="A7XX"/> <value name="BLIT_OP_SCALE_2D" value="42" variants="A5XX-"/> <value name="CONTEXT_DONE_2D" value="43" variants="A5XX-"/> <value name="UNK_2C" value="44" variants="A5XX-"/> @@ -372,7 +380,7 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <value name="CP_LOAD_STATE" value="0x30" variants="A3XX"/> <value name="CP_LOAD_STATE4" value="0x30" variants="A4XX-A5XX"/> <doc>Conditionally load a IB based on a flag, prefetch enabled</doc> - <value name="CP_COND_INDIRECT_BUFFER_PFE" value="0x3a"/> + <value name="CP_COND_INDIRECT_BUFFER_PFE" value="0x3a" variants="A3XX-A5XX"/> <doc>Conditionally load a IB based on a flag, prefetch disabled</doc> <value name="CP_COND_INDIRECT_BUFFER_PFD" value="0x32" variants="A3XX"/> <doc>Load a buffer with pre-fetch enabled</doc> @@ -538,7 +546,7 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <value name="CP_LOAD_STATE6_GEOM" value="0x32" variants="A6XX-"/> <value name="CP_LOAD_STATE6_FRAG" value="0x34" variants="A6XX-"/> <!-- - Note: For IBO state (Image/SSBOs) which have shared state across + Note: For UAV state (Image/SSBOs) which have shared state across shader stages, for 3d pipeline CP_LOAD_STATE6 is used. But for compute shaders, CP_LOAD_STATE6_FRAG is used. Possibly they are interchangable. @@ -567,7 +575,7 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <value name="IN_PREEMPT" value="0x0f" variants="A6XX-"/> <!-- TODO do these exist on A5xx? --> - <value name="CP_SCRATCH_WRITE" value="0x4c" variants="A6XX"/> + <value name="CP_SCRATCH_WRITE" value="0x4c" variants="A6XX-"/> <value name="CP_REG_TO_MEM_OFFSET_MEM" value="0x74" variants="A6XX-"/> <value name="CP_REG_TO_MEM_OFFSET_REG" value="0x72" variants="A6XX-"/> <value name="CP_WAIT_MEM_GTE" value="0x14" variants="A6XX"/> @@ -650,6 +658,11 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <doc>Reset various on-chip state used for synchronization</doc> <value name="CP_RESET_CONTEXT_STATE" value="0x1f" variants="A7XX-"/> + + <doc>Invalidates the "CCHE" introduced on a740</doc> + <value name="CP_CCHE_INVALIDATE" value="0x3a" variants="A7XX-"/> + + <value name="CP_SCOPE_CNTL" value="0x6c" variants="A7XX-"/> </enum> @@ -792,14 +805,14 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <value name="SB6_GS_SHADER" value="0xb"/> <value name="SB6_FS_SHADER" value="0xc"/> <value name="SB6_CS_SHADER" value="0xd"/> - <value name="SB6_IBO" value="0xe"/> - <value name="SB6_CS_IBO" value="0xf"/> + <value name="SB6_UAV" value="0xe"/> + <value name="SB6_CS_UAV" value="0xf"/> </enum> <enum name="a6xx_state_type"> <value name="ST6_SHADER" value="0"/> <value name="ST6_CONSTANTS" value="1"/> <value name="ST6_UBO" value="2"/> - <value name="ST6_IBO" value="3"/> + <value name="ST6_UAV" value="3"/> </enum> <enum name="a6xx_state_src"> <value name="SS6_DIRECT" value="0"/> @@ -1121,39 +1134,93 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) </reg32> </domain> +<enum name="a7xx_abs_mask_mode"> + <value name="ABS_MASK" value="0x1"/> + <value name="NO_ABS_MASK" value="0x0"/> +</enum> + <domain name="CP_SET_BIN_DATA5" width="32"> <reg32 offset="0" name="0"> + <bitfield name="VSC_MASK" low="0" high="15" type="hex"> + <doc> + A mask of bins, starting at VSC_N, whose + visibility is OR'd together. A value of 0 is + interpreted as 1 (i.e. just use VSC_N for + visbility) for backwards compatibility. Only + exists on a7xx. + </doc> + </bitfield> <!-- equiv to PC_VSTREAM_CONTROL.SIZE on a3xx/a4xx: --> <bitfield name="VSC_SIZE" low="16" high="21" type="uint"/> <!-- equiv to PC_VSTREAM_CONTROL.N on a3xx/a4xx: --> <bitfield name="VSC_N" low="22" high="26" type="uint"/> + <bitfield name="ABS_MASK" pos="28" type="a7xx_abs_mask_mode" addvariant="yes"> + <doc> + If this field is 1, VSC_MASK and VSC_N are + ignored and instead a new ordinal immediately + after specifies the full 32-bit mask of bins + to use. The mask is "absolute" instead of + relative to VSC_N. + </doc> + </bitfield> </reg32> - <!-- BIN_DATA_ADDR -> VSC_PIPE[p].DATA_ADDRESS --> - <reg32 offset="1" name="1"> - <bitfield name="BIN_DATA_ADDR_LO" low="0" high="31" type="hex"/> - </reg32> - <reg32 offset="2" name="2"> - <bitfield name="BIN_DATA_ADDR_HI" low="0" high="31" type="hex"/> - </reg32> - <!-- BIN_SIZE_ADDRESS -> VSC_SIZE_ADDRESS + (p * 4)--> - <reg32 offset="3" name="3"> - <bitfield name="BIN_SIZE_ADDRESS_LO" low="0" high="31"/> - </reg32> - <reg32 offset="4" name="4"> - <bitfield name="BIN_SIZE_ADDRESS_HI" low="0" high="31"/> - </reg32> - <!-- new on a6xx, where BIN_DATA_ADDR is the DRAW_STRM: --> - <reg32 offset="5" name="5"> - <bitfield name="BIN_PRIM_STRM_LO" low="0" high="31"/> - </reg32> - <reg32 offset="6" name="6"> - <bitfield name="BIN_PRIM_STRM_HI" low="0" high="31"/> - </reg32> - <!-- - a7xx adds a few more addresses to the end of the pkt - --> - <reg64 offset="7" name="7"/> - <reg64 offset="9" name="9"/> + <stripe varset="a7xx_abs_mask_mode" variants="NO_ABS_MASK"> + <!-- BIN_DATA_ADDR -> VSC_PIPE[p].DATA_ADDRESS --> + <reg32 offset="1" name="1"> + <bitfield name="BIN_DATA_ADDR_LO" low="0" high="31" type="hex"/> + </reg32> + <reg32 offset="2" name="2"> + <bitfield name="BIN_DATA_ADDR_HI" low="0" high="31" type="hex"/> + </reg32> + <!-- BIN_SIZE_ADDRESS -> VSC_SIZE_ADDRESS + (p * 4)--> + <reg32 offset="3" name="3"> + <bitfield name="BIN_SIZE_ADDRESS_LO" low="0" high="31"/> + </reg32> + <reg32 offset="4" name="4"> + <bitfield name="BIN_SIZE_ADDRESS_HI" low="0" high="31"/> + </reg32> + <!-- new on a6xx, where BIN_DATA_ADDR is the DRAW_STRM: --> + <reg32 offset="5" name="5"> + <bitfield name="BIN_PRIM_STRM_LO" low="0" high="31"/> + </reg32> + <reg32 offset="6" name="6"> + <bitfield name="BIN_PRIM_STRM_HI" low="0" high="31"/> + </reg32> + <!-- + a7xx adds a few more addresses to the end of the pkt + --> + <reg64 offset="7" name="7"/> + <reg64 offset="9" name="9"/> + </stripe> + <stripe varset="a7xx_abs_mask_mode" variants="ABS_MASK"> + <reg32 offset="1" name="ABS_MASK"/> + <!-- BIN_DATA_ADDR -> VSC_PIPE[p].DATA_ADDRESS --> + <reg32 offset="2" name="2"> + <bitfield name="BIN_DATA_ADDR_LO" low="0" high="31" type="hex"/> + </reg32> + <reg32 offset="3" name="3"> + <bitfield name="BIN_DATA_ADDR_HI" low="0" high="31" type="hex"/> + </reg32> + <!-- BIN_SIZE_ADDRESS -> VSC_SIZE_ADDRESS + (p * 4)--> + <reg32 offset="4" name="4"> + <bitfield name="BIN_SIZE_ADDRESS_LO" low="0" high="31"/> + </reg32> + <reg32 offset="5" name="5"> + <bitfield name="BIN_SIZE_ADDRESS_HI" low="0" high="31"/> + </reg32> + <!-- new on a6xx, where BIN_DATA_ADDR is the DRAW_STRM: --> + <reg32 offset="6" name="6"> + <bitfield name="BIN_PRIM_STRM_LO" low="0" high="31"/> + </reg32> + <reg32 offset="7" name="7"> + <bitfield name="BIN_PRIM_STRM_HI" low="0" high="31"/> + </reg32> + <!-- + a7xx adds a few more addresses to the end of the pkt + --> + <reg64 offset="8" name="8"/> + <reg64 offset="10" name="10"/> + </stripe> </domain> <domain name="CP_SET_BIN_DATA5_OFFSET" width="32"> @@ -1164,23 +1231,42 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) stream is recorded. </doc> <reg32 offset="0" name="0"> + <bitfield name="VSC_MASK" low="0" high="15" type="hex"/> <!-- equiv to PC_VSTREAM_CONTROL.SIZE on a3xx/a4xx: --> <bitfield name="VSC_SIZE" low="16" high="21" type="uint"/> <!-- equiv to PC_VSTREAM_CONTROL.N on a3xx/a4xx: --> <bitfield name="VSC_N" low="22" high="26" type="uint"/> + <bitfield name="ABS_MASK" pos="28" type="a7xx_abs_mask_mode" addvariant="yes"/> </reg32> - <!-- BIN_DATA_ADDR -> VSC_PIPE[p].DATA_ADDRESS --> - <reg32 offset="1" name="1"> - <bitfield name="BIN_DATA_OFFSET" low="0" high="31" type="uint"/> - </reg32> - <!-- BIN_SIZE_ADDRESS -> VSC_SIZE_ADDRESS + (p * 4)--> - <reg32 offset="2" name="2"> - <bitfield name="BIN_SIZE_OFFSET" low="0" high="31" type="uint"/> - </reg32> - <!-- BIN_DATA2_ADDR -> VSC_PIPE[p].DATA2_ADDRESS --> - <reg32 offset="3" name="3"> - <bitfield name="BIN_DATA2_OFFSET" low="0" high="31" type="uint"/> - </reg32> + <stripe varset="a7xx_abs_mask_mode" variants="NO_ABS_MASK"> + <!-- BIN_DATA_ADDR -> VSC_PIPE[p].DATA_ADDRESS --> + <reg32 offset="1" name="1"> + <bitfield name="BIN_DATA_OFFSET" low="0" high="31" type="uint"/> + </reg32> + <!-- BIN_SIZE_ADDRESS -> VSC_SIZE_ADDRESS + (p * 4)--> + <reg32 offset="2" name="2"> + <bitfield name="BIN_SIZE_OFFSET" low="0" high="31" type="uint"/> + </reg32> + <!-- BIN_DATA2_ADDR -> VSC_PIPE[p].DATA2_ADDRESS --> + <reg32 offset="3" name="3"> + <bitfield name="BIN_DATA2_OFFSET" low="0" high="31" type="uint"/> + </reg32> + </stripe> + <stripe varset="a7xx_abs_mask_mode" variants="ABS_MASK"> + <reg32 offset="1" name="ABS_MASK"/> + <!-- BIN_DATA_ADDR -> VSC_PIPE[p].DATA_ADDRESS --> + <reg32 offset="2" name="2"> + <bitfield name="BIN_DATA_OFFSET" low="0" high="31" type="uint"/> + </reg32> + <!-- BIN_SIZE_ADDRESS -> VSC_SIZE_ADDRESS + (p * 4)--> + <reg32 offset="3" name="3"> + <bitfield name="BIN_SIZE_OFFSET" low="0" high="31" type="uint"/> + </reg32> + <!-- BIN_DATA2_ADDR -> VSC_PIPE[p].DATA2_ADDRESS --> + <reg32 offset="4" name="4"> + <bitfield name="BIN_DATA2_OFFSET" low="0" high="31" type="uint"/> + </reg32> + </stripe> </domain> <domain name="CP_REG_RMW" width="32"> @@ -1198,6 +1284,9 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) </doc> <reg32 offset="0" name="0"> <bitfield name="DST_REG" low="0" high="17" type="hex"/> + <bitfield name="DST_SCRATCH" pos="19" type="boolean" varset="chip" variants="A7XX-"/> + <!-- skip implied CP_WAIT_FOR_IDLE + CP_WAIT_FOR_ME --> + <bitfield name="SKIP_WAIT_FOR_ME" pos="23" type="boolean" varset="chip" variants="A7XX-"/> <bitfield name="ROTATE" low="24" high="28" type="uint"/> <bitfield name="SRC1_ADD" pos="29" type="boolean"/> <bitfield name="SRC1_IS_REG" pos="30" type="boolean"/> @@ -1348,6 +1437,8 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <bitfield name="SCRATCH" low="20" high="22" type="uint"/> <!-- number of registers/dwords copied is CNT + 1. --> <bitfield name="CNT" low="24" high="26" type="uint"/> + <!-- skip implied CP_WAIT_FOR_IDLE + CP_WAIT_FOR_ME --> + <bitfield name="SKIP_WAIT_FOR_ME" pos="27" type="boolean" varset="chip" variants="A7XX-"/> </reg32> </domain> @@ -1655,8 +1746,8 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <bitfield name="WRITE_SAMPLE_COUNT" pos="12" type="boolean"/> <!-- Write sample count at (iova + 16) --> <bitfield name="SAMPLE_COUNT_END_OFFSET" pos="13" type="boolean"/> - <!-- *(iova + 8) = *(iova + 16) - *iova --> - <bitfield name="WRITE_SAMPLE_COUNT_DIFF" pos="14" type="boolean"/> + <!-- *(iova + 8) += *(iova + 16) - *iova --> + <bitfield name="WRITE_ACCUM_SAMPLE_COUNT_DIFF" pos="14" type="boolean"/> <!-- Next 4 flags are valid to set only when concurrent binning is enabled --> <!-- Increment 16b BV counter. Valid only in BV pipe --> @@ -1670,15 +1761,11 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <bitfield name="WRITE_DST" pos="24" type="event_write_dst" addvariant="yes"/> <!-- Writes into WRITE_DST from WRITE_SRC. RB_DONE_TS requires WRITE_ENABLED. --> <bitfield name="WRITE_ENABLED" pos="27" type="boolean"/> + <bitfield name="IRQ" pos="31" type="boolean"/> </reg32> <stripe varset="event_write_dst" variants="EV_DST_RAM"> - <reg32 offset="1" name="1"> - <bitfield name="ADDR_0_LO" low="0" high="31"/> - </reg32> - <reg32 offset="2" name="2"> - <bitfield name="ADDR_0_HI" low="0" high="31"/> - </reg32> + <reg64 offset="1" name="1" type="waddress"/> <reg32 offset="3" name="3"> <bitfield name="PAYLOAD_0" low="0" high="31"/> </reg32> @@ -1773,13 +1860,23 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <domain name="CP_SET_MARKER" width="32" varset="chip" prefix="chip" variants="A6XX-"> <doc>Tell CP the current operation mode, indicates save and restore procedure</doc> + <enum name="set_marker_mode"> + <value value="0" name="SET_RENDER_MODE"/> + <!-- IFPC - inter-frame power collapse --> + <value value="1" name="SET_IFPC_MODE"/> + </enum> + <enum name="a6xx_ifpc_mode"> + <value value="0" name="IFPC_ENABLE"/> + <value value="1" name="IFPC_DISABLE"/> + </enum> <enum name="a6xx_marker"> - <value value="1" name="RM6_BYPASS"/> - <value value="2" name="RM6_BINNING"/> - <value value="4" name="RM6_GMEM"/> - <value value="5" name="RM6_ENDVIS"/> - <value value="6" name="RM6_RESOLVE"/> - <value value="7" name="RM6_YIELD"/> + <value value="1" name="RM6_DIRECT_RENDER"/> + <value value="2" name="RM6_BIN_VISIBILITY"/> + <value value="3" name="RM6_BIN_DIRECT"/> + <value value="4" name="RM6_BIN_RENDER_START"/> + <value value="5" name="RM6_BIN_END_OF_DRAWS"/> + <value value="6" name="RM6_BIN_RESOLVE"/> + <value value="7" name="RM6_BIN_RENDER_END"/> <value value="8" name="RM6_COMPUTE"/> <value value="0xc" name="RM6_BLIT2DSCALE"/> <!-- no-op (at least on current sqe fw) --> @@ -1789,23 +1886,40 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) --> <value value="0xd" name="RM6_IB1LIST_START"/> <value value="0xe" name="RM6_IB1LIST_END"/> - <!-- IFPC - inter-frame power collapse --> - <value value="0x100" name="RM6_IFPC_ENABLE"/> - <value value="0x101" name="RM6_IFPC_DISABLE"/> </enum> <reg32 offset="0" name="0"> + <!-- if b8 is set, the low bits are interpreted differently (and b4 ignored) --> + <bitfield name="MARKER_MODE" pos="8" type="set_marker_mode" addvariant="yes"/> + + <bitfield name="MODE" low="0" high="3" type="a6xx_marker" varset="set_marker_mode" variants="SET_RENDER_MODE"/> + <!-- used by preemption to determine if GMEM needs to be saved or not --> + <bitfield name="USES_GMEM" pos="4" type="boolean" varset="set_marker_mode" variants="SET_RENDER_MODE"/> + + <bitfield name="IFPC_MODE" pos="0" type="a6xx_ifpc_mode" varset="set_marker_mode" variants="SET_IFPC_MODE"/> + <!-- - NOTE: blob driver and some versions of freedreno/turnip set - b4, which is unused (at least by current sqe fw), but interferes - with parsing if we extend the size of the bitfield to include - b8 (only sent by kernel mode driver). Really, the way the - parsing works in the firmware, only b0-b3 are considered, but - if b8 is set, the low bits are interpreted differently. To - model this, without getting confused by spurious b4, this is - described as two overlapping bitfields: - --> - <bitfield name="MODE" low="0" high="8" type="a6xx_marker"/> - <bitfield name="MARKER" low="0" high="3" type="a6xx_marker"/> + CP_SET_MARKER is used with these bits to create a + critical section around a workaround for ray tracing. + The workaround happens after BVH building, and appears + to invalidate the RTU's BVH node cache. It makes sure + that only one of BR/BV/LPAC is executing the + workaround at a time, and no draws using RT on BV/LPAC + are executing while the workaround is executed on BR (or + vice versa, that no draws on BV/BR using RT are executed + while the workaround executes on LPAC), by + hooking subsequent CP_EVENT_WRITE/CP_DRAW_*/CP_EXEC_CS. + The blob usage is: + + CP_SET_MARKER(RT_WA_START) + ... workaround here ... + CP_SET_MARKER(RT_WA_END) + ... + CP_SET_MARKER(SHADER_USES_RT) + CP_DRAW_INDX(...) or CP_EXEC_CS(...) + --> + <bitfield name="SHADER_USES_RT" pos="9" type="boolean" variants="A7XX-"/> + <bitfield name="RT_WA_START" pos="10" type="boolean" variants="A7XX-"/> + <bitfield name="RT_WA_END" pos="11" type="boolean" variants="A7XX-"/> </reg32> </domain> @@ -1832,9 +1946,9 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) If concurrent binning is disabled then BR also does binning so it will also write the "real" registers in BR. --> - <value value="8" name="DRAW_STRM_ADDRESS"/> - <value value="9" name="DRAW_STRM_SIZE_ADDRESS"/> - <value value="10" name="PRIM_STRM_ADDRESS"/> + <value value="8" name="VSC_PIPE_DATA_DRAW_BASE"/> + <value value="9" name="VSC_SIZE_BASE"/> + <value value="10" name="VSC_PIPE_DATA_PRIM_BASE"/> <value value="11" name="UNK_STRM_ADDRESS"/> <value value="12" name="UNK_STRM_SIZE_ADDRESS"/> @@ -1935,11 +2049,11 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) a bitmask of which modes pass the test. --> - <!-- RM6_BINNING --> + <!-- RM6_BIN_VISIBILITY --> <bitfield name="BINNING" pos="25" variants="RENDER_MODE" type="boolean"/> <!-- all others --> <bitfield name="GMEM" pos="26" variants="RENDER_MODE" type="boolean"/> - <!-- RM6_BYPASS --> + <!-- RM6_DIRECT_RENDER --> <bitfield name="SYSMEM" pos="27" variants="RENDER_MODE" type="boolean"/> <bitfield name="BV" pos="25" variants="THREAD_MODE" type="boolean"/> @@ -2014,10 +2128,10 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <domain name="CP_SET_AMBLE" width="32"> <doc> - Used by the userspace and kernel drivers to set various IB's - which are executed during context save/restore for handling - state that isn't restored by the context switch routine itself. - </doc> + Used by the userspace and kernel drivers to set various IB's + which are executed during context save/restore for handling + state that isn't restored by the context switch routine itself. + </doc> <enum name="amble_type"> <value name="PREAMBLE_AMBLE_TYPE" value="0"> <doc>Executed unconditionally when switching back to the context.</doc> @@ -2087,12 +2201,12 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <value name="UNK_EVENT_WRITE" value="0x4"/> <doc> Tracks GRAS_LRZ_CNTL::GREATER, GRAS_LRZ_CNTL::DIR, and - GRAS_LRZ_DEPTH_VIEW with previous values, and if one of + GRAS_LRZ_VIEW_INFO with previous values, and if one of the following is true: - GRAS_LRZ_CNTL::GREATER has changed - GRAS_LRZ_CNTL::DIR has changed, the old value is not CUR_DIR_GE, and the new value is not CUR_DIR_DISABLED - - GRAS_LRZ_DEPTH_VIEW has changed + - GRAS_LRZ_VIEW_INFO has changed then it does a LRZ_FLUSH with GRAS_LRZ_CNTL::ENABLE forced to 1. Only exists in a650_sqe.fw. @@ -2207,7 +2321,7 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <domain name="CP_MEM_TO_SCRATCH_MEM" width="32"> <doc> - Best guess is that it is a faster way to fetch all the VSC_STATE registers + Best guess is that it is a faster way to fetch all the VSC_CHANNEL_VISIBILITY registers and keep them in a local scratch memory instead of fetching every time when skipping IBs. </doc> @@ -2255,7 +2369,25 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <reg32 offset="0" name="0"> <bitfield name="CLEAR_ON_CHIP_TS" pos="0" type="boolean"/> <bitfield name="CLEAR_RESOURCE_TABLE" pos="1" type="boolean"/> - <bitfield name="CLEAR_GLOBAL_LOCAL_TS" pos="2" type="boolean"/> + <bitfield name="CLEAR_BV_BR_COUNTER" pos="2" type="boolean"/> + <bitfield name="RESET_GLOBAL_LOCAL_TS" pos="3" type="boolean"/> + </reg32> +</domain> + +<domain name="CP_SCOPE_CNTL" width="32"> + <enum name="cp_scope"> + <value value="0" name="INTERRUPTS"/> + </enum> + <reg32 offset="0" name="0"> + <bitfield name="DISABLE_PREEMPTION" pos="0" type="boolean"/> + <bitfield low="28" high="31" name="SCOPE" type="cp_scope"/> + </reg32> +</domain> + +<domain name="CP_INDIRECT_BUFFER" width="32" varset="chip" prefix="chip" variants="A5XX-"> + <reg64 offset="0" name="IB_BASE" type="address"/> + <reg32 offset="2" name="2"> + <bitfield name="IB_SIZE" low="0" high="19"/> </reg32> </domain> diff --git a/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml b/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml index 35f7f40e405b..d2c8c46bb041 100644 --- a/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml +++ b/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml @@ -17,6 +17,7 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <bitfield name="CLK_EN" pos="5" type="boolean"/> <bitfield name="CLK_EN_SEL" pos="4" type="boolean"/> <bitfield name="BITCLK_SEL" low="2" high="3" type="uint"/> + <bitfield name="DSICLK_SEL" low="0" high="1" type="uint"/> </reg32> <reg32 offset="0x00018" name="GLBL_CTRL"/> <reg32 offset="0x0001c" name="RBUF_CTRL"/> diff --git a/drivers/gpu/drm/msm/registers/display/hdmi.xml b/drivers/gpu/drm/msm/registers/display/hdmi.xml index 1cf1b14fbd91..0ebb96297dae 100644 --- a/drivers/gpu/drm/msm/registers/display/hdmi.xml +++ b/drivers/gpu/drm/msm/registers/display/hdmi.xml @@ -131,7 +131,7 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> --> <bitfield name="GENERIC0_SEND" pos="0" type="boolean"/> <bitfield name="GENERIC0_CONT" pos="1" type="boolean"/> - <bitfield name="GENERIC0_UPDATE" low="2" high="3" type="uint"/> <!-- ??? --> + <bitfield name="GENERIC0_UPDATE" pos="2" type="boolean"/> <bitfield name="GENERIC1_SEND" pos="4" type="boolean"/> <bitfield name="GENERIC1_CONT" pos="5" type="boolean"/> <bitfield name="GENERIC0_LINE" low="16" high="21" type="uint"/> diff --git a/drivers/gpu/drm/msm/registers/display/mdss.xml b/drivers/gpu/drm/msm/registers/display/mdss.xml index ac85caf1575c..6e9f81cd4690 100644 --- a/drivers/gpu/drm/msm/registers/display/mdss.xml +++ b/drivers/gpu/drm/msm/registers/display/mdss.xml @@ -21,7 +21,16 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <reg32 offset="0x00058" name="UBWC_DEC_HW_VERSION"/> - <reg32 offset="0x00144" name="UBWC_STATIC"/> + <reg32 offset="0x00144" name="UBWC_STATIC"> + <bitfield name="UBWC_SWIZZLE" low="0" high="2"/> + <bitfield name="UBWC_BANK_SPREAD" pos="3"/> + <!-- high=5 for UBWC < 4.0 --> + <bitfield name="HIGHEST_BANK_BIT" low="4" high="6"/> + <bitfield name="UBWC_MIN_ACC_LEN" low="8" high="9"/> + <bitfield name="UBWC_AMSBC" pos="10"/> + <bitfield name="MACROTILE_MODE" pos="12"/> + </reg32> + <reg32 offset="0x00150" name="UBWC_CTRL_2"/> <reg32 offset="0x00154" name="UBWC_PREDICTION_MODE"/> </domain> diff --git a/drivers/gpu/drm/msm/registers/gen_header.py b/drivers/gpu/drm/msm/registers/gen_header.py index 3926485bb197..a409404627c7 100644 --- a/drivers/gpu/drm/msm/registers/gen_header.py +++ b/drivers/gpu/drm/msm/registers/gen_header.py @@ -11,6 +11,7 @@ import collections import argparse import time import datetime +import re class Error(Exception): def __init__(self, message): @@ -877,13 +878,14 @@ The rules-ng-ng source files this header was generated from are: """) maxlen = 0 for filepath in p.xml_files: - maxlen = max(maxlen, len(filepath)) + new_filepath = re.sub("^.+drivers","drivers",filepath) + maxlen = max(maxlen, len(new_filepath)) for filepath in p.xml_files: - pad = " " * (maxlen - len(filepath)) + pad = " " * (maxlen - len(new_filepath)) filesize = str(os.path.getsize(filepath)) filesize = " " * (7 - len(filesize)) + filesize filetime = time.ctime(os.path.getmtime(filepath)) - print("- " + filepath + pad + " (" + filesize + " bytes, from " + filetime + ")") + print("- " + new_filepath + pad + " (" + filesize + " bytes, from <stripped>)") if p.copyright_year: current_year = str(datetime.date.today().year) print() |