diff options
Diffstat (limited to 'drivers/gpu/drm/msm/adreno/a6xx_gpu.c')
-rw-r--r-- | drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 622 |
1 files changed, 560 insertions, 62 deletions
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index 52da3795b175..b3ada1e7b598 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -21,7 +21,7 @@ static inline bool _a6xx_check_idle(struct msm_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)) + if (!adreno_has_gmu_wrapper(adreno_gpu) && !a6xx_gmu_isidle(&a6xx_gpu->gmu)) return false; /* Check tha the CX master is idle */ @@ -252,6 +252,56 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) a6xx_flush(gpu, ring); } +const struct adreno_reglist a612_hwcg[] = { + {REG_A6XX_RBBM_CLOCK_CNTL_SP0, 0x22222222}, + {REG_A6XX_RBBM_CLOCK_CNTL2_SP0, 0x02222220}, + {REG_A6XX_RBBM_CLOCK_DELAY_SP0, 0x00000081}, + {REG_A6XX_RBBM_CLOCK_HYST_SP0, 0x0000f3cf}, + {REG_A6XX_RBBM_CLOCK_CNTL_TP0, 0x22222222}, + {REG_A6XX_RBBM_CLOCK_CNTL2_TP0, 0x22222222}, + {REG_A6XX_RBBM_CLOCK_CNTL3_TP0, 0x22222222}, + {REG_A6XX_RBBM_CLOCK_CNTL4_TP0, 0x00022222}, + {REG_A6XX_RBBM_CLOCK_DELAY_TP0, 0x11111111}, + {REG_A6XX_RBBM_CLOCK_DELAY2_TP0, 0x11111111}, + {REG_A6XX_RBBM_CLOCK_DELAY3_TP0, 0x11111111}, + {REG_A6XX_RBBM_CLOCK_DELAY4_TP0, 0x00011111}, + {REG_A6XX_RBBM_CLOCK_HYST_TP0, 0x77777777}, + {REG_A6XX_RBBM_CLOCK_HYST2_TP0, 0x77777777}, + {REG_A6XX_RBBM_CLOCK_HYST3_TP0, 0x77777777}, + {REG_A6XX_RBBM_CLOCK_HYST4_TP0, 0x00077777}, + {REG_A6XX_RBBM_CLOCK_CNTL_RB0, 0x22222222}, + {REG_A6XX_RBBM_CLOCK_CNTL2_RB0, 0x01202222}, + {REG_A6XX_RBBM_CLOCK_CNTL_CCU0, 0x00002220}, + {REG_A6XX_RBBM_CLOCK_HYST_RB_CCU0, 0x00040f00}, + {REG_A6XX_RBBM_CLOCK_CNTL_RAC, 0x05522022}, + {REG_A6XX_RBBM_CLOCK_CNTL2_RAC, 0x00005555}, + {REG_A6XX_RBBM_CLOCK_DELAY_RAC, 0x00000011}, + {REG_A6XX_RBBM_CLOCK_HYST_RAC, 0x00445044}, + {REG_A6XX_RBBM_CLOCK_CNTL_TSE_RAS_RBBM, 0x04222222}, + {REG_A6XX_RBBM_CLOCK_MODE_VFD, 0x00002222}, + {REG_A6XX_RBBM_CLOCK_MODE_GPC, 0x02222222}, + {REG_A6XX_RBBM_CLOCK_DELAY_HLSQ_2, 0x00000002}, + {REG_A6XX_RBBM_CLOCK_MODE_HLSQ, 0x00002222}, + {REG_A6XX_RBBM_CLOCK_DELAY_TSE_RAS_RBBM, 0x00004000}, + {REG_A6XX_RBBM_CLOCK_DELAY_VFD, 0x00002222}, + {REG_A6XX_RBBM_CLOCK_DELAY_GPC, 0x00000200}, + {REG_A6XX_RBBM_CLOCK_DELAY_HLSQ, 0x00000000}, + {REG_A6XX_RBBM_CLOCK_HYST_TSE_RAS_RBBM, 0x00000000}, + {REG_A6XX_RBBM_CLOCK_HYST_VFD, 0x00000000}, + {REG_A6XX_RBBM_CLOCK_HYST_GPC, 0x04104004}, + {REG_A6XX_RBBM_CLOCK_HYST_HLSQ, 0x00000000}, + {REG_A6XX_RBBM_CLOCK_CNTL_UCHE, 0x22222222}, + {REG_A6XX_RBBM_CLOCK_HYST_UCHE, 0x00000004}, + {REG_A6XX_RBBM_CLOCK_DELAY_UCHE, 0x00000002}, + {REG_A6XX_RBBM_ISDB_CNT, 0x00000182}, + {REG_A6XX_RBBM_RAC_THRESHOLD_CNT, 0x00000000}, + {REG_A6XX_RBBM_SP_HYST_CNT, 0x00000000}, + {REG_A6XX_RBBM_CLOCK_CNTL_GMU_GX, 0x00000222}, + {REG_A6XX_RBBM_CLOCK_DELAY_GMU_GX, 0x00000111}, + {REG_A6XX_RBBM_CLOCK_HYST_GMU_GX, 0x00000555}, + {}, +}; + /* For a615 family (a615, a616, a618 and a619) */ const struct adreno_reglist a615_hwcg[] = { {REG_A6XX_RBBM_CLOCK_CNTL_SP0, 0x02222222}, @@ -588,6 +638,63 @@ const struct adreno_reglist a660_hwcg[] = { {}, }; +const struct adreno_reglist a690_hwcg[] = { + {REG_A6XX_RBBM_CLOCK_CNTL_SP0, 0x02222222}, + {REG_A6XX_RBBM_CLOCK_CNTL2_SP0, 0x02222220}, + {REG_A6XX_RBBM_CLOCK_DELAY_SP0, 0x00000080}, + {REG_A6XX_RBBM_CLOCK_HYST_SP0, 0x0000F3CF}, + {REG_A6XX_RBBM_CLOCK_CNTL_TP0, 0x22222222}, + {REG_A6XX_RBBM_CLOCK_CNTL2_TP0, 0x22222222}, + {REG_A6XX_RBBM_CLOCK_CNTL3_TP0, 0x22222222}, + {REG_A6XX_RBBM_CLOCK_CNTL4_TP0, 0x00022222}, + {REG_A6XX_RBBM_CLOCK_DELAY_TP0, 0x11111111}, + {REG_A6XX_RBBM_CLOCK_DELAY2_TP0, 0x11111111}, + {REG_A6XX_RBBM_CLOCK_DELAY3_TP0, 0x11111111}, + {REG_A6XX_RBBM_CLOCK_DELAY4_TP0, 0x00011111}, + {REG_A6XX_RBBM_CLOCK_HYST_TP0, 0x77777777}, + {REG_A6XX_RBBM_CLOCK_HYST2_TP0, 0x77777777}, + {REG_A6XX_RBBM_CLOCK_HYST3_TP0, 0x77777777}, + {REG_A6XX_RBBM_CLOCK_HYST4_TP0, 0x00077777}, + {REG_A6XX_RBBM_CLOCK_CNTL_RB0, 0x22222222}, + {REG_A6XX_RBBM_CLOCK_CNTL2_RB0, 0x01002222}, + {REG_A6XX_RBBM_CLOCK_CNTL_CCU0, 0x00002220}, + {REG_A6XX_RBBM_CLOCK_HYST_RB_CCU0, 0x00040F00}, + {REG_A6XX_RBBM_CLOCK_CNTL_RAC, 0x25222022}, + {REG_A6XX_RBBM_CLOCK_CNTL2_RAC, 0x00005555}, + {REG_A6XX_RBBM_CLOCK_DELAY_RAC, 0x00000011}, + {REG_A6XX_RBBM_CLOCK_HYST_RAC, 0x00445044}, + {REG_A6XX_RBBM_CLOCK_CNTL_TSE_RAS_RBBM, 0x04222222}, + {REG_A6XX_RBBM_CLOCK_MODE_VFD, 0x00002222}, + {REG_A6XX_RBBM_CLOCK_MODE_GPC, 0x00222222}, + {REG_A6XX_RBBM_CLOCK_DELAY_HLSQ_2, 0x00000002}, + {REG_A6XX_RBBM_CLOCK_MODE_HLSQ, 0x00002222}, + {REG_A6XX_RBBM_CLOCK_DELAY_TSE_RAS_RBBM, 0x00004000}, + {REG_A6XX_RBBM_CLOCK_DELAY_VFD, 0x00002222}, + {REG_A6XX_RBBM_CLOCK_DELAY_GPC, 0x00000200}, + {REG_A6XX_RBBM_CLOCK_DELAY_HLSQ, 0x00000000}, + {REG_A6XX_RBBM_CLOCK_HYST_TSE_RAS_RBBM, 0x00000000}, + {REG_A6XX_RBBM_CLOCK_HYST_VFD, 0x00000000}, + {REG_A6XX_RBBM_CLOCK_HYST_GPC, 0x04104004}, + {REG_A6XX_RBBM_CLOCK_HYST_HLSQ, 0x00000000}, + {REG_A6XX_RBBM_CLOCK_CNTL_TEX_FCHE, 0x00000222}, + {REG_A6XX_RBBM_CLOCK_DELAY_TEX_FCHE, 0x00000111}, + {REG_A6XX_RBBM_CLOCK_HYST_TEX_FCHE, 0x00000000}, + {REG_A6XX_RBBM_CLOCK_CNTL_UCHE, 0x22222222}, + {REG_A6XX_RBBM_CLOCK_HYST_UCHE, 0x00000004}, + {REG_A6XX_RBBM_CLOCK_DELAY_UCHE, 0x00000002}, + {REG_A6XX_RBBM_CLOCK_CNTL, 0x8AA8AA82}, + {REG_A6XX_RBBM_ISDB_CNT, 0x00000182}, + {REG_A6XX_RBBM_RAC_THRESHOLD_CNT, 0x00000000}, + {REG_A6XX_RBBM_SP_HYST_CNT, 0x00000000}, + {REG_A6XX_RBBM_CLOCK_CNTL_GMU_GX, 0x00000222}, + {REG_A6XX_RBBM_CLOCK_DELAY_GMU_GX, 0x00000111}, + {REG_A6XX_RBBM_CLOCK_HYST_GMU_GX, 0x00000555}, + {REG_A6XX_GPU_GMU_AO_GMU_CGC_MODE_CNTL, 0x20200}, + {REG_A6XX_GPU_GMU_AO_GMU_CGC_DELAY_CNTL, 0x10111}, + {REG_A6XX_GPU_GMU_AO_GMU_CGC_HYST_CNTL, 0x5555}, + {} +}; + static void a6xx_set_hwcg(struct msm_gpu *gpu, bool state) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); @@ -602,6 +709,8 @@ 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)) + clock_cntl_on = 0xaaa8aa82; else clock_cntl_on = 0x8aa8aa82; @@ -612,13 +721,15 @@ static void a6xx_set_hwcg(struct msm_gpu *gpu, bool state) return; /* Disable SP clock before programming HWCG registers */ - gmu_rmw(gmu, REG_A6XX_GPU_GMU_GX_SPTPRAC_CLOCK_CONTROL, 1, 0); + if (!adreno_is_a610(adreno_gpu)) + gmu_rmw(gmu, REG_A6XX_GPU_GMU_GX_SPTPRAC_CLOCK_CONTROL, 1, 0); for (i = 0; (reg = &adreno_gpu->info->hwcg[i], reg->offset); i++) gpu_write(gpu, reg->offset, state ? reg->value : 0); /* Enable SP clock */ - gmu_rmw(gmu, REG_A6XX_GPU_GMU_GX_SPTPRAC_CLOCK_CONTROL, 0, 1); + if (!adreno_is_a610(adreno_gpu)) + gmu_rmw(gmu, REG_A6XX_GPU_GMU_GX_SPTPRAC_CLOCK_CONTROL, 0, 1); gpu_write(gpu, REG_A6XX_RBBM_CLOCK_CNTL, state ? clock_cntl_on : 0); } @@ -747,6 +858,45 @@ static const u32 a660_protect[] = { A6XX_PROTECT_NORDWR(0x1f8c0, 0x0000), /* note: infinite range */ }; +/* These are for a690 */ +static const u32 a690_protect[] = { + A6XX_PROTECT_RDONLY(0x00000, 0x004ff), + A6XX_PROTECT_RDONLY(0x00501, 0x00001), + A6XX_PROTECT_RDONLY(0x0050b, 0x002f4), + A6XX_PROTECT_NORDWR(0x0050e, 0x00000), + A6XX_PROTECT_NORDWR(0x00510, 0x00000), + A6XX_PROTECT_NORDWR(0x00534, 0x00000), + A6XX_PROTECT_NORDWR(0x00800, 0x00082), + A6XX_PROTECT_NORDWR(0x008a0, 0x00008), + A6XX_PROTECT_NORDWR(0x008ab, 0x00024), + A6XX_PROTECT_RDONLY(0x008de, 0x000ae), + A6XX_PROTECT_NORDWR(0x00900, 0x0004d), + A6XX_PROTECT_NORDWR(0x0098d, 0x00272), + A6XX_PROTECT_NORDWR(0x00e00, 0x00001), + A6XX_PROTECT_NORDWR(0x00e03, 0x0000c), + A6XX_PROTECT_NORDWR(0x03c00, 0x000c3), + A6XX_PROTECT_RDONLY(0x03cc4, 0x01fff), + A6XX_PROTECT_NORDWR(0x08630, 0x001cf), + A6XX_PROTECT_NORDWR(0x08e00, 0x00000), + A6XX_PROTECT_NORDWR(0x08e08, 0x00007), + A6XX_PROTECT_NORDWR(0x08e50, 0x0001f), + A6XX_PROTECT_NORDWR(0x08e80, 0x0027f), + A6XX_PROTECT_NORDWR(0x09624, 0x001db), + A6XX_PROTECT_NORDWR(0x09e60, 0x00011), + A6XX_PROTECT_NORDWR(0x09e78, 0x00187), + A6XX_PROTECT_NORDWR(0x0a630, 0x001cf), + A6XX_PROTECT_NORDWR(0x0ae02, 0x00000), + A6XX_PROTECT_NORDWR(0x0ae50, 0x0012f), + A6XX_PROTECT_NORDWR(0x0b604, 0x00000), + A6XX_PROTECT_NORDWR(0x0b608, 0x00006), + A6XX_PROTECT_NORDWR(0x0be02, 0x00001), + A6XX_PROTECT_NORDWR(0x0be20, 0x0015f), + A6XX_PROTECT_NORDWR(0x0d000, 0x005ff), + A6XX_PROTECT_NORDWR(0x0f000, 0x00bff), + A6XX_PROTECT_RDONLY(0x0fc00, 0x01fff), + A6XX_PROTECT_NORDWR(0x11c00, 0x00000), /*note: infiite range */ +}; + static void a6xx_set_cp_protect(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); @@ -758,6 +908,11 @@ static void a6xx_set_cp_protect(struct msm_gpu *gpu) count = ARRAY_SIZE(a650_protect); count_max = 48; BUILD_BUG_ON(ARRAY_SIZE(a650_protect) > 48); + } else if (adreno_is_a690(adreno_gpu)) { + regs = a690_protect; + count = ARRAY_SIZE(a690_protect); + count_max = 48; + BUILD_BUG_ON(ARRAY_SIZE(a690_protect) > 48); } else if (adreno_is_a660_family(adreno_gpu)) { regs = a660_protect; count = ARRAY_SIZE(a660_protect); @@ -786,39 +941,77 @@ static void a6xx_set_cp_protect(struct msm_gpu *gpu) static void a6xx_set_ubwc_config(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); - u32 lower_bit = 2; - u32 amsbc = 0; + /* Unknown, introduced with A650 family, related to UBWC mode/ver 4 */ u32 rgb565_predicator = 0; + /* Unknown, introduced with A650 family */ u32 uavflagprd_inv = 0; + /* Whether the minimum access length is 64 bits */ + u32 min_acc_len = 0; + /* Entirely magic, per-GPU-gen value */ + u32 ubwc_mode = 0; + /* + * The Highest Bank Bit value represents the bit of the highest DDR bank. + * We then subtract 13 from it (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. This should ideally use DRAM + * type detection. + */ + u32 hbb_hi = 0; + u32 hbb_lo = 2; + /* Unknown, introduced with A640/680 */ + u32 amsbc = 0; + + if (adreno_is_a610(adreno_gpu)) { + /* HBB = 14 */ + hbb_lo = 1; + min_acc_len = 1; + ubwc_mode = 1; + } /* a618 is using the hw default values */ if (adreno_is_a618(adreno_gpu)) return; + if (adreno_is_a619_holi(adreno_gpu)) + hbb_lo = 0; + if (adreno_is_a640_family(adreno_gpu)) amsbc = 1; if (adreno_is_a650(adreno_gpu) || adreno_is_a660(adreno_gpu)) { /* TODO: get ddr type from bootloader and use 2 for LPDDR4 */ - lower_bit = 3; + hbb_lo = 3; + amsbc = 1; + rgb565_predicator = 1; + uavflagprd_inv = 2; + } + + if (adreno_is_a690(adreno_gpu)) { + hbb_lo = 2; amsbc = 1; rgb565_predicator = 1; uavflagprd_inv = 2; } if (adreno_is_7c3(adreno_gpu)) { - lower_bit = 1; + hbb_lo = 1; amsbc = 1; rgb565_predicator = 1; uavflagprd_inv = 2; } gpu_write(gpu, REG_A6XX_RB_NC_MODE_CNTL, - rgb565_predicator << 11 | amsbc << 4 | lower_bit << 1); - gpu_write(gpu, REG_A6XX_TPL1_NC_MODE_CNTL, lower_bit << 1); - gpu_write(gpu, REG_A6XX_SP_NC_MODE_CNTL, - uavflagprd_inv << 4 | lower_bit << 1); - gpu_write(gpu, REG_A6XX_UCHE_MODE_CNTL, lower_bit << 21); + rgb565_predicator << 11 | hbb_hi << 10 | amsbc << 4 | + min_acc_len << 3 | hbb_lo << 1 | ubwc_mode); + + gpu_write(gpu, REG_A6XX_TPL1_NC_MODE_CNTL, hbb_hi << 4 | + min_acc_len << 3 | hbb_lo << 1 | ubwc_mode); + + gpu_write(gpu, REG_A6XX_SP_NC_MODE_CNTL, hbb_hi << 10 | + uavflagprd_inv << 4 | min_acc_len << 3 | + hbb_lo << 1 | ubwc_mode); + + gpu_write(gpu, REG_A6XX_UCHE_MODE_CNTL, min_acc_len << 23 | hbb_lo << 21); } static int a6xx_cp_init(struct msm_gpu *gpu) @@ -997,17 +1190,32 @@ 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; int ret; - /* Make sure the GMU keeps the GPU on while we set it up */ - a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET); + if (!adreno_has_gmu_wrapper(adreno_gpu)) { + /* Make sure the GMU keeps the GPU on while we set it up */ + a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET); + } /* Clear GBIF halt in case GX domain was not collapsed */ - if (a6xx_has_gbif(adreno_gpu)) + if (adreno_is_a619_holi(adreno_gpu)) { + gpu_write(gpu, REG_A6XX_GBIF_HALT, 0); + gpu_write(gpu, REG_A6XX_RBBM_GPR0_CNTL, 0); + /* Let's make extra sure that the GPU can access the memory.. */ + mb(); + } else if (a6xx_has_gbif(adreno_gpu)) { + gpu_write(gpu, REG_A6XX_GBIF_HALT, 0); gpu_write(gpu, REG_A6XX_RBBM_GBIF_HALT, 0); + /* Let's make extra sure that the GPU can access the memory.. */ + mb(); + } gpu_write(gpu, REG_A6XX_RBBM_SECVID_TSB_CNTL, 0); + if (adreno_is_a619_holi(adreno_gpu)) + a6xx_sptprac_enable(gmu); + /* * 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 @@ -1034,13 +1242,13 @@ static int hw_init(struct msm_gpu *gpu) a6xx_set_hwcg(gpu, true); /* VBIF/GBIF start*/ - if (adreno_is_a640_family(adreno_gpu) || + if (adreno_is_a610(adreno_gpu) || + adreno_is_a640_family(adreno_gpu) || adreno_is_a650_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_GBIF_QSB_SIDE3, 0x00071620); gpu_write(gpu, REG_A6XX_RBBM_GBIF_CLIENT_QOS_CNTL, 0x3); } else { gpu_write(gpu, REG_A6XX_RBBM_VBIF_CLIENT_QOS_CNTL, 0x3); @@ -1068,28 +1276,40 @@ static int hw_init(struct msm_gpu *gpu) gpu_write(gpu, REG_A6XX_UCHE_FILTER_CNTL, 0x804); gpu_write(gpu, REG_A6XX_UCHE_CACHE_WAYS, 0x4); - if (adreno_is_a640_family(adreno_gpu) || - adreno_is_a650_family(adreno_gpu)) + if (adreno_is_a640_family(adreno_gpu) || adreno_is_a650_family(adreno_gpu)) { gpu_write(gpu, REG_A6XX_CP_ROQ_THRESHOLDS_2, 0x02000140); - else + gpu_write(gpu, REG_A6XX_CP_ROQ_THRESHOLDS_1, 0x8040362c); + } else if (adreno_is_a610(adreno_gpu)) { + gpu_write(gpu, REG_A6XX_CP_ROQ_THRESHOLDS_2, 0x00800060); + gpu_write(gpu, REG_A6XX_CP_ROQ_THRESHOLDS_1, 0x40201b16); + } else { gpu_write(gpu, REG_A6XX_CP_ROQ_THRESHOLDS_2, 0x010000c0); - gpu_write(gpu, REG_A6XX_CP_ROQ_THRESHOLDS_1, 0x8040362c); + gpu_write(gpu, REG_A6XX_CP_ROQ_THRESHOLDS_1, 0x8040362c); + } if (adreno_is_a660_family(adreno_gpu)) gpu_write(gpu, REG_A6XX_CP_LPAC_PROG_FIFO_SIZE, 0x00000020); /* Setting the mem pool size */ - gpu_write(gpu, REG_A6XX_CP_MEM_POOL_SIZE, 128); + if (adreno_is_a610(adreno_gpu)) { + gpu_write(gpu, REG_A6XX_CP_MEM_POOL_SIZE, 48); + gpu_write(gpu, REG_A6XX_CP_MEM_POOL_DBG_ADDR, 47); + } else + gpu_write(gpu, REG_A6XX_CP_MEM_POOL_SIZE, 128); /* Setting the primFifo thresholds default values, * and vccCacheSkipDis=1 bit (0x200) for A640 and newer */ - if (adreno_is_a650(adreno_gpu) || adreno_is_a660(adreno_gpu)) + if (adreno_is_a650(adreno_gpu) || adreno_is_a660(adreno_gpu) || adreno_is_a690(adreno_gpu)) gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00300200); else if (adreno_is_a640_family(adreno_gpu) || adreno_is_7c3(adreno_gpu)) gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00200200); else if (adreno_is_a650(adreno_gpu) || adreno_is_a660(adreno_gpu)) gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00300200); + else if (adreno_is_a619(adreno_gpu)) + gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00018000); + else if (adreno_is_a610(adreno_gpu)) + gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00080000); else gpu_write(gpu, REG_A6XX_PC_DBG_ECO_CNTL, 0x00180000); @@ -1105,8 +1325,12 @@ static int hw_init(struct msm_gpu *gpu) a6xx_set_ubwc_config(gpu); /* Enable fault detection */ - gpu_write(gpu, REG_A6XX_RBBM_INTERFACE_HANG_INT_CNTL, - (1 << 30) | 0x1fffff); + if (adreno_is_a619(adreno_gpu)) + gpu_write(gpu, REG_A6XX_RBBM_INTERFACE_HANG_INT_CNTL, (1 << 30) | 0x3fffff); + else if (adreno_is_a610(adreno_gpu)) + gpu_write(gpu, REG_A6XX_RBBM_INTERFACE_HANG_INT_CNTL, (1 << 30) | 0x3ffff); + else + gpu_write(gpu, REG_A6XX_RBBM_INTERFACE_HANG_INT_CNTL, (1 << 30) | 0x1fffff); gpu_write(gpu, REG_A6XX_UCHE_CLIENT_PF, 1); @@ -1123,6 +1347,13 @@ static int hw_init(struct msm_gpu *gpu) 0x3f0243f0); } + /* 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_A6XX_GMU_CX_GMU_POWER_COUNTER_SELECT_0, 0xff, BIT(5)); + gmu_write(gmu, REG_A6XX_GMU_CX_GMU_POWER_COUNTER_ENABLE, 1); + /* Protect registers from the CP */ a6xx_set_cp_protect(gpu); @@ -1212,6 +1443,8 @@ static int hw_init(struct msm_gpu *gpu) } out: + if (adreno_has_gmu_wrapper(adreno_gpu)) + return ret; /* * Tell the GMU that we are done touching the GPU and it can start power * management @@ -1246,9 +1479,6 @@ static void a6xx_dump(struct msm_gpu *gpu) adreno_dump(gpu); } -#define VBIF_RESET_ACK_TIMEOUT 100 -#define VBIF_RESET_ACK_MASK 0x00f0 - static void a6xx_recover(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); @@ -1274,12 +1504,6 @@ static void a6xx_recover(struct msm_gpu *gpu) /* Halt SQE first */ gpu_write(gpu, REG_A6XX_CP_SQE_CNTL, 3); - /* - * 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); - pm_runtime_dont_use_autosuspend(&gpu->pdev->dev); /* active_submit won't change until we make a submission */ @@ -1292,6 +1516,15 @@ static void a6xx_recover(struct msm_gpu *gpu) */ gpu->active_submits = 0; + if (adreno_has_gmu_wrapper(adreno_gpu)) { + /* Drain the outstanding traffic on memory buses */ + a6xx_bus_clear_pending_transactions(adreno_gpu, true); + + /* Reset the GPU to a clean state */ + a6xx_gpu_sw_reset(gpu, true); + a6xx_gpu_sw_reset(gpu, false); + } + reinit_completion(&gmu->pd_gate); dev_pm_genpd_add_notifier(gmu->cxpd, &gmu->pd_nb); dev_pm_genpd_synced_poweroff(gmu->cxpd); @@ -1442,7 +1675,8 @@ static void a6xx_fault_detect_irq(struct msm_gpu *gpu) * Force the GPU to stay on until after we finish * collecting information */ - gmu_write(&a6xx_gpu->gmu, REG_A6XX_GMU_GMU_PWR_COL_KEEPALIVE, 1); + 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 rb %4.4x/%4.4x ib1 %16.16llX/%4.4x ib2 %16.16llX/%4.4x\n", @@ -1573,6 +1807,10 @@ static void a6xx_llc_activate(struct a6xx_gpu *a6xx_gpu) static void a6xx_llc_slices_destroy(struct a6xx_gpu *a6xx_gpu) { + /* No LLCC on non-RPMh (and by extension, non-GMU) SoCs */ + if (adreno_has_gmu_wrapper(&a6xx_gpu->base)) + return; + llcc_slice_putd(a6xx_gpu->llc_slice); llcc_slice_putd(a6xx_gpu->htw_llc_slice); } @@ -1582,6 +1820,10 @@ static void a6xx_llc_slices_init(struct platform_device *pdev, { struct device_node *phandle; + /* No LLCC on non-RPMh (and by extension, non-GMU) SoCs */ + if (adreno_has_gmu_wrapper(&a6xx_gpu->base)) + return; + /* * There is a different programming path for targets with an mmu500 * attached, so detect if that is the case @@ -1603,7 +1845,66 @@ static void a6xx_llc_slices_init(struct platform_device *pdev, a6xx_gpu->llc_mmio = ERR_PTR(-EINVAL); } -static int a6xx_pm_resume(struct msm_gpu *gpu) +#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 a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu, bool gx_off) +{ + struct msm_gpu *gpu = &adreno_gpu->base; + + if (adreno_is_a619_holi(adreno_gpu)) { + gpu_write(gpu, REG_A6XX_RBBM_GPR0_CNTL, GPR0_GBIF_HALT_REQUEST); + spin_until((gpu_read(gpu, REG_A6XX_RBBM_VBIF_GX_RESET_STATUS) & + (VBIF_RESET_ACK_MASK)) == VBIF_RESET_ACK_MASK); + } else if (!a6xx_has_gbif(adreno_gpu)) { + gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, VBIF_XIN_HALT_CTRL0_MASK); + spin_until((gpu_read(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL1) & + (VBIF_XIN_HALT_CTRL0_MASK)) == VBIF_XIN_HALT_CTRL0_MASK); + gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0); + + return; + } + + if (gx_off) { + /* Halt the gx side of GBIF */ + gpu_write(gpu, REG_A6XX_RBBM_GBIF_HALT, 1); + spin_until(gpu_read(gpu, REG_A6XX_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); +} + +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))) + return; + + gpu_write(gpu, REG_A6XX_RBBM_SW_RESET_CMD, assert); + /* Perform a bogus read and add a brief delay to ensure ordering. */ + gpu_read(gpu, REG_A6XX_RBBM_SW_RESET_CMD); + udelay(1); + + /* The reset line needs to be asserted for at least 100 us */ + if (assert) + udelay(100); +} + +static int a6xx_gmu_pm_resume(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); @@ -1623,10 +1924,61 @@ static int a6xx_pm_resume(struct msm_gpu *gpu) a6xx_llc_activate(a6xx_gpu); - return 0; + return ret; } -static int a6xx_pm_suspend(struct msm_gpu *gpu) +static int a6xx_pm_resume(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 long freq = gpu->fast_rate; + struct dev_pm_opp *opp; + int ret; + + gpu->needs_hw_init = true; + + trace_msm_gpu_resume(0); + + mutex_lock(&a6xx_gpu->gmu.lock); + + opp = dev_pm_opp_find_freq_ceil(&gpu->pdev->dev, &freq); + if (IS_ERR(opp)) { + ret = PTR_ERR(opp); + goto err_set_opp; + } + dev_pm_opp_put(opp); + + /* Set the core clock and bus bw, having VDD scaling in mind */ + dev_pm_opp_set_opp(&gpu->pdev->dev, opp); + + pm_runtime_resume_and_get(gmu->dev); + pm_runtime_resume_and_get(gmu->gxpd); + + ret = clk_bulk_prepare_enable(gpu->nr_clocks, gpu->grp_clks); + if (ret) + goto err_bulk_clk; + + if (adreno_is_a619_holi(adreno_gpu)) + a6xx_sptprac_enable(gmu); + + /* If anything goes south, tear the GPU down piece by piece.. */ + if (ret) { +err_bulk_clk: + pm_runtime_put(gmu->gxpd); + pm_runtime_put(gmu->dev); + dev_pm_opp_set_opp(&gpu->pdev->dev, NULL); + } +err_set_opp: + mutex_unlock(&a6xx_gpu->gmu.lock); + + if (!ret) + msm_devfreq_resume(gpu); + + return ret; +} + +static int a6xx_gmu_pm_suspend(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); @@ -1653,7 +2005,43 @@ static int a6xx_pm_suspend(struct msm_gpu *gpu) return 0; } -static int a6xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value) +static int a6xx_pm_suspend(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; + + trace_msm_gpu_suspend(0); + + 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); + + if (adreno_is_a619_holi(adreno_gpu)) + a6xx_sptprac_disable(gmu); + + clk_bulk_disable_unprepare(gpu->nr_clocks, gpu->grp_clks); + + pm_runtime_put_sync(gmu->gxpd); + dev_pm_opp_set_opp(&gpu->pdev->dev, NULL); + pm_runtime_put_sync(gmu->dev); + + mutex_unlock(&a6xx_gpu->gmu.lock); + + if (a6xx_gpu->shadow_bo) + for (i = 0; i < gpu->nr_rings; i++) + a6xx_gpu->shadow[i] = 0; + + gpu->suspend_count++; + + return 0; +} + +static int a6xx_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); @@ -1672,6 +2060,12 @@ static int a6xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value) return 0; } +static int a6xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value) +{ + *value = gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER); + return 0; +} + static struct msm_ringbuffer *a6xx_active_ring(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); @@ -1744,7 +2138,8 @@ a6xx_create_address_space(struct msm_gpu *gpu, struct platform_device *pdev) * This allows GPU to set the bus attributes required to use system * cache on behalf of the iommu page table walker. */ - if (!IS_ERR_OR_NULL(a6xx_gpu->htw_llc_slice)) + if (!IS_ERR_OR_NULL(a6xx_gpu->htw_llc_slice) && + !device_iommu_capable(&pdev->dev, IOMMU_CAP_CACHE_COHERENCY)) quirks |= IO_PGTABLE_QUIRK_ARM_OUTER_WBWA; return adreno_iommu_create_address_space(gpu, pdev, quirks); @@ -1809,6 +2204,30 @@ static bool a6xx_progress(struct msm_gpu *gpu, struct msm_ringbuffer *ring) return progress; } +static u32 a610_get_speed_bin(u32 fuse) +{ + /* + * There are (at least) three SoCs implementing A610: SM6125 (trinket), + * SM6115 (bengal) and SM6225 (khaje). Trinket does not have speedbinning, + * as only a single SKU exists and we don't support khaje upstream yet. + * Hence, this matching table is only valid for bengal and can be easily + * expanded if need be. + */ + + if (fuse == 0) + return 0; + else if (fuse == 206) + return 1; + else if (fuse == 200) + return 2; + else if (fuse == 157) + return 3; + else if (fuse == 127) + return 4; + + return UINT_MAX; +} + static u32 a618_get_speed_bin(u32 fuse) { if (fuse == 0) @@ -1821,6 +2240,34 @@ static u32 a618_get_speed_bin(u32 fuse) return UINT_MAX; } +static u32 a619_holi_get_speed_bin(u32 fuse) +{ + /* + * There are (at least) two SoCs implementing A619_holi: SM4350 (holi) + * and SM6375 (blair). Limit the fuse matching to the corresponding + * SoC to prevent bogus frequency setting (as improbable as it may be, + * given unexpected fuse values are.. unexpected! But still possible.) + */ + + if (fuse == 0) + return 0; + + if (of_machine_is_compatible("qcom,sm4350")) { + if (fuse == 138) + return 1; + else if (fuse == 92) + return 2; + } else if (of_machine_is_compatible("qcom,sm6375")) { + if (fuse == 190) + return 1; + else if (fuse == 177) + return 2; + } else + pr_warn("Unknown SoC implementing A619_holi!\n"); + + return UINT_MAX; +} + static u32 a619_get_speed_bin(u32 fuse) { if (fuse == 0) @@ -1874,23 +2321,29 @@ static u32 adreno_7c3_get_speed_bin(u32 fuse) return UINT_MAX; } -static u32 fuse_to_supp_hw(struct device *dev, struct adreno_rev rev, u32 fuse) +static u32 fuse_to_supp_hw(struct device *dev, struct adreno_gpu *adreno_gpu, u32 fuse) { u32 val = UINT_MAX; - if (adreno_cmp_rev(ADRENO_REV(6, 1, 8, ANY_ID), rev)) + if (adreno_is_a610(adreno_gpu)) + val = a610_get_speed_bin(fuse); + + if (adreno_is_a618(adreno_gpu)) val = a618_get_speed_bin(fuse); - if (adreno_cmp_rev(ADRENO_REV(6, 1, 9, ANY_ID), rev)) + else if (adreno_is_a619_holi(adreno_gpu)) + val = a619_holi_get_speed_bin(fuse); + + else if (adreno_is_a619(adreno_gpu)) val = a619_get_speed_bin(fuse); - if (adreno_cmp_rev(ADRENO_REV(6, 3, 5, ANY_ID), rev)) + else if (adreno_is_7c3(adreno_gpu)) val = adreno_7c3_get_speed_bin(fuse); - if (adreno_cmp_rev(ADRENO_REV(6, 4, 0, ANY_ID), rev)) + else if (adreno_is_a640(adreno_gpu)) val = a640_get_speed_bin(fuse); - if (adreno_cmp_rev(ADRENO_REV(6, 5, 0, ANY_ID), rev)) + else if (adreno_is_a650(adreno_gpu)) val = a650_get_speed_bin(fuse); if (val == UINT_MAX) { @@ -1903,7 +2356,7 @@ static u32 fuse_to_supp_hw(struct device *dev, struct adreno_rev rev, u32 fuse) return (1 << val); } -static int a6xx_set_supported_hw(struct device *dev, struct adreno_rev rev) +static int a6xx_set_supported_hw(struct device *dev, struct adreno_gpu *adreno_gpu) { u32 supp_hw; u32 speedbin; @@ -1922,7 +2375,7 @@ static int a6xx_set_supported_hw(struct device *dev, struct adreno_rev rev) return ret; } - supp_hw = fuse_to_supp_hw(dev, rev, speedbin); + supp_hw = fuse_to_supp_hw(dev, adreno_gpu, speedbin); ret = devm_pm_opp_set_supported_hw(dev, &supp_hw, 1); if (ret) @@ -1937,8 +2390,8 @@ static const struct adreno_gpu_funcs funcs = { .set_param = adreno_set_param, .hw_init = a6xx_hw_init, .ucode_load = a6xx_ucode_load, - .pm_suspend = a6xx_pm_suspend, - .pm_resume = a6xx_pm_resume, + .pm_suspend = a6xx_gmu_pm_suspend, + .pm_resume = a6xx_gmu_pm_resume, .recover = a6xx_recover, .submit = a6xx_submit, .active_ring = a6xx_active_ring, @@ -1959,6 +2412,35 @@ static const struct adreno_gpu_funcs funcs = { .get_rptr = a6xx_get_rptr, .progress = a6xx_progress, }, + .get_timestamp = a6xx_gmu_get_timestamp, +}; + +static const struct adreno_gpu_funcs funcs_gmuwrapper = { + .base = { + .get_param = adreno_get_param, + .set_param = adreno_set_param, + .hw_init = a6xx_hw_init, + .ucode_load = a6xx_ucode_load, + .pm_suspend = a6xx_pm_suspend, + .pm_resume = a6xx_pm_resume, + .recover = a6xx_recover, + .submit = a6xx_submit, + .active_ring = a6xx_active_ring, + .irq = a6xx_irq, + .destroy = a6xx_destroy, +#if defined(CONFIG_DRM_MSM_GPU_STATE) + .show = a6xx_show, +#endif + .gpu_busy = a6xx_gpu_busy, +#if defined(CONFIG_DRM_MSM_GPU_STATE) + .gpu_state_get = a6xx_gpu_state_get, + .gpu_state_put = a6xx_gpu_state_put, +#endif + .create_address_space = a6xx_create_address_space, + .create_private_address_space = a6xx_create_private_address_space, + .get_rptr = a6xx_get_rptr, + .progress = a6xx_progress, + }, .get_timestamp = a6xx_get_timestamp, }; @@ -1985,26 +2467,45 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev) 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"); + /* * We need to know the platform type before calling into adreno_gpu_init * so that the hw_apriv flag can be correctly set. Snoop into the info * and grab the revision number */ info = adreno_info(config->rev); - - if (info && (info->revn == 650 || info->revn == 660 || - adreno_cmp_rev(ADRENO_REV(6, 3, 5, ANY_ID), info->rev))) + if (!info) + return ERR_PTR(-EINVAL); + + /* Assign these early so that we can use the is_aXYZ helpers */ + /* Numeric revision IDs (e.g. 630) */ + adreno_gpu->revn = info->revn; + /* New-style ADRENO_REV()-only */ + adreno_gpu->rev = info->rev; + /* Quirk data */ + adreno_gpu->info = info; + + if (adreno_is_a650(adreno_gpu) || adreno_is_a660_family(adreno_gpu)) adreno_gpu->base.hw_apriv = true; a6xx_llc_slices_init(pdev, a6xx_gpu); - ret = a6xx_set_supported_hw(&pdev->dev, config->rev); + ret = a6xx_set_supported_hw(&pdev->dev, adreno_gpu); if (ret) { a6xx_destroy(&(a6xx_gpu->base.base)); return ERR_PTR(ret); } - ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1); + 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); @@ -2017,13 +2518,10 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev) if (adreno_is_a618(adreno_gpu) || adreno_is_7c3(adreno_gpu)) priv->gpu_clamp_to_idle = true; - /* 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); - - ret = a6xx_gmu_init(a6xx_gpu, node); + 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)); |