diff options
Diffstat (limited to 'drivers/gpu/drm/msm')
74 files changed, 6781 insertions, 2302 deletions
diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile index 0c0dfb25f01b..8aa7d07303fb 100644 --- a/drivers/gpu/drm/msm/Makefile +++ b/drivers/gpu/drm/msm/Makefile @@ -24,6 +24,7 @@ adreno-y := \ adreno/a6xx_gmu.o \ adreno/a6xx_hfi.o \ adreno/a6xx_preempt.o \ + adreno/a8xx_gpu.o \ adreno-$(CONFIG_DEBUG_FS) += adreno/a5xx_debugfs.o \ @@ -201,6 +202,7 @@ ADRENO_HEADERS = \ generated/a6xx_perfcntrs.xml.h \ generated/a7xx_enums.xml.h \ generated/a7xx_perfcntrs.xml.h \ + generated/a8xx_enums.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 5ddd015f930d..e9dbf3ddf89e 100644 --- a/drivers/gpu/drm/msm/adreno/a2xx_catalog.c +++ b/drivers/gpu/drm/msm/adreno/a2xx_catalog.c @@ -7,6 +7,7 @@ */ #include "adreno_gpu.h" +#include "a2xx_gpu.h" static const struct adreno_info a2xx_gpus[] = { { @@ -19,7 +20,7 @@ static const struct adreno_info a2xx_gpus[] = { }, .gmem = SZ_256K, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a2xx_gpu_init, + .funcs = &a2xx_gpu_funcs, }, { /* a200 on i.mx51 has only 128kib gmem */ .chip_ids = ADRENO_CHIP_IDS(0x02000001), .family = ADRENO_2XX_GEN1, @@ -30,7 +31,7 @@ static const struct adreno_info a2xx_gpus[] = { }, .gmem = SZ_128K, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a2xx_gpu_init, + .funcs = &a2xx_gpu_funcs, }, { .chip_ids = ADRENO_CHIP_IDS(0x02020000), .family = ADRENO_2XX_GEN2, @@ -41,7 +42,7 @@ static const struct adreno_info a2xx_gpus[] = { }, .gmem = SZ_512K, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a2xx_gpu_init, + .funcs = &a2xx_gpu_funcs, } }; DECLARE_ADRENO_GPULIST(a2xx); diff --git a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c index ec38db45d8a3..1b1ee14b65cf 100644 --- a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c @@ -234,7 +234,7 @@ static int a2xx_hw_init(struct msm_gpu *gpu) * word (0x20xxxx for A200, 0x220xxx for A220, 0x225xxx for A225). * Older firmware files, which lack protection support, have 0 instead. */ - if (ptr[1] == 0) { + if (ptr[1] == 0 && !a2xx_gpu->protection_disabled) { dev_warn(gpu->dev->dev, "Legacy firmware detected, disabling protection support\n"); a2xx_gpu->protection_disabled = true; @@ -486,39 +486,18 @@ static u32 a2xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) return ring->memptrs->rptr; } -static const struct adreno_gpu_funcs funcs = { - .base = { - .get_param = adreno_get_param, - .set_param = adreno_set_param, - .hw_init = a2xx_hw_init, - .pm_suspend = msm_gpu_pm_suspend, - .pm_resume = msm_gpu_pm_resume, - .recover = a2xx_recover, - .submit = a2xx_submit, - .active_ring = adreno_active_ring, - .irq = a2xx_irq, - .destroy = a2xx_destroy, -#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP) - .show = adreno_show, -#endif - .gpu_state_get = a2xx_gpu_state_get, - .gpu_state_put = adreno_gpu_state_put, - .create_vm = a2xx_create_vm, - .get_rptr = a2xx_get_rptr, - }, -}; - static const struct msm_gpu_perfcntr perfcntrs[] = { /* TODO */ }; -struct msm_gpu *a2xx_gpu_init(struct drm_device *dev) +static struct msm_gpu *a2xx_gpu_init(struct drm_device *dev) { struct a2xx_gpu *a2xx_gpu = NULL; struct adreno_gpu *adreno_gpu; struct msm_gpu *gpu; struct msm_drm_private *priv = dev->dev_private; struct platform_device *pdev = priv->gpu_pdev; + struct adreno_platform_config *config = pdev->dev.platform_data; int ret; if (!pdev) { @@ -539,7 +518,7 @@ struct msm_gpu *a2xx_gpu_init(struct drm_device *dev) gpu->perfcntrs = perfcntrs; gpu->num_perfcntrs = ARRAY_SIZE(perfcntrs); - ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1); + ret = adreno_gpu_init(dev, pdev, adreno_gpu, config->info->funcs, 1); if (ret) goto fail; @@ -558,3 +537,26 @@ fail: return ERR_PTR(ret); } + +const struct adreno_gpu_funcs a2xx_gpu_funcs = { + .base = { + .get_param = adreno_get_param, + .set_param = adreno_set_param, + .hw_init = a2xx_hw_init, + .pm_suspend = msm_gpu_pm_suspend, + .pm_resume = msm_gpu_pm_resume, + .recover = a2xx_recover, + .submit = a2xx_submit, + .active_ring = adreno_active_ring, + .irq = a2xx_irq, + .destroy = a2xx_destroy, +#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP) + .show = adreno_show, +#endif + .gpu_state_get = a2xx_gpu_state_get, + .gpu_state_put = adreno_gpu_state_put, + .create_vm = a2xx_create_vm, + .get_rptr = a2xx_get_rptr, + }, + .init = a2xx_gpu_init, +}; diff --git a/drivers/gpu/drm/msm/adreno/a2xx_gpu.h b/drivers/gpu/drm/msm/adreno/a2xx_gpu.h index 53702f19990f..162ef98951f5 100644 --- a/drivers/gpu/drm/msm/adreno/a2xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a2xx_gpu.h @@ -19,6 +19,8 @@ struct a2xx_gpu { }; #define to_a2xx_gpu(x) container_of(x, struct a2xx_gpu, base) +extern const struct adreno_gpu_funcs a2xx_gpu_funcs; + struct msm_mmu *a2xx_gpummu_new(struct device *dev, struct msm_gpu *gpu); void a2xx_gpummu_params(struct msm_mmu *mmu, dma_addr_t *pt_base, dma_addr_t *tran_error); diff --git a/drivers/gpu/drm/msm/adreno/a3xx_catalog.c b/drivers/gpu/drm/msm/adreno/a3xx_catalog.c index 1498e6532f62..6ae8716fc08a 100644 --- a/drivers/gpu/drm/msm/adreno/a3xx_catalog.c +++ b/drivers/gpu/drm/msm/adreno/a3xx_catalog.c @@ -7,6 +7,7 @@ */ #include "adreno_gpu.h" +#include "a3xx_gpu.h" static const struct adreno_info a3xx_gpus[] = { { @@ -18,7 +19,7 @@ static const struct adreno_info a3xx_gpus[] = { }, .gmem = SZ_128K, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a3xx_gpu_init, + .funcs = &a3xx_gpu_funcs, }, { .chip_ids = ADRENO_CHIP_IDS(0x03000520), .family = ADRENO_3XX, @@ -29,7 +30,7 @@ static const struct adreno_info a3xx_gpus[] = { }, .gmem = SZ_256K, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a3xx_gpu_init, + .funcs = &a3xx_gpu_funcs, }, { .chip_ids = ADRENO_CHIP_IDS(0x03000600), .family = ADRENO_3XX, @@ -40,7 +41,7 @@ static const struct adreno_info a3xx_gpus[] = { }, .gmem = SZ_128K, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a3xx_gpu_init, + .funcs = &a3xx_gpu_funcs, }, { .chip_ids = ADRENO_CHIP_IDS(0x03000620), .family = ADRENO_3XX, @@ -51,7 +52,7 @@ static const struct adreno_info a3xx_gpus[] = { }, .gmem = SZ_128K, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a3xx_gpu_init, + .funcs = &a3xx_gpu_funcs, }, { .chip_ids = ADRENO_CHIP_IDS( 0x03020000, @@ -66,7 +67,7 @@ static const struct adreno_info a3xx_gpus[] = { }, .gmem = SZ_512K, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a3xx_gpu_init, + .funcs = &a3xx_gpu_funcs, }, { .chip_ids = ADRENO_CHIP_IDS( 0x03030000, @@ -81,7 +82,7 @@ static const struct adreno_info a3xx_gpus[] = { }, .gmem = SZ_1M, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a3xx_gpu_init, + .funcs = &a3xx_gpu_funcs, } }; DECLARE_ADRENO_GPULIST(a3xx); diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c index a956cd79195e..f22d33e99e81 100644 --- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c @@ -508,29 +508,6 @@ static u32 a3xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) return ring->memptrs->rptr; } -static const struct adreno_gpu_funcs funcs = { - .base = { - .get_param = adreno_get_param, - .set_param = adreno_set_param, - .hw_init = a3xx_hw_init, - .pm_suspend = msm_gpu_pm_suspend, - .pm_resume = msm_gpu_pm_resume, - .recover = a3xx_recover, - .submit = a3xx_submit, - .active_ring = adreno_active_ring, - .irq = a3xx_irq, - .destroy = a3xx_destroy, -#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP) - .show = adreno_show, -#endif - .gpu_busy = a3xx_gpu_busy, - .gpu_state_get = a3xx_gpu_state_get, - .gpu_state_put = adreno_gpu_state_put, - .create_vm = adreno_create_vm, - .get_rptr = a3xx_get_rptr, - }, -}; - static const struct msm_gpu_perfcntr perfcntrs[] = { { REG_A3XX_SP_PERFCOUNTER6_SELECT, REG_A3XX_RBBM_PERFCTR_SP_6_LO, SP_ALU_ACTIVE_CYCLES, "ALUACTIVE" }, @@ -538,13 +515,14 @@ static const struct msm_gpu_perfcntr perfcntrs[] = { SP_FS_FULL_ALU_INSTRUCTIONS, "ALUFULL" }, }; -struct msm_gpu *a3xx_gpu_init(struct drm_device *dev) +static struct msm_gpu *a3xx_gpu_init(struct drm_device *dev) { struct a3xx_gpu *a3xx_gpu = NULL; struct adreno_gpu *adreno_gpu; struct msm_gpu *gpu; struct msm_drm_private *priv = dev->dev_private; struct platform_device *pdev = priv->gpu_pdev; + struct adreno_platform_config *config = pdev->dev.platform_data; struct icc_path *ocmem_icc_path; struct icc_path *icc_path; int ret; @@ -569,7 +547,7 @@ struct msm_gpu *a3xx_gpu_init(struct drm_device *dev) adreno_gpu->registers = a3xx_registers; - ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1); + ret = adreno_gpu_init(dev, pdev, adreno_gpu, config->info->funcs, 1); if (ret) goto fail; @@ -613,3 +591,27 @@ fail: return ERR_PTR(ret); } + +const struct adreno_gpu_funcs a3xx_gpu_funcs = { + .base = { + .get_param = adreno_get_param, + .set_param = adreno_set_param, + .hw_init = a3xx_hw_init, + .pm_suspend = msm_gpu_pm_suspend, + .pm_resume = msm_gpu_pm_resume, + .recover = a3xx_recover, + .submit = a3xx_submit, + .active_ring = adreno_active_ring, + .irq = a3xx_irq, + .destroy = a3xx_destroy, +#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP) + .show = adreno_show, +#endif + .gpu_busy = a3xx_gpu_busy, + .gpu_state_get = a3xx_gpu_state_get, + .gpu_state_put = adreno_gpu_state_put, + .create_vm = adreno_create_vm, + .get_rptr = a3xx_get_rptr, + }, + .init = a3xx_gpu_init, +}; diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.h b/drivers/gpu/drm/msm/adreno/a3xx_gpu.h index c555fb13e0d7..3d4ec9dbd918 100644 --- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.h @@ -23,4 +23,6 @@ struct a3xx_gpu { }; #define to_a3xx_gpu(x) container_of(x, struct a3xx_gpu, base) +extern const struct adreno_gpu_funcs a3xx_gpu_funcs; + #endif /* __A3XX_GPU_H__ */ diff --git a/drivers/gpu/drm/msm/adreno/a4xx_catalog.c b/drivers/gpu/drm/msm/adreno/a4xx_catalog.c index 09f9f228b75e..9192586f7ef0 100644 --- a/drivers/gpu/drm/msm/adreno/a4xx_catalog.c +++ b/drivers/gpu/drm/msm/adreno/a4xx_catalog.c @@ -7,6 +7,7 @@ */ #include "adreno_gpu.h" +#include "a4xx_gpu.h" static const struct adreno_info a4xx_gpus[] = { { @@ -19,7 +20,7 @@ static const struct adreno_info a4xx_gpus[] = { }, .gmem = SZ_256K, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a4xx_gpu_init, + .funcs = &a4xx_gpu_funcs, }, { .chip_ids = ADRENO_CHIP_IDS(0x04020000), .family = ADRENO_4XX, @@ -30,7 +31,7 @@ static const struct adreno_info a4xx_gpus[] = { }, .gmem = (SZ_1M + SZ_512K), .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a4xx_gpu_init, + .funcs = &a4xx_gpu_funcs, }, { .chip_ids = ADRENO_CHIP_IDS(0x04030002), .family = ADRENO_4XX, @@ -41,7 +42,7 @@ static const struct adreno_info a4xx_gpus[] = { }, .gmem = (SZ_1M + SZ_512K), .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a4xx_gpu_init, + .funcs = &a4xx_gpu_funcs, } }; DECLARE_ADRENO_GPULIST(a4xx); diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c index 83f6329accba..db06c06067ae 100644 --- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c @@ -627,37 +627,14 @@ static u32 a4xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) return ring->memptrs->rptr; } -static const struct adreno_gpu_funcs funcs = { - .base = { - .get_param = adreno_get_param, - .set_param = adreno_set_param, - .hw_init = a4xx_hw_init, - .pm_suspend = a4xx_pm_suspend, - .pm_resume = a4xx_pm_resume, - .recover = a4xx_recover, - .submit = a4xx_submit, - .active_ring = adreno_active_ring, - .irq = a4xx_irq, - .destroy = a4xx_destroy, -#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP) - .show = adreno_show, -#endif - .gpu_busy = a4xx_gpu_busy, - .gpu_state_get = a4xx_gpu_state_get, - .gpu_state_put = adreno_gpu_state_put, - .create_vm = adreno_create_vm, - .get_rptr = a4xx_get_rptr, - }, - .get_timestamp = a4xx_get_timestamp, -}; - -struct msm_gpu *a4xx_gpu_init(struct drm_device *dev) +static struct msm_gpu *a4xx_gpu_init(struct drm_device *dev) { struct a4xx_gpu *a4xx_gpu = NULL; struct adreno_gpu *adreno_gpu; struct msm_gpu *gpu; struct msm_drm_private *priv = dev->dev_private; struct platform_device *pdev = priv->gpu_pdev; + struct adreno_platform_config *config = pdev->dev.platform_data; struct icc_path *ocmem_icc_path; struct icc_path *icc_path; int ret; @@ -680,7 +657,7 @@ struct msm_gpu *a4xx_gpu_init(struct drm_device *dev) gpu->perfcntrs = NULL; gpu->num_perfcntrs = 0; - ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1); + ret = adreno_gpu_init(dev, pdev, adreno_gpu, config->info->funcs, 1); if (ret) goto fail; @@ -726,3 +703,28 @@ fail: return ERR_PTR(ret); } + +const struct adreno_gpu_funcs a4xx_gpu_funcs = { + .base = { + .get_param = adreno_get_param, + .set_param = adreno_set_param, + .hw_init = a4xx_hw_init, + .pm_suspend = a4xx_pm_suspend, + .pm_resume = a4xx_pm_resume, + .recover = a4xx_recover, + .submit = a4xx_submit, + .active_ring = adreno_active_ring, + .irq = a4xx_irq, + .destroy = a4xx_destroy, +#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP) + .show = adreno_show, +#endif + .gpu_busy = a4xx_gpu_busy, + .gpu_state_get = a4xx_gpu_state_get, + .gpu_state_put = adreno_gpu_state_put, + .create_vm = adreno_create_vm, + .get_rptr = a4xx_get_rptr, + }, + .init = a4xx_gpu_init, + .get_timestamp = a4xx_get_timestamp, +}; diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.h b/drivers/gpu/drm/msm/adreno/a4xx_gpu.h index a01448cba2ea..71b164439f62 100644 --- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.h @@ -20,4 +20,6 @@ struct a4xx_gpu { }; #define to_a4xx_gpu(x) container_of(x, struct a4xx_gpu, base) +extern const struct adreno_gpu_funcs a4xx_gpu_funcs; + #endif /* __A4XX_GPU_H__ */ diff --git a/drivers/gpu/drm/msm/adreno/a5xx_catalog.c b/drivers/gpu/drm/msm/adreno/a5xx_catalog.c index b48a636d8237..babd320f3b73 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_catalog.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_catalog.c @@ -7,6 +7,7 @@ */ #include "adreno_gpu.h" +#include "a5xx_gpu.h" static const struct adreno_info a5xx_gpus[] = { { @@ -21,7 +22,7 @@ static const struct adreno_info a5xx_gpus[] = { .inactive_period = DRM_MSM_INACTIVE_PERIOD, .quirks = ADRENO_QUIRK_TWO_PASS_USE_WFI | ADRENO_QUIRK_LMLOADKILL_DISABLE, - .init = a5xx_gpu_init, + .funcs = &a5xx_gpu_funcs, }, { .chip_ids = ADRENO_CHIP_IDS(0x05000600), .family = ADRENO_5XX, @@ -38,7 +39,7 @@ static const struct adreno_info a5xx_gpus[] = { .inactive_period = 250, .quirks = ADRENO_QUIRK_TWO_PASS_USE_WFI | ADRENO_QUIRK_LMLOADKILL_DISABLE, - .init = a5xx_gpu_init, + .funcs = &a5xx_gpu_funcs, .zapfw = "a506_zap.mdt", }, { .chip_ids = ADRENO_CHIP_IDS(0x05000800), @@ -55,7 +56,7 @@ static const struct adreno_info a5xx_gpus[] = { */ .inactive_period = 250, .quirks = ADRENO_QUIRK_LMLOADKILL_DISABLE, - .init = a5xx_gpu_init, + .funcs = &a5xx_gpu_funcs, .zapfw = "a508_zap.mdt", }, { .chip_ids = ADRENO_CHIP_IDS(0x05000900), @@ -72,7 +73,7 @@ static const struct adreno_info a5xx_gpus[] = { */ .inactive_period = 250, .quirks = ADRENO_QUIRK_LMLOADKILL_DISABLE, - .init = a5xx_gpu_init, + .funcs = &a5xx_gpu_funcs, /* Adreno 509 uses the same ZAP as 512 */ .zapfw = "a512_zap.mdt", }, { @@ -89,7 +90,7 @@ static const struct adreno_info a5xx_gpus[] = { * the GDSC which appears to make it grumpy */ .inactive_period = 250, - .init = a5xx_gpu_init, + .funcs = &a5xx_gpu_funcs, }, { .chip_ids = ADRENO_CHIP_IDS(0x05010200), .family = ADRENO_5XX, @@ -105,7 +106,7 @@ static const struct adreno_info a5xx_gpus[] = { */ .inactive_period = 250, .quirks = ADRENO_QUIRK_LMLOADKILL_DISABLE, - .init = a5xx_gpu_init, + .funcs = &a5xx_gpu_funcs, .zapfw = "a512_zap.mdt", }, { .chip_ids = ADRENO_CHIP_IDS( @@ -127,7 +128,7 @@ static const struct adreno_info a5xx_gpus[] = { .inactive_period = 250, .quirks = ADRENO_QUIRK_TWO_PASS_USE_WFI | ADRENO_QUIRK_FAULT_DETECT_MASK, - .init = a5xx_gpu_init, + .funcs = &a5xx_gpu_funcs, .zapfw = "a530_zap.mdt", }, { .chip_ids = ADRENO_CHIP_IDS(0x05040001), @@ -145,7 +146,7 @@ static const struct adreno_info a5xx_gpus[] = { */ .inactive_period = 250, .quirks = ADRENO_QUIRK_LMLOADKILL_DISABLE, - .init = a5xx_gpu_init, + .funcs = &a5xx_gpu_funcs, .zapfw = "a540_zap.mdt", } }; diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index 4a04dc43a8e6..56eaff2ee4e4 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -1691,34 +1691,6 @@ static uint32_t a5xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) return ring->memptrs->rptr = gpu_read(gpu, REG_A5XX_CP_RB_RPTR); } -static const struct adreno_gpu_funcs funcs = { - .base = { - .get_param = adreno_get_param, - .set_param = adreno_set_param, - .hw_init = a5xx_hw_init, - .ucode_load = a5xx_ucode_load, - .pm_suspend = a5xx_pm_suspend, - .pm_resume = a5xx_pm_resume, - .recover = a5xx_recover, - .submit = a5xx_submit, - .active_ring = a5xx_active_ring, - .irq = a5xx_irq, - .destroy = a5xx_destroy, -#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP) - .show = a5xx_show, -#endif -#if defined(CONFIG_DEBUG_FS) - .debugfs_init = a5xx_debugfs_init, -#endif - .gpu_busy = a5xx_gpu_busy, - .gpu_state_get = a5xx_gpu_state_get, - .gpu_state_put = a5xx_gpu_state_put, - .create_vm = adreno_create_vm, - .get_rptr = a5xx_get_rptr, - }, - .get_timestamp = a5xx_get_timestamp, -}; - static void check_speed_bin(struct device *dev) { struct nvmem_cell *cell; @@ -1751,7 +1723,7 @@ static void check_speed_bin(struct device *dev) devm_pm_opp_set_supported_hw(dev, &val, 1); } -struct msm_gpu *a5xx_gpu_init(struct drm_device *dev) +static struct msm_gpu *a5xx_gpu_init(struct drm_device *dev) { struct msm_drm_private *priv = dev->dev_private; struct platform_device *pdev = priv->gpu_pdev; @@ -1781,7 +1753,7 @@ struct msm_gpu *a5xx_gpu_init(struct drm_device *dev) if (config->info->revn == 510) nr_rings = 1; - ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, nr_rings); + ret = adreno_gpu_init(dev, pdev, adreno_gpu, config->info->funcs, nr_rings); if (ret) { a5xx_destroy(&(a5xx_gpu->base.base)); return ERR_PTR(ret); @@ -1806,3 +1778,32 @@ struct msm_gpu *a5xx_gpu_init(struct drm_device *dev) return gpu; } + +const struct adreno_gpu_funcs a5xx_gpu_funcs = { + .base = { + .get_param = adreno_get_param, + .set_param = adreno_set_param, + .hw_init = a5xx_hw_init, + .ucode_load = a5xx_ucode_load, + .pm_suspend = a5xx_pm_suspend, + .pm_resume = a5xx_pm_resume, + .recover = a5xx_recover, + .submit = a5xx_submit, + .active_ring = a5xx_active_ring, + .irq = a5xx_irq, + .destroy = a5xx_destroy, +#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP) + .show = a5xx_show, +#endif +#if defined(CONFIG_DEBUG_FS) + .debugfs_init = a5xx_debugfs_init, +#endif + .gpu_busy = a5xx_gpu_busy, + .gpu_state_get = a5xx_gpu_state_get, + .gpu_state_put = a5xx_gpu_state_put, + .create_vm = adreno_create_vm, + .get_rptr = a5xx_get_rptr, + }, + .init = a5xx_gpu_init, + .get_timestamp = a5xx_get_timestamp, +}; diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.h b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h index 9c0d701fe4b8..407bb950d350 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h @@ -133,6 +133,7 @@ struct a5xx_preempt_record { */ #define A5XX_PREEMPT_COUNTER_SIZE (16 * 4) +extern const struct adreno_gpu_funcs a5xx_gpu_funcs; int a5xx_power_init(struct msm_gpu *gpu); void a5xx_gpmu_ucode_init(struct msm_gpu *gpu); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c index 44df6410bce1..29107b362346 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c @@ -672,6 +672,14 @@ static const u32 a690_protect_regs[] = { }; DECLARE_ADRENO_PROTECT(a690_protect, 48); +static const struct adreno_reglist a640_gbif[] = { + { REG_A6XX_GBIF_QSB_SIDE0, 0x00071620 }, + { REG_A6XX_GBIF_QSB_SIDE1, 0x00071620 }, + { REG_A6XX_GBIF_QSB_SIDE2, 0x00071620 }, + { REG_A6XX_GBIF_QSB_SIDE3, 0x00071620 }, + { }, +}; + static const struct adreno_info a6xx_gpus[] = { { .chip_ids = ADRENO_CHIP_IDS(0x06010000), @@ -683,11 +691,12 @@ static const struct adreno_info a6xx_gpus[] = { .gmem = (SZ_128K + SZ_4K), .quirks = ADRENO_QUIRK_4GB_VA, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a6xx_gpu_init, + .funcs = &a6xx_gmuwrapper_funcs, .zapfw = "a610_zap.mdt", .a6xx = &(const struct a6xx_info) { .hwcg = a612_hwcg, .protect = &a630_protect, + .gbif_cx = a640_gbif, .gmu_cgc_mode = 0x00020202, .prim_fifo_threshold = 0x00080000, }, @@ -706,6 +715,22 @@ static const struct adreno_info a6xx_gpus[] = { { 127, 4 }, ), }, { + .chip_ids = ADRENO_CHIP_IDS(0x06010200), + .family = ADRENO_6XX_GEN1, + .fw = { + [ADRENO_FW_SQE] = "a630_sqe.fw", + [ADRENO_FW_GMU] = "a612_rgmu.bin", + }, + .gmem = (SZ_128K + SZ_4K), + .inactive_period = DRM_MSM_INACTIVE_PERIOD, + .funcs = &a6xx_gmuwrapper_funcs, + .a6xx = &(const struct a6xx_info) { + .hwcg = a612_hwcg, + .protect = &a630_protect, + .gmu_cgc_mode = 0x00000022, + .prim_fifo_threshold = 0x00080000, + }, + }, { .chip_ids = ADRENO_CHIP_IDS(0x06010500), .family = ADRENO_6XX_GEN1, .revn = 615, @@ -716,7 +741,7 @@ static const struct adreno_info a6xx_gpus[] = { .gmem = SZ_512K, .quirks = ADRENO_QUIRK_4GB_VA, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .zapfw = "a615_zap.mdt", .a6xx = &(const struct a6xx_info) { .hwcg = a615_hwcg, @@ -747,7 +772,7 @@ static const struct adreno_info a6xx_gpus[] = { .inactive_period = DRM_MSM_INACTIVE_PERIOD, .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_4GB_VA, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .zapfw = "a615_zap.mbn", .a6xx = &(const struct a6xx_info) { .hwcg = a615_hwcg, @@ -774,7 +799,7 @@ static const struct adreno_info a6xx_gpus[] = { .inactive_period = DRM_MSM_INACTIVE_PERIOD, .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_4GB_VA, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .a6xx = &(const struct a6xx_info) { .protect = &a630_protect, .gmu_cgc_mode = 0x00000222, @@ -797,7 +822,7 @@ static const struct adreno_info a6xx_gpus[] = { .gmem = SZ_512K, .quirks = ADRENO_QUIRK_4GB_VA, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .zapfw = "a615_zap.mdt", .a6xx = &(const struct a6xx_info) { .hwcg = a615_hwcg, @@ -822,7 +847,7 @@ static const struct adreno_info a6xx_gpus[] = { .gmem = SZ_512K, .quirks = ADRENO_QUIRK_4GB_VA, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .zapfw = "a615_zap.mdt", .a6xx = &(const struct a6xx_info) { .hwcg = a615_hwcg, @@ -847,7 +872,7 @@ static const struct adreno_info a6xx_gpus[] = { .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_4GB_VA, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .zapfw = "a615_zap.mdt", .a6xx = &(const struct a6xx_info) { .hwcg = a615_hwcg, @@ -873,11 +898,12 @@ static const struct adreno_info a6xx_gpus[] = { .inactive_period = DRM_MSM_INACTIVE_PERIOD, .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_HAS_HW_APRIV, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .zapfw = "a620_zap.mbn", .a6xx = &(const struct a6xx_info) { .hwcg = a620_hwcg, .protect = &a650_protect, + .gbif_cx = a640_gbif, .gmu_cgc_mode = 0x00020200, .prim_fifo_threshold = 0x00010000, }, @@ -896,10 +922,11 @@ static const struct adreno_info a6xx_gpus[] = { .inactive_period = DRM_MSM_INACTIVE_PERIOD, .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_HAS_HW_APRIV, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .a6xx = &(const struct a6xx_info) { .hwcg = a690_hwcg, .protect = &a650_protect, + .gbif_cx = a640_gbif, .gmu_cgc_mode = 0x00020200, .prim_fifo_threshold = 0x00010000, .bcms = (const struct a6xx_bcm[]) { @@ -933,7 +960,7 @@ static const struct adreno_info a6xx_gpus[] = { .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_4GB_VA, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .zapfw = "a630_zap.mdt", .a6xx = &(const struct a6xx_info) { .hwcg = a630_hwcg, @@ -953,7 +980,7 @@ static const struct adreno_info a6xx_gpus[] = { .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_4GB_VA, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .zapfw = "a640_zap.mdt", .a6xx = &(const struct a6xx_info) { .hwcg = a640_hwcg, @@ -977,11 +1004,12 @@ static const struct adreno_info a6xx_gpus[] = { .inactive_period = DRM_MSM_INACTIVE_PERIOD, .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_HAS_HW_APRIV, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .zapfw = "a650_zap.mdt", .a6xx = &(const struct a6xx_info) { .hwcg = a650_hwcg, .protect = &a650_protect, + .gbif_cx = a640_gbif, .gmu_cgc_mode = 0x00020202, .prim_fifo_threshold = 0x00300200, }, @@ -1003,11 +1031,12 @@ static const struct adreno_info a6xx_gpus[] = { .inactive_period = DRM_MSM_INACTIVE_PERIOD, .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_HAS_HW_APRIV, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .zapfw = "a660_zap.mdt", .a6xx = &(const struct a6xx_info) { .hwcg = a660_hwcg, .protect = &a660_protect, + .gbif_cx = a640_gbif, .gmu_cgc_mode = 0x00020000, .prim_fifo_threshold = 0x00300200, }, @@ -1022,10 +1051,11 @@ static const struct adreno_info a6xx_gpus[] = { .inactive_period = DRM_MSM_INACTIVE_PERIOD, .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_HAS_HW_APRIV, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .a6xx = &(const struct a6xx_info) { .hwcg = a690_hwcg, .protect = &a660_protect, + .gbif_cx = a640_gbif, .gmu_cgc_mode = 0x00020200, .prim_fifo_threshold = 0x00300200, }, @@ -1045,11 +1075,12 @@ static const struct adreno_info a6xx_gpus[] = { .inactive_period = DRM_MSM_INACTIVE_PERIOD, .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_HAS_HW_APRIV, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .zapfw = "a660_zap.mbn", .a6xx = &(const struct a6xx_info) { .hwcg = a660_hwcg, .protect = &a660_protect, + .gbif_cx = a640_gbif, .gmu_cgc_mode = 0x00020202, .prim_fifo_threshold = 0x00200200, }, @@ -1072,7 +1103,7 @@ static const struct adreno_info a6xx_gpus[] = { .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_4GB_VA, .inactive_period = DRM_MSM_INACTIVE_PERIOD, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .zapfw = "a640_zap.mdt", .a6xx = &(const struct a6xx_info) { .hwcg = a640_hwcg, @@ -1091,11 +1122,12 @@ static const struct adreno_info a6xx_gpus[] = { .inactive_period = DRM_MSM_INACTIVE_PERIOD, .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_HAS_HW_APRIV, - .init = a6xx_gpu_init, + .funcs = &a6xx_gpu_funcs, .zapfw = "a690_zap.mdt", .a6xx = &(const struct a6xx_info) { .hwcg = a690_hwcg, .protect = &a690_protect, + .gbif_cx = a640_gbif, .gmu_cgc_mode = 0x00020200, .prim_fifo_threshold = 0x00800200, }, @@ -1426,11 +1458,12 @@ static const struct adreno_info a7xx_gpus[] = { .gmem = SZ_128K, .inactive_period = DRM_MSM_INACTIVE_PERIOD, .quirks = ADRENO_QUIRK_HAS_HW_APRIV, - .init = a6xx_gpu_init, + .funcs = &a6xx_gmuwrapper_funcs, .zapfw = "a702_zap.mbn", .a6xx = &(const struct a6xx_info) { .hwcg = a702_hwcg, .protect = &a650_protect, + .gbif_cx = a640_gbif, .gmu_cgc_mode = 0x00020202, .prim_fifo_threshold = 0x0000c000, }, @@ -1452,12 +1485,13 @@ static const struct adreno_info a7xx_gpus[] = { .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_HAS_HW_APRIV | ADRENO_QUIRK_PREEMPTION, - .init = a6xx_gpu_init, + .funcs = &a7xx_gpu_funcs, .zapfw = "a730_zap.mdt", .a6xx = &(const struct a6xx_info) { .hwcg = a730_hwcg, .protect = &a730_protect, .pwrup_reglist = &a7xx_pwrup_reglist, + .gbif_cx = a640_gbif, .gmu_cgc_mode = 0x00020000, }, .preempt_record_size = 2860 * SZ_1K, @@ -1473,12 +1507,13 @@ static const struct adreno_info a7xx_gpus[] = { .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_HAS_HW_APRIV | ADRENO_QUIRK_PREEMPTION, - .init = a6xx_gpu_init, + .funcs = &a7xx_gpu_funcs, .zapfw = "a740_zap.mdt", .a6xx = &(const struct a6xx_info) { .hwcg = a740_hwcg, .protect = &a730_protect, .pwrup_reglist = &a7xx_pwrup_reglist, + .gbif_cx = a640_gbif, .gmu_chipid = 0x7020100, .gmu_cgc_mode = 0x00020202, .bcms = (const struct a6xx_bcm[]) { @@ -1507,12 +1542,13 @@ static const struct adreno_info a7xx_gpus[] = { ADRENO_QUIRK_HAS_HW_APRIV | ADRENO_QUIRK_PREEMPTION | ADRENO_QUIRK_IFPC, - .init = a6xx_gpu_init, + .funcs = &a7xx_gpu_funcs, .a6xx = &(const struct a6xx_info) { .hwcg = a740_hwcg, .protect = &a730_protect, .pwrup_reglist = &a7xx_pwrup_reglist, .ifpc_reglist = &a750_ifpc_reglist, + .gbif_cx = a640_gbif, .gmu_chipid = 0x7050001, .gmu_cgc_mode = 0x00020202, .bcms = (const struct a6xx_bcm[]) { @@ -1548,12 +1584,13 @@ static const struct adreno_info a7xx_gpus[] = { ADRENO_QUIRK_HAS_HW_APRIV | ADRENO_QUIRK_PREEMPTION | ADRENO_QUIRK_IFPC, - .init = a6xx_gpu_init, + .funcs = &a7xx_gpu_funcs, .zapfw = "gen70900_zap.mbn", .a6xx = &(const struct a6xx_info) { .protect = &a730_protect, .pwrup_reglist = &a7xx_pwrup_reglist, .ifpc_reglist = &a750_ifpc_reglist, + .gbif_cx = a640_gbif, .gmu_chipid = 0x7090100, .gmu_cgc_mode = 0x00020202, .bcms = (const struct a6xx_bcm[]) { @@ -1581,11 +1618,12 @@ static const struct adreno_info a7xx_gpus[] = { .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | ADRENO_QUIRK_HAS_HW_APRIV | ADRENO_QUIRK_PREEMPTION, - .init = a6xx_gpu_init, + .funcs = &a7xx_gpu_funcs, .a6xx = &(const struct a6xx_info) { .hwcg = a740_hwcg, .protect = &a730_protect, .pwrup_reglist = &a7xx_pwrup_reglist, + .gbif_cx = a640_gbif, .gmu_chipid = 0x70f0000, .gmu_cgc_mode = 0x00020222, .bcms = (const struct a6xx_bcm[]) { @@ -1612,6 +1650,306 @@ static const struct adreno_info a7xx_gpus[] = { }; DECLARE_ADRENO_GPULIST(a7xx); +static const struct adreno_reglist_pipe x285_nonctxt_regs[] = { + { REG_A8XX_CP_SMMU_STREAM_ID_LPAC, 0x00000101, BIT(PIPE_NONE) }, + { REG_A8XX_GRAS_DBG_ECO_CNTL, 0x00000800, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_GRAS_TSEFE_DBG_ECO_CNTL, 0x00200000, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A6XX_PC_AUTO_VERTEX_STRIDE, 0x00000001, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_PC_VIS_STREAM_CNTL, 0x10010000, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_PC_CONTEXT_SWITCH_STABILIZE_CNTL_1, 0x00000002, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_PC_CHICKEN_BITS_1, 0x00000003, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_PC_CHICKEN_BITS_2, 0x00000200, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_PC_CHICKEN_BITS_3, 0x00500000, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_PC_CHICKEN_BITS_4, 0x00500050, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_RB_GC_GMEM_PROTECT, 0x15000000, BIT(PIPE_BR) }, + { REG_A8XX_RB_RESOLVE_PREFETCH_CNTL, 0x00000007, BIT(PIPE_BR) }, + { REG_A8XX_RB_CMP_DBG_ECO_CNTL, 0x00004000, BIT(PIPE_BR) }, + { REG_A8XX_RBBM_NC_MODE_CNTL, 0x00000001, BIT(PIPE_NONE) }, + { REG_A8XX_RBBM_SLICE_NC_MODE_CNTL, 0x00000001, BIT(PIPE_NONE) }, + { REG_A8XX_RBBM_WAIT_IDLE_CLOCKS_CNTL, 0x00000030, BIT(PIPE_NONE) }, + { REG_A8XX_RBBM_WAIT_IDLE_CLOCKS_CNTL2, 0x00000030, BIT(PIPE_NONE) }, + { REG_A8XX_RBBM_INTERFACE_HANG_INT_CNTL, 0x0fffffff, BIT(PIPE_NONE) }, + { REG_A8XX_RBBM_GBIF_CLIENT_QOS_CNTL, 0x22122212, BIT(PIPE_NONE) }, + { REG_A8XX_RBBM_CGC_P2S_CNTL, 0x00000040, BIT(PIPE_NONE) }, + { REG_A7XX_SP_CHICKEN_BITS_2, 0x00820800, BIT(PIPE_NONE) }, + { REG_A7XX_SP_CHICKEN_BITS_3, 0x00300000, BIT(PIPE_NONE) }, + { REG_A6XX_SP_PERFCTR_SHADER_MASK, 0x0000003f, BIT(PIPE_NONE) }, + /* Disable CS dead batch merge */ + { REG_A7XX_SP_HLSQ_DBG_ECO_CNTL_2, BIT(31), BIT(PIPE_NONE) }, + { REG_A7XX_SP_HLSQ_TIMEOUT_THRESHOLD_DP, 0x00000080, BIT(PIPE_NONE) }, + { REG_A7XX_SP_READ_SEL, 0x0001ff00, BIT(PIPE_NONE) }, + { REG_A6XX_TPL1_DBG_ECO_CNTL, 0x10000000, BIT(PIPE_NONE) }, + /* BIT(26): Disable final clamp for bicubic filtering */ + { REG_A6XX_TPL1_DBG_ECO_CNTL1, 0x00000720, BIT(PIPE_NONE) }, + { REG_A6XX_UCHE_MODE_CNTL, 0x80080000, BIT(PIPE_NONE) }, + { REG_A8XX_UCHE_CCHE_MODE_CNTL, 0x00001000, BIT(PIPE_NONE) }, + { REG_A8XX_UCHE_CCHE_CACHE_WAYS, 0x00000800, BIT(PIPE_NONE) }, + { REG_A8XX_UCHE_GBIF_GX_CONFIG, 0x010240e0, BIT(PIPE_NONE) }, + { REG_A8XX_UCHE_VARB_IDLE_TIMEOUT, 0x00000020, BIT(PIPE_NONE) }, + { REG_A7XX_VFD_DBG_ECO_CNTL, 0x00008000, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_VFD_CB_BV_THRESHOLD, 0x00500050, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_VFD_CB_BR_THRESHOLD, 0x00600060, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_VFD_CB_BUSY_REQ_CNT, 0x00200020, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_VFD_CB_LP_REQ_CNT, 0x00000020, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_VPC_FLATSHADE_MODE_CNTL, 0x00000001, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { }, +}; + +static const u32 x285_protect_regs[] = { + A6XX_PROTECT_RDONLY(0x00008, 0x039b), + A6XX_PROTECT_RDONLY(0x003b4, 0x008b), + A6XX_PROTECT_NORDWR(0x00440, 0x001f), + A6XX_PROTECT_RDONLY(0x00580, 0x005f), + A6XX_PROTECT_NORDWR(0x005e0, 0x011f), + A6XX_PROTECT_RDONLY(0x0074a, 0x0005), + A6XX_PROTECT_RDONLY(0x00759, 0x0026), + A6XX_PROTECT_RDONLY(0x00789, 0x0000), + A6XX_PROTECT_RDONLY(0x0078c, 0x0013), + A6XX_PROTECT_NORDWR(0x00800, 0x0029), + A6XX_PROTECT_NORDWR(0x0082c, 0x0000), + A6XX_PROTECT_NORDWR(0x00837, 0x00af), + A6XX_PROTECT_RDONLY(0x008e7, 0x00c9), + A6XX_PROTECT_NORDWR(0x008ec, 0x00c3), + A6XX_PROTECT_NORDWR(0x009b1, 0x0250), + A6XX_PROTECT_RDONLY(0x00ce0, 0x0001), + A6XX_PROTECT_RDONLY(0x00df0, 0x0000), + A6XX_PROTECT_NORDWR(0x00df1, 0x0000), + A6XX_PROTECT_NORDWR(0x00e01, 0x0000), + A6XX_PROTECT_NORDWR(0x00e03, 0x1fff), + A6XX_PROTECT_NORDWR(0x03c00, 0x00c5), + A6XX_PROTECT_RDONLY(0x03cc6, 0x0039), + A6XX_PROTECT_NORDWR(0x03d00, 0x1fff), + A6XX_PROTECT_NORDWR(0x08600, 0x01ff), + A6XX_PROTECT_NORDWR(0x08e00, 0x00ff), + A6XX_PROTECT_RDONLY(0x08f00, 0x0000), + A6XX_PROTECT_NORDWR(0x08f01, 0x01be), + A6XX_PROTECT_NORDWR(0x09600, 0x01ff), + A6XX_PROTECT_RDONLY(0x0981a, 0x02e5), + A6XX_PROTECT_NORDWR(0x09e00, 0x01ff), + A6XX_PROTECT_NORDWR(0x0a600, 0x01ff), + A6XX_PROTECT_NORDWR(0x0a82e, 0x0000), + A6XX_PROTECT_NORDWR(0x0ae00, 0x0006), + A6XX_PROTECT_NORDWR(0x0ae08, 0x0006), + A6XX_PROTECT_NORDWR(0x0ae10, 0x00bf), + A6XX_PROTECT_RDONLY(0x0aed0, 0x002f), + A6XX_PROTECT_NORDWR(0x0af00, 0x027f), + A6XX_PROTECT_NORDWR(0x0b600, 0x1fff), + A6XX_PROTECT_NORDWR(0x0dc00, 0x1fff), + A6XX_PROTECT_RDONLY(0x0fc00, 0x1fff), + A6XX_PROTECT_NORDWR(0x18400, 0x003f), + A6XX_PROTECT_RDONLY(0x18440, 0x013f), + A6XX_PROTECT_NORDWR(0x18580, 0x1fff), + A6XX_PROTECT_NORDWR(0x1b400, 0x1fff), + A6XX_PROTECT_NORDWR(0x1f400, 0x0477), + A6XX_PROTECT_RDONLY(0x1f878, 0x0507), + A6XX_PROTECT_NORDWR(0x1f930, 0x0329), + A6XX_PROTECT_NORDWR(0x1fd80, 0x1fff), + A6XX_PROTECT_NORDWR(0x27800, 0x007f), + A6XX_PROTECT_RDONLY(0x27880, 0x0385), + A6XX_PROTECT_NORDWR(0x27882, 0x000a), + A6XX_PROTECT_NORDWR(0x27c06, 0x0000), +}; + +DECLARE_ADRENO_PROTECT(x285_protect, 64); + +static const struct adreno_reglist_pipe a840_nonctxt_regs[] = { + { REG_A8XX_CP_SMMU_STREAM_ID_LPAC, 0x00000101, BIT(PIPE_NONE) }, + { REG_A8XX_GRAS_DBG_ECO_CNTL, 0x00000800, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_GRAS_TSEFE_DBG_ECO_CNTL, 0x00200000, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A6XX_PC_AUTO_VERTEX_STRIDE, 0x00000001, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_PC_VIS_STREAM_CNTL, 0x10010000, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_PC_CONTEXT_SWITCH_STABILIZE_CNTL_1, 0x00000002, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_PC_CHICKEN_BITS_1, 0x00000003, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_PC_CHICKEN_BITS_2, 0x00000200, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_PC_CHICKEN_BITS_3, 0x00500000, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_PC_CHICKEN_BITS_4, 0x00500050, BIT(PIPE_BV) | BIT(PIPE_BR) }, + /* Disable Dead Draw Merge scheme on RB-HLSQ */ + { REG_A6XX_RB_RBP_CNTL, BIT(5), BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A7XX_RB_CCU_CNTL, 0x00000068, BIT(PIPE_BR) }, + /* Partially enable perf clear, Disable DINT to c/z be data forwarding */ + { REG_A7XX_RB_CCU_DBG_ECO_CNTL, 0x00002200, BIT(PIPE_BR) }, + { REG_A8XX_RB_GC_GMEM_PROTECT, 0x12000000, BIT(PIPE_BR) }, + { REG_A8XX_RB_RESOLVE_PREFETCH_CNTL, 0x00000007, BIT(PIPE_BR) }, + { REG_A8XX_RB_CMP_DBG_ECO_CNTL, 0x00004000, BIT(PIPE_BR) }, + { REG_A8XX_RBBM_NC_MODE_CNTL, 0x00000001, BIT(PIPE_NONE) }, + { REG_A8XX_RBBM_SLICE_NC_MODE_CNTL, 0x00000001, BIT(PIPE_NONE) }, + { REG_A8XX_RBBM_POWER_UP_RESET_SW_OVERRIDE, 0x70809060, BIT(PIPE_NONE) }, + { REG_A8XX_RBBM_POWER_UP_RESET_SW_BV_OVERRIDE, 0x30000000, BIT(PIPE_NONE) }, + { REG_A8XX_RBBM_WAIT_IDLE_CLOCKS_CNTL, 0x00000030, BIT(PIPE_NONE) }, + { REG_A8XX_RBBM_WAIT_IDLE_CLOCKS_CNTL2, 0x00000030, BIT(PIPE_NONE) }, + { REG_A8XX_RBBM_INTERFACE_HANG_INT_CNTL, 0x0fffffff, BIT(PIPE_NONE) }, + { REG_A8XX_RBBM_GBIF_CLIENT_QOS_CNTL, 0x22122212, BIT(PIPE_NONE) }, + { REG_A8XX_RBBM_CGC_P2S_CNTL, 0x00000040, BIT(PIPE_NONE) }, + /* Disable mode_switch optimization in UMAS */ + { REG_A6XX_SP_CHICKEN_BITS, BIT(24) | BIT(26), BIT(PIPE_NONE) }, + /* Disable LPAC large-LM mode */ + { REG_A8XX_SP_SS_CHICKEN_BITS_0, BIT(3), BIT(PIPE_NONE) }, + /* Disable PS out of order retire */ + { REG_A7XX_SP_CHICKEN_BITS_2, 0x00c21800, BIT(PIPE_NONE) }, + { REG_A7XX_SP_CHICKEN_BITS_3, 0x00300000, BIT(PIPE_NONE) }, + /* Disable SP2TP info attribute */ + { REG_A8XX_SP_CHICKEN_BITS_4, 0x00000002, BIT(PIPE_NONE) }, + { REG_A6XX_SP_PERFCTR_SHADER_MASK, 0x0000003f, BIT(PIPE_NONE) }, + { REG_A7XX_SP_HLSQ_DBG_ECO_CNTL, BIT(14), BIT(PIPE_NONE) }, + /* Ignore HLSQ shared constant feedback from SP */ + { REG_A7XX_SP_HLSQ_DBG_ECO_CNTL_1, BIT(17), BIT(PIPE_NONE) }, + /* Disable CS dead batch merge */ + { REG_A7XX_SP_HLSQ_DBG_ECO_CNTL_2, BIT(24), BIT(PIPE_NONE) }, + { REG_A8XX_SP_HLSQ_DBG_ECO_CNTL_3, BIT(7), BIT(PIPE_NONE) }, + { REG_A7XX_SP_HLSQ_TIMEOUT_THRESHOLD_DP, 0x00000080, BIT(PIPE_NONE) }, + { REG_A7XX_SP_READ_SEL, 0x0001ff00, BIT(PIPE_NONE) }, + { REG_A6XX_TPL1_DBG_ECO_CNTL, 0x10100000, BIT(PIPE_NONE) }, + /* BIT(26): Disable final clamp for bicubic filtering */ + { REG_A6XX_TPL1_DBG_ECO_CNTL1, 0x04000720, BIT(PIPE_NONE) }, + { REG_A6XX_UCHE_MODE_CNTL, 0x80080000, BIT(PIPE_NONE) }, + { REG_A8XX_UCHE_CCHE_MODE_CNTL, 0x00001000, BIT(PIPE_NONE) }, + { REG_A8XX_UCHE_CCHE_CACHE_WAYS, 0x00000800, BIT(PIPE_NONE) }, + { REG_A8XX_UCHE_GBIF_GX_CONFIG, 0x010240e0, BIT(PIPE_NONE) }, + { REG_A8XX_UCHE_VARB_IDLE_TIMEOUT, 0x00000020, BIT(PIPE_NONE) }, + { REG_A7XX_VFD_DBG_ECO_CNTL, 0x00008000, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_VFD_CB_BV_THRESHOLD, 0x00500050, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_VFD_CB_BR_THRESHOLD, 0x00600060, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_VFD_CB_BUSY_REQ_CNT, 0x00200020, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_VFD_CB_LP_REQ_CNT, 0x00000020, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { REG_A8XX_VPC_FLATSHADE_MODE_CNTL, 0x00000001, BIT(PIPE_BV) | BIT(PIPE_BR) }, + { }, +}; + +static const u32 a840_protect_regs[] = { + A6XX_PROTECT_RDONLY(0x00008, 0x039b), + A6XX_PROTECT_RDONLY(0x003b4, 0x008b), + A6XX_PROTECT_NORDWR(0x00440, 0x001f), + A6XX_PROTECT_RDONLY(0x00580, 0x005f), + A6XX_PROTECT_NORDWR(0x005e0, 0x011f), + A6XX_PROTECT_RDONLY(0x0074a, 0x0005), + A6XX_PROTECT_RDONLY(0x00759, 0x001b), + A6XX_PROTECT_NORDWR(0x00775, 0x000a), + A6XX_PROTECT_RDONLY(0x00789, 0x0000), + A6XX_PROTECT_RDONLY(0x0078c, 0x0013), + A6XX_PROTECT_NORDWR(0x00800, 0x0029), + A6XX_PROTECT_NORDWR(0x00837, 0x00af), + A6XX_PROTECT_RDONLY(0x008e7, 0x00c9), + A6XX_PROTECT_NORDWR(0x008ec, 0x00c3), + A6XX_PROTECT_NORDWR(0x009b1, 0x0250), + A6XX_PROTECT_NORDWR(0x00c07, 0x0008), + A6XX_PROTECT_RDONLY(0x00ce0, 0x0001), + A6XX_PROTECT_RDONLY(0x00df0, 0x0000), + A6XX_PROTECT_NORDWR(0x00df1, 0x0000), + A6XX_PROTECT_NORDWR(0x00e01, 0x0000), + A6XX_PROTECT_NORDWR(0x00e03, 0x1fff), + A6XX_PROTECT_NORDWR(0x03c00, 0x00c5), + A6XX_PROTECT_RDONLY(0x03cc6, 0x0039), + A6XX_PROTECT_NORDWR(0x03d00, 0x1fff), + A6XX_PROTECT_NORDWR(0x08600, 0x01ff), + A6XX_PROTECT_NORDWR(0x08e00, 0x00ff), + A6XX_PROTECT_RDONLY(0x08f00, 0x0000), + A6XX_PROTECT_NORDWR(0x08f01, 0x01be), + A6XX_PROTECT_NORDWR(0x09600, 0x01ff), + A6XX_PROTECT_RDONLY(0x0981a, 0x02e5), + A6XX_PROTECT_NORDWR(0x09e00, 0x01ff), + A6XX_PROTECT_NORDWR(0x0a600, 0x01ff), + A6XX_PROTECT_NORDWR(0x0a82e, 0x0000), + A6XX_PROTECT_NORDWR(0x0ae00, 0x0000), + A6XX_PROTECT_NORDWR(0x0ae02, 0x0004), + A6XX_PROTECT_NORDWR(0x0ae08, 0x0006), + A6XX_PROTECT_NORDWR(0x0ae10, 0x00bf), + A6XX_PROTECT_RDONLY(0x0aed0, 0x002f), + A6XX_PROTECT_NORDWR(0x0af00, 0x027f), + A6XX_PROTECT_NORDWR(0x0b600, 0x1fff), + A6XX_PROTECT_NORDWR(0x0dc00, 0x1fff), + A6XX_PROTECT_RDONLY(0x0fc00, 0x1fff), + A6XX_PROTECT_NORDWR(0x18400, 0x003f), + A6XX_PROTECT_RDONLY(0x18440, 0x013f), + A6XX_PROTECT_NORDWR(0x18580, 0x1fff), + A6XX_PROTECT_NORDWR(0x1b400, 0x1fff), + A6XX_PROTECT_NORDWR(0x1f400, 0x0477), + A6XX_PROTECT_RDONLY(0x1f878, 0x0507), + A6XX_PROTECT_NORDWR(0x1f930, 0x0329), + A6XX_PROTECT_NORDWR(0x1fd80, 0x1fff), + A6XX_PROTECT_NORDWR(0x27800, 0x007f), + A6XX_PROTECT_RDONLY(0x27880, 0x0385), + A6XX_PROTECT_NORDWR(0x27882, 0x0009), + A6XX_PROTECT_NORDWR(0x27c06, 0x0000), +}; +DECLARE_ADRENO_PROTECT(a840_protect, 15); + +static const struct adreno_reglist a840_gbif[] = { + { REG_A6XX_GBIF_QSB_SIDE0, 0x00071e20 }, + { REG_A6XX_GBIF_QSB_SIDE1, 0x00071e20 }, + { REG_A6XX_GBIF_QSB_SIDE2, 0x00071e20 }, + { REG_A6XX_GBIF_QSB_SIDE3, 0x00071e20 }, + { REG_A8XX_GBIF_CX_CONFIG, 0x20023000 }, + { }, +}; + +static const struct adreno_info a8xx_gpus[] = { + { + .chip_ids = ADRENO_CHIP_IDS(0x44070001), + .family = ADRENO_8XX_GEN2, + .fw = { + [ADRENO_FW_SQE] = "gen80100_sqe.fw", + [ADRENO_FW_GMU] = "gen80100_gmu.bin", + }, + .gmem = 21 * SZ_1M, + .inactive_period = DRM_MSM_INACTIVE_PERIOD, + .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | + ADRENO_QUIRK_HAS_HW_APRIV, + .funcs = &a8xx_gpu_funcs, + .a6xx = &(const struct a6xx_info) { + .protect = &x285_protect, + .nonctxt_reglist = x285_nonctxt_regs, + .gbif_cx = a840_gbif, + .max_slices = 4, + .gmu_chipid = 0x8010100, + .bcms = (const struct a6xx_bcm[]) { + { .name = "SH0", .buswidth = 16 }, + { .name = "MC0", .buswidth = 4 }, + { + .name = "ACV", + .fixed = true, + .perfmode = BIT(2), + .perfmode_bw = 16500000, + }, + { /* sentinel */ }, + }, + }, + }, { + .chip_ids = ADRENO_CHIP_IDS(0x44050a01), + .family = ADRENO_8XX_GEN2, + .fw = { + [ADRENO_FW_SQE] = "gen80200_sqe.fw", + [ADRENO_FW_GMU] = "gen80200_gmu.bin", + [ADRENO_FW_AQE] = "gen80200_aqe.fw", + }, + .gmem = 18 * SZ_1M, + .inactive_period = DRM_MSM_INACTIVE_PERIOD, + .quirks = ADRENO_QUIRK_HAS_CACHED_COHERENT | + ADRENO_QUIRK_HAS_HW_APRIV, + .funcs = &a8xx_gpu_funcs, + .a6xx = &(const struct a6xx_info) { + .protect = &a840_protect, + .nonctxt_reglist = a840_nonctxt_regs, + .gbif_cx = a840_gbif, + .max_slices = 3, + .gmu_chipid = 0x8020100, + .bcms = (const struct a6xx_bcm[]) { + { .name = "SH0", .buswidth = 16 }, + { .name = "MC0", .buswidth = 4 }, + { + .name = "ACV", + .fixed = true, + .perfmode = BIT(2), + .perfmode_bw = 10687500, + }, + { /* sentinel */ }, + }, + }, + .preempt_record_size = 19708 * SZ_1K, + } +}; + +DECLARE_ADRENO_GPULIST(a8xx); + static inline __always_unused void __build_asserts(void) { BUILD_BUG_ON(a630_protect.count > a630_protect.count_max); @@ -1619,4 +1957,5 @@ static inline __always_unused void __build_asserts(void) BUILD_BUG_ON(a660_protect.count > a660_protect.count_max); BUILD_BUG_ON(a690_protect.count > a690_protect.count_max); BUILD_BUG_ON(a730_protect.count > a730_protect.count_max); + BUILD_BUG_ON(a840_protect.count > a840_protect.count_max); } diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index fc62fef2fed8..5903cd891b49 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -224,14 +224,19 @@ unsigned long a6xx_gmu_get_freq(struct msm_gpu *gpu) static bool a6xx_gmu_check_idle_level(struct a6xx_gmu *gmu) { - u32 val; + struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); + struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; int local = gmu->idle_level; + u32 val; /* SPTP and IFPC both report as IFPC */ if (gmu->idle_level == GMU_IDLE_STATE_SPTP) local = GMU_IDLE_STATE_IFPC; - val = gmu_read(gmu, REG_A6XX_GPU_GMU_CX_GMU_RPMH_POWER_STATE); + if (adreno_is_a8xx(adreno_gpu)) + val = gmu_read(gmu, REG_A8XX_GPU_GMU_CX_GMU_RPMH_POWER_STATE); + else + val = gmu_read(gmu, REG_A6XX_GPU_GMU_CX_GMU_RPMH_POWER_STATE); if (val == local) { if (gmu->idle_level != GMU_IDLE_STATE_IFPC || @@ -269,7 +274,9 @@ static int a6xx_gmu_start(struct a6xx_gmu *gmu) /* Set the log wptr index * note: downstream saves the value in poweroff and restores it here */ - if (adreno_is_a7xx(adreno_gpu)) + if (adreno_is_a8xx(adreno_gpu)) + gmu_write(gmu, REG_A8XX_GMU_GENERAL_9, 0); + else if (adreno_is_a7xx(adreno_gpu)) gmu_write(gmu, REG_A7XX_GMU_GENERAL_9, 0); else gmu_write(gmu, REG_A6XX_GPU_GMU_CX_GMU_PWR_COL_CP_RESP, 0); @@ -350,12 +357,18 @@ static const struct a6xx_gmu_oob_bits a6xx_gmu_oob_bits[] = { /* Trigger a OOB (out of band) request to the GMU */ int a6xx_gmu_set_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state) { + struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); + struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; int ret; u32 val; int request, ack; WARN_ON_ONCE(!mutex_is_locked(&gmu->lock)); + /* Skip OOB calls since RGMU is not enabled */ + if (adreno_has_rgmu(adreno_gpu)) + return 0; + if (state >= ARRAY_SIZE(a6xx_gmu_oob_bits)) return -EINVAL; @@ -376,9 +389,23 @@ int a6xx_gmu_set_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state) /* Trigger the equested OOB operation */ gmu_write(gmu, REG_A6XX_GMU_HOST2GMU_INTR_SET, 1 << request); - /* Wait for the acknowledge interrupt */ - ret = gmu_poll_timeout(gmu, REG_A6XX_GMU_GMU2HOST_INTR_INFO, val, - val & (1 << ack), 100, 10000); + do { + /* Wait for the acknowledge interrupt */ + ret = gmu_poll_timeout(gmu, REG_A6XX_GMU_GMU2HOST_INTR_INFO, val, + val & (1 << ack), 100, 10000); + + if (!ret) + break; + + if (completion_done(&a6xx_gpu->base.fault_coredump_done)) + break; + + /* We may timeout because the GMU is temporarily wedged from + * pending faults from the GPU and we are taking a devcoredump. + * Wait until the MMU is resumed and try again. + */ + wait_for_completion(&a6xx_gpu->base.fault_coredump_done); + } while (true); if (ret) DRM_DEV_ERROR(gmu->dev, @@ -395,10 +422,16 @@ int a6xx_gmu_set_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state) /* Clear a pending OOB state in the GMU */ void a6xx_gmu_clear_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state) { + struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); + struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; int bit; WARN_ON_ONCE(!mutex_is_locked(&gmu->lock)); + /* Skip OOB calls since RGMU is not enabled */ + if (adreno_has_rgmu(adreno_gpu)) + return; + if (state >= ARRAY_SIZE(a6xx_gmu_oob_bits)) return; @@ -485,17 +518,25 @@ static void a6xx_gemnoc_workaround(struct a6xx_gmu *gmu) * in the power down sequence not being fully executed. That in turn can * prevent CX_GDSC from collapsing. Assert Qactive to avoid this. */ - if (adreno_is_a621(adreno_gpu) || adreno_is_7c3(adreno_gpu)) - gmu_write(gmu, REG_A6XX_GMU_AO_AHB_FENCE_CTRL, BIT(0)); + if (adreno_is_a8xx(adreno_gpu)) + gmu_write(gmu, REG_A8XX_GPU_GMU_CX_GMU_CX_FALNEXT_INTF, BIT(0)); + else if (adreno_is_a7xx(adreno_gpu) || (adreno_is_a621(adreno_gpu) || + adreno_is_7c3(adreno_gpu))) + gmu_write(gmu, REG_A6XX_GPU_GMU_CX_GMU_CX_FALNEXT_INTF, BIT(0)); } /* Let the GMU know that we are about to go into slumber */ static int a6xx_gmu_notify_slumber(struct a6xx_gmu *gmu) { + struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); + struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; int ret; /* Disable the power counter so the GMU isn't busy */ - gmu_write(gmu, REG_A6XX_GMU_CX_GMU_POWER_COUNTER_ENABLE, 0); + if (adreno_is_a8xx(adreno_gpu)) + gmu_write(gmu, REG_A8XX_GMU_CX_GMU_POWER_COUNTER_ENABLE, 0); + else + gmu_write(gmu, REG_A6XX_GMU_CX_GMU_POWER_COUNTER_ENABLE, 0); /* Disable SPTP_PC if the CPU is responsible for it */ if (gmu->idle_level < GMU_IDLE_STATE_SPTP) @@ -522,10 +563,9 @@ static int a6xx_gmu_notify_slumber(struct a6xx_gmu *gmu) } out: - a6xx_gemnoc_workaround(gmu); - /* Put fence into allow mode */ gmu_write(gmu, REG_A6XX_GMU_AO_AHB_FENCE_CTRL, 0); + a6xx_gemnoc_workaround(gmu); return ret; } @@ -561,16 +601,22 @@ static int a6xx_rpmh_start(struct a6xx_gmu *gmu) static void a6xx_rpmh_stop(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 bitmask = BIT(16); int ret; u32 val; if (test_and_clear_bit(GMU_STATUS_FW_START, &gmu->status)) return; + if (adreno_is_a840(adreno_gpu)) + bitmask = BIT(30); + gmu_write(gmu, REG_A6XX_GMU_RSCC_CONTROL_REQ, 1); ret = gmu_poll_timeout_rscc(gmu, REG_A6XX_GPU_RSCC_RSC_STATUS0_DRV0, - val, val & (1 << 16), 100, 10000); + val, val & bitmask, 100, 10000); if (ret) DRM_DEV_ERROR(gmu->dev, "Unable to power off the GPU RSC\n"); @@ -584,22 +630,24 @@ static inline void pdc_write(void __iomem *ptr, u32 offset, u32 value) writel(value, ptr + (offset << 2)); } -static void __iomem *a6xx_gmu_get_mmio(struct platform_device *pdev, - const char *name); - static void a6xx_gmu_rpmh_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; struct platform_device *pdev = to_platform_device(gmu->dev); - void __iomem *pdcptr = a6xx_gmu_get_mmio(pdev, "gmu_pdc"); u32 seqmem0_drv0_reg = REG_A6XX_RSCC_SEQ_MEM_0_DRV0; void __iomem *seqptr = NULL; uint32_t pdc_address_offset; + void __iomem *pdcptr; bool pdc_in_aop = false; + /* On A8x and above, RPMH/PDC configurations are entirely configured in AOP */ + if (adreno_is_a8xx(adreno_gpu)) + return; + + pdcptr = devm_platform_ioremap_resource_byname(pdev, "gmu_pdc"); if (IS_ERR(pdcptr)) - goto err; + return; if (adreno_is_a650_family(adreno_gpu) || adreno_is_a7xx(adreno_gpu)) @@ -612,9 +660,9 @@ static void a6xx_gmu_rpmh_init(struct a6xx_gmu *gmu) pdc_address_offset = 0x30080; if (!pdc_in_aop) { - seqptr = a6xx_gmu_get_mmio(pdev, "gmu_pdc_seq"); + seqptr = devm_platform_ioremap_resource_byname(pdev, "gmu_pdc_seq"); if (IS_ERR(seqptr)) - goto err; + return; } /* Disable SDE clock gating */ @@ -704,12 +752,6 @@ setup_pdc: /* ensure no writes happen before the uCode is fully written */ wmb(); - -err: - if (!IS_ERR_OR_NULL(pdcptr)) - iounmap(pdcptr); - if (!IS_ERR_OR_NULL(seqptr)) - iounmap(seqptr); } /* @@ -732,7 +774,7 @@ static void a6xx_gmu_power_config(struct a6xx_gmu *gmu) gmu_write(gmu, REG_A6XX_GMU_DCACHE_CONFIG, 0x1); /* A7xx knows better by default! */ - if (adreno_is_a7xx(adreno_gpu)) + if (adreno_is_a7xx(adreno_gpu) || adreno_is_a8xx(adreno_gpu)) return; gmu_write(gmu, REG_A6XX_GMU_PWR_COL_INTER_FRAME_CTRL, 0x9c40400); @@ -780,6 +822,9 @@ static bool fw_block_mem(struct a6xx_gmu_bo *bo, const struct block_header *blk) return true; } +#define NEXT_BLK(blk) \ + ((const struct block_header *)((const char *)(blk) + sizeof(*(blk)) + (blk)->size)) + static int a6xx_gmu_fw_load(struct a6xx_gmu *gmu) { struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); @@ -792,7 +837,9 @@ static int a6xx_gmu_fw_load(struct a6xx_gmu *gmu) u32 itcm_base = 0x00000000; u32 dtcm_base = 0x00040000; - if (adreno_is_a650_family(adreno_gpu) || adreno_is_a7xx(adreno_gpu)) + if (adreno_is_a650_family(adreno_gpu) || + adreno_is_a7xx(adreno_gpu) || + adreno_is_a8xx(adreno_gpu)) dtcm_base = 0x10004000; if (gmu->legacy) { @@ -811,7 +858,7 @@ static int a6xx_gmu_fw_load(struct a6xx_gmu *gmu) for (blk = (const struct block_header *) fw_image->data; (const u8*) blk < fw_image->data + fw_image->size; - blk = (const struct block_header *) &blk->data[blk->size >> 2]) { + blk = NEXT_BLK(blk)) { if (blk->size == 0) continue; @@ -847,7 +894,9 @@ static int a6xx_gmu_fw_start(struct a6xx_gmu *gmu, unsigned int state) { struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; + struct msm_gpu *gpu = &adreno_gpu->base; const struct a6xx_info *a6xx_info = adreno_gpu->info->a6xx; + const struct adreno_reglist *gbif_cx = a6xx_info->gbif_cx; u32 fence_range_lower, fence_range_upper; u32 chipid = 0; int ret; @@ -856,12 +905,15 @@ static int a6xx_gmu_fw_start(struct a6xx_gmu *gmu, unsigned int state) if (adreno_is_a650_family(adreno_gpu) || adreno_is_a7xx(adreno_gpu)) { gmu_write(gmu, REG_A6XX_GPU_GMU_CX_GMU_CX_FALNEXT_INTF, 1); gmu_write(gmu, REG_A6XX_GPU_GMU_CX_GMU_CX_FAL_INTF, 1); + } else if (adreno_is_a8xx(adreno_gpu)) { + gmu_write(gmu, REG_A8XX_GPU_GMU_CX_GMU_CX_FALNEXT_INTF, 1); + gmu_write(gmu, REG_A8XX_GPU_GMU_CX_GMU_CX_FAL_INTF, 1); } /* Turn on TCM (Tightly Coupled Memory) retention */ if (adreno_is_a7xx(adreno_gpu)) a6xx_llc_write(a6xx_gpu, REG_A7XX_CX_MISC_TCM_RET_CNTL, 1); - else + else if (!adreno_is_a8xx(adreno_gpu)) gmu_write(gmu, REG_A6XX_GMU_GENERAL_7, 1); ret = a6xx_rpmh_start(gmu); @@ -886,7 +938,10 @@ static int a6xx_gmu_fw_start(struct a6xx_gmu *gmu, unsigned int state) gmu_write(gmu, REG_A6XX_GMU_HFI_QTBL_ADDR, gmu->hfi.iova); gmu_write(gmu, REG_A6XX_GMU_HFI_QTBL_INFO, 1); - if (adreno_is_a7xx(adreno_gpu)) { + if (adreno_is_a8xx(adreno_gpu)) { + fence_range_upper = 0x32; + fence_range_lower = 0x8c0; + } else if (adreno_is_a7xx(adreno_gpu)) { fence_range_upper = 0x32; fence_range_lower = 0x8a0; } else { @@ -920,7 +975,12 @@ static int a6xx_gmu_fw_start(struct a6xx_gmu *gmu, unsigned int state) chipid |= (adreno_gpu->chip_id << 8) & 0x0f00; /* patchid */ } - if (adreno_is_a7xx(adreno_gpu)) { + if (adreno_is_a8xx(adreno_gpu)) { + gmu_write(gmu, REG_A8XX_GMU_GENERAL_10, chipid); + gmu_write(gmu, REG_A8XX_GMU_GENERAL_8, + (gmu->log.iova & GENMASK(31, 12)) | + ((gmu->log.size / SZ_4K - 1) & GENMASK(7, 0))); + } else if (adreno_is_a7xx(adreno_gpu)) { gmu_write(gmu, REG_A7XX_GMU_GENERAL_10, chipid); gmu_write(gmu, REG_A7XX_GMU_GENERAL_8, (gmu->log.iova & GENMASK(31, 12)) | @@ -932,6 +992,15 @@ static int a6xx_gmu_fw_start(struct a6xx_gmu *gmu, unsigned int state) gmu->log.iova | (gmu->log.size / SZ_4K - 1)); } + /* For A7x and newer, do the CX GBIF configurations before GMU wake up */ + for (int i = 0; (gbif_cx && gbif_cx[i].offset); i++) + gpu_write(gpu, gbif_cx[i].offset, gbif_cx[i].value); + + if (adreno_is_a8xx(adreno_gpu)) { + gpu_write(gpu, REG_A8XX_GBIF_CX_CONFIG, 0x20023000); + gmu_write(gmu, REG_A6XX_GMU_MRC_GBIF_QOS_CTRL, 0x33); + } + /* Set up the lowest idle level on the GMU */ a6xx_gmu_power_config(gmu); @@ -983,7 +1052,7 @@ static void a6xx_gmu_rpmh_off(struct a6xx_gmu *gmu) u32 val, seqmem_off = 0; /* The second spin of A7xx GPUs messed with some register offsets.. */ - if (adreno_is_a740_family(adreno_gpu)) + if (adreno_is_a740_family(adreno_gpu) || adreno_is_a8xx(adreno_gpu)) seqmem_off = 4; /* Make sure there are no outstanding RPMh votes */ @@ -996,7 +1065,7 @@ static void a6xx_gmu_rpmh_off(struct a6xx_gmu *gmu) gmu_poll_timeout_rscc(gmu, REG_A6XX_RSCC_TCS3_DRV0_STATUS + seqmem_off, val, (val & 1), 100, 1000); - if (!adreno_is_a740_family(adreno_gpu)) + if (!adreno_is_a740_family(adreno_gpu) && !adreno_is_a8xx(adreno_gpu)) return; gmu_poll_timeout_rscc(gmu, REG_A7XX_RSCC_TCS4_DRV0_STATUS + seqmem_off, @@ -1024,7 +1093,10 @@ static void a6xx_gmu_force_off(struct a6xx_gmu *gmu) * Turn off keep alive that might have been enabled by the hang * interrupt */ - gmu_write(&a6xx_gpu->gmu, REG_A6XX_GMU_GMU_PWR_COL_KEEPALIVE, 0); + if (adreno_is_a8xx(adreno_gpu)) + gmu_write(&a6xx_gpu->gmu, REG_A8XX_GMU_GMU_PWR_COL_KEEPALIVE, 0); + else + gmu_write(&a6xx_gpu->gmu, REG_A6XX_GMU_GMU_PWR_COL_KEEPALIVE, 0); /* Flush all the queues */ a6xx_hfi_stop(gmu); @@ -1050,7 +1122,7 @@ static void a6xx_gmu_force_off(struct a6xx_gmu *gmu) /* Halt the gmu cm3 core */ gmu_write(gmu, REG_A6XX_GMU_CM3_SYSRESET, 1); - a6xx_bus_clear_pending_transactions(adreno_gpu, true); + adreno_gpu->funcs->bus_halt(adreno_gpu, true); /* Reset GPU core blocks */ a6xx_gpu_sw_reset(gpu, true); @@ -1119,6 +1191,9 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu) return ret; } + /* Read the slice info on A8x GPUs */ + a8xx_gpu_get_slice_info(gpu); + /* Set the bus quota to a reasonable value for boot */ a6xx_gmu_set_initial_bw(gpu, gmu); @@ -1128,7 +1203,7 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu) enable_irq(gmu->gmu_irq); /* Check to see if we are doing a cold or warm boot */ - if (adreno_is_a7xx(adreno_gpu)) { + if (adreno_is_a7xx(adreno_gpu) || adreno_is_a8xx(adreno_gpu)) { status = a6xx_llc_read(a6xx_gpu, REG_A7XX_CX_MISC_TCM_RET_CNTL) == 1 ? GMU_WARM_BOOT : GMU_COLD_BOOT; } else if (gmu->legacy) { @@ -1222,7 +1297,7 @@ static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu) if (ret) goto force_off; - a6xx_bus_clear_pending_transactions(adreno_gpu, a6xx_gpu->hung); + adreno_gpu->funcs->bus_halt(adreno_gpu, a6xx_gpu->hung); /* tell the GMU we want to slumber */ ret = a6xx_gmu_notify_slumber(gmu); @@ -1457,7 +1532,7 @@ static int a6xx_gmu_rpmh_bw_votes_init(struct adreno_gpu *adreno_gpu, vote = clamp(peak, 1, BCM_TCS_CMD_VOTE_MASK); /* GMUs on A7xx votes on both x & y */ - if (adreno_is_a7xx(adreno_gpu)) + if (adreno_is_a7xx(adreno_gpu) || adreno_is_a8xx(adreno_gpu)) data[bcm_index] = BCM_TCS_CMD(commit, true, vote, vote); else data[bcm_index] = BCM_TCS_CMD(commit, true, 0, vote); @@ -1489,13 +1564,14 @@ static unsigned int a6xx_gmu_get_arc_level(struct device *dev, } static int a6xx_gmu_rpmh_arc_votes_init(struct device *dev, u32 *votes, - unsigned long *freqs, int freqs_count, const char *id) + unsigned long *freqs, int freqs_count, + const char *pri_id, const char *sec_id) { int i, j; const u16 *pri, *sec; size_t pri_count, sec_count; - pri = cmd_db_read_aux_data(id, &pri_count); + pri = cmd_db_read_aux_data(pri_id, &pri_count); if (IS_ERR(pri)) return PTR_ERR(pri); /* @@ -1506,13 +1582,7 @@ static int a6xx_gmu_rpmh_arc_votes_init(struct device *dev, u32 *votes, if (!pri_count) return -EINVAL; - /* - * Some targets have a separate gfx mxc rail. So try to read that first and then fall back - * to regular mx rail if it is missing - */ - sec = cmd_db_read_aux_data("gmxc.lvl", &sec_count); - if (IS_ERR(sec) && sec != ERR_PTR(-EPROBE_DEFER)) - sec = cmd_db_read_aux_data("mx.lvl", &sec_count); + sec = cmd_db_read_aux_data(sec_id, &sec_count); if (IS_ERR(sec)) return PTR_ERR(sec); @@ -1566,6 +1636,57 @@ static int a6xx_gmu_rpmh_arc_votes_init(struct device *dev, u32 *votes, return 0; } +static int a6xx_gmu_rpmh_dep_votes_init(struct device *dev, u32 *votes, + unsigned long *freqs, int freqs_count) +{ + const u16 *mx; + size_t count; + + mx = cmd_db_read_aux_data("mx.lvl", &count); + if (IS_ERR(mx)) + return PTR_ERR(mx); + /* + * The data comes back as an array of unsigned shorts so adjust the + * count accordingly + */ + count >>= 1; + if (!count) + return -EINVAL; + + /* Fix the vote for zero frequency */ + votes[0] = 0xffffffff; + + /* Construct a vote for rest of the corners */ + for (int i = 1; i < freqs_count; i++) { + unsigned int level = a6xx_gmu_get_arc_level(dev, freqs[i]); + u8 j, index = 0; + + /* Get the primary index that matches the arc level */ + for (j = 0; j < count; j++) { + if (mx[j] >= level) { + index = j; + break; + } + } + + if (j == count) { + DRM_DEV_ERROR(dev, + "Mx Level %u not found in the RPMh list\n", + level); + DRM_DEV_ERROR(dev, "Available levels:\n"); + for (j = 0; j < count; j++) + DRM_DEV_ERROR(dev, " %u\n", mx[j]); + + return -EINVAL; + } + + /* Construct the vote */ + votes[i] = (0x3fff << 14) | (index << 8) | (0xff); + } + + return 0; +} + /* * 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 @@ -1580,15 +1701,27 @@ static int a6xx_gmu_rpmh_votes_init(struct a6xx_gmu *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; + const char *sec_id; + const u16 *gmxc; int ret; + gmxc = cmd_db_read_aux_data("gmxc.lvl", NULL); + if (gmxc == ERR_PTR(-EPROBE_DEFER)) + return -EPROBE_DEFER; + + /* If GMxC is present, prefer that as secondary rail for GX votes */ + sec_id = IS_ERR_OR_NULL(gmxc) ? "mx.lvl" : "gmxc.lvl"; + /* Build the GX votes */ ret = a6xx_gmu_rpmh_arc_votes_init(&gpu->pdev->dev, gmu->gx_arc_votes, - gmu->gpu_freqs, gmu->nr_gpu_freqs, "gfx.lvl"); + gmu->gpu_freqs, gmu->nr_gpu_freqs, "gfx.lvl", sec_id); /* Build the CX votes */ ret |= a6xx_gmu_rpmh_arc_votes_init(gmu->dev, gmu->cx_arc_votes, - gmu->gmu_freqs, gmu->nr_gmu_freqs, "cx.lvl"); + gmu->gmu_freqs, gmu->nr_gmu_freqs, "cx.lvl", "mx.lvl"); + + ret |= a6xx_gmu_rpmh_dep_votes_init(gmu->dev, gmu->dep_arc_votes, + gmu->gpu_freqs, gmu->nr_gpu_freqs); /* Build the interconnect votes */ if (info->bcms && gmu->nr_gpu_bws > 1) @@ -1792,27 +1925,6 @@ static int a6xx_gmu_clocks_probe(struct a6xx_gmu *gmu) return 0; } -static void __iomem *a6xx_gmu_get_mmio(struct platform_device *pdev, - const char *name) -{ - void __iomem *ret; - struct resource *res = platform_get_resource_byname(pdev, - IORESOURCE_MEM, name); - - if (!res) { - DRM_DEV_ERROR(&pdev->dev, "Unable to find the %s registers\n", name); - return ERR_PTR(-EINVAL); - } - - ret = ioremap(res->start, resource_size(res)); - if (!ret) { - DRM_DEV_ERROR(&pdev->dev, "Unable to map the %s registers\n", name); - return ERR_PTR(-EINVAL); - } - - return ret; -} - static int a6xx_gmu_get_irq(struct a6xx_gmu *gmu, struct platform_device *pdev, const char *name, irq_handler_t handler) { @@ -1863,7 +1975,6 @@ void a6xx_gmu_remove(struct a6xx_gpu *a6xx_gpu) { struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; struct a6xx_gmu *gmu = &a6xx_gpu->gmu; - struct platform_device *pdev = to_platform_device(gmu->dev); mutex_lock(&gmu->lock); if (!gmu->initialized) { @@ -1892,12 +2003,11 @@ void a6xx_gmu_remove(struct a6xx_gpu *a6xx_gpu) qmp_put(gmu->qmp); iounmap(gmu->mmio); - if (platform_get_resource_byname(pdev, IORESOURCE_MEM, "rscc")) - iounmap(gmu->rscc); gmu->mmio = NULL; gmu->rscc = NULL; - if (!adreno_has_gmu_wrapper(adreno_gpu)) { + if (!adreno_has_gmu_wrapper(adreno_gpu) && + !adreno_has_rgmu(adreno_gpu)) { a6xx_gmu_memory_free(gmu); free_irq(gmu->gmu_irq, gmu); @@ -1919,10 +2029,38 @@ static int cxpd_notifier_cb(struct notifier_block *nb, return 0; } +static void __iomem *a6xx_gmu_get_mmio(struct platform_device *pdev, + const char *name, resource_size_t *start) +{ + void __iomem *ret; + struct resource *res = platform_get_resource_byname(pdev, + IORESOURCE_MEM, name); + + if (!res) { + DRM_DEV_ERROR(&pdev->dev, "Unable to find the %s registers\n", name); + return ERR_PTR(-EINVAL); + } + + ret = ioremap(res->start, resource_size(res)); + if (!ret) { + DRM_DEV_ERROR(&pdev->dev, "Unable to map the %s registers\n", name); + return ERR_PTR(-EINVAL); + } + + if (start) + *start = res->start; + + return ret; +} + int a6xx_gmu_wrapper_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node) { struct platform_device *pdev = of_find_device_by_node(node); + struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; + struct msm_gpu *gpu = &adreno_gpu->base; struct a6xx_gmu *gmu = &a6xx_gpu->gmu; + resource_size_t start; + struct resource *res; int ret; if (!pdev) @@ -1939,13 +2077,29 @@ int a6xx_gmu_wrapper_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node) /* Mark legacy for manual SPTPRAC control */ gmu->legacy = true; + /* RGMU requires clocks */ + ret = devm_clk_bulk_get_all(gmu->dev, &gmu->clocks); + if (ret < 0) + goto err_clk; + + gmu->nr_clocks = ret; + /* Map the GMU registers */ - gmu->mmio = a6xx_gmu_get_mmio(pdev, "gmu"); + gmu->mmio = a6xx_gmu_get_mmio(pdev, "gmu", &start); if (IS_ERR(gmu->mmio)) { ret = PTR_ERR(gmu->mmio); goto err_mmio; } + res = platform_get_resource_byname(gpu->pdev, IORESOURCE_MEM, "kgsl_3d0_reg_memory"); + if (!res) { + ret = -EINVAL; + goto err_mmio; + } + + /* Identify gmu base offset from gpu base address */ + gmu->mmio_offset = (u32)(start - res->start); + gmu->cxpd = dev_pm_domain_attach_by_name(gmu->dev, "cx"); if (IS_ERR(gmu->cxpd)) { ret = PTR_ERR(gmu->cxpd); @@ -1978,6 +2132,7 @@ detach_cxpd: err_mmio: iounmap(gmu->mmio); +err_clk: /* Drop reference taken in of_find_device_by_node */ put_device(gmu->dev); @@ -1986,10 +2141,13 @@ err_mmio: int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node) { + struct platform_device *pdev = of_find_device_by_node(node); struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; + struct msm_gpu *gpu = &adreno_gpu->base; struct a6xx_gmu *gmu = &a6xx_gpu->gmu; - struct platform_device *pdev = of_find_device_by_node(node); struct device_link *link; + resource_size_t start; + struct resource *res; int ret; if (!pdev) @@ -2025,13 +2183,14 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node) */ gmu->dummy.size = SZ_4K; if (adreno_is_a660_family(adreno_gpu) || - adreno_is_a7xx(adreno_gpu)) { + adreno_is_a7xx(adreno_gpu) || + adreno_is_a8xx(adreno_gpu)) { ret = a6xx_gmu_memory_alloc(gmu, &gmu->debug, SZ_4K * 7, 0x60400000, "debug"); if (ret) goto err_memory; - gmu->dummy.size = SZ_8K; + gmu->dummy.size = SZ_16K; } /* Allocate memory for the GMU dummy page */ @@ -2042,7 +2201,8 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node) /* Note that a650 family also includes a660 family: */ if (adreno_is_a650_family(adreno_gpu) || - adreno_is_a7xx(adreno_gpu)) { + adreno_is_a7xx(adreno_gpu) || + adreno_is_a8xx(adreno_gpu)) { ret = a6xx_gmu_memory_alloc(gmu, &gmu->icache, SZ_16M - SZ_16K, 0x04000, "icache"); if (ret) @@ -2084,19 +2244,30 @@ int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node) goto err_memory; /* Map the GMU registers */ - gmu->mmio = a6xx_gmu_get_mmio(pdev, "gmu"); + gmu->mmio = a6xx_gmu_get_mmio(pdev, "gmu", &start); if (IS_ERR(gmu->mmio)) { ret = PTR_ERR(gmu->mmio); goto err_memory; } + res = platform_get_resource_byname(gpu->pdev, IORESOURCE_MEM, "kgsl_3d0_reg_memory"); + if (!res) { + ret = -EINVAL; + goto err_mmio; + } + + /* Identify gmu base offset from gpu base address */ + gmu->mmio_offset = (u32)(start - res->start); + if (adreno_is_a650_family(adreno_gpu) || adreno_is_a7xx(adreno_gpu)) { - gmu->rscc = a6xx_gmu_get_mmio(pdev, "rscc"); + gmu->rscc = devm_platform_ioremap_resource_byname(pdev, "rscc"); if (IS_ERR(gmu->rscc)) { ret = -ENODEV; goto err_mmio; } + } else if (adreno_is_a8xx(adreno_gpu)) { + gmu->rscc = gmu->mmio + 0x19000; } else { gmu->rscc = gmu->mmio + 0x23000; } @@ -2170,8 +2341,6 @@ detach_cxpd: err_mmio: iounmap(gmu->mmio); - if (platform_get_resource_byname(pdev, IORESOURCE_MEM, "rscc")) - iounmap(gmu->rscc); free_irq(gmu->gmu_irq, gmu); free_irq(gmu->hfi_irq, gmu); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h index 06cfc294016f..2af074c8e8cf 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.h @@ -19,8 +19,8 @@ struct a6xx_gmu_bo { u64 iova; }; -#define GMU_MAX_GX_FREQS 16 -#define GMU_MAX_CX_FREQS 4 +#define GMU_MAX_GX_FREQS 32 +#define GMU_MAX_CX_FREQS 6 #define GMU_MAX_BCMS 3 struct a6xx_bcm { @@ -68,6 +68,7 @@ struct a6xx_gmu { struct drm_gpuvm *vm; void __iomem *mmio; + u32 mmio_offset; void __iomem *rscc; int hfi_irq; @@ -96,6 +97,7 @@ struct a6xx_gmu { int nr_gpu_freqs; unsigned long gpu_freqs[GMU_MAX_GX_FREQS]; u32 gx_arc_votes[GMU_MAX_GX_FREQS]; + u32 dep_arc_votes[GMU_MAX_GX_FREQS]; struct a6xx_hfi_acd_table acd_table; int nr_gpu_bws; @@ -130,20 +132,23 @@ struct a6xx_gmu { unsigned long status; }; +#define GMU_BYTE_OFFSET(gmu, offset) (((offset) << 2) - (gmu)->mmio_offset) + static inline u32 gmu_read(struct a6xx_gmu *gmu, u32 offset) { - return readl(gmu->mmio + (offset << 2)); + /* The 'offset' is based on GPU's start address. Adjust it */ + return readl(gmu->mmio + GMU_BYTE_OFFSET(gmu, offset)); } static inline void gmu_write(struct a6xx_gmu *gmu, u32 offset, u32 value) { - writel(value, gmu->mmio + (offset << 2)); + writel(value, gmu->mmio + GMU_BYTE_OFFSET(gmu, offset)); } static inline void gmu_write_bulk(struct a6xx_gmu *gmu, u32 offset, const u32 *data, u32 size) { - memcpy_toio(gmu->mmio + (offset << 2), data, size); + memcpy_toio(gmu->mmio + GMU_BYTE_OFFSET(gmu, offset), data, size); wmb(); } @@ -160,17 +165,17 @@ static inline u64 gmu_read64(struct a6xx_gmu *gmu, u32 lo, u32 hi) { u64 val; - val = (u64) readl(gmu->mmio + (lo << 2)); - val |= ((u64) readl(gmu->mmio + (hi << 2)) << 32); + val = gmu_read(gmu, lo); + val |= ((u64) gmu_read(gmu, hi) << 32); return val; } #define gmu_poll_timeout(gmu, addr, val, cond, interval, timeout) \ - readl_poll_timeout((gmu)->mmio + ((addr) << 2), val, cond, \ - interval, timeout) + readl_poll_timeout((gmu)->mmio + (GMU_BYTE_OFFSET(gmu, addr)), val, \ + cond, interval, timeout) #define gmu_poll_timeout_atomic(gmu, addr, val, cond, interval, timeout) \ - readl_poll_timeout_atomic((gmu)->mmio + ((addr) << 2), val, cond, \ + readl_poll_timeout_atomic((gmu)->mmio + (GMU_BYTE_OFFSET(gmu, addr)), val, cond, \ interval, timeout) static inline u32 gmu_read_rscc(struct a6xx_gmu *gmu, u32 offset) diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index b8f8ae940b55..0200a7e71cdf 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -157,7 +157,7 @@ static void update_shadow_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) } } -static void a6xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring) +void a6xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); @@ -224,7 +224,7 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu, OUT_RING(ring, submit->seqno - 1); OUT_PKT7(ring, CP_THREAD_CONTROL, 1); - OUT_RING(ring, CP_SET_THREAD_BOTH); + OUT_RING(ring, CP_THREAD_CONTROL_0_SYNC_THREADS | CP_SET_THREAD_BOTH); /* Reset state used to synchronize BR and BV */ OUT_PKT7(ring, CP_RESET_CONTEXT_STATE, 1); @@ -235,18 +235,31 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu, CP_RESET_CONTEXT_STATE_0_RESET_GLOBAL_LOCAL_TS); OUT_PKT7(ring, CP_THREAD_CONTROL, 1); - OUT_RING(ring, CP_SET_THREAD_BR); + OUT_RING(ring, CP_THREAD_CONTROL_0_SYNC_THREADS | CP_SET_THREAD_BOTH); + + OUT_PKT7(ring, CP_EVENT_WRITE, 1); + OUT_RING(ring, LRZ_FLUSH_INVALIDATE); + + OUT_PKT7(ring, CP_THREAD_CONTROL, 1); + OUT_RING(ring, CP_THREAD_CONTROL_0_SYNC_THREADS | CP_SET_THREAD_BR); } if (!sysprof) { - if (!adreno_is_a7xx(adreno_gpu)) { + if (!(adreno_is_a7xx(adreno_gpu) || adreno_is_a8xx(adreno_gpu))) { /* Turn off protected mode to write to special registers */ OUT_PKT7(ring, CP_SET_PROTECTED_MODE, 1); OUT_RING(ring, 0); } - OUT_PKT4(ring, REG_A6XX_RBBM_PERFCTR_SRAM_INIT_CMD, 1); - OUT_RING(ring, 1); + if (adreno_is_a8xx(adreno_gpu)) { + OUT_PKT4(ring, REG_A8XX_RBBM_PERFCTR_SRAM_INIT_CMD, 1); + OUT_RING(ring, 1); + OUT_PKT4(ring, REG_A8XX_RBBM_SLICE_PERFCTR_SRAM_INIT_CMD, 1); + OUT_RING(ring, 1); + } else { + OUT_PKT4(ring, REG_A6XX_RBBM_PERFCTR_SRAM_INIT_CMD, 1); + OUT_RING(ring, 1); + } } /* Execute the table update */ @@ -275,7 +288,7 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu, * to make sure BV doesn't race ahead while BR is still switching * pagetables. */ - if (adreno_is_a7xx(&a6xx_gpu->base)) { + if (adreno_is_a7xx(&a6xx_gpu->base) || adreno_is_a8xx(&a6xx_gpu->base)) { OUT_PKT7(ring, CP_THREAD_CONTROL, 1); OUT_RING(ring, CP_THREAD_CONTROL_0_SYNC_THREADS | CP_SET_THREAD_BR); } @@ -289,20 +302,22 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu, OUT_RING(ring, CACHE_INVALIDATE); if (!sysprof) { + u32 reg_status = adreno_is_a8xx(adreno_gpu) ? + REG_A8XX_RBBM_PERFCTR_SRAM_INIT_STATUS : + REG_A6XX_RBBM_PERFCTR_SRAM_INIT_STATUS; /* * Wait for SRAM clear after the pgtable update, so the * two can happen in parallel: */ OUT_PKT7(ring, CP_WAIT_REG_MEM, 6); OUT_RING(ring, CP_WAIT_REG_MEM_0_FUNCTION(WRITE_EQ)); - OUT_RING(ring, CP_WAIT_REG_MEM_POLL_ADDR_LO( - REG_A6XX_RBBM_PERFCTR_SRAM_INIT_STATUS)); + OUT_RING(ring, CP_WAIT_REG_MEM_POLL_ADDR_LO(reg_status)); OUT_RING(ring, CP_WAIT_REG_MEM_POLL_ADDR_HI(0)); OUT_RING(ring, CP_WAIT_REG_MEM_3_REF(0x1)); OUT_RING(ring, CP_WAIT_REG_MEM_4_MASK(0x1)); OUT_RING(ring, CP_WAIT_REG_MEM_5_DELAY_LOOP_CYCLES(0)); - if (!adreno_is_a7xx(adreno_gpu)) { + if (!(adreno_is_a7xx(adreno_gpu) || adreno_is_a8xx(adreno_gpu))) { /* Re-enable protected mode: */ OUT_PKT7(ring, CP_SET_PROTECTED_MODE, 1); OUT_RING(ring, 1); @@ -375,7 +390,7 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) rbmemptr_stats(ring, index, alwayson_end)); /* Write the fence to the scratch register */ - OUT_PKT4(ring, REG_A6XX_CP_SCRATCH_REG(2), 1); + OUT_PKT4(ring, REG_A6XX_CP_SCRATCH(2), 1); OUT_RING(ring, submit->seqno); /* @@ -440,6 +455,7 @@ static void a7xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); struct msm_ringbuffer *ring = submit->ring; + u32 rbbm_perfctr_cp0, cp_always_on_counter; unsigned int i, ibs = 0; adreno_check_and_reenable_stall(adreno_gpu); @@ -460,10 +476,16 @@ static void a7xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) if (gpu->nr_rings > 1) a6xx_emit_set_pseudo_reg(ring, a6xx_gpu, submit->queue); - get_stats_counter(ring, REG_A7XX_RBBM_PERFCTR_CP(0), - rbmemptr_stats(ring, index, cpcycles_start)); - get_stats_counter(ring, REG_A6XX_CP_ALWAYS_ON_COUNTER, - rbmemptr_stats(ring, index, alwayson_start)); + if (adreno_is_a8xx(adreno_gpu)) { + rbbm_perfctr_cp0 = REG_A8XX_RBBM_PERFCTR_CP(0); + cp_always_on_counter = REG_A8XX_CP_ALWAYS_ON_COUNTER; + } else { + rbbm_perfctr_cp0 = REG_A7XX_RBBM_PERFCTR_CP(0); + cp_always_on_counter = REG_A6XX_CP_ALWAYS_ON_COUNTER; + } + + get_stats_counter(ring, rbbm_perfctr_cp0, rbmemptr_stats(ring, index, cpcycles_start)); + get_stats_counter(ring, cp_always_on_counter, rbmemptr_stats(ring, index, alwayson_start)); OUT_PKT7(ring, CP_THREAD_CONTROL, 1); OUT_RING(ring, CP_SET_THREAD_BOTH); @@ -510,14 +532,17 @@ static void a7xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) OUT_RING(ring, 0x00e); /* IB1LIST end */ } - get_stats_counter(ring, REG_A7XX_RBBM_PERFCTR_CP(0), - rbmemptr_stats(ring, index, cpcycles_end)); - get_stats_counter(ring, REG_A6XX_CP_ALWAYS_ON_COUNTER, - rbmemptr_stats(ring, index, alwayson_end)); + get_stats_counter(ring, rbbm_perfctr_cp0, rbmemptr_stats(ring, index, cpcycles_end)); + get_stats_counter(ring, cp_always_on_counter, rbmemptr_stats(ring, index, alwayson_end)); /* Write the fence to the scratch register */ - OUT_PKT4(ring, REG_A6XX_CP_SCRATCH_REG(2), 1); - OUT_RING(ring, submit->seqno); + if (adreno_is_a8xx(adreno_gpu)) { + OUT_PKT4(ring, REG_A8XX_CP_SCRATCH_GLOBAL(2), 1); + OUT_RING(ring, submit->seqno); + } else { + OUT_PKT4(ring, REG_A6XX_CP_SCRATCH(2), 1); + OUT_RING(ring, submit->seqno); + } OUT_PKT7(ring, CP_THREAD_CONTROL, 1); OUT_RING(ring, CP_SET_THREAD_BR); @@ -612,15 +637,26 @@ static void a6xx_set_hwcg(struct msm_gpu *gpu, bool state) if (adreno_is_a630(adreno_gpu)) clock_cntl_on = 0x8aa8aa02; - else if (adreno_is_a610(adreno_gpu)) + else if (adreno_is_a610(adreno_gpu) || adreno_is_a612(adreno_gpu)) clock_cntl_on = 0xaaa8aa82; else if (adreno_is_a702(adreno_gpu)) clock_cntl_on = 0xaaaaaa82; else clock_cntl_on = 0x8aa8aa82; - cgc_delay = adreno_is_a615_family(adreno_gpu) ? 0x111 : 0x10111; - cgc_hyst = adreno_is_a615_family(adreno_gpu) ? 0x555 : 0x5555; + if (adreno_is_a612(adreno_gpu)) + cgc_delay = 0x11; + else if (adreno_is_a615_family(adreno_gpu)) + cgc_delay = 0x111; + else + cgc_delay = 0x10111; + + if (adreno_is_a612(adreno_gpu)) + cgc_hyst = 0x55; + else if (adreno_is_a615_family(adreno_gpu)) + cgc_hyst = 0x555; + else + cgc_hyst = 0x5555; gmu_write(&a6xx_gpu->gmu, REG_A6XX_GPU_GMU_AO_GMU_CGC_MODE_CNTL, state ? adreno_gpu->info->a6xx->gmu_cgc_mode : 0); @@ -706,14 +742,20 @@ static int a6xx_calc_ubwc_config(struct adreno_gpu *gpu) /* Copy the data into the internal struct to drop the const qualifier (temporarily) */ *cfg = *common_cfg; - cfg->ubwc_swizzle = 0x6; - cfg->highest_bank_bit = 15; + /* Use common config as is for A8x */ + if (!adreno_is_a8xx(gpu)) { + cfg->ubwc_swizzle = 0x6; + cfg->highest_bank_bit = 15; + } if (adreno_is_a610(gpu)) { cfg->highest_bank_bit = 13; cfg->ubwc_swizzle = 0x7; } + if (adreno_is_a612(gpu)) + cfg->highest_bank_bit = 14; + if (adreno_is_a618(gpu)) cfg->highest_bank_bit = 14; @@ -993,7 +1035,7 @@ static bool a6xx_ucode_check_version(struct a6xx_gpu *a6xx_gpu, return false; /* A7xx is safe! */ - if (adreno_is_a7xx(adreno_gpu) || adreno_is_a702(adreno_gpu)) + if (adreno_is_a7xx(adreno_gpu) || adreno_is_a702(adreno_gpu) || adreno_is_a8xx(adreno_gpu)) return true; /* @@ -1076,6 +1118,23 @@ static int a6xx_ucode_load(struct msm_gpu *gpu) } } + if (!a6xx_gpu->aqe_bo && adreno_gpu->fw[ADRENO_FW_AQE]) { + a6xx_gpu->aqe_bo = adreno_fw_create_bo(gpu, + adreno_gpu->fw[ADRENO_FW_AQE], &a6xx_gpu->aqe_iova); + + if (IS_ERR(a6xx_gpu->aqe_bo)) { + int ret = PTR_ERR(a6xx_gpu->aqe_bo); + + a6xx_gpu->aqe_bo = NULL; + DRM_DEV_ERROR(&gpu->pdev->dev, + "Could not allocate AQE ucode: %d\n", ret); + + return ret; + } + + msm_gem_object_set_name(a6xx_gpu->aqe_bo, "aqefw"); + } + /* * Expanded APRIV and targets that support WHERE_AM_I both need a * privileged buffer to store the RPTR shadow @@ -1107,7 +1166,7 @@ static int a6xx_ucode_load(struct msm_gpu *gpu) return 0; } -static int a6xx_zap_shader_init(struct msm_gpu *gpu) +int a6xx_zap_shader_init(struct msm_gpu *gpu) { static bool loaded; int ret; @@ -1220,17 +1279,20 @@ static int hw_init(struct msm_gpu *gpu) /* enable hardware clockgating */ a6xx_set_hwcg(gpu, true); - /* VBIF/GBIF start*/ - if (adreno_is_a610_family(adreno_gpu) || - adreno_is_a640_family(adreno_gpu) || - adreno_is_a650_family(adreno_gpu) || - adreno_is_a7xx(adreno_gpu)) { + /* For gmuwrapper implementations, do the VBIF/GBIF CX configuration here */ + if (adreno_is_a610_family(adreno_gpu)) { gpu_write(gpu, REG_A6XX_GBIF_QSB_SIDE0, 0x00071620); gpu_write(gpu, REG_A6XX_GBIF_QSB_SIDE1, 0x00071620); gpu_write(gpu, REG_A6XX_GBIF_QSB_SIDE2, 0x00071620); gpu_write(gpu, REG_A6XX_GBIF_QSB_SIDE3, 0x00071620); - gpu_write(gpu, REG_A6XX_RBBM_GBIF_CLIENT_QOS_CNTL, - adreno_is_a7xx(adreno_gpu) ? 0x2120212 : 0x3); + } + + if (adreno_is_a610_family(adreno_gpu) || + adreno_is_a640_family(adreno_gpu) || + adreno_is_a650_family(adreno_gpu)) { + gpu_write(gpu, REG_A6XX_RBBM_GBIF_CLIENT_QOS_CNTL, 0x3); + } else if (adreno_is_a7xx(adreno_gpu)) { + gpu_write(gpu, REG_A6XX_RBBM_GBIF_CLIENT_QOS_CNTL, 0x2120212); } else { gpu_write(gpu, REG_A6XX_RBBM_VBIF_CLIENT_QOS_CNTL, 0x3); } @@ -1285,10 +1347,10 @@ static int hw_init(struct msm_gpu *gpu) } if (adreno_is_a660_family(adreno_gpu)) - gpu_write(gpu, REG_A6XX_CP_LPAC_PROG_FIFO_SIZE, 0x00000020); + gpu_write(gpu, REG_A7XX_CP_LPAC_PROG_FIFO_SIZE, 0x00000020); /* Setting the mem pool size */ - if (adreno_is_a610(adreno_gpu)) { + if (adreno_is_a610(adreno_gpu) || adreno_is_a612(adreno_gpu)) { gpu_write(gpu, REG_A6XX_CP_MEM_POOL_SIZE, 48); gpu_write(gpu, REG_A6XX_CP_MEM_POOL_DBG_ADDR, 47); } else if (adreno_is_a702(adreno_gpu)) { @@ -1321,7 +1383,8 @@ static int hw_init(struct msm_gpu *gpu) a6xx_set_ubwc_config(gpu); /* Enable fault detection */ - if (adreno_is_a730(adreno_gpu) || + if (adreno_is_a612(adreno_gpu) || + adreno_is_a730(adreno_gpu) || adreno_is_a740_family(adreno_gpu)) gpu_write(gpu, REG_A6XX_RBBM_INTERFACE_HANG_INT_CNTL, (1 << 30) | 0xcfffff); else if (adreno_is_a690(adreno_gpu)) @@ -1540,7 +1603,7 @@ static void a6xx_recover(struct msm_gpu *gpu) struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); struct a6xx_gmu *gmu = &a6xx_gpu->gmu; - int i, active_submits; + int active_submits; adreno_dump_info(gpu); @@ -1548,10 +1611,6 @@ static void a6xx_recover(struct msm_gpu *gpu) /* Sometimes crashstate capture is skipped, so SQE should be halted here again */ gpu_write(gpu, REG_A6XX_CP_SQE_CNTL, 3); - for (i = 0; i < 8; i++) - DRM_DEV_INFO(&gpu->pdev->dev, "CP_SCRATCH_REG%d: %u\n", i, - gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(i))); - if (hang_debug) a6xx_dump(gpu); @@ -1576,9 +1635,9 @@ static void a6xx_recover(struct msm_gpu *gpu) */ gpu->active_submits = 0; - if (adreno_has_gmu_wrapper(adreno_gpu)) { + if (adreno_has_gmu_wrapper(adreno_gpu) || adreno_has_rgmu(adreno_gpu)) { /* Drain the outstanding traffic on memory buses */ - a6xx_bus_clear_pending_transactions(adreno_gpu, true); + adreno_gpu->funcs->bus_halt(adreno_gpu, true); /* Reset the GPU to a clean state */ a6xx_gpu_sw_reset(gpu, true); @@ -1737,10 +1796,10 @@ static int a6xx_fault_handler(void *arg, unsigned long iova, int flags, void *da const char *block = "unknown"; u32 scratch[] = { - gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(4)), - gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(5)), - gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(6)), - gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(7)), + gpu_read(gpu, REG_A6XX_CP_SCRATCH(4)), + gpu_read(gpu, REG_A6XX_CP_SCRATCH(5)), + gpu_read(gpu, REG_A6XX_CP_SCRATCH(6)), + gpu_read(gpu, REG_A6XX_CP_SCRATCH(7)), }; if (info) @@ -2072,7 +2131,7 @@ static int a7xx_cx_mem_init(struct a6xx_gpu *a6xx_gpu) u32 fuse_val; int ret; - if (adreno_is_a750(adreno_gpu)) { + if (adreno_is_a750(adreno_gpu) || adreno_is_a8xx(adreno_gpu)) { /* * Assume that if qcom scm isn't available, that whatever * replacement allows writing the fuse register ourselves. @@ -2098,9 +2157,9 @@ static int a7xx_cx_mem_init(struct a6xx_gpu *a6xx_gpu) return ret; /* - * On a750 raytracing may be disabled by the firmware, find out - * whether that's the case. The scm call above sets the fuse - * register. + * On A7XX_GEN3 and newer, raytracing may be disabled by the + * firmware, find out whether that's the case. The scm call + * above sets the fuse register. */ fuse_val = a6xx_llc_read(a6xx_gpu, REG_A7XX_CX_MISC_SW_FUSE_VALUE); @@ -2161,7 +2220,7 @@ void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu, bool gx_ void a6xx_gpu_sw_reset(struct msm_gpu *gpu, bool assert) { /* 11nm chips (e.g. ones with A610) have hw issues with the reset line! */ - if (adreno_is_a610(to_adreno_gpu(gpu))) + if (adreno_is_a610(to_adreno_gpu(gpu)) || adreno_is_a8xx(to_adreno_gpu(gpu))) return; gpu_write(gpu, REG_A6XX_RBBM_SW_RESET_CMD, assert); @@ -2192,7 +2251,12 @@ static int a6xx_gmu_pm_resume(struct msm_gpu *gpu) msm_devfreq_resume(gpu); - adreno_is_a7xx(adreno_gpu) ? a7xx_llc_activate(a6xx_gpu) : a6xx_llc_activate(a6xx_gpu); + if (adreno_is_a8xx(adreno_gpu)) + a8xx_llc_activate(a6xx_gpu); + else if (adreno_is_a7xx(adreno_gpu)) + a7xx_llc_activate(a6xx_gpu); + else + a6xx_llc_activate(a6xx_gpu); return ret; } @@ -2229,6 +2293,12 @@ static int a6xx_pm_resume(struct msm_gpu *gpu) if (ret) goto err_bulk_clk; + ret = clk_bulk_prepare_enable(gmu->nr_clocks, gmu->clocks); + if (ret) { + clk_bulk_disable_unprepare(gpu->nr_clocks, gpu->grp_clks); + goto err_bulk_clk; + } + if (adreno_is_a619_holi(adreno_gpu)) a6xx_sptprac_enable(gmu); @@ -2242,8 +2312,10 @@ err_bulk_clk: err_set_opp: mutex_unlock(&a6xx_gpu->gmu.lock); - if (!ret) + if (!ret) { msm_devfreq_resume(gpu); + a6xx_llc_activate(a6xx_gpu); + } return ret; } @@ -2284,17 +2356,20 @@ static int a6xx_pm_suspend(struct msm_gpu *gpu) trace_msm_gpu_suspend(0); + a6xx_llc_deactivate(a6xx_gpu); + msm_devfreq_suspend(gpu); mutex_lock(&a6xx_gpu->gmu.lock); /* Drain the outstanding traffic on memory buses */ - a6xx_bus_clear_pending_transactions(adreno_gpu, true); + adreno_gpu->funcs->bus_halt(adreno_gpu, true); if (adreno_is_a619_holi(adreno_gpu)) a6xx_sptprac_disable(gmu); clk_bulk_disable_unprepare(gpu->nr_clocks, gpu->grp_clks); + clk_bulk_disable_unprepare(gmu->nr_clocks, gmu->clocks); pm_runtime_put_sync(gmu->gxpd); dev_pm_opp_set_opp(&gpu->pdev->dev, NULL); @@ -2345,6 +2420,11 @@ static void a6xx_destroy(struct msm_gpu *gpu) drm_gem_object_put(a6xx_gpu->sqe_bo); } + if (a6xx_gpu->aqe_bo) { + msm_gem_unpin_iova(a6xx_gpu->aqe_bo, gpu->vm); + drm_gem_object_put(a6xx_gpu->aqe_bo); + } + if (a6xx_gpu->shadow_bo) { msm_gem_unpin_iova(a6xx_gpu->shadow_bo, gpu->vm); drm_gem_object_put(a6xx_gpu->shadow_bo); @@ -2527,7 +2607,105 @@ static int a6xx_set_supported_hw(struct device *dev, const struct adreno_info *i return 0; } -static const struct adreno_gpu_funcs funcs = { +static struct msm_gpu *a6xx_gpu_init(struct drm_device *dev) +{ + struct msm_drm_private *priv = dev->dev_private; + struct platform_device *pdev = priv->gpu_pdev; + struct adreno_platform_config *config = pdev->dev.platform_data; + struct device_node *node; + struct a6xx_gpu *a6xx_gpu; + struct adreno_gpu *adreno_gpu; + struct msm_gpu *gpu; + extern int enable_preemption; + bool is_a7xx; + int ret, nr_rings = 1; + + a6xx_gpu = kzalloc(sizeof(*a6xx_gpu), GFP_KERNEL); + if (!a6xx_gpu) + return ERR_PTR(-ENOMEM); + + adreno_gpu = &a6xx_gpu->base; + gpu = &adreno_gpu->base; + + mutex_init(&a6xx_gpu->gmu.lock); + + adreno_gpu->registers = NULL; + + /* Check if there is a GMU phandle and set it up */ + node = of_parse_phandle(pdev->dev.of_node, "qcom,gmu", 0); + /* FIXME: How do we gracefully handle this? */ + BUG_ON(!node); + + adreno_gpu->gmu_is_wrapper = of_device_is_compatible(node, "qcom,adreno-gmu-wrapper"); + + adreno_gpu->base.hw_apriv = + !!(config->info->quirks & ADRENO_QUIRK_HAS_HW_APRIV); + + /* gpu->info only gets assigned in adreno_gpu_init(). A8x is included intentionally */ + is_a7xx = config->info->family >= ADRENO_7XX_GEN1; + + a6xx_llc_slices_init(pdev, a6xx_gpu, is_a7xx); + + ret = a6xx_set_supported_hw(&pdev->dev, config->info); + if (ret) { + a6xx_llc_slices_destroy(a6xx_gpu); + kfree(a6xx_gpu); + return ERR_PTR(ret); + } + + if ((enable_preemption == 1) || (enable_preemption == -1 && + (config->info->quirks & ADRENO_QUIRK_PREEMPTION))) + nr_rings = 4; + + ret = adreno_gpu_init(dev, pdev, adreno_gpu, config->info->funcs, nr_rings); + if (ret) { + a6xx_destroy(&(a6xx_gpu->base.base)); + return ERR_PTR(ret); + } + + /* + * For now only clamp to idle freq for devices where this is known not + * to cause power supply issues: + */ + if (adreno_is_a618(adreno_gpu) || adreno_is_7c3(adreno_gpu)) + priv->gpu_clamp_to_idle = true; + + if (adreno_has_gmu_wrapper(adreno_gpu) || adreno_has_rgmu(adreno_gpu)) + ret = a6xx_gmu_wrapper_init(a6xx_gpu, node); + else + ret = a6xx_gmu_init(a6xx_gpu, node); + of_node_put(node); + if (ret) { + a6xx_destroy(&(a6xx_gpu->base.base)); + return ERR_PTR(ret); + } + + if (adreno_is_a7xx(adreno_gpu) || adreno_is_a8xx(adreno_gpu)) { + ret = a7xx_cx_mem_init(a6xx_gpu); + if (ret) { + a6xx_destroy(&(a6xx_gpu->base.base)); + return ERR_PTR(ret); + } + } + + adreno_gpu->uche_trap_base = 0x1fffffffff000ull; + + msm_mmu_set_fault_handler(to_msm_vm(gpu->vm)->mmu, gpu, + adreno_gpu->funcs->mmu_fault_handler); + + ret = a6xx_calc_ubwc_config(adreno_gpu); + if (ret) { + a6xx_destroy(&(a6xx_gpu->base.base)); + return ERR_PTR(ret); + } + + /* Set up the preemption specific bits and pieces for each ringbuffer */ + a6xx_preempt_init(gpu); + + return gpu; +} + +const struct adreno_gpu_funcs a6xx_gpu_funcs = { .base = { .get_param = adreno_get_param, .set_param = adreno_set_param, @@ -2554,12 +2732,14 @@ static const struct adreno_gpu_funcs funcs = { .create_private_vm = a6xx_create_private_vm, .get_rptr = a6xx_get_rptr, .progress = a6xx_progress, - .sysprof_setup = a6xx_gmu_sysprof_setup, }, + .init = a6xx_gpu_init, .get_timestamp = a6xx_gmu_get_timestamp, + .bus_halt = a6xx_bus_clear_pending_transactions, + .mmu_fault_handler = a6xx_fault_handler, }; -static const struct adreno_gpu_funcs funcs_gmuwrapper = { +const struct adreno_gpu_funcs a6xx_gmuwrapper_funcs = { .base = { .get_param = adreno_get_param, .set_param = adreno_set_param, @@ -2585,10 +2765,13 @@ static const struct adreno_gpu_funcs funcs_gmuwrapper = { .get_rptr = a6xx_get_rptr, .progress = a6xx_progress, }, + .init = a6xx_gpu_init, .get_timestamp = a6xx_get_timestamp, + .bus_halt = a6xx_bus_clear_pending_transactions, + .mmu_fault_handler = a6xx_fault_handler, }; -static const struct adreno_gpu_funcs funcs_a7xx = { +const struct adreno_gpu_funcs a7xx_gpu_funcs = { .base = { .get_param = adreno_get_param, .set_param = adreno_set_param, @@ -2615,111 +2798,36 @@ static const struct adreno_gpu_funcs funcs_a7xx = { .create_private_vm = a6xx_create_private_vm, .get_rptr = a6xx_get_rptr, .progress = a6xx_progress, - .sysprof_setup = a6xx_gmu_sysprof_setup, }, + .init = a6xx_gpu_init, .get_timestamp = a6xx_gmu_get_timestamp, + .bus_halt = a6xx_bus_clear_pending_transactions, + .mmu_fault_handler = a6xx_fault_handler, }; -struct msm_gpu *a6xx_gpu_init(struct drm_device *dev) -{ - struct msm_drm_private *priv = dev->dev_private; - struct platform_device *pdev = priv->gpu_pdev; - struct adreno_platform_config *config = pdev->dev.platform_data; - struct device_node *node; - struct a6xx_gpu *a6xx_gpu; - struct adreno_gpu *adreno_gpu; - struct msm_gpu *gpu; - extern int enable_preemption; - bool is_a7xx; - int ret; - - a6xx_gpu = kzalloc(sizeof(*a6xx_gpu), GFP_KERNEL); - if (!a6xx_gpu) - return ERR_PTR(-ENOMEM); - - adreno_gpu = &a6xx_gpu->base; - gpu = &adreno_gpu->base; - - mutex_init(&a6xx_gpu->gmu.lock); - - adreno_gpu->registers = NULL; - - /* Check if there is a GMU phandle and set it up */ - node = of_parse_phandle(pdev->dev.of_node, "qcom,gmu", 0); - /* FIXME: How do we gracefully handle this? */ - BUG_ON(!node); - - adreno_gpu->gmu_is_wrapper = of_device_is_compatible(node, "qcom,adreno-gmu-wrapper"); - - adreno_gpu->base.hw_apriv = - !!(config->info->quirks & ADRENO_QUIRK_HAS_HW_APRIV); - - /* gpu->info only gets assigned in adreno_gpu_init() */ - is_a7xx = config->info->family == ADRENO_7XX_GEN1 || - config->info->family == ADRENO_7XX_GEN2 || - config->info->family == ADRENO_7XX_GEN3; - - a6xx_llc_slices_init(pdev, a6xx_gpu, is_a7xx); - - ret = a6xx_set_supported_hw(&pdev->dev, config->info); - if (ret) { - a6xx_llc_slices_destroy(a6xx_gpu); - kfree(a6xx_gpu); - return ERR_PTR(ret); - } - - if ((enable_preemption == 1) || (enable_preemption == -1 && - (config->info->quirks & ADRENO_QUIRK_PREEMPTION))) - ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs_a7xx, 4); - else if (is_a7xx) - ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs_a7xx, 1); - else if (adreno_has_gmu_wrapper(adreno_gpu)) - ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs_gmuwrapper, 1); - else - ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1); - if (ret) { - a6xx_destroy(&(a6xx_gpu->base.base)); - return ERR_PTR(ret); - } - - /* - * For now only clamp to idle freq for devices where this is known not - * to cause power supply issues: - */ - if (adreno_is_a618(adreno_gpu) || adreno_is_7c3(adreno_gpu)) - priv->gpu_clamp_to_idle = true; - - if (adreno_has_gmu_wrapper(adreno_gpu)) - ret = a6xx_gmu_wrapper_init(a6xx_gpu, node); - else - ret = a6xx_gmu_init(a6xx_gpu, node); - of_node_put(node); - if (ret) { - a6xx_destroy(&(a6xx_gpu->base.base)); - return ERR_PTR(ret); - } - - if (adreno_is_a7xx(adreno_gpu)) { - ret = a7xx_cx_mem_init(a6xx_gpu); - if (ret) { - a6xx_destroy(&(a6xx_gpu->base.base)); - return ERR_PTR(ret); - } - } - - adreno_gpu->uche_trap_base = 0x1fffffffff000ull; - - msm_mmu_set_fault_handler(to_msm_vm(gpu->vm)->mmu, gpu, - a6xx_fault_handler); - - ret = a6xx_calc_ubwc_config(adreno_gpu); - if (ret) { - a6xx_destroy(&(a6xx_gpu->base.base)); - return ERR_PTR(ret); - } - - /* Set up the preemption specific bits and pieces for each ringbuffer */ - a6xx_preempt_init(gpu); - - return gpu; -} +const struct adreno_gpu_funcs a8xx_gpu_funcs = { + .base = { + .get_param = adreno_get_param, + .set_param = adreno_set_param, + .hw_init = a8xx_hw_init, + .ucode_load = a6xx_ucode_load, + .pm_suspend = a6xx_gmu_pm_suspend, + .pm_resume = a6xx_gmu_pm_resume, + .recover = a8xx_recover, + .submit = a7xx_submit, + .active_ring = a6xx_active_ring, + .irq = a8xx_irq, + .destroy = a6xx_destroy, + .gpu_busy = a8xx_gpu_busy, + .gpu_get_freq = a6xx_gmu_get_freq, + .gpu_set_freq = a6xx_gpu_set_freq, + .create_vm = a6xx_create_vm, + .create_private_vm = a6xx_create_private_vm, + .get_rptr = a6xx_get_rptr, + .progress = a8xx_progress, + }, + .init = a6xx_gpu_init, + .get_timestamp = a8xx_gmu_get_timestamp, + .bus_halt = a8xx_bus_clear_pending_transactions, + .mmu_fault_handler = a8xx_fault_handler, +}; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h index 0b17d36c36a9..6820216ec5fc 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h @@ -46,6 +46,9 @@ struct a6xx_info { const struct adreno_protect *protect; const struct adreno_reglist_list *pwrup_reglist; const struct adreno_reglist_list *ifpc_reglist; + const struct adreno_reglist *gbif_cx; + const struct adreno_reglist_pipe *nonctxt_reglist; + u32 max_slices; u32 gmu_chipid; u32 gmu_cgc_mode; u32 prim_fifo_threshold; @@ -57,6 +60,8 @@ struct a6xx_gpu { struct drm_gem_object *sqe_bo; uint64_t sqe_iova; + struct drm_gem_object *aqe_bo; + uint64_t aqe_iova; struct msm_ringbuffer *cur_ring; struct msm_ringbuffer *next_ring; @@ -101,6 +106,11 @@ struct a6xx_gpu { void *htw_llc_slice; bool have_mmu500; bool hung; + + u32 cached_aperture; + spinlock_t aperture_lock; + + u32 slice_mask; }; #define to_a6xx_gpu(x) container_of(x, struct a6xx_gpu, base) @@ -216,6 +226,11 @@ struct a7xx_cp_smmu_info { #define A6XX_PROTECT_RDONLY(_reg, _len) \ ((((_len) & 0x3FFF) << 18) | ((_reg) & 0x3FFFF)) +extern const struct adreno_gpu_funcs a6xx_gpu_funcs; +extern const struct adreno_gpu_funcs a6xx_gmuwrapper_funcs; +extern const struct adreno_gpu_funcs a7xx_gpu_funcs; +extern const struct adreno_gpu_funcs a8xx_gpu_funcs; + static inline bool a6xx_has_gbif(struct adreno_gpu *gpu) { if(adreno_is_a630(gpu)) @@ -298,5 +313,19 @@ int a6xx_gpu_state_put(struct msm_gpu_state *state); void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu, bool gx_off); void a6xx_gpu_sw_reset(struct msm_gpu *gpu, bool assert); int a6xx_fenced_write(struct a6xx_gpu *gpu, u32 offset, u64 value, u32 mask, bool is_64b); - +void a6xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring); +int a6xx_zap_shader_init(struct msm_gpu *gpu); + +void a8xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu, bool gx_off); +int a8xx_fault_handler(void *arg, unsigned long iova, int flags, void *data); +void a8xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring); +int a8xx_gmu_get_timestamp(struct msm_gpu *gpu, uint64_t *value); +u64 a8xx_gpu_busy(struct msm_gpu *gpu, unsigned long *out_sample_rate); +int a8xx_gpu_feature_probe(struct msm_gpu *gpu); +void a8xx_gpu_get_slice_info(struct msm_gpu *gpu); +int a8xx_hw_init(struct msm_gpu *gpu); +irqreturn_t a8xx_irq(struct msm_gpu *gpu); +void a8xx_llc_activate(struct a6xx_gpu *a6xx_gpu); +bool a8xx_progress(struct msm_gpu *gpu, struct msm_ringbuffer *ring); +void a8xx_recover(struct msm_gpu *gpu); #endif /* __A6XX_GPU_H__ */ diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c index 4c7f3c642f6a..d2d6b2fd3cba 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c @@ -1255,7 +1255,7 @@ static void a6xx_get_gmu_registers(struct msm_gpu *gpu, return; /* Set the fence to ALLOW mode so we can access the registers */ - gpu_write(gpu, REG_A6XX_GMU_AO_AHB_FENCE_CTRL, 0); + gmu_write(&a6xx_gpu->gmu, REG_A6XX_GMU_AO_AHB_FENCE_CTRL, 0); _a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gmu_reglist[2], &a6xx_state->gmu_registers[3], false); @@ -1596,7 +1596,8 @@ struct msm_gpu_state *a6xx_gpu_state_get(struct msm_gpu *gpu) /* Get the generic state from the adreno core */ adreno_gpu_state_get(gpu, &a6xx_state->base); - if (!adreno_has_gmu_wrapper(adreno_gpu)) { + if (!adreno_has_gmu_wrapper(adreno_gpu) && + !adreno_has_rgmu(adreno_gpu)) { a6xx_get_gmu_registers(gpu, a6xx_state); a6xx_state->gmu_log = a6xx_snapshot_gmu_bo(a6xx_state, &a6xx_gpu->gmu.log); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h index 1c18499b60bb..b49d8427b59e 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h @@ -71,8 +71,8 @@ static const struct a6xx_cluster { u32 sel_val; } a6xx_clusters[] = { CLUSTER(CLUSTER_GRAS, a6xx_gras_cluster, 0, 0), - CLUSTER(CLUSTER_PS, a6xx_ps_cluster_rac, REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_CD, 0x0), - CLUSTER(CLUSTER_PS, a6xx_ps_cluster_rbp, REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_CD, 0x9), + CLUSTER(CLUSTER_PS, a6xx_ps_cluster_rac, REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_CD, 0x0), + CLUSTER(CLUSTER_PS, a6xx_ps_cluster_rbp, REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_CD, 0x9), CLUSTER(CLUSTER_PS, a6xx_ps_cluster, 0, 0), CLUSTER(CLUSTER_FE, a6xx_fe_cluster, 0, 0), CLUSTER(CLUSTER_PC_VS, a6xx_pc_vs_cluster, 0, 0), @@ -303,8 +303,8 @@ static const u32 a660_registers[] = { static const struct a6xx_registers a6xx_reglist[] = { REGS(a6xx_registers, 0, 0), REGS(a660_registers, 0, 0), - REGS(a6xx_rb_rac_registers, REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_CD, 0), - REGS(a6xx_rb_rbp_registers, REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_CD, 9), + REGS(a6xx_rb_rac_registers, REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_CD, 0), + REGS(a6xx_rb_rbp_registers, REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_CD, 9), }; static const u32 a6xx_ahb_registers[] = { @@ -343,48 +343,48 @@ static const struct a6xx_registers a6xx_gbif_reglist = static const u32 a6xx_gmu_gx_registers[] = { /* GMU GX */ - 0x0000, 0x0000, 0x0010, 0x0013, 0x0016, 0x0016, 0x0018, 0x001b, - 0x001e, 0x001e, 0x0020, 0x0023, 0x0026, 0x0026, 0x0028, 0x002b, - 0x002e, 0x002e, 0x0030, 0x0033, 0x0036, 0x0036, 0x0038, 0x003b, - 0x003e, 0x003e, 0x0040, 0x0043, 0x0046, 0x0046, 0x0080, 0x0084, - 0x0100, 0x012b, 0x0140, 0x0140, + 0x1a800, 0x1a800, 0x1a810, 0x1a813, 0x1a816, 0x1a816, 0x1a818, 0x1a81b, + 0x1a81e, 0x1a81e, 0x1a820, 0x1a823, 0x1a826, 0x1a826, 0x1a828, 0x1a82b, + 0x1a82e, 0x1a82e, 0x1a830, 0x1a833, 0x1a836, 0x1a836, 0x1a838, 0x1a83b, + 0x1a83e, 0x1a83e, 0x1a840, 0x1a843, 0x1a846, 0x1a846, 0x1a880, 0x1a884, + 0x1a900, 0x1a92b, 0x1a940, 0x1a940, }; static const u32 a6xx_gmu_cx_registers[] = { /* GMU CX */ - 0x4c00, 0x4c07, 0x4c10, 0x4c12, 0x4d00, 0x4d00, 0x4d07, 0x4d0a, - 0x5000, 0x5004, 0x5007, 0x5008, 0x500b, 0x500c, 0x500f, 0x501c, - 0x5024, 0x502a, 0x502d, 0x5030, 0x5040, 0x5053, 0x5087, 0x5089, - 0x50a0, 0x50a2, 0x50a4, 0x50af, 0x50c0, 0x50c3, 0x50d0, 0x50d0, - 0x50e4, 0x50e4, 0x50e8, 0x50ec, 0x5100, 0x5103, 0x5140, 0x5140, - 0x5142, 0x5144, 0x514c, 0x514d, 0x514f, 0x5151, 0x5154, 0x5154, - 0x5157, 0x5158, 0x515d, 0x515d, 0x5162, 0x5162, 0x5164, 0x5165, - 0x5180, 0x5186, 0x5190, 0x519e, 0x51c0, 0x51c0, 0x51c5, 0x51cc, - 0x51e0, 0x51e2, 0x51f0, 0x51f0, 0x5200, 0x5201, + 0x1f400, 0x1f407, 0x1f410, 0x1f412, 0x1f500, 0x1f500, 0x1f507, 0x1f50a, + 0x1f800, 0x1f804, 0x1f807, 0x1f808, 0x1f80b, 0x1f80c, 0x1f80f, 0x1f81c, + 0x1f824, 0x1f82a, 0x1f82d, 0x1f830, 0x1f840, 0x1f853, 0x1f887, 0x1f889, + 0x1f8a0, 0x1f8a2, 0x1f8a4, 0x1f8af, 0x1f8c0, 0x1f8c3, 0x1f8d0, 0x1f8d0, + 0x1f8e4, 0x1f8e4, 0x1f8e8, 0x1f8ec, 0x1f900, 0x1f903, 0x1f940, 0x1f940, + 0x1f942, 0x1f944, 0x1f94c, 0x1f94d, 0x1f94f, 0x1f951, 0x1f954, 0x1f954, + 0x1f957, 0x1f958, 0x1f95d, 0x1f95d, 0x1f962, 0x1f962, 0x1f964, 0x1f965, + 0x1f980, 0x1f986, 0x1f990, 0x1f99e, 0x1f9c0, 0x1f9c0, 0x1f9c5, 0x1f9cc, + 0x1f9e0, 0x1f9e2, 0x1f9f0, 0x1f9f0, 0x1fa00, 0x1fa01, /* GMU AO */ - 0x9300, 0x9316, 0x9400, 0x9400, + 0x23b00, 0x23b16, 0x23c00, 0x23c00, }; 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, - 0x9c42, 0x9c49, 0x9c58, 0x9c5a, 0x9d40, 0x9d5e, 0xa000, 0xa002, - 0xa400, 0xa402, 0xac00, 0xac02, 0xb000, 0xb002, 0xb400, 0xb402, - 0xb800, 0xb802, + 0x24000, 0x24012, 0x24040, 0x24052, 0x24400, 0x24404, 0x24407, 0x2440b, + 0x24415, 0x2441c, 0x2441e, 0x2442d, 0x2443c, 0x2443d, 0x2443f, 0x24440, + 0x24442, 0x24449, 0x24458, 0x2445a, 0x24540, 0x2455e, 0x24800, 0x24802, + 0x24c00, 0x24c02, 0x25400, 0x25402, 0x25800, 0x25802, 0x25c00, 0x25c02, + 0x26000, 0x26002, /* GPU CC ACD */ - 0xbc00, 0xbc16, 0xbc20, 0xbc27, + 0x26400, 0x26416, 0x26420, 0x26427, }; 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, + 0x24000, 0x2400e, 0x24400, 0x2440e, 0x25800, 0x25804, 0x25c00, 0x25c04, + 0x26000, 0x26004, 0x26400, 0x26405, 0x26414, 0x2641d, 0x2642a, 0x26430, + 0x26432, 0x26432, 0x26441, 0x26455, 0x26466, 0x26468, 0x26478, 0x2647a, + 0x26489, 0x2648a, 0x2649c, 0x2649e, 0x264a0, 0x264a3, 0x264b3, 0x264b5, + 0x264c5, 0x264c7, 0x264d6, 0x264d8, 0x264e8, 0x264e9, 0x264f9, 0x264fc, + 0x2650b, 0x2650c, 0x2651c, 0x2651e, 0x26540, 0x26570, 0x26600, 0x26616, + 0x26620, 0x2662d, }; static const u32 a6xx_gmu_cx_rscc_registers[] = { @@ -575,7 +575,7 @@ struct gen7_sptp_cluster_registers { /* statetype: SP block state type for the cluster */ enum a7xx_statetype_id statetype; /* pipe_id: Pipe identifier */ - enum a7xx_pipe pipe_id; + enum adreno_pipe pipe_id; /* context_id: Context identifier */ int context_id; /* location_id: Location identifier */ @@ -801,10 +801,10 @@ static const char *a7xx_statetype_names[] = { }; static const char *a7xx_pipe_names[] = { - A7XX_NAME(A7XX_PIPE_NONE), - A7XX_NAME(A7XX_PIPE_BR), - A7XX_NAME(A7XX_PIPE_BV), - A7XX_NAME(A7XX_PIPE_LPAC), + A7XX_NAME(PIPE_NONE), + A7XX_NAME(PIPE_BR), + A7XX_NAME(PIPE_BV), + A7XX_NAME(PIPE_LPAC), }; static const char *a7xx_cluster_names[] = { diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c index 550de6ad68ef..53cfdf4e6c34 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.c @@ -23,6 +23,7 @@ static const char * const a6xx_hfi_msg_id[] = { HFI_MSG_ID(HFI_H2F_MSG_START), HFI_MSG_ID(HFI_H2F_FEATURE_CTRL), HFI_MSG_ID(HFI_H2F_MSG_CORE_FW_START), + HFI_MSG_ID(HFI_H2F_MSG_TABLE), HFI_MSG_ID(HFI_H2F_MSG_GX_BW_PERF_VOTE), HFI_MSG_ID(HFI_H2F_MSG_PREPARE_SLUMBER), }; @@ -105,10 +106,25 @@ static int a6xx_hfi_wait_for_msg_interrupt(struct a6xx_gmu *gmu, u32 id, u32 seq { int ret; u32 val; + struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); + + do { + /* Wait for a response */ + ret = gmu_poll_timeout(gmu, REG_A6XX_GMU_GMU2HOST_INTR_INFO, val, + val & A6XX_GMU_GMU2HOST_INTR_INFO_MSGQ, 100, 1000000); + + if (!ret) + break; - /* Wait for a response */ - ret = gmu_poll_timeout(gmu, REG_A6XX_GMU_GMU2HOST_INTR_INFO, val, - val & A6XX_GMU_GMU2HOST_INTR_INFO_MSGQ, 100, 1000000); + if (completion_done(&a6xx_gpu->base.fault_coredump_done)) + break; + + /* We may timeout because the GMU is temporarily wedged from + * pending faults from the GPU and we are taking a devcoredump. + * Wait until the MMU is resumed and try again. + */ + wait_for_completion(&a6xx_gpu->base.fault_coredump_done); + } while (true); if (ret) { DRM_DEV_ERROR(gmu->dev, @@ -255,11 +271,63 @@ static int a6xx_hfi_send_perf_table_v1(struct a6xx_gmu *gmu) NULL, 0); } +static int a8xx_hfi_send_perf_table(struct a6xx_gmu *gmu) +{ + unsigned int num_gx_votes = 3, num_cx_votes = 2; + struct a6xx_hfi_table_entry *entry; + struct a6xx_hfi_table *tbl; + int ret, i; + u32 size; + + size = sizeof(*tbl) + (2 * sizeof(tbl->entry[0])) + + (gmu->nr_gpu_freqs * num_gx_votes * sizeof(gmu->gx_arc_votes[0])) + + (gmu->nr_gmu_freqs * num_cx_votes * sizeof(gmu->cx_arc_votes[0])); + tbl = kzalloc(size, GFP_KERNEL); + tbl->type = HFI_TABLE_GPU_PERF; + + /* First fill GX votes */ + entry = &tbl->entry[0]; + entry->count = gmu->nr_gpu_freqs; + entry->stride = num_gx_votes; + + for (i = 0; i < gmu->nr_gpu_freqs; i++) { + unsigned int base = i * entry->stride; + + entry->data[base+0] = gmu->gx_arc_votes[i]; + entry->data[base+1] = gmu->dep_arc_votes[i]; + entry->data[base+2] = gmu->gpu_freqs[i] / 1000; + } + + /* Then fill CX votes */ + entry = (struct a6xx_hfi_table_entry *) + &tbl->entry[0].data[gmu->nr_gpu_freqs * num_gx_votes]; + + entry->count = gmu->nr_gmu_freqs; + entry->stride = num_cx_votes; + + for (i = 0; i < gmu->nr_gmu_freqs; i++) { + unsigned int base = i * entry->stride; + + entry->data[base] = gmu->cx_arc_votes[i]; + entry->data[base+1] = gmu->gmu_freqs[i] / 1000; + } + + ret = a6xx_hfi_send_msg(gmu, HFI_H2F_MSG_TABLE, tbl, size, NULL, 0); + + kfree(tbl); + return ret; +} + static int a6xx_hfi_send_perf_table(struct a6xx_gmu *gmu) { + struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); + struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; struct a6xx_hfi_msg_perf_table msg = { 0 }; int i; + if (adreno_is_a8xx(adreno_gpu)) + return a8xx_hfi_send_perf_table(gmu); + msg.num_gpu_levels = gmu->nr_gpu_freqs; msg.num_gmu_levels = gmu->nr_gmu_freqs; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_hfi.h b/drivers/gpu/drm/msm/adreno/a6xx_hfi.h index 653ef720e2da..6f9f74a0bc85 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_hfi.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_hfi.h @@ -185,6 +185,23 @@ struct a6xx_hfi_msg_core_fw_start { u32 handle; }; +#define HFI_H2F_MSG_TABLE 15 + +struct a6xx_hfi_table_entry { + u32 count; + u32 stride; + u32 data[]; +}; + +struct a6xx_hfi_table { + u32 header; + u32 version; + u32 type; +#define HFI_TABLE_BW_VOTE 0 +#define HFI_TABLE_GPU_PERF 1 + struct a6xx_hfi_table_entry entry[]; +}; + #define HFI_H2F_MSG_GX_BW_PERF_VOTE 30 struct a6xx_hfi_gx_bw_perf_vote_cmd { diff --git a/drivers/gpu/drm/msm/adreno/a8xx_gpu.c b/drivers/gpu/drm/msm/adreno/a8xx_gpu.c new file mode 100644 index 000000000000..30de078e9dfd --- /dev/null +++ b/drivers/gpu/drm/msm/adreno/a8xx_gpu.c @@ -0,0 +1,1201 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ + + +#include "msm_gem.h" +#include "msm_mmu.h" +#include "msm_gpu_trace.h" +#include "a6xx_gpu.h" +#include "a6xx_gmu.xml.h" + +#include <linux/bitfield.h> +#include <linux/devfreq.h> +#include <linux/firmware/qcom/qcom_scm.h> +#include <linux/pm_domain.h> +#include <linux/soc/qcom/llcc-qcom.h> + +#define GPU_PAS_ID 13 + +static void a8xx_aperture_slice_set(struct msm_gpu *gpu, enum adreno_pipe pipe, u32 slice) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + u32 val; + + val = A8XX_CP_APERTURE_CNTL_HOST_PIPEID(pipe) | A8XX_CP_APERTURE_CNTL_HOST_SLICEID(slice); + + if (a6xx_gpu->cached_aperture == val) + return; + + gpu_write(gpu, REG_A8XX_CP_APERTURE_CNTL_HOST, val); + + a6xx_gpu->cached_aperture = val; +} + +static void a8xx_aperture_acquire(struct msm_gpu *gpu, enum adreno_pipe pipe, unsigned long *flags) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + + spin_lock_irqsave(&a6xx_gpu->aperture_lock, *flags); + + a8xx_aperture_slice_set(gpu, pipe, 0); +} + +static void a8xx_aperture_release(struct msm_gpu *gpu, unsigned long flags) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + + spin_unlock_irqrestore(&a6xx_gpu->aperture_lock, flags); +} + +static void a8xx_aperture_clear(struct msm_gpu *gpu) +{ + unsigned long flags; + + a8xx_aperture_acquire(gpu, PIPE_NONE, &flags); + a8xx_aperture_release(gpu, flags); +} + +static void a8xx_write_pipe(struct msm_gpu *gpu, enum adreno_pipe pipe, u32 offset, u32 data) +{ + unsigned long flags; + + a8xx_aperture_acquire(gpu, pipe, &flags); + gpu_write(gpu, offset, data); + a8xx_aperture_release(gpu, flags); +} + +static u32 a8xx_read_pipe_slice(struct msm_gpu *gpu, enum adreno_pipe pipe, u32 slice, u32 offset) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + unsigned long flags; + u32 val; + + spin_lock_irqsave(&a6xx_gpu->aperture_lock, flags); + a8xx_aperture_slice_set(gpu, pipe, slice); + val = gpu_read(gpu, offset); + spin_unlock_irqrestore(&a6xx_gpu->aperture_lock, flags); + + return val; +} + +void a8xx_gpu_get_slice_info(struct msm_gpu *gpu) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + const struct a6xx_info *info = adreno_gpu->info->a6xx; + u32 slice_mask; + + if (adreno_gpu->info->family < ADRENO_8XX_GEN1) + return; + + if (a6xx_gpu->slice_mask) + return; + + slice_mask = GENMASK(info->max_slices - 1, 0); + + /* GEN1 doesn't support partial slice configurations */ + if (adreno_gpu->info->family == ADRENO_8XX_GEN1) { + a6xx_gpu->slice_mask = slice_mask; + return; + } + + slice_mask &= a6xx_llc_read(a6xx_gpu, + REG_A8XX_CX_MISC_SLICE_ENABLE_FINAL); + + a6xx_gpu->slice_mask = slice_mask; + + /* Chip ID depends on the number of slices available. So update it */ + adreno_gpu->chip_id |= FIELD_PREP(GENMASK(7, 4), hweight32(slice_mask)); +} + +static u32 a8xx_get_first_slice(struct a6xx_gpu *a6xx_gpu) +{ + return ffs(a6xx_gpu->slice_mask) - 1; +} + +static inline bool _a8xx_check_idle(struct msm_gpu *gpu) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + + /* Check that the GMU is idle */ + if (!a6xx_gmu_isidle(&a6xx_gpu->gmu)) + return false; + + /* Check that the CX master is idle */ + if (gpu_read(gpu, REG_A8XX_RBBM_STATUS) & + ~A8XX_RBBM_STATUS_CP_AHB_BUSY_CX_MASTER) + return false; + + return !(gpu_read(gpu, REG_A8XX_RBBM_INT_0_STATUS) & + A6XX_RBBM_INT_0_MASK_RBBM_HANG_DETECT); +} + +static bool a8xx_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring) +{ + /* wait for CP to drain ringbuffer: */ + if (!adreno_idle(gpu, ring)) + return false; + + if (spin_until(_a8xx_check_idle(gpu))) { + DRM_ERROR( + "%s: %ps: timeout waiting for GPU to idle: status %8.8X irq %8.8X rptr/wptr %d/%d\n", + gpu->name, __builtin_return_address(0), + gpu_read(gpu, REG_A8XX_RBBM_STATUS), + gpu_read(gpu, REG_A8XX_RBBM_INT_0_STATUS), + gpu_read(gpu, REG_A6XX_CP_RB_RPTR), + gpu_read(gpu, REG_A6XX_CP_RB_WPTR)); + return false; + } + + return true; +} + +void a8xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + uint32_t wptr; + unsigned long flags; + + spin_lock_irqsave(&ring->preempt_lock, flags); + + /* Copy the shadow to the actual register */ + ring->cur = ring->next; + + /* Make sure to wrap wptr if we need to */ + wptr = get_wptr(ring); + + /* Update HW if this is the current ring and we are not in preempt*/ + if (!a6xx_in_preempt(a6xx_gpu)) { + if (a6xx_gpu->cur_ring == ring) + gpu_write(gpu, REG_A6XX_CP_RB_WPTR, wptr); + else + ring->restore_wptr = true; + } else { + ring->restore_wptr = true; + } + + spin_unlock_irqrestore(&ring->preempt_lock, flags); +} + +static void a8xx_set_hwcg(struct msm_gpu *gpu, bool state) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + struct a6xx_gmu *gmu = &a6xx_gpu->gmu; + u32 val; + + if (adreno_is_x285(adreno_gpu) && state) + gpu_write(gpu, REG_A8XX_RBBM_CGC_0_PC, 0x00000702); + + gmu_write(gmu, REG_A6XX_GPU_GMU_AO_GMU_CGC_MODE_CNTL, + state ? adreno_gpu->info->a6xx->gmu_cgc_mode : 0); + gmu_write(gmu, REG_A6XX_GPU_GMU_AO_GMU_CGC_DELAY_CNTL, + state ? 0x110111 : 0); + gmu_write(gmu, REG_A6XX_GPU_GMU_AO_GMU_CGC_HYST_CNTL, + state ? 0x55555 : 0); + + gpu_write(gpu, REG_A8XX_RBBM_CLOCK_CNTL_GLOBAL, 1); + gpu_write(gpu, REG_A8XX_RBBM_CGC_GLOBAL_LOAD_CMD, !!state); + + if (state) { + gpu_write(gpu, REG_A8XX_RBBM_CGC_P2S_TRIG_CMD, 1); + + if (gpu_poll_timeout(gpu, REG_A8XX_RBBM_CGC_P2S_STATUS, val, + val & A8XX_RBBM_CGC_P2S_STATUS_TXDONE, 1, 10)) { + dev_err(&gpu->pdev->dev, "RBBM_CGC_P2S_STATUS TXDONE Poll failed\n"); + return; + } + + gpu_write(gpu, REG_A8XX_RBBM_CLOCK_CNTL_GLOBAL, 0); + } else { + /* + * GMU enables clk gating in GBIF during boot up. So, + * override that here when hwcg feature is disabled + */ + gpu_rmw(gpu, REG_A8XX_GBIF_CX_CONFIG, BIT(0), 0); + } +} + +static void a8xx_set_cp_protect(struct msm_gpu *gpu) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + const struct adreno_protect *protect = adreno_gpu->info->a6xx->protect; + u32 cntl, final_cfg; + unsigned int i; + + cntl = A8XX_CP_PROTECT_CNTL_PIPE_ACCESS_PROT_EN | + A8XX_CP_PROTECT_CNTL_PIPE_ACCESS_FAULT_ON_VIOL_EN | + A8XX_CP_PROTECT_CNTL_PIPE_LAST_SPAN_INF_RANGE | + A8XX_CP_PROTECT_CNTL_PIPE_HALT_SQE_RANGE__MASK; + /* + * Enable access protection to privileged registers, fault on an access + * protect violation and select the last span to protect from the start + * address all the way to the end of the register address space + */ + a8xx_write_pipe(gpu, PIPE_BR, REG_A8XX_CP_PROTECT_CNTL_PIPE, cntl); + a8xx_write_pipe(gpu, PIPE_BV, REG_A8XX_CP_PROTECT_CNTL_PIPE, cntl); + + a8xx_aperture_clear(gpu); + + for (i = 0; i < protect->count; i++) { + /* Intentionally skip writing to some registers */ + if (protect->regs[i]) { + gpu_write(gpu, REG_A8XX_CP_PROTECT_GLOBAL(i), protect->regs[i]); + final_cfg = protect->regs[i]; + } + } + + /* + * Last span feature is only supported on PIPE specific register. + * So update those here + */ + a8xx_write_pipe(gpu, PIPE_BR, REG_A8XX_CP_PROTECT_PIPE(protect->count_max), final_cfg); + a8xx_write_pipe(gpu, PIPE_BV, REG_A8XX_CP_PROTECT_PIPE(protect->count_max), final_cfg); + + a8xx_aperture_clear(gpu); +} + +static void a8xx_set_ubwc_config(struct msm_gpu *gpu) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + const struct qcom_ubwc_cfg_data *cfg = adreno_gpu->ubwc_config; + u32 level2_swizzling_dis = !(cfg->ubwc_swizzle & UBWC_SWIZZLE_ENABLE_LVL2); + u32 level3_swizzling_dis = !(cfg->ubwc_swizzle & UBWC_SWIZZLE_ENABLE_LVL3); + bool rgba8888_lossless = false, fp16compoptdis = false; + bool yuvnotcomptofc = false, min_acc_len_64b = false; + bool rgb565_predicator = false, amsbc = false; + bool ubwc_mode = qcom_ubwc_get_ubwc_mode(cfg); + u32 ubwc_version = cfg->ubwc_enc_version; + u32 hbb, hbb_hi, hbb_lo, mode = 1; + u8 uavflagprd_inv = 2; + + switch (ubwc_version) { + case UBWC_5_0: + amsbc = true; + rgb565_predicator = true; + mode = 4; + break; + case UBWC_4_0: + amsbc = true; + rgb565_predicator = true; + fp16compoptdis = true; + rgba8888_lossless = true; + mode = 2; + break; + case UBWC_3_0: + amsbc = true; + mode = 1; + break; + default: + dev_err(&gpu->pdev->dev, "Unknown UBWC version: 0x%x\n", ubwc_version); + break; + } + + /* + * We subtract 13 from the highest bank bit (13 is the minimum value + * allowed by hw) and write the lowest two bits of the remaining value + * as hbb_lo and the one above it as hbb_hi to the hardware. + */ + WARN_ON(cfg->highest_bank_bit < 13); + hbb = cfg->highest_bank_bit - 13; + hbb_hi = hbb >> 2; + hbb_lo = hbb & 3; + a8xx_write_pipe(gpu, PIPE_BV, REG_A8XX_GRAS_NC_MODE_CNTL, hbb << 5); + a8xx_write_pipe(gpu, PIPE_BR, REG_A8XX_GRAS_NC_MODE_CNTL, hbb << 5); + + a8xx_write_pipe(gpu, PIPE_BR, REG_A8XX_RB_CCU_NC_MODE_CNTL, + yuvnotcomptofc << 6 | + hbb_hi << 3 | + hbb_lo << 1); + + a8xx_write_pipe(gpu, PIPE_BR, REG_A8XX_RB_CMP_NC_MODE_CNTL, + mode << 15 | + yuvnotcomptofc << 6 | + rgba8888_lossless << 4 | + fp16compoptdis << 3 | + rgb565_predicator << 2 | + amsbc << 1 | + min_acc_len_64b); + + a8xx_aperture_clear(gpu); + + gpu_write(gpu, REG_A6XX_SP_NC_MODE_CNTL, + level3_swizzling_dis << 13 | + level2_swizzling_dis << 12 | + hbb_hi << 10 | + uavflagprd_inv << 4 | + min_acc_len_64b << 3 | + hbb_lo << 1 | ubwc_mode); + + gpu_write(gpu, REG_A6XX_TPL1_NC_MODE_CNTL, + level3_swizzling_dis << 7 | + level2_swizzling_dis << 6 | + hbb_hi << 4 | + min_acc_len_64b << 3 | + hbb_lo << 1 | ubwc_mode); +} + +static void a8xx_nonctxt_config(struct msm_gpu *gpu, u32 *gmem_protect) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + const struct a6xx_info *info = adreno_gpu->info->a6xx; + const struct adreno_reglist_pipe *regs = info->nonctxt_reglist; + unsigned int pipe_id, i; + unsigned long flags; + + for (pipe_id = PIPE_NONE; pipe_id <= PIPE_DDE_BV; pipe_id++) { + /* We don't have support for LPAC yet */ + if (pipe_id == PIPE_LPAC) + continue; + + a8xx_aperture_acquire(gpu, pipe_id, &flags); + + for (i = 0; regs[i].offset; i++) { + if (!(BIT(pipe_id) & regs[i].pipe)) + continue; + + if (regs[i].offset == REG_A8XX_RB_GC_GMEM_PROTECT) + *gmem_protect = regs[i].value; + + gpu_write(gpu, regs[i].offset, regs[i].value); + } + + a8xx_aperture_release(gpu, flags); + } + + a8xx_aperture_clear(gpu); +} + +static int a8xx_cp_init(struct msm_gpu *gpu) +{ + struct msm_ringbuffer *ring = gpu->rb[0]; + u32 mask; + + /* Disable concurrent binning before sending CP init */ + OUT_PKT7(ring, CP_THREAD_CONTROL, 1); + OUT_RING(ring, BIT(27)); + + OUT_PKT7(ring, CP_ME_INIT, 4); + + /* Use multiple HW contexts */ + mask = BIT(0); + + /* Enable error detection */ + mask |= BIT(1); + + /* Set default reset state */ + mask |= BIT(3); + + /* Disable save/restore of performance counters across preemption */ + mask |= BIT(6); + + OUT_RING(ring, mask); + + /* Enable multiple hardware contexts */ + OUT_RING(ring, 0x00000003); + + /* Enable error detection */ + OUT_RING(ring, 0x20000000); + + /* Operation mode mask */ + OUT_RING(ring, 0x00000002); + + a6xx_flush(gpu, ring); + return a8xx_idle(gpu, ring) ? 0 : -EINVAL; +} + +#define A8XX_INT_MASK \ + (A6XX_RBBM_INT_0_MASK_CP_AHB_ERROR | \ + A6XX_RBBM_INT_0_MASK_RBBM_ATB_ASYNCFIFO_OVERFLOW | \ + A6XX_RBBM_INT_0_MASK_RBBM_GPC_ERROR | \ + A6XX_RBBM_INT_0_MASK_CP_SW | \ + A6XX_RBBM_INT_0_MASK_CP_HW_ERROR | \ + A6XX_RBBM_INT_0_MASK_PM4CPINTERRUPT | \ + A6XX_RBBM_INT_0_MASK_CP_RB_DONE_TS | \ + A6XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS | \ + A6XX_RBBM_INT_0_MASK_RBBM_ATB_BUS_OVERFLOW | \ + A6XX_RBBM_INT_0_MASK_RBBM_HANG_DETECT | \ + A6XX_RBBM_INT_0_MASK_UCHE_OOB_ACCESS | \ + A6XX_RBBM_INT_0_MASK_UCHE_TRAP_INTR | \ + A6XX_RBBM_INT_0_MASK_TSBWRITEERROR | \ + A6XX_RBBM_INT_0_MASK_SWFUSEVIOLATION) + +#define A8XX_APRIV_MASK \ + (A8XX_CP_APRIV_CNTL_PIPE_ICACHE | \ + A8XX_CP_APRIV_CNTL_PIPE_RBFETCH | \ + A8XX_CP_APRIV_CNTL_PIPE_RBPRIVLEVEL | \ + A8XX_CP_APRIV_CNTL_PIPE_RBRPWB) + +#define A8XX_BR_APRIV_MASK \ + (A8XX_APRIV_MASK | \ + A8XX_CP_APRIV_CNTL_PIPE_CDREAD | \ + A8XX_CP_APRIV_CNTL_PIPE_CDWRITE) + +#define A8XX_CP_GLOBAL_INT_MASK \ + (A8XX_CP_GLOBAL_INT_MASK_HWFAULTBR | \ + A8XX_CP_GLOBAL_INT_MASK_HWFAULTBV | \ + A8XX_CP_GLOBAL_INT_MASK_HWFAULTLPAC | \ + A8XX_CP_GLOBAL_INT_MASK_HWFAULTAQE0 | \ + A8XX_CP_GLOBAL_INT_MASK_HWFAULTAQE1 | \ + A8XX_CP_GLOBAL_INT_MASK_HWFAULTDDEBR | \ + A8XX_CP_GLOBAL_INT_MASK_HWFAULTDDEBV | \ + A8XX_CP_GLOBAL_INT_MASK_SWFAULTBR | \ + A8XX_CP_GLOBAL_INT_MASK_SWFAULTBV | \ + A8XX_CP_GLOBAL_INT_MASK_SWFAULTLPAC | \ + A8XX_CP_GLOBAL_INT_MASK_SWFAULTAQE0 | \ + A8XX_CP_GLOBAL_INT_MASK_SWFAULTAQE1 | \ + A8XX_CP_GLOBAL_INT_MASK_SWFAULTDDEBR | \ + A8XX_CP_GLOBAL_INT_MASK_SWFAULTDDEBV) + +#define A8XX_CP_INTERRUPT_STATUS_MASK_PIPE \ + (A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_CSFRBWRAP | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_CSFIB1WRAP | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_CSFIB2WRAP | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_CSFIB3WRAP | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_CSFSDSWRAP | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_CSFMRBWRAP | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_CSFVSDWRAP | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_OPCODEERROR | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_VSDPARITYERROR | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_REGISTERPROTECTIONERROR | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_ILLEGALINSTRUCTION | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_SMMUFAULT | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_VBIFRESPCLIENT| \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_VBIFRESPTYPE | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_VBIFRESPREAD | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_VBIFRESP | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_RTWROVF | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_LRZRTWROVF | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_LRZRTREFCNTOVF | \ + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE_LRZRTCLRRESMISS) + +#define A8XX_CP_HW_FAULT_STATUS_MASK_PIPE \ + (A8XX_CP_HW_FAULT_STATUS_MASK_PIPE_CSFRBFAULT | \ + A8XX_CP_HW_FAULT_STATUS_MASK_PIPE_CSFIB1FAULT | \ + A8XX_CP_HW_FAULT_STATUS_MASK_PIPE_CSFIB2FAULT | \ + A8XX_CP_HW_FAULT_STATUS_MASK_PIPE_CSFIB3FAULT | \ + A8XX_CP_HW_FAULT_STATUS_MASK_PIPE_CSFSDSFAULT | \ + A8XX_CP_HW_FAULT_STATUS_MASK_PIPE_CSFMRBFAULT | \ + A8XX_CP_HW_FAULT_STATUS_MASK_PIPE_CSFVSDFAULT | \ + A8XX_CP_HW_FAULT_STATUS_MASK_PIPE_SQEREADBURSTOVF | \ + A8XX_CP_HW_FAULT_STATUS_MASK_PIPE_EVENTENGINEOVF | \ + A8XX_CP_HW_FAULT_STATUS_MASK_PIPE_UCODEERROR) + +static int hw_init(struct msm_gpu *gpu) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + struct a6xx_gmu *gmu = &a6xx_gpu->gmu; + unsigned int pipe_id, i; + u32 gmem_protect = 0; + u64 gmem_range_min; + int ret; + + ret = a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET); + if (ret) + return ret; + + /* Clear the cached value to force aperture configuration next time */ + a6xx_gpu->cached_aperture = UINT_MAX; + a8xx_aperture_clear(gpu); + + /* Clear GBIF halt in case GX domain was not collapsed */ + gpu_write(gpu, REG_A6XX_GBIF_HALT, 0); + gpu_read(gpu, REG_A6XX_GBIF_HALT); + + gpu_write(gpu, REG_A8XX_RBBM_GBIF_HALT, 0); + gpu_read(gpu, REG_A8XX_RBBM_GBIF_HALT); + + gpu_write(gpu, REG_A6XX_RBBM_SECVID_TSB_CNTL, 0); + + /* + * Disable the trusted memory range - we don't actually supported secure + * memory rendering at this point in time and we don't want to block off + * part of the virtual memory space. + */ + gpu_write64(gpu, REG_A6XX_RBBM_SECVID_TSB_TRUSTED_BASE, 0x00000000); + gpu_write(gpu, REG_A6XX_RBBM_SECVID_TSB_TRUSTED_SIZE, 0x00000000); + + /* Make all blocks contribute to the GPU BUSY perf counter */ + gpu_write(gpu, REG_A8XX_RBBM_PERFCTR_GPU_BUSY_MASKED, 0xffffffff); + + /* Setup GMEM Range in UCHE */ + gmem_range_min = SZ_64M; + /* Set the GMEM VA range [0x100000:0x100000 + gpu->gmem - 1] */ + gpu_write64(gpu, REG_A8XX_UCHE_CCHE_GC_GMEM_RANGE_MIN, gmem_range_min); + gpu_write64(gpu, REG_A8XX_SP_HLSQ_GC_GMEM_RANGE_MIN, gmem_range_min); + + /* Setup UCHE Trap region */ + gpu_write64(gpu, REG_A8XX_UCHE_TRAP_BASE, adreno_gpu->uche_trap_base); + gpu_write64(gpu, REG_A8XX_UCHE_WRITE_THRU_BASE, adreno_gpu->uche_trap_base); + gpu_write64(gpu, REG_A8XX_UCHE_CCHE_TRAP_BASE, adreno_gpu->uche_trap_base); + gpu_write64(gpu, REG_A8XX_UCHE_CCHE_WRITE_THRU_BASE, adreno_gpu->uche_trap_base); + + /* Turn on performance counters */ + gpu_write(gpu, REG_A8XX_RBBM_PERFCTR_CNTL, 0x1); + gpu_write(gpu, REG_A8XX_RBBM_SLICE_PERFCTR_CNTL, 0x1); + + /* Turn on the IFPC counter (countable 4 on XOCLK1) */ + gmu_write(&a6xx_gpu->gmu, REG_A8XX_GMU_CX_GMU_POWER_COUNTER_SELECT_XOCLK_1, + FIELD_PREP(GENMASK(7, 0), 0x4)); + + /* Select CP0 to always count cycles */ + gpu_write(gpu, REG_A8XX_CP_PERFCTR_CP_SEL(0), 1); + + a8xx_set_ubwc_config(gpu); + + /* Set weights for bicubic filtering */ + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(0), 0); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(1), 0x3fe05ff4); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(2), 0x3fa0ebee); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(3), 0x3f5193ed); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(4), 0x3f0243f0); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(5), 0x00000000); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(6), 0x3fd093e8); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(7), 0x3f4133dc); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(8), 0x3ea1dfdb); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(9), 0x3e0283e0); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(10), 0x0000ac2b); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(11), 0x0000f01d); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(12), 0x00114412); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(13), 0x0021980a); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(14), 0x0051ec05); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(15), 0x0000380e); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(16), 0x3ff09001); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(17), 0x3fc10bfa); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(18), 0x3f9193f7); + gpu_write(gpu, REG_A8XX_TPL1_BICUBIC_WEIGHTS_TABLE(19), 0x3f7227f7); + + gpu_write(gpu, REG_A8XX_UCHE_CLIENT_PF, BIT(7) | 0x1); + + a8xx_nonctxt_config(gpu, &gmem_protect); + + /* Enable fault detection */ + gpu_write(gpu, REG_A8XX_RBBM_INTERFACE_HANG_INT_CNTL, BIT(30) | 0xcfffff); + gpu_write(gpu, REG_A8XX_RBBM_SLICE_INTERFACE_HANG_INT_CNTL, BIT(30)); + + /* Set up the CX GMU counter 0 to count busy ticks */ + gmu_write(gmu, REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_MASK, 0xff000000); + + /* Enable the power counter */ + gmu_rmw(gmu, REG_A8XX_GMU_CX_GMU_POWER_COUNTER_SELECT_XOCLK_0, 0xff, BIT(5)); + gmu_write(gmu, REG_A8XX_GMU_CX_GMU_POWER_COUNTER_ENABLE, 1); + + /* Protect registers from the CP */ + a8xx_set_cp_protect(gpu); + + /* Enable the GMEM save/restore feature for preemption */ + a8xx_write_pipe(gpu, PIPE_BR, REG_A6XX_RB_CONTEXT_SWITCH_GMEM_SAVE_RESTORE_ENABLE, 1); + + for (pipe_id = PIPE_BR; pipe_id <= PIPE_DDE_BV; pipe_id++) { + u32 apriv_mask = A8XX_APRIV_MASK; + unsigned long flags; + + if (pipe_id == PIPE_LPAC) + continue; + + if (pipe_id == PIPE_BR) + apriv_mask = A8XX_BR_APRIV_MASK; + + a8xx_aperture_acquire(gpu, pipe_id, &flags); + gpu_write(gpu, REG_A8XX_CP_APRIV_CNTL_PIPE, apriv_mask); + gpu_write(gpu, REG_A8XX_CP_INTERRUPT_STATUS_MASK_PIPE, + A8XX_CP_INTERRUPT_STATUS_MASK_PIPE); + gpu_write(gpu, REG_A8XX_CP_HW_FAULT_STATUS_MASK_PIPE, + A8XX_CP_HW_FAULT_STATUS_MASK_PIPE); + a8xx_aperture_release(gpu, flags); + } + + a8xx_aperture_clear(gpu); + + /* Enable interrupts */ + gpu_write(gpu, REG_A8XX_CP_INTERRUPT_STATUS_MASK_GLOBAL, A8XX_CP_GLOBAL_INT_MASK); + gpu_write(gpu, REG_A8XX_RBBM_INT_0_MASK, A8XX_INT_MASK); + + ret = adreno_hw_init(gpu); + if (ret) + goto out; + + gpu_write64(gpu, REG_A8XX_CP_SQE_INSTR_BASE, a6xx_gpu->sqe_iova); + if (a6xx_gpu->aqe_iova) + gpu_write64(gpu, REG_A8XX_CP_AQE_INSTR_BASE_0, a6xx_gpu->aqe_iova); + + /* Set the ringbuffer address */ + gpu_write64(gpu, REG_A6XX_CP_RB_BASE, gpu->rb[0]->iova); + gpu_write(gpu, REG_A6XX_CP_RB_CNTL, MSM_GPU_RB_CNTL_DEFAULT); + + /* Configure the RPTR shadow if needed: */ + gpu_write64(gpu, REG_A6XX_CP_RB_RPTR_ADDR, shadowptr(a6xx_gpu, gpu->rb[0])); + gpu_write64(gpu, REG_A8XX_CP_RB_RPTR_ADDR_BV, rbmemptr(gpu->rb[0], bv_rptr)); + + for (i = 0; i < gpu->nr_rings; i++) + a6xx_gpu->shadow[i] = 0; + + /* Always come up on rb 0 */ + a6xx_gpu->cur_ring = gpu->rb[0]; + + for (i = 0; i < gpu->nr_rings; i++) + gpu->rb[i]->cur_ctx_seqno = 0; + + /* Enable the SQE_to start the CP engine */ + gpu_write(gpu, REG_A8XX_CP_SQE_CNTL, 1); + + ret = a8xx_cp_init(gpu); + if (ret) + goto out; + + /* + * Try to load a zap shader into the secure world. If successful + * we can use the CP to switch out of secure mode. If not then we + * have no resource but to try to switch ourselves out manually. If we + * guessed wrong then access to the RBBM_SECVID_TRUST_CNTL register will + * be blocked and a permissions violation will soon follow. + */ + ret = a6xx_zap_shader_init(gpu); + if (!ret) { + OUT_PKT7(gpu->rb[0], CP_SET_SECURE_MODE, 1); + OUT_RING(gpu->rb[0], 0x00000000); + + a6xx_flush(gpu, gpu->rb[0]); + if (!a8xx_idle(gpu, gpu->rb[0])) + return -EINVAL; + } else if (ret == -ENODEV) { + /* + * This device does not use zap shader (but print a warning + * just in case someone got their dt wrong.. hopefully they + * have a debug UART to realize the error of their ways... + * if you mess this up you are about to crash horribly) + */ + dev_warn_once(gpu->dev->dev, + "Zap shader not enabled - using SECVID_TRUST_CNTL instead\n"); + gpu_write(gpu, REG_A6XX_RBBM_SECVID_TRUST_CNTL, 0x0); + ret = 0; + } else { + return ret; + } + + /* + * GMEM_PROTECT register should be programmed after GPU is transitioned to + * non-secure mode + */ + a8xx_write_pipe(gpu, PIPE_BR, REG_A8XX_RB_GC_GMEM_PROTECT, gmem_protect); + WARN_ON(!gmem_protect); + a8xx_aperture_clear(gpu); + + /* Enable hardware clockgating */ + a8xx_set_hwcg(gpu, true); +out: + /* + * Tell the GMU that we are done touching the GPU and it can start power + * management + */ + a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET); + + return ret; +} + +int a8xx_hw_init(struct msm_gpu *gpu) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + int ret; + + mutex_lock(&a6xx_gpu->gmu.lock); + ret = hw_init(gpu); + mutex_unlock(&a6xx_gpu->gmu.lock); + + return ret; +} + +static void a8xx_dump(struct msm_gpu *gpu) +{ + DRM_DEV_INFO(&gpu->pdev->dev, "status: %08x\n", gpu_read(gpu, REG_A8XX_RBBM_STATUS)); + adreno_dump(gpu); +} + +void a8xx_recover(struct msm_gpu *gpu) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + struct a6xx_gmu *gmu = &a6xx_gpu->gmu; + int active_submits; + + adreno_dump_info(gpu); + + if (hang_debug) + a8xx_dump(gpu); + + /* + * To handle recovery specific sequences during the rpm suspend we are + * about to trigger + */ + a6xx_gpu->hung = true; + + /* Halt SQE first */ + gpu_write(gpu, REG_A8XX_CP_SQE_CNTL, 3); + + pm_runtime_dont_use_autosuspend(&gpu->pdev->dev); + + /* active_submit won't change until we make a submission */ + mutex_lock(&gpu->active_lock); + active_submits = gpu->active_submits; + + /* + * Temporarily clear active_submits count to silence a WARN() in the + * runtime suspend cb + */ + gpu->active_submits = 0; + + reinit_completion(&gmu->pd_gate); + dev_pm_genpd_add_notifier(gmu->cxpd, &gmu->pd_nb); + dev_pm_genpd_synced_poweroff(gmu->cxpd); + + /* Drop the rpm refcount from active submits */ + if (active_submits) + pm_runtime_put(&gpu->pdev->dev); + + /* And the final one from recover worker */ + pm_runtime_put_sync(&gpu->pdev->dev); + + if (!wait_for_completion_timeout(&gmu->pd_gate, msecs_to_jiffies(1000))) + DRM_DEV_ERROR(&gpu->pdev->dev, "cx gdsc didn't collapse\n"); + + dev_pm_genpd_remove_notifier(gmu->cxpd); + + pm_runtime_use_autosuspend(&gpu->pdev->dev); + + if (active_submits) + pm_runtime_get(&gpu->pdev->dev); + + pm_runtime_get_sync(&gpu->pdev->dev); + + gpu->active_submits = active_submits; + mutex_unlock(&gpu->active_lock); + + msm_gpu_hw_init(gpu); + a6xx_gpu->hung = false; +} + +static const char *a8xx_uche_fault_block(struct msm_gpu *gpu, u32 mid) +{ + static const char * const uche_clients[] = { + "BR_VFD", "BR_SP", "BR_VSC", "BR_VPC", "BR_HLSQ", "BR_PC", "BR_LRZ", "BR_TP", + "BV_VFD", "BV_SP", "BV_VSC", "BV_VPC", "BV_HLSQ", "BV_PC", "BV_LRZ", "BV_TP", + "STCHE", + }; + static const char * const uche_clients_lpac[] = { + "-", "SP_LPAC", "-", "-", "HLSQ_LPAC", "-", "-", "TP_LPAC", + }; + u32 val; + + /* + * The source of the data depends on the mid ID read from FSYNR1. + * and the client ID read from the UCHE block + */ + val = gpu_read(gpu, REG_A8XX_UCHE_CLIENT_PF); + + val &= GENMASK(6, 0); + + /* mid=3 refers to BR or BV */ + if (mid == 3) { + if (val < ARRAY_SIZE(uche_clients)) + return uche_clients[val]; + else + return "UCHE"; + } + + /* mid=8 refers to LPAC */ + if (mid == 8) { + if (val < ARRAY_SIZE(uche_clients_lpac)) + return uche_clients_lpac[val]; + else + return "UCHE_LPAC"; + } + + return "Unknown"; +} + +static const char *a8xx_fault_block(struct msm_gpu *gpu, u32 id) +{ + switch (id) { + case 0x0: + return "CP"; + case 0x1: + return "UCHE: Unknown"; + case 0x2: + return "UCHE_LPAC: Unknown"; + case 0x3: + case 0x8: + return a8xx_uche_fault_block(gpu, id); + case 0x4: + return "CCU"; + case 0x5: + return "Flag cache"; + case 0x6: + return "PREFETCH"; + case 0x7: + return "GMU"; + case 0x9: + return "UCHE_HPAC"; + } + + return "Unknown"; +} + +int a8xx_fault_handler(void *arg, unsigned long iova, int flags, void *data) +{ + struct msm_gpu *gpu = arg; + struct adreno_smmu_fault_info *info = data; + const char *block = "unknown"; + + u32 scratch[] = { + gpu_read(gpu, REG_A8XX_CP_SCRATCH_GLOBAL(0)), + gpu_read(gpu, REG_A8XX_CP_SCRATCH_GLOBAL(1)), + gpu_read(gpu, REG_A8XX_CP_SCRATCH_GLOBAL(2)), + gpu_read(gpu, REG_A8XX_CP_SCRATCH_GLOBAL(3)), + }; + + if (info) + block = a8xx_fault_block(gpu, info->fsynr1 & 0xff); + + return adreno_fault_handler(gpu, iova, flags, info, block, scratch); +} + +static void a8xx_cp_hw_err_irq(struct msm_gpu *gpu) +{ + u32 status = gpu_read(gpu, REG_A8XX_CP_INTERRUPT_STATUS_GLOBAL); + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + u32 slice = a8xx_get_first_slice(a6xx_gpu); + u32 hw_fault_mask = GENMASK(6, 0); + u32 sw_fault_mask = GENMASK(22, 16); + u32 pipe = 0; + + dev_err_ratelimited(&gpu->pdev->dev, "CP Fault Global INT status: 0x%x\n", status); + + if (status & (A8XX_CP_GLOBAL_INT_MASK_HWFAULTBR | + A8XX_CP_GLOBAL_INT_MASK_SWFAULTBR)) + pipe |= BIT(PIPE_BR); + + if (status & (A8XX_CP_GLOBAL_INT_MASK_HWFAULTBV | + A8XX_CP_GLOBAL_INT_MASK_SWFAULTBV)) + pipe |= BIT(PIPE_BV); + + if (!pipe) { + dev_err_ratelimited(&gpu->pdev->dev, "CP Fault Unknown pipe\n"); + goto out; + } + + for (unsigned int pipe_id = PIPE_NONE; pipe_id <= PIPE_DDE_BV; pipe_id++) { + if (!(BIT(pipe_id) & pipe)) + continue; + + if (hw_fault_mask & status) { + status = a8xx_read_pipe_slice(gpu, pipe_id, slice, + REG_A8XX_CP_HW_FAULT_STATUS_PIPE); + dev_err_ratelimited(&gpu->pdev->dev, + "CP HW FAULT pipe: %u status: 0x%x\n", pipe_id, status); + } + + if (sw_fault_mask & status) { + status = a8xx_read_pipe_slice(gpu, pipe_id, slice, + REG_A8XX_CP_INTERRUPT_STATUS_PIPE); + dev_err_ratelimited(&gpu->pdev->dev, + "CP SW FAULT pipe: %u status: 0x%x\n", pipe_id, status); + + if (status & BIT(8)) { + a8xx_write_pipe(gpu, pipe_id, REG_A8XX_CP_SQE_STAT_ADDR_PIPE, 1); + status = a8xx_read_pipe_slice(gpu, pipe_id, slice, + REG_A8XX_CP_SQE_STAT_DATA_PIPE); + dev_err_ratelimited(&gpu->pdev->dev, + "CP Opcode error, opcode=0x%x\n", status); + } + + if (status & BIT(10)) { + status = a8xx_read_pipe_slice(gpu, pipe_id, slice, + REG_A8XX_CP_PROTECT_STATUS_PIPE); + dev_err_ratelimited(&gpu->pdev->dev, + "CP REG PROTECT error, status=0x%x\n", status); + } + } + } + +out: + /* Turn off interrupts to avoid triggering recovery again */ + a8xx_aperture_clear(gpu); + gpu_write(gpu, REG_A8XX_CP_INTERRUPT_STATUS_MASK_GLOBAL, 0); + gpu_write(gpu, REG_A8XX_RBBM_INT_0_MASK, 0); + + kthread_queue_work(gpu->worker, &gpu->recover_work); +} + +static u32 gpu_periph_read(struct msm_gpu *gpu, u32 dbg_offset) +{ + gpu_write(gpu, REG_A8XX_CP_SQE_UCODE_DBG_ADDR_PIPE, dbg_offset); + + return gpu_read(gpu, REG_A8XX_CP_SQE_UCODE_DBG_DATA_PIPE); +} + +static u64 gpu_periph_read64(struct msm_gpu *gpu, u32 dbg_offset) +{ + u64 lo, hi; + + lo = gpu_periph_read(gpu, dbg_offset); + hi = gpu_periph_read(gpu, dbg_offset + 1); + + return (hi << 32) | lo; +} + +#define CP_PERIPH_IB1_BASE_LO 0x7005 +#define CP_PERIPH_IB1_BASE_HI 0x7006 +#define CP_PERIPH_IB1_SIZE 0x7007 +#define CP_PERIPH_IB1_OFFSET 0x7008 +#define CP_PERIPH_IB2_BASE_LO 0x7009 +#define CP_PERIPH_IB2_BASE_HI 0x700a +#define CP_PERIPH_IB2_SIZE 0x700b +#define CP_PERIPH_IB2_OFFSET 0x700c +#define CP_PERIPH_IB3_BASE_LO 0x700d +#define CP_PERIPH_IB3_BASE_HI 0x700e +#define CP_PERIPH_IB3_SIZE 0x700f +#define CP_PERIPH_IB3_OFFSET 0x7010 + +static void a8xx_fault_detect_irq(struct msm_gpu *gpu) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + struct msm_ringbuffer *ring = gpu->funcs->active_ring(gpu); + unsigned long flags; + + /* + * If stalled on SMMU fault, we could trip the GPU's hang detection, + * but the fault handler will trigger the devcore dump, and we want + * to otherwise resume normally rather than killing the submit, so + * just bail. + */ + if (gpu_read(gpu, REG_A8XX_RBBM_MISC_STATUS) & A8XX_RBBM_MISC_STATUS_SMMU_STALLED_ON_FAULT) + return; + + /* + * Force the GPU to stay on until after we finish + * collecting information + */ + if (!adreno_has_gmu_wrapper(adreno_gpu)) + gmu_write(&a6xx_gpu->gmu, REG_A6XX_GMU_GMU_PWR_COL_KEEPALIVE, 1); + + DRM_DEV_ERROR(&gpu->pdev->dev, + "gpu fault ring %d fence %x status %8.8X gfx_status %8.8X\n", + ring ? ring->id : -1, ring ? ring->fctx->last_fence : 0, + gpu_read(gpu, REG_A8XX_RBBM_STATUS), gpu_read(gpu, REG_A8XX_RBBM_GFX_STATUS)); + + a8xx_aperture_acquire(gpu, PIPE_BR, &flags); + + DRM_DEV_ERROR(&gpu->pdev->dev, + "BR: status %8.8X rb %4.4x/%4.4x ib1 %16.16llX/%4.4x ib2 %16.16llX/%4.4x ib3 %16.16llX/%4.4x\n", + gpu_read(gpu, REG_A8XX_RBBM_GFX_BR_STATUS), + gpu_read(gpu, REG_A6XX_CP_RB_RPTR), + gpu_read(gpu, REG_A6XX_CP_RB_WPTR), + gpu_periph_read64(gpu, CP_PERIPH_IB1_BASE_LO), + gpu_periph_read(gpu, CP_PERIPH_IB1_OFFSET), + gpu_periph_read64(gpu, CP_PERIPH_IB2_BASE_LO), + gpu_periph_read(gpu, CP_PERIPH_IB2_OFFSET), + gpu_periph_read64(gpu, CP_PERIPH_IB3_BASE_LO), + gpu_periph_read(gpu, CP_PERIPH_IB3_OFFSET)); + + a8xx_aperture_release(gpu, flags); + a8xx_aperture_acquire(gpu, PIPE_BV, &flags); + + DRM_DEV_ERROR(&gpu->pdev->dev, + "BV: status %8.8X rb %4.4x/%4.4x ib1 %16.16llX/%4.4x ib2 %16.16llX/%4.4x ib3 %16.16llX/%4.4x\n", + gpu_read(gpu, REG_A8XX_RBBM_GFX_BV_STATUS), + gpu_read(gpu, REG_A8XX_CP_RB_RPTR_BV), + gpu_read(gpu, REG_A6XX_CP_RB_WPTR), + gpu_periph_read64(gpu, CP_PERIPH_IB1_BASE_LO), + gpu_periph_read(gpu, CP_PERIPH_IB1_OFFSET), + gpu_periph_read64(gpu, CP_PERIPH_IB2_BASE_LO), + gpu_periph_read(gpu, CP_PERIPH_IB2_OFFSET), + gpu_periph_read64(gpu, CP_PERIPH_IB3_BASE_LO), + gpu_periph_read(gpu, CP_PERIPH_IB3_OFFSET)); + + a8xx_aperture_release(gpu, flags); + a8xx_aperture_clear(gpu); + + /* Turn off the hangcheck timer to keep it from bothering us */ + timer_delete(&gpu->hangcheck_timer); + + kthread_queue_work(gpu->worker, &gpu->recover_work); +} + +static void a8xx_sw_fuse_violation_irq(struct msm_gpu *gpu) +{ + u32 status; + + status = gpu_read(gpu, REG_A8XX_RBBM_SW_FUSE_INT_STATUS); + gpu_write(gpu, REG_A8XX_RBBM_SW_FUSE_INT_MASK, 0); + + dev_err_ratelimited(&gpu->pdev->dev, "SW fuse violation status=%8.8x\n", status); + + /* + * Ignore FASTBLEND violations, because the HW will silently fall back + * to legacy blending. + */ + if (status & (A7XX_CX_MISC_SW_FUSE_VALUE_RAYTRACING | + A7XX_CX_MISC_SW_FUSE_VALUE_LPAC)) { + timer_delete(&gpu->hangcheck_timer); + + kthread_queue_work(gpu->worker, &gpu->recover_work); + } +} + +irqreturn_t a8xx_irq(struct msm_gpu *gpu) +{ + struct msm_drm_private *priv = gpu->dev->dev_private; + u32 status = gpu_read(gpu, REG_A8XX_RBBM_INT_0_STATUS); + + gpu_write(gpu, REG_A8XX_RBBM_INT_CLEAR_CMD, status); + + if (priv->disable_err_irq) + status &= A6XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS; + + if (status & A6XX_RBBM_INT_0_MASK_RBBM_HANG_DETECT) + a8xx_fault_detect_irq(gpu); + + if (status & A6XX_RBBM_INT_0_MASK_CP_AHB_ERROR) { + u32 rl0, rl1; + + rl0 = gpu_read(gpu, REG_A8XX_CP_RL_ERROR_DETAILS_0); + rl1 = gpu_read(gpu, REG_A8XX_CP_RL_ERROR_DETAILS_1); + dev_err_ratelimited(&gpu->pdev->dev, + "CP | AHB bus error RL_ERROR_0: %x, RL_ERROR_1: %x\n", rl0, rl1); + } + + if (status & A6XX_RBBM_INT_0_MASK_CP_HW_ERROR) + a8xx_cp_hw_err_irq(gpu); + + if (status & A6XX_RBBM_INT_0_MASK_RBBM_ATB_ASYNCFIFO_OVERFLOW) + dev_err_ratelimited(&gpu->pdev->dev, "RBBM | ATB ASYNC overflow\n"); + + if (status & A6XX_RBBM_INT_0_MASK_RBBM_ATB_BUS_OVERFLOW) + dev_err_ratelimited(&gpu->pdev->dev, "RBBM | ATB bus overflow\n"); + + if (status & A6XX_RBBM_INT_0_MASK_UCHE_OOB_ACCESS) + dev_err_ratelimited(&gpu->pdev->dev, "UCHE | Out of bounds access\n"); + + if (status & A6XX_RBBM_INT_0_MASK_UCHE_TRAP_INTR) + dev_err_ratelimited(&gpu->pdev->dev, "UCHE | Trap interrupt\n"); + + if (status & A6XX_RBBM_INT_0_MASK_SWFUSEVIOLATION) + a8xx_sw_fuse_violation_irq(gpu); + + if (status & A6XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS) { + msm_gpu_retire(gpu); + a6xx_preempt_trigger(gpu); + } + + if (status & A6XX_RBBM_INT_0_MASK_CP_SW) + a6xx_preempt_irq(gpu); + + return IRQ_HANDLED; +} + +void a8xx_llc_activate(struct a6xx_gpu *a6xx_gpu) +{ + struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; + struct msm_gpu *gpu = &adreno_gpu->base; + + if (!llcc_slice_activate(a6xx_gpu->llc_slice)) { + u32 gpu_scid = llcc_get_slice_id(a6xx_gpu->llc_slice); + + gpu_scid &= GENMASK(5, 0); + + gpu_write(gpu, REG_A6XX_GBIF_SCACHE_CNTL1, + FIELD_PREP(GENMASK(29, 24), gpu_scid) | + FIELD_PREP(GENMASK(23, 18), gpu_scid) | + FIELD_PREP(GENMASK(17, 12), gpu_scid) | + FIELD_PREP(GENMASK(11, 6), gpu_scid) | + FIELD_PREP(GENMASK(5, 0), gpu_scid)); + + gpu_write(gpu, REG_A6XX_GBIF_SCACHE_CNTL0, + FIELD_PREP(GENMASK(27, 22), gpu_scid) | + FIELD_PREP(GENMASK(21, 16), gpu_scid) | + FIELD_PREP(GENMASK(15, 10), gpu_scid) | + BIT(8)); + } + + llcc_slice_activate(a6xx_gpu->htw_llc_slice); +} + +#define GBIF_CLIENT_HALT_MASK BIT(0) +#define GBIF_ARB_HALT_MASK BIT(1) +#define VBIF_XIN_HALT_CTRL0_MASK GENMASK(3, 0) +#define VBIF_RESET_ACK_MASK 0xF0 +#define GPR0_GBIF_HALT_REQUEST 0x1E0 + +void a8xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu, bool gx_off) +{ + struct msm_gpu *gpu = &adreno_gpu->base; + + if (gx_off) { + /* Halt the gx side of GBIF */ + gpu_write(gpu, REG_A8XX_RBBM_GBIF_HALT, 1); + spin_until(gpu_read(gpu, REG_A8XX_RBBM_GBIF_HALT_ACK) & 1); + } + + /* Halt new client requests on GBIF */ + gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_CLIENT_HALT_MASK); + spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) & + (GBIF_CLIENT_HALT_MASK)) == GBIF_CLIENT_HALT_MASK); + + /* Halt all AXI requests on GBIF */ + gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_ARB_HALT_MASK); + spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) & + (GBIF_ARB_HALT_MASK)) == GBIF_ARB_HALT_MASK); + + /* The GBIF halt needs to be explicitly cleared */ + gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0); +} + +int a8xx_gmu_get_timestamp(struct msm_gpu *gpu, uint64_t *value) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + + mutex_lock(&a6xx_gpu->gmu.lock); + + /* Force the GPU power on so we can read this register */ + a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET); + + *value = gpu_read64(gpu, REG_A8XX_CP_ALWAYS_ON_COUNTER); + + a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET); + + mutex_unlock(&a6xx_gpu->gmu.lock); + + return 0; +} + +u64 a8xx_gpu_busy(struct msm_gpu *gpu, unsigned long *out_sample_rate) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + u64 busy_cycles; + + /* 19.2MHz */ + *out_sample_rate = 19200000; + + busy_cycles = gmu_read64(&a6xx_gpu->gmu, + REG_A8XX_GMU_CX_GMU_POWER_COUNTER_XOCLK_0_L, + REG_A8XX_GMU_CX_GMU_POWER_COUNTER_XOCLK_0_H); + + return busy_cycles; +} + +bool a8xx_progress(struct msm_gpu *gpu, struct msm_ringbuffer *ring) +{ + return true; +} diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c index 28f744f3caf7..554d746f115b 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_device.c +++ b/drivers/gpu/drm/msm/adreno/adreno_device.c @@ -34,6 +34,7 @@ extern const struct adreno_gpulist a4xx_gpulist; extern const struct adreno_gpulist a5xx_gpulist; extern const struct adreno_gpulist a6xx_gpulist; extern const struct adreno_gpulist a7xx_gpulist; +extern const struct adreno_gpulist a8xx_gpulist; static const struct adreno_gpulist *gpulists[] = { &a2xx_gpulist, @@ -42,6 +43,7 @@ static const struct adreno_gpulist *gpulists[] = { &a5xx_gpulist, &a6xx_gpulist, &a7xx_gpulist, + &a8xx_gpulist, }; static const struct adreno_info *adreno_info(uint32_t chip_id) @@ -235,7 +237,7 @@ static int adreno_bind(struct device *dev, struct device *master, void *data) priv->has_cached_coherent = !!(info->quirks & ADRENO_QUIRK_HAS_CACHED_COHERENT); - gpu = info->init(drm); + gpu = info->funcs->init(drm); if (IS_ERR(gpu)) { dev_warn(drm->dev, "failed to load adreno gpu\n"); return PTR_ERR(gpu); diff --git a/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h b/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h index 04b49d385f9d..d513e03fef08 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gen7_0_0_snapshot.h @@ -82,85 +82,85 @@ static const u32 gen7_0_0_debugbus_blocks[] = { }; static const struct gen7_shader_block gen7_0_0_shader_blocks[] = { - {A7XX_TP0_TMO_DATA, 0x200, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_TP0_SMO_DATA, 0x80, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_TP0_MIPMAP_BASE_DATA, 0x3c0, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_INST_DATA, 0x800, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_INST_DATA_1, 0x800, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_0_DATA, 0x800, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_1_DATA, 0x800, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_2_DATA, 0x800, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_3_DATA, 0x800, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_4_DATA, 0x800, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_5_DATA, 0x800, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_6_DATA, 0x800, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_7_DATA, 0x800, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_CB_RAM, 0x390, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_INST_TAG, 0x90, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_INST_DATA_2, 0x200, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_TMO_TAG, 0x80, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_SMO_TAG, 0x80, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_STATE_DATA, 0x40, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_HWAVE_RAM, 0x100, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_L0_INST_BUF, 0x50, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_8_DATA, 0x800, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_9_DATA, 0x800, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_10_DATA, 0x800, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_11_DATA, 0x800, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_12_DATA, 0x200, 4, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_HLSQ_CVS_BE_CTXT_BUF_RAM_TAG, 0x10, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CVS_BE_CTXT_BUF_RAM_TAG, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CPS_BE_CTXT_BUF_RAM_TAG, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CVS_BE_CTXT_BUF_RAM, 0x300, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CVS_BE_CTXT_BUF_RAM, 0x300, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CPS_BE_CTXT_BUF_RAM, 0x300, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CVS_RAM, 0x1c0, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CVS_RAM, 0x1c0, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CPS_RAM, 0x300, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CPS_RAM, 0x300, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CVS_RAM_TAG, 0x40, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CVS_RAM_TAG, 0x40, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CPS_RAM_TAG, 0x40, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CPS_RAM_TAG, 0x40, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_ICB_CVS_CB_BASE_TAG, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_ICB_CVS_CB_BASE_TAG, 0x10, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_ICB_CPS_CB_BASE_TAG, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_ICB_CPS_CB_BASE_TAG, 0x10, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CVS_MISC_RAM, 0x280, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CVS_MISC_RAM, 0x280, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CPS_MISC_RAM, 0x800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CPS_MISC_RAM, 0x800, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CPS_MISC_RAM_1, 0x200, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INST_RAM, 0x800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INST_RAM, 0x800, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INST_RAM, 0x800, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CVS_CONST_RAM, 0x800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CVS_CONST_RAM, 0x800, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CPS_CONST_RAM, 0x800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CPS_CONST_RAM, 0x800, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CVS_MISC_RAM_TAG, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CVS_MISC_RAM_TAG, 0x10, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CPS_MISC_RAM_TAG, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CPS_MISC_RAM_TAG, 0x10, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INST_RAM_TAG, 0x80, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INST_RAM_TAG, 0x80, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INST_RAM_TAG, 0x80, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CVS_CONST_RAM_TAG, 0x64, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CVS_CONST_RAM_TAG, 0x64, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CPS_CONST_RAM_TAG, 0x64, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CPS_CONST_RAM_TAG, 0x64, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INST_RAM_1, 0x800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_STPROC_META, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_BV_BE_META, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_BV_BE_META, 0x10, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_DATAPATH_META, 0x20, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_FRONTEND_META, 0x40, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_FRONTEND_META, 0x40, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_FRONTEND_META, 0x40, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INDIRECT_META, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_BACKEND_META, 0x40, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_BACKEND_META, 0x40, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_BACKEND_META, 0x40, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_TP0_TMO_DATA, 0x200, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_TP0_SMO_DATA, 0x80, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_TP0_MIPMAP_BASE_DATA, 0x3c0, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_INST_DATA, 0x800, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_INST_DATA_1, 0x800, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_0_DATA, 0x800, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_1_DATA, 0x800, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_2_DATA, 0x800, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_3_DATA, 0x800, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_4_DATA, 0x800, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_5_DATA, 0x800, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_6_DATA, 0x800, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_7_DATA, 0x800, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_CB_RAM, 0x390, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_INST_TAG, 0x90, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_INST_DATA_2, 0x200, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_TMO_TAG, 0x80, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_SMO_TAG, 0x80, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_STATE_DATA, 0x40, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_HWAVE_RAM, 0x100, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_L0_INST_BUF, 0x50, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_8_DATA, 0x800, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_9_DATA, 0x800, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_10_DATA, 0x800, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_11_DATA, 0x800, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_12_DATA, 0x200, 4, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_HLSQ_CVS_BE_CTXT_BUF_RAM_TAG, 0x10, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CVS_BE_CTXT_BUF_RAM_TAG, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CPS_BE_CTXT_BUF_RAM_TAG, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CVS_BE_CTXT_BUF_RAM, 0x300, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CVS_BE_CTXT_BUF_RAM, 0x300, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CPS_BE_CTXT_BUF_RAM, 0x300, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CVS_RAM, 0x1c0, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CVS_RAM, 0x1c0, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CPS_RAM, 0x300, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CPS_RAM, 0x300, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CVS_RAM_TAG, 0x40, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CVS_RAM_TAG, 0x40, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CPS_RAM_TAG, 0x40, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CPS_RAM_TAG, 0x40, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_ICB_CVS_CB_BASE_TAG, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_ICB_CVS_CB_BASE_TAG, 0x10, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_ICB_CPS_CB_BASE_TAG, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_ICB_CPS_CB_BASE_TAG, 0x10, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CVS_MISC_RAM, 0x280, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CVS_MISC_RAM, 0x280, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CPS_MISC_RAM, 0x800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CPS_MISC_RAM, 0x800, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CPS_MISC_RAM_1, 0x200, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INST_RAM, 0x800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INST_RAM, 0x800, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INST_RAM, 0x800, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CVS_CONST_RAM, 0x800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CVS_CONST_RAM, 0x800, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CPS_CONST_RAM, 0x800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CPS_CONST_RAM, 0x800, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CVS_MISC_RAM_TAG, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CVS_MISC_RAM_TAG, 0x10, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CPS_MISC_RAM_TAG, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CPS_MISC_RAM_TAG, 0x10, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INST_RAM_TAG, 0x80, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INST_RAM_TAG, 0x80, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INST_RAM_TAG, 0x80, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CVS_CONST_RAM_TAG, 0x64, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CVS_CONST_RAM_TAG, 0x64, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CPS_CONST_RAM_TAG, 0x64, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CPS_CONST_RAM_TAG, 0x64, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INST_RAM_1, 0x800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_STPROC_META, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_BV_BE_META, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_BV_BE_META, 0x10, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_DATAPATH_META, 0x20, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_FRONTEND_META, 0x40, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_FRONTEND_META, 0x40, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_FRONTEND_META, 0x40, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INDIRECT_META, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_BACKEND_META, 0x40, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_BACKEND_META, 0x40, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_BACKEND_META, 0x40, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, }; static const u32 gen7_0_0_pre_crashdumper_gpu_registers[] = { @@ -303,7 +303,7 @@ static const u32 gen7_0_0_noncontext_rb_rbp_pipe_br_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_noncontext_rb_rbp_pipe_br_registers), 8)); -/* Block: GRAS Cluster: A7XX_CLUSTER_GRAS Pipeline: A7XX_PIPE_BR */ +/* Block: GRAS Cluster: A7XX_CLUSTER_GRAS Pipeline: PIPE_BR */ static const u32 gen7_0_0_gras_cluster_gras_pipe_br_registers[] = { 0x08000, 0x08008, 0x08010, 0x08092, 0x08094, 0x08099, 0x0809b, 0x0809d, 0x080a0, 0x080a7, 0x080af, 0x080f1, 0x080f4, 0x080f6, 0x080f8, 0x080fa, @@ -313,7 +313,7 @@ static const u32 gen7_0_0_gras_cluster_gras_pipe_br_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_gras_cluster_gras_pipe_br_registers), 8)); -/* Block: GRAS Cluster: A7XX_CLUSTER_GRAS Pipeline: A7XX_PIPE_BV */ +/* Block: GRAS Cluster: A7XX_CLUSTER_GRAS Pipeline: PIPE_BV */ static const u32 gen7_0_0_gras_cluster_gras_pipe_bv_registers[] = { 0x08000, 0x08008, 0x08010, 0x08092, 0x08094, 0x08099, 0x0809b, 0x0809d, 0x080a0, 0x080a7, 0x080af, 0x080f1, 0x080f4, 0x080f6, 0x080f8, 0x080fa, @@ -323,7 +323,7 @@ static const u32 gen7_0_0_gras_cluster_gras_pipe_bv_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_gras_cluster_gras_pipe_bv_registers), 8)); -/* Block: PC Cluster: A7XX_CLUSTER_FE Pipeline: A7XX_PIPE_BR */ +/* Block: PC Cluster: A7XX_CLUSTER_FE Pipeline: PIPE_BR */ static const u32 gen7_0_0_pc_cluster_fe_pipe_br_registers[] = { 0x09800, 0x09804, 0x09806, 0x0980a, 0x09810, 0x09811, 0x09884, 0x09886, 0x09b00, 0x09b08, @@ -331,7 +331,7 @@ static const u32 gen7_0_0_pc_cluster_fe_pipe_br_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_pc_cluster_fe_pipe_br_registers), 8)); -/* Block: PC Cluster: A7XX_CLUSTER_FE Pipeline: A7XX_PIPE_BV */ +/* Block: PC Cluster: A7XX_CLUSTER_FE Pipeline: PIPE_BV */ static const u32 gen7_0_0_pc_cluster_fe_pipe_bv_registers[] = { 0x09800, 0x09804, 0x09806, 0x0980a, 0x09810, 0x09811, 0x09884, 0x09886, 0x09b00, 0x09b08, @@ -339,7 +339,7 @@ static const u32 gen7_0_0_pc_cluster_fe_pipe_bv_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_pc_cluster_fe_pipe_bv_registers), 8)); -/* Block: RB_RAC Cluster: A7XX_CLUSTER_PS Pipeline: A7XX_PIPE_BR */ +/* Block: RB_RAC Cluster: A7XX_CLUSTER_PS Pipeline: PIPE_BR */ static const u32 gen7_0_0_rb_rac_cluster_ps_pipe_br_registers[] = { 0x08802, 0x08802, 0x08804, 0x08806, 0x08809, 0x0880a, 0x0880e, 0x08811, 0x08818, 0x0881e, 0x08821, 0x08821, 0x08823, 0x08826, 0x08829, 0x08829, @@ -355,7 +355,7 @@ static const u32 gen7_0_0_rb_rac_cluster_ps_pipe_br_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_rb_rac_cluster_ps_pipe_br_registers), 8)); -/* Block: RB_RBP Cluster: A7XX_CLUSTER_PS Pipeline: A7XX_PIPE_BR */ +/* Block: RB_RBP Cluster: A7XX_CLUSTER_PS Pipeline: PIPE_BR */ static const u32 gen7_0_0_rb_rbp_cluster_ps_pipe_br_registers[] = { 0x08800, 0x08801, 0x08803, 0x08803, 0x0880b, 0x0880d, 0x08812, 0x08812, 0x08820, 0x08820, 0x08822, 0x08822, 0x08827, 0x08828, 0x0882a, 0x0882a, @@ -370,7 +370,7 @@ static const u32 gen7_0_0_rb_rbp_cluster_ps_pipe_br_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_rb_rbp_cluster_ps_pipe_br_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: A7XX_PIPE_BR Location: HLSQ_STATE */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: PIPE_BR Location: HLSQ_STATE */ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_state_registers[] = { 0x0a980, 0x0a980, 0x0a982, 0x0a984, 0x0a99e, 0x0a99e, 0x0a9a7, 0x0a9a7, 0x0a9aa, 0x0a9aa, 0x0a9ae, 0x0a9b0, 0x0a9b3, 0x0a9b5, 0x0a9ba, 0x0a9ba, @@ -381,7 +381,7 @@ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_state_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_state_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: A7XX_PIPE_LPAC Location: HLSQ_STATE */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: PIPE_LPAC Location: HLSQ_STATE */ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_lpac_hlsq_state_registers[] = { 0x0a9b0, 0x0a9b0, 0x0a9b3, 0x0a9b5, 0x0a9ba, 0x0a9ba, 0x0a9bc, 0x0a9bc, 0x0a9c4, 0x0a9c4, 0x0a9cd, 0x0a9cd, 0x0a9e2, 0x0a9e3, 0x0a9e6, 0x0a9fc, @@ -390,21 +390,21 @@ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_lpac_hlsq_state_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_ps_pipe_lpac_hlsq_state_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: A7XX_PIPE_BR Location: HLSQ_DP */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: PIPE_BR Location: HLSQ_DP */ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_dp_registers[] = { 0x0a9b1, 0x0a9b1, 0x0a9c6, 0x0a9cb, 0x0a9d4, 0x0a9df, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_dp_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: A7XX_PIPE_LPAC Location: HLSQ_DP */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: PIPE_LPAC Location: HLSQ_DP */ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_lpac_hlsq_dp_registers[] = { 0x0a9b1, 0x0a9b1, 0x0a9d4, 0x0a9df, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_ps_pipe_lpac_hlsq_dp_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: A7XX_PIPE_BR Location: SP_TOP */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: PIPE_BR Location: SP_TOP */ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_br_sp_top_registers[] = { 0x0a980, 0x0a980, 0x0a982, 0x0a984, 0x0a99e, 0x0a9a2, 0x0a9a7, 0x0a9a8, 0x0a9aa, 0x0a9aa, 0x0a9ae, 0x0a9ae, 0x0a9b0, 0x0a9b1, 0x0a9b3, 0x0a9b5, @@ -414,7 +414,7 @@ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_br_sp_top_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_ps_pipe_br_sp_top_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: A7XX_PIPE_LPAC Location: SP_TOP */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: PIPE_LPAC Location: SP_TOP */ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_lpac_sp_top_registers[] = { 0x0a9b0, 0x0a9b1, 0x0a9b3, 0x0a9b5, 0x0a9ba, 0x0a9bc, 0x0a9e2, 0x0a9e3, 0x0a9e6, 0x0a9f9, 0x0aa00, 0x0aa00, 0x0ab00, 0x0ab00, @@ -422,7 +422,7 @@ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_lpac_sp_top_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_ps_pipe_lpac_sp_top_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: A7XX_PIPE_BR Location: uSPTP */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: PIPE_BR Location: uSPTP */ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_br_usptp_registers[] = { 0x0a980, 0x0a982, 0x0a985, 0x0a9a6, 0x0a9a8, 0x0a9a9, 0x0a9ab, 0x0a9ae, 0x0a9b0, 0x0a9b3, 0x0a9b6, 0x0a9b9, 0x0a9bb, 0x0a9bf, 0x0a9c2, 0x0a9c3, @@ -432,7 +432,7 @@ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_br_usptp_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_ps_pipe_br_usptp_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: A7XX_PIPE_LPAC Location: uSPTP */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: PIPE_LPAC Location: uSPTP */ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_lpac_usptp_registers[] = { 0x0a9b0, 0x0a9b3, 0x0a9b6, 0x0a9b9, 0x0a9bb, 0x0a9be, 0x0a9c2, 0x0a9c3, 0x0a9cd, 0x0a9cd, 0x0a9d0, 0x0a9d3, 0x0aa31, 0x0aa31, 0x0ab00, 0x0ab01, @@ -440,7 +440,7 @@ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_lpac_usptp_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_ps_pipe_lpac_usptp_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_VS Pipeline: A7XX_PIPE_BR Location: HLSQ_STATE */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_VS Pipeline: PIPE_BR Location: HLSQ_STATE */ static const u32 gen7_0_0_sp_cluster_sp_vs_pipe_br_hlsq_state_registers[] = { 0x0a800, 0x0a800, 0x0a81b, 0x0a81d, 0x0a822, 0x0a822, 0x0a824, 0x0a824, 0x0a827, 0x0a82a, 0x0a830, 0x0a830, 0x0a833, 0x0a835, 0x0a83a, 0x0a83a, @@ -453,7 +453,7 @@ static const u32 gen7_0_0_sp_cluster_sp_vs_pipe_br_hlsq_state_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_vs_pipe_br_hlsq_state_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_VS Pipeline: A7XX_PIPE_BV Location: HLSQ_STATE */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_VS Pipeline: PIPE_BV Location: HLSQ_STATE */ static const u32 gen7_0_0_sp_cluster_sp_vs_pipe_bv_hlsq_state_registers[] = { 0x0a800, 0x0a800, 0x0a81b, 0x0a81d, 0x0a822, 0x0a822, 0x0a824, 0x0a824, 0x0a827, 0x0a82a, 0x0a830, 0x0a830, 0x0a833, 0x0a835, 0x0a83a, 0x0a83a, @@ -466,7 +466,7 @@ static const u32 gen7_0_0_sp_cluster_sp_vs_pipe_bv_hlsq_state_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_vs_pipe_bv_hlsq_state_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_VS Pipeline: A7XX_PIPE_BR Location: SP_TOP */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_VS Pipeline: PIPE_BR Location: SP_TOP */ static const u32 gen7_0_0_sp_cluster_sp_vs_pipe_br_sp_top_registers[] = { 0x0a800, 0x0a800, 0x0a81c, 0x0a81d, 0x0a822, 0x0a824, 0x0a830, 0x0a831, 0x0a834, 0x0a835, 0x0a83a, 0x0a83c, 0x0a840, 0x0a840, 0x0a85c, 0x0a85d, @@ -477,7 +477,7 @@ static const u32 gen7_0_0_sp_cluster_sp_vs_pipe_br_sp_top_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_vs_pipe_br_sp_top_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_VS Pipeline: A7XX_PIPE_BV Location: SP_TOP */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_VS Pipeline: PIPE_BV Location: SP_TOP */ static const u32 gen7_0_0_sp_cluster_sp_vs_pipe_bv_sp_top_registers[] = { 0x0a800, 0x0a800, 0x0a81c, 0x0a81d, 0x0a822, 0x0a824, 0x0a830, 0x0a831, 0x0a834, 0x0a835, 0x0a83a, 0x0a83c, 0x0a840, 0x0a840, 0x0a85c, 0x0a85d, @@ -488,7 +488,7 @@ static const u32 gen7_0_0_sp_cluster_sp_vs_pipe_bv_sp_top_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_vs_pipe_bv_sp_top_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_VS Pipeline: A7XX_PIPE_BR Location: uSPTP */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_VS Pipeline: PIPE_BR Location: uSPTP */ static const u32 gen7_0_0_sp_cluster_sp_vs_pipe_br_usptp_registers[] = { 0x0a800, 0x0a81b, 0x0a81e, 0x0a821, 0x0a823, 0x0a827, 0x0a830, 0x0a833, 0x0a836, 0x0a839, 0x0a83b, 0x0a85b, 0x0a85e, 0x0a861, 0x0a863, 0x0a867, @@ -498,7 +498,7 @@ static const u32 gen7_0_0_sp_cluster_sp_vs_pipe_br_usptp_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_vs_pipe_br_usptp_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_VS Pipeline: A7XX_PIPE_BV Location: uSPTP */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_VS Pipeline: PIPE_BV Location: uSPTP */ static const u32 gen7_0_0_sp_cluster_sp_vs_pipe_bv_usptp_registers[] = { 0x0a800, 0x0a81b, 0x0a81e, 0x0a821, 0x0a823, 0x0a827, 0x0a830, 0x0a833, 0x0a836, 0x0a839, 0x0a83b, 0x0a85b, 0x0a85e, 0x0a861, 0x0a863, 0x0a867, @@ -508,7 +508,7 @@ static const u32 gen7_0_0_sp_cluster_sp_vs_pipe_bv_usptp_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_vs_pipe_bv_usptp_registers), 8)); -/* Block: TPL1 Cluster: A7XX_CLUSTER_SP_PS Pipeline: A7XX_PIPE_BR */ +/* Block: TPL1 Cluster: A7XX_CLUSTER_SP_PS Pipeline: PIPE_BR */ static const u32 gen7_0_0_tpl1_cluster_sp_ps_pipe_br_registers[] = { 0x0b180, 0x0b183, 0x0b190, 0x0b195, 0x0b2c0, 0x0b2d5, 0x0b300, 0x0b307, 0x0b309, 0x0b309, 0x0b310, 0x0b310, @@ -516,35 +516,35 @@ static const u32 gen7_0_0_tpl1_cluster_sp_ps_pipe_br_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_tpl1_cluster_sp_ps_pipe_br_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: A7XX_PIPE_BV Location: HLSQ_STATE */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: PIPE_BV Location: HLSQ_STATE */ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_bv_hlsq_state_registers[] = { 0x0ab00, 0x0ab02, 0x0ab0a, 0x0ab1b, 0x0ab20, 0x0ab20, 0x0ab40, 0x0abbf, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_ps_pipe_bv_hlsq_state_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: A7XX_PIPE_BV Location: SP_TOP */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: PIPE_BV Location: SP_TOP */ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_bv_sp_top_registers[] = { 0x0ab00, 0x0ab00, 0x0ab02, 0x0ab02, 0x0ab0a, 0x0ab1b, 0x0ab20, 0x0ab20, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_ps_pipe_bv_sp_top_registers), 8)); -/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: A7XX_PIPE_BV Location: uSPTP */ +/* Block: SP Cluster: A7XX_CLUSTER_SP_PS Pipeline: PIPE_BV Location: uSPTP */ static const u32 gen7_0_0_sp_cluster_sp_ps_pipe_bv_usptp_registers[] = { 0x0ab00, 0x0ab02, 0x0ab21, 0x0ab22, 0x0ab40, 0x0abbf, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_cluster_sp_ps_pipe_bv_usptp_registers), 8)); -/* Block: TPL1 Cluster: A7XX_CLUSTER_SP_PS Pipeline: A7XX_PIPE_BV */ +/* Block: TPL1 Cluster: A7XX_CLUSTER_SP_PS Pipeline: PIPE_BV */ static const u32 gen7_0_0_tpl1_cluster_sp_ps_pipe_bv_registers[] = { 0x0b300, 0x0b307, 0x0b309, 0x0b309, 0x0b310, 0x0b310, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_tpl1_cluster_sp_ps_pipe_bv_registers), 8)); -/* Block: TPL1 Cluster: A7XX_CLUSTER_SP_PS Pipeline: A7XX_PIPE_LPAC */ +/* Block: TPL1 Cluster: A7XX_CLUSTER_SP_PS Pipeline: PIPE_LPAC */ static const u32 gen7_0_0_tpl1_cluster_sp_ps_pipe_lpac_registers[] = { 0x0b180, 0x0b181, 0x0b300, 0x0b301, 0x0b307, 0x0b307, 0x0b309, 0x0b309, 0x0b310, 0x0b310, @@ -552,84 +552,84 @@ static const u32 gen7_0_0_tpl1_cluster_sp_ps_pipe_lpac_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_tpl1_cluster_sp_ps_pipe_lpac_registers), 8)); -/* Block: TPL1 Cluster: A7XX_CLUSTER_SP_VS Pipeline: A7XX_PIPE_BR */ +/* Block: TPL1 Cluster: A7XX_CLUSTER_SP_VS Pipeline: PIPE_BR */ static const u32 gen7_0_0_tpl1_cluster_sp_vs_pipe_br_registers[] = { 0x0b300, 0x0b307, 0x0b309, 0x0b309, 0x0b310, 0x0b310, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_tpl1_cluster_sp_vs_pipe_br_registers), 8)); -/* Block: TPL1 Cluster: A7XX_CLUSTER_SP_VS Pipeline: A7XX_PIPE_BV */ +/* Block: TPL1 Cluster: A7XX_CLUSTER_SP_VS Pipeline: PIPE_BV */ static const u32 gen7_0_0_tpl1_cluster_sp_vs_pipe_bv_registers[] = { 0x0b300, 0x0b307, 0x0b309, 0x0b309, 0x0b310, 0x0b310, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_tpl1_cluster_sp_vs_pipe_bv_registers), 8)); -/* Block: VFD Cluster: A7XX_CLUSTER_FE Pipeline: A7XX_PIPE_BR */ +/* Block: VFD Cluster: A7XX_CLUSTER_FE Pipeline: PIPE_BR */ static const u32 gen7_0_0_vfd_cluster_fe_pipe_br_registers[] = { 0x0a000, 0x0a009, 0x0a00e, 0x0a0ef, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_vfd_cluster_fe_pipe_br_registers), 8)); -/* Block: VFD Cluster: A7XX_CLUSTER_FE Pipeline: A7XX_PIPE_BV */ +/* Block: VFD Cluster: A7XX_CLUSTER_FE Pipeline: PIPE_BV */ static const u32 gen7_0_0_vfd_cluster_fe_pipe_bv_registers[] = { 0x0a000, 0x0a009, 0x0a00e, 0x0a0ef, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_vfd_cluster_fe_pipe_bv_registers), 8)); -/* Block: VPC Cluster: A7XX_CLUSTER_FE Pipeline: A7XX_PIPE_BR */ +/* Block: VPC Cluster: A7XX_CLUSTER_FE Pipeline: PIPE_BR */ static const u32 gen7_0_0_vpc_cluster_fe_pipe_br_registers[] = { 0x09300, 0x09307, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_vpc_cluster_fe_pipe_br_registers), 8)); -/* Block: VPC Cluster: A7XX_CLUSTER_FE Pipeline: A7XX_PIPE_BV */ +/* Block: VPC Cluster: A7XX_CLUSTER_FE Pipeline: PIPE_BV */ static const u32 gen7_0_0_vpc_cluster_fe_pipe_bv_registers[] = { 0x09300, 0x09307, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_vpc_cluster_fe_pipe_bv_registers), 8)); -/* Block: VPC Cluster: A7XX_CLUSTER_PC_VS Pipeline: A7XX_PIPE_BR */ +/* Block: VPC Cluster: A7XX_CLUSTER_PC_VS Pipeline: PIPE_BR */ static const u32 gen7_0_0_vpc_cluster_pc_vs_pipe_br_registers[] = { 0x09101, 0x0910c, 0x09300, 0x09307, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_vpc_cluster_pc_vs_pipe_br_registers), 8)); -/* Block: VPC Cluster: A7XX_CLUSTER_PC_VS Pipeline: A7XX_PIPE_BV */ +/* Block: VPC Cluster: A7XX_CLUSTER_PC_VS Pipeline: PIPE_BV */ static const u32 gen7_0_0_vpc_cluster_pc_vs_pipe_bv_registers[] = { 0x09101, 0x0910c, 0x09300, 0x09307, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_vpc_cluster_pc_vs_pipe_bv_registers), 8)); -/* Block: VPC Cluster: A7XX_CLUSTER_VPC_PS Pipeline: A7XX_PIPE_BR */ +/* Block: VPC Cluster: A7XX_CLUSTER_VPC_PS Pipeline: PIPE_BR */ static const u32 gen7_0_0_vpc_cluster_vpc_ps_pipe_br_registers[] = { 0x09200, 0x0920f, 0x09212, 0x09216, 0x09218, 0x09236, 0x09300, 0x09307, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_vpc_cluster_vpc_ps_pipe_br_registers), 8)); -/* Block: VPC Cluster: A7XX_CLUSTER_VPC_PS Pipeline: A7XX_PIPE_BV */ +/* Block: VPC Cluster: A7XX_CLUSTER_VPC_PS Pipeline: PIPE_BV */ static const u32 gen7_0_0_vpc_cluster_vpc_ps_pipe_bv_registers[] = { 0x09200, 0x0920f, 0x09212, 0x09216, 0x09218, 0x09236, 0x09300, 0x09307, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_vpc_cluster_vpc_ps_pipe_bv_registers), 8)); -/* Block: SP Cluster: noncontext Pipeline: A7XX_PIPE_BR Location: HLSQ_STATE */ +/* Block: SP Cluster: noncontext Pipeline: PIPE_BR Location: HLSQ_STATE */ static const u32 gen7_0_0_sp_noncontext_pipe_br_hlsq_state_registers[] = { 0x0ae52, 0x0ae52, 0x0ae60, 0x0ae67, 0x0ae69, 0x0ae73, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_noncontext_pipe_br_hlsq_state_registers), 8)); -/* Block: SP Cluster: noncontext Pipeline: A7XX_PIPE_BR Location: SP_TOP */ +/* Block: SP Cluster: noncontext Pipeline: PIPE_BR Location: SP_TOP */ static const u32 gen7_0_0_sp_noncontext_pipe_br_sp_top_registers[] = { 0x0ae00, 0x0ae00, 0x0ae02, 0x0ae04, 0x0ae06, 0x0ae09, 0x0ae0c, 0x0ae0c, 0x0ae0f, 0x0ae0f, 0x0ae28, 0x0ae2b, 0x0ae35, 0x0ae35, 0x0ae3a, 0x0ae3f, @@ -638,7 +638,7 @@ static const u32 gen7_0_0_sp_noncontext_pipe_br_sp_top_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_noncontext_pipe_br_sp_top_registers), 8)); -/* Block: SP Cluster: noncontext Pipeline: A7XX_PIPE_BR Location: uSPTP */ +/* Block: SP Cluster: noncontext Pipeline: PIPE_BR Location: uSPTP */ static const u32 gen7_0_0_sp_noncontext_pipe_br_usptp_registers[] = { 0x0ae00, 0x0ae00, 0x0ae02, 0x0ae04, 0x0ae06, 0x0ae09, 0x0ae0c, 0x0ae0c, 0x0ae0f, 0x0ae0f, 0x0ae30, 0x0ae32, 0x0ae35, 0x0ae35, 0x0ae3a, 0x0ae3b, @@ -647,28 +647,28 @@ static const u32 gen7_0_0_sp_noncontext_pipe_br_usptp_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_noncontext_pipe_br_usptp_registers), 8)); -/* Block: SP Cluster: noncontext Pipeline: A7XX_PIPE_LPAC Location: HLSQ_STATE */ +/* Block: SP Cluster: noncontext Pipeline: PIPE_LPAC Location: HLSQ_STATE */ static const u32 gen7_0_0_sp_noncontext_pipe_lpac_hlsq_state_registers[] = { 0x0af88, 0x0af8a, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_noncontext_pipe_lpac_hlsq_state_registers), 8)); -/* Block: SP Cluster: noncontext Pipeline: A7XX_PIPE_LPAC Location: SP_TOP */ +/* Block: SP Cluster: noncontext Pipeline: PIPE_LPAC Location: SP_TOP */ static const u32 gen7_0_0_sp_noncontext_pipe_lpac_sp_top_registers[] = { 0x0af80, 0x0af84, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_noncontext_pipe_lpac_sp_top_registers), 8)); -/* Block: SP Cluster: noncontext Pipeline: A7XX_PIPE_LPAC Location: uSPTP */ +/* Block: SP Cluster: noncontext Pipeline: PIPE_LPAC Location: uSPTP */ static const u32 gen7_0_0_sp_noncontext_pipe_lpac_usptp_registers[] = { 0x0af80, 0x0af84, 0x0af90, 0x0af92, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_sp_noncontext_pipe_lpac_usptp_registers), 8)); -/* Block: TPl1 Cluster: noncontext Pipeline: A7XX_PIPE_NONE */ +/* Block: TPl1 Cluster: noncontext Pipeline: PIPE_NONE */ static const u32 gen7_0_0_tpl1_noncontext_pipe_none_registers[] = { 0x0b600, 0x0b600, 0x0b602, 0x0b602, 0x0b604, 0x0b604, 0x0b608, 0x0b60c, 0x0b60f, 0x0b621, 0x0b630, 0x0b633, @@ -676,14 +676,14 @@ static const u32 gen7_0_0_tpl1_noncontext_pipe_none_registers[] = { }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_tpl1_noncontext_pipe_none_registers), 8)); -/* Block: TPl1 Cluster: noncontext Pipeline: A7XX_PIPE_BR */ +/* Block: TPl1 Cluster: noncontext Pipeline: PIPE_BR */ static const u32 gen7_0_0_tpl1_noncontext_pipe_br_registers[] = { 0x0b600, 0x0b600, UINT_MAX, UINT_MAX, }; static_assert(IS_ALIGNED(sizeof(gen7_0_0_tpl1_noncontext_pipe_br_registers), 8)); -/* Block: TPl1 Cluster: noncontext Pipeline: A7XX_PIPE_LPAC */ +/* Block: TPl1 Cluster: noncontext Pipeline: PIPE_LPAC */ static const u32 gen7_0_0_tpl1_noncontext_pipe_lpac_registers[] = { 0x0b780, 0x0b780, UINT_MAX, UINT_MAX, @@ -691,184 +691,184 @@ static const u32 gen7_0_0_tpl1_noncontext_pipe_lpac_registers[] = { static_assert(IS_ALIGNED(sizeof(gen7_0_0_tpl1_noncontext_pipe_lpac_registers), 8)); static const struct gen7_sel_reg gen7_0_0_rb_rac_sel = { - .host_reg = REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_HOST, - .cd_reg = REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_CD, + .host_reg = REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_HOST, + .cd_reg = REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_CD, .val = 0x0, }; static const struct gen7_sel_reg gen7_0_0_rb_rbp_sel = { - .host_reg = REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_HOST, - .cd_reg = REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_CD, + .host_reg = REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_HOST, + .cd_reg = REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_CD, .val = 0x9, }; static const struct gen7_cluster_registers gen7_0_0_clusters[] = { - { A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT, + { A7XX_CLUSTER_NONE, PIPE_BR, STATE_NON_CONTEXT, gen7_0_0_noncontext_pipe_br_registers, }, - { A7XX_CLUSTER_NONE, A7XX_PIPE_BV, STATE_NON_CONTEXT, + { A7XX_CLUSTER_NONE, PIPE_BV, STATE_NON_CONTEXT, gen7_0_0_noncontext_pipe_bv_registers, }, - { A7XX_CLUSTER_NONE, A7XX_PIPE_LPAC, STATE_NON_CONTEXT, + { A7XX_CLUSTER_NONE, PIPE_LPAC, STATE_NON_CONTEXT, gen7_0_0_noncontext_pipe_lpac_registers, }, - { A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT, + { A7XX_CLUSTER_NONE, PIPE_BR, STATE_NON_CONTEXT, gen7_0_0_noncontext_rb_rac_pipe_br_registers, &gen7_0_0_rb_rac_sel, }, - { A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT, + { A7XX_CLUSTER_NONE, PIPE_BR, STATE_NON_CONTEXT, gen7_0_0_noncontext_rb_rbp_pipe_br_registers, &gen7_0_0_rb_rbp_sel, }, - { A7XX_CLUSTER_GRAS, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_GRAS, PIPE_BR, STATE_FORCE_CTXT_0, gen7_0_0_gras_cluster_gras_pipe_br_registers, }, - { A7XX_CLUSTER_GRAS, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_GRAS, PIPE_BV, STATE_FORCE_CTXT_0, gen7_0_0_gras_cluster_gras_pipe_bv_registers, }, - { A7XX_CLUSTER_GRAS, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_GRAS, PIPE_BR, STATE_FORCE_CTXT_1, gen7_0_0_gras_cluster_gras_pipe_br_registers, }, - { A7XX_CLUSTER_GRAS, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_GRAS, PIPE_BV, STATE_FORCE_CTXT_1, gen7_0_0_gras_cluster_gras_pipe_bv_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_0, gen7_0_0_pc_cluster_fe_pipe_br_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_0, gen7_0_0_pc_cluster_fe_pipe_bv_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_1, gen7_0_0_pc_cluster_fe_pipe_br_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_1, gen7_0_0_pc_cluster_fe_pipe_bv_registers, }, - { A7XX_CLUSTER_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_PS, PIPE_BR, STATE_FORCE_CTXT_0, gen7_0_0_rb_rac_cluster_ps_pipe_br_registers, &gen7_0_0_rb_rac_sel, }, - { A7XX_CLUSTER_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_PS, PIPE_BR, STATE_FORCE_CTXT_1, gen7_0_0_rb_rac_cluster_ps_pipe_br_registers, &gen7_0_0_rb_rac_sel, }, - { A7XX_CLUSTER_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_PS, PIPE_BR, STATE_FORCE_CTXT_0, gen7_0_0_rb_rbp_cluster_ps_pipe_br_registers, &gen7_0_0_rb_rbp_sel, }, - { A7XX_CLUSTER_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_PS, PIPE_BR, STATE_FORCE_CTXT_1, gen7_0_0_rb_rbp_cluster_ps_pipe_br_registers, &gen7_0_0_rb_rbp_sel, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_0, gen7_0_0_vfd_cluster_fe_pipe_br_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_0, gen7_0_0_vfd_cluster_fe_pipe_bv_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_1, gen7_0_0_vfd_cluster_fe_pipe_br_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_1, gen7_0_0_vfd_cluster_fe_pipe_bv_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_0, gen7_0_0_vpc_cluster_fe_pipe_br_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_0, gen7_0_0_vpc_cluster_fe_pipe_bv_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_1, gen7_0_0_vpc_cluster_fe_pipe_br_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_1, gen7_0_0_vpc_cluster_fe_pipe_bv_registers, }, - { A7XX_CLUSTER_PC_VS, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_PC_VS, PIPE_BR, STATE_FORCE_CTXT_0, gen7_0_0_vpc_cluster_pc_vs_pipe_br_registers, }, - { A7XX_CLUSTER_PC_VS, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_PC_VS, PIPE_BV, STATE_FORCE_CTXT_0, gen7_0_0_vpc_cluster_pc_vs_pipe_bv_registers, }, - { A7XX_CLUSTER_PC_VS, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_PC_VS, PIPE_BR, STATE_FORCE_CTXT_1, gen7_0_0_vpc_cluster_pc_vs_pipe_br_registers, }, - { A7XX_CLUSTER_PC_VS, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_PC_VS, PIPE_BV, STATE_FORCE_CTXT_1, gen7_0_0_vpc_cluster_pc_vs_pipe_bv_registers, }, - { A7XX_CLUSTER_VPC_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_VPC_PS, PIPE_BR, STATE_FORCE_CTXT_0, gen7_0_0_vpc_cluster_vpc_ps_pipe_br_registers, }, - { A7XX_CLUSTER_VPC_PS, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_VPC_PS, PIPE_BV, STATE_FORCE_CTXT_0, gen7_0_0_vpc_cluster_vpc_ps_pipe_bv_registers, }, - { A7XX_CLUSTER_VPC_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_VPC_PS, PIPE_BR, STATE_FORCE_CTXT_1, gen7_0_0_vpc_cluster_vpc_ps_pipe_br_registers, }, - { A7XX_CLUSTER_VPC_PS, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_VPC_PS, PIPE_BV, STATE_FORCE_CTXT_1, gen7_0_0_vpc_cluster_vpc_ps_pipe_bv_registers, }, }; static const struct gen7_sptp_cluster_registers gen7_0_0_sptp_clusters[] = { - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_BR, 0, A7XX_HLSQ_STATE, gen7_0_0_sp_noncontext_pipe_br_hlsq_state_registers, 0xae00 }, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_BR, 0, A7XX_SP_TOP, gen7_0_0_sp_noncontext_pipe_br_sp_top_registers, 0xae00 }, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_BR, 0, A7XX_USPTP, gen7_0_0_sp_noncontext_pipe_br_usptp_registers, 0xae00 }, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_LPAC, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_LPAC, 0, A7XX_HLSQ_STATE, gen7_0_0_sp_noncontext_pipe_lpac_hlsq_state_registers, 0xaf80 }, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_LPAC, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_LPAC, 0, A7XX_SP_TOP, gen7_0_0_sp_noncontext_pipe_lpac_sp_top_registers, 0xaf80 }, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_LPAC, 0, A7XX_USPTP, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_LPAC, 0, A7XX_USPTP, gen7_0_0_sp_noncontext_pipe_lpac_usptp_registers, 0xaf80 }, - { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, PIPE_BR, 0, A7XX_USPTP, gen7_0_0_tpl1_noncontext_pipe_br_registers, 0xb600 }, - { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_PIPE_LPAC, 0, A7XX_USPTP, + { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, PIPE_LPAC, 0, A7XX_USPTP, gen7_0_0_tpl1_noncontext_pipe_lpac_registers, 0xb780 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_HLSQ_STATE, gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_DP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_HLSQ_DP, gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_dp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_SP_TOP, gen7_0_0_sp_cluster_sp_ps_pipe_br_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_USPTP, gen7_0_0_sp_cluster_sp_ps_pipe_br_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_HLSQ_STATE, gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_HLSQ_DP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_HLSQ_DP, gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_dp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_SP_TOP, gen7_0_0_sp_cluster_sp_ps_pipe_br_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_USPTP, gen7_0_0_sp_cluster_sp_ps_pipe_br_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, A7XX_PIPE_BR, 2, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_HLSQ_STATE, gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, A7XX_PIPE_BR, 2, A7XX_HLSQ_DP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_HLSQ_DP, gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_dp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, A7XX_PIPE_BR, 2, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_SP_TOP, gen7_0_0_sp_cluster_sp_ps_pipe_br_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, A7XX_PIPE_BR, 2, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_USPTP, gen7_0_0_sp_cluster_sp_ps_pipe_br_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, A7XX_PIPE_BR, 3, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_HLSQ_STATE, gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, A7XX_PIPE_BR, 3, A7XX_HLSQ_DP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_HLSQ_DP, gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_dp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, A7XX_PIPE_BR, 3, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_SP_TOP, gen7_0_0_sp_cluster_sp_ps_pipe_br_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, A7XX_PIPE_BR, 3, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_USPTP, gen7_0_0_sp_cluster_sp_ps_pipe_br_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_LPAC, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_HLSQ_STATE, gen7_0_0_sp_cluster_sp_ps_pipe_lpac_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_LPAC, 0, A7XX_HLSQ_DP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_HLSQ_DP, gen7_0_0_sp_cluster_sp_ps_pipe_lpac_hlsq_dp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_LPAC, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_SP_TOP, gen7_0_0_sp_cluster_sp_ps_pipe_lpac_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_LPAC, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_USPTP, gen7_0_0_sp_cluster_sp_ps_pipe_lpac_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BR, 0, A7XX_HLSQ_STATE, gen7_0_0_sp_cluster_sp_vs_pipe_br_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BV, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BV, 0, A7XX_HLSQ_STATE, gen7_0_0_sp_cluster_sp_vs_pipe_bv_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BR, 0, A7XX_SP_TOP, gen7_0_0_sp_cluster_sp_vs_pipe_br_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BV, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BV, 0, A7XX_SP_TOP, gen7_0_0_sp_cluster_sp_vs_pipe_bv_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BR, 0, A7XX_USPTP, gen7_0_0_sp_cluster_sp_vs_pipe_br_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BV, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BV, 0, A7XX_USPTP, gen7_0_0_sp_cluster_sp_vs_pipe_bv_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BR, 1, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BR, 1, A7XX_HLSQ_STATE, gen7_0_0_sp_cluster_sp_vs_pipe_br_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BV, 1, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BV, 1, A7XX_HLSQ_STATE, gen7_0_0_sp_cluster_sp_vs_pipe_bv_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BR, 1, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BR, 1, A7XX_SP_TOP, gen7_0_0_sp_cluster_sp_vs_pipe_br_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BV, 1, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BV, 1, A7XX_SP_TOP, gen7_0_0_sp_cluster_sp_vs_pipe_bv_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BR, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BR, 1, A7XX_USPTP, gen7_0_0_sp_cluster_sp_vs_pipe_br_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BV, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BV, 1, A7XX_USPTP, gen7_0_0_sp_cluster_sp_vs_pipe_bv_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_ps_pipe_br_registers, 0xb000 }, - { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_ps_pipe_br_registers, 0xb000 }, - { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX2_3D_CPS_REG, A7XX_PIPE_BR, 2, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_ps_pipe_br_registers, 0xb000 }, - { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX3_3D_CPS_REG, A7XX_PIPE_BR, 3, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_ps_pipe_br_registers, 0xb000 }, - { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX0_3D_CPS_REG, A7XX_PIPE_LPAC, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_ps_pipe_lpac_registers, 0xb000 }, - { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX0_3D_CVS_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX0_3D_CVS_REG, PIPE_BR, 0, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_vs_pipe_br_registers, 0xb000 }, - { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX0_3D_CVS_REG, A7XX_PIPE_BV, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX0_3D_CVS_REG, PIPE_BV, 0, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_vs_pipe_bv_registers, 0xb000 }, - { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX1_3D_CVS_REG, A7XX_PIPE_BR, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX1_3D_CVS_REG, PIPE_BR, 1, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_vs_pipe_br_registers, 0xb000 }, - { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX1_3D_CVS_REG, A7XX_PIPE_BV, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX1_3D_CVS_REG, PIPE_BV, 1, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_vs_pipe_bv_registers, 0xb000 }, }; diff --git a/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h b/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h index 772652eb61f3..7897622ea6f7 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gen7_2_0_snapshot.h @@ -96,87 +96,87 @@ static const u32 gen7_2_0_debugbus_blocks[] = { }; static const struct gen7_shader_block gen7_2_0_shader_blocks[] = { - {A7XX_TP0_TMO_DATA, 0x200, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_TP0_SMO_DATA, 0x80, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_TP0_MIPMAP_BASE_DATA, 0x3c0, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_INST_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_INST_DATA_1, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_0_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_1_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_2_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_3_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_4_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_5_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_6_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_7_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_CB_RAM, 0x390, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_13_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_14_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_INST_TAG, 0xc0, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_INST_DATA_2, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_TMO_TAG, 0x80, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_SMO_TAG, 0x80, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_STATE_DATA, 0x40, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_HWAVE_RAM, 0x100, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_L0_INST_BUF, 0x50, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_8_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_9_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_10_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_11_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_SP_LB_12_DATA, 0x800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP}, - {A7XX_HLSQ_CVS_BE_CTXT_BUF_RAM_TAG, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CVS_BE_CTXT_BUF_RAM_TAG, 0x10, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CPS_BE_CTXT_BUF_RAM_TAG, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CVS_BE_CTXT_BUF_RAM, 0x300, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CVS_BE_CTXT_BUF_RAM, 0x300, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CPS_BE_CTXT_BUF_RAM, 0x300, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CVS_RAM, 0x1c0, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CVS_RAM, 0x1c0, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CPS_RAM, 0x300, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CPS_RAM, 0x180, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CVS_RAM_TAG, 0x40, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CVS_RAM_TAG, 0x40, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CPS_RAM_TAG, 0x40, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CHUNK_CPS_RAM_TAG, 0x40, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_ICB_CVS_CB_BASE_TAG, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_ICB_CVS_CB_BASE_TAG, 0x10, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_ICB_CPS_CB_BASE_TAG, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_ICB_CPS_CB_BASE_TAG, 0x10, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CVS_MISC_RAM, 0x280, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CVS_MISC_RAM, 0x280, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CPS_MISC_RAM, 0x800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CPS_MISC_RAM, 0x200, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CPS_MISC_RAM_1, 0x1c0, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INST_RAM, 0x800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INST_RAM, 0x800, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INST_RAM, 0x200, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CVS_MISC_RAM_TAG, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CVS_MISC_RAM_TAG, 0x10, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CPS_MISC_RAM_TAG, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_CPS_MISC_RAM_TAG, 0x10, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INST_RAM_TAG, 0x80, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INST_RAM_TAG, 0x80, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INST_RAM_TAG, 0x80, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CVS_CONST_RAM_TAG, 0x64, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CVS_CONST_RAM_TAG, 0x38, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CPS_CONST_RAM_TAG, 0x64, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CPS_CONST_RAM_TAG, 0x10, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CVS_CONST_RAM, 0x800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CVS_CONST_RAM, 0x800, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CPS_CONST_RAM, 0x800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_GFX_CPS_CONST_RAM, 0x800, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INST_RAM_1, 0x800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_STPROC_META, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_BV_BE_META, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_BV_BE_META, 0x10, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_DATAPATH_META, 0x20, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_FRONTEND_META, 0x80, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_FRONTEND_META, 0x80, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_FRONTEND_META, 0x80, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_INDIRECT_META, 0x10, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_BACKEND_META, 0x40, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_BACKEND_META, 0x40, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE}, - {A7XX_HLSQ_BACKEND_META, 0x40, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_TP0_TMO_DATA, 0x200, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_TP0_SMO_DATA, 0x80, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_TP0_MIPMAP_BASE_DATA, 0x3c0, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_INST_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_INST_DATA_1, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_0_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_1_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_2_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_3_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_4_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_5_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_6_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_7_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_CB_RAM, 0x390, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_13_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_14_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_INST_TAG, 0xc0, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_INST_DATA_2, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_TMO_TAG, 0x80, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_SMO_TAG, 0x80, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_STATE_DATA, 0x40, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_HWAVE_RAM, 0x100, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_L0_INST_BUF, 0x50, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_8_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_9_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_10_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_11_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_SP_LB_12_DATA, 0x800, 6, 2, PIPE_BR, A7XX_USPTP}, + {A7XX_HLSQ_CVS_BE_CTXT_BUF_RAM_TAG, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CVS_BE_CTXT_BUF_RAM_TAG, 0x10, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CPS_BE_CTXT_BUF_RAM_TAG, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CVS_BE_CTXT_BUF_RAM, 0x300, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CVS_BE_CTXT_BUF_RAM, 0x300, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CPS_BE_CTXT_BUF_RAM, 0x300, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CVS_RAM, 0x1c0, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CVS_RAM, 0x1c0, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CPS_RAM, 0x300, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CPS_RAM, 0x180, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CVS_RAM_TAG, 0x40, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CVS_RAM_TAG, 0x40, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CPS_RAM_TAG, 0x40, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CHUNK_CPS_RAM_TAG, 0x40, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_ICB_CVS_CB_BASE_TAG, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_ICB_CVS_CB_BASE_TAG, 0x10, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_ICB_CPS_CB_BASE_TAG, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_ICB_CPS_CB_BASE_TAG, 0x10, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CVS_MISC_RAM, 0x280, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CVS_MISC_RAM, 0x280, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CPS_MISC_RAM, 0x800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CPS_MISC_RAM, 0x200, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CPS_MISC_RAM_1, 0x1c0, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INST_RAM, 0x800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INST_RAM, 0x800, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INST_RAM, 0x200, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CVS_MISC_RAM_TAG, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CVS_MISC_RAM_TAG, 0x10, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CPS_MISC_RAM_TAG, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_CPS_MISC_RAM_TAG, 0x10, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INST_RAM_TAG, 0x80, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INST_RAM_TAG, 0x80, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INST_RAM_TAG, 0x80, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CVS_CONST_RAM_TAG, 0x64, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CVS_CONST_RAM_TAG, 0x38, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CPS_CONST_RAM_TAG, 0x64, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CPS_CONST_RAM_TAG, 0x10, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CVS_CONST_RAM, 0x800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CVS_CONST_RAM, 0x800, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CPS_CONST_RAM, 0x800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_GFX_CPS_CONST_RAM, 0x800, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INST_RAM_1, 0x800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_STPROC_META, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_BV_BE_META, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_BV_BE_META, 0x10, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_DATAPATH_META, 0x20, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_FRONTEND_META, 0x80, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_FRONTEND_META, 0x80, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_FRONTEND_META, 0x80, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_INDIRECT_META, 0x10, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_BACKEND_META, 0x40, 1, 1, PIPE_BR, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_BACKEND_META, 0x40, 1, 1, PIPE_BV, A7XX_HLSQ_STATE}, + {A7XX_HLSQ_BACKEND_META, 0x40, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE}, }; static const u32 gen7_2_0_gpu_registers[] = { @@ -478,182 +478,182 @@ static const u32 gen7_2_0_sp_noncontext_pipe_lpac_hlsq_state_registers[] = { static_assert(IS_ALIGNED(sizeof(gen7_2_0_sp_noncontext_pipe_lpac_hlsq_state_registers), 8)); static const struct gen7_sel_reg gen7_2_0_rb_rac_sel = { - .host_reg = REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_HOST, - .cd_reg = REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_CD, + .host_reg = REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_HOST, + .cd_reg = REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_CD, .val = 0x0, }; static const struct gen7_sel_reg gen7_2_0_rb_rbp_sel = { - .host_reg = REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_HOST, - .cd_reg = REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_CD, + .host_reg = REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_HOST, + .cd_reg = REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_CD, .val = 0x9, }; static const struct gen7_cluster_registers gen7_2_0_clusters[] = { - { A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT, + { A7XX_CLUSTER_NONE, PIPE_BR, STATE_NON_CONTEXT, gen7_2_0_noncontext_pipe_br_registers, }, - { A7XX_CLUSTER_NONE, A7XX_PIPE_BV, STATE_NON_CONTEXT, + { A7XX_CLUSTER_NONE, PIPE_BV, STATE_NON_CONTEXT, gen7_2_0_noncontext_pipe_bv_registers, }, - { A7XX_CLUSTER_NONE, A7XX_PIPE_LPAC, STATE_NON_CONTEXT, + { A7XX_CLUSTER_NONE, PIPE_LPAC, STATE_NON_CONTEXT, gen7_0_0_noncontext_pipe_lpac_registers, }, - { A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT, + { A7XX_CLUSTER_NONE, PIPE_BR, STATE_NON_CONTEXT, gen7_2_0_noncontext_rb_rac_pipe_br_registers, &gen7_2_0_rb_rac_sel, }, - { A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT, + { A7XX_CLUSTER_NONE, PIPE_BR, STATE_NON_CONTEXT, gen7_2_0_noncontext_rb_rbp_pipe_br_registers, &gen7_2_0_rb_rbp_sel, }, - { A7XX_CLUSTER_GRAS, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_GRAS, PIPE_BR, STATE_FORCE_CTXT_0, gen7_2_0_gras_cluster_gras_pipe_br_registers, }, - { A7XX_CLUSTER_GRAS, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_GRAS, PIPE_BV, STATE_FORCE_CTXT_0, gen7_2_0_gras_cluster_gras_pipe_bv_registers, }, - { A7XX_CLUSTER_GRAS, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_GRAS, PIPE_BR, STATE_FORCE_CTXT_1, gen7_2_0_gras_cluster_gras_pipe_br_registers, }, - { A7XX_CLUSTER_GRAS, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_GRAS, PIPE_BV, STATE_FORCE_CTXT_1, gen7_2_0_gras_cluster_gras_pipe_bv_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_0, gen7_0_0_pc_cluster_fe_pipe_br_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_0, gen7_0_0_pc_cluster_fe_pipe_bv_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_1, gen7_0_0_pc_cluster_fe_pipe_br_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_1, gen7_0_0_pc_cluster_fe_pipe_bv_registers, }, - { A7XX_CLUSTER_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_PS, PIPE_BR, STATE_FORCE_CTXT_0, gen7_2_0_rb_rac_cluster_ps_pipe_br_registers, &gen7_2_0_rb_rac_sel, }, - { A7XX_CLUSTER_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_PS, PIPE_BR, STATE_FORCE_CTXT_1, gen7_2_0_rb_rac_cluster_ps_pipe_br_registers, &gen7_2_0_rb_rac_sel, }, - { A7XX_CLUSTER_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_PS, PIPE_BR, STATE_FORCE_CTXT_0, gen7_0_0_rb_rbp_cluster_ps_pipe_br_registers, &gen7_2_0_rb_rbp_sel, }, - { A7XX_CLUSTER_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_PS, PIPE_BR, STATE_FORCE_CTXT_1, gen7_0_0_rb_rbp_cluster_ps_pipe_br_registers, &gen7_2_0_rb_rbp_sel, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_0, gen7_0_0_vfd_cluster_fe_pipe_br_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_0, gen7_0_0_vfd_cluster_fe_pipe_bv_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_1, gen7_0_0_vfd_cluster_fe_pipe_br_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_1, gen7_0_0_vfd_cluster_fe_pipe_bv_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_0, gen7_0_0_vpc_cluster_fe_pipe_br_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_0, gen7_0_0_vpc_cluster_fe_pipe_bv_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_1, gen7_0_0_vpc_cluster_fe_pipe_br_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_1, gen7_0_0_vpc_cluster_fe_pipe_bv_registers, }, - { A7XX_CLUSTER_PC_VS, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_PC_VS, PIPE_BR, STATE_FORCE_CTXT_0, gen7_0_0_vpc_cluster_pc_vs_pipe_br_registers, }, - { A7XX_CLUSTER_PC_VS, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_PC_VS, PIPE_BV, STATE_FORCE_CTXT_0, gen7_0_0_vpc_cluster_pc_vs_pipe_bv_registers, }, - { A7XX_CLUSTER_PC_VS, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_PC_VS, PIPE_BR, STATE_FORCE_CTXT_1, gen7_0_0_vpc_cluster_pc_vs_pipe_br_registers, }, - { A7XX_CLUSTER_PC_VS, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_PC_VS, PIPE_BV, STATE_FORCE_CTXT_1, gen7_0_0_vpc_cluster_pc_vs_pipe_bv_registers, }, - { A7XX_CLUSTER_VPC_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_VPC_PS, PIPE_BR, STATE_FORCE_CTXT_0, gen7_0_0_vpc_cluster_vpc_ps_pipe_br_registers, }, - { A7XX_CLUSTER_VPC_PS, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_VPC_PS, PIPE_BV, STATE_FORCE_CTXT_0, gen7_0_0_vpc_cluster_vpc_ps_pipe_bv_registers, }, - { A7XX_CLUSTER_VPC_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_VPC_PS, PIPE_BR, STATE_FORCE_CTXT_1, gen7_0_0_vpc_cluster_vpc_ps_pipe_br_registers, }, - { A7XX_CLUSTER_VPC_PS, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_VPC_PS, PIPE_BV, STATE_FORCE_CTXT_1, gen7_0_0_vpc_cluster_vpc_ps_pipe_bv_registers, }, }; static const struct gen7_sptp_cluster_registers gen7_2_0_sptp_clusters[] = { - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_BR, 0, A7XX_HLSQ_STATE, gen7_0_0_sp_noncontext_pipe_br_hlsq_state_registers, 0xae00 }, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_BR, 0, A7XX_SP_TOP, gen7_0_0_sp_noncontext_pipe_br_sp_top_registers, 0xae00 }, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_BR, 0, A7XX_USPTP, gen7_0_0_sp_noncontext_pipe_br_usptp_registers, 0xae00 }, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_LPAC, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_LPAC, 0, A7XX_HLSQ_STATE, gen7_2_0_sp_noncontext_pipe_lpac_hlsq_state_registers, 0xaf80 }, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_LPAC, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_LPAC, 0, A7XX_SP_TOP, gen7_0_0_sp_noncontext_pipe_lpac_sp_top_registers, 0xaf80 }, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_LPAC, 0, A7XX_USPTP, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_LPAC, 0, A7XX_USPTP, gen7_0_0_sp_noncontext_pipe_lpac_usptp_registers, 0xaf80 }, - { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, PIPE_BR, 0, A7XX_USPTP, gen7_0_0_tpl1_noncontext_pipe_br_registers, 0xb600 }, - { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_PIPE_NONE, 0, A7XX_USPTP, + { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, PIPE_NONE, 0, A7XX_USPTP, gen7_0_0_tpl1_noncontext_pipe_none_registers, 0xb600 }, - { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_PIPE_LPAC, 0, A7XX_USPTP, + { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, PIPE_LPAC, 0, A7XX_USPTP, gen7_0_0_tpl1_noncontext_pipe_lpac_registers, 0xb780 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_HLSQ_STATE, gen7_2_0_sp_cluster_sp_ps_pipe_br_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_DP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_HLSQ_DP, gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_dp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_SP_TOP, gen7_2_0_sp_cluster_sp_ps_pipe_br_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_USPTP, gen7_2_0_sp_cluster_sp_ps_pipe_br_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_HLSQ_STATE, gen7_2_0_sp_cluster_sp_ps_pipe_br_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_HLSQ_DP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_HLSQ_DP, gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_dp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_SP_TOP, gen7_2_0_sp_cluster_sp_ps_pipe_br_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_USPTP, gen7_2_0_sp_cluster_sp_ps_pipe_br_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, A7XX_PIPE_BR, 2, A7XX_HLSQ_DP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_HLSQ_DP, gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_dp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, A7XX_PIPE_BR, 3, A7XX_HLSQ_DP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_HLSQ_DP, gen7_0_0_sp_cluster_sp_ps_pipe_br_hlsq_dp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, A7XX_PIPE_BR, 2, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_SP_TOP, gen7_2_0_sp_cluster_sp_ps_pipe_br_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, A7XX_PIPE_BR, 2, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_USPTP, gen7_2_0_sp_cluster_sp_ps_pipe_br_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, A7XX_PIPE_BR, 3, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_SP_TOP, gen7_2_0_sp_cluster_sp_ps_pipe_br_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, A7XX_PIPE_BR, 3, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_USPTP, gen7_2_0_sp_cluster_sp_ps_pipe_br_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_LPAC, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_HLSQ_STATE, gen7_2_0_sp_cluster_sp_ps_pipe_lpac_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_LPAC, 0, A7XX_HLSQ_DP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_HLSQ_DP, gen7_0_0_sp_cluster_sp_ps_pipe_lpac_hlsq_dp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_LPAC, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_SP_TOP, gen7_2_0_sp_cluster_sp_ps_pipe_lpac_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_LPAC, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_USPTP, gen7_2_0_sp_cluster_sp_ps_pipe_lpac_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BR, 0, A7XX_HLSQ_STATE, gen7_2_0_sp_cluster_sp_vs_pipe_br_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BV, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BV, 0, A7XX_HLSQ_STATE, gen7_2_0_sp_cluster_sp_vs_pipe_bv_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BR, 0, A7XX_SP_TOP, gen7_2_0_sp_cluster_sp_vs_pipe_br_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BV, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BV, 0, A7XX_SP_TOP, gen7_2_0_sp_cluster_sp_vs_pipe_bv_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BR, 0, A7XX_USPTP, gen7_2_0_sp_cluster_sp_vs_pipe_br_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BV, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BV, 0, A7XX_USPTP, gen7_2_0_sp_cluster_sp_vs_pipe_bv_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BR, 1, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BR, 1, A7XX_HLSQ_STATE, gen7_2_0_sp_cluster_sp_vs_pipe_br_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BV, 1, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BV, 1, A7XX_HLSQ_STATE, gen7_2_0_sp_cluster_sp_vs_pipe_bv_hlsq_state_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BR, 1, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BR, 1, A7XX_SP_TOP, gen7_2_0_sp_cluster_sp_vs_pipe_br_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BV, 1, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BV, 1, A7XX_SP_TOP, gen7_2_0_sp_cluster_sp_vs_pipe_bv_sp_top_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BR, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BR, 1, A7XX_USPTP, gen7_2_0_sp_cluster_sp_vs_pipe_br_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BV, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BV, 1, A7XX_USPTP, gen7_2_0_sp_cluster_sp_vs_pipe_bv_usptp_registers, 0xa800 }, - { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_ps_pipe_br_registers, 0xb000 }, - { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_ps_pipe_br_registers, 0xb000 }, - { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX2_3D_CPS_REG, A7XX_PIPE_BR, 2, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_ps_pipe_br_registers, 0xb000 }, - { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX3_3D_CPS_REG, A7XX_PIPE_BR, 3, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_ps_pipe_br_registers, 0xb000 }, - { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX0_3D_CPS_REG, A7XX_PIPE_LPAC, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_TP0_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_ps_pipe_lpac_registers, 0xb000 }, - { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX0_3D_CVS_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX0_3D_CVS_REG, PIPE_BR, 0, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_vs_pipe_br_registers, 0xb000 }, - { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX0_3D_CVS_REG, A7XX_PIPE_BV, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX0_3D_CVS_REG, PIPE_BV, 0, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_vs_pipe_bv_registers, 0xb000 }, - { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX1_3D_CVS_REG, A7XX_PIPE_BR, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX1_3D_CVS_REG, PIPE_BR, 1, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_vs_pipe_br_registers, 0xb000 }, - { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX1_3D_CVS_REG, A7XX_PIPE_BV, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_TP0_CTX1_3D_CVS_REG, PIPE_BV, 1, A7XX_USPTP, gen7_0_0_tpl1_cluster_sp_vs_pipe_bv_registers, 0xb000 }, }; 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 0956dfca1f05..20125d1aa21d 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 @@ -118,97 +118,97 @@ static const u32 gen7_9_0_cx_debugbus_blocks[] = { }; static const struct gen7_shader_block gen7_9_0_shader_blocks[] = { - { A7XX_TP0_TMO_DATA, 0x0200, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_TP0_SMO_DATA, 0x0080, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_TP0_MIPMAP_BASE_DATA, 0x03C0, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_INST_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_INST_DATA_1, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_LB_0_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_LB_1_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_LB_2_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_LB_3_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_LB_4_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_LB_5_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_LB_6_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_LB_7_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_CB_RAM, 0x0390, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_LB_13_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_LB_14_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_INST_TAG, 0x00C0, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_INST_DATA_2, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_TMO_TAG, 0x0080, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_SMO_TAG, 0x0080, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_STATE_DATA, 0x0040, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_HWAVE_RAM, 0x0100, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_L0_INST_BUF, 0x0050, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_LB_8_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_LB_9_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_LB_10_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_LB_11_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_SP_LB_12_DATA, 0x0800, 6, 2, A7XX_PIPE_BR, A7XX_USPTP }, - { A7XX_HLSQ_DATAPATH_DSTR_META, 0x0010, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_DATAPATH_DSTR_META, 0x0010, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_L2STC_TAG_RAM, 0x0200, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_L2STC_INFO_CMD, 0x0474, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CVS_BE_CTXT_BUF_RAM_TAG, 0x0080, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CVS_BE_CTXT_BUF_RAM_TAG, 0x0080, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CPS_BE_CTXT_BUF_RAM_TAG, 0x0080, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_CVS_BE_CTXT_BUF_RAM, 0x0400, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_CVS_BE_CTXT_BUF_RAM, 0x0400, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_CPS_BE_CTXT_BUF_RAM, 0x0400, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CHUNK_CVS_RAM, 0x01C0, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CHUNK_CVS_RAM, 0x01C0, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CHUNK_CPS_RAM, 0x0300, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CHUNK_CPS_RAM, 0x0180, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CHUNK_CVS_RAM_TAG, 0x0040, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CHUNK_CVS_RAM_TAG, 0x0040, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CHUNK_CPS_RAM_TAG, 0x0040, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CHUNK_CPS_RAM_TAG, 0x0040, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_ICB_CVS_CB_BASE_TAG, 0x0010, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_ICB_CVS_CB_BASE_TAG, 0x0010, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_ICB_CPS_CB_BASE_TAG, 0x0010, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_ICB_CPS_CB_BASE_TAG, 0x0010, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CVS_MISC_RAM, 0x0540, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CVS_MISC_RAM, 0x0540, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CPS_MISC_RAM, 0x0640, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CPS_MISC_RAM, 0x00B0, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CPS_MISC_RAM_1, 0x0800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_INST_RAM, 0x0800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_INST_RAM, 0x0800, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_INST_RAM, 0x0200, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_CVS_CONST_RAM, 0x0800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_CVS_CONST_RAM, 0x0800, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_CPS_CONST_RAM, 0x0800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_CPS_CONST_RAM, 0x0800, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CVS_MISC_RAM_TAG, 0x0050, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CVS_MISC_RAM_TAG, 0x0050, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CPS_MISC_RAM_TAG, 0x0050, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_CPS_MISC_RAM_TAG, 0x0008, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_INST_RAM_TAG, 0x0014, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_INST_RAM_TAG, 0x0010, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_INST_RAM_TAG, 0x0004, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_CVS_CONST_RAM_TAG, 0x0040, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_CVS_CONST_RAM_TAG, 0x0040, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_CPS_CONST_RAM_TAG, 0x0040, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_CPS_CONST_RAM_TAG, 0x0020, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_LOCAL_MISC_RAM, 0x03C0, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_LOCAL_MISC_RAM, 0x0280, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_LOCAL_MISC_RAM, 0x0050, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_LOCAL_MISC_RAM_TAG, 0x0010, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_GFX_LOCAL_MISC_RAM_TAG, 0x0008, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_INST_RAM_1, 0x0800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_STPROC_META, 0x0010, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_BV_BE_META, 0x0018, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_BV_BE_META, 0x0018, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_INST_RAM_2, 0x0800, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_DATAPATH_META, 0x0020, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_FRONTEND_META, 0x0080, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_FRONTEND_META, 0x0080, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_FRONTEND_META, 0x0080, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_INDIRECT_META, 0x0010, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_BACKEND_META, 0x0040, 1, 1, A7XX_PIPE_BR, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_BACKEND_META, 0x0040, 1, 1, A7XX_PIPE_BV, A7XX_HLSQ_STATE }, - { A7XX_HLSQ_BACKEND_META, 0x0040, 1, 1, A7XX_PIPE_LPAC, A7XX_HLSQ_STATE }, + { A7XX_TP0_TMO_DATA, 0x0200, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_TP0_SMO_DATA, 0x0080, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_TP0_MIPMAP_BASE_DATA, 0x03C0, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_INST_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_INST_DATA_1, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_0_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_1_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_2_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_3_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_4_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_5_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_6_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_7_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_CB_RAM, 0x0390, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_13_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_14_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_INST_TAG, 0x00C0, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_INST_DATA_2, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_TMO_TAG, 0x0080, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_SMO_TAG, 0x0080, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_STATE_DATA, 0x0040, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_HWAVE_RAM, 0x0100, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_L0_INST_BUF, 0x0050, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_8_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_9_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_10_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_11_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_SP_LB_12_DATA, 0x0800, 6, 2, PIPE_BR, A7XX_USPTP }, + { A7XX_HLSQ_DATAPATH_DSTR_META, 0x0010, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_DATAPATH_DSTR_META, 0x0010, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_L2STC_TAG_RAM, 0x0200, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_L2STC_INFO_CMD, 0x0474, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CVS_BE_CTXT_BUF_RAM_TAG, 0x0080, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CVS_BE_CTXT_BUF_RAM_TAG, 0x0080, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CPS_BE_CTXT_BUF_RAM_TAG, 0x0080, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_CVS_BE_CTXT_BUF_RAM, 0x0400, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_CVS_BE_CTXT_BUF_RAM, 0x0400, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_CPS_BE_CTXT_BUF_RAM, 0x0400, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CHUNK_CVS_RAM, 0x01C0, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CHUNK_CVS_RAM, 0x01C0, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CHUNK_CPS_RAM, 0x0300, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CHUNK_CPS_RAM, 0x0180, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CHUNK_CVS_RAM_TAG, 0x0040, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CHUNK_CVS_RAM_TAG, 0x0040, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CHUNK_CPS_RAM_TAG, 0x0040, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CHUNK_CPS_RAM_TAG, 0x0040, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_ICB_CVS_CB_BASE_TAG, 0x0010, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_ICB_CVS_CB_BASE_TAG, 0x0010, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_ICB_CPS_CB_BASE_TAG, 0x0010, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_ICB_CPS_CB_BASE_TAG, 0x0010, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CVS_MISC_RAM, 0x0540, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CVS_MISC_RAM, 0x0540, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CPS_MISC_RAM, 0x0640, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CPS_MISC_RAM, 0x00B0, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CPS_MISC_RAM_1, 0x0800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_INST_RAM, 0x0800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_INST_RAM, 0x0800, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_INST_RAM, 0x0200, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_CVS_CONST_RAM, 0x0800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_CVS_CONST_RAM, 0x0800, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_CPS_CONST_RAM, 0x0800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_CPS_CONST_RAM, 0x0800, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CVS_MISC_RAM_TAG, 0x0050, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CVS_MISC_RAM_TAG, 0x0050, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CPS_MISC_RAM_TAG, 0x0050, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_CPS_MISC_RAM_TAG, 0x0008, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_INST_RAM_TAG, 0x0014, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_INST_RAM_TAG, 0x0010, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_INST_RAM_TAG, 0x0004, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_CVS_CONST_RAM_TAG, 0x0040, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_CVS_CONST_RAM_TAG, 0x0040, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_CPS_CONST_RAM_TAG, 0x0040, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_CPS_CONST_RAM_TAG, 0x0020, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_LOCAL_MISC_RAM, 0x03C0, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_LOCAL_MISC_RAM, 0x0280, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_LOCAL_MISC_RAM, 0x0050, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_LOCAL_MISC_RAM_TAG, 0x0010, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_GFX_LOCAL_MISC_RAM_TAG, 0x0008, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_INST_RAM_1, 0x0800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_STPROC_META, 0x0010, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_BV_BE_META, 0x0018, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_BV_BE_META, 0x0018, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_INST_RAM_2, 0x0800, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_DATAPATH_META, 0x0020, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_FRONTEND_META, 0x0080, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_FRONTEND_META, 0x0080, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_FRONTEND_META, 0x0080, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_INDIRECT_META, 0x0010, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_BACKEND_META, 0x0040, 1, 1, PIPE_BR, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_BACKEND_META, 0x0040, 1, 1, PIPE_BV, A7XX_HLSQ_STATE }, + { A7XX_HLSQ_BACKEND_META, 0x0040, 1, 1, PIPE_LPAC, A7XX_HLSQ_STATE }, }; /* @@ -226,7 +226,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_pre_crashdumper_gpu_registers), 8)); * Block : ['BROADCAST', 'CP', 'GRAS', 'GXCLKCTL'] * Block : ['PC', 'RBBM', 'RDVM', 'UCHE'] * Block : ['VFD', 'VPC', 'VSC'] - * Pipeline: A7XX_PIPE_NONE + * Pipeline: PIPE_NONE * pairs : 196 (Regs:1778) */ static const u32 gen7_9_0_gpu_registers[] = { @@ -290,7 +290,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_gxclkctl_registers), 8)); /* * Block : ['GMUAO', 'GMUCX', 'GMUCX_RAM'] - * Pipeline: A7XX_PIPE_NONE + * Pipeline: PIPE_NONE * pairs : 134 (Regs:429) */ static const u32 gen7_9_0_gmu_registers[] = { @@ -334,7 +334,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_gmu_registers), 8)); /* * Block : ['GMUGX'] - * Pipeline: A7XX_PIPE_NONE + * Pipeline: PIPE_NONE * pairs : 44 (Regs:454) */ static const u32 gen7_9_0_gmugx_registers[] = { @@ -355,7 +355,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_gmugx_registers), 8)); /* * Block : ['CX_MISC'] - * Pipeline: A7XX_PIPE_NONE + * Pipeline: PIPE_NONE * pairs : 7 (Regs:56) */ static const u32 gen7_9_0_cx_misc_registers[] = { @@ -367,7 +367,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_cx_misc_registers), 8)); /* * Block : ['DBGC'] - * Pipeline: A7XX_PIPE_NONE + * Pipeline: PIPE_NONE * pairs : 19 (Regs:155) */ static const u32 gen7_9_0_dbgc_registers[] = { @@ -382,7 +382,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_dbgc_registers), 8)); /* * Block : ['CX_DBGC'] - * Pipeline: A7XX_PIPE_NONE + * Pipeline: PIPE_NONE * pairs : 7 (Regs:75) */ static const u32 gen7_9_0_cx_dbgc_registers[] = { @@ -396,7 +396,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_cx_dbgc_registers), 8)); * Block : ['BROADCAST', 'CP', 'CX_DBGC', 'CX_MISC', 'DBGC', 'GBIF'] * Block : ['GMUAO', 'GMUCX', 'GMUGX', 'GRAS', 'GXCLKCTL', 'PC'] * Block : ['RBBM', 'RDVM', 'UCHE', 'VFD', 'VPC', 'VSC'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_NONE * pairs : 29 (Regs:573) */ @@ -417,7 +417,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_non_context_pipe_br_registers), 8)); * Block : ['BROADCAST', 'CP', 'CX_DBGC', 'CX_MISC', 'DBGC', 'GBIF'] * Block : ['GMUAO', 'GMUCX', 'GMUGX', 'GRAS', 'GXCLKCTL', 'PC'] * Block : ['RBBM', 'RDVM', 'UCHE', 'VFD', 'VPC', 'VSC'] - * Pipeline: A7XX_PIPE_BV + * Pipeline: PIPE_BV * Cluster : A7XX_CLUSTER_NONE * pairs : 29 (Regs:573) */ @@ -438,7 +438,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_non_context_pipe_bv_registers), 8)); * Block : ['BROADCAST', 'CP', 'CX_DBGC', 'CX_MISC', 'DBGC', 'GBIF'] * Block : ['GMUAO', 'GMUCX', 'GMUGX', 'GRAS', 'GXCLKCTL', 'PC'] * Block : ['RBBM', 'RDVM', 'UCHE', 'VFD', 'VPC', 'VSC'] - * Pipeline: A7XX_PIPE_LPAC + * Pipeline: PIPE_LPAC * Cluster : A7XX_CLUSTER_NONE * pairs : 2 (Regs:7) */ @@ -450,7 +450,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_non_context_pipe_lpac_registers), 8)); /* * Block : ['RB'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_NONE * pairs : 5 (Regs:37) */ @@ -463,7 +463,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_non_context_rb_pipe_br_rac_registers), /* * Block : ['RB'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_NONE * pairs : 15 (Regs:66) */ @@ -478,7 +478,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_non_context_rb_pipe_br_rbp_registers), /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_NONE * Location: A7XX_HLSQ_STATE * pairs : 4 (Regs:28) @@ -491,7 +491,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_non_context_sp_pipe_br_hlsq_state_regis /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_NONE * Location: A7XX_SP_TOP * pairs : 10 (Regs:61) @@ -506,7 +506,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_non_context_sp_pipe_br_sp_top_registers /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_NONE * Location: A7XX_USPTP * pairs : 12 (Regs:62) @@ -521,7 +521,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_non_context_sp_pipe_br_usptp_registers) /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_NONE * Location: A7XX_HLSQ_DP_STR * pairs : 2 (Regs:5) @@ -534,7 +534,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_non_context_sp_pipe_br_hlsq_dp_str_regi /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_LPAC + * Pipeline: PIPE_LPAC * Cluster : A7XX_CLUSTER_NONE * Location: A7XX_HLSQ_STATE * pairs : 1 (Regs:5) @@ -547,7 +547,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_non_context_sp_pipe_lpac_hlsq_state_reg /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_LPAC + * Pipeline: PIPE_LPAC * Cluster : A7XX_CLUSTER_NONE * Location: A7XX_SP_TOP * pairs : 1 (Regs:6) @@ -560,7 +560,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_non_context_sp_pipe_lpac_sp_top_registe /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_LPAC + * Pipeline: PIPE_LPAC * Cluster : A7XX_CLUSTER_NONE * Location: A7XX_USPTP * pairs : 2 (Regs:9) @@ -573,7 +573,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_non_context_sp_pipe_lpac_usptp_register /* * Block : ['TPL1'] - * Pipeline: A7XX_PIPE_NONE + * Pipeline: PIPE_NONE * Cluster : A7XX_CLUSTER_NONE * Location: A7XX_USPTP * pairs : 5 (Regs:29) @@ -587,7 +587,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_non_context_tpl1_pipe_none_usptp_regist /* * Block : ['TPL1'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_NONE * Location: A7XX_USPTP * pairs : 1 (Regs:1) @@ -600,7 +600,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_non_context_tpl1_pipe_br_usptp_register /* * Block : ['TPL1'] - * Pipeline: A7XX_PIPE_LPAC + * Pipeline: PIPE_LPAC * Cluster : A7XX_CLUSTER_NONE * Location: A7XX_USPTP * pairs : 1 (Regs:1) @@ -613,7 +613,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_non_context_tpl1_pipe_lpac_usptp_regist /* * Block : ['GRAS'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_GRAS * pairs : 14 (Regs:293) */ @@ -628,7 +628,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_gras_pipe_br_cluster_gras_registers), 8 /* * Block : ['GRAS'] - * Pipeline: A7XX_PIPE_BV + * Pipeline: PIPE_BV * Cluster : A7XX_CLUSTER_GRAS * pairs : 14 (Regs:293) */ @@ -643,7 +643,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_gras_pipe_bv_cluster_gras_registers), 8 /* * Block : ['PC'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_FE * pairs : 6 (Regs:31) */ @@ -656,7 +656,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_pc_pipe_br_cluster_fe_registers), 8)); /* * Block : ['PC'] - * Pipeline: A7XX_PIPE_BV + * Pipeline: PIPE_BV * Cluster : A7XX_CLUSTER_FE * pairs : 6 (Regs:31) */ @@ -669,7 +669,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_pc_pipe_bv_cluster_fe_registers), 8)); /* * Block : ['VFD'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_FE * pairs : 2 (Regs:236) */ @@ -681,7 +681,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_vfd_pipe_br_cluster_fe_registers), 8)); /* * Block : ['VFD'] - * Pipeline: A7XX_PIPE_BV + * Pipeline: PIPE_BV * Cluster : A7XX_CLUSTER_FE * pairs : 2 (Regs:236) */ @@ -693,7 +693,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_vfd_pipe_bv_cluster_fe_registers), 8)); /* * Block : ['VPC'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_FE * pairs : 2 (Regs:18) */ @@ -705,7 +705,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_vpc_pipe_br_cluster_fe_registers), 8)); /* * Block : ['VPC'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_PC_VS * pairs : 3 (Regs:30) */ @@ -717,7 +717,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_vpc_pipe_br_cluster_pc_vs_registers), 8 /* * Block : ['VPC'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_VPC_PS * pairs : 5 (Regs:76) */ @@ -730,7 +730,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_vpc_pipe_br_cluster_vpc_ps_registers), /* * Block : ['VPC'] - * Pipeline: A7XX_PIPE_BV + * Pipeline: PIPE_BV * Cluster : A7XX_CLUSTER_FE * pairs : 2 (Regs:18) */ @@ -742,7 +742,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_vpc_pipe_bv_cluster_fe_registers), 8)); /* * Block : ['VPC'] - * Pipeline: A7XX_PIPE_BV + * Pipeline: PIPE_BV * Cluster : A7XX_CLUSTER_PC_VS * pairs : 3 (Regs:30) */ @@ -754,7 +754,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_vpc_pipe_bv_cluster_pc_vs_registers), 8 /* * Block : ['VPC'] - * Pipeline: A7XX_PIPE_BV + * Pipeline: PIPE_BV * Cluster : A7XX_CLUSTER_VPC_PS * pairs : 5 (Regs:76) */ @@ -767,7 +767,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_vpc_pipe_bv_cluster_vpc_ps_registers), /* * Block : ['RB'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_PS * pairs : 39 (Regs:133) */ @@ -788,7 +788,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_rb_pipe_br_cluster_ps_rac_registers), 8 /* * Block : ['RB'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_PS * pairs : 34 (Regs:100) */ @@ -808,7 +808,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_rb_pipe_br_cluster_ps_rbp_registers), 8 /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_SP_VS * Location: A7XX_HLSQ_STATE * pairs : 29 (Regs:215) @@ -828,7 +828,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_sp_pipe_br_cluster_sp_vs_hlsq_state_reg /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_SP_VS * Location: A7XX_SP_TOP * pairs : 22 (Regs:73) @@ -846,7 +846,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_sp_pipe_br_cluster_sp_vs_sp_top_registe /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_SP_VS * Location: A7XX_USPTP * pairs : 16 (Regs:269) @@ -862,7 +862,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_sp_pipe_br_cluster_sp_vs_usptp_register /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_SP_PS * Location: A7XX_HLSQ_STATE * pairs : 21 (Regs:334) @@ -880,7 +880,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_sp_pipe_br_cluster_sp_ps_hlsq_state_reg /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_SP_PS * Location: A7XX_HLSQ_DP * pairs : 3 (Regs:19) @@ -893,7 +893,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_sp_pipe_br_cluster_sp_ps_hlsq_dp_regist /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_SP_PS * Location: A7XX_SP_TOP * pairs : 18 (Regs:77) @@ -910,7 +910,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_sp_pipe_br_cluster_sp_ps_sp_top_registe /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_SP_PS * Location: A7XX_USPTP * pairs : 17 (Regs:333) @@ -927,7 +927,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_sp_pipe_br_cluster_sp_ps_usptp_register /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_SP_PS * Location: A7XX_HLSQ_DP_STR * pairs : 1 (Regs:6) @@ -940,7 +940,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_sp_pipe_br_cluster_sp_ps_hlsq_dp_str_re /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_BV + * Pipeline: PIPE_BV * Cluster : A7XX_CLUSTER_SP_VS * Location: A7XX_HLSQ_STATE * pairs : 28 (Regs:213) @@ -959,7 +959,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_sp_pipe_bv_cluster_sp_vs_hlsq_state_reg /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_BV + * Pipeline: PIPE_BV * Cluster : A7XX_CLUSTER_SP_VS * Location: A7XX_SP_TOP * pairs : 21 (Regs:71) @@ -977,7 +977,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_sp_pipe_bv_cluster_sp_vs_sp_top_registe /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_BV + * Pipeline: PIPE_BV * Cluster : A7XX_CLUSTER_SP_VS * Location: A7XX_USPTP * pairs : 16 (Regs:266) @@ -993,7 +993,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_sp_pipe_bv_cluster_sp_vs_usptp_register /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_LPAC + * Pipeline: PIPE_LPAC * Cluster : A7XX_CLUSTER_SP_PS * Location: A7XX_HLSQ_STATE * pairs : 14 (Regs:299) @@ -1009,7 +1009,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_sp_pipe_lpac_cluster_sp_ps_hlsq_state_r /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_LPAC + * Pipeline: PIPE_LPAC * Cluster : A7XX_CLUSTER_SP_PS * Location: A7XX_HLSQ_DP * pairs : 2 (Regs:13) @@ -1022,7 +1022,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_sp_pipe_lpac_cluster_sp_ps_hlsq_dp_regi /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_LPAC + * Pipeline: PIPE_LPAC * Cluster : A7XX_CLUSTER_SP_PS * Location: A7XX_SP_TOP * pairs : 9 (Regs:34) @@ -1037,7 +1037,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_sp_pipe_lpac_cluster_sp_ps_sp_top_regis /* * Block : ['SP'] - * Pipeline: A7XX_PIPE_LPAC + * Pipeline: PIPE_LPAC * Cluster : A7XX_CLUSTER_SP_PS * Location: A7XX_USPTP * pairs : 11 (Regs:279) @@ -1052,7 +1052,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_sp_pipe_lpac_cluster_sp_ps_usptp_regist /* * Block : ['TPL1'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_SP_VS * Location: A7XX_USPTP * pairs : 3 (Regs:10) @@ -1065,7 +1065,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_tpl1_pipe_br_cluster_sp_vs_usptp_regist /* * Block : ['TPL1'] - * Pipeline: A7XX_PIPE_BR + * Pipeline: PIPE_BR * Cluster : A7XX_CLUSTER_SP_PS * Location: A7XX_USPTP * pairs : 6 (Regs:42) @@ -1079,7 +1079,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_tpl1_pipe_br_cluster_sp_ps_usptp_regist /* * Block : ['TPL1'] - * Pipeline: A7XX_PIPE_BV + * Pipeline: PIPE_BV * Cluster : A7XX_CLUSTER_SP_VS * Location: A7XX_USPTP * pairs : 3 (Regs:10) @@ -1092,7 +1092,7 @@ static_assert(IS_ALIGNED(sizeof(gen7_9_0_tpl1_pipe_bv_cluster_sp_vs_usptp_regist /* * Block : ['TPL1'] - * Pipeline: A7XX_PIPE_LPAC + * Pipeline: PIPE_LPAC * Cluster : A7XX_CLUSTER_SP_PS * Location: A7XX_USPTP * pairs : 5 (Regs:7) @@ -1105,192 +1105,192 @@ static const u32 gen7_9_0_tpl1_pipe_lpac_cluster_sp_ps_usptp_registers[] = { static_assert(IS_ALIGNED(sizeof(gen7_9_0_tpl1_pipe_lpac_cluster_sp_ps_usptp_registers), 8)); static const struct gen7_sel_reg gen7_9_0_rb_rac_sel = { - .host_reg = REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_HOST, - .cd_reg = REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_CD, + .host_reg = REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_HOST, + .cd_reg = REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_CD, .val = 0, }; static const struct gen7_sel_reg gen7_9_0_rb_rbp_sel = { - .host_reg = REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_HOST, - .cd_reg = REG_A6XX_RB_RB_SUB_BLOCK_SEL_CNTL_CD, + .host_reg = REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_HOST, + .cd_reg = REG_A6XX_RB_SUB_BLOCK_SEL_CNTL_CD, .val = 0x9, }; static const struct gen7_cluster_registers gen7_9_0_clusters[] = { - { A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT, + { A7XX_CLUSTER_NONE, PIPE_BR, STATE_NON_CONTEXT, gen7_9_0_non_context_pipe_br_registers, }, - { A7XX_CLUSTER_NONE, A7XX_PIPE_BV, STATE_NON_CONTEXT, + { A7XX_CLUSTER_NONE, PIPE_BV, STATE_NON_CONTEXT, gen7_9_0_non_context_pipe_bv_registers, }, - { A7XX_CLUSTER_NONE, A7XX_PIPE_LPAC, STATE_NON_CONTEXT, + { A7XX_CLUSTER_NONE, PIPE_LPAC, STATE_NON_CONTEXT, gen7_9_0_non_context_pipe_lpac_registers, }, - { A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT, + { A7XX_CLUSTER_NONE, PIPE_BR, STATE_NON_CONTEXT, gen7_9_0_non_context_rb_pipe_br_rac_registers, &gen7_9_0_rb_rac_sel, }, - { A7XX_CLUSTER_NONE, A7XX_PIPE_BR, STATE_NON_CONTEXT, + { A7XX_CLUSTER_NONE, PIPE_BR, STATE_NON_CONTEXT, gen7_9_0_non_context_rb_pipe_br_rbp_registers, &gen7_9_0_rb_rbp_sel, }, - { A7XX_CLUSTER_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_PS, PIPE_BR, STATE_FORCE_CTXT_0, gen7_9_0_rb_pipe_br_cluster_ps_rac_registers, &gen7_9_0_rb_rac_sel, }, - { A7XX_CLUSTER_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_PS, PIPE_BR, STATE_FORCE_CTXT_1, gen7_9_0_rb_pipe_br_cluster_ps_rac_registers, &gen7_9_0_rb_rac_sel, }, - { A7XX_CLUSTER_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_PS, PIPE_BR, STATE_FORCE_CTXT_0, gen7_9_0_rb_pipe_br_cluster_ps_rbp_registers, &gen7_9_0_rb_rbp_sel, }, - { A7XX_CLUSTER_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_PS, PIPE_BR, STATE_FORCE_CTXT_1, gen7_9_0_rb_pipe_br_cluster_ps_rbp_registers, &gen7_9_0_rb_rbp_sel, }, - { A7XX_CLUSTER_GRAS, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_GRAS, PIPE_BR, STATE_FORCE_CTXT_0, gen7_9_0_gras_pipe_br_cluster_gras_registers, }, - { A7XX_CLUSTER_GRAS, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_GRAS, PIPE_BR, STATE_FORCE_CTXT_1, gen7_9_0_gras_pipe_br_cluster_gras_registers, }, - { A7XX_CLUSTER_GRAS, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_GRAS, PIPE_BV, STATE_FORCE_CTXT_0, gen7_9_0_gras_pipe_bv_cluster_gras_registers, }, - { A7XX_CLUSTER_GRAS, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_GRAS, PIPE_BV, STATE_FORCE_CTXT_1, gen7_9_0_gras_pipe_bv_cluster_gras_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_0, gen7_9_0_pc_pipe_br_cluster_fe_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_1, gen7_9_0_pc_pipe_br_cluster_fe_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_0, gen7_9_0_pc_pipe_bv_cluster_fe_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_1, gen7_9_0_pc_pipe_bv_cluster_fe_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_0, gen7_9_0_vfd_pipe_br_cluster_fe_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_1, gen7_9_0_vfd_pipe_br_cluster_fe_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_0, gen7_9_0_vfd_pipe_bv_cluster_fe_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_1, gen7_9_0_vfd_pipe_bv_cluster_fe_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_0, gen7_9_0_vpc_pipe_br_cluster_fe_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BR, STATE_FORCE_CTXT_1, gen7_9_0_vpc_pipe_br_cluster_fe_registers, }, - { A7XX_CLUSTER_PC_VS, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_PC_VS, PIPE_BR, STATE_FORCE_CTXT_0, gen7_9_0_vpc_pipe_br_cluster_pc_vs_registers, }, - { A7XX_CLUSTER_PC_VS, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_PC_VS, PIPE_BR, STATE_FORCE_CTXT_1, gen7_9_0_vpc_pipe_br_cluster_pc_vs_registers, }, - { A7XX_CLUSTER_VPC_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_VPC_PS, PIPE_BR, STATE_FORCE_CTXT_0, gen7_9_0_vpc_pipe_br_cluster_vpc_ps_registers, }, - { A7XX_CLUSTER_VPC_PS, A7XX_PIPE_BR, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_VPC_PS, PIPE_BR, STATE_FORCE_CTXT_1, gen7_9_0_vpc_pipe_br_cluster_vpc_ps_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_0, gen7_9_0_vpc_pipe_bv_cluster_fe_registers, }, - { A7XX_CLUSTER_FE, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_FE, PIPE_BV, STATE_FORCE_CTXT_1, gen7_9_0_vpc_pipe_bv_cluster_fe_registers, }, - { A7XX_CLUSTER_PC_VS, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_PC_VS, PIPE_BV, STATE_FORCE_CTXT_0, gen7_9_0_vpc_pipe_bv_cluster_pc_vs_registers, }, - { A7XX_CLUSTER_PC_VS, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_PC_VS, PIPE_BV, STATE_FORCE_CTXT_1, gen7_9_0_vpc_pipe_bv_cluster_pc_vs_registers, }, - { A7XX_CLUSTER_VPC_PS, A7XX_PIPE_BV, STATE_FORCE_CTXT_0, + { A7XX_CLUSTER_VPC_PS, PIPE_BV, STATE_FORCE_CTXT_0, gen7_9_0_vpc_pipe_bv_cluster_vpc_ps_registers, }, - { A7XX_CLUSTER_VPC_PS, A7XX_PIPE_BV, STATE_FORCE_CTXT_1, + { A7XX_CLUSTER_VPC_PS, PIPE_BV, STATE_FORCE_CTXT_1, gen7_9_0_vpc_pipe_bv_cluster_vpc_ps_registers, }, }; static const struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] = { - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_BR, 0, A7XX_HLSQ_STATE, gen7_9_0_non_context_sp_pipe_br_hlsq_state_registers, 0xae00}, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_BR, 0, A7XX_SP_TOP, gen7_9_0_non_context_sp_pipe_br_sp_top_registers, 0xae00}, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_BR, 0, A7XX_USPTP, gen7_9_0_non_context_sp_pipe_br_usptp_registers, 0xae00}, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_DP_STR, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_BR, 0, A7XX_HLSQ_DP_STR, gen7_9_0_non_context_sp_pipe_br_hlsq_dp_str_registers, 0xae00}, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_LPAC, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_LPAC, 0, A7XX_HLSQ_STATE, gen7_9_0_non_context_sp_pipe_lpac_hlsq_state_registers, 0xaf80}, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_LPAC, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_LPAC, 0, A7XX_SP_TOP, gen7_9_0_non_context_sp_pipe_lpac_sp_top_registers, 0xaf80}, - { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, A7XX_PIPE_LPAC, 0, A7XX_USPTP, + { A7XX_CLUSTER_NONE, A7XX_SP_NCTX_REG, PIPE_LPAC, 0, A7XX_USPTP, gen7_9_0_non_context_sp_pipe_lpac_usptp_registers, 0xaf80}, - { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_PIPE_NONE, 0, A7XX_USPTP, + { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, PIPE_NONE, 0, A7XX_USPTP, gen7_9_0_non_context_tpl1_pipe_none_usptp_registers, 0xb600}, - { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, PIPE_BR, 0, A7XX_USPTP, gen7_9_0_non_context_tpl1_pipe_br_usptp_registers, 0xb600}, - { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, A7XX_PIPE_LPAC, 0, A7XX_USPTP, + { A7XX_CLUSTER_NONE, A7XX_TP0_NCTX_REG, PIPE_LPAC, 0, A7XX_USPTP, gen7_9_0_non_context_tpl1_pipe_lpac_usptp_registers, 0xb780}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BR, 0, A7XX_HLSQ_STATE, gen7_9_0_sp_pipe_br_cluster_sp_vs_hlsq_state_registers, 0xa800}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BR, 0, A7XX_SP_TOP, gen7_9_0_sp_pipe_br_cluster_sp_vs_sp_top_registers, 0xa800}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BR, 0, A7XX_USPTP, gen7_9_0_sp_pipe_br_cluster_sp_vs_usptp_registers, 0xa800}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BV, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BV, 0, A7XX_HLSQ_STATE, gen7_9_0_sp_pipe_bv_cluster_sp_vs_hlsq_state_registers, 0xa800}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BV, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BV, 0, A7XX_SP_TOP, gen7_9_0_sp_pipe_bv_cluster_sp_vs_sp_top_registers, 0xa800}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BV, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BV, 0, A7XX_USPTP, gen7_9_0_sp_pipe_bv_cluster_sp_vs_usptp_registers, 0xa800}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BR, 1, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BR, 1, A7XX_HLSQ_STATE, gen7_9_0_sp_pipe_br_cluster_sp_vs_hlsq_state_registers, 0xa800}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BR, 1, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BR, 1, A7XX_SP_TOP, gen7_9_0_sp_pipe_br_cluster_sp_vs_sp_top_registers, 0xa800}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BR, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BR, 1, A7XX_USPTP, gen7_9_0_sp_pipe_br_cluster_sp_vs_usptp_registers, 0xa800}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BV, 1, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BV, 1, A7XX_HLSQ_STATE, gen7_9_0_sp_pipe_bv_cluster_sp_vs_hlsq_state_registers, 0xa800}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BV, 1, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BV, 1, A7XX_SP_TOP, gen7_9_0_sp_pipe_bv_cluster_sp_vs_sp_top_registers, 0xa800}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BV, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BV, 1, A7XX_USPTP, gen7_9_0_sp_pipe_bv_cluster_sp_vs_usptp_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_HLSQ_STATE, gen7_9_0_sp_pipe_br_cluster_sp_ps_hlsq_state_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_DP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_HLSQ_DP, gen7_9_0_sp_pipe_br_cluster_sp_ps_hlsq_dp_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_SP_TOP, gen7_9_0_sp_pipe_br_cluster_sp_ps_sp_top_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_USPTP, gen7_9_0_sp_pipe_br_cluster_sp_ps_usptp_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_HLSQ_DP_STR, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_HLSQ_DP_STR, gen7_9_0_sp_pipe_br_cluster_sp_ps_hlsq_dp_str_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_LPAC, 0, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_HLSQ_STATE, gen7_9_0_sp_pipe_lpac_cluster_sp_ps_hlsq_state_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_LPAC, 0, A7XX_HLSQ_DP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_HLSQ_DP, gen7_9_0_sp_pipe_lpac_cluster_sp_ps_hlsq_dp_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_LPAC, 0, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_SP_TOP, gen7_9_0_sp_pipe_lpac_cluster_sp_ps_sp_top_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_LPAC, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_USPTP, gen7_9_0_sp_pipe_lpac_cluster_sp_ps_usptp_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_HLSQ_STATE, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_HLSQ_STATE, gen7_9_0_sp_pipe_br_cluster_sp_ps_hlsq_state_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_HLSQ_DP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_HLSQ_DP, gen7_9_0_sp_pipe_br_cluster_sp_ps_hlsq_dp_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_SP_TOP, gen7_9_0_sp_pipe_br_cluster_sp_ps_sp_top_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_USPTP, gen7_9_0_sp_pipe_br_cluster_sp_ps_usptp_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_HLSQ_DP_STR, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_HLSQ_DP_STR, gen7_9_0_sp_pipe_br_cluster_sp_ps_hlsq_dp_str_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, A7XX_PIPE_BR, 2, A7XX_HLSQ_DP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_HLSQ_DP, gen7_9_0_sp_pipe_br_cluster_sp_ps_hlsq_dp_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, A7XX_PIPE_BR, 2, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_SP_TOP, gen7_9_0_sp_pipe_br_cluster_sp_ps_sp_top_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, A7XX_PIPE_BR, 2, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_USPTP, gen7_9_0_sp_pipe_br_cluster_sp_ps_usptp_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, A7XX_PIPE_BR, 2, A7XX_HLSQ_DP_STR, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_HLSQ_DP_STR, gen7_9_0_sp_pipe_br_cluster_sp_ps_hlsq_dp_str_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, A7XX_PIPE_BR, 3, A7XX_HLSQ_DP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_HLSQ_DP, gen7_9_0_sp_pipe_br_cluster_sp_ps_hlsq_dp_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, A7XX_PIPE_BR, 3, A7XX_SP_TOP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_SP_TOP, gen7_9_0_sp_pipe_br_cluster_sp_ps_sp_top_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, A7XX_PIPE_BR, 3, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_USPTP, gen7_9_0_sp_pipe_br_cluster_sp_ps_usptp_registers, 0xa800}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, A7XX_PIPE_BR, 3, A7XX_HLSQ_DP_STR, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_HLSQ_DP_STR, gen7_9_0_sp_pipe_br_cluster_sp_ps_hlsq_dp_str_registers, 0xa800}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BR, 0, A7XX_USPTP, gen7_9_0_tpl1_pipe_br_cluster_sp_vs_usptp_registers, 0xb000}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, A7XX_PIPE_BV, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX0_3D_CVS_REG, PIPE_BV, 0, A7XX_USPTP, gen7_9_0_tpl1_pipe_bv_cluster_sp_vs_usptp_registers, 0xb000}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BR, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BR, 1, A7XX_USPTP, gen7_9_0_tpl1_pipe_br_cluster_sp_vs_usptp_registers, 0xb000}, - { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, A7XX_PIPE_BV, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_VS, A7XX_SP_CTX1_3D_CVS_REG, PIPE_BV, 1, A7XX_USPTP, gen7_9_0_tpl1_pipe_bv_cluster_sp_vs_usptp_registers, 0xb000}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_BR, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_BR, 0, A7XX_USPTP, gen7_9_0_tpl1_pipe_br_cluster_sp_ps_usptp_registers, 0xb000}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, A7XX_PIPE_LPAC, 0, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX0_3D_CPS_REG, PIPE_LPAC, 0, A7XX_USPTP, gen7_9_0_tpl1_pipe_lpac_cluster_sp_ps_usptp_registers, 0xb000}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, A7XX_PIPE_BR, 1, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX1_3D_CPS_REG, PIPE_BR, 1, A7XX_USPTP, gen7_9_0_tpl1_pipe_br_cluster_sp_ps_usptp_registers, 0xb000}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, A7XX_PIPE_BR, 2, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX2_3D_CPS_REG, PIPE_BR, 2, A7XX_USPTP, gen7_9_0_tpl1_pipe_br_cluster_sp_ps_usptp_registers, 0xb000}, - { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, A7XX_PIPE_BR, 3, A7XX_USPTP, + { A7XX_CLUSTER_SP_PS, A7XX_SP_CTX3_3D_CPS_REG, PIPE_BR, 3, A7XX_USPTP, gen7_9_0_tpl1_pipe_br_cluster_sp_ps_usptp_registers, 0xb000}, }; diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index afaa3cfefd35..1c80909e63ca 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -284,6 +284,7 @@ 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 adreno_gpu *adreno_gpu = container_of(gpu, struct adreno_gpu, base); struct msm_drm_private *priv = gpu->dev->dev_private; struct msm_mmu *mmu = to_msm_vm(gpu->vm)->mmu; const char *type = "UNKNOWN"; @@ -336,6 +337,11 @@ int adreno_fault_handler(struct msm_gpu *gpu, unsigned long iova, int flags, /* Turn off the hangcheck timer to keep it from bothering us */ timer_delete(&gpu->hangcheck_timer); + /* Let any concurrent GMU transactions know that the MMU may be + * blocked for a while and they should wait on us. + */ + reinit_completion(&adreno_gpu->fault_coredump_done); + fault_info.ttbr0 = info->ttbr0; fault_info.iova = iova; fault_info.flags = flags; @@ -343,18 +349,13 @@ int adreno_fault_handler(struct msm_gpu *gpu, unsigned long iova, int flags, fault_info.block = block; msm_gpu_fault_crashstate_capture(gpu, &fault_info); + + complete_all(&adreno_gpu->fault_coredump_done); } return 0; } -static bool -adreno_smmu_has_prr(struct msm_gpu *gpu) -{ - struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(&gpu->pdev->dev); - return adreno_smmu && adreno_smmu->set_prr_addr; -} - int adreno_get_param(struct msm_gpu *gpu, struct msm_context *ctx, uint32_t param, uint64_t *value, uint32_t *len) { @@ -1196,6 +1197,7 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev, /* Only handle the core clock when GMU is not in use (or is absent). */ if (adreno_has_gmu_wrapper(adreno_gpu) || + adreno_has_rgmu(adreno_gpu) || adreno_gpu->info->family < ADRENO_6XX_GEN1) { /* * This can only be done before devm_pm_opp_of_add_table(), or @@ -1229,6 +1231,9 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev, if (ret) return ret; + init_completion(&adreno_gpu->fault_coredump_done); + complete_all(&adreno_gpu->fault_coredump_done); + pm_runtime_set_autosuspend_delay(dev, adreno_gpu->info->inactive_period); pm_runtime_use_autosuspend(dev); diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h index 390fa6720d9b..0f8d3de97636 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h @@ -27,6 +27,7 @@ enum { ADRENO_FW_PFP = 1, ADRENO_FW_GMU = 1, /* a6xx */ ADRENO_FW_GPMU = 2, + ADRENO_FW_AQE = 3, ADRENO_FW_MAX, }; @@ -50,6 +51,8 @@ enum adreno_family { ADRENO_7XX_GEN1, /* a730 family */ ADRENO_7XX_GEN2, /* a740 family */ ADRENO_7XX_GEN3, /* a750 family */ + ADRENO_8XX_GEN1, /* a830 family */ + ADRENO_8XX_GEN2, /* a840 family */ }; #define ADRENO_QUIRK_TWO_PASS_USE_WFI BIT(0) @@ -71,9 +74,14 @@ enum adreno_family { (((_c) >> 8) & 0xff), \ ((_c) & 0xff) +struct adreno_gpu; + struct adreno_gpu_funcs { struct msm_gpu_funcs base; + struct msm_gpu *(*init)(struct drm_device *dev); int (*get_timestamp)(struct msm_gpu *gpu, uint64_t *value); + void (*bus_halt)(struct adreno_gpu *adreno_gpu, bool gx_off); + int (*mmu_fault_handler)(void *arg, unsigned long iova, int flags, void *data); }; struct adreno_reglist { @@ -81,6 +89,13 @@ struct adreno_reglist { u32 value; }; +/* Reglist with pipe information */ +struct adreno_reglist_pipe { + u32 offset; + u32 value; + u32 pipe; +}; + struct adreno_speedbin { uint16_t fuse; uint16_t speedbin; @@ -101,7 +116,7 @@ struct adreno_info { const char *fw[ADRENO_FW_MAX]; uint32_t gmem; u64 quirks; - struct msm_gpu *(*init)(struct drm_device *dev); + const struct adreno_gpu_funcs *funcs; const char *zapfw; u32 inactive_period; union { @@ -180,6 +195,8 @@ struct adreno_gpu { uint16_t speedbin; const struct adreno_gpu_funcs *funcs; + struct completion fault_coredump_done; + /* interesting register offsets to dump: */ const unsigned int *registers; @@ -392,6 +409,16 @@ static inline int adreno_is_a610(const struct adreno_gpu *gpu) return adreno_is_revn(gpu, 610); } +static inline int adreno_is_a612(const struct adreno_gpu *gpu) +{ + return gpu->info->chip_ids[0] == 0x06010200; +} + +static inline bool adreno_has_rgmu(const struct adreno_gpu *gpu) +{ + return adreno_is_a612(gpu); +} + static inline int adreno_is_a618(const struct adreno_gpu *gpu) { return adreno_is_revn(gpu, 618); @@ -466,9 +493,9 @@ static inline int adreno_is_a610_family(const struct adreno_gpu *gpu) { if (WARN_ON_ONCE(!gpu->info)) return false; - - /* TODO: A612 */ - return adreno_is_a610(gpu) || adreno_is_a702(gpu); + return adreno_is_a610(gpu) || + adreno_is_a612(gpu) || + adreno_is_a702(gpu); } /* TODO: 615/616 */ @@ -548,6 +575,21 @@ static inline int adreno_is_a7xx(struct adreno_gpu *gpu) adreno_is_a740_family(gpu); } +static inline int adreno_is_a8xx(struct adreno_gpu *gpu) +{ + return gpu->info->family >= ADRENO_8XX_GEN1; +} + +static inline int adreno_is_x285(struct adreno_gpu *gpu) +{ + return gpu->info->chip_ids[0] == 0x44070001; +} + +static inline int adreno_is_a840(struct adreno_gpu *gpu) +{ + return gpu->info->chip_ids[0] == 0x44050a01; +} + /* Put vm_start above 32b to catch issues with not setting xyz_BASE_HI */ #define ADRENO_VM_START 0x100000000ULL u64 adreno_private_vm_size(struct msm_gpu *gpu); @@ -673,12 +715,6 @@ OUT_PKT7(struct msm_ringbuffer *ring, uint8_t opcode, uint16_t cnt) OUT_RING(ring, PKT7(opcode, cnt)); } -struct msm_gpu *a2xx_gpu_init(struct drm_device *dev); -struct msm_gpu *a3xx_gpu_init(struct drm_device *dev); -struct msm_gpu *a4xx_gpu_init(struct drm_device *dev); -struct msm_gpu *a5xx_gpu_init(struct drm_device *dev); -struct msm_gpu *a6xx_gpu_init(struct drm_device *dev); - static inline uint32_t get_wptr(struct msm_ringbuffer *ring) { return (ring->cur - ring->start) % (MSM_GPU_RINGBUFFER_SZ >> 2); diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_12_2_glymur.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_12_2_glymur.h new file mode 100644 index 000000000000..13bb43ba67d3 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_12_2_glymur.h @@ -0,0 +1,541 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2025 Linaro Limited + */ + +#ifndef _DPU_12_2_GLYMUR_H +#define _DPU_12_2_GLYMUR_H + +static const struct dpu_caps glymur_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 = 8192, + .pixel_ram_size = DEFAULT_PIXEL_RAM_SIZE, +}; + +static const struct dpu_mdp_cfg glymur_mdp = { + .name = "top_0", + .base = 0, .len = 0x494, + .clk_ctrls = { + [DPU_CLK_CTRL_REG_DMA] = { .reg_off = 0x2bc, .bit_off = 20 }, + }, +}; + +static const struct dpu_ctl_cfg glymur_ctl[] = { + { + .name = "ctl_0", .id = CTL_0, + .base = 0x15000, .len = 0x1000, + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 9), + }, { + .name = "ctl_1", .id = CTL_1, + .base = 0x16000, .len = 0x1000, + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 10), + }, { + .name = "ctl_2", .id = CTL_2, + .base = 0x17000, .len = 0x1000, + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 11), + }, { + .name = "ctl_3", .id = CTL_3, + .base = 0x18000, .len = 0x1000, + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 12), + }, { + .name = "ctl_4", .id = CTL_4, + .base = 0x19000, .len = 0x1000, + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 13), + }, { + .name = "ctl_5", .id = CTL_5, + .base = 0x1a000, .len = 0x1000, + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 23), + }, { + .name = "ctl_6", .id = CTL_6, + .base = 0x1b000, .len = 0x1000, + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 14), + }, { + .name = "ctl_7", .id = CTL_7, + .base = 0x1c000, .len = 0x1000, + .intr_start = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 15), + }, +}; + +static const struct dpu_sspp_cfg glymur_sspp[] = { + { + .name = "sspp_0", .id = SSPP_VIG0, + .base = 0x4000, .len = 0x344, + .features = VIG_SDM845_MASK_SDMA, + .sblk = &dpu_vig_sblk_qseed3_3_4, + .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_4, + .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_4, + .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_4, + .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 glymur_lm[] = { + { + .name = "lm_0", .id = LM_0, + .base = 0x44000, .len = 0x400, + .features = MIXER_MSM8998_MASK, + .sblk = &sm8750_lm_sblk, + .lm_pair = LM_1, + .pingpong = PINGPONG_0, + .dspp = DSPP_0, + }, { + .name = "lm_1", .id = LM_1, + .base = 0x45000, .len = 0x400, + .features = MIXER_MSM8998_MASK, + .sblk = &sm8750_lm_sblk, + .lm_pair = LM_0, + .pingpong = PINGPONG_1, + .dspp = DSPP_1, + }, { + .name = "lm_2", .id = LM_2, + .base = 0x46000, .len = 0x400, + .features = MIXER_MSM8998_MASK, + .sblk = &sm8750_lm_sblk, + .lm_pair = LM_3, + .pingpong = PINGPONG_2, + .dspp = DSPP_2, + }, { + .name = "lm_3", .id = LM_3, + .base = 0x47000, .len = 0x400, + .features = MIXER_MSM8998_MASK, + .sblk = &sm8750_lm_sblk, + .lm_pair = LM_2, + .pingpong = PINGPONG_3, + .dspp = DSPP_3, + }, { + .name = "lm_4", .id = LM_4, + .base = 0x48000, .len = 0x400, + .features = MIXER_MSM8998_MASK, + .sblk = &sm8750_lm_sblk, + .lm_pair = LM_5, + .pingpong = PINGPONG_4, + }, { + .name = "lm_5", .id = LM_5, + .base = 0x49000, .len = 0x400, + .features = MIXER_MSM8998_MASK, + .sblk = &sm8750_lm_sblk, + .lm_pair = LM_4, + .pingpong = PINGPONG_5, + }, { + .name = "lm_6", .id = LM_6, + .base = 0x4a000, .len = 0x400, + .features = MIXER_MSM8998_MASK, + .sblk = &sm8750_lm_sblk, + .lm_pair = LM_7, + .pingpong = PINGPONG_6, + }, { + .name = "lm_7", .id = LM_7, + .base = 0x4b000, .len = 0x400, + .features = MIXER_MSM8998_MASK, + .sblk = &sm8750_lm_sblk, + .lm_pair = LM_6, + .pingpong = PINGPONG_7, + }, +}; + +static const struct dpu_dspp_cfg glymur_dspp[] = { + { + .name = "dspp_0", .id = DSPP_0, + .base = 0x54000, .len = 0x1800, + .sblk = &sm8750_dspp_sblk, + }, { + .name = "dspp_1", .id = DSPP_1, + .base = 0x56000, .len = 0x1800, + .sblk = &sm8750_dspp_sblk, + }, { + .name = "dspp_2", .id = DSPP_2, + .base = 0x58000, .len = 0x1800, + .sblk = &sm8750_dspp_sblk, + }, { + .name = "dspp_3", .id = DSPP_3, + .base = 0x5a000, .len = 0x1800, + .sblk = &sm8750_dspp_sblk, + }, { + .name = "dspp_4", .id = DSPP_4, + .base = 0x5c000, .len = 0x1800, + .sblk = &sm8750_dspp_sblk, + }, { + .name = "dspp_5", .id = DSPP_5, + .base = 0x5e000, .len = 0x1800, + .sblk = &sm8750_dspp_sblk, + }, { + .name = "dspp_6", .id = DSPP_6, + .base = 0x60000, .len = 0x1800, + .sblk = &sm8750_dspp_sblk, + }, { + .name = "dspp_7", .id = DSPP_7, + .base = 0x62000, .len = 0x1800, + .sblk = &sm8750_dspp_sblk, + }, +}; + +static const struct dpu_pingpong_cfg glymur_pp[] = { + { + .name = "pingpong_0", .id = PINGPONG_0, + .base = 0x69000, .len = 0, + .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, + .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, + .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, + .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, + .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, + .sblk = &sc7280_pp_sblk, + .merge_3d = MERGE_3D_2, + .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 31), + }, { + .name = "pingpong_6", .id = PINGPONG_6, + .base = 0x6f000, .len = 0, + .sblk = &sc7280_pp_sblk, + .merge_3d = MERGE_3D_3, + .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 20), + }, { + .name = "pingpong_7", .id = PINGPONG_7, + .base = 0x70000, .len = 0, + .sblk = &sc7280_pp_sblk, + .merge_3d = MERGE_3D_3, + .intr_done = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR2, 21), + }, { + .name = "pingpong_cwb_0", .id = PINGPONG_CWB_0, + .base = 0x66000, .len = 0, + .sblk = &sc7280_pp_sblk, + .merge_3d = MERGE_3D_4, + }, { + .name = "pingpong_cwb_1", .id = PINGPONG_CWB_1, + .base = 0x66400, .len = 0, + .sblk = &sc7280_pp_sblk, + .merge_3d = MERGE_3D_4, + }, +}; + +static const struct dpu_merge_3d_cfg glymur_merge_3d[] = { + { + .name = "merge_3d_0", .id = MERGE_3D_0, + .base = 0x4e000, .len = 0x1c, + }, { + .name = "merge_3d_1", .id = MERGE_3D_1, + .base = 0x4f000, .len = 0x1c, + }, { + .name = "merge_3d_2", .id = MERGE_3D_2, + .base = 0x50000, .len = 0x1c, + }, { + .name = "merge_3d_3", .id = MERGE_3D_3, + .base = 0x51000, .len = 0x1c, + }, +}; + +/* + * 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 glymur_dsc[] = { + { + .name = "dce_0_0", .id = DSC_0, + .base = 0x80000, .len = 0x8, + .features = BIT(DPU_DSC_NATIVE_42x_EN), + .sblk = &sm8750_dsc_sblk_0, + }, { + .name = "dce_0_1", .id = DSC_1, + .base = 0x80000, .len = 0x8, + .features = BIT(DPU_DSC_NATIVE_42x_EN), + .sblk = &sm8750_dsc_sblk_1, + }, { + .name = "dce_1_0", .id = DSC_2, + .base = 0x81000, .len = 0x8, + .features = BIT(DPU_DSC_NATIVE_42x_EN), + .sblk = &sm8750_dsc_sblk_0, + }, { + .name = "dce_1_1", .id = DSC_3, + .base = 0x81000, .len = 0x8, + .features = BIT(DPU_DSC_NATIVE_42x_EN), + .sblk = &sm8750_dsc_sblk_1, + }, { + .name = "dce_2_0", .id = DSC_4, + .base = 0x82000, .len = 0x8, + .features = BIT(DPU_DSC_NATIVE_42x_EN), + .sblk = &sm8750_dsc_sblk_0, + }, { + .name = "dce_2_1", .id = DSC_5, + .base = 0x82000, .len = 0x8, + .features = BIT(DPU_DSC_NATIVE_42x_EN), + .sblk = &sm8750_dsc_sblk_1, + }, { + .name = "dce_3_0", .id = DSC_6, + .base = 0x83000, .len = 0x8, + .features = BIT(DPU_DSC_NATIVE_42x_EN), + .sblk = &sm8750_dsc_sblk_0, + }, { + .name = "dce_3_1", .id = DSC_7, + .base = 0x83000, .len = 0x8, + .features = BIT(DPU_DSC_NATIVE_42x_EN), + .sblk = &sm8750_dsc_sblk_1, + }, + +}; + +static const struct dpu_wb_cfg glymur_wb[] = { + { + .name = "wb_2", .id = WB_2, + .base = 0x65000, .len = 0x2c8, + .features = WB_SDM845_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_cwb_cfg glymur_cwb[] = { + { + .name = "cwb_0", .id = CWB_0, + .base = 0x66200, .len = 0x20, + }, + { + .name = "cwb_1", .id = CWB_1, + .base = 0x66600, .len = 0x20, + }, + { + .name = "cwb_2", .id = CWB_2, + .base = 0x7e200, .len = 0x20, + }, + { + .name = "cwb_3", .id = CWB_3, + .base = 0x7e600, .len = 0x20, + }, +}; + +static const struct dpu_intf_cfg glymur_intf[] = { + { + .name = "intf_0", .id = INTF_0, + .base = 0x34000, .len = 0x400, + .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 = 0x400, + .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 = 0x400, + .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 = 0x400, + .type = INTF_NONE, + .controller_id = MSM_DP_CONTROLLER_0, /* pair with intf_0 for DP MST */ + .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), + }, { + .name = "intf_4", .id = INTF_4, + .base = 0x38000, .len = 0x400, + .type = INTF_DP, + .controller_id = MSM_DP_CONTROLLER_1, + .prog_fetch_lines_worst_case = 24, + .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 20), + .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 21), + }, { + .name = "intf_5", .id = INTF_5, + .base = 0x39000, .len = 0x400, + .type = INTF_DP, + .controller_id = MSM_DP_CONTROLLER_3, + .prog_fetch_lines_worst_case = 24, + .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 22), + .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 23), + }, { + .name = "intf_6", .id = INTF_6, + .base = 0x3A000, .len = 0x400, + .type = INTF_DP, + .controller_id = MSM_DP_CONTROLLER_2, + .prog_fetch_lines_worst_case = 24, + .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 16), + .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 17), + }, { + .name = "intf_7", .id = INTF_7, + .base = 0x3b000, .len = 0x400, + .type = INTF_NONE, + .controller_id = MSM_DP_CONTROLLER_2, /* pair with intf_6 for DP MST */ + .prog_fetch_lines_worst_case = 24, + .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 18), + .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 19), + }, { + .name = "intf_8", .id = INTF_8, + .base = 0x3c000, .len = 0x400, + .type = INTF_NONE, + .controller_id = MSM_DP_CONTROLLER_1, /* pair with intf_4 for DP MST */ + .prog_fetch_lines_worst_case = 24, + .intr_underrun = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 12), + .intr_vsync = DPU_IRQ_IDX(MDP_SSPP_TOP0_INTR, 13), + }, +}; + +static const struct dpu_perf_cfg glymur_perf_data = { + .max_bw_low = 18900000, + .max_bw_high = 28500000, + .min_core_ib = 2500000, + .min_llcc_ib = 0, + .min_dram_ib = 800000, + .min_prefill_lines = 35, + .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 = 1, .wr_enable = 1}, + {.rd_enable = 1, .wr_enable = 0} + }, + .clk_inefficiency_factor = 105, + .bw_inefficiency_factor = 120, +}; + +static const struct dpu_mdss_version glymur_mdss_ver = { + .core_major_ver = 12, + .core_minor_ver = 2, +}; + +const struct dpu_mdss_cfg dpu_glymur_cfg = { + .mdss_ver = &glymur_mdss_ver, + .caps = &glymur_dpu_caps, + .mdp = &glymur_mdp, + .cdm = &dpu_cdm_5_x, + .ctl_count = ARRAY_SIZE(glymur_ctl), + .ctl = glymur_ctl, + .sspp_count = ARRAY_SIZE(glymur_sspp), + .sspp = glymur_sspp, + .mixer_count = ARRAY_SIZE(glymur_lm), + .mixer = glymur_lm, + .dspp_count = ARRAY_SIZE(glymur_dspp), + .dspp = glymur_dspp, + .pingpong_count = ARRAY_SIZE(glymur_pp), + .pingpong = glymur_pp, + .dsc_count = ARRAY_SIZE(glymur_dsc), + .dsc = glymur_dsc, + .merge_3d_count = ARRAY_SIZE(glymur_merge_3d), + .merge_3d = glymur_merge_3d, + .wb_count = ARRAY_SIZE(glymur_wb), + .wb = glymur_wb, + .cwb_count = ARRAY_SIZE(glymur_cwb), + .cwb = sm8650_cwb, + .intf_count = ARRAY_SIZE(glymur_intf), + .intf = glymur_intf, + .vbif_count = ARRAY_SIZE(sm8650_vbif), + .vbif = sm8650_vbif, + .perf = &glymur_perf_data, +}; + +#endif diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c index 4b970a59deaf..c39f1908ea65 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c @@ -200,7 +200,7 @@ static int dpu_crtc_get_lm_crc(struct drm_crtc *crtc, struct dpu_crtc_state *crtc_state) { struct dpu_crtc_mixer *m; - u32 crcs[CRTC_DUAL_MIXERS]; + u32 crcs[CRTC_QUAD_MIXERS]; int rc = 0; int i; @@ -400,7 +400,7 @@ static void _dpu_crtc_program_lm_output_roi(struct drm_crtc *crtc) static void _dpu_crtc_blend_setup_pipe(struct drm_crtc *crtc, struct drm_plane *plane, struct dpu_crtc_mixer *mixer, - u32 num_mixers, + u32 lms_in_pair, enum dpu_stage stage, const struct msm_format *format, uint64_t modifier, @@ -419,7 +419,7 @@ static void _dpu_crtc_blend_setup_pipe(struct drm_crtc *crtc, trace_dpu_crtc_setup_mixer(DRMID(crtc), DRMID(plane), state, to_dpu_plane_state(state), stage_idx, - format->pixel_format, + format->pixel_format, pipe, modifier); DRM_DEBUG_ATOMIC("crtc %d stage:%d - plane %d sspp %d fb %d multirect_idx %d\n", @@ -434,7 +434,7 @@ static void _dpu_crtc_blend_setup_pipe(struct drm_crtc *crtc, stage_cfg->multirect_index[stage][stage_idx] = pipe->multirect_index; /* blend config update */ - for (lm_idx = 0; lm_idx < num_mixers; lm_idx++) + for (lm_idx = 0; lm_idx < lms_in_pair; lm_idx++) mixer[lm_idx].lm_ctl->ops.update_pending_flush_sspp(mixer[lm_idx].lm_ctl, sspp_idx); } @@ -449,7 +449,7 @@ static void _dpu_crtc_blend_setup_mixer(struct drm_crtc *crtc, struct dpu_plane_state *pstate = NULL; const struct msm_format *format; struct dpu_hw_ctl *ctl = mixer->lm_ctl; - u32 lm_idx; + u32 lm_idx, stage, i, pipe_idx, head_pipe_in_stage, lms_in_pair; bool bg_alpha_enable = false; DECLARE_BITMAP(active_fetch, SSPP_MAX); DECLARE_BITMAP(active_pipes, SSPP_MAX); @@ -472,22 +472,25 @@ 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, active_fetch); - set_bit(pstate->pipe.sspp->idx, active_pipes); - _dpu_crtc_blend_setup_pipe(crtc, plane, - mixer, cstate->num_mixers, - pstate->stage, - format, fb ? fb->modifier : 0, - &pstate->pipe, 0, stage_cfg); - - if (pstate->r_pipe.sspp) { - set_bit(pstate->r_pipe.sspp->idx, active_fetch); - set_bit(pstate->r_pipe.sspp->idx, active_pipes); - _dpu_crtc_blend_setup_pipe(crtc, plane, - mixer, cstate->num_mixers, - pstate->stage, - format, fb ? fb->modifier : 0, - &pstate->r_pipe, 1, stage_cfg); + /* loop pipe per mixer pair with config in stage structure */ + for (stage = 0; stage < STAGES_PER_PLANE; stage++) { + head_pipe_in_stage = stage * PIPES_PER_STAGE; + for (i = 0; i < PIPES_PER_STAGE; i++) { + pipe_idx = i + head_pipe_in_stage; + if (!pstate->pipe[pipe_idx].sspp) + continue; + lms_in_pair = min(cstate->num_mixers - (stage * PIPES_PER_STAGE), + PIPES_PER_STAGE); + set_bit(pstate->pipe[pipe_idx].sspp->idx, active_fetch); + set_bit(pstate->pipe[pipe_idx].sspp->idx, active_pipes); + _dpu_crtc_blend_setup_pipe(crtc, plane, + &mixer[head_pipe_in_stage], + lms_in_pair, + pstate->stage, + format, fb ? fb->modifier : 0, + &pstate->pipe[pipe_idx], i, + &stage_cfg[stage]); + } } /* blend config update */ @@ -523,7 +526,7 @@ static void _dpu_crtc_blend_setup(struct drm_crtc *crtc) struct dpu_crtc_mixer *mixer = cstate->mixers; struct dpu_hw_ctl *ctl; struct dpu_hw_mixer *lm; - struct dpu_hw_stage_cfg stage_cfg; + struct dpu_hw_stage_cfg stage_cfg[STAGES_PER_PLANE]; DECLARE_BITMAP(active_lms, LM_MAX); int i; @@ -544,10 +547,10 @@ static void _dpu_crtc_blend_setup(struct drm_crtc *crtc) } /* initialize stage cfg */ - memset(&stage_cfg, 0, sizeof(struct dpu_hw_stage_cfg)); + memset(&stage_cfg, 0, sizeof(stage_cfg)); memset(active_lms, 0, sizeof(active_lms)); - _dpu_crtc_blend_setup_mixer(crtc, dpu_crtc, mixer, &stage_cfg); + _dpu_crtc_blend_setup_mixer(crtc, dpu_crtc, mixer, stage_cfg); for (i = 0; i < cstate->num_mixers; i++) { ctl = mixer[i].lm_ctl; @@ -568,13 +571,17 @@ static void _dpu_crtc_blend_setup(struct drm_crtc *crtc) mixer[i].mixer_op_mode, ctl->idx - CTL_0); + /* + * call dpu_hw_ctl_setup_blendstage() to blend layers per stage cfg. + * stage data is shared between PIPES_PER_STAGE pipes. + */ if (ctl->ops.setup_blendstage) ctl->ops.setup_blendstage(ctl, mixer[i].hw_lm->idx, - &stage_cfg); + &stage_cfg[i / PIPES_PER_STAGE]); if (lm->ops.setup_blendstage) lm->ops.setup_blendstage(lm, mixer[i].hw_lm->idx, - &stage_cfg); + &stage_cfg[i / PIPES_PER_STAGE]); } } @@ -1310,7 +1317,7 @@ done: return ret; } -#define MAX_CHANNELS_PER_CRTC 2 +#define MAX_CHANNELS_PER_CRTC PIPES_PER_PLANE #define MAX_HDISPLAY_SPLIT 1080 static struct msm_display_topology dpu_crtc_get_topology( @@ -1321,6 +1328,7 @@ static struct msm_display_topology dpu_crtc_get_topology( struct drm_display_mode *mode = &crtc_state->adjusted_mode; struct msm_display_topology topology = {0}; struct drm_encoder *drm_enc; + u32 num_rt_intf; drm_for_each_encoder_mask(drm_enc, crtc->dev, crtc_state->encoder_mask) dpu_encoder_update_topology(drm_enc, &topology, crtc_state->state, @@ -1334,11 +1342,14 @@ static struct msm_display_topology dpu_crtc_get_topology( * Dual display * 2 LM, 2 INTF ( Split display using 2 interfaces) * + * If DSC is enabled, try to use 4:4:2 topology if there is enough + * resource. Otherwise, use 2:2:2 topology. + * * 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 + * If DSC is enabled, use 2:2:1 topology * * Add dspps to the reservation requirements if ctm is requested * @@ -1350,14 +1361,23 @@ static struct msm_display_topology dpu_crtc_get_topology( * (mode->hdisplay > MAX_HDISPLAY_SPLIT) check. */ - if (topology.num_intf == 2 && !topology.cwb_enabled) - topology.num_lm = 2; - else if (topology.num_dsc == 2) + num_rt_intf = topology.num_intf; + if (topology.cwb_enabled) + num_rt_intf--; + + if (topology.num_dsc) { + if (dpu_kms->catalog->dsc_count >= num_rt_intf * 2) + topology.num_dsc = num_rt_intf * 2; + else + topology.num_dsc = num_rt_intf; + topology.num_lm = topology.num_dsc; + } else if (num_rt_intf == 2) { topology.num_lm = 2; - else if (dpu_kms->catalog->caps->has_3d_merge) + } else if (dpu_kms->catalog->caps->has_3d_merge) { topology.num_lm = (mode->hdisplay > MAX_HDISPLAY_SPLIT) ? 2 : 1; - else + } else { topology.num_lm = 1; + } if (crtc_state->ctm) topology.num_dspp = topology.num_lm; @@ -1545,6 +1565,9 @@ static enum drm_mode_status dpu_crtc_mode_valid(struct drm_crtc *crtc, adjusted_mode_clk = dpu_core_perf_adjusted_mode_clk(mode->clock, dpu_kms->perf.perf_cfg); + if (dpu_kms->catalog->caps->has_3d_merge) + adjusted_mode_clk /= 2; + /* * The given mode, adjusted for the perf clock factor, should not exceed * the max core clock rate @@ -1597,6 +1620,17 @@ int dpu_crtc_vblank(struct drm_crtc *crtc, bool en) return 0; } +/** + * dpu_crtc_get_num_lm - Get mixer number in this CRTC pipeline + * @state: Pointer to drm crtc state object + */ +unsigned int dpu_crtc_get_num_lm(const struct drm_crtc_state *state) +{ + struct dpu_crtc_state *cstate = to_dpu_crtc_state(state); + + return cstate->num_mixers; +} + #ifdef CONFIG_DEBUG_FS static int _dpu_debugfs_status_show(struct seq_file *s, void *data) { @@ -1679,15 +1713,15 @@ static int _dpu_debugfs_status_show(struct seq_file *s, void *data) seq_printf(s, "\tdst x:%4d dst_y:%4d dst_w:%4d dst_h:%4d\n", state->crtc_x, state->crtc_y, state->crtc_w, state->crtc_h); - seq_printf(s, "\tsspp[0]:%s\n", - pstate->pipe.sspp->cap->name); - seq_printf(s, "\tmultirect[0]: mode: %d index: %d\n", - pstate->pipe.multirect_mode, pstate->pipe.multirect_index); - if (pstate->r_pipe.sspp) { - seq_printf(s, "\tsspp[1]:%s\n", - pstate->r_pipe.sspp->cap->name); - seq_printf(s, "\tmultirect[1]: mode: %d index: %d\n", - pstate->r_pipe.multirect_mode, pstate->r_pipe.multirect_index); + + for (i = 0; i < PIPES_PER_PLANE; i++) { + if (!pstate->pipe[i].sspp) + continue; + seq_printf(s, "\tsspp[%d]:%s\n", + i, pstate->pipe[i].sspp->cap->name); + seq_printf(s, "\tmultirect[%d]: mode: %d index: %d\n", + i, pstate->pipe[i].multirect_mode, + pstate->pipe[i].multirect_index); } seq_puts(s, "\n"); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h index 94392b9b9245..455073c7025b 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h @@ -210,7 +210,7 @@ struct dpu_crtc_state { bool bw_control; bool bw_split_vote; - struct drm_rect lm_bounds[CRTC_DUAL_MIXERS]; + struct drm_rect lm_bounds[CRTC_QUAD_MIXERS]; uint64_t input_fence_timeout_ns; @@ -218,10 +218,10 @@ struct dpu_crtc_state { /* HW Resources reserved for the crtc */ u32 num_mixers; - struct dpu_crtc_mixer mixers[CRTC_DUAL_MIXERS]; + struct dpu_crtc_mixer mixers[CRTC_QUAD_MIXERS]; u32 num_ctls; - struct dpu_hw_ctl *hw_ctls[CRTC_DUAL_MIXERS]; + struct dpu_hw_ctl *hw_ctls[CRTC_QUAD_MIXERS]; enum dpu_crtc_crc_source crc_source; int crc_frame_skip_count; @@ -267,4 +267,6 @@ static inline enum dpu_crtc_client_type dpu_crtc_get_client_type( void dpu_crtc_frame_event_cb(struct drm_crtc *crtc, u32 event); +unsigned int dpu_crtc_get_num_lm(const struct drm_crtc_state *state); + #endif /* _DPU_CRTC_H_ */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index 258edaa18fc0..d1cfe81a3373 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -55,7 +55,8 @@ #define MAX_PHYS_ENCODERS_PER_VIRTUAL \ (MAX_H_TILES_PER_DISPLAY * NUM_PHYS_ENCODER_TYPES) -#define MAX_CHANNELS_PER_ENC 2 +#define MAX_CHANNELS_PER_ENC 4 +#define MAX_CWB_PER_ENC 2 #define IDLE_SHORT_TIMEOUT 1 @@ -182,7 +183,7 @@ 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_cwb *hw_cwb[MAX_CWB_PER_ENC]; struct dpu_hw_dsc *hw_dsc[MAX_CHANNELS_PER_ENC]; unsigned int dsc_mask; @@ -660,7 +661,6 @@ void dpu_encoder_update_topology(struct drm_encoder *drm_enc, 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; @@ -674,22 +674,12 @@ void dpu_encoder_update_topology(struct drm_encoder *drm_enc, dsc = dpu_encoder_get_dsc_config(drm_enc); - /* We only support 2 DSC mode (with 2 LM and 1 INTF) */ - if (dsc) { - /* - * 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. - */ - 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; - } + /* + * Set DSC number as 1 to mark the enabled status, will be adjusted + * in dpu_crtc_get_topology() + */ + if (dsc) + topology->num_dsc = 1; connector = drm_atomic_get_new_connector_for_encoder(state, drm_enc); if (!connector) @@ -1160,7 +1150,7 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_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_ctl, num_pp, num_dsc, num_pp_per_intf; int num_cwb = 0; bool is_cwb_encoder; unsigned int dsc_mask = 0; @@ -1239,10 +1229,16 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc, dpu_enc->cur_master->hw_cdm = hw_cdm ? to_dpu_hw_cdm(hw_cdm) : NULL; } + /* + * There may be 4 PP and 2 INTF for quad pipe case, so INTF is not + * mapped to PP 1:1. Let's calculate the stride with pipe/INTF + */ + num_pp_per_intf = num_pp / dpu_enc->num_phys_encs; + for (i = 0; i < dpu_enc->num_phys_encs; i++) { struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i]; - phys->hw_pp = dpu_enc->hw_pp[i]; + phys->hw_pp = dpu_enc->hw_pp[num_pp_per_intf * i]; if (!phys->hw_pp) { DPU_ERROR_ENC(dpu_enc, "no pp block assigned at idx: %d\n", i); @@ -2171,15 +2167,12 @@ void dpu_encoder_kickoff(struct drm_encoder *drm_enc) static void dpu_encoder_helper_reset_mixers(struct dpu_encoder_phys *phys_enc) { - struct dpu_hw_mixer_cfg mixer; int i, num_lm; struct dpu_global_state *global_state; - struct dpu_hw_blk *hw_lm[2]; - struct dpu_hw_mixer *hw_mixer[2]; + struct dpu_hw_blk *hw_lm[MAX_CHANNELS_PER_ENC]; + struct dpu_hw_mixer *hw_mixer[MAX_CHANNELS_PER_ENC]; struct dpu_hw_ctl *ctl = phys_enc->hw_ctl; - memset(&mixer, 0, sizeof(mixer)); - /* reset all mixers for this encoder */ if (ctl->ops.clear_all_blendstages) ctl->ops.clear_all_blendstages(ctl); @@ -2383,7 +2376,7 @@ void dpu_encoder_helper_phys_setup_cwb(struct dpu_encoder_phys *phys_enc, */ cwb_cfg.input = INPUT_MODE_LM_OUT; - for (int i = 0; i < MAX_CHANNELS_PER_ENC; i++) { + for (int i = 0; i < MAX_CWB_PER_ENC; i++) { hw_cwb = dpu_enc->hw_cwb[i]; if (!hw_cwb) continue; 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 61b22d949454..09395d7910ac 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h @@ -302,7 +302,7 @@ static inline enum dpu_3d_blend_mode dpu_encoder_helper_get_3d_blend_mode( /* Use merge_3d unless DSC MERGE topology is used */ if (phys_enc->split_role == ENC_ROLE_SOLO && - dpu_cstate->num_mixers == CRTC_DUAL_MIXERS && + (dpu_cstate->num_mixers != 1) && !dpu_encoder_use_dsc_merge(phys_enc->parent)) return BLEND_3D_H_ROW_INT; 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 6641455c4ec6..23bb39b471b7 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c @@ -267,8 +267,8 @@ static const u32 wb2_formats_rgb_yuv[] = { .base = 0x200, .len = 0xa0,}, \ .csc_blk = {.name = "csc", \ .base = 0x320, .len = 0x100,}, \ - .format_list = plane_formats_yuv, \ - .num_formats = ARRAY_SIZE(plane_formats_yuv), \ + .format_list = plane_formats, \ + .num_formats = ARRAY_SIZE(plane_formats), \ .rotation_cfg = NULL, \ } @@ -726,3 +726,4 @@ static const struct dpu_qos_lut_entry sc7180_qos_nrt[] = { #include "catalog/dpu_10_0_sm8650.h" #include "catalog/dpu_12_0_sm8750.h" +#include "catalog/dpu_12_2_glymur.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 f0768f54e9b3..336757103b5a 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h @@ -24,7 +24,7 @@ #define DPU_MAX_IMG_WIDTH 0x3fff #define DPU_MAX_IMG_HEIGHT 0x3fff -#define CRTC_DUAL_MIXERS 2 +#define CRTC_QUAD_MIXERS 4 #define MAX_XIN_COUNT 16 @@ -749,6 +749,7 @@ struct dpu_mdss_cfg { const struct dpu_format_extended *vig_formats; }; +extern const struct dpu_mdss_cfg dpu_glymur_cfg; extern const struct dpu_mdss_cfg dpu_msm8917_cfg; extern const struct dpu_mdss_cfg dpu_msm8937_cfg; extern const struct dpu_mdss_cfg dpu_msm8953_cfg; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.h index b7013c9822d2..cc7cc6f6f7cd 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.h @@ -71,12 +71,6 @@ struct dpu_hw_dsc *dpu_hw_dsc_init_1_2(struct drm_device *dev, const struct dpu_dsc_cfg *cfg, void __iomem *addr); -/** - * dpu_hw_dsc_destroy - destroys dsc driver context - * @dsc: Pointer to dsc driver context returned by dpu_hw_dsc_init - */ -void dpu_hw_dsc_destroy(struct dpu_hw_dsc *dsc); - static inline struct dpu_hw_dsc *to_dpu_hw_dsc(struct dpu_hw_blk *hw) { return container_of(hw, struct dpu_hw_dsc, base); 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 175639c8bfbb..31451241f083 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h @@ -34,7 +34,9 @@ #define DPU_MAX_PLANES 4 #endif +#define STAGES_PER_PLANE 2 #define PIPES_PER_STAGE 2 +#define PIPES_PER_PLANE (PIPES_PER_STAGE * STAGES_PER_PLANE) #ifndef DPU_MAX_DE_CURVES #define DPU_MAX_DE_CURVES 3 #endif @@ -149,6 +151,10 @@ enum dpu_dspp { DSPP_1, DSPP_2, DSPP_3, + DSPP_4, + DSPP_5, + DSPP_6, + DSPP_7, DSPP_MAX }; @@ -159,6 +165,8 @@ enum dpu_ctl { CTL_3, CTL_4, CTL_5, + CTL_6, + CTL_7, CTL_MAX }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c index 4e5a8ecd31f7..f4c9767c418d 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c @@ -1505,6 +1505,7 @@ static const struct dev_pm_ops dpu_pm_ops = { }; static const struct of_device_id dpu_dt_match[] = { + { .compatible = "qcom,glymur-dpu", .data = &dpu_glymur_cfg, }, { .compatible = "qcom,msm8917-mdp5", .data = &dpu_msm8917_cfg, }, { .compatible = "qcom,msm8937-mdp5", .data = &dpu_msm8937_cfg, }, { .compatible = "qcom,msm8953-mdp5", .data = &dpu_msm8953_cfg, }, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c index f54cf0faa1c7..d07a6ab6e7ee 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c @@ -500,13 +500,15 @@ static void _dpu_plane_setup_pixel_ext(struct dpu_hw_scaler3_cfg *scale_cfg, int i; for (i = 0; i < DPU_MAX_PLANES; i++) { + uint32_t w = src_w, h = src_h; + if (i == DPU_SSPP_COMP_1_2 || i == DPU_SSPP_COMP_2) { - src_w /= chroma_subsmpl_h; - src_h /= chroma_subsmpl_v; + w /= chroma_subsmpl_h; + h /= chroma_subsmpl_v; } - pixel_ext->num_ext_pxls_top[i] = src_h; - pixel_ext->num_ext_pxls_left[i] = src_w; + pixel_ext->num_ext_pxls_top[i] = h; + pixel_ext->num_ext_pxls_left[i] = w; } } @@ -620,6 +622,7 @@ static void _dpu_plane_color_fill(struct dpu_plane *pdpu, struct msm_drm_private *priv = plane->dev->dev_private; struct dpu_plane_state *pstate = to_dpu_plane_state(plane->state); u32 fill_color = (color & 0xFFFFFF) | ((alpha & 0xFF) << 24); + int i; DPU_DEBUG_PLANE(pdpu, "\n"); @@ -633,12 +636,13 @@ static void _dpu_plane_color_fill(struct dpu_plane *pdpu, return; /* update sspp */ - _dpu_plane_color_fill_pipe(pstate, &pstate->pipe, &pstate->pipe_cfg.dst_rect, - fill_color, fmt); - - if (pstate->r_pipe.sspp) - _dpu_plane_color_fill_pipe(pstate, &pstate->r_pipe, &pstate->r_pipe_cfg.dst_rect, + for (i = 0; i < PIPES_PER_PLANE; i++) { + if (!pstate->pipe[i].sspp) + continue; + _dpu_plane_color_fill_pipe(pstate, &pstate->pipe[i], + &pstate->pipe_cfg[i].dst_rect, fill_color, fmt); + } } static int dpu_plane_prepare_fb(struct drm_plane *plane, @@ -740,7 +744,7 @@ static int dpu_plane_atomic_check_pipe(struct dpu_plane *pdpu, * We already have verified scaling against platform limitations. * Now check if the SSPP supports scaling at all. */ - if (!sblk->scaler_blk.len && + if (!(sblk->scaler_blk.len && pipe->sspp->ops.setup_scaler) && ((drm_rect_width(&new_plane_state->src) >> 16 != drm_rect_width(&new_plane_state->dst)) || (drm_rect_height(&new_plane_state->src) >> 16 != @@ -820,10 +824,14 @@ static int dpu_plane_atomic_check_nosspp(struct drm_plane *plane, struct dpu_kms *kms = _dpu_plane_get_kms(&pdpu->base); u64 max_mdp_clk_rate = kms->perf.max_core_clk_rate; struct dpu_plane_state *pstate = to_dpu_plane_state(new_plane_state); - struct dpu_sw_pipe_cfg *pipe_cfg = &pstate->pipe_cfg; - struct dpu_sw_pipe_cfg *r_pipe_cfg = &pstate->r_pipe_cfg; + struct dpu_sw_pipe_cfg *pipe_cfg; + struct dpu_sw_pipe_cfg *r_pipe_cfg; + struct dpu_sw_pipe_cfg init_pipe_cfg; struct drm_rect fb_rect = { 0 }; + const struct drm_display_mode *mode = &crtc_state->adjusted_mode; uint32_t max_linewidth; + u32 num_lm; + int stage_id, num_stages; min_scale = FRAC_16_16(1, MAX_UPSCALE_RATIO); max_scale = MAX_DOWNSCALE_RATIO << 16; @@ -846,10 +854,10 @@ static int dpu_plane_atomic_check_nosspp(struct drm_plane *plane, return -EINVAL; } - /* state->src is 16.16, src_rect is not */ - drm_rect_fp_to_int(&pipe_cfg->src_rect, &new_plane_state->src); + num_lm = dpu_crtc_get_num_lm(crtc_state); - pipe_cfg->dst_rect = new_plane_state->dst; + /* state->src is 16.16, src_rect is not */ + drm_rect_fp_to_int(&init_pipe_cfg.src_rect, &new_plane_state->src); fb_rect.x2 = new_plane_state->fb->width; fb_rect.y2 = new_plane_state->fb->height; @@ -874,35 +882,94 @@ static int dpu_plane_atomic_check_nosspp(struct drm_plane *plane, max_linewidth = pdpu->catalog->caps->max_linewidth; - drm_rect_rotate(&pipe_cfg->src_rect, + drm_rect_rotate(&init_pipe_cfg.src_rect, new_plane_state->fb->width, new_plane_state->fb->height, new_plane_state->rotation); - if ((drm_rect_width(&pipe_cfg->src_rect) > max_linewidth) || - _dpu_plane_calc_clk(&crtc_state->adjusted_mode, pipe_cfg) > max_mdp_clk_rate) { - if (drm_rect_width(&pipe_cfg->src_rect) > 2 * max_linewidth) { - DPU_DEBUG_PLANE(pdpu, "invalid src " DRM_RECT_FMT " line:%u\n", - DRM_RECT_ARG(&pipe_cfg->src_rect), max_linewidth); - return -E2BIG; + /* + * We have 1 mixer pair cfg for 1:1:1 and 2:2:1 topology, 2 mixer pair + * configs for left and right half screen in case of 4:4:2 topology. + * But we may have 2 rect to split wide plane that exceeds limit with 1 + * config for 2:2:1. So need to handle both wide plane splitting, and + * two halves of screen splitting for quad-pipe case. Check dest + * rectangle left/right clipping first, then check wide rectangle + * splitting in every half next. + */ + num_stages = (num_lm + 1) / 2; + /* iterate mixer configs for this plane, to separate left/right with the id */ + for (stage_id = 0; stage_id < num_stages; stage_id++) { + struct drm_rect mixer_rect = { + .x1 = stage_id * mode->hdisplay / num_stages, + .y1 = 0, + .x2 = (stage_id + 1) * mode->hdisplay / num_stages, + .y2 = mode->vdisplay + }; + int cfg_idx = stage_id * PIPES_PER_STAGE; + + pipe_cfg = &pstate->pipe_cfg[cfg_idx]; + r_pipe_cfg = &pstate->pipe_cfg[cfg_idx + 1]; + + drm_rect_fp_to_int(&pipe_cfg->src_rect, &new_plane_state->src); + pipe_cfg->dst_rect = new_plane_state->dst; + + DPU_DEBUG_PLANE(pdpu, "checking src " DRM_RECT_FMT + " vs clip window " DRM_RECT_FMT "\n", + DRM_RECT_ARG(&pipe_cfg->src_rect), + DRM_RECT_ARG(&mixer_rect)); + + /* + * If this plane does not fall into mixer rect, check next + * mixer rect. + */ + if (!drm_rect_clip_scaled(&pipe_cfg->src_rect, + &pipe_cfg->dst_rect, + &mixer_rect)) { + memset(pipe_cfg, 0, 2 * sizeof(struct dpu_sw_pipe_cfg)); + + continue; } - *r_pipe_cfg = *pipe_cfg; - pipe_cfg->src_rect.x2 = (pipe_cfg->src_rect.x1 + pipe_cfg->src_rect.x2) >> 1; - pipe_cfg->dst_rect.x2 = (pipe_cfg->dst_rect.x1 + pipe_cfg->dst_rect.x2) >> 1; - r_pipe_cfg->src_rect.x1 = pipe_cfg->src_rect.x2; - r_pipe_cfg->dst_rect.x1 = pipe_cfg->dst_rect.x2; - } else { - memset(r_pipe_cfg, 0, sizeof(*r_pipe_cfg)); - } + pipe_cfg->dst_rect.x1 -= mixer_rect.x1; + pipe_cfg->dst_rect.x2 -= mixer_rect.x1; + + DPU_DEBUG_PLANE(pdpu, "Got clip src:" DRM_RECT_FMT " dst: " DRM_RECT_FMT "\n", + DRM_RECT_ARG(&pipe_cfg->src_rect), DRM_RECT_ARG(&pipe_cfg->dst_rect)); + + /* Split wide rect into 2 rect */ + if ((drm_rect_width(&pipe_cfg->src_rect) > max_linewidth) || + _dpu_plane_calc_clk(mode, pipe_cfg) > max_mdp_clk_rate) { + + if (drm_rect_width(&pipe_cfg->src_rect) > 2 * max_linewidth) { + DPU_DEBUG_PLANE(pdpu, "invalid src " DRM_RECT_FMT " line:%u\n", + DRM_RECT_ARG(&pipe_cfg->src_rect), max_linewidth); + return -E2BIG; + } + + memcpy(r_pipe_cfg, pipe_cfg, sizeof(struct dpu_sw_pipe_cfg)); + pipe_cfg->src_rect.x2 = (pipe_cfg->src_rect.x1 + pipe_cfg->src_rect.x2) >> 1; + pipe_cfg->dst_rect.x2 = (pipe_cfg->dst_rect.x1 + pipe_cfg->dst_rect.x2) >> 1; + r_pipe_cfg->src_rect.x1 = pipe_cfg->src_rect.x2; + r_pipe_cfg->dst_rect.x1 = pipe_cfg->dst_rect.x2; + DPU_DEBUG_PLANE(pdpu, "Split wide plane into:" + DRM_RECT_FMT " and " DRM_RECT_FMT "\n", + DRM_RECT_ARG(&pipe_cfg->src_rect), + DRM_RECT_ARG(&r_pipe_cfg->src_rect)); + } else { + memset(r_pipe_cfg, 0, sizeof(struct dpu_sw_pipe_cfg)); + } - drm_rect_rotate_inv(&pipe_cfg->src_rect, - new_plane_state->fb->width, new_plane_state->fb->height, - new_plane_state->rotation); - 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, + drm_rect_rotate_inv(&pipe_cfg->src_rect, + new_plane_state->fb->width, + new_plane_state->fb->height, new_plane_state->rotation); + 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); + } + pstate->needs_qos_remap = drm_atomic_crtc_needs_modeset(crtc_state); return 0; @@ -952,6 +1019,23 @@ static int dpu_plane_is_multirect_parallel_capable(struct dpu_hw_sspp *sspp, dpu_plane_is_parallel_capable(pipe_cfg, fmt, max_linewidth); } +static bool dpu_plane_get_single_pipe_in_stage(struct dpu_plane_state *pstate, + struct dpu_sw_pipe **single_pipe, + struct dpu_sw_pipe_cfg **single_pipe_cfg, + int stage_index) +{ + int pipe_idx; + + pipe_idx = stage_index * PIPES_PER_STAGE; + if (drm_rect_width(&pstate->pipe_cfg[pipe_idx].src_rect) != 0 && + drm_rect_width(&pstate->pipe_cfg[pipe_idx + 1].src_rect) == 0) { + *single_pipe = &pstate->pipe[pipe_idx]; + *single_pipe_cfg = &pstate->pipe_cfg[pipe_idx]; + return true; + } + + return false; +} static int dpu_plane_atomic_check_sspp(struct drm_plane *plane, struct drm_atomic_state *state, @@ -961,20 +1045,17 @@ static int dpu_plane_atomic_check_sspp(struct drm_plane *plane, drm_atomic_get_new_plane_state(state, plane); struct dpu_plane *pdpu = to_dpu_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; - struct dpu_sw_pipe_cfg *pipe_cfg = &pstate->pipe_cfg; - struct dpu_sw_pipe_cfg *r_pipe_cfg = &pstate->r_pipe_cfg; - int ret = 0; - - ret = dpu_plane_atomic_check_pipe(pdpu, pipe, pipe_cfg, - &crtc_state->adjusted_mode, - new_plane_state); - if (ret) - return ret; + struct dpu_sw_pipe *pipe; + struct dpu_sw_pipe_cfg *pipe_cfg; + int ret = 0, i; - if (drm_rect_width(&r_pipe_cfg->src_rect) != 0) { - ret = dpu_plane_atomic_check_pipe(pdpu, r_pipe, r_pipe_cfg, + for (i = 0; i < PIPES_PER_PLANE; i++) { + pipe = &pstate->pipe[i]; + pipe_cfg = &pstate->pipe_cfg[i]; + if (!drm_rect_width(&pipe_cfg->src_rect)) + continue; + DPU_DEBUG_PLANE(pdpu, "pipe %d is in use, validate it\n", i); + ret = dpu_plane_atomic_check_pipe(pdpu, pipe, pipe_cfg, &crtc_state->adjusted_mode, new_plane_state); if (ret) @@ -1017,17 +1098,20 @@ static bool dpu_plane_try_multirect_parallel(struct dpu_sw_pipe *pipe, struct dp 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) + uint32_t max_linewidth, int stage_index) { - 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; + struct dpu_sw_pipe *pipe, *prev_pipe; + struct dpu_sw_pipe_cfg *pipe_cfg, *prev_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 || + if (!dpu_plane_get_single_pipe_in_stage(pstate, &pipe, + &pipe_cfg, stage_index)) + return false; + + if (!dpu_plane_get_single_pipe_in_stage(prev_adjacent_pstate, + &prev_pipe, &prev_pipe_cfg, + stage_index) || prev_pipe->multirect_mode != DPU_SSPP_MULTIRECT_NONE) return false; @@ -1042,11 +1126,6 @@ static int dpu_plane_try_multirect_shared(struct dpu_plane_state *pstate, 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 || @@ -1087,10 +1166,10 @@ static int dpu_plane_atomic_check(struct drm_plane *plane, struct dpu_plane *pdpu = to_dpu_plane(plane); struct dpu_plane_state *pstate = to_dpu_plane_state(new_plane_state); 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; + struct dpu_sw_pipe *pipe = &pstate->pipe[0]; + struct dpu_sw_pipe *r_pipe = &pstate->pipe[1]; + struct dpu_sw_pipe_cfg *pipe_cfg = &pstate->pipe_cfg[0]; + struct dpu_sw_pipe_cfg *r_pipe_cfg = &pstate->pipe_cfg[1]; const struct drm_crtc_state *crtc_state = NULL; uint32_t max_linewidth = dpu_kms->catalog->caps->max_linewidth; @@ -1134,7 +1213,7 @@ static int dpu_plane_virtual_atomic_check(struct drm_plane *plane, 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 = NULL; - int ret; + int ret, i; if (IS_ERR(plane_state)) return PTR_ERR(plane_state); @@ -1152,8 +1231,8 @@ static int dpu_plane_virtual_atomic_check(struct drm_plane *plane, * resources are freed by dpu_crtc_assign_plane_resources(), * but clean them here. */ - pstate->pipe.sspp = NULL; - pstate->r_pipe.sspp = NULL; + for (i = 0; i < PIPES_PER_PLANE; i++) + pstate->pipe[i].sspp = NULL; return 0; } @@ -1175,37 +1254,72 @@ static int dpu_plane_virtual_atomic_check(struct drm_plane *plane, return 0; } +static int dpu_plane_assign_resource_in_stage(struct dpu_sw_pipe *pipe, + struct dpu_sw_pipe_cfg *pipe_cfg, + struct drm_plane_state *plane_state, + struct dpu_global_state *global_state, + struct drm_crtc *crtc, + struct dpu_rm_sspp_requirements *reqs) +{ + struct drm_plane *plane = plane_state->plane; + struct dpu_kms *dpu_kms = _dpu_plane_get_kms(plane); + struct dpu_sw_pipe *r_pipe = pipe + 1; + struct dpu_sw_pipe_cfg *r_pipe_cfg = pipe_cfg + 1; + + if (drm_rect_width(&pipe_cfg->src_rect) == 0) + return 0; + + pipe->sspp = dpu_rm_reserve_sspp(&dpu_kms->rm, global_state, crtc, reqs); + if (!pipe->sspp) + return -ENODEV; + pipe->multirect_index = DPU_SSPP_RECT_SOLO; + pipe->multirect_mode = DPU_SSPP_MULTIRECT_NONE; + + if (drm_rect_width(&r_pipe_cfg->src_rect) == 0) + return 0; + + 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)) + return 0; + + r_pipe->sspp = dpu_rm_reserve_sspp(&dpu_kms->rm, global_state, crtc, reqs); + if (!r_pipe->sspp) + return -ENODEV; + r_pipe->multirect_index = DPU_SSPP_RECT_SOLO; + r_pipe->multirect_mode = DPU_SSPP_MULTIRECT_NONE; + + 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) + 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_plane_state *pstate, *prev_adjacent_pstate[STAGES_PER_PLANE]; 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; + int i, ret; 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; + for (i = 0; i < STAGES_PER_PLANE; i++) + prev_adjacent_pstate[i] = prev_adjacent_plane_state[i] ? + to_dpu_plane_state(prev_adjacent_plane_state[i]) : NULL; + + for (i = 0; i < PIPES_PER_PLANE; i++) + pstate->pipe[i].sspp = NULL; if (!plane_state->fb) return -EINVAL; @@ -1217,42 +1331,24 @@ static int dpu_plane_virtual_assign_resources(struct drm_crtc *crtc, 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; + for (i = 0; i < STAGES_PER_PLANE; i++) { + if (prev_adjacent_pstate[i] && + dpu_plane_try_multirect_shared(pstate, prev_adjacent_pstate[i], fmt, + dpu_kms->catalog->caps->max_linewidth, + i)) + continue; - pipe->multirect_index = DPU_SSPP_RECT_SOLO; - pipe->multirect_mode = DPU_SSPP_MULTIRECT_NONE; + if (dpu_plane_get_single_pipe_in_stage(pstate, &pipe, &pipe_cfg, i)) + prev_adjacent_plane_state[i] = plane_state; - 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; - } + pipe = &pstate->pipe[i * PIPES_PER_STAGE]; + pipe_cfg = &pstate->pipe_cfg[i * PIPES_PER_STAGE]; + ret = dpu_plane_assign_resource_in_stage(pipe, pipe_cfg, + plane_state, + global_state, + crtc, &reqs); + if (ret) + return ret; } return dpu_plane_atomic_check_sspp(plane, state, crtc_state); @@ -1265,7 +1361,7 @@ int dpu_assign_plane_resources(struct dpu_global_state *global_state, unsigned int num_planes) { unsigned int i; - struct drm_plane_state *prev_adjacent_plane_state = NULL; + struct drm_plane_state *prev_adjacent_plane_state[STAGES_PER_PLANE] = { NULL }; for (i = 0; i < num_planes; i++) { struct drm_plane_state *plane_state = states[i]; @@ -1278,9 +1374,7 @@ int dpu_assign_plane_resources(struct dpu_global_state *global_state, state, plane_state, prev_adjacent_plane_state); if (ret) - break; - - prev_adjacent_plane_state = plane_state; + return ret; } return 0; @@ -1316,6 +1410,7 @@ void dpu_plane_flush(struct drm_plane *plane) { struct dpu_plane *pdpu; struct dpu_plane_state *pstate; + int i; if (!plane || !plane->state) { DPU_ERROR("invalid plane\n"); @@ -1336,8 +1431,8 @@ void dpu_plane_flush(struct drm_plane *plane) /* force 100% alpha */ _dpu_plane_color_fill(pdpu, pdpu->color_fill, 0xFF); else { - dpu_plane_flush_csc(pdpu, &pstate->pipe); - dpu_plane_flush_csc(pdpu, &pstate->r_pipe); + for (i = 0; i < PIPES_PER_PLANE; i++) + dpu_plane_flush_csc(pdpu, &pstate->pipe[i]); } /* flag h/w flush complete */ @@ -1438,15 +1533,12 @@ static void dpu_plane_sspp_atomic_update(struct drm_plane *plane, struct dpu_plane *pdpu = to_dpu_plane(plane); struct drm_plane_state *state = plane->state; struct dpu_plane_state *pstate = to_dpu_plane_state(state); - struct dpu_sw_pipe *pipe = &pstate->pipe; - struct dpu_sw_pipe *r_pipe = &pstate->r_pipe; struct drm_crtc *crtc = state->crtc; struct drm_framebuffer *fb = state->fb; bool is_rt_pipe; const struct msm_format *fmt = msm_framebuffer_format(fb); - struct dpu_sw_pipe_cfg *pipe_cfg = &pstate->pipe_cfg; - struct dpu_sw_pipe_cfg *r_pipe_cfg = &pstate->r_pipe_cfg; + int i; pstate->pending = true; @@ -1461,12 +1553,11 @@ static void dpu_plane_sspp_atomic_update(struct drm_plane *plane, crtc->base.id, DRM_RECT_ARG(&state->dst), &fmt->pixel_format, MSM_FORMAT_IS_UBWC(fmt)); - dpu_plane_sspp_update_pipe(plane, pipe, pipe_cfg, fmt, - drm_mode_vrefresh(&crtc->mode), - &pstate->layout); - - if (r_pipe->sspp) { - dpu_plane_sspp_update_pipe(plane, r_pipe, r_pipe_cfg, fmt, + for (i = 0; i < PIPES_PER_PLANE; i++) { + if (!drm_rect_width(&pstate->pipe_cfg[i].src_rect)) + continue; + dpu_plane_sspp_update_pipe(plane, &pstate->pipe[i], + &pstate->pipe_cfg[i], fmt, drm_mode_vrefresh(&crtc->mode), &pstate->layout); } @@ -1474,15 +1565,17 @@ static void dpu_plane_sspp_atomic_update(struct drm_plane *plane, if (pstate->needs_qos_remap) pstate->needs_qos_remap = false; - pstate->plane_fetch_bw = _dpu_plane_calc_bw(pdpu->catalog, fmt, - &crtc->mode, pipe_cfg); - - pstate->plane_clk = _dpu_plane_calc_clk(&crtc->mode, pipe_cfg); - - if (r_pipe->sspp) { - pstate->plane_fetch_bw += _dpu_plane_calc_bw(pdpu->catalog, fmt, &crtc->mode, r_pipe_cfg); + pstate->plane_fetch_bw = 0; + pstate->plane_clk = 0; + for (i = 0; i < PIPES_PER_PLANE; i++) { + if (!drm_rect_width(&pstate->pipe_cfg[i].src_rect)) + continue; + pstate->plane_fetch_bw += _dpu_plane_calc_bw(pdpu->catalog, fmt, + &crtc->mode, &pstate->pipe_cfg[i]); - pstate->plane_clk = max(pstate->plane_clk, _dpu_plane_calc_clk(&crtc->mode, r_pipe_cfg)); + pstate->plane_clk = max(pstate->plane_clk, + _dpu_plane_calc_clk(&crtc->mode, + &pstate->pipe_cfg[i])); } } @@ -1490,17 +1583,28 @@ static void _dpu_plane_atomic_disable(struct drm_plane *plane) { struct drm_plane_state *state = plane->state; struct dpu_plane_state *pstate = to_dpu_plane_state(state); - struct dpu_sw_pipe *r_pipe = &pstate->r_pipe; + struct dpu_sw_pipe *pipe; + int i; + + for (i = 0; i < PIPES_PER_PLANE; i += 1) { + pipe = &pstate->pipe[i]; + if (!pipe->sspp) + continue; - trace_dpu_plane_disable(DRMID(plane), false, - pstate->pipe.multirect_mode); + trace_dpu_plane_disable(DRMID(plane), false, + pstate->pipe[i].multirect_mode); - if (r_pipe->sspp) { - r_pipe->multirect_index = DPU_SSPP_RECT_SOLO; - r_pipe->multirect_mode = DPU_SSPP_MULTIRECT_NONE; + if (i % PIPES_PER_STAGE == 0) + continue; - if (r_pipe->sspp->ops.setup_multirect) - r_pipe->sspp->ops.setup_multirect(r_pipe); + /* + * clear multirect for the right pipe so that the SSPP + * can be further reused in the solo mode + */ + pipe->multirect_index = DPU_SSPP_RECT_SOLO; + pipe->multirect_mode = DPU_SSPP_MULTIRECT_NONE; + if (pipe->sspp->ops.setup_multirect) + pipe->sspp->ops.setup_multirect(pipe); } pstate->pending = true; @@ -1595,31 +1699,26 @@ static void dpu_plane_atomic_print_state(struct drm_printer *p, const struct drm_plane_state *state) { const struct dpu_plane_state *pstate = to_dpu_plane_state(state); - const struct dpu_sw_pipe *pipe = &pstate->pipe; - const struct dpu_sw_pipe_cfg *pipe_cfg = &pstate->pipe_cfg; - const struct dpu_sw_pipe *r_pipe = &pstate->r_pipe; - const struct dpu_sw_pipe_cfg *r_pipe_cfg = &pstate->r_pipe_cfg; + const struct dpu_sw_pipe *pipe; + const struct dpu_sw_pipe_cfg *pipe_cfg; + int i; drm_printf(p, "\tstage=%d\n", pstate->stage); - if (pipe->sspp) { - drm_printf(p, "\tsspp[0]=%s\n", pipe->sspp->cap->name); - drm_printf(p, "\tmultirect_mode[0]=%s\n", + for (i = 0; i < PIPES_PER_PLANE; i++) { + pipe = &pstate->pipe[i]; + if (!pipe->sspp) + continue; + pipe_cfg = &pstate->pipe_cfg[i]; + drm_printf(p, "\tsspp[%d]=%s\n", i, pipe->sspp->cap->name); + drm_printf(p, "\tmultirect_mode[%d]=%s\n", i, dpu_get_multirect_mode(pipe->multirect_mode)); - drm_printf(p, "\tmultirect_index[0]=%s\n", + drm_printf(p, "\tmultirect_index[%d]=%s\n", i, dpu_get_multirect_index(pipe->multirect_index)); - drm_printf(p, "\tsrc[0]=" DRM_RECT_FMT "\n", DRM_RECT_ARG(&pipe_cfg->src_rect)); - drm_printf(p, "\tdst[0]=" DRM_RECT_FMT "\n", DRM_RECT_ARG(&pipe_cfg->dst_rect)); - } - - if (r_pipe->sspp) { - drm_printf(p, "\tsspp[1]=%s\n", r_pipe->sspp->cap->name); - drm_printf(p, "\tmultirect_mode[1]=%s\n", - dpu_get_multirect_mode(r_pipe->multirect_mode)); - drm_printf(p, "\tmultirect_index[1]=%s\n", - dpu_get_multirect_index(r_pipe->multirect_index)); - drm_printf(p, "\tsrc[1]=" DRM_RECT_FMT "\n", DRM_RECT_ARG(&r_pipe_cfg->src_rect)); - drm_printf(p, "\tdst[1]=" DRM_RECT_FMT "\n", DRM_RECT_ARG(&r_pipe_cfg->dst_rect)); + drm_printf(p, "\tsrc[%d]=" DRM_RECT_FMT "\n", i, + DRM_RECT_ARG(&pipe_cfg->src_rect)); + drm_printf(p, "\tdst[%d]=" DRM_RECT_FMT "\n", i, + DRM_RECT_ARG(&pipe_cfg->dst_rect)); } } @@ -1657,14 +1756,17 @@ void dpu_plane_danger_signal_ctrl(struct drm_plane *plane, bool enable) struct dpu_plane *pdpu = to_dpu_plane(plane); struct dpu_plane_state *pstate = to_dpu_plane_state(plane->state); struct dpu_kms *dpu_kms = _dpu_plane_get_kms(plane); + int i; if (!pdpu->is_rt_pipe) return; pm_runtime_get_sync(&dpu_kms->pdev->dev); - _dpu_plane_set_qos_ctrl(plane, &pstate->pipe, enable); - if (pstate->r_pipe.sspp) - _dpu_plane_set_qos_ctrl(plane, &pstate->r_pipe, enable); + for (i = 0; i < PIPES_PER_PLANE; i++) { + if (!pstate->pipe[i].sspp) + continue; + _dpu_plane_set_qos_ctrl(plane, &pstate->pipe[i], enable); + } pm_runtime_put_sync(&dpu_kms->pdev->dev); } #endif diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h index a3a6e9028333..1ef5a041b8ac 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h @@ -17,10 +17,8 @@ /** * struct dpu_plane_state: Define dpu extension of drm plane state object * @base: base drm plane state object - * @pipe: software pipe description - * @r_pipe: software pipe description of the second pipe - * @pipe_cfg: software pipe configuration - * @r_pipe_cfg: software pipe configuration for the second pipe + * @pipe: software pipe description array + * @pipe_cfg: software pipe configuration array * @stage: assigned by crtc blender * @needs_qos_remap: qos remap settings need to be updated * @multirect_index: index of the rectangle of SSPP @@ -33,10 +31,8 @@ */ struct dpu_plane_state { struct drm_plane_state base; - 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; + struct dpu_sw_pipe pipe[PIPES_PER_PLANE]; + struct dpu_sw_pipe_cfg pipe_cfg[PIPES_PER_PLANE]; enum dpu_stage stage; bool needs_qos_remap; bool pending; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c index 2c77c74fac0f..f6568ed8375f 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c @@ -374,7 +374,11 @@ static int _dpu_rm_reserve_lms(struct dpu_rm *rm, if (!rm->mixer_blks[i]) continue; - lm_count = 0; + /* + * Reset lm_count to an even index. This will drop the previous + * primary mixer if failed to find its peer. + */ + lm_count &= ~1; lm_idx[lm_count] = i; if (!_dpu_rm_check_lm_and_get_connected_blks(rm, global_state, @@ -842,7 +846,7 @@ struct dpu_hw_sspp *dpu_rm_reserve_sspp(struct dpu_rm *rm, if (!reqs->scale && !reqs->yuv) hw_sspp = dpu_rm_try_sspp(rm, global_state, crtc, reqs, SSPP_TYPE_DMA); - if (!hw_sspp && reqs->scale) + if (!hw_sspp && !reqs->yuv) 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); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h index 5307cbc2007c..cb24ad2a6d8d 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h @@ -651,9 +651,9 @@ TRACE_EVENT(dpu_crtc_setup_mixer, TP_PROTO(uint32_t crtc_id, uint32_t plane_id, struct drm_plane_state *state, struct dpu_plane_state *pstate, uint32_t stage_idx, uint32_t pixel_format, - uint64_t modifier), + struct dpu_sw_pipe *pipe, uint64_t modifier), TP_ARGS(crtc_id, plane_id, state, pstate, stage_idx, - pixel_format, modifier), + pixel_format, pipe, modifier), TP_STRUCT__entry( __field( uint32_t, crtc_id ) __field( uint32_t, plane_id ) @@ -676,9 +676,9 @@ TRACE_EVENT(dpu_crtc_setup_mixer, __entry->dst_rect = drm_plane_state_dest(state); __entry->stage_idx = stage_idx; __entry->stage = pstate->stage; - __entry->sspp = pstate->pipe.sspp->idx; - __entry->multirect_idx = pstate->pipe.multirect_index; - __entry->multirect_mode = pstate->pipe.multirect_mode; + __entry->sspp = pipe->sspp->idx; + __entry->multirect_idx = pipe->multirect_index; + __entry->multirect_mode = pipe->multirect_mode; __entry->pixel_format = pixel_format; __entry->modifier = modifier; ), diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c index cd73468e369a..7545c0293efb 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_writeback.c @@ -72,6 +72,9 @@ static int dpu_wb_conn_atomic_check(struct drm_connector *connector, DPU_ERROR("invalid fb w=%d, maxlinewidth=%u\n", fb->width, dpu_wb_conn->maxlinewidth); return -EINVAL; + } else if (fb->modifier != DRM_FORMAT_MOD_LINEAR) { + DPU_ERROR("unsupported fb modifier:%#llx\n", fb->modifier); + return -EINVAL; } return drm_atomic_helper_check_wb_connector_state(conn_state->connector, conn_state->state); diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c index da53ca88251e..e8066f9fd534 100644 --- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c +++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c @@ -527,13 +527,14 @@ static void mdp4_crtc_wait_for_flush_done(struct drm_crtc *crtc) struct drm_device *dev = crtc->dev; struct mdp4_crtc *mdp4_crtc = to_mdp4_crtc(crtc); struct mdp4_kms *mdp4_kms = get_kms(crtc); + wait_queue_head_t *queue = drm_crtc_vblank_waitqueue(crtc); int ret; ret = drm_crtc_vblank_get(crtc); if (ret) return; - ret = wait_event_timeout(dev->vblank[drm_crtc_index(crtc)].queue, + ret = wait_event_timeout(*queue, !(mdp4_read(mdp4_kms, REG_MDP4_OVERLAY_FLUSH) & mdp4_crtc->flushed_mask), msecs_to_jiffies(50)); diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c index 4c4900a7beda..373ae7d9bf01 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c @@ -1234,6 +1234,7 @@ static void mdp5_crtc_wait_for_flush_done(struct drm_crtc *crtc) struct mdp5_crtc *mdp5_crtc = to_mdp5_crtc(crtc); struct mdp5_crtc_state *mdp5_cstate = to_mdp5_crtc_state(crtc->state); struct mdp5_ctl *ctl = mdp5_cstate->ctl; + wait_queue_head_t *queue = drm_crtc_vblank_waitqueue(crtc); int ret; /* Should not call this function if crtc is disabled. */ @@ -1244,7 +1245,7 @@ static void mdp5_crtc_wait_for_flush_done(struct drm_crtc *crtc) if (ret) return; - ret = wait_event_timeout(dev->vblank[drm_crtc_index(crtc)].queue, + ret = wait_event_timeout(*queue, ((mdp5_ctl_get_commit_status(ctl) & mdp5_crtc->flushed_mask) == 0), msecs_to_jiffies(50)); diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c index 7c790406d533..4ca183fb61a9 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c @@ -336,8 +336,7 @@ static int mdp5_plane_atomic_check(struct drm_plane *plane, if (!crtc) return 0; - crtc_state = drm_atomic_get_existing_crtc_state(state, - crtc); + crtc_state = drm_atomic_get_new_crtc_state(state, crtc); if (WARN_ON(!crtc_state)) return -EINVAL; @@ -373,8 +372,8 @@ static int mdp5_plane_atomic_async_check(struct drm_plane *plane, int min_scale, max_scale; int ret; - crtc_state = drm_atomic_get_existing_crtc_state(state, - new_plane_state->crtc); + crtc_state = drm_atomic_get_new_crtc_state(state, + new_plane_state->crtc); if (WARN_ON(!crtc_state)) return -EINVAL; diff --git a/drivers/gpu/drm/msm/disp/msm_disp_snapshot.h b/drivers/gpu/drm/msm/disp/msm_disp_snapshot.h index b5f452bd7ada..53bd1dcde15f 100644 --- a/drivers/gpu/drm/msm/disp/msm_disp_snapshot.h +++ b/drivers/gpu/drm/msm/disp/msm_disp_snapshot.h @@ -38,6 +38,7 @@ * struct msm_disp_state - structure to store current dpu state * @dev: device pointer * @drm_dev: drm device pointer + * @blocks: list head for hardware state blocks * @atomic_state: atomic state duplicated at the time of the error * @time: timestamp at which the coredump was captured */ @@ -55,7 +56,7 @@ struct msm_disp_state { /** * struct msm_disp_state_block - structure to store each hardware block state * @name: name of the block - * @drm_dev: handle to the linked list head + * @node: handle to the linked list head * @size: size of the register space of this hardware block * @state: array holding the register dump of this hardware block * @base_addr: starting address of this hardware block's register space @@ -88,8 +89,9 @@ void msm_disp_snapshot_destroy(struct drm_device *drm_dev); * msm_disp_snapshot_state_sync - synchronously snapshot display state * @kms: the kms object * - * Returns state or error + * Returns: state or error * + * Context: * Must be called with &kms->dump_mutex held */ struct msm_disp_state *msm_disp_snapshot_state_sync(struct msm_kms *kms); @@ -97,7 +99,7 @@ struct msm_disp_state *msm_disp_snapshot_state_sync(struct msm_kms *kms); /** * msm_disp_snapshot_state - trigger to dump the display snapshot * @drm_dev: handle to drm device - + * * Returns: none */ void msm_disp_snapshot_state(struct drm_device *drm_dev); @@ -114,7 +116,7 @@ void msm_disp_state_print(struct msm_disp_state *disp_state, struct drm_printer /** * msm_disp_snapshot_capture_state - utility to capture atomic state and hw registers * @disp_state: handle to msm_disp_state struct - + * * Returns: none */ void msm_disp_snapshot_capture_state(struct msm_disp_state *disp_state); @@ -122,7 +124,7 @@ void msm_disp_snapshot_capture_state(struct msm_disp_state *disp_state); /** * msm_disp_state_free - free the memory after the coredump has been read * @data: handle to struct msm_disp_state - + * * Returns: none */ void msm_disp_state_free(void *data); @@ -130,7 +132,6 @@ void msm_disp_state_free(void *data); /** * msm_disp_snapshot_add_block - add a hardware block with its register dump * @disp_state: handle to struct msm_disp_state - * @name: name of the hardware block * @len: size of the register space of the hardware block * @base_addr: starting address of the register space of the hardware block * @fmt: format in which the block names need to be printed diff --git a/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c b/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c index 071bcdea80f7..19b470968f4d 100644 --- a/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c +++ b/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c @@ -82,8 +82,7 @@ void msm_disp_state_print(struct msm_disp_state *state, struct drm_printer *p) drm_printf(p, "kernel: " UTS_RELEASE "\n"); drm_printf(p, "module: " KBUILD_MODNAME "\n"); drm_printf(p, "dpu devcoredump\n"); - drm_printf(p, "time: %lld.%09ld\n", - state->time.tv_sec, state->time.tv_nsec); + drm_printf(p, "time: %ptSp\n", &state->time); list_for_each_entry_safe(block, tmp, &state->blocks, node) { drm_printf(p, "====================%s================\n", block->name); diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c index c42fd2c17a32..cbcc7c2f0ffc 100644 --- a/drivers/gpu/drm/msm/dp/dp_ctrl.c +++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c @@ -423,13 +423,13 @@ static void msm_dp_ctrl_config_ctrl(struct msm_dp_ctrl_private *ctrl) static void msm_dp_ctrl_lane_mapping(struct msm_dp_ctrl_private *ctrl) { - u32 ln_0 = 0, ln_1 = 1, ln_2 = 2, ln_3 = 3; /* One-to-One mapping */ + u32 *lane_map = ctrl->link->lane_map; u32 ln_mapping; - ln_mapping = ln_0 << LANE0_MAPPING_SHIFT; - ln_mapping |= ln_1 << LANE1_MAPPING_SHIFT; - ln_mapping |= ln_2 << LANE2_MAPPING_SHIFT; - ln_mapping |= ln_3 << LANE3_MAPPING_SHIFT; + ln_mapping = lane_map[0] << LANE0_MAPPING_SHIFT; + ln_mapping |= lane_map[1] << LANE1_MAPPING_SHIFT; + ln_mapping |= lane_map[2] << LANE2_MAPPING_SHIFT; + ln_mapping |= lane_map[3] << LANE3_MAPPING_SHIFT; msm_dp_write_link(ctrl, REG_DP_LOGICAL2PHYSICAL_LANE_MAPPING, ln_mapping); diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index d87d47cc7ec3..9bd9cd5c1e03 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -130,6 +130,14 @@ struct msm_dp_desc { bool wide_bus_supported; }; +static const struct msm_dp_desc msm_dp_desc_glymur[] = { + { .io_start = 0x0af54000, .id = MSM_DP_CONTROLLER_0, .wide_bus_supported = true }, + { .io_start = 0x0af5c000, .id = MSM_DP_CONTROLLER_1, .wide_bus_supported = true }, + { .io_start = 0x0af64000, .id = MSM_DP_CONTROLLER_2, .wide_bus_supported = true }, + { .io_start = 0x0af6c000, .id = MSM_DP_CONTROLLER_3, .wide_bus_supported = true }, + {} +}; + static const struct msm_dp_desc msm_dp_desc_sa8775p[] = { { .io_start = 0x0af54000, .id = MSM_DP_CONTROLLER_0, .wide_bus_supported = true }, { .io_start = 0x0af5c000, .id = MSM_DP_CONTROLLER_1, .wide_bus_supported = true }, @@ -187,6 +195,7 @@ static const struct msm_dp_desc msm_dp_desc_x1e80100[] = { }; static const struct of_device_id msm_dp_dt_match[] = { + { .compatible = "qcom,glymur-dp", .data = &msm_dp_desc_glymur }, { .compatible = "qcom,sa8775p-dp", .data = &msm_dp_desc_sa8775p }, { .compatible = "qcom,sc7180-dp", .data = &msm_dp_desc_sc7180 }, { .compatible = "qcom,sc7280-dp", .data = &msm_dp_desc_sc7280 }, diff --git a/drivers/gpu/drm/msm/dp/dp_link.c b/drivers/gpu/drm/msm/dp/dp_link.c index 66e1bbd80db3..34a91e194a12 100644 --- a/drivers/gpu/drm/msm/dp/dp_link.c +++ b/drivers/gpu/drm/msm/dp/dp_link.c @@ -6,12 +6,14 @@ #define pr_fmt(fmt) "[drm-dp] %s: " fmt, __func__ #include <drm/drm_device.h> +#include <drm/drm_of.h> #include <drm/drm_print.h> #include "dp_reg.h" #include "dp_link.h" #include "dp_panel.h" +#define DP_LINK_RATE_HBR2 540000 /* kbytes */ #define DP_TEST_REQUEST_MASK 0x7F enum audio_sample_rate { @@ -1210,10 +1212,121 @@ u32 msm_dp_link_get_test_bits_depth(struct msm_dp_link *msm_dp_link, u32 bpp) return tbd; } +static u32 msm_dp_link_link_frequencies(struct device_node *of_node) +{ + struct device_node *endpoint; + u64 frequency = 0; + int cnt; + + endpoint = of_graph_get_endpoint_by_regs(of_node, 1, 0); /* port@1 */ + if (!endpoint) + return 0; + + cnt = of_property_count_u64_elems(endpoint, "link-frequencies"); + + if (cnt > 0) + of_property_read_u64_index(endpoint, "link-frequencies", + cnt - 1, &frequency); + of_node_put(endpoint); + + do_div(frequency, + 10 * /* from symbol rate to link rate */ + 1000); /* kbytes */ + + return frequency; +} + +/* + * Always populate msm_dp_link->lane_map with 4 lanes. + * - Use DTS "data-lanes" if present; otherwise fall back to default mapping. + * - For partial definitions, fill remaining entries with unused lanes in + * ascending order. + */ +static int msm_dp_link_lane_map(struct device *dev, struct msm_dp_link *msm_dp_link) +{ + struct device_node *of_node = dev->of_node; + struct device_node *endpoint; + int cnt = msm_dp_link->max_dp_lanes; + u32 tmp[DP_MAX_NUM_DP_LANES]; + u32 map[DP_MAX_NUM_DP_LANES] = {0, 1, 2, 3}; /* default 1:1 mapping */ + bool used[DP_MAX_NUM_DP_LANES] = {false}; + int i, j = 0, ret = -EINVAL; + + endpoint = of_graph_get_endpoint_by_regs(of_node, 1, -1); + if (endpoint) { + ret = of_property_read_u32_array(endpoint, "data-lanes", tmp, cnt); + if (ret) + dev_dbg(dev, "endpoint data-lanes read failed (ret=%d)\n", ret); + } + + if (ret) { + ret = of_property_read_u32_array(of_node, "data-lanes", tmp, cnt); + if (ret) { + dev_info(dev, "data-lanes not defined, set to default\n"); + goto out; + } + } + + for (i = 0; i < cnt; i++) { + if (tmp[i] >= DP_MAX_NUM_DP_LANES) { + dev_err(dev, "data-lanes[%d]=%u out of range\n", i, tmp[i]); + return -EINVAL; + } + used[tmp[i]] = true; + map[i] = tmp[i]; + } + + /* Fill the remaining entries with unused physical lanes (ascending) */ + for (i = cnt; i < DP_MAX_NUM_DP_LANES && j < DP_MAX_NUM_DP_LANES; j++) { + if (!used[j]) + map[i++] = j; + } + +out: + if (endpoint) + of_node_put(endpoint); + + dev_dbg(dev, "data-lanes count %d <%d %d %d %d>\n", cnt, map[0], map[1], map[2], map[3]); + memcpy(msm_dp_link->lane_map, map, sizeof(map)); + return 0; +} + +static int msm_dp_link_parse_dt(struct device *dev, struct msm_dp_link *msm_dp_link) +{ + struct device_node *of_node = dev->of_node; + int cnt; + + /* + * data-lanes is the property of msm_dp_out endpoint + */ + cnt = drm_of_get_data_lanes_count_ep(of_node, 1, 0, 1, DP_MAX_NUM_DP_LANES); + if (cnt < 0) { + /* legacy code, data-lanes is the property of mdss_dp node */ + cnt = drm_of_get_data_lanes_count(of_node, 1, DP_MAX_NUM_DP_LANES); + } + + if (cnt > 0) + msm_dp_link->max_dp_lanes = cnt; + else + msm_dp_link->max_dp_lanes = DP_MAX_NUM_DP_LANES; /* 4 lanes */ + + if (msm_dp_link_lane_map(dev, msm_dp_link)) { + dev_err(dev, "failed to parse data-lanes\n"); + return -EINVAL; + } + + msm_dp_link->max_dp_link_rate = msm_dp_link_link_frequencies(of_node); + if (!msm_dp_link->max_dp_link_rate) + msm_dp_link->max_dp_link_rate = DP_LINK_RATE_HBR2; + + return 0; +} + struct msm_dp_link *msm_dp_link_get(struct device *dev, struct drm_dp_aux *aux) { struct msm_dp_link_private *link; struct msm_dp_link *msm_dp_link; + int ret; if (!dev || !aux) { DRM_ERROR("invalid input\n"); @@ -1229,5 +1342,9 @@ struct msm_dp_link *msm_dp_link_get(struct device *dev, struct drm_dp_aux *aux) mutex_init(&link->psm_mutex); msm_dp_link = &link->msm_dp_link; + ret = msm_dp_link_parse_dt(dev, msm_dp_link); + if (ret) + return ERR_PTR(ret); + return msm_dp_link; } diff --git a/drivers/gpu/drm/msm/dp/dp_link.h b/drivers/gpu/drm/msm/dp/dp_link.h index ba47c6d19fbf..b1eb2de6d2a7 100644 --- a/drivers/gpu/drm/msm/dp/dp_link.h +++ b/drivers/gpu/drm/msm/dp/dp_link.h @@ -12,6 +12,7 @@ #define DS_PORT_STATUS_CHANGED 0x200 #define DP_TEST_BIT_DEPTH_UNKNOWN 0xFFFFFFFF #define DP_LINK_CAP_ENHANCED_FRAMING (1 << 0) +#define DP_MAX_NUM_DP_LANES 4 struct msm_dp_link_info { unsigned char revision; @@ -72,6 +73,10 @@ struct msm_dp_link { struct msm_dp_link_test_audio test_audio; struct msm_dp_link_phy_params phy_params; struct msm_dp_link_info link_params; + + u32 lane_map[DP_MAX_NUM_DP_LANES]; + u32 max_dp_lanes; + u32 max_dp_link_rate; }; /** diff --git a/drivers/gpu/drm/msm/dp/dp_panel.c b/drivers/gpu/drm/msm/dp/dp_panel.c index 15b7f6c7146e..ad5d55bf009d 100644 --- a/drivers/gpu/drm/msm/dp/dp_panel.c +++ b/drivers/gpu/drm/msm/dp/dp_panel.c @@ -16,9 +16,6 @@ #define DP_INTF_CONFIG_DATABUS_WIDEN BIT(4) -#define DP_MAX_NUM_DP_LANES 4 -#define DP_LINK_RATE_HBR2 540000 /* kbytes */ - struct msm_dp_panel_private { struct device *dev; struct drm_device *drm_dev; @@ -91,6 +88,7 @@ static int msm_dp_panel_read_dpcd(struct msm_dp_panel *msm_dp_panel) int rc, max_lttpr_lanes, max_lttpr_rate; struct msm_dp_panel_private *panel; struct msm_dp_link_info *link_info; + struct msm_dp_link *link; u8 *dpcd, major, minor; panel = container_of(msm_dp_panel, struct msm_dp_panel_private, msm_dp_panel); @@ -105,16 +103,20 @@ static int msm_dp_panel_read_dpcd(struct msm_dp_panel *msm_dp_panel) major = (link_info->revision >> 4) & 0x0f; minor = link_info->revision & 0x0f; + link = panel->link; + drm_dbg_dp(panel->drm_dev, "max_lanes=%d max_link_rate=%d\n", + link->max_dp_lanes, link->max_dp_link_rate); + link_info->rate = drm_dp_max_link_rate(dpcd); link_info->num_lanes = drm_dp_max_lane_count(dpcd); /* Limit data lanes from data-lanes of endpoint property of dtsi */ - if (link_info->num_lanes > msm_dp_panel->max_dp_lanes) - link_info->num_lanes = msm_dp_panel->max_dp_lanes; + if (link_info->num_lanes > link->max_dp_lanes) + link_info->num_lanes = link->max_dp_lanes; /* Limit link rate from link-frequencies of endpoint property of dtsi */ - if (link_info->rate > msm_dp_panel->max_dp_link_rate) - link_info->rate = msm_dp_panel->max_dp_link_rate; + if (link_info->rate > link->max_dp_link_rate) + link_info->rate = link->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); @@ -173,9 +175,6 @@ int msm_dp_panel_read_sink_caps(struct msm_dp_panel *msm_dp_panel, panel = container_of(msm_dp_panel, struct msm_dp_panel_private, msm_dp_panel); - drm_dbg_dp(panel->drm_dev, "max_lanes=%d max_link_rate=%d\n", - msm_dp_panel->max_dp_lanes, msm_dp_panel->max_dp_link_rate); - rc = msm_dp_panel_read_dpcd(msm_dp_panel); if (rc) { DRM_ERROR("read dpcd failed %d\n", rc); @@ -648,60 +647,6 @@ int msm_dp_panel_init_panel_info(struct msm_dp_panel *msm_dp_panel) return 0; } -static u32 msm_dp_panel_link_frequencies(struct device_node *of_node) -{ - struct device_node *endpoint; - u64 frequency = 0; - int cnt; - - endpoint = of_graph_get_endpoint_by_regs(of_node, 1, 0); /* port@1 */ - if (!endpoint) - return 0; - - cnt = of_property_count_u64_elems(endpoint, "link-frequencies"); - - if (cnt > 0) - of_property_read_u64_index(endpoint, "link-frequencies", - cnt - 1, &frequency); - of_node_put(endpoint); - - do_div(frequency, - 10 * /* from symbol rate to link rate */ - 1000); /* kbytes */ - - return frequency; -} - -static int msm_dp_panel_parse_dt(struct msm_dp_panel *msm_dp_panel) -{ - struct msm_dp_panel_private *panel; - struct device_node *of_node; - int cnt; - - panel = container_of(msm_dp_panel, struct msm_dp_panel_private, msm_dp_panel); - of_node = panel->dev->of_node; - - /* - * data-lanes is the property of msm_dp_out endpoint - */ - cnt = drm_of_get_data_lanes_count_ep(of_node, 1, 0, 1, DP_MAX_NUM_DP_LANES); - if (cnt < 0) { - /* legacy code, data-lanes is the property of mdss_dp node */ - cnt = drm_of_get_data_lanes_count(of_node, 1, DP_MAX_NUM_DP_LANES); - } - - if (cnt > 0) - msm_dp_panel->max_dp_lanes = cnt; - else - msm_dp_panel->max_dp_lanes = DP_MAX_NUM_DP_LANES; /* 4 lanes */ - - msm_dp_panel->max_dp_link_rate = msm_dp_panel_link_frequencies(of_node); - if (!msm_dp_panel->max_dp_link_rate) - msm_dp_panel->max_dp_link_rate = DP_LINK_RATE_HBR2; - - return 0; -} - struct msm_dp_panel *msm_dp_panel_get(struct device *dev, struct drm_dp_aux *aux, struct msm_dp_link *link, void __iomem *link_base, @@ -709,7 +654,6 @@ struct msm_dp_panel *msm_dp_panel_get(struct device *dev, struct drm_dp_aux *aux { struct msm_dp_panel_private *panel; struct msm_dp_panel *msm_dp_panel; - int ret; if (!dev || !aux || !link) { DRM_ERROR("invalid input\n"); @@ -729,10 +673,6 @@ struct msm_dp_panel *msm_dp_panel_get(struct device *dev, struct drm_dp_aux *aux msm_dp_panel = &panel->msm_dp_panel; msm_dp_panel->max_bw_code = DP_LINK_BW_8_1; - ret = msm_dp_panel_parse_dt(msm_dp_panel); - if (ret) - return ERR_PTR(ret); - return msm_dp_panel; } diff --git a/drivers/gpu/drm/msm/dp/dp_panel.h b/drivers/gpu/drm/msm/dp/dp_panel.h index d2cf401506dc..921a296852d4 100644 --- a/drivers/gpu/drm/msm/dp/dp_panel.h +++ b/drivers/gpu/drm/msm/dp/dp_panel.h @@ -41,9 +41,6 @@ struct msm_dp_panel { bool vsc_sdp_supported; u32 hw_revision; - u32 max_dp_lanes; - u32 max_dp_link_rate; - u32 max_bw_code; }; diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h index e391505fdaf0..3cbf08231492 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h @@ -109,7 +109,6 @@ struct msm_dsi_phy { struct msm_dsi_dphy_timing timing; const struct msm_dsi_phy_cfg *cfg; void *tuning_cfg; - void *pll_data; enum msm_dsi_phy_usecase usecase; bool regulator_ldo_mode; 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 32f06edd21a9..c5e1d2016bcc 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c @@ -426,11 +426,8 @@ static void dsi_pll_enable_pll_bias(struct dsi_pll_7nm *pll) u32 data; spin_lock_irqsave(&pll->pll_enable_lock, flags); - if (pll->pll_enable_cnt++) { - spin_unlock_irqrestore(&pll->pll_enable_lock, flags); - WARN_ON(pll->pll_enable_cnt == INT_MAX); - return; - } + pll->pll_enable_cnt++; + WARN_ON(pll->pll_enable_cnt == INT_MAX); data = readl(pll->phy->base + REG_DSI_7nm_PHY_CMN_CTRL_0); data |= DSI_7nm_PHY_CMN_CTRL_0_PLL_SHUTDOWNB; @@ -876,7 +873,6 @@ static int dsi_pll_7nm_init(struct msm_dsi_phy *phy) spin_lock_init(&pll_7nm->pll_enable_lock); pll_7nm->phy = phy; - phy->pll_data = pll_7nm; ret = pll_7nm_register(pll_7nm, phy->provided_clocks->hws); if (ret) { @@ -965,10 +961,8 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy, u32 const delay_us = 5; u32 const timeout_us = 1000; struct msm_dsi_dphy_timing *timing = &phy->timing; - struct dsi_pll_7nm *pll = phy->pll_data; void __iomem *base = phy->base; bool less_than_1500_mhz; - unsigned long flags; u32 vreg_ctrl_0, vreg_ctrl_1, lane_ctrl0; u32 glbl_pemph_ctrl_0; u32 glbl_str_swi_cal_sel_ctrl, glbl_hstx_str_ctrl_0; @@ -1090,13 +1084,10 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy, glbl_rescode_bot_ctrl = 0x3c; } - spin_lock_irqsave(&pll->pll_enable_lock, flags); - pll->pll_enable_cnt = 1; /* de-assert digital and pll power down */ data = DSI_7nm_PHY_CMN_CTRL_0_DIGTOP_PWRDN_B | DSI_7nm_PHY_CMN_CTRL_0_PLL_SHUTDOWNB; writel(data, base + REG_DSI_7nm_PHY_CMN_CTRL_0); - spin_unlock_irqrestore(&pll->pll_enable_lock, flags); /* Assert PLL core reset */ writel(0x00, base + REG_DSI_7nm_PHY_CMN_PLL_CNTRL); @@ -1209,9 +1200,7 @@ static bool dsi_7nm_set_continuous_clock(struct msm_dsi_phy *phy, bool enable) static void dsi_7nm_phy_disable(struct msm_dsi_phy *phy) { - struct dsi_pll_7nm *pll = phy->pll_data; void __iomem *base = phy->base; - unsigned long flags; u32 data; DBG(""); @@ -1238,11 +1227,8 @@ static void dsi_7nm_phy_disable(struct msm_dsi_phy *phy) writel(data, base + REG_DSI_7nm_PHY_CMN_CTRL_0); writel(0, base + REG_DSI_7nm_PHY_CMN_LANE_CTRL0); - spin_lock_irqsave(&pll->pll_enable_lock, flags); - pll->pll_enable_cnt = 0; /* Turn off all PHY blocks */ writel(0x00, base + REG_DSI_7nm_PHY_CMN_CTRL_0); - spin_unlock_irqrestore(&pll->pll_enable_lock, flags); /* make sure phy is turned off */ wmb(); diff --git a/drivers/gpu/drm/msm/msm_fbdev.c b/drivers/gpu/drm/msm/msm_fbdev.c index b5969374d53f..fd19995b12b5 100644 --- a/drivers/gpu/drm/msm/msm_fbdev.c +++ b/drivers/gpu/drm/msm/msm_fbdev.c @@ -52,8 +52,6 @@ static void msm_fbdev_fb_destroy(struct fb_info *info) drm_framebuffer_remove(fb); drm_client_release(&helper->client); - drm_fb_helper_unprepare(helper); - kfree(helper); } static const struct fb_ops msm_fb_ops = { @@ -93,9 +91,9 @@ int msm_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper, { struct drm_device *dev = helper->dev; struct msm_drm_private *priv = dev->dev_private; + struct fb_info *fbi = helper->info; struct drm_framebuffer *fb = NULL; struct drm_gem_object *bo; - struct fb_info *fbi = NULL; uint64_t paddr; uint32_t format; int ret, pitch; @@ -128,13 +126,6 @@ int msm_fbdev_driver_fbdev_probe(struct drm_fb_helper *helper, goto fail; } - fbi = drm_fb_helper_alloc_info(helper); - if (IS_ERR(fbi)) { - DRM_DEV_ERROR(dev->dev, "failed to allocate fb info\n"); - ret = PTR_ERR(fbi); - goto fail; - } - DBG("fbi=%p, dev=%p", fbi, dev); helper->funcs = &msm_fbdev_helper_funcs; diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 07d8cdd6bb2e..017411a0bf45 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -10,8 +10,10 @@ #include <linux/shmem_fs.h> #include <linux/dma-buf.h> +#include <drm/drm_dumb_buffers.h> #include <drm/drm_prime.h> #include <drm/drm_file.h> +#include <drm/drm_fourcc.h> #include <trace/events/gpu_mem.h> @@ -698,8 +700,32 @@ void msm_gem_unpin_iova(struct drm_gem_object *obj, struct drm_gpuvm *vm) int msm_gem_dumb_create(struct drm_file *file, struct drm_device *dev, struct drm_mode_create_dumb *args) { - args->pitch = align_pitch(args->width, args->bpp); - args->size = PAGE_ALIGN(args->pitch * args->height); + u32 fourcc; + u64 pitch_align; + int ret; + + /* + * Adreno needs pitch aligned to 32 pixels. Compute the number + * of bytes for a block of 32 pixels at the given color format. + * Use the result as pitch alignment. + */ + fourcc = drm_driver_color_mode_format(dev, args->bpp); + if (fourcc != DRM_FORMAT_INVALID) { + const struct drm_format_info *info; + + info = drm_format_info(fourcc); + if (!info) + return -EINVAL; + pitch_align = drm_format_info_min_pitch(info, 0, 32); + } else { + pitch_align = round_up(args->width, 32) * DIV_ROUND_UP(args->bpp, SZ_8); + } + if (!pitch_align || pitch_align > U32_MAX) + return -EINVAL; + ret = drm_mode_size_dumb(dev, args, pitch_align, 0); + if (ret) + return ret; + return msm_gem_new_handle(dev, file, args->size, MSM_BO_SCANOUT | MSM_BO_WC, &args->handle, "dumb"); } @@ -1120,12 +1146,16 @@ static void msm_gem_free_object(struct drm_gem_object *obj) put_pages(obj); } - if (obj->resv != &obj->_resv) { + /* + * In error paths, we could end up here before msm_gem_new_handle() + * has changed obj->resv to point to the shared resv. In this case, + * we don't want to drop a ref to the shared r_obj that we haven't + * taken yet. + */ + if ((msm_obj->flags & MSM_BO_NO_SHARE) && (obj->resv != &obj->_resv)) { struct drm_gem_object *r_obj = container_of(obj->resv, struct drm_gem_object, _resv); - WARN_ON(!(msm_obj->flags & MSM_BO_NO_SHARE)); - /* Drop reference we hold to shared resv obj: */ drm_gem_object_put(r_obj); } diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index 3ab3b27134f9..75d9f3574370 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -414,6 +414,11 @@ static void submit_attach_object_fences(struct msm_gem_submit *submit) submit->user_fence, DMA_RESV_USAGE_BOOKKEEP, DMA_RESV_USAGE_BOOKKEEP); + + last_fence = vm->last_fence; + vm->last_fence = dma_fence_unwrap_merge(submit->user_fence, last_fence); + dma_fence_put(last_fence); + return; } @@ -427,10 +432,6 @@ static void submit_attach_object_fences(struct msm_gem_submit *submit) dma_resv_add_fence(obj->resv, submit->user_fence, DMA_RESV_USAGE_READ); } - - last_fence = vm->last_fence; - vm->last_fence = dma_fence_unwrap_merge(submit->user_fence, last_fence); - dma_fence_put(last_fence); } static int submit_bo(struct msm_gem_submit *submit, uint32_t idx, diff --git a/drivers/gpu/drm/msm/msm_gem_vma.c b/drivers/gpu/drm/msm/msm_gem_vma.c index 8316af1723c2..71d5238437eb 100644 --- a/drivers/gpu/drm/msm/msm_gem_vma.c +++ b/drivers/gpu/drm/msm/msm_gem_vma.c @@ -462,15 +462,20 @@ struct op_arg { bool kept; }; -static void +static int vm_op_enqueue(struct op_arg *arg, struct msm_vm_op _op) { struct msm_vm_op *op = kmalloc(sizeof(*op), GFP_KERNEL); + if (!op) + return -ENOMEM; + *op = _op; list_add_tail(&op->node, &arg->job->vm_ops); if (op->obj) drm_gem_object_get(op->obj); + + return 0; } static struct drm_gpuva * @@ -489,6 +494,7 @@ msm_gem_vm_sm_step_map(struct drm_gpuva_op *op, void *_arg) struct drm_gpuva *vma; struct sg_table *sgt; unsigned prot; + int ret; if (arg->kept) return 0; @@ -500,8 +506,6 @@ msm_gem_vm_sm_step_map(struct drm_gpuva_op *op, void *_arg) vm_dbg("%p:%p:%p: %016llx %016llx", vma->vm, vma, vma->gem.obj, vma->va.addr, vma->va.range); - vma->flags = ((struct op_arg *)arg)->flags; - if (obj) { sgt = to_msm_bo(obj)->sgt; prot = msm_gem_prot(obj); @@ -510,7 +514,7 @@ msm_gem_vm_sm_step_map(struct drm_gpuva_op *op, void *_arg) prot = IOMMU_READ | IOMMU_WRITE; } - vm_op_enqueue(arg, (struct msm_vm_op){ + ret = vm_op_enqueue(arg, (struct msm_vm_op){ .op = MSM_VM_OP_MAP, .map = { .sgt = sgt, @@ -523,6 +527,10 @@ msm_gem_vm_sm_step_map(struct drm_gpuva_op *op, void *_arg) .obj = vma->gem.obj, }); + if (ret) + return ret; + + vma->flags = ((struct op_arg *)arg)->flags; to_msm_vma(vma)->mapped = true; return 0; @@ -538,6 +546,7 @@ msm_gem_vm_sm_step_remap(struct drm_gpuva_op *op, void *arg) struct drm_gpuvm_bo *vm_bo = orig_vma->vm_bo; bool mapped = to_msm_vma(orig_vma)->mapped; unsigned flags; + int ret; vm_dbg("orig_vma: %p:%p:%p: %016llx %016llx", vm, orig_vma, orig_vma->gem.obj, orig_vma->va.addr, orig_vma->va.range); @@ -547,7 +556,7 @@ msm_gem_vm_sm_step_remap(struct drm_gpuva_op *op, void *arg) drm_gpuva_op_remap_to_unmap_range(&op->remap, &unmap_start, &unmap_range); - vm_op_enqueue(arg, (struct msm_vm_op){ + ret = vm_op_enqueue(arg, (struct msm_vm_op){ .op = MSM_VM_OP_UNMAP, .unmap = { .iova = unmap_start, @@ -557,6 +566,9 @@ msm_gem_vm_sm_step_remap(struct drm_gpuva_op *op, void *arg) .obj = orig_vma->gem.obj, }); + if (ret) + return ret; + /* * Part of this GEM obj is still mapped, but we're going to kill the * existing VMA and replace it with one or two new ones (ie. two if @@ -618,6 +630,7 @@ msm_gem_vm_sm_step_unmap(struct drm_gpuva_op *op, void *_arg) struct msm_vm_bind_job *job = arg->job; struct drm_gpuva *vma = op->unmap.va; struct msm_gem_vma *msm_vma = to_msm_vma(vma); + int ret; vm_dbg("%p:%p:%p: %016llx %016llx", vma->vm, vma, vma->gem.obj, vma->va.addr, vma->va.range); @@ -650,7 +663,7 @@ msm_gem_vm_sm_step_unmap(struct drm_gpuva_op *op, void *_arg) if (!msm_vma->mapped) goto out_close; - vm_op_enqueue(arg, (struct msm_vm_op){ + ret = vm_op_enqueue(arg, (struct msm_vm_op){ .op = MSM_VM_OP_UNMAP, .unmap = { .iova = vma->va.addr, @@ -660,6 +673,9 @@ msm_gem_vm_sm_step_unmap(struct drm_gpuva_op *op, void *_arg) .obj = vma->gem.obj, }); + if (ret) + return ret; + msm_vma->mapped = false; out_close: @@ -971,6 +987,7 @@ static int lookup_op(struct msm_vm_bind_job *job, const struct drm_msm_vm_bind_op *op) { struct drm_device *dev = job->vm->drm; + struct msm_drm_private *priv = dev->dev_private; int i = job->nr_ops++; int ret = 0; @@ -1017,6 +1034,11 @@ lookup_op(struct msm_vm_bind_job *job, const struct drm_msm_vm_bind_op *op) break; } + if ((op->op == MSM_VM_BIND_OP_MAP_NULL) && + !adreno_smmu_has_prr(priv->gpu)) { + ret = UERR(EINVAL, dev, "PRR not supported\n"); + } + return ret; } @@ -1421,7 +1443,7 @@ msm_ioctl_vm_bind(struct drm_device *dev, void *data, struct drm_file *file) * Maybe we could allow just UNMAP ops? OTOH userspace should just * immediately close the device file and all will be torn down. */ - if (to_msm_vm(ctx->vm)->unusable) + if (to_msm_vm(msm_context_vm(dev, ctx))->unusable) return UERR(EPIPE, dev, "context is unusable"); /* diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index 17759abc46d7..995549d0bbbc 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -197,8 +197,7 @@ static ssize_t msm_gpu_devcoredump_read(char *buffer, loff_t offset, drm_printf(&p, "---\n"); drm_printf(&p, "kernel: " UTS_RELEASE "\n"); drm_printf(&p, "module: " KBUILD_MODNAME "\n"); - drm_printf(&p, "time: %lld.%09ld\n", - state->time.tv_sec, state->time.tv_nsec); + drm_printf(&p, "time: %ptSp\n", &state->time); if (state->comm) drm_printf(&p, "comm: %s\n", state->comm); if (state->cmd) @@ -287,16 +286,17 @@ static void crashstate_get_bos(struct msm_gpu_state *state, struct msm_gem_submi state->bos = kcalloc(cnt, sizeof(struct msm_gpu_state_bo), GFP_KERNEL); - drm_gpuvm_for_each_va (vma, submit->vm) { - bool dump = rd_full || (vma->flags & MSM_VMA_DUMP); + if (state->bos) + drm_gpuvm_for_each_va(vma, submit->vm) { + bool dump = rd_full || (vma->flags & MSM_VMA_DUMP); - /* Skip MAP_NULL/PRR VMAs: */ - if (!vma->gem.obj) - continue; + /* Skip MAP_NULL/PRR VMAs: */ + if (!vma->gem.obj) + continue; - msm_gpu_crashstate_get_bo(state, vma->gem.obj, vma->va.addr, - dump, vma->gem.offset, vma->va.range); - } + msm_gpu_crashstate_get_bo(state, vma->gem.obj, vma->va.addr, + dump, vma->gem.offset, vma->va.range); + } drm_exec_fini(&exec); } else { @@ -348,6 +348,10 @@ static void crashstate_get_vm_logs(struct msm_gpu_state *state, struct msm_gem_v state->vm_logs = kmalloc_array( state->nr_vm_logs, sizeof(vm->log[0]), GFP_KERNEL); + if (!state->vm_logs) { + state->nr_vm_logs = 0; + } + for (int i = 0; i < state->nr_vm_logs; i++) { int idx = (i + first) & vm_log_mask; diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index a597f2bee30b..2894fc118485 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -299,6 +299,17 @@ static inline struct msm_gpu *dev_to_gpu(struct device *dev) return container_of(adreno_smmu, struct msm_gpu, adreno_smmu); } +static inline bool +adreno_smmu_has_prr(struct msm_gpu *gpu) +{ + struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(&gpu->pdev->dev); + + if (!adreno_smmu) + return false; + + return adreno_smmu && adreno_smmu->set_prr_addr; +} + /* It turns out that all targets use the same ringbuffer size */ #define MSM_GPU_RINGBUFFER_SZ SZ_32K #define MSM_GPU_RINGBUFFER_BLKSIZE 32 diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c index 0e18619f96cb..a188617653e8 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -338,6 +338,8 @@ msm_iommu_pagetable_prealloc_allocate(struct msm_mmu *mmu, struct msm_mmu_preall ret = kmem_cache_alloc_bulk(pt_cache, GFP_KERNEL, p->count, p->pages); if (ret != p->count) { + kfree(p->pages); + p->pages = NULL; p->count = ret; return -ENOMEM; } @@ -351,6 +353,9 @@ msm_iommu_pagetable_prealloc_cleanup(struct msm_mmu *mmu, struct msm_mmu_preallo struct kmem_cache *pt_cache = get_pt_cache(mmu); uint32_t remaining_pt_count = p->count - p->ptr; + if (!p->pages) + return; + if (p->count > 0) trace_msm_mmu_prealloc_cleanup(p->count, remaining_pt_count); diff --git a/drivers/gpu/drm/msm/msm_mdss.c b/drivers/gpu/drm/msm/msm_mdss.c index 2d0e3e784c04..bf9a33e925ac 100644 --- a/drivers/gpu/drm/msm/msm_mdss.c +++ b/drivers/gpu/drm/msm/msm_mdss.c @@ -553,8 +553,10 @@ static const struct msm_mdss_data data_153k6 = { static const struct of_device_id mdss_dt_match[] = { { .compatible = "qcom,mdss", .data = &data_153k6 }, + { .compatible = "qcom,glymur-mdss", .data = &data_57k }, { .compatible = "qcom,msm8998-mdss", .data = &data_76k8 }, { .compatible = "qcom,qcm2290-mdss", .data = &data_76k8 }, + { .compatible = "qcom,qcs8300-mdss", .data = &data_74k }, { .compatible = "qcom,sa8775p-mdss", .data = &data_74k }, { .compatible = "qcom,sar2130p-mdss", .data = &data_74k }, { .compatible = "qcom,sdm670-mdss", .data = &data_76k8 }, diff --git a/drivers/gpu/drm/msm/registers/adreno/a6xx.xml b/drivers/gpu/drm/msm/registers/adreno/a6xx.xml index 9459b6038217..3941e7510754 100644 --- a/drivers/gpu/drm/msm/registers/adreno/a6xx.xml +++ b/drivers/gpu/drm/msm/registers/adreno/a6xx.xml @@ -7,9 +7,11 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <import file="adreno/adreno_pm4.xml"/> <import file="adreno/a6xx_enums.xml"/> <import file="adreno/a7xx_enums.xml"/> +<import file="adreno/a8xx_enums.xml"/> <import file="adreno/a6xx_perfcntrs.xml"/> <import file="adreno/a7xx_perfcntrs.xml"/> <import file="adreno/a6xx_descriptors.xml"/> +<import file="adreno/a8xx_descriptors.xml"/> <!-- Each register that is actually being used by driver should have "usage" defined, @@ -84,29 +86,134 @@ by a particular renderpass/blit. <bitfield name="CP_ILLEGAL_INSTR_ERROR_BV" pos="17" type="boolean" variants="A7XX-"/> </bitset> + <bitset name="A8XX_CP_GLOBAL_INT_MASK" inline="no" varset="chip"> + <bitfield name="HWFAULTBR" pos="0" type="boolean"/> + <bitfield name="HWFAULTBV" pos="1" type="boolean"/> + <bitfield name="HWFAULTLPAC" pos="2" type="boolean"/> + <bitfield name="HWFAULTAQE0" pos="3" type="boolean"/> + <bitfield name="HWFAULTAQE1" pos="4" type="boolean"/> + <bitfield name="HWFAULTDDEBR" pos="5" type="boolean"/> + <bitfield name="HWFAULTDDEBV" pos="6" type="boolean"/> + <bitfield name="SWFAULTBR" pos="16" type="boolean"/> + <bitfield name="SWFAULTBV" pos="17" type="boolean"/> + <bitfield name="SWFAULTLPAC" pos="18" type="boolean"/> + <bitfield name="SWFAULTAQE0" pos="19" type="boolean"/> + <bitfield name="SWFAULTAQE1" pos="20" type="boolean"/> + <bitfield name="SWFAULTDDEBR" pos="21" type="boolean"/> + <bitfield name="SWFAULTDDEBV" pos="22" type="boolean"/> + </bitset> + + <bitset name="A8XX_CP_INTERRUPT_STATUS_MASK_PIPE" inline="no" varset="chip"> + <bitfield name="CSFRBWRAP" pos="0" type="boolean"/> + <bitfield name="CSFIB1WRAP" pos="1" type="boolean"/> + <bitfield name="CSFIB2WRAP" pos="2" type="boolean"/> + <bitfield name="CSFIB3WRAP" pos="3" type="boolean"/> + <bitfield name="CSFSDSWRAP" pos="4" type="boolean"/> + <bitfield name="CSFMRBWRAP" pos="5" type="boolean"/> + <bitfield name="CSFVSDWRAP" pos="6" type="boolean"/> + <bitfield name="OPCODEERROR" pos="8" type="boolean"/> + <bitfield name="VSDPARITYERROR" pos="9" type="boolean"/> + <bitfield name="REGISTERPROTECTIONERROR" pos="10" type="boolean"/> + <bitfield name="ILLEGALINSTRUCTION" pos="11" type="boolean"/> + <bitfield name="SMMUFAULT" pos="12" type="boolean"/> + <bitfield name="VBIFRESPCLIENT" pos="13" type="boolean"/> + <bitfield name="VBIFRESPTYPE" pos="19" type="boolean"/> + <bitfield name="VBIFRESPREAD" pos="21" type="boolean"/> + <bitfield name="VBIFRESP" pos="22" type="boolean"/> + <bitfield name="RTWROVF" pos="23" type="boolean"/> + <bitfield name="LRZRTWROVF" pos="24" type="boolean"/> + <bitfield name="LRZRTREFCNTOVF" pos="25" type="boolean"/> + <bitfield name="LRZRTCLRRESMISS" pos="26" type="boolean"/> + </bitset> + + <bitset name="A8XX_CP_HW_FAULT_STATUS_MASK_PIPE" inline="no" varset="chip"> + <bitfield name="CSFRBFAULT" pos="0" type="boolean"/> + <bitfield name="CSFIB1FAULT" pos="1" type="boolean"/> + <bitfield name="CSFIB2FAULT" pos="2" type="boolean"/> + <bitfield name="CSFIB3FAULT" pos="3" type="boolean"/> + <bitfield name="CSFSDSFAULT" pos="4" type="boolean"/> + <bitfield name="CSFMRBFAULT" pos="5" type="boolean"/> + <bitfield name="CSFVSDFAULT" pos="6" type="boolean"/> + <bitfield name="SQEREADBURSTOVF" pos="8" type="boolean"/> + <bitfield name="EVENTENGINEOVF" pos="9" type="boolean"/> + <bitfield name="UCODEERROR" pos="10" type="boolean"/> + </bitset> + <reg64 offset="0x0800" name="CP_RB_BASE"/> <reg32 offset="0x0802" name="CP_RB_CNTL"/> + <reg32 offset="0x0803" name="CP_RB_RPTR_WR" variants="A7XX-"/> <reg64 offset="0x0804" name="CP_RB_RPTR_ADDR"/> <reg32 offset="0x0806" name="CP_RB_RPTR"/> <reg32 offset="0x0807" name="CP_RB_WPTR"/> - <reg32 offset="0x0808" name="CP_SQE_CNTL"/> - <reg32 offset="0x0812" name="CP_CP2GMU_STATUS"> + <reg32 offset="0x0808" name="CP_RB_RPTR_ADDR_BV" variants="A8XX-"/> + <reg32 offset="0x080a" name="CP_RB_RPTR_BV" variants="A8XX-"/> + <reg64 offset="0x080b" name="CP_RB_BASE_LPAC" variants="A8XX-"/> + <reg32 offset="0x080d" name="CP_RB_CNTL_LPAC" variants="A8XX-"/> + <reg32 offset="0x080e" name="CP_RB_RPTR_WR_LPAC" variants="A8XX-"/> + <reg64 offset="0x080f" name="CP_RB_RPTR_ADDR_LPAC" variants="A8XX-"/> + <reg32 offset="0x0811" name="CP_RB_RPTR_LPAC" variants="A8XX-"/> + <reg32 offset="0x0812" name="CP_RB_WPTR_LPAC" variants="A8XX-"/> + <reg32 offset="0x0814" name="CP_SMMU_STREAM_ID_LPAC" variants="A8XX-"/> + <reg32 offset="0x0808" name="CP_SQE_CNTL" variants="A6XX-A7XX"/> + <reg32 offset="0x0815" name="CP_SQE_CNTL" variants="A8XX-"/> + <reg64 offset="0x0816" name="CP_SQE_INSTR_BASE" variants="A8XX-"/> + <reg64 offset="0x0818" name="CP_AQE_INSTR_BASE_0" variants="A8XX-"/> + <reg64 offset="0x081a" name="CP_AQE_INSTR_BASE_1" variants="A8XX-"/> + <reg32 offset="0x0812" name="CP_CP2GMU_STATUS" variants="A6XX-A7XX"> + <!-- Note, layout defined by microcode --> + <bitfield name="IFPC" pos="0" type="boolean"/> + </reg32> + <reg32 offset="0x0822" name="CP_CP2GMU_STATUS" variants="A8XX-"> <bitfield name="IFPC" pos="0" type="boolean"/> </reg32> - <reg32 offset="0x0821" name="CP_HW_FAULT"/> - <reg32 offset="0x0823" name="CP_INTERRUPT_STATUS" type="A6XX_CP_INT"/> - <reg32 offset="0x0824" name="CP_PROTECT_STATUS"/> - <reg32 offset="0x0825" name="CP_STATUS_1"/> - <reg64 offset="0x0830" name="CP_SQE_INSTR_BASE"/> - <reg32 offset="0x0840" name="CP_MISC_CNTL"/> - <reg32 offset="0x0844" name="CP_APRIV_CNTL"> + <reg32 offset="0x0821" name="CP_HW_FAULT" variants="A6XX-A7XX"/> + <reg32 offset="0x0823" name="CP_INTERRUPT_STATUS" type="A6XX_CP_INT" variants="A6XX-A7XX"/> + + <bitset name="a6xx_cp_protect_status" inline="yes"> + <bitfield name="ADDR" low="0" high="17"/> + <bitfield name="READ" pos="20" type="boolean"/> + <bitfield name="CP_HALTED" pos="21" type="boolean"/> + <bitfield name="ACCESS_VIOLATION" pos="22" type="boolean"/> + </bitset> + + <reg32 offset="0x0824" name="CP_PROTECT_STATUS" type="a6xx_cp_protect_status" variants="A6XX-A7XX"/> + <reg32 offset="0x084f" name="CP_PROTECT_STATUS_PIPE" type="a6xx_cp_protect_status" variants="A8XX-"/> + <reg32 offset="0x0825" name="CP_STATUS_1" variants="A6XX-A7XX"/> + + <reg32 offset="0x0825" name="CP_SEMAPHORE_REG_0" variants="A8XX-"/> + <array offset="0x082a" name="CP_SCRATCH_GLOBAL" stride="1" length="4" variants="A8XX-"> + <reg32 offset="0x0" name="REG"/> + </array> + <array offset="0x0830" name="CP_SCRATCH_PIPE" stride="1" length="5" variants="A8XX-"> + <reg32 offset="0x0" name="REG"/> + </array> + + <reg32 offset="0x0840" name="CP_RL_ERROR_DETAILS_0" variants="A8XX-"/> + <reg32 offset="0x0841" name="CP_RL_ERROR_DETAILS_1" variants="A8XX-"/> + + <reg64 offset="0x0830" name="CP_SQE_INSTR_BASE" variants="A6XX-A7XX"/> + <reg32 offset="0x0840" name="CP_MISC_CNTL" variants="A6XX-A7XX"/> + <reg32 offset="0x084c" name="CP_MISC_CNTL" variants="A8XX-"/> + + <reg32 offset="0x08b0" name="CP_SQE_ICACHE_CNTL_PIPE" variants="A8XX-"/> + <reg32 offset="0x08b1" name="CP_SQE_DCACHE_CNTL_PIPE" variants="A8XX-"/> + <reg32 offset="0x08b3" name="CP_HW_FAULT_STATUS_PIPE" variants="A8XX-"/> + <reg32 offset="0x08b4" name="CP_HW_FAULT_STATUS_MASK_PIPE" variants="A8XX-"/> + <reg32 offset="0x08b5" name="CP_INTERRUPT_STATUS_GLOBAL" type="A8XX_CP_GLOBAL_INT_MASK" variants="A8XX-"/> + <reg32 offset="0x08b6" name="CP_INTERRUPT_STATUS_MASK_GLOBAL" type="A8XX_CP_GLOBAL_INT_MASK" variants="A8XX-"/> + <reg32 offset="0x08b7" name="CP_INTERRUPT_STATUS_PIPE" type="A8XX_CP_INTERRUPT_STATUS_MASK_PIPE" variants="A8XX-"/> + <reg32 offset="0x08b8" name="CP_INTERRUPT_STATUS_MASK_PIPE" variants="A8XX-"/> + <reg32 offset="0x08b9" name="CP_PIPE_STATUS_PIPE" variants="A8XX-"/> + <reg32 offset="0x08ba" name="CP_GPU_BATCH_ID_PIPE" variants="A8XX-"/> + <reg32 offset="0x08bb" name="CP_SQE_STATUS_PIPE" variants="A8XX-"/> + + <bitset name="a6xx_cp_apriv_cntl" inline="yes"> <!-- Crashdumper writes --> <bitfield pos="6" name="CDWRITE" type="boolean"/> <!-- Crashdumper reads --> <bitfield pos="5" name="CDREAD" type="boolean"/> - - <!-- 4 is unknown --> - + <!-- CP Scratch reg copy to mem --> + <bitfield pos="4" name="SCRATCHWT" type="boolean"/> <!-- RPTR shadow writes --> <bitfield pos="3" name="RBRPWB" type="boolean"/> <!-- Memory accesses from PM4 packets in the ringbuffer --> @@ -115,11 +222,16 @@ by a particular renderpass/blit. <bitfield pos="1" name="RBFETCH" type="boolean"/> <!-- Instruction cache fetches --> <bitfield pos="0" name="ICACHE" type="boolean"/> - </reg32> + </bitset> + + <reg32 offset="0x0844" name="CP_APRIV_CNTL" type="a6xx_cp_apriv_cntl" variants="A6XX-A7XX"/> + <reg32 offset="0x084d" name="CP_APRIV_CNTL_PIPE" type="a6xx_cp_apriv_cntl" variants="A8XX-"/> + <!-- Preemptions taking longer than this threshold increment PERF_CP_LONG_PREEMPTIONS: --> - <reg32 offset="0x08C0" name="CP_PREEMPT_THRESHOLD"/> + <reg32 offset="0x08c0" name="CP_PREEMPT_THRESHOLD" variants="A6XX-A7XX"/> + <reg32 offset="0x08ec" name="CP_PREEMPT_THRESHOLD" variants="A8XX-"/> <!-- all the threshold values seem to be in units of quad-dwords: --> - <reg32 offset="0x08C1" name="CP_ROQ_THRESHOLDS_1"> + <reg32 offset="0x08c1" name="CP_ROQ_THRESHOLDS_1" variants="A6XX"> <doc> b0..7 identifies where MRB data starts (and RB data ends) b8.15 identifies where VSD data starts (and MRB data ends) @@ -131,7 +243,7 @@ by a particular renderpass/blit. <bitfield name="IB1_START" low="16" high="23" shr="2"/> <bitfield name="IB2_START" low="24" high="31" shr="2"/> </reg32> - <reg32 offset="0x08C2" name="CP_ROQ_THRESHOLDS_2"> + <reg32 offset="0x08c2" name="CP_ROQ_THRESHOLDS_2" variants="A6XX"> <doc> low bits identify where CP_SET_DRAW_STATE stateobj processing starts (and IB2 data ends). I'm guessing @@ -147,176 +259,293 @@ by a particular renderpass/blit. <!-- total ROQ size: --> <bitfield name="ROQ_SIZE" low="16" high="31" shr="2"/> </reg32> - <reg32 offset="0x08C3" name="CP_MEM_POOL_SIZE"/> - <reg32 offset="0x0841" name="CP_CHICKEN_DBG"/> - <reg32 offset="0x0842" name="CP_ADDR_MODE_CNTL" type="a5xx_address_mode"/> - <reg32 offset="0x0843" name="CP_DBG_ECO_CNTL"/> - <reg32 offset="0x084F" name="CP_PROTECT_CNTL"> + <reg32 offset="0x08C3" name="CP_MEM_POOL_SIZE" variants="A6XX"/> + <reg32 offset="0x0841" name="CP_CHICKEN_DBG" variants="A6XX-A7XX"/> + <reg32 offset="0x08b2" name="CP_CHICKEN_DBG_PIPE" variants="A8XX-"/> + <reg32 offset="0x0842" name="CP_ADDR_MODE_CNTL" type="a5xx_address_mode" variants="A6XX"/> + <reg32 offset="0x0843" name="CP_DBG_ECO_CNTL" variants="A6XX-A7XX"/> + <reg32 offset="0x084b" name="CP_DBG_ECO_CNTL" variants="A8XX-"/> + + <bitset name="a6xx_cp_protect_cntl" inline="yes"> <bitfield pos="3" name="LAST_SPAN_INF_RANGE" type="boolean"/> <bitfield pos="1" name="ACCESS_FAULT_ON_VIOL_EN" type="boolean"/> <bitfield pos="0" name="ACCESS_PROT_EN" type="boolean"/> - </reg32> + </bitset> - <array offset="0x0883" name="CP_SCRATCH" stride="1" length="8"> + <reg32 offset="0x084f" name="CP_PROTECT_CNTL" type="a6xx_cp_protect_cntl" variants="A6XX-A7XX"/> + <bitset name="a8xx_cp_protect_cntl" inline="yes"> + <bitfield name="HALT_SQE_RANGE" low="16" high="31"/> + <bitfield name="LAST_SPAN_INF_RANGE" pos="3" type="boolean"/> + <bitfield name="ACCESS_FAULT_ON_VIOL_EN" pos="1" type="boolean"/> + <bitfield name="ACCESS_PROT_EN" pos="0" type="boolean"/> + </bitset> + + <reg32 offset="0x084e" name="CP_PROTECT_CNTL_PIPE" type="a8xx_cp_protect_cntl" variants="A8XX-"/> + + <array offset="0x0883" name="CP_SCRATCH" stride="1" length="8" variants="A6XX-A7XX"> <reg32 offset="0x0" name="REG" type="uint"/> </array> - <array offset="0x0850" name="CP_PROTECT" stride="1" length="32"> + <array offset="0x0850" name="CP_PROTECT" stride="1" length="32" variants="A6XX-A7XX"> + <reg32 offset="0x0" name="REG" type="a6x_cp_protect"/> + </array> + <array offset="0x0850" name="CP_PROTECT_GLOBAL" stride="1" length="64" variants="A8XX-"> + <reg32 offset="0x0" name="REG" type="a6x_cp_protect"/> + </array> + <array offset="0x08a0" name="CP_PROTECT_PIPE" stride="1" length="16" variants="A8XX-"> <reg32 offset="0x0" name="REG" type="a6x_cp_protect"/> </array> - <reg32 offset="0x08A0" name="CP_CONTEXT_SWITCH_CNTL"> + <bitset name="a6xx_cp_context_switch_cntl" inline="yes"> <bitfield name="STOP" pos="0" type="boolean"/> <bitfield name="LEVEL" low="6" high="7"/> <bitfield name="USES_GMEM" pos="8" type="boolean"/> <bitfield name="SKIP_SAVE_RESTORE" pos="9" type="boolean"/> - </reg32> - <reg64 offset="0x08A1" name="CP_CONTEXT_SWITCH_SMMU_INFO"/> - <reg64 offset="0x08A3" name="CP_CONTEXT_SWITCH_PRIV_NON_SECURE_RESTORE_ADDR"/> - <reg64 offset="0x08A5" name="CP_CONTEXT_SWITCH_PRIV_SECURE_RESTORE_ADDR"/> - <reg64 offset="0x08A7" name="CP_CONTEXT_SWITCH_NON_PRIV_RESTORE_ADDR"/> - <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_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"/> - <reg32 offset="0x0909" name="CP_SQE_STAT_DATA"/> - <reg32 offset="0x090A" name="CP_DRAW_STATE_ADDR"/> - <reg32 offset="0x090B" name="CP_DRAW_STATE_DATA"/> - <reg32 offset="0x090C" name="CP_ROQ_DBG_ADDR"/> - <reg32 offset="0x090D" name="CP_ROQ_DBG_DATA"/> - <reg32 offset="0x090E" name="CP_MEM_POOL_DBG_ADDR"/> - <reg32 offset="0x090F" name="CP_MEM_POOL_DBG_DATA"/> - <reg32 offset="0x0910" name="CP_SQE_UCODE_DBG_ADDR"/> - <reg32 offset="0x0911" name="CP_SQE_UCODE_DBG_DATA"/> - <reg64 offset="0x0928" name="CP_IB1_BASE"/> - <reg32 offset="0x092A" name="CP_IB1_REM_SIZE"/> - <reg64 offset="0x092B" name="CP_IB2_BASE"/> - <reg32 offset="0x092D" name="CP_IB2_REM_SIZE"/> + </bitset> + + <reg32 offset="0x08a0" name="CP_CONTEXT_SWITCH_CNTL" type="a6xx_cp_context_switch_cntl" variants="A6XX-A7XX"/> + <reg32 offset="0x08c0" name="CP_CONTEXT_SWITCH_CNTL" type="a6xx_cp_context_switch_cntl" variants="A8XX-"/> + + <reg64 offset="0x08a1" name="CP_CONTEXT_SWITCH_SMMU_INFO" variants="A6XX-A7XX"/> + <reg64 offset="0x08a3" name="CP_CONTEXT_SWITCH_PRIV_NON_SECURE_RESTORE_ADDR" variants="A6XX-A7XX"/> + <reg64 offset="0x08a5" name="CP_CONTEXT_SWITCH_PRIV_SECURE_RESTORE_ADDR" variants="A6XX-A7XX"/> + <reg64 offset="0x08a7" name="CP_CONTEXT_SWITCH_NON_PRIV_RESTORE_ADDR" variants="A6XX-A7XX"/> + <reg32 offset="0x08ab" name="CP_CONTEXT_SWITCH_LEVEL_STATUS" variants="A7XX"/> + + <reg64 offset="0x08c1" name="CP_CONTEXT_SWITCH_SMMU_INFO" variants="A8XX-"/> + <reg64 offset="0x08c3" name="CP_CONTEXT_SWITCH_PRIV_NON_SECURE_RESTORE_ADDR" variants="A8XX-"/> + <reg64 offset="0x08c5" name="CP_CONTEXT_SWITCH_PRIV_SECURE_RESTORE_ADDR" variants="A8XX-"/> + <reg64 offset="0x08c7" name="CP_CONTEXT_SWITCH_NON_PRIV_RESTORE_ADDR" variants="A8XX-"/> + <reg32 offset="0x08cb" name="CP_CONTEXT_SWITCH_LEVEL_STATUS" variants="A8XX-"/> + + <array offset="0x08d0" name="CP_PERFCTR_CP_SEL" stride="1" length="14" variants="A6XX-A7XX"/> + <array offset="0x08d0" name="CP_PERFCTR_CP_SEL" stride="1" length="21" variants="A8XX-"/> + <array offset="0x08e0" name="CP_BV_PERFCTR_CP_SEL" stride="1" length="7" variants="A7XX"/> + <reg64 offset="0x0900" name="CP_CRASH_DUMP_SCRIPT_BASE" variants="A6XX-A7XX"/> + <reg32 offset="0x0902" name="CP_CRASH_DUMP_CNTL" variants="A6XX-A7XX"/> + <reg32 offset="0x0903" name="CP_CRASH_DUMP_STATUS" variants="A6XX-A7XX"/> + <reg64 offset="0x0842" name="CP_CRASH_DUMP_SCRIPT_BASE" variants="A8XX-"/> + <reg32 offset="0x0844" name="CP_CRASH_DUMP_CNTL" variants="A8XX-"/> + <reg32 offset="0x0845" name="CP_CRASH_DUMP_STATUS" variants="A8XX-"/> + <reg32 offset="0x0908" name="CP_SQE_STAT_ADDR" variants="A6XX-A7XX"/> + <reg32 offset="0x0909" name="CP_SQE_STAT_DATA" variants="A6XX-A7XX"/> + <reg32 offset="0x090a" name="CP_DRAW_STATE_ADDR" variants="A6XX-A7XX"/> + <reg32 offset="0x090b" name="CP_DRAW_STATE_DATA" variants="A6XX-A7XX"/> + <reg32 offset="0x090c" name="CP_ROQ_DBG_ADDR" variants="A6XX-A7XX"/> + <reg32 offset="0x090d" name="CP_ROQ_DBG_DATA" variants="A6XX-A7XX"/> + <reg32 offset="0x090e" name="CP_MEM_POOL_DBG_ADDR" variants="A6XX-A7XX"/> + <reg32 offset="0x090f" name="CP_MEM_POOL_DBG_DATA" variants="A6XX-A7XX"/> + <reg32 offset="0x0910" name="CP_SQE_UCODE_DBG_ADDR" variants="A6XX-A7XX"/> + <reg32 offset="0x0911" name="CP_SQE_UCODE_DBG_DATA" variants="A6XX-A7XX"/> + + <reg32 offset="0x08f0" name="CP_SQE_STAT_ADDR_PIPE" variants="A8XX-"/> + <reg32 offset="0x08f1" name="CP_SQE_STAT_DATA_PIPE" variants="A8XX-"/> + <reg32 offset="0x08f2" name="CP_DRAW_STATE_ADDR_PIPE" variants="A8XX-"/> + <reg32 offset="0x08f3" name="CP_DRAW_STATE_DATA_PIPE" variants="A8XX-"/> + <reg32 offset="0x08f4" name="CP_ROQ_DBG_ADDR_PIPE" variants="A8XX-"/> + <reg32 offset="0x08f5" name="CP_ROQ_DBG_DATA_PIPE" variants="A8XX-"/> + <reg32 offset="0x08f6" name="CP_MEM_POOL_DBG_ADDR_PIPE" variants="A8XX-"/> + <reg32 offset="0x08f7" name="CP_MEM_POOL_DBG_DATA_PIPE" variants="A8XX-"/> + <reg32 offset="0x08f8" name="CP_SQE_UCODE_DBG_ADDR_PIPE" variants="A8XX-"/> + <reg32 offset="0x08f9" name="CP_SQE_UCODE_DBG_DATA_PIPE" variants="A8XX-"/> + <reg32 offset="0x08fa" name="CP_RESOURCE_TABLE_DBG_ADDR_BV" variants="A8XX-"/> + <reg32 offset="0x08fb" name="CP_RESOURCE_TABLE_DBG_DATA_BV" variants="A8XX-"/> + <reg32 offset="0x08fc" name="CP_FIFO_DBG_ADDR_LPAC" variants="A8XX-"/> + <reg32 offset="0x08fd" name="CP_FIFO_DBG_DATA_LPAC" variants="A8XX-"/> + <reg32 offset="0x08fe" name="CP_FIFO_DBG_ADDR_DDE_PIPE" variants="A8XX-"/> + <reg32 offset="0x08ff" name="CP_FIFO_DBG_DATA_DDE_PIPE" variants="A8XX-"/> + + <reg32 offset="0x0b00" name="CP_SLICE_MEM_POOL_DBG_ADDR_PIPE" variants="A8XX-"/> + <reg32 offset="0x0b01" name="CP_SLICE_MEM_POOL_DBG_DATA_PIPE" variants="A8XX-"/> + <reg32 offset="0x0b93" name="CP_SLICE_CHICKEN_DBG_PIPE" variants="A8XX-"/> + + <reg64 offset="0x0928" name="CP_IB1_BASE" variants="A6XX-A7XX"/> + <reg32 offset="0x092a" name="CP_IB1_REM_SIZE" variants="A6XX-A7XX"/> + <reg64 offset="0x092b" name="CP_IB2_BASE" variants="A6XX-A7XX"/> + <reg32 offset="0x092d" name="CP_IB2_REM_SIZE" variants="A6XX-A7XX"/> <!-- SDS == CP_SET_DRAW_STATE: --> - <reg64 offset="0x092e" name="CP_SDS_BASE"/> - <reg32 offset="0x0930" name="CP_SDS_REM_SIZE"/> + <reg64 offset="0x092e" name="CP_SDS_BASE" variants="A6XX-A7XX"/> + <reg32 offset="0x0930" name="CP_SDS_REM_SIZE" variants="A6XX-A7XX"/> <!-- MRB == MEM_READ_ADDR/$addr in SQE firmware --> - <reg64 offset="0x0931" name="CP_MRB_BASE"/> - <reg32 offset="0x0933" name="CP_MRB_REM_SIZE"/> + <reg64 offset="0x0931" name="CP_MRB_BASE" variants="A6XX-A7XX"/> + <reg32 offset="0x0933" name="CP_MRB_REM_SIZE" variants="A6XX-A7XX"/> <!-- VSD == Visibility Stream Decode This is used by CP to read the draw stream and skip empty draws --> - <reg64 offset="0x0934" name="CP_VSD_BASE"/> + <reg64 offset="0x0934" name="CP_VSD_BASE" variants="A6XX-A7XX"/> + + <reg64 offset="0x0900" name="CP_IB1_BASE" variants="A8XX-"/> + <reg32 offset="0x0902" name="CP_IB1_REM_SIZE" variants="A8XX-"/> + <reg32 offset="0x0903" name="CP_IB1_INIT_SIZE" variants="A8XX-"/> + <reg64 offset="0x0904" name="CP_IB2_BASE" variants="A8XX-"/> + <reg32 offset="0x0906" name="CP_IB2_REM_SIZE" variants="A8XX-"/> + <reg32 offset="0x0907" name="CP_IB2_INIT_SIZE" variants="A8XX-"/> + <reg64 offset="0x0908" name="CP_IB3_BASE" variants="A8XX-"/> + <reg32 offset="0x090a" name="CP_IB3_REM_SIZE" variants="A8XX-"/> + <reg32 offset="0x090b" name="CP_IB3_INIT_SIZE" variants="A8XX-"/> + <reg64 offset="0x090c" name="CP_SDS_BASE" variants="A8XX-"/> + <reg32 offset="0x090e" name="CP_SDS_REM_SIZE" variants="A8XX-"/> + <reg32 offset="0x090f" name="CP_SDS_INIT_SIZE" variants="A8XX-"/> + <reg64 offset="0x0910" name="CP_MRB_BASE" variants="A8XX-"/> + <reg32 offset="0x0912" name="CP_MRB_REM_SIZE" variants="A8XX-"/> + <reg32 offset="0x0913" name="CP_MRB_INIT_SIZE" variants="A8XX-"/> + <reg64 offset="0x0914" name="CP_VSD_BASE" variants="A8XX-"/> + <reg32 offset="0x0916" name="CP_VSD_REM_SIZE" variants="A8XX-"/> + <reg32 offset="0x0917" name="CP_VSD_INIT_SIZE" variants="A8XX-"/> <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_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"> + <reg32 offset="0x0939" name="CP_ROQ_RB_STATUS" type="a6xx_roq_status" variants="A6XX-A7XX"/> + <reg32 offset="0x093a" name="CP_ROQ_IB1_STATUS" type="a6xx_roq_status" variants="A6XX-A7XX"/> + <reg32 offset="0x093b" name="CP_ROQ_IB2_STATUS" type="a6xx_roq_status" variants="A6XX-A7XX"/> + <reg32 offset="0x093c" name="CP_ROQ_SDS_STATUS" type="a6xx_roq_status" variants="A6XX-A7XX"/> + <reg32 offset="0x093d" name="CP_ROQ_MRB_STATUS" type="a6xx_roq_status" variants="A6XX-A7XX"/> + <reg32 offset="0x093e" name="CP_ROQ_VSD_STATUS" type="a6xx_roq_status" variants="A6XX-A7XX"/> + + <reg32 offset="0x0920" name="CP_ROQ_RB_STATUS" type="a6xx_roq_status" variants="A8XX-"/> + <reg32 offset="0x0921" name="CP_ROQ_IB1_STATUS" type="a6xx_roq_status" variants="A8XX-"/> + <reg32 offset="0x0922" name="CP_ROQ_IB2_STATUS" type="a6xx_roq_status" variants="A8XX-"/> + <reg32 offset="0x0923" name="CP_ROQ_IB3_STATUS" type="a6xx_roq_status" variants="A8XX-"/> + <reg32 offset="0x0924" name="CP_ROQ_SDS_STATUS" type="a6xx_roq_status" variants="A8XX-"/> + <reg32 offset="0x0925" name="CP_ROQ_MRB_STATUS" type="a6xx_roq_status" variants="A8XX-"/> + <reg32 offset="0x0926" name="CP_ROQ_VSD_STATUS" type="a6xx_roq_status" variants="A8XX-"/> + + <reg32 offset="0x0943" name="CP_IB1_INIT_SIZE" variants="A6XX-A7XX"/> + <reg32 offset="0x0944" name="CP_IB2_INIT_SIZE" variants="A6XX-A7XX"/> + <reg32 offset="0x0945" name="CP_SDS_INIT_SIZE" variants="A6XX-A7XX"/> + <reg32 offset="0x0946" name="CP_MRB_INIT_SIZE" variants="A6XX-A7XX"/> + <reg32 offset="0x0947" name="CP_VSD_INIT_SIZE" variants="A6XX-A7XX"/> + + <bitset name="a6xx_cp_roq_avail" inline="yes"> <doc>number of remaining dwords incl current dword being consumed?</doc> <bitfield name="REM" low="16" high="31"/> - </reg32> - <reg32 offset="0x0949" name="CP_ROQ_AVAIL_IB1"> - <doc>number of remaining dwords incl current dword being consumed?</doc> - <bitfield name="REM" low="16" high="31"/> - </reg32> - <reg32 offset="0x094a" name="CP_ROQ_AVAIL_IB2"> + </bitset> + + <reg32 offset="0x0948" name="CP_ROQ_AVAIL_RB" type="a6xx_cp_roq_avail" variants="A6XX-A7XX"/> + <reg32 offset="0x0949" name="CP_ROQ_AVAIL_IB1" type="a6xx_cp_roq_avail" variants="A6XX-A7XX"/> + <reg32 offset="0x094a" name="CP_ROQ_AVAIL_IB2" type="a6xx_cp_roq_avail" variants="A6XX-A7XX"/> + <reg32 offset="0x094b" name="CP_ROQ_AVAIL_SDS" type="a6xx_cp_roq_avail" variants="A6XX-A7XX"/> + <reg32 offset="0x094c" name="CP_ROQ_AVAIL_MRB" type="a6xx_cp_roq_avail" variants="A6XX-A7XX"/> + <reg32 offset="0x094d" name="CP_ROQ_AVAIL_VSD" type="a6xx_cp_roq_avail" variants="A6XX-A7XX"/> + + <reg32 offset="0x0918" name="CP_ROQ_AVAIL_RB" type="a6xx_cp_roq_avail" variants="A8XX-"/> + <reg32 offset="0x0919" name="CP_ROQ_AVAIL_IB1" type="a6xx_cp_roq_avail" variants="A8XX-"/> + <reg32 offset="0x091a" name="CP_ROQ_AVAIL_IB2" type="a6xx_cp_roq_avail" variants="A8XX-"/> + <reg32 offset="0x091b" name="CP_ROQ_AVAIL_IB3" type="a6xx_cp_roq_avail" variants="A8XX-"/> + <reg32 offset="0x091c" name="CP_ROQ_AVAIL_SDS" type="a6xx_cp_roq_avail" variants="A8XX-"/> + <reg32 offset="0x091d" name="CP_ROQ_AVAIL_MRB" type="a6xx_cp_roq_avail" variants="A8XX-"/> + <reg32 offset="0x091e" name="CP_ROQ_AVAIL_VSD" type="a6xx_cp_roq_avail" variants="A8XX-"/> + + <bitset name="a7xx_aperture_cntl" inline="yes"> + <bitfield name="PIPE" low="12" high="13" type="adreno_pipe"/> + <bitfield name="CLUSTER" low="8" high="10" type="a7xx_cluster"/> + <bitfield name="CONTEXT" low="4" high="5"/> + </bitset> + <reg64 offset="0x0980" name="CP_ALWAYS_ON_COUNTER" variants="A6XX-A7XX"/> + <reg64 offset="0x0982" name="CP_ALWAYS_ON_CONTEXT" variants="A6XX-A7XX"/> + <reg64 offset="0x08e7" name="CP_ALWAYS_ON_COUNTER" variants="A8XX-"/> + <reg64 offset="0x08e9" name="CP_ALWAYS_ON_CONTEXT" variants="A8XX-"/> + <reg32 offset="0x098d" name="CP_AHB_CNTL" variants="A6XX-A7XX"/> + <reg32 offset="0x0838" name="CP_AHB_CNTL" variants="A8XX-"/> + <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"/> + + <array offset="0x0a9c" name="CP_RESERVED_REG" stride="1" length="4" variants="A7XX"/> + <array offset="0x0958" name="CP_RESERVED_REG" stride="1" length="4" variants="A8XX-"/> + + <bitset name="a8xx_aperture_cntl" inline="yes"> + <bitfield name="CONTEXTID3D" low="4" high="5"/> + <bitfield name="CLUSTERID" low="8" high="11"/> + <bitfield name="PIPEID" low="12" high="15"/> + <bitfield name="SLICEID" low="16" high="18"/> + <bitfield name="USESLICEID" pos="23" type="boolean"/> + </bitset> + + <reg32 offset="0x081c" name="CP_APERTURE_CNTL_HOST" type="a8xx_aperture_cntl" variants="A8XX-"/> + <reg32 offset="0x081d" name="CP_APERTURE_CNTL_GMU" type="a8xx_aperture_cntl" variants="A8XX-"/> + <reg32 offset="0x081e" name="CP_APERTURE_CNTL_CD" type="a8xx_aperture_cntl" variants="A8XX-"/> + + <reg32 offset="0x0a61" name="CP_BV_PROTECT_STATUS" variants="A7XX"/> + <reg32 offset="0x0a64" name="CP_BV_HW_FAULT" variants="A7XX"/> + <reg32 offset="0x0a66" name="CP_BV_RB_RPTR" variants="A7XX"/> + <reg64 offset="0x0a6d" name="CP_BV_IB1_BASE" variants="A7XX"/> + <reg32 offset="0x0a70" name="CP_BV_IB1_REM_SIZE" variants="A7XX"/> + <reg64 offset="0x0a71" name="CP_BV_IB2_BASE" variants="A7XX"/> + <reg32 offset="0x0a74" name="CP_BV_IB2_REM_SIZE" variants="A7XX"/> + <reg32 offset="0x0a81" name="CP_BV_DRAW_STATE_ADDR" variants="A7XX"/> + <reg32 offset="0x0a82" name="CP_BV_DRAW_STATE_DATA" variants="A7XX"/> + <reg32 offset="0x0a83" name="CP_BV_ROQ_DBG_ADDR" variants="A7XX"/> + <reg32 offset="0x0a84" name="CP_BV_ROQ_DBG_DATA" variants="A7XX"/> + <reg32 offset="0x0a85" name="CP_BV_SQE_UCODE_DBG_ADDR" variants="A7XX"/> + <reg32 offset="0x0a86" name="CP_BV_SQE_UCODE_DBG_DATA" variants="A7XX"/> + <reg32 offset="0x0a87" name="CP_BV_SQE_STAT_ADDR" variants="A7XX"/> + <reg32 offset="0x0a88" name="CP_BV_SQE_STAT_DATA" variants="A7XX"/> + + <reg32 offset="0x0a8f" name="CP_BV_ROQ_AVAIL_RB" variants="A7XX"> <doc>number of remaining dwords incl current dword being consumed?</doc> <bitfield name="REM" low="16" high="31"/> </reg32> - <reg32 offset="0x094b" name="CP_ROQ_AVAIL_SDS"> + <reg32 offset="0x0a90" name="CP_BV_ROQ_AVAIL_IB1" variants="A7XX"> <doc>number of remaining dwords incl current dword being consumed?</doc> <bitfield name="REM" low="16" high="31"/> </reg32> - <reg32 offset="0x094c" name="CP_ROQ_AVAIL_MRB"> - <doc>number of dwords that have already been read but haven't been consumed by $addr</doc> - <bitfield name="REM" low="16" high="31"/> - </reg32> - <reg32 offset="0x094d" name="CP_ROQ_AVAIL_VSD"> + <reg32 offset="0x0a91" name="CP_BV_ROQ_AVAIL_IB2" variants="A7XX"> <doc>number of remaining dwords incl current dword being consumed?</doc> <bitfield name="REM" low="16" high="31"/> </reg32> - <bitset name="a7xx_aperture_cntl" inline="yes"> - <bitfield name="PIPE" low="12" high="13" type="a7xx_pipe"/> - <bitfield name="CLUSTER" low="8" high="10" type="a7xx_cluster"/> - <bitfield name="CONTEXT" low="4" high="5"/> - </bitset> - <reg64 offset="0x0980" name="CP_ALWAYS_ON_COUNTER"/> - <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-"/> - - <reg32 offset="0x0a61" name="CP_BV_PROTECT_STATUS" variants="A7XX-"/> - <reg32 offset="0x0a64" name="CP_BV_HW_FAULT" variants="A7XX-"/> - <reg32 offset="0x0a81" name="CP_BV_DRAW_STATE_ADDR" variants="A7XX-"/> - <reg32 offset="0x0a82" name="CP_BV_DRAW_STATE_DATA" variants="A7XX-"/> - <reg32 offset="0x0a83" name="CP_BV_ROQ_DBG_ADDR" variants="A7XX-"/> - <reg32 offset="0x0a84" name="CP_BV_ROQ_DBG_DATA" variants="A7XX-"/> - <reg32 offset="0x0a85" name="CP_BV_SQE_UCODE_DBG_ADDR" variants="A7XX-"/> - <reg32 offset="0x0a86" name="CP_BV_SQE_UCODE_DBG_DATA" variants="A7XX-"/> - <reg32 offset="0x0a87" name="CP_BV_SQE_STAT_ADDR" variants="A7XX-"/> - <reg32 offset="0x0a88" name="CP_BV_SQE_STAT_DATA" variants="A7XX-"/> - <reg32 offset="0x0a96" name="CP_BV_MEM_POOL_DBG_ADDR" variants="A7XX-"/> - <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_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-"/> - - <reg32 offset="0x0b0a" name="CP_LPAC_DRAW_STATE_ADDR" variants="A7XX-"/> - <reg32 offset="0x0b0b" name="CP_LPAC_DRAW_STATE_DATA" variants="A7XX-"/> - <reg32 offset="0x0b0c" name="CP_LPAC_ROQ_DBG_ADDR" variants="A7XX-"/> - <reg32 offset="0x0b27" name="CP_SQE_AC_UCODE_DBG_ADDR" variants="A7XX-"/> - <reg32 offset="0x0b28" name="CP_SQE_AC_UCODE_DBG_DATA" variants="A7XX-"/> - <reg32 offset="0x0b29" name="CP_SQE_AC_STAT_ADDR" variants="A7XX-"/> - <reg32 offset="0x0b2a" name="CP_SQE_AC_STAT_DATA" variants="A7XX-"/> - - <reg32 offset="0x0b31" name="CP_LPAC_APRIV_CNTL" variants="A7XX-"/> - <reg32 offset="0x0B34" name="CP_LPAC_PROG_FIFO_SIZE"/> - <reg32 offset="0x0b35" name="CP_LPAC_ROQ_DBG_DATA" variants="A7XX-"/> - <reg32 offset="0x0b36" name="CP_LPAC_FIFO_DBG_DATA" variants="A7XX-"/> - <reg32 offset="0x0b40" name="CP_LPAC_FIFO_DBG_ADDR" variants="A7XX-"/> - <reg32 offset="0x0b81" name="CP_LPAC_SQE_CNTL"/> - <reg64 offset="0x0b82" name="CP_LPAC_SQE_INSTR_BASE"/> - - <reg64 offset="0x0b70" name="CP_AQE_INSTR_BASE_0" variants="A7XX-"/> - <reg64 offset="0x0b72" name="CP_AQE_INSTR_BASE_1" variants="A7XX-"/> - <reg32 offset="0x0b78" name="CP_AQE_APRIV_CNTL" variants="A7XX-"/> - - <reg32 offset="0x0ba8" name="CP_AQE_ROQ_DBG_ADDR_0" variants="A7XX-"/> - <reg32 offset="0x0ba9" name="CP_AQE_ROQ_DBG_ADDR_1" variants="A7XX-"/> - <reg32 offset="0x0bac" name="CP_AQE_ROQ_DBG_DATA_0" variants="A7XX-"/> - <reg32 offset="0x0bad" name="CP_AQE_ROQ_DBG_DATA_1" variants="A7XX-"/> - <reg32 offset="0x0bb0" name="CP_AQE_UCODE_DBG_ADDR_0" variants="A7XX-"/> - <reg32 offset="0x0bb1" name="CP_AQE_UCODE_DBG_ADDR_1" variants="A7XX-"/> - <reg32 offset="0x0bb4" name="CP_AQE_UCODE_DBG_DATA_0" variants="A7XX-"/> - <reg32 offset="0x0bb5" name="CP_AQE_UCODE_DBG_DATA_1" variants="A7XX-"/> - <reg32 offset="0x0bb8" name="CP_AQE_STAT_ADDR_0" variants="A7XX-"/> - <reg32 offset="0x0bb9" name="CP_AQE_STAT_ADDR_1" variants="A7XX-"/> - <reg32 offset="0x0bbc" name="CP_AQE_STAT_DATA_0" variants="A7XX-"/> - <reg32 offset="0x0bbd" name="CP_AQE_STAT_DATA_1" variants="A7XX-"/> - - <reg32 offset="0x0C01" name="VSC_ADDR_MODE_CNTL" type="a5xx_address_mode"/> - <reg32 offset="0x0018" name="RBBM_GPR0_CNTL"/> - <reg32 offset="0x0201" name="RBBM_INT_0_STATUS" type="A6XX_RBBM_INT_0_MASK"/> - <reg32 offset="0x0210" name="RBBM_STATUS"> + <reg32 offset="0x0a96" name="CP_BV_MEM_POOL_DBG_ADDR" variants="A7XX"/> + <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_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"/> + + <reg32 offset="0x0b0a" name="CP_LPAC_DRAW_STATE_ADDR" variants="A7XX"/> + <reg32 offset="0x0b0b" name="CP_LPAC_DRAW_STATE_DATA" variants="A7XX"/> + <reg32 offset="0x0b0c" name="CP_LPAC_ROQ_DBG_ADDR" variants="A7XX"/> + <reg32 offset="0x0b27" name="CP_SQE_AC_UCODE_DBG_ADDR" variants="A7XX"/> + <reg32 offset="0x0b28" name="CP_SQE_AC_UCODE_DBG_DATA" variants="A7XX"/> + <reg32 offset="0x0b29" name="CP_SQE_AC_STAT_ADDR" variants="A7XX"/> + <reg32 offset="0x0b2a" name="CP_SQE_AC_STAT_DATA" variants="A7XX"/> + + <reg32 offset="0x0b31" name="CP_LPAC_APRIV_CNTL" variants="A7XX"/> + <reg32 offset="0x0b34" name="CP_LPAC_PROG_FIFO_SIZE" variants="A7XX"/> + <reg32 offset="0x0b35" name="CP_LPAC_ROQ_DBG_DATA" variants="A7XX"/> + <reg32 offset="0x0b36" name="CP_LPAC_FIFO_DBG_DATA" variants="A7XX"/> + <reg32 offset="0x0b40" name="CP_LPAC_FIFO_DBG_ADDR" variants="A7XX"/> + <reg32 offset="0x0b81" name="CP_LPAC_SQE_CNTL" variants="A6XX-A7XX"/> + <reg64 offset="0x0b82" name="CP_LPAC_SQE_INSTR_BASE" variants="A6XX-A7XX"/> + + <reg64 offset="0x0b70" name="CP_AQE_INSTR_BASE_0" variants="A7XX"/> + <reg64 offset="0x0b72" name="CP_AQE_INSTR_BASE_1" variants="A7XX"/> + <reg32 offset="0x0b78" name="CP_AQE_APRIV_CNTL" variants="A7XX"/> + + <reg32 offset="0x0ba8" name="CP_AQE_ROQ_DBG_ADDR_0" variants="A7XX"/> + <reg32 offset="0x0ba9" name="CP_AQE_ROQ_DBG_ADDR_1" variants="A7XX"/> + <reg32 offset="0x0bac" name="CP_AQE_ROQ_DBG_DATA_0" variants="A7XX"/> + <reg32 offset="0x0bad" name="CP_AQE_ROQ_DBG_DATA_1" variants="A7XX"/> + <reg32 offset="0x0bb0" name="CP_AQE_UCODE_DBG_ADDR_0" variants="A7XX"/> + <reg32 offset="0x0bb1" name="CP_AQE_UCODE_DBG_ADDR_1" variants="A7XX"/> + <reg32 offset="0x0bb4" name="CP_AQE_UCODE_DBG_DATA_0" variants="A7XX"/> + <reg32 offset="0x0bb5" name="CP_AQE_UCODE_DBG_DATA_1" variants="A7XX"/> + <reg32 offset="0x0bb8" name="CP_AQE_STAT_ADDR_0" variants="A7XX"/> + <reg32 offset="0x0bb9" name="CP_AQE_STAT_ADDR_1" variants="A7XX"/> + <reg32 offset="0x0bbc" name="CP_AQE_STAT_DATA_0" variants="A7XX"/> + <reg32 offset="0x0bbd" name="CP_AQE_STAT_DATA_1" variants="A7XX"/> + + <reg32 offset="0x0C01" name="VSC_ADDR_MODE_CNTL" type="a5xx_address_mode" variants="A6XX"/> + <reg32 offset="0x0018" name="RBBM_GPR0_CNTL" variants="A6XX"/> + <reg32 offset="0x0201" name="RBBM_INT_0_STATUS" type="A6XX_RBBM_INT_0_MASK" variants="A6XX-A7XX"/> + <reg32 offset="0x006a" name="RBBM_INT_0_STATUS" type="A6XX_RBBM_INT_0_MASK" variants="A8XX-"/> + <reg32 offset="0x0210" name="RBBM_STATUS" variants="A6XX-A7XX"> <bitfield pos="23" name="GPU_BUSY_IGN_AHB" type="boolean"/> <bitfield pos="22" name="GPU_BUSY_IGN_AHB_CP" type="boolean"/> <bitfield pos="21" name="HLSQ_BUSY" type="boolean"/> @@ -342,22 +571,59 @@ by a particular renderpass/blit. <bitfield pos="1" name="CP_AHB_BUSY_CP_MASTER" type="boolean"/> <bitfield pos="0" name="CP_AHB_BUSY_CX_MASTER" type="boolean"/> </reg32> - <reg32 offset="0x0211" name="RBBM_STATUS1"/> - <reg32 offset="0x0212" name="RBBM_STATUS2"/> - <reg32 offset="0x0213" name="RBBM_STATUS3"> + <reg32 offset="0x0211" name="RBBM_STATUS1" variants="A6XX-A7XX"/> + <reg32 offset="0x0212" name="RBBM_STATUS2" variants="A6XX-A7XX"/> + <reg32 offset="0x0213" name="RBBM_STATUS3" variants="A6XX-A7XX"> <bitfield pos="24" name="SMMU_STALLED_ON_FAULT" type="boolean"/> </reg32> - <reg32 offset="0x0215" name="RBBM_VBIF_GX_RESET_STATUS"/> - <reg32 offset="0x0260" name="RBBM_CLOCK_MODE_CP" variants="A7XX-"/> - <reg32 offset="0x0284" name="RBBM_CLOCK_MODE_BV_LRZ" variants="A7XX-"/> - <reg32 offset="0x0285" name="RBBM_CLOCK_MODE_BV_GRAS" variants="A7XX-"/> - <reg32 offset="0x0286" name="RBBM_CLOCK_MODE2_GRAS" variants="A7XX-"/> - <reg32 offset="0x0287" name="RBBM_CLOCK_MODE_BV_VFD" variants="A7XX-"/> - <reg32 offset="0x0288" name="RBBM_CLOCK_MODE_BV_GPC" variants="A7XX-"/> + <reg32 offset="0x012" name="RBBM_STATUS" variants="A8XX-"> + <bitfield pos="23" name="GPU_BUSY_IGN_AHB" type="boolean"/> + <bitfield pos="22" name="GPU_BUSY_IGN_AHB_CP" type="boolean"/> + <bitfield pos="21" name="SLICE_BUSY_IGN_CP" type="boolean"/> + <bitfield pos="20" name="CP_SLICE_BUSY" type="boolean"/> + <bitfield pos="19" name="UNSLICE_BUSY_IGN_AHB" type="boolean"/> + <bitfield pos="18" name="UNSLICE_BUSY_IGN_AHB_CP" type="boolean"/> + <bitfield pos="17" name="CP_SLICE_RL_BUSY" type="boolean"/> + <bitfield pos="14" name="UNSLICE_TOP_BUSY" type="boolean"/> + <bitfield pos="13" name="UFC_BUSY" type="boolean"/> + <bitfield pos="12" name="HLSQ_BUSY" type="boolean"/> + <bitfield pos="11" name="VSC_BUSY" type="boolean"/> + <bitfield pos="10" name="UCHE_BUSY" type="boolean"/> + <bitfield pos="9" name="VPC_BUSY" type="boolean"/> + <bitfield pos="8" name="PC_BUSY" type="boolean"/> + <bitfield pos="7" name="CMP_BUSY" type="boolean"/> + <bitfield pos="6" name="DCMP_BUSY" type="boolean"/> + <bitfield pos="5" name="VBIF_GX_BUSY" type="boolean"/> + <bitfield pos="4" name="DBGC_PERF_BUSY" type="boolean"/> + <bitfield pos="3" name="GFX_DBGC_BUSY" type="boolean"/> + <bitfield pos="2" name="CP_BUSY" type="boolean"/> + <bitfield pos="1" name="CP_AHB_BUSY_CP_MASTER" type="boolean"/> + <bitfield pos="0" name="CP_AHB_BUSY_CX_MASTER" type="boolean"/> + </reg32> + <reg32 offset="0x013" name="RBBM_STATUS1" variants="A8XX-"/> + <reg32 offset="0x015" name="RBBM_GFX_STATUS" variants="A8XX-"/> + <reg32 offset="0x016" name="RBBM_GFX_STATUS1" variants="A8XX-"/> + <reg32 offset="0x018" name="RBBM_LPAC_STATUS" variants="A8XX-"/> + <reg32 offset="0x01a" name="RBBM_GFX_BR_STATUS" variants="A8XX-"/> + <reg32 offset="0x01c" name="RBBM_GFX_BV_STATUS" variants="A8XX-"/> + <reg32 offset="0x01e" name="RBBM_MISC_STATUS" variants="A8XX-"> + <bitfield pos="0" name="SMMU_STALLED_ON_FAULT" type="boolean"/> + </reg32> + + <reg32 offset="0x0215" name="RBBM_VBIF_GX_RESET_STATUS" variants="A6XX"/> - <reg32 offset="0x02c0" name="RBBM_SW_FUSE_INT_STATUS" variants="A7XX-"/> - <reg32 offset="0x02c1" name="RBBM_SW_FUSE_INT_MASK" variants="A7XX-"/> + <reg32 offset="0x0260" name="RBBM_CLOCK_MODE_CP" variants="A7XX"/> + <reg32 offset="0x0284" name="RBBM_CLOCK_MODE_BV_LRZ" variants="A7XX"/> + <reg32 offset="0x0285" name="RBBM_CLOCK_MODE_BV_GRAS" variants="A7XX"/> + <reg32 offset="0x0286" name="RBBM_CLOCK_MODE2_GRAS" variants="A7XX"/> + <reg32 offset="0x0287" name="RBBM_CLOCK_MODE_BV_VFD" variants="A7XX"/> + <reg32 offset="0x0288" name="RBBM_CLOCK_MODE_BV_GPC" variants="A7XX"/> + + <reg32 offset="0x02c0" name="RBBM_SW_FUSE_INT_STATUS" variants="A7XX"/> + <reg32 offset="0x02c1" name="RBBM_SW_FUSE_INT_MASK" variants="A7XX"/> + <reg32 offset="0x0071" name="RBBM_SW_FUSE_INT_STATUS" variants="A8XX-"/> + <reg32 offset="0x0072" name="RBBM_SW_FUSE_INT_MASK" variants="A8XX-"/> <array offset="0x0400" name="RBBM_PERFCTR_CP" stride="2" length="14" variants="A6XX"/> <array offset="0x041c" name="RBBM_PERFCTR_RBBM" stride="2" length="4" variants="A6XX"/> @@ -376,49 +642,96 @@ by a particular renderpass/blit. <array offset="0x04ea" name="RBBM_PERFCTR_LRZ" stride="2" length="4" variants="A6XX"/> <array offset="0x04f2" name="RBBM_PERFCTR_CMP" stride="2" length="4" variants="A6XX"/> - <array offset="0x0300" name="RBBM_PERFCTR_CP" stride="2" length="14" variants="A7XX-"/> - <array offset="0x031c" name="RBBM_PERFCTR_RBBM" stride="2" length="4" variants="A7XX-"/> - <array offset="0x0324" name="RBBM_PERFCTR_PC" stride="2" length="8" variants="A7XX-"/> - <array offset="0x0334" name="RBBM_PERFCTR_VFD" stride="2" length="8" variants="A7XX-"/> - <array offset="0x0344" name="RBBM_PERFCTR_HLSQ" stride="2" length="6" variants="A7XX-"/> - <array offset="0x0350" name="RBBM_PERFCTR_VPC" stride="2" length="6" variants="A7XX-"/> - <array offset="0x035c" name="RBBM_PERFCTR_CCU" stride="2" length="5" variants="A7XX-"/> - <array offset="0x0366" name="RBBM_PERFCTR_TSE" stride="2" length="4" variants="A7XX-"/> - <array offset="0x036e" name="RBBM_PERFCTR_RAS" stride="2" length="4" variants="A7XX-"/> - <array offset="0x0376" name="RBBM_PERFCTR_UCHE" stride="2" length="12" variants="A7XX-"/> - <array offset="0x038e" name="RBBM_PERFCTR_TP" stride="2" length="12" variants="A7XX-"/> - <array offset="0x03a6" name="RBBM_PERFCTR_SP" stride="2" length="24" variants="A7XX-"/> - <array offset="0x03d6" name="RBBM_PERFCTR_RB" stride="2" length="8" variants="A7XX-"/> - <array offset="0x03e6" name="RBBM_PERFCTR_VSC" stride="2" length="2" variants="A7XX-"/> - <array offset="0x03ea" name="RBBM_PERFCTR_LRZ" stride="2" length="4" variants="A7XX-"/> - <array offset="0x03f2" name="RBBM_PERFCTR_CMP" stride="2" length="4" variants="A7XX-"/> - <array offset="0x03fa" name="RBBM_PERFCTR_UFC" stride="2" length="4" variants="A7XX-"/> - <array offset="0x0410" name="RBBM_PERFCTR2_HLSQ" stride="2" length="6" variants="A7XX-"/> - <array offset="0x041c" name="RBBM_PERFCTR2_CP" stride="2" length="7" variants="A7XX-"/> - <array offset="0x042a" name="RBBM_PERFCTR2_SP" stride="2" length="12" variants="A7XX-"/> - <array offset="0x0442" name="RBBM_PERFCTR2_TP" stride="2" length="6" variants="A7XX-"/> - <array offset="0x044e" name="RBBM_PERFCTR2_UFC" stride="2" length="2" variants="A7XX-"/> - <array offset="0x0460" name="RBBM_PERFCTR_BV_PC" stride="2" length="8" variants="A7XX-"/> - <array offset="0x0470" name="RBBM_PERFCTR_BV_VFD" stride="2" length="8" variants="A7XX-"/> - <array offset="0x0480" name="RBBM_PERFCTR_BV_VPC" stride="2" length="6" variants="A7XX-"/> - <array offset="0x048c" name="RBBM_PERFCTR_BV_TSE" stride="2" length="4" variants="A7XX-"/> - <array offset="0x0494" name="RBBM_PERFCTR_BV_RAS" stride="2" length="4" variants="A7XX-"/> - <array offset="0x049c" name="RBBM_PERFCTR_BV_LRZ" stride="2" length="4" variants="A7XX-"/> - - <reg32 offset="0x0500" name="RBBM_PERFCTR_CNTL"/> - <reg32 offset="0x0501" name="RBBM_PERFCTR_LOAD_CMD0"/> - <reg32 offset="0x0502" name="RBBM_PERFCTR_LOAD_CMD1"/> - <reg32 offset="0x0503" name="RBBM_PERFCTR_LOAD_CMD2"/> - <reg32 offset="0x0504" name="RBBM_PERFCTR_LOAD_CMD3"/> - <reg32 offset="0x0505" name="RBBM_PERFCTR_LOAD_VALUE_LO"/> - <reg32 offset="0x0506" name="RBBM_PERFCTR_LOAD_VALUE_HI"/> - <array offset="0x0507" name="RBBM_PERFCTR_RBBM_SEL" stride="1" length="4"/> - <reg32 offset="0x050B" name="RBBM_PERFCTR_GPU_BUSY_MASKED"/> - <reg32 offset="0x050e" name="RBBM_PERFCTR_SRAM_INIT_CMD"/> - <reg32 offset="0x050f" name="RBBM_PERFCTR_SRAM_INIT_STATUS"/> - <reg32 offset="0x0533" name="RBBM_ISDB_CNT"/> - <reg32 offset="0x0534" name="RBBM_NC_MODE_CNTL"/> - <reg32 offset="0x0535" name="RBBM_SNAPSHOT_STATUS" variants="A7XX-"/> + <array offset="0x0300" name="RBBM_PERFCTR_CP" stride="2" length="14" variants="A7XX"/> + <array offset="0x031c" name="RBBM_PERFCTR_RBBM" stride="2" length="4" variants="A7XX"/> + <array offset="0x0324" name="RBBM_PERFCTR_PC" stride="2" length="8" variants="A7XX"/> + <array offset="0x0334" name="RBBM_PERFCTR_VFD" stride="2" length="8" variants="A7XX"/> + <array offset="0x0344" name="RBBM_PERFCTR_HLSQ" stride="2" length="6" variants="A7XX"/> + <array offset="0x0350" name="RBBM_PERFCTR_VPC" stride="2" length="6" variants="A7XX"/> + <array offset="0x035c" name="RBBM_PERFCTR_CCU" stride="2" length="5" variants="A7XX"/> + <array offset="0x0366" name="RBBM_PERFCTR_TSE" stride="2" length="4" variants="A7XX"/> + <array offset="0x036e" name="RBBM_PERFCTR_RAS" stride="2" length="4" variants="A7XX"/> + <array offset="0x0376" name="RBBM_PERFCTR_UCHE" stride="2" length="12" variants="A7XX"/> + <array offset="0x038e" name="RBBM_PERFCTR_TP" stride="2" length="12" variants="A7XX"/> + <array offset="0x03a6" name="RBBM_PERFCTR_SP" stride="2" length="24" variants="A7XX"/> + <array offset="0x03d6" name="RBBM_PERFCTR_RB" stride="2" length="8" variants="A7XX"/> + <array offset="0x03e6" name="RBBM_PERFCTR_VSC" stride="2" length="2" variants="A7XX"/> + <array offset="0x03ea" name="RBBM_PERFCTR_LRZ" stride="2" length="4" variants="A7XX"/> + <array offset="0x03f2" name="RBBM_PERFCTR_CMP" stride="2" length="4" variants="A7XX"/> + <array offset="0x03fa" name="RBBM_PERFCTR_UFC" stride="2" length="4" variants="A7XX"/> + <array offset="0x0410" name="RBBM_PERFCTR2_HLSQ" stride="2" length="6" variants="A7XX"/> + <array offset="0x041c" name="RBBM_PERFCTR2_CP" stride="2" length="7" variants="A7XX"/> + <array offset="0x042a" name="RBBM_PERFCTR2_SP" stride="2" length="12" variants="A7XX"/> + <array offset="0x0442" name="RBBM_PERFCTR2_TP" stride="2" length="6" variants="A7XX"/> + <array offset="0x044e" name="RBBM_PERFCTR2_UFC" stride="2" length="2" variants="A7XX"/> + <array offset="0x0460" name="RBBM_PERFCTR_BV_PC" stride="2" length="8" variants="A7XX"/> + <array offset="0x0470" name="RBBM_PERFCTR_BV_VFD" stride="2" length="8" variants="A7XX"/> + <array offset="0x0480" name="RBBM_PERFCTR_BV_VPC" stride="2" length="6" variants="A7XX"/> + <array offset="0x048c" name="RBBM_PERFCTR_BV_TSE" stride="2" length="4" variants="A7XX"/> + <array offset="0x0494" name="RBBM_PERFCTR_BV_RAS" stride="2" length="4" variants="A7XX"/> + <array offset="0x049c" name="RBBM_PERFCTR_BV_LRZ" stride="2" length="4" variants="A7XX"/> + + <array offset="0x01b0" name="RBBM_PERFCTR_CP" stride="2" length="14" variants="A8XX"/> + <array offset="0x01cc" name="RBBM_PERFCTR_RBBM" stride="2" length="4" variants="A8XX"/> + <array offset="0x01d4" name="RBBM_PERFCTR_PC" stride="2" length="8" variants="A8XX"/> + <array offset="0x01e4" name="RBBM_PERFCTR_VFD" stride="2" length="8" variants="A8XX"/> + <array offset="0x01f4" name="RBBM_PERFCTR_HLSQ" stride="2" length="6" variants="A8XX"/> + <array offset="0x0200" name="RBBM_PERFCTR_VPC" stride="2" length="6" variants="A8XX"/> + <array offset="0x020c" name="RBBM_PERFCTR_CCU" stride="2" length="5" variants="A8XX"/> + <array offset="0x0216" name="RBBM_PERFCTR_TSE" stride="2" length="4" variants="A8XX"/> + <array offset="0x021e" name="RBBM_PERFCTR_RAS" stride="2" length="4" variants="A8XX"/> + <array offset="0x0226" name="RBBM_PERFCTR_UCHE" stride="2" length="24" variants="A8XX"/> + <array offset="0x0256" name="RBBM_PERFCTR_TP" stride="2" length="12" variants="A8XX"/> + <array offset="0x026e" name="RBBM_PERFCTR_SP" stride="2" length="24" variants="A8XX"/> + <array offset="0x029e" name="RBBM_PERFCTR_RB" stride="2" length="8" variants="A8XX"/> + <array offset="0x02ae" name="RBBM_PERFCTR_VSC" stride="2" length="2" variants="A8XX"/> + <array offset="0x02b2" name="RBBM_PERFCTR_LRZ" stride="2" length="4" variants="A8XX"/> + <array offset="0x02ba" name="RBBM_PERFCTR_CMP" stride="2" length="4" variants="A8XX"/> + <array offset="0x02c2" name="RBBM_PERFCTR_UFC" stride="2" length="4" variants="A8XX"/> + <array offset="0x02e2" name="RBBM_PERFCTR2_HLSQ" stride="2" length="6" variants="A8XX"/> + <array offset="0x02ee" name="RBBM_PERFCTR2_CP" stride="2" length="7" variants="A8XX"/> + <array offset="0x02fc" name="RBBM_PERFCTR2_SP" stride="2" length="12" variants="A8XX"/> + <array offset="0x0314" name="RBBM_PERFCTR2_TP" stride="2" length="8" variants="A8XX"/> + <array offset="0x0324" name="RBBM_PERFCTR2_UFC" stride="2" length="2" variants="A8XX"/> + <array offset="0x0328" name="RBBM_PERFCTR_BV_PC" stride="2" length="8" variants="A8XX"/> + <array offset="0x0338" name="RBBM_PERFCTR_BV_VFD" stride="2" length="8" variants="A8XX"/> + <array offset="0x0348" name="RBBM_PERFCTR_BV_VPC" stride="2" length="6" variants="A8XX"/> + <array offset="0x0354" name="RBBM_PERFCTR_BV_TSE" stride="2" length="4" variants="A8XX"/> + <array offset="0x035c" name="RBBM_PERFCTR_BV_RAS" stride="2" length="4" variants="A8XX"/> + <array offset="0x0364" name="RBBM_PERFCTR_BV_LRZ" stride="2" length="4" variants="A8XX"/> + <array offset="0x036c" name="RBBM_PERFCTR_BV_CCU" stride="2" length="3" variants="A8XX"/> + <array offset="0x0372" name="RBBM_PERFCTR_BV_RB" stride="2" length="6" variants="A8XX"/> + + <reg32 offset="0x0500" name="RBBM_PERFCTR_CNTL" variants="A6XX-A7XX"/> + <reg32 offset="0x0460" name="RBBM_PERFCTR_CNTL" variants="A8XX-"/> + <reg32 offset="0x0501" name="RBBM_PERFCTR_LOAD_CMD0" variants="A6XX"/> + <reg32 offset="0x0502" name="RBBM_PERFCTR_LOAD_CMD1" variants="A6XX"/> + <reg32 offset="0x0503" name="RBBM_PERFCTR_LOAD_CMD2" variants="A6XX"/> + <reg32 offset="0x0504" name="RBBM_PERFCTR_LOAD_CMD3" variants="A6XX"/> + <reg64 offset="0x0505" name="RBBM_PERFCTR_LOAD_VALUE" variants="A6XX"/> + <array offset="0x0507" name="RBBM_PERFCTR_RBBM_SEL" stride="1" length="4" variants="A6XX-A7XX"/> + <array offset="0x0441" name="RBBM_PERFCTR_RBBM_SEL" stride="1" length="4" variants="A8XX-"/> + <reg32 offset="0x050B" name="RBBM_PERFCTR_GPU_BUSY_MASKED" variants="A6XX-A7XX"/> + <reg32 offset="0x019e" name="RBBM_PERFCTR_GPU_BUSY_MASKED" variants="A8XX-"/> + <reg32 offset="0x050e" name="RBBM_PERFCTR_SRAM_INIT_CMD" variants="A6XX-A7XX"/> + <reg32 offset="0x0449" name="RBBM_PERFCTR_SRAM_INIT_CMD" variants="A8XX-"/> + <reg32 offset="0x050f" name="RBBM_PERFCTR_SRAM_INIT_STATUS" variants="A6XX-A7XX"/> + <reg32 offset="0x019f" name="RBBM_PERFCTR_SRAM_INIT_STATUS" variants="A8XX-"/> + <reg32 offset="0x01a1" name="RBBM_PERFCTR_FLUSH_HOST_STATUS" variants="A8XX-"/> + <reg32 offset="0x044c" name="RBBM_PERFCTR_FLUSH_HOST_CMD" variants="A8XX-"/> + <reg32 offset="0x0533" name="RBBM_ISDB_CNT" variants="A6XX-A7XX"/> + <reg32 offset="0x002d" name="RBBM_ISDB_CNT" variants="A8XX-"/> + <reg32 offset="0x0534" name="RBBM_NC_MODE_CNTL" variants="A6XX-A7XX"/> + <reg32 offset="0x0440" name="RBBM_NC_MODE_CNTL" variants="A8XX-"/> + <reg32 offset="0x0535" name="RBBM_SNAPSHOT_STATUS" variants="A7XX"/> + <reg32 offset="0x002e" name="RBBM_SNAPSHOT_STATUS" variants="A8XX-"/> + + <reg32 offset="0x500" name="RBBM_SLICE_PERFCTR_CNTL" variants="A8XX-"/> + <reg32 offset="0x58f" name="RBBM_SLICE_INTERFACE_HANG_INT_CNTL" variants="A8XX-"/> + <array offset="0x5e0" name="RBBM_SLICE_PERFCTR_RBBM_SEL" stride="1" length="4" variants="A8XX-"/> + <reg32 offset="0x5e8" name="RBBM_SLICE_PERFCTR_SRAM_INIT_CMD" variants="A8XX-"/> + <reg32 offset="0x5eb" name="RBBM_SLICE_PERFCTR_FLUSH_HOST_CMD" variants="A8XX-"/> + <reg32 offset="0x5ec" name="RBBM_SLICE_NC_MODE_CNTL" variants="A8XX-"/> <!--- This block of registers aren't tied to perf counters. They @@ -426,170 +739,211 @@ by a particular renderpass/blit. vertices in, number of primnitives assembled etc. --> - <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"/> + <reg64 offset="0x0540" name="RBBM_PIPESTAT_IAVERTICES" variants="A6XX-A7XX"/> + <reg64 offset="0x0542" name="RBBM_PIPESTAT_IAPRIMITIVES" variants="A6XX-A7XX"/> + <reg64 offset="0x0544" name="RBBM_PIPESTAT_VSINVOCATIONS" variants="A6XX-A7XX"/> + <reg64 offset="0x0546" name="RBBM_PIPESTAT_HSINVOCATIONS" variants="A6XX-A7XX"/> + <reg64 offset="0x0548" name="RBBM_PIPESTAT_DSINVOCATIONS" variants="A6XX-A7XX"/> + <reg64 offset="0x054a" name="RBBM_PIPESTAT_GSINVOCATIONS" variants="A6XX-A7XX"/> + <reg64 offset="0x054c" name="RBBM_PIPESTAT_GSPRIMITIVES" variants="A6XX-A7XX"/> + <reg64 offset="0x054e" name="RBBM_PIPESTAT_CINVOCATIONS" variants="A6XX-A7XX"/> + <reg64 offset="0x0550" name="RBBM_PIPESTAT_CPRIMITIVES" variants="A6XX-A7XX"/> + <reg64 offset="0x0552" name="RBBM_PIPESTAT_PSINVOCATIONS" variants="A6XX-A7XX"/> + <reg64 offset="0x0554" name="RBBM_PIPESTAT_CSINVOCATIONS" variants="A6XX-A7XX"/> + + <reg64 offset="0x0380" name="RBBM_PIPESTAT_IAVERTICES" variants="A8XX-"/> + <reg64 offset="0x0382" name="RBBM_PIPESTAT_IAPRIMITIVES" variants="A8XX-"/> + <reg64 offset="0x0384" name="RBBM_PIPESTAT_VSINVOCATIONS" variants="A8XX-"/> + <reg64 offset="0x0386" name="RBBM_PIPESTAT_GSINVOCATIONS" variants="A8XX-"/> + <reg64 offset="0x0388" name="RBBM_PIPESTAT_GSPRIMITIVES" variants="A8XX-"/> + <reg64 offset="0x038a" name="RBBM_PIPESTAT_CINVOCATIONS" variants="A8XX-"/> + <reg64 offset="0x038c" name="RBBM_PIPESTAT_CPRIMITIVES" variants="A8XX-"/> + <reg64 offset="0x038e" name="RBBM_PIPESTAT_PSINVOCATIONS" variants="A8XX-"/> + <reg64 offset="0x0390" name="RBBM_PIPESTAT_HSINVOCATIONS" variants="A8XX-"/> + <reg64 offset="0x0392" name="RBBM_PIPESTAT_DSINVOCATIONS" variants="A8XX-"/> + <reg64 offset="0x0394" name="RBBM_PIPESTAT_CSINVOCATIONS" variants="A8XX-"/> + <reg64 offset="0x0396" name="RBBM_PIPESTAT_ASINVOCATIONS" variants="A8XX-"/> + <reg64 offset="0x0398" name="RBBM_PIPESTAT_MSINVOCATIONS" variants="A8XX-"/> + <reg64 offset="0x039a" name="RBBM_PIPESTAT_MSPRIMITIVES" variants="A8XX-"/> <reg32 offset="0xF400" name="RBBM_SECVID_TRUST_CNTL"/> <reg64 offset="0xF800" name="RBBM_SECVID_TSB_TRUSTED_BASE"/> <reg32 offset="0xF802" name="RBBM_SECVID_TSB_TRUSTED_SIZE"/> <reg32 offset="0xF803" name="RBBM_SECVID_TSB_CNTL"/> - <reg32 offset="0xF810" name="RBBM_SECVID_TSB_ADDR_MODE_CNTL" type="a5xx_address_mode"/> + <reg32 offset="0xF810" name="RBBM_SECVID_TSB_ADDR_MODE_CNTL" type="a5xx_address_mode" variants="A6XX"/> <reg64 offset="0xfc00" name="RBBM_SECVID_TSB_STATUS" variants="A7XX-"/> - <reg32 offset="0x00010" name="RBBM_VBIF_CLIENT_QOS_CNTL"/> - <reg32 offset="0x00011" name="RBBM_GBIF_CLIENT_QOS_CNTL"/> - <reg32 offset="0x00016" name="RBBM_GBIF_HALT"/> - <reg32 offset="0x00017" name="RBBM_GBIF_HALT_ACK"/> - <reg32 offset="0x0001c" name="RBBM_WAIT_FOR_GPU_IDLE_CMD"> + <reg32 offset="0x00010" name="RBBM_VBIF_CLIENT_QOS_CNTL" variants="A6XX"/> + <reg32 offset="0x00011" name="RBBM_GBIF_CLIENT_QOS_CNTL" variants="A6XX-A7XX"/> + <reg32 offset="0x00008" name="RBBM_GBIF_CLIENT_QOS_CNTL" variants="A8XX-"/> + <reg32 offset="0x00016" name="RBBM_GBIF_HALT" variants="A6XX-A7XX"/> + <reg32 offset="0x0000a" name="RBBM_GBIF_HALT" variants="A8XX-"/> + <reg32 offset="0x00017" name="RBBM_GBIF_HALT_ACK" variants="A6XX-A7XX"/> + <reg32 offset="0x0000b" name="RBBM_GBIF_HALT_ACK" variants="A8XX-"/> + <reg32 offset="0x0001c" name="RBBM_WAIT_FOR_GPU_IDLE_CMD" variants="A6XX"> <bitfield pos="0" name="WAIT_GPU_IDLE" type="boolean"/> </reg32> - <reg32 offset="0x00016" name="RBBM_GBIF_HALT" variants="A7XX-"/> - <reg32 offset="0x00017" name="RBBM_GBIF_HALT_ACK" variants="A7XX-"/> - <reg32 offset="0x0001f" name="RBBM_INTERFACE_HANG_INT_CNTL"/> - <reg32 offset="0x00037" name="RBBM_INT_CLEAR_CMD" type="A6XX_RBBM_INT_0_MASK"/> - <reg32 offset="0x00038" name="RBBM_INT_0_MASK" type="A6XX_RBBM_INT_0_MASK"/> - <reg32 offset="0x0003a" name="RBBM_INT_2_MASK" variants="A7XX-"/> - <reg32 offset="0x00042" name="RBBM_SP_HYST_CNT"/> - <reg32 offset="0x00043" name="RBBM_SW_RESET_CMD"/> - <reg32 offset="0x00044" name="RBBM_RAC_THRESHOLD_CNT"/> - <reg32 offset="0x00045" name="RBBM_BLOCK_SW_RESET_CMD"/> - <reg32 offset="0x00046" name="RBBM_BLOCK_SW_RESET_CMD2"/> - <reg32 offset="0x000ad" name="RBBM_CLOCK_CNTL_GLOBAL" variants="A7XX-"/> - <reg32 offset="0x000ae" name="RBBM_CLOCK_CNTL"/> - <reg32 offset="0x000b0" name="RBBM_CLOCK_CNTL_SP0"/> - <reg32 offset="0x000b1" name="RBBM_CLOCK_CNTL_SP1"/> - <reg32 offset="0x000b2" name="RBBM_CLOCK_CNTL_SP2"/> - <reg32 offset="0x000b3" name="RBBM_CLOCK_CNTL_SP3"/> - <reg32 offset="0x000b4" name="RBBM_CLOCK_CNTL2_SP0"/> - <reg32 offset="0x000b5" name="RBBM_CLOCK_CNTL2_SP1"/> - <reg32 offset="0x000b6" name="RBBM_CLOCK_CNTL2_SP2"/> - <reg32 offset="0x000b7" name="RBBM_CLOCK_CNTL2_SP3"/> - <reg32 offset="0x000b8" name="RBBM_CLOCK_DELAY_SP0"/> - <reg32 offset="0x000b9" name="RBBM_CLOCK_DELAY_SP1"/> - <reg32 offset="0x000ba" name="RBBM_CLOCK_DELAY_SP2"/> - <reg32 offset="0x000bb" name="RBBM_CLOCK_DELAY_SP3"/> - <reg32 offset="0x000bc" name="RBBM_CLOCK_HYST_SP0"/> - <reg32 offset="0x000bd" name="RBBM_CLOCK_HYST_SP1"/> - <reg32 offset="0x000be" name="RBBM_CLOCK_HYST_SP2"/> - <reg32 offset="0x000bf" name="RBBM_CLOCK_HYST_SP3"/> - <reg32 offset="0x000c0" name="RBBM_CLOCK_CNTL_TP0"/> - <reg32 offset="0x000c1" name="RBBM_CLOCK_CNTL_TP1"/> - <reg32 offset="0x000c2" name="RBBM_CLOCK_CNTL_TP2"/> - <reg32 offset="0x000c3" name="RBBM_CLOCK_CNTL_TP3"/> - <reg32 offset="0x000c4" name="RBBM_CLOCK_CNTL2_TP0"/> - <reg32 offset="0x000c5" name="RBBM_CLOCK_CNTL2_TP1"/> - <reg32 offset="0x000c6" name="RBBM_CLOCK_CNTL2_TP2"/> - <reg32 offset="0x000c7" name="RBBM_CLOCK_CNTL2_TP3"/> - <reg32 offset="0x000c8" name="RBBM_CLOCK_CNTL3_TP0"/> - <reg32 offset="0x000c9" name="RBBM_CLOCK_CNTL3_TP1"/> - <reg32 offset="0x000ca" name="RBBM_CLOCK_CNTL3_TP2"/> - <reg32 offset="0x000cb" name="RBBM_CLOCK_CNTL3_TP3"/> - <reg32 offset="0x000cc" name="RBBM_CLOCK_CNTL4_TP0"/> - <reg32 offset="0x000cd" name="RBBM_CLOCK_CNTL4_TP1"/> - <reg32 offset="0x000ce" name="RBBM_CLOCK_CNTL4_TP2"/> - <reg32 offset="0x000cf" name="RBBM_CLOCK_CNTL4_TP3"/> - <reg32 offset="0x000d0" name="RBBM_CLOCK_DELAY_TP0"/> - <reg32 offset="0x000d1" name="RBBM_CLOCK_DELAY_TP1"/> - <reg32 offset="0x000d2" name="RBBM_CLOCK_DELAY_TP2"/> - <reg32 offset="0x000d3" name="RBBM_CLOCK_DELAY_TP3"/> - <reg32 offset="0x000d4" name="RBBM_CLOCK_DELAY2_TP0"/> - <reg32 offset="0x000d5" name="RBBM_CLOCK_DELAY2_TP1"/> - <reg32 offset="0x000d6" name="RBBM_CLOCK_DELAY2_TP2"/> - <reg32 offset="0x000d7" name="RBBM_CLOCK_DELAY2_TP3"/> - <reg32 offset="0x000d8" name="RBBM_CLOCK_DELAY3_TP0"/> - <reg32 offset="0x000d9" name="RBBM_CLOCK_DELAY3_TP1"/> - <reg32 offset="0x000da" name="RBBM_CLOCK_DELAY3_TP2"/> - <reg32 offset="0x000db" name="RBBM_CLOCK_DELAY3_TP3"/> - <reg32 offset="0x000dc" name="RBBM_CLOCK_DELAY4_TP0"/> - <reg32 offset="0x000dd" name="RBBM_CLOCK_DELAY4_TP1"/> - <reg32 offset="0x000de" name="RBBM_CLOCK_DELAY4_TP2"/> - <reg32 offset="0x000df" name="RBBM_CLOCK_DELAY4_TP3"/> - <reg32 offset="0x000e0" name="RBBM_CLOCK_HYST_TP0"/> - <reg32 offset="0x000e1" name="RBBM_CLOCK_HYST_TP1"/> - <reg32 offset="0x000e2" name="RBBM_CLOCK_HYST_TP2"/> - <reg32 offset="0x000e3" name="RBBM_CLOCK_HYST_TP3"/> - <reg32 offset="0x000e4" name="RBBM_CLOCK_HYST2_TP0"/> - <reg32 offset="0x000e5" name="RBBM_CLOCK_HYST2_TP1"/> - <reg32 offset="0x000e6" name="RBBM_CLOCK_HYST2_TP2"/> - <reg32 offset="0x000e7" name="RBBM_CLOCK_HYST2_TP3"/> - <reg32 offset="0x000e8" name="RBBM_CLOCK_HYST3_TP0"/> - <reg32 offset="0x000e9" name="RBBM_CLOCK_HYST3_TP1"/> - <reg32 offset="0x000ea" name="RBBM_CLOCK_HYST3_TP2"/> - <reg32 offset="0x000eb" name="RBBM_CLOCK_HYST3_TP3"/> - <reg32 offset="0x000ec" name="RBBM_CLOCK_HYST4_TP0"/> - <reg32 offset="0x000ed" name="RBBM_CLOCK_HYST4_TP1"/> - <reg32 offset="0x000ee" name="RBBM_CLOCK_HYST4_TP2"/> - <reg32 offset="0x000ef" name="RBBM_CLOCK_HYST4_TP3"/> - <reg32 offset="0x000f0" name="RBBM_CLOCK_CNTL_RB0"/> - <reg32 offset="0x000f1" name="RBBM_CLOCK_CNTL_RB1"/> - <reg32 offset="0x000f2" name="RBBM_CLOCK_CNTL_RB2"/> - <reg32 offset="0x000f3" name="RBBM_CLOCK_CNTL_RB3"/> - <reg32 offset="0x000f4" name="RBBM_CLOCK_CNTL2_RB0"/> - <reg32 offset="0x000f5" name="RBBM_CLOCK_CNTL2_RB1"/> - <reg32 offset="0x000f6" name="RBBM_CLOCK_CNTL2_RB2"/> - <reg32 offset="0x000f7" name="RBBM_CLOCK_CNTL2_RB3"/> - <reg32 offset="0x000f8" name="RBBM_CLOCK_CNTL_CCU0"/> - <reg32 offset="0x000f9" name="RBBM_CLOCK_CNTL_CCU1"/> - <reg32 offset="0x000fa" name="RBBM_CLOCK_CNTL_CCU2"/> - <reg32 offset="0x000fb" name="RBBM_CLOCK_CNTL_CCU3"/> - <reg32 offset="0x00100" name="RBBM_CLOCK_HYST_RB_CCU0"/> - <reg32 offset="0x00101" name="RBBM_CLOCK_HYST_RB_CCU1"/> - <reg32 offset="0x00102" name="RBBM_CLOCK_HYST_RB_CCU2"/> - <reg32 offset="0x00103" name="RBBM_CLOCK_HYST_RB_CCU3"/> - <reg32 offset="0x00104" name="RBBM_CLOCK_CNTL_RAC"/> - <reg32 offset="0x00105" name="RBBM_CLOCK_CNTL2_RAC"/> - <reg32 offset="0x00106" name="RBBM_CLOCK_DELAY_RAC"/> - <reg32 offset="0x00107" name="RBBM_CLOCK_HYST_RAC"/> - <reg32 offset="0x00108" name="RBBM_CLOCK_CNTL_TSE_RAS_RBBM"/> - <reg32 offset="0x00109" name="RBBM_CLOCK_DELAY_TSE_RAS_RBBM"/> - <reg32 offset="0x0010a" name="RBBM_CLOCK_HYST_TSE_RAS_RBBM"/> - <reg32 offset="0x0010b" name="RBBM_CLOCK_CNTL_UCHE"/> - <reg32 offset="0x0010c" name="RBBM_CLOCK_CNTL2_UCHE"/> - <reg32 offset="0x0010d" name="RBBM_CLOCK_CNTL3_UCHE"/> - <reg32 offset="0x0010e" name="RBBM_CLOCK_CNTL4_UCHE"/> - <reg32 offset="0x0010f" name="RBBM_CLOCK_DELAY_UCHE"/> - <reg32 offset="0x00110" name="RBBM_CLOCK_HYST_UCHE"/> - <reg32 offset="0x00111" name="RBBM_CLOCK_MODE_VFD"/> - <reg32 offset="0x00112" name="RBBM_CLOCK_DELAY_VFD"/> - <reg32 offset="0x00113" name="RBBM_CLOCK_HYST_VFD"/> - <reg32 offset="0x00114" name="RBBM_CLOCK_MODE_GPC"/> - <reg32 offset="0x00115" name="RBBM_CLOCK_DELAY_GPC"/> - <reg32 offset="0x00116" name="RBBM_CLOCK_HYST_GPC"/> - <reg32 offset="0x00117" name="RBBM_CLOCK_DELAY_HLSQ_2"/> - <reg32 offset="0x00118" name="RBBM_CLOCK_CNTL_GMU_GX"/> - <reg32 offset="0x00119" name="RBBM_CLOCK_DELAY_GMU_GX"/> - <reg32 offset="0x0011a" name="RBBM_CLOCK_HYST_GMU_GX"/> - <reg32 offset="0x0011b" name="RBBM_CLOCK_MODE_HLSQ"/> - <reg32 offset="0x0011c" name="RBBM_CLOCK_DELAY_HLSQ"/> - <reg32 offset="0x0011d" name="RBBM_CLOCK_HYST_HLSQ"/> - <reg32 offset="0x0011e" name="RBBM_CGC_GLOBAL_LOAD_CMD" variants="A7XX-"/> - <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="0x01a" name="RBBM_WAIT_IDLE_CLOCKS_CNTL" variants="A6XX-A7XX"/> + <reg32 offset="0x01b" name="RBBM_WAIT_IDLE_CLOCKS_CNTL2" variants="A6XX-A7XX"/> + <reg32 offset="0x010" name="RBBM_WAIT_IDLE_CLOCKS_CNTL" variants="A8XX-"/> + <reg32 offset="0x011" name="RBBM_WAIT_IDLE_CLOCKS_CNTL2" variants="A8XX-"/> + + <reg32 offset="0x0001f" name="RBBM_INTERFACE_HANG_INT_CNTL" variants="A6XX-A7XX"/> + <reg32 offset="0x0002f" name="RBBM_INTERFACE_HANG_INT_CNTL" variants="A8XX-"/> + <reg32 offset="0x00037" name="RBBM_INT_CLEAR_CMD" type="A6XX_RBBM_INT_0_MASK" variants="A6XX-A7XX"/> + <reg32 offset="0x00061" name="RBBM_INT_CLEAR_CMD" type="A6XX_RBBM_INT_0_MASK" variants="A8XX-"/> + <reg32 offset="0x00038" name="RBBM_INT_0_MASK" type="A6XX_RBBM_INT_0_MASK" variants="A6XX-A7XX"/> + <reg32 offset="0x00062" name="RBBM_INT_0_MASK" type="A6XX_RBBM_INT_0_MASK" variants="A8XX-"/> + <reg32 offset="0x0003a" name="RBBM_INT_2_MASK" variants="A7XX"/> + <reg32 offset="0x00064" name="RBBM_INT_2_MASK" variants="A8XX-"/> + <reg32 offset="0x00042" name="RBBM_SP_HYST_CNT" variants="A6XX-A7XX"/> + <reg32 offset="0x00043" name="RBBM_SW_RESET_CMD" variants="A6XX-A7XX"/> + <reg32 offset="0x00073" name="RBBM_SW_RESET_CMD" variants="A8XX-"/> + <reg32 offset="0x00044" name="RBBM_RAC_THRESHOLD_CNT" variants="A6XX-A7XX"/> + <reg32 offset="0x00029" name="RBBM_RAC_THRESHOLD_CNT" variants="A8XX-"/> + <reg32 offset="0x00045" name="RBBM_BLOCK_SW_RESET_CMD" variants="A6XX"/> + <reg32 offset="0x00046" name="RBBM_BLOCK_SW_RESET_CMD2" variants="A6XX"/> + <reg32 offset="0x000ad" name="RBBM_CLOCK_CNTL_GLOBAL" variants="A7XX"/> + <reg32 offset="0x0009a" name="RBBM_CLOCK_CNTL_GLOBAL" variants="A8XX-"/> + <reg32 offset="0x07d" name="RBBM_POWER_UP_RESET_SW_OVERRIDE" variants="A8XX-"/> + <reg32 offset="0x07e" name="RBBM_POWER_UP_RESET_SW_BV_OVERRIDE" variants="A8XX-"/> + <reg32 offset="0x000ae" name="RBBM_CLOCK_CNTL" variants="A6XX-A7XX"/> + <reg32 offset="0x000b0" name="RBBM_CLOCK_CNTL_SP0" variants="A6XX-A7XX"/> + <reg32 offset="0x000b1" name="RBBM_CLOCK_CNTL_SP1" variants="A6XX-A7XX"/> + <reg32 offset="0x000b2" name="RBBM_CLOCK_CNTL_SP2" variants="A6XX-A7XX"/> + <reg32 offset="0x000b3" name="RBBM_CLOCK_CNTL_SP3" variants="A6XX-A7XX"/> + <reg32 offset="0x000b4" name="RBBM_CLOCK_CNTL2_SP0" variants="A6XX-A7XX"/> + <reg32 offset="0x000b5" name="RBBM_CLOCK_CNTL2_SP1" variants="A6XX-A7XX"/> + <reg32 offset="0x000b6" name="RBBM_CLOCK_CNTL2_SP2" variants="A6XX-A7XX"/> + <reg32 offset="0x000b7" name="RBBM_CLOCK_CNTL2_SP3" variants="A6XX-A7XX"/> + <reg32 offset="0x000b8" name="RBBM_CLOCK_DELAY_SP0" variants="A6XX-A7XX"/> + <reg32 offset="0x000b9" name="RBBM_CLOCK_DELAY_SP1" variants="A6XX-A7XX"/> + <reg32 offset="0x000ba" name="RBBM_CLOCK_DELAY_SP2" variants="A6XX-A7XX"/> + <reg32 offset="0x000bb" name="RBBM_CLOCK_DELAY_SP3" variants="A6XX-A7XX"/> + <reg32 offset="0x000bc" name="RBBM_CLOCK_HYST_SP0" variants="A6XX-A7XX"/> + <reg32 offset="0x000bd" name="RBBM_CLOCK_HYST_SP1" variants="A6XX-A7XX"/> + <reg32 offset="0x000be" name="RBBM_CLOCK_HYST_SP2" variants="A6XX-A7XX"/> + <reg32 offset="0x000bf" name="RBBM_CLOCK_HYST_SP3" variants="A6XX-A7XX"/> + <reg32 offset="0x000c0" name="RBBM_CLOCK_CNTL_TP0" variants="A6XX-A7XX"/> + <reg32 offset="0x000c1" name="RBBM_CLOCK_CNTL_TP1" variants="A6XX-A7XX"/> + <reg32 offset="0x000c2" name="RBBM_CLOCK_CNTL_TP2" variants="A6XX-A7XX"/> + <reg32 offset="0x000c3" name="RBBM_CLOCK_CNTL_TP3" variants="A6XX-A7XX"/> + <reg32 offset="0x000c4" name="RBBM_CLOCK_CNTL2_TP0" variants="A6XX-A7XX"/> + <reg32 offset="0x000c5" name="RBBM_CLOCK_CNTL2_TP1" variants="A6XX-A7XX"/> + <reg32 offset="0x000c6" name="RBBM_CLOCK_CNTL2_TP2" variants="A6XX-A7XX"/> + <reg32 offset="0x000c7" name="RBBM_CLOCK_CNTL2_TP3" variants="A6XX-A7XX"/> + <reg32 offset="0x000c8" name="RBBM_CLOCK_CNTL3_TP0" variants="A6XX-A7XX"/> + <reg32 offset="0x000c9" name="RBBM_CLOCK_CNTL3_TP1" variants="A6XX-A7XX"/> + <reg32 offset="0x000ca" name="RBBM_CLOCK_CNTL3_TP2" variants="A6XX-A7XX"/> + <reg32 offset="0x000cb" name="RBBM_CLOCK_CNTL3_TP3" variants="A6XX-A7XX"/> + <reg32 offset="0x000cc" name="RBBM_CLOCK_CNTL4_TP0" variants="A6XX-A7XX"/> + <reg32 offset="0x000cd" name="RBBM_CLOCK_CNTL4_TP1" variants="A6XX-A7XX"/> + <reg32 offset="0x000ce" name="RBBM_CLOCK_CNTL4_TP2" variants="A6XX-A7XX"/> + <reg32 offset="0x000cf" name="RBBM_CLOCK_CNTL4_TP3" variants="A6XX-A7XX"/> + <reg32 offset="0x000d0" name="RBBM_CLOCK_DELAY_TP0" variants="A6XX-A7XX"/> + <reg32 offset="0x000d1" name="RBBM_CLOCK_DELAY_TP1" variants="A6XX-A7XX"/> + <reg32 offset="0x000d2" name="RBBM_CLOCK_DELAY_TP2" variants="A6XX-A7XX"/> + <reg32 offset="0x000d3" name="RBBM_CLOCK_DELAY_TP3" variants="A6XX-A7XX"/> + <reg32 offset="0x000d4" name="RBBM_CLOCK_DELAY2_TP0" variants="A6XX-A7XX"/> + <reg32 offset="0x000d5" name="RBBM_CLOCK_DELAY2_TP1" variants="A6XX-A7XX"/> + <reg32 offset="0x000d6" name="RBBM_CLOCK_DELAY2_TP2" variants="A6XX-A7XX"/> + <reg32 offset="0x000d7" name="RBBM_CLOCK_DELAY2_TP3" variants="A6XX-A7XX"/> + <reg32 offset="0x000d8" name="RBBM_CLOCK_DELAY3_TP0" variants="A6XX-A7XX"/> + <reg32 offset="0x000d9" name="RBBM_CLOCK_DELAY3_TP1" variants="A6XX-A7XX"/> + <reg32 offset="0x000da" name="RBBM_CLOCK_DELAY3_TP2" variants="A6XX-A7XX"/> + <reg32 offset="0x000db" name="RBBM_CLOCK_DELAY3_TP3" variants="A6XX-A7XX"/> + <reg32 offset="0x000dc" name="RBBM_CLOCK_DELAY4_TP0" variants="A6XX-A7XX"/> + <reg32 offset="0x000dd" name="RBBM_CLOCK_DELAY4_TP1" variants="A6XX-A7XX"/> + <reg32 offset="0x000de" name="RBBM_CLOCK_DELAY4_TP2" variants="A6XX-A7XX"/> + <reg32 offset="0x000df" name="RBBM_CLOCK_DELAY4_TP3" variants="A6XX-A7XX"/> + <reg32 offset="0x000e0" name="RBBM_CLOCK_HYST_TP0" variants="A6XX-A7XX"/> + <reg32 offset="0x000e1" name="RBBM_CLOCK_HYST_TP1" variants="A6XX-A7XX"/> + <reg32 offset="0x000e2" name="RBBM_CLOCK_HYST_TP2" variants="A6XX-A7XX"/> + <reg32 offset="0x000e3" name="RBBM_CLOCK_HYST_TP3" variants="A6XX-A7XX"/> + <reg32 offset="0x000e4" name="RBBM_CLOCK_HYST2_TP0" variants="A6XX-A7XX"/> + <reg32 offset="0x000e5" name="RBBM_CLOCK_HYST2_TP1" variants="A6XX-A7XX"/> + <reg32 offset="0x000e6" name="RBBM_CLOCK_HYST2_TP2" variants="A6XX-A7XX"/> + <reg32 offset="0x000e7" name="RBBM_CLOCK_HYST2_TP3" variants="A6XX-A7XX"/> + <reg32 offset="0x000e8" name="RBBM_CLOCK_HYST3_TP0" variants="A6XX-A7XX"/> + <reg32 offset="0x000e9" name="RBBM_CLOCK_HYST3_TP1" variants="A6XX-A7XX"/> + <reg32 offset="0x000ea" name="RBBM_CLOCK_HYST3_TP2" variants="A6XX-A7XX"/> + <reg32 offset="0x000eb" name="RBBM_CLOCK_HYST3_TP3" variants="A6XX-A7XX"/> + <reg32 offset="0x000ec" name="RBBM_CLOCK_HYST4_TP0" variants="A6XX-A7XX"/> + <reg32 offset="0x000ed" name="RBBM_CLOCK_HYST4_TP1" variants="A6XX-A7XX"/> + <reg32 offset="0x000ee" name="RBBM_CLOCK_HYST4_TP2" variants="A6XX-A7XX"/> + <reg32 offset="0x000ef" name="RBBM_CLOCK_HYST4_TP3" variants="A6XX-A7XX"/> + <reg32 offset="0x000f0" name="RBBM_CLOCK_CNTL_RB0" variants="A6XX-A7XX"/> + <reg32 offset="0x000f1" name="RBBM_CLOCK_CNTL_RB1" variants="A6XX-A7XX"/> + <reg32 offset="0x000f2" name="RBBM_CLOCK_CNTL_RB2" variants="A6XX-A7XX"/> + <reg32 offset="0x000f3" name="RBBM_CLOCK_CNTL_RB3" variants="A6XX-A7XX"/> + <reg32 offset="0x000f4" name="RBBM_CLOCK_CNTL2_RB0" variants="A6XX-A7XX"/> + <reg32 offset="0x000f5" name="RBBM_CLOCK_CNTL2_RB1" variants="A6XX-A7XX"/> + <reg32 offset="0x000f6" name="RBBM_CLOCK_CNTL2_RB2" variants="A6XX-A7XX"/> + <reg32 offset="0x000f7" name="RBBM_CLOCK_CNTL2_RB3" variants="A6XX-A7XX"/> + <reg32 offset="0x000f8" name="RBBM_CLOCK_CNTL_CCU0" variants="A6XX-A7XX"/> + <reg32 offset="0x000f9" name="RBBM_CLOCK_CNTL_CCU1" variants="A6XX-A7XX"/> + <reg32 offset="0x000fa" name="RBBM_CLOCK_CNTL_CCU2" variants="A6XX-A7XX"/> + <reg32 offset="0x000fb" name="RBBM_CLOCK_CNTL_CCU3" variants="A6XX-A7XX"/> + <reg32 offset="0x00100" name="RBBM_CLOCK_HYST_RB_CCU0" variants="A6XX-A7XX"/> + <reg32 offset="0x00101" name="RBBM_CLOCK_HYST_RB_CCU1" variants="A6XX-A7XX"/> + <reg32 offset="0x00102" name="RBBM_CLOCK_HYST_RB_CCU2" variants="A6XX-A7XX"/> + <reg32 offset="0x00103" name="RBBM_CLOCK_HYST_RB_CCU3" variants="A6XX-A7XX"/> + <reg32 offset="0x00104" name="RBBM_CLOCK_CNTL_RAC" variants="A6XX-A7XX"/> + <reg32 offset="0x00105" name="RBBM_CLOCK_CNTL2_RAC" variants="A6XX-A7XX"/> + <reg32 offset="0x00106" name="RBBM_CLOCK_DELAY_RAC" variants="A6XX-A7XX"/> + <reg32 offset="0x00107" name="RBBM_CLOCK_HYST_RAC" variants="A6XX-A7XX"/> + <reg32 offset="0x00108" name="RBBM_CLOCK_CNTL_TSE_RAS_RBBM" variants="A6XX-A7XX"/> + <reg32 offset="0x00109" name="RBBM_CLOCK_DELAY_TSE_RAS_RBBM" variants="A6XX-A7XX"/> + <reg32 offset="0x0010a" name="RBBM_CLOCK_HYST_TSE_RAS_RBBM" variants="A6XX-A7XX"/> + <reg32 offset="0x0010b" name="RBBM_CLOCK_CNTL_UCHE" variants="A6XX-A7XX"/> + <reg32 offset="0x0010c" name="RBBM_CLOCK_CNTL2_UCHE" variants="A6XX-A7XX"/> + <reg32 offset="0x0010d" name="RBBM_CLOCK_CNTL3_UCHE" variants="A6XX-A7XX"/> + <reg32 offset="0x0010e" name="RBBM_CLOCK_CNTL4_UCHE" variants="A6XX-A7XX"/> + <reg32 offset="0x0010f" name="RBBM_CLOCK_DELAY_UCHE" variants="A6XX-A7XX"/> + <reg32 offset="0x00110" name="RBBM_CLOCK_HYST_UCHE" variants="A6XX-A7XX"/> + <reg32 offset="0x00111" name="RBBM_CLOCK_MODE_VFD" variants="A6XX-A7XX"/> + <reg32 offset="0x00112" name="RBBM_CLOCK_DELAY_VFD" variants="A6XX-A7XX"/> + <reg32 offset="0x00113" name="RBBM_CLOCK_HYST_VFD" variants="A6XX-A7XX"/> + <reg32 offset="0x00114" name="RBBM_CLOCK_MODE_GPC" variants="A6XX-A7XX"/> + <reg32 offset="0x00115" name="RBBM_CLOCK_DELAY_GPC" variants="A6XX-A7XX"/> + <reg32 offset="0x00116" name="RBBM_CLOCK_HYST_GPC" variants="A6XX-A7XX"/> + <reg32 offset="0x00117" name="RBBM_CLOCK_DELAY_HLSQ_2" variants="A6XX-A7XX"/> + <reg32 offset="0x00118" name="RBBM_CLOCK_CNTL_GMU_GX" variants="A6XX-A7XX"/> + <reg32 offset="0x00119" name="RBBM_CLOCK_DELAY_GMU_GX" variants="A6XX-A7XX"/> + <reg32 offset="0x0011a" name="RBBM_CLOCK_HYST_GMU_GX" variants="A6XX-A7XX"/> + <reg32 offset="0x0011b" name="RBBM_CLOCK_MODE_HLSQ" variants="A6XX-A7XX"/> + <reg32 offset="0x0011c" name="RBBM_CLOCK_DELAY_HLSQ" variants="A6XX-A7XX"/> + <reg32 offset="0x0011d" name="RBBM_CLOCK_HYST_HLSQ" variants="A6XX-A7XX"/> + <reg32 offset="0x0011e" name="RBBM_CGC_GLOBAL_LOAD_CMD" variants="A7XX"/> + <reg32 offset="0x0009b" name="RBBM_CGC_GLOBAL_LOAD_CMD" variants="A8XX-"/> + <reg32 offset="0x0011f" name="RBBM_CGC_P2S_TRIG_CMD" variants="A7XX"/> + <reg32 offset="0x0009c" name="RBBM_CGC_P2S_TRIG_CMD" variants="A8XX-"/> + <reg32 offset="0x00120" name="RBBM_CGC_P2S_CNTL" variants="A7XX"/> + <reg32 offset="0x0009d" name="RBBM_CGC_P2S_CNTL" variants="A8XX-"/> + <reg32 offset="0x00120" name="RBBM_CLOCK_CNTL_TEX_FCHE" variants="A6XX"/> + <reg32 offset="0x00121" name="RBBM_CLOCK_DELAY_TEX_FCHE" variants="A6XX-A7XX"/> <reg32 offset="0x00122" name="RBBM_CLOCK_HYST_TEX_FCHE" variants="A6XX"/> - <reg32 offset="0x00122" name="RBBM_CGC_P2S_STATUS" variants="A7XX-"> + <reg32 offset="0x00122" name="RBBM_CGC_P2S_STATUS" variants="A7XX"> <bitfield name="TXDONE" pos="0" type="boolean"/> </reg32> - <reg32 offset="0x00123" name="RBBM_CLOCK_CNTL_FCHE"/> - <reg32 offset="0x00124" name="RBBM_CLOCK_DELAY_FCHE"/> - <reg32 offset="0x00125" name="RBBM_CLOCK_HYST_FCHE"/> - <reg32 offset="0x00126" name="RBBM_CLOCK_CNTL_MHUB"/> - <reg32 offset="0x00127" name="RBBM_CLOCK_DELAY_MHUB"/> - <reg32 offset="0x00128" name="RBBM_CLOCK_HYST_MHUB"/> - <reg32 offset="0x00129" name="RBBM_CLOCK_DELAY_GLC"/> - <reg32 offset="0x0012a" name="RBBM_CLOCK_HYST_GLC"/> - <reg32 offset="0x0012b" name="RBBM_CLOCK_CNTL_GLC"/> - <reg32 offset="0x0012f" name="RBBM_CLOCK_HYST2_VFD" variants="A7XX-"/> - <reg32 offset="0x005ff" name="RBBM_LPAC_GBIF_CLIENT_QOS_CNTL"/> + <reg32 offset="0x09f" name="RBBM_CGC_P2S_STATUS" variants="A8XX-"> + <bitfield name="TXDONE" pos="0" type="boolean"/> + </reg32> + <reg32 offset="0x00123" name="RBBM_CLOCK_CNTL_FCHE" variants="A6XX-A7XX"/> + <reg32 offset="0x00124" name="RBBM_CLOCK_DELAY_FCHE" variants="A6XX-A7XX"/> + <reg32 offset="0x00125" name="RBBM_CLOCK_HYST_FCHE" variants="A6XX-A7XX"/> + <reg32 offset="0x00126" name="RBBM_CLOCK_CNTL_MHUB" variants="A6XX-A7XX"/> + <reg32 offset="0x00127" name="RBBM_CLOCK_DELAY_MHUB" variants="A6XX-A7XX"/> + <reg32 offset="0x00128" name="RBBM_CLOCK_HYST_MHUB" variants="A6XX-A7XX"/> + <reg32 offset="0x00129" name="RBBM_CLOCK_DELAY_GLC" variants="A6XX-A7XX"/> + <reg32 offset="0x0012a" name="RBBM_CLOCK_HYST_GLC" variants="A6XX-A7XX"/> + <reg32 offset="0x0012b" name="RBBM_CLOCK_CNTL_GLC" variants="A6XX-A7XX"/> + <reg32 offset="0x0012f" name="RBBM_CLOCK_HYST2_VFD" variants="A7XX"/> + <reg32 offset="0x00195" name="RBBM_CGC_0_PC" variants="A7XX"/> + <reg32 offset="0x0010b" name="RBBM_CGC_0_PC" variants="A8XX-"/> + + <reg32 offset="0x005ff" name="RBBM_LPAC_GBIF_CLIENT_QOS_CNTL" variants="A6XX-A7XX"/> + <reg32 offset="0x00009" name="RBBM_LPAC_GBIF_CLIENT_QOS_CNTL" variants="A8XX-"/> <reg32 offset="0x0600" name="DBGC_CFG_DBGBUS_SEL_A"/> <reg32 offset="0x0601" name="DBGC_CFG_DBGBUS_SEL_B"/> @@ -610,6 +964,8 @@ by a particular renderpass/blit. <reg32 offset="0x0605" name="DBGC_CFG_DBGBUS_CNTLM"> <bitfield high="27" low="24" name="ENABLE"/> </reg32> + <reg32 offset="0x0606" name="DBGC_CFG_DBGBUS_OPL"/> + <reg32 offset="0x0607" name="DBGC_CFG_DBGBUS_OPE"/> <reg32 offset="0x0608" name="DBGC_CFG_DBGBUS_IVTL_0"/> <reg32 offset="0x0609" name="DBGC_CFG_DBGBUS_IVTL_1"/> <reg32 offset="0x060a" name="DBGC_CFG_DBGBUS_IVTL_2"/> @@ -638,72 +994,276 @@ by a particular renderpass/blit. <bitfield high="27" low="24" name="BYTEL14"/> <bitfield high="31" low="28" name="BYTEL15"/> </reg32> + <reg32 offset="0x0612" name="DBGC_CFG_DBGBUS_IVTE_0"/> + <reg32 offset="0x0613" name="DBGC_CFG_DBGBUS_IVTE_1"/> + <reg32 offset="0x0614" name="DBGC_CFG_DBGBUS_IVTE_2"/> + <reg32 offset="0x0615" name="DBGC_CFG_DBGBUS_IVTE_3"/> + <reg32 offset="0x0616" name="DBGC_CFG_DBGBUS_MASKE_0"/> + <reg32 offset="0x0617" name="DBGC_CFG_DBGBUS_MASKE_1"/> + <reg32 offset="0x0618" name="DBGC_CFG_DBGBUS_MASKE_2"/> + <reg32 offset="0x0619" name="DBGC_CFG_DBGBUS_MASKE_3"/> + <reg32 offset="0x061a" name="DBGC_CFG_DBGBUS_NIBBLEE"/> + <reg32 offset="0x061b" name="DBGC_CFG_DBGBUS_PTRC0"/> + <reg32 offset="0x061c" name="DBGC_CFG_DBGBUS_PTRC1"/> + <reg32 offset="0x061d" name="DBGC_CFG_DBGBUS_LOADREG"/> + <reg32 offset="0x061e" name="DBGC_CFG_DBGBUS_IDX"/> + <reg32 offset="0x061f" name="DBGC_CFG_DBGBUS_CLRC"/> + <reg32 offset="0x0620" name="DBGC_CFG_DBGBUS_LOADIVT"/> + <reg32 offset="0x0621" name="DBGC_VBIF_DBG_CNTL"/> + <reg32 offset="0x0622" name="DBGC_DBG_LO_HI_GPIO"/> + <reg32 offset="0x0623" name="DBGC_EXT_TRACE_BUS_CNTL"/> + <reg32 offset="0x0624" name="DBGC_READ_AHB_THROUGH_DBG"/> + <reg32 offset="0x0625" name="DBGC_CFG_DBGBUS_EVENT_LOGIC"/> + <reg32 offset="0x0626" name="DBGC_CFG_DBGBUS_OVER"/> + <reg32 offset="0x0627" name="DBGC_CFG_DBGBUS_COUNT0"/> + <reg32 offset="0x0628" name="DBGC_CFG_DBGBUS_COUNT1"/> + <reg32 offset="0x0629" name="DBGC_CFG_DBGBUS_COUNT2"/> + <reg32 offset="0x062a" name="DBGC_CFG_DBGBUS_COUNT3"/> + <reg32 offset="0x062b" name="DBGC_CFG_DBGBUS_COUNT4"/> + <reg32 offset="0x062c" name="DBGC_CFG_DBGBUS_COUNT5"/> + <reg32 offset="0x062d" name="DBGC_CFG_DBGBUS_TRACE_ADDR"/> + <reg32 offset="0x062e" name="DBGC_CFG_DBGBUS_TRACE_BUF0"/> <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" variants="A6XX"/> - <reg32 offset="0x0CD8" name="VSC_UNKNOWN_0CD8" variants="A7XX"> - <doc> - Set to true when binning, isn't changed afterwards - </doc> - <bitfield name="BINNING" pos="0" type="boolean"/> - </reg32> + <reg32 offset="0x0631" name="DBGC_CFG_DBGBUS_TRACE_BUF3"/> + <reg32 offset="0x0632" name="DBGC_CFG_DBGBUS_TRACE_BUF4"/> + <reg32 offset="0x0633" name="DBGC_CFG_DBGBUS_MISR0"/> + <reg32 offset="0x0634" name="DBGC_CFG_DBGBUS_MISR1"/> + <reg32 offset="0x0635" name="DBGC_EVT_CFG"/> + <reg32 offset="0x0636" name="DBGC_EVT_INTF_SEL_0"/> + <reg32 offset="0x0637" name="DBGC_EVT_INTF_SEL_1"/> + <reg32 offset="0x0638" name="DBGC_EVT_SLICE_CFG"/> + <reg32 offset="0x0639" name="DBGC_QDSS_TIMESTAMP_0"/> + <reg32 offset="0x063a" name="DBGC_QDSS_TIMESTAMP_1"/> + <reg32 offset="0x063b" name="DBGC_ECO_CNTL"/> + <reg32 offset="0x063c" name="DBGC_AHB_DBG_CNTL"/> + <reg32 offset="0x063d" name="DBGC_EVT_INTF_SEL_2"/> + <reg32 offset="0x0640" name="DBGC_CFG_DBGBUS_PONG_SEL_A"/> + <reg32 offset="0x0641" name="DBGC_CFG_DBGBUS_PONG_SEL_B"/> + <reg32 offset="0x0642" name="DBGC_CFG_DBGBUS_PONG_SEL_C"/> + <reg32 offset="0x0643" name="DBGC_CFG_DBGBUS_PONG_SEL_D"/> + <reg32 offset="0x0644" name="DBGC_CFG_DBGBUS_MISC_MODE"/> + <reg32 offset="0x0650" name="DBGC_EVT_INTF_SEL_3_0"/> + <reg32 offset="0x0651" name="DBGC_EVT_INTF_SEL_3_1"/> + <reg32 offset="0x0652" name="DBGC_EVT_INTF_SEL_3_2"/> + <reg32 offset="0x0653" name="DBGC_EVT_INTF_SEL_3_3"/> + <reg32 offset="0x0654" name="DBGC_EVT_INTF_SEL_3_4"/> + <reg32 offset="0x0655" name="DBGC_EVT_INTF_SEL_3_5"/> + <reg32 offset="0x0660" name="DBGC_TRACE_BUFFER_STATUS"/> + <reg32 offset="0x0661" name="DBGC_TRACE_BUFFER_CMD"/> + <reg32 offset="0x0662" name="DBGC_DBG_TRACE_BUFFER_RD_ADDR"/> + <reg32 offset="0x0663" name="DBGC_DBG_TRACE_BUFFER_RD_DATA"/> + <reg32 offset="0x0664" name="DBGC_TRACE_BUFFER_ATB_RD_STATUS"/> + <reg32 offset="0x0665" name="DBGC_SMMU_FAULT_BLOCK_HALT_CFG"/> + <reg32 offset="0x0666" name="DBGC_DBG_LOPC_SB_RD_ADDR"/> + <reg32 offset="0x0667" name="DBGC_DBG_LOPC_SB_RD_DATA"/> + <reg32 offset="0x0668" name="DBGC_DBG_LOPC_SB_WR_ADDR"/> + <reg32 offset="0x0669" name="DBGC_DBG_LOPC_SB_WR_DATA"/> + <reg32 offset="0x066a" name="DBGC_INTERRUPT_STATUS"/> + <reg64 offset="0x0680" name="DBGC_GBIF_DBG_BASE"/> + <reg32 offset="0x0682" name="DBGC_GBIF_DBG_BUFF_SIZE"/> + <reg32 offset="0x0683" name="DBGC_GBIF_DBG_CNTL"/> + <reg32 offset="0x0684" name="DBGC_GBIF_DBG_CMD"/> + <reg32 offset="0x0685" name="DBGC_GBIF_DBG_STATUS"/> + + <reg32 offset="0x0700" name="DBGC_SCOPE_PERF_COUNTER_CFG_US" variants="A8XX-"/> + <reg32 offset="0x0701" name="DBGC_CFG_PERF_TRIG_CLUSTER_FE_US" variants="A8XX-"/> + <reg32 offset="0x0702" name="DBGC_CFG_PERF_TRIG_CLUSTER_VPC_US" variants="A8XX-"/> + <reg32 offset="0x0703" name="DBGC_CFG_PERF_TRIG_CLUSTER_SP_VS_US" variants="A8XX-"/> + <reg32 offset="0x0704" name="DBGC_CFG_PERF_TRIG_CLUSTER_SP_PS_US" variants="A8XX-"/> + <reg32 offset="0x0707" name="DBGC_CFG_PERF_TRIG_CLUSTER_NONE_US" variants="A8XX-"/> + <reg32 offset="0x0708" name="DBGC_CFG_BV_PERF_TRIG_CLUSTER_FE_US" variants="A8XX-"/> + <reg32 offset="0x0709" name="DBGC_CFG_BV_PERF_TRIG_CLUSTER_VPC_US" variants="A8XX-"/> + <reg32 offset="0x070a" name="DBGC_CFG_BV_PERF_TRIG_CLUSTER_SP_VS_US" variants="A8XX-"/> + <reg32 offset="0x070f" name="DBGC_CFG_BV_PERF_TRIG_CLUSTER_NONE_US" variants="A8XX-"/> + <reg32 offset="0x0710" name="DBGC_CFG_PERF_COUNTER_SEL_FE_US" variants="A8XX-"/> + <reg32 offset="0x0711" name="DBGC_CFG_PERF_COUNTER_SEL_FE_US_1" variants="A8XX-"/> + <reg32 offset="0x0712" name="DBGC_CFG_PERF_COUNTER_SEL_FE_US_2" variants="A8XX-"/> + <reg32 offset="0x0713" name="DBGC_CFG_PERF_COUNTER_SEL_VPC_US" variants="A8XX-"/> + <reg32 offset="0x0714" name="DBGC_CFG_PERF_COUNTER_SEL_VPC_US_1" variants="A8XX-"/> + <reg32 offset="0x0715" name="DBGC_CFG_PERF_COUNTER_SEL_SP_VS_US" variants="A8XX-"/> + <reg32 offset="0x0716" name="DBGC_CFG_PERF_COUNTER_SEL_SP_PS_US" variants="A8XX-"/> + <reg32 offset="0x0720" name="DBGC_CFG_PERF_COUNTER_SEL_NONE_US" variants="A8XX-"/> + <reg32 offset="0x0721" name="DBGC_CFG_PERF_COUNTER_SEL_NONE_US_1" variants="A8XX-"/> + <reg32 offset="0x0722" name="DBGC_CFG_BV_PERF_COUNTER_SEL_FE_US" variants="A8XX-"/> + <reg32 offset="0x0723" name="DBGC_CFG_BV_PERF_COUNTER_SEL_FE_US_1" variants="A8XX-"/> + <reg32 offset="0x0724" name="DBGC_CFG_BV_PERF_COUNTER_SEL_FE_US_2" variants="A8XX-"/> + <reg32 offset="0x0730" name="DBGC_CFG_BV_PERF_COUNTER_SEL_VPC_US" variants="A8XX-"/> + <reg32 offset="0x0731" name="DBGC_CFG_BV_PERF_COUNTER_SEL_VPC_US_1" variants="A8XX-"/> + <reg32 offset="0x0732" name="DBGC_CFG_BV_PERF_COUNTER_SEL_SP_VS_US" variants="A8XX-"/> + <reg32 offset="0x0740" name="DBGC_CFG_BV_PERF_COUNTER_SEL_NONE_US" variants="A8XX-"/> + <reg32 offset="0x0742" name="DBGC_CFG_PERF_TIMESTAMP_TRIG_SEL_US" variants="A8XX-"/> + <reg32 offset="0x0743" name="DBGC_CFG_BV_PERF_TIMESTAMP_TRIG_SEL_US" variants="A8XX-"/> + <reg64 offset="0x0744" name="DBGC_CFG_GBIF_BR_PERF_CNTR_BASE" variants="A8XX-"/> + <reg32 offset="0x0746" name="DBGC_CFG_GBIF_BR_BUFFER_SIZE" variants="A8XX-"/> + <reg64 offset="0x0747" name="DBGC_CFG_GBIF_BV_PERF_CNTR_BASE" variants="A8XX-"/> + <reg32 offset="0x0749" name="DBGC_CFG_GBIF_BV_BUFFER_SIZE" variants="A8XX-"/> + <reg32 offset="0x074a" name="DBGC_CFG_GBIF_QOS_CTRL" variants="A8XX-"/> + <reg32 offset="0x0750" name="DBGC_GBIF_BR_PERF_CNTR_WRITE_POINTER" variants="A8XX-"/> + <reg32 offset="0x0751" name="DBGC_GBIF_BV_PERF_CNTR_WRITE_POINTER" variants="A8XX-"/> + <reg32 offset="0x0752" name="DBGC_PERF_COUNTER_FE_LOCAL_BATCH_ID" variants="A8XX-"/> + <reg32 offset="0x0753" name="DBGC_CFG_PERF_WAIT_IDLE_CLOCKS_CNTL" variants="A8XX-"/> + <reg32 offset="0x0754" name="DBGC_PERF_COUNTER_SCOPING_CMD_US" variants="A8XX-"/> + <reg32 offset="0x0755" name="DBGC_PERF_SKEW_BUFFER_INIT_CMD" variants="A8XX-"/> + <reg32 offset="0x0759" name="DBGC_LOPC_INTERRUPT_STATUS" variants="A8XX-"/> + <reg32 offset="0x075a" name="DBGC_LOPC_BUFFER_PTR_STATUS" variants="A8XX-"/> + <reg32 offset="0x075b" name="DBGC_PERF_SCOPING_STATUS" variants="A8XX-"/> + <reg32 offset="0x075c" name="DBGC_PERF_COUNTER_PKT_STATUS" variants="A8XX-"/> + <reg32 offset="0x0760" name="DBGC_GC_LIVE_MBX_PKT_STATUS" variants="A8XX-"/> + <reg32 offset="0x0761" name="DBGC_GC_ALW_MBX_PKT_STATUS" variants="A8XX-"/> + <reg32 offset="0x0762" name="DBGC_AO_CNTR_LO_STATUS" variants="A8XX-"/> + <reg32 offset="0x0763" name="DBGC_AO_CNTR_HI_STATUS" variants="A8XX-"/> + <reg32 offset="0x0770" name="DBGC_LOPC_GC_SB_DEPTH_STATUS" variants="A8XX-"/> + <reg32 offset="0x0780" name="DBGC_LPAC_SCOPE_PERF_COUNTER_CFG_US" variants="A8XX-"/> + <reg32 offset="0x0781" name="DBGC_CFG_PERF_TRIG_LPAC_US" variants="A8XX-"/> + <reg32 offset="0x0782" name="DBGC_CFG_PERF_COUNTER_SEL_LPAC_US" variants="A8XX-"/> + <reg32 offset="0x0783" name="DBGC_CFG_PERF_COUNTER_SEL_LPAC_US_1" variants="A8XX-"/> + <reg32 offset="0x0784" name="DBGC_CFG_PERF_COUNTER_SEL_LPAC_US_2" variants="A8XX-"/> + <reg32 offset="0x0785" name="DBGC_CFG_PERF_TIMESTAMP_TRIG_SEL_LPAC_US" variants="A8XX-"/> + <reg64 offset="0x0786" name="DBGC_CFG_GBIF_LPAC_PERF_CNTR_BASE" variants="A8XX-"/> + <reg32 offset="0x0788" name="DBGC_CFG_GBIF_LPAC_BUFFER_SIZE" variants="A8XX-"/> + <reg32 offset="0x0789" name="DBGC_GBIF_LPAC_PERF_CNTR_WRITE_POINTER" variants="A8XX-"/> + <reg32 offset="0x078a" name="DBGC_CFG_LPAC_PERF_WAIT_IDLE_CLOCKS_CNTL" variants="A8XX-"/> + <reg32 offset="0x078b" name="DBGC_LPAC_PERF_COUNTER_SCOPING_CMD_US" variants="A8XX-"/> + <reg32 offset="0x078c" name="DBGC_LPAC_MBX_PKT_STATUS" variants="A8XX-"/> + <reg32 offset="0x078d" name="DBGC_LPAC_PERF_SCOPING_STATUS" variants="A8XX-"/> + <reg32 offset="0x0790" name="DBGC_LOPC_LPAC_SB_DEPTH_STATUS" variants="A8XX-"/> + <reg32 offset="0x07a0" name="DBGC_SCOPE_PERF_COUNTER_CFG_S" variants="A8XX-"/> + <reg32 offset="0x07a1" name="DBGC_CFG_PERF_TRIG_CLUSTER_FE_S" variants="A8XX-"/> + <reg32 offset="0x07a2" name="DBGC_CFG_PERF_TRIG_CLUSTER_SP_VS" variants="A8XX-"/> + <reg32 offset="0x07a3" name="DBGC_CFG_PERF_TRIG_CLUSTER_VPC_VS" variants="A8XX-"/> + <reg32 offset="0x07a4" name="DBGC_CFG_PERF_TRIG_CLUSTER_GRAS" variants="A8XX-"/> + <reg32 offset="0x07a5" name="DBGC_CFG_PERF_TRIG_CLUSTER_SP_PS" variants="A8XX-"/> + <reg32 offset="0x07a6" name="DBGC_CFG_PERF_TRIG_CLUSTER_VPC_PS" variants="A8XX-"/> + <reg32 offset="0x07a7" name="DBGC_CFG_PERF_TRIG_CLUSTER_PS" variants="A8XX-"/> + <reg32 offset="0x07a8" name="DBGC_CFG_BV_PERF_TRIG_CLUSTER_FE_S" variants="A8XX-"/> + <reg32 offset="0x07a9" name="DBGC_CFG_BV_PERF_TRIG_CLUSTER_SP_VS" variants="A8XX-"/> + <reg32 offset="0x07aa" name="DBGC_CFG_BV_PERF_TRIG_CLUSTER_VPC_VS" variants="A8XX-"/> + <reg32 offset="0x07ab" name="DBGC_CFG_BV_PERF_TRIG_CLUSTER_GRAS" variants="A8XX-"/> + <reg32 offset="0x07ac" name="DBGC_CFG_BV_PERF_TRIG_CLUSTER_VPC_PS" variants="A8XX-"/> + <reg32 offset="0x07ad" name="DBGC_CFG_PERF_COUNTER_SEL_FE_S" variants="A8XX-"/> + <reg32 offset="0x07ae" name="DBGC_CFG_PERF_COUNTER_SEL_FE_S_1" variants="A8XX-"/> + <reg32 offset="0x07af" name="DBGC_CFG_PERF_COUNTER_SEL_FE_S_2" variants="A8XX-"/> + <reg32 offset="0x07b0" name="DBGC_CFG_PERF_COUNTER_SEL_FE_S_3" variants="A8XX-"/> + <reg32 offset="0x07b1" name="DBGC_CFG_PERF_COUNTER_SEL_SP_VS" variants="A8XX-"/> + <reg32 offset="0x07b2" name="DBGC_CFG_PERF_COUNTER_SEL_SP_VS_1" variants="A8XX-"/> + <reg32 offset="0x07b3" name="DBGC_CFG_PERF_COUNTER_SEL_SP_VS_2" variants="A8XX-"/> + <reg32 offset="0x07b4" name="DBGC_CFG_PERF_COUNTER_SEL_SP_VS_3" variants="A8XX-"/> + <reg32 offset="0x07b5" name="DBGC_CFG_PERF_COUNTER_SEL_VPC_VS" variants="A8XX-"/> + <reg32 offset="0x07b6" name="DBGC_CFG_PERF_COUNTER_SEL_VPC_VS_1" variants="A8XX-"/> + <reg32 offset="0x07b7" name="DBGC_CFG_PERF_COUNTER_SEL_GRAS" variants="A8XX-"/> + <reg32 offset="0x07b8" name="DBGC_CFG_PERF_COUNTER_SEL_GRAS_1" variants="A8XX-"/> + <reg32 offset="0x07b9" name="DBGC_CFG_PERF_COUNTER_SEL_GRAS_2" variants="A8XX-"/> + <reg32 offset="0x07ba" name="DBGC_CFG_PERF_COUNTER_SEL_SP_PS" variants="A8XX-"/> + <reg32 offset="0x07bb" name="DBGC_CFG_PERF_COUNTER_SEL_SP_PS_1" variants="A8XX-"/> + <reg32 offset="0x07bc" name="DBGC_CFG_PERF_COUNTER_SEL_SP_PS_2" variants="A8XX-"/> + <reg32 offset="0x07bd" name="DBGC_CFG_PERF_COUNTER_SEL_SP_PS_3" variants="A8XX-"/> + <reg32 offset="0x07be" name="DBGC_CFG_PERF_COUNTER_SEL_VPC_PS" variants="A8XX-"/> + <reg32 offset="0x07bf" name="DBGC_CFG_PERF_COUNTER_SEL_VPC_PS_1" variants="A8XX-"/> + <reg32 offset="0x07c0" name="DBGC_CFG_PERF_COUNTER_SEL_PS" variants="A8XX-"/> + <reg32 offset="0x07c1" name="DBGC_CFG_PERF_COUNTER_SEL_PS_1" variants="A8XX-"/> + <reg32 offset="0x07c2" name="DBGC_CFG_PERF_COUNTER_SEL_PS_2" variants="A8XX-"/> + <reg32 offset="0x07c3" name="DBGC_CFG_PERF_COUNTER_SEL_PS_3" variants="A8XX-"/> + <reg32 offset="0x07c4" name="DBGC_CFG_PERF_TIMESTAMP_TRIG_SEL_S" variants="A8XX-"/> + <reg32 offset="0x07c5" name="DBGC_CFG_BV_PERF_COUNTER_SEL_FE_S" variants="A8XX-"/> + <reg32 offset="0x07c6" name="DBGC_CFG_BV_PERF_COUNTER_SEL_FE_S_1" variants="A8XX-"/> + <reg32 offset="0x07c7" name="DBGC_CFG_BV_PERF_COUNTER_SEL_FE_S_2" variants="A8XX-"/> + <reg32 offset="0x07c8" name="DBGC_CFG_BV_PERF_COUNTER_SEL_FE_S_3" variants="A8XX-"/> + <reg32 offset="0x07c9" name="DBGC_CFG_BV_PERF_COUNTER_SEL_SP_VS" variants="A8XX-"/> + <reg32 offset="0x07ca" name="DBGC_CFG_BV_PERF_COUNTER_SEL_SP_VS_1" variants="A8XX-"/> + <reg32 offset="0x07cb" name="DBGC_CFG_BV_PERF_COUNTER_SEL_SP_VS_2" variants="A8XX-"/> + <reg32 offset="0x07cc" name="DBGC_CFG_BV_PERF_COUNTER_SEL_SP_VS_3" variants="A8XX-"/> + <reg32 offset="0x07cd" name="DBGC_CFG_BV_PERF_COUNTER_SEL_VPC_VS" variants="A8XX-"/> + <reg32 offset="0x07ce" name="DBGC_CFG_BV_PERF_COUNTER_SEL_VPC_VS_1" variants="A8XX-"/> + <reg32 offset="0x07cf" name="DBGC_CFG_BV_PERF_COUNTER_SEL_GRAS" variants="A8XX-"/> + <reg32 offset="0x07d0" name="DBGC_CFG_BV_PERF_COUNTER_SEL_GRAS_1" variants="A8XX-"/> + <reg32 offset="0x07d1" name="DBGC_CFG_BV_PERF_COUNTER_SEL_GRAS_2" variants="A8XX-"/> + <reg32 offset="0x07d2" name="DBGC_CFG_BV_PERF_COUNTER_SEL_VPC_PS" variants="A8XX-"/> + <reg32 offset="0x07d3" name="DBGC_CFG_BV_PERF_COUNTER_SEL_VPC_PS_1" variants="A8XX-"/> + <reg32 offset="0x07d4" name="DBGC_CFG_BV_PERF_TIMESTAMP_TRIG_SEL_S" variants="A8XX-"/> + <reg32 offset="0x07d5" name="DBGC_PERF_COUNTER_SCOPING_CMD_S" variants="A8XX-"/> + <reg32 offset="0x07e0" name="DBGC_LPAC_SCOPE_PERF_COUNTER_CFG_S" variants="A8XX-"/> + <reg32 offset="0x07e1" name="DBGC_CFG_PERF_TRIG_LPAC_S" variants="A8XX-"/> + <reg32 offset="0x07e2" name="DBGC_CFG_PERF_COUNTER_SEL_LPAC_S" variants="A8XX-"/> + <reg32 offset="0x07e3" name="DBGC_CFG_PERF_COUNTER_SEL_LPAC_S_1" variants="A8XX-"/> + <reg32 offset="0x07e4" name="DBGC_CFG_PERF_COUNTER_SEL_LPAC_S_2" variants="A8XX-"/> + <reg32 offset="0x07e5" name="DBGC_CFG_PERF_TIMESTAMP_TRIG_SEL_LPAC_S" variants="A8XX-"/> + <reg32 offset="0x07e6" name="DBGC_LPAC_PERF_COUNTER_SCOPING_CMD_S" variants="A8XX-"/> + + <array offset="0x0CD8" name="VSC_PERFCTR_VSC_SEL" stride="1" length="2"/> <reg32 offset="0xC800" name="HLSQ_DBG_AHB_READ_APERTURE"/> <reg32 offset="0xD000" name="HLSQ_DBG_READ_SEL"/> - <reg32 offset="0x0E00" name="UCHE_ADDR_MODE_CNTL" type="a5xx_address_mode"/> + <reg32 offset="0x0E00" name="UCHE_ADDR_MODE_CNTL" type="a5xx_address_mode" variants="A6XX"/> <reg32 offset="0x0E01" name="UCHE_MODE_CNTL"/> - <reg64 offset="0x0E05" name="UCHE_WRITE_RANGE_MAX"/> - <reg64 offset="0x0E07" name="UCHE_WRITE_THRU_BASE"/> - <reg64 offset="0x0E09" name="UCHE_TRAP_BASE"/> - <reg64 offset="0x0E0B" name="UCHE_GMEM_RANGE_MIN"/> - <reg64 offset="0x0E0D" name="UCHE_GMEM_RANGE_MAX"/> - <reg32 offset="0x0E17" name="UCHE_CACHE_WAYS" usage="cmd"/> + <reg64 offset="0x0E05" name="UCHE_WRITE_RANGE_MAX" variants="A6XX"/> + <reg64 offset="0x0E07" name="UCHE_WRITE_THRU_BASE" variants="A6XX-A7XX"/> + <reg64 offset="0x0E06" name="UCHE_WRITE_THRU_BASE" variants="A8XX-"/> + <reg64 offset="0x0E09" name="UCHE_TRAP_BASE" variants="A6XX-A7XX"/> + <reg64 offset="0x0E08" name="UCHE_TRAP_BASE" variants="A8XX-"/> + <reg64 offset="0x0E0B" name="UCHE_GMEM_RANGE_MIN" variants="A6XX-A7XX"/> + <reg64 offset="0x0E0D" name="UCHE_GMEM_RANGE_MAX" variants="A6XX-A7XX"/> + <reg32 offset="0x0e17" name="UCHE_CACHE_WAYS" variants="A6XX-A7XX" usage="init"/> + <reg32 offset="0x0e04" name="UCHE_CACHE_WAYS" variants="A8XX-"/> <reg32 offset="0x0E18" name="UCHE_FILTER_CNTL"/> - <reg32 offset="0x0E19" name="UCHE_CLIENT_PF" usage="cmd"> + <reg32 offset="0x0e19" name="UCHE_CLIENT_PF" variants="A6XX-A7XX" usage="init"> <bitfield high="7" low="0" name="PERFSEL"/> </reg32> - <array offset="0x0E1C" name="UCHE_PERFCTR_UCHE_SEL" stride="1" length="12"/> - <reg32 offset="0x0e3a" name="UCHE_GBIF_GX_CONFIG"/> - <reg32 offset="0x0e3c" name="UCHE_CMDQ_CONFIG"/> + <array offset="0x0e1c" name="UCHE_PERFCTR_UCHE_SEL" stride="1" length="12" variants="A6XX-A7XX"/> + <array offset="0x0e20" name="UCHE_PERFCTR_UCHE_SEL" stride="1" length="24" variants="A8XX-"/> + <reg32 offset="0x0e3a" name="UCHE_GBIF_GX_CONFIG" variants="A6XX-A7XX"/> + <reg32 offset="0x0e12" name="UCHE_GBIF_GX_CONFIG" variants="A8XX-"/> + <reg32 offset="0x0e3c" name="UCHE_CMDQ_CONFIG" variants="A6XX-A7XX"/> - <reg32 offset="0x3000" name="VBIF_VERSION"/> - <reg32 offset="0x3001" name="VBIF_CLKON"> + <reg32 offset="0x0f01" name="UCHE_CCHE_MODE_CNTL" variants="A8XX-"/> + <reg32 offset="0x0f02" name="UCHE_CCHE_CACHE_WAYS" variants="A8XX-"/> + <reg64 offset="0x0f04" name="UCHE_CCHE_WRITE_THRU_BASE" variants="A8XX-"/> + <reg64 offset="0x0f06" name="UCHE_CCHE_TRAP_BASE" variants="A8XX-"/> + <reg64 offset="0x0f08" name="UCHE_CCHE_GC_GMEM_RANGE_MIN" variants="A8XX-"/> + <reg64 offset="0x0f0a" name="UCHE_CCHE_LPAC_GMEM_RANGE_MIN" variants="A8XX-"/> + <reg32 offset="0x0f0c" name="UCHE_CCHE_HW_DBG_CNTL" variants="A8XX-"/> + + <!-- VBIF only existed on early a6xx, and was later replaced with GBIF --> + + <reg32 offset="0x3000" name="VBIF_VERSION" variants="A6XX"/> + <reg32 offset="0x3001" name="VBIF_CLKON" variants="A6XX"> <bitfield pos="1" name="FORCE_ON_TESTBUS" type="boolean"/> </reg32> - <reg32 offset="0x302A" name="VBIF_GATE_OFF_WRREQ_EN"/> - <reg32 offset="0x3080" name="VBIF_XIN_HALT_CTRL0"/> - <reg32 offset="0x3081" name="VBIF_XIN_HALT_CTRL1"/> - <reg32 offset="0x3084" name="VBIF_TEST_BUS_OUT_CTRL"/> - <reg32 offset="0x3085" name="VBIF_TEST_BUS1_CTRL0"/> - <reg32 offset="0x3086" name="VBIF_TEST_BUS1_CTRL1"> + <reg32 offset="0x302A" name="VBIF_GATE_OFF_WRREQ_EN" variants="A6XX"/> + <reg32 offset="0x3080" name="VBIF_XIN_HALT_CTRL0" variants="A6XX"/> + <reg32 offset="0x3081" name="VBIF_XIN_HALT_CTRL1" variants="A6XX"/> + <reg32 offset="0x3084" name="VBIF_TEST_BUS_OUT_CTRL" variants="A6XX"/> + <reg32 offset="0x3085" name="VBIF_TEST_BUS1_CTRL0" variants="A6XX"/> + <reg32 offset="0x3086" name="VBIF_TEST_BUS1_CTRL1" variants="A6XX"> <bitfield low="0" high="3" name="DATA_SEL"/> </reg32> - <reg32 offset="0x3087" name="VBIF_TEST_BUS2_CTRL0"/> - <reg32 offset="0x3088" name="VBIF_TEST_BUS2_CTRL1"> + <reg32 offset="0x3087" name="VBIF_TEST_BUS2_CTRL0" variants="A6XX"/> + <reg32 offset="0x3088" name="VBIF_TEST_BUS2_CTRL1" variants="A6XX"> <bitfield low="0" high="8" name="DATA_SEL"/> </reg32> - <reg32 offset="0x308c" name="VBIF_TEST_BUS_OUT"/> - <reg32 offset="0x30d0" name="VBIF_PERF_CNT_SEL0"/> - <reg32 offset="0x30d1" name="VBIF_PERF_CNT_SEL1"/> - <reg32 offset="0x30d2" name="VBIF_PERF_CNT_SEL2"/> - <reg32 offset="0x30d3" name="VBIF_PERF_CNT_SEL3"/> - <reg32 offset="0x30d8" name="VBIF_PERF_CNT_LOW0"/> - <reg32 offset="0x30d9" name="VBIF_PERF_CNT_LOW1"/> - <reg32 offset="0x30da" name="VBIF_PERF_CNT_LOW2"/> - <reg32 offset="0x30db" name="VBIF_PERF_CNT_LOW3"/> - <reg32 offset="0x30e0" name="VBIF_PERF_CNT_HIGH0"/> - <reg32 offset="0x30e1" name="VBIF_PERF_CNT_HIGH1"/> - <reg32 offset="0x30e2" name="VBIF_PERF_CNT_HIGH2"/> - <reg32 offset="0x30e3" name="VBIF_PERF_CNT_HIGH3"/> - <reg32 offset="0x3100" name="VBIF_PERF_PWR_CNT_EN0"/> - <reg32 offset="0x3101" name="VBIF_PERF_PWR_CNT_EN1"/> - <reg32 offset="0x3102" name="VBIF_PERF_PWR_CNT_EN2"/> - <reg32 offset="0x3110" name="VBIF_PERF_PWR_CNT_LOW0"/> - <reg32 offset="0x3111" name="VBIF_PERF_PWR_CNT_LOW1"/> - <reg32 offset="0x3112" name="VBIF_PERF_PWR_CNT_LOW2"/> - <reg32 offset="0x3118" name="VBIF_PERF_PWR_CNT_HIGH0"/> - <reg32 offset="0x3119" name="VBIF_PERF_PWR_CNT_HIGH1"/> - <reg32 offset="0x311a" name="VBIF_PERF_PWR_CNT_HIGH2"/> - + <reg32 offset="0x308c" name="VBIF_TEST_BUS_OUT" variants="A6XX"/> + <reg32 offset="0x30d0" name="VBIF_PERF_CNT_SEL0" variants="A6XX"/> + <reg32 offset="0x30d1" name="VBIF_PERF_CNT_SEL1" variants="A6XX"/> + <reg32 offset="0x30d2" name="VBIF_PERF_CNT_SEL2" variants="A6XX"/> + <reg32 offset="0x30d3" name="VBIF_PERF_CNT_SEL3" variants="A6XX"/> + <reg32 offset="0x30d8" name="VBIF_PERF_CNT_LOW0" variants="A6XX"/> + <reg32 offset="0x30d9" name="VBIF_PERF_CNT_LOW1" variants="A6XX"/> + <reg32 offset="0x30da" name="VBIF_PERF_CNT_LOW2" variants="A6XX"/> + <reg32 offset="0x30db" name="VBIF_PERF_CNT_LOW3" variants="A6XX"/> + <reg32 offset="0x30e0" name="VBIF_PERF_CNT_HIGH0" variants="A6XX"/> + <reg32 offset="0x30e1" name="VBIF_PERF_CNT_HIGH1" variants="A6XX"/> + <reg32 offset="0x30e2" name="VBIF_PERF_CNT_HIGH2" variants="A6XX"/> + <reg32 offset="0x30e3" name="VBIF_PERF_CNT_HIGH3" variants="A6XX"/> + <reg32 offset="0x3100" name="VBIF_PERF_PWR_CNT_EN0" variants="A6XX"/> + <reg32 offset="0x3101" name="VBIF_PERF_PWR_CNT_EN1" variants="A6XX"/> + <reg32 offset="0x3102" name="VBIF_PERF_PWR_CNT_EN2" variants="A6XX"/> + <reg32 offset="0x3110" name="VBIF_PERF_PWR_CNT_LOW0" variants="A6XX"/> + <reg32 offset="0x3111" name="VBIF_PERF_PWR_CNT_LOW1" variants="A6XX"/> + <reg32 offset="0x3112" name="VBIF_PERF_PWR_CNT_LOW2" variants="A6XX"/> + <reg32 offset="0x3118" name="VBIF_PERF_PWR_CNT_HIGH0" variants="A6XX"/> + <reg32 offset="0x3119" name="VBIF_PERF_PWR_CNT_HIGH1" variants="A6XX"/> + <reg32 offset="0x311a" name="VBIF_PERF_PWR_CNT_HIGH2" variants="A6XX"/> + + <reg32 offset="0x3c00" name="GBIF_CX_CONFIG" variants="A8XX-"/> <reg32 offset="0x3c01" name="GBIF_SCACHE_CNTL0"/> <reg32 offset="0x3c02" name="GBIF_SCACHE_CNTL1"/> <reg32 offset="0x3c03" name="GBIF_QSB_SIDE0"/> @@ -712,30 +1272,66 @@ by a particular renderpass/blit. <reg32 offset="0x3c06" name="GBIF_QSB_SIDE3"/> <reg32 offset="0x3c45" name="GBIF_HALT"/> <reg32 offset="0x3c46" name="GBIF_HALT_ACK"/> + <reg32 offset="0x3c49" name="GBIF_REINIT_ENABLE" variants="A8XX-"/> + <reg32 offset="0x3c4a" name="GBIF_REINIT_DONE" variants="A8XX-"/> <reg32 offset="0x3cc0" name="GBIF_PERF_PWR_CNT_EN"/> <reg32 offset="0x3cc1" name="GBIF_PERF_PWR_CNT_CLR"/> <reg32 offset="0x3cc2" name="GBIF_PERF_CNT_SEL"/> - <reg32 offset="0x3cc3" name="GBIF_PERF_PWR_CNT_SEL"/> - <reg32 offset="0x3cc4" name="GBIF_PERF_CNT_LOW0"/> - <reg32 offset="0x3cc5" name="GBIF_PERF_CNT_LOW1"/> - <reg32 offset="0x3cc6" name="GBIF_PERF_CNT_LOW2"/> - <reg32 offset="0x3cc7" name="GBIF_PERF_CNT_LOW3"/> - <reg32 offset="0x3cc8" name="GBIF_PERF_CNT_HIGH0"/> - <reg32 offset="0x3cc9" name="GBIF_PERF_CNT_HIGH1"/> - <reg32 offset="0x3cca" name="GBIF_PERF_CNT_HIGH2"/> - <reg32 offset="0x3ccb" name="GBIF_PERF_CNT_HIGH3"/> - <reg32 offset="0x3ccc" name="GBIF_PWR_CNT_LOW0"/> - <reg32 offset="0x3ccd" name="GBIF_PWR_CNT_LOW1"/> - <reg32 offset="0x3cce" name="GBIF_PWR_CNT_LOW2"/> - <reg32 offset="0x3ccf" name="GBIF_PWR_CNT_HIGH0"/> - <reg32 offset="0x3cd0" name="GBIF_PWR_CNT_HIGH1"/> - <reg32 offset="0x3cd1" name="GBIF_PWR_CNT_HIGH2"/> + <reg32 offset="0x3cc3" name="GBIF_PERF_CNT_SEL_1" variants="A8XX-"/> + + <reg32 offset="0x3cc3" name="GBIF_PERF_PWR_CNT_SEL" variants="A6XX-A7XX"/> + <reg32 offset="0x3cc4" name="GBIF_PERF_CNT_LOW0" variants="A6XX-A7XX"/> + <reg32 offset="0x3cc5" name="GBIF_PERF_CNT_LOW1" variants="A6XX-A7XX"/> + <reg32 offset="0x3cc6" name="GBIF_PERF_CNT_LOW2" variants="A6XX-A7XX"/> + <reg32 offset="0x3cc7" name="GBIF_PERF_CNT_LOW3" variants="A6XX-A7XX"/> + <reg32 offset="0x3cc8" name="GBIF_PERF_CNT_HIGH0" variants="A6XX-A7XX"/> + <reg32 offset="0x3cc9" name="GBIF_PERF_CNT_HIGH1" variants="A6XX-A7XX"/> + <reg32 offset="0x3cca" name="GBIF_PERF_CNT_HIGH2" variants="A6XX-A7XX"/> + <reg32 offset="0x3ccb" name="GBIF_PERF_CNT_HIGH3" variants="A6XX-A7XX"/> + <reg32 offset="0x3ccc" name="GBIF_PWR_CNT_LOW0" variants="A6XX-A7XX"/> + <reg32 offset="0x3ccd" name="GBIF_PWR_CNT_LOW1" variants="A6XX-A7XX"/> + <reg32 offset="0x3cce" name="GBIF_PWR_CNT_LOW2" variants="A6XX-A7XX"/> + <reg32 offset="0x3ccf" name="GBIF_PWR_CNT_HIGH0" variants="A6XX-A7XX"/> + <reg32 offset="0x3cd0" name="GBIF_PWR_CNT_HIGH1" variants="A6XX-A7XX"/> + <reg32 offset="0x3cd1" name="GBIF_PWR_CNT_HIGH2" variants="A6XX-A7XX"/> + + <reg32 offset="0x3cc4" name="GBIF_PWR_CNT_SEL" variants="A8XX"/> + <reg32 offset="0x3cc6" name="GBIF_PERF_CNT_LO_0" variants="A8XX"/> + <reg32 offset="0x3cc7" name="GBIF_PERF_CNT_HI_0" variants="A8XX"/> + <reg32 offset="0x3cc8" name="GBIF_PERF_CNT_LO_1" variants="A8XX"/> + <reg32 offset="0x3cc9" name="GBIF_PERF_CNT_HI_1" variants="A8XX"/> + <reg32 offset="0x3cca" name="GBIF_PERF_CNT_LO_2" variants="A8XX"/> + <reg32 offset="0x3ccb" name="GBIF_PERF_CNT_HI_2" variants="A8XX"/> + <reg32 offset="0x3ccc" name="GBIF_PERF_CNT_LO_3" variants="A8XX"/> + <reg32 offset="0x3ccd" name="GBIF_PERF_CNT_HI_3" variants="A8XX"/> + <reg32 offset="0x3cce" name="GBIF_PERF_CNT_LO_4" variants="A8XX"/> + <reg32 offset="0x3ccf" name="GBIF_PERF_CNT_HI_4" variants="A8XX"/> + <reg32 offset="0x3cd0" name="GBIF_PERF_CNT_LO_5" variants="A8XX"/> + <reg32 offset="0x3cd1" name="GBIF_PERF_CNT_HI_5" variants="A8XX"/> + <reg32 offset="0x3cd2" name="GBIF_PERF_CNT_LO_6" variants="A8XX"/> + <reg32 offset="0x3cd3" name="GBIF_PERF_CNT_HI_6" variants="A8XX"/> + <reg32 offset="0x3cd4" name="GBIF_PERF_CNT_LO_7" variants="A8XX"/> + <reg32 offset="0x3cd5" name="GBIF_PERF_CNT_HI_7" variants="A8XX"/> + <reg32 offset="0x3ce0" name="GBIF_PWR_CNT_LO_0" variants="A8XX"/> + <reg32 offset="0x3ce1" name="GBIF_PWR_CNT_LO_1" variants="A8XX"/> + <reg32 offset="0x3ce2" name="GBIF_PWR_CNT_LO_2" variants="A8XX"/> + <reg32 offset="0x3ce3" name="GBIF_PWR_CNT_HI_0" variants="A8XX"/> + <reg32 offset="0x3ce4" name="GBIF_PWR_CNT_HI_1" variants="A8XX"/> + <reg32 offset="0x3ce5" name="GBIF_PWR_CNT_HI_2" variants="A8XX"/> <reg32 offset="0x0c00" name="VSC_DBG_ECO_CNTL"/> - <reg32 offset="0x0c02" name="VSC_BIN_SIZE" usage="rp_blit"> - <bitfield name="WIDTH" low="0" high="7" shr="5" type="uint"/> - <bitfield name="HEIGHT" low="8" high="16" shr="4" type="uint"/> + <reg32 offset="0x0df0" name="VSC_KMD_DBG_ECO_CNTL" variants="A8XX-"/> + <reg32 offset="0x0c02" name="VSC_BIN_SIZE" usage="rp_blit" variants="A6XX-A7XX"> + <bitfield name="BINW" low="0" high="7" shr="5" type="uint"/> + <bitfield name="BINH" low="8" high="16" shr="4" type="uint"/> </reg32> + + <bitset name="a8xx_bin_size" inline="yes"> + <bitfield name="BINW" low="0" high="9" shr="5" type="uint"/> + <bitfield name="BINH" low="16" high="26" shr="4" type="uint"/> + </bitset> + + <reg32 offset="0x0c02" name="VSC_BIN_SIZE" type="a8xx_bin_size" usage="rp_blit" variants="A8XX"/> <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"/> @@ -803,10 +1399,14 @@ by a particular renderpass/blit. <reg32 offset="0x0d08" name="VSC_UNKNOWN_0D08" variants="A7XX-" usage="rp_blit"/> - <reg32 offset="0x0E10" name="UCHE_UNKNOWN_0E10" variants="A7XX-" usage="cmd"/> - <reg32 offset="0x0E11" name="UCHE_UNKNOWN_0E11" variants="A7XX-" usage="cmd"/> + <reg32 offset="0x0e10" name="UCHE_UNKNOWN_0E10" variants="A7XX" usage="init"/> + <reg32 offset="0x0e10" name="UCHE_VARB_IDLE_TIMEOUT" variants="A8XX-"/> + <reg32 offset="0x0e11" name="UCHE_UNKNOWN_0E11" variants="A7XX" usage="init"/> + <reg32 offset="0x0e11" name="UCHE_CLIENT_PF" variants="A8XX-"/> <!-- always 0x03200000 ? --> - <reg32 offset="0x0e12" name="UCHE_UNKNOWN_0E12" usage="cmd"/> + <reg32 offset="0x0e12" name="UCHE_UNKNOWN_0E12" variants="A6XX-A7XX" usage="init"/> + <reg32 offset="0x0e15" name="UCHE_DBG_ECO_CNTL_0" variants="A8XX-"/> + <reg32 offset="0x0e16" name="UCHE_HW_DBG_CNTL" variants="A8XX-"/> <!-- adreno_reg_xy has 15 bits per coordinate, but a6xx registers only have 14 --> <bitset name="a6xx_reg_xy" inline="yes"> @@ -829,6 +1429,7 @@ by a particular renderpass/blit. </bitset> <reg32 offset="0x8000" name="GRAS_CL_CNTL" type="a6xx_gras_cl_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x8200" name="GRAS_CL_CNTL" type="a6xx_gras_cl_cntl" variants="A8XX-" usage="rp_blit"/> <bitset name="a6xx_gras_xs_clip_cull_distance" inline="yes"> <bitfield name="CLIP_MASK" low="0" high="7"/> @@ -839,6 +1440,18 @@ by a particular renderpass/blit. <reg32 offset="0x8003" name="GRAS_CL_GS_CLIP_CULL_DISTANCE" type="a6xx_gras_xs_clip_cull_distance" usage="rp_blit" variants="A6XX-A7XX" /> <reg32 offset="0x8004" name="GRAS_CL_ARRAY_SIZE" low="0" high="10" type="uint" usage="rp_blit" variants="A6XX-A7XX" /> + <reg32 offset="0x8201" name="GRAS_CL_VS_CLIP_CULL_DISTANCE" type="a6xx_gras_xs_clip_cull_distance" usage="rp_blit" variants="A8XX" /> + <reg32 offset="0x8202" name="GRAS_CL_DS_CLIP_CULL_DISTANCE" type="a6xx_gras_xs_clip_cull_distance" usage="rp_blit" variants="A8XX" /> + <reg32 offset="0x8203" name="GRAS_CL_GS_CLIP_CULL_DISTANCE" type="a6xx_gras_xs_clip_cull_distance" usage="rp_blit" variants="A8XX" /> + <reg32 offset="0x8204" name="GRAS_CL_ARRAY_SIZE" low="0" high="10" type="uint" usage="rp_blit" variants="A8XX" /> + + <reg32 offset="0x8228" name="GRAS_UNKNOWN_8228" variants="A8XX-"/> + <reg32 offset="0x8229" name="GRAS_UNKNOWN_8229" variants="A8XX-"/> + <reg32 offset="0x822a" name="GRAS_UNKNOWN_822A" variants="A8XX-"/> + <reg32 offset="0x822b" name="GRAS_UNKNOWN_822B" variants="A8XX-"/> + <reg32 offset="0x822c" name="GRAS_UNKNOWN_822C" variants="A8XX-"/> + <reg32 offset="0x822d" name="GRAS_UNKNOWN_822D" variants="A8XX-"/> + <bitset name="a6xx_gras_cl_interp_cntl" inline="yes"> <!-- see also RB_INTERP_CNTL --> <bitfield name="IJ_PERSP_PIXEL" pos="0" type="boolean"/> @@ -853,6 +1466,7 @@ by a particular renderpass/blit. </bitset> <reg32 offset="0x8005" name="GRAS_CL_INTERP_CNTL" type="a6xx_gras_cl_interp_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x8080" name="GRAS_CL_INTERP_CNTL" type="a6xx_gras_cl_interp_cntl" variants="A8XX-" usage="rp_blit"/> <bitset name="a6xx_gras_cl_guardband_clip_adj" inline="true"> <bitfield name="HORZ" low="0" high="8" type="uint"/> @@ -860,9 +1474,7 @@ by a particular renderpass/blit. </bitset> <reg32 offset="0x8006" name="GRAS_CL_GUARDBAND_CLIP_ADJ" type="a6xx_gras_cl_guardband_clip_adj" variants="A6XX-A7XX" usage="rp_blit"/> - - <!-- Something connected to depth-stencil attachment size --> - <reg32 offset="0x8007" name="GRAS_UNKNOWN_8007" variants="A7XX-" usage="rp_blit"/> + <reg32 offset="0x8205" name="GRAS_CL_GUARDBAND_CLIP_ADJ" type="a6xx_gras_cl_guardband_clip_adj" variants="A8XX-" usage="rp_blit"/> <!-- the scale/offset is per view, with up to 6 views --> <bitset name="a6xx_gras_bin_foveat" inline="yes"> @@ -887,6 +1499,7 @@ by a particular renderpass/blit. </bitset> <reg32 offset="0x8008" name="GRAS_BIN_FOVEAT" type="a6xx_gras_bin_foveat" variants="A7XX" usage="cmd"/> + <reg32 offset="0x8206" name="GRAS_BIN_FOVEAT" type="a6xx_gras_bin_foveat" variants="A8XX-" usage="cmd"/> <reg32 offset="0x8009" name="GRAS_BIN_FOVEAT_OFFSET_0" variants="A7XX-" usage="cmd"> <bitfield name="XOFFSET_0" low="0" high="9" shr="2" type="uint"/> @@ -921,10 +1534,23 @@ by a particular renderpass/blit. <reg32 offset="5" name="ZSCALE" type="float"/> </array> + <array offset="0x82d0" name="GRAS_CL_VIEWPORT" stride="6" length="16" variants="A8XX-" usage="rp_blit"> + <reg32 offset="0" name="XOFFSET" type="float"/> + <reg32 offset="1" name="XSCALE" type="float"/> + <reg32 offset="2" name="YOFFSET" type="float"/> + <reg32 offset="3" name="YSCALE" type="float"/> + <reg32 offset="4" name="ZOFFSET" type="float"/> + <reg32 offset="5" name="ZSCALE" type="float"/> + </array> + <array offset="0x8070" name="GRAS_CL_VIEWPORT_ZCLAMP" stride="2" length="16" variants="A6XX-A7XX" usage="rp_blit"> <reg32 offset="0" name="MIN" type="float"/> <reg32 offset="1" name="MAX" type="float"/> </array> + <array offset="0x80c0" name="GRAS_CL_VIEWPORT_ZCLAMP" stride="2" length="16" variants="A8XX-" usage="rp_blit"> + <reg32 offset="0" name="MIN" type="float"/> + <reg32 offset="1" name="MAX" type="float"/> + </array> <bitset name="a6xx_gras_su_cntl" varset="chip"> <bitfield name="CULL_FRONT" pos="0" type="boolean"/> @@ -951,6 +1577,13 @@ by a particular renderpass/blit. <bitfield name="UNK20" low="20" high="22" variants="A6XX-A7XX"/> </bitset> <reg32 offset="0x8090" name="GRAS_SU_CNTL" type="a6xx_gras_su_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x8209" name="GRAS_SU_CNTL" type="a6xx_gras_su_cntl" variants="A8XX-" usage="rp_blit"/> + + <!-- Fields moved from GRAS_SU_CNTL on earlier gens: --> + <reg32 offset="0x820c" name="GRAS_SU_STEREO_CNTL" variants="A8XX-" usage="rp_blit"> + <bitfield name="RENDERTARGETINDEXINCR" pos="18" type="boolean"/> + <bitfield name="VIEWPORTINDEXINCR" pos="19" type="boolean"/> + </reg32> <bitset name="a6xx_gras_su_point_minmax" inline="yes"> <bitfield name="MIN" low="0" high="15" type="ufixed" radix="4"/> @@ -958,25 +1591,31 @@ by a particular renderpass/blit. </bitset> <reg32 offset="0x8091" name="GRAS_SU_POINT_MINMAX" type="a6xx_gras_su_point_minmax" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x820a" name="GRAS_SU_POINT_MINMAX" type="a6xx_gras_su_point_minmax" variants="A8XX-" usage="rp_blit"/> + <reg32 offset="0x8092" name="GRAS_SU_POINT_SIZE" low="0" high="15" type="fixed" radix="4" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x820b" name="GRAS_SU_POINT_SIZE" low="0" high="15" type="fixed" radix="4" variants="A8XX-" usage="rp_blit"/> <bitset name="a6xx_gras_su_depth_cntl" inline="yes"> <bitfield name="Z_TEST_ENABLE" pos="0" type="boolean"/> </bitset> <reg32 offset="0x8114" name="GRAS_SU_DEPTH_CNTL" variants="A6XX-A7XX" type="a6xx_gras_su_depth_cntl" usage="rp_blit"/> + <reg32 offset="0x8086" name="GRAS_SU_DEPTH_CNTL" variants="A8XX-" type="a6xx_gras_su_depth_cntl" usage="rp_blit"/> <bitset name="a6xx_gras_su_stencil_cntl" inline="yes"> <bitfield name="STENCIL_ENABLE" pos="0" type="boolean"/> </bitset> <reg32 offset="0x8115" name="GRAS_SU_STENCIL_CNTL" type="a6xx_gras_su_stencil_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x8087" name="GRAS_SU_STENCIL_CNTL" type="a6xx_gras_su_stencil_cntl" variants="A8XX-" usage="rp_blit"/> <bitset name="a6xx_gras_su_render_cntl" inline="yes"> <bitfield name="FS_DISABLE" pos="7" type="boolean"/> </bitset> <reg32 offset="0x8116" name="GRAS_SU_RENDER_CNTL" type="a6xx_gras_su_render_cntl" variants="A7XX" usage="rp_blit"/> + <reg32 offset="0x8088" name="GRAS_SU_RENDER_CNTL" type="a6xx_gras_su_render_cntl" variants="A8XX-" usage="rp_blit"/> <!-- 0x8093 invalid --> <bitset name="a6xx_depth_plane_cntl" inline="yes"> @@ -984,16 +1623,25 @@ by a particular renderpass/blit. </bitset> <reg32 offset="0x8094" name="GRAS_SU_DEPTH_PLANE_CNTL" type="a6xx_depth_plane_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x8089" name="GRAS_SU_DEPTH_PLANE_CNTL" type="a6xx_depth_plane_cntl" variants="A8XX-" usage="rp_blit"/> + <reg32 offset="0x8095" name="GRAS_SU_POLY_OFFSET_SCALE" type="float" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x808a" name="GRAS_SU_POLY_OFFSET_SCALE" type="float" variants="A8XX-" usage="rp_blit"/> + <reg32 offset="0x8096" name="GRAS_SU_POLY_OFFSET_OFFSET" type="float" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x808b" name="GRAS_SU_POLY_OFFSET_OFFSET" type="float" variants="A8XX-" usage="rp_blit"/> + <reg32 offset="0x8097" name="GRAS_SU_POLY_OFFSET_OFFSET_CLAMP" type="float" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x808c" name="GRAS_SU_POLY_OFFSET_OFFSET_CLAMP" type="float" variants="A8XX-" usage="rp_blit"/> + <bitset name="a6xx_depth_buffer_info" inline="yes"> <bitfield name="DEPTH_FORMAT" low="0" high="2" type="a6xx_depth_format"/> - <bitfield name="UNK3" pos="3"/> + <bitfield name="READ_ONLY" pos="3" type="boolean"/> </bitset> <!-- duplicates RB_DEPTH_BUFFER_INFO: --> <reg32 offset="0x8098" name="GRAS_SU_DEPTH_BUFFER_INFO" type="a6xx_depth_buffer_info" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x808d" name="GRAS_SU_DEPTH_BUFFER_INFO" type="a6xx_depth_buffer_info" variants="A8XX-" usage="rp_blit"/> <bitset name="a6xx_gras_su_conservative_ras_cntl" inline="yes"> <bitfield name="CONSERVATIVERASEN" pos="0" type="boolean"/> @@ -1008,6 +1656,7 @@ by a particular renderpass/blit. </bitset> <reg32 offset="0x8099" name="GRAS_SU_CONSERVATIVE_RAS_CNTL" type="a6xx_gras_su_conservative_ras_cntl" variants="A6XX-A7XX" usage="cmd"/> + <reg32 offset="0x820d" name="GRAS_SU_CONSERVATIVE_RAS_CNTL" type="a6xx_gras_su_conservative_ras_cntl" variants="A8XX-" usage="cmd"/> <reg32 offset="0x809a" name="GRAS_SU_PATH_RENDERING_CNTL"> <bitfield name="UNK0" pos="0" type="boolean"/> @@ -1022,10 +1671,16 @@ by a particular renderpass/blit. <reg32 offset="0x809c" name="GRAS_SU_GS_SIV_CNTL" type="a6xx_gras_us_xs_siv_cntl" variants="A6XX-A7XX" usage="rp_blit"/> <reg32 offset="0x809d" name="GRAS_SU_DS_SIV_CNTL" type="a6xx_gras_us_xs_siv_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x820e" name="GRAS_SU_VS_SIV_CNTL" type="a6xx_gras_us_xs_siv_cntl" variants="A8XX" usage="rp_blit"/> + <reg32 offset="0x820f" name="GRAS_SU_GS_SIV_CNTL" type="a6xx_gras_us_xs_siv_cntl" variants="A8XX" usage="rp_blit"/> + <reg32 offset="0x8210" name="GRAS_SU_DS_SIV_CNTL" type="a6xx_gras_us_xs_siv_cntl" variants="A8XX" usage="rp_blit"/> + <bitset name="a6xx_rast_cntl" inline="yes"> <bitfield name="MODE" low="0" high="1" type="a6xx_polygon_mode"/> </bitset> + <reg32 offset="0x8211" name="GRAS_RAST_CNTL" type="a6xx_rast_cntl" variants="A8XX-" usage="rp_blit"/> + <enum name="a6xx_sequenced_thread_dist"> <value value="0x0" name="DIST_SCREEN_COORD"/> <value value="0x1" name="DIST_ALL_TO_RB0"/> @@ -1073,7 +1728,6 @@ by a particular renderpass/blit. </enum> <bitset name="a6xx_gras_sc_cntl" inline="yes"> - <bitfield name="CCUSINGLECACHELINESIZE" low="0" high="2"/> <bitfield name="SINGLE_PRIM_MODE" low="3" high="4" type="a6xx_single_prim_mode"/> <bitfield name="RASTER_MODE" pos="5" type="a6xx_raster_mode"/> <bitfield name="RASTER_DIRECTION" low="6" high="7" type="a6xx_raster_direction"/> @@ -1084,7 +1738,10 @@ by a particular renderpass/blit. <bitfield name="EARLYVIZOUTEN" pos="12" type="boolean"/> </bitset> - <reg32 offset="0x80a0" name="GRAS_SC_CNTL" type="a6xx_gras_sc_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x80a0" name="GRAS_SC_CNTL" type="a6xx_gras_sc_cntl" variants="A6XX-A7XX" usage="rp_blit"> + <bitfield name="CCUSINGLECACHELINESIZE" low="0" high="2" variants="A6XX-A7XX"/> + </reg32> + <reg32 offset="0x8230" name="GRAS_SC_CNTL" type="a6xx_gras_sc_cntl" variants="A8XX-" usage="rp_blit"/> <enum name="a6xx_render_mode"> <value value="0x0" name="RENDERING_PASS"/> @@ -1123,6 +1780,28 @@ by a particular renderpass/blit. <reg32 offset="0x80a1" name="GRAS_SC_BIN_CNTL" type="a6xx_bin_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <!-- Common fields for RB_CNTL and GRAS_SC_BIN_CNTL --> + <bitset name="a8xx_bin_cntl" inline="yes"> + <bitfield name="BINW" low="0" high="9" shr="5" type="uint"/> + <bitfield name="BINH" low="16" high="26" shr="4" type="uint"/> + <bitfield name="RENDER_MODE" low="11" high="13" type="a6xx_render_mode"/> + <doc> + Allows draws that don't have GRAS_LRZ_CNTL.LRZ_WRITE but have + GRAS_LRZ_CNTL.ENABLE to contribute to LRZ during RENDERING pass. + In sysmem mode GRAS_LRZ_CNTL.LRZ_WRITE is not considered. + </doc> + <bitfield name="LRZ_FEEDBACK_ZMODE_MASK" low="28" high="30" type="a6xx_lrz_feedback_mask"/> + <doc>Disable LRZ feedback writes</doc> + <bitfield name="FORCE_LRZ_WRITE_DIS" pos="31" type="boolean"/> + </bitset> + + <reg32 offset="0x8231" name="GRAS_SC_BIN_CNTL" type="a8xx_bin_cntl" variants="A8XX-" usage="rp_blit"> + <bitfield name="CONS_VIS_IN_BINNING" pos="10" type="boolean"/> + <bitfield name="FORCE_BI_DIR_LRZ_DISABLE" pos="14" type="boolean"/> + <bitfield name="FORCE_LRZ_DIS" pos="15" type="boolean"/> + <bitfield name="BIN_VRS_DIS" pos="27" type="boolean"/> + </reg32> + <bitset name="a6xx_gras_sc_ras_msaa_cntl" inline="yes"> <bitfield name="SAMPLES" low="0" high="1" type="a3xx_msaa_samples"/> <bitfield name="UNK2" pos="2"/> @@ -1130,6 +1809,7 @@ by a particular renderpass/blit. </bitset> <reg32 offset="0x80a2" name="GRAS_SC_RAS_MSAA_CNTL" type="a6xx_gras_sc_ras_msaa_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x8232" name="GRAS_SC_RAS_MSAA_CNTL" type="a6xx_gras_sc_ras_msaa_cntl" variants="A8XX-" usage="rp_blit"/> <bitset name="a6xx_gras_sc_dest_msaa_cntl" inline="yes"> <bitfield name="SAMPLES" low="0" high="1" type="a3xx_msaa_samples"/> @@ -1137,6 +1817,7 @@ by a particular renderpass/blit. </bitset> <reg32 offset="0x80a3" name="GRAS_SC_DEST_MSAA_CNTL" type="a6xx_gras_sc_dest_msaa_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x8233" name="GRAS_SC_DEST_MSAA_CNTL" type="a6xx_gras_sc_dest_msaa_cntl" variants="A8XX-" usage="rp_blit"/> <bitset name="a6xx_msaa_sample_pos_cntl" inline="yes"> <bitfield name="UNK0" pos="0"/> @@ -1158,13 +1839,21 @@ by a particular renderpass/blit. <reg32 offset="0x80a5" name="GRAS_SC_PROGRAMMABLE_MSAA_POS_0" type="a6xx_programmable_msaa_pos" variants="A6XX-A7XX" usage="rp_blit"/> <reg32 offset="0x80a6" name="GRAS_SC_PROGRAMMABLE_MSAA_POS_1" type="a6xx_programmable_msaa_pos" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x8237" name="GRAS_SC_MSAA_SAMPLE_POS_CNTL" type="a6xx_msaa_sample_pos_cntl" variants="A8XX-" usage="rp_blit"/> + <reg32 offset="0x8238" name="GRAS_SC_PROGRAMMABLE_MSAA_POS_0" type="a6xx_programmable_msaa_pos" variants="A8XX-" usage="rp_blit"/> + <reg32 offset="0x8239" name="GRAS_SC_PROGRAMMABLE_MSAA_POS_1" type="a6xx_programmable_msaa_pos" variants="A8XX-" usage="rp_blit"/> + <reg32 offset="0x823a" name="GRAS_SC_PROGRAMMABLE_MSAA_POS_2" type="a6xx_programmable_msaa_pos" variants="A8XX-" usage="rp_blit"/> + <reg32 offset="0x823b" name="GRAS_SC_PROGRAMMABLE_MSAA_POS_3" type="a6xx_programmable_msaa_pos" variants="A8XX-" usage="rp_blit"/> + <reg32 offset="0x80a7" name="GRAS_ROTATION_CNTL" variants="A7XX" usage="cmd"/> + <reg32 offset="0x8207" name="GRAS_ROTATION_CNTL" variants="A8XX-" usage="cmd"/> <bitset name="a6xx_screen_scissor_cntl" inline="yes"> <bitfield name="SCISSOR_DISABLE" pos="0" type="boolean"/> </bitset> <reg32 offset="0x80af" name="GRAS_SC_SCREEN_SCISSOR_CNTL" type="a6xx_screen_scissor_cntl" variants="A6XX-A7XX" pos="0" usage="cmd"/> + <reg32 offset="0x8234" name="GRAS_SC_SCREEN_SCISSOR_CNTL" type="a6xx_screen_scissor_cntl" variants="A8XX-" pos="0" usage="cmd"/> <bitset name="a6xx_scissor_xy" inline="yes"> <bitfield name="X" low="0" high="15" type="uint"/> @@ -1176,14 +1865,26 @@ by a particular renderpass/blit. <reg32 offset="1" name="BR" type="a6xx_scissor_xy"/> </array> + <array offset="0x8240" name="GRAS_SC_SCREEN_SCISSOR" stride="2" length="16" variants="A8XX-" usage="rp_blit"> + <reg32 offset="0" name="TL" type="a6xx_scissor_xy"/> + <reg32 offset="1" name="BR" type="a6xx_scissor_xy"/> + </array> + <array offset="0x80d0" name="GRAS_SC_VIEWPORT_SCISSOR" stride="2" length="16" variants="A6XX-A7XX" usage="rp_blit"> <reg32 offset="0" name="TL" type="a6xx_scissor_xy"/> <reg32 offset="1" name="BR" type="a6xx_scissor_xy"/> </array> + <array offset="0x8270" name="GRAS_SC_VIEWPORT_SCISSOR" stride="2" length="16" variants="A8XX-" usage="rp_blit"> + <reg32 offset="0" name="TL" type="a6xx_scissor_xy"/> + <reg32 offset="1" name="BR" type="a6xx_scissor_xy"/> + </array> <reg32 offset="0x80f0" name="GRAS_SC_WINDOW_SCISSOR_TL" type="a6xx_reg_xy" variants="A6XX-A7XX" usage="rp_blit"/> <reg32 offset="0x80f1" name="GRAS_SC_WINDOW_SCISSOR_BR" type="a6xx_reg_xy" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x8235" name="GRAS_SC_WINDOW_SCISSOR_TL" type="a6xx_reg_xy" variants="A8XX-" usage="rp_blit"/> + <reg32 offset="0x8236" name="GRAS_SC_WINDOW_SCISSOR_BR" type="a6xx_reg_xy" variants="A8XX-" usage="rp_blit"/> + <enum name="a6xx_fsr_combiner"> <value value="0" name="FSR_COMBINER_OP_KEEP"/> <value value="1" name="FSR_COMBINER_OP_REPLACE"/> @@ -1203,6 +1904,7 @@ by a particular renderpass/blit. </bitset> <reg32 offset="0x80f4" name="GRAS_VRS_CONFIG" type="a6xx_gras_vrs_config" variants="A7XX" usage="rp_blit"/> + <reg32 offset="0x8208" name="GRAS_VRS_CONFIG" type="a6xx_gras_vrs_config" variants="A8XX-" usage="rp_blit"/> <bitset name="a6xx_gras_quality_buffer_info" inline="yes"> <bitfield name="LAYERED" pos="0" type="boolean"/> @@ -1210,6 +1912,7 @@ by a particular renderpass/blit. </bitset> <reg32 offset="0x80f5" name="GRAS_QUALITY_BUFFER_INFO" type="a6xx_gras_quality_buffer_info" variants="A7XX" usage="rp_blit"/> + <reg32 offset="0x808e" name="GRAS_QUALITY_BUFFER_INFO" type="a6xx_gras_quality_buffer_info" variants="A8XX-" usage="rp_blit"/> <bitset name="a6xx_gras_quality_buffer_dimension" inline="yes"> <bitfield name="WIDTH" low="0" high="15" type="uint"/> @@ -1217,8 +1920,10 @@ by a particular renderpass/blit. </bitset> <reg32 offset="0x80f6" name="GRAS_QUALITY_BUFFER_DIMENSION" type="a6xx_gras_quality_buffer_dimension" variants="A7XX" usage="rp_blit"/> + <reg32 offset="0x808f" name="GRAS_QUALITY_BUFFER_DIMENSION" type="a6xx_gras_quality_buffer_dimension" variants="A8XX-" usage="rp_blit"/> <reg64 offset="0x80f8" name="GRAS_QUALITY_BUFFER_BASE" variants="A7XX" type="waddress" usage="rp_blit"/> + <reg64 offset="0x8090" name="GRAS_QUALITY_BUFFER_BASE" variants="A8XX-" type="waddress" usage="rp_blit"/> <bitset name="a6xx_gras_quality_buffer_pitch" inline="yes"> <bitfield name="PITCH" shr="6" low="0" high="7" type="uint"/> @@ -1226,6 +1931,7 @@ by a particular renderpass/blit. </bitset> <reg32 offset="0x80fa" name="GRAS_QUALITY_BUFFER_PITCH" type="a6xx_gras_quality_buffer_pitch" variants="A7XX" usage="rp_blit"/> + <reg32 offset="0x8092" name="GRAS_QUALITY_BUFFER_PITCH" type="a6xx_gras_quality_buffer_pitch" variants="A8XX-" usage="rp_blit"/> <enum name="a6xx_lrz_dir_status"> <value value="0x1" name="LRZ_DIR_LE"/> @@ -1244,7 +1950,6 @@ by a particular renderpass/blit. - 0.0 if GREATER - 1.0 if LESS </doc> - <bitfield name="FC_ENABLE" pos="3" type="boolean" variants="A6XX"/> <!-- set when depth-test + depth-write enabled --> <bitfield name="Z_WRITE_ENABLE" pos="4" type="boolean"/> <bitfield name="Z_BOUNDS_ENABLE" pos="5" type="boolean"/> @@ -1258,11 +1963,27 @@ by a particular renderpass/blit. Disable LRZ based on previous direction and the current one. If DIR_WRITE is not enabled - there is no write to direction buffer. </doc> - <bitfield name="DISABLE_ON_WRONG_DIR" pos="9" type="boolean" variants="A6XX"/> <bitfield name="Z_FUNC" low="11" high="13" type="adreno_compare_func" variants="A7XX-"/> </bitset> - <reg32 offset="0x8100" name="GRAS_LRZ_CNTL" type="a6xx_gras_lrz_cntl" usage="rp_blit" variants="A6XX-A7XX"/> + <reg32 offset="0x8100" name="GRAS_LRZ_CNTL" type="a6xx_gras_lrz_cntl" usage="rp_blit" variants="A6XX"> + <bitfield name="FC_ENABLE" pos="3" type="boolean" variants="A6XX"/> + <bitfield name="DISABLE_ON_WRONG_DIR" pos="9" type="boolean" variants="A6XX"/> + </reg32> + <reg32 offset="0x8100" name="GRAS_LRZ_CNTL" type="a6xx_gras_lrz_cntl" usage="rp_blit" variants="A7XX"/> + <reg32 offset="0x8212" name="GRAS_LRZ_CNTL" type="a6xx_gras_lrz_cntl" usage="rp_blit" variants="A8XX-"/> + + <reg32 offset="0x8007" name="GRAS_LRZ_CB_CNTL" variants="A7XX" usage="rp_blit"> + <doc> + The total size of the LRZ image array (not including + fast clear buffer), used as a stride for double + buffering used with concurrent binning. + </doc> + <bitfield name="DOUBLE_BUFFER_STRIDE" low="8" high="31" shr="8"/> + </reg32> + <reg32 offset="0x8101" name="GRAS_LRZ_CB_CNTL" usage="rp_blit" variants="A8XX-"> + <bitfield name="DOUBLE_BUFFER_PITCH" low="8" high="31" shr="8"/> + </reg32> <enum name="a6xx_fragcoord_sample_mode"> <value value="0" name="FRAGCOORD_CENTER"/> @@ -1275,14 +1996,17 @@ by a particular renderpass/blit. </bitset> <reg32 offset="0x8101" name="GRAS_LRZ_PS_INPUT_CNTL" type="a6xx_gras_lrz_ps_input_cntl" usage="rp_blit" variants="A6XX-A7XX"/> + <reg32 offset="0x8102" name="GRAS_LRZ_PS_INPUT_CNTL" type="a6xx_gras_lrz_ps_input_cntl" usage="rp_blit" variants="A8XX-"/> <bitset name="a6xx_gras_lrz_mrt_buffer_info_0" inline="yes"> <bitfield name="COLOR_FORMAT" low="0" high="7" type="a6xx_format"/> </bitset> <reg32 offset="0x8102" name="GRAS_LRZ_MRT_BUFFER_INFO_0" type="a6xx_gras_lrz_mrt_buffer_info_0" usage="rp_blit" variants="A6XX-A7XX"/> + <reg32 offset="0x8103" name="GRAS_LRZ_MRT_BUFFER_INFO_0" type="a6xx_gras_lrz_mrt_buffer_info_0" usage="rp_blit" variants="A8XX-"/> <reg64 offset="0x8103" name="GRAS_LRZ_BUFFER_BASE" align="256" type="waddress" usage="rp_blit" variants="A6XX-A7XX"/> + <reg64 offset="0x8104" name="GRAS_LRZ_BUFFER_BASE" align="256" type="waddress" usage="rp_blit" variants="A8XX-"/> <bitset name="a6xx_gras_lrz_buffer_pitch" inline="yes"> <bitfield name="PITCH" low="0" high="7" shr="5" type="uint"/> @@ -1290,6 +2014,9 @@ by a particular renderpass/blit. </bitset> <reg32 offset="0x8105" name="GRAS_LRZ_BUFFER_PITCH" type="a6xx_gras_lrz_buffer_pitch" usage="rp_blit" variants="A6XX-A7XX"/> + <reg32 offset="0x8108" name="GRAS_LRZ_BUFFER_PITCH" type="a6xx_gras_lrz_buffer_pitch" usage="rp_blit" variants="A8XX-"/> + + <reg32 offset="0x810e" name="GRAS_LRZ_BUFFER_STRIDE" usage="rp_blit" low="0" high="16" shr="12" variants="A8XX-"/> <!-- The LRZ "fast clear" buffer is initialized to zero's by blob, and @@ -1346,22 +2073,32 @@ by a particular renderpass/blit. <!-- 0x810c-0x810f invalid --> + <reg32 offset="0x8110" name="GRAS_LRZ_BUFFER_SLICE_PITCH" low="0" high="31" shr="8" type="uint" variants="A8XX-"/> + <reg32 offset="0x8110" name="GRAS_MODE_CNTL" low="0" high="1" variants="A6XX-A7XX" usage="cmd"/> + <reg32 offset="0x8213" name="GRAS_MODE_CNTL" low="0" high="1" variants="A8XX-" usage="cmd"/> <!-- A bit tentative but it's a color and it is followed by LRZ_CLEAR --> <reg32 offset="0x8111" name="GRAS_LRZ_DEPTH_CLEAR" type="float" variants="A7XX"/> + <reg32 offset="0x810d" name="GRAS_LRZ_DEPTH_CLEAR" type="float" variants="A8XX-"/> - <bitset name="a6xx_gras_lrz_depth_buffer_info" inline="yes"> - <bitfield name="DEPTH_FORMAT" low="0" high="2" type="a6xx_depth_format"/> - <bitfield name="UNK3" pos="3"/> - </bitset> - - <reg32 offset="0x8113" name="GRAS_LRZ_DEPTH_BUFFER_INFO" type="a6xx_gras_lrz_depth_buffer_info" variants="A7XX" usage="rp_blit"/> + <reg32 offset="0x8113" name="GRAS_LRZ_DEPTH_BUFFER_INFO" type="a6xx_depth_buffer_info" variants="A7XX" usage="rp_blit"/> + <reg32 offset="0x810f" name="GRAS_LRZ_DEPTH_BUFFER_INFO" type="a6xx_depth_buffer_info" variants="A8XX" usage="rp_blit"/> <doc>LUT used to convert quality buffer values to HW shading rate values. An array of 4-bit values.</doc> - <array offset="0x8120" name="GRAS_LRZ_QUALITY_LOOKUP_TABLE" variants="A7XX-" stride="1" length="2"/> + <array offset="0x8120" name="GRAS_LRZ_QUALITY_LOOKUP_TABLE" variants="A7XX" stride="1" length="2"/> + <array offset="0x8130" name="GRAS_LRZ_QUALITY_LOOKUP_TABLE" variants="A8XX-" stride="1" length="2"/> - <!-- 0x8112-0x83ff invalid --> + <reg32 offset="0x810c" name="GRAS_LRZ_COLOR_COMP_MASK" variants="A8XX-"> + <bitfield name="MRT0" low="0" high="3"/> + <bitfield name="MRT1" low="4" high="7"/> + <bitfield name="MRT2" low="8" high="11"/> + <bitfield name="MRT3" low="12" high="15"/> + <bitfield name="MRT4" low="16" high="19"/> + <bitfield name="MRT5" low="20" high="23"/> + <bitfield name="MRT6" low="24" high="27"/> + <bitfield name="MRT7" low="28" high="31"/> + </reg32> <enum name="a6xx_rotation"> <value value="0x0" name="ROTATE_0"/> @@ -1372,7 +2109,7 @@ by a particular renderpass/blit. <value value="0x5" name="ROTATE_VFLIP"/> </enum> - <bitset name="a6xx_a2d_bit_cntl" inline="yes"> + <bitset name="a6xx_a2d_blt_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"/> @@ -1391,7 +2128,7 @@ by a particular renderpass/blit. <bitfield name="COPY" pos="30" type="boolean" variants="A7XX-"/> </bitset> - <reg32 offset="0x8400" name="GRAS_A2D_BLT_CNTL" type="a6xx_a2d_bit_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x8400" name="GRAS_A2D_BLT_CNTL" type="a6xx_a2d_blt_cntl" variants="A6XX-A7XX" 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? @@ -1408,16 +2145,35 @@ by a particular renderpass/blit. <reg32 offset="0x840a" name="GRAS_A2D_SCISSOR_TL" type="a6xx_reg_xy" variants="A6XX-A7XX" usage="rp_blit"/> <reg32 offset="0x840b" name="GRAS_A2D_SCISSOR_BR" type="a6xx_reg_xy" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x8500" name="GRAS_A2D_BLT_CNTL" type="a6xx_a2d_blt_cntl" variants="A8XX-" usage="rp_blit"/> + <reg32 offset="0x8501" name="GRAS_A2D_SRC_XMIN" low="8" high="24" type="int" variants="A8XX-" usage="rp_blit"/> + <reg32 offset="0x8502" name="GRAS_A2D_SRC_XMAX" low="8" high="24" type="int" variants="A8XX-" usage="rp_blit"/> + <reg32 offset="0x8503" name="GRAS_A2D_SRC_YMIN" low="8" high="24" type="int" variants="A8XX-" usage="rp_blit"/> + <reg32 offset="0x8504" name="GRAS_A2D_SRC_YMAX" low="8" high="24" type="int" variants="A8XX-" usage="rp_blit"/> + <reg32 offset="0x8505" name="GRAS_A2D_DEST_TL" type="a6xx_reg_xy" variants="A8XX-" usage="rp_blit"/> + <reg32 offset="0x8506" name="GRAS_A2D_DEST_BR" type="a6xx_reg_xy" variants="A8XX-" usage="rp_blit"/> + <reg32 offset="0x8507" name="GRAS_A2D_SCISSOR_TL" type="a6xx_reg_xy" variants="A8XX-" usage="rp_blit"/> + <reg32 offset="0x8508" name="GRAS_A2D_SCISSOR_BR" type="a6xx_reg_xy" variants="A8XX-" usage="rp_blit"/> + <!-- always 0x880 ? (and 0 in a640/a650 traces?) --> - <reg32 offset="0x8600" name="GRAS_DBG_ECO_CNTL" usage="cmd"> + <reg32 offset="0x8600" name="GRAS_DBG_ECO_CNTL" usage="init" variants="A6XX-A7XX"> <bitfield name="UNK7" pos="7" type="boolean"/> <bitfield name="LRZCACHELOCKDIS" pos="11" type="boolean"/> </reg32> - <reg32 offset="0x8601" name="GRAS_ADDR_MODE_CNTL" pos="0" type="a5xx_address_mode"/> - <reg32 offset="0x8602" name="GRAS_NC_MODE_CNTL" variants="A7XX-"/> - <array offset="0x8610" name="GRAS_PERFCTR_TSE_SEL" stride="1" length="4"/> - <array offset="0x8614" name="GRAS_PERFCTR_RAS_SEL" stride="1" length="4"/> - <array offset="0x8618" name="GRAS_PERFCTR_LRZ_SEL" stride="1" length="4"/> + <reg32 offset="0x8600" name="GRAS_TSEFE_DBG_ECO_CNTL" variants="A8XX-"/> + <reg32 offset="0x8702" name="GRAS_DBG_ECO_CNTL" variants="A8XX"/> + <reg32 offset="0x8601" name="GRAS_ADDR_MODE_CNTL" pos="0" type="a5xx_address_mode" variants="A6XX"/> + <reg32 offset="0x8602" name="GRAS_NC_MODE_CNTL" variants="A7XX"/> + <reg32 offset="0x8700" name="GRAS_NC_MODE_CNTL" variants="A8XX-"/> + <array offset="0x8610" name="GRAS_PERFCTR_TSE_SEL" stride="1" length="4" variants="A6XX-A7XX"/> + <array offset="0x8614" name="GRAS_PERFCTR_RAS_SEL" stride="1" length="4" variants="A6XX-A7XX"/> + <array offset="0x8618" name="GRAS_PERFCTR_LRZ_SEL" stride="1" length="4" variants="A6XX-A7XX"/> + + <array offset="0x8610" name="GRAS_PERFCTR_TSEFE_SEL" stride="1" length="6" variants="A8XX-"/> + <array offset="0x8710" name="GRAS_PERFCTR_TSE_SEL" stride="1" length="6" variants="A8XX-"/> + <array offset="0x8720" name="GRAS_PERFCTR_RAS_SEL" stride="1" length="4" variants="A8XX-"/> + <array offset="0x8730" name="GRAS_PERFCTR_LRZ_SEL" stride="1" length="6" variants="A8XX-"/> + <!-- note 0x8620-0x87ff are not all invalid (in particular, 0x8631/0x8632 have 0x3fff3fff mask and would be xy coords) @@ -1425,6 +2181,7 @@ by a particular renderpass/blit. <!-- same as GRAS_BIN_CONTROL, but without bit 27: --> <reg32 offset="0x8800" name="RB_CNTL" variants="A6XX-A7XX" type="a6xx_bin_cntl" usage="rp_blit"/> + <reg32 offset="0x8800" name="RB_CNTL" variants="A8XX-" type="a8xx_bin_cntl" usage="rp_blit"/> <reg32 offset="0x8801" name="RB_RENDER_CNTL" variants="A6XX" usage="rp_blit"> <bitfield name="CCUSINGLECACHELINESIZE" low="3" high="5"/> @@ -1462,7 +2219,8 @@ by a particular renderpass/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 --> + <reg32 offset="0x8807" name="RB_PROGRAMMABLE_MSAA_POS_2" type="a6xx_programmable_msaa_pos" usage="rp_blit" variants="A8XX-"/> + <reg32 offset="0x8808" name="RB_PROGRAMMABLE_MSAA_POS_3" type="a6xx_programmable_msaa_pos" usage="rp_blit" variants="A8XX-"/> <!-- note: maybe not actually called RB_RENDER_CONTROLn (since RB_RENDER_CNTL name comes from kernel and is probably right) @@ -1476,7 +2234,7 @@ by a particular renderpass/blit. <bitfield name="IJ_LINEAR_CENTROID" pos="4" type="boolean"/> <bitfield name="IJ_LINEAR_SAMPLE" pos="5" type="boolean"/> <bitfield name="COORD_MASK" low="6" high="9" type="hex"/> - <bitfield name="UNK10" pos="10" type="boolean"/> + <bitfield name="INTERP_EN" pos="10" type="boolean"/> </reg32> <reg32 offset="0x880a" name="RB_PS_INPUT_CNTL" usage="rp_blit"> <!-- enable bits for various FS sysvalue regs: --> @@ -1534,8 +2292,32 @@ by a particular renderpass/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"/> - <reg32 offset="0x8812" name="RB_UNKNOWN_8812" variants="A7XX-" usage="rp_blit"/> + <reg32 offset="0x8811" name="RB_MODE_CNTL" low="4" high="6" usage="cmd"/> + <reg32 offset="0x8812" name="RB_BUFFER_CNTL" variants="A7XX-" usage="rp_blit"> + <bitfield name="Z_SYSMEM" pos="0" type="boolean"/> + <bitfield name="S_SYSMEM" pos="1" type="boolean"/> + <bitfield name="RT0_SYSMEM" pos="2" type="boolean"/> + <bitfield name="RT1_SYSMEM" pos="3" type="boolean"/> + <bitfield name="RT2_SYSMEM" pos="4" type="boolean"/> + <bitfield name="RT3_SYSMEM" pos="5" type="boolean"/> + <bitfield name="RT4_SYSMEM" pos="6" type="boolean"/> + <bitfield name="RT5_SYSMEM" pos="7" type="boolean"/> + <bitfield name="RT6_SYSMEM" pos="8" type="boolean"/> + <bitfield name="RT7_SYSMEM" pos="9" type="boolean"/> + <bitfield name="Z_FULL_IN_GMEM" pos="10" type="boolean" variants="A8XX-"/> + <bitfield name="S_FULL_IN_GMEM" pos="11" type="boolean" variants="A8XX-"/> + <bitfield name="RT0_FULL_IN_GMEM" pos="12" type="boolean" variants="A8XX-"/> + <bitfield name="RT1_FULL_IN_GMEM" pos="13" type="boolean" variants="A8XX-"/> + <bitfield name="RT2_FULL_IN_GMEM" pos="14" type="boolean" variants="A8XX-"/> + <bitfield name="RT3_FULL_IN_GMEM" pos="15" type="boolean" variants="A8XX-"/> + <bitfield name="RT4_FULL_IN_GMEM" pos="16" type="boolean" variants="A8XX-"/> + <bitfield name="RT5_FULL_IN_GMEM" pos="17" type="boolean" variants="A8XX-"/> + <bitfield name="RT6_FULL_IN_GMEM" pos="18" type="boolean" variants="A8XX-"/> + <bitfield name="RT7_FULL_IN_GMEM" pos="19" type="boolean" variants="A8XX-"/> + </reg32> + + <reg32 offset="0x8816" name="RB_RESOLVE_CR_CNTL" variants="A8XX-" usage="rp_blit"/> + <!-- 0x8813-0x8817 invalid --> <!-- always 0x0 ? --> <reg32 offset="0x8818" name="RB_UNKNOWN_8818" low="0" high="6" usage="cmd"/> @@ -1546,11 +2328,17 @@ by a particular renderpass/blit. <reg32 offset="0x881c" name="RB_UNKNOWN_881C" usage="cmd"/> <reg32 offset="0x881d" name="RB_UNKNOWN_881D" usage="cmd"/> <reg32 offset="0x881e" name="RB_UNKNOWN_881E" usage="cmd"/> - <!-- 0x881f invalid --> + + <!-- Duplicates fields from SP_PS_CNTL_0 --> + <reg32 offset="0x881f" name="RB_PS_CNTL" variants="A8XX-" usage="rp_blit"> + <bitfield name="PIXLODENABLE" pos="0" type="boolean"/> + <bitfield name="LODPIXMASK" pos="1" type="boolean"/> + </reg32> + <array offset="0x8820" name="RB_MRT" stride="8" length="8" usage="rp_blit"> <reg32 offset="0x0" name="CONTROL"> - <bitfield name="BLEND" pos="0" type="boolean"/> - <bitfield name="BLEND2" pos="1" type="boolean"/> + <bitfield name="COLOR_BLEND_EN" pos="0" type="boolean"/> + <bitfield name="ALPHA_BLEND_EN" pos="1" type="boolean"/> <bitfield name="ROP_ENABLE" pos="2" type="boolean"/> <bitfield name="ROP_CODE" low="3" high="6" type="a3xx_rop_code"/> <bitfield name="COMPONENT_ENABLE" low="7" high="10" type="hex"/> @@ -1613,7 +2401,9 @@ by a particular renderpass/blit. <bitfield name="ALPHA_TO_ONE" pos="11" type="boolean"/> <bitfield name="SAMPLE_MASK" low="16" high="31"/> </reg32> - <!-- 0x8866-0x886f invalid --> + <reg32 offset="0x8866" name="RB_LB_PARAM_LIMIT" variants="A8XX-" usage="rp_blit"> + <bitfield name="PRIMALLOCTHRESHOLD" low="0" high="2" type="uint"/> + </reg32> <reg32 offset="0x8870" name="RB_DEPTH_PLANE_CNTL" type="a6xx_depth_plane_cntl" usage="rp_blit"/> <reg32 offset="0x8871" name="RB_DEPTH_CNTL" usage="rp_blit"> @@ -1627,14 +2417,15 @@ by a particular renderpass/blit. </doc> <bitfield name="Z_READ_ENABLE" pos="6" type="boolean"/> <bitfield name="Z_BOUNDS_ENABLE" pos="7" type="boolean"/> + <!-- clamp shader depth out to [0, 1] (instead of RB_VIEWPORT_ZCLAMP_MIN/MAX)--> + <bitfield name="O_DEPTH_01_CLAMP_EN" pos="8" type="boolean" variants="A8XX-"/> </reg32> <!-- duplicates GRAS_SU_DEPTH_BUFFER_INFO: --> <reg32 offset="0x8872" name="RB_DEPTH_BUFFER_INFO" variants="A6XX" type="a6xx_depth_buffer_info" usage="rp_blit"/> <!-- first 4 bits duplicates GRAS_SU_DEPTH_BUFFER_INFO --> - <reg32 offset="0x8872" name="RB_DEPTH_BUFFER_INFO" variants="A7XX-" usage="rp_blit"> - <bitfield name="DEPTH_FORMAT" low="0" high="2" type="a6xx_depth_format"/> - <bitfield name="UNK3" low="3" high="4"/> + <reg32 offset="0x8872" name="RB_DEPTH_BUFFER_INFO" type="a6xx_depth_buffer_info" variants="A7XX-" usage="rp_blit"> + <bitfield name="PRT" low="3" high="4"/> <bitfield name="TILEMODE" low="5" high="6" type="a6xx_tile_mode"/> <bitfield name="LOSSLESSCOMPEN" pos="7" type="boolean"/> </reg32> @@ -1702,12 +2493,22 @@ by a particular renderpass/blit. <reg32 offset="0x8898" name="RB_LRZ_CNTL" usage="rp_blit"> <bitfield name="ENABLE" pos="0" type="boolean"/> </reg32> - <reg32 offset="0x8899" name="RB_UNKNOWN_8899" variants="A7XX-" usage="cmd"/> + <reg32 offset="0x8899" name="RB_LRZ_CNTL2" variants="A7XX-" usage="cmd"> + <bitfield name="ENABLE_BIDIRECTIONAL_LRZ" pos="0" type="boolean"/> + </reg32> <!-- 0x8899-0x88bf invalid --> <!-- clamps depth value for depth test/write --> <reg32 offset="0x88c0" name="RB_VIEWPORT_ZCLAMP_MIN" type="float" usage="rp_blit" variants="A6XX-A7XX"/> <reg32 offset="0x88c1" name="RB_VIEWPORT_ZCLAMP_MAX" type="float" usage="rp_blit" variants="A6XX-A7XX"/> +<!-- todo allow type="float" on an <array/> --> + <array offset="0x88b0" name="RB_VIEWPORT_ZCLAMP_MIN" stride="1" length="16" usage="rp_blit" variants="A8XX-"> + <reg32 offset="0" name="REG" type="float"/> + </array> + <array offset="0x88c0" name="RB_VIEWPORT_ZCLAMP_MAX" stride="1" length="16" usage="rp_blit" variants="A8XX-"> + <reg32 offset="0" name="REG" type="float"/> + </array> + <!-- 0x88c2-0x88cf invalid--> <reg32 offset="0x88d0" name="RB_RESOLVE_CNTL_0" usage="rp_blit"> <bitfield name="UNK0" low="0" high="12"/> @@ -1720,6 +2521,11 @@ by a particular renderpass/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="0x88d3" name="RB_RESOLVE_CNTL_3" type="a8xx_bin_size" variants="A8XX-" usage="rp_blit"/> + <reg32 offset="0x88f0" name="RB_RESOLVE_CNTL_4" variants="A8XX-" usage="rp_blit"/> + <reg32 offset="0x88f1" name="RB_RESOLVE_CNTL_5" variants="A8XX-" 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"/> @@ -1798,8 +2604,10 @@ by a particular renderpass/blit. <value value="0x1" name="CCU_CACHE_SIZE_HALF"/> <value value="0x2" name="CCU_CACHE_SIZE_QUARTER"/> <value value="0x3" name="CCU_CACHE_SIZE_EIGHTH"/> + <!-- for DEPTH_CACHE_SIZE 3 == THREE_QUARTER from KNP --> + <value value="0x3" name="CCU_CACHE_SIZE_THREE_QUARTER"/> </enum> - <reg32 offset="0x88e5" name="RB_CCU_CACHE_CNTL" 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"/> @@ -1814,12 +2622,30 @@ by a particular renderpass/blit. --> <bitfield name="COLOR_OFFSET" low="23" high="31" shr="12" type="hex"/> </reg32> - <!-- 0x88e6-0x88ef invalid --> + + <reg32 offset="0x88e5" name="RB_CCU_CACHE_CNTL" variants="A8XX-" usage="cmd"> + <!-- + For color cache, full is 128KB per CCU. For depth cache, + full is 256KB per CCU. + + For attr/pos caches (see VPC_{ATTR,POS,BV_POS}_BUF_GMEM_SIZE), + the sizes are per CCU + --> + <bitfield name="COLOR_OFFSET" low="0" high="13" shr="12" type="hex"/> + <bitfield name="COLOR_CACHE_SIZE" low="14" high="15" type="a6xx_ccu_cache_size"/> + <bitfield name="DEPTH_OFFSET" low="16" high="29" shr="12" type="hex"/> + <bitfield name="DEPTH_CACHE_SIZE" low="30" high="31" type="a6xx_ccu_cache_size"/> + </reg32> + + <reg32 offset="0x88e6" name="RB_RESOLVE_GMEM_BUFFER_CNTL" variants="A8XX-"> + <bitfield name="FULL_IN_GMEM" pos="0" type="boolean"/> + </reg32> + <!-- always 0x0 ? --> - <reg32 offset="0x88f0" name="RB_UNKNOWN_88F0" low="0" high="11" usage="cmd"/> + <reg32 offset="0x88f0" name="RB_UNKNOWN_88F0" low="0" high="11" variants="A6XX" usage="cmd"/> <!-- could be for separate stencil? (or may not be a flag buffer at all) --> - <reg64 offset="0x88f1" name="RB_UNK_FLAG_BUFFER_BASE" type="waddress" align="64"/> - <reg32 offset="0x88f3" name="RB_UNK_FLAG_BUFFER_PITCH" type="a6xx_flag_buffer_pitch"/> + <reg64 offset="0x88f1" name="RB_UNK_FLAG_BUFFER_BASE" type="waddress" align="64" variants="A6XX"/> + <reg32 offset="0x88f3" name="RB_UNK_FLAG_BUFFER_PITCH" type="a6xx_flag_buffer_pitch" variants="A6XX"/> <reg32 offset="0x88f4" name="RB_VRS_CONFIG" usage="rp_blit"> <bitfield name="UNK2" pos="2" type="boolean"/> @@ -1849,9 +2675,19 @@ by a particular renderpass/blit. the address is specified through CP_EVENT_WRITE7::WRITE_SAMPLE_COUNT. </doc> <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 --> + <bitset name="a8xx_gmem_dimension" inline="yes"> + <bitfield name="WIDTH" low="0" high="14" type="uint"/> + <bitfield name="HEIGHT" low="16" high="30" type="uint"/> + </bitset> + + <reg32 offset="0x8813" name="RB_DEPTH_GMEM_DIMENSION" type="a8xx_gmem_dimension" variants="A8XX-"/> + <reg32 offset="0x8814" name="RB_STENCIL_GMEM_DIMENSION" type="a8xx_gmem_dimension" variants="A8XX-"/> + <reg32 offset="0x8815" name="RB_RESOLVE_GMEM_DIMENSION" type="a8xx_gmem_dimension" variants="A8XX-"/> + + <array offset="0x8930" name="RB_MRT_GMEM_DIMENSION" variants="A8XX-" stride="1" length="8"> + <reg32 offset="0" name="REG" type="a8xx_gmem_dimension"/> + </array> <!-- These show up in a6xx gen3+ but so far haven't found an example of @@ -1862,7 +2698,7 @@ by a particular renderpass/blit. <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_A2D_BLT_CNTL" type="a6xx_a2d_bit_cntl" usage="rp_blit"/> + <reg32 offset="0x8c00" name="RB_A2D_BLT_CNTL" type="a6xx_a2d_blt_cntl" usage="rp_blit"/> <reg32 offset="0x8c01" name="RB_A2D_PIXEL_CNTL" low="0" high="31" usage="rp_blit"/> <bitset name="a6xx_a2d_src_texture_info" inline="yes"> @@ -1921,10 +2757,10 @@ by a particular renderpass/blit. <!-- 0x8c35-0x8dff invalid --> <!-- always 0x1 ? either doesn't exist for a650 or write-only: --> - <reg32 offset="0x8e01" name="RB_UNKNOWN_8E01" usage="cmd"/> + <reg32 offset="0x8e01" name="RB_RBP_CNTL" usage="cmd"/> <!-- 0x8e00-0x8e03 invalid --> <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"/> + <reg32 offset="0x8e05" name="RB_ADDR_MODE_CNTL" pos="0" type="a5xx_address_mode" variants="A6XX"/> <!-- 0x02080000 in GMEM, zero otherwise? --> <reg32 offset="0x8e06" name="RB_CCU_DBG_ECO_CNTL" variants="A7XX-" usage="cmd"/> @@ -1963,7 +2799,7 @@ by a particular renderpass/blit. <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"> + <reg32 offset="0x8e08" name="RB_NC_MODE_CNTL" variants="A6XX-A7XX"> <bitfield name="MODE" pos="0" type="boolean"/> <bitfield name="LOWER_BIT" low="1" high="2" type="uint"/> <bitfield name="MIN_ACCESS_LENGTH" pos="3" type="boolean"/> <!-- true=64b false=32b --> @@ -1972,26 +2808,40 @@ by a particular renderpass/blit. <bitfield name="RGB565_PREDICATOR" pos="11" type="boolean"/> <bitfield name="UNK12" low="12" high="13"/> </reg32> - <reg32 offset="0x8e09" name="RB_UNKNOWN_8E09" variants="A7XX-" usage="cmd"/> + <reg32 offset="0x8e08" name="RB_CCU_NC_MODE_CNTL" variants="A8XX-"/> + + <reg32 offset="0x8e09" name="RB_UNKNOWN_8E09" variants="A7XX" usage="cmd"/> + <reg32 offset="0x8e09" name="RB_GC_GMEM_PROTECT" variants="A8XX-"/> + <reg32 offset="0x8e0a" name="RB_LPAC_GMEM_PROTECT" variants="A8XX-"/> <!-- 0x8e09-0x8e0f invalid --> <array offset="0x8e10" name="RB_PERFCTR_RB_SEL" stride="1" length="8"/> <array offset="0x8e18" name="RB_PERFCTR_CCU_SEL" stride="1" length="5"/> <!-- 0x8e1d-0x8e1f invalid --> <!-- 0x8e20-0x8e25 more perfcntr sel? --> <!-- 0x8e26-0x8e27 invalid --> - <reg32 offset="0x8e28" name="RB_CMP_DBG_ECO_CNTL"/> + + <reg32 offset="0x8f00" name="RB_CMP_NC_MODE_CNTL" variants="A8XX-"/> + <reg32 offset="0x8f01" name="RB_RESOLVE_PREFETCH_CNTL" variants="A8XX-"/> + <reg32 offset="0x8f02" name="RB_CMP_DBG_ECO_CNTL" variants="A8XX-"/> + + <reg32 offset="0x8f03" name="RB_UNSLICE_STATUS" variants="A8XX-"/> + <reg32 offset="0x8e28" name="RB_CMP_DBG_ECO_CNTL" variants="A6XX-A7XX"/> <!-- 0x8e29-0x8e2b invalid --> - <array offset="0x8e2c" name="RB_PERFCTR_CMP_SEL" stride="1" length="4"/> - <array offset="0x8e30" name="RB_PERFCTR_UFC_SEL" stride="1" length="6" variants="A7XX-"/> - <reg32 offset="0x8e3b" name="RB_RB_SUB_BLOCK_SEL_CNTL_HOST"/> - <reg32 offset="0x8e3d" name="RB_RB_SUB_BLOCK_SEL_CNTL_CD"/> + <array offset="0x8e2c" name="RB_PERFCTR_CMP_SEL" stride="1" length="4" variants="A6XX-A7XX"/> + <array offset="0x8e30" name="RB_PERFCTR_UFC_SEL" stride="1" length="6" variants="A7XX"/> + <array offset="0x8f04" name="RB_PERFCTR_CMP_SEL" stride="1" length="4" variants="A8XX-"/> + <array offset="0x8f10" name="RB_PERFCTR_UFC_SEL" stride="1" length="6" variants="A8XX-"/> + <reg32 offset="0x8e3b" name="RB_SUB_BLOCK_SEL_CNTL_HOST"/> + <reg32 offset="0x8e3d" name="RB_SUB_BLOCK_SEL_CNTL_CD"/> + <reg32 offset="0x8f29" name="RB_UFC_DBG_CNTL" variants="A8XX-"/> <!-- 0x8e3e-0x8e4f invalid --> <!-- GMEM save/restore for preemption: --> <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_CONTEXT_SWITCH_GMEM_SAVE_RESTORE_ADDR" type="waddress" align="1"/> - <!-- 0x8e53-0x8e7f invalid --> - <reg32 offset="0x8e79" name="RB_UNKNOWN_8E79" variants="A7XX-" usage="cmd"/> + <reg32 offset="0x8e77" name="RB_SLICE_UFC_PREFETCH_CNTL" variants="A8XX-"/> + <reg32 offset="0x8e78" name="RB_SLICE_UFC_DBG_CNTL" variants="A8XX-"/> + <reg32 offset="0x8e79" name="RB_UNKNOWN_8E79" variants="A7XX" usage="init"/> <!-- 0x8e80-0x8e83 are valid --> <!-- 0x8e84-0x90ff invalid --> @@ -2014,6 +2864,10 @@ by a particular renderpass/blit. <reg32 offset="0x9102" name="VPC_GS_CLIP_CULL_CNTL" type="a6xx_vpc_xs_clip_cntl" variants="A6XX-A7XX" usage="rp_blit"/> <reg32 offset="0x9103" name="VPC_DS_CLIP_CULL_CNTL" type="a6xx_vpc_xs_clip_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9307" name="VPC_VS_CLIP_CULL_CNTL" type="a6xx_vpc_xs_clip_cntl" variants="A8XX" usage="rp_blit"/> + <reg32 offset="0x9308" name="VPC_GS_CLIP_CULL_CNTL" type="a6xx_vpc_xs_clip_cntl" variants="A8XX" usage="rp_blit"/> + <reg32 offset="0x9309" name="VPC_DS_CLIP_CULL_CNTL" type="a6xx_vpc_xs_clip_cntl" variants="A8XX" usage="rp_blit"/> + <reg32 offset="0x9311" name="VPC_VS_CLIP_CULL_CNTL_V2" type="a6xx_vpc_xs_clip_cntl" variants="A6XX-A7XX" usage="rp_blit"/> <reg32 offset="0x9312" name="VPC_GS_CLIP_CULL_CNTL_V2" type="a6xx_vpc_xs_clip_cntl" variants="A6XX-A7XX" usage="rp_blit"/> <reg32 offset="0x9313" name="VPC_DS_CLIP_CULL_CNTL_V2" type="a6xx_vpc_xs_clip_cntl" variants="A6XX-A7XX" usage="rp_blit"/> @@ -2028,6 +2882,9 @@ by a particular renderpass/blit. <reg32 offset="0x9105" name="VPC_GS_SIV_CNTL" type="a6xx_vpc_xs_siv_cntl" variants="A6XX-A7XX" usage="rp_blit"/> <reg32 offset="0x9106" name="VPC_DS_SIV_CNTL" type="a6xx_vpc_xs_siv_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x930a" name="VPC_VS_SIV_CNTL" type="a6xx_vpc_xs_siv_cntl" variants="A8XX-" usage="rp_blit"/> + <reg32 offset="0x930b" name="VPC_GS_SIV_CNTL" type="a6xx_vpc_xs_siv_cntl" variants="A8XX-" usage="rp_blit"/> + <reg32 offset="0x930c" name="VPC_DS_SIV_CNTL" type="a6xx_vpc_xs_siv_cntl" variants="A8XX-" usage="rp_blit"/> <reg32 offset="0x9314" name="VPC_VS_SIV_CNTL_V2" type="a6xx_vpc_xs_siv_cntl" variants="A6XX-A7XX" usage="rp_blit"/> <reg32 offset="0x9315" name="VPC_GS_SIV_CNTL_V2" type="a6xx_vpc_xs_siv_cntl" variants="A6XX-A7XX" usage="rp_blit"/> @@ -2042,6 +2899,7 @@ by a particular renderpass/blit. <reg32 offset="0x9980" name="VPC_RAST_STREAM_CNTL" type="a6xx_vpc_rast_stream_cntl" variants="A6XX" usage="rp_blit"/> <reg32 offset="0x9107" name="VPC_RAST_STREAM_CNTL" type="a6xx_vpc_rast_stream_cntl" variants="A7XX" usage="rp_blit"/> + <reg32 offset="0x930d" name="VPC_RAST_STREAM_CNTL" type="a6xx_vpc_rast_stream_cntl" variants="A8XX-" usage="rp_blit"/> <reg32 offset="0x9317" name="VPC_RAST_STREAM_CNTL_V2" type="a6xx_vpc_rast_stream_cntl" variants="A7XX" usage="rp_blit"/> <reg32 offset="0x9107" name="VPC_UNKNOWN_9107" variants="A6XX" usage="rp_blit"> @@ -2051,6 +2909,7 @@ by a particular renderpass/blit. </reg32> <reg32 offset="0x9108" name="VPC_RAST_CNTL" type="a6xx_rast_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x930e" name="VPC_RAST_CNTL" type="a6xx_rast_cntl" variants="A8XX-" usage="rp_blit"/> <bitset name="a6xx_pc_cntl" inline="yes"> <bitfield name="PRIMITIVE_RESTART" pos="0" type="boolean"/> <bitfield name="PROVOKING_VTX_LAST" pos="1" type="boolean"/> @@ -2091,9 +2950,13 @@ by a particular renderpass/blit. </bitset> <reg32 offset="0x9109" name="VPC_PC_CNTL" type="a6xx_pc_cntl" variants="A7XX" usage="rp_blit"/> + <reg32 offset="0x930f" name="VPC_PC_CNTL" type="a6xx_pc_cntl" variants="A8XX-" usage="rp_blit"/> <reg32 offset="0x910a" name="VPC_GS_PARAM_0" type="a6xx_gs_param_0" variants="A7XX" usage="rp_blit"/> + <reg32 offset="0x90c0" name="VPC_GS_PARAM_0" type="a6xx_gs_param_0" variants="A8XX-" usage="rp_blit"/> <reg32 offset="0x910b" name="VPC_STEREO_RENDERING_VIEWMASK" type="hex" low="0" high="15" variants="A7XX" usage="rp_blit"/> + <reg32 offset="0x90c1" name="VPC_STEREO_RENDERING_VIEWMASK" type="hex" low="0" high="15" variants="A8XX-" usage="rp_blit"/> <reg32 offset="0x910c" name="VPC_STEREO_RENDERING_CNTL" type="a6xx_stereo_rendering_cntl" variants="A7XX" usage="rp_blit"/> + <reg32 offset="0x931a" name="VPC_STEREO_RENDERING_CNTL" type="a6xx_stereo_rendering_cntl" variants="A8XX-" usage="rp_blit"/> <enum name="a6xx_varying_interp_mode"> <value value="0" name="INTERP_SMOOTH"/> @@ -2119,6 +2982,15 @@ by a particular renderpass/blit. <reg32 offset="0x0" name="MODE"/> </array> + <array offset="0x9240" name="VPC_VARYING_INTERP_MODE" stride="1" length="8" variants="A8XX-" usage="rp_blit"> + <doc>Packed array of a6xx_varying_interp_mode</doc> + <reg32 offset="0x0" name="MODE"/> + </array> + <array offset="0x9248" name="VPC_VARYING_REPLACE_MODE" stride="1" length="8" variants="A8XX-" usage="rp_blit"> + <doc>Packed array of a6xx_varying_ps_repl_mode</doc> + <reg32 offset="0x0" name="MODE"/> + </array> + <!-- always 0x0 --> <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"/> @@ -2128,6 +3000,11 @@ by a particular renderpass/blit. <reg32 offset="0" name="DISABLE"/> </array> + <array offset="0x9252" name="VPC_VARYING_LM_TRANSFER_CNTL" stride="1" length="4" variants="A8XX-" usage="rp_blit"> + <!-- one bit per varying component: --> + <reg32 offset="0" name="DISABLE"/> + </array> + <bitset name="a6xx_vpc_so_mapping_wptr" inline="yes"> <!-- Choose which DWORD to write to. There is an array of @@ -2158,6 +3035,7 @@ by a particular renderpass/blit. </bitset> <reg32 offset="0x9216" name="VPC_SO_MAPPING_WPTR" type="a6xx_vpc_so_mapping_wptr" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9180" name="VPC_SO_MAPPING_WPTR" type="a6xx_vpc_so_mapping_wptr" variants="A8XX-" usage="rp_blit"/> <bitset name="a6xx_vpc_so_mapping_port" inline="yes"> <bitfield name="A_BUF" low="0" high="1" type="uint"/> @@ -2170,8 +3048,10 @@ by a particular renderpass/blit. <!-- special register, write multiple times to load SO program (not readable) --> <reg32 offset="0x9217" name="VPC_SO_MAPPING_PORT" type="a6xx_vpc_so_mapping_port" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9181" name="VPC_SO_MAPPING_PORT" type="a6xx_vpc_so_mapping_port" variants="A8XX-" usage="rp_blit"/> <reg64 offset="0x9218" name="VPC_SO_QUERY_BASE" type="waddress" align="32" variants="A6XX-A7XX" usage="cmd"/> + <reg64 offset="0x9182" name="VPC_SO_QUERY_BASE" type="waddress" align="32" variants="A8XX-" usage="cmd"/> <array offset="0x921a" name="VPC_SO" stride="7" length="4" variants="A6XX-A7XX" usage="cmd"> <reg64 offset="0" name="BUFFER_BASE" type="waddress" align="32"/> @@ -2181,13 +3061,23 @@ by a particular renderpass/blit. <reg64 offset="5" name="FLUSH_BASE" type="waddress" align="32"/> </array> + <array offset="0x9184" name="VPC_SO" stride="7" length="4" variants="A8XX-" usage="cmd"> + <reg64 offset="0" name="BUFFER_BASE" type="waddress" align="32"/> + <reg32 offset="2" name="BUFFER_SIZE" low="2" high="31" shr="2"/> + <reg32 offset="3" name="BUFFER_STRIDE" low="0" high="9" shr="2"/> + <reg32 offset="4" name="BUFFER_OFFSET" low="2" high="31" shr="2"/> + <reg64 offset="5" name="FLUSH_BASE" type="waddress" align="32"/> + </array> + <bitset name="a6xx_vpc_replace_mode_cntl" inline="yes"> <bitfield name="INVERT" pos="0" type="boolean"/> </bitset> <reg32 offset="0x9236" name="VPC_REPLACE_MODE_CNTL" type="a6xx_vpc_replace_mode_cntl" variants="A6XX-A7XX" usage="cmd"/> + <reg32 offset="0x9310" name="VPC_REPLACE_MODE_CNTL" type="a6xx_vpc_replace_mode_cntl" variants="A8XX-" usage="cmd"/> <reg32 offset="0x9300" name="VPC_ROTATION_CNTL" low="0" high="2" variants="A6XX-A7XX" usage="cmd"/> + <reg32 offset="0x9312" name="VPC_ROTATION_CNTL" low="0" high="2" variants="A8XX-" usage="cmd"/> <bitset name="a6xx_vpc_xs_cntl" inline="yes"> <doc> @@ -2211,6 +3101,10 @@ by a particular renderpass/blit. <reg32 offset="0x9302" name="VPC_GS_CNTL" type="a6xx_vpc_xs_cntl" variants="A6XX-A7XX" usage="rp_blit"/> <reg32 offset="0x9303" name="VPC_DS_CNTL" type="a6xx_vpc_xs_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9300" name="VPC_VS_CNTL" type="a6xx_vpc_xs_cntl" variants="A8XX-" usage="rp_blit"/> + <reg32 offset="0x9301" name="VPC_GS_CNTL" type="a6xx_vpc_xs_cntl" variants="A8XX-" usage="rp_blit"/> + <reg32 offset="0x9302" name="VPC_DS_CNTL" type="a6xx_vpc_xs_cntl" variants="A8XX-" usage="rp_blit"/> + <bitset name="a6xx_vpc_ps_cntl" inline="yes"> <bitfield name="NUMNONPOSVAR" low="0" high="7" type="uint"/> <!-- for fixed-function (i.e. no GS) gl_PrimitiveID in FS --> @@ -2231,6 +3125,7 @@ by a particular renderpass/blit. </bitset> <reg32 offset="0x9304" name="VPC_PS_CNTL" type="a6xx_vpc_ps_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9303" name="VPC_PS_CNTL" type="a6xx_vpc_ps_cntl" variants="A8XX-" usage="rp_blit"/> <bitset name="a6xx_vpc_so_cntl" inline="yes"> <!-- @@ -2244,40 +3139,73 @@ by a particular renderpass/blit. </bitset> <reg32 offset="0x9305" name="VPC_SO_CNTL" type="a6xx_vpc_so_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9304" name="VPC_SO_CNTL" type="a6xx_vpc_so_cntl" variants="A8XX-" usage="rp_blit"/> <bitset name="a6xx_so_override" inline="yes"> <bitfield name="DISABLE" pos="0" type="boolean"/> </bitset> <reg32 offset="0x9306" name="VPC_SO_OVERRIDE" type="a6xx_so_override" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9305" name="VPC_SO_OVERRIDE" type="a6xx_so_override" variants="A8XX-" usage="rp_blit"/> <reg32 offset="0x9807" name="PC_DGEN_SO_OVERRIDE" type="a6xx_so_override" variants="A7XX" usage="rp_blit"/> + <reg32 offset="0x9b0a" name="PC_DGEN_SO_OVERRIDE" type="a6xx_so_override" variants="A8XX-" usage="rp_blit"/> <reg32 offset="0x9307" name="VPC_PS_RAST_CNTL" type="a6xx_rast_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9306" name="VPC_PS_RAST_CNTL" type="a6xx_rast_cntl" variants="A8XX-" usage="rp_blit"/> - <reg32 offset="0x9308" name="VPC_ATTR_BUF_GMEM_SIZE" variants="A7XX" type="uint" usage="rp_blit"/> - <reg32 offset="0x9309" name="VPC_ATTR_BUF_GMEM_BASE" variants="A7XX" type="uint" usage="rp_blit"/> + <reg32 offset="0x9308" name="VPC_ATTR_BUF_GMEM_SIZE" variants="A7XX" type="uint" usage="cmd"/> + <reg32 offset="0x9309" name="VPC_ATTR_BUF_GMEM_BASE" variants="A7XX" type="hex" usage="cmd"/> - <reg32 offset="0x9b09" name="PC_ATTR_BUF_GMEM_SIZE" variants="A7XX" type="uint" usage="rp_blit"/> + <reg32 offset="0x9314" name="VPC_ATTR_BUF_GMEM_SIZE" variants="A8XX-" type="uint" usage="cmd"/> + <reg32 offset="0x9315" name="VPC_ATTR_BUF_GMEM_BASE" variants="A8XX-" type="hex" usage="cmd"/> + + <reg32 offset="0x9316" name="VPC_POS_BUF_GMEM_SIZE" variants="A8XX-" type="uint" usage="cmd"/> + <reg32 offset="0x9317" name="VPC_POS_BUF_GMEM_BASE" variants="A8XX-" type="hex" usage="cmd"/> + + <reg32 offset="0x9318" name="VPC_BV_POS_BUF_GMEM_SIZE" variants="A8XX-" type="uint" usage="cmd"/> + <reg32 offset="0x9319" name="VPC_BV_POS_BUF_GMEM_BASE" variants="A8XX-" type="hex" usage="cmd"/> + + <reg32 offset="0x9b09" name="PC_ATTR_BUF_GMEM_SIZE" variants="A7XX" type="uint" usage="cmd"/> + <reg32 offset="0x9b16" name="PC_ATTR_BUF_GMEM_SIZE" variants="A8XX-" type="uint" usage="cmd"/> + + <reg32 offset="0x9b17" name="PC_POS_BUF_GMEM_SIZE" variants="A8XX-" type="uint" usage="cmd"/> + <reg32 offset="0x9b18" name="PC_BV_POS_BUF_GMEM_SIZE" variants="A8XX-" type="uint" usage="cmd"/> <reg32 offset="0x930a" name="VPC_UNKNOWN_930A" variants="A7XX"/> + <reg32 offset="0x9313" name="VPC_UNKNOWN_9313" variants="A8XX-"/> + <reg32 offset="0x9e17" name="PC_UNKNOWN_9E17" variants="A8XX-"/> + <reg32 offset="0x960a" name="VPC_FLATSHADE_MODE_CNTL" variants="A7XX"/> + <reg32 offset="0x9741" name="VPC_FLATSHADE_MODE_CNTL" variants="A8XX-"/> <!-- 0x9307-0x95ff invalid --> <!-- TODO: 0x9600-0x97ff range --> - <reg32 offset="0x9600" name="VPC_DBG_ECO_CNTL" usage="cmd"/> <!-- always 0x0 ? TODO: 0x1fbf37ff valid mask --> - <reg32 offset="0x9601" name="VPC_ADDR_MODE_CNTL" pos="0" type="a5xx_address_mode" usage="cmd"/> - <reg32 offset="0x9602" name="VPC_UNKNOWN_9602" pos="0" usage="cmd"/> <!-- always 0x0 ? --> - <reg32 offset="0x9603" name="VPC_UNKNOWN_9603" low="0" high="26"/> + <reg32 offset="0x9600" name="VPC_DBG_ECO_CNTL" variants="A6XX-A7XX" usage="cmd"/> <!-- always 0x0 ? TODO: 0x1fbf37ff valid mask --> + <reg32 offset="0x9601" name="VPC_ADDR_MODE_CNTL" pos="0" type="a5xx_address_mode" usage="cmd" variants="A6XX"/> + <reg32 offset="0x9680" name="VPC_DBG_ECO_CNTL" variants="A8XX-"/> + <reg32 offset="0x9604" name="VPC_DBG_ECO_CNTL_2" variants="A8XX-"/> + <reg32 offset="0x9742" name="VPC_DBG_ECO_CNTL_1" variants="A8XX-"/> + <reg32 offset="0x9745" name="VPC_DBG_ECO_CNTL_3" variants="A8XX-"/> + <reg32 offset="0x9602" name="VPC_LB_MODE_CNTL" pos="0" variants="A6XX-A7XX" usage="init"/> <!-- always 0x0 ? --> + <reg32 offset="0x9740" name="VPC_LB_MODE_CNTL" pos="0" variants="A8XX-"/> + <reg32 offset="0x9603" name="VPC_STATUS" low="0" high="26" variants="A6XX-A7XX"/> + <reg32 offset="0x9600" name="VPC_STATUS" low="0" high="26" variants="A8XX-"/> <array offset="0x9604" name="VPC_PERFCTR_VPC_SEL" stride="1" length="6" variants="A6XX"/> - <array offset="0x960b" name="VPC_PERFCTR_VPC_SEL" stride="1" length="12" variants="A7XX-"/> - <!-- 0x960a-0x9623 invalid --> - <!-- TODO: regs from 0x9624-0x963a --> - <!-- 0x963b-0x97ff invalid --> + <array offset="0x960b" name="VPC_PERFCTR_VPC_SEL" stride="1" length="12" variants="A7XX"/> + <array offset="0x9670" name="VPC_PERFCTR_VPC_SEL_2" stride="1" length="12" variants="A8XX-"/> + <array offset="0x9690" name="VPC_PERFCTR_VPC_SEL" stride="1" length="12" variants="A8XX-"/> + <array offset="0x9750" name="VPC_PERFCTR_VPC_SEL_1" stride="1" length="12" variants="A8XX-"/> + + <reg64 offset="0x9634" name="VPC_CONTEXT_SWITCH_SO_SAVE_ADDR" type="waddress" variants="A6XX-A7XX"/> + <reg64 offset="0x9602" name="VPC_CONTEXT_SWITCH_SO_SAVE_ADDR" type="waddress" variants="A8XX-"/> + + <reg32 offset="0x980b" name="PC_UNKNOWN_980B" variants="A8XX-"/> <reg32 offset="0x9800" name="PC_HS_PARAM_0" low="0" high="5" type="uint" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9b10" name="PC_HS_PARAM_0" low="0" high="5" type="uint" variants="A8XX-" usage="rp_blit"/> <bitset name="a6xx_pc_hs_param_1" inline="yes"> <bitfield name="SIZE" low="0" high="10" type="uint"/> @@ -2285,6 +3213,7 @@ by a particular renderpass/blit. </bitset> <reg32 offset="0x9801" name="PC_HS_PARAM_1" type="a6xx_pc_hs_param_1" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9b11" name="PC_HS_PARAM_1" type="a6xx_pc_hs_param_1" variants="A8XX-" usage="rp_blit"/> <bitset name="a6xx_pc_ds_param" inline="yes"> <bitfield name="SPACING" low="0" high="1" type="a6xx_tess_spacing"/> @@ -2292,10 +3221,13 @@ by a particular renderpass/blit. </bitset> <reg32 offset="0x9802" name="PC_DS_PARAM" type="a6xx_pc_ds_param" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9b12" name="PC_DS_PARAM" type="a6xx_pc_ds_param" variants="A8XX-" usage="rp_blit"/> <reg32 offset="0x9803" name="PC_RESTART_INDEX" low="0" high="31" type="uint" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9b15" name="PC_RESTART_INDEX" low="0" high="31" type="uint" variants="A8XX-" usage="rp_blit"/> <reg32 offset="0x9804" name="PC_MODE_CNTL" low="0" high="7" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9b00" name="PC_MODE_CNTL" low="0" high="14" variants="A8XX" usage="rp_blit"/> <reg32 offset="0x9805" name="PC_POWER_CNTL" low="0" high="2" usage="rp_blit"/> @@ -2304,6 +3236,7 @@ by a particular renderpass/blit. </bitset> <reg32 offset="0x9806" name="PC_PS_CNTL" type="a6xx_pc_ps_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9b06" name="PC_PS_CNTL" type="a6xx_pc_ps_cntl" variants="A8XX-" usage="rp_blit"/> <bitset name="a6xx_pc_dgen_so_cntl" inline="yes"> <bitfield name="STREAM_ENABLE" low="15" high="18" type="hex"/> @@ -2311,12 +3244,19 @@ by a particular renderpass/blit. <!-- New in a6xx gen3+ --> <reg32 offset="0x9808" name="PC_DGEN_SO_CNTL" type="a6xx_pc_dgen_so_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9b0b" name="PC_DGEN_SO_CNTL" type="a6xx_pc_dgen_so_cntl" variants="A8XX-" usage="rp_blit"/> <bitset name="a6xx_pc_dgen_su_conservative_ras_cntl" inline="yes"> <bitfield name="CONSERVATIVERASEN" pos="0" type="boolean"/> </bitset> <reg32 offset="0x980a" name="PC_DGEN_SU_CONSERVATIVE_RAS_CNTL" type="a6xx_pc_dgen_su_conservative_ras_cntl" variants="A6XX-A7XX"/> + <reg32 offset="0x9b08" name="PC_DGEN_SU_CONSERVATIVE_RAS_CNTL" type="a6xx_pc_dgen_su_conservative_ras_cntl" variants="A8XX-"/> + + <reg32 offset="0x9b0c" name="PC_VS_INPUT_CNTL" variants="A8XX-" usage="rp_blit"> + <bitfield name="INSTR_CNT" low="0" high="5" type="uint"/> + <bitfield name="SIDEBAND_CNT" low="6" high="8" type="uint"/> + </reg32> <!-- 0x9840 - 0x9842 are not readable --> <bitset name="a6xx_draw_initiator" inline="yes"> @@ -2326,6 +3266,9 @@ by a particular renderpass/blit. <reg32 offset="0x9840" name="PC_DRAW_INITIATOR" type="a6xx_draw_initiator" variants="A6XX-A7XX"/> <reg32 offset="0x9841" name="PC_KERNEL_INITIATOR" type="a6xx_draw_initiator" variants="A6XX-A7XX"/> + <reg32 offset="0x9800" name="PC_DRAW_INITIATOR" type="a6xx_draw_initiator" variants="A8XX-"/> + <reg32 offset="0x9801" name="PC_KERNEL_INITIATOR" type="a6xx_draw_initiator" variants="A8XX-"/> + <bitset name="a6xx_event_initiator" inline="yes"> <!-- I think only the low bit is actually used? --> <bitfield name="STATE_ID" low="16" high="23"/> @@ -2333,6 +3276,7 @@ by a particular renderpass/blit. </bitset> <reg32 offset="0x9842" name="PC_EVENT_INITIATOR" type="a6xx_event_initiator" variants="A6XX-A7XX"/> + <reg32 offset="0x9802" name="PC_EVENT_INITIATOR" type="a6xx_event_initiator" variants="A8XX-"/> <!-- 0x9880 written in a lot of places by SQE, same value gets written @@ -2345,19 +3289,23 @@ by a particular renderpass/blit. <reg32 offset="0x9981" name="PC_DGEN_RAST_CNTL" type="a6xx_rast_cntl" variants="A6XX" usage="rp_blit"/> <reg32 offset="0x9809" name="PC_DGEN_RAST_CNTL" type="a6xx_rast_cntl" variants="A7XX" usage="rp_blit"/> + <reg32 offset="0x9812" name="PC_DGEN_RAST_CNTL" type="a6xx_rast_cntl" variants="A8XX" usage="rp_blit"/> <!-- Both are a750+. Probably needed to correctly overlap execution of several draws. --> <reg32 offset="0x9885" name="PC_HS_BUFFER_SIZE" variants="A7XX" usage="cmd"/> + <reg32 offset="0x9814" name="PC_HS_BUFFER_SIZE" variants="A8XX-" 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_TF_BUFFER_SIZE" variants="A7XX" usage="cmd"/> + <reg32 offset="0x9815" name="PC_TF_BUFFER_SIZE" variants="A8XX-" usage="cmd"/> <!-- 0x9982-0x9aff invalid --> <reg32 offset="0x9b00" name="PC_CNTL" type="a6xx_pc_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9b01" name="PC_CNTL" type="a6xx_pc_cntl" variants="A8XX-" usage="rp_blit"/> <bitset name="a6xx_pc_xs_cntl" inline="yes"> <doc> @@ -2381,7 +3329,13 @@ by a particular renderpass/blit. <reg32 offset="0x9b03" name="PC_HS_CNTL" type="a6xx_pc_xs_cntl" variants="A6XX-A7XX" usage="rp_blit"/> <reg32 offset="0x9b04" name="PC_DS_CNTL" type="a6xx_pc_xs_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9b02" name="PC_VS_CNTL" type="a6xx_pc_xs_cntl" variants="A8XX-" usage="rp_blit"/> + <reg32 offset="0x9b03" name="PC_GS_CNTL" type="a6xx_pc_xs_cntl" variants="A8XX-" usage="rp_blit"/> + <reg32 offset="0x9b04" name="PC_HS_CNTL" type="a6xx_pc_xs_cntl" variants="A8XX-" usage="rp_blit"/> + <reg32 offset="0x9b05" name="PC_DS_CNTL" type="a6xx_pc_xs_cntl" variants="A8XX-" usage="rp_blit"/> + <reg32 offset="0x9b05" name="PC_GS_PARAM_0" type="a6xx_gs_param_0" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9b13" name="PC_GS_PARAM_0" type="a6xx_gs_param_0" variants="A8XX-" usage="rp_blit"/> <reg32 offset="0x9b06" name="PC_PRIMITIVE_CNTL_6" variants="A6XX" usage="rp_blit"> <doc> @@ -2391,24 +3345,37 @@ by a particular renderpass/blit. </reg32> <reg32 offset="0x9b07" name="PC_STEREO_RENDERING_CNTL" type="a6xx_stereo_rendering_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9b09" name="PC_STEREO_RENDERING_CNTL" type="a6xx_stereo_rendering_cntl" variants="A8XX-" usage="rp_blit"/> <!-- mask of enabled views, doesn't exist on A630 --> <reg32 offset="0x9b08" name="PC_STEREO_RENDERING_VIEWMASK" type="hex" low="0" high="15" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0x9b0d" name="PC_STEREO_RENDERING_VIEWMASK" type="hex" low="0" high="15" variants="A8XX-" 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) --> <bitfield name="EVENT" low="0" high="6" type="vgt_event_type"/> <bitfield name="STATE_ID" low="8" high="15"/> </reg32> - <!-- 0x9c01-0x9dff invalid --> - <!-- 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"/> + + <reg32 offset="0x9e50" name="PC_CHICKEN_BITS_1" variants="A8XX-"/> + <reg32 offset="0x9f20" name="PC_CHICKEN_BITS_2" variants="A8XX-"/> + <reg32 offset="0x9e22" name="PC_CHICKEN_BITS_3" variants="A8XX-"/> + <reg32 offset="0x9e23" name="PC_CHICKEN_BITS_4" variants="A8XX-"/> + <reg32 offset="0x9f23" name="PC_CHICKEN_BITS_5" variants="A8XX-"/> + + <reg32 offset="0x9e00" name="PC_DBG_ECO_CNTL" variants="A6XX-A7XX"/> + <reg32 offset="0x9e53" name="PC_DBG_ECO_CNTL" variants="A8XX-"/> + <reg32 offset="0x9e01" name="PC_ADDR_MODE_CNTL" type="a5xx_address_mode" variants="A6XX"/> <reg64 offset="0x9e04" name="PC_DMA_BASE" type="address" variants="A6XX-A7XX"/> <reg32 offset="0x9e06" name="PC_DMA_OFFSET" type="uint" variants="A6XX-A7XX"/> <reg32 offset="0x9e07" name="PC_DMA_SIZE" type="uint" variants="A6XX-A7XX"/> + <reg64 offset="0x9e06" name="PC_DMA_BASE" type="address" variants="A8XX-"/> + <reg32 offset="0x9e08" name="PC_DMA_OFFSET" type="uint" variants="A8XX-"/> + <reg32 offset="0x9e09" name="PC_DMA_SIZE" type="uint" variants="A8XX-"/> + <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"/> + <reg64 offset="0x9816" name="PC_TESS_BASE" variants="A8XX-" type="waddress" align="32" usage="cmd"/> <reg32 offset="0x9e0b" name="PC_DRAWCALL_CNTL" type="vgt_draw_initiator_a4xx" variants="A6XX-A7XX"> <doc> @@ -2419,6 +3386,10 @@ by a particular renderpass/blit. <reg32 offset="0x9e0c" name="PC_DRAWCALL_INSTANCE_NUM" type="uint" variants="A6XX-A7XX"/> <reg32 offset="0x9e0d" name="PC_DRAWCALL_SIZE" type="uint" variants="A6XX-A7XX"/> + <reg32 offset="0x9e00" name="PC_DRAWCALL_CNTL" type="vgt_draw_initiator_a4xx" variants="A8XX-"/> + <reg32 offset="0x9e01" name="PC_DRAWCALL_INSTANCE_NUM" type="uint" variants="A8XX-"/> + <reg32 offset="0x9e02" name="PC_DRAWCALL_SIZE" type="uint" variants="A8XX-"/> + <!-- These match the contents of CP_SET_BIN_DATA (not written directly) --> <bitset name="a6xx_pc_vis_stream_cntl" inline="yes"> <bitfield name="UNK0" low="0" high="15"/> @@ -2430,20 +3401,30 @@ by a particular renderpass/blit. <reg64 offset="0x9e12" name="PC_PVIS_STREAM_BIN_BASE" type="waddress" align="32" variants="A6XX-A7XX"/> <reg64 offset="0x9e14" name="PC_DVIS_STREAM_BIN_BASE" type="waddress" align="32" variants="A6XX-A7XX"/> + <reg32 offset="0x9e0a" name="PC_AUTO_VERTEX_STRIDE"/> + <reg32 offset="0x9e0d" name="PC_VIS_STREAM_CNTL" type="a6xx_pc_vis_stream_cntl" variants="A8XX-"/> + <reg64 offset="0x9e0e" name="PC_PVIS_STREAM_BIN_BASE" type="waddress" align="32" variants="A8XX-"/> + <reg64 offset="0x9e10" name="PC_DVIS_STREAM_BIN_BASE" type="waddress" align="32" variants="A8XX-"/> + <bitset name="a6xx_pc_drawcall_cntl_override" inline="yes"> <doc>Written by CP_SET_VISIBILITY_OVERRIDE handler</doc> <bitfield name="OVERRIDE" pos="0" type="boolean"/> </bitset> <reg32 offset="0x9e1c" name="PC_DRAWCALL_CNTL_OVERRIDE" type="a6xx_pc_drawcall_cntl_override" variants="A6XX-A7XX"/> + <reg32 offset="0x9e04" name="PC_DRAWCALL_CNTL_OVERRIDE" type="a6xx_pc_drawcall_cntl_override" variants="A8XX-"/> - <reg32 offset="0x9e24" name="PC_UNKNOWN_9E24" variants="A7XX-" usage="cmd"/> + <reg32 offset="0x9e24" name="PC_UNKNOWN_9E24" variants="A7XX-" usage="init"/> <array offset="0x9e34" name="PC_PERFCTR_PC_SEL" stride="1" length="8" variants="A6XX"/> - <array offset="0x9e42" name="PC_PERFCTR_PC_SEL" stride="1" length="16" variants="A7XX-"/> + <array offset="0x9e42" name="PC_PERFCTR_PC_SEL" stride="1" length="16" variants="A7XX"/> + <array offset="0x9e30" name="PC_PERFCTR_PC_SEL" stride="1" length="16" variants="A8XX-"/> + <array offset="0x9f00" name="PC_SLICE_PERFCTR_PC_SEL" stride="1" length="16" variants="A8XX-"/> <!-- always 0x0 --> - <reg32 offset="0x9e72" name="PC_UNKNOWN_9E72" usage="cmd"/> + <reg32 offset="0x9e72" name="PC_CONTEXT_SWITCH_GFX_PREEMPTION_MODE" variants="A6XX-A7XX" usage="init"/> + <reg32 offset="0x9e63" name="PC_CONTEXT_SWITCH_GFX_PREEMPTION_MODE" variants="A8XX-"/> + <reg32 offset="0x9e64" name="PC_CONTEXT_SWITCH_STABILIZE_CNTL_1" variants="A8XX-"/> <reg32 offset="0xa000" name="VFD_CNTL_0" usage="rp_blit"> <bitfield name="FETCH_CNT" low="0" high="5" type="uint"/> @@ -2530,11 +3511,15 @@ by a particular renderpass/blit. <reg32 offset="0xa0f8" name="VFD_POWER_CNTL" low="0" high="2" usage="rp_blit"/> - <reg32 offset="0xa600" name="VFD_DBG_ECO_CNTL" variants="A7XX-" usage="cmd"/> + <reg32 offset="0xa600" name="VFD_DBG_ECO_CNTL" variants="A7XX-" usage="init"/> - <reg32 offset="0xa601" name="VFD_ADDR_MODE_CNTL" type="a5xx_address_mode"/> + <reg32 offset="0xa601" name="VFD_ADDR_MODE_CNTL" type="a5xx_address_mode" variants="A6XX"/> <array offset="0xa610" name="VFD_PERFCTR_VFD_SEL" stride="1" length="8" variants="A6XX"/> <array offset="0xa610" name="VFD_PERFCTR_VFD_SEL" stride="1" length="16" variants="A7XX-"/> + <reg32 offset="0xa639" name="VFD_CB_BV_THRESHOLD" variants="A8XX-"/> + <reg32 offset="0xa63a" name="VFD_CB_BR_THRESHOLD" variants="A8XX-"/> + <reg32 offset="0xa63b" name="VFD_CB_BUSY_REQ_CNT" variants="A8XX-"/> + <reg32 offset="0xa63c" name="VFD_CB_LP_REQ_CNT" variants="A8XX-"/> <!-- Note: this seems to always be paired with another bit in another @@ -2593,8 +3578,6 @@ by a particular renderpass/blit. <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_CNTL_0" type="a6xx_sp_xs_cntl_0" usage="rp_blit"> @@ -2720,6 +3703,15 @@ by a particular renderpass/blit. <bitfield name="OFFSET" low="0" high="18" shr="11"/> </bitset> + <bitset name="a6xx_sp_xs_hysteresis" inline="yes"> + <doc>Same on a6xx/a7xx, UMD should not need to write this</doc> + </bitset> + + <bitset name="a8xx_sp_xs_hysteresis" inline="yes"> + <doc>UMD needs to write in some cases</doc> + <!-- seen 0x400, 0xc00, 0x1000, 0x1c00, 0x1000, 0x2000, 0x3000 --> + </bitset> + <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"/> @@ -2729,6 +3721,8 @@ by a particular renderpass/blit. <reg32 offset="0xa823" name="SP_VS_CONFIG" type="a6xx_sp_xs_config" usage="rp_blit"/> <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="0xa826" name="SP_VS_HYSTERESIS" type="a6xx_sp_xs_hysteresis" variants="A6XX-A7XX"/> + <reg32 offset="0xa826" name="SP_VS_HYSTERESIS" type="a8xx_sp_xs_hysteresis" variants="A8XX-"/> <reg32 offset="0xa82d" name="SP_VS_VGS_CNTL" variants="A7XX-" usage="cmd"/> <reg32 offset="0xa830" name="SP_HS_CNTL_0" type="a6xx_sp_xs_cntl_0" usage="rp_blit"> @@ -2754,6 +3748,8 @@ by a particular renderpass/blit. <reg32 offset="0xa83b" name="SP_HS_CONFIG" type="a6xx_sp_xs_config" usage="rp_blit"/> <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="0xa83e" name="SP_HS_HYSTERESIS" type="a6xx_sp_xs_hysteresis" variants="A6XX-A7XX"/> + <reg32 offset="0xa83e" name="SP_HS_HYSTERESIS" type="a8xx_sp_xs_hysteresis" variants="A8XX-"/> <reg32 offset="0xa82f" name="SP_HS_VGS_CNTL" variants="A7XX-" usage="cmd"/> <reg32 offset="0xa840" name="SP_DS_CNTL_0" type="a6xx_sp_xs_cntl_0" usage="rp_blit"> @@ -2791,6 +3787,8 @@ by a particular renderpass/blit. <reg32 offset="0xa863" name="SP_DS_CONFIG" type="a6xx_sp_xs_config" usage="rp_blit"/> <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="0xa866" name="SP_DS_HYSTERESIS" type="a6xx_sp_xs_hysteresis" variants="A6XX-A7XX"/> + <reg32 offset="0xa866" name="SP_DS_HYSTERESIS" type="a8xx_sp_xs_hysteresis" variants="A8XX-"/> <reg32 offset="0xa868" name="SP_DS_VGS_CNTL" variants="A7XX-" usage="cmd"/> <reg32 offset="0xa870" name="SP_GS_CNTL_0" type="a6xx_sp_xs_cntl_0" usage="rp_blit"> @@ -2814,7 +3812,10 @@ by a particular renderpass/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_OUTPUT_CNTL" type="a6xx_sp_xs_output_cntl" usage="rp_blit"/> + <reg32 offset="0xa873" name="SP_GS_OUTPUT_CNTL" type="a6xx_sp_xs_output_cntl" usage="rp_blit"> + <!-- FLAGS_REGID only for GS --> + <bitfield name="FLAGS_REGID" low="6" high="13" type="a3xx_regid"/> + </reg32> <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"/> @@ -2843,6 +3844,8 @@ by a particular renderpass/blit. <reg32 offset="0xa894" name="SP_GS_CONFIG" type="a6xx_sp_xs_config" usage="rp_blit"/> <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="0xa897" name="SP_GS_HYSTERESIS" type="a6xx_sp_xs_hysteresis" variants="A6XX-A7XX"/> + <reg32 offset="0xa897" name="SP_GS_HYSTERESIS" type="a8xx_sp_xs_hysteresis" variants="A8XX-"/> <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"/> @@ -2886,13 +3889,19 @@ by a particular renderpass/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"> + <bitset name="a6xx_sp_blend_cntl" inline="yes"> <!-- per-mrt enable bit --> <bitfield name="ENABLE_BLEND" low="0" high="7"/> - <bitfield name="UNK8" pos="8" type="boolean"/> + <bitfield name="INDEPENDENT_BLEND_EN" pos="8" type="boolean"/> <bitfield name="DUAL_COLOR_IN_ENABLE" pos="9" type="boolean"/> <bitfield name="ALPHA_TO_COVERAGE" pos="10" type="boolean"/> + </bitset> + + <reg32 offset="0xa989" name="SP_BLEND_CNTL" type="a6xx_sp_blend_cntl" variants="A6XX-A7XX" usage="rp_blit"/> + <reg32 offset="0xa989" name="SP_BLEND_CNTL" type="a6xx_sp_blend_cntl" variants="A8XX-" usage="rp_blit"> + <bitfield name="ALPHA_TO_ONE" pos="11" type="boolean" variants="A8XX-"/> </reg32> + <reg32 offset="0xa98a" name="SP_SRGB_CNTL" usage="rp_blit"> <!-- Same as RB_SRGB_CNTL --> <bitfield name="SRGB_MRT0" pos="0" type="boolean"/> @@ -2993,13 +4002,11 @@ by a particular renderpass/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_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"/> + <reg32 offset="0xa9ab" name="SP_PS_HYSTERESIS" type="a6xx_sp_xs_hysteresis" variants="A6XX-A7XX"/> + <reg32 offset="0xa9ab" name="SP_PS_HYSTERESIS" type="a8xx_sp_xs_hysteresis" variants="A8XX-"/> <!-- TODO: unknown bool register at 0xa9aa, likely same as 0xa8c0-0xa8c3 but for FS --> - - - <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? --> @@ -3036,6 +4043,7 @@ by a particular renderpass/blit. must be at least the actual CONSTLEN. </doc> </bitfield> + <bitfield name="ALT_LM_ENCODE" pos="26" type="boolean"/> </reg32> <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"/> @@ -3047,7 +4055,8 @@ by a particular renderpass/blit. <reg32 offset="0xa9bb" name="SP_CS_CONFIG" type="a6xx_sp_xs_config" 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="0xa9be" name="SP_CS_HYSTERESIS" type="a6xx_sp_xs_hysteresis" variants="A6XX-A7XX"/> + <reg32 offset="0xa9be" name="SP_CS_HYSTERESIS" type="a8xx_sp_xs_hysteresis" variants="A8XX-"/> <reg32 offset="0xa9c5" name="SP_CS_VGS_CNTL" variants="A7XX-" usage="cmd"/> <!-- new in a6xx gen4, matches SP_CS_CONST_CONFIG_0 --> @@ -3158,6 +4167,18 @@ by a particular renderpass/blit. <bitfield name="RT7" low="28" high="31"/> </reg32> + <array offset="0xaa04" name="SP_MRT_BLEND_CNTL" stride="1" length="8" variants="A8XX-"> + <reg32 offset="0" name="REG"> + <bitfield name="COLOR_BLEND_EN" pos="0" type="boolean"/> + <bitfield name="ALPHA_BLEND_EN" pos="1" type="boolean"/> + <bitfield name="COMPONENT_WRITE_MASK" low="7" high="10"/> + </reg32> + </array> + + <reg32 offset="0xaa0c" name="SP_ALPHA_TEST_CNTL" variants="A8XX-"> + <bitfield name="ALPHA_TEST" pos="8" type="boolean"/> + </reg32> + <reg32 offset="0xaaf2" name="SP_UNKNOWN_AAF2" type="uint" usage="cmd"/> <!-- @@ -3182,15 +4203,19 @@ by a particular renderpass/blit. --> <bitfield name="CONSTANT_DEMOTION_ENABLE" pos="0" type="boolean"/> <bitfield name="ISAMMODE" low="1" high="2" type="a6xx_isam_mode"/> - <bitfield name="SHARED_CONSTS_ENABLE" pos="3" type="boolean"/> <!-- see HLSQ_SHARED_CONSTS --> + <bitfield name="SHARED_CONSTS_ENABLE" pos="3" type="boolean"/> <!-- see SP_SHARED_CONSTANT --> </reg32> <reg32 offset="0xab01" name="SP_UNKNOWN_AB01" variants="A7XX-" usage="cmd"/> - <reg32 offset="0xab02" name="SP_UNKNOWN_AB02" variants="A7XX-" usage="cmd"/> + <reg32 offset="0xab02" name="SP_HLSQ_MODE_CNTL" variants="A7XX-" usage="cmd"> + <bitfield name="SHARED_CONSTS_ENABLE" pos="0" type="boolean"/> <!-- see SP_SHARED_CONSTANT --> + </reg32> <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"/> + <reg32 offset="0xab06" name="SP_BIN_SIZE" type="a8xx_bin_size" variants="A8XX-" 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"/> @@ -3210,9 +4235,12 @@ by a particular renderpass/blit. --> <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" variants="A6XX-A7XX" usage="cmd"/> + <reg32 offset="0xab09" name="SP_GFX_USIZE" low="0" high="6" type="uint" variants="A8XX-" usage="cmd"/> <reg32 offset="0xab22" name="SP_UNKNOWN_AB22" variants="A7XX" usage="cmd"/> + <reg32 offset="0xab23" name="SP_UNKNOWN_AB23" variants="A8XX-"/> + <enum name="a6xx_sp_a2d_output_ifmt_type"> <value name="OUTPUT_IFMT_2D_FLOAT" value="0"/> <value name="OUTPUT_IFMT_2D_SINT" value="1"/> @@ -3234,22 +4262,27 @@ by a particular renderpass/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"/> + <reg32 offset="0xae00" name="SP_DBG_ECO_CNTL" usage="init"/> + <reg32 offset="0xae01" name="SP_ADDR_MODE_CNTL" pos="0" type="a5xx_address_mode" variants="A6XX"/> + <reg32 offset="0xae01" name="SP_SHADER_PROFILING" variants="A8XX-"/> <reg32 offset="0xae02" name="SP_NC_MODE_CNTL"> <!-- TODO: valid bits 0x3c3f, see kernel --> </reg32> - <reg32 offset="0xae03" name="SP_CHICKEN_BITS" usage="cmd"/> - <reg32 offset="0xae04" name="SP_NC_MODE_CNTL_2" usage="cmd"> + <reg32 offset="0xae03" name="SP_CHICKEN_BITS" usage="init"/> + <reg32 offset="0xae04" name="SP_NC_MODE_CNTL_2" usage="init"> <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_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="0xae05" name="SP_SS_CHICKEN_BITS_0" variants="A8XX-"/> + <reg32 offset="0xae06" name="SP_ISDB_CNTL" variants="A7XX-" usage="init"/> + <reg32 offset="0xae07" name="SP_PERFCTR_CNTL"/> + <reg32 offset="0xae08" name="SP_CHICKEN_BITS_1" variants="A7XX-" usage="init"/> + <reg32 offset="0xae09" name="SP_CHICKEN_BITS_2" variants="A7XX-" usage="init"/> + <reg32 offset="0xae0a" name="SP_CHICKEN_BITS_3" variants="A7XX-" usage="init"/> + <reg32 offset="0xae0b" name="SP_CHICKEN_BITS_4" variants="A8XX-"/> + <reg32 offset="0xae0c" name="SP_STATUS"/> - <reg32 offset="0xae0f" name="SP_PERFCTR_SHADER_MASK" usage="cmd"> + <reg32 offset="0xae0f" name="SP_PERFCTR_SHADER_MASK" usage="init"> <!-- 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 --> @@ -3260,24 +4293,47 @@ by a particular renderpass/blit. <bitfield name="FS" pos="4" type="boolean"/> <bitfield name="CS" pos="5" type="boolean"/> </reg32> - <array offset="0xae10" name="SP_PERFCTR_SP_SEL" stride="1" length="24"/> + <array offset="0xae10" name="SP_PERFCTR_SP_SEL" stride="1" length="24" variants="A6XX"/> <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_HLSQ_DBG_ECO_CNTL" variants="A7XX-" usage="cmd"/> + <reg32 offset="0xae6a" name="SP_UNKNOWN_AE6A" variants="A7XX-" usage="init"/> + <reg32 offset="0xae6b" name="SP_HLSQ_TIMEOUT_THRESHOLD_DP" variants="A7XX-" usage="init"/> + <reg32 offset="0xae6c" name="SP_HLSQ_DBG_ECO_CNTL" variants="A7XX-" usage="init"/> <reg32 offset="0xae6d" name="SP_READ_SEL" variants="A7XX-"> + <bitfield name="CONTEXT" low="26" high="30"/> + <bitfield name="SLICE" low="21" high="25"/> <bitfield name="LOCATION" low="18" high="20" type="a7xx_state_location"/> - <bitfield name="PIPE" low="16" high="17" type="a7xx_pipe"/> + <bitfield name="PIPE" low="16" high="17" type="adreno_pipe"/> <bitfield name="STATETYPE" low="8" high="15" type="a7xx_statetype_id"/> <bitfield name="USPTP" low="4" high="7"/> <bitfield name="SPTP" low="0" high="3"/> </reg32> <reg32 offset="0xae71" name="SP_DBG_CNTL" variants="A7XX-"/> - <reg32 offset="0xae73" name="SP_UNKNOWN_AE73" variants="A7XX-" usage="cmd"/> + <reg32 offset="0xae73" name="SP_HLSQ_DBG_ECO_CNTL_1" variants="A7XX-"/> + <reg32 offset="0xae74" name="SP_HLSQ_DBG_ECO_CNTL_2" variants="A7XX-"/> + <reg32 offset="0xae76" name="SP_HLSQ_DBG_ECO_CNTL_3" variants="A8XX-"/> <array offset="0xae80" name="SP_PERFCTR_SP_SEL" stride="1" length="36" variants="A7XX-"/> <!-- TODO: there are 4 more percntr select registers (0xae28-0xae2b) --> <!-- TODO: there are a few unknown registers in the 0xae30-0xae52 range --> - <reg32 offset="0xbe22" name="SP_CONTEXT_SWITCH_GFX_PREEMPTION_SAFE_MODE"/> + <reg32 offset="0xae52" name="SP_CONTEXT_SWITCH_GFX_PREEMPTION_SAFE_MODE"/> + + <reg64 offset="0xae10" name="SP_HLSQ_GC_GMEM_RANGE_MIN" variants="A8XX-"/> + <reg64 offset="0xae12" name="SP_HLSQ_LPAC_GMEM_RANGE_MIN" variants="A8XX-"/> + <reg32 offset="0xae15" name="SP_LPAC_CPI_STATUS" variants="A8XX-"/> + <reg32 offset="0xae16" name="SP_LPAC_DBG_STATUS" variants="A8XX-"/> + <reg32 offset="0xae17" name="SP_LPAC_ISDB_BATCH_COUNT" variants="A8XX-"/> + <reg32 offset="0xae18" name="SP_LPAC_ISDB_BATCH_COUNT_INCR_EN" variants="A8XX-"/> + <reg32 offset="0xae19" name="SP_LPAC_ISDB_BATCH_COUNT_SHADERS" variants="A8XX-"/> + <reg32 offset="0xae30" name="SP_ISDB_BATCH_COUNT" variants="A7XX-"/> + <reg32 offset="0xae31" name="SP_ISDB_BATCH_COUNT_INCR_EN" variants="A7XX-"/> + <reg32 offset="0xae32" name="SP_ISDB_BATCH_COUNT_SHADERS" variants="A7XX-"/> + <reg32 offset="0xae35" name="SP_ISDB_DEBUG_CONFIG" variants="A7XX-"/> + + <reg32 offset="0xae3a" name="SP_SELF_THROTTLE_CONTROL" variants="A7XX-"/> + <reg32 offset="0xae3b" name="SP_DISPATCH_CNTL" variants="A7XX-"/> + <reg64 offset="0xae3c" name="SP_SW_DEBUG_ADDR" variants="A7XX-"/> + <reg64 offset="0xae3e" name="SP_ISDB_DEBUG_ADDR" variants="A7XX-"/> + + <array offset="0xaec0" name="SP_PERFCTR_HLSQ_SEL_2_0" stride="1" length="6" variants="A7XX-"/> <!-- The downstream kernel calls the debug cluster of registers @@ -3285,12 +4341,15 @@ by a particular renderpass/blit. color base for compute shaders. --> <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="0xb182" name="TPL1_PS_ROTATION_CNTL" low="0" high="2" usage="cmd"/> + <reg32 offset="0xb183" name="TPL1_PS_SWIZZLE_CNTL" low="0" high="23" usage="cmd"/> <reg32 offset="0xb190" name="SP_UNKNOWN_B190"/> <reg32 offset="0xb191" name="SP_UNKNOWN_B191"/> + <reg32 offset="0xb2d6" name="TPL1_A2D_BIN_SIZE" type="a8xx_bin_size" variants="A8XX-" usage="rp_blit"/> + <reg32 offset="0xb2d7" name="TPL1_A2D_FILTER_CNTL" variants="A8XX-" 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"/> @@ -3303,10 +4362,12 @@ by a particular renderpass/blit. <!-- looks to work in the same way as a5xx: --> <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" variants="A6XX-A7XX" 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="0xb305" name="TPL1_PROGRAMMABLE_MSAA_POS_0" type="a6xx_programmable_msaa_pos" usage="rp_blit" variants="A6XX-A7XX" /> + <reg32 offset="0xb306" name="TPL1_PROGRAMMABLE_MSAA_POS_1" type="a6xx_programmable_msaa_pos" usage="rp_blit" variants="A6XX-A7XX" /> <reg32 offset="0xb307" name="TPL1_WINDOW_OFFSET" type="a6xx_reg_xy" usage="rp_blit"/> + <reg32 offset="0xb304" name="TPL1_BIN_SIZE" type="a8xx_bin_size" variants="A8XX-" usage="rp_blit"/> + <enum name="a6xx_coord_round"> <value value="0" name="COORD_TRUNCATE"/> <value value="1" name="COORD_ROUND_NEAREST_EVEN"/> @@ -3315,13 +4376,17 @@ by a particular renderpass/blit. <enum name="a6xx_nearest_mode"> <value value="0" name="ROUND_CLAMP_TRUNCATE"/> <value value="1" name="CLAMP_ROUND_TRUNCATE"/> + <value value="2" name="ROUND_FLOAT_TO_INT"/> <!-- only ARRAYCOORDROUNDMODE --> </enum> <reg32 offset="0xb309" name="TPL1_MODE_CNTL" usage="cmd"> <bitfield name="ISAMMODE" low="0" high="1" type="a6xx_isam_mode"/> <bitfield name="TEXCOORDROUNDMODE" pos="2" type="a6xx_coord_round"/> + <bitfield name="ARRAYCOORDROUNDMODE" low="3" high="4" type="a6xx_coord_round"/> <bitfield name="NEARESTMIPSNAP" pos="5" type="a6xx_nearest_mode"/> + <bitfield name="SAMPLEREPLICATE" pos="6" type="boolean"/> <bitfield name="DESTDATATYPEOVERRIDE" pos="7" type="boolean"/> + <bitfield name="PACK_SAMP_REDUCED_PRECISION" pos="8" type="boolean"/> </reg32> <reg32 offset="0xb310" name="SP_UNKNOWN_B310" variants="A7XX-" usage="cmd"/> @@ -3387,11 +4452,12 @@ by a particular renderpass/blit. <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"/> + <reg32 offset="0xab07" name="SP_WINDOW_OFFSET" type="a6xx_reg_xy" variants="A8XX-" usage="rp_blit"/> <!-- always 0x100000 or 0x1000000? --> - <reg32 offset="0xb600" name="TPL1_DBG_ECO_CNTL" low="0" high="25" usage="cmd"/> - <reg32 offset="0xb601" name="TPL1_ADDR_MODE_CNTL" type="a5xx_address_mode"/> - <reg32 offset="0xb602" name="TPL1_DBG_ECO_CNTL1" usage="cmd"> + <reg32 offset="0xb600" name="TPL1_DBG_ECO_CNTL" low="0" high="25" usage="init"/> + <reg32 offset="0xb601" name="TPL1_ADDR_MODE_CNTL" type="a5xx_address_mode" variants="A6XX"/> + <reg32 offset="0xb602" name="TPL1_DBG_ECO_CNTL1" usage="init"> <!-- Affects UBWC in some way, if BLIT_OP_SCALE is done with this bit set and if other blit is done without it - UBWC image may be copied incorrectly. --> @@ -3404,7 +4470,7 @@ by a particular renderpass/blit. <bitfield name="UPPER_BIT" pos="4" type="uint"/> <bitfield name="UNK6" low="6" high="7"/> </reg32> - <reg32 offset="0xb605" name="TPL1_UNKNOWN_B605" low="0" high="7" type="uint" variants="A6XX" usage="cmd"/> <!-- always 0x0 or 0x44 ? --> + <reg32 offset="0xb605" name="TPL1_UNKNOWN_B605" low="0" high="7" type="uint" variants="A6XX" usage="init"/> <!-- always 0x0 or 0x44 ? --> <array offset="0xb608" name="TPL1_BICUBIC_WEIGHTS_TABLE" stride="1" length="5" variants="A6XX"> <reg32 offset="0" name="REG" low="0" high="29"/> @@ -3414,8 +4480,13 @@ by a particular renderpass/blit. <reg32 offset="0" name="REG" low="0" high="29" usage="cmd"/> </array> + <array offset="0xb606" name="TPL1_BICUBIC_WEIGHTS_TABLE" stride="1" length="25" variants="A8XX"> + <reg32 offset="0" name="REG" low="0" high="29"/> + </array> + <array offset="0xb610" name="TPL1_PERFCTR_TP_SEL" stride="1" length="12" variants="A6XX"/> <array offset="0xb610" name="TPL1_PERFCTR_TP_SEL" stride="1" length="18" variants="A7XX"/> + <array offset="0xb620" name="TPL1_PERFCTR_TP_SEL" stride="1" length="20" variants="A8XX"/> <!-- TODO: 4 more perfcntr sel at 0xb620 ? --> @@ -3458,10 +4529,8 @@ by a particular renderpass/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"/> - <!-- UNK9 is set on a750 --> - <bitfield name="UNK9" pos="9" type="boolean"/> + <bitfield name="DEFER_WAVE_ALLOC_DIS" pos="8" type="boolean"/> + <bitfield name="EVICT_BUF_MODE" low="9" high="10"/> </reg32> <reg32 offset="0xb820" name="HLSQ_LOAD_STATE_GEOM_CMD"/> @@ -3512,9 +4581,12 @@ by a particular renderpass/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="0xa9c6" type="a6xx_sp_ps_wave_cntl" name="SP_PS_WAVE_CNTL" variants="A7XX" usage="rp_blit"/> + <reg32 offset="0xa9c6" name="SP_PS_WAVE_CNTL" variants="A8XX-" usage="rp_blit"> + <bitfield name="VARYINGS" pos="1" type="boolean"/> + </reg32> <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"/> + <bitfield name="PRIMALLOCTHRESHOLD" low="0" high="2" type="uint"/> </reg32> <reg32 offset="0xa9c8" name="SP_REG_PROG_ID_0" variants="A7XX-" usage="rp_blit"> <bitfield name="FACEREGID" low="0" high="7" type="a3xx_regid"/> @@ -3718,7 +4790,7 @@ by a particular renderpass/blit. <bitfield name="EVENT" low="0" high="6" type="vgt_event_type"/> </reg32> - <reg32 offset="0xab1f" name="SP_UPDATE_CNTL" 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 @@ -3741,10 +4813,30 @@ by a particular renderpass/blit. <bitfield name="GFX_BINDLESS" low="17" high="24" type="hex"/> </reg32> + <reg32 offset="0xab1f" name="SP_UPDATE_CNTL" variants="A8XX" usage="cmd"> + <doc> + This register clears pending loads queued up by + CP_LOAD_STATE6. Each bit resets a particular kind(s) of + CP_LOAD_STATE6. + </doc> + + <!-- per-stage state: shader, non-bindless UBO, textures, and samplers --> + <bitfield name="VS_STATE" pos="0" type="boolean"/> + <bitfield name="HS_STATE" pos="1" type="boolean"/> + <bitfield name="DS_STATE" pos="2" type="boolean"/> + <bitfield name="GS_STATE" pos="3" type="boolean"/> + <bitfield name="FS_STATE" pos="4" type="boolean"/> + <bitfield name="CS_STATE" pos="5" type="boolean"/> + </reg32> + + <reg32 offset="0xa9c0" name="SP_CS_BINDLESS_INVALIDATE"/> + <reg32 offset="0xab08" name="SP_GFX_BINDLESS_INVALIDATE"/> + <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="SP_SHARED_CONSTANT_GFX" stride="1" length="64" variants="A7XX"/> + <array offset="0xab30" name="SP_SHARED_CONSTANT_GFX" stride="1" length="128" variants="A8XX-"/> <reg32 offset="0xbb11" name="HLSQ_SHARED_CONSTS" variants="A6XX" usage="cmd"> <doc> @@ -3781,15 +4873,15 @@ by a particular renderpass/blit. <bitfield name="EVENT" low="0" high="6" type="vgt_event_type"/> </reg32> - <reg32 offset="0xbe00" name="HLSQ_UNKNOWN_BE00" variants="A6XX" usage="cmd"/> <!-- all bits valid except bit 29 --> - <reg32 offset="0xbe01" name="HLSQ_UNKNOWN_BE01" low="4" high="6" variants="A6XX" usage="cmd"/> - <reg32 offset="0xbe04" name="HLSQ_DBG_ECO_CNTL" variants="A6XX" usage="cmd"/> - <reg32 offset="0xbe05" name="HLSQ_ADDR_MODE_CNTL" type="a5xx_address_mode"/> + <reg32 offset="0xbe00" name="HLSQ_UNKNOWN_BE00" variants="A6XX" usage="init"/> <!-- all bits valid except bit 29 --> + <reg32 offset="0xbe01" name="HLSQ_UNKNOWN_BE01" low="4" high="6" variants="A6XX" usage="init"/> + <reg32 offset="0xbe04" name="HLSQ_DBG_ECO_CNTL" variants="A6XX" usage="init"/> + <reg32 offset="0xbe05" name="HLSQ_ADDR_MODE_CNTL" type="a5xx_address_mode" variants="A6XX"/> <reg32 offset="0xbe08" name="HLSQ_UNKNOWN_BE08" low="0" high="15"/> <array offset="0xbe10" name="HLSQ_PERFCTR_HLSQ_SEL" stride="1" length="6"/> <!-- TODO: some valid registers between 0xbe20 and 0xbe33 --> - <reg32 offset="0xbe22" name="HLSQ_CONTEXT_SWITCH_GFX_PREEMPTION_SAFE_MODE"/> + <reg32 offset="0xbe22" name="HLSQ_CONTEXT_SWITCH_GFX_PREEMPTION_SAFE_MODE" variants="A6XX"/> <reg32 offset="0xc000" name="SP_AHB_READ_APERTURE" variants="A7XX-"/> @@ -3918,6 +5010,7 @@ by a particular renderpass/blit. <reg32 offset="0x0001" name="SYSTEM_CACHE_CNTL_0"/> <reg32 offset="0x0002" name="SYSTEM_CACHE_CNTL_1"/> <reg32 offset="0x0039" name="CX_MISC_TCM_RET_CNTL" variants="A7XX-"/> + <reg32 offset="0x0087" name="CX_MISC_SLICE_ENABLE_FINAL" variants="A8XX"/> <reg32 offset="0x0400" name="CX_MISC_SW_FUSE_VALUE" variants="A7XX-"> <bitfield pos="0" name="FASTBLEND" type="boolean"/> <bitfield pos="1" name="LPAC" type="boolean"/> diff --git a/drivers/gpu/drm/msm/registers/adreno/a6xx_enums.xml b/drivers/gpu/drm/msm/registers/adreno/a6xx_enums.xml index 4e42f055b85f..81538831dc19 100644 --- a/drivers/gpu/drm/msm/registers/adreno/a6xx_enums.xml +++ b/drivers/gpu/drm/msm/registers/adreno/a6xx_enums.xml @@ -303,7 +303,7 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> </enum> <!-- -Used in a6xx_a2d_bit_cntl.. the value mostly seems to correlate to the +Used in a6xx_a2d_blt_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 diff --git a/drivers/gpu/drm/msm/registers/adreno/a6xx_gmu.xml b/drivers/gpu/drm/msm/registers/adreno/a6xx_gmu.xml index b15a242d974d..c4e00b1263cd 100644 --- a/drivers/gpu/drm/msm/registers/adreno/a6xx_gmu.xml +++ b/drivers/gpu/drm/msm/registers/adreno/a6xx_gmu.xml @@ -40,56 +40,62 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <bitfield name="IRQ_MASK_BIT" pos="0" /> </bitset> - <reg32 offset="0x80" name="GPU_GMU_GX_SPTPRAC_CLOCK_CONTROL"/> - <reg32 offset="0x81" name="GMU_GX_SPTPRAC_POWER_CONTROL"/> - <reg32 offset="0xc00" name="GMU_CM3_ITCM_START"/> - <reg32 offset="0x1c00" name="GMU_CM3_DTCM_START"/> - <reg32 offset="0x23f0" name="GMU_NMI_CONTROL_STATUS"/> - <reg32 offset="0x23f8" name="GMU_BOOT_SLUMBER_OPTION"/> - <reg32 offset="0x23f9" name="GMU_GX_VOTE_IDX"/> - <reg32 offset="0x23fa" name="GMU_MX_VOTE_IDX"/> - <reg32 offset="0x23fc" name="GMU_DCVS_ACK_OPTION"/> - <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"> + <reg32 offset="0x1a880" name="GPU_GMU_GX_SPTPRAC_CLOCK_CONTROL"/> + <reg32 offset="0x1a881" name="GMU_GX_SPTPRAC_POWER_CONTROL"/> + <reg32 offset="0x1b400" name="GMU_CM3_ITCM_START"/> + <reg32 offset="0x1c400" name="GMU_CM3_DTCM_START"/> + <reg32 offset="0x1cbf0" name="GMU_NMI_CONTROL_STATUS"/> + <reg32 offset="0x1cbf8" name="GMU_BOOT_SLUMBER_OPTION"/> + <reg32 offset="0x1cbf9" name="GMU_GX_VOTE_IDX"/> + <reg32 offset="0x1cbfa" name="GMU_MX_VOTE_IDX"/> + <reg32 offset="0x1cbfc" name="GMU_DCVS_ACK_OPTION"/> + <reg32 offset="0x1cbfd" name="GMU_DCVS_PERF_SETTING"/> + <reg32 offset="0x1cbfe" name="GMU_DCVS_BW_SETTING"/> + <reg32 offset="0x1cbff" name="GMU_DCVS_RETURN"/> + <reg32 offset="0x1d3f8" 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"/> - <reg32 offset="0x5000" name="GMU_CM3_SYSRESET"/> - <reg32 offset="0x5001" name="GMU_CM3_BOOT_CONFIG"/> - <reg32 offset="0x501a" name="GMU_CM3_FW_BUSY"/> - <reg32 offset="0x501c" name="GMU_CM3_FW_INIT_RESULT"/> - <reg32 offset="0x502d" name="GMU_CM3_CFG"/> - <reg32 offset="0x5040" name="GMU_CX_GMU_POWER_COUNTER_ENABLE"/> - <reg32 offset="0x5041" name="GMU_CX_GMU_POWER_COUNTER_SELECT_0"/> - <reg32 offset="0x5042" name="GMU_CX_GMU_POWER_COUNTER_SELECT_1"/> - <reg32 offset="0x5044" name="GMU_CX_GMU_POWER_COUNTER_XOCLK_0_L"/> - <reg32 offset="0x5045" name="GMU_CX_GMU_POWER_COUNTER_XOCLK_0_H"/> - <reg32 offset="0x5046" name="GMU_CX_GMU_POWER_COUNTER_XOCLK_1_L"/> - <reg32 offset="0x5047" name="GMU_CX_GMU_POWER_COUNTER_XOCLK_1_H"/> - <reg32 offset="0x5048" name="GMU_CX_GMU_POWER_COUNTER_XOCLK_2_L"/> - <reg32 offset="0x5049" name="GMU_CX_GMU_POWER_COUNTER_XOCLK_2_H"/> - <reg32 offset="0x504a" name="GMU_CX_GMU_POWER_COUNTER_XOCLK_3_L"/> - <reg32 offset="0x504b" name="GMU_CX_GMU_POWER_COUNTER_XOCLK_3_H"/> - <reg32 offset="0x504c" name="GMU_CX_GMU_POWER_COUNTER_XOCLK_4_L"/> - <reg32 offset="0x504d" name="GMU_CX_GMU_POWER_COUNTER_XOCLK_4_H"/> - <reg32 offset="0x504e" name="GMU_CX_GMU_POWER_COUNTER_XOCLK_5_L"/> - <reg32 offset="0x504f" name="GMU_CX_GMU_POWER_COUNTER_XOCLK_5_H"/> - <reg32 offset="0x50c0" name="GMU_PWR_COL_INTER_FRAME_CTRL"> + <reg32 offset="0x1f400" name="GMU_ICACHE_CONFIG"/> + <reg32 offset="0x1f401" name="GMU_DCACHE_CONFIG"/> + <reg32 offset="0x1f40f" name="GMU_SYS_BUS_CONFIG"/> + <reg32 offset="0x1f50b" name="GMU_MRC_GBIF_QOS_CTRL"/> + <reg32 offset="0x1f800" name="GMU_CM3_SYSRESET"/> + <reg32 offset="0x1f801" name="GMU_CM3_BOOT_CONFIG"/> + <reg32 offset="0x1f81a" name="GMU_CM3_FW_BUSY"/> + <reg32 offset="0x1f81c" name="GMU_CM3_FW_INIT_RESULT"/> + <reg32 offset="0x1f82d" name="GMU_CM3_CFG"/> + <reg32 offset="0x1f840" name="GMU_CX_GMU_POWER_COUNTER_ENABLE"/> + <reg32 offset="0x1fc10" name="GMU_CX_GMU_POWER_COUNTER_ENABLE" variants="A8XX"/> + <reg32 offset="0x1f841" name="GMU_CX_GMU_POWER_COUNTER_SELECT_0"/> + <reg32 offset="0x1f842" name="GMU_CX_GMU_POWER_COUNTER_SELECT_1"/> + <reg32 offset="0x1fc40" name="GMU_CX_GMU_POWER_COUNTER_SELECT_XOCLK_0" variants="A8XX-"/> + <reg32 offset="0x1fc41" name="GMU_CX_GMU_POWER_COUNTER_SELECT_XOCLK_1" variants="A8XX-"/> + <reg32 offset="0x1f844" name="GMU_CX_GMU_POWER_COUNTER_XOCLK_0_L"/> + <reg32 offset="0x1fca0" name="GMU_CX_GMU_POWER_COUNTER_XOCLK_0_L" variants="A8XX-"/> + <reg32 offset="0x1f845" name="GMU_CX_GMU_POWER_COUNTER_XOCLK_0_H"/> + <reg32 offset="0x1fca1" name="GMU_CX_GMU_POWER_COUNTER_XOCLK_0_H" variants="A8XX-"/> + <reg32 offset="0x1f846" name="GMU_CX_GMU_POWER_COUNTER_XOCLK_1_L"/> + <reg32 offset="0x1f847" name="GMU_CX_GMU_POWER_COUNTER_XOCLK_1_H"/> + <reg32 offset="0x1f848" name="GMU_CX_GMU_POWER_COUNTER_XOCLK_2_L"/> + <reg32 offset="0x1f849" name="GMU_CX_GMU_POWER_COUNTER_XOCLK_2_H"/> + <reg32 offset="0x1f84a" name="GMU_CX_GMU_POWER_COUNTER_XOCLK_3_L"/> + <reg32 offset="0x1f84b" name="GMU_CX_GMU_POWER_COUNTER_XOCLK_3_H"/> + <reg32 offset="0x1f84c" name="GMU_CX_GMU_POWER_COUNTER_XOCLK_4_L"/> + <reg32 offset="0x1f84d" name="GMU_CX_GMU_POWER_COUNTER_XOCLK_4_H"/> + <reg32 offset="0x1f84e" name="GMU_CX_GMU_POWER_COUNTER_XOCLK_5_L"/> + <reg32 offset="0x1f84f" name="GMU_CX_GMU_POWER_COUNTER_XOCLK_5_H"/> + <reg32 offset="0x1f8c0" name="GMU_PWR_COL_INTER_FRAME_CTRL"> <bitfield name="IFPC_ENABLE" pos="0" type="boolean"/> <bitfield name="HM_POWER_COLLAPSE_ENABLE" pos="1" type="boolean"/> <bitfield name="SPTPRAC_POWER_CONTROL_ENABLE" pos="2" type="boolean"/> <bitfield name="NUM_PASS_SKIPS" low="10" high="13"/> <bitfield name="MIN_PASS_LENGTH" low="14" high="31"/> </reg32> - <reg32 offset="0x50c1" name="GMU_PWR_COL_INTER_FRAME_HYST"/> - <reg32 offset="0x50c2" name="GMU_PWR_COL_SPTPRAC_HYST"/> - <reg32 offset="0x50d0" name="GMU_SPTPRAC_PWR_CLK_STATUS"> + <reg32 offset="0x1f8c1" name="GMU_PWR_COL_INTER_FRAME_HYST"/> + <reg32 offset="0x1f8c2" name="GMU_PWR_COL_SPTPRAC_HYST"/> + <reg32 offset="0x1f8d0" name="GMU_SPTPRAC_PWR_CLK_STATUS" variants="A6XX"> <bitfield name="SPTPRAC_GDSC_POWERING_OFF" pos="0" type="boolean"/> <bitfield name="SPTPRAC_GDSC_POWERING_ON" pos="1" type="boolean"/> <bitfield name="SPTPRAC_GDSC_POWER_OFF" pos="2" type="boolean"/> @@ -99,15 +105,19 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <bitfield name="GX_HM_GDSC_POWER_OFF" pos="6" type="boolean"/> <bitfield name="GX_HM_CLK_OFF" pos="7" type="boolean"/> </reg32> - <reg32 offset="0x50d0" name="GMU_SPTPRAC_PWR_CLK_STATUS" variants="A7XX"> + <reg32 offset="0x1f8d0" name="GMU_SPTPRAC_PWR_CLK_STATUS" variants="A7XX"> <bitfield name="GX_HM_GDSC_POWER_OFF" pos="0" type="boolean"/> <bitfield name="GX_HM_CLK_OFF" pos="1" type="boolean"/> </reg32> - <reg32 offset="0x50e4" name="GMU_GPU_NAP_CTRL"> + <reg32 offset="0x1f7e8" name="GMU_PWR_CLK_STATUS" variants="A8XX-"> + <bitfield name="GX_HM_GDSC_POWER_OFF" pos="0" type="boolean"/> + <bitfield name="GX_HM_CLK_OFF" pos="1" type="boolean"/> + </reg32> + <reg32 offset="0x1f8e4" name="GMU_GPU_NAP_CTRL"> <bitfield name="HW_NAP_ENABLE" pos="0"/> <bitfield name="SID" low="4" high="8"/> </reg32> - <reg32 offset="0x50e8" name="GMU_RPMH_CTRL"> + <reg32 offset="0x1f8e8" name="GMU_RPMH_CTRL"> <bitfield name="RPMH_INTERFACE_ENABLE" pos="0" type="boolean"/> <bitfield name="LLC_VOTE_ENABLE" pos="4" type="boolean"/> <bitfield name="DDR_VOTE_ENABLE" pos="8" type="boolean"/> @@ -119,71 +129,84 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <bitfield name="CX_MIN_VOTE_ENABLE" pos="14" type="boolean"/> <bitfield name="GFX_MIN_VOTE_ENABLE" pos="15" type="boolean"/> </reg32> - <reg32 offset="0x50e9" name="GMU_RPMH_HYST_CTRL"/> - <reg32 offset="0x50ec" name="GPU_GMU_CX_GMU_RPMH_POWER_STATE"/> - <reg32 offset="0x50f0" name="GPU_GMU_CX_GMU_CX_FAL_INTF"/> - <reg32 offset="0x50f1" name="GPU_GMU_CX_GMU_CX_FALNEXT_INTF"/> - <reg32 offset="0x5100" name="GPU_GMU_CX_GMU_PWR_COL_CP_MSG"/> - <reg32 offset="0x5101" name="GPU_GMU_CX_GMU_PWR_COL_CP_RESP"/> - <reg32 offset="0x51f0" name="GMU_BOOT_KMD_LM_HANDSHAKE"/> - <reg32 offset="0x5157" name="GMU_LLM_GLM_SLEEP_CTRL"/> - <reg32 offset="0x5158" name="GMU_LLM_GLM_SLEEP_STATUS"/> - <reg32 offset="0x5088" name="GMU_ALWAYS_ON_COUNTER_L"/> - <reg32 offset="0x5089" name="GMU_ALWAYS_ON_COUNTER_H"/> - <reg32 offset="0x50c3" name="GMU_GMU_PWR_COL_KEEPALIVE"/> - <reg32 offset="0x50c4" name="GMU_PWR_COL_PREEMPT_KEEPALIVE"/> - <reg32 offset="0x5180" name="GMU_HFI_CTRL_STATUS"/> - <reg32 offset="0x5181" name="GMU_HFI_VERSION_INFO"/> - <reg32 offset="0x5182" name="GMU_HFI_SFR_ADDR"/> - <reg32 offset="0x5183" name="GMU_HFI_MMAP_ADDR"/> - <reg32 offset="0x5184" name="GMU_HFI_QTBL_INFO"/> - <reg32 offset="0x5185" name="GMU_HFI_QTBL_ADDR"/> - <reg32 offset="0x5186" name="GMU_HFI_CTRL_INIT"/> - <reg32 offset="0x5190" name="GMU_GMU2HOST_INTR_SET"/> - <reg32 offset="0x5191" name="GMU_GMU2HOST_INTR_CLR"/> - <reg32 offset="0x5192" name="GMU_GMU2HOST_INTR_INFO"> + <reg32 offset="0x1f8e9" name="GMU_RPMH_HYST_CTRL"/> + <reg32 offset="0x1f8ec" name="GPU_GMU_CX_GMU_RPMH_POWER_STATE" variants="A6XX"/> + <reg32 offset="0x1f7e9" name="GPU_GMU_CX_GMU_RPMH_POWER_STATE" variants="A8XX-"/> + <reg32 offset="0x1f8f0" name="GPU_GMU_CX_GMU_CX_FAL_INTF" variants="A6XX"/> + <reg32 offset="0x1f7ec" name="GPU_GMU_CX_GMU_CX_FAL_INTF" variants="A8XX-"/> + <reg32 offset="0x1f8f1" name="GPU_GMU_CX_GMU_CX_FALNEXT_INTF" variants="A6XX"/> + <reg32 offset="0x1f7ed" name="GPU_GMU_CX_GMU_CX_FALNEXT_INTF" variants="A8XX-"/> + <reg32 offset="0x1f900" name="GPU_GMU_CX_GMU_PWR_COL_CP_MSG"/> + <reg32 offset="0x1f901" name="GPU_GMU_CX_GMU_PWR_COL_CP_RESP"/> + <reg32 offset="0x1f9f0" name="GMU_BOOT_KMD_LM_HANDSHAKE"/> + <reg32 offset="0x1f957" name="GMU_LLM_GLM_SLEEP_CTRL"/> + <reg32 offset="0x1f958" name="GMU_LLM_GLM_SLEEP_STATUS"/> + <reg32 offset="0x1f888" name="GMU_ALWAYS_ON_COUNTER_L"/> + <reg32 offset="0x1f889" name="GMU_ALWAYS_ON_COUNTER_H"/> + <reg32 offset="0x1f8c3" name="GMU_GMU_PWR_COL_KEEPALIVE" variants="A6XX-A7XX"/> + <reg32 offset="0x1f7e4" name="GMU_GMU_PWR_COL_KEEPALIVE" variants="A8XX-"/> + <reg32 offset="0x1f8c4" name="GMU_PWR_COL_PREEMPT_KEEPALIVE" variants="A6XX-A7XX"/> + <reg32 offset="0x1f7e5" name="GMU_PWR_COL_PREEMPT_KEEPALIVE" variants="A8XX-"/> + <reg32 offset="0x1f980" name="GMU_HFI_CTRL_STATUS"/> + <reg32 offset="0x1f981" name="GMU_HFI_VERSION_INFO"/> + <reg32 offset="0x1f982" name="GMU_HFI_SFR_ADDR"/> + <reg32 offset="0x1f983" name="GMU_HFI_MMAP_ADDR"/> + <reg32 offset="0x1f984" name="GMU_HFI_QTBL_INFO"/> + <reg32 offset="0x1f985" name="GMU_HFI_QTBL_ADDR"/> + <reg32 offset="0x1f986" name="GMU_HFI_CTRL_INIT"/> + <reg32 offset="0x1f990" name="GMU_GMU2HOST_INTR_SET"/> + <reg32 offset="0x1f991" name="GMU_GMU2HOST_INTR_CLR"/> + <reg32 offset="0x1f992" name="GMU_GMU2HOST_INTR_INFO"> <bitfield name="MSGQ" pos="0" type="boolean"/> <bitfield name="CM3_FAULT" pos="23" type="boolean"/> </reg32> - <reg32 offset="0x5193" name="GMU_GMU2HOST_INTR_MASK"/> - <reg32 offset="0x5194" name="GMU_HOST2GMU_INTR_SET"/> - <reg32 offset="0x5195" name="GMU_HOST2GMU_INTR_CLR"/> - <reg32 offset="0x5196" name="GMU_HOST2GMU_INTR_RAW_INFO"/> - <reg32 offset="0x5197" name="GMU_HOST2GMU_INTR_EN_0"/> - <reg32 offset="0x5198" name="GMU_HOST2GMU_INTR_EN_1"/> - <reg32 offset="0x5199" name="GMU_HOST2GMU_INTR_EN_2"/> - <reg32 offset="0x519a" name="GMU_HOST2GMU_INTR_EN_3"/> - <reg32 offset="0x519b" name="GMU_HOST2GMU_INTR_INFO_0"/> - <reg32 offset="0x519c" name="GMU_HOST2GMU_INTR_INFO_1"/> - <reg32 offset="0x519d" name="GMU_HOST2GMU_INTR_INFO_2"/> - <reg32 offset="0x519e" name="GMU_HOST2GMU_INTR_INFO_3"/> - <reg32 offset="0x51c5" name="GMU_GENERAL_0"/> - <reg32 offset="0x51c6" name="GMU_GENERAL_1"/> - <reg32 offset="0x51cb" name="GMU_GENERAL_6"/> - <reg32 offset="0x51cc" name="GMU_GENERAL_7"/> - <reg32 offset="0x51cd" name="GMU_GENERAL_8" variants="A7XX"/> - <reg32 offset="0x51ce" name="GMU_GENERAL_9" variants="A7XX"/> - <reg32 offset="0x51cf" name="GMU_GENERAL_10" variants="A7XX"/> - <reg32 offset="0x515d" name="GMU_ISENSE_CTRL"/> - <reg32 offset="0x8920" name="GPU_CS_ENABLE_REG"/> - <reg32 offset="0x515d" name="GPU_GMU_CX_GMU_ISENSE_CTRL"/> - <reg32 offset="0x8578" name="GPU_CS_AMP_CALIBRATION_CONTROL3"/> - <reg32 offset="0x8558" name="GPU_CS_AMP_CALIBRATION_CONTROL2"/> - <reg32 offset="0x8580" name="GPU_CS_A_SENSOR_CTRL_0"/> - <reg32 offset="0x27ada" name="GPU_CS_A_SENSOR_CTRL_2"/> - <reg32 offset="0x881a" name="GPU_CS_SENSOR_GENERAL_STATUS"/> - <reg32 offset="0x8957" name="GPU_CS_AMP_CALIBRATION_CONTROL1"/> - <reg32 offset="0x881a" name="GPU_CS_SENSOR_GENERAL_STATUS"/> - <reg32 offset="0x881d" name="GPU_CS_AMP_CALIBRATION_STATUS1_0"/> - <reg32 offset="0x881f" name="GPU_CS_AMP_CALIBRATION_STATUS1_2"/> - <reg32 offset="0x8821" name="GPU_CS_AMP_CALIBRATION_STATUS1_4"/> - <reg32 offset="0x8965" name="GPU_CS_AMP_CALIBRATION_DONE"/> - <reg32 offset="0x896d" name="GPU_CS_AMP_PERIOD_CTRL"/> - <reg32 offset="0x8965" name="GPU_CS_AMP_CALIBRATION_DONE"/> - <reg32 offset="0x514d" name="GPU_GMU_CX_GMU_PWR_THRESHOLD"/> - <reg32 offset="0x9303" name="GMU_AO_INTERRUPT_EN"/> - <reg32 offset="0x9304" name="GMU_AO_HOST_INTERRUPT_CLR"/> - <reg32 offset="0x9305" name="GMU_AO_HOST_INTERRUPT_STATUS"> + <reg32 offset="0x1f993" name="GMU_GMU2HOST_INTR_MASK"/> + <reg32 offset="0x1f994" name="GMU_HOST2GMU_INTR_SET"/> + <reg32 offset="0x1f995" name="GMU_HOST2GMU_INTR_CLR"/> + <reg32 offset="0x1f996" name="GMU_HOST2GMU_INTR_RAW_INFO"/> + <reg32 offset="0x1f997" name="GMU_HOST2GMU_INTR_EN_0"/> + <reg32 offset="0x1f998" name="GMU_HOST2GMU_INTR_EN_1"/> + <reg32 offset="0x1f999" name="GMU_HOST2GMU_INTR_EN_2"/> + <reg32 offset="0x1f99a" name="GMU_HOST2GMU_INTR_EN_3"/> + <reg32 offset="0x1f99b" name="GMU_HOST2GMU_INTR_INFO_0"/> + <reg32 offset="0x1f99c" name="GMU_HOST2GMU_INTR_INFO_1"/> + <reg32 offset="0x1f99d" name="GMU_HOST2GMU_INTR_INFO_2"/> + <reg32 offset="0x1f99e" name="GMU_HOST2GMU_INTR_INFO_3"/> + <reg32 offset="0x1f9c5" name="GMU_GENERAL_0"/> + <reg32 offset="0x1f9c6" name="GMU_GENERAL_1"/> + <reg32 offset="0x1f9cb" name="GMU_GENERAL_6"/> + <reg32 offset="0x1f9cc" name="GMU_GENERAL_7"/> + <reg32 offset="0x1f9cd" name="GMU_GENERAL_8" variants="A7XX"/> + <reg32 offset="0x1f9ce" name="GMU_GENERAL_9" variants="A7XX"/> + <reg32 offset="0x1f9cf" name="GMU_GENERAL_10" variants="A7XX"/> + <reg32 offset="0x1f9c0" name="GMU_GENERAL_0" variants="A8XX"/> + <reg32 offset="0x1f9c1" name="GMU_GENERAL_1" variants="A8XX"/> + <reg32 offset="0x1f9c6" name="GMU_GENERAL_6" variants="A8XX"/> + <reg32 offset="0x1f9c7" name="GMU_GENERAL_7" variants="A8XX"/> + <reg32 offset="0x1f9c8" name="GMU_GENERAL_8" variants="A8XX"/> + <reg32 offset="0x1f9c9" name="GMU_GENERAL_9" variants="A8XX"/> + <reg32 offset="0x1f9ca" name="GMU_GENERAL_10" variants="A8XX"/> + <reg32 offset="0x1f9cb" name="GMU_GENERAL_11" variants="A8XX"/> + <reg32 offset="0x1f95d" name="GMU_ISENSE_CTRL"/> + <reg32 offset="0x23120" name="GPU_CS_ENABLE_REG"/> + <reg32 offset="0x1f95d" name="GPU_GMU_CX_GMU_ISENSE_CTRL"/> + <reg32 offset="0x22d78" name="GPU_CS_AMP_CALIBRATION_CONTROL3"/> + <reg32 offset="0x22d58" name="GPU_CS_AMP_CALIBRATION_CONTROL2"/> + <reg32 offset="0x22d80" name="GPU_CS_A_SENSOR_CTRL_0"/> + <reg32 offset="0x422da" name="GPU_CS_A_SENSOR_CTRL_2"/> + <reg32 offset="0x2301a" name="GPU_CS_SENSOR_GENERAL_STATUS"/> + <reg32 offset="0x23157" name="GPU_CS_AMP_CALIBRATION_CONTROL1"/> + <reg32 offset="0x2301a" name="GPU_CS_SENSOR_GENERAL_STATUS"/> + <reg32 offset="0x2301d" name="GPU_CS_AMP_CALIBRATION_STATUS1_0"/> + <reg32 offset="0x2301f" name="GPU_CS_AMP_CALIBRATION_STATUS1_2"/> + <reg32 offset="0x23021" name="GPU_CS_AMP_CALIBRATION_STATUS1_4"/> + <reg32 offset="0x23165" name="GPU_CS_AMP_CALIBRATION_DONE"/> + <reg32 offset="0x2316d" name="GPU_CS_AMP_PERIOD_CTRL"/> + <reg32 offset="0x23165" name="GPU_CS_AMP_CALIBRATION_DONE"/> + <reg32 offset="0x1f94d" name="GPU_GMU_CX_GMU_PWR_THRESHOLD"/> + <reg32 offset="0x23b03" name="GMU_AO_INTERRUPT_EN"/> + <reg32 offset="0x23b04" name="GMU_AO_HOST_INTERRUPT_CLR"/> + <reg32 offset="0x23b05" name="GMU_AO_HOST_INTERRUPT_STATUS"> <bitfield name="WDOG_BITE" pos="0" type="boolean"/> <bitfield name="RSCC_COMP" pos="1" type="boolean"/> <bitfield name="VDROOP" pos="2" type="boolean"/> @@ -191,27 +214,27 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <bitfield name="DBD_WAKEUP" pos="4" type="boolean"/> <bitfield name="HOST_AHB_BUS_ERROR" pos="5" type="boolean"/> </reg32> - <reg32 offset="0x9306" name="GMU_AO_HOST_INTERRUPT_MASK"/> - <reg32 offset="0x9309" name="GPU_GMU_AO_GMU_CGC_MODE_CNTL"/> - <reg32 offset="0x930a" name="GPU_GMU_AO_GMU_CGC_DELAY_CNTL"/> - <reg32 offset="0x930b" name="GPU_GMU_AO_GMU_CGC_HYST_CNTL"/> - <reg32 offset="0x930c" name="GPU_GMU_AO_GPU_CX_BUSY_STATUS"> + <reg32 offset="0x23b06" name="GMU_AO_HOST_INTERRUPT_MASK"/> + <reg32 offset="0x23b09" name="GPU_GMU_AO_GMU_CGC_MODE_CNTL"/> + <reg32 offset="0x23b0a" name="GPU_GMU_AO_GMU_CGC_DELAY_CNTL"/> + <reg32 offset="0x23b0b" name="GPU_GMU_AO_GMU_CGC_HYST_CNTL"/> + <reg32 offset="0x23b0c" name="GPU_GMU_AO_GPU_CX_BUSY_STATUS"> <bitfield name = "GPUBUSYIGNAHB" pos="23" type="boolean"/> </reg32> - <reg32 offset="0x930d" name="GPU_GMU_AO_GPU_CX_BUSY_STATUS2"/> - <reg32 offset="0x930e" name="GPU_GMU_AO_GPU_CX_BUSY_MASK"/> - <reg32 offset="0x9310" name="GMU_AO_AHB_FENCE_CTRL"/> - <reg32 offset="0x9313" name="GMU_AHB_FENCE_STATUS"/> - <reg32 offset="0x9314" name="GMU_AHB_FENCE_STATUS_CLR"/> - <reg32 offset="0x9315" name="GMU_RBBM_INT_UNMASKED_STATUS"/> - <reg32 offset="0x9316" name="GMU_AO_SPARE_CNTL"/> - <reg32 offset="0x9307" name="GMU_RSCC_CONTROL_REQ"/> - <reg32 offset="0x9308" name="GMU_RSCC_CONTROL_ACK"/> - <reg32 offset="0x9311" name="GMU_AHB_FENCE_RANGE_0"/> - <reg32 offset="0x9312" name="GMU_AHB_FENCE_RANGE_1"/> - <reg32 offset="0x9c03" name="GPU_CC_GX_GDSCR"/> - <reg32 offset="0x9d42" name="GPU_CC_GX_DOMAIN_MISC"/> - <reg32 offset="0xc001" name="GPU_CPR_FSM_CTL"/> + <reg32 offset="0x23b0d" name="GPU_GMU_AO_GPU_CX_BUSY_STATUS2"/> + <reg32 offset="0x23b0e" name="GPU_GMU_AO_GPU_CX_BUSY_MASK"/> + <reg32 offset="0x23b10" name="GMU_AO_AHB_FENCE_CTRL"/> + <reg32 offset="0x23b13" name="GMU_AHB_FENCE_STATUS"/> + <reg32 offset="0x23b14" name="GMU_AHB_FENCE_STATUS_CLR"/> + <reg32 offset="0x23b15" name="GMU_RBBM_INT_UNMASKED_STATUS"/> + <reg32 offset="0x23b16" name="GMU_AO_SPARE_CNTL"/> + <reg32 offset="0x23b07" name="GMU_RSCC_CONTROL_REQ"/> + <reg32 offset="0x23b08" name="GMU_RSCC_CONTROL_ACK"/> + <reg32 offset="0x23b11" name="GMU_AHB_FENCE_RANGE_0"/> + <reg32 offset="0x23b12" name="GMU_AHB_FENCE_RANGE_1"/> + <reg32 offset="0x24403" name="GPU_CC_GX_GDSCR"/> + <reg32 offset="0x24542" name="GPU_CC_GX_DOMAIN_MISC"/> + <reg32 offset="0x26801" name="GPU_CPR_FSM_CTL"/> <!-- starts at offset 0x8c00 on most gpus --> <reg32 offset="0x0004" name="GPU_RSCC_RSC_STATUS0_DRV0"/> @@ -233,12 +256,12 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <reg32 offset="0x03ee" name="RSCC_TCS1_DRV0_STATUS"/> <reg32 offset="0x0496" name="RSCC_TCS2_DRV0_STATUS"/> <reg32 offset="0x053e" name="RSCC_TCS3_DRV0_STATUS"/> - <reg32 offset="0x05e6" name="RSCC_TCS4_DRV0_STATUS" variants="A7XX"/> - <reg32 offset="0x068e" name="RSCC_TCS5_DRV0_STATUS" variants="A7XX"/> - <reg32 offset="0x0736" name="RSCC_TCS6_DRV0_STATUS" variants="A7XX"/> - <reg32 offset="0x07de" name="RSCC_TCS7_DRV0_STATUS" variants="A7XX"/> - <reg32 offset="0x0886" name="RSCC_TCS8_DRV0_STATUS" variants="A7XX"/> - <reg32 offset="0x092e" name="RSCC_TCS9_DRV0_STATUS" variants="A7XX"/> + <reg32 offset="0x05e6" name="RSCC_TCS4_DRV0_STATUS" variants="A7XX-"/> + <reg32 offset="0x068e" name="RSCC_TCS5_DRV0_STATUS" variants="A7XX-"/> + <reg32 offset="0x0736" name="RSCC_TCS6_DRV0_STATUS" variants="A7XX-"/> + <reg32 offset="0x07de" name="RSCC_TCS7_DRV0_STATUS" variants="A7XX-"/> + <reg32 offset="0x0886" name="RSCC_TCS8_DRV0_STATUS" variants="A7XX-"/> + <reg32 offset="0x092e" name="RSCC_TCS9_DRV0_STATUS" variants="A7XX-"/> </domain> </database> diff --git a/drivers/gpu/drm/msm/registers/adreno/a7xx_enums.xml b/drivers/gpu/drm/msm/registers/adreno/a7xx_enums.xml index 661b0dd0f675..8d195ee5d284 100644 --- a/drivers/gpu/drm/msm/registers/adreno/a7xx_enums.xml +++ b/drivers/gpu/drm/msm/registers/adreno/a7xx_enums.xml @@ -93,13 +93,6 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <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"/> diff --git a/drivers/gpu/drm/msm/registers/adreno/a8xx_descriptors.xml b/drivers/gpu/drm/msm/registers/adreno/a8xx_descriptors.xml new file mode 100644 index 000000000000..edcbdb3b6921 --- /dev/null +++ b/drivers/gpu/drm/msm/registers/adreno/a8xx_descriptors.xml @@ -0,0 +1,121 @@ +<?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"/> +<import file="adreno/a8xx_enums.xml"/> + +<domain name="A8XX_TEX_SAMP" width="32"> + <doc>Texture sampler dwords</doc> + <reg32 offset="0" name="0"> + <bitfield name="MIPFILTER_LINEAR_NEAR" pos="0" type="boolean"/> + <bitfield name="MIPMAPING_DIS" pos="1" type="boolean"/> + <bitfield name="XY_MAG" low="2" high="3" type="a6xx_tex_filter"/> + <bitfield name="XY_MIN" low="4" high="5" type="a6xx_tex_filter"/> + <bitfield name="WRAP_S" low="6" high="8" type="a6xx_tex_clamp"/> + <bitfield name="WRAP_T" low="9" high="11" type="a6xx_tex_clamp"/> + <bitfield name="WRAP_R" low="12" high="14" type="a6xx_tex_clamp"/> + <bitfield name="MSAA_BOX_FILTERING" pos="15" type="boolean"/> + <bitfield name="LOD_BIAS" low="16" high="28" type="fixed" radix="8"/> + <bitfield name="ANISO" low="29" high="31" type="a6xx_tex_aniso"/> + </reg32> + <reg32 offset="1" name="1"> + <bitfield name="MAX_LOD" low="0" high="11" type="ufixed" radix="8"/> + <bitfield name="MIN_LOD" low="12" high="23" type="ufixed" radix="8"/> + <bitfield name="REDUCTION_MODE" low="24" high="25" type="a6xx_reduction_mode"/> + <bitfield name="COMPARE_FUNC" low="26" high="28" type="adreno_compare_func"/> + <bitfield name="CHROMA_LINEAR" pos="29" type="boolean"/> + <bitfield name="CUBEMAPSEAMLESSFILTOFF" pos="30" type="boolean"/> + <bitfield name="UNNORM_COORDS" pos="31" type="boolean"/> + </reg32> + <reg32 offset="2" name="2"> + <bitfield name="FASTBORDERCOLOREN" pos="0" type="boolean"/> + <bitfield name="FASTBORDERCOLOR" low="1" high="2" type="a6xx_fast_border_color"/> + <bitfield name="BCOLOR" low="7" high="31"/> + </reg32> + <reg32 offset="3" name="3"/> +</domain> + +<domain name="A8XX_TEX_MEMOBJ" width="32" varset="chip"> + <doc>Texture memobj dwords</doc> + <reg32 offset="0" name="0"> + <bitfield name="BASE_LO" low="6" high="31" shr="6"/> + </reg32> + <reg32 offset="1" name="1"> + <bitfield name="BASE_HI" low="0" high="16"/> + <bitfield name="TYPE" low="17" high="19" type="a6xx_tex_type"/> + <bitfield name="DEPTH" low="20" high="31" type="uint"/> + </reg32> + <reg32 offset="2" name="2"> + <bitfield name="WIDTH" low="0" high="14" type="uint"/> + <bitfield name="HEIGHT" low="15" high="29" type="uint"/> + <bitfield name="SAMPLES" low="30" high="31" type="a3xx_msaa_samples"/> + </reg32> + <reg32 offset="3" name="3"> + <bitfield name="FMT" low="0" high="7" type="a6xx_format"/> + <bitfield name="SWAP" low="8" high="9" type="a3xx_color_swap"/> + <bitfield name="SWIZ_X" low="10" high="12" type="a8xx_tex_swiz"/> + <bitfield name="SWIZ_Y" low="13" high="15" type="a8xx_tex_swiz"/> + <bitfield name="SWIZ_Z" low="16" high="18" type="a8xx_tex_swiz"/> + <bitfield name="SWIZ_W" low="19" high="21" type="a8xx_tex_swiz"/> + </reg32> + <reg32 offset="4" name="4"> + <bitfield name="TILE_MODE" low="0" high="1" type="a6xx_tile_mode"/> + <bitfield name="FLAG" pos="2" type="boolean"/> + <bitfield name="PRT_EN" pos="3" type="boolean"/> + <bitfield name="TILE_ALL" pos="4" type="boolean"/> + <bitfield name="SRGB" pos="5" type="boolean"/> + <bitfield name="FLAG_LO" low="6" high="31" shr="6"/> + <!-- For multiplanar: --> + <bitfield name="BASE_U_LO" low="6" high="31" shr="6"/> + </reg32> + <reg32 offset="5" name="5"> + <bitfield name="FLAG_HI" low="0" high="16"/> + <!-- For multiplanar: --> + <bitfield name="BASE_U_HI" low="0" high="16"/> + <bitfield name="FLAG_BUFFER_PITCH" low="17" high="24" shr="6" type="uint"/> + <bitfield name="ALL_SAMPLES_CENTER" pos="29" type="boolean"/> + <bitfield name="MUTABLEEN" pos="31" type="boolean"/> + </reg32> + <reg32 offset="6" name="6"> + <bitfield name="TEX_LINE_OFFSET" low="0" high="23" type="uint"/> <!-- PITCH --> + <bitfield name="MIN_LINE_OFFSET" low="24" high="27" type="uint"/> <!-- PITCHALIGN --> + <bitfield name="MIPLVLS" low="28" high="31" type="uint"/> + </reg32> + <reg32 offset="7" name="7"> + <bitfield name="ARRAY_SLICE_OFFSET" low="0" high="22" shr="12" type="uint"/> <!-- ARRAY_PITCH --> + <bitfield name="ASO_UNIT" pos="23"/> <!-- 4KB or 32B ? --> + <bitfield name="MIN_ARRAY_SLIZE_OFFSET" low="24" high="27" shr="12"/> <!-- MIN_LAYERSZ --> + <bitfield name="GMEM_TILING_FALLBACK_EN" pos="28" type="boolean"/> + <bitfield name="CORNER_BASED_EN" pos="30" type="boolean"/> + <bitfield name="GMEM_FULL_SURF" pos="31" type="boolean"/> + <!-- For multiplanar. This overlaps other single-planar fields: --> + <bitfield name="UV_OFFSET_H" low="24" high="25" type="ufixed" radix="2"/> <!-- CHROMA_MIDPOINT_X --> + <bitfield name="UV_OFFSET_V" low="26" high="27" type="ufixed" radix="2"/> <!-- CHROMA_MIDPOINT_Y --> + </reg32> + <reg32 offset="8" name="8"> + <bitfield name="FLAG_ARRAY_PITCH" low="0" high="14" shr="12" type="uint"/> <!-- FLAG_BUFFER_ARRAY_PITCH --> + <!-- log2 size of the first level, required for mipmapping --> + <bitfield name="FLAG_BUFFER_LOGW" low="24" high="27" type="uint"/> + <bitfield name="FLAG_BUFFER_LOGH" low="28" high="31" type="uint"/> + <!-- For multiplanar. This overlaps other single-planar fields: --> + <bitfield name="BASE_V_LO" low="6" high="31" shr="6"/> + </reg32> + <reg32 offset="9" name="9"> + <bitfield name="MIN_LOD_CLAMP" low="19" high="30" type="ufixed" radix="8"/> + <!-- For multiplanar, this overlaps other fields: --> + <bitfield name="BASE_V_HI" low="0" high="16"/> + <bitfield name="UV_PITCH" low="17" high="26"/> <!-- PLANE_PITCH --> + </reg32> + <reg32 offset="10" name="10"/> + <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> + +</database> diff --git a/drivers/gpu/drm/msm/registers/adreno/a8xx_enums.xml b/drivers/gpu/drm/msm/registers/adreno/a8xx_enums.xml new file mode 100644 index 000000000000..c842db8c78d6 --- /dev/null +++ b/drivers/gpu/drm/msm/registers/adreno/a8xx_enums.xml @@ -0,0 +1,299 @@ +<?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="a8xx_statetype_id"> + <value value="0" name="A8XX_TP0_NCTX_REG"/> + <value value="1" name="A8XX_TP0_CTX0_3D_CVS_REG"/> + <value value="2" name="A8XX_TP0_CTX0_3D_CPS_REG"/> + <value value="3" name="A8XX_TP0_CTX1_3D_CVS_REG"/> + <value value="4" name="A8XX_TP0_CTX1_3D_CPS_REG"/> + <value value="5" name="A8XX_TP0_CTX2_3D_CPS_REG"/> + <value value="6" name="A8XX_TP0_CTX3_3D_CPS_REG"/> + <value value="9" name="A8XX_TP0_TMO_DATA"/> + <value value="10" name="A8XX_TP0_SMO_DATA"/> + <value value="11" name="A8XX_TP0_MIPMAP_BASE_DATA"/> + <value value="12" name="A8XX_TP_3D_CVS_REG"/> + <value value="13" name="A8XX_TP_3D_CPS_REG"/> + <value value="16" name="A8XX_SP_3D_CVS_REG"/> + <value value="17" name="A8XX_SP_3D_CPS_REG"/> + <value value="22" name="A8XX_SP_LB_DATA_RAM"/> + <value value="23" name="A8XX_SP_INST_DATA_RAM"/> + <value value="24" name="A8XX_SP_STH"/> + <value value="25" name="A8XX_SP_EVQ"/> + <value value="26" name="A8XX_SP_CONSMNG"/> + <value value="30" name="A8XX_HLSQ_INST_DATA_RAM"/> + <value value="31" name="A8XX_SP_INST_DATA_3"/> + <value value="32" name="A8XX_SP_NCTX_REG"/> + <value value="33" name="A8XX_SP_CTX0_3D_CVS_REG"/> + <value value="34" name="A8XX_SP_CTX0_3D_CPS_REG"/> + <value value="35" name="A8XX_SP_CTX1_3D_CVS_REG"/> + <value value="36" name="A8XX_SP_CTX1_3D_CPS_REG"/> + <value value="37" name="A8XX_SP_CTX2_3D_CPS_REG"/> + <value value="38" name="A8XX_SP_CTX3_3D_CPS_REG"/> + <value value="39" name="A8XX_SP_INST_DATA"/> + <value value="40" name="A8XX_SP_INST_DATA_1"/> + <value value="41" name="A8XX_SP_LB_0_DATA"/> + <value value="42" name="A8XX_SP_LB_1_DATA"/> + <value value="43" name="A8XX_SP_LB_2_DATA"/> + <value value="44" name="A8XX_SP_LB_3_DATA"/> + <value value="45" name="A8XX_SP_LB_4_DATA"/> + <value value="46" name="A8XX_SP_LB_5_DATA"/> + <value value="47" name="A8XX_SP_LB_6_DATA"/> + <value value="48" name="A8XX_SP_LB_7_DATA"/> + <value value="49" name="A8XX_SP_CB_RAM"/> + <value value="50" name="A8XX_SP_LB_13_DATA"/> + <value value="51" name="A8XX_SP_LB_14_DATA"/> + <value value="52" name="A8XX_SP_INST_TAG"/> + <value value="53" name="A8XX_SP_INST_DATA_2"/> + <value value="54" name="A8XX_SP_TMO_TAG"/> + <value value="55" name="A8XX_SP_SMO_TAG"/> + <value value="56" name="A8XX_SP_STATE_DATA"/> + <value value="57" name="A8XX_SP_HWAVE_RAM"/> + <value value="58" name="A8XX_SP_L0_INST_BUF"/> + <value value="59" name="A8XX_SP_LB_8_DATA"/> + <value value="60" name="A8XX_SP_LB_9_DATA"/> + <value value="61" name="A8XX_SP_LB_10_DATA"/> + <value value="62" name="A8XX_SP_LB_11_DATA"/> + <value value="63" name="A8XX_SP_LB_12_DATA"/> + <value value="64" name="A8XX_HLSQ_DATAPATH_DSTR_META"/> + <value value="65" name="A8XX_HLSQ_DESC_REMAP_META"/> + <value value="66" name="A8XX_HLSQ_SLICE_TOP_META"/> + <value value="67" name="A8XX_HLSQ_L2STC_TAG_RAM"/> + <value value="68" name="A8XX_HLSQ_L2STC_INFO_CMD"/> + <value value="69" name="A8XX_HLSQ_CVS_BE_CTXT_BUF_RAM_TAG"/> + <value value="70" name="A8XX_HLSQ_CPS_BE_CTXT_BUF_RAM_TAG"/> + <value value="71" name="A8XX_HLSQ_GFX_CVS_BE_CTXT_BUF_RAM"/> + <value value="72" name="A8XX_HLSQ_GFX_CPS_BE_CTXT_BUF_RAM"/> + <value value="73" name="A8XX_HLSQ_CHUNK_CVS_RAM"/> + <value value="74" name="A8XX_HLSQ_CHUNK_CPS_RAM"/> + <value value="75" name="A8XX_HLSQ_CHUNK_CVS_RAM_TAG"/> + <value value="76" name="A8XX_HLSQ_CHUNK_CPS_RAM_TAG"/> + <value value="77" name="A8XX_HLSQ_ICB_CVS_CB_BASE_TAG"/> + <value value="78" name="A8XX_HLSQ_ICB_CPS_CB_BASE_TAG"/> + <value value="79" name="A8XX_HLSQ_CVS_MISC_RAM"/> + <value value="80" name="A8XX_HLSQ_CPS_MISC_RAM"/> + <value value="81" name="A8XX_HLSQ_CPS_MISC_RAM_1"/> + <value value="82" name="A8XX_HLSQ_INST_RAM"/> + <value value="83" name="A8XX_HLSQ_GFX_CVS_CONST_RAM"/> + <value value="84" name="A8XX_HLSQ_GFX_CPS_CONST_RAM"/> + <value value="85" name="A8XX_HLSQ_CVS_MISC_RAM_TAG"/> + <value value="86" name="A8XX_HLSQ_CPS_MISC_RAM_TAG"/> + <value value="87" name="A8XX_HLSQ_INST_RAM_TAG"/> + <value value="88" name="A8XX_HLSQ_GFX_CVS_CONST_RAM_TAG"/> + <value value="89" name="A8XX_HLSQ_GFX_CPS_CONST_RAM_TAG"/> + <value value="90" name="A8XX_HLSQ_GFX_LOCAL_MISC_RAM"/> + <value value="91" name="A8XX_HLSQ_GFX_LOCAL_MISC_RAM_TAG"/> + <value value="92" name="A8XX_HLSQ_INST_RAM_1"/> + <value value="93" name="A8XX_HLSQ_STPROC_META"/> + <value value="94" name="A8XX_HLSQ_SLICE_BACKEND_META"/> + <value value="95" name="A8XX_HLSQ_INST_RAM_2"/> + <value value="96" name="A8XX_HLSQ_DATAPATH_META"/> + <value value="97" name="A8XX_HLSQ_FRONTEND_META"/> + <value value="98" name="A8XX_HLSQ_INDIRECT_META"/> + <value value="99" name="A8XX_HLSQ_BACKEND_META"/> +</enum> + +<enum name="a8xx_state_location"> + <value value="0" name="A8XX_HLSQ_STATE"/> + <value value="1" name="A8XX_HLSQ_DP"/> + <value value="2" name="A8XX_SP_TOP"/> + <value value="3" name="A8XX_USPTP"/> + <value value="4" name="A8XX_HLSQ_DP_STR"/> +</enum> + +<enum name="a8xx_cluster"> + <value value="0" name="A8XX_CLUSTER_NONE"/> + <value value="1" name="A8XX_CLUSTER_FE_US"/> + <value value="2" name="A8XX_CLUSTER_FE_S"/> + <value value="3" name="A8XX_CLUSTER_SP_VS"/> + <value value="4" name="A8XX_CLUSTER_VPC_VS"/> + <value value="5" name="A8XX_CLUSTER_VPC_US"/> + <value value="6" name="A8XX_CLUSTER_GRAS"/> + <value value="7" name="A8XX_CLUSTER_SP_PS"/> + <value value="8" name="A8XX_CLUSTER_VPC_PS"/> + <value value="9" name="A8XX_CLUSTER_PS"/> +</enum> + +<enum name="a8xx_debugbus_id"> + <value value="1" name="A8XX_DEBUGBUS_GBIF_CX_GC_US_I_0"/> + <value value="2" name="A8XX_DEBUGBUS_GMU_CX_GC_US_I_0"/> + <value value="3" name="A8XX_DEBUGBUS_CX_GC_US_I_0"/> + <value value="8" name="A8XX_DEBUGBUS_GBIF_GX_GC_US_I_0"/> + <value value="9" name="A8XX_DEBUGBUS_GMU_GX_GC_US_I_0"/> + <value value="10" name="A8XX_DEBUGBUS_DBGC_GC_US_I_0"/> + <value value="11" name="A8XX_DEBUGBUS_RBBM_GC_US_I_0"/> + <value value="12" name="A8XX_DEBUGBUS_LARC_GC_US_I_0"/> + <value value="13" name="A8XX_DEBUGBUS_COM_GC_US_I_0"/> + <value value="14" name="A8XX_DEBUGBUS_HLSQ_GC_US_I_0"/> + <value value="15" name="A8XX_DEBUGBUS_CGC_GC_US_I_0"/> + <value value="20" name="A8XX_DEBUGBUS_VSC_GC_US_I_0_0"/> + <value value="21" name="A8XX_DEBUGBUS_VSC_GC_US_I_0_1"/> + <value value="24" name="A8XX_DEBUGBUS_UFC_GC_US_I_0"/> + <value value="25" name="A8XX_DEBUGBUS_UFC_GC_US_I_1"/> + <value value="40" name="A8XX_DEBUGBUS_CP_GC_US_I_0_0"/> + <value value="41" name="A8XX_DEBUGBUS_CP_GC_US_I_0_1"/> + <value value="42" name="A8XX_DEBUGBUS_CP_GC_US_I_0_2"/> + <value value="56" name="A8XX_DEBUGBUS_PC_BR_US_I_0"/> + <value value="57" name="A8XX_DEBUGBUS_PC_BV_US_I_0"/> + <value value="58" name="A8XX_DEBUGBUS_GPC_BR_US_I_0"/> + <value value="59" name="A8XX_DEBUGBUS_GPC_BV_US_I_0"/> + <value value="60" name="A8XX_DEBUGBUS_VPC_BR_US_I_0"/> + <value value="61" name="A8XX_DEBUGBUS_VPC_BV_US_I_0"/> + <value value="80" name="A8XX_DEBUGBUS_UCHE_WRAPPER_GC_US_I_0"/> + <value value="81" name="A8XX_DEBUGBUS_UCHE_GC_US_I_0"/> + <value value="82" name="A8XX_DEBUGBUS_UCHE_GC_US_I_1"/> + <value value="83" name="A8XX_DEBUGBUS_UCHE_GC_US_I_0_1"/> + <value value="84" name="A8XX_DEBUGBUS_UCHE_GC_US_I_1_1"/> + <value value="128" name="A8XX_DEBUGBUS_CP_GC_S_0_I_0"/> + <value value="129" name="A8XX_DEBUGBUS_PC_BR_S_0_I_0"/> + <value value="130" name="A8XX_DEBUGBUS_PC_BV_S_0_I_0"/> + <value value="131" name="A8XX_DEBUGBUS_TESS_GC_S_0_I_0"/> + <value value="132" name="A8XX_DEBUGBUS_TSEFE_GC_S_0_I_0"/> + <value value="133" name="A8XX_DEBUGBUS_TSEBE_GC_S_0_I_0"/> + <value value="134" name="A8XX_DEBUGBUS_RAS_GC_S_0_I_0"/> + <value value="135" name="A8XX_DEBUGBUS_LRZ_BR_S_0_I_0"/> + <value value="136" name="A8XX_DEBUGBUS_LRZ_BV_S_0_I_0"/> + <value value="137" name="A8XX_DEBUGBUS_VFDP_GC_S_0_I_0"/> + <value value="138" name="A8XX_DEBUGBUS_GPC_BR_S_0_I_0"/> + <value value="139" name="A8XX_DEBUGBUS_GPC_BV_S_0_I_0"/> + <value value="140" name="A8XX_DEBUGBUS_VPCFE_BR_S_0_I_0"/> + <value value="141" name="A8XX_DEBUGBUS_VPCFE_BV_S_0_I_0"/> + <value value="142" name="A8XX_DEBUGBUS_VPCBE_BR_S_0_I_0"/> + <value value="143" name="A8XX_DEBUGBUS_VPCBE_BV_S_0_I_0"/> + <value value="144" name="A8XX_DEBUGBUS_CCHE_GC_S_0_I_0"/> + <value value="145" name="A8XX_DEBUGBUS_DBGC_GC_S_0_I_0"/> + <value value="146" name="A8XX_DEBUGBUS_LARC_GC_S_0_I_0"/> + <value value="147" name="A8XX_DEBUGBUS_RBBM_GC_S_0_I_0"/> + <value value="148" name="A8XX_DEBUGBUS_CCRE_GC_S_0_I_0"/> + <value value="149" name="A8XX_DEBUGBUS_CGC_GC_S_0_I_0"/> + <value value="150" name="A8XX_DEBUGBUS_GMU_GC_S_0_I_0"/> + <value value="151" name="A8XX_DEBUGBUS_SLICE_GC_S_0_I_0"/> + <value value="152" name="A8XX_DEBUGBUS_HLSQ_SPTP_STAR_GC_S_0_I_0"/> + <value value="160" name="A8XX_DEBUGBUS_USP_GC_S_0_I_0"/> + <value value="161" name="A8XX_DEBUGBUS_USP_GC_S_0_I_1"/> + <value value="166" name="A8XX_DEBUGBUS_USPTP_GC_S_0_I_0"/> + <value value="167" name="A8XX_DEBUGBUS_USPTP_GC_S_0_I_1"/> + <value value="168" name="A8XX_DEBUGBUS_USPTP_GC_S_0_I_2"/> + <value value="169" name="A8XX_DEBUGBUS_USPTP_GC_S_0_I_3"/> + <value value="178" name="A8XX_DEBUGBUS_TP_GC_S_0_I_0"/> + <value value="179" name="A8XX_DEBUGBUS_TP_GC_S_0_I_1"/> + <value value="180" name="A8XX_DEBUGBUS_TP_GC_S_0_I_2"/> + <value value="181" name="A8XX_DEBUGBUS_TP_GC_S_0_I_3"/> + <value value="190" name="A8XX_DEBUGBUS_RB_GC_S_0_I_0"/> + <value value="191" name="A8XX_DEBUGBUS_RB_GC_S_0_I_1"/> + <value value="196" name="A8XX_DEBUGBUS_CCU_GC_S_0_I_0"/> + <value value="197" name="A8XX_DEBUGBUS_CCU_GC_S_0_I_1"/> + <value value="202" name="A8XX_DEBUGBUS_HLSQ_GC_S_0_I_0"/> + <value value="203" name="A8XX_DEBUGBUS_HLSQ_GC_S_0_I_1"/> + <value value="208" name="A8XX_DEBUGBUS_VFD_GC_S_0_I_0"/> + <value value="209" name="A8XX_DEBUGBUS_VFD_GC_S_0_I_1"/> + <value value="256" name="A8XX_DEBUGBUS_CP_GC_S_1_I_0"/> + <value value="257" name="A8XX_DEBUGBUS_PC_BR_S_1_I_0"/> + <value value="258" name="A8XX_DEBUGBUS_PC_BV_S_1_I_0"/> + <value value="259" name="A8XX_DEBUGBUS_TESS_GC_S_1_I_0"/> + <value value="260" name="A8XX_DEBUGBUS_TSEFE_GC_S_1_I_0"/> + <value value="261" name="A8XX_DEBUGBUS_TSEBE_GC_S_1_I_0"/> + <value value="262" name="A8XX_DEBUGBUS_RAS_GC_S_1_I_0"/> + <value value="263" name="A8XX_DEBUGBUS_LRZ_BR_S_1_I_0"/> + <value value="264" name="A8XX_DEBUGBUS_LRZ_BV_S_1_I_0"/> + <value value="265" name="A8XX_DEBUGBUS_VFDP_GC_S_1_I_0"/> + <value value="266" name="A8XX_DEBUGBUS_GPC_BR_S_1_I_0"/> + <value value="267" name="A8XX_DEBUGBUS_GPC_BV_S_1_I_0"/> + <value value="268" name="A8XX_DEBUGBUS_VPCFE_BR_S_1_I_0"/> + <value value="269" name="A8XX_DEBUGBUS_VPCFE_BV_S_1_I_0"/> + <value value="270" name="A8XX_DEBUGBUS_VPCBE_BR_S_1_I_0"/> + <value value="271" name="A8XX_DEBUGBUS_VPCBE_BV_S_1_I_0"/> + <value value="272" name="A8XX_DEBUGBUS_CCHE_GC_S_1_I_0"/> + <value value="273" name="A8XX_DEBUGBUS_DBGC_GC_S_1_I_0"/> + <value value="274" name="A8XX_DEBUGBUS_LARC_GC_S_1_I_0"/> + <value value="275" name="A8XX_DEBUGBUS_RBBM_GC_S_1_I_0"/> + <value value="276" name="A8XX_DEBUGBUS_CCRE_GC_S_1_I_0"/> + <value value="277" name="A8XX_DEBUGBUS_CGC_GC_S_1_I_0"/> + <value value="278" name="A8XX_DEBUGBUS_GMU_GC_S_1_I_0"/> + <value value="279" name="A8XX_DEBUGBUS_SLICE_GC_S_1_I_0"/> + <value value="280" name="A8XX_DEBUGBUS_HLSQ_SPTP_STAR_GC_S_1_I_0"/> + <value value="288" name="A8XX_DEBUGBUS_USP_GC_S_1_I_0"/> + <value value="289" name="A8XX_DEBUGBUS_USP_GC_S_1_I_1"/> + <value value="294" name="A8XX_DEBUGBUS_USPTP_GC_S_1_I_0"/> + <value value="295" name="A8XX_DEBUGBUS_USPTP_GC_S_1_I_1"/> + <value value="296" name="A8XX_DEBUGBUS_USPTP_GC_S_1_I_2"/> + <value value="297" name="A8XX_DEBUGBUS_USPTP_GC_S_1_I_3"/> + <value value="306" name="A8XX_DEBUGBUS_TP_GC_S_1_I_0"/> + <value value="307" name="A8XX_DEBUGBUS_TP_GC_S_1_I_1"/> + <value value="308" name="A8XX_DEBUGBUS_TP_GC_S_1_I_2"/> + <value value="309" name="A8XX_DEBUGBUS_TP_GC_S_1_I_3"/> + <value value="318" name="A8XX_DEBUGBUS_RB_GC_S_1_I_0"/> + <value value="319" name="A8XX_DEBUGBUS_RB_GC_S_1_I_1"/> + <value value="324" name="A8XX_DEBUGBUS_CCU_GC_S_1_I_0"/> + <value value="325" name="A8XX_DEBUGBUS_CCU_GC_S_1_I_1"/> + <value value="330" name="A8XX_DEBUGBUS_HLSQ_GC_S_1_I_0"/> + <value value="331" name="A8XX_DEBUGBUS_HLSQ_GC_S_1_I_1"/> + <value value="336" name="A8XX_DEBUGBUS_VFD_GC_S_1_I_0"/> + <value value="337" name="A8XX_DEBUGBUS_VFD_GC_S_1_I_1"/> + <value value="384" name="A8XX_DEBUGBUS_CP_GC_S_2_I_0"/> + <value value="385" name="A8XX_DEBUGBUS_PC_BR_S_2_I_0"/> + <value value="386" name="A8XX_DEBUGBUS_PC_BV_S_2_I_0"/> + <value value="387" name="A8XX_DEBUGBUS_TESS_GC_S_2_I_0"/> + <value value="388" name="A8XX_DEBUGBUS_TSEFE_GC_S_2_I_0"/> + <value value="389" name="A8XX_DEBUGBUS_TSEBE_GC_S_2_I_0"/> + <value value="390" name="A8XX_DEBUGBUS_RAS_GC_S_2_I_0"/> + <value value="391" name="A8XX_DEBUGBUS_LRZ_BR_S_2_I_0"/> + <value value="392" name="A8XX_DEBUGBUS_LRZ_BV_S_2_I_0"/> + <value value="393" name="A8XX_DEBUGBUS_VFDP_GC_S_2_I_0"/> + <value value="394" name="A8XX_DEBUGBUS_GPC_BR_S_2_I_0"/> + <value value="395" name="A8XX_DEBUGBUS_GPC_BV_S_2_I_0"/> + <value value="396" name="A8XX_DEBUGBUS_VPCFE_BR_S_2_I_0"/> + <value value="397" name="A8XX_DEBUGBUS_VPCFE_BV_S_2_I_0"/> + <value value="398" name="A8XX_DEBUGBUS_VPCBE_BR_S_2_I_0"/> + <value value="399" name="A8XX_DEBUGBUS_VPCBE_BV_S_2_I_0"/> + <value value="400" name="A8XX_DEBUGBUS_CCHE_GC_S_2_I_0"/> + <value value="401" name="A8XX_DEBUGBUS_DBGC_GC_S_2_I_0"/> + <value value="402" name="A8XX_DEBUGBUS_LARC_GC_S_2_I_0"/> + <value value="403" name="A8XX_DEBUGBUS_RBBM_GC_S_2_I_0"/> + <value value="404" name="A8XX_DEBUGBUS_CCRE_GC_S_2_I_0"/> + <value value="405" name="A8XX_DEBUGBUS_CGC_GC_S_2_I_0"/> + <value value="406" name="A8XX_DEBUGBUS_GMU_GC_S_2_I_0"/> + <value value="407" name="A8XX_DEBUGBUS_SLICE_GC_S_2_I_0"/> + <value value="408" name="A8XX_DEBUGBUS_HLSQ_SPTP_STAR_GC_S_2_I_0"/> + <value value="416" name="A8XX_DEBUGBUS_USP_GC_S_2_I_0"/> + <value value="417" name="A8XX_DEBUGBUS_USP_GC_S_2_I_1"/> + <value value="422" name="A8XX_DEBUGBUS_USPTP_GC_S_2_I_0"/> + <value value="423" name="A8XX_DEBUGBUS_USPTP_GC_S_2_I_1"/> + <value value="424" name="A8XX_DEBUGBUS_USPTP_GC_S_2_I_2"/> + <value value="425" name="A8XX_DEBUGBUS_USPTP_GC_S_2_I_3"/> + <value value="434" name="A8XX_DEBUGBUS_TP_GC_S_2_I_0"/> + <value value="435" name="A8XX_DEBUGBUS_TP_GC_S_2_I_1"/> + <value value="436" name="A8XX_DEBUGBUS_TP_GC_S_2_I_2"/> + <value value="437" name="A8XX_DEBUGBUS_TP_GC_S_2_I_3"/> + <value value="446" name="A8XX_DEBUGBUS_RB_GC_S_2_I_0"/> + <value value="447" name="A8XX_DEBUGBUS_RB_GC_S_2_I_1"/> + <value value="452" name="A8XX_DEBUGBUS_CCU_GC_S_2_I_0"/> + <value value="453" name="A8XX_DEBUGBUS_CCU_GC_S_2_I_1"/> + <value value="458" name="A8XX_DEBUGBUS_HLSQ_GC_S_2_I_0"/> + <value value="459" name="A8XX_DEBUGBUS_HLSQ_GC_S_2_I_1"/> + <value value="464" name="A8XX_DEBUGBUS_VFD_GC_S_2_I_0"/> + <value value="465" name="A8XX_DEBUGBUS_VFD_GC_S_2_I_1"/> +</enum> + +<enum name="a8xx_usptp_id"> + <value value="0" name="A8XX_uSPTP0"/> + <value value="1" name="A8XX_uSPTP1"/> + <value value="15" name="A8XX_SPTOP"/> +</enum> + +<enum name="a8xx_tex_swiz"> + <value name="A8XX_SWIZ_IDENTITY" value="0"/> + <value name="A8XX_SWIZ_ZERO" value="1"/> + <value name="A8XX_SWIZ_ONE" value="2"/> + <value name="A8XX_SWIZ_X" value="3"/> + <value name="A8XX_SWIZ_Y" value="4"/> + <value name="A8XX_SWIZ_Z" value="5"/> + <value name="A8XX_SWIZ_W" value="6"/> +</enum> + +</database> diff --git a/drivers/gpu/drm/msm/registers/adreno/adreno_common.xml b/drivers/gpu/drm/msm/registers/adreno/adreno_common.xml index 218ec8bb966e..79d204f1e400 100644 --- a/drivers/gpu/drm/msm/registers/adreno/adreno_common.xml +++ b/drivers/gpu/drm/msm/registers/adreno/adreno_common.xml @@ -11,6 +11,7 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <value name="A5XX" value="5"/> <value name="A6XX" value="6"/> <value name="A7XX" value="7"/> + <value name="A8XX" value="8"/> </enum> <enum name="adreno_pa_su_sc_draw"> @@ -397,4 +398,15 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <value value="0x7" name="TEX_PREFETCH_UNK7"/> </enum> +<enum name="adreno_pipe"> + <value value="0" name="PIPE_NONE"/> + <value value="1" name="PIPE_BR"/> + <value value="2" name="PIPE_BV"/> + <value value="3" name="PIPE_LPAC"/> + <value value="4" name="PIPE_AQE0"/> + <value value="5" name="PIPE_AQE1"/> + <value value="6" name="PIPE_DDE_BR"/> + <value value="7" name="PIPE_DDE_BV"/> +</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 0e10e1c6d263..51e9c94f5e37 100644 --- a/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml +++ b/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml @@ -6,103 +6,102 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <import file="adreno/adreno_common.xml"/> <enum name="vgt_event_type" varset="chip"> - <value name="VS_DEALLOC" value="0"/> - <value name="PS_DEALLOC" value="1" variants="A2XX-A6XX"/> - <value name="VS_DONE_TS" value="2"/> - <value name="PS_DONE_TS" value="3"/> + <value name="VS_DEALLOC" value="0x00" variants="A2XX-A5XX"/> + <value name="PS_DEALLOC" value="0x01" variants="A2XX-A5XX"/> + <value name="VS_DONE_TS" value="0x02" variants="A2XX-A5XX"/> + <value name="PS_DONE_TS" value="0x03" variants="A2XX-A5XX"/> <doc> Flushes dirty data from UCHE, and also writes a GPU timestamp to the address if one is provided. </doc> - <value name="CACHE_FLUSH_TS" value="4"/> - <value name="CONTEXT_DONE" value="5"/> - <value name="CACHE_FLUSH" value="6" variants="A2XX-A4XX"/> - <value name="VIZQUERY_START" value="7" variants="A2XX"/> - <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="CACHE_FLUSH_TS" value="0x04"/> + <value name="CONTEXT_DONE" value="0x05"/> + <value name="CACHE_FLUSH" value="0x06" variants="A2XX-A4XX"/> + <value name="VIZQUERY_START" value="0x07" variants="A2XX"/> + <value name="HLSQ_FLUSH" value="0x07" variants="A3XX-A4XX"/> + <value name="VIZQUERY_END" value="0x08" variants="A2XX"/> + <value name="SC_WAIT_WC" value="0x09" variants="A2XX"/> + <value name="WRITE_PRIMITIVE_COUNTS" value="0x09" variants="A6XX-"/> + <value name="START_PRIMITIVE_CTRS" value="0x0b" variants="A6XX-"/> + <value name="STOP_PRIMITIVE_CTRS" value="0x0c" 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"/> - <value name="TILE_FLUSH" value="15" variants="A2XX-A4XX"/> - <value name="STAT_EVENT" value="16" variants="A2XX-A4XX"/> - <value name="CACHE_FLUSH_AND_INV_TS_EVENT" value="20" variants="A2XX-A4XX"/> + <value name="RST_PIX_CNT" value="0x0d" variants="A2XX-A4XX"/> + <value name="RST_VTX_CNT" value="0x0e" variants="A2XX-A4XX"/> + <value name="TILE_FLUSH" value="0x0f" variants="A2XX-A4XX"/> + <value name="STAT_EVENT" value="0x10" variants="A2XX-A4XX"/> + <value name="CACHE_FLUSH_AND_INV_TS_EVENT" value="0x14" variants="A2XX-A4XX"/> <doc> 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"/> - <value name="CACHE_FLUSH_AND_INV_EVENT" value="22" variants="A2XX"/> + <value name="ZPASS_DONE" value="0x15"/> + <value name="CACHE_FLUSH_AND_INV_EVENT" value="0x16" variants="A2XX"/> <doc> Writes the GPU timestamp to the address that follows, once RB access and flushes are complete. </doc> - <value name="RB_DONE_TS" value="22" variants="A3XX-"/> + <value name="RB_DONE_TS" value="0x16" variants="A3XX-"/> - <value name="PERFCOUNTER_START" value="23" variants="A2XX-A4XX"/> - <value name="PERFCOUNTER_STOP" value="24" variants="A2XX-A4XX"/> - <value name="VS_FETCH_DONE" value="27"/> - <value name="FACENESS_FLUSH" value="28" variants="A2XX-A4XX"/> + <value name="PERFCOUNTER_START" value="0x17" variants="A2XX-A4XX"/> + <value name="PERFCOUNTER_STOP" value="0x18" variants="A2XX-A4XX"/> + <value name="VS_FETCH_DONE" value="0x1b" variants="A2XX-A5XX"/> + <value name="FACENESS_FLUSH" value="0x1c" variants="A2XX-A4XX"/> <!-- a5xx events --> - <value name="WT_DONE_TS" value="8" variants="A5XX-"/> - <value name="START_FRAGMENT_CTRS" value="13" variants="A5XX-"/> - <value name="STOP_FRAGMENT_CTRS" value="14" variants="A5XX-"/> - <value name="START_COMPUTE_CTRS" value="15" variants="A5XX-"/> - <value name="STOP_COMPUTE_CTRS" value="16" variants="A5XX-"/> - <value name="FLUSH_SO_0" value="17" variants="A5XX-"/> - <value name="FLUSH_SO_1" value="18" variants="A5XX-"/> - <value name="FLUSH_SO_2" value="19" variants="A5XX-"/> - <value name="FLUSH_SO_3" value="20" variants="A5XX-"/> + <value name="WT_DONE_TS" value="0x08" variants="A5XX-A6XX"/> + <value name="START_FRAGMENT_CTRS" value="0x0d" variants="A5XX-"/> + <value name="STOP_FRAGMENT_CTRS" value="0x0e" variants="A5XX-"/> + <value name="START_COMPUTE_CTRS" value="0x0f" variants="A5XX-"/> + <value name="STOP_COMPUTE_CTRS" value="0x10" variants="A5XX-"/> + <value name="FLUSH_SO_0" value="0x11" variants="A5XX-"/> + <value name="FLUSH_SO_1" value="0x12" variants="A5XX-"/> + <value name="FLUSH_SO_2" value="0x13" variants="A5XX-"/> + <value name="FLUSH_SO_3" value="0x14" variants="A5XX-"/> <doc> Invalidates depth attachment data from the CCU. We assume this happens in the last stage. </doc> - <value name="PC_CCU_INVALIDATE_DEPTH" value="24" variants="A5XX-"/> + <value name="PC_CCU_INVALIDATE_DEPTH" value="0x18" variants="A5XX-A6XX"/> <doc> Invalidates color attachment data from the CCU. We assume this happens in the last stage. </doc> - <value name="PC_CCU_INVALIDATE_COLOR" value="25" variants="A5XX-"/> + <value name="PC_CCU_INVALIDATE_COLOR" value="0x19" variants="A5XX-A6XX"/> <doc> Flushes the small cache used by CP_EVENT_WRITE::BLIT (which, along with its registers, would be better named RESOLVE). </doc> - <value name="PC_CCU_RESOLVE_TS" value="26" variants="A6XX"/> + <value name="PC_CCU_RESOLVE_TS" value="0x1a" variants="A6XX"/> <doc> Flushes depth attachment data from the CCU. We assume this happens in the last stage. </doc> - <value name="PC_CCU_FLUSH_DEPTH_TS" value="28" variants="A5XX-"/> + <value name="PC_CCU_FLUSH_DEPTH_TS" value="0x1c" variants="A5XX-A6XX"/> <doc> Flushes color attachment data from the CCU. We assume this happens in the last stage. </doc> - <value name="PC_CCU_FLUSH_COLOR_TS" value="29" variants="A5XX-"/> + <value name="PC_CCU_FLUSH_COLOR_TS" value="0x1d" variants="A5XX-A6XX"/> <doc> - 2D blit to resolve GMEM to system memory (skipping CCU) at the - end of a render pass. Compare to CP_BLIT's BLIT_OP_SCALE for - more general blitting. + Triggers a resolve (GMEM to sysmem) or unresolve (sysmem to + GMEM) or clear blit, depending on CCU programming. </doc> - <value name="BLIT" value="30" variants="A5XX-"/> + <value name="CCU_RESOLVE" value="0x1e" 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"/> + <value name="LRZ_FLIP_BUFFER" value="0x24" variants="A7XX-"/> <doc> Clears based on GRAS_LRZ_CNTL configuration, could clear @@ -115,44 +114,46 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> CUR_DIR_UNSET = 0x3 Clear of direction means setting the direction to CUR_DIR_UNSET. </doc> - <value name="LRZ_CLEAR" value="37" variants="A5XX-"/> - - <value name="LRZ_FLUSH" value="38" variants="A5XX-"/> - <value name="BLIT_OP_FILL_2D" value="39" variants="A5XX-"/> - <value name="BLIT_OP_COPY_2D" value="40" variants="A5XX-A6XX"/> - <value name="LRZ_CACHE_INVALIDATE" 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="VSC_BINNING_START" value="44" variants="A5XX-"/> - <value name="VSC_BINNING_END" value="45" variants="A5XX-"/> + <value name="LRZ_CLEAR" value="0x25" variants="A5XX-"/> + + <value name="LRZ_FLUSH_INVALIDATE" value="0x26" variants="A5XX-A6XX"/> + <value name="LRZ_CACHE_FLUSH" value="0x26" variants="A7XX-"/> + <value name="BLIT_OP_FILL_2D" value="0x27" variants="A5XX-A6XX"/> + <value name="BLIT_OP_COPY_2D" value="0x28" variants="A5XX-A6XX"/> + <value name="LRZ_CACHE_INVALIDATE" value="0x28" variants="A7XX-"/> + <value name="LRZ_Q_CACHE_INVALIDATE" value="0x29" variants="A7XX-"/> + <value name="BLIT_OP_SCALE_2D" value="0x2a" variants="A5XX-"/> + <value name="CONTEXT_DONE_2D" value="0x2b" variants="A5XX-"/> + <value name="VSC_BINNING_START" value="0x2c" variants="A5XX-"/> + <value name="VSC_BINNING_END" value="0x2d" variants="A5XX-"/> <!-- a6xx events --> <doc> Invalidates UCHE. </doc> - <value name="CACHE_INVALIDATE" value="49" variants="A6XX"/> + <value name="CACHE_INVALIDATE" value="0x31" variants="A6XX"/> - <value name="LABEL" value="63" variants="A6XX-"/> + <value name="DEBUG_LABEL" value="0x3f" variants="A6XX-"/> <!-- note, some of these are the same as a6xx, just named differently --> <doc> Doesn't seem to do anything </doc> - <value name="DUMMY_EVENT" value="1" variants="A7XX"/> - <value name="CCU_INVALIDATE_DEPTH" value="24" variants="A7XX"/> - <value name="CCU_INVALIDATE_COLOR" value="25" variants="A7XX"/> - <value name="CCU_RESOLVE_CLEAN" value="26" variants="A7XX"/> - <value name="CCU_FLUSH_DEPTH" value="28" variants="A7XX"/> - <value name="CCU_FLUSH_COLOR" value="29" variants="A7XX"/> - <value name="CCU_RESOLVE" value="30" variants="A7XX"/> - <value name="CCU_END_RESOLVE_GROUP" value="31" variants="A7XX"/> - <value name="CCU_CLEAN_DEPTH" value="32" variants="A7XX"/> - <value name="CCU_CLEAN_COLOR" value="33" variants="A7XX"/> - <value name="CACHE_RESET" value="48" variants="A7XX"/> - <value name="CACHE_CLEAN" value="49" variants="A7XX"/> + <value name="DUMMY_EVENT" value="0x01" variants="A7XX-"/> + <value name="CCU_INVALIDATE_DEPTH" value="0x18" variants="A7XX-"/> + <value name="CCU_INVALIDATE_COLOR" value="0x19" variants="A7XX-"/> + <value name="CCU_RESOLVE_CLEAN" value="0x1a" variants="A7XX-"/> + <value name="CCU_FLUSH_DEPTH" value="0x1c" variants="A7XX-"/> + <value name="CCU_FLUSH_COLOR" value="0x1d" variants="A7XX-"/> + <value name="CCU_END_RESOLVE_GROUP" value="0x1f" variants="A7XX-"/> + <value name="CCU_CLEAN_DEPTH" value="0x20" variants="A7XX-"/> + <value name="CCU_CLEAN_COLOR" value="0x21" variants="A7XX-"/> + <value name="CACHE_RESET" value="0x30" variants="A7XX-"/> + <value name="CACHE_CLEAN" value="0x31" variants="A7XX-"/> <!-- TODO: deal with name conflicts with other gens --> - <value name="CACHE_FLUSH7" value="50" variants="A7XX"/> - <value name="CACHE_INVALIDATE7" value="51" variants="A7XX"/> + <value name="CACHE_FLUSH7" value="0x32" variants="A7XX-"/> + <value name="CACHE_INVALIDATE7" value="0x33" variants="A7XX-"/> + <value name="DEPTH_BUFFER_FLIP" value="0x3d" variants="A8XX-"/> + <value name="CCH_FAST_CLEAR_CLEAN" value="0x1b" variants="A8XX-"/> </enum> <enum name="pc_di_primtype"> @@ -310,11 +311,11 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <value name="CP_EVENT_WRITE" value="0x46" variants="A2XX-A6XX"/> <value name="CP_EVENT_WRITE7" value="0x46" variants="A7XX-"/> <doc>generate a VS|PS_done event</doc> - <value name="CP_EVENT_WRITE_SHD" value="0x58"/> + <value name="CP_EVENT_WRITE_SHD" value="0x58" variants="A2XX"/> <doc>generate a cache flush done event</doc> - <value name="CP_EVENT_WRITE_CFL" value="0x59"/> + <value name="CP_EVENT_WRITE_CFL" value="0x59" variants="A2XX"/> <doc>generate a z_pass done event</doc> - <value name="CP_EVENT_WRITE_ZPD" value="0x5b"/> + <value name="CP_EVENT_WRITE_ZPD" value="0x5b" variants="A2XX"/> <doc> not sure the real name, but this seems to be what is used for opencl, instead of CP_DRAW_INDX.. @@ -335,9 +336,9 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <doc>load constant into chip and to memory</doc> <value name="CP_SET_CONSTANT" value="0x2d" variants="A2XX"/> <doc>load sequencer instruction memory (pointer-based)</doc> - <value name="CP_IM_LOAD" value="0x27"/> + <value name="CP_IM_LOAD" value="0x27" variants="A2XX"/> <doc>load sequencer instruction memory (code embedded in packet)</doc> - <value name="CP_IM_LOAD_IMMEDIATE" value="0x2b"/> + <value name="CP_IM_LOAD_IMMEDIATE" value="0x2b" variants="A2XX"/> <doc>load constants from a location in memory</doc> <value name="CP_LOAD_CONSTANT_CONTEXT" value="0x2e" variants="A2XX"/> <doc>selective invalidation of state pointers</doc> @@ -662,6 +663,12 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <value name="CP_CCHE_INVALIDATE" value="0x3a" variants="A7XX-"/> <value name="CP_SCOPE_CNTL" value="0x6c" variants="A7XX-"/> + + <value name="CP_SKIP_IB_MODE" value="0x27" variants="A7XX-"/> + + <value name="CP_MEMORY_MAP_UPDATE" value="0x58" variants="A8XX-"/> + + <value name="CP_BARRIER" value="0x59" variants="A8XX-"/> </enum> @@ -1800,49 +1807,73 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) <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) --> + <value value="12" name="RM6_BLIT2DSCALE"/> <!-- no-op (at least on current sqe fw) --> <!-- These values come from a6xx_set_marker() in the downstream kernel, and they can only be set by the kernel --> - <value value="0xd" name="RM6_IB1LIST_START"/> - <value value="0xe" name="RM6_IB1LIST_END"/> + <value value="13" name="RM6_IB1LIST_START"/> + <value value="14" name="RM6_IB1LIST_END"/> + <value value="15" name="RM7_BIN_VISIBILITY_END"/> + + <!-- new in a8xx: --> + <value value="32" name="RM8_DEPTH_PASS_START"/> + <value value="33" name="RM8_DEPTH_PASS_END"/> + <value value="34" name="RM8_SET_RENDER_TARGET"/> + <value value="35" name="RM8_PGMEM_ON"/> + <value value="36" name="RM8_PGMEM_OFF"/> </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"/> - - <!-- - 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> + <stripe varset="chip" variants="A6XX-A7XX"> + <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"/> + + + <!-- + 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> + </stripe> + <stripe varset="chip" variants="A8XX-"> + <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="6" type="a6xx_marker" varset="set_marker_mode" variants="SET_RENDER_MODE"/> + <bitfield name="USES_GMEM" pos="7" 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"/> + <!-- idk if the RT w/a fields apply to a8xx as well --> + </reg32> + </stripe> </domain> <domain name="CP_SET_PSEUDO_REG" width="32" varset="chip" prefix="chip" variants="A6XX-"> @@ -2066,6 +2097,14 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) payload *and* skipsaverestore is set. This is expected to restore static register values not saved when skipsaverestore is set. + + On BV, a skipsaverestore preemption is triggered + and this preamble type is executed whenever a + CP_THREAD_CONTROL that synchronizes threads + happens. This can be explicitly via + SYNC_THREADS, or implicitly when the value of + CONCURRENT_BIN_DISABLE changes from the previous + thread control. </doc> </value> <value name="POSTAMBLE_AMBLE_TYPE" value="2"> @@ -2308,5 +2347,99 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords) </reg32> </domain> +<domain name="CP_RESOURCE_LIST" width="32"> + <doc> + A7xx introduces the "resource table" which is managed by + CP_RESOURCE_LIST. It is used to synchronize BR and BV access + to resources such as LRZ buffers. + + The resource table consists of resources that are in-use by BR. + Each "resource" has a base address, which is + usually a pointer but is treated by the HW as an opaque handle, + a read/write bit, and a timestamp when it was last used. + Resources are removed from the table upon event completion when + a special CP_EVENT_WRITE::CLEAR_RENDER_RESOURCE bit is set, which + will remove all resources with a timestamp up to the current + timestamp. + + CP_RESOURCE_LIST first specifies a list of BV resources. For + each BV resource, the HW will check if there is a corresponding + BR resource in the table, and if at least one of the BV and BR + resources is marked WRITE then it will stall until the BR + resource is removed. + + It then specifies a list of BR resources. These will be added to + the resource table, unless there is an overflow in which case + the designated overflow register will have bit 0 set. Overflow + should cause the next binning pass to stall until BR is done, + effectively disabling concurrent binning. + + CP_RESOURCE_LIST must be executed by BV. BR resources are added + by BV and removed by BR. + + There is a separate table for "LRZ resources." These behave a + bit differently: specifying an LRZ resource via BV_RES_LRZ + stalls on any matching resource existing and then adds it to the + table, making it both a BV and BR resource in one. There is a + separate CLEAR_LRZ_RESOURCE bit for removing resources from the + LRZ table, and it only removes one resource given by a base + address passed to CP_EVENT_WRITE. Therefore timestamps are + unnecessary. + </doc> + <reg32 offset="0" name="BV_COUNT" type="uint"/> + <doc> + What follows is a list of CP_BV_RESOURCE and then CP_RESOURCE_LIST_BR. + </doc> +</domain> + +<domain name="CP_BV_RESOURCE" width="32"> + <doc> + BV resources don't go in the table. Instead CP waits until any + corresponding BR resources with the same base pointer are + finished before the packet completes. + </doc> + <enum name="cp_bv_resource_encoding"> + <value value="0" name="BV_RES_DIRECT"/> + <doc> + INDIRECT resources are encoded as a 32b offset + 3b + bindless base selector. The offset is added to the given + BINDLESS_BASE pseudoregister and then the 64b value + fetched there is used as the pointer. + </doc> + <value value="1" name="BV_RES_INDIRECT_READ"/> + <value value="2" name="BV_RES_LRZ"/> + <value value="3" name="BV_RES_INDIRECT_WRITE"/> + </enum> + <reg64 offset="0" name="0"> + <bitfield name="BASE_ADDR" low="1" high="61" shr="1" type="address"/> + <bitfield name="WRITE" pos="0" type="boolean"/> + <bitfield name="ENCODING" low="62" high="63" type="cp_bv_resource_encoding"/> + </reg64> +</domain> + +<domain name="CP_RESOURCE_LIST_BR" width="32"> + <reg32 offset="0" name="0"> + <bitfield name="BR_COUNT" low="0" high="23" type="uint"/> + <bitfield name="OVERFLOW_ONCHIP_ADDR" low="24" high="26"/> + <bitfield name="OVERFLOW" pos="31" type="boolean"/> + </reg32> + <doc> + What follows is a list of CP_BR_RESOURCE. + </doc> +</domain> + +<domain name="CP_BR_RESOURCE" width="32"> + <enum name="cp_br_resource_encoding"> + <value value="0" name="BR_RES_DIRECT"/> + <value value="2" name="BR_RES_INDIRECT_READ"/> + <value value="3" name="BR_RES_INDIRECT_WRITE"/> <!-- set WRITE bit --> + </enum> + <reg64 offset="0" name="0"> + <bitfield name="BASE_ADDR" low="1" high="61" shr="1" type="address"/> + <bitfield name="WRITE" pos="0" type="boolean"/> + <bitfield name="ENCODING" low="62" high="63" type="cp_br_resource_encoding"/> + </reg64> +</domain> + </database> diff --git a/drivers/gpu/drm/msm/registers/gen_header.py b/drivers/gpu/drm/msm/registers/gen_header.py index 1d603dadfabd..2acad951f1e2 100644 --- a/drivers/gpu/drm/msm/registers/gen_header.py +++ b/drivers/gpu/drm/msm/registers/gen_header.py @@ -189,12 +189,13 @@ class Bitset(object): print(" return (struct fd_reg_pair) {") print(" .reg = (uint32_t)%s," % reg.reg_offset()) print(" .value =") + cast = "(uint64_t)" if reg.bit_size == 64 else "" for f in self.fields: if f.type in [ "address", "waddress" ]: continue else: type, val = f.ctype("fields.%s" % field_name(reg, f)) - print(" (%-40s << %2d) |" % (val, f.low)) + print(" (%s%-40s << %2d) |" % (cast, val, f.low)) value_name = "dword" if reg.bit_size == 64: value_name = "qword" @@ -264,10 +265,11 @@ class Bitset(object): (prefix, prefix, prefix, skip)) - def dump(self, is_deprecated, prefix=None): + def dump(self, is_deprecated, prefix=None, reg=None): if prefix is None: prefix = self.name - if self.reg and self.reg.bit_size == 64: + reg64 = reg and self.reg and self.reg.bit_size == 64 + if reg64: print("static inline uint32_t %s_LO(uint32_t val)\n{" % prefix) print("\treturn val;\n}") print("static inline uint32_t %s_HI(uint32_t val)\n{" % prefix) @@ -283,14 +285,17 @@ class Bitset(object): elif f.type == "boolean" or (f.type is None and f.low == f.high): tab_to("#define %s" % name, "0x%08x" % (1 << f.low)) else: - tab_to("#define %s__MASK" % name, "0x%08x" % mask(f.low, f.high)) + typespec = "ull" if reg64 else "u" + tab_to("#define %s__MASK" % name, "0x%08x%s" % (mask(f.low, f.high), typespec)) tab_to("#define %s__SHIFT" % name, "%d" % f.low) type, val = f.ctype("val") + ret_type = "uint64_t" if reg64 else "uint32_t" + cast = "(uint64_t)" if reg64 else "" - print("static inline uint32_t %s(%s val)\n{" % (name, type)) + print("static inline %s %s(%s val)\n{" % (ret_type, name, type)) if f.shr > 0: print("\tassert(!(val & 0x%x));" % mask(0, f.shr - 1)) - print("\treturn ((%s) << %s__SHIFT) & %s__MASK;\n}" % (val, name, name)) + print("\treturn (%s(%s) << %s__SHIFT) & %s__MASK;\n}" % (cast, val, name, name)) print() class Array(object): @@ -437,7 +442,7 @@ class Reg(object): print("static inline%s uint32_t REG_%s(%s) { return 0x%08x + %s; }" % (depcrstr, self.full_name, proto, offset, strides)) if self.bitset.inline: - self.bitset.dump(is_deprecated, self.full_name) + self.bitset.dump(is_deprecated, self.full_name, self) print("") def dump_pack_struct(self, is_deprecated): |